diff options
| author | Jes Sorensen <Jes.Sorensen@redhat.com> | 2016-01-06 13:50:08 -0500 |
|---|---|---|
| committer | Jes Sorensen <Jes.Sorensen@redhat.com> | 2016-01-06 13:50:08 -0500 |
| commit | 08c4c3019480c28d5b1c50dbcf9d30df1635fe85 (patch) | |
| tree | ac97cad1a2cbff4db44f9e38f41a1a984fcdf5f8 | |
| parent | ce09c8efd913feb811ccc0afab0d83fc6d272be9 (diff) | |
| parent | 00ce3a15d811978fcb204a1a3f5f8c059096fa5e (diff) | |
| download | linux-rtl8723au-mac80211.tar.gz | |
Merge branch 'wireless-drivers-next' into rtl8723au-mac80211rtl8723au-mac80211
1251 files changed, 41578 insertions, 11804 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-net-mesh b/Documentation/ABI/testing/sysfs-class-net-mesh index c464062966317..c2b956d44a952 100644 --- a/Documentation/ABI/testing/sysfs-class-net-mesh +++ b/Documentation/ABI/testing/sysfs-class-net-mesh @@ -8,7 +8,7 @@ Description: What: /sys/class/net/<mesh_iface>/mesh/<vlan_subdir>/ap_isolation Date: May 2011 -Contact: Antonio Quartulli <antonio@meshcoding.com> +Contact: Antonio Quartulli <a@unstable.cc> Description: Indicates whether the data traffic going from a wireless client to another wireless client will be @@ -70,7 +70,7 @@ Description: What: /sys/class/net/<mesh_iface>/mesh/isolation_mark Date: Nov 2013 -Contact: Antonio Quartulli <antonio@meshcoding.com> +Contact: Antonio Quartulli <a@unstable.cc> Description: Defines the isolation mark (and its bitmask) which is used to classify clients as "isolated" by the diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt index d3d0a4fb1c733..079b42a81d7cf 100644 --- a/Documentation/devicetree/bindings/dma/ti-edma.txt +++ b/Documentation/devicetree/bindings/dma/ti-edma.txt @@ -22,8 +22,7 @@ Required properties: Optional properties: - ti,hwmods: Name of the hwmods associated to the eDMA CC - ti,edma-memcpy-channels: List of channels allocated to be used for memcpy, iow - these channels will be SW triggered channels. The list must - contain 16 bits numbers, see example. + these channels will be SW triggered channels. See example. - ti,edma-reserved-slot-ranges: PaRAM slot ranges which should not be used by the driver, they are allocated to be used by for example the DSP. See example. @@ -56,10 +55,9 @@ edma: edma@49000000 { ti,tptcs = <&edma_tptc0 7>, <&edma_tptc1 7>, <&edma_tptc2 0>; /* Channel 20 and 21 is allocated for memcpy */ - ti,edma-memcpy-channels = /bits/ 16 <20 21>; - /* The following PaRAM slots are reserved: 35-45 and 100-110 */ - ti,edma-reserved-slot-ranges = /bits/ 16 <35 10>, - /bits/ 16 <100 10>; + ti,edma-memcpy-channels = <20 21>; + /* The following PaRAM slots are reserved: 35-44 and 100-109 */ + ti,edma-reserved-slot-ranges = <35 10>, <100 10>; }; edma_tptc0: tptc@49800000 { diff --git a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt index f2455c50533d6..120bc4971cf3e 100644 --- a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt +++ b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt @@ -11,6 +11,10 @@ Required properties: 0 = active high 1 = active low +Optional properties: +- little-endian : GPIO registers are used as little endian. If not + present registers are used as big endian by default. + Example: gpio0: gpio@1100 { diff --git a/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt b/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt index b9c32f6fd687b..4357e498ef042 100644 --- a/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt +++ b/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt @@ -12,7 +12,7 @@ Each key is represented as a sub-node of "allwinner,sun4i-a10-lradc-keys": Required subnode-properties: - label: Descriptive name of the key. - linux,code: Keycode to emit. - - channel: Channel this key is attached to, mut be 0 or 1. + - channel: Channel this key is attached to, must be 0 or 1. - voltage: Voltage in µV at lradc input when this key is pressed. Example: diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt index f1e2a02381a49..1c63e40659fca 100644 --- a/Documentation/devicetree/bindings/mtd/partition.txt +++ b/Documentation/devicetree/bindings/mtd/partition.txt @@ -6,7 +6,9 @@ used for what purposes, but which don't use an on-flash partition table such as RedBoot. The partition table should be a subnode of the mtd node and should be named -'partitions'. Partitions are defined in subnodes of the partitions node. +'partitions'. This node should have the following property: +- compatible : (required) must be "fixed-partitions" +Partitions are then defined in subnodes of the partitions node. For backwards compatibility partitions as direct subnodes of the mtd device are supported. This use is discouraged. @@ -36,6 +38,7 @@ Examples: flash@0 { partitions { + compatible = "fixed-partitions"; #address-cells = <1>; #size-cells = <1>; @@ -53,6 +56,7 @@ flash@0 { flash@1 { partitions { + compatible = "fixed-partitions"; #address-cells = <1>; #size-cells = <2>; @@ -66,6 +70,7 @@ flash@1 { flash@2 { partitions { + compatible = "fixed-partitions"; #address-cells = <2>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 9853f8e709661..28a4781ab6d7b 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -40,18 +40,18 @@ Optional properties: Slave Properties: Required properties: -- phy_id : Specifies slave phy id - phy-mode : See ethernet.txt file in the same directory Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports - mac-address : See ethernet.txt file in the same directory +- phy_id : Specifies slave phy id - phy-handle : See ethernet.txt file in the same directory Slave sub-nodes: - fixed-link : See fixed-link.txt file in the same directory - Either the properties phy_id and phy-mode, - or the sub-node fixed-link can be specified + Either the property phy_id, or the sub-node + fixed-link can be specified Note: "ti,hwmods" field is used to fetch the base address and irq resources from TI, omap hwmod data base during device registration. diff --git a/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt b/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt new file mode 100644 index 0000000000000..dea5124cdc52d --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt @@ -0,0 +1,18 @@ +* ADF7242 IEEE 802.15.4 * + +Required properties: + - compatible: should be "adi,adf7242" + - spi-max-frequency: maximal bus speed (12.5 MHz) + - reg: the chipselect index + - interrupts: the interrupt generated by the device via pin IRQ1. + IRQ_TYPE_LEVEL_HIGH (4) or IRQ_TYPE_EDGE_FALLING (1) + +Example: + + adf7242@0 { + compatible = "adi,adf7242"; + spi-max-frequency = <10000000>; + reg = <0>; + interrupts = <98 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&gpio3>; + }; diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index b5d79761ac970..38c8e845ac5dc 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -19,6 +19,9 @@ Required properties: Optional elements: 'tx_clk' - clocks: Phandles to input clocks. +Optional properties for PHY child node: +- reset-gpios : Should specify the gpio for phy reset + Examples: macb0: ethernet@fffc4000 { @@ -29,4 +32,8 @@ Examples: local-mac-address = [3a 0e 03 04 05 06]; clock-names = "pclk", "hclk", "tx_clk"; clocks = <&clkc 30>, <&clkc 30>, <&clkc 13>; + ethernet-phy@1 { + reg = <0x1>; + reset-gpios = <&pioE 6 1>; + }; }; diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt index 692076fda0e58..f9c32adab5c64 100644 --- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -1,8 +1,9 @@ Micrel KSZ9021/KSZ9031 Gigabit Ethernet PHY -Some boards require special tuning values, particularly when it comes to -clock delays. You can specify clock delay values by adding -micrel-specific properties to an Ethernet OF device node. +Some boards require special tuning values, particularly when it comes +to clock delays. You can specify clock delay values in the PHY OF +device node. Deprecated, but still supported, these properties can +also be added to an Ethernet OF device node. Note that these settings are applied after any phy-specific fixup from phy_fixup_list (see phy_init_hw() from drivers/net/phy/phy_device.c), @@ -57,16 +58,6 @@ KSZ9031: Examples: - /* Attach to an Ethernet device with autodetected PHY */ - &enet { - rxc-skew-ps = <3000>; - rxdv-skew-ps = <0>; - txc-skew-ps = <3000>; - txen-skew-ps = <0>; - status = "okay"; - }; - - /* Attach to an explicitly-specified PHY */ mdio { phy0: ethernet-phy@0 { rxc-skew-ps = <3000>; diff --git a/Documentation/devicetree/bindings/net/nfc/st95hf.txt b/Documentation/devicetree/bindings/net/nfc/st95hf.txt new file mode 100644 index 0000000000000..ea3178bc9ddd5 --- /dev/null +++ b/Documentation/devicetree/bindings/net/nfc/st95hf.txt @@ -0,0 +1,50 @@ +* STMicroelectronics : NFC Transceiver ST95HF + +ST NFC Transceiver is required to attach with SPI bus. +ST95HF node should be defined in DT as SPI slave device of SPI +master with which ST95HF transceiver is physically connected. +The properties defined below are required to be the part of DT +to include ST95HF transceiver into the platform. + +Required properties: +=================== +- reg: Address of SPI slave "ST95HF transceiver" on SPI master bus. + +- compatible: should be "st,st95hf" for ST95HF NFC transceiver + +- spi-max-frequency: Max. operating SPI frequency for ST95HF + transceiver. + +- enable-gpio: GPIO line to enable ST95HF transceiver. + +- interrupt-parent : Standard way to specify the controller to which + ST95HF transceiver's interrupt is routed. + +- interrupts : Standard way to define ST95HF transceiver's out + interrupt. + +Optional property: +================= +- st95hfvin-supply : This is an optional property. It contains a + phandle to ST95HF transceiver's regulator supply node in DT. + +Example: +======= +spi@9840000 { + reg = <0x9840000 0x110>; + #address-cells = <1>; + #size-cells = <0>; + cs-gpios = <&pio0 4>; + status = "okay"; + + st95hf@0{ + reg = <0>; + compatible = "st,st95hf"; + status = "okay"; + spi-max-frequency = <1000000>; + enable-gpio = <&pio4 0>; + interrupt-parent = <&pio0>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + }; + +}; diff --git a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt index 3a9d679516065..72d82d684342b 100644 --- a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt +++ b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt @@ -11,6 +11,8 @@ Required properties: designware version numbers documented in stmmac.txt - altr,sysmgr-syscon : Should be the phandle to the system manager node that encompasses the glue register, the register offset, and the register shift. + - altr,f2h_ptp_ref_clk use f2h_ptp_ref_clk instead of default eosc1 clock + for ptp ref clk. This affects all emacs as the clock is common. Optional properties: altr,emac-splitter: Should be the phandle to the emac splitter soft IP node if diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index f34fc3c81a755..e862a922bd3f9 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -35,18 +35,18 @@ Optional properties: - reset-names: Should contain the reset signal name "stmmaceth", if a reset phandle is given - max-frame-size: See ethernet.txt file in the same directory -- clocks: If present, the first clock should be the GMAC main clock and - the second clock should be peripheral's register interface clock. Further - clocks may be specified in derived bindings. -- clock-names: One name for each entry in the clocks property, the - first one should be "stmmaceth" and the second one should be "pclk". -- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is - available this clock is used for programming the Timestamp Addend Register. - If not passed then the system clock will be used and this is fine on some - platforms. +- clocks: If present, the first clock should be the GMAC main clock + The optional second clock should be peripheral's register interface clock. + The third optional clock should be the ptp reference clock. + Further clocks may be specified in derived bindings. +- clock-names: One name for each entry in the clocks property. + The first one should be "stmmaceth". + The optional second one should be "pclk". + The optional third one should be "clk_ptp_ref". - snps,burst_len: The AXI burst lenth value of the AXI BUS MODE register. - tx-fifo-depth: See ethernet.txt file in the same directory - rx-fifo-depth: See ethernet.txt file in the same directory +- mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus. Examples: @@ -65,4 +65,11 @@ Examples: tx-fifo-depth = <16384>; clocks = <&clock>; clock-names = "stmmaceth"; + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + phy1: ethernet-phy@0 { + }; + }; }; diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt index f862cf3aff349..42ddbd4b52a9d 100644 --- a/Documentation/networking/e100.txt +++ b/Documentation/networking/e100.txt @@ -181,17 +181,3 @@ For general information, go to the Intel support website at: If an issue is identified with the released source code on the supported kernel with a supported adapter, email the specific information related to the issue to e1000-devel@lists.sourceforge.net. - - -License -======= - -This software program is released under the terms of a license agreement -between you ('Licensee') and Intel. Do not use or load this software or any -associated materials (collectively, the 'Software') until you have carefully -read the full terms and conditions of the file COPYING located in this software -package. By loading or using the Software, you agree to the terms of this -Agreement. If you do not agree with the terms of this Agreement, do not install -or use the Software. - -* Other names and brands may be claimed as the property of others. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 2ea4c45cf1c87..ceb44a095a27b 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -335,6 +335,14 @@ tcp_keepalive_intvl - INTEGER after probes started. Default value: 75sec i.e. connection will be aborted after ~11 minutes of retries. +tcp_l3mdev_accept - BOOLEAN + Enables child sockets to inherit the L3 master device index. + Enabling this option allows a "global" listen socket to work + across L3 master domains (e.g., VRFs) with connected sockets + derived from the listen socket to be bound to the L3 domain in + which the packets originated. Only valid when the kernel was + compiled with CONFIG_NET_L3_MASTER_DEV. + tcp_low_latency - BOOLEAN If set, the TCP stack makes decisions that prefer lower latency as opposed to higher throughput. By default, this @@ -1723,6 +1731,25 @@ addip_enable - BOOLEAN Default: 0 +pf_enable - INTEGER + Enable or disable pf (pf is short for potentially failed) state. A value + of pf_retrans > path_max_retrans also disables pf state. That is, one of + both pf_enable and pf_retrans > path_max_retrans can disable pf state. + Since pf_retrans and path_max_retrans can be changed by userspace + application, sometimes user expects to disable pf state by the value of + pf_retrans > path_max_retrans, but occasionally the value of pf_retrans + or path_max_retrans is changed by the user application, this pf state is + enabled. As such, it is necessary to add this to dynamically enable + and disable pf state. See: + https://datatracker.ietf.org/doc/draft-ietf-tsvwg-sctp-failover for + details. + + 1: Enable pf. + + 0: Disable pf. + + Default: 1 + addip_noauth_enable - BOOLEAN Dynamic Address Reconfiguration (ADD-IP) requires the use of authentication to protect the operations of adding or removing new @@ -1799,7 +1826,9 @@ pf_retrans - INTEGER having to reduce path_max_retrans to a very low value. See: http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt for details. Note also that a value of pf_retrans > path_max_retrans - disables this feature + disables this feature. Since both pf_retrans and path_max_retrans can + be changed by userspace application, a variable pf_enable is used to + disable pf state. Default: 0 diff --git a/MAINTAINERS b/MAINTAINERS index 8eba565b2b464..74b84d44ee98b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -318,7 +318,7 @@ M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org W: https://01.org/linux-acpi S: Supported -F: drivers/acpi/video.c +F: drivers/acpi/acpi_video.c ACPI WMI DRIVER L: platform-driver-x86@vger.kernel.org @@ -371,6 +371,15 @@ ADDRESS SPACE LAYOUT RANDOMIZATION (ASLR) M: Jiri Kosina <jikos@kernel.org> S: Maintained +ADF7242 IEEE 802.15.4 RADIO DRIVER +M: Michael Hennerich <michael.hennerich@analog.com> +W: https://wiki.analog.com/ADF7242 +W: http://ez.analog.com/community/linux-device-drivers +L: linux-wpan@vger.kernel.org +S: Supported +F: drivers/net/ieee802154/adf7242.c +F: Documentation/devicetree/bindings/net/ieee802154/adf7242.txt + ADM1025 HARDWARE MONITOR DRIVER M: Jean Delvare <jdelvare@suse.com> L: lm-sensors@lm-sensors.org @@ -2102,7 +2111,7 @@ F: include/linux/backlight.h BATMAN ADVANCED M: Marek Lindner <mareklindner@neomailbox.ch> M: Simon Wunderlich <sw@simonwunderlich.de> -M: Antonio Quartulli <antonio@meshcoding.com> +M: Antonio Quartulli <a@unstable.cc> L: b.a.t.m.a.n@lists.open-mesh.org W: http://www.open-mesh.org/ S: Maintained @@ -2975,6 +2984,7 @@ F: kernel/cpuset.c CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG) M: Johannes Weiner <hannes@cmpxchg.org> M: Michal Hocko <mhocko@kernel.org> +M: Vladimir Davydov <vdavydov@virtuozzo.com> L: cgroups@vger.kernel.org L: linux-mm@kvack.org S: Maintained @@ -5282,6 +5292,13 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmveth.* +IBM Power SRIOV Virtual NIC Device Driver +M: Thomas Falcon <tlfalcon@linux.vnet.ibm.com> +M: John Allen <jallen@linux.vnet.ibm.com> +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/ibm/ibmvnic.* + IBM Power Virtual SCSI Device Drivers M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> L: linux-scsi@vger.kernel.org @@ -5577,7 +5594,7 @@ R: Jesse Brandeburg <jesse.brandeburg@intel.com> R: Shannon Nelson <shannon.nelson@intel.com> R: Carolyn Wyborny <carolyn.wyborny@intel.com> R: Don Skidmore <donald.c.skidmore@intel.com> -R: Matthew Vick <matthew.vick@intel.com> +R: Bruce Allan <bruce.w.allan@intel.com> R: John Ronciak <john.ronciak@intel.com> R: Mitch Williams <mitch.a.williams@intel.com> L: intel-wired-lan@lists.osuosl.org @@ -7506,7 +7523,12 @@ F: net/nfc/ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: drivers/nfc/ +F: include/linux/platform_data/microread.h +F: include/linux/platform_data/nfcmrvl.h +F: include/linux/platform_data/nxp-nci.h F: include/linux/platform_data/pn544.h +F: include/linux/platform_data/st21nfca.h +F: include/linux/platform_data/st-nci.h F: Documentation/devicetree/bindings/net/nfc/ NFS, SUNRPC, AND LOCKD CLIENTS @@ -8293,7 +8315,7 @@ F: include/linux/delayacct.h F: kernel/delayacct.c PERFORMANCE EVENTS SUBSYSTEM -M: Peter Zijlstra <a.p.zijlstra@chello.nl> +M: Peter Zijlstra <peterz@infradead.org> M: Ingo Molnar <mingo@redhat.com> M: Arnaldo Carvalho de Melo <acme@kernel.org> L: linux-kernel@vger.kernel.org @@ -8386,6 +8408,14 @@ L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) S: Maintained F: drivers/pinctrl/samsung/ +PIN CONTROLLER - SINGLE +M: Tony Lindgren <tony@atomide.com> +M: Haojian Zhuang <haojian.zhuang@linaro.org> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-omap@vger.kernel.org +S: Maintained +F: drivers/pinctrl/pinctrl-single.c + PIN CONTROLLER - ST SPEAR M: Viresh Kumar <vireshk@kernel.org> L: spear-devel@list.st.com @@ -8952,6 +8982,13 @@ F: drivers/rpmsg/ F: Documentation/rpmsg.txt F: include/linux/rpmsg.h +RENESAS ETHERNET DRIVERS +R: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> +L: netdev@vger.kernel.org +L: linux-sh@vger.kernel.org +F: drivers/net/ethernet/renesas/ +F: include/linux/sh_eth.h + RESET CONTROLLER FRAMEWORK M: Philipp Zabel <p.zabel@pengutronix.de> S: Maintained @@ -9125,7 +9162,7 @@ F: drivers/s390/block/dasd* F: block/partitions/ibm.c S390 NETWORK DRIVERS -M: Ursula Braun <ursula.braun@de.ibm.com> +M: Ursula Braun <ubraun@linux.vnet.ibm.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ S: Supported @@ -9155,7 +9192,7 @@ S: Supported F: drivers/s390/scsi/zfcp_* S390 IUCV NETWORK LAYER -M: Ursula Braun <ursula.braun@de.ibm.com> +M: Ursula Braun <ubraun@linux.vnet.ibm.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ S: Supported @@ -9434,8 +9471,10 @@ F: include/scsi/sg.h SCSI SUBSYSTEM M: "James E.J. Bottomley" <JBottomley@odin.com> -L: linux-scsi@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git +M: "Martin K. Petersen" <martin.petersen@oracle.com> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git +L: linux-scsi@vger.kernel.org S: Maintained F: drivers/scsi/ F: include/scsi/ diff --git a/Makefile b/Makefile index 904a1d65df302..1122433a5cd54 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc7 NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 9a20821b111c6..c5fb9e6bc3a51 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -92,4 +92,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 2c2ac3f3ff803..6312f607932fd 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -445,6 +445,7 @@ config LINUX_LINK_BASE However some customers have peripherals mapped at this addr, so Linux needs to be scooted a bit. If you don't know what the above means, leave this setting alone. + This needs to match memory start address specified in Device Tree config HIGHMEM bool "High Memory Support" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index cf0cf34eeb24b..aeb19021099e3 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -81,7 +81,7 @@ endif LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel -KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls -mno-millicode # Finally dump eveything into kernel build system KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index f3db321549737..44a578c10732c 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -46,6 +46,7 @@ snps,pbl = < 32 >; clocks = <&apbclk>; clock-names = "stmmaceth"; + max-speed = <100>; }; ehci@0x40000 { diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts index b0eb0e7fe21d8..fc81879bc1f58 100644 --- a/arch/arc/boot/dts/nsim_hs.dts +++ b/arch/arc/boot/dts/nsim_hs.dts @@ -17,7 +17,8 @@ memory { device_type = "memory"; - reg = <0x0 0x80000000 0x0 0x40000000 /* 1 GB low mem */ + /* CONFIG_LINUX_LINK_BASE needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */ 0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */ }; diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index abf06e81c9290..210ef3e723322 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -62,9 +62,7 @@ extern int ioc_exists; #define ARC_REG_IC_IVIC 0x10 #define ARC_REG_IC_CTRL 0x11 #define ARC_REG_IC_IVIL 0x19 -#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4) #define ARC_REG_IC_PTAG 0x1E -#endif #define ARC_REG_IC_PTAG_HI 0x1F /* Bit val in IC_CTRL */ diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h index 6ff657a904b61..c28e6c347b490 100644 --- a/arch/arc/include/asm/mach_desc.h +++ b/arch/arc/include/asm/mach_desc.h @@ -23,7 +23,7 @@ * @dt_compat: Array of device tree 'compatible' strings * (XXX: although only 1st entry is looked at) * @init_early: Very early callback [called from setup_arch()] - * @init_cpu_smp: for each CPU as it is coming up (SMP as well as UP) + * @init_per_cpu: for each CPU as it is coming up (SMP as well as UP) * [(M):init_IRQ(), (o):start_kernel_secondary()] * @init_machine: arch initcall level callback (e.g. populate static * platform devices or parse Devicetree) @@ -35,7 +35,7 @@ struct machine_desc { const char **dt_compat; void (*init_early)(void); #ifdef CONFIG_SMP - void (*init_cpu_smp)(unsigned int); + void (*init_per_cpu)(unsigned int); #endif void (*init_machine)(void); void (*init_late)(void); diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index 133c867d15af0..991380438d6bf 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -48,7 +48,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq); * @init_early_smp: A SMP specific h/w block can init itself * Could be common across platforms so not covered by * mach_desc->init_early() - * @init_irq_cpu: Called for each core so SMP h/w block driver can do + * @init_per_cpu: Called for each core so SMP h/w block driver can do * any needed setup per cpu (e.g. IPI request) * @cpu_kick: For Master to kickstart a cpu (optionally at a PC) * @ipi_send: To send IPI to a @cpu @@ -57,7 +57,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq); struct plat_smp_ops { const char *info; void (*init_early_smp)(void); - void (*init_irq_cpu)(int cpu); + void (*init_per_cpu)(int cpu); void (*cpu_kick)(int cpu, unsigned long pc); void (*ipi_send)(int cpu); void (*ipi_clear)(int irq); diff --git a/arch/arc/include/asm/unwind.h b/arch/arc/include/asm/unwind.h index 7ca628b6ee2aa..c11a25bb8158d 100644 --- a/arch/arc/include/asm/unwind.h +++ b/arch/arc/include/asm/unwind.h @@ -112,7 +112,6 @@ struct unwind_frame_info { extern int arc_unwind(struct unwind_frame_info *frame); extern void arc_unwind_init(void); -extern void arc_unwind_setup(void); extern void *unwind_add_table(struct module *module, const void *table_start, unsigned long table_size); extern void unwind_remove_table(void *handle, int init_only); @@ -152,9 +151,6 @@ static inline void arc_unwind_init(void) { } -static inline void arc_unwind_setup(void) -{ -} #define unwind_add_table(a, b, c) #define unwind_remove_table(a, b) diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 26c1568274796..0394f9f61b466 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -106,10 +106,21 @@ static struct irq_chip arcv2_irq_chip = { static int arcv2_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { - if (irq == TIMER0_IRQ || irq == IPI_IRQ) + /* + * core intc IRQs [16, 23]: + * Statically assigned always private-per-core (Timers, WDT, IPI, PCT) + */ + if (hw < 24) { + /* + * A subsequent request_percpu_irq() fails if percpu_devid is + * not set. That in turns sets NOAUTOEN, meaning each core needs + * to call enable_percpu_irq() + */ + irq_set_percpu_devid(irq); irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq); - else + } else { irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq); + } return 0; } diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 2ee226546c6a8..ba17f85285cfe 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -29,11 +29,11 @@ void __init init_IRQ(void) #ifdef CONFIG_SMP /* a SMP H/w block could do IPI IRQ request here */ - if (plat_smp_ops.init_irq_cpu) - plat_smp_ops.init_irq_cpu(smp_processor_id()); + if (plat_smp_ops.init_per_cpu) + plat_smp_ops.init_per_cpu(smp_processor_id()); - if (machine_desc->init_cpu_smp) - machine_desc->init_cpu_smp(smp_processor_id()); + if (machine_desc->init_per_cpu) + machine_desc->init_per_cpu(smp_processor_id()); #endif } @@ -51,6 +51,18 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * API called for requesting percpu interrupts - called by each CPU + * - For boot CPU, actually request the IRQ with genirq core + enables + * - For subsequent callers only enable called locally + * + * Relies on being called by boot cpu first (i.e. request called ahead) of + * any enable as expected by genirq. Hence Suitable only for TIMER, IPI + * which are guaranteed to be setup on boot core first. + * Late probed peripherals such as perf can't use this as there no guarantee + * of being called on boot CPU first. + */ + void arc_request_percpu_irq(int irq, int cpu, irqreturn_t (*isr)(int irq, void *dev), const char *irq_nm, @@ -60,14 +72,17 @@ void arc_request_percpu_irq(int irq, int cpu, if (!cpu) { int rc; +#ifdef CONFIG_ISA_ARCOMPACT /* - * These 2 calls are essential to making percpu IRQ APIs work - * Ideally these details could be hidden in irq chip map function - * but the issue is IPIs IRQs being static (non-DT) and platform - * specific, so we can't identify them there. + * A subsequent request_percpu_irq() fails if percpu_devid is + * not set. That in turns sets NOAUTOEN, meaning each core needs + * to call enable_percpu_irq() + * + * For ARCv2, this is done in irq map function since we know + * which irqs are strictly per cpu */ irq_set_percpu_devid(irq); - irq_modify_status(irq, IRQ_NOAUTOEN, 0); /* @irq, @clr, @set */ +#endif rc = request_percpu_irq(irq, isr, irq_nm, percpu_dev); if (rc) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 74a9b074ac3e4..bd237acdf4f2f 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -132,7 +132,7 @@ static void mcip_probe_n_setup(void) struct plat_smp_ops plat_smp_ops = { .info = smp_cpuinfo_buf, .init_early_smp = mcip_probe_n_setup, - .init_irq_cpu = mcip_setup_per_cpu, + .init_per_cpu = mcip_setup_per_cpu, .ipi_send = mcip_ipi_send, .ipi_clear = mcip_ipi_clear, }; diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 0c08bb1ce15aa..8b134cfe5e1f1 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -428,12 +428,11 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev) #endif /* CONFIG_ISA_ARCV2 */ -void arc_cpu_pmu_irq_init(void) +static void arc_cpu_pmu_irq_init(void *data) { - struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); + int irq = *(int *)data; - arc_request_percpu_irq(arc_pmu->irq, smp_processor_id(), arc_pmu_intr, - "ARC perf counters", pmu_cpu); + enable_percpu_irq(irq, IRQ_TYPE_NONE); /* Clear all pending interrupt flags */ write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff); @@ -515,7 +514,6 @@ static int arc_pmu_device_probe(struct platform_device *pdev) if (has_interrupts) { int irq = platform_get_irq(pdev, 0); - unsigned long flags; if (irq < 0) { pr_err("Cannot get IRQ number for the platform\n"); @@ -524,24 +522,12 @@ static int arc_pmu_device_probe(struct platform_device *pdev) arc_pmu->irq = irq; - /* - * arc_cpu_pmu_irq_init() needs to be called on all cores for - * their respective local PMU. - * However we use opencoded on_each_cpu() to ensure it is called - * on core0 first, so that arc_request_percpu_irq() sets up - * AUTOEN etc. Otherwise enable_percpu_irq() fails to enable - * perf IRQ on non master cores. - * see arc_request_percpu_irq() - */ - preempt_disable(); - local_irq_save(flags); - arc_cpu_pmu_irq_init(); - local_irq_restore(flags); - smp_call_function((smp_call_func_t)arc_cpu_pmu_irq_init, 0, 1); - preempt_enable(); - - /* Clean all pending interrupt flags */ - write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff); + /* intc map function ensures irq_set_percpu_devid() called */ + request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", + this_cpu_ptr(&arc_pmu_cpu)); + + on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); + } else arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index c33e77c0ad3e9..e1b87444ea9a0 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -429,7 +429,6 @@ void __init setup_arch(char **cmdline_p) #endif arc_unwind_init(); - arc_unwind_setup(); } static int __init customize_machine(void) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 580587805fa30..ef6e9e15b82ab 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -132,11 +132,11 @@ void start_kernel_secondary(void) pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu); /* Some SMP H/w setup - for each cpu */ - if (plat_smp_ops.init_irq_cpu) - plat_smp_ops.init_irq_cpu(cpu); + if (plat_smp_ops.init_per_cpu) + plat_smp_ops.init_per_cpu(cpu); - if (machine_desc->init_cpu_smp) - machine_desc->init_cpu_smp(cpu); + if (machine_desc->init_per_cpu) + machine_desc->init_per_cpu(cpu); arc_local_timer_setup(); diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 7352475451f6c..5eb707640e9c4 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -170,6 +170,23 @@ static struct unwind_table *find_table(unsigned long pc) static unsigned long read_pointer(const u8 **pLoc, const void *end, signed ptrType); +static void init_unwind_hdr(struct unwind_table *table, + void *(*alloc) (unsigned long)); + +/* + * wrappers for header alloc (vs. calling one vs. other at call site) + * to elide section mismatches warnings + */ +static void *__init unw_hdr_alloc_early(unsigned long sz) +{ + return __alloc_bootmem_nopanic(sz, sizeof(unsigned int), + MAX_DMA_ADDRESS); +} + +static void *unw_hdr_alloc(unsigned long sz) +{ + return kmalloc(sz, GFP_KERNEL); +} static void init_unwind_table(struct unwind_table *table, const char *name, const void *core_start, unsigned long core_size, @@ -209,6 +226,8 @@ void __init arc_unwind_init(void) __start_unwind, __end_unwind - __start_unwind, NULL, 0); /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/ + + init_unwind_hdr(&root_table, unw_hdr_alloc_early); } static const u32 bad_cie, not_fde; @@ -241,8 +260,8 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size) e2->fde = v; } -static void __init setup_unwind_table(struct unwind_table *table, - void *(*alloc) (unsigned long)) +static void init_unwind_hdr(struct unwind_table *table, + void *(*alloc) (unsigned long)) { const u8 *ptr; unsigned long tableSize = table->size, hdrSize; @@ -277,10 +296,10 @@ static void __init setup_unwind_table(struct unwind_table *table, if (cie == ¬_fde) continue; if (cie == NULL || cie == &bad_cie) - return; + goto ret_err; ptrType = fde_pointer_type(cie); if (ptrType < 0) - return; + goto ret_err; ptr = (const u8 *)(fde + 2); if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde, @@ -296,13 +315,15 @@ static void __init setup_unwind_table(struct unwind_table *table, } if (tableSize || !n) - return; + goto ret_err; hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int) + 2 * n * sizeof(unsigned long); + header = alloc(hdrSize); if (!header) - return; + goto ret_err; + header->version = 1; header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native; header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4; @@ -340,18 +361,10 @@ static void __init setup_unwind_table(struct unwind_table *table, table->hdrsz = hdrSize; smp_wmb(); table->header = (const void *)header; -} - -static void *__init balloc(unsigned long sz) -{ - return __alloc_bootmem_nopanic(sz, - sizeof(unsigned int), - __pa(MAX_DMA_ADDRESS)); -} + return; -void __init arc_unwind_setup(void) -{ - setup_unwind_table(&root_table, balloc); +ret_err: + panic("Attention !!! Dwarf FDE parsing errors\n");; } #ifdef CONFIG_MODULES @@ -377,6 +390,8 @@ void *unwind_add_table(struct module *module, const void *table_start, table_start, table_size, NULL, 0); + init_unwind_hdr(table, unw_hdr_alloc); + #ifdef UNWIND_DEBUG unw_debug("Table added for [%s] %lx %lx\n", module->name, table->core.pc, table->core.range); @@ -439,6 +454,7 @@ void unwind_remove_table(void *handle, int init_only) info.init_only = init_only; unlink_table(&info); /* XXX: SMP */ + kfree(table->header); kfree(table); } @@ -588,9 +604,6 @@ static signed fde_pointer_type(const u32 *cie) const u8 *ptr = (const u8 *)(cie + 2); unsigned version = *ptr; - if (version != 1) - return -1; /* unsupported */ - if (*++ptr) { const char *aug; const u8 *end = (const u8 *)(cie + 1) + *cie; @@ -1002,9 +1015,7 @@ int arc_unwind(struct unwind_frame_info *frame) ptr = (const u8 *)(cie + 2); end = (const u8 *)(cie + 1) + *cie; frame->call_frame = 1; - if ((state.version = *ptr) != 1) - cie = NULL; /* unsupported version */ - else if (*++ptr) { + if (*++ptr) { /* check if augmentation size is first (thus present) */ if (*ptr == 'z') { while (++ptr < end && *ptr) { diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 065ee6bfa82a2..92dd92cad7f92 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -111,7 +111,7 @@ void __kunmap_atomic(void *kv) } EXPORT_SYMBOL(__kunmap_atomic); -noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr) +static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr) { pgd_t *pgd_k; pud_t *pud_k; @@ -127,7 +127,7 @@ noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr) return pte_k; } -void kmap_init(void) +void __init kmap_init(void) { /* Due to recursive include hell, we can't do this in processor.h */ BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE)); diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index a9305b5a2cd4b..7d2c4fbf4f22e 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -51,7 +51,9 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) int in_use = 0; if (!low_mem_sz) { - BUG_ON(base != low_mem_start); + if (base != low_mem_start) + panic("CONFIG_LINUX_LINK_BASE != DT memory { }"); + low_mem_sz = size; in_use = 1; } else { diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index d83ff9c9701e3..de8791a4d1311 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -74,7 +74,7 @@ reg = <0x48240200 0x100>; interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&dpll_mpu_m2_ck>; + clocks = <&mpu_periphclk>; }; local_timer: timer@48240600 { @@ -82,7 +82,7 @@ reg = <0x48240600 0x100>; interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&dpll_mpu_m2_ck>; + clocks = <&mpu_periphclk>; }; l2-cache-controller@48242000 { diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi index cc88728d751de..a38af2bfbfcfb 100644 --- a/arch/arm/boot/dts/am43xx-clocks.dtsi +++ b/arch/arm/boot/dts/am43xx-clocks.dtsi @@ -259,6 +259,14 @@ ti,invert-autoidle-bit; }; + mpu_periphclk: mpu_periphclk { + #clock-cells = <0>; + compatible = "fixed-factor-clock"; + clocks = <&dpll_mpu_m2_ck>; + clock-mult = <1>; + clock-div = <2>; + }; + dpll_ddr_ck: dpll_ddr_ck { #clock-cells = <0>; compatible = "ti,am3-dpll-clock"; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index ad6de73ed5a5f..e74df327cdd3b 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -184,6 +184,7 @@ regulator-name = "VDD_SDHC_1V8"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; }; }; }; diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi index 8ea177f375ddd..fb1da99996ea4 100644 --- a/arch/arm/boot/dts/berlin2q.dtsi +++ b/arch/arm/boot/dts/berlin2q.dtsi @@ -118,7 +118,8 @@ sdhci0: sdhci@ab0000 { compatible = "mrvl,pxav3-mmc"; reg = <0xab0000 0x200>; - clocks = <&chip_clk CLKID_SDIO1XIN>; + clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>; + clock-names = "io", "core"; interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -126,7 +127,8 @@ sdhci1: sdhci@ab0800 { compatible = "mrvl,pxav3-mmc"; reg = <0xab0800 0x200>; - clocks = <&chip_clk CLKID_SDIO1XIN>; + clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>; + clock-names = "io", "core"; interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -135,7 +137,7 @@ compatible = "mrvl,pxav3-mmc"; reg = <0xab1000 0x200>; interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_NFC>; + clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_SDIO>; clock-names = "io", "core"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi index 3c99cfa1a8761..eee636de4cd84 100644 --- a/arch/arm/boot/dts/dm816x.dtsi +++ b/arch/arm/boot/dts/dm816x.dtsi @@ -218,6 +218,7 @@ reg = <0x480c8000 0x2000>; interrupts = <77>; ti,hwmods = "mailbox"; + #mbox-cells = <1>; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <12>; mbox_dsp: mbox_dsp { @@ -279,8 +280,11 @@ ti,spi-num-cs = <4>; ti,hwmods = "mcspi1"; dmas = <&edma 16 &edma 17 - &edma 18 &edma 19>; - dma-names = "tx0", "rx0", "tx1", "rx1"; + &edma 18 &edma 19 + &edma 20 &edma 21 + &edma 22 &edma 23>; + dma-names = "tx0", "rx0", "tx1", "rx1", + "tx2", "rx2", "tx3", "rx3"; }; mmc1: mmc@48060000 { diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts index 58adf176425a6..a51834e1dd278 100644 --- a/arch/arm/boot/dts/imx6q-gw5400-a.dts +++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts @@ -154,7 +154,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi index 7b31fdb79ced5..dc0cebfe22d7b 100644 --- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi @@ -94,7 +94,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 1b66328a84987..18cd4114a23e8 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -154,7 +154,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi index 7c51839ff9346..eea90f37bbb8c 100644 --- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi @@ -155,7 +155,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi index 929e0b37bd9e5..6c11a2ae35ef9 100644 --- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi @@ -145,7 +145,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 8263fc18a7d95..d354d406954da 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -113,14 +113,14 @@ &clks { assigned-clocks = <&clks IMX6QDL_PLL4_BYPASS_SRC>, <&clks IMX6QDL_PLL4_BYPASS>, - <&clks IMX6QDL_CLK_PLL4_POST_DIV>, <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, + <&clks IMX6QDL_CLK_PLL4_POST_DIV>; assigned-clock-parents = <&clks IMX6QDL_CLK_LVDS2_IN>, <&clks IMX6QDL_PLL4_BYPASS_SRC>, <&clks IMX6QDL_CLK_PLL3_USB_OTG>, <&clks IMX6QDL_CLK_PLL3_USB_OTG>; - assigned-clock-rates = <0>, <0>, <24576000>; + assigned-clock-rates = <0>, <0>, <0>, <0>, <24576000>; }; &ecspi1 { diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index 1a78f013f37ab..b75f7b2b7c4ac 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -189,3 +189,7 @@ }; }; +&uart3 { + interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH + &omap4_pmx_core OMAP4_UART3_RX>; +}; diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts index 2d4250b1faf80..68b479b8772c6 100644 --- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts +++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts @@ -83,6 +83,7 @@ reg = <0x5d>; interrupt-parent = <&pio>; interrupts = <0 3 IRQ_TYPE_LEVEL_HIGH>; /* PA3 */ + touchscreen-swapped-x-y; }; }; diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi index 40c23a0b7cfc2..ec1aa64ded681 100644 --- a/arch/arm/boot/dts/tegra124-nyan.dtsi +++ b/arch/arm/boot/dts/tegra124-nyan.dtsi @@ -399,7 +399,7 @@ /* CPU DFLL clock */ clock@0,70110000 { - status = "okay"; + status = "disabled"; vdd-cpu-supply = <&vdd_cpu>; nvidia,i2c-fs-rate = <400000>; }; diff --git a/arch/arm/boot/dts/vf610-colibri.dtsi b/arch/arm/boot/dts/vf610-colibri.dtsi index 19fe045b83342..2d7eab7552100 100644 --- a/arch/arm/boot/dts/vf610-colibri.dtsi +++ b/arch/arm/boot/dts/vf610-colibri.dtsi @@ -18,8 +18,3 @@ reg = <0x80000000 0x10000000>; }; }; - -&L2 { - arm,data-latency = <2 1 2>; - arm,tag-latency = <3 2 3>; -}; diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi index 5f8eb1bd782bf..58bc6e448be56 100644 --- a/arch/arm/boot/dts/vf610.dtsi +++ b/arch/arm/boot/dts/vf610.dtsi @@ -19,7 +19,7 @@ reg = <0x40006000 0x1000>; cache-unified; cache-level = <2>; - arm,data-latency = <1 1 1>; + arm,data-latency = <3 3 3>; arm,tag-latency = <2 2 2>; }; }; diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi index 0d5acc2cdc8ef..3cd1b27f26978 100644 --- a/arch/arm/boot/dts/vfxxx.dtsi +++ b/arch/arm/boot/dts/vfxxx.dtsi @@ -178,8 +178,10 @@ compatible = "fsl,vf610-sai"; reg = <0x40031000 0x1000>; interrupts = <86 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks VF610_CLK_SAI2>; - clock-names = "sai"; + clocks = <&clks VF610_CLK_SAI2>, + <&clks VF610_CLK_SAI2_DIV>, + <&clks 0>, <&clks 0>; + clock-names = "bus", "mclk1", "mclk2", "mclk3"; dma-names = "tx", "rx"; dmas = <&edma0 0 21>, <&edma0 0 20>; diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 6607d976e07d0..7da5503c05914 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -21,6 +21,7 @@ #ifndef __ASSEMBLY__ #include <linux/io.h> +#include <asm/barrier.h> #define __ACCESS_CP15(CRn, Op1, CRm, Op2) p15, Op1, %0, CRn, CRm, Op2 #define __ACCESS_CP15_64(Op1, CRm) p15, Op1, %Q0, %R0, CRm diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index a9c80a2ea1a77..3095df091ff8a 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -28,6 +28,18 @@ unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu); +static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu, + u8 reg_num) +{ + return *vcpu_reg(vcpu, reg_num); +} + +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, + unsigned long val) +{ + *vcpu_reg(vcpu, reg_num) = val; +} + bool kvm_condition_valid(struct kvm_vcpu *vcpu); void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr); void kvm_inject_undefined(struct kvm_vcpu *vcpu); diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 8cc85a4ebec20..35c9db857ebe9 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -510,10 +510,14 @@ __copy_to_user_std(void __user *to, const void *from, unsigned long n); static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { +#ifndef CONFIG_UACCESS_WITH_MEMCPY unsigned int __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; +#else + return arm_copy_to_user(to, from, n); +#endif } extern unsigned long __must_check diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 7a7c4cea55231..4adfb46e3ee93 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -95,6 +95,22 @@ void __show_regs(struct pt_regs *regs) { unsigned long flags; char buf[64]; +#ifndef CONFIG_CPU_V7M + unsigned int domain; +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Get the domain register for the parent context. In user + * mode, we don't save the DACR, so lets use what it should + * be. For other modes, we place it after the pt_regs struct. + */ + if (user_mode(regs)) + domain = DACR_UACCESS_ENABLE; + else + domain = *(unsigned int *)(regs + 1); +#else + domain = get_domain(); +#endif +#endif show_regs_print_info(KERN_DEFAULT); @@ -123,21 +139,8 @@ void __show_regs(struct pt_regs *regs) #ifndef CONFIG_CPU_V7M { - unsigned int domain = get_domain(); const char *segment; -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Get the domain register for the parent context. In user - * mode, we don't save the DACR, so lets use what it should - * be. For other modes, we place it after the pt_regs struct. - */ - if (user_mode(regs)) - domain = DACR_UACCESS_ENABLE; - else - domain = *(unsigned int *)(regs + 1); -#endif - if ((domain & domain_mask(DOMAIN_USER)) == domain_val(DOMAIN_USER, DOMAIN_NOACCESS)) segment = "none"; @@ -163,11 +166,11 @@ void __show_regs(struct pt_regs *regs) buf[0] = '\0'; #ifdef CONFIG_CPU_CP15_MMU { - unsigned int transbase, dac = get_domain(); + unsigned int transbase; asm("mrc p15, 0, %0, c2, c0\n\t" : "=r" (transbase)); snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x", - transbase, dac); + transbase, domain); } #endif asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl)); diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index 5b26e7efa9ea4..c3fe769d75584 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -36,10 +36,10 @@ */ #define __user_swpX_asm(data, addr, res, temp, B) \ __asm__ __volatile__( \ - " mov %2, %1\n" \ - "0: ldrex"B" %1, [%3]\n" \ - "1: strex"B" %0, %2, [%3]\n" \ + "0: ldrex"B" %2, [%3]\n" \ + "1: strex"B" %0, %1, [%3]\n" \ " cmp %0, #0\n" \ + " moveq %1, %2\n" \ " movne %0, %4\n" \ "2:\n" \ " .section .text.fixup,\"ax\"\n" \ diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index b83f3b7737fb9..087acb569b63a 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -193,15 +193,44 @@ struct oabi_flock64 { pid_t l_pid; } __attribute__ ((packed,aligned(4))); -asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, +static long do_locks(unsigned int fd, unsigned int cmd, unsigned long arg) { - struct oabi_flock64 user; struct flock64 kernel; - mm_segment_t fs = USER_DS; /* initialized to kill a warning */ - unsigned long local_arg = arg; - int ret; + struct oabi_flock64 user; + mm_segment_t fs; + long ret; + + if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, + sizeof(user))) + return -EFAULT; + kernel.l_type = user.l_type; + kernel.l_whence = user.l_whence; + kernel.l_start = user.l_start; + kernel.l_len = user.l_len; + kernel.l_pid = user.l_pid; + + fs = get_fs(); + set_fs(KERNEL_DS); + ret = sys_fcntl64(fd, cmd, (unsigned long)&kernel); + set_fs(fs); + + if (!ret && (cmd == F_GETLK64 || cmd == F_OFD_GETLK)) { + user.l_type = kernel.l_type; + user.l_whence = kernel.l_whence; + user.l_start = kernel.l_start; + user.l_len = kernel.l_len; + user.l_pid = kernel.l_pid; + if (copy_to_user((struct oabi_flock64 __user *)arg, + &user, sizeof(user))) + ret = -EFAULT; + } + return ret; +} +asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, + unsigned long arg) +{ switch (cmd) { case F_OFD_GETLK: case F_OFD_SETLK: @@ -209,39 +238,11 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: - if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, - sizeof(user))) - return -EFAULT; - kernel.l_type = user.l_type; - kernel.l_whence = user.l_whence; - kernel.l_start = user.l_start; - kernel.l_len = user.l_len; - kernel.l_pid = user.l_pid; - local_arg = (unsigned long)&kernel; - fs = get_fs(); - set_fs(KERNEL_DS); - } - - ret = sys_fcntl64(fd, cmd, local_arg); + return do_locks(fd, cmd, arg); - switch (cmd) { - case F_GETLK64: - if (!ret) { - user.l_type = kernel.l_type; - user.l_whence = kernel.l_whence; - user.l_start = kernel.l_start; - user.l_len = kernel.l_len; - user.l_pid = kernel.l_pid; - if (copy_to_user((struct oabi_flock64 __user *)arg, - &user, sizeof(user))) - ret = -EFAULT; - } - case F_SETLK64: - case F_SETLKW64: - set_fs(fs); + default: + return sys_fcntl64(fd, cmd, arg); } - - return ret; } struct oabi_epoll_event { diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 974b1c606d044..3a10c9f1d0a46 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, data); data = vcpu_data_host_to_guest(vcpu, data, len); - *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data; + vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data); } return 0; @@ -186,7 +186,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, rt = vcpu->arch.mmio_decode.rt; if (is_write) { - data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), + len); trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); mmio_write_buf(data_buf, len, data); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 7dace909d5cf1..61d96a645ff38 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -218,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, kvm_tlb_flush_vmid_ipa(kvm, addr); /* No need to invalidate the cache for device mappings */ - if (!kvm_is_device_pfn(__phys_to_pfn(addr))) + if (!kvm_is_device_pfn(pte_pfn(old_pte))) kvm_flush_dcache_pte(old_pte); put_page(virt_to_page(pte)); @@ -310,7 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte) && !kvm_is_device_pfn(__phys_to_pfn(addr))) + if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte))) kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 0b556968a6da1..a9b3b905e661d 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -75,7 +75,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) unsigned long context_id; phys_addr_t target_pc; - cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK; + cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK; if (vcpu_mode_is_32bit(source_vcpu)) cpu_id &= ~((u32) 0); @@ -94,8 +94,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) return PSCI_RET_INVALID_PARAMS; } - target_pc = *vcpu_reg(source_vcpu, 2); - context_id = *vcpu_reg(source_vcpu, 3); + target_pc = vcpu_get_reg(source_vcpu, 2); + context_id = vcpu_get_reg(source_vcpu, 3); kvm_reset_vcpu(vcpu); @@ -114,7 +114,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) * NOTE: We always update r0 (or x0) because for PSCI v0.1 * the general puspose registers are undefined upon CPU_ON. */ - *vcpu_reg(vcpu, 0) = context_id; + vcpu_set_reg(vcpu, 0, context_id); vcpu->arch.power_off = false; smp_mb(); /* Make sure the above is visible */ @@ -134,8 +134,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; - target_affinity = *vcpu_reg(vcpu, 1); - lowest_affinity_level = *vcpu_reg(vcpu, 2); + target_affinity = vcpu_get_reg(vcpu, 1); + lowest_affinity_level = vcpu_get_reg(vcpu, 2); /* Determine target affinity mask */ target_affinity_mask = psci_affinity_mask(lowest_affinity_level); @@ -209,7 +209,7 @@ int kvm_psci_version(struct kvm_vcpu *vcpu) static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { int ret = 1; - unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0); + unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); unsigned long val; switch (psci_fn) { @@ -273,13 +273,13 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } - *vcpu_reg(vcpu, 0) = val; + vcpu_set_reg(vcpu, 0, val); return ret; } static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) { - unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0); + unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); unsigned long val; switch (psci_fn) { @@ -295,7 +295,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) break; } - *vcpu_reg(vcpu, 0) = val; + vcpu_set_reg(vcpu, 0, val); return 1; } diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index d72b909051324..588bbc288396a 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -88,6 +88,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) static unsigned long noinline __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) { + unsigned long ua_flags; int atomic; if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { @@ -118,7 +119,9 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memcpy((void *)to, from, tocopy); + uaccess_restore(ua_flags); to += tocopy; from += tocopy; n -= tocopy; @@ -145,14 +148,21 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n) * With frame pointer disabled, tail call optimization kicks in * as well making this test almost invisible. */ - if (n < 64) - return __copy_to_user_std(to, from, n); - return __copy_to_user_memcpy(to, from, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __copy_to_user_std(to, from, n); + uaccess_restore(ua_flags); + } else { + n = __copy_to_user_memcpy(to, from, n); + } + return n; } static unsigned long noinline __clear_user_memset(void __user *addr, unsigned long n) { + unsigned long ua_flags; + if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { memset((void *)addr, 0, n); return 0; @@ -175,7 +185,9 @@ __clear_user_memset(void __user *addr, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memset((void *)addr, 0, tocopy); + uaccess_restore(ua_flags); addr += tocopy; n -= tocopy; @@ -193,9 +205,14 @@ out: unsigned long arm_clear_user(void __user *addr, unsigned long n) { /* See rational for this in __copy_to_user() above. */ - if (n < 64) - return __clear_user_std(addr, n); - return __clear_user_memset(addr, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __clear_user_std(addr, n); + uaccess_restore(ua_flags); + } else { + n = __clear_user_memset(addr, n); + } + return n; } #if 0 diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 92673006e55c4..28656c2b54a0b 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -4,7 +4,6 @@ menuconfig ARCH_AT91 select ARCH_REQUIRE_GPIOLIB select COMMON_CLK_AT91 select PINCTRL - select PINCTRL_AT91 select SOC_BUS if ARCH_AT91 @@ -17,6 +16,7 @@ config SOC_SAMA5D2 select HAVE_AT91_USB_CLK select HAVE_AT91_H32MX select HAVE_AT91_GENERATED_CLK + select PINCTRL_AT91PIO4 help Select this if ou are using one of Atmel's SAMA5D2 family SoC. @@ -27,6 +27,7 @@ config SOC_SAMA5D3 select HAVE_AT91_UTMI select HAVE_AT91_SMD select HAVE_AT91_USB_CLK + select PINCTRL_AT91 help Select this if you are using one of Atmel's SAMA5D3 family SoC. This support covers SAMA5D31, SAMA5D33, SAMA5D34, SAMA5D35, SAMA5D36. @@ -40,6 +41,7 @@ config SOC_SAMA5D4 select HAVE_AT91_SMD select HAVE_AT91_USB_CLK select HAVE_AT91_H32MX + select PINCTRL_AT91 help Select this if you are using one of Atmel's SAMA5D4 family SoC. @@ -50,6 +52,7 @@ config SOC_AT91RM9200 select CPU_ARM920T select HAVE_AT91_USB_CLK select MIGHT_HAVE_PCI + select PINCTRL_AT91 select SOC_SAM_V4_V5 select SRAM if PM help @@ -65,6 +68,7 @@ config SOC_AT91SAM9 select HAVE_AT91_UTMI select HAVE_FB_ATMEL select MEMORY + select PINCTRL_AT91 select SOC_SAM_V4_V5 select SRAM if PM help diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 80e277cfcc8b6..23726fb31741e 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -41,8 +41,10 @@ * implementation should be moved down into the pinctrl driver and get * called as part of the generic suspend/resume path. */ +#ifdef CONFIG_PINCTRL_AT91 extern void at91_pinctrl_gpio_suspend(void); extern void at91_pinctrl_gpio_resume(void); +#endif static struct { unsigned long uhp_udp_mask; @@ -151,8 +153,9 @@ static void at91_pm_suspend(suspend_state_t state) static int at91_pm_enter(suspend_state_t state) { +#ifdef CONFIG_PINCTRL_AT91 at91_pinctrl_gpio_suspend(); - +#endif switch (state) { /* * Suspend-to-RAM is like STANDBY plus slow clock mode, so @@ -192,7 +195,9 @@ static int at91_pm_enter(suspend_state_t state) error: target_state = PM_SUSPEND_ON; +#ifdef CONFIG_PINCTRL_AT91 at91_pinctrl_gpio_resume(); +#endif return 0; } diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c index de68938ee6aa8..c21e41dad19c1 100644 --- a/arch/arm/mach-exynos/pmu.c +++ b/arch/arm/mach-exynos/pmu.c @@ -748,8 +748,12 @@ static void exynos5_powerdown_conf(enum sys_powerdown mode) void exynos_sys_powerdown_conf(enum sys_powerdown mode) { unsigned int i; + const struct exynos_pmu_data *pmu_data; + + if (!pmu_context) + return; - const struct exynos_pmu_data *pmu_data = pmu_context->pmu_data; + pmu_data = pmu_context->pmu_data; if (pmu_data->powerdown_conf) pmu_data->powerdown_conf(mode); diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h index b024390199639..7a0c13bf42694 100644 --- a/arch/arm/mach-ixp4xx/include/mach/io.h +++ b/arch/arm/mach-ixp4xx/include/mach/io.h @@ -143,7 +143,7 @@ static inline void __indirect_writesl(volatile void __iomem *bus_addr, writel(*vaddr++, bus_addr); } -static inline unsigned char __indirect_readb(const volatile void __iomem *p) +static inline u8 __indirect_readb(const volatile void __iomem *p) { u32 addr = (u32)p; u32 n, byte_enables, data; @@ -166,7 +166,7 @@ static inline void __indirect_readsb(const volatile void __iomem *bus_addr, *vaddr++ = readb(bus_addr); } -static inline unsigned short __indirect_readw(const volatile void __iomem *p) +static inline u16 __indirect_readw(const volatile void __iomem *p) { u32 addr = (u32)p; u32 n, byte_enables, data; @@ -189,7 +189,7 @@ static inline void __indirect_readsw(const volatile void __iomem *bus_addr, *vaddr++ = readw(bus_addr); } -static inline unsigned long __indirect_readl(const volatile void __iomem *p) +static inline u32 __indirect_readl(const volatile void __iomem *p) { u32 addr = (__force u32)p; u32 data; @@ -350,7 +350,7 @@ static inline void insl(u32 io_addr, void *p, u32 count) ((unsigned long)p <= (PIO_MASK + PIO_OFFSET))) #define ioread8(p) ioread8(p) -static inline unsigned int ioread8(const void __iomem *addr) +static inline u8 ioread8(const void __iomem *addr) { unsigned long port = (unsigned long __force)addr; if (__is_io_address(port)) @@ -378,7 +378,7 @@ static inline void ioread8_rep(const void __iomem *addr, void *vaddr, u32 count) } #define ioread16(p) ioread16(p) -static inline unsigned int ioread16(const void __iomem *addr) +static inline u16 ioread16(const void __iomem *addr) { unsigned long port = (unsigned long __force)addr; if (__is_io_address(port)) @@ -407,7 +407,7 @@ static inline void ioread16_rep(const void __iomem *addr, void *vaddr, } #define ioread32(p) ioread32(p) -static inline unsigned int ioread32(const void __iomem *addr) +static inline u32 ioread32(const void __iomem *addr) { unsigned long port = (unsigned long __force)addr; if (__is_io_address(port)) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 5076d3f334d28..0517f0c1581a7 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -65,6 +65,8 @@ config SOC_AM43XX select MACH_OMAP_GENERIC select MIGHT_HAVE_CACHE_L2X0 select HAVE_ARM_SCU + select GENERIC_CLOCKEVENTS_BROADCAST + select HAVE_ARM_TWD config SOC_DRA7XX bool "TI DRA7XX" @@ -121,6 +123,7 @@ config ARCH_OMAP2PLUS_TYPICAL select NEON if CPU_V7 select PM select REGULATOR + select REGULATOR_FIXED_VOLTAGE select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4 select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4 select VFP @@ -201,7 +204,6 @@ config MACH_OMAP3_PANDORA depends on ARCH_OMAP3 default y select OMAP_PACKAGE_CBB - select REGULATOR_FIXED_VOLTAGE if REGULATOR config MACH_NOKIA_N810 bool diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index b18ebbefae095..f86692dbcfd56 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -320,6 +320,12 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer, return r; } +#if !defined(CONFIG_SMP) && defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) +void tick_broadcast(const struct cpumask *mask) +{ +} +#endif + static void __init omap2_gp_clockevent_init(int gptimer_id, const char *fck_source, const char *property) diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c index 9a9c15bfcd345..7c0d5618be5e8 100644 --- a/arch/arm/mach-pxa/ezx.c +++ b/arch/arm/mach-pxa/ezx.c @@ -889,6 +889,7 @@ static void __init e680_init(void) pxa_set_keypad_info(&e680_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(e680_devices)); } @@ -956,6 +957,7 @@ static void __init a1200_init(void) pxa_set_keypad_info(&a1200_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(a1200_devices)); } @@ -1148,6 +1150,7 @@ static void __init a910_init(void) platform_device_register(&a910_camera); } + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(a910_devices)); } @@ -1215,6 +1218,7 @@ static void __init e6_init(void) pxa_set_keypad_info(&e6_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(e6_devices)); } @@ -1256,6 +1260,7 @@ static void __init e2_init(void) pxa_set_keypad_info(&e2_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(e2_devices)); } diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c index a19460e6e7b0e..b355fca6cc2ef 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c @@ -20,7 +20,7 @@ #include <plat/cpu.h> #include <plat/cpu-freq-core.h> -static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = { +static struct cpufreq_frequency_table s3c2440_plls_12[] = { { .frequency = 75000000, .driver_data = PLLVAL(0x75, 3, 3), }, /* FVco 600.000000 */ { .frequency = 80000000, .driver_data = PLLVAL(0x98, 4, 3), }, /* FVco 640.000000 */ { .frequency = 90000000, .driver_data = PLLVAL(0x70, 2, 3), }, /* FVco 720.000000 */ diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c index 1191b29056252..be9a248b5ce90 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c @@ -20,7 +20,7 @@ #include <plat/cpu.h> #include <plat/cpu-freq-core.h> -static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = { +static struct cpufreq_frequency_table s3c2440_plls_169344[] = { { .frequency = 78019200, .driver_data = PLLVAL(121, 5, 3), }, /* FVco 624.153600 */ { .frequency = 84067200, .driver_data = PLLVAL(131, 5, 3), }, /* FVco 672.537600 */ { .frequency = 90115200, .driver_data = PLLVAL(141, 5, 3), }, /* FVco 720.921600 */ diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 845769e413323..c8c8b9ed02e09 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -165,13 +165,28 @@ static void flush_context(unsigned int cpu) __flush_icache_all(); } -static int is_reserved_asid(u64 asid) +static bool check_update_reserved_asid(u64 asid, u64 newasid) { int cpu; - for_each_possible_cpu(cpu) - if (per_cpu(reserved_asids, cpu) == asid) - return 1; - return 0; + bool hit = false; + + /* + * Iterate over the set of reserved ASIDs looking for a match. + * If we find one, then we can update our mm to use newasid + * (i.e. the same ASID in the current generation) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old ASID are updated to reflect the mm. Failure to do + * so could result in us missing the reserved ASID in a future + * generation. + */ + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_asids, cpu) == asid) { + hit = true; + per_cpu(reserved_asids, cpu) = newasid; + } + } + + return hit; } static u64 new_context(struct mm_struct *mm, unsigned int cpu) @@ -181,12 +196,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) u64 generation = atomic64_read(&asid_generation); if (asid != 0) { + u64 newasid = generation | (asid & ~ASID_MASK); + /* * If our current ASID was active during a rollover, we * can continue to use it and this was just a false alarm. */ - if (is_reserved_asid(asid)) - return generation | (asid & ~ASID_MASK); + if (check_update_reserved_asid(asid, newasid)) + return newasid; /* * We had a valid ASID in a previous life, so try to re-use @@ -194,7 +211,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) */ asid &= ~ASID_MASK; if (!__test_and_set_bit(asid, asid_map)) - goto bump_gen; + return newasid; } /* @@ -216,11 +233,8 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) __set_bit(asid, asid_map); cur_idx = asid; - -bump_gen: - asid |= generation; cpumask_clear(mm_cpumask(mm)); - return asid; + return asid | generation; } void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e62400e5fb99f..534a60ae282e7 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1521,7 +1521,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, return -ENOMEM; for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) { - phys_addr_t phys = sg_phys(s) & PAGE_MASK; + phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); if (!is_coherent && diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 8a63b4cdc0f27..7f8cd1b3557f0 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -22,6 +22,7 @@ #include <linux/memblock.h> #include <linux/dma-contiguous.h> #include <linux/sizes.h> +#include <linux/stop_machine.h> #include <asm/cp15.h> #include <asm/mach-types.h> @@ -627,12 +628,10 @@ static struct section_perm ro_perms[] = { * safe to be called with preemption disabled, as under stop_machine(). */ static inline void section_update(unsigned long addr, pmdval_t mask, - pmdval_t prot) + pmdval_t prot, struct mm_struct *mm) { - struct mm_struct *mm; pmd_t *pmd; - mm = current->active_mm; pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr); #ifdef CONFIG_ARM_LPAE @@ -656,49 +655,82 @@ static inline bool arch_has_strict_perms(void) return !!(get_cr() & CR_XP); } -#define set_section_perms(perms, field) { \ - size_t i; \ - unsigned long addr; \ - \ - if (!arch_has_strict_perms()) \ - return; \ - \ - for (i = 0; i < ARRAY_SIZE(perms); i++) { \ - if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || \ - !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { \ - pr_err("BUG: section %lx-%lx not aligned to %lx\n", \ - perms[i].start, perms[i].end, \ - SECTION_SIZE); \ - continue; \ - } \ - \ - for (addr = perms[i].start; \ - addr < perms[i].end; \ - addr += SECTION_SIZE) \ - section_update(addr, perms[i].mask, \ - perms[i].field); \ - } \ +void set_section_perms(struct section_perm *perms, int n, bool set, + struct mm_struct *mm) +{ + size_t i; + unsigned long addr; + + if (!arch_has_strict_perms()) + return; + + for (i = 0; i < n; i++) { + if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || + !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { + pr_err("BUG: section %lx-%lx not aligned to %lx\n", + perms[i].start, perms[i].end, + SECTION_SIZE); + continue; + } + + for (addr = perms[i].start; + addr < perms[i].end; + addr += SECTION_SIZE) + section_update(addr, perms[i].mask, + set ? perms[i].prot : perms[i].clear, mm); + } + } -static inline void fix_kernmem_perms(void) +static void update_sections_early(struct section_perm perms[], int n) { - set_section_perms(nx_perms, prot); + struct task_struct *t, *s; + + read_lock(&tasklist_lock); + for_each_process(t) { + if (t->flags & PF_KTHREAD) + continue; + for_each_thread(t, s) + set_section_perms(perms, n, true, s->mm); + } + read_unlock(&tasklist_lock); + set_section_perms(perms, n, true, current->active_mm); + set_section_perms(perms, n, true, &init_mm); +} + +int __fix_kernmem_perms(void *unused) +{ + update_sections_early(nx_perms, ARRAY_SIZE(nx_perms)); + return 0; +} + +void fix_kernmem_perms(void) +{ + stop_machine(__fix_kernmem_perms, NULL, NULL); } #ifdef CONFIG_DEBUG_RODATA +int __mark_rodata_ro(void *unused) +{ + update_sections_early(ro_perms, ARRAY_SIZE(ro_perms)); + return 0; +} + void mark_rodata_ro(void) { - set_section_perms(ro_perms, prot); + stop_machine(__mark_rodata_ro, NULL, NULL); } void set_kernel_text_rw(void) { - set_section_perms(ro_perms, clear); + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false, + current->active_mm); } void set_kernel_text_ro(void) { - set_section_perms(ro_perms, prot); + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true, + current->active_mm); } #endif /* CONFIG_DEBUG_RODATA */ diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index de2b246fed380..8e1ea433c3f1e 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area) .equ cpu_v7_suspend_size, 4 * 9 #ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID mrc p15, 0, r5, c13, c0, 3 @ User r/o thread ID stmia r0!, {r4 - r5} @@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend) mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control stmia r0, {r5 - r11} - ldmfd sp!, {r4 - r10, pc} + ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_v7_do_suspend) ENTRY(cpu_v7_do_resume) diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi index e81cd48d6245e..925552e7b4f3e 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi @@ -269,6 +269,7 @@ clock-frequency = <0>; /* Updated by bootloader */ voltage-ranges = <1800 1800 3300 3300>; sdhci,auto-cmd12; + little-endian; bus-width = <4>; }; @@ -277,6 +278,7 @@ reg = <0x0 0x2300000 0x0 0x10000>; interrupts = <0 36 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -287,6 +289,7 @@ reg = <0x0 0x2310000 0x0 0x10000>; interrupts = <0 36 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -297,6 +300,7 @@ reg = <0x0 0x2320000 0x0 0x10000>; interrupts = <0 37 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -307,6 +311,7 @@ reg = <0x0 0x2330000 0x0 0x10000>; interrupts = <0 37 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 030cdcb46c6bd..2731d3b25ed2e 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -77,6 +77,7 @@ #ifndef __ASSEMBLY__ #include <linux/stringify.h> +#include <asm/barrier.h> /* * Low-level accessors diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 3ca894ecf699b..25a40213bd9b8 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -100,13 +100,21 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) } /* - * vcpu_reg should always be passed a register number coming from a - * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32 - * with banked registers. + * vcpu_get_reg and vcpu_set_reg should always be passed a register number + * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on + * AArch32 with banked registers. */ -static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num) +static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, + u8 reg_num) { - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num]; + return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; +} + +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, + unsigned long val) +{ + if (reg_num != 31) + vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val; } /* Get vcpu SPSR for current mode */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7e074f93f383f..63f52b55defe1 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -276,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && - pte_valid(*ptep)) { - BUG_ON(!pte_young(pte)); - BUG_ON(pte_write(*ptep) && !pte_dirty(pte)); + if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && + pte_valid(*ptep) && pte_valid(pte)) { + VM_WARN_ONCE(!pte_young(pte), + "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); + VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); } set_pte(ptep, pte); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 1ee2c3937d4e8..71426a78db123 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -5,6 +5,7 @@ */ #include <asm-generic/vmlinux.lds.h> +#include <asm/cache.h> #include <asm/kernel-pgtable.h> #include <asm/thread_info.h> #include <asm/memory.h> @@ -140,7 +141,7 @@ SECTIONS ARM_EXIT_KEEP(EXIT_DATA) } - PERCPU_SECTION(64) + PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(PAGE_SIZE); __init_end = .; @@ -158,7 +159,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); _data = .; _sdata = .; - RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE) + RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) PECOFF_EDATA_PADDING _edata = .; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 68a0759b1375e..15f0477b0d2ad 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -37,7 +37,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret; - trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), + trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0), kvm_vcpu_hvc_get_imm(vcpu)); ret = kvm_psci_call(vcpu); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 87a64e8db04c4..d2650e84faf2f 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -78,7 +78,7 @@ static u32 get_ccsidr(u32 csselr) * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). */ static bool access_dcsw(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!p->is_write) @@ -94,21 +94,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, * sys_regs and leave it in complete control of the caches. */ static bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { - unsigned long val; bool was_enabled = vcpu_has_cache_enabled(vcpu); BUG_ON(!p->is_write); - val = *vcpu_reg(vcpu, p->Rt); if (!p->is_aarch32) { - vcpu_sys_reg(vcpu, r->reg) = val; + vcpu_sys_reg(vcpu, r->reg) = p->regval; } else { if (!p->is_32bit) - vcpu_cp15_64_high(vcpu, r->reg) = val >> 32; - vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL; + vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval); + vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval); } kvm_toggle_cache(vcpu, was_enabled); @@ -122,22 +120,19 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, * for both AArch64 and AArch32 accesses. */ static bool access_gic_sgi(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 val; - if (!p->is_write) return read_from_write_only(vcpu, p); - val = *vcpu_reg(vcpu, p->Rt); - vgic_v3_dispatch_sgi(vcpu, val); + vgic_v3_dispatch_sgi(vcpu, p->regval); return true; } static bool trap_raz_wi(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) @@ -147,19 +142,19 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { return ignore_write(vcpu, p); } else { - *vcpu_reg(vcpu, p->Rt) = (1 << 3); + p->regval = (1 << 3); return true; } } static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { @@ -167,7 +162,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, } else { u32 val; asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val)); - *vcpu_reg(vcpu, p->Rt) = val; + p->regval = val; return true; } } @@ -200,17 +195,17 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, * now use the debug registers. */ static bool trap_debug_regs(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { - vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt); + vcpu_sys_reg(vcpu, r->reg) = p->regval; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg); + p->regval = vcpu_sys_reg(vcpu, r->reg); } - trace_trap_reg(__func__, r->reg, p->is_write, *vcpu_reg(vcpu, p->Rt)); + trace_trap_reg(__func__, r->reg, p->is_write, p->regval); return true; } @@ -225,10 +220,10 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, * hyp.S code switches between host and guest values in future. */ static inline void reg_to_dbg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, u64 *dbg_reg) { - u64 val = *vcpu_reg(vcpu, p->Rt); + u64 val = p->regval; if (p->is_32bit) { val &= 0xffffffffUL; @@ -240,19 +235,16 @@ static inline void reg_to_dbg(struct kvm_vcpu *vcpu, } static inline void dbg_to_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, u64 *dbg_reg) { - u64 val = *dbg_reg; - + p->regval = *dbg_reg; if (p->is_32bit) - val &= 0xffffffffUL; - - *vcpu_reg(vcpu, p->Rt) = val; + p->regval &= 0xffffffffUL; } static inline bool trap_bvr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; @@ -294,7 +286,7 @@ static inline void reset_bvr(struct kvm_vcpu *vcpu, } static inline bool trap_bcr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; @@ -337,7 +329,7 @@ static inline void reset_bcr(struct kvm_vcpu *vcpu, } static inline bool trap_wvr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; @@ -380,7 +372,7 @@ static inline void reset_wvr(struct kvm_vcpu *vcpu, } static inline bool trap_wcr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; @@ -687,7 +679,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { }; static bool trap_dbgidr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { @@ -697,23 +689,23 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu, u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1); u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT); - *vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) | - (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) | - (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) | - (6 << 16) | (el3 << 14) | (el3 << 12)); + p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) | + (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) | + (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) + | (6 << 16) | (el3 << 14) | (el3 << 12)); return true; } } static bool trap_debug32(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { - vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt); + vcpu_cp14(vcpu, r->reg) = p->regval; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg); + p->regval = vcpu_cp14(vcpu, r->reg); } return true; @@ -731,7 +723,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu, */ static inline bool trap_xvr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; @@ -740,12 +732,12 @@ static inline bool trap_xvr(struct kvm_vcpu *vcpu, u64 val = *dbg_reg; val &= 0xffffffffUL; - val |= *vcpu_reg(vcpu, p->Rt) << 32; + val |= p->regval << 32; *dbg_reg = val; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = *dbg_reg >> 32; + p->regval = *dbg_reg >> 32; } trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); @@ -991,7 +983,7 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run) * Return 0 if the access has been handled, and -1 if not. */ static int emulate_cp(struct kvm_vcpu *vcpu, - const struct sys_reg_params *params, + struct sys_reg_params *params, const struct sys_reg_desc *table, size_t num) { @@ -1062,12 +1054,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + int Rt = (hsr >> 5) & 0xf; int Rt2 = (hsr >> 10) & 0xf; params.is_aarch32 = true; params.is_32bit = false; params.CRm = (hsr >> 1) & 0xf; - params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); params.Op0 = 0; @@ -1076,15 +1068,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, params.CRn = 0; /* - * Massive hack here. Store Rt2 in the top 32bits so we only - * have one register to deal with. As we use the same trap + * Make a 64-bit value out of Rt and Rt2. As we use the same trap * backends between AArch32 and AArch64, we get away with it. */ if (params.is_write) { - u64 val = *vcpu_reg(vcpu, params.Rt); - val &= 0xffffffff; - val |= *vcpu_reg(vcpu, Rt2) << 32; - *vcpu_reg(vcpu, params.Rt) = val; + params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff; + params.regval |= vcpu_get_reg(vcpu, Rt2) << 32; } if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific)) @@ -1095,11 +1084,10 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, unhandled_cp_access(vcpu, ¶ms); out: - /* Do the opposite hack for the read side */ + /* Split up the value between registers for the read side */ if (!params.is_write) { - u64 val = *vcpu_reg(vcpu, params.Rt); - val >>= 32; - *vcpu_reg(vcpu, Rt2) = val; + vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); + vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval)); } return 1; @@ -1118,21 +1106,24 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + int Rt = (hsr >> 5) & 0xf; params.is_aarch32 = true; params.is_32bit = true; params.CRm = (hsr >> 1) & 0xf; - params.Rt = (hsr >> 5) & 0xf; + params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = ((hsr & 1) == 0); params.CRn = (hsr >> 10) & 0xf; params.Op0 = 0; params.Op1 = (hsr >> 14) & 0x7; params.Op2 = (hsr >> 17) & 0x7; - if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific)) - return 1; - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) + if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific) || + !emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); return 1; + } unhandled_cp_access(vcpu, ¶ms); return 1; @@ -1175,7 +1166,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) } static int emulate_sys_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *params) + struct sys_reg_params *params) { size_t num; const struct sys_reg_desc *table, *r; @@ -1230,6 +1221,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_hsr(vcpu); + int Rt = (esr >> 5) & 0x1f; + int ret; trace_kvm_handle_sys_reg(esr); @@ -1240,10 +1233,14 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) params.CRn = (esr >> 10) & 0xf; params.CRm = (esr >> 1) & 0xf; params.Op2 = (esr >> 17) & 0x7; - params.Rt = (esr >> 5) & 0x1f; + params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = !(esr & 1); - return emulate_sys_reg(vcpu, ¶ms); + ret = emulate_sys_reg(vcpu, ¶ms); + + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); + return ret; } /****************************************************************************** diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index eaa324e4db4da..dbbb01cfbee9c 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -28,7 +28,7 @@ struct sys_reg_params { u8 CRn; u8 CRm; u8 Op2; - u8 Rt; + u64 regval; bool is_write; bool is_aarch32; bool is_32bit; /* Only valid if is_aarch32 is true */ @@ -44,7 +44,7 @@ struct sys_reg_desc { /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, - const struct sys_reg_params *, + struct sys_reg_params *, const struct sys_reg_desc *); /* Initialization for vcpu. */ @@ -77,9 +77,9 @@ static inline bool ignore_write(struct kvm_vcpu *vcpu, } static inline bool read_zero(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p) + struct sys_reg_params *p) { - *vcpu_reg(vcpu, p->Rt) = 0; + p->regval = 0; return true; } diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c index 1e45768241655..ed90578fa120e 100644 --- a/arch/arm64/kvm/sys_regs_generic_v8.c +++ b/arch/arm64/kvm/sys_regs_generic_v8.c @@ -31,13 +31,13 @@ #include "sys_regs.h" static bool access_actlr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return ignore_write(vcpu, p); - *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1); + p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1); return true; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index b162ad70effcf..7658612d915ca 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -152,8 +152,6 @@ static void build_prologue(struct jit_ctx *ctx) const u8 r8 = bpf2a64[BPF_REG_8]; const u8 r9 = bpf2a64[BPF_REG_9]; const u8 fp = bpf2a64[BPF_REG_FP]; - const u8 ra = bpf2a64[BPF_REG_A]; - const u8 rx = bpf2a64[BPF_REG_X]; const u8 tmp1 = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; @@ -200,10 +198,6 @@ static void build_prologue(struct jit_ctx *ctx) /* Set up function call stack */ emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); - - /* Clear registers A and X */ - emit_a64_mov_i64(ra, 0, ctx); - emit_a64_mov_i64(rx, 0, ctx); } static void build_epilogue(struct jit_ctx *ctx) diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 2b65ed6b277ca..9de0796240a00 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -85,4 +85,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _UAPI__ASM_AVR32_SOCKET_H */ diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c index 1e9c8b0bf4866..170d786807c46 100644 --- a/arch/blackfin/kernel/perf_event.c +++ b/arch/blackfin/kernel/perf_event.c @@ -14,7 +14,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * * ppc: diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index 4823ad1255782..f02e4849ae838 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -85,5 +85,8 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index db73390568c8d..74c132d901bd2 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -11,7 +11,7 @@ -#define NR_syscalls 322 /* length of syscall table */ +#define NR_syscalls 323 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 59be3d87f86d6..bce29166de1bf 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -94,4 +94,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index 9038726e7d267..762edce7572eb 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -335,5 +335,6 @@ #define __NR_userfaultfd 1343 #define __NR_membarrier 1344 #define __NR_kcmp 1345 +#define __NR_mlock2 1346 #endif /* _UAPI_ASM_IA64_UNISTD_H */ diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index dcd97f84d0654..534a74acb849d 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1771,5 +1771,6 @@ sys_call_table: data8 sys_userfaultfd data8 sys_membarrier data8 sys_kcmp // 1345 + data8 sys_mlock2 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index fd104bd221ced..860e440611c98 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += clkdev.h generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h index 61b8931bc1925..4b0f5e001d4d5 100644 --- a/arch/m32r/include/asm/io.h +++ b/arch/m32r/include/asm/io.h @@ -168,13 +168,21 @@ static inline void _writel(unsigned long l, unsigned long addr) #define writew_relaxed writew #define writel_relaxed writel -#define ioread8 read +#define ioread8 readb #define ioread16 readw #define ioread32 readl #define iowrite8 writeb #define iowrite16 writew #define iowrite32 writel +#define ioread8_rep(p, dst, count) insb((unsigned long)(p), (dst), (count)) +#define ioread16_rep(p, dst, count) insw((unsigned long)(p), (dst), (count)) +#define ioread32_rep(p, dst, count) insl((unsigned long)(p), (dst), (count)) + +#define iowrite8_rep(p, src, count) outsb((unsigned long)(p), (src), (count)) +#define iowrite16_rep(p, src, count) outsw((unsigned long)(p), (src), (count)) +#define iowrite32_rep(p, src, count) outsl((unsigned long)(p), (src), (count)) + #define ioread16be(addr) be16_to_cpu(readw(addr)) #define ioread32be(addr) be32_to_cpu(readl(addr)) #define iowrite16be(v, addr) writew(cpu_to_be16(v), (addr)) diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 7bc4cb2738565..14aa4a6bccf12 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -85,4 +85,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index c89da63129545..bf4dec229437a 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -61,7 +61,8 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, /* FIXME this part of code is untested */ for_each_sg(sgl, sg, nents, i) { sg->dma_address = sg_phys(sg); - __dma_sync(sg_phys(sg), sg->length, direction); + __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, + sg->length, direction); } return nents; diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 5305d694ffe52..095ecafe6bd35 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -599,7 +599,7 @@ extern void __put_user_unknown(void); * On error, the variable @x is set to zero. */ #define __get_user_unaligned(x,ptr) \ - __get_user__unalignednocheck((x),(ptr),sizeof(*(ptr))) + __get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) /* * Yuck. We need two variants, one for 64bit operation and one @@ -620,8 +620,8 @@ extern void __get_user_unaligned_unknown(void); do { \ switch (size) { \ case 1: __get_data_asm(val, "lb", ptr); break; \ - case 2: __get_user_unaligned_asm(val, "ulh", ptr); break; \ - case 4: __get_user_unaligned_asm(val, "ulw", ptr); break; \ + case 2: __get_data_unaligned_asm(val, "ulh", ptr); break; \ + case 4: __get_data_unaligned_asm(val, "ulw", ptr); break; \ case 8: __GET_USER_UNALIGNED_DW(val, ptr); break; \ default: __get_user_unaligned_unknown(); break; \ } \ @@ -1122,9 +1122,15 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n); __cu_to = (to); \ __cu_from = (from); \ __cu_len = (n); \ - might_fault(); \ - __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \ - __cu_len); \ + if (eva_kernel_access()) { \ + __cu_len = __invoke_copy_from_kernel(__cu_to, \ + __cu_from, \ + __cu_len); \ + } else { \ + might_fault(); \ + __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \ + __cu_len); \ + } \ __cu_len; \ }) @@ -1229,16 +1235,28 @@ __clear_user(void __user *addr, __kernel_size_t size) { __kernel_size_t res; - might_fault(); - __asm__ __volatile__( - "move\t$4, %1\n\t" - "move\t$5, $0\n\t" - "move\t$6, %2\n\t" - __MODULE_JAL(__bzero) - "move\t%0, $6" - : "=r" (res) - : "r" (addr), "r" (size) - : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + if (eva_kernel_access()) { + __asm__ __volatile__( + "move\t$4, %1\n\t" + "move\t$5, $0\n\t" + "move\t$6, %2\n\t" + __MODULE_JAL(__bzero_kernel) + "move\t%0, $6" + : "=r" (res) + : "r" (addr), "r" (size) + : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + } else { + might_fault(); + __asm__ __volatile__( + "move\t$4, %1\n\t" + "move\t$5, $0\n\t" + "move\t$6, %2\n\t" + __MODULE_JAL(__bzero) + "move\t%0, $6" + : "=r" (res) + : "r" (addr), "r" (size) + : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + } return res; } @@ -1384,7 +1402,7 @@ static inline long strlen_user(const char __user *s) might_fault(); __asm__ __volatile__( "move\t$4, %1\n\t" - __MODULE_JAL(__strlen_kernel_asm) + __MODULE_JAL(__strlen_user_asm) "move\t%0, $2" : "=r" (res) : "r" (s) diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index dec3c850f36be..5910fe294e932 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -103,4 +103,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 8fd5a276cad23..ac81edd445631 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -257,7 +257,6 @@ LEAF(mips_cps_core_init) has_mt t0, 3f .set push - .set mips64r2 .set mt /* Only allow 1 TC per VPE to execute... */ @@ -376,7 +375,6 @@ LEAF(mips_cps_boot_vpes) nop .set push - .set mips64r2 .set mt 1: /* Enter VPE configuration state */ diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 291af0b5c4828..e2b6ab74643db 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -17,6 +17,7 @@ #include <asm/fpu.h> #include <asm/msa.h> +extern void *__bzero_kernel(void *__s, size_t __count); extern void *__bzero(void *__s, size_t __count); extern long __strncpy_from_kernel_nocheck_asm(char *__to, const char *__from, long __len); @@ -64,6 +65,7 @@ EXPORT_SYMBOL(__copy_from_user_eva); EXPORT_SYMBOL(__copy_in_user_eva); EXPORT_SYMBOL(__copy_to_user_eva); EXPORT_SYMBOL(__copy_user_inatomic_eva); +EXPORT_SYMBOL(__bzero_kernel); #endif EXPORT_SYMBOL(__bzero); EXPORT_SYMBOL(__strncpy_from_kernel_nocheck_asm); diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index b8e63fd003754..8f0019a2e5c84 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -283,6 +283,8 @@ LEAF(memset) 1: #ifndef CONFIG_EVA FEXPORT(__bzero) +#else +FEXPORT(__bzero_kernel) #endif __BUILD_BZERO LEGACY_MODE diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index d8117be729a20..730d394ce5f01 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size, gfp = massage_gfp_flags(dev, gfp); - if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC)) + if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp)) page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (!page) diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c index dbbeccc3d714a..a245cad4372a4 100644 --- a/arch/mips/pci/pci-rt2880.c +++ b/arch/mips/pci/pci-rt2880.c @@ -221,7 +221,6 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) static int rt288x_pci_probe(struct platform_device *pdev) { void __iomem *io_map_base; - int i; rt2880_pci_base = ioremap_nocache(RT2880_PCI_BASE, PAGE_SIZE); diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c index 78b2ef49dbc7a..9d293b3e91301 100644 --- a/arch/mips/pmcs-msp71xx/msp_setup.c +++ b/arch/mips/pmcs-msp71xx/msp_setup.c @@ -39,7 +39,6 @@ extern void msp_serial_setup(void); void msp7120_reset(void) { void *start, *end, *iptr; - register int i; /* Diasble all interrupts */ local_irq_disable(); diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c index db8f88b6a3af9..6afa34346b814 100644 --- a/arch/mips/sni/reset.c +++ b/arch/mips/sni/reset.c @@ -26,7 +26,7 @@ static inline void kb_wait(void) /* XXX This ends up at the ARC firmware prompt ... */ void sni_machine_restart(char *command) { - int i, j; + int i; /* This does a normal via the keyboard controller like a PC. We can do that easier ... */ diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index ef5f348f386a1..018f8c7b94f2a 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -26,8 +26,8 @@ aflags-vdso := $(ccflags-vdso) \ # the comments on that file. # ifndef CONFIG_CPU_MIPSR6 - ifeq ($(call ld-ifversion, -gt, 22400000, y),) - $(warning MIPS VDSO requires binutils > 2.24) + ifeq ($(call ld-ifversion, -lt, 22500000, y),) + $(warning MIPS VDSO requires binutils >= 2.25) obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO endif diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index cab7d6d50051b..58b1aa01ab9f1 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -85,4 +85,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index d8534f95915a3..291cee28ccb60 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -372,7 +372,8 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; } */ #ifdef CONFIG_HUGETLB_PAGE #define pte_huge(pte) (pte_val(pte) & _PAGE_HUGE) -#define pte_mkhuge(pte) (__pte(pte_val(pte) | _PAGE_HUGE)) +#define pte_mkhuge(pte) (__pte(pte_val(pte) | \ + (parisc_requires_coherency() ? 0 : _PAGE_HUGE))) #else #define pte_huge(pte) (0) #define pte_mkhuge(pte) (pte) diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index a5cd40cd8ee1c..f9cf1223422ce 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -84,4 +84,7 @@ #define SO_ATTACH_BPF 0x402B #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 0x402C +#define SO_ATTACH_REUSEPORT_EBPF 0x402D + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 33170384d3ac1..35bdccbb20362 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -360,8 +360,9 @@ #define __NR_execveat (__NR_Linux + 342) #define __NR_membarrier (__NR_Linux + 343) #define __NR_userfaultfd (__NR_Linux + 344) +#define __NR_mlock2 (__NR_Linux + 345) -#define __NR_Linux_syscalls (__NR_userfaultfd + 1) +#define __NR_Linux_syscalls (__NR_mlock2 + 1) #define __IGNORE_select /* newselect */ diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c index 64f2764a8cef8..c99f3dde455ce 100644 --- a/arch/parisc/kernel/pci.c +++ b/arch/parisc/kernel/pci.c @@ -171,24 +171,6 @@ void pcibios_set_master(struct pci_dev *dev) } -void __init pcibios_init_bus(struct pci_bus *bus) -{ - struct pci_dev *dev = bus->self; - unsigned short bridge_ctl; - - /* We deal only with pci controllers and pci-pci bridges. */ - if (!dev || (dev->class >> 8) != PCI_CLASS_BRIDGE_PCI) - return; - - /* PCI-PCI bridge - set the cache line and default latency - (32) for primary and secondary buses. */ - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, 32); - - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bridge_ctl); - bridge_ctl |= PCI_BRIDGE_CTL_PARITY | PCI_BRIDGE_CTL_SERR; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bridge_ctl); -} - /* * pcibios align resources() is called every time generic PCI code * wants to generate a new address. The process of looking for diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index dc1ea796fd605..2264f68f3c2f9 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -435,6 +435,55 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs, int in_syscall) regs->gr[28]); } +/* + * Check how the syscall number gets loaded into %r20 within + * the delay branch in userspace and adjust as needed. + */ + +static void check_syscallno_in_delay_branch(struct pt_regs *regs) +{ + u32 opcode, source_reg; + u32 __user *uaddr; + int err; + + /* Usually we don't have to restore %r20 (the system call number) + * because it gets loaded in the delay slot of the branch external + * instruction via the ldi instruction. + * In some cases a register-to-register copy instruction might have + * been used instead, in which case we need to copy the syscall + * number into the source register before returning to userspace. + */ + + /* A syscall is just a branch, so all we have to do is fiddle the + * return pointer so that the ble instruction gets executed again. + */ + regs->gr[31] -= 8; /* delayed branching */ + + /* Get assembler opcode of code in delay branch */ + uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4); + err = get_user(opcode, uaddr); + if (err) + return; + + /* Check if delay branch uses "ldi int,%r20" */ + if ((opcode & 0xffff0000) == 0x34140000) + return; /* everything ok, just return */ + + /* Check if delay branch uses "nop" */ + if (opcode == INSN_NOP) + return; + + /* Check if delay branch uses "copy %rX,%r20" */ + if ((opcode & 0xffe0ffff) == 0x08000254) { + source_reg = (opcode >> 16) & 31; + regs->gr[source_reg] = regs->gr[20]; + return; + } + + pr_warn("syscall restart: %s (pid %d): unexpected opcode 0x%08x\n", + current->comm, task_pid_nr(current), opcode); +} + static inline void syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) { @@ -457,10 +506,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) } /* fallthrough */ case -ERESTARTNOINTR: - /* A syscall is just a branch, so all - * we have to do is fiddle the return pointer. - */ - regs->gr[31] -= 8; /* delayed branching */ + check_syscallno_in_delay_branch(regs); break; } } @@ -510,15 +556,9 @@ insert_restart_trampoline(struct pt_regs *regs) } case -ERESTARTNOHAND: case -ERESTARTSYS: - case -ERESTARTNOINTR: { - /* Hooray for delayed branching. We don't - * have to restore %r20 (the system call - * number) because it gets loaded in the delay - * slot of the branch external instruction. - */ - regs->gr[31] -= 8; + case -ERESTARTNOINTR: + check_syscallno_in_delay_branch(regs); return; - } default: break; } diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 78c3ef8c348d5..d4ffcfbc98851 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -440,6 +440,7 @@ ENTRY_COMP(execveat) ENTRY_SAME(membarrier) ENTRY_SAME(userfaultfd) + ENTRY_SAME(mlock2) /* 345 */ .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) diff --git a/arch/powerpc/boot/dts/sbc8641d.dts b/arch/powerpc/boot/dts/sbc8641d.dts index 631ede72e226c..68f0ed7626bd9 100644 --- a/arch/powerpc/boot/dts/sbc8641d.dts +++ b/arch/powerpc/boot/dts/sbc8641d.dts @@ -227,23 +227,15 @@ reg = <0x520 0x20>; phy0: ethernet-phy@1f { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <0x1f>; }; phy1: ethernet-phy@0 { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <0>; }; phy2: ethernet-phy@1 { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <1>; }; phy3: ethernet-phy@2 { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <2>; }; tbi0: tbi-phy@11 { diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 85bc8c0d257b7..e3b54dd4f7307 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -258,11 +258,16 @@ #define H_DEL_CONN 0x288 #define H_JOIN 0x298 #define H_VASI_STATE 0x2A4 +#define H_VIOCTL 0x2A8 #define H_ENABLE_CRQ 0x2B0 #define H_GET_EM_PARMS 0x2B8 #define H_SET_MPP 0x2D0 #define H_GET_MPP 0x2D4 +#define H_REG_SUB_CRQ 0x2DC #define H_HOME_NODE_ASSOCIATIVITY 0x2EC +#define H_FREE_SUB_CRQ 0x2E0 +#define H_SEND_SUB_CRQ 0x2E4 +#define H_SEND_SUB_CRQ_INDIRECT 0x2E8 #define H_BEST_ENERGY 0x2F4 #define H_XIRR_X 0x2FC #define H_RANDOM 0x300 @@ -271,6 +276,21 @@ #define H_SET_MODE 0x31C #define MAX_HCALL_OPCODE H_SET_MODE +/* H_VIOCTL functions */ +#define H_GET_VIOA_DUMP_SIZE 0x01 +#define H_GET_VIOA_DUMP 0x02 +#define H_GET_ILLAN_NUM_VLAN_IDS 0x03 +#define H_GET_ILLAN_VLAN_ID_LIST 0x04 +#define H_GET_ILLAN_SWITCH_ID 0x05 +#define H_DISABLE_MIGRATION 0x06 +#define H_ENABLE_MIGRATION 0x07 +#define H_GET_PARTNER_INFO 0x08 +#define H_GET_PARTNER_WWPN_LIST 0x09 +#define H_DISABLE_ALL_VIO_INTS 0x0A +#define H_DISABLE_VIO_INTERRUPT 0x0B +#define H_ENABLE_VIO_INTERRUPT 0x0C + + /* Platform specific hcalls, used by KVM */ #define H_RTAS 0xf000 diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index f2b0b1b0c72ac..5654ece02c0db 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -370,16 +370,16 @@ COMPAT_SYS(execveat) PPC64ONLY(switch_endian) SYSCALL_SPU(userfaultfd) SYSCALL_SPU(membarrier) -SYSCALL(semop) -SYSCALL(semget) -COMPAT_SYS(semctl) -COMPAT_SYS(semtimedop) -COMPAT_SYS(msgsnd) -COMPAT_SYS(msgrcv) -SYSCALL(msgget) -COMPAT_SYS(msgctl) -COMPAT_SYS(shmat) -SYSCALL(shmdt) -SYSCALL(shmget) -COMPAT_SYS(shmctl) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) SYSCALL(mlock2) diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index c046666038f85..dd54f28ecdeca 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -92,4 +92,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 1effea5193d68..12a05652377a2 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -388,18 +388,6 @@ #define __NR_switch_endian 363 #define __NR_userfaultfd 364 #define __NR_membarrier 365 -#define __NR_semop 366 -#define __NR_semget 367 -#define __NR_semctl 368 -#define __NR_semtimedop 369 -#define __NR_msgsnd 370 -#define __NR_msgrcv 371 -#define __NR_msgget 372 -#define __NR_msgctl 373 -#define __NR_shmat 374 -#define __NR_shmdt 375 -#define __NR_shmget 376 -#define __NR_shmctl 377 #define __NR_mlock2 378 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 80dfe8965df9f..8d14feb40f121 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -590,16 +590,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); - /* - * If it's PHB PE, the frozen state on all available PEs should have - * been cleared by the PHB reset. Otherwise, we unfreeze the PE and its - * child PEs because they might be in frozen state. - */ - if (!(pe->type & EEH_PE_PHB)) { - rc = eeh_clear_pe_frozen_state(pe, false); - if (rc) - return rc; - } + /* Clear frozen state */ + rc = eeh_clear_pe_frozen_state(pe, false); + if (rc) + return rc; /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 54b45b73195f9..a7352b59e6f9b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -224,6 +224,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) { + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; vcpu->arch.shregs.msr = msr; kvmppc_end_cede(vcpu); } diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index 6ccfb6c1c707b..e505223b4ec5e 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -43,11 +43,34 @@ static unsigned int opal_irq_count; static unsigned int *opal_irqs; static void opal_handle_irq_work(struct irq_work *work); -static __be64 last_outstanding_events; +static u64 last_outstanding_events; static struct irq_work opal_event_irq_work = { .func = opal_handle_irq_work, }; +void opal_handle_events(uint64_t events) +{ + int virq, hwirq = 0; + u64 mask = opal_event_irqchip.mask; + + if (!in_irq() && (events & mask)) { + last_outstanding_events = events; + irq_work_queue(&opal_event_irq_work); + return; + } + + while (events & mask) { + hwirq = fls64(events) - 1; + if (BIT_ULL(hwirq) & mask) { + virq = irq_find_mapping(opal_event_irqchip.domain, + hwirq); + if (virq) + generic_handle_irq(virq); + } + events &= ~BIT_ULL(hwirq); + } +} + static void opal_event_mask(struct irq_data *d) { clear_bit(d->hwirq, &opal_event_irqchip.mask); @@ -55,9 +78,21 @@ static void opal_event_mask(struct irq_data *d) static void opal_event_unmask(struct irq_data *d) { + __be64 events; + set_bit(d->hwirq, &opal_event_irqchip.mask); - opal_poll_events(&last_outstanding_events); + opal_poll_events(&events); + last_outstanding_events = be64_to_cpu(events); + + /* + * We can't just handle the events now with opal_handle_events(). + * If we did we would deadlock when opal_event_unmask() is called from + * handle_level_irq() with the irq descriptor lock held, because + * calling opal_handle_events() would call generic_handle_irq() and + * then handle_level_irq() which would try to take the descriptor lock + * again. Instead queue the events for later. + */ if (last_outstanding_events & opal_event_irqchip.mask) /* Need to retrigger the interrupt */ irq_work_queue(&opal_event_irq_work); @@ -96,29 +131,6 @@ static int opal_event_map(struct irq_domain *d, unsigned int irq, return 0; } -void opal_handle_events(uint64_t events) -{ - int virq, hwirq = 0; - u64 mask = opal_event_irqchip.mask; - - if (!in_irq() && (events & mask)) { - last_outstanding_events = events; - irq_work_queue(&opal_event_irq_work); - return; - } - - while (events & mask) { - hwirq = fls64(events) - 1; - if (BIT_ULL(hwirq) & mask) { - virq = irq_find_mapping(opal_event_irqchip.domain, - hwirq); - if (virq) - generic_handle_irq(virq); - } - events &= ~BIT_ULL(hwirq); - } -} - static irqreturn_t opal_interrupt(int irq, void *data) { __be64 events; @@ -131,7 +143,7 @@ static irqreturn_t opal_interrupt(int irq, void *data) static void opal_handle_irq_work(struct irq_work *work) { - opal_handle_events(be64_to_cpu(last_outstanding_events)); + opal_handle_events(last_outstanding_events); } static int opal_event_match(struct irq_domain *h, struct device_node *node, diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 4296d55e88f30..57cffb80bc36a 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -278,7 +278,7 @@ static void opal_handle_message(void) /* Sanity check */ if (type >= OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Unknown message type: %u\n", __func__, type); + pr_warn_once("%s: Unknown message type: %u\n", __func__, type); return; } opal_message_do_notify(type, (void *)&msg); diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 296942d56e6a0..d02e89d14fefe 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -91,4 +91,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 8140d10c67850..6e72961608f0d 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1920,16 +1920,23 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) } if (separator) ptr += sprintf(ptr, "%c", separator); + /* + * Use four '%' characters below because of the + * following two conversions: + * + * 1) sprintf: %%%%r -> %%r + * 2) printk : %%r -> %r + */ if (operand->flags & OPERAND_GPR) - ptr += sprintf(ptr, "%%r%i", value); + ptr += sprintf(ptr, "%%%%r%i", value); else if (operand->flags & OPERAND_FPR) - ptr += sprintf(ptr, "%%f%i", value); + ptr += sprintf(ptr, "%%%%f%i", value); else if (operand->flags & OPERAND_AR) - ptr += sprintf(ptr, "%%a%i", value); + ptr += sprintf(ptr, "%%%%a%i", value); else if (operand->flags & OPERAND_CR) - ptr += sprintf(ptr, "%%c%i", value); + ptr += sprintf(ptr, "%%%%c%i", value); else if (operand->flags & OPERAND_VR) - ptr += sprintf(ptr, "%%v%i", value); + ptr += sprintf(ptr, "%%%%v%i", value); else if (operand->flags & OPERAND_PCREL) ptr += sprintf(ptr, "%lx", (signed int) value + addr); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9a0c4c22e5367..3c0bfc1f26941 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -408,7 +408,7 @@ static void emit_load_skb_data_hlen(struct bpf_jit *jit) * Save registers and create stack frame if necessary. * See stack frame layout desription in "bpf_jit.h"! */ -static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic) +static void bpf_jit_prologue(struct bpf_jit *jit) { if (jit->seen & SEEN_TAIL_CALL) { /* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */ @@ -448,15 +448,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic) /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_SKBP); - /* Clear A (%b0) and X (%b7) registers for converted BPF programs */ - if (is_classic) { - if (REG_SEEN(BPF_REG_A)) - /* lghi %ba,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_A, 0); - if (REG_SEEN(BPF_REG_X)) - /* lghi %bx,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_X, 0); - } } /* @@ -1245,7 +1236,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) jit->lit = jit->lit_start; jit->prg = 0; - bpf_jit_prologue(jit, bpf_prog_was_classic(fp)); + bpf_jit_prologue(jit); for (i = 0; i < fp->len; i += insn_count) { insn_count = bpf_jit_insn(jit, fp, i); if (insn_count < 0) diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h index e6820c86e8c7b..47ebd5b5ed55e 100644 --- a/arch/sh/include/uapi/asm/unistd_64.h +++ b/arch/sh/include/uapi/asm/unistd_64.h @@ -278,7 +278,7 @@ #define __NR_fsetxattr 256 #define __NR_getxattr 257 #define __NR_lgetxattr 258 -#define __NR_fgetxattr 269 +#define __NR_fgetxattr 259 #define __NR_listxattr 260 #define __NR_llistxattr 261 #define __NR_flistxattr 262 diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7cfd7f1539667..4dca18347ee9a 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -10,7 +10,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * * ppc: diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h index 370ca1e71ffbc..93310837c2dfa 100644 --- a/arch/sparc/include/asm/elf_64.h +++ b/arch/sparc/include/asm/elf_64.h @@ -95,6 +95,7 @@ * really available. So we simply advertise only "crypto" support. */ #define HWCAP_SPARC_CRYPTO 0x04000000 /* CRYPTO insns available */ +#define HWCAP_SPARC_ADI 0x08000000 /* ADI available */ #define CORE_DUMP_USE_REGSET diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index e6a16c40be5f0..d270ee91968e5 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -81,6 +81,9 @@ #define SO_ATTACH_BPF 0x0034 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 0x0035 +#define SO_ATTACH_REUSEPORT_EBPF 0x0036 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index efe9479f837bb..1c26d440d288d 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -417,8 +417,13 @@ #define __NR_bpf 349 #define __NR_execveat 350 #define __NR_membarrier 351 +#define __NR_userfaultfd 352 +#define __NR_bind 353 +#define __NR_listen 354 +#define __NR_setsockopt 355 +#define __NR_mlock2 356 -#define NR_syscalls 352 +#define NR_syscalls 357 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 3d61fcae7ee38..f2d30cab5b3f3 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -946,6 +946,12 @@ ENTRY(__retl_one) mov 1, %o0 ENDPROC(__retl_one) +ENTRY(__retl_one_fp) + VISExitHalf + retl + mov 1, %o0 +ENDPROC(__retl_one_fp) + ENTRY(__ret_one_asi) wr %g0, ASI_AIUS, %asi ret @@ -958,6 +964,13 @@ ENTRY(__retl_one_asi) mov 1, %o0 ENDPROC(__retl_one_asi) +ENTRY(__retl_one_asi_fp) + wr %g0, ASI_AIUS, %asi + VISExitHalf + retl + mov 1, %o0 +ENDPROC(__retl_one_asi_fp) + ENTRY(__retl_o1) retl mov %o1, %o0 diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b0da5aedb336c..6596f66ce1126 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -9,7 +9,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra */ #include <linux/perf_event.h> @@ -1828,11 +1828,18 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { + u64 saved_fault_address = current_thread_info()->fault_address; + u8 saved_fault_code = get_thread_fault_code(); + mm_segment_t old_fs; + perf_callchain_store(entry, regs->tpc); if (!current->mm) return; + old_fs = get_fs(); + set_fs(USER_DS); + flushw_user(); pagefault_disable(); @@ -1843,4 +1850,8 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_user_64(entry, regs); pagefault_enable(); + + set_fs(old_fs); + set_thread_fault_code(saved_fault_code); + current_thread_info()->fault_address = saved_fault_address; } diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 39f0c662f4c81..d08bdaffdbfcc 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -73,7 +73,13 @@ rtrap_nmi: ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 andn %l1, %l4, %l1 srl %l4, 20, %l4 ba,pt %xcc, rtrap_no_irq_enable - wrpr %l4, %pil + nop + /* Do not actually set the %pil here. We will do that + * below after we clear PSTATE_IE in the %pstate register. + * If we re-enable interrupts here, we can recurse down + * the hardirq stack potentially endlessly, causing a + * stack overflow. + */ .align 64 .globl rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index f7b261749383b..f3185e2b028b8 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -380,7 +380,8 @@ static const char *hwcaps[] = { */ "mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2", "ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau", - "ima", "cspare", "pause", "cbcond", + "ima", "cspare", "pause", "cbcond", NULL /*reserved for crypto */, + "adp", }; static const char *crypto_hwcaps[] = { @@ -396,7 +397,7 @@ void cpucap_info(struct seq_file *m) seq_puts(m, "cpucaps\t\t: "); for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (caps & bit) { + if (hwcaps[i] && (caps & bit)) { seq_printf(m, "%s%s", printed ? "," : "", hwcaps[i]); printed++; @@ -450,7 +451,7 @@ static void __init report_hwcaps(unsigned long caps) for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (caps & bit) + if (hwcaps[i] && (caps & bit)) report_one_hwcap(&printed, hwcaps[i]); } if (caps & HWCAP_SPARC_CRYPTO) @@ -485,7 +486,7 @@ static unsigned long __init mdesc_cpu_hwcap_list(void) for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (!strcmp(prop, hwcaps[i])) { + if (hwcaps[i] && !strcmp(prop, hwcaps[i])) { caps |= bit; break; } diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index cc23b62b6e38a..e663b6c78de2e 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -35,18 +35,18 @@ sys_call_table: /*80*/ .long sys_setgroups16, sys_getpgrp, sys_setgroups, sys_setitimer, sys_ftruncate64 /*85*/ .long sys_swapon, sys_getitimer, sys_setuid, sys_sethostname, sys_setgid /*90*/ .long sys_dup2, sys_setfsuid, sys_fcntl, sys_select, sys_setfsgid -/*95*/ .long sys_fsync, sys_setpriority, sys_nis_syscall, sys_nis_syscall, sys_nis_syscall +/*95*/ .long sys_fsync, sys_setpriority, sys_socket, sys_connect, sys_accept /*100*/ .long sys_getpriority, sys_rt_sigreturn, sys_rt_sigaction, sys_rt_sigprocmask, sys_rt_sigpending /*105*/ .long sys_rt_sigtimedwait, sys_rt_sigqueueinfo, sys_rt_sigsuspend, sys_setresuid, sys_getresuid -/*110*/ .long sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall -/*115*/ .long sys_getgroups, sys_gettimeofday, sys_getrusage, sys_nis_syscall, sys_getcwd +/*110*/ .long sys_setresgid, sys_getresgid, sys_setregid, sys_recvmsg, sys_sendmsg +/*115*/ .long sys_getgroups, sys_gettimeofday, sys_getrusage, sys_getsockopt, sys_getcwd /*120*/ .long sys_readv, sys_writev, sys_settimeofday, sys_fchown16, sys_fchmod -/*125*/ .long sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate -/*130*/ .long sys_ftruncate, sys_flock, sys_lstat64, sys_nis_syscall, sys_nis_syscall -/*135*/ .long sys_nis_syscall, sys_mkdir, sys_rmdir, sys_utimes, sys_stat64 -/*140*/ .long sys_sendfile64, sys_nis_syscall, sys_futex, sys_gettid, sys_getrlimit +/*125*/ .long sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate +/*130*/ .long sys_ftruncate, sys_flock, sys_lstat64, sys_sendto, sys_shutdown +/*135*/ .long sys_socketpair, sys_mkdir, sys_rmdir, sys_utimes, sys_stat64 +/*140*/ .long sys_sendfile64, sys_getpeername, sys_futex, sys_gettid, sys_getrlimit /*145*/ .long sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write -/*150*/ .long sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 +/*150*/ .long sys_getsockname, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 /*155*/ .long sys_fcntl64, sys_inotify_rm_watch, sys_statfs, sys_fstatfs, sys_oldumount /*160*/ .long sys_sched_setaffinity, sys_sched_getaffinity, sys_getdomainname, sys_setdomainname, sys_nis_syscall /*165*/ .long sys_quotactl, sys_set_tid_address, sys_mount, sys_ustat, sys_setxattr @@ -87,4 +87,5 @@ sys_call_table: /*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .long sys_execveat, sys_membarrier +/*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen +/*355*/ .long sys_setsockopt, sys_mlock2 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f229468a74797..1557121f4cdce 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -37,15 +37,15 @@ sys_call_table32: /*80*/ .word sys_setgroups16, sys_getpgrp, sys_setgroups, compat_sys_setitimer, sys32_ftruncate64 .word sys_swapon, compat_sys_getitimer, sys_setuid, sys_sethostname, sys_setgid /*90*/ .word sys_dup2, sys_setfsuid, compat_sys_fcntl, sys32_select, sys_setfsgid - .word sys_fsync, sys_setpriority, sys_nis_syscall, sys_nis_syscall, sys_nis_syscall + .word sys_fsync, sys_setpriority, sys_socket, sys_connect, sys_accept /*100*/ .word sys_getpriority, sys32_rt_sigreturn, compat_sys_rt_sigaction, compat_sys_rt_sigprocmask, compat_sys_rt_sigpending .word compat_sys_rt_sigtimedwait, compat_sys_rt_sigqueueinfo, compat_sys_rt_sigsuspend, sys_setresuid, sys_getresuid -/*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall - .word sys_getgroups, compat_sys_gettimeofday, compat_sys_getrusage, sys_nis_syscall, sys_getcwd +/*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, compat_sys_recvmsg, compat_sys_sendmsg + .word sys_getgroups, compat_sys_gettimeofday, compat_sys_getrusage, compat_sys_getsockopt, sys_getcwd /*120*/ .word compat_sys_readv, compat_sys_writev, compat_sys_settimeofday, sys_fchown16, sys_fchmod - .word sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate -/*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_nis_syscall, sys_nis_syscall - .word sys_nis_syscall, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 + .word sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate +/*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_sendto, sys_shutdown + .word sys_socketpair, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 /*140*/ .word sys_sendfile64, sys_nis_syscall, sys32_futex, sys_gettid, compat_sys_getrlimit .word compat_sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write /*150*/ .word sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 @@ -88,7 +88,8 @@ sys_call_table32: .word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .word sys32_execveat, sys_membarrier +/*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen + .word compat_sys_setsockopt, sys_mlock2 #endif /* CONFIG_COMPAT */ @@ -168,4 +169,5 @@ sys_call_table: .word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .word sys64_execveat, sys_membarrier +/*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen + .word sys_setsockopt, sys_mlock2 diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index 119ccb9a54f49..d5242b8c4f949 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index 7fe1ccefd9d05..4e962d993b10c 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index 30eee6e8a81b2..d5f585df2f3fc 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -34,10 +34,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -134,40 +140,40 @@ fsrc2 %x6, %f12; \ fsrc2 %x7, %f14; #define FREG_LOAD_1(base, x0) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)) + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)) #define FREG_LOAD_2(base, x0, x1) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); #define FREG_LOAD_3(base, x0, x1, x2) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); #define FREG_LOAD_4(base, x0, x1, x2, x3) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD(LOAD(ldd, base + 0x28, %x5)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD(LOAD(ldd, base + 0x28, %x5)); \ - EX_LD(LOAD(ldd, base + 0x30, %x6)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \ + EX_LD_FP(LOAD(ldd, base + 0x30, %x6)); .register %g2,#scratch .register %g3,#scratch @@ -275,11 +281,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop /* fall through for 0 < low bits < 8 */ 110: sub %o4, 64, %g2 - EX_LD(LOAD_BLK(%g2, %f0)) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) + EX_LD_FP(LOAD_BLK(%g2, %f0)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -290,10 +296,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 120: sub %o4, 56, %g2 FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -304,10 +310,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 130: sub %o4, 48, %g2 FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_6(f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -318,10 +324,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 140: sub %o4, 40, %g2 FREG_LOAD_5(%g2, f0, f2, f4, f6, f8) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_5(f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -332,10 +338,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 150: sub %o4, 32, %g2 FREG_LOAD_4(%g2, f0, f2, f4, f6) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_4(f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -346,10 +352,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 160: sub %o4, 24, %g2 FREG_LOAD_3(%g2, f0, f2, f4) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_3(f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -360,10 +366,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 170: sub %o4, 16, %g2 FREG_LOAD_2(%g2, f0, f2) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_2(f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -374,10 +380,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 180: sub %o4, 8, %g2 FREG_LOAD_1(%g2, f0) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_1(f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -387,10 +393,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop 190: -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) subcc %g1, 64, %g1 - EX_LD(LOAD_BLK(%o4, %f0)) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f0)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) add %o4, 64, %o4 bne,pt %xcc, 1b LOAD(prefetch, %o4 + 64, #one_read) diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S index fd9f903ffa326..2e8ee7ad07a9c 100644 --- a/arch/sparc/lib/NG4copy_from_user.S +++ b/arch/sparc/lib/NG4copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S index 9744c4540a8d9..be0bf4590df89 100644 --- a/arch/sparc/lib/NG4copy_to_user.S +++ b/arch/sparc/lib/NG4copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 83aeeb1dffdb3..8e13ee1f4454e 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -48,10 +48,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -210,17 +216,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %o4, %o2 alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 - EX_LD(LOAD(ldd, %g1 + 0x00, %f0)) -1: EX_LD(LOAD(ldd, %g1 + 0x08, %f2)) + EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0)) +1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2)) subcc %o4, 0x40, %o4 - EX_LD(LOAD(ldd, %g1 + 0x10, %f4)) - EX_LD(LOAD(ldd, %g1 + 0x18, %f6)) - EX_LD(LOAD(ldd, %g1 + 0x20, %f8)) - EX_LD(LOAD(ldd, %g1 + 0x28, %f10)) - EX_LD(LOAD(ldd, %g1 + 0x30, %f12)) - EX_LD(LOAD(ldd, %g1 + 0x38, %f14)) + EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4)) + EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6)) + EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8)) + EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10)) + EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12)) + EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14)) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %g1 + 0x40, %f0)) + EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0)) faligndata %f2, %f4, %f18 add %g1, 0x40, %g1 faligndata %f4, %f6, %f20 @@ -229,14 +235,14 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST(STORE(std, %f16, %o0 + 0x00)) - EX_ST(STORE(std, %f18, %o0 + 0x08)) - EX_ST(STORE(std, %f20, %o0 + 0x10)) - EX_ST(STORE(std, %f22, %o0 + 0x18)) - EX_ST(STORE(std, %f24, %o0 + 0x20)) - EX_ST(STORE(std, %f26, %o0 + 0x28)) - EX_ST(STORE(std, %f28, %o0 + 0x30)) - EX_ST(STORE(std, %f30, %o0 + 0x38)) + EX_ST_FP(STORE(std, %f16, %o0 + 0x00)) + EX_ST_FP(STORE(std, %f18, %o0 + 0x08)) + EX_ST_FP(STORE(std, %f20, %o0 + 0x10)) + EX_ST_FP(STORE(std, %f22, %o0 + 0x18)) + EX_ST_FP(STORE(std, %f24, %o0 + 0x20)) + EX_ST_FP(STORE(std, %f26, %o0 + 0x28)) + EX_ST_FP(STORE(std, %f28, %o0 + 0x30)) + EX_ST_FP(STORE(std, %f30, %o0 + 0x38)) add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index a6ae2ea04bf5d..ecc5692fa2b49 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME ___copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_AIUS, dest diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index f4b970eeb485f..9eea392e44d47 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME ___copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S index b67142b7768e5..3e6209ebb7d78 100644 --- a/arch/sparc/lib/U1memcpy.S +++ b/arch/sparc/lib/U1memcpy.S @@ -25,10 +25,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -73,8 +79,8 @@ faligndata %f8, %f9, %f62; #define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \ - EX_LD(LOAD_BLK(%src, %fdest)); \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_LD_FP(LOAD_BLK(%src, %fdest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %src, 0x40, %src; \ subcc %len, 0x40, %len; \ be,pn %xcc, jmptgt; \ @@ -89,12 +95,12 @@ #define DO_SYNC membar #Sync; #define STORE_SYNC(dest, fsrc) \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %dest, 0x40, %dest; \ DO_SYNC #define STORE_JUMP(dest, fsrc, target) \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %dest, 0x40, %dest; \ ba,pt %xcc, target; \ nop; @@ -103,7 +109,7 @@ subcc %left, 8, %left;\ bl,pn %xcc, 95f; \ faligndata %f0, %f1, %f48; \ - EX_ST(STORE(std, %f48, %dest)); \ + EX_ST_FP(STORE(std, %f48, %dest)); \ add %dest, 8, %dest; #define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ @@ -160,8 +166,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) + EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -172,20 +178,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD(LOAD(ldd, %o1, %f4)) -1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -208,13 +214,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %g1, %GLOBAL_SPARE, %g1 subcc %o2, %g3, %o2 - EX_LD(LOAD_BLK(%o1, %f0)) + EX_LD_FP(LOAD_BLK(%o1, %f0)) add %o1, 0x40, %o1 add %g1, %g3, %g1 - EX_LD(LOAD_BLK(%o1, %f16)) + EX_LD_FP(LOAD_BLK(%o1, %f16)) add %o1, 0x40, %o1 sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE - EX_LD(LOAD_BLK(%o1, %f32)) + EX_LD_FP(LOAD_BLK(%o1, %f32)) add %o1, 0x40, %o1 /* There are 8 instances of the unrolled loop, @@ -426,28 +432,28 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 62: FINISH_VISCHUNK(o0, f44, f46, g3) 63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3) -93: EX_LD(LOAD(ldd, %o1, %f2)) +93: EX_LD_FP(LOAD(ldd, %o1, %f2)) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f0, %f2, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bl,pn %xcc, 95f add %o0, 8, %o0 - EX_LD(LOAD(ldd, %o1, %f0)) + EX_LD_FP(LOAD(ldd, %o1, %f0)) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f2, %f0, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bge,pt %xcc, 93b add %o0, 8, %o0 95: brz,pt %o2, 2f mov %g1, %o1 -1: EX_LD(LOAD(ldub, %o1, %o3)) +1: EX_LD_FP(LOAD(ldub, %o1, %o3)) add %o1, 1, %o1 subcc %o2, 1, %o2 - EX_ST(STORE(stb, %o3, %o0)) + EX_ST_FP(STORE(stb, %o3, %o0)) bne,pt %xcc, 1b add %o0, 1, %o0 diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S index b1acd1331c338..88ad73d86fe44 100644 --- a/arch/sparc/lib/U3copy_from_user.S +++ b/arch/sparc/lib/U3copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME U3copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define EX_RETVAL(x) 0 diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index ef1e493afdfa9..845139d755372 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME U3copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S index 7cae9cc6a204a..491ee69e49951 100644 --- a/arch/sparc/lib/U3memcpy.S +++ b/arch/sparc/lib/U3memcpy.S @@ -24,10 +24,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -120,8 +126,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) + EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -132,20 +138,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD(LOAD(ldd, %o1, %f4)) -1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f2 - EX_ST(STORE(std, %f2, %o0)) + EX_ST_FP(STORE(std, %f2, %o0)) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -155,25 +161,25 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ LOAD(prefetch, %o1 + 0x080, #one_read) LOAD(prefetch, %o1 + 0x0c0, #one_read) LOAD(prefetch, %o1 + 0x100, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x000, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0)) LOAD(prefetch, %o1 + 0x140, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) LOAD(prefetch, %o1 + 0x180, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) faligndata %f8, %f10, %f24 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f10, %f12, %f26 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE add %o1, 0x40, %o1 @@ -184,26 +190,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) faligndata %f12, %f14, %f28 - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f0, %f2, %f16 add %o0, 0x40, %o0 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) subcc %o3, 0x01, %o3 faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f8, %f10, %f24 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f10, %f12, %f26 bg,pt %XCC, 1b @@ -211,29 +217,29 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ /* Finally we copy the last full 64-byte block. */ 2: - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) faligndata %f12, %f14, %f28 - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f8, %f10, %f24 cmp %g1, 0 be,pt %XCC, 1f add %o0, 0x40, %o0 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) 1: faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) + EX_ST_FP(STORE_BLK(%f16, %o0)) add %o0, 0x40, %o0 add %o1, 0x40, %o1 membar #Sync @@ -253,20 +259,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g2, %o2 be,a,pt %XCC, 1f - EX_LD(LOAD(ldd, %o1 + 0x00, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0)) -1: EX_LD(LOAD(ldd, %o1 + 0x08, %f2)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f0, %f2, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) be,pn %XCC, 2f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x08, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f2, %f0, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bne,pn %XCC, 1b add %o0, 0x8, %o0 diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c index bb509cee3b598..8767060d70fb3 100644 --- a/arch/tile/kernel/perf_event.c +++ b/arch/tile/kernel/perf_event.c @@ -21,7 +21,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian */ diff --git a/arch/um/Makefile b/arch/um/Makefile index 25ed4098640ee..e3abe6f3156d3 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -131,7 +131,7 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT) # The wrappers will select whether using "malloc" or the kernel allocator. LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc -LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt +LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) # Used by link-vmlinux.sh which has special support for um link export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c index e697a4136707e..e9f8445861dc7 100644 --- a/arch/um/drivers/net_user.c +++ b/arch/um/drivers/net_user.c @@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg) char *split_if_spec(char *str, ...) { - char **arg, *end; + char **arg, *end, *ret = NULL; va_list ap; va_start(ap, str); while ((arg = va_arg(ap, char **)) != NULL) { if (*str == '\0') - return NULL; + goto out; end = strchr(str, ','); if (end != str) *arg = str; if (end == NULL) - return NULL; + goto out; *end++ = '\0'; str = end; } + ret = str; +out: va_end(ap); - return str; + return ret; } diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 57acbd67d85db..fc8be0e3a4ff8 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs) struct ksignal ksig; int handled_sig = 0; - while (get_signal(&ksig)) { + if (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 0033e96c3f09c..9011a88353ded 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -23,7 +23,6 @@ #include <stdarg.h> #include <linux/types.h> #include <linux/edd.h> -#include <asm/boot.h> #include <asm/setup.h> #include "bitops.h" #include "ctype.h" diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c index aa8a96b052e30..95c7a818c0ed6 100644 --- a/arch/x86/boot/video-mode.c +++ b/arch/x86/boot/video-mode.c @@ -19,6 +19,8 @@ #include "video.h" #include "vesa.h" +#include <uapi/asm/boot.h> + /* * Common variables */ diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c index 05111bb8d018e..77780e386e9b2 100644 --- a/arch/x86/boot/video.c +++ b/arch/x86/boot/video.c @@ -13,6 +13,8 @@ * Select video mode */ +#include <uapi/asm/boot.h> + #include "boot.h" #include "video.h" #include "vesa.h" diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 53616ca032444..a55697d198247 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -509,6 +509,17 @@ END(irq_entries_start) * tracking that we're in kernel mode. */ SWAPGS + + /* + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * the simplest way to handle it is to just call it twice if + * we enter from user mode. There's no reason to optimize this since + * TRACE_IRQS_OFF is a no-op if lockdep is off. + */ + TRACE_IRQS_OFF + #ifdef CONFIG_CONTEXT_TRACKING call enter_from_user_mode #endif @@ -1049,12 +1060,18 @@ ENTRY(error_entry) SWAPGS .Lerror_entry_from_usermode_after_swapgs: + /* + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). + */ + TRACE_IRQS_OFF #ifdef CONFIG_CONTEXT_TRACKING call enter_from_user_mode #endif + ret .Lerror_entry_done: - TRACE_IRQS_OFF ret diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index c5b7fb2774d08..cc071c6f7d4da 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -9,19 +9,21 @@ #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) +#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) + +#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) + #define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) -/* Cast PAGE_MASK to a signed type so that it is sign-extended if +/* Cast *PAGE_MASK to a signed type so that it is sign-extended if virtual addresses are 32-bits but physical addresses are larger (ie, 32-bit PAE). */ #define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) - -#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) -#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) - -#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) -#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) +#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK) #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index dd5b0aa9dd2f9..a471cadb9630e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -279,17 +279,14 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) static inline pudval_t pud_pfn_mask(pud_t pud) { if (native_pud_val(pud) & _PAGE_PSE) - return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK; + return PHYSICAL_PUD_PAGE_MASK; else return PTE_PFN_MASK; } static inline pudval_t pud_flags_mask(pud_t pud) { - if (native_pud_val(pud) & _PAGE_PSE) - return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK); - else - return ~PTE_PFN_MASK; + return ~pud_pfn_mask(pud); } static inline pudval_t pud_flags(pud_t pud) @@ -300,17 +297,14 @@ static inline pudval_t pud_flags(pud_t pud) static inline pmdval_t pmd_pfn_mask(pmd_t pmd) { if (native_pmd_val(pmd) & _PAGE_PSE) - return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK; + return PHYSICAL_PMD_PAGE_MASK; else return PTE_PFN_MASK; } static inline pmdval_t pmd_flags_mask(pmd_t pmd) { - if (native_pmd_val(pmd) & _PAGE_PSE) - return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK); - else - return ~PTE_PFN_MASK; + return ~pmd_pfn_mask(pmd); } static inline pmdval_t pmd_flags(pmd_t pmd) diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 48d34d28f5a60..cd0fc0cc78bc3 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H -#include <asm/pgtable_types.h> #include <asm/bootparam.h> struct mpc_bus; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 7fc27f1cca586..b3e94ef461fdd 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -698,3 +698,4 @@ int __init microcode_init(void) return error; } +late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4562cf070c279..2bf79d7c97dfb 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 499f533dd3ccb..d0e35ebb2adb1 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -387,7 +387,7 @@ struct cpu_hw_events { /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ - INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) @@ -627,6 +627,7 @@ struct x86_perf_task_context { u64 lbr_from[MAX_LBR_ENTRIES]; u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; + int tos; int lbr_callstack_users; int lbr_stack_state; }; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f63360be22387..e2a430021e46e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ - INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 377e8f8ed3918..a316ca96f1b63 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index bfd0b717e944c..659f01e165d57 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) } mask = x86_pmu.lbr_nr - 1; - tos = intel_pmu_lbr_tos(); + tos = task_ctx->tos; for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); @@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } @@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; } diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index dc5fa6a1e8d64..3512ba6073614 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 4f00b63d7ff33..14415aff18136 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -4,10 +4,22 @@ */ #include <linux/platform_device.h> #include <linux/module.h> +#include <linux/ioport.h> + +static int found(u64 start, u64 end, void *data) +{ + return 1; +} static __init int register_e820_pmem(void) { + char *pmem = "Persistent Memory (legacy)"; struct platform_device *pdev; + int rc; + + rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found); + if (rc <= 0) + return 0; /* * See drivers/nvdimm/e820.c for the implementation, this is diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 29db25f9a745e..d2bbe343fda74 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1250,8 +1250,6 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_apply_memmap_quirks(); #endif - - microcode_init(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b7ffb7c000757..cb6282c3638ff 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -690,12 +690,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(failed, ksig, stepping); } -#ifdef CONFIG_X86_32 -#define NR_restart_syscall __NR_restart_syscall -#else /* !CONFIG_X86_32 */ -#define NR_restart_syscall \ - test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall -#endif /* CONFIG_X86_32 */ +static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) +{ +#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64) + return __NR_restart_syscall; +#else /* !CONFIG_X86_32 && CONFIG_X86_64 */ + return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : + __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); +#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */ +} /* * Note that 'init' is a special process: it doesn't get signals it doesn't @@ -724,7 +727,7 @@ void do_signal(struct pt_regs *regs) break; case -ERESTART_RESTARTBLOCK: - regs->ax = NR_restart_syscall; + regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 892ee2e5ecbce..fbabe4fcc7fbb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid) */ #define UDELAY_10MS_DEFAULT 10000 -static unsigned int init_udelay = INT_MAX; +static unsigned int init_udelay = UINT_MAX; static int __init cpu_init_udelay(char *str) { @@ -522,14 +522,15 @@ early_param("cpu_init_udelay", cpu_init_udelay); static void __init smp_quirk_init_udelay(void) { /* if cmdline changed it from default, leave it alone */ - if (init_udelay != INT_MAX) + if (init_udelay != UINT_MAX) return; /* if modern processor, use no delay */ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || - ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) + ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) { init_udelay = 0; - + return; + } /* else, use legacy delay */ init_udelay = UDELAY_10MS_DEFAULT; } diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 06332cb7e7d1d..3f5c48ddba453 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -38,6 +38,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->edx & bit(X86_FEATURE_MTRR)); +} + static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 9e8bf13572e6d..3f8c732117ecc 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,14 +120,22 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; } -static u8 mtrr_disabled_type(void) +static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) { /* * Intel SDM 11.11.2.2: all MTRRs are disabled when * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC * memory type is applied to all of physical memory. + * + * However, virtual machines can be run with CPUID such that + * there are no MTRRs. In that case, the firmware will never + * enable MTRRs and it is obviously undesirable to run the + * guest entirely with UC memory and we use WB. */ - return MTRR_TYPE_UNCACHABLE; + if (guest_cpuid_has_mtrr(vcpu)) + return MTRR_TYPE_UNCACHABLE; + else + return MTRR_TYPE_WRBACK; } /* @@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr) for (seg = 0; seg < seg_num; seg++) { mtrr_seg = &fixed_seg_table[seg]; - if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + if (mtrr_seg->start <= addr && addr < mtrr_seg->end) return seg; } @@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) *start = range->base & PAGE_MASK; mask = range->mask & PAGE_MASK; - mask |= ~0ULL << boot_cpu_data.x86_phys_bits; /* This cannot overflow because writing to the reserved bits of * variable MTRRs causes a #GP. @@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (var_mtrr_range_is_valid(cur)) list_del(&mtrr_state->var_ranges[index].node); + /* Extend the mask with all 1 bits to the left, since those + * bits must implicitly be 0. The bits are then cleared + * when reading them. + */ if (!is_mtrr_mask) cur->base = data; else - cur->mask = data; + cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); /* add it to the list if it's enabled. */ if (var_mtrr_range_is_valid(cur)) { @@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; else *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + + *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; } return 0; @@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } if (iter.mtrr_disabled) - return mtrr_disabled_type(); + return mtrr_disabled_type(vcpu); /* not contained in any MTRRs. */ if (type == -1) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 83a1c643f9a50..899c40f826dd9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3422,6 +3422,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; + trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3892,8 +3894,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); - if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index af823a388c199..44976a596fa65 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2803,7 +2803,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: @@ -2909,7 +2909,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -8042,6 +8042,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -8668,7 +8670,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eed32283d22cc..7ffc224bbe412 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3572,9 +3572,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -3593,6 +3595,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { int start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3602,7 +3605,8 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -6515,6 +6519,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); + trace_kvm_entry(vcpu->vcpu_id); + wait_lapic_expire(vcpu); __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -6527,8 +6533,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); kvm_x86_ops->run(vcpu); /* diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a035c2aa78019..0f1c6fc3ddd88 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -89,7 +89,7 @@ static struct addr_marker address_markers[] = { { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/*VMALLOC_END*/, "vmalloc() End" }, # ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, + { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, # endif { 0/*FIXADDR_START*/, "Fixmap Area" }, #endif diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 1202d5ca2fb58..b2fd67da17014 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -101,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, switch (type) { case REG_TYPE_RM: regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value) == 1) + if (X86_REX_X(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_BASE: regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 75991979f667f..4286f3618bd07 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -193,7 +193,7 @@ struct jit_context { 32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 51 +#define PROLOGUE_SIZE 48 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program @@ -229,11 +229,15 @@ static void emit_prologue(u8 **pprog) /* mov qword ptr [rbp-X],r15 */ EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); - /* clear A and X registers */ - EMIT2(0x31, 0xc0); /* xor eax, eax */ - EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */ + /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls + * we need to reset the counter to 0. It's done in two instructions, + * resetting rax register to 0 (xor on eax gets 0 extended), and + * moving it to the counter location. + */ - /* clear tail_cnt: mov qword ptr [rbp-X], rax */ + /* xor eax, eax */ + EMIT2(0x31, 0xc0); + /* mov qword ptr [rbp-X], rax */ EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); @@ -455,6 +459,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } case BPF_ALU | BPF_MOV | BPF_K: + /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + break; + } + /* mov %eax, imm32 */ if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); @@ -469,6 +485,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, return -EINVAL; } + /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' + * to save 7 bytes. + */ + if (insn[0].imm == 0 && insn[1].imm == 0) { + b1 = add_2mod(0x48, dst_reg, dst_reg); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); + + insn++; + i++; + break; + } + /* movabsq %rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(insn[0].imm, 4); diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 7bcf06a7cd120..6eb3c8af96e23 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -50,18 +50,9 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) if (!found) pci_add_resource(resources, &info->busn); - list_for_each_entry(root_res, &info->resources, list) { - struct resource *res; - struct resource *root; + list_for_each_entry(root_res, &info->resources, list) + pci_add_resource(resources, &root_res->res); - res = &root_res->res; - pci_add_resource(resources, res); - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - root = &iomem_resource; - insert_resource(root, res); - } return; default_resources: diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 06934a8a48724..14fcd01ed9929 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs, if (err) return 1; - err = convert_fxsr_from_user(&fpx, sc.fpstate); + err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate); if (err) return 1; @@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs, { struct user_i387_struct fp; - err = copy_from_user(&fp, sc.fpstate, + err = copy_from_user(&fp, (void *)sc.fpstate, sizeof(struct user_i387_struct)); if (err) return 1; @@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, #endif #undef PUTREG sc.oldmask = mask; - sc.fpstate = to_fp; + sc.fpstate = (unsigned long)to_fp; err = copy_to_user(to, &sc, sizeof(struct sigcontext)); if (err) @@ -468,12 +468,10 @@ long sys_sigreturn(void) struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); sigset_t set; struct sigcontext __user *sc = &frame->sc; - unsigned long __user *oldmask = &sc->oldmask; - unsigned long __user *extramask = frame->extramask; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) || - copy_from_user(&set.sig[1], extramask, sig_size)) + if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) || + copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; set_current_blocked(&set); @@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, { struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; + unsigned long fp_to; frame = (struct rt_sigframe __user *) round_down(stack_top - sizeof(struct rt_sigframe), 16); @@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, set->sig[0]); - err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate); + + fp_to = (unsigned long)&frame->fpstate; + + err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index ac161db633885..cb5e266a8bf75 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2495,14 +2495,9 @@ void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; - /* Optimization - we can use the HVM one but it has no idea which - * VCPUs are descheduled - which means that it will needlessly IPI - * them. Xen knows so let it do the job. - */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - pv_mmu_ops.flush_tlb_others = xen_flush_tlb_others; + if (xen_feature(XENFEAT_auto_translated_physmap)) return; - } + pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index feddabdab4488..df0c405595837 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include <linux/tick.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> @@ -68,26 +69,16 @@ static void xen_pv_post_suspend(int suspend_cancelled) void xen_arch_pre_suspend(void) { - int cpu; - - for_each_online_cpu(cpu) - xen_pmu_finish(cpu); - if (xen_pv_domain()) xen_pv_pre_suspend(); } void xen_arch_post_suspend(int cancelled) { - int cpu; - if (xen_pv_domain()) xen_pv_post_suspend(cancelled); else xen_hvm_post_suspend(cancelled); - - for_each_online_cpu(cpu) - xen_pmu_init(cpu); } static void xen_vcpu_notify_restore(void *data) @@ -106,10 +97,20 @@ static void xen_vcpu_notify_suspend(void *data) void xen_arch_resume(void) { + int cpu; + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); + + for_each_online_cpu(cpu) + xen_pmu_init(cpu); } void xen_arch_suspend(void) { + int cpu; + + for_each_online_cpu(cpu) + xen_pmu_finish(cpu); + on_each_cpu(xen_vcpu_notify_suspend, NULL, 1); } diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 4120af0861605..fd3b96d1153fd 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -96,4 +96,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _XTENSA_SOCKET_H */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5bcdfc10c23a6..5a37188b559fb 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q) * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ -static int blkcg_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int blkcg_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *dst_css; struct io_context *ioc; int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) diff --git a/block/blk-core.c b/block/blk-core.c index a0af4043dda2b..33e2f62d50622 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -207,6 +207,22 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs) EXPORT_SYMBOL(blk_delay_queue); /** + * blk_start_queue_async - asynchronously restart a previously stopped queue + * @q: The &struct request_queue in question + * + * Description: + * blk_start_queue_async() will clear the stop flag on the queue, and + * ensure that the request_fn for the queue is run from an async + * context. + **/ +void blk_start_queue_async(struct request_queue *q) +{ + queue_flag_clear(QUEUE_FLAG_STOPPED, q); + blk_run_queue_async(q); +} +EXPORT_SYMBOL(blk_start_queue_async); + +/** * blk_start_queue - restart a previously stopped queue * @q: The &struct request_queue in question * @@ -1689,8 +1705,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) struct request *req; unsigned int request_count = 0; - blk_queue_split(q, &bio, q->bio_split); - /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1698,6 +1712,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); + blk_queue_split(q, &bio, q->bio_split); + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio->bi_error = -EIO; bio_endio(bio); @@ -3405,6 +3421,9 @@ int blk_pre_runtime_suspend(struct request_queue *q) { int ret = 0; + if (!q->dev) + return ret; + spin_lock_irq(q->queue_lock); if (q->nr_pending) { ret = -EBUSY; @@ -3432,6 +3451,9 @@ EXPORT_SYMBOL(blk_pre_runtime_suspend); */ void blk_post_runtime_suspend(struct request_queue *q, int err) { + if (!q->dev) + return; + spin_lock_irq(q->queue_lock); if (!err) { q->rpm_status = RPM_SUSPENDED; @@ -3456,6 +3478,9 @@ EXPORT_SYMBOL(blk_post_runtime_suspend); */ void blk_pre_runtime_resume(struct request_queue *q) { + if (!q->dev) + return; + spin_lock_irq(q->queue_lock); q->rpm_status = RPM_RESUMING; spin_unlock_irq(q->queue_lock); @@ -3478,6 +3503,9 @@ EXPORT_SYMBOL(blk_pre_runtime_resume); */ void blk_post_runtime_resume(struct request_queue *q, int err) { + if (!q->dev) + return; + spin_lock_irq(q->queue_lock); if (!err) { q->rpm_status = RPM_ACTIVE; diff --git a/block/blk-merge.c b/block/blk-merge.c index e01405a3e8b3f..e73846a3d08a6 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -81,7 +81,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *new = NULL; bio_for_each_segment(bv, bio, iter) { - if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) + if (sectors + (bv.bv_len >> 9) > blk_max_size_offset(q, bio->bi_iter.bi_sector)) goto split; /* diff --git a/block/blk-settings.c b/block/blk-settings.c index 7d8f129a1516b..dd49735839789 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -91,7 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim) lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->virt_boundary_mask = 0; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; - lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; + lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors = + BLK_SAFE_MAX_SECTORS; lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; lim->max_discard_sectors = 0; @@ -127,6 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim) lim->max_hw_sectors = UINT_MAX; lim->max_segment_size = UINT_MAX; lim->max_sectors = UINT_MAX; + lim->max_dev_sectors = UINT_MAX; lim->max_write_same_sectors = UINT_MAX; } EXPORT_SYMBOL(blk_set_stacking_limits); @@ -214,8 +216,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr) EXPORT_SYMBOL(blk_queue_bounce_limit); /** - * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request - * @limits: the queue limits + * blk_queue_max_hw_sectors - set max sectors for a request for this queue + * @q: the request queue for the device * @max_hw_sectors: max hardware sectors in the usual 512b unit * * Description: @@ -224,13 +226,19 @@ EXPORT_SYMBOL(blk_queue_bounce_limit); * the device driver based upon the capabilities of the I/O * controller. * + * max_dev_sectors is a hard limit imposed by the storage device for + * READ/WRITE requests. It is set by the disk driver. + * * max_sectors is a soft limit imposed by the block layer for * filesystem type requests. This value can be overridden on a * per-device basis in /sys/block/<device>/queue/max_sectors_kb. * The soft limit can not exceed max_hw_sectors. **/ -void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors) +void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) { + struct queue_limits *limits = &q->limits; + unsigned int max_sectors; + if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) { max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9); printk(KERN_INFO "%s: set to minimum %d\n", @@ -238,22 +246,9 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_ } limits->max_hw_sectors = max_hw_sectors; - limits->max_sectors = min_t(unsigned int, max_hw_sectors, - BLK_DEF_MAX_SECTORS); -} -EXPORT_SYMBOL(blk_limits_max_hw_sectors); - -/** - * blk_queue_max_hw_sectors - set max sectors for a request for this queue - * @q: the request queue for the device - * @max_hw_sectors: max hardware sectors in the usual 512b unit - * - * Description: - * See description for blk_limits_max_hw_sectors(). - **/ -void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) -{ - blk_limits_max_hw_sectors(&q->limits, max_hw_sectors); + max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); + max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); + limits->max_sectors = max_sectors; } EXPORT_SYMBOL(blk_queue_max_hw_sectors); @@ -527,6 +522,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); + t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors); t->max_write_same_sectors = min(t->max_write_same_sectors, b->max_write_same_sectors); t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 565b8dac57829..e140cc487ce11 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -205,6 +205,9 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) if (ret < 0) return ret; + max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, (unsigned long) + q->limits.max_dev_sectors >> 1); + if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb) return -EINVAL; diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c index b4ffc5be1a93c..e5b5721809e21 100644 --- a/crypto/ablkcipher.c +++ b/crypto/ablkcipher.c @@ -277,12 +277,12 @@ static int ablkcipher_walk_first(struct ablkcipher_request *req, if (WARN_ON_ONCE(in_irq())) return -EDEADLK; + walk->iv = req->info; walk->nbytes = walk->total; if (unlikely(!walk->total)) return 0; walk->iv_buffer = NULL; - walk->iv = req->info; if (unlikely(((unsigned long)walk->iv & alignmask))) { int err = ablkcipher_copy_iv(walk, tfm, alignmask); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index caf58b4e46be2..5e20ca1a4c94f 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -47,7 +47,7 @@ struct skcipher_ctx { bool merge; bool enc; - struct ablkcipher_request req; + struct skcipher_request req; }; struct skcipher_async_rsgl { @@ -64,13 +64,13 @@ struct skcipher_async_req { }; #define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \ - crypto_ablkcipher_reqsize(crypto_ablkcipher_reqtfm(&ctx->req))) + crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))) #define GET_REQ_SIZE(ctx) \ - crypto_ablkcipher_reqsize(crypto_ablkcipher_reqtfm(&ctx->req)) + crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)) #define GET_IV_SIZE(ctx) \ - crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(&ctx->req)) + crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req)) #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) @@ -302,8 +302,8 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req); - unsigned ivsize = crypto_ablkcipher_ivsize(tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); + unsigned ivsize = crypto_skcipher_ivsize(tfm); struct skcipher_sg_list *sgl; struct af_alg_control con = {}; long copied = 0; @@ -507,7 +507,7 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, struct skcipher_sg_list *sgl; struct scatterlist *sg; struct skcipher_async_req *sreq; - struct ablkcipher_request *req; + struct skcipher_request *req; struct skcipher_async_rsgl *last_rsgl = NULL; unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx); unsigned int reqlen = sizeof(struct skcipher_async_req) + @@ -531,9 +531,9 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, } sg_init_table(sreq->tsg, tx_nents); memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx)); - ablkcipher_request_set_tfm(req, crypto_ablkcipher_reqtfm(&ctx->req)); - ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - skcipher_async_cb, sk); + skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req)); + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_async_cb, sk); while (iov_iter_count(&msg->msg_iter)) { struct skcipher_async_rsgl *rsgl; @@ -608,10 +608,10 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, if (mark) sg_mark_end(sreq->tsg + txbufs - 1); - ablkcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, - len, sreq->iv); - err = ctx->enc ? crypto_ablkcipher_encrypt(req) : - crypto_ablkcipher_decrypt(req); + skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, + len, sreq->iv); + err = ctx->enc ? crypto_skcipher_encrypt(req) : + crypto_skcipher_decrypt(req); if (err == -EINPROGRESS) { atomic_inc(&ctx->inflight); err = -EIOCBQUEUED; @@ -632,7 +632,7 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - unsigned bs = crypto_ablkcipher_blocksize(crypto_ablkcipher_reqtfm( + unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm( &ctx->req)); struct skcipher_sg_list *sgl; struct scatterlist *sg; @@ -669,14 +669,13 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, if (!used) goto free; - ablkcipher_request_set_crypt(&ctx->req, sg, - ctx->rsgl.sg, used, - ctx->iv); + skcipher_request_set_crypt(&ctx->req, sg, ctx->rsgl.sg, used, + ctx->iv); err = af_alg_wait_for_completion( ctx->enc ? - crypto_ablkcipher_encrypt(&ctx->req) : - crypto_ablkcipher_decrypt(&ctx->req), + crypto_skcipher_encrypt(&ctx->req) : + crypto_skcipher_decrypt(&ctx->req), &ctx->completion); free: @@ -751,17 +750,17 @@ static struct proto_ops algif_skcipher_ops = { static void *skcipher_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_ablkcipher(name, type, mask); + return crypto_alloc_skcipher(name, type, mask); } static void skcipher_release(void *private) { - crypto_free_ablkcipher(private); + crypto_free_skcipher(private); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_ablkcipher_setkey(private, key, keylen); + return crypto_skcipher_setkey(private, key, keylen); } static void skcipher_wait(struct sock *sk) @@ -778,13 +777,13 @@ static void skcipher_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); if (atomic_read(&ctx->inflight)) skcipher_wait(sk); skcipher_free_sgl(sk); - sock_kzfree_s(sk, ctx->iv, crypto_ablkcipher_ivsize(tfm)); + sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } @@ -793,20 +792,20 @@ static int skcipher_accept_parent(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(private); + unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(private); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; - ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(private), + ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(private), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_ablkcipher_ivsize(private)); + memset(ctx->iv, 0, crypto_skcipher_ivsize(private)); INIT_LIST_HEAD(&ctx->tsgl); ctx->len = len; @@ -819,9 +818,9 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ask->private = ctx; - ablkcipher_request_set_tfm(&ctx->req, private); - ablkcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, - af_alg_complete, &ctx->completion); + skcipher_request_set_tfm(&ctx->req, private); + skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, + af_alg_complete, &ctx->completion); sk->sk_destruct = skcipher_sock_destruct; diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c index 11b9814920313..8cc1622b2ee00 100644 --- a/crypto/blkcipher.c +++ b/crypto/blkcipher.c @@ -326,12 +326,12 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc, if (WARN_ON_ONCE(in_irq())) return -EDEADLK; + walk->iv = desc->info; walk->nbytes = walk->total; if (unlikely(!walk->total)) return 0; walk->buffer = NULL; - walk->iv = desc->info; if (unlikely(((unsigned long)walk->iv & walk->alignmask))) { int err = blkcipher_copy_iv(walk); if (err) diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 25dbb76c02ccb..5eef4cb4f70e6 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -58,10 +58,10 @@ config ACPI_CCA_REQUIRED bool config ACPI_DEBUGGER - bool "In-kernel debugger (EXPERIMENTAL)" + bool "AML debugger interface (EXPERIMENTAL)" select ACPI_DEBUG help - Enable in-kernel debugging facilities: statistics, internal + Enable in-kernel debugging of AML facilities: statistics, internal object dump, single step control method execution. This is still under development, currently enabling this only results in the compilation of the ACPICA debugger files. diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index f7dab53b352ae..aa45d48027072 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -233,11 +233,12 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_system_address *spa) { + size_t length = min_t(size_t, sizeof(*spa), spa->header.length); struct device *dev = acpi_desc->dev; struct nfit_spa *nfit_spa; list_for_each_entry(nfit_spa, &prev->spas, list) { - if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) { + if (memcmp(nfit_spa->spa, spa, length) == 0) { list_move_tail(&nfit_spa->list, &acpi_desc->spas); return true; } @@ -259,11 +260,12 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_memory_map *memdev) { + size_t length = min_t(size_t, sizeof(*memdev), memdev->header.length); struct device *dev = acpi_desc->dev; struct nfit_memdev *nfit_memdev; list_for_each_entry(nfit_memdev, &prev->memdevs, list) - if (memcmp(nfit_memdev->memdev, memdev, sizeof(*memdev)) == 0) { + if (memcmp(nfit_memdev->memdev, memdev, length) == 0) { list_move_tail(&nfit_memdev->list, &acpi_desc->memdevs); return true; } @@ -284,11 +286,12 @@ static bool add_dcr(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_control_region *dcr) { + size_t length = min_t(size_t, sizeof(*dcr), dcr->header.length); struct device *dev = acpi_desc->dev; struct nfit_dcr *nfit_dcr; list_for_each_entry(nfit_dcr, &prev->dcrs, list) - if (memcmp(nfit_dcr->dcr, dcr, sizeof(*dcr)) == 0) { + if (memcmp(nfit_dcr->dcr, dcr, length) == 0) { list_move_tail(&nfit_dcr->list, &acpi_desc->dcrs); return true; } @@ -308,11 +311,12 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_data_region *bdw) { + size_t length = min_t(size_t, sizeof(*bdw), bdw->header.length); struct device *dev = acpi_desc->dev; struct nfit_bdw *nfit_bdw; list_for_each_entry(nfit_bdw, &prev->bdws, list) - if (memcmp(nfit_bdw->bdw, bdw, sizeof(*bdw)) == 0) { + if (memcmp(nfit_bdw->bdw, bdw, length) == 0) { list_move_tail(&nfit_bdw->list, &acpi_desc->bdws); return true; } @@ -332,11 +336,12 @@ static bool add_idt(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_interleave *idt) { + size_t length = min_t(size_t, sizeof(*idt), idt->header.length); struct device *dev = acpi_desc->dev; struct nfit_idt *nfit_idt; list_for_each_entry(nfit_idt, &prev->idts, list) - if (memcmp(nfit_idt->idt, idt, sizeof(*idt)) == 0) { + if (memcmp(nfit_idt->idt, idt, length) == 0) { list_move_tail(&nfit_idt->list, &acpi_desc->idts); return true; } @@ -356,11 +361,12 @@ static bool add_flush(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_flush_address *flush) { + size_t length = min_t(size_t, sizeof(*flush), flush->header.length); struct device *dev = acpi_desc->dev; struct nfit_flush *nfit_flush; list_for_each_entry(nfit_flush, &prev->flushes, list) - if (memcmp(nfit_flush->flush, flush, sizeof(*flush)) == 0) { + if (memcmp(nfit_flush->flush, flush, length) == 0) { list_move_tail(&nfit_flush->list, &acpi_desc->flushes); return true; } @@ -655,7 +661,7 @@ static ssize_t revision_show(struct device *dev, struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); - return sprintf(buf, "%d\n", acpi_desc->nfit->header.revision); + return sprintf(buf, "%d\n", acpi_desc->acpi_header.revision); } static DEVICE_ATTR_RO(revision); @@ -1652,7 +1658,6 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz) data = (u8 *) acpi_desc->nfit; end = data + sz; - data += sizeof(struct acpi_table_nfit); while (!IS_ERR_OR_NULL(data)) data = add_table(acpi_desc, &prev, data, end); @@ -1748,13 +1753,29 @@ static int acpi_nfit_add(struct acpi_device *adev) return PTR_ERR(acpi_desc); } - acpi_desc->nfit = (struct acpi_table_nfit *) tbl; + /* + * Save the acpi header for later and then skip it, + * making nfit point to the first nfit table header. + */ + acpi_desc->acpi_header = *tbl; + acpi_desc->nfit = (void *) tbl + sizeof(struct acpi_table_nfit); + sz -= sizeof(struct acpi_table_nfit); /* Evaluate _FIT and override with that if present */ status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf); if (ACPI_SUCCESS(status) && buf.length > 0) { - acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer; - sz = buf.length; + union acpi_object *obj; + /* + * Adjust for the acpi_object header of the _FIT + */ + obj = buf.pointer; + if (obj->type == ACPI_TYPE_BUFFER) { + acpi_desc->nfit = + (struct acpi_nfit_header *)obj->buffer.pointer; + sz = obj->buffer.length; + } else + dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n", + __func__, (int) obj->type); } rc = acpi_nfit_init(acpi_desc, sz); @@ -1777,7 +1798,8 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event) { struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev); struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL }; - struct acpi_table_nfit *nfit_saved; + struct acpi_nfit_header *nfit_saved; + union acpi_object *obj; struct device *dev = &adev->dev; acpi_status status; int ret; @@ -1788,7 +1810,7 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event) if (!dev->driver) { /* dev->driver may be null if we're being removed */ dev_dbg(dev, "%s: no driver found for dev\n", __func__); - return; + goto out_unlock; } if (!acpi_desc) { @@ -1808,12 +1830,19 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event) } nfit_saved = acpi_desc->nfit; - acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer; - ret = acpi_nfit_init(acpi_desc, buf.length); - if (!ret) { - /* Merge failed, restore old nfit, and exit */ - acpi_desc->nfit = nfit_saved; - dev_err(dev, "failed to merge updated NFIT\n"); + obj = buf.pointer; + if (obj->type == ACPI_TYPE_BUFFER) { + acpi_desc->nfit = + (struct acpi_nfit_header *)obj->buffer.pointer; + ret = acpi_nfit_init(acpi_desc, obj->buffer.length); + if (ret) { + /* Merge failed, restore old nfit, and exit */ + acpi_desc->nfit = nfit_saved; + dev_err(dev, "failed to merge updated NFIT\n"); + } + } else { + /* Bad _FIT, restore old nfit */ + dev_err(dev, "Invalid _FIT\n"); } kfree(buf.pointer); diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index 2ea5c0797c8f4..3d549a3836590 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -96,7 +96,8 @@ struct nfit_mem { struct acpi_nfit_desc { struct nvdimm_bus_descriptor nd_desc; - struct acpi_table_nfit *nfit; + struct acpi_table_header acpi_header; + struct acpi_nfit_header *nfit; struct mutex spa_map_mutex; struct mutex init_mutex; struct list_head spa_maps; diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 850d7bf0c873f..ae3fe4e642035 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -768,6 +768,13 @@ static void pci_acpi_root_add_resources(struct acpi_pci_root_info *info) else continue; + /* + * Some legacy x86 host bridge drivers use iomem_resource and + * ioport_resource as default resource pool, skip it. + */ + if (res == root) + continue; + conflict = insert_resource_conflict(root, res); if (conflict) { dev_info(&info->bridge->dev, diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index f4e02ae93f585..11154a330f075 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -200,7 +200,8 @@ static int acpi_pss_perf_init(struct acpi_processor *pr, goto err_remove_sysfs_thermal; } - sysfs_remove_link(&pr->cdev->device.kobj, "device"); + return 0; + err_remove_sysfs_thermal: sysfs_remove_link(&device->dev.kobj, "thermal_cooling"); err_thermal_unregister: diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index ff02bb4218fca..cdfbcc54821fd 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -314,16 +314,6 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */ - { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ - { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ - { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */ { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */ { PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */ @@ -350,10 +340,22 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */ { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ + { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ + { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index 8490d37aee2a4..f7a7fa81740e8 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -62,6 +62,7 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv) writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA); } +#ifdef CONFIG_PM_SLEEP static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state) { return ahci_platform_suspend_host(&pdev->dev); @@ -81,6 +82,10 @@ static int ahci_mvebu_resume(struct platform_device *pdev) return ahci_platform_resume_host(&pdev->dev); } +#else +#define ahci_mvebu_suspend NULL +#define ahci_mvebu_resume NULL +#endif static const struct ata_port_info ahci_mvebu_port_info = { .flags = AHCI_FLAG_COMMON, diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 096064cd6c52b..4665512dae44d 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1273,6 +1273,15 @@ static int ahci_exec_polled_cmd(struct ata_port *ap, int pmp, ata_tf_to_fis(tf, pmp, is_cmd, fis); ahci_fill_cmd_slot(pp, 0, cmd_fis_len | flags | (pmp << 12)); + /* set port value for softreset of Port Multiplier */ + if (pp->fbs_enabled && pp->fbs_last_dev != pmp) { + tmp = readl(port_mmio + PORT_FBS); + tmp &= ~(PORT_FBS_DEV_MASK | PORT_FBS_DEC); + tmp |= pmp << PORT_FBS_DEV_OFFSET; + writel(tmp, port_mmio + PORT_FBS); + pp->fbs_last_dev = pmp; + } + /* issue & wait */ writel(1, port_mmio + PORT_CMD_ISSUE); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index cb0508af1459a..961acc788f449 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1505,12 +1505,20 @@ static const char *ata_err_string(unsigned int err_mask) unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors) { + unsigned long ap_flags = dev->link->ap->flags; struct ata_taskfile tf; unsigned int err_mask; bool dma = false; DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); + /* + * Return error without actually issuing the command on controllers + * which e.g. lockup on a read log page. + */ + if (ap_flags & ATA_FLAG_NO_LOG_PAGE) + return AC_ERR_DEV; + retry: ata_tf_init(dev, &tf); if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) && diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 5389579c51204..a723ae9297831 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -45,7 +45,8 @@ enum { SATA_FSL_MAX_PRD_DIRECT = 16, /* Direct PRDT entries */ SATA_FSL_HOST_FLAGS = (ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | - ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN), + ATA_FLAG_PMP | ATA_FLAG_NCQ | + ATA_FLAG_AN | ATA_FLAG_NO_LOG_PAGE), SATA_FSL_MAX_CMDS = SATA_FSL_QUEUE_DEPTH, SATA_FSL_CMD_HDR_SIZE = 16, /* 4 DWORDS */ diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index dea6edcbf145c..29bcff086bced 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -630,6 +630,9 @@ static void sil_dev_config(struct ata_device *dev) unsigned int n, quirks = 0; unsigned char model_num[ATA_ID_PROD_LEN + 1]; + /* This controller doesn't support trim */ + dev->horkage |= ATA_HORKAGE_NOTRIM; + ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); for (n = 0; sil_blacklist[n].product; n++) diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 0c2b4ba068139..6ac2b2b1e8dec 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -525,7 +525,7 @@ struct geos_gpio_attr { static ssize_t geos_gpio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); + struct pci_dev *pdev = to_pci_dev(dev); struct geos_gpio_attr *gattr = container_of(attr, struct geos_gpio_attr, attr); struct solos_card *card = pci_get_drvdata(pdev); uint32_t data32; @@ -551,7 +551,7 @@ static ssize_t geos_gpio_store(struct device *dev, struct device_attribute *attr static ssize_t geos_gpio_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); + struct pci_dev *pdev = to_pci_dev(dev); struct geos_gpio_attr *gattr = container_of(attr, struct geos_gpio_attr, attr); struct solos_card *card = pci_get_drvdata(pdev); uint32_t data32; @@ -565,7 +565,7 @@ static ssize_t geos_gpio_show(struct device *dev, struct device_attribute *attr, static ssize_t hardware_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); + struct pci_dev *pdev = to_pci_dev(dev); struct geos_gpio_attr *gattr = container_of(attr, struct geos_gpio_attr, attr); struct solos_card *card = pci_get_drvdata(pdev); uint32_t data32; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 2804aed3f416a..25425d3f25753 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -303,6 +303,10 @@ static int memory_subsys_offline(struct device *dev) if (mem->state == MEM_OFFLINE) return 0; + /* Can't offline block with non-present sections */ + if (mem->section_count != sections_per_block) + return -EINVAL; + return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); } diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index e03b1ad25a906..65f50eccd49b0 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -390,6 +390,7 @@ static int pm_genpd_runtime_suspend(struct device *dev) struct generic_pm_domain *genpd; bool (*stop_ok)(struct device *__dev); struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + bool runtime_pm = pm_runtime_enabled(dev); ktime_t time_start; s64 elapsed_ns; int ret; @@ -400,12 +401,19 @@ static int pm_genpd_runtime_suspend(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; + /* + * A runtime PM centric subsystem/driver may re-use the runtime PM + * callbacks for other purposes than runtime PM. In those scenarios + * runtime PM is disabled. Under these circumstances, we shall skip + * validating/measuring the PM QoS latency. + */ stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL; - if (stop_ok && !stop_ok(dev)) + if (runtime_pm && stop_ok && !stop_ok(dev)) return -EBUSY; /* Measure suspend latency. */ - time_start = ktime_get(); + if (runtime_pm) + time_start = ktime_get(); ret = genpd_save_dev(genpd, dev); if (ret) @@ -418,13 +426,15 @@ static int pm_genpd_runtime_suspend(struct device *dev) } /* Update suspend latency value if the measured time exceeds it. */ - elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns > td->suspend_latency_ns) { - td->suspend_latency_ns = elapsed_ns; - dev_dbg(dev, "suspend latency exceeded, %lld ns\n", - elapsed_ns); - genpd->max_off_time_changed = true; - td->constraint_changed = true; + if (runtime_pm) { + elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); + if (elapsed_ns > td->suspend_latency_ns) { + td->suspend_latency_ns = elapsed_ns; + dev_dbg(dev, "suspend latency exceeded, %lld ns\n", + elapsed_ns); + genpd->max_off_time_changed = true; + td->constraint_changed = true; + } } /* @@ -453,6 +463,7 @@ static int pm_genpd_runtime_resume(struct device *dev) { struct generic_pm_domain *genpd; struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + bool runtime_pm = pm_runtime_enabled(dev); ktime_t time_start; s64 elapsed_ns; int ret; @@ -479,14 +490,14 @@ static int pm_genpd_runtime_resume(struct device *dev) out: /* Measure resume latency. */ - if (timed) + if (timed && runtime_pm) time_start = ktime_get(); genpd_start_dev(genpd, dev); genpd_restore_dev(genpd, dev); /* Update resume latency value if the measured time exceeds it. */ - if (timed) { + if (timed && runtime_pm) { elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); if (elapsed_ns > td->resume_latency_ns) { td->resume_latency_ns = elapsed_ns; @@ -1775,10 +1786,10 @@ int genpd_dev_pm_attach(struct device *dev) } pd = of_genpd_get_from_provider(&pd_args); + of_node_put(pd_args.np); if (IS_ERR(pd)) { dev_dbg(dev, "%s() failed to find PM domain: %ld\n", __func__, PTR_ERR(pd)); - of_node_put(dev->of_node); return -EPROBE_DEFER; } @@ -1796,7 +1807,6 @@ int genpd_dev_pm_attach(struct device *dev) if (ret < 0) { dev_err(dev, "failed to add to PM domain %s: %d", pd->name, ret); - of_node_put(dev->of_node); goto out; } diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index e60dd12e23aae..1e937ac5f4566 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -160,9 +160,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) struct gpd_timing_data *td; s64 constraint_ns; - if (!pdd->dev->driver) - continue; - /* * Check if the device is allowed to be off long enough for the * domain to turn off and on (that's how much time it will diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 0c3940ec5e62c..09e3c0d87eccf 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -219,6 +219,9 @@ static void end_cmd(struct nullb_cmd *cmd) { struct request_queue *q = NULL; + if (cmd->rq) + q = cmd->rq->q; + switch (queue_mode) { case NULL_Q_MQ: blk_mq_end_request(cmd->rq, 0); @@ -229,23 +232,19 @@ static void end_cmd(struct nullb_cmd *cmd) break; case NULL_Q_BIO: bio_endio(cmd->bio); - goto free_cmd; + break; } - if (cmd->rq) - q = cmd->rq->q; + free_cmd(cmd); /* Restart queue if needed, as we are freeing a tag */ - if (q && !q->mq_ops && blk_queue_stopped(q)) { + if (queue_mode == NULL_Q_RQ && blk_queue_stopped(q)) { unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - if (blk_queue_stopped(q)) - blk_start_queue(q); + blk_start_queue_async(q); spin_unlock_irqrestore(q->queue_lock, flags); } -free_cmd: - free_cmd(cmd); } static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) @@ -444,8 +443,9 @@ static void null_lnvm_end_io(struct request *rq, int error) blk_put_request(rq); } -static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) +static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) { + struct request_queue *q = dev->q; struct request *rq; struct bio *bio = rqd->bio; @@ -470,7 +470,7 @@ static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) return 0; } -static int null_lnvm_id(struct request_queue *q, struct nvm_id *id) +static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id) { sector_t size = gb * 1024 * 1024 * 1024ULL; sector_t blksize; @@ -523,7 +523,7 @@ static int null_lnvm_id(struct request_queue *q, struct nvm_id *id) return 0; } -static void *null_lnvm_create_dma_pool(struct request_queue *q, char *name) +static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name) { mempool_t *virtmem_pool; @@ -541,7 +541,7 @@ static void null_lnvm_destroy_dma_pool(void *pool) mempool_destroy(pool); } -static void *null_lnvm_dev_dma_alloc(struct request_queue *q, void *pool, +static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool, gfp_t mem_flags, dma_addr_t *dma_handler) { return mempool_alloc(pool, mem_flags); @@ -765,7 +765,9 @@ out: static int __init null_init(void) { + int ret = 0; unsigned int i; + struct nullb *nullb; if (bs > PAGE_SIZE) { pr_warn("null_blk: invalid block size\n"); @@ -807,22 +809,29 @@ static int __init null_init(void) 0, 0, NULL); if (!ppa_cache) { pr_err("null_blk: unable to create ppa cache\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err_ppa; } } for (i = 0; i < nr_devices; i++) { - if (null_add_dev()) { - unregister_blkdev(null_major, "nullb"); - goto err_ppa; - } + ret = null_add_dev(); + if (ret) + goto err_dev; } pr_info("null: module loaded\n"); return 0; -err_ppa: + +err_dev: + while (!list_empty(&nullb_list)) { + nullb = list_entry(nullb_list.next, struct nullb, list); + null_del_dev(nullb); + } kmem_cache_destroy(ppa_cache); - return -EINVAL; +err_ppa: + unregister_blkdev(null_major, "nullb"); + return ret; } static void __exit null_exit(void) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 235708c7c46ee..81ea69fee7ca1 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3442,6 +3442,7 @@ static void rbd_queue_workfn(struct work_struct *work) goto err_rq; } img_request->rq = rq; + snapc = NULL; /* img_request consumes a ref */ if (op_type == OBJ_OP_DISCARD) result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA, diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index f9099940c2720..41fb1a917b172 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -950,6 +950,8 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, goto unmap; for (n = 0, i = 0; n < nseg; n++) { + uint8_t first_sect, last_sect; + if ((n % SEGS_PER_INDIRECT_FRAME) == 0) { /* Map indirect segments */ if (segments) @@ -957,15 +959,18 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, segments = kmap_atomic(pages[n/SEGS_PER_INDIRECT_FRAME]->page); } i = n % SEGS_PER_INDIRECT_FRAME; + pending_req->segments[n]->gref = segments[i].gref; - seg[n].nsec = segments[i].last_sect - - segments[i].first_sect + 1; - seg[n].offset = (segments[i].first_sect << 9); - if ((segments[i].last_sect >= (XEN_PAGE_SIZE >> 9)) || - (segments[i].last_sect < segments[i].first_sect)) { + + first_sect = READ_ONCE(segments[i].first_sect); + last_sect = READ_ONCE(segments[i].last_sect); + if (last_sect >= (XEN_PAGE_SIZE >> 9) || last_sect < first_sect) { rc = -EINVAL; goto unmap; } + + seg[n].nsec = last_sect - first_sect + 1; + seg[n].offset = first_sect << 9; preq->nr_sects += seg[n].nsec; } diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 68e87a037b992..c929ae22764c9 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -408,8 +408,8 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst, struct blkif_x86_32_request *src) { int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; - dst->operation = src->operation; - switch (src->operation) { + dst->operation = READ_ONCE(src->operation); + switch (dst->operation) { case BLKIF_OP_READ: case BLKIF_OP_WRITE: case BLKIF_OP_WRITE_BARRIER: @@ -456,8 +456,8 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst, struct blkif_x86_64_request *src) { int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; - dst->operation = src->operation; - switch (src->operation) { + dst->operation = READ_ONCE(src->operation); + switch (dst->operation) { case BLKIF_OP_READ: case BLKIF_OP_WRITE: case BLKIF_OP_WRITE_BARRIER: diff --git a/drivers/bluetooth/bcm203x.c b/drivers/bluetooth/bcm203x.c index 364f82b34d036..5b0ef7bbe8ac8 100644 --- a/drivers/bluetooth/bcm203x.c +++ b/drivers/bluetooth/bcm203x.c @@ -178,10 +178,8 @@ static int bcm203x_probe(struct usb_interface *intf, const struct usb_device_id return -ENODEV; data = devm_kzalloc(&intf->dev, sizeof(*data), GFP_KERNEL); - if (!data) { - BT_ERR("Can't allocate memory for data structure"); + if (!data) return -ENOMEM; - } data->udev = udev; data->state = BCM203X_LOAD_MINIDRV; diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c index 72d8bfabef095..3bf4ec60e0736 100644 --- a/drivers/bluetooth/bfusb.c +++ b/drivers/bluetooth/bfusb.c @@ -636,10 +636,8 @@ static int bfusb_probe(struct usb_interface *intf, const struct usb_device_id *i /* Initialize control structure and load firmware */ data = devm_kzalloc(&intf->dev, sizeof(struct bfusb_data), GFP_KERNEL); - if (!data) { - BT_ERR("Can't allocate memory for control structure"); - goto done; - } + if (!data) + return -ENOMEM; data->udev = udev; data->bulk_in_ep = bulk_in_ep->desc.bEndpointAddress; diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 1f13e617bf560..fce1548557181 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -73,6 +73,48 @@ int btintel_check_bdaddr(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(btintel_check_bdaddr); +int btintel_enter_mfg(struct hci_dev *hdev) +{ + const u8 param[] = { 0x01, 0x00 }; + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Entering manufacturer mode failed (%ld)", + PTR_ERR(skb)); + return PTR_ERR(skb); + } + kfree_skb(skb); + + return 0; +} +EXPORT_SYMBOL_GPL(btintel_enter_mfg); + +int btintel_exit_mfg(struct hci_dev *hdev, bool reset, bool patched) +{ + u8 param[] = { 0x00, 0x00 }; + struct sk_buff *skb; + + /* The 2nd command parameter specifies the manufacturing exit method: + * 0x00: Just disable the manufacturing mode (0x00). + * 0x01: Disable manufacturing mode and reset with patches deactivated. + * 0x02: Disable manufacturing mode and reset with patches activated. + */ + if (reset) + param[1] |= patched ? 0x02 : 0x01; + + skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Exiting manufacturer mode failed (%ld)", + PTR_ERR(skb)); + return PTR_ERR(skb); + } + kfree_skb(skb); + + return 0; +} +EXPORT_SYMBOL_GPL(btintel_exit_mfg); + int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) { struct sk_buff *skb; @@ -126,37 +168,19 @@ EXPORT_SYMBOL_GPL(btintel_set_diag); int btintel_set_diag_mfg(struct hci_dev *hdev, bool enable) { - struct sk_buff *skb; - u8 param[2]; - int err; - - param[0] = 0x01; - param[1] = 0x00; - - skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - BT_ERR("%s: Entering Intel manufacturer mode failed (%d)", - hdev->name, err); - return PTR_ERR(skb); - } - kfree_skb(skb); + int err, ret; - err = btintel_set_diag(hdev, enable); + err = btintel_enter_mfg(hdev); + if (err) + return err; - param[0] = 0x00; - param[1] = 0x00; + ret = btintel_set_diag(hdev, enable); - skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - BT_ERR("%s: Leaving Intel manufacturer mode failed (%d)", - hdev->name, err); - return PTR_ERR(skb); - } - kfree_skb(skb); + err = btintel_exit_mfg(hdev, false, false); + if (err) + return err; - return err; + return ret; } EXPORT_SYMBOL_GPL(btintel_set_diag_mfg); @@ -309,39 +333,46 @@ EXPORT_SYMBOL_GPL(btintel_set_event_mask); int btintel_set_event_mask_mfg(struct hci_dev *hdev, bool debug) { - struct sk_buff *skb; - u8 param[2]; - int err; + int err, ret; - param[0] = 0x01; - param[1] = 0x00; + err = btintel_enter_mfg(hdev); + if (err) + return err; - skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - BT_ERR("%s: Entering Intel manufacturer mode failed (%d)", - hdev->name, err); - return PTR_ERR(skb); - } - kfree_skb(skb); + ret = btintel_set_event_mask(hdev, debug); - err = btintel_set_event_mask(hdev, debug); + err = btintel_exit_mfg(hdev, false, false); + if (err) + return err; - param[0] = 0x00; - param[1] = 0x00; + return ret; +} +EXPORT_SYMBOL_GPL(btintel_set_event_mask_mfg); - skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_INIT_TIMEOUT); +int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) +{ + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_CMD_TIMEOUT); if (IS_ERR(skb)) { - err = PTR_ERR(skb); - BT_ERR("%s: Leaving Intel manufacturer mode failed (%d)", - hdev->name, err); + bt_dev_err(hdev, "Reading Intel version information failed (%ld)", + PTR_ERR(skb)); return PTR_ERR(skb); } + + if (skb->len != sizeof(*ver)) { + bt_dev_err(hdev, "Intel version event size mismatch"); + kfree_skb(skb); + return -EILSEQ; + } + + memcpy(ver, skb->data, sizeof(*ver)); + kfree_skb(skb); - return err; + return 0; } -EXPORT_SYMBOL_GPL(btintel_set_event_mask_mfg); +EXPORT_SYMBOL_GPL(btintel_read_version); /* ------- REGMAP IBT SUPPORT ------- */ diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index 07e58e05a7fa6..1e8955aaafedd 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -72,6 +72,8 @@ struct intel_secure_send_result { #if IS_ENABLED(CONFIG_BT_INTEL) int btintel_check_bdaddr(struct hci_dev *hdev); +int btintel_enter_mfg(struct hci_dev *hdev); +int btintel_exit_mfg(struct hci_dev *hdev, bool reset, bool patched); int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr); int btintel_set_diag(struct hci_dev *hdev, bool enable); int btintel_set_diag_mfg(struct hci_dev *hdev, bool enable); @@ -83,6 +85,7 @@ int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen, int btintel_load_ddc_config(struct hci_dev *hdev, const char *ddc_name); int btintel_set_event_mask(struct hci_dev *hdev, bool debug); int btintel_set_event_mask_mfg(struct hci_dev *hdev, bool debug); +int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver); struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read, u16 opcode_write); @@ -94,6 +97,16 @@ static inline int btintel_check_bdaddr(struct hci_dev *hdev) return -EOPNOTSUPP; } +static inline int btintel_enter_mfg(struct hci_dev *hdev) +{ + return -EOPNOTSUPP; +} + +static inline int btintel_exit_mfg(struct hci_dev *hdev, bool reset, bool patched) +{ + return -EOPNOTSUPP; +} + static inline int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) { return -EOPNOTSUPP; @@ -140,6 +153,12 @@ static inline int btintel_set_event_mask_mfg(struct hci_dev *hdev, bool debug) return -EOPNOTSUPP; } +static inline int btintel_read_version(struct hci_dev *hdev, + struct intel_version *ver) +{ + return -EOPNOTSUPP; +} + static inline struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read, u16 opcode_write) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 806353410eb7e..a191e318fab88 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -153,6 +153,10 @@ static const struct usb_device_id btusb_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01), .driver_info = BTUSB_BCM_PATCHRAM }, + /* Toshiba Corp - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x0930, 0xff, 0x01, 0x01), + .driver_info = BTUSB_BCM_PATCHRAM }, + /* Intel Bluetooth USB Bootloader (RAM module) */ { USB_DEVICE(0x8087, 0x0a5a), .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC }, @@ -1642,13 +1646,8 @@ static int btusb_setup_intel(struct hci_dev *hdev) struct sk_buff *skb; const struct firmware *fw; const u8 *fw_ptr; - int disable_patch; - struct intel_version *ver; - - const u8 mfg_enable[] = { 0x01, 0x00 }; - const u8 mfg_disable[] = { 0x00, 0x00 }; - const u8 mfg_reset_deactivate[] = { 0x00, 0x01 }; - const u8 mfg_reset_activate[] = { 0x00, 0x02 }; + int disable_patch, err; + struct intel_version ver; BT_DBG("%s", hdev->name); @@ -1674,35 +1673,22 @@ static int btusb_setup_intel(struct hci_dev *hdev) * The returned information are hardware variant and revision plus * firmware variant, revision and build number. */ - skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s reading Intel fw version command failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - - if (skb->len != sizeof(*ver)) { - BT_ERR("%s Intel version event length mismatch", hdev->name); - kfree_skb(skb); - return -EIO; - } - - ver = (struct intel_version *)skb->data; + err = btintel_read_version(hdev, &ver); + if (err) + return err; BT_INFO("%s: read Intel version: %02x%02x%02x%02x%02x%02x%02x%02x%02x", - hdev->name, ver->hw_platform, ver->hw_variant, - ver->hw_revision, ver->fw_variant, ver->fw_revision, - ver->fw_build_num, ver->fw_build_ww, ver->fw_build_yy, - ver->fw_patch_num); + hdev->name, ver.hw_platform, ver.hw_variant, ver.hw_revision, + ver.fw_variant, ver.fw_revision, ver.fw_build_num, + ver.fw_build_ww, ver.fw_build_yy, ver.fw_patch_num); /* fw_patch_num indicates the version of patch the device currently * have. If there is no patch data in the device, it is always 0x00. * So, if it is other than 0x00, no need to patch the device again. */ - if (ver->fw_patch_num) { + if (ver.fw_patch_num) { BT_INFO("%s: Intel device is already patched. patch num: %02x", - hdev->name, ver->fw_patch_num); - kfree_skb(skb); + hdev->name, ver.fw_patch_num); goto complete; } @@ -1712,31 +1698,21 @@ static int btusb_setup_intel(struct hci_dev *hdev) * If no patch file is found, allow the device to operate without * a patch. */ - fw = btusb_setup_intel_get_fw(hdev, ver); - if (!fw) { - kfree_skb(skb); + fw = btusb_setup_intel_get_fw(hdev, &ver); + if (!fw) goto complete; - } fw_ptr = fw->data; - kfree_skb(skb); - - /* This Intel specific command enables the manufacturer mode of the - * controller. - * + /* Enable the manufacturer mode of the controller. * Only while this mode is enabled, the driver can download the * firmware patch data and configuration parameters. */ - skb = __hci_cmd_sync(hdev, 0xfc11, 2, mfg_enable, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s entering Intel manufacturer mode failed (%ld)", - hdev->name, PTR_ERR(skb)); + err = btintel_enter_mfg(hdev); + if (err) { release_firmware(fw); - return PTR_ERR(skb); + return err; } - kfree_skb(skb); - disable_patch = 1; /* The firmware data file consists of list of Intel specific HCI @@ -1776,14 +1752,9 @@ static int btusb_setup_intel(struct hci_dev *hdev) /* Patching completed successfully and disable the manufacturer mode * with reset and activate the downloaded firmware patches. */ - skb = __hci_cmd_sync(hdev, 0xfc11, sizeof(mfg_reset_activate), - mfg_reset_activate, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s exiting Intel manufacturer mode failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - kfree_skb(skb); + err = btintel_exit_mfg(hdev, true, true); + if (err) + return err; BT_INFO("%s: Intel Bluetooth firmware patch completed and activated", hdev->name); @@ -1792,14 +1763,9 @@ static int btusb_setup_intel(struct hci_dev *hdev) exit_mfg_disable: /* Disable the manufacturer mode without reset */ - skb = __hci_cmd_sync(hdev, 0xfc11, sizeof(mfg_disable), mfg_disable, - HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s exiting Intel manufacturer mode failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - kfree_skb(skb); + err = btintel_exit_mfg(hdev, false, false); + if (err) + return err; BT_INFO("%s: Intel Bluetooth firmware patch completed", hdev->name); @@ -1811,14 +1777,9 @@ exit_mfg_deactivate: /* Patching failed. Disable the manufacturer mode with reset and * deactivate the downloaded firmware patches. */ - skb = __hci_cmd_sync(hdev, 0xfc11, sizeof(mfg_reset_deactivate), - mfg_reset_deactivate, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s exiting Intel manufacturer mode failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - kfree_skb(skb); + err = btintel_exit_mfg(hdev, true, false); + if (err) + return err; BT_INFO("%s: Intel Bluetooth firmware patch completed and deactivated", hdev->name); @@ -2005,7 +1966,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) 0x00, 0x08, 0x04, 0x00 }; struct btusb_data *data = hci_get_drvdata(hdev); struct sk_buff *skb; - struct intel_version *ver; + struct intel_version ver; struct intel_boot_params *params; const struct firmware *fw; const u8 *fw_ptr; @@ -2023,28 +1984,16 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * is in bootloader mode or if it already has operational firmware * loaded. */ - skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s: Reading Intel version information failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - - if (skb->len != sizeof(*ver)) { - BT_ERR("%s: Intel version event size mismatch", hdev->name); - kfree_skb(skb); - return -EILSEQ; - } - - ver = (struct intel_version *)skb->data; + err = btintel_read_version(hdev, &ver); + if (err) + return err; /* The hardware platform number has a fixed value of 0x37 and * for now only accept this single value. */ - if (ver->hw_platform != 0x37) { + if (ver.hw_platform != 0x37) { BT_ERR("%s: Unsupported Intel hardware platform (%u)", - hdev->name, ver->hw_platform); - kfree_skb(skb); + hdev->name, ver.hw_platform); return -EINVAL; } @@ -2053,14 +2002,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * put in place to ensure correct forward compatibility options * when newer hardware variants come along. */ - if (ver->hw_variant != 0x0b) { + if (ver.hw_variant != 0x0b) { BT_ERR("%s: Unsupported Intel hardware variant (%u)", - hdev->name, ver->hw_variant); - kfree_skb(skb); + hdev->name, ver.hw_variant); return -EINVAL; } - btintel_version_info(hdev, ver); + btintel_version_info(hdev, &ver); /* The firmware variant determines if the device is in bootloader * mode or is running operational firmware. The value 0x06 identifies @@ -2075,8 +2023,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * It is not possible to use the Secure Boot Parameters in this * case since that command is only available in bootloader mode. */ - if (ver->fw_variant == 0x23) { - kfree_skb(skb); + if (ver.fw_variant == 0x23) { clear_bit(BTUSB_BOOTLOADER, &data->flags); btintel_check_bdaddr(hdev); return 0; @@ -2085,15 +2032,12 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) /* If the device is not in bootloader mode, then the only possible * choice is to return an error and abort the device initialization. */ - if (ver->fw_variant != 0x06) { + if (ver.fw_variant != 0x06) { BT_ERR("%s: Unsupported Intel firmware variant (%u)", - hdev->name, ver->fw_variant); - kfree_skb(skb); + hdev->name, ver.fw_variant); return -ENODEV; } - kfree_skb(skb); - /* Read the secure boot parameters to identify the operating * details of the bootloader. */ diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 3eed35e0207c4..5c7c696c58381 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -815,6 +815,7 @@ static const struct hci_uart_proto bcm_proto = { #ifdef CONFIG_ACPI static const struct acpi_device_id bcm_acpi_match[] = { { "BCM2E39", 0 }, + { "BCM2E65", 0 }, { "BCM2E67", 0 }, { }, }; diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index db039f2ce6554..0879d64b1caf5 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -116,18 +116,14 @@ static void h5_link_control(struct hci_uart *hu, const void *data, size_t len) static u8 h5_cfg_field(struct h5 *h5) { - u8 field = 0; - /* Sliding window size (first 3 bits) */ - field |= (h5->tx_win & 0x07); - - return field; + return h5->tx_win & 0x07; } static void h5_timed_event(unsigned long arg) { const unsigned char sync_req[] = { 0x01, 0x7e }; - unsigned char conf_req[] = { 0x03, 0xfc, 0x01 }; + unsigned char conf_req[3] = { 0x03, 0xfc }; struct hci_uart *hu = (struct hci_uart *)arg; struct h5 *h5 = hu->priv; struct sk_buff *skb; @@ -285,7 +281,7 @@ static void h5_handle_internal_rx(struct hci_uart *hu) struct h5 *h5 = hu->priv; const unsigned char sync_req[] = { 0x01, 0x7e }; const unsigned char sync_rsp[] = { 0x02, 0x7d }; - unsigned char conf_req[] = { 0x03, 0xfc, 0x01 }; + unsigned char conf_req[3] = { 0x03, 0xfc }; const unsigned char conf_rsp[] = { 0x04, 0x7b }; const unsigned char wakeup_req[] = { 0x05, 0xfa }; const unsigned char woken_req[] = { 0x06, 0xf9 }; @@ -317,7 +313,7 @@ static void h5_handle_internal_rx(struct hci_uart *hu) h5_link_control(hu, conf_req, 3); } else if (memcmp(data, conf_rsp, 2) == 0) { if (H5_HDR_LEN(hdr) > 2) - h5->tx_win = (data[2] & 7); + h5->tx_win = (data[2] & 0x07); BT_DBG("Three-wire init complete. tx_win %u", h5->tx_win); h5->state = H5_ACTIVE; hci_uart_init_ready(hu); diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 69760e2850d96..3d63ea37bd4ca 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -502,7 +502,7 @@ static int intel_set_baudrate(struct hci_uart *hu, unsigned int speed) /* Device will not accept speed change if Intel version has not been * previously requested. */ - skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); + skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_CMD_TIMEOUT); if (IS_ERR(skb)) { bt_dev_err(hdev, "Reading Intel version information failed (%ld)", PTR_ERR(skb)); @@ -542,7 +542,7 @@ static int intel_setup(struct hci_uart *hu) struct intel_device *idev = NULL; struct hci_dev *hdev = hu->hdev; struct sk_buff *skb; - struct intel_version *ver; + struct intel_version ver; struct intel_boot_params *params; struct list_head *p; const struct firmware *fw; @@ -590,35 +590,16 @@ static int intel_setup(struct hci_uart *hu) * is in bootloader mode or if it already has operational firmware * loaded. */ - skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - bt_dev_err(hdev, "Reading Intel version information failed (%ld)", - PTR_ERR(skb)); - return PTR_ERR(skb); - } - - if (skb->len != sizeof(*ver)) { - bt_dev_err(hdev, "Intel version event size mismatch"); - kfree_skb(skb); - return -EILSEQ; - } - - ver = (struct intel_version *)skb->data; - if (ver->status) { - bt_dev_err(hdev, "Intel version command failure (%02x)", - ver->status); - err = -bt_to_errno(ver->status); - kfree_skb(skb); + err = btintel_read_version(hdev, &ver); + if (err) return err; - } /* The hardware platform number has a fixed value of 0x37 and * for now only accept this single value. */ - if (ver->hw_platform != 0x37) { + if (ver.hw_platform != 0x37) { bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)", - ver->hw_platform); - kfree_skb(skb); + ver.hw_platform); return -EINVAL; } @@ -627,14 +608,13 @@ static int intel_setup(struct hci_uart *hu) * put in place to ensure correct forward compatibility options * when newer hardware variants come along. */ - if (ver->hw_variant != 0x0b) { + if (ver.hw_variant != 0x0b) { bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)", - ver->hw_variant); - kfree_skb(skb); + ver.hw_variant); return -EINVAL; } - btintel_version_info(hdev, ver); + btintel_version_info(hdev, &ver); /* The firmware variant determines if the device is in bootloader * mode or is running operational firmware. The value 0x06 identifies @@ -649,8 +629,7 @@ static int intel_setup(struct hci_uart *hu) * It is not possible to use the Secure Boot Parameters in this * case since that command is only available in bootloader mode. */ - if (ver->fw_variant == 0x23) { - kfree_skb(skb); + if (ver.fw_variant == 0x23) { clear_bit(STATE_BOOTLOADER, &intel->flags); btintel_check_bdaddr(hdev); return 0; @@ -659,19 +638,16 @@ static int intel_setup(struct hci_uart *hu) /* If the device is not in bootloader mode, then the only possible * choice is to return an error and abort the device initialization. */ - if (ver->fw_variant != 0x06) { + if (ver.fw_variant != 0x06) { bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)", - ver->fw_variant); - kfree_skb(skb); + ver.fw_variant); return -ENODEV; } - kfree_skb(skb); - /* Read the secure boot parameters to identify the operating * details of the bootloader. */ - skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT); + skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_CMD_TIMEOUT); if (IS_ERR(skb)) { bt_dev_err(hdev, "Reading Intel boot parameters failed (%ld)", PTR_ERR(skb)); @@ -881,7 +857,7 @@ done: set_bit(STATE_BOOTING, &intel->flags); skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param, - HCI_INIT_TIMEOUT); + HCI_CMD_TIMEOUT); if (IS_ERR(skb)) return PTR_ERR(skb); diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 03146d707a95c..73202624133b4 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -462,13 +462,7 @@ static int hci_uart_tty_open(struct tty_struct *tty) INIT_WORK(&hu->init_ready, hci_uart_init_work); INIT_WORK(&hu->write_work, hci_uart_write_work); - /* Flush any pending characters in the driver and line discipline. */ - - /* FIXME: why is this needed. Note don't use ldisc_ref here as the - open path is before the ldisc is referencable */ - - if (tty->ldisc->ops->flush_buffer) - tty->ldisc->ops->flush_buffer(tty); + /* Flush any pending characters in the driver */ tty_driver_flush_buffer(tty); return 0; diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 846bc29c157dc..25996e2561105 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -342,13 +342,13 @@ static int sunxi_rsb_read(struct sunxi_rsb *rsb, u8 rtaddr, u8 addr, ret = _sunxi_rsb_run_xfer(rsb); if (ret) - goto out; + goto unlock; *buf = readl(rsb->regs + RSB_DATA); +unlock: mutex_unlock(&rsb->lock); -out: return ret; } @@ -527,9 +527,9 @@ static int sunxi_rsb_init_device_mode(struct sunxi_rsb *rsb) */ static const struct sunxi_rsb_addr_map sunxi_rsb_addr_maps[] = { - { 0x3e3, 0x2d }, /* Primary PMIC: AXP223, AXP809, AXP81X, ... */ + { 0x3a3, 0x2d }, /* Primary PMIC: AXP223, AXP809, AXP81X, ... */ { 0x745, 0x3a }, /* Secondary PMIC: AXP806, ... */ - { 0xe89, 0x45 }, /* Peripheral IC: AC100, ... */ + { 0xe89, 0x4e }, /* Peripheral IC: AC100, ... */ }; static u8 sunxi_rsb_get_rtaddr(u16 hwaddr) diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 55fe9020459f2..4cc72fa017c7b 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1230,14 +1230,14 @@ static int smi_start_processing(void *send_info, new_smi->intf = intf; - /* Try to claim any interrupts. */ - if (new_smi->irq_setup) - new_smi->irq_setup(new_smi); - /* Set up the timer that drives the interface. */ setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi); smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES); + /* Try to claim any interrupts. */ + if (new_smi->irq_setup) + new_smi->irq_setup(new_smi); + /* * Check if the user forcefully enabled the daemon. */ diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c index 10819e2484145..335322dc403f4 100644 --- a/drivers/clk/clk-gpio.c +++ b/drivers/clk/clk-gpio.c @@ -209,6 +209,8 @@ EXPORT_SYMBOL_GPL(clk_register_gpio_mux); struct clk_gpio_delayed_register_data { const char *gpio_name; + int num_parents; + const char **parent_names; struct device_node *node; struct mutex lock; struct clk *clk; @@ -222,8 +224,6 @@ static struct clk *of_clk_gpio_delayed_register_get( { struct clk_gpio_delayed_register_data *data = _data; struct clk *clk; - const char **parent_names; - int i, num_parents; int gpio; enum of_gpio_flags of_flags; @@ -248,26 +248,14 @@ static struct clk *of_clk_gpio_delayed_register_get( return ERR_PTR(gpio); } - num_parents = of_clk_get_parent_count(data->node); - - parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL); - if (!parent_names) { - clk = ERR_PTR(-ENOMEM); - goto out; - } - - for (i = 0; i < num_parents; i++) - parent_names[i] = of_clk_get_parent_name(data->node, i); - - clk = data->clk_register_get(data->node->name, parent_names, - num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW); + clk = data->clk_register_get(data->node->name, data->parent_names, + data->num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW); if (IS_ERR(clk)) goto out; data->clk = clk; out: mutex_unlock(&data->lock); - kfree(parent_names); return clk; } @@ -296,11 +284,24 @@ static void __init of_gpio_clk_setup(struct device_node *node, unsigned gpio, bool active_low)) { struct clk_gpio_delayed_register_data *data; + const char **parent_names; + int i, num_parents; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return; + num_parents = of_clk_get_parent_count(node); + + parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL); + if (!parent_names) + return; + + for (i = 0; i < num_parents; i++) + parent_names[i] = of_clk_get_parent_name(node, i); + + data->num_parents = num_parents; + data->parent_names = parent_names; data->node = node; data->gpio_name = gpio_name; data->clk_register_get = clk_register_get; diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c index 1ab0fb81c6a0e..7bc1c4527ae48 100644 --- a/drivers/clk/clk-qoriq.c +++ b/drivers/clk/clk-qoriq.c @@ -778,8 +778,10 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx) */ clksel = (cg_in(cg, hwc->reg) & CLKSEL_MASK) >> CLKSEL_SHIFT; div = get_pll_div(cg, hwc, clksel); - if (!div) + if (!div) { + kfree(hwc); return NULL; + } pct80_rate = clk_get_rate(div->clk); pct80_rate *= 8; diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c index 0b501a9fef92b..cd0f2726f5e0d 100644 --- a/drivers/clk/clk-scpi.c +++ b/drivers/clk/clk-scpi.c @@ -292,6 +292,7 @@ static int scpi_clocks_probe(struct platform_device *pdev) ret = scpi_clk_add(dev, child, match); if (ret) { scpi_clocks_remove(pdev); + of_node_put(child); return ret; } } diff --git a/drivers/clk/imx/clk-pllv1.c b/drivers/clk/imx/clk-pllv1.c index 8564e4342c7d1..82fe3662b5f6d 100644 --- a/drivers/clk/imx/clk-pllv1.c +++ b/drivers/clk/imx/clk-pllv1.c @@ -52,7 +52,7 @@ static unsigned long clk_pllv1_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { struct clk_pllv1 *pll = to_clk_pllv1(hw); - long long ll; + unsigned long long ull; int mfn_abs; unsigned int mfi, mfn, mfd, pd; u32 reg; @@ -94,16 +94,16 @@ static unsigned long clk_pllv1_recalc_rate(struct clk_hw *hw, rate = parent_rate * 2; rate /= pd + 1; - ll = (unsigned long long)rate * mfn_abs; + ull = (unsigned long long)rate * mfn_abs; - do_div(ll, mfd + 1); + do_div(ull, mfd + 1); if (mfn_is_negative(pll, mfn)) - ll = -ll; + ull = (rate * mfi) - ull; + else + ull = (rate * mfi) + ull; - ll = (rate * mfi) + ll; - - return ll; + return ull; } static struct clk_ops clk_pllv1_ops = { diff --git a/drivers/clk/imx/clk-pllv2.c b/drivers/clk/imx/clk-pllv2.c index b18f875eac6ac..4aeda56ce3727 100644 --- a/drivers/clk/imx/clk-pllv2.c +++ b/drivers/clk/imx/clk-pllv2.c @@ -79,7 +79,7 @@ static unsigned long __clk_pllv2_recalc_rate(unsigned long parent_rate, { long mfi, mfn, mfd, pdf, ref_clk; unsigned long dbl; - s64 temp; + u64 temp; dbl = dp_ctl & MXC_PLL_DP_CTL_DPDCK0_2_EN; @@ -98,8 +98,9 @@ static unsigned long __clk_pllv2_recalc_rate(unsigned long parent_rate, temp = (u64) ref_clk * abs(mfn); do_div(temp, mfd + 1); if (mfn < 0) - temp = -temp; - temp = (ref_clk * mfi) + temp; + temp = (ref_clk * mfi) - temp; + else + temp = (ref_clk * mfi) + temp; return temp; } @@ -126,7 +127,7 @@ static int __clk_pllv2_set_rate(unsigned long rate, unsigned long parent_rate, { u32 reg; long mfi, pdf, mfn, mfd = 999999; - s64 temp64; + u64 temp64; unsigned long quad_parent_rate; quad_parent_rate = 4 * parent_rate; diff --git a/drivers/clk/imx/clk-vf610.c b/drivers/clk/imx/clk-vf610.c index d1b1c95177bbe..0a94d9661d912 100644 --- a/drivers/clk/imx/clk-vf610.c +++ b/drivers/clk/imx/clk-vf610.c @@ -335,22 +335,22 @@ static void __init vf610_clocks_init(struct device_node *ccm_node) clk[VF610_CLK_SAI0_SEL] = imx_clk_mux("sai0_sel", CCM_CSCMR1, 0, 2, sai_sels, 4); clk[VF610_CLK_SAI0_EN] = imx_clk_gate("sai0_en", "sai0_sel", CCM_CSCDR1, 16); clk[VF610_CLK_SAI0_DIV] = imx_clk_divider("sai0_div", "sai0_en", CCM_CSCDR1, 0, 4); - clk[VF610_CLK_SAI0] = imx_clk_gate2("sai0", "sai0_div", CCM_CCGR0, CCM_CCGRx_CGn(15)); + clk[VF610_CLK_SAI0] = imx_clk_gate2("sai0", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(15)); clk[VF610_CLK_SAI1_SEL] = imx_clk_mux("sai1_sel", CCM_CSCMR1, 2, 2, sai_sels, 4); clk[VF610_CLK_SAI1_EN] = imx_clk_gate("sai1_en", "sai1_sel", CCM_CSCDR1, 17); clk[VF610_CLK_SAI1_DIV] = imx_clk_divider("sai1_div", "sai1_en", CCM_CSCDR1, 4, 4); - clk[VF610_CLK_SAI1] = imx_clk_gate2("sai1", "sai1_div", CCM_CCGR1, CCM_CCGRx_CGn(0)); + clk[VF610_CLK_SAI1] = imx_clk_gate2("sai1", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(0)); clk[VF610_CLK_SAI2_SEL] = imx_clk_mux("sai2_sel", CCM_CSCMR1, 4, 2, sai_sels, 4); clk[VF610_CLK_SAI2_EN] = imx_clk_gate("sai2_en", "sai2_sel", CCM_CSCDR1, 18); clk[VF610_CLK_SAI2_DIV] = imx_clk_divider("sai2_div", "sai2_en", CCM_CSCDR1, 8, 4); - clk[VF610_CLK_SAI2] = imx_clk_gate2("sai2", "sai2_div", CCM_CCGR1, CCM_CCGRx_CGn(1)); + clk[VF610_CLK_SAI2] = imx_clk_gate2("sai2", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(1)); clk[VF610_CLK_SAI3_SEL] = imx_clk_mux("sai3_sel", CCM_CSCMR1, 6, 2, sai_sels, 4); clk[VF610_CLK_SAI3_EN] = imx_clk_gate("sai3_en", "sai3_sel", CCM_CSCDR1, 19); clk[VF610_CLK_SAI3_DIV] = imx_clk_divider("sai3_div", "sai3_en", CCM_CSCDR1, 12, 4); - clk[VF610_CLK_SAI3] = imx_clk_gate2("sai3", "sai3_div", CCM_CCGR1, CCM_CCGRx_CGn(2)); + clk[VF610_CLK_SAI3] = imx_clk_gate2("sai3", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(2)); clk[VF610_CLK_NFC_SEL] = imx_clk_mux("nfc_sel", CCM_CSCMR1, 12, 2, nfc_sels, 4); clk[VF610_CLK_NFC_EN] = imx_clk_gate("nfc_en", "nfc_sel", CCM_CSCDR2, 9); diff --git a/drivers/clk/mmp/clk-mmp2.c b/drivers/clk/mmp/clk-mmp2.c index 09d2832fbd782..71fd29348f28b 100644 --- a/drivers/clk/mmp/clk-mmp2.c +++ b/drivers/clk/mmp/clk-mmp2.c @@ -9,6 +9,7 @@ * warranty of any kind, whether express or implied. */ +#include <linux/clk.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/spinlock.h> diff --git a/drivers/clk/mmp/clk-pxa168.c b/drivers/clk/mmp/clk-pxa168.c index 93e967c0f972f..75244915df05f 100644 --- a/drivers/clk/mmp/clk-pxa168.c +++ b/drivers/clk/mmp/clk-pxa168.c @@ -9,6 +9,7 @@ * warranty of any kind, whether express or implied. */ +#include <linux/clk.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/spinlock.h> diff --git a/drivers/clk/mmp/clk-pxa910.c b/drivers/clk/mmp/clk-pxa910.c index 993abcdb32cce..37ba04ba13686 100644 --- a/drivers/clk/mmp/clk-pxa910.c +++ b/drivers/clk/mmp/clk-pxa910.c @@ -9,6 +9,7 @@ * warranty of any kind, whether express or implied. */ +#include <linux/clk.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/spinlock.h> diff --git a/drivers/clk/sunxi/clk-a10-pll2.c b/drivers/clk/sunxi/clk-a10-pll2.c index 5484c31ec5683..0ee1f363e4be1 100644 --- a/drivers/clk/sunxi/clk-a10-pll2.c +++ b/drivers/clk/sunxi/clk-a10-pll2.c @@ -41,15 +41,10 @@ #define SUN4I_PLL2_OUTPUTS 4 -struct sun4i_pll2_data { - u32 post_div_offset; - u32 pre_div_flags; -}; - static DEFINE_SPINLOCK(sun4i_a10_pll2_lock); static void __init sun4i_pll2_setup(struct device_node *node, - struct sun4i_pll2_data *data) + int post_div_offset) { const char *clk_name = node->name, *parent; struct clk **clks, *base_clk, *prediv_clk; @@ -76,7 +71,7 @@ static void __init sun4i_pll2_setup(struct device_node *node, parent, 0, reg, SUN4I_PLL2_PRE_DIV_SHIFT, SUN4I_PLL2_PRE_DIV_WIDTH, - data->pre_div_flags, + CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO, &sun4i_a10_pll2_lock); if (!prediv_clk) { pr_err("Couldn't register the prediv clock\n"); @@ -127,7 +122,7 @@ static void __init sun4i_pll2_setup(struct device_node *node, */ val = readl(reg); val &= ~(SUN4I_PLL2_POST_DIV_MASK << SUN4I_PLL2_POST_DIV_SHIFT); - val |= (SUN4I_PLL2_POST_DIV_VALUE - data->post_div_offset) << SUN4I_PLL2_POST_DIV_SHIFT; + val |= (SUN4I_PLL2_POST_DIV_VALUE - post_div_offset) << SUN4I_PLL2_POST_DIV_SHIFT; writel(val, reg); of_property_read_string_index(node, "clock-output-names", @@ -191,25 +186,17 @@ err_unmap: iounmap(reg); } -static struct sun4i_pll2_data sun4i_a10_pll2_data = { - .pre_div_flags = CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO, -}; - static void __init sun4i_a10_pll2_setup(struct device_node *node) { - sun4i_pll2_setup(node, &sun4i_a10_pll2_data); + sun4i_pll2_setup(node, 0); } CLK_OF_DECLARE(sun4i_a10_pll2, "allwinner,sun4i-a10-pll2-clk", sun4i_a10_pll2_setup); -static struct sun4i_pll2_data sun5i_a13_pll2_data = { - .post_div_offset = 1, -}; - static void __init sun5i_a13_pll2_setup(struct device_node *node) { - sun4i_pll2_setup(node, &sun5i_a13_pll2_data); + sun4i_pll2_setup(node, 1); } CLK_OF_DECLARE(sun5i_a13_pll2, "allwinner,sun5i-a13-pll2-clk", diff --git a/drivers/clk/ti/clk-816x.c b/drivers/clk/ti/clk-816x.c index 1dfad0c712cd8..2a5d84fdddc5d 100644 --- a/drivers/clk/ti/clk-816x.c +++ b/drivers/clk/ti/clk-816x.c @@ -20,6 +20,8 @@ static struct ti_dt_clk dm816x_clks[] = { DT_CLK(NULL, "sys_clkin", "sys_clkin_ck"), DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"), DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"), + DT_CLK(NULL, "timer_32k_ck", "sysclk18_ck"), + DT_CLK(NULL, "timer_ext_ck", "tclkin_ck"), DT_CLK(NULL, "mpu_ck", "mpu_ck"), DT_CLK(NULL, "timer1_fck", "timer1_fck"), DT_CLK(NULL, "timer2_fck", "timer2_fck"), diff --git a/drivers/clk/ti/clkt_dpll.c b/drivers/clk/ti/clkt_dpll.c index 9023ca9caf84d..b5cc6f66ae5df 100644 --- a/drivers/clk/ti/clkt_dpll.c +++ b/drivers/clk/ti/clkt_dpll.c @@ -240,7 +240,7 @@ u8 omap2_init_dpll_parent(struct clk_hw *hw) */ unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk) { - long long dpll_clk; + u64 dpll_clk; u32 dpll_mult, dpll_div, v; struct dpll_data *dd; @@ -262,7 +262,7 @@ unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk) dpll_div = v & dd->div1_mask; dpll_div >>= __ffs(dd->div1_mask); - dpll_clk = (long long)clk_get_rate(dd->clk_ref) * dpll_mult; + dpll_clk = (u64)clk_get_rate(dd->clk_ref) * dpll_mult; do_div(dpll_clk, dpll_div + 1); return dpll_clk; diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c index 5b1726829e6df..df2558350fc1d 100644 --- a/drivers/clk/ti/divider.c +++ b/drivers/clk/ti/divider.c @@ -214,7 +214,6 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, { struct clk_divider *divider; unsigned int div, value; - unsigned long flags = 0; u32 val; if (!hw || !rate) @@ -228,9 +227,6 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, if (value > div_mask(divider)) value = div_mask(divider); - if (divider->lock) - spin_lock_irqsave(divider->lock, flags); - if (divider->flags & CLK_DIVIDER_HIWORD_MASK) { val = div_mask(divider) << (divider->shift + 16); } else { @@ -240,9 +236,6 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, val |= value << divider->shift; ti_clk_ll_ops->clk_writel(val, divider->reg); - if (divider->lock) - spin_unlock_irqrestore(divider->lock, flags); - return 0; } @@ -256,8 +249,7 @@ static struct clk *_register_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, - const struct clk_div_table *table, - spinlock_t *lock) + const struct clk_div_table *table) { struct clk_divider *div; struct clk *clk; @@ -288,7 +280,6 @@ static struct clk *_register_divider(struct device *dev, const char *name, div->shift = shift; div->width = width; div->flags = clk_divider_flags; - div->lock = lock; div->hw.init = &init; div->table = table; @@ -421,7 +412,7 @@ struct clk *ti_clk_register_divider(struct ti_clk *setup) clk = _register_divider(NULL, setup->name, div->parent, flags, (void __iomem *)reg, div->bit_shift, - width, div_flags, table, NULL); + width, div_flags, table); if (IS_ERR(clk)) kfree(table); @@ -584,8 +575,7 @@ static void __init of_ti_divider_clk_setup(struct device_node *node) goto cleanup; clk = _register_divider(NULL, node->name, parent_name, flags, reg, - shift, width, clk_divider_flags, table, - NULL); + shift, width, clk_divider_flags, table); if (!IS_ERR(clk)) { of_clk_add_provider(node, of_clk_src_simple_get, clk); diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c index f4b2e9888bdf3..66a0d0ed8b550 100644 --- a/drivers/clk/ti/fapll.c +++ b/drivers/clk/ti/fapll.c @@ -168,7 +168,7 @@ static unsigned long ti_fapll_recalc_rate(struct clk_hw *hw, { struct fapll_data *fd = to_fapll(hw); u32 fapll_n, fapll_p, v; - long long rate; + u64 rate; if (ti_fapll_clock_is_bypass(fd)) return parent_rate; @@ -314,7 +314,7 @@ static unsigned long ti_fapll_synth_recalc_rate(struct clk_hw *hw, { struct fapll_synth *synth = to_synth(hw); u32 synth_div_m; - long long rate; + u64 rate; /* The audio_pll_clk1 is hardwired to produce 32.768KiHz clock */ if (!synth->div) diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c index 69f08a1d047d8..dab9ba88b9d6d 100644 --- a/drivers/clk/ti/mux.c +++ b/drivers/clk/ti/mux.c @@ -69,7 +69,6 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index) { struct clk_mux *mux = to_clk_mux(hw); u32 val; - unsigned long flags = 0; if (mux->table) { index = mux->table[index]; @@ -81,9 +80,6 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index) index++; } - if (mux->lock) - spin_lock_irqsave(mux->lock, flags); - if (mux->flags & CLK_MUX_HIWORD_MASK) { val = mux->mask << (mux->shift + 16); } else { @@ -93,9 +89,6 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index) val |= index << mux->shift; ti_clk_ll_ops->clk_writel(val, mux->reg); - if (mux->lock) - spin_unlock_irqrestore(mux->lock, flags); - return 0; } @@ -109,7 +102,7 @@ static struct clk *_register_mux(struct device *dev, const char *name, const char **parent_names, u8 num_parents, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, - u32 *table, spinlock_t *lock) + u32 *table) { struct clk_mux *mux; struct clk *clk; @@ -133,7 +126,6 @@ static struct clk *_register_mux(struct device *dev, const char *name, mux->shift = shift; mux->mask = mask; mux->flags = clk_mux_flags; - mux->lock = lock; mux->table = table; mux->hw.init = &init; @@ -175,7 +167,7 @@ struct clk *ti_clk_register_mux(struct ti_clk *setup) return _register_mux(NULL, setup->name, mux->parents, mux->num_parents, flags, (void __iomem *)reg, mux->bit_shift, mask, - mux_flags, NULL, NULL); + mux_flags, NULL); } /** @@ -227,8 +219,7 @@ static void of_mux_clk_setup(struct device_node *node) mask = (1 << fls(mask)) - 1; clk = _register_mux(NULL, node->name, parent_names, num_parents, - flags, reg, shift, mask, clk_mux_flags, NULL, - NULL); + flags, reg, shift, mask, clk_mux_flags, NULL); if (!IS_ERR(clk)) of_clk_add_provider(node, of_clk_src_simple_get, clk); diff --git a/drivers/clocksource/mmio.c b/drivers/clocksource/mmio.c index 1593ade2a8154..c4f7d7a9b6898 100644 --- a/drivers/clocksource/mmio.c +++ b/drivers/clocksource/mmio.c @@ -55,7 +55,7 @@ int __init clocksource_mmio_init(void __iomem *base, const char *name, { struct clocksource_mmio *cs; - if (bits > 32 || bits < 16) + if (bits > 64 || bits < 16) return -EINVAL; cs = kzalloc(sizeof(struct clocksource_mmio), GFP_KERNEL); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 235a1ba73d92d..b1f8a73e5a943 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -226,7 +226,7 @@ config ARM_TEGRA20_CPUFREQ config ARM_TEGRA124_CPUFREQ tristate "Tegra124 CPUFreq support" - depends on ARCH_TEGRA && CPUFREQ_DT + depends on ARCH_TEGRA && CPUFREQ_DT && REGULATOR default y help This adds the CPUFreq driver support for Tegra124 SOCs. diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index a83c995a62dfe..8412ce5f93a71 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -976,10 +976,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy) new_policy.governor = gov; - /* Use the default policy if its valid. */ - if (cpufreq_driver->setpolicy) - cpufreq_parse_governor(gov->name, &new_policy.policy, NULL); - + /* Use the default policy if there is no last_policy. */ + if (cpufreq_driver->setpolicy) { + if (policy->last_policy) + new_policy.policy = policy->last_policy; + else + cpufreq_parse_governor(gov->name, &new_policy.policy, + NULL); + } /* set default policy */ return cpufreq_set_policy(policy, &new_policy); } @@ -1330,6 +1334,8 @@ static void cpufreq_offline_prepare(unsigned int cpu) if (has_target()) strncpy(policy->last_governor, policy->governor->name, CPUFREQ_NAME_LEN); + else + policy->last_policy = policy->policy; } else if (cpu == policy->cpu) { /* Nominate new CPU */ policy->cpu = cpumask_any(policy->cpus); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 4d07cbd2b23cf..98fb8821382d8 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1123,7 +1123,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits->max_sysfs_pct); limits->max_perf_pct = max(limits->min_policy_pct, limits->max_perf_pct); - limits->max_perf = round_up(limits->max_perf, 8); + limits->max_perf = round_up(limits->max_perf, FRAC_BITS); /* Make sure min_perf_pct <= max_perf_pct */ limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 733aa5153e745..68ef8fd9482fd 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -648,7 +648,7 @@ late_initcall(s3c_cpufreq_initcall); * * Register the given set of PLLs with the system. */ -int __init s3c_plltab_register(struct cpufreq_frequency_table *plls, +int s3c_plltab_register(struct cpufreq_frequency_table *plls, unsigned int plls_no) { struct cpufreq_frequency_table *vals; diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index 2c3b16fd3a01f..de5e89b2eaaa3 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -31,7 +31,7 @@ static struct scpi_ops *scpi_ops; static struct scpi_dvfs_info *scpi_get_dvfs_info(struct device *cpu_dev) { - u8 domain = topology_physical_package_id(cpu_dev->id); + int domain = topology_physical_package_id(cpu_dev->id); if (domain < 0) return ERR_PTR(-EINVAL); diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c index 73ef499227881..7038f364acb51 100644 --- a/drivers/crypto/nx/nx-aes-ccm.c +++ b/drivers/crypto/nx/nx-aes-ccm.c @@ -409,7 +409,7 @@ static int ccm_nx_decrypt(struct aead_request *req, processed += to_process; } while (processed < nbytes); - rc = memcmp(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag, + rc = crypto_memneq(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag, authsize) ? -EBADMSG : 0; out: spin_unlock_irqrestore(&nx_ctx->lock, irq_flags); diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c index eee624f589b65..abd465f479c43 100644 --- a/drivers/crypto/nx/nx-aes-gcm.c +++ b/drivers/crypto/nx/nx-aes-gcm.c @@ -21,6 +21,7 @@ #include <crypto/internal/aead.h> #include <crypto/aes.h> +#include <crypto/algapi.h> #include <crypto/scatterwalk.h> #include <linux/module.h> #include <linux/types.h> @@ -418,7 +419,7 @@ mac: itag, req->src, req->assoclen + nbytes, crypto_aead_authsize(crypto_aead_reqtfm(req)), SCATTERWALK_FROM_SG); - rc = memcmp(itag, otag, + rc = crypto_memneq(itag, otag, crypto_aead_authsize(crypto_aead_reqtfm(req))) ? -EBADMSG : 0; } diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 46f531e19ccf0..b6f9f42e2985b 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -977,7 +977,7 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev, } else oicv = (char *)&edesc->link_tbl[0]; - err = memcmp(oicv, icv, authsize) ? -EBADMSG : 0; + err = crypto_memneq(oicv, icv, authsize) ? -EBADMSG : 0; } kfree(edesc); diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7f039de143f0d..370c661c7d7b2 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -156,7 +156,7 @@ #define AT_XDMAC_CC_WRIP (0x1 << 23) /* Write in Progress (read only) */ #define AT_XDMAC_CC_WRIP_DONE (0x0 << 23) #define AT_XDMAC_CC_WRIP_IN_PROGRESS (0x1 << 23) -#define AT_XDMAC_CC_PERID(i) (0x7f & (h) << 24) /* Channel Peripheral Identifier */ +#define AT_XDMAC_CC_PERID(i) (0x7f & (i) << 24) /* Channel Peripheral Identifier */ #define AT_XDMAC_CDS_MSP 0x2C /* Channel Data Stride Memory Set Pattern */ #define AT_XDMAC_CSUS 0x30 /* Channel Source Microblock Stride */ #define AT_XDMAC_CDUS 0x34 /* Channel Destination Microblock Stride */ @@ -965,7 +965,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); - for (i = 0; i < xt->numf; i++) + + /* Length of the block is (BLEN+1) microblocks. */ + for (i = 0; i < xt->numf - 1; i++) at_xdmac_increment_block_count(chan, first); dev_dbg(chan2dev(chan), "%s: add desc 0x%p to descs_list 0x%p\n", @@ -1086,6 +1088,7 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, /* Check remaining length and change data width if needed. */ dwidth = at_xdmac_align_width(chan, src_addr | dst_addr | xfer_size); + chan_cc &= ~AT_XDMAC_CC_DWIDTH_MASK; chan_cc |= AT_XDMAC_CC_DWIDTH(dwidth); ublen = xfer_size >> dwidth; @@ -1333,7 +1336,7 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl, * since we don't care about the stride anymore. */ if ((i == (sg_len - 1)) && - sg_dma_len(ppsg) == sg_dma_len(psg)) { + sg_dma_len(psg) == sg_dma_len(sg)) { dev_dbg(chan2dev(chan), "%s: desc 0x%p can be merged with desc 0x%p\n", __func__, desc, pdesc); diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index c92d6a70ccf30..996c4b00d323e 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -31,6 +31,7 @@ */ #include <linux/dmaengine.h> #include <linux/dma-mapping.h> +#include <linux/dmapool.h> #include <linux/err.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -62,6 +63,11 @@ struct bcm2835_dma_cb { uint32_t pad[2]; }; +struct bcm2835_cb_entry { + struct bcm2835_dma_cb *cb; + dma_addr_t paddr; +}; + struct bcm2835_chan { struct virt_dma_chan vc; struct list_head node; @@ -72,18 +78,18 @@ struct bcm2835_chan { int ch; struct bcm2835_desc *desc; + struct dma_pool *cb_pool; void __iomem *chan_base; int irq_number; }; struct bcm2835_desc { + struct bcm2835_chan *c; struct virt_dma_desc vd; enum dma_transfer_direction dir; - unsigned int control_block_size; - struct bcm2835_dma_cb *control_block_base; - dma_addr_t control_block_base_phys; + struct bcm2835_cb_entry *cb_list; unsigned int frames; size_t size; @@ -143,10 +149,13 @@ static inline struct bcm2835_desc *to_bcm2835_dma_desc( static void bcm2835_dma_desc_free(struct virt_dma_desc *vd) { struct bcm2835_desc *desc = container_of(vd, struct bcm2835_desc, vd); - dma_free_coherent(desc->vd.tx.chan->device->dev, - desc->control_block_size, - desc->control_block_base, - desc->control_block_base_phys); + int i; + + for (i = 0; i < desc->frames; i++) + dma_pool_free(desc->c->cb_pool, desc->cb_list[i].cb, + desc->cb_list[i].paddr); + + kfree(desc->cb_list); kfree(desc); } @@ -199,7 +208,7 @@ static void bcm2835_dma_start_desc(struct bcm2835_chan *c) c->desc = d = to_bcm2835_dma_desc(&vd->tx); - writel(d->control_block_base_phys, c->chan_base + BCM2835_DMA_ADDR); + writel(d->cb_list[0].paddr, c->chan_base + BCM2835_DMA_ADDR); writel(BCM2835_DMA_ACTIVE, c->chan_base + BCM2835_DMA_CS); } @@ -232,9 +241,16 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan) { struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); + struct device *dev = c->vc.chan.device->dev; + + dev_dbg(dev, "Allocating DMA channel %d\n", c->ch); - dev_dbg(c->vc.chan.device->dev, - "Allocating DMA channel %d\n", c->ch); + c->cb_pool = dma_pool_create(dev_name(dev), dev, + sizeof(struct bcm2835_dma_cb), 0, 0); + if (!c->cb_pool) { + dev_err(dev, "unable to allocate descriptor pool\n"); + return -ENOMEM; + } return request_irq(c->irq_number, bcm2835_dma_callback, 0, "DMA IRQ", c); @@ -246,6 +262,7 @@ static void bcm2835_dma_free_chan_resources(struct dma_chan *chan) vchan_free_chan_resources(&c->vc); free_irq(c->irq_number, c); + dma_pool_destroy(c->cb_pool); dev_dbg(c->vc.chan.device->dev, "Freeing DMA channel %u\n", c->ch); } @@ -261,8 +278,7 @@ static size_t bcm2835_dma_desc_size_pos(struct bcm2835_desc *d, dma_addr_t addr) size_t size; for (size = i = 0; i < d->frames; i++) { - struct bcm2835_dma_cb *control_block = - &d->control_block_base[i]; + struct bcm2835_dma_cb *control_block = d->cb_list[i].cb; size_t this_size = control_block->length; dma_addr_t dma; @@ -343,6 +359,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( dma_addr_t dev_addr; unsigned int es, sync_type; unsigned int frame; + int i; /* Grab configuration */ if (!is_slave_direction(direction)) { @@ -374,27 +391,31 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( if (!d) return NULL; + d->c = c; d->dir = direction; d->frames = buf_len / period_len; - /* Allocate memory for control blocks */ - d->control_block_size = d->frames * sizeof(struct bcm2835_dma_cb); - d->control_block_base = dma_zalloc_coherent(chan->device->dev, - d->control_block_size, &d->control_block_base_phys, - GFP_NOWAIT); - - if (!d->control_block_base) { + d->cb_list = kcalloc(d->frames, sizeof(*d->cb_list), GFP_KERNEL); + if (!d->cb_list) { kfree(d); return NULL; } + /* Allocate memory for control blocks */ + for (i = 0; i < d->frames; i++) { + struct bcm2835_cb_entry *cb_entry = &d->cb_list[i]; + + cb_entry->cb = dma_pool_zalloc(c->cb_pool, GFP_ATOMIC, + &cb_entry->paddr); + if (!cb_entry->cb) + goto error_cb; + } /* * Iterate over all frames, create a control block * for each frame and link them together. */ for (frame = 0; frame < d->frames; frame++) { - struct bcm2835_dma_cb *control_block = - &d->control_block_base[frame]; + struct bcm2835_dma_cb *control_block = d->cb_list[frame].cb; /* Setup adresses */ if (d->dir == DMA_DEV_TO_MEM) { @@ -428,12 +449,21 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( * This DMA engine driver currently only supports cyclic DMA. * Therefore, wrap around at number of frames. */ - control_block->next = d->control_block_base_phys + - sizeof(struct bcm2835_dma_cb) - * ((frame + 1) % d->frames); + control_block->next = d->cb_list[((frame + 1) % d->frames)].paddr; } return vchan_tx_prep(&c->vc, &d->vd, flags); +error_cb: + i--; + for (; i >= 0; i--) { + struct bcm2835_cb_entry *cb_entry = &d->cb_list[i]; + + dma_pool_free(c->cb_pool, cb_entry->cb, cb_entry->paddr); + } + + kfree(d->cb_list); + kfree(d); + return NULL; } static int bcm2835_dma_slave_config(struct dma_chan *chan, diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 0675e268d5777..16fe773fb846b 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -1752,16 +1752,14 @@ static enum dma_status edma_tx_status(struct dma_chan *chan, return ret; } -static bool edma_is_memcpy_channel(int ch_num, u16 *memcpy_channels) +static bool edma_is_memcpy_channel(int ch_num, s32 *memcpy_channels) { - s16 *memcpy_ch = memcpy_channels; - if (!memcpy_channels) return false; - while (*memcpy_ch != -1) { - if (*memcpy_ch == ch_num) + while (*memcpy_channels != -1) { + if (*memcpy_channels == ch_num) return true; - memcpy_ch++; + memcpy_channels++; } return false; } @@ -1775,7 +1773,7 @@ static void edma_dma_init(struct edma_cc *ecc, bool legacy_mode) { struct dma_device *s_ddev = &ecc->dma_slave; struct dma_device *m_ddev = NULL; - s16 *memcpy_channels = ecc->info->memcpy_channels; + s32 *memcpy_channels = ecc->info->memcpy_channels; int i, j; dma_cap_zero(s_ddev->cap_mask); @@ -1996,16 +1994,16 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev, prop = of_find_property(dev->of_node, "ti,edma-memcpy-channels", &sz); if (prop) { const char pname[] = "ti,edma-memcpy-channels"; - size_t nelm = sz / sizeof(s16); - s16 *memcpy_ch; + size_t nelm = sz / sizeof(s32); + s32 *memcpy_ch; - memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s16), + memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s32), GFP_KERNEL); if (!memcpy_ch) return ERR_PTR(-ENOMEM); - ret = of_property_read_u16_array(dev->of_node, pname, - (u16 *)memcpy_ch, nelm); + ret = of_property_read_u32_array(dev->of_node, pname, + (u32 *)memcpy_ch, nelm); if (ret) return ERR_PTR(ret); @@ -2017,31 +2015,50 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev, &sz); if (prop) { const char pname[] = "ti,edma-reserved-slot-ranges"; + u32 (*tmp)[2]; s16 (*rsv_slots)[2]; - size_t nelm = sz / sizeof(*rsv_slots); + size_t nelm = sz / sizeof(*tmp); struct edma_rsv_info *rsv_info; + int i; if (!nelm) return info; + tmp = kcalloc(nelm, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ERR_PTR(-ENOMEM); + rsv_info = devm_kzalloc(dev, sizeof(*rsv_info), GFP_KERNEL); - if (!rsv_info) + if (!rsv_info) { + kfree(tmp); return ERR_PTR(-ENOMEM); + } rsv_slots = devm_kcalloc(dev, nelm + 1, sizeof(*rsv_slots), GFP_KERNEL); - if (!rsv_slots) + if (!rsv_slots) { + kfree(tmp); return ERR_PTR(-ENOMEM); + } - ret = of_property_read_u16_array(dev->of_node, pname, - (u16 *)rsv_slots, nelm * 2); - if (ret) + ret = of_property_read_u32_array(dev->of_node, pname, + (u32 *)tmp, nelm * 2); + if (ret) { + kfree(tmp); return ERR_PTR(ret); + } + for (i = 0; i < nelm; i++) { + rsv_slots[i][0] = tmp[i][0]; + rsv_slots[i][1] = tmp[i][1]; + } rsv_slots[nelm][0] = -1; rsv_slots[nelm][1] = -1; + info->rsv = rsv_info; info->rsv->rsv_slots = (const s16 (*)[2])rsv_slots; + + kfree(tmp); } return info; diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index 068e920ecb68d..cddfa8dbf4bdf 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -317,6 +317,7 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); struct device *dev = mic_dma_ch_to_device(mic_ch); int result; + struct dma_async_tx_descriptor *tx = NULL; if (!len && !flags) return NULL; @@ -324,10 +325,13 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, spin_lock(&mic_ch->prep_lock); result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len); if (result >= 0) - return allocate_tx(mic_ch); - dev_err(dev, "Error enqueueing dma, error=%d\n", result); + tx = allocate_tx(mic_ch); + + if (!tx) + dev_err(dev, "Error enqueueing dma, error=%d\n", result); + spin_unlock(&mic_ch->prep_lock); - return NULL; + return tx; } static struct dma_async_tx_descriptor * @@ -335,13 +339,14 @@ mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags) { struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); int ret; + struct dma_async_tx_descriptor *tx = NULL; spin_lock(&mic_ch->prep_lock); ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0); if (!ret) - return allocate_tx(mic_ch); + tx = allocate_tx(mic_ch); spin_unlock(&mic_ch->prep_lock); - return NULL; + return tx; } /* Return the status of the transaction */ diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index a24f5cb877e0a..953dc9195937d 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -122,12 +122,10 @@ int fpga_mgr_firmware_load(struct fpga_manager *mgr, u32 flags, } ret = fpga_mgr_buf_load(mgr, flags, fw->data, fw->size); - if (ret) - return ret; release_firmware(fw); - return 0; + return ret; } EXPORT_SYMBOL_GPL(fpga_mgr_firmware_load); @@ -256,7 +254,6 @@ int fpga_mgr_register(struct device *dev, const char *name, void *priv) { struct fpga_manager *mgr; - const char *dt_label; int id, ret; if (!mops || !mops->write_init || !mops->write || @@ -300,11 +297,9 @@ int fpga_mgr_register(struct device *dev, const char *name, mgr->dev.id = id; dev_set_drvdata(dev, mgr); - dt_label = of_get_property(mgr->dev.of_node, "label", NULL); - if (dt_label) - ret = dev_set_name(&mgr->dev, "%s", dt_label); - else - ret = dev_set_name(&mgr->dev, "fpga%d", id); + ret = dev_set_name(&mgr->dev, "fpga%d", id); + if (ret) + goto error_device; ret = device_add(&mgr->dev); if (ret) diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c index e5827a56ff3b5..5eaea8b812cf3 100644 --- a/drivers/gpio/gpio-ath79.c +++ b/drivers/gpio/gpio-ath79.c @@ -113,7 +113,7 @@ static int ar934x_gpio_direction_output(struct gpio_chip *chip, unsigned offset, __raw_writel(BIT(offset), ctrl->base + AR71XX_GPIO_REG_CLEAR); __raw_writel( - __raw_readl(ctrl->base + AR71XX_GPIO_REG_OE) & BIT(offset), + __raw_readl(ctrl->base + AR71XX_GPIO_REG_OE) & ~BIT(offset), ctrl->base + AR71XX_GPIO_REG_OE); spin_unlock_irqrestore(&ctrl->lock, flags); diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c index bd5193c67a9c2..88ae70ddb1274 100644 --- a/drivers/gpio/gpio-generic.c +++ b/drivers/gpio/gpio-generic.c @@ -141,9 +141,9 @@ static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio) unsigned long pinmask = bgc->pin2mask(bgc, gpio); if (bgc->dir & pinmask) - return bgc->read_reg(bgc->reg_set) & pinmask; + return !!(bgc->read_reg(bgc->reg_set) & pinmask); else - return bgc->read_reg(bgc->reg_dat) & pinmask; + return !!(bgc->read_reg(bgc->reg_dat) & pinmask); } static int bgpio_get(struct gpio_chip *gc, unsigned int gpio) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 2a91f3287e3b7..4e4c3083ae567 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1279,7 +1279,13 @@ static int _gpiod_get_raw_value(const struct gpio_desc *desc) chip = desc->chip; offset = gpio_chip_hwgpio(desc); value = chip->get ? chip->get(chip, offset) : -EIO; - value = value < 0 ? value : !!value; + /* + * FIXME: fix all drivers to clamp to [0,1] or return negative, + * then change this to: + * value = value < 0 ? value : !!value; + * so we can properly propagate error codes. + */ + value = !!value; trace_gpio_value(desc_to_gpio(desc), 1, value); return value; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 251b14736de92..048cfe073dae6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -539,6 +539,7 @@ struct amdgpu_bo { /* Constant after initialization */ struct amdgpu_device *adev; struct drm_gem_object gem_base; + struct amdgpu_bo *parent; struct ttm_bo_kmap_obj dma_buf_vmap; pid_t pid; @@ -955,6 +956,8 @@ struct amdgpu_vm { struct amdgpu_vm_id ids[AMDGPU_MAX_RINGS]; /* for interval tree */ spinlock_t it_lock; + /* protecting freed */ + spinlock_t freed_lock; }; struct amdgpu_vm_manager { @@ -1261,7 +1264,8 @@ struct amdgpu_cs_parser { struct ww_acquire_ctx ticket; /* user fence */ - struct amdgpu_user_fence uf; + struct amdgpu_user_fence uf; + struct amdgpu_bo_list_entry uf_entry; }; struct amdgpu_job { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 1d44d508d4d4f..25a3e2485cc2e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -127,6 +127,37 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, return 0; } +static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, + struct drm_amdgpu_cs_chunk_fence *fence_data) +{ + struct drm_gem_object *gobj; + uint32_t handle; + + handle = fence_data->handle; + gobj = drm_gem_object_lookup(p->adev->ddev, p->filp, + fence_data->handle); + if (gobj == NULL) + return -EINVAL; + + p->uf.bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj)); + p->uf.offset = fence_data->offset; + + if (amdgpu_ttm_tt_has_userptr(p->uf.bo->tbo.ttm)) { + drm_gem_object_unreference_unlocked(gobj); + return -EINVAL; + } + + p->uf_entry.robj = amdgpu_bo_ref(p->uf.bo); + p->uf_entry.prefered_domains = AMDGPU_GEM_DOMAIN_GTT; + p->uf_entry.allowed_domains = AMDGPU_GEM_DOMAIN_GTT; + p->uf_entry.priority = 0; + p->uf_entry.tv.bo = &p->uf_entry.robj->tbo; + p->uf_entry.tv.shared = true; + + drm_gem_object_unreference_unlocked(gobj); + return 0; +} + int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) { union drm_amdgpu_cs *cs = data; @@ -207,26 +238,15 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) case AMDGPU_CHUNK_ID_FENCE: size = sizeof(struct drm_amdgpu_cs_chunk_fence); - if (p->chunks[i].length_dw * sizeof(uint32_t) >= size) { - uint32_t handle; - struct drm_gem_object *gobj; - struct drm_amdgpu_cs_chunk_fence *fence_data; - - fence_data = (void *)p->chunks[i].kdata; - handle = fence_data->handle; - gobj = drm_gem_object_lookup(p->adev->ddev, - p->filp, handle); - if (gobj == NULL) { - ret = -EINVAL; - goto free_partial_kdata; - } - - p->uf.bo = gem_to_amdgpu_bo(gobj); - p->uf.offset = fence_data->offset; - } else { + if (p->chunks[i].length_dw * sizeof(uint32_t) < size) { ret = -EINVAL; goto free_partial_kdata; } + + ret = amdgpu_cs_user_fence_chunk(p, (void *)p->chunks[i].kdata); + if (ret) + goto free_partial_kdata; + break; case AMDGPU_CHUNK_ID_DEPENDENCIES: @@ -389,6 +409,9 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p) p->vm_bos = amdgpu_vm_get_bos(p->adev, &fpriv->vm, &p->validated); + if (p->uf.bo) + list_add(&p->uf_entry.tv.head, &p->validated); + if (need_mmap_lock) down_read(¤t->mm->mmap_sem); @@ -486,8 +509,8 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo for (i = 0; i < parser->num_ibs; i++) amdgpu_ib_free(parser->adev, &parser->ibs[i]); kfree(parser->ibs); - if (parser->uf.bo) - drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base); + amdgpu_bo_unref(&parser->uf.bo); + amdgpu_bo_unref(&parser->uf_entry.robj); } static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p, @@ -776,7 +799,7 @@ static int amdgpu_cs_free_job(struct amdgpu_job *job) amdgpu_ib_free(job->adev, &job->ibs[i]); kfree(job->ibs); if (job->uf.bo) - drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base); + amdgpu_bo_unref(&job->uf.bo); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index e173a5a02f0d8..5580d3420c3a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -73,6 +73,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; unsigned i; + int vpos, hpos, stat, min_udelay; + struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); for (i = 0; i < work->shared_count; ++i) @@ -81,6 +83,41 @@ static void amdgpu_flip_work_func(struct work_struct *__work) /* We borrow the event spin lock for protecting flip_status */ spin_lock_irqsave(&crtc->dev->event_lock, flags); + /* If this happens to execute within the "virtually extended" vblank + * interval before the start of the real vblank interval then it needs + * to delay programming the mmio flip until the real vblank is entered. + * This prevents completing a flip too early due to the way we fudge + * our vblank counter and vblank timestamps in order to work around the + * problem that the hw fires vblank interrupts before actual start of + * vblank (when line buffer refilling is done for a frame). It + * complements the fudging logic in amdgpu_get_crtc_scanoutpos() for + * timestamping and amdgpu_get_vblank_counter_kms() for vblank counts. + * + * In practice this won't execute very often unless on very fast + * machines because the time window for this to happen is very small. + */ + for (;;) { + /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank + * start in hpos, and to the "fudged earlier" vblank start in + * vpos. + */ + stat = amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id, + GET_DISTANCE_TO_VBLANKSTART, + &vpos, &hpos, NULL, NULL, + &crtc->hwmode); + + if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) != + (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) || + !(vpos >= 0 && hpos <= 0)) + break; + + /* Sleep at least until estimated real start of hw vblank */ + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + usleep_range(min_udelay, 2 * min_udelay); + spin_lock_irqsave(&crtc->dev->event_lock, flags); + }; + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ @@ -109,7 +146,7 @@ static void amdgpu_unpin_work_func(struct work_struct *__work) } else DRM_ERROR("failed to reserve buffer after flip\n"); - drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base); + amdgpu_bo_unref(&work->old_rbo); kfree(work->shared); kfree(work); } @@ -148,8 +185,8 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc, obj = old_amdgpu_fb->obj; /* take a reference to the old object */ - drm_gem_object_reference(obj); work->old_rbo = gem_to_amdgpu_bo(obj); + amdgpu_bo_ref(work->old_rbo); new_amdgpu_fb = to_amdgpu_framebuffer(fb); obj = new_amdgpu_fb->obj; @@ -222,7 +259,7 @@ pflip_cleanup: amdgpu_bo_unreserve(new_rbo); cleanup: - drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base); + amdgpu_bo_unref(&work->old_rbo); fence_put(work->excl); for (i = 0; i < work->shared_count; ++i) fence_put(work->shared[i]); @@ -712,6 +749,15 @@ bool amdgpu_crtc_scaling_mode_fixup(struct drm_crtc *crtc, * \param dev Device to query. * \param pipe Crtc to query. * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0). + * For driver internal use only also supports these flags: + * + * USE_REAL_VBLANKSTART to use the real start of vblank instead + * of a fudged earlier start of vblank. + * + * GET_DISTANCE_TO_VBLANKSTART to return distance to the + * fudged earlier start of vblank in *vpos and the distance + * to true start of vblank in *hpos. + * * \param *vpos Location where vertical scanout position should be stored. * \param *hpos Location where horizontal scanout position should go. * \param *stime Target location for timestamp taken immediately before @@ -776,10 +822,40 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, vbl_end = 0; } + /* Called from driver internal vblank counter query code? */ + if (flags & GET_DISTANCE_TO_VBLANKSTART) { + /* Caller wants distance from real vbl_start in *hpos */ + *hpos = *vpos - vbl_start; + } + + /* Fudge vblank to start a few scanlines earlier to handle the + * problem that vblank irqs fire a few scanlines before start + * of vblank. Some driver internal callers need the true vblank + * start to be used and signal this via the USE_REAL_VBLANKSTART flag. + * + * The cause of the "early" vblank irq is that the irq is triggered + * by the line buffer logic when the line buffer read position enters + * the vblank, whereas our crtc scanout position naturally lags the + * line buffer read position. + */ + if (!(flags & USE_REAL_VBLANKSTART)) + vbl_start -= adev->mode_info.crtcs[pipe]->lb_vblank_lead_lines; + /* Test scanout position against vblank region. */ if ((*vpos < vbl_start) && (*vpos >= vbl_end)) in_vbl = false; + /* In vblank? */ + if (in_vbl) + ret |= DRM_SCANOUTPOS_IN_VBLANK; + + /* Called from driver internal vblank counter query code? */ + if (flags & GET_DISTANCE_TO_VBLANKSTART) { + /* Caller wants distance from fudged earlier vbl_start */ + *vpos -= vbl_start; + return ret; + } + /* Check if inside vblank area and apply corrective offsets: * vpos will then be >=0 in video scanout area, but negative * within vblank area, counting down the number of lines until @@ -795,32 +871,6 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, /* Correct for shifted end of vbl at vbl_end. */ *vpos = *vpos - vbl_end; - /* In vblank? */ - if (in_vbl) - ret |= DRM_SCANOUTPOS_IN_VBLANK; - - /* Is vpos outside nominal vblank area, but less than - * 1/100 of a frame height away from start of vblank? - * If so, assume this isn't a massively delayed vblank - * interrupt, but a vblank interrupt that fired a few - * microseconds before true start of vblank. Compensate - * by adding a full frame duration to the final timestamp. - * Happens, e.g., on ATI R500, R600. - * - * We only do this if DRM_CALLED_FROM_VBLIRQ. - */ - if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) { - vbl_start = mode->crtc_vdisplay; - vtotal = mode->crtc_vtotal; - - if (vbl_start - *vpos < vtotal / 100) { - *vpos -= vtotal; - - /* Signal this correction as "applied". */ - ret |= 0x8; - } - } - return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index fc32fc01a64ba..9c253c535d260 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -235,8 +235,9 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, AMDGPU_GEM_USERPTR_REGISTER)) return -EINVAL; - if (!(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) || - !(args->flags & AMDGPU_GEM_USERPTR_REGISTER)) { + if (!(args->flags & AMDGPU_GEM_USERPTR_READONLY) && ( + !(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) || + !(args->flags & AMDGPU_GEM_USERPTR_REGISTER))) { /* if we want to write to it we must require anonymous memory and install a MMU notifier */ @@ -476,6 +477,14 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (domain == AMDGPU_GEM_DOMAIN_CPU) goto error_unreserve; } + list_for_each_entry(entry, &duplicates, head) { + domain = amdgpu_mem_type_to_domain(entry->bo->mem.mem_type); + /* if anything is swapped out don't swap it in here, + just abort and wait for the next CS */ + if (domain == AMDGPU_GEM_DOMAIN_CPU) + goto error_unreserve; + } + r = amdgpu_vm_update_page_directory(adev, bo_va->vm); if (r) goto error_unreserve; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 1618e2294a160..e23843f4d877b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -611,13 +611,59 @@ void amdgpu_driver_preclose_kms(struct drm_device *dev, u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe) { struct amdgpu_device *adev = dev->dev_private; + int vpos, hpos, stat; + u32 count; if (pipe >= adev->mode_info.num_crtc) { DRM_ERROR("Invalid crtc %u\n", pipe); return -EINVAL; } - return amdgpu_display_vblank_get_counter(adev, pipe); + /* The hw increments its frame counter at start of vsync, not at start + * of vblank, as is required by DRM core vblank counter handling. + * Cook the hw count here to make it appear to the caller as if it + * incremented at start of vblank. We measure distance to start of + * vblank in vpos. vpos therefore will be >= 0 between start of vblank + * and start of vsync, so vpos >= 0 means to bump the hw frame counter + * result by 1 to give the proper appearance to caller. + */ + if (adev->mode_info.crtcs[pipe]) { + /* Repeat readout if needed to provide stable result if + * we cross start of vsync during the queries. + */ + do { + count = amdgpu_display_vblank_get_counter(adev, pipe); + /* Ask amdgpu_get_crtc_scanoutpos to return vpos as + * distance to start of vblank, instead of regular + * vertical scanout pos. + */ + stat = amdgpu_get_crtc_scanoutpos( + dev, pipe, GET_DISTANCE_TO_VBLANKSTART, + &vpos, &hpos, NULL, NULL, + &adev->mode_info.crtcs[pipe]->base.hwmode); + } while (count != amdgpu_display_vblank_get_counter(adev, pipe)); + + if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) != + (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) { + DRM_DEBUG_VBL("Query failed! stat %d\n", stat); + } else { + DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n", + pipe, vpos); + + /* Bump counter if we are at >= leading edge of vblank, + * but before vsync where vpos would turn negative and + * the hw counter really increments. + */ + if (vpos >= 0) + count++; + } + } else { + /* Fallback to use value as is. */ + count = amdgpu_display_vblank_get_counter(adev, pipe); + DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n"); + } + + return count; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index b62c1710cab6b..064ebb3470748 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -407,6 +407,7 @@ struct amdgpu_crtc { u32 line_time; u32 wm_low; u32 wm_high; + u32 lb_vblank_lead_lines; struct drm_display_mode hw_mode; }; @@ -528,6 +529,10 @@ struct amdgpu_framebuffer { #define ENCODER_MODE_IS_DP(em) (((em) == ATOM_ENCODER_MODE_DP) || \ ((em) == ATOM_ENCODER_MODE_DP_MST)) +/* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */ +#define USE_REAL_VBLANKSTART (1 << 30) +#define GET_DISTANCE_TO_VBLANKSTART (1 << 31) + void amdgpu_link_encoder_connector(struct drm_device *dev); struct drm_connector * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 0d524384ff79c..c3ce103b6a33b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -100,6 +100,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo) list_del_init(&bo->list); mutex_unlock(&bo->adev->gem.mutex); drm_gem_object_release(&bo->gem_base); + amdgpu_bo_unref(&bo->parent); kfree(bo->metadata); kfree(bo); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index d4bac5f49939e..8a1752ff3d8e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -587,9 +587,13 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm, uint32_t flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem); int r; - if (gtt->userptr) - amdgpu_ttm_tt_pin_userptr(ttm); - + if (gtt->userptr) { + r = amdgpu_ttm_tt_pin_userptr(ttm); + if (r) { + DRM_ERROR("failed to pin userptr\n"); + return r; + } + } gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT); if (!ttm->num_pages) { WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n", @@ -797,11 +801,12 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, if (mem && mem->mem_type != TTM_PL_SYSTEM) flags |= AMDGPU_PTE_VALID; - if (mem && mem->mem_type == TTM_PL_TT) + if (mem && mem->mem_type == TTM_PL_TT) { flags |= AMDGPU_PTE_SYSTEM; - if (!ttm || ttm->caching_state == tt_cached) - flags |= AMDGPU_PTE_SNOOPED; + if (ttm->caching_state == tt_cached) + flags |= AMDGPU_PTE_SNOOPED; + } if (adev->asic_type >= CHIP_TOPAZ) flags |= AMDGPU_PTE_EXECUTABLE; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ae037e5b6ad01..b53d273eb7a10 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -885,17 +885,21 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *mapping; int r; + spin_lock(&vm->freed_lock); while (!list_empty(&vm->freed)) { mapping = list_first_entry(&vm->freed, struct amdgpu_bo_va_mapping, list); list_del(&mapping->list); - + spin_unlock(&vm->freed_lock); r = amdgpu_vm_bo_update_mapping(adev, vm, mapping, 0, 0, NULL); kfree(mapping); if (r) return r; + spin_lock(&vm->freed_lock); } + spin_unlock(&vm->freed_lock); + return 0; } @@ -1079,6 +1083,11 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, if (r) goto error_free; + /* Keep a reference to the page table to avoid freeing + * them up in the wrong order. + */ + pt->parent = amdgpu_bo_ref(vm->page_directory); + r = amdgpu_vm_clear_bo(adev, pt); if (r) { amdgpu_bo_unref(&pt); @@ -1150,10 +1159,13 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); - if (valid) + if (valid) { + spin_lock(&vm->freed_lock); list_add(&mapping->list, &vm->freed); - else + spin_unlock(&vm->freed_lock); + } else { kfree(mapping); + } return 0; } @@ -1186,7 +1198,9 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, interval_tree_remove(&mapping->it, &vm->va); spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); + spin_lock(&vm->freed_lock); list_add(&mapping->list, &vm->freed); + spin_unlock(&vm->freed_lock); } list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) { list_del(&mapping->list); @@ -1247,6 +1261,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) INIT_LIST_HEAD(&vm->cleared); INIT_LIST_HEAD(&vm->freed); spin_lock_init(&vm->it_lock); + spin_lock_init(&vm->freed_lock); pd_size = amdgpu_vm_directory_size(adev); pd_entries = amdgpu_vm_num_pdes(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index cb0f7747e3dca..4dcc8fba57920 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1250,7 +1250,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, u32 pixel_period; u32 line_time = 0; u32 latency_watermark_a = 0, latency_watermark_b = 0; - u32 tmp, wm_mask; + u32 tmp, wm_mask, lb_vblank_lead_lines = 0; if (amdgpu_crtc->base.enabled && num_heads && mode) { pixel_period = 1000000 / (u32)mode->clock; @@ -1333,6 +1333,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, (adev->mode_info.disp_priority == 2)) { DRM_DEBUG_KMS("force priority to high\n"); } + lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); } /* select wm A */ @@ -1357,6 +1358,8 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, amdgpu_crtc->line_time = line_time; amdgpu_crtc->wm_high = latency_watermark_a; amdgpu_crtc->wm_low = latency_watermark_b; + /* Save number of lines the linebuffer leads before the scanout */ + amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 5af3721851d67..8f1e51128b338 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -1238,7 +1238,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, u32 pixel_period; u32 line_time = 0; u32 latency_watermark_a = 0, latency_watermark_b = 0; - u32 tmp, wm_mask; + u32 tmp, wm_mask, lb_vblank_lead_lines = 0; if (amdgpu_crtc->base.enabled && num_heads && mode) { pixel_period = 1000000 / (u32)mode->clock; @@ -1321,6 +1321,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, (adev->mode_info.disp_priority == 2)) { DRM_DEBUG_KMS("force priority to high\n"); } + lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); } /* select wm A */ @@ -1345,6 +1346,8 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, amdgpu_crtc->line_time = line_time; amdgpu_crtc->wm_high = latency_watermark_a; amdgpu_crtc->wm_low = latency_watermark_b; + /* Save number of lines the linebuffer leads before the scanout */ + amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 4f7b49a6dc500..42d954dc436d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1193,7 +1193,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, u32 pixel_period; u32 line_time = 0; u32 latency_watermark_a = 0, latency_watermark_b = 0; - u32 tmp, wm_mask; + u32 tmp, wm_mask, lb_vblank_lead_lines = 0; if (amdgpu_crtc->base.enabled && num_heads && mode) { pixel_period = 1000000 / (u32)mode->clock; @@ -1276,6 +1276,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, (adev->mode_info.disp_priority == 2)) { DRM_DEBUG_KMS("force priority to high\n"); } + lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); } /* select wm A */ @@ -1302,6 +1303,8 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, amdgpu_crtc->line_time = line_time; amdgpu_crtc->wm_high = latency_watermark_a; amdgpu_crtc->wm_low = latency_watermark_b; + /* Save number of lines the linebuffer leads before the scanout */ + amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 7427d8cd4c43f..ed8abb58a785e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -513,7 +513,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) WREG32(mmVM_L2_CNTL3, tmp); /* setup context0 */ WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12); - WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1); + WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12); WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12); WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR, (u32)(adev->dummy_page.addr >> 12)); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index cb0e50ebb5285..d390284408144 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -657,7 +657,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev) WREG32(mmVM_L2_CNTL4, tmp); /* setup context0 */ WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12); - WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1); + WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12); WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12); WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR, (u32)(adev->dummy_page.addr >> 12)); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 651129f2ec1d1..3a4820e863ecb 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -288,6 +288,7 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity) */ static bool amd_sched_entity_in(struct amd_sched_job *sched_job) { + struct amd_gpu_scheduler *sched = sched_job->sched; struct amd_sched_entity *entity = sched_job->s_entity; bool added, first = false; @@ -302,7 +303,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job) /* first job wakes up scheduler */ if (first) - amd_sched_wakeup(sched_job->sched); + amd_sched_wakeup(sched); return added; } @@ -318,9 +319,9 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job) { struct amd_sched_entity *entity = sched_job->s_entity; + trace_amd_sched_job(sched_job); wait_event(entity->sched->job_scheduled, amd_sched_entity_in(sched_job)); - trace_amd_sched_job(sched_job); } /** diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 9362609df38ae..7dd6728dd092e 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -160,6 +160,11 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, goto out_unlock; } + if (!file_priv->allowed_master) { + ret = drm_new_set_master(dev, file_priv); + goto out_unlock; + } + file_priv->minor->master = drm_master_get(file_priv->master); file_priv->is_master = 1; if (dev->driver->master_set) { diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c index c59ce4d0ef75f..6b5625e661197 100644 --- a/drivers/gpu/drm/drm_fops.c +++ b/drivers/gpu/drm/drm_fops.c @@ -126,6 +126,60 @@ static int drm_cpu_valid(void) } /** + * drm_new_set_master - Allocate a new master object and become master for the + * associated master realm. + * + * @dev: The associated device. + * @fpriv: File private identifying the client. + * + * This function must be called with dev::struct_mutex held. + * Returns negative error code on failure. Zero on success. + */ +int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv) +{ + struct drm_master *old_master; + int ret; + + lockdep_assert_held_once(&dev->master_mutex); + + /* create a new master */ + fpriv->minor->master = drm_master_create(fpriv->minor); + if (!fpriv->minor->master) + return -ENOMEM; + + /* take another reference for the copy in the local file priv */ + old_master = fpriv->master; + fpriv->master = drm_master_get(fpriv->minor->master); + + if (dev->driver->master_create) { + ret = dev->driver->master_create(dev, fpriv->master); + if (ret) + goto out_err; + } + if (dev->driver->master_set) { + ret = dev->driver->master_set(dev, fpriv, true); + if (ret) + goto out_err; + } + + fpriv->is_master = 1; + fpriv->allowed_master = 1; + fpriv->authenticated = 1; + if (old_master) + drm_master_put(&old_master); + + return 0; + +out_err: + /* drop both references and restore old master on failure */ + drm_master_put(&fpriv->minor->master); + drm_master_put(&fpriv->master); + fpriv->master = old_master; + + return ret; +} + +/** * Called whenever a process opens /dev/drm. * * \param filp file pointer. @@ -189,35 +243,9 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor) mutex_lock(&dev->master_mutex); if (drm_is_primary_client(priv) && !priv->minor->master) { /* create a new master */ - priv->minor->master = drm_master_create(priv->minor); - if (!priv->minor->master) { - ret = -ENOMEM; + ret = drm_new_set_master(dev, priv); + if (ret) goto out_close; - } - - priv->is_master = 1; - /* take another reference for the copy in the local file priv */ - priv->master = drm_master_get(priv->minor->master); - priv->authenticated = 1; - - if (dev->driver->master_create) { - ret = dev->driver->master_create(dev, priv->master); - if (ret) { - /* drop both references if this fails */ - drm_master_put(&priv->minor->master); - drm_master_put(&priv->master); - goto out_close; - } - } - if (dev->driver->master_set) { - ret = dev->driver->master_set(dev, priv, true); - if (ret) { - /* drop both references if this fails */ - drm_master_put(&priv->minor->master); - drm_master_put(&priv->master); - goto out_close; - } - } } else if (drm_is_primary_client(priv)) { /* get a reference to the master */ priv->master = drm_master_get(priv->minor->master); diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 2151ea551d3bd..607f493ae8013 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -980,7 +980,8 @@ static void send_vblank_event(struct drm_device *dev, struct drm_pending_vblank_event *e, unsigned long seq, struct timeval *now) { - WARN_ON_SMP(!spin_is_locked(&dev->event_lock)); + assert_spin_locked(&dev->event_lock); + e->event.sequence = seq; e->event.tv_sec = now->tv_sec; e->event.tv_usec = now->tv_usec; @@ -993,6 +994,57 @@ static void send_vblank_event(struct drm_device *dev, } /** + * drm_arm_vblank_event - arm vblank event after pageflip + * @dev: DRM device + * @pipe: CRTC index + * @e: the event to prepare to send + * + * A lot of drivers need to generate vblank events for the very next vblank + * interrupt. For example when the page flip interrupt happens when the page + * flip gets armed, but not when it actually executes within the next vblank + * period. This helper function implements exactly the required vblank arming + * behaviour. + * + * Caller must hold event lock. Caller must also hold a vblank reference for + * the event @e, which will be dropped when the next vblank arrives. + * + * This is the legacy version of drm_crtc_arm_vblank_event(). + */ +void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe, + struct drm_pending_vblank_event *e) +{ + assert_spin_locked(&dev->event_lock); + + e->pipe = pipe; + e->event.sequence = drm_vblank_count(dev, pipe); + list_add_tail(&e->base.link, &dev->vblank_event_list); +} +EXPORT_SYMBOL(drm_arm_vblank_event); + +/** + * drm_crtc_arm_vblank_event - arm vblank event after pageflip + * @crtc: the source CRTC of the vblank event + * @e: the event to send + * + * A lot of drivers need to generate vblank events for the very next vblank + * interrupt. For example when the page flip interrupt happens when the page + * flip gets armed, but not when it actually executes within the next vblank + * period. This helper function implements exactly the required vblank arming + * behaviour. + * + * Caller must hold event lock. Caller must also hold a vblank reference for + * the event @e, which will be dropped when the next vblank arrives. + * + * This is the native KMS version of drm_arm_vblank_event(). + */ +void drm_crtc_arm_vblank_event(struct drm_crtc *crtc, + struct drm_pending_vblank_event *e) +{ + drm_arm_vblank_event(crtc->dev, drm_crtc_index(crtc), e); +} +EXPORT_SYMBOL(drm_crtc_arm_vblank_event); + +/** * drm_send_vblank_event - helper to send vblank event after pageflip * @dev: DRM device * @pipe: CRTC index diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index a18164f2f6d28..f8b5fcfa91a27 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -229,7 +229,8 @@ static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connect mode_flags |= DRM_MODE_FLAG_3D_MASK; list_for_each_entry(mode, &connector->modes, head) { - mode->status = drm_mode_validate_basic(mode); + if (mode->status == MODE_OK) + mode->status = drm_mode_validate_basic(mode); if (mode->status == MODE_OK) mode->status = drm_mode_validate_size(mode, maxX, maxY); diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index b3ba27fd9a6bc..e69357172ffb5 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -55,6 +55,9 @@ static int exynos_crtc_atomic_check(struct drm_crtc *crtc, { struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); + if (!state->enable) + return 0; + if (exynos_crtc->ops->atomic_check) return exynos_crtc->ops->atomic_check(exynos_crtc, state); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index a3b22bdacd44f..8aab974b0564c 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -2734,6 +2734,8 @@ static const char *power_domain_str(enum intel_display_power_domain domain) return "AUX_C"; case POWER_DOMAIN_AUX_D: return "AUX_D"; + case POWER_DOMAIN_GMBUS: + return "GMBUS"; case POWER_DOMAIN_INIT: return "INIT"; default: diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 95bb27de774f8..f4af19a0d5696 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -199,6 +199,7 @@ enum intel_display_power_domain { POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_AUX_D, + POWER_DOMAIN_GMBUS, POWER_DOMAIN_INIT, POWER_DOMAIN_NUM, @@ -2192,8 +2193,17 @@ struct drm_i915_gem_request { struct drm_i915_private *i915; struct intel_engine_cs *ring; - /** GEM sequence number associated with this request. */ - uint32_t seqno; + /** GEM sequence number associated with the previous request, + * when the HWS breadcrumb is equal to this the GPU is processing + * this request. + */ + u32 previous_seqno; + + /** GEM sequence number associated with this request, + * when the HWS breadcrumb is equal or greater than this the GPU + * has finished processing this request. + */ + u32 seqno; /** Position in the ringbuffer of the start of the request */ u32 head; @@ -2838,6 +2848,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags); +void __i915_vma_set_map_and_fenceable(struct i915_vma *vma); int __must_check i915_vma_unbind(struct i915_vma *vma); /* * BEWARE: Do not use the function below unless you can _absolutely_ @@ -2909,15 +2920,17 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2) return (int32_t)(seq1 - seq2) >= 0; } +static inline bool i915_gem_request_started(struct drm_i915_gem_request *req, + bool lazy_coherency) +{ + u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency); + return i915_seqno_passed(seqno, req->previous_seqno); +} + static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req, bool lazy_coherency) { - u32 seqno; - - BUG_ON(req == NULL); - - seqno = req->ring->get_seqno(req->ring, lazy_coherency); - + u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency); return i915_seqno_passed(seqno, req->seqno); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 91bb1fc27420f..f56af0aaafde5 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1146,23 +1146,74 @@ static bool missed_irq(struct drm_i915_private *dev_priv, return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings); } -static int __i915_spin_request(struct drm_i915_gem_request *req) +static unsigned long local_clock_us(unsigned *cpu) +{ + unsigned long t; + + /* Cheaply and approximately convert from nanoseconds to microseconds. + * The result and subsequent calculations are also defined in the same + * approximate microseconds units. The principal source of timing + * error here is from the simple truncation. + * + * Note that local_clock() is only defined wrt to the current CPU; + * the comparisons are no longer valid if we switch CPUs. Instead of + * blocking preemption for the entire busywait, we can detect the CPU + * switch and use that as indicator of system load and a reason to + * stop busywaiting, see busywait_stop(). + */ + *cpu = get_cpu(); + t = local_clock() >> 10; + put_cpu(); + + return t; +} + +static bool busywait_stop(unsigned long timeout, unsigned cpu) +{ + unsigned this_cpu; + + if (time_after(local_clock_us(&this_cpu), timeout)) + return true; + + return this_cpu != cpu; +} + +static int __i915_spin_request(struct drm_i915_gem_request *req, int state) { unsigned long timeout; + unsigned cpu; + + /* When waiting for high frequency requests, e.g. during synchronous + * rendering split between the CPU and GPU, the finite amount of time + * required to set up the irq and wait upon it limits the response + * rate. By busywaiting on the request completion for a short while we + * can service the high frequency waits as quick as possible. However, + * if it is a slow request, we want to sleep as quickly as possible. + * The tradeoff between waiting and sleeping is roughly the time it + * takes to sleep on a request, on the order of a microsecond. + */ - if (i915_gem_request_get_ring(req)->irq_refcount) + if (req->ring->irq_refcount) return -EBUSY; - timeout = jiffies + 1; + /* Only spin if we know the GPU is processing this request */ + if (!i915_gem_request_started(req, true)) + return -EAGAIN; + + timeout = local_clock_us(&cpu) + 5; while (!need_resched()) { if (i915_gem_request_completed(req, true)) return 0; - if (time_after_eq(jiffies, timeout)) + if (signal_pending_state(state, current)) + break; + + if (busywait_stop(timeout, cpu)) break; cpu_relax_lowlatency(); } + if (i915_gem_request_completed(req, false)) return 0; @@ -1197,6 +1248,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, struct drm_i915_private *dev_priv = dev->dev_private; const bool irq_test_in_progress = ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring); + int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; DEFINE_WAIT(wait); unsigned long timeout_expire; s64 before, now; @@ -1210,8 +1262,16 @@ int __i915_wait_request(struct drm_i915_gem_request *req, if (i915_gem_request_completed(req, true)) return 0; - timeout_expire = timeout ? - jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0; + timeout_expire = 0; + if (timeout) { + if (WARN_ON(*timeout < 0)) + return -EINVAL; + + if (*timeout == 0) + return -ETIME; + + timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout); + } if (INTEL_INFO(dev_priv)->gen >= 6) gen6_rps_boost(dev_priv, rps, req->emitted_jiffies); @@ -1221,7 +1281,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, before = ktime_get_raw_ns(); /* Optimistic spin for the next jiffie before touching IRQs */ - ret = __i915_spin_request(req); + ret = __i915_spin_request(req, state); if (ret == 0) goto out; @@ -1233,8 +1293,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, for (;;) { struct timer_list timer; - prepare_to_wait(&ring->irq_queue, &wait, - interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); + prepare_to_wait(&ring->irq_queue, &wait, state); /* We need to check whether any gpu reset happened in between * the caller grabbing the seqno and now ... */ @@ -1252,7 +1311,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, break; } - if (interruptible && signal_pending(current)) { + if (signal_pending_state(state, current)) { ret = -ERESTARTSYS; break; } @@ -2546,6 +2605,7 @@ void __i915_add_request(struct drm_i915_gem_request *request, request->batch_obj = obj; request->emitted_jiffies = jiffies; + request->previous_seqno = ring->last_submitted_seqno; ring->last_submitted_seqno = request->seqno; list_add_tail(&request->list, &ring->request_list); @@ -4072,6 +4132,29 @@ i915_vma_misplaced(struct i915_vma *vma, uint32_t alignment, uint64_t flags) return false; } +void __i915_vma_set_map_and_fenceable(struct i915_vma *vma) +{ + struct drm_i915_gem_object *obj = vma->obj; + bool mappable, fenceable; + u32 fence_size, fence_alignment; + + fence_size = i915_gem_get_gtt_size(obj->base.dev, + obj->base.size, + obj->tiling_mode); + fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev, + obj->base.size, + obj->tiling_mode, + true); + + fenceable = (vma->node.size == fence_size && + (vma->node.start & (fence_alignment - 1)) == 0); + + mappable = (vma->node.start + fence_size <= + to_i915(obj->base.dev)->gtt.mappable_end); + + obj->map_and_fenceable = mappable && fenceable; +} + static int i915_gem_object_do_pin(struct drm_i915_gem_object *obj, struct i915_address_space *vm, @@ -4139,25 +4222,7 @@ i915_gem_object_do_pin(struct drm_i915_gem_object *obj, if (ggtt_view && ggtt_view->type == I915_GGTT_VIEW_NORMAL && (bound ^ vma->bound) & GLOBAL_BIND) { - bool mappable, fenceable; - u32 fence_size, fence_alignment; - - fence_size = i915_gem_get_gtt_size(obj->base.dev, - obj->base.size, - obj->tiling_mode); - fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev, - obj->base.size, - obj->tiling_mode, - true); - - fenceable = (vma->node.size == fence_size && - (vma->node.start & (fence_alignment - 1)) == 0); - - mappable = (vma->node.start + fence_size <= - dev_priv->gtt.mappable_end); - - obj->map_and_fenceable = mappable && fenceable; - + __i915_vma_set_map_and_fenceable(vma); WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable); } diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 8c688a5f15893..02ceb7a4b4815 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -141,8 +141,6 @@ static void i915_gem_context_clean(struct intel_context *ctx) if (!ppgtt) return; - WARN_ON(!list_empty(&ppgtt->base.active_list)); - list_for_each_entry_safe(vma, next, &ppgtt->base.inactive_list, mm_list) { if (WARN_ON(__i915_vma_unbind_no_wait(vma))) diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c index 40a10b25956c2..f010391b87f5c 100644 --- a/drivers/gpu/drm/i915/i915_gem_fence.c +++ b/drivers/gpu/drm/i915/i915_gem_fence.c @@ -642,11 +642,10 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) } /* check for L-shaped memory aka modified enhanced addressing */ - if (IS_GEN4(dev)) { - uint32_t ddc2 = I915_READ(DCC2); - - if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE)) - dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES; + if (IS_GEN4(dev) && + !(I915_READ(DCC2) & DCC2_MODIFIED_ENHANCED_DISABLE)) { + swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN; + swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN; } if (dcc == 0xffffffff) { @@ -675,16 +674,35 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) * matching, which was the case for the swizzling required in * the table above, or from the 1-ch value being less than * the minimum size of a rank. + * + * Reports indicate that the swizzling actually + * varies depending upon page placement inside the + * channels, i.e. we see swizzled pages where the + * banks of memory are paired and unswizzled on the + * uneven portion, so leave that as unknown. */ - if (I915_READ16(C0DRB3) != I915_READ16(C1DRB3)) { - swizzle_x = I915_BIT_6_SWIZZLE_NONE; - swizzle_y = I915_BIT_6_SWIZZLE_NONE; - } else { + if (I915_READ16(C0DRB3) == I915_READ16(C1DRB3)) { swizzle_x = I915_BIT_6_SWIZZLE_9_10; swizzle_y = I915_BIT_6_SWIZZLE_9; } } + if (swizzle_x == I915_BIT_6_SWIZZLE_UNKNOWN || + swizzle_y == I915_BIT_6_SWIZZLE_UNKNOWN) { + /* Userspace likes to explode if it sees unknown swizzling, + * so lie. We will finish the lie when reporting through + * the get-tiling-ioctl by reporting the physical swizzle + * mode as unknown instead. + * + * As we don't strictly know what the swizzling is, it may be + * bit17 dependent, and so we need to also prevent the pages + * from being moved. + */ + dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES; + swizzle_x = I915_BIT_6_SWIZZLE_NONE; + swizzle_y = I915_BIT_6_SWIZZLE_NONE; + } + dev_priv->mm.bit_6_swizzle_x = swizzle_x; dev_priv->mm.bit_6_swizzle_y = swizzle_y; } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 43f35d12b6776..86c7500454b4d 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2676,6 +2676,7 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev, return ret; } vma->bound |= GLOBAL_BIND; + __i915_vma_set_map_and_fenceable(vma); list_add_tail(&vma->mm_list, &ggtt_vm->inactive_list); } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index cdacf3f5b77a5..87e919a06b277 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -687,6 +687,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, } vma->bound |= GLOBAL_BIND; + __i915_vma_set_map_and_fenceable(vma); list_add_tail(&vma->mm_list, &ggtt->inactive_list); } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 71860f8680f9f..beb0374a19f19 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -116,6 +116,7 @@ static void skylake_pfit_enable(struct intel_crtc *crtc); static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force); static void ironlake_pfit_enable(struct intel_crtc *crtc); static void intel_modeset_setup_hw_state(struct drm_device *dev); +static void intel_pre_disable_primary(struct drm_crtc *crtc); typedef struct { int min, max; @@ -2607,6 +2608,8 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, struct drm_i915_gem_object *obj; struct drm_plane *primary = intel_crtc->base.primary; struct drm_plane_state *plane_state = primary->state; + struct drm_crtc_state *crtc_state = intel_crtc->base.state; + struct intel_plane *intel_plane = to_intel_plane(primary); struct drm_framebuffer *fb; if (!plane_config->fb) @@ -2643,6 +2646,18 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, } } + /* + * We've failed to reconstruct the BIOS FB. Current display state + * indicates that the primary plane is visible, but has a NULL FB, + * which will lead to problems later if we don't fix it up. The + * simplest solution is to just disable the primary plane now and + * pretend the BIOS never had it enabled. + */ + to_intel_plane_state(plane_state)->visible = false; + crtc_state->plane_mask &= ~(1 << drm_plane_index(primary)); + intel_pre_disable_primary(&intel_crtc->base); + intel_plane->disable_plane(primary, &intel_crtc->base); + return; valid_fb: @@ -5194,11 +5209,31 @@ static enum intel_display_power_domain port_to_power_domain(enum port port) case PORT_E: return POWER_DOMAIN_PORT_DDI_E_2_LANES; default: - WARN_ON_ONCE(1); + MISSING_CASE(port); return POWER_DOMAIN_PORT_OTHER; } } +static enum intel_display_power_domain port_to_aux_power_domain(enum port port) +{ + switch (port) { + case PORT_A: + return POWER_DOMAIN_AUX_A; + case PORT_B: + return POWER_DOMAIN_AUX_B; + case PORT_C: + return POWER_DOMAIN_AUX_C; + case PORT_D: + return POWER_DOMAIN_AUX_D; + case PORT_E: + /* FIXME: Check VBT for actual wiring of PORT E */ + return POWER_DOMAIN_AUX_D; + default: + MISSING_CASE(port); + return POWER_DOMAIN_AUX_A; + } +} + #define for_each_power_domain(domain, mask) \ for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++) \ if ((1 << (domain)) & (mask)) @@ -5230,6 +5265,36 @@ intel_display_port_power_domain(struct intel_encoder *intel_encoder) } } +enum intel_display_power_domain +intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder) +{ + struct drm_device *dev = intel_encoder->base.dev; + struct intel_digital_port *intel_dig_port; + + switch (intel_encoder->type) { + case INTEL_OUTPUT_UNKNOWN: + case INTEL_OUTPUT_HDMI: + /* + * Only DDI platforms should ever use these output types. + * We can get here after the HDMI detect code has already set + * the type of the shared encoder. Since we can't be sure + * what's the status of the given connectors, play safe and + * run the DP detection too. + */ + WARN_ON_ONCE(!HAS_DDI(dev)); + case INTEL_OUTPUT_DISPLAYPORT: + case INTEL_OUTPUT_EDP: + intel_dig_port = enc_to_dig_port(&intel_encoder->base); + return port_to_aux_power_domain(intel_dig_port->port); + case INTEL_OUTPUT_DP_MST: + intel_dig_port = enc_to_mst(&intel_encoder->base)->primary; + return port_to_aux_power_domain(intel_dig_port->port); + default: + MISSING_CASE(intel_encoder->type); + return POWER_DOMAIN_AUX_A; + } +} + static unsigned long get_crtc_power_domains(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -6259,9 +6324,11 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) if (to_intel_plane_state(crtc->primary->state)->visible) { intel_crtc_wait_for_pending_flips(crtc); intel_pre_disable_primary(crtc); + + intel_crtc_disable_planes(crtc, 1 << drm_plane_index(crtc->primary)); + to_intel_plane_state(crtc->primary->state)->visible = false; } - intel_crtc_disable_planes(crtc, crtc->state->plane_mask); dev_priv->display.crtc_disable(crtc); intel_crtc->active = false; intel_update_watermarks(crtc); @@ -9858,14 +9925,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, return true; } -static void i845_update_cursor(struct drm_crtc *crtc, u32 base) +static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t cntl = 0, size = 0; - if (base) { + if (on) { unsigned int width = intel_crtc->base.cursor->state->crtc_w; unsigned int height = intel_crtc->base.cursor->state->crtc_h; unsigned int stride = roundup_pow_of_two(width) * 4; @@ -9920,16 +9987,15 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base) } } -static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) +static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - uint32_t cntl; + uint32_t cntl = 0; - cntl = 0; - if (base) { + if (on) { cntl = MCURSOR_GAMMA_ENABLE; switch (intel_crtc->base.cursor->state->crtc_w) { case 64: @@ -9980,18 +10046,17 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, int y = cursor_state->crtc_y; u32 base = 0, pos = 0; - if (on) - base = intel_crtc->cursor_addr; + base = intel_crtc->cursor_addr; if (x >= intel_crtc->config->pipe_src_w) - base = 0; + on = false; if (y >= intel_crtc->config->pipe_src_h) - base = 0; + on = false; if (x < 0) { if (x + cursor_state->crtc_w <= 0) - base = 0; + on = false; pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; x = -x; @@ -10000,16 +10065,13 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, if (y < 0) { if (y + cursor_state->crtc_h <= 0) - base = 0; + on = false; pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; y = -y; } pos |= y << CURSOR_Y_SHIFT; - if (base == 0 && intel_crtc->cursor_base == 0) - return; - I915_WRITE(CURPOS(pipe), pos); /* ILK+ do this automagically */ @@ -10020,9 +10082,9 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, } if (IS_845G(dev) || IS_I865G(dev)) - i845_update_cursor(crtc, base); + i845_update_cursor(crtc, base, on); else - i9xx_update_cursor(crtc, base); + i9xx_update_cursor(crtc, base, on); } static bool cursor_size_ok(struct drm_device *dev, @@ -12460,7 +12522,6 @@ intel_pipe_config_compare(struct drm_device *dev, if (INTEL_INFO(dev)->gen < 8) { PIPE_CONF_CHECK_M_N(dp_m_n); - PIPE_CONF_CHECK_I(has_drrs); if (current_config->has_drrs) PIPE_CONF_CHECK_M_N(dp_m2_n2); } else @@ -13667,6 +13728,7 @@ intel_check_cursor_plane(struct drm_plane *plane, struct drm_crtc *crtc = crtc_state->base.crtc; struct drm_framebuffer *fb = state->base.fb; struct drm_i915_gem_object *obj = intel_fb_obj(fb); + enum pipe pipe = to_intel_plane(plane)->pipe; unsigned stride; int ret; @@ -13700,6 +13762,22 @@ intel_check_cursor_plane(struct drm_plane *plane, return -EINVAL; } + /* + * There's something wrong with the cursor on CHV pipe C. + * If it straddles the left edge of the screen then + * moving it away from the edge or disabling it often + * results in a pipe underrun, and often that can lead to + * dead pipe (constant underrun reported, and it scans + * out just a solid color). To recover from that, the + * display power well must be turned off and on again. + * Refuse the put the cursor into that compromised position. + */ + if (IS_CHERRYVIEW(plane->dev) && pipe == PIPE_C && + state->visible && state->base.crtc_x < 0) { + DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n"); + return -EINVAL; + } + return 0; } @@ -13723,9 +13801,6 @@ intel_commit_cursor_plane(struct drm_plane *plane, crtc = crtc ? crtc : plane->crtc; intel_crtc = to_intel_crtc(crtc); - if (intel_crtc->cursor_bo == obj) - goto update; - if (!obj) addr = 0; else if (!INTEL_INFO(dev)->cursor_needs_physical) @@ -13734,9 +13809,7 @@ intel_commit_cursor_plane(struct drm_plane *plane, addr = obj->phys_handle->busaddr; intel_crtc->cursor_addr = addr; - intel_crtc->cursor_bo = obj; -update: if (crtc->state->active) intel_crtc_update_cursor(crtc, state->visible); } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 09bdd94ca3ba4..78b8ec84d576d 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -277,7 +277,7 @@ static void pps_lock(struct intel_dp *intel_dp) * See vlv_power_sequencer_reset() why we need * a power domain reference here. */ - power_domain = intel_display_port_power_domain(encoder); + power_domain = intel_display_port_aux_power_domain(encoder); intel_display_power_get(dev_priv, power_domain); mutex_lock(&dev_priv->pps_mutex); @@ -293,7 +293,7 @@ static void pps_unlock(struct intel_dp *intel_dp) mutex_unlock(&dev_priv->pps_mutex); - power_domain = intel_display_port_power_domain(encoder); + power_domain = intel_display_port_aux_power_domain(encoder); intel_display_power_put(dev_priv, power_domain); } @@ -816,8 +816,6 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, intel_dp_check_edp(intel_dp); - intel_aux_display_runtime_get(dev_priv); - /* Try to wait for any previous AUX channel activity */ for (try = 0; try < 3; try++) { status = I915_READ_NOTRACE(ch_ctl); @@ -926,7 +924,6 @@ done: ret = recv_bytes; out: pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE); - intel_aux_display_runtime_put(dev_priv); if (vdd) edp_panel_vdd_off(intel_dp, false); @@ -1784,7 +1781,7 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp) if (edp_have_panel_vdd(intel_dp)) return need_to_disable; - power_domain = intel_display_port_power_domain(intel_encoder); + power_domain = intel_display_port_aux_power_domain(intel_encoder); intel_display_power_get(dev_priv, power_domain); DRM_DEBUG_KMS("Turning eDP port %c VDD on\n", @@ -1874,7 +1871,7 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp) if ((pp & POWER_TARGET_ON) == 0) intel_dp->last_power_cycle = jiffies; - power_domain = intel_display_port_power_domain(intel_encoder); + power_domain = intel_display_port_aux_power_domain(intel_encoder); intel_display_power_put(dev_priv, power_domain); } @@ -2025,7 +2022,7 @@ static void edp_panel_off(struct intel_dp *intel_dp) wait_panel_off(intel_dp); /* We got a reference when we enabled the VDD. */ - power_domain = intel_display_port_power_domain(intel_encoder); + power_domain = intel_display_port_aux_power_domain(intel_encoder); intel_display_power_put(dev_priv, power_domain); } @@ -4765,26 +4762,6 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) intel_dp->has_audio = false; } -static enum intel_display_power_domain -intel_dp_power_get(struct intel_dp *dp) -{ - struct intel_encoder *encoder = &dp_to_dig_port(dp)->base; - enum intel_display_power_domain power_domain; - - power_domain = intel_display_port_power_domain(encoder); - intel_display_power_get(to_i915(encoder->base.dev), power_domain); - - return power_domain; -} - -static void -intel_dp_power_put(struct intel_dp *dp, - enum intel_display_power_domain power_domain) -{ - struct intel_encoder *encoder = &dp_to_dig_port(dp)->base; - intel_display_power_put(to_i915(encoder->base.dev), power_domain); -} - static enum drm_connector_status intel_dp_detect(struct drm_connector *connector, bool force) { @@ -4808,7 +4785,8 @@ intel_dp_detect(struct drm_connector *connector, bool force) return connector_status_disconnected; } - power_domain = intel_dp_power_get(intel_dp); + power_domain = intel_display_port_aux_power_domain(intel_encoder); + intel_display_power_get(to_i915(dev), power_domain); /* Can't disconnect eDP, but you can close the lid... */ if (is_edp(intel_dp)) @@ -4853,7 +4831,7 @@ intel_dp_detect(struct drm_connector *connector, bool force) } out: - intel_dp_power_put(intel_dp, power_domain); + intel_display_power_put(to_i915(dev), power_domain); return status; } @@ -4862,6 +4840,7 @@ intel_dp_force(struct drm_connector *connector) { struct intel_dp *intel_dp = intel_attached_dp(connector); struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev); enum intel_display_power_domain power_domain; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", @@ -4871,11 +4850,12 @@ intel_dp_force(struct drm_connector *connector) if (connector->status != connector_status_connected) return; - power_domain = intel_dp_power_get(intel_dp); + power_domain = intel_display_port_aux_power_domain(intel_encoder); + intel_display_power_get(dev_priv, power_domain); intel_dp_set_edid(intel_dp); - intel_dp_power_put(intel_dp, power_domain); + intel_display_power_put(dev_priv, power_domain); if (intel_encoder->type != INTEL_OUTPUT_EDP) intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; @@ -5091,7 +5071,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) * indefinitely. */ DRM_DEBUG_KMS("VDD left on by BIOS, adjusting state tracking\n"); - power_domain = intel_display_port_power_domain(&intel_dig_port->base); + power_domain = intel_display_port_aux_power_domain(&intel_dig_port->base); intel_display_power_get(dev_priv, power_domain); edp_panel_vdd_schedule_off(intel_dp); @@ -5153,7 +5133,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) enum intel_display_power_domain power_domain; enum irqreturn ret = IRQ_NONE; - if (intel_dig_port->base.type != INTEL_OUTPUT_EDP) + if (intel_dig_port->base.type != INTEL_OUTPUT_EDP && + intel_dig_port->base.type != INTEL_OUTPUT_HDMI) intel_dig_port->base.type = INTEL_OUTPUT_DISPLAYPORT; if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) { @@ -5172,7 +5153,7 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) port_name(intel_dig_port->port), long_hpd ? "long" : "short"); - power_domain = intel_display_port_power_domain(intel_encoder); + power_domain = intel_display_port_aux_power_domain(intel_encoder); intel_display_power_get(dev_priv, power_domain); if (long_hpd) { diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0598932ce6235..0d00f07b7163c 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -550,7 +550,6 @@ struct intel_crtc { int adjusted_x; int adjusted_y; - struct drm_i915_gem_object *cursor_bo; uint32_t cursor_addr; uint32_t cursor_cntl; uint32_t cursor_size; @@ -1169,6 +1168,8 @@ void hsw_enable_ips(struct intel_crtc *crtc); void hsw_disable_ips(struct intel_crtc *crtc); enum intel_display_power_domain intel_display_port_power_domain(struct intel_encoder *intel_encoder); +enum intel_display_power_domain +intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder); void intel_mode_from_pipe_config(struct drm_display_mode *mode, struct intel_crtc_state *pipe_config); void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc); @@ -1377,8 +1378,6 @@ void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); void intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); -void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv); -void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv); void intel_runtime_pm_get(struct drm_i915_private *dev_priv); void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv); void intel_runtime_pm_put(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 9eafa191cee2e..64086f2d4e26c 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1335,21 +1335,17 @@ intel_hdmi_set_edid(struct drm_connector *connector, bool force) { struct drm_i915_private *dev_priv = to_i915(connector->dev); struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); - struct intel_encoder *intel_encoder = - &hdmi_to_dig_port(intel_hdmi)->base; - enum intel_display_power_domain power_domain; struct edid *edid = NULL; bool connected = false; - power_domain = intel_display_port_power_domain(intel_encoder); - intel_display_power_get(dev_priv, power_domain); + intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); if (force) edid = drm_get_edid(connector, intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus)); - intel_display_power_put(dev_priv, power_domain); + intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS); to_intel_connector(connector)->detect_edid = edid; if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) { @@ -1378,15 +1374,18 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); struct drm_i915_private *dev_priv = to_i915(connector->dev); bool live_status = false; - unsigned int retry = 3; + unsigned int try; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); - while (!live_status && --retry) { + intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); + + for (try = 0; !live_status && try < 4; try++) { + if (try) + msleep(10); live_status = intel_digital_port_connected(dev_priv, hdmi_to_dig_port(intel_hdmi)); - mdelay(10); } if (!live_status) @@ -1402,6 +1401,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) } else status = connector_status_disconnected; + intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS); + return status; } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 1369fc41d0391..8324654037b65 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -483,7 +483,7 @@ gmbus_xfer(struct i2c_adapter *adapter, int i = 0, inc, try = 0; int ret = 0; - intel_aux_display_runtime_get(dev_priv); + intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); mutex_lock(&dev_priv->gmbus_mutex); if (bus->force_bit) { @@ -595,7 +595,9 @@ timeout: out: mutex_unlock(&dev_priv->gmbus_mutex); - intel_aux_display_runtime_put(dev_priv); + + intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS); + return ret; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 071a76b9ac523..f091ad12d694a 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4782,8 +4782,7 @@ static void gen9_enable_rc6(struct drm_device *dev) /* 2b: Program RC6 thresholds.*/ /* WaRsDoubleRc6WrlWithCoarsePowerGating: Doubling WRL only when CPG is enabled */ - if (IS_SKYLAKE(dev) && !((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && - (INTEL_REVID(dev) <= SKL_REVID_E0))) + if (IS_SKYLAKE(dev)) I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16); else I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16); @@ -4825,7 +4824,7 @@ static void gen9_enable_rc6(struct drm_device *dev) * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6. */ if ((IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) || - ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && (INTEL_REVID(dev) <= SKL_REVID_E0))) + ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && (INTEL_REVID(dev) <= SKL_REVID_F0))) I915_WRITE(GEN9_PG_ENABLE, 0); else I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index d89c1d0aa1b74..7e23d65c9b246 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -362,6 +362,7 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv, BIT(POWER_DOMAIN_AUX_C) | \ BIT(POWER_DOMAIN_AUDIO) | \ BIT(POWER_DOMAIN_VGA) | \ + BIT(POWER_DOMAIN_GMBUS) | \ BIT(POWER_DOMAIN_INIT)) #define BXT_DISPLAY_POWERWELL_1_POWER_DOMAINS ( \ BXT_DISPLAY_POWERWELL_2_POWER_DOMAINS | \ @@ -1483,6 +1484,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv, BIT(POWER_DOMAIN_AUX_B) | \ BIT(POWER_DOMAIN_AUX_C) | \ BIT(POWER_DOMAIN_AUX_D) | \ + BIT(POWER_DOMAIN_GMBUS) | \ BIT(POWER_DOMAIN_INIT)) #define HSW_DISPLAY_POWER_DOMAINS ( \ (POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS) | \ @@ -1845,6 +1847,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv) i915.disable_power_well = sanitize_disable_power_well_option(dev_priv, i915.disable_power_well); + BUILD_BUG_ON(POWER_DOMAIN_NUM > 31); + mutex_init(&power_domains->lock); /* @@ -2064,36 +2068,6 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv) } /** - * intel_aux_display_runtime_get - grab an auxiliary power domain reference - * @dev_priv: i915 device instance - * - * This function grabs a power domain reference for the auxiliary power domain - * (for access to the GMBUS and DP AUX blocks) and ensures that it and all its - * parents are powered up. Therefore users should only grab a reference to the - * innermost power domain they need. - * - * Any power domain reference obtained by this function must have a symmetric - * call to intel_aux_display_runtime_put() to release the reference again. - */ -void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv) -{ - intel_runtime_pm_get(dev_priv); -} - -/** - * intel_aux_display_runtime_put - release an auxiliary power domain reference - * @dev_priv: i915 device instance - * - * This function drops the auxiliary power domain reference obtained by - * intel_aux_display_runtime_get() and might power down the corresponding - * hardware block right away if this is the last reference. - */ -void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv) -{ - intel_runtime_pm_put(dev_priv); -} - -/** * intel_runtime_pm_get - grab a runtime pm reference * @dev_priv: i915 device instance * diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 64f16ea779ef3..7b990b4e96d23 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -63,8 +63,7 @@ static void imx_drm_driver_lastclose(struct drm_device *drm) #if IS_ENABLED(CONFIG_DRM_IMX_FB_HELPER) struct imx_drm_device *imxdrm = drm->dev_private; - if (imxdrm->fbhelper) - drm_fbdev_cma_restore_mode(imxdrm->fbhelper); + drm_fbdev_cma_restore_mode(imxdrm->fbhelper); #endif } @@ -340,7 +339,7 @@ err_kms: * imx_drm_add_crtc - add a new crtc */ int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc, - struct imx_drm_crtc **new_crtc, + struct imx_drm_crtc **new_crtc, struct drm_plane *primary_plane, const struct imx_drm_crtc_helper_funcs *imx_drm_helper_funcs, struct device_node *port) { @@ -379,7 +378,7 @@ int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc, drm_crtc_helper_add(crtc, imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs); - drm_crtc_init(drm, crtc, + drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL, imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs); return 0; diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h index 28e776d8d9d27..83284b4d4be1e 100644 --- a/drivers/gpu/drm/imx/imx-drm.h +++ b/drivers/gpu/drm/imx/imx-drm.h @@ -9,6 +9,7 @@ struct drm_display_mode; struct drm_encoder; struct drm_fbdev_cma; struct drm_framebuffer; +struct drm_plane; struct imx_drm_crtc; struct platform_device; @@ -24,7 +25,7 @@ struct imx_drm_crtc_helper_funcs { }; int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc, - struct imx_drm_crtc **new_crtc, + struct imx_drm_crtc **new_crtc, struct drm_plane *primary_plane, const struct imx_drm_crtc_helper_funcs *imx_helper_funcs, struct device_node *port); int imx_drm_remove_crtc(struct imx_drm_crtc *); diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index e671ad3694166..f9597146dc674 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -721,6 +721,7 @@ static const struct of_device_id imx_tve_dt_ids[] = { { .compatible = "fsl,imx53-tve", }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, imx_tve_dt_ids); static struct platform_driver imx_tve_driver = { .probe = imx_tve_probe, diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 7bc8301faffff..4ab841eebee19 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -212,7 +212,8 @@ static void ipu_crtc_handle_pageflip(struct ipu_crtc *ipu_crtc) spin_lock_irqsave(&drm->event_lock, flags); if (ipu_crtc->page_flip_event) - drm_send_vblank_event(drm, -1, ipu_crtc->page_flip_event); + drm_crtc_send_vblank_event(&ipu_crtc->base, + ipu_crtc->page_flip_event); ipu_crtc->page_flip_event = NULL; imx_drm_crtc_vblank_put(ipu_crtc->imx_crtc); spin_unlock_irqrestore(&drm->event_lock, flags); @@ -349,7 +350,6 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc, struct ipu_soc *ipu = dev_get_drvdata(ipu_crtc->dev->parent); int dp = -EINVAL; int ret; - int id; ret = ipu_get_resources(ipu_crtc, pdata); if (ret) { @@ -358,18 +358,23 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc, return ret; } + if (pdata->dp >= 0) + dp = IPU_DP_FLOW_SYNC_BG; + ipu_crtc->plane[0] = ipu_plane_init(drm, ipu, pdata->dma[0], dp, 0, + DRM_PLANE_TYPE_PRIMARY); + if (IS_ERR(ipu_crtc->plane[0])) { + ret = PTR_ERR(ipu_crtc->plane[0]); + goto err_put_resources; + } + ret = imx_drm_add_crtc(drm, &ipu_crtc->base, &ipu_crtc->imx_crtc, - &ipu_crtc_helper_funcs, ipu_crtc->dev->of_node); + &ipu_crtc->plane[0]->base, &ipu_crtc_helper_funcs, + ipu_crtc->dev->of_node); if (ret) { dev_err(ipu_crtc->dev, "adding crtc failed with %d.\n", ret); goto err_put_resources; } - if (pdata->dp >= 0) - dp = IPU_DP_FLOW_SYNC_BG; - id = imx_drm_crtc_id(ipu_crtc->imx_crtc); - ipu_crtc->plane[0] = ipu_plane_init(ipu_crtc->base.dev, ipu, - pdata->dma[0], dp, BIT(id), true); ret = ipu_plane_get_resources(ipu_crtc->plane[0]); if (ret) { dev_err(ipu_crtc->dev, "getting plane 0 resources failed with %d.\n", @@ -379,10 +384,10 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc, /* If this crtc is using the DP, add an overlay plane */ if (pdata->dp >= 0 && pdata->dma[1] > 0) { - ipu_crtc->plane[1] = ipu_plane_init(ipu_crtc->base.dev, ipu, - pdata->dma[1], - IPU_DP_FLOW_SYNC_FG, - BIT(id), false); + ipu_crtc->plane[1] = ipu_plane_init(drm, ipu, pdata->dma[1], + IPU_DP_FLOW_SYNC_FG, + drm_crtc_mask(&ipu_crtc->base), + DRM_PLANE_TYPE_OVERLAY); if (IS_ERR(ipu_crtc->plane[1])) ipu_crtc->plane[1] = NULL; } @@ -407,28 +412,6 @@ err_put_resources: return ret; } -static struct device_node *ipu_drm_get_port_by_id(struct device_node *parent, - int port_id) -{ - struct device_node *port; - int id, ret; - - port = of_get_child_by_name(parent, "port"); - while (port) { - ret = of_property_read_u32(port, "reg", &id); - if (!ret && id == port_id) - return port; - - do { - port = of_get_next_child(parent, port); - if (!port) - return NULL; - } while (of_node_cmp(port->name, "port")); - } - - return NULL; -} - static int ipu_drm_bind(struct device *dev, struct device *master, void *data) { struct ipu_client_platformdata *pdata = dev->platform_data; @@ -470,23 +453,11 @@ static const struct component_ops ipu_crtc_ops = { static int ipu_drm_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct ipu_client_platformdata *pdata = dev->platform_data; int ret; if (!dev->platform_data) return -EINVAL; - if (!dev->of_node) { - /* Associate crtc device with the corresponding DI port node */ - dev->of_node = ipu_drm_get_port_by_id(dev->parent->of_node, - pdata->di + 2); - if (!dev->of_node) { - dev_err(dev, "missing port@%d node in %s\n", - pdata->di + 2, dev->parent->of_node->full_name); - return -ENODEV; - } - } - ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); if (ret) return ret; diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 575f4c84388f0..e2ff410bab744 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -381,7 +381,7 @@ static struct drm_plane_funcs ipu_plane_funcs = { struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu, int dma, int dp, unsigned int possible_crtcs, - bool priv) + enum drm_plane_type type) { struct ipu_plane *ipu_plane; int ret; @@ -399,10 +399,9 @@ struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu, ipu_plane->dma = dma; ipu_plane->dp_flow = dp; - ret = drm_plane_init(dev, &ipu_plane->base, possible_crtcs, - &ipu_plane_funcs, ipu_plane_formats, - ARRAY_SIZE(ipu_plane_formats), - priv); + ret = drm_universal_plane_init(dev, &ipu_plane->base, possible_crtcs, + &ipu_plane_funcs, ipu_plane_formats, + ARRAY_SIZE(ipu_plane_formats), type); if (ret) { DRM_ERROR("failed to initialize plane\n"); kfree(ipu_plane); diff --git a/drivers/gpu/drm/imx/ipuv3-plane.h b/drivers/gpu/drm/imx/ipuv3-plane.h index 9b5eff18f5b82..3a443b413c60c 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.h +++ b/drivers/gpu/drm/imx/ipuv3-plane.h @@ -34,7 +34,7 @@ struct ipu_plane { struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu, int dma, int dp, unsigned int possible_crtcs, - bool priv); + enum drm_plane_type type); /* Init IDMAC, DMFC, DP */ int ipu_plane_mode_set(struct ipu_plane *plane, struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index b4deb9cf9d716..2e9b9f1b5cd2b 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -54,7 +54,11 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) if (imxpd->panel && imxpd->panel->funcs && imxpd->panel->funcs->get_modes) { + struct drm_display_info *di = &connector->display_info; + num_modes = imxpd->panel->funcs->get_modes(imxpd->panel); + if (!imxpd->bus_format && di->num_bus_formats) + imxpd->bus_format = di->bus_formats[0]; if (num_modes > 0) return num_modes; } diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h index 8f760002e4018..913192c94876f 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h @@ -159,7 +159,6 @@ struct nvkm_device_func { struct nvkm_device_quirk { u8 tv_pin_mask; u8 tv_gpio; - bool War00C800_0; }; struct nvkm_device_chip { diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index db6bc67605451..64c8d932d5f19 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -829,7 +829,6 @@ nouveau_finish_page_flip(struct nouveau_channel *chan, struct drm_device *dev = drm->dev; struct nouveau_page_flip_state *s; unsigned long flags; - int crtcid = -1; spin_lock_irqsave(&dev->event_lock, flags); @@ -841,15 +840,19 @@ nouveau_finish_page_flip(struct nouveau_channel *chan, s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head); if (s->event) { - /* Vblank timestamps/counts are only correct on >= NV-50 */ - if (drm->device.info.family >= NV_DEVICE_INFO_V0_TESLA) - crtcid = s->crtc; + if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) { + drm_arm_vblank_event(dev, s->crtc, s->event); + } else { + drm_send_vblank_event(dev, s->crtc, s->event); - drm_send_vblank_event(dev, crtcid, s->event); + /* Give up ownership of vblank for page-flipped crtc */ + drm_vblank_put(dev, s->crtc); + } + } + else { + /* Give up ownership of vblank for page-flipped crtc */ + drm_vblank_put(dev, s->crtc); } - - /* Give up ownership of vblank for page-flipped crtc */ - drm_vblank_put(dev, s->crtc); list_del(&s->head); if (ps) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c index caf22b589edc3..62ad0300cfa5a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c @@ -259,12 +259,6 @@ nvkm_device_pci_10de_0df4[] = { }; static const struct nvkm_device_pci_vendor -nvkm_device_pci_10de_0fcd[] = { - { 0x17aa, 0x3801, NULL, { .War00C800_0 = true } }, /* Lenovo Y510P */ - {} -}; - -static const struct nvkm_device_pci_vendor nvkm_device_pci_10de_0fd2[] = { { 0x1028, 0x0595, "GeForce GT 640M LE" }, { 0x1028, 0x05b2, "GeForce GT 640M LE" }, @@ -279,12 +273,6 @@ nvkm_device_pci_10de_0fe3[] = { }; static const struct nvkm_device_pci_vendor -nvkm_device_pci_10de_0fe4[] = { - { 0x144d, 0xc740, NULL, { .War00C800_0 = true } }, - {} -}; - -static const struct nvkm_device_pci_vendor nvkm_device_pci_10de_104b[] = { { 0x1043, 0x844c, "GeForce GT 625" }, { 0x1043, 0x846b, "GeForce GT 625" }, @@ -690,13 +678,6 @@ nvkm_device_pci_10de_1189[] = { static const struct nvkm_device_pci_vendor nvkm_device_pci_10de_1199[] = { { 0x1458, 0xd001, "GeForce GTX 760" }, - { 0x1462, 0x1106, "GeForce GTX 780M", { .War00C800_0 = true } }, /* Medion Erazer X7827 */ - {} -}; - -static const struct nvkm_device_pci_vendor -nvkm_device_pci_10de_11e0[] = { - { 0x1558, 0x5106, NULL, { .War00C800_0 = true } }, {} }; @@ -707,14 +688,6 @@ nvkm_device_pci_10de_11e3[] = { }; static const struct nvkm_device_pci_vendor -nvkm_device_pci_10de_11fc[] = { - { 0x1179, 0x0001, NULL, { .War00C800_0 = true } }, /* Toshiba Tecra W50 */ - { 0x17aa, 0x2211, NULL, { .War00C800_0 = true } }, /* Lenovo W541 */ - { 0x17aa, 0x221e, NULL, { .War00C800_0 = true } }, /* Lenovo W541 */ - {} -}; - -static const struct nvkm_device_pci_vendor nvkm_device_pci_10de_1247[] = { { 0x1043, 0x212a, "GeForce GT 635M" }, { 0x1043, 0x212b, "GeForce GT 635M" }, @@ -1368,7 +1341,7 @@ nvkm_device_pci_10de[] = { { 0x0fc6, "GeForce GTX 650" }, { 0x0fc8, "GeForce GT 740" }, { 0x0fc9, "GeForce GT 730" }, - { 0x0fcd, "GeForce GT 755M", nvkm_device_pci_10de_0fcd }, + { 0x0fcd, "GeForce GT 755M" }, { 0x0fce, "GeForce GT 640M LE" }, { 0x0fd1, "GeForce GT 650M" }, { 0x0fd2, "GeForce GT 640M", nvkm_device_pci_10de_0fd2 }, @@ -1382,7 +1355,7 @@ nvkm_device_pci_10de[] = { { 0x0fe1, "GeForce GT 730M" }, { 0x0fe2, "GeForce GT 745M" }, { 0x0fe3, "GeForce GT 745M", nvkm_device_pci_10de_0fe3 }, - { 0x0fe4, "GeForce GT 750M", nvkm_device_pci_10de_0fe4 }, + { 0x0fe4, "GeForce GT 750M" }, { 0x0fe9, "GeForce GT 750M" }, { 0x0fea, "GeForce GT 755M" }, { 0x0fec, "GeForce 710A" }, @@ -1497,12 +1470,12 @@ nvkm_device_pci_10de[] = { { 0x11c6, "GeForce GTX 650 Ti" }, { 0x11c8, "GeForce GTX 650" }, { 0x11cb, "GeForce GT 740" }, - { 0x11e0, "GeForce GTX 770M", nvkm_device_pci_10de_11e0 }, + { 0x11e0, "GeForce GTX 770M" }, { 0x11e1, "GeForce GTX 765M" }, { 0x11e2, "GeForce GTX 765M" }, { 0x11e3, "GeForce GTX 760M", nvkm_device_pci_10de_11e3 }, { 0x11fa, "Quadro K4000" }, - { 0x11fc, "Quadro K2100M", nvkm_device_pci_10de_11fc }, + { 0x11fc, "Quadro K2100M" }, { 0x1200, "GeForce GTX 560 Ti" }, { 0x1201, "GeForce GTX 560" }, { 0x1203, "GeForce GTX 460 SE v2" }, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c index 43006db6fd582..80fed7e78dcbe 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c @@ -83,6 +83,7 @@ nvbios_fan_parse(struct nvkm_bios *bios, struct nvbios_therm_fan *fan) fan->type = NVBIOS_THERM_FAN_UNK; } + fan->fan_mode = NVBIOS_THERM_FAN_LINEAR; fan->min_duty = nvbios_rd08(bios, data + 0x02); fan->max_duty = nvbios_rd08(bios, data + 0x03); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c index d942fa7b9f187..86f9f3b13f71f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c @@ -81,9 +81,7 @@ gk104_pmu_pgob(struct nvkm_pmu *pmu, bool enable) nvkm_mask(device, 0x000200, 0x00001000, 0x00001000); nvkm_rd32(device, 0x000200); - if ( nvkm_boolopt(device->cfgopt, "War00C800_0", - device->quirk ? device->quirk->War00C800_0 : false)) { - nvkm_info(&pmu->subdev, "hw bug workaround enabled\n"); + if (nvkm_boolopt(device->cfgopt, "War00C800_0", true)) { switch (device->chipset) { case 0xe4: magic(device, 0x04000000); diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index b8e4cdec28c36..24f92bea39c7d 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -112,11 +112,8 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, dma_addr_t paddr; int ret; - /* only doing ARGB32 since this is what is needed to alpha-blend - * with video overlays: - */ sizes->surface_bpp = 32; - sizes->surface_depth = 32; + sizes->surface_depth = 24; DBG("create fbdev: %dx%d@%d (%dx%d)", sizes->surface_width, sizes->surface_height, sizes->surface_bpp, diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 248953d2fdb74..f81fb26410976 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -4173,11 +4173,7 @@ void cik_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) control |= ib->length_dw | (vm_id << 24); radeon_ring_write(ring, header); - radeon_ring_write(ring, -#ifdef __BIG_ENDIAN - (2 << 0) | -#endif - (ib->gpu_addr & 0xFFFFFFFC)); + radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFFC)); radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF); radeon_ring_write(ring, control); } @@ -8472,7 +8468,7 @@ restart_ih: if (queue_dp) schedule_work(&rdev->dp_work); if (queue_hotplug) - schedule_work(&rdev->hotplug_work); + schedule_delayed_work(&rdev->hotplug_work, 0); if (queue_reset) { rdev->needs_reset = true; wake_up_all(&rdev->fence_queue); @@ -9630,6 +9626,9 @@ static void dce8_program_watermarks(struct radeon_device *rdev, (rdev->disp_priority == 2)) { DRM_DEBUG_KMS("force priority to high\n"); } + + /* Save number of lines the linebuffer leads before the scanout */ + radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); } /* select wm A */ diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 7f33767d7ed65..2ad462896896b 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2372,6 +2372,9 @@ static void evergreen_program_watermarks(struct radeon_device *rdev, c.full = dfixed_div(c, a); priority_b_mark = dfixed_trunc(c); priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK; + + /* Save number of lines the linebuffer leads before the scanout */ + radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); } /* select wm A */ @@ -5344,7 +5347,7 @@ restart_ih: if (queue_dp) schedule_work(&rdev->dp_work); if (queue_hotplug) - schedule_work(&rdev->hotplug_work); + schedule_delayed_work(&rdev->hotplug_work, 0); if (queue_hdmi) schedule_work(&rdev->audio_work); if (queue_thermal && rdev->pm.dpm_enabled) diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 238b13f045c18..9e7e2bf03b815 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -806,7 +806,7 @@ int r100_irq_process(struct radeon_device *rdev) status = r100_irq_ack(rdev); } if (queue_hotplug) - schedule_work(&rdev->hotplug_work); + schedule_delayed_work(&rdev->hotplug_work, 0); if (rdev->msi_enabled) { switch (rdev->family) { case CHIP_RS400: @@ -3217,6 +3217,9 @@ void r100_bandwidth_update(struct radeon_device *rdev) uint32_t pixel_bytes1 = 0; uint32_t pixel_bytes2 = 0; + /* Guess line buffer size to be 8192 pixels */ + u32 lb_size = 8192; + if (!rdev->mode_info.mode_config_initialized) return; @@ -3631,6 +3634,13 @@ void r100_bandwidth_update(struct radeon_device *rdev) DRM_DEBUG_KMS("GRPH2_BUFFER_CNTL from to %x\n", (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL)); } + + /* Save number of lines the linebuffer leads before the scanout */ + if (mode1) + rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay); + + if (mode2) + rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay); } int r100_ring_test(struct radeon_device *rdev, struct radeon_ring *ring) diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 4ea5b10ff5f41..cc2fdf0be37a6 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -4276,7 +4276,7 @@ restart_ih: WREG32(IH_RB_RPTR, rptr); } if (queue_hotplug) - schedule_work(&rdev->hotplug_work); + schedule_delayed_work(&rdev->hotplug_work, 0); if (queue_hdmi) schedule_work(&rdev->audio_work); if (queue_thermal && rdev->pm.dpm_enabled) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index b6cbd816537e7..87db64983ea8c 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2414,7 +2414,7 @@ struct radeon_device { struct r600_ih ih; /* r6/700 interrupt ring */ struct radeon_rlc rlc; struct radeon_mec mec; - struct work_struct hotplug_work; + struct delayed_work hotplug_work; struct work_struct dp_work; struct work_struct audio_work; int num_crtc; /* number of crtcs */ diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c index fe994aac3b040..c77d349c561c6 100644 --- a/drivers/gpu/drm/radeon/radeon_agp.c +++ b/drivers/gpu/drm/radeon/radeon_agp.c @@ -54,6 +54,9 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = { /* Intel 82855PM host bridge / Mobility 9600 M10 RV350 Needs AGPMode 1 (lp #195051) */ { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4e50, PCI_VENDOR_ID_IBM, 0x0550, 1}, + /* Intel 82855PM host bridge / RV250/M9 GL [Mobility FireGL 9000/Radeon 9000] needs AGPMode 1 (Thinkpad T40p) */ + { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c66, + PCI_VENDOR_ID_IBM, 0x054d, 1}, /* Intel 82855PM host bridge / Mobility M7 needs AGPMode 1 */ { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c57, PCI_VENDOR_ID_IBM, 0x0530, 1}, diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 5a2cafb4f1bc5..340f3f549f295 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1234,13 +1234,32 @@ radeon_dvi_detect(struct drm_connector *connector, bool force) if (r < 0) return connector_status_disconnected; + if (radeon_connector->detected_hpd_without_ddc) { + force = true; + radeon_connector->detected_hpd_without_ddc = false; + } + if (!force && radeon_check_hpd_status_unchanged(connector)) { ret = connector->status; goto exit; } - if (radeon_connector->ddc_bus) + if (radeon_connector->ddc_bus) { dret = radeon_ddc_probe(radeon_connector, false); + + /* Sometimes the pins required for the DDC probe on DVI + * connectors don't make contact at the same time that the ones + * for HPD do. If the DDC probe fails even though we had an HPD + * signal, try again later */ + if (!dret && !force && + connector->status != connector_status_connected) { + DRM_DEBUG_KMS("hpd detected without ddc, retrying in 1 second\n"); + radeon_connector->detected_hpd_without_ddc = true; + schedule_delayed_work(&rdev->hotplug_work, + msecs_to_jiffies(1000)); + goto exit; + } + } if (dret) { radeon_connector->detected_by_load = false; radeon_connector_free_edid(connector); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index a8d9927ed9eb9..1eca0acac016f 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -322,7 +322,9 @@ void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id) * to complete in this vblank? */ if (update_pending && - (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id, 0, + (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, + crtc_id, + USE_REAL_VBLANKSTART, &vpos, &hpos, NULL, NULL, &rdev->mode_info.crtcs[crtc_id]->base.hwmode)) && ((vpos >= (99 * rdev->mode_info.crtcs[crtc_id]->base.hwmode.crtc_vdisplay)/100) || @@ -401,6 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &radeon_crtc->base; unsigned long flags; int r; + int vpos, hpos, stat, min_udelay; + struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; down_read(&rdev->exclusive_lock); if (work->fence) { @@ -437,6 +441,41 @@ static void radeon_flip_work_func(struct work_struct *__work) /* set the proper interrupt */ radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id); + /* If this happens to execute within the "virtually extended" vblank + * interval before the start of the real vblank interval then it needs + * to delay programming the mmio flip until the real vblank is entered. + * This prevents completing a flip too early due to the way we fudge + * our vblank counter and vblank timestamps in order to work around the + * problem that the hw fires vblank interrupts before actual start of + * vblank (when line buffer refilling is done for a frame). It + * complements the fudging logic in radeon_get_crtc_scanoutpos() for + * timestamping and radeon_get_vblank_counter_kms() for vblank counts. + * + * In practice this won't execute very often unless on very fast + * machines because the time window for this to happen is very small. + */ + for (;;) { + /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank + * start in hpos, and to the "fudged earlier" vblank start in + * vpos. + */ + stat = radeon_get_crtc_scanoutpos(rdev->ddev, work->crtc_id, + GET_DISTANCE_TO_VBLANKSTART, + &vpos, &hpos, NULL, NULL, + &crtc->hwmode); + + if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) != + (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) || + !(vpos >= 0 && hpos <= 0)) + break; + + /* Sleep at least until estimated real start of hw vblank */ + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + usleep_range(min_udelay, 2 * min_udelay); + spin_lock_irqsave(&crtc->dev->event_lock, flags); + }; + /* do the flip (mmio) */ radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); @@ -1768,6 +1807,15 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc, * \param dev Device to query. * \param crtc Crtc to query. * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0). + * For driver internal use only also supports these flags: + * + * USE_REAL_VBLANKSTART to use the real start of vblank instead + * of a fudged earlier start of vblank. + * + * GET_DISTANCE_TO_VBLANKSTART to return distance to the + * fudged earlier start of vblank in *vpos and the distance + * to true start of vblank in *hpos. + * * \param *vpos Location where vertical scanout position should be stored. * \param *hpos Location where horizontal scanout position should go. * \param *stime Target location for timestamp taken immediately before @@ -1911,10 +1959,40 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, vbl_end = 0; } + /* Called from driver internal vblank counter query code? */ + if (flags & GET_DISTANCE_TO_VBLANKSTART) { + /* Caller wants distance from real vbl_start in *hpos */ + *hpos = *vpos - vbl_start; + } + + /* Fudge vblank to start a few scanlines earlier to handle the + * problem that vblank irqs fire a few scanlines before start + * of vblank. Some driver internal callers need the true vblank + * start to be used and signal this via the USE_REAL_VBLANKSTART flag. + * + * The cause of the "early" vblank irq is that the irq is triggered + * by the line buffer logic when the line buffer read position enters + * the vblank, whereas our crtc scanout position naturally lags the + * line buffer read position. + */ + if (!(flags & USE_REAL_VBLANKSTART)) + vbl_start -= rdev->mode_info.crtcs[pipe]->lb_vblank_lead_lines; + /* Test scanout position against vblank region. */ if ((*vpos < vbl_start) && (*vpos >= vbl_end)) in_vbl = false; + /* In vblank? */ + if (in_vbl) + ret |= DRM_SCANOUTPOS_IN_VBLANK; + + /* Called from driver internal vblank counter query code? */ + if (flags & GET_DISTANCE_TO_VBLANKSTART) { + /* Caller wants distance from fudged earlier vbl_start */ + *vpos -= vbl_start; + return ret; + } + /* Check if inside vblank area and apply corrective offsets: * vpos will then be >=0 in video scanout area, but negative * within vblank area, counting down the number of lines until @@ -1930,31 +2008,5 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, /* Correct for shifted end of vbl at vbl_end. */ *vpos = *vpos - vbl_end; - /* In vblank? */ - if (in_vbl) - ret |= DRM_SCANOUTPOS_IN_VBLANK; - - /* Is vpos outside nominal vblank area, but less than - * 1/100 of a frame height away from start of vblank? - * If so, assume this isn't a massively delayed vblank - * interrupt, but a vblank interrupt that fired a few - * microseconds before true start of vblank. Compensate - * by adding a full frame duration to the final timestamp. - * Happens, e.g., on ATI R500, R600. - * - * We only do this if DRM_CALLED_FROM_VBLIRQ. - */ - if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) { - vbl_start = mode->crtc_vdisplay; - vtotal = mode->crtc_vtotal; - - if (vbl_start - *vpos < vtotal / 100) { - *vpos -= vtotal; - - /* Signal this correction as "applied". */ - ret |= 0x8; - } - } - return ret; } diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 171d3e43c30cc..979f3bf65f2c4 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -74,7 +74,7 @@ irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg) static void radeon_hotplug_work_func(struct work_struct *work) { struct radeon_device *rdev = container_of(work, struct radeon_device, - hotplug_work); + hotplug_work.work); struct drm_device *dev = rdev->ddev; struct drm_mode_config *mode_config = &dev->mode_config; struct drm_connector *connector; @@ -302,7 +302,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev) } } - INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func); + INIT_DELAYED_WORK(&rdev->hotplug_work, radeon_hotplug_work_func); INIT_WORK(&rdev->dp_work, radeon_dp_work_func); INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi); @@ -310,7 +310,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev) r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq); if (r) { rdev->irq.installed = false; - flush_work(&rdev->hotplug_work); + flush_delayed_work(&rdev->hotplug_work); return r; } @@ -333,7 +333,7 @@ void radeon_irq_kms_fini(struct radeon_device *rdev) rdev->irq.installed = false; if (rdev->msi_enabled) pci_disable_msi(rdev->pdev); - flush_work(&rdev->hotplug_work); + flush_delayed_work(&rdev->hotplug_work); } } diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 0ec6fcca16d3b..d290a8a09036e 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -755,6 +755,8 @@ void radeon_driver_preclose_kms(struct drm_device *dev, */ u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc) { + int vpos, hpos, stat; + u32 count; struct radeon_device *rdev = dev->dev_private; if (crtc < 0 || crtc >= rdev->num_crtc) { @@ -762,7 +764,53 @@ u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc) return -EINVAL; } - return radeon_get_vblank_counter(rdev, crtc); + /* The hw increments its frame counter at start of vsync, not at start + * of vblank, as is required by DRM core vblank counter handling. + * Cook the hw count here to make it appear to the caller as if it + * incremented at start of vblank. We measure distance to start of + * vblank in vpos. vpos therefore will be >= 0 between start of vblank + * and start of vsync, so vpos >= 0 means to bump the hw frame counter + * result by 1 to give the proper appearance to caller. + */ + if (rdev->mode_info.crtcs[crtc]) { + /* Repeat readout if needed to provide stable result if + * we cross start of vsync during the queries. + */ + do { + count = radeon_get_vblank_counter(rdev, crtc); + /* Ask radeon_get_crtc_scanoutpos to return vpos as + * distance to start of vblank, instead of regular + * vertical scanout pos. + */ + stat = radeon_get_crtc_scanoutpos( + dev, crtc, GET_DISTANCE_TO_VBLANKSTART, + &vpos, &hpos, NULL, NULL, + &rdev->mode_info.crtcs[crtc]->base.hwmode); + } while (count != radeon_get_vblank_counter(rdev, crtc)); + + if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) != + (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) { + DRM_DEBUG_VBL("Query failed! stat %d\n", stat); + } + else { + DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n", + crtc, vpos); + + /* Bump counter if we are at >= leading edge of vblank, + * but before vsync where vpos would turn negative and + * the hw counter really increments. + */ + if (vpos >= 0) + count++; + } + } + else { + /* Fallback to use value as is. */ + count = radeon_get_vblank_counter(rdev, crtc); + DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n"); + } + + return count; } /** diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index 830e171c3a9e3..bba112628b478 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -367,6 +367,7 @@ struct radeon_crtc { u32 line_time; u32 wm_low; u32 wm_high; + u32 lb_vblank_lead_lines; struct drm_display_mode hw_mode; enum radeon_output_csc output_csc; }; @@ -553,6 +554,7 @@ struct radeon_connector { void *con_priv; bool dac_load_detect; bool detected_by_load; /* if the connection status was determined by load */ + bool detected_hpd_without_ddc; /* if an HPD signal was detected on DVI, but ddc probing failed */ uint16_t connector_object_id; struct radeon_hpd hpd; struct radeon_router router; @@ -686,6 +688,9 @@ struct atom_voltage_table struct atom_voltage_table_entry entries[MAX_VOLTAGE_ENTRIES]; }; +/* Driver internal use only flags of radeon_get_crtc_scanoutpos() */ +#define USE_REAL_VBLANKSTART (1 << 30) +#define GET_DISTANCE_TO_VBLANKSTART (1 << 31) extern void radeon_add_atom_connector(struct drm_device *dev, diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index f4f03dcc15304..59abebd6b5dc4 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1756,7 +1756,9 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev) */ for (crtc = 0; (crtc < rdev->num_crtc) && in_vbl; crtc++) { if (rdev->pm.active_crtcs & (1 << crtc)) { - vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0, + vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, + crtc, + USE_REAL_VBLANKSTART, &vpos, &hpos, NULL, NULL, &rdev->mode_info.crtcs[crtc]->base.hwmode); if ((vbl_status & DRM_SCANOUTPOS_VALID) && diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c index 574f62bbd215b..7eb1ae7589061 100644 --- a/drivers/gpu/drm/radeon/radeon_vce.c +++ b/drivers/gpu/drm/radeon/radeon_vce.c @@ -361,31 +361,31 @@ int radeon_vce_get_create_msg(struct radeon_device *rdev, int ring, /* stitch together an VCE create msg */ ib.length_dw = 0; - ib.ptr[ib.length_dw++] = 0x0000000c; /* len */ - ib.ptr[ib.length_dw++] = 0x00000001; /* session cmd */ - ib.ptr[ib.length_dw++] = handle; - - ib.ptr[ib.length_dw++] = 0x00000030; /* len */ - ib.ptr[ib.length_dw++] = 0x01000001; /* create cmd */ - ib.ptr[ib.length_dw++] = 0x00000000; - ib.ptr[ib.length_dw++] = 0x00000042; - ib.ptr[ib.length_dw++] = 0x0000000a; - ib.ptr[ib.length_dw++] = 0x00000001; - ib.ptr[ib.length_dw++] = 0x00000080; - ib.ptr[ib.length_dw++] = 0x00000060; - ib.ptr[ib.length_dw++] = 0x00000100; - ib.ptr[ib.length_dw++] = 0x00000100; - ib.ptr[ib.length_dw++] = 0x0000000c; - ib.ptr[ib.length_dw++] = 0x00000000; - - ib.ptr[ib.length_dw++] = 0x00000014; /* len */ - ib.ptr[ib.length_dw++] = 0x05000005; /* feedback buffer */ - ib.ptr[ib.length_dw++] = upper_32_bits(dummy); - ib.ptr[ib.length_dw++] = dummy; - ib.ptr[ib.length_dw++] = 0x00000001; + ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); /* len */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); /* session cmd */ + ib.ptr[ib.length_dw++] = cpu_to_le32(handle); + + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000030); /* len */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x01000001); /* create cmd */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000000); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000042); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000a); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000080); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000060); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000100); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000100); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000000); + + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000014); /* len */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x05000005); /* feedback buffer */ + ib.ptr[ib.length_dw++] = cpu_to_le32(upper_32_bits(dummy)); + ib.ptr[ib.length_dw++] = cpu_to_le32(dummy); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); for (i = ib.length_dw; i < ib_size_dw; ++i) - ib.ptr[i] = 0x0; + ib.ptr[i] = cpu_to_le32(0x0); r = radeon_ib_schedule(rdev, &ib, NULL, false); if (r) { @@ -428,21 +428,21 @@ int radeon_vce_get_destroy_msg(struct radeon_device *rdev, int ring, /* stitch together an VCE destroy msg */ ib.length_dw = 0; - ib.ptr[ib.length_dw++] = 0x0000000c; /* len */ - ib.ptr[ib.length_dw++] = 0x00000001; /* session cmd */ - ib.ptr[ib.length_dw++] = handle; + ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); /* len */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); /* session cmd */ + ib.ptr[ib.length_dw++] = cpu_to_le32(handle); - ib.ptr[ib.length_dw++] = 0x00000014; /* len */ - ib.ptr[ib.length_dw++] = 0x05000005; /* feedback buffer */ - ib.ptr[ib.length_dw++] = upper_32_bits(dummy); - ib.ptr[ib.length_dw++] = dummy; - ib.ptr[ib.length_dw++] = 0x00000001; + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000014); /* len */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x05000005); /* feedback buffer */ + ib.ptr[ib.length_dw++] = cpu_to_le32(upper_32_bits(dummy)); + ib.ptr[ib.length_dw++] = cpu_to_le32(dummy); + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); - ib.ptr[ib.length_dw++] = 0x00000008; /* len */ - ib.ptr[ib.length_dw++] = 0x02000001; /* destroy cmd */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000008); /* len */ + ib.ptr[ib.length_dw++] = cpu_to_le32(0x02000001); /* destroy cmd */ for (i = ib.length_dw; i < ib_size_dw; ++i) - ib.ptr[i] = 0x0; + ib.ptr[i] = cpu_to_le32(0x0); r = radeon_ib_schedule(rdev, &ib, NULL, false); if (r) { @@ -699,12 +699,12 @@ bool radeon_vce_semaphore_emit(struct radeon_device *rdev, { uint64_t addr = semaphore->gpu_addr; - radeon_ring_write(ring, VCE_CMD_SEMAPHORE); - radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF); - radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF); - radeon_ring_write(ring, 0x01003000 | (emit_wait ? 1 : 0)); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_SEMAPHORE)); + radeon_ring_write(ring, cpu_to_le32((addr >> 3) & 0x000FFFFF)); + radeon_ring_write(ring, cpu_to_le32((addr >> 23) & 0x000FFFFF)); + radeon_ring_write(ring, cpu_to_le32(0x01003000 | (emit_wait ? 1 : 0))); if (!emit_wait) - radeon_ring_write(ring, VCE_CMD_END); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END)); return true; } @@ -719,10 +719,10 @@ bool radeon_vce_semaphore_emit(struct radeon_device *rdev, void radeon_vce_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) { struct radeon_ring *ring = &rdev->ring[ib->ring]; - radeon_ring_write(ring, VCE_CMD_IB); - radeon_ring_write(ring, ib->gpu_addr); - radeon_ring_write(ring, upper_32_bits(ib->gpu_addr)); - radeon_ring_write(ring, ib->length_dw); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_IB)); + radeon_ring_write(ring, cpu_to_le32(ib->gpu_addr)); + radeon_ring_write(ring, cpu_to_le32(upper_32_bits(ib->gpu_addr))); + radeon_ring_write(ring, cpu_to_le32(ib->length_dw)); } /** @@ -738,12 +738,12 @@ void radeon_vce_fence_emit(struct radeon_device *rdev, struct radeon_ring *ring = &rdev->ring[fence->ring]; uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr; - radeon_ring_write(ring, VCE_CMD_FENCE); - radeon_ring_write(ring, addr); - radeon_ring_write(ring, upper_32_bits(addr)); - radeon_ring_write(ring, fence->seq); - radeon_ring_write(ring, VCE_CMD_TRAP); - radeon_ring_write(ring, VCE_CMD_END); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_FENCE)); + radeon_ring_write(ring, cpu_to_le32(addr)); + radeon_ring_write(ring, cpu_to_le32(upper_32_bits(addr))); + radeon_ring_write(ring, cpu_to_le32(fence->seq)); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_TRAP)); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END)); } /** @@ -765,7 +765,7 @@ int radeon_vce_ring_test(struct radeon_device *rdev, struct radeon_ring *ring) ring->idx, r); return r; } - radeon_ring_write(ring, VCE_CMD_END); + radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END)); radeon_ring_unlock_commit(rdev, ring, false); for (i = 0; i < rdev->usec_timeout; i++) { diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 97a904835759f..6244f4e44e9a5 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -813,7 +813,7 @@ int rs600_irq_process(struct radeon_device *rdev) status = rs600_irq_ack(rdev); } if (queue_hotplug) - schedule_work(&rdev->hotplug_work); + schedule_delayed_work(&rdev->hotplug_work, 0); if (queue_hdmi) schedule_work(&rdev->audio_work); if (rdev->msi_enabled) { diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 516ca27cfa128..6bc44c24e837b 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -207,6 +207,9 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev, { u32 tmp; + /* Guess line buffer size to be 8192 pixels */ + u32 lb_size = 8192; + /* * Line Buffer Setup * There is a single line buffer shared by both display controllers. @@ -243,6 +246,13 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev, tmp |= V_006520_DC_LB_MEMORY_SPLIT_D1_1Q_D2_3Q; } WREG32(R_006520_DC_LB_MEMORY_SPLIT, tmp); + + /* Save number of lines the linebuffer leads before the scanout */ + if (mode1) + rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay); + + if (mode2) + rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay); } struct rs690_watermark { diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 07037e32dea32..f878d6962da58 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2376,6 +2376,9 @@ static void dce6_program_watermarks(struct radeon_device *rdev, c.full = dfixed_div(c, a); priority_b_mark = dfixed_trunc(c); priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK; + + /* Save number of lines the linebuffer leads before the scanout */ + radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); } /* select wm A */ @@ -6848,7 +6851,7 @@ restart_ih: if (queue_dp) schedule_work(&rdev->dp_work); if (queue_hotplug) - schedule_work(&rdev->hotplug_work); + schedule_delayed_work(&rdev->hotplug_work, 0); if (queue_thermal && rdev->pm.dpm_enabled) schedule_work(&rdev->pm.dpm.thermal.work); rdev->ih.rptr = rptr; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 8caea0a33dd84..d908321b94ced 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -67,6 +67,7 @@ static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj, * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap(). */ vma->vm_flags &= ~VM_PFNMAP; + vma->vm_pgoff = 0; ret = dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr, obj->size, &rk_obj->dma_attrs); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 5d8ae5e49c440..03c47eeadc812 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -374,6 +374,7 @@ static const struct of_device_id vop_driver_dt_match[] = { .data = &rk3288_vop }, {}, }; +MODULE_DEVICE_TABLE(of, vop_driver_dt_match); static inline void vop_writel(struct vop *vop, uint32_t offset, uint32_t v) { @@ -959,8 +960,8 @@ static int vop_update_plane_event(struct drm_plane *plane, val = (dest.y2 - dest.y1 - 1) << 16; val |= (dest.x2 - dest.x1 - 1) & 0xffff; VOP_WIN_SET(vop, win, dsp_info, val); - val = (dsp_sty - 1) << 16; - val |= (dsp_stx - 1) & 0xffff; + val = dsp_sty << 16; + val |= dsp_stx & 0xffff; VOP_WIN_SET(vop, win, dsp_st, val); VOP_WIN_SET(vop, win, rb_swap, rb_swap); @@ -1289,7 +1290,7 @@ static void vop_win_state_complete(struct vop_win *vop_win, if (state->event) { spin_lock_irqsave(&drm->event_lock, flags); - drm_send_vblank_event(drm, -1, state->event); + drm_crtc_send_vblank_event(crtc, state->event); spin_unlock_irqrestore(&drm->event_lock, flags); } @@ -1575,32 +1576,25 @@ static int vop_initial(struct vop *vop) return PTR_ERR(vop->dclk); } - ret = clk_prepare(vop->hclk); - if (ret < 0) { - dev_err(vop->dev, "failed to prepare hclk\n"); - return ret; - } - ret = clk_prepare(vop->dclk); if (ret < 0) { dev_err(vop->dev, "failed to prepare dclk\n"); - goto err_unprepare_hclk; + return ret; } - ret = clk_prepare(vop->aclk); + /* Enable both the hclk and aclk to setup the vop */ + ret = clk_prepare_enable(vop->hclk); if (ret < 0) { - dev_err(vop->dev, "failed to prepare aclk\n"); + dev_err(vop->dev, "failed to prepare/enable hclk\n"); goto err_unprepare_dclk; } - /* - * enable hclk, so that we can config vop register. - */ - ret = clk_enable(vop->hclk); + ret = clk_prepare_enable(vop->aclk); if (ret < 0) { - dev_err(vop->dev, "failed to prepare aclk\n"); - goto err_unprepare_aclk; + dev_err(vop->dev, "failed to prepare/enable aclk\n"); + goto err_disable_hclk; } + /* * do hclk_reset, reset all vop registers. */ @@ -1608,7 +1602,7 @@ static int vop_initial(struct vop *vop) if (IS_ERR(ahb_rst)) { dev_err(vop->dev, "failed to get ahb reset\n"); ret = PTR_ERR(ahb_rst); - goto err_disable_hclk; + goto err_disable_aclk; } reset_control_assert(ahb_rst); usleep_range(10, 20); @@ -1634,26 +1628,25 @@ static int vop_initial(struct vop *vop) if (IS_ERR(vop->dclk_rst)) { dev_err(vop->dev, "failed to get dclk reset\n"); ret = PTR_ERR(vop->dclk_rst); - goto err_unprepare_aclk; + goto err_disable_aclk; } reset_control_assert(vop->dclk_rst); usleep_range(10, 20); reset_control_deassert(vop->dclk_rst); clk_disable(vop->hclk); + clk_disable(vop->aclk); vop->is_enabled = false; return 0; +err_disable_aclk: + clk_disable_unprepare(vop->aclk); err_disable_hclk: - clk_disable(vop->hclk); -err_unprepare_aclk: - clk_unprepare(vop->aclk); + clk_disable_unprepare(vop->hclk); err_unprepare_dclk: clk_unprepare(vop->dclk); -err_unprepare_hclk: - clk_unprepare(vop->hclk); return ret; } diff --git a/drivers/gpu/drm/ttm/ttm_lock.c b/drivers/gpu/drm/ttm/ttm_lock.c index 6a954544727f3..f154fb1929bd1 100644 --- a/drivers/gpu/drm/ttm/ttm_lock.c +++ b/drivers/gpu/drm/ttm/ttm_lock.c @@ -180,7 +180,7 @@ int ttm_write_lock(struct ttm_lock *lock, bool interruptible) spin_unlock(&lock->lock); } } else - wait_event(lock->queue, __ttm_read_lock(lock)); + wait_event(lock->queue, __ttm_write_lock(lock)); return ret; } diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index f545913a56c7a..578fe0a9324cd 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -412,7 +412,7 @@ static const struct drm_connector_funcs virtio_gpu_connector_funcs = { .save = virtio_gpu_conn_save, .restore = virtio_gpu_conn_restore, .detect = virtio_gpu_conn_detect, - .fill_modes = drm_helper_probe_single_connector_modes, + .fill_modes = drm_helper_probe_single_connector_modes_nomerge, .destroy = virtio_gpu_conn_destroy, .reset = drm_atomic_helper_connector_reset, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index a09cf8529b9f6..c49812b80dd0d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1233,6 +1233,7 @@ static void vmw_master_drop(struct drm_device *dev, vmw_fp->locked_master = drm_master_get(file_priv->master); ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile); + vmw_kms_legacy_hotspot_clear(dev_priv); if (unlikely((ret != 0))) { DRM_ERROR("Unable to lock TTM at VT switch.\n"); drm_master_put(&vmw_fp->locked_master); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index a8ae9dfb83b7d..469cdd520615d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -925,6 +925,7 @@ int vmw_kms_present(struct vmw_private *dev_priv, uint32_t num_clips); int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); +void vmw_kms_legacy_hotspot_clear(struct vmw_private *dev_priv); int vmw_dumb_create(struct drm_file *file_priv, struct drm_device *dev, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index a8baf5f5e7655..b6a0806b06bff 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -390,7 +390,7 @@ void *vmw_fifo_reserve_dx(struct vmw_private *dev_priv, uint32_t bytes, else if (ctx_id == SVGA3D_INVALID_ID) ret = vmw_local_fifo_reserve(dev_priv, bytes); else { - WARN_ON("Command buffer has not been allocated.\n"); + WARN(1, "Command buffer has not been allocated.\n"); ret = NULL; } if (IS_ERR_OR_NULL(ret)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 9fcd7f82995c3..9b4bb9e74d730 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -133,13 +133,19 @@ void vmw_cursor_update_position(struct vmw_private *dev_priv, vmw_mmio_write(++count, fifo_mem + SVGA_FIFO_CURSOR_COUNT); } -int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, - uint32_t handle, uint32_t width, uint32_t height) + +/* + * vmw_du_crtc_cursor_set2 - Driver cursor_set2 callback. + */ +int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv, + uint32_t handle, uint32_t width, uint32_t height, + int32_t hot_x, int32_t hot_y) { struct vmw_private *dev_priv = vmw_priv(crtc->dev); struct vmw_display_unit *du = vmw_crtc_to_du(crtc); struct vmw_surface *surface = NULL; struct vmw_dma_buffer *dmabuf = NULL; + s32 hotspot_x, hotspot_y; int ret; /* @@ -151,6 +157,8 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, */ drm_modeset_unlock_crtc(crtc); drm_modeset_lock_all(dev_priv->dev); + hotspot_x = hot_x + du->hotspot_x; + hotspot_y = hot_y + du->hotspot_y; /* A lot of the code assumes this */ if (handle && (width != 64 || height != 64)) { @@ -187,31 +195,34 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, vmw_dmabuf_unreference(&du->cursor_dmabuf); /* setup new image */ + ret = 0; if (surface) { /* vmw_user_surface_lookup takes one reference */ du->cursor_surface = surface; du->cursor_surface->snooper.crtc = crtc; du->cursor_age = du->cursor_surface->snooper.age; - vmw_cursor_update_image(dev_priv, surface->snooper.image, - 64, 64, du->hotspot_x, du->hotspot_y); + ret = vmw_cursor_update_image(dev_priv, surface->snooper.image, + 64, 64, hotspot_x, hotspot_y); } else if (dmabuf) { /* vmw_user_surface_lookup takes one reference */ du->cursor_dmabuf = dmabuf; ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, width, height, - du->hotspot_x, du->hotspot_y); + hotspot_x, hotspot_y); } else { vmw_cursor_update_position(dev_priv, false, 0, 0); - ret = 0; goto out; } - vmw_cursor_update_position(dev_priv, true, - du->cursor_x + du->hotspot_x, - du->cursor_y + du->hotspot_y); + if (!ret) { + vmw_cursor_update_position(dev_priv, true, + du->cursor_x + hotspot_x, + du->cursor_y + hotspot_y); + du->core_hotspot_x = hot_x; + du->core_hotspot_y = hot_y; + } - ret = 0; out: drm_modeset_unlock_all(dev_priv->dev); drm_modeset_lock_crtc(crtc, crtc->cursor); @@ -239,8 +250,10 @@ int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) drm_modeset_lock_all(dev_priv->dev); vmw_cursor_update_position(dev_priv, shown, - du->cursor_x + du->hotspot_x, - du->cursor_y + du->hotspot_y); + du->cursor_x + du->hotspot_x + + du->core_hotspot_x, + du->cursor_y + du->hotspot_y + + du->core_hotspot_y); drm_modeset_unlock_all(dev_priv->dev); drm_modeset_lock_crtc(crtc, crtc->cursor); @@ -334,6 +347,29 @@ err_unreserve: ttm_bo_unreserve(bo); } +/** + * vmw_kms_legacy_hotspot_clear - Clear legacy hotspots + * + * @dev_priv: Pointer to the device private struct. + * + * Clears all legacy hotspots. + */ +void vmw_kms_legacy_hotspot_clear(struct vmw_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct vmw_display_unit *du; + struct drm_crtc *crtc; + + drm_modeset_lock_all(dev); + drm_for_each_crtc(crtc, dev) { + du = vmw_crtc_to_du(crtc); + + du->hotspot_x = 0; + du->hotspot_y = 0; + } + drm_modeset_unlock_all(dev); +} + void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -351,7 +387,9 @@ void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv) du->cursor_age = du->cursor_surface->snooper.age; vmw_cursor_update_image(dev_priv, du->cursor_surface->snooper.image, - 64, 64, du->hotspot_x, du->hotspot_y); + 64, 64, + du->hotspot_x + du->core_hotspot_x, + du->hotspot_y + du->core_hotspot_y); } mutex_unlock(&dev->mode_config.mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index 782df7ca97946..edd81503516db 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -159,6 +159,8 @@ struct vmw_display_unit { int hotspot_x; int hotspot_y; + s32 core_hotspot_x; + s32 core_hotspot_y; unsigned unit; @@ -193,8 +195,9 @@ void vmw_du_crtc_restore(struct drm_crtc *crtc); void vmw_du_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b, uint32_t start, uint32_t size); -int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, - uint32_t handle, uint32_t width, uint32_t height); +int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv, + uint32_t handle, uint32_t width, uint32_t height, + int32_t hot_x, int32_t hot_y); int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y); int vmw_du_connector_dpms(struct drm_connector *connector, int mode); void vmw_du_connector_save(struct drm_connector *connector); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index bb63e4d795fae..52caecb4502ed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -297,7 +297,7 @@ static int vmw_ldu_crtc_set_config(struct drm_mode_set *set) static struct drm_crtc_funcs vmw_legacy_crtc_funcs = { .save = vmw_du_crtc_save, .restore = vmw_du_crtc_restore, - .cursor_set = vmw_du_crtc_cursor_set, + .cursor_set2 = vmw_du_crtc_cursor_set2, .cursor_move = vmw_du_crtc_cursor_move, .gamma_set = vmw_du_crtc_gamma_set, .destroy = vmw_ldu_crtc_destroy, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index b96d1ab610c55..13926ff192e3d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -533,7 +533,7 @@ out_no_fence: static struct drm_crtc_funcs vmw_screen_object_crtc_funcs = { .save = vmw_du_crtc_save, .restore = vmw_du_crtc_restore, - .cursor_set = vmw_du_crtc_cursor_set, + .cursor_set2 = vmw_du_crtc_cursor_set2, .cursor_move = vmw_du_crtc_cursor_move, .gamma_set = vmw_du_crtc_gamma_set, .destroy = vmw_sou_crtc_destroy, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index b1fc1c02792d4..f823fc3efed72 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -1043,7 +1043,7 @@ out_finish: static struct drm_crtc_funcs vmw_stdu_crtc_funcs = { .save = vmw_du_crtc_save, .restore = vmw_du_crtc_restore, - .cursor_set = vmw_du_crtc_cursor_set, + .cursor_set2 = vmw_du_crtc_cursor_set2, .cursor_move = vmw_du_crtc_cursor_move, .gamma_set = vmw_du_crtc_gamma_set, .destroy = vmw_stdu_crtc_destroy, diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index ba47b30d28fad..f2e13eb8339ff 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -28,6 +28,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/of_device.h> +#include <linux/of_graph.h> #include <drm/drm_fourcc.h> @@ -993,12 +994,26 @@ static void platform_device_unregister_children(struct platform_device *pdev) struct ipu_platform_reg { struct ipu_client_platformdata pdata; const char *name; - int reg_offset; }; +/* These must be in the order of the corresponding device tree port nodes */ static const struct ipu_platform_reg client_reg[] = { { .pdata = { + .csi = 0, + .dma[0] = IPUV3_CHANNEL_CSI0, + .dma[1] = -EINVAL, + }, + .name = "imx-ipuv3-camera", + }, { + .pdata = { + .csi = 1, + .dma[0] = IPUV3_CHANNEL_CSI1, + .dma[1] = -EINVAL, + }, + .name = "imx-ipuv3-camera", + }, { + .pdata = { .di = 0, .dc = 5, .dp = IPU_DP_FLOW_SYNC_BG, @@ -1015,22 +1030,6 @@ static const struct ipu_platform_reg client_reg[] = { .dma[1] = -EINVAL, }, .name = "imx-ipuv3-crtc", - }, { - .pdata = { - .csi = 0, - .dma[0] = IPUV3_CHANNEL_CSI0, - .dma[1] = -EINVAL, - }, - .reg_offset = IPU_CM_CSI0_REG_OFS, - .name = "imx-ipuv3-camera", - }, { - .pdata = { - .csi = 1, - .dma[0] = IPUV3_CHANNEL_CSI1, - .dma[1] = -EINVAL, - }, - .reg_offset = IPU_CM_CSI1_REG_OFS, - .name = "imx-ipuv3-camera", }, }; @@ -1051,22 +1050,30 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) for (i = 0; i < ARRAY_SIZE(client_reg); i++) { const struct ipu_platform_reg *reg = &client_reg[i]; struct platform_device *pdev; - struct resource res; - - if (reg->reg_offset) { - memset(&res, 0, sizeof(res)); - res.flags = IORESOURCE_MEM; - res.start = ipu_base + ipu->devtype->cm_ofs + reg->reg_offset; - res.end = res.start + PAGE_SIZE - 1; - pdev = platform_device_register_resndata(dev, reg->name, - id++, &res, 1, ®->pdata, sizeof(reg->pdata)); - } else { - pdev = platform_device_register_data(dev, reg->name, - id++, ®->pdata, sizeof(reg->pdata)); + + pdev = platform_device_alloc(reg->name, id++); + if (!pdev) { + ret = -ENOMEM; + goto err_register; + } + + pdev->dev.parent = dev; + + /* Associate subdevice with the corresponding port node */ + pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i); + if (!pdev->dev.of_node) { + dev_err(dev, "missing port@%d node in %s\n", i, + dev->of_node->full_name); + ret = -ENODEV; + goto err_register; } - if (IS_ERR(pdev)) { - ret = PTR_ERR(pdev); + ret = platform_device_add_data(pdev, ®->pdata, + sizeof(reg->pdata)); + if (!ret) + ret = platform_device_add(pdev); + if (ret) { + platform_device_put(pdev); goto err_register; } } diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c index 3166e4bc4eb6d..9abcaa53bd25a 100644 --- a/drivers/gpu/vga/vgaarb.c +++ b/drivers/gpu/vga/vgaarb.c @@ -395,8 +395,10 @@ int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible) set_current_state(interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); - if (signal_pending(current)) { - rc = -EINTR; + if (interruptible && signal_pending(current)) { + __set_current_state(TASK_RUNNING); + remove_wait_queue(&vga_wait_queue, &wait); + rc = -ERESTARTSYS; break; } schedule(); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 9024a3de40325..8b78a7f1f779f 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -316,11 +316,6 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 #define USB_VENDOR_ID_ELAN 0x04f3 -#define USB_DEVICE_ID_ELAN_TOUCHSCREEN 0x0089 -#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B 0x009b -#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_0103 0x0103 -#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_010c 0x010c -#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F 0x016f #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 2324520b006dc..7dd0953cd70f2 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -72,11 +72,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT }, - { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL }, - { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL }, - { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_0103, HID_QUIRK_ALWAYS_POLL }, - { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_010c, HID_QUIRK_ALWAYS_POLL }, - { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, @@ -340,7 +336,8 @@ static const struct hid_blacklist *usbhid_exists_squirk(const u16 idVendor, for (; hid_blacklist[n].idVendor; n++) if (hid_blacklist[n].idVendor == idVendor && - hid_blacklist[n].idProduct == idProduct) + (hid_blacklist[n].idProduct == (__u16) HID_ANY_ID || + hid_blacklist[n].idProduct == idProduct)) bl_entry = &hid_blacklist[n]; if (bl_entry != NULL) diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 8f59f057cdf4a..80a73bfc1a658 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1217,6 +1217,7 @@ config SENSORS_PWM_FAN config SENSORS_SHT15 tristate "Sensiron humidity and temperature sensors. SHT15 and compat." depends on GPIOLIB || COMPILE_TEST + select BITREVERSE help If you say yes here you get support for the Sensiron SHT10, SHT11, SHT15, SHT71, SHT75 humidity and temperature sensors. diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c index 65482624ea2c8..5289aa0980a8f 100644 --- a/drivers/hwmon/tmp102.c +++ b/drivers/hwmon/tmp102.c @@ -58,6 +58,7 @@ struct tmp102 { u16 config_orig; unsigned long last_update; int temp[3]; + bool first_time; }; /* convert left adjusted 13-bit TMP102 register value to milliCelsius */ @@ -93,6 +94,7 @@ static struct tmp102 *tmp102_update_device(struct device *dev) tmp102->temp[i] = tmp102_reg_to_mC(status); } tmp102->last_update = jiffies; + tmp102->first_time = false; } mutex_unlock(&tmp102->lock); return tmp102; @@ -102,6 +104,12 @@ static int tmp102_read_temp(void *dev, int *temp) { struct tmp102 *tmp102 = tmp102_update_device(dev); + /* Is it too early even to return a conversion? */ + if (tmp102->first_time) { + dev_dbg(dev, "%s: Conversion not ready yet..\n", __func__); + return -EAGAIN; + } + *temp = tmp102->temp[0]; return 0; @@ -114,6 +122,10 @@ static ssize_t tmp102_show_temp(struct device *dev, struct sensor_device_attribute *sda = to_sensor_dev_attr(attr); struct tmp102 *tmp102 = tmp102_update_device(dev); + /* Is it too early even to return a read? */ + if (tmp102->first_time) + return -EAGAIN; + return sprintf(buf, "%d\n", tmp102->temp[sda->index]); } @@ -207,7 +219,9 @@ static int tmp102_probe(struct i2c_client *client, status = -ENODEV; goto fail_restore_config; } - tmp102->last_update = jiffies - HZ; + tmp102->last_update = jiffies; + /* Mark that we are not ready with data until conversion is complete */ + tmp102->first_time = true; mutex_init(&tmp102->lock); hwmon_dev = hwmon_device_register_with_groups(dev, client->name, diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index c5628a42170ac..a8bdcb5292f5b 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -202,8 +202,15 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) * d is always 6 on Keystone I2C controller */ - /* get minimum of 7 MHz clock, but max of 12 MHz */ - psc = (input_clock / 7000000) - 1; + /* + * Both Davinci and current Keystone User Guides recommend a value + * between 7MHz and 12MHz. In reality 7MHz module clock doesn't + * always produce enough margin between SDA and SCL transitions. + * Measurements show that the higher the module clock is, the + * bigger is the margin, providing more reliable communication. + * So we better target for 12MHz. + */ + psc = (input_clock / 12000000) - 1; if ((input_clock / (psc + 1)) > 12000000) psc++; /* better to run under spec than over */ d = (psc >= 2) ? 5 : 7 - psc; diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index 8c48b27ba0597..de7fbbb374cd3 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -813,6 +813,12 @@ static irqreturn_t i2c_dw_isr(int this_irq, void *dev_id) tx_aborted: if ((stat & (DW_IC_INTR_TX_ABRT | DW_IC_INTR_STOP_DET)) || dev->msg_err) complete(&dev->cmd_complete); + else if (unlikely(dev->accessor_flags & ACCESS_INTR_MASK)) { + /* workaround to trigger pending interrupt */ + stat = dw_readl(dev, DW_IC_INTR_MASK); + i2c_dw_disable_int(dev); + dw_writel(dev, stat, DW_IC_INTR_MASK); + } return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 1d50898e7b240..9ffb63a60f954 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -111,6 +111,7 @@ struct dw_i2c_dev { #define ACCESS_SWAP 0x00000001 #define ACCESS_16BIT 0x00000002 +#define ACCESS_INTR_MASK 0x00000004 extern int i2c_dw_init(struct dw_i2c_dev *dev); extern void i2c_dw_disable(struct dw_i2c_dev *dev); diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 809579ecb5a44..6b00061c37469 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -93,6 +93,7 @@ static void dw_i2c_acpi_params(struct platform_device *pdev, char method[], static int dw_i2c_acpi_configure(struct platform_device *pdev) { struct dw_i2c_dev *dev = platform_get_drvdata(pdev); + const struct acpi_device_id *id; dev->adapter.nr = -1; dev->tx_fifo_depth = 32; @@ -106,6 +107,10 @@ static int dw_i2c_acpi_configure(struct platform_device *pdev) dw_i2c_acpi_params(pdev, "FMCN", &dev->fs_hcnt, &dev->fs_lcnt, &dev->sda_hold_time); + id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev); + if (id && id->driver_data) + dev->accessor_flags |= (u32)id->driver_data; + return 0; } @@ -116,7 +121,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = { { "INT3433", 0 }, { "80860F41", 0 }, { "808622C1", 0 }, - { "AMD0010", 0 }, + { "AMD0010", ACCESS_INTR_MASK }, { } }; MODULE_DEVICE_TABLE(acpi, dw_i2c_acpi_match); @@ -240,12 +245,10 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) } r = i2c_dw_probe(dev); - if (r) { + if (r && !dev->pm_runtime_disabled) pm_runtime_disable(&pdev->dev); - return r; - } - return 0; + return r; } static int dw_i2c_plat_remove(struct platform_device *pdev) @@ -260,7 +263,8 @@ static int dw_i2c_plat_remove(struct platform_device *pdev) pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); + if (!dev->pm_runtime_disabled) + pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 9bb0b056b25f2..d4d853680ae47 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1119,6 +1119,8 @@ static int i2c_imx_probe(struct platform_device *pdev) i2c_imx, IMX_I2C_I2CR); imx_i2c_write_reg(i2c_imx->hwdata->i2sr_clr_opcode, i2c_imx, IMX_I2C_I2SR); + i2c_imx_init_recovery_info(i2c_imx, pdev); + /* Add I2C adapter */ ret = i2c_add_numbered_adapter(&i2c_imx->adapter); if (ret < 0) { @@ -1126,8 +1128,6 @@ static int i2c_imx_probe(struct platform_device *pdev) goto clk_disable; } - i2c_imx_init_recovery_info(i2c_imx, pdev); - /* Set up platform driver data */ platform_set_drvdata(pdev, i2c_imx); clk_disable_unprepare(i2c_imx->clk); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index 5801227b97ab0..43207f52e5a37 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -146,6 +146,8 @@ struct mv64xxx_i2c_data { bool errata_delay; struct reset_control *rstc; bool irq_clear_inverted; + /* Clk div is 2 to the power n, not 2 to the power n + 1 */ + bool clk_n_base_0; }; static struct mv64xxx_i2c_regs mv64xxx_i2c_regs_mv64xxx = { @@ -757,25 +759,29 @@ MODULE_DEVICE_TABLE(of, mv64xxx_i2c_of_match_table); #ifdef CONFIG_OF #ifdef CONFIG_HAVE_CLK static int -mv64xxx_calc_freq(const int tclk, const int n, const int m) +mv64xxx_calc_freq(struct mv64xxx_i2c_data *drv_data, + const int tclk, const int n, const int m) { - return tclk / (10 * (m + 1) * (2 << n)); + if (drv_data->clk_n_base_0) + return tclk / (10 * (m + 1) * (1 << n)); + else + return tclk / (10 * (m + 1) * (2 << n)); } static bool -mv64xxx_find_baud_factors(const u32 req_freq, const u32 tclk, u32 *best_n, - u32 *best_m) +mv64xxx_find_baud_factors(struct mv64xxx_i2c_data *drv_data, + const u32 req_freq, const u32 tclk) { int freq, delta, best_delta = INT_MAX; int m, n; for (n = 0; n <= 7; n++) for (m = 0; m <= 15; m++) { - freq = mv64xxx_calc_freq(tclk, n, m); + freq = mv64xxx_calc_freq(drv_data, tclk, n, m); delta = req_freq - freq; if (delta >= 0 && delta < best_delta) { - *best_m = m; - *best_n = n; + drv_data->freq_m = m; + drv_data->freq_n = n; best_delta = delta; } if (best_delta == 0) @@ -813,8 +819,11 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, if (of_property_read_u32(np, "clock-frequency", &bus_freq)) bus_freq = 100000; /* 100kHz by default */ - if (!mv64xxx_find_baud_factors(bus_freq, tclk, - &drv_data->freq_n, &drv_data->freq_m)) { + if (of_device_is_compatible(np, "allwinner,sun4i-a10-i2c") || + of_device_is_compatible(np, "allwinner,sun6i-a31-i2c")) + drv_data->clk_n_base_0 = true; + + if (!mv64xxx_find_baud_factors(drv_data, bus_freq, tclk)) { rc = -EINVAL; goto out; } diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index b0ae560b38c30..599c0d7bd906d 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -576,7 +576,7 @@ static int rcar_reg_slave(struct i2c_client *slave) if (slave->flags & I2C_CLIENT_TEN) return -EAFNOSUPPORT; - pm_runtime_forbid(rcar_i2c_priv_to_dev(priv)); + pm_runtime_get_sync(rcar_i2c_priv_to_dev(priv)); priv->slave = slave; rcar_i2c_write(priv, ICSAR, slave->addr); @@ -598,7 +598,7 @@ static int rcar_unreg_slave(struct i2c_client *slave) priv->slave = NULL; - pm_runtime_allow(rcar_i2c_priv_to_dev(priv)); + pm_runtime_put(rcar_i2c_priv_to_dev(priv)); return 0; } diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index c1935ebd6a9c3..9096d17beb5bb 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -908,7 +908,7 @@ static int rk3x_i2c_probe(struct platform_device *pdev) &i2c->scl_fall_ns)) i2c->scl_fall_ns = 300; if (of_property_read_u32(pdev->dev.of_node, "i2c-sda-falling-time-ns", - &i2c->scl_fall_ns)) + &i2c->sda_fall_ns)) i2c->sda_fall_ns = i2c->scl_fall_ns; strlcpy(i2c->adap.name, "rk3x-i2c", sizeof(i2c->adap.name)); diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c index ea72dca32fdfd..25020ec777c97 100644 --- a/drivers/i2c/busses/i2c-st.c +++ b/drivers/i2c/busses/i2c-st.c @@ -822,7 +822,7 @@ static int st_i2c_probe(struct platform_device *pdev) adap = &i2c_dev->adap; i2c_set_adapdata(adap, i2c_dev); - snprintf(adap->name, sizeof(adap->name), "ST I2C(0x%pa)", &res->start); + snprintf(adap->name, sizeof(adap->name), "ST I2C(%pa)", &res->start); adap->owner = THIS_MODULE; adap->timeout = 2 * HZ; adap->retries = 0; diff --git a/drivers/iio/adc/qcom-spmi-vadc.c b/drivers/iio/adc/qcom-spmi-vadc.c index 0c4618b4d5154..c2babe50a0d8f 100644 --- a/drivers/iio/adc/qcom-spmi-vadc.c +++ b/drivers/iio/adc/qcom-spmi-vadc.c @@ -839,8 +839,10 @@ static int vadc_get_dt_data(struct vadc_priv *vadc, struct device_node *node) for_each_available_child_of_node(node, child) { ret = vadc_get_dt_channel_data(vadc->dev, &prop, child); - if (ret) + if (ret) { + of_node_put(child); return ret; + } vadc->chan_props[index] = prop; diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index d7e908acb4802..0f6f63b202637 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -302,7 +302,7 @@ static int iio_scan_mask_set(struct iio_dev *indio_dev, if (trialmask == NULL) return -ENOMEM; if (!indio_dev->masklength) { - WARN_ON("Trying to set scanmask prior to registering buffer\n"); + WARN(1, "Trying to set scanmask prior to registering buffer\n"); goto err_invalid_mask; } bitmap_copy(trialmask, buffer->scan_mask, indio_dev->masklength); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 208358f9e7e36..159ede61f7931 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -655,7 +655,7 @@ int __iio_device_attr_init(struct device_attribute *dev_attr, break; case IIO_SEPARATE: if (!chan->indexed) { - WARN_ON("Differential channels must be indexed\n"); + WARN(1, "Differential channels must be indexed\n"); ret = -EINVAL; goto error_free_full_postfix; } diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c index 7d269ef9e0625..f6a07dc32ae48 100644 --- a/drivers/iio/light/apds9960.c +++ b/drivers/iio/light/apds9960.c @@ -453,6 +453,7 @@ static int apds9960_set_power_state(struct apds9960_data *data, bool on) usleep_range(data->als_adc_int_us, APDS9960_MAX_INT_TIME_IN_US); } else { + pm_runtime_mark_last_busy(dev); ret = pm_runtime_put_autosuspend(dev); } diff --git a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c index 961f9f990faff..e544fcfd5cedf 100644 --- a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c +++ b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c @@ -130,10 +130,10 @@ static int lidar_get_measurement(struct lidar_data *data, u16 *reg) if (ret < 0) break; - /* return 0 since laser is likely pointed out of range */ + /* return -EINVAL since laser is likely pointed out of range */ if (ret & LIDAR_REG_STATUS_INVALID) { *reg = 0; - ret = 0; + ret = -EINVAL; break; } @@ -197,7 +197,7 @@ static irqreturn_t lidar_trigger_handler(int irq, void *private) if (!ret) { iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, iio_get_time_ns()); - } else { + } else if (ret != -EINVAL) { dev_err(&data->client->dev, "cannot read LIDAR measurement"); } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 944cd90417bcc..2d762a2ecd812 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1126,10 +1126,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev, rcu_read_lock(); err = fib_lookup(dev_net(net_dev), &fl4, &res, 0); - if (err) - return false; - - ret = FIB_RES_DEV(res) == net_dev; + ret = err == 0 && FIB_RES_DEV(res) == net_dev; rcu_read_unlock(); return ret; @@ -1268,15 +1265,17 @@ static bool cma_protocol_roce(const struct rdma_cm_id *id) return cma_protocol_roce_dev_port(device, port_num); } -static bool cma_match_net_dev(const struct rdma_id_private *id_priv, - const struct net_device *net_dev) +static bool cma_match_net_dev(const struct rdma_cm_id *id, + const struct net_device *net_dev, + u8 port_num) { - const struct rdma_addr *addr = &id_priv->id.route.addr; + const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request or a RoCE request */ - return addr->src_addr.ss_family == AF_IB || - cma_protocol_roce(&id_priv->id); + return (!id->port_num || id->port_num == port_num) && + (addr->src_addr.ss_family == AF_IB || + cma_protocol_roce_dev_port(id->device, port_num)); return !addr->dev_addr.bound_dev_if || (net_eq(dev_net(net_dev), addr->dev_addr.net) && @@ -1298,13 +1297,13 @@ static struct rdma_id_private *cma_find_listener( hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && - cma_match_net_dev(id_priv, net_dev)) + cma_match_net_dev(&id_priv->id, net_dev, req->port)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_list) { if (id_priv_dev->id.device == cm_id->device && - cma_match_net_dev(id_priv_dev, net_dev)) + cma_match_net_dev(&id_priv_dev->id, net_dev, req->port)) return id_priv_dev; } } diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 8d8af7a41a30f..2281de122038e 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -1811,6 +1811,11 @@ static int validate_mad(const struct ib_mad_hdr *mad_hdr, if (qp_num == 0) valid = 1; } else { + /* CM attributes other than ClassPortInfo only use Send method */ + if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_CM) && + (mad_hdr->attr_id != IB_MGMT_CLASSPORTINFO_ATTR_ID) && + (mad_hdr->method != IB_MGMT_METHOD_SEND)) + goto out; /* Filter GSI packets sent to QP0 */ if (qp_num != 0) valid = 1; diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 2aba774f835b9..a95a32ba596ed 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -512,7 +512,7 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask) return len; } -static int ib_nl_send_msg(struct ib_sa_query *query) +static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask) { struct sk_buff *skb = NULL; struct nlmsghdr *nlh; @@ -526,7 +526,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query) if (len <= 0) return -EMSGSIZE; - skb = nlmsg_new(len, GFP_KERNEL); + skb = nlmsg_new(len, gfp_mask); if (!skb) return -ENOMEM; @@ -544,7 +544,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query) /* Repair the nlmsg header length */ nlmsg_end(skb, nlh); - ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL); + ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask); if (!ret) ret = len; else @@ -553,7 +553,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query) return ret; } -static int ib_nl_make_request(struct ib_sa_query *query) +static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask) { unsigned long flags; unsigned long delay; @@ -562,25 +562,27 @@ static int ib_nl_make_request(struct ib_sa_query *query) INIT_LIST_HEAD(&query->list); query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq); + /* Put the request on the list first.*/ spin_lock_irqsave(&ib_nl_request_lock, flags); - ret = ib_nl_send_msg(query); - if (ret <= 0) { - ret = -EIO; - goto request_out; - } else { - ret = 0; - } - delay = msecs_to_jiffies(sa_local_svc_timeout_ms); query->timeout = delay + jiffies; list_add_tail(&query->list, &ib_nl_request_list); /* Start the timeout if this is the only request */ if (ib_nl_request_list.next == &query->list) queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay); - -request_out: spin_unlock_irqrestore(&ib_nl_request_lock, flags); + ret = ib_nl_send_msg(query, gfp_mask); + if (ret <= 0) { + ret = -EIO; + /* Remove the request */ + spin_lock_irqsave(&ib_nl_request_lock, flags); + list_del(&query->list); + spin_unlock_irqrestore(&ib_nl_request_lock, flags); + } else { + ret = 0; + } + return ret; } @@ -1108,7 +1110,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask) if (query->flags & IB_SA_ENABLE_LOCAL_SERVICE) { if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) { - if (!ib_nl_make_request(query)) + if (!ib_nl_make_request(query, gfp_mask)) return id; } ib_sa_disable_local_svc(query); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 94816aeb95a0a..1c02deab068fb 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -62,9 +62,11 @@ static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" }; * The ib_uobject locking scheme is as follows: * * - ib_uverbs_idr_lock protects the uverbs idrs themselves, so it - * needs to be held during all idr operations. When an object is + * needs to be held during all idr write operations. When an object is * looked up, a reference must be taken on the object's kref before - * dropping this lock. + * dropping this lock. For read operations, the rcu_read_lock() + * and rcu_write_lock() but similarly the kref reference is grabbed + * before the rcu_read_unlock(). * * - Each object also has an rwsem. This rwsem must be held for * reading while an operation that uses the object is performed. @@ -96,7 +98,7 @@ static void init_uobj(struct ib_uobject *uobj, u64 user_handle, static void release_uobj(struct kref *kref) { - kfree(container_of(kref, struct ib_uobject, ref)); + kfree_rcu(container_of(kref, struct ib_uobject, ref), rcu); } static void put_uobj(struct ib_uobject *uobj) @@ -145,7 +147,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id, { struct ib_uobject *uobj; - spin_lock(&ib_uverbs_idr_lock); + rcu_read_lock(); uobj = idr_find(idr, id); if (uobj) { if (uobj->context == context) @@ -153,7 +155,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id, else uobj = NULL; } - spin_unlock(&ib_uverbs_idr_lock); + rcu_read_unlock(); return uobj; } @@ -2446,6 +2448,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, int i, sg_ind; int is_ud; ssize_t ret = -EINVAL; + size_t next_size; if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; @@ -2490,7 +2493,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, goto out_put; } - ud = alloc_wr(sizeof(*ud), user_wr->num_sge); + next_size = sizeof(*ud); + ud = alloc_wr(next_size, user_wr->num_sge); if (!ud) { ret = -ENOMEM; goto out_put; @@ -2511,7 +2515,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, user_wr->opcode == IB_WR_RDMA_READ) { struct ib_rdma_wr *rdma; - rdma = alloc_wr(sizeof(*rdma), user_wr->num_sge); + next_size = sizeof(*rdma); + rdma = alloc_wr(next_size, user_wr->num_sge); if (!rdma) { ret = -ENOMEM; goto out_put; @@ -2525,7 +2530,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, user_wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) { struct ib_atomic_wr *atomic; - atomic = alloc_wr(sizeof(*atomic), user_wr->num_sge); + next_size = sizeof(*atomic); + atomic = alloc_wr(next_size, user_wr->num_sge); if (!atomic) { ret = -ENOMEM; goto out_put; @@ -2540,7 +2546,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, } else if (user_wr->opcode == IB_WR_SEND || user_wr->opcode == IB_WR_SEND_WITH_IMM || user_wr->opcode == IB_WR_SEND_WITH_INV) { - next = alloc_wr(sizeof(*next), user_wr->num_sge); + next_size = sizeof(*next); + next = alloc_wr(next_size, user_wr->num_sge); if (!next) { ret = -ENOMEM; goto out_put; @@ -2572,7 +2579,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, if (next->num_sge) { next->sg_list = (void *) next + - ALIGN(sizeof *next, sizeof (struct ib_sge)); + ALIGN(next_size, sizeof(struct ib_sge)); if (copy_from_user(next->sg_list, buf + sizeof cmd + cmd.wr_count * cmd.wqe_size + diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 043a60ee6836d..545906dec26dc 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1516,7 +1516,7 @@ EXPORT_SYMBOL(ib_map_mr_sg); * @sg_nents: number of entries in sg * @set_page: driver page assignment function pointer * - * Core service helper for drivers to covert the largest + * Core service helper for drivers to convert the largest * prefix of given sg list to a page vector. The sg list * prefix converted is the prefix that meet the requirements * of ib_map_mr_sg. @@ -1533,7 +1533,7 @@ int ib_sg_to_pages(struct ib_mr *mr, u64 last_end_dma_addr = 0, last_page_addr = 0; unsigned int last_page_off = 0; u64 page_mask = ~((u64)mr->page_size - 1); - int i; + int i, ret; mr->iova = sg_dma_address(&sgl[0]); mr->length = 0; @@ -1544,27 +1544,29 @@ int ib_sg_to_pages(struct ib_mr *mr, u64 end_dma_addr = dma_addr + dma_len; u64 page_addr = dma_addr & page_mask; - if (i && page_addr != dma_addr) { - if (last_end_dma_addr != dma_addr) { - /* gap */ - goto done; - - } else if (last_page_off + dma_len <= mr->page_size) { - /* chunk this fragment with the last */ - mr->length += dma_len; - last_end_dma_addr += dma_len; - last_page_off += dma_len; - continue; - } else { - /* map starting from the next page */ - page_addr = last_page_addr + mr->page_size; - dma_len -= mr->page_size - last_page_off; - } + /* + * For the second and later elements, check whether either the + * end of element i-1 or the start of element i is not aligned + * on a page boundary. + */ + if (i && (last_page_off != 0 || page_addr != dma_addr)) { + /* Stop mapping if there is a gap. */ + if (last_end_dma_addr != dma_addr) + break; + + /* + * Coalesce this element with the last. If it is small + * enough just update mr->length. Otherwise start + * mapping from the next page. + */ + goto next_page; } do { - if (unlikely(set_page(mr, page_addr))) - goto done; + ret = set_page(mr, page_addr); + if (unlikely(ret < 0)) + return i ? : ret; +next_page: page_addr += mr->page_size; } while (page_addr < end_dma_addr); @@ -1574,7 +1576,6 @@ int ib_sg_to_pages(struct ib_mr *mr, last_page_off = end_dma_addr & ~page_mask; } -done: return i; } EXPORT_SYMBOL(ib_sg_to_pages); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index f567160a4a56e..97d6878f99382 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -456,7 +456,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; props->max_sge = min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); - props->max_sge_rd = props->max_sge; + props->max_sge_rd = MLX4_MAX_SGE_RD; props->max_cq = dev->dev->quotas.cq; props->max_cqe = dev->dev->caps.max_cqes; props->max_mr = dev->dev->quotas.mpt; diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index a2e4ca56da44e..13eaaf45288f8 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -34,6 +34,7 @@ #include <linux/log2.h> #include <linux/slab.h> #include <linux/netdevice.h> +#include <linux/vmalloc.h> #include <rdma/ib_cache.h> #include <rdma/ib_pack.h> @@ -795,8 +796,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (err) goto err_mtt; - qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof (u64), gfp); - qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof (u64), gfp); + qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof(u64), gfp); + if (!qp->sq.wrid) + qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64), + gfp, PAGE_KERNEL); + qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof(u64), gfp); + if (!qp->rq.wrid) + qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64), + gfp, PAGE_KERNEL); if (!qp->sq.wrid || !qp->rq.wrid) { err = -ENOMEM; goto err_wrid; @@ -886,8 +893,8 @@ err_wrid: if (qp_has_rq(init_attr)) mlx4_ib_db_unmap_user(to_mucontext(pd->uobject->context), &qp->db); } else { - kfree(qp->sq.wrid); - kfree(qp->rq.wrid); + kvfree(qp->sq.wrid); + kvfree(qp->rq.wrid); } err_mtt: @@ -1062,8 +1069,8 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, &qp->db); ib_umem_release(qp->umem); } else { - kfree(qp->sq.wrid); - kfree(qp->rq.wrid); + kvfree(qp->sq.wrid); + kvfree(qp->rq.wrid); if (qp->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) free_proxy_bufs(&dev->ib_dev, qp); diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c index dce5dfe3a70ea..c394376ebe06f 100644 --- a/drivers/infiniband/hw/mlx4/srq.c +++ b/drivers/infiniband/hw/mlx4/srq.c @@ -34,6 +34,7 @@ #include <linux/mlx4/qp.h> #include <linux/mlx4/srq.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include "mlx4_ib.h" #include "user.h" @@ -172,8 +173,12 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd, srq->wrid = kmalloc(srq->msrq.max * sizeof (u64), GFP_KERNEL); if (!srq->wrid) { - err = -ENOMEM; - goto err_mtt; + srq->wrid = __vmalloc(srq->msrq.max * sizeof(u64), + GFP_KERNEL, PAGE_KERNEL); + if (!srq->wrid) { + err = -ENOMEM; + goto err_mtt; + } } } @@ -204,7 +209,7 @@ err_wrid: if (pd->uobject) mlx4_ib_db_unmap_user(to_mucontext(pd->uobject->context), &srq->db); else - kfree(srq->wrid); + kvfree(srq->wrid); err_mtt: mlx4_mtt_cleanup(dev->dev, &srq->mtt); @@ -281,7 +286,7 @@ int mlx4_ib_destroy_srq(struct ib_srq *srq) mlx4_ib_db_unmap_user(to_mucontext(srq->uobject->context), &msrq->db); ib_umem_release(msrq->umem); } else { - kfree(msrq->wrid); + kvfree(msrq->wrid); mlx4_buf_free(dev->dev, msrq->msrq.max << msrq->msrq.wqe_shift, &msrq->buf); mlx4_db_free(dev->dev, &msrq->db); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index ec8993a7b3bee..6000f7aeede94 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -381,7 +381,19 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) } } } else if (ent->cur > 2 * ent->limit) { - if (!someone_adding(cache) && + /* + * The remove_keys() logic is performed as garbage collection + * task. Such task is intended to be run when no other active + * processes are running. + * + * The need_resched() will return TRUE if there are user tasks + * to be activated in near future. + * + * In such case, we don't execute remove_keys() and postpone + * the garbage collection work to try to run in next cycle, + * in order to free CPU resources to other tasks. + */ + if (!need_resched() && !someone_adding(cache) && time_after(jiffies, cache->last_add + 300 * HZ)) { remove_keys(dev, i, 1); if (ent->cur > ent->limit) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h index ae80590aabdf7..040bb8b5cb15a 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma.h @@ -232,6 +232,10 @@ struct phy_info { u16 interface_type; }; +enum ocrdma_flags { + OCRDMA_FLAGS_LINK_STATUS_INIT = 0x01 +}; + struct ocrdma_dev { struct ib_device ibdev; struct ocrdma_dev_attr attr; @@ -287,6 +291,7 @@ struct ocrdma_dev { atomic_t update_sl; u16 pvid; u32 asic_id; + u32 flags; ulong last_stats_time; struct mutex stats_lock; /* provide synch for debugfs operations */ @@ -591,4 +596,9 @@ static inline u8 ocrdma_is_enabled_and_synced(u32 state) (state & OCRDMA_STATE_FLAG_SYNC); } +static inline u8 ocrdma_get_ae_link_state(u32 ae_state) +{ + return ((ae_state & OCRDMA_AE_LSC_LS_MASK) >> OCRDMA_AE_LSC_LS_SHIFT); +} + #endif diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 30f67bebffa35..283ca842ff749 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -579,6 +579,8 @@ static int ocrdma_mbx_create_mq(struct ocrdma_dev *dev, cmd->async_event_bitmap = BIT(OCRDMA_ASYNC_GRP5_EVE_CODE); cmd->async_event_bitmap |= BIT(OCRDMA_ASYNC_RDMA_EVE_CODE); + /* Request link events on this MQ. */ + cmd->async_event_bitmap |= BIT(OCRDMA_ASYNC_LINK_EVE_CODE); cmd->async_cqid_ringsize = cq->id; cmd->async_cqid_ringsize |= (ocrdma_encoded_q_len(mq->len) << @@ -819,20 +821,42 @@ static void ocrdma_process_grp5_aync(struct ocrdma_dev *dev, } } +static void ocrdma_process_link_state(struct ocrdma_dev *dev, + struct ocrdma_ae_mcqe *cqe) +{ + struct ocrdma_ae_lnkst_mcqe *evt; + u8 lstate; + + evt = (struct ocrdma_ae_lnkst_mcqe *)cqe; + lstate = ocrdma_get_ae_link_state(evt->speed_state_ptn); + + if (!(lstate & OCRDMA_AE_LSC_LLINK_MASK)) + return; + + if (dev->flags & OCRDMA_FLAGS_LINK_STATUS_INIT) + ocrdma_update_link_state(dev, (lstate & OCRDMA_LINK_ST_MASK)); +} + static void ocrdma_process_acqe(struct ocrdma_dev *dev, void *ae_cqe) { /* async CQE processing */ struct ocrdma_ae_mcqe *cqe = ae_cqe; u32 evt_code = (cqe->valid_ae_event & OCRDMA_AE_MCQE_EVENT_CODE_MASK) >> OCRDMA_AE_MCQE_EVENT_CODE_SHIFT; - - if (evt_code == OCRDMA_ASYNC_RDMA_EVE_CODE) + switch (evt_code) { + case OCRDMA_ASYNC_LINK_EVE_CODE: + ocrdma_process_link_state(dev, cqe); + break; + case OCRDMA_ASYNC_RDMA_EVE_CODE: ocrdma_dispatch_ibevent(dev, cqe); - else if (evt_code == OCRDMA_ASYNC_GRP5_EVE_CODE) + break; + case OCRDMA_ASYNC_GRP5_EVE_CODE: ocrdma_process_grp5_aync(dev, cqe); - else + break; + default: pr_err("%s(%d) invalid evt code=0x%x\n", __func__, dev->id, evt_code); + } } static void ocrdma_process_mcqe(struct ocrdma_dev *dev, struct ocrdma_mcqe *cqe) @@ -1363,7 +1387,8 @@ mbx_err: return status; } -int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed) +int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed, + u8 *lnk_state) { int status = -ENOMEM; struct ocrdma_get_link_speed_rsp *rsp; @@ -1384,8 +1409,11 @@ int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed) goto mbx_err; rsp = (struct ocrdma_get_link_speed_rsp *)cmd; - *lnk_speed = (rsp->pflt_pps_ld_pnum & OCRDMA_PHY_PS_MASK) - >> OCRDMA_PHY_PS_SHIFT; + if (lnk_speed) + *lnk_speed = (rsp->pflt_pps_ld_pnum & OCRDMA_PHY_PS_MASK) + >> OCRDMA_PHY_PS_SHIFT; + if (lnk_state) + *lnk_state = (rsp->res_lnk_st & OCRDMA_LINK_ST_MASK); mbx_err: kfree(cmd); @@ -2515,9 +2543,10 @@ static int ocrdma_set_av_params(struct ocrdma_qp *qp, ocrdma_cpu_to_le32(&cmd->params.sgid[0], sizeof(cmd->params.sgid)); cmd->params.vlan_dmac_b4_to_b5 = mac_addr[4] | (mac_addr[5] << 8); - if (vlan_id < 0x1000) { - if (dev->pfc_state) { - vlan_id = 0; + if (vlan_id == 0xFFFF) + vlan_id = 0; + if (vlan_id || dev->pfc_state) { + if (!vlan_id) { pr_err("ocrdma%d:Using VLAN with PFC is recommended\n", dev->id); pr_err("ocrdma%d:Using VLAN 0 for this connection\n", diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h index 7ed885c1851e2..ebc1f442aec37 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h @@ -106,7 +106,8 @@ void ocrdma_ring_cq_db(struct ocrdma_dev *, u16 cq_id, bool armed, bool solicited, u16 cqe_popped); /* verbs specific mailbox commands */ -int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed); +int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed, + u8 *lnk_st); int ocrdma_query_config(struct ocrdma_dev *, struct ocrdma_mbx_query_config *config); @@ -153,5 +154,6 @@ char *port_speed_string(struct ocrdma_dev *dev); void ocrdma_init_service_level(struct ocrdma_dev *); void ocrdma_alloc_pd_pool(struct ocrdma_dev *dev); void ocrdma_free_pd_range(struct ocrdma_dev *dev); +void ocrdma_update_link_state(struct ocrdma_dev *dev, u8 lstate); #endif /* __OCRDMA_HW_H__ */ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 62b7009daa6c1..3afb40b85159b 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -290,6 +290,7 @@ static void ocrdma_remove_sysfiles(struct ocrdma_dev *dev) static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info) { int status = 0, i; + u8 lstate = 0; struct ocrdma_dev *dev; dev = (struct ocrdma_dev *)ib_alloc_device(sizeof(struct ocrdma_dev)); @@ -319,6 +320,11 @@ static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info) if (status) goto alloc_err; + /* Query Link state and update */ + status = ocrdma_mbx_get_link_speed(dev, NULL, &lstate); + if (!status) + ocrdma_update_link_state(dev, lstate); + for (i = 0; i < ARRAY_SIZE(ocrdma_attributes); i++) if (device_create_file(&dev->ibdev.dev, ocrdma_attributes[i])) goto sysfs_err; @@ -373,7 +379,7 @@ static void ocrdma_remove(struct ocrdma_dev *dev) ocrdma_remove_free(dev); } -static int ocrdma_open(struct ocrdma_dev *dev) +static int ocrdma_dispatch_port_active(struct ocrdma_dev *dev) { struct ib_event port_event; @@ -384,32 +390,9 @@ static int ocrdma_open(struct ocrdma_dev *dev) return 0; } -static int ocrdma_close(struct ocrdma_dev *dev) +static int ocrdma_dispatch_port_error(struct ocrdma_dev *dev) { - int i; - struct ocrdma_qp *qp, **cur_qp; struct ib_event err_event; - struct ib_qp_attr attrs; - int attr_mask = IB_QP_STATE; - - attrs.qp_state = IB_QPS_ERR; - mutex_lock(&dev->dev_lock); - if (dev->qp_tbl) { - cur_qp = dev->qp_tbl; - for (i = 0; i < OCRDMA_MAX_QP; i++) { - qp = cur_qp[i]; - if (qp && qp->ibqp.qp_type != IB_QPT_GSI) { - /* change the QP state to ERROR */ - _ocrdma_modify_qp(&qp->ibqp, &attrs, attr_mask); - - err_event.event = IB_EVENT_QP_FATAL; - err_event.element.qp = &qp->ibqp; - err_event.device = &dev->ibdev; - ib_dispatch_event(&err_event); - } - } - } - mutex_unlock(&dev->dev_lock); err_event.event = IB_EVENT_PORT_ERR; err_event.element.port_num = 1; @@ -420,7 +403,7 @@ static int ocrdma_close(struct ocrdma_dev *dev) static void ocrdma_shutdown(struct ocrdma_dev *dev) { - ocrdma_close(dev); + ocrdma_dispatch_port_error(dev); ocrdma_remove(dev); } @@ -431,18 +414,28 @@ static void ocrdma_shutdown(struct ocrdma_dev *dev) static void ocrdma_event_handler(struct ocrdma_dev *dev, u32 event) { switch (event) { - case BE_DEV_UP: - ocrdma_open(dev); - break; - case BE_DEV_DOWN: - ocrdma_close(dev); - break; case BE_DEV_SHUTDOWN: ocrdma_shutdown(dev); break; + default: + break; } } +void ocrdma_update_link_state(struct ocrdma_dev *dev, u8 lstate) +{ + if (!(dev->flags & OCRDMA_FLAGS_LINK_STATUS_INIT)) { + dev->flags |= OCRDMA_FLAGS_LINK_STATUS_INIT; + if (!lstate) + return; + } + + if (!lstate) + ocrdma_dispatch_port_error(dev); + else + ocrdma_dispatch_port_active(dev); +} + static struct ocrdma_driver ocrdma_drv = { .name = "ocrdma_driver", .add = ocrdma_add, diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 6a38268bbe9fb..99dd6fdf06d7b 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -465,8 +465,11 @@ struct ocrdma_ae_qp_mcqe { u32 valid_ae_event; }; -#define OCRDMA_ASYNC_RDMA_EVE_CODE 0x14 -#define OCRDMA_ASYNC_GRP5_EVE_CODE 0x5 +enum ocrdma_async_event_code { + OCRDMA_ASYNC_LINK_EVE_CODE = 0x01, + OCRDMA_ASYNC_GRP5_EVE_CODE = 0x05, + OCRDMA_ASYNC_RDMA_EVE_CODE = 0x14 +}; enum ocrdma_async_grp5_events { OCRDMA_ASYNC_EVENT_QOS_VALUE = 0x01, @@ -489,6 +492,44 @@ enum OCRDMA_ASYNC_EVENT_TYPE { OCRDMA_MAX_ASYNC_ERRORS }; +struct ocrdma_ae_lnkst_mcqe { + u32 speed_state_ptn; + u32 qos_reason_falut; + u32 evt_tag; + u32 valid_ae_event; +}; + +enum { + OCRDMA_AE_LSC_PORT_NUM_MASK = 0x3F, + OCRDMA_AE_LSC_PT_SHIFT = 0x06, + OCRDMA_AE_LSC_PT_MASK = (0x03 << + OCRDMA_AE_LSC_PT_SHIFT), + OCRDMA_AE_LSC_LS_SHIFT = 0x08, + OCRDMA_AE_LSC_LS_MASK = (0xFF << + OCRDMA_AE_LSC_LS_SHIFT), + OCRDMA_AE_LSC_LD_SHIFT = 0x10, + OCRDMA_AE_LSC_LD_MASK = (0xFF << + OCRDMA_AE_LSC_LD_SHIFT), + OCRDMA_AE_LSC_PPS_SHIFT = 0x18, + OCRDMA_AE_LSC_PPS_MASK = (0xFF << + OCRDMA_AE_LSC_PPS_SHIFT), + OCRDMA_AE_LSC_PPF_MASK = 0xFF, + OCRDMA_AE_LSC_ER_SHIFT = 0x08, + OCRDMA_AE_LSC_ER_MASK = (0xFF << + OCRDMA_AE_LSC_ER_SHIFT), + OCRDMA_AE_LSC_QOS_SHIFT = 0x10, + OCRDMA_AE_LSC_QOS_MASK = (0xFFFF << + OCRDMA_AE_LSC_QOS_SHIFT) +}; + +enum { + OCRDMA_AE_LSC_PLINK_DOWN = 0x00, + OCRDMA_AE_LSC_PLINK_UP = 0x01, + OCRDMA_AE_LSC_LLINK_DOWN = 0x02, + OCRDMA_AE_LSC_LLINK_MASK = 0x02, + OCRDMA_AE_LSC_LLINK_UP = 0x03 +}; + /* mailbox command request and responses */ enum { OCRDMA_MBX_QUERY_CFG_CQ_OVERFLOW_SHIFT = 2, @@ -676,7 +717,7 @@ enum { OCRDMA_PHY_PFLT_SHIFT = 0x18, OCRDMA_QOS_LNKSP_MASK = 0xFFFF0000, OCRDMA_QOS_LNKSP_SHIFT = 0x10, - OCRDMA_LLST_MASK = 0xFF, + OCRDMA_LINK_ST_MASK = 0x01, OCRDMA_PLFC_MASK = 0x00000400, OCRDMA_PLFC_SHIFT = 0x8, OCRDMA_PLRFC_MASK = 0x00000200, @@ -691,7 +732,7 @@ struct ocrdma_get_link_speed_rsp { u32 pflt_pps_ld_pnum; u32 qos_lsp; - u32 res_lls; + u32 res_lnk_st; }; enum { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 583001bcfb8fc..76e96f97b3f64 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -171,7 +171,7 @@ static inline void get_link_speed_and_width(struct ocrdma_dev *dev, int status; u8 speed; - status = ocrdma_mbx_get_link_speed(dev, &speed); + status = ocrdma_mbx_get_link_speed(dev, &speed, NULL); if (status) speed = OCRDMA_PHYS_LINK_SPEED_ZERO; diff --git a/drivers/infiniband/hw/qib/qib_qsfp.c b/drivers/infiniband/hw/qib/qib_qsfp.c index 5e27f76805e28..4c7c3c84a7417 100644 --- a/drivers/infiniband/hw/qib/qib_qsfp.c +++ b/drivers/infiniband/hw/qib/qib_qsfp.c @@ -292,7 +292,7 @@ int qib_refresh_qsfp_cache(struct qib_pportdata *ppd, struct qib_qsfp_cache *cp) qib_dev_porterr(ppd->dd, ppd->port, "QSFP byte0 is 0x%02X, S/B 0x0C/D\n", peek[0]); - if ((peek[2] & 2) == 0) { + if ((peek[2] & 4) == 0) { /* * If cable is paged, rather than "flat memory", we need to * set the page to zero, Even if it already appears to be zero. @@ -538,7 +538,7 @@ int qib_qsfp_dump(struct qib_pportdata *ppd, char *buf, int len) sofar += scnprintf(buf + sofar, len - sofar, "Date:%.*s\n", QSFP_DATE_LEN, cd.date); sofar += scnprintf(buf + sofar, len - sofar, "Lot:%.*s\n", - QSFP_LOT_LEN, cd.date); + QSFP_LOT_LEN, cd.lot); while (bidx < QSFP_DEFAULT_HDR_CNT) { int iidx; diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h index 2baf5ad251ed2..bc803f33d5f68 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.h +++ b/drivers/infiniband/hw/qib/qib_verbs.h @@ -329,9 +329,9 @@ struct qib_sge { struct qib_mr { struct ib_mr ibmr; struct ib_umem *umem; - struct qib_mregion mr; /* must be last */ u64 *pages; u32 npages; + struct qib_mregion mr; /* must be last */ }; /* diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index a930702101096..42f4da620f2e9 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -1293,7 +1293,7 @@ u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task, if (mr_status.fail_status & IB_MR_CHECK_SIG_STATUS) { sector_t sector_off = mr_status.sig_err.sig_err_offset; - do_div(sector_off, sector_size + 8); + sector_div(sector_off, sector_size + 8); *sector = scsi_get_lba(iser_task->sc) + sector_off; pr_err("PI error found type %d at sector %llx " diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index dfbbbb28090b2..8a51c3b5d657e 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -157,16 +157,9 @@ isert_create_qp(struct isert_conn *isert_conn, attr.recv_cq = comp->cq; attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS; attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS + 1; - /* - * FIXME: Use devattr.max_sge - 2 for max_send_sge as - * work-around for RDMA_READs with ConnectX-2. - * - * Also, still make sure to have at least two SGEs for - * outgoing control PDU responses. - */ - attr.cap.max_send_sge = max(2, device->dev_attr.max_sge - 2); - isert_conn->max_sge = attr.cap.max_send_sge; - + attr.cap.max_send_sge = device->dev_attr.max_sge; + isert_conn->max_sge = min(device->dev_attr.max_sge, + device->dev_attr.max_sge_rd); attr.cap.max_recv_sge = 1; attr.sq_sig_type = IB_SIGNAL_REQ_WR; attr.qp_type = IB_QPT_RC; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 9909022dc6c3e..3db9a659719b0 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -488,7 +488,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch) struct ib_qp *qp; struct ib_fmr_pool *fmr_pool = NULL; struct srp_fr_pool *fr_pool = NULL; - const int m = 1 + dev->use_fast_reg; + const int m = dev->use_fast_reg ? 3 : 1; struct ib_cq_init_attr cq_attr = {}; int ret; @@ -994,16 +994,16 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich) ret = srp_lookup_path(ch); if (ret) - return ret; + goto out; while (1) { init_completion(&ch->done); ret = srp_send_req(ch, multich); if (ret) - return ret; + goto out; ret = wait_for_completion_interruptible(&ch->done); if (ret < 0) - return ret; + goto out; /* * The CM event handling code will set status to @@ -1011,15 +1011,16 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich) * back, or SRP_DLID_REDIRECT if we get a lid/qp * redirect REJ back. */ - switch (ch->status) { + ret = ch->status; + switch (ret) { case 0: ch->connected = true; - return 0; + goto out; case SRP_PORT_REDIRECT: ret = srp_lookup_path(ch); if (ret) - return ret; + goto out; break; case SRP_DLID_REDIRECT: @@ -1028,13 +1029,16 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich) case SRP_STALE_CONN: shost_printk(KERN_ERR, target->scsi_host, PFX "giving up on stale connection\n"); - ch->status = -ECONNRESET; - return ch->status; + ret = -ECONNRESET; + goto out; default: - return ch->status; + goto out; } } + +out: + return ret <= 0 ? ret : -ENODEV; } static int srp_inv_rkey(struct srp_rdma_ch *ch, u32 rkey) @@ -1309,7 +1313,7 @@ reset_state: } static int srp_map_finish_fr(struct srp_map_state *state, - struct srp_rdma_ch *ch) + struct srp_rdma_ch *ch, int sg_nents) { struct srp_target_port *target = ch->target; struct srp_device *dev = target->srp_host->srp_dev; @@ -1324,10 +1328,10 @@ static int srp_map_finish_fr(struct srp_map_state *state, WARN_ON_ONCE(!dev->use_fast_reg); - if (state->sg_nents == 0) + if (sg_nents == 0) return 0; - if (state->sg_nents == 1 && target->global_mr) { + if (sg_nents == 1 && target->global_mr) { srp_map_desc(state, sg_dma_address(state->sg), sg_dma_len(state->sg), target->global_mr->rkey); @@ -1341,8 +1345,7 @@ static int srp_map_finish_fr(struct srp_map_state *state, rkey = ib_inc_rkey(desc->mr->rkey); ib_update_fast_reg_key(desc->mr, rkey); - n = ib_map_mr_sg(desc->mr, state->sg, state->sg_nents, - dev->mr_page_size); + n = ib_map_mr_sg(desc->mr, state->sg, sg_nents, dev->mr_page_size); if (unlikely(n < 0)) return n; @@ -1448,16 +1451,15 @@ static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch, state->fr.next = req->fr_list; state->fr.end = req->fr_list + ch->target->cmd_sg_cnt; state->sg = scat; - state->sg_nents = scsi_sg_count(req->scmnd); - while (state->sg_nents) { + while (count) { int i, n; - n = srp_map_finish_fr(state, ch); + n = srp_map_finish_fr(state, ch, count); if (unlikely(n < 0)) return n; - state->sg_nents -= n; + count -= n; for (i = 0; i < n; i++) state->sg = sg_next(state->sg); } @@ -1517,10 +1519,12 @@ static int srp_map_idb(struct srp_rdma_ch *ch, struct srp_request *req, if (dev->use_fast_reg) { state.sg = idb_sg; - state.sg_nents = 1; sg_set_buf(idb_sg, req->indirect_desc, idb_len); idb_sg->dma_address = req->indirect_dma_addr; /* hack! */ - ret = srp_map_finish_fr(&state, ch); +#ifdef CONFIG_NEED_SG_DMA_LENGTH + idb_sg->dma_length = idb_sg->length; /* hack^2 */ +#endif + ret = srp_map_finish_fr(&state, ch, 1); if (ret < 0) return ret; } else if (dev->use_fmr) { @@ -1655,7 +1659,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, return ret; req->nmdesc++; } else { - idb_rkey = target->global_mr->rkey; + idb_rkey = cpu_to_be32(target->global_mr->rkey); } indirect_hdr->table_desc.va = cpu_to_be64(req->indirect_dma_addr); diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index 87a2a919dc438..f6af531f9f32c 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -300,10 +300,7 @@ struct srp_map_state { dma_addr_t base_dma_addr; u32 dma_len; u32 total_len; - union { - unsigned int npages; - int sg_nents; - }; + unsigned int npages; unsigned int nmdesc; unsigned int ndesc; }; diff --git a/drivers/input/joystick/db9.c b/drivers/input/joystick/db9.c index 932d07307454b..da326090c2b0e 100644 --- a/drivers/input/joystick/db9.c +++ b/drivers/input/joystick/db9.c @@ -592,6 +592,7 @@ static void db9_attach(struct parport *pp) return; } + memset(&db9_parport_cb, 0, sizeof(db9_parport_cb)); db9_parport_cb.flags = PARPORT_FLAG_EXCL; pd = parport_register_dev_model(pp, "db9", &db9_parport_cb, port_idx); diff --git a/drivers/input/joystick/gamecon.c b/drivers/input/joystick/gamecon.c index 5a672dcac0d81..eae14d512353a 100644 --- a/drivers/input/joystick/gamecon.c +++ b/drivers/input/joystick/gamecon.c @@ -951,6 +951,7 @@ static void gc_attach(struct parport *pp) pads = gc_cfg[port_idx].args + 1; n_pads = gc_cfg[port_idx].nargs - 1; + memset(&gc_parport_cb, 0, sizeof(gc_parport_cb)); gc_parport_cb.flags = PARPORT_FLAG_EXCL; pd = parport_register_dev_model(pp, "gamecon", &gc_parport_cb, diff --git a/drivers/input/joystick/turbografx.c b/drivers/input/joystick/turbografx.c index 9f5bca26bd2fb..77f575dd0901f 100644 --- a/drivers/input/joystick/turbografx.c +++ b/drivers/input/joystick/turbografx.c @@ -181,6 +181,7 @@ static void tgfx_attach(struct parport *pp) n_buttons = tgfx_cfg[port_idx].args + 1; n_devs = tgfx_cfg[port_idx].nargs - 1; + memset(&tgfx_parport_cb, 0, sizeof(tgfx_parport_cb)); tgfx_parport_cb.flags = PARPORT_FLAG_EXCL; pd = parport_register_dev_model(pp, "turbografx", &tgfx_parport_cb, diff --git a/drivers/input/joystick/walkera0701.c b/drivers/input/joystick/walkera0701.c index 9c07fe911075f..70a893a174676 100644 --- a/drivers/input/joystick/walkera0701.c +++ b/drivers/input/joystick/walkera0701.c @@ -218,6 +218,7 @@ static void walkera0701_attach(struct parport *pp) w->parport = pp; + memset(&walkera0701_parport_cb, 0, sizeof(walkera0701_parport_cb)); walkera0701_parport_cb.flags = PARPORT_FLAG_EXCL; walkera0701_parport_cb.irq_func = walkera0701_irq_handler; walkera0701_parport_cb.private = w; diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c index 4bf678541496e..d5994a745ffa5 100644 --- a/drivers/input/misc/arizona-haptics.c +++ b/drivers/input/misc/arizona-haptics.c @@ -97,8 +97,7 @@ static void arizona_haptics_work(struct work_struct *work) ret = regmap_update_bits(arizona->regmap, ARIZONA_HAPTICS_CONTROL_1, - ARIZONA_HAP_CTRL_MASK, - 1 << ARIZONA_HAP_CTRL_SHIFT); + ARIZONA_HAP_CTRL_MASK, 0); if (ret != 0) { dev_err(arizona->dev, "Failed to stop haptics: %d\n", ret); diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 5e1665bbaa0ba..2f589857a0395 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -41,6 +41,7 @@ #define DRIVER_NAME "elan_i2c" #define ELAN_DRIVER_VERSION "1.6.1" +#define ELAN_VENDOR_ID 0x04f3 #define ETP_MAX_PRESSURE 255 #define ETP_FWIDTH_REDUCE 90 #define ETP_FINGER_WIDTH 15 @@ -914,6 +915,8 @@ static int elan_setup_input_device(struct elan_tp_data *data) input->name = "Elan Touchpad"; input->id.bustype = BUS_I2C; + input->id.vendor = ELAN_VENDOR_ID; + input->id.product = data->product_id; input_set_drvdata(input, data); error = input_mt_init_slots(input, ETP_MAX_FINGERS, diff --git a/drivers/input/serio/parkbd.c b/drivers/input/serio/parkbd.c index 92c31b8f8fb48..1edfac78d4ac7 100644 --- a/drivers/input/serio/parkbd.c +++ b/drivers/input/serio/parkbd.c @@ -145,6 +145,7 @@ static int parkbd_getport(struct parport *pp) { struct pardev_cb parkbd_parport_cb; + memset(&parkbd_parport_cb, 0, sizeof(parkbd_parport_cb)); parkbd_parport_cb.irq_func = parkbd_interrupt; parkbd_parport_cb.flags = PARPORT_FLAG_EXCL; diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c index e7f966da6efa3..78ca44840d60c 100644 --- a/drivers/input/tablet/aiptek.c +++ b/drivers/input/tablet/aiptek.c @@ -1819,6 +1819,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) input_set_abs_params(inputdev, ABS_TILT_Y, AIPTEK_TILT_MIN, AIPTEK_TILT_MAX, 0, 0); input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0); + /* Verify that a device really has an endpoint */ + if (intf->altsetting[0].desc.bNumEndpoints < 1) { + dev_err(&intf->dev, + "interface has %d endpoints, but must have minimum 1\n", + intf->altsetting[0].desc.bNumEndpoints); + err = -EINVAL; + goto fail3; + } endpoint = &intf->altsetting[0].endpoint[0].desc; /* Go set up our URB, which is called when the tablet receives @@ -1861,6 +1869,7 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) if (i == ARRAY_SIZE(speeds)) { dev_info(&intf->dev, "Aiptek tried all speeds, no sane response\n"); + err = -EINVAL; goto fail3; } diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index c5622058c22bb..2d5794ec338b7 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -2487,6 +2487,31 @@ static struct mxt_acpi_platform_data samus_platform_data[] = { { } }; +static unsigned int chromebook_tp_buttons[] = { + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + BTN_LEFT +}; + +static struct mxt_acpi_platform_data chromebook_platform_data[] = { + { + /* Touchpad */ + .hid = "ATML0000", + .pdata = { + .t19_num_keys = ARRAY_SIZE(chromebook_tp_buttons), + .t19_keymap = chromebook_tp_buttons, + }, + }, + { + /* Touchscreen */ + .hid = "ATML0001", + }, + { } +}; + static const struct dmi_system_id mxt_dmi_table[] = { { /* 2015 Google Pixel */ @@ -2497,6 +2522,14 @@ static const struct dmi_system_id mxt_dmi_table[] = { }, .driver_data = samus_platform_data, }, + { + /* Other Google Chromebooks */ + .ident = "Chromebook", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), + }, + .driver_data = chromebook_platform_data, + }, { } }; @@ -2701,6 +2734,7 @@ static const struct i2c_device_id mxt_id[] = { { "qt602240_ts", 0 }, { "atmel_mxt_ts", 0 }, { "atmel_mxt_tp", 0 }, + { "maxtouch", 0 }, { "mXT224", 0 }, { } }; diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 17cc20ef4923b..ac09855fa435d 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -1316,7 +1316,13 @@ static int __maybe_unused elants_i2c_suspend(struct device *dev) disable_irq(client->irq); - if (device_may_wakeup(dev) || ts->keep_power_in_suspend) { + if (device_may_wakeup(dev)) { + /* + * The device will automatically enter idle mode + * that has reduced power consumption. + */ + ts->wake_irq_enabled = (enable_irq_wake(client->irq) == 0); + } else if (ts->keep_power_in_suspend) { for (retry_cnt = 0; retry_cnt < MAX_RETRIES; retry_cnt++) { error = elants_i2c_send(client, set_sleep_cmd, sizeof(set_sleep_cmd)); @@ -1326,10 +1332,6 @@ static int __maybe_unused elants_i2c_suspend(struct device *dev) dev_err(&client->dev, "suspend command failed: %d\n", error); } - - if (device_may_wakeup(dev)) - ts->wake_irq_enabled = - (enable_irq_wake(client->irq) == 0); } else { elants_i2c_power_off(ts); } @@ -1345,10 +1347,11 @@ static int __maybe_unused elants_i2c_resume(struct device *dev) int retry_cnt; int error; - if (device_may_wakeup(dev) && ts->wake_irq_enabled) - disable_irq_wake(client->irq); - - if (ts->keep_power_in_suspend) { + if (device_may_wakeup(dev)) { + if (ts->wake_irq_enabled) + disable_irq_wake(client->irq); + elants_i2c_sw_reset(client); + } else if (ts->keep_power_in_suspend) { for (retry_cnt = 0; retry_cnt < MAX_RETRIES; retry_cnt++) { error = elants_i2c_send(client, set_active_cmd, sizeof(set_active_cmd)); diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index d21d4edf7236a..7caf2fa237f22 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -494,6 +494,22 @@ static void handle_fault_error(struct fault *fault) } } +static bool access_error(struct vm_area_struct *vma, struct fault *fault) +{ + unsigned long requested = 0; + + if (fault->flags & PPR_FAULT_EXEC) + requested |= VM_EXEC; + + if (fault->flags & PPR_FAULT_READ) + requested |= VM_READ; + + if (fault->flags & PPR_FAULT_WRITE) + requested |= VM_WRITE; + + return (requested & ~vma->vm_flags) != 0; +} + static void do_fault(struct work_struct *work) { struct fault *fault = container_of(work, struct fault, work); @@ -516,8 +532,8 @@ static void do_fault(struct work_struct *work) goto out; } - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) { - /* handle_mm_fault would BUG_ON() */ + /* Check if we have the right permissions on the vma */ + if (access_error(vma, fault)) { up_read(&mm->mmap_sem); handle_fault_error(fault); goto out; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index f1042daef9ada..ac7387686ddc7 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2159,7 +2159,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, sg_res = aligned_nrpages(sg->offset, sg->length); sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset; sg->dma_length = sg->length; - pteval = (sg_phys(sg) & PAGE_MASK) | prot; + pteval = page_to_phys(sg_page(sg)) | prot; phys_pfn = pteval >> VTD_PAGE_SHIFT; } @@ -3704,7 +3704,7 @@ static int intel_nontranslate_map_sg(struct device *hddev, for_each_sg(sglist, sg, nelems, i) { BUG_ON(!sg_page(sg)); - sg->dma_address = sg_phys(sg); + sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset; sg->dma_length = sg->length; } return nelems; diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index c69e3f9ec9586..50464833d0b84 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -484,6 +484,23 @@ struct page_req_dsc { }; #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x10) + +static bool access_error(struct vm_area_struct *vma, struct page_req_dsc *req) +{ + unsigned long requested = 0; + + if (req->exe_req) + requested |= VM_EXEC; + + if (req->rd_req) + requested |= VM_READ; + + if (req->wr_req) + requested |= VM_WRITE; + + return (requested & ~vma->vm_flags) != 0; +} + static irqreturn_t prq_event_thread(int irq, void *d) { struct intel_iommu *iommu = d; @@ -539,6 +556,9 @@ static irqreturn_t prq_event_thread(int irq, void *d) if (!vma || address < vma->vm_start) goto invalid; + if (access_error(vma, req)) + goto invalid; + ret = handle_mm_fault(svm->mm, vma, address, req->wr_req ? FAULT_FLAG_WRITE : 0); if (ret & VM_FAULT_ERROR) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index abae363c7b9bd..0e3b0092ec92c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1430,7 +1430,7 @@ size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); for_each_sg(sg, s, nents, i) { - phys_addr_t phys = sg_phys(s); + phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset; /* * We are mapping on IOMMU page boundaries, so offset within diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c index 598ab3f0e0ac5..cadf104e30746 100644 --- a/drivers/irqchip/irq-versatile-fpga.c +++ b/drivers/irqchip/irq-versatile-fpga.c @@ -210,7 +210,12 @@ int __init fpga_irq_of_init(struct device_node *node, parent_irq = -1; } +#ifdef CONFIG_ARCH_VERSATILE + fpga_irq_init(base, node->name, IRQ_SIC_START, parent_irq, valid_mask, + node); +#else fpga_irq_init(base, node->name, 0, parent_irq, valid_mask, node); +#endif writel(clear_mask, base + IRQ_ENABLE_CLEAR); writel(clear_mask, base + FIQ_ENABLE_CLEAR); diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index 375be509e95f5..2a506fe0c8a45 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -67,8 +67,7 @@ static int write_modem(struct cardstate *cs) struct sk_buff *skb = bcs->tx_skb; int sent = -EOPNOTSUPP; - if (!tty || !tty->driver || !skb) - return -EINVAL; + WARN_ON(!tty || !tty->ops || !skb); if (!skb->len) { dev_kfree_skb_any(skb); @@ -109,8 +108,7 @@ static int send_cb(struct cardstate *cs) unsigned long flags; int sent = 0; - if (!tty || !tty->driver) - return -EFAULT; + WARN_ON(!tty || !tty->ops); cb = cs->cmdbuf; if (!cb) @@ -370,19 +368,18 @@ static void gigaset_freecshw(struct cardstate *cs) tasklet_kill(&cs->write_tasklet); if (!cs->hw.ser) return; - dev_set_drvdata(&cs->hw.ser->dev.dev, NULL); platform_device_unregister(&cs->hw.ser->dev); - kfree(cs->hw.ser); - cs->hw.ser = NULL; } static void gigaset_device_release(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); + struct cardstate *cs = dev_get_drvdata(dev); - /* adapted from platform_device_release() in drivers/base/platform.c */ - kfree(dev->platform_data); - kfree(pdev->resource); + if (!cs) + return; + dev_set_drvdata(dev, NULL); + kfree(cs->hw.ser); + cs->hw.ser = NULL; } /* @@ -432,7 +429,9 @@ static int gigaset_set_modem_ctrl(struct cardstate *cs, unsigned old_state, struct tty_struct *tty = cs->hw.ser->tty; unsigned int set, clear; - if (!tty || !tty->driver || !tty->ops->tiocmset) + WARN_ON(!tty || !tty->ops); + /* tiocmset is an optional tty driver method */ + if (!tty->ops->tiocmset) return -EINVAL; set = new_state & ~old_state; clear = old_state & ~new_state; diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c index a77eea594b695..cb428b9ee441b 100644 --- a/drivers/isdn/hardware/mISDN/mISDNipac.c +++ b/drivers/isdn/hardware/mISDN/mISDNipac.c @@ -1170,7 +1170,7 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) if (ipac->type & IPAC_TYPE_IPACX) { ista = ReadIPAC(ipac, ISACX_ISTA); - while (ista && cnt--) { + while (ista && --cnt) { pr_debug("%s: ISTA %02x\n", ipac->name, ista); if (ista & IPACX__ICA) ipac_irq(&ipac->hscx[0], ista); @@ -1182,7 +1182,7 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) } } else if (ipac->type & IPAC_TYPE_IPAC) { ista = ReadIPAC(ipac, IPAC_ISTA); - while (ista && cnt--) { + while (ista && --cnt) { pr_debug("%s: ISTA %02x\n", ipac->name, ista); if (ista & (IPAC__ICD | IPAC__EXD)) { istad = ReadISAC(isac, ISAC_ISTA); @@ -1200,7 +1200,7 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) ista = ReadIPAC(ipac, IPAC_ISTA); } } else if (ipac->type & IPAC_TYPE_HSCX) { - while (cnt) { + while (--cnt) { ista = ReadIPAC(ipac, IPAC_ISTAB + ipac->hscx[1].off); pr_debug("%s: B2 ISTA %02x\n", ipac->name, ista); if (ista) @@ -1211,7 +1211,6 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) mISDNisac_irq(isac, istad); if (0 == (ista | istad)) break; - cnt--; } } if (cnt > maxloop) /* only for ISAC/HSCX without PCI IRQ test */ diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig index a16bf56d3f283..85a339030e4b8 100644 --- a/drivers/lightnvm/Kconfig +++ b/drivers/lightnvm/Kconfig @@ -18,6 +18,7 @@ if NVM config NVM_DEBUG bool "Open-Channel SSD debugging support" + default n ---help--- Exposes a debug management interface to create/remove targets at: diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 86ce887b2ed6a..8f41b245cd55b 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -74,7 +74,7 @@ EXPORT_SYMBOL(nvm_unregister_target); void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags, dma_addr_t *dma_handler) { - return dev->ops->dev_dma_alloc(dev->q, dev->ppalist_pool, mem_flags, + return dev->ops->dev_dma_alloc(dev, dev->ppalist_pool, mem_flags, dma_handler); } EXPORT_SYMBOL(nvm_dev_dma_alloc); @@ -97,15 +97,47 @@ static struct nvmm_type *nvm_find_mgr_type(const char *name) return NULL; } +struct nvmm_type *nvm_init_mgr(struct nvm_dev *dev) +{ + struct nvmm_type *mt; + int ret; + + lockdep_assert_held(&nvm_lock); + + list_for_each_entry(mt, &nvm_mgrs, list) { + ret = mt->register_mgr(dev); + if (ret < 0) { + pr_err("nvm: media mgr failed to init (%d) on dev %s\n", + ret, dev->name); + return NULL; /* initialization failed */ + } else if (ret > 0) + return mt; + } + + return NULL; +} + int nvm_register_mgr(struct nvmm_type *mt) { + struct nvm_dev *dev; int ret = 0; down_write(&nvm_lock); - if (nvm_find_mgr_type(mt->name)) + if (nvm_find_mgr_type(mt->name)) { ret = -EEXIST; - else + goto finish; + } else { list_add(&mt->list, &nvm_mgrs); + } + + /* try to register media mgr if any device have none configured */ + list_for_each_entry(dev, &nvm_devices, devices) { + if (dev->mt) + continue; + + dev->mt = nvm_init_mgr(dev); + } +finish: up_write(&nvm_lock); return ret; @@ -123,26 +155,6 @@ void nvm_unregister_mgr(struct nvmm_type *mt) } EXPORT_SYMBOL(nvm_unregister_mgr); -/* register with device with a supported manager */ -static int register_mgr(struct nvm_dev *dev) -{ - struct nvmm_type *mt; - int ret = 0; - - list_for_each_entry(mt, &nvm_mgrs, list) { - ret = mt->register_mgr(dev); - if (ret > 0) { - dev->mt = mt; - break; /* successfully initialized */ - } - } - - if (!ret) - pr_info("nvm: no compatible nvm manager found.\n"); - - return ret; -} - static struct nvm_dev *nvm_find_nvm_dev(const char *name) { struct nvm_dev *dev; @@ -246,7 +258,7 @@ static int nvm_init(struct nvm_dev *dev) if (!dev->q || !dev->ops) return ret; - if (dev->ops->identity(dev->q, &dev->identity)) { + if (dev->ops->identity(dev, &dev->identity)) { pr_err("nvm: device could not be identified\n"); goto err; } @@ -271,14 +283,6 @@ static int nvm_init(struct nvm_dev *dev) goto err; } - down_write(&nvm_lock); - ret = register_mgr(dev); - up_write(&nvm_lock); - if (ret < 0) - goto err; - if (!ret) - return 0; - pr_info("nvm: registered %s [%u/%u/%u/%u/%u/%u]\n", dev->name, dev->sec_per_pg, dev->nr_planes, dev->pgs_per_blk, dev->blks_per_lun, dev->nr_luns, @@ -326,8 +330,7 @@ int nvm_register(struct request_queue *q, char *disk_name, } if (dev->ops->max_phys_sect > 1) { - dev->ppalist_pool = dev->ops->create_dma_pool(dev->q, - "ppalist"); + dev->ppalist_pool = dev->ops->create_dma_pool(dev, "ppalist"); if (!dev->ppalist_pool) { pr_err("nvm: could not create ppa pool\n"); ret = -ENOMEM; @@ -335,7 +338,9 @@ int nvm_register(struct request_queue *q, char *disk_name, } } + /* register device with a supported media manager */ down_write(&nvm_lock); + dev->mt = nvm_init_mgr(dev); list_add(&dev->devices, &nvm_devices); up_write(&nvm_lock); @@ -380,19 +385,13 @@ static int nvm_create_target(struct nvm_dev *dev, struct nvm_tgt_type *tt; struct nvm_target *t; void *targetdata; - int ret = 0; - down_write(&nvm_lock); if (!dev->mt) { - ret = register_mgr(dev); - if (!ret) - ret = -ENODEV; - if (ret < 0) { - up_write(&nvm_lock); - return ret; - } + pr_info("nvm: device has no media manager registered.\n"); + return -ENODEV; } + down_write(&nvm_lock); tt = nvm_find_target_type(create->tgttype); if (!tt) { pr_err("nvm: target type %s not found\n", create->tgttype); diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c index 35dde84b71e97..a54b339951a3e 100644 --- a/drivers/lightnvm/gennvm.c +++ b/drivers/lightnvm/gennvm.c @@ -75,7 +75,7 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks, struct nvm_block *blk; int i; - lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun]; + lun = &gn->luns[(dev->luns_per_chnl * ppa.g.ch) + ppa.g.lun]; for (i = 0; i < nr_blocks; i++) { if (blks[i] == 0) @@ -195,7 +195,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn) } if (dev->ops->get_l2p_tbl) { - ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages, + ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages, gennvm_block_map, dev); if (ret) { pr_err("gennvm: could not read L2P table.\n"); @@ -219,6 +219,9 @@ static int gennvm_register(struct nvm_dev *dev) struct gen_nvm *gn; int ret; + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + gn = kzalloc(sizeof(struct gen_nvm), GFP_KERNEL); if (!gn) return -ENOMEM; @@ -242,12 +245,14 @@ static int gennvm_register(struct nvm_dev *dev) return 1; err: gennvm_free(dev); + module_put(THIS_MODULE); return ret; } static void gennvm_unregister(struct nvm_dev *dev) { gennvm_free(dev); + module_put(THIS_MODULE); } static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev, @@ -262,14 +267,11 @@ static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev, if (list_empty(&lun->free_list)) { pr_err_ratelimited("gennvm: lun %u have no free pages available", lun->vlun.id); - spin_unlock(&vlun->lock); goto out; } - while (!is_gc && lun->vlun.nr_free_blocks < lun->reserved_blocks) { - spin_unlock(&vlun->lock); + if (!is_gc && lun->vlun.nr_free_blocks < lun->reserved_blocks) goto out; - } blk = list_first_entry(&lun->free_list, struct nvm_block, list); list_move_tail(&blk->list, &lun->used_list); @@ -278,8 +280,8 @@ static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev, lun->vlun.nr_free_blocks--; lun->vlun.nr_inuse_blocks++; - spin_unlock(&vlun->lock); out: + spin_unlock(&vlun->lock); return blk; } @@ -349,7 +351,7 @@ static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) gennvm_generic_to_addr_mode(dev, rqd); rqd->dev = dev; - return dev->ops->submit_io(dev->q, rqd); + return dev->ops->submit_io(dev, rqd); } static void gennvm_blk_set_type(struct nvm_dev *dev, struct ppa_addr *ppa, @@ -385,7 +387,7 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd) if (!dev->ops->set_bb_tbl) return; - if (dev->ops->set_bb_tbl(dev->q, rqd, 1)) + if (dev->ops->set_bb_tbl(dev, rqd, 1)) return; gennvm_addr_to_generic_mode(dev, rqd); @@ -453,7 +455,7 @@ static int gennvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk, gennvm_generic_to_addr_mode(dev, &rqd); - ret = dev->ops->erase_block(dev->q, &rqd); + ret = dev->ops->erase_block(dev, &rqd); if (plane_cnt) nvm_dev_dma_free(dev, rqd.ppa_list, rqd.dma_ppa_list); diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c index 75e59c3a3f96d..134e4faba4825 100644 --- a/drivers/lightnvm/rrpc.c +++ b/drivers/lightnvm/rrpc.c @@ -182,7 +182,7 @@ static struct rrpc_block *rrpc_get_blk(struct rrpc *rrpc, struct rrpc_lun *rlun, struct nvm_block *blk; struct rrpc_block *rblk; - blk = nvm_get_blk(rrpc->dev, rlun->parent, 0); + blk = nvm_get_blk(rrpc->dev, rlun->parent, flags); if (!blk) return NULL; @@ -202,6 +202,20 @@ static void rrpc_put_blk(struct rrpc *rrpc, struct rrpc_block *rblk) nvm_put_blk(rrpc->dev, rblk->parent); } +static void rrpc_put_blks(struct rrpc *rrpc) +{ + struct rrpc_lun *rlun; + int i; + + for (i = 0; i < rrpc->nr_luns; i++) { + rlun = &rrpc->luns[i]; + if (rlun->cur) + rrpc_put_blk(rrpc, rlun->cur); + if (rlun->gc_cur) + rrpc_put_blk(rrpc, rlun->gc_cur); + } +} + static struct rrpc_lun *get_next_lun(struct rrpc *rrpc) { int next = atomic_inc_return(&rrpc->next_lun); @@ -1002,7 +1016,7 @@ static int rrpc_map_init(struct rrpc *rrpc) return 0; /* Bring up the mapping table from device */ - ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages, + ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages, rrpc_l2p_update, rrpc); if (ret) { pr_err("nvm: rrpc: could not read L2P table.\n"); @@ -1224,18 +1238,21 @@ static int rrpc_luns_configure(struct rrpc *rrpc) rblk = rrpc_get_blk(rrpc, rlun, 0); if (!rblk) - return -EINVAL; + goto err; rrpc_set_lun_cur(rlun, rblk); /* Emergency gc block */ rblk = rrpc_get_blk(rrpc, rlun, 1); if (!rblk) - return -EINVAL; + goto err; rlun->gc_cur = rblk; } return 0; +err: + rrpc_put_blks(rrpc); + return -EINVAL; } static struct nvm_tgt_type tt_rrpc; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 1fa45695b68a4..c219a053c7f66 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1207,6 +1207,12 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd) dm_block_t held_root; /* + * We commit to ensure the btree roots which we increment in a + * moment are up to date. + */ + __commit_transaction(pmd); + + /* * Copy the superblock. */ dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION); @@ -1538,7 +1544,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block) static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end) { int r; - unsigned count; + unsigned count, total_count = 0; struct dm_pool_metadata *pmd = td->pmd; dm_block_t keys[1] = { td->id }; __le64 value; @@ -1561,11 +1567,29 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_ if (r) return r; - r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count); - if (r) - return r; + /* + * Remove leaves stops at the first unmapped entry, so we have to + * loop round finding mapped ranges. + */ + while (begin < end) { + r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value); + if (r == -ENODATA) + break; + + if (r) + return r; + + if (begin >= end) + break; + + r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count); + if (r) + return r; + + total_count += count; + } - td->mapped_blocks -= count; + td->mapped_blocks -= total_count; td->changed = 1; /* diff --git a/drivers/md/md.c b/drivers/md/md.c index 807095f4c793b..61aacab424cf1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -314,8 +314,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) */ void mddev_suspend(struct mddev *mddev) { - BUG_ON(mddev->suspended); - mddev->suspended = 1; + if (mddev->suspended++) + return; synchronize_rcu(); wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0); mddev->pers->quiesce(mddev, 1); @@ -326,7 +326,8 @@ EXPORT_SYMBOL_GPL(mddev_suspend); void mddev_resume(struct mddev *mddev) { - mddev->suspended = 0; + if (--mddev->suspended) + return; wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); @@ -1652,7 +1653,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->journal_tail = le64_to_cpu(sb->journal_tail); if (mddev->recovery_cp == MaxSector) set_bit(MD_JOURNAL_CLEAN, &mddev->flags); - rdev->raid_disk = mddev->raid_disks; + rdev->raid_disk = 0; break; default: rdev->saved_raid_disk = role; @@ -2773,6 +2774,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) /* Activating a spare .. or possibly reactivating * if we ever get bitmaps working here. */ + int err; if (rdev->raid_disk != -1) return -EBUSY; @@ -2794,9 +2796,15 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) rdev->saved_raid_disk = -1; clear_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); - remove_and_add_spares(rdev->mddev, rdev); - if (rdev->raid_disk == -1) - return -EBUSY; + err = rdev->mddev->pers-> + hot_add_disk(rdev->mddev, rdev); + if (err) { + rdev->raid_disk = -1; + return err; + } else + sysfs_notify_dirent_safe(rdev->sysfs_state); + if (sysfs_link_rdev(rdev->mddev, rdev)) + /* failure here is OK */; /* don't wakeup anyone, leave that to userspace. */ } else { if (slot >= rdev->mddev->raid_disks && @@ -4318,8 +4326,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) } mddev_unlock(mddev); } - } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || - test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) + } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; else if (cmd_match(page, "resync")) clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); @@ -4332,8 +4339,12 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - err = mddev->pers->start_reshape(mddev); + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + err = -EBUSY; + else { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + err = mddev->pers->start_reshape(mddev); + } mddev_unlock(mddev); } if (err) diff --git a/drivers/md/md.h b/drivers/md/md.h index 2bea51edfab70..ca0b643fe3c18 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -566,7 +566,9 @@ static inline char * mdname (struct mddev * mddev) static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + if (!test_bit(Replacement, &rdev->flags) && + !test_bit(Journal, &rdev->flags) && + mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } else @@ -576,7 +578,9 @@ static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + if (!test_bit(Replacement, &rdev->flags) && + !test_bit(Journal, &rdev->flags) && + mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&mddev->kobj, nm); } diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index c573402033b2d..b1ced58eb5e14 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -63,6 +63,11 @@ int lower_bound(struct btree_node *n, uint64_t key) return bsearch(n, key, 0); } +static int upper_bound(struct btree_node *n, uint64_t key) +{ + return bsearch(n, key, 1); +} + void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, struct dm_btree_value_type *vt) { @@ -252,6 +257,16 @@ static void pop_frame(struct del_stack *s) dm_tm_unlock(s->tm, f->b); } +static void unlock_all_frames(struct del_stack *s) +{ + struct frame *f; + + while (unprocessed_frames(s)) { + f = s->spine + s->top--; + dm_tm_unlock(s->tm, f->b); + } +} + int dm_btree_del(struct dm_btree_info *info, dm_block_t root) { int r; @@ -308,9 +323,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) pop_frame(s); } } - out: + if (r) { + /* cleanup all frames of del_stack */ + unlock_all_frames(s); + } kfree(s); + return r; } EXPORT_SYMBOL_GPL(dm_btree_del); @@ -392,6 +411,82 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, } EXPORT_SYMBOL_GPL(dm_btree_lookup); +static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t root, + uint64_t key, uint64_t *rkey, void *value_le) +{ + int r, i; + uint32_t flags, nr_entries; + struct dm_block *node; + struct btree_node *n; + + r = bn_read_lock(info, root, &node); + if (r) + return r; + + n = dm_block_data(node); + flags = le32_to_cpu(n->header.flags); + nr_entries = le32_to_cpu(n->header.nr_entries); + + if (flags & INTERNAL_NODE) { + i = lower_bound(n, key); + if (i < 0 || i >= nr_entries) { + r = -ENODATA; + goto out; + } + + r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le); + if (r == -ENODATA && i < (nr_entries - 1)) { + i++; + r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le); + } + + } else { + i = upper_bound(n, key); + if (i < 0 || i >= nr_entries) { + r = -ENODATA; + goto out; + } + + *rkey = le64_to_cpu(n->keys[i]); + memcpy(value_le, value_ptr(n, i), info->value_type.size); + } +out: + dm_tm_unlock(info->tm, node); + return r; +} + +int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, uint64_t *rkey, void *value_le) +{ + unsigned level; + int r = -ENODATA; + __le64 internal_value_le; + struct ro_spine spine; + + init_ro_spine(&spine, info); + for (level = 0; level < info->levels - 1u; level++) { + r = btree_lookup_raw(&spine, root, keys[level], + lower_bound, rkey, + &internal_value_le, sizeof(uint64_t)); + if (r) + goto out; + + if (*rkey != keys[level]) { + r = -ENODATA; + goto out; + } + + root = le64_to_cpu(internal_value_le); + } + + r = dm_btree_lookup_next_single(info, root, keys[level], rkey, value_le); +out: + exit_ro_spine(&spine); + return r; +} + +EXPORT_SYMBOL_GPL(dm_btree_lookup_next); + /* * Splits a node by creating a sibling node and shifting half the nodes * contents across. Assumes there is a parent node, and it has room for @@ -473,8 +568,10 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index, r = insert_at(sizeof(__le64), pn, parent_index + 1, le64_to_cpu(rn->keys[0]), &location); - if (r) + if (r) { + unlock_block(s->info, right); return r; + } if (key < le64_to_cpu(rn->keys[0])) { unlock_block(s->info, right); diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h index 11d8cf78621dd..c74301fa5a379 100644 --- a/drivers/md/persistent-data/dm-btree.h +++ b/drivers/md/persistent-data/dm-btree.h @@ -110,6 +110,13 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, void *value_le); /* + * Tries to find the first key where the bottom level key is >= to that + * given. Useful for skipping empty sections of the btree. + */ +int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, uint64_t *rkey, void *value_le); + +/* * Insertion (or overwrite an existing value). O(ln(n)) */ int dm_btree_insert(struct dm_btree_info *info, dm_block_t root, @@ -135,9 +142,10 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root); /* - * Removes values between 'keys' and keys2, where keys2 is keys with the - * final key replaced with 'end_key'. 'end_key' is the one-past-the-end - * value. 'keys' may be altered. + * Removes a _contiguous_ run of values starting from 'keys' and not + * reaching keys2 (where keys2 is keys with the final key replaced with + * 'end_key'). 'end_key' is the one-past-the-end value. 'keys' may be + * altered. */ int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, uint64_t end_key, diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 53091295fce9b..fca6dbcf9a472 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -136,7 +136,7 @@ static int brb_push(struct bop_ring_buffer *brb, return 0; } -static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result) +static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result) { struct block_op *bop; @@ -147,6 +147,17 @@ static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result) result->type = bop->type; result->block = bop->block; + return 0; +} + +static int brb_pop(struct bop_ring_buffer *brb) +{ + struct block_op *bop; + + if (brb_empty(brb)) + return -ENODATA; + + bop = brb->bops + brb->begin; brb->begin = brb_next(brb, brb->begin); return 0; @@ -211,7 +222,7 @@ static int apply_bops(struct sm_metadata *smm) while (!brb_empty(&smm->uncommitted)) { struct block_op bop; - r = brb_pop(&smm->uncommitted, &bop); + r = brb_peek(&smm->uncommitted, &bop); if (r) { DMERR("bug in bop ring buffer"); break; @@ -220,6 +231,8 @@ static int apply_bops(struct sm_metadata *smm) r = commit_bop(smm, &bop); if (r) break; + + brb_pop(&smm->uncommitted); } return r; @@ -683,7 +696,6 @@ static struct dm_space_map bootstrap_ops = { static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) { int r, i; - enum allocation_event ev; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); dm_block_t old_len = smm->ll.nr_blocks; @@ -705,11 +717,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) * allocate any new blocks. */ do { - for (i = old_len; !r && i < smm->begin; i++) { - r = sm_ll_inc(&smm->ll, i, &ev); - if (r) - goto out; - } + for (i = old_len; !r && i < smm->begin; i++) + r = add_bop(smm, BOP_INC, i); + + if (r) + goto out; + old_len = smm->begin; r = apply_bops(smm); @@ -754,7 +767,6 @@ int dm_sm_metadata_create(struct dm_space_map *sm, { int r; dm_block_t i; - enum allocation_event ev; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); smm->begin = superblock + 1; @@ -782,7 +794,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm, * allocated blocks that they were built from. */ for (i = superblock; !r && i < smm->begin; i++) - r = sm_ll_inc(&smm->ll, i, &ev); + r = add_bop(smm, BOP_INC, i); if (r) return r; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 41d70bc9ba2f8..84e597e1c4890 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1946,6 +1946,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) first = i; fbio = r10_bio->devs[i].bio; + fbio->bi_iter.bi_size = r10_bio->sectors << 9; + fbio->bi_iter.bi_idx = 0; vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9); /* now find blocks with errors */ @@ -1989,7 +1991,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) bio_reset(tbio); tbio->bi_vcnt = vcnt; - tbio->bi_iter.bi_size = r10_bio->sectors << 9; + tbio->bi_iter.bi_size = fbio->bi_iter.bi_size; tbio->bi_rw = WRITE; tbio->bi_private = r10_bio; tbio->bi_iter.bi_sector = r10_bio->devs[i].addr; diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c index 8616fa8193bca..c2e60b4f292d1 100644 --- a/drivers/media/pci/ivtv/ivtv-driver.c +++ b/drivers/media/pci/ivtv/ivtv-driver.c @@ -805,11 +805,11 @@ static void ivtv_init_struct2(struct ivtv *itv) { int i; - for (i = 0; i < IVTV_CARD_MAX_VIDEO_INPUTS - 1; i++) + for (i = 0; i < IVTV_CARD_MAX_VIDEO_INPUTS; i++) if (itv->card->video_inputs[i].video_type == 0) break; itv->nof_inputs = i; - for (i = 0; i < IVTV_CARD_MAX_AUDIO_INPUTS - 1; i++) + for (i = 0; i < IVTV_CARD_MAX_AUDIO_INPUTS; i++) if (itv->card->audio_inputs[i].audio_type == 0) break; itv->nof_audio_inputs = i; diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c index fcbb497576144..565a593107476 100644 --- a/drivers/media/usb/airspy/airspy.c +++ b/drivers/media/usb/airspy/airspy.c @@ -134,7 +134,7 @@ struct airspy { int urbs_submitted; /* USB control message buffer */ - #define BUF_SIZE 24 + #define BUF_SIZE 128 u8 buf[BUF_SIZE]; /* Current configuration */ diff --git a/drivers/media/usb/hackrf/hackrf.c b/drivers/media/usb/hackrf/hackrf.c index e05bfec90f460..0fe5cb2c260c2 100644 --- a/drivers/media/usb/hackrf/hackrf.c +++ b/drivers/media/usb/hackrf/hackrf.c @@ -24,6 +24,15 @@ #include <media/videobuf2-v4l2.h> #include <media/videobuf2-vmalloc.h> +/* + * Used Avago MGA-81563 RF amplifier could be destroyed pretty easily with too + * strong signal or transmitting to bad antenna. + * Set RF gain control to 'grabbed' state by default for sure. + */ +static bool hackrf_enable_rf_gain_ctrl; +module_param_named(enable_rf_gain_ctrl, hackrf_enable_rf_gain_ctrl, bool, 0644); +MODULE_PARM_DESC(enable_rf_gain_ctrl, "enable RX/TX RF amplifier control (warn: could damage amplifier)"); + /* HackRF USB API commands (from HackRF Library) */ enum { CMD_SET_TRANSCEIVER_MODE = 0x01, @@ -1451,6 +1460,7 @@ static int hackrf_probe(struct usb_interface *intf, dev_err(dev->dev, "Could not initialize controls\n"); goto err_v4l2_ctrl_handler_free_rx; } + v4l2_ctrl_grab(dev->rx_rf_gain, !hackrf_enable_rf_gain_ctrl); v4l2_ctrl_handler_setup(&dev->rx_ctrl_handler); /* Register controls for transmitter */ @@ -1471,6 +1481,7 @@ static int hackrf_probe(struct usb_interface *intf, dev_err(dev->dev, "Could not initialize controls\n"); goto err_v4l2_ctrl_handler_free_tx; } + v4l2_ctrl_grab(dev->tx_rf_gain, !hackrf_enable_rf_gain_ctrl); v4l2_ctrl_handler_setup(&dev->tx_ctrl_handler); /* Register the v4l2_device structure */ @@ -1530,7 +1541,7 @@ err_v4l2_ctrl_handler_free_rx: err_kfree: kfree(dev); err: - dev_dbg(dev->dev, "failed=%d\n", ret); + dev_dbg(&intf->dev, "failed=%d\n", ret); return ret; } diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c index e87459f6d686d..acd1460cf7871 100644 --- a/drivers/memory/fsl_ifc.c +++ b/drivers/memory/fsl_ifc.c @@ -22,6 +22,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/compiler.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/slab.h> diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index d2e75c88f4d21..f409097934906 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -497,6 +497,7 @@ static u64 calculate_sr(struct cxl_context *ctx) { u64 sr = 0; + set_endian(sr); if (ctx->master) sr |= CXL_PSL_SR_An_MP; if (mfspr(SPRN_LPCR) & LPCR_TC) @@ -506,7 +507,6 @@ static u64 calculate_sr(struct cxl_context *ctx) sr |= CXL_PSL_SR_An_HV; } else { sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R; - set_endian(sr); sr &= ~(CXL_PSL_SR_An_HV); if (!test_tsk_thread_flag(current, TIF_32BIT)) sr |= CXL_PSL_SR_An_SF; diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c index 669c3452f278f..9ed6038e47d21 100644 --- a/drivers/mtd/ofpart.c +++ b/drivers/mtd/ofpart.c @@ -46,10 +46,18 @@ static int parse_ofpart_partitions(struct mtd_info *master, ofpart_node = of_get_child_by_name(mtd_node, "partitions"); if (!ofpart_node) { - pr_warn("%s: 'partitions' subnode not found on %s. Trying to parse direct subnodes as partitions.\n", - master->name, mtd_node->full_name); + /* + * We might get here even when ofpart isn't used at all (e.g., + * when using another parser), so don't be louder than + * KERN_DEBUG + */ + pr_debug("%s: 'partitions' subnode not found on %s. Trying to parse direct subnodes as partitions.\n", + master->name, mtd_node->full_name); ofpart_node = mtd_node; dedicated = false; + } else if (!of_device_is_compatible(ofpart_node, "fixed-partitions")) { + /* The 'partitions' subnode might be used by another parser */ + return 0; } /* First count the subnodes */ diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index b077e43b5ba91..c4cb15a3098c0 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -236,7 +236,7 @@ int ubi_debugfs_init(void) dfs_rootdir = debugfs_create_dir("ubi", NULL); if (IS_ERR_OR_NULL(dfs_rootdir)) { - int err = dfs_rootdir ? -ENODEV : PTR_ERR(dfs_rootdir); + int err = dfs_rootdir ? PTR_ERR(dfs_rootdir) : -ENODEV; pr_err("UBI error: cannot create \"ubi\" debugfs directory, error %d\n", err); diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index 1fc23e48fe8e4..10cf3b549959c 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -1299,7 +1299,7 @@ static int self_check_peb_vid_hdr(const struct ubi_device *ubi, int pnum) if (err && err != UBI_IO_BITFLIPS && !mtd_is_eccerr(err)) goto exit; - crc = crc32(UBI_CRC32_INIT, vid_hdr, UBI_EC_HDR_SIZE_CRC); + crc = crc32(UBI_CRC32_INIT, vid_hdr, UBI_VID_HDR_SIZE_CRC); hdr_crc = be32_to_cpu(vid_hdr->hdr_crc); if (hdr_crc != crc) { ubi_err(ubi, "bad VID header CRC at PEB %d, calculated %#08x, read %#08x", diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index eb4489f9082fe..56065632a5b85 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -603,6 +603,7 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, return 0; } +static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk); /** * do_sync_erase - run the erase worker synchronously. * @ubi: UBI device description object @@ -615,20 +616,16 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, static int do_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int vol_id, int lnum, int torture) { - struct ubi_work *wl_wrk; + struct ubi_work wl_wrk; dbg_wl("sync erase of PEB %i", e->pnum); - wl_wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS); - if (!wl_wrk) - return -ENOMEM; - - wl_wrk->e = e; - wl_wrk->vol_id = vol_id; - wl_wrk->lnum = lnum; - wl_wrk->torture = torture; + wl_wrk.e = e; + wl_wrk.vol_id = vol_id; + wl_wrk.lnum = lnum; + wl_wrk.torture = torture; - return erase_worker(ubi, wl_wrk, 0); + return __erase_worker(ubi, &wl_wrk); } /** @@ -1014,7 +1011,7 @@ out_unlock: } /** - * erase_worker - physical eraseblock erase worker function. + * __erase_worker - physical eraseblock erase worker function. * @ubi: UBI device description object * @wl_wrk: the work object * @shutdown: non-zero if the worker has to free memory and exit @@ -1025,8 +1022,7 @@ out_unlock: * needed. Returns zero in case of success and a negative error code in case of * failure. */ -static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, - int shutdown) +static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) { struct ubi_wl_entry *e = wl_wrk->e; int pnum = e->pnum; @@ -1034,21 +1030,11 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, int lnum = wl_wrk->lnum; int err, available_consumed = 0; - if (shutdown) { - dbg_wl("cancel erasure of PEB %d EC %d", pnum, e->ec); - kfree(wl_wrk); - wl_entry_destroy(ubi, e); - return 0; - } - dbg_wl("erase PEB %d EC %d LEB %d:%d", pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum); err = sync_erase(ubi, e, wl_wrk->torture); if (!err) { - /* Fine, we've erased it successfully */ - kfree(wl_wrk); - spin_lock(&ubi->wl_lock); wl_tree_add(e, &ubi->free); ubi->free_count++; @@ -1066,7 +1052,6 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, } ubi_err(ubi, "failed to erase PEB %d, error %d", pnum, err); - kfree(wl_wrk); if (err == -EINTR || err == -ENOMEM || err == -EAGAIN || err == -EBUSY) { @@ -1075,6 +1060,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, /* Re-schedule the LEB for erasure */ err1 = schedule_erase(ubi, e, vol_id, lnum, 0); if (err1) { + wl_entry_destroy(ubi, e); err = err1; goto out_ro; } @@ -1150,6 +1136,25 @@ out_ro: return err; } +static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, + int shutdown) +{ + int ret; + + if (shutdown) { + struct ubi_wl_entry *e = wl_wrk->e; + + dbg_wl("cancel erasure of PEB %d EC %d", e->pnum, e->ec); + kfree(wl_wrk); + wl_entry_destroy(ubi, e); + return 0; + } + + ret = __erase_worker(ubi, wl_wrk); + kfree(wl_wrk); + return ret; +} + /** * ubi_wl_put_peb - return a PEB to the wear-leveling sub-system. * @ubi: UBI device description object diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index fe0e7a6f4d726..cab99fd44c8ef 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1067,12 +1067,12 @@ static netdev_features_t bond_fix_features(struct net_device *dev, return features; } -#define BOND_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ +#define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ NETIF_F_HIGHDMA | NETIF_F_LRO) -#define BOND_ENC_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_RXCSUM |\ - NETIF_F_ALL_TSO) +#define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_RXCSUM | NETIF_F_ALL_TSO) static void bond_compute_features(struct bonding *bond) { @@ -4182,7 +4182,6 @@ void bond_setup(struct net_device *bond_dev) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM); bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; } diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index f4ae720862158..313dbac207ee8 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -42,7 +42,6 @@ #include <net/bonding.h> -#define to_dev(obj) container_of(obj, struct device, kobj) #define to_bond(cd) ((struct bonding *)(netdev_priv(to_net_dev(cd)))) /* "show" function for the bond_masters attribute. diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 75e245c4235e9..9fe33fc3c2b9a 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -617,98 +617,112 @@ static void _mv88e6xxx_stats_read(struct dsa_switch *ds, int stat, u32 *val) } static struct mv88e6xxx_hw_stat mv88e6xxx_hw_stats[] = { - { "in_good_octets", 8, 0x00, }, - { "in_bad_octets", 4, 0x02, }, - { "in_unicast", 4, 0x04, }, - { "in_broadcasts", 4, 0x06, }, - { "in_multicasts", 4, 0x07, }, - { "in_pause", 4, 0x16, }, - { "in_undersize", 4, 0x18, }, - { "in_fragments", 4, 0x19, }, - { "in_oversize", 4, 0x1a, }, - { "in_jabber", 4, 0x1b, }, - { "in_rx_error", 4, 0x1c, }, - { "in_fcs_error", 4, 0x1d, }, - { "out_octets", 8, 0x0e, }, - { "out_unicast", 4, 0x10, }, - { "out_broadcasts", 4, 0x13, }, - { "out_multicasts", 4, 0x12, }, - { "out_pause", 4, 0x15, }, - { "excessive", 4, 0x11, }, - { "collisions", 4, 0x1e, }, - { "deferred", 4, 0x05, }, - { "single", 4, 0x14, }, - { "multiple", 4, 0x17, }, - { "out_fcs_error", 4, 0x03, }, - { "late", 4, 0x1f, }, - { "hist_64bytes", 4, 0x08, }, - { "hist_65_127bytes", 4, 0x09, }, - { "hist_128_255bytes", 4, 0x0a, }, - { "hist_256_511bytes", 4, 0x0b, }, - { "hist_512_1023bytes", 4, 0x0c, }, - { "hist_1024_max_bytes", 4, 0x0d, }, - /* Not all devices have the following counters */ - { "sw_in_discards", 4, 0x110, }, - { "sw_in_filtered", 2, 0x112, }, - { "sw_out_filtered", 2, 0x113, }, - + { "in_good_octets", 8, 0x00, BANK0, }, + { "in_bad_octets", 4, 0x02, BANK0, }, + { "in_unicast", 4, 0x04, BANK0, }, + { "in_broadcasts", 4, 0x06, BANK0, }, + { "in_multicasts", 4, 0x07, BANK0, }, + { "in_pause", 4, 0x16, BANK0, }, + { "in_undersize", 4, 0x18, BANK0, }, + { "in_fragments", 4, 0x19, BANK0, }, + { "in_oversize", 4, 0x1a, BANK0, }, + { "in_jabber", 4, 0x1b, BANK0, }, + { "in_rx_error", 4, 0x1c, BANK0, }, + { "in_fcs_error", 4, 0x1d, BANK0, }, + { "out_octets", 8, 0x0e, BANK0, }, + { "out_unicast", 4, 0x10, BANK0, }, + { "out_broadcasts", 4, 0x13, BANK0, }, + { "out_multicasts", 4, 0x12, BANK0, }, + { "out_pause", 4, 0x15, BANK0, }, + { "excessive", 4, 0x11, BANK0, }, + { "collisions", 4, 0x1e, BANK0, }, + { "deferred", 4, 0x05, BANK0, }, + { "single", 4, 0x14, BANK0, }, + { "multiple", 4, 0x17, BANK0, }, + { "out_fcs_error", 4, 0x03, BANK0, }, + { "late", 4, 0x1f, BANK0, }, + { "hist_64bytes", 4, 0x08, BANK0, }, + { "hist_65_127bytes", 4, 0x09, BANK0, }, + { "hist_128_255bytes", 4, 0x0a, BANK0, }, + { "hist_256_511bytes", 4, 0x0b, BANK0, }, + { "hist_512_1023bytes", 4, 0x0c, BANK0, }, + { "hist_1024_max_bytes", 4, 0x0d, BANK0, }, + { "sw_in_discards", 4, 0x10, PORT, }, + { "sw_in_filtered", 2, 0x12, PORT, }, + { "sw_out_filtered", 2, 0x13, PORT, }, + { "in_discards", 4, 0x00 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_filtered", 4, 0x01 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_accepted", 4, 0x02 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_bad_accepted", 4, 0x03 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_good_avb_class_a", 4, 0x04 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_good_avb_class_b", 4, 0x05 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_bad_avb_class_a", 4, 0x06 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_bad_avb_class_b", 4, 0x07 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "tcam_counter_0", 4, 0x08 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "tcam_counter_1", 4, 0x09 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "tcam_counter_2", 4, 0x0a | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "tcam_counter_3", 4, 0x0b | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_da_unknown", 4, 0x0e | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "in_management", 4, 0x0f | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_0", 4, 0x10 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_1", 4, 0x11 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_2", 4, 0x12 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_3", 4, 0x13 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_4", 4, 0x14 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_5", 4, 0x15 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_6", 4, 0x16 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_queue_7", 4, 0x17 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_cut_through", 4, 0x18 | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_octets_a", 4, 0x1a | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_octets_b", 4, 0x1b | GLOBAL_STATS_OP_BANK_1, BANK1, }, + { "out_management", 4, 0x1f | GLOBAL_STATS_OP_BANK_1, BANK1, }, }; -static bool have_sw_in_discards(struct dsa_switch *ds) +static bool mv88e6xxx_has_stat(struct dsa_switch *ds, + struct mv88e6xxx_hw_stat *stat) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - - switch (ps->id) { - case PORT_SWITCH_ID_6095: case PORT_SWITCH_ID_6161: - case PORT_SWITCH_ID_6165: case PORT_SWITCH_ID_6171: - case PORT_SWITCH_ID_6172: case PORT_SWITCH_ID_6176: - case PORT_SWITCH_ID_6182: case PORT_SWITCH_ID_6185: - case PORT_SWITCH_ID_6352: + switch (stat->type) { + case BANK0: return true; - default: - return false; - } -} - -static void _mv88e6xxx_get_strings(struct dsa_switch *ds, - int nr_stats, - struct mv88e6xxx_hw_stat *stats, - int port, uint8_t *data) -{ - int i; - - for (i = 0; i < nr_stats; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - stats[i].string, ETH_GSTRING_LEN); + case BANK1: + return mv88e6xxx_6320_family(ds); + case PORT: + return mv88e6xxx_6095_family(ds) || + mv88e6xxx_6185_family(ds) || + mv88e6xxx_6097_family(ds) || + mv88e6xxx_6165_family(ds) || + mv88e6xxx_6351_family(ds) || + mv88e6xxx_6352_family(ds); } + return false; } static uint64_t _mv88e6xxx_get_ethtool_stat(struct dsa_switch *ds, - int stat, - struct mv88e6xxx_hw_stat *stats, + struct mv88e6xxx_hw_stat *s, int port) { - struct mv88e6xxx_hw_stat *s = stats + stat; u32 low; u32 high = 0; int ret; u64 value; - if (s->reg >= 0x100) { - ret = _mv88e6xxx_reg_read(ds, REG_PORT(port), - s->reg - 0x100); + switch (s->type) { + case PORT: + ret = _mv88e6xxx_reg_read(ds, REG_PORT(port), s->reg); if (ret < 0) return UINT64_MAX; low = ret; if (s->sizeof_stat == 4) { ret = _mv88e6xxx_reg_read(ds, REG_PORT(port), - s->reg - 0x100 + 1); + s->reg + 1); if (ret < 0) return UINT64_MAX; high = ret; } - } else { + break; + case BANK0: + case BANK1: _mv88e6xxx_stats_read(ds, s->reg, &low); if (s->sizeof_stat == 8) _mv88e6xxx_stats_read(ds, s->reg + 1, &high); @@ -717,61 +731,59 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct dsa_switch *ds, return value; } -static void _mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, - int nr_stats, - struct mv88e6xxx_hw_stat *stats, - int port, uint64_t *data) +void mv88e6xxx_get_strings(struct dsa_switch *ds, int port, uint8_t *data) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - int ret; - int i; - - mutex_lock(&ps->smi_mutex); + struct mv88e6xxx_hw_stat *stat; + int i, j; - ret = _mv88e6xxx_stats_snapshot(ds, port); - if (ret < 0) { - mutex_unlock(&ps->smi_mutex); - return; + for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { + stat = &mv88e6xxx_hw_stats[i]; + if (mv88e6xxx_has_stat(ds, stat)) { + memcpy(data + j * ETH_GSTRING_LEN, stat->string, + ETH_GSTRING_LEN); + j++; + } } - - /* Read each of the counters. */ - for (i = 0; i < nr_stats; i++) - data[i] = _mv88e6xxx_get_ethtool_stat(ds, i, stats, port); - - mutex_unlock(&ps->smi_mutex); -} - -/* All the statistics in the table */ -void -mv88e6xxx_get_strings(struct dsa_switch *ds, int port, uint8_t *data) -{ - if (have_sw_in_discards(ds)) - _mv88e6xxx_get_strings(ds, ARRAY_SIZE(mv88e6xxx_hw_stats), - mv88e6xxx_hw_stats, port, data); - else - _mv88e6xxx_get_strings(ds, ARRAY_SIZE(mv88e6xxx_hw_stats) - 3, - mv88e6xxx_hw_stats, port, data); } int mv88e6xxx_get_sset_count(struct dsa_switch *ds) { - if (have_sw_in_discards(ds)) - return ARRAY_SIZE(mv88e6xxx_hw_stats); - return ARRAY_SIZE(mv88e6xxx_hw_stats) - 3; + struct mv88e6xxx_hw_stat *stat; + int i, j; + + for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { + stat = &mv88e6xxx_hw_stats[i]; + if (mv88e6xxx_has_stat(ds, stat)) + j++; + } + return j; } void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) { - if (have_sw_in_discards(ds)) - _mv88e6xxx_get_ethtool_stats( - ds, ARRAY_SIZE(mv88e6xxx_hw_stats), - mv88e6xxx_hw_stats, port, data); - else - _mv88e6xxx_get_ethtool_stats( - ds, ARRAY_SIZE(mv88e6xxx_hw_stats) - 3, - mv88e6xxx_hw_stats, port, data); + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + struct mv88e6xxx_hw_stat *stat; + int ret; + int i, j; + + mutex_lock(&ps->smi_mutex); + + ret = _mv88e6xxx_stats_snapshot(ds, port); + if (ret < 0) { + mutex_unlock(&ps->smi_mutex); + return; + } + for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { + stat = &mv88e6xxx_hw_stats[i]; + if (mv88e6xxx_has_stat(ds, stat)) { + data[j] = _mv88e6xxx_get_ethtool_stat(ds, stat, port); + j++; + } + } + + mutex_unlock(&ps->smi_mutex); } int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 21c8daa03f788..ca08f913d302c 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -288,6 +288,7 @@ #define GLOBAL_STATS_OP_HIST_RX ((1 << 10) | GLOBAL_STATS_OP_BUSY) #define GLOBAL_STATS_OP_HIST_TX ((2 << 10) | GLOBAL_STATS_OP_BUSY) #define GLOBAL_STATS_OP_HIST_RX_TX ((3 << 10) | GLOBAL_STATS_OP_BUSY) +#define GLOBAL_STATS_OP_BANK_1 BIT(9) #define GLOBAL_STATS_COUNTER_32 0x1e #define GLOBAL_STATS_COUNTER_01 0x1f @@ -420,10 +421,17 @@ struct mv88e6xxx_priv_state { struct work_struct bridge_work; }; +enum stat_type { + BANK0, + BANK1, + PORT, +}; + struct mv88e6xxx_hw_stat { char string[ETH_GSTRING_LEN]; int sizeof_stat; int reg; + enum stat_type type; }; int mv88e6xxx_switch_reset(struct dsa_switch *ds, bool ppu_active); diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index 4547a1b8b958b..7677c745fb30b 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -562,7 +562,7 @@ static void el3_common_remove (struct net_device *dev) } #ifdef CONFIG_EISA -static int __init el3_eisa_probe (struct device *device) +static int el3_eisa_probe(struct device *device) { short i; int ioaddr, irq, if_port; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 2839af00f20cd..1c5f3b273e6ac 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -907,7 +907,7 @@ static struct eisa_device_id vortex_eisa_ids[] = { }; MODULE_DEVICE_TABLE(eisa, vortex_eisa_ids); -static int __init vortex_eisa_probe(struct device *device) +static int vortex_eisa_probe(struct device *device) { void __iomem *ioaddr; struct eisa_device *edev; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 970781a9e6777..f6a7161e3b852 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1849,7 +1849,7 @@ static int xgbe_exit(struct xgbe_prv_data *pdata) usleep_range(10, 15); /* Poll Until Poll Condition */ - while (count-- && XGMAC_IOREAD_BITS(pdata, DMA_MR, SWR)) + while (--count && XGMAC_IOREAD_BITS(pdata, DMA_MR, SWR)) usleep_range(500, 600); if (!count) @@ -1873,7 +1873,7 @@ static int xgbe_flush_tx_queues(struct xgbe_prv_data *pdata) /* Poll Until Poll Condition */ for (i = 0; i < pdata->tx_q_count; i++) { count = 2000; - while (count-- && XGMAC_MTL_IOREAD_BITS(pdata, i, + while (--count && XGMAC_MTL_IOREAD_BITS(pdata, i, MTL_Q_TQOMR, FTQ)) usleep_range(500, 600); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 2394191ad28e5..a4799c1fc7d4d 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -289,6 +289,7 @@ static int xgene_enet_setup_tx_desc(struct xgene_enet_desc_ring *tx_ring, struct sk_buff *skb) { struct device *dev = ndev_to_dev(tx_ring->ndev); + struct xgene_enet_pdata *pdata = netdev_priv(tx_ring->ndev); struct xgene_enet_raw_desc *raw_desc; __le64 *exp_desc = NULL, *exp_bufs = NULL; dma_addr_t dma_addr, pbuf_addr, *frag_dma_addr; @@ -419,6 +420,7 @@ out: raw_desc->m0 = cpu_to_le64(SET_VAL(LL, ll) | SET_VAL(NV, nv) | SET_VAL(USERINFO, tx_ring->tail)); tx_ring->cp_ring->cp_skb[tx_ring->tail] = skb; + pdata->tx_level += count; tx_ring->tail = tail; return count; @@ -429,14 +431,13 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb, { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct xgene_enet_desc_ring *tx_ring = pdata->tx_ring; - struct xgene_enet_desc_ring *cp_ring = tx_ring->cp_ring; - u32 tx_level, cq_level; + u32 tx_level = pdata->tx_level; int count; - tx_level = pdata->ring_ops->len(tx_ring); - cq_level = pdata->ring_ops->len(cp_ring); - if (unlikely(tx_level > pdata->tx_qcnt_hi || - cq_level > pdata->cp_qcnt_hi)) { + if (tx_level < pdata->txc_level) + tx_level += ((typeof(pdata->tx_level))~0U); + + if ((tx_level - pdata->txc_level) > pdata->tx_qcnt_hi) { netif_stop_queue(ndev); return NETDEV_TX_BUSY; } @@ -539,10 +540,13 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, struct xgene_enet_raw_desc *raw_desc, *exp_desc; u16 head = ring->head; u16 slots = ring->slots - 1; - int ret, count = 0, processed = 0; + int ret, desc_count, count = 0, processed = 0; + bool is_completion; do { raw_desc = &ring->raw_desc[head]; + desc_count = 0; + is_completion = false; exp_desc = NULL; if (unlikely(xgene_enet_is_desc_slot_empty(raw_desc))) break; @@ -559,18 +563,24 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, } dma_rmb(); count++; + desc_count++; } - if (is_rx_desc(raw_desc)) + if (is_rx_desc(raw_desc)) { ret = xgene_enet_rx_frame(ring, raw_desc); - else + } else { ret = xgene_enet_tx_completion(ring, raw_desc); + is_completion = true; + } xgene_enet_mark_desc_slot_empty(raw_desc); if (exp_desc) xgene_enet_mark_desc_slot_empty(exp_desc); head = (head + 1) & slots; count++; + desc_count++; processed++; + if (is_completion) + pdata->txc_level += desc_count; if (ret) break; @@ -580,10 +590,8 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, pdata->ring_ops->wr_cmd(ring, -count); ring->head = head; - if (netif_queue_stopped(ring->ndev)) { - if (pdata->ring_ops->len(ring) < pdata->cp_qcnt_low) - netif_wake_queue(ring->ndev); - } + if (netif_queue_stopped(ring->ndev)) + netif_start_queue(ring->ndev); } return processed; @@ -1033,9 +1041,7 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev) pdata->tx_ring->cp_ring = cp_ring; pdata->tx_ring->dst_ring_num = xgene_enet_dst_ring_num(cp_ring); - pdata->tx_qcnt_hi = pdata->tx_ring->slots / 2; - pdata->cp_qcnt_hi = pdata->rx_ring->slots / 2; - pdata->cp_qcnt_low = pdata->cp_qcnt_hi / 2; + pdata->tx_qcnt_hi = pdata->tx_ring->slots - 128; return 0; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 054caf055f0a0..70d5b62c125a4 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -155,11 +155,11 @@ struct xgene_enet_pdata { enum xgene_enet_id enet_id; struct xgene_enet_desc_ring *tx_ring; struct xgene_enet_desc_ring *rx_ring; + u16 tx_level; + u16 txc_level; char *dev_name; u32 rx_buff_cnt; u32 tx_qcnt_hi; - u32 cp_qcnt_hi; - u32 cp_qcnt_low; u32 rx_irq; u32 txc_irq; u8 cq_cnt; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 2795d6db10e18..8b5988e210d55 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1016,13 +1016,12 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter) sizeof(struct atl1c_recv_ret_status) * rx_desc_count + 8 * 4; - ring_header->desc = pci_alloc_consistent(pdev, ring_header->size, - &ring_header->dma); + ring_header->desc = dma_zalloc_coherent(&pdev->dev, ring_header->size, + &ring_header->dma, GFP_KERNEL); if (unlikely(!ring_header->desc)) { - dev_err(&pdev->dev, "pci_alloc_consistend failed\n"); + dev_err(&pdev->dev, "could not get memory for DMA buffer\n"); goto err_nomem; } - memset(ring_header->desc, 0, ring_header->size); /* init TPD ring */ tpd_ring[0].dma = roundup(ring_header->dma, 8); diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig index a3c7106fdf85e..8ba7f8ff34340 100644 --- a/drivers/net/ethernet/aurora/Kconfig +++ b/drivers/net/ethernet/aurora/Kconfig @@ -13,6 +13,7 @@ if NET_VENDOR_AURORA config AURORA_NB8800 tristate "Aurora AU-NB8800 support" + depends on HAS_DMA select PHYLIB help Support for the AU-NB8800 gigabit Ethernet controller. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index b3552dd749c4f..9695a4c4a434a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3370,25 +3370,29 @@ static u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb) return rc; } -#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - 3) +/* VXLAN: 4 = 1 (for linear data BD) + 3 (2 for PBD and last BD) */ +#define BNX2X_NUM_VXLAN_TSO_WIN_SUB_BDS 4 + +/* Regular: 3 = 1 (for linear data BD) + 2 (for PBD and last BD) */ +#define BNX2X_NUM_TSO_WIN_SUB_BDS 3 + +#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - BDS_PER_TX_PKT) /* check if packet requires linearization (packet is too fragmented) no need to check fragmentation if page size > 8K (there will be no violation to FW restrictions) */ static int bnx2x_pkt_req_lin(struct bnx2x *bp, struct sk_buff *skb, u32 xmit_type) { - int to_copy = 0; - int hlen = 0; - int first_bd_sz = 0; + int first_bd_sz = 0, num_tso_win_sub = BNX2X_NUM_TSO_WIN_SUB_BDS; + int to_copy = 0, hlen = 0; - /* 3 = 1 (for linear data BD) + 2 (for PBD and last BD) */ - if (skb_shinfo(skb)->nr_frags >= (MAX_FETCH_BD - 3)) { + if (xmit_type & XMIT_GSO_ENC) + num_tso_win_sub = BNX2X_NUM_VXLAN_TSO_WIN_SUB_BDS; + if (skb_shinfo(skb)->nr_frags >= (MAX_FETCH_BD - num_tso_win_sub)) { if (xmit_type & XMIT_GSO) { unsigned short lso_mss = skb_shinfo(skb)->gso_size; - /* Check if LSO packet needs to be copied: - 3 = 1 (for headers BD) + 2 (for PBD and last BD) */ - int wnd_size = MAX_FETCH_BD - 3; + int wnd_size = MAX_FETCH_BD - num_tso_win_sub; /* Number of windows to check */ int num_wnds = skb_shinfo(skb)->nr_frags - wnd_size; int wnd_idx = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 11446adc03cc0..f9569493034b4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -72,8 +72,10 @@ MODULE_VERSION(DRV_MODULE_VERSION); #define BNXT_TX_PUSH_THRESH 92 enum board_idx { + BCM57301, BCM57302, BCM57304, + BCM57402, BCM57404, BCM57406, BCM57304_VF, @@ -84,17 +86,21 @@ enum board_idx { static const struct { char *name; } board_info[] = { - { "Broadcom BCM57302 NetXtreme-C Single-port 10Gb/25Gb/40Gb/50Gb Ethernet" }, + { "Broadcom BCM57301 NetXtreme-C Single-port 10Gb Ethernet" }, + { "Broadcom BCM57302 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" }, { "Broadcom BCM57304 NetXtreme-C Dual-port 10Gb/25Gb/40Gb/50Gb Ethernet" }, + { "Broadcom BCM57402 NetXtreme-E Dual-port 10Gb Ethernet" }, { "Broadcom BCM57404 NetXtreme-E Dual-port 10Gb/25Gb Ethernet" }, - { "Broadcom BCM57406 NetXtreme-E Dual-port 10Gb Ethernet" }, + { "Broadcom BCM57406 NetXtreme-E Dual-port 10GBase-T Ethernet" }, { "Broadcom BCM57304 NetXtreme-C Ethernet Virtual Function" }, { "Broadcom BCM57404 NetXtreme-E Ethernet Virtual Function" }, }; static const struct pci_device_id bnxt_pci_tbl[] = { + { PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 }, { PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 }, { PCI_VDEVICE(BROADCOM, 0x16ca), .driver_data = BCM57304 }, + { PCI_VDEVICE(BROADCOM, 0x16d0), .driver_data = BCM57402 }, { PCI_VDEVICE(BROADCOM, 0x16d1), .driver_data = BCM57404 }, { PCI_VDEVICE(BROADCOM, 0x16d2), .driver_data = BCM57406 }, #ifdef CONFIG_BNXT_SRIOV @@ -173,7 +179,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) u32 len, free_size, vlan_tag_flags, cfa_action, flags; u16 prod, last_frag; struct pci_dev *pdev = bp->pdev; - struct bnxt_napi *bnapi; struct bnxt_tx_ring_info *txr; struct bnxt_sw_tx_bd *tx_buf; @@ -183,8 +188,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - bnapi = bp->bnapi[i]; - txr = &bnapi->tx_ring; + txr = &bp->tx_ring[i]; txq = netdev_get_tx_queue(dev, i); prod = txr->tx_prod; @@ -417,8 +421,8 @@ tx_dma_error: static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) { - struct bnxt_tx_ring_info *txr = &bnapi->tx_ring; - int index = bnapi->index; + struct bnxt_tx_ring_info *txr = bnapi->tx_ring; + int index = txr - &bp->tx_ring[0]; struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, index); u16 cons = txr->tx_cons; struct pci_dev *pdev = bp->pdev; @@ -596,7 +600,7 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_napi *bnapi, u16 cp_cons, { struct bnxt *bp = bnapi->bp; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; u16 sw_prod = rxr->rx_sw_agg_prod; u32 i; @@ -675,7 +679,7 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_napi *bnapi, { struct pci_dev *pdev = bp->pdev; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; u32 i; @@ -856,8 +860,13 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt_tpa_info *tpa_info, struct tcphdr *th; int payload_off, tcp_opt_len = 0; int len, nw_off; + u16 segs; + + segs = TPA_END_TPA_SEGS(tpa_end); + if (segs == 1) + return skb; - NAPI_GRO_CB(skb)->count = TPA_END_TPA_SEGS(tpa_end); + NAPI_GRO_CB(skb)->count = segs; skb_shinfo(skb)->gso_size = le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len); skb_shinfo(skb)->gso_type = tpa_info->gso_type; @@ -929,7 +938,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, bool *agg_event) { struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u8 agg_id = TPA_END_AGG_ID(tpa_end); u8 *data, agg_bufs; u16 cp_cons = RING_CMP(*raw_cons); @@ -1045,7 +1054,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, bool *agg_event) { struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; struct net_device *dev = bp->dev; struct rx_cmp *rxcmp; struct rx_cmp_ext *rxcmp1; @@ -1187,8 +1196,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, skb->csum_level = RX_CMP_ENCAP(rxcmp1); } } else { - if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L4_CS_ERR_BITS) - cpr->rx_l4_csum_errors++; + if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L4_CS_ERR_BITS) { + if (dev->features & NETIF_F_RXCSUM) + cpr->rx_l4_csum_errors++; + } } skb_record_rx_queue(skb, bnapi->index); @@ -1377,7 +1388,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) bnxt_tx_int(bp, bnapi, tx_pkts); if (rx_event) { - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell); writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell); @@ -1446,19 +1457,14 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) int i, max_idx; struct pci_dev *pdev = bp->pdev; - if (!bp->bnapi) + if (!bp->tx_ring) return; max_idx = bp->tx_nr_pages * TX_DESC_CNT; for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_tx_ring_info *txr; + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; int j; - if (!bnapi) - continue; - - txr = &bnapi->tx_ring; for (j = 0; j < max_idx;) { struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j]; struct sk_buff *skb = tx_buf->skb; @@ -1504,21 +1510,15 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) int i, max_idx, max_agg_idx; struct pci_dev *pdev = bp->pdev; - if (!bp->bnapi) + if (!bp->rx_ring) return; max_idx = bp->rx_nr_pages * RX_DESC_CNT; max_agg_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr; + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; int j; - if (!bnapi) - continue; - - rxr = &bnapi->rx_ring; - if (rxr->rx_tpa) { for (j = 0; j < MAX_TPA; j++) { struct bnxt_tpa_info *tpa_info = @@ -1646,19 +1646,13 @@ static void bnxt_free_rx_rings(struct bnxt *bp) { int i; - if (!bp->bnapi) + if (!bp->rx_ring) return; for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr; + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring; - if (!bnapi) - continue; - - rxr = &bnapi->rx_ring; - kfree(rxr->rx_tpa); rxr->rx_tpa = NULL; @@ -1677,6 +1671,9 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) { int i, rc, agg_rings = 0, tpa_rings = 0; + if (!bp->rx_ring) + return -ENOMEM; + if (bp->flags & BNXT_FLAG_AGG_RINGS) agg_rings = 1; @@ -1684,14 +1681,9 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) tpa_rings = 1; for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr; + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring; - if (!bnapi) - continue; - - rxr = &bnapi->rx_ring; ring = &rxr->rx_ring_struct; rc = bnxt_alloc_ring(bp, ring); @@ -1729,19 +1721,13 @@ static void bnxt_free_tx_rings(struct bnxt *bp) int i; struct pci_dev *pdev = bp->pdev; - if (!bp->bnapi) + if (!bp->tx_ring) return; for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_tx_ring_info *txr; + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; struct bnxt_ring_struct *ring; - if (!bnapi) - continue; - - txr = &bnapi->tx_ring; - if (txr->tx_push) { dma_free_coherent(&pdev->dev, bp->tx_push_size, txr->tx_push, txr->tx_push_mapping); @@ -1775,14 +1761,9 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) } for (i = 0, j = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_tx_ring_info *txr; + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; struct bnxt_ring_struct *ring; - if (!bnapi) - continue; - - txr = &bnapi->tx_ring; ring = &txr->tx_ring_struct; rc = bnxt_alloc_ring(bp, ring); @@ -1885,7 +1866,10 @@ static void bnxt_init_ring_struct(struct bnxt *bp) ring->dma_arr = cpr->cp_desc_mapping; ring->vmem_size = 0; - rxr = &bnapi->rx_ring; + rxr = bnapi->rx_ring; + if (!rxr) + goto skip_rx; + ring = &rxr->rx_ring_struct; ring->nr_pages = bp->rx_nr_pages; ring->page_size = HW_RXBD_RING_SIZE; @@ -1902,7 +1886,11 @@ static void bnxt_init_ring_struct(struct bnxt *bp) ring->vmem_size = SW_RXBD_AGG_RING_SIZE * bp->rx_agg_nr_pages; ring->vmem = (void **)&rxr->rx_agg_ring; - txr = &bnapi->tx_ring; +skip_rx: + txr = bnapi->tx_ring; + if (!txr) + continue; + ring = &txr->tx_ring_struct; ring->nr_pages = bp->tx_nr_pages; ring->page_size = HW_RXBD_RING_SIZE; @@ -1938,22 +1926,18 @@ static void bnxt_init_rxbd_pages(struct bnxt_ring_struct *ring, u32 type) static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) { struct net_device *dev = bp->dev; - struct bnxt_napi *bnapi = bp->bnapi[ring_nr]; struct bnxt_rx_ring_info *rxr; struct bnxt_ring_struct *ring; u32 prod, type; int i; - if (!bnapi) - return -EINVAL; - type = (bp->rx_buf_use_size << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_PACKET_BD | RX_BD_FLAGS_EOP; if (NET_IP_ALIGN == 2) type |= RX_BD_FLAGS_SOP; - rxr = &bnapi->rx_ring; + rxr = &bp->rx_ring[ring_nr]; ring = &rxr->rx_ring_struct; bnxt_init_rxbd_pages(ring, type); @@ -1969,11 +1953,12 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) rxr->rx_prod = prod; ring->fw_ring_id = INVALID_HW_RING_ID; + ring = &rxr->rx_agg_ring_struct; + ring->fw_ring_id = INVALID_HW_RING_ID; + if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) return 0; - ring = &rxr->rx_agg_ring_struct; - type = ((u32)PAGE_SIZE << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; @@ -1989,7 +1974,6 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) prod = NEXT_RX_AGG(prod); } rxr->rx_agg_prod = prod; - ring->fw_ring_id = INVALID_HW_RING_ID; if (bp->flags & BNXT_FLAG_TPA) { if (rxr->rx_tpa) { @@ -2035,8 +2019,7 @@ static int bnxt_init_tx_rings(struct bnxt *bp) MAX_SKB_FRAGS + 1); for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_tx_ring_info *txr = &bnapi->tx_ring; + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; struct bnxt_ring_struct *ring = &txr->tx_ring_struct; ring->fw_ring_id = INVALID_HW_RING_ID; @@ -2423,14 +2406,18 @@ static void bnxt_clear_ring_indices(struct bnxt *bp) cpr = &bnapi->cp_ring; cpr->cp_raw_cons = 0; - txr = &bnapi->tx_ring; - txr->tx_prod = 0; - txr->tx_cons = 0; + txr = bnapi->tx_ring; + if (txr) { + txr->tx_prod = 0; + txr->tx_cons = 0; + } - rxr = &bnapi->rx_ring; - rxr->rx_prod = 0; - rxr->rx_agg_prod = 0; - rxr->rx_sw_agg_prod = 0; + rxr = bnapi->rx_ring; + if (rxr) { + rxr->rx_prod = 0; + rxr->rx_agg_prod = 0; + rxr->rx_sw_agg_prod = 0; + } } } @@ -2496,6 +2483,10 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init) bnxt_free_stats(bp); bnxt_free_ring_grps(bp); bnxt_free_vnics(bp); + kfree(bp->tx_ring); + bp->tx_ring = NULL; + kfree(bp->rx_ring); + bp->rx_ring = NULL; kfree(bp->bnapi); bp->bnapi = NULL; } else { @@ -2505,7 +2496,7 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init) static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init) { - int i, rc, size, arr_size; + int i, j, rc, size, arr_size; void *bnapi; if (irq_re_init) { @@ -2527,6 +2518,33 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init) bp->bnapi[i]->bp = bp; } + bp->rx_ring = kcalloc(bp->rx_nr_rings, + sizeof(struct bnxt_rx_ring_info), + GFP_KERNEL); + if (!bp->rx_ring) + return -ENOMEM; + + for (i = 0; i < bp->rx_nr_rings; i++) { + bp->rx_ring[i].bnapi = bp->bnapi[i]; + bp->bnapi[i]->rx_ring = &bp->rx_ring[i]; + } + + bp->tx_ring = kcalloc(bp->tx_nr_rings, + sizeof(struct bnxt_tx_ring_info), + GFP_KERNEL); + if (!bp->tx_ring) + return -ENOMEM; + + if (bp->flags & BNXT_FLAG_SHARED_RINGS) + j = 0; + else + j = bp->rx_nr_rings; + + for (i = 0; i < bp->tx_nr_rings; i++, j++) { + bp->tx_ring[i].bnapi = bp->bnapi[j]; + bp->bnapi[j]->tx_ring = &bp->tx_ring[i]; + } + rc = bnxt_alloc_stats(bp); if (rc) goto alloc_mem_err; @@ -2693,17 +2711,16 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) req.ver_upd = DRV_VER_UPD; if (BNXT_PF(bp)) { - unsigned long vf_req_snif_bmap[4]; + DECLARE_BITMAP(vf_req_snif_bmap, 256); u32 *data = (u32 *)vf_req_snif_bmap; - memset(vf_req_snif_bmap, 0, 32); + memset(vf_req_snif_bmap, 0, sizeof(vf_req_snif_bmap)); for (i = 0; i < ARRAY_SIZE(bnxt_vf_req_snif); i++) __set_bit(bnxt_vf_req_snif[i], vf_req_snif_bmap); - for (i = 0; i < 8; i++) { - req.vf_req_fwd[i] = cpu_to_le32(*data); - data++; - } + for (i = 0; i < 8; i++) + req.vf_req_fwd[i] = cpu_to_le32(data[i]); + req.enables |= cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD); } @@ -2711,6 +2728,14 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } +static int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp) +{ + struct hwrm_func_drv_unrgtr_input req = {0}; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_UNRGTR, -1, -1); + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type) { u32 rc = 0; @@ -2773,7 +2798,7 @@ static int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, u16 vnic_id) struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_L2_SET_RX_MASK, -1, -1); - req.dflt_vnic_id = cpu_to_le32(vnic->fw_vnic_id); + req.vnic_id = cpu_to_le32(vnic->fw_vnic_id); req.num_mc_entries = cpu_to_le32(vnic->mc_list_count); req.mc_tbl_addr = cpu_to_le64(vnic->mc_list_mapping); @@ -2806,7 +2831,7 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp, CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT_MASK | \ CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT | \ CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT_MASK | \ - CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID) + CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID) static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp, struct bnxt_ntuple_filter *fltr) @@ -2825,7 +2850,7 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp, req.ethertype = htons(ETH_P_IP); memcpy(req.src_macaddr, fltr->src_mac_addr, ETH_ALEN); - req.ipaddr_type = 4; + req.ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4; req.ip_protocol = keys->basic.ip_proto; req.src_ipaddr[0] = keys->addrs.v4addrs.src; @@ -2838,7 +2863,7 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp, req.dst_port = keys->ports.dst; req.dst_port_mask = cpu_to_be16(0xffff); - req.dst_vnic_id = cpu_to_le16(vnic->fw_vnic_id); + req.dst_id = cpu_to_le16(vnic->fw_vnic_id); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) @@ -2858,10 +2883,10 @@ static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_L2_FILTER_ALLOC, -1, -1); req.flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX | CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST); - req.dst_vnic_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id); + req.dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id); req.enables = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR | - CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID | + CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID | CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK); memcpy(req.l2_addr, mac_addr, ETH_ALEN); req.l2_addr_mask[0] = 0xff; @@ -2931,7 +2956,8 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) req.enables = cpu_to_le32(VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS | - VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS); + VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS | + VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN); /* Number of segs are log2 units, and first packet is not * included as part of this units. @@ -2949,6 +2975,8 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) segs = ilog2(nsegs); req.max_agg_segs = cpu_to_le16(segs); req.max_aggs = cpu_to_le16(VNIC_TPA_CFG_REQ_MAX_AGGS_MAX); + + req.min_agg_len = cpu_to_le32(512); } req.vnic_id = cpu_to_le16(vnic->fw_vnic_id); @@ -3059,7 +3087,7 @@ static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id) static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id) { - int grp_idx = 0; + unsigned int ring = 0, grp_idx; struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; struct hwrm_vnic_cfg_input req = {0}; @@ -3070,10 +3098,11 @@ static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id) req.rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx); req.cos_rule = cpu_to_le16(0xffff); if (vnic->flags & BNXT_VNIC_RSS_FLAG) - grp_idx = 0; + ring = 0; else if (vnic->flags & BNXT_VNIC_RFS_FLAG) - grp_idx = vnic_id - 1; + ring = vnic_id - 1; + grp_idx = bp->rx_ring[ring].bnapi->index; req.vnic_id = cpu_to_le16(vnic->fw_vnic_id); req.dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id); @@ -3114,22 +3143,25 @@ static void bnxt_hwrm_vnic_free(struct bnxt *bp) bnxt_hwrm_vnic_free_one(bp, i); } -static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id, u16 start_grp_id, - u16 end_grp_id) +static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id, + unsigned int start_rx_ring_idx, + unsigned int nr_rings) { - u32 rc = 0, i, j; + int rc = 0; + unsigned int i, j, grp_idx, end_idx = start_rx_ring_idx + nr_rings; struct hwrm_vnic_alloc_input req = {0}; struct hwrm_vnic_alloc_output *resp = bp->hwrm_cmd_resp_addr; /* map ring groups to this vnic */ - for (i = start_grp_id, j = 0; i < end_grp_id; i++, j++) { - if (bp->grp_info[i].fw_grp_id == INVALID_HW_RING_ID) { + for (i = start_rx_ring_idx, j = 0; i < end_idx; i++, j++) { + grp_idx = bp->rx_ring[i].bnapi->index; + if (bp->grp_info[grp_idx].fw_grp_id == INVALID_HW_RING_ID) { netdev_err(bp->dev, "Not enough ring groups avail:%x req:%x\n", - j, (end_grp_id - start_grp_id)); + j, nr_rings); break; } bp->vnic_info[vnic_id].fw_grp_ids[j] = - bp->grp_info[i].fw_grp_id; + bp->grp_info[grp_idx].fw_grp_id; } bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx = INVALID_HW_RING_ID; @@ -3156,20 +3188,22 @@ static int bnxt_hwrm_ring_grp_alloc(struct bnxt *bp) struct hwrm_ring_grp_alloc_input req = {0}; struct hwrm_ring_grp_alloc_output *resp = bp->hwrm_cmd_resp_addr; + unsigned int grp_idx = bp->rx_ring[i].bnapi->index; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_GRP_ALLOC, -1, -1); - req.cr = cpu_to_le16(bp->grp_info[i].cp_fw_ring_id); - req.rr = cpu_to_le16(bp->grp_info[i].rx_fw_ring_id); - req.ar = cpu_to_le16(bp->grp_info[i].agg_fw_ring_id); - req.sc = cpu_to_le16(bp->grp_info[i].fw_stats_ctx); + req.cr = cpu_to_le16(bp->grp_info[grp_idx].cp_fw_ring_id); + req.rr = cpu_to_le16(bp->grp_info[grp_idx].rx_fw_ring_id); + req.ar = cpu_to_le16(bp->grp_info[grp_idx].agg_fw_ring_id); + req.sc = cpu_to_le16(bp->grp_info[grp_idx].fw_stats_ctx); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) break; - bp->grp_info[i].fw_grp_id = le32_to_cpu(resp->ring_group_id); + bp->grp_info[grp_idx].fw_grp_id = + le32_to_cpu(resp->ring_group_id); } mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -3294,75 +3328,66 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) { int i, rc = 0; - if (bp->cp_nr_rings) { - for (i = 0; i < bp->cp_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_napi *bnapi = bp->bnapi[i]; + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; - rc = hwrm_ring_alloc_send_msg(bp, ring, - HWRM_RING_ALLOC_CMPL, i, - INVALID_STATS_CTX_ID); - if (rc) - goto err_out; - cpr->cp_doorbell = bp->bar1 + i * 0x80; - BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons); - bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; - } + rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_CMPL, i, + INVALID_STATS_CTX_ID); + if (rc) + goto err_out; + cpr->cp_doorbell = bp->bar1 + i * 0x80; + BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons); + bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; } - if (bp->tx_nr_rings) { - for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_tx_ring_info *txr = &bnapi->tx_ring; - struct bnxt_ring_struct *ring = &txr->tx_ring_struct; - u16 fw_stats_ctx = bp->grp_info[i].fw_stats_ctx; + for (i = 0; i < bp->tx_nr_rings; i++) { + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; + struct bnxt_ring_struct *ring = &txr->tx_ring_struct; + u32 map_idx = txr->bnapi->index; + u16 fw_stats_ctx = bp->grp_info[map_idx].fw_stats_ctx; - rc = hwrm_ring_alloc_send_msg(bp, ring, - HWRM_RING_ALLOC_TX, i, - fw_stats_ctx); - if (rc) - goto err_out; - txr->tx_doorbell = bp->bar1 + i * 0x80; - } + rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_TX, + map_idx, fw_stats_ctx); + if (rc) + goto err_out; + txr->tx_doorbell = bp->bar1 + map_idx * 0x80; } - if (bp->rx_nr_rings) { - for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; - struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + u32 map_idx = rxr->bnapi->index; - rc = hwrm_ring_alloc_send_msg(bp, ring, - HWRM_RING_ALLOC_RX, i, - INVALID_STATS_CTX_ID); - if (rc) - goto err_out; - rxr->rx_doorbell = bp->bar1 + i * 0x80; - writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell); - bp->grp_info[i].rx_fw_ring_id = ring->fw_ring_id; - } + rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_RX, + map_idx, INVALID_STATS_CTX_ID); + if (rc) + goto err_out; + rxr->rx_doorbell = bp->bar1 + map_idx * 0x80; + writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell); + bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id; } if (bp->flags & BNXT_FLAG_AGG_RINGS) { for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 map_idx = grp_idx + bp->rx_nr_rings; rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_AGG, - bp->rx_nr_rings + i, + map_idx, INVALID_STATS_CTX_ID); if (rc) goto err_out; - rxr->rx_agg_doorbell = - bp->bar1 + (bp->rx_nr_rings + i) * 0x80; + rxr->rx_agg_doorbell = bp->bar1 + map_idx * 0x80; writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell); - bp->grp_info[i].agg_fw_ring_id = ring->fw_ring_id; + bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id; } } err_out: @@ -3409,91 +3434,75 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, return 0; } -static int bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) +static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) { - int i, rc = 0; + int i; if (!bp->bnapi) - return 0; + return; - if (bp->tx_nr_rings) { - for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_tx_ring_info *txr = &bnapi->tx_ring; - struct bnxt_ring_struct *ring = &txr->tx_ring_struct; - u32 cmpl_ring_id = bp->grp_info[i].cp_fw_ring_id; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - hwrm_ring_free_send_msg( - bp, ring, - RING_FREE_REQ_RING_TYPE_TX, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - } + for (i = 0; i < bp->tx_nr_rings; i++) { + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; + struct bnxt_ring_struct *ring = &txr->tx_ring_struct; + u32 grp_idx = txr->bnapi->index; + u32 cmpl_ring_id = bp->grp_info[grp_idx].cp_fw_ring_id; + + if (ring->fw_ring_id != INVALID_HW_RING_ID) { + hwrm_ring_free_send_msg(bp, ring, + RING_FREE_REQ_RING_TYPE_TX, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; } } - if (bp->rx_nr_rings) { - for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; - struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; - u32 cmpl_ring_id = bp->grp_info[i].cp_fw_ring_id; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - hwrm_ring_free_send_msg( - bp, ring, - RING_FREE_REQ_RING_TYPE_RX, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[i].rx_fw_ring_id = - INVALID_HW_RING_ID; - } + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 cmpl_ring_id = bp->grp_info[grp_idx].cp_fw_ring_id; + + if (ring->fw_ring_id != INVALID_HW_RING_ID) { + hwrm_ring_free_send_msg(bp, ring, + RING_FREE_REQ_RING_TYPE_RX, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[grp_idx].rx_fw_ring_id = + INVALID_HW_RING_ID; } } - if (bp->rx_agg_nr_pages) { - for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_rx_ring_info *rxr = &bnapi->rx_ring; - struct bnxt_ring_struct *ring = - &rxr->rx_agg_ring_struct; - u32 cmpl_ring_id = bp->grp_info[i].cp_fw_ring_id; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - hwrm_ring_free_send_msg( - bp, ring, - RING_FREE_REQ_RING_TYPE_RX, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[i].agg_fw_ring_id = - INVALID_HW_RING_ID; - } + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 cmpl_ring_id = bp->grp_info[grp_idx].cp_fw_ring_id; + + if (ring->fw_ring_id != INVALID_HW_RING_ID) { + hwrm_ring_free_send_msg(bp, ring, + RING_FREE_REQ_RING_TYPE_RX, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[grp_idx].agg_fw_ring_id = + INVALID_HW_RING_ID; } } - if (bp->cp_nr_rings) { - for (i = 0; i < bp->cp_nr_rings; i++) { - struct bnxt_napi *bnapi = bp->bnapi[i]; - struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - hwrm_ring_free_send_msg( - bp, ring, - RING_FREE_REQ_RING_TYPE_CMPL, - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[i].cp_fw_ring_id = - INVALID_HW_RING_ID; - } + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_napi *bnapi = bp->bnapi[i]; + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + + if (ring->fw_ring_id != INVALID_HW_RING_ID) { + hwrm_ring_free_send_msg(bp, ring, + RING_FREE_REQ_RING_TYPE_CMPL, + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[i].cp_fw_ring_id = INVALID_HW_RING_ID; } } - - return rc; } int bnxt_hwrm_set_coal(struct bnxt *bp) @@ -3605,7 +3614,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) return 0; } -static int bnxt_hwrm_func_qcaps(struct bnxt *bp) +int bnxt_hwrm_func_qcaps(struct bnxt *bp) { int rc = 0; struct hwrm_func_qcaps_input req = {0}; @@ -3629,9 +3638,10 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) pf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx); pf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings); pf->max_tx_rings = le16_to_cpu(resp->max_tx_rings); - pf->max_pf_tx_rings = pf->max_tx_rings; pf->max_rx_rings = le16_to_cpu(resp->max_rx_rings); - pf->max_pf_rx_rings = pf->max_rx_rings; + pf->max_hw_ring_grps = le32_to_cpu(resp->max_hw_ring_grps); + if (!pf->max_hw_ring_grps) + pf->max_hw_ring_grps = pf->max_tx_rings; pf->max_l2_ctxs = le16_to_cpu(resp->max_l2_ctxs); pf->max_vnics = le16_to_cpu(resp->max_vnics); pf->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx); @@ -3659,6 +3669,9 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) vf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings); vf->max_tx_rings = le16_to_cpu(resp->max_tx_rings); vf->max_rx_rings = le16_to_cpu(resp->max_rx_rings); + vf->max_hw_ring_grps = le32_to_cpu(resp->max_hw_ring_grps); + if (!vf->max_hw_ring_grps) + vf->max_hw_ring_grps = vf->max_tx_rings; vf->max_l2_ctxs = le16_to_cpu(resp->max_l2_ctxs); vf->max_vnics = le16_to_cpu(resp->max_vnics); vf->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx); @@ -3735,14 +3748,11 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) memcpy(&bp->ver_resp, resp, sizeof(struct hwrm_ver_get_output)); - if (req.hwrm_intf_maj != resp->hwrm_intf_maj || - req.hwrm_intf_min != resp->hwrm_intf_min || - req.hwrm_intf_upd != resp->hwrm_intf_upd) { - netdev_warn(bp->dev, "HWRM interface %d.%d.%d does not match driver interface %d.%d.%d.\n", + if (resp->hwrm_intf_maj < 1) { + netdev_warn(bp->dev, "HWRM interface %d.%d.%d is older than 1.0.0.\n", resp->hwrm_intf_maj, resp->hwrm_intf_min, - resp->hwrm_intf_upd, req.hwrm_intf_maj, - req.hwrm_intf_min, req.hwrm_intf_upd); - netdev_warn(bp->dev, "Please update driver or firmware with matching interface versions.\n"); + resp->hwrm_intf_upd); + netdev_warn(bp->dev, "Please update firmware with HWRM interface 1.0.0 or newer.\n"); } snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "bc %d.%d.%d rm %d.%d.%d", resp->hwrm_fw_maj, resp->hwrm_fw_min, resp->hwrm_fw_bld, @@ -3868,7 +3878,7 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp) break; bp->vnic_info[vnic_id].flags |= BNXT_VNIC_RFS_FLAG; - rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, ring_id, ring_id + 1); + rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, ring_id, 1); if (rc) { netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n", vnic_id, rc); @@ -3945,8 +3955,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) } bp->vnic_info[0].uc_filter_count = 1; - bp->vnic_info[0].rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_UNICAST | - CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; + bp->vnic_info[0].rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; if ((bp->dev->flags & IFF_PROMISC) && BNXT_PF(bp)) bp->vnic_info[0].rx_mask |= @@ -4027,20 +4036,42 @@ static int bnxt_set_real_num_queues(struct bnxt *bp) return rc; #ifdef CONFIG_RFS_ACCEL - if (bp->rx_nr_rings) + if (bp->flags & BNXT_FLAG_RFS) dev->rx_cpu_rmap = alloc_irq_cpu_rmap(bp->rx_nr_rings); - if (!dev->rx_cpu_rmap) - rc = -ENOMEM; #endif return rc; } +static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max, + bool shared) +{ + int _rx = *rx, _tx = *tx; + + if (shared) { + *rx = min_t(int, _rx, max); + *tx = min_t(int, _tx, max); + } else { + if (max < 2) + return -ENOMEM; + + while (_rx + _tx > max) { + if (_rx > _tx && _rx > 1) + _rx--; + else if (_tx > 1) + _tx--; + } + *rx = _rx; + *tx = _tx; + } + return 0; +} + static int bnxt_setup_msix(struct bnxt *bp) { struct msix_entry *msix_ent; struct net_device *dev = bp->dev; - int i, total_vecs, rc = 0; + int i, total_vecs, rc = 0, min = 1; const int len = sizeof(bp->irq_tbl[0].name); bp->flags &= ~BNXT_FLAG_USING_MSIX; @@ -4055,7 +4086,10 @@ static int bnxt_setup_msix(struct bnxt *bp) msix_ent[i].vector = 0; } - total_vecs = pci_enable_msix_range(bp->pdev, msix_ent, 1, total_vecs); + if (!(bp->flags & BNXT_FLAG_SHARED_RINGS)) + min = 2; + + total_vecs = pci_enable_msix_range(bp->pdev, msix_ent, min, total_vecs); if (total_vecs < 0) { rc = -ENODEV; goto msix_setup_exit; @@ -4066,8 +4100,11 @@ static int bnxt_setup_msix(struct bnxt *bp) int tcs; /* Trim rings based upon num of vectors allocated */ - bp->rx_nr_rings = min_t(int, total_vecs, bp->rx_nr_rings); - bp->tx_nr_rings = min_t(int, total_vecs, bp->tx_nr_rings); + rc = bnxt_trim_rings(bp, &bp->rx_nr_rings, &bp->tx_nr_rings, + total_vecs, min == 1); + if (rc) + goto msix_setup_exit; + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; tcs = netdev_get_num_tc(dev); if (tcs > 1) { @@ -4086,12 +4123,21 @@ static int bnxt_setup_msix(struct bnxt *bp) } } } - bp->cp_nr_rings = max_t(int, bp->rx_nr_rings, bp->tx_nr_rings); + bp->cp_nr_rings = total_vecs; for (i = 0; i < bp->cp_nr_rings; i++) { + char *attr; + bp->irq_tbl[i].vector = msix_ent[i].vector; + if (bp->flags & BNXT_FLAG_SHARED_RINGS) + attr = "TxRx"; + else if (i < bp->rx_nr_rings) + attr = "rx"; + else + attr = "tx"; + snprintf(bp->irq_tbl[i].name, len, - "%s-%s-%d", dev->name, "TxRx", i); + "%s-%s-%d", dev->name, attr, i); bp->irq_tbl[i].handler = bnxt_msix; } rc = bnxt_set_real_num_queues(bp); @@ -4129,6 +4175,7 @@ static int bnxt_setup_inta(struct bnxt *bp) bp->tx_nr_rings = 1; bp->cp_nr_rings = 1; bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + bp->flags |= BNXT_FLAG_SHARED_RINGS; bp->irq_tbl[0].vector = bp->pdev->irq; snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx", 0); @@ -4177,7 +4224,7 @@ static void bnxt_free_irq(struct bnxt *bp) static int bnxt_request_irq(struct bnxt *bp) { - int i, rc = 0; + int i, j, rc = 0; unsigned long flags = 0; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap = bp->dev->rx_cpu_rmap; @@ -4186,14 +4233,15 @@ static int bnxt_request_irq(struct bnxt *bp) if (!(bp->flags & BNXT_FLAG_USING_MSIX)) flags = IRQF_SHARED; - for (i = 0; i < bp->cp_nr_rings; i++) { + for (i = 0, j = 0; i < bp->cp_nr_rings; i++) { struct bnxt_irq *irq = &bp->irq_tbl[i]; #ifdef CONFIG_RFS_ACCEL - if (rmap && (i < bp->rx_nr_rings)) { + if (rmap && bp->bnapi[i]->rx_ring) { rc = irq_cpu_rmap_add(rmap, irq->vector); if (rc) netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n", - i); + j); + j++; } #endif rc = request_irq(irq->vector, irq->handler, flags, irq->name, @@ -4264,14 +4312,12 @@ static void bnxt_enable_napi(struct bnxt *bp) static void bnxt_tx_disable(struct bnxt *bp) { int i; - struct bnxt_napi *bnapi; struct bnxt_tx_ring_info *txr; struct netdev_queue *txq; - if (bp->bnapi) { + if (bp->tx_ring) { for (i = 0; i < bp->tx_nr_rings; i++) { - bnapi = bp->bnapi[i]; - txr = &bnapi->tx_ring; + txr = &bp->tx_ring[i]; txq = netdev_get_tx_queue(bp->dev, i); __netif_tx_lock(txq, smp_processor_id()); txr->dev_state = BNXT_DEV_STATE_CLOSING; @@ -4286,13 +4332,11 @@ static void bnxt_tx_disable(struct bnxt *bp) static void bnxt_tx_enable(struct bnxt *bp) { int i; - struct bnxt_napi *bnapi; struct bnxt_tx_ring_info *txr; struct netdev_queue *txq; for (i = 0; i < bp->tx_nr_rings; i++) { - bnapi = bp->bnapi[i]; - txr = &bnapi->tx_ring; + txr = &bp->tx_ring[i]; txq = netdev_get_tx_queue(bp->dev, i); txr->dev_state = 0; } @@ -4354,7 +4398,7 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state) link_info->auto_mode = resp->auto_mode; link_info->auto_pause_setting = resp->auto_pause; link_info->force_pause_setting = resp->force_pause; - link_info->duplex_setting = resp->duplex_setting; + link_info->duplex_setting = resp->duplex; if (link_info->phy_link_status == BNXT_LINK_LINK) link_info->link_speed = le16_to_cpu(resp->link_speed); else @@ -4601,7 +4645,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) bp->nge_port_cnt = 1; } - bp->state = BNXT_STATE_OPEN; + set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); /* Enable TX queues */ bnxt_tx_enable(bp); @@ -4677,8 +4721,10 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* Change device state to avoid TX queue wake up's */ bnxt_tx_disable(bp); - bp->state = BNXT_STATE_CLOSED; - cancel_work_sync(&bp->sp_task); + clear_bit(BNXT_STATE_OPEN, &bp->state); + smp_mb__after_atomic(); + while (test_bit(BNXT_STATE_IN_SP_TASK, &bp->state)) + msleep(20); /* Flush rings before disabling interrupts */ bnxt_shutdown_nic(bp, irq_re_init); @@ -4929,9 +4975,32 @@ skip_uc: return rc; } +static bool bnxt_rfs_capable(struct bnxt *bp) +{ +#ifdef CONFIG_RFS_ACCEL + struct bnxt_pf_info *pf = &bp->pf; + int vnics; + + if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_MSIX_CAP)) + return false; + + vnics = 1 + bp->rx_nr_rings; + if (vnics > pf->max_rsscos_ctxs || vnics > pf->max_vnics) + return false; + + return true; +#else + return false; +#endif +} + static netdev_features_t bnxt_fix_features(struct net_device *dev, netdev_features_t features) { + struct bnxt *bp = netdev_priv(dev); + + if (!bnxt_rfs_capable(bp)) + features &= ~NETIF_F_NTUPLE; return features; } @@ -4972,7 +5041,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) bp->flags = flags; - if (!netif_running(dev)) { + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_tpa) bnxt_set_ring_params(bp); return rc; @@ -4996,31 +5065,53 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) return rc; } +static void bnxt_dump_tx_sw_state(struct bnxt_napi *bnapi) +{ + struct bnxt_tx_ring_info *txr = bnapi->tx_ring; + int i = bnapi->index; + + if (!txr) + return; + + netdev_info(bnapi->bp->dev, "[%d]: tx{fw_ring: %d prod: %x cons: %x}\n", + i, txr->tx_ring_struct.fw_ring_id, txr->tx_prod, + txr->tx_cons); +} + +static void bnxt_dump_rx_sw_state(struct bnxt_napi *bnapi) +{ + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; + int i = bnapi->index; + + if (!rxr) + return; + + netdev_info(bnapi->bp->dev, "[%d]: rx{fw_ring: %d prod: %x} rx_agg{fw_ring: %d agg_prod: %x sw_agg_prod: %x}\n", + i, rxr->rx_ring_struct.fw_ring_id, rxr->rx_prod, + rxr->rx_agg_ring_struct.fw_ring_id, rxr->rx_agg_prod, + rxr->rx_sw_agg_prod); +} + +static void bnxt_dump_cp_sw_state(struct bnxt_napi *bnapi) +{ + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + int i = bnapi->index; + + netdev_info(bnapi->bp->dev, "[%d]: cp{fw_ring: %d raw_cons: %x}\n", + i, cpr->cp_ring_struct.fw_ring_id, cpr->cp_raw_cons); +} + static void bnxt_dbg_dump_states(struct bnxt *bp) { int i; struct bnxt_napi *bnapi; - struct bnxt_tx_ring_info *txr; - struct bnxt_rx_ring_info *rxr; - struct bnxt_cp_ring_info *cpr; for (i = 0; i < bp->cp_nr_rings; i++) { bnapi = bp->bnapi[i]; - txr = &bnapi->tx_ring; - rxr = &bnapi->rx_ring; - cpr = &bnapi->cp_ring; if (netif_msg_drv(bp)) { - netdev_info(bp->dev, "[%d]: tx{fw_ring: %d prod: %x cons: %x}\n", - i, txr->tx_ring_struct.fw_ring_id, - txr->tx_prod, txr->tx_cons); - netdev_info(bp->dev, "[%d]: rx{fw_ring: %d prod: %x} rx_agg{fw_ring: %d agg_prod: %x sw_agg_prod: %x}\n", - i, rxr->rx_ring_struct.fw_ring_id, - rxr->rx_prod, - rxr->rx_agg_ring_struct.fw_ring_id, - rxr->rx_agg_prod, rxr->rx_sw_agg_prod); - netdev_info(bp->dev, "[%d]: cp{fw_ring: %d raw_cons: %x}\n", - i, cpr->cp_ring_struct.fw_ring_id, - cpr->cp_raw_cons); + bnxt_dump_tx_sw_state(bnapi); + bnxt_dump_rx_sw_state(bnapi); + bnxt_dump_cp_sw_state(bnapi); } } } @@ -5028,8 +5119,10 @@ static void bnxt_dbg_dump_states(struct bnxt *bp) static void bnxt_reset_task(struct bnxt *bp) { bnxt_dbg_dump_states(bp); - if (netif_running(bp->dev)) - bnxt_tx_disable(bp); /* prevent tx timout again */ + if (netif_running(bp->dev)) { + bnxt_close_nic(bp, false, false); + bnxt_open_nic(bp, false, false); + } } static void bnxt_tx_timeout(struct net_device *dev) @@ -5079,8 +5172,12 @@ static void bnxt_sp_task(struct work_struct *work) struct bnxt *bp = container_of(work, struct bnxt, sp_task); int rc; - if (bp->state != BNXT_STATE_OPEN) + set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + smp_mb__after_atomic(); + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); return; + } if (test_and_clear_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event)) bnxt_cfg_rx_mode(bp); @@ -5104,8 +5201,19 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_hwrm_tunnel_dst_port_free( bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN); } - if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) + if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) { + /* bnxt_reset_task() calls bnxt_close_nic() which waits + * for BNXT_STATE_IN_SP_TASK to clear. + */ + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + rtnl_lock(); bnxt_reset_task(bp); + set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + rtnl_unlock(); + } + + smp_mb__before_atomic(); + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); } static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) @@ -5184,7 +5292,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) bp->timer.function = bnxt_timer; bp->current_interval = BNXT_TIMER_INTERVAL; - bp->state = BNXT_STATE_CLOSED; + clear_bit(BNXT_STATE_OPEN, &bp->state); return 0; @@ -5274,10 +5382,14 @@ static int bnxt_setup_tc(struct net_device *dev, u8 tc) return 0; if (tc) { - int max_rx_rings, max_tx_rings; + int max_rx_rings, max_tx_rings, rc; + bool sh = false; + + if (bp->flags & BNXT_FLAG_SHARED_RINGS) + sh = true; - bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings); - if (bp->tx_nr_rings_per_tc * tc > max_tx_rings) + rc = bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh); + if (rc || bp->tx_nr_rings_per_tc * tc > max_tx_rings) return -ENOMEM; } @@ -5531,6 +5643,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) cancel_work_sync(&bp->sp_task); bp->sp_event = 0; + bnxt_hwrm_func_drv_unrgtr(bp); bnxt_free_hwrm_resources(bp); pci_iounmap(pdev, bp->bar2); pci_iounmap(pdev, bp->bar1); @@ -5590,28 +5703,62 @@ static int bnxt_get_max_irq(struct pci_dev *pdev) return (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1; } -void bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx) +static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, + int *max_cp) { - int max_rings = 0; + int max_ring_grps = 0; if (BNXT_PF(bp)) { - *max_tx = bp->pf.max_pf_tx_rings; - *max_rx = bp->pf.max_pf_rx_rings; - max_rings = min_t(int, bp->pf.max_irqs, bp->pf.max_cp_rings); - max_rings = min_t(int, max_rings, bp->pf.max_stat_ctxs); + *max_tx = bp->pf.max_tx_rings; + *max_rx = bp->pf.max_rx_rings; + *max_cp = min_t(int, bp->pf.max_irqs, bp->pf.max_cp_rings); + *max_cp = min_t(int, *max_cp, bp->pf.max_stat_ctxs); + max_ring_grps = bp->pf.max_hw_ring_grps; } else { #ifdef CONFIG_BNXT_SRIOV *max_tx = bp->vf.max_tx_rings; *max_rx = bp->vf.max_rx_rings; - max_rings = min_t(int, bp->vf.max_irqs, bp->vf.max_cp_rings); - max_rings = min_t(int, max_rings, bp->vf.max_stat_ctxs); + *max_cp = min_t(int, bp->vf.max_irqs, bp->vf.max_cp_rings); + *max_cp = min_t(int, *max_cp, bp->vf.max_stat_ctxs); + max_ring_grps = bp->vf.max_hw_ring_grps; #endif } if (bp->flags & BNXT_FLAG_AGG_RINGS) *max_rx >>= 1; + *max_rx = min_t(int, *max_rx, max_ring_grps); +} + +int bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, bool shared) +{ + int rx, tx, cp; + + _bnxt_get_max_rings(bp, &rx, &tx, &cp); + if (!rx || !tx || !cp) + return -ENOMEM; - *max_rx = min_t(int, *max_rx, max_rings); - *max_tx = min_t(int, *max_tx, max_rings); + *max_rx = rx; + *max_tx = tx; + return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared); +} + +static int bnxt_set_dflt_rings(struct bnxt *bp) +{ + int dflt_rings, max_rx_rings, max_tx_rings, rc; + bool sh = true; + + if (sh) + bp->flags |= BNXT_FLAG_SHARED_RINGS; + dflt_rings = netif_get_num_default_rss_queues(); + rc = bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh); + if (rc) + return rc; + bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings); + bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings); + bp->tx_nr_rings = bp->tx_nr_rings_per_tc; + bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) : + bp->tx_nr_rings + bp->rx_nr_rings; + bp->num_stat_ctxs = bp->cp_nr_rings; + return rc; } static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -5619,7 +5766,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) static int version_printed; struct net_device *dev; struct bnxt *bp; - int rc, max_rx_rings, max_tx_rings, max_irqs, dflt_rings; + int rc, max_irqs; if (version_printed++ == 0) pr_info("%s", version); @@ -5634,11 +5781,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (bnxt_vf_pciid(ent->driver_data)) bp->flags |= BNXT_FLAG_VF; - if (pdev->msix_cap) { + if (pdev->msix_cap) bp->flags |= BNXT_FLAG_MSIX_CAP; - if (BNXT_PF(bp)) - bp->flags |= BNXT_FLAG_RFS; - } rc = bnxt_init_board(pdev, dev); if (rc < 0) @@ -5657,9 +5801,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_RXHASH | NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO; - if (bp->flags & BNXT_FLAG_RFS) - dev->hw_features |= NETIF_F_NTUPLE; - dev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | @@ -5704,19 +5845,21 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_set_tpa_flags(bp); bnxt_set_ring_params(bp); - dflt_rings = netif_get_num_default_rss_queues(); if (BNXT_PF(bp)) bp->pf.max_irqs = max_irqs; #if defined(CONFIG_BNXT_SRIOV) else bp->vf.max_irqs = max_irqs; #endif - bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings); - bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings); - bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings); - bp->tx_nr_rings = bp->tx_nr_rings_per_tc; - bp->cp_nr_rings = max_t(int, bp->rx_nr_rings, bp->tx_nr_rings); - bp->num_stat_ctxs = bp->cp_nr_rings; + bnxt_set_dflt_rings(bp); + + if (BNXT_PF(bp)) { + dev->hw_features |= NETIF_F_NTUPLE; + if (bnxt_rfs_capable(bp)) { + bp->flags |= BNXT_FLAG_RFS; + dev->features |= NETIF_F_NTUPLE; + } + } if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX) bp->flags |= BNXT_FLAG_STRIP_VLAN; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 674bc5159b91c..8af3ca8efcef9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -11,11 +11,11 @@ #define BNXT_H #define DRV_MODULE_NAME "bnxt_en" -#define DRV_MODULE_VERSION "0.1.24" +#define DRV_MODULE_VERSION "1.0.0" -#define DRV_VER_MAJ 0 -#define DRV_VER_MIN 1 -#define DRV_VER_UPD 24 +#define DRV_VER_MAJ 1 +#define DRV_VER_MIN 0 +#define DRV_VER_UPD 0 struct tx_bd { __le32 tx_bd_len_flags_type; @@ -528,6 +528,7 @@ struct tx_push_bd { }; struct bnxt_tx_ring_info { + struct bnxt_napi *bnapi; u16 tx_prod; u16 tx_cons; void __iomem *tx_doorbell; @@ -558,6 +559,7 @@ struct bnxt_tpa_info { }; struct bnxt_rx_ring_info { + struct bnxt_napi *bnapi; u16 rx_prod; u16 rx_agg_prod; u16 rx_sw_agg_prod; @@ -604,8 +606,8 @@ struct bnxt_napi { int index; struct bnxt_cp_ring_info cp_ring; - struct bnxt_rx_ring_info rx_ring; - struct bnxt_tx_ring_info tx_ring; + struct bnxt_rx_ring_info *rx_ring; + struct bnxt_tx_ring_info *tx_ring; #ifdef CONFIG_NET_RX_BUSY_POLL atomic_t poll_state; @@ -695,6 +697,7 @@ struct bnxt_vf_info { u16 max_cp_rings; u16 max_tx_rings; u16 max_rx_rings; + u16 max_hw_ring_grps; u16 max_l2_ctxs; u16 max_irqs; u16 max_vnics; @@ -722,9 +725,8 @@ struct bnxt_pf_info { u16 max_rsscos_ctxs; u16 max_cp_rings; u16 max_tx_rings; /* HW assigned max tx rings for this PF */ - u16 max_pf_tx_rings; /* runtime max tx rings owned by PF */ u16 max_rx_rings; /* HW assigned max rx rings for this PF */ - u16 max_pf_rx_rings; /* runtime max rx rings owned by PF */ + u16 max_hw_ring_grps; u16 max_irqs; u16 max_l2_ctxs; u16 max_vnics; @@ -875,6 +877,8 @@ struct bnxt { #define BNXT_FLAG_USING_MSIX 0x40 #define BNXT_FLAG_MSIX_CAP 0x80 #define BNXT_FLAG_RFS 0x100 + #define BNXT_FLAG_SHARED_RINGS 0x200 + #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ BNXT_FLAG_RFS | \ BNXT_FLAG_STRIP_VLAN) @@ -884,6 +888,9 @@ struct bnxt { struct bnxt_napi **bnapi; + struct bnxt_rx_ring_info *rx_ring; + struct bnxt_tx_ring_info *tx_ring; + u32 rx_buf_size; u32 rx_buf_use_size; /* useable size */ u32 rx_ring_size; @@ -913,6 +920,8 @@ struct bnxt { int cp_nr_rings; int num_stat_ctxs; + + /* grp_info indexed by completion ring index */ struct bnxt_ring_grp_info *grp_info; struct bnxt_vnic_info *vnic_info; int nr_vnics; @@ -925,9 +934,9 @@ struct bnxt { struct timer_list timer; - int state; -#define BNXT_STATE_CLOSED 0 -#define BNXT_STATE_OPEN 1 + unsigned long state; +#define BNXT_STATE_OPEN 0 +#define BNXT_STATE_IN_SP_TASK 1 struct bnxt_irq *irq_tbl; u8 mac_addr[ETH_ALEN]; @@ -1084,9 +1093,10 @@ void bnxt_hwrm_cmd_hdr_init(struct bnxt *, void *, u16, u16, u16); int _hwrm_send_message(struct bnxt *, void *, u32, int); int hwrm_send_message(struct bnxt *, void *, u32, int); int bnxt_hwrm_set_coal(struct bnxt *); +int bnxt_hwrm_func_qcaps(struct bnxt *); int bnxt_hwrm_set_pause(struct bnxt *); int bnxt_hwrm_set_link_setting(struct bnxt *, bool); int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_close_nic(struct bnxt *, bool, bool); -void bnxt_get_max_rings(struct bnxt *, int *, int *); +int bnxt_get_max_rings(struct bnxt *, int *, int *, bool); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 45bd628eaf3aa..4f62c9fa96d58 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -211,7 +211,10 @@ static void bnxt_get_channels(struct net_device *dev, struct bnxt *bp = netdev_priv(dev); int max_rx_rings, max_tx_rings, tcs; - bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings); + bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, true); + channel->max_combined = max_rx_rings; + + bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, false); tcs = netdev_get_num_tc(dev); if (tcs > 1) max_tx_rings /= tcs; @@ -219,9 +222,12 @@ static void bnxt_get_channels(struct net_device *dev, channel->max_rx = max_rx_rings; channel->max_tx = max_tx_rings; channel->max_other = 0; - channel->max_combined = 0; - channel->rx_count = bp->rx_nr_rings; - channel->tx_count = bp->tx_nr_rings_per_tc; + if (bp->flags & BNXT_FLAG_SHARED_RINGS) { + channel->combined_count = bp->rx_nr_rings; + } else { + channel->rx_count = bp->rx_nr_rings; + channel->tx_count = bp->tx_nr_rings_per_tc; + } } static int bnxt_set_channels(struct net_device *dev, @@ -230,19 +236,35 @@ static int bnxt_set_channels(struct net_device *dev, struct bnxt *bp = netdev_priv(dev); int max_rx_rings, max_tx_rings, tcs; u32 rc = 0; + bool sh = false; + + if (channel->other_count) + return -EINVAL; - if (channel->other_count || channel->combined_count || - !channel->rx_count || !channel->tx_count) + if (!channel->combined_count && + (!channel->rx_count || !channel->tx_count)) return -EINVAL; - bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings); + if (channel->combined_count && + (channel->rx_count || channel->tx_count)) + return -EINVAL; + + if (channel->combined_count) + sh = true; + + bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh); + tcs = netdev_get_num_tc(dev); if (tcs > 1) max_tx_rings /= tcs; - if (channel->rx_count > max_rx_rings || - channel->tx_count > max_tx_rings) - return -EINVAL; + if (sh && (channel->combined_count > max_rx_rings || + channel->combined_count > max_tx_rings)) + return -ENOMEM; + + if (!sh && (channel->rx_count > max_rx_rings || + channel->tx_count > max_tx_rings)) + return -ENOMEM; if (netif_running(dev)) { if (BNXT_PF(bp)) { @@ -258,14 +280,27 @@ static int bnxt_set_channels(struct net_device *dev, } } - bp->rx_nr_rings = channel->rx_count; - bp->tx_nr_rings_per_tc = channel->tx_count; + if (sh) { + bp->flags |= BNXT_FLAG_SHARED_RINGS; + bp->rx_nr_rings = channel->combined_count; + bp->tx_nr_rings_per_tc = channel->combined_count; + } else { + bp->flags &= ~BNXT_FLAG_SHARED_RINGS; + bp->rx_nr_rings = channel->rx_count; + bp->tx_nr_rings_per_tc = channel->tx_count; + } + bp->tx_nr_rings = bp->tx_nr_rings_per_tc; if (tcs > 1) bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs; - bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings); + + bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) : + bp->tx_nr_rings + bp->rx_nr_rings; + bp->num_stat_ctxs = bp->cp_nr_rings; + /* After changing number of rx channels, update NTUPLE feature. */ + netdev_update_features(dev); if (netif_running(dev)) { rc = bnxt_open_nic(bp, true, false); if ((!rc) && BNXT_PF(bp)) { @@ -818,6 +853,9 @@ static int bnxt_flash_firmware(struct net_device *dev, case BNX_DIR_TYPE_BOOTCODE_2: code_type = CODE_BOOT; break; + case BNX_DIR_TYPE_APE_FW: + code_type = CODE_MCTP_PASSTHRU; + break; default: netdev_err(dev, "Unsupported directory entry type: %u\n", dir_type); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 70fc8253c07fc..4badbedcb4217 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -103,19 +103,22 @@ struct hwrm_async_event_cmpl { #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE (0x2UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE (0x3UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED (0x4UL << 0) + #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_NOT_ALLOWED (0x5UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD (0x10UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD (0x11UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD (0x20UL << 0) - #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_LOAD (0x20UL << 0) + #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_LOAD (0x21UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_VF_FLR (0x30UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE (0x31UL << 0) + #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE (0x32UL << 0) #define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR (0xffUL << 0) __le32 event_data2; u8 opaque_v; #define HWRM_ASYNC_EVENT_CMPL_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; }; @@ -132,9 +135,16 @@ struct hwrm_async_event_cmpl_link_status_change { #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; - #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_UP 0x1UL + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE 0x1UL + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_DOWN (0x0UL << 0) + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP (0x1UL << 0) + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_MASK 0xeUL + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT 1 + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK 0xffff0UL + #define HWRM_ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT 4 }; /* HWRM Asynchronous Event Completion Record for link MTU change (16 bytes) */ @@ -150,7 +160,8 @@ struct hwrm_async_event_cmpl_link_mtu_change { #define HWRM_ASYNC_EVENT_CMPL_LINK_MTU_CHANGE_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_LINK_MTU_CHANGE_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_LINK_MTU_CHANGE_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_LINK_MTU_CHANGE_EVENT_DATA1_NEW_MTU_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_LINK_MTU_CHANGE_EVENT_DATA1_NEW_MTU_SFT 0 @@ -169,7 +180,8 @@ struct hwrm_async_event_cmpl_link_speed_change { #define HWRM_ASYNC_EVENT_CMPL_LINK_SPEED_CHANGE_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_LINK_SPEED_CHANGE_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_LINK_SPEED_CHANGE_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_LINK_SPEED_CHANGE_EVENT_DATA1_FORCE 0x1UL #define HWRM_ASYNC_EVENT_CMPL_LINK_SPEED_CHANGE_EVENT_DATA1_NEW_LINK_SPEED_100MBPS_MASK 0xfffeUL @@ -200,7 +212,8 @@ struct hwrm_async_event_cmpl_dcb_config_change { #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_PORT_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_PORT_ID_SFT 0 @@ -219,7 +232,8 @@ struct hwrm_async_event_cmpl_port_conn_not_allowed { #define HWRM_ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_SFT 0 @@ -238,7 +252,8 @@ struct hwrm_async_event_cmpl_func_drvr_unload { #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_UNLOAD_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_UNLOAD_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_UNLOAD_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_UNLOAD_EVENT_DATA1_FUNC_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_UNLOAD_EVENT_DATA1_FUNC_ID_SFT 0 @@ -257,7 +272,8 @@ struct hwrm_async_event_cmpl_func_drvr_load { #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_LOAD_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_LOAD_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_LOAD_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_LOAD_EVENT_DATA1_FUNC_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_FUNC_DRVR_LOAD_EVENT_DATA1_FUNC_ID_SFT 0 @@ -276,10 +292,13 @@ struct hwrm_async_event_cmpl_pf_drvr_unload { #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_EVENT_DATA1_FUNC_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_EVENT_DATA1_FUNC_ID_SFT 0 + #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_EVENT_DATA1_PORT_MASK 0x70000UL + #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_UNLOAD_EVENT_DATA1_PORT_SFT 16 }; /* HWRM Asynchronous Event Completion Record for PF Driver load (16 bytes) */ @@ -289,16 +308,19 @@ struct hwrm_async_event_cmpl_pf_drvr_load { #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_TYPE_SFT 0 #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_TYPE_HWRM_ASYNC_EVENT (0x2eUL << 0) __le16 event_id; - #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_EVENT_ID_PF_DRVR_LOAD (0x20UL << 0) + #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_EVENT_ID_PF_DRVR_LOAD (0x21UL << 0) __le32 event_data2; u8 opaque_v; #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_EVENT_DATA1_FUNC_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_EVENT_DATA1_FUNC_ID_SFT 0 + #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_EVENT_DATA1_PORT_MASK 0x70000UL + #define HWRM_ASYNC_EVENT_CMPL_PF_DRVR_LOAD_EVENT_DATA1_PORT_SFT 16 }; /* HWRM Asynchronous Event Completion Record for VF FLR (16 bytes) */ @@ -314,7 +336,8 @@ struct hwrm_async_event_cmpl_vf_flr { #define HWRM_ASYNC_EVENT_CMPL_VF_FLR_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_VF_FLR_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_VF_FLR_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_VF_FLR_EVENT_DATA1_VF_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_VF_FLR_EVENT_DATA1_VF_ID_SFT 0 @@ -333,7 +356,8 @@ struct hwrm_async_event_cmpl_vf_mac_addr_change { #define HWRM_ASYNC_EVENT_CMPL_VF_MAC_ADDR_CHANGE_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_VF_MAC_ADDR_CHANGE_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_VF_MAC_ADDR_CHANGE_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_VF_MAC_ADDR_CHANGE_EVENT_DATA1_VF_ID_MASK 0xffffUL #define HWRM_ASYNC_EVENT_CMPL_VF_MAC_ADDR_CHANGE_EVENT_DATA1_VF_ID_SFT 0 @@ -357,18 +381,20 @@ struct hwrm_async_event_cmpl_hwrm_error { #define HWRM_ASYNC_EVENT_CMPL_HWRM_ERROR_V 0x1UL #define HWRM_ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_MASK 0xfeUL #define HWRM_ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_SFT 1 - u8 unused_1[3]; + u8 timestamp_lo; + __le16 timestamp_hi; __le32 event_data1; #define HWRM_ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP 0x1UL }; -/* HW Resource Manager Specification 0.7.8 */ -#define HWRM_VERSION_MAJOR 0 -#define HWRM_VERSION_MINOR 7 -#define HWRM_VERSION_UPDATE 8 +/* HW Resource Manager Specification 1.0.0 */ +#define HWRM_VERSION_MAJOR 1 +#define HWRM_VERSION_MINOR 0 +#define HWRM_VERSION_UPDATE 0 -#define HWRM_VERSION_STR "0.7.8" -/* Following is the signature for HWRM message field that indicates not +#define HWRM_VERSION_STR "1.0.0" +/* + * Following is the signature for HWRM message field that indicates not * applicable (All F's). Need to cast it the size of the field if needed. */ #define HWRM_NA_SIGNATURE ((__le32)(-1)) @@ -398,7 +424,9 @@ struct output { struct cmd_nums { __le16 req_type; #define HWRM_VER_GET (0x0UL) - #define HWRM_FUNC_DISABLE (0x10UL) + #define HWRM_FUNC_BUF_UNRGTR (0xeUL) + #define HWRM_FUNC_VF_CFG (0xfUL) + #define RESERVED1 (0x10UL) #define HWRM_FUNC_RESET (0x11UL) #define HWRM_FUNC_GETFID (0x12UL) #define HWRM_FUNC_VF_ALLOC (0x13UL) @@ -414,10 +442,9 @@ struct cmd_nums { #define HWRM_FUNC_DRV_RGTR (0x1dUL) #define HWRM_FUNC_DRV_QVER (0x1eUL) #define HWRM_FUNC_BUF_RGTR (0x1fUL) - #define HWRM_FUNC_VF_CFG (0x20UL) #define HWRM_PORT_PHY_CFG (0x20UL) #define HWRM_PORT_MAC_CFG (0x21UL) - #define HWRM_PORT_ENABLE (0x22UL) + #define RESERVED2 (0x22UL) #define HWRM_PORT_QSTATS (0x23UL) #define HWRM_PORT_LPBK_QSTATS (0x24UL) #define HWRM_PORT_CLR_STATS (0x25UL) @@ -455,13 +482,11 @@ struct cmd_nums { #define HWRM_RING_GRP_FREE (0x61UL) #define HWRM_VNIC_RSS_COS_LB_CTX_ALLOC (0x70UL) #define HWRM_VNIC_RSS_COS_LB_CTX_FREE (0x71UL) - #define HWRM_ARB_GRP_ALLOC (0x80UL) - #define HWRM_ARB_GRP_CFG (0x81UL) #define HWRM_CFA_L2_FILTER_ALLOC (0x90UL) #define HWRM_CFA_L2_FILTER_FREE (0x91UL) #define HWRM_CFA_L2_FILTER_CFG (0x92UL) #define HWRM_CFA_L2_SET_RX_MASK (0x93UL) - #define HWRM_CFA_L2_SET_BCASTMCAST_MIRRORING (0x94UL) + #define RESERVED3 (0x94UL) #define HWRM_CFA_TUNNEL_FILTER_ALLOC (0x95UL) #define HWRM_CFA_TUNNEL_FILTER_FREE (0x96UL) #define HWRM_CFA_ENCAP_RECORD_ALLOC (0x97UL) @@ -469,6 +494,9 @@ struct cmd_nums { #define HWRM_CFA_NTUPLE_FILTER_ALLOC (0x99UL) #define HWRM_CFA_NTUPLE_FILTER_FREE (0x9aUL) #define HWRM_CFA_NTUPLE_FILTER_CFG (0x9bUL) + #define HWRM_CFA_EM_FLOW_ALLOC (0x9cUL) + #define HWRM_CFA_EM_FLOW_FREE (0x9dUL) + #define HWRM_CFA_EM_FLOW_CFG (0x9eUL) #define HWRM_TUNNEL_DST_PORT_QUERY (0xa0UL) #define HWRM_TUNNEL_DST_PORT_ALLOC (0xa1UL) #define HWRM_TUNNEL_DST_PORT_FREE (0xa2UL) @@ -483,8 +511,6 @@ struct cmd_nums { #define HWRM_FWD_RESP (0xd2UL) #define HWRM_FWD_ASYNC_EVENT_CMPL (0xd3UL) #define HWRM_TEMP_MONITOR_QUERY (0xe0UL) - #define HWRM_MGMT_L2_FILTER_ALLOC (0x100UL) - #define HWRM_MGMT_L2_FILTER_FREE (0x101UL) #define HWRM_DBG_READ_DIRECT (0xff10UL) #define HWRM_DBG_READ_INDIRECT (0xff11UL) #define HWRM_DBG_WRITE_DIRECT (0xff12UL) @@ -505,7 +531,6 @@ struct cmd_nums { __le16 unused_0[3]; }; -/* Return Codes (8 bytes) */ struct ret_codes { __le16 error_code; #define HWRM_ERR_CODE_SUCCESS (0x0UL) @@ -529,7 +554,7 @@ struct hwrm_err_output { __le16 resp_len; __le32 opaque_0; __le16 opaque_1; - u8 opaque_2; + u8 cmd_err; u8 valid; }; @@ -686,65 +711,38 @@ struct hwrm_ver_get_output { u8 hwrm_fw_min; u8 hwrm_fw_bld; u8 hwrm_fw_rsvd; - u8 ape_fw_maj; - u8 ape_fw_min; - u8 ape_fw_bld; - u8 ape_fw_rsvd; - u8 kong_fw_maj; - u8 kong_fw_min; - u8 kong_fw_bld; - u8 kong_fw_rsvd; - u8 tang_fw_maj; - u8 tang_fw_min; - u8 tang_fw_bld; - u8 tang_fw_rsvd; - u8 bono_fw_maj; - u8 bono_fw_min; - u8 bono_fw_bld; - u8 bono_fw_rsvd; + u8 mgmt_fw_maj; + u8 mgmt_fw_min; + u8 mgmt_fw_bld; + u8 mgmt_fw_rsvd; + u8 netctrl_fw_maj; + u8 netctrl_fw_min; + u8 netctrl_fw_bld; + u8 netctrl_fw_rsvd; + __le32 reserved1; + u8 roce_fw_maj; + u8 roce_fw_min; + u8 roce_fw_bld; + u8 roce_fw_rsvd; char hwrm_fw_name[16]; - char ape_fw_name[16]; - char kong_fw_name[16]; - char tang_fw_name[16]; - char bono_fw_name[16]; + char mgmt_fw_name[16]; + char netctrl_fw_name[16]; + __le32 reserved2[4]; + char roce_fw_name[16]; __le16 chip_num; u8 chip_rev; u8 chip_metal; u8 chip_bond_id; - u8 unused_0; + u8 chip_platform_type; + #define VER_GET_RESP_CHIP_PLATFORM_TYPE_ASIC (0x0UL << 0) + #define VER_GET_RESP_CHIP_PLATFORM_TYPE_FPGA (0x1UL << 0) + #define VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM (0x2UL << 0) __le16 max_req_win_len; __le16 max_resp_len; __le16 def_req_timeout; + u8 unused_0; u8 unused_1; u8 unused_2; - u8 unused_3; - u8 valid; -}; - -/* hwrm_func_disable */ -/* Input (24 bytes) */ -struct hwrm_func_disable_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le32 enables; - #define FUNC_DISABLE_REQ_ENABLES_VF_ID_VALID 0x1UL - __le16 vf_id; - __le16 unused_0; -}; - -/* Output (16 bytes) */ -struct hwrm_func_disable_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; u8 valid; }; @@ -759,7 +757,12 @@ struct hwrm_func_reset_input { __le32 enables; #define FUNC_RESET_REQ_ENABLES_VF_ID_VALID 0x1UL __le16 vf_id; - __le16 unused_0; + u8 func_reset_level; + #define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETALL (0x0UL << 0) + #define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETME (0x1UL << 0) + #define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETCHILDREN (0x2UL << 0) + #define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF (0x3UL << 0) + u8 unused_0; }; /* Output (16 bytes) */ @@ -861,7 +864,7 @@ struct hwrm_func_vf_free_output { }; /* hwrm_func_vf_cfg */ -/* Input (24 bytes) */ +/* Input (32 bytes) */ struct hwrm_func_vf_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -871,8 +874,11 @@ struct hwrm_func_vf_cfg_input { __le32 enables; #define FUNC_VF_CFG_REQ_ENABLES_MTU 0x1UL #define FUNC_VF_CFG_REQ_ENABLES_GUEST_VLAN 0x2UL + #define FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR 0x4UL __le16 mtu; __le16 guest_vlan; + __le16 async_event_cr; + __le16 unused_0[3]; }; /* Output (16 bytes) */ @@ -944,7 +950,7 @@ struct hwrm_func_cfg_input { __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le16 vf_id; + __le16 fid; u8 unused_0; u8 unused_1; __le32 flags; @@ -1000,10 +1006,6 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_IF_VLANDNE (0x2UL << 0) #define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN (0x3UL << 0) u8 allowed_vlan_pris; - #define FUNC_CFG_REQ_ALLOWED_VLAN_PRIS_NOCHECK (0x0UL << 0) - #define FUNC_CFG_REQ_ALLOWED_VLAN_PRIS_VALIDATE_VLAN (0x1UL << 0) - #define FUNC_CFG_REQ_ALLOWED_VLAN_PRIS_INSERT_IF_VLANDNE (0x2UL << 0) - #define FUNC_CFG_REQ_ALLOWED_VLAN_PRIS_INSERT_OR_OVERRIDE_VLAN (0x3UL << 0) u8 evb_mode; #define FUNC_CFG_REQ_EVB_MODE_NO_EVB (0x0UL << 0) #define FUNC_CFG_REQ_EVB_MODE_VEB (0x1UL << 0) @@ -1166,6 +1168,15 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD 0x8UL #define FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD 0x10UL __le16 os_type; + #define FUNC_DRV_RGTR_REQ_OS_TYPE_UNKNOWN (0x0UL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_OTHER (0x1UL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_MSDOS (0xeUL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_SOLARIS (0x1dUL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX (0x24UL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_FREEBSD (0x2aUL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_ESXI (0x68UL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN864 (0x73UL << 0) + #define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN2012R2 (0x74UL << 0) u8 ver_maj; u8 ver_min; u8 ver_upd; @@ -1276,9 +1287,7 @@ struct hwrm_func_drv_qver_input { __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le32 enables; - #define FUNC_DRV_QVER_REQ_ENABLES_OS_TYPE_VALID 0x1UL - #define FUNC_DRV_QVER_REQ_ENABLES_VER_VALID 0x2UL + __le32 reserved; __le16 fid; __le16 unused_0; }; @@ -1290,6 +1299,15 @@ struct hwrm_func_drv_qver_output { __le16 seq_id; __le16 resp_len; __le16 os_type; + #define FUNC_DRV_QVER_RESP_OS_TYPE_UNKNOWN (0x0UL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_OTHER (0x1UL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_MSDOS (0xeUL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_SOLARIS (0x1dUL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_LINUX (0x24UL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_FREEBSD (0x2aUL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_ESXI (0x68UL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_WIN864 (0x73UL << 0) + #define FUNC_DRV_QVER_RESP_OS_TYPE_WIN2012R2 (0x74UL << 0) u8 ver_maj; u8 ver_min; u8 ver_upd; @@ -1498,9 +1516,7 @@ struct hwrm_port_phy_qcfg_output { u8 force_pause; #define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX 0x1UL #define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX 0x2UL - u8 duplex_setting; - #define PORT_PHY_QCFG_RESP_DUPLEX_SETTING_HALF (0x0UL << 0) - #define PORT_PHY_QCFG_RESP_DUPLEX_SETTING_FULL (0x1UL << 0) + u8 reserved1; __le32 preemphasis; u8 phy_maj; u8 phy_min; @@ -1601,33 +1617,6 @@ struct hwrm_port_mac_cfg_output { u8 valid; }; -/* hwrm_port_enable */ -/* Input (24 bytes) */ -struct hwrm_port_enable_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le32 flags; - #define PORT_ENABLE_REQ_FLAGS_FORWARD_TRAFFIC 0x1UL - __le16 port_id; - __le16 unused_0; -}; - -/* Output (16 bytes) */ -struct hwrm_port_enable_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - /* hwrm_port_qstats */ /* Input (40 bytes) */ struct hwrm_port_qstats_input { @@ -1651,10 +1640,11 @@ struct hwrm_port_qstats_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - __le32 unused_0; + __le16 tx_stat_size; + __le16 rx_stat_size; + u8 unused_0; u8 unused_1; u8 unused_2; - u8 unused_3; u8 valid; }; @@ -1668,7 +1658,7 @@ struct hwrm_port_lpbk_qstats_input { __le64 resp_addr; }; -/* Output (64 bytes) */ +/* Output (96 bytes) */ struct hwrm_port_lpbk_qstats_output { __le16 error_code; __le16 req_type; @@ -1680,6 +1670,10 @@ struct hwrm_port_lpbk_qstats_output { __le64 lpbk_ucast_bytes; __le64 lpbk_mcast_bytes; __le64 lpbk_bcast_bytes; + __le64 tx_stat_discard; + __le64 tx_stat_error; + __le64 rx_stat_discard; + __le64 rx_stat_error; __le32 unused_0; u8 unused_1; u8 unused_2; @@ -1884,12 +1878,11 @@ struct hwrm_queue_buffers_cfg_input { __le32 enables; #define QUEUE_BUFFERS_CFG_REQ_ENABLES_RESERVED 0x1UL #define QUEUE_BUFFERS_CFG_REQ_ENABLES_SHARED 0x2UL - #define QUEUE_BUFFERS_CFG_REQ_ENABLES_GROUP 0x4UL - #define QUEUE_BUFFERS_CFG_REQ_ENABLES_XOFF 0x8UL - #define QUEUE_BUFFERS_CFG_REQ_ENABLES_XON 0x10UL - #define QUEUE_BUFFERS_CFG_REQ_ENABLES_FULL 0x20UL - #define QUEUE_BUFFERS_CFG_REQ_ENABLES_NOTFULL 0x40UL - #define QUEUE_BUFFERS_CFG_REQ_ENABLES_MAX 0x80UL + #define QUEUE_BUFFERS_CFG_REQ_ENABLES_XOFF 0x4UL + #define QUEUE_BUFFERS_CFG_REQ_ENABLES_XON 0x8UL + #define QUEUE_BUFFERS_CFG_REQ_ENABLES_FULL 0x10UL + #define QUEUE_BUFFERS_CFG_REQ_ENABLES_NOTFULL 0x20UL + #define QUEUE_BUFFERS_CFG_REQ_ENABLES_MAX 0x40UL __le32 queue_id; __le32 reserved; __le32 shared; @@ -1921,15 +1914,15 @@ struct hwrm_queue_pfcenable_cfg_input { __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le32 enables; - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI0_PFC_ENABLED 0x1UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI1_PFC_ENABLED 0x2UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI2_PFC_ENABLED 0x4UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI3_PFC_ENABLED 0x8UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI4_PFC_ENABLED 0x10UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI5_PFC_ENABLED 0x20UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI6_PFC_ENABLED 0x40UL - #define QUEUE_PFCENABLE_CFG_REQ_ENABLES_PRI7_PFC_ENABLED 0x80UL + __le32 flags; + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED 0x1UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED 0x2UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED 0x4UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED 0x8UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED 0x10UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED 0x20UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED 0x40UL + #define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED 0x80UL __le16 port_id; __le16 unused_0; }; @@ -1962,14 +1955,14 @@ struct hwrm_queue_pri2cos_cfg_input { #define QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN 0x2UL __le32 enables; u8 port_id; - u8 pri0_cos; - u8 pri1_cos; - u8 pri2_cos; - u8 pri3_cos; - u8 pri4_cos; - u8 pri5_cos; - u8 pri6_cos; - u8 pri7_cos; + u8 pri0_cos_queue_id; + u8 pri1_cos_queue_id; + u8 pri2_cos_queue_id; + u8 pri3_cos_queue_id; + u8 pri4_cos_queue_id; + u8 pri5_cos_queue_id; + u8 pri6_cos_queue_id; + u8 pri7_cos_queue_id; u8 unused_0[7]; }; @@ -2164,6 +2157,7 @@ struct hwrm_vnic_cfg_input { __le32 flags; #define VNIC_CFG_REQ_FLAGS_DEFAULT 0x1UL #define VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE 0x2UL + #define VNIC_CFG_REQ_FLAGS_BD_STALL_MODE 0x4UL __le32 enables; #define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP 0x1UL #define VNIC_CFG_REQ_ENABLES_RSS_RULE 0x2UL @@ -2380,18 +2374,16 @@ struct hwrm_ring_alloc_input { __le16 target_id; __le64 resp_addr; __le32 enables; - #define RING_ALLOC_REQ_ENABLES_ARB_GRP_ID_VALID 0x1UL - #define RING_ALLOC_REQ_ENABLES_INPUT_NUM_VALID 0x2UL - #define RING_ALLOC_REQ_ENABLES_WEIGHT_VALID 0x4UL + #define RING_ALLOC_REQ_ENABLES_RESERVED1 0x1UL + #define RING_ALLOC_REQ_ENABLES_RESERVED2 0x2UL + #define RING_ALLOC_REQ_ENABLES_RESERVED3 0x4UL #define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID 0x8UL - #define RING_ALLOC_REQ_ENABLES_MIN_BW_VALID 0x10UL + #define RING_ALLOC_REQ_ENABLES_RESERVED4 0x10UL #define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID 0x20UL u8 ring_type; #define RING_ALLOC_REQ_RING_TYPE_CMPL (0x0UL << 0) #define RING_ALLOC_REQ_RING_TYPE_TX (0x1UL << 0) #define RING_ALLOC_REQ_RING_TYPE_RX (0x2UL << 0) - #define RING_ALLOC_REQ_RING_TYPE_STATUS (0x3UL << 0) - #define RING_ALLOC_REQ_RING_TYPE_CMD (0x4UL << 0) u8 unused_0; __le16 unused_1; __le64 page_tbl_addr; @@ -2406,17 +2398,17 @@ struct hwrm_ring_alloc_input { __le16 queue_id; u8 unused_4; u8 unused_5; - __le32 arb_grp_id; - __le16 input_number; + __le32 reserved1; + __le16 reserved2; u8 unused_6; u8 unused_7; - __le32 weight; + __le32 reserved3; __le32 stat_ctx_id; - __le32 min_bw; + __le32 reserved4; __le32 max_bw; u8 int_mode; #define RING_ALLOC_REQ_INT_MODE_LEGACY (0x0UL << 0) - #define RING_ALLOC_REQ_INT_MODE_MSI (0x1UL << 0) + #define RING_ALLOC_REQ_INT_MODE_RSVD (0x1UL << 0) #define RING_ALLOC_REQ_INT_MODE_MSIX (0x2UL << 0) #define RING_ALLOC_REQ_INT_MODE_POLL (0x3UL << 0) u8 unused_8[3]; @@ -2448,8 +2440,6 @@ struct hwrm_ring_free_input { #define RING_FREE_REQ_RING_TYPE_CMPL (0x0UL << 0) #define RING_FREE_REQ_RING_TYPE_TX (0x1UL << 0) #define RING_FREE_REQ_RING_TYPE_RX (0x2UL << 0) - #define RING_FREE_REQ_RING_TYPE_STATUS (0x3UL << 0) - #define RING_FREE_REQ_RING_TYPE_CMD (0x4UL << 0) u8 unused_0; __le16 ring_id; __le32 unused_1; @@ -2550,8 +2540,6 @@ struct hwrm_ring_reset_input { #define RING_RESET_REQ_RING_TYPE_CMPL (0x0UL << 0) #define RING_RESET_REQ_RING_TYPE_TX (0x1UL << 0) #define RING_RESET_REQ_RING_TYPE_RX (0x2UL << 0) - #define RING_RESET_REQ_RING_TYPE_STATUS (0x3UL << 0) - #define RING_RESET_REQ_RING_TYPE_CMD (0x4UL << 0) u8 unused_0; __le16 ring_id; __le32 unused_1; @@ -2622,61 +2610,6 @@ struct hwrm_ring_grp_free_output { u8 valid; }; -/* hwrm_arb_grp_alloc */ -/* Input (24 bytes) */ -struct hwrm_arb_grp_alloc_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le16 input_number; - __le16 unused_0[3]; -}; - -/* Output (16 bytes) */ -struct hwrm_arb_grp_alloc_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le16 arb_grp_id; - u8 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 unused_4; - u8 valid; -}; - -/* hwrm_arb_grp_cfg */ -/* Input (32 bytes) */ -struct hwrm_arb_grp_cfg_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le32 arb_grp_id; - __le16 input_number; - __le16 tx_ring; - __le32 weight; - __le32 unused_0; -}; - -/* Output (16 bytes) */ -struct hwrm_arb_grp_cfg_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - /* hwrm_cfa_l2_filter_alloc */ /* Input (96 bytes) */ struct hwrm_cfa_l2_filter_alloc_input { @@ -2708,7 +2641,7 @@ struct hwrm_cfa_l2_filter_alloc_input { #define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_TYPE 0x1000UL #define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_ID 0x2000UL #define CFA_L2_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE 0x4000UL - #define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID 0x8000UL + #define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID 0x8000UL #define CFA_L2_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID 0x10000UL u8 l2_addr[6]; u8 unused_0; @@ -2751,7 +2684,7 @@ struct hwrm_cfa_l2_filter_alloc_input { #define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE (0x8UL << 0) #define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL (0xffUL << 0) u8 unused_7; - __le16 dst_vnic_id; + __le16 dst_id; __le16 mirror_vnic_id; u8 pri_hint; #define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER (0x0UL << 0) @@ -2816,10 +2749,11 @@ struct hwrm_cfa_l2_filter_cfg_input { #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX (0x1UL << 0) #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL __le32 enables; - #define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_VNIC_ID_VALID 0x1UL + #define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID 0x1UL + #define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID 0x2UL __le64 l2_filter_id; - __le32 dst_vnic_id; - __le32 unused_0; + __le32 dst_id; + __le32 new_mirror_vnic_id; }; /* Output (16 bytes) */ @@ -2843,9 +2777,9 @@ struct hwrm_cfa_l2_set_rx_mask_input { __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le32 dflt_vnic_id; + __le32 vnic_id; __le32 mask; - #define CFA_L2_SET_RX_MASK_REQ_MASK_UNICAST 0x1UL + #define CFA_L2_SET_RX_MASK_REQ_MASK_RESERVED 0x1UL #define CFA_L2_SET_RX_MASK_REQ_MASK_MCAST 0x2UL #define CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST 0x4UL #define CFA_L2_SET_RX_MASK_REQ_MASK_BCAST 0x8UL @@ -2869,46 +2803,6 @@ struct hwrm_cfa_l2_set_rx_mask_output { u8 valid; }; -/* hwrm_cfa_l2_set_bcastmcast_mirroring */ -/* Input (32 bytes) */ -struct hwrm_cfa_l2_set_bcastmcast_mirroring_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le32 dflt_vnic_id; - __le32 mirroring_flags; - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MIRRORING_FLAGS_BCAST_MIRRORING 0x1UL - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MIRRORING_FLAGS_MCAST_MIRRORING 0x2UL - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MIRRORING_FLAGS_BCAST_SRC_KNOCKOUT 0x4UL - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MIRRORING_FLAGS_MCAST_SRC_KNOCKOUT 0x8UL - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MIRRORING_FLAGS_VLAN_ID_VALID 0x10UL - __le16 vlan_id; - u8 bcast_domain; - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_BCAST_DOMAIN_PFONLY (0x0UL << 0) - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_BCAST_DOMAIN_ALLPFS (0x1UL << 0) - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_BCAST_DOMAIN_ALLPFSVFS (0x2UL << 0) - u8 mcast_domain; - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MCAST_DOMAIN_PFONLY (0x0UL << 0) - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MCAST_DOMAIN_ALLPFS (0x1UL << 0) - #define CFA_L2_SET_BCASTMCAST_MIRRORING_REQ_MCAST_DOMAIN_ALLPFSVFS (0x2UL << 0) - __le32 unused_0; -}; - -/* Output (16 bytes) */ -struct hwrm_cfa_l2_set_bcastmcast_mirroring_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - /* hwrm_cfa_tunnel_filter_alloc */ /* Input (88 bytes) */ struct hwrm_cfa_tunnel_filter_alloc_input { @@ -3017,17 +2911,16 @@ struct hwrm_cfa_encap_record_alloc_input { __le32 encap_data[16]; }; -/* Output (24 bytes) */ +/* Output (16 bytes) */ struct hwrm_cfa_encap_record_alloc_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; - __le64 encap_record_id; - __le32 unused_0; + __le32 encap_record_id; + u8 unused_0; u8 unused_1; u8 unused_2; - u8 unused_3; u8 valid; }; @@ -3039,7 +2932,8 @@ struct hwrm_cfa_encap_record_free_input { __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le64 encap_record_id; + __le32 encap_record_id; + __le32 unused_0; }; /* Output (16 bytes) */ @@ -3083,14 +2977,21 @@ struct hwrm_cfa_ntuple_filter_alloc_input { #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT_MASK 0x2000UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_PRI_HINT 0x4000UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_NTUPLE_FILTER_ID 0x8000UL - #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID 0x10000UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID 0x10000UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID 0x20000UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR 0x40000UL __le64 l2_filter_id; u8 src_macaddr[6]; __be16 ethertype; - u8 ipaddr_type; + u8 ip_addr_type; + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN (0x0UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4 (0x4UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6 (0x6UL << 0) u8 ip_protocol; - __le16 dst_vnic_id; + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN (0x0UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP (0x6UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP (0x11UL << 0) + __le16 dst_id; __le16 mirror_vnic_id; u8 tunnel_type; #define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL (0x0UL << 0) @@ -3104,6 +3005,11 @@ struct hwrm_cfa_ntuple_filter_alloc_input { #define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE (0x8UL << 0) #define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL (0xffUL << 0) u8 pri_hint; + #define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER (0x0UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE (0x1UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_BELOW (0x2UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_HIGHEST (0x3UL << 0) + #define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST (0x4UL << 0) __be32 src_ipaddr[4]; __be32 src_ipaddr_mask[4]; __be32 dst_ipaddr[4]; @@ -3162,11 +3068,11 @@ struct hwrm_cfa_ntuple_filter_cfg_input { __le16 target_id; __le64 resp_addr; __le32 enables; - #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_VNIC_ID_VALID 0x1UL - #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID_VALID 0x2UL + #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID 0x1UL + #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID 0x2UL __le32 unused_0; __le64 ntuple_filter_id; - __le32 new_dst_vnic_id; + __le32 new_dst_id; __le32 new_mirror_vnic_id; }; @@ -3192,16 +3098,8 @@ struct hwrm_tunnel_dst_port_query_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_NONTUNNEL (0x0UL << 0) #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN (0x1UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_NVGRE (0x2UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2GRE (0x3UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPIP (0x4UL << 0) #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE (0x5UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_MPLS (0x6UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_STT (0x7UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE (0x8UL << 0) - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ANYTUNNEL (0xffUL << 0) u8 unused_0[7]; }; @@ -3228,16 +3126,8 @@ struct hwrm_tunnel_dst_port_alloc_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL (0x0UL << 0) #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN (0x1UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_NVGRE (0x2UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2GRE (0x3UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPIP (0x4UL << 0) #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE (0x5UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_MPLS (0x6UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_STT (0x7UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE (0x8UL << 0) - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL (0xffUL << 0) u8 unused_0; __be16 tunnel_dst_port_val; __le32 unused_1; @@ -3267,16 +3157,8 @@ struct hwrm_tunnel_dst_port_free_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_NONTUNNEL (0x0UL << 0) #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN (0x1UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_NVGRE (0x2UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2GRE (0x3UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPIP (0x4UL << 0) #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE (0x5UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_MPLS (0x6UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_STT (0x7UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE (0x8UL << 0) - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ANYTUNNEL (0xffUL << 0) u8 unused_0; __le16 tunnel_dst_port_id; __le32 unused_1; @@ -3416,68 +3298,145 @@ struct hwrm_stat_ctx_clr_stats_output { u8 valid; }; -/* hwrm_mgmt_l2_filter_alloc */ -/* Input (56 bytes) */ -struct hwrm_mgmt_l2_filter_alloc_input { +/* hwrm_fw_reset */ +/* Input (24 bytes) */ +struct hwrm_fw_reset_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le32 flags; - #define MGMT_L2_FILTER_ALLOC_REQ_FLAGS_PATH 0x1UL - #define MGMT_L2_FILTER_ALLOC_REQ_FLAGS_PATH_TX (0x0UL << 0) - #define MGMT_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX (0x1UL << 0) - __le32 enables; - #define MGMT_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDRESS 0x1UL - #define MGMT_L2_FILTER_ALLOC_REQ_ENABLES_OVLAN 0x2UL - #define MGMT_L2_FILTER_ALLOC_REQ_ENABLES_IVLAN 0x4UL - #define MGMT_L2_FILTER_ALLOC_REQ_ENABLES_ACTION_ID 0x8UL - u8 l2_address[6]; + u8 embedded_proc_type; + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT (0x0UL << 0) + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT (0x1UL << 0) + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL (0x2UL << 0) + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE (0x3UL << 0) + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_RSVD (0x4UL << 0) + u8 selfrst_status; + #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE (0x0UL << 0) + #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP (0x1UL << 0) + #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST (0x2UL << 0) + __le16 unused_0[3]; +}; + +/* Output (16 bytes) */ +struct hwrm_fw_reset_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 selfrst_status; + #define FW_RESET_RESP_SELFRST_STATUS_SELFRSTNONE (0x0UL << 0) + #define FW_RESET_RESP_SELFRST_STATUS_SELFRSTASAP (0x1UL << 0) + #define FW_RESET_RESP_SELFRST_STATUS_SELFRSTPCIERST (0x2UL << 0) u8 unused_0; + __le16 unused_1; + u8 unused_2; + u8 unused_3; + u8 unused_4; + u8 valid; +}; + +/* hwrm_exec_fwd_resp */ +/* Input (128 bytes) */ +struct hwrm_exec_fwd_resp_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 encap_request[26]; + __le16 encap_resp_target_id; + __le16 unused_0[3]; +}; + +/* Output (16 bytes) */ +struct hwrm_exec_fwd_resp_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 unused_0; u8 unused_1; - u8 l2_address_mask[6]; - __le16 ovlan; - __le16 ovlan_mask; - __le16 ivlan; - __le16 ivlan_mask; u8 unused_2; u8 unused_3; - __le32 action_id; - u8 action_bypass; - #define MGMT_L2_FILTER_ALLOC_REQ_ACTION_BYPASS 0x1UL - u8 unused_5[3]; + u8 valid; +}; + +/* hwrm_reject_fwd_resp */ +/* Input (128 bytes) */ +struct hwrm_reject_fwd_resp_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 encap_request[26]; + __le16 encap_resp_target_id; + __le16 unused_0[3]; }; /* Output (16 bytes) */ -struct hwrm_mgmt_l2_filter_alloc_output { +struct hwrm_reject_fwd_resp_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; - __le16 mgmt_l2_filter_id; + __le32 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_fwd_resp */ +/* Input (40 bytes) */ +struct hwrm_fwd_resp_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 encap_resp_target_id; + __le16 encap_resp_cmpl_ring; + __le16 encap_resp_len; u8 unused_0; u8 unused_1; + __le64 encap_resp_addr; + __le32 encap_resp[24]; +}; + +/* Output (16 bytes) */ +struct hwrm_fwd_resp_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 unused_0; + u8 unused_1; u8 unused_2; u8 unused_3; - u8 unused_4; u8 valid; }; -/* hwrm_mgmt_l2_filter_free */ -/* Input (24 bytes) */ -struct hwrm_mgmt_l2_filter_free_input { +/* hwrm_fwd_async_event_cmpl */ +/* Input (32 bytes) */ +struct hwrm_fwd_async_event_cmpl_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le16 mgmt_l2_filter_id; - __le16 unused_0[3]; + __le16 encap_async_event_target_id; + u8 unused_0; + u8 unused_1; + u8 unused_2[3]; + u8 unused_3; + __le32 encap_async_event_cmpl[4]; }; /* Output (16 bytes) */ -struct hwrm_mgmt_l2_filter_free_output { +struct hwrm_fwd_async_event_cmpl_output { __le16 error_code; __le16 req_type; __le16 seq_id; @@ -3489,6 +3448,31 @@ struct hwrm_mgmt_l2_filter_free_output { u8 valid; }; +/* hwrm_temp_monitor_query */ +/* Input (16 bytes) */ +struct hwrm_temp_monitor_query_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* Output (16 bytes) */ +struct hwrm_temp_monitor_query_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 temp; + u8 unused_0; + __le16 unused_1; + u8 unused_2; + u8 unused_3; + u8 unused_4; + u8 valid; +}; + /* hwrm_nvm_raw_write_blk */ /* Input (32 bytes) */ struct hwrm_nvm_raw_write_blk_input { @@ -3621,7 +3605,7 @@ struct hwrm_nvm_get_dir_info_output { }; /* hwrm_nvm_write */ -/* Input (40 bytes) */ +/* Input (48 bytes) */ struct hwrm_nvm_write_input { __le16 req_type; __le16 cmpl_ring; @@ -3637,6 +3621,8 @@ struct hwrm_nvm_write_input { __le16 option; __le16 flags; #define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG 0x1UL + __le32 dir_item_length; + __le32 unused_0; }; /* Output (16 bytes) */ @@ -3645,10 +3631,9 @@ struct hwrm_nvm_write_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; + __le32 dir_item_length; + __le16 dir_idx; + u8 unused_0; u8 valid; }; @@ -3833,214 +3818,4 @@ struct hwrm_nvm_verify_update_output { u8 valid; }; -/* hwrm_exec_fwd_resp */ -/* Input (120 bytes) */ -struct hwrm_exec_fwd_resp_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le32 encap_request[24]; - __le16 encap_resp_target_id; - __le16 unused_0[3]; -}; - -/* Output (16 bytes) */ -struct hwrm_exec_fwd_resp_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - -/* hwrm_reject_fwd_resp */ -/* Input (120 bytes) */ -struct hwrm_reject_fwd_resp_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le32 encap_request[24]; - __le16 encap_resp_target_id; - __le16 unused_0[3]; -}; - -/* Output (16 bytes) */ -struct hwrm_reject_fwd_resp_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - -/* hwrm_fwd_resp */ -/* Input (40 bytes) */ -struct hwrm_fwd_resp_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le16 encap_resp_target_id; - __le16 encap_resp_cmpl_ring; - __le16 encap_resp_len; - u8 unused_0; - u8 unused_1; - __le64 encap_resp_addr; - __le32 encap_resp[24]; -}; - -/* Output (16 bytes) */ -struct hwrm_fwd_resp_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - -/* hwrm_fwd_async_event_cmpl */ -/* Input (32 bytes) */ -struct hwrm_fwd_async_event_cmpl_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le16 encap_async_event_target_id; - u8 unused_0; - u8 unused_1; - u8 unused_2[3]; - u8 unused_3; - __le32 encap_async_event_cmpl[4]; -}; - -/* Output (16 bytes) */ -struct hwrm_fwd_async_event_cmpl_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 unused_0; - u8 unused_1; - u8 unused_2; - u8 unused_3; - u8 valid; -}; - -/* hwrm_fw_reset */ -/* Input (24 bytes) */ -struct hwrm_fw_reset_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - u8 embedded_proc_type; - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIMP (0x0UL << 0) - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_APE (0x1UL << 0) - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_KONG (0x2UL << 0) - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BONO (0x3UL << 0) - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_TANG (0x4UL << 0) - u8 selfrst_status; - #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE (0x0UL << 0) - #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP (0x1UL << 0) - #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST (0x2UL << 0) - __le16 unused_0[3]; -}; - -/* Output (16 bytes) */ -struct hwrm_fw_reset_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - u8 selfrst_status; - #define FW_RESET_RESP_SELFRST_STATUS_SELFRSTNONE (0x0UL << 0) - #define FW_RESET_RESP_SELFRST_STATUS_SELFRSTASAP (0x1UL << 0) - #define FW_RESET_RESP_SELFRST_STATUS_SELFRSTPCIERST (0x2UL << 0) - u8 unused_0; - __le16 unused_1; - u8 unused_2; - u8 unused_3; - u8 unused_4; - u8 valid; -}; - -/* hwrm_fw_qstatus */ -/* Input (24 bytes) */ -struct hwrm_fw_qstatus_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - u8 embedded_proc_type; - #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIMP (0x0UL << 0) - #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_APE (0x1UL << 0) - #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_KONG (0x2UL << 0) - #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_BONO (0x3UL << 0) - #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_TANG (0x4UL << 0) - u8 unused_0[7]; -}; - -/* Output (16 bytes) */ -struct hwrm_fw_qstatus_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - u8 selfrst_status; - #define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTNONE (0x0UL << 0) - #define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTASAP (0x1UL << 0) - #define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST (0x2UL << 0) - u8 unused_0; - __le16 unused_1; - u8 unused_2; - u8 unused_3; - u8 unused_4; - u8 valid; -}; - -/* hwrm_temp_monitor_query */ -/* Input (16 bytes) */ -struct hwrm_temp_monitor_query_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; -}; - -/* Output (16 bytes) */ -struct hwrm_temp_monitor_query_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - u8 temp; - u8 unused_0; - __le16 unused_1; - u8 unused_2; - u8 unused_3; - u8 unused_4; - u8 valid; -}; - #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 7a9af2887d8ed..c1cc83d7e38c6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -21,7 +21,7 @@ #ifdef CONFIG_BNXT_SRIOV static int bnxt_vf_ndo_prep(struct bnxt *bp, int vf_id) { - if (bp->state != BNXT_STATE_OPEN) { + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { netdev_err(bp->dev, "vf ndo called though PF is down\n"); return -EINVAL; } @@ -64,7 +64,7 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) * the spoof check should also include vlan anti-spoofing */ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); - req.vf_id = cpu_to_le16(vf->fw_fid); + req.fid = cpu_to_le16(vf->fw_fid); req.flags = cpu_to_le32(func_flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { @@ -128,7 +128,7 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) memcpy(vf->mac_addr, mac, ETH_ALEN); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); - req.vf_id = cpu_to_le16(vf->fw_fid); + req.fid = cpu_to_le16(vf->fw_fid); req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); memcpy(req.dflt_mac_addr, mac, ETH_ALEN); @@ -159,7 +159,7 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos) return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); - req.vf_id = cpu_to_le16(vf->fw_fid); + req.fid = cpu_to_le16(vf->fw_fid); req.flags = cpu_to_le32(vf->func_flags); req.dflt_vlan = cpu_to_le16(vlan_tag); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); @@ -198,7 +198,7 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, if (min_tx_rate == vf->min_tx_rate && max_tx_rate == vf->max_tx_rate) return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); - req.vf_id = cpu_to_le16(vf->fw_fid); + req.fid = cpu_to_le16(vf->fw_fid); req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); req.max_bw = cpu_to_le32(max_tx_rate); @@ -363,10 +363,11 @@ static int bnxt_hwrm_func_buf_rgtr(struct bnxt *bp) } /* only call by PF to reserve resources for VF */ -static int bnxt_hwrm_func_cfg(struct bnxt *bp, int *num_vfs) +static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) { u32 rc = 0, mtu, i; u16 vf_tx_rings, vf_rx_rings, vf_cp_rings, vf_stat_ctx, vf_vnics; + u16 vf_ring_grps; struct hwrm_func_cfg_input req = {0}; struct bnxt_pf_info *pf = &bp->pf; @@ -378,18 +379,18 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int *num_vfs) * be removed once new HWRM provides HW ring groups capability in * hwrm_func_qcap. */ - vf_cp_rings = min_t(u16, bp->pf.max_cp_rings, bp->pf.max_stat_ctxs); - vf_cp_rings = (vf_cp_rings - bp->cp_nr_rings) / *num_vfs; + vf_cp_rings = min_t(u16, pf->max_cp_rings, pf->max_stat_ctxs); + vf_cp_rings = (vf_cp_rings - bp->cp_nr_rings) / num_vfs; /* TODO: restore this logic below once the WA above is removed */ - /* vf_cp_rings = (bp->pf.max_cp_rings - bp->cp_nr_rings) / *num_vfs; */ - vf_stat_ctx = (bp->pf.max_stat_ctxs - bp->num_stat_ctxs) / *num_vfs; + /* vf_cp_rings = (pf->max_cp_rings - bp->cp_nr_rings) / num_vfs; */ + vf_stat_ctx = (pf->max_stat_ctxs - bp->num_stat_ctxs) / num_vfs; if (bp->flags & BNXT_FLAG_AGG_RINGS) - vf_rx_rings = (bp->pf.max_rx_rings - bp->rx_nr_rings * 2) / - *num_vfs; + vf_rx_rings = (pf->max_rx_rings - bp->rx_nr_rings * 2) / + num_vfs; else - vf_rx_rings = (bp->pf.max_rx_rings - bp->rx_nr_rings) / - *num_vfs; - vf_tx_rings = (bp->pf.max_tx_rings - bp->tx_nr_rings) / *num_vfs; + vf_rx_rings = (pf->max_rx_rings - bp->rx_nr_rings) / num_vfs; + vf_ring_grps = (bp->pf.max_hw_ring_grps - bp->rx_nr_rings) / num_vfs; + vf_tx_rings = (pf->max_tx_rings - bp->tx_nr_rings) / num_vfs; req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MTU | FUNC_CFG_REQ_ENABLES_MRU | @@ -399,7 +400,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int *num_vfs) FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS | FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS | FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS | - FUNC_CFG_REQ_ENABLES_NUM_VNICS); + FUNC_CFG_REQ_ENABLES_NUM_VNICS | + FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS); mtu = bp->dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; req.mru = cpu_to_le16(mtu); @@ -409,6 +411,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int *num_vfs) req.num_cmpl_rings = cpu_to_le16(vf_cp_rings); req.num_tx_rings = cpu_to_le16(vf_tx_rings); req.num_rx_rings = cpu_to_le16(vf_rx_rings); + req.num_hw_ring_grps = cpu_to_le16(vf_ring_grps); req.num_l2_ctxs = cpu_to_le16(4); vf_vnics = 1; @@ -417,22 +420,24 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int *num_vfs) req.num_stat_ctxs = cpu_to_le16(vf_stat_ctx); mutex_lock(&bp->hwrm_cmd_lock); - for (i = 0; i < *num_vfs; i++) { - req.vf_id = cpu_to_le16(pf->first_vf_id + i); + for (i = 0; i < num_vfs; i++) { + req.fid = cpu_to_le16(pf->first_vf_id + i); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) break; - bp->pf.active_vfs = i + 1; - bp->pf.vf[i].fw_fid = le16_to_cpu(req.vf_id); + pf->active_vfs = i + 1; + pf->vf[i].fw_fid = le16_to_cpu(req.fid); } mutex_unlock(&bp->hwrm_cmd_lock); if (!rc) { - bp->pf.max_pf_tx_rings = bp->tx_nr_rings; - if (bp->flags & BNXT_FLAG_AGG_RINGS) - bp->pf.max_pf_rx_rings = bp->rx_nr_rings * 2; - else - bp->pf.max_pf_rx_rings = bp->rx_nr_rings; + pf->max_tx_rings -= vf_tx_rings * num_vfs; + pf->max_rx_rings -= vf_rx_rings * num_vfs; + pf->max_hw_ring_grps -= vf_ring_grps * num_vfs; + pf->max_cp_rings -= vf_cp_rings * num_vfs; + pf->max_rsscos_ctxs -= num_vfs; + pf->max_stat_ctxs -= vf_stat_ctx * num_vfs; + pf->max_vnics -= vf_vnics * num_vfs; } return rc; } @@ -492,7 +497,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) goto err_out1; /* Reserve resources for VFs */ - rc = bnxt_hwrm_func_cfg(bp, num_vfs); + rc = bnxt_hwrm_func_cfg(bp, *num_vfs); if (rc) goto err_out2; @@ -536,8 +541,8 @@ void bnxt_sriov_disable(struct bnxt *bp) bnxt_free_vf_resources(bp); bp->pf.active_vfs = 0; - bp->pf.max_pf_rx_rings = bp->pf.max_rx_rings; - bp->pf.max_pf_tx_rings = bp->pf.max_tx_rings; + /* Reclaim all resources for the PF. */ + bnxt_hwrm_func_qcaps(bp); } int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs) @@ -595,6 +600,7 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, /* Set the new target id */ req.target_id = cpu_to_le16(vf->fw_fid); + req.encap_resp_target_id = cpu_to_le16(vf->fw_fid); req.encap_resp_len = cpu_to_le16(msg_size); req.encap_resp_addr = encap_resp_addr; req.encap_resp_cmpl_ring = encap_resp_cpr; @@ -629,6 +635,7 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_REJECT_FWD_RESP, -1, -1); /* Set the new target id */ req.target_id = cpu_to_le16(vf->fw_fid); + req.encap_resp_target_id = cpu_to_le16(vf->fw_fid); memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size); mutex_lock(&bp->hwrm_cmd_lock); @@ -660,6 +667,7 @@ static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_EXEC_FWD_RESP, -1, -1); /* Set the new target id */ req.target_id = cpu_to_le16(vf->fw_fid); + req.encap_resp_target_id = cpu_to_le16(vf->fw_fid); memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size); mutex_lock(&bp->hwrm_cmd_lock); diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 169059c92f80b..8b45bc9ac29e8 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -28,6 +29,7 @@ #include <linux/phy.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/of_gpio.h> #include <linux/of_mdio.h> #include <linux/of_net.h> @@ -2817,6 +2819,7 @@ static int macb_probe(struct platform_device *pdev) = macb_clk_init; int (*init)(struct platform_device *) = macb_init; struct device_node *np = pdev->dev.of_node; + struct device_node *phy_node; const struct macb_config *macb_config = NULL; struct clk *pclk, *hclk, *tx_clk; unsigned int queue_mask, num_queues; @@ -2904,6 +2907,16 @@ static int macb_probe(struct platform_device *pdev) else macb_get_hwaddr(bp); + /* Power up the PHY if there is a GPIO reset */ + phy_node = of_get_next_available_child(np, NULL); + if (phy_node) { + int gpio = of_get_named_gpio(phy_node, "reset-gpios", 0); + if (gpio_is_valid(gpio)) + bp->reset_gpio = gpio_to_desc(gpio); + gpiod_set_value(bp->reset_gpio, GPIOD_OUT_HIGH); + } + of_node_put(phy_node); + err = of_get_phy_mode(np); if (err < 0) { pdata = dev_get_platdata(&pdev->dev); @@ -2970,6 +2983,10 @@ static int macb_remove(struct platform_device *pdev) mdiobus_unregister(bp->mii_bus); kfree(bp->mii_bus->irq); mdiobus_free(bp->mii_bus); + + /* Shutdown the PHY if there is a GPIO reset */ + gpiod_set_value(bp->reset_gpio, GPIOD_OUT_LOW); + unregister_netdev(dev); clk_disable_unprepare(bp->tx_clk); clk_disable_unprepare(bp->hclk); diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index d83b0db778219..5c03e811224d3 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -829,6 +829,7 @@ struct macb { unsigned int dma_burst_length; phy_interface_t phy_interface; + struct gpio_desc *reset_gpio; /* AT91RM9200 transmit */ struct sk_buff *skb; /* holds skb until xmit interrupt completes */ diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 39ca6744a4e68..688828865c482 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -265,6 +265,7 @@ struct nicvf { u8 tns_mode:1; u8 sqs_mode:1; u8 loopback_supported:1; + bool hw_tso; u16 mtu; struct queue_set *qs; #define MAX_SQS_PER_VF_SINGLE_NODE 5 @@ -489,6 +490,11 @@ static inline int nic_get_node_id(struct pci_dev *pdev) return ((addr >> NIC_NODE_ID_SHIFT) & NIC_NODE_ID_MASK); } +static inline bool pass1_silicon(struct pci_dev *pdev) +{ + return pdev->revision < 8; +} + int nicvf_set_real_num_queues(struct net_device *netdev, int tx_queues, int rx_queues); int nicvf_open(struct net_device *netdev); diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 4b7fd63ae57c1..4dded90076c87 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -37,7 +37,6 @@ struct nicpf { #define NIC_GET_BGX_FROM_VF_LMAC_MAP(map) ((map >> 4) & 0xF) #define NIC_GET_LMAC_FROM_VF_LMAC_MAP(map) (map & 0xF) u8 vf_lmac_map[MAX_LMAC]; - u8 lmac_cnt; struct delayed_work dwork; struct workqueue_struct *check_link; u8 link[MAX_LMAC]; @@ -55,11 +54,6 @@ struct nicpf { bool irq_allocated[NIC_PF_MSIX_VECTORS]; }; -static inline bool pass1_silicon(struct nicpf *nic) -{ - return nic->pdev->revision < 8; -} - /* Supported devices */ static const struct pci_device_id nic_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) }, @@ -123,7 +117,7 @@ static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx) * when PF writes to MBOX(1), in next revisions when * PF writes to MBOX(0) */ - if (pass1_silicon(nic)) { + if (pass1_silicon(nic->pdev)) { /* see the comment for nic_reg_write()/nic_reg_read() * functions above */ @@ -280,7 +274,6 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) u64 lmac_credit; nic->num_vf_en = 0; - nic->lmac_cnt = 0; for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) { if (!(bgx_map & (1 << bgx))) @@ -290,7 +283,6 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) nic->vf_lmac_map[next_bgx_lmac++] = NIC_SET_VF_LMAC_MAP(bgx, lmac); nic->num_vf_en += lmac_cnt; - nic->lmac_cnt += lmac_cnt; /* Program LMAC credits */ lmac_credit = (1ull << 1); /* channel credit enable */ @@ -400,7 +392,7 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg) padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */ /* Leave RSS_SIZE as '0' to disable RSS */ - if (pass1_silicon(nic)) { + if (pass1_silicon(nic->pdev)) { nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), (vnic << 24) | (padd << 16) | (rssi_base + rssi)); @@ -470,7 +462,7 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg) } cpi_base = nic->cpi_base[cfg->vf_id]; - if (pass1_silicon(nic)) + if (pass1_silicon(nic->pdev)) idx_addr = NIC_PF_CPI_0_2047_CFG; else idx_addr = NIC_PF_MPI_0_2047_CFG; @@ -618,6 +610,21 @@ static int nic_config_loopback(struct nicpf *nic, struct set_loopback *lbk) return 0; } +static void nic_enable_vf(struct nicpf *nic, int vf, bool enable) +{ + int bgx, lmac; + + nic->vf_enabled[vf] = enable; + + if (vf >= nic->num_vf_en) + return; + + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + + bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, enable); +} + /* Interrupt handler to handle mailbox messages from VFs */ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) { @@ -717,29 +724,14 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_CFG_DONE: /* Last message of VF config msg sequence */ - nic->vf_enabled[vf] = true; - if (vf >= nic->lmac_cnt) - goto unlock; - - bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - - bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, true); + nic_enable_vf(nic, vf, true); goto unlock; case NIC_MBOX_MSG_SHUTDOWN: /* First msg in VF teardown sequence */ - nic->vf_enabled[vf] = false; if (vf >= nic->num_vf_en) nic->sqs_used[vf - nic->num_vf_en] = false; nic->pqs_vf[vf] = 0; - - if (vf >= nic->lmac_cnt) - break; - - bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - - bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, false); + nic_enable_vf(nic, vf, false); break; case NIC_MBOX_MSG_ALLOC_SQS: nic_alloc_sqs(nic, &mbx.sqs_alloc); @@ -958,7 +950,7 @@ static void nic_poll_for_link(struct work_struct *work) mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; - for (vf = 0; vf < nic->lmac_cnt; vf++) { + for (vf = 0; vf < nic->num_vf_en; vf++) { /* Poll only if VF is UP */ if (!nic->vf_enabled[vf]) continue; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index dde8dc720cd3f..c24cb2a86a42f 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -525,14 +525,22 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, __func__, cqe_tx->sq_qs, cqe_tx->sq_idx, cqe_tx->sqe_ptr, hdr->subdesc_cnt); - nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); nicvf_check_cqe_tx_errs(nic, cq, cqe_tx); skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr]; - /* For TSO offloaded packets only one head SKB needs to be freed */ + /* For TSO offloaded packets only one SQE will have a valid SKB */ if (skb) { + nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); prefetch(skb); dev_consume_skb_any(skb); sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL; + } else { + /* In case of HW TSO, HW sends a CQE for each segment of a TSO + * packet instead of a single CQE for the whole TSO packet + * transmitted. Each of this CQE points to the same SQE, so + * avoid freeing same SQE multiple times. + */ + if (!nic->hw_tso) + nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); } } @@ -1549,6 +1557,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; + if (!pass1_silicon(nic->pdev)) + nic->hw_tso = true; + netdev->netdev_ops = &nicvf_netdev_ops; netdev->watchdog_timeo = NICVF_TX_TIMEOUT; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 1fbd9084333e8..d0d1b54900610 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -299,7 +299,7 @@ static int nicvf_init_cmp_queue(struct nicvf *nic, return err; cq->desc = cq->dmem.base; - cq->thresh = CMP_QUEUE_CQE_THRESH; + cq->thresh = pass1_silicon(nic->pdev) ? 0 : CMP_QUEUE_CQE_THRESH; nic->cq_coalesce_usecs = (CMP_QUEUE_TIMER_THRESH * 0.05) - 1; return 0; @@ -925,7 +925,7 @@ static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb) { int subdesc_cnt = MIN_SQ_DESC_PER_PKT_XMIT; - if (skb_shinfo(skb)->gso_size) { + if (skb_shinfo(skb)->gso_size && !nic->hw_tso) { subdesc_cnt = nicvf_tso_count_subdescs(skb); return subdesc_cnt; } @@ -940,7 +940,7 @@ static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb) * First subdescriptor for every send descriptor. */ static inline void -nicvf_sq_add_hdr_subdesc(struct snd_queue *sq, int qentry, +nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry, int subdesc_cnt, struct sk_buff *skb, int len) { int proto; @@ -976,6 +976,15 @@ nicvf_sq_add_hdr_subdesc(struct snd_queue *sq, int qentry, break; } } + + if (nic->hw_tso && skb_shinfo(skb)->gso_size) { + hdr->tso = 1; + hdr->tso_start = skb_transport_offset(skb) + tcp_hdrlen(skb); + hdr->tso_max_paysize = skb_shinfo(skb)->gso_size; + /* For non-tunneled pkts, point this to L2 ethertype */ + hdr->inner_l3_offset = skb_network_offset(skb) - 2; + nic->drv_stats.tx_tso++; + } } /* SQ GATHER subdescriptor @@ -1045,7 +1054,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, data_left -= size; tso_build_data(skb, &tso, size); } - nicvf_sq_add_hdr_subdesc(sq, hdr_qentry, + nicvf_sq_add_hdr_subdesc(nic, sq, hdr_qentry, seg_subdescs - 1, skb, seg_len); sq->skbuff[hdr_qentry] = (u64)NULL; qentry = nicvf_get_nxt_sqentry(sq, qentry); @@ -1098,11 +1107,12 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb) qentry = nicvf_get_sq_desc(sq, subdesc_cnt); /* Check if its a TSO packet */ - if (skb_shinfo(skb)->gso_size) + if (skb_shinfo(skb)->gso_size && !nic->hw_tso) return nicvf_sq_append_tso(nic, sq, sq_num, qentry, skb); /* Add SQ header subdesc */ - nicvf_sq_add_hdr_subdesc(sq, qentry, subdesc_cnt - 1, skb, skb->len); + nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1, + skb, skb->len); /* Add SQ gather subdescs */ qentry = nicvf_get_nxt_sqentry(sq, qentry); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index a4f6667fdbd44..c5030a7f213ae 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -75,7 +75,7 @@ */ #define CMP_QSIZE CMP_QUEUE_SIZE2 #define CMP_QUEUE_LEN (1ULL << (CMP_QSIZE + 10)) -#define CMP_QUEUE_CQE_THRESH 0 +#define CMP_QUEUE_CQE_THRESH (NAPI_POLL_WEIGHT / 2) #define CMP_QUEUE_TIMER_THRESH 80 /* ~2usec */ #define RBDR_SIZE RBDR_SIZE0 diff --git a/drivers/net/ethernet/cavium/thunder/q_struct.h b/drivers/net/ethernet/cavium/thunder/q_struct.h index 3c1de97b1add9..9e6d9876bfd04 100644 --- a/drivers/net/ethernet/cavium/thunder/q_struct.h +++ b/drivers/net/ethernet/cavium/thunder/q_struct.h @@ -545,25 +545,28 @@ struct sq_hdr_subdesc { u64 subdesc_cnt:8; u64 csum_l4:2; u64 csum_l3:1; - u64 rsvd0:5; + u64 csum_inner_l4:2; + u64 csum_inner_l3:1; + u64 rsvd0:2; u64 l4_offset:8; u64 l3_offset:8; u64 rsvd1:4; u64 tot_len:20; /* W0 */ - u64 tso_sdc_cont:8; - u64 tso_sdc_first:8; - u64 tso_l4_offset:8; - u64 tso_flags_last:12; - u64 tso_flags_first:12; - u64 rsvd2:2; + u64 rsvd2:24; + u64 inner_l4_offset:8; + u64 inner_l3_offset:8; + u64 tso_start:8; + u64 rsvd3:2; u64 tso_max_paysize:14; /* W1 */ #elif defined(__LITTLE_ENDIAN_BITFIELD) u64 tot_len:20; u64 rsvd1:4; u64 l3_offset:8; u64 l4_offset:8; - u64 rsvd0:5; + u64 rsvd0:2; + u64 csum_inner_l3:1; + u64 csum_inner_l4:2; u64 csum_l3:1; u64 csum_l4:2; u64 subdesc_cnt:8; @@ -574,12 +577,11 @@ struct sq_hdr_subdesc { u64 subdesc_type:4; /* W0 */ u64 tso_max_paysize:14; - u64 rsvd2:2; - u64 tso_flags_first:12; - u64 tso_flags_last:12; - u64 tso_l4_offset:8; - u64 tso_sdc_first:8; - u64 tso_sdc_cont:8; /* W1 */ + u64 rsvd3:2; + u64 tso_start:8; + u64 inner_l3_offset:8; + u64 inner_l4_offset:8; + u64 rsvd2:24; /* W1 */ #endif }; diff --git a/drivers/net/ethernet/chelsio/cxgb/cphy.h b/drivers/net/ethernet/chelsio/cxgb/cphy.h index a4d2a4c08d3f7..bf43da6c6a635 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cphy.h +++ b/drivers/net/ethernet/chelsio/cxgb/cphy.h @@ -137,7 +137,7 @@ static inline int simple_mdio_write(struct cphy *cphy, int reg, /* Convenience initializer */ static inline void cphy_init(struct cphy *phy, struct net_device *dev, - int phy_addr, struct cphy_ops *phy_ops, + int phy_addr, const struct cphy_ops *phy_ops, const struct mdio_ops *mdio_ops) { struct adapter *adapter = netdev_priv(dev); diff --git a/drivers/net/ethernet/chelsio/cxgb/mv88e1xxx.c b/drivers/net/ethernet/chelsio/cxgb/mv88e1xxx.c index 71018a4fdf151..76ce6e538326c 100644 --- a/drivers/net/ethernet/chelsio/cxgb/mv88e1xxx.c +++ b/drivers/net/ethernet/chelsio/cxgb/mv88e1xxx.c @@ -337,7 +337,7 @@ static void mv88e1xxx_destroy(struct cphy *cphy) kfree(cphy); } -static struct cphy_ops mv88e1xxx_ops = { +static const struct cphy_ops mv88e1xxx_ops = { .destroy = mv88e1xxx_destroy, .reset = mv88e1xxx_reset, .interrupt_enable = mv88e1xxx_interrupt_enable, diff --git a/drivers/net/ethernet/chelsio/cxgb/mv88x201x.c b/drivers/net/ethernet/chelsio/cxgb/mv88x201x.c index d0cf611551a17..7ddb301bcba0e 100644 --- a/drivers/net/ethernet/chelsio/cxgb/mv88x201x.c +++ b/drivers/net/ethernet/chelsio/cxgb/mv88x201x.c @@ -195,7 +195,7 @@ static void mv88x201x_destroy(struct cphy *cphy) kfree(cphy); } -static struct cphy_ops mv88x201x_ops = { +static const struct cphy_ops mv88x201x_ops = { .destroy = mv88x201x_destroy, .reset = mv88x201x_reset, .interrupt_enable = mv88x201x_interrupt_enable, diff --git a/drivers/net/ethernet/chelsio/cxgb/my3126.c b/drivers/net/ethernet/chelsio/cxgb/my3126.c index a683fd3bb624d..d546f46c8ef79 100644 --- a/drivers/net/ethernet/chelsio/cxgb/my3126.c +++ b/drivers/net/ethernet/chelsio/cxgb/my3126.c @@ -154,7 +154,7 @@ static void my3126_destroy(struct cphy *cphy) kfree(cphy); } -static struct cphy_ops my3126_ops = { +static const struct cphy_ops my3126_ops = { .destroy = my3126_destroy, .reset = my3126_reset, .interrupt_enable = my3126_interrupt_enable, diff --git a/drivers/net/ethernet/chelsio/cxgb3/ael1002.c b/drivers/net/ethernet/chelsio/cxgb3/ael1002.c index 2028da95afa11..dadf11e3dddb4 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/ael1002.c +++ b/drivers/net/ethernet/chelsio/cxgb3/ael1002.c @@ -198,7 +198,7 @@ static int get_link_status_r(struct cphy *phy, int *link_ok, int *speed, return 0; } -static struct cphy_ops ael1002_ops = { +static const struct cphy_ops ael1002_ops = { .reset = ael1002_reset, .intr_enable = ael1002_intr_noop, .intr_disable = ael1002_intr_noop, @@ -224,7 +224,7 @@ static int ael1006_reset(struct cphy *phy, int wait) return t3_phy_reset(phy, MDIO_MMD_PMAPMD, wait); } -static struct cphy_ops ael1006_ops = { +static const struct cphy_ops ael1006_ops = { .reset = ael1006_reset, .intr_enable = t3_phy_lasi_intr_enable, .intr_disable = t3_phy_lasi_intr_disable, @@ -495,7 +495,7 @@ static int ael2005_intr_handler(struct cphy *phy) return ret ? ret : cphy_cause_link_change; } -static struct cphy_ops ael2005_ops = { +static const struct cphy_ops ael2005_ops = { .reset = ael2005_reset, .intr_enable = ael2005_intr_enable, .intr_disable = ael2005_intr_disable, @@ -801,7 +801,7 @@ static int ael2020_intr_handler(struct cphy *phy) return ret ? ret : cphy_cause_link_change; } -static struct cphy_ops ael2020_ops = { +static const struct cphy_ops ael2020_ops = { .reset = ael2020_reset, .intr_enable = ael2020_intr_enable, .intr_disable = ael2020_intr_disable, @@ -856,7 +856,7 @@ static int get_link_status_x(struct cphy *phy, int *link_ok, int *speed, return 0; } -static struct cphy_ops qt2045_ops = { +static const struct cphy_ops qt2045_ops = { .reset = ael1006_reset, .intr_enable = t3_phy_lasi_intr_enable, .intr_disable = t3_phy_lasi_intr_disable, @@ -921,7 +921,7 @@ static int xaui_direct_power_down(struct cphy *phy, int enable) return 0; } -static struct cphy_ops xaui_direct_ops = { +static const struct cphy_ops xaui_direct_ops = { .reset = xaui_direct_reset, .intr_enable = ael1002_intr_noop, .intr_disable = ael1002_intr_noop, diff --git a/drivers/net/ethernet/chelsio/cxgb3/aq100x.c b/drivers/net/ethernet/chelsio/cxgb3/aq100x.c index 341b7ef1508f2..6af5d200e44fd 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/aq100x.c +++ b/drivers/net/ethernet/chelsio/cxgb3/aq100x.c @@ -247,7 +247,7 @@ static int aq100x_get_link_status(struct cphy *phy, int *link_ok, return 0; } -static struct cphy_ops aq100x_ops = { +static const struct cphy_ops aq100x_ops = { .reset = aq100x_reset, .intr_enable = aq100x_intr_enable, .intr_disable = aq100x_intr_disable, diff --git a/drivers/net/ethernet/chelsio/cxgb3/common.h b/drivers/net/ethernet/chelsio/cxgb3/common.h index 442480982d3f6..1bd7d89666c49 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/common.h +++ b/drivers/net/ethernet/chelsio/cxgb3/common.h @@ -575,7 +575,7 @@ static inline int t3_mdio_write(struct cphy *phy, int mmd, int reg, /* Convenience initializer */ static inline void cphy_init(struct cphy *phy, struct adapter *adapter, - int phy_addr, struct cphy_ops *phy_ops, + int phy_addr, const struct cphy_ops *phy_ops, const struct mdio_ops *mdio_ops, unsigned int caps, const char *desc) { diff --git a/drivers/net/ethernet/chelsio/cxgb3/vsc8211.c b/drivers/net/ethernet/chelsio/cxgb3/vsc8211.c index 4f9a1c2724f4e..8638ad42bf603 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/vsc8211.c +++ b/drivers/net/ethernet/chelsio/cxgb3/vsc8211.c @@ -336,7 +336,7 @@ static int vsc8211_intr_handler(struct cphy *cphy) return cphy_cause; } -static struct cphy_ops vsc8211_ops = { +static const struct cphy_ops vsc8211_ops = { .reset = vsc8211_reset, .intr_enable = vsc8211_intr_enable, .intr_disable = vsc8211_intr_disable, @@ -350,7 +350,7 @@ static struct cphy_ops vsc8211_ops = { .power_down = vsc8211_power_down, }; -static struct cphy_ops vsc8211_fiber_ops = { +static const struct cphy_ops vsc8211_fiber_ops = { .reset = vsc8211_reset, .intr_enable = vsc8211_intr_enable, .intr_disable = vsc8211_intr_disable, diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c index c308429dd9c7f..d288dcf6062f8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c @@ -118,6 +118,11 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6) ret = clip6_get_mbox(dev, (const struct in6_addr *)lip); if (ret) { write_unlock_bh(&ctbl->lock); + dev_err(adap->pdev_dev, + "CLIP FW cmd failed with error %d, " + "Connections using %pI6c wont be " + "offloaded", + ret, ce->addr6.sin6_addr.s6_addr); return ret; } } else { @@ -127,6 +132,9 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6) } } else { write_unlock_bh(&ctbl->lock); + dev_info(adap->pdev_dev, "CLIP table overflow, " + "Connections using %pI6c wont be offloaded", + (void *)lip); return -ENOMEM; } write_unlock_bh(&ctbl->lock); @@ -146,6 +154,9 @@ void cxgb4_clip_release(const struct net_device *dev, const u32 *lip, u8 v6) int hash; int ret = -1; + if (!ctbl) + return; + hash = clip_addr_hash(ctbl, addr, v6); read_lock_bh(&ctbl->lock); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index e01e7228f607d..ec6e849676c14 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -301,6 +301,8 @@ struct devlog_params { /* Stores chip specific parameters */ struct arch_specific_params { u8 nchan; + u8 pm_stats_cnt; + u8 cng_ch_bits_log; /* congestion channel map bits width */ u16 mps_rplc_size; u16 vfcount; u32 sge_fl_db; @@ -398,11 +400,10 @@ struct link_config { enum { MAX_ETH_QSETS = 32, /* # of Ethernet Tx/Rx queue sets */ - MAX_OFLD_QSETS = 16, /* # of offload Tx/Rx queue sets */ + MAX_OFLD_QSETS = 16, /* # of offload Tx, iscsi Rx queue sets */ MAX_CTRL_QUEUES = NCHAN, /* # of control Tx queues */ MAX_RDMA_QUEUES = NCHAN, /* # of streaming RDMA Rx queues */ MAX_RDMA_CIQS = 32, /* # of RDMA concentrator IQs */ - MAX_ISCSI_QUEUES = NCHAN, /* # of streaming iSCSI Rx queues */ }; enum { @@ -420,7 +421,7 @@ enum { INGQ_EXTRAS = 2, /* firmware event queue and */ /* forwarded interrupts */ MAX_INGQ = MAX_ETH_QSETS + MAX_OFLD_QSETS + MAX_RDMA_QUEUES - + MAX_RDMA_CIQS + MAX_ISCSI_QUEUES + INGQ_EXTRAS, + + MAX_RDMA_CIQS + INGQ_EXTRAS, }; struct adapter; @@ -639,7 +640,7 @@ struct sge { struct sge_ctrl_txq ctrlq[MAX_CTRL_QUEUES]; struct sge_eth_rxq ethrxq[MAX_ETH_QSETS]; - struct sge_ofld_rxq ofldrxq[MAX_OFLD_QSETS]; + struct sge_ofld_rxq iscsirxq[MAX_OFLD_QSETS]; struct sge_ofld_rxq rdmarxq[MAX_RDMA_QUEUES]; struct sge_ofld_rxq rdmaciq[MAX_RDMA_CIQS]; struct sge_rspq fw_evtq ____cacheline_aligned_in_smp; @@ -650,10 +651,10 @@ struct sge { u16 max_ethqsets; /* # of available Ethernet queue sets */ u16 ethqsets; /* # of active Ethernet queue sets */ u16 ethtxq_rover; /* Tx queue to clean up next */ - u16 ofldqsets; /* # of active offload queue sets */ + u16 iscsiqsets; /* # of active iSCSI queue sets */ u16 rdmaqs; /* # of available RDMA Rx queues */ u16 rdmaciqs; /* # of available RDMA concentrator IQs */ - u16 ofld_rxq[MAX_OFLD_QSETS]; + u16 iscsi_rxq[MAX_OFLD_QSETS]; u16 rdma_rxq[MAX_RDMA_QUEUES]; u16 rdma_ciq[MAX_RDMA_CIQS]; u16 timer_val[SGE_NTIMERS]; @@ -679,7 +680,7 @@ struct sge { }; #define for_each_ethrxq(sge, i) for (i = 0; i < (sge)->ethqsets; i++) -#define for_each_ofldrxq(sge, i) for (i = 0; i < (sge)->ofldqsets; i++) +#define for_each_iscsirxq(sge, i) for (i = 0; i < (sge)->iscsiqsets; i++) #define for_each_rdmarxq(sge, i) for (i = 0; i < (sge)->rdmaqs; i++) #define for_each_rdmaciq(sge, i) for (i = 0; i < (sge)->rdmaciqs; i++) @@ -1256,6 +1257,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver); int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op); int t4_fw_upgrade(struct adapter *adap, unsigned int mbox, const u8 *fw_data, unsigned int size, int force); +int t4_fl_pkt_align(struct adapter *adap); unsigned int t4_flash_cfg_addr(struct adapter *adapter); int t4_check_fw_version(struct adapter *adap); int t4_get_fw_version(struct adapter *adapter, u32 *vers); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 0d579b192350e..1bab34f923e72 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -757,8 +757,8 @@ static int pm_stats_show(struct seq_file *seq, void *v) }; int i; - u32 tx_cnt[PM_NSTATS], rx_cnt[PM_NSTATS]; - u64 tx_cyc[PM_NSTATS], rx_cyc[PM_NSTATS]; + u32 tx_cnt[T6_PM_NSTATS], rx_cnt[T6_PM_NSTATS]; + u64 tx_cyc[T6_PM_NSTATS], rx_cyc[T6_PM_NSTATS]; struct adapter *adap = seq->private; t4_pmtx_get_stats(adap, tx_cnt, tx_cyc); @@ -773,6 +773,32 @@ static int pm_stats_show(struct seq_file *seq, void *v) for (i = 0; i < PM_NSTATS - 1; i++) seq_printf(seq, "%-13s %10u %20llu\n", rx_pm_stats[i], rx_cnt[i], rx_cyc[i]); + + if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) { + /* In T5 the granularity of the total wait is too fine. + * It is not useful as it reaches the max value too fast. + * Hence display this Input FIFO wait for T6 onwards. + */ + seq_printf(seq, "%13s %10s %20s\n", + " ", "Total wait", "Total Occupancy"); + seq_printf(seq, "Tx FIFO wait %10u %20llu\n", + tx_cnt[i], tx_cyc[i]); + seq_printf(seq, "Rx FIFO wait %10u %20llu\n", + rx_cnt[i], rx_cyc[i]); + + /* Skip index 6 as there is nothing useful ihere */ + i += 2; + + /* At index 7, a new stat for read latency (count, total wait) + * is added. + */ + seq_printf(seq, "%13s %10s %20s\n", + " ", "Reads", "Total wait"); + seq_printf(seq, "Tx latency %10u %20llu\n", + tx_cnt[i], tx_cyc[i]); + seq_printf(seq, "Rx latency %10u %20llu\n", + rx_cnt[i], rx_cyc[i]); + } return 0; } @@ -1559,25 +1585,35 @@ static int mps_tcam_show(struct seq_file *seq, void *v) { struct adapter *adap = seq->private; unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); - if (v == SEQ_START_TOKEN) { - if (adap->params.arch.mps_rplc_size > 128) + if (chip_ver > CHELSIO_T5) { seq_puts(seq, "Idx Ethernet address Mask " + " VNI Mask IVLAN Vld " + "DIP_Hit Lookup Port " "Vld Ports PF VF " "Replication " " P0 P1 P2 P3 ML\n"); - else - seq_puts(seq, "Idx Ethernet address Mask " - "Vld Ports PF VF Replication" - " P0 P1 P2 P3 ML\n"); + } else { + if (adap->params.arch.mps_rplc_size > 128) + seq_puts(seq, "Idx Ethernet address Mask " + "Vld Ports PF VF " + "Replication " + " P0 P1 P2 P3 ML\n"); + else + seq_puts(seq, "Idx Ethernet address Mask " + "Vld Ports PF VF Replication" + " P0 P1 P2 P3 ML\n"); + } } else { u64 mask; u8 addr[ETH_ALEN]; - bool replicate; + bool replicate, dip_hit = false, vlan_vld = false; unsigned int idx = (uintptr_t)v - 2; u64 tcamy, tcamx, val; - u32 cls_lo, cls_hi, ctl; + u32 cls_lo, cls_hi, ctl, data2, vnix = 0, vniy = 0; u32 rplc[8] = {0}; + u8 lookup_type = 0, port_num = 0; + u16 ivlan = 0; if (chip_ver > CHELSIO_T5) { /* CtlCmdType - 0: Read, 1: Write @@ -1596,6 +1632,22 @@ static int mps_tcam_show(struct seq_file *seq, void *v) val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A); tcamy = DMACH_G(val) << 32; tcamy |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A); + data2 = t4_read_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A); + lookup_type = DATALKPTYPE_G(data2); + /* 0 - Outer header, 1 - Inner header + * [71:48] bit locations are overloaded for + * outer vs. inner lookup types. + */ + if (lookup_type && (lookup_type != DATALKPTYPE_M)) { + /* Inner header VNI */ + vniy = ((data2 & DATAVIDH2_F) << 23) | + (DATAVIDH1_G(data2) << 16) | VIDL_G(val); + dip_hit = data2 & DATADIPHIT_F; + } else { + vlan_vld = data2 & DATAVIDH2_F; + ivlan = VIDL_G(val); + } + port_num = DATAPORTNUM_G(data2); /* Read tcamx. Change the control param */ ctl |= CTLXYBITSEL_V(1); @@ -1603,6 +1655,12 @@ static int mps_tcam_show(struct seq_file *seq, void *v) val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A); tcamx = DMACH_G(val) << 32; tcamx |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A); + data2 = t4_read_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A); + if (lookup_type && (lookup_type != DATALKPTYPE_M)) { + /* Inner header VNI mask */ + vnix = ((data2 & DATAVIDH2_F) << 23) | + (DATAVIDH1_G(data2) << 16) | VIDL_G(val); + } } else { tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx)); tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx)); @@ -1662,17 +1720,47 @@ static int mps_tcam_show(struct seq_file *seq, void *v) } tcamxy2valmask(tcamx, tcamy, addr, &mask); - if (chip_ver > CHELSIO_T5) - seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x " - "%012llx%3c %#x%4u%4d", - idx, addr[0], addr[1], addr[2], addr[3], - addr[4], addr[5], (unsigned long long)mask, - (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N', - PORTMAP_G(cls_hi), - T6_PF_G(cls_lo), - (cls_lo & T6_VF_VALID_F) ? - T6_VF_G(cls_lo) : -1); - else + if (chip_ver > CHELSIO_T5) { + /* Inner header lookup */ + if (lookup_type && (lookup_type != DATALKPTYPE_M)) { + seq_printf(seq, + "%3u %02x:%02x:%02x:%02x:%02x:%02x " + "%012llx %06x %06x - - %3c" + " %3c %4x " + "%3c %#x%4u%4d", idx, addr[0], + addr[1], addr[2], addr[3], + addr[4], addr[5], + (unsigned long long)mask, + vniy, vnix, dip_hit ? 'Y' : 'N', + lookup_type ? 'I' : 'O', port_num, + (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N', + PORTMAP_G(cls_hi), + T6_PF_G(cls_lo), + (cls_lo & T6_VF_VALID_F) ? + T6_VF_G(cls_lo) : -1); + } else { + seq_printf(seq, + "%3u %02x:%02x:%02x:%02x:%02x:%02x " + "%012llx - - ", + idx, addr[0], addr[1], addr[2], + addr[3], addr[4], addr[5], + (unsigned long long)mask); + + if (vlan_vld) + seq_printf(seq, "%4u Y ", ivlan); + else + seq_puts(seq, " - N "); + + seq_printf(seq, + "- %3c %4x %3c %#x%4u%4d", + lookup_type ? 'I' : 'O', port_num, + (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N', + PORTMAP_G(cls_hi), + T6_PF_G(cls_lo), + (cls_lo & T6_VF_VALID_F) ? + T6_VF_G(cls_lo) : -1); + } + } else seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x " "%012llx%3c %#x%4u%4d", idx, addr[0], addr[1], addr[2], addr[3], @@ -2245,7 +2333,7 @@ static int sge_qinfo_show(struct seq_file *seq, void *v) { struct adapter *adap = seq->private; int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4); - int iscsi_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4); + int iscsi_entries = DIV_ROUND_UP(adap->sge.iscsiqsets, 4); int rdma_entries = DIV_ROUND_UP(adap->sge.rdmaqs, 4); int ciq_entries = DIV_ROUND_UP(adap->sge.rdmaciqs, 4); int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4); @@ -2331,10 +2419,10 @@ do { \ } else if (iscsi_idx < iscsi_entries) { const struct sge_ofld_rxq *rx = - &adap->sge.ofldrxq[iscsi_idx * 4]; + &adap->sge.iscsirxq[iscsi_idx * 4]; const struct sge_ofld_txq *tx = &adap->sge.ofldtxq[iscsi_idx * 4]; - int n = min(4, adap->sge.ofldqsets - 4 * iscsi_idx); + int n = min(4, adap->sge.iscsiqsets - 4 * iscsi_idx); S("QType:", "iSCSI"); T("TxQ ID:", q.cntxt_id); @@ -2454,7 +2542,7 @@ do { \ static int sge_queue_entries(const struct adapter *adap) { return DIV_ROUND_UP(adap->sge.ethqsets, 4) + - DIV_ROUND_UP(adap->sge.ofldqsets, 4) + + DIV_ROUND_UP(adap->sge.iscsiqsets, 4) + DIV_ROUND_UP(adap->sge.rdmaqs, 4) + DIV_ROUND_UP(adap->sge.rdmaciqs, 4) + DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 2a61a42ab033d..7a0b92b2f73c6 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -686,7 +686,7 @@ static int set_pauseparam(struct net_device *dev, if (epause->tx_pause) lc->requested_fc |= PAUSE_TX; if (netif_running(dev)) - return t4_link_l1cfg(p->adapter, p->adapter->pf, p->tx_chan, + return t4_link_l1cfg(p->adapter, p->adapter->mbox, p->tx_chan, lc); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 0d147610a06f1..b8a5fb0c32d4a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -162,19 +162,8 @@ MODULE_FIRMWARE(FW6_FNAME); static uint force_init; module_param(force_init, uint, 0644); -MODULE_PARM_DESC(force_init, "Forcibly become Master PF and initialize adapter"); - -/* - * Normally if the firmware we connect to has Configuration File support, we - * use that and only fall back to the old Driver-based initialization if the - * Configuration File fails for some reason. If force_old_init is set, then - * we'll always use the old Driver-based initialization sequence. - */ -static uint force_old_init; - -module_param(force_old_init, uint, 0644); -MODULE_PARM_DESC(force_old_init, "Force old initialization sequence, deprecated" - " parameter"); +MODULE_PARM_DESC(force_init, "Forcibly become Master PF and initialize adapter," + "deprecated parameter"); static int dflt_msg_enable = DFLT_MSG_ENABLE; @@ -196,23 +185,6 @@ module_param(msi, int, 0644); MODULE_PARM_DESC(msi, "whether to use INTx (0), MSI (1) or MSI-X (2)"); /* - * Queue interrupt hold-off timer values. Queues default to the first of these - * upon creation. - */ -static unsigned int intr_holdoff[SGE_NTIMERS - 1] = { 5, 10, 20, 50, 100 }; - -module_param_array(intr_holdoff, uint, NULL, 0644); -MODULE_PARM_DESC(intr_holdoff, "values for queue interrupt hold-off timers " - "0..4 in microseconds, deprecated parameter"); - -static unsigned int intr_cnt[SGE_NCOUNTERS - 1] = { 4, 8, 16 }; - -module_param_array(intr_cnt, uint, NULL, 0644); -MODULE_PARM_DESC(intr_cnt, - "thresholds 1..3 for queue interrupt packet counters, " - "deprecated parameter"); - -/* * Normally we tell the chip to deliver Ingress Packets into our DMA buffers * offset by 2 bytes in order to have the IP headers line up on 4-byte * boundaries. This is a requirement for many architectures which will throw @@ -226,13 +198,7 @@ MODULE_PARM_DESC(intr_cnt, */ static int rx_dma_offset = 2; -static bool vf_acls; - #ifdef CONFIG_PCI_IOV -module_param(vf_acls, bool, 0644); -MODULE_PARM_DESC(vf_acls, "if set enable virtualization L2 ACL enforcement, " - "deprecated parameter"); - /* Configure the number of PCI-E Virtual Function which are to be instantiated * on SR-IOV Capable Physical Functions. */ @@ -253,12 +219,6 @@ module_param(select_queue, int, 0644); MODULE_PARM_DESC(select_queue, "Select between kernel provided method of selecting or driver method of selecting TX queue. Default is kernel method."); -static unsigned int tp_vlan_pri_map = HW_TPL_FR_MT_PR_IV_P_FC; - -module_param(tp_vlan_pri_map, uint, 0644); -MODULE_PARM_DESC(tp_vlan_pri_map, "global compressed filter configuration, " - "deprecated parameter"); - static struct dentry *cxgb4_debugfs_root; static LIST_HEAD(adapter_list); @@ -766,8 +726,8 @@ static void name_msix_vecs(struct adapter *adap) } /* offload queues */ - for_each_ofldrxq(&adap->sge, i) - snprintf(adap->msix_info[msi_idx++].desc, n, "%s-ofld%d", + for_each_iscsirxq(&adap->sge, i) + snprintf(adap->msix_info[msi_idx++].desc, n, "%s-iscsi%d", adap->port[0]->name, i); for_each_rdmarxq(&adap->sge, i) @@ -782,7 +742,7 @@ static void name_msix_vecs(struct adapter *adap) static int request_msix_queue_irqs(struct adapter *adap) { struct sge *s = &adap->sge; - int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0; + int err, ethqidx, iscsiqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0; int msi_index = 2; err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0, @@ -799,11 +759,11 @@ static int request_msix_queue_irqs(struct adapter *adap) goto unwind; msi_index++; } - for_each_ofldrxq(s, ofldqidx) { + for_each_iscsirxq(s, iscsiqidx) { err = request_irq(adap->msix_info[msi_index].vec, t4_sge_intr_msix, 0, adap->msix_info[msi_index].desc, - &s->ofldrxq[ofldqidx].rspq); + &s->iscsirxq[iscsiqidx].rspq); if (err) goto unwind; msi_index++; @@ -835,9 +795,9 @@ unwind: while (--rdmaqidx >= 0) free_irq(adap->msix_info[--msi_index].vec, &s->rdmarxq[rdmaqidx].rspq); - while (--ofldqidx >= 0) + while (--iscsiqidx >= 0) free_irq(adap->msix_info[--msi_index].vec, - &s->ofldrxq[ofldqidx].rspq); + &s->iscsirxq[iscsiqidx].rspq); while (--ethqidx >= 0) free_irq(adap->msix_info[--msi_index].vec, &s->ethrxq[ethqidx].rspq); @@ -853,8 +813,9 @@ static void free_msix_queue_irqs(struct adapter *adap) free_irq(adap->msix_info[1].vec, &s->fw_evtq); for_each_ethrxq(s, i) free_irq(adap->msix_info[msi_index++].vec, &s->ethrxq[i].rspq); - for_each_ofldrxq(s, i) - free_irq(adap->msix_info[msi_index++].vec, &s->ofldrxq[i].rspq); + for_each_iscsirxq(s, i) + free_irq(adap->msix_info[msi_index++].vec, + &s->iscsirxq[i].rspq); for_each_rdmarxq(s, i) free_irq(adap->msix_info[msi_index++].vec, &s->rdmarxq[i].rspq); for_each_rdmaciq(s, i) @@ -1093,8 +1054,8 @@ freeout: t4_free_sge_resources(adap); } } - j = s->ofldqsets / adap->params.nports; /* ofld queues per channel */ - for_each_ofldrxq(s, i) { + j = s->iscsiqsets / adap->params.nports; /* iscsi queues per channel */ + for_each_iscsirxq(s, i) { err = t4_sge_alloc_ofld_txq(adap, &s->ofldtxq[i], adap->port[i / j], s->fw_evtq.cntxt_id); @@ -1110,7 +1071,7 @@ freeout: t4_free_sge_resources(adap); msi_idx += nq; \ } while (0) - ALLOC_OFLD_RXQS(s->ofldrxq, s->ofldqsets, j, s->ofld_rxq); + ALLOC_OFLD_RXQS(s->iscsirxq, s->iscsiqsets, j, s->iscsi_rxq); ALLOC_OFLD_RXQS(s->rdmarxq, s->rdmaqs, 1, s->rdma_rxq); j = s->rdmaciqs / adap->params.nports; /* rdmaq queues per channel */ ALLOC_OFLD_RXQS(s->rdmaciq, s->rdmaciqs, j, s->rdma_ciq); @@ -1181,16 +1142,10 @@ static int set_filter_wr(struct adapter *adapter, int fidx) */ if (f->fs.newdmac || f->fs.newvlan) { /* allocate L2T entry for new filter */ - f->l2t = t4_l2t_alloc_switching(adapter->l2t); + f->l2t = t4_l2t_alloc_switching(adapter, f->fs.vlan, + f->fs.eport, f->fs.dmac); if (f->l2t == NULL) { kfree_skb(skb); - return -EAGAIN; - } - if (t4_l2t_set_switching(adapter, f->l2t, f->fs.vlan, - f->fs.eport, f->fs.dmac)) { - cxgb4_l2t_release(f->l2t); - f->l2t = NULL; - kfree_skb(skb); return -ENOMEM; } } @@ -1511,7 +1466,7 @@ int cxgb4_alloc_stid(struct tid_info *t, int family, void *data) else stid = -1; } else { - stid = bitmap_find_free_region(t->stid_bmap, t->nstids, 2); + stid = bitmap_find_free_region(t->stid_bmap, t->nstids, 1); if (stid < 0) stid = -1; } @@ -1525,7 +1480,7 @@ int cxgb4_alloc_stid(struct tid_info *t, int family, void *data) if (family == PF_INET) t->stids_in_use++; else - t->stids_in_use += 4; + t->stids_in_use += 2; } spin_unlock_bh(&t->stid_lock); return stid; @@ -1576,13 +1531,13 @@ void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family) if (family == PF_INET) __clear_bit(stid, t->stid_bmap); else - bitmap_release_region(t->stid_bmap, stid, 2); + bitmap_release_region(t->stid_bmap, stid, 1); t->stid_tab[stid].data = NULL; if (stid < t->nstids) { if (family == PF_INET) t->stids_in_use--; else - t->stids_in_use -= 4; + t->stids_in_use -= 2; } else { t->sftids_in_use--; } @@ -2283,7 +2238,7 @@ static void disable_dbs(struct adapter *adap) for_each_ethrxq(&adap->sge, i) disable_txq_db(&adap->sge.ethtxq[i].q); - for_each_ofldrxq(&adap->sge, i) + for_each_iscsirxq(&adap->sge, i) disable_txq_db(&adap->sge.ofldtxq[i].q); for_each_port(adap, i) disable_txq_db(&adap->sge.ctrlq[i].q); @@ -2295,7 +2250,7 @@ static void enable_dbs(struct adapter *adap) for_each_ethrxq(&adap->sge, i) enable_txq_db(adap, &adap->sge.ethtxq[i].q); - for_each_ofldrxq(&adap->sge, i) + for_each_iscsirxq(&adap->sge, i) enable_txq_db(adap, &adap->sge.ofldtxq[i].q); for_each_port(adap, i) enable_txq_db(adap, &adap->sge.ctrlq[i].q); @@ -2365,7 +2320,7 @@ static void recover_all_queues(struct adapter *adap) for_each_ethrxq(&adap->sge, i) sync_txq_pidx(adap, &adap->sge.ethtxq[i].q); - for_each_ofldrxq(&adap->sge, i) + for_each_iscsirxq(&adap->sge, i) sync_txq_pidx(adap, &adap->sge.ofldtxq[i].q); for_each_port(adap, i) sync_txq_pidx(adap, &adap->sge.ctrlq[i].q); @@ -2449,10 +2404,10 @@ static void uld_attach(struct adapter *adap, unsigned int uld) lli.nrxq = adap->sge.rdmaqs; lli.nciq = adap->sge.rdmaciqs; } else if (uld == CXGB4_ULD_ISCSI) { - lli.rxq_ids = adap->sge.ofld_rxq; - lli.nrxq = adap->sge.ofldqsets; + lli.rxq_ids = adap->sge.iscsi_rxq; + lli.nrxq = adap->sge.iscsiqsets; } - lli.ntxq = adap->sge.ofldqsets; + lli.ntxq = adap->sge.iscsiqsets; lli.nchan = adap->params.nports; lli.nports = adap->params.nports; lli.wr_cred = adap->params.ofldq_wr_cred; @@ -3146,16 +3101,6 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) if (ret < 0) return ret; - /* select capabilities we'll be using */ - if (c->niccaps & htons(FW_CAPS_CONFIG_NIC_VM)) { - if (!vf_acls) - c->niccaps ^= htons(FW_CAPS_CONFIG_NIC_VM); - else - c->niccaps = htons(FW_CAPS_CONFIG_NIC_VM); - } else if (vf_acls) { - dev_err(adap->pdev_dev, "virtualization ACLs not supported"); - return ret; - } c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F); ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), NULL); @@ -4348,11 +4293,11 @@ static void cfg_queues(struct adapter *adap) * capped by the number of available cores. */ if (n10g) { - i = min_t(int, ARRAY_SIZE(s->ofldrxq), + i = min_t(int, ARRAY_SIZE(s->iscsirxq), num_online_cpus()); - s->ofldqsets = roundup(i, adap->params.nports); + s->iscsiqsets = roundup(i, adap->params.nports); } else - s->ofldqsets = adap->params.nports; + s->iscsiqsets = adap->params.nports; /* For RDMA one Rx queue per channel suffices */ s->rdmaqs = adap->params.nports; /* Try and allow at least 1 CIQ per cpu rounding down @@ -4383,8 +4328,8 @@ static void cfg_queues(struct adapter *adap) for (i = 0; i < ARRAY_SIZE(s->ofldtxq); i++) s->ofldtxq[i].q.size = 1024; - for (i = 0; i < ARRAY_SIZE(s->ofldrxq); i++) { - struct sge_ofld_rxq *r = &s->ofldrxq[i]; + for (i = 0; i < ARRAY_SIZE(s->iscsirxq); i++) { + struct sge_ofld_rxq *r = &s->iscsirxq[i]; init_rspq(adap, &r->rspq, 5, 1, 1024, 64); r->rspq.uld = CXGB4_ULD_ISCSI; @@ -4465,7 +4410,7 @@ static int enable_msix(struct adapter *adap) want = s->max_ethqsets + EXTRA_VECS; if (is_offload(adap)) { - want += s->rdmaqs + s->rdmaciqs + s->ofldqsets; + want += s->rdmaqs + s->rdmaciqs + s->iscsiqsets; /* need nchan for each possible ULD */ ofld_need = 3 * nchan; } @@ -4504,13 +4449,13 @@ static int enable_msix(struct adapter *adap) /* leftovers go to OFLD */ i = allocated - EXTRA_VECS - s->max_ethqsets - s->rdmaqs - s->rdmaciqs; - s->ofldqsets = (i / nchan) * nchan; /* round down */ + s->iscsiqsets = (i / nchan) * nchan; /* round down */ } for (i = 0; i < allocated; ++i) adap->msix_info[i].vec = entries[i].vector; dev_info(adap->pdev_dev, "%d MSI-X vectors allocated, " "nic %d iscsi %d rdma cpl %d rdma ciq %d\n", - allocated, s->max_ethqsets, s->ofldqsets, s->rdmaqs, + allocated, s->max_ethqsets, s->iscsiqsets, s->rdmaqs, s->rdmaciqs); kfree(entries); @@ -4538,6 +4483,79 @@ static int init_rss(struct adapter *adap) return 0; } +static int cxgb4_get_pcie_dev_link_caps(struct adapter *adap, + enum pci_bus_speed *speed, + enum pcie_link_width *width) +{ + u32 lnkcap1, lnkcap2; + int err1, err2; + +#define PCIE_MLW_CAP_SHIFT 4 /* start of MLW mask in link capabilities */ + + *speed = PCI_SPEED_UNKNOWN; + *width = PCIE_LNK_WIDTH_UNKNOWN; + + err1 = pcie_capability_read_dword(adap->pdev, PCI_EXP_LNKCAP, + &lnkcap1); + err2 = pcie_capability_read_dword(adap->pdev, PCI_EXP_LNKCAP2, + &lnkcap2); + if (!err2 && lnkcap2) { /* PCIe r3.0-compliant */ + if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB) + *speed = PCIE_SPEED_8_0GT; + else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB) + *speed = PCIE_SPEED_5_0GT; + else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB) + *speed = PCIE_SPEED_2_5GT; + } + if (!err1) { + *width = (lnkcap1 & PCI_EXP_LNKCAP_MLW) >> PCIE_MLW_CAP_SHIFT; + if (!lnkcap2) { /* pre-r3.0 */ + if (lnkcap1 & PCI_EXP_LNKCAP_SLS_5_0GB) + *speed = PCIE_SPEED_5_0GT; + else if (lnkcap1 & PCI_EXP_LNKCAP_SLS_2_5GB) + *speed = PCIE_SPEED_2_5GT; + } + } + + if (*speed == PCI_SPEED_UNKNOWN || *width == PCIE_LNK_WIDTH_UNKNOWN) + return err1 ? err1 : err2 ? err2 : -EINVAL; + return 0; +} + +static void cxgb4_check_pcie_caps(struct adapter *adap) +{ + enum pcie_link_width width, width_cap; + enum pci_bus_speed speed, speed_cap; + +#define PCIE_SPEED_STR(speed) \ + (speed == PCIE_SPEED_8_0GT ? "8.0GT/s" : \ + speed == PCIE_SPEED_5_0GT ? "5.0GT/s" : \ + speed == PCIE_SPEED_2_5GT ? "2.5GT/s" : \ + "Unknown") + + if (cxgb4_get_pcie_dev_link_caps(adap, &speed_cap, &width_cap)) { + dev_warn(adap->pdev_dev, + "Unable to determine PCIe device BW capabilities\n"); + return; + } + + if (pcie_get_minimum_link(adap->pdev, &speed, &width) || + speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN) { + dev_warn(adap->pdev_dev, + "Unable to determine PCI Express bandwidth.\n"); + return; + } + + dev_info(adap->pdev_dev, "PCIe link speed is %s, device supports %s\n", + PCIE_SPEED_STR(speed), PCIE_SPEED_STR(speed_cap)); + dev_info(adap->pdev_dev, "PCIe link width is x%d, device supports x%d\n", + width, width_cap); + if (speed < speed_cap || width < width_cap) + dev_info(adap->pdev_dev, + "A slot with more lanes and/or higher speed is " + "suggested for optimal performance.\n"); +} + static void print_port_info(const struct net_device *dev) { char buf[80]; @@ -4565,10 +4583,10 @@ static void print_port_info(const struct net_device *dev) --bufp; sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type)); - netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n", + netdev_info(dev, "Chelsio %s rev %d %s %sNIC %s\n", adap->params.vpd.id, CHELSIO_CHIP_RELEASE(adap->params.chip), buf, - is_offload(adap) ? "R" : "", adap->params.pci.width, spd, + is_offload(adap) ? "R" : "", (adap->flags & USING_MSIX) ? " MSI-X" : (adap->flags & USING_MSI) ? " MSI" : ""); netdev_info(dev, "S/N: %s, P/N: %s\n", @@ -4787,8 +4805,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* configure SGE_STAT_CFG_A to read WC stats */ if (!is_t4(adapter->params.chip)) - t4_write_reg(adapter, SGE_STAT_CFG_A, - STATSOURCE_T5_V(7) | STATMODE_V(0)); + t4_write_reg(adapter, SGE_STAT_CFG_A, STATSOURCE_T5_V(7) | + (is_t5(adapter->params.chip) ? STATMODE_V(0) : + T6_STATMODE_V(0))); for_each_port(adapter, i) { struct net_device *netdev; @@ -4865,15 +4884,25 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } #if IS_ENABLED(CONFIG_IPV6) - adapter->clipt = t4_init_clip_tbl(adapter->clipt_start, - adapter->clipt_end); - if (!adapter->clipt) { - /* We tolerate a lack of clip_table, giving up - * some functionality + if ((CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) && + (!(t4_read_reg(adapter, LE_DB_CONFIG_A) & ASLIPCOMPEN_F))) { + /* CLIP functionality is not present in hardware, + * hence disable all offload features */ dev_warn(&pdev->dev, - "could not allocate Clip table, continuing\n"); + "CLIP not enabled in hardware, continuing\n"); adapter->params.offload = 0; + } else { + adapter->clipt = t4_init_clip_tbl(adapter->clipt_start, + adapter->clipt_end); + if (!adapter->clipt) { + /* We tolerate a lack of clip_table, giving up + * some functionality + */ + dev_warn(&pdev->dev, + "could not allocate Clip table, continuing\n"); + adapter->params.offload = 0; + } } #endif if (is_offload(adapter) && tid_init(&adapter->tids) < 0) { @@ -4904,6 +4933,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) else if (msi > 0 && pci_enable_msi(pdev) == 0) adapter->flags |= USING_MSI; + /* check for PCI Express bandwidth capabiltites */ + cxgb4_check_pcie_caps(adapter); + err = init_rss(adapter); if (err) goto out_free_dev; diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index ac27898c6ab0b..5b0f3ef348e9e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -66,7 +66,7 @@ struct l2t_data { static inline unsigned int vlan_prio(const struct l2t_entry *e) { - return e->vlan >> 13; + return e->vlan >> VLAN_PRIO_SHIFT; } static inline void l2t_hold(struct l2t_data *d, struct l2t_entry *e) @@ -161,8 +161,7 @@ static int write_l2e(struct adapter *adap, struct l2t_entry *e, int sync) memcpy(e->dmac, e->neigh->ha, sizeof(e->dmac)); memcpy(req->dst_mac, e->dmac, sizeof(req->dst_mac)); - set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0); - t4_ofld_send(adap, skb); + t4_mgmt_tx(adap, skb); if (sync && e->state != L2T_STATE_SWITCHING) e->state = L2T_STATE_SYNC_WRITE; @@ -175,14 +174,10 @@ static int write_l2e(struct adapter *adap, struct l2t_entry *e, int sync) */ static void send_pending(struct adapter *adap, struct l2t_entry *e) { - while (e->arpq_head) { - struct sk_buff *skb = e->arpq_head; + struct sk_buff *skb; - e->arpq_head = skb->next; - skb->next = NULL; + while ((skb = __skb_dequeue(&e->arpq)) != NULL) t4_ofld_send(adap, skb); - } - e->arpq_tail = NULL; } /* @@ -222,12 +217,7 @@ void do_l2t_write_rpl(struct adapter *adap, const struct cpl_l2t_write_rpl *rpl) */ static inline void arpq_enqueue(struct l2t_entry *e, struct sk_buff *skb) { - skb->next = NULL; - if (e->arpq_head) - e->arpq_tail->next = skb; - else - e->arpq_head = skb; - e->arpq_tail = skb; + __skb_queue_tail(&e->arpq, skb); } int cxgb4_l2t_send(struct net_device *dev, struct sk_buff *skb, @@ -259,7 +249,8 @@ again: if (e->state == L2T_STATE_RESOLVING && !neigh_event_send(e->neigh, NULL)) { spin_lock_bh(&e->lock); - if (e->state == L2T_STATE_RESOLVING && e->arpq_head) + if (e->state == L2T_STATE_RESOLVING && + !skb_queue_empty(&e->arpq)) write_l2e(adap, e, 1); spin_unlock_bh(&e->lock); } @@ -305,12 +296,82 @@ found: return e; } -/* - * Called when an L2T entry has no more users. +static struct l2t_entry *find_or_alloc_l2e(struct l2t_data *d, u16 vlan, + u8 port, u8 *dmac) +{ + struct l2t_entry *end, *e, **p; + struct l2t_entry *first_free = NULL; + + for (e = &d->l2tab[0], end = &d->l2tab[d->l2t_size]; e != end; ++e) { + if (atomic_read(&e->refcnt) == 0) { + if (!first_free) + first_free = e; + } else { + if (e->state == L2T_STATE_SWITCHING) { + if (ether_addr_equal(e->dmac, dmac) && + (e->vlan == vlan) && (e->lport == port)) + goto exists; + } + } + } + + if (first_free) { + e = first_free; + goto found; + } + + return NULL; + +found: + /* The entry we found may be an inactive entry that is + * presently in the hash table. We need to remove it. + */ + if (e->state < L2T_STATE_SWITCHING) + for (p = &d->l2tab[e->hash].first; *p; p = &(*p)->next) + if (*p == e) { + *p = e->next; + e->next = NULL; + break; + } + e->state = L2T_STATE_UNUSED; + +exists: + return e; +} + +/* Called when an L2T entry has no more users. The entry is left in the hash + * table since it is likely to be reused but we also bump nfree to indicate + * that the entry can be reallocated for a different neighbor. We also drop + * the existing neighbor reference in case the neighbor is going away and is + * waiting on our reference. + * + * Because entries can be reallocated to other neighbors once their ref count + * drops to 0 we need to take the entry's lock to avoid races with a new + * incarnation. */ +static void _t4_l2e_free(struct l2t_entry *e) +{ + struct l2t_data *d; + struct sk_buff *skb; + + if (atomic_read(&e->refcnt) == 0) { /* hasn't been recycled */ + if (e->neigh) { + neigh_release(e->neigh); + e->neigh = NULL; + } + while ((skb = __skb_dequeue(&e->arpq)) != NULL) + kfree_skb(skb); + } + + d = container_of(e, struct l2t_data, l2tab[e->idx]); + atomic_inc(&d->nfree); +} + +/* Locked version of _t4_l2e_free */ static void t4_l2e_free(struct l2t_entry *e) { struct l2t_data *d; + struct sk_buff *skb; spin_lock_bh(&e->lock); if (atomic_read(&e->refcnt) == 0) { /* hasn't been recycled */ @@ -318,13 +379,8 @@ static void t4_l2e_free(struct l2t_entry *e) neigh_release(e->neigh); e->neigh = NULL; } - while (e->arpq_head) { - struct sk_buff *skb = e->arpq_head; - - e->arpq_head = skb->next; + while ((skb = __skb_dequeue(&e->arpq)) != NULL) kfree_skb(skb); - } - e->arpq_tail = NULL; } spin_unlock_bh(&e->lock); @@ -457,18 +513,19 @@ EXPORT_SYMBOL(cxgb4_select_ntuple); * on the arpq head. If a packet specifies a failure handler it is invoked, * otherwise the packet is sent to the device. */ -static void handle_failed_resolution(struct adapter *adap, struct sk_buff *arpq) +static void handle_failed_resolution(struct adapter *adap, struct l2t_entry *e) { - while (arpq) { - struct sk_buff *skb = arpq; + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&e->arpq)) != NULL) { const struct l2t_skb_cb *cb = L2T_SKB_CB(skb); - arpq = skb->next; - skb->next = NULL; + spin_unlock(&e->lock); if (cb->arp_err_handler) cb->arp_err_handler(cb->handle, skb); else t4_ofld_send(adap, skb); + spin_lock(&e->lock); } } @@ -479,7 +536,7 @@ static void handle_failed_resolution(struct adapter *adap, struct sk_buff *arpq) void t4_l2t_update(struct adapter *adap, struct neighbour *neigh) { struct l2t_entry *e; - struct sk_buff *arpq = NULL; + struct sk_buff_head *arpq = NULL; struct l2t_data *d = adap->l2t; int addr_len = neigh->tbl->key_len; u32 *addr = (u32 *) neigh->primary_key; @@ -506,10 +563,9 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh) if (e->state == L2T_STATE_RESOLVING) { if (neigh->nud_state & NUD_FAILED) { - arpq = e->arpq_head; - e->arpq_head = e->arpq_tail = NULL; + arpq = &e->arpq; } else if ((neigh->nud_state & (NUD_CONNECTED | NUD_STALE)) && - e->arpq_head) { + !skb_queue_empty(&e->arpq)) { write_l2e(adap, e, 1); } } else { @@ -519,43 +575,66 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh) write_l2e(adap, e, 0); } - spin_unlock_bh(&e->lock); - if (arpq) - handle_failed_resolution(adap, arpq); + handle_failed_resolution(adap, e); + spin_unlock_bh(&e->lock); } /* Allocate an L2T entry for use by a switching rule. Such need to be * explicitly freed and while busy they are not on any hash chain, so normal * address resolution updates do not see them. */ -struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d) +struct l2t_entry *t4_l2t_alloc_switching(struct adapter *adap, u16 vlan, + u8 port, u8 *eth_addr) { + struct l2t_data *d = adap->l2t; struct l2t_entry *e; + int ret; write_lock_bh(&d->lock); - e = alloc_l2e(d); + e = find_or_alloc_l2e(d, vlan, port, eth_addr); if (e) { spin_lock(&e->lock); /* avoid race with t4_l2t_free */ - e->state = L2T_STATE_SWITCHING; - atomic_set(&e->refcnt, 1); + if (!atomic_read(&e->refcnt)) { + e->state = L2T_STATE_SWITCHING; + e->vlan = vlan; + e->lport = port; + ether_addr_copy(e->dmac, eth_addr); + atomic_set(&e->refcnt, 1); + ret = write_l2e(adap, e, 0); + if (ret < 0) { + _t4_l2e_free(e); + spin_unlock(&e->lock); + write_unlock_bh(&d->lock); + return NULL; + } + } else { + atomic_inc(&e->refcnt); + } + spin_unlock(&e->lock); } write_unlock_bh(&d->lock); return e; } -/* Sets/updates the contents of a switching L2T entry that has been allocated - * with an earlier call to @t4_l2t_alloc_switching. +/** + * @dev: net_device pointer + * @vlan: VLAN Id + * @port: Associated port + * @dmac: Destination MAC address to add to L2T + * Returns pointer to the allocated l2t entry + * + * Allocates an L2T entry for use by switching rule of a filter */ -int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan, - u8 port, u8 *eth_addr) +struct l2t_entry *cxgb4_l2t_alloc_switching(struct net_device *dev, u16 vlan, + u8 port, u8 *dmac) { - e->vlan = vlan; - e->lport = port; - memcpy(e->dmac, eth_addr, ETH_ALEN); - return write_l2e(adap, e, 0); + struct adapter *adap = netdev2adap(dev); + + return t4_l2t_alloc_switching(adap, vlan, port, dmac); } +EXPORT_SYMBOL(cxgb4_l2t_alloc_switching); struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end) { @@ -585,6 +664,7 @@ struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end) d->l2tab[i].state = L2T_STATE_UNUSED; spin_lock_init(&d->l2tab[i].lock); atomic_set(&d->l2tab[i].refcnt, 0); + skb_queue_head_init(&d->l2tab[i].arpq); } return d; } @@ -619,7 +699,8 @@ static char l2e_state(const struct l2t_entry *e) case L2T_STATE_VALID: return 'V'; case L2T_STATE_STALE: return 'S'; case L2T_STATE_SYNC_WRITE: return 'W'; - case L2T_STATE_RESOLVING: return e->arpq_head ? 'A' : 'R'; + case L2T_STATE_RESOLVING: + return skb_queue_empty(&e->arpq) ? 'R' : 'A'; case L2T_STATE_SWITCHING: return 'X'; default: return 'U'; diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h index b38dc526aad56..4e2d47ac102b5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.h @@ -76,8 +76,7 @@ struct l2t_entry { struct neighbour *neigh; /* associated neighbour */ struct l2t_entry *first; /* start of hash chain */ struct l2t_entry *next; /* next l2t_entry on chain */ - struct sk_buff *arpq_head; /* queue of packets awaiting resolution */ - struct sk_buff *arpq_tail; + struct sk_buff_head arpq; /* packet queue awaiting resolution */ spinlock_t lock; atomic_t refcnt; /* entry reference count */ u16 hash; /* hash bucket the entry is on */ @@ -114,10 +113,11 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh, unsigned int priority); u64 cxgb4_select_ntuple(struct net_device *dev, const struct l2t_entry *l2t); +struct l2t_entry *cxgb4_l2t_alloc_switching(struct net_device *dev, u16 vlan, + u8 port, u8 *dmac); void t4_l2t_update(struct adapter *adap, struct neighbour *neigh); -struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d); -int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan, - u8 port, u8 *eth_addr); +struct l2t_entry *t4_l2t_alloc_switching(struct adapter *adap, u16 vlan, + u8 port, u8 *dmac); struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end); void do_l2t_write_rpl(struct adapter *p, const struct cpl_l2t_write_rpl *rpl); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 8d35ce317f679..b4eb4680a27cc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2288,7 +2288,7 @@ static int napi_rx_handler(struct napi_struct *napi, int budget) if (likely(work_done < budget)) { int timer_index; - napi_complete(napi); + napi_complete_done(napi, work_done); timer_index = QINTR_TIMER_IDX_G(q->next_intr_params); if (q->adaptive_rx) { @@ -2555,7 +2555,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, iq->size = roundup(iq->size, 16); iq->desc = alloc_ring(adap->pdev_dev, iq->size, iq->iqe_len, 0, - &iq->phys_addr, NULL, 0, NUMA_NO_NODE); + &iq->phys_addr, NULL, 0, + dev_to_node(adap->pdev_dev)); if (!iq->desc) return -ENOMEM; @@ -2595,7 +2596,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, fl->size = roundup(fl->size, 8); fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64), sizeof(struct rx_sw_desc), &fl->addr, - &fl->sdesc, s->stat_len, NUMA_NO_NODE); + &fl->sdesc, s->stat_len, + dev_to_node(adap->pdev_dev)); if (!fl->desc) goto fl_nomem; @@ -2668,8 +2670,9 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, * simple (and hopefully less wrong). */ if (!is_t4(adap->params.chip) && cong >= 0) { - u32 param, val; + u32 param, val, ch_map = 0; int i; + u16 cng_ch_bits_log = adap->params.arch.cng_ch_bits_log; param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_CONM_CTXT) | @@ -2681,9 +2684,9 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, CONMCTXT_CNGTPMODE_V(CONMCTXT_CNGTPMODE_CHANNEL_X); for (i = 0; i < 4; i++) { if (cong & (1 << i)) - val |= - CONMCTXT_CNGCHMAP_V(1 << (i << 2)); + ch_map |= 1 << (i << cng_ch_bits_log); } + val |= CONMCTXT_CNGCHMAP_V(ch_map); } ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val); @@ -2978,7 +2981,7 @@ void t4_free_sge_resources(struct adapter *adap) } /* clean up RDMA and iSCSI Rx queues */ - t4_free_ofld_rxqs(adap, adap->sge.ofldqsets, adap->sge.ofldrxq); + t4_free_ofld_rxqs(adap, adap->sge.iscsiqsets, adap->sge.iscsirxq); t4_free_ofld_rxqs(adap, adap->sge.rdmaqs, adap->sge.rdmarxq); t4_free_ofld_rxqs(adap, adap->sge.rdmaciqs, adap->sge.rdmaciq); @@ -3171,8 +3174,7 @@ static int t4_sge_init_soft(struct adapter *adap) int t4_sge_init(struct adapter *adap) { struct sge *s = &adap->sge; - u32 sge_control, sge_control2, sge_conm_ctrl; - unsigned int ingpadboundary, ingpackboundary; + u32 sge_control, sge_conm_ctrl; int ret, egress_threshold; /* @@ -3183,35 +3185,7 @@ int t4_sge_init(struct adapter *adap) s->pktshift = PKTSHIFT_G(sge_control); s->stat_len = (sge_control & EGRSTATUSPAGESIZE_F) ? 128 : 64; - /* T4 uses a single control field to specify both the PCIe Padding and - * Packing Boundary. T5 introduced the ability to specify these - * separately. The actual Ingress Packet Data alignment boundary - * within Packed Buffer Mode is the maximum of these two - * specifications. (Note that it makes no real practical sense to - * have the Pading Boudary be larger than the Packing Boundary but you - * could set the chip up that way and, in fact, legacy T4 code would - * end doing this because it would initialize the Padding Boundary and - * leave the Packing Boundary initialized to 0 (16 bytes).) - */ - ingpadboundary = 1 << (INGPADBOUNDARY_G(sge_control) + - INGPADBOUNDARY_SHIFT_X); - if (is_t4(adap->params.chip)) { - s->fl_align = ingpadboundary; - } else { - /* T5 has a different interpretation of one of the PCIe Packing - * Boundary values. - */ - sge_control2 = t4_read_reg(adap, SGE_CONTROL2_A); - ingpackboundary = INGPACKBOUNDARY_G(sge_control2); - if (ingpackboundary == INGPACKBOUNDARY_16B_X) - ingpackboundary = 16; - else - ingpackboundary = 1 << (ingpackboundary + - INGPACKBOUNDARY_SHIFT_X); - - s->fl_align = max(ingpadboundary, ingpackboundary); - } - + s->fl_align = t4_fl_pkt_align(adap); ret = t4_sge_init_soft(adap); if (ret < 0) return ret; @@ -3229,10 +3203,21 @@ int t4_sge_init(struct adapter *adap) * buffers. */ sge_conm_ctrl = t4_read_reg(adap, SGE_CONM_CTRL_A); - if (is_t4(adap->params.chip)) + switch (CHELSIO_CHIP_VERSION(adap->params.chip)) { + case CHELSIO_T4: egress_threshold = EGRTHRESHOLD_G(sge_conm_ctrl); - else + break; + case CHELSIO_T5: egress_threshold = EGRTHRESHOLDPACKING_G(sge_conm_ctrl); + break; + case CHELSIO_T6: + egress_threshold = T6_EGRTHRESHOLDPACKING_G(sge_conm_ctrl); + break; + default: + dev_err(adap->pdev_dev, "Unsupported Chip version %d\n", + CHELSIO_CHIP_VERSION(adap->params.chip)); + return -EINVAL; + } s->fl_starve_thres = 2*egress_threshold + 1; t4_idma_monitor_init(adap, &s->idma_monitor); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index cf61a5869c6e0..636b4691f2527 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -1942,8 +1942,12 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x1190, 0x1194, 0x11a0, 0x11a4, 0x11b0, 0x11b4, - 0x11fc, 0x1254, - 0x1280, 0x133c, + 0x11fc, 0x1258, + 0x1280, 0x12d4, + 0x12d9, 0x12d9, + 0x12de, 0x12de, + 0x12e3, 0x12e3, + 0x12e8, 0x133c, 0x1800, 0x18fc, 0x3000, 0x302c, 0x3060, 0x30b0, @@ -1973,7 +1977,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x5e50, 0x5e94, 0x5ea0, 0x5eb0, 0x5ec0, 0x5ec0, - 0x5ec8, 0x5ecc, + 0x5ec8, 0x5ed0, 0x6000, 0x6020, 0x6028, 0x6040, 0x6058, 0x609c, @@ -2048,7 +2052,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x19150, 0x19194, 0x1919c, 0x191b0, 0x191d0, 0x191e8, - 0x19238, 0x192b0, + 0x19238, 0x19290, + 0x192a4, 0x192b0, 0x192bc, 0x192bc, 0x19348, 0x1934c, 0x193f8, 0x19418, @@ -2442,7 +2447,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x40280, 0x40280, 0x40304, 0x40304, 0x40330, 0x4033c, - 0x41304, 0x413c8, + 0x41304, 0x413b8, + 0x413c0, 0x413c8, 0x413d0, 0x413dc, 0x413f0, 0x413f0, 0x41400, 0x4140c, @@ -5254,7 +5260,7 @@ void t4_pmtx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[]) int i; u32 data[2]; - for (i = 0; i < PM_NSTATS; i++) { + for (i = 0; i < adap->params.arch.pm_stats_cnt; i++) { t4_write_reg(adap, PM_TX_STAT_CONFIG_A, i + 1); cnt[i] = t4_read_reg(adap, PM_TX_STAT_COUNT_A); if (is_t4(adap->params.chip)) { @@ -5281,7 +5287,7 @@ void t4_pmrx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[]) int i; u32 data[2]; - for (i = 0; i < PM_NSTATS; i++) { + for (i = 0; i < adap->params.arch.pm_stats_cnt; i++) { t4_write_reg(adap, PM_RX_STAT_CONFIG_A, i + 1); cnt[i] = t4_read_reg(adap, PM_RX_STAT_COUNT_A); if (is_t4(adap->params.chip)) { @@ -5310,7 +5316,14 @@ unsigned int t4_get_mps_bg_map(struct adapter *adap, int idx) if (n == 0) return idx == 0 ? 0xf : 0; - if (n == 1) + /* In T6 (which is a 2 port card), + * port 0 is mapped to channel 0 and port 1 is mapped to channel 1. + * For 2 port T4/T5 adapter, + * port 0 is mapped to channel 0 and 1, + * port 1 is mapped to channel 2 and 3. + */ + if ((n == 1) && + (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)) return idx < 2 ? (3 << (2 * idx)) : 0; return 1 << idx; } @@ -5689,6 +5702,39 @@ void t4_sge_decode_idma_state(struct adapter *adapter, int state) "IDMA_FL_SEND_PADDING", "IDMA_FL_SEND_COMPLETION_TO_IMSG", }; + static const char * const t6_decode[] = { + "IDMA_IDLE", + "IDMA_PUSH_MORE_CPL_FIFO", + "IDMA_PUSH_CPL_MSG_HEADER_TO_FIFO", + "IDMA_SGEFLRFLUSH_SEND_PCIEHDR", + "IDMA_PHYSADDR_SEND_PCIEHDR", + "IDMA_PHYSADDR_SEND_PAYLOAD_FIRST", + "IDMA_PHYSADDR_SEND_PAYLOAD", + "IDMA_FL_REQ_DATA_FL", + "IDMA_FL_DROP", + "IDMA_FL_DROP_SEND_INC", + "IDMA_FL_H_REQ_HEADER_FL", + "IDMA_FL_H_SEND_PCIEHDR", + "IDMA_FL_H_PUSH_CPL_FIFO", + "IDMA_FL_H_SEND_CPL", + "IDMA_FL_H_SEND_IP_HDR_FIRST", + "IDMA_FL_H_SEND_IP_HDR", + "IDMA_FL_H_REQ_NEXT_HEADER_FL", + "IDMA_FL_H_SEND_NEXT_PCIEHDR", + "IDMA_FL_H_SEND_IP_HDR_PADDING", + "IDMA_FL_D_SEND_PCIEHDR", + "IDMA_FL_D_SEND_CPL_AND_IP_HDR", + "IDMA_FL_D_REQ_NEXT_DATA_FL", + "IDMA_FL_SEND_PCIEHDR", + "IDMA_FL_PUSH_CPL_FIFO", + "IDMA_FL_SEND_CPL", + "IDMA_FL_SEND_PAYLOAD_FIRST", + "IDMA_FL_SEND_PAYLOAD", + "IDMA_FL_REQ_NEXT_DATA_FL", + "IDMA_FL_SEND_NEXT_PCIEHDR", + "IDMA_FL_SEND_PADDING", + "IDMA_FL_SEND_COMPLETION_TO_IMSG", + }; static const u32 sge_regs[] = { SGE_DEBUG_DATA_LOW_INDEX_2_A, SGE_DEBUG_DATA_LOW_INDEX_3_A, @@ -5697,6 +5743,32 @@ void t4_sge_decode_idma_state(struct adapter *adapter, int state) const char **sge_idma_decode; int sge_idma_decode_nstates; int i; + unsigned int chip_version = CHELSIO_CHIP_VERSION(adapter->params.chip); + + /* Select the right set of decode strings to dump depending on the + * adapter chip type. + */ + switch (chip_version) { + case CHELSIO_T4: + sge_idma_decode = (const char **)t4_decode; + sge_idma_decode_nstates = ARRAY_SIZE(t4_decode); + break; + + case CHELSIO_T5: + sge_idma_decode = (const char **)t5_decode; + sge_idma_decode_nstates = ARRAY_SIZE(t5_decode); + break; + + case CHELSIO_T6: + sge_idma_decode = (const char **)t6_decode; + sge_idma_decode_nstates = ARRAY_SIZE(t6_decode); + break; + + default: + dev_err(adapter->pdev_dev, + "Unsupported chip version %d\n", chip_version); + return; + } if (is_t4(adapter->params.chip)) { sge_idma_decode = (const char **)t4_decode; @@ -6097,6 +6169,59 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox, } /** + * t4_fl_pkt_align - return the fl packet alignment + * @adap: the adapter + * + * T4 has a single field to specify the packing and padding boundary. + * T5 onwards has separate fields for this and hence the alignment for + * next packet offset is maximum of these two. + * + */ +int t4_fl_pkt_align(struct adapter *adap) +{ + u32 sge_control, sge_control2; + unsigned int ingpadboundary, ingpackboundary, fl_align, ingpad_shift; + + sge_control = t4_read_reg(adap, SGE_CONTROL_A); + + /* T4 uses a single control field to specify both the PCIe Padding and + * Packing Boundary. T5 introduced the ability to specify these + * separately. The actual Ingress Packet Data alignment boundary + * within Packed Buffer Mode is the maximum of these two + * specifications. (Note that it makes no real practical sense to + * have the Pading Boudary be larger than the Packing Boundary but you + * could set the chip up that way and, in fact, legacy T4 code would + * end doing this because it would initialize the Padding Boundary and + * leave the Packing Boundary initialized to 0 (16 bytes).) + * Padding Boundary values in T6 starts from 8B, + * where as it is 32B for T4 and T5. + */ + if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) + ingpad_shift = INGPADBOUNDARY_SHIFT_X; + else + ingpad_shift = T6_INGPADBOUNDARY_SHIFT_X; + + ingpadboundary = 1 << (INGPADBOUNDARY_G(sge_control) + ingpad_shift); + + fl_align = ingpadboundary; + if (!is_t4(adap->params.chip)) { + /* T5 has a weird interpretation of one of the PCIe Packing + * Boundary values. No idea why ... + */ + sge_control2 = t4_read_reg(adap, SGE_CONTROL2_A); + ingpackboundary = INGPACKBOUNDARY_G(sge_control2); + if (ingpackboundary == INGPACKBOUNDARY_16B_X) + ingpackboundary = 16; + else + ingpackboundary = 1 << (ingpackboundary + + INGPACKBOUNDARY_SHIFT_X); + + fl_align = max(ingpadboundary, ingpackboundary); + } + return fl_align; +} + +/** * t4_fixup_host_params - fix up host-dependent parameters * @adap: the adapter * @page_size: the host's Base Page Size @@ -6114,6 +6239,7 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, unsigned int stat_len = cache_line_size > 64 ? 128 : 64; unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size; unsigned int fl_align_log = fls(fl_align) - 1; + unsigned int ingpad; t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A, HOSTPAGESIZEPF0_V(sge_hps) | @@ -6161,10 +6287,16 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, fl_align = 64; fl_align_log = 6; } + + if (is_t5(adap->params.chip)) + ingpad = INGPCIEBOUNDARY_32B_X; + else + ingpad = T6_INGPADBOUNDARY_32B_X; + t4_set_reg_field(adap, SGE_CONTROL_A, INGPADBOUNDARY_V(INGPADBOUNDARY_M) | EGRSTATUSPAGESIZE_F, - INGPADBOUNDARY_V(INGPCIEBOUNDARY_32B_X) | + INGPADBOUNDARY_V(ingpad) | EGRSTATUSPAGESIZE_V(stat_len != 64)); t4_set_reg_field(adap, SGE_CONTROL2_A, INGPACKBOUNDARY_V(INGPACKBOUNDARY_M), @@ -7060,7 +7192,12 @@ int t4_prep_adapter(struct adapter *adapter) NUM_MPS_CLS_SRAM_L_INSTANCES; adapter->params.arch.mps_rplc_size = 128; adapter->params.arch.nchan = NCHAN; + adapter->params.arch.pm_stats_cnt = PM_NSTATS; adapter->params.arch.vfcount = 128; + /* Congestion map is for 4 channels so that + * MPS can have 4 priority per port. + */ + adapter->params.arch.cng_ch_bits_log = 2; break; case CHELSIO_T5: adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T5, pl_rev); @@ -7069,7 +7206,9 @@ int t4_prep_adapter(struct adapter *adapter) NUM_MPS_T5_CLS_SRAM_L_INSTANCES; adapter->params.arch.mps_rplc_size = 128; adapter->params.arch.nchan = NCHAN; + adapter->params.arch.pm_stats_cnt = PM_NSTATS; adapter->params.arch.vfcount = 128; + adapter->params.arch.cng_ch_bits_log = 2; break; case CHELSIO_T6: adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T6, pl_rev); @@ -7078,7 +7217,12 @@ int t4_prep_adapter(struct adapter *adapter) NUM_MPS_T5_CLS_SRAM_L_INSTANCES; adapter->params.arch.mps_rplc_size = 256; adapter->params.arch.nchan = 2; + adapter->params.arch.pm_stats_cnt = T6_PM_NSTATS; adapter->params.arch.vfcount = 256; + /* Congestion map will be for 2 channels so that + * MPS can have 8 priority per port. + */ + adapter->params.arch.cng_ch_bits_log = 3; break; default: dev_err(adapter->pdev_dev, "Device %d is not supported\n", diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index 13708fde1668b..2fc60e83a7a15 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -48,6 +48,7 @@ enum { NMTUS = 16, /* size of MTU table */ NCCTRL_WIN = 32, /* # of congestion control windows */ PM_NSTATS = 5, /* # of PM stats */ + T6_PM_NSTATS = 7, /* # of PM stats in T6 */ MBOX_LEN = 64, /* mailbox size in bytes */ TRACE_LEN = 112, /* length of trace data and mask */ FILTER_OPT_LEN = 36, /* filter tuple width for optional components */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index fc3044c8ac1c9..9fea255c7e87a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -492,6 +492,9 @@ #define STATSOURCE_T5_V(x) ((x) << STATSOURCE_T5_S) #define STATSOURCE_T5_G(x) (((x) >> STATSOURCE_T5_S) & STATSOURCE_T5_M) +#define T6_STATMODE_S 0 +#define T6_STATMODE_V(x) ((x) << T6_STATMODE_S) + #define SGE_DBFIFO_STATUS2_A 0x1118 #define HP_INT_THRESH_T5_S 10 @@ -2395,6 +2398,30 @@ #define MPS_CLS_TCAM_DATA0_A 0xf000 #define MPS_CLS_TCAM_DATA1_A 0xf004 +#define VIDL_S 16 +#define VIDL_M 0xffffU +#define VIDL_G(x) (((x) >> VIDL_S) & VIDL_M) + +#define DATALKPTYPE_S 10 +#define DATALKPTYPE_M 0x3U +#define DATALKPTYPE_G(x) (((x) >> DATALKPTYPE_S) & DATALKPTYPE_M) + +#define DATAPORTNUM_S 12 +#define DATAPORTNUM_M 0xfU +#define DATAPORTNUM_G(x) (((x) >> DATAPORTNUM_S) & DATAPORTNUM_M) + +#define DATADIPHIT_S 8 +#define DATADIPHIT_V(x) ((x) << DATADIPHIT_S) +#define DATADIPHIT_F DATADIPHIT_V(1U) + +#define DATAVIDH2_S 7 +#define DATAVIDH2_V(x) ((x) << DATAVIDH2_S) +#define DATAVIDH2_F DATAVIDH2_V(1U) + +#define DATAVIDH1_S 0 +#define DATAVIDH1_M 0x7fU +#define DATAVIDH1_G(x) (((x) >> DATAVIDH1_S) & DATAVIDH1_M) + #define USED_S 16 #define USED_M 0x7ffU #define USED_G(x) (((x) >> USED_S) & USED_M) @@ -2802,6 +2829,10 @@ #define HASHEN_V(x) ((x) << HASHEN_S) #define HASHEN_F HASHEN_V(1U) +#define ASLIPCOMPEN_S 17 +#define ASLIPCOMPEN_V(x) ((x) << ASLIPCOMPEN_S) +#define ASLIPCOMPEN_F ASLIPCOMPEN_V(1U) + #define REQQPARERR_S 16 #define REQQPARERR_V(x) ((x) << REQQPARERR_S) #define REQQPARERR_F REQQPARERR_V(1U) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h index 7bdee3bf75ec2..a5231fa771db9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h @@ -53,6 +53,9 @@ #define INGPADBOUNDARY_SHIFT_X 5 +#define T6_INGPADBOUNDARY_SHIFT_X 3 +#define T6_INGPADBOUNDARY_32B_X 2 + /* CONTROL2 register */ #define INGPACKBOUNDARY_SHIFT_X 5 #define INGPACKBOUNDARY_16B_X 0 diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index fa3786a9d30ea..6528231d8a59d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -2607,7 +2607,7 @@ int t4vf_sge_init(struct adapter *adapter) u32 fl0 = sge_params->sge_fl_buffer_size[0]; u32 fl1 = sge_params->sge_fl_buffer_size[1]; struct sge *s = &adapter->sge; - unsigned int ingpadboundary, ingpackboundary; + unsigned int ingpadboundary, ingpackboundary, ingpad_shift; /* * Start by vetting the basic SGE parameters which have been set up by @@ -2642,9 +2642,16 @@ int t4vf_sge_init(struct adapter *adapter) * could set the chip up that way and, in fact, legacy T4 code would * end doing this because it would initialize the Padding Boundary and * leave the Packing Boundary initialized to 0 (16 bytes).) + * Padding Boundary values in T6 starts from 8B, + * where as it is 32B for T4 and T5. */ + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) + ingpad_shift = INGPADBOUNDARY_SHIFT_X; + else + ingpad_shift = T6_INGPADBOUNDARY_SHIFT_X; + ingpadboundary = 1 << (INGPADBOUNDARY_G(sge_params->sge_control) + - INGPADBOUNDARY_SHIFT_X); + ingpad_shift); if (is_t4(adapter->params.chip)) { s->fl_align = ingpadboundary; } else { diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_defs.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_defs.h index b516b12b18845..f859db3d254cd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_defs.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_defs.h @@ -54,6 +54,7 @@ #define T4VF_MPS_BASE_ADDR 0x0100 #define T4VF_PL_BASE_ADDR 0x0200 #define T4VF_MBDATA_BASE_ADDR 0x0240 +#define T6VF_MBDATA_BASE_ADDR 0x0280 #define T4VF_CIM_BASE_ADDR 0x0300 #define T4VF_REGMAP_START 0x0000 diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 63dd5fdac5b91..b6fa74aafe477 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -120,12 +120,19 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, 1, 1, 3, 5, 10, 10, 20, 50, 100 }; - u32 v; + u32 v, mbox_data; int i, ms, delay_idx; const __be64 *p; - u32 mbox_data = T4VF_MBDATA_BASE_ADDR; u32 mbox_ctl = T4VF_CIM_BASE_ADDR + CIM_VF_EXT_MAILBOX_CTRL; + /* In T6, mailbox size is changed to 128 bytes to avoid + * invalidating the entire prefetch buffer. + */ + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) + mbox_data = T4VF_MBDATA_BASE_ADDR; + else + mbox_data = T6VF_MBDATA_BASE_ADDR; + /* * Commands must be multiples of 16 bytes in length and may not be * larger than the size of the Mailbox Data register array. diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 8966f3159bb2b..3acde3b9b767c 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -1990,7 +1990,7 @@ SetMulticastFilter(struct net_device *dev) static u_char de4x5_irq[] = EISA_ALLOWED_IRQ_LIST; -static int __init de4x5_eisa_probe (struct device *gendev) +static int de4x5_eisa_probe(struct device *gendev) { struct eisa_device *edev; u_long iobase; diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index d463563e1f703..cf837831304be 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -37,7 +37,7 @@ #include "be_hw.h" #include "be_roce.h" -#define DRV_VER "10.6.0.3" +#define DRV_VER "11.0.0.0" #define DRV_NAME "be2net" #define BE_NAME "Emulex BladeEngine2" #define BE3_NAME "Emulex BladeEngine3" @@ -521,7 +521,7 @@ struct be_adapter { struct be_drv_stats drv_stats; struct be_aic_obj aic_obj[MAX_EVT_QS]; u8 vlan_prio_bmap; /* Available Priority BitMap */ - u16 recommended_prio; /* Recommended Priority */ + u16 recommended_prio_bits;/* Recommended Priority bits in vlan tag */ struct be_dma_mem rx_filter; /* Cmd DMA mem for rx-filter */ struct be_dma_mem stats_cmd; @@ -547,10 +547,6 @@ struct be_adapter { u32 beacon_state; /* for set_phys_id */ - bool eeh_error; - bool fw_timeout; - bool hw_error; - u32 port_num; char port_name; u8 mc_type; @@ -574,6 +570,8 @@ struct be_adapter { struct be_resources pool_res; /* resources available for the port */ struct be_resources res; /* resources available for the func */ u16 num_vfs; /* Number of VFs provisioned by PF */ + u8 pf_num; /* Numbering used by FW, starts at 0 */ + u8 vf_num; /* Numbering used by FW, starts at 1 */ u8 virtfn; struct be_vf_cfg *vf_cfg; bool be3_native; @@ -591,11 +589,10 @@ struct be_adapter { u32 msg_enable; int be_get_temp_freq; struct be_hwmon hwmon_info; - u8 pf_number; - u8 pci_func_num; struct rss_info rss_info; /* Filters for packets that need to be sent to BMC */ u32 bmc_filt_mask; + u32 fat_dump_len; u16 serial_num[CNTL_SERIAL_NUM_WORDS]; }; @@ -848,8 +845,6 @@ void be_roce_dev_remove(struct be_adapter *); /* * internal function to open-close roce device during ifup-ifdown. */ -void be_roce_dev_open(struct be_adapter *); -void be_roce_dev_close(struct be_adapter *); void be_roce_dev_shutdown(struct be_adapter *); #endif /* BE_H */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 1795c935ff023..b63d8ad2e1157 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -308,8 +308,7 @@ static void be_async_grp5_cos_priority_process(struct be_adapter *adapter, if (evt->valid) { adapter->vlan_prio_bmap = evt->available_priority_bmap; - adapter->recommended_prio &= ~VLAN_PRIO_MASK; - adapter->recommended_prio = + adapter->recommended_prio_bits = evt->reco_default_priority << VLAN_PRIO_SHIFT; } } @@ -1713,49 +1712,40 @@ err: } /* Uses synchronous mcc */ -int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size) +int be_cmd_get_fat_dump_len(struct be_adapter *adapter, u32 *dump_size) { - struct be_mcc_wrb *wrb; + struct be_mcc_wrb wrb = {0}; struct be_cmd_req_get_fat *req; int status; - spin_lock_bh(&adapter->mcc_lock); - - wrb = wrb_from_mccq(adapter); - if (!wrb) { - status = -EBUSY; - goto err; - } - req = embedded_payload(wrb); + req = embedded_payload(&wrb); be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, - OPCODE_COMMON_MANAGE_FAT, sizeof(*req), wrb, - NULL); + OPCODE_COMMON_MANAGE_FAT, sizeof(*req), + &wrb, NULL); req->fat_operation = cpu_to_le32(QUERY_FAT); - status = be_mcc_notify_wait(adapter); + status = be_cmd_notify_wait(adapter, &wrb); if (!status) { - struct be_cmd_resp_get_fat *resp = embedded_payload(wrb); + struct be_cmd_resp_get_fat *resp = embedded_payload(&wrb); - if (log_size && resp->log_size) - *log_size = le32_to_cpu(resp->log_size) - + if (dump_size && resp->log_size) + *dump_size = le32_to_cpu(resp->log_size) - sizeof(u32); } -err: - spin_unlock_bh(&adapter->mcc_lock); return status; } -int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf) +int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf) { struct be_dma_mem get_fat_cmd; struct be_mcc_wrb *wrb; struct be_cmd_req_get_fat *req; u32 offset = 0, total_size, buf_size, log_offset = sizeof(u32), payload_len; - int status = 0; + int status; if (buf_len == 0) - return -EIO; + return 0; total_size = buf_len; @@ -1763,11 +1753,8 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf) get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, get_fat_cmd.size, &get_fat_cmd.dma, GFP_ATOMIC); - if (!get_fat_cmd.va) { - dev_err(&adapter->pdev->dev, - "Memory allocation failure while reading FAT data\n"); + if (!get_fat_cmd.va) return -ENOMEM; - } spin_lock_bh(&adapter->mcc_lock); @@ -2291,10 +2278,11 @@ err: return status; } -int lancer_cmd_write_object(struct be_adapter *adapter, struct be_dma_mem *cmd, - u32 data_size, u32 data_offset, - const char *obj_name, u32 *data_written, - u8 *change_status, u8 *addn_status) +static int lancer_cmd_write_object(struct be_adapter *adapter, + struct be_dma_mem *cmd, u32 data_size, + u32 data_offset, const char *obj_name, + u32 *data_written, u8 *change_status, + u8 *addn_status) { struct be_mcc_wrb *wrb; struct lancer_cmd_req_write_object *req; @@ -2410,7 +2398,8 @@ int be_cmd_query_sfp_info(struct be_adapter *adapter) return status; } -int lancer_cmd_delete_object(struct be_adapter *adapter, const char *obj_name) +static int lancer_cmd_delete_object(struct be_adapter *adapter, + const char *obj_name) { struct lancer_cmd_req_delete_object *req; struct be_mcc_wrb *wrb; @@ -2485,9 +2474,9 @@ err_unlock: return status; } -int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd, - u32 flash_type, u32 flash_opcode, u32 img_offset, - u32 buf_size) +static int be_cmd_write_flashrom(struct be_adapter *adapter, + struct be_dma_mem *cmd, u32 flash_type, + u32 flash_opcode, u32 img_offset, u32 buf_size) { struct be_mcc_wrb *wrb; struct be_cmd_write_flashrom *req; @@ -2533,8 +2522,8 @@ err_unlock: return status; } -int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc, - u16 img_optype, u32 img_offset, u32 crc_offset) +static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc, + u16 img_optype, u32 img_offset, u32 crc_offset) { struct be_cmd_read_flash_crc *req; struct be_mcc_wrb *wrb; @@ -2571,6 +2560,579 @@ err: return status; } +static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "}; + +static bool phy_flashing_required(struct be_adapter *adapter) +{ + return (adapter->phy.phy_type == PHY_TYPE_TN_8022 && + adapter->phy.interface_type == PHY_TYPE_BASET_10GB); +} + +static bool is_comp_in_ufi(struct be_adapter *adapter, + struct flash_section_info *fsec, int type) +{ + int i = 0, img_type = 0; + struct flash_section_info_g2 *fsec_g2 = NULL; + + if (BE2_chip(adapter)) + fsec_g2 = (struct flash_section_info_g2 *)fsec; + + for (i = 0; i < MAX_FLASH_COMP; i++) { + if (fsec_g2) + img_type = le32_to_cpu(fsec_g2->fsec_entry[i].type); + else + img_type = le32_to_cpu(fsec->fsec_entry[i].type); + + if (img_type == type) + return true; + } + return false; +} + +static struct flash_section_info *get_fsec_info(struct be_adapter *adapter, + int header_size, + const struct firmware *fw) +{ + struct flash_section_info *fsec = NULL; + const u8 *p = fw->data; + + p += header_size; + while (p < (fw->data + fw->size)) { + fsec = (struct flash_section_info *)p; + if (!memcmp(flash_cookie, fsec->cookie, sizeof(flash_cookie))) + return fsec; + p += 32; + } + return NULL; +} + +static int be_check_flash_crc(struct be_adapter *adapter, const u8 *p, + u32 img_offset, u32 img_size, int hdr_size, + u16 img_optype, bool *crc_match) +{ + u32 crc_offset; + int status; + u8 crc[4]; + + status = be_cmd_get_flash_crc(adapter, crc, img_optype, img_offset, + img_size - 4); + if (status) + return status; + + crc_offset = hdr_size + img_offset + img_size - 4; + + /* Skip flashing, if crc of flashed region matches */ + if (!memcmp(crc, p + crc_offset, 4)) + *crc_match = true; + else + *crc_match = false; + + return status; +} + +static int be_flash(struct be_adapter *adapter, const u8 *img, + struct be_dma_mem *flash_cmd, int optype, int img_size, + u32 img_offset) +{ + u32 flash_op, num_bytes, total_bytes = img_size, bytes_sent = 0; + struct be_cmd_write_flashrom *req = flash_cmd->va; + int status; + + while (total_bytes) { + num_bytes = min_t(u32, 32 * 1024, total_bytes); + + total_bytes -= num_bytes; + + if (!total_bytes) { + if (optype == OPTYPE_PHY_FW) + flash_op = FLASHROM_OPER_PHY_FLASH; + else + flash_op = FLASHROM_OPER_FLASH; + } else { + if (optype == OPTYPE_PHY_FW) + flash_op = FLASHROM_OPER_PHY_SAVE; + else + flash_op = FLASHROM_OPER_SAVE; + } + + memcpy(req->data_buf, img, num_bytes); + img += num_bytes; + status = be_cmd_write_flashrom(adapter, flash_cmd, optype, + flash_op, img_offset + + bytes_sent, num_bytes); + if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST && + optype == OPTYPE_PHY_FW) + break; + else if (status) + return status; + + bytes_sent += num_bytes; + } + return 0; +} + +/* For BE2, BE3 and BE3-R */ +static int be_flash_BEx(struct be_adapter *adapter, + const struct firmware *fw, + struct be_dma_mem *flash_cmd, int num_of_images) +{ + int img_hdrs_size = (num_of_images * sizeof(struct image_hdr)); + struct device *dev = &adapter->pdev->dev; + struct flash_section_info *fsec = NULL; + int status, i, filehdr_size, num_comp; + const struct flash_comp *pflashcomp; + bool crc_match; + const u8 *p; + + struct flash_comp gen3_flash_types[] = { + { BE3_ISCSI_PRIMARY_IMAGE_START, OPTYPE_ISCSI_ACTIVE, + BE3_COMP_MAX_SIZE, IMAGE_FIRMWARE_ISCSI}, + { BE3_REDBOOT_START, OPTYPE_REDBOOT, + BE3_REDBOOT_COMP_MAX_SIZE, IMAGE_BOOT_CODE}, + { BE3_ISCSI_BIOS_START, OPTYPE_BIOS, + BE3_BIOS_COMP_MAX_SIZE, IMAGE_OPTION_ROM_ISCSI}, + { BE3_PXE_BIOS_START, OPTYPE_PXE_BIOS, + BE3_BIOS_COMP_MAX_SIZE, IMAGE_OPTION_ROM_PXE}, + { BE3_FCOE_BIOS_START, OPTYPE_FCOE_BIOS, + BE3_BIOS_COMP_MAX_SIZE, IMAGE_OPTION_ROM_FCOE}, + { BE3_ISCSI_BACKUP_IMAGE_START, OPTYPE_ISCSI_BACKUP, + BE3_COMP_MAX_SIZE, IMAGE_FIRMWARE_BACKUP_ISCSI}, + { BE3_FCOE_PRIMARY_IMAGE_START, OPTYPE_FCOE_FW_ACTIVE, + BE3_COMP_MAX_SIZE, IMAGE_FIRMWARE_FCOE}, + { BE3_FCOE_BACKUP_IMAGE_START, OPTYPE_FCOE_FW_BACKUP, + BE3_COMP_MAX_SIZE, IMAGE_FIRMWARE_BACKUP_FCOE}, + { BE3_NCSI_START, OPTYPE_NCSI_FW, + BE3_NCSI_COMP_MAX_SIZE, IMAGE_NCSI}, + { BE3_PHY_FW_START, OPTYPE_PHY_FW, + BE3_PHY_FW_COMP_MAX_SIZE, IMAGE_FIRMWARE_PHY} + }; + + struct flash_comp gen2_flash_types[] = { + { BE2_ISCSI_PRIMARY_IMAGE_START, OPTYPE_ISCSI_ACTIVE, + BE2_COMP_MAX_SIZE, IMAGE_FIRMWARE_ISCSI}, + { BE2_REDBOOT_START, OPTYPE_REDBOOT, + BE2_REDBOOT_COMP_MAX_SIZE, IMAGE_BOOT_CODE}, + { BE2_ISCSI_BIOS_START, OPTYPE_BIOS, + BE2_BIOS_COMP_MAX_SIZE, IMAGE_OPTION_ROM_ISCSI}, + { BE2_PXE_BIOS_START, OPTYPE_PXE_BIOS, + BE2_BIOS_COMP_MAX_SIZE, IMAGE_OPTION_ROM_PXE}, + { BE2_FCOE_BIOS_START, OPTYPE_FCOE_BIOS, + BE2_BIOS_COMP_MAX_SIZE, IMAGE_OPTION_ROM_FCOE}, + { BE2_ISCSI_BACKUP_IMAGE_START, OPTYPE_ISCSI_BACKUP, + BE2_COMP_MAX_SIZE, IMAGE_FIRMWARE_BACKUP_ISCSI}, + { BE2_FCOE_PRIMARY_IMAGE_START, OPTYPE_FCOE_FW_ACTIVE, + BE2_COMP_MAX_SIZE, IMAGE_FIRMWARE_FCOE}, + { BE2_FCOE_BACKUP_IMAGE_START, OPTYPE_FCOE_FW_BACKUP, + BE2_COMP_MAX_SIZE, IMAGE_FIRMWARE_BACKUP_FCOE} + }; + + if (BE3_chip(adapter)) { + pflashcomp = gen3_flash_types; + filehdr_size = sizeof(struct flash_file_hdr_g3); + num_comp = ARRAY_SIZE(gen3_flash_types); + } else { + pflashcomp = gen2_flash_types; + filehdr_size = sizeof(struct flash_file_hdr_g2); + num_comp = ARRAY_SIZE(gen2_flash_types); + img_hdrs_size = 0; + } + + /* Get flash section info*/ + fsec = get_fsec_info(adapter, filehdr_size + img_hdrs_size, fw); + if (!fsec) { + dev_err(dev, "Invalid Cookie. FW image may be corrupted\n"); + return -1; + } + for (i = 0; i < num_comp; i++) { + if (!is_comp_in_ufi(adapter, fsec, pflashcomp[i].img_type)) + continue; + + if ((pflashcomp[i].optype == OPTYPE_NCSI_FW) && + memcmp(adapter->fw_ver, "3.102.148.0", 11) < 0) + continue; + + if (pflashcomp[i].optype == OPTYPE_PHY_FW && + !phy_flashing_required(adapter)) + continue; + + if (pflashcomp[i].optype == OPTYPE_REDBOOT) { + status = be_check_flash_crc(adapter, fw->data, + pflashcomp[i].offset, + pflashcomp[i].size, + filehdr_size + + img_hdrs_size, + OPTYPE_REDBOOT, &crc_match); + if (status) { + dev_err(dev, + "Could not get CRC for 0x%x region\n", + pflashcomp[i].optype); + continue; + } + + if (crc_match) + continue; + } + + p = fw->data + filehdr_size + pflashcomp[i].offset + + img_hdrs_size; + if (p + pflashcomp[i].size > fw->data + fw->size) + return -1; + + status = be_flash(adapter, p, flash_cmd, pflashcomp[i].optype, + pflashcomp[i].size, 0); + if (status) { + dev_err(dev, "Flashing section type 0x%x failed\n", + pflashcomp[i].img_type); + return status; + } + } + return 0; +} + +static u16 be_get_img_optype(struct flash_section_entry fsec_entry) +{ + u32 img_type = le32_to_cpu(fsec_entry.type); + u16 img_optype = le16_to_cpu(fsec_entry.optype); + + if (img_optype != 0xFFFF) + return img_optype; + + switch (img_type) { + case IMAGE_FIRMWARE_ISCSI: + img_optype = OPTYPE_ISCSI_ACTIVE; + break; + case IMAGE_BOOT_CODE: + img_optype = OPTYPE_REDBOOT; + break; + case IMAGE_OPTION_ROM_ISCSI: + img_optype = OPTYPE_BIOS; + break; + case IMAGE_OPTION_ROM_PXE: + img_optype = OPTYPE_PXE_BIOS; + break; + case IMAGE_OPTION_ROM_FCOE: + img_optype = OPTYPE_FCOE_BIOS; + break; + case IMAGE_FIRMWARE_BACKUP_ISCSI: + img_optype = OPTYPE_ISCSI_BACKUP; + break; + case IMAGE_NCSI: + img_optype = OPTYPE_NCSI_FW; + break; + case IMAGE_FLASHISM_JUMPVECTOR: + img_optype = OPTYPE_FLASHISM_JUMPVECTOR; + break; + case IMAGE_FIRMWARE_PHY: + img_optype = OPTYPE_SH_PHY_FW; + break; + case IMAGE_REDBOOT_DIR: + img_optype = OPTYPE_REDBOOT_DIR; + break; + case IMAGE_REDBOOT_CONFIG: + img_optype = OPTYPE_REDBOOT_CONFIG; + break; + case IMAGE_UFI_DIR: + img_optype = OPTYPE_UFI_DIR; + break; + default: + break; + } + + return img_optype; +} + +static int be_flash_skyhawk(struct be_adapter *adapter, + const struct firmware *fw, + struct be_dma_mem *flash_cmd, int num_of_images) +{ + int img_hdrs_size = num_of_images * sizeof(struct image_hdr); + bool crc_match, old_fw_img, flash_offset_support = true; + struct device *dev = &adapter->pdev->dev; + struct flash_section_info *fsec = NULL; + u32 img_offset, img_size, img_type; + u16 img_optype, flash_optype; + int status, i, filehdr_size; + const u8 *p; + + filehdr_size = sizeof(struct flash_file_hdr_g3); + fsec = get_fsec_info(adapter, filehdr_size + img_hdrs_size, fw); + if (!fsec) { + dev_err(dev, "Invalid Cookie. FW image may be corrupted\n"); + return -EINVAL; + } + +retry_flash: + for (i = 0; i < le32_to_cpu(fsec->fsec_hdr.num_images); i++) { + img_offset = le32_to_cpu(fsec->fsec_entry[i].offset); + img_size = le32_to_cpu(fsec->fsec_entry[i].pad_size); + img_type = le32_to_cpu(fsec->fsec_entry[i].type); + img_optype = be_get_img_optype(fsec->fsec_entry[i]); + old_fw_img = fsec->fsec_entry[i].optype == 0xFFFF; + + if (img_optype == 0xFFFF) + continue; + + if (flash_offset_support) + flash_optype = OPTYPE_OFFSET_SPECIFIED; + else + flash_optype = img_optype; + + /* Don't bother verifying CRC if an old FW image is being + * flashed + */ + if (old_fw_img) + goto flash; + + status = be_check_flash_crc(adapter, fw->data, img_offset, + img_size, filehdr_size + + img_hdrs_size, flash_optype, + &crc_match); + if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST || + base_status(status) == MCC_STATUS_ILLEGAL_FIELD) { + /* The current FW image on the card does not support + * OFFSET based flashing. Retry using older mechanism + * of OPTYPE based flashing + */ + if (flash_optype == OPTYPE_OFFSET_SPECIFIED) { + flash_offset_support = false; + goto retry_flash; + } + + /* The current FW image on the card does not recognize + * the new FLASH op_type. The FW download is partially + * complete. Reboot the server now to enable FW image + * to recognize the new FLASH op_type. To complete the + * remaining process, download the same FW again after + * the reboot. + */ + dev_err(dev, "Flash incomplete. Reset the server\n"); + dev_err(dev, "Download FW image again after reset\n"); + return -EAGAIN; + } else if (status) { + dev_err(dev, "Could not get CRC for 0x%x region\n", + img_optype); + return -EFAULT; + } + + if (crc_match) + continue; + +flash: + p = fw->data + filehdr_size + img_offset + img_hdrs_size; + if (p + img_size > fw->data + fw->size) + return -1; + + status = be_flash(adapter, p, flash_cmd, flash_optype, img_size, + img_offset); + + /* The current FW image on the card does not support OFFSET + * based flashing. Retry using older mechanism of OPTYPE based + * flashing + */ + if (base_status(status) == MCC_STATUS_ILLEGAL_FIELD && + flash_optype == OPTYPE_OFFSET_SPECIFIED) { + flash_offset_support = false; + goto retry_flash; + } + + /* For old FW images ignore ILLEGAL_FIELD error or errors on + * UFI_DIR region + */ + if (old_fw_img && + (base_status(status) == MCC_STATUS_ILLEGAL_FIELD || + (img_optype == OPTYPE_UFI_DIR && + base_status(status) == MCC_STATUS_FAILED))) { + continue; + } else if (status) { + dev_err(dev, "Flashing section type 0x%x failed\n", + img_type); + + switch (addl_status(status)) { + case MCC_ADDL_STATUS_MISSING_SIGNATURE: + dev_err(dev, + "Digital signature missing in FW\n"); + return -EINVAL; + case MCC_ADDL_STATUS_INVALID_SIGNATURE: + dev_err(dev, + "Invalid digital signature in FW\n"); + return -EINVAL; + default: + return -EFAULT; + } + } + } + return 0; +} + +int lancer_fw_download(struct be_adapter *adapter, + const struct firmware *fw) +{ + struct device *dev = &adapter->pdev->dev; + struct be_dma_mem flash_cmd; + const u8 *data_ptr = NULL; + u8 *dest_image_ptr = NULL; + size_t image_size = 0; + u32 chunk_size = 0; + u32 data_written = 0; + u32 offset = 0; + int status = 0; + u8 add_status = 0; + u8 change_status; + + if (!IS_ALIGNED(fw->size, sizeof(u32))) { + dev_err(dev, "FW image size should be multiple of 4\n"); + return -EINVAL; + } + + flash_cmd.size = sizeof(struct lancer_cmd_req_write_object) + + LANCER_FW_DOWNLOAD_CHUNK; + flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, + &flash_cmd.dma, GFP_KERNEL); + if (!flash_cmd.va) + return -ENOMEM; + + dest_image_ptr = flash_cmd.va + + sizeof(struct lancer_cmd_req_write_object); + image_size = fw->size; + data_ptr = fw->data; + + while (image_size) { + chunk_size = min_t(u32, image_size, LANCER_FW_DOWNLOAD_CHUNK); + + /* Copy the image chunk content. */ + memcpy(dest_image_ptr, data_ptr, chunk_size); + + status = lancer_cmd_write_object(adapter, &flash_cmd, + chunk_size, offset, + LANCER_FW_DOWNLOAD_LOCATION, + &data_written, &change_status, + &add_status); + if (status) + break; + + offset += data_written; + data_ptr += data_written; + image_size -= data_written; + } + + if (!status) { + /* Commit the FW written */ + status = lancer_cmd_write_object(adapter, &flash_cmd, + 0, offset, + LANCER_FW_DOWNLOAD_LOCATION, + &data_written, &change_status, + &add_status); + } + + dma_free_coherent(dev, flash_cmd.size, flash_cmd.va, flash_cmd.dma); + if (status) { + dev_err(dev, "Firmware load error\n"); + return be_cmd_status(status); + } + + dev_info(dev, "Firmware flashed successfully\n"); + + if (change_status == LANCER_FW_RESET_NEEDED) { + dev_info(dev, "Resetting adapter to activate new FW\n"); + status = lancer_physdev_ctrl(adapter, + PHYSDEV_CONTROL_FW_RESET_MASK); + if (status) { + dev_err(dev, "Adapter busy, could not reset FW\n"); + dev_err(dev, "Reboot server to activate new FW\n"); + } + } else if (change_status != LANCER_NO_RESET_NEEDED) { + dev_info(dev, "Reboot server to activate new FW\n"); + } + + return 0; +} + +/* Check if the flash image file is compatible with the adapter that + * is being flashed. + */ +static bool be_check_ufi_compatibility(struct be_adapter *adapter, + struct flash_file_hdr_g3 *fhdr) +{ + if (!fhdr) { + dev_err(&adapter->pdev->dev, "Invalid FW UFI file"); + return false; + } + + /* First letter of the build version is used to identify + * which chip this image file is meant for. + */ + switch (fhdr->build[0]) { + case BLD_STR_UFI_TYPE_SH: + if (!skyhawk_chip(adapter)) + return false; + break; + case BLD_STR_UFI_TYPE_BE3: + if (!BE3_chip(adapter)) + return false; + break; + case BLD_STR_UFI_TYPE_BE2: + if (!BE2_chip(adapter)) + return false; + break; + default: + return false; + } + + /* In BE3 FW images the "asic_type_rev" field doesn't track the + * asic_rev of the chips it is compatible with. + * When asic_type_rev is 0 the image is compatible only with + * pre-BE3-R chips (asic_rev < 0x10) + */ + if (BEx_chip(adapter) && fhdr->asic_type_rev == 0) + return adapter->asic_rev < 0x10; + else + return (fhdr->asic_type_rev >= adapter->asic_rev); +} + +int be_fw_download(struct be_adapter *adapter, const struct firmware *fw) +{ + struct device *dev = &adapter->pdev->dev; + struct flash_file_hdr_g3 *fhdr3; + struct image_hdr *img_hdr_ptr; + int status = 0, i, num_imgs; + struct be_dma_mem flash_cmd; + + fhdr3 = (struct flash_file_hdr_g3 *)fw->data; + if (!be_check_ufi_compatibility(adapter, fhdr3)) { + dev_err(dev, "Flash image is not compatible with adapter\n"); + return -EINVAL; + } + + flash_cmd.size = sizeof(struct be_cmd_write_flashrom); + flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, &flash_cmd.dma, + GFP_KERNEL); + if (!flash_cmd.va) + return -ENOMEM; + + num_imgs = le32_to_cpu(fhdr3->num_imgs); + for (i = 0; i < num_imgs; i++) { + img_hdr_ptr = (struct image_hdr *)(fw->data + + (sizeof(struct flash_file_hdr_g3) + + i * sizeof(struct image_hdr))); + if (!BE2_chip(adapter) && + le32_to_cpu(img_hdr_ptr->imageid) != 1) + continue; + + if (skyhawk_chip(adapter)) + status = be_flash_skyhawk(adapter, fw, &flash_cmd, + num_imgs); + else + status = be_flash_BEx(adapter, fw, &flash_cmd, + num_imgs); + } + + dma_free_coherent(dev, flash_cmd.size, flash_cmd.va, flash_cmd.dma); + if (!status) + dev_info(dev, "Firmware flashed successfully\n"); + + return status; +} + int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac, struct be_dma_mem *nonemb_cmd) { @@ -2892,7 +3454,6 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter) if (!status) { attribs = attribs_cmd.va + sizeof(struct be_cmd_resp_hdr); adapter->hba_port_num = attribs->hba_attribs.phy_port; - adapter->pci_func_num = attribs->pci_func_num; serial_num = attribs->hba_attribs.controller_serial_number; for (i = 0; i < CNTL_SERIAL_NUM_WORDS; i++) adapter->serial_num[i] = le32_to_cpu(serial_num[i]) & @@ -3575,14 +4136,16 @@ int be_cmd_query_port_name(struct be_adapter *adapter) return status; } -/* Descriptor type */ -enum { - FUNC_DESC = 1, - VFT_DESC = 2 -}; - +/* When more than 1 NIC descriptor is present in the descriptor list, + * the caller must specify the pf_num to obtain the NIC descriptor + * corresponding to its pci function. + * get_vft must be true when the caller wants the VF-template desc of the + * PF-pool. + * The pf_num should be set to PF_NUM_IGNORE when the caller knows + * that only it's NIC descriptor is present in the descriptor list. + */ static struct be_nic_res_desc *be_get_nic_desc(u8 *buf, u32 desc_count, - int desc_type) + bool get_vft, u8 pf_num) { struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf; struct be_nic_res_desc *nic; @@ -3592,40 +4155,42 @@ static struct be_nic_res_desc *be_get_nic_desc(u8 *buf, u32 desc_count, if (hdr->desc_type == NIC_RESOURCE_DESC_TYPE_V0 || hdr->desc_type == NIC_RESOURCE_DESC_TYPE_V1) { nic = (struct be_nic_res_desc *)hdr; - if (desc_type == FUNC_DESC || - (desc_type == VFT_DESC && - nic->flags & (1 << VFT_SHIFT))) + + if ((pf_num == PF_NUM_IGNORE || + nic->pf_num == pf_num) && + (!get_vft || nic->flags & BIT(VFT_SHIFT))) return nic; } - hdr->desc_len = hdr->desc_len ? : RESOURCE_DESC_SIZE_V0; hdr = (void *)hdr + hdr->desc_len; } return NULL; } -static struct be_nic_res_desc *be_get_vft_desc(u8 *buf, u32 desc_count) +static struct be_nic_res_desc *be_get_vft_desc(u8 *buf, u32 desc_count, + u8 pf_num) { - return be_get_nic_desc(buf, desc_count, VFT_DESC); + return be_get_nic_desc(buf, desc_count, true, pf_num); } -static struct be_nic_res_desc *be_get_func_nic_desc(u8 *buf, u32 desc_count) +static struct be_nic_res_desc *be_get_func_nic_desc(u8 *buf, u32 desc_count, + u8 pf_num) { - return be_get_nic_desc(buf, desc_count, FUNC_DESC); + return be_get_nic_desc(buf, desc_count, false, pf_num); } -static struct be_pcie_res_desc *be_get_pcie_desc(u8 devfn, u8 *buf, - u32 desc_count) +static struct be_pcie_res_desc *be_get_pcie_desc(u8 *buf, u32 desc_count, + u8 pf_num) { struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf; struct be_pcie_res_desc *pcie; int i; for (i = 0; i < desc_count; i++) { - if ((hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V0 || - hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V1)) { - pcie = (struct be_pcie_res_desc *)hdr; - if (pcie->pf_num == devfn) + if (hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V0 || + hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V1) { + pcie = (struct be_pcie_res_desc *)hdr; + if (pcie->pf_num == pf_num) return pcie; } @@ -3710,13 +4275,23 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res) u32 desc_count = le32_to_cpu(resp->desc_count); struct be_nic_res_desc *desc; - desc = be_get_func_nic_desc(resp->func_param, desc_count); + /* GET_FUNC_CONFIG returns resource descriptors of the + * current function only. So, pf_num should be set to + * PF_NUM_IGNORE. + */ + desc = be_get_func_nic_desc(resp->func_param, desc_count, + PF_NUM_IGNORE); if (!desc) { status = -EINVAL; goto err; } - adapter->pf_number = desc->pf_num; - be_copy_nic_desc(res, desc); + + /* Store pf_num & vf_num for later use in GET_PROFILE_CONFIG */ + adapter->pf_num = desc->pf_num; + adapter->vf_num = desc->vf_num; + + if (res) + be_copy_nic_desc(res, desc); } err: mutex_unlock(&adapter->mbox_lock); @@ -3726,10 +4301,7 @@ err: return status; } -/* Will use MBOX only if MCCQ has not been created - * non-zero domain => a PF is querying this on behalf of a VF - * zero domain => a PF or a VF is querying this for itself - */ +/* Will use MBOX only if MCCQ has not been created */ int be_cmd_get_profile_config(struct be_adapter *adapter, struct be_resources *res, u8 query, u8 domain) { @@ -3759,12 +4331,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, if (!lancer_chip(adapter)) req->hdr.version = 1; req->type = ACTIVE_PROFILE_TYPE; - /* When a function is querying profile information relating to - * itself hdr.pf_number must be set to it's pci_func_num + 1 - */ req->hdr.domain = domain; - if (domain == 0) - req->hdr.pf_num = adapter->pci_func_num + 1; /* When QUERY_MODIFIABLE_FIELDS_TYPE bit is set, cmd returns the * descriptors with all bits set to "1" for the fields which can be @@ -3780,8 +4347,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, resp = cmd.va; desc_count = le16_to_cpu(resp->desc_count); - pcie = be_get_pcie_desc(adapter->pdev->devfn, resp->func_param, - desc_count); + pcie = be_get_pcie_desc(resp->func_param, desc_count, + adapter->pf_num); if (pcie) res->max_vfs = le16_to_cpu(pcie->num_vfs); @@ -3789,11 +4356,13 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, if (port) adapter->mc_type = port->mc_type; - nic = be_get_func_nic_desc(resp->func_param, desc_count); + nic = be_get_func_nic_desc(resp->func_param, desc_count, + adapter->pf_num); if (nic) be_copy_nic_desc(res, nic); - vf_res = be_get_vft_desc(resp->func_param, desc_count); + vf_res = be_get_vft_desc(resp->func_param, desc_count, + adapter->pf_num); if (vf_res) res->vf_if_cap_flags = vf_res->cap_flags; err: @@ -3883,7 +4452,7 @@ int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate, u16 link_speed, return be_cmd_set_qos(adapter, max_rate / 10, domain); be_reset_nic_desc(&nic_desc); - nic_desc.pf_num = adapter->pf_number; + nic_desc.pf_num = adapter->pf_num; nic_desc.vf_num = domain; nic_desc.bw_min = 0; if (lancer_chip(adapter)) { @@ -4260,16 +4829,13 @@ err: return status; } -int be_cmd_set_logical_link_config(struct be_adapter *adapter, - int link_state, u8 domain) +int __be_cmd_set_logical_link_config(struct be_adapter *adapter, + int link_state, int version, u8 domain) { struct be_mcc_wrb *wrb; struct be_cmd_req_set_ll_link *req; int status; - if (BEx_chip(adapter) || lancer_chip(adapter)) - return -EOPNOTSUPP; - spin_lock_bh(&adapter->mcc_lock); wrb = wrb_from_mccq(adapter); @@ -4284,14 +4850,15 @@ int be_cmd_set_logical_link_config(struct be_adapter *adapter, OPCODE_COMMON_SET_LOGICAL_LINK_CONFIG, sizeof(*req), wrb, NULL); - req->hdr.version = 1; + req->hdr.version = version; req->hdr.domain = domain; - if (link_state == IFLA_VF_LINK_STATE_ENABLE) - req->link_config |= 1; + if (link_state == IFLA_VF_LINK_STATE_ENABLE || + link_state == IFLA_VF_LINK_STATE_AUTO) + req->link_config |= PLINK_ENABLE; if (link_state == IFLA_VF_LINK_STATE_AUTO) - req->link_config |= 1 << PLINK_TRACK_SHIFT; + req->link_config |= PLINK_TRACK; status = be_mcc_notify_wait(adapter); err: @@ -4299,6 +4866,25 @@ err: return status; } +int be_cmd_set_logical_link_config(struct be_adapter *adapter, + int link_state, u8 domain) +{ + int status; + + if (BEx_chip(adapter)) + return -EOPNOTSUPP; + + status = __be_cmd_set_logical_link_config(adapter, link_state, + 2, domain); + + /* Version 2 of the command will not be recognized by older FW. + * On such a failure issue version 1 of the command. + */ + if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST) + status = __be_cmd_set_logical_link_config(adapter, link_state, + 1, domain); + return status; +} int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload, int wrb_payload_size, u16 *cmd_status, u16 *ext_status) { diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 91155ea74f342..241819b36ca72 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -66,7 +66,9 @@ enum mcc_addl_status { MCC_ADDL_STATUS_INSUFFICIENT_RESOURCES = 0x16, MCC_ADDL_STATUS_FLASH_IMAGE_CRC_MISMATCH = 0x4d, MCC_ADDL_STATUS_TOO_MANY_INTERFACES = 0x4a, - MCC_ADDL_STATUS_INSUFFICIENT_VLANS = 0xab + MCC_ADDL_STATUS_INSUFFICIENT_VLANS = 0xab, + MCC_ADDL_STATUS_INVALID_SIGNATURE = 0x56, + MCC_ADDL_STATUS_MISSING_SIGNATURE = 0x57 }; #define CQE_BASE_STATUS_MASK 0xFFFF @@ -289,9 +291,7 @@ struct be_cmd_req_hdr { u32 timeout; /* dword 1 */ u32 request_length; /* dword 2 */ u8 version; /* dword 3 */ - u8 rsvd1; /* dword 3 */ - u8 pf_num; /* dword 3 */ - u8 rsvd2; /* dword 3 */ + u8 rsvd[3]; /* dword 3 */ }; #define RESP_HDR_INFO_OPCODE_SHIFT 0 /* bits 0 - 7 */ @@ -1207,68 +1207,85 @@ struct be_cmd_resp_get_beacon_state { /* Flashrom related descriptors */ #define MAX_FLASH_COMP 32 -#define OPTYPE_ISCSI_ACTIVE 0 -#define OPTYPE_REDBOOT 1 -#define OPTYPE_BIOS 2 -#define OPTYPE_PXE_BIOS 3 -#define OPTYPE_OFFSET_SPECIFIED 7 -#define OPTYPE_FCOE_BIOS 8 -#define OPTYPE_ISCSI_BACKUP 9 -#define OPTYPE_FCOE_FW_ACTIVE 10 -#define OPTYPE_FCOE_FW_BACKUP 11 -#define OPTYPE_NCSI_FW 13 -#define OPTYPE_REDBOOT_DIR 18 -#define OPTYPE_REDBOOT_CONFIG 19 -#define OPTYPE_SH_PHY_FW 21 -#define OPTYPE_FLASHISM_JUMPVECTOR 22 -#define OPTYPE_UFI_DIR 23 -#define OPTYPE_PHY_FW 99 - -#define FLASH_BIOS_IMAGE_MAX_SIZE_g2 262144 /* Max OPTION ROM image sz */ -#define FLASH_REDBOOT_IMAGE_MAX_SIZE_g2 262144 /* Max Redboot image sz */ -#define FLASH_IMAGE_MAX_SIZE_g2 1310720 /* Max firmware image size */ - -#define FLASH_NCSI_IMAGE_MAX_SIZE_g3 262144 -#define FLASH_PHY_FW_IMAGE_MAX_SIZE_g3 262144 -#define FLASH_BIOS_IMAGE_MAX_SIZE_g3 524288 /* Max OPTION ROM image sz */ -#define FLASH_REDBOOT_IMAGE_MAX_SIZE_g3 1048576 /* Max Redboot image sz */ -#define FLASH_IMAGE_MAX_SIZE_g3 2097152 /* Max firmware image size */ - -/* Offsets for components on Flash. */ -#define FLASH_REDBOOT_START_g2 0 -#define FLASH_FCoE_BIOS_START_g2 524288 -#define FLASH_iSCSI_PRIMARY_IMAGE_START_g2 1048576 -#define FLASH_iSCSI_BACKUP_IMAGE_START_g2 2359296 -#define FLASH_FCoE_PRIMARY_IMAGE_START_g2 3670016 -#define FLASH_FCoE_BACKUP_IMAGE_START_g2 4980736 -#define FLASH_iSCSI_BIOS_START_g2 7340032 -#define FLASH_PXE_BIOS_START_g2 7864320 - -#define FLASH_REDBOOT_START_g3 262144 -#define FLASH_PHY_FW_START_g3 1310720 -#define FLASH_iSCSI_PRIMARY_IMAGE_START_g3 2097152 -#define FLASH_iSCSI_BACKUP_IMAGE_START_g3 4194304 -#define FLASH_FCoE_PRIMARY_IMAGE_START_g3 6291456 -#define FLASH_FCoE_BACKUP_IMAGE_START_g3 8388608 -#define FLASH_iSCSI_BIOS_START_g3 12582912 -#define FLASH_PXE_BIOS_START_g3 13107200 -#define FLASH_FCoE_BIOS_START_g3 13631488 -#define FLASH_NCSI_START_g3 15990784 - -#define IMAGE_NCSI 16 -#define IMAGE_OPTION_ROM_PXE 32 -#define IMAGE_OPTION_ROM_FCoE 33 -#define IMAGE_OPTION_ROM_ISCSI 34 -#define IMAGE_FLASHISM_JUMPVECTOR 48 -#define IMAGE_FIRMWARE_iSCSI 160 -#define IMAGE_FIRMWARE_FCoE 162 -#define IMAGE_FIRMWARE_BACKUP_iSCSI 176 -#define IMAGE_FIRMWARE_BACKUP_FCoE 178 -#define IMAGE_FIRMWARE_PHY 192 -#define IMAGE_REDBOOT_DIR 208 -#define IMAGE_REDBOOT_CONFIG 209 -#define IMAGE_UFI_DIR 210 -#define IMAGE_BOOT_CODE 224 +/* Optypes of each component in the UFI */ +enum { + OPTYPE_ISCSI_ACTIVE = 0, + OPTYPE_REDBOOT = 1, + OPTYPE_BIOS = 2, + OPTYPE_PXE_BIOS = 3, + OPTYPE_OFFSET_SPECIFIED = 7, + OPTYPE_FCOE_BIOS = 8, + OPTYPE_ISCSI_BACKUP = 9, + OPTYPE_FCOE_FW_ACTIVE = 10, + OPTYPE_FCOE_FW_BACKUP = 11, + OPTYPE_NCSI_FW = 13, + OPTYPE_REDBOOT_DIR = 18, + OPTYPE_REDBOOT_CONFIG = 19, + OPTYPE_SH_PHY_FW = 21, + OPTYPE_FLASHISM_JUMPVECTOR = 22, + OPTYPE_UFI_DIR = 23, + OPTYPE_PHY_FW = 99 +}; + +/* Maximum sizes of components in BE2 FW UFI */ +enum { + BE2_BIOS_COMP_MAX_SIZE = 0x40000, + BE2_REDBOOT_COMP_MAX_SIZE = 0x40000, + BE2_COMP_MAX_SIZE = 0x140000 +}; + +/* Maximum sizes of components in BE3 FW UFI */ +enum { + BE3_NCSI_COMP_MAX_SIZE = 0x40000, + BE3_PHY_FW_COMP_MAX_SIZE = 0x40000, + BE3_BIOS_COMP_MAX_SIZE = 0x80000, + BE3_REDBOOT_COMP_MAX_SIZE = 0x100000, + BE3_COMP_MAX_SIZE = 0x200000 +}; + +/* Offsets for components in BE2 FW UFI */ +enum { + BE2_REDBOOT_START = 0x8000, + BE2_FCOE_BIOS_START = 0x80000, + BE2_ISCSI_PRIMARY_IMAGE_START = 0x100000, + BE2_ISCSI_BACKUP_IMAGE_START = 0x240000, + BE2_FCOE_PRIMARY_IMAGE_START = 0x380000, + BE2_FCOE_BACKUP_IMAGE_START = 0x4c0000, + BE2_ISCSI_BIOS_START = 0x700000, + BE2_PXE_BIOS_START = 0x780000 +}; + +/* Offsets for components in BE3 FW UFI */ +enum { + BE3_REDBOOT_START = 0x40000, + BE3_PHY_FW_START = 0x140000, + BE3_ISCSI_PRIMARY_IMAGE_START = 0x200000, + BE3_ISCSI_BACKUP_IMAGE_START = 0x400000, + BE3_FCOE_PRIMARY_IMAGE_START = 0x600000, + BE3_FCOE_BACKUP_IMAGE_START = 0x800000, + BE3_ISCSI_BIOS_START = 0xc00000, + BE3_PXE_BIOS_START = 0xc80000, + BE3_FCOE_BIOS_START = 0xd00000, + BE3_NCSI_START = 0xf40000 +}; + +/* Component entry types */ +enum { + IMAGE_NCSI = 0x10, + IMAGE_OPTION_ROM_PXE = 0x20, + IMAGE_OPTION_ROM_FCOE = 0x21, + IMAGE_OPTION_ROM_ISCSI = 0x22, + IMAGE_FLASHISM_JUMPVECTOR = 0x30, + IMAGE_FIRMWARE_ISCSI = 0xa0, + IMAGE_FIRMWARE_FCOE = 0xa2, + IMAGE_FIRMWARE_BACKUP_ISCSI = 0xb0, + IMAGE_FIRMWARE_BACKUP_FCOE = 0xb2, + IMAGE_FIRMWARE_PHY = 0xc0, + IMAGE_REDBOOT_DIR = 0xd0, + IMAGE_REDBOOT_CONFIG = 0xd1, + IMAGE_UFI_DIR = 0xd2, + IMAGE_BOOT_CODE = 0xe2 +}; struct controller_id { u32 vendor; @@ -1394,6 +1411,9 @@ struct be_cmd_read_flash_crc { } __packed; /**************** Lancer Firmware Flash ************/ +#define LANCER_FW_DOWNLOAD_CHUNK (32 * 1024) +#define LANCER_FW_DOWNLOAD_LOCATION "/prg" + struct amap_lancer_write_obj_context { u8 write_length[24]; u8 reserved1[7]; @@ -1654,11 +1674,7 @@ struct mgmt_hba_attribs { struct mgmt_controller_attrib { struct mgmt_hba_attribs hba_attribs; - u32 rsvd0[2]; - u16 rsvd1; - u8 pci_func_num; - u8 rsvd2; - u32 rsvd3[7]; + u32 rsvd0[10]; } __packed; struct be_cmd_req_cntl_attribs { @@ -2083,6 +2099,7 @@ struct be_port_res_desc { #define NV_TYPE_VXLAN 3 #define SOCVID_SHIFT 2 /* Strip outer vlan */ #define RCVID_SHIFT 4 /* Report vlan */ +#define PF_NUM_IGNORE 255 u8 nv_flags; u8 rsvd2; __le16 nv_port; /* vxlan/gre port */ @@ -2246,7 +2263,8 @@ struct be_cmd_resp_get_iface_list { }; /*************** Set logical link ********************/ -#define PLINK_TRACK_SHIFT 8 +#define PLINK_ENABLE BIT(0) +#define PLINK_TRACK BIT(8) struct be_cmd_req_set_ll_link { struct be_cmd_req_hdr hdr; u32 link_config; /* Bit 0: UP_DOWN, Bit 9: PLINK */ @@ -2321,19 +2339,11 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, u8 page_num, u8 *data); int be_cmd_query_cable_type(struct be_adapter *adapter); int be_cmd_query_sfp_info(struct be_adapter *adapter); -int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd, - u32 flash_oper, u32 flash_opcode, u32 img_offset, - u32 buf_size); -int lancer_cmd_write_object(struct be_adapter *adapter, struct be_dma_mem *cmd, - u32 data_size, u32 data_offset, - const char *obj_name, u32 *data_written, - u8 *change_status, u8 *addn_status); int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd, u32 data_size, u32 data_offset, const char *obj_name, u32 *data_read, u32 *eof, u8 *addn_status); -int lancer_cmd_delete_object(struct be_adapter *adapter, const char *obj_name); -int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc, - u16 img_optype, u32 img_offset, u32 crc_offset); +int lancer_fw_download(struct be_adapter *adapter, const struct firmware *fw); +int be_fw_download(struct be_adapter *adapter, const struct firmware *fw); int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac, struct be_dma_mem *nonemb_cmd); int be_cmd_fw_init(struct be_adapter *adapter); @@ -2355,9 +2365,9 @@ int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate, void be_detect_error(struct be_adapter *adapter); int be_cmd_get_die_temperature(struct be_adapter *adapter); int be_cmd_get_cntl_attributes(struct be_adapter *adapter); +int be_cmd_get_fat_dump_len(struct be_adapter *adapter, u32 *dump_size); +int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf); int be_cmd_req_native_mode(struct be_adapter *adapter); -int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size); -int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf); int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege, u32 domain); int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges, diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index d2a5baf019ab8..a19ac441336f7 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -250,6 +250,19 @@ static u32 lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name) return data_read; } +static int be_get_dump_len(struct be_adapter *adapter) +{ + u32 dump_size = 0; + + if (lancer_chip(adapter)) + dump_size = lancer_cmd_get_file_len(adapter, + LANCER_FW_DUMP_FILE); + else + dump_size = adapter->fat_dump_len; + + return dump_size; +} + static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name, u32 buf_len, void *buf) { @@ -291,37 +304,18 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name, return status; } -static int be_get_reg_len(struct net_device *netdev) +static int be_read_dump_data(struct be_adapter *adapter, u32 dump_len, + void *buf) { - struct be_adapter *adapter = netdev_priv(netdev); - u32 log_size = 0; - - if (!check_privilege(adapter, MAX_PRIVILEGES)) - return 0; - - if (be_physfn(adapter)) { - if (lancer_chip(adapter)) - log_size = lancer_cmd_get_file_len(adapter, - LANCER_FW_DUMP_FILE); - else - be_cmd_get_reg_len(adapter, &log_size); - } - return log_size; -} + int status = 0; -static void -be_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *buf) -{ - struct be_adapter *adapter = netdev_priv(netdev); + if (lancer_chip(adapter)) + status = lancer_cmd_read_file(adapter, LANCER_FW_DUMP_FILE, + dump_len, buf); + else + status = be_cmd_get_fat_dump(adapter, dump_len, buf); - if (be_physfn(adapter)) { - memset(buf, 0, regs->len); - if (lancer_chip(adapter)) - lancer_cmd_read_file(adapter, LANCER_FW_DUMP_FILE, - regs->len, buf); - else - be_cmd_get_regs(adapter, regs->len, buf); - } + return status; } static int be_get_coalesce(struct net_device *netdev, @@ -914,6 +908,34 @@ static int be_do_flash(struct net_device *netdev, struct ethtool_flash *efl) return be_load_fw(adapter, efl->data); } +static int +be_get_dump_flag(struct net_device *netdev, struct ethtool_dump *dump) +{ + struct be_adapter *adapter = netdev_priv(netdev); + + if (!check_privilege(adapter, MAX_PRIVILEGES)) + return -EOPNOTSUPP; + + dump->len = be_get_dump_len(adapter); + dump->version = 1; + dump->flag = 0x1; /* FW dump is enabled */ + return 0; +} + +static int +be_get_dump_data(struct net_device *netdev, struct ethtool_dump *dump, + void *buf) +{ + struct be_adapter *adapter = netdev_priv(netdev); + int status; + + if (!check_privilege(adapter, MAX_PRIVILEGES)) + return -EOPNOTSUPP; + + status = be_read_dump_data(adapter, dump->len, buf); + return be_cmd_status(status); +} + static int be_get_eeprom_len(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -1311,8 +1333,6 @@ const struct ethtool_ops be_ethtool_ops = { .set_msglevel = be_set_msg_level, .get_sset_count = be_get_sset_count, .get_ethtool_stats = be_get_ethtool_stats, - .get_regs_len = be_get_reg_len, - .get_regs = be_get_regs, .flash_device = be_do_flash, .self_test = be_self_test, .get_rxnfc = be_get_rxnfc, @@ -1321,6 +1341,8 @@ const struct ethtool_ops be_ethtool_ops = { .get_rxfh_key_size = be_get_rxfh_key_size, .get_rxfh = be_get_rxfh, .set_rxfh = be_set_rxfh, + .get_dump_flag = be_get_dump_flag, + .get_dump_data = be_get_dump_data, .get_channels = be_get_channels, .set_channels = be_set_channels, .get_module_info = be_get_module_info, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 4cab8879f5ae4..f99de3657ce3b 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -729,7 +729,7 @@ static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter, /* If vlan priority provided by OS is NOT in available bmap */ if (!(adapter->vlan_prio_bmap & (1 << vlan_prio))) vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) | - adapter->recommended_prio; + adapter->recommended_prio_bits; return vlan_tag; } @@ -3297,8 +3297,10 @@ static int be_msix_register(struct be_adapter *adapter) return 0; err_msix: - for (i--, eqo = &adapter->eq_obj[i]; i >= 0; i--, eqo--) + for (i--; i >= 0; i--) { + eqo = &adapter->eq_obj[i]; free_irq(be_msix_vec_get(adapter, eqo), eqo); + } dev_warn(&adapter->pdev->dev, "MSIX Request IRQ failed - err %d\n", status); be_msix_disable(adapter); @@ -3430,8 +3432,6 @@ static int be_close(struct net_device *netdev) be_disable_if_filters(adapter); - be_roce_dev_close(adapter); - if (adapter->flags & BE_FLAGS_NAPI_ENABLED) { for_all_evt_queues(adapter, eqo, i) { napi_disable(&eqo->napi); @@ -3599,8 +3599,6 @@ static int be_open(struct net_device *netdev) be_link_status_update(adapter, link_status); netif_tx_start_all_queues(netdev); - be_roce_dev_open(adapter); - #ifdef CONFIG_BE2NET_VXLAN if (skyhawk_chip(adapter)) vxlan_get_rx_port(netdev); @@ -4204,10 +4202,17 @@ static int be_get_config(struct be_adapter *adapter) int status, level; u16 profile_id; + status = be_cmd_get_cntl_attributes(adapter); + if (status) + return status; + status = be_cmd_query_fw_cfg(adapter); if (status) return status; + if (!lancer_chip(adapter) && be_physfn(adapter)) + be_cmd_get_fat_dump_len(adapter, &adapter->fat_dump_len); + if (BEx_chip(adapter)) { level = be_cmd_get_fw_log_level(adapter); adapter->msg_enable = @@ -4402,10 +4407,14 @@ static int be_setup(struct be_adapter *adapter) if (!lancer_chip(adapter)) be_cmd_req_native_mode(adapter); - /* Need to invoke this cmd first to get the PCI Function Number */ - status = be_cmd_get_cntl_attributes(adapter); - if (status) - return status; + /* invoke this cmd first to get pf_num and vf_num which are needed + * for issuing profile related cmds + */ + if (!BEx_chip(adapter)) { + status = be_cmd_get_func_config(adapter, NULL); + if (status) + return status; + } if (!BE2_chip(adapter) && be_physfn(adapter)) be_alloc_sriov_res(adapter); @@ -4490,570 +4499,6 @@ static void be_netpoll(struct net_device *netdev) } #endif -static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "}; - -static bool phy_flashing_required(struct be_adapter *adapter) -{ - return (adapter->phy.phy_type == PHY_TYPE_TN_8022 && - adapter->phy.interface_type == PHY_TYPE_BASET_10GB); -} - -static bool is_comp_in_ufi(struct be_adapter *adapter, - struct flash_section_info *fsec, int type) -{ - int i = 0, img_type = 0; - struct flash_section_info_g2 *fsec_g2 = NULL; - - if (BE2_chip(adapter)) - fsec_g2 = (struct flash_section_info_g2 *)fsec; - - for (i = 0; i < MAX_FLASH_COMP; i++) { - if (fsec_g2) - img_type = le32_to_cpu(fsec_g2->fsec_entry[i].type); - else - img_type = le32_to_cpu(fsec->fsec_entry[i].type); - - if (img_type == type) - return true; - } - return false; - -} - -static struct flash_section_info *get_fsec_info(struct be_adapter *adapter, - int header_size, - const struct firmware *fw) -{ - struct flash_section_info *fsec = NULL; - const u8 *p = fw->data; - - p += header_size; - while (p < (fw->data + fw->size)) { - fsec = (struct flash_section_info *)p; - if (!memcmp(flash_cookie, fsec->cookie, sizeof(flash_cookie))) - return fsec; - p += 32; - } - return NULL; -} - -static int be_check_flash_crc(struct be_adapter *adapter, const u8 *p, - u32 img_offset, u32 img_size, int hdr_size, - u16 img_optype, bool *crc_match) -{ - u32 crc_offset; - int status; - u8 crc[4]; - - status = be_cmd_get_flash_crc(adapter, crc, img_optype, img_offset, - img_size - 4); - if (status) - return status; - - crc_offset = hdr_size + img_offset + img_size - 4; - - /* Skip flashing, if crc of flashed region matches */ - if (!memcmp(crc, p + crc_offset, 4)) - *crc_match = true; - else - *crc_match = false; - - return status; -} - -static int be_flash(struct be_adapter *adapter, const u8 *img, - struct be_dma_mem *flash_cmd, int optype, int img_size, - u32 img_offset) -{ - u32 flash_op, num_bytes, total_bytes = img_size, bytes_sent = 0; - struct be_cmd_write_flashrom *req = flash_cmd->va; - int status; - - while (total_bytes) { - num_bytes = min_t(u32, 32*1024, total_bytes); - - total_bytes -= num_bytes; - - if (!total_bytes) { - if (optype == OPTYPE_PHY_FW) - flash_op = FLASHROM_OPER_PHY_FLASH; - else - flash_op = FLASHROM_OPER_FLASH; - } else { - if (optype == OPTYPE_PHY_FW) - flash_op = FLASHROM_OPER_PHY_SAVE; - else - flash_op = FLASHROM_OPER_SAVE; - } - - memcpy(req->data_buf, img, num_bytes); - img += num_bytes; - status = be_cmd_write_flashrom(adapter, flash_cmd, optype, - flash_op, img_offset + - bytes_sent, num_bytes); - if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST && - optype == OPTYPE_PHY_FW) - break; - else if (status) - return status; - - bytes_sent += num_bytes; - } - return 0; -} - -/* For BE2, BE3 and BE3-R */ -static int be_flash_BEx(struct be_adapter *adapter, - const struct firmware *fw, - struct be_dma_mem *flash_cmd, int num_of_images) -{ - int img_hdrs_size = (num_of_images * sizeof(struct image_hdr)); - struct device *dev = &adapter->pdev->dev; - struct flash_section_info *fsec = NULL; - int status, i, filehdr_size, num_comp; - const struct flash_comp *pflashcomp; - bool crc_match; - const u8 *p; - - struct flash_comp gen3_flash_types[] = { - { FLASH_iSCSI_PRIMARY_IMAGE_START_g3, OPTYPE_ISCSI_ACTIVE, - FLASH_IMAGE_MAX_SIZE_g3, IMAGE_FIRMWARE_iSCSI}, - { FLASH_REDBOOT_START_g3, OPTYPE_REDBOOT, - FLASH_REDBOOT_IMAGE_MAX_SIZE_g3, IMAGE_BOOT_CODE}, - { FLASH_iSCSI_BIOS_START_g3, OPTYPE_BIOS, - FLASH_BIOS_IMAGE_MAX_SIZE_g3, IMAGE_OPTION_ROM_ISCSI}, - { FLASH_PXE_BIOS_START_g3, OPTYPE_PXE_BIOS, - FLASH_BIOS_IMAGE_MAX_SIZE_g3, IMAGE_OPTION_ROM_PXE}, - { FLASH_FCoE_BIOS_START_g3, OPTYPE_FCOE_BIOS, - FLASH_BIOS_IMAGE_MAX_SIZE_g3, IMAGE_OPTION_ROM_FCoE}, - { FLASH_iSCSI_BACKUP_IMAGE_START_g3, OPTYPE_ISCSI_BACKUP, - FLASH_IMAGE_MAX_SIZE_g3, IMAGE_FIRMWARE_BACKUP_iSCSI}, - { FLASH_FCoE_PRIMARY_IMAGE_START_g3, OPTYPE_FCOE_FW_ACTIVE, - FLASH_IMAGE_MAX_SIZE_g3, IMAGE_FIRMWARE_FCoE}, - { FLASH_FCoE_BACKUP_IMAGE_START_g3, OPTYPE_FCOE_FW_BACKUP, - FLASH_IMAGE_MAX_SIZE_g3, IMAGE_FIRMWARE_BACKUP_FCoE}, - { FLASH_NCSI_START_g3, OPTYPE_NCSI_FW, - FLASH_NCSI_IMAGE_MAX_SIZE_g3, IMAGE_NCSI}, - { FLASH_PHY_FW_START_g3, OPTYPE_PHY_FW, - FLASH_PHY_FW_IMAGE_MAX_SIZE_g3, IMAGE_FIRMWARE_PHY} - }; - - struct flash_comp gen2_flash_types[] = { - { FLASH_iSCSI_PRIMARY_IMAGE_START_g2, OPTYPE_ISCSI_ACTIVE, - FLASH_IMAGE_MAX_SIZE_g2, IMAGE_FIRMWARE_iSCSI}, - { FLASH_REDBOOT_START_g2, OPTYPE_REDBOOT, - FLASH_REDBOOT_IMAGE_MAX_SIZE_g2, IMAGE_BOOT_CODE}, - { FLASH_iSCSI_BIOS_START_g2, OPTYPE_BIOS, - FLASH_BIOS_IMAGE_MAX_SIZE_g2, IMAGE_OPTION_ROM_ISCSI}, - { FLASH_PXE_BIOS_START_g2, OPTYPE_PXE_BIOS, - FLASH_BIOS_IMAGE_MAX_SIZE_g2, IMAGE_OPTION_ROM_PXE}, - { FLASH_FCoE_BIOS_START_g2, OPTYPE_FCOE_BIOS, - FLASH_BIOS_IMAGE_MAX_SIZE_g2, IMAGE_OPTION_ROM_FCoE}, - { FLASH_iSCSI_BACKUP_IMAGE_START_g2, OPTYPE_ISCSI_BACKUP, - FLASH_IMAGE_MAX_SIZE_g2, IMAGE_FIRMWARE_BACKUP_iSCSI}, - { FLASH_FCoE_PRIMARY_IMAGE_START_g2, OPTYPE_FCOE_FW_ACTIVE, - FLASH_IMAGE_MAX_SIZE_g2, IMAGE_FIRMWARE_FCoE}, - { FLASH_FCoE_BACKUP_IMAGE_START_g2, OPTYPE_FCOE_FW_BACKUP, - FLASH_IMAGE_MAX_SIZE_g2, IMAGE_FIRMWARE_BACKUP_FCoE} - }; - - if (BE3_chip(adapter)) { - pflashcomp = gen3_flash_types; - filehdr_size = sizeof(struct flash_file_hdr_g3); - num_comp = ARRAY_SIZE(gen3_flash_types); - } else { - pflashcomp = gen2_flash_types; - filehdr_size = sizeof(struct flash_file_hdr_g2); - num_comp = ARRAY_SIZE(gen2_flash_types); - img_hdrs_size = 0; - } - - /* Get flash section info*/ - fsec = get_fsec_info(adapter, filehdr_size + img_hdrs_size, fw); - if (!fsec) { - dev_err(dev, "Invalid Cookie. FW image may be corrupted\n"); - return -1; - } - for (i = 0; i < num_comp; i++) { - if (!is_comp_in_ufi(adapter, fsec, pflashcomp[i].img_type)) - continue; - - if ((pflashcomp[i].optype == OPTYPE_NCSI_FW) && - memcmp(adapter->fw_ver, "3.102.148.0", 11) < 0) - continue; - - if (pflashcomp[i].optype == OPTYPE_PHY_FW && - !phy_flashing_required(adapter)) - continue; - - if (pflashcomp[i].optype == OPTYPE_REDBOOT) { - status = be_check_flash_crc(adapter, fw->data, - pflashcomp[i].offset, - pflashcomp[i].size, - filehdr_size + - img_hdrs_size, - OPTYPE_REDBOOT, &crc_match); - if (status) { - dev_err(dev, - "Could not get CRC for 0x%x region\n", - pflashcomp[i].optype); - continue; - } - - if (crc_match) - continue; - } - - p = fw->data + filehdr_size + pflashcomp[i].offset + - img_hdrs_size; - if (p + pflashcomp[i].size > fw->data + fw->size) - return -1; - - status = be_flash(adapter, p, flash_cmd, pflashcomp[i].optype, - pflashcomp[i].size, 0); - if (status) { - dev_err(dev, "Flashing section type 0x%x failed\n", - pflashcomp[i].img_type); - return status; - } - } - return 0; -} - -static u16 be_get_img_optype(struct flash_section_entry fsec_entry) -{ - u32 img_type = le32_to_cpu(fsec_entry.type); - u16 img_optype = le16_to_cpu(fsec_entry.optype); - - if (img_optype != 0xFFFF) - return img_optype; - - switch (img_type) { - case IMAGE_FIRMWARE_iSCSI: - img_optype = OPTYPE_ISCSI_ACTIVE; - break; - case IMAGE_BOOT_CODE: - img_optype = OPTYPE_REDBOOT; - break; - case IMAGE_OPTION_ROM_ISCSI: - img_optype = OPTYPE_BIOS; - break; - case IMAGE_OPTION_ROM_PXE: - img_optype = OPTYPE_PXE_BIOS; - break; - case IMAGE_OPTION_ROM_FCoE: - img_optype = OPTYPE_FCOE_BIOS; - break; - case IMAGE_FIRMWARE_BACKUP_iSCSI: - img_optype = OPTYPE_ISCSI_BACKUP; - break; - case IMAGE_NCSI: - img_optype = OPTYPE_NCSI_FW; - break; - case IMAGE_FLASHISM_JUMPVECTOR: - img_optype = OPTYPE_FLASHISM_JUMPVECTOR; - break; - case IMAGE_FIRMWARE_PHY: - img_optype = OPTYPE_SH_PHY_FW; - break; - case IMAGE_REDBOOT_DIR: - img_optype = OPTYPE_REDBOOT_DIR; - break; - case IMAGE_REDBOOT_CONFIG: - img_optype = OPTYPE_REDBOOT_CONFIG; - break; - case IMAGE_UFI_DIR: - img_optype = OPTYPE_UFI_DIR; - break; - default: - break; - } - - return img_optype; -} - -static int be_flash_skyhawk(struct be_adapter *adapter, - const struct firmware *fw, - struct be_dma_mem *flash_cmd, int num_of_images) -{ - int img_hdrs_size = num_of_images * sizeof(struct image_hdr); - bool crc_match, old_fw_img, flash_offset_support = true; - struct device *dev = &adapter->pdev->dev; - struct flash_section_info *fsec = NULL; - u32 img_offset, img_size, img_type; - u16 img_optype, flash_optype; - int status, i, filehdr_size; - const u8 *p; - - filehdr_size = sizeof(struct flash_file_hdr_g3); - fsec = get_fsec_info(adapter, filehdr_size + img_hdrs_size, fw); - if (!fsec) { - dev_err(dev, "Invalid Cookie. FW image may be corrupted\n"); - return -EINVAL; - } - -retry_flash: - for (i = 0; i < le32_to_cpu(fsec->fsec_hdr.num_images); i++) { - img_offset = le32_to_cpu(fsec->fsec_entry[i].offset); - img_size = le32_to_cpu(fsec->fsec_entry[i].pad_size); - img_type = le32_to_cpu(fsec->fsec_entry[i].type); - img_optype = be_get_img_optype(fsec->fsec_entry[i]); - old_fw_img = fsec->fsec_entry[i].optype == 0xFFFF; - - if (img_optype == 0xFFFF) - continue; - - if (flash_offset_support) - flash_optype = OPTYPE_OFFSET_SPECIFIED; - else - flash_optype = img_optype; - - /* Don't bother verifying CRC if an old FW image is being - * flashed - */ - if (old_fw_img) - goto flash; - - status = be_check_flash_crc(adapter, fw->data, img_offset, - img_size, filehdr_size + - img_hdrs_size, flash_optype, - &crc_match); - if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST || - base_status(status) == MCC_STATUS_ILLEGAL_FIELD) { - /* The current FW image on the card does not support - * OFFSET based flashing. Retry using older mechanism - * of OPTYPE based flashing - */ - if (flash_optype == OPTYPE_OFFSET_SPECIFIED) { - flash_offset_support = false; - goto retry_flash; - } - - /* The current FW image on the card does not recognize - * the new FLASH op_type. The FW download is partially - * complete. Reboot the server now to enable FW image - * to recognize the new FLASH op_type. To complete the - * remaining process, download the same FW again after - * the reboot. - */ - dev_err(dev, "Flash incomplete. Reset the server\n"); - dev_err(dev, "Download FW image again after reset\n"); - return -EAGAIN; - } else if (status) { - dev_err(dev, "Could not get CRC for 0x%x region\n", - img_optype); - return -EFAULT; - } - - if (crc_match) - continue; - -flash: - p = fw->data + filehdr_size + img_offset + img_hdrs_size; - if (p + img_size > fw->data + fw->size) - return -1; - - status = be_flash(adapter, p, flash_cmd, flash_optype, img_size, - img_offset); - - /* The current FW image on the card does not support OFFSET - * based flashing. Retry using older mechanism of OPTYPE based - * flashing - */ - if (base_status(status) == MCC_STATUS_ILLEGAL_FIELD && - flash_optype == OPTYPE_OFFSET_SPECIFIED) { - flash_offset_support = false; - goto retry_flash; - } - - /* For old FW images ignore ILLEGAL_FIELD error or errors on - * UFI_DIR region - */ - if (old_fw_img && - (base_status(status) == MCC_STATUS_ILLEGAL_FIELD || - (img_optype == OPTYPE_UFI_DIR && - base_status(status) == MCC_STATUS_FAILED))) { - continue; - } else if (status) { - dev_err(dev, "Flashing section type 0x%x failed\n", - img_type); - return -EFAULT; - } - } - return 0; -} - -static int lancer_fw_download(struct be_adapter *adapter, - const struct firmware *fw) -{ -#define LANCER_FW_DOWNLOAD_CHUNK (32 * 1024) -#define LANCER_FW_DOWNLOAD_LOCATION "/prg" - struct device *dev = &adapter->pdev->dev; - struct be_dma_mem flash_cmd; - const u8 *data_ptr = NULL; - u8 *dest_image_ptr = NULL; - size_t image_size = 0; - u32 chunk_size = 0; - u32 data_written = 0; - u32 offset = 0; - int status = 0; - u8 add_status = 0; - u8 change_status; - - if (!IS_ALIGNED(fw->size, sizeof(u32))) { - dev_err(dev, "FW image size should be multiple of 4\n"); - return -EINVAL; - } - - flash_cmd.size = sizeof(struct lancer_cmd_req_write_object) - + LANCER_FW_DOWNLOAD_CHUNK; - flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, - &flash_cmd.dma, GFP_KERNEL); - if (!flash_cmd.va) - return -ENOMEM; - - dest_image_ptr = flash_cmd.va + - sizeof(struct lancer_cmd_req_write_object); - image_size = fw->size; - data_ptr = fw->data; - - while (image_size) { - chunk_size = min_t(u32, image_size, LANCER_FW_DOWNLOAD_CHUNK); - - /* Copy the image chunk content. */ - memcpy(dest_image_ptr, data_ptr, chunk_size); - - status = lancer_cmd_write_object(adapter, &flash_cmd, - chunk_size, offset, - LANCER_FW_DOWNLOAD_LOCATION, - &data_written, &change_status, - &add_status); - if (status) - break; - - offset += data_written; - data_ptr += data_written; - image_size -= data_written; - } - - if (!status) { - /* Commit the FW written */ - status = lancer_cmd_write_object(adapter, &flash_cmd, - 0, offset, - LANCER_FW_DOWNLOAD_LOCATION, - &data_written, &change_status, - &add_status); - } - - dma_free_coherent(dev, flash_cmd.size, flash_cmd.va, flash_cmd.dma); - if (status) { - dev_err(dev, "Firmware load error\n"); - return be_cmd_status(status); - } - - dev_info(dev, "Firmware flashed successfully\n"); - - if (change_status == LANCER_FW_RESET_NEEDED) { - dev_info(dev, "Resetting adapter to activate new FW\n"); - status = lancer_physdev_ctrl(adapter, - PHYSDEV_CONTROL_FW_RESET_MASK); - if (status) { - dev_err(dev, "Adapter busy, could not reset FW\n"); - dev_err(dev, "Reboot server to activate new FW\n"); - } - } else if (change_status != LANCER_NO_RESET_NEEDED) { - dev_info(dev, "Reboot server to activate new FW\n"); - } - - return 0; -} - -/* Check if the flash image file is compatible with the adapter that - * is being flashed. - */ -static bool be_check_ufi_compatibility(struct be_adapter *adapter, - struct flash_file_hdr_g3 *fhdr) -{ - if (!fhdr) { - dev_err(&adapter->pdev->dev, "Invalid FW UFI file"); - return false; - } - - /* First letter of the build version is used to identify - * which chip this image file is meant for. - */ - switch (fhdr->build[0]) { - case BLD_STR_UFI_TYPE_SH: - if (!skyhawk_chip(adapter)) - return false; - break; - case BLD_STR_UFI_TYPE_BE3: - if (!BE3_chip(adapter)) - return false; - break; - case BLD_STR_UFI_TYPE_BE2: - if (!BE2_chip(adapter)) - return false; - break; - default: - return false; - } - - /* In BE3 FW images the "asic_type_rev" field doesn't track the - * asic_rev of the chips it is compatible with. - * When asic_type_rev is 0 the image is compatible only with - * pre-BE3-R chips (asic_rev < 0x10) - */ - if (BEx_chip(adapter) && fhdr->asic_type_rev == 0) - return adapter->asic_rev < 0x10; - else - return (fhdr->asic_type_rev >= adapter->asic_rev); -} - -static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw) -{ - struct device *dev = &adapter->pdev->dev; - struct flash_file_hdr_g3 *fhdr3; - struct image_hdr *img_hdr_ptr; - int status = 0, i, num_imgs; - struct be_dma_mem flash_cmd; - - fhdr3 = (struct flash_file_hdr_g3 *)fw->data; - if (!be_check_ufi_compatibility(adapter, fhdr3)) { - dev_err(dev, "Flash image is not compatible with adapter\n"); - return -EINVAL; - } - - flash_cmd.size = sizeof(struct be_cmd_write_flashrom); - flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, &flash_cmd.dma, - GFP_KERNEL); - if (!flash_cmd.va) - return -ENOMEM; - - num_imgs = le32_to_cpu(fhdr3->num_imgs); - for (i = 0; i < num_imgs; i++) { - img_hdr_ptr = (struct image_hdr *)(fw->data + - (sizeof(struct flash_file_hdr_g3) + - i * sizeof(struct image_hdr))); - if (!BE2_chip(adapter) && - le32_to_cpu(img_hdr_ptr->imageid) != 1) - continue; - - if (skyhawk_chip(adapter)) - status = be_flash_skyhawk(adapter, fw, &flash_cmd, - num_imgs); - else - status = be_flash_BEx(adapter, fw, &flash_cmd, - num_imgs); - } - - dma_free_coherent(dev, flash_cmd.size, flash_cmd.va, flash_cmd.dma); - if (!status) - dev_info(dev, "Firmware flashed successfully\n"); - - return status; -} - int be_load_fw(struct be_adapter *adapter, u8 *fw_file) { const struct firmware *fw; @@ -5108,6 +4553,9 @@ static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, return -EINVAL; mode = nla_get_u16(attr); + if (BE3_chip(adapter) && mode == BRIDGE_MODE_VEPA) + return -EOPNOTSUPP; + if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) return -EINVAL; @@ -5289,7 +4737,7 @@ static netdev_features_t be_features_check(struct sk_buff *skb, skb->inner_protocol != htons(ETH_P_TEB) || skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)) - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c index 60368207bf584..4089156a7f5e2 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.c +++ b/drivers/net/ethernet/emulex/benet/be_roce.c @@ -116,40 +116,6 @@ void be_roce_dev_remove(struct be_adapter *adapter) } } -static void _be_roce_dev_open(struct be_adapter *adapter) -{ - if (ocrdma_drv && adapter->ocrdma_dev && - ocrdma_drv->state_change_handler) - ocrdma_drv->state_change_handler(adapter->ocrdma_dev, - BE_DEV_UP); -} - -void be_roce_dev_open(struct be_adapter *adapter) -{ - if (be_roce_supported(adapter)) { - mutex_lock(&be_adapter_list_lock); - _be_roce_dev_open(adapter); - mutex_unlock(&be_adapter_list_lock); - } -} - -static void _be_roce_dev_close(struct be_adapter *adapter) -{ - if (ocrdma_drv && adapter->ocrdma_dev && - ocrdma_drv->state_change_handler) - ocrdma_drv->state_change_handler(adapter->ocrdma_dev, - BE_DEV_DOWN); -} - -void be_roce_dev_close(struct be_adapter *adapter) -{ - if (be_roce_supported(adapter)) { - mutex_lock(&be_adapter_list_lock); - _be_roce_dev_close(adapter); - mutex_unlock(&be_adapter_list_lock); - } -} - void be_roce_dev_shutdown(struct be_adapter *adapter) { if (be_roce_supported(adapter)) { @@ -177,8 +143,6 @@ int be_roce_register_driver(struct ocrdma_driver *drv) _be_roce_dev_add(dev); netdev = dev->netdev; - if (netif_running(netdev) && netif_oper_up(netdev)) - _be_roce_dev_open(dev); } mutex_unlock(&be_adapter_list_lock); return 0; diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h index cde6ef905ec48..fde6097894838 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.h +++ b/drivers/net/ethernet/emulex/benet/be_roce.h @@ -60,9 +60,7 @@ struct ocrdma_driver { void (*state_change_handler) (struct ocrdma_dev *, u32 new_state); }; -enum { - BE_DEV_UP = 0, - BE_DEV_DOWN = 1, +enum be_roce_event { BE_DEV_SHUTDOWN = 2 }; diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 63c2bcf8031a8..b1026689b78f4 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -48,21 +48,15 @@ static void nps_enet_read_rx_fifo(struct net_device *ndev, *reg = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); else { /* !dst_is_aligned */ for (i = 0; i < len; i++, reg++) { - u32 buf = - nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); - - /* to accommodate word-unaligned address of "reg" - * we have to do memcpy_toio() instead of simple "=". - */ - memcpy_toio((void __iomem *)reg, &buf, sizeof(buf)); + u32 buf = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); + put_unaligned(buf, reg); } } /* copy last bytes (if any) */ if (last) { u32 buf = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); - - memcpy_toio((void __iomem *)reg, &buf, last); + memcpy((u8*)reg, &buf, last); } } @@ -367,7 +361,7 @@ static void nps_enet_send_frame(struct net_device *ndev, struct nps_enet_tx_ctl tx_ctrl; short length = skb->len; u32 i, len = DIV_ROUND_UP(length, sizeof(u32)); - u32 *src = (u32 *)virt_to_phys(skb->data); + u32 *src = (void *)skb->data; bool src_is_aligned = IS_ALIGNED((unsigned long)src, sizeof(u32)); tx_ctrl.value = 0; @@ -375,17 +369,11 @@ static void nps_enet_send_frame(struct net_device *ndev, if (src_is_aligned) for (i = 0; i < len; i++, src++) nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, *src); - else { /* !src_is_aligned */ - for (i = 0; i < len; i++, src++) { - u32 buf; - - /* to accommodate word-unaligned address of "src" - * we have to do memcpy_fromio() instead of simple "=" - */ - memcpy_fromio(&buf, (void __iomem *)src, sizeof(buf)); - nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, buf); - } - } + else /* !src_is_aligned */ + for (i = 0; i < len; i++, src++) + nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, + get_unaligned(src)); + /* Write the length of the Frame */ tx_ctrl.nt = length; diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index bee32a9d9876f..d1ca45fbb1645 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -54,6 +54,7 @@ config FEC_MPC52xx_MDIO If compiled as module, it will be called fec_mpc52xx_phy. source "drivers/net/ethernet/freescale/fs_enet/Kconfig" +source "drivers/net/ethernet/freescale/fman/Kconfig" config FSL_PQ_MDIO tristate "Freescale PQ MDIO" diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index 71debd1c18c99..4097c58d17a75 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -17,3 +17,5 @@ gianfar_driver-objs := gianfar.o \ gianfar_ethtool.o obj-$(CONFIG_UCC_GETH) += ucc_geth_driver.o ucc_geth_driver-objs := ucc_geth.o ucc_geth_ethtool.o + +obj-$(CONFIG_FSL_FMAN) += fman/ diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig new file mode 100644 index 0000000000000..79b7c84b78699 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -0,0 +1,9 @@ +config FSL_FMAN + tristate "FMan support" + depends on FSL_SOC || COMPILE_TEST + select GENERIC_ALLOCATOR + select PHYLIB + default n + help + Freescale Data-Path Acceleration Architecture Frame Manager + (FMan) support diff --git a/drivers/net/ethernet/freescale/fman/Makefile b/drivers/net/ethernet/freescale/fman/Makefile new file mode 100644 index 0000000000000..51fd2e6c1b844 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/Makefile @@ -0,0 +1,7 @@ +subdir-ccflags-y += -I$(srctree)/drivers/net/ethernet/freescale/fman + +obj-y += fsl_fman.o fsl_fman_mac.o fsl_mac.o + +fsl_fman-objs := fman_muram.o fman.o fman_sp.o fman_port.o +fsl_fman_mac-objs := fman_dtsec.o fman_memac.o fman_tgec.o +fsl_mac-objs += mac.o diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c new file mode 100644 index 0000000000000..623aa1c8ebc6b --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -0,0 +1,2871 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include "fman.h" +#include "fman_muram.h" + +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/clk.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/interrupt.h> +#include <linux/libfdt_env.h> + +/* General defines */ +#define FMAN_LIODN_TBL 64 /* size of LIODN table */ +#define MAX_NUM_OF_MACS 10 +#define FM_NUM_OF_FMAN_CTRL_EVENT_REGS 4 +#define BASE_RX_PORTID 0x08 +#define BASE_TX_PORTID 0x28 + +/* Modules registers offsets */ +#define BMI_OFFSET 0x00080000 +#define QMI_OFFSET 0x00080400 +#define DMA_OFFSET 0x000C2000 +#define FPM_OFFSET 0x000C3000 +#define IMEM_OFFSET 0x000C4000 +#define CGP_OFFSET 0x000DB000 + +/* Exceptions bit map */ +#define EX_DMA_BUS_ERROR 0x80000000 +#define EX_DMA_READ_ECC 0x40000000 +#define EX_DMA_SYSTEM_WRITE_ECC 0x20000000 +#define EX_DMA_FM_WRITE_ECC 0x10000000 +#define EX_FPM_STALL_ON_TASKS 0x08000000 +#define EX_FPM_SINGLE_ECC 0x04000000 +#define EX_FPM_DOUBLE_ECC 0x02000000 +#define EX_QMI_SINGLE_ECC 0x01000000 +#define EX_QMI_DEQ_FROM_UNKNOWN_PORTID 0x00800000 +#define EX_QMI_DOUBLE_ECC 0x00400000 +#define EX_BMI_LIST_RAM_ECC 0x00200000 +#define EX_BMI_STORAGE_PROFILE_ECC 0x00100000 +#define EX_BMI_STATISTICS_RAM_ECC 0x00080000 +#define EX_IRAM_ECC 0x00040000 +#define EX_MURAM_ECC 0x00020000 +#define EX_BMI_DISPATCH_RAM_ECC 0x00010000 +#define EX_DMA_SINGLE_PORT_ECC 0x00008000 + +/* DMA defines */ +/* masks */ +#define DMA_MODE_BER 0x00200000 +#define DMA_MODE_ECC 0x00000020 +#define DMA_MODE_SECURE_PROT 0x00000800 +#define DMA_MODE_AXI_DBG_MASK 0x0F000000 + +#define DMA_TRANSFER_PORTID_MASK 0xFF000000 +#define DMA_TRANSFER_TNUM_MASK 0x00FF0000 +#define DMA_TRANSFER_LIODN_MASK 0x00000FFF + +#define DMA_STATUS_BUS_ERR 0x08000000 +#define DMA_STATUS_READ_ECC 0x04000000 +#define DMA_STATUS_SYSTEM_WRITE_ECC 0x02000000 +#define DMA_STATUS_FM_WRITE_ECC 0x01000000 +#define DMA_STATUS_FM_SPDAT_ECC 0x00080000 + +#define DMA_MODE_CACHE_OR_SHIFT 30 +#define DMA_MODE_AXI_DBG_SHIFT 24 +#define DMA_MODE_CEN_SHIFT 13 +#define DMA_MODE_CEN_MASK 0x00000007 +#define DMA_MODE_DBG_SHIFT 7 +#define DMA_MODE_AID_MODE_SHIFT 4 + +#define DMA_THRESH_COMMQ_SHIFT 24 +#define DMA_THRESH_READ_INT_BUF_SHIFT 16 +#define DMA_THRESH_READ_INT_BUF_MASK 0x0000003f +#define DMA_THRESH_WRITE_INT_BUF_MASK 0x0000003f + +#define DMA_TRANSFER_PORTID_SHIFT 24 +#define DMA_TRANSFER_TNUM_SHIFT 16 + +#define DMA_CAM_SIZEOF_ENTRY 0x40 +#define DMA_CAM_UNITS 8 + +#define DMA_LIODN_SHIFT 16 +#define DMA_LIODN_BASE_MASK 0x00000FFF + +/* FPM defines */ +#define FPM_EV_MASK_DOUBLE_ECC 0x80000000 +#define FPM_EV_MASK_STALL 0x40000000 +#define FPM_EV_MASK_SINGLE_ECC 0x20000000 +#define FPM_EV_MASK_RELEASE_FM 0x00010000 +#define FPM_EV_MASK_DOUBLE_ECC_EN 0x00008000 +#define FPM_EV_MASK_STALL_EN 0x00004000 +#define FPM_EV_MASK_SINGLE_ECC_EN 0x00002000 +#define FPM_EV_MASK_EXTERNAL_HALT 0x00000008 +#define FPM_EV_MASK_ECC_ERR_HALT 0x00000004 + +#define FPM_RAM_MURAM_ECC 0x00008000 +#define FPM_RAM_IRAM_ECC 0x00004000 +#define FPM_IRAM_ECC_ERR_EX_EN 0x00020000 +#define FPM_MURAM_ECC_ERR_EX_EN 0x00040000 +#define FPM_RAM_IRAM_ECC_EN 0x40000000 +#define FPM_RAM_RAMS_ECC_EN 0x80000000 +#define FPM_RAM_RAMS_ECC_EN_SRC_SEL 0x08000000 + +#define FPM_REV1_MAJOR_MASK 0x0000FF00 +#define FPM_REV1_MINOR_MASK 0x000000FF + +#define FPM_DISP_LIMIT_SHIFT 24 + +#define FPM_PRT_FM_CTL1 0x00000001 +#define FPM_PRT_FM_CTL2 0x00000002 +#define FPM_PORT_FM_CTL_PORTID_SHIFT 24 +#define FPM_PRC_ORA_FM_CTL_SEL_SHIFT 16 + +#define FPM_THR1_PRS_SHIFT 24 +#define FPM_THR1_KG_SHIFT 16 +#define FPM_THR1_PLCR_SHIFT 8 +#define FPM_THR1_BMI_SHIFT 0 + +#define FPM_THR2_QMI_ENQ_SHIFT 24 +#define FPM_THR2_QMI_DEQ_SHIFT 0 +#define FPM_THR2_FM_CTL1_SHIFT 16 +#define FPM_THR2_FM_CTL2_SHIFT 8 + +#define FPM_EV_MASK_CAT_ERR_SHIFT 1 +#define FPM_EV_MASK_DMA_ERR_SHIFT 0 + +#define FPM_REV1_MAJOR_SHIFT 8 + +#define FPM_RSTC_FM_RESET 0x80000000 +#define FPM_RSTC_MAC0_RESET 0x40000000 +#define FPM_RSTC_MAC1_RESET 0x20000000 +#define FPM_RSTC_MAC2_RESET 0x10000000 +#define FPM_RSTC_MAC3_RESET 0x08000000 +#define FPM_RSTC_MAC8_RESET 0x04000000 +#define FPM_RSTC_MAC4_RESET 0x02000000 +#define FPM_RSTC_MAC5_RESET 0x01000000 +#define FPM_RSTC_MAC6_RESET 0x00800000 +#define FPM_RSTC_MAC7_RESET 0x00400000 +#define FPM_RSTC_MAC9_RESET 0x00200000 + +#define FPM_TS_INT_SHIFT 16 +#define FPM_TS_CTL_EN 0x80000000 + +/* BMI defines */ +#define BMI_INIT_START 0x80000000 +#define BMI_ERR_INTR_EN_STORAGE_PROFILE_ECC 0x80000000 +#define BMI_ERR_INTR_EN_LIST_RAM_ECC 0x40000000 +#define BMI_ERR_INTR_EN_STATISTICS_RAM_ECC 0x20000000 +#define BMI_ERR_INTR_EN_DISPATCH_RAM_ECC 0x10000000 +#define BMI_NUM_OF_TASKS_MASK 0x3F000000 +#define BMI_NUM_OF_EXTRA_TASKS_MASK 0x000F0000 +#define BMI_NUM_OF_DMAS_MASK 0x00000F00 +#define BMI_NUM_OF_EXTRA_DMAS_MASK 0x0000000F +#define BMI_FIFO_SIZE_MASK 0x000003FF +#define BMI_EXTRA_FIFO_SIZE_MASK 0x03FF0000 +#define BMI_CFG2_DMAS_MASK 0x0000003F +#define BMI_CFG2_TASKS_MASK 0x0000003F + +#define BMI_CFG2_TASKS_SHIFT 16 +#define BMI_CFG2_DMAS_SHIFT 0 +#define BMI_CFG1_FIFO_SIZE_SHIFT 16 +#define BMI_NUM_OF_TASKS_SHIFT 24 +#define BMI_EXTRA_NUM_OF_TASKS_SHIFT 16 +#define BMI_NUM_OF_DMAS_SHIFT 8 +#define BMI_EXTRA_NUM_OF_DMAS_SHIFT 0 + +#define BMI_FIFO_ALIGN 0x100 + +#define BMI_EXTRA_FIFO_SIZE_SHIFT 16 + +/* QMI defines */ +#define QMI_CFG_ENQ_EN 0x80000000 +#define QMI_CFG_DEQ_EN 0x40000000 +#define QMI_CFG_EN_COUNTERS 0x10000000 +#define QMI_CFG_DEQ_MASK 0x0000003F +#define QMI_CFG_ENQ_MASK 0x00003F00 +#define QMI_CFG_ENQ_SHIFT 8 + +#define QMI_ERR_INTR_EN_DOUBLE_ECC 0x80000000 +#define QMI_ERR_INTR_EN_DEQ_FROM_DEF 0x40000000 +#define QMI_INTR_EN_SINGLE_ECC 0x80000000 + +#define QMI_GS_HALT_NOT_BUSY 0x00000002 + +/* IRAM defines */ +#define IRAM_IADD_AIE 0x80000000 +#define IRAM_READY 0x80000000 + +/* Default values */ +#define DEFAULT_CATASTROPHIC_ERR 0 +#define DEFAULT_DMA_ERR 0 +#define DEFAULT_AID_MODE FMAN_DMA_AID_OUT_TNUM +#define DEFAULT_DMA_COMM_Q_LOW 0x2A +#define DEFAULT_DMA_COMM_Q_HIGH 0x3F +#define DEFAULT_CACHE_OVERRIDE 0 +#define DEFAULT_DMA_CAM_NUM_OF_ENTRIES 64 +#define DEFAULT_DMA_DBG_CNT_MODE 0 +#define DEFAULT_DMA_SOS_EMERGENCY 0 +#define DEFAULT_DMA_WATCHDOG 0 +#define DEFAULT_DISP_LIMIT 0 +#define DEFAULT_PRS_DISP_TH 16 +#define DEFAULT_PLCR_DISP_TH 16 +#define DEFAULT_KG_DISP_TH 16 +#define DEFAULT_BMI_DISP_TH 16 +#define DEFAULT_QMI_ENQ_DISP_TH 16 +#define DEFAULT_QMI_DEQ_DISP_TH 16 +#define DEFAULT_FM_CTL1_DISP_TH 16 +#define DEFAULT_FM_CTL2_DISP_TH 16 + +#define DFLT_AXI_DBG_NUM_OF_BEATS 1 + +#define DFLT_DMA_READ_INT_BUF_LOW(dma_thresh_max_buf) \ + ((dma_thresh_max_buf + 1) / 2) +#define DFLT_DMA_READ_INT_BUF_HIGH(dma_thresh_max_buf) \ + ((dma_thresh_max_buf + 1) * 3 / 4) +#define DFLT_DMA_WRITE_INT_BUF_LOW(dma_thresh_max_buf) \ + ((dma_thresh_max_buf + 1) / 2) +#define DFLT_DMA_WRITE_INT_BUF_HIGH(dma_thresh_max_buf)\ + ((dma_thresh_max_buf + 1) * 3 / 4) + +#define DMA_COMM_Q_LOW_FMAN_V3 0x2A +#define DMA_COMM_Q_LOW_FMAN_V2(dma_thresh_max_commq) \ + ((dma_thresh_max_commq + 1) / 2) +#define DFLT_DMA_COMM_Q_LOW(major, dma_thresh_max_commq) \ + ((major == 6) ? DMA_COMM_Q_LOW_FMAN_V3 : \ + DMA_COMM_Q_LOW_FMAN_V2(dma_thresh_max_commq)) + +#define DMA_COMM_Q_HIGH_FMAN_V3 0x3f +#define DMA_COMM_Q_HIGH_FMAN_V2(dma_thresh_max_commq) \ + ((dma_thresh_max_commq + 1) * 3 / 4) +#define DFLT_DMA_COMM_Q_HIGH(major, dma_thresh_max_commq) \ + ((major == 6) ? DMA_COMM_Q_HIGH_FMAN_V3 : \ + DMA_COMM_Q_HIGH_FMAN_V2(dma_thresh_max_commq)) + +#define TOTAL_NUM_OF_TASKS_FMAN_V3L 59 +#define TOTAL_NUM_OF_TASKS_FMAN_V3H 124 +#define DFLT_TOTAL_NUM_OF_TASKS(major, minor, bmi_max_num_of_tasks) \ + ((major == 6) ? ((minor == 1 || minor == 4) ? \ + TOTAL_NUM_OF_TASKS_FMAN_V3L : TOTAL_NUM_OF_TASKS_FMAN_V3H) : \ + bmi_max_num_of_tasks) + +#define DMA_CAM_NUM_OF_ENTRIES_FMAN_V3 64 +#define DMA_CAM_NUM_OF_ENTRIES_FMAN_V2 32 +#define DFLT_DMA_CAM_NUM_OF_ENTRIES(major) \ + (major == 6 ? DMA_CAM_NUM_OF_ENTRIES_FMAN_V3 : \ + DMA_CAM_NUM_OF_ENTRIES_FMAN_V2) + +#define FM_TIMESTAMP_1_USEC_BIT 8 + +/* Defines used for enabling/disabling FMan interrupts */ +#define ERR_INTR_EN_DMA 0x00010000 +#define ERR_INTR_EN_FPM 0x80000000 +#define ERR_INTR_EN_BMI 0x00800000 +#define ERR_INTR_EN_QMI 0x00400000 +#define ERR_INTR_EN_MURAM 0x00040000 +#define ERR_INTR_EN_MAC0 0x00004000 +#define ERR_INTR_EN_MAC1 0x00002000 +#define ERR_INTR_EN_MAC2 0x00001000 +#define ERR_INTR_EN_MAC3 0x00000800 +#define ERR_INTR_EN_MAC4 0x00000400 +#define ERR_INTR_EN_MAC5 0x00000200 +#define ERR_INTR_EN_MAC6 0x00000100 +#define ERR_INTR_EN_MAC7 0x00000080 +#define ERR_INTR_EN_MAC8 0x00008000 +#define ERR_INTR_EN_MAC9 0x00000040 + +#define INTR_EN_QMI 0x40000000 +#define INTR_EN_MAC0 0x00080000 +#define INTR_EN_MAC1 0x00040000 +#define INTR_EN_MAC2 0x00020000 +#define INTR_EN_MAC3 0x00010000 +#define INTR_EN_MAC4 0x00000040 +#define INTR_EN_MAC5 0x00000020 +#define INTR_EN_MAC6 0x00000008 +#define INTR_EN_MAC7 0x00000002 +#define INTR_EN_MAC8 0x00200000 +#define INTR_EN_MAC9 0x00100000 +#define INTR_EN_REV0 0x00008000 +#define INTR_EN_REV1 0x00004000 +#define INTR_EN_REV2 0x00002000 +#define INTR_EN_REV3 0x00001000 +#define INTR_EN_TMR 0x01000000 + +enum fman_dma_aid_mode { + FMAN_DMA_AID_OUT_PORT_ID = 0, /* 4 LSB of PORT_ID */ + FMAN_DMA_AID_OUT_TNUM /* 4 LSB of TNUM */ +}; + +struct fman_iram_regs { + u32 iadd; /* FM IRAM instruction address register */ + u32 idata; /* FM IRAM instruction data register */ + u32 itcfg; /* FM IRAM timing config register */ + u32 iready; /* FM IRAM ready register */ +}; + +struct fman_fpm_regs { + u32 fmfp_tnc; /* FPM TNUM Control 0x00 */ + u32 fmfp_prc; /* FPM Port_ID FmCtl Association 0x04 */ + u32 fmfp_brkc; /* FPM Breakpoint Control 0x08 */ + u32 fmfp_mxd; /* FPM Flush Control 0x0c */ + u32 fmfp_dist1; /* FPM Dispatch Thresholds1 0x10 */ + u32 fmfp_dist2; /* FPM Dispatch Thresholds2 0x14 */ + u32 fm_epi; /* FM Error Pending Interrupts 0x18 */ + u32 fm_rie; /* FM Error Interrupt Enable 0x1c */ + u32 fmfp_fcev[4]; /* FPM FMan-Controller Event 1-4 0x20-0x2f */ + u32 res0030[4]; /* res 0x30 - 0x3f */ + u32 fmfp_cee[4]; /* PM FMan-Controller Event 1-4 0x40-0x4f */ + u32 res0050[4]; /* res 0x50-0x5f */ + u32 fmfp_tsc1; /* FPM TimeStamp Control1 0x60 */ + u32 fmfp_tsc2; /* FPM TimeStamp Control2 0x64 */ + u32 fmfp_tsp; /* FPM Time Stamp 0x68 */ + u32 fmfp_tsf; /* FPM Time Stamp Fraction 0x6c */ + u32 fm_rcr; /* FM Rams Control 0x70 */ + u32 fmfp_extc; /* FPM External Requests Control 0x74 */ + u32 fmfp_ext1; /* FPM External Requests Config1 0x78 */ + u32 fmfp_ext2; /* FPM External Requests Config2 0x7c */ + u32 fmfp_drd[16]; /* FPM Data_Ram Data 0-15 0x80 - 0xbf */ + u32 fmfp_dra; /* FPM Data Ram Access 0xc0 */ + u32 fm_ip_rev_1; /* FM IP Block Revision 1 0xc4 */ + u32 fm_ip_rev_2; /* FM IP Block Revision 2 0xc8 */ + u32 fm_rstc; /* FM Reset Command 0xcc */ + u32 fm_cld; /* FM Classifier Debug 0xd0 */ + u32 fm_npi; /* FM Normal Pending Interrupts 0xd4 */ + u32 fmfp_exte; /* FPM External Requests Enable 0xd8 */ + u32 fmfp_ee; /* FPM Event&Mask 0xdc */ + u32 fmfp_cev[4]; /* FPM CPU Event 1-4 0xe0-0xef */ + u32 res00f0[4]; /* res 0xf0-0xff */ + u32 fmfp_ps[50]; /* FPM Port Status 0x100-0x1c7 */ + u32 res01c8[14]; /* res 0x1c8-0x1ff */ + u32 fmfp_clfabc; /* FPM CLFABC 0x200 */ + u32 fmfp_clfcc; /* FPM CLFCC 0x204 */ + u32 fmfp_clfaval; /* FPM CLFAVAL 0x208 */ + u32 fmfp_clfbval; /* FPM CLFBVAL 0x20c */ + u32 fmfp_clfcval; /* FPM CLFCVAL 0x210 */ + u32 fmfp_clfamsk; /* FPM CLFAMSK 0x214 */ + u32 fmfp_clfbmsk; /* FPM CLFBMSK 0x218 */ + u32 fmfp_clfcmsk; /* FPM CLFCMSK 0x21c */ + u32 fmfp_clfamc; /* FPM CLFAMC 0x220 */ + u32 fmfp_clfbmc; /* FPM CLFBMC 0x224 */ + u32 fmfp_clfcmc; /* FPM CLFCMC 0x228 */ + u32 fmfp_decceh; /* FPM DECCEH 0x22c */ + u32 res0230[116]; /* res 0x230 - 0x3ff */ + u32 fmfp_ts[128]; /* 0x400: FPM Task Status 0x400 - 0x5ff */ + u32 res0600[0x400 - 384]; +}; + +struct fman_bmi_regs { + u32 fmbm_init; /* BMI Initialization 0x00 */ + u32 fmbm_cfg1; /* BMI Configuration 1 0x04 */ + u32 fmbm_cfg2; /* BMI Configuration 2 0x08 */ + u32 res000c[5]; /* 0x0c - 0x1f */ + u32 fmbm_ievr; /* Interrupt Event Register 0x20 */ + u32 fmbm_ier; /* Interrupt Enable Register 0x24 */ + u32 fmbm_ifr; /* Interrupt Force Register 0x28 */ + u32 res002c[5]; /* 0x2c - 0x3f */ + u32 fmbm_arb[8]; /* BMI Arbitration 0x40 - 0x5f */ + u32 res0060[12]; /* 0x60 - 0x8f */ + u32 fmbm_dtc[3]; /* Debug Trap Counter 0x90 - 0x9b */ + u32 res009c; /* 0x9c */ + u32 fmbm_dcv[3][4]; /* Debug Compare val 0xa0-0xcf */ + u32 fmbm_dcm[3][4]; /* Debug Compare Mask 0xd0-0xff */ + u32 fmbm_gde; /* BMI Global Debug Enable 0x100 */ + u32 fmbm_pp[63]; /* BMI Port Parameters 0x104 - 0x1ff */ + u32 res0200; /* 0x200 */ + u32 fmbm_pfs[63]; /* BMI Port FIFO Size 0x204 - 0x2ff */ + u32 res0300; /* 0x300 */ + u32 fmbm_spliodn[63]; /* Port Partition ID 0x304 - 0x3ff */ +}; + +struct fman_qmi_regs { + u32 fmqm_gc; /* General Configuration Register 0x00 */ + u32 res0004; /* 0x04 */ + u32 fmqm_eie; /* Error Interrupt Event Register 0x08 */ + u32 fmqm_eien; /* Error Interrupt Enable Register 0x0c */ + u32 fmqm_eif; /* Error Interrupt Force Register 0x10 */ + u32 fmqm_ie; /* Interrupt Event Register 0x14 */ + u32 fmqm_ien; /* Interrupt Enable Register 0x18 */ + u32 fmqm_if; /* Interrupt Force Register 0x1c */ + u32 fmqm_gs; /* Global Status Register 0x20 */ + u32 fmqm_ts; /* Task Status Register 0x24 */ + u32 fmqm_etfc; /* Enqueue Total Frame Counter 0x28 */ + u32 fmqm_dtfc; /* Dequeue Total Frame Counter 0x2c */ + u32 fmqm_dc0; /* Dequeue Counter 0 0x30 */ + u32 fmqm_dc1; /* Dequeue Counter 1 0x34 */ + u32 fmqm_dc2; /* Dequeue Counter 2 0x38 */ + u32 fmqm_dc3; /* Dequeue Counter 3 0x3c */ + u32 fmqm_dfdc; /* Dequeue FQID from Default Counter 0x40 */ + u32 fmqm_dfcc; /* Dequeue FQID from Context Counter 0x44 */ + u32 fmqm_dffc; /* Dequeue FQID from FD Counter 0x48 */ + u32 fmqm_dcc; /* Dequeue Confirm Counter 0x4c */ + u32 res0050[7]; /* 0x50 - 0x6b */ + u32 fmqm_tapc; /* Tnum Aging Period Control 0x6c */ + u32 fmqm_dmcvc; /* Dequeue MAC Command Valid Counter 0x70 */ + u32 fmqm_difdcc; /* Dequeue Invalid FD Command Counter 0x74 */ + u32 fmqm_da1v; /* Dequeue A1 Valid Counter 0x78 */ + u32 res007c; /* 0x7c */ + u32 fmqm_dtc; /* 0x80 Debug Trap Counter 0x80 */ + u32 fmqm_efddd; /* 0x84 Enqueue Frame desc Dynamic dbg 0x84 */ + u32 res0088[2]; /* 0x88 - 0x8f */ + struct { + u32 fmqm_dtcfg1; /* 0x90 dbg trap cfg 1 Register 0x00 */ + u32 fmqm_dtval1; /* Debug Trap Value 1 Register 0x04 */ + u32 fmqm_dtm1; /* Debug Trap Mask 1 Register 0x08 */ + u32 fmqm_dtc1; /* Debug Trap Counter 1 Register 0x0c */ + u32 fmqm_dtcfg2; /* dbg Trap cfg 2 Register 0x10 */ + u32 fmqm_dtval2; /* Debug Trap Value 2 Register 0x14 */ + u32 fmqm_dtm2; /* Debug Trap Mask 2 Register 0x18 */ + u32 res001c; /* 0x1c */ + } dbg_traps[3]; /* 0x90 - 0xef */ + u8 res00f0[0x400 - 0xf0]; /* 0xf0 - 0x3ff */ +}; + +struct fman_dma_regs { + u32 fmdmsr; /* FM DMA status register 0x00 */ + u32 fmdmmr; /* FM DMA mode register 0x04 */ + u32 fmdmtr; /* FM DMA bus threshold register 0x08 */ + u32 fmdmhy; /* FM DMA bus hysteresis register 0x0c */ + u32 fmdmsetr; /* FM DMA SOS emergency Threshold Register 0x10 */ + u32 fmdmtah; /* FM DMA transfer bus address high reg 0x14 */ + u32 fmdmtal; /* FM DMA transfer bus address low reg 0x18 */ + u32 fmdmtcid; /* FM DMA transfer bus communication ID reg 0x1c */ + u32 fmdmra; /* FM DMA bus internal ram address register 0x20 */ + u32 fmdmrd; /* FM DMA bus internal ram data register 0x24 */ + u32 fmdmwcr; /* FM DMA CAM watchdog counter value 0x28 */ + u32 fmdmebcr; /* FM DMA CAM base in MURAM register 0x2c */ + u32 fmdmccqdr; /* FM DMA CAM and CMD Queue Debug reg 0x30 */ + u32 fmdmccqvr1; /* FM DMA CAM and CMD Queue Value reg #1 0x34 */ + u32 fmdmccqvr2; /* FM DMA CAM and CMD Queue Value reg #2 0x38 */ + u32 fmdmcqvr3; /* FM DMA CMD Queue Value register #3 0x3c */ + u32 fmdmcqvr4; /* FM DMA CMD Queue Value register #4 0x40 */ + u32 fmdmcqvr5; /* FM DMA CMD Queue Value register #5 0x44 */ + u32 fmdmsefrc; /* FM DMA Semaphore Entry Full Reject Cntr 0x48 */ + u32 fmdmsqfrc; /* FM DMA Semaphore Queue Full Reject Cntr 0x4c */ + u32 fmdmssrc; /* FM DMA Semaphore SYNC Reject Counter 0x50 */ + u32 fmdmdcr; /* FM DMA Debug Counter 0x54 */ + u32 fmdmemsr; /* FM DMA Emergency Smoother Register 0x58 */ + u32 res005c; /* 0x5c */ + u32 fmdmplr[FMAN_LIODN_TBL / 2]; /* DMA LIODN regs 0x60-0xdf */ + u32 res00e0[0x400 - 56]; +}; + +/* Structure that holds current FMan state. + * Used for saving run time information. + */ +struct fman_state_struct { + u8 fm_id; + u16 fm_clk_freq; + struct fman_rev_info rev_info; + bool enabled_time_stamp; + u8 count1_micro_bit; + u8 total_num_of_tasks; + u8 accumulated_num_of_tasks; + u32 accumulated_fifo_size; + u8 accumulated_num_of_open_dmas; + u8 accumulated_num_of_deq_tnums; + u32 exceptions; + u32 extra_fifo_pool_size; + u8 extra_tasks_pool_size; + u8 extra_open_dmas_pool_size; + u16 port_mfl[MAX_NUM_OF_MACS]; + u16 mac_mfl[MAX_NUM_OF_MACS]; + + /* SOC specific */ + u32 fm_iram_size; + /* DMA */ + u32 dma_thresh_max_commq; + u32 dma_thresh_max_buf; + u32 max_num_of_open_dmas; + /* QMI */ + u32 qmi_max_num_of_tnums; + u32 qmi_def_tnums_thresh; + /* BMI */ + u32 bmi_max_num_of_tasks; + u32 bmi_max_fifo_size; + /* General */ + u32 fm_port_num_of_cg; + u32 num_of_rx_ports; + u32 total_fifo_size; + + u32 qman_channel_base; + u32 num_of_qman_channels; + + struct resource *res; +}; + +/* Structure that holds FMan initial configuration */ +struct fman_cfg { + u8 disp_limit_tsh; + u8 prs_disp_tsh; + u8 plcr_disp_tsh; + u8 kg_disp_tsh; + u8 bmi_disp_tsh; + u8 qmi_enq_disp_tsh; + u8 qmi_deq_disp_tsh; + u8 fm_ctl1_disp_tsh; + u8 fm_ctl2_disp_tsh; + int dma_cache_override; + enum fman_dma_aid_mode dma_aid_mode; + u32 dma_axi_dbg_num_of_beats; + u32 dma_cam_num_of_entries; + u32 dma_watchdog; + u8 dma_comm_qtsh_asrt_emer; + u32 dma_write_buf_tsh_asrt_emer; + u32 dma_read_buf_tsh_asrt_emer; + u8 dma_comm_qtsh_clr_emer; + u32 dma_write_buf_tsh_clr_emer; + u32 dma_read_buf_tsh_clr_emer; + u32 dma_sos_emergency; + int dma_dbg_cnt_mode; + int catastrophic_err; + int dma_err; + u32 exceptions; + u16 clk_freq; + u32 cam_base_addr; + u32 fifo_base_addr; + u32 total_fifo_size; + u32 total_num_of_tasks; + u32 qmi_def_tnums_thresh; +}; + +/* Structure that holds information received from device tree */ +struct fman_dts_params { + void __iomem *base_addr; /* FMan virtual address */ + struct resource *res; /* FMan memory resource */ + u8 id; /* FMan ID */ + + int err_irq; /* FMan Error IRQ */ + + u16 clk_freq; /* FMan clock freq (In Mhz) */ + + u32 qman_channel_base; /* QMan channels base */ + u32 num_of_qman_channels; /* Number of QMan channels */ + + struct resource muram_res; /* MURAM resource */ +}; + +/** fman_exceptions_cb + * fman - Pointer to FMan + * exception - The exception. + * + * Exceptions user callback routine, will be called upon an exception + * passing the exception identification. + * + * Return: irq status + */ +typedef irqreturn_t (fman_exceptions_cb)(struct fman *fman, + enum fman_exceptions exception); + +/** fman_bus_error_cb + * fman - Pointer to FMan + * port_id - Port id + * addr - Address that caused the error + * tnum - Owner of error + * liodn - Logical IO device number + * + * Bus error user callback routine, will be called upon bus error, + * passing parameters describing the errors and the owner. + * + * Return: IRQ status + */ +typedef irqreturn_t (fman_bus_error_cb)(struct fman *fman, u8 port_id, + u64 addr, u8 tnum, u16 liodn); + +struct fman { + struct device *dev; + void __iomem *base_addr; + struct fman_intr_src intr_mng[FMAN_EV_CNT]; + + struct fman_fpm_regs __iomem *fpm_regs; + struct fman_bmi_regs __iomem *bmi_regs; + struct fman_qmi_regs __iomem *qmi_regs; + struct fman_dma_regs __iomem *dma_regs; + fman_exceptions_cb *exception_cb; + fman_bus_error_cb *bus_error_cb; + /* Spinlock for FMan use */ + spinlock_t spinlock; + struct fman_state_struct *state; + + struct fman_cfg *cfg; + struct muram_info *muram; + /* cam section in muram */ + int cam_offset; + size_t cam_size; + /* Fifo in MURAM */ + int fifo_offset; + size_t fifo_size; + + u32 liodn_base[64]; + u32 liodn_offset[64]; + + struct fman_dts_params dts_params; +}; + +static irqreturn_t fman_exceptions(struct fman *fman, + enum fman_exceptions exception) +{ + dev_dbg(fman->dev, "%s: FMan[%d] exception %d\n", + __func__, fman->state->fm_id, exception); + + return IRQ_HANDLED; +} + +static irqreturn_t fman_bus_error(struct fman *fman, u8 __maybe_unused port_id, + u64 __maybe_unused addr, + u8 __maybe_unused tnum, + u16 __maybe_unused liodn) +{ + dev_dbg(fman->dev, "%s: FMan[%d] bus error: port_id[%d]\n", + __func__, fman->state->fm_id, port_id); + + return IRQ_HANDLED; +} + +static inline irqreturn_t call_mac_isr(struct fman *fman, u8 id) +{ + if (fman->intr_mng[id].isr_cb) { + fman->intr_mng[id].isr_cb(fman->intr_mng[id].src_handle); + + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static inline u8 hw_port_id_to_sw_port_id(u8 major, u8 hw_port_id) +{ + u8 sw_port_id = 0; + + if (hw_port_id >= BASE_TX_PORTID) + sw_port_id = hw_port_id - BASE_TX_PORTID; + else if (hw_port_id >= BASE_RX_PORTID) + sw_port_id = hw_port_id - BASE_RX_PORTID; + else + sw_port_id = 0; + + return sw_port_id; +} + +static void set_port_order_restoration(struct fman_fpm_regs __iomem *fpm_rg, + u8 port_id) +{ + u32 tmp = 0; + + tmp = port_id << FPM_PORT_FM_CTL_PORTID_SHIFT; + + tmp |= FPM_PRT_FM_CTL2 | FPM_PRT_FM_CTL1; + + /* order restoration */ + if (port_id % 2) + tmp |= FPM_PRT_FM_CTL1 << FPM_PRC_ORA_FM_CTL_SEL_SHIFT; + else + tmp |= FPM_PRT_FM_CTL2 << FPM_PRC_ORA_FM_CTL_SEL_SHIFT; + + iowrite32be(tmp, &fpm_rg->fmfp_prc); +} + +static void set_port_liodn(struct fman *fman, u8 port_id, + u32 liodn_base, u32 liodn_ofst) +{ + u32 tmp; + + /* set LIODN base for this port */ + tmp = ioread32be(&fman->dma_regs->fmdmplr[port_id / 2]); + if (port_id % 2) { + tmp &= ~DMA_LIODN_BASE_MASK; + tmp |= liodn_base; + } else { + tmp &= ~(DMA_LIODN_BASE_MASK << DMA_LIODN_SHIFT); + tmp |= liodn_base << DMA_LIODN_SHIFT; + } + iowrite32be(tmp, &fman->dma_regs->fmdmplr[port_id / 2]); + iowrite32be(liodn_ofst, &fman->bmi_regs->fmbm_spliodn[port_id - 1]); +} + +static void enable_rams_ecc(struct fman_fpm_regs __iomem *fpm_rg) +{ + u32 tmp; + + tmp = ioread32be(&fpm_rg->fm_rcr); + if (tmp & FPM_RAM_RAMS_ECC_EN_SRC_SEL) + iowrite32be(tmp | FPM_RAM_IRAM_ECC_EN, &fpm_rg->fm_rcr); + else + iowrite32be(tmp | FPM_RAM_RAMS_ECC_EN | + FPM_RAM_IRAM_ECC_EN, &fpm_rg->fm_rcr); +} + +static void disable_rams_ecc(struct fman_fpm_regs __iomem *fpm_rg) +{ + u32 tmp; + + tmp = ioread32be(&fpm_rg->fm_rcr); + if (tmp & FPM_RAM_RAMS_ECC_EN_SRC_SEL) + iowrite32be(tmp & ~FPM_RAM_IRAM_ECC_EN, &fpm_rg->fm_rcr); + else + iowrite32be(tmp & ~(FPM_RAM_RAMS_ECC_EN | FPM_RAM_IRAM_ECC_EN), + &fpm_rg->fm_rcr); +} + +static void fman_defconfig(struct fman_cfg *cfg) +{ + memset(cfg, 0, sizeof(struct fman_cfg)); + + cfg->catastrophic_err = DEFAULT_CATASTROPHIC_ERR; + cfg->dma_err = DEFAULT_DMA_ERR; + cfg->dma_aid_mode = DEFAULT_AID_MODE; + cfg->dma_comm_qtsh_clr_emer = DEFAULT_DMA_COMM_Q_LOW; + cfg->dma_comm_qtsh_asrt_emer = DEFAULT_DMA_COMM_Q_HIGH; + cfg->dma_cache_override = DEFAULT_CACHE_OVERRIDE; + cfg->dma_cam_num_of_entries = DEFAULT_DMA_CAM_NUM_OF_ENTRIES; + cfg->dma_dbg_cnt_mode = DEFAULT_DMA_DBG_CNT_MODE; + cfg->dma_sos_emergency = DEFAULT_DMA_SOS_EMERGENCY; + cfg->dma_watchdog = DEFAULT_DMA_WATCHDOG; + cfg->disp_limit_tsh = DEFAULT_DISP_LIMIT; + cfg->prs_disp_tsh = DEFAULT_PRS_DISP_TH; + cfg->plcr_disp_tsh = DEFAULT_PLCR_DISP_TH; + cfg->kg_disp_tsh = DEFAULT_KG_DISP_TH; + cfg->bmi_disp_tsh = DEFAULT_BMI_DISP_TH; + cfg->qmi_enq_disp_tsh = DEFAULT_QMI_ENQ_DISP_TH; + cfg->qmi_deq_disp_tsh = DEFAULT_QMI_DEQ_DISP_TH; + cfg->fm_ctl1_disp_tsh = DEFAULT_FM_CTL1_DISP_TH; + cfg->fm_ctl2_disp_tsh = DEFAULT_FM_CTL2_DISP_TH; +} + +static int dma_init(struct fman *fman) +{ + struct fman_dma_regs __iomem *dma_rg = fman->dma_regs; + struct fman_cfg *cfg = fman->cfg; + u32 tmp_reg; + + /* Init DMA Registers */ + + /* clear status reg events */ + tmp_reg = (DMA_STATUS_BUS_ERR | DMA_STATUS_READ_ECC | + DMA_STATUS_SYSTEM_WRITE_ECC | DMA_STATUS_FM_WRITE_ECC); + iowrite32be(ioread32be(&dma_rg->fmdmsr) | tmp_reg, &dma_rg->fmdmsr); + + /* configure mode register */ + tmp_reg = 0; + tmp_reg |= cfg->dma_cache_override << DMA_MODE_CACHE_OR_SHIFT; + if (cfg->exceptions & EX_DMA_BUS_ERROR) + tmp_reg |= DMA_MODE_BER; + if ((cfg->exceptions & EX_DMA_SYSTEM_WRITE_ECC) | + (cfg->exceptions & EX_DMA_READ_ECC) | + (cfg->exceptions & EX_DMA_FM_WRITE_ECC)) + tmp_reg |= DMA_MODE_ECC; + if (cfg->dma_axi_dbg_num_of_beats) + tmp_reg |= (DMA_MODE_AXI_DBG_MASK & + ((cfg->dma_axi_dbg_num_of_beats - 1) + << DMA_MODE_AXI_DBG_SHIFT)); + + tmp_reg |= (((cfg->dma_cam_num_of_entries / DMA_CAM_UNITS) - 1) & + DMA_MODE_CEN_MASK) << DMA_MODE_CEN_SHIFT; + tmp_reg |= DMA_MODE_SECURE_PROT; + tmp_reg |= cfg->dma_dbg_cnt_mode << DMA_MODE_DBG_SHIFT; + tmp_reg |= cfg->dma_aid_mode << DMA_MODE_AID_MODE_SHIFT; + + iowrite32be(tmp_reg, &dma_rg->fmdmmr); + + /* configure thresholds register */ + tmp_reg = ((u32)cfg->dma_comm_qtsh_asrt_emer << + DMA_THRESH_COMMQ_SHIFT); + tmp_reg |= (cfg->dma_read_buf_tsh_asrt_emer & + DMA_THRESH_READ_INT_BUF_MASK) << DMA_THRESH_READ_INT_BUF_SHIFT; + tmp_reg |= cfg->dma_write_buf_tsh_asrt_emer & + DMA_THRESH_WRITE_INT_BUF_MASK; + + iowrite32be(tmp_reg, &dma_rg->fmdmtr); + + /* configure hysteresis register */ + tmp_reg = ((u32)cfg->dma_comm_qtsh_clr_emer << + DMA_THRESH_COMMQ_SHIFT); + tmp_reg |= (cfg->dma_read_buf_tsh_clr_emer & + DMA_THRESH_READ_INT_BUF_MASK) << DMA_THRESH_READ_INT_BUF_SHIFT; + tmp_reg |= cfg->dma_write_buf_tsh_clr_emer & + DMA_THRESH_WRITE_INT_BUF_MASK; + + iowrite32be(tmp_reg, &dma_rg->fmdmhy); + + /* configure emergency threshold */ + iowrite32be(cfg->dma_sos_emergency, &dma_rg->fmdmsetr); + + /* configure Watchdog */ + iowrite32be((cfg->dma_watchdog * cfg->clk_freq), &dma_rg->fmdmwcr); + + iowrite32be(cfg->cam_base_addr, &dma_rg->fmdmebcr); + + /* Allocate MURAM for CAM */ + fman->cam_size = + (u32)(fman->cfg->dma_cam_num_of_entries * DMA_CAM_SIZEOF_ENTRY); + fman->cam_offset = fman_muram_alloc(fman->muram, fman->cam_size); + if (IS_ERR_VALUE(fman->cam_offset)) { + dev_err(fman->dev, "%s: MURAM alloc for DMA CAM failed\n", + __func__); + return -ENOMEM; + } + + if (fman->state->rev_info.major == 2) { + u32 __iomem *cam_base_addr; + + fman_muram_free_mem(fman->muram, fman->cam_offset, + fman->cam_size); + + fman->cam_size = fman->cfg->dma_cam_num_of_entries * 72 + 128; + fman->cam_offset = fman_muram_alloc(fman->muram, + fman->cam_size); + if (IS_ERR_VALUE(fman->cam_offset)) { + dev_err(fman->dev, "%s: MURAM alloc for DMA CAM failed\n", + __func__); + return -ENOMEM; + } + + if (fman->cfg->dma_cam_num_of_entries % 8 || + fman->cfg->dma_cam_num_of_entries > 32) { + dev_err(fman->dev, "%s: wrong dma_cam_num_of_entries\n", + __func__); + return -EINVAL; + } + + cam_base_addr = (u32 __iomem *) + fman_muram_offset_to_vbase(fman->muram, + fman->cam_offset); + iowrite32be(~((1 << + (32 - fman->cfg->dma_cam_num_of_entries)) - 1), + cam_base_addr); + } + + fman->cfg->cam_base_addr = fman->cam_offset; + + return 0; +} + +static void fpm_init(struct fman_fpm_regs __iomem *fpm_rg, struct fman_cfg *cfg) +{ + u32 tmp_reg; + int i; + + /* Init FPM Registers */ + + tmp_reg = (u32)(cfg->disp_limit_tsh << FPM_DISP_LIMIT_SHIFT); + iowrite32be(tmp_reg, &fpm_rg->fmfp_mxd); + + tmp_reg = (((u32)cfg->prs_disp_tsh << FPM_THR1_PRS_SHIFT) | + ((u32)cfg->kg_disp_tsh << FPM_THR1_KG_SHIFT) | + ((u32)cfg->plcr_disp_tsh << FPM_THR1_PLCR_SHIFT) | + ((u32)cfg->bmi_disp_tsh << FPM_THR1_BMI_SHIFT)); + iowrite32be(tmp_reg, &fpm_rg->fmfp_dist1); + + tmp_reg = + (((u32)cfg->qmi_enq_disp_tsh << FPM_THR2_QMI_ENQ_SHIFT) | + ((u32)cfg->qmi_deq_disp_tsh << FPM_THR2_QMI_DEQ_SHIFT) | + ((u32)cfg->fm_ctl1_disp_tsh << FPM_THR2_FM_CTL1_SHIFT) | + ((u32)cfg->fm_ctl2_disp_tsh << FPM_THR2_FM_CTL2_SHIFT)); + iowrite32be(tmp_reg, &fpm_rg->fmfp_dist2); + + /* define exceptions and error behavior */ + tmp_reg = 0; + /* Clear events */ + tmp_reg |= (FPM_EV_MASK_STALL | FPM_EV_MASK_DOUBLE_ECC | + FPM_EV_MASK_SINGLE_ECC); + /* enable interrupts */ + if (cfg->exceptions & EX_FPM_STALL_ON_TASKS) + tmp_reg |= FPM_EV_MASK_STALL_EN; + if (cfg->exceptions & EX_FPM_SINGLE_ECC) + tmp_reg |= FPM_EV_MASK_SINGLE_ECC_EN; + if (cfg->exceptions & EX_FPM_DOUBLE_ECC) + tmp_reg |= FPM_EV_MASK_DOUBLE_ECC_EN; + tmp_reg |= (cfg->catastrophic_err << FPM_EV_MASK_CAT_ERR_SHIFT); + tmp_reg |= (cfg->dma_err << FPM_EV_MASK_DMA_ERR_SHIFT); + /* FMan is not halted upon external halt activation */ + tmp_reg |= FPM_EV_MASK_EXTERNAL_HALT; + /* Man is not halted upon Unrecoverable ECC error behavior */ + tmp_reg |= FPM_EV_MASK_ECC_ERR_HALT; + iowrite32be(tmp_reg, &fpm_rg->fmfp_ee); + + /* clear all fmCtls event registers */ + for (i = 0; i < FM_NUM_OF_FMAN_CTRL_EVENT_REGS; i++) + iowrite32be(0xFFFFFFFF, &fpm_rg->fmfp_cev[i]); + + /* RAM ECC - enable and clear events */ + /* first we need to clear all parser memory, + * as it is uninitialized and may cause ECC errors + */ + /* event bits */ + tmp_reg = (FPM_RAM_MURAM_ECC | FPM_RAM_IRAM_ECC); + + iowrite32be(tmp_reg, &fpm_rg->fm_rcr); + + tmp_reg = 0; + if (cfg->exceptions & EX_IRAM_ECC) { + tmp_reg |= FPM_IRAM_ECC_ERR_EX_EN; + enable_rams_ecc(fpm_rg); + } + if (cfg->exceptions & EX_MURAM_ECC) { + tmp_reg |= FPM_MURAM_ECC_ERR_EX_EN; + enable_rams_ecc(fpm_rg); + } + iowrite32be(tmp_reg, &fpm_rg->fm_rie); +} + +static void bmi_init(struct fman_bmi_regs __iomem *bmi_rg, + struct fman_cfg *cfg) +{ + u32 tmp_reg; + + /* Init BMI Registers */ + + /* define common resources */ + tmp_reg = cfg->fifo_base_addr; + tmp_reg = tmp_reg / BMI_FIFO_ALIGN; + + tmp_reg |= ((cfg->total_fifo_size / FMAN_BMI_FIFO_UNITS - 1) << + BMI_CFG1_FIFO_SIZE_SHIFT); + iowrite32be(tmp_reg, &bmi_rg->fmbm_cfg1); + + tmp_reg = ((cfg->total_num_of_tasks - 1) & BMI_CFG2_TASKS_MASK) << + BMI_CFG2_TASKS_SHIFT; + /* num of DMA's will be dynamically updated when each port is set */ + iowrite32be(tmp_reg, &bmi_rg->fmbm_cfg2); + + /* define unmaskable exceptions, enable and clear events */ + tmp_reg = 0; + iowrite32be(BMI_ERR_INTR_EN_LIST_RAM_ECC | + BMI_ERR_INTR_EN_STORAGE_PROFILE_ECC | + BMI_ERR_INTR_EN_STATISTICS_RAM_ECC | + BMI_ERR_INTR_EN_DISPATCH_RAM_ECC, &bmi_rg->fmbm_ievr); + + if (cfg->exceptions & EX_BMI_LIST_RAM_ECC) + tmp_reg |= BMI_ERR_INTR_EN_LIST_RAM_ECC; + if (cfg->exceptions & EX_BMI_STORAGE_PROFILE_ECC) + tmp_reg |= BMI_ERR_INTR_EN_STORAGE_PROFILE_ECC; + if (cfg->exceptions & EX_BMI_STATISTICS_RAM_ECC) + tmp_reg |= BMI_ERR_INTR_EN_STATISTICS_RAM_ECC; + if (cfg->exceptions & EX_BMI_DISPATCH_RAM_ECC) + tmp_reg |= BMI_ERR_INTR_EN_DISPATCH_RAM_ECC; + iowrite32be(tmp_reg, &bmi_rg->fmbm_ier); +} + +static void qmi_init(struct fman_qmi_regs __iomem *qmi_rg, + struct fman_cfg *cfg) +{ + u32 tmp_reg; + + /* Init QMI Registers */ + + /* Clear error interrupt events */ + + iowrite32be(QMI_ERR_INTR_EN_DOUBLE_ECC | QMI_ERR_INTR_EN_DEQ_FROM_DEF, + &qmi_rg->fmqm_eie); + tmp_reg = 0; + if (cfg->exceptions & EX_QMI_DEQ_FROM_UNKNOWN_PORTID) + tmp_reg |= QMI_ERR_INTR_EN_DEQ_FROM_DEF; + if (cfg->exceptions & EX_QMI_DOUBLE_ECC) + tmp_reg |= QMI_ERR_INTR_EN_DOUBLE_ECC; + /* enable events */ + iowrite32be(tmp_reg, &qmi_rg->fmqm_eien); + + tmp_reg = 0; + /* Clear interrupt events */ + iowrite32be(QMI_INTR_EN_SINGLE_ECC, &qmi_rg->fmqm_ie); + if (cfg->exceptions & EX_QMI_SINGLE_ECC) + tmp_reg |= QMI_INTR_EN_SINGLE_ECC; + /* enable events */ + iowrite32be(tmp_reg, &qmi_rg->fmqm_ien); +} + +static int enable(struct fman *fman, struct fman_cfg *cfg) +{ + u32 cfg_reg = 0; + + /* Enable all modules */ + + /* clear&enable global counters - calculate reg and save for later, + * because it's the same reg for QMI enable + */ + cfg_reg = QMI_CFG_EN_COUNTERS; + + /* Set enqueue and dequeue thresholds */ + cfg_reg |= (cfg->qmi_def_tnums_thresh << 8) | cfg->qmi_def_tnums_thresh; + + iowrite32be(BMI_INIT_START, &fman->bmi_regs->fmbm_init); + iowrite32be(cfg_reg | QMI_CFG_ENQ_EN | QMI_CFG_DEQ_EN, + &fman->qmi_regs->fmqm_gc); + + return 0; +} + +static int set_exception(struct fman *fman, + enum fman_exceptions exception, bool enable) +{ + u32 tmp; + + switch (exception) { + case FMAN_EX_DMA_BUS_ERROR: + tmp = ioread32be(&fman->dma_regs->fmdmmr); + if (enable) + tmp |= DMA_MODE_BER; + else + tmp &= ~DMA_MODE_BER; + /* disable bus error */ + iowrite32be(tmp, &fman->dma_regs->fmdmmr); + break; + case FMAN_EX_DMA_READ_ECC: + case FMAN_EX_DMA_SYSTEM_WRITE_ECC: + case FMAN_EX_DMA_FM_WRITE_ECC: + tmp = ioread32be(&fman->dma_regs->fmdmmr); + if (enable) + tmp |= DMA_MODE_ECC; + else + tmp &= ~DMA_MODE_ECC; + iowrite32be(tmp, &fman->dma_regs->fmdmmr); + break; + case FMAN_EX_FPM_STALL_ON_TASKS: + tmp = ioread32be(&fman->fpm_regs->fmfp_ee); + if (enable) + tmp |= FPM_EV_MASK_STALL_EN; + else + tmp &= ~FPM_EV_MASK_STALL_EN; + iowrite32be(tmp, &fman->fpm_regs->fmfp_ee); + break; + case FMAN_EX_FPM_SINGLE_ECC: + tmp = ioread32be(&fman->fpm_regs->fmfp_ee); + if (enable) + tmp |= FPM_EV_MASK_SINGLE_ECC_EN; + else + tmp &= ~FPM_EV_MASK_SINGLE_ECC_EN; + iowrite32be(tmp, &fman->fpm_regs->fmfp_ee); + break; + case FMAN_EX_FPM_DOUBLE_ECC: + tmp = ioread32be(&fman->fpm_regs->fmfp_ee); + if (enable) + tmp |= FPM_EV_MASK_DOUBLE_ECC_EN; + else + tmp &= ~FPM_EV_MASK_DOUBLE_ECC_EN; + iowrite32be(tmp, &fman->fpm_regs->fmfp_ee); + break; + case FMAN_EX_QMI_SINGLE_ECC: + tmp = ioread32be(&fman->qmi_regs->fmqm_ien); + if (enable) + tmp |= QMI_INTR_EN_SINGLE_ECC; + else + tmp &= ~QMI_INTR_EN_SINGLE_ECC; + iowrite32be(tmp, &fman->qmi_regs->fmqm_ien); + break; + case FMAN_EX_QMI_DOUBLE_ECC: + tmp = ioread32be(&fman->qmi_regs->fmqm_eien); + if (enable) + tmp |= QMI_ERR_INTR_EN_DOUBLE_ECC; + else + tmp &= ~QMI_ERR_INTR_EN_DOUBLE_ECC; + iowrite32be(tmp, &fman->qmi_regs->fmqm_eien); + break; + case FMAN_EX_QMI_DEQ_FROM_UNKNOWN_PORTID: + tmp = ioread32be(&fman->qmi_regs->fmqm_eien); + if (enable) + tmp |= QMI_ERR_INTR_EN_DEQ_FROM_DEF; + else + tmp &= ~QMI_ERR_INTR_EN_DEQ_FROM_DEF; + iowrite32be(tmp, &fman->qmi_regs->fmqm_eien); + break; + case FMAN_EX_BMI_LIST_RAM_ECC: + tmp = ioread32be(&fman->bmi_regs->fmbm_ier); + if (enable) + tmp |= BMI_ERR_INTR_EN_LIST_RAM_ECC; + else + tmp &= ~BMI_ERR_INTR_EN_LIST_RAM_ECC; + iowrite32be(tmp, &fman->bmi_regs->fmbm_ier); + break; + case FMAN_EX_BMI_STORAGE_PROFILE_ECC: + tmp = ioread32be(&fman->bmi_regs->fmbm_ier); + if (enable) + tmp |= BMI_ERR_INTR_EN_STORAGE_PROFILE_ECC; + else + tmp &= ~BMI_ERR_INTR_EN_STORAGE_PROFILE_ECC; + iowrite32be(tmp, &fman->bmi_regs->fmbm_ier); + break; + case FMAN_EX_BMI_STATISTICS_RAM_ECC: + tmp = ioread32be(&fman->bmi_regs->fmbm_ier); + if (enable) + tmp |= BMI_ERR_INTR_EN_STATISTICS_RAM_ECC; + else + tmp &= ~BMI_ERR_INTR_EN_STATISTICS_RAM_ECC; + iowrite32be(tmp, &fman->bmi_regs->fmbm_ier); + break; + case FMAN_EX_BMI_DISPATCH_RAM_ECC: + tmp = ioread32be(&fman->bmi_regs->fmbm_ier); + if (enable) + tmp |= BMI_ERR_INTR_EN_DISPATCH_RAM_ECC; + else + tmp &= ~BMI_ERR_INTR_EN_DISPATCH_RAM_ECC; + iowrite32be(tmp, &fman->bmi_regs->fmbm_ier); + break; + case FMAN_EX_IRAM_ECC: + tmp = ioread32be(&fman->fpm_regs->fm_rie); + if (enable) { + /* enable ECC if not enabled */ + enable_rams_ecc(fman->fpm_regs); + /* enable ECC interrupts */ + tmp |= FPM_IRAM_ECC_ERR_EX_EN; + } else { + /* ECC mechanism may be disabled, + * depending on driver status + */ + disable_rams_ecc(fman->fpm_regs); + tmp &= ~FPM_IRAM_ECC_ERR_EX_EN; + } + iowrite32be(tmp, &fman->fpm_regs->fm_rie); + break; + case FMAN_EX_MURAM_ECC: + tmp = ioread32be(&fman->fpm_regs->fm_rie); + if (enable) { + /* enable ECC if not enabled */ + enable_rams_ecc(fman->fpm_regs); + /* enable ECC interrupts */ + tmp |= FPM_MURAM_ECC_ERR_EX_EN; + } else { + /* ECC mechanism may be disabled, + * depending on driver status + */ + disable_rams_ecc(fman->fpm_regs); + tmp &= ~FPM_MURAM_ECC_ERR_EX_EN; + } + iowrite32be(tmp, &fman->fpm_regs->fm_rie); + break; + default: + return -EINVAL; + } + return 0; +} + +static void resume(struct fman_fpm_regs __iomem *fpm_rg) +{ + u32 tmp; + + tmp = ioread32be(&fpm_rg->fmfp_ee); + /* clear tmp_reg event bits in order not to clear standing events */ + tmp &= ~(FPM_EV_MASK_DOUBLE_ECC | + FPM_EV_MASK_STALL | FPM_EV_MASK_SINGLE_ECC); + tmp |= FPM_EV_MASK_RELEASE_FM; + + iowrite32be(tmp, &fpm_rg->fmfp_ee); +} + +static int fill_soc_specific_params(struct fman_state_struct *state) +{ + u8 minor = state->rev_info.minor; + /* P4080 - Major 2 + * P2041/P3041/P5020/P5040 - Major 3 + * Tx/Bx - Major 6 + */ + switch (state->rev_info.major) { + case 3: + state->bmi_max_fifo_size = 160 * 1024; + state->fm_iram_size = 64 * 1024; + state->dma_thresh_max_commq = 31; + state->dma_thresh_max_buf = 127; + state->qmi_max_num_of_tnums = 64; + state->qmi_def_tnums_thresh = 48; + state->bmi_max_num_of_tasks = 128; + state->max_num_of_open_dmas = 32; + state->fm_port_num_of_cg = 256; + state->num_of_rx_ports = 6; + state->total_fifo_size = 122 * 1024; + break; + + case 2: + state->bmi_max_fifo_size = 160 * 1024; + state->fm_iram_size = 64 * 1024; + state->dma_thresh_max_commq = 31; + state->dma_thresh_max_buf = 127; + state->qmi_max_num_of_tnums = 64; + state->qmi_def_tnums_thresh = 48; + state->bmi_max_num_of_tasks = 128; + state->max_num_of_open_dmas = 32; + state->fm_port_num_of_cg = 256; + state->num_of_rx_ports = 5; + state->total_fifo_size = 100 * 1024; + break; + + case 6: + state->dma_thresh_max_commq = 83; + state->dma_thresh_max_buf = 127; + state->qmi_max_num_of_tnums = 64; + state->qmi_def_tnums_thresh = 32; + state->fm_port_num_of_cg = 256; + + /* FManV3L */ + if (minor == 1 || minor == 4) { + state->bmi_max_fifo_size = 192 * 1024; + state->bmi_max_num_of_tasks = 64; + state->max_num_of_open_dmas = 32; + state->num_of_rx_ports = 5; + if (minor == 1) + state->fm_iram_size = 32 * 1024; + else + state->fm_iram_size = 64 * 1024; + state->total_fifo_size = 156 * 1024; + } + /* FManV3H */ + else if (minor == 0 || minor == 2 || minor == 3) { + state->bmi_max_fifo_size = 384 * 1024; + state->fm_iram_size = 64 * 1024; + state->bmi_max_num_of_tasks = 128; + state->max_num_of_open_dmas = 84; + state->num_of_rx_ports = 8; + state->total_fifo_size = 295 * 1024; + } else { + pr_err("Unsupported FManv3 version\n"); + return -EINVAL; + } + + break; + default: + pr_err("Unsupported FMan version\n"); + return -EINVAL; + } + + return 0; +} + +static bool is_init_done(struct fman_cfg *cfg) +{ + /* Checks if FMan driver parameters were initialized */ + if (!cfg) + return true; + + return false; +} + +static void free_init_resources(struct fman *fman) +{ + if (fman->cam_offset) + fman_muram_free_mem(fman->muram, fman->cam_offset, + fman->cam_size); + if (fman->fifo_offset) + fman_muram_free_mem(fman->muram, fman->fifo_offset, + fman->fifo_size); +} + +static irqreturn_t bmi_err_event(struct fman *fman) +{ + u32 event, mask, force; + struct fman_bmi_regs __iomem *bmi_rg = fman->bmi_regs; + irqreturn_t ret = IRQ_NONE; + + event = ioread32be(&bmi_rg->fmbm_ievr); + mask = ioread32be(&bmi_rg->fmbm_ier); + event &= mask; + /* clear the forced events */ + force = ioread32be(&bmi_rg->fmbm_ifr); + if (force & event) + iowrite32be(force & ~event, &bmi_rg->fmbm_ifr); + /* clear the acknowledged events */ + iowrite32be(event, &bmi_rg->fmbm_ievr); + + if (event & BMI_ERR_INTR_EN_STORAGE_PROFILE_ECC) + ret = fman->exception_cb(fman, FMAN_EX_BMI_STORAGE_PROFILE_ECC); + if (event & BMI_ERR_INTR_EN_LIST_RAM_ECC) + ret = fman->exception_cb(fman, FMAN_EX_BMI_LIST_RAM_ECC); + if (event & BMI_ERR_INTR_EN_STATISTICS_RAM_ECC) + ret = fman->exception_cb(fman, FMAN_EX_BMI_STATISTICS_RAM_ECC); + if (event & BMI_ERR_INTR_EN_DISPATCH_RAM_ECC) + ret = fman->exception_cb(fman, FMAN_EX_BMI_DISPATCH_RAM_ECC); + + return ret; +} + +static irqreturn_t qmi_err_event(struct fman *fman) +{ + u32 event, mask, force; + struct fman_qmi_regs __iomem *qmi_rg = fman->qmi_regs; + irqreturn_t ret = IRQ_NONE; + + event = ioread32be(&qmi_rg->fmqm_eie); + mask = ioread32be(&qmi_rg->fmqm_eien); + event &= mask; + + /* clear the forced events */ + force = ioread32be(&qmi_rg->fmqm_eif); + if (force & event) + iowrite32be(force & ~event, &qmi_rg->fmqm_eif); + /* clear the acknowledged events */ + iowrite32be(event, &qmi_rg->fmqm_eie); + + if (event & QMI_ERR_INTR_EN_DOUBLE_ECC) + ret = fman->exception_cb(fman, FMAN_EX_QMI_DOUBLE_ECC); + if (event & QMI_ERR_INTR_EN_DEQ_FROM_DEF) + ret = fman->exception_cb(fman, + FMAN_EX_QMI_DEQ_FROM_UNKNOWN_PORTID); + + return ret; +} + +static irqreturn_t dma_err_event(struct fman *fman) +{ + u32 status, mask, com_id; + u8 tnum, port_id, relative_port_id; + u16 liodn; + struct fman_dma_regs __iomem *dma_rg = fman->dma_regs; + irqreturn_t ret = IRQ_NONE; + + status = ioread32be(&dma_rg->fmdmsr); + mask = ioread32be(&dma_rg->fmdmmr); + + /* clear DMA_STATUS_BUS_ERR if mask has no DMA_MODE_BER */ + if ((mask & DMA_MODE_BER) != DMA_MODE_BER) + status &= ~DMA_STATUS_BUS_ERR; + + /* clear relevant bits if mask has no DMA_MODE_ECC */ + if ((mask & DMA_MODE_ECC) != DMA_MODE_ECC) + status &= ~(DMA_STATUS_FM_SPDAT_ECC | + DMA_STATUS_READ_ECC | + DMA_STATUS_SYSTEM_WRITE_ECC | + DMA_STATUS_FM_WRITE_ECC); + + /* clear set events */ + iowrite32be(status, &dma_rg->fmdmsr); + + if (status & DMA_STATUS_BUS_ERR) { + u64 addr; + + addr = (u64)ioread32be(&dma_rg->fmdmtal); + addr |= ((u64)(ioread32be(&dma_rg->fmdmtah)) << 32); + + com_id = ioread32be(&dma_rg->fmdmtcid); + port_id = (u8)(((com_id & DMA_TRANSFER_PORTID_MASK) >> + DMA_TRANSFER_PORTID_SHIFT)); + relative_port_id = + hw_port_id_to_sw_port_id(fman->state->rev_info.major, port_id); + tnum = (u8)((com_id & DMA_TRANSFER_TNUM_MASK) >> + DMA_TRANSFER_TNUM_SHIFT); + liodn = (u16)(com_id & DMA_TRANSFER_LIODN_MASK); + ret = fman->bus_error_cb(fman, relative_port_id, addr, tnum, + liodn); + } + if (status & DMA_STATUS_FM_SPDAT_ECC) + ret = fman->exception_cb(fman, FMAN_EX_DMA_SINGLE_PORT_ECC); + if (status & DMA_STATUS_READ_ECC) + ret = fman->exception_cb(fman, FMAN_EX_DMA_READ_ECC); + if (status & DMA_STATUS_SYSTEM_WRITE_ECC) + ret = fman->exception_cb(fman, FMAN_EX_DMA_SYSTEM_WRITE_ECC); + if (status & DMA_STATUS_FM_WRITE_ECC) + ret = fman->exception_cb(fman, FMAN_EX_DMA_FM_WRITE_ECC); + + return ret; +} + +static irqreturn_t fpm_err_event(struct fman *fman) +{ + u32 event; + struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs; + irqreturn_t ret = IRQ_NONE; + + event = ioread32be(&fpm_rg->fmfp_ee); + /* clear the all occurred events */ + iowrite32be(event, &fpm_rg->fmfp_ee); + + if ((event & FPM_EV_MASK_DOUBLE_ECC) && + (event & FPM_EV_MASK_DOUBLE_ECC_EN)) + ret = fman->exception_cb(fman, FMAN_EX_FPM_DOUBLE_ECC); + if ((event & FPM_EV_MASK_STALL) && (event & FPM_EV_MASK_STALL_EN)) + ret = fman->exception_cb(fman, FMAN_EX_FPM_STALL_ON_TASKS); + if ((event & FPM_EV_MASK_SINGLE_ECC) && + (event & FPM_EV_MASK_SINGLE_ECC_EN)) + ret = fman->exception_cb(fman, FMAN_EX_FPM_SINGLE_ECC); + + return ret; +} + +static irqreturn_t muram_err_intr(struct fman *fman) +{ + u32 event, mask; + struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs; + irqreturn_t ret = IRQ_NONE; + + event = ioread32be(&fpm_rg->fm_rcr); + mask = ioread32be(&fpm_rg->fm_rie); + + /* clear MURAM event bit (do not clear IRAM event) */ + iowrite32be(event & ~FPM_RAM_IRAM_ECC, &fpm_rg->fm_rcr); + + if ((mask & FPM_MURAM_ECC_ERR_EX_EN) && (event & FPM_RAM_MURAM_ECC)) + ret = fman->exception_cb(fman, FMAN_EX_MURAM_ECC); + + return ret; +} + +static irqreturn_t qmi_event(struct fman *fman) +{ + u32 event, mask, force; + struct fman_qmi_regs __iomem *qmi_rg = fman->qmi_regs; + irqreturn_t ret = IRQ_NONE; + + event = ioread32be(&qmi_rg->fmqm_ie); + mask = ioread32be(&qmi_rg->fmqm_ien); + event &= mask; + /* clear the forced events */ + force = ioread32be(&qmi_rg->fmqm_if); + if (force & event) + iowrite32be(force & ~event, &qmi_rg->fmqm_if); + /* clear the acknowledged events */ + iowrite32be(event, &qmi_rg->fmqm_ie); + + if (event & QMI_INTR_EN_SINGLE_ECC) + ret = fman->exception_cb(fman, FMAN_EX_QMI_SINGLE_ECC); + + return ret; +} + +static void enable_time_stamp(struct fman *fman) +{ + struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs; + u16 fm_clk_freq = fman->state->fm_clk_freq; + u32 tmp, intgr, ts_freq; + u64 frac; + + ts_freq = (u32)(1 << fman->state->count1_micro_bit); + /* configure timestamp so that bit 8 will count 1 microsecond + * Find effective count rate at TIMESTAMP least significant bits: + * Effective_Count_Rate = 1MHz x 2^8 = 256MHz + * Find frequency ratio between effective count rate and the clock: + * Effective_Count_Rate / CLK e.g. for 600 MHz clock: + * 256/600 = 0.4266666... + */ + + intgr = ts_freq / fm_clk_freq; + /* we multiply by 2^16 to keep the fraction of the division + * we do not div back, since we write this value as a fraction + * see spec + */ + + frac = ((ts_freq << 16) - (intgr << 16) * fm_clk_freq) / fm_clk_freq; + /* we check remainder of the division in order to round up if not int */ + if (((ts_freq << 16) - (intgr << 16) * fm_clk_freq) % fm_clk_freq) + frac++; + + tmp = (intgr << FPM_TS_INT_SHIFT) | (u16)frac; + iowrite32be(tmp, &fpm_rg->fmfp_tsc2); + + /* enable timestamp with original clock */ + iowrite32be(FPM_TS_CTL_EN, &fpm_rg->fmfp_tsc1); + fman->state->enabled_time_stamp = true; +} + +static int clear_iram(struct fman *fman) +{ + struct fman_iram_regs __iomem *iram; + int i, count; + + iram = fman->base_addr + IMEM_OFFSET; + + /* Enable the auto-increment */ + iowrite32be(IRAM_IADD_AIE, &iram->iadd); + count = 100; + do { + udelay(1); + } while ((ioread32be(&iram->iadd) != IRAM_IADD_AIE) && --count); + if (count == 0) + return -EBUSY; + + for (i = 0; i < (fman->state->fm_iram_size / 4); i++) + iowrite32be(0xffffffff, &iram->idata); + + iowrite32be(fman->state->fm_iram_size - 4, &iram->iadd); + count = 100; + do { + udelay(1); + } while ((ioread32be(&iram->idata) != 0xffffffff) && --count); + if (count == 0) + return -EBUSY; + + return 0; +} + +static u32 get_exception_flag(enum fman_exceptions exception) +{ + u32 bit_mask; + + switch (exception) { + case FMAN_EX_DMA_BUS_ERROR: + bit_mask = EX_DMA_BUS_ERROR; + break; + case FMAN_EX_DMA_SINGLE_PORT_ECC: + bit_mask = EX_DMA_SINGLE_PORT_ECC; + break; + case FMAN_EX_DMA_READ_ECC: + bit_mask = EX_DMA_READ_ECC; + break; + case FMAN_EX_DMA_SYSTEM_WRITE_ECC: + bit_mask = EX_DMA_SYSTEM_WRITE_ECC; + break; + case FMAN_EX_DMA_FM_WRITE_ECC: + bit_mask = EX_DMA_FM_WRITE_ECC; + break; + case FMAN_EX_FPM_STALL_ON_TASKS: + bit_mask = EX_FPM_STALL_ON_TASKS; + break; + case FMAN_EX_FPM_SINGLE_ECC: + bit_mask = EX_FPM_SINGLE_ECC; + break; + case FMAN_EX_FPM_DOUBLE_ECC: + bit_mask = EX_FPM_DOUBLE_ECC; + break; + case FMAN_EX_QMI_SINGLE_ECC: + bit_mask = EX_QMI_SINGLE_ECC; + break; + case FMAN_EX_QMI_DOUBLE_ECC: + bit_mask = EX_QMI_DOUBLE_ECC; + break; + case FMAN_EX_QMI_DEQ_FROM_UNKNOWN_PORTID: + bit_mask = EX_QMI_DEQ_FROM_UNKNOWN_PORTID; + break; + case FMAN_EX_BMI_LIST_RAM_ECC: + bit_mask = EX_BMI_LIST_RAM_ECC; + break; + case FMAN_EX_BMI_STORAGE_PROFILE_ECC: + bit_mask = EX_BMI_STORAGE_PROFILE_ECC; + break; + case FMAN_EX_BMI_STATISTICS_RAM_ECC: + bit_mask = EX_BMI_STATISTICS_RAM_ECC; + break; + case FMAN_EX_BMI_DISPATCH_RAM_ECC: + bit_mask = EX_BMI_DISPATCH_RAM_ECC; + break; + case FMAN_EX_MURAM_ECC: + bit_mask = EX_MURAM_ECC; + break; + default: + bit_mask = 0; + break; + } + + return bit_mask; +} + +static int get_module_event(enum fman_event_modules module, u8 mod_id, + enum fman_intr_type intr_type) +{ + int event; + + switch (module) { + case FMAN_MOD_MAC: + if (intr_type == FMAN_INTR_TYPE_ERR) + event = FMAN_EV_ERR_MAC0 + mod_id; + else + event = FMAN_EV_MAC0 + mod_id; + break; + case FMAN_MOD_FMAN_CTRL: + if (intr_type == FMAN_INTR_TYPE_ERR) + event = FMAN_EV_CNT; + else + event = (FMAN_EV_FMAN_CTRL_0 + mod_id); + break; + case FMAN_MOD_DUMMY_LAST: + event = FMAN_EV_CNT; + break; + default: + event = FMAN_EV_CNT; + break; + } + + return event; +} + +static int set_size_of_fifo(struct fman *fman, u8 port_id, u32 *size_of_fifo, + u32 *extra_size_of_fifo) +{ + struct fman_bmi_regs __iomem *bmi_rg = fman->bmi_regs; + u32 fifo = *size_of_fifo; + u32 extra_fifo = *extra_size_of_fifo; + u32 tmp; + + /* if this is the first time a port requires extra_fifo_pool_size, + * the total extra_fifo_pool_size must be initialized to 1 buffer per + * port + */ + if (extra_fifo && !fman->state->extra_fifo_pool_size) + fman->state->extra_fifo_pool_size = + fman->state->num_of_rx_ports * FMAN_BMI_FIFO_UNITS; + + fman->state->extra_fifo_pool_size = + max(fman->state->extra_fifo_pool_size, extra_fifo); + + /* check that there are enough uncommitted fifo size */ + if ((fman->state->accumulated_fifo_size + fifo) > + (fman->state->total_fifo_size - + fman->state->extra_fifo_pool_size)) { + dev_err(fman->dev, "%s: Requested fifo size and extra size exceed total FIFO size.\n", + __func__); + return -EAGAIN; + } + + /* Read, modify and write to HW */ + tmp = (fifo / FMAN_BMI_FIFO_UNITS - 1) | + ((extra_fifo / FMAN_BMI_FIFO_UNITS) << + BMI_EXTRA_FIFO_SIZE_SHIFT); + iowrite32be(tmp, &bmi_rg->fmbm_pfs[port_id - 1]); + + /* update accumulated */ + fman->state->accumulated_fifo_size += fifo; + + return 0; +} + +static int set_num_of_tasks(struct fman *fman, u8 port_id, u8 *num_of_tasks, + u8 *num_of_extra_tasks) +{ + struct fman_bmi_regs __iomem *bmi_rg = fman->bmi_regs; + u8 tasks = *num_of_tasks; + u8 extra_tasks = *num_of_extra_tasks; + u32 tmp; + + if (extra_tasks) + fman->state->extra_tasks_pool_size = + max(fman->state->extra_tasks_pool_size, extra_tasks); + + /* check that there are enough uncommitted tasks */ + if ((fman->state->accumulated_num_of_tasks + tasks) > + (fman->state->total_num_of_tasks - + fman->state->extra_tasks_pool_size)) { + dev_err(fman->dev, "%s: Requested num_of_tasks and extra tasks pool for fm%d exceed total num_of_tasks.\n", + __func__, fman->state->fm_id); + return -EAGAIN; + } + /* update accumulated */ + fman->state->accumulated_num_of_tasks += tasks; + + /* Write to HW */ + tmp = ioread32be(&bmi_rg->fmbm_pp[port_id - 1]) & + ~(BMI_NUM_OF_TASKS_MASK | BMI_NUM_OF_EXTRA_TASKS_MASK); + tmp |= ((u32)((tasks - 1) << BMI_NUM_OF_TASKS_SHIFT) | + (u32)(extra_tasks << BMI_EXTRA_NUM_OF_TASKS_SHIFT)); + iowrite32be(tmp, &bmi_rg->fmbm_pp[port_id - 1]); + + return 0; +} + +static int set_num_of_open_dmas(struct fman *fman, u8 port_id, + u8 *num_of_open_dmas, + u8 *num_of_extra_open_dmas) +{ + struct fman_bmi_regs __iomem *bmi_rg = fman->bmi_regs; + u8 open_dmas = *num_of_open_dmas; + u8 extra_open_dmas = *num_of_extra_open_dmas; + u8 total_num_dmas = 0, current_val = 0, current_extra_val = 0; + u32 tmp; + + if (!open_dmas) { + /* Configuration according to values in the HW. + * read the current number of open Dma's + */ + tmp = ioread32be(&bmi_rg->fmbm_pp[port_id - 1]); + current_extra_val = (u8)((tmp & BMI_NUM_OF_EXTRA_DMAS_MASK) >> + BMI_EXTRA_NUM_OF_DMAS_SHIFT); + + tmp = ioread32be(&bmi_rg->fmbm_pp[port_id - 1]); + current_val = (u8)(((tmp & BMI_NUM_OF_DMAS_MASK) >> + BMI_NUM_OF_DMAS_SHIFT) + 1); + + /* This is the first configuration and user did not + * specify value (!open_dmas), reset values will be used + * and we just save these values for resource management + */ + fman->state->extra_open_dmas_pool_size = + (u8)max(fman->state->extra_open_dmas_pool_size, + current_extra_val); + fman->state->accumulated_num_of_open_dmas += current_val; + *num_of_open_dmas = current_val; + *num_of_extra_open_dmas = current_extra_val; + return 0; + } + + if (extra_open_dmas > current_extra_val) + fman->state->extra_open_dmas_pool_size = + (u8)max(fman->state->extra_open_dmas_pool_size, + extra_open_dmas); + + if ((fman->state->rev_info.major < 6) && + (fman->state->accumulated_num_of_open_dmas - current_val + + open_dmas > fman->state->max_num_of_open_dmas)) { + dev_err(fman->dev, "%s: Requested num_of_open_dmas for fm%d exceeds total num_of_open_dmas.\n", + __func__, fman->state->fm_id); + return -EAGAIN; + } else if ((fman->state->rev_info.major >= 6) && + !((fman->state->rev_info.major == 6) && + (fman->state->rev_info.minor == 0)) && + (fman->state->accumulated_num_of_open_dmas - + current_val + open_dmas > + fman->state->dma_thresh_max_commq + 1)) { + dev_err(fman->dev, "%s: Requested num_of_open_dmas for fm%d exceeds DMA Command queue (%d)\n", + __func__, fman->state->fm_id, + fman->state->dma_thresh_max_commq + 1); + return -EAGAIN; + } + + WARN_ON(fman->state->accumulated_num_of_open_dmas < current_val); + /* update acummulated */ + fman->state->accumulated_num_of_open_dmas -= current_val; + fman->state->accumulated_num_of_open_dmas += open_dmas; + + if (fman->state->rev_info.major < 6) + total_num_dmas = + (u8)(fman->state->accumulated_num_of_open_dmas + + fman->state->extra_open_dmas_pool_size); + + /* calculate reg */ + tmp = ioread32be(&bmi_rg->fmbm_pp[port_id - 1]) & + ~(BMI_NUM_OF_DMAS_MASK | BMI_NUM_OF_EXTRA_DMAS_MASK); + tmp |= (u32)(((open_dmas - 1) << BMI_NUM_OF_DMAS_SHIFT) | + (extra_open_dmas << BMI_EXTRA_NUM_OF_DMAS_SHIFT)); + iowrite32be(tmp, &bmi_rg->fmbm_pp[port_id - 1]); + + /* update total num of DMA's with committed number of open DMAS, + * and max uncommitted pool. + */ + if (total_num_dmas) { + tmp = ioread32be(&bmi_rg->fmbm_cfg2) & ~BMI_CFG2_DMAS_MASK; + tmp |= (u32)(total_num_dmas - 1) << BMI_CFG2_DMAS_SHIFT; + iowrite32be(tmp, &bmi_rg->fmbm_cfg2); + } + + return 0; +} + +static int fman_config(struct fman *fman) +{ + void __iomem *base_addr; + int err; + + base_addr = fman->dts_params.base_addr; + + fman->state = kzalloc(sizeof(*fman->state), GFP_KERNEL); + if (!fman->state) + goto err_fm_state; + + /* Allocate the FM driver's parameters structure */ + fman->cfg = kzalloc(sizeof(*fman->cfg), GFP_KERNEL); + if (!fman->cfg) + goto err_fm_drv; + + /* Initialize MURAM block */ + fman->muram = + fman_muram_init(fman->dts_params.muram_res.start, + resource_size(&fman->dts_params.muram_res)); + if (!fman->muram) + goto err_fm_soc_specific; + + /* Initialize FM parameters which will be kept by the driver */ + fman->state->fm_id = fman->dts_params.id; + fman->state->fm_clk_freq = fman->dts_params.clk_freq; + fman->state->qman_channel_base = fman->dts_params.qman_channel_base; + fman->state->num_of_qman_channels = + fman->dts_params.num_of_qman_channels; + fman->state->res = fman->dts_params.res; + fman->exception_cb = fman_exceptions; + fman->bus_error_cb = fman_bus_error; + fman->fpm_regs = base_addr + FPM_OFFSET; + fman->bmi_regs = base_addr + BMI_OFFSET; + fman->qmi_regs = base_addr + QMI_OFFSET; + fman->dma_regs = base_addr + DMA_OFFSET; + fman->base_addr = base_addr; + + spin_lock_init(&fman->spinlock); + fman_defconfig(fman->cfg); + + fman->state->extra_fifo_pool_size = 0; + fman->state->exceptions = (EX_DMA_BUS_ERROR | + EX_DMA_READ_ECC | + EX_DMA_SYSTEM_WRITE_ECC | + EX_DMA_FM_WRITE_ECC | + EX_FPM_STALL_ON_TASKS | + EX_FPM_SINGLE_ECC | + EX_FPM_DOUBLE_ECC | + EX_QMI_DEQ_FROM_UNKNOWN_PORTID | + EX_BMI_LIST_RAM_ECC | + EX_BMI_STORAGE_PROFILE_ECC | + EX_BMI_STATISTICS_RAM_ECC | + EX_MURAM_ECC | + EX_BMI_DISPATCH_RAM_ECC | + EX_QMI_DOUBLE_ECC | + EX_QMI_SINGLE_ECC); + + /* Read FMan revision for future use*/ + fman_get_revision(fman, &fman->state->rev_info); + + err = fill_soc_specific_params(fman->state); + if (err) + goto err_fm_soc_specific; + + /* FM_AID_MODE_NO_TNUM_SW005 Errata workaround */ + if (fman->state->rev_info.major >= 6) + fman->cfg->dma_aid_mode = FMAN_DMA_AID_OUT_PORT_ID; + + fman->cfg->qmi_def_tnums_thresh = fman->state->qmi_def_tnums_thresh; + + fman->state->total_num_of_tasks = + (u8)DFLT_TOTAL_NUM_OF_TASKS(fman->state->rev_info.major, + fman->state->rev_info.minor, + fman->state->bmi_max_num_of_tasks); + + if (fman->state->rev_info.major < 6) { + fman->cfg->dma_comm_qtsh_clr_emer = + (u8)DFLT_DMA_COMM_Q_LOW(fman->state->rev_info.major, + fman->state->dma_thresh_max_commq); + + fman->cfg->dma_comm_qtsh_asrt_emer = + (u8)DFLT_DMA_COMM_Q_HIGH(fman->state->rev_info.major, + fman->state->dma_thresh_max_commq); + + fman->cfg->dma_cam_num_of_entries = + DFLT_DMA_CAM_NUM_OF_ENTRIES(fman->state->rev_info.major); + + fman->cfg->dma_read_buf_tsh_clr_emer = + DFLT_DMA_READ_INT_BUF_LOW(fman->state->dma_thresh_max_buf); + + fman->cfg->dma_read_buf_tsh_asrt_emer = + DFLT_DMA_READ_INT_BUF_HIGH(fman->state->dma_thresh_max_buf); + + fman->cfg->dma_write_buf_tsh_clr_emer = + DFLT_DMA_WRITE_INT_BUF_LOW(fman->state->dma_thresh_max_buf); + + fman->cfg->dma_write_buf_tsh_asrt_emer = + DFLT_DMA_WRITE_INT_BUF_HIGH(fman->state->dma_thresh_max_buf); + + fman->cfg->dma_axi_dbg_num_of_beats = + DFLT_AXI_DBG_NUM_OF_BEATS; + } + + return 0; + +err_fm_soc_specific: + kfree(fman->cfg); +err_fm_drv: + kfree(fman->state); +err_fm_state: + kfree(fman); + return -EINVAL; +} + +static int fman_init(struct fman *fman) +{ + struct fman_cfg *cfg = NULL; + int err = 0, i, count; + + if (is_init_done(fman->cfg)) + return -EINVAL; + + fman->state->count1_micro_bit = FM_TIMESTAMP_1_USEC_BIT; + + cfg = fman->cfg; + + /* clear revision-dependent non existing exception */ + if (fman->state->rev_info.major < 6) + fman->state->exceptions &= ~FMAN_EX_BMI_DISPATCH_RAM_ECC; + + if (fman->state->rev_info.major >= 6) + fman->state->exceptions &= ~FMAN_EX_QMI_SINGLE_ECC; + + /* clear CPG */ + memset_io((void __iomem *)(fman->base_addr + CGP_OFFSET), 0, + fman->state->fm_port_num_of_cg); + + /* Save LIODN info before FMan reset + * Skipping non-existent port 0 (i = 1) + */ + for (i = 1; i < FMAN_LIODN_TBL; i++) { + u32 liodn_base; + + fman->liodn_offset[i] = + ioread32be(&fman->bmi_regs->fmbm_spliodn[i - 1]); + liodn_base = ioread32be(&fman->dma_regs->fmdmplr[i / 2]); + if (i % 2) { + /* FMDM_PLR LSB holds LIODN base for odd ports */ + liodn_base &= DMA_LIODN_BASE_MASK; + } else { + /* FMDM_PLR MSB holds LIODN base for even ports */ + liodn_base >>= DMA_LIODN_SHIFT; + liodn_base &= DMA_LIODN_BASE_MASK; + } + fman->liodn_base[i] = liodn_base; + } + + /* FMan Reset (supported only for FMan V2) */ + if (fman->state->rev_info.major >= 6) { + /* Errata A007273 */ + dev_dbg(fman->dev, "%s: FManV3 reset is not supported!\n", + __func__); + } else { + iowrite32be(FPM_RSTC_FM_RESET, &fman->fpm_regs->fm_rstc); + /* Wait for reset completion */ + count = 100; + do { + udelay(1); + } while (((ioread32be(&fman->fpm_regs->fm_rstc)) & + FPM_RSTC_FM_RESET) && --count); + if (count == 0) + return -EBUSY; + } + + if (ioread32be(&fman->qmi_regs->fmqm_gs) & QMI_GS_HALT_NOT_BUSY) { + resume(fman->fpm_regs); + /* Wait until QMI is not in halt not busy state */ + count = 100; + do { + udelay(1); + } while (((ioread32be(&fman->qmi_regs->fmqm_gs)) & + QMI_GS_HALT_NOT_BUSY) && --count); + if (count == 0) + dev_warn(fman->dev, "%s: QMI is in halt not busy state\n", + __func__); + } + + if (clear_iram(fman) != 0) + return -EINVAL; + + cfg->exceptions = fman->state->exceptions; + + /* Init DMA Registers */ + + err = dma_init(fman); + if (err != 0) { + free_init_resources(fman); + return err; + } + + /* Init FPM Registers */ + fpm_init(fman->fpm_regs, fman->cfg); + + /* define common resources */ + /* allocate MURAM for FIFO according to total size */ + fman->fifo_offset = fman_muram_alloc(fman->muram, + fman->state->total_fifo_size); + if (IS_ERR_VALUE(fman->cam_offset)) { + free_init_resources(fman); + dev_err(fman->dev, "%s: MURAM alloc for BMI FIFO failed\n", + __func__); + return -ENOMEM; + } + + cfg->fifo_base_addr = fman->fifo_offset; + cfg->total_fifo_size = fman->state->total_fifo_size; + cfg->total_num_of_tasks = fman->state->total_num_of_tasks; + cfg->clk_freq = fman->state->fm_clk_freq; + + /* Init BMI Registers */ + bmi_init(fman->bmi_regs, fman->cfg); + + /* Init QMI Registers */ + qmi_init(fman->qmi_regs, fman->cfg); + + err = enable(fman, cfg); + if (err != 0) + return err; + + enable_time_stamp(fman); + + kfree(fman->cfg); + fman->cfg = NULL; + + return 0; +} + +static int fman_set_exception(struct fman *fman, + enum fman_exceptions exception, bool enable) +{ + u32 bit_mask = 0; + + if (!is_init_done(fman->cfg)) + return -EINVAL; + + bit_mask = get_exception_flag(exception); + if (bit_mask) { + if (enable) + fman->state->exceptions |= bit_mask; + else + fman->state->exceptions &= ~bit_mask; + } else { + dev_err(fman->dev, "%s: Undefined exception (%d)\n", + __func__, exception); + return -EINVAL; + } + + return set_exception(fman, exception, enable); +} + +/** + * fman_register_intr + * @fman: A Pointer to FMan device + * @mod: Calling module + * @mod_id: Module id (if more than 1 exists, '0' if not) + * @intr_type: Interrupt type (error/normal) selection. + * @f_isr: The interrupt service routine. + * @h_src_arg: Argument to be passed to f_isr. + * + * Used to register an event handler to be processed by FMan + * + * Return: 0 on success; Error code otherwise. + */ +void fman_register_intr(struct fman *fman, enum fman_event_modules module, + u8 mod_id, enum fman_intr_type intr_type, + void (*isr_cb)(void *src_arg), void *src_arg) +{ + int event = 0; + + event = get_module_event(module, mod_id, intr_type); + WARN_ON(event >= FMAN_EV_CNT); + + /* register in local FM structure */ + fman->intr_mng[event].isr_cb = isr_cb; + fman->intr_mng[event].src_handle = src_arg; +} + +/** + * fman_unregister_intr + * @fman: A Pointer to FMan device + * @mod: Calling module + * @mod_id: Module id (if more than 1 exists, '0' if not) + * @intr_type: Interrupt type (error/normal) selection. + * + * Used to unregister an event handler to be processed by FMan + * + * Return: 0 on success; Error code otherwise. + */ +void fman_unregister_intr(struct fman *fman, enum fman_event_modules module, + u8 mod_id, enum fman_intr_type intr_type) +{ + int event = 0; + + event = get_module_event(module, mod_id, intr_type); + WARN_ON(event >= FMAN_EV_CNT); + + fman->intr_mng[event].isr_cb = NULL; + fman->intr_mng[event].src_handle = NULL; +} + +/** + * fman_set_port_params + * @fman: A Pointer to FMan device + * @port_params: Port parameters + * + * Used by FMan Port to pass parameters to the FMan + * + * Return: 0 on success; Error code otherwise. + */ +int fman_set_port_params(struct fman *fman, + struct fman_port_init_params *port_params) +{ + int err; + unsigned long flags; + u8 port_id = port_params->port_id, mac_id; + + spin_lock_irqsave(&fman->spinlock, flags); + + err = set_num_of_tasks(fman, port_params->port_id, + &port_params->num_of_tasks, + &port_params->num_of_extra_tasks); + if (err) + goto return_err; + + /* TX Ports */ + if (port_params->port_type != FMAN_PORT_TYPE_RX) { + u32 enq_th, deq_th, reg; + + /* update qmi ENQ/DEQ threshold */ + fman->state->accumulated_num_of_deq_tnums += + port_params->deq_pipeline_depth; + enq_th = (ioread32be(&fman->qmi_regs->fmqm_gc) & + QMI_CFG_ENQ_MASK) >> QMI_CFG_ENQ_SHIFT; + /* if enq_th is too big, we reduce it to the max value + * that is still 0 + */ + if (enq_th >= (fman->state->qmi_max_num_of_tnums - + fman->state->accumulated_num_of_deq_tnums)) { + enq_th = + fman->state->qmi_max_num_of_tnums - + fman->state->accumulated_num_of_deq_tnums - 1; + + reg = ioread32be(&fman->qmi_regs->fmqm_gc); + reg &= ~QMI_CFG_ENQ_MASK; + reg |= (enq_th << QMI_CFG_ENQ_SHIFT); + iowrite32be(reg, &fman->qmi_regs->fmqm_gc); + } + + deq_th = ioread32be(&fman->qmi_regs->fmqm_gc) & + QMI_CFG_DEQ_MASK; + /* if deq_th is too small, we enlarge it to the min + * value that is still 0. + * depTh may not be larger than 63 + * (fman->state->qmi_max_num_of_tnums-1). + */ + if ((deq_th <= fman->state->accumulated_num_of_deq_tnums) && + (deq_th < fman->state->qmi_max_num_of_tnums - 1)) { + deq_th = fman->state->accumulated_num_of_deq_tnums + 1; + reg = ioread32be(&fman->qmi_regs->fmqm_gc); + reg &= ~QMI_CFG_DEQ_MASK; + reg |= deq_th; + iowrite32be(reg, &fman->qmi_regs->fmqm_gc); + } + } + + err = set_size_of_fifo(fman, port_params->port_id, + &port_params->size_of_fifo, + &port_params->extra_size_of_fifo); + if (err) + goto return_err; + + err = set_num_of_open_dmas(fman, port_params->port_id, + &port_params->num_of_open_dmas, + &port_params->num_of_extra_open_dmas); + if (err) + goto return_err; + + set_port_liodn(fman, port_id, fman->liodn_base[port_id], + fman->liodn_offset[port_id]); + + if (fman->state->rev_info.major < 6) + set_port_order_restoration(fman->fpm_regs, port_id); + + mac_id = hw_port_id_to_sw_port_id(fman->state->rev_info.major, port_id); + + if (port_params->max_frame_length >= fman->state->mac_mfl[mac_id]) { + fman->state->port_mfl[mac_id] = port_params->max_frame_length; + } else { + dev_warn(fman->dev, "%s: Port (%d) max_frame_length is smaller than MAC (%d) current MTU\n", + __func__, port_id, mac_id); + err = -EINVAL; + goto return_err; + } + + spin_unlock_irqrestore(&fman->spinlock, flags); + + return 0; + +return_err: + spin_unlock_irqrestore(&fman->spinlock, flags); + return err; +} + +/** + * fman_reset_mac + * @fman: A Pointer to FMan device + * @mac_id: MAC id to be reset + * + * Reset a specific MAC + * + * Return: 0 on success; Error code otherwise. + */ +int fman_reset_mac(struct fman *fman, u8 mac_id) +{ + struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs; + u32 msk, timeout = 100; + + if (fman->state->rev_info.major >= 6) { + dev_err(fman->dev, "%s: FMan MAC reset no available for FMan V3!\n", + __func__); + return -EINVAL; + } + + /* Get the relevant bit mask */ + switch (mac_id) { + case 0: + msk = FPM_RSTC_MAC0_RESET; + break; + case 1: + msk = FPM_RSTC_MAC1_RESET; + break; + case 2: + msk = FPM_RSTC_MAC2_RESET; + break; + case 3: + msk = FPM_RSTC_MAC3_RESET; + break; + case 4: + msk = FPM_RSTC_MAC4_RESET; + break; + case 5: + msk = FPM_RSTC_MAC5_RESET; + break; + case 6: + msk = FPM_RSTC_MAC6_RESET; + break; + case 7: + msk = FPM_RSTC_MAC7_RESET; + break; + case 8: + msk = FPM_RSTC_MAC8_RESET; + break; + case 9: + msk = FPM_RSTC_MAC9_RESET; + break; + default: + dev_warn(fman->dev, "%s: Illegal MAC Id [%d]\n", + __func__, mac_id); + return -EINVAL; + } + + /* reset */ + iowrite32be(msk, &fpm_rg->fm_rstc); + while ((ioread32be(&fpm_rg->fm_rstc) & msk) && --timeout) + udelay(10); + + if (!timeout) + return -EIO; + + return 0; +} + +/** + * fman_set_mac_max_frame + * @fman: A Pointer to FMan device + * @mac_id: MAC id + * @mfl: Maximum frame length + * + * Set maximum frame length of specific MAC in FMan driver + * + * Return: 0 on success; Error code otherwise. + */ +int fman_set_mac_max_frame(struct fman *fman, u8 mac_id, u16 mfl) +{ + /* if port is already initialized, check that MaxFrameLength is smaller + * or equal to the port's max + */ + if ((!fman->state->port_mfl[mac_id]) || + (fman->state->port_mfl[mac_id] && + (mfl <= fman->state->port_mfl[mac_id]))) { + fman->state->mac_mfl[mac_id] = mfl; + } else { + dev_warn(fman->dev, "%s: MAC max_frame_length is larger than Port max_frame_length\n", + __func__); + return -EINVAL; + } + return 0; +} + +/** + * fman_get_clock_freq + * @fman: A Pointer to FMan device + * + * Get FMan clock frequency + * + * Return: FMan clock frequency + */ +u16 fman_get_clock_freq(struct fman *fman) +{ + return fman->state->fm_clk_freq; +} + +/** + * fman_get_bmi_max_fifo_size + * @fman: A Pointer to FMan device + * + * Get FMan maximum FIFO size + * + * Return: FMan Maximum FIFO size + */ +u32 fman_get_bmi_max_fifo_size(struct fman *fman) +{ + return fman->state->bmi_max_fifo_size; +} + +/** + * fman_get_revision + * @fman - Pointer to the FMan module + * @rev_info - A structure of revision information parameters. + * + * Returns the FM revision + * + * Allowed only following fman_init(). + * + * Return: 0 on success; Error code otherwise. + */ +void fman_get_revision(struct fman *fman, struct fman_rev_info *rev_info) +{ + u32 tmp; + + tmp = ioread32be(&fman->fpm_regs->fm_ip_rev_1); + rev_info->major = (u8)((tmp & FPM_REV1_MAJOR_MASK) >> + FPM_REV1_MAJOR_SHIFT); + rev_info->minor = tmp & FPM_REV1_MINOR_MASK; +} + +/** + * fman_get_qman_channel_id + * @fman: A Pointer to FMan device + * @port_id: Port id + * + * Get QMan channel ID associated to the Port id + * + * Return: QMan channel ID + */ +u32 fman_get_qman_channel_id(struct fman *fman, u32 port_id) +{ + int i; + + if (fman->state->rev_info.major >= 6) { + u32 port_ids[] = {0x30, 0x31, 0x28, 0x29, 0x2a, 0x2b, + 0x2c, 0x2d, 0x2, 0x3, 0x4, 0x5, 0x7, 0x7}; + for (i = 0; i < fman->state->num_of_qman_channels; i++) { + if (port_ids[i] == port_id) + break; + } + } else { + u32 port_ids[] = {0x30, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x1, + 0x2, 0x3, 0x4, 0x5, 0x7, 0x7}; + for (i = 0; i < fman->state->num_of_qman_channels; i++) { + if (port_ids[i] == port_id) + break; + } + } + + if (i == fman->state->num_of_qman_channels) + return 0; + + return fman->state->qman_channel_base + i; +} + +/** + * fman_get_mem_region + * @fman: A Pointer to FMan device + * + * Get FMan memory region + * + * Return: A structure with FMan memory region information + */ +struct resource *fman_get_mem_region(struct fman *fman) +{ + return fman->state->res; +} + +/* Bootargs defines */ +/* Extra headroom for RX buffers - Default, min and max */ +#define FSL_FM_RX_EXTRA_HEADROOM 64 +#define FSL_FM_RX_EXTRA_HEADROOM_MIN 16 +#define FSL_FM_RX_EXTRA_HEADROOM_MAX 384 + +/* Maximum frame length */ +#define FSL_FM_MAX_FRAME_SIZE 1522 +#define FSL_FM_MAX_POSSIBLE_FRAME_SIZE 9600 +#define FSL_FM_MIN_POSSIBLE_FRAME_SIZE 64 + +/* Extra headroom for Rx buffers. + * FMan is instructed to allocate, on the Rx path, this amount of + * space at the beginning of a data buffer, beside the DPA private + * data area and the IC fields. + * Does not impact Tx buffer layout. + * Configurable from bootargs. 64 by default, it's needed on + * particular forwarding scenarios that add extra headers to the + * forwarded frame. + */ +int fsl_fm_rx_extra_headroom = FSL_FM_RX_EXTRA_HEADROOM; +module_param(fsl_fm_rx_extra_headroom, int, 0); +MODULE_PARM_DESC(fsl_fm_rx_extra_headroom, "Extra headroom for Rx buffers"); + +/* Max frame size, across all interfaces. + * Configurable from bootargs, to avoid allocating oversized (socket) + * buffers when not using jumbo frames. + * Must be large enough to accommodate the network MTU, but small enough + * to avoid wasting skb memory. + * + * Could be overridden once, at boot-time, via the + * fm_set_max_frm() callback. + */ +int fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE; +module_param(fsl_fm_max_frm, int, 0); +MODULE_PARM_DESC(fsl_fm_max_frm, "Maximum frame size, across all interfaces"); + +/** + * fman_get_max_frm + * + * Return: Max frame length configured in the FM driver + */ +u16 fman_get_max_frm(void) +{ + static bool fm_check_mfl; + + if (!fm_check_mfl) { + if (fsl_fm_max_frm > FSL_FM_MAX_POSSIBLE_FRAME_SIZE || + fsl_fm_max_frm < FSL_FM_MIN_POSSIBLE_FRAME_SIZE) { + pr_warn("Invalid fsl_fm_max_frm value (%d) in bootargs, valid range is %d-%d. Falling back to the default (%d)\n", + fsl_fm_max_frm, + FSL_FM_MIN_POSSIBLE_FRAME_SIZE, + FSL_FM_MAX_POSSIBLE_FRAME_SIZE, + FSL_FM_MAX_FRAME_SIZE); + fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE; + } + fm_check_mfl = true; + } + + return fsl_fm_max_frm; +} +EXPORT_SYMBOL(fman_get_max_frm); + +/** + * fman_get_rx_extra_headroom + * + * Return: Extra headroom size configured in the FM driver + */ +int fman_get_rx_extra_headroom(void) +{ + static bool fm_check_rx_extra_headroom; + + if (!fm_check_rx_extra_headroom) { + if (fsl_fm_rx_extra_headroom > FSL_FM_RX_EXTRA_HEADROOM_MAX || + fsl_fm_rx_extra_headroom < FSL_FM_RX_EXTRA_HEADROOM_MIN) { + pr_warn("Invalid fsl_fm_rx_extra_headroom value (%d) in bootargs, valid range is %d-%d. Falling back to the default (%d)\n", + fsl_fm_rx_extra_headroom, + FSL_FM_RX_EXTRA_HEADROOM_MIN, + FSL_FM_RX_EXTRA_HEADROOM_MAX, + FSL_FM_RX_EXTRA_HEADROOM); + fsl_fm_rx_extra_headroom = FSL_FM_RX_EXTRA_HEADROOM; + } + + fm_check_rx_extra_headroom = true; + fsl_fm_rx_extra_headroom = ALIGN(fsl_fm_rx_extra_headroom, 16); + } + + return fsl_fm_rx_extra_headroom; +} +EXPORT_SYMBOL(fman_get_rx_extra_headroom); + +/** + * fman_bind + * @dev: FMan OF device pointer + * + * Bind to a specific FMan device. + * + * Allowed only after the port was created. + * + * Return: A pointer to the FMan device + */ +struct fman *fman_bind(struct device *fm_dev) +{ + return (struct fman *)(dev_get_drvdata(get_device(fm_dev))); +} + +static irqreturn_t fman_err_irq(int irq, void *handle) +{ + struct fman *fman = (struct fman *)handle; + u32 pending; + struct fman_fpm_regs __iomem *fpm_rg; + irqreturn_t single_ret, ret = IRQ_NONE; + + if (!is_init_done(fman->cfg)) + return IRQ_NONE; + + fpm_rg = fman->fpm_regs; + + /* error interrupts */ + pending = ioread32be(&fpm_rg->fm_epi); + if (!pending) + return IRQ_NONE; + + if (pending & ERR_INTR_EN_BMI) { + single_ret = bmi_err_event(fman); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_QMI) { + single_ret = qmi_err_event(fman); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_FPM) { + single_ret = fpm_err_event(fman); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_DMA) { + single_ret = dma_err_event(fman); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MURAM) { + single_ret = muram_err_intr(fman); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + + /* MAC error interrupts */ + if (pending & ERR_INTR_EN_MAC0) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 0); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC1) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 1); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC2) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 2); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC3) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 3); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC4) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 4); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC5) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 5); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC6) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 6); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC7) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 7); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC8) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 8); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & ERR_INTR_EN_MAC9) { + single_ret = call_mac_isr(fman, FMAN_EV_ERR_MAC0 + 9); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + + return ret; +} + +static irqreturn_t fman_irq(int irq, void *handle) +{ + struct fman *fman = (struct fman *)handle; + u32 pending; + struct fman_fpm_regs __iomem *fpm_rg; + irqreturn_t single_ret, ret = IRQ_NONE; + + if (!is_init_done(fman->cfg)) + return IRQ_NONE; + + fpm_rg = fman->fpm_regs; + + /* normal interrupts */ + pending = ioread32be(&fpm_rg->fm_npi); + if (!pending) + return IRQ_NONE; + + if (pending & INTR_EN_QMI) { + single_ret = qmi_event(fman); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + + /* MAC interrupts */ + if (pending & INTR_EN_MAC0) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 0); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC1) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 1); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC2) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 2); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC3) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 3); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC4) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 4); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC5) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 5); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC6) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 6); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC7) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 7); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC8) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 8); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + if (pending & INTR_EN_MAC9) { + single_ret = call_mac_isr(fman, FMAN_EV_MAC0 + 9); + if (single_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + + return ret; +} + +static const struct of_device_id fman_muram_match[] = { + { + .compatible = "fsl,fman-muram"}, + {} +}; +MODULE_DEVICE_TABLE(of, fman_muram_match); + +static struct fman *read_dts_node(struct platform_device *of_dev) +{ + struct fman *fman; + struct device_node *fm_node, *muram_node; + struct resource *res; + const u32 *u32_prop; + int lenp, err, irq; + struct clk *clk; + u32 clk_rate; + phys_addr_t phys_base_addr; + resource_size_t mem_size; + + fman = kzalloc(sizeof(*fman), GFP_KERNEL); + if (!fman) + return NULL; + + fm_node = of_node_get(of_dev->dev.of_node); + + u32_prop = (const u32 *)of_get_property(fm_node, "cell-index", &lenp); + if (!u32_prop) { + dev_err(&of_dev->dev, "%s: of_get_property(%s, cell-index) failed\n", + __func__, fm_node->full_name); + goto fman_node_put; + } + if (WARN_ON(lenp != sizeof(u32))) + goto fman_node_put; + + fman->dts_params.id = (u8)fdt32_to_cpu(u32_prop[0]); + + /* Get the FM interrupt */ + res = platform_get_resource(of_dev, IORESOURCE_IRQ, 0); + if (!res) { + dev_err(&of_dev->dev, "%s: Can't get FMan IRQ resource\n", + __func__); + goto fman_node_put; + } + irq = res->start; + + /* Get the FM error interrupt */ + res = platform_get_resource(of_dev, IORESOURCE_IRQ, 1); + if (!res) { + dev_err(&of_dev->dev, "%s: Can't get FMan Error IRQ resource\n", + __func__); + goto fman_node_put; + } + fman->dts_params.err_irq = res->start; + + /* Get the FM address */ + res = platform_get_resource(of_dev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&of_dev->dev, "%s: Can't get FMan memory resouce\n", + __func__); + goto fman_node_put; + } + + phys_base_addr = res->start; + mem_size = resource_size(res); + + clk = of_clk_get(fm_node, 0); + if (IS_ERR(clk)) { + dev_err(&of_dev->dev, "%s: Failed to get FM%d clock structure\n", + __func__, fman->dts_params.id); + goto fman_node_put; + } + + clk_rate = clk_get_rate(clk); + if (!clk_rate) { + dev_err(&of_dev->dev, "%s: Failed to determine FM%d clock rate\n", + __func__, fman->dts_params.id); + goto fman_node_put; + } + /* Rounding to MHz */ + fman->dts_params.clk_freq = DIV_ROUND_UP(clk_rate, 1000000); + + u32_prop = (const u32 *)of_get_property(fm_node, + "fsl,qman-channel-range", + &lenp); + if (!u32_prop) { + dev_err(&of_dev->dev, "%s: of_get_property(%s, fsl,qman-channel-range) failed\n", + __func__, fm_node->full_name); + goto fman_node_put; + } + if (WARN_ON(lenp != sizeof(u32) * 2)) + goto fman_node_put; + fman->dts_params.qman_channel_base = fdt32_to_cpu(u32_prop[0]); + fman->dts_params.num_of_qman_channels = fdt32_to_cpu(u32_prop[1]); + + /* Get the MURAM base address and size */ + muram_node = of_find_matching_node(fm_node, fman_muram_match); + if (!muram_node) { + dev_err(&of_dev->dev, "%s: could not find MURAM node\n", + __func__); + goto fman_node_put; + } + + err = of_address_to_resource(muram_node, 0, + &fman->dts_params.muram_res); + if (err) { + of_node_put(muram_node); + dev_err(&of_dev->dev, "%s: of_address_to_resource() = %d\n", + __func__, err); + goto fman_node_put; + } + + of_node_put(muram_node); + of_node_put(fm_node); + + err = devm_request_irq(&of_dev->dev, irq, fman_irq, 0, "fman", fman); + if (err < 0) { + dev_err(&of_dev->dev, "%s: irq %d allocation failed (error = %d)\n", + __func__, irq, err); + goto fman_free; + } + + if (fman->dts_params.err_irq != 0) { + err = devm_request_irq(&of_dev->dev, fman->dts_params.err_irq, + fman_err_irq, IRQF_SHARED, + "fman-err", fman); + if (err < 0) { + dev_err(&of_dev->dev, "%s: irq %d allocation failed (error = %d)\n", + __func__, fman->dts_params.err_irq, err); + goto fman_free; + } + } + + fman->dts_params.res = + devm_request_mem_region(&of_dev->dev, phys_base_addr, + mem_size, "fman"); + if (!fman->dts_params.res) { + dev_err(&of_dev->dev, "%s: request_mem_region() failed\n", + __func__); + goto fman_free; + } + + fman->dts_params.base_addr = + devm_ioremap(&of_dev->dev, phys_base_addr, mem_size); + if (fman->dts_params.base_addr == 0) { + dev_err(&of_dev->dev, "%s: devm_ioremap() failed\n", __func__); + goto fman_free; + } + + return fman; + +fman_node_put: + of_node_put(fm_node); +fman_free: + kfree(fman); + return NULL; +} + +static int fman_probe(struct platform_device *of_dev) +{ + struct fman *fman; + struct device *dev; + int err; + + dev = &of_dev->dev; + + fman = read_dts_node(of_dev); + if (!fman) + return -EIO; + + err = fman_config(fman); + if (err) { + dev_err(dev, "%s: FMan config failed\n", __func__); + return -EINVAL; + } + + if (fman_init(fman) != 0) { + dev_err(dev, "%s: FMan init failed\n", __func__); + return -EINVAL; + } + + if (fman->dts_params.err_irq == 0) { + fman_set_exception(fman, FMAN_EX_DMA_BUS_ERROR, false); + fman_set_exception(fman, FMAN_EX_DMA_READ_ECC, false); + fman_set_exception(fman, FMAN_EX_DMA_SYSTEM_WRITE_ECC, false); + fman_set_exception(fman, FMAN_EX_DMA_FM_WRITE_ECC, false); + fman_set_exception(fman, FMAN_EX_DMA_SINGLE_PORT_ECC, false); + fman_set_exception(fman, FMAN_EX_FPM_STALL_ON_TASKS, false); + fman_set_exception(fman, FMAN_EX_FPM_SINGLE_ECC, false); + fman_set_exception(fman, FMAN_EX_FPM_DOUBLE_ECC, false); + fman_set_exception(fman, FMAN_EX_QMI_SINGLE_ECC, false); + fman_set_exception(fman, FMAN_EX_QMI_DOUBLE_ECC, false); + fman_set_exception(fman, + FMAN_EX_QMI_DEQ_FROM_UNKNOWN_PORTID, false); + fman_set_exception(fman, FMAN_EX_BMI_LIST_RAM_ECC, false); + fman_set_exception(fman, FMAN_EX_BMI_STORAGE_PROFILE_ECC, + false); + fman_set_exception(fman, FMAN_EX_BMI_STATISTICS_RAM_ECC, false); + fman_set_exception(fman, FMAN_EX_BMI_DISPATCH_RAM_ECC, false); + } + + dev_set_drvdata(dev, fman); + + fman->dev = dev; + + dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id); + + return 0; +} + +static const struct of_device_id fman_match[] = { + { + .compatible = "fsl,fman"}, + {} +}; + +MODULE_DEVICE_TABLE(of, fm_match); + +static struct platform_driver fman_driver = { + .driver = { + .name = "fsl-fman", + .of_match_table = fman_match, + }, + .probe = fman_probe, +}; + +builtin_platform_driver(fman_driver); diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h new file mode 100644 index 0000000000000..57aae8d17d771 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -0,0 +1,325 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __FM_H +#define __FM_H + +#include <linux/io.h> + +/* FM Frame descriptor macros */ +/* Frame queue Context Override */ +#define FM_FD_CMD_FCO 0x80000000 +#define FM_FD_CMD_RPD 0x40000000 /* Read Prepended Data */ +#define FM_FD_CMD_DTC 0x10000000 /* Do L4 Checksum */ + +/* TX-Port: Unsupported Format */ +#define FM_FD_ERR_UNSUPPORTED_FORMAT 0x04000000 +/* TX Port: Length Error */ +#define FM_FD_ERR_LENGTH 0x02000000 +#define FM_FD_ERR_DMA 0x01000000 /* DMA Data error */ + +/* IPR frame (not error) */ +#define FM_FD_IPR 0x00000001 +/* IPR non-consistent-sp */ +#define FM_FD_ERR_IPR_NCSP (0x00100000 | FM_FD_IPR) +/* IPR error */ +#define FM_FD_ERR_IPR (0x00200000 | FM_FD_IPR) +/* IPR timeout */ +#define FM_FD_ERR_IPR_TO (0x00300000 | FM_FD_IPR) +/* TX Port: Length Error */ +#define FM_FD_ERR_IPRE (FM_FD_ERR_IPR & ~FM_FD_IPR) + +/* Rx FIFO overflow, FCS error, code error, running disparity error + * (SGMII and TBI modes), FIFO parity error. PHY Sequence error, + * PHY error control character detected. + */ +#define FM_FD_ERR_PHYSICAL 0x00080000 +/* Frame too long OR Frame size exceeds max_length_frame */ +#define FM_FD_ERR_SIZE 0x00040000 +/* classification discard */ +#define FM_FD_ERR_CLS_DISCARD 0x00020000 +/* Extract Out of Frame */ +#define FM_FD_ERR_EXTRACTION 0x00008000 +/* No Scheme Selected */ +#define FM_FD_ERR_NO_SCHEME 0x00004000 +/* Keysize Overflow */ +#define FM_FD_ERR_KEYSIZE_OVERFLOW 0x00002000 +/* Frame color is red */ +#define FM_FD_ERR_COLOR_RED 0x00000800 +/* Frame color is yellow */ +#define FM_FD_ERR_COLOR_YELLOW 0x00000400 +/* Parser Time out Exceed */ +#define FM_FD_ERR_PRS_TIMEOUT 0x00000080 +/* Invalid Soft Parser instruction */ +#define FM_FD_ERR_PRS_ILL_INSTRUCT 0x00000040 +/* Header error was identified during parsing */ +#define FM_FD_ERR_PRS_HDR_ERR 0x00000020 +/* Frame parsed beyind 256 first bytes */ +#define FM_FD_ERR_BLOCK_LIMIT_EXCEEDED 0x00000008 + +/* non Frame-Manager error */ +#define FM_FD_RX_STATUS_ERR_NON_FM 0x00400000 + +/* FMan driver defines */ +#define FMAN_BMI_FIFO_UNITS 0x100 +#define OFFSET_UNITS 16 + +/* BMan defines */ +#define BM_MAX_NUM_OF_POOLS 64 /* Buffers pools */ +#define FMAN_PORT_MAX_EXT_POOLS_NUM 8 /* External BM pools per Rx port */ + +struct fman; /* FMan data */ + +/* Enum for defining port types */ +enum fman_port_type { + FMAN_PORT_TYPE_TX = 0, /* TX Port */ + FMAN_PORT_TYPE_RX, /* RX Port */ +}; + +struct fman_rev_info { + u8 major; /* Major revision */ + u8 minor; /* Minor revision */ +}; + +enum fman_exceptions { + FMAN_EX_DMA_BUS_ERROR = 0, /* DMA bus error. */ + FMAN_EX_DMA_READ_ECC, /* Read Buffer ECC error */ + FMAN_EX_DMA_SYSTEM_WRITE_ECC, /* Write Buffer ECC err on sys side */ + FMAN_EX_DMA_FM_WRITE_ECC, /* Write Buffer ECC error on FM side */ + FMAN_EX_DMA_SINGLE_PORT_ECC, /* Single Port ECC error on FM side */ + FMAN_EX_FPM_STALL_ON_TASKS, /* Stall of tasks on FPM */ + FMAN_EX_FPM_SINGLE_ECC, /* Single ECC on FPM. */ + FMAN_EX_FPM_DOUBLE_ECC, /* Double ECC error on FPM ram access */ + FMAN_EX_QMI_SINGLE_ECC, /* Single ECC on QMI. */ + FMAN_EX_QMI_DOUBLE_ECC, /* Double bit ECC occurred on QMI */ + FMAN_EX_QMI_DEQ_FROM_UNKNOWN_PORTID,/* DeQ from unknown port id */ + FMAN_EX_BMI_LIST_RAM_ECC, /* Linked List RAM ECC error */ + FMAN_EX_BMI_STORAGE_PROFILE_ECC,/* storage profile */ + FMAN_EX_BMI_STATISTICS_RAM_ECC,/* Statistics RAM ECC Err Enable */ + FMAN_EX_BMI_DISPATCH_RAM_ECC, /* Dispatch RAM ECC Error Enable */ + FMAN_EX_IRAM_ECC, /* Double bit ECC occurred on IRAM */ + FMAN_EX_MURAM_ECC /* Double bit ECC occurred on MURAM */ +}; + +/* Parse results memory layout */ +struct fman_prs_result { + u8 lpid; /* Logical port id */ + u8 shimr; /* Shim header result */ + u16 l2r; /* Layer 2 result */ + u16 l3r; /* Layer 3 result */ + u8 l4r; /* Layer 4 result */ + u8 cplan; /* Classification plan id */ + u16 nxthdr; /* Next Header */ + u16 cksum; /* Running-sum */ + /* Flags&fragment-offset field of the last IP-header */ + u16 flags_frag_off; + /* Routing type field of a IPV6 routing extension header */ + u8 route_type; + /* Routing Extension Header Present; last bit is IP valid */ + u8 rhp_ip_valid; + u8 shim_off[2]; /* Shim offset */ + u8 ip_pid_off; /* IP PID (last IP-proto) offset */ + u8 eth_off; /* ETH offset */ + u8 llc_snap_off; /* LLC_SNAP offset */ + u8 vlan_off[2]; /* VLAN offset */ + u8 etype_off; /* ETYPE offset */ + u8 pppoe_off; /* PPP offset */ + u8 mpls_off[2]; /* MPLS offset */ + u8 ip_off[2]; /* IP offset */ + u8 gre_off; /* GRE offset */ + u8 l4_off; /* Layer 4 offset */ + u8 nxthdr_off; /* Parser end point */ +}; + +/* A structure for defining buffer prefix area content. */ +struct fman_buffer_prefix_content { + /* Number of bytes to be left at the beginning of the external + * buffer; Note that the private-area will start from the base + * of the buffer address. + */ + u16 priv_data_size; + /* true to pass the parse result to/from the FM; + * User may use FM_PORT_GetBufferPrsResult() in + * order to get the parser-result from a buffer. + */ + bool pass_prs_result; + /* true to pass the timeStamp to/from the FM User */ + bool pass_time_stamp; + /* true to pass the KG hash result to/from the FM User may + * use FM_PORT_GetBufferHashResult() in order to get the + * parser-result from a buffer. + */ + bool pass_hash_result; + /* Add all other Internal-Context information: AD, + * hash-result, key, etc. + */ + u16 data_align; +}; + +/* A structure of information about each of the external + * buffer pools used by a port or storage-profile. + */ +struct fman_ext_pool_params { + u8 id; /* External buffer pool id */ + u16 size; /* External buffer pool buffer size */ +}; + +/* A structure for informing the driver about the external + * buffer pools allocated in the BM and used by a port or a + * storage-profile. + */ +struct fman_ext_pools { + u8 num_of_pools_used; /* Number of pools use by this port */ + struct fman_ext_pool_params ext_buf_pool[FMAN_PORT_MAX_EXT_POOLS_NUM]; + /* Parameters for each port */ +}; + +/* A structure for defining BM pool depletion criteria */ +struct fman_buf_pool_depletion { + /* select mode in which pause frames will be sent after a + * number of pools (all together!) are depleted + */ + bool pools_grp_mode_enable; + /* the number of depleted pools that will invoke pause + * frames transmission. + */ + u8 num_of_pools; + /* For each pool, true if it should be considered for + * depletion (Note - this pool must be used by this port!). + */ + bool pools_to_consider[BM_MAX_NUM_OF_POOLS]; + /* select mode in which pause frames will be sent + * after a single-pool is depleted; + */ + bool single_pool_mode_enable; + /* For each pool, true if it should be considered + * for depletion (Note - this pool must be used by this port!) + */ + bool pools_to_consider_for_single_mode[BM_MAX_NUM_OF_POOLS]; +}; + +/* Enum for inter-module interrupts registration */ +enum fman_event_modules { + FMAN_MOD_MAC = 0, /* MAC event */ + FMAN_MOD_FMAN_CTRL, /* FMAN Controller */ + FMAN_MOD_DUMMY_LAST +}; + +/* Enum for interrupts types */ +enum fman_intr_type { + FMAN_INTR_TYPE_ERR, + FMAN_INTR_TYPE_NORMAL +}; + +/* Enum for inter-module interrupts registration */ +enum fman_inter_module_event { + FMAN_EV_ERR_MAC0 = 0, /* MAC 0 error event */ + FMAN_EV_ERR_MAC1, /* MAC 1 error event */ + FMAN_EV_ERR_MAC2, /* MAC 2 error event */ + FMAN_EV_ERR_MAC3, /* MAC 3 error event */ + FMAN_EV_ERR_MAC4, /* MAC 4 error event */ + FMAN_EV_ERR_MAC5, /* MAC 5 error event */ + FMAN_EV_ERR_MAC6, /* MAC 6 error event */ + FMAN_EV_ERR_MAC7, /* MAC 7 error event */ + FMAN_EV_ERR_MAC8, /* MAC 8 error event */ + FMAN_EV_ERR_MAC9, /* MAC 9 error event */ + FMAN_EV_MAC0, /* MAC 0 event (Magic packet detection) */ + FMAN_EV_MAC1, /* MAC 1 event (Magic packet detection) */ + FMAN_EV_MAC2, /* MAC 2 (Magic packet detection) */ + FMAN_EV_MAC3, /* MAC 3 (Magic packet detection) */ + FMAN_EV_MAC4, /* MAC 4 (Magic packet detection) */ + FMAN_EV_MAC5, /* MAC 5 (Magic packet detection) */ + FMAN_EV_MAC6, /* MAC 6 (Magic packet detection) */ + FMAN_EV_MAC7, /* MAC 7 (Magic packet detection) */ + FMAN_EV_MAC8, /* MAC 8 event (Magic packet detection) */ + FMAN_EV_MAC9, /* MAC 9 event (Magic packet detection) */ + FMAN_EV_FMAN_CTRL_0, /* Fman controller event 0 */ + FMAN_EV_FMAN_CTRL_1, /* Fman controller event 1 */ + FMAN_EV_FMAN_CTRL_2, /* Fman controller event 2 */ + FMAN_EV_FMAN_CTRL_3, /* Fman controller event 3 */ + FMAN_EV_CNT +}; + +struct fman_intr_src { + void (*isr_cb)(void *src_arg); + void *src_handle; +}; + +/* Structure for port-FM communication during fman_port_init. */ +struct fman_port_init_params { + u8 port_id; /* port Id */ + enum fman_port_type port_type; /* Port type */ + u16 port_speed; /* Port speed */ + u16 liodn_offset; /* Port's requested resource */ + u8 num_of_tasks; /* Port's requested resource */ + u8 num_of_extra_tasks; /* Port's requested resource */ + u8 num_of_open_dmas; /* Port's requested resource */ + u8 num_of_extra_open_dmas; /* Port's requested resource */ + u32 size_of_fifo; /* Port's requested resource */ + u32 extra_size_of_fifo; /* Port's requested resource */ + u8 deq_pipeline_depth; /* Port's requested resource */ + u16 max_frame_length; /* Port's max frame length. */ + u16 liodn_base; + /* LIODN base for this port, to be used together with LIODN offset. */ +}; + +void fman_get_revision(struct fman *fman, struct fman_rev_info *rev_info); + +void fman_register_intr(struct fman *fman, enum fman_event_modules mod, + u8 mod_id, enum fman_intr_type intr_type, + void (*f_isr)(void *h_src_arg), void *h_src_arg); + +void fman_unregister_intr(struct fman *fman, enum fman_event_modules mod, + u8 mod_id, enum fman_intr_type intr_type); + +int fman_set_port_params(struct fman *fman, + struct fman_port_init_params *port_params); + +int fman_reset_mac(struct fman *fman, u8 mac_id); + +u16 fman_get_clock_freq(struct fman *fman); + +u32 fman_get_bmi_max_fifo_size(struct fman *fman); + +int fman_set_mac_max_frame(struct fman *fman, u8 mac_id, u16 mfl); + +u32 fman_get_qman_channel_id(struct fman *fman, u32 port_id); + +struct resource *fman_get_mem_region(struct fman *fman); + +u16 fman_get_max_frm(void); + +int fman_get_rx_extra_headroom(void); + +struct fman *fman_bind(struct device *dev); + +#endif /* __FM_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c new file mode 100644 index 0000000000000..d78e2ba73ffab --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -0,0 +1,1453 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include "fman_dtsec.h" +#include "fman.h" + +#include <linux/slab.h> +#include <linux/bitrev.h> +#include <linux/io.h> +#include <linux/delay.h> +#include <linux/phy.h> +#include <linux/crc32.h> +#include <linux/of_mdio.h> +#include <linux/mii.h> + +/* TBI register addresses */ +#define MII_TBICON 0x11 + +/* TBICON register bit fields */ +#define TBICON_SOFT_RESET 0x8000 /* Soft reset */ +#define TBICON_DISABLE_RX_DIS 0x2000 /* Disable receive disparity */ +#define TBICON_DISABLE_TX_DIS 0x1000 /* Disable transmit disparity */ +#define TBICON_AN_SENSE 0x0100 /* Auto-negotiation sense enable */ +#define TBICON_CLK_SELECT 0x0020 /* Clock select */ +#define TBICON_MI_MODE 0x0010 /* GMII mode (TBI if not set) */ + +#define TBIANA_SGMII 0x4001 +#define TBIANA_1000X 0x01a0 + +/* Interrupt Mask Register (IMASK) */ +#define DTSEC_IMASK_BREN 0x80000000 +#define DTSEC_IMASK_RXCEN 0x40000000 +#define DTSEC_IMASK_MSROEN 0x04000000 +#define DTSEC_IMASK_GTSCEN 0x02000000 +#define DTSEC_IMASK_BTEN 0x01000000 +#define DTSEC_IMASK_TXCEN 0x00800000 +#define DTSEC_IMASK_TXEEN 0x00400000 +#define DTSEC_IMASK_LCEN 0x00040000 +#define DTSEC_IMASK_CRLEN 0x00020000 +#define DTSEC_IMASK_XFUNEN 0x00010000 +#define DTSEC_IMASK_ABRTEN 0x00008000 +#define DTSEC_IMASK_IFERREN 0x00004000 +#define DTSEC_IMASK_MAGEN 0x00000800 +#define DTSEC_IMASK_MMRDEN 0x00000400 +#define DTSEC_IMASK_MMWREN 0x00000200 +#define DTSEC_IMASK_GRSCEN 0x00000100 +#define DTSEC_IMASK_TDPEEN 0x00000002 +#define DTSEC_IMASK_RDPEEN 0x00000001 + +#define DTSEC_EVENTS_MASK \ + ((u32)(DTSEC_IMASK_BREN | \ + DTSEC_IMASK_RXCEN | \ + DTSEC_IMASK_BTEN | \ + DTSEC_IMASK_TXCEN | \ + DTSEC_IMASK_TXEEN | \ + DTSEC_IMASK_ABRTEN | \ + DTSEC_IMASK_LCEN | \ + DTSEC_IMASK_CRLEN | \ + DTSEC_IMASK_XFUNEN | \ + DTSEC_IMASK_IFERREN | \ + DTSEC_IMASK_MAGEN | \ + DTSEC_IMASK_TDPEEN | \ + DTSEC_IMASK_RDPEEN)) + +/* dtsec timestamp event bits */ +#define TMR_PEMASK_TSREEN 0x00010000 +#define TMR_PEVENT_TSRE 0x00010000 + +/* Group address bit indication */ +#define MAC_GROUP_ADDRESS 0x0000010000000000ULL + +/* Defaults */ +#define DEFAULT_HALFDUP_RETRANSMIT 0xf +#define DEFAULT_HALFDUP_COLL_WINDOW 0x37 +#define DEFAULT_TX_PAUSE_TIME 0xf000 +#define DEFAULT_RX_PREPEND 0 +#define DEFAULT_PREAMBLE_LEN 7 +#define DEFAULT_TX_PAUSE_TIME_EXTD 0 +#define DEFAULT_NON_BACK_TO_BACK_IPG1 0x40 +#define DEFAULT_NON_BACK_TO_BACK_IPG2 0x60 +#define DEFAULT_MIN_IFG_ENFORCEMENT 0x50 +#define DEFAULT_BACK_TO_BACK_IPG 0x60 +#define DEFAULT_MAXIMUM_FRAME 0x600 + +/* register related defines (bits, field offsets..) */ +#define DTSEC_ID2_INT_REDUCED_OFF 0x00010000 + +#define DTSEC_ECNTRL_GMIIM 0x00000040 +#define DTSEC_ECNTRL_TBIM 0x00000020 +#define DTSEC_ECNTRL_SGMIIM 0x00000002 +#define DTSEC_ECNTRL_RPM 0x00000010 +#define DTSEC_ECNTRL_R100M 0x00000008 +#define DTSEC_ECNTRL_QSGMIIM 0x00000001 + +#define DTSEC_TCTRL_GTS 0x00000020 + +#define RCTRL_PAL_MASK 0x001f0000 +#define RCTRL_PAL_SHIFT 16 +#define RCTRL_GHTX 0x00000400 +#define RCTRL_GRS 0x00000020 +#define RCTRL_MPROM 0x00000008 +#define RCTRL_RSF 0x00000004 +#define RCTRL_UPROM 0x00000001 + +#define MACCFG1_SOFT_RESET 0x80000000 +#define MACCFG1_RX_FLOW 0x00000020 +#define MACCFG1_TX_FLOW 0x00000010 +#define MACCFG1_TX_EN 0x00000001 +#define MACCFG1_RX_EN 0x00000004 + +#define MACCFG2_NIBBLE_MODE 0x00000100 +#define MACCFG2_BYTE_MODE 0x00000200 +#define MACCFG2_PAD_CRC_EN 0x00000004 +#define MACCFG2_FULL_DUPLEX 0x00000001 +#define MACCFG2_PREAMBLE_LENGTH_MASK 0x0000f000 +#define MACCFG2_PREAMBLE_LENGTH_SHIFT 12 + +#define IPGIFG_NON_BACK_TO_BACK_IPG_1_SHIFT 24 +#define IPGIFG_NON_BACK_TO_BACK_IPG_2_SHIFT 16 +#define IPGIFG_MIN_IFG_ENFORCEMENT_SHIFT 8 + +#define IPGIFG_NON_BACK_TO_BACK_IPG_1 0x7F000000 +#define IPGIFG_NON_BACK_TO_BACK_IPG_2 0x007F0000 +#define IPGIFG_MIN_IFG_ENFORCEMENT 0x0000FF00 +#define IPGIFG_BACK_TO_BACK_IPG 0x0000007F + +#define HAFDUP_EXCESS_DEFER 0x00010000 +#define HAFDUP_COLLISION_WINDOW 0x000003ff +#define HAFDUP_RETRANSMISSION_MAX_SHIFT 12 +#define HAFDUP_RETRANSMISSION_MAX 0x0000f000 + +#define NUM_OF_HASH_REGS 8 /* Number of hash table registers */ + +#define PTV_PTE_MASK 0xffff0000 +#define PTV_PT_MASK 0x0000ffff +#define PTV_PTE_SHIFT 16 + +#define MAX_PACKET_ALIGNMENT 31 +#define MAX_INTER_PACKET_GAP 0x7f +#define MAX_RETRANSMISSION 0x0f +#define MAX_COLLISION_WINDOW 0x03ff + +/* Hash table size (32 bits*8 regs) */ +#define DTSEC_HASH_TABLE_SIZE 256 +/* Extended Hash table size (32 bits*16 regs) */ +#define EXTENDED_HASH_TABLE_SIZE 512 + +/* dTSEC Memory Map registers */ +struct dtsec_regs { + /* dTSEC General Control and Status Registers */ + u32 tsec_id; /* 0x000 ETSEC_ID register */ + u32 tsec_id2; /* 0x004 ETSEC_ID2 register */ + u32 ievent; /* 0x008 Interrupt event register */ + u32 imask; /* 0x00C Interrupt mask register */ + u32 reserved0010[1]; + u32 ecntrl; /* 0x014 E control register */ + u32 ptv; /* 0x018 Pause time value register */ + u32 tbipa; /* 0x01C TBI PHY address register */ + u32 tmr_ctrl; /* 0x020 Time-stamp Control register */ + u32 tmr_pevent; /* 0x024 Time-stamp event register */ + u32 tmr_pemask; /* 0x028 Timer event mask register */ + u32 reserved002c[5]; + u32 tctrl; /* 0x040 Transmit control register */ + u32 reserved0044[3]; + u32 rctrl; /* 0x050 Receive control register */ + u32 reserved0054[11]; + u32 igaddr[8]; /* 0x080-0x09C Individual/group address */ + u32 gaddr[8]; /* 0x0A0-0x0BC Group address registers 0-7 */ + u32 reserved00c0[16]; + u32 maccfg1; /* 0x100 MAC configuration #1 */ + u32 maccfg2; /* 0x104 MAC configuration #2 */ + u32 ipgifg; /* 0x108 IPG/IFG */ + u32 hafdup; /* 0x10C Half-duplex */ + u32 maxfrm; /* 0x110 Maximum frame */ + u32 reserved0114[10]; + u32 ifstat; /* 0x13C Interface status */ + u32 macstnaddr1; /* 0x140 Station Address,part 1 */ + u32 macstnaddr2; /* 0x144 Station Address,part 2 */ + struct { + u32 exact_match1; /* octets 1-4 */ + u32 exact_match2; /* octets 5-6 */ + } macaddr[15]; /* 0x148-0x1BC mac exact match addresses 1-15 */ + u32 reserved01c0[16]; + u32 tr64; /* 0x200 Tx and Rx 64 byte frame counter */ + u32 tr127; /* 0x204 Tx and Rx 65 to 127 byte frame counter */ + u32 tr255; /* 0x208 Tx and Rx 128 to 255 byte frame counter */ + u32 tr511; /* 0x20C Tx and Rx 256 to 511 byte frame counter */ + u32 tr1k; /* 0x210 Tx and Rx 512 to 1023 byte frame counter */ + u32 trmax; /* 0x214 Tx and Rx 1024 to 1518 byte frame counter */ + u32 trmgv; + /* 0x218 Tx and Rx 1519 to 1522 byte good VLAN frame count */ + u32 rbyt; /* 0x21C receive byte counter */ + u32 rpkt; /* 0x220 receive packet counter */ + u32 rfcs; /* 0x224 receive FCS error counter */ + u32 rmca; /* 0x228 RMCA Rx multicast packet counter */ + u32 rbca; /* 0x22C Rx broadcast packet counter */ + u32 rxcf; /* 0x230 Rx control frame packet counter */ + u32 rxpf; /* 0x234 Rx pause frame packet counter */ + u32 rxuo; /* 0x238 Rx unknown OP code counter */ + u32 raln; /* 0x23C Rx alignment error counter */ + u32 rflr; /* 0x240 Rx frame length error counter */ + u32 rcde; /* 0x244 Rx code error counter */ + u32 rcse; /* 0x248 Rx carrier sense error counter */ + u32 rund; /* 0x24C Rx undersize packet counter */ + u32 rovr; /* 0x250 Rx oversize packet counter */ + u32 rfrg; /* 0x254 Rx fragments counter */ + u32 rjbr; /* 0x258 Rx jabber counter */ + u32 rdrp; /* 0x25C Rx drop */ + u32 tbyt; /* 0x260 Tx byte counter */ + u32 tpkt; /* 0x264 Tx packet counter */ + u32 tmca; /* 0x268 Tx multicast packet counter */ + u32 tbca; /* 0x26C Tx broadcast packet counter */ + u32 txpf; /* 0x270 Tx pause control frame counter */ + u32 tdfr; /* 0x274 Tx deferral packet counter */ + u32 tedf; /* 0x278 Tx excessive deferral packet counter */ + u32 tscl; /* 0x27C Tx single collision packet counter */ + u32 tmcl; /* 0x280 Tx multiple collision packet counter */ + u32 tlcl; /* 0x284 Tx late collision packet counter */ + u32 txcl; /* 0x288 Tx excessive collision packet counter */ + u32 tncl; /* 0x28C Tx total collision counter */ + u32 reserved0290[1]; + u32 tdrp; /* 0x294 Tx drop frame counter */ + u32 tjbr; /* 0x298 Tx jabber frame counter */ + u32 tfcs; /* 0x29C Tx FCS error counter */ + u32 txcf; /* 0x2A0 Tx control frame counter */ + u32 tovr; /* 0x2A4 Tx oversize frame counter */ + u32 tund; /* 0x2A8 Tx undersize frame counter */ + u32 tfrg; /* 0x2AC Tx fragments frame counter */ + u32 car1; /* 0x2B0 carry register one register* */ + u32 car2; /* 0x2B4 carry register two register* */ + u32 cam1; /* 0x2B8 carry register one mask register */ + u32 cam2; /* 0x2BC carry register two mask register */ + u32 reserved02c0[848]; +}; + +/* struct dtsec_cfg - dTSEC configuration + * Transmit half-duplex flow control, under software control for 10/100-Mbps + * half-duplex media. If set, back pressure is applied to media by raising + * carrier. + * halfdup_retransmit: + * Number of retransmission attempts following a collision. + * If this is exceeded dTSEC aborts transmission due to excessive collisions. + * The standard specifies the attempt limit to be 15. + * halfdup_coll_window: + * The number of bytes of the frame during which collisions may occur. + * The default value of 55 corresponds to the frame byte at the end of the + * standard 512-bit slot time window. If collisions are detected after this + * byte, the late collision event is asserted and transmission of current + * frame is aborted. + * tx_pad_crc: + * Pad and append CRC. If set, the MAC pads all ransmitted short frames and + * appends a CRC to every frame regardless of padding requirement. + * tx_pause_time: + * Transmit pause time value. This pause value is used as part of the pause + * frame to be sent when a transmit pause frame is initiated. + * If set to 0 this disables transmission of pause frames. + * preamble_len: + * Length, in bytes, of the preamble field preceding each Ethernet + * start-of-frame delimiter byte. The default value of 0x7 should be used in + * order to guarantee reliable operation with IEEE 802.3 compliant hardware. + * rx_prepend: + * Packet alignment padding length. The specified number of bytes (1-31) + * of zero padding are inserted before the start of each received frame. + * For Ethernet, where optional preamble extraction is enabled, the padding + * appears before the preamble, otherwise the padding precedes the + * layer 2 header. + * + * This structure contains basic dTSEC configuration and must be passed to + * init() function. A default set of configuration values can be + * obtained by calling set_dflts(). + */ +struct dtsec_cfg { + u16 halfdup_retransmit; + u16 halfdup_coll_window; + bool tx_pad_crc; + u16 tx_pause_time; + bool ptp_tsu_en; + bool ptp_exception_en; + u32 preamble_len; + u32 rx_prepend; + u16 tx_pause_time_extd; + u16 maximum_frame; + u32 non_back_to_back_ipg1; + u32 non_back_to_back_ipg2; + u32 min_ifg_enforcement; + u32 back_to_back_ipg; +}; + +struct fman_mac { + /* pointer to dTSEC memory mapped registers */ + struct dtsec_regs __iomem *regs; + /* MAC address of device */ + u64 addr; + /* Ethernet physical interface */ + phy_interface_t phy_if; + u16 max_speed; + void *dev_id; /* device cookie used by the exception cbs */ + fman_mac_exception_cb *exception_cb; + fman_mac_exception_cb *event_cb; + /* Number of individual addresses in registers for this station */ + u8 num_of_ind_addr_in_regs; + /* pointer to driver's global address hash table */ + struct eth_hash_t *multicast_addr_hash; + /* pointer to driver's individual address hash table */ + struct eth_hash_t *unicast_addr_hash; + u8 mac_id; + u32 exceptions; + bool ptp_tsu_enabled; + bool en_tsu_err_exeption; + struct dtsec_cfg *dtsec_drv_param; + void *fm; + struct fman_rev_info fm_rev_info; + bool basex_if; + struct phy_device *tbiphy; +}; + +static void set_dflts(struct dtsec_cfg *cfg) +{ + cfg->halfdup_retransmit = DEFAULT_HALFDUP_RETRANSMIT; + cfg->halfdup_coll_window = DEFAULT_HALFDUP_COLL_WINDOW; + cfg->tx_pad_crc = true; + cfg->tx_pause_time = DEFAULT_TX_PAUSE_TIME; + /* PHY address 0 is reserved (DPAA RM) */ + cfg->rx_prepend = DEFAULT_RX_PREPEND; + cfg->ptp_tsu_en = true; + cfg->ptp_exception_en = true; + cfg->preamble_len = DEFAULT_PREAMBLE_LEN; + cfg->tx_pause_time_extd = DEFAULT_TX_PAUSE_TIME_EXTD; + cfg->non_back_to_back_ipg1 = DEFAULT_NON_BACK_TO_BACK_IPG1; + cfg->non_back_to_back_ipg2 = DEFAULT_NON_BACK_TO_BACK_IPG2; + cfg->min_ifg_enforcement = DEFAULT_MIN_IFG_ENFORCEMENT; + cfg->back_to_back_ipg = DEFAULT_BACK_TO_BACK_IPG; + cfg->maximum_frame = DEFAULT_MAXIMUM_FRAME; +} + +static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg, + phy_interface_t iface, u16 iface_speed, u8 *macaddr, + u32 exception_mask, u8 tbi_addr) +{ + bool is_rgmii, is_sgmii, is_qsgmii; + int i; + u32 tmp; + + /* Soft reset */ + iowrite32be(MACCFG1_SOFT_RESET, ®s->maccfg1); + iowrite32be(0, ®s->maccfg1); + + /* dtsec_id2 */ + tmp = ioread32be(®s->tsec_id2); + + /* check RGMII support */ + if (iface == PHY_INTERFACE_MODE_RGMII || + iface == PHY_INTERFACE_MODE_RMII) + if (tmp & DTSEC_ID2_INT_REDUCED_OFF) + return -EINVAL; + + if (iface == PHY_INTERFACE_MODE_SGMII || + iface == PHY_INTERFACE_MODE_MII) + if (tmp & DTSEC_ID2_INT_REDUCED_OFF) + return -EINVAL; + + is_rgmii = iface == PHY_INTERFACE_MODE_RGMII; + is_sgmii = iface == PHY_INTERFACE_MODE_SGMII; + is_qsgmii = iface == PHY_INTERFACE_MODE_QSGMII; + + tmp = 0; + if (is_rgmii || iface == PHY_INTERFACE_MODE_GMII) + tmp |= DTSEC_ECNTRL_GMIIM; + if (is_sgmii) + tmp |= (DTSEC_ECNTRL_SGMIIM | DTSEC_ECNTRL_TBIM); + if (is_qsgmii) + tmp |= (DTSEC_ECNTRL_SGMIIM | DTSEC_ECNTRL_TBIM | + DTSEC_ECNTRL_QSGMIIM); + if (is_rgmii) + tmp |= DTSEC_ECNTRL_RPM; + if (iface_speed == SPEED_100) + tmp |= DTSEC_ECNTRL_R100M; + + iowrite32be(tmp, ®s->ecntrl); + + tmp = 0; + + if (cfg->tx_pause_time) + tmp |= cfg->tx_pause_time; + if (cfg->tx_pause_time_extd) + tmp |= cfg->tx_pause_time_extd << PTV_PTE_SHIFT; + iowrite32be(tmp, ®s->ptv); + + tmp = 0; + tmp |= (cfg->rx_prepend << RCTRL_PAL_SHIFT) & RCTRL_PAL_MASK; + /* Accept short frames */ + tmp |= RCTRL_RSF; + + iowrite32be(tmp, ®s->rctrl); + + /* Assign a Phy Address to the TBI (TBIPA). + * Done also in cases where TBI is not selected to avoid conflict with + * the external PHY's Physical address + */ + iowrite32be(tbi_addr, ®s->tbipa); + + iowrite32be(0, ®s->tmr_ctrl); + + if (cfg->ptp_tsu_en) { + tmp = 0; + tmp |= TMR_PEVENT_TSRE; + iowrite32be(tmp, ®s->tmr_pevent); + + if (cfg->ptp_exception_en) { + tmp = 0; + tmp |= TMR_PEMASK_TSREEN; + iowrite32be(tmp, ®s->tmr_pemask); + } + } + + tmp = 0; + tmp |= MACCFG1_RX_FLOW; + tmp |= MACCFG1_TX_FLOW; + iowrite32be(tmp, ®s->maccfg1); + + tmp = 0; + + if (iface_speed < SPEED_1000) + tmp |= MACCFG2_NIBBLE_MODE; + else if (iface_speed == SPEED_1000) + tmp |= MACCFG2_BYTE_MODE; + + tmp |= (cfg->preamble_len << MACCFG2_PREAMBLE_LENGTH_SHIFT) & + MACCFG2_PREAMBLE_LENGTH_MASK; + if (cfg->tx_pad_crc) + tmp |= MACCFG2_PAD_CRC_EN; + /* Full Duplex */ + tmp |= MACCFG2_FULL_DUPLEX; + iowrite32be(tmp, ®s->maccfg2); + + tmp = (((cfg->non_back_to_back_ipg1 << + IPGIFG_NON_BACK_TO_BACK_IPG_1_SHIFT) + & IPGIFG_NON_BACK_TO_BACK_IPG_1) + | ((cfg->non_back_to_back_ipg2 << + IPGIFG_NON_BACK_TO_BACK_IPG_2_SHIFT) + & IPGIFG_NON_BACK_TO_BACK_IPG_2) + | ((cfg->min_ifg_enforcement << IPGIFG_MIN_IFG_ENFORCEMENT_SHIFT) + & IPGIFG_MIN_IFG_ENFORCEMENT) + | (cfg->back_to_back_ipg & IPGIFG_BACK_TO_BACK_IPG)); + iowrite32be(tmp, ®s->ipgifg); + + tmp = 0; + tmp |= HAFDUP_EXCESS_DEFER; + tmp |= ((cfg->halfdup_retransmit << HAFDUP_RETRANSMISSION_MAX_SHIFT) + & HAFDUP_RETRANSMISSION_MAX); + tmp |= (cfg->halfdup_coll_window & HAFDUP_COLLISION_WINDOW); + + iowrite32be(tmp, ®s->hafdup); + + /* Initialize Maximum frame length */ + iowrite32be(cfg->maximum_frame, ®s->maxfrm); + + iowrite32be(0xffffffff, ®s->cam1); + iowrite32be(0xffffffff, ®s->cam2); + + iowrite32be(exception_mask, ®s->imask); + + iowrite32be(0xffffffff, ®s->ievent); + + tmp = (u32)((macaddr[5] << 24) | + (macaddr[4] << 16) | (macaddr[3] << 8) | macaddr[2]); + iowrite32be(tmp, ®s->macstnaddr1); + + tmp = (u32)((macaddr[1] << 24) | (macaddr[0] << 16)); + iowrite32be(tmp, ®s->macstnaddr2); + + /* HASH */ + for (i = 0; i < NUM_OF_HASH_REGS; i++) { + /* Initialize IADDRx */ + iowrite32be(0, ®s->igaddr[i]); + /* Initialize GADDRx */ + iowrite32be(0, ®s->gaddr[i]); + } + + return 0; +} + +static void set_mac_address(struct dtsec_regs __iomem *regs, u8 *adr) +{ + u32 tmp; + + tmp = (u32)((adr[5] << 24) | + (adr[4] << 16) | (adr[3] << 8) | adr[2]); + iowrite32be(tmp, ®s->macstnaddr1); + + tmp = (u32)((adr[1] << 24) | (adr[0] << 16)); + iowrite32be(tmp, ®s->macstnaddr2); +} + +static void set_bucket(struct dtsec_regs __iomem *regs, int bucket, + bool enable) +{ + int reg_idx = (bucket >> 5) & 0xf; + int bit_idx = bucket & 0x1f; + u32 bit_mask = 0x80000000 >> bit_idx; + u32 __iomem *reg; + + if (reg_idx > 7) + reg = ®s->gaddr[reg_idx - 8]; + else + reg = ®s->igaddr[reg_idx]; + + if (enable) + iowrite32be(ioread32be(reg) | bit_mask, reg); + else + iowrite32be(ioread32be(reg) & (~bit_mask), reg); +} + +static int check_init_parameters(struct fman_mac *dtsec) +{ + if (dtsec->max_speed >= SPEED_10000) { + pr_err("1G MAC driver supports 1G or lower speeds\n"); + return -EINVAL; + } + if (dtsec->addr == 0) { + pr_err("Ethernet MAC Must have a valid MAC Address\n"); + return -EINVAL; + } + if ((dtsec->dtsec_drv_param)->rx_prepend > + MAX_PACKET_ALIGNMENT) { + pr_err("packetAlignmentPadding can't be > than %d\n", + MAX_PACKET_ALIGNMENT); + return -EINVAL; + } + if (((dtsec->dtsec_drv_param)->non_back_to_back_ipg1 > + MAX_INTER_PACKET_GAP) || + ((dtsec->dtsec_drv_param)->non_back_to_back_ipg2 > + MAX_INTER_PACKET_GAP) || + ((dtsec->dtsec_drv_param)->back_to_back_ipg > + MAX_INTER_PACKET_GAP)) { + pr_err("Inter packet gap can't be greater than %d\n", + MAX_INTER_PACKET_GAP); + return -EINVAL; + } + if ((dtsec->dtsec_drv_param)->halfdup_retransmit > + MAX_RETRANSMISSION) { + pr_err("maxRetransmission can't be greater than %d\n", + MAX_RETRANSMISSION); + return -EINVAL; + } + if ((dtsec->dtsec_drv_param)->halfdup_coll_window > + MAX_COLLISION_WINDOW) { + pr_err("collisionWindow can't be greater than %d\n", + MAX_COLLISION_WINDOW); + return -EINVAL; + /* If Auto negotiation process is disabled, need to set up the PHY + * using the MII Management Interface + */ + } + if (!dtsec->exception_cb) { + pr_err("uninitialized exception_cb\n"); + return -EINVAL; + } + if (!dtsec->event_cb) { + pr_err("uninitialized event_cb\n"); + return -EINVAL; + } + + return 0; +} + +static int get_exception_flag(enum fman_mac_exceptions exception) +{ + u32 bit_mask; + + switch (exception) { + case FM_MAC_EX_1G_BAB_RX: + bit_mask = DTSEC_IMASK_BREN; + break; + case FM_MAC_EX_1G_RX_CTL: + bit_mask = DTSEC_IMASK_RXCEN; + break; + case FM_MAC_EX_1G_GRATEFUL_TX_STP_COMPLET: + bit_mask = DTSEC_IMASK_GTSCEN; + break; + case FM_MAC_EX_1G_BAB_TX: + bit_mask = DTSEC_IMASK_BTEN; + break; + case FM_MAC_EX_1G_TX_CTL: + bit_mask = DTSEC_IMASK_TXCEN; + break; + case FM_MAC_EX_1G_TX_ERR: + bit_mask = DTSEC_IMASK_TXEEN; + break; + case FM_MAC_EX_1G_LATE_COL: + bit_mask = DTSEC_IMASK_LCEN; + break; + case FM_MAC_EX_1G_COL_RET_LMT: + bit_mask = DTSEC_IMASK_CRLEN; + break; + case FM_MAC_EX_1G_TX_FIFO_UNDRN: + bit_mask = DTSEC_IMASK_XFUNEN; + break; + case FM_MAC_EX_1G_MAG_PCKT: + bit_mask = DTSEC_IMASK_MAGEN; + break; + case FM_MAC_EX_1G_MII_MNG_RD_COMPLET: + bit_mask = DTSEC_IMASK_MMRDEN; + break; + case FM_MAC_EX_1G_MII_MNG_WR_COMPLET: + bit_mask = DTSEC_IMASK_MMWREN; + break; + case FM_MAC_EX_1G_GRATEFUL_RX_STP_COMPLET: + bit_mask = DTSEC_IMASK_GRSCEN; + break; + case FM_MAC_EX_1G_DATA_ERR: + bit_mask = DTSEC_IMASK_TDPEEN; + break; + case FM_MAC_EX_1G_RX_MIB_CNT_OVFL: + bit_mask = DTSEC_IMASK_MSROEN; + break; + default: + bit_mask = 0; + break; + } + + return bit_mask; +} + +static bool is_init_done(struct dtsec_cfg *dtsec_drv_params) +{ + /* Checks if dTSEC driver parameters were initialized */ + if (!dtsec_drv_params) + return true; + + return false; +} + +static u16 dtsec_get_max_frame_length(struct fman_mac *dtsec) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + + if (is_init_done(dtsec->dtsec_drv_param)) + return 0; + + return (u16)ioread32be(®s->maxfrm); +} + +static void dtsec_isr(void *handle) +{ + struct fman_mac *dtsec = (struct fman_mac *)handle; + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 event; + + /* do not handle MDIO events */ + event = ioread32be(®s->ievent) & + (u32)(~(DTSEC_IMASK_MMRDEN | DTSEC_IMASK_MMWREN)); + + event &= ioread32be(®s->imask); + + iowrite32be(event, ®s->ievent); + + if (event & DTSEC_IMASK_BREN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_BAB_RX); + if (event & DTSEC_IMASK_RXCEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_RX_CTL); + if (event & DTSEC_IMASK_GTSCEN) + dtsec->exception_cb(dtsec->dev_id, + FM_MAC_EX_1G_GRATEFUL_TX_STP_COMPLET); + if (event & DTSEC_IMASK_BTEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_BAB_TX); + if (event & DTSEC_IMASK_TXCEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_TX_CTL); + if (event & DTSEC_IMASK_TXEEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_TX_ERR); + if (event & DTSEC_IMASK_LCEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_LATE_COL); + if (event & DTSEC_IMASK_CRLEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_COL_RET_LMT); + if (event & DTSEC_IMASK_XFUNEN) { + /* FM_TX_LOCKUP_ERRATA_DTSEC6 Errata workaround */ + if (dtsec->fm_rev_info.major == 2) { + u32 tpkt1, tmp_reg1, tpkt2, tmp_reg2, i; + /* a. Write 0x00E0_0C00 to DTSEC_ID + * This is a read only register + * b. Read and save the value of TPKT + */ + tpkt1 = ioread32be(®s->tpkt); + + /* c. Read the register at dTSEC address offset 0x32C */ + tmp_reg1 = ioread32be(®s->reserved02c0[27]); + + /* d. Compare bits [9:15] to bits [25:31] of the + * register at address offset 0x32C. + */ + if ((tmp_reg1 & 0x007F0000) != + (tmp_reg1 & 0x0000007F)) { + /* If they are not equal, save the value of + * this register and wait for at least + * MAXFRM*16 ns + */ + usleep_range((u32)(min + (dtsec_get_max_frame_length(dtsec) * + 16 / 1000, 1)), (u32) + (min(dtsec_get_max_frame_length + (dtsec) * 16 / 1000, 1) + 1)); + } + + /* e. Read and save TPKT again and read the register + * at dTSEC address offset 0x32C again + */ + tpkt2 = ioread32be(®s->tpkt); + tmp_reg2 = ioread32be(®s->reserved02c0[27]); + + /* f. Compare the value of TPKT saved in step b to + * value read in step e. Also compare bits [9:15] of + * the register at offset 0x32C saved in step d to the + * value of bits [9:15] saved in step e. If the two + * registers values are unchanged, then the transmit + * portion of the dTSEC controller is locked up and + * the user should proceed to the recover sequence. + */ + if ((tpkt1 == tpkt2) && ((tmp_reg1 & 0x007F0000) == + (tmp_reg2 & 0x007F0000))) { + /* recover sequence */ + + /* a.Write a 1 to RCTRL[GRS] */ + + iowrite32be(ioread32be(®s->rctrl) | + RCTRL_GRS, ®s->rctrl); + + /* b.Wait until IEVENT[GRSC]=1, or at least + * 100 us has elapsed. + */ + for (i = 0; i < 100; i++) { + if (ioread32be(®s->ievent) & + DTSEC_IMASK_GRSCEN) + break; + udelay(1); + } + if (ioread32be(®s->ievent) & + DTSEC_IMASK_GRSCEN) + iowrite32be(DTSEC_IMASK_GRSCEN, + ®s->ievent); + else + pr_debug("Rx lockup due to Tx lockup\n"); + + /* c.Write a 1 to bit n of FM_RSTC + * (offset 0x0CC of FPM) + */ + fman_reset_mac(dtsec->fm, dtsec->mac_id); + + /* d.Wait 4 Tx clocks (32 ns) */ + udelay(1); + + /* e.Write a 0 to bit n of FM_RSTC. */ + /* cleared by FMAN + */ + } + } + + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_TX_FIFO_UNDRN); + } + if (event & DTSEC_IMASK_MAGEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_MAG_PCKT); + if (event & DTSEC_IMASK_GRSCEN) + dtsec->exception_cb(dtsec->dev_id, + FM_MAC_EX_1G_GRATEFUL_RX_STP_COMPLET); + if (event & DTSEC_IMASK_TDPEEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_DATA_ERR); + if (event & DTSEC_IMASK_RDPEEN) + dtsec->exception_cb(dtsec->dev_id, FM_MAC_1G_RX_DATA_ERR); + + /* masked interrupts */ + WARN_ON(event & DTSEC_IMASK_ABRTEN); + WARN_ON(event & DTSEC_IMASK_IFERREN); +} + +static void dtsec_1588_isr(void *handle) +{ + struct fman_mac *dtsec = (struct fman_mac *)handle; + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 event; + + if (dtsec->ptp_tsu_enabled) { + event = ioread32be(®s->tmr_pevent); + event &= ioread32be(®s->tmr_pemask); + + if (event) { + iowrite32be(event, ®s->tmr_pevent); + WARN_ON(event & TMR_PEVENT_TSRE); + dtsec->exception_cb(dtsec->dev_id, + FM_MAC_EX_1G_1588_TS_RX_ERR); + } + } +} + +static void free_init_resources(struct fman_mac *dtsec) +{ + fman_unregister_intr(dtsec->fm, FMAN_MOD_MAC, dtsec->mac_id, + FMAN_INTR_TYPE_ERR); + fman_unregister_intr(dtsec->fm, FMAN_MOD_MAC, dtsec->mac_id, + FMAN_INTR_TYPE_NORMAL); + + /* release the driver's group hash table */ + free_hash_table(dtsec->multicast_addr_hash); + dtsec->multicast_addr_hash = NULL; + + /* release the driver's individual hash table */ + free_hash_table(dtsec->unicast_addr_hash); + dtsec->unicast_addr_hash = NULL; +} + +int dtsec_cfg_max_frame_len(struct fman_mac *dtsec, u16 new_val) +{ + if (is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + dtsec->dtsec_drv_param->maximum_frame = new_val; + + return 0; +} + +int dtsec_cfg_pad_and_crc(struct fman_mac *dtsec, bool new_val) +{ + if (is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + dtsec->dtsec_drv_param->tx_pad_crc = new_val; + + return 0; +} + +int dtsec_enable(struct fman_mac *dtsec, enum comm_mode mode) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + /* Enable */ + tmp = ioread32be(®s->maccfg1); + if (mode & COMM_MODE_RX) + tmp |= MACCFG1_RX_EN; + if (mode & COMM_MODE_TX) + tmp |= MACCFG1_TX_EN; + + iowrite32be(tmp, ®s->maccfg1); + + /* Graceful start - clear the graceful receive stop bit */ + if (mode & COMM_MODE_TX) + iowrite32be(ioread32be(®s->tctrl) & ~DTSEC_TCTRL_GTS, + ®s->tctrl); + if (mode & COMM_MODE_RX) + iowrite32be(ioread32be(®s->rctrl) & ~RCTRL_GRS, + ®s->rctrl); + + return 0; +} + +int dtsec_disable(struct fman_mac *dtsec, enum comm_mode mode) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + /* Gracefull stop - Assert the graceful transmit stop bit */ + if (mode & COMM_MODE_RX) { + tmp = ioread32be(®s->rctrl) | RCTRL_GRS; + iowrite32be(tmp, ®s->rctrl); + + if (dtsec->fm_rev_info.major == 2) + usleep_range(100, 200); + else + udelay(10); + } + + if (mode & COMM_MODE_TX) { + if (dtsec->fm_rev_info.major == 2) + pr_debug("GTS not supported due to DTSEC_A004 errata.\n"); + else + pr_debug("GTS not supported due to DTSEC_A0014 errata.\n"); + } + + tmp = ioread32be(®s->maccfg1); + if (mode & COMM_MODE_RX) + tmp &= ~MACCFG1_RX_EN; + if (mode & COMM_MODE_TX) + tmp &= ~MACCFG1_TX_EN; + + iowrite32be(tmp, ®s->maccfg1); + + return 0; +} + +int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, + u8 __maybe_unused priority, + u16 pause_time, u16 __maybe_unused thresh_time) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 ptv = 0; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + /* FM_BAD_TX_TS_IN_B_2_B_ERRATA_DTSEC_A003 Errata workaround */ + if (dtsec->fm_rev_info.major == 2) + if (pause_time < 0 && pause_time <= 320) { + pr_warn("pause-time: %d illegal.Should be > 320\n", + pause_time); + return -EINVAL; + } + + if (pause_time) { + ptv = ioread32be(®s->ptv); + ptv &= PTV_PTE_MASK; + ptv |= pause_time & PTV_PT_MASK; + iowrite32be(ptv, ®s->ptv); + + /* trigger the transmission of a flow-control pause frame */ + iowrite32be(ioread32be(®s->maccfg1) | MACCFG1_TX_FLOW, + ®s->maccfg1); + } else + iowrite32be(ioread32be(®s->maccfg1) & ~MACCFG1_TX_FLOW, + ®s->maccfg1); + + return 0; +} + +int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->maccfg1); + if (en) + tmp |= MACCFG1_RX_FLOW; + else + tmp &= ~MACCFG1_RX_FLOW; + iowrite32be(tmp, ®s->maccfg1); + + return 0; +} + +int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) +{ + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + /* Initialize MAC Station Address registers (1 & 2) + * Station address have to be swapped (big endian to little endian + */ + dtsec->addr = ENET_ADDR_TO_UINT64(*enet_addr); + set_mac_address(dtsec->regs, (u8 *)(*enet_addr)); + + return 0; +} + +int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + struct eth_hash_entry *hash_entry; + u64 addr; + s32 bucket; + u32 crc = 0xFFFFFFFF; + bool mcast, ghtx; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + addr = ENET_ADDR_TO_UINT64(*eth_addr); + + ghtx = (bool)((ioread32be(®s->rctrl) & RCTRL_GHTX) ? true : false); + mcast = (bool)((addr & MAC_GROUP_ADDRESS) ? true : false); + + /* Cannot handle unicast mac addr when GHTX is on */ + if (ghtx && !mcast) { + pr_err("Could not compute hash bucket\n"); + return -EINVAL; + } + crc = crc32_le(crc, (u8 *)eth_addr, ETH_ALEN); + crc = bitrev32(crc); + + /* considering the 9 highest order bits in crc H[8:0]: + *if ghtx = 0 H[8:6] (highest order 3 bits) identify the hash register + *and H[5:1] (next 5 bits) identify the hash bit + *if ghts = 1 H[8:5] (highest order 4 bits) identify the hash register + *and H[4:0] (next 5 bits) identify the hash bit. + * + *In bucket index output the low 5 bits identify the hash register + *bit, while the higher 4 bits identify the hash register + */ + + if (ghtx) { + bucket = (s32)((crc >> 23) & 0x1ff); + } else { + bucket = (s32)((crc >> 24) & 0xff); + /* if !ghtx and mcast the bit must be set in gaddr instead of + *igaddr. + */ + if (mcast) + bucket += 0x100; + } + + set_bucket(dtsec->regs, bucket, true); + + /* Create element to be added to the driver hash table */ + hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + if (!hash_entry) + return -ENOMEM; + hash_entry->addr = addr; + INIT_LIST_HEAD(&hash_entry->node); + + if (addr & MAC_GROUP_ADDRESS) + /* Group Address */ + list_add_tail(&hash_entry->node, + &dtsec->multicast_addr_hash->lsts[bucket]); + else + list_add_tail(&hash_entry->node, + &dtsec->unicast_addr_hash->lsts[bucket]); + + return 0; +} + +int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + struct list_head *pos; + struct eth_hash_entry *hash_entry = NULL; + u64 addr; + s32 bucket; + u32 crc = 0xFFFFFFFF; + bool mcast, ghtx; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + addr = ENET_ADDR_TO_UINT64(*eth_addr); + + ghtx = (bool)((ioread32be(®s->rctrl) & RCTRL_GHTX) ? true : false); + mcast = (bool)((addr & MAC_GROUP_ADDRESS) ? true : false); + + /* Cannot handle unicast mac addr when GHTX is on */ + if (ghtx && !mcast) { + pr_err("Could not compute hash bucket\n"); + return -EINVAL; + } + crc = crc32_le(crc, (u8 *)eth_addr, ETH_ALEN); + crc = bitrev32(crc); + + if (ghtx) { + bucket = (s32)((crc >> 23) & 0x1ff); + } else { + bucket = (s32)((crc >> 24) & 0xff); + /* if !ghtx and mcast the bit must be set + * in gaddr instead of igaddr. + */ + if (mcast) + bucket += 0x100; + } + + if (addr & MAC_GROUP_ADDRESS) { + /* Group Address */ + list_for_each(pos, + &dtsec->multicast_addr_hash->lsts[bucket]) { + hash_entry = ETH_HASH_ENTRY_OBJ(pos); + if (hash_entry->addr == addr) { + list_del_init(&hash_entry->node); + kfree(hash_entry); + break; + } + } + if (list_empty(&dtsec->multicast_addr_hash->lsts[bucket])) + set_bucket(dtsec->regs, bucket, false); + } else { + /* Individual Address */ + list_for_each(pos, + &dtsec->unicast_addr_hash->lsts[bucket]) { + hash_entry = ETH_HASH_ENTRY_OBJ(pos); + if (hash_entry->addr == addr) { + list_del_init(&hash_entry->node); + kfree(hash_entry); + break; + } + } + if (list_empty(&dtsec->unicast_addr_hash->lsts[bucket])) + set_bucket(dtsec->regs, bucket, false); + } + + /* address does not exist */ + WARN_ON(!hash_entry); + + return 0; +} + +int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + /* Set unicast promiscuous */ + tmp = ioread32be(®s->rctrl); + if (new_val) + tmp |= RCTRL_UPROM; + else + tmp &= ~RCTRL_UPROM; + + iowrite32be(tmp, ®s->rctrl); + + /* Set multicast promiscuous */ + tmp = ioread32be(®s->rctrl); + if (new_val) + tmp |= RCTRL_MPROM; + else + tmp &= ~RCTRL_MPROM; + + iowrite32be(tmp, ®s->rctrl); + + return 0; +} + +int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->maccfg2); + + /* Full Duplex */ + tmp |= MACCFG2_FULL_DUPLEX; + + tmp &= ~(MACCFG2_NIBBLE_MODE | MACCFG2_BYTE_MODE); + if (speed < SPEED_1000) + tmp |= MACCFG2_NIBBLE_MODE; + else if (speed == SPEED_1000) + tmp |= MACCFG2_BYTE_MODE; + iowrite32be(tmp, ®s->maccfg2); + + tmp = ioread32be(®s->ecntrl); + if (speed == SPEED_100) + tmp |= DTSEC_ECNTRL_R100M; + else + tmp &= ~DTSEC_ECNTRL_R100M; + iowrite32be(tmp, ®s->ecntrl); + + return 0; +} + +int dtsec_restart_autoneg(struct fman_mac *dtsec) +{ + u16 tmp_reg16; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + tmp_reg16 = phy_read(dtsec->tbiphy, MII_BMCR); + + tmp_reg16 &= ~(BMCR_SPEED100 | BMCR_SPEED1000); + tmp_reg16 |= (BMCR_ANENABLE | BMCR_ANRESTART | + BMCR_FULLDPLX | BMCR_SPEED1000); + + phy_write(dtsec->tbiphy, MII_BMCR, tmp_reg16); + + return 0; +} + +int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + *mac_version = ioread32be(®s->tsec_id); + + return 0; +} + +int dtsec_set_exception(struct fman_mac *dtsec, + enum fman_mac_exceptions exception, bool enable) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 bit_mask = 0; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + if (exception != FM_MAC_EX_1G_1588_TS_RX_ERR) { + bit_mask = get_exception_flag(exception); + if (bit_mask) { + if (enable) + dtsec->exceptions |= bit_mask; + else + dtsec->exceptions &= ~bit_mask; + } else { + pr_err("Undefined exception\n"); + return -EINVAL; + } + if (enable) + iowrite32be(ioread32be(®s->imask) | bit_mask, + ®s->imask); + else + iowrite32be(ioread32be(®s->imask) & ~bit_mask, + ®s->imask); + } else { + if (!dtsec->ptp_tsu_enabled) { + pr_err("Exception valid for 1588 only\n"); + return -EINVAL; + } + switch (exception) { + case FM_MAC_EX_1G_1588_TS_RX_ERR: + if (enable) { + dtsec->en_tsu_err_exeption = true; + iowrite32be(ioread32be(®s->tmr_pemask) | + TMR_PEMASK_TSREEN, + ®s->tmr_pemask); + } else { + dtsec->en_tsu_err_exeption = false; + iowrite32be(ioread32be(®s->tmr_pemask) & + ~TMR_PEMASK_TSREEN, + ®s->tmr_pemask); + } + break; + default: + pr_err("Undefined exception\n"); + return -EINVAL; + } + } + + return 0; +} + +int dtsec_init(struct fman_mac *dtsec) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + struct dtsec_cfg *dtsec_drv_param; + int err; + u16 max_frm_ln; + enet_addr_t eth_addr; + + if (is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + if (DEFAULT_RESET_ON_INIT && + (fman_reset_mac(dtsec->fm, dtsec->mac_id) != 0)) { + pr_err("Can't reset MAC!\n"); + return -EINVAL; + } + + err = check_init_parameters(dtsec); + if (err) + return err; + + dtsec_drv_param = dtsec->dtsec_drv_param; + + MAKE_ENET_ADDR_FROM_UINT64(dtsec->addr, eth_addr); + + err = init(dtsec->regs, dtsec_drv_param, dtsec->phy_if, + dtsec->max_speed, (u8 *)eth_addr, dtsec->exceptions, + dtsec->tbiphy->addr); + if (err) { + free_init_resources(dtsec); + pr_err("DTSEC version doesn't support this i/f mode\n"); + return err; + } + + if (dtsec->phy_if == PHY_INTERFACE_MODE_SGMII) { + u16 tmp_reg16; + + /* Configure the TBI PHY Control Register */ + tmp_reg16 = TBICON_CLK_SELECT | TBICON_SOFT_RESET; + phy_write(dtsec->tbiphy, MII_TBICON, tmp_reg16); + + tmp_reg16 = TBICON_CLK_SELECT; + phy_write(dtsec->tbiphy, MII_TBICON, tmp_reg16); + + tmp_reg16 = (BMCR_RESET | BMCR_ANENABLE | + BMCR_FULLDPLX | BMCR_SPEED1000); + phy_write(dtsec->tbiphy, MII_BMCR, tmp_reg16); + + if (dtsec->basex_if) + tmp_reg16 = TBIANA_1000X; + else + tmp_reg16 = TBIANA_SGMII; + phy_write(dtsec->tbiphy, MII_ADVERTISE, tmp_reg16); + + tmp_reg16 = (BMCR_ANENABLE | BMCR_ANRESTART | + BMCR_FULLDPLX | BMCR_SPEED1000); + + phy_write(dtsec->tbiphy, MII_BMCR, tmp_reg16); + } + + /* Max Frame Length */ + max_frm_ln = (u16)ioread32be(®s->maxfrm); + err = fman_set_mac_max_frame(dtsec->fm, dtsec->mac_id, max_frm_ln); + if (err) { + pr_err("Setting max frame length failed\n"); + free_init_resources(dtsec); + return -EINVAL; + } + + dtsec->multicast_addr_hash = + alloc_hash_table(EXTENDED_HASH_TABLE_SIZE); + if (!dtsec->multicast_addr_hash) { + free_init_resources(dtsec); + pr_err("MC hash table is failed\n"); + return -ENOMEM; + } + + dtsec->unicast_addr_hash = alloc_hash_table(DTSEC_HASH_TABLE_SIZE); + if (!dtsec->unicast_addr_hash) { + free_init_resources(dtsec); + pr_err("UC hash table is failed\n"); + return -ENOMEM; + } + + /* register err intr handler for dtsec to FPM (err) */ + fman_register_intr(dtsec->fm, FMAN_MOD_MAC, dtsec->mac_id, + FMAN_INTR_TYPE_ERR, dtsec_isr, dtsec); + /* register 1588 intr handler for TMR to FPM (normal) */ + fman_register_intr(dtsec->fm, FMAN_MOD_MAC, dtsec->mac_id, + FMAN_INTR_TYPE_NORMAL, dtsec_1588_isr, dtsec); + + kfree(dtsec_drv_param); + dtsec->dtsec_drv_param = NULL; + + return 0; +} + +int dtsec_free(struct fman_mac *dtsec) +{ + free_init_resources(dtsec); + + kfree(dtsec->dtsec_drv_param); + dtsec->dtsec_drv_param = NULL; + kfree(dtsec); + + return 0; +} + +struct fman_mac *dtsec_config(struct fman_mac_params *params) +{ + struct fman_mac *dtsec; + struct dtsec_cfg *dtsec_drv_param; + void __iomem *base_addr; + + base_addr = params->base_addr; + + /* allocate memory for the UCC GETH data structure. */ + dtsec = kzalloc(sizeof(*dtsec), GFP_KERNEL); + if (!dtsec) + return NULL; + + /* allocate memory for the d_tsec driver parameters data structure. */ + dtsec_drv_param = kzalloc(sizeof(*dtsec_drv_param), GFP_KERNEL); + if (!dtsec_drv_param) + goto err_dtsec; + + /* Plant parameter structure pointer */ + dtsec->dtsec_drv_param = dtsec_drv_param; + + set_dflts(dtsec_drv_param); + + dtsec->regs = base_addr; + dtsec->addr = ENET_ADDR_TO_UINT64(params->addr); + dtsec->max_speed = params->max_speed; + dtsec->phy_if = params->phy_if; + dtsec->mac_id = params->mac_id; + dtsec->exceptions = (DTSEC_IMASK_BREN | + DTSEC_IMASK_RXCEN | + DTSEC_IMASK_BTEN | + DTSEC_IMASK_TXCEN | + DTSEC_IMASK_TXEEN | + DTSEC_IMASK_ABRTEN | + DTSEC_IMASK_LCEN | + DTSEC_IMASK_CRLEN | + DTSEC_IMASK_XFUNEN | + DTSEC_IMASK_IFERREN | + DTSEC_IMASK_MAGEN | + DTSEC_IMASK_TDPEEN | + DTSEC_IMASK_RDPEEN); + dtsec->exception_cb = params->exception_cb; + dtsec->event_cb = params->event_cb; + dtsec->dev_id = params->dev_id; + dtsec->ptp_tsu_enabled = dtsec->dtsec_drv_param->ptp_tsu_en; + dtsec->en_tsu_err_exeption = dtsec->dtsec_drv_param->ptp_exception_en; + + dtsec->fm = params->fm; + dtsec->basex_if = params->basex_if; + + if (!params->internal_phy_node) { + pr_err("TBI PHY node is not available\n"); + goto err_dtsec_drv_param; + } + + dtsec->tbiphy = of_phy_find_device(params->internal_phy_node); + if (!dtsec->tbiphy) { + pr_err("of_phy_find_device (TBI PHY) failed\n"); + put_device(&dtsec->tbiphy->dev); + goto err_dtsec_drv_param; + } + + put_device(&dtsec->tbiphy->dev); + + /* Save FMan revision */ + fman_get_revision(dtsec->fm, &dtsec->fm_rev_info); + + return dtsec; + +err_dtsec_drv_param: + kfree(dtsec_drv_param); +err_dtsec: + kfree(dtsec); + return NULL; +} diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h new file mode 100644 index 0000000000000..c4467c0720586 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -0,0 +1,59 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __DTSEC_H +#define __DTSEC_H + +#include "fman_mac.h" + +struct fman_mac *dtsec_config(struct fman_mac_params *params); +int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val); +int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr); +int dtsec_adjust_link(struct fman_mac *dtsec, + u16 speed); +int dtsec_restart_autoneg(struct fman_mac *dtsec); +int dtsec_cfg_max_frame_len(struct fman_mac *dtsec, u16 new_val); +int dtsec_cfg_pad_and_crc(struct fman_mac *dtsec, bool new_val); +int dtsec_enable(struct fman_mac *dtsec, enum comm_mode mode); +int dtsec_disable(struct fman_mac *dtsec, enum comm_mode mode); +int dtsec_init(struct fman_mac *dtsec); +int dtsec_free(struct fman_mac *dtsec); +int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en); +int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, u8 priority, + u16 pause_time, u16 thresh_time); +int dtsec_set_exception(struct fman_mac *dtsec, + enum fman_mac_exceptions exception, bool enable); +int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); +int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); +int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version); + +#endif /* __DTSEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h new file mode 100644 index 0000000000000..8ddeedbcef9ce --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_mac.h @@ -0,0 +1,278 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/* FM MAC ... */ +#ifndef __FM_MAC_H +#define __FM_MAC_H + +#include "fman.h" + +#include <linux/slab.h> +#include <linux/phy.h> +#include <linux/if_ether.h> + +struct fman_mac; + +/* Ethernet Address */ +typedef u8 enet_addr_t[ETH_ALEN]; + +#define ENET_ADDR_TO_UINT64(_enet_addr) \ + (u64)(((u64)(_enet_addr)[0] << 40) | \ + ((u64)(_enet_addr)[1] << 32) | \ + ((u64)(_enet_addr)[2] << 24) | \ + ((u64)(_enet_addr)[3] << 16) | \ + ((u64)(_enet_addr)[4] << 8) | \ + ((u64)(_enet_addr)[5])) + +#define MAKE_ENET_ADDR_FROM_UINT64(_addr64, _enet_addr) \ + do { \ + int i; \ + for (i = 0; i < ETH_ALEN; i++) \ + (_enet_addr)[i] = \ + (u8)((_addr64) >> ((5 - i) * 8)); \ + } while (0) + +/* defaults */ +#define DEFAULT_RESET_ON_INIT false + +/* PFC defines */ +#define FSL_FM_PAUSE_TIME_ENABLE 0xf000 +#define FSL_FM_PAUSE_TIME_DISABLE 0 +#define FSL_FM_PAUSE_THRESH_DEFAULT 0 + +#define FM_MAC_NO_PFC 0xff + +/* HASH defines */ +#define ETH_HASH_ENTRY_OBJ(ptr) \ + hlist_entry_safe(ptr, struct eth_hash_entry, node) + +/* Enumeration (bit flags) of communication modes (Transmit, + * receive or both). + */ +enum comm_mode { + COMM_MODE_NONE = 0, /* No transmit/receive communication */ + COMM_MODE_RX = 1, /* Only receive communication */ + COMM_MODE_TX = 2, /* Only transmit communication */ + COMM_MODE_RX_AND_TX = 3 /* Both transmit and receive communication */ +}; + +/* FM MAC Exceptions */ +enum fman_mac_exceptions { + FM_MAC_EX_10G_MDIO_SCAN_EVENT = 0 + /* 10GEC MDIO scan event interrupt */ + , FM_MAC_EX_10G_MDIO_CMD_CMPL + /* 10GEC MDIO command completion interrupt */ + , FM_MAC_EX_10G_REM_FAULT + /* 10GEC, mEMAC Remote fault interrupt */ + , FM_MAC_EX_10G_LOC_FAULT + /* 10GEC, mEMAC Local fault interrupt */ + , FM_MAC_EX_10G_TX_ECC_ER + /* 10GEC, mEMAC Transmit frame ECC error interrupt */ + , FM_MAC_EX_10G_TX_FIFO_UNFL + /* 10GEC, mEMAC Transmit FIFO underflow interrupt */ + , FM_MAC_EX_10G_TX_FIFO_OVFL + /* 10GEC, mEMAC Transmit FIFO overflow interrupt */ + , FM_MAC_EX_10G_TX_ER + /* 10GEC Transmit frame error interrupt */ + , FM_MAC_EX_10G_RX_FIFO_OVFL + /* 10GEC, mEMAC Receive FIFO overflow interrupt */ + , FM_MAC_EX_10G_RX_ECC_ER + /* 10GEC, mEMAC Receive frame ECC error interrupt */ + , FM_MAC_EX_10G_RX_JAB_FRM + /* 10GEC Receive jabber frame interrupt */ + , FM_MAC_EX_10G_RX_OVRSZ_FRM + /* 10GEC Receive oversized frame interrupt */ + , FM_MAC_EX_10G_RX_RUNT_FRM + /* 10GEC Receive runt frame interrupt */ + , FM_MAC_EX_10G_RX_FRAG_FRM + /* 10GEC Receive fragment frame interrupt */ + , FM_MAC_EX_10G_RX_LEN_ER + /* 10GEC Receive payload length error interrupt */ + , FM_MAC_EX_10G_RX_CRC_ER + /* 10GEC Receive CRC error interrupt */ + , FM_MAC_EX_10G_RX_ALIGN_ER + /* 10GEC Receive alignment error interrupt */ + , FM_MAC_EX_1G_BAB_RX + /* dTSEC Babbling receive error */ + , FM_MAC_EX_1G_RX_CTL + /* dTSEC Receive control (pause frame) interrupt */ + , FM_MAC_EX_1G_GRATEFUL_TX_STP_COMPLET + /* dTSEC Graceful transmit stop complete */ + , FM_MAC_EX_1G_BAB_TX + /* dTSEC Babbling transmit error */ + , FM_MAC_EX_1G_TX_CTL + /* dTSEC Transmit control (pause frame) interrupt */ + , FM_MAC_EX_1G_TX_ERR + /* dTSEC Transmit error */ + , FM_MAC_EX_1G_LATE_COL + /* dTSEC Late collision */ + , FM_MAC_EX_1G_COL_RET_LMT + /* dTSEC Collision retry limit */ + , FM_MAC_EX_1G_TX_FIFO_UNDRN + /* dTSEC Transmit FIFO underrun */ + , FM_MAC_EX_1G_MAG_PCKT + /* dTSEC Magic Packet detection */ + , FM_MAC_EX_1G_MII_MNG_RD_COMPLET + /* dTSEC MII management read completion */ + , FM_MAC_EX_1G_MII_MNG_WR_COMPLET + /* dTSEC MII management write completion */ + , FM_MAC_EX_1G_GRATEFUL_RX_STP_COMPLET + /* dTSEC Graceful receive stop complete */ + , FM_MAC_EX_1G_DATA_ERR + /* dTSEC Internal data error on transmit */ + , FM_MAC_1G_RX_DATA_ERR + /* dTSEC Internal data error on receive */ + , FM_MAC_EX_1G_1588_TS_RX_ERR + /* dTSEC Time-Stamp Receive Error */ + , FM_MAC_EX_1G_RX_MIB_CNT_OVFL + /* dTSEC MIB counter overflow */ + , FM_MAC_EX_TS_FIFO_ECC_ERR + /* mEMAC Time-stamp FIFO ECC error interrupt; + * not supported on T4240/B4860 rev1 chips + */ + , FM_MAC_EX_MAGIC_PACKET_INDICATION = FM_MAC_EX_1G_MAG_PCKT + /* mEMAC Magic Packet Indication Interrupt */ +}; + +struct eth_hash_entry { + u64 addr; /* Ethernet Address */ + struct list_head node; +}; + +typedef void (fman_mac_exception_cb)(void *dev_id, + enum fman_mac_exceptions exceptions); + +/* FMan MAC config input */ +struct fman_mac_params { + /* Base of memory mapped FM MAC registers */ + void __iomem *base_addr; + /* MAC address of device; First octet is sent first */ + enet_addr_t addr; + /* MAC ID; numbering of dTSEC and 1G-mEMAC: + * 0 - FM_MAX_NUM_OF_1G_MACS; + * numbering of 10G-MAC (TGEC) and 10G-mEMAC: + * 0 - FM_MAX_NUM_OF_10G_MACS + */ + u8 mac_id; + /* PHY interface */ + phy_interface_t phy_if; + /* Note that the speed should indicate the maximum rate that + * this MAC should support rather than the actual speed; + */ + u16 max_speed; + /* A handle to the FM object this port related to */ + void *fm; + /* MDIO exceptions interrupt source - not valid for all + * MACs; MUST be set to 'NO_IRQ' for MACs that don't have + * mdio-irq, or for polling + */ + void *dev_id; /* device cookie used by the exception cbs */ + fman_mac_exception_cb *event_cb; /* MDIO Events Callback Routine */ + fman_mac_exception_cb *exception_cb;/* Exception Callback Routine */ + /* SGMII/QSGII interface with 1000BaseX auto-negotiation between MAC + * and phy or backplane; Note: 1000BaseX auto-negotiation relates only + * to interface between MAC and phy/backplane, SGMII phy can still + * synchronize with far-end phy at 10Mbps, 100Mbps or 1000Mbps + */ + bool basex_if; + /* Pointer to TBI/PCS PHY node, used for TBI/PCS PHY access */ + struct device_node *internal_phy_node; +}; + +struct eth_hash_t { + u16 size; + struct list_head *lsts; +}; + +static inline struct eth_hash_entry +*dequeue_addr_from_hash_entry(struct list_head *addr_lst) +{ + struct eth_hash_entry *hash_entry = NULL; + + if (!list_empty(addr_lst)) { + hash_entry = ETH_HASH_ENTRY_OBJ(addr_lst->next); + list_del_init(&hash_entry->node); + } + return hash_entry; +} + +static inline void free_hash_table(struct eth_hash_t *hash) +{ + struct eth_hash_entry *hash_entry; + int i = 0; + + if (hash) { + if (hash->lsts) { + for (i = 0; i < hash->size; i++) { + hash_entry = + dequeue_addr_from_hash_entry(&hash->lsts[i]); + while (hash_entry) { + kfree(hash_entry); + hash_entry = + dequeue_addr_from_hash_entry(&hash-> + lsts[i]); + } + } + + kfree(hash->lsts); + } + + kfree(hash); + } +} + +static inline struct eth_hash_t *alloc_hash_table(u16 size) +{ + u32 i; + struct eth_hash_t *hash; + + /* Allocate address hash table */ + hash = kmalloc_array(size, sizeof(struct eth_hash_t *), GFP_KERNEL); + if (!hash) + return NULL; + + hash->size = size; + + hash->lsts = kmalloc_array(hash->size, sizeof(struct list_head), + GFP_KERNEL); + if (!hash->lsts) { + kfree(hash); + return NULL; + } + + for (i = 0; i < hash->size; i++) + INIT_LIST_HEAD(&hash->lsts[i]); + + return hash; +} + +#endif /* __FM_MAC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c new file mode 100644 index 0000000000000..58bb72071c147 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -0,0 +1,1170 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include "fman_memac.h" +#include "fman.h" + +#include <linux/slab.h> +#include <linux/io.h> +#include <linux/phy.h> +#include <linux/of_mdio.h> + +/* PCS registers */ +#define MDIO_SGMII_CR 0x00 +#define MDIO_SGMII_DEV_ABIL_SGMII 0x04 +#define MDIO_SGMII_LINK_TMR_L 0x12 +#define MDIO_SGMII_LINK_TMR_H 0x13 +#define MDIO_SGMII_IF_MODE 0x14 + +/* SGMII Control defines */ +#define SGMII_CR_AN_EN 0x1000 +#define SGMII_CR_RESTART_AN 0x0200 +#define SGMII_CR_FD 0x0100 +#define SGMII_CR_SPEED_SEL1_1G 0x0040 +#define SGMII_CR_DEF_VAL (SGMII_CR_AN_EN | SGMII_CR_FD | \ + SGMII_CR_SPEED_SEL1_1G) + +/* SGMII Device Ability for SGMII defines */ +#define MDIO_SGMII_DEV_ABIL_SGMII_MODE 0x4001 +#define MDIO_SGMII_DEV_ABIL_BASEX_MODE 0x01A0 + +/* Link timer define */ +#define LINK_TMR_L 0xa120 +#define LINK_TMR_H 0x0007 +#define LINK_TMR_L_BASEX 0xaf08 +#define LINK_TMR_H_BASEX 0x002f + +/* SGMII IF Mode defines */ +#define IF_MODE_USE_SGMII_AN 0x0002 +#define IF_MODE_SGMII_EN 0x0001 +#define IF_MODE_SGMII_SPEED_100M 0x0004 +#define IF_MODE_SGMII_SPEED_1G 0x0008 +#define IF_MODE_SGMII_DUPLEX_HALF 0x0010 + +/* Num of additional exact match MAC adr regs */ +#define MEMAC_NUM_OF_PADDRS 7 + +/* Control and Configuration Register (COMMAND_CONFIG) */ +#define CMD_CFG_REG_LOWP_RXETY 0x01000000 /* 07 Rx low power indication */ +#define CMD_CFG_TX_LOWP_ENA 0x00800000 /* 08 Tx Low Power Idle Enable */ +#define CMD_CFG_PFC_MODE 0x00080000 /* 12 Enable PFC */ +#define CMD_CFG_NO_LEN_CHK 0x00020000 /* 14 Payload length check disable */ +#define CMD_CFG_SW_RESET 0x00001000 /* 19 S/W Reset, self clearing bit */ +#define CMD_CFG_TX_PAD_EN 0x00000800 /* 20 Enable Tx padding of frames */ +#define CMD_CFG_PAUSE_IGNORE 0x00000100 /* 23 Ignore Pause frame quanta */ +#define CMD_CFG_CRC_FWD 0x00000040 /* 25 Terminate/frwd CRC of frames */ +#define CMD_CFG_PAD_EN 0x00000020 /* 26 Frame padding removal */ +#define CMD_CFG_PROMIS_EN 0x00000010 /* 27 Promiscuous operation enable */ +#define CMD_CFG_RX_EN 0x00000002 /* 30 MAC receive path enable */ +#define CMD_CFG_TX_EN 0x00000001 /* 31 MAC transmit path enable */ + +/* Transmit FIFO Sections Register (TX_FIFO_SECTIONS) */ +#define TX_FIFO_SECTIONS_TX_EMPTY_MASK 0xFFFF0000 +#define TX_FIFO_SECTIONS_TX_AVAIL_MASK 0x0000FFFF +#define TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G 0x00400000 +#define TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_1G 0x00100000 +#define TX_FIFO_SECTIONS_TX_AVAIL_10G 0x00000019 +#define TX_FIFO_SECTIONS_TX_AVAIL_1G 0x00000020 +#define TX_FIFO_SECTIONS_TX_AVAIL_SLOW_10G 0x00000060 + +#define GET_TX_EMPTY_DEFAULT_VALUE(_val) \ +do { \ + _val &= ~TX_FIFO_SECTIONS_TX_EMPTY_MASK; \ + ((_val == TX_FIFO_SECTIONS_TX_AVAIL_10G) ? \ + (_val |= TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G) :\ + (_val |= TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_1G));\ +} while (0) + +/* Interface Mode Register (IF_MODE) */ + +#define IF_MODE_MASK 0x00000003 /* 30-31 Mask on i/f mode bits */ +#define IF_MODE_XGMII 0x00000000 /* 30-31 XGMII (10G) interface */ +#define IF_MODE_GMII 0x00000002 /* 30-31 GMII (1G) interface */ +#define IF_MODE_RGMII 0x00000004 +#define IF_MODE_RGMII_AUTO 0x00008000 +#define IF_MODE_RGMII_1000 0x00004000 /* 10 - 1000Mbps RGMII */ +#define IF_MODE_RGMII_100 0x00000000 /* 00 - 100Mbps RGMII */ +#define IF_MODE_RGMII_10 0x00002000 /* 01 - 10Mbps RGMII */ +#define IF_MODE_RGMII_SP_MASK 0x00006000 /* Setsp mask bits */ +#define IF_MODE_RGMII_FD 0x00001000 /* Full duplex RGMII */ +#define IF_MODE_HD 0x00000040 /* Half duplex operation */ + +/* Hash table Control Register (HASHTABLE_CTRL) */ +#define HASH_CTRL_MCAST_EN 0x00000100 +/* 26-31 Hash table address code */ +#define HASH_CTRL_ADDR_MASK 0x0000003F +/* MAC mcast indication */ +#define GROUP_ADDRESS 0x0000010000000000LL +#define HASH_TABLE_SIZE 64 /* Hash tbl size */ + +/* Interrupt Mask Register (IMASK) */ +#define MEMAC_IMASK_MGI 0x40000000 /* 1 Magic pkt detect indication */ +#define MEMAC_IMASK_TSECC_ER 0x20000000 /* 2 Timestamp FIFO ECC error evnt */ +#define MEMAC_IMASK_TECC_ER 0x02000000 /* 6 Transmit frame ECC error evnt */ +#define MEMAC_IMASK_RECC_ER 0x01000000 /* 7 Receive frame ECC error evnt */ + +#define MEMAC_ALL_ERRS_IMASK \ + ((u32)(MEMAC_IMASK_TSECC_ER | \ + MEMAC_IMASK_TECC_ER | \ + MEMAC_IMASK_RECC_ER | \ + MEMAC_IMASK_MGI)) + +#define MEMAC_IEVNT_PCS 0x80000000 /* PCS (XG). Link sync (G) */ +#define MEMAC_IEVNT_AN 0x40000000 /* Auto-negotiation */ +#define MEMAC_IEVNT_LT 0x20000000 /* Link Training/New page */ +#define MEMAC_IEVNT_MGI 0x00004000 /* Magic pkt detection */ +#define MEMAC_IEVNT_TS_ECC_ER 0x00002000 /* Timestamp FIFO ECC error*/ +#define MEMAC_IEVNT_RX_FIFO_OVFL 0x00001000 /* Rx FIFO overflow */ +#define MEMAC_IEVNT_TX_FIFO_UNFL 0x00000800 /* Tx FIFO underflow */ +#define MEMAC_IEVNT_TX_FIFO_OVFL 0x00000400 /* Tx FIFO overflow */ +#define MEMAC_IEVNT_TX_ECC_ER 0x00000200 /* Tx frame ECC error */ +#define MEMAC_IEVNT_RX_ECC_ER 0x00000100 /* Rx frame ECC error */ +#define MEMAC_IEVNT_LI_FAULT 0x00000080 /* Link Interruption flt */ +#define MEMAC_IEVNT_RX_EMPTY 0x00000040 /* Rx FIFO empty */ +#define MEMAC_IEVNT_TX_EMPTY 0x00000020 /* Tx FIFO empty */ +#define MEMAC_IEVNT_RX_LOWP 0x00000010 /* Low Power Idle */ +#define MEMAC_IEVNT_PHY_LOS 0x00000004 /* Phy loss of signal */ +#define MEMAC_IEVNT_REM_FAULT 0x00000002 /* Remote fault (XGMII) */ +#define MEMAC_IEVNT_LOC_FAULT 0x00000001 /* Local fault (XGMII) */ + +#define DEFAULT_PAUSE_QUANTA 0xf000 +#define DEFAULT_FRAME_LENGTH 0x600 +#define DEFAULT_TX_IPG_LENGTH 12 + +#define CLXY_PAUSE_QUANTA_CLX_PQNT 0x0000FFFF +#define CLXY_PAUSE_QUANTA_CLY_PQNT 0xFFFF0000 +#define CLXY_PAUSE_THRESH_CLX_QTH 0x0000FFFF +#define CLXY_PAUSE_THRESH_CLY_QTH 0xFFFF0000 + +struct mac_addr { + /* Lower 32 bits of 48-bit MAC address */ + u32 mac_addr_l; + /* Upper 16 bits of 48-bit MAC address */ + u32 mac_addr_u; +}; + +/* memory map */ +struct memac_regs { + u32 res0000[2]; /* General Control and Status */ + u32 command_config; /* 0x008 Ctrl and cfg */ + struct mac_addr mac_addr0; /* 0x00C-0x010 MAC_ADDR_0...1 */ + u32 maxfrm; /* 0x014 Max frame length */ + u32 res0018[1]; + u32 rx_fifo_sections; /* Receive FIFO configuration reg */ + u32 tx_fifo_sections; /* Transmit FIFO configuration reg */ + u32 res0024[2]; + u32 hashtable_ctrl; /* 0x02C Hash table control */ + u32 res0030[4]; + u32 ievent; /* 0x040 Interrupt event */ + u32 tx_ipg_length; /* 0x044 Transmitter inter-packet-gap */ + u32 res0048; + u32 imask; /* 0x04C Interrupt mask */ + u32 res0050; + u32 pause_quanta[4]; /* 0x054 Pause quanta */ + u32 pause_thresh[4]; /* 0x064 Pause quanta threshold */ + u32 rx_pause_status; /* 0x074 Receive pause status */ + u32 res0078[2]; + struct mac_addr mac_addr[MEMAC_NUM_OF_PADDRS];/* 0x80-0x0B4 mac padr */ + u32 lpwake_timer; /* 0x0B8 Low Power Wakeup Timer */ + u32 sleep_timer; /* 0x0BC Transmit EEE Low Power Timer */ + u32 res00c0[8]; + u32 statn_config; /* 0x0E0 Statistics configuration */ + u32 res00e4[7]; + /* Rx Statistics Counter */ + u32 reoct_l; + u32 reoct_u; + u32 roct_l; + u32 roct_u; + u32 raln_l; + u32 raln_u; + u32 rxpf_l; + u32 rxpf_u; + u32 rfrm_l; + u32 rfrm_u; + u32 rfcs_l; + u32 rfcs_u; + u32 rvlan_l; + u32 rvlan_u; + u32 rerr_l; + u32 rerr_u; + u32 ruca_l; + u32 ruca_u; + u32 rmca_l; + u32 rmca_u; + u32 rbca_l; + u32 rbca_u; + u32 rdrp_l; + u32 rdrp_u; + u32 rpkt_l; + u32 rpkt_u; + u32 rund_l; + u32 rund_u; + u32 r64_l; + u32 r64_u; + u32 r127_l; + u32 r127_u; + u32 r255_l; + u32 r255_u; + u32 r511_l; + u32 r511_u; + u32 r1023_l; + u32 r1023_u; + u32 r1518_l; + u32 r1518_u; + u32 r1519x_l; + u32 r1519x_u; + u32 rovr_l; + u32 rovr_u; + u32 rjbr_l; + u32 rjbr_u; + u32 rfrg_l; + u32 rfrg_u; + u32 rcnp_l; + u32 rcnp_u; + u32 rdrntp_l; + u32 rdrntp_u; + u32 res01d0[12]; + /* Tx Statistics Counter */ + u32 teoct_l; + u32 teoct_u; + u32 toct_l; + u32 toct_u; + u32 res0210[2]; + u32 txpf_l; + u32 txpf_u; + u32 tfrm_l; + u32 tfrm_u; + u32 tfcs_l; + u32 tfcs_u; + u32 tvlan_l; + u32 tvlan_u; + u32 terr_l; + u32 terr_u; + u32 tuca_l; + u32 tuca_u; + u32 tmca_l; + u32 tmca_u; + u32 tbca_l; + u32 tbca_u; + u32 res0258[2]; + u32 tpkt_l; + u32 tpkt_u; + u32 tund_l; + u32 tund_u; + u32 t64_l; + u32 t64_u; + u32 t127_l; + u32 t127_u; + u32 t255_l; + u32 t255_u; + u32 t511_l; + u32 t511_u; + u32 t1023_l; + u32 t1023_u; + u32 t1518_l; + u32 t1518_u; + u32 t1519x_l; + u32 t1519x_u; + u32 res02a8[6]; + u32 tcnp_l; + u32 tcnp_u; + u32 res02c8[14]; + /* Line Interface Control */ + u32 if_mode; /* 0x300 Interface Mode Control */ + u32 if_status; /* 0x304 Interface Status */ + u32 res0308[14]; + /* HiGig/2 */ + u32 hg_config; /* 0x340 Control and cfg */ + u32 res0344[3]; + u32 hg_pause_quanta; /* 0x350 Pause quanta */ + u32 res0354[3]; + u32 hg_pause_thresh; /* 0x360 Pause quanta threshold */ + u32 res0364[3]; + u32 hgrx_pause_status; /* 0x370 Receive pause status */ + u32 hg_fifos_status; /* 0x374 fifos status */ + u32 rhm; /* 0x378 rx messages counter */ + u32 thm; /* 0x37C tx messages counter */ +}; + +struct memac_cfg { + bool reset_on_init; + bool pause_ignore; + bool promiscuous_mode_enable; + struct fixed_phy_status *fixed_link; + u16 max_frame_length; + u16 pause_quanta; + u32 tx_ipg_length; +}; + +struct fman_mac { + /* Pointer to MAC memory mapped registers */ + struct memac_regs __iomem *regs; + /* MAC address of device */ + u64 addr; + /* Ethernet physical interface */ + phy_interface_t phy_if; + u16 max_speed; + void *dev_id; /* device cookie used by the exception cbs */ + fman_mac_exception_cb *exception_cb; + fman_mac_exception_cb *event_cb; + /* Pointer to driver's global address hash table */ + struct eth_hash_t *multicast_addr_hash; + /* Pointer to driver's individual address hash table */ + struct eth_hash_t *unicast_addr_hash; + u8 mac_id; + u32 exceptions; + struct memac_cfg *memac_drv_param; + void *fm; + struct fman_rev_info fm_rev_info; + bool basex_if; + struct phy_device *pcsphy; +}; + +static void add_addr_in_paddr(struct memac_regs __iomem *regs, u8 *adr, + u8 paddr_num) +{ + u32 tmp0, tmp1; + + tmp0 = (u32)(adr[0] | adr[1] << 8 | adr[2] << 16 | adr[3] << 24); + tmp1 = (u32)(adr[4] | adr[5] << 8); + + if (paddr_num == 0) { + iowrite32be(tmp0, ®s->mac_addr0.mac_addr_l); + iowrite32be(tmp1, ®s->mac_addr0.mac_addr_u); + } else { + iowrite32be(tmp0, ®s->mac_addr[paddr_num - 1].mac_addr_l); + iowrite32be(tmp1, ®s->mac_addr[paddr_num - 1].mac_addr_u); + } +} + +static int reset(struct memac_regs __iomem *regs) +{ + u32 tmp; + int count; + + tmp = ioread32be(®s->command_config); + + tmp |= CMD_CFG_SW_RESET; + + iowrite32be(tmp, ®s->command_config); + + count = 100; + do { + udelay(1); + } while ((ioread32be(®s->command_config) & CMD_CFG_SW_RESET) && + --count); + + if (count == 0) + return -EBUSY; + + return 0; +} + +static void set_exception(struct memac_regs __iomem *regs, u32 val, + bool enable) +{ + u32 tmp; + + tmp = ioread32be(®s->imask); + if (enable) + tmp |= val; + else + tmp &= ~val; + + iowrite32be(tmp, ®s->imask); +} + +static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg, + phy_interface_t phy_if, u16 speed, bool slow_10g_if, + u32 exceptions) +{ + u32 tmp; + + /* Config */ + tmp = 0; + if (cfg->promiscuous_mode_enable) + tmp |= CMD_CFG_PROMIS_EN; + if (cfg->pause_ignore) + tmp |= CMD_CFG_PAUSE_IGNORE; + + /* Payload length check disable */ + tmp |= CMD_CFG_NO_LEN_CHK; + /* Enable padding of frames in transmit direction */ + tmp |= CMD_CFG_TX_PAD_EN; + + tmp |= CMD_CFG_CRC_FWD; + + iowrite32be(tmp, ®s->command_config); + + /* Max Frame Length */ + iowrite32be((u32)cfg->max_frame_length, ®s->maxfrm); + + /* Pause Time */ + iowrite32be((u32)cfg->pause_quanta, ®s->pause_quanta[0]); + iowrite32be((u32)0, ®s->pause_thresh[0]); + + /* IF_MODE */ + tmp = 0; + switch (phy_if) { + case PHY_INTERFACE_MODE_XGMII: + tmp |= IF_MODE_XGMII; + break; + default: + tmp |= IF_MODE_GMII; + if (phy_if == PHY_INTERFACE_MODE_RGMII) + tmp |= IF_MODE_RGMII | IF_MODE_RGMII_AUTO; + } + iowrite32be(tmp, ®s->if_mode); + + /* TX_FIFO_SECTIONS */ + tmp = 0; + if (phy_if == PHY_INTERFACE_MODE_XGMII) { + if (slow_10g_if) { + tmp |= (TX_FIFO_SECTIONS_TX_AVAIL_SLOW_10G | + TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G); + } else { + tmp |= (TX_FIFO_SECTIONS_TX_AVAIL_10G | + TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G); + } + } else { + tmp |= (TX_FIFO_SECTIONS_TX_AVAIL_1G | + TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_1G); + } + iowrite32be(tmp, ®s->tx_fifo_sections); + + /* clear all pending events and set-up interrupts */ + iowrite32be(0xffffffff, ®s->ievent); + set_exception(regs, exceptions, true); + + return 0; +} + +static void set_dflts(struct memac_cfg *cfg) +{ + cfg->reset_on_init = false; + cfg->promiscuous_mode_enable = false; + cfg->pause_ignore = false; + cfg->tx_ipg_length = DEFAULT_TX_IPG_LENGTH; + cfg->max_frame_length = DEFAULT_FRAME_LENGTH; + cfg->pause_quanta = DEFAULT_PAUSE_QUANTA; +} + +static u32 get_mac_addr_hash_code(u64 eth_addr) +{ + u64 mask1, mask2; + u32 xor_val = 0; + u8 i, j; + + for (i = 0; i < 6; i++) { + mask1 = eth_addr & (u64)0x01; + eth_addr >>= 1; + + for (j = 0; j < 7; j++) { + mask2 = eth_addr & (u64)0x01; + mask1 ^= mask2; + eth_addr >>= 1; + } + + xor_val |= (mask1 << (5 - i)); + } + + return xor_val; +} + +static void setup_sgmii_internal_phy(struct fman_mac *memac, + struct fixed_phy_status *fixed_link) +{ + u16 tmp_reg16; + + /* SGMII mode */ + tmp_reg16 = IF_MODE_SGMII_EN; + if (!fixed_link) + /* AN enable */ + tmp_reg16 |= IF_MODE_USE_SGMII_AN; + else { + switch (fixed_link->speed) { + case 10: + /* For 10M: IF_MODE[SPEED_10M] = 0 */ + break; + case 100: + tmp_reg16 |= IF_MODE_SGMII_SPEED_100M; + break; + case 1000: /* fallthrough */ + default: + tmp_reg16 |= IF_MODE_SGMII_SPEED_1G; + break; + } + if (!fixed_link->duplex) + tmp_reg16 |= IF_MODE_SGMII_DUPLEX_HALF; + } + phy_write(memac->pcsphy, MDIO_SGMII_IF_MODE, tmp_reg16); + + /* Device ability according to SGMII specification */ + tmp_reg16 = MDIO_SGMII_DEV_ABIL_SGMII_MODE; + phy_write(memac->pcsphy, MDIO_SGMII_DEV_ABIL_SGMII, tmp_reg16); + + /* Adjust link timer for SGMII - + * According to Cisco SGMII specification the timer should be 1.6 ms. + * The link_timer register is configured in units of the clock. + * - When running as 1G SGMII, Serdes clock is 125 MHz, so + * unit = 1 / (125*10^6 Hz) = 8 ns. + * 1.6 ms in units of 8 ns = 1.6ms / 8ns = 2*10^5 = 0x30d40 + * - When running as 2.5G SGMII, Serdes clock is 312.5 MHz, so + * unit = 1 / (312.5*10^6 Hz) = 3.2 ns. + * 1.6 ms in units of 3.2 ns = 1.6ms / 3.2ns = 5*10^5 = 0x7a120. + * Since link_timer value of 1G SGMII will be too short for 2.5 SGMII, + * we always set up here a value of 2.5 SGMII. + */ + phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_H, LINK_TMR_H); + phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_L, LINK_TMR_L); + + if (!fixed_link) + /* Restart AN */ + tmp_reg16 = SGMII_CR_DEF_VAL | SGMII_CR_RESTART_AN; + else + /* AN disabled */ + tmp_reg16 = SGMII_CR_DEF_VAL & ~SGMII_CR_AN_EN; + phy_write(memac->pcsphy, 0x0, tmp_reg16); +} + +static void setup_sgmii_internal_phy_base_x(struct fman_mac *memac) +{ + u16 tmp_reg16; + + /* AN Device capability */ + tmp_reg16 = MDIO_SGMII_DEV_ABIL_BASEX_MODE; + phy_write(memac->pcsphy, MDIO_SGMII_DEV_ABIL_SGMII, tmp_reg16); + + /* Adjust link timer for SGMII - + * For Serdes 1000BaseX auto-negotiation the timer should be 10 ms. + * The link_timer register is configured in units of the clock. + * - When running as 1G SGMII, Serdes clock is 125 MHz, so + * unit = 1 / (125*10^6 Hz) = 8 ns. + * 10 ms in units of 8 ns = 10ms / 8ns = 1250000 = 0x1312d0 + * - When running as 2.5G SGMII, Serdes clock is 312.5 MHz, so + * unit = 1 / (312.5*10^6 Hz) = 3.2 ns. + * 10 ms in units of 3.2 ns = 10ms / 3.2ns = 3125000 = 0x2faf08. + * Since link_timer value of 1G SGMII will be too short for 2.5 SGMII, + * we always set up here a value of 2.5 SGMII. + */ + phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_H, LINK_TMR_H_BASEX); + phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_L, LINK_TMR_L_BASEX); + + /* Restart AN */ + tmp_reg16 = SGMII_CR_DEF_VAL | SGMII_CR_RESTART_AN; + phy_write(memac->pcsphy, 0x0, tmp_reg16); +} + +static int check_init_parameters(struct fman_mac *memac) +{ + if (memac->addr == 0) { + pr_err("Ethernet MAC must have a valid MAC address\n"); + return -EINVAL; + } + if (!memac->exception_cb) { + pr_err("Uninitialized exception handler\n"); + return -EINVAL; + } + if (!memac->event_cb) { + pr_warn("Uninitialize event handler\n"); + return -EINVAL; + } + + return 0; +} + +static int get_exception_flag(enum fman_mac_exceptions exception) +{ + u32 bit_mask; + + switch (exception) { + case FM_MAC_EX_10G_TX_ECC_ER: + bit_mask = MEMAC_IMASK_TECC_ER; + break; + case FM_MAC_EX_10G_RX_ECC_ER: + bit_mask = MEMAC_IMASK_RECC_ER; + break; + case FM_MAC_EX_TS_FIFO_ECC_ERR: + bit_mask = MEMAC_IMASK_TSECC_ER; + break; + case FM_MAC_EX_MAGIC_PACKET_INDICATION: + bit_mask = MEMAC_IMASK_MGI; + break; + default: + bit_mask = 0; + break; + } + + return bit_mask; +} + +static void memac_err_exception(void *handle) +{ + struct fman_mac *memac = (struct fman_mac *)handle; + struct memac_regs __iomem *regs = memac->regs; + u32 event, imask; + + event = ioread32be(®s->ievent); + imask = ioread32be(®s->imask); + + /* Imask include both error and notification/event bits. + * Leaving only error bits enabled by imask. + * The imask error bits are shifted by 16 bits offset from + * their corresponding location in the ievent - hence the >> 16 + */ + event &= ((imask & MEMAC_ALL_ERRS_IMASK) >> 16); + + iowrite32be(event, ®s->ievent); + + if (event & MEMAC_IEVNT_TS_ECC_ER) + memac->exception_cb(memac->dev_id, FM_MAC_EX_TS_FIFO_ECC_ERR); + if (event & MEMAC_IEVNT_TX_ECC_ER) + memac->exception_cb(memac->dev_id, FM_MAC_EX_10G_TX_ECC_ER); + if (event & MEMAC_IEVNT_RX_ECC_ER) + memac->exception_cb(memac->dev_id, FM_MAC_EX_10G_RX_ECC_ER); +} + +static void memac_exception(void *handle) +{ + struct fman_mac *memac = (struct fman_mac *)handle; + struct memac_regs __iomem *regs = memac->regs; + u32 event, imask; + + event = ioread32be(®s->ievent); + imask = ioread32be(®s->imask); + + /* Imask include both error and notification/event bits. + * Leaving only error bits enabled by imask. + * The imask error bits are shifted by 16 bits offset from + * their corresponding location in the ievent - hence the >> 16 + */ + event &= ((imask & MEMAC_ALL_ERRS_IMASK) >> 16); + + iowrite32be(event, ®s->ievent); + + if (event & MEMAC_IEVNT_MGI) + memac->exception_cb(memac->dev_id, + FM_MAC_EX_MAGIC_PACKET_INDICATION); +} + +static void free_init_resources(struct fman_mac *memac) +{ + fman_unregister_intr(memac->fm, FMAN_MOD_MAC, memac->mac_id, + FMAN_INTR_TYPE_ERR); + + fman_unregister_intr(memac->fm, FMAN_MOD_MAC, memac->mac_id, + FMAN_INTR_TYPE_NORMAL); + + /* release the driver's group hash table */ + free_hash_table(memac->multicast_addr_hash); + memac->multicast_addr_hash = NULL; + + /* release the driver's individual hash table */ + free_hash_table(memac->unicast_addr_hash); + memac->unicast_addr_hash = NULL; +} + +static bool is_init_done(struct memac_cfg *memac_drv_params) +{ + /* Checks if mEMAC driver parameters were initialized */ + if (!memac_drv_params) + return true; + + return false; +} + +int memac_enable(struct fman_mac *memac, enum comm_mode mode) +{ + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (mode & COMM_MODE_RX) + tmp |= CMD_CFG_RX_EN; + if (mode & COMM_MODE_TX) + tmp |= CMD_CFG_TX_EN; + + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int memac_disable(struct fman_mac *memac, enum comm_mode mode) +{ + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (mode & COMM_MODE_RX) + tmp &= ~CMD_CFG_RX_EN; + if (mode & COMM_MODE_TX) + tmp &= ~CMD_CFG_TX_EN; + + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int memac_set_promiscuous(struct fman_mac *memac, bool new_val) +{ + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (new_val) + tmp |= CMD_CFG_PROMIS_EN; + else + tmp &= ~CMD_CFG_PROMIS_EN; + + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int memac_adjust_link(struct fman_mac *memac, u16 speed) +{ + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->if_mode); + + /* Set full duplex */ + tmp &= ~IF_MODE_HD; + + if (memac->phy_if == PHY_INTERFACE_MODE_RGMII) { + /* Configure RGMII in manual mode */ + tmp &= ~IF_MODE_RGMII_AUTO; + tmp &= ~IF_MODE_RGMII_SP_MASK; + /* Full duplex */ + tmp |= IF_MODE_RGMII_FD; + + switch (speed) { + case SPEED_1000: + tmp |= IF_MODE_RGMII_1000; + break; + case SPEED_100: + tmp |= IF_MODE_RGMII_100; + break; + case SPEED_10: + tmp |= IF_MODE_RGMII_10; + break; + default: + break; + } + } + + iowrite32be(tmp, ®s->if_mode); + + return 0; +} + +int memac_cfg_max_frame_len(struct fman_mac *memac, u16 new_val) +{ + if (is_init_done(memac->memac_drv_param)) + return -EINVAL; + + memac->memac_drv_param->max_frame_length = new_val; + + return 0; +} + +int memac_cfg_reset_on_init(struct fman_mac *memac, bool enable) +{ + if (is_init_done(memac->memac_drv_param)) + return -EINVAL; + + memac->memac_drv_param->reset_on_init = enable; + + return 0; +} + +int memac_cfg_fixed_link(struct fman_mac *memac, + struct fixed_phy_status *fixed_link) +{ + if (is_init_done(memac->memac_drv_param)) + return -EINVAL; + + memac->memac_drv_param->fixed_link = fixed_link; + + return 0; +} + +int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority, + u16 pause_time, u16 thresh_time) +{ + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->tx_fifo_sections); + + GET_TX_EMPTY_DEFAULT_VALUE(tmp); + iowrite32be(tmp, ®s->tx_fifo_sections); + + tmp = ioread32be(®s->command_config); + tmp &= ~CMD_CFG_PFC_MODE; + priority = 0; + + iowrite32be(tmp, ®s->command_config); + + tmp = ioread32be(®s->pause_quanta[priority / 2]); + if (priority % 2) + tmp &= CLXY_PAUSE_QUANTA_CLX_PQNT; + else + tmp &= CLXY_PAUSE_QUANTA_CLY_PQNT; + tmp |= ((u32)pause_time << (16 * (priority % 2))); + iowrite32be(tmp, ®s->pause_quanta[priority / 2]); + + tmp = ioread32be(®s->pause_thresh[priority / 2]); + if (priority % 2) + tmp &= CLXY_PAUSE_THRESH_CLX_QTH; + else + tmp &= CLXY_PAUSE_THRESH_CLY_QTH; + tmp |= ((u32)thresh_time << (16 * (priority % 2))); + iowrite32be(tmp, ®s->pause_thresh[priority / 2]); + + return 0; +} + +int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en) +{ + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (en) + tmp &= ~CMD_CFG_PAUSE_IGNORE; + else + tmp |= CMD_CFG_PAUSE_IGNORE; + + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr) +{ + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + add_addr_in_paddr(memac->regs, (u8 *)(*enet_addr), 0); + + return 0; +} + +int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) +{ + struct memac_regs __iomem *regs = memac->regs; + struct eth_hash_entry *hash_entry; + u32 hash; + u64 addr; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + addr = ENET_ADDR_TO_UINT64(*eth_addr); + + if (!(addr & GROUP_ADDRESS)) { + /* Unicast addresses not supported in hash */ + pr_err("Unicast Address\n"); + return -EINVAL; + } + hash = get_mac_addr_hash_code(addr) & HASH_CTRL_ADDR_MASK; + + /* Create element to be added to the driver hash table */ + hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + if (!hash_entry) + return -ENOMEM; + hash_entry->addr = addr; + INIT_LIST_HEAD(&hash_entry->node); + + list_add_tail(&hash_entry->node, + &memac->multicast_addr_hash->lsts[hash]); + iowrite32be(hash | HASH_CTRL_MCAST_EN, ®s->hashtable_ctrl); + + return 0; +} + +int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) +{ + struct memac_regs __iomem *regs = memac->regs; + struct eth_hash_entry *hash_entry = NULL; + struct list_head *pos; + u32 hash; + u64 addr; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + addr = ENET_ADDR_TO_UINT64(*eth_addr); + + hash = get_mac_addr_hash_code(addr) & HASH_CTRL_ADDR_MASK; + + list_for_each(pos, &memac->multicast_addr_hash->lsts[hash]) { + hash_entry = ETH_HASH_ENTRY_OBJ(pos); + if (hash_entry->addr == addr) { + list_del_init(&hash_entry->node); + kfree(hash_entry); + break; + } + } + if (list_empty(&memac->multicast_addr_hash->lsts[hash])) + iowrite32be(hash & ~HASH_CTRL_MCAST_EN, ®s->hashtable_ctrl); + + return 0; +} + +int memac_set_exception(struct fman_mac *memac, + enum fman_mac_exceptions exception, bool enable) +{ + u32 bit_mask = 0; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + bit_mask = get_exception_flag(exception); + if (bit_mask) { + if (enable) + memac->exceptions |= bit_mask; + else + memac->exceptions &= ~bit_mask; + } else { + pr_err("Undefined exception\n"); + return -EINVAL; + } + set_exception(memac->regs, bit_mask, enable); + + return 0; +} + +int memac_init(struct fman_mac *memac) +{ + struct memac_cfg *memac_drv_param; + u8 i; + enet_addr_t eth_addr; + bool slow_10g_if = false; + struct fixed_phy_status *fixed_link; + int err; + u32 reg32 = 0; + + if (is_init_done(memac->memac_drv_param)) + return -EINVAL; + + err = check_init_parameters(memac); + if (err) + return err; + + memac_drv_param = memac->memac_drv_param; + + if (memac->fm_rev_info.major == 6 && memac->fm_rev_info.minor == 4) + slow_10g_if = true; + + /* First, reset the MAC if desired. */ + if (memac_drv_param->reset_on_init) { + err = reset(memac->regs); + if (err) { + pr_err("mEMAC reset failed\n"); + return err; + } + } + + /* MAC Address */ + MAKE_ENET_ADDR_FROM_UINT64(memac->addr, eth_addr); + add_addr_in_paddr(memac->regs, (u8 *)eth_addr, 0); + + fixed_link = memac_drv_param->fixed_link; + + init(memac->regs, memac->memac_drv_param, memac->phy_if, + memac->max_speed, slow_10g_if, memac->exceptions); + + /* FM_RX_FIFO_CORRUPT_ERRATA_10GMAC_A006320 errata workaround + * Exists only in FMan 6.0 and 6.3. + */ + if ((memac->fm_rev_info.major == 6) && + ((memac->fm_rev_info.minor == 0) || + (memac->fm_rev_info.minor == 3))) { + /* MAC strips CRC from received frames - this workaround + * should decrease the likelihood of bug appearance + */ + reg32 = ioread32be(&memac->regs->command_config); + reg32 &= ~CMD_CFG_CRC_FWD; + iowrite32be(reg32, &memac->regs->command_config); + } + + if (memac->phy_if == PHY_INTERFACE_MODE_SGMII) { + /* Configure internal SGMII PHY */ + if (memac->basex_if) + setup_sgmii_internal_phy_base_x(memac); + else + setup_sgmii_internal_phy(memac, fixed_link); + } else if (memac->phy_if == PHY_INTERFACE_MODE_QSGMII) { + /* Configure 4 internal SGMII PHYs */ + for (i = 0; i < 4; i++) { + u8 qsmgii_phy_addr, phy_addr; + /* QSGMII PHY address occupies 3 upper bits of 5-bit + * phy_address; the lower 2 bits are used to extend + * register address space and access each one of 4 + * ports inside QSGMII. + */ + phy_addr = memac->pcsphy->addr; + qsmgii_phy_addr = (u8)((phy_addr << 2) | i); + memac->pcsphy->addr = qsmgii_phy_addr; + if (memac->basex_if) + setup_sgmii_internal_phy_base_x(memac); + else + setup_sgmii_internal_phy(memac, fixed_link); + + memac->pcsphy->addr = phy_addr; + } + } + + /* Max Frame Length */ + err = fman_set_mac_max_frame(memac->fm, memac->mac_id, + memac_drv_param->max_frame_length); + if (err) { + pr_err("settings Mac max frame length is FAILED\n"); + return err; + } + + memac->multicast_addr_hash = alloc_hash_table(HASH_TABLE_SIZE); + if (!memac->multicast_addr_hash) { + free_init_resources(memac); + pr_err("allocation hash table is FAILED\n"); + return -ENOMEM; + } + + memac->unicast_addr_hash = alloc_hash_table(HASH_TABLE_SIZE); + if (!memac->unicast_addr_hash) { + free_init_resources(memac); + pr_err("allocation hash table is FAILED\n"); + return -ENOMEM; + } + + fman_register_intr(memac->fm, FMAN_MOD_MAC, memac->mac_id, + FMAN_INTR_TYPE_ERR, memac_err_exception, memac); + + fman_register_intr(memac->fm, FMAN_MOD_MAC, memac->mac_id, + FMAN_INTR_TYPE_NORMAL, memac_exception, memac); + + kfree(memac_drv_param); + memac->memac_drv_param = NULL; + + return 0; +} + +int memac_free(struct fman_mac *memac) +{ + free_init_resources(memac); + + kfree(memac->memac_drv_param); + kfree(memac); + + return 0; +} + +struct fman_mac *memac_config(struct fman_mac_params *params) +{ + struct fman_mac *memac; + struct memac_cfg *memac_drv_param; + void __iomem *base_addr; + + base_addr = params->base_addr; + /* allocate memory for the m_emac data structure */ + memac = kzalloc(sizeof(*memac), GFP_KERNEL); + if (!memac) + return NULL; + + /* allocate memory for the m_emac driver parameters data structure */ + memac_drv_param = kzalloc(sizeof(*memac_drv_param), GFP_KERNEL); + if (!memac_drv_param) { + memac_free(memac); + return NULL; + } + + /* Plant parameter structure pointer */ + memac->memac_drv_param = memac_drv_param; + + set_dflts(memac_drv_param); + + memac->addr = ENET_ADDR_TO_UINT64(params->addr); + + memac->regs = base_addr; + memac->max_speed = params->max_speed; + memac->phy_if = params->phy_if; + memac->mac_id = params->mac_id; + memac->exceptions = (MEMAC_IMASK_TSECC_ER | MEMAC_IMASK_TECC_ER | + MEMAC_IMASK_RECC_ER | MEMAC_IMASK_MGI); + memac->exception_cb = params->exception_cb; + memac->event_cb = params->event_cb; + memac->dev_id = params->dev_id; + memac->fm = params->fm; + memac->basex_if = params->basex_if; + + /* Save FMan revision */ + fman_get_revision(memac->fm, &memac->fm_rev_info); + + if (memac->phy_if == PHY_INTERFACE_MODE_SGMII) { + if (!params->internal_phy_node) { + pr_err("PCS PHY node is not available\n"); + memac_free(memac); + return NULL; + } + + memac->pcsphy = of_phy_find_device(params->internal_phy_node); + if (!memac->pcsphy) { + pr_err("of_phy_find_device (PCS PHY) failed\n"); + memac_free(memac); + return NULL; + } + } + + return memac; +} diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h new file mode 100644 index 0000000000000..173d8e0fd7166 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -0,0 +1,60 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __MEMAC_H +#define __MEMAC_H + +#include "fman_mac.h" + +#include <linux/netdevice.h> + +struct fman_mac *memac_config(struct fman_mac_params *params); +int memac_set_promiscuous(struct fman_mac *memac, bool new_val); +int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr); +int memac_adjust_link(struct fman_mac *memac, u16 speed); +int memac_cfg_max_frame_len(struct fman_mac *memac, u16 new_val); +int memac_cfg_reset_on_init(struct fman_mac *memac, bool enable); +int memac_cfg_fixed_link(struct fman_mac *memac, + struct fixed_phy_status *fixed_link); +int memac_enable(struct fman_mac *memac, enum comm_mode mode); +int memac_disable(struct fman_mac *memac, enum comm_mode mode); +int memac_init(struct fman_mac *memac); +int memac_free(struct fman_mac *memac); +int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en); +int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority, + u16 pause_time, u16 thresh_time); +int memac_set_exception(struct fman_mac *memac, + enum fman_mac_exceptions exception, bool enable); +int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); +int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); + +#endif /* __MEMAC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.c b/drivers/net/ethernet/freescale/fman/fman_muram.c new file mode 100644 index 0000000000000..4eb0e9ac71824 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_muram.c @@ -0,0 +1,158 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "fman_muram.h" + +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/genalloc.h> + +struct muram_info { + struct gen_pool *pool; + void __iomem *vbase; + size_t size; + phys_addr_t pbase; +}; + +static unsigned long fman_muram_vbase_to_offset(struct muram_info *muram, + unsigned long vaddr) +{ + return vaddr - (unsigned long)muram->vbase; +} + +/** + * fman_muram_init + * @base: Pointer to base of memory mapped FM-MURAM. + * @size: Size of the FM-MURAM partition. + * + * Creates partition in the MURAM. + * The routine returns a pointer to the MURAM partition. + * This pointer must be passed as to all other FM-MURAM function calls. + * No actual initialization or configuration of FM_MURAM hardware is done by + * this routine. + * + * Return: pointer to FM-MURAM object, or NULL for Failure. + */ +struct muram_info *fman_muram_init(phys_addr_t base, size_t size) +{ + struct muram_info *muram; + void __iomem *vaddr; + int ret; + + muram = kzalloc(sizeof(*muram), GFP_KERNEL); + if (!muram) + return NULL; + + muram->pool = gen_pool_create(ilog2(64), -1); + if (!muram->pool) { + pr_err("%s(): MURAM pool create failed\n", __func__); + goto muram_free; + } + + vaddr = ioremap(base, size); + if (!vaddr) { + pr_err("%s(): MURAM ioremap failed\n", __func__); + goto pool_destroy; + } + + ret = gen_pool_add_virt(muram->pool, (unsigned long)vaddr, + base, size, -1); + if (ret < 0) { + pr_err("%s(): MURAM pool add failed\n", __func__); + iounmap(vaddr); + goto pool_destroy; + } + + memset_io(vaddr, 0, (int)size); + + muram->vbase = vaddr; + muram->pbase = base; + return muram; + +pool_destroy: + gen_pool_destroy(muram->pool); +muram_free: + kfree(muram); + return NULL; +} + +/** + * fman_muram_offset_to_vbase + * @muram: FM-MURAM module pointer. + * @offset: the offset of the memory block + * + * Gives the address of the memory region from specific offset + * + * Return: The address of the memory block + */ +unsigned long fman_muram_offset_to_vbase(struct muram_info *muram, + unsigned long offset) +{ + return offset + (unsigned long)muram->vbase; +} + +/** + * fman_muram_alloc + * @muram: FM-MURAM module pointer. + * @size: Size of the memory to be allocated. + * + * Allocate some memory from FM-MURAM partition. + * + * Return: address of the allocated memory; NULL otherwise. + */ +int fman_muram_alloc(struct muram_info *muram, size_t size) +{ + unsigned long vaddr; + + vaddr = gen_pool_alloc(muram->pool, size); + if (!vaddr) + return -ENOMEM; + + memset_io((void __iomem *)vaddr, 0, size); + + return fman_muram_vbase_to_offset(muram, vaddr); +} + +/** + * fman_muram_free_mem + * muram: FM-MURAM module pointer. + * offset: offset of the memory region to be freed. + * size: size of the memory to be freed. + * + * Free an allocated memory from FM-MURAM partition. + */ +void fman_muram_free_mem(struct muram_info *muram, u32 offset, size_t size) +{ + unsigned long addr = fman_muram_offset_to_vbase(muram, offset); + + gen_pool_free(muram->pool, addr, size); +} diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.h b/drivers/net/ethernet/freescale/fman/fman_muram.h new file mode 100644 index 0000000000000..dbf0af9e5bb58 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_muram.h @@ -0,0 +1,51 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef __FM_MURAM_EXT +#define __FM_MURAM_EXT + +#include <linux/types.h> + +#define FM_MURAM_INVALID_ALLOCATION -1 + +/* Structure for FM MURAM information */ +struct muram_info; + +struct muram_info *fman_muram_init(phys_addr_t base, size_t size); + +unsigned long fman_muram_offset_to_vbase(struct muram_info *muram, + unsigned long offset); + +int fman_muram_alloc(struct muram_info *muram, size_t size); + +void fman_muram_free_mem(struct muram_info *muram, u32 offset, size_t size); + +#endif /* __FM_MURAM_EXT */ diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c new file mode 100644 index 0000000000000..70c198d072dcf --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -0,0 +1,1778 @@ +/* + * Copyright 2008 - 2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include "fman_port.h" +#include "fman.h" +#include "fman_sp.h" + +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/of_platform.h> +#include <linux/of_address.h> +#include <linux/delay.h> +#include <linux/libfdt_env.h> + +/* Queue ID */ +#define DFLT_FQ_ID 0x00FFFFFF + +/* General defines */ +#define PORT_BMI_FIFO_UNITS 0x100 + +#define MAX_PORT_FIFO_SIZE(bmi_max_fifo_size) \ + min((u32)bmi_max_fifo_size, (u32)1024 * FMAN_BMI_FIFO_UNITS) + +#define PORT_CG_MAP_NUM 8 +#define PORT_PRS_RESULT_WORDS_NUM 8 +#define PORT_IC_OFFSET_UNITS 0x10 + +#define MIN_EXT_BUF_SIZE 64 + +#define BMI_PORT_REGS_OFFSET 0 +#define QMI_PORT_REGS_OFFSET 0x400 + +/* Default values */ +#define DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN \ + DFLT_FM_SP_BUFFER_PREFIX_CONTEXT_DATA_ALIGN + +#define DFLT_PORT_CUT_BYTES_FROM_END 4 + +#define DFLT_PORT_ERRORS_TO_DISCARD FM_PORT_FRM_ERR_CLS_DISCARD +#define DFLT_PORT_MAX_FRAME_LENGTH 9600 + +#define DFLT_PORT_RX_FIFO_PRI_ELEVATION_LEV(bmi_max_fifo_size) \ + MAX_PORT_FIFO_SIZE(bmi_max_fifo_size) + +#define DFLT_PORT_RX_FIFO_THRESHOLD(major, bmi_max_fifo_size) \ + (major == 6 ? \ + MAX_PORT_FIFO_SIZE(bmi_max_fifo_size) : \ + (MAX_PORT_FIFO_SIZE(bmi_max_fifo_size) * 3 / 4)) \ + +#define DFLT_PORT_EXTRA_NUM_OF_FIFO_BUFS 0 + +/* QMI defines */ +#define QMI_DEQ_CFG_SUBPORTAL_MASK 0x1f + +#define QMI_PORT_CFG_EN 0x80000000 +#define QMI_PORT_STATUS_DEQ_FD_BSY 0x20000000 + +#define QMI_DEQ_CFG_PRI 0x80000000 +#define QMI_DEQ_CFG_TYPE1 0x10000000 +#define QMI_DEQ_CFG_TYPE2 0x20000000 +#define QMI_DEQ_CFG_TYPE3 0x30000000 +#define QMI_DEQ_CFG_PREFETCH_PARTIAL 0x01000000 +#define QMI_DEQ_CFG_PREFETCH_FULL 0x03000000 +#define QMI_DEQ_CFG_SP_MASK 0xf +#define QMI_DEQ_CFG_SP_SHIFT 20 + +#define QMI_BYTE_COUNT_LEVEL_CONTROL(_type) \ + (_type == FMAN_PORT_TYPE_TX ? 0x1400 : 0x400) + +/* BMI defins */ +#define BMI_EBD_EN 0x80000000 + +#define BMI_PORT_CFG_EN 0x80000000 + +#define BMI_PORT_STATUS_BSY 0x80000000 + +#define BMI_DMA_ATTR_SWP_SHIFT FMAN_SP_DMA_ATTR_SWP_SHIFT +#define BMI_DMA_ATTR_WRITE_OPTIMIZE FMAN_SP_DMA_ATTR_WRITE_OPTIMIZE + +#define BMI_RX_FIFO_PRI_ELEVATION_SHIFT 16 +#define BMI_RX_FIFO_THRESHOLD_ETHE 0x80000000 + +#define BMI_FRAME_END_CS_IGNORE_SHIFT 24 +#define BMI_FRAME_END_CS_IGNORE_MASK 0x0000001f + +#define BMI_RX_FRAME_END_CUT_SHIFT 16 +#define BMI_RX_FRAME_END_CUT_MASK 0x0000001f + +#define BMI_IC_TO_EXT_SHIFT FMAN_SP_IC_TO_EXT_SHIFT +#define BMI_IC_TO_EXT_MASK 0x0000001f +#define BMI_IC_FROM_INT_SHIFT FMAN_SP_IC_FROM_INT_SHIFT +#define BMI_IC_FROM_INT_MASK 0x0000000f +#define BMI_IC_SIZE_MASK 0x0000001f + +#define BMI_INT_BUF_MARG_SHIFT 28 +#define BMI_INT_BUF_MARG_MASK 0x0000000f +#define BMI_EXT_BUF_MARG_START_SHIFT FMAN_SP_EXT_BUF_MARG_START_SHIFT +#define BMI_EXT_BUF_MARG_START_MASK 0x000001ff +#define BMI_EXT_BUF_MARG_END_MASK 0x000001ff + +#define BMI_CMD_MR_LEAC 0x00200000 +#define BMI_CMD_MR_SLEAC 0x00100000 +#define BMI_CMD_MR_MA 0x00080000 +#define BMI_CMD_MR_DEAS 0x00040000 +#define BMI_CMD_RX_MR_DEF (BMI_CMD_MR_LEAC | \ + BMI_CMD_MR_SLEAC | \ + BMI_CMD_MR_MA | \ + BMI_CMD_MR_DEAS) +#define BMI_CMD_TX_MR_DEF 0 + +#define BMI_CMD_ATTR_ORDER 0x80000000 +#define BMI_CMD_ATTR_SYNC 0x02000000 +#define BMI_CMD_ATTR_COLOR_SHIFT 26 + +#define BMI_FIFO_PIPELINE_DEPTH_SHIFT 12 +#define BMI_FIFO_PIPELINE_DEPTH_MASK 0x0000000f +#define BMI_NEXT_ENG_FD_BITS_SHIFT 24 + +#define BMI_EXT_BUF_POOL_VALID FMAN_SP_EXT_BUF_POOL_VALID +#define BMI_EXT_BUF_POOL_EN_COUNTER FMAN_SP_EXT_BUF_POOL_EN_COUNTER +#define BMI_EXT_BUF_POOL_BACKUP FMAN_SP_EXT_BUF_POOL_BACKUP +#define BMI_EXT_BUF_POOL_ID_SHIFT 16 +#define BMI_EXT_BUF_POOL_ID_MASK 0x003F0000 +#define BMI_POOL_DEP_NUM_OF_POOLS_SHIFT 16 + +#define BMI_TX_FIFO_MIN_FILL_SHIFT 16 + +#define BMI_PRIORITY_ELEVATION_LEVEL ((0x3FF + 1) * PORT_BMI_FIFO_UNITS) +#define BMI_FIFO_THRESHOLD ((0x3FF + 1) * PORT_BMI_FIFO_UNITS) + +#define BMI_DEQUEUE_PIPELINE_DEPTH(_type, _speed) \ + ((_type == FMAN_PORT_TYPE_TX && _speed == 10000) ? 4 : 1) + +#define RX_ERRS_TO_ENQ \ + (FM_PORT_FRM_ERR_DMA | \ + FM_PORT_FRM_ERR_PHYSICAL | \ + FM_PORT_FRM_ERR_SIZE | \ + FM_PORT_FRM_ERR_EXTRACTION | \ + FM_PORT_FRM_ERR_NO_SCHEME | \ + FM_PORT_FRM_ERR_PRS_TIMEOUT | \ + FM_PORT_FRM_ERR_PRS_ILL_INSTRUCT | \ + FM_PORT_FRM_ERR_BLOCK_LIMIT_EXCEEDED | \ + FM_PORT_FRM_ERR_PRS_HDR_ERR | \ + FM_PORT_FRM_ERR_KEYSIZE_OVERFLOW | \ + FM_PORT_FRM_ERR_IPRE) + +/* NIA defines */ +#define NIA_ORDER_RESTOR 0x00800000 +#define NIA_ENG_BMI 0x00500000 +#define NIA_ENG_QMI_ENQ 0x00540000 +#define NIA_ENG_QMI_DEQ 0x00580000 + +#define NIA_BMI_AC_ENQ_FRAME 0x00000002 +#define NIA_BMI_AC_TX_RELEASE 0x000002C0 +#define NIA_BMI_AC_RELEASE 0x000000C0 +#define NIA_BMI_AC_TX 0x00000274 +#define NIA_BMI_AC_FETCH_ALL_FRAME 0x0000020c + +/* Port IDs */ +#define TX_10G_PORT_BASE 0x30 +#define RX_10G_PORT_BASE 0x10 + +/* BMI Rx port register map */ +struct fman_port_rx_bmi_regs { + u32 fmbm_rcfg; /* Rx Configuration */ + u32 fmbm_rst; /* Rx Status */ + u32 fmbm_rda; /* Rx DMA attributes */ + u32 fmbm_rfp; /* Rx FIFO Parameters */ + u32 fmbm_rfed; /* Rx Frame End Data */ + u32 fmbm_ricp; /* Rx Internal Context Parameters */ + u32 fmbm_rim; /* Rx Internal Buffer Margins */ + u32 fmbm_rebm; /* Rx External Buffer Margins */ + u32 fmbm_rfne; /* Rx Frame Next Engine */ + u32 fmbm_rfca; /* Rx Frame Command Attributes. */ + u32 fmbm_rfpne; /* Rx Frame Parser Next Engine */ + u32 fmbm_rpso; /* Rx Parse Start Offset */ + u32 fmbm_rpp; /* Rx Policer Profile */ + u32 fmbm_rccb; /* Rx Coarse Classification Base */ + u32 fmbm_reth; /* Rx Excessive Threshold */ + u32 reserved003c[1]; /* (0x03C 0x03F) */ + u32 fmbm_rprai[PORT_PRS_RESULT_WORDS_NUM]; + /* Rx Parse Results Array Init */ + u32 fmbm_rfqid; /* Rx Frame Queue ID */ + u32 fmbm_refqid; /* Rx Error Frame Queue ID */ + u32 fmbm_rfsdm; /* Rx Frame Status Discard Mask */ + u32 fmbm_rfsem; /* Rx Frame Status Error Mask */ + u32 fmbm_rfene; /* Rx Frame Enqueue Next Engine */ + u32 reserved0074[0x2]; /* (0x074-0x07C) */ + u32 fmbm_rcmne; /* Rx Frame Continuous Mode Next Engine */ + u32 reserved0080[0x20]; /* (0x080 0x0FF) */ + u32 fmbm_ebmpi[FMAN_PORT_MAX_EXT_POOLS_NUM]; + /* Buffer Manager pool Information- */ + u32 fmbm_acnt[FMAN_PORT_MAX_EXT_POOLS_NUM]; /* Allocate Counter- */ + u32 reserved0130[8]; /* 0x130/0x140 - 0x15F reserved - */ + u32 fmbm_rcgm[PORT_CG_MAP_NUM]; /* Congestion Group Map */ + u32 fmbm_mpd; /* BM Pool Depletion */ + u32 reserved0184[0x1F]; /* (0x184 0x1FF) */ + u32 fmbm_rstc; /* Rx Statistics Counters */ + u32 fmbm_rfrc; /* Rx Frame Counter */ + u32 fmbm_rfbc; /* Rx Bad Frames Counter */ + u32 fmbm_rlfc; /* Rx Large Frames Counter */ + u32 fmbm_rffc; /* Rx Filter Frames Counter */ + u32 fmbm_rfdc; /* Rx Frame Discard Counter */ + u32 fmbm_rfldec; /* Rx Frames List DMA Error Counter */ + u32 fmbm_rodc; /* Rx Out of Buffers Discard nntr */ + u32 fmbm_rbdc; /* Rx Buffers Deallocate Counter */ + u32 fmbm_rpec; /* RX Prepare to enqueue Counte */ + u32 reserved0224[0x16]; /* (0x224 0x27F) */ + u32 fmbm_rpc; /* Rx Performance Counters */ + u32 fmbm_rpcp; /* Rx Performance Count Parameters */ + u32 fmbm_rccn; /* Rx Cycle Counter */ + u32 fmbm_rtuc; /* Rx Tasks Utilization Counter */ + u32 fmbm_rrquc; /* Rx Receive Queue Utilization cntr */ + u32 fmbm_rduc; /* Rx DMA Utilization Counter */ + u32 fmbm_rfuc; /* Rx FIFO Utilization Counter */ + u32 fmbm_rpac; /* Rx Pause Activation Counter */ + u32 reserved02a0[0x18]; /* (0x2A0 0x2FF) */ + u32 fmbm_rdcfg[0x3]; /* Rx Debug Configuration */ + u32 fmbm_rgpr; /* Rx General Purpose Register */ + u32 reserved0310[0x3a]; +}; + +/* BMI Tx port register map */ +struct fman_port_tx_bmi_regs { + u32 fmbm_tcfg; /* Tx Configuration */ + u32 fmbm_tst; /* Tx Status */ + u32 fmbm_tda; /* Tx DMA attributes */ + u32 fmbm_tfp; /* Tx FIFO Parameters */ + u32 fmbm_tfed; /* Tx Frame End Data */ + u32 fmbm_ticp; /* Tx Internal Context Parameters */ + u32 fmbm_tfdne; /* Tx Frame Dequeue Next Engine. */ + u32 fmbm_tfca; /* Tx Frame Command attribute. */ + u32 fmbm_tcfqid; /* Tx Confirmation Frame Queue ID. */ + u32 fmbm_tefqid; /* Tx Frame Error Queue ID */ + u32 fmbm_tfene; /* Tx Frame Enqueue Next Engine */ + u32 fmbm_trlmts; /* Tx Rate Limiter Scale */ + u32 fmbm_trlmt; /* Tx Rate Limiter */ + u32 reserved0034[0x0e]; /* (0x034-0x6c) */ + u32 fmbm_tccb; /* Tx Coarse Classification base */ + u32 fmbm_tfne; /* Tx Frame Next Engine */ + u32 fmbm_tpfcm[0x02]; + /* Tx Priority based Flow Control (PFC) Mapping */ + u32 fmbm_tcmne; /* Tx Frame Continuous Mode Next Engine */ + u32 reserved0080[0x60]; /* (0x080-0x200) */ + u32 fmbm_tstc; /* Tx Statistics Counters */ + u32 fmbm_tfrc; /* Tx Frame Counter */ + u32 fmbm_tfdc; /* Tx Frames Discard Counter */ + u32 fmbm_tfledc; /* Tx Frame len error discard cntr */ + u32 fmbm_tfufdc; /* Tx Frame unsprt frmt discard cntr */ + u32 fmbm_tbdc; /* Tx Buffers Deallocate Counter */ + u32 reserved0218[0x1A]; /* (0x218-0x280) */ + u32 fmbm_tpc; /* Tx Performance Counters */ + u32 fmbm_tpcp; /* Tx Performance Count Parameters */ + u32 fmbm_tccn; /* Tx Cycle Counter */ + u32 fmbm_ttuc; /* Tx Tasks Utilization Counter */ + u32 fmbm_ttcquc; /* Tx Transmit conf Q util Counter */ + u32 fmbm_tduc; /* Tx DMA Utilization Counter */ + u32 fmbm_tfuc; /* Tx FIFO Utilization Counter */ + u32 reserved029c[16]; /* (0x29C-0x2FF) */ + u32 fmbm_tdcfg[0x3]; /* Tx Debug Configuration */ + u32 fmbm_tgpr; /* Tx General Purpose Register */ + u32 reserved0310[0x3a]; /* (0x310-0x3FF) */ +}; + +/* BMI port register map */ +union fman_port_bmi_regs { + struct fman_port_rx_bmi_regs rx; + struct fman_port_tx_bmi_regs tx; +}; + +/* QMI port register map */ +struct fman_port_qmi_regs { + u32 fmqm_pnc; /* PortID n Configuration Register */ + u32 fmqm_pns; /* PortID n Status Register */ + u32 fmqm_pnts; /* PortID n Task Status Register */ + u32 reserved00c[4]; /* 0xn00C - 0xn01B */ + u32 fmqm_pnen; /* PortID n Enqueue NIA Register */ + u32 fmqm_pnetfc; /* PortID n Enq Total Frame Counter */ + u32 reserved024[2]; /* 0xn024 - 0x02B */ + u32 fmqm_pndn; /* PortID n Dequeue NIA Register */ + u32 fmqm_pndc; /* PortID n Dequeue Config Register */ + u32 fmqm_pndtfc; /* PortID n Dequeue tot Frame cntr */ + u32 fmqm_pndfdc; /* PortID n Dequeue FQID Dflt Cntr */ + u32 fmqm_pndcc; /* PortID n Dequeue Confirm Counter */ +}; + +/* QMI dequeue prefetch modes */ +enum fman_port_deq_prefetch { + FMAN_PORT_DEQ_NO_PREFETCH, /* No prefetch mode */ + FMAN_PORT_DEQ_PART_PREFETCH, /* Partial prefetch mode */ + FMAN_PORT_DEQ_FULL_PREFETCH /* Full prefetch mode */ +}; + +/* A structure for defining FM port resources */ +struct fman_port_rsrc { + u32 num; /* Committed required resource */ + u32 extra; /* Extra (not committed) required resource */ +}; + +enum fman_port_dma_swap { + FMAN_PORT_DMA_NO_SWAP, /* No swap, transfer data as is */ + FMAN_PORT_DMA_SWAP_LE, + /* The transferred data should be swapped in PPC Little Endian mode */ + FMAN_PORT_DMA_SWAP_BE + /* The transferred data should be swapped in Big Endian mode */ +}; + +/* Default port color */ +enum fman_port_color { + FMAN_PORT_COLOR_GREEN, /* Default port color is green */ + FMAN_PORT_COLOR_YELLOW, /* Default port color is yellow */ + FMAN_PORT_COLOR_RED, /* Default port color is red */ + FMAN_PORT_COLOR_OVERRIDE /* Ignore color */ +}; + +/* QMI dequeue from the SP channel - types */ +enum fman_port_deq_type { + FMAN_PORT_DEQ_BY_PRI, + /* Priority precedence and Intra-Class scheduling */ + FMAN_PORT_DEQ_ACTIVE_FQ, + /* Active FQ precedence and Intra-Class scheduling */ + FMAN_PORT_DEQ_ACTIVE_FQ_NO_ICS + /* Active FQ precedence and override Intra-Class scheduling */ +}; + +/* External buffer pools configuration */ +struct fman_port_bpools { + u8 count; /* Num of pools to set up */ + bool counters_enable; /* Enable allocate counters */ + u8 grp_bp_depleted_num; + /* Number of depleted pools - if reached the BMI indicates + * the MAC to send a pause frame + */ + struct { + u8 bpid; /* BM pool ID */ + u16 size; + /* Pool's size - must be in ascending order */ + bool is_backup; + /* If this is a backup pool */ + bool grp_bp_depleted; + /* Consider this buffer in multiple pools depletion criteria */ + bool single_bp_depleted; + /* Consider this buffer in single pool depletion criteria */ + } bpool[FMAN_PORT_MAX_EXT_POOLS_NUM]; +}; + +struct fman_port_cfg { + u32 dflt_fqid; + u32 err_fqid; + u8 deq_sp; + bool deq_high_priority; + enum fman_port_deq_type deq_type; + enum fman_port_deq_prefetch deq_prefetch_option; + u16 deq_byte_cnt; + u8 cheksum_last_bytes_ignore; + u8 rx_cut_end_bytes; + struct fman_buf_pool_depletion buf_pool_depletion; + struct fman_ext_pools ext_buf_pools; + u32 tx_fifo_min_level; + u32 tx_fifo_low_comf_level; + u32 rx_pri_elevation; + u32 rx_fifo_thr; + struct fman_sp_buf_margins buf_margins; + u32 int_buf_start_margin; + struct fman_sp_int_context_data_copy int_context; + u32 discard_mask; + u32 err_mask; + struct fman_buffer_prefix_content buffer_prefix_content; + bool dont_release_buf; + + u8 rx_fd_bits; + u32 tx_fifo_deq_pipeline_depth; + bool errata_A006320; + bool excessive_threshold_register; + bool fmbm_tfne_has_features; + + enum fman_port_dma_swap dma_swap_data; + enum fman_port_color color; +}; + +struct fman_port_rx_pools_params { + u8 num_of_pools; + u16 second_largest_buf_size; + u16 largest_buf_size; +}; + +struct fman_port_dts_params { + void __iomem *base_addr; /* FMan port virtual memory */ + enum fman_port_type type; /* Port type */ + u16 speed; /* Port speed */ + u8 id; /* HW Port Id */ + u32 qman_channel_id; /* QMan channel id (non RX only) */ + struct fman *fman; /* FMan Handle */ +}; + +struct fman_port { + void *fm; + struct device *dev; + struct fman_rev_info rev_info; + u8 port_id; + enum fman_port_type port_type; + u16 port_speed; + + union fman_port_bmi_regs __iomem *bmi_regs; + struct fman_port_qmi_regs __iomem *qmi_regs; + + struct fman_sp_buffer_offsets buffer_offsets; + + u8 internal_buf_offset; + struct fman_ext_pools ext_buf_pools; + + u16 max_frame_length; + struct fman_port_rsrc open_dmas; + struct fman_port_rsrc tasks; + struct fman_port_rsrc fifo_bufs; + struct fman_port_rx_pools_params rx_pools_params; + + struct fman_port_cfg *cfg; + struct fman_port_dts_params dts_params; + + u8 ext_pools_num; + u32 max_port_fifo_size; + u32 max_num_of_ext_pools; + u32 max_num_of_sub_portals; + u32 bm_max_num_of_pools; +}; + +static int init_bmi_rx(struct fman_port *port) +{ + struct fman_port_rx_bmi_regs __iomem *regs = &port->bmi_regs->rx; + struct fman_port_cfg *cfg = port->cfg; + u32 tmp; + + /* DMA attributes */ + tmp = (u32)cfg->dma_swap_data << BMI_DMA_ATTR_SWP_SHIFT; + /* Enable write optimization */ + tmp |= BMI_DMA_ATTR_WRITE_OPTIMIZE; + iowrite32be(tmp, ®s->fmbm_rda); + + /* Rx FIFO parameters */ + tmp = (cfg->rx_pri_elevation / PORT_BMI_FIFO_UNITS - 1) << + BMI_RX_FIFO_PRI_ELEVATION_SHIFT; + tmp |= cfg->rx_fifo_thr / PORT_BMI_FIFO_UNITS - 1; + iowrite32be(tmp, ®s->fmbm_rfp); + + if (cfg->excessive_threshold_register) + /* always allow access to the extra resources */ + iowrite32be(BMI_RX_FIFO_THRESHOLD_ETHE, ®s->fmbm_reth); + + /* Frame end data */ + tmp = (cfg->cheksum_last_bytes_ignore & BMI_FRAME_END_CS_IGNORE_MASK) << + BMI_FRAME_END_CS_IGNORE_SHIFT; + tmp |= (cfg->rx_cut_end_bytes & BMI_RX_FRAME_END_CUT_MASK) << + BMI_RX_FRAME_END_CUT_SHIFT; + if (cfg->errata_A006320) + tmp &= 0xffe0ffff; + iowrite32be(tmp, ®s->fmbm_rfed); + + /* Internal context parameters */ + tmp = ((cfg->int_context.ext_buf_offset / PORT_IC_OFFSET_UNITS) & + BMI_IC_TO_EXT_MASK) << BMI_IC_TO_EXT_SHIFT; + tmp |= ((cfg->int_context.int_context_offset / PORT_IC_OFFSET_UNITS) & + BMI_IC_FROM_INT_MASK) << BMI_IC_FROM_INT_SHIFT; + tmp |= (cfg->int_context.size / PORT_IC_OFFSET_UNITS) & + BMI_IC_SIZE_MASK; + iowrite32be(tmp, ®s->fmbm_ricp); + + /* Internal buffer offset */ + tmp = ((cfg->int_buf_start_margin / PORT_IC_OFFSET_UNITS) & + BMI_INT_BUF_MARG_MASK) << BMI_INT_BUF_MARG_SHIFT; + iowrite32be(tmp, ®s->fmbm_rim); + + /* External buffer margins */ + tmp = (cfg->buf_margins.start_margins & BMI_EXT_BUF_MARG_START_MASK) << + BMI_EXT_BUF_MARG_START_SHIFT; + tmp |= cfg->buf_margins.end_margins & BMI_EXT_BUF_MARG_END_MASK; + iowrite32be(tmp, ®s->fmbm_rebm); + + /* Frame attributes */ + tmp = BMI_CMD_RX_MR_DEF; + tmp |= BMI_CMD_ATTR_ORDER; + tmp |= (u32)cfg->color << BMI_CMD_ATTR_COLOR_SHIFT; + /* Synchronization request */ + tmp |= BMI_CMD_ATTR_SYNC; + + iowrite32be(tmp, ®s->fmbm_rfca); + + /* NIA */ + tmp = (u32)cfg->rx_fd_bits << BMI_NEXT_ENG_FD_BITS_SHIFT; + + tmp |= NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME; + iowrite32be(tmp, ®s->fmbm_rfne); + + /* Enqueue NIA */ + iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, ®s->fmbm_rfene); + + /* Default/error queues */ + iowrite32be((cfg->dflt_fqid & DFLT_FQ_ID), ®s->fmbm_rfqid); + iowrite32be((cfg->err_fqid & DFLT_FQ_ID), ®s->fmbm_refqid); + + /* Discard/error masks */ + iowrite32be(cfg->discard_mask, ®s->fmbm_rfsdm); + iowrite32be(cfg->err_mask, ®s->fmbm_rfsem); + + return 0; +} + +static int init_bmi_tx(struct fman_port *port) +{ + struct fman_port_tx_bmi_regs __iomem *regs = &port->bmi_regs->tx; + struct fman_port_cfg *cfg = port->cfg; + u32 tmp; + + /* Tx Configuration register */ + tmp = 0; + iowrite32be(tmp, ®s->fmbm_tcfg); + + /* DMA attributes */ + tmp = (u32)cfg->dma_swap_data << BMI_DMA_ATTR_SWP_SHIFT; + iowrite32be(tmp, ®s->fmbm_tda); + + /* Tx FIFO parameters */ + tmp = (cfg->tx_fifo_min_level / PORT_BMI_FIFO_UNITS) << + BMI_TX_FIFO_MIN_FILL_SHIFT; + tmp |= ((cfg->tx_fifo_deq_pipeline_depth - 1) & + BMI_FIFO_PIPELINE_DEPTH_MASK) << BMI_FIFO_PIPELINE_DEPTH_SHIFT; + tmp |= (cfg->tx_fifo_low_comf_level / PORT_BMI_FIFO_UNITS) - 1; + iowrite32be(tmp, ®s->fmbm_tfp); + + /* Frame end data */ + tmp = (cfg->cheksum_last_bytes_ignore & BMI_FRAME_END_CS_IGNORE_MASK) << + BMI_FRAME_END_CS_IGNORE_SHIFT; + iowrite32be(tmp, ®s->fmbm_tfed); + + /* Internal context parameters */ + tmp = ((cfg->int_context.ext_buf_offset / PORT_IC_OFFSET_UNITS) & + BMI_IC_TO_EXT_MASK) << BMI_IC_TO_EXT_SHIFT; + tmp |= ((cfg->int_context.int_context_offset / PORT_IC_OFFSET_UNITS) & + BMI_IC_FROM_INT_MASK) << BMI_IC_FROM_INT_SHIFT; + tmp |= (cfg->int_context.size / PORT_IC_OFFSET_UNITS) & + BMI_IC_SIZE_MASK; + iowrite32be(tmp, ®s->fmbm_ticp); + + /* Frame attributes */ + tmp = BMI_CMD_TX_MR_DEF; + tmp |= BMI_CMD_ATTR_ORDER; + tmp |= (u32)cfg->color << BMI_CMD_ATTR_COLOR_SHIFT; + iowrite32be(tmp, ®s->fmbm_tfca); + + /* Dequeue NIA + enqueue NIA */ + iowrite32be(NIA_ENG_QMI_DEQ, ®s->fmbm_tfdne); + iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, ®s->fmbm_tfene); + if (cfg->fmbm_tfne_has_features) + iowrite32be(!cfg->dflt_fqid ? + BMI_EBD_EN | NIA_BMI_AC_FETCH_ALL_FRAME : + NIA_BMI_AC_FETCH_ALL_FRAME, ®s->fmbm_tfne); + if (!cfg->dflt_fqid && cfg->dont_release_buf) { + iowrite32be(DFLT_FQ_ID, ®s->fmbm_tcfqid); + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_TX_RELEASE, + ®s->fmbm_tfene); + if (cfg->fmbm_tfne_has_features) + iowrite32be(ioread32be(®s->fmbm_tfne) & ~BMI_EBD_EN, + ®s->fmbm_tfne); + } + + /* Confirmation/error queues */ + if (cfg->dflt_fqid || !cfg->dont_release_buf) + iowrite32be(cfg->dflt_fqid & DFLT_FQ_ID, ®s->fmbm_tcfqid); + iowrite32be((cfg->err_fqid & DFLT_FQ_ID), ®s->fmbm_tefqid); + + return 0; +} + +static int init_qmi(struct fman_port *port) +{ + struct fman_port_qmi_regs __iomem *regs = port->qmi_regs; + struct fman_port_cfg *cfg = port->cfg; + u32 tmp; + + /* Rx port configuration */ + if (port->port_type == FMAN_PORT_TYPE_RX) { + /* Enqueue NIA */ + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_RELEASE, ®s->fmqm_pnen); + return 0; + } + + /* Continue with Tx port configuration */ + if (port->port_type == FMAN_PORT_TYPE_TX) { + /* Enqueue NIA */ + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_TX_RELEASE, + ®s->fmqm_pnen); + /* Dequeue NIA */ + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_TX, ®s->fmqm_pndn); + } + + /* Dequeue Configuration register */ + tmp = 0; + if (cfg->deq_high_priority) + tmp |= QMI_DEQ_CFG_PRI; + + switch (cfg->deq_type) { + case FMAN_PORT_DEQ_BY_PRI: + tmp |= QMI_DEQ_CFG_TYPE1; + break; + case FMAN_PORT_DEQ_ACTIVE_FQ: + tmp |= QMI_DEQ_CFG_TYPE2; + break; + case FMAN_PORT_DEQ_ACTIVE_FQ_NO_ICS: + tmp |= QMI_DEQ_CFG_TYPE3; + break; + default: + return -EINVAL; + } + + switch (cfg->deq_prefetch_option) { + case FMAN_PORT_DEQ_NO_PREFETCH: + break; + case FMAN_PORT_DEQ_PART_PREFETCH: + tmp |= QMI_DEQ_CFG_PREFETCH_PARTIAL; + break; + case FMAN_PORT_DEQ_FULL_PREFETCH: + tmp |= QMI_DEQ_CFG_PREFETCH_FULL; + break; + default: + return -EINVAL; + } + + tmp |= (cfg->deq_sp & QMI_DEQ_CFG_SP_MASK) << QMI_DEQ_CFG_SP_SHIFT; + tmp |= cfg->deq_byte_cnt; + iowrite32be(tmp, ®s->fmqm_pndc); + + return 0; +} + +static int init(struct fman_port *port) +{ + int err; + + /* Init BMI registers */ + switch (port->port_type) { + case FMAN_PORT_TYPE_RX: + err = init_bmi_rx(port); + break; + case FMAN_PORT_TYPE_TX: + err = init_bmi_tx(port); + break; + default: + return -EINVAL; + } + + if (err) + return err; + + /* Init QMI registers */ + err = init_qmi(port); + return err; + + return 0; +} + +static int set_bpools(const struct fman_port *port, + const struct fman_port_bpools *bp) +{ + u32 __iomem *bp_reg, *bp_depl_reg; + u32 tmp; + u8 i, max_bp_num; + bool grp_depl_used = false, rx_port; + + switch (port->port_type) { + case FMAN_PORT_TYPE_RX: + max_bp_num = port->ext_pools_num; + rx_port = true; + bp_reg = port->bmi_regs->rx.fmbm_ebmpi; + bp_depl_reg = &port->bmi_regs->rx.fmbm_mpd; + break; + default: + return -EINVAL; + } + + if (rx_port) { + /* Check buffers are provided in ascending order */ + for (i = 0; (i < (bp->count - 1) && + (i < FMAN_PORT_MAX_EXT_POOLS_NUM - 1)); i++) { + if (bp->bpool[i].size > bp->bpool[i + 1].size) + return -EINVAL; + } + } + + /* Set up external buffers pools */ + for (i = 0; i < bp->count; i++) { + tmp = BMI_EXT_BUF_POOL_VALID; + tmp |= ((u32)bp->bpool[i].bpid << + BMI_EXT_BUF_POOL_ID_SHIFT) & BMI_EXT_BUF_POOL_ID_MASK; + + if (rx_port) { + if (bp->counters_enable) + tmp |= BMI_EXT_BUF_POOL_EN_COUNTER; + + if (bp->bpool[i].is_backup) + tmp |= BMI_EXT_BUF_POOL_BACKUP; + + tmp |= (u32)bp->bpool[i].size; + } + + iowrite32be(tmp, &bp_reg[i]); + } + + /* Clear unused pools */ + for (i = bp->count; i < max_bp_num; i++) + iowrite32be(0, &bp_reg[i]); + + /* Pools depletion */ + tmp = 0; + for (i = 0; i < FMAN_PORT_MAX_EXT_POOLS_NUM; i++) { + if (bp->bpool[i].grp_bp_depleted) { + grp_depl_used = true; + tmp |= 0x80000000 >> i; + } + + if (bp->bpool[i].single_bp_depleted) + tmp |= 0x80 >> i; + } + + if (grp_depl_used) + tmp |= ((u32)bp->grp_bp_depleted_num - 1) << + BMI_POOL_DEP_NUM_OF_POOLS_SHIFT; + + iowrite32be(tmp, bp_depl_reg); + return 0; +} + +static bool is_init_done(struct fman_port_cfg *cfg) +{ + /* Checks if FMan port driver parameters were initialized */ + if (!cfg) + return true; + + return false; +} + +static int verify_size_of_fifo(struct fman_port *port) +{ + u32 min_fifo_size_required = 0, opt_fifo_size_for_b2b = 0; + + /* TX Ports */ + if (port->port_type == FMAN_PORT_TYPE_TX) { + min_fifo_size_required = (u32) + (roundup(port->max_frame_length, + FMAN_BMI_FIFO_UNITS) + (3 * FMAN_BMI_FIFO_UNITS)); + + min_fifo_size_required += + port->cfg->tx_fifo_deq_pipeline_depth * + FMAN_BMI_FIFO_UNITS; + + opt_fifo_size_for_b2b = min_fifo_size_required; + + /* Add some margin for back-to-back capability to improve + * performance, allows the hardware to pipeline new frame dma + * while the previous frame not yet transmitted. + */ + if (port->port_speed == 10000) + opt_fifo_size_for_b2b += 3 * FMAN_BMI_FIFO_UNITS; + else + opt_fifo_size_for_b2b += 2 * FMAN_BMI_FIFO_UNITS; + } + + /* RX Ports */ + else if (port->port_type == FMAN_PORT_TYPE_RX) { + if (port->rev_info.major >= 6) + min_fifo_size_required = (u32) + (roundup(port->max_frame_length, + FMAN_BMI_FIFO_UNITS) + + (5 * FMAN_BMI_FIFO_UNITS)); + /* 4 according to spec + 1 for FOF>0 */ + else + min_fifo_size_required = (u32) + (roundup(min(port->max_frame_length, + port->rx_pools_params.largest_buf_size), + FMAN_BMI_FIFO_UNITS) + + (7 * FMAN_BMI_FIFO_UNITS)); + + opt_fifo_size_for_b2b = min_fifo_size_required; + + /* Add some margin for back-to-back capability to improve + * performance,allows the hardware to pipeline new frame dma + * while the previous frame not yet transmitted. + */ + if (port->port_speed == 10000) + opt_fifo_size_for_b2b += 8 * FMAN_BMI_FIFO_UNITS; + else + opt_fifo_size_for_b2b += 3 * FMAN_BMI_FIFO_UNITS; + } + + WARN_ON(min_fifo_size_required <= 0); + WARN_ON(opt_fifo_size_for_b2b < min_fifo_size_required); + + /* Verify the size */ + if (port->fifo_bufs.num < min_fifo_size_required) + dev_dbg(port->dev, "%s: FIFO size should be enlarged to %d bytes\n", + __func__, min_fifo_size_required); + else if (port->fifo_bufs.num < opt_fifo_size_for_b2b) + dev_dbg(port->dev, "%s: For b2b processing,FIFO may be enlarged to %d bytes\n", + __func__, opt_fifo_size_for_b2b); + + return 0; +} + +static int set_ext_buffer_pools(struct fman_port *port) +{ + struct fman_ext_pools *ext_buf_pools = &port->cfg->ext_buf_pools; + struct fman_buf_pool_depletion *buf_pool_depletion = + &port->cfg->buf_pool_depletion; + u8 ordered_array[FMAN_PORT_MAX_EXT_POOLS_NUM]; + u16 sizes_array[BM_MAX_NUM_OF_POOLS]; + int i = 0, j = 0, err; + struct fman_port_bpools bpools; + + memset(&ordered_array, 0, sizeof(u8) * FMAN_PORT_MAX_EXT_POOLS_NUM); + memset(&sizes_array, 0, sizeof(u16) * BM_MAX_NUM_OF_POOLS); + memcpy(&port->ext_buf_pools, ext_buf_pools, + sizeof(struct fman_ext_pools)); + + fman_sp_set_buf_pools_in_asc_order_of_buf_sizes(ext_buf_pools, + ordered_array, + sizes_array); + + memset(&bpools, 0, sizeof(struct fman_port_bpools)); + bpools.count = ext_buf_pools->num_of_pools_used; + bpools.counters_enable = true; + for (i = 0; i < ext_buf_pools->num_of_pools_used; i++) { + bpools.bpool[i].bpid = ordered_array[i]; + bpools.bpool[i].size = sizes_array[ordered_array[i]]; + } + + /* save pools parameters for later use */ + port->rx_pools_params.num_of_pools = ext_buf_pools->num_of_pools_used; + port->rx_pools_params.largest_buf_size = + sizes_array[ordered_array[ext_buf_pools->num_of_pools_used - 1]]; + port->rx_pools_params.second_largest_buf_size = + sizes_array[ordered_array[ext_buf_pools->num_of_pools_used - 2]]; + + /* FMBM_RMPD reg. - pool depletion */ + if (buf_pool_depletion->pools_grp_mode_enable) { + bpools.grp_bp_depleted_num = buf_pool_depletion->num_of_pools; + for (i = 0; i < port->bm_max_num_of_pools; i++) { + if (buf_pool_depletion->pools_to_consider[i]) { + for (j = 0; j < ext_buf_pools-> + num_of_pools_used; j++) { + if (i == ordered_array[j]) { + bpools.bpool[j]. + grp_bp_depleted = true; + break; + } + } + } + } + } + + if (buf_pool_depletion->single_pool_mode_enable) { + for (i = 0; i < port->bm_max_num_of_pools; i++) { + if (buf_pool_depletion-> + pools_to_consider_for_single_mode[i]) { + for (j = 0; j < ext_buf_pools-> + num_of_pools_used; j++) { + if (i == ordered_array[j]) { + bpools.bpool[j]. + single_bp_depleted = true; + break; + } + } + } + } + } + + err = set_bpools(port, &bpools); + if (err != 0) { + dev_err(port->dev, "%s: set_bpools() failed\n", __func__); + return -EINVAL; + } + + return 0; +} + +static int init_low_level_driver(struct fman_port *port) +{ + struct fman_port_cfg *cfg = port->cfg; + u32 tmp_val; + + switch (port->port_type) { + case FMAN_PORT_TYPE_RX: + cfg->err_mask = (RX_ERRS_TO_ENQ & ~cfg->discard_mask); + break; + default: + break; + } + + tmp_val = (u32)((port->internal_buf_offset % OFFSET_UNITS) ? + (port->internal_buf_offset / OFFSET_UNITS + 1) : + (port->internal_buf_offset / OFFSET_UNITS)); + port->internal_buf_offset = (u8)(tmp_val * OFFSET_UNITS); + port->cfg->int_buf_start_margin = port->internal_buf_offset; + + if (init(port) != 0) { + dev_err(port->dev, "%s: fman port initialization failed\n", + __func__); + return -ENODEV; + } + + /* The code bellow is a trick so the FM will not release the buffer + * to BM nor will try to enqueue the frame to QM + */ + if (port->port_type == FMAN_PORT_TYPE_TX) { + if (!cfg->dflt_fqid && cfg->dont_release_buf) { + /* override fmbm_tcfqid 0 with a false non-0 value. + * This will force FM to act according to tfene. + * Otherwise, if fmbm_tcfqid is 0 the FM will release + * buffers to BM regardless of fmbm_tfene + */ + iowrite32be(0xFFFFFF, &port->bmi_regs->tx.fmbm_tcfqid); + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_TX_RELEASE, + &port->bmi_regs->tx.fmbm_tfene); + } + } + + return 0; +} + +static int fill_soc_specific_params(struct fman_port *port) +{ + u32 bmi_max_fifo_size; + + bmi_max_fifo_size = fman_get_bmi_max_fifo_size(port->fm); + port->max_port_fifo_size = MAX_PORT_FIFO_SIZE(bmi_max_fifo_size); + port->bm_max_num_of_pools = 64; + + /* P4080 - Major 2 + * P2041/P3041/P5020/P5040 - Major 3 + * Tx/Bx - Major 6 + */ + switch (port->rev_info.major) { + case 2: + case 3: + port->max_num_of_ext_pools = 4; + port->max_num_of_sub_portals = 12; + break; + + case 6: + port->max_num_of_ext_pools = 8; + port->max_num_of_sub_portals = 16; + break; + + default: + dev_err(port->dev, "%s: Unsupported FMan version\n", __func__); + return -EINVAL; + } + + return 0; +} + +static int get_dflt_fifo_deq_pipeline_depth(u8 major, enum fman_port_type type, + u16 speed) +{ + switch (type) { + case FMAN_PORT_TYPE_RX: + case FMAN_PORT_TYPE_TX: + switch (speed) { + case 10000: + return 4; + case 1000: + if (major >= 6) + return 2; + else + return 1; + default: + return 0; + } + default: + return 0; + } +} + +static int get_dflt_num_of_tasks(u8 major, enum fman_port_type type, + u16 speed) +{ + switch (type) { + case FMAN_PORT_TYPE_RX: + case FMAN_PORT_TYPE_TX: + switch (speed) { + case 10000: + return 16; + case 1000: + if (major >= 6) + return 4; + else + return 3; + default: + return 0; + } + default: + return 0; + } +} + +static int get_dflt_extra_num_of_tasks(u8 major, enum fman_port_type type, + u16 speed) +{ + switch (type) { + case FMAN_PORT_TYPE_RX: + /* FMan V3 */ + if (major >= 6) + return 0; + + /* FMan V2 */ + if (speed == 10000) + return 8; + else + return 2; + case FMAN_PORT_TYPE_TX: + default: + return 0; + } +} + +static int get_dflt_num_of_open_dmas(u8 major, enum fman_port_type type, + u16 speed) +{ + int val; + + if (major >= 6) { + switch (type) { + case FMAN_PORT_TYPE_TX: + if (speed == 10000) + val = 12; + else + val = 3; + break; + case FMAN_PORT_TYPE_RX: + if (speed == 10000) + val = 8; + else + val = 2; + break; + default: + return 0; + } + } else { + switch (type) { + case FMAN_PORT_TYPE_TX: + case FMAN_PORT_TYPE_RX: + if (speed == 10000) + val = 8; + else + val = 1; + break; + default: + val = 0; + } + } + + return val; +} + +static int get_dflt_extra_num_of_open_dmas(u8 major, enum fman_port_type type, + u16 speed) +{ + /* FMan V3 */ + if (major >= 6) + return 0; + + /* FMan V2 */ + switch (type) { + case FMAN_PORT_TYPE_RX: + case FMAN_PORT_TYPE_TX: + if (speed == 10000) + return 8; + else + return 1; + default: + return 0; + } +} + +static int get_dflt_num_of_fifo_bufs(u8 major, enum fman_port_type type, + u16 speed) +{ + int val; + + if (major >= 6) { + switch (type) { + case FMAN_PORT_TYPE_TX: + if (speed == 10000) + val = 64; + else + val = 50; + break; + case FMAN_PORT_TYPE_RX: + if (speed == 10000) + val = 96; + else + val = 50; + break; + default: + val = 0; + } + } else { + switch (type) { + case FMAN_PORT_TYPE_TX: + if (speed == 10000) + val = 48; + else + val = 44; + break; + case FMAN_PORT_TYPE_RX: + if (speed == 10000) + val = 48; + else + val = 45; + break; + default: + val = 0; + } + } + + return val; +} + +static void set_dflt_cfg(struct fman_port *port, + struct fman_port_params *port_params) +{ + struct fman_port_cfg *cfg = port->cfg; + + cfg->dma_swap_data = FMAN_PORT_DMA_NO_SWAP; + cfg->color = FMAN_PORT_COLOR_GREEN; + cfg->rx_cut_end_bytes = DFLT_PORT_CUT_BYTES_FROM_END; + cfg->rx_pri_elevation = BMI_PRIORITY_ELEVATION_LEVEL; + cfg->rx_fifo_thr = BMI_FIFO_THRESHOLD; + cfg->tx_fifo_low_comf_level = (5 * 1024); + cfg->deq_type = FMAN_PORT_DEQ_BY_PRI; + cfg->deq_prefetch_option = FMAN_PORT_DEQ_FULL_PREFETCH; + cfg->tx_fifo_deq_pipeline_depth = + BMI_DEQUEUE_PIPELINE_DEPTH(port->port_type, port->port_speed); + cfg->deq_byte_cnt = QMI_BYTE_COUNT_LEVEL_CONTROL(port->port_type); + + cfg->rx_pri_elevation = + DFLT_PORT_RX_FIFO_PRI_ELEVATION_LEV(port->max_port_fifo_size); + port->cfg->rx_fifo_thr = + DFLT_PORT_RX_FIFO_THRESHOLD(port->rev_info.major, + port->max_port_fifo_size); + + if ((port->rev_info.major == 6) && + ((port->rev_info.minor == 0) || (port->rev_info.minor == 3))) + cfg->errata_A006320 = true; + + /* Excessive Threshold register - exists for pre-FMv3 chips only */ + if (port->rev_info.major < 6) + cfg->excessive_threshold_register = true; + else + cfg->fmbm_tfne_has_features = true; + + cfg->buffer_prefix_content.data_align = + DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN; +} + +static void set_rx_dflt_cfg(struct fman_port *port, + struct fman_port_params *port_params) +{ + port->cfg->discard_mask = DFLT_PORT_ERRORS_TO_DISCARD; + + memcpy(&port->cfg->ext_buf_pools, + &port_params->specific_params.rx_params.ext_buf_pools, + sizeof(struct fman_ext_pools)); + port->cfg->err_fqid = + port_params->specific_params.rx_params.err_fqid; + port->cfg->dflt_fqid = + port_params->specific_params.rx_params.dflt_fqid; +} + +static void set_tx_dflt_cfg(struct fman_port *port, + struct fman_port_params *port_params, + struct fman_port_dts_params *dts_params) +{ + port->cfg->tx_fifo_deq_pipeline_depth = + get_dflt_fifo_deq_pipeline_depth(port->rev_info.major, + port->port_type, + port->port_speed); + port->cfg->err_fqid = + port_params->specific_params.non_rx_params.err_fqid; + port->cfg->deq_sp = + (u8)(dts_params->qman_channel_id & QMI_DEQ_CFG_SUBPORTAL_MASK); + port->cfg->dflt_fqid = + port_params->specific_params.non_rx_params.dflt_fqid; + port->cfg->deq_high_priority = true; +} + +/** + * fman_port_config + * @port: Pointer to the port structure + * @params: Pointer to data structure of parameters + * + * Creates a descriptor for the FM PORT module. + * The routine returns a pointer to the FM PORT object. + * This descriptor must be passed as first parameter to all other FM PORT + * function calls. + * No actual initialization or configuration of FM hardware is done by this + * routine. + * + * Return: 0 on success; Error code otherwise. + */ +int fman_port_config(struct fman_port *port, struct fman_port_params *params) +{ + void __iomem *base_addr = port->dts_params.base_addr; + int err; + + /* Allocate the FM driver's parameters structure */ + port->cfg = kzalloc(sizeof(*port->cfg), GFP_KERNEL); + if (!port->cfg) + goto err_params; + + /* Initialize FM port parameters which will be kept by the driver */ + port->port_type = port->dts_params.type; + port->port_speed = port->dts_params.speed; + port->port_id = port->dts_params.id; + port->fm = port->dts_params.fman; + port->ext_pools_num = (u8)8; + + /* get FM revision */ + fman_get_revision(port->fm, &port->rev_info); + + err = fill_soc_specific_params(port); + if (err) + goto err_port_cfg; + + switch (port->port_type) { + case FMAN_PORT_TYPE_RX: + set_rx_dflt_cfg(port, params); + case FMAN_PORT_TYPE_TX: + set_tx_dflt_cfg(port, params, &port->dts_params); + default: + set_dflt_cfg(port, params); + } + + /* Continue with other parameters */ + /* set memory map pointers */ + port->bmi_regs = base_addr + BMI_PORT_REGS_OFFSET; + port->qmi_regs = base_addr + QMI_PORT_REGS_OFFSET; + + port->max_frame_length = DFLT_PORT_MAX_FRAME_LENGTH; + /* resource distribution. */ + + port->fifo_bufs.num = + get_dflt_num_of_fifo_bufs(port->rev_info.major, port->port_type, + port->port_speed) * FMAN_BMI_FIFO_UNITS; + port->fifo_bufs.extra = + DFLT_PORT_EXTRA_NUM_OF_FIFO_BUFS * FMAN_BMI_FIFO_UNITS; + + port->open_dmas.num = + get_dflt_num_of_open_dmas(port->rev_info.major, + port->port_type, port->port_speed); + port->open_dmas.extra = + get_dflt_extra_num_of_open_dmas(port->rev_info.major, + port->port_type, port->port_speed); + port->tasks.num = + get_dflt_num_of_tasks(port->rev_info.major, + port->port_type, port->port_speed); + port->tasks.extra = + get_dflt_extra_num_of_tasks(port->rev_info.major, + port->port_type, port->port_speed); + + /* FM_HEAVY_TRAFFIC_SEQUENCER_HANG_ERRATA_FMAN_A006981 errata + * workaround + */ + if ((port->rev_info.major == 6) && (port->rev_info.minor == 0) && + (((port->port_type == FMAN_PORT_TYPE_TX) && + (port->port_speed == 1000)))) { + port->open_dmas.num = 16; + port->open_dmas.extra = 0; + } + + if (port->rev_info.major >= 6 && + port->port_type == FMAN_PORT_TYPE_TX && + port->port_speed == 1000) { + /* FM_WRONG_RESET_VALUES_ERRATA_FMAN_A005127 Errata + * workaround + */ + if (port->rev_info.major >= 6) { + u32 reg; + + reg = 0x00001013; + iowrite32be(reg, &port->bmi_regs->tx.fmbm_tfp); + } + } + + return 0; + +err_port_cfg: + kfree(port->cfg); +err_params: + kfree(port); + return -EINVAL; +} +EXPORT_SYMBOL(fman_port_config); + +/** + * fman_port_init + * port: A pointer to a FM Port module. + * Initializes the FM PORT module by defining the software structure and + * configuring the hardware registers. + * + * Return: 0 on success; Error code otherwise. + */ +int fman_port_init(struct fman_port *port) +{ + struct fman_port_cfg *cfg; + int err; + struct fman_port_init_params params; + + if (is_init_done(port->cfg)) + return -EINVAL; + + err = fman_sp_build_buffer_struct(&port->cfg->int_context, + &port->cfg->buffer_prefix_content, + &port->cfg->buf_margins, + &port->buffer_offsets, + &port->internal_buf_offset); + if (err) + return err; + + cfg = port->cfg; + + if (port->port_type == FMAN_PORT_TYPE_RX) { + /* Call the external Buffer routine which also checks fifo + * size and updates it if necessary + */ + /* define external buffer pools and pool depletion */ + err = set_ext_buffer_pools(port); + if (err) + return err; + /* check if the largest external buffer pool is large enough */ + if (cfg->buf_margins.start_margins + MIN_EXT_BUF_SIZE + + cfg->buf_margins.end_margins > + port->rx_pools_params.largest_buf_size) { + dev_err(port->dev, "%s: buf_margins.start_margins (%d) + minimum buf size (64) + buf_margins.end_margins (%d) is larger than maximum external buffer size (%d)\n", + __func__, cfg->buf_margins.start_margins, + cfg->buf_margins.end_margins, + port->rx_pools_params.largest_buf_size); + return -EINVAL; + } + } + + /* Call FM module routine for communicating parameters */ + memset(¶ms, 0, sizeof(params)); + params.port_id = port->port_id; + params.port_type = port->port_type; + params.port_speed = port->port_speed; + params.num_of_tasks = (u8)port->tasks.num; + params.num_of_extra_tasks = (u8)port->tasks.extra; + params.num_of_open_dmas = (u8)port->open_dmas.num; + params.num_of_extra_open_dmas = (u8)port->open_dmas.extra; + + if (port->fifo_bufs.num) { + err = verify_size_of_fifo(port); + if (err) + return err; + } + params.size_of_fifo = port->fifo_bufs.num; + params.extra_size_of_fifo = port->fifo_bufs.extra; + params.deq_pipeline_depth = port->cfg->tx_fifo_deq_pipeline_depth; + params.max_frame_length = port->max_frame_length; + + err = fman_set_port_params(port->fm, ¶ms); + if (err) + return err; + + err = init_low_level_driver(port); + if (err) + return err; + + kfree(port->cfg); + port->cfg = NULL; + + return 0; +} +EXPORT_SYMBOL(fman_port_init); + +/** + * fman_port_cfg_buf_prefix_content + * @port A pointer to a FM Port module. + * @buffer_prefix_content A structure of parameters describing + * the structure of the buffer. + * Out parameter: + * Start margin - offset of data from + * start of external buffer. + * Defines the structure, size and content of the application buffer. + * The prefix, in Tx ports, if 'pass_prs_result', the application should set + * a value to their offsets in the prefix of the FM will save the first + * 'priv_data_size', than, depending on 'pass_prs_result' and + * 'pass_time_stamp', copy parse result and timeStamp, and the packet itself + * (in this order), to the application buffer, and to offset. + * Calling this routine changes the buffer margins definitions in the internal + * driver data base from its default configuration: + * Data size: [DEFAULT_PORT_BUFFER_PREFIX_CONTENT_PRIV_DATA_SIZE] + * Pass Parser result: [DEFAULT_PORT_BUFFER_PREFIX_CONTENT_PASS_PRS_RESULT]. + * Pass timestamp: [DEFAULT_PORT_BUFFER_PREFIX_CONTENT_PASS_TIME_STAMP]. + * May be used for all ports + * + * Allowed only following fman_port_config() and before fman_port_init(). + * + * Return: 0 on success; Error code otherwise. + */ +int fman_port_cfg_buf_prefix_content(struct fman_port *port, + struct fman_buffer_prefix_content * + buffer_prefix_content) +{ + if (is_init_done(port->cfg)) + return -EINVAL; + + memcpy(&port->cfg->buffer_prefix_content, + buffer_prefix_content, + sizeof(struct fman_buffer_prefix_content)); + /* if data_align was not initialized by user, + * we return to driver's default + */ + if (!port->cfg->buffer_prefix_content.data_align) + port->cfg->buffer_prefix_content.data_align = + DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN; + + return 0; +} +EXPORT_SYMBOL(fman_port_cfg_buf_prefix_content); + +/** + * fman_port_disable + * port: A pointer to a FM Port module. + * + * Gracefully disable an FM port. The port will not start new tasks after all + * tasks associated with the port are terminated. + * + * This is a blocking routine, it returns after port is gracefully stopped, + * i.e. the port will not except new frames, but it will finish all frames + * or tasks which were already began. + * Allowed only following fman_port_init(). + * + * Return: 0 on success; Error code otherwise. + */ +int fman_port_disable(struct fman_port *port) +{ + u32 __iomem *bmi_cfg_reg, *bmi_status_reg, tmp; + bool rx_port, failure = false; + int count; + + if (!is_init_done(port->cfg)) + return -EINVAL; + + switch (port->port_type) { + case FMAN_PORT_TYPE_RX: + bmi_cfg_reg = &port->bmi_regs->rx.fmbm_rcfg; + bmi_status_reg = &port->bmi_regs->rx.fmbm_rst; + rx_port = true; + break; + case FMAN_PORT_TYPE_TX: + bmi_cfg_reg = &port->bmi_regs->tx.fmbm_tcfg; + bmi_status_reg = &port->bmi_regs->tx.fmbm_tst; + rx_port = false; + break; + default: + return -EINVAL; + } + + /* Disable QMI */ + if (!rx_port) { + tmp = ioread32be(&port->qmi_regs->fmqm_pnc) & ~QMI_PORT_CFG_EN; + iowrite32be(tmp, &port->qmi_regs->fmqm_pnc); + + /* Wait for QMI to finish FD handling */ + count = 100; + do { + udelay(10); + tmp = ioread32be(&port->qmi_regs->fmqm_pns); + } while ((tmp & QMI_PORT_STATUS_DEQ_FD_BSY) && --count); + + if (count == 0) { + /* Timeout */ + failure = true; + } + } + + /* Disable BMI */ + tmp = ioread32be(bmi_cfg_reg) & ~BMI_PORT_CFG_EN; + iowrite32be(tmp, bmi_cfg_reg); + + /* Wait for graceful stop end */ + count = 500; + do { + udelay(10); + tmp = ioread32be(bmi_status_reg); + } while ((tmp & BMI_PORT_STATUS_BSY) && --count); + + if (count == 0) { + /* Timeout */ + failure = true; + } + + if (failure) + dev_dbg(port->dev, "%s: FMan Port[%d]: BMI or QMI is Busy. Port forced down\n", + __func__, port->port_id); + + return 0; +} +EXPORT_SYMBOL(fman_port_disable); + +/** + * fman_port_enable + * port: A pointer to a FM Port module. + * + * A runtime routine provided to allow disable/enable of port. + * + * Allowed only following fman_port_init(). + * + * Return: 0 on success; Error code otherwise. + */ +int fman_port_enable(struct fman_port *port) +{ + u32 __iomem *bmi_cfg_reg, tmp; + bool rx_port; + + if (!is_init_done(port->cfg)) + return -EINVAL; + + switch (port->port_type) { + case FMAN_PORT_TYPE_RX: + bmi_cfg_reg = &port->bmi_regs->rx.fmbm_rcfg; + rx_port = true; + break; + case FMAN_PORT_TYPE_TX: + bmi_cfg_reg = &port->bmi_regs->tx.fmbm_tcfg; + rx_port = false; + break; + default: + return -EINVAL; + } + + /* Enable QMI */ + if (!rx_port) { + tmp = ioread32be(&port->qmi_regs->fmqm_pnc) | QMI_PORT_CFG_EN; + iowrite32be(tmp, &port->qmi_regs->fmqm_pnc); + } + + /* Enable BMI */ + tmp = ioread32be(bmi_cfg_reg) | BMI_PORT_CFG_EN; + iowrite32be(tmp, bmi_cfg_reg); + + return 0; +} +EXPORT_SYMBOL(fman_port_enable); + +/** + * fman_port_bind + * dev: FMan Port OF device pointer + * + * Bind to a specific FMan Port. + * + * Allowed only after the port was created. + * + * Return: A pointer to the FMan port device. + */ +struct fman_port *fman_port_bind(struct device *dev) +{ + return (struct fman_port *)(dev_get_drvdata(get_device(dev))); +} +EXPORT_SYMBOL(fman_port_bind); + +/** + * fman_port_get_qman_channel_id + * port: Pointer to the FMan port devuce + * + * Get the QMan channel ID for the specific port + * + * Return: QMan channel ID + */ +u32 fman_port_get_qman_channel_id(struct fman_port *port) +{ + return port->dts_params.qman_channel_id; +} +EXPORT_SYMBOL(fman_port_get_qman_channel_id); + +static int fman_port_probe(struct platform_device *of_dev) +{ + struct fman_port *port; + struct fman *fman; + struct device_node *fm_node, *port_node; + struct resource res; + struct resource *dev_res; + const u32 *u32_prop; + int err = 0, lenp; + enum fman_port_type port_type; + u16 port_speed; + u8 port_id; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->dev = &of_dev->dev; + + port_node = of_node_get(of_dev->dev.of_node); + + /* Get the FM node */ + fm_node = of_get_parent(port_node); + if (!fm_node) { + dev_err(port->dev, "%s: of_get_parent() failed\n", __func__); + err = -ENODEV; + goto return_err; + } + + fman = dev_get_drvdata(&of_find_device_by_node(fm_node)->dev); + of_node_put(fm_node); + if (!fman) { + err = -EINVAL; + goto return_err; + } + + u32_prop = (const u32 *)of_get_property(port_node, "cell-index", &lenp); + if (!u32_prop) { + dev_err(port->dev, "%s: of_get_property(%s, cell-index) failed\n", + __func__, port_node->full_name); + err = -EINVAL; + goto return_err; + } + if (WARN_ON(lenp != sizeof(u32))) { + err = -EINVAL; + goto return_err; + } + port_id = (u8)fdt32_to_cpu(u32_prop[0]); + + port->dts_params.id = port_id; + + if (of_device_is_compatible(port_node, "fsl,fman-v3-port-tx")) { + port_type = FMAN_PORT_TYPE_TX; + port_speed = 1000; + u32_prop = (const u32 *)of_get_property(port_node, + "fsl,fman-10g-port", + &lenp); + if (u32_prop) + port_speed = 10000; + + } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-tx")) { + if (port_id >= TX_10G_PORT_BASE) + port_speed = 10000; + else + port_speed = 1000; + port_type = FMAN_PORT_TYPE_TX; + + } else if (of_device_is_compatible(port_node, "fsl,fman-v3-port-rx")) { + port_type = FMAN_PORT_TYPE_RX; + port_speed = 1000; + u32_prop = (const u32 *)of_get_property(port_node, + "fsl,fman-10g-port", &lenp); + if (u32_prop) + port_speed = 10000; + + } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-rx")) { + if (port_id >= RX_10G_PORT_BASE) + port_speed = 10000; + else + port_speed = 1000; + port_type = FMAN_PORT_TYPE_RX; + + } else { + dev_err(port->dev, "%s: Illegal port type\n", __func__); + err = -EINVAL; + goto return_err; + } + + port->dts_params.type = port_type; + port->dts_params.speed = port_speed; + + if (port_type == FMAN_PORT_TYPE_TX) { + u32 qman_channel_id; + + qman_channel_id = fman_get_qman_channel_id(fman, port_id); + if (qman_channel_id == 0) { + dev_err(port->dev, "%s: incorrect qman-channel-id\n", + __func__); + err = -EINVAL; + goto return_err; + } + port->dts_params.qman_channel_id = qman_channel_id; + } + + err = of_address_to_resource(port_node, 0, &res); + if (err < 0) { + dev_err(port->dev, "%s: of_address_to_resource() failed\n", + __func__); + err = -ENOMEM; + goto return_err; + } + + port->dts_params.fman = fman; + + of_node_put(port_node); + + dev_res = __devm_request_region(port->dev, &res, res.start, + resource_size(&res), "fman-port"); + if (!dev_res) { + dev_err(port->dev, "%s: __devm_request_region() failed\n", + __func__); + err = -EINVAL; + goto free_port; + } + + port->dts_params.base_addr = devm_ioremap(port->dev, res.start, + resource_size(&res)); + if (port->dts_params.base_addr == 0) + dev_err(port->dev, "%s: devm_ioremap() failed\n", __func__); + + dev_set_drvdata(&of_dev->dev, port); + + return 0; + +return_err: + of_node_put(port_node); +free_port: + kfree(port); + return err; +} + +static const struct of_device_id fman_port_match[] = { + {.compatible = "fsl,fman-v3-port-rx"}, + {.compatible = "fsl,fman-v2-port-rx"}, + {.compatible = "fsl,fman-v3-port-tx"}, + {.compatible = "fsl,fman-v2-port-tx"}, + {} +}; + +MODULE_DEVICE_TABLE(of, fman_port_match); + +static struct platform_driver fman_port_driver = { + .driver = { + .name = "fsl-fman-port", + .of_match_table = fman_port_match, + }, + .probe = fman_port_probe, +}; + +builtin_platform_driver(fman_port_driver); diff --git a/drivers/net/ethernet/freescale/fman/fman_port.h b/drivers/net/ethernet/freescale/fman/fman_port.h new file mode 100644 index 0000000000000..8ba901737048d --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_port.h @@ -0,0 +1,151 @@ +/* + * Copyright 2008 - 2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __FMAN_PORT_H +#define __FMAN_PORT_H + +#include "fman.h" + +/* FM Port API + * The FM uses a general module called "port" to represent a Tx port (MAC), + * an Rx port (MAC). + * The number of ports in an FM varies between SOCs. + * The SW driver manages these ports as sub-modules of the FM,i.e. after an + * FM is initialized, its ports may be initialized and operated upon. + * The port is initialized aware of its type, but other functions on a port + * may be indifferent to its type. When necessary, the driver verifies + * coherence and returns error if applicable. + * On initialization, user specifies the port type and it's index (relative + * to the port's type) - always starting at 0. + */ + +/* FM Frame error */ +/* Frame Descriptor errors */ +/* Not for Rx-Port! Unsupported Format */ +#define FM_PORT_FRM_ERR_UNSUPPORTED_FORMAT FM_FD_ERR_UNSUPPORTED_FORMAT +/* Not for Rx-Port! Length Error */ +#define FM_PORT_FRM_ERR_LENGTH FM_FD_ERR_LENGTH +/* DMA Data error */ +#define FM_PORT_FRM_ERR_DMA FM_FD_ERR_DMA +/* non Frame-Manager error; probably come from SEC that was chained to FM */ +#define FM_PORT_FRM_ERR_NON_FM FM_FD_RX_STATUS_ERR_NON_FM + /* IPR error */ +#define FM_PORT_FRM_ERR_IPRE (FM_FD_ERR_IPR & ~FM_FD_IPR) +/* IPR non-consistent-sp */ +#define FM_PORT_FRM_ERR_IPR_NCSP (FM_FD_ERR_IPR_NCSP & \ + ~FM_FD_IPR) + +/* Rx FIFO overflow, FCS error, code error, running disparity + * error (SGMII and TBI modes), FIFO parity error. + * PHY Sequence error, PHY error control character detected. + */ +#define FM_PORT_FRM_ERR_PHYSICAL FM_FD_ERR_PHYSICAL +/* Frame too long OR Frame size exceeds max_length_frame */ +#define FM_PORT_FRM_ERR_SIZE FM_FD_ERR_SIZE +/* indicates a classifier "drop" operation */ +#define FM_PORT_FRM_ERR_CLS_DISCARD FM_FD_ERR_CLS_DISCARD +/* Extract Out of Frame */ +#define FM_PORT_FRM_ERR_EXTRACTION FM_FD_ERR_EXTRACTION +/* No Scheme Selected */ +#define FM_PORT_FRM_ERR_NO_SCHEME FM_FD_ERR_NO_SCHEME +/* Keysize Overflow */ +#define FM_PORT_FRM_ERR_KEYSIZE_OVERFLOW FM_FD_ERR_KEYSIZE_OVERFLOW +/* Frame color is red */ +#define FM_PORT_FRM_ERR_COLOR_RED FM_FD_ERR_COLOR_RED +/* Frame color is yellow */ +#define FM_PORT_FRM_ERR_COLOR_YELLOW FM_FD_ERR_COLOR_YELLOW +/* Parser Time out Exceed */ +#define FM_PORT_FRM_ERR_PRS_TIMEOUT FM_FD_ERR_PRS_TIMEOUT +/* Invalid Soft Parser instruction */ +#define FM_PORT_FRM_ERR_PRS_ILL_INSTRUCT FM_FD_ERR_PRS_ILL_INSTRUCT +/* Header error was identified during parsing */ +#define FM_PORT_FRM_ERR_PRS_HDR_ERR FM_FD_ERR_PRS_HDR_ERR +/* Frame parsed beyind 256 first bytes */ +#define FM_PORT_FRM_ERR_BLOCK_LIMIT_EXCEEDED FM_FD_ERR_BLOCK_LIMIT_EXCEEDED +/* FPM Frame Processing Timeout Exceeded */ +#define FM_PORT_FRM_ERR_PROCESS_TIMEOUT 0x00000001 + +struct fman_port; + +/* A structure for additional Rx port parameters */ +struct fman_port_rx_params { + u32 err_fqid; /* Error Queue Id. */ + u32 dflt_fqid; /* Default Queue Id. */ + /* Which external buffer pools are used + * (up to FMAN_PORT_MAX_EXT_POOLS_NUM), and their sizes. + */ + struct fman_ext_pools ext_buf_pools; +}; + +/* A structure for additional non-Rx port parameters */ +struct fman_port_non_rx_params { + /* Error Queue Id. */ + u32 err_fqid; + /* For Tx - Default Confirmation queue, 0 means no Tx confirmation + * for processed frames. For OP port - default Rx queue. + */ + u32 dflt_fqid; +}; + +/* A union for additional parameters depending on port type */ +union fman_port_specific_params { + /* Rx port parameters structure */ + struct fman_port_rx_params rx_params; + /* Non-Rx port parameters structure */ + struct fman_port_non_rx_params non_rx_params; +}; + +/* A structure representing FM initialization parameters */ +struct fman_port_params { + /* Virtual Address of memory mapped FM Port registers. */ + void *fm; + union fman_port_specific_params specific_params; + /* Additional parameters depending on port type. */ +}; + +int fman_port_config(struct fman_port *port, struct fman_port_params *params); + +int fman_port_init(struct fman_port *port); + +int fman_port_cfg_buf_prefix_content(struct fman_port *port, + struct fman_buffer_prefix_content + *buffer_prefix_content); + +int fman_port_disable(struct fman_port *port); + +int fman_port_enable(struct fman_port *port); + +u32 fman_port_get_qman_channel_id(struct fman_port *port); + +struct fman_port *fman_port_bind(struct device *dev); + +#endif /* __FMAN_PORT_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_sp.c b/drivers/net/ethernet/freescale/fman/fman_sp.c new file mode 100644 index 0000000000000..f9e7aa385cbad --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_sp.c @@ -0,0 +1,166 @@ +/* + * Copyright 2008 - 2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "fman_sp.h" +#include "fman.h" + +void fman_sp_set_buf_pools_in_asc_order_of_buf_sizes(struct fman_ext_pools + *fm_ext_pools, + u8 *ordered_array, + u16 *sizes_array) +{ + u16 buf_size = 0; + int i = 0, j = 0, k = 0; + + /* First we copy the external buffers pools information + * to an ordered local array + */ + for (i = 0; i < fm_ext_pools->num_of_pools_used; i++) { + /* get pool size */ + buf_size = fm_ext_pools->ext_buf_pool[i].size; + + /* keep sizes in an array according to poolId + * for direct access + */ + sizes_array[fm_ext_pools->ext_buf_pool[i].id] = buf_size; + + /* save poolId in an ordered array according to size */ + for (j = 0; j <= i; j++) { + /* this is the next free place in the array */ + if (j == i) + ordered_array[i] = + fm_ext_pools->ext_buf_pool[i].id; + else { + /* find the right place for this poolId */ + if (buf_size < sizes_array[ordered_array[j]]) { + /* move the pool_ids one place ahead + * to make room for this poolId + */ + for (k = i; k > j; k--) + ordered_array[k] = + ordered_array[k - 1]; + + /* now k==j, this is the place for + * the new size + */ + ordered_array[k] = + fm_ext_pools->ext_buf_pool[i].id; + break; + } + } + } + } +} + +int fman_sp_build_buffer_struct(struct fman_sp_int_context_data_copy * + int_context_data_copy, + struct fman_buffer_prefix_content * + buffer_prefix_content, + struct fman_sp_buf_margins *buf_margins, + struct fman_sp_buffer_offsets *buffer_offsets, + u8 *internal_buf_offset) +{ + u32 tmp; + + /* Align start of internal context data to 16 byte */ + int_context_data_copy->ext_buf_offset = (u16) + ((buffer_prefix_content->priv_data_size & (OFFSET_UNITS - 1)) ? + ((buffer_prefix_content->priv_data_size + OFFSET_UNITS) & + ~(u16)(OFFSET_UNITS - 1)) : + buffer_prefix_content->priv_data_size); + + /* Translate margin and int_context params to FM parameters */ + /* Initialize with illegal value. Later we'll set legal values. */ + buffer_offsets->prs_result_offset = (u32)ILLEGAL_BASE; + buffer_offsets->time_stamp_offset = (u32)ILLEGAL_BASE; + buffer_offsets->hash_result_offset = (u32)ILLEGAL_BASE; + + /* Internally the driver supports 4 options + * 1. prsResult/timestamp/hashResult selection (in fact 8 options, + * but for simplicity we'll + * relate to it as 1). + * 2. All IC context (from AD) not including debug. + */ + + /* This case covers the options under 1 */ + /* Copy size must be in 16-byte granularity. */ + int_context_data_copy->size = + (u16)((buffer_prefix_content->pass_prs_result ? 32 : 0) + + ((buffer_prefix_content->pass_time_stamp || + buffer_prefix_content->pass_hash_result) ? 16 : 0)); + + /* Align start of internal context data to 16 byte */ + int_context_data_copy->int_context_offset = + (u8)(buffer_prefix_content->pass_prs_result ? 32 : + ((buffer_prefix_content->pass_time_stamp || + buffer_prefix_content->pass_hash_result) ? 64 : 0)); + + if (buffer_prefix_content->pass_prs_result) + buffer_offsets->prs_result_offset = + int_context_data_copy->ext_buf_offset; + if (buffer_prefix_content->pass_time_stamp) + buffer_offsets->time_stamp_offset = + buffer_prefix_content->pass_prs_result ? + (int_context_data_copy->ext_buf_offset + + sizeof(struct fman_prs_result)) : + int_context_data_copy->ext_buf_offset; + if (buffer_prefix_content->pass_hash_result) + /* If PR is not requested, whether TS is + * requested or not, IC will be copied from TS + */ + buffer_offsets->hash_result_offset = + buffer_prefix_content->pass_prs_result ? + (int_context_data_copy->ext_buf_offset + + sizeof(struct fman_prs_result) + 8) : + int_context_data_copy->ext_buf_offset + 8; + + if (int_context_data_copy->size) + buf_margins->start_margins = + (u16)(int_context_data_copy->ext_buf_offset + + int_context_data_copy->size); + else + /* No Internal Context passing, STartMargin is + * immediately after private_info + */ + buf_margins->start_margins = + buffer_prefix_content->priv_data_size; + + /* align data start */ + tmp = (u32)(buf_margins->start_margins % + buffer_prefix_content->data_align); + if (tmp) + buf_margins->start_margins += + (buffer_prefix_content->data_align - tmp); + buffer_offsets->data_offset = buf_margins->start_margins; + + return 0; +} diff --git a/drivers/net/ethernet/freescale/fman/fman_sp.h b/drivers/net/ethernet/freescale/fman/fman_sp.h new file mode 100644 index 0000000000000..820b7f63088f5 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_sp.h @@ -0,0 +1,103 @@ +/* + * Copyright 2008 - 2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __FM_SP_H +#define __FM_SP_H + +#include "fman.h" +#include <linux/types.h> + +#define ILLEGAL_BASE (~0) + +/* defaults */ +#define DFLT_FM_SP_BUFFER_PREFIX_CONTEXT_DATA_ALIGN 64 + +/* Registers bit fields */ +#define FMAN_SP_EXT_BUF_POOL_EN_COUNTER 0x40000000 +#define FMAN_SP_EXT_BUF_POOL_VALID 0x80000000 +#define FMAN_SP_EXT_BUF_POOL_BACKUP 0x20000000 +#define FMAN_SP_DMA_ATTR_WRITE_OPTIMIZE 0x00100000 +#define FMAN_SP_SG_DISABLE 0x80000000 + +/* shifts */ +#define FMAN_SP_EXT_BUF_MARG_START_SHIFT 16 +#define FMAN_SP_DMA_ATTR_SWP_SHIFT 30 +#define FMAN_SP_IC_TO_EXT_SHIFT 16 +#define FMAN_SP_IC_FROM_INT_SHIFT 8 + +/* structure for defining internal context copying */ +struct fman_sp_int_context_data_copy { + /* < Offset in External buffer to which internal + * context is copied to (Rx) or taken from (Tx, Op). + */ + u16 ext_buf_offset; + /* Offset within internal context to copy from + * (Rx) or to copy to (Tx, Op). + */ + u8 int_context_offset; + /* Internal offset size to be copied */ + u16 size; +}; + +/* struct for defining external buffer margins */ +struct fman_sp_buf_margins { + /* Number of bytes to be left at the beginning + * of the external buffer (must be divisible by 16) + */ + u16 start_margins; + /* number of bytes to be left at the end + * of the external buffer(must be divisible by 16) + */ + u16 end_margins; +}; + +struct fman_sp_buffer_offsets { + u32 data_offset; + u32 prs_result_offset; + u32 time_stamp_offset; + u32 hash_result_offset; +}; + +int fman_sp_build_buffer_struct(struct fman_sp_int_context_data_copy + *int_context_data_copy, + struct fman_buffer_prefix_content + *buffer_prefix_content, + struct fman_sp_buf_margins *buf_margins, + struct fman_sp_buffer_offsets + *buffer_offsets, + u8 *internal_buf_offset); + +void fman_sp_set_buf_pools_in_asc_order_of_buf_sizes(struct fman_ext_pools + *fm_ext_pools, + u8 *ordered_array, + u16 *sizes_array); + +#endif /* __FM_SP_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c new file mode 100644 index 0000000000000..efabb04a1ae8c --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -0,0 +1,786 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include "fman_tgec.h" +#include "fman.h" + +#include <linux/slab.h> +#include <linux/bitrev.h> +#include <linux/io.h> +#include <linux/crc32.h> + +/* Transmit Inter-Packet Gap Length Register (TX_IPG_LENGTH) */ +#define TGEC_TX_IPG_LENGTH_MASK 0x000003ff + +/* Command and Configuration Register (COMMAND_CONFIG) */ +#define CMD_CFG_NO_LEN_CHK 0x00020000 +#define CMD_CFG_PAUSE_IGNORE 0x00000100 +#define CMF_CFG_CRC_FWD 0x00000040 +#define CMD_CFG_PROMIS_EN 0x00000010 +#define CMD_CFG_RX_EN 0x00000002 +#define CMD_CFG_TX_EN 0x00000001 + +/* Interrupt Mask Register (IMASK) */ +#define TGEC_IMASK_MDIO_SCAN_EVENT 0x00010000 +#define TGEC_IMASK_MDIO_CMD_CMPL 0x00008000 +#define TGEC_IMASK_REM_FAULT 0x00004000 +#define TGEC_IMASK_LOC_FAULT 0x00002000 +#define TGEC_IMASK_TX_ECC_ER 0x00001000 +#define TGEC_IMASK_TX_FIFO_UNFL 0x00000800 +#define TGEC_IMASK_TX_FIFO_OVFL 0x00000400 +#define TGEC_IMASK_TX_ER 0x00000200 +#define TGEC_IMASK_RX_FIFO_OVFL 0x00000100 +#define TGEC_IMASK_RX_ECC_ER 0x00000080 +#define TGEC_IMASK_RX_JAB_FRM 0x00000040 +#define TGEC_IMASK_RX_OVRSZ_FRM 0x00000020 +#define TGEC_IMASK_RX_RUNT_FRM 0x00000010 +#define TGEC_IMASK_RX_FRAG_FRM 0x00000008 +#define TGEC_IMASK_RX_LEN_ER 0x00000004 +#define TGEC_IMASK_RX_CRC_ER 0x00000002 +#define TGEC_IMASK_RX_ALIGN_ER 0x00000001 + +/* Hashtable Control Register (HASHTABLE_CTRL) */ +#define TGEC_HASH_MCAST_SHIFT 23 +#define TGEC_HASH_MCAST_EN 0x00000200 +#define TGEC_HASH_ADR_MSK 0x000001ff + +#define DEFAULT_TX_IPG_LENGTH 12 +#define DEFAULT_MAX_FRAME_LENGTH 0x600 +#define DEFAULT_PAUSE_QUANT 0xf000 + +/* number of pattern match registers (entries) */ +#define TGEC_NUM_OF_PADDRS 1 + +/* Group address bit indication */ +#define GROUP_ADDRESS 0x0000010000000000LL + +/* Hash table size (= 32 bits*8 regs) */ +#define TGEC_HASH_TABLE_SIZE 512 + +/* tGEC memory map */ +struct tgec_regs { + u32 tgec_id; /* 0x000 Controller ID */ + u32 reserved001[1]; /* 0x004 */ + u32 command_config; /* 0x008 Control and configuration */ + u32 mac_addr_0; /* 0x00c Lower 32 bits of the MAC adr */ + u32 mac_addr_1; /* 0x010 Upper 16 bits of the MAC adr */ + u32 maxfrm; /* 0x014 Maximum frame length */ + u32 pause_quant; /* 0x018 Pause quanta */ + u32 rx_fifo_sections; /* 0x01c */ + u32 tx_fifo_sections; /* 0x020 */ + u32 rx_fifo_almost_f_e; /* 0x024 */ + u32 tx_fifo_almost_f_e; /* 0x028 */ + u32 hashtable_ctrl; /* 0x02c Hash table control */ + u32 mdio_cfg_status; /* 0x030 */ + u32 mdio_command; /* 0x034 */ + u32 mdio_data; /* 0x038 */ + u32 mdio_regaddr; /* 0x03c */ + u32 status; /* 0x040 */ + u32 tx_ipg_len; /* 0x044 Transmitter inter-packet-gap */ + u32 mac_addr_2; /* 0x048 Lower 32 bits of 2nd MAC adr */ + u32 mac_addr_3; /* 0x04c Upper 16 bits of 2nd MAC adr */ + u32 rx_fifo_ptr_rd; /* 0x050 */ + u32 rx_fifo_ptr_wr; /* 0x054 */ + u32 tx_fifo_ptr_rd; /* 0x058 */ + u32 tx_fifo_ptr_wr; /* 0x05c */ + u32 imask; /* 0x060 Interrupt mask */ + u32 ievent; /* 0x064 Interrupt event */ + u32 udp_port; /* 0x068 Defines a UDP Port number */ + u32 type_1588v2; /* 0x06c Type field for 1588v2 */ + u32 reserved070[4]; /* 0x070 */ + /* 10Ge Statistics Counter */ + u32 tfrm_u; /* 80 aFramesTransmittedOK */ + u32 tfrm_l; /* 84 aFramesTransmittedOK */ + u32 rfrm_u; /* 88 aFramesReceivedOK */ + u32 rfrm_l; /* 8c aFramesReceivedOK */ + u32 rfcs_u; /* 90 aFrameCheckSequenceErrors */ + u32 rfcs_l; /* 94 aFrameCheckSequenceErrors */ + u32 raln_u; /* 98 aAlignmentErrors */ + u32 raln_l; /* 9c aAlignmentErrors */ + u32 txpf_u; /* A0 aPAUSEMACCtrlFramesTransmitted */ + u32 txpf_l; /* A4 aPAUSEMACCtrlFramesTransmitted */ + u32 rxpf_u; /* A8 aPAUSEMACCtrlFramesReceived */ + u32 rxpf_l; /* Ac aPAUSEMACCtrlFramesReceived */ + u32 rlong_u; /* B0 aFrameTooLongErrors */ + u32 rlong_l; /* B4 aFrameTooLongErrors */ + u32 rflr_u; /* B8 aInRangeLengthErrors */ + u32 rflr_l; /* Bc aInRangeLengthErrors */ + u32 tvlan_u; /* C0 VLANTransmittedOK */ + u32 tvlan_l; /* C4 VLANTransmittedOK */ + u32 rvlan_u; /* C8 VLANReceivedOK */ + u32 rvlan_l; /* Cc VLANReceivedOK */ + u32 toct_u; /* D0 if_out_octets */ + u32 toct_l; /* D4 if_out_octets */ + u32 roct_u; /* D8 if_in_octets */ + u32 roct_l; /* Dc if_in_octets */ + u32 ruca_u; /* E0 if_in_ucast_pkts */ + u32 ruca_l; /* E4 if_in_ucast_pkts */ + u32 rmca_u; /* E8 ifInMulticastPkts */ + u32 rmca_l; /* Ec ifInMulticastPkts */ + u32 rbca_u; /* F0 ifInBroadcastPkts */ + u32 rbca_l; /* F4 ifInBroadcastPkts */ + u32 terr_u; /* F8 if_out_errors */ + u32 terr_l; /* Fc if_out_errors */ + u32 reserved100[2]; /* 100-108 */ + u32 tuca_u; /* 108 if_out_ucast_pkts */ + u32 tuca_l; /* 10c if_out_ucast_pkts */ + u32 tmca_u; /* 110 ifOutMulticastPkts */ + u32 tmca_l; /* 114 ifOutMulticastPkts */ + u32 tbca_u; /* 118 ifOutBroadcastPkts */ + u32 tbca_l; /* 11c ifOutBroadcastPkts */ + u32 rdrp_u; /* 120 etherStatsDropEvents */ + u32 rdrp_l; /* 124 etherStatsDropEvents */ + u32 reoct_u; /* 128 etherStatsOctets */ + u32 reoct_l; /* 12c etherStatsOctets */ + u32 rpkt_u; /* 130 etherStatsPkts */ + u32 rpkt_l; /* 134 etherStatsPkts */ + u32 trund_u; /* 138 etherStatsUndersizePkts */ + u32 trund_l; /* 13c etherStatsUndersizePkts */ + u32 r64_u; /* 140 etherStatsPkts64Octets */ + u32 r64_l; /* 144 etherStatsPkts64Octets */ + u32 r127_u; /* 148 etherStatsPkts65to127Octets */ + u32 r127_l; /* 14c etherStatsPkts65to127Octets */ + u32 r255_u; /* 150 etherStatsPkts128to255Octets */ + u32 r255_l; /* 154 etherStatsPkts128to255Octets */ + u32 r511_u; /* 158 etherStatsPkts256to511Octets */ + u32 r511_l; /* 15c etherStatsPkts256to511Octets */ + u32 r1023_u; /* 160 etherStatsPkts512to1023Octets */ + u32 r1023_l; /* 164 etherStatsPkts512to1023Octets */ + u32 r1518_u; /* 168 etherStatsPkts1024to1518Octets */ + u32 r1518_l; /* 16c etherStatsPkts1024to1518Octets */ + u32 r1519x_u; /* 170 etherStatsPkts1519toX */ + u32 r1519x_l; /* 174 etherStatsPkts1519toX */ + u32 trovr_u; /* 178 etherStatsOversizePkts */ + u32 trovr_l; /* 17c etherStatsOversizePkts */ + u32 trjbr_u; /* 180 etherStatsJabbers */ + u32 trjbr_l; /* 184 etherStatsJabbers */ + u32 trfrg_u; /* 188 etherStatsFragments */ + u32 trfrg_l; /* 18C etherStatsFragments */ + u32 rerr_u; /* 190 if_in_errors */ + u32 rerr_l; /* 194 if_in_errors */ +}; + +struct tgec_cfg { + bool pause_ignore; + bool promiscuous_mode_enable; + u16 max_frame_length; + u16 pause_quant; + u32 tx_ipg_length; +}; + +struct fman_mac { + /* Pointer to the memory mapped registers. */ + struct tgec_regs __iomem *regs; + /* MAC address of device; */ + u64 addr; + u16 max_speed; + void *dev_id; /* device cookie used by the exception cbs */ + fman_mac_exception_cb *exception_cb; + fman_mac_exception_cb *event_cb; + /* pointer to driver's global address hash table */ + struct eth_hash_t *multicast_addr_hash; + /* pointer to driver's individual address hash table */ + struct eth_hash_t *unicast_addr_hash; + u8 mac_id; + u32 exceptions; + struct tgec_cfg *cfg; + void *fm; + struct fman_rev_info fm_rev_info; +}; + +static void set_mac_address(struct tgec_regs __iomem *regs, u8 *adr) +{ + u32 tmp0, tmp1; + + tmp0 = (u32)(adr[0] | adr[1] << 8 | adr[2] << 16 | adr[3] << 24); + tmp1 = (u32)(adr[4] | adr[5] << 8); + iowrite32be(tmp0, ®s->mac_addr_0); + iowrite32be(tmp1, ®s->mac_addr_1); +} + +static void set_dflts(struct tgec_cfg *cfg) +{ + cfg->promiscuous_mode_enable = false; + cfg->pause_ignore = false; + cfg->tx_ipg_length = DEFAULT_TX_IPG_LENGTH; + cfg->max_frame_length = DEFAULT_MAX_FRAME_LENGTH; + cfg->pause_quant = DEFAULT_PAUSE_QUANT; +} + +static int init(struct tgec_regs __iomem *regs, struct tgec_cfg *cfg, + u32 exception_mask) +{ + u32 tmp; + + /* Config */ + tmp = CMF_CFG_CRC_FWD; + if (cfg->promiscuous_mode_enable) + tmp |= CMD_CFG_PROMIS_EN; + if (cfg->pause_ignore) + tmp |= CMD_CFG_PAUSE_IGNORE; + /* Payload length check disable */ + tmp |= CMD_CFG_NO_LEN_CHK; + iowrite32be(tmp, ®s->command_config); + + /* Max Frame Length */ + iowrite32be((u32)cfg->max_frame_length, ®s->maxfrm); + /* Pause Time */ + iowrite32be(cfg->pause_quant, ®s->pause_quant); + + /* clear all pending events and set-up interrupts */ + iowrite32be(0xffffffff, ®s->ievent); + iowrite32be(ioread32be(®s->imask) | exception_mask, ®s->imask); + + return 0; +} + +static int check_init_parameters(struct fman_mac *tgec) +{ + if (tgec->max_speed < SPEED_10000) { + pr_err("10G MAC driver only support 10G speed\n"); + return -EINVAL; + } + if (tgec->addr == 0) { + pr_err("Ethernet 10G MAC Must have valid MAC Address\n"); + return -EINVAL; + } + if (!tgec->exception_cb) { + pr_err("uninitialized exception_cb\n"); + return -EINVAL; + } + if (!tgec->event_cb) { + pr_err("uninitialized event_cb\n"); + return -EINVAL; + } + + return 0; +} + +static int get_exception_flag(enum fman_mac_exceptions exception) +{ + u32 bit_mask; + + switch (exception) { + case FM_MAC_EX_10G_MDIO_SCAN_EVENT: + bit_mask = TGEC_IMASK_MDIO_SCAN_EVENT; + break; + case FM_MAC_EX_10G_MDIO_CMD_CMPL: + bit_mask = TGEC_IMASK_MDIO_CMD_CMPL; + break; + case FM_MAC_EX_10G_REM_FAULT: + bit_mask = TGEC_IMASK_REM_FAULT; + break; + case FM_MAC_EX_10G_LOC_FAULT: + bit_mask = TGEC_IMASK_LOC_FAULT; + break; + case FM_MAC_EX_10G_TX_ECC_ER: + bit_mask = TGEC_IMASK_TX_ECC_ER; + break; + case FM_MAC_EX_10G_TX_FIFO_UNFL: + bit_mask = TGEC_IMASK_TX_FIFO_UNFL; + break; + case FM_MAC_EX_10G_TX_FIFO_OVFL: + bit_mask = TGEC_IMASK_TX_FIFO_OVFL; + break; + case FM_MAC_EX_10G_TX_ER: + bit_mask = TGEC_IMASK_TX_ER; + break; + case FM_MAC_EX_10G_RX_FIFO_OVFL: + bit_mask = TGEC_IMASK_RX_FIFO_OVFL; + break; + case FM_MAC_EX_10G_RX_ECC_ER: + bit_mask = TGEC_IMASK_RX_ECC_ER; + break; + case FM_MAC_EX_10G_RX_JAB_FRM: + bit_mask = TGEC_IMASK_RX_JAB_FRM; + break; + case FM_MAC_EX_10G_RX_OVRSZ_FRM: + bit_mask = TGEC_IMASK_RX_OVRSZ_FRM; + break; + case FM_MAC_EX_10G_RX_RUNT_FRM: + bit_mask = TGEC_IMASK_RX_RUNT_FRM; + break; + case FM_MAC_EX_10G_RX_FRAG_FRM: + bit_mask = TGEC_IMASK_RX_FRAG_FRM; + break; + case FM_MAC_EX_10G_RX_LEN_ER: + bit_mask = TGEC_IMASK_RX_LEN_ER; + break; + case FM_MAC_EX_10G_RX_CRC_ER: + bit_mask = TGEC_IMASK_RX_CRC_ER; + break; + case FM_MAC_EX_10G_RX_ALIGN_ER: + bit_mask = TGEC_IMASK_RX_ALIGN_ER; + break; + default: + bit_mask = 0; + break; + } + + return bit_mask; +} + +static void tgec_err_exception(void *handle) +{ + struct fman_mac *tgec = (struct fman_mac *)handle; + struct tgec_regs __iomem *regs = tgec->regs; + u32 event; + + /* do not handle MDIO events */ + event = ioread32be(®s->ievent) & + ~(TGEC_IMASK_MDIO_SCAN_EVENT | + TGEC_IMASK_MDIO_CMD_CMPL); + + event &= ioread32be(®s->imask); + + iowrite32be(event, ®s->ievent); + + if (event & TGEC_IMASK_REM_FAULT) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_REM_FAULT); + if (event & TGEC_IMASK_LOC_FAULT) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_LOC_FAULT); + if (event & TGEC_IMASK_TX_ECC_ER) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_TX_ECC_ER); + if (event & TGEC_IMASK_TX_FIFO_UNFL) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_TX_FIFO_UNFL); + if (event & TGEC_IMASK_TX_FIFO_OVFL) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_TX_FIFO_OVFL); + if (event & TGEC_IMASK_TX_ER) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_TX_ER); + if (event & TGEC_IMASK_RX_FIFO_OVFL) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_FIFO_OVFL); + if (event & TGEC_IMASK_RX_ECC_ER) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_ECC_ER); + if (event & TGEC_IMASK_RX_JAB_FRM) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_JAB_FRM); + if (event & TGEC_IMASK_RX_OVRSZ_FRM) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_OVRSZ_FRM); + if (event & TGEC_IMASK_RX_RUNT_FRM) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_RUNT_FRM); + if (event & TGEC_IMASK_RX_FRAG_FRM) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_FRAG_FRM); + if (event & TGEC_IMASK_RX_LEN_ER) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_LEN_ER); + if (event & TGEC_IMASK_RX_CRC_ER) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_CRC_ER); + if (event & TGEC_IMASK_RX_ALIGN_ER) + tgec->exception_cb(tgec->dev_id, FM_MAC_EX_10G_RX_ALIGN_ER); +} + +static void free_init_resources(struct fman_mac *tgec) +{ + fman_unregister_intr(tgec->fm, FMAN_MOD_MAC, tgec->mac_id, + FMAN_INTR_TYPE_ERR); + + /* release the driver's group hash table */ + free_hash_table(tgec->multicast_addr_hash); + tgec->multicast_addr_hash = NULL; + + /* release the driver's individual hash table */ + free_hash_table(tgec->unicast_addr_hash); + tgec->unicast_addr_hash = NULL; +} + +static bool is_init_done(struct tgec_cfg *cfg) +{ + /* Checks if tGEC driver parameters were initialized */ + if (!cfg) + return true; + + return false; +} + +int tgec_enable(struct fman_mac *tgec, enum comm_mode mode) +{ + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (mode & COMM_MODE_RX) + tmp |= CMD_CFG_RX_EN; + if (mode & COMM_MODE_TX) + tmp |= CMD_CFG_TX_EN; + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int tgec_disable(struct fman_mac *tgec, enum comm_mode mode) +{ + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (mode & COMM_MODE_RX) + tmp &= ~CMD_CFG_RX_EN; + if (mode & COMM_MODE_TX) + tmp &= ~CMD_CFG_TX_EN; + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val) +{ + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (new_val) + tmp |= CMD_CFG_PROMIS_EN; + else + tmp &= ~CMD_CFG_PROMIS_EN; + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int tgec_cfg_max_frame_len(struct fman_mac *tgec, u16 new_val) +{ + if (is_init_done(tgec->cfg)) + return -EINVAL; + + tgec->cfg->max_frame_length = new_val; + + return 0; +} + +int tgec_set_tx_pause_frames(struct fman_mac *tgec, u8 __maybe_unused priority, + u16 pause_time, u16 __maybe_unused thresh_time) +{ + struct tgec_regs __iomem *regs = tgec->regs; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + iowrite32be((u32)pause_time, ®s->pause_quant); + + return 0; +} + +int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en) +{ + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + if (!en) + tmp |= CMD_CFG_PAUSE_IGNORE; + else + tmp &= ~CMD_CFG_PAUSE_IGNORE; + iowrite32be(tmp, ®s->command_config); + + return 0; +} + +int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *p_enet_addr) +{ + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + tgec->addr = ENET_ADDR_TO_UINT64(*p_enet_addr); + set_mac_address(tgec->regs, (u8 *)(*p_enet_addr)); + + return 0; +} + +int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) +{ + struct tgec_regs __iomem *regs = tgec->regs; + struct eth_hash_entry *hash_entry; + u32 crc = 0xFFFFFFFF, hash; + u64 addr; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + addr = ENET_ADDR_TO_UINT64(*eth_addr); + + if (!(addr & GROUP_ADDRESS)) { + /* Unicast addresses not supported in hash */ + pr_err("Unicast Address\n"); + return -EINVAL; + } + /* CRC calculation */ + crc = crc32_le(crc, (u8 *)eth_addr, ETH_ALEN); + crc = bitrev32(crc); + /* Take 9 MSB bits */ + hash = (crc >> TGEC_HASH_MCAST_SHIFT) & TGEC_HASH_ADR_MSK; + + /* Create element to be added to the driver hash table */ + hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + if (!hash_entry) + return -ENOMEM; + hash_entry->addr = addr; + INIT_LIST_HEAD(&hash_entry->node); + + list_add_tail(&hash_entry->node, + &tgec->multicast_addr_hash->lsts[hash]); + iowrite32be((hash | TGEC_HASH_MCAST_EN), ®s->hashtable_ctrl); + + return 0; +} + +int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) +{ + struct tgec_regs __iomem *regs = tgec->regs; + struct eth_hash_entry *hash_entry = NULL; + struct list_head *pos; + u32 crc = 0xFFFFFFFF, hash; + u64 addr; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + addr = ((*(u64 *)eth_addr) >> 16); + + /* CRC calculation */ + crc = crc32_le(crc, (u8 *)eth_addr, ETH_ALEN); + crc = bitrev32(crc); + /* Take 9 MSB bits */ + hash = (crc >> TGEC_HASH_MCAST_SHIFT) & TGEC_HASH_ADR_MSK; + + list_for_each(pos, &tgec->multicast_addr_hash->lsts[hash]) { + hash_entry = ETH_HASH_ENTRY_OBJ(pos); + if (hash_entry->addr == addr) { + list_del_init(&hash_entry->node); + kfree(hash_entry); + break; + } + } + if (list_empty(&tgec->multicast_addr_hash->lsts[hash])) + iowrite32be((hash & ~TGEC_HASH_MCAST_EN), + ®s->hashtable_ctrl); + + return 0; +} + +int tgec_get_version(struct fman_mac *tgec, u32 *mac_version) +{ + struct tgec_regs __iomem *regs = tgec->regs; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + *mac_version = ioread32be(®s->tgec_id); + + return 0; +} + +int tgec_set_exception(struct fman_mac *tgec, + enum fman_mac_exceptions exception, bool enable) +{ + struct tgec_regs __iomem *regs = tgec->regs; + u32 bit_mask = 0; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + bit_mask = get_exception_flag(exception); + if (bit_mask) { + if (enable) + tgec->exceptions |= bit_mask; + else + tgec->exceptions &= ~bit_mask; + } else { + pr_err("Undefined exception\n"); + return -EINVAL; + } + if (enable) + iowrite32be(ioread32be(®s->imask) | bit_mask, ®s->imask); + else + iowrite32be(ioread32be(®s->imask) & ~bit_mask, ®s->imask); + + return 0; +} + +int tgec_init(struct fman_mac *tgec) +{ + struct tgec_cfg *cfg; + enet_addr_t eth_addr; + int err; + + if (is_init_done(tgec->cfg)) + return -EINVAL; + + if (DEFAULT_RESET_ON_INIT && + (fman_reset_mac(tgec->fm, tgec->mac_id) != 0)) { + pr_err("Can't reset MAC!\n"); + return -EINVAL; + } + + err = check_init_parameters(tgec); + if (err) + return err; + + cfg = tgec->cfg; + + MAKE_ENET_ADDR_FROM_UINT64(tgec->addr, eth_addr); + set_mac_address(tgec->regs, (u8 *)eth_addr); + + /* interrupts */ + /* FM_10G_REM_N_LCL_FLT_EX_10GMAC_ERRATA_SW005 Errata workaround */ + if (tgec->fm_rev_info.major <= 2) + tgec->exceptions &= ~(TGEC_IMASK_REM_FAULT | + TGEC_IMASK_LOC_FAULT); + + err = init(tgec->regs, cfg, tgec->exceptions); + if (err) { + free_init_resources(tgec); + pr_err("TGEC version doesn't support this i/f mode\n"); + return err; + } + + /* Max Frame Length */ + err = fman_set_mac_max_frame(tgec->fm, tgec->mac_id, + cfg->max_frame_length); + if (err) { + pr_err("Setting max frame length FAILED\n"); + free_init_resources(tgec); + return -EINVAL; + } + + /* FM_TX_FIFO_CORRUPTION_ERRATA_10GMAC_A007 Errata workaround */ + if (tgec->fm_rev_info.major == 2) { + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + /* restore the default tx ipg Length */ + tmp = (ioread32be(®s->tx_ipg_len) & + ~TGEC_TX_IPG_LENGTH_MASK) | 12; + + iowrite32be(tmp, ®s->tx_ipg_len); + } + + tgec->multicast_addr_hash = alloc_hash_table(TGEC_HASH_TABLE_SIZE); + if (!tgec->multicast_addr_hash) { + free_init_resources(tgec); + pr_err("allocation hash table is FAILED\n"); + return -ENOMEM; + } + + tgec->unicast_addr_hash = alloc_hash_table(TGEC_HASH_TABLE_SIZE); + if (!tgec->unicast_addr_hash) { + free_init_resources(tgec); + pr_err("allocation hash table is FAILED\n"); + return -ENOMEM; + } + + fman_register_intr(tgec->fm, FMAN_MOD_MAC, tgec->mac_id, + FMAN_INTR_TYPE_ERR, tgec_err_exception, tgec); + + kfree(cfg); + tgec->cfg = NULL; + + return 0; +} + +int tgec_free(struct fman_mac *tgec) +{ + free_init_resources(tgec); + + if (tgec->cfg) + tgec->cfg = NULL; + + kfree(tgec->cfg); + kfree(tgec); + + return 0; +} + +struct fman_mac *tgec_config(struct fman_mac_params *params) +{ + struct fman_mac *tgec; + struct tgec_cfg *cfg; + void __iomem *base_addr; + + base_addr = params->base_addr; + /* allocate memory for the UCC GETH data structure. */ + tgec = kzalloc(sizeof(*tgec), GFP_KERNEL); + if (!tgec) + return NULL; + + /* allocate memory for the 10G MAC driver parameters data structure. */ + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) { + tgec_free(tgec); + return NULL; + } + + /* Plant parameter structure pointer */ + tgec->cfg = cfg; + + set_dflts(cfg); + + tgec->regs = base_addr; + tgec->addr = ENET_ADDR_TO_UINT64(params->addr); + tgec->max_speed = params->max_speed; + tgec->mac_id = params->mac_id; + tgec->exceptions = (TGEC_IMASK_MDIO_SCAN_EVENT | + TGEC_IMASK_REM_FAULT | + TGEC_IMASK_LOC_FAULT | + TGEC_IMASK_TX_ECC_ER | + TGEC_IMASK_TX_FIFO_UNFL | + TGEC_IMASK_TX_FIFO_OVFL | + TGEC_IMASK_TX_ER | + TGEC_IMASK_RX_FIFO_OVFL | + TGEC_IMASK_RX_ECC_ER | + TGEC_IMASK_RX_JAB_FRM | + TGEC_IMASK_RX_OVRSZ_FRM | + TGEC_IMASK_RX_RUNT_FRM | + TGEC_IMASK_RX_FRAG_FRM | + TGEC_IMASK_RX_CRC_ER | + TGEC_IMASK_RX_ALIGN_ER); + tgec->exception_cb = params->exception_cb; + tgec->event_cb = params->event_cb; + tgec->dev_id = params->dev_id; + tgec->fm = params->fm; + + /* Save FMan revision */ + fman_get_revision(tgec->fm, &tgec->fm_rev_info); + + return tgec; +} diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h new file mode 100644 index 0000000000000..514bba9f47ce6 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -0,0 +1,55 @@ +/* + * Copyright 2008-2015 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __TGEC_H +#define __TGEC_H + +#include "fman_mac.h" + +struct fman_mac *tgec_config(struct fman_mac_params *params); +int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val); +int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *enet_addr); +int tgec_cfg_max_frame_len(struct fman_mac *tgec, u16 new_val); +int tgec_enable(struct fman_mac *tgec, enum comm_mode mode); +int tgec_disable(struct fman_mac *tgec, enum comm_mode mode); +int tgec_init(struct fman_mac *tgec); +int tgec_free(struct fman_mac *tgec); +int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en); +int tgec_set_tx_pause_frames(struct fman_mac *tgec, u8 priority, + u16 pause_time, u16 thresh_time); +int tgec_set_exception(struct fman_mac *tgec, + enum fman_mac_exceptions exception, bool enable); +int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); +int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); +int tgec_get_version(struct fman_mac *tgec, u32 *mac_version); + +#endif /* __TGEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c new file mode 100644 index 0000000000000..743a393ba657f --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -0,0 +1,978 @@ +/* Copyright 2008-2015 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/of_net.h> +#include <linux/of_mdio.h> +#include <linux/device.h> +#include <linux/phy.h> +#include <linux/netdevice.h> +#include <linux/phy_fixed.h> +#include <linux/etherdevice.h> +#include <linux/libfdt_env.h> + +#include "mac.h" +#include "fman_mac.h" +#include "fman_dtsec.h" +#include "fman_tgec.h" +#include "fman_memac.h" + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("FSL FMan MAC API based driver"); + +struct mac_priv_s { + struct device *dev; + void __iomem *vaddr; + u8 cell_index; + phy_interface_t phy_if; + struct fman *fman; + struct device_node *phy_node; + struct device_node *internal_phy_node; + /* List of multicast addresses */ + struct list_head mc_addr_list; + struct platform_device *eth_dev; + struct fixed_phy_status *fixed_link; + u16 speed; + u16 max_speed; + + int (*enable)(struct fman_mac *mac_dev, enum comm_mode mode); + int (*disable)(struct fman_mac *mac_dev, enum comm_mode mode); +}; + +struct mac_address { + u8 addr[ETH_ALEN]; + struct list_head list; +}; + +static void mac_exception(void *handle, enum fman_mac_exceptions ex) +{ + struct mac_device *mac_dev; + struct mac_priv_s *priv; + + mac_dev = handle; + priv = mac_dev->priv; + + if (ex == FM_MAC_EX_10G_RX_FIFO_OVFL) { + /* don't flag RX FIFO after the first */ + mac_dev->set_exception(mac_dev->fman_mac, + FM_MAC_EX_10G_RX_FIFO_OVFL, false); + dev_err(priv->dev, "10G MAC got RX FIFO Error = %x\n", ex); + } + + dev_dbg(priv->dev, "%s:%s() -> %d\n", KBUILD_BASENAME ".c", + __func__, ex); +} + +static void set_fman_mac_params(struct mac_device *mac_dev, + struct fman_mac_params *params) +{ + struct mac_priv_s *priv = mac_dev->priv; + + params->base_addr = (typeof(params->base_addr)) + devm_ioremap(priv->dev, mac_dev->res->start, + resource_size(mac_dev->res)); + memcpy(¶ms->addr, mac_dev->addr, sizeof(mac_dev->addr)); + params->max_speed = priv->max_speed; + params->phy_if = priv->phy_if; + params->basex_if = false; + params->mac_id = priv->cell_index; + params->fm = (void *)priv->fman; + params->exception_cb = mac_exception; + params->event_cb = mac_exception; + params->dev_id = mac_dev; + params->internal_phy_node = priv->internal_phy_node; +} + +static int tgec_initialization(struct mac_device *mac_dev) +{ + int err; + struct mac_priv_s *priv; + struct fman_mac_params params; + u32 version; + + priv = mac_dev->priv; + + set_fman_mac_params(mac_dev, ¶ms); + + mac_dev->fman_mac = tgec_config(¶ms); + if (!mac_dev->fman_mac) { + err = -EINVAL; + goto _return; + } + + err = tgec_cfg_max_frame_len(mac_dev->fman_mac, fman_get_max_frm()); + if (err < 0) + goto _return_fm_mac_free; + + err = tgec_init(mac_dev->fman_mac); + if (err < 0) + goto _return_fm_mac_free; + + /* For 10G MAC, disable Tx ECC exception */ + err = mac_dev->set_exception(mac_dev->fman_mac, + FM_MAC_EX_10G_TX_ECC_ER, false); + if (err < 0) + goto _return_fm_mac_free; + + err = tgec_get_version(mac_dev->fman_mac, &version); + if (err < 0) + goto _return_fm_mac_free; + + dev_info(priv->dev, "FMan XGEC version: 0x%08x\n", version); + + goto _return; + +_return_fm_mac_free: + tgec_free(mac_dev->fman_mac); + +_return: + return err; +} + +static int dtsec_initialization(struct mac_device *mac_dev) +{ + int err; + struct mac_priv_s *priv; + struct fman_mac_params params; + u32 version; + + priv = mac_dev->priv; + + set_fman_mac_params(mac_dev, ¶ms); + + mac_dev->fman_mac = dtsec_config(¶ms); + if (!mac_dev->fman_mac) { + err = -EINVAL; + goto _return; + } + + err = dtsec_cfg_max_frame_len(mac_dev->fman_mac, fman_get_max_frm()); + if (err < 0) + goto _return_fm_mac_free; + + err = dtsec_cfg_pad_and_crc(mac_dev->fman_mac, true); + if (err < 0) + goto _return_fm_mac_free; + + err = dtsec_init(mac_dev->fman_mac); + if (err < 0) + goto _return_fm_mac_free; + + /* For 1G MAC, disable by default the MIB counters overflow interrupt */ + err = mac_dev->set_exception(mac_dev->fman_mac, + FM_MAC_EX_1G_RX_MIB_CNT_OVFL, false); + if (err < 0) + goto _return_fm_mac_free; + + err = dtsec_get_version(mac_dev->fman_mac, &version); + if (err < 0) + goto _return_fm_mac_free; + + dev_info(priv->dev, "FMan dTSEC version: 0x%08x\n", version); + + goto _return; + +_return_fm_mac_free: + dtsec_free(mac_dev->fman_mac); + +_return: + return err; +} + +static int memac_initialization(struct mac_device *mac_dev) +{ + int err; + struct mac_priv_s *priv; + struct fman_mac_params params; + + priv = mac_dev->priv; + + set_fman_mac_params(mac_dev, ¶ms); + + if (priv->max_speed == SPEED_10000) + params.phy_if = PHY_INTERFACE_MODE_XGMII; + + mac_dev->fman_mac = memac_config(¶ms); + if (!mac_dev->fman_mac) { + err = -EINVAL; + goto _return; + } + + err = memac_cfg_max_frame_len(mac_dev->fman_mac, fman_get_max_frm()); + if (err < 0) + goto _return_fm_mac_free; + + err = memac_cfg_reset_on_init(mac_dev->fman_mac, true); + if (err < 0) + goto _return_fm_mac_free; + + err = memac_cfg_fixed_link(mac_dev->fman_mac, priv->fixed_link); + if (err < 0) + goto _return_fm_mac_free; + + err = memac_init(mac_dev->fman_mac); + if (err < 0) + goto _return_fm_mac_free; + + dev_info(priv->dev, "FMan MEMAC\n"); + + goto _return; + +_return_fm_mac_free: + memac_free(mac_dev->fman_mac); + +_return: + return err; +} + +static int start(struct mac_device *mac_dev) +{ + int err; + struct phy_device *phy_dev = mac_dev->phy_dev; + struct mac_priv_s *priv = mac_dev->priv; + + err = priv->enable(mac_dev->fman_mac, COMM_MODE_RX_AND_TX); + if (!err && phy_dev) + phy_start(phy_dev); + + return err; +} + +static int stop(struct mac_device *mac_dev) +{ + struct mac_priv_s *priv = mac_dev->priv; + + if (mac_dev->phy_dev) + phy_stop(mac_dev->phy_dev); + + return priv->disable(mac_dev->fman_mac, COMM_MODE_RX_AND_TX); +} + +static int set_multi(struct net_device *net_dev, struct mac_device *mac_dev) +{ + struct mac_priv_s *priv; + struct mac_address *old_addr, *tmp; + struct netdev_hw_addr *ha; + int err; + enet_addr_t *addr; + + priv = mac_dev->priv; + + /* Clear previous address list */ + list_for_each_entry_safe(old_addr, tmp, &priv->mc_addr_list, list) { + addr = (enet_addr_t *)old_addr->addr; + err = mac_dev->remove_hash_mac_addr(mac_dev->fman_mac, addr); + if (err < 0) + return err; + + list_del(&old_addr->list); + kfree(old_addr); + } + + /* Add all the addresses from the new list */ + netdev_for_each_mc_addr(ha, net_dev) { + addr = (enet_addr_t *)ha->addr; + err = mac_dev->add_hash_mac_addr(mac_dev->fman_mac, addr); + if (err < 0) + return err; + + tmp = kmalloc(sizeof(*tmp), GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + + ether_addr_copy(tmp->addr, ha->addr); + list_add(&tmp->list, &priv->mc_addr_list); + } + return 0; +} + +/** + * fman_set_mac_active_pause + * @mac_dev: A pointer to the MAC device + * @rx: Pause frame setting for RX + * @tx: Pause frame setting for TX + * + * Set the MAC RX/TX PAUSE frames settings + * + * Avoid redundant calls to FMD, if the MAC driver already contains the desired + * active PAUSE settings. Otherwise, the new active settings should be reflected + * in FMan. + * + * Return: 0 on success; Error code otherwise. + */ +int fman_set_mac_active_pause(struct mac_device *mac_dev, bool rx, bool tx) +{ + struct fman_mac *fman_mac = mac_dev->fman_mac; + int err = 0; + + if (rx != mac_dev->rx_pause_active) { + err = mac_dev->set_rx_pause(fman_mac, rx); + if (likely(err == 0)) + mac_dev->rx_pause_active = rx; + } + + if (tx != mac_dev->tx_pause_active) { + u16 pause_time = (tx ? FSL_FM_PAUSE_TIME_ENABLE : + FSL_FM_PAUSE_TIME_DISABLE); + + err = mac_dev->set_tx_pause(fman_mac, 0, pause_time, 0); + + if (likely(err == 0)) + mac_dev->tx_pause_active = tx; + } + + return err; +} +EXPORT_SYMBOL(fman_set_mac_active_pause); + +/** + * fman_get_pause_cfg + * @mac_dev: A pointer to the MAC device + * @rx: Return value for RX setting + * @tx: Return value for TX setting + * + * Determine the MAC RX/TX PAUSE frames settings based on PHY + * autonegotiation or values set by eththool. + * + * Return: Pointer to FMan device. + */ +void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, + bool *tx_pause) +{ + struct phy_device *phy_dev = mac_dev->phy_dev; + u16 lcl_adv, rmt_adv; + u8 flowctrl; + + *rx_pause = *tx_pause = false; + + if (!phy_dev->duplex) + return; + + /* If PAUSE autonegotiation is disabled, the TX/RX PAUSE settings + * are those set by ethtool. + */ + if (!mac_dev->autoneg_pause) { + *rx_pause = mac_dev->rx_pause_req; + *tx_pause = mac_dev->tx_pause_req; + return; + } + + /* Else if PAUSE autonegotiation is enabled, the TX/RX PAUSE + * settings depend on the result of the link negotiation. + */ + + /* get local capabilities */ + lcl_adv = 0; + if (phy_dev->advertising & ADVERTISED_Pause) + lcl_adv |= ADVERTISE_PAUSE_CAP; + if (phy_dev->advertising & ADVERTISED_Asym_Pause) + lcl_adv |= ADVERTISE_PAUSE_ASYM; + + /* get link partner capabilities */ + rmt_adv = 0; + if (phy_dev->pause) + rmt_adv |= LPA_PAUSE_CAP; + if (phy_dev->asym_pause) + rmt_adv |= LPA_PAUSE_ASYM; + + /* Calculate TX/RX settings based on local and peer advertised + * symmetric/asymmetric PAUSE capabilities. + */ + flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); + if (flowctrl & FLOW_CTRL_RX) + *rx_pause = true; + if (flowctrl & FLOW_CTRL_TX) + *tx_pause = true; +} +EXPORT_SYMBOL(fman_get_pause_cfg); + +static void adjust_link_void(struct net_device *net_dev) +{ +} + +static void adjust_link_dtsec(struct net_device *net_dev) +{ + struct device *dev = net_dev->dev.parent; + struct dpaa_eth_data *eth_data = dev->platform_data; + struct mac_device *mac_dev = eth_data->mac_dev; + struct phy_device *phy_dev = mac_dev->phy_dev; + struct fman_mac *fman_mac; + bool rx_pause, tx_pause; + int err; + + fman_mac = mac_dev->fman_mac; + if (!phy_dev->link) { + dtsec_restart_autoneg(fman_mac); + + return; + } + + dtsec_adjust_link(fman_mac, phy_dev->speed); + fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); + err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); + if (err < 0) + netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err); +} + +static void adjust_link_memac(struct net_device *net_dev) +{ + struct device *dev = net_dev->dev.parent; + struct dpaa_eth_data *eth_data = dev->platform_data; + struct mac_device *mac_dev = eth_data->mac_dev; + struct phy_device *phy_dev = mac_dev->phy_dev; + struct fman_mac *fman_mac; + bool rx_pause, tx_pause; + int err; + + fman_mac = mac_dev->fman_mac; + memac_adjust_link(fman_mac, phy_dev->speed); + + fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); + err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); + if (err < 0) + netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err); +} + +/* Initializes driver's PHY state, and attaches to the PHY. + * Returns 0 on success. + */ +static int init_phy(struct net_device *net_dev, + struct mac_device *mac_dev, + void (*adj_lnk)(struct net_device *)) +{ + struct phy_device *phy_dev; + struct mac_priv_s *priv = mac_dev->priv; + + phy_dev = of_phy_connect(net_dev, priv->phy_node, adj_lnk, 0, + priv->phy_if); + if (!phy_dev) { + netdev_err(net_dev, "Could not connect to PHY\n"); + return -ENODEV; + } + + /* Remove any features not supported by the controller */ + phy_dev->supported &= mac_dev->if_support; + /* Enable the symmetric and asymmetric PAUSE frame advertisements, + * as most of the PHY drivers do not enable them by default. + */ + phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + phy_dev->advertising = phy_dev->supported; + + mac_dev->phy_dev = phy_dev; + + return 0; +} + +static int dtsec_init_phy(struct net_device *net_dev, + struct mac_device *mac_dev) +{ + return init_phy(net_dev, mac_dev, &adjust_link_dtsec); +} + +static int tgec_init_phy(struct net_device *net_dev, + struct mac_device *mac_dev) +{ + return init_phy(net_dev, mac_dev, adjust_link_void); +} + +static int memac_init_phy(struct net_device *net_dev, + struct mac_device *mac_dev) +{ + return init_phy(net_dev, mac_dev, &adjust_link_memac); +} + +static void setup_dtsec(struct mac_device *mac_dev) +{ + mac_dev->init_phy = dtsec_init_phy; + mac_dev->init = dtsec_initialization; + mac_dev->set_promisc = dtsec_set_promiscuous; + mac_dev->change_addr = dtsec_modify_mac_address; + mac_dev->add_hash_mac_addr = dtsec_add_hash_mac_address; + mac_dev->remove_hash_mac_addr = dtsec_del_hash_mac_address; + mac_dev->set_tx_pause = dtsec_set_tx_pause_frames; + mac_dev->set_rx_pause = dtsec_accept_rx_pause_frames; + mac_dev->set_exception = dtsec_set_exception; + mac_dev->set_multi = set_multi; + mac_dev->start = start; + mac_dev->stop = stop; + + mac_dev->priv->enable = dtsec_enable; + mac_dev->priv->disable = dtsec_disable; +} + +static void setup_tgec(struct mac_device *mac_dev) +{ + mac_dev->init_phy = tgec_init_phy; + mac_dev->init = tgec_initialization; + mac_dev->set_promisc = tgec_set_promiscuous; + mac_dev->change_addr = tgec_modify_mac_address; + mac_dev->add_hash_mac_addr = tgec_add_hash_mac_address; + mac_dev->remove_hash_mac_addr = tgec_del_hash_mac_address; + mac_dev->set_tx_pause = tgec_set_tx_pause_frames; + mac_dev->set_rx_pause = tgec_accept_rx_pause_frames; + mac_dev->set_exception = tgec_set_exception; + mac_dev->set_multi = set_multi; + mac_dev->start = start; + mac_dev->stop = stop; + + mac_dev->priv->enable = tgec_enable; + mac_dev->priv->disable = tgec_disable; +} + +static void setup_memac(struct mac_device *mac_dev) +{ + mac_dev->init_phy = memac_init_phy; + mac_dev->init = memac_initialization; + mac_dev->set_promisc = memac_set_promiscuous; + mac_dev->change_addr = memac_modify_mac_address; + mac_dev->add_hash_mac_addr = memac_add_hash_mac_address; + mac_dev->remove_hash_mac_addr = memac_del_hash_mac_address; + mac_dev->set_tx_pause = memac_set_tx_pause_frames; + mac_dev->set_rx_pause = memac_accept_rx_pause_frames; + mac_dev->set_exception = memac_set_exception; + mac_dev->set_multi = set_multi; + mac_dev->start = start; + mac_dev->stop = stop; + + mac_dev->priv->enable = memac_enable; + mac_dev->priv->disable = memac_disable; +} + +#define DTSEC_SUPPORTED \ + (SUPPORTED_10baseT_Half \ + | SUPPORTED_10baseT_Full \ + | SUPPORTED_100baseT_Half \ + | SUPPORTED_100baseT_Full \ + | SUPPORTED_Autoneg \ + | SUPPORTED_Pause \ + | SUPPORTED_Asym_Pause \ + | SUPPORTED_MII) + +static DEFINE_MUTEX(eth_lock); + +static const char phy_str[][11] = { + [PHY_INTERFACE_MODE_MII] = "mii", + [PHY_INTERFACE_MODE_GMII] = "gmii", + [PHY_INTERFACE_MODE_SGMII] = "sgmii", + [PHY_INTERFACE_MODE_TBI] = "tbi", + [PHY_INTERFACE_MODE_RMII] = "rmii", + [PHY_INTERFACE_MODE_RGMII] = "rgmii", + [PHY_INTERFACE_MODE_RGMII_ID] = "rgmii-id", + [PHY_INTERFACE_MODE_RGMII_RXID] = "rgmii-rxid", + [PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid", + [PHY_INTERFACE_MODE_RTBI] = "rtbi", + [PHY_INTERFACE_MODE_XGMII] = "xgmii" +}; + +static phy_interface_t __pure __attribute__((nonnull)) str2phy(const char *str) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(phy_str); i++) + if (strcmp(str, phy_str[i]) == 0) + return (phy_interface_t)i; + + return PHY_INTERFACE_MODE_MII; +} + +static const u16 phy2speed[] = { + [PHY_INTERFACE_MODE_MII] = SPEED_100, + [PHY_INTERFACE_MODE_GMII] = SPEED_1000, + [PHY_INTERFACE_MODE_SGMII] = SPEED_1000, + [PHY_INTERFACE_MODE_TBI] = SPEED_1000, + [PHY_INTERFACE_MODE_RMII] = SPEED_100, + [PHY_INTERFACE_MODE_RGMII] = SPEED_1000, + [PHY_INTERFACE_MODE_RGMII_ID] = SPEED_1000, + [PHY_INTERFACE_MODE_RGMII_RXID] = SPEED_1000, + [PHY_INTERFACE_MODE_RGMII_TXID] = SPEED_1000, + [PHY_INTERFACE_MODE_RTBI] = SPEED_1000, + [PHY_INTERFACE_MODE_XGMII] = SPEED_10000 +}; + +static struct platform_device *dpaa_eth_add_device(int fman_id, + struct mac_device *mac_dev, + struct device_node *node) +{ + struct platform_device *pdev; + struct dpaa_eth_data data; + struct mac_priv_s *priv; + static int dpaa_eth_dev_cnt; + int ret; + + priv = mac_dev->priv; + + data.mac_dev = mac_dev; + data.mac_hw_id = priv->cell_index; + data.fman_hw_id = fman_id; + data.mac_node = node; + + mutex_lock(ð_lock); + + pdev = platform_device_alloc("dpaa-ethernet", dpaa_eth_dev_cnt); + if (!pdev) { + ret = -ENOMEM; + goto no_mem; + } + + ret = platform_device_add_data(pdev, &data, sizeof(data)); + if (ret) + goto err; + + ret = platform_device_add(pdev); + if (ret) + goto err; + + dpaa_eth_dev_cnt++; + mutex_unlock(ð_lock); + + return pdev; + +err: + platform_device_put(pdev); +no_mem: + mutex_unlock(ð_lock); + + return ERR_PTR(ret); +} + +static const struct of_device_id mac_match[] = { + { .compatible = "fsl,fman-dtsec" }, + { .compatible = "fsl,fman-xgec" }, + { .compatible = "fsl,fman-memac" }, + {} +}; +MODULE_DEVICE_TABLE(of, mac_match); + +static int mac_probe(struct platform_device *_of_dev) +{ + int err, i, lenp, nph; + struct device *dev; + struct device_node *mac_node, *dev_node; + struct mac_device *mac_dev; + struct platform_device *of_dev; + struct resource res; + struct mac_priv_s *priv; + const u8 *mac_addr; + const char *char_prop; + const u32 *u32_prop; + u8 fman_id; + + dev = &_of_dev->dev; + mac_node = dev->of_node; + + mac_dev = devm_kzalloc(dev, sizeof(*mac_dev), GFP_KERNEL); + if (!mac_dev) { + err = -ENOMEM; + dev_err(dev, "devm_kzalloc() = %d\n", err); + goto _return; + } + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto _return; + } + + /* Save private information */ + mac_dev->priv = priv; + priv->dev = dev; + + if (of_device_is_compatible(mac_node, "fsl,fman-dtsec")) { + setup_dtsec(mac_dev); + priv->internal_phy_node = of_parse_phandle(mac_node, + "tbi-handle", 0); + } else if (of_device_is_compatible(mac_node, "fsl,fman-xgec")) { + setup_tgec(mac_dev); + } else if (of_device_is_compatible(mac_node, "fsl,fman-memac")) { + setup_memac(mac_dev); + priv->internal_phy_node = of_parse_phandle(mac_node, + "pcsphy-handle", 0); + } else { + dev_err(dev, "MAC node (%s) contains unsupported MAC\n", + mac_node->full_name); + err = -EINVAL; + goto _return; + } + + /* Register mac_dev */ + dev_set_drvdata(dev, mac_dev); + + INIT_LIST_HEAD(&priv->mc_addr_list); + + /* Get the FM node */ + dev_node = of_get_parent(mac_node); + if (!dev_node) { + dev_err(dev, "of_get_parent(%s) failed\n", + mac_node->full_name); + err = -EINVAL; + goto _return_dev_set_drvdata; + } + + of_dev = of_find_device_by_node(dev_node); + if (!of_dev) { + dev_err(dev, "of_find_device_by_node(%s) failed\n", + dev_node->full_name); + err = -EINVAL; + goto _return_of_node_put; + } + + /* Get the FMan cell-index */ + u32_prop = of_get_property(dev_node, "cell-index", &lenp); + if (!u32_prop) { + dev_err(dev, "of_get_property(%s, cell-index) failed\n", + dev_node->full_name); + err = -EINVAL; + goto _return_of_node_put; + } + WARN_ON(lenp != sizeof(u32)); + /* cell-index 0 => FMan id 1 */ + fman_id = (u8)(fdt32_to_cpu(u32_prop[0]) + 1); + + priv->fman = fman_bind(&of_dev->dev); + if (!priv->fman) { + dev_err(dev, "fman_bind(%s) failed\n", dev_node->full_name); + err = -ENODEV; + goto _return_of_node_put; + } + + of_node_put(dev_node); + + /* Get the address of the memory mapped registers */ + err = of_address_to_resource(mac_node, 0, &res); + if (err < 0) { + dev_err(dev, "of_address_to_resource(%s) = %d\n", + mac_node->full_name, err); + goto _return_dev_set_drvdata; + } + + mac_dev->res = __devm_request_region(dev, + fman_get_mem_region(priv->fman), + res.start, res.end + 1 - res.start, + "mac"); + if (!mac_dev->res) { + dev_err(dev, "__devm_request_mem_region(mac) failed\n"); + err = -EBUSY; + goto _return_dev_set_drvdata; + } + + priv->vaddr = devm_ioremap(dev, mac_dev->res->start, + mac_dev->res->end + 1 - mac_dev->res->start); + if (!priv->vaddr) { + dev_err(dev, "devm_ioremap() failed\n"); + err = -EIO; + goto _return_dev_set_drvdata; + } + + if (!of_device_is_available(mac_node)) { + devm_iounmap(dev, priv->vaddr); + __devm_release_region(dev, fman_get_mem_region(priv->fman), + res.start, res.end + 1 - res.start); + devm_kfree(dev, mac_dev); + dev_set_drvdata(dev, NULL); + return -ENODEV; + } + + /* Get the cell-index */ + u32_prop = of_get_property(mac_node, "cell-index", &lenp); + if (!u32_prop) { + dev_err(dev, "of_get_property(%s, cell-index) failed\n", + mac_node->full_name); + err = -EINVAL; + goto _return_dev_set_drvdata; + } + WARN_ON(lenp != sizeof(u32)); + priv->cell_index = (u8)fdt32_to_cpu(u32_prop[0]); + + /* Get the MAC address */ + mac_addr = of_get_mac_address(mac_node); + if (!mac_addr) { + dev_err(dev, "of_get_mac_address(%s) failed\n", + mac_node->full_name); + err = -EINVAL; + goto _return_dev_set_drvdata; + } + memcpy(mac_dev->addr, mac_addr, sizeof(mac_dev->addr)); + + /* Get the port handles */ + nph = of_count_phandle_with_args(mac_node, "fsl,fman-ports", NULL); + if (unlikely(nph < 0)) { + dev_err(dev, "of_count_phandle_with_args(%s, fsl,fman-ports) failed\n", + mac_node->full_name); + err = nph; + goto _return_dev_set_drvdata; + } + + if (nph != ARRAY_SIZE(mac_dev->port)) { + dev_err(dev, "Not supported number of fman-ports handles of mac node %s from device tree\n", + mac_node->full_name); + err = -EINVAL; + goto _return_dev_set_drvdata; + } + + for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { + /* Find the port node */ + dev_node = of_parse_phandle(mac_node, "fsl,fman-ports", i); + if (!dev_node) { + dev_err(dev, "of_parse_phandle(%s, fsl,fman-ports) failed\n", + mac_node->full_name); + err = -EINVAL; + goto _return_of_node_put; + } + + of_dev = of_find_device_by_node(dev_node); + if (!of_dev) { + dev_err(dev, "of_find_device_by_node(%s) failed\n", + dev_node->full_name); + err = -EINVAL; + goto _return_of_node_put; + } + + mac_dev->port[i] = fman_port_bind(&of_dev->dev); + if (!mac_dev->port[i]) { + dev_err(dev, "dev_get_drvdata(%s) failed\n", + dev_node->full_name); + err = -EINVAL; + goto _return_of_node_put; + } + of_node_put(dev_node); + } + + /* Get the PHY connection type */ + char_prop = (const char *)of_get_property(mac_node, + "phy-connection-type", NULL); + if (!char_prop) { + dev_warn(dev, + "of_get_property(%s, phy-connection-type) failed. Defaulting to MII\n", + mac_node->full_name); + priv->phy_if = PHY_INTERFACE_MODE_MII; + } else { + priv->phy_if = str2phy(char_prop); + } + + priv->speed = phy2speed[priv->phy_if]; + priv->max_speed = priv->speed; + mac_dev->if_support = DTSEC_SUPPORTED; + /* We don't support half-duplex in SGMII mode */ + if (priv->phy_if == PHY_INTERFACE_MODE_SGMII) + mac_dev->if_support &= ~(SUPPORTED_10baseT_Half | + SUPPORTED_100baseT_Half); + + /* Gigabit support (no half-duplex) */ + if (priv->max_speed == 1000) + mac_dev->if_support |= SUPPORTED_1000baseT_Full; + + /* The 10G interface only supports one mode */ + if (priv->phy_if == PHY_INTERFACE_MODE_XGMII) + mac_dev->if_support = SUPPORTED_10000baseT_Full; + + /* Get the rest of the PHY information */ + priv->phy_node = of_parse_phandle(mac_node, "phy-handle", 0); + if (!priv->phy_node && of_phy_is_fixed_link(mac_node)) { + struct phy_device *phy; + + err = of_phy_register_fixed_link(mac_node); + if (err) + goto _return_dev_set_drvdata; + + priv->fixed_link = kzalloc(sizeof(*priv->fixed_link), + GFP_KERNEL); + if (!priv->fixed_link) + goto _return_dev_set_drvdata; + + priv->phy_node = of_node_get(mac_node); + phy = of_phy_find_device(priv->phy_node); + if (!phy) + goto _return_dev_set_drvdata; + + priv->fixed_link->link = phy->link; + priv->fixed_link->speed = phy->speed; + priv->fixed_link->duplex = phy->duplex; + priv->fixed_link->pause = phy->pause; + priv->fixed_link->asym_pause = phy->asym_pause; + } + + err = mac_dev->init(mac_dev); + if (err < 0) { + dev_err(dev, "mac_dev->init() = %d\n", err); + of_node_put(priv->phy_node); + goto _return_dev_set_drvdata; + } + + /* pause frame autonegotiation enabled */ + mac_dev->autoneg_pause = true; + + /* By intializing the values to false, force FMD to enable PAUSE frames + * on RX and TX + */ + mac_dev->rx_pause_req = true; + mac_dev->tx_pause_req = true; + mac_dev->rx_pause_active = false; + mac_dev->tx_pause_active = false; + err = fman_set_mac_active_pause(mac_dev, true, true); + if (err < 0) + dev_err(dev, "fman_set_mac_active_pause() = %d\n", err); + + dev_info(dev, "FMan MAC address: %02hx:%02hx:%02hx:%02hx:%02hx:%02hx\n", + mac_dev->addr[0], mac_dev->addr[1], mac_dev->addr[2], + mac_dev->addr[3], mac_dev->addr[4], mac_dev->addr[5]); + + priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev, mac_node); + if (IS_ERR(priv->eth_dev)) { + dev_err(dev, "failed to add Ethernet platform device for MAC %d\n", + priv->cell_index); + priv->eth_dev = NULL; + } + + goto _return; + +_return_of_node_put: + of_node_put(dev_node); +_return_dev_set_drvdata: + kfree(priv->fixed_link); + kfree(priv); + dev_set_drvdata(dev, NULL); +_return: + return err; +} + +static struct platform_driver mac_driver = { + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = mac_match, + }, + .probe = mac_probe, +}; + +builtin_platform_driver(mac_driver); diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h new file mode 100644 index 0000000000000..0211cc9a46d63 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -0,0 +1,97 @@ +/* Copyright 2008-2015 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __MAC_H +#define __MAC_H + +#include <linux/device.h> +#include <linux/if_ether.h> +#include <linux/phy.h> +#include <linux/list.h> + +#include "fman_port.h" +#include "fman.h" +#include "fman_mac.h" + +struct fman_mac; +struct mac_priv_s; + +struct mac_device { + struct resource *res; + u8 addr[ETH_ALEN]; + struct fman_port *port[2]; + u32 if_support; + struct phy_device *phy_dev; + + bool autoneg_pause; + bool rx_pause_req; + bool tx_pause_req; + bool rx_pause_active; + bool tx_pause_active; + bool promisc; + + int (*init_phy)(struct net_device *net_dev, struct mac_device *mac_dev); + int (*init)(struct mac_device *mac_dev); + int (*start)(struct mac_device *mac_dev); + int (*stop)(struct mac_device *mac_dev); + int (*set_promisc)(struct fman_mac *mac_dev, bool enable); + int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); + int (*set_multi)(struct net_device *net_dev, + struct mac_device *mac_dev); + int (*set_rx_pause)(struct fman_mac *mac_dev, bool en); + int (*set_tx_pause)(struct fman_mac *mac_dev, u8 priority, + u16 pause_time, u16 thresh_time); + int (*set_exception)(struct fman_mac *mac_dev, + enum fman_mac_exceptions exception, bool enable); + int (*add_hash_mac_addr)(struct fman_mac *mac_dev, + enet_addr_t *eth_addr); + int (*remove_hash_mac_addr)(struct fman_mac *mac_dev, + enet_addr_t *eth_addr); + + struct fman_mac *fman_mac; + struct mac_priv_s *priv; +}; + +struct dpaa_eth_data { + struct device_node *mac_node; + struct mac_device *mac_dev; + int mac_hw_id; + int fman_hw_id; +}; + +extern const char *mac_driver_description; + +int fman_set_mac_active_pause(struct mac_device *mac_dev, bool rx, bool tx); + +void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, + bool *tx_pause); + +#endif /* __MAC_H */ diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c index 08f5b911d96be..52e0091b4fb26 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c @@ -552,7 +552,7 @@ static void tx_restart(struct net_device *dev) cbd_t __iomem *prev_bd; cbd_t __iomem *last_tx_bd; - last_tx_bd = fep->tx_bd_base + (fpi->tx_ring * sizeof(cbd_t)); + last_tx_bd = fep->tx_bd_base + ((fpi->tx_ring - 1) * sizeof(cbd_t)); /* get the current bd held in TBPTR and scan back from this point */ recheck_bd = curr_tbptr = (cbd_t __iomem *) diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 55c36230e1763..40071dad1c570 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -464,7 +464,7 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) * address). Print error message but continue anyway. */ if ((void *)tbipa > priv->map + resource_size(&res) - 4) - dev_err(&pdev->dev, "invalid register map (should be at least 0x%04x to contain TBI address)\n", + dev_err(&pdev->dev, "invalid register map (should be at least 0x%04zx to contain TBI address)\n", ((void *)tbipa - priv->map) + 4); iowrite32be(be32_to_cpup(prop), tbipa); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4ce60e0c83413..4e394f75261e3 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -891,7 +891,8 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) FSL_GIANFAR_DEV_HAS_VLAN | FSL_GIANFAR_DEV_HAS_MAGIC_PACKET | FSL_GIANFAR_DEV_HAS_EXTENDED_HASH | - FSL_GIANFAR_DEV_HAS_TIMER; + FSL_GIANFAR_DEV_HAS_TIMER | + FSL_GIANFAR_DEV_HAS_RX_FILER; err = of_property_read_string(np, "phy-connection-type", &ctype); @@ -1393,8 +1394,9 @@ static int gfar_probe(struct platform_device *ofdev) priv->rx_queue[i]->rxic = DEFAULT_RXIC; } - /* always enable rx filer */ - priv->rx_filer_enable = 1; + /* Always enable rx filer if available */ + priv->rx_filer_enable = + (priv->device_flags & FSL_GIANFAR_DEV_HAS_RX_FILER) ? 1 : 0; /* Enable most messages by default */ priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1; /* use pritority h/w tx queue scheduling for single queue devices */ diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index f266b20f9ef5b..cb77667971a7e 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -923,6 +923,7 @@ struct gfar { #define FSL_GIANFAR_DEV_HAS_BUF_STASHING 0x00000400 #define FSL_GIANFAR_DEV_HAS_TIMER 0x00000800 #define FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER 0x00001000 +#define FSL_GIANFAR_DEV_HAS_RX_FILER 0x00002000 #if (MAXGROUPS == 2) #define DEFAULT_MAPPING 0xAA diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 636b205a23660..1c33bd06bd5cc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -1376,12 +1376,8 @@ int hns_dsaf_set_mac_uc_entry( if (MAC_IS_ALL_ZEROS(mac_entry->addr) || MAC_IS_BROADCAST(mac_entry->addr) || MAC_IS_MULTICAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "set_uc %s Mac %02x:%02x:%02x:%02x:%02x:%02x err!\n", - dsaf_dev->ae_dev.name, mac_entry->addr[0], - mac_entry->addr[1], mac_entry->addr[2], - mac_entry->addr[3], mac_entry->addr[4], - mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "set_uc %s Mac %pM err!\n", + dsaf_dev->ae_dev.name, mac_entry->addr); return -EINVAL; } @@ -1448,12 +1444,8 @@ int hns_dsaf_set_mac_mc_entry( /* mac addr check */ if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "set uc %s Mac %02x:%02x:%02x:%02x:%02x:%02x err!\n", - dsaf_dev->ae_dev.name, mac_entry->addr[0], - mac_entry->addr[1], mac_entry->addr[2], - mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "set uc %s Mac %pM err!\n", + dsaf_dev->ae_dev.name, mac_entry->addr); return -EINVAL; } @@ -1527,11 +1519,8 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, /*chechk mac addr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "set_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x!\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "set_entry failed,addr %pM!\n", + mac_entry->addr); return -EINVAL; } @@ -1614,9 +1603,8 @@ int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id, /*check mac addr */ if (MAC_IS_ALL_ZEROS(addr) || MAC_IS_BROADCAST(addr)) { - dev_err(dsaf_dev->dev, - "del_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x!\n", - addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + dev_err(dsaf_dev->dev, "del_entry failed,addr %pM!\n", + addr); return -EINVAL; } @@ -1680,11 +1668,8 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, /*check mac addr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "del_port failed, addr %02x:%02x:%02x:%02x:%02x:%02x!\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "del_port failed, addr %pM!\n", + mac_entry->addr); return -EINVAL; } @@ -1761,11 +1746,8 @@ int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev, /* check macaddr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr) || MAC_IS_BROADCAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "get_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n", + mac_entry->addr); return -EINVAL; } @@ -1812,11 +1794,8 @@ int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev, /*check mac addr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr) || MAC_IS_BROADCAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "get_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n", + mac_entry->addr); return -EINVAL; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 8c30cec8850a8..d2263c72bd8a4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -499,8 +499,7 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common) int base_irq_idx = hns_rcb_get_base_irq_idx(rcb_common); struct device_node *np = rcb_common->dsaf_dev->dev->of_node; struct platform_device *pdev = - container_of(rcb_common->dsaf_dev->dev, - struct platform_device, dev); + to_platform_device(rcb_common->dsaf_dev->dev); bool is_ver1 = AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver); for (i = 0; i < ring_num; i++) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index c4d7c26952c42..5d1b746e141d7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -956,7 +956,7 @@ #define XGMAC_PAUSE_CTL_RSP_MODE_B 2 #define XGMAC_PAUSE_CTL_TX_XOFF_B 3 -static inline void dsaf_write_reg(void *base, u32 reg, u32 value) +static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) { u8 __iomem *reg_addr = ACCESS_ONCE(base); @@ -966,7 +966,7 @@ static inline void dsaf_write_reg(void *base, u32 reg, u32 value) #define dsaf_write_dev(a, reg, value) \ dsaf_write_reg((a)->io_base, (reg), (value)) -static inline u32 dsaf_read_reg(u8 *base, u32 reg) +static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg) { u8 __iomem *reg_addr = ACCESS_ONCE(base); @@ -985,8 +985,8 @@ static inline u32 dsaf_read_reg(u8 *base, u32 reg) #define dsaf_set_bit(origin, shift, val) \ dsaf_set_field((origin), (1ull << (shift)), (shift), (val)) -static inline void dsaf_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, - u32 val) +static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask, + u32 shift, u32 val) { u32 origin = dsaf_read_reg(base, reg); @@ -1005,7 +1005,8 @@ static inline void dsaf_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, #define dsaf_get_bit(origin, shift) \ dsaf_get_field((origin), (1ull << (shift)), (shift)) -static inline u32 dsaf_get_reg_field(void *base, u32 reg, u32 mask, u32 shift) +static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask, + u32 shift) { u32 origin; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 5a81dafd725e2..0e30846a24f89 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -499,50 +499,47 @@ static void hns_nic_reuse_page(struct sk_buff *skb, int i, struct hnae_desc *desc; int truesize, size; int last_offset; + bool twobufs; + + twobufs = ((PAGE_SIZE < 8192) && hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048); desc = &ring->desc[ring->next_to_clean]; size = le16_to_cpu(desc->rx.size); -#if (PAGE_SIZE < 8192) - if (hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048) { + if (twobufs) { truesize = hnae_buf_size(ring); } else { truesize = ALIGN(size, L1_CACHE_BYTES); last_offset = hnae_page_size(ring) - hnae_buf_size(ring); } -#else - truesize = ALIGN(size, L1_CACHE_BYTES); - last_offset = hnae_page_size(ring) - hnae_buf_size(ring); -#endif - skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, size - pull_len, truesize - pull_len); /* avoid re-using remote pages,flag default unreuse */ - if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) { -#if (PAGE_SIZE < 8192) - if (hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048) { - /* if we are only owner of page we can reuse it */ - if (likely(page_count(desc_cb->priv) == 1)) { - /* flip page offset to other buffer */ - desc_cb->page_offset ^= truesize; - - desc_cb->reuse_flag = 1; - /* bump ref count on page before it is given*/ - get_page(desc_cb->priv); - } - return; - } -#endif - /* move offset up to the next cache line */ - desc_cb->page_offset += truesize; + if (unlikely(page_to_nid(desc_cb->priv) != numa_node_id())) + return; + + if (twobufs) { + /* if we are only owner of page we can reuse it */ + if (likely(page_count(desc_cb->priv) == 1)) { + /* flip page offset to other buffer */ + desc_cb->page_offset ^= truesize; - if (desc_cb->page_offset <= last_offset) { desc_cb->reuse_flag = 1; /* bump ref count on page before it is given*/ get_page(desc_cb->priv); } + return; + } + + /* move offset up to the next cache line */ + desc_cb->page_offset += truesize; + + if (desc_cb->page_offset <= last_offset) { + desc_cb->reuse_flag = 1; + /* bump ref count on page before it is given*/ + get_page(desc_cb->priv); } } diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index ae6e30d39f0f6..1d5c3e16d8f4f 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -2843,7 +2843,7 @@ static void cleanup_dev(struct net_device *d) } #ifdef CONFIG_EISA -static int __init hp100_eisa_probe (struct device *gendev) +static int hp100_eisa_probe(struct device *gendev) { struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private)); struct eisa_device *edev = to_eisa_device(gendev); diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig index 99c1cebd002d7..37dceabf8861a 100644 --- a/drivers/net/ethernet/ibm/Kconfig +++ b/drivers/net/ethernet/ibm/Kconfig @@ -37,4 +37,14 @@ config EHEA To compile the driver as a module, choose M here. The module will be called ehea. +config IBMVNIC + tristate "IBM Virtual NIC support" + depends on PPC_PSERIES + ---help--- + This driver supports Virtual NIC adapters on IBM i and IBM System p + systems. + + To compile this driver as a module, choose M here. The module will + be called ibmvnic. + endif # NET_VENDOR_IBM diff --git a/drivers/net/ethernet/ibm/Makefile b/drivers/net/ethernet/ibm/Makefile index 2f04e71a5926c..447865c8b632d 100644 --- a/drivers/net/ethernet/ibm/Makefile +++ b/drivers/net/ethernet/ibm/Makefile @@ -3,5 +3,6 @@ # obj-$(CONFIG_IBMVETH) += ibmveth.o +obj-$(CONFIG_IBMVNIC) += ibmvnic.o obj-$(CONFIG_IBM_EMAC) += emac/ obj-$(CONFIG_EHEA) += ehea/ diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 7af870a3c5495..335417b4756b7 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -169,7 +169,7 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) if (!pool->free_map) return -1; - pool->dma_addr = kmalloc(sizeof(dma_addr_t) * pool->size, GFP_KERNEL); + pool->dma_addr = kcalloc(pool->size, sizeof(dma_addr_t), GFP_KERNEL); if (!pool->dma_addr) { kfree(pool->free_map); pool->free_map = NULL; @@ -187,8 +187,6 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) return -1; } - memset(pool->dma_addr, 0, sizeof(dma_addr_t) * pool->size); - for (i = 0; i < pool->size; ++i) pool->free_map[i] = i; @@ -763,7 +761,7 @@ static netdev_features_t ibmveth_fix_features(struct net_device *dev, */ if (!(features & NETIF_F_RXCSUM)) - features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_CSUM_MASK; return features; } @@ -928,7 +926,8 @@ static int ibmveth_set_features(struct net_device *dev, rc1 = ibmveth_set_csum_offload(dev, rx_csum); if (rc1 && !adapter->rx_csum) dev->features = - features & ~(NETIF_F_ALL_CSUM | NETIF_F_RXCSUM); + features & ~(NETIF_F_CSUM_MASK | + NETIF_F_RXCSUM); } if (large_send != adapter->large_send) { diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c new file mode 100644 index 0000000000000..7d65708437238 --- /dev/null +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -0,0 +1,3585 @@ +/**************************************************************************/ +/* */ +/* IBM System i and System p Virtual NIC Device Driver */ +/* Copyright (C) 2014 IBM Corp. */ +/* Santiago Leon (santi_leon@yahoo.com) */ +/* Thomas Falcon (tlfalcon@linux.vnet.ibm.com) */ +/* John Allen (jallen@linux.vnet.ibm.com) */ +/* */ +/* This program is free software; you can redistribute it and/or modify */ +/* it under the terms of the GNU General Public License as published by */ +/* the Free Software Foundation; either version 2 of the License, or */ +/* (at your option) any later version. */ +/* */ +/* This program is distributed in the hope that it will be useful, */ +/* but WITHOUT ANY WARRANTY; without even the implied warranty of */ +/* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the */ +/* GNU General Public License for more details. */ +/* */ +/* You should have received a copy of the GNU General Public License */ +/* along with this program. */ +/* */ +/* This module contains the implementation of a virtual ethernet device */ +/* for use with IBM i/p Series LPAR Linux. It utilizes the logical LAN */ +/* option of the RS/6000 Platform Architecture to interface with virtual */ +/* ethernet NICs that are presented to the partition by the hypervisor. */ +/* */ +/* Messages are passed between the VNIC driver and the VNIC server using */ +/* Command/Response Queues (CRQs) and sub CRQs (sCRQs). CRQs are used to */ +/* issue and receive commands that initiate communication with the server */ +/* on driver initialization. Sub CRQs (sCRQs) are similar to CRQs, but */ +/* are used by the driver to notify the server that a packet is */ +/* ready for transmission or that a buffer has been added to receive a */ +/* packet. Subsequently, sCRQs are used by the server to notify the */ +/* driver that a packet transmission has been completed or that a packet */ +/* has been received and placed in a waiting buffer. */ +/* */ +/* In lieu of a more conventional "on-the-fly" DMA mapping strategy in */ +/* which skbs are DMA mapped and immediately unmapped when the transmit */ +/* or receive has been completed, the VNIC driver is required to use */ +/* "long term mapping". This entails that large, continuous DMA mapped */ +/* buffers are allocated on driver initialization and these buffers are */ +/* then continuously reused to pass skbs to and from the VNIC server. */ +/* */ +/**************************************************************************/ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/completion.h> +#include <linux/ioport.h> +#include <linux/dma-mapping.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/mm.h> +#include <linux/ethtool.h> +#include <linux/proc_fs.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/irq.h> +#include <linux/kthread.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/interrupt.h> +#include <net/net_namespace.h> +#include <asm/hvcall.h> +#include <linux/atomic.h> +#include <asm/vio.h> +#include <asm/iommu.h> +#include <linux/uaccess.h> +#include <asm/firmware.h> +#include <linux/seq_file.h> + +#include "ibmvnic.h" + +static const char ibmvnic_driver_name[] = "ibmvnic"; +static const char ibmvnic_driver_string[] = "IBM System i/p Virtual NIC Driver"; + +MODULE_AUTHOR("Santiago Leon <santi_leon@yahoo.com>"); +MODULE_DESCRIPTION("IBM System i/p Virtual NIC Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(IBMVNIC_DRIVER_VERSION); + +static int ibmvnic_version = IBMVNIC_INITIAL_VERSION; +static int ibmvnic_remove(struct vio_dev *); +static void release_sub_crqs(struct ibmvnic_adapter *); +static int ibmvnic_reset_crq(struct ibmvnic_adapter *); +static int ibmvnic_send_crq_init(struct ibmvnic_adapter *); +static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *); +static int ibmvnic_send_crq(struct ibmvnic_adapter *, union ibmvnic_crq *); +static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle, + union sub_crq *sub_crq); +static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance); +static int enable_scrq_irq(struct ibmvnic_adapter *, + struct ibmvnic_sub_crq_queue *); +static int disable_scrq_irq(struct ibmvnic_adapter *, + struct ibmvnic_sub_crq_queue *); +static int pending_scrq(struct ibmvnic_adapter *, + struct ibmvnic_sub_crq_queue *); +static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, + struct ibmvnic_sub_crq_queue *); +static int ibmvnic_poll(struct napi_struct *napi, int data); +static void send_map_query(struct ibmvnic_adapter *adapter); +static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8); +static void send_request_unmap(struct ibmvnic_adapter *, u8); + +struct ibmvnic_stat { + char name[ETH_GSTRING_LEN]; + int offset; +}; + +#define IBMVNIC_STAT_OFF(stat) (offsetof(struct ibmvnic_adapter, stats) + \ + offsetof(struct ibmvnic_statistics, stat)) +#define IBMVNIC_GET_STAT(a, off) (*((u64 *)(((unsigned long)(a)) + off))) + +static const struct ibmvnic_stat ibmvnic_stats[] = { + {"rx_packets", IBMVNIC_STAT_OFF(rx_packets)}, + {"rx_bytes", IBMVNIC_STAT_OFF(rx_bytes)}, + {"tx_packets", IBMVNIC_STAT_OFF(tx_packets)}, + {"tx_bytes", IBMVNIC_STAT_OFF(tx_bytes)}, + {"ucast_tx_packets", IBMVNIC_STAT_OFF(ucast_tx_packets)}, + {"ucast_rx_packets", IBMVNIC_STAT_OFF(ucast_rx_packets)}, + {"mcast_tx_packets", IBMVNIC_STAT_OFF(mcast_tx_packets)}, + {"mcast_rx_packets", IBMVNIC_STAT_OFF(mcast_rx_packets)}, + {"bcast_tx_packets", IBMVNIC_STAT_OFF(bcast_tx_packets)}, + {"bcast_rx_packets", IBMVNIC_STAT_OFF(bcast_rx_packets)}, + {"align_errors", IBMVNIC_STAT_OFF(align_errors)}, + {"fcs_errors", IBMVNIC_STAT_OFF(fcs_errors)}, + {"single_collision_frames", IBMVNIC_STAT_OFF(single_collision_frames)}, + {"multi_collision_frames", IBMVNIC_STAT_OFF(multi_collision_frames)}, + {"sqe_test_errors", IBMVNIC_STAT_OFF(sqe_test_errors)}, + {"deferred_tx", IBMVNIC_STAT_OFF(deferred_tx)}, + {"late_collisions", IBMVNIC_STAT_OFF(late_collisions)}, + {"excess_collisions", IBMVNIC_STAT_OFF(excess_collisions)}, + {"internal_mac_tx_errors", IBMVNIC_STAT_OFF(internal_mac_tx_errors)}, + {"carrier_sense", IBMVNIC_STAT_OFF(carrier_sense)}, + {"too_long_frames", IBMVNIC_STAT_OFF(too_long_frames)}, + {"internal_mac_rx_errors", IBMVNIC_STAT_OFF(internal_mac_rx_errors)}, +}; + +static long h_reg_sub_crq(unsigned long unit_address, unsigned long token, + unsigned long length, unsigned long *number, + unsigned long *irq) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_REG_SUB_CRQ, retbuf, unit_address, token, length); + *number = retbuf[0]; + *irq = retbuf[1]; + + return rc; +} + +/* net_device_ops functions */ + +static void init_rx_pool(struct ibmvnic_adapter *adapter, + struct ibmvnic_rx_pool *rx_pool, int num, int index, + int buff_size, int active) +{ + netdev_dbg(adapter->netdev, + "Initializing rx_pool %d, %d buffs, %d bytes each\n", + index, num, buff_size); + rx_pool->size = num; + rx_pool->index = index; + rx_pool->buff_size = buff_size; + rx_pool->active = active; +} + +static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, + struct ibmvnic_long_term_buff *ltb, int size) +{ + struct device *dev = &adapter->vdev->dev; + + ltb->size = size; + ltb->buff = dma_alloc_coherent(dev, ltb->size, <b->addr, + GFP_KERNEL); + + if (!ltb->buff) { + dev_err(dev, "Couldn't alloc long term buffer\n"); + return -ENOMEM; + } + ltb->map_id = adapter->map_id; + adapter->map_id++; + send_request_map(adapter, ltb->addr, + ltb->size, ltb->map_id); + init_completion(&adapter->fw_done); + wait_for_completion(&adapter->fw_done); + return 0; +} + +static void free_long_term_buff(struct ibmvnic_adapter *adapter, + struct ibmvnic_long_term_buff *ltb) +{ + struct device *dev = &adapter->vdev->dev; + + dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); + send_request_unmap(adapter, ltb->map_id); +} + +static int alloc_rx_pool(struct ibmvnic_adapter *adapter, + struct ibmvnic_rx_pool *pool) +{ + struct device *dev = &adapter->vdev->dev; + int i; + + pool->free_map = kcalloc(pool->size, sizeof(int), GFP_KERNEL); + if (!pool->free_map) + return -ENOMEM; + + pool->rx_buff = kcalloc(pool->size, sizeof(struct ibmvnic_rx_buff), + GFP_KERNEL); + + if (!pool->rx_buff) { + dev_err(dev, "Couldn't alloc rx buffers\n"); + kfree(pool->free_map); + return -ENOMEM; + } + + if (alloc_long_term_buff(adapter, &pool->long_term_buff, + pool->size * pool->buff_size)) { + kfree(pool->free_map); + kfree(pool->rx_buff); + return -ENOMEM; + } + + for (i = 0; i < pool->size; ++i) + pool->free_map[i] = i; + + atomic_set(&pool->available, 0); + pool->next_alloc = 0; + pool->next_free = 0; + + return 0; +} + +static void replenish_rx_pool(struct ibmvnic_adapter *adapter, + struct ibmvnic_rx_pool *pool) +{ + int count = pool->size - atomic_read(&pool->available); + struct device *dev = &adapter->vdev->dev; + int buffers_added = 0; + unsigned long lpar_rc; + union sub_crq sub_crq; + struct sk_buff *skb; + unsigned int offset; + dma_addr_t dma_addr; + unsigned char *dst; + u64 *handle_array; + int shift = 0; + int index; + int i; + + handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf-> + off_rxadd_subcrqs)); + + for (i = 0; i < count; ++i) { + skb = alloc_skb(pool->buff_size, GFP_ATOMIC); + if (!skb) { + dev_err(dev, "Couldn't replenish rx buff\n"); + adapter->replenish_no_mem++; + break; + } + + index = pool->free_map[pool->next_free]; + + if (pool->rx_buff[index].skb) + dev_err(dev, "Inconsistent free_map!\n"); + + /* Copy the skb to the long term mapped DMA buffer */ + offset = index * pool->buff_size; + dst = pool->long_term_buff.buff + offset; + memset(dst, 0, pool->buff_size); + dma_addr = pool->long_term_buff.addr + offset; + pool->rx_buff[index].data = dst; + + pool->free_map[pool->next_free] = IBMVNIC_INVALID_MAP; + pool->rx_buff[index].dma = dma_addr; + pool->rx_buff[index].skb = skb; + pool->rx_buff[index].pool_index = pool->index; + pool->rx_buff[index].size = pool->buff_size; + + memset(&sub_crq, 0, sizeof(sub_crq)); + sub_crq.rx_add.first = IBMVNIC_CRQ_CMD; + sub_crq.rx_add.correlator = + cpu_to_be64((u64)&pool->rx_buff[index]); + sub_crq.rx_add.ioba = cpu_to_be32(dma_addr); + sub_crq.rx_add.map_id = pool->long_term_buff.map_id; + + /* The length field of the sCRQ is defined to be 24 bits so the + * buffer size needs to be left shifted by a byte before it is + * converted to big endian to prevent the last byte from being + * truncated. + */ +#ifdef __LITTLE_ENDIAN__ + shift = 8; +#endif + sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift); + + lpar_rc = send_subcrq(adapter, handle_array[pool->index], + &sub_crq); + if (lpar_rc != H_SUCCESS) + goto failure; + + buffers_added++; + adapter->replenish_add_buff_success++; + pool->next_free = (pool->next_free + 1) % pool->size; + } + atomic_add(buffers_added, &pool->available); + return; + +failure: + dev_info(dev, "replenish pools failure\n"); + pool->free_map[pool->next_free] = index; + pool->rx_buff[index].skb = NULL; + if (!dma_mapping_error(dev, dma_addr)) + dma_unmap_single(dev, dma_addr, pool->buff_size, + DMA_FROM_DEVICE); + + dev_kfree_skb_any(skb); + adapter->replenish_add_buff_failure++; + atomic_add(buffers_added, &pool->available); +} + +static void replenish_pools(struct ibmvnic_adapter *adapter) +{ + int i; + + if (adapter->migrated) + return; + + adapter->replenish_task_cycles++; + for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + i++) { + if (adapter->rx_pool[i].active) + replenish_rx_pool(adapter, &adapter->rx_pool[i]); + } +} + +static void free_rx_pool(struct ibmvnic_adapter *adapter, + struct ibmvnic_rx_pool *pool) +{ + int i; + + kfree(pool->free_map); + pool->free_map = NULL; + + if (!pool->rx_buff) + return; + + for (i = 0; i < pool->size; i++) { + if (pool->rx_buff[i].skb) { + dev_kfree_skb_any(pool->rx_buff[i].skb); + pool->rx_buff[i].skb = NULL; + } + } + kfree(pool->rx_buff); + pool->rx_buff = NULL; +} + +static int ibmvnic_open(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_tx_pool *tx_pool; + union ibmvnic_crq crq; + int rxadd_subcrqs; + u64 *size_array; + int tx_subcrqs; + int i, j; + + rxadd_subcrqs = + be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + tx_subcrqs = + be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf-> + off_rxadd_buff_size)); + adapter->map_id = 1; + adapter->napi = kcalloc(adapter->req_rx_queues, + sizeof(struct napi_struct), GFP_KERNEL); + if (!adapter->napi) + goto alloc_napi_failed; + for (i = 0; i < adapter->req_rx_queues; i++) { + netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll, + NAPI_POLL_WEIGHT); + napi_enable(&adapter->napi[i]); + } + adapter->rx_pool = + kcalloc(rxadd_subcrqs, sizeof(struct ibmvnic_rx_pool), GFP_KERNEL); + + if (!adapter->rx_pool) + goto rx_pool_arr_alloc_failed; + send_map_query(adapter); + for (i = 0; i < rxadd_subcrqs; i++) { + init_rx_pool(adapter, &adapter->rx_pool[i], + IBMVNIC_BUFFS_PER_POOL, i, + be64_to_cpu(size_array[i]), 1); + if (alloc_rx_pool(adapter, &adapter->rx_pool[i])) { + dev_err(dev, "Couldn't alloc rx pool\n"); + goto rx_pool_alloc_failed; + } + } + adapter->tx_pool = + kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); + + if (!adapter->tx_pool) + goto tx_pool_arr_alloc_failed; + for (i = 0; i < tx_subcrqs; i++) { + tx_pool = &adapter->tx_pool[i]; + tx_pool->tx_buff = + kcalloc(adapter->max_tx_entries_per_subcrq, + sizeof(struct ibmvnic_tx_buff), GFP_KERNEL); + if (!tx_pool->tx_buff) + goto tx_pool_alloc_failed; + + if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff, + adapter->max_tx_entries_per_subcrq * + adapter->req_mtu)) + goto tx_ltb_alloc_failed; + + tx_pool->free_map = + kcalloc(adapter->max_tx_entries_per_subcrq, + sizeof(int), GFP_KERNEL); + if (!tx_pool->free_map) + goto tx_fm_alloc_failed; + + for (j = 0; j < adapter->max_tx_entries_per_subcrq; j++) + tx_pool->free_map[j] = j; + + tx_pool->consumer_index = 0; + tx_pool->producer_index = 0; + } + adapter->bounce_buffer_size = + (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1; + adapter->bounce_buffer = kmalloc(adapter->bounce_buffer_size, + GFP_KERNEL); + if (!adapter->bounce_buffer) + goto bounce_alloc_failed; + + adapter->bounce_buffer_dma = dma_map_single(dev, adapter->bounce_buffer, + adapter->bounce_buffer_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) { + dev_err(dev, "Couldn't map tx bounce buffer\n"); + goto bounce_map_failed; + } + replenish_pools(adapter); + + /* We're ready to receive frames, enable the sub-crq interrupts and + * set the logical link state to up + */ + for (i = 0; i < adapter->req_rx_queues; i++) + enable_scrq_irq(adapter, adapter->rx_scrq[i]); + + for (i = 0; i < adapter->req_tx_queues; i++) + enable_scrq_irq(adapter, adapter->tx_scrq[i]); + + memset(&crq, 0, sizeof(crq)); + crq.logical_link_state.first = IBMVNIC_CRQ_CMD; + crq.logical_link_state.cmd = LOGICAL_LINK_STATE; + crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP; + ibmvnic_send_crq(adapter, &crq); + + netif_start_queue(netdev); + return 0; + +bounce_map_failed: + kfree(adapter->bounce_buffer); +bounce_alloc_failed: + i = tx_subcrqs - 1; + kfree(adapter->tx_pool[i].free_map); +tx_fm_alloc_failed: + free_long_term_buff(adapter, &adapter->tx_pool[i].long_term_buff); +tx_ltb_alloc_failed: + kfree(adapter->tx_pool[i].tx_buff); +tx_pool_alloc_failed: + for (j = 0; j < i; j++) { + kfree(adapter->tx_pool[j].tx_buff); + free_long_term_buff(adapter, + &adapter->tx_pool[j].long_term_buff); + kfree(adapter->tx_pool[j].free_map); + } + kfree(adapter->tx_pool); + adapter->tx_pool = NULL; +tx_pool_arr_alloc_failed: + i = rxadd_subcrqs; +rx_pool_alloc_failed: + for (j = 0; j < i; j++) { + free_rx_pool(adapter, &adapter->rx_pool[j]); + free_long_term_buff(adapter, + &adapter->rx_pool[j].long_term_buff); + } + kfree(adapter->rx_pool); + adapter->rx_pool = NULL; +rx_pool_arr_alloc_failed: + for (i = 0; i < adapter->req_rx_queues; i++) + napi_enable(&adapter->napi[i]); +alloc_napi_failed: + return -ENOMEM; +} + +static int ibmvnic_close(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + struct device *dev = &adapter->vdev->dev; + union ibmvnic_crq crq; + int i; + + adapter->closing = true; + + for (i = 0; i < adapter->req_rx_queues; i++) + napi_disable(&adapter->napi[i]); + + netif_stop_queue(netdev); + + if (adapter->bounce_buffer) { + if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) { + dma_unmap_single(&adapter->vdev->dev, + adapter->bounce_buffer_dma, + adapter->bounce_buffer_size, + DMA_BIDIRECTIONAL); + adapter->bounce_buffer_dma = DMA_ERROR_CODE; + } + kfree(adapter->bounce_buffer); + adapter->bounce_buffer = NULL; + } + + memset(&crq, 0, sizeof(crq)); + crq.logical_link_state.first = IBMVNIC_CRQ_CMD; + crq.logical_link_state.cmd = LOGICAL_LINK_STATE; + crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_DN; + ibmvnic_send_crq(adapter, &crq); + + for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + i++) { + kfree(adapter->tx_pool[i].tx_buff); + free_long_term_buff(adapter, + &adapter->tx_pool[i].long_term_buff); + kfree(adapter->tx_pool[i].free_map); + } + kfree(adapter->tx_pool); + adapter->tx_pool = NULL; + + for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + i++) { + free_rx_pool(adapter, &adapter->rx_pool[i]); + free_long_term_buff(adapter, + &adapter->rx_pool[i].long_term_buff); + } + kfree(adapter->rx_pool); + adapter->rx_pool = NULL; + + adapter->closing = false; + + return 0; +} + +static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int queue_num = skb_get_queue_mapping(skb); + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_tx_buff *tx_buff = NULL; + struct ibmvnic_tx_pool *tx_pool; + unsigned int tx_send_failed = 0; + unsigned int tx_map_failed = 0; + unsigned int tx_dropped = 0; + unsigned int tx_packets = 0; + unsigned int tx_bytes = 0; + dma_addr_t data_dma_addr; + struct netdev_queue *txq; + bool used_bounce = false; + unsigned long lpar_rc; + union sub_crq tx_crq; + unsigned int offset; + unsigned char *dst; + u64 *handle_array; + int index = 0; + int ret = 0; + + tx_pool = &adapter->tx_pool[queue_num]; + txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb)); + handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf-> + off_txsubm_subcrqs)); + if (adapter->migrated) { + tx_send_failed++; + tx_dropped++; + ret = NETDEV_TX_BUSY; + goto out; + } + + index = tx_pool->free_map[tx_pool->consumer_index]; + offset = index * adapter->req_mtu; + dst = tx_pool->long_term_buff.buff + offset; + memset(dst, 0, adapter->req_mtu); + skb_copy_from_linear_data(skb, dst, skb->len); + data_dma_addr = tx_pool->long_term_buff.addr + offset; + + tx_pool->consumer_index = + (tx_pool->consumer_index + 1) % + adapter->max_tx_entries_per_subcrq; + + tx_buff = &tx_pool->tx_buff[index]; + tx_buff->skb = skb; + tx_buff->data_dma[0] = data_dma_addr; + tx_buff->data_len[0] = skb->len; + tx_buff->index = index; + tx_buff->pool_index = queue_num; + tx_buff->last_frag = true; + tx_buff->used_bounce = used_bounce; + + memset(&tx_crq, 0, sizeof(tx_crq)); + tx_crq.v1.first = IBMVNIC_CRQ_CMD; + tx_crq.v1.type = IBMVNIC_TX_DESC; + tx_crq.v1.n_crq_elem = 1; + tx_crq.v1.n_sge = 1; + tx_crq.v1.flags1 = IBMVNIC_TX_COMP_NEEDED; + tx_crq.v1.correlator = cpu_to_be32(index); + tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id); + tx_crq.v1.sge_len = cpu_to_be32(skb->len); + tx_crq.v1.ioba = cpu_to_be64(data_dma_addr); + + if (adapter->vlan_header_insertion) { + tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT; + tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci); + } + + if (skb->protocol == htons(ETH_P_IP)) { + if (ip_hdr(skb)->version == 4) + tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_IPV4; + else if (ip_hdr(skb)->version == 6) + tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_IPV6; + + if (ip_hdr(skb)->protocol == IPPROTO_TCP) + tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_TCP; + else if (ip_hdr(skb)->protocol != IPPROTO_TCP) + tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_UDP; + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) + tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD; + + lpar_rc = send_subcrq(adapter, handle_array[0], &tx_crq); + + if (lpar_rc != H_SUCCESS) { + dev_err(dev, "tx failed with code %ld\n", lpar_rc); + + if (tx_pool->consumer_index == 0) + tx_pool->consumer_index = + adapter->max_tx_entries_per_subcrq - 1; + else + tx_pool->consumer_index--; + + tx_send_failed++; + tx_dropped++; + ret = NETDEV_TX_BUSY; + goto out; + } + tx_packets++; + tx_bytes += skb->len; + txq->trans_start = jiffies; + ret = NETDEV_TX_OK; + +out: + netdev->stats.tx_dropped += tx_dropped; + netdev->stats.tx_bytes += tx_bytes; + netdev->stats.tx_packets += tx_packets; + adapter->tx_send_failed += tx_send_failed; + adapter->tx_map_failed += tx_map_failed; + + return ret; +} + +static void ibmvnic_set_multi(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + struct netdev_hw_addr *ha; + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.request_capability.first = IBMVNIC_CRQ_CMD; + crq.request_capability.cmd = REQUEST_CAPABILITY; + + if (netdev->flags & IFF_PROMISC) { + if (!adapter->promisc_supported) + return; + } else { + if (netdev->flags & IFF_ALLMULTI) { + /* Accept all multicast */ + memset(&crq, 0, sizeof(crq)); + crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD; + crq.multicast_ctrl.cmd = MULTICAST_CTRL; + crq.multicast_ctrl.flags = IBMVNIC_ENABLE_ALL; + ibmvnic_send_crq(adapter, &crq); + } else if (netdev_mc_empty(netdev)) { + /* Reject all multicast */ + memset(&crq, 0, sizeof(crq)); + crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD; + crq.multicast_ctrl.cmd = MULTICAST_CTRL; + crq.multicast_ctrl.flags = IBMVNIC_DISABLE_ALL; + ibmvnic_send_crq(adapter, &crq); + } else { + /* Accept one or more multicast(s) */ + netdev_for_each_mc_addr(ha, netdev) { + memset(&crq, 0, sizeof(crq)); + crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD; + crq.multicast_ctrl.cmd = MULTICAST_CTRL; + crq.multicast_ctrl.flags = IBMVNIC_ENABLE_MC; + ether_addr_copy(&crq.multicast_ctrl.mac_addr[0], + ha->addr); + ibmvnic_send_crq(adapter, &crq); + } + } + } +} + +static int ibmvnic_set_mac(struct net_device *netdev, void *p) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + struct sockaddr *addr = p; + union ibmvnic_crq crq; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + memset(&crq, 0, sizeof(crq)); + crq.change_mac_addr.first = IBMVNIC_CRQ_CMD; + crq.change_mac_addr.cmd = CHANGE_MAC_ADDR; + ether_addr_copy(&crq.change_mac_addr.mac_addr[0], addr->sa_data); + ibmvnic_send_crq(adapter, &crq); + /* netdev->dev_addr is changed in handle_change_mac_rsp function */ + return 0; +} + +static int ibmvnic_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + if (new_mtu > adapter->req_mtu || new_mtu < adapter->min_mtu) + return -EINVAL; + + netdev->mtu = new_mtu; + return 0; +} + +static void ibmvnic_tx_timeout(struct net_device *dev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(dev); + int rc; + + /* Adapter timed out, resetting it */ + release_sub_crqs(adapter); + rc = ibmvnic_reset_crq(adapter); + if (rc) + dev_err(&adapter->vdev->dev, "Adapter timeout, reset failed\n"); + else + ibmvnic_send_crq_init(adapter); +} + +static void remove_buff_from_pool(struct ibmvnic_adapter *adapter, + struct ibmvnic_rx_buff *rx_buff) +{ + struct ibmvnic_rx_pool *pool = &adapter->rx_pool[rx_buff->pool_index]; + + rx_buff->skb = NULL; + + pool->free_map[pool->next_alloc] = (int)(rx_buff - pool->rx_buff); + pool->next_alloc = (pool->next_alloc + 1) % pool->size; + + atomic_dec(&pool->available); +} + +static int ibmvnic_poll(struct napi_struct *napi, int budget) +{ + struct net_device *netdev = napi->dev; + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int scrq_num = (int)(napi - adapter->napi); + int frames_processed = 0; +restart_poll: + while (frames_processed < budget) { + struct sk_buff *skb; + struct ibmvnic_rx_buff *rx_buff; + union sub_crq *next; + u32 length; + u16 offset; + u8 flags = 0; + + if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num])) + break; + next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]); + rx_buff = + (struct ibmvnic_rx_buff *)be64_to_cpu(next-> + rx_comp.correlator); + /* do error checking */ + if (next->rx_comp.rc) { + netdev_err(netdev, "rx error %x\n", next->rx_comp.rc); + /* free the entry */ + next->rx_comp.first = 0; + remove_buff_from_pool(adapter, rx_buff); + break; + } + + length = be32_to_cpu(next->rx_comp.len); + offset = be16_to_cpu(next->rx_comp.off_frame_data); + flags = next->rx_comp.flags; + skb = rx_buff->skb; + skb_copy_to_linear_data(skb, rx_buff->data + offset, + length); + skb->vlan_tci = be16_to_cpu(next->rx_comp.vlan_tci); + /* free the entry */ + next->rx_comp.first = 0; + remove_buff_from_pool(adapter, rx_buff); + + skb_put(skb, length); + skb->protocol = eth_type_trans(skb, netdev); + + if (flags & IBMVNIC_IP_CHKSUM_GOOD && + flags & IBMVNIC_TCP_UDP_CHKSUM_GOOD) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + + length = skb->len; + napi_gro_receive(napi, skb); /* send it up */ + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += length; + frames_processed++; + } + replenish_pools(adapter); + + if (frames_processed < budget) { + enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]); + napi_complete(napi); + if (pending_scrq(adapter, adapter->rx_scrq[scrq_num]) && + napi_reschedule(napi)) { + disable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]); + goto restart_poll; + } + } + return frames_processed; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void ibmvnic_netpoll_controller(struct net_device *dev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(dev); + int i; + + replenish_pools(netdev_priv(dev)); + for (i = 0; i < adapter->req_rx_queues; i++) + ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq, + adapter->rx_scrq[i]); +} +#endif + +static const struct net_device_ops ibmvnic_netdev_ops = { + .ndo_open = ibmvnic_open, + .ndo_stop = ibmvnic_close, + .ndo_start_xmit = ibmvnic_xmit, + .ndo_set_rx_mode = ibmvnic_set_multi, + .ndo_set_mac_address = ibmvnic_set_mac, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = ibmvnic_change_mtu, + .ndo_tx_timeout = ibmvnic_tx_timeout, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = ibmvnic_netpoll_controller, +#endif +}; + +/* ethtool functions */ + +static int ibmvnic_get_settings(struct net_device *netdev, + struct ethtool_cmd *cmd) +{ + cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | + SUPPORTED_FIBRE); + cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | + ADVERTISED_FIBRE); + ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->duplex = DUPLEX_FULL; + cmd->port = PORT_FIBRE; + cmd->phy_address = 0; + cmd->transceiver = XCVR_INTERNAL; + cmd->autoneg = AUTONEG_ENABLE; + cmd->maxtxpkt = 0; + cmd->maxrxpkt = 1; + return 0; +} + +static void ibmvnic_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, ibmvnic_driver_name, sizeof(info->driver)); + strlcpy(info->version, IBMVNIC_DRIVER_VERSION, sizeof(info->version)); +} + +static u32 ibmvnic_get_msglevel(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + return adapter->msg_enable; +} + +static void ibmvnic_set_msglevel(struct net_device *netdev, u32 data) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + adapter->msg_enable = data; +} + +static u32 ibmvnic_get_link(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + /* Don't need to send a query because we request a logical link up at + * init and then we wait for link state indications + */ + return adapter->logical_link_state; +} + +static void ibmvnic_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + ring->rx_max_pending = 0; + ring->tx_max_pending = 0; + ring->rx_mini_max_pending = 0; + ring->rx_jumbo_max_pending = 0; + ring->rx_pending = 0; + ring->tx_pending = 0; + ring->rx_mini_pending = 0; + ring->rx_jumbo_pending = 0; +} + +static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + int i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN) + memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); +} + +static int ibmvnic_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(ibmvnic_stats); + default: + return -EOPNOTSUPP; + } +} + +static void ibmvnic_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct ibmvnic_adapter *adapter = netdev_priv(dev); + union ibmvnic_crq crq; + int i; + + memset(&crq, 0, sizeof(crq)); + crq.request_statistics.first = IBMVNIC_CRQ_CMD; + crq.request_statistics.cmd = REQUEST_STATISTICS; + crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token); + crq.request_statistics.len = + cpu_to_be32(sizeof(struct ibmvnic_statistics)); + ibmvnic_send_crq(adapter, &crq); + + /* Wait for data to be written */ + init_completion(&adapter->stats_done); + wait_for_completion(&adapter->stats_done); + + for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++) + data[i] = IBMVNIC_GET_STAT(adapter, ibmvnic_stats[i].offset); +} + +static const struct ethtool_ops ibmvnic_ethtool_ops = { + .get_settings = ibmvnic_get_settings, + .get_drvinfo = ibmvnic_get_drvinfo, + .get_msglevel = ibmvnic_get_msglevel, + .set_msglevel = ibmvnic_set_msglevel, + .get_link = ibmvnic_get_link, + .get_ringparam = ibmvnic_get_ringparam, + .get_strings = ibmvnic_get_strings, + .get_sset_count = ibmvnic_get_sset_count, + .get_ethtool_stats = ibmvnic_get_ethtool_stats, +}; + +/* Routines for managing CRQs/sCRQs */ + +static void release_sub_crq_queue(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *scrq) +{ + struct device *dev = &adapter->vdev->dev; + long rc; + + netdev_dbg(adapter->netdev, "Releasing sub-CRQ\n"); + + /* Close the sub-crqs */ + do { + rc = plpar_hcall_norets(H_FREE_SUB_CRQ, + adapter->vdev->unit_address, + scrq->crq_num); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); + + dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, + DMA_BIDIRECTIONAL); + free_pages((unsigned long)scrq->msgs, 2); + kfree(scrq); +} + +static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter + *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_sub_crq_queue *scrq; + int rc; + + scrq = kmalloc(sizeof(*scrq), GFP_ATOMIC); + if (!scrq) + return NULL; + + scrq->msgs = (union sub_crq *)__get_free_pages(GFP_KERNEL, 2); + memset(scrq->msgs, 0, 4 * PAGE_SIZE); + if (!scrq->msgs) { + dev_warn(dev, "Couldn't allocate crq queue messages page\n"); + goto zero_page_failed; + } + + scrq->msg_token = dma_map_single(dev, scrq->msgs, 4 * PAGE_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, scrq->msg_token)) { + dev_warn(dev, "Couldn't map crq queue messages page\n"); + goto map_failed; + } + + rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token, + 4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq); + + if (rc == H_RESOURCE) + rc = ibmvnic_reset_crq(adapter); + + if (rc == H_CLOSED) { + dev_warn(dev, "Partner adapter not ready, waiting.\n"); + } else if (rc) { + dev_warn(dev, "Error %d registering sub-crq\n", rc); + goto reg_failed; + } + + scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); + if (scrq->irq == NO_IRQ) { + dev_err(dev, "Error mapping irq\n"); + goto map_irq_failed; + } + + scrq->adapter = adapter; + scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs); + scrq->cur = 0; + scrq->rx_skb_top = NULL; + spin_lock_init(&scrq->lock); + + netdev_dbg(adapter->netdev, + "sub-crq initialized, num %lx, hw_irq=%lx, irq=%x\n", + scrq->crq_num, scrq->hw_irq, scrq->irq); + + return scrq; + +map_irq_failed: + do { + rc = plpar_hcall_norets(H_FREE_SUB_CRQ, + adapter->vdev->unit_address, + scrq->crq_num); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); +reg_failed: + dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, + DMA_BIDIRECTIONAL); +map_failed: + free_pages((unsigned long)scrq->msgs, 2); +zero_page_failed: + kfree(scrq); + + return NULL; +} + +static void release_sub_crqs(struct ibmvnic_adapter *adapter) +{ + int i; + + if (adapter->tx_scrq) { + for (i = 0; i < adapter->req_tx_queues; i++) + if (adapter->tx_scrq[i]) { + free_irq(adapter->tx_scrq[i]->irq, + adapter->tx_scrq[i]); + release_sub_crq_queue(adapter, + adapter->tx_scrq[i]); + } + adapter->tx_scrq = NULL; + } + + if (adapter->rx_scrq) { + for (i = 0; i < adapter->req_rx_queues; i++) + if (adapter->rx_scrq[i]) { + free_irq(adapter->rx_scrq[i]->irq, + adapter->rx_scrq[i]); + release_sub_crq_queue(adapter, + adapter->rx_scrq[i]); + } + adapter->rx_scrq = NULL; + } + + adapter->requested_caps = 0; +} + +static int disable_scrq_irq(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *scrq) +{ + struct device *dev = &adapter->vdev->dev; + unsigned long rc; + + rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, + H_DISABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0); + if (rc) + dev_err(dev, "Couldn't disable scrq irq 0x%lx. rc=%ld\n", + scrq->hw_irq, rc); + return rc; +} + +static int enable_scrq_irq(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *scrq) +{ + struct device *dev = &adapter->vdev->dev; + unsigned long rc; + + if (scrq->hw_irq > 0x100000000ULL) { + dev_err(dev, "bad hw_irq = %lx\n", scrq->hw_irq); + return 1; + } + + rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, + H_ENABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0); + if (rc) + dev_err(dev, "Couldn't enable scrq irq 0x%lx. rc=%ld\n", + scrq->hw_irq, rc); + return rc; +} + +static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *scrq) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_tx_buff *txbuff; + union sub_crq *next; + int index; + int i, j; + +restart_loop: + while (pending_scrq(adapter, scrq)) { + unsigned int pool = scrq->pool_index; + + next = ibmvnic_next_scrq(adapter, scrq); + for (i = 0; i < next->tx_comp.num_comps; i++) { + if (next->tx_comp.rcs[i]) { + dev_err(dev, "tx error %x\n", + next->tx_comp.rcs[i]); + continue; + } + index = be32_to_cpu(next->tx_comp.correlators[i]); + txbuff = &adapter->tx_pool[pool].tx_buff[index]; + + for (j = 0; j < IBMVNIC_MAX_FRAGS_PER_CRQ; j++) { + if (!txbuff->data_dma[j]) + continue; + + txbuff->data_dma[j] = 0; + txbuff->used_bounce = false; + } + + if (txbuff->last_frag) + dev_kfree_skb_any(txbuff->skb); + + adapter->tx_pool[pool].free_map[adapter->tx_pool[pool]. + producer_index] = index; + adapter->tx_pool[pool].producer_index = + (adapter->tx_pool[pool].producer_index + 1) % + adapter->max_tx_entries_per_subcrq; + } + /* remove tx_comp scrq*/ + next->tx_comp.first = 0; + } + + enable_scrq_irq(adapter, scrq); + + if (pending_scrq(adapter, scrq)) { + disable_scrq_irq(adapter, scrq); + goto restart_loop; + } + + return 0; +} + +static irqreturn_t ibmvnic_interrupt_tx(int irq, void *instance) +{ + struct ibmvnic_sub_crq_queue *scrq = instance; + struct ibmvnic_adapter *adapter = scrq->adapter; + + disable_scrq_irq(adapter, scrq); + ibmvnic_complete_tx(adapter, scrq); + + return IRQ_HANDLED; +} + +static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance) +{ + struct ibmvnic_sub_crq_queue *scrq = instance; + struct ibmvnic_adapter *adapter = scrq->adapter; + + if (napi_schedule_prep(&adapter->napi[scrq->scrq_num])) { + disable_scrq_irq(adapter, scrq); + __napi_schedule(&adapter->napi[scrq->scrq_num]); + } + + return IRQ_HANDLED; +} + +static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_sub_crq_queue **allqueues; + int registered_queues = 0; + union ibmvnic_crq crq; + int total_queues; + int more = 0; + int i, j; + int rc; + + if (!retry) { + /* Sub-CRQ entries are 32 byte long */ + int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4); + + if (adapter->min_tx_entries_per_subcrq > entries_page || + adapter->min_rx_add_entries_per_subcrq > entries_page) { + dev_err(dev, "Fatal, invalid entries per sub-crq\n"); + goto allqueues_failed; + } + + /* Get the minimum between the queried max and the entries + * that fit in our PAGE_SIZE + */ + adapter->req_tx_entries_per_subcrq = + adapter->max_tx_entries_per_subcrq > entries_page ? + entries_page : adapter->max_tx_entries_per_subcrq; + adapter->req_rx_add_entries_per_subcrq = + adapter->max_rx_add_entries_per_subcrq > entries_page ? + entries_page : adapter->max_rx_add_entries_per_subcrq; + + /* Choosing the maximum number of queues supported by firmware*/ + adapter->req_tx_queues = adapter->min_tx_queues; + adapter->req_rx_queues = adapter->min_rx_queues; + adapter->req_rx_add_queues = adapter->min_rx_add_queues; + + adapter->req_mtu = adapter->max_mtu; + } + + total_queues = adapter->req_tx_queues + adapter->req_rx_queues; + + allqueues = kcalloc(total_queues, sizeof(*allqueues), GFP_ATOMIC); + if (!allqueues) + goto allqueues_failed; + + for (i = 0; i < total_queues; i++) { + allqueues[i] = init_sub_crq_queue(adapter); + if (!allqueues[i]) { + dev_warn(dev, "Couldn't allocate all sub-crqs\n"); + break; + } + registered_queues++; + } + + /* Make sure we were able to register the minimum number of queues */ + if (registered_queues < + adapter->min_tx_queues + adapter->min_rx_queues) { + dev_err(dev, "Fatal: Couldn't init min number of sub-crqs\n"); + goto tx_failed; + } + + /* Distribute the failed allocated queues*/ + for (i = 0; i < total_queues - registered_queues + more ; i++) { + netdev_dbg(adapter->netdev, "Reducing number of queues\n"); + switch (i % 3) { + case 0: + if (adapter->req_rx_queues > adapter->min_rx_queues) + adapter->req_rx_queues--; + else + more++; + break; + case 1: + if (adapter->req_tx_queues > adapter->min_tx_queues) + adapter->req_tx_queues--; + else + more++; + break; + } + } + + adapter->tx_scrq = kcalloc(adapter->req_tx_queues, + sizeof(*adapter->tx_scrq), GFP_ATOMIC); + if (!adapter->tx_scrq) + goto tx_failed; + + for (i = 0; i < adapter->req_tx_queues; i++) { + adapter->tx_scrq[i] = allqueues[i]; + adapter->tx_scrq[i]->pool_index = i; + rc = request_irq(adapter->tx_scrq[i]->irq, ibmvnic_interrupt_tx, + 0, "ibmvnic_tx", adapter->tx_scrq[i]); + if (rc) { + dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", + adapter->tx_scrq[i]->irq, rc); + goto req_tx_irq_failed; + } + } + + adapter->rx_scrq = kcalloc(adapter->req_rx_queues, + sizeof(*adapter->rx_scrq), GFP_ATOMIC); + if (!adapter->rx_scrq) + goto rx_failed; + + for (i = 0; i < adapter->req_rx_queues; i++) { + adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues]; + adapter->rx_scrq[i]->scrq_num = i; + rc = request_irq(adapter->rx_scrq[i]->irq, ibmvnic_interrupt_rx, + 0, "ibmvnic_rx", adapter->rx_scrq[i]); + if (rc) { + dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n", + adapter->rx_scrq[i]->irq, rc); + goto req_rx_irq_failed; + } + } + + memset(&crq, 0, sizeof(crq)); + crq.request_capability.first = IBMVNIC_CRQ_CMD; + crq.request_capability.cmd = REQUEST_CAPABILITY; + + crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); + crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues); + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); + crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues); + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); + crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues); + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = + cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); + crq.request_capability.number = + cpu_to_be32(adapter->req_tx_entries_per_subcrq); + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = + cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); + crq.request_capability.number = + cpu_to_be32(adapter->req_rx_add_entries_per_subcrq); + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = cpu_to_be16(REQ_MTU); + crq.request_capability.number = cpu_to_be32(adapter->req_mtu); + ibmvnic_send_crq(adapter, &crq); + + if (adapter->netdev->flags & IFF_PROMISC) { + if (adapter->promisc_supported) { + crq.request_capability.capability = + cpu_to_be16(PROMISC_REQUESTED); + crq.request_capability.number = cpu_to_be32(1); + ibmvnic_send_crq(adapter, &crq); + } + } else { + crq.request_capability.capability = + cpu_to_be16(PROMISC_REQUESTED); + crq.request_capability.number = cpu_to_be32(0); + ibmvnic_send_crq(adapter, &crq); + } + + kfree(allqueues); + + return; + +req_rx_irq_failed: + for (j = 0; j < i; j++) + free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]); + i = adapter->req_tx_queues; +req_tx_irq_failed: + for (j = 0; j < i; j++) + free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); + kfree(adapter->rx_scrq); + adapter->rx_scrq = NULL; +rx_failed: + kfree(adapter->tx_scrq); + adapter->tx_scrq = NULL; +tx_failed: + for (i = 0; i < registered_queues; i++) + release_sub_crq_queue(adapter, allqueues[i]); + kfree(allqueues); +allqueues_failed: + ibmvnic_remove(adapter->vdev); +} + +static int pending_scrq(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *scrq) +{ + union sub_crq *entry = &scrq->msgs[scrq->cur]; + + if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP || adapter->closing) + return 1; + else + return 0; +} + +static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *scrq) +{ + union sub_crq *entry; + unsigned long flags; + + spin_lock_irqsave(&scrq->lock, flags); + entry = &scrq->msgs[scrq->cur]; + if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP) { + if (++scrq->cur == scrq->size) + scrq->cur = 0; + } else { + entry = NULL; + } + spin_unlock_irqrestore(&scrq->lock, flags); + + return entry; +} + +static union ibmvnic_crq *ibmvnic_next_crq(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_crq_queue *queue = &adapter->crq; + union ibmvnic_crq *crq; + + crq = &queue->msgs[queue->cur]; + if (crq->generic.first & IBMVNIC_CRQ_CMD_RSP) { + if (++queue->cur == queue->size) + queue->cur = 0; + } else { + crq = NULL; + } + + return crq; +} + +static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle, + union sub_crq *sub_crq) +{ + unsigned int ua = adapter->vdev->unit_address; + struct device *dev = &adapter->vdev->dev; + u64 *u64_crq = (u64 *)sub_crq; + int rc; + + netdev_dbg(adapter->netdev, + "Sending sCRQ %016lx: %016lx %016lx %016lx %016lx\n", + (unsigned long int)cpu_to_be64(remote_handle), + (unsigned long int)cpu_to_be64(u64_crq[0]), + (unsigned long int)cpu_to_be64(u64_crq[1]), + (unsigned long int)cpu_to_be64(u64_crq[2]), + (unsigned long int)cpu_to_be64(u64_crq[3])); + + /* Make sure the hypervisor sees the complete request */ + mb(); + + rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua, + cpu_to_be64(remote_handle), + cpu_to_be64(u64_crq[0]), + cpu_to_be64(u64_crq[1]), + cpu_to_be64(u64_crq[2]), + cpu_to_be64(u64_crq[3])); + + if (rc) { + if (rc == H_CLOSED) + dev_warn(dev, "CRQ Queue closed\n"); + dev_err(dev, "Send error (rc=%d)\n", rc); + } + + return rc; +} + +static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter, + union ibmvnic_crq *crq) +{ + unsigned int ua = adapter->vdev->unit_address; + struct device *dev = &adapter->vdev->dev; + u64 *u64_crq = (u64 *)crq; + int rc; + + netdev_dbg(adapter->netdev, "Sending CRQ: %016lx %016lx\n", + (unsigned long int)cpu_to_be64(u64_crq[0]), + (unsigned long int)cpu_to_be64(u64_crq[1])); + + /* Make sure the hypervisor sees the complete request */ + mb(); + + rc = plpar_hcall_norets(H_SEND_CRQ, ua, + cpu_to_be64(u64_crq[0]), + cpu_to_be64(u64_crq[1])); + + if (rc) { + if (rc == H_CLOSED) + dev_warn(dev, "CRQ Queue closed\n"); + dev_warn(dev, "Send error (rc=%d)\n", rc); + } + + return rc; +} + +static int ibmvnic_send_crq_init(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.generic.first = IBMVNIC_CRQ_INIT_CMD; + crq.generic.cmd = IBMVNIC_CRQ_INIT; + netdev_dbg(adapter->netdev, "Sending CRQ init\n"); + + return ibmvnic_send_crq(adapter, &crq); +} + +static int ibmvnic_send_crq_init_complete(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.generic.first = IBMVNIC_CRQ_INIT_CMD; + crq.generic.cmd = IBMVNIC_CRQ_INIT_COMPLETE; + netdev_dbg(adapter->netdev, "Sending CRQ init complete\n"); + + return ibmvnic_send_crq(adapter, &crq); +} + +static int send_version_xchg(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.version_exchange.first = IBMVNIC_CRQ_CMD; + crq.version_exchange.cmd = VERSION_EXCHANGE; + crq.version_exchange.version = cpu_to_be16(ibmvnic_version); + + return ibmvnic_send_crq(adapter, &crq); +} + +static void send_login(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_login_rsp_buffer *login_rsp_buffer; + struct ibmvnic_login_buffer *login_buffer; + struct ibmvnic_inflight_cmd *inflight_cmd; + struct device *dev = &adapter->vdev->dev; + dma_addr_t rsp_buffer_token; + dma_addr_t buffer_token; + size_t rsp_buffer_size; + union ibmvnic_crq crq; + unsigned long flags; + size_t buffer_size; + __be64 *tx_list_p; + __be64 *rx_list_p; + int i; + + buffer_size = + sizeof(struct ibmvnic_login_buffer) + + sizeof(u64) * (adapter->req_tx_queues + adapter->req_rx_queues); + + login_buffer = kmalloc(buffer_size, GFP_ATOMIC); + if (!login_buffer) + goto buf_alloc_failed; + + buffer_token = dma_map_single(dev, login_buffer, buffer_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, buffer_token)) { + dev_err(dev, "Couldn't map login buffer\n"); + goto buf_map_failed; + } + + rsp_buffer_size = + sizeof(struct ibmvnic_login_rsp_buffer) + + sizeof(u64) * (adapter->req_tx_queues + + adapter->req_rx_queues * + adapter->req_rx_add_queues + adapter-> + req_rx_add_queues) + + sizeof(u8) * (IBMVNIC_TX_DESC_VERSIONS); + + login_rsp_buffer = kmalloc(rsp_buffer_size, GFP_ATOMIC); + if (!login_rsp_buffer) + goto buf_rsp_alloc_failed; + + rsp_buffer_token = dma_map_single(dev, login_rsp_buffer, + rsp_buffer_size, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, rsp_buffer_token)) { + dev_err(dev, "Couldn't map login rsp buffer\n"); + goto buf_rsp_map_failed; + } + inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC); + if (!inflight_cmd) { + dev_err(dev, "Couldn't allocate inflight_cmd\n"); + goto inflight_alloc_failed; + } + adapter->login_buf = login_buffer; + adapter->login_buf_token = buffer_token; + adapter->login_buf_sz = buffer_size; + adapter->login_rsp_buf = login_rsp_buffer; + adapter->login_rsp_buf_token = rsp_buffer_token; + adapter->login_rsp_buf_sz = rsp_buffer_size; + + login_buffer->len = cpu_to_be32(buffer_size); + login_buffer->version = cpu_to_be32(INITIAL_VERSION_LB); + login_buffer->num_txcomp_subcrqs = cpu_to_be32(adapter->req_tx_queues); + login_buffer->off_txcomp_subcrqs = + cpu_to_be32(sizeof(struct ibmvnic_login_buffer)); + login_buffer->num_rxcomp_subcrqs = cpu_to_be32(adapter->req_rx_queues); + login_buffer->off_rxcomp_subcrqs = + cpu_to_be32(sizeof(struct ibmvnic_login_buffer) + + sizeof(u64) * adapter->req_tx_queues); + login_buffer->login_rsp_ioba = cpu_to_be32(rsp_buffer_token); + login_buffer->login_rsp_len = cpu_to_be32(rsp_buffer_size); + + tx_list_p = (__be64 *)((char *)login_buffer + + sizeof(struct ibmvnic_login_buffer)); + rx_list_p = (__be64 *)((char *)login_buffer + + sizeof(struct ibmvnic_login_buffer) + + sizeof(u64) * adapter->req_tx_queues); + + for (i = 0; i < adapter->req_tx_queues; i++) { + if (adapter->tx_scrq[i]) { + tx_list_p[i] = cpu_to_be64(adapter->tx_scrq[i]-> + crq_num); + } + } + + for (i = 0; i < adapter->req_rx_queues; i++) { + if (adapter->rx_scrq[i]) { + rx_list_p[i] = cpu_to_be64(adapter->rx_scrq[i]-> + crq_num); + } + } + + netdev_dbg(adapter->netdev, "Login Buffer:\n"); + for (i = 0; i < (adapter->login_buf_sz - 1) / 8 + 1; i++) { + netdev_dbg(adapter->netdev, "%016lx\n", + ((unsigned long int *)(adapter->login_buf))[i]); + } + + memset(&crq, 0, sizeof(crq)); + crq.login.first = IBMVNIC_CRQ_CMD; + crq.login.cmd = LOGIN; + crq.login.ioba = cpu_to_be32(buffer_token); + crq.login.len = cpu_to_be32(buffer_size); + + memcpy(&inflight_cmd->crq, &crq, sizeof(crq)); + + spin_lock_irqsave(&adapter->inflight_lock, flags); + list_add_tail(&inflight_cmd->list, &adapter->inflight); + spin_unlock_irqrestore(&adapter->inflight_lock, flags); + + ibmvnic_send_crq(adapter, &crq); + + return; + +inflight_alloc_failed: + dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, + DMA_FROM_DEVICE); +buf_rsp_map_failed: + kfree(login_rsp_buffer); +buf_rsp_alloc_failed: + dma_unmap_single(dev, buffer_token, buffer_size, DMA_TO_DEVICE); +buf_map_failed: + kfree(login_buffer); +buf_alloc_failed: + return; +} + +static void send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr, + u32 len, u8 map_id) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.request_map.first = IBMVNIC_CRQ_CMD; + crq.request_map.cmd = REQUEST_MAP; + crq.request_map.map_id = map_id; + crq.request_map.ioba = cpu_to_be32(addr); + crq.request_map.len = cpu_to_be32(len); + ibmvnic_send_crq(adapter, &crq); +} + +static void send_request_unmap(struct ibmvnic_adapter *adapter, u8 map_id) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.request_unmap.first = IBMVNIC_CRQ_CMD; + crq.request_unmap.cmd = REQUEST_UNMAP; + crq.request_unmap.map_id = map_id; + ibmvnic_send_crq(adapter, &crq); +} + +static void send_map_query(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.query_map.first = IBMVNIC_CRQ_CMD; + crq.query_map.cmd = QUERY_MAP; + ibmvnic_send_crq(adapter, &crq); +} + +/* Send a series of CRQs requesting various capabilities of the VNIC server */ +static void send_cap_queries(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + atomic_set(&adapter->running_cap_queries, 0); + memset(&crq, 0, sizeof(crq)); + crq.query_capability.first = IBMVNIC_CRQ_CMD; + crq.query_capability.cmd = QUERY_CAPABILITY; + + crq.query_capability.capability = cpu_to_be16(MIN_TX_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MIN_RX_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MAX_TX_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MAX_RX_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(MIN_TX_ENTRIES_PER_SUBCRQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(MIN_RX_ADD_ENTRIES_PER_SUBCRQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(MAX_TX_ENTRIES_PER_SUBCRQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(MAX_RX_ADD_ENTRIES_PER_SUBCRQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(TCP_IP_OFFLOAD); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(PROMISC_SUPPORTED); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MIN_MTU); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MAX_MTU); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MAX_MULTICAST_FILTERS); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(VLAN_HEADER_INSERTION); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(MAX_TX_SG_ENTRIES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(RX_SG_SUPPORTED); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(OPT_TX_COMP_SUB_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(OPT_RX_COMP_QUEUES); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(OPT_RX_BUFADD_Q_PER_RX_COMP_Q); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(OPT_TX_ENTRIES_PER_SUBCRQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = + cpu_to_be16(OPT_RXBA_ENTRIES_PER_SUBCRQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); + + crq.query_capability.capability = cpu_to_be16(TX_RX_DESC_REQ); + atomic_inc(&adapter->running_cap_queries); + ibmvnic_send_crq(adapter, &crq); +} + +static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf; + union ibmvnic_crq crq; + int i; + + dma_unmap_single(dev, adapter->ip_offload_tok, + sizeof(adapter->ip_offload_buf), DMA_FROM_DEVICE); + + netdev_dbg(adapter->netdev, "Query IP Offload Buffer:\n"); + for (i = 0; i < (sizeof(adapter->ip_offload_buf) - 1) / 8 + 1; i++) + netdev_dbg(adapter->netdev, "%016lx\n", + ((unsigned long int *)(buf))[i]); + + netdev_dbg(adapter->netdev, "ipv4_chksum = %d\n", buf->ipv4_chksum); + netdev_dbg(adapter->netdev, "ipv6_chksum = %d\n", buf->ipv6_chksum); + netdev_dbg(adapter->netdev, "tcp_ipv4_chksum = %d\n", + buf->tcp_ipv4_chksum); + netdev_dbg(adapter->netdev, "tcp_ipv6_chksum = %d\n", + buf->tcp_ipv6_chksum); + netdev_dbg(adapter->netdev, "udp_ipv4_chksum = %d\n", + buf->udp_ipv4_chksum); + netdev_dbg(adapter->netdev, "udp_ipv6_chksum = %d\n", + buf->udp_ipv6_chksum); + netdev_dbg(adapter->netdev, "large_tx_ipv4 = %d\n", + buf->large_tx_ipv4); + netdev_dbg(adapter->netdev, "large_tx_ipv6 = %d\n", + buf->large_tx_ipv6); + netdev_dbg(adapter->netdev, "large_rx_ipv4 = %d\n", + buf->large_rx_ipv4); + netdev_dbg(adapter->netdev, "large_rx_ipv6 = %d\n", + buf->large_rx_ipv6); + netdev_dbg(adapter->netdev, "max_ipv4_hdr_sz = %d\n", + buf->max_ipv4_header_size); + netdev_dbg(adapter->netdev, "max_ipv6_hdr_sz = %d\n", + buf->max_ipv6_header_size); + netdev_dbg(adapter->netdev, "max_tcp_hdr_size = %d\n", + buf->max_tcp_header_size); + netdev_dbg(adapter->netdev, "max_udp_hdr_size = %d\n", + buf->max_udp_header_size); + netdev_dbg(adapter->netdev, "max_large_tx_size = %d\n", + buf->max_large_tx_size); + netdev_dbg(adapter->netdev, "max_large_rx_size = %d\n", + buf->max_large_rx_size); + netdev_dbg(adapter->netdev, "ipv6_ext_hdr = %d\n", + buf->ipv6_extension_header); + netdev_dbg(adapter->netdev, "tcp_pseudosum_req = %d\n", + buf->tcp_pseudosum_req); + netdev_dbg(adapter->netdev, "num_ipv6_ext_hd = %d\n", + buf->num_ipv6_ext_headers); + netdev_dbg(adapter->netdev, "off_ipv6_ext_hd = %d\n", + buf->off_ipv6_ext_headers); + + adapter->ip_offload_ctrl_tok = + dma_map_single(dev, &adapter->ip_offload_ctrl, + sizeof(adapter->ip_offload_ctrl), DMA_TO_DEVICE); + + if (dma_mapping_error(dev, adapter->ip_offload_ctrl_tok)) { + dev_err(dev, "Couldn't map ip offload control buffer\n"); + return; + } + + adapter->ip_offload_ctrl.version = cpu_to_be32(INITIAL_VERSION_IOB); + adapter->ip_offload_ctrl.tcp_ipv4_chksum = buf->tcp_ipv4_chksum; + adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum; + adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum; + adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum; + + /* large_tx/rx disabled for now, additional features needed */ + adapter->ip_offload_ctrl.large_tx_ipv4 = 0; + adapter->ip_offload_ctrl.large_tx_ipv6 = 0; + adapter->ip_offload_ctrl.large_rx_ipv4 = 0; + adapter->ip_offload_ctrl.large_rx_ipv6 = 0; + + adapter->netdev->features = NETIF_F_GSO; + + if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum) + adapter->netdev->features |= NETIF_F_IP_CSUM; + + if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum) + adapter->netdev->features |= NETIF_F_IPV6_CSUM; + + memset(&crq, 0, sizeof(crq)); + crq.control_ip_offload.first = IBMVNIC_CRQ_CMD; + crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD; + crq.control_ip_offload.len = + cpu_to_be32(sizeof(adapter->ip_offload_ctrl)); + crq.control_ip_offload.ioba = cpu_to_be32(adapter->ip_offload_ctrl_tok); + ibmvnic_send_crq(adapter, &crq); +} + +static void handle_error_info_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_error_buff *error_buff; + unsigned long flags; + bool found = false; + int i; + + if (!crq->request_error_rsp.rc.code) { + dev_info(dev, "Request Error Rsp returned with rc=%x\n", + crq->request_error_rsp.rc.code); + return; + } + + spin_lock_irqsave(&adapter->error_list_lock, flags); + list_for_each_entry(error_buff, &adapter->errors, list) + if (error_buff->error_id == crq->request_error_rsp.error_id) { + found = true; + list_del(&error_buff->list); + break; + } + spin_unlock_irqrestore(&adapter->error_list_lock, flags); + + if (!found) { + dev_err(dev, "Couldn't find error id %x\n", + crq->request_error_rsp.error_id); + return; + } + + dev_err(dev, "Detailed info for error id %x:", + crq->request_error_rsp.error_id); + + for (i = 0; i < error_buff->len; i++) { + pr_cont("%02x", (int)error_buff->buff[i]); + if (i % 8 == 7) + pr_cont(" "); + } + pr_cont("\n"); + + dma_unmap_single(dev, error_buff->dma, error_buff->len, + DMA_FROM_DEVICE); + kfree(error_buff->buff); + kfree(error_buff); +} + +static void handle_dump_size_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + int len = be32_to_cpu(crq->request_dump_size_rsp.len); + struct ibmvnic_inflight_cmd *inflight_cmd; + struct device *dev = &adapter->vdev->dev; + union ibmvnic_crq newcrq; + unsigned long flags; + + /* allocate and map buffer */ + adapter->dump_data = kmalloc(len, GFP_KERNEL); + if (!adapter->dump_data) { + complete(&adapter->fw_done); + return; + } + + adapter->dump_data_token = dma_map_single(dev, adapter->dump_data, len, + DMA_FROM_DEVICE); + + if (dma_mapping_error(dev, adapter->dump_data_token)) { + if (!firmware_has_feature(FW_FEATURE_CMO)) + dev_err(dev, "Couldn't map dump data\n"); + kfree(adapter->dump_data); + complete(&adapter->fw_done); + return; + } + + inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC); + if (!inflight_cmd) { + dma_unmap_single(dev, adapter->dump_data_token, len, + DMA_FROM_DEVICE); + kfree(adapter->dump_data); + complete(&adapter->fw_done); + return; + } + + memset(&newcrq, 0, sizeof(newcrq)); + newcrq.request_dump.first = IBMVNIC_CRQ_CMD; + newcrq.request_dump.cmd = REQUEST_DUMP; + newcrq.request_dump.ioba = cpu_to_be32(adapter->dump_data_token); + newcrq.request_dump.len = cpu_to_be32(adapter->dump_data_size); + + memcpy(&inflight_cmd->crq, &newcrq, sizeof(newcrq)); + + spin_lock_irqsave(&adapter->inflight_lock, flags); + list_add_tail(&inflight_cmd->list, &adapter->inflight); + spin_unlock_irqrestore(&adapter->inflight_lock, flags); + + ibmvnic_send_crq(adapter, &newcrq); +} + +static void handle_error_indication(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + int detail_len = be32_to_cpu(crq->error_indication.detail_error_sz); + struct ibmvnic_inflight_cmd *inflight_cmd; + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_error_buff *error_buff; + union ibmvnic_crq new_crq; + unsigned long flags; + + dev_err(dev, "Firmware reports %serror id %x, cause %d\n", + crq->error_indication. + flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "", + crq->error_indication.error_id, + crq->error_indication.error_cause); + + error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC); + if (!error_buff) + return; + + error_buff->buff = kmalloc(detail_len, GFP_ATOMIC); + if (!error_buff->buff) { + kfree(error_buff); + return; + } + + error_buff->dma = dma_map_single(dev, error_buff->buff, detail_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(dev, error_buff->dma)) { + if (!firmware_has_feature(FW_FEATURE_CMO)) + dev_err(dev, "Couldn't map error buffer\n"); + kfree(error_buff->buff); + kfree(error_buff); + return; + } + + inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC); + if (!inflight_cmd) { + dma_unmap_single(dev, error_buff->dma, detail_len, + DMA_FROM_DEVICE); + kfree(error_buff->buff); + kfree(error_buff); + return; + } + + error_buff->len = detail_len; + error_buff->error_id = crq->error_indication.error_id; + + spin_lock_irqsave(&adapter->error_list_lock, flags); + list_add_tail(&error_buff->list, &adapter->errors); + spin_unlock_irqrestore(&adapter->error_list_lock, flags); + + memset(&new_crq, 0, sizeof(new_crq)); + new_crq.request_error_info.first = IBMVNIC_CRQ_CMD; + new_crq.request_error_info.cmd = REQUEST_ERROR_INFO; + new_crq.request_error_info.ioba = cpu_to_be32(error_buff->dma); + new_crq.request_error_info.len = cpu_to_be32(detail_len); + new_crq.request_error_info.error_id = crq->error_indication.error_id; + + memcpy(&inflight_cmd->crq, &crq, sizeof(crq)); + + spin_lock_irqsave(&adapter->inflight_lock, flags); + list_add_tail(&inflight_cmd->list, &adapter->inflight); + spin_unlock_irqrestore(&adapter->inflight_lock, flags); + + ibmvnic_send_crq(adapter, &new_crq); +} + +static void handle_change_mac_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct device *dev = &adapter->vdev->dev; + long rc; + + rc = crq->change_mac_addr_rsp.rc.code; + if (rc) { + dev_err(dev, "Error %ld in CHANGE_MAC_ADDR_RSP\n", rc); + return; + } + memcpy(netdev->dev_addr, &crq->change_mac_addr_rsp.mac_addr[0], + ETH_ALEN); +} + +static void handle_request_cap_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + u64 *req_value; + char *name; + + switch (be16_to_cpu(crq->request_capability_rsp.capability)) { + case REQ_TX_QUEUES: + req_value = &adapter->req_tx_queues; + name = "tx"; + break; + case REQ_RX_QUEUES: + req_value = &adapter->req_rx_queues; + name = "rx"; + break; + case REQ_RX_ADD_QUEUES: + req_value = &adapter->req_rx_add_queues; + name = "rx_add"; + break; + case REQ_TX_ENTRIES_PER_SUBCRQ: + req_value = &adapter->req_tx_entries_per_subcrq; + name = "tx_entries_per_subcrq"; + break; + case REQ_RX_ADD_ENTRIES_PER_SUBCRQ: + req_value = &adapter->req_rx_add_entries_per_subcrq; + name = "rx_add_entries_per_subcrq"; + break; + case REQ_MTU: + req_value = &adapter->req_mtu; + name = "mtu"; + break; + case PROMISC_REQUESTED: + req_value = &adapter->promisc; + name = "promisc"; + break; + default: + dev_err(dev, "Got invalid cap request rsp %d\n", + crq->request_capability.capability); + return; + } + + switch (crq->request_capability_rsp.rc.code) { + case SUCCESS: + break; + case PARTIALSUCCESS: + dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n", + *req_value, + (long int)be32_to_cpu(crq->request_capability_rsp. + number), name); + release_sub_crqs(adapter); + *req_value = be32_to_cpu(crq->request_capability_rsp.number); + complete(&adapter->init_done); + return; + default: + dev_err(dev, "Error %d in request cap rsp\n", + crq->request_capability_rsp.rc.code); + return; + } + + /* Done receiving requested capabilities, query IP offload support */ + if (++adapter->requested_caps == 7) { + union ibmvnic_crq newcrq; + int buf_sz = sizeof(struct ibmvnic_query_ip_offload_buffer); + struct ibmvnic_query_ip_offload_buffer *ip_offload_buf = + &adapter->ip_offload_buf; + + adapter->ip_offload_tok = dma_map_single(dev, ip_offload_buf, + buf_sz, + DMA_FROM_DEVICE); + + if (dma_mapping_error(dev, adapter->ip_offload_tok)) { + if (!firmware_has_feature(FW_FEATURE_CMO)) + dev_err(dev, "Couldn't map offload buffer\n"); + return; + } + + memset(&newcrq, 0, sizeof(newcrq)); + newcrq.query_ip_offload.first = IBMVNIC_CRQ_CMD; + newcrq.query_ip_offload.cmd = QUERY_IP_OFFLOAD; + newcrq.query_ip_offload.len = cpu_to_be32(buf_sz); + newcrq.query_ip_offload.ioba = + cpu_to_be32(adapter->ip_offload_tok); + + ibmvnic_send_crq(adapter, &newcrq); + } +} + +static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, + struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf; + struct ibmvnic_login_buffer *login = adapter->login_buf; + union ibmvnic_crq crq; + int i; + + dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, + DMA_BIDIRECTIONAL); + dma_unmap_single(dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, DMA_BIDIRECTIONAL); + + netdev_dbg(adapter->netdev, "Login Response Buffer:\n"); + for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) { + netdev_dbg(adapter->netdev, "%016lx\n", + ((unsigned long int *)(adapter->login_rsp_buf))[i]); + } + + /* Sanity checks */ + if (login->num_txcomp_subcrqs != login_rsp->num_txsubm_subcrqs || + (be32_to_cpu(login->num_rxcomp_subcrqs) * + adapter->req_rx_add_queues != + be32_to_cpu(login_rsp->num_rxadd_subcrqs))) { + dev_err(dev, "FATAL: Inconsistent login and login rsp\n"); + ibmvnic_remove(adapter->vdev); + return -EIO; + } + complete(&adapter->init_done); + + memset(&crq, 0, sizeof(crq)); + crq.request_ras_comp_num.first = IBMVNIC_CRQ_CMD; + crq.request_ras_comp_num.cmd = REQUEST_RAS_COMP_NUM; + ibmvnic_send_crq(adapter, &crq); + + return 0; +} + +static void handle_request_map_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + u8 map_id = crq->request_map_rsp.map_id; + int tx_subcrqs; + int rx_subcrqs; + long rc; + int i; + + tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + rx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + + rc = crq->request_map_rsp.rc.code; + if (rc) { + dev_err(dev, "Error %ld in REQUEST_MAP_RSP\n", rc); + adapter->map_id--; + /* need to find and zero tx/rx_pool map_id */ + for (i = 0; i < tx_subcrqs; i++) { + if (adapter->tx_pool[i].long_term_buff.map_id == map_id) + adapter->tx_pool[i].long_term_buff.map_id = 0; + } + for (i = 0; i < rx_subcrqs; i++) { + if (adapter->rx_pool[i].long_term_buff.map_id == map_id) + adapter->rx_pool[i].long_term_buff.map_id = 0; + } + } + complete(&adapter->fw_done); +} + +static void handle_request_unmap_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + long rc; + + rc = crq->request_unmap_rsp.rc.code; + if (rc) + dev_err(dev, "Error %ld in REQUEST_UNMAP_RSP\n", rc); +} + +static void handle_query_map_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct device *dev = &adapter->vdev->dev; + long rc; + + rc = crq->query_map_rsp.rc.code; + if (rc) { + dev_err(dev, "Error %ld in QUERY_MAP_RSP\n", rc); + return; + } + netdev_dbg(netdev, "page_size = %d\ntot_pages = %d\nfree_pages = %d\n", + crq->query_map_rsp.page_size, crq->query_map_rsp.tot_pages, + crq->query_map_rsp.free_pages); +} + +static void handle_query_cap_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct device *dev = &adapter->vdev->dev; + long rc; + + atomic_dec(&adapter->running_cap_queries); + netdev_dbg(netdev, "Outstanding queries: %d\n", + atomic_read(&adapter->running_cap_queries)); + rc = crq->query_capability.rc.code; + if (rc) { + dev_err(dev, "Error %ld in QUERY_CAP_RSP\n", rc); + goto out; + } + + switch (be16_to_cpu(crq->query_capability.capability)) { + case MIN_TX_QUEUES: + adapter->min_tx_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "min_tx_queues = %lld\n", + adapter->min_tx_queues); + break; + case MIN_RX_QUEUES: + adapter->min_rx_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "min_rx_queues = %lld\n", + adapter->min_rx_queues); + break; + case MIN_RX_ADD_QUEUES: + adapter->min_rx_add_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "min_rx_add_queues = %lld\n", + adapter->min_rx_add_queues); + break; + case MAX_TX_QUEUES: + adapter->max_tx_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_tx_queues = %lld\n", + adapter->max_tx_queues); + break; + case MAX_RX_QUEUES: + adapter->max_rx_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_rx_queues = %lld\n", + adapter->max_rx_queues); + break; + case MAX_RX_ADD_QUEUES: + adapter->max_rx_add_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_rx_add_queues = %lld\n", + adapter->max_rx_add_queues); + break; + case MIN_TX_ENTRIES_PER_SUBCRQ: + adapter->min_tx_entries_per_subcrq = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n", + adapter->min_tx_entries_per_subcrq); + break; + case MIN_RX_ADD_ENTRIES_PER_SUBCRQ: + adapter->min_rx_add_entries_per_subcrq = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n", + adapter->min_rx_add_entries_per_subcrq); + break; + case MAX_TX_ENTRIES_PER_SUBCRQ: + adapter->max_tx_entries_per_subcrq = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n", + adapter->max_tx_entries_per_subcrq); + break; + case MAX_RX_ADD_ENTRIES_PER_SUBCRQ: + adapter->max_rx_add_entries_per_subcrq = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n", + adapter->max_rx_add_entries_per_subcrq); + break; + case TCP_IP_OFFLOAD: + adapter->tcp_ip_offload = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "tcp_ip_offload = %lld\n", + adapter->tcp_ip_offload); + break; + case PROMISC_SUPPORTED: + adapter->promisc_supported = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "promisc_supported = %lld\n", + adapter->promisc_supported); + break; + case MIN_MTU: + adapter->min_mtu = be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); + break; + case MAX_MTU: + adapter->max_mtu = be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); + break; + case MAX_MULTICAST_FILTERS: + adapter->max_multicast_filters = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_multicast_filters = %lld\n", + adapter->max_multicast_filters); + break; + case VLAN_HEADER_INSERTION: + adapter->vlan_header_insertion = + be32_to_cpu(crq->query_capability.number); + if (adapter->vlan_header_insertion) + netdev->features |= NETIF_F_HW_VLAN_STAG_TX; + netdev_dbg(netdev, "vlan_header_insertion = %lld\n", + adapter->vlan_header_insertion); + break; + case MAX_TX_SG_ENTRIES: + adapter->max_tx_sg_entries = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "max_tx_sg_entries = %lld\n", + adapter->max_tx_sg_entries); + break; + case RX_SG_SUPPORTED: + adapter->rx_sg_supported = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "rx_sg_supported = %lld\n", + adapter->rx_sg_supported); + break; + case OPT_TX_COMP_SUB_QUEUES: + adapter->opt_tx_comp_sub_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n", + adapter->opt_tx_comp_sub_queues); + break; + case OPT_RX_COMP_QUEUES: + adapter->opt_rx_comp_queues = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n", + adapter->opt_rx_comp_queues); + break; + case OPT_RX_BUFADD_Q_PER_RX_COMP_Q: + adapter->opt_rx_bufadd_q_per_rx_comp_q = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n", + adapter->opt_rx_bufadd_q_per_rx_comp_q); + break; + case OPT_TX_ENTRIES_PER_SUBCRQ: + adapter->opt_tx_entries_per_subcrq = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n", + adapter->opt_tx_entries_per_subcrq); + break; + case OPT_RXBA_ENTRIES_PER_SUBCRQ: + adapter->opt_rxba_entries_per_subcrq = + be32_to_cpu(crq->query_capability.number); + netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n", + adapter->opt_rxba_entries_per_subcrq); + break; + case TX_RX_DESC_REQ: + adapter->tx_rx_desc_req = crq->query_capability.number; + netdev_dbg(netdev, "tx_rx_desc_req = %llx\n", + adapter->tx_rx_desc_req); + break; + + default: + netdev_err(netdev, "Got invalid cap rsp %d\n", + crq->query_capability.capability); + } + +out: + if (atomic_read(&adapter->running_cap_queries) == 0) + complete(&adapter->init_done); + /* We're done querying the capabilities, initialize sub-crqs */ +} + +static void handle_control_ras_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + u8 correlator = crq->control_ras_rsp.correlator; + struct device *dev = &adapter->vdev->dev; + bool found = false; + int i; + + if (crq->control_ras_rsp.rc.code) { + dev_warn(dev, "Control ras failed rc=%d\n", + crq->control_ras_rsp.rc.code); + return; + } + + for (i = 0; i < adapter->ras_comp_num; i++) { + if (adapter->ras_comps[i].correlator == correlator) { + found = true; + break; + } + } + + if (!found) { + dev_warn(dev, "Correlator not found on control_ras_rsp\n"); + return; + } + + switch (crq->control_ras_rsp.op) { + case IBMVNIC_TRACE_LEVEL: + adapter->ras_comps[i].trace_level = crq->control_ras.level; + break; + case IBMVNIC_ERROR_LEVEL: + adapter->ras_comps[i].error_check_level = + crq->control_ras.level; + break; + case IBMVNIC_TRACE_PAUSE: + adapter->ras_comp_int[i].paused = 1; + break; + case IBMVNIC_TRACE_RESUME: + adapter->ras_comp_int[i].paused = 0; + break; + case IBMVNIC_TRACE_ON: + adapter->ras_comps[i].trace_on = 1; + break; + case IBMVNIC_TRACE_OFF: + adapter->ras_comps[i].trace_on = 0; + break; + case IBMVNIC_CHG_TRACE_BUFF_SZ: + /* trace_buff_sz is 3 bytes, stuff it into an int */ + ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[0] = 0; + ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[1] = + crq->control_ras_rsp.trace_buff_sz[0]; + ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[2] = + crq->control_ras_rsp.trace_buff_sz[1]; + ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[3] = + crq->control_ras_rsp.trace_buff_sz[2]; + break; + default: + dev_err(dev, "invalid op %d on control_ras_rsp", + crq->control_ras_rsp.op); + } +} + +static int ibmvnic_fw_comp_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + return 0; +} + +static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len, + loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_fw_trace_entry *trace; + int num = ras_comp_int->num; + union ibmvnic_crq crq; + dma_addr_t trace_tok; + + if (*ppos >= be32_to_cpu(adapter->ras_comps[num].trace_buff_size)) + return 0; + + trace = + dma_alloc_coherent(dev, + be32_to_cpu(adapter->ras_comps[num]. + trace_buff_size), &trace_tok, + GFP_KERNEL); + if (!trace) { + dev_err(dev, "Couldn't alloc trace buffer\n"); + return 0; + } + + memset(&crq, 0, sizeof(crq)); + crq.collect_fw_trace.first = IBMVNIC_CRQ_CMD; + crq.collect_fw_trace.cmd = COLLECT_FW_TRACE; + crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator; + crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok); + crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size; + ibmvnic_send_crq(adapter, &crq); + + init_completion(&adapter->fw_done); + wait_for_completion(&adapter->fw_done); + + if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size)) + len = + be32_to_cpu(adapter->ras_comps[num].trace_buff_size) - + *ppos; + + copy_to_user(user_buf, &((u8 *)trace)[*ppos], len); + + dma_free_coherent(dev, + be32_to_cpu(adapter->ras_comps[num].trace_buff_size), + trace, trace_tok); + *ppos += len; + return len; +} + +static const struct file_operations trace_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_fw_comp_open, + .read = trace_read, +}; + +static ssize_t paused_read(struct file *file, char __user *user_buf, size_t len, + loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + char buff[5]; /* 1 or 0 plus \n and \0 */ + int size; + + size = sprintf(buff, "%d\n", adapter->ras_comp_int[num].paused); + + if (*ppos >= size) + return 0; + + copy_to_user(user_buf, buff, size); + *ppos += size; + return size; +} + +static ssize_t paused_write(struct file *file, const char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + union ibmvnic_crq crq; + unsigned long val; + char buff[9]; /* decimal max int plus \n and \0 */ + + copy_from_user(buff, user_buf, sizeof(buff)); + val = kstrtoul(buff, 10, NULL); + + adapter->ras_comp_int[num].paused = val ? 1 : 0; + + memset(&crq, 0, sizeof(crq)); + crq.control_ras.first = IBMVNIC_CRQ_CMD; + crq.control_ras.cmd = CONTROL_RAS; + crq.control_ras.correlator = adapter->ras_comps[num].correlator; + crq.control_ras.op = val ? IBMVNIC_TRACE_PAUSE : IBMVNIC_TRACE_RESUME; + ibmvnic_send_crq(adapter, &crq); + + return len; +} + +static const struct file_operations paused_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_fw_comp_open, + .read = paused_read, + .write = paused_write, +}; + +static ssize_t tracing_read(struct file *file, char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + char buff[5]; /* 1 or 0 plus \n and \0 */ + int size; + + size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_on); + + if (*ppos >= size) + return 0; + + copy_to_user(user_buf, buff, size); + *ppos += size; + return size; +} + +static ssize_t tracing_write(struct file *file, const char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + union ibmvnic_crq crq; + unsigned long val; + char buff[9]; /* decimal max int plus \n and \0 */ + + copy_from_user(buff, user_buf, sizeof(buff)); + val = kstrtoul(buff, 10, NULL); + + memset(&crq, 0, sizeof(crq)); + crq.control_ras.first = IBMVNIC_CRQ_CMD; + crq.control_ras.cmd = CONTROL_RAS; + crq.control_ras.correlator = adapter->ras_comps[num].correlator; + crq.control_ras.op = val ? IBMVNIC_TRACE_ON : IBMVNIC_TRACE_OFF; + + return len; +} + +static const struct file_operations tracing_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_fw_comp_open, + .read = tracing_read, + .write = tracing_write, +}; + +static ssize_t error_level_read(struct file *file, char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + char buff[5]; /* decimal max char plus \n and \0 */ + int size; + + size = sprintf(buff, "%d\n", adapter->ras_comps[num].error_check_level); + + if (*ppos >= size) + return 0; + + copy_to_user(user_buf, buff, size); + *ppos += size; + return size; +} + +static ssize_t error_level_write(struct file *file, const char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + union ibmvnic_crq crq; + unsigned long val; + char buff[9]; /* decimal max int plus \n and \0 */ + + copy_from_user(buff, user_buf, sizeof(buff)); + val = kstrtoul(buff, 10, NULL); + + if (val > 9) + val = 9; + + memset(&crq, 0, sizeof(crq)); + crq.control_ras.first = IBMVNIC_CRQ_CMD; + crq.control_ras.cmd = CONTROL_RAS; + crq.control_ras.correlator = adapter->ras_comps[num].correlator; + crq.control_ras.op = IBMVNIC_ERROR_LEVEL; + crq.control_ras.level = val; + ibmvnic_send_crq(adapter, &crq); + + return len; +} + +static const struct file_operations error_level_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_fw_comp_open, + .read = error_level_read, + .write = error_level_write, +}; + +static ssize_t trace_level_read(struct file *file, char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + char buff[5]; /* decimal max char plus \n and \0 */ + int size; + + size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_level); + if (*ppos >= size) + return 0; + + copy_to_user(user_buf, buff, size); + *ppos += size; + return size; +} + +static ssize_t trace_level_write(struct file *file, const char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + union ibmvnic_crq crq; + unsigned long val; + char buff[9]; /* decimal max int plus \n and \0 */ + + copy_from_user(buff, user_buf, sizeof(buff)); + val = kstrtoul(buff, 10, NULL); + if (val > 9) + val = 9; + + memset(&crq, 0, sizeof(crq)); + crq.control_ras.first = IBMVNIC_CRQ_CMD; + crq.control_ras.cmd = CONTROL_RAS; + crq.control_ras.correlator = + adapter->ras_comps[ras_comp_int->num].correlator; + crq.control_ras.op = IBMVNIC_TRACE_LEVEL; + crq.control_ras.level = val; + ibmvnic_send_crq(adapter, &crq); + + return len; +} + +static const struct file_operations trace_level_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_fw_comp_open, + .read = trace_level_read, + .write = trace_level_write, +}; + +static ssize_t trace_buff_size_read(struct file *file, char __user *user_buf, + size_t len, loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + int num = ras_comp_int->num; + char buff[9]; /* decimal max int plus \n and \0 */ + int size; + + size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_buff_size); + if (*ppos >= size) + return 0; + + copy_to_user(user_buf, buff, size); + *ppos += size; + return size; +} + +static ssize_t trace_buff_size_write(struct file *file, + const char __user *user_buf, size_t len, + loff_t *ppos) +{ + struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data; + struct ibmvnic_adapter *adapter = ras_comp_int->adapter; + union ibmvnic_crq crq; + unsigned long val; + char buff[9]; /* decimal max int plus \n and \0 */ + + copy_from_user(buff, user_buf, sizeof(buff)); + val = kstrtoul(buff, 10, NULL); + + memset(&crq, 0, sizeof(crq)); + crq.control_ras.first = IBMVNIC_CRQ_CMD; + crq.control_ras.cmd = CONTROL_RAS; + crq.control_ras.correlator = + adapter->ras_comps[ras_comp_int->num].correlator; + crq.control_ras.op = IBMVNIC_CHG_TRACE_BUFF_SZ; + /* trace_buff_sz is 3 bytes, stuff an int into it */ + crq.control_ras.trace_buff_sz[0] = ((u8 *)(&val))[5]; + crq.control_ras.trace_buff_sz[1] = ((u8 *)(&val))[6]; + crq.control_ras.trace_buff_sz[2] = ((u8 *)(&val))[7]; + ibmvnic_send_crq(adapter, &crq); + + return len; +} + +static const struct file_operations trace_size_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_fw_comp_open, + .read = trace_buff_size_read, + .write = trace_buff_size_write, +}; + +static void handle_request_ras_comps_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct dentry *dir_ent; + struct dentry *ent; + int i; + + debugfs_remove_recursive(adapter->ras_comps_ent); + + adapter->ras_comps_ent = debugfs_create_dir("ras_comps", + adapter->debugfs_dir); + if (!adapter->ras_comps_ent || IS_ERR(adapter->ras_comps_ent)) { + dev_info(dev, "debugfs create ras_comps dir failed\n"); + return; + } + + for (i = 0; i < adapter->ras_comp_num; i++) { + dir_ent = debugfs_create_dir(adapter->ras_comps[i].name, + adapter->ras_comps_ent); + if (!dir_ent || IS_ERR(dir_ent)) { + dev_info(dev, "debugfs create %s dir failed\n", + adapter->ras_comps[i].name); + continue; + } + + adapter->ras_comp_int[i].adapter = adapter; + adapter->ras_comp_int[i].num = i; + adapter->ras_comp_int[i].desc_blob.data = + &adapter->ras_comps[i].description; + adapter->ras_comp_int[i].desc_blob.size = + sizeof(adapter->ras_comps[i].description); + + /* Don't need to remember the dentry's because the debugfs dir + * gets removed recursively + */ + ent = debugfs_create_blob("description", S_IRUGO, dir_ent, + &adapter->ras_comp_int[i].desc_blob); + ent = debugfs_create_file("trace_buf_size", S_IRUGO | S_IWUSR, + dir_ent, &adapter->ras_comp_int[i], + &trace_size_ops); + ent = debugfs_create_file("trace_level", + S_IRUGO | + (adapter->ras_comps[i].trace_level != + 0xFF ? S_IWUSR : 0), + dir_ent, &adapter->ras_comp_int[i], + &trace_level_ops); + ent = debugfs_create_file("error_level", + S_IRUGO | + (adapter-> + ras_comps[i].error_check_level != + 0xFF ? S_IWUSR : 0), + dir_ent, &adapter->ras_comp_int[i], + &trace_level_ops); + ent = debugfs_create_file("tracing", S_IRUGO | S_IWUSR, + dir_ent, &adapter->ras_comp_int[i], + &tracing_ops); + ent = debugfs_create_file("paused", S_IRUGO | S_IWUSR, + dir_ent, &adapter->ras_comp_int[i], + &paused_ops); + ent = debugfs_create_file("trace", S_IRUGO, dir_ent, + &adapter->ras_comp_int[i], + &trace_ops); + } +} + +static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + int len = adapter->ras_comp_num * sizeof(struct ibmvnic_fw_component); + struct device *dev = &adapter->vdev->dev; + union ibmvnic_crq newcrq; + + adapter->ras_comps = dma_alloc_coherent(dev, len, + &adapter->ras_comps_tok, + GFP_KERNEL); + if (!adapter->ras_comps) { + if (!firmware_has_feature(FW_FEATURE_CMO)) + dev_err(dev, "Couldn't alloc fw comps buffer\n"); + return; + } + + adapter->ras_comp_int = kmalloc(adapter->ras_comp_num * + sizeof(struct ibmvnic_fw_comp_internal), + GFP_KERNEL); + if (!adapter->ras_comp_int) + dma_free_coherent(dev, len, adapter->ras_comps, + adapter->ras_comps_tok); + + memset(&newcrq, 0, sizeof(newcrq)); + newcrq.request_ras_comps.first = IBMVNIC_CRQ_CMD; + newcrq.request_ras_comps.cmd = REQUEST_RAS_COMPS; + newcrq.request_ras_comps.ioba = cpu_to_be32(adapter->ras_comps_tok); + newcrq.request_ras_comps.len = cpu_to_be32(len); + ibmvnic_send_crq(adapter, &newcrq); +} + +static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_inflight_cmd *inflight_cmd; + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_error_buff *error_buff; + unsigned long flags; + unsigned long flags2; + + spin_lock_irqsave(&adapter->inflight_lock, flags); + list_for_each_entry(inflight_cmd, &adapter->inflight, list) { + switch (inflight_cmd->crq.generic.cmd) { + case LOGIN: + dma_unmap_single(dev, adapter->login_buf_token, + adapter->login_buf_sz, + DMA_BIDIRECTIONAL); + dma_unmap_single(dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, + DMA_BIDIRECTIONAL); + kfree(adapter->login_rsp_buf); + kfree(adapter->login_buf); + break; + case REQUEST_DUMP: + complete(&adapter->fw_done); + break; + case REQUEST_ERROR_INFO: + spin_lock_irqsave(&adapter->error_list_lock, flags2); + list_for_each_entry(error_buff, &adapter->errors, + list) { + dma_unmap_single(dev, error_buff->dma, + error_buff->len, + DMA_FROM_DEVICE); + kfree(error_buff->buff); + list_del(&error_buff->list); + kfree(error_buff); + } + spin_unlock_irqrestore(&adapter->error_list_lock, + flags2); + break; + } + list_del(&inflight_cmd->list); + kfree(inflight_cmd); + } + spin_unlock_irqrestore(&adapter->inflight_lock, flags); +} + +static void ibmvnic_handle_crq(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_generic_crq *gen_crq = &crq->generic; + struct net_device *netdev = adapter->netdev; + struct device *dev = &adapter->vdev->dev; + long rc; + + netdev_dbg(netdev, "Handling CRQ: %016lx %016lx\n", + ((unsigned long int *)crq)[0], + ((unsigned long int *)crq)[1]); + switch (gen_crq->first) { + case IBMVNIC_CRQ_INIT_RSP: + switch (gen_crq->cmd) { + case IBMVNIC_CRQ_INIT: + dev_info(dev, "Partner initialized\n"); + /* Send back a response */ + rc = ibmvnic_send_crq_init_complete(adapter); + if (rc == 0) + send_version_xchg(adapter); + else + dev_err(dev, "Can't send initrsp rc=%ld\n", rc); + break; + case IBMVNIC_CRQ_INIT_COMPLETE: + dev_info(dev, "Partner initialization complete\n"); + send_version_xchg(adapter); + break; + default: + dev_err(dev, "Unknown crq cmd: %d\n", gen_crq->cmd); + } + return; + case IBMVNIC_CRQ_XPORT_EVENT: + if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) { + dev_info(dev, "Re-enabling adapter\n"); + adapter->migrated = true; + ibmvnic_free_inflight(adapter); + release_sub_crqs(adapter); + rc = ibmvnic_reenable_crq_queue(adapter); + if (rc) + dev_err(dev, "Error after enable rc=%ld\n", rc); + adapter->migrated = false; + rc = ibmvnic_send_crq_init(adapter); + if (rc) + dev_err(dev, "Error sending init rc=%ld\n", rc); + } else { + /* The adapter lost the connection */ + dev_err(dev, "Virtual Adapter failed (rc=%d)\n", + gen_crq->cmd); + ibmvnic_free_inflight(adapter); + release_sub_crqs(adapter); + } + return; + case IBMVNIC_CRQ_CMD_RSP: + break; + default: + dev_err(dev, "Got an invalid msg type 0x%02x\n", + gen_crq->first); + return; + } + + switch (gen_crq->cmd) { + case VERSION_EXCHANGE_RSP: + rc = crq->version_exchange_rsp.rc.code; + if (rc) { + dev_err(dev, "Error %ld in VERSION_EXCHG_RSP\n", rc); + break; + } + dev_info(dev, "Partner protocol version is %d\n", + crq->version_exchange_rsp.version); + if (be16_to_cpu(crq->version_exchange_rsp.version) < + ibmvnic_version) + ibmvnic_version = + be16_to_cpu(crq->version_exchange_rsp.version); + send_cap_queries(adapter); + break; + case QUERY_CAPABILITY_RSP: + handle_query_cap_rsp(crq, adapter); + break; + case QUERY_MAP_RSP: + handle_query_map_rsp(crq, adapter); + break; + case REQUEST_MAP_RSP: + handle_request_map_rsp(crq, adapter); + break; + case REQUEST_UNMAP_RSP: + handle_request_unmap_rsp(crq, adapter); + break; + case REQUEST_CAPABILITY_RSP: + handle_request_cap_rsp(crq, adapter); + break; + case LOGIN_RSP: + netdev_dbg(netdev, "Got Login Response\n"); + handle_login_rsp(crq, adapter); + break; + case LOGICAL_LINK_STATE_RSP: + netdev_dbg(netdev, "Got Logical Link State Response\n"); + adapter->logical_link_state = + crq->logical_link_state_rsp.link_state; + break; + case LINK_STATE_INDICATION: + netdev_dbg(netdev, "Got Logical Link State Indication\n"); + adapter->phys_link_state = + crq->link_state_indication.phys_link_state; + adapter->logical_link_state = + crq->link_state_indication.logical_link_state; + break; + case CHANGE_MAC_ADDR_RSP: + netdev_dbg(netdev, "Got MAC address change Response\n"); + handle_change_mac_rsp(crq, adapter); + break; + case ERROR_INDICATION: + netdev_dbg(netdev, "Got Error Indication\n"); + handle_error_indication(crq, adapter); + break; + case REQUEST_ERROR_RSP: + netdev_dbg(netdev, "Got Error Detail Response\n"); + handle_error_info_rsp(crq, adapter); + break; + case REQUEST_STATISTICS_RSP: + netdev_dbg(netdev, "Got Statistics Response\n"); + complete(&adapter->stats_done); + break; + case REQUEST_DUMP_SIZE_RSP: + netdev_dbg(netdev, "Got Request Dump Size Response\n"); + handle_dump_size_rsp(crq, adapter); + break; + case REQUEST_DUMP_RSP: + netdev_dbg(netdev, "Got Request Dump Response\n"); + complete(&adapter->fw_done); + break; + case QUERY_IP_OFFLOAD_RSP: + netdev_dbg(netdev, "Got Query IP offload Response\n"); + handle_query_ip_offload_rsp(adapter); + break; + case MULTICAST_CTRL_RSP: + netdev_dbg(netdev, "Got multicast control Response\n"); + break; + case CONTROL_IP_OFFLOAD_RSP: + netdev_dbg(netdev, "Got Control IP offload Response\n"); + dma_unmap_single(dev, adapter->ip_offload_ctrl_tok, + sizeof(adapter->ip_offload_ctrl), + DMA_TO_DEVICE); + /* We're done with the queries, perform the login */ + send_login(adapter); + break; + case REQUEST_RAS_COMP_NUM_RSP: + netdev_dbg(netdev, "Got Request RAS Comp Num Response\n"); + if (crq->request_ras_comp_num_rsp.rc.code == 10) { + netdev_dbg(netdev, "Request RAS Comp Num not supported\n"); + break; + } + adapter->ras_comp_num = + be32_to_cpu(crq->request_ras_comp_num_rsp.num_components); + handle_request_ras_comp_num_rsp(crq, adapter); + break; + case REQUEST_RAS_COMPS_RSP: + netdev_dbg(netdev, "Got Request RAS Comps Response\n"); + handle_request_ras_comps_rsp(crq, adapter); + break; + case CONTROL_RAS_RSP: + netdev_dbg(netdev, "Got Control RAS Response\n"); + handle_control_ras_rsp(crq, adapter); + break; + case COLLECT_FW_TRACE_RSP: + netdev_dbg(netdev, "Got Collect firmware trace Response\n"); + complete(&adapter->fw_done); + break; + default: + netdev_err(netdev, "Got an invalid cmd type 0x%02x\n", + gen_crq->cmd); + } +} + +static irqreturn_t ibmvnic_interrupt(int irq, void *instance) +{ + struct ibmvnic_adapter *adapter = instance; + struct ibmvnic_crq_queue *queue = &adapter->crq; + struct vio_dev *vdev = adapter->vdev; + union ibmvnic_crq *crq; + unsigned long flags; + bool done = false; + + spin_lock_irqsave(&queue->lock, flags); + vio_disable_interrupts(vdev); + while (!done) { + /* Pull all the valid messages off the CRQ */ + while ((crq = ibmvnic_next_crq(adapter)) != NULL) { + ibmvnic_handle_crq(crq, adapter); + crq->generic.first = 0; + } + vio_enable_interrupts(vdev); + crq = ibmvnic_next_crq(adapter); + if (crq) { + vio_disable_interrupts(vdev); + ibmvnic_handle_crq(crq, adapter); + crq->generic.first = 0; + } else { + done = true; + } + } + spin_unlock_irqrestore(&queue->lock, flags); + return IRQ_HANDLED; +} + +static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *adapter) +{ + struct vio_dev *vdev = adapter->vdev; + int rc; + + do { + rc = plpar_hcall_norets(H_ENABLE_CRQ, vdev->unit_address); + } while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc)); + + if (rc) + dev_err(&vdev->dev, "Error enabling adapter (rc=%d)\n", rc); + + return rc; +} + +static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_crq_queue *crq = &adapter->crq; + struct device *dev = &adapter->vdev->dev; + struct vio_dev *vdev = adapter->vdev; + int rc; + + /* Close the CRQ */ + do { + rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); + + /* Clean out the queue */ + memset(crq->msgs, 0, PAGE_SIZE); + crq->cur = 0; + + /* And re-open it again */ + rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address, + crq->msg_token, PAGE_SIZE); + + if (rc == H_CLOSED) + /* Adapter is good, but other end is not ready */ + dev_warn(dev, "Partner adapter not ready\n"); + else if (rc != 0) + dev_warn(dev, "Couldn't register crq (rc=%d)\n", rc); + + return rc; +} + +static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_crq_queue *crq = &adapter->crq; + struct vio_dev *vdev = adapter->vdev; + long rc; + + netdev_dbg(adapter->netdev, "Releasing CRQ\n"); + free_irq(vdev->irq, adapter); + do { + rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); + + dma_unmap_single(&vdev->dev, crq->msg_token, PAGE_SIZE, + DMA_BIDIRECTIONAL); + free_page((unsigned long)crq->msgs); +} + +static int ibmvnic_init_crq_queue(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_crq_queue *crq = &adapter->crq; + struct device *dev = &adapter->vdev->dev; + struct vio_dev *vdev = adapter->vdev; + int rc, retrc = -ENOMEM; + + crq->msgs = (union ibmvnic_crq *)get_zeroed_page(GFP_KERNEL); + /* Should we allocate more than one page? */ + + if (!crq->msgs) + return -ENOMEM; + + crq->size = PAGE_SIZE / sizeof(*crq->msgs); + crq->msg_token = dma_map_single(dev, crq->msgs, PAGE_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, crq->msg_token)) + goto map_failed; + + rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address, + crq->msg_token, PAGE_SIZE); + + if (rc == H_RESOURCE) + /* maybe kexecing and resource is busy. try a reset */ + rc = ibmvnic_reset_crq(adapter); + retrc = rc; + + if (rc == H_CLOSED) { + dev_warn(dev, "Partner adapter not ready\n"); + } else if (rc) { + dev_warn(dev, "Error %d opening adapter\n", rc); + goto reg_crq_failed; + } + + retrc = 0; + + netdev_dbg(adapter->netdev, "registering irq 0x%x\n", vdev->irq); + rc = request_irq(vdev->irq, ibmvnic_interrupt, 0, IBMVNIC_NAME, + adapter); + if (rc) { + dev_err(dev, "Couldn't register irq 0x%x. rc=%d\n", + vdev->irq, rc); + goto req_irq_failed; + } + + rc = vio_enable_interrupts(vdev); + if (rc) { + dev_err(dev, "Error %d enabling interrupts\n", rc); + goto req_irq_failed; + } + + crq->cur = 0; + spin_lock_init(&crq->lock); + + return retrc; + +req_irq_failed: + do { + rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); +reg_crq_failed: + dma_unmap_single(dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL); +map_failed: + free_page((unsigned long)crq->msgs); + return retrc; +} + +/* debugfs for dump */ +static int ibmvnic_dump_show(struct seq_file *seq, void *v) +{ + struct net_device *netdev = seq->private; + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + struct device *dev = &adapter->vdev->dev; + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.request_dump_size.first = IBMVNIC_CRQ_CMD; + crq.request_dump_size.cmd = REQUEST_DUMP_SIZE; + ibmvnic_send_crq(adapter, &crq); + + init_completion(&adapter->fw_done); + wait_for_completion(&adapter->fw_done); + + seq_write(seq, adapter->dump_data, adapter->dump_data_size); + + dma_unmap_single(dev, adapter->dump_data_token, adapter->dump_data_size, + DMA_BIDIRECTIONAL); + + kfree(adapter->dump_data); + + return 0; +} + +static int ibmvnic_dump_open(struct inode *inode, struct file *file) +{ + return single_open(file, ibmvnic_dump_show, inode->i_private); +} + +static const struct file_operations ibmvnic_dump_ops = { + .owner = THIS_MODULE, + .open = ibmvnic_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) +{ + struct ibmvnic_adapter *adapter; + struct net_device *netdev; + unsigned char *mac_addr_p; + struct dentry *ent; + char buf[16]; /* debugfs name buf */ + int rc; + + dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n", + dev->unit_address); + + mac_addr_p = (unsigned char *)vio_get_attribute(dev, + VETH_MAC_ADDR, NULL); + if (!mac_addr_p) { + dev_err(&dev->dev, + "(%s:%3.3d) ERROR: Can't find MAC_ADDR attribute\n", + __FILE__, __LINE__); + return 0; + } + + netdev = alloc_etherdev_mq(sizeof(struct ibmvnic_adapter), + IBMVNIC_MAX_TX_QUEUES); + if (!netdev) + return -ENOMEM; + + adapter = netdev_priv(netdev); + dev_set_drvdata(&dev->dev, netdev); + adapter->vdev = dev; + adapter->netdev = netdev; + + ether_addr_copy(adapter->mac_addr, mac_addr_p); + ether_addr_copy(netdev->dev_addr, adapter->mac_addr); + netdev->irq = dev->irq; + netdev->netdev_ops = &ibmvnic_netdev_ops; + netdev->ethtool_ops = &ibmvnic_ethtool_ops; + SET_NETDEV_DEV(netdev, &dev->dev); + + spin_lock_init(&adapter->stats_lock); + + rc = ibmvnic_init_crq_queue(adapter); + if (rc) { + dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", rc); + goto free_netdev; + } + + INIT_LIST_HEAD(&adapter->errors); + INIT_LIST_HEAD(&adapter->inflight); + spin_lock_init(&adapter->error_list_lock); + spin_lock_init(&adapter->inflight_lock); + + adapter->stats_token = dma_map_single(&dev->dev, &adapter->stats, + sizeof(struct ibmvnic_statistics), + DMA_FROM_DEVICE); + if (dma_mapping_error(&dev->dev, adapter->stats_token)) { + if (!firmware_has_feature(FW_FEATURE_CMO)) + dev_err(&dev->dev, "Couldn't map stats buffer\n"); + goto free_crq; + } + + snprintf(buf, sizeof(buf), "ibmvnic_%x", dev->unit_address); + ent = debugfs_create_dir(buf, NULL); + if (!ent || IS_ERR(ent)) { + dev_info(&dev->dev, "debugfs create directory failed\n"); + adapter->debugfs_dir = NULL; + } else { + adapter->debugfs_dir = ent; + ent = debugfs_create_file("dump", S_IRUGO, adapter->debugfs_dir, + netdev, &ibmvnic_dump_ops); + if (!ent || IS_ERR(ent)) { + dev_info(&dev->dev, + "debugfs create dump file failed\n"); + adapter->debugfs_dump = NULL; + } else { + adapter->debugfs_dump = ent; + } + } + ibmvnic_send_crq_init(adapter); + + init_completion(&adapter->init_done); + wait_for_completion(&adapter->init_done); + + /* needed to pull init_sub_crqs outside of an interrupt context + * because it creates IRQ mappings for the subCRQ queues, causing + * a kernel warning + */ + init_sub_crqs(adapter, 0); + + reinit_completion(&adapter->init_done); + wait_for_completion(&adapter->init_done); + + /* if init_sub_crqs is partially successful, retry */ + while (!adapter->tx_scrq || !adapter->rx_scrq) { + init_sub_crqs(adapter, 1); + + reinit_completion(&adapter->init_done); + wait_for_completion(&adapter->init_done); + } + + netdev->real_num_tx_queues = adapter->req_tx_queues; + + rc = register_netdev(netdev); + if (rc) { + dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); + goto free_debugfs; + } + dev_info(&dev->dev, "ibmvnic registered\n"); + + return 0; + +free_debugfs: + if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) + debugfs_remove_recursive(adapter->debugfs_dir); +free_crq: + ibmvnic_release_crq_queue(adapter); +free_netdev: + free_netdev(netdev); + return rc; +} + +static int ibmvnic_remove(struct vio_dev *dev) +{ + struct net_device *netdev = dev_get_drvdata(&dev->dev); + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + unregister_netdev(netdev); + + release_sub_crqs(adapter); + + ibmvnic_release_crq_queue(adapter); + + if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) + debugfs_remove_recursive(adapter->debugfs_dir); + + if (adapter->ras_comps) + dma_free_coherent(&dev->dev, + adapter->ras_comp_num * + sizeof(struct ibmvnic_fw_component), + adapter->ras_comps, adapter->ras_comps_tok); + + kfree(adapter->ras_comp_int); + + free_netdev(netdev); + dev_set_drvdata(&dev->dev, NULL); + + return 0; +} + +static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev) +{ + struct net_device *netdev = dev_get_drvdata(&vdev->dev); + struct ibmvnic_adapter *adapter; + struct iommu_table *tbl; + unsigned long ret = 0; + int i; + + tbl = get_iommu_table_base(&vdev->dev); + + /* netdev inits at probe time along with the structures we need below*/ + if (!netdev) + return IOMMU_PAGE_ALIGN(IBMVNIC_IO_ENTITLEMENT_DEFAULT, tbl); + + adapter = netdev_priv(netdev); + + ret += PAGE_SIZE; /* the crq message queue */ + ret += adapter->bounce_buffer_size; + ret += IOMMU_PAGE_ALIGN(sizeof(struct ibmvnic_statistics), tbl); + + for (i = 0; i < adapter->req_tx_queues + adapter->req_rx_queues; i++) + ret += 4 * PAGE_SIZE; /* the scrq message queue */ + + for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + i++) + ret += adapter->rx_pool[i].size * + IOMMU_PAGE_ALIGN(adapter->rx_pool[i].buff_size, tbl); + + return ret; +} + +static int ibmvnic_resume(struct device *dev) +{ + struct net_device *netdev = dev_get_drvdata(dev); + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int i; + + /* kick the interrupt handlers just in case we lost an interrupt */ + for (i = 0; i < adapter->req_rx_queues; i++) + ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq, + adapter->rx_scrq[i]); + + return 0; +} + +static struct vio_device_id ibmvnic_device_table[] = { + {"network", "IBM,vnic"}, + {"", "" } +}; +MODULE_DEVICE_TABLE(vio, ibmvnic_device_table); + +static const struct dev_pm_ops ibmvnic_pm_ops = { + .resume = ibmvnic_resume +}; + +static struct vio_driver ibmvnic_driver = { + .id_table = ibmvnic_device_table, + .probe = ibmvnic_probe, + .remove = ibmvnic_remove, + .get_desired_dma = ibmvnic_get_desired_dma, + .name = ibmvnic_driver_name, + .pm = &ibmvnic_pm_ops, +}; + +/* module functions */ +static int __init ibmvnic_module_init(void) +{ + pr_info("%s: %s %s\n", ibmvnic_driver_name, ibmvnic_driver_string, + IBMVNIC_DRIVER_VERSION); + + return vio_register_driver(&ibmvnic_driver); +} + +static void __exit ibmvnic_module_exit(void) +{ + vio_unregister_driver(&ibmvnic_driver); +} + +module_init(ibmvnic_module_init); +module_exit(ibmvnic_module_exit); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h new file mode 100644 index 0000000000000..1242925ad34cb --- /dev/null +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -0,0 +1,1046 @@ +/**************************************************************************/ +/* */ +/* IBM System i and System p Virtual NIC Device Driver */ +/* Copyright (C) 2014 IBM Corp. */ +/* Santiago Leon (santi_leon@yahoo.com) */ +/* Thomas Falcon (tlfalcon@linux.vnet.ibm.com) */ +/* John Allen (jallen@linux.vnet.ibm.com) */ +/* */ +/* This program is free software; you can redistribute it and/or modify */ +/* it under the terms of the GNU General Public License as published by */ +/* the Free Software Foundation; either version 2 of the License, or */ +/* (at your option) any later version. */ +/* */ +/* This program is distributed in the hope that it will be useful, */ +/* but WITHOUT ANY WARRANTY; without even the implied warranty of */ +/* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the */ +/* GNU General Public License for more details. */ +/* */ +/* You should have received a copy of the GNU General Public License */ +/* along with this program. */ +/* */ +/* This module contains the implementation of a virtual ethernet device */ +/* for use with IBM i/pSeries LPAR Linux. It utilizes the logical LAN */ +/* option of the RS/6000 Platform Architecture to interface with virtual */ +/* ethernet NICs that are presented to the partition by the hypervisor. */ +/* */ +/**************************************************************************/ + +#define IBMVNIC_NAME "ibmvnic" +#define IBMVNIC_DRIVER_VERSION "1.0" +#define IBMVNIC_INVALID_MAP -1 +#define IBMVNIC_STATS_TIMEOUT 1 +/* basic structures plus 100 2k buffers */ +#define IBMVNIC_IO_ENTITLEMENT_DEFAULT 610305 + +/* Initial module_parameters */ +#define IBMVNIC_RX_WEIGHT 16 +/* when changing this, update IBMVNIC_IO_ENTITLEMENT_DEFAULT */ +#define IBMVNIC_BUFFS_PER_POOL 100 +#define IBMVNIC_MAX_TX_QUEUES 5 + +struct ibmvnic_login_buffer { + __be32 len; + __be32 version; +#define INITIAL_VERSION_LB 1 + __be32 num_txcomp_subcrqs; + __be32 off_txcomp_subcrqs; + __be32 num_rxcomp_subcrqs; + __be32 off_rxcomp_subcrqs; + __be32 login_rsp_ioba; + __be32 login_rsp_len; +} __packed __aligned(8); + +struct ibmvnic_login_rsp_buffer { + __be32 len; + __be32 version; +#define INITIAL_VERSION_LRB 1 + __be32 num_txsubm_subcrqs; + __be32 off_txsubm_subcrqs; + __be32 num_rxadd_subcrqs; + __be32 off_rxadd_subcrqs; + __be32 off_rxadd_buff_size; + __be32 num_supp_tx_desc; + __be32 off_supp_tx_desc; +} __packed __aligned(8); + +struct ibmvnic_query_ip_offload_buffer { + __be32 len; + __be32 version; +#define INITIAL_VERSION_IOB 1 + u8 ipv4_chksum; + u8 ipv6_chksum; + u8 tcp_ipv4_chksum; + u8 tcp_ipv6_chksum; + u8 udp_ipv4_chksum; + u8 udp_ipv6_chksum; + u8 large_tx_ipv4; + u8 large_tx_ipv6; + u8 large_rx_ipv4; + u8 large_rx_ipv6; + u8 reserved1[14]; + __be16 max_ipv4_header_size; + __be16 max_ipv6_header_size; + __be16 max_tcp_header_size; + __be16 max_udp_header_size; + __be32 max_large_tx_size; + __be32 max_large_rx_size; + u8 reserved2[16]; + u8 ipv6_extension_header; +#define IPV6_EH_NOT_SUPPORTED 0x00 +#define IPV6_EH_SUPPORTED_LIM 0x01 +#define IPV6_EH_SUPPORTED 0xFF + u8 tcp_pseudosum_req; +#define TCP_PS_NOT_REQUIRED 0x00 +#define TCP_PS_REQUIRED 0x01 + u8 reserved3[30]; + __be16 num_ipv6_ext_headers; + __be32 off_ipv6_ext_headers; + u8 reserved4[154]; +} __packed __aligned(8); + +struct ibmvnic_control_ip_offload_buffer { + __be32 len; + __be32 version; +#define INITIAL_VERSION_IOB 1 + u8 ipv4_chksum; + u8 ipv6_chksum; + u8 tcp_ipv4_chksum; + u8 tcp_ipv6_chksum; + u8 udp_ipv4_chksum; + u8 udp_ipv6_chksum; + u8 large_tx_ipv4; + u8 large_tx_ipv6; + u8 bad_packet_rx; + u8 large_rx_ipv4; + u8 large_rx_ipv6; + u8 reserved4[111]; +} __packed __aligned(8); + +struct ibmvnic_fw_component { + u8 name[48]; + __be32 trace_buff_size; + u8 correlator; + u8 trace_level; + u8 parent_correlator; + u8 error_check_level; + u8 trace_on; + u8 reserved[7]; + u8 description[192]; +} __packed __aligned(8); + +struct ibmvnic_fw_trace_entry { + __be32 trace_id; + u8 num_valid_data; + u8 reserved[3]; + __be64 pmc_registers; + __be64 timebase; + __be64 trace_data[5]; +} __packed __aligned(8); + +struct ibmvnic_statistics { + __be32 version; + __be32 promiscuous; + __be64 rx_packets; + __be64 rx_bytes; + __be64 tx_packets; + __be64 tx_bytes; + __be64 ucast_tx_packets; + __be64 ucast_rx_packets; + __be64 mcast_tx_packets; + __be64 mcast_rx_packets; + __be64 bcast_tx_packets; + __be64 bcast_rx_packets; + __be64 align_errors; + __be64 fcs_errors; + __be64 single_collision_frames; + __be64 multi_collision_frames; + __be64 sqe_test_errors; + __be64 deferred_tx; + __be64 late_collisions; + __be64 excess_collisions; + __be64 internal_mac_tx_errors; + __be64 carrier_sense; + __be64 too_long_frames; + __be64 internal_mac_rx_errors; + u8 reserved[72]; +} __packed __aligned(8); + +struct ibmvnic_acl_buffer { + __be32 len; + __be32 version; +#define INITIAL_VERSION_IOB 1 + u8 mac_acls_restrict; + u8 vlan_acls_restrict; + u8 reserved1[22]; + __be32 num_mac_addrs; + __be32 offset_mac_addrs; + __be32 num_vlan_ids; + __be32 offset_vlan_ids; + u8 reserved2[80]; +} __packed __aligned(8); + +/* descriptors have been changed, how should this be defined? 1? 4? */ + +#define IBMVNIC_TX_DESC_VERSIONS 3 + +/* is this still needed? */ +struct ibmvnic_tx_comp_desc { + u8 first; + u8 num_comps; + __be16 rcs[5]; + __be32 correlators[5]; +} __packed __aligned(8); + +/* some flags that included in v0 descriptor, which is gone + * only used for IBMVNIC_TCP_CHKSUM and IBMVNIC_UDP_CHKSUM + * and only in some offload_flags variable that doesn't seem + * to be used anywhere, can probably be removed? + */ + +#define IBMVNIC_TCP_CHKSUM 0x20 +#define IBMVNIC_UDP_CHKSUM 0x08 + +#define IBMVNIC_MAX_FRAGS_PER_CRQ 3 + +struct ibmvnic_tx_desc { + u8 first; + u8 type; + +#define IBMVNIC_TX_DESC 0x10 + u8 n_crq_elem; + u8 n_sge; + u8 flags1; +#define IBMVNIC_TX_COMP_NEEDED 0x80 +#define IBMVNIC_TX_CHKSUM_OFFLOAD 0x40 +#define IBMVNIC_TX_LSO 0x20 +#define IBMVNIC_TX_PROT_TCP 0x10 +#define IBMVNIC_TX_PROT_UDP 0x08 +#define IBMVNIC_TX_PROT_IPV4 0x04 +#define IBMVNIC_TX_PROT_IPV6 0x02 +#define IBMVNIC_TX_VLAN_PRESENT 0x01 + u8 flags2; +#define IBMVNIC_TX_VLAN_INSERT 0x80 + __be16 mss; + u8 reserved[4]; + __be32 correlator; + __be16 vlan_id; + __be16 dma_reg; + __be32 sge_len; + __be64 ioba; +} __packed __aligned(8); + +struct ibmvnic_hdr_desc { + u8 first; + u8 type; +#define IBMVNIC_HDR_DESC 0x11 + u8 len; + u8 l2_len; + __be16 l3_len; + u8 l4_len; + u8 flag; + u8 data[24]; +} __packed __aligned(8); + +struct ibmvnic_hdr_ext_desc { + u8 first; + u8 type; +#define IBMVNIC_HDR_EXT_DESC 0x12 + u8 len; + u8 data[29]; +} __packed __aligned(8); + +struct ibmvnic_sge_desc { + u8 first; + u8 type; +#define IBMVNIC_SGE_DESC 0x30 + __be16 sge1_dma_reg; + __be32 sge1_len; + __be64 sge1_ioba; + __be16 reserved; + __be16 sge2_dma_reg; + __be32 sge2_len; + __be64 sge2_ioba; +} __packed __aligned(8); + +struct ibmvnic_rx_comp_desc { + u8 first; + u8 flags; +#define IBMVNIC_IP_CHKSUM_GOOD 0x80 +#define IBMVNIC_TCP_UDP_CHKSUM_GOOD 0x40 +#define IBMVNIC_END_FRAME 0x20 +#define IBMVNIC_EXACT_MC 0x10 +#define IBMVNIC_VLAN_STRIPPED 0x08 + __be16 off_frame_data; + __be32 len; + __be64 correlator; + __be16 vlan_tci; + __be16 rc; + u8 reserved[12]; +} __packed __aligned(8); + +struct ibmvnic_generic_scrq { + u8 first; + u8 reserved[31]; +} __packed __aligned(8); + +struct ibmvnic_rx_buff_add_desc { + u8 first; + u8 reserved[7]; + __be64 correlator; + __be32 ioba; + u8 map_id; + __be32 len:24; + u8 reserved2[8]; +} __packed __aligned(8); + +struct ibmvnic_rc { + u8 code; /* one of enum ibmvnic_rc_codes */ + u8 detailed_data[3]; +} __packed __aligned(4); + +struct ibmvnic_generic_crq { + u8 first; + u8 cmd; + u8 params[10]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_version_exchange { + u8 first; + u8 cmd; + __be16 version; +#define IBMVNIC_INITIAL_VERSION 1 + u8 reserved[8]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_capability { + u8 first; + u8 cmd; + __be16 capability; /* one of ibmvnic_capabilities */ + struct ibmvnic_rc rc; + __be32 number; /*FIX: should be __be64, but I'm getting the least + * significant word first + */ +} __packed __aligned(8); + +struct ibmvnic_login { + u8 first; + u8 cmd; + u8 reserved[6]; + __be32 ioba; + __be32 len; +} __packed __aligned(8); + +struct ibmvnic_phys_parms { + u8 first; + u8 cmd; + u8 flags1; +#define IBMVNIC_EXTERNAL_LOOPBACK 0x80 +#define IBMVNIC_INTERNAL_LOOPBACK 0x40 +#define IBMVNIC_PROMISC 0x20 +#define IBMVNIC_PHYS_LINK_ACTIVE 0x10 +#define IBMVNIC_AUTONEG_DUPLEX 0x08 +#define IBMVNIC_FULL_DUPLEX 0x04 +#define IBMVNIC_HALF_DUPLEX 0x02 +#define IBMVNIC_CAN_CHG_PHYS_PARMS 0x01 + u8 flags2; +#define IBMVNIC_LOGICAL_LNK_ACTIVE 0x80 + __be32 speed; +#define IBMVNIC_AUTONEG 0x80 +#define IBMVNIC_10MBPS 0x40 +#define IBMVNIC_100MBPS 0x20 +#define IBMVNIC_1GBPS 0x10 +#define IBMVNIC_10GBPS 0x08 + __be32 mtu; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_logical_link_state { + u8 first; + u8 cmd; + u8 link_state; +#define IBMVNIC_LOGICAL_LNK_DN 0x00 +#define IBMVNIC_LOGICAL_LNK_UP 0x01 +#define IBMVNIC_LOGICAL_LNK_QUERY 0xff + u8 reserved[9]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_query_ip_offload { + u8 first; + u8 cmd; + u8 reserved[2]; + __be32 len; + __be32 ioba; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_control_ip_offload { + u8 first; + u8 cmd; + u8 reserved[2]; + __be32 ioba; + __be32 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_request_dump_size { + u8 first; + u8 cmd; + u8 reserved[6]; + __be32 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_request_dump { + u8 first; + u8 cmd; + u8 reserved1[2]; + __be32 ioba; + __be32 len; + u8 reserved2[4]; +} __packed __aligned(8); + +struct ibmvnic_request_dump_rsp { + u8 first; + u8 cmd; + u8 reserved[6]; + __be32 dumped_len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_request_ras_comp_num { + u8 first; + u8 cmd; + u8 reserved1[2]; + __be32 num_components; + u8 reserved2[4]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_request_ras_comps { + u8 first; + u8 cmd; + u8 reserved[2]; + __be32 ioba; + __be32 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_control_ras { + u8 first; + u8 cmd; + u8 correlator; + u8 level; + u8 op; +#define IBMVNIC_TRACE_LEVEL 1 +#define IBMVNIC_ERROR_LEVEL 2 +#define IBMVNIC_TRACE_PAUSE 3 +#define IBMVNIC_TRACE_RESUME 4 +#define IBMVNIC_TRACE_ON 5 +#define IBMVNIC_TRACE_OFF 6 +#define IBMVNIC_CHG_TRACE_BUFF_SZ 7 + u8 trace_buff_sz[3]; + u8 reserved[4]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_collect_fw_trace { + u8 first; + u8 cmd; + u8 correlator; + u8 reserved; + __be32 ioba; + __be32 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_request_statistics { + u8 first; + u8 cmd; + u8 flags; +#define IBMVNIC_PHYSICAL_PORT 0x80 + u8 reserved1; + __be32 ioba; + __be32 len; + u8 reserved[4]; +} __packed __aligned(8); + +struct ibmvnic_request_debug_stats { + u8 first; + u8 cmd; + u8 reserved[2]; + __be32 ioba; + __be32 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_error_indication { + u8 first; + u8 cmd; + u8 flags; +#define IBMVNIC_FATAL_ERROR 0x80 + u8 reserved1; + __be32 error_id; + __be32 detail_error_sz; + __be16 error_cause; + u8 reserved2[2]; +} __packed __aligned(8); + +struct ibmvnic_request_error_info { + u8 first; + u8 cmd; + u8 reserved[2]; + __be32 ioba; + __be32 len; + __be32 error_id; +} __packed __aligned(8); + +struct ibmvnic_request_error_rsp { + u8 first; + u8 cmd; + u8 reserved[2]; + __be32 error_id; + __be32 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_link_state_indication { + u8 first; + u8 cmd; + u8 reserved1[2]; + u8 phys_link_state; + u8 logical_link_state; + u8 reserved2[10]; +} __packed __aligned(8); + +struct ibmvnic_change_mac_addr { + u8 first; + u8 cmd; + u8 mac_addr[6]; + struct ibmvnic_rc rc; + u8 reserved[4]; +} __packed __aligned(8); + +struct ibmvnic_multicast_ctrl { + u8 first; + u8 cmd; + u8 mac_addr[6]; + u8 flags; +#define IBMVNIC_ENABLE_MC 0x80 +#define IBMVNIC_DISABLE_MC 0x40 +#define IBMVNIC_ENABLE_ALL 0x20 +#define IBMVNIC_DISABLE_ALL 0x10 + u8 reserved1; + __be16 reserved2; /* was num_enabled_mc_addr; */ + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_get_vpd_size_rsp { + u8 first; + u8 cmd; + u8 reserved[2]; + __be64 len; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_get_vpd { + u8 first; + u8 cmd; + u8 reserved1[2]; + __be32 ioba; + __be32 len; + u8 reserved[4]; +} __packed __aligned(8); + +struct ibmvnic_acl_change_indication { + u8 first; + u8 cmd; + __be16 change_type; +#define IBMVNIC_MAC_ACL 0 +#define IBMVNIC_VLAN_ACL 1 + u8 reserved[12]; +} __packed __aligned(8); + +struct ibmvnic_acl_query { + u8 first; + u8 cmd; + u8 reserved1[2]; + __be32 ioba; + __be32 len; + u8 reserved2[4]; +} __packed __aligned(8); + +struct ibmvnic_tune { + u8 first; + u8 cmd; + u8 reserved1[2]; + __be32 ioba; + __be32 len; + u8 reserved2[4]; +} __packed __aligned(8); + +struct ibmvnic_request_map { + u8 first; + u8 cmd; + u8 reserved1; + u8 map_id; + __be32 ioba; + __be32 len; + u8 reserved2[4]; +} __packed __aligned(8); + +struct ibmvnic_request_map_rsp { + u8 first; + u8 cmd; + u8 reserved1; + u8 map_id; + u8 reserved2[4]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_request_unmap { + u8 first; + u8 cmd; + u8 reserved1; + u8 map_id; + u8 reserved2[12]; +} __packed __aligned(8); + +struct ibmvnic_request_unmap_rsp { + u8 first; + u8 cmd; + u8 reserved1; + u8 map_id; + u8 reserved2[8]; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +struct ibmvnic_query_map { + u8 first; + u8 cmd; + u8 reserved[14]; +} __packed __aligned(8); + +struct ibmvnic_query_map_rsp { + u8 first; + u8 cmd; + u8 reserved; + u8 page_size; + __be32 tot_pages; + __be32 free_pages; + struct ibmvnic_rc rc; +} __packed __aligned(8); + +union ibmvnic_crq { + struct ibmvnic_generic_crq generic; + struct ibmvnic_version_exchange version_exchange; + struct ibmvnic_version_exchange version_exchange_rsp; + struct ibmvnic_capability query_capability; + struct ibmvnic_capability query_capability_rsp; + struct ibmvnic_capability request_capability; + struct ibmvnic_capability request_capability_rsp; + struct ibmvnic_login login; + struct ibmvnic_generic_crq login_rsp; + struct ibmvnic_phys_parms query_phys_parms; + struct ibmvnic_phys_parms query_phys_parms_rsp; + struct ibmvnic_phys_parms query_phys_capabilities; + struct ibmvnic_phys_parms query_phys_capabilities_rsp; + struct ibmvnic_phys_parms set_phys_parms; + struct ibmvnic_phys_parms set_phys_parms_rsp; + struct ibmvnic_logical_link_state logical_link_state; + struct ibmvnic_logical_link_state logical_link_state_rsp; + struct ibmvnic_query_ip_offload query_ip_offload; + struct ibmvnic_query_ip_offload query_ip_offload_rsp; + struct ibmvnic_control_ip_offload control_ip_offload; + struct ibmvnic_control_ip_offload control_ip_offload_rsp; + struct ibmvnic_request_dump_size request_dump_size; + struct ibmvnic_request_dump_size request_dump_size_rsp; + struct ibmvnic_request_dump request_dump; + struct ibmvnic_request_dump_rsp request_dump_rsp; + struct ibmvnic_request_ras_comp_num request_ras_comp_num; + struct ibmvnic_request_ras_comp_num request_ras_comp_num_rsp; + struct ibmvnic_request_ras_comps request_ras_comps; + struct ibmvnic_request_ras_comps request_ras_comps_rsp; + struct ibmvnic_control_ras control_ras; + struct ibmvnic_control_ras control_ras_rsp; + struct ibmvnic_collect_fw_trace collect_fw_trace; + struct ibmvnic_collect_fw_trace collect_fw_trace_rsp; + struct ibmvnic_request_statistics request_statistics; + struct ibmvnic_generic_crq request_statistics_rsp; + struct ibmvnic_request_debug_stats request_debug_stats; + struct ibmvnic_request_debug_stats request_debug_stats_rsp; + struct ibmvnic_error_indication error_indication; + struct ibmvnic_request_error_info request_error_info; + struct ibmvnic_request_error_rsp request_error_rsp; + struct ibmvnic_link_state_indication link_state_indication; + struct ibmvnic_change_mac_addr change_mac_addr; + struct ibmvnic_change_mac_addr change_mac_addr_rsp; + struct ibmvnic_multicast_ctrl multicast_ctrl; + struct ibmvnic_multicast_ctrl multicast_ctrl_rsp; + struct ibmvnic_generic_crq get_vpd_size; + struct ibmvnic_get_vpd_size_rsp get_vpd_size_rsp; + struct ibmvnic_get_vpd get_vpd; + struct ibmvnic_generic_crq get_vpd_rsp; + struct ibmvnic_acl_change_indication acl_change_indication; + struct ibmvnic_acl_query acl_query; + struct ibmvnic_generic_crq acl_query_rsp; + struct ibmvnic_tune tune; + struct ibmvnic_generic_crq tune_rsp; + struct ibmvnic_request_map request_map; + struct ibmvnic_request_map_rsp request_map_rsp; + struct ibmvnic_request_unmap request_unmap; + struct ibmvnic_request_unmap_rsp request_unmap_rsp; + struct ibmvnic_query_map query_map; + struct ibmvnic_query_map_rsp query_map_rsp; +}; + +enum ibmvnic_rc_codes { + SUCCESS = 0, + PARTIALSUCCESS = 1, + PERMISSION = 2, + NOMEMORY = 3, + PARAMETER = 4, + UNKNOWNCOMMAND = 5, + ABORTED = 6, + INVALIDSTATE = 7, + INVALIDIOBA = 8, + INVALIDLENGTH = 9, + UNSUPPORTEDOPTION = 10, +}; + +enum ibmvnic_capabilities { + MIN_TX_QUEUES = 1, + MIN_RX_QUEUES = 2, + MIN_RX_ADD_QUEUES = 3, + MAX_TX_QUEUES = 4, + MAX_RX_QUEUES = 5, + MAX_RX_ADD_QUEUES = 6, + REQ_TX_QUEUES = 7, + REQ_RX_QUEUES = 8, + REQ_RX_ADD_QUEUES = 9, + MIN_TX_ENTRIES_PER_SUBCRQ = 10, + MIN_RX_ADD_ENTRIES_PER_SUBCRQ = 11, + MAX_TX_ENTRIES_PER_SUBCRQ = 12, + MAX_RX_ADD_ENTRIES_PER_SUBCRQ = 13, + REQ_TX_ENTRIES_PER_SUBCRQ = 14, + REQ_RX_ADD_ENTRIES_PER_SUBCRQ = 15, + TCP_IP_OFFLOAD = 16, + PROMISC_REQUESTED = 17, + PROMISC_SUPPORTED = 18, + MIN_MTU = 19, + MAX_MTU = 20, + REQ_MTU = 21, + MAX_MULTICAST_FILTERS = 22, + VLAN_HEADER_INSERTION = 23, + MAX_TX_SG_ENTRIES = 25, + RX_SG_SUPPORTED = 26, + RX_SG_REQUESTED = 27, + OPT_TX_COMP_SUB_QUEUES = 28, + OPT_RX_COMP_QUEUES = 29, + OPT_RX_BUFADD_Q_PER_RX_COMP_Q = 30, + OPT_TX_ENTRIES_PER_SUBCRQ = 31, + OPT_RXBA_ENTRIES_PER_SUBCRQ = 32, + TX_RX_DESC_REQ = 33, +}; + +enum ibmvnic_error_cause { + ADAPTER_PROBLEM = 0, + BUS_PROBLEM = 1, + FW_PROBLEM = 2, + DD_PROBLEM = 3, + EEH_RECOVERY = 4, + FW_UPDATED = 5, + LOW_MEMORY = 6, +}; + +enum ibmvnic_commands { + VERSION_EXCHANGE = 0x01, + VERSION_EXCHANGE_RSP = 0x81, + QUERY_CAPABILITY = 0x02, + QUERY_CAPABILITY_RSP = 0x82, + REQUEST_CAPABILITY = 0x03, + REQUEST_CAPABILITY_RSP = 0x83, + LOGIN = 0x04, + LOGIN_RSP = 0x84, + QUERY_PHYS_PARMS = 0x05, + QUERY_PHYS_PARMS_RSP = 0x85, + QUERY_PHYS_CAPABILITIES = 0x06, + QUERY_PHYS_CAPABILITIES_RSP = 0x86, + SET_PHYS_PARMS = 0x07, + SET_PHYS_PARMS_RSP = 0x87, + ERROR_INDICATION = 0x08, + REQUEST_ERROR_INFO = 0x09, + REQUEST_ERROR_RSP = 0x89, + REQUEST_DUMP_SIZE = 0x0A, + REQUEST_DUMP_SIZE_RSP = 0x8A, + REQUEST_DUMP = 0x0B, + REQUEST_DUMP_RSP = 0x8B, + LOGICAL_LINK_STATE = 0x0C, + LOGICAL_LINK_STATE_RSP = 0x8C, + REQUEST_STATISTICS = 0x0D, + REQUEST_STATISTICS_RSP = 0x8D, + REQUEST_RAS_COMP_NUM = 0x0E, + REQUEST_RAS_COMP_NUM_RSP = 0x8E, + REQUEST_RAS_COMPS = 0x0F, + REQUEST_RAS_COMPS_RSP = 0x8F, + CONTROL_RAS = 0x10, + CONTROL_RAS_RSP = 0x90, + COLLECT_FW_TRACE = 0x11, + COLLECT_FW_TRACE_RSP = 0x91, + LINK_STATE_INDICATION = 0x12, + CHANGE_MAC_ADDR = 0x13, + CHANGE_MAC_ADDR_RSP = 0x93, + MULTICAST_CTRL = 0x14, + MULTICAST_CTRL_RSP = 0x94, + GET_VPD_SIZE = 0x15, + GET_VPD_SIZE_RSP = 0x95, + GET_VPD = 0x16, + GET_VPD_RSP = 0x96, + TUNE = 0x17, + TUNE_RSP = 0x97, + QUERY_IP_OFFLOAD = 0x18, + QUERY_IP_OFFLOAD_RSP = 0x98, + CONTROL_IP_OFFLOAD = 0x19, + CONTROL_IP_OFFLOAD_RSP = 0x99, + ACL_CHANGE_INDICATION = 0x1A, + ACL_QUERY = 0x1B, + ACL_QUERY_RSP = 0x9B, + REQUEST_DEBUG_STATS = 0x1C, + REQUEST_DEBUG_STATS_RSP = 0x9C, + QUERY_MAP = 0x1D, + QUERY_MAP_RSP = 0x9D, + REQUEST_MAP = 0x1E, + REQUEST_MAP_RSP = 0x9E, + REQUEST_UNMAP = 0x1F, + REQUEST_UNMAP_RSP = 0x9F, + VLAN_CTRL = 0x20, + VLAN_CTRL_RSP = 0xA0, +}; + +enum ibmvnic_crq_type { + IBMVNIC_CRQ_CMD = 0x80, + IBMVNIC_CRQ_CMD_RSP = 0x80, + IBMVNIC_CRQ_INIT_CMD = 0xC0, + IBMVNIC_CRQ_INIT_RSP = 0xC0, + IBMVNIC_CRQ_XPORT_EVENT = 0xFF, +}; + +enum ibmvfc_crq_format { + IBMVNIC_CRQ_INIT = 0x01, + IBMVNIC_CRQ_INIT_COMPLETE = 0x02, + IBMVNIC_PARTITION_MIGRATED = 0x06, +}; + +struct ibmvnic_crq_queue { + union ibmvnic_crq *msgs; + int size, cur; + dma_addr_t msg_token; + spinlock_t lock; +}; + +union sub_crq { + struct ibmvnic_generic_scrq generic; + struct ibmvnic_tx_comp_desc tx_comp; + struct ibmvnic_tx_desc v1; + struct ibmvnic_hdr_desc hdr; + struct ibmvnic_hdr_ext_desc hdr_ext; + struct ibmvnic_sge_desc sge; + struct ibmvnic_rx_comp_desc rx_comp; + struct ibmvnic_rx_buff_add_desc rx_add; +}; + +struct ibmvnic_sub_crq_queue { + union sub_crq *msgs; + int size, cur; + dma_addr_t msg_token; + unsigned long crq_num; + unsigned long hw_irq; + unsigned int irq; + unsigned int pool_index; + int scrq_num; + spinlock_t lock; + struct sk_buff *rx_skb_top; + struct ibmvnic_adapter *adapter; +}; + +struct ibmvnic_long_term_buff { + unsigned char *buff; + dma_addr_t addr; + u64 size; + u8 map_id; +}; + +struct ibmvnic_tx_buff { + struct sk_buff *skb; + dma_addr_t data_dma[IBMVNIC_MAX_FRAGS_PER_CRQ]; + unsigned int data_len[IBMVNIC_MAX_FRAGS_PER_CRQ]; + int index; + int pool_index; + bool last_frag; + bool used_bounce; +}; + +struct ibmvnic_tx_pool { + struct ibmvnic_tx_buff *tx_buff; + int *free_map; + int consumer_index; + int producer_index; + wait_queue_head_t ibmvnic_tx_comp_q; + struct task_struct *work_thread; + struct ibmvnic_long_term_buff long_term_buff; +}; + +struct ibmvnic_rx_buff { + struct sk_buff *skb; + dma_addr_t dma; + unsigned char *data; + int size; + int pool_index; +}; + +struct ibmvnic_rx_pool { + struct ibmvnic_rx_buff *rx_buff; + int size; + int index; + int buff_size; + atomic_t available; + int *free_map; + int next_free; + int next_alloc; + int active; + struct ibmvnic_long_term_buff long_term_buff; +}; + +struct ibmvnic_error_buff { + char *buff; + dma_addr_t dma; + int len; + struct list_head list; + __be32 error_id; +}; + +struct ibmvnic_fw_comp_internal { + struct ibmvnic_adapter *adapter; + int num; + struct debugfs_blob_wrapper desc_blob; + int paused; +}; + +struct ibmvnic_inflight_cmd { + union ibmvnic_crq crq; + struct list_head list; +}; + +struct ibmvnic_adapter { + struct vio_dev *vdev; + struct net_device *netdev; + struct ibmvnic_crq_queue crq; + u8 mac_addr[ETH_ALEN]; + struct ibmvnic_query_ip_offload_buffer ip_offload_buf; + dma_addr_t ip_offload_tok; + struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl; + dma_addr_t ip_offload_ctrl_tok; + bool migrated; + u32 msg_enable; + void *bounce_buffer; + int bounce_buffer_size; + dma_addr_t bounce_buffer_dma; + + /* Statistics */ + struct net_device_stats net_stats; + struct ibmvnic_statistics stats; + dma_addr_t stats_token; + struct completion stats_done; + spinlock_t stats_lock; + int replenish_no_mem; + int replenish_add_buff_success; + int replenish_add_buff_failure; + int replenish_task_cycles; + int tx_send_failed; + int tx_map_failed; + + int phys_link_state; + int logical_link_state; + + /* login data */ + struct ibmvnic_login_buffer *login_buf; + dma_addr_t login_buf_token; + int login_buf_sz; + + struct ibmvnic_login_rsp_buffer *login_rsp_buf; + dma_addr_t login_rsp_buf_token; + int login_rsp_buf_sz; + + atomic_t running_cap_queries; + + struct ibmvnic_sub_crq_queue **tx_scrq; + struct ibmvnic_sub_crq_queue **rx_scrq; + int requested_caps; + + /* rx structs */ + struct napi_struct *napi; + struct ibmvnic_rx_pool *rx_pool; + u64 promisc; + + struct ibmvnic_tx_pool *tx_pool; + bool closing; + struct completion init_done; + + struct list_head errors; + spinlock_t error_list_lock; + + /* debugfs */ + struct dentry *debugfs_dir; + struct dentry *debugfs_dump; + struct completion fw_done; + char *dump_data; + dma_addr_t dump_data_token; + int dump_data_size; + int ras_comp_num; + struct ibmvnic_fw_component *ras_comps; + struct ibmvnic_fw_comp_internal *ras_comp_int; + dma_addr_t ras_comps_tok; + struct dentry *ras_comps_ent; + + /* in-flight commands that allocate and/or map memory*/ + struct list_head inflight; + spinlock_t inflight_lock; + + /* partner capabilities */ + u64 min_tx_queues; + u64 min_rx_queues; + u64 min_rx_add_queues; + u64 max_tx_queues; + u64 max_rx_queues; + u64 max_rx_add_queues; + u64 req_tx_queues; + u64 req_rx_queues; + u64 req_rx_add_queues; + u64 min_tx_entries_per_subcrq; + u64 min_rx_add_entries_per_subcrq; + u64 max_tx_entries_per_subcrq; + u64 max_rx_add_entries_per_subcrq; + u64 req_tx_entries_per_subcrq; + u64 req_rx_add_entries_per_subcrq; + u64 tcp_ip_offload; + u64 promisc_requested; + u64 promisc_supported; + u64 min_mtu; + u64 max_mtu; + u64 req_mtu; + u64 max_multicast_filters; + u64 vlan_header_insertion; + u64 max_tx_sg_entries; + u64 rx_sg_supported; + u64 rx_sg_requested; + u64 opt_tx_comp_sub_queues; + u64 opt_rx_comp_queues; + u64 opt_rx_bufadd_q_per_rx_comp_q; + u64 opt_tx_entries_per_subcrq; + u64 opt_rxba_entries_per_subcrq; + __be64 tx_rx_desc_req; + u8 map_id; +}; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 4163b16489b35..fa593dd3efe12 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -280,6 +280,16 @@ config I40E_VXLAN Say Y here if you want to use Virtual eXtensible Local Area Network (VXLAN) in the driver. +config I40E_GENEVE + bool "Generic Network Virtualization Encapsulation (GENEVE) Support" + depends on I40E && GENEVE && !(I40E=y && GENEVE=m) + default n + ---help--- + This allows one to create GENEVE virtual interfaces that provide + Layer 2 Networks over Layer 3 Networks. GENEVE is often used + to tunnel virtual network infrastructure in virtualized environments. + Say Y here if you want to use GENEVE in the driver. + config I40E_DCB bool "Data Center Bridging (DCB) Support" default n diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h index 69707108d23cd..98fe5a2cd6e3e 100644 --- a/drivers/net/ethernet/intel/e1000/e1000.h +++ b/drivers/net/ethernet/intel/e1000/e1000.h @@ -213,8 +213,11 @@ struct e1000_rx_ring { }; #define E1000_DESC_UNUSED(R) \ - ((((R)->next_to_clean > (R)->next_to_use) \ - ? 0 : (R)->count) + (R)->next_to_clean - (R)->next_to_use - 1) +({ \ + unsigned int clean = smp_load_acquire(&(R)->next_to_clean); \ + unsigned int use = READ_ONCE((R)->next_to_use); \ + (clean > use ? 0 : (R)->count) + clean - use - 1; \ +}) #define E1000_RX_DESC_EXT(R, i) \ (&(((union e1000_rx_desc_extended *)((R).desc))[i])) diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index b1af0d613caab..8172cf08cc330 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -1,5 +1,5 @@ /******************************************************************************* - +* Intel PRO/1000 Linux driver Copyright(c) 1999 - 2006 Intel Corporation. @@ -106,7 +106,7 @@ u16 e1000_igp_cable_length_table[IGP01E1000_AGC_LENGTH_TABLE_SIZE] = { 120, 120 }; -static DEFINE_SPINLOCK(e1000_eeprom_lock); +static DEFINE_MUTEX(e1000_eeprom_lock); static DEFINE_SPINLOCK(e1000_phy_lock); /** @@ -624,8 +624,8 @@ s32 e1000_init_hw(struct e1000_hw *hw) /* Workaround for PCI-X problem when BIOS sets MMRBC * incorrectly. */ - if (hw->bus_type == e1000_bus_type_pcix - && e1000_pcix_get_mmrbc(hw) > 2048) + if (hw->bus_type == e1000_bus_type_pcix && + e1000_pcix_get_mmrbc(hw) > 2048) e1000_pcix_set_mmrbc(hw, 2048); break; } @@ -683,10 +683,9 @@ static s32 e1000_adjust_serdes_amplitude(struct e1000_hw *hw) } ret_val = e1000_read_eeprom(hw, EEPROM_SERDES_AMPLITUDE, 1, - &eeprom_data); - if (ret_val) { + &eeprom_data); + if (ret_val) return ret_val; - } if (eeprom_data != EEPROM_RESERVED_WORD) { /* Adjust SERDES output amplitude only. */ @@ -1074,8 +1073,8 @@ static s32 e1000_copper_link_preconfig(struct e1000_hw *hw) if (hw->mac_type <= e1000_82543 || hw->mac_type == e1000_82541 || hw->mac_type == e1000_82547 || - hw->mac_type == e1000_82541_rev_2 - || hw->mac_type == e1000_82547_rev_2) + hw->mac_type == e1000_82541_rev_2 || + hw->mac_type == e1000_82547_rev_2) hw->phy_reset_disable = false; return E1000_SUCCESS; @@ -1652,7 +1651,7 @@ s32 e1000_phy_setup_autoneg(struct e1000_hw *hw) mii_1000t_ctrl_reg = 0; } else { ret_val = e1000_write_phy_reg(hw, PHY_1000T_CTRL, - mii_1000t_ctrl_reg); + mii_1000t_ctrl_reg); if (ret_val) return ret_val; } @@ -1881,10 +1880,11 @@ static s32 e1000_phy_force_speed_duplex(struct e1000_hw *hw) if (ret_val) return ret_val; - if ((hw->mac_type == e1000_82544 || hw->mac_type == e1000_82543) - && (!hw->autoneg) - && (hw->forced_speed_duplex == e1000_10_full - || hw->forced_speed_duplex == e1000_10_half)) { + if ((hw->mac_type == e1000_82544 || + hw->mac_type == e1000_82543) && + (!hw->autoneg) && + (hw->forced_speed_duplex == e1000_10_full || + hw->forced_speed_duplex == e1000_10_half)) { ret_val = e1000_polarity_reversal_workaround(hw); if (ret_val) return ret_val; @@ -2084,11 +2084,12 @@ static s32 e1000_config_fc_after_link_up(struct e1000_hw *hw) * so we had to force link. In this case, we need to force the * configuration of the MAC to match the "fc" parameter. */ - if (((hw->media_type == e1000_media_type_fiber) && (hw->autoneg_failed)) - || ((hw->media_type == e1000_media_type_internal_serdes) - && (hw->autoneg_failed)) - || ((hw->media_type == e1000_media_type_copper) - && (!hw->autoneg))) { + if (((hw->media_type == e1000_media_type_fiber) && + (hw->autoneg_failed)) || + ((hw->media_type == e1000_media_type_internal_serdes) && + (hw->autoneg_failed)) || + ((hw->media_type == e1000_media_type_copper) && + (!hw->autoneg))) { ret_val = e1000_force_mac_fc(hw); if (ret_val) { e_dbg("Error forcing flow control settings\n"); @@ -2193,8 +2194,7 @@ static s32 e1000_config_fc_after_link_up(struct e1000_hw *hw) else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) - { + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { hw->fc = E1000_FC_TX_PAUSE; e_dbg ("Flow Control = TX PAUSE frames only.\n"); @@ -2210,8 +2210,7 @@ static s32 e1000_config_fc_after_link_up(struct e1000_hw *hw) else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) - { + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { hw->fc = E1000_FC_RX_PAUSE; e_dbg ("Flow Control = RX PAUSE frames only.\n"); @@ -2460,10 +2459,11 @@ s32 e1000_check_for_link(struct e1000_hw *hw) * happen due to the execution of this workaround. */ - if ((hw->mac_type == e1000_82544 - || hw->mac_type == e1000_82543) && (!hw->autoneg) - && (hw->forced_speed_duplex == e1000_10_full - || hw->forced_speed_duplex == e1000_10_half)) { + if ((hw->mac_type == e1000_82544 || + hw->mac_type == e1000_82543) && + (!hw->autoneg) && + (hw->forced_speed_duplex == e1000_10_full || + hw->forced_speed_duplex == e1000_10_half)) { ew32(IMC, 0xffffffff); ret_val = e1000_polarity_reversal_workaround(hw); @@ -2528,8 +2528,10 @@ s32 e1000_check_for_link(struct e1000_hw *hw) */ if (hw->tbi_compatibility_en) { u16 speed, duplex; + ret_val = e1000_get_speed_and_duplex(hw, &speed, &duplex); + if (ret_val) { e_dbg ("Error getting link speed and duplex\n"); @@ -2628,10 +2630,10 @@ s32 e1000_get_speed_and_duplex(struct e1000_hw *hw, u16 *speed, u16 *duplex) e1000_read_phy_reg(hw, PHY_LP_ABILITY, &phy_data); if (ret_val) return ret_val; - if ((*speed == SPEED_100 - && !(phy_data & NWAY_LPAR_100TX_FD_CAPS)) - || (*speed == SPEED_10 - && !(phy_data & NWAY_LPAR_10T_FD_CAPS))) + if ((*speed == SPEED_100 && + !(phy_data & NWAY_LPAR_100TX_FD_CAPS)) || + (*speed == SPEED_10 && + !(phy_data & NWAY_LPAR_10T_FD_CAPS))) *duplex = HALF_DUPLEX; } } @@ -2664,9 +2666,9 @@ static s32 e1000_wait_autoneg(struct e1000_hw *hw) ret_val = e1000_read_phy_reg(hw, PHY_STATUS, &phy_data); if (ret_val) return ret_val; - if (phy_data & MII_SR_AUTONEG_COMPLETE) { + if (phy_data & MII_SR_AUTONEG_COMPLETE) return E1000_SUCCESS; - } + msleep(100); } return E1000_SUCCESS; @@ -2803,11 +2805,11 @@ static u16 e1000_shift_in_mdi_bits(struct e1000_hw *hw) return data; } - /** * e1000_read_phy_reg - read a phy register * @hw: Struct containing variables accessed by shared code * @reg_addr: address of the PHY register to read + * @phy_data: pointer to the value on the PHY register * * Reads the value from a PHY register, if the value is on a specific non zero * page, sets the page first. @@ -2823,14 +2825,13 @@ s32 e1000_read_phy_reg(struct e1000_hw *hw, u32 reg_addr, u16 *phy_data) (reg_addr > MAX_PHY_MULTI_PAGE_REG)) { ret_val = e1000_write_phy_reg_ex(hw, IGP01E1000_PHY_PAGE_SELECT, (u16) reg_addr); - if (ret_val) { - spin_unlock_irqrestore(&e1000_phy_lock, flags); - return ret_val; - } + if (ret_val) + goto out; } ret_val = e1000_read_phy_reg_ex(hw, MAX_PHY_REG_ADDRESS & reg_addr, phy_data); +out: spin_unlock_irqrestore(&e1000_phy_lock, flags); return ret_val; @@ -2881,7 +2882,7 @@ static s32 e1000_read_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr, e_dbg("MDI Read Error\n"); return -E1000_ERR_PHY; } - *phy_data = (u16) mdic; + *phy_data = (u16)mdic; } else { mdic = ((reg_addr << E1000_MDIC_REG_SHIFT) | (phy_addr << E1000_MDIC_PHY_SHIFT) | @@ -2906,7 +2907,7 @@ static s32 e1000_read_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr, e_dbg("MDI Error\n"); return -E1000_ERR_PHY; } - *phy_data = (u16) mdic; + *phy_data = (u16)mdic; } } else { /* We must first send a preamble through the MDIO pin to signal @@ -2960,7 +2961,7 @@ s32 e1000_write_phy_reg(struct e1000_hw *hw, u32 reg_addr, u16 phy_data) if ((hw->phy_type == e1000_phy_igp) && (reg_addr > MAX_PHY_MULTI_PAGE_REG)) { ret_val = e1000_write_phy_reg_ex(hw, IGP01E1000_PHY_PAGE_SELECT, - (u16) reg_addr); + (u16)reg_addr); if (ret_val) { spin_unlock_irqrestore(&e1000_phy_lock, flags); return ret_val; @@ -2993,7 +2994,7 @@ static s32 e1000_write_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr, * the desired data. */ if (hw->mac_type == e1000_ce4100) { - mdic = (((u32) phy_data) | + mdic = (((u32)phy_data) | (reg_addr << E1000_MDIC_REG_SHIFT) | (phy_addr << E1000_MDIC_PHY_SHIFT) | (INTEL_CE_GBE_MDIC_OP_WRITE) | @@ -3015,7 +3016,7 @@ static s32 e1000_write_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr, return -E1000_ERR_PHY; } } else { - mdic = (((u32) phy_data) | + mdic = (((u32)phy_data) | (reg_addr << E1000_MDIC_REG_SHIFT) | (phy_addr << E1000_MDIC_PHY_SHIFT) | (E1000_MDIC_OP_WRITE)); @@ -3053,7 +3054,7 @@ static s32 e1000_write_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr, mdic = ((PHY_TURNAROUND) | (reg_addr << 2) | (phy_addr << 7) | (PHY_OP_WRITE << 12) | (PHY_SOF << 14)); mdic <<= 16; - mdic |= (u32) phy_data; + mdic |= (u32)phy_data; e1000_shift_out_mdi_bits(hw, mdic, 32); } @@ -3176,14 +3177,14 @@ static s32 e1000_detect_gig_phy(struct e1000_hw *hw) if (ret_val) return ret_val; - hw->phy_id = (u32) (phy_id_high << 16); + hw->phy_id = (u32)(phy_id_high << 16); udelay(20); ret_val = e1000_read_phy_reg(hw, PHY_ID2, &phy_id_low); if (ret_val) return ret_val; - hw->phy_id |= (u32) (phy_id_low & PHY_REVISION_MASK); - hw->phy_revision = (u32) phy_id_low & ~PHY_REVISION_MASK; + hw->phy_id |= (u32)(phy_id_low & PHY_REVISION_MASK); + hw->phy_revision = (u32)phy_id_low & ~PHY_REVISION_MASK; switch (hw->mac_type) { case e1000_82543: @@ -3401,7 +3402,6 @@ static s32 e1000_phy_m88_get_info(struct e1000_hw *hw, phy_info->remote_rx = ((phy_data & SR_1000T_REMOTE_RX_STATUS) >> SR_1000T_REMOTE_RX_STATUS_SHIFT) ? e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok; - } return E1000_SUCCESS; @@ -3449,7 +3449,7 @@ s32 e1000_phy_get_info(struct e1000_hw *hw, struct e1000_phy_info *phy_info) if (hw->phy_type == e1000_phy_igp) return e1000_phy_igp_get_info(hw, phy_info); else if ((hw->phy_type == e1000_phy_8211) || - (hw->phy_type == e1000_phy_8201)) + (hw->phy_type == e1000_phy_8201)) return E1000_SUCCESS; else return e1000_phy_m88_get_info(hw, phy_info); @@ -3611,11 +3611,11 @@ static void e1000_shift_out_ee_bits(struct e1000_hw *hw, u16 data, u16 count) */ mask = 0x01 << (count - 1); eecd = er32(EECD); - if (eeprom->type == e1000_eeprom_microwire) { + if (eeprom->type == e1000_eeprom_microwire) eecd &= ~E1000_EECD_DO; - } else if (eeprom->type == e1000_eeprom_spi) { + else if (eeprom->type == e1000_eeprom_spi) eecd |= E1000_EECD_DO; - } + do { /* A "1" is shifted out to the EEPROM by setting bit "DI" to a * "1", and then raising and then lowering the clock (the SK bit @@ -3851,7 +3851,7 @@ static s32 e1000_spi_eeprom_ready(struct e1000_hw *hw) do { e1000_shift_out_ee_bits(hw, EEPROM_RDSR_OPCODE_SPI, hw->eeprom.opcode_bits); - spi_stat_reg = (u8) e1000_shift_in_ee_bits(hw, 8); + spi_stat_reg = (u8)e1000_shift_in_ee_bits(hw, 8); if (!(spi_stat_reg & EEPROM_STATUS_RDY_SPI)) break; @@ -3882,9 +3882,10 @@ static s32 e1000_spi_eeprom_ready(struct e1000_hw *hw) s32 e1000_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) { s32 ret; - spin_lock(&e1000_eeprom_lock); + + mutex_lock(&e1000_eeprom_lock); ret = e1000_do_read_eeprom(hw, offset, words, data); - spin_unlock(&e1000_eeprom_lock); + mutex_unlock(&e1000_eeprom_lock); return ret; } @@ -3896,15 +3897,16 @@ static s32 e1000_do_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words, if (hw->mac_type == e1000_ce4100) { GBE_CONFIG_FLASH_READ(GBE_CONFIG_BASE_VIRT, offset, words, - data); + data); return E1000_SUCCESS; } /* A check for invalid values: offset too large, too many words, and * not enough words. */ - if ((offset >= eeprom->word_size) - || (words > eeprom->word_size - offset) || (words == 0)) { + if ((offset >= eeprom->word_size) || + (words > eeprom->word_size - offset) || + (words == 0)) { e_dbg("\"words\" parameter out of bounds. Words = %d," "size = %d\n", offset, eeprom->word_size); return -E1000_ERR_EEPROM; @@ -3940,7 +3942,7 @@ static s32 e1000_do_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words, /* Send the READ command (opcode + addr) */ e1000_shift_out_ee_bits(hw, read_opcode, eeprom->opcode_bits); - e1000_shift_out_ee_bits(hw, (u16) (offset * 2), + e1000_shift_out_ee_bits(hw, (u16)(offset * 2), eeprom->address_bits); /* Read the data. The address of the eeprom internally @@ -3960,7 +3962,7 @@ static s32 e1000_do_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words, e1000_shift_out_ee_bits(hw, EEPROM_READ_OPCODE_MICROWIRE, eeprom->opcode_bits); - e1000_shift_out_ee_bits(hw, (u16) (offset + i), + e1000_shift_out_ee_bits(hw, (u16)(offset + i), eeprom->address_bits); /* Read the data. For microwire, each word requires the @@ -3968,6 +3970,7 @@ static s32 e1000_do_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words, */ data[i] = e1000_shift_in_ee_bits(hw, 16); e1000_standby_eeprom(hw); + cond_resched(); } } @@ -4004,7 +4007,7 @@ s32 e1000_validate_eeprom_checksum(struct e1000_hw *hw) return E1000_SUCCESS; #endif - if (checksum == (u16) EEPROM_SUM) + if (checksum == (u16)EEPROM_SUM) return E1000_SUCCESS; else { e_dbg("EEPROM Checksum Invalid\n"); @@ -4031,7 +4034,7 @@ s32 e1000_update_eeprom_checksum(struct e1000_hw *hw) } checksum += eeprom_data; } - checksum = (u16) EEPROM_SUM - checksum; + checksum = (u16)EEPROM_SUM - checksum; if (e1000_write_eeprom(hw, EEPROM_CHECKSUM_REG, 1, &checksum) < 0) { e_dbg("EEPROM Write Error\n"); return -E1000_ERR_EEPROM; @@ -4052,9 +4055,10 @@ s32 e1000_update_eeprom_checksum(struct e1000_hw *hw) s32 e1000_write_eeprom(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) { s32 ret; - spin_lock(&e1000_eeprom_lock); + + mutex_lock(&e1000_eeprom_lock); ret = e1000_do_write_eeprom(hw, offset, words, data); - spin_unlock(&e1000_eeprom_lock); + mutex_unlock(&e1000_eeprom_lock); return ret; } @@ -4066,15 +4070,16 @@ static s32 e1000_do_write_eeprom(struct e1000_hw *hw, u16 offset, u16 words, if (hw->mac_type == e1000_ce4100) { GBE_CONFIG_FLASH_WRITE(GBE_CONFIG_BASE_VIRT, offset, words, - data); + data); return E1000_SUCCESS; } /* A check for invalid values: offset too large, too many words, and * not enough words. */ - if ((offset >= eeprom->word_size) - || (words > eeprom->word_size - offset) || (words == 0)) { + if ((offset >= eeprom->word_size) || + (words > eeprom->word_size - offset) || + (words == 0)) { e_dbg("\"words\" parameter out of bounds\n"); return -E1000_ERR_EEPROM; } @@ -4116,6 +4121,7 @@ static s32 e1000_write_eeprom_spi(struct e1000_hw *hw, u16 offset, u16 words, return -E1000_ERR_EEPROM; e1000_standby_eeprom(hw); + cond_resched(); /* Send the WRITE ENABLE command (8 bit opcode ) */ e1000_shift_out_ee_bits(hw, EEPROM_WREN_OPCODE_SPI, @@ -4132,7 +4138,7 @@ static s32 e1000_write_eeprom_spi(struct e1000_hw *hw, u16 offset, u16 words, /* Send the Write command (8-bit opcode + addr) */ e1000_shift_out_ee_bits(hw, write_opcode, eeprom->opcode_bits); - e1000_shift_out_ee_bits(hw, (u16) ((offset + widx) * 2), + e1000_shift_out_ee_bits(hw, (u16)((offset + widx) * 2), eeprom->address_bits); /* Send the data */ @@ -4142,6 +4148,7 @@ static s32 e1000_write_eeprom_spi(struct e1000_hw *hw, u16 offset, u16 words, */ while (widx < words) { u16 word_out = data[widx]; + word_out = (word_out >> 8) | (word_out << 8); e1000_shift_out_ee_bits(hw, word_out, 16); widx++; @@ -4183,9 +4190,9 @@ static s32 e1000_write_eeprom_microwire(struct e1000_hw *hw, u16 offset, * EEPROM into write/erase mode. */ e1000_shift_out_ee_bits(hw, EEPROM_EWEN_OPCODE_MICROWIRE, - (u16) (eeprom->opcode_bits + 2)); + (u16)(eeprom->opcode_bits + 2)); - e1000_shift_out_ee_bits(hw, 0, (u16) (eeprom->address_bits - 2)); + e1000_shift_out_ee_bits(hw, 0, (u16)(eeprom->address_bits - 2)); /* Prepare the EEPROM */ e1000_standby_eeprom(hw); @@ -4195,7 +4202,7 @@ static s32 e1000_write_eeprom_microwire(struct e1000_hw *hw, u16 offset, e1000_shift_out_ee_bits(hw, EEPROM_WRITE_OPCODE_MICROWIRE, eeprom->opcode_bits); - e1000_shift_out_ee_bits(hw, (u16) (offset + words_written), + e1000_shift_out_ee_bits(hw, (u16)(offset + words_written), eeprom->address_bits); /* Send the data */ @@ -4224,6 +4231,7 @@ static s32 e1000_write_eeprom_microwire(struct e1000_hw *hw, u16 offset, /* Recover from write */ e1000_standby_eeprom(hw); + cond_resched(); words_written++; } @@ -4235,9 +4243,9 @@ static s32 e1000_write_eeprom_microwire(struct e1000_hw *hw, u16 offset, * EEPROM out of write/erase mode. */ e1000_shift_out_ee_bits(hw, EEPROM_EWDS_OPCODE_MICROWIRE, - (u16) (eeprom->opcode_bits + 2)); + (u16)(eeprom->opcode_bits + 2)); - e1000_shift_out_ee_bits(hw, 0, (u16) (eeprom->address_bits - 2)); + e1000_shift_out_ee_bits(hw, 0, (u16)(eeprom->address_bits - 2)); return E1000_SUCCESS; } @@ -4260,8 +4268,8 @@ s32 e1000_read_mac_addr(struct e1000_hw *hw) e_dbg("EEPROM Read Error\n"); return -E1000_ERR_EEPROM; } - hw->perm_mac_addr[i] = (u8) (eeprom_data & 0x00FF); - hw->perm_mac_addr[i + 1] = (u8) (eeprom_data >> 8); + hw->perm_mac_addr[i] = (u8)(eeprom_data & 0x00FF); + hw->perm_mac_addr[i + 1] = (u8)(eeprom_data >> 8); } switch (hw->mac_type) { @@ -4328,19 +4336,19 @@ u32 e1000_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) */ case 0: /* [47:36] i.e. 0x563 for above example address */ - hash_value = ((mc_addr[4] >> 4) | (((u16) mc_addr[5]) << 4)); + hash_value = ((mc_addr[4] >> 4) | (((u16)mc_addr[5]) << 4)); break; case 1: /* [46:35] i.e. 0xAC6 for above example address */ - hash_value = ((mc_addr[4] >> 3) | (((u16) mc_addr[5]) << 5)); + hash_value = ((mc_addr[4] >> 3) | (((u16)mc_addr[5]) << 5)); break; case 2: /* [45:34] i.e. 0x5D8 for above example address */ - hash_value = ((mc_addr[4] >> 2) | (((u16) mc_addr[5]) << 6)); + hash_value = ((mc_addr[4] >> 2) | (((u16)mc_addr[5]) << 6)); break; case 3: /* [43:32] i.e. 0x634 for above example address */ - hash_value = ((mc_addr[4]) | (((u16) mc_addr[5]) << 8)); + hash_value = ((mc_addr[4]) | (((u16)mc_addr[5]) << 8)); break; } @@ -4361,9 +4369,9 @@ void e1000_rar_set(struct e1000_hw *hw, u8 *addr, u32 index) /* HW expects these in little endian so we reverse the byte order * from network order (big endian) to little endian */ - rar_low = ((u32) addr[0] | ((u32) addr[1] << 8) | - ((u32) addr[2] << 16) | ((u32) addr[3] << 24)); - rar_high = ((u32) addr[4] | ((u32) addr[5] << 8)); + rar_low = ((u32)addr[0] | ((u32)addr[1] << 8) | + ((u32)addr[2] << 16) | ((u32)addr[3] << 24)); + rar_high = ((u32)addr[4] | ((u32)addr[5] << 8)); /* Disable Rx and flush all Rx frames before enabling RSS to avoid Rx * unit hang. @@ -4537,7 +4545,7 @@ s32 e1000_setup_led(struct e1000_hw *hw) if (ret_val) return ret_val; ret_val = e1000_write_phy_reg(hw, IGP01E1000_GMII_FIFO, - (u16) (hw->phy_spd_default & + (u16)(hw->phy_spd_default & ~IGP01E1000_GMII_SPD)); if (ret_val) return ret_val; @@ -4802,7 +4810,7 @@ void e1000_reset_adaptive(struct e1000_hw *hw) void e1000_update_adaptive(struct e1000_hw *hw) { if (hw->adaptive_ifs) { - if ((hw->collision_delta *hw->ifs_ratio) > hw->tx_packet_delta) { + if ((hw->collision_delta * hw->ifs_ratio) > hw->tx_packet_delta) { if (hw->tx_packet_delta > MIN_NUM_XMITS) { hw->in_ifs_mode = true; if (hw->current_ifs_val < hw->ifs_max_val) { @@ -4816,8 +4824,8 @@ void e1000_update_adaptive(struct e1000_hw *hw) } } } else { - if (hw->in_ifs_mode - && (hw->tx_packet_delta <= MIN_NUM_XMITS)) { + if (hw->in_ifs_mode && + (hw->tx_packet_delta <= MIN_NUM_XMITS)) { hw->current_ifs_val = 0; hw->in_ifs_mode = false; ew32(AIT, 0); @@ -4922,7 +4930,6 @@ static s32 e1000_get_cable_length(struct e1000_hw *hw, u16 *min_length, /* Use old method for Phy older than IGP */ if (hw->phy_type == e1000_phy_m88) { - ret_val = e1000_read_phy_reg(hw, M88E1000_PHY_SPEC_STATUS, &phy_data); if (ret_val) @@ -4966,7 +4973,6 @@ static s32 e1000_get_cable_length(struct e1000_hw *hw, u16 *min_length, }; /* Read the AGC registers for all channels */ for (i = 0; i < IGP01E1000_PHY_CHANNEL_NUM; i++) { - ret_val = e1000_read_phy_reg(hw, agc_reg_array[i], &phy_data); if (ret_val) @@ -4976,8 +4982,8 @@ static s32 e1000_get_cable_length(struct e1000_hw *hw, u16 *min_length, /* Value bound check. */ if ((cur_agc_value >= - IGP01E1000_AGC_LENGTH_TABLE_SIZE - 1) - || (cur_agc_value == 0)) + IGP01E1000_AGC_LENGTH_TABLE_SIZE - 1) || + (cur_agc_value == 0)) return -E1000_ERR_PHY; agc_value += cur_agc_value; @@ -5054,7 +5060,6 @@ static s32 e1000_check_polarity(struct e1000_hw *hw, */ if ((phy_data & IGP01E1000_PSSR_SPEED_MASK) == IGP01E1000_PSSR_SPEED_1000MBPS) { - /* Read the GIG initialization PCS register (0x00B4) */ ret_val = e1000_read_phy_reg(hw, IGP01E1000_PHY_PCS_INIT_REG, @@ -5175,8 +5180,8 @@ static s32 e1000_1000Mb_check_cable_length(struct e1000_hw *hw) hw->ffe_config_state = e1000_ffe_config_active; ret_val = e1000_write_phy_reg(hw, - IGP01E1000_PHY_DSP_FFE, - IGP01E1000_PHY_DSP_FFE_CM_CP); + IGP01E1000_PHY_DSP_FFE, + IGP01E1000_PHY_DSP_FFE_CM_CP); if (ret_val) return ret_val; break; @@ -5243,7 +5248,7 @@ static s32 e1000_config_dsp_after_link_change(struct e1000_hw *hw, bool link_up) msleep(20); ret_val = e1000_write_phy_reg(hw, 0x0000, - IGP01E1000_IEEE_FORCE_GIGA); + IGP01E1000_IEEE_FORCE_GIGA); if (ret_val) return ret_val; for (i = 0; i < IGP01E1000_PHY_CHANNEL_NUM; i++) { @@ -5264,7 +5269,7 @@ static s32 e1000_config_dsp_after_link_change(struct e1000_hw *hw, bool link_up) } ret_val = e1000_write_phy_reg(hw, 0x0000, - IGP01E1000_IEEE_RESTART_AUTONEG); + IGP01E1000_IEEE_RESTART_AUTONEG); if (ret_val) return ret_val; @@ -5299,7 +5304,7 @@ static s32 e1000_config_dsp_after_link_change(struct e1000_hw *hw, bool link_up) msleep(20); ret_val = e1000_write_phy_reg(hw, 0x0000, - IGP01E1000_IEEE_FORCE_GIGA); + IGP01E1000_IEEE_FORCE_GIGA); if (ret_val) return ret_val; ret_val = @@ -5309,7 +5314,7 @@ static s32 e1000_config_dsp_after_link_change(struct e1000_hw *hw, bool link_up) return ret_val; ret_val = e1000_write_phy_reg(hw, 0x0000, - IGP01E1000_IEEE_RESTART_AUTONEG); + IGP01E1000_IEEE_RESTART_AUTONEG); if (ret_val) return ret_val; @@ -5346,9 +5351,8 @@ static s32 e1000_set_phy_mode(struct e1000_hw *hw) ret_val = e1000_read_eeprom(hw, EEPROM_PHY_CLASS_WORD, 1, &eeprom_data); - if (ret_val) { + if (ret_val) return ret_val; - } if ((eeprom_data != EEPROM_RESERVED_WORD) && (eeprom_data & EEPROM_PHY_CLASS_A)) { @@ -5395,8 +5399,8 @@ static s32 e1000_set_d3_lplu_state(struct e1000_hw *hw, bool active) * from the lowest speeds starting from 10Mbps. The capability is used * for Dx transitions and states */ - if (hw->mac_type == e1000_82541_rev_2 - || hw->mac_type == e1000_82547_rev_2) { + if (hw->mac_type == e1000_82541_rev_2 || + hw->mac_type == e1000_82547_rev_2) { ret_val = e1000_read_phy_reg(hw, IGP01E1000_GMII_FIFO, &phy_data); if (ret_val) @@ -5446,11 +5450,9 @@ static s32 e1000_set_d3_lplu_state(struct e1000_hw *hw, bool active) if (ret_val) return ret_val; } - } else if ((hw->autoneg_advertised == AUTONEG_ADVERTISE_SPEED_DEFAULT) - || (hw->autoneg_advertised == AUTONEG_ADVERTISE_10_ALL) - || (hw->autoneg_advertised == - AUTONEG_ADVERTISE_10_100_ALL)) { - + } else if ((hw->autoneg_advertised == AUTONEG_ADVERTISE_SPEED_DEFAULT) || + (hw->autoneg_advertised == AUTONEG_ADVERTISE_10_ALL) || + (hw->autoneg_advertised == AUTONEG_ADVERTISE_10_100_ALL)) { if (hw->mac_type == e1000_82541_rev_2 || hw->mac_type == e1000_82547_rev_2) { phy_data |= IGP01E1000_GMII_FLEX_SPD; @@ -5474,7 +5476,6 @@ static s32 e1000_set_d3_lplu_state(struct e1000_hw *hw, bool active) phy_data); if (ret_val) return ret_val; - } return E1000_SUCCESS; } @@ -5542,7 +5543,6 @@ static s32 e1000_set_vco_speed(struct e1000_hw *hw) return E1000_SUCCESS; } - /** * e1000_enable_mng_pass_thru - check for bmc pass through * @hw: Struct containing variables accessed by shared code diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index fd7be860c2013..3fc7bde699ba5 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -99,13 +99,13 @@ int e1000_setup_all_rx_resources(struct e1000_adapter *adapter); void e1000_free_all_tx_resources(struct e1000_adapter *adapter); void e1000_free_all_rx_resources(struct e1000_adapter *adapter); static int e1000_setup_tx_resources(struct e1000_adapter *adapter, - struct e1000_tx_ring *txdr); + struct e1000_tx_ring *txdr); static int e1000_setup_rx_resources(struct e1000_adapter *adapter, - struct e1000_rx_ring *rxdr); + struct e1000_rx_ring *rxdr); static void e1000_free_tx_resources(struct e1000_adapter *adapter, - struct e1000_tx_ring *tx_ring); + struct e1000_tx_ring *tx_ring); static void e1000_free_rx_resources(struct e1000_adapter *adapter, - struct e1000_rx_ring *rx_ring); + struct e1000_rx_ring *rx_ring); void e1000_update_stats(struct e1000_adapter *adapter); static int e1000_init_module(void); @@ -122,16 +122,16 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter); static void e1000_clean_all_tx_rings(struct e1000_adapter *adapter); static void e1000_clean_all_rx_rings(struct e1000_adapter *adapter); static void e1000_clean_tx_ring(struct e1000_adapter *adapter, - struct e1000_tx_ring *tx_ring); + struct e1000_tx_ring *tx_ring); static void e1000_clean_rx_ring(struct e1000_adapter *adapter, - struct e1000_rx_ring *rx_ring); + struct e1000_rx_ring *rx_ring); static void e1000_set_rx_mode(struct net_device *netdev); static void e1000_update_phy_info_task(struct work_struct *work); static void e1000_watchdog(struct work_struct *work); static void e1000_82547_tx_fifo_stall_task(struct work_struct *work); static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev); -static struct net_device_stats * e1000_get_stats(struct net_device *netdev); +static struct net_device_stats *e1000_get_stats(struct net_device *netdev); static int e1000_change_mtu(struct net_device *netdev, int new_mtu); static int e1000_set_mac(struct net_device *netdev, void *p); static irqreturn_t e1000_intr(int irq, void *data); @@ -164,7 +164,7 @@ static void e1000_tx_timeout(struct net_device *dev); static void e1000_reset_task(struct work_struct *work); static void e1000_smartspeed(struct e1000_adapter *adapter); static int e1000_82547_fifo_workaround(struct e1000_adapter *adapter, - struct sk_buff *skb); + struct sk_buff *skb); static bool e1000_vlan_used(struct e1000_adapter *adapter); static void e1000_vlan_mode(struct net_device *netdev, @@ -195,7 +195,7 @@ MODULE_PARM_DESC(copybreak, "Maximum size of packet that is copied to a new buffer on receive"); static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, - pci_channel_state_t state); + pci_channel_state_t state); static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev); static void e1000_io_resume(struct pci_dev *pdev); @@ -287,7 +287,7 @@ static int e1000_request_irq(struct e1000_adapter *adapter) int err; err = request_irq(adapter->pdev->irq, handler, irq_flags, netdev->name, - netdev); + netdev); if (err) { e_err(probe, "Unable to allocate interrupt Error: %d\n", err); } @@ -636,8 +636,8 @@ void e1000_reset(struct e1000_adapter *adapter) * but don't include ethernet FCS because hardware appends it */ min_tx_space = (hw->max_frame_size + - sizeof(struct e1000_tx_desc) - - ETH_FCS_LEN) * 2; + sizeof(struct e1000_tx_desc) - + ETH_FCS_LEN) * 2; min_tx_space = ALIGN(min_tx_space, 1024); min_tx_space >>= 10; /* software strips receive CRC, so leave room for it */ @@ -943,8 +943,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct e1000_adapter *adapter; struct e1000_hw *hw; - static int cards_found = 0; - static int global_quad_port_a = 0; /* global ksp3 port a indication */ + static int cards_found; + static int global_quad_port_a; /* global ksp3 port a indication */ int i, err, pci_using_dac; u16 eeprom_data = 0; u16 tmp = 0; @@ -1046,7 +1046,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->mac_type == e1000_ce4100) { hw->ce4100_gbe_mdio_base_virt = ioremap(pci_resource_start(pdev, BAR_1), - pci_resource_len(pdev, BAR_1)); + pci_resource_len(pdev, BAR_1)); if (!hw->ce4100_gbe_mdio_base_virt) goto err_mdio_ioremap; @@ -1148,7 +1148,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) break; case e1000_82546: case e1000_82546_rev_3: - if (er32(STATUS) & E1000_STATUS_FUNC_1){ + if (er32(STATUS) & E1000_STATUS_FUNC_1) { e1000_read_eeprom(hw, EEPROM_INIT_CONTROL3_PORT_B, 1, &eeprom_data); break; @@ -1199,13 +1199,13 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) for (i = 0; i < 32; i++) { hw->phy_addr = i; e1000_read_phy_reg(hw, PHY_ID2, &tmp); - if (tmp == 0 || tmp == 0xFF) { - if (i == 31) - goto err_eeprom; - continue; - } else + + if (tmp != 0 && tmp != 0xFF) break; } + + if (i >= 32) + goto err_eeprom; } /* reset the hardware with the new settings */ @@ -1263,7 +1263,7 @@ err_pci_reg: * @pdev: PCI device information struct * * e1000_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. The could be caused by a + * that it should release a PCI device. That could be caused by a * Hot-Plug event, or because the driver is going to be removed from * memory. **/ @@ -1334,12 +1334,12 @@ static int e1000_sw_init(struct e1000_adapter *adapter) static int e1000_alloc_queues(struct e1000_adapter *adapter) { adapter->tx_ring = kcalloc(adapter->num_tx_queues, - sizeof(struct e1000_tx_ring), GFP_KERNEL); + sizeof(struct e1000_tx_ring), GFP_KERNEL); if (!adapter->tx_ring) return -ENOMEM; adapter->rx_ring = kcalloc(adapter->num_rx_queues, - sizeof(struct e1000_rx_ring), GFP_KERNEL); + sizeof(struct e1000_rx_ring), GFP_KERNEL); if (!adapter->rx_ring) { kfree(adapter->tx_ring); return -ENOMEM; @@ -1811,20 +1811,20 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) rctl &= ~E1000_RCTL_SZ_4096; rctl |= E1000_RCTL_BSEX; switch (adapter->rx_buffer_len) { - case E1000_RXBUFFER_2048: - default: - rctl |= E1000_RCTL_SZ_2048; - rctl &= ~E1000_RCTL_BSEX; - break; - case E1000_RXBUFFER_4096: - rctl |= E1000_RCTL_SZ_4096; - break; - case E1000_RXBUFFER_8192: - rctl |= E1000_RCTL_SZ_8192; - break; - case E1000_RXBUFFER_16384: - rctl |= E1000_RCTL_SZ_16384; - break; + case E1000_RXBUFFER_2048: + default: + rctl |= E1000_RCTL_SZ_2048; + rctl &= ~E1000_RCTL_BSEX; + break; + case E1000_RXBUFFER_4096: + rctl |= E1000_RCTL_SZ_4096; + break; + case E1000_RXBUFFER_8192: + rctl |= E1000_RCTL_SZ_8192; + break; + case E1000_RXBUFFER_16384: + rctl |= E1000_RCTL_SZ_16384; + break; } /* This is useful for sniffing bad packets. */ @@ -1861,12 +1861,12 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) if (adapter->netdev->mtu > ETH_DATA_LEN) { rdlen = adapter->rx_ring[0].count * - sizeof(struct e1000_rx_desc); + sizeof(struct e1000_rx_desc); adapter->clean_rx = e1000_clean_jumbo_rx_irq; adapter->alloc_rx_buf = e1000_alloc_jumbo_rx_buffers; } else { rdlen = adapter->rx_ring[0].count * - sizeof(struct e1000_rx_desc); + sizeof(struct e1000_rx_desc); adapter->clean_rx = e1000_clean_rx_irq; adapter->alloc_rx_buf = e1000_alloc_rx_buffers; } @@ -2761,7 +2761,9 @@ static int e1000_tso(struct e1000_adapter *adapter, buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - if (++i == tx_ring->count) i = 0; + if (++i == tx_ring->count) + i = 0; + tx_ring->next_to_use = i; return true; @@ -2816,7 +2818,9 @@ static bool e1000_tx_csum(struct e1000_adapter *adapter, buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - if (unlikely(++i == tx_ring->count)) i = 0; + if (unlikely(++i == tx_ring->count)) + i = 0; + tx_ring->next_to_use = i; return true; @@ -2865,8 +2869,8 @@ static int e1000_tx_map(struct e1000_adapter *adapter, * packet is smaller than 2048 - 16 - 16 (or 2016) bytes */ if (unlikely((hw->bus_type == e1000_bus_type_pcix) && - (size > 2015) && count == 0)) - size = 2015; + (size > 2015) && count == 0)) + size = 2015; /* Workaround for potential 82544 hang in PCI-X. Avoid * terminating buffers within evenly-aligned dwords. @@ -2963,7 +2967,7 @@ dma_error: count--; while (count--) { - if (i==0) + if (i == 0) i += tx_ring->count; i--; buffer_info = &tx_ring->buffer_info[i]; @@ -3013,7 +3017,8 @@ static void e1000_tx_queue(struct e1000_adapter *adapter, tx_desc->lower.data = cpu_to_le32(txd_lower | buffer_info->length); tx_desc->upper.data = cpu_to_le32(txd_upper); - if (unlikely(++i == tx_ring->count)) i = 0; + if (unlikely(++i == tx_ring->count)) + i = 0; } tx_desc->lower.data |= cpu_to_le32(adapter->txd_cmd); @@ -3101,7 +3106,7 @@ static int e1000_maybe_stop_tx(struct net_device *netdev, return __e1000_maybe_stop_tx(netdev, size); } -#define TXD_USE_COUNT(S, X) (((S) >> (X)) + 1 ) +#define TXD_USE_COUNT(S, X) (((S) >> (X)) + 1) static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { @@ -3841,7 +3846,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, struct e1000_tx_buffer *buffer_info; unsigned int i, eop; unsigned int count = 0; - unsigned int total_tx_bytes=0, total_tx_packets=0; + unsigned int total_tx_bytes = 0, total_tx_packets = 0; unsigned int bytes_compl = 0, pkts_compl = 0; i = tx_ring->next_to_clean; @@ -3869,14 +3874,18 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, e1000_unmap_and_free_tx_resource(adapter, buffer_info); tx_desc->upper.data = 0; - if (unlikely(++i == tx_ring->count)) i = 0; + if (unlikely(++i == tx_ring->count)) + i = 0; } eop = tx_ring->buffer_info[i].next_to_watch; eop_desc = E1000_TX_DESC(*tx_ring, eop); } - tx_ring->next_to_clean = i; + /* Synchronize with E1000_DESC_UNUSED called from e1000_xmit_frame, + * which will reuse the cleaned buffers. + */ + smp_store_release(&tx_ring->next_to_clean, i); netdev_completed_queue(netdev, pkts_compl, bytes_compl); @@ -3954,9 +3963,11 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, skb_checksum_none_assert(skb); /* 82543 or newer only */ - if (unlikely(hw->mac_type < e1000_82543)) return; + if (unlikely(hw->mac_type < e1000_82543)) + return; /* Ignore Checksum bit is set */ - if (unlikely(status & E1000_RXD_STAT_IXSM)) return; + if (unlikely(status & E1000_RXD_STAT_IXSM)) + return; /* TCP/UDP checksum error bit is set */ if (unlikely(errors & E1000_RXD_ERR_TCPE)) { /* let the stack verify checksum errors */ @@ -4136,7 +4147,7 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, unsigned int i; int cleaned_count = 0; bool cleaned = false; - unsigned int total_rx_bytes=0, total_rx_packets=0; + unsigned int total_rx_bytes = 0, total_rx_packets = 0; i = rx_ring->next_to_clean; rx_desc = E1000_RX_DESC(*rx_ring, i); @@ -4153,7 +4164,9 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, status = rx_desc->status; - if (++i == rx_ring->count) i = 0; + if (++i == rx_ring->count) + i = 0; + next_rxd = E1000_RX_DESC(*rx_ring, i); prefetch(next_rxd); @@ -4356,7 +4369,7 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, unsigned int i; int cleaned_count = 0; bool cleaned = false; - unsigned int total_rx_bytes=0, total_rx_packets=0; + unsigned int total_rx_bytes = 0, total_rx_packets = 0; i = rx_ring->next_to_clean; rx_desc = E1000_RX_DESC(*rx_ring, i); @@ -4395,7 +4408,9 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, buffer_info->rxbuf.data = NULL; } - if (++i == rx_ring->count) i = 0; + if (++i == rx_ring->count) + i = 0; + next_rxd = E1000_RX_DESC(*rx_ring, i); prefetch(next_rxd); @@ -4683,9 +4698,11 @@ static void e1000_smartspeed(struct e1000_adapter *adapter) * we assume back-to-back */ e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_status); - if (!(phy_status & SR_1000T_MS_CONFIG_FAULT)) return; + if (!(phy_status & SR_1000T_MS_CONFIG_FAULT)) + return; e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_status); - if (!(phy_status & SR_1000T_MS_CONFIG_FAULT)) return; + if (!(phy_status & SR_1000T_MS_CONFIG_FAULT)) + return; e1000_read_phy_reg(hw, PHY_1000T_CTRL, &phy_ctrl); if (phy_ctrl & CR_1000T_MS_ENABLE) { phy_ctrl &= ~CR_1000T_MS_ENABLE; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 133d4074dbe48..f7c7804d79e57 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -441,12 +441,13 @@ #define E1000_IMS_RXQ1 E1000_ICR_RXQ1 /* Rx Queue 1 Interrupt */ #define E1000_IMS_TXQ0 E1000_ICR_TXQ0 /* Tx Queue 0 Interrupt */ #define E1000_IMS_TXQ1 E1000_ICR_TXQ1 /* Tx Queue 1 Interrupt */ -#define E1000_IMS_OTHER E1000_ICR_OTHER /* Other Interrupts */ +#define E1000_IMS_OTHER E1000_ICR_OTHER /* Other Interrupt */ /* Interrupt Cause Set */ #define E1000_ICS_LSC E1000_ICR_LSC /* Link Status Change */ #define E1000_ICS_RXSEQ E1000_ICR_RXSEQ /* Rx sequence error */ #define E1000_ICS_RXDMT0 E1000_ICR_RXDMT0 /* Rx desc min. threshold */ +#define E1000_ICS_OTHER E1000_ICR_OTHER /* Other Interrupt */ /* Transmit Descriptor Control */ #define E1000_TXDCTL_PTHRESH 0x0000003F /* TXDCTL Prefetch Threshold */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 0b748d1959d93..1dc293bad87b5 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -480,7 +480,7 @@ extern const char e1000e_driver_version[]; void e1000e_check_options(struct e1000_adapter *adapter); void e1000e_set_ethtool_ops(struct net_device *netdev); -int e1000e_up(struct e1000_adapter *adapter); +void e1000e_up(struct e1000_adapter *adapter); void e1000e_down(struct e1000_adapter *adapter, bool reset); void e1000e_reinit_locked(struct e1000_adapter *adapter); void e1000e_reset(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index c9da4654e9cad..b3949d5bef5c3 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -91,6 +91,7 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_SPT_I219_V 0x1570 /* SPT PCH */ #define E1000_DEV_ID_PCH_SPT_I219_LM2 0x15B7 /* SPT-H PCH */ #define E1000_DEV_ID_PCH_SPT_I219_V2 0x15B8 /* SPT-H PCH */ +#define E1000_DEV_ID_PCH_LBG_I219_LM3 0x15B9 /* LBG PCH */ #define E1000_REVISION_4 4 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 91a5a0ae9cd73..a049e30639a13 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1984,7 +1984,7 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) int i = 0; while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) && - (i++ < 10)) + (i++ < 30)) usleep_range(10000, 20000); return blocked ? E1000_BLK_PHY_RESET : 0; } @@ -3093,24 +3093,45 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) struct e1000_nvm_info *nvm = &hw->nvm; u32 bank1_offset = nvm->flash_bank_size * sizeof(u16); u32 act_offset = E1000_ICH_NVM_SIG_WORD * 2 + 1; + u32 nvm_dword = 0; u8 sig_byte = 0; s32 ret_val; switch (hw->mac.type) { - /* In SPT, read from the CTRL_EXT reg instead of - * accessing the sector valid bits from the nvm - */ case e1000_pch_spt: - *bank = er32(CTRL_EXT) - & E1000_CTRL_EXT_NVMVS; - if ((*bank == 0) || (*bank == 1)) { - e_dbg("ERROR: No valid NVM bank present\n"); - return -E1000_ERR_NVM; - } else { - *bank = *bank - 2; + bank1_offset = nvm->flash_bank_size; + act_offset = E1000_ICH_NVM_SIG_WORD; + + /* set bank to 0 in case flash read fails */ + *bank = 0; + + /* Check bank 0 */ + ret_val = e1000_read_flash_dword_ich8lan(hw, act_offset, + &nvm_dword); + if (ret_val) + return ret_val; + sig_byte = (u8)((nvm_dword & 0xFF00) >> 8); + if ((sig_byte & E1000_ICH_NVM_VALID_SIG_MASK) == + E1000_ICH_NVM_SIG_VALUE) { + *bank = 0; return 0; } - break; + + /* Check bank 1 */ + ret_val = e1000_read_flash_dword_ich8lan(hw, act_offset + + bank1_offset, + &nvm_dword); + if (ret_val) + return ret_val; + sig_byte = (u8)((nvm_dword & 0xFF00) >> 8); + if ((sig_byte & E1000_ICH_NVM_VALID_SIG_MASK) == + E1000_ICH_NVM_SIG_VALUE) { + *bank = 1; + return 0; + } + + e_dbg("ERROR: No valid NVM bank present\n"); + return -E1000_ERR_NVM; case e1000_ich8lan: case e1000_ich9lan: eecd = er32(EECD); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 0a854a47d31a7..c71ba1bfc1ec1 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1905,30 +1905,15 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 icr = er32(ICR); - - if (!(icr & E1000_ICR_INT_ASSERTED)) { - if (!test_bit(__E1000_DOWN, &adapter->state)) - ew32(IMS, E1000_IMS_OTHER); - return IRQ_NONE; - } - if (icr & adapter->eiac_mask) - ew32(ICS, (icr & adapter->eiac_mask)); + hw->mac.get_link_status = true; - if (icr & E1000_ICR_OTHER) { - if (!(icr & E1000_ICR_LSC)) - goto no_link_interrupt; - hw->mac.get_link_status = true; - /* guard against interrupt when we're going down */ - if (!test_bit(__E1000_DOWN, &adapter->state)) - mod_timer(&adapter->watchdog_timer, jiffies + 1); + /* guard against interrupt when we're going down */ + if (!test_bit(__E1000_DOWN, &adapter->state)) { + mod_timer(&adapter->watchdog_timer, jiffies + 1); + ew32(IMS, E1000_IMS_OTHER); } -no_link_interrupt: - if (!test_bit(__E1000_DOWN, &adapter->state)) - ew32(IMS, E1000_IMS_LSC | E1000_IMS_OTHER); - return IRQ_HANDLED; } @@ -1946,6 +1931,9 @@ static irqreturn_t e1000_intr_msix_tx(int __always_unused irq, void *data) /* Ring was not completely cleaned, so fire another interrupt */ ew32(ICS, tx_ring->ims_val); + if (!test_bit(__E1000_DOWN, &adapter->state)) + ew32(IMS, adapter->tx_ring->ims_val); + return IRQ_HANDLED; } @@ -1959,8 +1947,10 @@ static irqreturn_t e1000_intr_msix_rx(int __always_unused irq, void *data) * previous interrupt. */ if (rx_ring->set_itr) { - writel(1000000000 / (rx_ring->itr_val * 256), - rx_ring->itr_register); + u32 itr = rx_ring->itr_val ? + 1000000000 / (rx_ring->itr_val * 256) : 0; + + writel(itr, rx_ring->itr_register); rx_ring->set_itr = 0; } @@ -2025,6 +2015,7 @@ static void e1000_configure_msix(struct e1000_adapter *adapter) hw->hw_addr + E1000_EITR_82574(vector)); else writel(1, hw->hw_addr + E1000_EITR_82574(vector)); + adapter->eiac_mask |= E1000_IMS_OTHER; /* Cause Tx interrupts on every write back */ ivar |= (1 << 31); @@ -2032,12 +2023,8 @@ static void e1000_configure_msix(struct e1000_adapter *adapter) ew32(IVAR, ivar); /* enable MSI-X PBA support */ - ctrl_ext = er32(CTRL_EXT); - ctrl_ext |= E1000_CTRL_EXT_PBA_CLR; - - /* Auto-Mask Other interrupts upon ICR read */ - ew32(IAM, ~E1000_EIAC_MASK_82574 | E1000_IMS_OTHER); - ctrl_ext |= E1000_CTRL_EXT_EIAME; + ctrl_ext = er32(CTRL_EXT) & ~E1000_CTRL_EXT_IAME; + ctrl_ext |= E1000_CTRL_EXT_PBA_CLR | E1000_CTRL_EXT_EIAME; ew32(CTRL_EXT, ctrl_ext); e1e_flush(); } @@ -2253,7 +2240,7 @@ static void e1000_irq_enable(struct e1000_adapter *adapter) if (adapter->msix_entries) { ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574); - ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC); + ew32(IMS, adapter->eiac_mask | E1000_IMS_LSC); } else if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) { ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER); @@ -4144,10 +4131,24 @@ void e1000e_reset(struct e1000_adapter *adapter) } -int e1000e_up(struct e1000_adapter *adapter) +/** + * e1000e_trigger_lsc - trigger an LSC interrupt + * @adapter: + * + * Fire a link status change interrupt to start the watchdog. + **/ +static void e1000e_trigger_lsc(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + if (adapter->msix_entries) + ew32(ICS, E1000_ICS_OTHER); + else + ew32(ICS, E1000_ICS_LSC); +} + +void e1000e_up(struct e1000_adapter *adapter) +{ /* hardware has been reset, we need to reload some things */ e1000_configure(adapter); @@ -4159,13 +4160,7 @@ int e1000e_up(struct e1000_adapter *adapter) netif_start_queue(adapter->netdev); - /* fire a link change interrupt to start the watchdog */ - if (adapter->msix_entries) - ew32(ICS, E1000_ICS_LSC | E1000_ICR_OTHER); - else - ew32(ICS, E1000_ICS_LSC); - - return 0; + e1000e_trigger_lsc(adapter); } static void e1000e_flush_descriptors(struct e1000_adapter *adapter) @@ -4590,11 +4585,7 @@ static int e1000_open(struct net_device *netdev) hw->mac.get_link_status = true; pm_runtime_put(&pdev->dev); - /* fire a link status change interrupt to start the watchdog */ - if (adapter->msix_entries) - ew32(ICS, E1000_ICS_LSC | E1000_ICR_OTHER); - else - ew32(ICS, E1000_ICS_LSC); + e1000e_trigger_lsc(adapter); return 0; @@ -6631,7 +6622,7 @@ static int e1000e_pm_runtime_resume(struct device *dev) return rc; if (netdev->flags & IFF_UP) - rc = e1000e_up(adapter); + e1000e_up(adapter); return rc; } @@ -6822,13 +6813,8 @@ static void e1000_io_resume(struct pci_dev *pdev) e1000_init_manageability_pt(adapter); - if (netif_running(netdev)) { - if (e1000e_up(adapter)) { - dev_err(&pdev->dev, - "can't bring device back up after reset\n"); - return; - } - } + if (netif_running(netdev)) + e1000e_up(adapter); netif_device_attach(netdev); @@ -7465,6 +7451,7 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V), board_pch_spt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM2), board_pch_spt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V2), board_pch_spt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LBG_I219_LM3), board_pch_spt }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; @@ -7504,14 +7491,11 @@ static struct pci_driver e1000_driver = { **/ static int __init e1000_init_module(void) { - int ret; - pr_info("Intel(R) PRO/1000 Network Driver - %s\n", e1000e_driver_version); pr_info("Copyright(c) 1999 - 2015 Intel Corporation.\n"); - ret = pci_register_driver(&e1000_driver); - return ret; + return pci_register_driver(&e1000_driver); } module_init(e1000_init_module); diff --git a/drivers/net/ethernet/intel/fm10k/Makefile b/drivers/net/ethernet/intel/fm10k/Makefile index 08859dd220a8b..b006ff66d0286 100644 --- a/drivers/net/ethernet/intel/fm10k/Makefile +++ b/drivers/net/ethernet/intel/fm10k/Makefile @@ -1,7 +1,7 @@ ################################################################################ # # Intel Ethernet Switch Host Interface Driver -# Copyright(c) 2013 - 2014 Intel Corporation. +# Copyright(c) 2013 - 2015 Intel Corporation. # # This program is free software; you can redistribute it and/or modify it # under the terms and conditions of the GNU General Public License, @@ -27,7 +27,17 @@ obj-$(CONFIG_FM10K) += fm10k.o -fm10k-objs := fm10k_main.o fm10k_common.o fm10k_pci.o \ - fm10k_netdev.o fm10k_ethtool.o fm10k_pf.o fm10k_vf.o \ - fm10k_mbx.o fm10k_iov.o fm10k_tlv.o \ - fm10k_debugfs.o fm10k_ptp.o fm10k_dcbnl.o +fm10k-y := fm10k_main.o \ + fm10k_common.o \ + fm10k_pci.o \ + fm10k_ptp.o \ + fm10k_netdev.o \ + fm10k_ethtool.o \ + fm10k_pf.o \ + fm10k_vf.o \ + fm10k_mbx.o \ + fm10k_iov.o \ + fm10k_tlv.o + +fm10k-$(CONFIG_DEBUG_FS) += fm10k_debugfs.o +fm10k-$(CONFIG_DCB) += fm10k_dcbnl.o diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index fa26e20445a53..b34bb008b1045 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -23,6 +23,7 @@ #include <linux/types.h> #include <linux/etherdevice.h> +#include <linux/cpumask.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> #include <linux/pci.h> @@ -66,6 +67,7 @@ struct fm10k_l2_accel { enum fm10k_ring_state_t { __FM10K_TX_DETECT_HANG, __FM10K_HANG_CHECK_ARMED, + __FM10K_TX_XPS_INIT_DONE, }; #define check_for_tx_hang(ring) \ @@ -138,7 +140,7 @@ struct fm10k_ring { * different for DCB and RSS modes */ u8 qos_pc; /* priority class of queue */ - u16 vid; /* default vlan ID of queue */ + u16 vid; /* default VLAN ID of queue */ u16 count; /* amount of descriptors */ u16 next_to_alloc; @@ -164,7 +166,7 @@ struct fm10k_ring_container { unsigned int total_packets; /* total packets processed this int */ u16 work_limit; /* total work allowed per interrupt */ u16 itr; /* interrupt throttle rate value */ - u8 itr_scale; /* ITR adjustment scaler based on PCI speed */ + u8 itr_scale; /* ITR adjustment based on PCI speed */ u8 count; /* total number of rings in vector */ }; @@ -209,6 +211,7 @@ struct fm10k_q_vector { struct fm10k_ring_container rx, tx; struct napi_struct napi; + cpumask_t affinity_mask; char name[IFNAMSIZ + 9]; #ifdef CONFIG_DEBUG_FS @@ -419,7 +422,7 @@ static inline u16 fm10k_desc_unused(struct fm10k_ring *ring) (&(((union fm10k_rx_desc *)((R)->desc))[i])) #define FM10K_MAX_TXD_PWR 14 -#define FM10K_MAX_DATA_PER_TXD (1 << FM10K_MAX_TXD_PWR) +#define FM10K_MAX_DATA_PER_TXD BIT(FM10K_MAX_TXD_PWR) /* Tx Descriptors needed, worst case */ #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), FM10K_MAX_DATA_PER_TXD) @@ -440,7 +443,7 @@ union fm10k_ftag_info { struct { /* dglort and sglort combined into a single 32bit desc read */ __le32 glort; - /* upper 16 bits of vlan are reserved 0 for swpri_type_user */ + /* upper 16 bits of VLAN are reserved 0 for swpri_type_user */ __le32 vlan; } d; struct { @@ -557,5 +560,9 @@ int fm10k_get_ts_config(struct net_device *netdev, struct ifreq *ifr); int fm10k_set_ts_config(struct net_device *netdev, struct ifreq *ifr); /* DCB */ +#ifdef CONFIG_DCB void fm10k_dcbnl_set_ops(struct net_device *dev); +#else +static inline void fm10k_dcbnl_set_ops(struct net_device *dev) {} +#endif #endif /* _FM10K_H_ */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c index 5c7a4d7662d89..2be4361839db2 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c @@ -20,7 +20,6 @@ #include "fm10k.h" -#ifdef CONFIG_DCB /** * fm10k_dcbnl_ieee_getets - get the ETS configuration for the device * @dev: netdev interface for the device @@ -155,7 +154,6 @@ static const struct dcbnl_rtnl_ops fm10k_dcbnl_ops = { .setdcbx = fm10k_dcbnl_setdcbx, }; -#endif /* CONFIG_DCB */ /** * fm10k_dcbnl_set_ops - Configures dcbnl ops pointer for netdev * @dev: netdev interface for the device @@ -164,11 +162,9 @@ static const struct dcbnl_rtnl_ops fm10k_dcbnl_ops = { **/ void fm10k_dcbnl_set_ops(struct net_device *dev) { -#ifdef CONFIG_DCB struct fm10k_intfc *interface = netdev_priv(dev); struct fm10k_hw *hw = &interface->hw; if (hw->mac.type == fm10k_mac_pf) dev->dcbnl_ops = &fm10k_dcbnl_ops; -#endif /* CONFIG_DCB */ } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index 5304bc1fbecd4..5d6137faf7d17 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -18,8 +18,6 @@ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 */ -#ifdef CONFIG_DEBUG_FS - #include "fm10k.h" #include <linux/debugfs.h> @@ -258,5 +256,3 @@ void fm10k_dbg_exit(void) debugfs_remove_recursive(dbg_root); dbg_root = NULL; } - -#endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 109e2111bddaa..2f6a05b572288 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -127,7 +127,7 @@ static const struct fm10k_stats fm10k_gstrings_mbx_stats[] = { #define FM10K_MBX_STATS_LEN ARRAY_SIZE(fm10k_gstrings_mbx_stats) #define FM10K_QUEUE_STATS_LEN(_n) \ - ( (_n) * 2 * (sizeof(struct fm10k_queue_stats) / sizeof(u64))) + ((_n) * 2 * (sizeof(struct fm10k_queue_stats) / sizeof(u64))) #define FM10K_STATIC_STATS_LEN (FM10K_GLOBAL_STATS_LEN + \ FM10K_NETDEV_STATS_LEN + \ @@ -259,7 +259,8 @@ static int fm10k_get_sset_count(struct net_device *dev, int sset) stats_len += FM10K_DEBUG_STATS_LEN; if (iov_data) - stats_len += FM10K_MBX_STATS_LEN * iov_data->num_vfs; + stats_len += FM10K_MBX_STATS_LEN * + iov_data->num_vfs; } return stats_len; @@ -298,14 +299,16 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, if (interface->flags & FM10K_FLAG_DEBUG_STATS) { for (i = 0; i < FM10K_DEBUG_STATS_LEN; i++) { - p = (char *)interface + fm10k_gstrings_debug_stats[i].stat_offset; + p = (char *)interface + + fm10k_gstrings_debug_stats[i].stat_offset; *(data++) = (fm10k_gstrings_debug_stats[i].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } } for (i = 0; i < FM10K_MBX_STATS_LEN; i++) { - p = (char *)&interface->hw.mbx + fm10k_gstrings_mbx_stats[i].stat_offset; + p = (char *)&interface->hw.mbx + + fm10k_gstrings_mbx_stats[i].stat_offset; *(data++) = (fm10k_gstrings_mbx_stats[i].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } @@ -322,6 +325,7 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, if ((interface->flags & FM10K_FLAG_DEBUG_STATS) && iov_data) { for (i = 0; i < iov_data->num_vfs; i++) { struct fm10k_vf_info *vf_info; + vf_info = &iov_data->vf_info[i]; /* skip stats if we don't have a vf info */ @@ -331,7 +335,8 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, } for (j = 0; j < FM10K_MBX_STATS_LEN; j++) { - p = (char *)&vf_info->mbx + fm10k_gstrings_mbx_stats[j].stat_offset; + p = (char *)&vf_info->mbx + + fm10k_gstrings_mbx_stats[j].stat_offset; *(data++) = (fm10k_gstrings_mbx_stats[j].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } @@ -1020,7 +1025,6 @@ static int fm10k_set_priv_flags(struct net_device *netdev, u32 priv_flags) return 0; } - static u32 fm10k_get_reta_size(struct net_device __always_unused *netdev) { return FM10K_RETA_SIZE * FM10K_RETA_ENTRIES_PER_REG; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 1c17b6284daaa..b243c3cbe68fa 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -28,7 +28,7 @@ #include "fm10k.h" -#define DRV_VERSION "0.15.2-k" +#define DRV_VERSION "0.19.3-k" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = @@ -42,7 +42,7 @@ MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); /* single workqueue for entire fm10k driver */ -struct workqueue_struct *fm10k_workqueue = NULL; +struct workqueue_struct *fm10k_workqueue; /** * fm10k_init_module - Driver Registration Routine @@ -56,8 +56,7 @@ static int __init fm10k_init_module(void) pr_info("%s\n", fm10k_copyright); /* create driver workqueue */ - if (!fm10k_workqueue) - fm10k_workqueue = create_workqueue("fm10k"); + fm10k_workqueue = create_workqueue("fm10k"); fm10k_dbg_init(); @@ -80,7 +79,6 @@ static void __exit fm10k_exit_module(void) /* destroy driver workqueue */ flush_workqueue(fm10k_workqueue); destroy_workqueue(fm10k_workqueue); - fm10k_workqueue = NULL; } module_exit(fm10k_exit_module); @@ -917,7 +915,7 @@ static u8 fm10k_tx_desc_flags(struct sk_buff *skb, u32 tx_flags) /* set timestamping bits */ if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && likely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) - desc_flags |= FM10K_TXD_FLAG_TIME; + desc_flags |= FM10K_TXD_FLAG_TIME; /* set checksum offload bits */ desc_flags |= FM10K_SET_FLAG(tx_flags, FM10K_TX_FLAGS_CSUM, @@ -1462,7 +1460,7 @@ static int fm10k_poll(struct napi_struct *napi, int budget) * allow the budget to go below 1 because we'll exit polling */ if (q_vector->rx.count > 1) - per_ring_budget = max(budget/q_vector->rx.count, 1); + per_ring_budget = max(budget / q_vector->rx.count, 1); else per_ring_budget = budget; @@ -1998,8 +1996,10 @@ int fm10k_init_queueing_scheme(struct fm10k_intfc *interface) /* Allocate memory for queues */ err = fm10k_alloc_q_vectors(interface); - if (err) + if (err) { + fm10k_reset_msix_capability(interface); return err; + } /* Map rings to devices, and map devices to physical queues */ fm10k_assign_rings(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 2bce47490723f..98202c3d591c8 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -57,7 +57,7 @@ static u16 fm10k_fifo_unused(struct fm10k_mbx_fifo *fifo) } /** - * fm10k_fifo_empty - Test to verify if fifo is empty + * fm10k_fifo_empty - Test to verify if FIFO is empty * @fifo: pointer to FIFO * * This function returns true if the FIFO is empty, else false @@ -72,7 +72,7 @@ static bool fm10k_fifo_empty(struct fm10k_mbx_fifo *fifo) * @fifo: pointer to FIFO * @offset: offset to add to head * - * This function returns the indices into the fifo based on head + offset + * This function returns the indices into the FIFO based on head + offset **/ static u16 fm10k_fifo_head_offset(struct fm10k_mbx_fifo *fifo, u16 offset) { @@ -84,7 +84,7 @@ static u16 fm10k_fifo_head_offset(struct fm10k_mbx_fifo *fifo, u16 offset) * @fifo: pointer to FIFO * @offset: offset to add to tail * - * This function returns the indices into the fifo based on tail + offset + * This function returns the indices into the FIFO based on tail + offset **/ static u16 fm10k_fifo_tail_offset(struct fm10k_mbx_fifo *fifo, u16 offset) { @@ -160,7 +160,7 @@ static u16 fm10k_mbx_index_len(struct fm10k_mbx_info *mbx, u16 head, u16 tail) /** * fm10k_mbx_tail_add - Determine new tail value with added offset * @mbx: pointer to mailbox - * @offset: length to add to head offset + * @offset: length to add to tail offset * * This function takes the local tail index and recomputes it for * a given length added as an offset. @@ -176,7 +176,7 @@ static u16 fm10k_mbx_tail_add(struct fm10k_mbx_info *mbx, u16 offset) /** * fm10k_mbx_tail_sub - Determine new tail value with subtracted offset * @mbx: pointer to mailbox - * @offset: length to add to head offset + * @offset: length to add to tail offset * * This function takes the local tail index and recomputes it for * a given length added as an offset. @@ -240,7 +240,7 @@ static u16 fm10k_mbx_pushed_tail_len(struct fm10k_mbx_info *mbx) } /** - * fm10k_fifo_write_copy - pulls data off of msg and places it in fifo + * fm10k_fifo_write_copy - pulls data off of msg and places it in FIFO * @fifo: pointer to FIFO * @msg: message array to populate * @tail_offset: additional offset to add to tail pointer @@ -336,6 +336,7 @@ static u16 fm10k_mbx_validate_msg_size(struct fm10k_mbx_info *mbx, u16 len) /** * fm10k_mbx_write_copy - pulls data off of Tx FIFO and places it in mbmem + * @hw: pointer to hardware structure * @mbx: pointer to mailbox * * This function will take a section of the Tx FIFO and copy it into the @@ -711,7 +712,7 @@ static bool fm10k_mbx_tx_complete(struct fm10k_mbx_info *mbx) * @hw: pointer to hardware structure * @mbx: pointer to mailbox * - * This function dequeues messages and hands them off to the tlv parser. + * This function dequeues messages and hands them off to the TLV parser. * It will return the number of messages processed when called. **/ static u16 fm10k_mbx_dequeue_rx(struct fm10k_hw *hw, @@ -903,7 +904,7 @@ static void fm10k_mbx_create_disconnect_hdr(struct fm10k_mbx_info *mbx) } /** - * fm10k_mbx_create_fake_disconnect_hdr - Generate a false disconnect mailbox header + * fm10k_mbx_create_fake_disconnect_hdr - Generate a false disconnect mbox hdr * @mbx: pointer to mailbox * * This function creates a fake disconnect header for loading into remote @@ -924,7 +925,7 @@ static void fm10k_mbx_create_fake_disconnect_hdr(struct fm10k_mbx_info *mbx) } /** - * fm10k_mbx_create_error_msg - Generate a error message + * fm10k_mbx_create_error_msg - Generate an error message * @mbx: pointer to mailbox * @err: local error encountered * @@ -957,7 +958,6 @@ static void fm10k_mbx_create_error_msg(struct fm10k_mbx_info *mbx, s32 err) /** * fm10k_mbx_validate_msg_hdr - Validate common fields in the message header * @mbx: pointer to mailbox - * @msg: message array to read * * This function will parse up the fields in the mailbox header and return * an error if the header contains any of a number of invalid configurations @@ -1021,11 +1021,12 @@ static s32 fm10k_mbx_validate_msg_hdr(struct fm10k_mbx_info *mbx) /** * fm10k_mbx_create_reply - Generate reply based on state and remote head + * @hw: pointer to hardware structure * @mbx: pointer to mailbox * @head: acknowledgement number * * This function will generate an outgoing message based on the current - * mailbox state and the remote fifo head. It will return the length + * mailbox state and the remote FIFO head. It will return the length * of the outgoing message excluding header on success, and a negative value * on error. **/ @@ -1151,8 +1152,8 @@ static void fm10k_mbx_connect_reset(struct fm10k_mbx_info *mbx) /** * fm10k_mbx_process_connect - Process connect header + * @hw: pointer to hardware structure * @mbx: pointer to mailbox - * @msg: message array to process * * This function will read an incoming connect header and reply with the * appropriate message. It will return a value indicating the number of @@ -1198,6 +1199,7 @@ static s32 fm10k_mbx_process_connect(struct fm10k_hw *hw, /** * fm10k_mbx_process_data - Process data header + * @hw: pointer to hardware structure * @mbx: pointer to mailbox * * This function will read an incoming data header and reply with the @@ -1239,6 +1241,7 @@ static s32 fm10k_mbx_process_data(struct fm10k_hw *hw, /** * fm10k_mbx_process_disconnect - Process disconnect header + * @hw: pointer to hardware structure * @mbx: pointer to mailbox * * This function will read an incoming disconnect header and reply with the @@ -1291,6 +1294,7 @@ static s32 fm10k_mbx_process_disconnect(struct fm10k_hw *hw, /** * fm10k_mbx_process_error - Process error header + * @hw: pointer to hardware structure * @mbx: pointer to mailbox * * This function will read an incoming error header and reply with the @@ -1560,7 +1564,7 @@ static s32 fm10k_mbx_register_handlers(struct fm10k_mbx_info *mbx, * @id: ID reference for PF as it supports up to 64 PF/VF mailboxes * * This function initializes the mailbox for use. It will split the - * buffer provided an use that th populate both the Tx and Rx FIFO by + * buffer provided and use that to populate both the Tx and Rx FIFO by * evenly splitting it. In order to allow for easy masking of head/tail * the value reported in size must be a power of 2 and is reported in * DWORDs, not bytes. Any invalid values will cause the mailbox to return @@ -1637,7 +1641,7 @@ s32 fm10k_pfvf_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, * fm10k_sm_mbx_create_data_hdr - Generate a mailbox header for local FIFO * @mbx: pointer to mailbox * - * This function returns a connection mailbox header + * This function returns a data mailbox header **/ static void fm10k_sm_mbx_create_data_hdr(struct fm10k_mbx_info *mbx) { @@ -1730,8 +1734,6 @@ static s32 fm10k_sm_mbx_connect(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx) fm10k_sm_mbx_create_connect_hdr(mbx, 0); fm10k_mbx_write(hw, mbx); - /* enable interrupt and notify other party of new message */ - return 0; } @@ -1775,7 +1777,7 @@ static void fm10k_sm_mbx_disconnect(struct fm10k_hw *hw, } /** - * fm10k_mbx_validate_fifo_hdr - Validate fields in the remote FIFO header + * fm10k_sm_mbx_validate_fifo_hdr - Validate fields in the remote FIFO header * @mbx: pointer to mailbox * * This function will parse up the fields in the mailbox header and return @@ -1853,7 +1855,7 @@ static void fm10k_sm_mbx_process_error(struct fm10k_mbx_info *mbx) } /** - * fm10k_sm_mbx_create_error_message - Process an error in FIFO hdr + * fm10k_sm_mbx_create_error_msg - Process an error in FIFO header * @mbx: pointer to mailbox * @err: local error encountered * @@ -1883,6 +1885,7 @@ static void fm10k_sm_mbx_create_error_msg(struct fm10k_mbx_info *mbx, s32 err) * fm10k_sm_mbx_receive - Take message from Rx mailbox FIFO and put it in Rx * @hw: pointer to hardware structure * @mbx: pointer to mailbox + * @tail: tail index of message * * This function will dequeue one message from the Rx switch manager mailbox * FIFO and place it in the Rx mailbox FIFO for processing by software. @@ -1922,6 +1925,7 @@ static s32 fm10k_sm_mbx_receive(struct fm10k_hw *hw, * fm10k_sm_mbx_transmit - Take message from Tx and put it in Tx mailbox FIFO * @hw: pointer to hardware structure * @mbx: pointer to mailbox + * @head: head index of message * * This function will dequeue one message from the Tx mailbox FIFO and place * it in the Tx switch manager mailbox FIFO for processing by hardware. @@ -1961,11 +1965,12 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /** * fm10k_sm_mbx_create_reply - Generate reply based on state and remote head + * @hw: pointer to hardware structure * @mbx: pointer to mailbox * @head: acknowledgement number * * This function will generate an outgoing message based on the current - * mailbox state and the remote fifo head. It will return the length + * mailbox state and the remote FIFO head. It will return the length * of the outgoing message excluding header on success, and a negative value * on error. **/ @@ -2077,7 +2082,7 @@ send_reply: } /** - * fm10k_sm_mbx_process - Process mailbox switch mailbox interrupt + * fm10k_sm_mbx_process - Process switch manager mailbox interrupt * @hw: pointer to hardware structure * @mbx: pointer to mailbox * @@ -2133,13 +2138,19 @@ fifo_err: * @mbx: pointer to mailbox * @msg_data: handlers for mailbox events * - * This function for now is used to stub out the PF/SM mailbox + * This function initializes the PF/SM mailbox for use. It will split the + * buffer provided and use that to populate both the Tx and Rx FIFO by + * evenly splitting it. In order to allow for easy masking of head/tail + * the value reported in size must be a power of 2 and is reported in + * DWORDs, not bytes. Any invalid values will cause the mailbox to return + * error. **/ s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, const struct fm10k_msg_data *msg_data) { mbx->mbx_reg = FM10K_GMBX; mbx->mbmem_reg = FM10K_MBMEM_PF(0); + /* start out in closed state */ mbx->state = FM10K_STATE_CLOSED; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h index c4f18a8f176c9..245a0a3dc32e0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h @@ -128,11 +128,11 @@ enum fm10k_mbx_state { * The maximum message size is provided during connect to avoid * jamming the mailbox with messages that do not fit. * Err_no: Error number - Applies only to error headers - * The error number provides a indication of the type of error + * The error number provides an indication of the type of error * experienced. */ -/* macros for retriving and setting header values */ +/* macros for retrieving and setting header values */ #define FM10K_MSG_HDR_MASK(name) \ ((0x1u << FM10K_MSG_##name##_SIZE) - 1) #define FM10K_MSG_HDR_FIELD_SET(value, name) \ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 79f6b7dd23621..662569d5b7c01 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -20,7 +20,7 @@ #include "fm10k.h" #include <linux/vmalloc.h> -#if IS_ENABLED(CONFIG_FM10K_VXLAN) +#ifdef CONFIG_FM10K_VXLAN #include <net/vxlan.h> #endif /* CONFIG_FM10K_VXLAN */ @@ -556,11 +556,11 @@ int fm10k_open(struct net_device *netdev) if (err) goto err_set_queues; -#if IS_ENABLED(CONFIG_FM10K_VXLAN) +#ifdef CONFIG_FM10K_VXLAN /* update VXLAN port configuration */ vxlan_get_rx_port(netdev); - #endif + fm10k_up(interface); return 0; @@ -608,7 +608,7 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) unsigned int r_idx = skb->queue_mapping; int err; - if ((skb->protocol == htons(ETH_P_8021Q)) && + if ((skb->protocol == htons(ETH_P_8021Q)) && !skb_vlan_tag_present(skb)) { /* FM10K only supports hardware tagging, any tags in frame * are considered 2nd level or "outer" tags @@ -632,7 +632,7 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - /* locate vlan header */ + /* locate VLAN header */ vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); /* pull the 2 key pieces of data out of it */ @@ -705,7 +705,7 @@ static void fm10k_tx_timeout(struct net_device *netdev) } else { netif_info(interface, drv, netdev, "Fake Tx hang detected with timeout of %d seconds\n", - netdev->watchdog_timeo/HZ); + netdev->watchdog_timeo / HZ); /* fake Tx hang - increase the kernel timeout */ if (netdev->watchdog_timeo < TX_TIMEO_LIMIT) @@ -778,7 +778,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) if (!set) clear_bit(vid, interface->active_vlans); - /* disable the default VID on ring if we have an active VLAN */ + /* disable the default VLAN ID on ring if we have an active VLAN */ for (i = 0; i < interface->num_rx_queues; i++) { struct fm10k_ring *rx_ring = interface->rx_ring[i]; u16 rx_vid = rx_ring->vid & (VLAN_N_VID - 1); @@ -789,7 +789,9 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) rx_ring->vid &= ~FM10K_VLAN_CLEAR; } - /* Do not remove default VID related entries from VLAN and MAC tables */ + /* Do not remove default VLAN ID related entries from VLAN and MAC + * tables + */ if (!set && vid == hw->mac.default_vid) return 0; @@ -814,7 +816,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) if (err) goto err_out; - /* set vid prior to syncing/unsyncing the VLAN */ + /* set VLAN ID prior to syncing/unsyncing the VLAN */ interface->vid = vid + (set ? VLAN_N_VID : 0); /* Update the unicast and multicast address list to add/drop VLAN */ @@ -1151,6 +1153,7 @@ static struct rtnl_link_stats64 *fm10k_get_stats64(struct net_device *netdev, int fm10k_setup_tc(struct net_device *dev, u8 tc) { struct fm10k_intfc *interface = netdev_priv(dev); + int err; /* Currently only the PF supports priority classes */ if (tc && (interface->hw.mac.type != fm10k_mac_pf)) @@ -1175,17 +1178,30 @@ int fm10k_setup_tc(struct net_device *dev, u8 tc) netdev_reset_tc(dev); netdev_set_num_tc(dev, tc); - fm10k_init_queueing_scheme(interface); + err = fm10k_init_queueing_scheme(interface); + if (err) + goto err_queueing_scheme; - fm10k_mbx_request_irq(interface); + err = fm10k_mbx_request_irq(interface); + if (err) + goto err_mbx_irq; - if (netif_running(dev)) - fm10k_open(dev); + err = netif_running(dev) ? fm10k_open(dev) : 0; + if (err) + goto err_open; /* flag to indicate SWPRI has yet to be updated */ interface->flags |= FM10K_FLAG_SWPRI_CONFIG; return 0; +err_open: + fm10k_mbx_free_irq(interface); +err_mbx_irq: + fm10k_clear_queueing_scheme(interface); +err_queueing_scheme: + netif_device_detach(dev); + + return err; } static int fm10k_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) @@ -1355,7 +1371,7 @@ static netdev_features_t fm10k_features_check(struct sk_buff *skb, if (!skb->encapsulation || fm10k_tx_encap_offload(skb)) return features; - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } static const struct net_device_ops fm10k_netdev_ops = { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 15d8e10c25048..4eb7a6fa6b0dd 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -180,12 +180,19 @@ static void fm10k_reinit(struct fm10k_intfc *interface) err = fm10k_init_queueing_scheme(interface); if (err) { - dev_err(&interface->pdev->dev, "init_queueing_scheme failed: %d\n", err); + dev_err(&interface->pdev->dev, + "init_queueing_scheme failed: %d\n", err); goto reinit_err; } /* reassociate interrupts */ - fm10k_mbx_request_irq(interface); + err = fm10k_mbx_request_irq(interface); + if (err) + goto err_mbx_irq; + + err = fm10k_hw_ready(interface); + if (err) + goto err_open; /* update hardware address for VFs if perm_addr has changed */ if (hw->mac.type == fm10k_mac_vf) { @@ -205,14 +212,23 @@ static void fm10k_reinit(struct fm10k_intfc *interface) /* reset clock */ fm10k_ts_reset(interface); - if (netif_running(netdev)) - fm10k_open(netdev); + err = netif_running(netdev) ? fm10k_open(netdev) : 0; + if (err) + goto err_open; fm10k_iov_resume(interface->pdev); + rtnl_unlock(); + + clear_bit(__FM10K_RESETTING, &interface->state); + + return; +err_open: + fm10k_mbx_free_irq(interface); +err_mbx_irq: + fm10k_clear_queueing_scheme(interface); reinit_err: - if (err) - netif_device_detach(netdev); + netif_device_detach(netdev); rtnl_unlock(); @@ -600,6 +616,13 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, fm10k_write_reg(hw, FM10K_PFVTCTL(reg_idx), FM10K_PFVTCTL_FTAG_DESC_ENABLE); + /* Initialize XPS */ + if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, &ring->state) && + ring->q_vector) + netif_set_xps_queue(ring->netdev, + &ring->q_vector->affinity_mask, + ring->queue_index); + /* enable queue */ fm10k_write_reg(hw, FM10K_TXDCTL(reg_idx), txdctl); } @@ -715,7 +738,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* assign default VLAN to queue */ ring->vid = hw->mac.default_vid; - /* if we have an active VLAN, disable default VID */ + /* if we have an active VLAN, disable default VLAN ID */ if (test_bit(hw->mac.default_vid, interface->active_vlans)) ring->vid |= FM10K_VLAN_CLEAR; @@ -889,7 +912,7 @@ static irqreturn_t fm10k_msix_mbx_vf(int __always_unused irq, void *data) fm10k_mbx_unlock(interface); } - hw->mac.get_host_state = 1; + hw->mac.get_host_state = true; fm10k_service_event_schedule(interface); return IRQ_HANDLED; @@ -919,7 +942,7 @@ void fm10k_netpoll(struct net_device *netdev) #endif #define FM10K_ERR_MSG(type) case (type): error = #type; break static void fm10k_handle_fault(struct fm10k_intfc *interface, int type, - struct fm10k_fault *fault) + struct fm10k_fault *fault) { struct pci_dev *pdev = interface->pdev; struct fm10k_hw *hw = &interface->hw; @@ -1105,7 +1128,7 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) } /* we should validate host state after interrupt event */ - hw->mac.get_host_state = 1; + hw->mac.get_host_state = true; /* validate host state, and handle VF mailboxes in the service task */ fm10k_service_event_schedule(interface); @@ -1124,6 +1147,10 @@ void fm10k_mbx_free_irq(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; int itr_reg; + /* no mailbox IRQ to free if MSI-X is not enabled */ + if (!interface->msix_entries) + return; + /* disconnect the mailbox */ hw->mbx.ops.disconnect(hw, &hw->mbx); @@ -1164,7 +1191,7 @@ static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results, /* MAC was changed so we need reset */ if (is_valid_ether_addr(hw->mac.perm_addr) && - memcmp(hw->mac.perm_addr, hw->mac.addr, ETH_ALEN)) + !ether_addr_equal(hw->mac.perm_addr, hw->mac.addr)) interface->flags |= FM10K_FLAG_RESET_REQUESTED; /* VLAN override was changed, or default VLAN changed */ @@ -1292,7 +1319,7 @@ static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results, if (!fm10k_glort_valid_pf(hw, glort)) return FM10K_ERR_PARAM; - /* verify VID is valid */ + /* verify VLAN ID is valid */ if (pvid >= FM10K_VLAN_TABLE_VID_MAX) return FM10K_ERR_PARAM; @@ -1411,14 +1438,14 @@ static int fm10k_mbx_request_irq_pf(struct fm10k_intfc *interface) } /* Enable interrupts w/ no moderation for "other" interrupts */ - fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_PCIeFault), other_itr); - fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_SwitchUpDown), other_itr); - fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_SRAM), other_itr); - fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_MaxHoldTime), other_itr); - fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_VFLR), other_itr); + fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_pcie_fault), other_itr); + fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_switch_up_down), other_itr); + fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_sram), other_itr); + fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_max_hold_time), other_itr); + fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_vflr), other_itr); /* Enable interrupts w/ moderation for mailbox */ - fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_Mailbox), mbx_itr); + fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_mailbox), mbx_itr); /* Enable individual interrupt causes */ fm10k_write_reg(hw, FM10K_EIMR, FM10K_EIMR_ENABLE(PCA_FAULT) | @@ -1446,10 +1473,15 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface) err = fm10k_mbx_request_irq_pf(interface); else err = fm10k_mbx_request_irq_vf(interface); + if (err) + return err; /* connect mailbox */ - if (!err) - err = hw->mbx.ops.connect(hw, &hw->mbx); + err = hw->mbx.ops.connect(hw, &hw->mbx); + + /* if the mailbox failed to connect, then free IRQ */ + if (err) + fm10k_mbx_free_irq(interface); return err; } @@ -1478,8 +1510,10 @@ void fm10k_qv_free_irq(struct fm10k_intfc *interface) if (!q_vector->tx.count && !q_vector->rx.count) continue; - /* disable interrupts */ + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(entry->vector, NULL); + /* disable interrupts */ writel(FM10K_ITR_MASK_SET, q_vector->itr); free_irq(entry->vector, q_vector); @@ -1537,6 +1571,9 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) goto err_out; } + /* assign the mask for this irq */ + irq_set_affinity_hint(entry->vector, &q_vector->affinity_mask); + /* Enable q_vector */ writel(FM10K_ITR_ENABLE, q_vector->itr); @@ -1557,8 +1594,10 @@ err_out: if (!q_vector->tx.count && !q_vector->rx.count) continue; - /* disable interrupts */ + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(entry->vector, NULL); + /* disable interrupts */ writel(FM10K_ITR_MASK_SET, q_vector->itr); free_irq(entry->vector, q_vector); @@ -1596,7 +1635,7 @@ void fm10k_up(struct fm10k_intfc *interface) netif_tx_start_all_queues(interface->netdev); /* kick off the service timer now */ - hw->mac.get_host_state = 1; + hw->mac.get_host_state = true; mod_timer(&interface->service_timer, jiffies); } @@ -1857,17 +1896,18 @@ static void fm10k_slot_warn(struct fm10k_intfc *interface) return; } - if (max_gts < expected_gts) { - dev_warn(&interface->pdev->dev, - "This device requires %dGT/s of bandwidth for optimal performance.\n", - expected_gts); - dev_warn(&interface->pdev->dev, - "A %sslot with x%d lanes is suggested.\n", - (hw->bus_caps.speed == fm10k_bus_speed_2500 ? "2.5GT/s " : - hw->bus_caps.speed == fm10k_bus_speed_5000 ? "5.0GT/s " : - hw->bus_caps.speed == fm10k_bus_speed_8000 ? "8.0GT/s " : ""), - hw->bus_caps.width); - } + if (max_gts >= expected_gts) + return; + + dev_warn(&interface->pdev->dev, + "This device requires %dGT/s of bandwidth for optimal performance.\n", + expected_gts); + dev_warn(&interface->pdev->dev, + "A %sslot with x%d lanes is suggested.\n", + (hw->bus_caps.speed == fm10k_bus_speed_2500 ? "2.5GT/s " : + hw->bus_caps.speed == fm10k_bus_speed_5000 ? "5.0GT/s " : + hw->bus_caps.speed == fm10k_bus_speed_8000 ? "8.0GT/s " : ""), + hw->bus_caps.width); } /** @@ -1881,8 +1921,7 @@ static void fm10k_slot_warn(struct fm10k_intfc *interface) * The OS initialization, configuring of the interface private structure, * and a hardware reset occur. **/ -static int fm10k_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) +static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; struct fm10k_intfc *interface; @@ -2107,16 +2146,22 @@ static int fm10k_resume(struct pci_dev *pdev) rtnl_lock(); err = fm10k_init_queueing_scheme(interface); - if (!err) { - fm10k_mbx_request_irq(interface); - if (netif_running(netdev)) - err = fm10k_open(netdev); - } + if (err) + goto err_queueing_scheme; - rtnl_unlock(); + err = fm10k_mbx_request_irq(interface); + if (err) + goto err_mbx_irq; + err = fm10k_hw_ready(interface); if (err) - return err; + goto err_open; + + err = netif_running(netdev) ? fm10k_open(netdev) : 0; + if (err) + goto err_open; + + rtnl_unlock(); /* assume host is not ready, to prevent race with watchdog in case we * actually don't have connection to the switch @@ -2134,6 +2179,14 @@ static int fm10k_resume(struct pci_dev *pdev) netif_device_attach(netdev); return 0; +err_open: + fm10k_mbx_free_irq(interface); +err_mbx_irq: + fm10k_clear_queueing_scheme(interface); +err_queueing_scheme: + rtnl_unlock(); + + return err; } /** @@ -2286,7 +2339,8 @@ static void fm10k_io_resume(struct pci_dev *pdev) err = fm10k_init_queueing_scheme(interface); if (err) { - dev_err(&interface->pdev->dev, "init_queueing_scheme failed: %d\n", err); + dev_err(&interface->pdev->dev, + "init_queueing_scheme failed: %d\n", err); return; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 8b9b6ba5b92bf..62ccebc5f7288 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -266,7 +266,6 @@ static s32 fm10k_read_mac_addr_pf(struct fm10k_hw *hw) { u8 perm_addr[ETH_ALEN]; u32 serial_num; - int i; serial_num = fm10k_read_reg(hw, FM10K_SM_AREA(1)); @@ -288,10 +287,8 @@ static s32 fm10k_read_mac_addr_pf(struct fm10k_hw *hw) perm_addr[4] = (u8)(serial_num >> 8); perm_addr[5] = (u8)(serial_num); - for (i = 0; i < ETH_ALEN; i++) { - hw->mac.perm_addr[i] = perm_addr[i]; - hw->mac.addr[i] = perm_addr[i]; - } + ether_addr_copy(hw->mac.perm_addr, perm_addr); + ether_addr_copy(hw->mac.addr, perm_addr); return 0; } @@ -332,7 +329,7 @@ static s32 fm10k_update_xc_addr_pf(struct fm10k_hw *hw, u16 glort, /* clear set bit from VLAN ID */ vid &= ~FM10K_VLAN_CLEAR; - /* if glort or vlan are not valid return error */ + /* if glort or VLAN are not valid return error */ if (!fm10k_glort_valid_pf(hw, glort) || vid >= FM10K_VLAN_TABLE_VID_MAX) return FM10K_ERR_PARAM; @@ -417,6 +414,7 @@ static s32 fm10k_update_xcast_mode_pf(struct fm10k_hw *hw, u16 glort, u8 mode) if (mode > FM10K_XCAST_MODE_NONE) return FM10K_ERR_PARAM; + /* if glort is not valid return error */ if (!fm10k_glort_valid_pf(hw, glort)) return FM10K_ERR_PARAM; @@ -924,7 +922,7 @@ err_out: txqctl |= (vf_idx << FM10K_TXQCTL_TC_SHIFT) | FM10K_TXQCTL_VF | vf_idx; - /* assign VID */ + /* assign VLAN ID */ for (i = 0; i < queues_per_pool; i++) fm10k_write_reg(hw, FM10K_TXQCTL(vf_q_idx + i), txqctl); @@ -1175,14 +1173,14 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, } /** - * fm10k_iov_select_vid - Select correct default VID + * fm10k_iov_select_vid - Select correct default VLAN ID * @hw: Pointer to hardware structure - * @vid: VID to correct + * @vid: VLAN ID to correct * - * Will report an error if VID is out of range. For VID = 0, it will return - * either the pf_vid or sw_vid depending on which one is set. + * Will report an error if the VLAN ID is out of range. For VID = 0, it will + * return either the pf_vid or sw_vid depending on which one is set. */ -static inline s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) +static s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) { if (!vid) return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid; @@ -1235,8 +1233,8 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, err = fm10k_iov_select_vid(vf_info, (u16)vid); if (err < 0) return err; - else - vid = err; + + vid = err; /* update VSI info for VF in regards to VLAN table */ err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set); @@ -1252,7 +1250,7 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, /* block attempts to set MAC for a locked device */ if (is_valid_ether_addr(vf_info->mac) && - memcmp(mac, vf_info->mac, ETH_ALEN)) + !ether_addr_equal(mac, vf_info->mac)) return FM10K_ERR_PARAM; set = !(vlan & FM10K_VLAN_CLEAR); @@ -1261,8 +1259,8 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, err = fm10k_iov_select_vid(vf_info, vlan); if (err < 0) return err; - else - vlan = (u16)err; + + vlan = (u16)err; /* notify switch of request for new unicast address */ err = hw->mac.ops.update_uc_addr(hw, vf_info->glort, @@ -1287,8 +1285,8 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, err = fm10k_iov_select_vid(vf_info, vlan); if (err < 0) return err; - else - vlan = (u16)err; + + vlan = (u16)err; /* notify switch of request for new multicast address */ err = hw->mac.ops.update_mc_addr(hw, vf_info->glort, @@ -1416,14 +1414,6 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, return err; } -const struct fm10k_msg_data fm10k_iov_msg_data_pf[] = { - FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test), - FM10K_VF_MSG_MSIX_HANDLER(fm10k_iov_msg_msix_pf), - FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_mac_vlan_pf), - FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_iov_msg_lport_state_pf), - FM10K_TLV_MSG_ERROR_HANDLER(fm10k_tlv_msg_error), -}; - /** * fm10k_update_stats_hw_pf - Updates hardware related statistics of PF * @hw: pointer to hardware structure @@ -1451,9 +1441,10 @@ static void fm10k_update_hw_stats_pf(struct fm10k_hw *hw, xec = fm10k_read_hw_stats_32b(hw, FM10K_STATS_XEC, &stats->xec); vlan_drop = fm10k_read_hw_stats_32b(hw, FM10K_STATS_VLAN_DROP, &stats->vlan_drop); - loopback_drop = fm10k_read_hw_stats_32b(hw, - FM10K_STATS_LOOPBACK_DROP, - &stats->loopback_drop); + loopback_drop = + fm10k_read_hw_stats_32b(hw, + FM10K_STATS_LOOPBACK_DROP, + &stats->loopback_drop); nodesc_drop = fm10k_read_hw_stats_32b(hw, FM10K_STATS_NODESC_DROP, &stats->nodesc_drop); @@ -1698,8 +1689,8 @@ const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[] = { * * This handler configures the default VLAN for the PF **/ -s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) +static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, + struct fm10k_mbx_info *mbx) { u16 glort, pvid; u32 pvid_update; @@ -1718,7 +1709,7 @@ s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, if (!fm10k_glort_valid_pf(hw, glort)) return FM10K_ERR_PARAM; - /* verify VID is valid */ + /* verify VLAN ID is valid */ if (pvid >= FM10K_VLAN_TABLE_VID_MAX) return FM10K_ERR_PARAM; @@ -1875,39 +1866,39 @@ static const struct fm10k_msg_data fm10k_msg_data_pf[] = { FM10K_TLV_MSG_ERROR_HANDLER(fm10k_tlv_msg_error), }; -static struct fm10k_mac_ops mac_ops_pf = { - .get_bus_info = &fm10k_get_bus_info_generic, - .reset_hw = &fm10k_reset_hw_pf, - .init_hw = &fm10k_init_hw_pf, - .start_hw = &fm10k_start_hw_generic, - .stop_hw = &fm10k_stop_hw_generic, - .update_vlan = &fm10k_update_vlan_pf, - .read_mac_addr = &fm10k_read_mac_addr_pf, - .update_uc_addr = &fm10k_update_uc_addr_pf, - .update_mc_addr = &fm10k_update_mc_addr_pf, - .update_xcast_mode = &fm10k_update_xcast_mode_pf, - .update_int_moderator = &fm10k_update_int_moderator_pf, - .update_lport_state = &fm10k_update_lport_state_pf, - .update_hw_stats = &fm10k_update_hw_stats_pf, - .rebind_hw_stats = &fm10k_rebind_hw_stats_pf, - .configure_dglort_map = &fm10k_configure_dglort_map_pf, - .set_dma_mask = &fm10k_set_dma_mask_pf, - .get_fault = &fm10k_get_fault_pf, - .get_host_state = &fm10k_get_host_state_pf, - .adjust_systime = &fm10k_adjust_systime_pf, - .read_systime = &fm10k_read_systime_pf, +static const struct fm10k_mac_ops mac_ops_pf = { + .get_bus_info = fm10k_get_bus_info_generic, + .reset_hw = fm10k_reset_hw_pf, + .init_hw = fm10k_init_hw_pf, + .start_hw = fm10k_start_hw_generic, + .stop_hw = fm10k_stop_hw_generic, + .update_vlan = fm10k_update_vlan_pf, + .read_mac_addr = fm10k_read_mac_addr_pf, + .update_uc_addr = fm10k_update_uc_addr_pf, + .update_mc_addr = fm10k_update_mc_addr_pf, + .update_xcast_mode = fm10k_update_xcast_mode_pf, + .update_int_moderator = fm10k_update_int_moderator_pf, + .update_lport_state = fm10k_update_lport_state_pf, + .update_hw_stats = fm10k_update_hw_stats_pf, + .rebind_hw_stats = fm10k_rebind_hw_stats_pf, + .configure_dglort_map = fm10k_configure_dglort_map_pf, + .set_dma_mask = fm10k_set_dma_mask_pf, + .get_fault = fm10k_get_fault_pf, + .get_host_state = fm10k_get_host_state_pf, + .adjust_systime = fm10k_adjust_systime_pf, + .read_systime = fm10k_read_systime_pf, }; -static struct fm10k_iov_ops iov_ops_pf = { - .assign_resources = &fm10k_iov_assign_resources_pf, - .configure_tc = &fm10k_iov_configure_tc_pf, - .assign_int_moderator = &fm10k_iov_assign_int_moderator_pf, +static const struct fm10k_iov_ops iov_ops_pf = { + .assign_resources = fm10k_iov_assign_resources_pf, + .configure_tc = fm10k_iov_configure_tc_pf, + .assign_int_moderator = fm10k_iov_assign_int_moderator_pf, .assign_default_mac_vlan = fm10k_iov_assign_default_mac_vlan_pf, - .reset_resources = &fm10k_iov_reset_resources_pf, - .set_lport = &fm10k_iov_set_lport_pf, - .reset_lport = &fm10k_iov_reset_lport_pf, - .update_stats = &fm10k_iov_update_stats_pf, - .report_timestamp = &fm10k_iov_report_timestamp_pf, + .reset_resources = fm10k_iov_reset_resources_pf, + .set_lport = fm10k_iov_set_lport_pf, + .reset_lport = fm10k_iov_reset_lport_pf, + .update_stats = fm10k_iov_update_stats_pf, + .report_timestamp = fm10k_iov_report_timestamp_pf, }; static s32 fm10k_get_invariants_pf(struct fm10k_hw *hw) @@ -1917,9 +1908,9 @@ static s32 fm10k_get_invariants_pf(struct fm10k_hw *hw) return fm10k_sm_mbx_init(hw, &hw->mbx, fm10k_msg_data_pf); } -struct fm10k_info fm10k_pf_info = { +const struct fm10k_info fm10k_pf_info = { .mac = fm10k_mac_pf, - .get_invariants = &fm10k_get_invariants_pf, + .get_invariants = fm10k_get_invariants_pf, .mac_ops = &mac_ops_pf, .iov_ops = &iov_ops_pf, }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h index 40a0dbc62a04a..b2d96b45ca3cc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h @@ -1,5 +1,5 @@ /* Intel Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -74,6 +74,11 @@ enum fm10k_pf_tlv_attr_id_v1 { #define FM10K_MSG_UPDATE_PVID_PVID_SHIFT 16 #define FM10K_MSG_UPDATE_PVID_PVID_SIZE 16 +/* The following data structures are overlayed directly onto TLV mailbox + * messages, and must not break 4 byte alignment. Ensure the structures line + * up correctly as per their TLV definition. + */ + struct fm10k_mac_update { __le32 mac_lower; __le16 mac_upper; @@ -81,34 +86,32 @@ struct fm10k_mac_update { __le16 glort; u8 flags; u8 action; -} __packed; +} __aligned(4) __packed; struct fm10k_global_table_data { __le32 used; __le32 avail; -} __packed; +} __aligned(4) __packed; struct fm10k_swapi_error { __le32 status; struct fm10k_global_table_data mac; struct fm10k_global_table_data nexthop; struct fm10k_global_table_data ffu; -} __packed; +} __aligned(4) __packed; struct fm10k_swapi_1588_timestamp { __le64 egress; __le64 ingress; __le16 dglort; __le16 sglort; -} __packed; +} __aligned(4) __packed; s32 fm10k_msg_lport_map_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); extern const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[]; #define FM10K_PF_MSG_LPORT_MAP_HANDLER(func) \ FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_LPORT_MAP, \ fm10k_lport_map_msg_attr, func) -s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *, u32 **, - struct fm10k_mbx_info *); extern const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[]; #define FM10K_PF_MSG_UPDATE_PVID_HANDLER(func) \ FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_UPDATE_PVID, \ @@ -129,7 +132,6 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); -extern const struct fm10k_msg_data fm10k_iov_msg_data_pf[]; -extern struct fm10k_info fm10k_pf_info; +extern const struct fm10k_info fm10k_pf_info; #endif /* _FM10K_PF_H */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index 9b29d7b0377a4..ab01bb30752f9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,5 +1,5 @@ /* Intel Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -48,8 +48,8 @@ s32 fm10k_tlv_msg_init(u32 *msg, u16 msg_id) * the attribute buffer. It will return success if provided with a valid * pointers. **/ -s32 fm10k_tlv_attr_put_null_string(u32 *msg, u16 attr_id, - const unsigned char *string) +static s32 fm10k_tlv_attr_put_null_string(u32 *msg, u16 attr_id, + const unsigned char *string) { u32 attr_data = 0, len = 0; u32 *attr; @@ -98,7 +98,7 @@ s32 fm10k_tlv_attr_put_null_string(u32 *msg, u16 attr_id, * it in the array pointed by by string. It will return success if provided * with a valid pointers. **/ -s32 fm10k_tlv_attr_get_null_string(u32 *attr, unsigned char *string) +static s32 fm10k_tlv_attr_get_null_string(u32 *attr, unsigned char *string) { u32 len; @@ -353,7 +353,7 @@ s32 fm10k_tlv_attr_get_le_struct(u32 *attr, void *le_struct, u32 len) * function will return NULL on failure, and a pointer to the start * of the nested attributes on success. **/ -u32 *fm10k_tlv_attr_nest_start(u32 *msg, u16 attr_id) +static u32 *fm10k_tlv_attr_nest_start(u32 *msg, u16 attr_id) { u32 *attr; @@ -370,7 +370,7 @@ u32 *fm10k_tlv_attr_nest_start(u32 *msg, u16 attr_id) } /** - * fm10k_tlv_attr_nest_start - Start a set of nested attributes + * fm10k_tlv_attr_nest_stop - Stop a set of nested attributes * @msg: Pointer to message block * * This function closes off an existing set of nested attributes. The @@ -378,7 +378,7 @@ u32 *fm10k_tlv_attr_nest_start(u32 *msg, u16 attr_id) * the case of a nest within the nest this would be the outer nest pointer. * This function will return success provided all pointers are valid. **/ -s32 fm10k_tlv_attr_nest_stop(u32 *msg) +static s32 fm10k_tlv_attr_nest_stop(u32 *msg) { u32 *attr; u32 len; @@ -483,8 +483,8 @@ static s32 fm10k_tlv_attr_validate(u32 *attr, * FM10K_NOT_IMPLEMENTED for any attribute that is outside of the array * and 0 on success. **/ -s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, - const struct fm10k_tlv_attr *tlv_attr) +static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, + const struct fm10k_tlv_attr *tlv_attr) { u32 i, attr_id, offset = 0; s32 err = 0; @@ -755,7 +755,7 @@ parse_nested: err = fm10k_tlv_attr_get_mac_vlan( results[FM10K_TEST_MSG_MAC_ADDR], result_mac, &result_vlan); - if (!err && memcmp(test_mac, result_mac, ETH_ALEN)) + if (!err && !ether_addr_equal(test_mac, result_mac)) err = FM10K_ERR_INVALID_VALUE; if (!err && test_vlan != result_vlan) err = FM10K_ERR_INVALID_VALUE; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h index 7e045e8bf1eba..e1845e0a17d81 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h @@ -1,5 +1,5 @@ /* Intel Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -38,9 +38,9 @@ struct fm10k_msg_data; * mailbox size we will provide a message with the above header and it * will be segmented and transported to the mailbox to the other side where * it is reassembled. It contains the following fields: - * Len: Length of the message in bytes excluding the message header + * Length: Length of the message in bytes excluding the message header * Flags: TBD - * Rule: These will be the message/argument types we pass + * Type/ID: These will be the message/argument types we pass */ /* message data header */ #define FM10K_TLV_ID_SHIFT 0 @@ -106,8 +106,6 @@ struct fm10k_msg_data { #define FM10K_MSG_HANDLER(id, attr, func) { id, attr, func } s32 fm10k_tlv_msg_init(u32 *, u16); -s32 fm10k_tlv_attr_put_null_string(u32 *, u16, const unsigned char *); -s32 fm10k_tlv_attr_get_null_string(u32 *, unsigned char *); s32 fm10k_tlv_attr_put_mac_vlan(u32 *, u16, const u8 *, u16); s32 fm10k_tlv_attr_get_mac_vlan(u32 *, u8 *, u16 *); s32 fm10k_tlv_attr_put_bool(u32 *, u16); @@ -147,9 +145,6 @@ s32 fm10k_tlv_attr_get_value(u32 *, void *, u32); fm10k_tlv_attr_get_value(attr, ptr, sizeof(s64)) s32 fm10k_tlv_attr_put_le_struct(u32 *, u16, const void *, u32); s32 fm10k_tlv_attr_get_le_struct(u32 *, void *, u32); -u32 *fm10k_tlv_attr_nest_start(u32 *, u16); -s32 fm10k_tlv_attr_nest_stop(u32 *); -s32 fm10k_tlv_attr_parse(u32 *, u32 **, const struct fm10k_tlv_attr *); s32 fm10k_tlv_msg_parse(struct fm10k_hw *, u32 *, struct fm10k_mbx_info *, const struct fm10k_msg_data *); s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 02727250ce1f5..854ebb1906bf7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -354,7 +354,7 @@ struct fm10k_hw; #define FM10K_VLAN_TABLE_VID_MAX 4096 #define FM10K_VLAN_TABLE_VSI_MAX 64 #define FM10K_VLAN_LENGTH_SHIFT 16 -#define FM10K_VLAN_CLEAR (1 << 15) +#define FM10K_VLAN_CLEAR BIT(15) #define FM10K_VLAN_ALL \ ((FM10K_VLAN_TABLE_VID_MAX - 1) << FM10K_VLAN_LENGTH_SHIFT) @@ -388,13 +388,13 @@ struct fm10k_hw; #define FM10K_SW_SYSTIME_PULSE(_n) ((_n) + 0x02252) enum fm10k_int_source { - fm10k_int_Mailbox = 0, - fm10k_int_PCIeFault = 1, - fm10k_int_SwitchUpDown = 2, - fm10k_int_SwitchEvent = 3, - fm10k_int_SRAM = 4, - fm10k_int_VFLR = 5, - fm10k_int_MaxHoldTime = 6, + fm10k_int_mailbox = 0, + fm10k_int_pcie_fault = 1, + fm10k_int_switch_up_down = 2, + fm10k_int_switch_event = 3, + fm10k_int_sram = 4, + fm10k_int_vflr = 5, + fm10k_int_max_hold_time = 6, fm10k_int_sources_max_pf }; @@ -550,7 +550,6 @@ struct fm10k_mac_ops { struct fm10k_dglort_cfg *); void (*set_dma_mask)(struct fm10k_hw *, u64); s32 (*get_fault)(struct fm10k_hw *, int, struct fm10k_fault *); - void (*request_lport_map)(struct fm10k_hw *); s32 (*adjust_systime)(struct fm10k_hw *, s32 ppb); u64 (*read_systime)(struct fm10k_hw *); }; @@ -660,10 +659,10 @@ enum fm10k_devices { }; struct fm10k_info { - enum fm10k_mac_type mac; - s32 (*get_invariants)(struct fm10k_hw *); - struct fm10k_mac_ops *mac_ops; - struct fm10k_iov_ops *iov_ops; + enum fm10k_mac_type mac; + s32 (*get_invariants)(struct fm10k_hw *); + const struct fm10k_mac_ops *mac_ops; + const struct fm10k_iov_ops *iov_ops; }; struct fm10k_hw { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index 2af697df5abc1..91f8d7311f3bf 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -298,7 +298,7 @@ static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, /* verify we are not locked down on the MAC address */ if (is_valid_ether_addr(hw->mac.perm_addr) && - memcmp(hw->mac.perm_addr, mac, ETH_ALEN)) + !ether_addr_equal(hw->mac.perm_addr, mac)) return FM10K_ERR_PARAM; /* add bit to notify us if this is a set or clear operation */ @@ -442,6 +442,7 @@ static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, u16 glort, u8 mode) if (mode > FM10K_XCAST_MODE_NONE) return FM10K_ERR_PARAM; + /* generate message requesting to change xcast mode */ fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_LPORT_STATE); fm10k_tlv_attr_put_u8(msg, FM10K_LPORT_STATE_MSG_XCAST_MODE, mode); @@ -561,25 +562,25 @@ static const struct fm10k_msg_data fm10k_msg_data_vf[] = { FM10K_TLV_MSG_ERROR_HANDLER(fm10k_tlv_msg_error), }; -static struct fm10k_mac_ops mac_ops_vf = { - .get_bus_info = &fm10k_get_bus_info_generic, - .reset_hw = &fm10k_reset_hw_vf, - .init_hw = &fm10k_init_hw_vf, - .start_hw = &fm10k_start_hw_generic, - .stop_hw = &fm10k_stop_hw_vf, - .update_vlan = &fm10k_update_vlan_vf, - .read_mac_addr = &fm10k_read_mac_addr_vf, - .update_uc_addr = &fm10k_update_uc_addr_vf, - .update_mc_addr = &fm10k_update_mc_addr_vf, - .update_xcast_mode = &fm10k_update_xcast_mode_vf, - .update_int_moderator = &fm10k_update_int_moderator_vf, - .update_lport_state = &fm10k_update_lport_state_vf, - .update_hw_stats = &fm10k_update_hw_stats_vf, - .rebind_hw_stats = &fm10k_rebind_hw_stats_vf, - .configure_dglort_map = &fm10k_configure_dglort_map_vf, - .get_host_state = &fm10k_get_host_state_generic, - .adjust_systime = &fm10k_adjust_systime_vf, - .read_systime = &fm10k_read_systime_vf, +static const struct fm10k_mac_ops mac_ops_vf = { + .get_bus_info = fm10k_get_bus_info_generic, + .reset_hw = fm10k_reset_hw_vf, + .init_hw = fm10k_init_hw_vf, + .start_hw = fm10k_start_hw_generic, + .stop_hw = fm10k_stop_hw_vf, + .update_vlan = fm10k_update_vlan_vf, + .read_mac_addr = fm10k_read_mac_addr_vf, + .update_uc_addr = fm10k_update_uc_addr_vf, + .update_mc_addr = fm10k_update_mc_addr_vf, + .update_xcast_mode = fm10k_update_xcast_mode_vf, + .update_int_moderator = fm10k_update_int_moderator_vf, + .update_lport_state = fm10k_update_lport_state_vf, + .update_hw_stats = fm10k_update_hw_stats_vf, + .rebind_hw_stats = fm10k_rebind_hw_stats_vf, + .configure_dglort_map = fm10k_configure_dglort_map_vf, + .get_host_state = fm10k_get_host_state_generic, + .adjust_systime = fm10k_adjust_systime_vf, + .read_systime = fm10k_read_systime_vf, }; static s32 fm10k_get_invariants_vf(struct fm10k_hw *hw) @@ -589,8 +590,8 @@ static s32 fm10k_get_invariants_vf(struct fm10k_hw *hw) return fm10k_pfvf_mbx_init(hw, &hw->mbx, fm10k_msg_data_vf, 0); } -struct fm10k_info fm10k_vf_info = { +const struct fm10k_info fm10k_vf_info = { .mac = fm10k_mac_vf, - .get_invariants = &fm10k_get_invariants_vf, + .get_invariants = fm10k_get_invariants_vf, .mac_ops = &mac_ops_vf, }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.h b/drivers/net/ethernet/intel/fm10k/fm10k_vf.h index 06a99d794c99b..c4439f1313a01 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.h @@ -74,5 +74,5 @@ extern const struct fm10k_tlv_attr fm10k_1588_msg_attr[]; #define FM10K_VF_MSG_1588_HANDLER(func) \ FM10K_MSG_HANDLER(FM10K_VF_MSG_ID_1588, fm10k_1588_msg_attr, func) -extern struct fm10k_info fm10k_vf_info; +extern const struct fm10k_info fm10k_vf_info; #endif /* _FM10K_VF_H */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index bd6d9c002acca..c202f9b9386a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -245,6 +245,11 @@ struct i40e_tc_configuration { struct i40e_tc_info tc_info[I40E_MAX_TRAFFIC_CLASS]; }; +struct i40e_udp_port_config { + __be16 index; + u8 type; +}; + /* struct that defines the Ethernet device */ struct i40e_pf { struct pci_dev *pdev; @@ -281,11 +286,9 @@ struct i40e_pf { u32 fd_atr_cnt; u32 fd_tcp_rule; -#ifdef CONFIG_I40E_VXLAN - __be16 vxlan_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS]; - u16 pending_vxlan_bitmap; + struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS]; + u16 pending_udp_bitmap; -#endif enum i40e_interrupt_policy int_policy; u16 rx_itr_default; u16 tx_itr_default; @@ -322,9 +325,7 @@ struct i40e_pf { #define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(22) #define I40E_FLAG_PTP BIT_ULL(25) #define I40E_FLAG_MFP_ENABLED BIT_ULL(26) -#ifdef CONFIG_I40E_VXLAN -#define I40E_FLAG_VXLAN_FILTER_SYNC BIT_ULL(27) -#endif +#define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27) #define I40E_FLAG_PORT_ID_VALID BIT_ULL(28) #define I40E_FLAG_DCB_CAPABLE BIT_ULL(29) #define I40E_FLAG_RSS_AQ_CAPABLE BIT_ULL(31) @@ -336,6 +337,7 @@ struct i40e_pf { #define I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(38) #define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39) #define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40) +#define I40E_FLAG_GENEVE_OFFLOAD_CAPABLE BIT_ULL(41) #define I40E_FLAG_NO_PCI_LINK_CHECK BIT_ULL(42) /* tracks features that get auto disabled by errors */ @@ -776,6 +778,8 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid); int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid); struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr, bool is_vf, bool is_netdev); +int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr, + bool is_vf, bool is_netdev); bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi); struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, bool is_vf, bool is_netdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 0ff8f01e57ee5..1fd5ea82a9bc8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -567,10 +567,6 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) goto init_adminq_exit; } - /* initialize locks */ - mutex_init(&hw->aq.asq_mutex); - mutex_init(&hw->aq.arq_mutex); - /* Set up register offsets */ i40e_adminq_init_regs(hw); @@ -664,8 +660,6 @@ i40e_status i40e_shutdown_adminq(struct i40e_hw *hw) i40e_shutdown_asq(hw); i40e_shutdown_arq(hw); - /* destroy the locks */ - if (hw->nvm_buff.va) i40e_free_virt_mem(hw, &hw->nvm_buff); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 61a4979359412..b22012a446a6e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -227,6 +227,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_nvm_update = 0x0703, i40e_aqc_opc_nvm_config_read = 0x0704, i40e_aqc_opc_nvm_config_write = 0x0705, + i40e_aqc_opc_oem_post_update = 0x0720, /* virtualization commands */ i40e_aqc_opc_send_msg_to_pf = 0x0801, @@ -1891,6 +1892,26 @@ struct i40e_aqc_nvm_config_data_immediate_field { I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field); +/* OEM Post Update (indirect 0x0720) + * no command data struct used + */ +struct i40e_aqc_nvm_oem_post_update { +#define I40E_AQ_NVM_OEM_POST_UPDATE_EXTERNAL_DATA 0x01 + u8 sel_data; + u8 reserved[7]; +}; + +I40E_CHECK_STRUCT_LEN(0x8, i40e_aqc_nvm_oem_post_update); + +struct i40e_aqc_nvm_oem_post_update_buffer { + u8 str_len; + u8 dev_addr; + __le16 eeprom_addr; + u8 data[36]; +}; + +I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer); + /* Send to PF command (indirect 0x0801) id is only used by PF * Send to VF command (indirect 0x0802) id is only used by PF * Send to Peer PF command (indirect 0x0803) diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index 79ae7beeafe5a..daa9204426d42 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -762,7 +762,7 @@ static void i40e_write_byte(u8 *hmc_bits, /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - mask = BIT(ce_info->width) - 1; + mask = (u8)(BIT(ce_info->width) - 1); src_byte = *from; src_byte &= mask; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2b1b655a3b525..1598fb31477a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -27,9 +27,12 @@ /* Local includes */ #include "i40e.h" #include "i40e_diag.h" -#ifdef CONFIG_I40E_VXLAN +#if IS_ENABLED(CONFIG_VXLAN) #include <net/vxlan.h> #endif +#if IS_ENABLED(CONFIG_GENEVE) +#include <net/geneve.h> +#endif const char i40e_driver_name[] = "i40e"; static const char i40e_driver_string[] = @@ -39,7 +42,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 4 -#define DRV_VERSION_BUILD 7 +#define DRV_VERSION_BUILD 8 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -1259,6 +1262,42 @@ struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr, } /** + * i40e_del_mac_all_vlan - Remove a MAC filter from all VLANS + * @vsi: the VSI to be searched + * @macaddr: the mac address to be removed + * @is_vf: true if it is a VF + * @is_netdev: true if it is a netdev + * + * Removes a given MAC address from a VSI, regardless of VLAN + * + * Returns 0 for success, or error + **/ +int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr, + bool is_vf, bool is_netdev) +{ + struct i40e_mac_filter *f = NULL; + int changed = 0; + + WARN(!spin_is_locked(&vsi->mac_filter_list_lock), + "Missing mac_filter_list_lock\n"); + list_for_each_entry(f, &vsi->mac_filter_list, list) { + if ((ether_addr_equal(macaddr, f->macaddr)) && + (is_vf == f->is_vf) && + (is_netdev == f->is_netdev)) { + f->counter--; + f->changed = true; + changed = 1; + } + } + if (changed) { + vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; + vsi->back->flags |= I40E_FLAG_FILTER_SYNC; + return 0; + } + return -ENOENT; +} + +/** * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM * @vsi: the PF Main VSI - inappropriate for any other VSI * @macaddr: the MAC address @@ -1531,7 +1570,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) { /* Find numtc from enabled TC bitmap */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - if (enabled_tc & BIT_ULL(i)) /* TC is enabled */ + if (enabled_tc & BIT(i)) /* TC is enabled */ numtc++; } if (!numtc) { @@ -1560,7 +1599,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, /* Setup queue offset/count for all TCs for given VSI */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { /* See if the given TC is enabled for the given VSI */ - if (vsi->tc_config.enabled_tc & BIT_ULL(i)) { + if (vsi->tc_config.enabled_tc & BIT(i)) { /* TC is enabled */ int pow, num_qps; @@ -1880,11 +1919,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* Now process 'del_list' outside the lock */ if (!list_empty(&tmp_del_list)) { + int del_list_size; + filter_list_len = pf->hw.aq.asq_buf_size / sizeof(struct i40e_aqc_remove_macvlan_element_data); - del_list = kcalloc(filter_list_len, - sizeof(struct i40e_aqc_remove_macvlan_element_data), - GFP_KERNEL); + del_list_size = filter_list_len * + sizeof(struct i40e_aqc_remove_macvlan_element_data); + del_list = kzalloc(del_list_size, GFP_KERNEL); if (!del_list) { i40e_cleanup_add_list(&tmp_add_list); @@ -1919,7 +1960,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) NULL); aq_err = pf->hw.aq.asq_last_status; num_del = 0; - memset(del_list, 0, sizeof(*del_list)); + memset(del_list, 0, del_list_size); if (aq_ret && aq_err != I40E_AQ_RC_ENOENT) { retval = -EIO; @@ -1955,13 +1996,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } if (!list_empty(&tmp_add_list)) { + int add_list_size; /* do all the adds now */ filter_list_len = pf->hw.aq.asq_buf_size / sizeof(struct i40e_aqc_add_macvlan_element_data), - add_list = kcalloc(filter_list_len, - sizeof(struct i40e_aqc_add_macvlan_element_data), - GFP_KERNEL); + add_list_size = filter_list_len * + sizeof(struct i40e_aqc_add_macvlan_element_data); + add_list = kzalloc(add_list_size, GFP_KERNEL); if (!add_list) { /* Purge element from temporary lists */ i40e_cleanup_add_list(&tmp_add_list); @@ -2000,7 +2042,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) if (aq_ret) break; - memset(add_list, 0, sizeof(*add_list)); + memset(add_list, 0, add_list_size); } /* Entries from tmp_add_list were cloned from MAC * filter list, hence clean those cloned entries @@ -4433,7 +4475,7 @@ static u8 i40e_get_iscsi_tc_map(struct i40e_pf *pf) if (app.selector == I40E_APP_SEL_TCPIP && app.protocolid == I40E_APP_PROTOID_ISCSI) { tc = dcbcfg->etscfg.prioritytable[app.priority]; - enabled_tc |= BIT_ULL(tc); + enabled_tc |= BIT(tc); break; } } @@ -4517,7 +4559,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) /* At least have TC0 */ enabled_tc = (enabled_tc ? enabled_tc : 0x1); for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - if (enabled_tc & BIT_ULL(i)) + if (enabled_tc & BIT(i)) num_tc++; } return num_tc; @@ -4539,7 +4581,7 @@ static u8 i40e_pf_get_default_tc(struct i40e_pf *pf) /* Find the first enabled TC */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - if (enabled_tc & BIT_ULL(i)) + if (enabled_tc & BIT(i)) break; } @@ -4699,7 +4741,7 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc) * will set the numtc for netdev as 2 that will be * referenced by the netdev layer as TC 0 and 1. */ - if (vsi->tc_config.enabled_tc & BIT_ULL(i)) + if (vsi->tc_config.enabled_tc & BIT(i)) netdev_set_tc_queue(netdev, vsi->tc_config.tc_info[i].netdev_tc, vsi->tc_config.tc_info[i].qcount, @@ -4761,7 +4803,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) /* Enable ETS TCs with equal BW Share for now across all VSIs */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - if (enabled_tc & BIT_ULL(i)) + if (enabled_tc & BIT(i)) bw_share[i] = 1; } @@ -4835,7 +4877,7 @@ int i40e_veb_config_tc(struct i40e_veb *veb, u8 enabled_tc) /* Enable ETS TCs with equal BW Share for now */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - if (enabled_tc & BIT_ULL(i)) + if (enabled_tc & BIT(i)) bw_data.tc_bw_share_credits[i] = 1; } @@ -5232,7 +5274,7 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc) /* Generate TC map for number of tc requested */ for (i = 0; i < tc; i++) - enabled_tc |= BIT_ULL(i); + enabled_tc |= BIT(i); /* Requesting same TC configuration as already enabled */ if (enabled_tc == vsi->tc_config.enabled_tc) @@ -5297,6 +5339,9 @@ int i40e_open(struct net_device *netdev) #ifdef CONFIG_I40E_VXLAN vxlan_get_rx_port(netdev); #endif +#ifdef CONFIG_I40E_GENEVE + geneve_get_rx_port(netdev); +#endif return 0; } @@ -6096,23 +6141,23 @@ static void i40e_reset_subtask(struct i40e_pf *pf) rtnl_lock(); if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) { - reset_flags |= BIT_ULL(__I40E_REINIT_REQUESTED); + reset_flags |= BIT(__I40E_REINIT_REQUESTED); clear_bit(__I40E_REINIT_REQUESTED, &pf->state); } if (test_bit(__I40E_PF_RESET_REQUESTED, &pf->state)) { - reset_flags |= BIT_ULL(__I40E_PF_RESET_REQUESTED); + reset_flags |= BIT(__I40E_PF_RESET_REQUESTED); clear_bit(__I40E_PF_RESET_REQUESTED, &pf->state); } if (test_bit(__I40E_CORE_RESET_REQUESTED, &pf->state)) { - reset_flags |= BIT_ULL(__I40E_CORE_RESET_REQUESTED); + reset_flags |= BIT(__I40E_CORE_RESET_REQUESTED); clear_bit(__I40E_CORE_RESET_REQUESTED, &pf->state); } if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state)) { - reset_flags |= BIT_ULL(__I40E_GLOBAL_RESET_REQUESTED); + reset_flags |= BIT(__I40E_GLOBAL_RESET_REQUESTED); clear_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state); } if (test_bit(__I40E_DOWN_REQUESTED, &pf->state)) { - reset_flags |= BIT_ULL(__I40E_DOWN_REQUESTED); + reset_flags |= BIT(__I40E_DOWN_REQUESTED); clear_bit(__I40E_DOWN_REQUESTED, &pf->state); } @@ -6183,15 +6228,18 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) val = rd32(&pf->hw, pf->hw.aq.arq.len); oldval = val; if (val & I40E_PF_ARQLEN_ARQVFE_MASK) { - dev_info(&pf->pdev->dev, "ARQ VF Error detected\n"); + if (hw->debug_mask & I40E_DEBUG_AQ) + dev_info(&pf->pdev->dev, "ARQ VF Error detected\n"); val &= ~I40E_PF_ARQLEN_ARQVFE_MASK; } if (val & I40E_PF_ARQLEN_ARQOVFL_MASK) { - dev_info(&pf->pdev->dev, "ARQ Overflow Error detected\n"); + if (hw->debug_mask & I40E_DEBUG_AQ) + dev_info(&pf->pdev->dev, "ARQ Overflow Error detected\n"); val &= ~I40E_PF_ARQLEN_ARQOVFL_MASK; } if (val & I40E_PF_ARQLEN_ARQCRIT_MASK) { - dev_info(&pf->pdev->dev, "ARQ Critical Error detected\n"); + if (hw->debug_mask & I40E_DEBUG_AQ) + dev_info(&pf->pdev->dev, "ARQ Critical Error detected\n"); val &= ~I40E_PF_ARQLEN_ARQCRIT_MASK; } if (oldval != val) @@ -6200,15 +6248,18 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) val = rd32(&pf->hw, pf->hw.aq.asq.len); oldval = val; if (val & I40E_PF_ATQLEN_ATQVFE_MASK) { - dev_info(&pf->pdev->dev, "ASQ VF Error detected\n"); + if (pf->hw.debug_mask & I40E_DEBUG_AQ) + dev_info(&pf->pdev->dev, "ASQ VF Error detected\n"); val &= ~I40E_PF_ATQLEN_ATQVFE_MASK; } if (val & I40E_PF_ATQLEN_ATQOVFL_MASK) { - dev_info(&pf->pdev->dev, "ASQ Overflow Error detected\n"); + if (pf->hw.debug_mask & I40E_DEBUG_AQ) + dev_info(&pf->pdev->dev, "ASQ Overflow Error detected\n"); val &= ~I40E_PF_ATQLEN_ATQOVFL_MASK; } if (val & I40E_PF_ATQLEN_ATQCRIT_MASK) { - dev_info(&pf->pdev->dev, "ASQ Critical Error detected\n"); + if (pf->hw.debug_mask & I40E_DEBUG_AQ) + dev_info(&pf->pdev->dev, "ASQ Critical Error detected\n"); val &= ~I40E_PF_ATQLEN_ATQCRIT_MASK; } if (oldval != val) @@ -6259,6 +6310,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) break; case i40e_aqc_opc_nvm_erase: case i40e_aqc_opc_nvm_update: + case i40e_aqc_opc_oem_post_update: i40e_debug(&pf->hw, I40E_DEBUG_NVM, "ARQ NVM operation completed\n"); break; default: @@ -6990,30 +7042,30 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) i40e_flush(hw); } -#ifdef CONFIG_I40E_VXLAN /** - * i40e_sync_vxlan_filters_subtask - Sync the VSI filter list with HW + * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW * @pf: board private structure **/ -static void i40e_sync_vxlan_filters_subtask(struct i40e_pf *pf) +static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) { +#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE) struct i40e_hw *hw = &pf->hw; i40e_status ret; __be16 port; int i; - if (!(pf->flags & I40E_FLAG_VXLAN_FILTER_SYNC)) + if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC)) return; - pf->flags &= ~I40E_FLAG_VXLAN_FILTER_SYNC; + pf->flags &= ~I40E_FLAG_UDP_FILTER_SYNC; for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { - if (pf->pending_vxlan_bitmap & BIT_ULL(i)) { - pf->pending_vxlan_bitmap &= ~BIT_ULL(i); - port = pf->vxlan_ports[i]; + if (pf->pending_udp_bitmap & BIT_ULL(i)) { + pf->pending_udp_bitmap &= ~BIT_ULL(i); + port = pf->udp_ports[i].index; if (port) ret = i40e_aq_add_udp_tunnel(hw, ntohs(port), - I40E_AQC_TUNNEL_TYPE_VXLAN, + pf->udp_ports[i].type, NULL, NULL); else ret = i40e_aq_del_udp_tunnel(hw, i, NULL); @@ -7026,13 +7078,13 @@ static void i40e_sync_vxlan_filters_subtask(struct i40e_pf *pf) i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - pf->vxlan_ports[i] = 0; + pf->udp_ports[i].index = 0; } } } +#endif } -#endif /** * i40e_service_task - Run the driver's async subtasks * @work: pointer to work_struct containing our data @@ -7057,8 +7109,8 @@ static void i40e_service_task(struct work_struct *work) i40e_watchdog_subtask(pf); i40e_fdir_reinit_subtask(pf); i40e_sync_filters_subtask(pf); -#ifdef CONFIG_I40E_VXLAN - i40e_sync_vxlan_filters_subtask(pf); +#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE) + i40e_sync_udp_filters_subtask(pf); #endif i40e_clean_adminq_subtask(pf); @@ -8334,7 +8386,8 @@ static int i40e_sw_init(struct i40e_pf *pf) I40E_FLAG_HW_ATR_EVICT_CAPABLE | I40E_FLAG_OUTER_UDP_CSUM_CAPABLE | I40E_FLAG_WB_ON_ITR_CAPABLE | - I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE; + I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE | + I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; } pf->eeprom_version = 0xDEAD; pf->lan_veb = I40E_NO_VEB; @@ -8433,26 +8486,27 @@ static int i40e_set_features(struct net_device *netdev, return 0; } -#ifdef CONFIG_I40E_VXLAN +#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE) /** - * i40e_get_vxlan_port_idx - Lookup a possibly offloaded for Rx UDP port + * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port * @pf: board private structure * @port: The UDP port to look up * * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found **/ -static u8 i40e_get_vxlan_port_idx(struct i40e_pf *pf, __be16 port) +static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) { u8 i; for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { - if (pf->vxlan_ports[i] == port) + if (pf->udp_ports[i].index == port) return i; } return i; } +#endif /** * i40e_add_vxlan_port - Get notifications about VXLAN ports that come up * @netdev: This physical port's netdev @@ -8462,6 +8516,7 @@ static u8 i40e_get_vxlan_port_idx(struct i40e_pf *pf, __be16 port) static void i40e_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { +#if IS_ENABLED(CONFIG_VXLAN) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8471,7 +8526,7 @@ static void i40e_add_vxlan_port(struct net_device *netdev, if (sa_family == AF_INET6) return; - idx = i40e_get_vxlan_port_idx(pf, port); + idx = i40e_get_udp_port_idx(pf, port); /* Check if port already exists */ if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { @@ -8481,7 +8536,7 @@ static void i40e_add_vxlan_port(struct net_device *netdev, } /* Now check if there is space to add the new port */ - next_idx = i40e_get_vxlan_port_idx(pf, 0); + next_idx = i40e_get_udp_port_idx(pf, 0); if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) { netdev_info(netdev, "maximum number of vxlan UDP ports reached, not adding port %d\n", @@ -8490,9 +8545,11 @@ static void i40e_add_vxlan_port(struct net_device *netdev, } /* New port: add it and mark its index in the bitmap */ - pf->vxlan_ports[next_idx] = port; - pf->pending_vxlan_bitmap |= BIT_ULL(next_idx); - pf->flags |= I40E_FLAG_VXLAN_FILTER_SYNC; + pf->udp_ports[next_idx].index = port; + pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN; + pf->pending_udp_bitmap |= BIT_ULL(next_idx); + pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; +#endif } /** @@ -8504,6 +8561,7 @@ static void i40e_add_vxlan_port(struct net_device *netdev, static void i40e_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { +#if IS_ENABLED(CONFIG_VXLAN) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8512,23 +8570,108 @@ static void i40e_del_vxlan_port(struct net_device *netdev, if (sa_family == AF_INET6) return; - idx = i40e_get_vxlan_port_idx(pf, port); + idx = i40e_get_udp_port_idx(pf, port); /* Check if port already exists */ if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { /* if port exists, set it to 0 (mark for deletion) * and make it pending */ - pf->vxlan_ports[idx] = 0; - pf->pending_vxlan_bitmap |= BIT_ULL(idx); - pf->flags |= I40E_FLAG_VXLAN_FILTER_SYNC; + pf->udp_ports[idx].index = 0; + pf->pending_udp_bitmap |= BIT_ULL(idx); + pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; } else { netdev_warn(netdev, "vxlan port %d was not found, not deleting\n", ntohs(port)); } +#endif +} + +/** + * i40e_add_geneve_port - Get notifications about GENEVE ports that come up + * @netdev: This physical port's netdev + * @sa_family: Socket Family that GENEVE is notifying us about + * @port: New UDP port number that GENEVE started listening to + **/ +static void i40e_add_geneve_port(struct net_device *netdev, + sa_family_t sa_family, __be16 port) +{ +#if IS_ENABLED(CONFIG_GENEVE) + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; + u8 next_idx; + u8 idx; + + if (sa_family == AF_INET6) + return; + + idx = i40e_get_udp_port_idx(pf, port); + + /* Check if port already exists */ + if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { + netdev_info(netdev, "udp port %d already offloaded\n", + ntohs(port)); + return; + } + + /* Now check if there is space to add the new port */ + next_idx = i40e_get_udp_port_idx(pf, 0); + + if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) { + netdev_info(netdev, "maximum number of UDP ports reached, not adding port %d\n", + ntohs(port)); + return; + } + + /* New port: add it and mark its index in the bitmap */ + pf->udp_ports[next_idx].index = port; + pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE; + pf->pending_udp_bitmap |= BIT_ULL(next_idx); + pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; + + dev_info(&pf->pdev->dev, "adding geneve port %d\n", ntohs(port)); +#endif } +/** + * i40e_del_geneve_port - Get notifications about GENEVE ports that go away + * @netdev: This physical port's netdev + * @sa_family: Socket Family that GENEVE is notifying us about + * @port: UDP port number that GENEVE stopped listening to + **/ +static void i40e_del_geneve_port(struct net_device *netdev, + sa_family_t sa_family, __be16 port) +{ +#if IS_ENABLED(CONFIG_GENEVE) + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; + u8 idx; + + if (sa_family == AF_INET6) + return; + + idx = i40e_get_udp_port_idx(pf, port); + + /* Check if port already exists */ + if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { + /* if port exists, set it to 0 (mark for deletion) + * and make it pending + */ + pf->udp_ports[idx].index = 0; + pf->pending_udp_bitmap |= BIT_ULL(idx); + pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; + + dev_info(&pf->pdev->dev, "deleting geneve port %d\n", + ntohs(port)); + } else { + netdev_warn(netdev, "geneve port %d was not found, not deleting\n", + ntohs(port)); + } #endif +} + static int i40e_get_phys_port_id(struct net_device *netdev, struct netdev_phys_item_id *ppid) { @@ -8706,7 +8849,10 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, nlflags, 0, 0, filter_mask, NULL); } -#define I40E_MAX_TUNNEL_HDR_LEN 80 +/* Hardware supports L4 tunnel length of 128B (=2^7) which includes + * inner mac plus all inner ethertypes. + */ +#define I40E_MAX_TUNNEL_HDR_LEN 128 /** * i40e_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff @@ -8718,9 +8864,9 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb->encapsulation && - (skb_inner_mac_header(skb) - skb_transport_header(skb) > + ((skb_inner_network_header(skb) - skb_transport_header(skb)) > I40E_MAX_TUNNEL_HDR_LEN)) - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } @@ -8753,10 +8899,14 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_get_vf_config = i40e_ndo_get_vf_config, .ndo_set_vf_link_state = i40e_ndo_set_vf_link_state, .ndo_set_vf_spoofchk = i40e_ndo_set_vf_spoofchk, -#ifdef CONFIG_I40E_VXLAN +#if IS_ENABLED(CONFIG_VXLAN) .ndo_add_vxlan_port = i40e_add_vxlan_port, .ndo_del_vxlan_port = i40e_del_vxlan_port, #endif +#if IS_ENABLED(CONFIG_GENEVE) + .ndo_add_geneve_port = i40e_add_geneve_port, + .ndo_del_geneve_port = i40e_del_geneve_port, +#endif .ndo_get_phys_port_id = i40e_get_phys_port_id, .ndo_fdb_add = i40e_ndo_fdb_add, .ndo_features_check = i40e_features_check, @@ -8790,13 +8940,14 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) np->vsi = vsi; netdev->hw_enc_features |= NETIF_F_IP_CSUM | + NETIF_F_RXCSUM | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_TSO; netdev->features = NETIF_F_SG | NETIF_F_IP_CSUM | - NETIF_F_SCTP_CSUM | + NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | @@ -10303,6 +10454,9 @@ static void i40e_print_features(struct i40e_pf *pf) #if IS_ENABLED(CONFIG_VXLAN) i += snprintf(&buf[i], REMAIN(i), " VxLAN"); #endif +#if IS_ENABLED(CONFIG_GENEVE) + i += snprintf(&buf[i], REMAIN(i), " Geneve"); +#endif if (pf->flags & I40E_FLAG_PTP) i += snprintf(&buf[i], REMAIN(i), " PTP"); #ifdef I40E_FCOE @@ -10453,6 +10607,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* set up a default setting for link flow control */ pf->hw.fc.requested_mode = I40E_FC_NONE; + /* set up the locks for the AQ, do this only once in probe + * and destroy them only once in remove + */ + mutex_init(&hw->aq.asq_mutex); + mutex_init(&hw->aq.arq_mutex); + err = i40e_init_adminq(hw); if (err) { if (err == I40E_ERR_FIRMWARE_API_VERSION) @@ -10567,7 +10727,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* NVM bit on means WoL disabled for the port */ i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits); - if ((1 << hw->port) & wol_nvm_bits || hw->partition_id != 1) + if (BIT (hw->port) & wol_nvm_bits || hw->partition_id != 1) pf->wol_en = false; else pf->wol_en = true; @@ -10870,7 +11030,6 @@ static void i40e_remove(struct pci_dev *pdev) set_bit(__I40E_DOWN, &pf->state); del_timer_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); - i40e_fdir_teardown(pf); if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { i40e_free_vfs(pf); @@ -10913,6 +11072,10 @@ static void i40e_remove(struct pci_dev *pdev) "Failed to destroy the Admin Queue resources: %d\n", ret_code); + /* destroy the locks only once, here */ + mutex_destroy(&hw->aq.arq_mutex); + mutex_destroy(&hw->aq.asq_mutex); + /* Clear all dynamic memory lists of rings, q_vectors, and VSIs */ i40e_clear_interrupt_scheme(pf); for (i = 0; i < pf->num_alloc_vsi; i++) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b0ae3e6957839..e9e9a37ee274c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1380,7 +1380,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* If VXLAN traffic has an outer UDPv4 checksum we need to check + /* If VXLAN/GENEVE traffic has an outer UDPv4 checksum we need to check * it in the driver, hardware does not do it for us. * Since L3L4P bit was set we assume a valid IHL value (>=5) * so the total length of IPv4 header is IHL*4 bytes @@ -2001,7 +2001,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6))) return; - if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL)) { + if (!(tx_flags & I40E_TX_FLAGS_UDP_TUNNEL)) { /* snag network header to get L4 type and address */ hdr.network = skb_network_header(skb); @@ -2086,7 +2086,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT; dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK; - if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL)) + if (!(tx_flags & I40E_TX_FLAGS_UDP_TUNNEL)) dtype_cmd |= ((u32)I40E_FD_ATR_STAT_IDX(pf->hw.pf_id) << I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & @@ -2319,7 +2319,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, oudph = udp_hdr(skb); oiph = ip_hdr(skb); l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING; - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + *tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL; break; case IPPROTO_GRE: l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index dccc1eb576f25..3f081e25e097a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -163,7 +163,7 @@ enum i40e_dyn_idx_t { #define I40E_TX_FLAGS_FSO BIT(7) #define I40E_TX_FLAGS_TSYN BIT(8) #define I40E_TX_FLAGS_FD_SB BIT(9) -#define I40E_TX_FLAGS_VXLAN_TUNNEL BIT(10) +#define I40E_TX_FLAGS_UDP_TUNNEL BIT(10) #define I40E_TX_FLAGS_VLAN_MASK 0xffff0000 #define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h index ae879826084b7..3226946bf3d44 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h @@ -153,6 +153,7 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 #define I40E_VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 +#define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 struct i40e_virtchnl_vf_resource { u16 num_vsis; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b3bd81c3e1cee..aa58a498c239e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -549,12 +549,15 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) i40e_vsi_add_pvid(vsi, vf->port_vlan_id); spin_lock_bh(&vsi->mac_filter_list_lock); - f = i40e_add_filter(vsi, vf->default_lan_addr.addr, - vf->port_vlan_id ? vf->port_vlan_id : -1, - true, false); - if (!f) - dev_info(&pf->pdev->dev, - "Could not allocate VF MAC addr\n"); + if (is_valid_ether_addr(vf->default_lan_addr.addr)) { + f = i40e_add_filter(vsi, vf->default_lan_addr.addr, + vf->port_vlan_id ? vf->port_vlan_id : -1, + true, false); + if (!f) + dev_info(&pf->pdev->dev, + "Could not add MAC filter %pM for VF %d\n", + vf->default_lan_addr.addr, vf->vf_id); + } f = i40e_add_filter(vsi, brdcast, vf->port_vlan_id ? vf->port_vlan_id : -1, true, false); @@ -1683,8 +1686,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) spin_lock_bh(&vsi->mac_filter_list_lock); /* delete addresses from the list */ for (i = 0; i < al->num_elements; i++) - i40e_del_filter(vsi, al->list[i].addr, - I40E_VLAN_ANY, true, false); + if (i40e_del_mac_all_vlan(vsi, al->list[i].addr, true, false)) { + ret = I40E_ERR_INVALID_MAC_ADDR; + spin_unlock_bh(&vsi->mac_filter_list_lock); + goto error_param; + } + spin_unlock_bh(&vsi->mac_filter_list_lock); /* program the updated filter list */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index fd123ca60761e..3f65e39b3fe43 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -551,10 +551,6 @@ i40e_status i40evf_init_adminq(struct i40e_hw *hw) goto init_adminq_exit; } - /* initialize locks */ - mutex_init(&hw->aq.asq_mutex); - mutex_init(&hw->aq.arq_mutex); - /* Set up register offsets */ i40e_adminq_init_regs(hw); @@ -596,8 +592,6 @@ i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) i40e_shutdown_asq(hw); i40e_shutdown_arq(hw); - /* destroy the locks */ - if (hw->nvm_buff.va) i40e_free_virt_mem(hw, &hw->nvm_buff); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 1c76389bd8882..f5b2b369dc7ce 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -227,6 +227,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_nvm_update = 0x0703, i40e_aqc_opc_nvm_config_read = 0x0704, i40e_aqc_opc_nvm_config_write = 0x0705, + i40e_aqc_opc_oem_post_update = 0x0720, /* virtualization commands */ i40e_aqc_opc_send_msg_to_pf = 0x0801, @@ -1888,6 +1889,26 @@ struct i40e_aqc_nvm_config_data_immediate_field { I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field); +/* OEM Post Update (indirect 0x0720) + * no command data struct used + */ + struct i40e_aqc_nvm_oem_post_update { +#define I40E_AQ_NVM_OEM_POST_UPDATE_EXTERNAL_DATA 0x01 + u8 sel_data; + u8 reserved[7]; +}; + +I40E_CHECK_STRUCT_LEN(0x8, i40e_aqc_nvm_oem_post_update); + +struct i40e_aqc_nvm_oem_post_update_buffer { + u8 str_len; + u8 dev_addr; + __le16 eeprom_addr; + u8 data[36]; +}; + +I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer); + /* Send to PF command (indirect 0x0801) id is only used by PF * Send to VF command (indirect 0x0802) id is only used by PF * Send to Peer PF command (indirect 0x0803) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index 9f7b279b9d9c8..3b9d2037456cc 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -153,6 +153,7 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 #define I40E_VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 +#define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 struct i40e_virtchnl_vf_resource { u16 num_vsis; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index b4c632f417f68..a0bbb6b9f5aa4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -34,7 +34,15 @@ char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = "Intel(R) XL710/X710 Virtual Function Network Driver"; -#define DRV_VERSION "1.4.3" +#define DRV_KERN "-k" + +#define DRV_VERSION_MAJOR 1 +#define DRV_VERSION_MINOR 4 +#define DRV_VERSION_BUILD 4 +#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ + __stringify(DRV_VERSION_MINOR) "." \ + __stringify(DRV_VERSION_BUILD) \ + DRV_KERN const char i40evf_driver_version[] = DRV_VERSION; static const char i40evf_copyright[] = "Copyright (c) 2013 - 2015 Intel Corporation."; @@ -2034,6 +2042,9 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) { int i; + if (!adapter->tx_rings) + return; + for (i = 0; i < adapter->num_active_queues; i++) if (adapter->tx_rings[i].desc) i40evf_free_tx_resources(&adapter->tx_rings[i]); @@ -2102,6 +2113,9 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) { int i; + if (!adapter->rx_rings) + return; + for (i = 0; i < adapter->num_active_queues; i++) if (adapter->rx_rings[i].desc) i40evf_free_rx_resources(&adapter->rx_rings[i]); @@ -2307,7 +2321,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter) netdev->features |= NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_IP_CSUM | - NETIF_F_SCTP_CSUM | + NETIF_F_SCTP_CRC | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | @@ -2652,6 +2666,12 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.device = PCI_SLOT(pdev->devfn); hw->bus.func = PCI_FUNC(pdev->devfn); + /* set up the locks for the AQ, do this only once in probe + * and destroy them only once in remove + */ + mutex_init(&hw->aq.asq_mutex); + mutex_init(&hw->aq.arq_mutex); + INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); @@ -2808,6 +2828,10 @@ static void i40evf_remove(struct pci_dev *pdev) if (hw->aq.asq.count) i40evf_shutdown_adminq(hw); + /* destroy the locks only once, here */ + mutex_destroy(&hw->aq.arq_mutex); + mutex_destroy(&hw->aq.asq_mutex); + iounmap(hw->hw_addr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 3c9c008b168b7..c1c5262837572 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -157,7 +157,9 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) I40E_VIRTCHNL_VF_OFFLOAD_RSS_AQ | I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG | I40E_VIRTCHNL_VF_OFFLOAD_VLAN | - I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; + I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | + I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + adapter->current_op = I40E_VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; if (PF_IS_V11(adapter)) diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 7a73510e547cd..adb33e2a01376 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -45,8 +45,6 @@ static s32 igb_get_cfg_done_82575(struct e1000_hw *); static s32 igb_init_hw_82575(struct e1000_hw *); static s32 igb_phy_hw_reset_sgmii_82575(struct e1000_hw *); static s32 igb_read_phy_reg_sgmii_82575(struct e1000_hw *, u32, u16 *); -static s32 igb_read_phy_reg_82580(struct e1000_hw *, u32, u16 *); -static s32 igb_write_phy_reg_82580(struct e1000_hw *, u32, u16); static s32 igb_reset_hw_82575(struct e1000_hw *); static s32 igb_reset_hw_82580(struct e1000_hw *); static s32 igb_set_d0_lplu_state_82575(struct e1000_hw *, bool); @@ -205,13 +203,10 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) case e1000_82580: case e1000_i350: case e1000_i354: - phy->ops.read_reg = igb_read_phy_reg_82580; - phy->ops.write_reg = igb_write_phy_reg_82580; - break; case e1000_i210: case e1000_i211: - phy->ops.read_reg = igb_read_phy_reg_gs40g; - phy->ops.write_reg = igb_write_phy_reg_gs40g; + phy->ops.read_reg = igb_read_phy_reg_82580; + phy->ops.write_reg = igb_write_phy_reg_82580; break; default: phy->ops.read_reg = igb_read_phy_reg_igp; @@ -272,6 +267,11 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) if (ret_val) goto out; } + if (phy->id == M88E1543_E_PHY_ID) { + ret_val = igb_initialize_M88E1543_phy(hw); + if (ret_val) + goto out; + } break; case IGP03E1000_E_PHY_ID: phy->type = e1000_phy_igp_3; @@ -294,6 +294,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) case I210_I_PHY_ID: phy->type = e1000_phy_i210; phy->ops.check_polarity = igb_check_polarity_m88; + phy->ops.get_cfg_done = igb_get_cfg_done_i210; phy->ops.get_phy_info = igb_get_phy_info_m88; phy->ops.get_cable_length = igb_get_cable_length_m88_gen2; phy->ops.set_d0_lplu_state = igb_set_d0_lplu_state_82580; @@ -925,6 +926,8 @@ static s32 igb_phy_hw_reset_sgmii_82575(struct e1000_hw *hw) if (phy->id == M88E1512_E_PHY_ID) ret_val = igb_initialize_M88E1512_phy(hw); + if (phy->id == M88E1543_E_PHY_ID) + ret_val = igb_initialize_M88E1543_phy(hw); out: return ret_val; } @@ -2145,7 +2148,7 @@ void igb_vmdq_set_replication_pf(struct e1000_hw *hw, bool enable) * Reads the MDI control register in the PHY at offset and stores the * information read to data. **/ -static s32 igb_read_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 *data) +s32 igb_read_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 *data) { s32 ret_val; @@ -2169,7 +2172,7 @@ out: * * Writes data to MDI control register in the PHY at offset. **/ -static s32 igb_write_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 data) +s32 igb_write_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 data) { s32 ret_val; diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index b1915043bc0cf..c3c598c347a95 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -927,7 +927,10 @@ /* Intel i347-AT4 Registers */ -#define I347AT4_PCDL 0x10 /* PHY Cable Diagnostics Length */ +#define I347AT4_PCDL0 0x10 /* Pair 0 PHY Cable Diagnostics Length */ +#define I347AT4_PCDL1 0x11 /* Pair 1 PHY Cable Diagnostics Length */ +#define I347AT4_PCDL2 0x12 /* Pair 2 PHY Cable Diagnostics Length */ +#define I347AT4_PCDL3 0x13 /* Pair 3 PHY Cable Diagnostics Length */ #define I347AT4_PCDC 0x15 /* PHY Cable Diagnostics Control */ #define I347AT4_PAGE_SELECT 0x16 @@ -990,6 +993,7 @@ #define E1000_M88E1543_PAGE_ADDR 0x16 /* Page Offset Register */ #define E1000_M88E1543_EEE_CTRL_1 0x0 #define E1000_M88E1543_EEE_CTRL_1_MS 0x0001 /* EEE Master/Slave */ +#define E1000_M88E1543_FIBER_CTRL 0x0 #define E1000_EEE_ADV_DEV_I354 7 #define E1000_EEE_ADV_ADDR_I354 60 #define E1000_EEE_ADV_100_SUPPORTED (1 << 1) /* 100BaseTx EEE Supported */ diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index 2003b3756ba2d..4034207eb5ccb 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -441,6 +441,7 @@ struct e1000_phy_info { u16 cable_length; u16 max_cable_length; u16 min_cable_length; + u16 pair_length[4]; u8 mdix; diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index 65d931669f813..8aa798737d4d3 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -861,10 +861,10 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw) if (ret_val) nvm_word = E1000_INVM_DEFAULT_AL; tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL; + igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, E1000_PHY_PLL_FREQ_PAGE); for (i = 0; i < E1000_MAX_PLL_TRIES; i++) { /* check current state directly from internal PHY */ - igb_read_phy_reg_gs40g(hw, (E1000_PHY_PLL_FREQ_PAGE | - E1000_PHY_PLL_FREQ_REG), &phy_word); + igb_read_phy_reg_82580(hw, E1000_PHY_PLL_FREQ_REG, &phy_word); if ((phy_word & E1000_PHY_PLL_UNCONF) != E1000_PHY_PLL_UNCONF) { ret_val = 0; @@ -896,7 +896,35 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw) /* restore WUC register */ wr32(E1000_WUC, wuc); } + igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, 0); /* restore MDICNFG setting */ wr32(E1000_MDICNFG, mdicnfg); return ret_val; } + +/** + * igb_get_cfg_done_i210 - Read config done bit + * @hw: pointer to the HW structure + * + * Read the management control register for the config done bit for + * completion status. NOTE: silicon which is EEPROM-less will fail trying + * to read the config done bit, so an error is *ONLY* logged and returns + * 0. If we were to return with error, EEPROM-less silicon + * would not be able to be reset or change link. + **/ +s32 igb_get_cfg_done_i210(struct e1000_hw *hw) +{ + s32 timeout = PHY_CFG_TIMEOUT; + u32 mask = E1000_NVM_CFG_DONE_PORT_0; + + while (timeout) { + if (rd32(E1000_EEMNGCTL_I210) & mask) + break; + usleep_range(1000, 2000); + timeout--; + } + if (!timeout) + hw_dbg("MNG configuration cycle has not completed.\n"); + + return 0; +} diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h index 3442b6357d012..b2964a2a60b1a 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.h +++ b/drivers/net/ethernet/intel/igb/e1000_i210.h @@ -34,6 +34,7 @@ s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data); s32 igb_init_nvm_params_i210(struct e1000_hw *hw); bool igb_get_flash_presence_i210(struct e1000_hw *hw); s32 igb_pll_workaround_i210(struct e1000_hw *hw); +s32 igb_get_cfg_done_i210(struct e1000_hw *hw); #define E1000_STM_OPCODE 0xDB00 #define E1000_EEPROM_FLASH_SIZE_WORD 0x11 @@ -84,7 +85,7 @@ enum E1000_INVM_STRUCTURE_TYPE { #define E1000_PCI_PMCSR_D3 0x03 #define E1000_MAX_PLL_TRIES 5 #define E1000_PHY_PLL_UNCONF 0xFF -#define E1000_PHY_PLL_FREQ_PAGE 0xFC0000 +#define E1000_PHY_PLL_FREQ_PAGE 0xFC #define E1000_PHY_PLL_FREQ_REG 0x000E #define E1000_INVM_DEFAULT_AL 0x202F #define E1000_INVM_AUTOLOAD 0x0A diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index 23ec28f43f6d3..5b54254aed4f3 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -1717,59 +1717,76 @@ s32 igb_get_cable_length_m88_gen2(struct e1000_hw *hw) struct e1000_phy_info *phy = &hw->phy; s32 ret_val; u16 phy_data, phy_data2, index, default_page, is_cm; + int len_tot = 0; + u16 len_min; + u16 len_max; switch (hw->phy.id) { + case M88E1543_E_PHY_ID: + case M88E1512_E_PHY_ID: + case I347AT4_E_PHY_ID: case I210_I_PHY_ID: - /* Get cable length from PHY Cable Diagnostics Control Reg */ - ret_val = phy->ops.read_reg(hw, (0x7 << GS40G_PAGE_SHIFT) + - (I347AT4_PCDL + phy->addr), - &phy_data); + /* Remember the original page select and set it to 7 */ + ret_val = phy->ops.read_reg(hw, I347AT4_PAGE_SELECT, + &default_page); if (ret_val) - return ret_val; + goto out; + + ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0x07); + if (ret_val) + goto out; /* Check if the unit of cable length is meters or cm */ - ret_val = phy->ops.read_reg(hw, (0x7 << GS40G_PAGE_SHIFT) + - I347AT4_PCDC, &phy_data2); + ret_val = phy->ops.read_reg(hw, I347AT4_PCDC, &phy_data2); if (ret_val) - return ret_val; + goto out; is_cm = !(phy_data2 & I347AT4_PCDC_CABLE_LENGTH_UNIT); - /* Populate the phy structure with cable length in meters */ - phy->min_cable_length = phy_data / (is_cm ? 100 : 1); - phy->max_cable_length = phy_data / (is_cm ? 100 : 1); - phy->cable_length = phy_data / (is_cm ? 100 : 1); - break; - case M88E1543_E_PHY_ID: - case M88E1512_E_PHY_ID: - case I347AT4_E_PHY_ID: - /* Remember the original page select and set it to 7 */ - ret_val = phy->ops.read_reg(hw, I347AT4_PAGE_SELECT, - &default_page); + /* Get cable length from Pair 0 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL0, &phy_data); if (ret_val) goto out; - ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0x07); + phy->pair_length[0] = phy_data / (is_cm ? 100 : 1); + len_tot = phy->pair_length[0]; + len_min = phy->pair_length[0]; + len_max = phy->pair_length[0]; + + /* Get cable length from Pair 1 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL1, &phy_data); if (ret_val) goto out; - /* Get cable length from PHY Cable Diagnostics Control Reg */ - ret_val = phy->ops.read_reg(hw, (I347AT4_PCDL + phy->addr), - &phy_data); + phy->pair_length[1] = phy_data / (is_cm ? 100 : 1); + len_tot += phy->pair_length[1]; + len_min = min(len_min, phy->pair_length[1]); + len_max = max(len_max, phy->pair_length[1]); + + /* Get cable length from Pair 2 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL2, &phy_data); if (ret_val) goto out; - /* Check if the unit of cable length is meters or cm */ - ret_val = phy->ops.read_reg(hw, I347AT4_PCDC, &phy_data2); + phy->pair_length[2] = phy_data / (is_cm ? 100 : 1); + len_tot += phy->pair_length[2]; + len_min = min(len_min, phy->pair_length[2]); + len_max = max(len_max, phy->pair_length[2]); + + /* Get cable length from Pair 3 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL3, &phy_data); if (ret_val) goto out; - is_cm = !(phy_data2 & I347AT4_PCDC_CABLE_LENGTH_UNIT); + phy->pair_length[3] = phy_data / (is_cm ? 100 : 1); + len_tot += phy->pair_length[3]; + len_min = min(len_min, phy->pair_length[3]); + len_max = max(len_max, phy->pair_length[3]); /* Populate the phy structure with cable length in meters */ - phy->min_cable_length = phy_data / (is_cm ? 100 : 1); - phy->max_cable_length = phy_data / (is_cm ? 100 : 1); - phy->cable_length = phy_data / (is_cm ? 100 : 1); + phy->min_cable_length = len_min; + phy->max_cable_length = len_max; + phy->cable_length = len_tot / 4; /* Reset the page selec to its original value */ ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, @@ -2278,6 +2295,100 @@ out: } /** + * igb_initialize_M88E1543_phy - Initialize M88E1512 PHY + * @hw: pointer to the HW structure + * + * Initialize Marvell 1543 to work correctly with Avoton. + **/ +s32 igb_initialize_M88E1543_phy(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + + /* Switch to PHY page 0xFF. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x00FF); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0x214B); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2144); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0x0C28); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2146); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0xB233); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x214D); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0xDC0C); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2159); + if (ret_val) + goto out; + + /* Switch to PHY page 0xFB. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x00FB); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_3, 0x0C0D); + if (ret_val) + goto out; + + /* Switch to PHY page 0x12. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x12); + if (ret_val) + goto out; + + /* Change mode to SGMII-to-Copper */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_MODE, 0x8001); + if (ret_val) + goto out; + + /* Switch to PHY page 1. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x1); + if (ret_val) + goto out; + + /* Change mode to 1000BASE-X/SGMII and autoneg enable */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_FIBER_CTRL, 0x9140); + if (ret_val) + goto out; + + /* Return the PHY to page 0. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0); + if (ret_val) + goto out; + + ret_val = igb_phy_sw_reset(hw); + if (ret_val) { + hw_dbg("Error committing the PHY changes\n"); + return ret_val; + } + + /* msec_delay(1000); */ + usleep_range(1000, 2000); +out: + return ret_val; +} + +/** * igb_power_up_phy_copper - Restore copper link in case of PHY power down * @hw: pointer to the HW structure * @@ -2494,66 +2605,6 @@ out: } /** - * igb_write_phy_reg_gs40g - Write GS40G PHY register - * @hw: pointer to the HW structure - * @offset: lower half is register offset to write to - * upper half is page to use. - * @data: data to write at register offset - * - * Acquires semaphore, if necessary, then writes the data to PHY register - * at the offset. Release any acquired semaphores before exiting. - **/ -s32 igb_write_phy_reg_gs40g(struct e1000_hw *hw, u32 offset, u16 data) -{ - s32 ret_val; - u16 page = offset >> GS40G_PAGE_SHIFT; - - offset = offset & GS40G_OFFSET_MASK; - ret_val = hw->phy.ops.acquire(hw); - if (ret_val) - return ret_val; - - ret_val = igb_write_phy_reg_mdic(hw, GS40G_PAGE_SELECT, page); - if (ret_val) - goto release; - ret_val = igb_write_phy_reg_mdic(hw, offset, data); - -release: - hw->phy.ops.release(hw); - return ret_val; -} - -/** - * igb_read_phy_reg_gs40g - Read GS40G PHY register - * @hw: pointer to the HW structure - * @offset: lower half is register offset to read to - * upper half is page to use. - * @data: data to read at register offset - * - * Acquires semaphore, if necessary, then reads the data in the PHY register - * at the offset. Release any acquired semaphores before exiting. - **/ -s32 igb_read_phy_reg_gs40g(struct e1000_hw *hw, u32 offset, u16 *data) -{ - s32 ret_val; - u16 page = offset >> GS40G_PAGE_SHIFT; - - offset = offset & GS40G_OFFSET_MASK; - ret_val = hw->phy.ops.acquire(hw); - if (ret_val) - return ret_val; - - ret_val = igb_write_phy_reg_mdic(hw, GS40G_PAGE_SELECT, page); - if (ret_val) - goto release; - ret_val = igb_read_phy_reg_mdic(hw, offset, data); - -release: - hw->phy.ops.release(hw); - return ret_val; -} - -/** * igb_set_master_slave_mode - Setup PHY for Master/slave mode * @hw: pointer to the HW structure * diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h index 24d55edbb0e3a..969a6ddafa3bc 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.h +++ b/drivers/net/ethernet/intel/igb/e1000_phy.h @@ -62,6 +62,7 @@ void igb_power_up_phy_copper(struct e1000_hw *hw); void igb_power_down_phy_copper(struct e1000_hw *hw); s32 igb_phy_init_script_igp3(struct e1000_hw *hw); s32 igb_initialize_M88E1512_phy(struct e1000_hw *hw); +s32 igb_initialize_M88E1543_phy(struct e1000_hw *hw); s32 igb_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data); s32 igb_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data); s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data); @@ -71,8 +72,8 @@ s32 igb_copper_link_setup_82580(struct e1000_hw *hw); s32 igb_get_phy_info_82580(struct e1000_hw *hw); s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw); s32 igb_get_cable_length_82580(struct e1000_hw *hw); -s32 igb_read_phy_reg_gs40g(struct e1000_hw *hw, u32 offset, u16 *data); -s32 igb_write_phy_reg_gs40g(struct e1000_hw *hw, u32 offset, u16 data); +s32 igb_read_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 *data); +s32 igb_write_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 data); s32 igb_check_polarity_m88(struct e1000_hw *hw); /* IGP01E1000 Specific Registers */ @@ -143,17 +144,6 @@ s32 igb_check_polarity_m88(struct e1000_hw *hw); #define E1000_CABLE_LENGTH_UNDEFINED 0xFF -/* GS40G - I210 PHY defines */ -#define GS40G_PAGE_SELECT 0x16 -#define GS40G_PAGE_SHIFT 16 -#define GS40G_OFFSET_MASK 0xFFFF -#define GS40G_PAGE_2 0x20000 -#define GS40G_MAC_REG2 0x15 -#define GS40G_MAC_LB 0x4140 -#define GS40G_MAC_SPEED_1G 0X0006 -#define GS40G_COPPER_SPEC 0x0010 -#define GS40G_LINE_LB 0x4000 - /* SFP modules ID memory locations */ #define E1000_SFF_IDENTIFIER_OFFSET 0x00 #define E1000_SFF_IDENTIFIER_SFF 0x02 diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 4af2870e49f88..21d9d02885cb0 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -66,6 +66,7 @@ #define E1000_PBA 0x01000 /* Packet Buffer Allocation - RW */ #define E1000_PBS 0x01008 /* Packet Buffer Size */ #define E1000_EEMNGCTL 0x01010 /* MNG EEprom Control */ +#define E1000_EEMNGCTL_I210 0x12030 /* MNG EEprom Control */ #define E1000_EEARBC_I210 0x12024 /* EEPROM Auto Read Bus Control */ #define E1000_EEWR 0x0102C /* EEPROM Write Register - RW */ #define E1000_I2CCMD 0x01028 /* SFPI2C Command Register - RW */ @@ -385,8 +386,7 @@ do { \ #define array_wr32(reg, offset, value) \ wr32((reg) + ((offset) << 2), (value)) -#define array_rd32(reg, offset) \ - (readl(hw->hw_addr + reg + ((offset) << 2))) +#define array_rd32(reg, offset) (igb_rd32(hw, reg + ((offset) << 2))) /* DMA Coalescing registers */ #define E1000_PCIEMISC 0x05BB8 /* PCIE misc config register */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 1a2f1cc44b283..e3cb93bdb21ae 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -389,6 +389,8 @@ struct igb_adapter { u16 link_speed; u16 link_duplex; + u8 __iomem *io_addr; /* Mainly for iounmap use */ + struct work_struct reset_task; struct work_struct watchdog_task; bool fc_autoneg; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 2529bc625de45..1d329f1d047be 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -127,10 +127,20 @@ static const struct igb_stats igb_gstrings_net_stats[] = { #define IGB_STATS_LEN \ (IGB_GLOBAL_STATS_LEN + IGB_NETDEV_STATS_LEN + IGB_QUEUE_STATS_LEN) +enum igb_diagnostics_results { + TEST_REG = 0, + TEST_EEP, + TEST_IRQ, + TEST_LOOP, + TEST_LINK +}; + static const char igb_gstrings_test[][ETH_GSTRING_LEN] = { - "Register test (offline)", "Eeprom test (offline)", - "Interrupt test (offline)", "Loopback test (offline)", - "Link test (on/offline)" + [TEST_REG] = "Register test (offline)", + [TEST_EEP] = "Eeprom test (offline)", + [TEST_IRQ] = "Interrupt test (offline)", + [TEST_LOOP] = "Loopback test (offline)", + [TEST_LINK] = "Link test (on/offline)" }; #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) @@ -2002,7 +2012,7 @@ static void igb_diag_test(struct net_device *netdev, /* Link test performed before hardware reset so autoneg doesn't * interfere with test result */ - if (igb_link_test(adapter, &data[4])) + if (igb_link_test(adapter, &data[TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; if (if_running) @@ -2011,21 +2021,21 @@ static void igb_diag_test(struct net_device *netdev, else igb_reset(adapter); - if (igb_reg_test(adapter, &data[0])) + if (igb_reg_test(adapter, &data[TEST_REG])) eth_test->flags |= ETH_TEST_FL_FAILED; igb_reset(adapter); - if (igb_eeprom_test(adapter, &data[1])) + if (igb_eeprom_test(adapter, &data[TEST_EEP])) eth_test->flags |= ETH_TEST_FL_FAILED; igb_reset(adapter); - if (igb_intr_test(adapter, &data[2])) + if (igb_intr_test(adapter, &data[TEST_IRQ])) eth_test->flags |= ETH_TEST_FL_FAILED; igb_reset(adapter); /* power up link for loopback test */ igb_power_up_link(adapter); - if (igb_loopback_test(adapter, &data[3])) + if (igb_loopback_test(adapter, &data[TEST_LOOP])) eth_test->flags |= ETH_TEST_FL_FAILED; /* restore speed, duplex, autoneg settings */ @@ -2045,16 +2055,16 @@ static void igb_diag_test(struct net_device *netdev, dev_info(&adapter->pdev->dev, "online testing starting\n"); /* PHY is powered down when interface is down */ - if (if_running && igb_link_test(adapter, &data[4])) + if (if_running && igb_link_test(adapter, &data[TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; else - data[4] = 0; + data[TEST_LINK] = 0; /* Online tests aren't run; pass by default */ - data[0] = 0; - data[1] = 0; - data[2] = 0; - data[3] = 0; + data[TEST_REG] = 0; + data[TEST_EEP] = 0; + data[TEST_IRQ] = 0; + data[TEST_LOOP] = 0; clear_bit(__IGB_TESTING, &adapter->state); } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index ea7b098872456..31e5f39428393 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -946,7 +946,6 @@ static void igb_configure_msix(struct igb_adapter *adapter) static int igb_request_msix(struct igb_adapter *adapter) { struct net_device *netdev = adapter->netdev; - struct e1000_hw *hw = &adapter->hw; int i, err = 0, vector = 0, free_vector = 0; err = request_irq(adapter->msix_entries[vector].vector, @@ -959,7 +958,7 @@ static int igb_request_msix(struct igb_adapter *adapter) vector++; - q_vector->itr_register = hw->hw_addr + E1000_EITR(vector); + q_vector->itr_register = adapter->io_addr + E1000_EITR(vector); if (q_vector->rx.ring && q_vector->tx.ring) sprintf(q_vector->name, "%s-TxRx-%u", netdev->name, @@ -1230,7 +1229,7 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, q_vector->tx.work_limit = adapter->tx_work_limit; /* initialize ITR configuration */ - q_vector->itr_register = adapter->hw.hw_addr + E1000_EITR(0); + q_vector->itr_register = adapter->io_addr + E1000_EITR(0); q_vector->itr_val = IGB_START_ITR; /* initialize pointer to rings */ @@ -2294,9 +2293,11 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); err = -EIO; - hw->hw_addr = pci_iomap(pdev, 0, 0); - if (!hw->hw_addr) + adapter->io_addr = pci_iomap(pdev, 0, 0); + if (!adapter->io_addr) goto err_ioremap; + /* hw->hw_addr can be altered, we'll use adapter->io_addr for unmap */ + hw->hw_addr = adapter->io_addr; netdev->netdev_ops = &igb_netdev_ops; igb_set_ethtool_ops(netdev); @@ -2378,8 +2379,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } if (hw->mac.type >= e1000_82576) { - netdev->hw_features |= NETIF_F_SCTP_CSUM; - netdev->features |= NETIF_F_SCTP_CSUM; + netdev->hw_features |= NETIF_F_SCTP_CRC; + netdev->features |= NETIF_F_SCTP_CRC; } netdev->priv_flags |= IFF_UNICAST_FLT; @@ -2656,7 +2657,7 @@ err_sw_init: #ifdef CONFIG_PCI_IOV igb_disable_sriov(pdev); #endif - pci_iounmap(pdev, hw->hw_addr); + pci_iounmap(pdev, adapter->io_addr); err_ioremap: free_netdev(netdev); err_alloc_etherdev: @@ -2823,7 +2824,7 @@ static void igb_remove(struct pci_dev *pdev) igb_clear_interrupt_scheme(adapter); - pci_iounmap(pdev, hw->hw_addr); + pci_iounmap(pdev, adapter->io_addr); if (hw->flash_address) iounmap(hw->flash_address); pci_release_selected_regions(pdev, @@ -2856,6 +2857,13 @@ static void igb_probe_vfs(struct igb_adapter *adapter) if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) return; + /* Of the below we really only want the effect of getting + * IGB_FLAG_HAS_MSIX set (if available), without which + * igb_enable_sriov() has no effect. + */ + igb_set_interrupt_capability(adapter, true); + igb_reset_interrupt_capability(adapter); + pci_sriov_set_totalvfs(pdev, 7); igb_enable_sriov(pdev, max_vfs); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 445b4c9169b61..4b9156cd8b93c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -317,7 +317,7 @@ enum ixgbe_ring_f_enum { }; #define IXGBE_MAX_RSS_INDICES 16 -#define IXGBE_MAX_RSS_INDICES_X550 64 +#define IXGBE_MAX_RSS_INDICES_X550 63 #define IXGBE_MAX_VMDQ_INDICES 64 #define IXGBE_MAX_FDIR_INDICES 63 /* based on q_vector limit */ #define IXGBE_MAX_FCOE_INDICES 8 @@ -664,6 +664,7 @@ struct ixgbe_adapter { #ifdef CONFIG_IXGBE_VXLAN #define IXGBE_FLAG2_VXLAN_REREG_NEEDED BIT(12) #endif +#define IXGBE_FLAG2_VLAN_PROMISC BIT(13) /* Tx fast path data */ int num_tx_queues; @@ -897,6 +898,7 @@ int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, const u8 *addr, u16 queue); int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, const u8 *addr, u16 queue); +void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid); void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter); netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, struct ixgbe_adapter *, struct ixgbe_ring *); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 8f09d291a0430..d8a9fb8a59e20 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -880,11 +880,12 @@ static s32 ixgbe_clear_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) * @vlan: VLAN id to write to VLAN filter * @vind: VMDq output index that maps queue to VLAN id in VFTA * @vlan_on: boolean flag to turn on/off VLAN in VFTA + * @vlvf_bypass: boolean flag - unused * * Turn on/off specified VLAN in the VLAN filter table. **/ static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind, - bool vlan_on) + bool vlan_on, bool vlvf_bypass) { u32 regindex; u32 bitindex; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index b8bd72589f729..fa8d4f40ac2af 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1083,12 +1083,16 @@ mac_reset_top: /* Add the SAN MAC address to the RAR only if it's a valid address */ if (is_valid_ether_addr(hw->mac.san_addr)) { - hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, - hw->mac.san_addr, 0, IXGBE_RAH_AV); - /* Save the SAN MAC RAR index */ hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; + hw->mac.ops.set_rar(hw, hw->mac.san_mac_rar_index, + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* clear VMDq pool/queue selection for this RAR */ + hw->mac.ops.clear_vmdq(hw, hw->mac.san_mac_rar_index, + IXGBE_CLEAR_VMDQ_ALL); + /* Reserve the last RAR for the SAN MAC address */ hw->mac.num_rar_entries--; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index daec6aef5dc8b..64045053e874b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1884,10 +1884,11 @@ s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw) hw_dbg(hw, " New MAC Addr =%pM\n", hw->mac.addr); hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV); - - /* clear VMDq pool/queue selection for RAR 0 */ - hw->mac.ops.clear_vmdq(hw, 0, IXGBE_CLEAR_VMDQ_ALL); } + + /* clear VMDq pool/queue selection for RAR 0 */ + hw->mac.ops.clear_vmdq(hw, 0, IXGBE_CLEAR_VMDQ_ALL); + hw->addr_ctrl.overflow_promisc = 0; hw->addr_ctrl.rar_used_count = 1; @@ -2999,43 +3000,44 @@ s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw) * return the VLVF index where this VLAN id should be placed * **/ -static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan) +static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) { - u32 bits = 0; - u32 first_empty_slot = 0; - s32 regindex; + s32 regindex, first_empty_slot; + u32 bits; /* short cut the special case */ if (vlan == 0) return 0; - /* - * Search for the vlan id in the VLVF entries. Save off the first empty - * slot found along the way - */ - for (regindex = 1; regindex < IXGBE_VLVF_ENTRIES; regindex++) { + /* if vlvf_bypass is set we don't want to use an empty slot, we + * will simply bypass the VLVF if there are no entries present in the + * VLVF that contain our VLAN + */ + first_empty_slot = vlvf_bypass ? IXGBE_ERR_NO_SPACE : 0; + + /* add VLAN enable bit for comparison */ + vlan |= IXGBE_VLVF_VIEN; + + /* Search for the vlan id in the VLVF entries. Save off the first empty + * slot found along the way. + * + * pre-decrement loop covering (IXGBE_VLVF_ENTRIES - 1) .. 1 + */ + for (regindex = IXGBE_VLVF_ENTRIES; --regindex;) { bits = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); - if (!bits && !(first_empty_slot)) + if (bits == vlan) + return regindex; + if (!first_empty_slot && !bits) first_empty_slot = regindex; - else if ((bits & 0x0FFF) == vlan) - break; } - /* - * If regindex is less than IXGBE_VLVF_ENTRIES, then we found the vlan - * in the VLVF. Else use the first empty VLVF register for this - * vlan id. - */ - if (regindex >= IXGBE_VLVF_ENTRIES) { - if (first_empty_slot) - regindex = first_empty_slot; - else { - hw_dbg(hw, "No space in VLVF.\n"); - regindex = IXGBE_ERR_NO_SPACE; - } - } + /* If we are here then we didn't find the VLAN. Return first empty + * slot we found during our search, else error. + */ + if (!first_empty_slot) + hw_dbg(hw, "No space in VLVF.\n"); - return regindex; + return first_empty_slot ? : IXGBE_ERR_NO_SPACE; } /** @@ -3044,21 +3046,17 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan) * @vlan: VLAN id to write to VLAN filter * @vind: VMDq output index that maps queue to VLAN id in VFVFB * @vlan_on: boolean flag to turn on/off VLAN in VFVF + * @vlvf_bypass: boolean flag indicating updating default pool is okay * * Turn on/off specified VLAN in the VLAN filter table. **/ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, - bool vlan_on) + bool vlan_on, bool vlvf_bypass) { - s32 regindex; - u32 bitindex; - u32 vfta; - u32 bits; - u32 vt; - u32 targetbit; - bool vfta_changed = false; + u32 regidx, vfta_delta, vfta, bits; + s32 vlvf_index; - if (vlan > 4095) + if ((vlan > 4095) || (vind > 63)) return IXGBE_ERR_PARAM; /* @@ -3073,22 +3071,16 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, * bits[11-5]: which register * bits[4-0]: which bit in the register */ - regindex = (vlan >> 5) & 0x7F; - bitindex = vlan & 0x1F; - targetbit = (1 << bitindex); - vfta = IXGBE_READ_REG(hw, IXGBE_VFTA(regindex)); - - if (vlan_on) { - if (!(vfta & targetbit)) { - vfta |= targetbit; - vfta_changed = true; - } - } else { - if ((vfta & targetbit)) { - vfta &= ~targetbit; - vfta_changed = true; - } - } + regidx = vlan / 32; + vfta_delta = 1 << (vlan % 32); + vfta = IXGBE_READ_REG(hw, IXGBE_VFTA(regidx)); + + /* vfta_delta represents the difference between the current value + * of vfta and the value we want in the register. Since the diff + * is an XOR mask we can just update vfta using an XOR. + */ + vfta_delta &= vlan_on ? ~vfta : vfta; + vfta ^= vfta_delta; /* Part 2 * If VT Mode is set @@ -3098,85 +3090,67 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, * Or !vlan_on * clear the pool bit and possibly the vind */ - vt = IXGBE_READ_REG(hw, IXGBE_VT_CTL); - if (vt & IXGBE_VT_CTL_VT_ENABLE) { - s32 vlvf_index; - - vlvf_index = ixgbe_find_vlvf_slot(hw, vlan); - if (vlvf_index < 0) - return vlvf_index; - - if (vlan_on) { - /* set the pool bit */ - if (vind < 32) { - bits = IXGBE_READ_REG(hw, - IXGBE_VLVFB(vlvf_index*2)); - bits |= (1 << vind); - IXGBE_WRITE_REG(hw, - IXGBE_VLVFB(vlvf_index*2), - bits); - } else { - bits = IXGBE_READ_REG(hw, - IXGBE_VLVFB((vlvf_index*2)+1)); - bits |= (1 << (vind-32)); - IXGBE_WRITE_REG(hw, - IXGBE_VLVFB((vlvf_index*2)+1), - bits); - } - } else { - /* clear the pool bit */ - if (vind < 32) { - bits = IXGBE_READ_REG(hw, - IXGBE_VLVFB(vlvf_index*2)); - bits &= ~(1 << vind); - IXGBE_WRITE_REG(hw, - IXGBE_VLVFB(vlvf_index*2), - bits); - bits |= IXGBE_READ_REG(hw, - IXGBE_VLVFB((vlvf_index*2)+1)); - } else { - bits = IXGBE_READ_REG(hw, - IXGBE_VLVFB((vlvf_index*2)+1)); - bits &= ~(1 << (vind-32)); - IXGBE_WRITE_REG(hw, - IXGBE_VLVFB((vlvf_index*2)+1), - bits); - bits |= IXGBE_READ_REG(hw, - IXGBE_VLVFB(vlvf_index*2)); - } - } + if (!(IXGBE_READ_REG(hw, IXGBE_VT_CTL) & IXGBE_VT_CTL_VT_ENABLE)) + goto vfta_update; + + vlvf_index = ixgbe_find_vlvf_slot(hw, vlan, vlvf_bypass); + if (vlvf_index < 0) { + if (vlvf_bypass) + goto vfta_update; + return vlvf_index; + } - /* - * If there are still bits set in the VLVFB registers - * for the VLAN ID indicated we need to see if the - * caller is requesting that we clear the VFTA entry bit. - * If the caller has requested that we clear the VFTA - * entry bit but there are still pools/VFs using this VLAN - * ID entry then ignore the request. We're not worried - * about the case where we're turning the VFTA VLAN ID - * entry bit on, only when requested to turn it off as - * there may be multiple pools and/or VFs using the - * VLAN ID entry. In that case we cannot clear the - * VFTA bit until all pools/VFs using that VLAN ID have also - * been cleared. This will be indicated by "bits" being - * zero. + bits = IXGBE_READ_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + vind / 32)); + + /* set the pool bit */ + bits |= 1 << (vind % 32); + if (vlan_on) + goto vlvf_update; + + /* clear the pool bit */ + bits ^= 1 << (vind % 32); + + if (!bits && + !IXGBE_READ_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + 1 - vind / 32))) { + /* Clear VFTA first, then disable VLVF. Otherwise + * we run the risk of stray packets leaking into + * the PF via the default pool */ - if (bits) { - IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), - (IXGBE_VLVF_VIEN | vlan)); - if (!vlan_on) { - /* someone wants to clear the vfta entry - * but some pools/VFs are still using it. - * Ignore it. */ - vfta_changed = false; - } - } else { - IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), 0); - } + if (vfta_delta) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(regidx), vfta); + + /* disable VLVF and clear remaining bit from pool */ + IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + vind / 32), 0); + + return 0; } - if (vfta_changed) - IXGBE_WRITE_REG(hw, IXGBE_VFTA(regindex), vfta); + /* If there are still bits set in the VLVFB registers + * for the VLAN ID indicated we need to see if the + * caller is requesting that we clear the VFTA entry bit. + * If the caller has requested that we clear the VFTA + * entry bit but there are still pools/VFs using this VLAN + * ID entry then ignore the request. We're not worried + * about the case where we're turning the VFTA VLAN ID + * entry bit on, only when requested to turn it off as + * there may be multiple pools and/or VFs using the + * VLAN ID entry. In that case we cannot clear the + * VFTA bit until all pools/VFs using that VLAN ID have also + * been cleared. This will be indicated by "bits" being + * zero. + */ + vfta_delta = 0; + +vlvf_update: + /* record pool change and enable VLAN ID if not already enabled */ + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + vind / 32), bits); + IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), IXGBE_VLVF_VIEN | vlan); + +vfta_update: + /* Update VFTA now that we are ready for traffic */ + if (vfta_delta) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(regidx), vfta); return 0; } @@ -3196,8 +3170,8 @@ s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw) for (offset = 0; offset < IXGBE_VLVF_ENTRIES; offset++) { IXGBE_WRITE_REG(hw, IXGBE_VLVF(offset), 0); - IXGBE_WRITE_REG(hw, IXGBE_VLVFB(offset*2), 0); - IXGBE_WRITE_REG(hw, IXGBE_VLVFB((offset*2)+1), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(offset * 2), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(offset * 2 + 1), 0); } return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index a0044e4a8b90c..2b9563137fd88 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -92,7 +92,7 @@ s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq); s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw); s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, - u32 vind, bool vlan_on); + u32 vind, bool vlan_on, bool vlvf_bypass); s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw); s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index d681273bd39d5..2448eba2eecd1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -151,6 +151,34 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { }; #define IXGBE_TEST_LEN sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN +/* currently supported speeds for 10G */ +#define ADVRTSD_MSK_10G (SUPPORTED_10000baseT_Full | \ + SUPPORTED_10000baseKX4_Full | \ + SUPPORTED_10000baseKR_Full) + +#define ixgbe_isbackplane(type) ((type) == ixgbe_media_type_backplane) + +static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw) +{ + if (!ixgbe_isbackplane(hw->phy.media_type)) + return SUPPORTED_10000baseT_Full; + + switch (hw->device_id) { + case IXGBE_DEV_ID_82598: + case IXGBE_DEV_ID_82599_KX4: + case IXGBE_DEV_ID_82599_KX4_MEZZ: + case IXGBE_DEV_ID_X550EM_X_KX4: + return SUPPORTED_10000baseKX4_Full; + case IXGBE_DEV_ID_82598_BX: + case IXGBE_DEV_ID_82599_KR: + case IXGBE_DEV_ID_X550EM_X_KR: + return SUPPORTED_10000baseKR_Full; + default: + return SUPPORTED_10000baseKX4_Full | + SUPPORTED_10000baseKR_Full; + } +} + static int ixgbe_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) { @@ -165,33 +193,30 @@ static int ixgbe_get_settings(struct net_device *netdev, /* set the supported link speeds */ if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->supported |= SUPPORTED_10000baseT_Full; - if (supported_link & IXGBE_LINK_SPEED_2_5GB_FULL) - ecmd->supported |= SUPPORTED_2500baseX_Full; + ecmd->supported |= ixgbe_get_supported_10gtypes(hw); if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) ecmd->supported |= SUPPORTED_1000baseT_Full; if (supported_link & IXGBE_LINK_SPEED_100_FULL) - ecmd->supported |= SUPPORTED_100baseT_Full; + ecmd->supported |= ixgbe_isbackplane(hw->phy.media_type) ? + SUPPORTED_1000baseKX_Full : + SUPPORTED_1000baseT_Full; + /* default advertised speed if phy.autoneg_advertised isn't set */ + ecmd->advertising = ecmd->supported; /* set the advertised speeds */ if (hw->phy.autoneg_advertised) { + ecmd->advertising = 0; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) ecmd->advertising |= ADVERTISED_100baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising |= ADVERTISED_10000baseT_Full; - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) - ecmd->advertising |= ADVERTISED_2500baseX_Full; - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G; + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { + if (ecmd->supported & SUPPORTED_1000baseKX_Full) + ecmd->advertising |= ADVERTISED_1000baseKX_Full; + else + ecmd->advertising |= ADVERTISED_1000baseT_Full; + } } else { - /* default modes in case phy.autoneg_advertised isn't set */ - if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising |= ADVERTISED_10000baseT_Full; - if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) - ecmd->advertising |= ADVERTISED_1000baseT_Full; - if (supported_link & IXGBE_LINK_SPEED_100_FULL) - ecmd->advertising |= ADVERTISED_100baseT_Full; - if (hw->phy.multispeed_fiber && !autoneg) { if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) ecmd->advertising = ADVERTISED_10000baseT_Full; @@ -229,6 +254,10 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_phy_sfp_avago: case ixgbe_phy_sfp_intel: case ixgbe_phy_sfp_unknown: + case ixgbe_phy_qsfp_passive_unknown: + case ixgbe_phy_qsfp_active_unknown: + case ixgbe_phy_qsfp_intel: + case ixgbe_phy_qsfp_unknown: /* SFP+ devices, further checking needed */ switch (adapter->hw.phy.sfp_type) { case ixgbe_sfp_type_da_cu: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ebd4522e7879d..ea9537d0e63a9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3702,6 +3702,9 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) /* Map PF MAC address in RAR Entry 0 to first pool following VFs */ hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0)); + /* clear VLAN promisc flag so VFTA will be updated if necessary */ + adapter->flags2 &= ~IXGBE_FLAG2_VLAN_PROMISC; + /* * Set up VF register offsets for selected VT Mode, * i.e. 32 or 64 VFs for SR-IOV @@ -3899,12 +3902,56 @@ static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, struct ixgbe_hw *hw = &adapter->hw; /* add VID to filter table */ - hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true); + hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true, true); set_bit(vid, adapter->active_vlans); return 0; } +static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan) +{ + u32 vlvf; + int idx; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the vlan id in the VLVF entries */ + for (idx = IXGBE_VLVF_ENTRIES; --idx;) { + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(idx)); + if ((vlvf & VLAN_VID_MASK) == vlan) + break; + } + + return idx; +} + +void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 bits, word; + int idx; + + idx = ixgbe_find_vlvf_entry(hw, vid); + if (!idx) + return; + + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + word = idx * 2 + (VMDQ_P(0) / 32); + bits = ~(1 << (VMDQ_P(0)) % 32); + bits &= IXGBE_READ_REG(hw, IXGBE_VLVFB(word)); + + /* Disable the filter so this falls into the default pool. */ + if (!bits && !IXGBE_READ_REG(hw, IXGBE_VLVFB(word ^ 1))) { + if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVF(idx), 0); + } +} + static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { @@ -3912,7 +3959,11 @@ static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, struct ixgbe_hw *hw = &adapter->hw; /* remove VID from filter table */ - hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), false); + if (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC) + ixgbe_update_pf_promisc_vlvf(adapter, vid); + else + hw->mac.ops.set_vfta(hw, vid, VMDQ_P(0), false, true); + clear_bit(vid, adapter->active_vlans); return 0; @@ -3990,6 +4041,129 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) } } +static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl, i; + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + default: + if (adapter->flags & IXGBE_FLAG_VMDQ_ENABLED) + break; + /* fall through */ + case ixgbe_mac_82598EB: + /* legacy case, we can just disable VLAN filtering */ + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + return; + } + + /* We are already in VLAN promisc, nothing to do */ + if (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC) + return; + + /* Set flag so we don't redo unnecessary work */ + adapter->flags2 |= IXGBE_FLAG2_VLAN_PROMISC; + + /* Add PF to all active pools */ + for (i = IXGBE_VLVF_ENTRIES; --i;) { + u32 reg_offset = IXGBE_VLVFB(i * 2 + VMDQ_P(0) / 32); + u32 vlvfb = IXGBE_READ_REG(hw, reg_offset); + + vlvfb |= 1 << (VMDQ_P(0) % 32); + IXGBE_WRITE_REG(hw, reg_offset, vlvfb); + } + + /* Set all bits in the VLAN filter table array */ + for (i = hw->mac.vft_size; i--;) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U); +} + +#define VFTA_BLOCK_SIZE 8 +static void ixgbe_scrub_vfta(struct ixgbe_adapter *adapter, u32 vfta_offset) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vfta[VFTA_BLOCK_SIZE] = { 0 }; + u32 vid_start = vfta_offset * 32; + u32 vid_end = vid_start + (VFTA_BLOCK_SIZE * 32); + u32 i, vid, word, bits; + + for (i = IXGBE_VLVF_ENTRIES; --i;) { + u32 vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(i)); + + /* pull VLAN ID from VLVF */ + vid = vlvf & VLAN_VID_MASK; + + /* only concern outselves with a certain range */ + if (vid < vid_start || vid >= vid_end) + continue; + + if (vlvf) { + /* record VLAN ID in VFTA */ + vfta[(vid - vid_start) / 32] |= 1 << (vid % 32); + + /* if PF is part of this then continue */ + if (test_bit(vid, adapter->active_vlans)) + continue; + } + + /* remove PF from the pool */ + word = i * 2 + VMDQ_P(0) / 32; + bits = ~(1 << (VMDQ_P(0) % 32)); + bits &= IXGBE_READ_REG(hw, IXGBE_VLVFB(word)); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), bits); + } + + /* extract values from active_vlans and write back to VFTA */ + for (i = VFTA_BLOCK_SIZE; i--;) { + vid = (vfta_offset + i) * 32; + word = vid / BITS_PER_LONG; + bits = vid % BITS_PER_LONG; + + vfta[i] |= adapter->active_vlans[word] >> bits; + + IXGBE_WRITE_REG(hw, IXGBE_VFTA(vfta_offset + i), vfta[i]); + } +} + +static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl, i; + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + default: + if (adapter->flags & IXGBE_FLAG_VMDQ_ENABLED) + break; + /* fall through */ + case ixgbe_mac_82598EB: + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl &= ~IXGBE_VLNCTRL_CFIEN; + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + return; + } + + /* We are not in VLAN promisc, nothing to do */ + if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + return; + + /* Set flag so we don't redo unnecessary work */ + adapter->flags2 &= ~IXGBE_FLAG2_VLAN_PROMISC; + + for (i = 0; i < hw->mac.vft_size; i += VFTA_BLOCK_SIZE) + ixgbe_scrub_vfta(adapter, i); +} + static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) { u16 vid; @@ -4246,12 +4420,10 @@ void ixgbe_set_rx_mode(struct net_device *netdev) struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE; - u32 vlnctrl; int count; /* Check for Promiscuous and All Multicast modes */ fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); /* set all bits that we expect to always be set */ fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */ @@ -4261,25 +4433,18 @@ void ixgbe_set_rx_mode(struct net_device *netdev) /* clear the bits we are changing the status of */ fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); - vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); if (netdev->flags & IFF_PROMISC) { hw->addr_ctrl.user_set_promisc = true; fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); vmolr |= IXGBE_VMOLR_MPE; - /* Only disable hardware filter vlans in promiscuous mode - * if SR-IOV and VMDQ are disabled - otherwise ensure - * that hardware VLAN filters remain enabled. - */ - if (adapter->flags & (IXGBE_FLAG_VMDQ_ENABLED | - IXGBE_FLAG_SRIOV_ENABLED)) - vlnctrl |= (IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); + ixgbe_vlan_promisc_enable(adapter); } else { if (netdev->flags & IFF_ALLMULTI) { fctrl |= IXGBE_FCTRL_MPE; vmolr |= IXGBE_VMOLR_MPE; } - vlnctrl |= IXGBE_VLNCTRL_VFE; hw->addr_ctrl.user_set_promisc = false; + ixgbe_vlan_promisc_disable(adapter); } /* @@ -4323,7 +4488,6 @@ void ixgbe_set_rx_mode(struct net_device *netdev) /* NOTE: VLAN filtering is disabled by setting PROMISC */ } - IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl); if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) @@ -5381,6 +5545,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) adapter->mac_table = kzalloc(sizeof(struct ixgbe_mac_addr) * hw->mac.num_rar_entries, GFP_ATOMIC); + if (!adapter->mac_table) + return -ENOMEM; /* Set MAC specific capability flags and exceptions */ switch (hw->mac.type) { @@ -7965,6 +8131,9 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) */ if (netif_running(dev)) ixgbe_close(dev); + else + ixgbe_reset(adapter); + ixgbe_clear_interrupt_scheme(adapter); #ifdef CONFIG_IXGBE_DCB @@ -8432,7 +8601,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, if (unlikely(skb_inner_mac_header(skb) - skb_transport_header(skb) > IXGBE_MAX_TUNNEL_HDR_LEN)) - return features & ~NETIF_F_ALL_CSUM; + return features & ~NETIF_F_CSUM_MASK; return features; } @@ -8829,8 +8998,8 @@ skip_sriov: case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: - netdev->features |= NETIF_F_SCTP_CSUM; - netdev->hw_features |= NETIF_F_SCTP_CSUM | + netdev->features |= NETIF_F_SCTP_CRC; + netdev->hw_features |= NETIF_F_SCTP_CRC | NETIF_F_NTUPLE; break; default: @@ -8846,8 +9015,7 @@ skip_sriov: netdev->vlan_features |= NETIF_F_IPV6_CSUM; netdev->vlan_features |= NETIF_F_SG; - netdev->hw_enc_features |= NETIF_F_SG | NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM; + netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; @@ -8856,9 +9024,7 @@ skip_sriov: switch (adapter->hw.mac.type) { case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: - netdev->hw_enc_features |= NETIF_F_RXCSUM | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM; + netdev->hw_enc_features |= NETIF_F_RXCSUM; break; default: break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 31de6cf7adb01..8025a3f935980 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -452,11 +452,34 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, u32 vf) { - /* VLAN 0 is a special case, don't allow it to be removed */ - if (!vid && !add) - return 0; + struct ixgbe_hw *hw = &adapter->hw; + int err; + + /* If VLAN overlaps with one the PF is currently monitoring make + * sure that we are able to allocate a VLVF entry. This may be + * redundant but it guarantees PF will maintain visibility to + * the VLAN. + */ + if (add && test_bit(vid, adapter->active_vlans)) { + err = hw->mac.ops.set_vfta(hw, vid, VMDQ_P(0), true, false); + if (err) + return err; + } - return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add); + err = hw->mac.ops.set_vfta(hw, vid, vf, !!add, false); + + if (add && !err) + return err; + + /* If we failed to add the VF VLAN or we are removing the VF VLAN + * we may need to drop the PF pool bit in order to allow us to free + * up the VLVF resources. + */ + if (test_bit(vid, adapter->active_vlans) || + (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + ixgbe_update_pf_promisc_vlvf(adapter, vid); + + return err; } static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) @@ -562,13 +585,75 @@ static void ixgbe_clear_vmvir(struct ixgbe_adapter *adapter, u32 vf) IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0); } + +static void ixgbe_clear_vf_vlans(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 i; + + /* post increment loop, covers VLVF_ENTRIES - 1 to 0 */ + for (i = IXGBE_VLVF_ENTRIES; i--;) { + u32 bits[2], vlvfb, vid, vfta, vlvf; + u32 word = i * 2 + vf / 32; + u32 mask = 1 << (vf % 32); + + vlvfb = IXGBE_READ_REG(hw, IXGBE_VLVFB(word)); + + /* if our bit isn't set we can skip it */ + if (!(vlvfb & mask)) + continue; + + /* clear our bit from vlvfb */ + vlvfb ^= mask; + + /* create 64b mask to chedk to see if we should clear VLVF */ + bits[word % 2] = vlvfb; + bits[~word % 2] = IXGBE_READ_REG(hw, IXGBE_VLVFB(word ^ 1)); + + /* if promisc is enabled, PF will be present, leave VFTA */ + if (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC) { + bits[VMDQ_P(0) / 32] &= ~(1 << (VMDQ_P(0) % 32)); + + if (bits[0] || bits[1]) + goto update_vlvfb; + goto update_vlvf; + } + + /* if other pools are present, just remove ourselves */ + if (bits[0] || bits[1]) + goto update_vlvfb; + + /* if we cannot determine VLAN just remove ourselves */ + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(i)); + if (!vlvf) + goto update_vlvfb; + + vid = vlvf & VLAN_VID_MASK; + mask = 1 << (vid % 32); + + /* clear bit from VFTA */ + vfta = IXGBE_READ_REG(hw, IXGBE_VFTA(vid / 32)); + if (vfta & mask) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(vid / 32), vfta ^ mask); +update_vlvf: + /* clear POOL selection enable */ + IXGBE_WRITE_REG(hw, IXGBE_VLVF(i), 0); +update_vlvfb: + /* clear pool bits */ + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), vlvfb); + } +} + static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; u8 num_tcs = netdev_get_num_tc(adapter->netdev); - /* add PF assigned VLAN or VLAN 0 */ + /* remove VLAN filters beloning to this VF */ + ixgbe_clear_vf_vlans(adapter, vf); + + /* add back PF assigned VLAN or VLAN 0 */ ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf); /* reset offloads to defaults */ @@ -814,40 +899,14 @@ static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter, return ixgbe_set_vf_mac(adapter, vf, new_mac) < 0; } -static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan) -{ - u32 vlvf; - s32 regindex; - - /* short cut the special case */ - if (vlan == 0) - return 0; - - /* Search for the vlan id in the VLVF entries */ - for (regindex = 1; regindex < IXGBE_VLVF_ENTRIES; regindex++) { - vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); - if ((vlvf & VLAN_VID_MASK) == vlan) - break; - } - - /* Return a negative value if not found */ - if (regindex >= IXGBE_VLVF_ENTRIES) - regindex = -1; - - return regindex; -} - static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { + u32 add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; + u32 vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); + u8 tcs = netdev_get_num_tc(adapter->netdev); struct ixgbe_hw *hw = &adapter->hw; - int add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; - int vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); int err; - s32 reg_ndx; - u32 vlvf; - u32 bits; - u8 tcs = netdev_get_num_tc(adapter->netdev); if (adapter->vfinfo[vf].pf_vlan || tcs) { e_warn(drv, @@ -857,54 +916,23 @@ static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, return -1; } - if (add) - adapter->vfinfo[vf].vlan_count++; - else if (adapter->vfinfo[vf].vlan_count) - adapter->vfinfo[vf].vlan_count--; - - /* in case of promiscuous mode any VLAN filter set for a VF must - * also have the PF pool added to it. - */ - if (add && adapter->netdev->flags & IFF_PROMISC) - err = ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + /* VLAN 0 is a special case, don't allow it to be removed */ + if (!vid && !add) + return 0; err = ixgbe_set_vf_vlan(adapter, add, vid, vf); - if (!err && adapter->vfinfo[vf].spoofchk_enabled) - hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + if (err) + return err; - /* Go through all the checks to see if the VLAN filter should - * be wiped completely. - */ - if (!add && adapter->netdev->flags & IFF_PROMISC) { - reg_ndx = ixgbe_find_vlvf_entry(hw, vid); - if (reg_ndx < 0) - return err; - vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(reg_ndx)); - /* See if any other pools are set for this VLAN filter - * entry other than the PF. - */ - if (VMDQ_P(0) < 32) { - bits = IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); - bits &= ~(1 << VMDQ_P(0)); - bits |= IXGBE_READ_REG(hw, - IXGBE_VLVFB(reg_ndx * 2) + 1); - } else { - bits = IXGBE_READ_REG(hw, - IXGBE_VLVFB(reg_ndx * 2) + 1); - bits &= ~(1 << (VMDQ_P(0) - 32)); - bits |= IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); - } + if (adapter->vfinfo[vf].spoofchk_enabled) + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); - /* If the filter was removed then ensure PF pool bit - * is cleared if the PF only added itself to the pool - * because the PF is in promiscuous mode. - */ - if ((vlvf & VLAN_VID_MASK) == vid && - !test_bit(vid, adapter->active_vlans) && !bits) - ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); - } + if (add) + adapter->vfinfo[vf].vlan_count++; + else if (adapter->vfinfo[vf].vlan_count) + adapter->vfinfo[vf].vlan_count--; - return err; + return 0; } static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter, @@ -1285,6 +1313,9 @@ static int ixgbe_enable_port_vlan(struct ixgbe_adapter *adapter, int vf, if (err) goto out; + /* Revoke tagless access via VLAN 0 */ + ixgbe_set_vf_vlan(adapter, false, 0, vf); + ixgbe_set_vmvir(adapter, vlan, qos, vf); ixgbe_set_vmolr(hw, vf, false); if (adapter->vfinfo[vf].spoofchk_enabled) @@ -1318,6 +1349,8 @@ static int ixgbe_disable_port_vlan(struct ixgbe_adapter *adapter, int vf) err = ixgbe_set_vf_vlan(adapter, false, adapter->vfinfo[vf].pf_vlan, vf); + /* Restore tagless access via VLAN 0 */ + ixgbe_set_vf_vlan(adapter, true, 0, vf); ixgbe_clear_vmvir(adapter, vf); ixgbe_set_vmolr(hw, vf, true); hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 1329eddfc9ce7..5f53cc6c609a0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -3300,7 +3300,7 @@ struct ixgbe_mac_operations { s32 (*enable_mc)(struct ixgbe_hw *); s32 (*disable_mc)(struct ixgbe_hw *); s32 (*clear_vfta)(struct ixgbe_hw *); - s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool); + s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool, bool); s32 (*init_uta_tables)(struct ixgbe_hw *); void (*set_mac_anti_spoofing)(struct ixgbe_hw *, bool, int); void (*set_vlan_anti_spoofing)(struct ixgbe_hw *, bool, int); @@ -3520,7 +3520,7 @@ struct ixgbe_info { #define IXGBE_FUSES0_GROUP(_i) (0x11158 + ((_i) * 4)) #define IXGBE_FUSES0_300MHZ BIT(5) -#define IXGBE_FUSES0_REV1 BIT(6) +#define IXGBE_FUSES0_REV_MASK (3 << 6) #define IXGBE_KRM_PORT_CAR_GEN_CTRL(P) ((P) ? 0x8010 : 0x4010) #define IXGBE_KRM_LINK_CTRL_1(P) ((P) ? 0x820C : 0x420C) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index bf8225ceab8e4..2358c1b7d5864 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -154,12 +154,16 @@ mac_reset_top: /* Add the SAN MAC address to the RAR only if it's a valid address */ if (is_valid_ether_addr(hw->mac.san_addr)) { - hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, - hw->mac.san_addr, 0, IXGBE_RAH_AV); - /* Save the SAN MAC RAR index */ hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; + hw->mac.ops.set_rar(hw, hw->mac.san_mac_rar_index, + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* clear VMDq pool/queue selection for this RAR */ + hw->mac.ops.clear_vmdq(hw, hw->mac.san_mac_rar_index, + IXGBE_CLEAR_VMDQ_ALL); + /* Reserve the last RAR for the SAN MAC address */ hw->mac.num_rar_entries--; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index f4ef0d1a5dbea..87aca3f7c3dec 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1857,10 +1857,6 @@ static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw) u32 save_autoneg; bool link_up; - /* SW LPLU not required on later HW revisions. */ - if (IXGBE_FUSES0_REV1 & IXGBE_READ_REG(hw, IXGBE_FUSES0_GROUP(0))) - return 0; - /* If blocked by MNG FW, then don't restart AN */ if (ixgbe_check_reset_blocked(hw)) return 0; @@ -2000,8 +1996,9 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) ixgbe_setup_internal_phy_t_x550em; /* setup SW LPLU only for first revision */ - if (!(IXGBE_FUSES0_REV1 & IXGBE_READ_REG(hw, - IXGBE_FUSES0_GROUP(0)))) + if (hw->mac.type == ixgbe_mac_X550EM_x && + !(IXGBE_READ_REG(hw, IXGBE_FUSES0_GROUP(0)) & + IXGBE_FUSES0_REV_MASK)) phy->ops.enter_lplu = ixgbe_enter_lplu_t_x550em; phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index f098952d4fb4a..3558f019b6311 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1016,6 +1016,8 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) ixgbevf_for_each_ring(ring, q_vector->tx) clean_complete &= ixgbevf_clean_tx_irq(q_vector, ring); + if (budget <= 0) + return budget; #ifdef CONFIG_NET_RX_BUSY_POLL if (!ixgbevf_qv_lock_napi(q_vector)) return budget; @@ -1045,7 +1047,7 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) return budget; /* all work done, exit the polling mode */ napi_complete_done(napi, work_done); - if (adapter->rx_itr_setting & 1) + if (adapter->rx_itr_setting == 1) ixgbevf_set_itr(q_vector); if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && !test_bit(__IXGBEVF_REMOVING, &adapter->state)) @@ -1248,9 +1250,10 @@ static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector) new_itr = IXGBE_20K_ITR; break; case bulk_latency: - default: new_itr = IXGBE_12K_ITR; break; + default: + break; } if (new_itr != q_vector->itr) { diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 060dd39229747..b1de7afd41166 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2753,7 +2753,7 @@ static netdev_features_t jme_fix_features(struct net_device *netdev, netdev_features_t features) { if (netdev->mtu > 1900) - features &= ~(NETIF_F_ALL_TSO | NETIF_F_ALL_CSUM); + features &= ~(NETIF_F_ALL_TSO | NETIF_F_CSUM_MASK); return features; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 528c2544389b9..15b1f6bbd92de 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -110,9 +110,17 @@ #define MVNETA_CPU_MAP(cpu) (0x2540 + ((cpu) << 2)) #define MVNETA_CPU_RXQ_ACCESS_ALL_MASK 0x000000ff #define MVNETA_CPU_TXQ_ACCESS_ALL_MASK 0x0000ff00 +#define MVNETA_CPU_RXQ_ACCESS(rxq) BIT(rxq) +#define MVNETA_CPU_TXQ_ACCESS(txq) BIT(txq + 8) #define MVNETA_RXQ_TIME_COAL_REG(q) (0x2580 + ((q) << 2)) -/* Exception Interrupt Port/Queue Cause register */ +/* Exception Interrupt Port/Queue Cause register + * + * Their behavior depend of the mapping done using the PCPX2Q + * registers. For a given CPU if the bit associated to a queue is not + * set, then for the register a read from this CPU will always return + * 0 and a write won't do anything + */ #define MVNETA_INTR_NEW_CAUSE 0x25a0 #define MVNETA_INTR_NEW_MASK 0x25a4 @@ -254,6 +262,11 @@ #define MVNETA_TX_MTU_MAX 0x3ffff +/* The RSS lookup table actually has 256 entries but we do not use + * them yet + */ +#define MVNETA_RSS_LU_TABLE_SIZE 1 + /* TSO header size */ #define TSO_HEADER_SIZE 128 @@ -356,6 +369,7 @@ struct mvneta_port { struct mvneta_tx_queue *txqs; struct net_device *dev; struct notifier_block cpu_notifier; + int rxq_def; /* Core clock */ struct clk *clk; @@ -374,6 +388,8 @@ struct mvneta_port { unsigned int use_inband_status:1; u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)]; + + u32 indir[MVNETA_RSS_LU_TABLE_SIZE]; }; /* The mvneta_tx_desc and mvneta_rx_desc structures describe the @@ -499,6 +515,9 @@ struct mvneta_tx_queue { /* DMA address of TSO headers */ dma_addr_t tso_hdrs_phys; + + /* Affinity mask for CPUs*/ + cpumask_t affinity_mask; }; struct mvneta_rx_queue { @@ -819,7 +838,13 @@ static void mvneta_port_up(struct mvneta_port *pp) mvreg_write(pp, MVNETA_TXQ_CMD, q_map); /* Enable all initialized RXQs. */ - mvreg_write(pp, MVNETA_RXQ_CMD, BIT(rxq_def)); + for (queue = 0; queue < rxq_number; queue++) { + struct mvneta_rx_queue *rxq = &pp->rxqs[queue]; + + if (rxq->descs != NULL) + q_map |= (1 << queue); + } + mvreg_write(pp, MVNETA_RXQ_CMD, q_map); } /* Stop the Ethernet port activity */ @@ -1025,6 +1050,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp) int cpu; int queue; u32 val; + int max_cpu = num_present_cpus(); /* Clear all Cause registers */ mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0); @@ -1040,13 +1066,33 @@ static void mvneta_defaults_set(struct mvneta_port *pp) /* Enable MBUS Retry bit16 */ mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20); - /* Set CPU queue access map - all CPUs have access to all RX - * queues and to all TX queues + /* Set CPU queue access map. CPUs are assigned to the RX and + * TX queues modulo their number. If there is only one TX + * queue then it is assigned to the CPU associated to the + * default RX queue. */ - for_each_present_cpu(cpu) - mvreg_write(pp, MVNETA_CPU_MAP(cpu), - (MVNETA_CPU_RXQ_ACCESS_ALL_MASK | - MVNETA_CPU_TXQ_ACCESS_ALL_MASK)); + for_each_present_cpu(cpu) { + int rxq_map = 0, txq_map = 0; + int rxq, txq; + + for (rxq = 0; rxq < rxq_number; rxq++) + if ((rxq % max_cpu) == cpu) + rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq); + + for (txq = 0; txq < txq_number; txq++) + if ((txq % max_cpu) == cpu) + txq_map |= MVNETA_CPU_TXQ_ACCESS(txq); + + /* With only one TX queue we configure a special case + * which will allow to get all the irq on a single + * CPU + */ + if (txq_number == 1) + txq_map = (cpu == pp->rxq_def) ? + MVNETA_CPU_TXQ_ACCESS(1) : 0; + + mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map); + } /* Reset RX and TX DMAs */ mvreg_write(pp, MVNETA_PORT_RX_RESET, MVNETA_PORT_RX_DMA_RESET); @@ -1067,7 +1113,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp) mvreg_write(pp, MVNETA_ACC_MODE, val); /* Update val of portCfg register accordingly with all RxQueue types */ - val = MVNETA_PORT_CONFIG_DEFL_VALUE(rxq_def); + val = MVNETA_PORT_CONFIG_DEFL_VALUE(pp->rxq_def); mvreg_write(pp, MVNETA_PORT_CONFIG, val); val = 0; @@ -2101,19 +2147,19 @@ static void mvneta_set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { /* Accept all: Multicast + Unicast */ mvneta_rx_unicast_promisc_set(pp, 1); - mvneta_set_ucast_table(pp, rxq_def); - mvneta_set_special_mcast_table(pp, rxq_def); - mvneta_set_other_mcast_table(pp, rxq_def); + mvneta_set_ucast_table(pp, pp->rxq_def); + mvneta_set_special_mcast_table(pp, pp->rxq_def); + mvneta_set_other_mcast_table(pp, pp->rxq_def); } else { /* Accept single Unicast */ mvneta_rx_unicast_promisc_set(pp, 0); mvneta_set_ucast_table(pp, -1); - mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def); + mvneta_mac_addr_set(pp, dev->dev_addr, pp->rxq_def); if (dev->flags & IFF_ALLMULTI) { /* Accept all multicast */ - mvneta_set_special_mcast_table(pp, rxq_def); - mvneta_set_other_mcast_table(pp, rxq_def); + mvneta_set_special_mcast_table(pp, pp->rxq_def); + mvneta_set_other_mcast_table(pp, pp->rxq_def); } else { /* Accept only initialized multicast */ mvneta_set_special_mcast_table(pp, -1); @@ -2122,7 +2168,7 @@ static void mvneta_set_rx_mode(struct net_device *dev) if (!netdev_mc_empty(dev)) { netdev_for_each_mc_addr(ha, dev) { mvneta_mcast_addr_set(pp, ha->addr, - rxq_def); + pp->rxq_def); } } } @@ -2173,6 +2219,7 @@ static int mvneta_poll(struct napi_struct *napi, int budget) { int rx_done = 0; u32 cause_rx_tx; + int rx_queue; struct mvneta_port *pp = netdev_priv(napi->dev); struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports); @@ -2204,8 +2251,15 @@ static int mvneta_poll(struct napi_struct *napi, int budget) /* For the case where the last mvneta_poll did not process all * RX packets */ + rx_queue = fls(((cause_rx_tx >> 8) & 0xff)); + cause_rx_tx |= port->cause_rx_tx; - rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]); + + if (rx_queue) { + rx_queue = rx_queue - 1; + rx_done = mvneta_rx(pp, budget, &pp->rxqs[rx_queue]); + } + budget -= rx_done; if (budget > 0) { @@ -2322,6 +2376,8 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp, static int mvneta_txq_init(struct mvneta_port *pp, struct mvneta_tx_queue *txq) { + int cpu; + txq->size = pp->tx_ring_size; /* A queue must always have room for at least one skb. @@ -2374,6 +2430,14 @@ static int mvneta_txq_init(struct mvneta_port *pp, } mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal); + /* Setup XPS mapping */ + if (txq_number > 1) + cpu = txq->id % num_present_cpus(); + else + cpu = pp->rxq_def % num_present_cpus(); + cpumask_set_cpu(cpu, &txq->affinity_mask); + netif_set_xps_queue(pp->dev, &txq->affinity_mask, txq->id); + return 0; } @@ -2418,19 +2482,27 @@ static void mvneta_cleanup_txqs(struct mvneta_port *pp) /* Cleanup all Rx queues */ static void mvneta_cleanup_rxqs(struct mvneta_port *pp) { - mvneta_rxq_deinit(pp, &pp->rxqs[rxq_def]); + int queue; + + for (queue = 0; queue < txq_number; queue++) + mvneta_rxq_deinit(pp, &pp->rxqs[queue]); } /* Init all Rx queues */ static int mvneta_setup_rxqs(struct mvneta_port *pp) { - int err = mvneta_rxq_init(pp, &pp->rxqs[rxq_def]); - if (err) { - netdev_err(pp->dev, "%s: can't create rxq=%d\n", - __func__, rxq_def); - mvneta_cleanup_rxqs(pp); - return err; + int queue; + + for (queue = 0; queue < rxq_number; queue++) { + int err = mvneta_rxq_init(pp, &pp->rxqs[queue]); + + if (err) { + netdev_err(pp->dev, "%s: can't create rxq=%d\n", + __func__, queue); + mvneta_cleanup_rxqs(pp); + return err; + } } return 0; @@ -2454,6 +2526,31 @@ static int mvneta_setup_txqs(struct mvneta_port *pp) return 0; } +static void mvneta_percpu_unmask_interrupt(void *arg) +{ + struct mvneta_port *pp = arg; + + /* All the queue are unmasked, but actually only the ones + * maped to this CPU will be unmasked + */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, + MVNETA_RX_INTR_MASK_ALL | + MVNETA_TX_INTR_MASK_ALL | + MVNETA_MISCINTR_INTR_MASK); +} + +static void mvneta_percpu_mask_interrupt(void *arg) +{ + struct mvneta_port *pp = arg; + + /* All the queue are masked, but actually only the ones + * maped to this CPU will be masked + */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); + mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); +} + static void mvneta_start_dev(struct mvneta_port *pp) { unsigned int cpu; @@ -2471,11 +2568,10 @@ static void mvneta_start_dev(struct mvneta_port *pp) napi_enable(&port->napi); } - /* Unmask interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK(rxq_number) | - MVNETA_TX_INTR_MASK(txq_number) | - MVNETA_MISCINTR_INTR_MASK); + /* Unmask interrupts. It has to be done from each CPU */ + for_each_online_cpu(cpu) + smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt, + pp, true); mvreg_write(pp, MVNETA_INTR_MISC_MASK, MVNETA_CAUSE_PHY_STATUS_CHANGE | MVNETA_CAUSE_LINK_CHANGE | @@ -2634,7 +2730,7 @@ static int mvneta_set_mac_addr(struct net_device *dev, void *addr) mvneta_mac_addr_set(pp, dev->dev_addr, -1); /* Set new addr in hw */ - mvneta_mac_addr_set(pp, sockaddr->sa_data, rxq_def); + mvneta_mac_addr_set(pp, sockaddr->sa_data, pp->rxq_def); eth_commit_mac_addr_change(dev, addr); return 0; @@ -2751,22 +2847,45 @@ static void mvneta_percpu_disable(void *arg) static void mvneta_percpu_elect(struct mvneta_port *pp) { - int online_cpu_idx, cpu, i = 0; + int online_cpu_idx, max_cpu, cpu, i = 0; - online_cpu_idx = rxq_def % num_online_cpus(); + online_cpu_idx = pp->rxq_def % num_online_cpus(); + max_cpu = num_present_cpus(); for_each_online_cpu(cpu) { + int rxq_map = 0, txq_map = 0; + int rxq; + + for (rxq = 0; rxq < rxq_number; rxq++) + if ((rxq % max_cpu) == cpu) + rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq); + if (i == online_cpu_idx) - /* Enable per-CPU interrupt on the one CPU we - * just elected + /* Map the default receive queue queue to the + * elected CPU */ - smp_call_function_single(cpu, mvneta_percpu_enable, - pp, true); + rxq_map |= MVNETA_CPU_RXQ_ACCESS(pp->rxq_def); + + /* We update the TX queue map only if we have one + * queue. In this case we associate the TX queue to + * the CPU bound to the default RX queue + */ + if (txq_number == 1) + txq_map = (i == online_cpu_idx) ? + MVNETA_CPU_TXQ_ACCESS(1) : 0; else - /* Disable per-CPU interrupt on all the other CPU */ - smp_call_function_single(cpu, mvneta_percpu_disable, - pp, true); + txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) & + MVNETA_CPU_TXQ_ACCESS_ALL_MASK; + + mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map); + + /* Update the interrupt mask on each CPU according the + * new mapping + */ + smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt, + pp, true); i++; + } }; @@ -2801,12 +2920,22 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); napi_enable(&port->napi); + + /* Enable per-CPU interrupts on the CPU that is + * brought up. + */ + smp_call_function_single(cpu, mvneta_percpu_enable, + pp, true); + /* Enable per-CPU interrupt on the one CPU we care * about. */ mvneta_percpu_elect(pp); - /* Unmask all ethernet port interrupts */ + /* Unmask all ethernet port interrupts, as this + * notifier is called for each CPU then the CPU to + * Queue mapping is applied + */ mvreg_write(pp, MVNETA_INTR_NEW_MASK, MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number) | @@ -2857,7 +2986,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, static int mvneta_open(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); - int ret; + int ret, cpu; pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) + @@ -2887,8 +3016,13 @@ static int mvneta_open(struct net_device *dev) */ mvneta_percpu_disable(pp); - /* Elect a CPU to handle our RX queue interrupt */ - mvneta_percpu_elect(pp); + /* Enable per-CPU interrupt on all the CPU to handle our RX + * queue interrupts + */ + for_each_online_cpu(cpu) + smp_call_function_single(cpu, mvneta_percpu_enable, + pp, true); + /* Register a CPU notifier to handle the case where our CPU * might be taken offline. @@ -3150,6 +3284,106 @@ static int mvneta_ethtool_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } +static u32 mvneta_ethtool_get_rxfh_indir_size(struct net_device *dev) +{ + return MVNETA_RSS_LU_TABLE_SIZE; +} + +static int mvneta_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, + u32 *rules __always_unused) +{ + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = rxq_number; + return 0; + case ETHTOOL_GRXFH: + return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } +} + +static int mvneta_config_rss(struct mvneta_port *pp) +{ + int cpu; + u32 val; + + netif_tx_stop_all_queues(pp->dev); + + for_each_online_cpu(cpu) + smp_call_function_single(cpu, mvneta_percpu_mask_interrupt, + pp, true); + + /* We have to synchronise on the napi of each CPU */ + for_each_online_cpu(cpu) { + struct mvneta_pcpu_port *pcpu_port = + per_cpu_ptr(pp->ports, cpu); + + napi_synchronize(&pcpu_port->napi); + napi_disable(&pcpu_port->napi); + } + + pp->rxq_def = pp->indir[0]; + + /* Update unicast mapping */ + mvneta_set_rx_mode(pp->dev); + + /* Update val of portCfg register accordingly with all RxQueue types */ + val = MVNETA_PORT_CONFIG_DEFL_VALUE(pp->rxq_def); + mvreg_write(pp, MVNETA_PORT_CONFIG, val); + + /* Update the elected CPU matching the new rxq_def */ + mvneta_percpu_elect(pp); + + /* We have to synchronise on the napi of each CPU */ + for_each_online_cpu(cpu) { + struct mvneta_pcpu_port *pcpu_port = + per_cpu_ptr(pp->ports, cpu); + + napi_enable(&pcpu_port->napi); + } + + netif_tx_start_all_queues(pp->dev); + + return 0; +} + +static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct mvneta_port *pp = netdev_priv(dev); + /* We require at least one supported parameter to be changed + * and no change in any of the unsupported parameters + */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + + if (!indir) + return 0; + + memcpy(pp->indir, indir, MVNETA_RSS_LU_TABLE_SIZE); + + return mvneta_config_rss(pp); +} + +static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct mvneta_port *pp = netdev_priv(dev); + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + if (!indir) + return 0; + + memcpy(indir, pp->indir, MVNETA_RSS_LU_TABLE_SIZE); + + return 0; +} + static const struct net_device_ops mvneta_netdev_ops = { .ndo_open = mvneta_open, .ndo_stop = mvneta_stop, @@ -3174,6 +3408,10 @@ const struct ethtool_ops mvneta_eth_tool_ops = { .get_strings = mvneta_ethtool_get_strings, .get_ethtool_stats = mvneta_ethtool_get_stats, .get_sset_count = mvneta_ethtool_get_sset_count, + .get_rxfh_indir_size = mvneta_ethtool_get_rxfh_indir_size, + .get_rxnfc = mvneta_ethtool_get_rxnfc, + .get_rxfh = mvneta_ethtool_get_rxfh, + .set_rxfh = mvneta_ethtool_set_rxfh, }; /* Initialize hw */ @@ -3363,6 +3601,10 @@ static int mvneta_probe(struct platform_device *pdev) strcmp(managed, "in-band-status") == 0); pp->cpu_notifier.notifier_call = mvneta_percpu_notifier; + pp->rxq_def = rxq_def; + + pp->indir[0] = rxq_def; + pp->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pp->clk)) { err = PTR_ERR(pp->clk); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index d9884fd15b453..a4beccf1fd46e 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -3413,16 +3413,23 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv, } /* Free all buffers from the pool */ -static void mvpp2_bm_bufs_free(struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) +static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, + struct mvpp2_bm_pool *bm_pool) { int i; for (i = 0; i < bm_pool->buf_num; i++) { + dma_addr_t buf_phys_addr; u32 vaddr; /* Get buffer virtual address (indirect access) */ - mvpp2_read(priv, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); + buf_phys_addr = mvpp2_read(priv, + MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + + dma_unmap_single(dev, buf_phys_addr, + bm_pool->buf_size, DMA_FROM_DEVICE); + if (!vaddr) break; dev_kfree_skb_any((struct sk_buff *)vaddr); @@ -3439,7 +3446,7 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, { u32 val; - mvpp2_bm_bufs_free(priv, bm_pool); + mvpp2_bm_bufs_free(&pdev->dev, priv, bm_pool); if (bm_pool->buf_num) { WARN(1, "cannot free all buffers in pool %d\n", bm_pool->id); return 0; @@ -3692,7 +3699,8 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, MVPP2_BM_LONG_BUF_NUM : MVPP2_BM_SHORT_BUF_NUM; else - mvpp2_bm_bufs_free(port->priv, new_pool); + mvpp2_bm_bufs_free(port->dev->dev.parent, + port->priv, new_pool); new_pool->pkt_size = pkt_size; @@ -3756,7 +3764,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) int pkt_size = MVPP2_RX_PKT_SIZE(mtu); /* Update BM pool with new buffer size */ - mvpp2_bm_bufs_free(port->priv, port_pool); + mvpp2_bm_bufs_free(dev->dev.parent, port->priv, port_pool); if (port_pool->buf_num) { WARN(1, "cannot free all buffers in pool %d\n", port_pool->id); return -EIO; @@ -4401,11 +4409,10 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, mvpp2_txq_inc_get(txq_pcpu); - if (!skb) - continue; - dma_unmap_single(port->dev->dev.parent, buf_phys_addr, skb_headlen(skb), DMA_TO_DEVICE); + if (!skb) + continue; dev_kfree_skb_any(skb); } } @@ -5092,7 +5099,8 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct mvpp2_rx_queue *rxq) { struct net_device *dev = port->dev; - int rx_received, rx_filled, i; + int rx_received; + int rx_done = 0; u32 rcvd_pkts = 0; u32 rcvd_bytes = 0; @@ -5101,17 +5109,18 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, if (rx_todo > rx_received) rx_todo = rx_received; - rx_filled = 0; - for (i = 0; i < rx_todo; i++) { + while (rx_done < rx_todo) { struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq); struct mvpp2_bm_pool *bm_pool; struct sk_buff *skb; + dma_addr_t phys_addr; u32 bm, rx_status; int pool, rx_bytes, err; - rx_filled++; + rx_done++; rx_status = rx_desc->status; rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE; + phys_addr = rx_desc->buf_phys_addr; bm = mvpp2_bm_cookie_build(rx_desc); pool = mvpp2_bm_cookie_pool_get(bm); @@ -5128,8 +5137,10 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, * comprised by the RX descriptor. */ if (rx_status & MVPP2_RXD_ERR_SUMMARY) { + err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); + /* Return the buffer to the pool */ mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr, rx_desc->buf_cookie); continue; @@ -5137,6 +5148,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, skb = (struct sk_buff *)rx_desc->buf_cookie; + err = mvpp2_rx_refill(port, bm_pool, bm, 0); + if (err) { + netdev_err(port->dev, "failed to refill BM pools\n"); + goto err_drop_frame; + } + + dma_unmap_single(dev->dev.parent, phys_addr, + bm_pool->buf_size, DMA_FROM_DEVICE); + rcvd_pkts++; rcvd_bytes += rx_bytes; atomic_inc(&bm_pool->in_use); @@ -5147,12 +5167,6 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, mvpp2_rx_csum(port, rx_status, skb); napi_gro_receive(&port->napi, skb); - - err = mvpp2_rx_refill(port, bm_pool, bm, 0); - if (err) { - netdev_err(port->dev, "failed to refill BM pools\n"); - rx_filled--; - } } if (rcvd_pkts) { @@ -5166,7 +5180,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, /* Update Rx queue management counters */ wmb(); - mvpp2_rxq_status_update(port, rxq->id, rx_todo, rx_filled); + mvpp2_rxq_status_update(port, rxq->id, rx_done, rx_done); return rx_todo; } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 5606a043063e3..ec0a22119e09e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4380,7 +4380,7 @@ static netdev_features_t sky2_fix_features(struct net_device *dev, */ if (dev->mtu > ETH_DATA_LEN && hw->chip_id == CHIP_ID_YUKON_EC_U) { netdev_info(dev, "checksum offload not possible with jumbo frames\n"); - features &= ~(NETIF_F_TSO|NETIF_F_SG|NETIF_F_ALL_CSUM); + features &= ~(NETIF_F_TSO | NETIF_F_SG | NETIF_F_CSUM_MASK); } /* Some hardware requires receive checksum for RSS to work. */ diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 2177e56ed0be7..d48d5793407d9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1010,7 +1010,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, if (!(smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED && smp->method == IB_MGMT_METHOD_GET) || network_view) { mlx4_err(dev, "Unprivileged slave %d is trying to execute a Subnet MGMT MAD, class 0x%x, method 0x%x, view=%s for attr 0x%x. Rejecting\n", - slave, smp->method, smp->mgmt_class, + slave, smp->mgmt_class, smp->method, network_view ? "Network" : "Host", be16_to_cpu(smp->attr_id)); return -EPERM; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 8a083d73efdba..038f9ce391e62 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -242,6 +242,13 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) unsigned long flags; u64 ns, zero = 0; + /* mlx4_en_init_timestamp is called for each netdev. + * mdev->ptp_clock is common for all ports, skip initialization if + * was done for other port. + */ + if (mdev->ptp_clock) + return; + rwlock_init(&mdev->clock_lock); memset(&mdev->cycles, 0, sizeof(mdev->cycles)); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 005f910ec955e..e0ec280a7fa13 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -232,9 +232,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) if (mdev->pndev[i]) mlx4_en_destroy_netdev(mdev->pndev[i]); - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - mlx4_en_remove_timestamp(mdev); - flush_workqueue(mdev->workqueue); destroy_workqueue(mdev->workqueue); (void) mlx4_mr_free(dev, &mdev->mr); @@ -320,10 +317,6 @@ static void *mlx4_en_add(struct mlx4_dev *dev) mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) mdev->port_cnt++; - /* Initialize time stamp mechanism */ - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - mlx4_en_init_timestamp(mdev); - /* Set default number of RX rings*/ mlx4_en_set_num_rx_rings(mdev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 659209ff7af67..0c7e3f69a73bb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2035,6 +2035,9 @@ void mlx4_en_destroy_netdev(struct net_device *dev) /* flush any pending task for this netdev */ flush_workqueue(mdev->workqueue); + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + mlx4_en_remove_timestamp(mdev); + /* Detach the netdev so tasks would not attempt to access it */ mutex_lock(&mdev->state_lock); mdev->pndev[priv->port] = NULL; @@ -3018,9 +3021,12 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY); + /* Initialize time stamp mechanism */ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - queue_delayed_work(mdev->workqueue, &priv->service_task, - SERVICE_TASK_DELAY); + mlx4_en_init_timestamp(mdev); + + queue_delayed_work(mdev->workqueue, &priv->service_task, + SERVICE_TASK_DELAY); mlx4_en_set_stats_bitmap(mdev->dev, &priv->stats_bitmap, mdev->profile.prof[priv->port].rx_ppp, diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index da7f578a3fe13..b46dbe29ef6c8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4331,9 +4331,10 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, return -EOPNOTSUPP; ctrl = (struct mlx4_net_trans_rule_hw_ctrl *)inbox->buf; - ctrl->port = mlx4_slave_convert_port(dev, slave, ctrl->port); - if (ctrl->port <= 0) + err = mlx4_slave_convert_port(dev, slave, ctrl->port); + if (err <= 0) return -EINVAL; + ctrl->port = err; qpn = be32_to_cpu(ctrl->qpn) & 0xffffff; err = get_res(dev, slave, qpn, RES_QP, &rqp); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 158c88c69ef91..c503ea05e7427 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -13,6 +13,7 @@ config MLX5_CORE config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE + select PTP_1588_CLOCK default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index a0755919ccaf0..01c0256effb8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ - mad.o transobj.o vport.o sriov.o -mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o flow_table.o eswitch.o \ - en_main.o en_flow_table.o en_ethtool.o en_tx.o en_rx.o \ - en_txrx.o + mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o +mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \ + en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \ + en_txrx.o en_clock.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 89313d46952de..9ea49a8933231 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -32,6 +32,9 @@ #include <linux/if_vlan.h> #include <linux/etherdevice.h> +#include <linux/timecounter.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/qp.h> #include <linux/mlx5/cq.h> @@ -64,6 +67,8 @@ #define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */ #define MLX5E_SQ_BF_BUDGET 16 +#define MLX5E_NUM_MAIN_GROUPS 9 + static const char vport_strings[][ETH_GSTRING_LEN] = { /* vport statistics */ "rx_packets", @@ -282,6 +287,19 @@ struct mlx5e_params { u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE]; }; +struct mlx5e_tstamp { + rwlock_t lock; + struct cyclecounter cycles; + struct timecounter clock; + struct hwtstamp_config hwtstamp_config; + u32 nominal_c_mult; + unsigned long overflow_period; + struct delayed_work overflow_work; + struct mlx5_core_dev *mdev; + struct ptp_clock *ptp; + struct ptp_clock_info ptp_info; +}; + enum { MLX5E_RQ_STATE_POST_WQES_ENABLE, }; @@ -313,6 +331,7 @@ struct mlx5e_rq { struct device *pdev; struct net_device *netdev; + struct mlx5e_tstamp *tstamp; struct mlx5e_rq_stats stats; struct mlx5e_cq cq; @@ -326,14 +345,12 @@ struct mlx5e_rq { struct mlx5e_priv *priv; } ____cacheline_aligned_in_smp; -struct mlx5e_tx_skb_cb { +struct mlx5e_tx_wqe_info { u32 num_bytes; u8 num_wqebbs; u8 num_dma; }; -#define MLX5E_TX_SKB_CB(__skb) ((struct mlx5e_tx_skb_cb *)__skb->cb) - enum mlx5e_dma_map_type { MLX5E_DMA_MAP_SINGLE, MLX5E_DMA_MAP_PAGE @@ -369,6 +386,7 @@ struct mlx5e_sq { /* pointers to per packet info: write@xmit, read@completion */ struct sk_buff **skb; struct mlx5e_sq_dma *dma_fifo; + struct mlx5e_tx_wqe_info *wqe_info; /* read only */ struct mlx5_wq_cyc wq; @@ -381,6 +399,7 @@ struct mlx5e_sq { u16 max_inline; u16 edge; struct device *pdev; + struct mlx5e_tstamp *tstamp; __be32 mkey_be; unsigned long state; @@ -442,7 +461,7 @@ enum mlx5e_rqt_ix { struct mlx5e_eth_addr_info { u8 addr[ETH_ALEN + 2]; u32 tt_vec; - u32 ft_ix[MLX5E_NUM_TT]; /* flow table index per traffic type */ + struct mlx5_flow_rule *ft_rule[MLX5E_NUM_TT]; }; #define MLX5E_ETH_ADDR_HASH_SIZE (1 << BITS_PER_BYTE) @@ -466,15 +485,22 @@ enum { struct mlx5e_vlan_db { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - u32 active_vlans_ft_ix[VLAN_N_VID]; - u32 untagged_rule_ft_ix; - u32 any_vlan_rule_ft_ix; + struct mlx5_flow_rule *active_vlans_rule[VLAN_N_VID]; + struct mlx5_flow_rule *untagged_rule; + struct mlx5_flow_rule *any_vlan_rule; bool filter_disabled; }; struct mlx5e_flow_table { - void *vlan; - void *main; + int num_groups; + struct mlx5_flow_table *t; + struct mlx5_flow_group **g; +}; + +struct mlx5e_flow_tables { + struct mlx5_flow_namespace *ns; + struct mlx5e_flow_table vlan; + struct mlx5e_flow_table main; }; struct mlx5e_priv { @@ -497,7 +523,7 @@ struct mlx5e_priv { u32 rqtn[MLX5E_NUM_RQT]; u32 tirn[MLX5E_NUM_TT]; - struct mlx5e_flow_table ft; + struct mlx5e_flow_tables fts; struct mlx5e_eth_addr_db eth_addr; struct mlx5e_vlan_db vlan; @@ -510,6 +536,7 @@ struct mlx5e_priv { struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_stats stats; + struct mlx5e_tstamp tstamp; }; #define MLX5E_NET_IP_ALIGN 2 @@ -576,6 +603,13 @@ void mlx5e_destroy_flow_tables(struct mlx5e_priv *priv); void mlx5e_init_eth_addr(struct mlx5e_priv *priv); void mlx5e_set_rx_mode_work(struct work_struct *work); +void mlx5e_fill_hwstamp(struct mlx5e_tstamp *clock, u64 timestamp, + struct skb_shared_hwtstamps *hwts); +void mlx5e_timestamp_init(struct mlx5e_priv *priv); +void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv); +int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr); +int mlx5e_hwstamp_get(struct net_device *dev, struct ifreq *ifr); + int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c new file mode 100644 index 0000000000000..be6543570b2be --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -0,0 +1,287 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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 AUTHORS OR COPYRIGHT HOLDERS + * 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. + */ + +#include <linux/clocksource.h> +#include "en.h" + +enum { + MLX5E_CYCLES_SHIFT = 23 +}; + +void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp, + struct skb_shared_hwtstamps *hwts) +{ + u64 nsec; + + read_lock(&tstamp->lock); + nsec = timecounter_cyc2time(&tstamp->clock, timestamp); + read_unlock(&tstamp->lock); + + hwts->hwtstamp = ns_to_ktime(nsec); +} + +static cycle_t mlx5e_read_internal_timer(const struct cyclecounter *cc) +{ + struct mlx5e_tstamp *tstamp = container_of(cc, struct mlx5e_tstamp, + cycles); + + return mlx5_read_internal_timer(tstamp->mdev) & cc->mask; +} + +static void mlx5e_timestamp_overflow(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, + overflow_work); + + write_lock(&tstamp->lock); + timecounter_read(&tstamp->clock); + write_unlock(&tstamp->lock); + schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period); +} + +int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct hwtstamp_config config; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* TX HW timestamp */ + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + /* RX HW timestamp */ + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + memcpy(&priv->tstamp.hwtstamp_config, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +int mlx5e_hwstamp_get(struct net_device *dev, struct ifreq *ifr) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct hwtstamp_config *cfg = &priv->tstamp.hwtstamp_config; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; +} + +static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, + ptp_info); + u64 ns = timespec64_to_ns(ts); + + write_lock(&tstamp->lock); + timecounter_init(&tstamp->clock, &tstamp->cycles, ns); + write_unlock(&tstamp->lock); + + return 0; +} + +static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, + ptp_info); + u64 ns; + + write_lock(&tstamp->lock); + ns = timecounter_read(&tstamp->clock); + write_unlock(&tstamp->lock); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, + ptp_info); + + write_lock(&tstamp->lock); + timecounter_adjtime(&tstamp->clock, delta); + write_unlock(&tstamp->lock); + + return 0; +} + +static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) +{ + u64 adj; + u32 diff; + int neg_adj = 0; + struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, + ptp_info); + + if (delta < 0) { + neg_adj = 1; + delta = -delta; + } + + adj = tstamp->nominal_c_mult; + adj *= delta; + diff = div_u64(adj, 1000000000ULL); + + write_lock(&tstamp->lock); + timecounter_read(&tstamp->clock); + tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : + tstamp->nominal_c_mult + diff; + write_unlock(&tstamp->lock); + + return 0; +} + +static const struct ptp_clock_info mlx5e_ptp_clock_info = { + .owner = THIS_MODULE, + .max_adj = 100000000, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 0, + .adjfreq = mlx5e_ptp_adjfreq, + .adjtime = mlx5e_ptp_adjtime, + .gettime64 = mlx5e_ptp_gettime, + .settime64 = mlx5e_ptp_settime, + .enable = NULL, +}; + +static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp) +{ + tstamp->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; + tstamp->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; +} + +void mlx5e_timestamp_init(struct mlx5e_priv *priv) +{ + struct mlx5e_tstamp *tstamp = &priv->tstamp; + u64 ns; + u64 frac = 0; + u32 dev_freq; + + mlx5e_timestamp_init_config(tstamp); + dev_freq = MLX5_CAP_GEN(priv->mdev, device_frequency_khz); + if (!dev_freq) { + mlx5_core_warn(priv->mdev, "invalid device_frequency_khz, aborting HW clock init\n"); + return; + } + rwlock_init(&tstamp->lock); + tstamp->cycles.read = mlx5e_read_internal_timer; + tstamp->cycles.shift = MLX5E_CYCLES_SHIFT; + tstamp->cycles.mult = clocksource_khz2mult(dev_freq, + tstamp->cycles.shift); + tstamp->nominal_c_mult = tstamp->cycles.mult; + tstamp->cycles.mask = CLOCKSOURCE_MASK(41); + tstamp->mdev = priv->mdev; + + timecounter_init(&tstamp->clock, &tstamp->cycles, + ktime_to_ns(ktime_get_real())); + + /* Calculate period in seconds to call the overflow watchdog - to make + * sure counter is checked at least once every wrap around. + */ + ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask, + frac, &frac); + do_div(ns, NSEC_PER_SEC / 2 / HZ); + tstamp->overflow_period = ns; + + INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); + if (tstamp->overflow_period) + schedule_delayed_work(&tstamp->overflow_work, 0); + else + mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n"); + + /* Configure the PHC */ + tstamp->ptp_info = mlx5e_ptp_clock_info; + snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp"); + + tstamp->ptp = ptp_clock_register(&tstamp->ptp_info, + &priv->mdev->pdev->dev); + if (IS_ERR_OR_NULL(tstamp->ptp)) { + mlx5_core_warn(priv->mdev, "ptp_clock_register failed %ld\n", + PTR_ERR(tstamp->ptp)); + tstamp->ptp = NULL; + } +} + +void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_tstamp *tstamp = &priv->tstamp; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return; + + if (priv->tstamp.ptp) { + ptp_clock_unregister(priv->tstamp.ptp); + priv->tstamp.ptp = NULL; + } + + cancel_delayed_work_sync(&tstamp->overflow_work); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 2e022e9009393..65624ac65b4c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -855,6 +855,35 @@ static int mlx5e_set_pauseparam(struct net_device *netdev, return err; } +static int mlx5e_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int ret; + + ret = ethtool_op_get_ts_info(dev, info); + if (ret) + return ret; + + info->phc_index = priv->tstamp.ptp ? + ptp_clock_index(priv->tstamp.ptp) : -1; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return 0; + + info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->tx_types = (BIT(1) << HWTSTAMP_TX_OFF) | + (BIT(1) << HWTSTAMP_TX_ON); + + info->rx_filters = (BIT(1) << HWTSTAMP_FILTER_NONE) | + (BIT(1) << HWTSTAMP_FILTER_ALL); + + return 0; +} + const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, .get_link = ethtool_op_get_link, @@ -878,4 +907,5 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .set_tunable = mlx5e_set_tunable, .get_pauseparam = mlx5e_get_pauseparam, .set_pauseparam = mlx5e_set_pauseparam, + .get_ts_info = mlx5e_get_ts_info, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 5b93c9c6e341d..80d81abc4820d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -34,9 +34,11 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> -#include <linux/mlx5/flow_table.h> +#include <linux/mlx5/fs.h> #include "en.h" +#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) + enum { MLX5E_FULLMATCH = 0, MLX5E_ALLMULTI = 1, @@ -103,44 +105,38 @@ static void mlx5e_del_eth_addr_from_hash(struct mlx5e_eth_addr_hash_node *hn) static void mlx5e_del_eth_addr_from_flow_table(struct mlx5e_priv *priv, struct mlx5e_eth_addr_info *ai) { - void *ft = priv->ft.main; - if (ai->tt_vec & BIT(MLX5E_TT_IPV6_IPSEC_ESP)) - mlx5_del_flow_table_entry(ft, - ai->ft_ix[MLX5E_TT_IPV6_IPSEC_ESP]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV6_IPSEC_ESP]); if (ai->tt_vec & BIT(MLX5E_TT_IPV4_IPSEC_ESP)) - mlx5_del_flow_table_entry(ft, - ai->ft_ix[MLX5E_TT_IPV4_IPSEC_ESP]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV4_IPSEC_ESP]); if (ai->tt_vec & BIT(MLX5E_TT_IPV6_IPSEC_AH)) - mlx5_del_flow_table_entry(ft, - ai->ft_ix[MLX5E_TT_IPV6_IPSEC_AH]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV6_IPSEC_AH]); if (ai->tt_vec & BIT(MLX5E_TT_IPV4_IPSEC_AH)) - mlx5_del_flow_table_entry(ft, - ai->ft_ix[MLX5E_TT_IPV4_IPSEC_AH]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV4_IPSEC_AH]); if (ai->tt_vec & BIT(MLX5E_TT_IPV6_TCP)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6_TCP]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV6_TCP]); if (ai->tt_vec & BIT(MLX5E_TT_IPV4_TCP)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4_TCP]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV4_TCP]); if (ai->tt_vec & BIT(MLX5E_TT_IPV6_UDP)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6_UDP]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV6_UDP]); if (ai->tt_vec & BIT(MLX5E_TT_IPV4_UDP)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4_UDP]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV4_UDP]); if (ai->tt_vec & BIT(MLX5E_TT_IPV6)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV6]); if (ai->tt_vec & BIT(MLX5E_TT_IPV4)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_IPV4]); if (ai->tt_vec & BIT(MLX5E_TT_ANY)) - mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_ANY]); + mlx5_del_flow_rule(ai->ft_rule[MLX5E_TT_ANY]); } static int mlx5e_get_eth_addr_type(u8 *addr) @@ -240,44 +236,34 @@ static u32 mlx5e_get_tt_vec(struct mlx5e_eth_addr_info *ai, int type) } static int __mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv, - struct mlx5e_eth_addr_info *ai, int type, - void *flow_context, void *match_criteria) + struct mlx5e_eth_addr_info *ai, + int type, u32 *mc, u32 *mv) { + struct mlx5_flow_destination dest; u8 match_criteria_enable = 0; - void *match_value; - void *dest; - u8 *dmac; - u8 *match_criteria_dmac; - void *ft = priv->ft.main; - u32 *tirn = priv->tirn; - u32 *ft_ix; - u32 tt_vec; - int err; - - match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value); - dmac = MLX5_ADDR_OF(fte_match_param, match_value, - outer_headers.dmac_47_16); - match_criteria_dmac = MLX5_ADDR_OF(fte_match_param, match_criteria, - outer_headers.dmac_47_16); - dest = MLX5_ADDR_OF(flow_context, flow_context, destination); - - MLX5_SET(flow_context, flow_context, action, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); - MLX5_SET(flow_context, flow_context, destination_list_size, 1); - MLX5_SET(dest_format_struct, dest, destination_type, - MLX5_FLOW_CONTEXT_DEST_TYPE_TIR); + struct mlx5_flow_rule **rule_p; + struct mlx5_flow_table *ft = priv->fts.main.t; + u8 *mc_dmac = MLX5_ADDR_OF(fte_match_param, mc, + outer_headers.dmac_47_16); + u8 *mv_dmac = MLX5_ADDR_OF(fte_match_param, mv, + outer_headers.dmac_47_16); + u32 *tirn = priv->tirn; + u32 tt_vec; + int err = 0; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; switch (type) { case MLX5E_FULLMATCH: match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - memset(match_criteria_dmac, 0xff, ETH_ALEN); - ether_addr_copy(dmac, ai->addr); + eth_broadcast_addr(mc_dmac); + ether_addr_copy(mv_dmac, ai->addr); break; case MLX5E_ALLMULTI: match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - match_criteria_dmac[0] = 0x01; - dmac[0] = 0x01; + mc_dmac[0] = 0x01; + mv_dmac[0] = 0x01; break; case MLX5E_PROMISC: @@ -286,190 +272,165 @@ static int __mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv, tt_vec = mlx5e_get_tt_vec(ai, type); - ft_ix = &ai->ft_ix[MLX5E_TT_ANY]; if (tt_vec & BIT(MLX5E_TT_ANY)) { - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_ANY]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + rule_p = &ai->ft_rule[MLX5E_TT_ANY]; + dest.tir_num = tirn[MLX5E_TT_ANY]; + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_ANY); } match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); - ft_ix = &ai->ft_ix[MLX5E_TT_IPV4]; if (tt_vec & BIT(MLX5E_TT_IPV4)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV4]; + dest.tir_num = tirn[MLX5E_TT_IPV4]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IP); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV4]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV4); } - ft_ix = &ai->ft_ix[MLX5E_TT_IPV6]; if (tt_vec & BIT(MLX5E_TT_IPV6)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV6]; + dest.tir_num = tirn[MLX5E_TT_IPV6]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IPV6); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV6]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV6); } - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - outer_headers.ip_protocol); - MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, - IPPROTO_UDP); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); + MLX5_SET(fte_match_param, mv, outer_headers.ip_protocol, IPPROTO_UDP); - ft_ix = &ai->ft_ix[MLX5E_TT_IPV4_UDP]; if (tt_vec & BIT(MLX5E_TT_IPV4_UDP)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV4_UDP]; + dest.tir_num = tirn[MLX5E_TT_IPV4_UDP]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IP); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV4_UDP]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV4_UDP); } - ft_ix = &ai->ft_ix[MLX5E_TT_IPV6_UDP]; if (tt_vec & BIT(MLX5E_TT_IPV6_UDP)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV6_UDP]; + dest.tir_num = tirn[MLX5E_TT_IPV6_UDP]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IPV6); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV6_UDP]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV6_UDP); } - MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, - IPPROTO_TCP); + MLX5_SET(fte_match_param, mv, outer_headers.ip_protocol, IPPROTO_TCP); - ft_ix = &ai->ft_ix[MLX5E_TT_IPV4_TCP]; if (tt_vec & BIT(MLX5E_TT_IPV4_TCP)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV4_TCP]; + dest.tir_num = tirn[MLX5E_TT_IPV4_TCP]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IP); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV4_TCP]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV4_TCP); } - ft_ix = &ai->ft_ix[MLX5E_TT_IPV6_TCP]; if (tt_vec & BIT(MLX5E_TT_IPV6_TCP)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV6_TCP]; + dest.tir_num = tirn[MLX5E_TT_IPV6_TCP]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IPV6); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV6_TCP]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; ai->tt_vec |= BIT(MLX5E_TT_IPV6_TCP); } - MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, - IPPROTO_AH); + MLX5_SET(fte_match_param, mv, outer_headers.ip_protocol, IPPROTO_AH); - ft_ix = &ai->ft_ix[MLX5E_TT_IPV4_IPSEC_AH]; if (tt_vec & BIT(MLX5E_TT_IPV4_IPSEC_AH)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV4_IPSEC_AH]; + dest.tir_num = tirn[MLX5E_TT_IPV4_IPSEC_AH]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IP); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV4_IPSEC_AH]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV4_IPSEC_AH); } - ft_ix = &ai->ft_ix[MLX5E_TT_IPV6_IPSEC_AH]; if (tt_vec & BIT(MLX5E_TT_IPV6_IPSEC_AH)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV6_IPSEC_AH]; + dest.tir_num = tirn[MLX5E_TT_IPV6_IPSEC_AH]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IPV6); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV6_IPSEC_AH]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV6_IPSEC_AH); } - MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, - IPPROTO_ESP); + MLX5_SET(fte_match_param, mv, outer_headers.ip_protocol, IPPROTO_ESP); - ft_ix = &ai->ft_ix[MLX5E_TT_IPV4_IPSEC_ESP]; if (tt_vec & BIT(MLX5E_TT_IPV4_IPSEC_ESP)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV4_IPSEC_ESP]; + dest.tir_num = tirn[MLX5E_TT_IPV4_IPSEC_ESP]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IP); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV4_IPSEC_ESP]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV4_IPSEC_ESP); } - ft_ix = &ai->ft_ix[MLX5E_TT_IPV6_IPSEC_ESP]; if (tt_vec & BIT(MLX5E_TT_IPV6_IPSEC_ESP)) { - MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + rule_p = &ai->ft_rule[MLX5E_TT_IPV6_IPSEC_ESP]; + dest.tir_num = tirn[MLX5E_TT_IPV6_IPSEC_ESP]; + MLX5_SET(fte_match_param, mv, outer_headers.ethertype, ETH_P_IPV6); - MLX5_SET(dest_format_struct, dest, destination_id, - tirn[MLX5E_TT_IPV6_IPSEC_ESP]); - err = mlx5_add_flow_table_entry(ft, match_criteria_enable, - match_criteria, flow_context, - ft_ix); - if (err) + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, &dest); + if (IS_ERR_OR_NULL(*rule_p)) goto err_del_ai; - ai->tt_vec |= BIT(MLX5E_TT_IPV6_IPSEC_ESP); } return 0; err_del_ai: + err = PTR_ERR(*rule_p); + *rule_p = NULL; mlx5e_del_eth_addr_from_flow_table(priv, ai); return err; @@ -478,27 +439,25 @@ err_del_ai: static int mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv, struct mlx5e_eth_addr_info *ai, int type) { - u32 *flow_context; u32 *match_criteria; - int err; + u32 *match_value; + int err = 0; - flow_context = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) + - MLX5_ST_SZ_BYTES(dest_format_struct)); - match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); - if (!flow_context || !match_criteria) { + match_value = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); + match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); + if (!match_value || !match_criteria) { netdev_err(priv->netdev, "%s: alloc failed\n", __func__); err = -ENOMEM; goto add_eth_addr_rule_out; } - err = __mlx5e_add_eth_addr_rule(priv, ai, type, flow_context, - match_criteria); - if (err) - netdev_err(priv->netdev, "%s: failed\n", __func__); + err = __mlx5e_add_eth_addr_rule(priv, ai, type, match_criteria, + match_value); add_eth_addr_rule_out: kvfree(match_criteria); - kvfree(flow_context); + kvfree(match_value); + return err; } @@ -551,72 +510,77 @@ enum mlx5e_vlan_rule_type { MLX5E_VLAN_RULE_TYPE_MATCH_VID, }; -static int mlx5e_add_vlan_rule(struct mlx5e_priv *priv, - enum mlx5e_vlan_rule_type rule_type, u16 vid) +static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv, + enum mlx5e_vlan_rule_type rule_type, + u16 vid, u32 *mc, u32 *mv) { + struct mlx5_flow_table *ft = priv->fts.vlan.t; + struct mlx5_flow_destination dest; u8 match_criteria_enable = 0; - u32 *flow_context; - void *match_value; - void *dest; - u32 *match_criteria; - u32 *ft_ix; - int err; + struct mlx5_flow_rule **rule_p; + int err = 0; - flow_context = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) + - MLX5_ST_SZ_BYTES(dest_format_struct)); - match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); - if (!flow_context || !match_criteria) { - netdev_err(priv->netdev, "%s: alloc failed\n", __func__); - err = -ENOMEM; - goto add_vlan_rule_out; - } - match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value); - dest = MLX5_ADDR_OF(flow_context, flow_context, destination); - - MLX5_SET(flow_context, flow_context, action, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); - MLX5_SET(flow_context, flow_context, destination_list_size, 1); - MLX5_SET(dest_format_struct, dest, destination_type, - MLX5_FLOW_CONTEXT_DEST_TYPE_FLOW_TABLE); - MLX5_SET(dest_format_struct, dest, destination_id, - mlx5_get_flow_table_id(priv->ft.main)); + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = priv->fts.main.t; match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - outer_headers.vlan_tag); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.vlan_tag); switch (rule_type) { case MLX5E_VLAN_RULE_TYPE_UNTAGGED: - ft_ix = &priv->vlan.untagged_rule_ft_ix; + rule_p = &priv->vlan.untagged_rule; break; case MLX5E_VLAN_RULE_TYPE_ANY_VID: - ft_ix = &priv->vlan.any_vlan_rule_ft_ix; - MLX5_SET(fte_match_param, match_value, outer_headers.vlan_tag, - 1); + rule_p = &priv->vlan.any_vlan_rule; + MLX5_SET(fte_match_param, mv, outer_headers.vlan_tag, 1); break; default: /* MLX5E_VLAN_RULE_TYPE_MATCH_VID */ - err = mlx5e_vport_context_update_vlans(priv); - if (err) - goto add_vlan_rule_out; - - ft_ix = &priv->vlan.active_vlans_ft_ix[vid]; - MLX5_SET(fte_match_param, match_value, outer_headers.vlan_tag, - 1); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - outer_headers.first_vid); - MLX5_SET(fte_match_param, match_value, outer_headers.first_vid, - vid); + rule_p = &priv->vlan.active_vlans_rule[vid]; + MLX5_SET(fte_match_param, mv, outer_headers.vlan_tag, 1); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.first_vid); + MLX5_SET(fte_match_param, mv, outer_headers.first_vid, vid); break; } - err = mlx5_add_flow_table_entry(priv->ft.vlan, match_criteria_enable, - match_criteria, flow_context, ft_ix); - if (err) - netdev_err(priv->netdev, "%s: failed\n", __func__); + *rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + MLX5_FS_DEFAULT_FLOW_TAG, + &dest); + + if (IS_ERR(*rule_p)) { + err = PTR_ERR(*rule_p); + *rule_p = NULL; + netdev_err(priv->netdev, "%s: add rule failed\n", __func__); + } + + return err; +} + +static int mlx5e_add_vlan_rule(struct mlx5e_priv *priv, + enum mlx5e_vlan_rule_type rule_type, u16 vid) +{ + u32 *match_criteria; + u32 *match_value; + int err = 0; + + match_value = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); + match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); + if (!match_value || !match_criteria) { + netdev_err(priv->netdev, "%s: alloc failed\n", __func__); + err = -ENOMEM; + goto add_vlan_rule_out; + } + + if (rule_type == MLX5E_VLAN_RULE_TYPE_MATCH_VID) + mlx5e_vport_context_update_vlans(priv); + + err = __mlx5e_add_vlan_rule(priv, rule_type, vid, match_criteria, + match_value); add_vlan_rule_out: kvfree(match_criteria); - kvfree(flow_context); + kvfree(match_value); + return err; } @@ -625,16 +589,23 @@ static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv, { switch (rule_type) { case MLX5E_VLAN_RULE_TYPE_UNTAGGED: - mlx5_del_flow_table_entry(priv->ft.vlan, - priv->vlan.untagged_rule_ft_ix); + if (priv->vlan.untagged_rule) { + mlx5_del_flow_rule(priv->vlan.untagged_rule); + priv->vlan.untagged_rule = NULL; + } break; case MLX5E_VLAN_RULE_TYPE_ANY_VID: - mlx5_del_flow_table_entry(priv->ft.vlan, - priv->vlan.any_vlan_rule_ft_ix); + if (priv->vlan.any_vlan_rule) { + mlx5_del_flow_rule(priv->vlan.any_vlan_rule); + priv->vlan.any_vlan_rule = NULL; + } break; case MLX5E_VLAN_RULE_TYPE_MATCH_VID: - mlx5_del_flow_table_entry(priv->ft.vlan, - priv->vlan.active_vlans_ft_ix[vid]); + mlx5e_vport_context_update_vlans(priv); + if (priv->vlan.active_vlans_rule[vid]) { + mlx5_del_flow_rule(priv->vlan.active_vlans_rule[vid]); + priv->vlan.active_vlans_rule[vid] = NULL; + } mlx5e_vport_context_update_vlans(priv); break; } @@ -889,151 +860,358 @@ void mlx5e_set_rx_mode_work(struct work_struct *work) mlx5e_vport_context_update(priv); } +static void mlx5e_destroy_groups(struct mlx5e_flow_table *ft) +{ + int i; + + for (i = ft->num_groups - 1; i >= 0; i--) { + if (!IS_ERR_OR_NULL(ft->g[i])) + mlx5_destroy_flow_group(ft->g[i]); + ft->g[i] = NULL; + } + ft->num_groups = 0; +} + void mlx5e_init_eth_addr(struct mlx5e_priv *priv) { ether_addr_copy(priv->eth_addr.broadcast.addr, priv->netdev->broadcast); } -static int mlx5e_create_main_flow_table(struct mlx5e_priv *priv) +#define MLX5E_MAIN_GROUP0_SIZE BIT(3) +#define MLX5E_MAIN_GROUP1_SIZE BIT(1) +#define MLX5E_MAIN_GROUP2_SIZE BIT(0) +#define MLX5E_MAIN_GROUP3_SIZE BIT(14) +#define MLX5E_MAIN_GROUP4_SIZE BIT(13) +#define MLX5E_MAIN_GROUP5_SIZE BIT(11) +#define MLX5E_MAIN_GROUP6_SIZE BIT(2) +#define MLX5E_MAIN_GROUP7_SIZE BIT(1) +#define MLX5E_MAIN_GROUP8_SIZE BIT(0) +#define MLX5E_MAIN_TABLE_SIZE (MLX5E_MAIN_GROUP0_SIZE +\ + MLX5E_MAIN_GROUP1_SIZE +\ + MLX5E_MAIN_GROUP2_SIZE +\ + MLX5E_MAIN_GROUP3_SIZE +\ + MLX5E_MAIN_GROUP4_SIZE +\ + MLX5E_MAIN_GROUP5_SIZE +\ + MLX5E_MAIN_GROUP6_SIZE +\ + MLX5E_MAIN_GROUP7_SIZE +\ + MLX5E_MAIN_GROUP8_SIZE) + +static int __mlx5e_create_main_groups(struct mlx5e_flow_table *ft, u32 *in, + int inlen) { - struct mlx5_flow_table_group *g; - u8 *dmac; + u8 *mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + u8 *dmac = MLX5_ADDR_OF(create_flow_group_in, in, + match_criteria.outer_headers.dmac_47_16); + int err; + int ix = 0; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP0_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP2_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); + eth_broadcast_addr(dmac); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP3_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + eth_broadcast_addr(dmac); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP4_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + eth_broadcast_addr(dmac); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP5_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); + dmac[0] = 0x01; + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP6_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + dmac[0] = 0x01; + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP7_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + dmac[0] = 0x01; + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_MAIN_GROUP8_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + return 0; + +err_destroy_groups: + err = PTR_ERR(ft->g[ft->num_groups]); + ft->g[ft->num_groups] = NULL; + mlx5e_destroy_groups(ft); + + return err; +} - g = kcalloc(9, sizeof(*g), GFP_KERNEL); - if (!g) +static int mlx5e_create_main_groups(struct mlx5e_flow_table *ft) +{ + u32 *in; + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + int err; + + in = mlx5_vzalloc(inlen); + if (!in) return -ENOMEM; - g[0].log_sz = 3; - g[0].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, - outer_headers.ethertype); - MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, - outer_headers.ip_protocol); - - g[1].log_sz = 1; - g[1].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, g[1].match_criteria, - outer_headers.ethertype); - - g[2].log_sz = 0; - - g[3].log_sz = 14; - g[3].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g[3].match_criteria, - outer_headers.dmac_47_16); - memset(dmac, 0xff, ETH_ALEN); - MLX5_SET_TO_ONES(fte_match_param, g[3].match_criteria, - outer_headers.ethertype); - MLX5_SET_TO_ONES(fte_match_param, g[3].match_criteria, - outer_headers.ip_protocol); - - g[4].log_sz = 13; - g[4].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g[4].match_criteria, - outer_headers.dmac_47_16); - memset(dmac, 0xff, ETH_ALEN); - MLX5_SET_TO_ONES(fte_match_param, g[4].match_criteria, - outer_headers.ethertype); - - g[5].log_sz = 11; - g[5].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g[5].match_criteria, - outer_headers.dmac_47_16); - memset(dmac, 0xff, ETH_ALEN); - - g[6].log_sz = 2; - g[6].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g[6].match_criteria, - outer_headers.dmac_47_16); - dmac[0] = 0x01; - MLX5_SET_TO_ONES(fte_match_param, g[6].match_criteria, - outer_headers.ethertype); - MLX5_SET_TO_ONES(fte_match_param, g[6].match_criteria, - outer_headers.ip_protocol); - - g[7].log_sz = 1; - g[7].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g[7].match_criteria, - outer_headers.dmac_47_16); - dmac[0] = 0x01; - MLX5_SET_TO_ONES(fte_match_param, g[7].match_criteria, - outer_headers.ethertype); + err = __mlx5e_create_main_groups(ft, in, inlen); - g[8].log_sz = 0; - g[8].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g[8].match_criteria, - outer_headers.dmac_47_16); - dmac[0] = 0x01; - priv->ft.main = mlx5_create_flow_table(priv->mdev, 1, - MLX5_FLOW_TABLE_TYPE_NIC_RCV, - 9, g); - kfree(g); + kvfree(in); + return err; +} - return priv->ft.main ? 0 : -ENOMEM; +static int mlx5e_create_main_flow_table(struct mlx5e_priv *priv) +{ + struct mlx5e_flow_table *ft = &priv->fts.main; + int err; + + ft->num_groups = 0; + ft->t = mlx5_create_flow_table(priv->fts.ns, 0, MLX5E_MAIN_TABLE_SIZE); + + if (IS_ERR(ft->t)) { + err = PTR_ERR(ft->t); + ft->t = NULL; + return err; + } + ft->g = kcalloc(MLX5E_NUM_MAIN_GROUPS, sizeof(*ft->g), GFP_KERNEL); + if (!ft->g) { + err = -ENOMEM; + goto err_destroy_main_flow_table; + } + + err = mlx5e_create_main_groups(ft); + if (err) + goto err_free_g; + return 0; + +err_free_g: + kfree(ft->g); + +err_destroy_main_flow_table: + mlx5_destroy_flow_table(ft->t); + ft->t = NULL; + + return err; +} + +static void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft) +{ + mlx5e_destroy_groups(ft); + kfree(ft->g); + mlx5_destroy_flow_table(ft->t); + ft->t = NULL; } static void mlx5e_destroy_main_flow_table(struct mlx5e_priv *priv) { - mlx5_destroy_flow_table(priv->ft.main); + mlx5e_destroy_flow_table(&priv->fts.main); } -static int mlx5e_create_vlan_flow_table(struct mlx5e_priv *priv) +#define MLX5E_NUM_VLAN_GROUPS 2 +#define MLX5E_VLAN_GROUP0_SIZE BIT(12) +#define MLX5E_VLAN_GROUP1_SIZE BIT(1) +#define MLX5E_VLAN_TABLE_SIZE (MLX5E_VLAN_GROUP0_SIZE +\ + MLX5E_VLAN_GROUP1_SIZE) + +static int __mlx5e_create_vlan_groups(struct mlx5e_flow_table *ft, u32 *in, + int inlen) +{ + int err; + int ix = 0; + u8 *mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.vlan_tag); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.first_vid); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_VLAN_GROUP0_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + memset(in, 0, inlen); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.vlan_tag); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_VLAN_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err_destroy_groups; + ft->num_groups++; + + return 0; + +err_destroy_groups: + err = PTR_ERR(ft->g[ft->num_groups]); + ft->g[ft->num_groups] = NULL; + mlx5e_destroy_groups(ft); + + return err; +} + +static int mlx5e_create_vlan_groups(struct mlx5e_flow_table *ft) { - struct mlx5_flow_table_group *g; + u32 *in; + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + int err; - g = kcalloc(2, sizeof(*g), GFP_KERNEL); - if (!g) + in = mlx5_vzalloc(inlen); + if (!in) return -ENOMEM; - g[0].log_sz = 12; - g[0].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, - outer_headers.vlan_tag); - MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, - outer_headers.first_vid); - - /* untagged + any vlan id */ - g[1].log_sz = 1; - g[1].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, g[1].match_criteria, - outer_headers.vlan_tag); - - priv->ft.vlan = mlx5_create_flow_table(priv->mdev, 0, - MLX5_FLOW_TABLE_TYPE_NIC_RCV, - 2, g); - - kfree(g); - return priv->ft.vlan ? 0 : -ENOMEM; + err = __mlx5e_create_vlan_groups(ft, in, inlen); + + kvfree(in); + return err; +} + +static int mlx5e_create_vlan_flow_table(struct mlx5e_priv *priv) +{ + struct mlx5e_flow_table *ft = &priv->fts.vlan; + int err; + + ft->num_groups = 0; + ft->t = mlx5_create_flow_table(priv->fts.ns, 0, MLX5E_VLAN_TABLE_SIZE); + + if (IS_ERR(ft->t)) { + err = PTR_ERR(ft->t); + ft->t = NULL; + return err; + } + ft->g = kcalloc(MLX5E_NUM_VLAN_GROUPS, sizeof(*ft->g), GFP_KERNEL); + if (!ft->g) { + err = -ENOMEM; + goto err_destroy_vlan_flow_table; + } + + err = mlx5e_create_vlan_groups(ft); + if (err) + goto err_free_g; + + return 0; + +err_free_g: + kfree(ft->g); + +err_destroy_vlan_flow_table: + mlx5_destroy_flow_table(ft->t); + ft->t = NULL; + + return err; } static void mlx5e_destroy_vlan_flow_table(struct mlx5e_priv *priv) { - mlx5_destroy_flow_table(priv->ft.vlan); + mlx5e_destroy_flow_table(&priv->fts.vlan); } int mlx5e_create_flow_tables(struct mlx5e_priv *priv) { int err; - err = mlx5e_create_main_flow_table(priv); + priv->fts.ns = mlx5_get_flow_namespace(priv->mdev, + MLX5_FLOW_NAMESPACE_KERNEL); + + if (!priv->fts.ns) + return -EINVAL; + + err = mlx5e_create_vlan_flow_table(priv); if (err) return err; - err = mlx5e_create_vlan_flow_table(priv); + err = mlx5e_create_main_flow_table(priv); if (err) - goto err_destroy_main_flow_table; + goto err_destroy_vlan_flow_table; err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_UNTAGGED, 0); if (err) - goto err_destroy_vlan_flow_table; + goto err_destroy_main_flow_table; return 0; -err_destroy_vlan_flow_table: - mlx5e_destroy_vlan_flow_table(priv); - err_destroy_main_flow_table: mlx5e_destroy_main_flow_table(priv); +err_destroy_vlan_flow_table: + mlx5e_destroy_vlan_flow_table(priv); return err; } @@ -1041,6 +1219,6 @@ err_destroy_main_flow_table: void mlx5e_destroy_flow_tables(struct mlx5e_priv *priv) { mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_UNTAGGED, 0); - mlx5e_destroy_vlan_flow_table(priv); mlx5e_destroy_main_flow_table(priv); + mlx5e_destroy_vlan_flow_table(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d67058afe87ec..5c74a734f1589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -30,7 +30,7 @@ * SOFTWARE. */ -#include <linux/mlx5/flow_table.h> +#include <linux/mlx5/fs.h> #include "en.h" #include "eswitch.h" @@ -351,6 +351,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, rq->pdev = c->pdev; rq->netdev = c->netdev; + rq->tstamp = &priv->tstamp; rq->channel = c; rq->ix = c->ix; rq->priv = c->priv; @@ -507,6 +508,7 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq) static void mlx5e_free_sq_db(struct mlx5e_sq *sq) { + kfree(sq->wqe_info); kfree(sq->dma_fifo); kfree(sq->skb); } @@ -519,8 +521,10 @@ static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa) sq->skb = kzalloc_node(wq_sz * sizeof(*sq->skb), GFP_KERNEL, numa); sq->dma_fifo = kzalloc_node(df_sz * sizeof(*sq->dma_fifo), GFP_KERNEL, numa); + sq->wqe_info = kzalloc_node(wq_sz * sizeof(*sq->wqe_info), GFP_KERNEL, + numa); - if (!sq->skb || !sq->dma_fifo) { + if (!sq->skb || !sq->dma_fifo || !sq->wqe_info) { mlx5e_free_sq_db(sq); return -ENOMEM; } @@ -568,6 +572,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix); sq->pdev = c->pdev; + sq->tstamp = &priv->tstamp; sq->mkey_be = c->mkey_be; sq->channel = c; sq->tc = tc; @@ -1427,6 +1432,7 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_update_carrier(priv); mlx5e_redirect_rqts(priv); + mlx5e_timestamp_init(priv); schedule_delayed_work(&priv->update_stats_work, 0); @@ -1463,6 +1469,7 @@ int mlx5e_close_locked(struct net_device *netdev) clear_bit(MLX5E_STATE_OPENED, &priv->state); + mlx5e_timestamp_cleanup(priv); mlx5e_redirect_rqts(priv); netif_carrier_off(priv->netdev); mlx5e_close_channels(priv); @@ -1932,6 +1939,18 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) return err; } +static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + switch (cmd) { + case SIOCSHWTSTAMP: + return mlx5e_hwstamp_set(dev, ifr); + case SIOCGHWTSTAMP: + return mlx5e_hwstamp_get(dev, ifr); + default: + return -EOPNOTSUPP; + } +} + static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -2015,7 +2034,8 @@ static struct net_device_ops mlx5e_netdev_ops = { .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, .ndo_set_features = mlx5e_set_features, - .ndo_change_mtu = mlx5e_change_mtu + .ndo_change_mtu = mlx5e_change_mtu, + .ndo_do_ioctl = mlx5e_ioctl, }; static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) @@ -2103,6 +2123,11 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) struct mlx5e_priv *priv = netdev_priv(netdev); mlx5_query_nic_vport_mac_address(priv->mdev, 0, netdev->dev_addr); + if (is_zero_ether_addr(netdev->dev_addr) && + !MLX5_CAP_GEN(priv->mdev, vport_group_manager)) { + eth_hw_addr_random(netdev); + mlx5_core_info(priv->mdev, "Assigned random MAC address %pM\n", netdev->dev_addr); + } } static void mlx5e_build_netdev(struct net_device *netdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 7c8c4088d1be0..dd959d929aadd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -36,6 +36,11 @@ #include <net/busy_poll.h> #include "en.h" +static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp) +{ + return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; +} + static inline int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) { @@ -190,6 +195,7 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, { struct net_device *netdev = rq->netdev; u32 cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + struct mlx5e_tstamp *tstamp = rq->tstamp; int lro_num_seg; skb_put(skb, cqe_bcnt); @@ -202,6 +208,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, rq->stats.lro_bytes += cqe_bcnt; } + if (unlikely(mlx5e_rx_hw_stamp(tstamp))) + mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + mlx5e_handle_csum(netdev, cqe, rq, skb); skb->protocol = eth_type_trans(skb, netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 1341b1d3c421d..2c3fba0fff546 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -92,11 +92,11 @@ static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i) return &sq->dma_fifo[i & sq->dma_fifo_mask]; } -static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) +static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, u8 num_dma) { int i; - for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { + for (i = 0; i < num_dma; i++) { struct mlx5e_sq_dma *last_pushed_dma = mlx5e_dma_get(sq, --sq->dma_fifo_pc); @@ -139,19 +139,28 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, return MLX5E_MIN_INLINE; } -static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) +static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data, + unsigned int *skb_len, + unsigned int len) +{ + *skb_len -= len; + *skb_data += len; +} + +static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs, + unsigned char **skb_data, + unsigned int *skb_len) { struct vlan_ethhdr *vhdr = (struct vlan_ethhdr *)start; int cpy1_sz = 2 * ETH_ALEN; int cpy2_sz = ihs - cpy1_sz; - skb_copy_from_linear_data(skb, vhdr, cpy1_sz); - skb_pull_inline(skb, cpy1_sz); + memcpy(vhdr, *skb_data, cpy1_sz); + mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy1_sz); vhdr->h_vlan_proto = skb->vlan_proto; vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); - skb_copy_from_linear_data(skb, &vhdr->h_vlan_encapsulated_proto, - cpy2_sz); - skb_pull_inline(skb, cpy2_sz); + memcpy(&vhdr->h_vlan_encapsulated_proto, *skb_data, cpy2_sz); + mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz); } static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) @@ -160,11 +169,14 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) u16 pi = sq->pc & wq->sz_m1; struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + struct mlx5e_tx_wqe_info *wi = &sq->wqe_info[pi]; struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg; + unsigned char *skb_data = skb->data; + unsigned int skb_len = skb->len; u8 opcode = MLX5_OPCODE_SEND; dma_addr_t dma_addr = 0; bool bf = false; @@ -192,8 +204,8 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) opcode = MLX5_OPCODE_LSO; ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); payload_len = skb->len - ihs; - MLX5E_TX_SKB_CB(skb)->num_bytes = skb->len + - (skb_shinfo(skb)->gso_segs - 1) * ihs; + wi->num_bytes = skb->len + + (skb_shinfo(skb)->gso_segs - 1) * ihs; sq->stats.tso_packets++; sq->stats.tso_bytes += payload_len; } else { @@ -201,16 +213,16 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) !skb->xmit_more && !skb_shinfo(skb)->nr_frags; ihs = mlx5e_get_inline_hdr_size(sq, skb, bf); - MLX5E_TX_SKB_CB(skb)->num_bytes = max_t(unsigned int, skb->len, - ETH_ZLEN); + wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } if (skb_vlan_tag_present(skb)) { - mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs); + mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data, + &skb_len); ihs += VLAN_HLEN; } else { - skb_copy_from_linear_data(skb, eseg->inline_hdr_start, ihs); - skb_pull_inline(skb, ihs); + memcpy(eseg->inline_hdr_start, skb_data, ihs); + mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs); } eseg->inline_hdr_sz = cpu_to_be16(ihs); @@ -220,11 +232,11 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) MLX5_SEND_WQE_DS); dseg = (struct mlx5_wqe_data_seg *)cseg + ds_cnt; - MLX5E_TX_SKB_CB(skb)->num_dma = 0; + wi->num_dma = 0; - headlen = skb_headlen(skb); + headlen = skb_len - skb->data_len; if (headlen) { - dma_addr = dma_map_single(sq->pdev, skb->data, headlen, + dma_addr = dma_map_single(sq->pdev, skb_data, headlen, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) goto dma_unmap_wqe_err; @@ -234,7 +246,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->byte_count = cpu_to_be32(headlen); mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE); - MLX5E_TX_SKB_CB(skb)->num_dma++; + wi->num_dma++; dseg++; } @@ -253,23 +265,25 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->byte_count = cpu_to_be32(fsz); mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); - MLX5E_TX_SKB_CB(skb)->num_dma++; + wi->num_dma++; dseg++; } - ds_cnt += MLX5E_TX_SKB_CB(skb)->num_dma; + ds_cnt += wi->num_dma; cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode); cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt); sq->skb[pi] = skb; - MLX5E_TX_SKB_CB(skb)->num_wqebbs = DIV_ROUND_UP(ds_cnt, - MLX5_SEND_WQEBB_NUM_DS); - sq->pc += MLX5E_TX_SKB_CB(skb)->num_wqebbs; + wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); + sq->pc += wi->num_wqebbs; + + netdev_tx_sent_queue(sq->txq, wi->num_bytes); - netdev_tx_sent_queue(sq->txq, MLX5E_TX_SKB_CB(skb)->num_bytes); + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM))) { netif_tx_stop_queue(sq->txq); @@ -280,7 +294,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) int bf_sz = 0; if (bf && sq->uar_bf_map) - bf_sz = MLX5E_TX_SKB_CB(skb)->num_wqebbs << 3; + bf_sz = wi->num_wqebbs << 3; cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; mlx5e_tx_notify_hw(sq, wqe, bf_sz); @@ -297,7 +311,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dma_unmap_wqe_err: sq->stats.dropped++; - mlx5e_dma_unmap_wqe_err(sq, skb); + mlx5e_dma_unmap_wqe_err(sq, wi->num_dma); dev_kfree_skb_any(skb); @@ -352,6 +366,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) wqe_counter = be16_to_cpu(cqe->wqe_counter); do { + struct mlx5e_tx_wqe_info *wi; struct sk_buff *skb; u16 ci; int j; @@ -360,6 +375,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) ci = sqcc & sq->wq.sz_m1; skb = sq->skb[ci]; + wi = &sq->wqe_info[ci]; if (unlikely(!skb)) { /* nop */ sq->stats.nop++; @@ -367,7 +383,16 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) continue; } - for (j = 0; j < MLX5E_TX_SKB_CB(skb)->num_dma; j++) { + if (unlikely(skb_shinfo(skb)->tx_flags & + SKBTX_HW_TSTAMP)) { + struct skb_shared_hwtstamps hwts = {}; + + mlx5e_fill_hwstamp(sq->tstamp, + get_cqe_ts(cqe), &hwts); + skb_tstamp_tx(skb, &hwts); + } + + for (j = 0; j < wi->num_dma; j++) { struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, dma_fifo_cc++); @@ -375,8 +400,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) } npkts++; - nbytes += MLX5E_TX_SKB_CB(skb)->num_bytes; - sqcc += MLX5E_TX_SKB_CB(skb)->num_wqebbs; + nbytes += wi->num_bytes; + sqcc += wi->num_wqebbs; dev_kfree_skb(skb); } while (!last_wqe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d8939e597c546..bc3d9f8a75c1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -34,7 +34,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> #include <linux/mlx5/vport.h> -#include <linux/mlx5/flow_table.h> +#include <linux/mlx5/fs.h> #include "mlx5_core.h" #include "eswitch.h" @@ -321,220 +321,6 @@ static void del_l2_table_entry(struct mlx5_core_dev *dev, u32 index) free_l2_table_index(l2_table, index); } -/* E-Switch FDB flow steering */ -struct dest_node { - struct list_head list; - struct mlx5_flow_destination dest; -}; - -static int _mlx5_flow_rule_apply(struct mlx5_flow_rule *fr) -{ - bool was_valid = fr->valid; - struct dest_node *dest_n; - u32 dest_list_size = 0; - void *in_match_value; - u32 *flow_context; - u32 flow_index; - int err; - int i; - - if (list_empty(&fr->dest_list)) { - if (fr->valid) - mlx5_del_flow_table_entry(fr->ft, fr->fi); - fr->valid = false; - return 0; - } - - list_for_each_entry(dest_n, &fr->dest_list, list) - dest_list_size++; - - flow_context = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) + - MLX5_ST_SZ_BYTES(dest_format_struct) * - dest_list_size); - if (!flow_context) - return -ENOMEM; - - MLX5_SET(flow_context, flow_context, flow_tag, fr->flow_tag); - MLX5_SET(flow_context, flow_context, action, fr->action); - MLX5_SET(flow_context, flow_context, destination_list_size, - dest_list_size); - - i = 0; - list_for_each_entry(dest_n, &fr->dest_list, list) { - void *dest_addr = MLX5_ADDR_OF(flow_context, flow_context, - destination[i++]); - - MLX5_SET(dest_format_struct, dest_addr, destination_type, - dest_n->dest.type); - MLX5_SET(dest_format_struct, dest_addr, destination_id, - dest_n->dest.vport_num); - } - - in_match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value); - memcpy(in_match_value, fr->match_value, MLX5_ST_SZ_BYTES(fte_match_param)); - - err = mlx5_add_flow_table_entry(fr->ft, fr->match_criteria_enable, - fr->match_criteria, flow_context, - &flow_index); - if (!err) { - if (was_valid) - mlx5_del_flow_table_entry(fr->ft, fr->fi); - fr->fi = flow_index; - fr->valid = true; - } - kfree(flow_context); - return err; -} - -static int mlx5_flow_rule_add_dest(struct mlx5_flow_rule *fr, - struct mlx5_flow_destination *new_dest) -{ - struct dest_node *dest_n; - int err; - - dest_n = kzalloc(sizeof(*dest_n), GFP_KERNEL); - if (!dest_n) - return -ENOMEM; - - memcpy(&dest_n->dest, new_dest, sizeof(dest_n->dest)); - mutex_lock(&fr->mutex); - list_add(&dest_n->list, &fr->dest_list); - err = _mlx5_flow_rule_apply(fr); - if (err) { - list_del(&dest_n->list); - kfree(dest_n); - } - mutex_unlock(&fr->mutex); - return err; -} - -static int mlx5_flow_rule_del_dest(struct mlx5_flow_rule *fr, - struct mlx5_flow_destination *dest) -{ - struct dest_node *dest_n; - struct dest_node *n; - int err; - - mutex_lock(&fr->mutex); - list_for_each_entry_safe(dest_n, n, &fr->dest_list, list) { - if (dest->vport_num == dest_n->dest.vport_num) - goto found; - } - mutex_unlock(&fr->mutex); - return -ENOENT; - -found: - list_del(&dest_n->list); - err = _mlx5_flow_rule_apply(fr); - mutex_unlock(&fr->mutex); - kfree(dest_n); - - return err; -} - -static struct mlx5_flow_rule *find_fr(struct mlx5_eswitch *esw, - u8 match_criteria_enable, - u32 *match_value) -{ - struct hlist_head *hash = esw->mc_table; - struct esw_mc_addr *esw_mc; - u8 *dmac_v; - - dmac_v = MLX5_ADDR_OF(fte_match_param, match_value, - outer_headers.dmac_47_16); - - /* UNICAST FULL MATCH */ - if (!is_multicast_ether_addr(dmac_v)) - return NULL; - - /* MULTICAST FULL MATCH */ - esw_mc = l2addr_hash_find(hash, dmac_v, struct esw_mc_addr); - - return esw_mc ? esw_mc->uplink_rule : NULL; -} - -static struct mlx5_flow_rule *alloc_fr(void *ft, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, - u32 action, - u32 flow_tag) -{ - struct mlx5_flow_rule *fr = kzalloc(sizeof(*fr), GFP_KERNEL); - - if (!fr) - return NULL; - - fr->match_criteria = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL); - fr->match_value = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL); - if (!fr->match_criteria || !fr->match_value) { - kfree(fr->match_criteria); - kfree(fr->match_value); - kfree(fr); - return NULL; - } - - memcpy(fr->match_criteria, match_criteria, MLX5_ST_SZ_BYTES(fte_match_param)); - memcpy(fr->match_value, match_value, MLX5_ST_SZ_BYTES(fte_match_param)); - fr->match_criteria_enable = match_criteria_enable; - fr->flow_tag = flow_tag; - fr->action = action; - - mutex_init(&fr->mutex); - INIT_LIST_HEAD(&fr->dest_list); - atomic_set(&fr->refcount, 0); - fr->ft = ft; - return fr; -} - -static void deref_fr(struct mlx5_flow_rule *fr) -{ - if (!atomic_dec_and_test(&fr->refcount)) - return; - - kfree(fr->match_criteria); - kfree(fr->match_value); - kfree(fr); -} - -static struct mlx5_flow_rule * -mlx5_add_flow_rule(struct mlx5_eswitch *esw, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, - u32 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_rule *fr; - int err; - - fr = find_fr(esw, match_criteria_enable, match_value); - fr = fr ? fr : alloc_fr(esw->fdb_table.fdb, match_criteria_enable, match_criteria, - match_value, action, flow_tag); - if (!fr) - return NULL; - - atomic_inc(&fr->refcount); - - err = mlx5_flow_rule_add_dest(fr, dest); - if (err) { - deref_fr(fr); - return NULL; - } - - return fr; -} - -static void mlx5_del_flow_rule(struct mlx5_flow_rule *fr, u32 vport) -{ - struct mlx5_flow_destination dest; - - dest.vport_num = vport; - mlx5_flow_rule_del_dest(fr, &dest); - deref_fr(fr); -} - /* E-Switch FDB */ static struct mlx5_flow_rule * esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) @@ -569,7 +355,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) "\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n", dmac_v, dmac_c, vport); flow_rule = - mlx5_add_flow_rule(esw, + mlx5_add_flow_rule(esw->fdb_table.fdb, match_header, match_c, match_v, @@ -589,33 +375,61 @@ out: static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports) { + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_core_dev *dev = esw->dev; - struct mlx5_flow_table_group g; + struct mlx5_flow_namespace *root_ns; struct mlx5_flow_table *fdb; + struct mlx5_flow_group *g; + void *match_criteria; + int table_size; + u32 *flow_group_in; u8 *dmac; + int err = 0; esw_debug(dev, "Create FDB log_max_size(%d)\n", MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); - memset(&g, 0, sizeof(g)); - /* UC MC Full match rules*/ - g.log_sz = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size); - g.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - dmac = MLX5_ADDR_OF(fte_match_param, g.match_criteria, - outer_headers.dmac_47_16); - /* Match criteria mask */ - memset(dmac, 0xff, 6); + root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!root_ns) { + esw_warn(dev, "Failed to get FDB flow namespace\n"); + return -ENOMEM; + } - fdb = mlx5_create_flow_table(dev, 0, - MLX5_FLOW_TABLE_TYPE_ESWITCH, - 1, &g); - if (fdb) - esw_debug(dev, "ESW: FDB Table created fdb->id %d\n", mlx5_get_flow_table_id(fdb)); - else - esw_warn(dev, "ESW: Failed to create FDB Table\n"); + flow_group_in = mlx5_vzalloc(inlen); + if (!flow_group_in) + return -ENOMEM; + memset(flow_group_in, 0, inlen); + + table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); + fdb = mlx5_create_flow_table(root_ns, 0, table_size); + if (IS_ERR_OR_NULL(fdb)) { + err = PTR_ERR(fdb); + esw_warn(dev, "Failed to create FDB Table err %d\n", err); + goto out; + } + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); + dmac = MLX5_ADDR_OF(fte_match_param, match_criteria, outer_headers.dmac_47_16); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1); + eth_broadcast_addr(dmac); + + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR_OR_NULL(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create flow group err(%d)\n", err); + goto out; + } + + esw->fdb_table.addr_grp = g; esw->fdb_table.fdb = fdb; - return fdb ? 0 : -ENOMEM; +out: + kfree(flow_group_in); + if (err && !IS_ERR_OR_NULL(fdb)) + mlx5_destroy_flow_table(fdb); + return err; } static void esw_destroy_fdb_table(struct mlx5_eswitch *esw) @@ -623,10 +437,11 @@ static void esw_destroy_fdb_table(struct mlx5_eswitch *esw) if (!esw->fdb_table.fdb) return; - esw_debug(esw->dev, "Destroy FDB Table fdb(%d)\n", - mlx5_get_flow_table_id(esw->fdb_table.fdb)); + esw_debug(esw->dev, "Destroy FDB Table\n"); + mlx5_destroy_flow_group(esw->fdb_table.addr_grp); mlx5_destroy_flow_table(esw->fdb_table.fdb); esw->fdb_table.fdb = NULL; + esw->fdb_table.addr_grp = NULL; } /* E-Switch vport UC/MC lists management */ @@ -689,7 +504,7 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) del_l2_table_entry(esw->dev, esw_uc->table_index); if (vaddr->flow_rule) - mlx5_del_flow_rule(vaddr->flow_rule, vport); + mlx5_del_flow_rule(vaddr->flow_rule); vaddr->flow_rule = NULL; l2addr_hash_del(esw_uc); @@ -750,14 +565,14 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) esw_mc->uplink_rule); if (vaddr->flow_rule) - mlx5_del_flow_rule(vaddr->flow_rule, vport); + mlx5_del_flow_rule(vaddr->flow_rule); vaddr->flow_rule = NULL; if (--esw_mc->refcnt) return 0; if (esw_mc->uplink_rule) - mlx5_del_flow_rule(esw_mc->uplink_rule, UPLINK_VPORT); + mlx5_del_flow_rule(esw_mc->uplink_rule); l2addr_hash_del(esw_mc); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 02ff3eade0260..3416a428f70fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -88,20 +88,6 @@ struct l2addr_node { kfree(ptr); \ }) -struct mlx5_flow_rule { - void *ft; - u32 fi; - u8 match_criteria_enable; - u32 *match_criteria; - u32 *match_value; - u32 action; - u32 flow_tag; - bool valid; - atomic_t refcount; - struct mutex mutex; /* protect flow rule updates */ - struct list_head dest_list; -}; - struct mlx5_vport { struct mlx5_core_dev *dev; int vport; @@ -126,6 +112,7 @@ struct mlx5_l2_table { struct mlx5_eswitch_fdb { void *fdb; + struct mlx5_flow_group *addr_grp; }; struct mlx5_eswitch { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c deleted file mode 100644 index ca90b9bc3b95e..0000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c +++ /dev/null @@ -1,422 +0,0 @@ -/* - * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * 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 AUTHORS OR COPYRIGHT HOLDERS - * 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. - */ - -#include <linux/export.h> -#include <linux/mlx5/driver.h> -#include <linux/mlx5/flow_table.h> -#include "mlx5_core.h" - -struct mlx5_ftg { - struct mlx5_flow_table_group g; - u32 id; - u32 start_ix; -}; - -struct mlx5_flow_table { - struct mlx5_core_dev *dev; - u8 level; - u8 type; - u32 id; - struct mutex mutex; /* sync bitmap alloc */ - u16 num_groups; - struct mlx5_ftg *group; - unsigned long *bitmap; - u32 size; -}; - -static int mlx5_set_flow_entry_cmd(struct mlx5_flow_table *ft, u32 group_ix, - u32 flow_index, void *flow_context) -{ - u32 out[MLX5_ST_SZ_DW(set_fte_out)]; - u32 *in; - void *in_flow_context; - int fcdls = - MLX5_GET(flow_context, flow_context, destination_list_size) * - MLX5_ST_SZ_BYTES(dest_format_struct); - int inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fcdls; - int err; - - in = mlx5_vzalloc(inlen); - if (!in) { - mlx5_core_warn(ft->dev, "failed to allocate inbox\n"); - return -ENOMEM; - } - - MLX5_SET(set_fte_in, in, table_type, ft->type); - MLX5_SET(set_fte_in, in, table_id, ft->id); - MLX5_SET(set_fte_in, in, flow_index, flow_index); - MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY); - - in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); - memcpy(in_flow_context, flow_context, - MLX5_ST_SZ_BYTES(flow_context) + fcdls); - - MLX5_SET(flow_context, in_flow_context, group_id, - ft->group[group_ix].id); - - memset(out, 0, sizeof(out)); - err = mlx5_cmd_exec_check_status(ft->dev, in, inlen, out, - sizeof(out)); - kvfree(in); - - return err; -} - -static void mlx5_del_flow_entry_cmd(struct mlx5_flow_table *ft, u32 flow_index) -{ - u32 in[MLX5_ST_SZ_DW(delete_fte_in)]; - u32 out[MLX5_ST_SZ_DW(delete_fte_out)]; - - memset(in, 0, sizeof(in)); - memset(out, 0, sizeof(out)); - -#define MLX5_SET_DFTEI(p, x, v) MLX5_SET(delete_fte_in, p, x, v) - MLX5_SET_DFTEI(in, table_type, ft->type); - MLX5_SET_DFTEI(in, table_id, ft->id); - MLX5_SET_DFTEI(in, flow_index, flow_index); - MLX5_SET_DFTEI(in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY); - - mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out)); -} - -static void mlx5_destroy_flow_group_cmd(struct mlx5_flow_table *ft, int i) -{ - u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)]; - u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)]; - - memset(in, 0, sizeof(in)); - memset(out, 0, sizeof(out)); - -#define MLX5_SET_DFGI(p, x, v) MLX5_SET(destroy_flow_group_in, p, x, v) - MLX5_SET_DFGI(in, table_type, ft->type); - MLX5_SET_DFGI(in, table_id, ft->id); - MLX5_SET_DFGI(in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP); - MLX5_SET_DFGI(in, group_id, ft->group[i].id); - mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out)); -} - -static int mlx5_create_flow_group_cmd(struct mlx5_flow_table *ft, int i) -{ - u32 out[MLX5_ST_SZ_DW(create_flow_group_out)]; - u32 *in; - void *in_match_criteria; - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_flow_table_group *g = &ft->group[i].g; - u32 start_ix = ft->group[i].start_ix; - u32 end_ix = start_ix + (1 << g->log_sz) - 1; - int err; - - in = mlx5_vzalloc(inlen); - if (!in) { - mlx5_core_warn(ft->dev, "failed to allocate inbox\n"); - return -ENOMEM; - } - in_match_criteria = MLX5_ADDR_OF(create_flow_group_in, in, - match_criteria); - - memset(out, 0, sizeof(out)); - -#define MLX5_SET_CFGI(p, x, v) MLX5_SET(create_flow_group_in, p, x, v) - MLX5_SET_CFGI(in, table_type, ft->type); - MLX5_SET_CFGI(in, table_id, ft->id); - MLX5_SET_CFGI(in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP); - MLX5_SET_CFGI(in, start_flow_index, start_ix); - MLX5_SET_CFGI(in, end_flow_index, end_ix); - MLX5_SET_CFGI(in, match_criteria_enable, g->match_criteria_enable); - - memcpy(in_match_criteria, g->match_criteria, - MLX5_ST_SZ_BYTES(fte_match_param)); - - err = mlx5_cmd_exec_check_status(ft->dev, in, inlen, out, - sizeof(out)); - if (!err) - ft->group[i].id = MLX5_GET(create_flow_group_out, out, - group_id); - - kvfree(in); - - return err; -} - -static void mlx5_destroy_flow_table_groups(struct mlx5_flow_table *ft) -{ - int i; - - for (i = 0; i < ft->num_groups; i++) - mlx5_destroy_flow_group_cmd(ft, i); -} - -static int mlx5_create_flow_table_groups(struct mlx5_flow_table *ft) -{ - int err; - int i; - - for (i = 0; i < ft->num_groups; i++) { - err = mlx5_create_flow_group_cmd(ft, i); - if (err) - goto err_destroy_flow_table_groups; - } - - return 0; - -err_destroy_flow_table_groups: - for (i--; i >= 0; i--) - mlx5_destroy_flow_group_cmd(ft, i); - - return err; -} - -static int mlx5_create_flow_table_cmd(struct mlx5_flow_table *ft) -{ - u32 in[MLX5_ST_SZ_DW(create_flow_table_in)]; - u32 out[MLX5_ST_SZ_DW(create_flow_table_out)]; - int err; - - memset(in, 0, sizeof(in)); - - MLX5_SET(create_flow_table_in, in, table_type, ft->type); - MLX5_SET(create_flow_table_in, in, level, ft->level); - MLX5_SET(create_flow_table_in, in, log_size, order_base_2(ft->size)); - - MLX5_SET(create_flow_table_in, in, opcode, - MLX5_CMD_OP_CREATE_FLOW_TABLE); - - memset(out, 0, sizeof(out)); - err = mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, - sizeof(out)); - if (err) - return err; - - ft->id = MLX5_GET(create_flow_table_out, out, table_id); - - return 0; -} - -static void mlx5_destroy_flow_table_cmd(struct mlx5_flow_table *ft) -{ - u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)]; - u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)]; - - memset(in, 0, sizeof(in)); - memset(out, 0, sizeof(out)); - -#define MLX5_SET_DFTI(p, x, v) MLX5_SET(destroy_flow_table_in, p, x, v) - MLX5_SET_DFTI(in, table_type, ft->type); - MLX5_SET_DFTI(in, table_id, ft->id); - MLX5_SET_DFTI(in, opcode, MLX5_CMD_OP_DESTROY_FLOW_TABLE); - - mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out)); -} - -static int mlx5_find_group(struct mlx5_flow_table *ft, u8 match_criteria_enable, - u32 *match_criteria, int *group_ix) -{ - void *mc_outer = MLX5_ADDR_OF(fte_match_param, match_criteria, - outer_headers); - void *mc_misc = MLX5_ADDR_OF(fte_match_param, match_criteria, - misc_parameters); - void *mc_inner = MLX5_ADDR_OF(fte_match_param, match_criteria, - inner_headers); - int mc_outer_sz = MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4); - int mc_misc_sz = MLX5_ST_SZ_BYTES(fte_match_set_misc); - int mc_inner_sz = MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4); - int i; - - for (i = 0; i < ft->num_groups; i++) { - struct mlx5_flow_table_group *g = &ft->group[i].g; - void *gmc_outer = MLX5_ADDR_OF(fte_match_param, - g->match_criteria, - outer_headers); - void *gmc_misc = MLX5_ADDR_OF(fte_match_param, - g->match_criteria, - misc_parameters); - void *gmc_inner = MLX5_ADDR_OF(fte_match_param, - g->match_criteria, - inner_headers); - - if (g->match_criteria_enable != match_criteria_enable) - continue; - - if (match_criteria_enable & MLX5_MATCH_OUTER_HEADERS) - if (memcmp(mc_outer, gmc_outer, mc_outer_sz)) - continue; - - if (match_criteria_enable & MLX5_MATCH_MISC_PARAMETERS) - if (memcmp(mc_misc, gmc_misc, mc_misc_sz)) - continue; - - if (match_criteria_enable & MLX5_MATCH_INNER_HEADERS) - if (memcmp(mc_inner, gmc_inner, mc_inner_sz)) - continue; - - *group_ix = i; - return 0; - } - - return -EINVAL; -} - -static int alloc_flow_index(struct mlx5_flow_table *ft, int group_ix, u32 *ix) -{ - struct mlx5_ftg *g = &ft->group[group_ix]; - int err = 0; - - mutex_lock(&ft->mutex); - - *ix = find_next_zero_bit(ft->bitmap, ft->size, g->start_ix); - if (*ix >= (g->start_ix + (1 << g->g.log_sz))) - err = -ENOSPC; - else - __set_bit(*ix, ft->bitmap); - - mutex_unlock(&ft->mutex); - - return err; -} - -static void mlx5_free_flow_index(struct mlx5_flow_table *ft, u32 ix) -{ - __clear_bit(ix, ft->bitmap); -} - -int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, - void *match_criteria, void *flow_context, - u32 *flow_index) -{ - struct mlx5_flow_table *ft = flow_table; - int group_ix; - int err; - - err = mlx5_find_group(ft, match_criteria_enable, match_criteria, - &group_ix); - if (err) { - mlx5_core_warn(ft->dev, "mlx5_find_group failed\n"); - return err; - } - - err = alloc_flow_index(ft, group_ix, flow_index); - if (err) { - mlx5_core_warn(ft->dev, "alloc_flow_index failed\n"); - return err; - } - - return mlx5_set_flow_entry_cmd(ft, group_ix, *flow_index, flow_context); -} -EXPORT_SYMBOL(mlx5_add_flow_table_entry); - -void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index) -{ - struct mlx5_flow_table *ft = flow_table; - - mlx5_del_flow_entry_cmd(ft, flow_index); - mlx5_free_flow_index(ft, flow_index); -} -EXPORT_SYMBOL(mlx5_del_flow_table_entry); - -void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, - u16 num_groups, - struct mlx5_flow_table_group *group) -{ - struct mlx5_flow_table *ft; - u32 start_ix = 0; - u32 ft_size = 0; - void *gr; - void *bm; - int err; - int i; - - for (i = 0; i < num_groups; i++) - ft_size += (1 << group[i].log_sz); - - ft = kzalloc(sizeof(*ft), GFP_KERNEL); - gr = kcalloc(num_groups, sizeof(struct mlx5_ftg), GFP_KERNEL); - bm = kcalloc(BITS_TO_LONGS(ft_size), sizeof(uintptr_t), GFP_KERNEL); - if (!ft || !gr || !bm) - goto err_free_ft; - - ft->group = gr; - ft->bitmap = bm; - ft->num_groups = num_groups; - ft->level = level; - ft->type = table_type; - ft->size = ft_size; - ft->dev = dev; - mutex_init(&ft->mutex); - - for (i = 0; i < ft->num_groups; i++) { - memcpy(&ft->group[i].g, &group[i], sizeof(*group)); - ft->group[i].start_ix = start_ix; - start_ix += 1 << group[i].log_sz; - } - - err = mlx5_create_flow_table_cmd(ft); - if (err) - goto err_free_ft; - - err = mlx5_create_flow_table_groups(ft); - if (err) - goto err_destroy_flow_table_cmd; - - return ft; - -err_destroy_flow_table_cmd: - mlx5_destroy_flow_table_cmd(ft); - -err_free_ft: - mlx5_core_warn(dev, "failed to alloc flow table\n"); - kfree(bm); - kfree(gr); - kfree(ft); - - return NULL; -} -EXPORT_SYMBOL(mlx5_create_flow_table); - -void mlx5_destroy_flow_table(void *flow_table) -{ - struct mlx5_flow_table *ft = flow_table; - - mlx5_destroy_flow_table_groups(ft); - mlx5_destroy_flow_table_cmd(ft); - kfree(ft->bitmap); - kfree(ft->group); - kfree(ft); -} -EXPORT_SYMBOL(mlx5_destroy_flow_table); - -u32 mlx5_get_flow_table_id(void *flow_table) -{ - struct mlx5_flow_table *ft = flow_table; - - return ft->id; -} -EXPORT_SYMBOL(mlx5_get_flow_table_id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c new file mode 100644 index 0000000000000..5096f4f336bdb --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -0,0 +1,239 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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 AUTHORS OR COPYRIGHT HOLDERS + * 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. + */ + +#include <linux/mlx5/driver.h> +#include <linux/mlx5/device.h> +#include <linux/mlx5/mlx5_ifc.h> + +#include "fs_core.h" +#include "fs_cmd.h" +#include "mlx5_core.h" + +int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, + enum fs_flow_table_type type, unsigned int level, + unsigned int log_size, unsigned int *table_id) +{ + u32 out[MLX5_ST_SZ_DW(create_flow_table_out)]; + u32 in[MLX5_ST_SZ_DW(create_flow_table_in)]; + int err; + + memset(in, 0, sizeof(in)); + + MLX5_SET(create_flow_table_in, in, opcode, + MLX5_CMD_OP_CREATE_FLOW_TABLE); + + MLX5_SET(create_flow_table_in, in, table_type, type); + MLX5_SET(create_flow_table_in, in, level, level); + MLX5_SET(create_flow_table_in, in, log_size, log_size); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, + sizeof(out)); + + if (!err) + *table_id = MLX5_GET(create_flow_table_out, out, + table_id); + return err; +} + +int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft) +{ + u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)]; + u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(destroy_flow_table_in, in, opcode, + MLX5_CMD_OP_DESTROY_FLOW_TABLE); + MLX5_SET(destroy_flow_table_in, in, table_type, ft->type); + MLX5_SET(destroy_flow_table_in, in, table_id, ft->id); + + return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, + sizeof(out)); +} + +int mlx5_cmd_create_flow_group(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + u32 *in, + unsigned int *group_id) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + u32 out[MLX5_ST_SZ_DW(create_flow_group_out)]; + int err; + + memset(out, 0, sizeof(out)); + + MLX5_SET(create_flow_group_in, in, opcode, + MLX5_CMD_OP_CREATE_FLOW_GROUP); + MLX5_SET(create_flow_group_in, in, table_type, ft->type); + MLX5_SET(create_flow_group_in, in, table_id, ft->id); + + err = mlx5_cmd_exec_check_status(dev, in, + inlen, out, + sizeof(out)); + if (!err) + *group_id = MLX5_GET(create_flow_group_out, out, + group_id); + + return err; +} + +int mlx5_cmd_destroy_flow_group(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned int group_id) +{ + u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)]; + u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(destroy_flow_group_in, in, opcode, + MLX5_CMD_OP_DESTROY_FLOW_GROUP); + MLX5_SET(destroy_flow_group_in, in, table_type, ft->type); + MLX5_SET(destroy_flow_group_in, in, table_id, ft->id); + MLX5_SET(destroy_flow_group_in, in, group_id, group_id); + + return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, + sizeof(out)); +} + +static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, + int opmod, int modify_mask, + struct mlx5_flow_table *ft, + unsigned group_id, + struct fs_fte *fte) +{ + unsigned int inlen = MLX5_ST_SZ_BYTES(set_fte_in) + + fte->dests_size * MLX5_ST_SZ_BYTES(dest_format_struct); + u32 out[MLX5_ST_SZ_DW(set_fte_out)]; + struct mlx5_flow_rule *dst; + void *in_flow_context; + void *in_match_value; + void *in_dests; + u32 *in; + int err; + + in = mlx5_vzalloc(inlen); + if (!in) { + mlx5_core_warn(dev, "failed to allocate inbox\n"); + return -ENOMEM; + } + + MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY); + MLX5_SET(set_fte_in, in, op_mod, opmod); + MLX5_SET(set_fte_in, in, modify_enable_mask, modify_mask); + MLX5_SET(set_fte_in, in, table_type, ft->type); + MLX5_SET(set_fte_in, in, table_id, ft->id); + MLX5_SET(set_fte_in, in, flow_index, fte->index); + + in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); + MLX5_SET(flow_context, in_flow_context, group_id, group_id); + MLX5_SET(flow_context, in_flow_context, flow_tag, fte->flow_tag); + MLX5_SET(flow_context, in_flow_context, action, fte->action); + MLX5_SET(flow_context, in_flow_context, destination_list_size, + fte->dests_size); + in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context, + match_value); + memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param)); + + in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); + list_for_each_entry(dst, &fte->node.children, node.list) { + unsigned int id; + + MLX5_SET(dest_format_struct, in_dests, destination_type, + dst->dest_attr.type); + if (dst->dest_attr.type == + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) + id = dst->dest_attr.ft->id; + else + id = dst->dest_attr.tir_num; + MLX5_SET(dest_format_struct, in_dests, destination_id, id); + in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); + } + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(dev, in, inlen, out, + sizeof(out)); + kvfree(in); + + return err; +} + +int mlx5_cmd_create_fte(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned group_id, + struct fs_fte *fte) +{ + return mlx5_cmd_set_fte(dev, 0, 0, ft, group_id, fte); +} + +int mlx5_cmd_update_fte(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned group_id, + struct fs_fte *fte) +{ + int opmod; + int modify_mask; + int atomic_mod_cap = MLX5_CAP_FLOWTABLE(dev, + flow_table_properties_nic_receive. + flow_modify_en); + if (!atomic_mod_cap) + return -ENOTSUPP; + opmod = 1; + modify_mask = 1 << + MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST; + + return mlx5_cmd_set_fte(dev, opmod, modify_mask, ft, group_id, fte); +} + +int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned int index) +{ + u32 out[MLX5_ST_SZ_DW(delete_fte_out)]; + u32 in[MLX5_ST_SZ_DW(delete_fte_in)]; + int err; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY); + MLX5_SET(delete_fte_in, in, table_type, ft->type); + MLX5_SET(delete_fte_in, in, table_id, ft->id); + MLX5_SET(delete_fte_in, in, flow_index, index); + + err = mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out)); + + return err; +} diff --git a/include/linux/mlx5/flow_table.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 0f2a15cf33173..f39304ede186d 100644 --- a/include/linux/mlx5/flow_table.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -30,34 +30,36 @@ * SOFTWARE. */ -#ifndef MLX5_FLOW_TABLE_H -#define MLX5_FLOW_TABLE_H - -#include <linux/mlx5/driver.h> - -struct mlx5_flow_table_group { - u8 log_sz; - u8 match_criteria_enable; - u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; -}; - -struct mlx5_flow_destination { - enum mlx5_flow_destination_type type; - union { - u32 tir_num; - void *ft; - u32 vport_num; - }; -}; - -void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, - u16 num_groups, - struct mlx5_flow_table_group *group); -void mlx5_destroy_flow_table(void *flow_table); -int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, - void *match_criteria, void *flow_context, - u32 *flow_index); -void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index); -u32 mlx5_get_flow_table_id(void *flow_table); - -#endif /* MLX5_FLOW_TABLE_H */ +#ifndef _MLX5_FS_CMD_ +#define _MLX5_FS_CMD_ + +int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, + enum fs_flow_table_type type, unsigned int level, + unsigned int log_size, unsigned int *table_id); + +int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft); + +int mlx5_cmd_create_flow_group(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + u32 *in, unsigned int *group_id); + +int mlx5_cmd_destroy_flow_group(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned int group_id); + +int mlx5_cmd_create_fte(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned group_id, + struct fs_fte *fte); + +int mlx5_cmd_update_fte(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned group_id, + struct fs_fte *fte); + +int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + unsigned int index); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c new file mode 100644 index 0000000000000..f7d62fe595f63 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -0,0 +1,1047 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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 AUTHORS OR COPYRIGHT HOLDERS + * 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. + */ + +#include <linux/mutex.h> +#include <linux/mlx5/driver.h> + +#include "mlx5_core.h" +#include "fs_core.h" +#include "fs_cmd.h" + +#define INIT_TREE_NODE_ARRAY_SIZE(...) (sizeof((struct init_tree_node[]){__VA_ARGS__}) /\ + sizeof(struct init_tree_node)) + +#define INIT_PRIO(min_level_val, max_ft_val,\ + start_level_val, ...) {.type = FS_TYPE_PRIO,\ + .min_ft_level = min_level_val,\ + .start_level = start_level_val,\ + .max_ft = max_ft_val,\ + .children = (struct init_tree_node[]) {__VA_ARGS__},\ + .ar_size = INIT_TREE_NODE_ARRAY_SIZE(__VA_ARGS__) \ +} + +#define ADD_PRIO(min_level_val, max_ft_val, start_level_val, ...)\ + INIT_PRIO(min_level_val, max_ft_val, start_level_val,\ + __VA_ARGS__)\ + +#define ADD_FT_PRIO(max_ft_val, start_level_val, ...)\ + INIT_PRIO(0, max_ft_val, start_level_val,\ + __VA_ARGS__)\ + +#define ADD_NS(...) {.type = FS_TYPE_NAMESPACE,\ + .children = (struct init_tree_node[]) {__VA_ARGS__},\ + .ar_size = INIT_TREE_NODE_ARRAY_SIZE(__VA_ARGS__) \ +} + +#define KERNEL_START_LEVEL 0 +#define KERNEL_P0_START_LEVEL KERNEL_START_LEVEL +#define KERNEL_MAX_FT 2 +#define KENREL_MIN_LEVEL 2 +static struct init_tree_node { + enum fs_node_type type; + struct init_tree_node *children; + int ar_size; + int min_ft_level; + int prio; + int max_ft; + int start_level; +} root_fs = { + .type = FS_TYPE_NAMESPACE, + .ar_size = 1, + .children = (struct init_tree_node[]) { + ADD_PRIO(KENREL_MIN_LEVEL, KERNEL_MAX_FT, + KERNEL_START_LEVEL, + ADD_NS(ADD_FT_PRIO(KERNEL_MAX_FT, + KERNEL_P0_START_LEVEL))), + } +}; + +static void del_rule(struct fs_node *node); +static void del_flow_table(struct fs_node *node); +static void del_flow_group(struct fs_node *node); +static void del_fte(struct fs_node *node); + +static void tree_init_node(struct fs_node *node, + unsigned int refcount, + void (*remove_func)(struct fs_node *)) +{ + atomic_set(&node->refcount, refcount); + INIT_LIST_HEAD(&node->list); + INIT_LIST_HEAD(&node->children); + mutex_init(&node->lock); + node->remove_func = remove_func; +} + +static void tree_add_node(struct fs_node *node, struct fs_node *parent) +{ + if (parent) + atomic_inc(&parent->refcount); + node->parent = parent; + + /* Parent is the root */ + if (!parent) + node->root = node; + else + node->root = parent->root; +} + +static void tree_get_node(struct fs_node *node) +{ + atomic_inc(&node->refcount); +} + +static void nested_lock_ref_node(struct fs_node *node) +{ + if (node) { + mutex_lock_nested(&node->lock, SINGLE_DEPTH_NESTING); + atomic_inc(&node->refcount); + } +} + +static void lock_ref_node(struct fs_node *node) +{ + if (node) { + mutex_lock(&node->lock); + atomic_inc(&node->refcount); + } +} + +static void unlock_ref_node(struct fs_node *node) +{ + if (node) { + atomic_dec(&node->refcount); + mutex_unlock(&node->lock); + } +} + +static void tree_put_node(struct fs_node *node) +{ + struct fs_node *parent_node = node->parent; + + lock_ref_node(parent_node); + if (atomic_dec_and_test(&node->refcount)) { + if (parent_node) + list_del_init(&node->list); + if (node->remove_func) + node->remove_func(node); + kfree(node); + node = NULL; + } + unlock_ref_node(parent_node); + if (!node && parent_node) + tree_put_node(parent_node); +} + +static int tree_remove_node(struct fs_node *node) +{ + if (atomic_read(&node->refcount) > 1) + return -EPERM; + tree_put_node(node); + return 0; +} + +static struct fs_prio *find_prio(struct mlx5_flow_namespace *ns, + unsigned int prio) +{ + struct fs_prio *iter_prio; + + fs_for_each_prio(iter_prio, ns) { + if (iter_prio->prio == prio) + return iter_prio; + } + + return NULL; +} + +static unsigned int find_next_free_level(struct fs_prio *prio) +{ + if (!list_empty(&prio->node.children)) { + struct mlx5_flow_table *ft; + + ft = list_last_entry(&prio->node.children, + struct mlx5_flow_table, + node.list); + return ft->level + 1; + } + return prio->start_level; +} + +static bool masked_memcmp(void *mask, void *val1, void *val2, size_t size) +{ + unsigned int i; + + for (i = 0; i < size; i++, mask++, val1++, val2++) + if ((*((u8 *)val1) & (*(u8 *)mask)) != + ((*(u8 *)val2) & (*(u8 *)mask))) + return false; + + return true; +} + +static bool compare_match_value(struct mlx5_flow_group_mask *mask, + void *fte_param1, void *fte_param2) +{ + if (mask->match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS) { + void *fte_match1 = MLX5_ADDR_OF(fte_match_param, + fte_param1, outer_headers); + void *fte_match2 = MLX5_ADDR_OF(fte_match_param, + fte_param2, outer_headers); + void *fte_mask = MLX5_ADDR_OF(fte_match_param, + mask->match_criteria, outer_headers); + + if (!masked_memcmp(fte_mask, fte_match1, fte_match2, + MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4))) + return false; + } + + if (mask->match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS) { + void *fte_match1 = MLX5_ADDR_OF(fte_match_param, + fte_param1, misc_parameters); + void *fte_match2 = MLX5_ADDR_OF(fte_match_param, + fte_param2, misc_parameters); + void *fte_mask = MLX5_ADDR_OF(fte_match_param, + mask->match_criteria, misc_parameters); + + if (!masked_memcmp(fte_mask, fte_match1, fte_match2, + MLX5_ST_SZ_BYTES(fte_match_set_misc))) + return false; + } + + if (mask->match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS) { + void *fte_match1 = MLX5_ADDR_OF(fte_match_param, + fte_param1, inner_headers); + void *fte_match2 = MLX5_ADDR_OF(fte_match_param, + fte_param2, inner_headers); + void *fte_mask = MLX5_ADDR_OF(fte_match_param, + mask->match_criteria, inner_headers); + + if (!masked_memcmp(fte_mask, fte_match1, fte_match2, + MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4))) + return false; + } + return true; +} + +static bool compare_match_criteria(u8 match_criteria_enable1, + u8 match_criteria_enable2, + void *mask1, void *mask2) +{ + return match_criteria_enable1 == match_criteria_enable2 && + !memcmp(mask1, mask2, MLX5_ST_SZ_BYTES(fte_match_param)); +} + +static struct mlx5_flow_root_namespace *find_root(struct fs_node *node) +{ + struct fs_node *root; + struct mlx5_flow_namespace *ns; + + root = node->root; + + if (WARN_ON(root->type != FS_TYPE_NAMESPACE)) { + pr_warn("mlx5: flow steering node is not in tree or garbaged\n"); + return NULL; + } + + ns = container_of(root, struct mlx5_flow_namespace, node); + return container_of(ns, struct mlx5_flow_root_namespace, ns); +} + +static inline struct mlx5_core_dev *get_dev(struct fs_node *node) +{ + struct mlx5_flow_root_namespace *root = find_root(node); + + if (root) + return root->dev; + return NULL; +} + +static void del_flow_table(struct fs_node *node) +{ + struct mlx5_flow_table *ft; + struct mlx5_core_dev *dev; + struct fs_prio *prio; + int err; + + fs_get_obj(ft, node); + dev = get_dev(&ft->node); + + err = mlx5_cmd_destroy_flow_table(dev, ft); + if (err) + pr_warn("flow steering can't destroy ft\n"); + fs_get_obj(prio, ft->node.parent); + prio->num_ft--; +} + +static void del_rule(struct fs_node *node) +{ + struct mlx5_flow_rule *rule; + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct fs_fte *fte; + u32 *match_value; + struct mlx5_core_dev *dev = get_dev(node); + int match_len = MLX5_ST_SZ_BYTES(fte_match_param); + int err; + + match_value = mlx5_vzalloc(match_len); + if (!match_value) { + pr_warn("failed to allocate inbox\n"); + return; + } + + fs_get_obj(rule, node); + fs_get_obj(fte, rule->node.parent); + fs_get_obj(fg, fte->node.parent); + memcpy(match_value, fte->val, sizeof(fte->val)); + fs_get_obj(ft, fg->node.parent); + list_del(&rule->node.list); + fte->dests_size--; + if (fte->dests_size) { + err = mlx5_cmd_update_fte(dev, ft, + fg->id, fte); + if (err) + pr_warn("%s can't del rule fg id=%d fte_index=%d\n", + __func__, fg->id, fte->index); + } + kvfree(match_value); +} + +static void del_fte(struct fs_node *node) +{ + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct mlx5_core_dev *dev; + struct fs_fte *fte; + int err; + + fs_get_obj(fte, node); + fs_get_obj(fg, fte->node.parent); + fs_get_obj(ft, fg->node.parent); + + dev = get_dev(&ft->node); + err = mlx5_cmd_delete_fte(dev, ft, + fte->index); + if (err) + pr_warn("flow steering can't delete fte in index %d of flow group id %d\n", + fte->index, fg->id); + + fte->status = 0; + fg->num_ftes--; +} + +static void del_flow_group(struct fs_node *node) +{ + struct mlx5_flow_group *fg; + struct mlx5_flow_table *ft; + struct mlx5_core_dev *dev; + + fs_get_obj(fg, node); + fs_get_obj(ft, fg->node.parent); + dev = get_dev(&ft->node); + + if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) + pr_warn("flow steering can't destroy fg %d of ft %d\n", + fg->id, ft->id); +} + +static struct fs_fte *alloc_fte(u8 action, + u32 flow_tag, + u32 *match_value, + unsigned int index) +{ + struct fs_fte *fte; + + fte = kzalloc(sizeof(*fte), GFP_KERNEL); + if (!fte) + return ERR_PTR(-ENOMEM); + + memcpy(fte->val, match_value, sizeof(fte->val)); + fte->node.type = FS_TYPE_FLOW_ENTRY; + fte->flow_tag = flow_tag; + fte->index = index; + fte->action = action; + + return fte; +} + +static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) +{ + struct mlx5_flow_group *fg; + void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, + create_fg_in, match_criteria); + u8 match_criteria_enable = MLX5_GET(create_flow_group_in, + create_fg_in, + match_criteria_enable); + fg = kzalloc(sizeof(*fg), GFP_KERNEL); + if (!fg) + return ERR_PTR(-ENOMEM); + + fg->mask.match_criteria_enable = match_criteria_enable; + memcpy(&fg->mask.match_criteria, match_criteria, + sizeof(fg->mask.match_criteria)); + fg->node.type = FS_TYPE_FLOW_GROUP; + fg->start_index = MLX5_GET(create_flow_group_in, create_fg_in, + start_flow_index); + fg->max_ftes = MLX5_GET(create_flow_group_in, create_fg_in, + end_flow_index) - fg->start_index + 1; + return fg; +} + +static struct mlx5_flow_table *alloc_flow_table(int level, int max_fte, + enum fs_flow_table_type table_type) +{ + struct mlx5_flow_table *ft; + + ft = kzalloc(sizeof(*ft), GFP_KERNEL); + if (!ft) + return NULL; + + ft->level = level; + ft->node.type = FS_TYPE_FLOW_TABLE; + ft->type = table_type; + ft->max_fte = max_fte; + + return ft; +} + +struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns, + int prio, + int max_fte) +{ + struct mlx5_flow_table *ft; + int err; + int log_table_sz; + struct mlx5_flow_root_namespace *root = + find_root(&ns->node); + struct fs_prio *fs_prio = NULL; + + if (!root) { + pr_err("mlx5: flow steering failed to find root of namespace\n"); + return ERR_PTR(-ENODEV); + } + + fs_prio = find_prio(ns, prio); + if (!fs_prio) + return ERR_PTR(-EINVAL); + + lock_ref_node(&fs_prio->node); + if (fs_prio->num_ft == fs_prio->max_ft) { + err = -ENOSPC; + goto unlock_prio; + } + + ft = alloc_flow_table(find_next_free_level(fs_prio), + roundup_pow_of_two(max_fte), + root->table_type); + if (!ft) { + err = -ENOMEM; + goto unlock_prio; + } + + tree_init_node(&ft->node, 1, del_flow_table); + log_table_sz = ilog2(ft->max_fte); + err = mlx5_cmd_create_flow_table(root->dev, ft->type, ft->level, + log_table_sz, &ft->id); + if (err) + goto free_ft; + + tree_add_node(&ft->node, &fs_prio->node); + list_add_tail(&ft->node.list, &fs_prio->node.children); + fs_prio->num_ft++; + unlock_ref_node(&fs_prio->node); + + return ft; + +free_ft: + kfree(ft); +unlock_prio: + unlock_ref_node(&fs_prio->node); + return ERR_PTR(err); +} + +struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, + u32 *fg_in) +{ + struct mlx5_flow_group *fg; + struct mlx5_core_dev *dev = get_dev(&ft->node); + int err; + + if (!dev) + return ERR_PTR(-ENODEV); + + fg = alloc_flow_group(fg_in); + if (IS_ERR(fg)) + return fg; + + lock_ref_node(&ft->node); + err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); + if (err) { + kfree(fg); + unlock_ref_node(&ft->node); + return ERR_PTR(err); + } + /* Add node to tree */ + tree_init_node(&fg->node, 1, del_flow_group); + tree_add_node(&fg->node, &ft->node); + /* Add node to group list */ + list_add(&fg->node.list, ft->node.children.prev); + unlock_ref_node(&ft->node); + + return fg; +} + +static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_rule *rule; + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return NULL; + + rule->node.type = FS_TYPE_FLOW_DEST; + memcpy(&rule->dest_attr, dest, sizeof(*dest)); + + return rule; +} + +/* fte should not be deleted while calling this function */ +static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, + struct mlx5_flow_group *fg, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_table *ft; + struct mlx5_flow_rule *rule; + int err; + + rule = alloc_rule(dest); + if (!rule) + return ERR_PTR(-ENOMEM); + + fs_get_obj(ft, fg->node.parent); + /* Add dest to dests list- added as first element after the head */ + tree_init_node(&rule->node, 1, del_rule); + list_add_tail(&rule->node.list, &fte->node.children); + fte->dests_size++; + if (fte->dests_size == 1) + err = mlx5_cmd_create_fte(get_dev(&ft->node), + ft, fg->id, fte); + else + err = mlx5_cmd_update_fte(get_dev(&ft->node), + ft, fg->id, fte); + if (err) + goto free_rule; + + fte->status |= FS_FTE_STATUS_EXISTING; + + return rule; + +free_rule: + list_del(&rule->node.list); + kfree(rule); + fte->dests_size--; + return ERR_PTR(err); +} + +/* Assumed fg is locked */ +static unsigned int get_free_fte_index(struct mlx5_flow_group *fg, + struct list_head **prev) +{ + struct fs_fte *fte; + unsigned int start = fg->start_index; + + if (prev) + *prev = &fg->node.children; + + /* assumed list is sorted by index */ + fs_for_each_fte(fte, fg) { + if (fte->index != start) + return start; + start++; + if (prev) + *prev = &fte->node.list; + } + + return start; +} + +/* prev is output, prev->next = new_fte */ +static struct fs_fte *create_fte(struct mlx5_flow_group *fg, + u32 *match_value, + u8 action, + u32 flow_tag, + struct list_head **prev) +{ + struct fs_fte *fte; + int index; + + index = get_free_fte_index(fg, prev); + fte = alloc_fte(action, flow_tag, match_value, index); + if (IS_ERR(fte)) + return fte; + + return fte; +} + +/* Assuming parent fg(flow table) is locked */ +static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg, + u32 *match_value, + u8 action, + u32 flow_tag, + struct mlx5_flow_destination *dest) +{ + struct fs_fte *fte; + struct mlx5_flow_rule *rule; + struct mlx5_flow_table *ft; + struct list_head *prev; + + lock_ref_node(&fg->node); + fs_for_each_fte(fte, fg) { + nested_lock_ref_node(&fte->node); + if (compare_match_value(&fg->mask, match_value, &fte->val) && + action == fte->action && flow_tag == fte->flow_tag) { + rule = add_rule_fte(fte, fg, dest); + unlock_ref_node(&fte->node); + if (IS_ERR(rule)) + goto unlock_fg; + else + goto add_rule; + } + unlock_ref_node(&fte->node); + } + fs_get_obj(ft, fg->node.parent); + if (fg->num_ftes >= fg->max_ftes) { + rule = ERR_PTR(-ENOSPC); + goto unlock_fg; + } + + fte = create_fte(fg, match_value, action, flow_tag, &prev); + if (IS_ERR(fte)) { + rule = (void *)fte; + goto unlock_fg; + } + tree_init_node(&fte->node, 0, del_fte); + rule = add_rule_fte(fte, fg, dest); + if (IS_ERR(rule)) { + kfree(fte); + goto unlock_fg; + } + + fg->num_ftes++; + + tree_add_node(&fte->node, &fg->node); + list_add(&fte->node.list, prev); +add_rule: + tree_add_node(&rule->node, &fte->node); +unlock_fg: + unlock_ref_node(&fg->node); + return rule; +} + +struct mlx5_flow_rule * +mlx5_add_flow_rule(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + u32 *match_criteria, + u32 *match_value, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_group *g; + struct mlx5_flow_rule *rule = ERR_PTR(-EINVAL); + + tree_get_node(&ft->node); + lock_ref_node(&ft->node); + fs_for_each_fg(g, ft) + if (compare_match_criteria(g->mask.match_criteria_enable, + match_criteria_enable, + g->mask.match_criteria, + match_criteria)) { + unlock_ref_node(&ft->node); + rule = add_rule_fg(g, match_value, + action, flow_tag, dest); + goto put; + } + unlock_ref_node(&ft->node); +put: + tree_put_node(&ft->node); + return rule; +} + +void mlx5_del_flow_rule(struct mlx5_flow_rule *rule) +{ + tree_remove_node(&rule->node); +} + +int mlx5_destroy_flow_table(struct mlx5_flow_table *ft) +{ + if (tree_remove_node(&ft->node)) + mlx5_core_warn(get_dev(&ft->node), "Flow table %d wasn't destroyed, refcount > 1\n", + ft->id); + + return 0; +} + +void mlx5_destroy_flow_group(struct mlx5_flow_group *fg) +{ + if (tree_remove_node(&fg->node)) + mlx5_core_warn(get_dev(&fg->node), "Flow group %d wasn't destroyed, refcount > 1\n", + fg->id); +} + +struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type type) +{ + struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns; + int prio; + static struct fs_prio *fs_prio; + struct mlx5_flow_namespace *ns; + + if (!root_ns) + return NULL; + + switch (type) { + case MLX5_FLOW_NAMESPACE_KERNEL: + prio = 0; + break; + case MLX5_FLOW_NAMESPACE_FDB: + if (dev->priv.fdb_root_ns) + return &dev->priv.fdb_root_ns->ns; + else + return NULL; + default: + return NULL; + } + + fs_prio = find_prio(&root_ns->ns, prio); + if (!fs_prio) + return NULL; + + ns = list_first_entry(&fs_prio->node.children, + typeof(*ns), + node.list); + + return ns; +} + +static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, + unsigned prio, int max_ft, + int start_level) +{ + struct fs_prio *fs_prio; + + fs_prio = kzalloc(sizeof(*fs_prio), GFP_KERNEL); + if (!fs_prio) + return ERR_PTR(-ENOMEM); + + fs_prio->node.type = FS_TYPE_PRIO; + tree_init_node(&fs_prio->node, 1, NULL); + tree_add_node(&fs_prio->node, &ns->node); + fs_prio->max_ft = max_ft; + fs_prio->prio = prio; + fs_prio->start_level = start_level; + list_add_tail(&fs_prio->node.list, &ns->node.children); + + return fs_prio; +} + +static struct mlx5_flow_namespace *fs_init_namespace(struct mlx5_flow_namespace + *ns) +{ + ns->node.type = FS_TYPE_NAMESPACE; + + return ns; +} + +static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) +{ + struct mlx5_flow_namespace *ns; + + ns = kzalloc(sizeof(*ns), GFP_KERNEL); + if (!ns) + return ERR_PTR(-ENOMEM); + + fs_init_namespace(ns); + tree_init_node(&ns->node, 1, NULL); + tree_add_node(&ns->node, &prio->node); + list_add_tail(&ns->node.list, &prio->node.children); + + return ns; +} + +static int init_root_tree_recursive(int max_ft_level, struct init_tree_node *init_node, + struct fs_node *fs_parent_node, + struct init_tree_node *init_parent_node, + int index) +{ + struct mlx5_flow_namespace *fs_ns; + struct fs_prio *fs_prio; + struct fs_node *base; + int i; + int err; + + if (init_node->type == FS_TYPE_PRIO) { + if (init_node->min_ft_level > max_ft_level) + return -ENOTSUPP; + + fs_get_obj(fs_ns, fs_parent_node); + fs_prio = fs_create_prio(fs_ns, index, init_node->max_ft, + init_node->start_level); + if (IS_ERR(fs_prio)) + return PTR_ERR(fs_prio); + base = &fs_prio->node; + } else if (init_node->type == FS_TYPE_NAMESPACE) { + fs_get_obj(fs_prio, fs_parent_node); + fs_ns = fs_create_namespace(fs_prio); + if (IS_ERR(fs_ns)) + return PTR_ERR(fs_ns); + base = &fs_ns->node; + } else { + return -EINVAL; + } + for (i = 0; i < init_node->ar_size; i++) { + err = init_root_tree_recursive(max_ft_level, + &init_node->children[i], base, + init_node, i); + if (err) + return err; + } + + return 0; +} + +static int init_root_tree(int max_ft_level, struct init_tree_node *init_node, + struct fs_node *fs_parent_node) +{ + int i; + struct mlx5_flow_namespace *fs_ns; + int err; + + fs_get_obj(fs_ns, fs_parent_node); + for (i = 0; i < init_node->ar_size; i++) { + err = init_root_tree_recursive(max_ft_level, + &init_node->children[i], + &fs_ns->node, + init_node, i); + if (err) + return err; + } + return 0; +} + +static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_core_dev *dev, + enum fs_flow_table_type + table_type) +{ + struct mlx5_flow_root_namespace *root_ns; + struct mlx5_flow_namespace *ns; + + /* Create the root namespace */ + root_ns = mlx5_vzalloc(sizeof(*root_ns)); + if (!root_ns) + return NULL; + + root_ns->dev = dev; + root_ns->table_type = table_type; + + ns = &root_ns->ns; + fs_init_namespace(ns); + tree_init_node(&ns->node, 1, NULL); + tree_add_node(&ns->node, NULL); + + return root_ns; +} + +static int init_root_ns(struct mlx5_core_dev *dev) +{ + int max_ft_level = MLX5_CAP_FLOWTABLE(dev, + flow_table_properties_nic_receive. + max_ft_level); + + dev->priv.root_ns = create_root_ns(dev, FS_FT_NIC_RX); + if (IS_ERR_OR_NULL(dev->priv.root_ns)) + goto cleanup; + + if (init_root_tree(max_ft_level, &root_fs, &dev->priv.root_ns->ns.node)) + goto cleanup; + + return 0; + +cleanup: + mlx5_cleanup_fs(dev); + return -ENOMEM; +} + +static void cleanup_single_prio_root_ns(struct mlx5_core_dev *dev, + struct mlx5_flow_root_namespace *root_ns) +{ + struct fs_node *prio; + + if (!root_ns) + return; + + if (!list_empty(&root_ns->ns.node.children)) { + prio = list_first_entry(&root_ns->ns.node.children, + struct fs_node, + list); + if (tree_remove_node(prio)) + mlx5_core_warn(dev, + "Flow steering priority wasn't destroyed, refcount > 1\n"); + } + if (tree_remove_node(&root_ns->ns.node)) + mlx5_core_warn(dev, + "Flow steering namespace wasn't destroyed, refcount > 1\n"); + root_ns = NULL; +} + +static void cleanup_root_ns(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns; + struct fs_prio *iter_prio; + + if (!MLX5_CAP_GEN(dev, nic_flow_table)) + return; + + if (!root_ns) + return; + + /* stage 1 */ + fs_for_each_prio(iter_prio, &root_ns->ns) { + struct fs_node *node; + struct mlx5_flow_namespace *iter_ns; + + fs_for_each_ns_or_ft(node, iter_prio) { + if (node->type == FS_TYPE_FLOW_TABLE) + continue; + fs_get_obj(iter_ns, node); + while (!list_empty(&iter_ns->node.children)) { + struct fs_prio *obj_iter_prio2; + struct fs_node *iter_prio2 = + list_first_entry(&iter_ns->node.children, + struct fs_node, + list); + + fs_get_obj(obj_iter_prio2, iter_prio2); + if (tree_remove_node(iter_prio2)) { + mlx5_core_warn(dev, + "Priority %d wasn't destroyed, refcount > 1\n", + obj_iter_prio2->prio); + return; + } + } + } + } + + /* stage 2 */ + fs_for_each_prio(iter_prio, &root_ns->ns) { + while (!list_empty(&iter_prio->node.children)) { + struct fs_node *iter_ns = + list_first_entry(&iter_prio->node.children, + struct fs_node, + list); + if (tree_remove_node(iter_ns)) { + mlx5_core_warn(dev, + "Namespace wasn't destroyed, refcount > 1\n"); + return; + } + } + } + + /* stage 3 */ + while (!list_empty(&root_ns->ns.node.children)) { + struct fs_prio *obj_prio_node; + struct fs_node *prio_node = + list_first_entry(&root_ns->ns.node.children, + struct fs_node, + list); + + fs_get_obj(obj_prio_node, prio_node); + if (tree_remove_node(prio_node)) { + mlx5_core_warn(dev, + "Priority %d wasn't destroyed, refcount > 1\n", + obj_prio_node->prio); + return; + } + } + + if (tree_remove_node(&root_ns->ns.node)) { + mlx5_core_warn(dev, + "root namespace wasn't destroyed, refcount > 1\n"); + return; + } + + dev->priv.root_ns = NULL; +} + +void mlx5_cleanup_fs(struct mlx5_core_dev *dev) +{ + cleanup_root_ns(dev); + cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns); +} + +static int init_fdb_root_ns(struct mlx5_core_dev *dev) +{ + struct fs_prio *prio; + + dev->priv.fdb_root_ns = create_root_ns(dev, FS_FT_FDB); + if (!dev->priv.fdb_root_ns) + return -ENOMEM; + + /* Create single prio */ + prio = fs_create_prio(&dev->priv.fdb_root_ns->ns, 0, 1, 0); + if (IS_ERR(prio)) { + cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns); + return PTR_ERR(prio); + } else { + return 0; + } +} + +int mlx5_init_fs(struct mlx5_core_dev *dev) +{ + int err = 0; + + if (MLX5_CAP_GEN(dev, nic_flow_table)) { + err = init_root_ns(dev); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + err = init_fdb_root_ns(dev); + if (err) + cleanup_root_ns(dev); + } + + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h new file mode 100644 index 0000000000000..4ebb97fd55445 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -0,0 +1,155 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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 AUTHORS OR COPYRIGHT HOLDERS + * 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. + */ + +#ifndef _MLX5_FS_CORE_ +#define _MLX5_FS_CORE_ + +#include <linux/mlx5/fs.h> + +enum fs_node_type { + FS_TYPE_NAMESPACE, + FS_TYPE_PRIO, + FS_TYPE_FLOW_TABLE, + FS_TYPE_FLOW_GROUP, + FS_TYPE_FLOW_ENTRY, + FS_TYPE_FLOW_DEST +}; + +enum fs_flow_table_type { + FS_FT_NIC_RX = 0x0, + FS_FT_FDB = 0X4, +}; + +enum fs_fte_status { + FS_FTE_STATUS_EXISTING = 1UL << 0, +}; + +struct fs_node { + struct list_head list; + struct list_head children; + enum fs_node_type type; + struct fs_node *parent; + struct fs_node *root; + /* lock the node for writing and traversing */ + struct mutex lock; + atomic_t refcount; + void (*remove_func)(struct fs_node *); +}; + +struct mlx5_flow_rule { + struct fs_node node; + struct mlx5_flow_destination dest_attr; +}; + +/* Type of children is mlx5_flow_group */ +struct mlx5_flow_table { + struct fs_node node; + u32 id; + unsigned int max_fte; + unsigned int level; + enum fs_flow_table_type type; +}; + +/* Type of children is mlx5_flow_rule */ +struct fs_fte { + struct fs_node node; + u32 val[MLX5_ST_SZ_DW(fte_match_param)]; + u32 dests_size; + u32 flow_tag; + u32 index; + u32 action; + enum fs_fte_status status; +}; + +/* Type of children is mlx5_flow_table/namespace */ +struct fs_prio { + struct fs_node node; + unsigned int max_ft; + unsigned int start_level; + unsigned int prio; + unsigned int num_ft; +}; + +/* Type of children is fs_prio */ +struct mlx5_flow_namespace { + /* parent == NULL => root ns */ + struct fs_node node; +}; + +struct mlx5_flow_group_mask { + u8 match_criteria_enable; + u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; +}; + +/* Type of children is fs_fte */ +struct mlx5_flow_group { + struct fs_node node; + struct mlx5_flow_group_mask mask; + u32 start_index; + u32 max_ftes; + u32 num_ftes; + u32 id; +}; + +struct mlx5_flow_root_namespace { + struct mlx5_flow_namespace ns; + enum fs_flow_table_type table_type; + struct mlx5_core_dev *dev; +}; + +int mlx5_init_fs(struct mlx5_core_dev *dev); +void mlx5_cleanup_fs(struct mlx5_core_dev *dev); + +#define fs_get_obj(v, _node) {v = container_of((_node), typeof(*v), node); } + +#define fs_list_for_each_entry(pos, root) \ + list_for_each_entry(pos, root, node.list) + +#define fs_for_each_ns_or_ft_reverse(pos, prio) \ + list_for_each_entry_reverse(pos, &(prio)->node.children, list) + +#define fs_for_each_ns_or_ft(pos, prio) \ + list_for_each_entry(pos, (&(prio)->node.children), list) + +#define fs_for_each_prio(pos, ns) \ + fs_list_for_each_entry(pos, &(ns)->node.children) + +#define fs_for_each_fg(pos, ft) \ + fs_list_for_each_entry(pos, &(ft)->node.children) + +#define fs_for_each_fte(pos, fg) \ + fs_list_for_each_entry(pos, &(fg)->node.children) + +#define fs_for_each_dst(pos, fte) \ + fs_list_for_each_entry(pos, &(fte)->node.children) + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 1c9f9a54a8733..aa1ab47023852 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -173,7 +173,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, vport_group_manager)) { + if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH, HCA_CAP_OPMOD_GET_CUR); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c6de3240f76f2..67676cf0d507b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -49,6 +49,7 @@ #include <linux/delay.h> #include <linux/mlx5/mlx5_ifc.h> #include "mlx5_core.h" +#include "fs_core.h" #ifdef CONFIG_MLX5_CORE_EN #include "eswitch.h" #endif @@ -503,6 +504,19 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id) return mlx5_cmd_status_to_err_v2(out); } +cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev) +{ + u32 timer_h, timer_h1, timer_l; + + timer_h = ioread32be(&dev->iseg->internal_timer_h); + timer_l = ioread32be(&dev->iseg->internal_timer_l); + timer_h1 = ioread32be(&dev->iseg->internal_timer_h); + if (timer_h != timer_h1) /* wrap around */ + timer_l = ioread32be(&dev->iseg->internal_timer_l); + + return (cycle_t)timer_l | (cycle_t)timer_h1 << 32; +} + static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) { struct mlx5_priv *priv = &mdev->priv; @@ -1055,6 +1069,11 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_srq_table(dev); mlx5_init_mr_table(dev); + err = mlx5_init_fs(dev); + if (err) { + dev_err(&pdev->dev, "Failed to init flow steering\n"); + goto err_fs; + } #ifdef CONFIG_MLX5_CORE_EN err = mlx5_eswitch_init(dev); if (err) { @@ -1093,6 +1112,8 @@ err_sriov: mlx5_eswitch_cleanup(dev->priv.eswitch); #endif err_reg_dev: + mlx5_cleanup_fs(dev); +err_fs: mlx5_cleanup_mr_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); @@ -1165,6 +1186,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_eswitch_cleanup(dev->priv.eswitch); #endif + mlx5_cleanup_fs(dev); mlx5_cleanup_mr_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index bee7da822dfe2..0336847ec9a16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -65,6 +65,9 @@ do { \ (__dev)->priv.name, __func__, __LINE__, current->pid, \ ##__VA_ARGS__) +#define mlx5_core_info(__dev, format, ...) \ + dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__) + enum { MLX5_CMD_DATA, /* print command payload only */ MLX5_CMD_TIME, /* print command execution time */ @@ -95,6 +98,7 @@ int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs); int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id); int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id); int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); +cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev); void mlx5e_init(void); void mlx5e_cleanup(void); diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index ec8caf8fedc63..ce26adcb49881 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -41,7 +41,7 @@ config MLXSW_SWITCHX2 config MLXSW_SPECTRUM tristate "Mellanox Technologies Spectrum support" - depends on MLXSW_CORE && NET_SWITCHDEV + depends on MLXSW_CORE && NET_SWITCHDEV && VLAN_8021Q default m ---help--- This driver supports Mellanox Technologies Spectrum Ethernet diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index af8a48b3b3ad6..22379eb8e9245 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -855,7 +855,6 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, err_debugfs_init: mlxsw_core->driver->fini(mlxsw_core->driver_priv); err_driver_init: - mlxsw_hwmon_fini(mlxsw_core->hwmon); err_hwmon_init: mlxsw_emad_fini(mlxsw_core); err_emad_init: @@ -878,7 +877,6 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core) mlxsw_core_debugfs_fini(mlxsw_core); mlxsw_core->driver->fini(mlxsw_core->driver_priv); - mlxsw_hwmon_fini(mlxsw_core->hwmon); mlxsw_emad_fini(mlxsw_core); mlxsw_core->bus->fini(mlxsw_core->bus_priv); kfree(mlxsw_core->lag.mapping); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 4833fb33ce07a..a01723600f0ae 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -239,10 +239,6 @@ static inline int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, return 0; } -static inline void mlxsw_hwmon_fini(struct mlxsw_hwmon *mlxsw_hwmon) -{ -} - #endif #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 4dad146b41ae5..5b9364f4837df 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -49,7 +49,7 @@ struct mlxsw_hwmon_attr { struct device_attribute dev_attr; struct mlxsw_hwmon *hwmon; unsigned int type_index; - char name[16]; + char name[32]; }; struct mlxsw_hwmon { @@ -107,6 +107,32 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev, return sprintf(buf, "%u\n", temp_max); } +static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char mtmp_pl[MLXSW_REG_MTMP_LEN]; + unsigned long val; + int err; + + err = kstrtoul(buf, 10, &val); + if (err) + return err; + if (val != 1) + return -EINVAL; + + mlxsw_reg_mtmp_pack(mtmp_pl, mlwsw_hwmon_attr->type_index, true, true); + err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); + if (err) { + dev_err(mlxsw_hwmon->bus_info->dev, "Failed to reset temp sensor history\n"); + return err; + } + return err ? err : len; +} + static ssize_t mlxsw_hwmon_fan_rpm_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -169,12 +195,13 @@ static ssize_t mlxsw_hwmon_pwm_store(struct device *dev, dev_err(mlxsw_hwmon->bus_info->dev, "Failed to write PWM\n"); return err; } - return err ? err : len; + return len; } enum mlxsw_hwmon_attr_type { MLXSW_HWMON_ATTR_TYPE_TEMP, MLXSW_HWMON_ATTR_TYPE_TEMP_MAX, + MLXSW_HWMON_ATTR_TYPE_TEMP_RST, MLXSW_HWMON_ATTR_TYPE_FAN_RPM, MLXSW_HWMON_ATTR_TYPE_PWM, }; @@ -201,6 +228,12 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), "temp%u_highest", num + 1); break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_RST: + mlxsw_hwmon_attr->dev_attr.store = mlxsw_hwmon_temp_rst_store; + mlxsw_hwmon_attr->dev_attr.attr.mode = S_IWUSR; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_reset_history", num + 1); + break; case MLXSW_HWMON_ATTR_TYPE_FAN_RPM: mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_fan_rpm_show; mlxsw_hwmon_attr->dev_attr.attr.mode = S_IRUGO; @@ -242,7 +275,7 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon) } sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl); for (i = 0; i < sensor_count; i++) { - mlxsw_reg_mtmp_pack(mtmp_pl, 0, true, true); + mlxsw_reg_mtmp_pack(mtmp_pl, i, true, true); err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); if (err) { @@ -254,6 +287,8 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon) MLXSW_HWMON_ATTR_TYPE_TEMP, i, i); mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_TEMP_MAX, i, i); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_RST, i, i); } return 0; } @@ -299,7 +334,8 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, struct device *hwmon_dev; int err; - mlxsw_hwmon = kzalloc(sizeof(*mlxsw_hwmon), GFP_KERNEL); + mlxsw_hwmon = devm_kzalloc(mlxsw_bus_info->dev, sizeof(*mlxsw_hwmon), + GFP_KERNEL); if (!mlxsw_hwmon) return -ENOMEM; mlxsw_hwmon->core = mlxsw_core; @@ -332,11 +368,5 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, err_hwmon_register: err_fans_init: err_temp_init: - kfree(mlxsw_hwmon); return err; } - -void mlxsw_hwmon_fini(struct mlxsw_hwmon *mlxsw_hwmon) -{ - kfree(mlxsw_hwmon); -} diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index d2102e572b1d5..c071077aafbdb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -384,7 +384,7 @@ static int mlxsw_pci_sdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, /* Set CQ of same number of this SDQ. */ mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, q->num); - mlxsw_cmd_mbox_sw2hw_dq_sdq_tclass_set(mbox, 7); + mlxsw_cmd_mbox_sw2hw_dq_sdq_tclass_set(mbox, 3); mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */ for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 4e4e4dcf054ff..66d851d4dfb4d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -396,7 +396,7 @@ static inline void mlxsw_reg_sfd_rec_pack(char *payload, int rec_index, static inline void mlxsw_reg_sfd_uc_pack(char *payload, int rec_index, enum mlxsw_reg_sfd_rec_policy policy, - const char *mac, u16 vid, + const char *mac, u16 fid_vid, enum mlxsw_reg_sfd_rec_action action, u8 local_port) { @@ -404,16 +404,16 @@ static inline void mlxsw_reg_sfd_uc_pack(char *payload, int rec_index, MLXSW_REG_SFD_REC_TYPE_UNICAST, policy, mac, action); mlxsw_reg_sfd_uc_sub_port_set(payload, rec_index, 0); - mlxsw_reg_sfd_uc_fid_vid_set(payload, rec_index, vid); + mlxsw_reg_sfd_uc_fid_vid_set(payload, rec_index, fid_vid); mlxsw_reg_sfd_uc_system_port_set(payload, rec_index, local_port); } static inline void mlxsw_reg_sfd_uc_unpack(char *payload, int rec_index, - char *mac, u16 *p_vid, + char *mac, u16 *p_fid_vid, u8 *p_local_port) { mlxsw_reg_sfd_rec_mac_memcpy_from(payload, rec_index, mac); - *p_vid = mlxsw_reg_sfd_uc_fid_vid_get(payload, rec_index); + *p_fid_vid = mlxsw_reg_sfd_uc_fid_vid_get(payload, rec_index); *p_local_port = mlxsw_reg_sfd_uc_system_port_get(payload, rec_index); } @@ -438,6 +438,13 @@ MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_sub_port, MLXSW_REG_SFD_BASE_LEN, 16, 8, MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_fid_vid, MLXSW_REG_SFD_BASE_LEN, 0, 16, MLXSW_REG_SFD_REC_LEN, 0x08, false); +/* reg_sfd_uc_lag_lag_vid + * Indicates VID in case of vFIDs. Reserved for FIDs. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_lag_vid, MLXSW_REG_SFD_BASE_LEN, 16, 12, + MLXSW_REG_SFD_REC_LEN, 0x0C, false); + /* reg_sfd_uc_lag_lag_id * LAG Identifier - pointer into the LAG descriptor table. * Access: RW @@ -448,15 +455,16 @@ MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_lag_id, MLXSW_REG_SFD_BASE_LEN, 0, 10, static inline void mlxsw_reg_sfd_uc_lag_pack(char *payload, int rec_index, enum mlxsw_reg_sfd_rec_policy policy, - const char *mac, u16 vid, - enum mlxsw_reg_sfd_rec_action action, + const char *mac, u16 fid_vid, + enum mlxsw_reg_sfd_rec_action action, u16 lag_vid, u16 lag_id) { mlxsw_reg_sfd_rec_pack(payload, rec_index, MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG, policy, mac, action); mlxsw_reg_sfd_uc_lag_sub_port_set(payload, rec_index, 0); - mlxsw_reg_sfd_uc_lag_fid_vid_set(payload, rec_index, vid); + mlxsw_reg_sfd_uc_lag_fid_vid_set(payload, rec_index, fid_vid); + mlxsw_reg_sfd_uc_lag_lag_vid_set(payload, rec_index, lag_vid); mlxsw_reg_sfd_uc_lag_lag_id_set(payload, rec_index, lag_id); } @@ -2684,7 +2692,7 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp, *p_temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); } if (p_max_temp) { - temp = mlxsw_reg_mtmp_temperature_get(payload); + temp = mlxsw_reg_mtmp_max_temperature_get(payload); *p_max_temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); } if (sensor_name) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3ec07b9a458df..74ff0110e899c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -48,6 +48,7 @@ #include <linux/workqueue.h> #include <linux/jiffies.h> #include <linux/bitops.h> +#include <linux/list.h> #include <net/switchdev.h> #include <generated/utsrelease.h> @@ -186,33 +187,6 @@ static int mlxsw_sp_port_oper_status_get(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } -static int mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, u16 vfid) -{ - char sfmr_pl[MLXSW_REG_SFMR_LEN]; - int err; - - mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, - MLXSW_SP_VFID_BASE + vfid, 0); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); - - if (err) - return err; - - set_bit(vfid, mlxsw_sp->active_vfids); - return 0; -} - -static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, u16 vfid) -{ - char sfmr_pl[MLXSW_REG_SFMR_LEN]; - - clear_bit(vfid, mlxsw_sp->active_vfids); - - mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, - MLXSW_SP_VFID_BASE + vfid, 0); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); -} - static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port, unsigned char *addr) { @@ -549,12 +523,132 @@ static int mlxsw_sp_port_vlan_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } +static struct mlxsw_sp_vfid * +mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, u16 vid) +{ + struct mlxsw_sp_vfid *vfid; + + list_for_each_entry(vfid, &mlxsw_sp->port_vfids.list, list) { + if (vfid->vid == vid) + return vfid; + } + + return NULL; +} + +static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp) +{ + return find_first_zero_bit(mlxsw_sp->port_vfids.mapped, + MLXSW_SP_VFID_PORT_MAX); +} + +static int __mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, u16 vfid) +{ + u16 fid = mlxsw_sp_vfid_to_fid(vfid); + char sfmr_pl[MLXSW_REG_SFMR_LEN]; + + mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); +} + +static void __mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, u16 vfid) +{ + u16 fid = mlxsw_sp_vfid_to_fid(vfid); + char sfmr_pl[MLXSW_REG_SFMR_LEN]; + + mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, fid, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); +} + +static struct mlxsw_sp_vfid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, + u16 vid) +{ + struct device *dev = mlxsw_sp->bus_info->dev; + struct mlxsw_sp_vfid *vfid; + u16 n_vfid; + int err; + + n_vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp); + if (n_vfid == MLXSW_SP_VFID_PORT_MAX) { + dev_err(dev, "No available vFIDs\n"); + return ERR_PTR(-ERANGE); + } + + err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid); + if (err) { + dev_err(dev, "Failed to create vFID=%d\n", n_vfid); + return ERR_PTR(err); + } + + vfid = kzalloc(sizeof(*vfid), GFP_KERNEL); + if (!vfid) + goto err_allocate_vfid; + + vfid->vfid = n_vfid; + vfid->vid = vid; + + list_add(&vfid->list, &mlxsw_sp->port_vfids.list); + set_bit(n_vfid, mlxsw_sp->port_vfids.mapped); + + return vfid; + +err_allocate_vfid: + __mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid); + return ERR_PTR(-ENOMEM); +} + +static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vfid *vfid) +{ + clear_bit(vfid->vfid, mlxsw_sp->port_vfids.mapped); + list_del(&vfid->list); + + __mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid); + + kfree(vfid); +} + +static struct mlxsw_sp_port * +mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_vfid *vfid) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = kzalloc(sizeof(*mlxsw_sp_vport), GFP_KERNEL); + if (!mlxsw_sp_vport) + return NULL; + + /* dev will be set correctly after the VLAN device is linked + * with the real device. In case of bridge SELF invocation, dev + * will remain as is. + */ + mlxsw_sp_vport->dev = mlxsw_sp_port->dev; + mlxsw_sp_vport->mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + mlxsw_sp_vport->local_port = mlxsw_sp_port->local_port; + mlxsw_sp_vport->stp_state = BR_STATE_FORWARDING; + mlxsw_sp_vport->lagged = mlxsw_sp_port->lagged; + mlxsw_sp_vport->lag_id = mlxsw_sp_port->lag_id; + mlxsw_sp_vport->vport.vfid = vfid; + mlxsw_sp_vport->vport.vid = vfid->vid; + + list_add(&mlxsw_sp_vport->vport.list, &mlxsw_sp_port->vports_list); + + return mlxsw_sp_vport; +} + +static void mlxsw_sp_port_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + list_del(&mlxsw_sp_vport->vport.list); + kfree(mlxsw_sp_vport); +} + int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char *sftr_pl; + struct mlxsw_sp_port *mlxsw_sp_vport; + struct mlxsw_sp_vfid *vfid; int err; /* VLAN 0 is added to HW filter when device goes up, but it is @@ -563,100 +657,105 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, if (!vid) return 0; - if (test_bit(vid, mlxsw_sp_port->active_vfids)) { + if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid)) { netdev_warn(dev, "VID=%d already configured\n", vid); return 0; } - if (!test_bit(vid, mlxsw_sp->active_vfids)) { - err = mlxsw_sp_vfid_create(mlxsw_sp, vid); - if (err) { - netdev_err(dev, "Failed to create vFID=%d\n", - MLXSW_SP_VFID_BASE + vid); - return err; + vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid); + if (!vfid) { + vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid); + if (IS_ERR(vfid)) { + netdev_err(dev, "Failed to create vFID for VID=%d\n", + vid); + return PTR_ERR(vfid); } + } - sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); - if (!sftr_pl) { - err = -ENOMEM; - goto err_flood_table_alloc; - } - mlxsw_reg_sftr_pack(sftr_pl, 0, vid, - MLXSW_REG_SFGC_TABLE_TYPE_FID, 0, - MLXSW_PORT_CPU_PORT, true); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); - kfree(sftr_pl); + mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vfid); + if (!mlxsw_sp_vport) { + netdev_err(dev, "Failed to create vPort for VID=%d\n", vid); + err = -ENOMEM; + goto err_port_vport_create; + } + + if (!vfid->nr_vports) { + err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, + true, false); if (err) { - netdev_err(dev, "Failed to configure flood table\n"); - goto err_flood_table_config; + netdev_err(dev, "Failed to setup flooding for vFID=%d\n", + vfid->vfid); + goto err_vport_flood_set; } } - /* In case we fail in the following steps, we intentionally do not - * destroy the associated vFID. - */ - /* When adding the first VLAN interface on a bridged port we need to * transition all the active 802.1Q bridge VLANs to use explicit * {Port, VID} to FID mappings and set the port's mode to Virtual mode. */ - if (!mlxsw_sp_port->nr_vfids) { + if (list_is_singular(&mlxsw_sp_port->vports_list)) { err = mlxsw_sp_port_vp_mode_trans(mlxsw_sp_port); if (err) { netdev_err(dev, "Failed to set to Virtual mode\n"); - return err; + goto err_port_vp_mode_trans; } } - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - true, MLXSW_SP_VFID_BASE + vid, vid); + true, + mlxsw_sp_vfid_to_fid(vfid->vfid), + vid); if (err) { netdev_err(dev, "Failed to map {Port, VID=%d} to vFID=%d\n", - vid, MLXSW_SP_VFID_BASE + vid); + vid, vfid->vfid); goto err_port_vid_to_fid_set; } - err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, false); + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); if (err) { netdev_err(dev, "Failed to disable learning for VID=%d\n", vid); goto err_port_vid_learning_set; } - err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true, false); + err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, false); if (err) { netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", vid); goto err_port_add_vid; } - err = mlxsw_sp_port_stp_state_set(mlxsw_sp_port, vid, + err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid, MLXSW_REG_SPMS_STATE_FORWARDING); if (err) { netdev_err(dev, "Failed to set STP state for VID=%d\n", vid); goto err_port_stp_state_set; } - mlxsw_sp_port->nr_vfids++; - set_bit(vid, mlxsw_sp_port->active_vfids); + vfid->nr_vports++; return 0; -err_flood_table_config: -err_flood_table_alloc: - mlxsw_sp_vfid_destroy(mlxsw_sp, vid); - return err; - err_port_stp_state_set: - mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false); + mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); err_port_add_vid: - mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true); + mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); err_port_vid_learning_set: - mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, + mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false, - MLXSW_SP_VFID_BASE + vid, vid); + mlxsw_sp_vfid_to_fid(vfid->vfid), vid); err_port_vid_to_fid_set: - mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); + if (list_is_singular(&mlxsw_sp_port->vports_list)) + mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); +err_port_vp_mode_trans: + if (!vfid->nr_vports) + mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, + false); +err_vport_flood_set: + mlxsw_sp_port_vport_destroy(mlxsw_sp_vport); +err_port_vport_create: + if (!vfid->nr_vports) + mlxsw_sp_vfid_destroy(mlxsw_sp, vfid); return err; } @@ -664,6 +763,8 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp_port *mlxsw_sp_vport; + struct mlxsw_sp_vfid *vfid; int err; /* VLAN 0 is removed from HW filter when device goes down, but @@ -672,38 +773,42 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, if (!vid) return 0; - if (!test_bit(vid, mlxsw_sp_port->active_vfids)) { + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (!mlxsw_sp_vport) { netdev_warn(dev, "VID=%d does not exist\n", vid); return 0; } - err = mlxsw_sp_port_stp_state_set(mlxsw_sp_port, vid, + vfid = mlxsw_sp_vport->vport.vfid; + + err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid, MLXSW_REG_SPMS_STATE_DISCARDING); if (err) { netdev_err(dev, "Failed to set STP state for VID=%d\n", vid); return err; } - err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false); + err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); if (err) { netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", vid); return err; } - err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true); + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); if (err) { netdev_err(dev, "Failed to enable learning for VID=%d\n", vid); return err; } - err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, - false, MLXSW_SP_VFID_BASE + vid, + false, + mlxsw_sp_vfid_to_fid(vfid->vfid), vid); if (err) { netdev_err(dev, "Failed to invalidate {Port, VID=%d} to vFID=%d mapping\n", - vid, MLXSW_SP_VFID_BASE + vid); + vid, vfid->vfid); return err; } @@ -711,7 +816,7 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, * transition all active 802.1Q bridge VLANs to use VID to FID * mappings and set port's mode to VLAN mode. */ - if (mlxsw_sp_port->nr_vfids == 1) { + if (list_is_singular(&mlxsw_sp_port->vports_list)) { err = mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); if (err) { netdev_err(dev, "Failed to set to VLAN mode\n"); @@ -719,8 +824,12 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, } } - mlxsw_sp_port->nr_vfids--; - clear_bit(vid, mlxsw_sp_port->active_vfids); + vfid->nr_vports--; + mlxsw_sp_port_vport_destroy(mlxsw_sp_vport); + + /* Destroy the vFID if no vPorts are assigned to it anymore. */ + if (!vfid->nr_vports) + mlxsw_sp_vfid_destroy(mlxsw_sp_port->mlxsw_sp, vfid); return 0; } @@ -1245,6 +1354,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) struct mlxsw_sp_port *mlxsw_sp_port; struct net_device *dev; bool usable; + size_t bytes; int err; dev = alloc_etherdev(sizeof(struct mlxsw_sp_port)); @@ -1254,10 +1364,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_sp_port->dev = dev; mlxsw_sp_port->mlxsw_sp = mlxsw_sp; mlxsw_sp_port->local_port = local_port; - mlxsw_sp_port->learning = 1; - mlxsw_sp_port->learning_sync = 1; - mlxsw_sp_port->uc_flood = 1; - mlxsw_sp_port->pvid = 1; + bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE); + mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL); + if (!mlxsw_sp_port->active_vlans) { + err = -ENOMEM; + goto err_port_active_vlans_alloc; + } + INIT_LIST_HEAD(&mlxsw_sp_port->vports_list); mlxsw_sp_port->pcpu_stats = netdev_alloc_pcpu_stats(struct mlxsw_sp_port_pcpu_stats); @@ -1359,16 +1472,27 @@ err_port_module_check: err_dev_addr_init: free_percpu(mlxsw_sp_port->pcpu_stats); err_alloc_stats: + kfree(mlxsw_sp_port->active_vlans); +err_port_active_vlans_alloc: free_netdev(dev); return err; } -static void mlxsw_sp_vfids_fini(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port) { - u16 vfid; + struct net_device *dev = mlxsw_sp_port->dev; + struct mlxsw_sp_port *mlxsw_sp_vport, *tmp; - for_each_set_bit(vfid, mlxsw_sp->active_vfids, VLAN_N_VID) - mlxsw_sp_vfid_destroy(mlxsw_sp, vfid); + list_for_each_entry_safe(mlxsw_sp_vport, tmp, + &mlxsw_sp_port->vports_list, vport.list) { + u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + + /* vPorts created for VLAN devices should already be gone + * by now, since we unregistered the port netdev. + */ + WARN_ON(is_vlan_dev(mlxsw_sp_vport->dev)); + mlxsw_sp_port_kill_vid(dev, 0, vid); + } } static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) @@ -1377,10 +1501,11 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) if (!mlxsw_sp_port) return; - mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ + mlxsw_sp_port_vports_fini(mlxsw_sp_port); mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); free_percpu(mlxsw_sp_port->pcpu_stats); + kfree(mlxsw_sp_port->active_vlans); free_netdev(mlxsw_sp_port->dev); } @@ -1662,16 +1787,15 @@ static int __mlxsw_sp_flood_init(struct mlxsw_core *mlxsw_core, enum mlxsw_sp_flood_table flood_table; char sfgc_pl[MLXSW_REG_SFGC_LEN]; - if (bridge_type == MLXSW_REG_SFGC_BRIDGE_TYPE_VFID) { + if (bridge_type == MLXSW_REG_SFGC_BRIDGE_TYPE_VFID) table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID; - flood_table = 0; - } else { + else table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; - if (type == MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST) - flood_table = MLXSW_SP_FLOOD_TABLE_UC; - else - flood_table = MLXSW_SP_FLOOD_TABLE_BM; - } + + if (type == MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST) + flood_table = MLXSW_SP_FLOOD_TABLE_UC; + else + flood_table = MLXSW_SP_FLOOD_TABLE_BM; mlxsw_reg_sfgc_pack(sfgc_pl, type, bridge_type, table_type, flood_table); @@ -1682,9 +1806,6 @@ static int mlxsw_sp_flood_init(struct mlxsw_sp *mlxsw_sp) { int type, err; - /* For non-offloaded netdevs, flood all traffic types to CPU - * port. - */ for (type = 0; type < MLXSW_REG_SFGC_TYPE_MAX; type++) { if (type == MLXSW_REG_SFGC_TYPE_RESERVED) continue; @@ -1693,15 +1814,6 @@ static int mlxsw_sp_flood_init(struct mlxsw_sp *mlxsw_sp) MLXSW_REG_SFGC_BRIDGE_TYPE_VFID); if (err) return err; - } - - /* For bridged ports, use one flooding table for unknown unicast - * traffic and a second table for unregistered multicast and - * broadcast. - */ - for (type = 0; type < MLXSW_REG_SFGC_TYPE_MAX; type++) { - if (type == MLXSW_REG_SFGC_TYPE_RESERVED) - continue; err = __mlxsw_sp_flood_init(mlxsw_sp->core, type, MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID); @@ -1736,6 +1848,8 @@ static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core, mlxsw_sp->core = mlxsw_core; mlxsw_sp->bus_info = mlxsw_bus_info; + INIT_LIST_HEAD(&mlxsw_sp->port_vfids.list); + INIT_LIST_HEAD(&mlxsw_sp->br_vfids.list); err = mlxsw_sp_base_mac_get(mlxsw_sp); if (err) { @@ -1746,7 +1860,7 @@ static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core, err = mlxsw_sp_ports_create(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); - goto err_ports_create; + return err; } err = mlxsw_sp_event_register(mlxsw_sp, MLXSW_TRAP_ID_PUDE); @@ -1796,8 +1910,6 @@ err_rx_listener_register: mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE); err_event_register: mlxsw_sp_ports_remove(mlxsw_sp); -err_ports_create: - mlxsw_sp_vfids_fini(mlxsw_sp); return err; } @@ -1809,7 +1921,6 @@ static void mlxsw_sp_fini(void *priv) mlxsw_sp_traps_fini(mlxsw_sp); mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE); mlxsw_sp_ports_remove(mlxsw_sp); - mlxsw_sp_vfids_fini(mlxsw_sp); } static struct mlxsw_config_profile mlxsw_sp_config_profile = { @@ -1834,8 +1945,8 @@ static struct mlxsw_config_profile mlxsw_sp_config_profile = { .flood_mode = 3, .max_fid_offset_flood_tables = 2, .fid_offset_flood_table_size = VLAN_N_VID - 1, - .max_fid_flood_tables = 1, - .fid_flood_table_size = VLAN_N_VID, + .max_fid_flood_tables = 2, + .fid_flood_table_size = MLXSW_SP_VFID_MAX, .used_max_ib_mc = 1, .max_ib_mc = 0, .used_max_pkey = 1, @@ -1876,24 +1987,29 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) */ err = mlxsw_sp_port_kill_vid(dev, 0, 1); if (err) - netdev_err(dev, "Failed to remove VID 1\n"); + return err; - return err; + mlxsw_sp_port->learning = 1; + mlxsw_sp_port->learning_sync = 1; + mlxsw_sp_port->uc_flood = 1; + mlxsw_sp_port->bridged = 1; + + return 0; } static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port) { struct net_device *dev = mlxsw_sp_port->dev; - int err; + + mlxsw_sp_port->learning = 0; + mlxsw_sp_port->learning_sync = 0; + mlxsw_sp_port->uc_flood = 0; + mlxsw_sp_port->bridged = 0; /* Add implicit VLAN interface in the device, so that untagged * packets will be classified to the default vFID. */ - err = mlxsw_sp_port_add_vid(dev, 0, 1); - if (err) - netdev_err(dev, "Failed to add VID 1\n"); - - return err; + return mlxsw_sp_port_add_vid(dev, 0, 1); } static bool mlxsw_sp_master_bridge_check(struct mlxsw_sp *mlxsw_sp, @@ -2091,7 +2207,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id); if (err) return err; - mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); + err = mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); if (err) return err; @@ -2147,6 +2263,54 @@ static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled); } +static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *br_dev); + +static int mlxsw_sp_port_vlan_link(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *vlan_dev) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + u16 vid = vlan_dev_vlan_id(vlan_dev); + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (!mlxsw_sp_vport) { + WARN_ON(!mlxsw_sp_vport); + return -EINVAL; + } + + mlxsw_sp_vport->dev = vlan_dev; + + return 0; +} + +static int mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port, + struct net_device *vlan_dev) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + u16 vid = vlan_dev_vlan_id(vlan_dev); + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (!mlxsw_sp_vport) { + WARN_ON(!mlxsw_sp_vport); + return -EINVAL; + } + + /* When removing a VLAN device while still bridged we should first + * remove it from the bridge, as we receive the bridge's notification + * when the vPort is already gone. + */ + if (mlxsw_sp_vport->bridged) { + struct net_device *br_dev; + + br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev); + } + + mlxsw_sp_vport->dev = mlxsw_sp_port->dev; + + return 0; +} + static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, unsigned long event, void *ptr) { @@ -2176,21 +2340,37 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; - if (!info->master) - break; - if (netif_is_bridge_master(upper_dev)) { + if (is_vlan_dev(upper_dev)) { + if (info->linking) { + err = mlxsw_sp_port_vlan_link(mlxsw_sp_port, + upper_dev); + if (err) { + netdev_err(dev, "Failed to link VLAN device\n"); + return NOTIFY_BAD; + } + } else { + err = mlxsw_sp_port_vlan_unlink(mlxsw_sp_port, + upper_dev); + if (err) { + netdev_err(dev, "Failed to unlink VLAN device\n"); + return NOTIFY_BAD; + } + } + } else if (netif_is_bridge_master(upper_dev)) { if (info->linking) { err = mlxsw_sp_port_bridge_join(mlxsw_sp_port); - if (err) + if (err) { netdev_err(dev, "Failed to join bridge\n"); + return NOTIFY_BAD; + } mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev); - mlxsw_sp_port->bridged = 1; } else { err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port); - if (err) - netdev_err(dev, "Failed to leave bridge\n"); - mlxsw_sp_port->bridged = 0; mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev); + if (err) { + netdev_err(dev, "Failed to leave bridge\n"); + return NOTIFY_BAD; + } } } else if (netif_is_lag_master(upper_dev)) { if (info->linking) { @@ -2271,6 +2451,370 @@ static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev, return NOTIFY_DONE; } +static struct mlxsw_sp_vfid * +mlxsw_sp_br_vfid_find(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *br_dev) +{ + struct mlxsw_sp_vfid *vfid; + + list_for_each_entry(vfid, &mlxsw_sp->br_vfids.list, list) { + if (vfid->br_dev == br_dev) + return vfid; + } + + return NULL; +} + +static u16 mlxsw_sp_vfid_to_br_vfid(u16 vfid) +{ + return vfid - MLXSW_SP_VFID_PORT_MAX; +} + +static u16 mlxsw_sp_br_vfid_to_vfid(u16 br_vfid) +{ + return MLXSW_SP_VFID_PORT_MAX + br_vfid; +} + +static u16 mlxsw_sp_avail_br_vfid_get(const struct mlxsw_sp *mlxsw_sp) +{ + return find_first_zero_bit(mlxsw_sp->br_vfids.mapped, + MLXSW_SP_VFID_BR_MAX); +} + +static struct mlxsw_sp_vfid *mlxsw_sp_br_vfid_create(struct mlxsw_sp *mlxsw_sp, + struct net_device *br_dev) +{ + struct device *dev = mlxsw_sp->bus_info->dev; + struct mlxsw_sp_vfid *vfid; + u16 n_vfid; + int err; + + n_vfid = mlxsw_sp_br_vfid_to_vfid(mlxsw_sp_avail_br_vfid_get(mlxsw_sp)); + if (n_vfid == MLXSW_SP_VFID_MAX) { + dev_err(dev, "No available vFIDs\n"); + return ERR_PTR(-ERANGE); + } + + err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid); + if (err) { + dev_err(dev, "Failed to create vFID=%d\n", n_vfid); + return ERR_PTR(err); + } + + vfid = kzalloc(sizeof(*vfid), GFP_KERNEL); + if (!vfid) + goto err_allocate_vfid; + + vfid->vfid = n_vfid; + vfid->br_dev = br_dev; + + list_add(&vfid->list, &mlxsw_sp->br_vfids.list); + set_bit(mlxsw_sp_vfid_to_br_vfid(n_vfid), mlxsw_sp->br_vfids.mapped); + + return vfid; + +err_allocate_vfid: + __mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid); + return ERR_PTR(-ENOMEM); +} + +static void mlxsw_sp_br_vfid_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vfid *vfid) +{ + u16 br_vfid = mlxsw_sp_vfid_to_br_vfid(vfid->vfid); + + clear_bit(br_vfid, mlxsw_sp->br_vfids.mapped); + list_del(&vfid->list); + + __mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid); + + kfree(vfid); +} + +static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *br_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + struct net_device *dev = mlxsw_sp_vport->dev; + struct mlxsw_sp_vfid *vfid, *new_vfid; + int err; + + vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev); + if (!vfid) { + WARN_ON(!vfid); + return -EINVAL; + } + + /* We need a vFID to go back to after leaving the bridge's vFID. */ + new_vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid); + if (!new_vfid) { + new_vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid); + if (IS_ERR(new_vfid)) { + netdev_err(dev, "Failed to create vFID for VID=%d\n", + vid); + return PTR_ERR(new_vfid); + } + } + + /* Invalidate existing {Port, VID} to vFID mapping and create a new + * one for the new vFID. + */ + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, + false, + mlxsw_sp_vfid_to_fid(vfid->vfid), + vid); + if (err) { + netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n", + vfid->vfid); + goto err_port_vid_to_fid_invalidate; + } + + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, + true, + mlxsw_sp_vfid_to_fid(new_vfid->vfid), + vid); + if (err) { + netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n", + new_vfid->vfid); + goto err_port_vid_to_fid_validate; + } + + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); + if (err) { + netdev_err(dev, "Failed to disable learning\n"); + goto err_port_vid_learning_set; + } + + err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, + false); + if (err) { + netdev_err(dev, "Failed clear to clear flooding\n"); + goto err_vport_flood_set; + } + + /* Switch between the vFIDs and destroy the old one if needed. */ + new_vfid->nr_vports++; + mlxsw_sp_vport->vport.vfid = new_vfid; + vfid->nr_vports--; + if (!vfid->nr_vports) + mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid); + + mlxsw_sp_vport->learning = 0; + mlxsw_sp_vport->learning_sync = 0; + mlxsw_sp_vport->uc_flood = 0; + mlxsw_sp_vport->bridged = 0; + + return 0; + +err_vport_flood_set: +err_port_vid_learning_set: +err_port_vid_to_fid_validate: +err_port_vid_to_fid_invalidate: + /* Rollback vFID only if new. */ + if (!new_vfid->nr_vports) + mlxsw_sp_vfid_destroy(mlxsw_sp, new_vfid); + return err; +} + +static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *br_dev) +{ + struct mlxsw_sp_vfid *old_vfid = mlxsw_sp_vport->vport.vfid; + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + struct net_device *dev = mlxsw_sp_vport->dev; + struct mlxsw_sp_vfid *vfid; + int err; + + vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev); + if (!vfid) { + vfid = mlxsw_sp_br_vfid_create(mlxsw_sp, br_dev); + if (IS_ERR(vfid)) { + netdev_err(dev, "Failed to create bridge vFID\n"); + return PTR_ERR(vfid); + } + } + + err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, true, false); + if (err) { + netdev_err(dev, "Failed to setup flooding for vFID=%d\n", + vfid->vfid); + goto err_port_flood_set; + } + + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); + if (err) { + netdev_err(dev, "Failed to enable learning\n"); + goto err_port_vid_learning_set; + } + + /* We need to invalidate existing {Port, VID} to vFID mapping and + * create a new one for the bridge's vFID. + */ + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, + false, + mlxsw_sp_vfid_to_fid(old_vfid->vfid), + vid); + if (err) { + netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n", + old_vfid->vfid); + goto err_port_vid_to_fid_invalidate; + } + + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, + true, + mlxsw_sp_vfid_to_fid(vfid->vfid), + vid); + if (err) { + netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n", + vfid->vfid); + goto err_port_vid_to_fid_validate; + } + + /* Switch between the vFIDs and destroy the old one if needed. */ + vfid->nr_vports++; + mlxsw_sp_vport->vport.vfid = vfid; + old_vfid->nr_vports--; + if (!old_vfid->nr_vports) + mlxsw_sp_vfid_destroy(mlxsw_sp, old_vfid); + + mlxsw_sp_vport->learning = 1; + mlxsw_sp_vport->learning_sync = 1; + mlxsw_sp_vport->uc_flood = 1; + mlxsw_sp_vport->bridged = 1; + + return 0; + +err_port_vid_to_fid_validate: + mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false, + mlxsw_sp_vfid_to_fid(old_vfid->vfid), vid); +err_port_vid_to_fid_invalidate: + mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); +err_port_vid_learning_set: + mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, false); +err_port_flood_set: + if (!vfid->nr_vports) + mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid); + return err; +} + +static bool +mlxsw_sp_port_master_bridge_check(const struct mlxsw_sp_port *mlxsw_sp_port, + const struct net_device *br_dev) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, + vport.list) { + if (mlxsw_sp_vport_br_get(mlxsw_sp_vport) == br_dev) + return false; + } + + return true; +} + +static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, + unsigned long event, void *ptr, + u16 vid) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct netdev_notifier_changeupper_info *info = ptr; + struct mlxsw_sp_port *mlxsw_sp_vport; + struct net_device *upper_dev; + int err; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + + switch (event) { + case NETDEV_PRECHANGEUPPER: + upper_dev = info->upper_dev; + if (!info->master || !info->linking) + break; + if (!netif_is_bridge_master(upper_dev)) + return NOTIFY_BAD; + /* We can't have multiple VLAN interfaces configured on + * the same port and being members in the same bridge. + */ + if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port, + upper_dev)) + return NOTIFY_BAD; + break; + case NETDEV_CHANGEUPPER: + upper_dev = info->upper_dev; + if (!info->master) + break; + if (info->linking) { + if (!mlxsw_sp_vport) { + WARN_ON(!mlxsw_sp_vport); + return NOTIFY_BAD; + } + err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport, + upper_dev); + if (err) { + netdev_err(dev, "Failed to join bridge\n"); + return NOTIFY_BAD; + } + } else { + /* We ignore bridge's unlinking notifications if vPort + * is gone, since we already left the bridge when the + * VLAN device was unlinked from the real device. + */ + if (!mlxsw_sp_vport) + return NOTIFY_DONE; + err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, + upper_dev); + if (err) { + netdev_err(dev, "Failed to leave bridge\n"); + return NOTIFY_BAD; + } + } + } + + return NOTIFY_DONE; +} + +static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev, + unsigned long event, void *ptr, + u16 vid) +{ + struct net_device *dev; + struct list_head *iter; + int ret; + + netdev_for_each_lower_dev(lag_dev, dev, iter) { + if (mlxsw_sp_port_dev_check(dev)) { + ret = mlxsw_sp_netdevice_vport_event(dev, event, ptr, + vid); + if (ret == NOTIFY_BAD) + return ret; + } + } + + return NOTIFY_DONE; +} + +static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, + unsigned long event, void *ptr) +{ + struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); + u16 vid = vlan_dev_vlan_id(vlan_dev); + + if (mlxsw_sp_port_dev_check(real_dev)) + return mlxsw_sp_netdevice_vport_event(real_dev, event, ptr, + vid); + else if (netif_is_lag_master(real_dev)) + return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr, + vid); + + return NOTIFY_DONE; +} + static int mlxsw_sp_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -2282,6 +2826,9 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused, if (netif_is_lag_master(dev)) return mlxsw_sp_netdevice_lag_event(dev, event, ptr); + if (is_vlan_dev(dev)) + return mlxsw_sp_netdevice_vlan_event(dev, event, ptr); + return NOTIFY_DONE; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 48be5a63b9b5b..463ed6dcc7099 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -41,11 +41,16 @@ #include <linux/netdevice.h> #include <linux/bitops.h> #include <linux/if_vlan.h> +#include <linux/list.h> #include <net/switchdev.h> #include "core.h" #define MLXSW_SP_VFID_BASE VLAN_N_VID +#define MLXSW_SP_VFID_PORT_MAX 512 /* Non-bridged VLAN interfaces */ +#define MLXSW_SP_VFID_BR_MAX 8192 /* Bridged VLAN interfaces */ +#define MLXSW_SP_VFID_MAX (MLXSW_SP_VFID_PORT_MAX + MLXSW_SP_VFID_BR_MAX) + #define MLXSW_SP_LAG_MAX 64 #define MLXSW_SP_PORT_PER_LAG_MAX 16 @@ -56,8 +61,38 @@ struct mlxsw_sp_upper { unsigned int ref_count; }; +struct mlxsw_sp_vfid { + struct list_head list; + u16 nr_vports; + u16 vfid; /* Starting at 0 */ + struct net_device *br_dev; + u16 vid; +}; + +static inline u16 mlxsw_sp_vfid_to_fid(u16 vfid) +{ + return MLXSW_SP_VFID_BASE + vfid; +} + +static inline u16 mlxsw_sp_fid_to_vfid(u16 fid) +{ + return fid - MLXSW_SP_VFID_BASE; +} + +static inline bool mlxsw_sp_fid_is_vfid(u16 fid) +{ + return fid >= MLXSW_SP_VFID_BASE; +} + struct mlxsw_sp { - unsigned long active_vfids[BITS_TO_LONGS(VLAN_N_VID)]; + struct { + struct list_head list; + unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_PORT_MAX)]; + } port_vfids; + struct { + struct list_head list; + unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_BR_MAX)]; + } br_vfids; unsigned long active_fids[BITS_TO_LONGS(VLAN_N_VID)]; struct mlxsw_sp_port **ports; struct mlxsw_core *core; @@ -102,11 +137,15 @@ struct mlxsw_sp_port { lagged:1; u16 pvid; u16 lag_id; + struct { + struct list_head list; + struct mlxsw_sp_vfid *vfid; + u16 vid; + } vport; /* 802.1Q bridge VLANs */ - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + unsigned long *active_vlans; /* VLAN interfaces */ - unsigned long active_vfids[BITS_TO_LONGS(VLAN_N_VID)]; - u16 nr_vfids; + struct list_head vports_list; }; static inline struct mlxsw_sp_port * @@ -121,6 +160,59 @@ mlxsw_sp_port_lagged_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id, u8 port_index) return mlxsw_sp_port && mlxsw_sp_port->lagged ? mlxsw_sp_port : NULL; } +static inline bool +mlxsw_sp_port_is_vport(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + return mlxsw_sp_port->vport.vfid; +} + +static inline struct net_device * +mlxsw_sp_vport_br_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +{ + return mlxsw_sp_vport->vport.vfid->br_dev; +} + +static inline u16 +mlxsw_sp_vport_vid_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +{ + return mlxsw_sp_vport->vport.vid; +} + +static inline u16 +mlxsw_sp_vport_vfid_get(const struct mlxsw_sp_port *mlxsw_sp_vport) +{ + return mlxsw_sp_vport->vport.vfid->vfid; +} + +static inline struct mlxsw_sp_port * +mlxsw_sp_port_vport_find(const struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, + vport.list) { + if (mlxsw_sp_vport_vid_get(mlxsw_sp_vport) == vid) + return mlxsw_sp_vport; + } + + return NULL; +} + +static inline struct mlxsw_sp_port * +mlxsw_sp_port_vport_find_by_vfid(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 vfid) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, + vport.list) { + if (mlxsw_sp_vport_vfid_get(mlxsw_sp_vport) == vfid) + return mlxsw_sp_vport; + } + + return NULL; +} + enum mlxsw_sp_flood_table { MLXSW_SP_FLOOD_TABLE_UC, MLXSW_SP_FLOOD_TABLE_BM, @@ -143,5 +235,7 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid); int mlxsw_sp_port_kill_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid); +int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, + bool set, bool only_uc); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 406dab2f6b17c..62159547ebf9d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -51,12 +51,33 @@ #include "core.h" #include "reg.h" +static struct mlxsw_sp_port * +mlxsw_sp_port_orig_get(struct net_device *dev, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + u16 vid; + + if (!is_vlan_dev(dev)) + return mlxsw_sp_port; + + vid = vlan_dev_vlan_id(dev); + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + WARN_ON(!mlxsw_sp_vport); + + return mlxsw_sp_vport; +} + static int mlxsw_sp_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + mlxsw_sp_port = mlxsw_sp_port_orig_get(attr->orig_dev, mlxsw_sp_port); + if (!mlxsw_sp_port) + return -EINVAL; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(mlxsw_sp->base_mac); @@ -105,8 +126,14 @@ static int mlxsw_sp_port_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, if (!spms_pl) return -ENOMEM; mlxsw_reg_spms_pack(spms_pl, mlxsw_sp_port->local_port); - for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) + + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); mlxsw_reg_spms_vid_pack(spms_pl, vid, spms_state); + } else { + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) + mlxsw_reg_spms_vid_pack(spms_pl, vid, spms_state); + } err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spms), spms_pl); kfree(spms_pl); @@ -124,22 +151,38 @@ static int mlxsw_sp_port_attr_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_port_stp_state_set(mlxsw_sp_port, state); } +static bool mlxsw_sp_vfid_is_vport_br(u16 vfid) +{ + return vfid >= MLXSW_SP_VFID_PORT_MAX; +} + static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, - u16 fid_begin, u16 fid_end, bool set, + u16 idx_begin, u16 idx_end, bool set, bool only_uc) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - u16 range = fid_end - fid_begin + 1; + u16 local_port = mlxsw_sp_port->local_port; + enum mlxsw_flood_table_type table_type; + u16 range = idx_end - idx_begin + 1; char *sftr_pl; int err; + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID; + if (mlxsw_sp_vfid_is_vport_br(idx_begin)) + local_port = mlxsw_sp_port->local_port; + else + local_port = MLXSW_PORT_CPU_PORT; + } else { + table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; + } + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); if (!sftr_pl) return -ENOMEM; - mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, fid_begin, - MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST, range, - mlxsw_sp_port->local_port, set); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, idx_begin, + table_type, range, local_port, set); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); if (err) goto buffer_out; @@ -150,9 +193,8 @@ static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, if (only_uc) goto buffer_out; - mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, fid_begin, - MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST, range, - mlxsw_sp_port->local_port, set); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, idx_begin, + table_type, range, local_port, set); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); buffer_out: @@ -167,6 +209,13 @@ static int mlxsw_sp_port_uc_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, last_visited_vid; int err; + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); + + return __mlxsw_sp_port_flood_set(mlxsw_sp_port, vfid, vfid, + set, true); + } + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) { err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid, vid, set, true); @@ -185,6 +234,16 @@ err_port_flood_set: return err; } +int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, + bool set, bool only_uc) +{ + /* In case of vFIDs, index into the flooding table is relative to + * the start of the vFIDs range. + */ + return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set, + only_uc); +} + static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, struct switchdev_trans *trans, unsigned long brport_flags) @@ -193,6 +252,9 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, bool set; int err; + if (!mlxsw_sp_port->bridged) + return -EINVAL; + if (switchdev_trans_ph_prepare(trans)) return 0; @@ -244,6 +306,10 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int err = 0; + mlxsw_sp_port = mlxsw_sp_port_orig_get(attr->orig_dev, mlxsw_sp_port); + if (!mlxsw_sp_port) + return -EINVAL; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: err = mlxsw_sp_port_attr_stp_state_set(mlxsw_sp_port, trans, @@ -304,7 +370,7 @@ static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid) { enum mlxsw_reg_svfa_mt mt; - if (mlxsw_sp_port->nr_vfids) + if (!list_empty(&mlxsw_sp_port->vports_list)) mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; else mt = MLXSW_REG_SVFA_MT_VID_TO_FID; @@ -316,7 +382,7 @@ static int mlxsw_sp_port_fid_unmap(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid) { enum mlxsw_reg_svfa_mt mt; - if (!mlxsw_sp_port->nr_vfids) + if (list_empty(&mlxsw_sp_port->vports_list)) return 0; mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; @@ -503,7 +569,7 @@ static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding) } static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp_port *mlxsw_sp_port, - const char *mac, u16 vid, bool adding, + const char *mac, u16 fid, bool adding, bool dynamic) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; @@ -516,7 +582,7 @@ static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), - mac, vid, MLXSW_REG_SFD_REC_ACTION_NOP, + mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP, mlxsw_sp_port->local_port); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); kfree(sfd_pl); @@ -525,8 +591,8 @@ static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp_port *mlxsw_sp_port, } static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, - const char *mac, u16 vid, bool adding, - bool dynamic) + const char *mac, u16 fid, u16 lag_vid, + bool adding, bool dynamic) { char *sfd_pl; int err; @@ -537,8 +603,8 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), - mac, vid, MLXSW_REG_SFD_REC_ACTION_NOP, - lag_id); + mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP, + lag_vid, lag_id); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); kfree(sfd_pl); @@ -550,21 +616,30 @@ mlxsw_sp_port_fdb_static_add(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans) { - u16 vid = fdb->vid; + u16 fid = fdb->vid; + u16 lag_vid = 0; if (switchdev_trans_ph_prepare(trans)) return 0; - if (!vid) - vid = mlxsw_sp_port->pvid; + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); + + fid = mlxsw_sp_vfid_to_fid(vfid); + lag_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); + } + + if (!fid) + fid = mlxsw_sp_port->pvid; if (!mlxsw_sp_port->lagged) return mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port, - fdb->addr, vid, true, false); + fdb->addr, fid, true, false); else return mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp_port->mlxsw_sp, mlxsw_sp_port->lag_id, - fdb->addr, vid, true, false); + fdb->addr, fid, lag_vid, + true, false); } static int mlxsw_sp_port_obj_add(struct net_device *dev, @@ -574,8 +649,15 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int err = 0; + mlxsw_sp_port = mlxsw_sp_port_orig_get(obj->orig_dev, mlxsw_sp_port); + if (!mlxsw_sp_port) + return -EINVAL; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) + return 0; + err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, SWITCHDEV_OBJ_PORT_VLAN(obj), trans); @@ -679,14 +761,24 @@ static int mlxsw_sp_port_fdb_static_del(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_fdb *fdb) { + u16 fid = fdb->vid; + u16 lag_vid = 0; + + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); + + fid = mlxsw_sp_vfid_to_fid(vfid); + lag_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); + } + if (!mlxsw_sp_port->lagged) return mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port, - fdb->addr, fdb->vid, + fdb->addr, fid, false, false); else return mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp_port->mlxsw_sp, mlxsw_sp_port->lag_id, - fdb->addr, fdb->vid, + fdb->addr, fid, lag_vid, false, false); } @@ -696,8 +788,15 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int err = 0; + mlxsw_sp_port = mlxsw_sp_port_orig_get(obj->orig_dev, mlxsw_sp_port); + if (!mlxsw_sp_port) + return -EINVAL; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) + return 0; + err = mlxsw_sp_port_vlans_del(mlxsw_sp_port, SWITCHDEV_OBJ_PORT_VLAN(obj)); break; @@ -732,9 +831,10 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, switchdev_obj_dump_cb_t *cb) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u16 vport_vid = 0, vport_fid = 0; char *sfd_pl; char mac[ETH_ALEN]; - u16 vid; + u16 fid; u8 local_port; u16 lag_id; u8 num_rec; @@ -746,6 +846,14 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, if (!sfd_pl) return -ENOMEM; + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + u16 tmp; + + tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); + vport_fid = mlxsw_sp_vfid_to_fid(tmp); + vport_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); + } + mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0); do { mlxsw_reg_sfd_num_rec_set(sfd_pl, MLXSW_REG_SFD_REC_MAX_COUNT); @@ -764,12 +872,17 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, for (i = 0; i < num_rec; i++) { switch (mlxsw_reg_sfd_rec_type_get(sfd_pl, i)) { case MLXSW_REG_SFD_REC_TYPE_UNICAST: - mlxsw_reg_sfd_uc_unpack(sfd_pl, i, mac, &vid, + mlxsw_reg_sfd_uc_unpack(sfd_pl, i, mac, &fid, &local_port); if (local_port == mlxsw_sp_port->local_port) { + if (vport_fid && vport_fid != fid) + continue; + else if (vport_fid) + fdb->vid = vport_vid; + else + fdb->vid = fid; ether_addr_copy(fdb->addr, mac); fdb->ndm_state = NUD_REACHABLE; - fdb->vid = vid; err = cb(&fdb->obj); if (err) stored_err = err; @@ -777,12 +890,17 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, break; case MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG: mlxsw_reg_sfd_uc_lag_unpack(sfd_pl, i, - mac, &vid, &lag_id); + mac, &fid, &lag_id); if (mlxsw_sp_port == mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id)) { + if (vport_fid && vport_fid != fid) + continue; + else if (vport_fid) + fdb->vid = vport_vid; + else + fdb->vid = fid; ether_addr_copy(fdb->addr, mac); fdb->ndm_state = NUD_REACHABLE; - fdb->vid = vid; err = cb(&fdb->obj); if (err) stored_err = err; @@ -804,6 +922,13 @@ static int mlxsw_sp_port_vlan_dump(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid; int err = 0; + if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { + vlan->flags = 0; + vlan->vid_begin = mlxsw_sp_vport_vid_get(mlxsw_sp_port); + vlan->vid_end = mlxsw_sp_vport_vid_get(mlxsw_sp_port); + return cb(&vlan->obj); + } + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) { vlan->flags = 0; if (vid == mlxsw_sp_port->pvid) @@ -824,6 +949,10 @@ static int mlxsw_sp_port_obj_dump(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int err = 0; + mlxsw_sp_port = mlxsw_sp_port_orig_get(obj->orig_dev, mlxsw_sp_port); + if (!mlxsw_sp_port) + return -EINVAL; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: err = mlxsw_sp_port_vlan_dump(mlxsw_sp_port, @@ -871,17 +1000,35 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_port *mlxsw_sp_port; char mac[ETH_ALEN]; u8 local_port; - u16 vid; + u16 vid, fid; int err; - mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &vid, &local_port); + mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port); mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) { dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect local port in FDB notification\n"); return; } - err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port, mac, vid, + if (mlxsw_sp_fid_is_vfid(fid)) { + u16 vfid = mlxsw_sp_fid_to_vfid(fid); + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port, + vfid); + if (!mlxsw_sp_vport) { + netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n"); + return; + } + + vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + /* Override the physical port with the vPort. */ + mlxsw_sp_port = mlxsw_sp_vport; + } else { + vid = fid; + } + + err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port, mac, fid, adding && mlxsw_sp_port->learning, true); if (err) { if (net_ratelimit()) @@ -900,18 +1047,38 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_port *mlxsw_sp_port; char mac[ETH_ALEN]; + u16 lag_vid = 0; u16 lag_id; - u16 vid; + u16 vid, fid; int err; - mlxsw_reg_sfn_mac_lag_unpack(sfn_pl, rec_index, mac, &vid, &lag_id); + mlxsw_reg_sfn_mac_lag_unpack(sfn_pl, rec_index, mac, &fid, &lag_id); mlxsw_sp_port = mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id); if (!mlxsw_sp_port) { dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Cannot find port representor for LAG\n"); return; } - err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, vid, + if (mlxsw_sp_fid_is_vfid(fid)) { + u16 vfid = mlxsw_sp_fid_to_vfid(fid); + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port, + vfid); + if (!mlxsw_sp_vport) { + netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n"); + return; + } + + vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + lag_vid = vid; + /* Override the physical port with the vPort. */ + mlxsw_sp_port = mlxsw_sp_vport; + } else { + vid = fid; + } + + err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid, adding && mlxsw_sp_port->learning, true); if (err) { diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index b83f7c0fcf996..122c2ee3dfe2a 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -1937,6 +1937,12 @@ static void refill_rx(struct net_device *dev) break; /* Better luck next round. */ np->rx_dma[entry] = pci_map_single(np->pci_dev, skb->data, buflen, PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(np->pci_dev, + np->rx_dma[entry])) { + dev_kfree_skb_any(skb); + np->rx_skbuff[entry] = NULL; + break; /* Better luck next round. */ + } np->rx_ring[entry].addr = cpu_to_le32(np->rx_dma[entry]); } np->rx_ring[entry].cmd_status = cpu_to_le32(np->rx_buf_sz); @@ -2093,6 +2099,12 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) np->tx_skbuff[entry] = skb; np->tx_dma[entry] = pci_map_single(np->pci_dev, skb->data,skb->len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(np->pci_dev, np->tx_dma[entry])) { + np->tx_skbuff[entry] = NULL; + dev_kfree_skb_irq(skb); + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } np->tx_ring[entry].addr = cpu_to_le32(np->tx_dma[entry]); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 038ac6b14a603..43c618bafdb64 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1363,6 +1363,7 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) tx_ring->wr_p = 0; tx_ring->rd_p = 0; tx_ring->qcp_rd_p = 0; + tx_ring->wr_ptr_add = 0; tx_ring->txbufs = NULL; tx_ring->txds = NULL; @@ -1437,6 +1438,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) rx_ring->cnt = 0; rx_ring->wr_p = 0; rx_ring->rd_p = 0; + rx_ring->wr_ptr_add = 0; rx_ring->rxbufs = NULL; rx_ring->rxds = NULL; @@ -2071,7 +2073,7 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev, l4_hdr = ipv6_hdr(skb)->nexthdr; break; default: - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } if (skb->inner_protocol_type != ENCAP_TYPE_ETHER || @@ -2080,7 +2082,7 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev, (l4_hdr == IPPROTO_UDP && (skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } @@ -2415,6 +2417,7 @@ int nfp_net_netdev_init(struct net_device *netdev) ether_setup(netdev); netdev->netdev_ops = &nfp_net_netdev_ops; netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000); + netif_carrier_off(netdev); nfp_net_set_ethtool_ops(netdev); nfp_net_irqs_assign(netdev); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c index 08d4be6160648..e097e6baaac43 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c @@ -500,7 +500,7 @@ void pch_gbe_check_options(struct pch_gbe_adapter *adapter) val = XsumTX; pch_gbe_validate_option(&val, &opt, adapter); if (!val) - dev->features &= ~NETIF_F_ALL_CSUM; + dev->features &= ~NETIF_F_CSUM_MASK; } { /* Flow Control */ static const struct pch_gbe_option opt = { diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index ac17d8669b1ad..1292c360390cd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -299,6 +299,7 @@ struct qed_hwfn { /* Flag indicating whether interrupts are enabled or not*/ bool b_int_enabled; + bool b_int_requested; struct qed_mcp_info *mcp_info; @@ -491,6 +492,8 @@ u32 qed_unzip_data(struct qed_hwfn *p_hwfn, u32 input_len, u8 *input_buf, u32 max_size, u8 *unzip_buf); +int qed_slowpath_irq_req(struct qed_hwfn *hwfn); + #define QED_ETH_INTERFACE_VERSION 300 #endif /* _QED_H */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 803b190ccada9..817bbd5476ffb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1385,52 +1385,63 @@ err0: return rc; } -static u32 qed_hw_bar_size(struct qed_dev *cdev, - u8 bar_id) +static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, + u8 bar_id) { - u32 size = pci_resource_len(cdev->pdev, (bar_id > 0) ? 2 : 0); + u32 bar_reg = (bar_id == 0 ? PGLUE_B_REG_PF_BAR0_SIZE + : PGLUE_B_REG_PF_BAR1_SIZE); + u32 val = qed_rd(p_hwfn, p_hwfn->p_main_ptt, bar_reg); - return size / cdev->num_hwfns; + /* Get the BAR size(in KB) from hardware given val */ + return 1 << (val + 15); } int qed_hw_prepare(struct qed_dev *cdev, int personality) { - int rc, i; + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + int rc; /* Store the precompiled init data ptrs */ qed_init_iro_array(cdev); /* Initialize the first hwfn - will learn number of hwfns */ - rc = qed_hw_prepare_single(&cdev->hwfns[0], cdev->regview, + rc = qed_hw_prepare_single(p_hwfn, + cdev->regview, cdev->doorbells, personality); if (rc) return rc; - personality = cdev->hwfns[0].hw_info.personality; + personality = p_hwfn->hw_info.personality; /* Initialize the rest of the hwfns */ - for (i = 1; i < cdev->num_hwfns; i++) { + if (cdev->num_hwfns > 1) { void __iomem *p_regview, *p_doorbell; + u8 __iomem *addr; + + /* adjust bar offset for second engine */ + addr = cdev->regview + qed_hw_bar_size(p_hwfn, 0) / 2; + p_regview = addr; - p_regview = cdev->regview + - i * qed_hw_bar_size(cdev, 0); - p_doorbell = cdev->doorbells + - i * qed_hw_bar_size(cdev, 1); - rc = qed_hw_prepare_single(&cdev->hwfns[i], p_regview, + /* adjust doorbell bar offset for second engine */ + addr = cdev->doorbells + qed_hw_bar_size(p_hwfn, 1) / 2; + p_doorbell = addr; + + /* prepare second hw function */ + rc = qed_hw_prepare_single(&cdev->hwfns[1], p_regview, p_doorbell, personality); + + /* in case of error, need to free the previously + * initiliazed hwfn 0. + */ if (rc) { - /* Cleanup previously initialized hwfns */ - while (--i >= 0) { - qed_init_free(&cdev->hwfns[i]); - qed_mcp_free(&cdev->hwfns[i]); - qed_hw_hwfn_free(&cdev->hwfns[i]); - } - return rc; + qed_init_free(p_hwfn); + qed_mcp_free(p_hwfn); + qed_hw_hwfn_free(p_hwfn); } } - return 0; + return rc; } void qed_hw_remove(struct qed_dev *cdev) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index de50e84902afe..9cc9d62c1fec6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -783,22 +783,16 @@ void qed_int_igu_enable_int(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, IGU_REG_PF_CONFIGURATION, igu_pf_conf); } -void qed_int_igu_enable(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - enum qed_int_mode int_mode) +int qed_int_igu_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + enum qed_int_mode int_mode) { - int i; - - p_hwfn->b_int_enabled = 1; + int rc, i; /* Mask non-link attentions */ for (i = 0; i < 9; i++) qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_ENABLE1_IGU_OUT_0 + (i << 2), 0); - /* Enable interrupt Generation */ - qed_int_igu_enable_int(p_hwfn, p_ptt, int_mode); - /* Configure AEU signal change to produce attentions for link */ qed_wr(p_hwfn, p_ptt, IGU_REG_LEADING_EDGE_LATCH, 0xfff); qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff); @@ -808,6 +802,19 @@ void qed_int_igu_enable(struct qed_hwfn *p_hwfn, /* Unmask AEU signals toward IGU */ qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff); + if ((int_mode != QED_INT_MODE_INTA) || IS_LEAD_HWFN(p_hwfn)) { + rc = qed_slowpath_irq_req(p_hwfn); + if (rc != 0) { + DP_NOTICE(p_hwfn, "Slowpath IRQ request failed\n"); + return -EINVAL; + } + p_hwfn->b_int_requested = true; + } + /* Enable interrupt Generation */ + qed_int_igu_enable_int(p_hwfn, p_ptt, int_mode); + p_hwfn->b_int_enabled = 1; + + return rc; } void qed_int_igu_disable_int(struct qed_hwfn *p_hwfn, @@ -1127,3 +1134,11 @@ int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, return info->igu_sb_cnt; } + +void qed_int_disable_post_isr_release(struct qed_dev *cdev) +{ + int i; + + for_each_hwfn(cdev, i) + cdev->hwfns[i].b_int_requested = false; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 16b57518e7067..51e0b09a7f47d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -169,10 +169,14 @@ int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, int *p_iov_blks); /** - * @file + * @brief qed_int_disable_post_isr_release - performs the cleanup post ISR + * release. The API need to be called after releasing all slowpath IRQs + * of the device. + * + * @param cdev * - * @brief Interrupt handler */ +void qed_int_disable_post_isr_release(struct qed_dev *cdev); #define QED_CAU_DEF_RX_TIMER_RES 0 #define QED_CAU_DEF_TX_TIMER_RES 0 @@ -366,10 +370,11 @@ void qed_int_setup(struct qed_hwfn *p_hwfn, * @param p_hwfn * @param p_ptt * @param int_mode + * + * @return int */ -void qed_int_igu_enable(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - enum qed_int_mode int_mode); +int qed_int_igu_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + enum qed_int_mode int_mode); /** * @brief - Initialize CAU status block entry diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 6b02e11343601..9d76ce249277a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -476,41 +476,22 @@ static irqreturn_t qed_single_int(int irq, void *dev_instance) return rc; } -static int qed_slowpath_irq_req(struct qed_dev *cdev) +int qed_slowpath_irq_req(struct qed_hwfn *hwfn) { - int i = 0, rc = 0; + struct qed_dev *cdev = hwfn->cdev; + int rc = 0; + u8 id; if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) { - /* Request all the slowpath MSI-X vectors */ - for (i = 0; i < cdev->num_hwfns; i++) { - snprintf(cdev->hwfns[i].name, NAME_SIZE, - "sp-%d-%02x:%02x.%02x", - i, cdev->pdev->bus->number, - PCI_SLOT(cdev->pdev->devfn), - cdev->hwfns[i].abs_pf_id); - - rc = request_irq(cdev->int_params.msix_table[i].vector, - qed_msix_sp_int, 0, - cdev->hwfns[i].name, - cdev->hwfns[i].sp_dpc); - if (rc) - break; - - DP_VERBOSE(&cdev->hwfns[i], - (NETIF_MSG_INTR | QED_MSG_SP), + id = hwfn->my_id; + snprintf(hwfn->name, NAME_SIZE, "sp-%d-%02x:%02x.%02x", + id, cdev->pdev->bus->number, + PCI_SLOT(cdev->pdev->devfn), hwfn->abs_pf_id); + rc = request_irq(cdev->int_params.msix_table[id].vector, + qed_msix_sp_int, 0, hwfn->name, hwfn->sp_dpc); + if (!rc) + DP_VERBOSE(hwfn, (NETIF_MSG_INTR | QED_MSG_SP), "Requested slowpath MSI-X\n"); - } - - if (i != cdev->num_hwfns) { - /* Free already request MSI-X vectors */ - for (i--; i >= 0; i--) { - unsigned int vec = - cdev->int_params.msix_table[i].vector; - synchronize_irq(vec); - free_irq(cdev->int_params.msix_table[i].vector, - cdev->hwfns[i].sp_dpc); - } - } } else { unsigned long flags = 0; @@ -534,13 +515,17 @@ static void qed_slowpath_irq_free(struct qed_dev *cdev) if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) { for_each_hwfn(cdev, i) { + if (!cdev->hwfns[i].b_int_requested) + break; synchronize_irq(cdev->int_params.msix_table[i].vector); free_irq(cdev->int_params.msix_table[i].vector, cdev->hwfns[i].sp_dpc); } } else { - free_irq(cdev->pdev->irq, cdev); + if (QED_LEADING_HWFN(cdev)->b_int_requested) + free_irq(cdev->pdev->irq, cdev); } + qed_int_disable_post_isr_release(cdev); } static int qed_nic_stop(struct qed_dev *cdev) @@ -765,16 +750,11 @@ static int qed_slowpath_start(struct qed_dev *cdev, if (rc) goto err1; - /* Request the slowpath IRQ */ - rc = qed_slowpath_irq_req(cdev); - if (rc) - goto err2; - /* Allocate stream for unzipping */ rc = qed_alloc_stream_mem(cdev); if (rc) { DP_NOTICE(cdev, "Failed to allocate stream memory\n"); - goto err3; + goto err2; } /* Start the slowpath */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 7a5ce5914ace2..e8df12335a972 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -363,4 +363,8 @@ 0x7 << 0) #define MCP_REG_NVM_CFG4_FLASH_SIZE_SHIFT \ 0 +#define PGLUE_B_REG_PF_BAR0_SIZE \ + 0x2aae60UL +#define PGLUE_B_REG_PF_BAR1_SIZE \ + 0x2aae64UL #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 31a1f1eb4f56a..287fadfab52d7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -124,8 +124,12 @@ struct qed_spq { dma_addr_t p_phys; struct qed_spq_entry *p_virt; - /* Used as index for completions (returns on EQ by FW) */ - u16 echo_idx; +#define SPQ_RING_SIZE \ + (CORE_SPQE_PAGE_SIZE_BYTES / sizeof(struct slow_path_element)) + + /* Bitmap for handling out-of-order completions */ + DECLARE_BITMAP(p_comp_bitmap, SPQ_RING_SIZE); + u8 comp_bitmap_idx; /* Statistics */ u32 unlimited_pending_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 7c0b8459666ed..3dd548ab8df14 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -112,8 +112,6 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent) { - p_ent->elem.hdr.echo = 0; - p_hwfn->p_spq->echo_idx++; p_ent->flags = 0; switch (p_ent->comp_mode) { @@ -195,10 +193,12 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq, struct qed_spq_entry *p_ent) { - struct qed_chain *p_chain = &p_hwfn->p_spq->chain; + struct qed_chain *p_chain = &p_hwfn->p_spq->chain; + u16 echo = qed_chain_get_prod_idx(p_chain); struct slow_path_element *elem; struct core_db_data db; + p_ent->elem.hdr.echo = cpu_to_le16(echo); elem = qed_chain_produce(p_chain); if (!elem) { DP_NOTICE(p_hwfn, "Failed to produce from SPQ chain\n"); @@ -437,7 +437,9 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn) p_spq->comp_count = 0; p_spq->comp_sent_count = 0; p_spq->unlimited_pending_count = 0; - p_spq->echo_idx = 0; + + bitmap_zero(p_spq->p_comp_bitmap, SPQ_RING_SIZE); + p_spq->comp_bitmap_idx = 0; /* SPQ cid, cannot fail */ qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_spq->cid); @@ -582,26 +584,32 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq = p_hwfn->p_spq; if (p_ent->queue == &p_spq->unlimited_pending) { - struct qed_spq_entry *p_en2; if (list_empty(&p_spq->free_pool)) { list_add_tail(&p_ent->list, &p_spq->unlimited_pending); p_spq->unlimited_pending_count++; return 0; - } + } else { + struct qed_spq_entry *p_en2; - p_en2 = list_first_entry(&p_spq->free_pool, - struct qed_spq_entry, - list); - list_del(&p_en2->list); + p_en2 = list_first_entry(&p_spq->free_pool, + struct qed_spq_entry, + list); + list_del(&p_en2->list); + + /* Copy the ring element physical pointer to the new + * entry, since we are about to override the entire ring + * entry and don't want to lose the pointer. + */ + p_ent->elem.data_ptr = p_en2->elem.data_ptr; - /* Strcut assignment */ - *p_en2 = *p_ent; + *p_en2 = *p_ent; - kfree(p_ent); + kfree(p_ent); - p_ent = p_en2; + p_ent = p_en2; + } } /* entry is to be placed in 'pending' queue */ @@ -777,13 +785,38 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, list_for_each_entry_safe(p_ent, tmp, &p_spq->completion_pending, list) { if (p_ent->elem.hdr.echo == echo) { + u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; + list_del(&p_ent->list); - qed_chain_return_produced(&p_spq->chain); + /* Avoid overriding of SPQ entries when getting + * out-of-order completions, by marking the completions + * in a bitmap and increasing the chain consumer only + * for the first successive completed entries. + */ + bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE); + + while (test_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap)) { + bitmap_clear(p_spq->p_comp_bitmap, + p_spq->comp_bitmap_idx, + SPQ_RING_SIZE); + p_spq->comp_bitmap_idx++; + qed_chain_return_produced(&p_spq->chain); + } + p_spq->comp_count++; found = p_ent; break; } + + /* This is relatively uncommon - depends on scenarios + * which have mutliple per-PF sent ramrods. + */ + DP_VERBOSE(p_hwfn, QED_MSG_SPQ, + "Got completion for echo %04x - doesn't match echo %04x in completion pending list\n", + le16_to_cpu(echo), + le16_to_cpu(p_ent->elem.hdr.echo)); } /* Release lock before callback, as callback may post diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c index be7d7a62cc0d8..34906750b7e70 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c @@ -246,12 +246,13 @@ int qlcnic_83xx_check_vnic_state(struct qlcnic_adapter *adapter) u32 state; state = QLCRDX(ahw, QLC_83XX_VNIC_STATE); - while (state != QLCNIC_DEV_NPAR_OPER && idc->vnic_wait_limit--) { + while (state != QLCNIC_DEV_NPAR_OPER && idc->vnic_wait_limit) { + idc->vnic_wait_limit--; msleep(1000); state = QLCRDX(ahw, QLC_83XX_VNIC_STATE); } - if (!idc->vnic_wait_limit) { + if (state != QLCNIC_DEV_NPAR_OPER) { dev_err(&adapter->pdev->dev, "vNIC mode not operational, state check timed out.\n"); return -EIO; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c index a72bcddf160ac..4b76c69fe86d2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c @@ -167,7 +167,7 @@ struct qlcnic_dcb_cfg { u32 version; }; -static struct qlcnic_dcb_ops qlcnic_83xx_dcb_ops = { +static const struct qlcnic_dcb_ops qlcnic_83xx_dcb_ops = { .init_dcbnl_ops = __qlcnic_init_dcbnl_ops, .free = __qlcnic_dcb_free, .attach = __qlcnic_dcb_attach, @@ -180,7 +180,7 @@ static struct qlcnic_dcb_ops qlcnic_83xx_dcb_ops = { .aen_handler = qlcnic_83xx_dcb_aen_handler, }; -static struct qlcnic_dcb_ops qlcnic_82xx_dcb_ops = { +static const struct qlcnic_dcb_ops qlcnic_82xx_dcb_ops = { .init_dcbnl_ops = __qlcnic_init_dcbnl_ops, .free = __qlcnic_dcb_free, .attach = __qlcnic_dcb_attach, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h index 3cf4a10fbe1e0..9777e57135253 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h @@ -37,7 +37,7 @@ struct qlcnic_dcb { struct qlcnic_adapter *adapter; struct delayed_work aen_work; struct workqueue_struct *wq; - struct qlcnic_dcb_ops *ops; + const struct qlcnic_dcb_ops *ops; struct qlcnic_dcb_cfg *cfg; unsigned long state; }; diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 02b7115b6aaa6..997976426799d 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4211,8 +4211,9 @@ static int ql_change_rx_buffers(struct ql_adapter *qdev) /* Wait for an outstanding reset to complete. */ if (!test_bit(QL_ADAPTER_UP, &qdev->flags)) { - int i = 3; - while (i-- && !test_bit(QL_ADAPTER_UP, &qdev->flags)) { + int i = 4; + + while (--i && !test_bit(QL_ADAPTER_UP, &qdev->flags)) { netif_err(qdev, ifup, qdev->ndev, "Waiting for adapter UP...\n"); ssleep(1); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index ddb2c6c6ec940..689a4a5c8dcfc 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -736,9 +736,8 @@ qcaspi_netdev_tx_timeout(struct net_device *dev) netdev_info(qca->net_dev, "Transmit timeout at %ld, latency %ld\n", jiffies, jiffies - dev->trans_start); qca->net_dev->stats.tx_errors++; - /* wake the queue if there is room */ - if (qcaspi_tx_ring_has_space(&qca->txr)) - netif_wake_queue(dev); + /* Trigger tx queue flush and QCA7000 reset */ + qca->sync = QCASPI_SYNC_UNKNOWN; } static int diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 79ef799f88ab1..17d5571d04322 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -3894,7 +3894,7 @@ static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp) /* disable phy pfm mode */ rtl_writephy(tp, 0x1f, 0x0a44); - rtl_w0w1_phy(tp, 0x14, 0x0000, 0x0080); + rtl_w0w1_phy(tp, 0x11, 0x0000, 0x0080); rtl_writephy(tp, 0x1f, 0x0000); /* Check ALDPS bit, disable it if enabled */ @@ -3947,7 +3947,7 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp) data = (ioffset_p3<<12)|(ioffset_p2<<8)|(ioffset_p1<<4)|(ioffset_p0); if ((ioffset_p3 != 0x0f) || (ioffset_p2 != 0x0f) || - (ioffset_p1 != 0x0f) || (ioffset_p0 == 0x0f)) { + (ioffset_p1 != 0x0f) || (ioffset_p0 != 0x0f)) { rtl_writephy(tp, 0x1f, 0x0bcf); rtl_writephy(tp, 0x16, data); rtl_writephy(tp, 0x1f, 0x0000); @@ -3967,7 +3967,7 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp) /* disable phy pfm mode */ rtl_writephy(tp, 0x1f, 0x0a44); - rtl_w0w1_phy(tp, 0x14, 0x0000, 0x0080); + rtl_w0w1_phy(tp, 0x11, 0x0000, 0x0080); rtl_writephy(tp, 0x1f, 0x0000); /* Check ALDPS bit, disable it if enabled */ @@ -5818,11 +5818,10 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; static const struct ephy_info e_info_8168d_4[] = { - { 0x0b, ~0, 0x48 }, - { 0x19, 0x20, 0x50 }, - { 0x0c, ~0, 0x20 } + { 0x0b, 0x0000, 0x0048 }, + { 0x19, 0x0020, 0x0050 }, + { 0x0c, 0x0100, 0x0020 } }; - int i; rtl_csi_access_enable_1(tp); @@ -5830,13 +5829,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) RTL_W8(MaxTxPacketSize, TxPacketMax); - for (i = 0; i < ARRAY_SIZE(e_info_8168d_4); i++) { - const struct ephy_info *e = e_info_8168d_4 + i; - u16 w; - - w = rtl_ephy_read(tp, e->offset); - rtl_ephy_write(tp, 0x03, (w & e->mask) | e->bits); - } + rtl_ephy_init(tp, e_info_8168d_4, ARRAY_SIZE(e_info_8168d_4)); rtl_enable_clock_request(pdev); } @@ -6127,7 +6120,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07); RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); - RTL_W8(DLLPR, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); + RTL_W8(MISC_1, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); RTL_W8(DLLPR, RTL_R8(DLLPR) & ~TX_10M_PS_EN); @@ -6136,7 +6129,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_pcie_state_l2l3_enable(tp, false); rtl_writephy(tp, 0x1f, 0x0c42); - rg_saw_cnt = rtl_readphy(tp, 0x13); + rg_saw_cnt = (rtl_readphy(tp, 0x13) & 0x3fff); rtl_writephy(tp, 0x1f, 0x0000); if (rg_saw_cnt > 0) { u16 sw_cnt_1ms_ini; @@ -6252,7 +6245,7 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) rtl_hw_start_8168ep(tp); RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); - RTL_W8(DLLPR, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); + RTL_W8(MISC_1, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); } static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) @@ -6274,7 +6267,7 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) rtl_hw_start_8168ep(tp); RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); - RTL_W8(DLLPR, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); + RTL_W8(MISC_1, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); data = r8168_mac_ocp_read(tp, 0xd3e2); data &= 0xf000; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 1cf12264861cf..0e1ebb39ab462 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -410,9 +410,11 @@ static int ravb_dmac_init(struct net_device *ndev) /* Timestamp enable */ ravb_write(ndev, TCCR_TFEN, TCCR); - /* Interrupt enable: */ + /* Interrupt init: */ /* Frame receive */ ravb_write(ndev, RIC0_FRE0 | RIC0_FRE1, RIC0); + /* Disable FIFO full warning */ + ravb_write(ndev, 0, RIC1); /* Receive FIFO full error, descriptor empty */ ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2); /* Frame transmitted, timestamp FIFO updated */ @@ -880,6 +882,7 @@ static int ravb_phy_init(struct net_device *ndev) struct ravb_private *priv = netdev_priv(ndev); struct phy_device *phydev; struct device_node *pn; + int err; priv->link = 0; priv->speed = 0; @@ -887,6 +890,17 @@ static int ravb_phy_init(struct net_device *ndev) /* Try connecting to PHY */ pn = of_parse_phandle(np, "phy-handle", 0); + if (!pn) { + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ + if (of_phy_is_fixed_link(np)) { + err = of_phy_register_fixed_link(np); + if (err) + return err; + } + pn = of_node_get(np); + } phydev = of_phy_connect(ndev, pn, ravb_adjust_link, 0, priv->phy_interface); if (!phydev) { @@ -910,6 +924,9 @@ static int ravb_phy_init(struct net_device *ndev) netdev_info(ndev, "limited PHY to 100Mbit/s\n"); } + /* 10BASE is not supported */ + phydev->supported &= ~PHY_10BT_FEATURES; + netdev_info(ndev, "attached PHY %d (IRQ %d) to driver %s\n", phydev->addr, phydev->irq, phydev->drv->name); @@ -1042,7 +1059,7 @@ static const char ravb_gstrings_stats[][ETH_GSTRING_LEN] = { "rx_queue_1_mcast_packets", "rx_queue_1_errors", "rx_queue_1_crc_errors", - "rx_queue_1_frame_errors_", + "rx_queue_1_frame_errors", "rx_queue_1_length_errors", "rx_queue_1_missed_errors", "rx_queue_1_over_errors", @@ -1478,7 +1495,6 @@ static int ravb_close(struct net_device *ndev) /* Disable interrupts by clearing the interrupt masks. */ ravb_write(ndev, 0, RIC0); - ravb_write(ndev, 0, RIC1); ravb_write(ndev, 0, RIC2); ravb_write(ndev, 0, TIC); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 67cd24312c115..baa81535a8fc1 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -52,6 +52,8 @@ NETIF_MSG_RX_ERR| \ NETIF_MSG_TX_ERR) +#define SH_ETH_OFFSET_INVALID ((u16)~0) + #define SH_ETH_OFFSET_DEFAULTS \ [0 ... SH_ETH_MAX_REGISTER_OFFSET - 1] = SH_ETH_OFFSET_INVALID @@ -404,6 +406,28 @@ static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = { static void sh_eth_rcv_snd_disable(struct net_device *ndev); static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev); +static void sh_eth_write(struct net_device *ndev, u32 data, int enum_index) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + u16 offset = mdp->reg_offset[enum_index]; + + if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) + return; + + iowrite32(data, mdp->addr + offset); +} + +static u32 sh_eth_read(struct net_device *ndev, int enum_index) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + u16 offset = mdp->reg_offset[enum_index]; + + if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) + return ~0U; + + return ioread32(mdp->addr + offset); +} + static bool sh_eth_is_gether(struct sh_eth_private *mdp) { return mdp->reg_offset == sh_eth_offset_gigabit; @@ -943,30 +967,6 @@ static void sh_eth_set_receive_align(struct sk_buff *skb) skb_reserve(skb, SH_ETH_RX_ALIGN - reserve); } - -/* CPU <-> EDMAC endian convert */ -static inline __u32 cpu_to_edmac(struct sh_eth_private *mdp, u32 x) -{ - switch (mdp->edmac_endian) { - case EDMAC_LITTLE_ENDIAN: - return cpu_to_le32(x); - case EDMAC_BIG_ENDIAN: - return cpu_to_be32(x); - } - return x; -} - -static inline __u32 edmac_to_cpu(struct sh_eth_private *mdp, u32 x) -{ - switch (mdp->edmac_endian) { - case EDMAC_LITTLE_ENDIAN: - return le32_to_cpu(x); - case EDMAC_BIG_ENDIAN: - return be32_to_cpu(x); - } - return x; -} - /* Program the hardware MAC address from dev->dev_addr. */ static void update_mac_address(struct net_device *ndev) { @@ -1118,6 +1118,7 @@ static void sh_eth_ring_format(struct net_device *ndev) int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring; int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; + u32 buf_len; mdp->cur_rx = 0; mdp->cur_tx = 0; @@ -1138,17 +1139,17 @@ static void sh_eth_ring_format(struct net_device *ndev) /* RX descriptor */ rxdesc = &mdp->rx_ring[i]; /* The size of the buffer is a multiple of 32 bytes. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); - dma_addr = dma_map_single(&ndev->dev, skb->data, - rxdesc->buffer_length, + buf_len = ALIGN(mdp->rx_buf_sz, 32); + rxdesc->len = cpu_to_le32(buf_len << 16); + dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, dma_addr)) { kfree_skb(skb); break; } mdp->rx_skbuff[i] = skb; - rxdesc->addr = dma_addr; - rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP); + rxdesc->addr = cpu_to_le32(dma_addr); + rxdesc->status = cpu_to_le32(RD_RACT | RD_RFP); /* Rx descriptor address set */ if (i == 0) { @@ -1162,7 +1163,7 @@ static void sh_eth_ring_format(struct net_device *ndev) mdp->dirty_rx = (u32) (i - mdp->num_rx_ring); /* Mark the last entry as wrapping the ring. */ - rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE); + rxdesc->status |= cpu_to_le32(RD_RDLE); memset(mdp->tx_ring, 0, tx_ringsize); @@ -1170,8 +1171,8 @@ static void sh_eth_ring_format(struct net_device *ndev) for (i = 0; i < mdp->num_tx_ring; i++) { mdp->tx_skbuff[i] = NULL; txdesc = &mdp->tx_ring[i]; - txdesc->status = cpu_to_edmac(mdp, TD_TFP); - txdesc->buffer_length = 0; + txdesc->status = cpu_to_le32(TD_TFP); + txdesc->len = cpu_to_le32(0); if (i == 0) { /* Tx descriptor address set */ sh_eth_write(ndev, mdp->tx_desc_dma, TDLAR); @@ -1181,7 +1182,7 @@ static void sh_eth_ring_format(struct net_device *ndev) } } - txdesc->status |= cpu_to_edmac(mdp, TD_TDLE); + txdesc->status |= cpu_to_le32(TD_TDLE); } /* Get skb and descriptor buffer */ @@ -1337,7 +1338,7 @@ static void sh_eth_dev_exit(struct net_device *ndev) * packet boundary if it's currently running */ for (i = 0; i < mdp->num_tx_ring; i++) - mdp->tx_ring[i].status &= ~cpu_to_edmac(mdp, TD_TACT); + mdp->tx_ring[i].status &= ~cpu_to_le32(TD_TACT); /* Disable TX FIFO egress to MAC */ sh_eth_rcv_snd_disable(ndev); @@ -1369,27 +1370,28 @@ static int sh_eth_txfree(struct net_device *ndev) for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { entry = mdp->dirty_tx % mdp->num_tx_ring; txdesc = &mdp->tx_ring[entry]; - if (txdesc->status & cpu_to_edmac(mdp, TD_TACT)) + if (txdesc->status & cpu_to_le32(TD_TACT)) break; /* TACT bit must be checked before all the following reads */ dma_rmb(); netif_info(mdp, tx_done, ndev, "tx entry %d status 0x%08x\n", - entry, edmac_to_cpu(mdp, txdesc->status)); + entry, le32_to_cpu(txdesc->status)); /* Free the original skb. */ if (mdp->tx_skbuff[entry]) { - dma_unmap_single(&ndev->dev, txdesc->addr, - txdesc->buffer_length, DMA_TO_DEVICE); + dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), + le32_to_cpu(txdesc->len) >> 16, + DMA_TO_DEVICE); dev_kfree_skb_irq(mdp->tx_skbuff[entry]); mdp->tx_skbuff[entry] = NULL; free_num++; } - txdesc->status = cpu_to_edmac(mdp, TD_TFP); + txdesc->status = cpu_to_le32(TD_TFP); if (entry >= mdp->num_tx_ring - 1) - txdesc->status |= cpu_to_edmac(mdp, TD_TDLE); + txdesc->status |= cpu_to_le32(TD_TDLE); ndev->stats.tx_packets++; - ndev->stats.tx_bytes += txdesc->buffer_length; + ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; } return free_num; } @@ -1408,15 +1410,16 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) u32 desc_status; int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; + u32 buf_len; boguscnt = min(boguscnt, *quota); limit = boguscnt; rxdesc = &mdp->rx_ring[entry]; - while (!(rxdesc->status & cpu_to_edmac(mdp, RD_RACT))) { + while (!(rxdesc->status & cpu_to_le32(RD_RACT))) { /* RACT bit must be checked before all the following reads */ dma_rmb(); - desc_status = edmac_to_cpu(mdp, rxdesc->status); - pkt_len = rxdesc->frame_length; + desc_status = le32_to_cpu(rxdesc->status); + pkt_len = le32_to_cpu(rxdesc->len) & RD_RFL; if (--boguscnt < 0) break; @@ -1437,6 +1440,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) if (mdp->cd->shift_rd0) desc_status >>= 16; + skb = mdp->rx_skbuff[entry]; if (desc_status & (RD_RFS1 | RD_RFS2 | RD_RFS3 | RD_RFS4 | RD_RFS5 | RD_RFS6 | RD_RFS10)) { ndev->stats.rx_errors++; @@ -1452,16 +1456,16 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) ndev->stats.rx_missed_errors++; if (desc_status & RD_RFS10) ndev->stats.rx_over_errors++; - } else { + } else if (skb) { + dma_addr = le32_to_cpu(rxdesc->addr); if (!mdp->cd->hw_swap) sh_eth_soft_swap( - phys_to_virt(ALIGN(rxdesc->addr, 4)), + phys_to_virt(ALIGN(dma_addr, 4)), pkt_len + 2); - skb = mdp->rx_skbuff[entry]; mdp->rx_skbuff[entry] = NULL; if (mdp->cd->rpadir) skb_reserve(skb, NET_IP_ALIGN); - dma_unmap_single(&ndev->dev, rxdesc->addr, + dma_unmap_single(&ndev->dev, dma_addr, ALIGN(mdp->rx_buf_sz, 32), DMA_FROM_DEVICE); skb_put(skb, pkt_len); @@ -1481,7 +1485,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) entry = mdp->dirty_rx % mdp->num_rx_ring; rxdesc = &mdp->rx_ring[entry]; /* The size of the buffer is 32 byte boundary. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); + buf_len = ALIGN(mdp->rx_buf_sz, 32); + rxdesc->len = cpu_to_le32(buf_len << 16); if (mdp->rx_skbuff[entry] == NULL) { skb = netdev_alloc_skb(ndev, skbuff_size); @@ -1489,8 +1494,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) break; /* Better luck next round. */ sh_eth_set_receive_align(skb); dma_addr = dma_map_single(&ndev->dev, skb->data, - rxdesc->buffer_length, - DMA_FROM_DEVICE); + buf_len, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, dma_addr)) { kfree_skb(skb); break; @@ -1498,15 +1502,14 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) mdp->rx_skbuff[entry] = skb; skb_checksum_none_assert(skb); - rxdesc->addr = dma_addr; + rxdesc->addr = cpu_to_le32(dma_addr); } dma_wmb(); /* RACT bit must be set after all the above writes */ if (entry >= mdp->num_rx_ring - 1) rxdesc->status |= - cpu_to_edmac(mdp, RD_RACT | RD_RFP | RD_RDLE); + cpu_to_le32(RD_RACT | RD_RFP | RD_RDLE); else - rxdesc->status |= - cpu_to_edmac(mdp, RD_RACT | RD_RFP); + rxdesc->status |= cpu_to_le32(RD_RACT | RD_RFP); } /* Restart Rx engine if stopped. */ @@ -2306,8 +2309,8 @@ static void sh_eth_tx_timeout(struct net_device *ndev) /* Free all the skbuffs in the Rx queue. */ for (i = 0; i < mdp->num_rx_ring; i++) { rxdesc = &mdp->rx_ring[i]; - rxdesc->status = 0; - rxdesc->addr = 0xBADF00D0; + rxdesc->status = cpu_to_le32(0); + rxdesc->addr = cpu_to_le32(0xBADF00D0); dev_kfree_skb(mdp->rx_skbuff[i]); mdp->rx_skbuff[i] = NULL; } @@ -2325,6 +2328,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); struct sh_eth_txdesc *txdesc; + dma_addr_t dma_addr; u32 entry; unsigned long flags; @@ -2347,21 +2351,21 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) txdesc = &mdp->tx_ring[entry]; /* soft swap. */ if (!mdp->cd->hw_swap) - sh_eth_soft_swap(phys_to_virt(ALIGN(txdesc->addr, 4)), - skb->len + 2); - txdesc->addr = dma_map_single(&ndev->dev, skb->data, skb->len, - DMA_TO_DEVICE); - if (dma_mapping_error(&ndev->dev, txdesc->addr)) { + sh_eth_soft_swap(PTR_ALIGN(skb->data, 4), skb->len + 2); + dma_addr = dma_map_single(&ndev->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&ndev->dev, dma_addr)) { kfree_skb(skb); return NETDEV_TX_OK; } - txdesc->buffer_length = skb->len; + txdesc->addr = cpu_to_le32(dma_addr); + txdesc->len = cpu_to_le32(skb->len << 16); dma_wmb(); /* TACT bit must be set after all the above writes */ if (entry >= mdp->num_tx_ring - 1) - txdesc->status |= cpu_to_edmac(mdp, TD_TACT | TD_TDLE); + txdesc->status |= cpu_to_le32(TD_TACT | TD_TDLE); else - txdesc->status |= cpu_to_edmac(mdp, TD_TACT); + txdesc->status |= cpu_to_le32(TD_TACT); mdp->cur_tx++; @@ -3067,8 +3071,6 @@ static int sh_eth_drv_probe(struct platform_device *pdev) /* get PHY ID */ mdp->phy_id = pd->phy; mdp->phy_interface = pd->phy_interface; - /* EDMAC endian */ - mdp->edmac_endian = pd->edmac_endian; mdp->no_ether_link = pd->no_ether_link; mdp->ether_link_active_low = pd->ether_link_active_low; diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 50382b1c9ddcf..8fa4ef3a7fdd2 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -283,7 +283,7 @@ enum DMAC_IM_BIT { DMAC_M_RINT1 = 0x00000001, }; -/* Receive descriptor bit */ +/* Receive descriptor 0 bits */ enum RD_STS_BIT { RD_RACT = 0x80000000, RD_RDLE = 0x40000000, RD_RFP1 = 0x20000000, RD_RFP0 = 0x10000000, @@ -298,6 +298,12 @@ enum RD_STS_BIT { #define RDFEND RD_RFP0 #define RD_RFP (RD_RFP1|RD_RFP0) +/* Receive descriptor 1 bits */ +enum RD_LEN_BIT { + RD_RFL = 0x0000ffff, /* receive frame length */ + RD_RBL = 0xffff0000, /* receive buffer length */ +}; + /* FCFTR */ enum FCFTR_BIT { FCFTR_RFF2 = 0x00040000, FCFTR_RFF1 = 0x00020000, @@ -307,7 +313,7 @@ enum FCFTR_BIT { #define DEFAULT_FIFO_F_D_RFF (FCFTR_RFF2 | FCFTR_RFF1 | FCFTR_RFF0) #define DEFAULT_FIFO_F_D_RFD (FCFTR_RFD2 | FCFTR_RFD1 | FCFTR_RFD0) -/* Transmit descriptor bit */ +/* Transmit descriptor 0 bits */ enum TD_STS_BIT { TD_TACT = 0x80000000, TD_TDLE = 0x40000000, TD_TFP1 = 0x20000000, TD_TFP0 = 0x10000000, @@ -317,6 +323,11 @@ enum TD_STS_BIT { #define TDFEND TD_TFP0 #define TD_TFP (TD_TFP1|TD_TFP0) +/* Transmit descriptor 1 bits */ +enum TD_LEN_BIT { + TD_TBL = 0xffff0000, /* transmit buffer length */ +}; + /* RMCR */ enum RMCR_BIT { RMCR_RNC = 0x00000001, @@ -425,15 +436,9 @@ enum TSU_FWSLC_BIT { */ struct sh_eth_txdesc { u32 status; /* TD0 */ -#if defined(__LITTLE_ENDIAN) - u16 pad0; /* TD1 */ - u16 buffer_length; /* TD1 */ -#else - u16 buffer_length; /* TD1 */ - u16 pad0; /* TD1 */ -#endif + u32 len; /* TD1 */ u32 addr; /* TD2 */ - u32 pad1; /* padding data */ + u32 pad0; /* padding data */ } __aligned(2) __packed; /* The sh ether Rx buffer descriptors. @@ -441,13 +446,7 @@ struct sh_eth_txdesc { */ struct sh_eth_rxdesc { u32 status; /* RD0 */ -#if defined(__LITTLE_ENDIAN) - u16 frame_length; /* RD1 */ - u16 buffer_length; /* RD1 */ -#else - u16 buffer_length; /* RD1 */ - u16 frame_length; /* RD1 */ -#endif + u32 len; /* RD1 */ u32 addr; /* RD2 */ u32 pad0; /* padding data */ } __aligned(2) __packed; @@ -514,7 +513,6 @@ struct sh_eth_private { u32 cur_rx, dirty_rx; /* Producer/consumer ring indices */ u32 cur_tx, dirty_tx; u32 rx_buf_sz; /* Based on MTU+slack. */ - int edmac_endian; struct napi_struct napi; bool irq_enabled; /* MII transceiver section. */ @@ -546,31 +544,6 @@ static inline void sh_eth_soft_swap(char *src, int len) #endif } -#define SH_ETH_OFFSET_INVALID ((u16) ~0) - -static inline void sh_eth_write(struct net_device *ndev, u32 data, - int enum_index) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - u16 offset = mdp->reg_offset[enum_index]; - - if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) - return; - - iowrite32(data, mdp->addr + offset); -} - -static inline u32 sh_eth_read(struct net_device *ndev, int enum_index) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - u16 offset = mdp->reg_offset[enum_index]; - - if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) - return ~0U; - - return ioread32(mdp->addr + offset); -} - static inline void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index c4a0e8a967dd7..98d33d462c6ca 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -486,10 +486,17 @@ static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n) BUILD_BUG_ON(MC_CMD_ALLOC_PIOBUF_IN_LEN != 0); for (i = 0; i < n; i++) { - rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_PIOBUF, NULL, 0, - outbuf, sizeof(outbuf), &outlen); - if (rc) + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_ALLOC_PIOBUF, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) { + /* Don't display the MC error if we didn't have space + * for a VF. + */ + if (!(efx_ef10_is_vf(efx) && rc == -ENOSPC)) + efx_mcdi_display_error(efx, MC_CMD_ALLOC_PIOBUF, + 0, outbuf, outlen, rc); break; + } if (outlen < MC_CMD_ALLOC_PIOBUF_OUT_LEN) { rc = -EIO; break; @@ -3309,7 +3316,8 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx, new_spec.priority = EFX_FILTER_PRI_AUTO; new_spec.flags = (EFX_FILTER_FLAG_RX | - EFX_FILTER_FLAG_RX_RSS); + (efx_rss_enabled(efx) ? + EFX_FILTER_FLAG_RX_RSS : 0)); new_spec.dmaq_id = 0; new_spec.rss_context = EFX_FILTER_RSS_CONTEXT_DEFAULT; rc = efx_ef10_filter_push(efx, &new_spec, @@ -3832,13 +3840,12 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx) MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE); MCDI_SET_QWORD(inbuf, FILTER_OP_IN_HANDLE, table->entry[filter_idx].handle); - rc = efx_mcdi_rpc(efx, MC_CMD_FILTER_OP, inbuf, sizeof(inbuf), - NULL, 0, NULL); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FILTER_OP, inbuf, + sizeof(inbuf), NULL, 0, NULL); if (rc) - netdev_WARN(efx->net_dev, - "filter_idx=%#x handle=%#llx\n", - filter_idx, - table->entry[filter_idx].handle); + netif_info(efx, drv, efx->net_dev, + "%s: filter %04x remove failed\n", + __func__, filter_idx); kfree(spec); } @@ -3847,11 +3854,14 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx) } #define EFX_EF10_FILTER_DO_MARK_OLD(id) \ - if (id != EFX_EF10_FILTER_ID_INVALID) { \ - filter_idx = efx_ef10_filter_get_unsafe_id(efx, id); \ - WARN_ON(!table->entry[filter_idx].spec); \ - table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD; \ - } + if (id != EFX_EF10_FILTER_ID_INVALID) { \ + filter_idx = efx_ef10_filter_get_unsafe_id(efx, id); \ + if (!table->entry[filter_idx].spec) \ + netif_dbg(efx, drv, efx->net_dev, \ + "%s: marked null spec old %04x:%04x\n", \ + __func__, id, filter_idx); \ + table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;\ + } static void efx_ef10_filter_mark_old(struct efx_nic *efx) { struct efx_ef10_filter_table *table = efx->filter_state; @@ -3931,6 +3941,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, { struct efx_ef10_filter_table *table = efx->filter_state; struct efx_ef10_dev_addr *addr_list; + enum efx_filter_flags filter_flags; struct efx_filter_spec spec; u8 baddr[ETH_ALEN]; unsigned int i, j; @@ -3945,11 +3956,11 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, addr_count = table->dev_uc_count; } + filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0; + /* Insert/renew filters */ for (i = 0; i < addr_count; i++) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, addr_list[i].addr); rc = efx_ef10_filter_insert(efx, &spec, true); @@ -3978,9 +3989,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, if (multicast && rollback) { /* Also need an Ethernet broadcast filter */ - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr); rc = efx_ef10_filter_insert(efx, &spec, true); @@ -4010,13 +4019,14 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast, { struct efx_ef10_filter_table *table = efx->filter_state; struct efx_ef10_nic_data *nic_data = efx->nic_data; + enum efx_filter_flags filter_flags; struct efx_filter_spec spec; u8 baddr[ETH_ALEN]; int rc; - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0; + + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); if (multicast) efx_filter_set_mc_def(&spec); @@ -4025,16 +4035,16 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast, rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { - netif_warn(efx, drv, efx->net_dev, - "%scast mismatch filter insert failed rc=%d\n", - multicast ? "Multi" : "Uni", rc); + netif_printk(efx, drv, rc == -EPERM ? KERN_DEBUG : KERN_WARNING, + efx->net_dev, + "%scast mismatch filter insert failed rc=%d\n", + multicast ? "Multi" : "Uni", rc); } else if (multicast) { table->mcdef_id = efx_ef10_filter_get_unsafe_id(efx, rc); if (!nic_data->workaround_26807) { /* Also need an Ethernet broadcast filter */ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr); @@ -4070,19 +4080,31 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast, static void efx_ef10_filter_remove_old(struct efx_nic *efx) { struct efx_ef10_filter_table *table = efx->filter_state; - bool remove_failed = false; + int remove_failed = 0; + int remove_noent = 0; + int rc; int i; for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) { if (ACCESS_ONCE(table->entry[i].spec) & EFX_EF10_FILTER_FLAG_AUTO_OLD) { - if (efx_ef10_filter_remove_internal( - efx, 1U << EFX_FILTER_PRI_AUTO, - i, true) < 0) - remove_failed = true; + rc = efx_ef10_filter_remove_internal(efx, + 1U << EFX_FILTER_PRI_AUTO, i, true); + if (rc == -ENOENT) + remove_noent++; + else if (rc) + remove_failed++; } } - WARN_ON(remove_failed); + + if (remove_failed) + netif_info(efx, drv, efx->net_dev, + "%s: failed to remove %d filters\n", + __func__, remove_failed); + if (remove_noent) + netif_info(efx, drv, efx->net_dev, + "%s: failed to remove %d non-existent filters\n", + __func__, remove_noent); } static int efx_ef10_vport_set_mac_address(struct efx_nic *efx) diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index b405349a570c2..0705ec8694879 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -3128,10 +3128,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev, net_dev->features |= (efx->type->offload_features | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_RXCSUM); - if (efx->type->offload_features & NETIF_F_V6_CSUM) + if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) net_dev->features |= NETIF_F_TSO6; /* Mask for features that also apply to VLAN devices */ - net_dev->vlan_features |= (NETIF_F_ALL_CSUM | NETIF_F_SG | + net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_ALL_TSO | NETIF_F_RXCSUM); /* All offloads can be toggled */ @@ -3174,14 +3174,15 @@ static int efx_pci_probe(struct pci_dev *pci_dev, rtnl_lock(); rc = efx_mtd_probe(efx); rtnl_unlock(); - if (rc) + if (rc && rc != -EPERM) netif_warn(efx, probe, efx->net_dev, "failed to create MTDs (%d)\n", rc); rc = pci_enable_pcie_error_reporting(pci_dev); if (rc && rc != -EINVAL) - netif_warn(efx, probe, efx->net_dev, - "pci_enable_pcie_error_reporting failed (%d)\n", rc); + netif_notice(efx, probe, efx->net_dev, + "PCIE error reporting unavailable (%d).\n", + rc); return 0; diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 1aaf76c1ace86..10827476bc0b3 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -76,6 +76,11 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); #define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_35388(efx) ? \ EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE) +static inline bool efx_rss_enabled(struct efx_nic *efx) +{ + return efx->rss_spread > 1; +} + /* Filters */ void efx_mac_reconfigure(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 5a1c5a8f278ad..133e9e35be9e9 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -2242,7 +2242,7 @@ efx_farch_filter_init_rx_auto(struct efx_nic *efx, */ spec->priority = EFX_FILTER_PRI_AUTO; spec->flags = (EFX_FILTER_FLAG_RX | - (efx->n_rx_channels > 1 ? EFX_FILTER_FLAG_RX_RSS : 0) | + (efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0) | (efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0)); spec->dmaq_id = 0; } diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 41fb6b60a3f07..d28e7dd8fa3ca 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -82,6 +82,7 @@ int efx_mcdi_init(struct efx_nic *efx) mcdi->logging_enabled = mcdi_logging_default; #endif init_waitqueue_head(&mcdi->wq); + init_waitqueue_head(&mcdi->proxy_rx_wq); spin_lock_init(&mcdi->iface_lock); mcdi->state = MCDI_STATE_QUIESCENT; mcdi->mode = MCDI_MODE_POLL; @@ -315,6 +316,7 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx) } #endif + mcdi->resprc_raw = 0; if (error && mcdi->resp_data_len == 0) { netif_err(efx, hw, efx->net_dev, "MC rebooted\n"); mcdi->resprc = -EIO; @@ -325,8 +327,8 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx) mcdi->resprc = -EIO; } else if (error) { efx->type->mcdi_read_response(efx, &hdr, mcdi->resp_hdr_len, 4); - mcdi->resprc = - efx_mcdi_errno(EFX_DWORD_FIELD(hdr, EFX_DWORD_0)); + mcdi->resprc_raw = EFX_DWORD_FIELD(hdr, EFX_DWORD_0); + mcdi->resprc = efx_mcdi_errno(mcdi->resprc_raw); } else { mcdi->resprc = 0; } @@ -621,9 +623,30 @@ efx_mcdi_check_supported(struct efx_nic *efx, unsigned int cmd, size_t inlen) return 0; } -static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, +static bool efx_mcdi_get_proxy_handle(struct efx_nic *efx, + size_t hdr_len, size_t data_len, + u32 *proxy_handle) +{ + MCDI_DECLARE_BUF_ERR(testbuf); + const size_t buflen = sizeof(testbuf); + + if (!proxy_handle || data_len < buflen) + return false; + + efx->type->mcdi_read_response(efx, testbuf, hdr_len, buflen); + if (MCDI_DWORD(testbuf, ERR_CODE) == MC_CMD_ERR_PROXY_PENDING) { + *proxy_handle = MCDI_DWORD(testbuf, ERR_PROXY_PENDING_HANDLE); + return true; + } + + return false; +} + +static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned int cmd, + size_t inlen, efx_dword_t *outbuf, size_t outlen, - size_t *outlen_actual, bool quiet) + size_t *outlen_actual, bool quiet, + u32 *proxy_handle, int *raw_rc) { struct efx_mcdi_iface *mcdi = efx_mcdi(efx); MCDI_DECLARE_BUF_ERR(errbuf); @@ -657,6 +680,9 @@ static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, spin_unlock_bh(&mcdi->iface_lock); } + if (proxy_handle) + *proxy_handle = 0; + if (rc != 0) { if (outlen_actual) *outlen_actual = 0; @@ -669,6 +695,8 @@ static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, * acquiring the iface_lock. */ spin_lock_bh(&mcdi->iface_lock); rc = mcdi->resprc; + if (raw_rc) + *raw_rc = mcdi->resprc_raw; hdr_len = mcdi->resp_hdr_len; data_len = mcdi->resp_data_len; err_len = min(sizeof(errbuf), data_len); @@ -689,6 +717,12 @@ static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, netif_err(efx, hw, efx->net_dev, "MC fatal error %d\n", -rc); efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); + } else if (proxy_handle && (rc == -EPROTO) && + efx_mcdi_get_proxy_handle(efx, hdr_len, data_len, + proxy_handle)) { + mcdi->proxy_rx_status = 0; + mcdi->proxy_rx_handle = 0; + mcdi->state = MCDI_STATE_PROXY_WAIT; } else if (rc && !quiet) { efx_mcdi_display_error(efx, cmd, inlen, errbuf, err_len, rc); @@ -701,34 +735,195 @@ static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, } } - efx_mcdi_release(mcdi); + if (!proxy_handle || !*proxy_handle) + efx_mcdi_release(mcdi); return rc; } -static int _efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, +static void efx_mcdi_proxy_abort(struct efx_mcdi_iface *mcdi) +{ + if (mcdi->state == MCDI_STATE_PROXY_WAIT) { + /* Interrupt the proxy wait. */ + mcdi->proxy_rx_status = -EINTR; + wake_up(&mcdi->proxy_rx_wq); + } +} + +static void efx_mcdi_ev_proxy_response(struct efx_nic *efx, + u32 handle, int status) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + WARN_ON(mcdi->state != MCDI_STATE_PROXY_WAIT); + + mcdi->proxy_rx_status = efx_mcdi_errno(status); + /* Ensure the status is written before we update the handle, since the + * latter is used to check if we've finished. + */ + wmb(); + mcdi->proxy_rx_handle = handle; + wake_up(&mcdi->proxy_rx_wq); +} + +static int efx_mcdi_proxy_wait(struct efx_nic *efx, u32 handle, bool quiet) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + int rc; + + /* Wait for a proxy event, or timeout. */ + rc = wait_event_timeout(mcdi->proxy_rx_wq, + mcdi->proxy_rx_handle != 0 || + mcdi->proxy_rx_status == -EINTR, + MCDI_RPC_TIMEOUT); + + if (rc <= 0) { + netif_dbg(efx, hw, efx->net_dev, + "MCDI proxy timeout %d\n", handle); + return -ETIMEDOUT; + } else if (mcdi->proxy_rx_handle != handle) { + netif_warn(efx, hw, efx->net_dev, + "MCDI proxy unexpected handle %d (expected %d)\n", + mcdi->proxy_rx_handle, handle); + return -EINVAL; + } + + return mcdi->proxy_rx_status; +} + +static int _efx_mcdi_rpc(struct efx_nic *efx, unsigned int cmd, const efx_dword_t *inbuf, size_t inlen, efx_dword_t *outbuf, size_t outlen, - size_t *outlen_actual, bool quiet) + size_t *outlen_actual, bool quiet, int *raw_rc) { + u32 proxy_handle = 0; /* Zero is an invalid proxy handle. */ int rc; + if (inbuf && inlen && (inbuf == outbuf)) { + /* The input buffer can't be aliased with the output. */ + WARN_ON(1); + return -EINVAL; + } + rc = efx_mcdi_rpc_start(efx, cmd, inbuf, inlen); - if (rc) { - if (outlen_actual) - *outlen_actual = 0; + if (rc) return rc; + + rc = _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, + outlen_actual, quiet, &proxy_handle, raw_rc); + + if (proxy_handle) { + /* Handle proxy authorisation. This allows approval of MCDI + * operations to be delegated to the admin function, allowing + * fine control over (eg) multicast subscriptions. + */ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + netif_dbg(efx, hw, efx->net_dev, + "MCDI waiting for proxy auth %d\n", + proxy_handle); + rc = efx_mcdi_proxy_wait(efx, proxy_handle, quiet); + + if (rc == 0) { + netif_dbg(efx, hw, efx->net_dev, + "MCDI proxy retry %d\n", proxy_handle); + + /* We now retry the original request. */ + mcdi->state = MCDI_STATE_RUNNING_SYNC; + efx_mcdi_send_request(efx, cmd, inbuf, inlen); + + rc = _efx_mcdi_rpc_finish(efx, cmd, inlen, + outbuf, outlen, outlen_actual, + quiet, NULL, raw_rc); + } else { + netif_printk(efx, hw, + rc == -EPERM ? KERN_DEBUG : KERN_ERR, + efx->net_dev, + "MC command 0x%x failed after proxy auth rc=%d\n", + cmd, rc); + + if (rc == -EINTR || rc == -EIO) + efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); + efx_mcdi_release(mcdi); + } } - return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, - outlen_actual, quiet); + + return rc; } +static int _efx_mcdi_rpc_evb_retry(struct efx_nic *efx, unsigned cmd, + const efx_dword_t *inbuf, size_t inlen, + efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual, bool quiet) +{ + int raw_rc = 0; + int rc; + + rc = _efx_mcdi_rpc(efx, cmd, inbuf, inlen, + outbuf, outlen, outlen_actual, true, &raw_rc); + + if ((rc == -EPROTO) && (raw_rc == MC_CMD_ERR_NO_EVB_PORT) && + efx->type->is_vf) { + /* If the EVB port isn't available within a VF this may + * mean the PF is still bringing the switch up. We should + * retry our request shortly. + */ + unsigned long abort_time = jiffies + MCDI_RPC_TIMEOUT; + unsigned int delay_us = 10000; + + netif_dbg(efx, hw, efx->net_dev, + "%s: NO_EVB_PORT; will retry request\n", + __func__); + + do { + usleep_range(delay_us, delay_us + 10000); + rc = _efx_mcdi_rpc(efx, cmd, inbuf, inlen, + outbuf, outlen, outlen_actual, + true, &raw_rc); + if (delay_us < 100000) + delay_us <<= 1; + } while ((rc == -EPROTO) && + (raw_rc == MC_CMD_ERR_NO_EVB_PORT) && + time_before(jiffies, abort_time)); + } + + if (rc && !quiet && !(cmd == MC_CMD_REBOOT && rc == -EIO)) + efx_mcdi_display_error(efx, cmd, inlen, + outbuf, outlen, rc); + + return rc; +} + +/** + * efx_mcdi_rpc - Issue an MCDI command and wait for completion + * @efx: NIC through which to issue the command + * @cmd: Command type number + * @inbuf: Command parameters + * @inlen: Length of command parameters, in bytes. Must be a multiple + * of 4 and no greater than %MCDI_CTL_SDU_LEN_MAX_V1. + * @outbuf: Response buffer. May be %NULL if @outlen is 0. + * @outlen: Length of response buffer, in bytes. If the actual + * response is longer than @outlen & ~3, it will be truncated + * to that length. + * @outlen_actual: Pointer through which to return the actual response + * length. May be %NULL if this is not needed. + * + * This function may sleep and therefore must be called in an appropriate + * context. + * + * Return: A negative error code, or zero if successful. The error + * code may come from the MCDI response or may indicate a failure + * to communicate with the MC. In the former case, the response + * will still be copied to @outbuf and *@outlen_actual will be + * set accordingly. In the latter case, *@outlen_actual will be + * set to zero. + */ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const efx_dword_t *inbuf, size_t inlen, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual) { - return _efx_mcdi_rpc(efx, cmd, inbuf, inlen, outbuf, outlen, - outlen_actual, false); + return _efx_mcdi_rpc_evb_retry(efx, cmd, inbuf, inlen, outbuf, outlen, + outlen_actual, false); } /* Normally, on receiving an error code in the MCDI response, @@ -744,8 +939,8 @@ int efx_mcdi_rpc_quiet(struct efx_nic *efx, unsigned cmd, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual) { - return _efx_mcdi_rpc(efx, cmd, inbuf, inlen, outbuf, outlen, - outlen_actual, true); + return _efx_mcdi_rpc_evb_retry(efx, cmd, inbuf, inlen, outbuf, outlen, + outlen_actual, true); } int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, @@ -866,7 +1061,7 @@ int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, size_t *outlen_actual) { return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, - outlen_actual, false); + outlen_actual, false, NULL, NULL); } int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, size_t inlen, @@ -874,7 +1069,7 @@ int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, size_t inlen, size_t *outlen_actual) { return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, - outlen_actual, true); + outlen_actual, true, NULL, NULL); } void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd, @@ -887,9 +1082,10 @@ void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd, code = MCDI_DWORD(outbuf, ERR_CODE); if (outlen >= MC_CMD_ERR_ARG_OFST + 4) err_arg = MCDI_DWORD(outbuf, ERR_ARG); - netif_err(efx, hw, efx->net_dev, - "MC command 0x%x inlen %d failed rc=%d (raw=%d) arg=%d\n", - cmd, (int)inlen, rc, code, err_arg); + netif_printk(efx, hw, rc == -EPERM ? KERN_DEBUG : KERN_ERR, + efx->net_dev, + "MC command 0x%x inlen %zu failed rc=%d (raw=%d) arg=%d\n", + cmd, inlen, rc, code, err_arg); } /* Switch to polled MCDI completions. This can be called in various @@ -1014,8 +1210,13 @@ static void efx_mcdi_ev_death(struct efx_nic *efx, int rc) * receiving a REBOOT event after posting the MCDI * request. Did the mc reboot before or after the copyout? The * best we can do always is just return failure. + * + * If there is an outstanding proxy response expected it is not going + * to arrive. We should thus abort it. */ spin_lock(&mcdi->iface_lock); + efx_mcdi_proxy_abort(mcdi); + if (efx_mcdi_complete_sync(mcdi)) { if (mcdi->mode == MCDI_MODE_EVENTS) { mcdi->resprc = rc; @@ -1063,6 +1264,8 @@ static void efx_mcdi_ev_bist(struct efx_nic *efx) spin_lock(&mcdi->iface_lock); efx->mc_bist_for_other_fn = true; + efx_mcdi_proxy_abort(mcdi); + if (efx_mcdi_complete_sync(mcdi)) { if (mcdi->mode == MCDI_MODE_EVENTS) { mcdi->resprc = -EIO; @@ -1171,6 +1374,11 @@ void efx_mcdi_process_event(struct efx_channel *channel, EFX_QWORD_VAL(*event)); efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR); break; + case MCDI_EVENT_CODE_PROXY_RESPONSE: + efx_mcdi_ev_proxy_response(efx, + MCDI_EVENT_FIELD(*event, PROXY_RESPONSE_HANDLE), + MCDI_EVENT_FIELD(*event, PROXY_RESPONSE_RC)); + break; default: netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n", code); diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 025d504c472b5..c9aeb0701c9a6 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -17,6 +17,8 @@ * @MCDI_STATE_RUNNING_SYNC: There is a synchronous MCDI request pending. * Only the thread that moved into this state is allowed to move out of it. * @MCDI_STATE_RUNNING_ASYNC: There is an asynchronous MCDI request pending. + * @MCDI_STATE_PROXY_WAIT: An MCDI request has completed with a response that + * indicates we must wait for a proxy try again message. * @MCDI_STATE_COMPLETED: An MCDI request has completed, but the owning thread * has not yet consumed the result. For all other threads, equivalent to * %MCDI_STATE_RUNNING. @@ -25,6 +27,7 @@ enum efx_mcdi_state { MCDI_STATE_QUIESCENT, MCDI_STATE_RUNNING_SYNC, MCDI_STATE_RUNNING_ASYNC, + MCDI_STATE_PROXY_WAIT, MCDI_STATE_COMPLETED, }; @@ -60,6 +63,9 @@ enum efx_mcdi_mode { * @async_timer: Timer for asynchronous request timeout * @logging_buffer: buffer that may be used to build MCDI tracing messages * @logging_enabled: whether to trace MCDI + * @proxy_rx_handle: Most recently received proxy authorisation handle + * @proxy_rx_status: Status of most recent proxy authorisation + * @proxy_rx_wq: Wait queue for updates to proxy_rx_handle */ struct efx_mcdi_iface { struct efx_nic *efx; @@ -71,6 +77,7 @@ struct efx_mcdi_iface { unsigned int credits; unsigned int seqno; int resprc; + int resprc_raw; size_t resp_hdr_len; size_t resp_data_len; spinlock_t async_lock; @@ -80,6 +87,9 @@ struct efx_mcdi_iface { char *logging_buffer; bool logging_enabled; #endif + unsigned int proxy_rx_handle; + int proxy_rx_status; + wait_queue_head_t proxy_rx_wq; }; struct efx_mcdi_mon { diff --git a/drivers/net/ethernet/sfc/txc43128_phy.c b/drivers/net/ethernet/sfc/txc43128_phy.c index 3d5ee3259885d..194f67d9f3bfa 100644 --- a/drivers/net/ethernet/sfc/txc43128_phy.c +++ b/drivers/net/ethernet/sfc/txc43128_phy.c @@ -418,7 +418,7 @@ static void txc_reset_logic_mmd(struct efx_nic *efx, int mmd) val |= (1 << TXC_GLCMD_LMTSWRST_LBN); efx_mdio_write(efx, mmd, TXC_GLRGS_GLCMD, val); - while (tries--) { + while (--tries) { val = efx_mdio_read(efx, mmd, TXC_GLRGS_GLCMD); if (!(val & (1 << TXC_GLCMD_LMTSWRST_LBN))) break; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index f4518bc2cd288..1e19c8fd8b823 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -439,7 +439,7 @@ struct stmmac_ops { /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data); - void (*config_sub_second_increment) (void __iomem *ioaddr); + u32 (*config_sub_second_increment) (void __iomem *ioaddr, u32 clk_rate); int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec); int (*config_addend) (void __iomem *ioaddr, u32 addend); int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 401383b252a8f..f0d797ab74d8f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -32,6 +32,7 @@ #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII 0x2 #define SYSMGR_EMACGRP_CTRL_PHYSEL_WIDTH 2 #define SYSMGR_EMACGRP_CTRL_PHYSEL_MASK 0x00000003 +#define SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK 0x00000010 #define EMAC_SPLITTER_CTRL_REG 0x0 #define EMAC_SPLITTER_CTRL_SPEED_MASK 0x3 @@ -47,6 +48,7 @@ struct socfpga_dwmac { struct regmap *sys_mgr_base_addr; struct reset_control *stmmac_rst; void __iomem *splitter_base; + bool f2h_ptp_ref_clk; }; static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) @@ -116,6 +118,8 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * return -EINVAL; } + dwmac->f2h_ptp_ref_clk = of_property_read_bool(np, "altr,f2h_ptp_ref_clk"); + np_splitter = of_parse_phandle(np, "altr,emac-splitter", 0); if (np_splitter) { if (of_address_to_resource(np_splitter, 0, &res_splitter)) { @@ -171,6 +175,11 @@ static int socfpga_dwmac_setup(struct socfpga_dwmac *dwmac) ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK << reg_shift); ctrl |= val << reg_shift; + if (dwmac->f2h_ptp_ref_clk) + ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2); + else + ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2)); + regmap_write(sys_mgr_base_addr, reg_offset, ctrl); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 52b8ed9bd87c2..adff46375a322 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -153,7 +153,11 @@ static int sun7i_gmac_probe(struct platform_device *pdev) if (ret) return ret; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + sun7i_gmac_exit(pdev, plat_dat->bsp_priv); + + return ret; } static const struct of_device_id sun7i_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 76ad214b40369..a77f68918010d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -33,22 +33,25 @@ static void stmmac_config_hw_tstamping(void __iomem *ioaddr, u32 data) writel(data, ioaddr + PTP_TCR); } -static void stmmac_config_sub_second_increment(void __iomem *ioaddr) +static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, + u32 ptp_clock) { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; /* Convert the ptp_clock to nano second - * formula = (1/ptp_clock) * 1000000000 + * formula = (2/ptp_clock) * 1000000000 * where, ptp_clock = 50MHz. */ - data = (1000000000ULL / 50000000); + data = (2000000000ULL / ptp_clock); /* 0.465ns accuracy */ if (!(value & PTP_TCR_TSCTRLSSR)) data = (data * 1000) / 465; writel(data, ioaddr + PTP_SSIR); + + return data; } static int stmmac_init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3c6549aee11de..c21015b68097a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -53,6 +53,7 @@ #include "stmmac.h" #include <linux/reset.h> #include <linux/of_mdio.h> +#include "dwmac1000.h" #define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) @@ -185,7 +186,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv) priv->clk_csr = STMMAC_CSR_100_150M; else if ((clk_rate >= CSR_F_150M) && (clk_rate < CSR_F_250M)) priv->clk_csr = STMMAC_CSR_150_250M; - else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M)) + else if ((clk_rate >= CSR_F_250M) && (clk_rate < CSR_F_300M)) priv->clk_csr = STMMAC_CSR_250_300M; } } @@ -435,6 +436,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) u32 ts_master_en = 0; u32 ts_event_en = 0; u32 value = 0; + u32 sec_inc; if (!(priv->dma_cap.time_stamp || priv->adv_ts)) { netdev_alert(priv->dev, "No support for HW time stamping\n"); @@ -598,24 +600,19 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) tstamp_all | ptp_v2 | ptp_over_ethernet | ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | ts_master_en | snap_type_sel); - priv->hw->ptp->config_hw_tstamping(priv->ioaddr, value); /* program Sub Second Increment reg */ - priv->hw->ptp->config_sub_second_increment(priv->ioaddr); + sec_inc = priv->hw->ptp->config_sub_second_increment( + priv->ioaddr, priv->clk_ptp_rate); + temp = div_u64(1000000000ULL, sec_inc); /* calculate default added value: * formula is : * addend = (2^32)/freq_div_ratio; - * where, freq_div_ratio = clk_ptp_ref_i/50MHz - * hence, addend = ((2^32) * 50MHz)/clk_ptp_ref_i; - * NOTE: clk_ptp_ref_i should be >= 50MHz to - * achieve 20ns accuracy. - * - * 2^x * y == (y << x), hence - * 2^32 * 50000000 ==> (50000000 << 32) + * where, freq_div_ratio = 1e9ns/sec_inc */ - temp = (u64) (50000000ULL << 32); + temp = (u64)(temp << 32); priv->default_addend = div_u64(temp, priv->clk_ptp_rate); priv->hw->ptp->config_addend(priv->ioaddr, priv->default_addend); @@ -2402,7 +2399,7 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev, features &= ~NETIF_F_RXCSUM; if (!priv->plat->tx_coe) - features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_CSUM_MASK; /* Some GMAC devices have a bugged Jumbo frame support that * needs to have the Tx COE disabled for oversized frames @@ -2410,7 +2407,7 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev, * the TX csum insertionin the TDES and not use SF. */ if (priv->plat->bugged_jumbo && (dev->mtu > ETH_DATA_LEN)) - features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_CSUM_MASK; return features; } @@ -3046,8 +3043,6 @@ int stmmac_suspend(struct net_device *ndev) priv->hw->dma->stop_tx(priv->ioaddr); priv->hw->dma->stop_rx(priv->ioaddr); - stmmac_clear_descriptors(priv); - /* Enable Power down mode by programming the PMT regs */ if (device_may_wakeup(priv->device)) { priv->hw->mac->pmt(priv->hw, priv->wolopts); @@ -3105,7 +3100,12 @@ int stmmac_resume(struct net_device *ndev) netif_device_attach(ndev); - init_dma_desc_rings(ndev, GFP_ATOMIC); + priv->cur_rx = 0; + priv->dirty_rx = 0; + priv->dirty_tx = 0; + priv->cur_tx = 0; + stmmac_clear_descriptors(priv); + stmmac_hw_setup(ndev, false); stmmac_init_tx_coalesce(priv); stmmac_set_rx_mode(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index bba670c42e374..16c85ccd1762c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -29,7 +29,7 @@ #include <linux/slab.h> #include <linux/of.h> #include <linux/of_gpio.h> - +#include <linux/of_mdio.h> #include <asm/io.h> #include "stmmac.h" @@ -200,10 +200,29 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; int addr, found; + struct device_node *mdio_node = NULL; + struct device_node *child_node = NULL; if (!mdio_bus_data) return 0; + if (IS_ENABLED(CONFIG_OF)) { + for_each_child_of_node(priv->device->of_node, child_node) { + if (of_device_is_compatible(child_node, + "snps,dwmac-mdio")) { + mdio_node = child_node; + break; + } + } + + if (mdio_node) { + netdev_dbg(ndev, "FOUND MDIO subnode\n"); + } else { + netdev_err(ndev, "NO MDIO subnode\n"); + return 0; + } + } + new_bus = mdiobus_alloc(); if (new_bus == NULL) return -ENOMEM; @@ -231,7 +250,8 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->irq = irqlist; new_bus->phy_mask = mdio_bus_data->phy_mask; new_bus->parent = priv->device; - err = mdiobus_register(new_bus); + + err = of_mdiobus_register(new_bus, mdio_node); if (err != 0) { pr_err("%s: Cannot register as MDIO bus\n", new_bus->name); goto bus_register_fail; @@ -284,7 +304,7 @@ int stmmac_mdio_register(struct net_device *ndev) } } - if (!found) { + if (!found && !mdio_node) { pr_warn("%s: No PHY found\n", ndev->name); mdiobus_unregister(new_bus); mdiobus_free(new_bus); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index d02691ba3d7fe..6a52fa18cbf2e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -146,7 +146,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if (plat->phy_node || plat->phy_bus_name) + if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 15322c08de80e..34ce7dce8c9db 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2026,45 +2026,54 @@ static int cpsw_probe_dt(struct cpsw_priv *priv, for_each_child_of_node(node, slave_node) { struct cpsw_slave_data *slave_data = data->slave_data + i; const void *mac_addr = NULL; - u32 phyid; int lenp; const __be32 *parp; - struct device_node *mdio_node; - struct platform_device *mdio; /* This is no slave child node, continue */ if (strcmp(slave_node->name, "slave")) continue; priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); + parp = of_get_property(slave_node, "phy_id", &lenp); if (of_phy_is_fixed_link(slave_node)) { - struct phy_device *pd; + struct device_node *phy_node; + struct phy_device *phy_dev; + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ ret = of_phy_register_fixed_link(slave_node); if (ret) return ret; - pd = of_phy_find_device(slave_node); - if (!pd) + phy_node = of_node_get(slave_node); + phy_dev = of_phy_find_device(phy_node); + if (!phy_dev) return -ENODEV; snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, pd->bus->id, pd->phy_id); - goto no_phy_slave; - } - parp = of_get_property(slave_node, "phy_id", &lenp); - if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) { - dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i); + PHY_ID_FMT, phy_dev->bus->id, phy_dev->addr); + } else if (parp) { + u32 phyid; + struct device_node *mdio_node; + struct platform_device *mdio; + + if (lenp != (sizeof(__be32) * 2)) { + dev_err(&pdev->dev, "Invalid slave[%d] phy_id property\n", i); + goto no_phy_slave; + } + mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); + phyid = be32_to_cpup(parp+1); + mdio = of_find_device_by_node(mdio_node); + of_node_put(mdio_node); + if (!mdio) { + dev_err(&pdev->dev, "Missing mdio platform device\n"); + return -EINVAL; + } + snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), + PHY_ID_FMT, mdio->name, phyid); + } else { + dev_err(&pdev->dev, "No slave[%d] phy_id or fixed-link property\n", i); goto no_phy_slave; } - mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); - phyid = be32_to_cpup(parp+1); - mdio = of_find_device_by_node(mdio_node); - of_node_put(mdio_node); - if (!mdio) { - dev_err(&pdev->dev, "Missing mdio platform device\n"); - return -EINVAL; - } - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, mdio->name, phyid); slave_data->phy_if = of_get_phy_mode(slave_node); if (slave_data->phy_if < 0) { dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", @@ -2418,7 +2427,7 @@ static int cpsw_probe(struct platform_device *pdev) ndev->irq = platform_get_irq(pdev, 1); if (ndev->irq < 0) { dev_err(priv->dev, "error getting irq resource\n"); - ret = -ENOENT; + ret = ndev->irq; goto clean_ale_ret; } @@ -2439,8 +2448,10 @@ static int cpsw_probe(struct platform_device *pdev) /* RX IRQ */ irq = platform_get_irq(pdev, 1); - if (irq < 0) + if (irq < 0) { + ret = irq; goto clean_ale_ret; + } priv->irqs_table[0] = irq; ret = devm_request_irq(&pdev->dev, irq, cpsw_rx_interrupt, @@ -2452,8 +2463,10 @@ static int cpsw_probe(struct platform_device *pdev) /* TX IRQ */ irq = platform_get_irq(pdev, 2); - if (irq < 0) + if (irq < 0) { + ret = irq; goto clean_ale_ret; + } priv->irqs_table[1] = irq; ret = devm_request_irq(&pdev->dev, irq, cpsw_tx_interrupt, diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index bb1bb72121c04..17a26a429b71f 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -113,7 +113,7 @@ struct netcp_intf { #define NETCP_PSDATA_LEN KNAV_DMA_NUM_PS_WORDS struct netcp_packet { struct sk_buff *skb; - u32 *epib; + __le32 *epib; u32 *psdata; unsigned int psdata_len; struct netcp_intf *netcp; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index e5e20e734f21a..c61d66d386346 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -109,69 +109,80 @@ module_param(netcp_debug_level, int, 0); MODULE_PARM_DESC(netcp_debug_level, "Netcp debug level (NETIF_MSG bits) (0=none,...,16=all)"); /* Helper functions - Get/Set */ -static void get_pkt_info(u32 *buff, u32 *buff_len, u32 *ndesc, +static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc, struct knav_dma_desc *desc) { - *buff_len = desc->buff_len; - *buff = desc->buff; - *ndesc = desc->next_desc; + *buff_len = le32_to_cpu(desc->buff_len); + *buff = le32_to_cpu(desc->buff); + *ndesc = le32_to_cpu(desc->next_desc); } -static void get_pad_info(u32 *pad0, u32 *pad1, struct knav_dma_desc *desc) +static void get_pad_info(u32 *pad0, u32 *pad1, u32 *pad2, struct knav_dma_desc *desc) { - *pad0 = desc->pad[0]; - *pad1 = desc->pad[1]; + *pad0 = le32_to_cpu(desc->pad[0]); + *pad1 = le32_to_cpu(desc->pad[1]); + *pad2 = le32_to_cpu(desc->pad[2]); } -static void get_org_pkt_info(u32 *buff, u32 *buff_len, +static void get_pad_ptr(void **padptr, struct knav_dma_desc *desc) +{ + u64 pad64; + + pad64 = le32_to_cpu(desc->pad[0]) + + ((u64)le32_to_cpu(desc->pad[1]) << 32); + *padptr = (void *)(uintptr_t)pad64; +} + +static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len, struct knav_dma_desc *desc) { - *buff = desc->orig_buff; - *buff_len = desc->orig_len; + *buff = le32_to_cpu(desc->orig_buff); + *buff_len = le32_to_cpu(desc->orig_len); } -static void get_words(u32 *words, int num_words, u32 *desc) +static void get_words(dma_addr_t *words, int num_words, __le32 *desc) { int i; for (i = 0; i < num_words; i++) - words[i] = desc[i]; + words[i] = le32_to_cpu(desc[i]); } -static void set_pkt_info(u32 buff, u32 buff_len, u32 ndesc, +static void set_pkt_info(dma_addr_t buff, u32 buff_len, u32 ndesc, struct knav_dma_desc *desc) { - desc->buff_len = buff_len; - desc->buff = buff; - desc->next_desc = ndesc; + desc->buff_len = cpu_to_le32(buff_len); + desc->buff = cpu_to_le32(buff); + desc->next_desc = cpu_to_le32(ndesc); } static void set_desc_info(u32 desc_info, u32 pkt_info, struct knav_dma_desc *desc) { - desc->desc_info = desc_info; - desc->packet_info = pkt_info; + desc->desc_info = cpu_to_le32(desc_info); + desc->packet_info = cpu_to_le32(pkt_info); } -static void set_pad_info(u32 pad0, u32 pad1, struct knav_dma_desc *desc) +static void set_pad_info(u32 pad0, u32 pad1, u32 pad2, struct knav_dma_desc *desc) { - desc->pad[0] = pad0; - desc->pad[1] = pad1; + desc->pad[0] = cpu_to_le32(pad0); + desc->pad[1] = cpu_to_le32(pad1); + desc->pad[2] = cpu_to_le32(pad1); } -static void set_org_pkt_info(u32 buff, u32 buff_len, +static void set_org_pkt_info(dma_addr_t buff, u32 buff_len, struct knav_dma_desc *desc) { - desc->orig_buff = buff; - desc->orig_len = buff_len; + desc->orig_buff = cpu_to_le32(buff); + desc->orig_len = cpu_to_le32(buff_len); } -static void set_words(u32 *words, int num_words, u32 *desc) +static void set_words(u32 *words, int num_words, __le32 *desc) { int i; for (i = 0; i < num_words; i++) - desc[i] = words[i]; + desc[i] = cpu_to_le32(words[i]); } /* Read the e-fuse value as 32 bit values to be endian independent */ @@ -570,6 +581,7 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, dma_addr_t dma_desc, dma_buf; unsigned int buf_len, dma_sz = sizeof(*ndesc); void *buf_ptr; + u32 pad[2]; u32 tmp; get_words(&dma_desc, 1, &desc->next_desc); @@ -581,13 +593,15 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, break; } get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc); - get_pad_info((u32 *)&buf_ptr, &tmp, ndesc); + get_pad_ptr(&buf_ptr, ndesc); dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE); __free_page(buf_ptr); knav_pool_desc_put(netcp->rx_pool, desc); } - get_pad_info((u32 *)&buf_ptr, &buf_len, desc); + get_pad_info(&pad[0], &pad[1], &buf_len, desc); + buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32)); + if (buf_ptr) netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr); knav_pool_desc_put(netcp->rx_pool, desc); @@ -625,8 +639,8 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) dma_addr_t dma_desc, dma_buff; struct netcp_packet p_info; struct sk_buff *skb; + u32 pad[2]; void *org_buf_ptr; - u32 tmp; dma_desc = knav_queue_pop(netcp->rx_queue, &dma_sz); if (!dma_desc) @@ -639,7 +653,8 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc); - get_pad_info((u32 *)&org_buf_ptr, &org_buf_len, desc); + get_pad_info(&pad[0], &pad[1], &org_buf_len, desc); + org_buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32)); if (unlikely(!org_buf_ptr)) { dev_err(netcp->ndev_dev, "NULL bufptr in desc\n"); @@ -664,6 +679,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) /* Fill in the page fragment list */ while (dma_desc) { struct page *page; + void *ptr; ndesc = knav_pool_desc_unmap(netcp->rx_pool, dma_desc, dma_sz); if (unlikely(!ndesc)) { @@ -672,14 +688,15 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc); - get_pad_info((u32 *)&page, &tmp, ndesc); + get_pad_ptr(&ptr, ndesc); + page = ptr; if (likely(dma_buff && buf_len && page)) { dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE, DMA_FROM_DEVICE); } else { - dev_err(netcp->ndev_dev, "Bad Rx desc dma_buff(%p), len(%d), page(%p)\n", - (void *)dma_buff, buf_len, page); + dev_err(netcp->ndev_dev, "Bad Rx desc dma_buff(%pad), len(%d), page(%p)\n", + &dma_buff, buf_len, page); goto free_desc; } @@ -750,7 +767,6 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) unsigned int buf_len, dma_sz; dma_addr_t dma; void *buf_ptr; - u32 tmp; /* Allocate descriptor */ while ((dma = knav_queue_pop(netcp->rx_fdq[fdq], &dma_sz))) { @@ -761,7 +777,7 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) } get_org_pkt_info(&dma, &buf_len, desc); - get_pad_info((u32 *)&buf_ptr, &tmp, desc); + get_pad_ptr(&buf_ptr, desc); if (unlikely(!dma)) { dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n"); @@ -813,7 +829,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) struct page *page; dma_addr_t dma; void *bufptr; - u32 pad[2]; + u32 pad[3]; /* Allocate descriptor */ hwdesc = knav_pool_desc_get(netcp->rx_pool); @@ -830,7 +846,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); bufptr = netdev_alloc_frag(primary_buf_len); - pad[1] = primary_buf_len; + pad[2] = primary_buf_len; if (unlikely(!bufptr)) { dev_warn_ratelimited(netcp->ndev_dev, @@ -842,7 +858,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (unlikely(dma_mapping_error(netcp->dev, dma))) goto fail; - pad[0] = (u32)bufptr; + pad[0] = lower_32_bits((uintptr_t)bufptr); + pad[1] = upper_32_bits((uintptr_t)bufptr); } else { /* Allocate a secondary receive queue entry */ @@ -853,8 +870,9 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) } buf_len = PAGE_SIZE; dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE); - pad[0] = (u32)page; - pad[1] = 0; + pad[0] = lower_32_bits(dma); + pad[1] = upper_32_bits(dma); + pad[2] = 0; } desc_info = KNAV_DMA_DESC_PS_INFO_IN_DESC; @@ -864,7 +882,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) << KNAV_DMA_DESC_RETQ_SHIFT; set_org_pkt_info(dma, buf_len, hwdesc); - set_pad_info(pad[0], pad[1], hwdesc); + set_pad_info(pad[0], pad[1], pad[2], hwdesc); set_desc_info(desc_info, pkt_info, hwdesc); /* Push to FDQs */ @@ -935,8 +953,8 @@ static void netcp_free_tx_desc_chain(struct netcp_intf *netcp, dma_unmap_single(netcp->dev, dma_buf, buf_len, DMA_TO_DEVICE); else - dev_warn(netcp->ndev_dev, "bad Tx desc buf(%p), len(%d)\n", - (void *)dma_buf, buf_len); + dev_warn(netcp->ndev_dev, "bad Tx desc buf(%pad), len(%d)\n", + &dma_buf, buf_len); knav_pool_desc_put(netcp->tx_pool, ndesc); ndesc = NULL; @@ -953,11 +971,11 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, unsigned int budget) { struct knav_dma_desc *desc; + void *ptr; struct sk_buff *skb; unsigned int dma_sz; dma_addr_t dma; int pkts = 0; - u32 tmp; while (budget--) { dma = knav_queue_pop(netcp->tx_compl_q, &dma_sz); @@ -970,7 +988,8 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, continue; } - get_pad_info((u32 *)&skb, &tmp, desc); + get_pad_ptr(&ptr, desc); + skb = ptr; netcp_free_tx_desc_chain(netcp, desc, dma_sz); if (!skb) { dev_err(netcp->ndev_dev, "No skb in Tx desc\n"); @@ -1059,6 +1078,7 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp) u32 page_offset = frag->page_offset; u32 buf_len = skb_frag_size(frag); dma_addr_t desc_dma; + u32 desc_dma_32; u32 pkt_info; dma_addr = dma_map_page(dev, page, page_offset, buf_len, @@ -1075,13 +1095,13 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp) goto free_descs; } - desc_dma = knav_pool_desc_virt_to_dma(netcp->tx_pool, - (void *)ndesc); + desc_dma = knav_pool_desc_virt_to_dma(netcp->tx_pool, ndesc); pkt_info = (netcp->tx_compl_qid & KNAV_DMA_DESC_RETQ_MASK) << KNAV_DMA_DESC_RETQ_SHIFT; set_pkt_info(dma_addr, buf_len, 0, ndesc); - set_words(&desc_dma, 1, &pdesc->next_desc); + desc_dma_32 = (u32)desc_dma; + set_words(&desc_dma_32, 1, &pdesc->next_desc); pkt_len += buf_len; if (pdesc != desc) knav_pool_desc_map(netcp->tx_pool, pdesc, @@ -1129,8 +1149,8 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, p_info.ts_context = NULL; p_info.txtstamp_complete = NULL; p_info.epib = desc->epib; - p_info.psdata = desc->psdata; - memset(p_info.epib, 0, KNAV_DMA_NUM_EPIB_WORDS * sizeof(u32)); + p_info.psdata = (u32 __force *)desc->psdata; + memset(p_info.epib, 0, KNAV_DMA_NUM_EPIB_WORDS * sizeof(__le32)); /* Find out where to inject the packet for transmission */ list_for_each_entry(tx_hook, &netcp->txhook_list_head, list) { @@ -1154,11 +1174,12 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, /* update descriptor */ if (p_info.psdata_len) { - u32 *psdata = p_info.psdata; + /* psdata points to both native-endian and device-endian data */ + __le32 *psdata = (void __force *)p_info.psdata; memmove(p_info.psdata, p_info.psdata + p_info.psdata_len, p_info.psdata_len); - set_words(psdata, p_info.psdata_len, psdata); + set_words(p_info.psdata, p_info.psdata_len, psdata); tmp |= (p_info.psdata_len & KNAV_DMA_DESC_PSLEN_MASK) << KNAV_DMA_DESC_PSLEN_SHIFT; } @@ -1173,11 +1194,14 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, } set_words(&tmp, 1, &desc->packet_info); - set_words((u32 *)&skb, 1, &desc->pad[0]); + tmp = lower_32_bits((uintptr_t)&skb); + set_words(&tmp, 1, &desc->pad[0]); + tmp = upper_32_bits((uintptr_t)&skb); + set_words(&tmp, 1, &desc->pad[1]); if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) { tmp = tx_pipe->switch_to_port; - set_words((u32 *)&tmp, 1, &desc->tag_info); + set_words(&tmp, 1, &desc->tag_info); } /* submit packet descriptor */ diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c index 6f0a4495c7f33..298e059d04986 100644 --- a/drivers/net/ethernet/tile/tilepro.c +++ b/drivers/net/ethernet/tile/tilepro.c @@ -1349,8 +1349,7 @@ static int tile_net_open_inner(struct net_device *dev) */ static void tile_net_open_retry(struct work_struct *w) { - struct delayed_work *dw = - container_of(w, struct delayed_work, work); + struct delayed_work *dw = to_delayed_work(w); struct tile_net_priv *priv = container_of(dw, struct tile_net_priv, retry_work); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index de5c30c9f0592..24b077a32c1c9 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -71,8 +71,14 @@ struct geneve_dev { __be16 dst_port; bool collect_md; struct gro_cells gro_cells; + u32 flags; }; +/* Geneve device flags */ +#define GENEVE_F_UDP_CSUM BIT(0) +#define GENEVE_F_UDP_ZERO_CSUM6_TX BIT(1) +#define GENEVE_F_UDP_ZERO_CSUM6_RX BIT(2) + struct geneve_sock { bool collect_md; struct list_head list; @@ -81,6 +87,7 @@ struct geneve_sock { int refcnt; struct udp_offload udp_offloads; struct hlist_head vni_list[VNI_HASH_SIZE]; + u32 flags; }; static inline __u32 geneve_net_vni_hash(u8 vni[3]) @@ -343,7 +350,7 @@ error: } static struct socket *geneve_create_sock(struct net *net, bool ipv6, - __be16 port) + __be16 port, u32 flags) { struct socket *sock; struct udp_port_cfg udp_conf; @@ -354,6 +361,8 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6, if (ipv6) { udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; + udp_conf.use_udp6_rx_checksums = + !(flags & GENEVE_F_UDP_ZERO_CSUM6_RX); } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); @@ -371,8 +380,11 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6, static void geneve_notify_add_rx_port(struct geneve_sock *gs) { + struct net_device *dev; struct sock *sk = gs->sock->sk; + struct net *net = sock_net(sk); sa_family_t sa_family = sk->sk_family; + __be16 port = inet_sk(sk)->inet_sport; int err; if (sa_family == AF_INET) { @@ -381,6 +393,14 @@ static void geneve_notify_add_rx_port(struct geneve_sock *gs) pr_warn("geneve: udp_add_offload failed with status %d\n", err); } + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->netdev_ops->ndo_add_geneve_port) + dev->netdev_ops->ndo_add_geneve_port(dev, sa_family, + port); + } + rcu_read_unlock(); } static int geneve_hlen(struct genevehdr *gh) @@ -480,7 +500,7 @@ static int geneve_gro_complete(struct sk_buff *skb, int nhoff, /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, - bool ipv6) + bool ipv6, u32 flags) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; @@ -492,7 +512,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, if (!gs) return ERR_PTR(-ENOMEM); - sock = geneve_create_sock(net, ipv6, port); + sock = geneve_create_sock(net, ipv6, port, flags); if (IS_ERR(sock)) { kfree(gs); return ERR_CAST(sock); @@ -521,8 +541,20 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, static void geneve_notify_del_rx_port(struct geneve_sock *gs) { + struct net_device *dev; struct sock *sk = gs->sock->sk; + struct net *net = sock_net(sk); sa_family_t sa_family = sk->sk_family; + __be16 port = inet_sk(sk)->inet_sport; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->netdev_ops->ndo_del_geneve_port) + dev->netdev_ops->ndo_del_geneve_port(dev, sa_family, + port); + } + + rcu_read_unlock(); if (sa_family == AF_INET) udp_del_offload(&gs->udp_offloads); @@ -575,12 +607,13 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) goto out; } - gs = geneve_socket_create(net, geneve->dst_port, ipv6); + gs = geneve_socket_create(net, geneve->dst_port, ipv6, geneve->flags); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->collect_md; + gs->flags = geneve->flags; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) geneve->sock6 = gs; @@ -642,11 +675,12 @@ static void geneve_build_header(struct genevehdr *geneveh, static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb, __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, - bool csum, bool xnet) + u32 flags, bool xnet) { struct genevehdr *gnvh; int min_headroom; int err; + bool udp_sum = !!(flags & GENEVE_F_UDP_CSUM); skb_scrub_packet(skb, xnet); @@ -658,7 +692,7 @@ static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb, goto free_rt; } - skb = udp_tunnel_handle_offloads(skb, csum); + skb = udp_tunnel_handle_offloads(skb, udp_sum); if (IS_ERR(skb)) { err = PTR_ERR(skb); goto free_rt; @@ -678,11 +712,12 @@ free_rt: #if IS_ENABLED(CONFIG_IPV6) static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb, __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, - bool csum, bool xnet) + u32 flags, bool xnet) { struct genevehdr *gnvh; int min_headroom; int err; + bool udp_sum = !(flags & GENEVE_F_UDP_ZERO_CSUM6_TX); skb_scrub_packet(skb, xnet); @@ -694,7 +729,7 @@ static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb, goto free_dst; } - skb = udp_tunnel_handle_offloads(skb, csum); + skb = udp_tunnel_handle_offloads(skb, udp_sum); if (IS_ERR(skb)) { err = PTR_ERR(skb); goto free_dst; @@ -824,9 +859,9 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct flowi4 fl4; __u8 tos, ttl; __be16 sport; - bool udp_csum; __be16 df; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); + u32 flags = geneve->flags; if (geneve->collect_md) { if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { @@ -857,9 +892,13 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (key->tun_flags & TUNNEL_GENEVE_OPT) opts = ip_tunnel_info_opts(info); - udp_csum = !!(key->tun_flags & TUNNEL_CSUM); + if (key->tun_flags & TUNNEL_CSUM) + flags |= GENEVE_F_UDP_CSUM; + else + flags &= ~GENEVE_F_UDP_CSUM; + err = geneve_build_skb(rt, skb, key->tun_flags, vni, - info->options_len, opts, udp_csum, xnet); + info->options_len, opts, flags, xnet); if (unlikely(err)) goto err; @@ -867,9 +906,8 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; } else { - udp_csum = false; err = geneve_build_skb(rt, skb, 0, geneve->vni, - 0, NULL, udp_csum, xnet); + 0, NULL, flags, xnet); if (unlikely(err)) goto err; @@ -880,12 +918,11 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); df = 0; } - err = udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, fl4.saddr, fl4.daddr, - tos, ttl, df, sport, geneve->dst_port, - !net_eq(geneve->net, dev_net(geneve->dev)), - !udp_csum); + udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, fl4.saddr, fl4.daddr, + tos, ttl, df, sport, geneve->dst_port, + !net_eq(geneve->net, dev_net(geneve->dev)), + !(flags & GENEVE_F_UDP_CSUM)); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; tx_error: @@ -912,8 +949,8 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct flowi6 fl6; __u8 prio, ttl; __be16 sport; - bool udp_csum; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); + u32 flags = geneve->flags; if (geneve->collect_md) { if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { @@ -942,19 +979,22 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (key->tun_flags & TUNNEL_GENEVE_OPT) opts = ip_tunnel_info_opts(info); - udp_csum = !!(key->tun_flags & TUNNEL_CSUM); + if (key->tun_flags & TUNNEL_CSUM) + flags |= GENEVE_F_UDP_CSUM; + else + flags &= ~GENEVE_F_UDP_CSUM; + err = geneve6_build_skb(dst, skb, key->tun_flags, vni, info->options_len, opts, - udp_csum, xnet); + flags, xnet); if (unlikely(err)) goto err; prio = ip_tunnel_ecn_encap(key->tos, iip, skb); ttl = key->ttl; } else { - udp_csum = false; err = geneve6_build_skb(dst, skb, 0, geneve->vni, - 0, NULL, udp_csum, xnet); + 0, NULL, flags, xnet); if (unlikely(err)) goto err; @@ -964,11 +1004,10 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = 1; ttl = ttl ? : ip6_dst_hoplimit(dst); } - err = udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, - &fl6.saddr, &fl6.daddr, prio, ttl, - sport, geneve->dst_port, !udp_csum); - - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, + &fl6.saddr, &fl6.daddr, prio, ttl, + sport, geneve->dst_port, + !!(flags & GENEVE_F_UDP_ZERO_CSUM6_TX)); return NETDEV_TX_OK; tx_error: @@ -1067,6 +1106,30 @@ static struct device_type geneve_type = { .name = "geneve", }; +/* Calls the ndo_add_geneve_port of the caller in order to + * supply the listening GENEVE udp ports. Callers are expected + * to implement the ndo_add_geneve_port. + */ +void geneve_get_rx_port(struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct geneve_net *gn = net_generic(net, geneve_net_id); + struct geneve_sock *gs; + sa_family_t sa_family; + struct sock *sk; + __be16 port; + + rcu_read_lock(); + list_for_each_entry_rcu(gs, &gn->sock_list, list) { + sk = gs->sock->sk; + sa_family = sk->sk_family; + port = inet_sk(sk)->inet_sport; + dev->netdev_ops->ndo_add_geneve_port(dev, sa_family, port); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(geneve_get_rx_port); + /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { @@ -1099,6 +1162,9 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, + [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, + [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, + [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -1152,12 +1218,12 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, static int geneve_configure(struct net *net, struct net_device *dev, union geneve_addr *remote, __u32 vni, __u8 ttl, __u8 tos, __be16 dst_port, - bool metadata) + bool metadata, u32 flags) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); bool tun_collect_md, tun_on_same_port; - int err; + int err, encap_len; if (!remote) return -EINVAL; @@ -1183,12 +1249,21 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->tos = tos; geneve->dst_port = dst_port; geneve->collect_md = metadata; + geneve->flags = flags; t = geneve_find_dev(gn, dst_port, remote, geneve->vni, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; + /* make enough headroom for basic scenario */ + encap_len = GENEVE_BASE_HLEN + ETH_HLEN; + if (remote->sa.sa_family == AF_INET) + encap_len += sizeof(struct iphdr); + else + encap_len += sizeof(struct ipv6hdr); + dev->needed_headroom = encap_len + ETH_HLEN; + if (metadata) { if (tun_on_same_port) return -EPERM; @@ -1213,6 +1288,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev, bool metadata = false; union geneve_addr remote = geneve_remote_unspec; __u32 vni = 0; + u32 flags = 0; if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) return -EINVAL; @@ -1253,8 +1329,20 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (data[IFLA_GENEVE_COLLECT_METADATA]) metadata = true; + if (data[IFLA_GENEVE_UDP_CSUM] && + nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) + flags |= GENEVE_F_UDP_CSUM; + + if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX] && + nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) + flags |= GENEVE_F_UDP_ZERO_CSUM6_TX; + + if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX] && + nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) + flags |= GENEVE_F_UDP_ZERO_CSUM6_RX; + return geneve_configure(net, dev, &remote, vni, ttl, tos, dst_port, - metadata); + metadata, flags); } static void geneve_dellink(struct net_device *dev, struct list_head *head) @@ -1273,6 +1361,9 @@ static size_t geneve_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ 0; } @@ -1309,6 +1400,14 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } + if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, + !!(geneve->flags & GENEVE_F_UDP_CSUM)) || + nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + !!(geneve->flags & GENEVE_F_UDP_ZERO_CSUM6_TX)) || + nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + !!(geneve->flags & GENEVE_F_UDP_ZERO_CSUM6_RX))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -1342,7 +1441,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, return dev; err = geneve_configure(net, dev, &geneve_remote_unspec, - 0, 0, 0, htons(dst_port), true); + 0, 0, 0, htons(dst_port), true, 0); if (err) { free_netdev(dev); return ERR_PTR(err); diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 7c4a4151ef0f2..9f0b1c342b770 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -683,14 +683,14 @@ static void sixpack_close(struct tty_struct *tty) if (!atomic_dec_and_test(&sp->refcnt)) down(&sp->dead_sem); - unregister_netdev(sp->dev); - - del_timer(&sp->tx_t); - del_timer(&sp->resync_t); + del_timer_sync(&sp->tx_t); + del_timer_sync(&sp->resync_t); /* Free all 6pack frame buffers. */ kfree(sp->rbuff); kfree(sp->xbuff); + + unregister_netdev(sp->dev); } /* Perform I/O control on an active 6pack channel. */ diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 216bfd350169a..0b72b9de52072 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -798,13 +798,13 @@ static void mkiss_close(struct tty_struct *tty) if (!atomic_dec_and_test(&ax->refcnt)) down(&ax->dead_sem); - unregister_netdev(ax->dev); - /* Free all AX25 frame buffers. */ kfree(ax->rbuff); kfree(ax->xbuff); ax->tty = NULL; + + unregister_netdev(ax->dev); } /* Perform I/O control on an active ax25 channel. */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 02bab9a7c9ff6..059fc52316010 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -867,6 +867,14 @@ int netvsc_send(struct hv_device *device, packet->send_buf_index = NETVSC_INVALID_INDEX; packet->cp_partial = false; + /* Send control message directly without accessing msd (Multi-Send + * Data) field which may be changed during data packet processing. + */ + if (!skb) { + cur_send = packet; + goto send_now; + } + msdp = &net_device->msd[q_idx]; /* batch packets in send buffer if possible */ @@ -939,6 +947,7 @@ int netvsc_send(struct hv_device *device, } } +send_now: if (cur_send) ret = netvsc_send_pkt(cur_send, net_device, pb, skb); diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index ce5f1a21e6d73..3057a8df4ce93 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -71,3 +71,14 @@ config IEEE802154_ATUSB This driver can also be built as a module. To do so say M here. The module will be called 'atusb'. + +config IEEE802154_ADF7242 + tristate "ADF7242 transceiver driver" + depends on IEEE802154_DRIVERS && MAC802154 + depends on SPI + ---help--- + Say Y here to enable the ADF7242 SPI 802.15.4 wireless + controller. + + This driver can also be built as a module. To do so, say M here. + the module will be called 'adf7242'. diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile index cf1d2a6db0239..3a923d339497e 100644 --- a/drivers/net/ieee802154/Makefile +++ b/drivers/net/ieee802154/Makefile @@ -3,3 +3,4 @@ obj-$(CONFIG_IEEE802154_AT86RF230) += at86rf230.o obj-$(CONFIG_IEEE802154_MRF24J40) += mrf24j40.o obj-$(CONFIG_IEEE802154_CC2520) += cc2520.o obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o +obj-$(CONFIG_IEEE802154_ADF7242) += adf7242.o diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c new file mode 100644 index 0000000000000..89154c0797888 --- /dev/null +++ b/drivers/net/ieee802154/adf7242.c @@ -0,0 +1,1285 @@ +/* + * Analog Devices ADF7242 Low-Power IEEE 802.15.4 Transceiver + * + * Copyright 2009-2015 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + * + * http://www.analog.com/ADF7242 + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/mutex.h> +#include <linux/workqueue.h> +#include <linux/spinlock.h> +#include <linux/firmware.h> +#include <linux/spi/spi.h> +#include <linux/skbuff.h> +#include <linux/of.h> +#include <linux/irq.h> +#include <linux/delay.h> +#include <linux/debugfs.h> +#include <linux/bitops.h> +#include <linux/ieee802154.h> +#include <net/mac802154.h> +#include <net/cfg802154.h> + +#define FIRMWARE "adf7242_firmware.bin" +#define MAX_POLL_LOOPS 200 + +/* All Registers */ + +#define REG_EXT_CTRL 0x100 /* RW External LNA/PA and internal PA control */ +#define REG_TX_FSK_TEST 0x101 /* RW TX FSK test mode configuration */ +#define REG_CCA1 0x105 /* RW RSSI threshold for CCA */ +#define REG_CCA2 0x106 /* RW CCA mode configuration */ +#define REG_BUFFERCFG 0x107 /* RW RX_BUFFER overwrite control */ +#define REG_PKT_CFG 0x108 /* RW FCS evaluation configuration */ +#define REG_DELAYCFG0 0x109 /* RW RC_RX command to SFD or sync word delay */ +#define REG_DELAYCFG1 0x10A /* RW RC_TX command to TX state */ +#define REG_DELAYCFG2 0x10B /* RW Mac delay extension */ +#define REG_SYNC_WORD0 0x10C /* RW sync word bits [7:0] of [23:0] */ +#define REG_SYNC_WORD1 0x10D /* RW sync word bits [15:8] of [23:0] */ +#define REG_SYNC_WORD2 0x10E /* RW sync word bits [23:16] of [23:0] */ +#define REG_SYNC_CONFIG 0x10F /* RW sync word configuration */ +#define REG_RC_CFG 0x13E /* RW RX / TX packet configuration */ +#define REG_RC_VAR44 0x13F /* RW RESERVED */ +#define REG_CH_FREQ0 0x300 /* RW Channel Frequency Settings - Low */ +#define REG_CH_FREQ1 0x301 /* RW Channel Frequency Settings - Middle */ +#define REG_CH_FREQ2 0x302 /* RW Channel Frequency Settings - High */ +#define REG_TX_FD 0x304 /* RW TX Frequency Deviation Register */ +#define REG_DM_CFG0 0x305 /* RW RX Discriminator BW Register */ +#define REG_TX_M 0x306 /* RW TX Mode Register */ +#define REG_RX_M 0x307 /* RW RX Mode Register */ +#define REG_RRB 0x30C /* R RSSI Readback Register */ +#define REG_LRB 0x30D /* R Link Quality Readback Register */ +#define REG_DR0 0x30E /* RW bits [15:8] of [15:0] data rate setting */ +#define REG_DR1 0x30F /* RW bits [7:0] of [15:0] data rate setting */ +#define REG_PRAMPG 0x313 /* RW RESERVED */ +#define REG_TXPB 0x314 /* RW TX Packet Storage Base Address */ +#define REG_RXPB 0x315 /* RW RX Packet Storage Base Address */ +#define REG_TMR_CFG0 0x316 /* RW Wake up Timer Conf Register - High */ +#define REG_TMR_CFG1 0x317 /* RW Wake up Timer Conf Register - Low */ +#define REG_TMR_RLD0 0x318 /* RW Wake up Timer Value Register - High */ +#define REG_TMR_RLD1 0x319 /* RW Wake up Timer Value Register - Low */ +#define REG_TMR_CTRL 0x31A /* RW Wake up Timer Timeout flag */ +#define REG_PD_AUX 0x31E /* RW Battmon enable */ +#define REG_GP_CFG 0x32C /* RW GPIO Configuration */ +#define REG_GP_OUT 0x32D /* RW GPIO Configuration */ +#define REG_GP_IN 0x32E /* R GPIO Configuration */ +#define REG_SYNT 0x335 /* RW bandwidth calibration timers */ +#define REG_CAL_CFG 0x33D /* RW Calibration Settings */ +#define REG_PA_BIAS 0x36E /* RW PA BIAS */ +#define REG_SYNT_CAL 0x371 /* RW Oscillator and Doubler Configuration */ +#define REG_IIRF_CFG 0x389 /* RW BB Filter Decimation Rate */ +#define REG_CDR_CFG 0x38A /* RW CDR kVCO */ +#define REG_DM_CFG1 0x38B /* RW Postdemodulator Filter */ +#define REG_AGCSTAT 0x38E /* R RXBB Ref Osc Calibration Engine Readback */ +#define REG_RXCAL0 0x395 /* RW RX BB filter tuning, LSB */ +#define REG_RXCAL1 0x396 /* RW RX BB filter tuning, MSB */ +#define REG_RXFE_CFG 0x39B /* RW RXBB Ref Osc & RXFE Calibration */ +#define REG_PA_RR 0x3A7 /* RW Set PA ramp rate */ +#define REG_PA_CFG 0x3A8 /* RW PA enable */ +#define REG_EXTPA_CFG 0x3A9 /* RW External PA BIAS DAC */ +#define REG_EXTPA_MSC 0x3AA /* RW PA Bias Mode */ +#define REG_ADC_RBK 0x3AE /* R Readback temp */ +#define REG_AGC_CFG1 0x3B2 /* RW GC Parameters */ +#define REG_AGC_MAX 0x3B4 /* RW Slew rate */ +#define REG_AGC_CFG2 0x3B6 /* RW RSSI Parameters */ +#define REG_AGC_CFG3 0x3B7 /* RW RSSI Parameters */ +#define REG_AGC_CFG4 0x3B8 /* RW RSSI Parameters */ +#define REG_AGC_CFG5 0x3B9 /* RW RSSI & NDEC Parameters */ +#define REG_AGC_CFG6 0x3BA /* RW NDEC Parameters */ +#define REG_OCL_CFG1 0x3C4 /* RW OCL System Parameters */ +#define REG_IRQ1_EN0 0x3C7 /* RW Interrupt Mask set bits for IRQ1 */ +#define REG_IRQ1_EN1 0x3C8 /* RW Interrupt Mask set bits for IRQ1 */ +#define REG_IRQ2_EN0 0x3C9 /* RW Interrupt Mask set bits for IRQ2 */ +#define REG_IRQ2_EN1 0x3CA /* RW Interrupt Mask set bits for IRQ2 */ +#define REG_IRQ1_SRC0 0x3CB /* RW Interrupt Source bits for IRQ */ +#define REG_IRQ1_SRC1 0x3CC /* RW Interrupt Source bits for IRQ */ +#define REG_OCL_BW0 0x3D2 /* RW OCL System Parameters */ +#define REG_OCL_BW1 0x3D3 /* RW OCL System Parameters */ +#define REG_OCL_BW2 0x3D4 /* RW OCL System Parameters */ +#define REG_OCL_BW3 0x3D5 /* RW OCL System Parameters */ +#define REG_OCL_BW4 0x3D6 /* RW OCL System Parameters */ +#define REG_OCL_BWS 0x3D7 /* RW OCL System Parameters */ +#define REG_OCL_CFG13 0x3E0 /* RW OCL System Parameters */ +#define REG_GP_DRV 0x3E3 /* RW I/O pads Configuration and bg trim */ +#define REG_BM_CFG 0x3E6 /* RW Batt. Monitor Threshold Voltage setting */ +#define REG_SFD_15_4 0x3F4 /* RW Option to set non standard SFD */ +#define REG_AFC_CFG 0x3F7 /* RW AFC mode and polarity */ +#define REG_AFC_KI_KP 0x3F8 /* RW AFC ki and kp */ +#define REG_AFC_RANGE 0x3F9 /* RW AFC range */ +#define REG_AFC_READ 0x3FA /* RW Readback frequency error */ + +/* REG_EXTPA_MSC */ +#define PA_PWR(x) (((x) & 0xF) << 4) +#define EXTPA_BIAS_SRC BIT(3) +#define EXTPA_BIAS_MODE(x) (((x) & 0x7) << 0) + +/* REG_PA_CFG */ +#define PA_BRIDGE_DBIAS(x) (((x) & 0x1F) << 0) +#define PA_DBIAS_HIGH_POWER 21 +#define PA_DBIAS_LOW_POWER 13 + +/* REG_PA_BIAS */ +#define PA_BIAS_CTRL(x) (((x) & 0x1F) << 1) +#define REG_PA_BIAS_DFL BIT(0) +#define PA_BIAS_HIGH_POWER 63 +#define PA_BIAS_LOW_POWER 55 + +#define REG_PAN_ID0 0x112 +#define REG_PAN_ID1 0x113 +#define REG_SHORT_ADDR_0 0x114 +#define REG_SHORT_ADDR_1 0x115 +#define REG_IEEE_ADDR_0 0x116 +#define REG_IEEE_ADDR_1 0x117 +#define REG_IEEE_ADDR_2 0x118 +#define REG_IEEE_ADDR_3 0x119 +#define REG_IEEE_ADDR_4 0x11A +#define REG_IEEE_ADDR_5 0x11B +#define REG_IEEE_ADDR_6 0x11C +#define REG_IEEE_ADDR_7 0x11D +#define REG_FFILT_CFG 0x11E +#define REG_AUTO_CFG 0x11F +#define REG_AUTO_TX1 0x120 +#define REG_AUTO_TX2 0x121 +#define REG_AUTO_STATUS 0x122 + +/* REG_FFILT_CFG */ +#define ACCEPT_BEACON_FRAMES BIT(0) +#define ACCEPT_DATA_FRAMES BIT(1) +#define ACCEPT_ACK_FRAMES BIT(2) +#define ACCEPT_MACCMD_FRAMES BIT(3) +#define ACCEPT_RESERVED_FRAMES BIT(4) +#define ACCEPT_ALL_ADDRESS BIT(5) + +/* REG_AUTO_CFG */ +#define AUTO_ACK_FRAMEPEND BIT(0) +#define IS_PANCOORD BIT(1) +#define RX_AUTO_ACK_EN BIT(3) +#define CSMA_CA_RX_TURNAROUND BIT(4) + +/* REG_AUTO_TX1 */ +#define MAX_FRAME_RETRIES(x) ((x) & 0xF) +#define MAX_CCA_RETRIES(x) (((x) & 0x7) << 4) + +/* REG_AUTO_TX2 */ +#define CSMA_MAX_BE(x) ((x) & 0xF) +#define CSMA_MIN_BE(x) (((x) & 0xF) << 4) + +#define CMD_SPI_NOP 0xFF /* No operation. Use for dummy writes */ +#define CMD_SPI_PKT_WR 0x10 /* Write telegram to the Packet RAM + * starting from the TX packet base address + * pointer tx_packet_base + */ +#define CMD_SPI_PKT_RD 0x30 /* Read telegram from the Packet RAM + * starting from RX packet base address + * pointer rxpb.rx_packet_base + */ +#define CMD_SPI_MEM_WR(x) (0x18 + (x >> 8)) /* Write data to MCR or + * Packet RAM sequentially + */ +#define CMD_SPI_MEM_RD(x) (0x38 + (x >> 8)) /* Read data from MCR or + * Packet RAM sequentially + */ +#define CMD_SPI_MEMR_WR(x) (0x08 + (x >> 8)) /* Write data to MCR or Packet + * RAM as random block + */ +#define CMD_SPI_MEMR_RD(x) (0x28 + (x >> 8)) /* Read data from MCR or + * Packet RAM random block + */ +#define CMD_SPI_PRAM_WR 0x1E /* Write data sequentially to current + * PRAM page selected + */ +#define CMD_SPI_PRAM_RD 0x3E /* Read data sequentially from current + * PRAM page selected + */ +#define CMD_RC_SLEEP 0xB1 /* Invoke transition of radio controller + * into SLEEP state + */ +#define CMD_RC_IDLE 0xB2 /* Invoke transition of radio controller + * into IDLE state + */ +#define CMD_RC_PHY_RDY 0xB3 /* Invoke transition of radio controller + * into PHY_RDY state + */ +#define CMD_RC_RX 0xB4 /* Invoke transition of radio controller + * into RX state + */ +#define CMD_RC_TX 0xB5 /* Invoke transition of radio controller + * into TX state + */ +#define CMD_RC_MEAS 0xB6 /* Invoke transition of radio controller + * into MEAS state + */ +#define CMD_RC_CCA 0xB7 /* Invoke Clear channel assessment */ +#define CMD_RC_CSMACA 0xC1 /* initiates CSMA-CA channel access + * sequence and frame transmission + */ +#define CMD_RC_PC_RESET 0xC7 /* Program counter reset */ +#define CMD_RC_RESET 0xC8 /* Resets the ADF7242 and puts it in + * the sleep state + */ +#define CMD_RC_PC_RESET_NO_WAIT (CMD_RC_PC_RESET | BIT(31)) + +/* STATUS */ + +#define STAT_SPI_READY BIT(7) +#define STAT_IRQ_STATUS BIT(6) +#define STAT_RC_READY BIT(5) +#define STAT_CCA_RESULT BIT(4) +#define RC_STATUS_IDLE 1 +#define RC_STATUS_MEAS 2 +#define RC_STATUS_PHY_RDY 3 +#define RC_STATUS_RX 4 +#define RC_STATUS_TX 5 +#define RC_STATUS_MASK 0xF + +/* AUTO_STATUS */ + +#define SUCCESS 0 +#define SUCCESS_DATPEND 1 +#define FAILURE_CSMACA 2 +#define FAILURE_NOACK 3 +#define AUTO_STATUS_MASK 0x3 + +#define PRAM_PAGESIZE 256 + +/* IRQ1 */ + +#define IRQ_CCA_COMPLETE BIT(0) +#define IRQ_SFD_RX BIT(1) +#define IRQ_SFD_TX BIT(2) +#define IRQ_RX_PKT_RCVD BIT(3) +#define IRQ_TX_PKT_SENT BIT(4) +#define IRQ_FRAME_VALID BIT(5) +#define IRQ_ADDRESS_VALID BIT(6) +#define IRQ_CSMA_CA BIT(7) + +#define AUTO_TX_TURNAROUND BIT(3) +#define ADDON_EN BIT(4) + +#define FLAG_XMIT 0 +#define FLAG_START 1 + +#define ADF7242_REPORT_CSMA_CA_STAT 0 /* framework doesn't handle yet */ + +struct adf7242_local { + struct spi_device *spi; + struct completion tx_complete; + struct ieee802154_hw *hw; + struct mutex bmux; /* protect SPI messages */ + struct spi_message stat_msg; + struct spi_transfer stat_xfer; + struct dentry *debugfs_root; + unsigned long flags; + int tx_stat; + bool promiscuous; + s8 rssi; + u8 max_frame_retries; + u8 max_cca_retries; + u8 max_be; + u8 min_be; + + /* DMA (thus cache coherency maintenance) requires the + * transfer buffers to live in their own cache lines. + */ + + u8 buf[3] ____cacheline_aligned; + u8 buf_reg_tx[3]; + u8 buf_read_tx[4]; + u8 buf_read_rx[4]; + u8 buf_stat_rx; + u8 buf_stat_tx; + u8 buf_cmd; +}; + +static int adf7242_soft_reset(struct adf7242_local *lp, int line); + +static int adf7242_status(struct adf7242_local *lp, u8 *stat) +{ + int status; + + mutex_lock(&lp->bmux); + status = spi_sync(lp->spi, &lp->stat_msg); + *stat = lp->buf_stat_rx; + mutex_unlock(&lp->bmux); + + return status; +} + +static int adf7242_wait_status(struct adf7242_local *lp, unsigned status, + unsigned mask, int line) +{ + int cnt = 0, ret = 0; + u8 stat; + + do { + adf7242_status(lp, &stat); + cnt++; + } while (((stat & mask) != status) && (cnt < MAX_POLL_LOOPS)); + + if (cnt >= MAX_POLL_LOOPS) { + ret = -ETIMEDOUT; + + if (!(stat & STAT_RC_READY)) { + adf7242_soft_reset(lp, line); + adf7242_status(lp, &stat); + + if ((stat & mask) == status) + ret = 0; + } + + if (ret < 0) + dev_warn(&lp->spi->dev, + "%s:line %d Timeout status 0x%x (%d)\n", + __func__, line, stat, cnt); + } + + dev_vdbg(&lp->spi->dev, "%s : loops=%d line %d\n", __func__, cnt, line); + + return ret; +} + +static int adf7242_wait_ready(struct adf7242_local *lp, int line) +{ + return adf7242_wait_status(lp, STAT_RC_READY | STAT_SPI_READY, + STAT_RC_READY | STAT_SPI_READY, line); +} + +static int adf7242_write_fbuf(struct adf7242_local *lp, u8 *data, u8 len) +{ + u8 *buf = lp->buf; + int status; + struct spi_message msg; + struct spi_transfer xfer_head = { + .len = 2, + .tx_buf = buf, + + }; + struct spi_transfer xfer_buf = { + .len = len, + .tx_buf = data, + }; + + spi_message_init(&msg); + spi_message_add_tail(&xfer_head, &msg); + spi_message_add_tail(&xfer_buf, &msg); + + adf7242_wait_ready(lp, __LINE__); + + mutex_lock(&lp->bmux); + buf[0] = CMD_SPI_PKT_WR; + buf[1] = len + 2; + + status = spi_sync(lp->spi, &msg); + mutex_unlock(&lp->bmux); + + return status; +} + +static int adf7242_read_fbuf(struct adf7242_local *lp, + u8 *data, size_t len, bool packet_read) +{ + u8 *buf = lp->buf; + int status; + struct spi_message msg; + struct spi_transfer xfer_head = { + .len = 3, + .tx_buf = buf, + .rx_buf = buf, + }; + struct spi_transfer xfer_buf = { + .len = len, + .rx_buf = data, + }; + + spi_message_init(&msg); + spi_message_add_tail(&xfer_head, &msg); + spi_message_add_tail(&xfer_buf, &msg); + + adf7242_wait_ready(lp, __LINE__); + + mutex_lock(&lp->bmux); + if (packet_read) { + buf[0] = CMD_SPI_PKT_RD; + buf[1] = CMD_SPI_NOP; + buf[2] = 0; /* PHR */ + } else { + buf[0] = CMD_SPI_PRAM_RD; + buf[1] = 0; + buf[2] = CMD_SPI_NOP; + } + + status = spi_sync(lp->spi, &msg); + + mutex_unlock(&lp->bmux); + + return status; +} + +static int adf7242_read_reg(struct adf7242_local *lp, u16 addr, u8 *data) +{ + int status; + struct spi_message msg; + + struct spi_transfer xfer = { + .len = 4, + .tx_buf = lp->buf_read_tx, + .rx_buf = lp->buf_read_rx, + }; + + adf7242_wait_ready(lp, __LINE__); + + mutex_lock(&lp->bmux); + lp->buf_read_tx[0] = CMD_SPI_MEM_RD(addr); + lp->buf_read_tx[1] = addr; + lp->buf_read_tx[2] = CMD_SPI_NOP; + lp->buf_read_tx[3] = CMD_SPI_NOP; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + status = spi_sync(lp->spi, &msg); + if (msg.status) + status = msg.status; + + if (!status) + *data = lp->buf_read_rx[3]; + + mutex_unlock(&lp->bmux); + + dev_vdbg(&lp->spi->dev, "%s : REG 0x%X, VAL 0x%X\n", __func__, + addr, *data); + + return status; +} + +static int adf7242_write_reg(struct adf7242_local *lp, u16 addr, u8 data) +{ + int status; + + adf7242_wait_ready(lp, __LINE__); + + mutex_lock(&lp->bmux); + lp->buf_reg_tx[0] = CMD_SPI_MEM_WR(addr); + lp->buf_reg_tx[1] = addr; + lp->buf_reg_tx[2] = data; + status = spi_write(lp->spi, lp->buf_reg_tx, 3); + mutex_unlock(&lp->bmux); + + dev_vdbg(&lp->spi->dev, "%s : REG 0x%X, VAL 0x%X\n", + __func__, addr, data); + + return status; +} + +static int adf7242_cmd(struct adf7242_local *lp, unsigned cmd) +{ + int status; + + dev_vdbg(&lp->spi->dev, "%s : CMD=0x%X\n", __func__, cmd); + + if (cmd != CMD_RC_PC_RESET_NO_WAIT) + adf7242_wait_ready(lp, __LINE__); + + mutex_lock(&lp->bmux); + lp->buf_cmd = cmd; + status = spi_write(lp->spi, &lp->buf_cmd, 1); + mutex_unlock(&lp->bmux); + + return status; +} + +static int adf7242_upload_firmware(struct adf7242_local *lp, u8 *data, u16 len) +{ + struct spi_message msg; + struct spi_transfer xfer_buf = { }; + int status, i, page = 0; + u8 *buf = lp->buf; + + struct spi_transfer xfer_head = { + .len = 2, + .tx_buf = buf, + }; + + buf[0] = CMD_SPI_PRAM_WR; + buf[1] = 0; + + spi_message_init(&msg); + spi_message_add_tail(&xfer_head, &msg); + spi_message_add_tail(&xfer_buf, &msg); + + for (i = len; i >= 0; i -= PRAM_PAGESIZE) { + adf7242_write_reg(lp, REG_PRAMPG, page); + + xfer_buf.len = (i >= PRAM_PAGESIZE) ? PRAM_PAGESIZE : i; + xfer_buf.tx_buf = &data[page * PRAM_PAGESIZE]; + + mutex_lock(&lp->bmux); + status = spi_sync(lp->spi, &msg); + mutex_unlock(&lp->bmux); + page++; + } + + return status; +} + +static int adf7242_verify_firmware(struct adf7242_local *lp, + const u8 *data, size_t len) +{ +#ifdef DEBUG + int i, j; + unsigned int page; + u8 *buf = kmalloc(PRAM_PAGESIZE, GFP_KERNEL); + + if (!buf) + return -ENOMEM; + + for (page = 0, i = len; i >= 0; i -= PRAM_PAGESIZE, page++) { + size_t nb = (i >= PRAM_PAGESIZE) ? PRAM_PAGESIZE : i; + + adf7242_write_reg(lp, REG_PRAMPG, page); + adf7242_read_fbuf(lp, buf, nb, false); + + for (j = 0; j < nb; j++) { + if (buf[j] != data[page * PRAM_PAGESIZE + j]) { + kfree(buf); + return -EIO; + } + } + } + kfree(buf); +#endif + return 0; +} + +static int adf7242_set_txpower(struct ieee802154_hw *hw, int mbm) +{ + struct adf7242_local *lp = hw->priv; + u8 pwr, bias_ctrl, dbias, tmp; + int db = mbm / 100; + + dev_vdbg(&lp->spi->dev, "%s : Power %d dB\n", __func__, db); + + if (db > 5 || db < -26) + return -EINVAL; + + db = DIV_ROUND_CLOSEST(db + 29, 2); + + if (db > 15) { + dbias = PA_DBIAS_HIGH_POWER; + bias_ctrl = PA_BIAS_HIGH_POWER; + } else { + dbias = PA_DBIAS_LOW_POWER; + bias_ctrl = PA_BIAS_LOW_POWER; + } + + pwr = clamp_t(u8, db, 3, 15); + + adf7242_read_reg(lp, REG_PA_CFG, &tmp); + tmp &= ~PA_BRIDGE_DBIAS(~0); + tmp |= PA_BRIDGE_DBIAS(dbias); + adf7242_write_reg(lp, REG_PA_CFG, tmp); + + adf7242_read_reg(lp, REG_PA_BIAS, &tmp); + tmp &= ~PA_BIAS_CTRL(~0); + tmp |= PA_BIAS_CTRL(bias_ctrl); + adf7242_write_reg(lp, REG_PA_BIAS, tmp); + + adf7242_read_reg(lp, REG_EXTPA_MSC, &tmp); + tmp &= ~PA_PWR(~0); + tmp |= PA_PWR(pwr); + + return adf7242_write_reg(lp, REG_EXTPA_MSC, tmp); +} + +static int adf7242_set_csma_params(struct ieee802154_hw *hw, u8 min_be, + u8 max_be, u8 retries) +{ + struct adf7242_local *lp = hw->priv; + int ret; + + dev_vdbg(&lp->spi->dev, "%s : min_be=%d max_be=%d retries=%d\n", + __func__, min_be, max_be, retries); + + if (min_be > max_be || max_be > 8 || retries > 5) + return -EINVAL; + + ret = adf7242_write_reg(lp, REG_AUTO_TX1, + MAX_FRAME_RETRIES(lp->max_frame_retries) | + MAX_CCA_RETRIES(retries)); + if (ret) + return ret; + + lp->max_cca_retries = retries; + lp->max_be = max_be; + lp->min_be = min_be; + + return adf7242_write_reg(lp, REG_AUTO_TX2, CSMA_MAX_BE(max_be) | + CSMA_MIN_BE(min_be)); +} + +static int adf7242_set_frame_retries(struct ieee802154_hw *hw, s8 retries) +{ + struct adf7242_local *lp = hw->priv; + int ret = 0; + + dev_vdbg(&lp->spi->dev, "%s : Retries = %d\n", __func__, retries); + + if (retries < -1 || retries > 15) + return -EINVAL; + + if (retries >= 0) + ret = adf7242_write_reg(lp, REG_AUTO_TX1, + MAX_FRAME_RETRIES(retries) | + MAX_CCA_RETRIES(lp->max_cca_retries)); + + lp->max_frame_retries = retries; + + return ret; +} + +static int adf7242_ed(struct ieee802154_hw *hw, u8 *level) +{ + struct adf7242_local *lp = hw->priv; + + *level = lp->rssi; + + dev_vdbg(&lp->spi->dev, "%s :Exit level=%d\n", + __func__, *level); + + return 0; +} + +static int adf7242_start(struct ieee802154_hw *hw) +{ + struct adf7242_local *lp = hw->priv; + + adf7242_cmd(lp, CMD_RC_PHY_RDY); + adf7242_write_reg(lp, REG_IRQ1_SRC1, 0xFF); + enable_irq(lp->spi->irq); + set_bit(FLAG_START, &lp->flags); + + return adf7242_cmd(lp, CMD_RC_RX); +} + +static void adf7242_stop(struct ieee802154_hw *hw) +{ + struct adf7242_local *lp = hw->priv; + + adf7242_cmd(lp, CMD_RC_IDLE); + clear_bit(FLAG_START, &lp->flags); + disable_irq(lp->spi->irq); + adf7242_write_reg(lp, REG_IRQ1_SRC1, 0xFF); +} + +static int adf7242_channel(struct ieee802154_hw *hw, u8 page, u8 channel) +{ + struct adf7242_local *lp = hw->priv; + unsigned long freq; + + dev_dbg(&lp->spi->dev, "%s :Channel=%d\n", __func__, channel); + + might_sleep(); + + WARN_ON(page != 0); + WARN_ON(channel < 11); + WARN_ON(channel > 26); + + freq = (2405 + 5 * (channel - 11)) * 100; + adf7242_cmd(lp, CMD_RC_PHY_RDY); + + adf7242_write_reg(lp, REG_CH_FREQ0, freq); + adf7242_write_reg(lp, REG_CH_FREQ1, freq >> 8); + adf7242_write_reg(lp, REG_CH_FREQ2, freq >> 16); + + return adf7242_cmd(lp, CMD_RC_RX); +} + +static int adf7242_set_hw_addr_filt(struct ieee802154_hw *hw, + struct ieee802154_hw_addr_filt *filt, + unsigned long changed) +{ + struct adf7242_local *lp = hw->priv; + u8 reg; + + dev_dbg(&lp->spi->dev, "%s :Changed=0x%lX\n", __func__, changed); + + might_sleep(); + + if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) { + u8 addr[8], i; + + memcpy(addr, &filt->ieee_addr, 8); + + for (i = 0; i < 8; i++) + adf7242_write_reg(lp, REG_IEEE_ADDR_0 + i, addr[i]); + } + + if (changed & IEEE802154_AFILT_SADDR_CHANGED) { + u16 saddr = le16_to_cpu(filt->short_addr); + + adf7242_write_reg(lp, REG_SHORT_ADDR_0, saddr); + adf7242_write_reg(lp, REG_SHORT_ADDR_1, saddr >> 8); + } + + if (changed & IEEE802154_AFILT_PANID_CHANGED) { + u16 pan_id = le16_to_cpu(filt->pan_id); + + adf7242_write_reg(lp, REG_PAN_ID0, pan_id); + adf7242_write_reg(lp, REG_PAN_ID1, pan_id >> 8); + } + + if (changed & IEEE802154_AFILT_PANC_CHANGED) { + adf7242_read_reg(lp, REG_AUTO_CFG, ®); + if (filt->pan_coord) + reg |= IS_PANCOORD; + else + reg &= ~IS_PANCOORD; + adf7242_write_reg(lp, REG_AUTO_CFG, reg); + } + + return 0; +} + +static int adf7242_set_promiscuous_mode(struct ieee802154_hw *hw, bool on) +{ + struct adf7242_local *lp = hw->priv; + + dev_dbg(&lp->spi->dev, "%s : mode %d\n", __func__, on); + + lp->promiscuous = on; + + if (on) { + adf7242_write_reg(lp, REG_AUTO_CFG, 0); + return adf7242_write_reg(lp, REG_FFILT_CFG, + ACCEPT_BEACON_FRAMES | + ACCEPT_DATA_FRAMES | + ACCEPT_MACCMD_FRAMES | + ACCEPT_ALL_ADDRESS | + ACCEPT_ACK_FRAMES | + ACCEPT_RESERVED_FRAMES); + } else { + adf7242_write_reg(lp, REG_FFILT_CFG, + ACCEPT_BEACON_FRAMES | + ACCEPT_DATA_FRAMES | + ACCEPT_MACCMD_FRAMES | + ACCEPT_RESERVED_FRAMES); + + return adf7242_write_reg(lp, REG_AUTO_CFG, RX_AUTO_ACK_EN); + } +} + +static int adf7242_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm) +{ + struct adf7242_local *lp = hw->priv; + s8 level = clamp_t(s8, mbm / 100, S8_MIN, S8_MAX); + + dev_dbg(&lp->spi->dev, "%s : level %d\n", __func__, level); + + return adf7242_write_reg(lp, REG_CCA1, level); +} + +static int adf7242_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) +{ + struct adf7242_local *lp = hw->priv; + int ret; + + set_bit(FLAG_XMIT, &lp->flags); + reinit_completion(&lp->tx_complete); + adf7242_cmd(lp, CMD_RC_PHY_RDY); + + ret = adf7242_write_fbuf(lp, skb->data, skb->len); + if (ret) + goto err; + + ret = adf7242_cmd(lp, CMD_RC_CSMACA); + if (ret) + goto err; + + ret = wait_for_completion_interruptible_timeout(&lp->tx_complete, + HZ / 10); + if (ret < 0) + goto err; + if (ret == 0) { + dev_dbg(&lp->spi->dev, "Timeout waiting for TX interrupt\n"); + ret = -ETIMEDOUT; + goto err; + } + + if (lp->tx_stat != SUCCESS) { + dev_dbg(&lp->spi->dev, + "Error xmit: Retry count exceeded Status=0x%x\n", + lp->tx_stat); + ret = -ECOMM; + } else { + ret = 0; + } + +err: + clear_bit(FLAG_XMIT, &lp->flags); + adf7242_cmd(lp, CMD_RC_RX); + + return ret; +} + +static int adf7242_rx(struct adf7242_local *lp) +{ + struct sk_buff *skb; + size_t len; + int ret; + u8 lqi, len_u8, *data; + + adf7242_read_reg(lp, 0, &len_u8); + + len = len_u8; + + if (!ieee802154_is_valid_psdu_len(len)) { + dev_dbg(&lp->spi->dev, + "corrupted frame received len %d\n", (int)len); + len = IEEE802154_MTU; + } + + skb = dev_alloc_skb(len); + if (!skb) { + adf7242_cmd(lp, CMD_RC_RX); + return -ENOMEM; + } + + data = skb_put(skb, len); + ret = adf7242_read_fbuf(lp, data, len, true); + if (ret < 0) { + kfree_skb(skb); + adf7242_cmd(lp, CMD_RC_RX); + return ret; + } + + lqi = data[len - 2]; + lp->rssi = data[len - 1]; + + adf7242_cmd(lp, CMD_RC_RX); + + skb_trim(skb, len - 2); /* Don't put RSSI/LQI or CRC into the frame */ + + ieee802154_rx_irqsafe(lp->hw, skb, lqi); + + dev_dbg(&lp->spi->dev, "%s: ret=%d len=%d lqi=%d rssi=%d\n", + __func__, ret, (int)len, (int)lqi, lp->rssi); + + return 0; +} + +static struct ieee802154_ops adf7242_ops = { + .owner = THIS_MODULE, + .xmit_sync = adf7242_xmit, + .ed = adf7242_ed, + .set_channel = adf7242_channel, + .set_hw_addr_filt = adf7242_set_hw_addr_filt, + .start = adf7242_start, + .stop = adf7242_stop, + .set_csma_params = adf7242_set_csma_params, + .set_frame_retries = adf7242_set_frame_retries, + .set_txpower = adf7242_set_txpower, + .set_promiscuous_mode = adf7242_set_promiscuous_mode, + .set_cca_ed_level = adf7242_set_cca_ed_level, +}; + +static void adf7242_debug(u8 irq1) +{ +#ifdef DEBUG + u8 stat; + + adf7242_status(lp, &stat); + + dev_dbg(&lp->spi->dev, "%s IRQ1 = %X:\n%s%s%s%s%s%s%s%s\n", + __func__, irq1, + irq1 & IRQ_CCA_COMPLETE ? "IRQ_CCA_COMPLETE\n" : "", + irq1 & IRQ_SFD_RX ? "IRQ_SFD_RX\n" : "", + irq1 & IRQ_SFD_TX ? "IRQ_SFD_TX\n" : "", + irq1 & IRQ_RX_PKT_RCVD ? "IRQ_RX_PKT_RCVD\n" : "", + irq1 & IRQ_TX_PKT_SENT ? "IRQ_TX_PKT_SENT\n" : "", + irq1 & IRQ_CSMA_CA ? "IRQ_CSMA_CA\n" : "", + irq1 & IRQ_FRAME_VALID ? "IRQ_FRAME_VALID\n" : "", + irq1 & IRQ_ADDRESS_VALID ? "IRQ_ADDRESS_VALID\n" : ""); + + dev_dbg(&lp->spi->dev, "%s STATUS = %X:\n%s\n%s%s%s%s%s\n", + __func__, stat, + stat & STAT_RC_READY ? "RC_READY" : "RC_BUSY", + (stat & 0xf) == RC_STATUS_IDLE ? "RC_STATUS_IDLE" : "", + (stat & 0xf) == RC_STATUS_MEAS ? "RC_STATUS_MEAS" : "", + (stat & 0xf) == RC_STATUS_PHY_RDY ? "RC_STATUS_PHY_RDY" : "", + (stat & 0xf) == RC_STATUS_RX ? "RC_STATUS_RX" : "", + (stat & 0xf) == RC_STATUS_TX ? "RC_STATUS_TX" : ""); + } +#endif +} + +static irqreturn_t adf7242_isr(int irq, void *data) +{ + struct adf7242_local *lp = data; + unsigned xmit; + u8 irq1; + + adf7242_wait_status(lp, RC_STATUS_PHY_RDY, RC_STATUS_MASK, __LINE__); + + adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1); + adf7242_write_reg(lp, REG_IRQ1_SRC1, irq1); + + if (!(irq1 & (IRQ_RX_PKT_RCVD | IRQ_CSMA_CA))) + dev_err(&lp->spi->dev, "%s :ERROR IRQ1 = 0x%X\n", + __func__, irq1); + + adf7242_debug(irq1); + + xmit = test_bit(FLAG_XMIT, &lp->flags); + + if (xmit && (irq1 & IRQ_CSMA_CA)) { + if (ADF7242_REPORT_CSMA_CA_STAT) { + u8 astat; + + adf7242_read_reg(lp, REG_AUTO_STATUS, &astat); + astat &= AUTO_STATUS_MASK; + + dev_dbg(&lp->spi->dev, "AUTO_STATUS = %X:\n%s%s%s%s\n", + astat, + astat == SUCCESS ? "SUCCESS" : "", + astat == + SUCCESS_DATPEND ? "SUCCESS_DATPEND" : "", + astat == FAILURE_CSMACA ? "FAILURE_CSMACA" : "", + astat == FAILURE_NOACK ? "FAILURE_NOACK" : ""); + + /* save CSMA-CA completion status */ + lp->tx_stat = astat; + } else { + lp->tx_stat = SUCCESS; + } + complete(&lp->tx_complete); + } else if (!xmit && (irq1 & IRQ_RX_PKT_RCVD) && + (irq1 & IRQ_FRAME_VALID)) { + adf7242_rx(lp); + } else if (!xmit && test_bit(FLAG_START, &lp->flags)) { + /* Invalid packet received - drop it and restart */ + dev_dbg(&lp->spi->dev, "%s:%d : ERROR IRQ1 = 0x%X\n", + __func__, __LINE__, irq1); + adf7242_cmd(lp, CMD_RC_PHY_RDY); + adf7242_write_reg(lp, REG_IRQ1_SRC1, 0xFF); + adf7242_cmd(lp, CMD_RC_RX); + } else { + /* This can only be xmit without IRQ, likely a RX packet. + * we get an TX IRQ shortly - do nothing or let the xmit + * timeout handle this + */ + dev_dbg(&lp->spi->dev, "%s:%d : ERROR IRQ1 = 0x%X, xmit %d\n", + __func__, __LINE__, irq1, xmit); + complete(&lp->tx_complete); + } + + return IRQ_HANDLED; +} + +static int adf7242_soft_reset(struct adf7242_local *lp, int line) +{ + dev_warn(&lp->spi->dev, "%s (line %d)\n", __func__, line); + + if (test_bit(FLAG_START, &lp->flags)) + disable_irq_nosync(lp->spi->irq); + + adf7242_cmd(lp, CMD_RC_PC_RESET_NO_WAIT); + usleep_range(200, 250); + adf7242_write_reg(lp, REG_PKT_CFG, ADDON_EN | BIT(2)); + adf7242_cmd(lp, CMD_RC_PHY_RDY); + adf7242_set_promiscuous_mode(lp->hw, lp->promiscuous); + adf7242_set_csma_params(lp->hw, lp->min_be, lp->max_be, + lp->max_cca_retries); + adf7242_write_reg(lp, REG_IRQ1_SRC1, 0xFF); + + if (test_bit(FLAG_START, &lp->flags)) { + enable_irq(lp->spi->irq); + return adf7242_cmd(lp, CMD_RC_RX); + } + + return 0; +} + +static int adf7242_hw_init(struct adf7242_local *lp) +{ + int ret; + const struct firmware *fw; + + adf7242_cmd(lp, CMD_RC_RESET); + adf7242_cmd(lp, CMD_RC_IDLE); + + /* get ADF7242 addon firmware + * build this driver as module + * and place under /lib/firmware/adf7242_firmware.bin + * or compile firmware into the kernel. + */ + ret = request_firmware(&fw, FIRMWARE, &lp->spi->dev); + if (ret) { + dev_err(&lp->spi->dev, + "request_firmware() failed with %d\n", ret); + return ret; + } + + ret = adf7242_upload_firmware(lp, (u8 *)fw->data, fw->size); + if (ret) { + dev_err(&lp->spi->dev, + "upload firmware failed with %d\n", ret); + return ret; + } + + ret = adf7242_verify_firmware(lp, (u8 *)fw->data, fw->size); + if (ret) { + dev_err(&lp->spi->dev, + "verify firmware failed with %d\n", ret); + return ret; + } + + adf7242_cmd(lp, CMD_RC_PC_RESET); + + release_firmware(fw); + + adf7242_write_reg(lp, REG_FFILT_CFG, + ACCEPT_BEACON_FRAMES | + ACCEPT_DATA_FRAMES | + ACCEPT_MACCMD_FRAMES | + ACCEPT_RESERVED_FRAMES); + + adf7242_write_reg(lp, REG_AUTO_CFG, RX_AUTO_ACK_EN); + + adf7242_write_reg(lp, REG_PKT_CFG, ADDON_EN | BIT(2)); + + adf7242_write_reg(lp, REG_EXTPA_MSC, 0xF1); + adf7242_write_reg(lp, REG_RXFE_CFG, 0x1D); + + adf7242_write_reg(lp, REG_IRQ1_EN0, 0); + adf7242_write_reg(lp, REG_IRQ1_EN1, IRQ_RX_PKT_RCVD | IRQ_CSMA_CA); + + adf7242_write_reg(lp, REG_IRQ1_SRC1, 0xFF); + adf7242_write_reg(lp, REG_IRQ1_SRC0, 0xFF); + + adf7242_cmd(lp, CMD_RC_IDLE); + + return 0; +} + +static int adf7242_stats_show(struct seq_file *file, void *offset) +{ + struct adf7242_local *lp = spi_get_drvdata(file->private); + u8 stat, irq1; + + adf7242_status(lp, &stat); + adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1); + + seq_printf(file, "IRQ1 = %X:\n%s%s%s%s%s%s%s%s\n", irq1, + irq1 & IRQ_CCA_COMPLETE ? "IRQ_CCA_COMPLETE\n" : "", + irq1 & IRQ_SFD_RX ? "IRQ_SFD_RX\n" : "", + irq1 & IRQ_SFD_TX ? "IRQ_SFD_TX\n" : "", + irq1 & IRQ_RX_PKT_RCVD ? "IRQ_RX_PKT_RCVD\n" : "", + irq1 & IRQ_TX_PKT_SENT ? "IRQ_TX_PKT_SENT\n" : "", + irq1 & IRQ_CSMA_CA ? "IRQ_CSMA_CA\n" : "", + irq1 & IRQ_FRAME_VALID ? "IRQ_FRAME_VALID\n" : "", + irq1 & IRQ_ADDRESS_VALID ? "IRQ_ADDRESS_VALID\n" : ""); + + seq_printf(file, "STATUS = %X:\n%s\n%s%s%s%s%s\n", stat, + stat & STAT_RC_READY ? "RC_READY" : "RC_BUSY", + (stat & 0xf) == RC_STATUS_IDLE ? "RC_STATUS_IDLE" : "", + (stat & 0xf) == RC_STATUS_MEAS ? "RC_STATUS_MEAS" : "", + (stat & 0xf) == RC_STATUS_PHY_RDY ? "RC_STATUS_PHY_RDY" : "", + (stat & 0xf) == RC_STATUS_RX ? "RC_STATUS_RX" : "", + (stat & 0xf) == RC_STATUS_TX ? "RC_STATUS_TX" : ""); + + seq_printf(file, "RSSI = %d\n", lp->rssi); + + return 0; +} + +static int adf7242_debugfs_init(struct adf7242_local *lp) +{ + char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "adf7242-"; + struct dentry *stats; + + strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); + + lp->debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); + if (IS_ERR_OR_NULL(lp->debugfs_root)) + return PTR_ERR_OR_ZERO(lp->debugfs_root); + + stats = debugfs_create_devm_seqfile(&lp->spi->dev, "status", + lp->debugfs_root, + adf7242_stats_show); + return PTR_ERR_OR_ZERO(stats); + + return 0; +} + +static const s32 adf7242_powers[] = { + 500, 400, 300, 200, 100, 0, -100, -200, -300, -400, -500, -600, -700, + -800, -900, -1000, -1100, -1200, -1300, -1400, -1500, -1600, -1700, + -1800, -1900, -2000, -2100, -2200, -2300, -2400, -2500, -2600, +}; + +static const s32 adf7242_ed_levels[] = { + -9000, -8900, -8800, -8700, -8600, -8500, -8400, -8300, -8200, -8100, + -8000, -7900, -7800, -7700, -7600, -7500, -7400, -7300, -7200, -7100, + -7000, -6900, -6800, -6700, -6600, -6500, -6400, -6300, -6200, -6100, + -6000, -5900, -5800, -5700, -5600, -5500, -5400, -5300, -5200, -5100, + -5000, -4900, -4800, -4700, -4600, -4500, -4400, -4300, -4200, -4100, + -4000, -3900, -3800, -3700, -3600, -3500, -3400, -3200, -3100, -3000 +}; + +static int adf7242_probe(struct spi_device *spi) +{ + struct ieee802154_hw *hw; + struct adf7242_local *lp; + int ret, irq_type; + + if (!spi->irq) { + dev_err(&spi->dev, "no IRQ specified\n"); + return -EINVAL; + } + + hw = ieee802154_alloc_hw(sizeof(*lp), &adf7242_ops); + if (!hw) + return -ENOMEM; + + lp = hw->priv; + lp->hw = hw; + lp->spi = spi; + + hw->priv = lp; + hw->parent = &spi->dev; + hw->extra_tx_headroom = 0; + + /* We support only 2.4 Ghz */ + hw->phy->supported.channels[0] = 0x7FFF800; + + hw->flags = IEEE802154_HW_OMIT_CKSUM | + IEEE802154_HW_CSMA_PARAMS | + IEEE802154_HW_FRAME_RETRIES | IEEE802154_HW_AFILT | + IEEE802154_HW_PROMISCUOUS; + + hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | + WPAN_PHY_FLAG_CCA_ED_LEVEL | + WPAN_PHY_FLAG_CCA_MODE; + + hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY); + + hw->phy->supported.cca_ed_levels = adf7242_ed_levels; + hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(adf7242_ed_levels); + + hw->phy->cca.mode = NL802154_CCA_ENERGY; + + hw->phy->supported.tx_powers = adf7242_powers; + hw->phy->supported.tx_powers_size = ARRAY_SIZE(adf7242_powers); + + hw->phy->supported.min_minbe = 0; + hw->phy->supported.max_minbe = 8; + + hw->phy->supported.min_maxbe = 3; + hw->phy->supported.max_maxbe = 8; + + hw->phy->supported.min_frame_retries = 0; + hw->phy->supported.max_frame_retries = 15; + + hw->phy->supported.min_csma_backoffs = 0; + hw->phy->supported.max_csma_backoffs = 5; + + ieee802154_random_extended_addr(&hw->phy->perm_extended_addr); + + mutex_init(&lp->bmux); + init_completion(&lp->tx_complete); + + /* Setup Status Message */ + lp->stat_xfer.len = 1; + lp->stat_xfer.tx_buf = &lp->buf_stat_tx; + lp->stat_xfer.rx_buf = &lp->buf_stat_rx; + lp->buf_stat_tx = CMD_SPI_NOP; + + spi_message_init(&lp->stat_msg); + spi_message_add_tail(&lp->stat_xfer, &lp->stat_msg); + + spi_set_drvdata(spi, lp); + + ret = adf7242_hw_init(lp); + if (ret) + goto err_hw_init; + + irq_type = irq_get_trigger_type(spi->irq); + if (!irq_type) + irq_type = IRQF_TRIGGER_HIGH; + + ret = devm_request_threaded_irq(&spi->dev, spi->irq, NULL, adf7242_isr, + irq_type | IRQF_ONESHOT, + dev_name(&spi->dev), lp); + if (ret) + goto err_hw_init; + + disable_irq(spi->irq); + + ret = ieee802154_register_hw(lp->hw); + if (ret) + goto err_hw_init; + + dev_set_drvdata(&spi->dev, lp); + + adf7242_debugfs_init(lp); + + dev_info(&spi->dev, "mac802154 IRQ-%d registered\n", spi->irq); + + return ret; + +err_hw_init: + mutex_destroy(&lp->bmux); + ieee802154_free_hw(lp->hw); + + return ret; +} + +static int adf7242_remove(struct spi_device *spi) +{ + struct adf7242_local *lp = spi_get_drvdata(spi); + + if (!IS_ERR_OR_NULL(lp->debugfs_root)) + debugfs_remove_recursive(lp->debugfs_root); + + ieee802154_unregister_hw(lp->hw); + mutex_destroy(&lp->bmux); + ieee802154_free_hw(lp->hw); + + return 0; +} + +static const struct of_device_id adf7242_of_match[] = { + { .compatible = "adi,adf7242", }, + { }, +}; +MODULE_DEVICE_TABLE(of, adf7242_of_match); + +static const struct spi_device_id adf7242_device_id[] = { + { .name = "adf7242", }, + { }, +}; +MODULE_DEVICE_TABLE(spi, adf7242_device_id); + +static struct spi_driver adf7242_driver = { + .id_table = adf7242_device_id, + .driver = { + .of_match_table = of_match_ptr(adf7242_of_match), + .name = "adf7242", + .owner = THIS_MODULE, + }, + .probe = adf7242_probe, + .remove = adf7242_remove, +}; + +module_spi_driver(adf7242_driver); + +MODULE_AUTHOR("Michael Hennerich <michael.hennerich@analog.com>"); +MODULE_DESCRIPTION("ADF7242 IEEE802.15.4 Transceiver Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 199a94a9c8bcf..b1cd865ade2e0 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -310,8 +310,7 @@ static void atusb_free_urbs(struct atusb *atusb) urb = usb_get_from_anchor(&atusb->idle_urbs); if (!urb) break; - if (urb->context) - kfree_skb(urb->context); + kfree_skb(urb->context); usb_free_urb(urb); } } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index a9268db4e349f..f94392d07126c 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -88,7 +88,7 @@ static struct lock_class_key ipvlan_netdev_xmit_lock_key; static struct lock_class_key ipvlan_netdev_addr_lock_key; #define IPVLAN_FEATURES \ - (NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index dc7d970bd1c0b..a400288cb37b9 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -175,7 +175,7 @@ static void loopback_setup(struct net_device *dev) | NETIF_F_UFO | NETIF_F_HW_CSUM | NETIF_F_RXCSUM - | NETIF_F_SCTP_CSUM + | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 06c8bfeaccd6c..6a57a005e0ca8 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -758,11 +758,11 @@ static struct lock_class_key macvlan_netdev_xmit_lock_key; static struct lock_class_key macvlan_netdev_addr_lock_key; #define ALWAYS_ON_FEATURES \ - (NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \ NETIF_F_GSO_ROBUST) #define MACVLAN_FEATURES \ - (NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 0fc521941c718..d636d051fac83 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -388,7 +388,7 @@ static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb) * check, we either support them all or none. */ if (skb->ip_summed == CHECKSUM_PARTIAL && - !(features & NETIF_F_ALL_CSUM) && + !(features & NETIF_F_CSUM_MASK) && skb_checksum_help(skb)) goto drop; skb_queue_tail(&q->sk.sk_receive_queue, skb); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 0240552b50f32..50b5eac75854e 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -137,6 +137,22 @@ MODULE_DESCRIPTION("Marvell PHY driver"); MODULE_AUTHOR("Andy Fleming"); MODULE_LICENSE("GPL"); +struct marvell_hw_stat { + const char *string; + u8 page; + u8 reg; + u8 bits; +}; + +static struct marvell_hw_stat marvell_hw_stats[] = { + { "phy_receive_errors", 0, 21, 16}, + { "phy_idle_errors", 0, 10, 8 }, +}; + +struct marvell_priv { + u64 stats[ARRAY_SIZE(marvell_hw_stats)]; +}; + static int marvell_ack_interrupt(struct phy_device *phydev) { int err; @@ -986,12 +1002,80 @@ static int m88e1318_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *w return 0; } +static int marvell_get_sset_count(struct phy_device *phydev) +{ + return ARRAY_SIZE(marvell_hw_stats); +} + +static void marvell_get_strings(struct phy_device *phydev, u8 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) { + memcpy(data + i * ETH_GSTRING_LEN, + marvell_hw_stats[i].string, ETH_GSTRING_LEN); + } +} + +#ifndef UINT64_MAX +#define UINT64_MAX (u64)(~((u64)0)) +#endif +static u64 marvell_get_stat(struct phy_device *phydev, int i) +{ + struct marvell_hw_stat stat = marvell_hw_stats[i]; + struct marvell_priv *priv = phydev->priv; + int err, oldpage; + u64 val; + + oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE); + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, + stat.page); + if (err < 0) + return UINT64_MAX; + + val = phy_read(phydev, stat.reg); + if (val < 0) { + val = UINT64_MAX; + } else { + val = val & ((1 << stat.bits) - 1); + priv->stats[i] += val; + val = priv->stats[i]; + } + + phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage); + + return val; +} + +static void marvell_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) + data[i] = marvell_get_stat(phydev, i); +} + +static int marvell_probe(struct phy_device *phydev) +{ + struct marvell_priv *priv; + + priv = devm_kzalloc(&phydev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver marvell_drivers[] = { { .phy_id = MARVELL_PHY_ID_88E1101, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E1101", .features = PHY_GBIT_FEATURES, + .probe = marvell_probe, .flags = PHY_HAS_INTERRUPT, .config_aneg = &marvell_config_aneg, .read_status = &genphy_read_status, @@ -999,6 +1083,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1007,6 +1094,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1112", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1111_config_init, .config_aneg = &marvell_config_aneg, .read_status = &genphy_read_status, @@ -1014,6 +1102,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1022,6 +1113,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1111", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1111_config_init, .config_aneg = &marvell_config_aneg, .read_status = &marvell_read_status, @@ -1029,6 +1121,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1037,6 +1132,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1118", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1118_config_init, .config_aneg = &m88e1118_config_aneg, .read_status = &genphy_read_status, @@ -1044,6 +1140,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = {.owner = THIS_MODULE,}, }, { @@ -1052,6 +1151,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1121R", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_aneg = &m88e1121_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1059,6 +1159,9 @@ static struct phy_driver marvell_drivers[] = { .did_interrupt = &m88e1121_did_interrupt, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1067,6 +1170,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1318S", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_aneg = &m88e1318_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1076,6 +1180,9 @@ static struct phy_driver marvell_drivers[] = { .set_wol = &m88e1318_set_wol, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1084,6 +1191,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1145", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1145_config_init, .config_aneg = &marvell_config_aneg, .read_status = &genphy_read_status, @@ -1091,6 +1199,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1099,6 +1210,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1149R", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1149_config_init, .config_aneg = &m88e1118_config_aneg, .read_status = &genphy_read_status, @@ -1106,6 +1218,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1114,6 +1229,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1240", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1111_config_init, .config_aneg = &marvell_config_aneg, .read_status = &genphy_read_status, @@ -1121,6 +1237,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1129,6 +1248,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1116R", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_init = &m88e1116r_config_init, .config_aneg = &genphy_config_aneg, .read_status = &genphy_read_status, @@ -1136,6 +1256,9 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1144,6 +1267,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1510", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_aneg = &m88e1510_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1151,6 +1275,9 @@ static struct phy_driver marvell_drivers[] = { .did_interrupt = &m88e1121_did_interrupt, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1159,6 +1286,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1540", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_aneg = &m88e1510_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1166,6 +1294,9 @@ static struct phy_driver marvell_drivers[] = { .did_interrupt = &m88e1121_did_interrupt, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, { @@ -1174,6 +1305,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E3016", .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, + .probe = marvell_probe, .config_aneg = &genphy_config_aneg, .config_init = &m88e3016_config_init, .aneg_done = &marvell_aneg_done, @@ -1183,6 +1315,9 @@ static struct phy_driver marvell_drivers[] = { .did_interrupt = &m88e1121_did_interrupt, .resume = &genphy_resume, .suspend = &genphy_suspend, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, .driver = { .owner = THIS_MODULE }, }, }; diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 908e8d4863429..7f8e7662e28cb 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -149,9 +149,14 @@ int mdio_mux_init(struct device *dev, } cb->bus_number = v; cb->parent = pb; + cb->mii_bus = mdiobus_alloc(); + if (!cb->mii_bus) { + ret_val = -ENOMEM; + of_node_put(child_bus_node); + break; + } cb->mii_bus->priv = cb; - cb->mii_bus->irq = cb->phy_irq; cb->mii_bus->name = "mdio_mux"; snprintf(cb->mii_bus->id, MII_BUS_ID_SIZE, "%x.%x", diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index cf6312fafea54..1a6048a8c29d3 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -73,6 +73,17 @@ #define PS_TO_REG 200 +struct kszphy_hw_stat { + const char *string; + u8 reg; + u8 bits; +}; + +static struct kszphy_hw_stat kszphy_hw_stats[] = { + { "phy_receive_errors", 21, 16}, + { "phy_idle_errors", 10, 8 }, +}; + struct kszphy_type { u32 led_mode_reg; u16 interrupt_level_mask; @@ -86,6 +97,7 @@ struct kszphy_priv { int led_mode; bool rmii_ref_clk_sel; bool rmii_ref_clk_sel_val; + u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; static const struct kszphy_type ksz8021_type = { @@ -339,9 +351,18 @@ static int ksz9021_config_init(struct phy_device *phydev) { const struct device *dev = &phydev->dev; const struct device_node *of_node = dev->of_node; + const struct device *dev_walker; - if (!of_node && dev->parent->of_node) - of_node = dev->parent->of_node; + /* The Micrel driver has a deprecated option to place phy OF + * properties in the MAC node. Walk up the tree of devices to + * find a device with an OF node. + */ + dev_walker = &phydev->dev; + do { + of_node = dev_walker->of_node; + dev_walker = dev_walker->parent; + + } while (!of_node && dev_walker); if (of_node) { ksz9021_load_values_from_of(phydev, of_node, @@ -560,6 +581,51 @@ ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum, { } +static int kszphy_get_sset_count(struct phy_device *phydev) +{ + return ARRAY_SIZE(kszphy_hw_stats); +} + +static void kszphy_get_strings(struct phy_device *phydev, u8 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kszphy_hw_stats); i++) { + memcpy(data + i * ETH_GSTRING_LEN, + kszphy_hw_stats[i].string, ETH_GSTRING_LEN); + } +} + +#ifndef UINT64_MAX +#define UINT64_MAX (u64)(~((u64)0)) +#endif +static u64 kszphy_get_stat(struct phy_device *phydev, int i) +{ + struct kszphy_hw_stat stat = kszphy_hw_stats[i]; + struct kszphy_priv *priv = phydev->priv; + u64 val; + + val = phy_read(phydev, stat.reg); + if (val < 0) { + val = UINT64_MAX; + } else { + val = val & ((1 << stat.bits) - 1); + priv->stats[i] += val; + val = priv->stats[i]; + } + + return val; +} + +static void kszphy_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kszphy_hw_stats); i++) + data[i] = kszphy_get_stat(phydev, i); +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -633,6 +699,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -650,6 +719,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -667,6 +739,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -684,6 +759,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -701,6 +779,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -718,6 +799,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -734,6 +818,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -750,6 +837,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -764,6 +854,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, @@ -779,6 +872,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .read_mmd_indirect = ksz9021_rd_mmd_phyreg, @@ -796,6 +892,9 @@ static struct phy_driver ksphy_driver[] = { .read_status = ksz9031_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE, }, @@ -808,6 +907,9 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE, }, @@ -820,6 +922,9 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE, }, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 9a863c6a6a33a..fc8ad001bc949 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1138,9 +1138,15 @@ static const struct net_device_ops ppp_netdev_ops = { .ndo_get_stats64 = ppp_get_stats64, }; +static struct device_type ppp_type = { + .name = "ppp", +}; + static void ppp_setup(struct net_device *dev) { dev->netdev_ops = &ppp_netdev_ops; + SET_NETDEV_DEVTYPE(dev, &ppp_type); + dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; dev->addr_len = 0; @@ -2720,8 +2726,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, int ret = -ENOMEM; int i; - dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_UNKNOWN, - ppp_setup); + dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_ENUM, ppp_setup); if (!dev) goto out1; diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index b8da2eabac3ef..f3c63022eb3c5 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -550,6 +550,9 @@ static int pppoe_create(struct net *net, struct socket *sock, int kern) sk->sk_family = PF_PPPOX; sk->sk_protocol = PX_PROTO_OE; + INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work, + pppoe_unbind_sock_work); + return 0; } @@ -614,8 +617,6 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); - INIT_WORK(&po->proto.pppoe.padt_work, pppoe_unbind_sock_work); - error = -EINVAL; if (sp->sa_protocol != PX_PROTO_OE) goto end; @@ -645,8 +646,13 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, po->pppoe_dev = NULL; } - memset(sk_pppox(po) + 1, 0, - sizeof(struct pppox_sock) - sizeof(struct sock)); + po->pppoe_ifindex = 0; + memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa)); + memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay)); + memset(&po->chan, 0, sizeof(po->chan)); + po->next = NULL; + po->num = 0; + sk->sk_state = PPPOX_NONE; } diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index e18e0980bc61c..90868ca5e3412 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -419,6 +419,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct pptp_opt *opt = &po->proto.pptp; int error = 0; + if (sockaddr_len < sizeof(struct sockaddr_pppox)) + return -EINVAL; + lock_sock(sk); opt->src_addr = sp->sa_addr.pptp; @@ -440,6 +443,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, struct flowi4 fl4; int error = 0; + if (sockaddr_len < sizeof(struct sockaddr_pppox)) + return -EINVAL; + if (sp->sa_protocol != PX_PROTO_PPTP) return -EINVAL; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 059c0f60a2b28..2528331de1935 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -981,14 +981,18 @@ static void team_port_disable(struct team *team, team_lower_state_changed(port); } -#define TEAM_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ +#define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ NETIF_F_HIGHDMA | NETIF_F_LRO) +#define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_RXCSUM | NETIF_F_ALL_TSO) + static void __team_compute_features(struct team *team) { struct team_port *port; u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL; + netdev_features_t enc_features = TEAM_ENC_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; @@ -997,6 +1001,11 @@ static void __team_compute_features(struct team *team) vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, TEAM_VLAN_FEATURES); + enc_features = + netdev_increment_features(enc_features, + port->dev->hw_enc_features, + TEAM_ENC_FEATURES); + dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) @@ -1004,6 +1013,7 @@ static void __team_compute_features(struct team *team) } team->dev->vlan_features = vlan_features; + team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL; team->dev->hard_header_len = max_hard_header_len; team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -2091,7 +2101,7 @@ static void team_setup(struct net_device *dev) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM); + dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index f0db770e8b2f9..88bb8cc3555b8 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1095,6 +1095,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, u32 rxhash; ssize_t n; + if (!(tun->dev->flags & IFF_UP)) + return -EIO; + if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index bd9acff1eb7bf..0c5c22b84da85 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -118,7 +118,7 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, return 0; } if (size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) { - netdev_err(dev->net, "asix_rx_fixup() Bad RX Length %d\n", + netdev_dbg(dev->net, "asix_rx_fixup() Bad RX Length %d\n", size); return 0; } diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index bbde9884ab8ae..bdd83d95ec0aa 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -100,7 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = { .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, - .ndo_change_mtu = usbnet_change_mtu, + .ndo_change_mtu = cdc_ncm_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = cdc_mbim_rx_add_vid, @@ -158,7 +158,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf) if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting)) goto err; - ret = cdc_ncm_bind_common(dev, intf, data_altsetting, 0); + ret = cdc_ncm_bind_common(dev, intf, data_altsetting, dev->driver_info->data); if (ret) goto err; @@ -582,6 +582,26 @@ static const struct driver_info cdc_mbim_info_zlp = { .tx_fixup = cdc_mbim_tx_fixup, }; +/* The spefication explicitly allows NDPs to be placed anywhere in the + * frame, but some devices fail unless the NDP is placed after the IP + * packets. Using the CDC_NCM_FLAG_NDP_TO_END flags to force this + * behaviour. + * + * Note: The current implementation of this feature restricts each NTB + * to a single NDP, implying that multiplexed sessions cannot share an + * NTB. This might affect performace for multiplexed sessions. + */ +static const struct driver_info cdc_mbim_info_ndp_to_end = { + .description = "CDC MBIM", + .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN, + .bind = cdc_mbim_bind, + .unbind = cdc_mbim_unbind, + .manage_power = cdc_mbim_manage_power, + .rx_fixup = cdc_mbim_rx_fixup, + .tx_fixup = cdc_mbim_tx_fixup, + .data = CDC_NCM_FLAG_NDP_TO_END, +}; + static const struct usb_device_id mbim_devs[] = { /* This duplicate NCM entry is intentional. MBIM devices can * be disguised as NCM by default, and this is necessary to @@ -597,6 +617,10 @@ static const struct usb_device_id mbim_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x0bdb, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info, }, + /* Huawei E3372 fails unless NDP comes after the IP packets */ + { USB_DEVICE_AND_INTERFACE_INFO(0x12d1, 0x157d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end, + }, /* default entry */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_zlp, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index b45e5cae2a6b0..dc0212c3cc28c 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -41,6 +41,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ctype.h> +#include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/workqueue.h> #include <linux/mii.h> @@ -732,6 +733,33 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx) kfree(ctx); } +/* we need to override the usbnet change_mtu ndo for two reasons: + * - respect the negotiated maximum datagram size + * - avoid unwanted changes to rx and tx buffers + */ +int cdc_ncm_change_mtu(struct net_device *net, int new_mtu) +{ + struct usbnet *dev = netdev_priv(net); + struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; + int maxmtu = ctx->max_datagram_size - cdc_ncm_eth_hlen(dev); + + if (new_mtu <= 0 || new_mtu > maxmtu) + return -EINVAL; + net->mtu = new_mtu; + return 0; +} +EXPORT_SYMBOL_GPL(cdc_ncm_change_mtu); + +static const struct net_device_ops cdc_ncm_netdev_ops = { + .ndo_open = usbnet_open, + .ndo_stop = usbnet_stop, + .ndo_start_xmit = usbnet_start_xmit, + .ndo_tx_timeout = usbnet_tx_timeout, + .ndo_change_mtu = cdc_ncm_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags) { struct cdc_ncm_ctx *ctx; @@ -866,6 +894,9 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ /* add our sysfs attrs */ dev->net->sysfs_groups[0] = &cdc_ncm_sysfs_attr_group; + /* must handle MTU changes */ + dev->net->netdev_ops = &cdc_ncm_netdev_ops; + return 0; error2: @@ -998,10 +1029,18 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_ * NTH16 header as we would normally do. NDP isn't written to the SKB yet, and * the wNdpIndex field in the header is actually not consistent with reality. It will be later. */ - if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) + if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) { if (ctx->delayed_ndp16->dwSignature == sign) return ctx->delayed_ndp16; + /* We can only push a single NDP to the end. Return + * NULL to send what we've already got and queue this + * skb for later. + */ + else if (ctx->delayed_ndp16->dwSignature) + return NULL; + } + /* follow the chain of NDPs, looking for a match */ while (ndpoffset) { ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb->data + ndpoffset); @@ -1593,6 +1632,24 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long) &wwan_info, }, + /* DW5812 LTE Verizon Mobile Broadband Card + * Unlike DW5550 this device requires FLAG_NOARP + */ + { USB_DEVICE_AND_INTERFACE_INFO(0x413c, 0x81bb, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, + + /* DW5813 LTE AT&T Mobile Broadband Card + * Unlike DW5550 this device requires FLAG_NOARP + */ + { USB_DEVICE_AND_INTERFACE_INFO(0x413c, 0x81bc, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, + /* Dell branded MBM devices like DW5550 */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_VENDOR, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index babc84a3946c2..d0b29733c021f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -374,7 +374,10 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf) "bogus CDC Union: master=%u, slave=%u\n", cdc_union->bMasterInterface0, cdc_union->bSlaveInterface0); - goto err; + + /* ignore and continue... */ + cdc_union = NULL; + info->data = intf; } } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index d9427ca3dba79..e691c7df1ac2e 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1986,7 +1986,7 @@ rtl8152_features_check(struct sk_buff *skb, struct net_device *dev, int offset = skb_transport_offset(skb); if ((mss || skb->ip_summed == CHECKSUM_PARTIAL) && offset > max_offset) - features &= ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); else if ((skb->len + sizeof(struct tx_desc)) > agg_buf_sz) features &= ~NETIF_F_GSO_MASK; @@ -3067,17 +3067,6 @@ static int rtl8152_open(struct net_device *netdev) mutex_lock(&tp->control); - /* The WORK_ENABLE may be set when autoresume occurs */ - if (test_bit(WORK_ENABLE, &tp->flags)) { - clear_bit(WORK_ENABLE, &tp->flags); - usb_kill_urb(tp->intr_urb); - cancel_delayed_work_sync(&tp->schedule); - - /* disable the tx/rx, if the workqueue has enabled them. */ - if (netif_carrier_ok(netdev)) - tp->rtl_ops.disable(tp); - } - tp->rtl_ops.up(tp); rtl8152_set_speed(tp, AUTONEG_ENABLE, @@ -3124,12 +3113,6 @@ static int rtl8152_close(struct net_device *netdev) } else { mutex_lock(&tp->control); - /* The autosuspend may have been enabled and wouldn't - * be disable when autoresume occurs, because the - * netif_running() would be false. - */ - rtl_runtime_suspend_enable(tp, false); - tp->rtl_ops.down(tp); mutex_unlock(&tp->control); @@ -3512,7 +3495,7 @@ static int rtl8152_resume(struct usb_interface *intf) netif_device_attach(tp->netdev); } - if (netif_running(tp->netdev)) { + if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) { if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { rtl_runtime_suspend_enable(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); @@ -3532,6 +3515,8 @@ static int rtl8152_resume(struct usb_interface *intf) } usb_submit_urb(tp->intr_urb, GFP_KERNEL); } else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + if (tp->netdev->flags & IFF_UP) + rtl_runtime_suspend_enable(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0ef4a5ad55573..ba21d072be31c 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -117,12 +117,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) kfree_skb(skb); goto drop; } - /* don't change ip_summed == CHECKSUM_PARTIAL, as that - * will cause bad checksum on forwarded packets - */ - if (skb->ip_summed == CHECKSUM_NONE && - rcv->features & NETIF_F_RXCSUM) - skb->ip_summed = CHECKSUM_UNNECESSARY; if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) { struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b1ae4cbf24534..767ab11a6e9f6 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -140,6 +140,12 @@ struct virtnet_info { /* CPU hot plug notifier */ struct notifier_block nb; + + /* Control VQ buffers: protected by the rtnl lock */ + struct virtio_net_ctrl_hdr ctrl_hdr; + virtio_net_ctrl_ack ctrl_status; + u8 ctrl_promisc; + u8 ctrl_allmulti; }; struct padded_vnet_hdr { @@ -974,31 +980,30 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, struct scatterlist *out) { struct scatterlist *sgs[4], hdr, stat; - struct virtio_net_ctrl_hdr ctrl; - virtio_net_ctrl_ack status = ~0; unsigned out_num = 0, tmp; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); - ctrl.class = class; - ctrl.cmd = cmd; + vi->ctrl_status = ~0; + vi->ctrl_hdr.class = class; + vi->ctrl_hdr.cmd = cmd; /* Add header */ - sg_init_one(&hdr, &ctrl, sizeof(ctrl)); + sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr)); sgs[out_num++] = &hdr; if (out) sgs[out_num++] = out; /* Add return status. */ - sg_init_one(&stat, &status, sizeof(status)); + sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status)); sgs[out_num] = &stat; BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); if (unlikely(!virtqueue_kick(vi->cvq))) - return status == VIRTIO_NET_OK; + return vi->ctrl_status == VIRTIO_NET_OK; /* Spin for a response, the kick causes an ioport write, trapping * into the hypervisor, so the request should be handled immediately. @@ -1007,7 +1012,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, !virtqueue_is_broken(vi->cvq)) cpu_relax(); - return status == VIRTIO_NET_OK; + return vi->ctrl_status == VIRTIO_NET_OK; } static int virtnet_set_mac_address(struct net_device *dev, void *p) @@ -1149,7 +1154,6 @@ static void virtnet_set_rx_mode(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg[2]; - u8 promisc, allmulti; struct virtio_net_ctrl_mac *mac_data; struct netdev_hw_addr *ha; int uc_count; @@ -1161,22 +1165,22 @@ static void virtnet_set_rx_mode(struct net_device *dev) if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; - promisc = ((dev->flags & IFF_PROMISC) != 0); - allmulti = ((dev->flags & IFF_ALLMULTI) != 0); + vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0); + vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0); - sg_init_one(sg, &promisc, sizeof(promisc)); + sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_PROMISC, sg)) dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", - promisc ? "en" : "dis"); + vi->ctrl_promisc ? "en" : "dis"); - sg_init_one(sg, &allmulti, sizeof(allmulti)); + sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_ALLMULTI, sg)) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", - allmulti ? "en" : "dis"); + vi->ctrl_allmulti ? "en" : "dis"); uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6369a5734d4c3..fecf7b6c732e9 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1158,7 +1158,6 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, struct pcpu_sw_netstats *stats; union vxlan_addr saddr; int err = 0; - union vxlan_addr *remote_ip; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA) @@ -1169,7 +1168,6 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, if (!vxlan) goto drop; - remote_ip = &vxlan->default_dst.remote_ip; skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev))); skb->protocol = eth_type_trans(skb, vxlan->dev); @@ -1179,8 +1177,8 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) goto drop; - /* Re-examine inner Ethernet packet */ - if (remote_ip->sa.sa_family == AF_INET) { + /* Get data from the outer IP header */ + if (vxlan_get_sk_family(vs) == AF_INET) { oip = ip_hdr(skb); saddr.sin.sin_addr.s_addr = oip->saddr; saddr.sa.sa_family = AF_INET; @@ -1843,10 +1841,39 @@ static int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *sk skb_set_inner_protocol(skb, htons(ETH_P_TEB)); - return udp_tunnel_xmit_skb(rt, sk, skb, src, dst, tos, - ttl, df, src_port, dst_port, xnet, - !(vxflags & VXLAN_F_UDP_CSUM)); + udp_tunnel_xmit_skb(rt, sk, skb, src, dst, tos, ttl, df, + src_port, dst_port, xnet, + !(vxflags & VXLAN_F_UDP_CSUM)); + return 0; +} + +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, + struct sk_buff *skb, int oif, + const struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct dst_entry *ndst; + struct flowi6 fl6; + int err; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.daddr = *daddr; + fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = IPPROTO_UDP; + + err = ipv6_stub->ipv6_dst_lookup(vxlan->net, + vxlan->vn6_sock->sock->sk, + &ndst, &fl6); + if (err < 0) + return ERR_PTR(err); + + *saddr = fl6.saddr; + return ndst; } +#endif /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, @@ -2030,26 +2057,20 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, skb = NULL; goto rt_tx_error; } - - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); #if IS_ENABLED(CONFIG_IPV6) } else { struct dst_entry *ndst; - struct flowi6 fl6; + struct in6_addr saddr; u32 rt6i_flags; if (!vxlan->vn6_sock) goto drop; sk = vxlan->vn6_sock->sock->sk; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0; - fl6.daddr = dst->sin6.sin6_addr; - fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; - fl6.flowi6_mark = skb->mark; - fl6.flowi6_proto = IPPROTO_UDP; - - if (ipv6_stub->ipv6_dst_lookup(vxlan->net, sk, &ndst, &fl6)) { + ndst = vxlan6_get_route(vxlan, skb, + rdst ? rdst->remote_ifindex : 0, + &dst->sin6.sin6_addr, &saddr); + if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", &dst->sin6.sin6_addr); dev->stats.tx_carrier_errors++; @@ -2081,7 +2102,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ttl = ttl ? : ip6_dst_hoplimit(ndst); - err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr, + err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr, 0, ttl, src_port, dst_port, htonl(vni << 8), md, !net_eq(vxlan->net, dev_net(vxlan->dev)), flags); @@ -2395,9 +2416,30 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; - if (ip_tunnel_info_af(info) == AF_INET) + if (ip_tunnel_info_af(info) == AF_INET) { + if (!vxlan->vn4_sock) + return -EINVAL; return egress_ipv4_tun_info(dev, skb, info, sport, dport); - return -EINVAL; + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct dst_entry *ndst; + + if (!vxlan->vn6_sock) + return -EINVAL; + ndst = vxlan6_get_route(vxlan, skb, 0, + &info->key.u.ipv6.dst, + &info->key.u.ipv6.src); + if (IS_ERR(ndst)) + return PTR_ERR(ndst); + dst_release(ndst); + + info->key.tp_src = sport; + info->key.tp_dst = dport; +#else /* !CONFIG_IPV6 */ + return -EPFNOSUPPORT; +#endif + } + return 0; } static const struct net_device_ops vxlan_netdev_ops = { diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index e73f138578468..a20d688d25957 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -586,6 +586,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(28)) || pci_set_dma_mask(pdev, DMA_BIT_MASK(28))) { pr_err("No usable DMA configuration\n"); + pci_disable_device(pdev); return -EIO; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index e481f3710bd38..1049c34e7d430 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -258,18 +258,18 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, struct netrx_pending_operations *npo) { struct xenvif_rx_meta *meta; - struct xen_netif_rx_request *req; + struct xen_netif_rx_request req; - req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); + RING_COPY_REQUEST(&queue->rx, queue->rx.req_cons++, &req); meta = npo->meta + npo->meta_prod++; meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; meta->size = 0; - meta->id = req->id; + meta->id = req.id; npo->copy_off = 0; - npo->copy_gref = req->gref; + npo->copy_gref = req.gref; return meta; } @@ -424,7 +424,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, struct xenvif *vif = netdev_priv(skb->dev); int nr_frags = skb_shinfo(skb)->nr_frags; int i; - struct xen_netif_rx_request *req; + struct xen_netif_rx_request req; struct xenvif_rx_meta *meta; unsigned char *data; int head = 1; @@ -443,15 +443,15 @@ static int xenvif_gop_skb(struct sk_buff *skb, /* Set up a GSO prefix descriptor, if necessary */ if ((1 << gso_type) & vif->gso_prefix_mask) { - req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); + RING_COPY_REQUEST(&queue->rx, queue->rx.req_cons++, &req); meta = npo->meta + npo->meta_prod++; meta->gso_type = gso_type; meta->gso_size = skb_shinfo(skb)->gso_size; meta->size = 0; - meta->id = req->id; + meta->id = req.id; } - req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); + RING_COPY_REQUEST(&queue->rx, queue->rx.req_cons++, &req); meta = npo->meta + npo->meta_prod++; if ((1 << gso_type) & vif->gso_mask) { @@ -463,9 +463,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, } meta->size = 0; - meta->id = req->id; + meta->id = req.id; npo->copy_off = 0; - npo->copy_gref = req->gref; + npo->copy_gref = req.gref; data = skb->data; while (data < skb_tail_pointer(skb)) { @@ -679,9 +679,7 @@ static void tx_add_credit(struct xenvif_queue *queue) * Allow a burst big enough to transmit a jumbo packet of up to 128kB. * Otherwise the interface can seize up due to insufficient credit. */ - max_burst = RING_GET_REQUEST(&queue->tx, queue->tx.req_cons)->size; - max_burst = min(max_burst, 131072UL); - max_burst = max(max_burst, queue->credit_bytes); + max_burst = max(131072UL, queue->credit_bytes); /* Take care that adding a new chunk of credit doesn't wrap to zero. */ max_credit = queue->remaining_credit + queue->credit_bytes; @@ -711,7 +709,7 @@ static void xenvif_tx_err(struct xenvif_queue *queue, spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; - txp = RING_GET_REQUEST(&queue->tx, cons++); + RING_COPY_REQUEST(&queue->tx, cons++, txp); } while (1); queue->tx.req_cons = cons; } @@ -778,8 +776,7 @@ static int xenvif_count_requests(struct xenvif_queue *queue, if (drop_err) txp = &dropped_tx; - memcpy(txp, RING_GET_REQUEST(&queue->tx, cons + slots), - sizeof(*txp)); + RING_COPY_REQUEST(&queue->tx, cons + slots, txp); /* If the guest submitted a frame >= 64 KiB then * first->size overflowed and following slots will @@ -1112,8 +1109,7 @@ static int xenvif_get_extras(struct xenvif_queue *queue, return -EBADR; } - memcpy(&extra, RING_GET_REQUEST(&queue->tx, cons), - sizeof(extra)); + RING_COPY_REQUEST(&queue->tx, cons, &extra); if (unlikely(!extra.type || extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { queue->tx.req_cons = ++cons; @@ -1322,7 +1318,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, idx = queue->tx.req_cons; rmb(); /* Ensure that we see the request before we copy it. */ - memcpy(&txreq, RING_GET_REQUEST(&queue->tx, idx), sizeof(txreq)); + RING_COPY_REQUEST(&queue->tx, idx, &txreq); /* Credit-based scheduling. */ if (txreq.size > queue->remaining_credit && diff --git a/drivers/nfc/Kconfig b/drivers/nfc/Kconfig index 0d6003dee3af6..7437c9dfd8fc8 100644 --- a/drivers/nfc/Kconfig +++ b/drivers/nfc/Kconfig @@ -76,4 +76,5 @@ source "drivers/nfc/st21nfca/Kconfig" source "drivers/nfc/st-nci/Kconfig" source "drivers/nfc/nxp-nci/Kconfig" source "drivers/nfc/s3fwrn5/Kconfig" +source "drivers/nfc/st95hf/Kconfig" endmenu diff --git a/drivers/nfc/Makefile b/drivers/nfc/Makefile index e3621416a48ef..0a99e67daa10f 100644 --- a/drivers/nfc/Makefile +++ b/drivers/nfc/Makefile @@ -16,3 +16,4 @@ obj-$(CONFIG_NFC_ST21NFCA) += st21nfca/ obj-$(CONFIG_NFC_ST_NCI) += st-nci/ obj-$(CONFIG_NFC_NXP_NCI) += nxp-nci/ obj-$(CONFIG_NFC_S3FWRN5) += s3fwrn5/ +obj-$(CONFIG_NFC_ST95HF) += st95hf/ diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 532db28145c7d..5e797d5c38edc 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -298,6 +298,12 @@ static int fdp_nci_i2c_probe(struct i2c_client *client, return -ENODEV; } + /* Checking if we have an irq */ + if (client->irq <= 0) { + nfc_err(dev, "IRQ not present\n"); + return -ENODEV; + } + phy = devm_kzalloc(dev, sizeof(struct fdp_i2c_phy), GFP_KERNEL); if (!phy) @@ -307,12 +313,6 @@ static int fdp_nci_i2c_probe(struct i2c_client *client, phy->next_read_size = FDP_NCI_I2C_MIN_PAYLOAD; i2c_set_clientdata(client, phy); - /* Checking if we have an irq */ - if (client->irq <= 0) { - dev_err(dev, "IRQ not present\n"); - return -ENODEV; - } - r = request_threaded_irq(client->irq, NULL, fdp_nci_i2c_irq_thread_fn, IRQF_TRIGGER_RISING | IRQF_ONESHOT, FDP_I2C_DRIVER_NAME, phy); diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index daf352597ef8f..918e8f2eac47f 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -50,8 +50,6 @@ struct microread_i2c_phy { struct i2c_client *i2c_dev; struct nfc_hci_dev *hdev; - int irq; - int hard_fault; /* * < 0 if hardware error occured (e.g. i2c err) * and prevents normal operation. diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index 26ac9e5fa1ab2..93aaca5868580 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -32,6 +32,8 @@ #define NFCSIM_POLL_TARGET 2 #define NFCSIM_POLL_DUAL (NFCSIM_POLL_INITIATOR | NFCSIM_POLL_TARGET) +#define RX_DEFAULT_DELAY 5 + struct nfcsim { struct nfc_dev *nfc_dev; @@ -51,6 +53,8 @@ struct nfcsim { u8 initiator; + u32 rx_delay; + data_exchange_cb_t cb; void *cb_context; @@ -320,10 +324,9 @@ static int nfcsim_tx(struct nfc_dev *nfc_dev, struct nfc_target *target, * If packet transmission occurs immediately between them, we have a * non-stop flow of several tens of thousands SYMM packets per second * and a burning cpu. - * - * TODO: Add support for a sysfs entry to control this delay. */ - queue_delayed_work(wq, &peer->recv_work, msecs_to_jiffies(5)); + queue_delayed_work(wq, &peer->recv_work, + msecs_to_jiffies(dev->rx_delay)); mutex_unlock(&peer->lock); @@ -461,6 +464,7 @@ static struct nfcsim *nfcsim_init_dev(void) if (rc) goto free_nfc_dev; + dev->rx_delay = RX_DEFAULT_DELAY; return dev; free_nfc_dev: diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index df4333c7ee0f8..11520f472f982 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -52,7 +52,6 @@ struct nxp_nci_i2c_phy { unsigned int gpio_en; unsigned int gpio_fw; - unsigned int gpio_irq; int hard_fault; /* * < 0 if hardware error occurred (e.g. i2c err) @@ -85,7 +84,7 @@ static int nxp_nci_i2c_write(void *phy_id, struct sk_buff *skb) return phy->hard_fault; r = i2c_master_send(client, skb->data, skb->len); - if (r == -EREMOTEIO) { + if (r < 0) { /* Retry, chip was in standby */ usleep_range(110000, 120000); r = i2c_master_send(client, skb->data, skb->len); @@ -264,8 +263,6 @@ exit_irq_none: return IRQ_NONE; } -#ifdef CONFIG_OF - static int nxp_nci_i2c_parse_devtree(struct i2c_client *client) { struct nxp_nci_i2c_phy *phy = i2c_get_clientdata(client); @@ -294,48 +291,24 @@ static int nxp_nci_i2c_parse_devtree(struct i2c_client *client) } phy->gpio_fw = r; - r = irq_of_parse_and_map(pp, 0); - if (r < 0) { - nfc_err(&client->dev, "Unable to get irq, error: %d\n", r); - return r; - } - client->irq = r; - return 0; } -#else - -static int nxp_nci_i2c_parse_devtree(struct i2c_client *client) -{ - return -ENODEV; -} - -#endif - static int nxp_nci_i2c_acpi_config(struct nxp_nci_i2c_phy *phy) { struct i2c_client *client = phy->i2c_dev; - struct gpio_desc *gpiod_en, *gpiod_fw, *gpiod_irq; + struct gpio_desc *gpiod_en, *gpiod_fw; gpiod_en = devm_gpiod_get_index(&client->dev, NULL, 2, GPIOD_OUT_LOW); gpiod_fw = devm_gpiod_get_index(&client->dev, NULL, 1, GPIOD_OUT_LOW); - gpiod_irq = devm_gpiod_get_index(&client->dev, NULL, 0, GPIOD_IN); - if (IS_ERR(gpiod_en) || IS_ERR(gpiod_fw) || IS_ERR(gpiod_irq)) { + if (IS_ERR(gpiod_en) || IS_ERR(gpiod_fw)) { nfc_err(&client->dev, "No GPIOs\n"); return -EINVAL; } - client->irq = gpiod_to_irq(gpiod_irq); - if (client->irq < 0) { - nfc_err(&client->dev, "No IRQ\n"); - return -EINVAL; - } - phy->gpio_en = desc_to_gpio(gpiod_en); phy->gpio_fw = desc_to_gpio(gpiod_fw); - phy->gpio_irq = desc_to_gpio(gpiod_irq); return 0; } @@ -374,7 +347,6 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, } else if (pdata) { phy->gpio_en = pdata->gpio_en; phy->gpio_fw = pdata->gpio_fw; - client->irq = pdata->irq; } else if (ACPI_HANDLE(&client->dev)) { r = nxp_nci_i2c_acpi_config(phy); if (r < 0) diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index fa75c53f3fa53..76c318444304e 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -166,7 +166,6 @@ struct pn544_i2c_phy { struct nfc_hci_dev *hdev; unsigned int gpio_en; - unsigned int gpio_irq; unsigned int gpio_fw; unsigned int en_polarity; @@ -879,9 +878,8 @@ static int pn544_hci_i2c_acpi_request_resources(struct i2c_client *client) { struct pn544_i2c_phy *phy = i2c_get_clientdata(client); const struct acpi_device_id *id; - struct gpio_desc *gpiod_en, *gpiod_irq, *gpiod_fw; + struct gpio_desc *gpiod_en, *gpiod_fw; struct device *dev; - int ret; if (!client) return -EINVAL; @@ -914,32 +912,9 @@ static int pn544_hci_i2c_acpi_request_resources(struct i2c_client *client) phy->gpio_fw = desc_to_gpio(gpiod_fw); - /* Get IRQ GPIO */ - gpiod_irq = devm_gpiod_get_index(dev, PN544_GPIO_NAME_IRQ, 0, - GPIOD_IN); - if (IS_ERR(gpiod_irq)) { - nfc_err(dev, "Unable to get IRQ GPIO\n"); - return -ENODEV; - } - - phy->gpio_irq = desc_to_gpio(gpiod_irq); - - /* Map the pin to an IRQ */ - ret = gpiod_to_irq(gpiod_irq); - if (ret < 0) { - nfc_err(dev, "Fail pin IRQ mapping\n"); - return ret; - } - - nfc_info(dev, "GPIO resource, no:%d irq:%d\n", - desc_to_gpio(gpiod_irq), ret); - client->irq = ret; - return 0; } -#ifdef CONFIG_OF - static int pn544_hci_i2c_of_request_resources(struct i2c_client *client) { struct pn544_i2c_phy *phy = i2c_get_clientdata(client); @@ -996,15 +971,6 @@ static int pn544_hci_i2c_of_request_resources(struct i2c_client *client) goto err_gpio_fw; } - /* IRQ */ - ret = irq_of_parse_and_map(pp, 0); - if (ret < 0) { - nfc_err(&client->dev, - "Unable to get irq, error: %d\n", ret); - goto err_gpio_fw; - } - client->irq = ret; - return 0; err_gpio_fw: @@ -1015,15 +981,6 @@ err_dt: return ret; } -#else - -static int pn544_hci_i2c_of_request_resources(struct i2c_client *client) -{ - return -ENODEV; -} - -#endif - static int pn544_hci_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -1076,7 +1033,6 @@ static int pn544_hci_i2c_probe(struct i2c_client *client, phy->gpio_en = pdata->get_gpio(NFC_GPIO_ENABLE); phy->gpio_fw = pdata->get_gpio(NFC_GPIO_FW_RESET); - phy->gpio_irq = pdata->get_gpio(NFC_GPIO_IRQ); /* Using ACPI */ } else if (ACPI_HANDLE(&client->dev)) { r = pn544_hci_i2c_acpi_request_resources(client); diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 0d866ca295e3f..9d9c8d57a042d 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -147,7 +147,7 @@ static struct nci_ops s3fwrn5_nci_ops = { }; int s3fwrn5_probe(struct nci_dev **ndev, void *phy_id, struct device *pdev, - struct s3fwrn5_phy_ops *phy_ops, unsigned int max_payload) + const struct s3fwrn5_phy_ops *phy_ops, unsigned int max_payload) { struct s3fwrn5_info *info; int ret; diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index c61d8a308da45..3ed0adf6479b0 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -125,7 +125,7 @@ static int s3fwrn5_i2c_write(void *phy_id, struct sk_buff *skb) return 0; } -static struct s3fwrn5_phy_ops i2c_phy_ops = { +static const struct s3fwrn5_phy_ops i2c_phy_ops = { .set_wake = s3fwrn5_i2c_set_wake, .set_mode = s3fwrn5_i2c_set_mode, .get_mode = s3fwrn5_i2c_get_mode, diff --git a/drivers/nfc/s3fwrn5/s3fwrn5.h b/drivers/nfc/s3fwrn5/s3fwrn5.h index 89210d4828b87..7d5e516036fb2 100644 --- a/drivers/nfc/s3fwrn5/s3fwrn5.h +++ b/drivers/nfc/s3fwrn5/s3fwrn5.h @@ -44,7 +44,7 @@ struct s3fwrn5_info { void *phy_id; struct device *pdev; - struct s3fwrn5_phy_ops *phy_ops; + const struct s3fwrn5_phy_ops *phy_ops; unsigned int max_payload; struct s3fwrn5_fw_info fw_info; @@ -90,7 +90,7 @@ static inline int s3fwrn5_write(struct s3fwrn5_info *info, struct sk_buff *skb) } int s3fwrn5_probe(struct nci_dev **ndev, void *phy_id, struct device *pdev, - struct s3fwrn5_phy_ops *phy_ops, unsigned int max_payload); + const struct s3fwrn5_phy_ops *phy_ops, unsigned int max_payload); void s3fwrn5_remove(struct nci_dev *ndev); int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb, diff --git a/drivers/nfc/st-nci/Kconfig b/drivers/nfc/st-nci/Kconfig index e7c6db9c58607..dc9b777d78f62 100644 --- a/drivers/nfc/st-nci/Kconfig +++ b/drivers/nfc/st-nci/Kconfig @@ -1,19 +1,14 @@ config NFC_ST_NCI - tristate "STMicroelectronics ST NCI NFC driver" - depends on NFC_NCI - default n + tristate ---help--- STMicroelectronics NFC NCI chips core driver. It implements the chipset NCI logic and hooks into the NFC kernel APIs. Physical layers will register against it. - To compile this driver as a module, choose m here. The module will - be called st-nci. - Say N if unsure. - config NFC_ST_NCI_I2C - tristate "NFC ST NCI i2c support" - depends on NFC_ST_NCI && I2C + tristate "STMicroelectronics ST NCI NFC driver (I2C)" + depends on NFC_NCI && I2C + select NFC_ST_NCI ---help--- This module adds support for an I2C interface to the STMicroelectronics NFC NCI chips familly. @@ -23,8 +18,9 @@ config NFC_ST_NCI_I2C Say N if unsure. config NFC_ST_NCI_SPI - tristate "NFC ST NCI spi support" - depends on NFC_ST_NCI && SPI + tristate "STMicroelectronics ST NCI NFC driver (SPI)" + depends on NFC_NCI && SPI + select NFC_ST_NCI ---help--- This module adds support for an SPI interface to the STMicroelectronics NFC NCI chips familly. diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index 15e3ce2d274c7..8a56b5c6e4c4e 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -20,8 +20,10 @@ #include <linux/module.h> #include <linux/i2c.h> #include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/of_irq.h> #include <linux/of_gpio.h> +#include <linux/acpi.h> #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/nfc.h> @@ -40,11 +42,7 @@ #define ST_NCI_I2C_DRIVER_NAME "st_nci_i2c" -static struct i2c_device_id st_nci_i2c_id_table[] = { - {ST_NCI_DRIVER_NAME, 0}, - {} -}; -MODULE_DEVICE_TABLE(i2c, st_nci_i2c_id_table); +#define ST_NCI_GPIO_NAME_RESET "clf_reset" struct st_nci_i2c_phy { struct i2c_client *i2c_dev; @@ -210,7 +208,43 @@ static struct nfc_phy_ops i2c_phy_ops = { .disable = st_nci_i2c_disable, }; -#ifdef CONFIG_OF +static int st_nci_i2c_acpi_request_resources(struct i2c_client *client) +{ + struct st_nci_i2c_phy *phy = i2c_get_clientdata(client); + const struct acpi_device_id *id; + struct gpio_desc *gpiod_reset; + struct device *dev; + + if (!client) + return -EINVAL; + + dev = &client->dev; + + /* Match the struct device against a given list of ACPI IDs */ + id = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!id) + return -ENODEV; + + /* Get RESET GPIO from ACPI */ + gpiod_reset = devm_gpiod_get_index(dev, ST_NCI_GPIO_NAME_RESET, 1, + GPIOD_OUT_HIGH); + if (IS_ERR(gpiod_reset)) { + nfc_err(dev, "Unable to get RESET GPIO\n"); + return -ENODEV; + } + + phy->gpio_reset = desc_to_gpio(gpiod_reset); + + phy->irq_polarity = irq_get_trigger_type(client->irq); + + phy->se_status.is_ese_present = + device_property_present(dev, "ese-present"); + phy->se_status.is_uicc_present = + device_property_present(dev, "uicc-present"); + + return 0; +} + static int st_nci_i2c_of_request_resources(struct i2c_client *client) { struct st_nci_i2c_phy *phy = i2c_get_clientdata(client); @@ -232,7 +266,7 @@ static int st_nci_i2c_of_request_resources(struct i2c_client *client) /* GPIO request and configuration */ r = devm_gpio_request_one(&client->dev, gpio, - GPIOF_OUT_INIT_HIGH, "clf_reset"); + GPIOF_OUT_INIT_HIGH, ST_NCI_GPIO_NAME_RESET); if (r) { nfc_err(&client->dev, "Failed to request reset pin\n"); return r; @@ -248,12 +282,6 @@ static int st_nci_i2c_of_request_resources(struct i2c_client *client) return 0; } -#else -static int st_nci_i2c_of_request_resources(struct i2c_client *client) -{ - return -ENODEV; -} -#endif static int st_nci_i2c_request_resources(struct i2c_client *client) { @@ -272,7 +300,8 @@ static int st_nci_i2c_request_resources(struct i2c_client *client) phy->irq_polarity = pdata->irq_polarity; r = devm_gpio_request_one(&client->dev, - phy->gpio_reset, GPIOF_OUT_INIT_HIGH, "clf_reset"); + phy->gpio_reset, GPIOF_OUT_INIT_HIGH, + ST_NCI_GPIO_NAME_RESET); if (r) { pr_err("%s : reset gpio_request failed\n", __FILE__); return r; @@ -322,6 +351,12 @@ static int st_nci_i2c_probe(struct i2c_client *client, "Cannot get platform resources\n"); return r; } + } else if (ACPI_HANDLE(&client->dev)) { + r = st_nci_i2c_acpi_request_resources(client); + if (r) { + nfc_err(&client->dev, "Cannot get ACPI data\n"); + return r; + } } else { nfc_err(&client->dev, "st_nci platform resources not available\n"); @@ -358,7 +393,19 @@ static int st_nci_i2c_remove(struct i2c_client *client) return 0; } -#ifdef CONFIG_OF +static struct i2c_device_id st_nci_i2c_id_table[] = { + {ST_NCI_DRIVER_NAME, 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, st_nci_i2c_id_table); + +static const struct acpi_device_id st_nci_i2c_acpi_match[] = { + {"SMO2101"}, + {"SMO2102"}, + {} +}; +MODULE_DEVICE_TABLE(acpi, st_nci_i2c_acpi_match); + static const struct of_device_id of_st_nci_i2c_match[] = { { .compatible = "st,st21nfcb-i2c", }, { .compatible = "st,st21nfcb_i2c", }, @@ -366,19 +413,18 @@ static const struct of_device_id of_st_nci_i2c_match[] = { {} }; MODULE_DEVICE_TABLE(of, of_st_nci_i2c_match); -#endif static struct i2c_driver st_nci_i2c_driver = { .driver = { .owner = THIS_MODULE, .name = ST_NCI_I2C_DRIVER_NAME, .of_match_table = of_match_ptr(of_st_nci_i2c_match), + .acpi_match_table = ACPI_PTR(st_nci_i2c_acpi_match), }, .probe = st_nci_i2c_probe, .id_table = st_nci_i2c_id_table, .remove = st_nci_i2c_remove, }; - module_i2c_driver(st_nci_i2c_driver); MODULE_LICENSE("GPL"); diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index 0884b11001ef0..50880d747b021 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -20,7 +20,6 @@ #include <net/nfc/nci_core.h> #include "st-nci.h" -#include "ndlc.h" #define NDLC_TIMER_T1 100 #define NDLC_TIMER_T1_WAIT 400 diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index dbab722a06546..a53e5df803eb2 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -331,7 +331,7 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, switch (event) { case ST_NCI_EVT_CONNECTIVITY: - + r = nfc_se_connectivity(ndev->nfc_dev, host); break; case ST_NCI_EVT_TRANSACTION: /* According to specification etsi 102 622 @@ -392,7 +392,6 @@ void st_nci_hci_event_received(struct nci_dev *ndev, u8 pipe, } EXPORT_SYMBOL_GPL(st_nci_hci_event_received); - void st_nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb) { diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c index d6519bb9dba51..821dfa950fa8f 100644 --- a/drivers/nfc/st-nci/spi.c +++ b/drivers/nfc/st-nci/spi.c @@ -20,8 +20,10 @@ #include <linux/module.h> #include <linux/spi/spi.h> #include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/of_irq.h> #include <linux/of_gpio.h> +#include <linux/acpi.h> #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/nfc.h> @@ -34,18 +36,14 @@ /* ndlc header */ #define ST_NCI_FRAME_HEADROOM 1 -#define ST_NCI_FRAME_TAILROOM 0 +#define ST_NCI_FRAME_TAILROOM 0 #define ST_NCI_SPI_MIN_SIZE 4 /* PCB(1) + NCI Packet header(3) */ #define ST_NCI_SPI_MAX_SIZE 250 /* req 4.2.1 */ #define ST_NCI_SPI_DRIVER_NAME "st_nci_spi" -static struct spi_device_id st_nci_spi_id_table[] = { - {ST_NCI_SPI_DRIVER_NAME, 0}, - {} -}; -MODULE_DEVICE_TABLE(spi, st_nci_spi_id_table); +#define ST_NCI_GPIO_NAME_RESET "clf_reset" struct st_nci_spi_phy { struct spi_device *spi_dev; @@ -225,7 +223,43 @@ static struct nfc_phy_ops spi_phy_ops = { .disable = st_nci_spi_disable, }; -#ifdef CONFIG_OF +static int st_nci_spi_acpi_request_resources(struct spi_device *spi_dev) +{ + struct st_nci_spi_phy *phy = spi_get_drvdata(spi_dev); + const struct acpi_device_id *id; + struct gpio_desc *gpiod_reset; + struct device *dev; + + if (!spi_dev) + return -EINVAL; + + dev = &spi_dev->dev; + + /* Match the struct device against a given list of ACPI IDs */ + id = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!id) + return -ENODEV; + + /* Get RESET GPIO from ACPI */ + gpiod_reset = devm_gpiod_get_index(dev, ST_NCI_GPIO_NAME_RESET, 1, + GPIOD_OUT_HIGH); + if (IS_ERR(gpiod_reset)) { + nfc_err(dev, "Unable to get RESET GPIO\n"); + return -ENODEV; + } + + phy->gpio_reset = desc_to_gpio(gpiod_reset); + + phy->irq_polarity = irq_get_trigger_type(spi_dev->irq); + + phy->se_status.is_ese_present = + device_property_present(dev, "ese-present"); + phy->se_status.is_uicc_present = + device_property_present(dev, "uicc-present"); + + return 0; +} + static int st_nci_spi_of_request_resources(struct spi_device *dev) { struct st_nci_spi_phy *phy = spi_get_drvdata(dev); @@ -247,7 +281,7 @@ static int st_nci_spi_of_request_resources(struct spi_device *dev) /* GPIO request and configuration */ r = devm_gpio_request_one(&dev->dev, gpio, - GPIOF_OUT_INIT_HIGH, "clf_reset"); + GPIOF_OUT_INIT_HIGH, ST_NCI_GPIO_NAME_RESET); if (r) { nfc_err(&dev->dev, "Failed to request reset pin\n"); return r; @@ -263,12 +297,6 @@ static int st_nci_spi_of_request_resources(struct spi_device *dev) return 0; } -#else -static int st_nci_spi_of_request_resources(struct spi_device *dev) -{ - return -ENODEV; -} -#endif static int st_nci_spi_request_resources(struct spi_device *dev) { @@ -287,7 +315,8 @@ static int st_nci_spi_request_resources(struct spi_device *dev) phy->irq_polarity = pdata->irq_polarity; r = devm_gpio_request_one(&dev->dev, - phy->gpio_reset, GPIOF_OUT_INIT_HIGH, "clf_reset"); + phy->gpio_reset, GPIOF_OUT_INIT_HIGH, + ST_NCI_GPIO_NAME_RESET); if (r) { pr_err("%s : reset gpio_request failed\n", __FILE__); return r; @@ -338,6 +367,12 @@ static int st_nci_spi_probe(struct spi_device *dev) "Cannot get platform resources\n"); return r; } + } else if (ACPI_HANDLE(&dev->dev)) { + r = st_nci_spi_acpi_request_resources(dev); + if (r) { + nfc_err(&dev->dev, "Cannot get ACPI data\n"); + return r; + } } else { nfc_err(&dev->dev, "st_nci platform resources not available\n"); @@ -374,24 +409,34 @@ static int st_nci_spi_remove(struct spi_device *dev) return 0; } -#ifdef CONFIG_OF +static struct spi_device_id st_nci_spi_id_table[] = { + {ST_NCI_SPI_DRIVER_NAME, 0}, + {} +}; +MODULE_DEVICE_TABLE(spi, st_nci_spi_id_table); + +static const struct acpi_device_id st_nci_spi_acpi_match[] = { + {"SMO2101", 0}, + {} +}; +MODULE_DEVICE_TABLE(acpi, st_nci_spi_acpi_match); + static const struct of_device_id of_st_nci_spi_match[] = { { .compatible = "st,st21nfcb-spi", }, {} }; MODULE_DEVICE_TABLE(of, of_st_nci_spi_match); -#endif static struct spi_driver st_nci_spi_driver = { .driver = { .name = ST_NCI_SPI_DRIVER_NAME, .of_match_table = of_match_ptr(of_st_nci_spi_match), + .acpi_match_table = ACPI_PTR(st_nci_spi_acpi_match), }, .probe = st_nci_spi_probe, .id_table = st_nci_spi_id_table, .remove = st_nci_spi_remove, }; - module_spi_driver(st_nci_spi_driver); MODULE_LICENSE("GPL"); diff --git a/drivers/nfc/st21nfca/Kconfig b/drivers/nfc/st21nfca/Kconfig index ee459f066ade8..cc3bd56589018 100644 --- a/drivers/nfc/st21nfca/Kconfig +++ b/drivers/nfc/st21nfca/Kconfig @@ -1,20 +1,15 @@ config NFC_ST21NFCA - tristate "STMicroelectronics ST21NFCA NFC driver" - depends on NFC_HCI + tristate select CRC_CCITT - default n ---help--- STMicroelectronics ST21NFCA core driver. It implements the chipset HCI logic and hooks into the NFC kernel APIs. Physical layers will register against it. - To compile this driver as a module, choose m here. The module will - be called st21nfca. - Say N if unsure. - config NFC_ST21NFCA_I2C - tristate "NFC ST21NFCA i2c support" - depends on NFC_ST21NFCA && I2C && NFC_SHDLC + tristate "STMicroelectronics ST21NFCA NFC driver (I2C)" + depends on NFC_HCI && I2C && NFC_SHDLC + select NFC_ST21NFCA ---help--- This module adds support for the STMicroelectronics st21nfca i2c interface. Select this if your platform is using the i2c bus. diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index a98da33e680a4..1f44a151d2061 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -21,8 +21,10 @@ #include <linux/module.h> #include <linux/i2c.h> #include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/of_irq.h> #include <linux/of_gpio.h> +#include <linux/acpi.h> #include <linux/miscdevice.h> #include <linux/interrupt.h> #include <linux/delay.h> @@ -60,12 +62,7 @@ #define ST21NFCA_HCI_I2C_DRIVER_NAME "st21nfca_hci_i2c" -static struct i2c_device_id st21nfca_hci_i2c_id_table[] = { - {ST21NFCA_HCI_DRIVER_NAME, 0}, - {} -}; - -MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table); +#define ST21NFCA_GPIO_NAME_EN "clf_enable" struct st21nfca_i2c_phy { struct i2c_client *i2c_dev; @@ -167,7 +164,6 @@ static void st21nfca_hci_i2c_disable(void *phy_id) { struct st21nfca_i2c_phy *phy = phy_id; - pr_info("\n"); gpio_set_value(phy->gpio_ena, 0); phy->powered = 0; @@ -210,7 +206,6 @@ static int st21nfca_hci_i2c_write(void *phy_id, struct sk_buff *skb) I2C_DUMP_SKB("st21nfca_hci_i2c_write", skb); - if (phy->hard_fault != 0) return phy->hard_fault; @@ -509,7 +504,41 @@ static struct nfc_phy_ops i2c_phy_ops = { .disable = st21nfca_hci_i2c_disable, }; -#ifdef CONFIG_OF +static int st21nfca_hci_i2c_acpi_request_resources(struct i2c_client *client) +{ + struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client); + const struct acpi_device_id *id; + struct gpio_desc *gpiod_ena; + struct device *dev; + + if (!client) + return -EINVAL; + + dev = &client->dev; + + /* Match the struct device against a given list of ACPI IDs */ + id = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!id) + return -ENODEV; + + /* Get EN GPIO from ACPI */ + gpiod_ena = devm_gpiod_get_index(dev, ST21NFCA_GPIO_NAME_EN, 1, + GPIOD_OUT_LOW); + if (!IS_ERR(gpiod_ena)) + phy->gpio_ena = desc_to_gpio(gpiod_ena); + + phy->gpio_ena = desc_to_gpio(gpiod_ena); + + phy->irq_polarity = irq_get_trigger_type(client->irq); + + phy->se_status.is_ese_present = + device_property_present(dev, "ese-present"); + phy->se_status.is_uicc_present = + device_property_present(dev, "uicc-present"); + + return 0; +} + static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client) { struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client); @@ -530,7 +559,7 @@ static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client) /* GPIO request and configuration */ r = devm_gpio_request_one(&client->dev, gpio, GPIOF_OUT_INIT_HIGH, - "clf_enable"); + ST21NFCA_GPIO_NAME_EN); if (r) { nfc_err(&client->dev, "Failed to request enable pin\n"); return r; @@ -547,12 +576,6 @@ static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client) return 0; } -#else -static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client) -{ - return -ENODEV; -} -#endif static int st21nfca_hci_i2c_request_resources(struct i2c_client *client) { @@ -572,7 +595,8 @@ static int st21nfca_hci_i2c_request_resources(struct i2c_client *client) if (phy->gpio_ena > 0) { r = devm_gpio_request_one(&client->dev, phy->gpio_ena, - GPIOF_OUT_INIT_HIGH, "clf_enable"); + GPIOF_OUT_INIT_HIGH, + ST21NFCA_GPIO_NAME_EN); if (r) { pr_err("%s : ena gpio_request failed\n", __FILE__); return r; @@ -628,6 +652,12 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client, nfc_err(&client->dev, "Cannot get platform resources\n"); return r; } + } else if (ACPI_HANDLE(&client->dev)) { + r = st21nfca_hci_i2c_acpi_request_resources(client); + if (r) { + nfc_err(&client->dev, "Cannot get ACPI data\n"); + return r; + } } else { nfc_err(&client->dev, "st21nfca platform resources not available\n"); return -ENODEV; @@ -670,26 +700,36 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client) return 0; } -#ifdef CONFIG_OF +static struct i2c_device_id st21nfca_hci_i2c_id_table[] = { + {ST21NFCA_HCI_DRIVER_NAME, 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table); + +static const struct acpi_device_id st21nfca_hci_i2c_acpi_match[] = { + {"SMO2100", 0}, + {} +}; +MODULE_DEVICE_TABLE(acpi, st21nfca_hci_i2c_acpi_match); + static const struct of_device_id of_st21nfca_i2c_match[] = { { .compatible = "st,st21nfca-i2c", }, { .compatible = "st,st21nfca_i2c", }, {} }; MODULE_DEVICE_TABLE(of, of_st21nfca_i2c_match); -#endif static struct i2c_driver st21nfca_hci_i2c_driver = { .driver = { .owner = THIS_MODULE, .name = ST21NFCA_HCI_I2C_DRIVER_NAME, .of_match_table = of_match_ptr(of_st21nfca_i2c_match), + .acpi_match_table = ACPI_PTR(st21nfca_hci_i2c_acpi_match), }, .probe = st21nfca_hci_i2c_probe, .id_table = st21nfca_hci_i2c_id_table, .remove = st21nfca_hci_i2c_remove, }; - module_i2c_driver(st21nfca_hci_i2c_driver); MODULE_LICENSE("GPL"); diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index c79d99b24c961..bd56a16e40073 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -312,7 +312,8 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, switch (event) { case ST21NFCA_EVT_CONNECTIVITY: - break; + r = nfc_se_connectivity(hdev->ndev, host); + break; case ST21NFCA_EVT_TRANSACTION: /* * According to specification etsi 102 622 @@ -342,7 +343,7 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, transaction->aid_len + 4, transaction->params_len); r = nfc_se_transaction(hdev->ndev, host, transaction); - break; + break; default: nfc_err(&hdev->ndev->dev, "Unexpected event on connectivity gate\n"); return 1; diff --git a/drivers/nfc/st95hf/Kconfig b/drivers/nfc/st95hf/Kconfig new file mode 100644 index 0000000000000..224f266fdcb6e --- /dev/null +++ b/drivers/nfc/st95hf/Kconfig @@ -0,0 +1,10 @@ +config NFC_ST95HF + tristate "ST95HF NFC Transceiver driver" + depends on SPI && NFC_DIGITAL + help + This enables the ST NFC driver for ST95HF NFC transceiver. + This makes use of SPI framework to communicate with transceiver + and registered with NFC digital core to support Linux NFC framework. + + Say Y here to compile support for ST NFC transceiver ST95HF + linux driver into the kernel or say M to compile it as module. diff --git a/drivers/nfc/st95hf/Makefile b/drivers/nfc/st95hf/Makefile new file mode 100644 index 0000000000000..00760b38ab7e8 --- /dev/null +++ b/drivers/nfc/st95hf/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for STMicroelectronics NFC transceiver ST95HF +# + +obj-$(CONFIG_NFC_ST95HF) += st95hf.o +st95hf-objs := spi.o core.o diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c new file mode 100644 index 0000000000000..c2840e4129624 --- /dev/null +++ b/drivers/nfc/st95hf/core.c @@ -0,0 +1,1273 @@ +/* + * -------------------------------------------------------------------- + * Driver for ST NFC Transceiver ST95HF + * -------------------------------------------------------------------- + * Copyright (C) 2015 STMicroelectronics Pvt. Ltd. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/nfc.h> +#include <linux/of_gpio.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/property.h> +#include <linux/regulator/consumer.h> +#include <linux/wait.h> +#include <net/nfc/digital.h> +#include <net/nfc/nfc.h> + +#include "spi.h" + +/* supported protocols */ +#define ST95HF_SUPPORTED_PROT (NFC_PROTO_ISO14443_MASK | \ + NFC_PROTO_ISO14443_B_MASK | \ + NFC_PROTO_ISO15693_MASK) +/* driver capabilities */ +#define ST95HF_CAPABILITIES NFC_DIGITAL_DRV_CAPS_IN_CRC + +/* Command Send Interface */ +/* ST95HF_COMMAND_SEND CMD Ids */ +#define ECHO_CMD 0x55 +#define WRITE_REGISTER_CMD 0x9 +#define PROTOCOL_SELECT_CMD 0x2 +#define SEND_RECEIVE_CMD 0x4 + +/* Select protocol codes */ +#define ISO15693_PROTOCOL_CODE 0x1 +#define ISO14443A_PROTOCOL_CODE 0x2 +#define ISO14443B_PROTOCOL_CODE 0x3 + +/* + * head room len is 3 + * 1 byte for control byte + * 1 byte for cmd + * 1 byte for size + */ +#define ST95HF_HEADROOM_LEN 3 + +/* + * tailroom is 1 for ISO14443A + * and 0 for ISO14443B/ISO15693, + * hence the max value 1 should be + * taken. + */ +#define ST95HF_TAILROOM_LEN 1 + +/* Command Response interface */ +#define MAX_RESPONSE_BUFFER_SIZE 280 +#define ECHORESPONSE 0x55 +#define ST95HF_ERR_MASK 0xF +#define ST95HF_TIMEOUT_ERROR 0x87 +#define ST95HF_NFCA_CRC_ERR_MASK 0x20 +#define ST95HF_NFCB_CRC_ERR_MASK 0x01 + +/* ST95HF transmission flag values */ +#define TRFLAG_NFCA_SHORT_FRAME 0x07 +#define TRFLAG_NFCA_STD_FRAME 0x08 +#define TRFLAG_NFCA_STD_FRAME_CRC 0x28 + +/* Misc defs */ +#define HIGH 1 +#define LOW 0 +#define ISO14443A_RATS_REQ 0xE0 +#define RATS_TB1_PRESENT_MASK 0x20 +#define RATS_TA1_PRESENT_MASK 0x10 +#define TB1_FWI_MASK 0xF0 +#define WTX_REQ_FROM_TAG 0xF2 + +#define MAX_CMD_LEN 0x7 + +#define MAX_CMD_PARAMS 4 +struct cmd { + int cmd_len; + unsigned char cmd_id; + unsigned char no_cmd_params; + unsigned char cmd_params[MAX_CMD_PARAMS]; + enum req_type req; +}; + +struct param_list { + int param_offset; + int new_param_val; +}; + +/* + * List of top-level cmds to be used internally by the driver. + * All these commands are build on top of ST95HF basic commands + * such as SEND_RECEIVE_CMD, PROTOCOL_SELECT_CMD, etc. + * These top level cmds are used internally while implementing various ops of + * digital layer/driver probe or extending the digital framework layer for + * features that are not yet implemented there, for example, WTX cmd handling. + */ +enum st95hf_cmd_list { + CMD_ECHO, + CMD_ISO14443A_CONFIG, + CMD_ISO14443A_DEMOGAIN, + CMD_ISO14443B_DEMOGAIN, + CMD_ISO14443A_PROTOCOL_SELECT, + CMD_ISO14443B_PROTOCOL_SELECT, + CMD_WTX_RESPONSE, + CMD_FIELD_OFF, + CMD_ISO15693_PROTOCOL_SELECT, +}; + +static const struct cmd cmd_array[] = { + [CMD_ECHO] = { + .cmd_len = 0x2, + .cmd_id = ECHO_CMD, + .no_cmd_params = 0, + .req = SYNC, + }, + [CMD_ISO14443A_CONFIG] = { + .cmd_len = 0x7, + .cmd_id = WRITE_REGISTER_CMD, + .no_cmd_params = 0x4, + .cmd_params = {0x3A, 0x00, 0x5A, 0x04}, + .req = SYNC, + }, + [CMD_ISO14443A_DEMOGAIN] = { + .cmd_len = 0x7, + .cmd_id = WRITE_REGISTER_CMD, + .no_cmd_params = 0x4, + .cmd_params = {0x68, 0x01, 0x01, 0xDF}, + .req = SYNC, + }, + [CMD_ISO14443B_DEMOGAIN] = { + .cmd_len = 0x7, + .cmd_id = WRITE_REGISTER_CMD, + .no_cmd_params = 0x4, + .cmd_params = {0x68, 0x01, 0x01, 0x51}, + .req = SYNC, + }, + [CMD_ISO14443A_PROTOCOL_SELECT] = { + .cmd_len = 0x7, + .cmd_id = PROTOCOL_SELECT_CMD, + .no_cmd_params = 0x4, + .cmd_params = {ISO14443A_PROTOCOL_CODE, 0x00, 0x01, 0xA0}, + .req = SYNC, + }, + [CMD_ISO14443B_PROTOCOL_SELECT] = { + .cmd_len = 0x7, + .cmd_id = PROTOCOL_SELECT_CMD, + .no_cmd_params = 0x4, + .cmd_params = {ISO14443B_PROTOCOL_CODE, 0x01, 0x03, 0xFF}, + .req = SYNC, + }, + [CMD_WTX_RESPONSE] = { + .cmd_len = 0x6, + .cmd_id = SEND_RECEIVE_CMD, + .no_cmd_params = 0x3, + .cmd_params = {0xF2, 0x00, TRFLAG_NFCA_STD_FRAME_CRC}, + .req = ASYNC, + }, + [CMD_FIELD_OFF] = { + .cmd_len = 0x5, + .cmd_id = PROTOCOL_SELECT_CMD, + .no_cmd_params = 0x2, + .cmd_params = {0x0, 0x0}, + .req = SYNC, + }, + [CMD_ISO15693_PROTOCOL_SELECT] = { + .cmd_len = 0x5, + .cmd_id = PROTOCOL_SELECT_CMD, + .no_cmd_params = 0x2, + .cmd_params = {ISO15693_PROTOCOL_CODE, 0x0D}, + .req = SYNC, + }, +}; + +/* st95_digital_cmd_complete_arg stores client context */ +struct st95_digital_cmd_complete_arg { + struct sk_buff *skb_resp; + nfc_digital_cmd_complete_t complete_cb; + void *cb_usrarg; + bool rats; +}; + +/* + * structure containing ST95HF driver specific data. + * @spicontext: structure containing information required + * for spi communication between st95hf and host. + * @ddev: nfc digital device object. + * @nfcdev: nfc device object. + * @enable_gpio: gpio used to enable st95hf transceiver. + * @complete_cb_arg: structure to store various context information + * that is passed from nfc requesting thread to the threaded ISR. + * @st95hf_supply: regulator "consumer" for NFC device. + * @sendrcv_trflag: last byte of frame send by sendrecv command + * of st95hf. This byte contains transmission flag info. + * @exchange_lock: semaphore used for signaling the st95hf_remove + * function that the last outstanding async nfc request is finished. + * @rm_lock: mutex for ensuring safe access of nfc digital object + * from threaded ISR. Usage of this mutex avoids any race between + * deletion of the object from st95hf_remove() and its access from + * the threaded ISR. + * @nfcdev_free: flag to have the state of nfc device object. + * [alive | died] + * @current_protocol: current nfc protocol. + * @current_rf_tech: current rf technology. + * @fwi: frame waiting index, received in reply of RATS according to + * digital protocol. + */ +struct st95hf_context { + struct st95hf_spi_context spicontext; + struct nfc_digital_dev *ddev; + struct nfc_dev *nfcdev; + unsigned int enable_gpio; + struct st95_digital_cmd_complete_arg complete_cb_arg; + struct regulator *st95hf_supply; + unsigned char sendrcv_trflag; + struct semaphore exchange_lock; + struct mutex rm_lock; + bool nfcdev_free; + u8 current_protocol; + u8 current_rf_tech; + int fwi; +}; + +/* + * st95hf_send_recv_cmd() is for sending commands to ST95HF + * that are described in the cmd_array[]. It can optionally + * receive the response if the cmd request is of type + * SYNC. For that to happen caller must pass true to recv_res. + * For ASYNC request, recv_res is ignored and the + * function will never try to receive the response on behalf + * of the caller. + */ +static int st95hf_send_recv_cmd(struct st95hf_context *st95context, + enum st95hf_cmd_list cmd, + int no_modif, + struct param_list *list_array, + bool recv_res) +{ + unsigned char spi_cmd_buffer[MAX_CMD_LEN]; + int i, ret; + struct device *dev = &st95context->spicontext.spidev->dev; + + if (cmd_array[cmd].cmd_len > MAX_CMD_LEN) + return -EINVAL; + if (cmd_array[cmd].no_cmd_params < no_modif) + return -EINVAL; + if (no_modif && !list_array) + return -EINVAL; + + spi_cmd_buffer[0] = ST95HF_COMMAND_SEND; + spi_cmd_buffer[1] = cmd_array[cmd].cmd_id; + spi_cmd_buffer[2] = cmd_array[cmd].no_cmd_params; + + memcpy(&spi_cmd_buffer[3], cmd_array[cmd].cmd_params, + spi_cmd_buffer[2]); + + for (i = 0; i < no_modif; i++) { + if (list_array[i].param_offset >= cmd_array[cmd].no_cmd_params) + return -EINVAL; + spi_cmd_buffer[3 + list_array[i].param_offset] = + list_array[i].new_param_val; + } + + ret = st95hf_spi_send(&st95context->spicontext, + spi_cmd_buffer, + cmd_array[cmd].cmd_len, + cmd_array[cmd].req); + if (ret) { + dev_err(dev, "st95hf_spi_send failed with error %d\n", ret); + return ret; + } + + if (cmd_array[cmd].req == SYNC && recv_res) { + unsigned char st95hf_response_arr[2]; + + ret = st95hf_spi_recv_response(&st95context->spicontext, + st95hf_response_arr); + if (ret < 0) { + dev_err(dev, "spi error from st95hf_spi_recv_response(), err = 0x%x\n", + ret); + return ret; + } + + if (st95hf_response_arr[0]) { + dev_err(dev, "st95hf error from st95hf_spi_recv_response(), err = 0x%x\n", + st95hf_response_arr[0]); + return -EIO; + } + } + + return 0; +} + +static int st95hf_echo_command(struct st95hf_context *st95context) +{ + int result = 0; + unsigned char echo_response; + + result = st95hf_send_recv_cmd(st95context, CMD_ECHO, 0, NULL, false); + if (result) + return result; + + /* If control reached here, response can be taken */ + result = st95hf_spi_recv_echo_res(&st95context->spicontext, + &echo_response); + if (result) { + dev_err(&st95context->spicontext.spidev->dev, + "err: echo response receieve error = 0x%x\n", result); + return result; + } + + if (echo_response == ECHORESPONSE) + return 0; + + dev_err(&st95context->spicontext.spidev->dev, "err: echo res is 0x%x\n", + echo_response); + + return -EIO; +} + +static int secondary_configuration_type4a(struct st95hf_context *stcontext) +{ + int result = 0; + struct device *dev = &stcontext->nfcdev->dev; + + /* 14443A config setting after select protocol */ + result = st95hf_send_recv_cmd(stcontext, + CMD_ISO14443A_CONFIG, + 0, + NULL, + true); + if (result) { + dev_err(dev, "type a config cmd, err = 0x%x\n", result); + return result; + } + + /* 14443A demo gain setting */ + result = st95hf_send_recv_cmd(stcontext, + CMD_ISO14443A_DEMOGAIN, + 0, + NULL, + true); + if (result) + dev_err(dev, "type a demogain cmd, err = 0x%x\n", result); + + return result; +} + +static int secondary_configuration_type4b(struct st95hf_context *stcontext) +{ + int result = 0; + struct device *dev = &stcontext->nfcdev->dev; + + result = st95hf_send_recv_cmd(stcontext, + CMD_ISO14443B_DEMOGAIN, + 0, + NULL, + true); + if (result) + dev_err(dev, "type b demogain cmd, err = 0x%x\n", result); + + return result; +} + +static int st95hf_select_protocol(struct st95hf_context *stcontext, int type) +{ + int result = 0; + struct device *dev; + + dev = &stcontext->nfcdev->dev; + + switch (type) { + case NFC_DIGITAL_RF_TECH_106A: + stcontext->current_rf_tech = NFC_DIGITAL_RF_TECH_106A; + result = st95hf_send_recv_cmd(stcontext, + CMD_ISO14443A_PROTOCOL_SELECT, + 0, + NULL, + true); + if (result) { + dev_err(dev, "protocol sel, err = 0x%x\n", + result); + return result; + } + + /* secondary config. for 14443Type 4A after protocol select */ + result = secondary_configuration_type4a(stcontext); + if (result) { + dev_err(dev, "type a secondary config, err = 0x%x\n", + result); + return result; + } + break; + case NFC_DIGITAL_RF_TECH_106B: + stcontext->current_rf_tech = NFC_DIGITAL_RF_TECH_106B; + result = st95hf_send_recv_cmd(stcontext, + CMD_ISO14443B_PROTOCOL_SELECT, + 0, + NULL, + true); + if (result) { + dev_err(dev, "protocol sel send, err = 0x%x\n", + result); + return result; + } + + /* + * delay of 5-6 ms is required after select protocol + * command in case of ISO14443 Type B + */ + usleep_range(50000, 60000); + + /* secondary config. for 14443Type 4B after protocol select */ + result = secondary_configuration_type4b(stcontext); + if (result) { + dev_err(dev, "type b secondary config, err = 0x%x\n", + result); + return result; + } + break; + case NFC_DIGITAL_RF_TECH_ISO15693: + stcontext->current_rf_tech = NFC_DIGITAL_RF_TECH_ISO15693; + result = st95hf_send_recv_cmd(stcontext, + CMD_ISO15693_PROTOCOL_SELECT, + 0, + NULL, + true); + if (result) { + dev_err(dev, "protocol sel send, err = 0x%x\n", + result); + return result; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +static void st95hf_send_st95enable_negativepulse(struct st95hf_context *st95con) +{ + /* First make irq_in pin high */ + gpio_set_value(st95con->enable_gpio, HIGH); + + /* wait for 1 milisecond */ + usleep_range(1000, 2000); + + /* Make irq_in pin low */ + gpio_set_value(st95con->enable_gpio, LOW); + + /* wait for minimum interrupt pulse to make st95 active */ + usleep_range(1000, 2000); + + /* At end make it high */ + gpio_set_value(st95con->enable_gpio, HIGH); +} + +/* + * Send a reset sequence over SPI bus (Reset command + wait 3ms + + * negative pulse on st95hf enable gpio + */ +static int st95hf_send_spi_reset_sequence(struct st95hf_context *st95context) +{ + int result = 0; + unsigned char reset_cmd = ST95HF_COMMAND_RESET; + + result = st95hf_spi_send(&st95context->spicontext, + &reset_cmd, + ST95HF_RESET_CMD_LEN, + ASYNC); + if (result) { + dev_err(&st95context->spicontext.spidev->dev, + "spi reset sequence cmd error = %d", result); + return result; + } + + /* wait for 3 milisecond to complete the controller reset process */ + usleep_range(3000, 4000); + + /* send negative pulse to make st95hf active */ + st95hf_send_st95enable_negativepulse(st95context); + + /* wait for 10 milisecond : HFO setup time */ + usleep_range(10000, 20000); + + return result; +} + +static int st95hf_por_sequence(struct st95hf_context *st95context) +{ + int nth_attempt = 1; + int result; + + st95hf_send_st95enable_negativepulse(st95context); + + usleep_range(5000, 6000); + do { + /* send an ECHO command and checks ST95HF response */ + result = st95hf_echo_command(st95context); + + dev_dbg(&st95context->spicontext.spidev->dev, + "response from echo function = 0x%x, attempt = %d\n", + result, nth_attempt); + + if (!result) + return 0; + + /* send an pulse on IRQ in case of the chip is on sleep state */ + if (nth_attempt == 2) + st95hf_send_st95enable_negativepulse(st95context); + else + st95hf_send_spi_reset_sequence(st95context); + + /* delay of 50 milisecond */ + usleep_range(50000, 51000); + } while (nth_attempt++ < 3); + + return -ETIMEDOUT; +} + +static int iso14443_config_fdt(struct st95hf_context *st95context, int wtxm) +{ + int result = 0; + struct device *dev = &st95context->spicontext.spidev->dev; + struct nfc_digital_dev *nfcddev = st95context->ddev; + unsigned char pp_typeb; + struct param_list new_params[2]; + + pp_typeb = cmd_array[CMD_ISO14443B_PROTOCOL_SELECT].cmd_params[2]; + + if (nfcddev->curr_protocol == NFC_PROTO_ISO14443 && + st95context->fwi < 4) + st95context->fwi = 4; + + new_params[0].param_offset = 2; + if (nfcddev->curr_protocol == NFC_PROTO_ISO14443) + new_params[0].new_param_val = st95context->fwi; + else if (nfcddev->curr_protocol == NFC_PROTO_ISO14443_B) + new_params[0].new_param_val = pp_typeb; + + new_params[1].param_offset = 3; + new_params[1].new_param_val = wtxm; + + switch (nfcddev->curr_protocol) { + case NFC_PROTO_ISO14443: + result = st95hf_send_recv_cmd(st95context, + CMD_ISO14443A_PROTOCOL_SELECT, + 2, + new_params, + true); + if (result) { + dev_err(dev, "WTX type a sel proto, err = 0x%x\n", + result); + return result; + } + + /* secondary config. for 14443Type 4A after protocol select */ + result = secondary_configuration_type4a(st95context); + if (result) { + dev_err(dev, "WTX type a second. config, err = 0x%x\n", + result); + return result; + } + break; + case NFC_PROTO_ISO14443_B: + result = st95hf_send_recv_cmd(st95context, + CMD_ISO14443B_PROTOCOL_SELECT, + 2, + new_params, + true); + if (result) { + dev_err(dev, "WTX type b sel proto, err = 0x%x\n", + result); + return result; + } + + /* secondary config. for 14443Type 4B after protocol select */ + result = secondary_configuration_type4b(st95context); + if (result) { + dev_err(dev, "WTX type b second. config, err = 0x%x\n", + result); + return result; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +static int st95hf_handle_wtx(struct st95hf_context *stcontext, + bool new_wtx, + int wtx_val) +{ + int result = 0; + unsigned char val_mm = 0; + struct param_list new_params[1]; + struct nfc_digital_dev *nfcddev = stcontext->ddev; + struct device *dev = &stcontext->nfcdev->dev; + + if (new_wtx) { + result = iso14443_config_fdt(stcontext, wtx_val & 0x3f); + if (result) { + dev_err(dev, "Config. setting error on WTX req, err = 0x%x\n", + result); + return result; + } + + /* Send response of wtx with ASYNC as no response expected */ + new_params[0].param_offset = 1; + new_params[0].new_param_val = wtx_val; + + result = st95hf_send_recv_cmd(stcontext, + CMD_WTX_RESPONSE, + 1, + new_params, + false); + if (result) + dev_err(dev, "WTX response send, err = 0x%x\n", result); + return result; + } + + /* if no new wtx, cofigure with default values */ + if (nfcddev->curr_protocol == NFC_PROTO_ISO14443) + val_mm = cmd_array[CMD_ISO14443A_PROTOCOL_SELECT].cmd_params[3]; + else if (nfcddev->curr_protocol == NFC_PROTO_ISO14443_B) + val_mm = cmd_array[CMD_ISO14443B_PROTOCOL_SELECT].cmd_params[3]; + + result = iso14443_config_fdt(stcontext, val_mm); + if (result) + dev_err(dev, "Default config. setting error after WTX processing, err = 0x%x\n", + result); + + return result; +} + +static int st95hf_error_handling(struct st95hf_context *stcontext, + struct sk_buff *skb_resp, + int res_len) +{ + int result = 0; + unsigned char error_byte; + struct device *dev = &stcontext->nfcdev->dev; + + /* First check ST95HF specific error */ + if (skb_resp->data[0] & ST95HF_ERR_MASK) { + if (skb_resp->data[0] == ST95HF_TIMEOUT_ERROR) + result = -ETIMEDOUT; + else + result = -EIO; + return result; + } + + /* Check for CRC err only if CRC is present in the tag response */ + switch (stcontext->current_rf_tech) { + case NFC_DIGITAL_RF_TECH_106A: + if (stcontext->sendrcv_trflag == TRFLAG_NFCA_STD_FRAME_CRC) { + error_byte = skb_resp->data[res_len - 3]; + if (error_byte & ST95HF_NFCA_CRC_ERR_MASK) { + /* CRC error occurred */ + dev_err(dev, "CRC error, byte received = 0x%x\n", + error_byte); + result = -EIO; + } + } + break; + case NFC_DIGITAL_RF_TECH_106B: + case NFC_DIGITAL_RF_TECH_ISO15693: + error_byte = skb_resp->data[res_len - 1]; + if (error_byte & ST95HF_NFCB_CRC_ERR_MASK) { + /* CRC error occurred */ + dev_err(dev, "CRC error, byte received = 0x%x\n", + error_byte); + result = -EIO; + } + break; + } + + return result; +} + +static int st95hf_response_handler(struct st95hf_context *stcontext, + struct sk_buff *skb_resp, + int res_len) +{ + int result = 0; + int skb_len; + unsigned char val_mm; + struct nfc_digital_dev *nfcddev = stcontext->ddev; + struct device *dev = &stcontext->nfcdev->dev; + struct st95_digital_cmd_complete_arg *cb_arg; + + cb_arg = &stcontext->complete_cb_arg; + + /* Process the response */ + skb_put(skb_resp, res_len); + + /* Remove st95 header */ + skb_pull(skb_resp, 2); + + skb_len = skb_resp->len; + + /* check if it is case of RATS request reply & FWI is present */ + if (nfcddev->curr_protocol == NFC_PROTO_ISO14443 && cb_arg->rats && + (skb_resp->data[1] & RATS_TB1_PRESENT_MASK)) { + if (skb_resp->data[1] & RATS_TA1_PRESENT_MASK) + stcontext->fwi = + (skb_resp->data[3] & TB1_FWI_MASK) >> 4; + else + stcontext->fwi = + (skb_resp->data[2] & TB1_FWI_MASK) >> 4; + + val_mm = cmd_array[CMD_ISO14443A_PROTOCOL_SELECT].cmd_params[3]; + + result = iso14443_config_fdt(stcontext, val_mm); + if (result) { + dev_err(dev, "error in config_fdt to handle fwi of ATS, error=%d\n", + result); + return result; + } + } + cb_arg->rats = false; + + /* Remove CRC bytes only if received frames data has an eod (CRC) */ + switch (stcontext->current_rf_tech) { + case NFC_DIGITAL_RF_TECH_106A: + if (stcontext->sendrcv_trflag == TRFLAG_NFCA_STD_FRAME_CRC) + skb_trim(skb_resp, (skb_len - 5)); + else + skb_trim(skb_resp, (skb_len - 3)); + break; + case NFC_DIGITAL_RF_TECH_106B: + case NFC_DIGITAL_RF_TECH_ISO15693: + skb_trim(skb_resp, (skb_len - 3)); + break; + } + + return result; +} + +static irqreturn_t st95hf_irq_handler(int irq, void *st95hfcontext) +{ + struct st95hf_context *stcontext = + (struct st95hf_context *)st95hfcontext; + + if (stcontext->spicontext.req_issync) { + complete(&stcontext->spicontext.done); + stcontext->spicontext.req_issync = false; + return IRQ_HANDLED; + } + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t st95hf_irq_thread_handler(int irq, void *st95hfcontext) +{ + int result = 0; + int res_len; + static bool wtx; + struct device *dev; + struct device *spidevice; + struct nfc_digital_dev *nfcddev; + struct sk_buff *skb_resp; + struct st95hf_context *stcontext = + (struct st95hf_context *)st95hfcontext; + struct st95_digital_cmd_complete_arg *cb_arg; + + spidevice = &stcontext->spicontext.spidev->dev; + + /* + * check semaphore, if not down() already, then we don't + * know in which context the ISR is called and surely it + * will be a bug. Note that down() of the semaphore is done + * in the corresponding st95hf_in_send_cmd() and then + * only this ISR should be called. ISR will up() the + * semaphore before leaving. Hence when the ISR is called + * the correct behaviour is down_trylock() should always + * return 1 (indicating semaphore cant be taken and hence no + * change in semaphore count). + * If not, then we up() the semaphore and crash on + * a BUG() ! + */ + if (!down_trylock(&stcontext->exchange_lock)) { + up(&stcontext->exchange_lock); + WARN(1, "unknown context in ST95HF ISR"); + return IRQ_NONE; + } + + cb_arg = &stcontext->complete_cb_arg; + skb_resp = cb_arg->skb_resp; + + mutex_lock(&stcontext->rm_lock); + res_len = st95hf_spi_recv_response(&stcontext->spicontext, + skb_resp->data); + if (res_len < 0) { + dev_err(spidevice, "TISR spi response err = 0x%x\n", res_len); + result = res_len; + goto end; + } + + /* if stcontext->nfcdev_free is true, it means remove already ran */ + if (stcontext->nfcdev_free) { + result = -ENODEV; + goto end; + } + + dev = &stcontext->nfcdev->dev; + nfcddev = stcontext->ddev; + if (skb_resp->data[2] == WTX_REQ_FROM_TAG) { + /* Request for new FWT from tag */ + result = st95hf_handle_wtx(stcontext, true, skb_resp->data[3]); + if (result) + goto end; + + wtx = true; + mutex_unlock(&stcontext->rm_lock); + return IRQ_HANDLED; + } + + result = st95hf_error_handling(stcontext, skb_resp, res_len); + if (result) + goto end; + + result = st95hf_response_handler(stcontext, skb_resp, res_len); + if (result) + goto end; + + /* + * If select protocol is done on wtx req. do select protocol + * again with default values + */ + if (wtx) { + wtx = false; + result = st95hf_handle_wtx(stcontext, false, 0); + if (result) + goto end; + } + + /* call digital layer callback */ + cb_arg->complete_cb(stcontext->ddev, cb_arg->cb_usrarg, skb_resp); + + /* up the semaphore before returning */ + up(&stcontext->exchange_lock); + mutex_unlock(&stcontext->rm_lock); + + return IRQ_HANDLED; + +end: + kfree_skb(skb_resp); + wtx = false; + cb_arg->rats = false; + skb_resp = ERR_PTR(result); + /* call of callback with error */ + cb_arg->complete_cb(stcontext->ddev, cb_arg->cb_usrarg, skb_resp); + /* up the semaphore before returning */ + up(&stcontext->exchange_lock); + mutex_unlock(&stcontext->rm_lock); + return IRQ_HANDLED; +} + +/* NFC ops functions definition */ +static int st95hf_in_configure_hw(struct nfc_digital_dev *ddev, + int type, + int param) +{ + struct st95hf_context *stcontext = nfc_digital_get_drvdata(ddev); + + if (type == NFC_DIGITAL_CONFIG_RF_TECH) + return st95hf_select_protocol(stcontext, param); + + if (type == NFC_DIGITAL_CONFIG_FRAMING) { + switch (param) { + case NFC_DIGITAL_FRAMING_NFCA_SHORT: + stcontext->sendrcv_trflag = TRFLAG_NFCA_SHORT_FRAME; + break; + case NFC_DIGITAL_FRAMING_NFCA_STANDARD: + stcontext->sendrcv_trflag = TRFLAG_NFCA_STD_FRAME; + break; + case NFC_DIGITAL_FRAMING_NFCA_T4T: + case NFC_DIGITAL_FRAMING_NFCA_NFC_DEP: + case NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A: + stcontext->sendrcv_trflag = TRFLAG_NFCA_STD_FRAME_CRC; + break; + case NFC_DIGITAL_FRAMING_NFCB: + case NFC_DIGITAL_FRAMING_ISO15693_INVENTORY: + case NFC_DIGITAL_FRAMING_ISO15693_T5T: + break; + } + } + + return 0; +} + +static int rf_off(struct st95hf_context *stcontext) +{ + int rc; + struct device *dev; + + dev = &stcontext->nfcdev->dev; + + rc = st95hf_send_recv_cmd(stcontext, CMD_FIELD_OFF, 0, NULL, true); + if (rc) + dev_err(dev, "protocol sel send field off, err = 0x%x\n", rc); + + return rc; +} + +static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev, + struct sk_buff *skb, + u16 timeout, + nfc_digital_cmd_complete_t cb, + void *arg) +{ + struct st95hf_context *stcontext = nfc_digital_get_drvdata(ddev); + int rc; + struct sk_buff *skb_resp; + int len_data_to_tag = 0; + + skb_resp = nfc_alloc_recv_skb(MAX_RESPONSE_BUFFER_SIZE, GFP_KERNEL); + if (!skb_resp) { + rc = -ENOMEM; + goto error; + } + + switch (stcontext->current_rf_tech) { + case NFC_DIGITAL_RF_TECH_106A: + len_data_to_tag = skb->len + 1; + *skb_put(skb, 1) = stcontext->sendrcv_trflag; + break; + case NFC_DIGITAL_RF_TECH_106B: + case NFC_DIGITAL_RF_TECH_ISO15693: + len_data_to_tag = skb->len; + break; + default: + rc = -EINVAL; + goto free_skb_resp; + } + + skb_push(skb, 3); + skb->data[0] = ST95HF_COMMAND_SEND; + skb->data[1] = SEND_RECEIVE_CMD; + skb->data[2] = len_data_to_tag; + + stcontext->complete_cb_arg.skb_resp = skb_resp; + stcontext->complete_cb_arg.cb_usrarg = arg; + stcontext->complete_cb_arg.complete_cb = cb; + + if ((skb->data[3] == ISO14443A_RATS_REQ) && + ddev->curr_protocol == NFC_PROTO_ISO14443) + stcontext->complete_cb_arg.rats = true; + + /* + * down the semaphore to indicate to remove func that an + * ISR is pending, note that it will not block here in any case. + * If found blocked, it is a BUG! + */ + rc = down_killable(&stcontext->exchange_lock); + if (rc) { + WARN(1, "Semaphore is not found up in st95hf_in_send_cmd\n"); + return rc; + } + + rc = st95hf_spi_send(&stcontext->spicontext, skb->data, + skb->len, + ASYNC); + if (rc) { + dev_err(&stcontext->nfcdev->dev, + "Error %d trying to perform data_exchange", rc); + /* up the semaphore since ISR will never come in this case */ + up(&stcontext->exchange_lock); + goto free_skb_resp; + } + + kfree_skb(skb); + + return rc; + +free_skb_resp: + kfree_skb(skb_resp); +error: + return rc; +} + +/* p2p will be supported in a later release ! */ +static int st95hf_tg_configure_hw(struct nfc_digital_dev *ddev, + int type, + int param) +{ + return 0; +} + +static int st95hf_tg_send_cmd(struct nfc_digital_dev *ddev, + struct sk_buff *skb, + u16 timeout, + nfc_digital_cmd_complete_t cb, + void *arg) +{ + return 0; +} + +static int st95hf_tg_listen(struct nfc_digital_dev *ddev, + u16 timeout, + nfc_digital_cmd_complete_t cb, + void *arg) +{ + return 0; +} + +static int st95hf_tg_get_rf_tech(struct nfc_digital_dev *ddev, u8 *rf_tech) +{ + return 0; +} + +static int st95hf_switch_rf(struct nfc_digital_dev *ddev, bool on) +{ + u8 rf_tech; + struct st95hf_context *stcontext = nfc_digital_get_drvdata(ddev); + + rf_tech = ddev->curr_rf_tech; + + if (on) + /* switch on RF field */ + return st95hf_select_protocol(stcontext, rf_tech); + + /* switch OFF RF field */ + return rf_off(stcontext); +} + +/* TODO st95hf_abort_cmd */ +static void st95hf_abort_cmd(struct nfc_digital_dev *ddev) +{ +} + +static struct nfc_digital_ops st95hf_nfc_digital_ops = { + .in_configure_hw = st95hf_in_configure_hw, + .in_send_cmd = st95hf_in_send_cmd, + + .tg_listen = st95hf_tg_listen, + .tg_configure_hw = st95hf_tg_configure_hw, + .tg_send_cmd = st95hf_tg_send_cmd, + .tg_get_rf_tech = st95hf_tg_get_rf_tech, + + .switch_rf = st95hf_switch_rf, + .abort_cmd = st95hf_abort_cmd, +}; + +static const struct spi_device_id st95hf_id[] = { + { "st95hf", 0 }, + {} +}; +MODULE_DEVICE_TABLE(spi, st95hf_id); + +static int st95hf_probe(struct spi_device *nfc_spi_dev) +{ + int ret; + + struct st95hf_context *st95context; + struct st95hf_spi_context *spicontext; + + nfc_info(&nfc_spi_dev->dev, "ST95HF driver probe called.\n"); + + st95context = devm_kzalloc(&nfc_spi_dev->dev, + sizeof(struct st95hf_context), + GFP_KERNEL); + if (!st95context) + return -ENOMEM; + + spicontext = &st95context->spicontext; + + spicontext->spidev = nfc_spi_dev; + + st95context->fwi = + cmd_array[CMD_ISO14443A_PROTOCOL_SELECT].cmd_params[2]; + + if (device_property_present(&nfc_spi_dev->dev, "st95hfvin")) { + st95context->st95hf_supply = + devm_regulator_get(&nfc_spi_dev->dev, + "st95hfvin"); + if (IS_ERR(st95context->st95hf_supply)) { + dev_err(&nfc_spi_dev->dev, "failed to acquire regulator\n"); + return PTR_ERR(st95context->st95hf_supply); + } + + ret = regulator_enable(st95context->st95hf_supply); + if (ret) { + dev_err(&nfc_spi_dev->dev, "failed to enable regulator\n"); + return ret; + } + } + + init_completion(&spicontext->done); + mutex_init(&spicontext->spi_lock); + + /* + * Store spicontext in spi device object for using it in + * remove function + */ + dev_set_drvdata(&nfc_spi_dev->dev, spicontext); + + st95context->enable_gpio = + of_get_named_gpio(nfc_spi_dev->dev.of_node, + "enable-gpio", + 0); + if (!gpio_is_valid(st95context->enable_gpio)) { + dev_err(&nfc_spi_dev->dev, "No valid enable gpio\n"); + ret = st95context->enable_gpio; + goto err_disable_regulator; + } + + ret = devm_gpio_request_one(&nfc_spi_dev->dev, st95context->enable_gpio, + GPIOF_DIR_OUT | GPIOF_INIT_HIGH, + "enable_gpio"); + if (ret) + goto err_disable_regulator; + + if (nfc_spi_dev->irq > 0) { + if (devm_request_threaded_irq(&nfc_spi_dev->dev, + nfc_spi_dev->irq, + st95hf_irq_handler, + st95hf_irq_thread_handler, + IRQF_TRIGGER_FALLING, + "st95hf", + (void *)st95context) < 0) { + dev_err(&nfc_spi_dev->dev, "err: irq request for st95hf is failed\n"); + ret = -EINVAL; + goto err_disable_regulator; + } + } else { + dev_err(&nfc_spi_dev->dev, "not a valid IRQ associated with ST95HF\n"); + ret = -EINVAL; + goto err_disable_regulator; + } + + /* + * First reset SPI to handle warm reset of the system. + * It will put the ST95HF device in Power ON state + * which make the state of device identical to state + * at the time of cold reset of the system. + */ + ret = st95hf_send_spi_reset_sequence(st95context); + if (ret) { + dev_err(&nfc_spi_dev->dev, "err: spi_reset_sequence failed\n"); + goto err_disable_regulator; + } + + /* call PowerOnReset sequence of ST95hf to activate it */ + ret = st95hf_por_sequence(st95context); + if (ret) { + dev_err(&nfc_spi_dev->dev, "err: por seq failed for st95hf\n"); + goto err_disable_regulator; + } + + /* create NFC dev object and register with NFC Subsystem */ + st95context->ddev = nfc_digital_allocate_device(&st95hf_nfc_digital_ops, + ST95HF_SUPPORTED_PROT, + ST95HF_CAPABILITIES, + ST95HF_HEADROOM_LEN, + ST95HF_TAILROOM_LEN); + if (!st95context->ddev) { + ret = -ENOMEM; + goto err_disable_regulator; + } + + st95context->nfcdev = st95context->ddev->nfc_dev; + nfc_digital_set_parent_dev(st95context->ddev, &nfc_spi_dev->dev); + + ret = nfc_digital_register_device(st95context->ddev); + if (ret) { + dev_err(&st95context->nfcdev->dev, "st95hf registration failed\n"); + goto err_free_digital_device; + } + + /* store st95context in nfc device object */ + nfc_digital_set_drvdata(st95context->ddev, st95context); + + sema_init(&st95context->exchange_lock, 1); + mutex_init(&st95context->rm_lock); + + return ret; + +err_free_digital_device: + nfc_digital_free_device(st95context->ddev); +err_disable_regulator: + if (st95context->st95hf_supply) + regulator_disable(st95context->st95hf_supply); + + return ret; +} + +static int st95hf_remove(struct spi_device *nfc_spi_dev) +{ + int result = 0; + unsigned char reset_cmd = ST95HF_COMMAND_RESET; + struct st95hf_spi_context *spictx = dev_get_drvdata(&nfc_spi_dev->dev); + + struct st95hf_context *stcontext = container_of(spictx, + struct st95hf_context, + spicontext); + + mutex_lock(&stcontext->rm_lock); + + nfc_digital_unregister_device(stcontext->ddev); + nfc_digital_free_device(stcontext->ddev); + stcontext->nfcdev_free = true; + + mutex_unlock(&stcontext->rm_lock); + + /* if last in_send_cmd's ISR is pending, wait for it to finish */ + result = down_killable(&stcontext->exchange_lock); + if (result == -EINTR) + dev_err(&spictx->spidev->dev, "sleep for semaphore interrupted by signal\n"); + + /* next reset the ST95HF controller */ + result = st95hf_spi_send(&stcontext->spicontext, + &reset_cmd, + ST95HF_RESET_CMD_LEN, + ASYNC); + if (result) { + dev_err(&spictx->spidev->dev, + "ST95HF reset failed in remove() err = %d\n", result); + return result; + } + + /* wait for 3 ms to complete the controller reset process */ + usleep_range(3000, 4000); + + /* disable regulator */ + if (stcontext->st95hf_supply) + regulator_disable(stcontext->st95hf_supply); + + return result; +} + +/* Register as SPI protocol driver */ +static struct spi_driver st95hf_driver = { + .driver = { + .name = "st95hf", + .owner = THIS_MODULE, + }, + .id_table = st95hf_id, + .probe = st95hf_probe, + .remove = st95hf_remove, +}; + +module_spi_driver(st95hf_driver); + +MODULE_AUTHOR("Shikha Singh <shikha.singh@st.com>"); +MODULE_DESCRIPTION("ST NFC Transceiver ST95HF driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/nfc/st95hf/spi.c b/drivers/nfc/st95hf/spi.c new file mode 100644 index 0000000000000..e2d3bbcc8c345 --- /dev/null +++ b/drivers/nfc/st95hf/spi.c @@ -0,0 +1,167 @@ +/* + * ---------------------------------------------------------------------------- + * drivers/nfc/st95hf/spi.c function definitions for SPI communication + * ---------------------------------------------------------------------------- + * Copyright (C) 2015 STMicroelectronics Pvt. Ltd. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "spi.h" + +/* Function to send user provided buffer to ST95HF through SPI */ +int st95hf_spi_send(struct st95hf_spi_context *spicontext, + unsigned char *buffertx, + int datalen, + enum req_type reqtype) +{ + struct spi_message m; + int result = 0; + struct spi_device *spidev = spicontext->spidev; + struct spi_transfer tx_transfer = { + .tx_buf = buffertx, + .len = datalen, + }; + + mutex_lock(&spicontext->spi_lock); + + if (reqtype == SYNC) { + spicontext->req_issync = true; + reinit_completion(&spicontext->done); + } else { + spicontext->req_issync = false; + } + + spi_message_init(&m); + spi_message_add_tail(&tx_transfer, &m); + + result = spi_sync(spidev, &m); + if (result) { + dev_err(&spidev->dev, "error: sending cmd to st95hf using SPI = %d\n", + result); + mutex_unlock(&spicontext->spi_lock); + return result; + } + + /* return for asynchronous or no-wait case */ + if (reqtype == ASYNC) { + mutex_unlock(&spicontext->spi_lock); + return 0; + } + + result = wait_for_completion_timeout(&spicontext->done, + msecs_to_jiffies(1000)); + /* check for timeout or success */ + if (!result) { + dev_err(&spidev->dev, "error: response not ready timeout\n"); + result = -ETIMEDOUT; + } else { + result = 0; + } + + mutex_unlock(&spicontext->spi_lock); + + return result; +} +EXPORT_SYMBOL_GPL(st95hf_spi_send); + +/* Function to Receive command Response */ +int st95hf_spi_recv_response(struct st95hf_spi_context *spicontext, + unsigned char *receivebuff) +{ + int len = 0; + struct spi_transfer tx_takedata; + struct spi_message m; + struct spi_device *spidev = spicontext->spidev; + unsigned char readdata_cmd = ST95HF_COMMAND_RECEIVE; + struct spi_transfer t[2] = { + {.tx_buf = &readdata_cmd, .len = 1,}, + {.rx_buf = receivebuff, .len = 2, .cs_change = 1,}, + }; + + int ret = 0; + + memset(&tx_takedata, 0x0, sizeof(struct spi_transfer)); + + mutex_lock(&spicontext->spi_lock); + + /* First spi transfer to know the length of valid data */ + spi_message_init(&m); + spi_message_add_tail(&t[0], &m); + spi_message_add_tail(&t[1], &m); + + ret = spi_sync(spidev, &m); + if (ret) { + dev_err(&spidev->dev, "spi_recv_resp, data length error = %d\n", + ret); + mutex_unlock(&spicontext->spi_lock); + return ret; + } + + /* As 2 bytes are already read */ + len = 2; + + /* Support of long frame */ + if (receivebuff[0] & 0x60) + len += (((receivebuff[0] & 0x60) >> 5) << 8) | receivebuff[1]; + else + len += receivebuff[1]; + + /* Now make a transfer to read only relevant bytes */ + tx_takedata.rx_buf = &receivebuff[2]; + tx_takedata.len = len - 2; + + spi_message_init(&m); + spi_message_add_tail(&tx_takedata, &m); + + ret = spi_sync(spidev, &m); + + mutex_unlock(&spicontext->spi_lock); + if (ret) { + dev_err(&spidev->dev, "spi_recv_resp, data read error = %d\n", + ret); + return ret; + } + + return len; +} +EXPORT_SYMBOL_GPL(st95hf_spi_recv_response); + +int st95hf_spi_recv_echo_res(struct st95hf_spi_context *spicontext, + unsigned char *receivebuff) +{ + unsigned char readdata_cmd = ST95HF_COMMAND_RECEIVE; + struct spi_transfer t[2] = { + {.tx_buf = &readdata_cmd, .len = 1,}, + {.rx_buf = receivebuff, .len = 1,}, + }; + struct spi_message m; + struct spi_device *spidev = spicontext->spidev; + int ret = 0; + + mutex_lock(&spicontext->spi_lock); + + spi_message_init(&m); + spi_message_add_tail(&t[0], &m); + spi_message_add_tail(&t[1], &m); + ret = spi_sync(spidev, &m); + + mutex_unlock(&spicontext->spi_lock); + + if (ret) + dev_err(&spidev->dev, "recv_echo_res, data read error = %d\n", + ret); + + return ret; +} +EXPORT_SYMBOL_GPL(st95hf_spi_recv_echo_res); diff --git a/drivers/nfc/st95hf/spi.h b/drivers/nfc/st95hf/spi.h new file mode 100644 index 0000000000000..552d220747cdc --- /dev/null +++ b/drivers/nfc/st95hf/spi.h @@ -0,0 +1,64 @@ +/* + * --------------------------------------------------------------------------- + * drivers/nfc/st95hf/spi.h functions declarations for SPI communication + * --------------------------------------------------------------------------- + * Copyright (C) 2015 STMicroelectronics – All Rights Reserved + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __LINUX_ST95HF_SPI_H +#define __LINUX_ST95HF_SPI_H + +#include <linux/spi/spi.h> + +/* Basic ST95HF SPI CMDs */ +#define ST95HF_COMMAND_SEND 0x0 +#define ST95HF_COMMAND_RESET 0x1 +#define ST95HF_COMMAND_RECEIVE 0x2 + +#define ST95HF_RESET_CMD_LEN 0x1 + +/* + * structure to contain st95hf spi communication specific information. + * @req_issync: true for synchronous calls. + * @spidev: st95hf spi device object. + * @done: completion structure to wait for st95hf response + * for synchronous calls. + * @spi_lock: mutex to allow only one spi transfer at a time. + */ +struct st95hf_spi_context { + bool req_issync; + struct spi_device *spidev; + struct completion done; + struct mutex spi_lock; +}; + +/* flag to differentiate synchronous & asynchronous spi request */ +enum req_type { + SYNC, + ASYNC, +}; + +int st95hf_spi_send(struct st95hf_spi_context *spicontext, + unsigned char *buffertx, + int datalen, + enum req_type reqtype); + +int st95hf_spi_recv_response(struct st95hf_spi_context *spicontext, + unsigned char *receivebuff); + +int st95hf_spi_recv_echo_res(struct st95hf_spi_context *spicontext, + unsigned char *receivebuff); + +#endif diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index f857feb2b573e..10842b7051b32 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -2139,7 +2139,7 @@ static int trf7970a_remove(struct spi_device *spi) #ifdef CONFIG_PM_SLEEP static int trf7970a_suspend(struct device *dev) { - struct spi_device *spi = container_of(dev, struct spi_device, dev); + struct spi_device *spi = to_spi_device(dev); struct trf7970a *trf = spi_get_drvdata(spi); dev_dbg(dev, "Suspend\n"); @@ -2155,7 +2155,7 @@ static int trf7970a_suspend(struct device *dev) static int trf7970a_resume(struct device *dev) { - struct spi_device *spi = container_of(dev, struct spi_device, dev); + struct spi_device *spi = to_spi_device(dev); struct trf7970a *trf = spi_get_drvdata(spi); int ret; @@ -2174,7 +2174,7 @@ static int trf7970a_resume(struct device *dev) #ifdef CONFIG_PM static int trf7970a_pm_runtime_suspend(struct device *dev) { - struct spi_device *spi = container_of(dev, struct spi_device, dev); + struct spi_device *spi = to_spi_device(dev); struct trf7970a *trf = spi_get_drvdata(spi); int ret; @@ -2191,7 +2191,7 @@ static int trf7970a_pm_runtime_suspend(struct device *dev) static int trf7970a_pm_runtime_resume(struct device *dev) { - struct spi_device *spi = container_of(dev, struct spi_device, dev); + struct spi_device *spi = to_spi_device(dev); struct trf7970a *trf = spi_get_drvdata(spi); int ret; diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index 06c3364102350..15f2acb4d5cd4 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -271,9 +271,9 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id) return 0; } -static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id) +static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_id *nvme_nvm_id; struct nvme_nvm_command c = {}; @@ -308,10 +308,10 @@ out: return ret; } -static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb, +static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb, nvm_l2p_update_fn *update_l2p, void *priv) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_command c = {}; u32 len = queue_max_hw_sectors(dev->admin_q) << 9; @@ -415,10 +415,10 @@ out: return ret; } -static int nvme_nvm_set_bb_tbl(struct request_queue *q, struct nvm_rq *rqd, +static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd, int type) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_command c = {}; int ret = 0; @@ -455,7 +455,7 @@ static void nvme_nvm_end_io(struct request *rq, int error) struct nvm_rq *rqd = rq->end_io_data; struct nvm_dev *dev = rqd->dev; - if (dev->mt->end_io(rqd, error)) + if (dev->mt && dev->mt->end_io(rqd, error)) pr_err("nvme: err status: %x result: %lx\n", rq->errors, (unsigned long)rq->special); @@ -463,8 +463,9 @@ static void nvme_nvm_end_io(struct request *rq, int error) blk_mq_free_request(rq); } -static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) +static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) { + struct request_queue *q = dev->q; struct nvme_ns *ns = q->queuedata; struct request *rq; struct bio *bio = rqd->bio; @@ -502,8 +503,9 @@ static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) return 0; } -static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd) +static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd) { + struct request_queue *q = dev->q; struct nvme_ns *ns = q->queuedata; struct nvme_nvm_command c = {}; @@ -515,9 +517,9 @@ static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd) return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0); } -static void *nvme_nvm_create_dma_pool(struct request_queue *q, char *name) +static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; return dma_pool_create(name, dev->dev, PAGE_SIZE, PAGE_SIZE, 0); @@ -530,7 +532,7 @@ static void nvme_nvm_destroy_dma_pool(void *pool) dma_pool_destroy(dma_pool); } -static void *nvme_nvm_dev_dma_alloc(struct request_queue *q, void *pool, +static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool, gfp_t mem_flags, dma_addr_t *dma_handler) { return dma_pool_alloc(pool, mem_flags, dma_handler); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9e294ff4e652a..0c67b57be83c4 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2540,8 +2540,17 @@ static void nvme_ns_remove(struct nvme_ns *ns) { bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue); - if (kill) + if (kill) { blk_set_queue_dying(ns->queue); + + /* + * The controller was shutdown first if we got here through + * device removal. The shutdown may requeue outstanding + * requests. These need to be aborted immediately so + * del_gendisk doesn't block indefinitely for their completion. + */ + blk_mq_abort_requeue_list(ns->queue); + } if (ns->disk->flags & GENHD_FL_UP) del_gendisk(ns->disk); if (kill || !blk_queue_dying(ns->queue)) { @@ -2977,6 +2986,15 @@ static void nvme_dev_remove(struct nvme_dev *dev) { struct nvme_ns *ns, *next; + if (nvme_io_incapable(dev)) { + /* + * If the device is not capable of IO (surprise hot-removal, + * for example), we need to quiesce prior to deleting the + * namespaces. This will end outstanding requests and prevent + * attempts to sync dirty data. + */ + nvme_dev_shutdown(dev); + } list_for_each_entry_safe(ns, next, &dev->namespaces, list) nvme_ns_remove(ns); } diff --git a/drivers/of/address.c b/drivers/of/address.c index cd53fe4a0c868..9582c5703b3c9 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -485,9 +485,10 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, int rone; u64 offset = OF_BAD_ADDR; - /* Normally, an absence of a "ranges" property means we are + /* + * Normally, an absence of a "ranges" property means we are * crossing a non-translatable boundary, and thus the addresses - * below the current not cannot be converted to CPU physical ones. + * below the current cannot be converted to CPU physical ones. * Unfortunately, while this is very clear in the spec, it's not * what Apple understood, and they do have things like /uni-n or * /ht nodes with no "ranges" property and a lot of perfectly diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index d2430298a309a..655f79db7899f 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/initrd.h> #include <linux/memblock.h> +#include <linux/mutex.h> #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_reserved_mem.h> @@ -436,6 +437,8 @@ static void *kernel_tree_alloc(u64 size, u64 align) return kzalloc(size, GFP_KERNEL); } +static DEFINE_MUTEX(of_fdt_unflatten_mutex); + /** * of_fdt_unflatten_tree - create tree of device_nodes from flat blob * @@ -447,7 +450,9 @@ static void *kernel_tree_alloc(u64 size, u64 align) void of_fdt_unflatten_tree(const unsigned long *blob, struct device_node **mynodes) { + mutex_lock(&of_fdt_unflatten_mutex); __unflatten_device_tree(blob, mynodes, &kernel_tree_alloc); + mutex_unlock(&of_fdt_unflatten_mutex); } EXPORT_SYMBOL_GPL(of_fdt_unflatten_tree); @@ -1041,7 +1046,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, bool nomap) { - pr_err("Reserved memory not supported, ignoring range 0x%pa - 0x%pa%s\n", + pr_err("Reserved memory not supported, ignoring range %pa - %pa%s\n", &base, &size, nomap ? " (nomap)" : ""); return -ENOSYS; } diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 902b89be72171..4fa916dffc919 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map); * Returns a pointer to the interrupt parent node, or NULL if the interrupt * parent could not be determined. */ -static struct device_node *of_irq_find_parent(struct device_node *child) +struct device_node *of_irq_find_parent(struct device_node *child) { struct device_node *p; const __be32 *parp; @@ -77,6 +77,7 @@ static struct device_node *of_irq_find_parent(struct device_node *child) return p; } +EXPORT_SYMBOL_GPL(of_irq_find_parent); /** * of_irq_parse_raw - Low level interrupt tree parsing diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index be77e75c587db..1a3556a9e9ea1 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -206,7 +206,13 @@ static int __init __rmem_cmp(const void *a, const void *b) { const struct reserved_mem *ra = a, *rb = b; - return ra->base - rb->base; + if (ra->base < rb->base) + return -1; + + if (ra->base > rb->base) + return 1; + + return 0; } static void __init __rmem_check_for_overlap(void) diff --git a/drivers/parisc/iommu-helpers.h b/drivers/parisc/iommu-helpers.h index 761e77bfce5d2..e56f1569f6c39 100644 --- a/drivers/parisc/iommu-helpers.h +++ b/drivers/parisc/iommu-helpers.h @@ -104,7 +104,11 @@ iommu_coalesce_chunks(struct ioc *ioc, struct device *dev, struct scatterlist *contig_sg; /* contig chunk head */ unsigned long dma_offset, dma_len; /* start/len of DMA stream */ unsigned int n_mappings = 0; - unsigned int max_seg_size = dma_get_max_seg_size(dev); + unsigned int max_seg_size = min(dma_get_max_seg_size(dev), + (unsigned)DMA_CHUNK_SIZE); + unsigned int max_seg_boundary = dma_get_seg_boundary(dev) + 1; + if (max_seg_boundary) /* check if the addition above didn't overflow */ + max_seg_size = min(max_seg_size, max_seg_boundary); while (nents > 0) { @@ -138,14 +142,11 @@ iommu_coalesce_chunks(struct ioc *ioc, struct device *dev, /* ** First make sure current dma stream won't - ** exceed DMA_CHUNK_SIZE if we coalesce the + ** exceed max_seg_size if we coalesce the ** next entry. */ - if(unlikely(ALIGN(dma_len + dma_offset + startsg->length, - IOVP_SIZE) > DMA_CHUNK_SIZE)) - break; - - if (startsg->length + dma_len > max_seg_size) + if (unlikely(ALIGN(dma_len + dma_offset + startsg->length, IOVP_SIZE) > + max_seg_size)) break; /* diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c index e5dda38bdde5e..99da549d5d06a 100644 --- a/drivers/pci/host/pcie-altera.c +++ b/drivers/pci/host/pcie-altera.c @@ -55,8 +55,10 @@ #define TLP_CFG_DW2(bus, devfn, offset) \ (((bus) << 24) | ((devfn) << 16) | (offset)) #define TLP_REQ_ID(bus, devfn) (((bus) << 8) | (devfn)) +#define TLP_COMP_STATUS(s) (((s) >> 12) & 7) #define TLP_HDR_SIZE 3 #define TLP_LOOP 500 +#define RP_DEVFN 0 #define INTX_NUM 4 @@ -166,34 +168,41 @@ static bool altera_pcie_valid_config(struct altera_pcie *pcie, static int tlp_read_packet(struct altera_pcie *pcie, u32 *value) { - u8 loop; + int i; bool sop = 0; u32 ctrl; u32 reg0, reg1; + u32 comp_status = 1; /* * Minimum 2 loops to read TLP headers and 1 loop to read data * payload. */ - for (loop = 0; loop < TLP_LOOP; loop++) { + for (i = 0; i < TLP_LOOP; i++) { ctrl = cra_readl(pcie, RP_RXCPL_STATUS); if ((ctrl & RP_RXCPL_SOP) || (ctrl & RP_RXCPL_EOP) || sop) { reg0 = cra_readl(pcie, RP_RXCPL_REG0); reg1 = cra_readl(pcie, RP_RXCPL_REG1); - if (ctrl & RP_RXCPL_SOP) + if (ctrl & RP_RXCPL_SOP) { sop = true; + comp_status = TLP_COMP_STATUS(reg1); + } if (ctrl & RP_RXCPL_EOP) { + if (comp_status) + return PCIBIOS_DEVICE_NOT_FOUND; + if (value) *value = reg0; + return PCIBIOS_SUCCESSFUL; } } udelay(5); } - return -ENOENT; + return PCIBIOS_DEVICE_NOT_FOUND; } static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers, @@ -233,7 +242,7 @@ static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn, else headers[0] = TLP_CFG_DW0(TLP_FMTTYPE_CFGRD1); - headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, devfn), + headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN), TLP_READ_TAG, byte_en); headers[2] = TLP_CFG_DW2(bus, devfn, where); @@ -253,7 +262,7 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn, else headers[0] = TLP_CFG_DW0(TLP_FMTTYPE_CFGWR1); - headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, devfn), + headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN), TLP_WRITE_TAG, byte_en); headers[2] = TLP_CFG_DW2(bus, devfn, where); @@ -458,7 +467,7 @@ static int altera_pcie_init_irq_domain(struct altera_pcie *pcie) struct device_node *node = dev->of_node; /* Setup INTx */ - pcie->irq_domain = irq_domain_add_linear(node, INTX_NUM, + pcie->irq_domain = irq_domain_add_linear(node, INTX_NUM + 1, &intx_domain_ops, pcie); if (!pcie->irq_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); diff --git a/drivers/pci/host/pcie-hisi.c b/drivers/pci/host/pcie-hisi.c index 163671a4f798d..77f7c669a1b9b 100644 --- a/drivers/pci/host/pcie-hisi.c +++ b/drivers/pci/host/pcie-hisi.c @@ -61,7 +61,9 @@ static int hisi_pcie_cfg_read(struct pcie_port *pp, int where, int size, *val = *(u8 __force *) walker; else if (size == 2) *val = *(u16 __force *) walker; - else if (size != 4) + else if (size == 4) + *val = reg_val; + else return PCIBIOS_BAD_REGISTER_NUMBER; return PCIBIOS_SUCCESSFUL; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 53e463244bb7e..7eaa4c87fec71 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -54,7 +54,7 @@ static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) struct irq_domain *domain; domain = pci_msi_get_domain(dev); - if (domain) + if (domain && irq_domain_is_hierarchy(domain)) return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); return arch_setup_msi_irqs(dev, nvec, type); @@ -65,7 +65,7 @@ static void pci_msi_teardown_msi_irqs(struct pci_dev *dev) struct irq_domain *domain; domain = pci_msi_get_domain(dev); - if (domain) + if (domain && irq_domain_is_hierarchy(domain)) pci_msi_domain_free_irqs(domain, dev); else arch_teardown_msi_irqs(dev); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 4446fcb5effd3..d7ffd66814bb5 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1146,9 +1146,21 @@ static int pci_pm_runtime_suspend(struct device *dev) pci_dev->state_saved = false; pci_dev->no_d3cold = false; error = pm->runtime_suspend(dev); - suspend_report_result(pm->runtime_suspend, error); - if (error) + if (error) { + /* + * -EBUSY and -EAGAIN is used to request the runtime PM core + * to schedule a new suspend, so log the event only with debug + * log level. + */ + if (error == -EBUSY || error == -EAGAIN) + dev_dbg(dev, "can't suspend now (%pf returned %d)\n", + pm->runtime_suspend, error); + else + dev_err(dev, "can't suspend (%pf returned %d)\n", + pm->runtime_suspend, error); + return error; + } if (!pci_dev->d3cold_allowed) pci_dev->no_d3cold = true; diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index 7eb5859dd035f..03cb3ea2d2c03 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -233,6 +233,7 @@ config PHY_SUN9I_USB tristate "Allwinner sun9i SoC USB PHY driver" depends on ARCH_SUNXI && HAS_IOMEM && OF depends on RESET_CONTROLLER + depends on USB_COMMON select GENERIC_PHY help Enable this to support the transceiver that is part of Allwinner diff --git a/drivers/phy/phy-bcm-cygnus-pcie.c b/drivers/phy/phy-bcm-cygnus-pcie.c index 7ad72b7d2b981..082c03f6438f7 100644 --- a/drivers/phy/phy-bcm-cygnus-pcie.c +++ b/drivers/phy/phy-bcm-cygnus-pcie.c @@ -128,6 +128,7 @@ static int cygnus_pcie_phy_probe(struct platform_device *pdev) struct phy_provider *provider; struct resource *res; unsigned cnt = 0; + int ret; if (of_get_child_count(node) == 0) { dev_err(dev, "PHY no child node\n"); @@ -154,24 +155,28 @@ static int cygnus_pcie_phy_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &id)) { dev_err(dev, "missing reg property for %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (id >= MAX_NUM_PHYS) { dev_err(dev, "invalid PHY id: %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (core->phys[id].phy) { dev_err(dev, "duplicated PHY id: %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } p = &core->phys[id]; p->phy = devm_phy_create(dev, child, &cygnus_pcie_phy_ops); if (IS_ERR(p->phy)) { dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(p->phy); + ret = PTR_ERR(p->phy); + goto put_child; } p->core = core; @@ -191,6 +196,9 @@ static int cygnus_pcie_phy_probe(struct platform_device *pdev) dev_dbg(dev, "registered %u PCIe PHY(s)\n", cnt); return 0; +put_child: + of_node_put(child); + return ret; } static const struct of_device_id cygnus_pcie_phy_match_table[] = { diff --git a/drivers/phy/phy-berlin-sata.c b/drivers/phy/phy-berlin-sata.c index 77a2e054fdea0..f84a33a1bdd93 100644 --- a/drivers/phy/phy-berlin-sata.c +++ b/drivers/phy/phy-berlin-sata.c @@ -195,7 +195,7 @@ static int phy_berlin_sata_probe(struct platform_device *pdev) struct phy_provider *phy_provider; struct phy_berlin_priv *priv; struct resource *res; - int i = 0; + int ret, i = 0; u32 phy_id; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -237,22 +237,27 @@ static int phy_berlin_sata_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &phy_id)) { dev_err(dev, "missing reg property in node %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (phy_id >= ARRAY_SIZE(phy_berlin_power_down_bits)) { dev_err(dev, "invalid reg in node %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } phy_desc = devm_kzalloc(dev, sizeof(*phy_desc), GFP_KERNEL); - if (!phy_desc) - return -ENOMEM; + if (!phy_desc) { + ret = -ENOMEM; + goto put_child; + } phy = devm_phy_create(dev, NULL, &phy_berlin_sata_ops); if (IS_ERR(phy)) { dev_err(dev, "failed to create PHY %d\n", phy_id); - return PTR_ERR(phy); + ret = PTR_ERR(phy); + goto put_child; } phy_desc->phy = phy; @@ -269,6 +274,9 @@ static int phy_berlin_sata_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, phy_berlin_sata_phy_xlate); return PTR_ERR_OR_ZERO(phy_provider); +put_child: + of_node_put(child); + return ret; } static const struct of_device_id phy_berlin_sata_of_match[] = { diff --git a/drivers/phy/phy-brcmstb-sata.c b/drivers/phy/phy-brcmstb-sata.c index 8a2cb16a1937d..cd9dba8205668 100644 --- a/drivers/phy/phy-brcmstb-sata.c +++ b/drivers/phy/phy-brcmstb-sata.c @@ -140,7 +140,7 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) struct brcm_sata_phy *priv; struct resource *res; struct phy_provider *provider; - int count = 0; + int ret, count = 0; if (of_get_child_count(dn) == 0) return -ENODEV; @@ -163,16 +163,19 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &id)) { dev_err(dev, "missing reg property in node %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (id >= MAX_PORTS) { dev_err(dev, "invalid reg: %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (priv->phys[id].phy) { dev_err(dev, "already registered port %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } port = &priv->phys[id]; @@ -182,7 +185,8 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) port->ssc_en = of_property_read_bool(child, "brcm,enable-ssc"); if (IS_ERR(port->phy)) { dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(port->phy); + ret = PTR_ERR(port->phy); + goto put_child; } phy_set_drvdata(port->phy, port); @@ -198,6 +202,9 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) dev_info(dev, "registered %d port(s)\n", count); return 0; +put_child: + of_node_put(child); + return ret; } static struct platform_driver brcm_sata_phy_driver = { diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index fc48fac003a62..8c7f27db6ad35 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -636,8 +636,9 @@ EXPORT_SYMBOL_GPL(devm_of_phy_get); * @np: node containing the phy * @index: index of the phy * - * Gets the phy using _of_phy_get(), and associates a device with it using - * devres. On driver detach, release function is invoked on the devres data, + * Gets the phy using _of_phy_get(), then gets a refcount to it, + * and associates a device with it using devres. On driver detach, + * release function is invoked on the devres data, * then, devres data is freed. * */ @@ -651,13 +652,21 @@ struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, return ERR_PTR(-ENOMEM); phy = _of_phy_get(np, index); - if (!IS_ERR(phy)) { - *ptr = phy; - devres_add(dev, ptr); - } else { + if (IS_ERR(phy)) { devres_free(ptr); + return phy; } + if (!try_module_get(phy->ops->owner)) { + devres_free(ptr); + return ERR_PTR(-EPROBE_DEFER); + } + + get_device(&phy->dev); + + *ptr = phy; + devres_add(dev, ptr); + return phy; } EXPORT_SYMBOL_GPL(devm_of_phy_get_by_index); diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c index c47b56b4a2b88..3acd2a1808dfb 100644 --- a/drivers/phy/phy-miphy28lp.c +++ b/drivers/phy/phy-miphy28lp.c @@ -1226,15 +1226,18 @@ static int miphy28lp_probe(struct platform_device *pdev) miphy_phy = devm_kzalloc(&pdev->dev, sizeof(*miphy_phy), GFP_KERNEL); - if (!miphy_phy) - return -ENOMEM; + if (!miphy_phy) { + ret = -ENOMEM; + goto put_child; + } miphy_dev->phys[port] = miphy_phy; phy = devm_phy_create(&pdev->dev, child, &miphy28lp_ops); if (IS_ERR(phy)) { dev_err(&pdev->dev, "failed to create PHY\n"); - return PTR_ERR(phy); + ret = PTR_ERR(phy); + goto put_child; } miphy_dev->phys[port]->phy = phy; @@ -1242,11 +1245,11 @@ static int miphy28lp_probe(struct platform_device *pdev) ret = miphy28lp_of_probe(child, miphy_phy); if (ret) - return ret; + goto put_child; ret = miphy28lp_probe_resets(child, miphy_dev->phys[port]); if (ret) - return ret; + goto put_child; phy_set_drvdata(phy, miphy_dev->phys[port]); port++; @@ -1255,6 +1258,9 @@ static int miphy28lp_probe(struct platform_device *pdev) provider = devm_of_phy_provider_register(&pdev->dev, miphy28lp_xlate); return PTR_ERR_OR_ZERO(provider); +put_child: + of_node_put(child); + return ret; } static const struct of_device_id miphy28lp_of_match[] = { diff --git a/drivers/phy/phy-miphy365x.c b/drivers/phy/phy-miphy365x.c index 00a686a073ed6..e661f3b36eaa0 100644 --- a/drivers/phy/phy-miphy365x.c +++ b/drivers/phy/phy-miphy365x.c @@ -566,22 +566,25 @@ static int miphy365x_probe(struct platform_device *pdev) miphy_phy = devm_kzalloc(&pdev->dev, sizeof(*miphy_phy), GFP_KERNEL); - if (!miphy_phy) - return -ENOMEM; + if (!miphy_phy) { + ret = -ENOMEM; + goto put_child; + } miphy_dev->phys[port] = miphy_phy; phy = devm_phy_create(&pdev->dev, child, &miphy365x_ops); if (IS_ERR(phy)) { dev_err(&pdev->dev, "failed to create PHY\n"); - return PTR_ERR(phy); + ret = PTR_ERR(phy); + goto put_child; } miphy_dev->phys[port]->phy = phy; ret = miphy365x_of_probe(child, miphy_phy); if (ret) - return ret; + goto put_child; phy_set_drvdata(phy, miphy_dev->phys[port]); @@ -591,12 +594,15 @@ static int miphy365x_probe(struct platform_device *pdev) &miphy_phy->ctrlreg); if (ret) { dev_err(&pdev->dev, "No sysconfig offset found\n"); - return ret; + goto put_child; } } provider = devm_of_phy_provider_register(&pdev->dev, miphy365x_xlate); return PTR_ERR_OR_ZERO(provider); +put_child: + of_node_put(child); + return ret; } static const struct of_device_id miphy365x_of_match[] = { diff --git a/drivers/phy/phy-mt65xx-usb3.c b/drivers/phy/phy-mt65xx-usb3.c index f30b28bd41fe7..e427c3b788ff3 100644 --- a/drivers/phy/phy-mt65xx-usb3.c +++ b/drivers/phy/phy-mt65xx-usb3.c @@ -415,7 +415,7 @@ static int mt65xx_u3phy_probe(struct platform_device *pdev) struct resource *sif_res; struct mt65xx_u3phy *u3phy; struct resource res; - int port; + int port, retval; u3phy = devm_kzalloc(dev, sizeof(*u3phy), GFP_KERNEL); if (!u3phy) @@ -447,31 +447,34 @@ static int mt65xx_u3phy_probe(struct platform_device *pdev) for_each_child_of_node(np, child_np) { struct mt65xx_phy_instance *instance; struct phy *phy; - int retval; instance = devm_kzalloc(dev, sizeof(*instance), GFP_KERNEL); - if (!instance) - return -ENOMEM; + if (!instance) { + retval = -ENOMEM; + goto put_child; + } u3phy->phys[port] = instance; phy = devm_phy_create(dev, child_np, &mt65xx_u3phy_ops); if (IS_ERR(phy)) { dev_err(dev, "failed to create phy\n"); - return PTR_ERR(phy); + retval = PTR_ERR(phy); + goto put_child; } retval = of_address_to_resource(child_np, 0, &res); if (retval) { dev_err(dev, "failed to get address resource(id-%d)\n", port); - return retval; + goto put_child; } instance->port_base = devm_ioremap_resource(&phy->dev, &res); if (IS_ERR(instance->port_base)) { dev_err(dev, "failed to remap phy regs\n"); - return PTR_ERR(instance->port_base); + retval = PTR_ERR(instance->port_base); + goto put_child; } instance->phy = phy; @@ -483,6 +486,9 @@ static int mt65xx_u3phy_probe(struct platform_device *pdev) provider = devm_of_phy_provider_register(dev, mt65xx_phy_xlate); return PTR_ERR_OR_ZERO(provider); +put_child: + of_node_put(child_np); + return retval; } static const struct of_device_id mt65xx_u3phy_id_table[] = { diff --git a/drivers/phy/phy-rockchip-usb.c b/drivers/phy/phy-rockchip-usb.c index 91d6f342c5659..62c43c4351943 100644 --- a/drivers/phy/phy-rockchip-usb.c +++ b/drivers/phy/phy-rockchip-usb.c @@ -108,13 +108,16 @@ static int rockchip_usb_phy_probe(struct platform_device *pdev) for_each_available_child_of_node(dev->of_node, child) { rk_phy = devm_kzalloc(dev, sizeof(*rk_phy), GFP_KERNEL); - if (!rk_phy) - return -ENOMEM; + if (!rk_phy) { + err = -ENOMEM; + goto put_child; + } if (of_property_read_u32(child, "reg", ®_offset)) { dev_err(dev, "missing reg property in node %s\n", child->name); - return -EINVAL; + err = -EINVAL; + goto put_child; } rk_phy->reg_offset = reg_offset; @@ -127,18 +130,22 @@ static int rockchip_usb_phy_probe(struct platform_device *pdev) rk_phy->phy = devm_phy_create(dev, child, &ops); if (IS_ERR(rk_phy->phy)) { dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(rk_phy->phy); + err = PTR_ERR(rk_phy->phy); + goto put_child; } phy_set_drvdata(rk_phy->phy, rk_phy); /* only power up usb phy when it use, so disable it when init*/ err = rockchip_usb_phy_power(rk_phy, 1); if (err) - return err; + goto put_child; } phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); return PTR_ERR_OR_ZERO(phy_provider); +put_child: + of_node_put(child); + return err; } static const struct of_device_id rockchip_usb_phy_dt_ids[] = { diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index a1ea565fcd464..2e6ca69635aa0 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -342,12 +342,6 @@ static int bcm2835_gpio_get(struct gpio_chip *chip, unsigned offset) return bcm2835_gpio_get_bit(pc, GPLEV0, offset); } -static int bcm2835_gpio_direction_output(struct gpio_chip *chip, - unsigned offset, int value) -{ - return pinctrl_gpio_direction_output(chip->base + offset); -} - static void bcm2835_gpio_set(struct gpio_chip *chip, unsigned offset, int value) { struct bcm2835_pinctrl *pc = dev_get_drvdata(chip->dev); @@ -355,6 +349,13 @@ static void bcm2835_gpio_set(struct gpio_chip *chip, unsigned offset, int value) bcm2835_gpio_set_bit(pc, value ? GPSET0 : GPCLR0, offset); } +static int bcm2835_gpio_direction_output(struct gpio_chip *chip, + unsigned offset, int value) +{ + bcm2835_gpio_set(chip, offset, value); + return pinctrl_gpio_direction_output(chip->base + offset); +} + static int bcm2835_gpio_to_irq(struct gpio_chip *chip, unsigned offset) { struct bcm2835_pinctrl *pc = dev_get_drvdata(chip->dev); diff --git a/drivers/pinctrl/freescale/pinctrl-vf610.c b/drivers/pinctrl/freescale/pinctrl-vf610.c index 37a037543d299..587d1ff6210ef 100644 --- a/drivers/pinctrl/freescale/pinctrl-vf610.c +++ b/drivers/pinctrl/freescale/pinctrl-vf610.c @@ -299,7 +299,7 @@ static const struct pinctrl_pin_desc vf610_pinctrl_pads[] = { static struct imx_pinctrl_soc_info vf610_pinctrl_info = { .pins = vf610_pinctrl_pads, .npins = ARRAY_SIZE(vf610_pinctrl_pads), - .flags = SHARE_MUX_CONF_REG, + .flags = SHARE_MUX_CONF_REG | ZERO_OFFSET_VALID, }; static const struct of_device_id vf610_pinctrl_of_match[] = { diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c index e42d5d4183f57..5979d38c46b25 100644 --- a/drivers/pinctrl/intel/pinctrl-broxton.c +++ b/drivers/pinctrl/intel/pinctrl-broxton.c @@ -28,6 +28,7 @@ .padcfglock_offset = BXT_PADCFGLOCK, \ .hostown_offset = BXT_HOSTSW_OWN, \ .ie_offset = BXT_GPI_IE, \ + .gpp_size = 32, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ } diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 392e28d3f48d0..26f6b6ffea5b2 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -25,9 +25,6 @@ #include "pinctrl-intel.h" -/* Maximum number of pads in each group */ -#define NPADS_IN_GPP 24 - /* Offset from regs */ #define PADBAR 0x00c #define GPI_IS 0x100 @@ -37,6 +34,7 @@ #define PADOWN_BITS 4 #define PADOWN_SHIFT(p) ((p) % 8 * PADOWN_BITS) #define PADOWN_MASK(p) (0xf << PADOWN_SHIFT(p)) +#define PADOWN_GPP(p) ((p) / 8) /* Offset from pad_regs */ #define PADCFG0 0x000 @@ -142,7 +140,7 @@ static void __iomem *intel_get_padcfg(struct intel_pinctrl *pctrl, unsigned pin, static bool intel_pad_owned_by_host(struct intel_pinctrl *pctrl, unsigned pin) { const struct intel_community *community; - unsigned padno, gpp, gpp_offset, offset; + unsigned padno, gpp, offset, group; void __iomem *padown; community = intel_get_community(pctrl, pin); @@ -152,9 +150,9 @@ static bool intel_pad_owned_by_host(struct intel_pinctrl *pctrl, unsigned pin) return true; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; - gpp_offset = padno % NPADS_IN_GPP; - offset = community->padown_offset + gpp * 16 + (gpp_offset / 8) * 4; + group = padno / community->gpp_size; + gpp = PADOWN_GPP(padno % community->gpp_size); + offset = community->padown_offset + 0x10 * group + gpp * 4; padown = community->regs + offset; return !(readl(padown) & PADOWN_MASK(padno)); @@ -173,11 +171,11 @@ static bool intel_pad_acpi_mode(struct intel_pinctrl *pctrl, unsigned pin) return false; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; + gpp = padno / community->gpp_size; offset = community->hostown_offset + gpp * 4; hostown = community->regs + offset; - return !(readl(hostown) & BIT(padno % NPADS_IN_GPP)); + return !(readl(hostown) & BIT(padno % community->gpp_size)); } static bool intel_pad_locked(struct intel_pinctrl *pctrl, unsigned pin) @@ -193,7 +191,7 @@ static bool intel_pad_locked(struct intel_pinctrl *pctrl, unsigned pin) return false; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; + gpp = padno / community->gpp_size; /* * If PADCFGLOCK and PADCFGLOCKTX bits are both clear for this pad, @@ -202,12 +200,12 @@ static bool intel_pad_locked(struct intel_pinctrl *pctrl, unsigned pin) */ offset = community->padcfglock_offset + gpp * 8; value = readl(community->regs + offset); - if (value & BIT(pin % NPADS_IN_GPP)) + if (value & BIT(pin % community->gpp_size)) return true; offset = community->padcfglock_offset + 4 + gpp * 8; value = readl(community->regs + offset); - if (value & BIT(pin % NPADS_IN_GPP)) + if (value & BIT(pin % community->gpp_size)) return true; return false; @@ -663,8 +661,8 @@ static void intel_gpio_irq_ack(struct irq_data *d) community = intel_get_community(pctrl, pin); if (community) { unsigned padno = pin_to_padno(community, pin); - unsigned gpp_offset = padno % NPADS_IN_GPP; - unsigned gpp = padno / NPADS_IN_GPP; + unsigned gpp_offset = padno % community->gpp_size; + unsigned gpp = padno / community->gpp_size; writel(BIT(gpp_offset), community->regs + GPI_IS + gpp * 4); } @@ -685,8 +683,8 @@ static void intel_gpio_irq_mask_unmask(struct irq_data *d, bool mask) community = intel_get_community(pctrl, pin); if (community) { unsigned padno = pin_to_padno(community, pin); - unsigned gpp_offset = padno % NPADS_IN_GPP; - unsigned gpp = padno / NPADS_IN_GPP; + unsigned gpp_offset = padno % community->gpp_size; + unsigned gpp = padno / community->gpp_size; void __iomem *reg; u32 value; @@ -780,8 +778,8 @@ static int intel_gpio_irq_wake(struct irq_data *d, unsigned int on) return -EINVAL; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; - gpp_offset = padno % NPADS_IN_GPP; + gpp = padno / community->gpp_size; + gpp_offset = padno % community->gpp_size; /* Clear the existing wake status */ writel(BIT(gpp_offset), community->regs + GPI_GPE_STS + gpp * 4); @@ -819,14 +817,14 @@ static irqreturn_t intel_gpio_community_irq_handler(struct intel_pinctrl *pctrl, /* Only interrupts that are enabled */ pending &= enabled; - for_each_set_bit(gpp_offset, &pending, NPADS_IN_GPP) { + for_each_set_bit(gpp_offset, &pending, community->gpp_size) { unsigned padno, irq; /* * The last group in community can have less pins * than NPADS_IN_GPP. */ - padno = gpp_offset + gpp * NPADS_IN_GPP; + padno = gpp_offset + gpp * community->gpp_size; if (padno >= community->npins) break; @@ -1002,7 +1000,8 @@ int intel_pinctrl_probe(struct platform_device *pdev, community->regs = regs; community->pad_regs = regs + padbar; - community->ngpps = DIV_ROUND_UP(community->npins, NPADS_IN_GPP); + community->ngpps = DIV_ROUND_UP(community->npins, + community->gpp_size); } irq = platform_get_irq(pdev, 0); diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index 4ec8b572a288f..b60215793017b 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -55,6 +55,8 @@ struct intel_function { * ACPI). * @ie_offset: Register offset of GPI_IE from @regs. * @pin_base: Starting pin of pins in this community + * @gpp_size: Maximum number of pads in each group, such as PADCFGLOCK, + * HOSTSW_OWN, GPI_IS, GPI_IE, etc. * @npins: Number of pins in this community * @regs: Community specific common registers (reserved for core driver) * @pad_regs: Community specific pad registers (reserved for core driver) @@ -68,6 +70,7 @@ struct intel_community { unsigned hostown_offset; unsigned ie_offset; unsigned pin_base; + unsigned gpp_size; size_t npins; void __iomem *regs; void __iomem *pad_regs; diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 1de9ae5010db2..c725a5313b4e6 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -30,6 +30,7 @@ .padcfglock_offset = SPT_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ .ie_offset = SPT_GPI_IE, \ + .gpp_size = 24, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ } diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index cc97f0869791d..48747c28a43d4 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -1341,10 +1341,13 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu) for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { /* check if the domain is locked by BIOS */ - if (rapl_read_data_raw(rd, FW_LOCK, false, &locked)) { + ret = rapl_read_data_raw(rd, FW_LOCK, false, &locked); + if (ret) + return ret; + if (locked) { pr_info("RAPL package %d domain %s locked by BIOS\n", rp->id, rd->name); - rd->state |= DOMAIN_STATE_BIOS_LOCKED; + rd->state |= DOMAIN_STATE_BIOS_LOCKED; } } diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c index 284b587da65c5..d6c853bbfa9fc 100644 --- a/drivers/rtc/rtc-da9063.c +++ b/drivers/rtc/rtc-da9063.c @@ -483,24 +483,23 @@ static int da9063_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); + rtc->rtc_dev = devm_rtc_device_register(&pdev->dev, DA9063_DRVNAME_RTC, + &da9063_rtc_ops, THIS_MODULE); + if (IS_ERR(rtc->rtc_dev)) + return PTR_ERR(rtc->rtc_dev); + + da9063_data_to_tm(data, &rtc->alarm_time, rtc); + rtc->rtc_sync = false; + irq_alarm = platform_get_irq_byname(pdev, "ALARM"); ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL, da9063_alarm_event, IRQF_TRIGGER_LOW | IRQF_ONESHOT, "ALARM", rtc); - if (ret) { + if (ret) dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n", irq_alarm, ret); - return ret; - } - - rtc->rtc_dev = devm_rtc_device_register(&pdev->dev, DA9063_DRVNAME_RTC, - &da9063_rtc_ops, THIS_MODULE); - if (IS_ERR(rtc->rtc_dev)) - return PTR_ERR(rtc->rtc_dev); - da9063_data_to_tm(data, &rtc->alarm_time, rtc); - rtc->rtc_sync = false; return ret; } diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c index 91ca0bc1b484b..35c9aada07c8e 100644 --- a/drivers/rtc/rtc-rk808.c +++ b/drivers/rtc/rtc-rk808.c @@ -56,6 +56,42 @@ struct rk808_rtc { int irq; }; +/* + * The Rockchip calendar used by the RK808 counts November with 31 days. We use + * these translation functions to convert its dates to/from the Gregorian + * calendar used by the rest of the world. We arbitrarily define Jan 1st, 2016 + * as the day when both calendars were in sync, and treat all other dates + * relative to that. + * NOTE: Other system software (e.g. firmware) that reads the same hardware must + * implement this exact same conversion algorithm, with the same anchor date. + */ +static time64_t nov2dec_transitions(struct rtc_time *tm) +{ + return (tm->tm_year + 1900) - 2016 + (tm->tm_mon + 1 > 11 ? 1 : 0); +} + +static void rockchip_to_gregorian(struct rtc_time *tm) +{ + /* If it's Nov 31st, rtc_tm_to_time64() will count that like Dec 1st */ + time64_t time = rtc_tm_to_time64(tm); + rtc_time64_to_tm(time + nov2dec_transitions(tm) * 86400, tm); +} + +static void gregorian_to_rockchip(struct rtc_time *tm) +{ + time64_t extra_days = nov2dec_transitions(tm); + time64_t time = rtc_tm_to_time64(tm); + rtc_time64_to_tm(time - extra_days * 86400, tm); + + /* Compensate if we went back over Nov 31st (will work up to 2381) */ + if (nov2dec_transitions(tm) < extra_days) { + if (tm->tm_mon + 1 == 11) + tm->tm_mday++; /* This may result in 31! */ + else + rtc_time64_to_tm(time - (extra_days - 1) * 86400, tm); + } +} + /* Read current time and date in RTC */ static int rk808_rtc_readtime(struct device *dev, struct rtc_time *tm) { @@ -101,9 +137,10 @@ static int rk808_rtc_readtime(struct device *dev, struct rtc_time *tm) tm->tm_mon = (bcd2bin(rtc_data[4] & MONTHS_REG_MSK)) - 1; tm->tm_year = (bcd2bin(rtc_data[5] & YEARS_REG_MSK)) + 100; tm->tm_wday = bcd2bin(rtc_data[6] & WEEKS_REG_MSK); + rockchip_to_gregorian(tm); dev_dbg(dev, "RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n", 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, - tm->tm_wday, tm->tm_hour , tm->tm_min, tm->tm_sec); + tm->tm_wday, tm->tm_hour, tm->tm_min, tm->tm_sec); return ret; } @@ -116,6 +153,10 @@ static int rk808_rtc_set_time(struct device *dev, struct rtc_time *tm) u8 rtc_data[NUM_TIME_REGS]; int ret; + dev_dbg(dev, "set RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n", + 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, + tm->tm_wday, tm->tm_hour, tm->tm_min, tm->tm_sec); + gregorian_to_rockchip(tm); rtc_data[0] = bin2bcd(tm->tm_sec); rtc_data[1] = bin2bcd(tm->tm_min); rtc_data[2] = bin2bcd(tm->tm_hour); @@ -123,9 +164,6 @@ static int rk808_rtc_set_time(struct device *dev, struct rtc_time *tm) rtc_data[4] = bin2bcd(tm->tm_mon + 1); rtc_data[5] = bin2bcd(tm->tm_year - 100); rtc_data[6] = bin2bcd(tm->tm_wday); - dev_dbg(dev, "set RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n", - 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, - tm->tm_wday, tm->tm_hour , tm->tm_min, tm->tm_sec); /* Stop RTC while updating the RTC registers */ ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG, @@ -170,6 +208,7 @@ static int rk808_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm) alrm->time.tm_mday = bcd2bin(alrm_data[3] & DAYS_REG_MSK); alrm->time.tm_mon = (bcd2bin(alrm_data[4] & MONTHS_REG_MSK)) - 1; alrm->time.tm_year = (bcd2bin(alrm_data[5] & YEARS_REG_MSK)) + 100; + rockchip_to_gregorian(&alrm->time); ret = regmap_read(rk808->regmap, RK808_RTC_INT_REG, &int_reg); if (ret) { @@ -227,6 +266,7 @@ static int rk808_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) alrm->time.tm_mday, alrm->time.tm_wday, alrm->time.tm_hour, alrm->time.tm_min, alrm->time.tm_sec); + gregorian_to_rockchip(&alrm->time); alrm_data[0] = bin2bcd(alrm->time.tm_sec); alrm_data[1] = bin2bcd(alrm->time.tm_min); alrm_data[2] = bin2bcd(alrm->time.tm_hour); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 61f768518a34b..24ec282e15d8a 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -599,8 +599,10 @@ static enum ap_wait ap_sm_read(struct ap_device *ap_dev) status = ap_sm_recv(ap_dev); switch (status.response_code) { case AP_RESPONSE_NORMAL: - if (ap_dev->queue_count > 0) + if (ap_dev->queue_count > 0) { + ap_dev->state = AP_STATE_WORKING; return AP_WAIT_AGAIN; + } ap_dev->state = AP_STATE_IDLE; return AP_WAIT_NONE; case AP_RESPONSE_NO_PENDING_REPLY: diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 05c37d6d4afef..c3e22523faf36 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1677,11 +1677,8 @@ static int ctcm_shutdown_device(struct ccwgroup_device *cgdev) ccw_device_set_offline(cgdev->cdev[1]); ccw_device_set_offline(cgdev->cdev[0]); - - if (priv->channel[CTCM_READ]) - channel_remove(priv->channel[CTCM_READ]); - if (priv->channel[CTCM_WRITE]) - channel_remove(priv->channel[CTCM_WRITE]); + channel_remove(priv->channel[CTCM_READ]); + channel_remove(priv->channel[CTCM_WRITE]); priv->channel[CTCM_READ] = priv->channel[CTCM_WRITE] = NULL; return 0; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 1766a20ebcb11..ec2e014e885c2 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -981,6 +981,10 @@ int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16, int (*reply_cb)(struct qeth_card *, struct qeth_reply *, unsigned long), void *); +struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, + enum qeth_ipa_funcs, + __u16, __u16, + enum qeth_prot_versions); int qeth_start_ipa_tx_checksum(struct qeth_card *); int qeth_set_rx_csum(struct qeth_card *, int); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 31ac53fa5cee9..787153764120c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2684,8 +2684,6 @@ void qeth_print_status_message(struct qeth_card *card) sprintf(card->info.mcl_level, "%02x%02x", card->info.mcl_level[2], card->info.mcl_level[3]); - - card->info.mcl_level[QETH_MCL_LENGTH] = 0; break; } /* fallthrough */ @@ -5297,10 +5295,10 @@ static int qeth_setassparms_cb(struct qeth_card *card, return 0; } -static struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, - enum qeth_ipa_funcs ipa_func, - __u16 cmd_code, __u16 len, - enum qeth_prot_versions prot) +struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + __u16 cmd_code, __u16 len, + enum qeth_prot_versions prot) { struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; @@ -5319,6 +5317,7 @@ static struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, return iob; } +EXPORT_SYMBOL_GPL(qeth_get_setassparms_cmd); int qeth_send_setassparms(struct qeth_card *card, struct qeth_cmd_buffer *iob, __u16 len, long data, diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 8f1b091e17327..80b1979e8d955 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1126,6 +1126,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) qeth_l2_request_initial_mac(card); SET_NETDEV_DEV(card->dev, &card->gdev->dev); netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT); + netif_carrier_off(card->dev); return register_netdev(card->dev); } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 543960e96b42b..7c8c68c26540f 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1043,28 +1043,6 @@ static int qeth_l3_default_setassparms_cb(struct qeth_card *card, return 0; } -static struct qeth_cmd_buffer *qeth_l3_get_setassparms_cmd( - struct qeth_card *card, enum qeth_ipa_funcs ipa_func, __u16 cmd_code, - __u16 len, enum qeth_prot_versions prot) -{ - struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; - - QETH_CARD_TEXT(card, 4, "getasscm"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETASSPARMS, prot); - - if (iob) { - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); - cmd->data.setassparms.hdr.assist_no = ipa_func; - cmd->data.setassparms.hdr.length = 8 + len; - cmd->data.setassparms.hdr.command_code = cmd_code; - cmd->data.setassparms.hdr.return_code = 0; - cmd->data.setassparms.hdr.seq_no = 0; - } - - return iob; -} - #ifdef CONFIG_QETH_IPV6 static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, __u16 cmd_code) @@ -1073,7 +1051,7 @@ static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card, struct qeth_cmd_buffer *iob; QETH_CARD_TEXT(card, 4, "simassp6"); - iob = qeth_l3_get_setassparms_cmd(card, ipa_func, cmd_code, + iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, 0, QETH_PROT_IPV6); if (!iob) return -ENOMEM; @@ -2344,10 +2322,11 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, QETH_CARD_TEXT_(card, 3, "qarpipv%i", prot); - iob = qeth_l3_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_QUERY_INFO, - sizeof(struct qeth_arp_query_data) - sizeof(char), - prot); + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, + IPA_CMD_ASS_ARP_QUERY_INFO, + sizeof(struct qeth_arp_query_data) + - sizeof(char), + prot); if (!iob) return -ENOMEM; cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); @@ -2439,7 +2418,7 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, return -EOPNOTSUPP; } - iob = qeth_l3_get_setassparms_cmd(card, IPA_ARP_PROCESSING, + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_ADD_ENTRY, sizeof(struct qeth_arp_cache_entry), QETH_PROT_IPV4); @@ -2480,7 +2459,7 @@ static int qeth_l3_arp_remove_entry(struct qeth_card *card, return -EOPNOTSUPP; } memcpy(buf, entry, 12); - iob = qeth_l3_get_setassparms_cmd(card, IPA_ARP_PROCESSING, + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_REMOVE_ENTRY, 12, QETH_PROT_IPV4); @@ -2818,7 +2797,7 @@ static inline int qeth_l3_tso_elements(struct sk_buff *skb) { unsigned long tcpd = (unsigned long)tcp_hdr(skb) + tcp_hdr(skb)->doff * 4; - int tcpd_len = skb->len - (tcpd - (unsigned long)skb->data); + int tcpd_len = skb_headlen(skb) - (tcpd - (unsigned long)skb->data); int elements = PFN_UP(tcpd + tcpd_len - 1) - PFN_DOWN(tcpd); elements += qeth_get_elements_for_frags(skb); @@ -3220,6 +3199,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) SET_NETDEV_DEV(card->dev, &card->gdev->dev); netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT); + netif_carrier_off(card->dev); return register_netdev(card->dev); } diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index b2a1a81e6fc8f..1b831598df7c6 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -984,6 +984,36 @@ static struct virtqueue *virtio_ccw_vq_by_ind(struct virtio_ccw_device *vcdev, return vq; } +static void virtio_ccw_check_activity(struct virtio_ccw_device *vcdev, + __u32 activity) +{ + if (vcdev->curr_io & activity) { + switch (activity) { + case VIRTIO_CCW_DOING_READ_FEAT: + case VIRTIO_CCW_DOING_WRITE_FEAT: + case VIRTIO_CCW_DOING_READ_CONFIG: + case VIRTIO_CCW_DOING_WRITE_CONFIG: + case VIRTIO_CCW_DOING_WRITE_STATUS: + case VIRTIO_CCW_DOING_SET_VQ: + case VIRTIO_CCW_DOING_SET_IND: + case VIRTIO_CCW_DOING_SET_CONF_IND: + case VIRTIO_CCW_DOING_RESET: + case VIRTIO_CCW_DOING_READ_VQ_CONF: + case VIRTIO_CCW_DOING_SET_IND_ADAPTER: + case VIRTIO_CCW_DOING_SET_VIRTIO_REV: + vcdev->curr_io &= ~activity; + wake_up(&vcdev->wait_q); + break; + default: + /* don't know what to do... */ + dev_warn(&vcdev->cdev->dev, + "Suspicious activity '%08x'\n", activity); + WARN_ON(1); + break; + } + } +} + static void virtio_ccw_int_handler(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) @@ -995,6 +1025,12 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev, if (!vcdev) return; + if (IS_ERR(irb)) { + vcdev->err = PTR_ERR(irb); + virtio_ccw_check_activity(vcdev, activity); + /* Don't poke around indicators, something's wrong. */ + return; + } /* Check if it's a notification from the host. */ if ((intparm == 0) && (scsw_stctl(&irb->scsw) == @@ -1010,31 +1046,7 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev, /* Map everything else to -EIO. */ vcdev->err = -EIO; } - if (vcdev->curr_io & activity) { - switch (activity) { - case VIRTIO_CCW_DOING_READ_FEAT: - case VIRTIO_CCW_DOING_WRITE_FEAT: - case VIRTIO_CCW_DOING_READ_CONFIG: - case VIRTIO_CCW_DOING_WRITE_CONFIG: - case VIRTIO_CCW_DOING_WRITE_STATUS: - case VIRTIO_CCW_DOING_SET_VQ: - case VIRTIO_CCW_DOING_SET_IND: - case VIRTIO_CCW_DOING_SET_CONF_IND: - case VIRTIO_CCW_DOING_RESET: - case VIRTIO_CCW_DOING_READ_VQ_CONF: - case VIRTIO_CCW_DOING_SET_IND_ADAPTER: - case VIRTIO_CCW_DOING_SET_VIRTIO_REV: - vcdev->curr_io &= ~activity; - wake_up(&vcdev->wait_q); - break; - default: - /* don't know what to do... */ - dev_warn(&cdev->dev, "Suspicious activity '%08x'\n", - activity); - WARN_ON(1); - break; - } - } + virtio_ccw_check_activity(vcdev, activity); for_each_set_bit(i, &vcdev->indicators, sizeof(vcdev->indicators) * BITS_PER_BYTE) { /* The bit clear must happen before the vring kick. */ diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 5f692ae407495..64eed87d34a87 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -364,6 +364,7 @@ config SCSI_HPSA tristate "HP Smart Array SCSI driver" depends on PCI && SCSI select CHECK_SIGNATURE + select SCSI_SAS_ATTRS help This driver supports HP Smart Array Controllers (circa 2009). It is a SCSI alternative to the cciss driver, which is a block @@ -499,6 +500,7 @@ config SCSI_ADVANSYS tristate "AdvanSys SCSI support" depends on SCSI depends on ISA || EISA || PCI + depends on ISA_DMA_API || !ISA help This is a driver for all SCSI host adapters manufactured by AdvanSys. It is documented in the kernel source in diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c index 519f9a4b3dadf..febbd83e2ecd9 100644 --- a/drivers/scsi/advansys.c +++ b/drivers/scsi/advansys.c @@ -7803,7 +7803,7 @@ adv_build_req(struct asc_board *boardp, struct scsi_cmnd *scp, return ASC_BUSY; } scsiqp->sense_addr = cpu_to_le32(sense_addr); - scsiqp->sense_len = cpu_to_le32(SCSI_SENSE_BUFFERSIZE); + scsiqp->sense_len = SCSI_SENSE_BUFFERSIZE; /* Build ADV_SCSI_REQ_Q */ diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index f4424063b8601..0efe7112fc1f2 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1625,7 +1625,7 @@ static int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp) /* crc offload */ if (likely(lport->crc_offload)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb); skb->csum_offset = skb->len; crc = 0; diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 323982fd00c3b..82ac1cd818ac1 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -333,6 +333,17 @@ static void scsi_host_dev_release(struct device *dev) kfree(queuedata); } + if (shost->shost_state == SHOST_CREATED) { + /* + * Free the shost_dev device name here if scsi_host_alloc() + * and scsi_host_put() have been called but neither + * scsi_host_add() nor scsi_host_remove() has been called. + * This avoids that the memory allocated for the shost_dev + * name is leaked. + */ + kfree(dev_name(&shost->shost_dev)); + } + scsi_destroy_command_freelist(shost); if (shost_use_blk_mq(shost)) { if (shost->tag_set.tags) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 6a8f95808ee0f..a3860367b568a 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -8671,7 +8671,7 @@ static void hpsa_disable_rld_caching(struct ctlr_info *h) if ((rc != 0) || (c->err_info->CommandStatus != 0)) goto errout; - if (*options && HPSA_DIAG_OPTS_DISABLE_RLD_CACHING) + if (*options & HPSA_DIAG_OPTS_DISABLE_RLD_CACHING) goto out; errout: diff --git a/drivers/scsi/mpt3sas/Kconfig b/drivers/scsi/mpt3sas/Kconfig index 29061467cc174..b736dbc804853 100644 --- a/drivers/scsi/mpt3sas/Kconfig +++ b/drivers/scsi/mpt3sas/Kconfig @@ -71,3 +71,12 @@ config SCSI_MPT3SAS_MAX_SGE MAX_PHYS_SEGMENTS in most kernels. However in SuSE kernels this can be 256. However, it may decreased down to 16. Decreasing this parameter will reduce memory requirements on a per controller instance. + +config SCSI_MPT2SAS + tristate "Legacy MPT2SAS config option" + default n + select SCSI_MPT3SAS + depends on PCI && SCSI + ---help--- + Dummy config option for backwards compatiblity: configure the MPT3SAS + driver instead. diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index d95206b7e1167..9ab77b06434d1 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3905,8 +3905,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd) * We do not expose raid functionality to upper layer for warpdrive. */ if (!ioc->is_warpdrive && !scsih_is_raid(&scmd->device->sdev_gendev) - && (sas_device_priv_data->flags & MPT_DEVICE_TLR_ON) && - scmd->cmd_len != 32) + && sas_is_tlr_enabled(scmd->device) && scmd->cmd_len != 32) mpi_control |= MPI2_SCSIIO_CONTROL_TLR_ON; smid = mpt3sas_base_get_smid_scsiio(ioc, ioc->scsi_io_cb_idx, scmd); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 90fdf0e859e31..675e7fab0796e 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -758,7 +758,7 @@ mvs_store_interrupt_coalescing(struct device *cdev, struct device_attribute *attr, const char *buffer, size_t size) { - int val = 0; + unsigned int val = 0; struct mvs_info *mvi = NULL; struct Scsi_Host *shost = class_to_shost(cdev); struct sas_ha_struct *sha = SHOST_TO_SAS_HA(shost); @@ -766,7 +766,7 @@ mvs_store_interrupt_coalescing(struct device *cdev, if (buffer == NULL) return size; - if (sscanf(buffer, "%d", &val) != 1) + if (sscanf(buffer, "%u", &val) != 1) return -EINVAL; if (val >= 0x10000) { diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c index eb0cc5475c451..b6b4cfdd76201 100644 --- a/drivers/scsi/qla2xxx/qla_nx.c +++ b/drivers/scsi/qla2xxx/qla_nx.c @@ -433,7 +433,7 @@ qla82xx_pci_get_crb_addr_2M(struct qla_hw_data *ha, ulong off_in, if (off_in < QLA82XX_PCI_CRBSPACE) return -1; - *off_out = (void __iomem *)(off_in - QLA82XX_PCI_CRBSPACE); + off_in -= QLA82XX_PCI_CRBSPACE; /* Try direct map */ m = &crb_128M_2M_map[CRB_BLK(off_in)].sub_block[CRB_SUBBLK(off_in)]; @@ -443,6 +443,7 @@ qla82xx_pci_get_crb_addr_2M(struct qla_hw_data *ha, ulong off_in, return 0; } /* Not in direct map, use crb window */ + *off_out = (void __iomem *)off_in; return 1; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index dfcc45bb03b1f..d09d60293c272 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -465,8 +465,9 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = { 0} }, {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* MAINT OUT */ {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, - {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* VERIFY */ - {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, + {0, 0x2f, 0, F_D_OUT_MAYBE | FF_DIRECT_IO, NULL, NULL, /* VERIFY(10) */ + {10, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc7, + 0, 0, 0, 0, 0, 0} }, {1, 0x7f, 0x9, F_SA_HIGH | F_D_IN | FF_DIRECT_IO, resp_read_dt0, vl_iarr, {32, 0xc7, 0, 0, 0, 0, 0x1f, 0x18, 0x0, 0x9, 0xfe, 0, 0xff, 0xff, 0xff, 0xff} },/* VARIABLE LENGTH, READ(32) */ @@ -477,8 +478,8 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = { {10, 0x13, 0xff, 0xff, 0, 0, 0, 0xff, 0xff, 0xc7, 0, 0, 0, 0, 0, 0} }, /* 20 */ - {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ALLOW REMOVAL */ - {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, + {0, 0x1e, 0, 0, NULL, NULL, /* ALLOW REMOVAL */ + {6, 0, 0, 0, 0x3, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, {0, 0x1, 0, 0, resp_start_stop, NULL, /* REWIND ?? */ {6, 0x1, 0, 0, 0, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ATA_PT */ diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c index e4b7998379485..459abe1dcc87a 100644 --- a/drivers/scsi/scsi_pm.c +++ b/drivers/scsi/scsi_pm.c @@ -219,13 +219,13 @@ static int sdev_runtime_suspend(struct device *dev) struct scsi_device *sdev = to_scsi_device(dev); int err = 0; - if (pm && pm->runtime_suspend) { - err = blk_pre_runtime_suspend(sdev->request_queue); - if (err) - return err; + err = blk_pre_runtime_suspend(sdev->request_queue); + if (err) + return err; + if (pm && pm->runtime_suspend) err = pm->runtime_suspend(dev); - blk_post_runtime_suspend(sdev->request_queue, err); - } + blk_post_runtime_suspend(sdev->request_queue, err); + return err; } @@ -248,11 +248,11 @@ static int sdev_runtime_resume(struct device *dev) const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int err = 0; - if (pm && pm->runtime_resume) { - blk_pre_runtime_resume(sdev->request_queue); + blk_pre_runtime_resume(sdev->request_queue); + if (pm && pm->runtime_resume) err = pm->runtime_resume(dev); - blk_post_runtime_resume(sdev->request_queue, err); - } + blk_post_runtime_resume(sdev->request_queue, err); + return err; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 83245391e956b..054923e3393c6 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -701,9 +701,12 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result, * strings. */ if (sdev->inquiry_len < 36) { - sdev_printk(KERN_INFO, sdev, - "scsi scan: INQUIRY result too short (%d)," - " using 36\n", sdev->inquiry_len); + if (!sdev->host->short_inquiry) { + shost_printk(KERN_INFO, sdev->host, + "scsi scan: INQUIRY result too short (%d)," + " using 36\n", sdev->inquiry_len); + sdev->host->short_inquiry = 1; + } sdev->inquiry_len = 36; } diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 8d2312239ae0c..21930c9ac9cd9 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1102,6 +1102,14 @@ void __scsi_remove_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; + /* + * This cleanup path is not reentrant and while it is impossible + * to get a new reference with scsi_device_get() someone can still + * hold a previously acquired one. + */ + if (sdev->sdev_state == SDEV_DEL) + return; + if (sdev->is_visible) { if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0) return; @@ -1110,7 +1118,9 @@ void __scsi_remove_device(struct scsi_device *sdev) device_unregister(&sdev->sdev_dev); transport_remove_device(dev); scsi_dh_remove_device(sdev); - } + device_del(dev); + } else + put_device(&sdev->sdev_dev); /* * Stop accepting new requests and wait until all queuecommand() and @@ -1121,16 +1131,6 @@ void __scsi_remove_device(struct scsi_device *sdev) blk_cleanup_queue(sdev->request_queue); cancel_work_sync(&sdev->requeue_work); - /* - * Remove the device after blk_cleanup_queue() has been called such - * a possible bdi_register() call with the same name occurs after - * blk_cleanup_queue() has called bdi_destroy(). - */ - if (sdev->is_visible) - device_del(dev); - else - put_device(&sdev->sdev_dev); - if (sdev->host->hostt->slave_destroy) sdev->host->hostt->slave_destroy(sdev); transport_destroy_device(dev); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 54519804c46a5..3d22fc3e3c1a7 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -638,11 +638,24 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) unsigned int max_blocks = 0; q->limits.discard_zeroes_data = 0; - q->limits.discard_alignment = sdkp->unmap_alignment * - logical_block_size; - q->limits.discard_granularity = - max(sdkp->physical_block_size, - sdkp->unmap_granularity * logical_block_size); + + /* + * When LBPRZ is reported, discard alignment and granularity + * must be fixed to the logical block size. Otherwise the block + * layer will drop misaligned portions of the request which can + * lead to data corruption. If LBPRZ is not set, we honor the + * device preference. + */ + if (sdkp->lbprz) { + q->limits.discard_alignment = 0; + q->limits.discard_granularity = 1; + } else { + q->limits.discard_alignment = sdkp->unmap_alignment * + logical_block_size; + q->limits.discard_granularity = + max(sdkp->physical_block_size, + sdkp->unmap_granularity * logical_block_size); + } sdkp->provisioning_mode = mode; @@ -2321,11 +2334,8 @@ got_data: } } - if (sdkp->capacity > 0xffffffff) { + if (sdkp->capacity > 0xffffffff) sdp->use_16_for_rw = 1; - sdkp->max_xfer_blocks = SD_MAX_XFER_BLOCKS; - } else - sdkp->max_xfer_blocks = SD_DEF_XFER_BLOCKS; /* Rescale capacity to 512-byte units */ if (sector_size == 4096) @@ -2642,7 +2652,6 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) { unsigned int sector_sz = sdkp->device->sector_size; const int vpd_len = 64; - u32 max_xfer_length; unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL); if (!buffer || @@ -2650,14 +2659,11 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len)) goto out; - max_xfer_length = get_unaligned_be32(&buffer[8]); - if (max_xfer_length) - sdkp->max_xfer_blocks = max_xfer_length; - blk_queue_io_min(sdkp->disk->queue, get_unaligned_be16(&buffer[6]) * sector_sz); - blk_queue_io_opt(sdkp->disk->queue, - get_unaligned_be32(&buffer[12]) * sector_sz); + + sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]); + sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]); if (buffer[3] == 0x3c) { unsigned int lba_count, desc_count; @@ -2806,6 +2812,11 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp) return 0; } +static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks) +{ + return blocks << (ilog2(sdev->sector_size) - 9); +} + /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. @@ -2815,8 +2826,9 @@ static int sd_revalidate_disk(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; + struct request_queue *q = sdkp->disk->queue; unsigned char *buffer; - unsigned int max_xfer; + unsigned int dev_max, rw_max; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_revalidate_disk\n")); @@ -2864,11 +2876,26 @@ static int sd_revalidate_disk(struct gendisk *disk) */ sd_set_flush_flag(sdkp); - max_xfer = sdkp->max_xfer_blocks; - max_xfer <<= ilog2(sdp->sector_size) - 9; + /* Initial block count limit based on CDB TRANSFER LENGTH field size. */ + dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS; + + /* Some devices report a maximum block count for READ/WRITE requests. */ + dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks); + q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); + + /* + * Use the device's preferred I/O size for reads and writes + * unless the reported value is unreasonably large (or garbage). + */ + if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max && + sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS) + rw_max = q->limits.io_opt = + logical_to_sectors(sdp, sdkp->opt_xfer_blocks); + else + rw_max = BLK_DEF_MAX_SECTORS; - sdkp->disk->queue->limits.max_sectors = - min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer); + /* Combine with controller limits */ + q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); set_capacity(disk, sdkp->capacity); sd_config_write_same(sdkp); diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 63ba5ca7f9a16..5f2a84aff29fb 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -67,6 +67,7 @@ struct scsi_disk { atomic_t openers; sector_t capacity; /* size in 512-byte sectors */ u32 max_xfer_blocks; + u32 opt_xfer_blocks; u32 max_ws_blocks; u32 max_unmap_blocks; u32 unmap_granularity; diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index dcb0d76d73128..044d06410d4c8 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -84,6 +84,7 @@ static void init_device_slot_control(unsigned char *dest_desc, static int ses_recv_diag(struct scsi_device *sdev, int page_code, void *buf, int bufflen) { + int ret; unsigned char cmd[] = { RECEIVE_DIAGNOSTIC, 1, /* Set PCV bit */ @@ -92,9 +93,26 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code, bufflen & 0xff, 0 }; + unsigned char recv_page_code; - return scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen, + ret = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen, NULL, SES_TIMEOUT, SES_RETRIES, NULL); + if (unlikely(!ret)) + return ret; + + recv_page_code = ((unsigned char *)buf)[0]; + + if (likely(recv_page_code == page_code)) + return ret; + + /* successful diagnostic but wrong page code. This happens to some + * USB devices, just print a message and pretend there was an error */ + + sdev_printk(KERN_ERR, sdev, + "Wrong diagnostic page; asked for %d got %u\n", + page_code, recv_page_code); + + return -EINVAL; } static int ses_send_diag(struct scsi_device *sdev, int page_code, @@ -541,7 +559,15 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, if (desc_ptr) desc_ptr += len; - if (addl_desc_ptr) + if (addl_desc_ptr && + /* only find additional descriptions for specific devices */ + (type_ptr[0] == ENCLOSURE_COMPONENT_DEVICE || + type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE || + type_ptr[0] == ENCLOSURE_COMPONENT_SAS_EXPANDER || + /* these elements are optional */ + type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_TARGET_PORT || + type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT || + type_ptr[0] == ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS)) addl_desc_ptr += addl_desc_ptr[1] + 2; } diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index e0a1e52a04e73..2e522951b6197 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4083,6 +4083,7 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew) } cdev->owner = THIS_MODULE; cdev->ops = &st_fops; + STm->cdevs[rew] = cdev; error = cdev_add(cdev, cdev_devno, 1); if (error) { @@ -4091,7 +4092,6 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew) pr_err("st%d: Device not attached.\n", dev_num); goto out_free; } - STm->cdevs[rew] = cdev; i = mode << (4 - ST_NBR_MODE_BITS); snprintf(name, 10, "%s%s%s", rew ? "n" : "", @@ -4110,8 +4110,9 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew) return 0; out_free: cdev_del(STm->cdevs[rew]); - STm->cdevs[rew] = NULL; out: + STm->cdevs[rew] = NULL; + STm->devs[rew] = NULL; return error; } diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 59a11437db709..39412c9097c6a 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -167,7 +167,7 @@ static inline int is_double_byte_mode(struct fsl_dspi *dspi) { unsigned int val; - regmap_read(dspi->regmap, SPI_CTAR(dspi->cs), &val); + regmap_read(dspi->regmap, SPI_CTAR(0), &val); return ((val & SPI_FRAME_BITS_MASK) == SPI_FRAME_BITS(8)) ? 0 : 1; } @@ -257,7 +257,7 @@ static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word) return SPI_PUSHR_TXDATA(d16) | SPI_PUSHR_PCS(dspi->cs) | - SPI_PUSHR_CTAS(dspi->cs) | + SPI_PUSHR_CTAS(0) | SPI_PUSHR_CONT; } @@ -290,7 +290,7 @@ static int dspi_eoq_write(struct fsl_dspi *dspi) */ if (tx_word && (dspi->len == 1)) { dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM; - regmap_update_bits(dspi->regmap, SPI_CTAR(dspi->cs), + regmap_update_bits(dspi->regmap, SPI_CTAR(0), SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8)); tx_word = 0; } @@ -339,7 +339,7 @@ static int dspi_tcfq_write(struct fsl_dspi *dspi) if (tx_word && (dspi->len == 1)) { dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM; - regmap_update_bits(dspi->regmap, SPI_CTAR(dspi->cs), + regmap_update_bits(dspi->regmap, SPI_CTAR(0), SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8)); tx_word = 0; } @@ -407,7 +407,7 @@ static int dspi_transfer_one_message(struct spi_master *master, regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF); - regmap_write(dspi->regmap, SPI_CTAR(dspi->cs), + regmap_write(dspi->regmap, SPI_CTAR(0), dspi->cur_chip->ctar_val); trans_mode = dspi->devtype_data->trans_mode; @@ -566,7 +566,7 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id) if (!dspi->len) { if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM) { regmap_update_bits(dspi->regmap, - SPI_CTAR(dspi->cs), + SPI_CTAR(0), SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(16)); dspi->dataflags &= ~TRAN_STATE_WORD_ODD_NUM; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 2b0a8ec3affb8..dee1cb87d24f4 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1705,7 +1705,7 @@ struct spi_master *spi_alloc_master(struct device *dev, unsigned size) master->bus_num = -1; master->num_chipselect = 1; master->dev.class = &spi_master_class; - master->dev.parent = get_device(dev); + master->dev.parent = dev; spi_master_set_devdata(master, &master[1]); return master; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 91a0fcd724230..d0e7dfc647cf2 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -651,11 +651,11 @@ static int spidev_release(struct inode *inode, struct file *filp) kfree(spidev->rx_buffer); spidev->rx_buffer = NULL; + spin_lock_irq(&spidev->spi_lock); if (spidev->spi) spidev->speed_hz = spidev->spi->max_speed_hz; /* ... after we unbound from the underlying device? */ - spin_lock_irq(&spidev->spi_lock); dofree = (spidev->spi == NULL); spin_unlock_irq(&spidev->spi_lock); diff --git a/drivers/staging/android/ion/ion_chunk_heap.c b/drivers/staging/android/ion/ion_chunk_heap.c index 195c41d7bd53b..0813163f962f0 100644 --- a/drivers/staging/android/ion/ion_chunk_heap.c +++ b/drivers/staging/android/ion/ion_chunk_heap.c @@ -81,7 +81,7 @@ static int ion_chunk_heap_allocate(struct ion_heap *heap, err: sg = table->sgl; for (i -= 1; i >= 0; i--) { - gen_pool_free(chunk_heap->pool, sg_phys(sg) & PAGE_MASK, + gen_pool_free(chunk_heap->pool, page_to_phys(sg_page(sg)), sg->length); sg = sg_next(sg); } @@ -109,7 +109,7 @@ static void ion_chunk_heap_free(struct ion_buffer *buffer) DMA_BIDIRECTIONAL); for_each_sg(table->sgl, sg, table->nents, i) { - gen_pool_free(chunk_heap->pool, sg_phys(sg) & PAGE_MASK, + gen_pool_free(chunk_heap->pool, page_to_phys(sg_page(sg)), sg->length); } chunk_heap->allocated -= allocated_size; diff --git a/drivers/staging/iio/iio_simple_dummy_events.c b/drivers/staging/iio/iio_simple_dummy_events.c index bfbf1c56bd226..6eb600ff70569 100644 --- a/drivers/staging/iio/iio_simple_dummy_events.c +++ b/drivers/staging/iio/iio_simple_dummy_events.c @@ -159,7 +159,7 @@ static irqreturn_t iio_simple_dummy_get_timestamp(int irq, void *private) struct iio_dummy_state *st = iio_priv(indio_dev); st->event_timestamp = iio_get_time_ns(); - return IRQ_HANDLED; + return IRQ_WAKE_THREAD; } /** diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h index f5d741f25ffde..485ab26709185 100644 --- a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h +++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h @@ -110,7 +110,6 @@ struct libcfs_ioctl_handler { #define IOC_LIBCFS_CLEAR_DEBUG _IOWR('e', 31, long) #define IOC_LIBCFS_MARK_DEBUG _IOWR('e', 32, long) #define IOC_LIBCFS_MEMHOG _IOWR('e', 36, long) -#define IOC_LIBCFS_PING_TEST _IOWR('e', 37, long) /* lnet ioctls */ #define IOC_LIBCFS_GET_NI _IOWR('e', 50, long) #define IOC_LIBCFS_FAIL_NID _IOWR('e', 51, long) diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c index 679785b0209cf..9de4f23910d8b 100644 --- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c +++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c @@ -69,7 +69,7 @@ ksocknal_lib_zc_capable(ksock_conn_t *conn) /* ZC if the socket supports scatter/gather and doesn't need software * checksums */ - return ((caps & NETIF_F_SG) != 0 && (caps & NETIF_F_ALL_CSUM) != 0); + return ((caps & NETIF_F_SG) != 0 && (caps & NETIF_F_CSUM_MASK) != 0); } int diff --git a/drivers/staging/lustre/lustre/libcfs/module.c b/drivers/staging/lustre/lustre/libcfs/module.c index 07a68594c2791..e7c2b26156b9d 100644 --- a/drivers/staging/lustre/lustre/libcfs/module.c +++ b/drivers/staging/lustre/lustre/libcfs/module.c @@ -274,23 +274,6 @@ static int libcfs_ioctl_int(struct cfs_psdev_file *pfile, unsigned long cmd, } break; - case IOC_LIBCFS_PING_TEST: { - extern void (kping_client)(struct libcfs_ioctl_data *); - void (*ping)(struct libcfs_ioctl_data *); - - CDEBUG(D_IOCTL, "doing %d pings to nid %s (%s)\n", - data->ioc_count, libcfs_nid2str(data->ioc_nid), - libcfs_nid2str(data->ioc_nid)); - ping = symbol_get(kping_client); - if (!ping) - CERROR("symbol_get failed\n"); - else { - ping(data); - symbol_put(kping_client); - } - return 0; - } - default: { struct libcfs_ioctl_handler *hand; diff --git a/drivers/staging/lustre/lustre/obdecho/echo_client.c b/drivers/staging/lustre/lustre/obdecho/echo_client.c index f61ef669644cd..a4a9a763ff023 100644 --- a/drivers/staging/lustre/lustre/obdecho/echo_client.c +++ b/drivers/staging/lustre/lustre/obdecho/echo_client.c @@ -1270,6 +1270,7 @@ static int echo_copyout_lsm(struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob) { struct lov_stripe_md *ulsm = _ulsm; + struct lov_oinfo **p; int nob, i; nob = offsetof(struct lov_stripe_md, lsm_oinfo[lsm->lsm_stripe_count]); @@ -1279,9 +1280,10 @@ echo_copyout_lsm(struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob) if (copy_to_user(ulsm, lsm, sizeof(*ulsm))) return -EFAULT; - for (i = 0; i < lsm->lsm_stripe_count; i++) { - if (copy_to_user(ulsm->lsm_oinfo[i], lsm->lsm_oinfo[i], - sizeof(lsm->lsm_oinfo[0]))) + for (i = 0, p = lsm->lsm_oinfo; i < lsm->lsm_stripe_count; i++, p++) { + struct lov_oinfo __user *up; + if (get_user(up, ulsm->lsm_oinfo + i) || + copy_to_user(up, *p, sizeof(struct lov_oinfo))) return -EFAULT; } return 0; @@ -1289,9 +1291,10 @@ echo_copyout_lsm(struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob) static int echo_copyin_lsm(struct echo_device *ed, struct lov_stripe_md *lsm, - void *ulsm, int ulsm_nob) + struct lov_stripe_md __user *ulsm, int ulsm_nob) { struct echo_client_obd *ec = ed->ed_ec; + struct lov_oinfo **p; int i; if (ulsm_nob < sizeof(*lsm)) @@ -1306,11 +1309,10 @@ echo_copyin_lsm(struct echo_device *ed, struct lov_stripe_md *lsm, ((__u64)lsm->lsm_stripe_size * lsm->lsm_stripe_count > ~0UL)) return -EINVAL; - for (i = 0; i < lsm->lsm_stripe_count; i++) { - if (copy_from_user(lsm->lsm_oinfo[i], - ((struct lov_stripe_md *)ulsm)-> \ - lsm_oinfo[i], - sizeof(lsm->lsm_oinfo[0]))) + for (i = 0, p = lsm->lsm_oinfo; i < lsm->lsm_stripe_count; i++, p++) { + struct lov_oinfo __user *up; + if (get_user(up, ulsm->lsm_oinfo + i) || + copy_from_user(*p, up, sizeof(struct lov_oinfo))) return -EFAULT; } return 0; diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index ed776149261ea..e49c2bce551d3 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2054,13 +2054,13 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, size_t eol; size_t tail; int ret, found = 0; - bool eof_push = 0; /* N.B. avoid overrun if nr == 0 */ - n = min(*nr, smp_load_acquire(&ldata->canon_head) - ldata->read_tail); - if (!n) + if (!*nr) return 0; + n = min(*nr + 1, smp_load_acquire(&ldata->canon_head) - ldata->read_tail); + tail = ldata->read_tail & (N_TTY_BUF_SIZE - 1); size = min_t(size_t, tail + n, N_TTY_BUF_SIZE); @@ -2081,12 +2081,11 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, n = eol - tail; if (n > N_TTY_BUF_SIZE) n += N_TTY_BUF_SIZE; - n += found; - c = n; + c = n + found; - if (found && !ldata->push && read_buf(ldata, eol) == __DISABLED_CHAR) { - n--; - eof_push = !n && ldata->read_tail != ldata->line_start; + if (!found || read_buf(ldata, eol) != __DISABLED_CHAR) { + c = min(*nr, c); + n = c; } n_tty_trace("%s: eol:%zu found:%d n:%zu c:%zu size:%zu more:%zu\n", @@ -2116,7 +2115,7 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, ldata->push = 0; tty_audit_push(tty); } - return eof_push ? -EAGAIN : 0; + return 0; } extern ssize_t redirected_tty_write(struct file *, const char __user *, @@ -2273,10 +2272,7 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, if (ldata->icanon && !L_EXTPROC(tty)) { retval = canon_copy_from_read_buf(tty, &b, &nr); - if (retval == -EAGAIN) { - retval = 0; - continue; - } else if (retval) + if (retval) break; } else { int uncopied; diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c index d11621e2cf1df..245edbb68d4ba 100644 --- a/drivers/tty/serial/8250/8250_uniphier.c +++ b/drivers/tty/serial/8250/8250_uniphier.c @@ -115,12 +115,16 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value) */ static int uniphier_serial_dl_read(struct uart_8250_port *up) { - return readl(up->port.membase + UNIPHIER_UART_DLR); + int offset = UNIPHIER_UART_DLR << up->port.regshift; + + return readl(up->port.membase + offset); } static void uniphier_serial_dl_write(struct uart_8250_port *up, int value) { - writel(value, up->port.membase + UNIPHIER_UART_DLR); + int offset = UNIPHIER_UART_DLR << up->port.regshift; + + writel(value, up->port.membase + offset); } static int uniphier_of_serial_setup(struct device *dev, struct uart_port *port, diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c index f09636083426d..b5b2f2be6be7c 100644 --- a/drivers/tty/serial/earlycon.c +++ b/drivers/tty/serial/earlycon.c @@ -115,6 +115,7 @@ static int __init register_earlycon(char *buf, const struct earlycon_id *match) if (buf && !parse_options(&early_console_dev, buf)) buf = NULL; + spin_lock_init(&port->lock); port->uartclk = BASE_BAUD * 16; if (port->mapbase) port->membase = earlycon_map(port->mapbase, 64); @@ -202,6 +203,7 @@ int __init of_setup_earlycon(unsigned long addr, int err; struct uart_port *port = &early_console_dev.port; + spin_lock_init(&port->lock); port->iotype = UPIO_MEM; port->mapbase = addr; port->uartclk = BASE_BAUD * 16; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 960e50a97558c..51c7507b04449 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1437,7 +1437,7 @@ static void sci_request_dma(struct uart_port *port) sg_init_table(sg, 1); s->rx_buf[i] = buf; sg_dma_address(sg) = dma; - sg->length = s->buf_len_rx; + sg_dma_len(sg) = s->buf_len_rx; buf += s->buf_len_rx; dma += s->buf_len_rx; diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c index 064031870ba0d..ca0d3802f2af4 100644 --- a/drivers/tty/serial/sunhv.c +++ b/drivers/tty/serial/sunhv.c @@ -148,8 +148,10 @@ static int receive_chars_read(struct uart_port *port) uart_handle_dcd_change(port, 1); } - for (i = 0; i < bytes_read; i++) - uart_handle_sysrq_char(port, con_read_page[i]); + if (port->sysrq != 0 && *con_read_page) { + for (i = 0; i < bytes_read; i++) + uart_handle_sysrq_char(port, con_read_page[i]); + } if (port->state == NULL) continue; @@ -168,17 +170,17 @@ struct sunhv_ops { int (*receive_chars)(struct uart_port *port); }; -static struct sunhv_ops bychar_ops = { +static const struct sunhv_ops bychar_ops = { .transmit_chars = transmit_chars_putchar, .receive_chars = receive_chars_getchar, }; -static struct sunhv_ops bywrite_ops = { +static const struct sunhv_ops bywrite_ops = { .transmit_chars = transmit_chars_write, .receive_chars = receive_chars_read, }; -static struct sunhv_ops *sunhv_ops = &bychar_ops; +static const struct sunhv_ops *sunhv_ops = &bychar_ops; static struct tty_port *receive_chars(struct uart_port *port) { diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 9a479e61791a2..3cd31e0d4bd95 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -450,7 +450,7 @@ receive_buf(struct tty_struct *tty, struct tty_buffer *head, int count) count = disc->ops->receive_buf2(tty, p, f, count); else { count = min_t(int, count, tty->receive_room); - if (count) + if (count && disc->ops->receive_buf) disc->ops->receive_buf(tty, p, f, count); } return count; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index b30e7423549b0..26ca4f910cb02 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1838,6 +1838,11 @@ static const struct usb_device_id acm_ids[] = { }, #endif + /* Exclude Infineon Flash Loader utility */ + { USB_DEVICE(0x058b, 0x0041), + .driver_info = IGNORE_DEVICE, + }, + /* control interfaces without any protocol set */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_PROTO_NONE) }, diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 7caff020106e2..5050760f5e17c 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -115,7 +115,8 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno, USB_SS_MULT(desc->bmAttributes) > 3) { dev_warn(ddev, "Isoc endpoint has Mult of %d in " "config %d interface %d altsetting %d ep %d: " - "setting to 3\n", desc->bmAttributes + 1, + "setting to 3\n", + USB_SS_MULT(desc->bmAttributes), cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 2; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index bdeadc112d29f..ddbf32d599cba 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -124,6 +124,10 @@ struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev) int usb_device_supports_lpm(struct usb_device *udev) { + /* Some devices have trouble with LPM */ + if (udev->quirks & USB_QUIRK_NO_LPM) + return 0; + /* USB 2.1 (and greater) devices indicate LPM support through * their USB 2.0 Extended Capabilities BOS descriptor. */ @@ -1031,10 +1035,20 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) unsigned delay; /* Continue a partial initialization */ - if (type == HUB_INIT2) - goto init2; - if (type == HUB_INIT3) + if (type == HUB_INIT2 || type == HUB_INIT3) { + device_lock(hub->intfdev); + + /* Was the hub disconnected while we were waiting? */ + if (hub->disconnected) { + device_unlock(hub->intfdev); + kref_put(&hub->kref, hub_release); + return; + } + if (type == HUB_INIT2) + goto init2; goto init3; + } + kref_get(&hub->kref); /* The superspeed hub except for root hub has to use Hub Depth * value as an offset into the route string to locate the bits @@ -1232,6 +1246,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) queue_delayed_work(system_power_efficient_wq, &hub->init_work, msecs_to_jiffies(delay)); + device_unlock(hub->intfdev); return; /* Continues at init3: below */ } else { msleep(delay); @@ -1253,6 +1268,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Allow autosuspend if it was suppressed */ if (type <= HUB_INIT3) usb_autopm_put_interface_async(to_usb_interface(hub->intfdev)); + + if (type == HUB_INIT2 || type == HUB_INIT3) + device_unlock(hub->intfdev); + + kref_put(&hub->kref, hub_release); } /* Implement the continuations for the delays above */ @@ -4512,6 +4532,8 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, goto fail; } + usb_detect_quirks(udev); + if (udev->wusb == 0 && le16_to_cpu(udev->descriptor.bcdUSB) >= 0x0201) { retval = usb_get_bos_descriptor(udev); if (!retval) { @@ -4710,7 +4732,6 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, if (status < 0) goto loop; - usb_detect_quirks(udev); if (udev->quirks & USB_QUIRK_DELAY_INIT) msleep(1000); @@ -5326,9 +5347,6 @@ static int usb_reset_and_verify_device(struct usb_device *udev) if (udev->usb2_hw_lpm_enabled == 1) usb_set_usb2_hardware_lpm(udev, 0); - bos = udev->bos; - udev->bos = NULL; - /* Disable LPM and LTM while we reset the device and reinstall the alt * settings. Device-initiated LPM settings, and system exit latency * settings are cleared when the device is reset, so we have to set @@ -5337,15 +5355,18 @@ static int usb_reset_and_verify_device(struct usb_device *udev) ret = usb_unlocked_disable_lpm(udev); if (ret) { dev_err(&udev->dev, "%s Failed to disable LPM\n.", __func__); - goto re_enumerate; + goto re_enumerate_no_bos; } ret = usb_disable_ltm(udev); if (ret) { dev_err(&udev->dev, "%s Failed to disable LTM\n.", __func__); - goto re_enumerate; + goto re_enumerate_no_bos; } + bos = udev->bos; + udev->bos = NULL; + for (i = 0; i < SET_CONFIG_TRIES; ++i) { /* ep0 maxpacket size may change; let the HCD know about it. @@ -5442,10 +5463,11 @@ done: return 0; re_enumerate: - /* LPM state doesn't matter when we're about to destroy the device. */ - hub_port_logical_disconnect(parent_hub, port1); usb_release_bos_descriptor(udev); udev->bos = bos; +re_enumerate_no_bos: + /* LPM state doesn't matter when we're about to destroy the device. */ + hub_port_logical_disconnect(parent_hub, port1); return -ENODEV; } diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 210618319f10a..5487fe308f01b 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -206,7 +206,7 @@ static int link_peers(struct usb_port *left, struct usb_port *right) else method = "default"; - pr_warn("usb: failed to peer %s and %s by %s (%s:%s) (%s:%s)\n", + pr_debug("usb: failed to peer %s and %s by %s (%s:%s) (%s:%s)\n", dev_name(&left->dev), dev_name(&right->dev), method, dev_name(&left->dev), lpeer ? dev_name(&lpeer->dev) : "none", @@ -265,7 +265,7 @@ static void link_peers_report(struct usb_port *left, struct usb_port *right) if (rc == 0) { dev_dbg(&left->dev, "peered to %s\n", dev_name(&right->dev)); } else { - dev_warn(&left->dev, "failed to peer to %s (%d)\n", + dev_dbg(&left->dev, "failed to peer to %s (%d)\n", dev_name(&right->dev), rc); pr_warn_once("usb: port power management may be unreliable\n"); usb_port_block_power_off = 1; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f5a381945db28..6dc810bce295a 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -125,6 +125,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x04f3, 0x016f), .driver_info = USB_QUIRK_DEVICE_QUALIFIER }, + { USB_DEVICE(0x04f3, 0x21b8), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + /* Roland SC-8820 */ { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -199,6 +202,12 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1a0a, 0x0200), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Blackmagic Design Intensity Shuttle */ + { USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM }, + + /* Blackmagic Design UltraStudio SDI */ + { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index e61d773cf65e7..39c1cbf0e75d9 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -125,9 +125,11 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) if (ret) return ret; - ret = clk_prepare_enable(hsotg->clk); - if (ret) - return ret; + if (hsotg->clk) { + ret = clk_prepare_enable(hsotg->clk); + if (ret) + return ret; + } if (hsotg->uphy) ret = usb_phy_init(hsotg->uphy); @@ -175,7 +177,8 @@ static int __dwc2_lowlevel_hw_disable(struct dwc2_hsotg *hsotg) if (ret) return ret; - clk_disable_unprepare(hsotg->clk); + if (hsotg->clk) + clk_disable_unprepare(hsotg->clk); ret = regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); @@ -212,14 +215,41 @@ static int dwc2_lowlevel_hw_init(struct dwc2_hsotg *hsotg) */ hsotg->phy = devm_phy_get(hsotg->dev, "usb2-phy"); if (IS_ERR(hsotg->phy)) { - hsotg->phy = NULL; + ret = PTR_ERR(hsotg->phy); + switch (ret) { + case -ENODEV: + case -ENOSYS: + hsotg->phy = NULL; + break; + case -EPROBE_DEFER: + return ret; + default: + dev_err(hsotg->dev, "error getting phy %d\n", ret); + return ret; + } + } + + if (!hsotg->phy) { hsotg->uphy = devm_usb_get_phy(hsotg->dev, USB_PHY_TYPE_USB2); - if (IS_ERR(hsotg->uphy)) - hsotg->uphy = NULL; - else - hsotg->plat = dev_get_platdata(hsotg->dev); + if (IS_ERR(hsotg->uphy)) { + ret = PTR_ERR(hsotg->uphy); + switch (ret) { + case -ENODEV: + case -ENXIO: + hsotg->uphy = NULL; + break; + case -EPROBE_DEFER: + return ret; + default: + dev_err(hsotg->dev, "error getting usb phy %d\n", + ret); + return ret; + } + } } + hsotg->plat = dev_get_platdata(hsotg->dev); + if (hsotg->phy) { /* * If using the generic PHY framework, check if the PHY bus @@ -229,11 +259,6 @@ static int dwc2_lowlevel_hw_init(struct dwc2_hsotg *hsotg) hsotg->phyif = GUSBCFG_PHYIF8; } - if (!hsotg->phy && !hsotg->uphy && !hsotg->plat) { - dev_err(hsotg->dev, "no platform data or transceiver defined\n"); - return -EPROBE_DEFER; - } - /* Clock */ hsotg->clk = devm_clk_get(hsotg->dev, "otg"); if (IS_ERR(hsotg->clk)) { @@ -342,20 +367,6 @@ static int dwc2_driver_probe(struct platform_device *dev) if (retval) return retval; - irq = platform_get_irq(dev, 0); - if (irq < 0) { - dev_err(&dev->dev, "missing IRQ resource\n"); - return irq; - } - - dev_dbg(hsotg->dev, "registering common handler for irq%d\n", - irq); - retval = devm_request_irq(hsotg->dev, irq, - dwc2_handle_common_intr, IRQF_SHARED, - dev_name(hsotg->dev), hsotg); - if (retval) - return retval; - res = platform_get_resource(dev, IORESOURCE_MEM, 0); hsotg->regs = devm_ioremap_resource(&dev->dev, res); if (IS_ERR(hsotg->regs)) @@ -390,6 +401,20 @@ static int dwc2_driver_probe(struct platform_device *dev) dwc2_set_all_params(hsotg->core_params, -1); + irq = platform_get_irq(dev, 0); + if (irq < 0) { + dev_err(&dev->dev, "missing IRQ resource\n"); + return irq; + } + + dev_dbg(hsotg->dev, "registering common handler for irq%d\n", + irq); + retval = devm_request_irq(hsotg->dev, irq, + dwc2_handle_common_intr, IRQF_SHARED, + dev_name(hsotg->dev), hsotg); + if (retval) + return retval; + retval = dwc2_lowlevel_hw_enable(hsotg); if (retval) return retval; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index e24a01cc98df4..a58376fd65fe6 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1078,6 +1078,7 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req) * little bit faster. */ if (!usb_endpoint_xfer_isoc(dep->endpoint.desc) && + !usb_endpoint_xfer_int(dep->endpoint.desc) && !(dep->flags & DWC3_EP_BUSY)) { ret = __dwc3_gadget_kick_transfer(dep, 0, true); goto out; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index adc6d52efa463..cf43e9e18368d 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -423,7 +423,7 @@ static ssize_t __ffs_ep0_read_events(struct ffs_data *ffs, char __user *buf, spin_unlock_irq(&ffs->ev.waitq.lock); mutex_unlock(&ffs->mutex); - return unlikely(__copy_to_user(buf, events, size)) ? -EFAULT : size; + return unlikely(copy_to_user(buf, events, size)) ? -EFAULT : size; } static ssize_t ffs_ep0_read(struct file *file, char __user *buf, @@ -513,7 +513,7 @@ static ssize_t ffs_ep0_read(struct file *file, char __user *buf, /* unlocks spinlock */ ret = __ffs_ep0_queue_wait(ffs, data, len); - if (likely(ret > 0) && unlikely(__copy_to_user(buf, data, len))) + if (likely(ret > 0) && unlikely(copy_to_user(buf, data, len))) ret = -EFAULT; goto done_mutex; @@ -3493,7 +3493,7 @@ static char *ffs_prepare_buffer(const char __user *buf, size_t len) if (unlikely(!data)) return ERR_PTR(-ENOMEM); - if (unlikely(__copy_from_user(data, buf, len))) { + if (unlikely(copy_from_user(data, buf, len))) { kfree(data); return ERR_PTR(-EFAULT); } diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 42acb45e1ab42..898a570319f17 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -370,6 +370,7 @@ static int f_midi_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (err) { ERROR(midi, "%s queue req: %d\n", midi->out_ep->name, err); + free_ep_req(midi->out_ep, req); } } @@ -545,7 +546,7 @@ static void f_midi_transmit(struct f_midi *midi, struct usb_request *req) } } - if (req->length > 0) { + if (req->length > 0 && ep->enabled) { int err; err = usb_ep_queue(ep, req, GFP_ATOMIC); diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 289ebca316d3f..ad8c9b05572d7 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -20,7 +20,7 @@ #define UVC_ATTR(prefix, cname, aname) \ static struct configfs_attribute prefix##attr_##cname = { \ .ca_name = __stringify(aname), \ - .ca_mode = S_IRUGO, \ + .ca_mode = S_IRUGO | S_IWUGO, \ .ca_owner = THIS_MODULE, \ .show = prefix##cname##_show, \ .store = prefix##cname##_store, \ diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c index 670ac0b12f008..001a3b74a993e 100644 --- a/drivers/usb/gadget/udc/pxa27x_udc.c +++ b/drivers/usb/gadget/udc/pxa27x_udc.c @@ -2536,6 +2536,9 @@ static int pxa_udc_suspend(struct platform_device *_dev, pm_message_t state) udc->pullup_resume = udc->pullup_on; dplus_pullup(udc, 0); + if (udc->driver) + udc->driver->disconnect(&udc->gadget); + return 0; } diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index 342ffd1401222..8c6e15bd6ff0b 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -473,6 +473,8 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev) if (!pdata) return -ENOMEM; + pdev->dev.platform_data = pdata; + if (!of_property_read_u32(np, "num-ports", &ports)) pdata->ports = ports; @@ -483,6 +485,7 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev) */ if (i >= pdata->ports) { pdata->vbus_pin[i] = -EINVAL; + pdata->overcurrent_pin[i] = -EINVAL; continue; } @@ -513,10 +516,8 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev) } at91_for_each_port(i) { - if (i >= pdata->ports) { - pdata->overcurrent_pin[i] = -EINVAL; - continue; - } + if (i >= pdata->ports) + break; pdata->overcurrent_pin[i] = of_get_named_gpio_flags(np, "atmel,oc-gpio", i, &flags); @@ -552,8 +553,6 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev) } } - pdev->dev.platform_data = pdata; - device_init_wakeup(&pdev->dev, 1); return usb_hcd_at91_probe(&ohci_at91_hc_driver, pdev); } diff --git a/drivers/usb/host/whci/qset.c b/drivers/usb/host/whci/qset.c index dc31c425ce017..9f1c0538b2112 100644 --- a/drivers/usb/host/whci/qset.c +++ b/drivers/usb/host/whci/qset.c @@ -377,6 +377,10 @@ static int qset_fill_page_list(struct whc *whc, struct whc_std *std, gfp_t mem_f if (std->pl_virt == NULL) return -ENOMEM; std->dma_addr = dma_map_single(whc->wusbhc.dev, std->pl_virt, pl_len, DMA_TO_DEVICE); + if (dma_mapping_error(whc->wusbhc.dev, std->dma_addr)) { + kfree(std->pl_virt); + return -EFAULT; + } for (p = 0; p < std->num_pointers; p++) { std->pl_virt[p].buf_ptr = cpu_to_le64(dma_addr); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 0230965fb78cf..f980c239eded9 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -733,8 +733,30 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, if ((raw_port_status & PORT_RESET) || !(raw_port_status & PORT_PE)) return 0xffffffff; - if (time_after_eq(jiffies, - bus_state->resume_done[wIndex])) { + /* did port event handler already start resume timing? */ + if (!bus_state->resume_done[wIndex]) { + /* If not, maybe we are in a host initated resume? */ + if (test_bit(wIndex, &bus_state->resuming_ports)) { + /* Host initated resume doesn't time the resume + * signalling using resume_done[]. + * It manually sets RESUME state, sleeps 20ms + * and sets U0 state. This should probably be + * changed, but not right now. + */ + } else { + /* port resume was discovered now and here, + * start resume timing + */ + unsigned long timeout = jiffies + + msecs_to_jiffies(USB_RESUME_TIMEOUT); + + set_bit(wIndex, &bus_state->resuming_ports); + bus_state->resume_done[wIndex] = timeout; + mod_timer(&hcd->rh_timer, timeout); + } + /* Has resume been signalled for USB_RESUME_TIME yet? */ + } else if (time_after_eq(jiffies, + bus_state->resume_done[wIndex])) { int time_left; xhci_dbg(xhci, "Resume USB2 port %d\n", @@ -775,13 +797,26 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, } else { /* * The resume has been signaling for less than - * 20ms. Report the port status as SUSPEND, - * let the usbcore check port status again - * and clear resume signaling later. + * USB_RESUME_TIME. Report the port status as SUSPEND, + * let the usbcore check port status again and clear + * resume signaling later. */ status |= USB_PORT_STAT_SUSPEND; } } + /* + * Clear stale usb2 resume signalling variables in case port changed + * state during resume signalling. For example on error + */ + if ((bus_state->resume_done[wIndex] || + test_bit(wIndex, &bus_state->resuming_ports)) && + (raw_port_status & PORT_PLS_MASK) != XDEV_U3 && + (raw_port_status & PORT_PLS_MASK) != XDEV_RESUME) { + bus_state->resume_done[wIndex] = 0; + clear_bit(wIndex, &bus_state->resuming_ports); + } + + if ((raw_port_status & PORT_PLS_MASK) == XDEV_U0 && (raw_port_status & PORT_POWER)) { if (bus_state->suspended_ports & (1 << wIndex)) { @@ -1115,6 +1150,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, if ((temp & PORT_PE) == 0) goto error; + set_bit(wIndex, &bus_state->resuming_ports); xhci_set_link_state(xhci, port_array, wIndex, XDEV_RESUME); spin_unlock_irqrestore(&xhci->lock, flags); @@ -1122,6 +1158,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, spin_lock_irqsave(&xhci->lock, flags); xhci_set_link_state(xhci, port_array, wIndex, XDEV_U0); + clear_bit(wIndex, &bus_state->resuming_ports); } bus_state->port_c_suspend |= 1 << wIndex; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 17f6897acde2a..c62109091d128 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -188,10 +188,14 @@ static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) 0xb7, 0x0c, 0x34, 0xac, 0x01, 0xe9, 0xbf, 0x45, 0xb7, 0xe6, 0x2b, 0x34, 0xec, 0x93, 0x1e, 0x23, }; - acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), intel_dsm_uuid, 3, 1, NULL); + union acpi_object *obj; + + obj = acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), intel_dsm_uuid, 3, 1, + NULL); + ACPI_FREE(obj); } #else - static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { } +static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { } #endif /* CONFIG_ACPI */ /* called during probe() after chip reset completes */ diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 6c5e8133cf87c..eeaa6c6bd5408 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1583,7 +1583,8 @@ static void handle_port_status(struct xhci_hcd *xhci, */ bogus_port_status = true; goto cleanup; - } else { + } else if (!test_bit(faked_port_index, + &bus_state->resuming_ports)) { xhci_dbg(xhci, "resume HS port %d\n", port_id); bus_state->resume_done[faked_port_index] = jiffies + msecs_to_jiffies(USB_RESUME_TIMEOUT); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index dfa44d3e8eee4..3f912705dcef9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4778,8 +4778,16 @@ int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, ctrl_ctx->add_flags |= cpu_to_le32(SLOT_FLAG); slot_ctx = xhci_get_slot_ctx(xhci, config_cmd->in_ctx); slot_ctx->dev_info |= cpu_to_le32(DEV_HUB); + /* + * refer to section 6.2.2: MTT should be 0 for full speed hub, + * but it may be already set to 1 when setup an xHCI virtual + * device, so clear it anyway. + */ if (tt->multi) slot_ctx->dev_info |= cpu_to_le32(DEV_MTT); + else if (hdev->speed == USB_SPEED_FULL) + slot_ctx->dev_info &= cpu_to_le32(~DEV_MTT); + if (xhci->hci_version > 0x95) { xhci_dbg(xhci, "xHCI version %x needs hub " "TT think time and number of ports\n", diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig index 1f2037bbeb0d1..45c83baf675df 100644 --- a/drivers/usb/musb/Kconfig +++ b/drivers/usb/musb/Kconfig @@ -159,7 +159,7 @@ config USB_TI_CPPI_DMA config USB_TI_CPPI41_DMA bool 'TI CPPI 4.1 (AM335x)' - depends on ARCH_OMAP + depends on ARCH_OMAP && DMADEVICES select TI_CPPI41 config USB_TUSB_OMAP_DMA diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 18cfc0a361cb3..ee9ff7028b926 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2017,7 +2017,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) /* We need musb_read/write functions initialized for PM */ pm_runtime_use_autosuspend(musb->controller); pm_runtime_set_autosuspend_delay(musb->controller, 200); - pm_runtime_irq_safe(musb->controller); pm_runtime_enable(musb->controller); /* The musb_platform_init() call: @@ -2095,6 +2094,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) #ifndef CONFIG_MUSB_PIO_ONLY if (!musb->ops->dma_init || !musb->ops->dma_exit) { dev_err(dev, "DMA controller not set\n"); + status = -ENODEV; goto fail2; } musb_dma_controller_create = musb->ops->dma_init; @@ -2218,6 +2218,12 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) pm_runtime_put(musb->controller); + /* + * For why this is currently needed, see commit 3e43a0725637 + * ("usb: musb: core: add pm_runtime_irq_safe()") + */ + pm_runtime_irq_safe(musb->controller); + return 0; fail5: diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 80eb991c2506c..0d19a6d61a71f 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -1506,7 +1506,6 @@ static int msm_otg_read_dt(struct platform_device *pdev, struct msm_otg *motg) { struct msm_otg_platform_data *pdata; struct extcon_dev *ext_id, *ext_vbus; - const struct of_device_id *id; struct device_node *node = pdev->dev.of_node; struct property *prop; int len, ret, words; @@ -1518,8 +1517,9 @@ static int msm_otg_read_dt(struct platform_device *pdev, struct msm_otg *motg) motg->pdata = pdata; - id = of_match_device(msm_otg_dt_match, &pdev->dev); - pdata->phy_type = (enum msm_usb_phy_type) id->data; + pdata->phy_type = (enum msm_usb_phy_type)of_device_get_match_data(&pdev->dev); + if (!pdata->phy_type) + return 1; motg->link_rst = devm_reset_control_get(&pdev->dev, "link"); if (IS_ERR(motg->link_rst)) diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c index b7536af777ab9..c2936dc48ca7b 100644 --- a/drivers/usb/phy/phy-mxs-usb.c +++ b/drivers/usb/phy/phy-mxs-usb.c @@ -143,12 +143,17 @@ static const struct mxs_phy_data imx6sx_phy_data = { .flags = MXS_PHY_DISCONNECT_LINE_WITHOUT_VBUS, }; +static const struct mxs_phy_data imx6ul_phy_data = { + .flags = MXS_PHY_DISCONNECT_LINE_WITHOUT_VBUS, +}; + static const struct of_device_id mxs_phy_dt_ids[] = { { .compatible = "fsl,imx6sx-usbphy", .data = &imx6sx_phy_data, }, { .compatible = "fsl,imx6sl-usbphy", .data = &imx6sl_phy_data, }, { .compatible = "fsl,imx6q-usbphy", .data = &imx6q_phy_data, }, { .compatible = "fsl,imx23-usbphy", .data = &imx23_phy_data, }, { .compatible = "fsl,vf610-usbphy", .data = &vf610_phy_data, }, + { .compatible = "fsl,imx6ul-usbphy", .data = &imx6ul_phy_data, }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, mxs_phy_dt_ids); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index de4f97d84a822..8f7a78e709759 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -131,7 +131,8 @@ static void __usbhsg_queue_pop(struct usbhsg_uep *uep, struct device *dev = usbhsg_gpriv_to_dev(gpriv); struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv); - dev_dbg(dev, "pipe %d : queue pop\n", usbhs_pipe_number(pipe)); + if (pipe) + dev_dbg(dev, "pipe %d : queue pop\n", usbhs_pipe_number(pipe)); ureq->req.status = status; spin_unlock(usbhs_priv_to_lock(priv)); @@ -685,7 +686,13 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req) struct usbhsg_request *ureq = usbhsg_req_to_ureq(req); struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep); - usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq)); + if (pipe) + usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq)); + + /* + * To dequeue a request, this driver should call the usbhsg_queue_pop() + * even if the pipe is NULL. + */ usbhsg_queue_pop(uep, ureq, -ECONNRESET); return 0; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index eac7ccaa3c859..7d4f51a32e66f 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -132,7 +132,6 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ - { USB_DEVICE(0x10C4, 0xEA80) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA71) }, /* Infinity GPS-MIC-1 Radio Monophone */ { USB_DEVICE(0x10C4, 0xF001) }, /* Elan Digital Systems USBscope50 */ { USB_DEVICE(0x10C4, 0xF002) }, /* Elan Digital Systems USBwave12 */ diff --git a/drivers/usb/serial/ipaq.c b/drivers/usb/serial/ipaq.c index f51a5d52c0eda..ec1b8f2c11837 100644 --- a/drivers/usb/serial/ipaq.c +++ b/drivers/usb/serial/ipaq.c @@ -531,7 +531,8 @@ static int ipaq_open(struct tty_struct *tty, * through. Since this has a reasonably high failure rate, we retry * several times. */ - while (retries--) { + while (retries) { + retries--; result = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), 0x22, 0x21, 0x1, 0, NULL, 0, 100); diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c index 3658662898fcb..a204782ae530e 100644 --- a/drivers/usb/serial/usb-serial-simple.c +++ b/drivers/usb/serial/usb-serial-simple.c @@ -53,6 +53,7 @@ DEVICE(funsoft, FUNSOFT_IDS); /* Infineon Flashloader driver */ #define FLASHLOADER_IDS() \ + { USB_DEVICE_INTERFACE_CLASS(0x058b, 0x0041, USB_CLASS_CDC_DATA) }, \ { USB_DEVICE(0x8087, 0x0716) } DEVICE(flashloader, FLASHLOADER_IDS); diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index e691516644360..5c66d3f7a6d07 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -796,6 +796,10 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_NO_REPORT_OPCODES) sdev->no_report_opcodes = 1; + /* A few buggy USB-ATA bridges don't understand FUA */ + if (devinfo->flags & US_FL_BROKEN_FUA) + sdev->broken_fua = 1; + scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 6b2479123de77..7ffe4209067bb 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1987,7 +1987,7 @@ UNUSUAL_DEV( 0x14cd, 0x6600, 0x0201, 0x0201, US_FL_IGNORE_RESIDUE ), /* Reported by Michael Büsch <m@bues.ch> */ -UNUSUAL_DEV( 0x152d, 0x0567, 0x0114, 0x0114, +UNUSUAL_DEV( 0x152d, 0x0567, 0x0114, 0x0116, "JMicron", "USB to ATA/ATAPI Bridge", USB_SC_DEVICE, USB_PR_DEVICE, NULL, diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index c85ea530085f1..ccc113e83d88e 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -132,7 +132,7 @@ UNUSUAL_DEV(0x152d, 0x0567, 0x0000, 0x9999, "JMicron", "JMS567", USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_NO_REPORT_OPCODES), + US_FL_BROKEN_FUA | US_FL_NO_REPORT_OPCODES), /* Reported-by: Hans de Goede <hdegoede@redhat.com> */ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index da6e2ce77495b..850d86ca685b2 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -31,21 +31,6 @@ menuconfig VFIO If you don't know what to do here, say N. -menuconfig VFIO_NOIOMMU - bool "VFIO No-IOMMU support" - depends on VFIO - help - VFIO is built on the ability to isolate devices using the IOMMU. - Only with an IOMMU can userspace access to DMA capable devices be - considered secure. VFIO No-IOMMU mode enables IOMMU groups for - devices without IOMMU backing for the purpose of re-using the VFIO - infrastructure in a non-secure mode. Use of this mode will result - in an unsupportable kernel and will therefore taint the kernel. - Device assignment to virtual machines is also not possible with - this mode since there is no IOMMU to provide DMA translation. - - If you don't know what to do here, say N. - source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "virt/lib/Kconfig" diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 32b88bd2c82c7..56bf6dbb93db7 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; - group = vfio_iommu_group_get(&pdev->dev); + group = iommu_group_get(&pdev->dev); if (!group) return -EINVAL; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) { - vfio_iommu_group_put(group, &pdev->dev); + iommu_group_put(group); return -ENOMEM; } @@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { - vfio_iommu_group_put(group, &pdev->dev); + iommu_group_put(group); kfree(vdev); return ret; } @@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; - vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); + iommu_group_put(pdev->dev.iommu_group); kfree(vdev); if (vfio_pci_is_vga(pdev)) { @@ -1035,7 +1035,7 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_CAN_RECOVER; } -static struct pci_error_handlers vfio_err_handlers = { +static const struct pci_error_handlers vfio_err_handlers = { .error_detected = vfio_pci_aer_err_detected, }; diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c index f1625dcfbb23d..b1cc3a7687844 100644 --- a/drivers/vfio/platform/vfio_platform.c +++ b/drivers/vfio/platform/vfio_platform.c @@ -92,7 +92,6 @@ static struct platform_driver vfio_platform_driver = { .remove = vfio_platform_remove, .driver = { .name = "vfio-platform", - .owner = THIS_MODULE, }, }; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index a1c50d6307920..418cdd9ba3f48 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -51,13 +51,10 @@ static vfio_platform_reset_fn_t vfio_platform_lookup_reset(const char *compat, static void vfio_platform_get_reset(struct vfio_platform_device *vdev) { - char modname[256]; - vdev->reset = vfio_platform_lookup_reset(vdev->compat, &vdev->reset_module); if (!vdev->reset) { - snprintf(modname, 256, "vfio-reset:%s", vdev->compat); - request_module(modname); + request_module("vfio-reset:%s", vdev->compat); vdev->reset = vfio_platform_lookup_reset(vdev->compat, &vdev->reset_module); } diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index de632da2e22f6..6070b793cbcb2 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -62,7 +62,6 @@ struct vfio_container { struct rw_semaphore group_lock; struct vfio_iommu_driver *iommu_driver; void *iommu_data; - bool noiommu; }; struct vfio_unbound_dev { @@ -85,7 +84,6 @@ struct vfio_group { struct list_head unbound_list; struct mutex unbound_lock; atomic_t opened; - bool noiommu; }; struct vfio_device { @@ -97,147 +95,6 @@ struct vfio_device { void *device_data; }; -#ifdef CONFIG_VFIO_NOIOMMU -static bool noiommu __read_mostly; -module_param_named(enable_unsafe_noiommu_support, - noiommu, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); -#endif - -/* - * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe - * and remove functions, any use cases other than acquiring the first - * reference for the purpose of calling vfio_add_group_dev() or removing - * that symmetric reference after vfio_del_group_dev() should use the raw - * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() - * removes the device from the dummy group and cannot be nested. - */ -struct iommu_group *vfio_iommu_group_get(struct device *dev) -{ - struct iommu_group *group; - int __maybe_unused ret; - - group = iommu_group_get(dev); - -#ifdef CONFIG_VFIO_NOIOMMU - /* - * With noiommu enabled, an IOMMU group will be created for a device - * that doesn't already have one and doesn't have an iommu_ops on their - * bus. We use iommu_present() again in the main code to detect these - * fake groups. - */ - if (group || !noiommu || iommu_present(dev->bus)) - return group; - - group = iommu_group_alloc(); - if (IS_ERR(group)) - return NULL; - - iommu_group_set_name(group, "vfio-noiommu"); - ret = iommu_group_add_device(group, dev); - iommu_group_put(group); - if (ret) - return NULL; - - /* - * Where to taint? At this point we've added an IOMMU group for a - * device that is not backed by iommu_ops, therefore any iommu_ - * callback using iommu_ops can legitimately Oops. So, while we may - * be about to give a DMA capable device to a user without IOMMU - * protection, which is clearly taint-worthy, let's go ahead and do - * it here. - */ - add_taint(TAINT_USER, LOCKDEP_STILL_OK); - dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); -#endif - - return group; -} -EXPORT_SYMBOL_GPL(vfio_iommu_group_get); - -void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) -{ -#ifdef CONFIG_VFIO_NOIOMMU - if (!iommu_present(dev->bus)) - iommu_group_remove_device(dev); -#endif - - iommu_group_put(group); -} -EXPORT_SYMBOL_GPL(vfio_iommu_group_put); - -#ifdef CONFIG_VFIO_NOIOMMU -static void *vfio_noiommu_open(unsigned long arg) -{ - if (arg != VFIO_NOIOMMU_IOMMU) - return ERR_PTR(-EINVAL); - if (!capable(CAP_SYS_RAWIO)) - return ERR_PTR(-EPERM); - - return NULL; -} - -static void vfio_noiommu_release(void *iommu_data) -{ -} - -static long vfio_noiommu_ioctl(void *iommu_data, - unsigned int cmd, unsigned long arg) -{ - if (cmd == VFIO_CHECK_EXTENSION) - return arg == VFIO_NOIOMMU_IOMMU ? 1 : 0; - - return -ENOTTY; -} - -static int vfio_iommu_present(struct device *dev, void *unused) -{ - return iommu_present(dev->bus) ? 1 : 0; -} - -static int vfio_noiommu_attach_group(void *iommu_data, - struct iommu_group *iommu_group) -{ - return iommu_group_for_each_dev(iommu_group, NULL, - vfio_iommu_present) ? -EINVAL : 0; -} - -static void vfio_noiommu_detach_group(void *iommu_data, - struct iommu_group *iommu_group) -{ -} - -static struct vfio_iommu_driver_ops vfio_noiommu_ops = { - .name = "vfio-noiommu", - .owner = THIS_MODULE, - .open = vfio_noiommu_open, - .release = vfio_noiommu_release, - .ioctl = vfio_noiommu_ioctl, - .attach_group = vfio_noiommu_attach_group, - .detach_group = vfio_noiommu_detach_group, -}; - -static struct vfio_iommu_driver vfio_noiommu_driver = { - .ops = &vfio_noiommu_ops, -}; - -/* - * Wrap IOMMU drivers, the noiommu driver is the one and only driver for - * noiommu groups (and thus containers) and not available for normal groups. - */ -#define vfio_for_each_iommu_driver(con, pos) \ - for (pos = con->noiommu ? &vfio_noiommu_driver : \ - list_first_entry(&vfio.iommu_drivers_list, \ - struct vfio_iommu_driver, vfio_next); \ - (con->noiommu ? pos != NULL : \ - &pos->vfio_next != &vfio.iommu_drivers_list); \ - pos = con->noiommu ? NULL : list_next_entry(pos, vfio_next)) -#else -#define vfio_for_each_iommu_driver(con, pos) \ - list_for_each_entry(pos, &vfio.iommu_drivers_list, vfio_next) -#endif - - /** * IOMMU driver registration */ @@ -342,8 +199,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, - bool noiommu) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) { struct vfio_group *group, *tmp; struct device *dev; @@ -361,7 +217,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; - group->noiommu = noiommu; group->nb.notifier_call = vfio_iommu_group_notifier; @@ -397,8 +252,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, dev = device_create(vfio.class, NULL, MKDEV(MAJOR(vfio.group_devt), minor), - group, "%s%d", noiommu ? "noiommu-" : "", - iommu_group_id(iommu_group)); + group, "%d", iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); @@ -682,7 +536,7 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev) return 0; /* TODO Prevent device auto probing */ - WARN("Device %s added to live group %d!\n", dev_name(dev), + WARN(1, "Device %s added to live group %d!\n", dev_name(dev), iommu_group_id(group->iommu_group)); return 0; @@ -786,8 +640,7 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group, - !iommu_present(dev->bus)); + group = vfio_create_group(iommu_group); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); @@ -999,7 +852,8 @@ static long vfio_ioctl_check_extension(struct vfio_container *container, */ if (!driver) { mutex_lock(&vfio.iommu_drivers_lock); - vfio_for_each_iommu_driver(container, driver) { + list_for_each_entry(driver, &vfio.iommu_drivers_list, + vfio_next) { if (!try_module_get(driver->ops->owner)) continue; @@ -1068,7 +922,7 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, } mutex_lock(&vfio.iommu_drivers_lock); - vfio_for_each_iommu_driver(container, driver) { + list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { void *data; if (!try_module_get(driver->ops->owner)) @@ -1333,9 +1187,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) - return -EPERM; - f = fdget(container_fd); if (!f.file) return -EBADF; @@ -1351,13 +1202,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) down_write(&container->group_lock); - /* Real groups and fake groups cannot mix */ - if (!list_empty(&container->group_list) && - container->noiommu != group->noiommu) { - ret = -EPERM; - goto unlock_out; - } - driver = container->iommu_driver; if (driver) { ret = driver->ops->attach_group(container->iommu_data, @@ -1367,7 +1211,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; - container->noiommu = group->noiommu; list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1398,9 +1241,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) - return -EPERM; - device = vfio_device_get_from_name(group, buf); if (!device) return -ENODEV; @@ -1443,10 +1283,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(ret, filep); - if (group->noiommu) - dev_warn(device->dev, "vfio-noiommu device opened by user " - "(%s:%d)\n", current->comm, task_pid_nr(current)); - return ret; } @@ -1535,11 +1371,6 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) { - vfio_group_put(group); - return -EPERM; - } - /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { @@ -1702,11 +1533,6 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) if (!atomic_inc_not_zero(&group->container_users)) return ERR_PTR(-EINVAL); - if (group->noiommu) { - atomic_dec(&group->container_users); - return ERR_PTR(-EPERM); - } - if (!group->container->iommu_driver || !vfio_group_viable(group)) { atomic_dec(&group->container_users); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index eec2f11809ff2..ad2146a9ab2d4 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -819,7 +819,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE); if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) || (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) || - (a.log_guest_addr & (sizeof(u64) - 1))) { + (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) { r = -EINVAL; break; } @@ -1369,7 +1369,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ if (unlikely(__get_user(ring_head, - &vq->avail->ring[last_avail_idx % vq->num]))) { + &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); @@ -1489,7 +1489,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, u16 old, new; int start; - start = vq->last_used_idx % vq->num; + start = vq->last_used_idx & (vq->num - 1); used = vq->used->ring + start; if (count == 1) { if (__put_user(heads[0].id, &used->id)) { @@ -1531,7 +1531,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, { int start, n, r; - start = vq->last_used_idx % vq->num; + start = vq->last_used_idx & (vq->num - 1); n = vq->num - start; if (n < count) { r = __vhost_add_used_n(vq, heads, n); diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index b335c1ae86251..fe00a07c122e6 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -479,7 +479,10 @@ static enum fsl_diu_monitor_port fsl_diu_name_to_port(const char *s) port = FSL_DIU_PORT_DLVDS; } - return diu_ops.valid_monitor_port(port); + if (diu_ops.valid_monitor_port) + port = diu_ops.valid_monitor_port(port); + + return port; } /* @@ -1915,6 +1918,14 @@ static int __init fsl_diu_init(void) #else monitor_port = fsl_diu_name_to_port(monitor_string); #endif + + /* + * Must to verify set_pixel_clock. If not implement on platform, + * then that means that there is no platform support for the DIU. + */ + if (!diu_ops.set_pixel_clock) + return -ENODEV; + pr_info("Freescale Display Interface Unit (DIU) framebuffer driver\n"); #ifdef CONFIG_NOT_COHERENT_CACHE diff --git a/drivers/video/fbdev/omap2/dss/venc.c b/drivers/video/fbdev/omap2/dss/venc.c index 99ca268c1cddf..d05a54922ba69 100644 --- a/drivers/video/fbdev/omap2/dss/venc.c +++ b/drivers/video/fbdev/omap2/dss/venc.c @@ -275,6 +275,12 @@ const struct omap_video_timings omap_dss_pal_timings = { .vbp = 41, .interlace = true, + + .hsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .vsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .data_pclk_edge = OMAPDSS_DRIVE_SIG_RISING_EDGE, + .de_level = OMAPDSS_SIG_ACTIVE_HIGH, + .sync_pclk_edge = OMAPDSS_DRIVE_SIG_FALLING_EDGE, }; EXPORT_SYMBOL(omap_dss_pal_timings); @@ -290,6 +296,12 @@ const struct omap_video_timings omap_dss_ntsc_timings = { .vbp = 31, .interlace = true, + + .hsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .vsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .data_pclk_edge = OMAPDSS_DRIVE_SIG_RISING_EDGE, + .de_level = OMAPDSS_SIG_ACTIVE_HIGH, + .sync_pclk_edge = OMAPDSS_DRIVE_SIG_FALLING_EDGE, }; EXPORT_SYMBOL(omap_dss_ntsc_timings); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index b1877d73fa563..7062bb0975a52 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -412,6 +412,7 @@ static int virtio_init(void) static void __exit virtio_exit(void) { bus_unregister(&virtio_bus); + ida_destroy(&virtio_index_ida); } core_initcall(virtio_init); module_exit(virtio_exit); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 096b857e7b75a..ee663c458b20a 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -80,6 +80,12 @@ struct vring_virtqueue { /* Last used index we've seen. */ u16 last_used_idx; + /* Last written value to avail->flags */ + u16 avail_flags_shadow; + + /* Last written value to avail->idx in guest byte order */ + u16 avail_idx_shadow; + /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); @@ -109,7 +115,7 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq, * otherwise virt_to_phys will give us bogus addresses in the * virtqueue. */ - gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH); + gfp &= ~__GFP_HIGHMEM; desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp); if (!desc) @@ -235,13 +241,14 @@ static inline int virtqueue_add(struct virtqueue *_vq, /* Put entry in available array (but don't update avail->idx until they * do sync). */ - avail = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) & (vq->vring.num - 1); + avail = vq->avail_idx_shadow & (vq->vring.num - 1); vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head); /* Descriptors and available array need to be set before we expose the * new available array entries. */ virtio_wmb(vq->weak_barriers); - vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) + 1); + vq->avail_idx_shadow++; + vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow); vq->num_added++; pr_debug("Added buffer head %i to %p\n", head, vq); @@ -354,8 +361,8 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq) * event. */ virtio_mb(vq->weak_barriers); - old = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->num_added; - new = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx); + old = vq->avail_idx_shadow - vq->num_added; + new = vq->avail_idx_shadow; vq->num_added = 0; #ifdef DEBUG @@ -510,7 +517,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) /* If we expect an interrupt for the next entry, tell host * by writing event index and flush out the write before * the read in the next get_buf call. */ - if (!(vq->vring.avail->flags & cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT))) { + if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx); virtio_mb(vq->weak_barriers); } @@ -537,7 +544,11 @@ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - vq->vring.avail->flags |= cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT); + if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { + vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow); + } + } EXPORT_SYMBOL_GPL(virtqueue_disable_cb); @@ -565,7 +576,10 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq) /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always do both to keep code simple. */ - vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT); + if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { + vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow); + } vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx); END_USE(vq); return last_used_idx; @@ -633,9 +647,12 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always do both to keep code simple. */ - vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT); + if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { + vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow); + } /* TODO: tune this threshold */ - bufs = (u16)(virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->last_used_idx) * 3 / 4; + bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4; vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs); virtio_mb(vq->weak_barriers); if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) { @@ -670,7 +687,8 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq) /* detach_buf clears data, so grab it now. */ buf = vq->data[i]; detach_buf(vq, i); - vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - 1); + vq->avail_idx_shadow--; + vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow); END_USE(vq); return buf; } @@ -735,6 +753,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, vq->weak_barriers = weak_barriers; vq->broken = false; vq->last_used_idx = 0; + vq->avail_flags_shadow = 0; + vq->avail_idx_shadow = 0; vq->num_added = 0; list_add_tail(&vq->vq.list, &vdev->vqs); #ifdef DEBUG @@ -746,8 +766,10 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); /* No callback? Tell other side not to bother us. */ - if (!callback) - vq->vring.avail->flags |= cpu_to_virtio16(vdev, VRING_AVAIL_F_NO_INTERRUPT); + if (!callback) { + vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow); + } /* Put everything in free lists. */ vq->free_head = 0; diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index e3e9e3d46d1bf..96a1b8da53715 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -281,7 +281,8 @@ static void handle_irq_for_port(unsigned port) static void consume_one_event(unsigned cpu, struct evtchn_fifo_control_block *control_block, - unsigned priority, unsigned long *ready) + unsigned priority, unsigned long *ready, + bool drop) { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; @@ -313,13 +314,17 @@ static void consume_one_event(unsigned cpu, if (head == 0) clear_bit(priority, ready); - if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) - handle_irq_for_port(port); + if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) { + if (unlikely(drop)) + pr_warn("Dropping pending event for port %u\n", port); + else + handle_irq_for_port(port); + } q->head[priority] = head; } -static void evtchn_fifo_handle_events(unsigned cpu) +static void __evtchn_fifo_handle_events(unsigned cpu, bool drop) { struct evtchn_fifo_control_block *control_block; unsigned long ready; @@ -331,11 +336,16 @@ static void evtchn_fifo_handle_events(unsigned cpu) while (ready) { q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES); - consume_one_event(cpu, control_block, q, &ready); + consume_one_event(cpu, control_block, q, &ready, drop); ready |= xchg(&control_block->ready, 0); } } +static void evtchn_fifo_handle_events(unsigned cpu) +{ + __evtchn_fifo_handle_events(cpu, false); +} + static void evtchn_fifo_resume(void) { unsigned cpu; @@ -420,6 +430,9 @@ static int evtchn_fifo_cpu_notification(struct notifier_block *self, if (!per_cpu(cpu_control_block, cpu)) ret = evtchn_fifo_alloc_control_block(cpu); break; + case CPU_DEAD: + __evtchn_fifo_handle_events(cpu, true); + break; default: break; } diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index 58e38d586f524..4d529f3e40df9 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -37,6 +37,7 @@ struct xen_pcibk_device { struct xen_pci_sharedinfo *sh_info; unsigned long flags; struct work_struct op_work; + struct xen_pci_op op; }; struct xen_pcibk_dev_data { diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index c4a0666de6f5e..73dafdc494aa8 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -70,6 +70,13 @@ static void xen_pcibk_control_isr(struct pci_dev *dev, int reset) enable ? "enable" : "disable"); if (enable) { + /* + * The MSI or MSI-X should not have an IRQ handler. Otherwise + * if the guest terminates we BUG_ON in free_msi_irqs. + */ + if (dev->msi_enabled || dev->msix_enabled) + goto out; + rc = request_irq(dev_data->irq, xen_pcibk_guest_interrupt, IRQF_SHARED, dev_data->irq_name, dev); @@ -144,7 +151,12 @@ int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev, if (unlikely(verbose_request)) printk(KERN_DEBUG DRV_NAME ": %s: enable MSI\n", pci_name(dev)); - status = pci_enable_msi(dev); + if (dev->msi_enabled) + status = -EALREADY; + else if (dev->msix_enabled) + status = -ENXIO; + else + status = pci_enable_msi(dev); if (status) { pr_warn_ratelimited("%s: error enabling MSI for guest %u: err %d\n", @@ -173,20 +185,23 @@ static int xen_pcibk_disable_msi(struct xen_pcibk_device *pdev, struct pci_dev *dev, struct xen_pci_op *op) { - struct xen_pcibk_dev_data *dev_data; - if (unlikely(verbose_request)) printk(KERN_DEBUG DRV_NAME ": %s: disable MSI\n", pci_name(dev)); - pci_disable_msi(dev); + if (dev->msi_enabled) { + struct xen_pcibk_dev_data *dev_data; + + pci_disable_msi(dev); + + dev_data = pci_get_drvdata(dev); + if (dev_data) + dev_data->ack_intr = 1; + } op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0; if (unlikely(verbose_request)) printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev), op->value); - dev_data = pci_get_drvdata(dev); - if (dev_data) - dev_data->ack_intr = 1; return 0; } @@ -197,13 +212,26 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, struct xen_pcibk_dev_data *dev_data; int i, result; struct msix_entry *entries; + u16 cmd; if (unlikely(verbose_request)) printk(KERN_DEBUG DRV_NAME ": %s: enable MSI-X\n", pci_name(dev)); + if (op->value > SH_INFO_MAX_VEC) return -EINVAL; + if (dev->msix_enabled) + return -EALREADY; + + /* + * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able + * to access the BARs where the MSI-X entries reside. + */ + pci_read_config_word(dev, PCI_COMMAND, &cmd); + if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY)) + return -ENXIO; + entries = kmalloc(op->value * sizeof(*entries), GFP_KERNEL); if (entries == NULL) return -ENOMEM; @@ -245,23 +273,27 @@ static int xen_pcibk_disable_msix(struct xen_pcibk_device *pdev, struct pci_dev *dev, struct xen_pci_op *op) { - struct xen_pcibk_dev_data *dev_data; if (unlikely(verbose_request)) printk(KERN_DEBUG DRV_NAME ": %s: disable MSI-X\n", pci_name(dev)); - pci_disable_msix(dev); + if (dev->msix_enabled) { + struct xen_pcibk_dev_data *dev_data; + + pci_disable_msix(dev); + + dev_data = pci_get_drvdata(dev); + if (dev_data) + dev_data->ack_intr = 1; + } /* * SR-IOV devices (which don't have any legacy IRQ) have * an undefined IRQ value of zero. */ op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0; if (unlikely(verbose_request)) - printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n", pci_name(dev), - op->value); - dev_data = pci_get_drvdata(dev); - if (dev_data) - dev_data->ack_intr = 1; + printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n", + pci_name(dev), op->value); return 0; } #endif @@ -298,9 +330,11 @@ void xen_pcibk_do_op(struct work_struct *data) container_of(data, struct xen_pcibk_device, op_work); struct pci_dev *dev; struct xen_pcibk_dev_data *dev_data = NULL; - struct xen_pci_op *op = &pdev->sh_info->op; + struct xen_pci_op *op = &pdev->op; int test_intx = 0; + *op = pdev->sh_info->op; + barrier(); dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn); if (dev == NULL) @@ -342,6 +376,17 @@ void xen_pcibk_do_op(struct work_struct *data) if ((dev_data->enable_intx != test_intx)) xen_pcibk_control_isr(dev, 0 /* no reset */); } + pdev->sh_info->op.err = op->err; + pdev->sh_info->op.value = op->value; +#ifdef CONFIG_PCI_MSI + if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) { + unsigned int i; + + for (i = 0; i < op->value; i++) + pdev->sh_info->op.msix_entries[i].vector = + op->msix_entries[i].vector; + } +#endif /* Tell the driver domain that we're done. */ wmb(); clear_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags); diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 98bc345f296ef..4843741e703a3 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -44,7 +44,6 @@ static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev) dev_dbg(&xdev->dev, "allocated pdev @ 0x%p\n", pdev); pdev->xdev = xdev; - dev_set_drvdata(&xdev->dev, pdev); mutex_init(&pdev->dev_lock); @@ -58,6 +57,9 @@ static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev) kfree(pdev); pdev = NULL; } + + dev_set_drvdata(&xdev->dev, pdev); + out: return pdev; } diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 43bcae852546a..ad4eb1024d1ff 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -726,7 +726,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) if (!pending_req) return 1; - ring_req = *RING_GET_REQUEST(ring, rc); + RING_COPY_REQUEST(ring, rc, &ring_req); ring->req_cons = ++rc; err = prepare_pending_reqs(info, &ring_req, pending_req); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 699941e906672..511078586fa13 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -451,9 +451,9 @@ void v9fs_evict_inode(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); - truncate_inode_pages_final(inode->i_mapping); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - filemap_fdatawrite(inode->i_mapping); + filemap_fdatawrite(&inode->i_data); v9fs_cache_inode_put_cookie(inode); /* clunk the fid stashed in writeback_fid */ diff --git a/fs/block_dev.c b/fs/block_dev.c index c25639e907bd2..44d4a1e9244e7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1523,11 +1523,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); kill_bdev(bdev); + + bdev_write_inode(bdev); /* - * ->release can cause the queue to disappear, so flush all - * dirty data before. + * Detaching bdev inode from its wb in __destroy_inode() + * is too late: the queue which embeds its bdi (along with + * root wb) can be gone as soon as we put_disk() below. */ - bdev_write_inode(bdev); + inode_detach_wb(bdev->bd_inode); } if (bdev->bd_contains == bdev) { if (disk->fops->release) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4b89680a19233..c4661db2b72ae 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10480,11 +10480,15 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * until transaction commit to do the actual discard. */ if (trimming) { - WARN_ON(!list_empty(&block_group->bg_list)); - spin_lock(&trans->transaction->deleted_bgs_lock); + spin_lock(&fs_info->unused_bgs_lock); + /* + * A concurrent scrub might have added us to the list + * fs_info->unused_bgs, so use a list_move operation + * to add the block group to the deleted_bgs list. + */ list_move(&block_group->bg_list, &trans->transaction->deleted_bgs); - spin_unlock(&trans->transaction->deleted_bgs_lock); + spin_unlock(&fs_info->unused_bgs_lock); btrfs_get_block_group(block_group); } end_trans: diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 72e73461c0643..0f09526aa7d9d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1291,7 +1291,8 @@ out: * on error we return an unlocked page and the error value * on success we return a locked page and 0 */ -static int prepare_uptodate_page(struct page *page, u64 pos, +static int prepare_uptodate_page(struct inode *inode, + struct page *page, u64 pos, bool force_uptodate) { int ret = 0; @@ -1306,6 +1307,10 @@ static int prepare_uptodate_page(struct page *page, u64 pos, unlock_page(page); return -EIO; } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + return -EAGAIN; + } } return 0; } @@ -1324,6 +1329,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages, int faili; for (i = 0; i < num_pages; i++) { +again: pages[i] = find_or_create_page(inode->i_mapping, index + i, mask | __GFP_WRITE); if (!pages[i]) { @@ -1333,13 +1339,17 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages, } if (i == 0) - err = prepare_uptodate_page(pages[i], pos, + err = prepare_uptodate_page(inode, pages[i], pos, force_uptodate); - if (i == num_pages - 1) - err = prepare_uptodate_page(pages[i], + if (!err && i == num_pages - 1) + err = prepare_uptodate_page(inode, pages[i], pos + write_bytes, false); if (err) { page_cache_release(pages[i]); + if (err == -EAGAIN) { + err = 0; + goto again; + } faili = i - 1; goto fail; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 85a1f8621b51f..cfe99bec49ded 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -891,7 +891,7 @@ out: spin_unlock(&block_group->lock); ret = 0; - btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now", + btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuilding it now", block_group->key.objectid); } @@ -2972,7 +2972,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, u64 cont1_bytes, u64 min_bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; - struct btrfs_free_space *entry; + struct btrfs_free_space *entry = NULL; int ret = -ENOSPC; u64 bitmap_offset = offset_to_bitmap(ctl, offset); @@ -2983,8 +2983,10 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, * The bitmap that covers offset won't be in the list unless offset * is just its start offset. */ - entry = list_first_entry(bitmaps, struct btrfs_free_space, list); - if (entry->offset != bitmap_offset) { + if (!list_empty(bitmaps)) + entry = list_first_entry(bitmaps, struct btrfs_free_space, list); + + if (!entry || entry->offset != bitmap_offset) { entry = tree_search_offset(ctl, bitmap_offset, 1, 0); if (entry && list_empty(&entry->list)) list_add(&entry->list, bitmaps); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3367a3c6f214f..be8eae80ff657 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -274,7 +274,6 @@ loop: cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); - spin_lock_init(&cur_trans->deleted_bgs_lock); spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 0da21ca9b3fb3..64c8221b6165b 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -77,8 +77,8 @@ struct btrfs_transaction { */ struct mutex cache_write_mutex; spinlock_t dirty_bgs_lock; + /* Protected by spin lock fs_info->unused_bgs_lock. */ struct list_head deleted_bgs; - spinlock_t deleted_bgs_lock; spinlock_t dropped_roots_lock; struct btrfs_delayed_ref_root delayed_refs; int aborted; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4564522066099..a23399e8e3aba 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3548,12 +3548,11 @@ again: ret = btrfs_force_chunk_alloc(trans, chunk_root, BTRFS_BLOCK_GROUP_DATA); + btrfs_end_transaction(trans, chunk_root); if (ret < 0) { mutex_unlock(&fs_info->delete_unused_bgs_mutex); goto error; } - - btrfs_end_transaction(trans, chunk_root); chunk_reserved = 1; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 6b66dd5d15408..a329f5ba35aad 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1831,11 +1831,11 @@ cifs_invalidate_mapping(struct inode *inode) * @word: long word containing the bit lock */ static int -cifs_wait_bit_killable(struct wait_bit_key *key) +cifs_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } diff --git a/fs/direct-io.c b/fs/direct-io.c index 1c75a3a07f8f0..602e8441bc0fb 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1175,6 +1175,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, if (dio->flags & DIO_LOCKING) mutex_unlock(&inode->i_mutex); kmem_cache_free(dio_cache, dio); + retval = 0; goto out; } diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 73c64daa0f551..60f03b78914e3 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate); return page; } else { diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index af06830bfc00c..1a0835073663f 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -389,7 +389,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; struct bio *bio; - ext4_lblk_t lblk = ex->ee_block; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); ext4_fsblk_t pblk = ext4_ext_pblock(ex); unsigned int len = ext4_ext_get_actual_len(ex); int ret, err = 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 750063f7a50c6..cc7ca4e87144a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -26,6 +26,7 @@ #include <linux/seqlock.h> #include <linux/mutex.h> #include <linux/timer.h> +#include <linux/version.h> #include <linux/wait.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> @@ -727,19 +728,55 @@ struct move_extent { <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ +/* + * We use an encoding that preserves the times for extra epoch "00": + * + * extra msb of adjust for signed + * epoch 32-bit 32-bit tv_sec to + * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range + * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31 + * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19 + * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07 + * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25 + * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16 + * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04 + * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22 + * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10 + * + * Note that previous versions of the kernel on 64-bit systems would + * incorrectly use extra epoch bits 1,1 for dates between 1901 and + * 1970. e2fsck will correct this, assuming that it is run on the + * affected filesystem before 2242. + */ + static inline __le32 ext4_encode_extra_time(struct timespec *time) { - return cpu_to_le32((sizeof(time->tv_sec) > 4 ? - (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) | - ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK)); + u32 extra = sizeof(time->tv_sec) > 4 ? + ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0; + return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS)); } static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) { - if (sizeof(time->tv_sec) > 4) - time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) - << 32; - time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; + if (unlikely(sizeof(time->tv_sec) > 4 && + (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) { +#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0) + /* Handle legacy encoding of pre-1970 dates with epoch + * bits 1,1. We assume that by kernel version 4.20, + * everyone will have run fsck over the affected + * filesystems to correct the problem. (This + * backwards compatibility may be removed before this + * time, at the discretion of the ext4 developers.) + */ + u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK; + if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0) + extra_bits = 0; + time->tv_sec += extra_bits << 32; +#else + time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; +#endif + } + time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; } #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index abe2401ce4056..e8e7af62ac95f 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -52,7 +52,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Symlink is encrypted */ sd = (struct ext4_encrypted_symlink_data *)caddr; cstr.name = sd->encrypted_path; - cstr.len = le32_to_cpu(sd->len); + cstr.len = le16_to_cpu(sd->len); if ((cstr.len + sizeof(struct ext4_encrypted_symlink_data) - 1) > max_size) { diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 1b57c72f4a009..1420a3c614afb 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \ return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \ } \ \ -const struct file_operations ext4_seq_##name##_fops = { \ +static const struct file_operations ext4_seq_##name##_fops = { \ .owner = THIS_MODULE, \ .open = name##_open, \ .read = seq_read, \ diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index eae2c11268bcb..8e3ee1936c7e3 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -549,6 +549,8 @@ static int cuse_channel_release(struct inode *inode, struct file *file) unregister_chrdev_region(cc->cdev->dev, 1); cdev_del(cc->cdev); } + /* Base reference is now owned by "fud" */ + fuse_conn_put(&cc->fc); rc = fuse_dev_release(inode, file); /* puts the base reference */ diff --git a/fs/fuse/file.c b/fs/fuse/file.c index e0faf8f2c868a..570ca4053c805 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1049,6 +1049,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); + iov_iter_advance(ii, tmp); if (!tmp) { unlock_page(page); page_cache_release(page); @@ -1061,7 +1062,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, req->page_descs[req->num_pages].length = tmp; req->num_pages++; - iov_iter_advance(ii, tmp); count += tmp; pos += tmp; offset += tmp; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 89463eee67914..ca181e81c7655 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1009,7 +1009,8 @@ out: } /* Fast check whether buffer is already attached to the required transaction */ -static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) +static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, + bool undo) { struct journal_head *jh; bool ret = false; @@ -1036,6 +1037,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) jh = READ_ONCE(bh->b_private); if (!jh) goto out; + /* For undo access buffer must have data copied */ + if (undo && !jh->b_committed_data) + goto out; if (jh->b_transaction != handle->h_transaction && jh->b_next_transaction != handle->h_transaction) goto out; @@ -1073,7 +1077,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int rc; - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, false)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -1210,7 +1214,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) char *committed_data = NULL; JBUFFER_TRACE(jh, "entry"); - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -2152,6 +2156,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, if (!buffer_dirty(bh)) { /* bdflush has written it. We can drop it now */ + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } @@ -2181,6 +2186,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, /* The orphan record's transaction has * committed. We can cleanse this buffer */ clear_buffer_jbddirty(bh); + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } } diff --git a/fs/namei.c b/fs/namei.c index d84d7c7515fc4..0c3974cd3ecd5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1996,7 +1996,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; nd->depth = 0; - nd->total_link_count = 0; if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index beac58b0e09cb..646cdac73488e 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -78,8 +78,7 @@ static __be32 *read_buf(struct xdr_stream *xdr, int nbytes) p = xdr_inline_decode(xdr, nbytes); if (unlikely(p == NULL)) - printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed " - "or truncated request.\n"); + printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n"); return p; } @@ -890,7 +889,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r struct cb_compound_hdr_arg hdr_arg = { 0 }; struct cb_compound_hdr_res hdr_res = { NULL }; struct xdr_stream xdr_in, xdr_out; - struct xdr_buf *rq_arg = &rqstp->rq_arg; __be32 *p, status; struct cb_process_state cps = { .drc_status = 0, @@ -902,8 +900,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r dprintk("%s: start\n", __func__); - rq_arg->len = rq_arg->head[0].iov_len + rq_arg->page_len; - xdr_init_decode(&xdr_in, rq_arg, rq_arg->head[0].iov_base); + xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base); p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len); xdr_init_encode(&xdr_out, &rqstp->rq_res, p); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 31b0a52223a73..c7e8b87da5b24 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -75,11 +75,11 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks * @word: long word containing the bit lock */ -int nfs_wait_bit_killable(struct wait_bit_key *key) +int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 56cfde26fb9ce..9dea85f7f918e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -379,7 +379,7 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); -extern int nfs_wait_bit_killable(struct wait_bit_key *key); +extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); /* super.c */ extern const struct super_operations nfs_sops; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 5c0c6b58157f9..9aebffb405059 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate); return page; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index fe3ddd20ff890..452a011ba0d8a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -129,7 +129,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) set_bit(NFS_IO_INPROGRESS, &c->flags); if (atomic_read(&c->io_count) == 0) break; - ret = nfs_wait_bit_killable(&q.key); + ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE); } while (atomic_read(&c->io_count) != 0 && !ret); finish_wait(wq, &q.wait); return ret; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5a8ae2125b508..bec0384499f76 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1466,11 +1466,11 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, } /* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */ -static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key) +static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key, int mode) { if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags)) return 1; - return nfs_wait_bit_killable(key); + return nfs_wait_bit_killable(key, mode); } static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 9ffef06b30d51..c9d6c715c0fb7 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -616,6 +616,7 @@ nfsd4_cb_layout_prepare(struct nfsd4_callback *cb) mutex_lock(&ls->ls_mutex); nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid); + mutex_unlock(&ls->ls_mutex); } static int @@ -659,7 +660,6 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) trace_layout_recall_release(&ls->ls_stid.sc_stateid); - mutex_unlock(&ls->ls_mutex); nfsd4_return_all_layouts(ls, &reaplist); nfsd4_free_layouts(&reaplist); nfs4_put_stid(&ls->ls_stid); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index ce38b4ccc9ab6..84f2f8079466a 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2843,6 +2843,8 @@ again: res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY; if (!ret) BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING)); + else + res->migration_pending = 0; spin_unlock(&res->spinlock); /* diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index 652ece4a9d9e2..d56f0079b8580 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -67,7 +67,10 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, */ locks_lock_file_wait(file, - &(struct file_lock){.fl_type = F_UNLCK}); + &(struct file_lock) { + .fl_type = F_UNLCK, + .fl_flags = FL_FLOCK + }); ocfs2_file_unlock(file); } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index a03f6f433075c..3123408da9352 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -367,13 +367,11 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = posix_acl_create(dir, &mode, &default_acl, &acl); + status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (status) { mlog_errno(status); goto leave; } - /* update inode->i_mode after mask with "umask". */ - inode->i_mode = mode; handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index d5da6f6241428..79b8021302b3e 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -54,11 +54,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode, struct ocfs2_group_desc *gd, u16 cl_cpg, + u16 old_bg_clusters, int set) { int i; u16 backups = 0; - u32 cluster; + u32 cluster, lgd_cluster; u64 blkno, gd_blkno, lgd_blkno = le64_to_cpu(gd->bg_blkno); for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) { @@ -71,6 +72,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode, else if (gd_blkno > lgd_blkno) break; + /* check if already done backup super */ + lgd_cluster = ocfs2_blocks_to_clusters(inode->i_sb, lgd_blkno); + lgd_cluster += old_bg_clusters; + if (lgd_cluster >= cluster) + continue; + if (set) ocfs2_set_bit(cluster % cl_cpg, (unsigned long *)gd->bg_bitmap); @@ -99,6 +106,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, u16 chain, num_bits, backups = 0; u16 cl_bpc = le16_to_cpu(cl->cl_bpc); u16 cl_cpg = le16_to_cpu(cl->cl_cpg); + u16 old_bg_clusters; trace_ocfs2_update_last_group_and_inode(new_clusters, first_new_cluster); @@ -112,6 +120,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, group = (struct ocfs2_group_desc *)group_bh->b_data; + old_bg_clusters = le16_to_cpu(group->bg_bits) / cl_bpc; /* update the group first. */ num_bits = new_clusters * cl_bpc; le16_add_cpu(&group->bg_bits, num_bits); @@ -125,7 +134,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, OCFS2_FEATURE_COMPAT_BACKUP_SB)) { backups = ocfs2_calc_new_backup_super(bm_inode, group, - cl_cpg, 1); + cl_cpg, old_bg_clusters, 1); le16_add_cpu(&group->bg_free_bits_count, -1 * backups); } @@ -163,7 +172,7 @@ out_rollback: if (ret < 0) { ocfs2_calc_new_backup_super(bm_inode, group, - cl_cpg, 0); + cl_cpg, old_bg_clusters, 0); le16_add_cpu(&group->bg_free_bits_count, backups); le16_add_cpu(&group->bg_bits, -1 * num_bits); le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 871fcb67be974..0a8983492d917 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -195,8 +195,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, struct dentry *dentry, struct path *lowerpath, - struct kstat *stat, struct iattr *attr, - const char *link) + struct kstat *stat, const char *link) { struct inode *wdir = workdir->d_inode; struct inode *udir = upperdir->d_inode; @@ -240,8 +239,6 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, mutex_lock(&newdentry->d_inode->i_mutex); err = ovl_set_attr(newdentry, stat); - if (!err && attr) - err = notify_change(newdentry, attr, NULL); mutex_unlock(&newdentry->d_inode->i_mutex); if (err) goto out_cleanup; @@ -286,8 +283,7 @@ out_cleanup: * that point the file will have already been copied up anyway. */ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, - struct path *lowerpath, struct kstat *stat, - struct iattr *attr) + struct path *lowerpath, struct kstat *stat) { struct dentry *workdir = ovl_workdir(dentry); int err; @@ -345,26 +341,19 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, } upperdentry = ovl_dentry_upper(dentry); if (upperdentry) { - unlock_rename(workdir, upperdir); + /* Raced with another copy-up? Nothing to do, then... */ err = 0; - /* Raced with another copy-up? Do the setattr here */ - if (attr) { - mutex_lock(&upperdentry->d_inode->i_mutex); - err = notify_change(upperdentry, attr, NULL); - mutex_unlock(&upperdentry->d_inode->i_mutex); - } - goto out_put_cred; + goto out_unlock; } err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, - stat, attr, link); + stat, link); if (!err) { /* Restore timestamps on parent (best effort) */ ovl_set_timestamps(upperdir, &pstat); } out_unlock: unlock_rename(workdir, upperdir); -out_put_cred: revert_creds(old_cred); put_cred(override_cred); @@ -406,7 +395,7 @@ int ovl_copy_up(struct dentry *dentry) ovl_path_lower(next, &lowerpath); err = vfs_getattr(&lowerpath, &stat); if (!err) - err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL); + err = ovl_copy_up_one(parent, next, &lowerpath, &stat); dput(parent); dput(next); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index ec0c2a050043a..4060ffde87225 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -12,8 +12,7 @@ #include <linux/xattr.h> #include "overlayfs.h" -static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, - bool no_data) +static int ovl_copy_up_truncate(struct dentry *dentry) { int err; struct dentry *parent; @@ -30,10 +29,8 @@ static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, if (err) goto out_dput_parent; - if (no_data) - stat.size = 0; - - err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr); + stat.size = 0; + err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat); out_dput_parent: dput(parent); @@ -49,13 +46,13 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) if (err) goto out; - upperdentry = ovl_dentry_upper(dentry); - if (upperdentry) { + err = ovl_copy_up(dentry); + if (!err) { + upperdentry = ovl_dentry_upper(dentry); + mutex_lock(&upperdentry->d_inode->i_mutex); err = notify_change(upperdentry, attr, NULL); mutex_unlock(&upperdentry->d_inode->i_mutex); - } else { - err = ovl_copy_up_last(dentry, attr, false); } ovl_drop_write(dentry); out: @@ -353,7 +350,7 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) return ERR_PTR(err); if (file_flags & O_TRUNC) - err = ovl_copy_up_last(dentry, NULL, true); + err = ovl_copy_up_truncate(dentry); else err = ovl_copy_up(dentry); ovl_drop_write(dentry); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index ea5a40b06e3ad..e17154aeaae47 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -194,7 +194,6 @@ void ovl_cleanup(struct inode *dir, struct dentry *dentry); /* copy_up.c */ int ovl_copy_up(struct dentry *dentry); int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, - struct path *lowerpath, struct kstat *stat, - struct iattr *attr); + struct path *lowerpath, struct kstat *stat); int ovl_copy_xattr(struct dentry *old, struct dentry *new); int ovl_set_attr(struct dentry *upper, struct kstat *stat); diff --git a/fs/proc/base.c b/fs/proc/base.c index bd3e9e68125b8..4bd5d3118acd4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2494,6 +2494,7 @@ static ssize_t proc_coredump_filter_write(struct file *file, mm = get_task_mm(task); if (!mm) goto out_no_mm; + ret = 0; for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { if (val & mask) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index db284bff29dcc..9dbb739cafa0c 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -5,7 +5,7 @@ * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * - * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright 2011 Red Hat, Inc., Peter Zijlstra * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 0b921ae06cd83..0a271ca1f7c7e 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -309,6 +309,11 @@ struct drm_file { unsigned universal_planes:1; /* true if client understands atomic properties */ unsigned atomic:1; + /* + * This client is allowed to gain master privileges for @master. + * Protected by struct drm_device::master_mutex. + */ + unsigned allowed_master:1; struct pid *pid; kuid_t uid; @@ -910,6 +915,7 @@ extern int drm_open(struct inode *inode, struct file *filp); extern ssize_t drm_read(struct file *filp, char __user *buffer, size_t count, loff_t *offset); extern int drm_release(struct inode *inode, struct file *filp); +extern int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv); /* Mapping support (drm_vm.h) */ extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait); @@ -947,6 +953,10 @@ extern void drm_send_vblank_event(struct drm_device *dev, unsigned int pipe, struct drm_pending_vblank_event *e); extern void drm_crtc_send_vblank_event(struct drm_crtc *crtc, struct drm_pending_vblank_event *e); +extern void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe, + struct drm_pending_vblank_event *e); +extern void drm_crtc_arm_vblank_event(struct drm_crtc *crtc, + struct drm_pending_vblank_event *e); extern bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe); extern bool drm_crtc_handle_vblank(struct drm_crtc *crtc); extern int drm_vblank_get(struct drm_device *dev, unsigned int pipe); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 0548339399953..1991aea2ec4cf 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -870,8 +870,8 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, } static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, - const char *name, const char *cells_name, - size_t index, struct acpi_reference_args *args) + const char *name, size_t index, + struct acpi_reference_args *args) { return -ENXIO; } diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2b8ed123ad36b..defeaac0745f1 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift) */ static inline __u32 rol32(__u32 word, unsigned int shift) { - return (word << shift) | (word >> (32 - shift)); + return (word << shift) | (word >> ((-shift) & 31)); } /** diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c06f8eaa42ff9..c70e3588a48c7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -254,6 +254,7 @@ struct queue_limits { unsigned long virt_boundary_mask; unsigned int max_hw_sectors; + unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; @@ -796,6 +797,7 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int blk_queue_enter(struct request_queue *q, gfp_t gfp); extern void blk_queue_exit(struct request_queue *q); extern void blk_start_queue(struct request_queue *q); +extern void blk_start_queue_async(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); @@ -959,7 +961,6 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9dc226345e4e1..e5f4164cbd993 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -90,7 +90,6 @@ enum { */ struct cgroup_file { /* do not access any fields from outside cgroup core */ - struct list_head node; /* anchored at css->files */ struct kernfs_node *kn; }; @@ -134,9 +133,6 @@ struct cgroup_subsys_state { */ u64 serial_nr; - /* all cgroup_files associated with this css */ - struct list_head files; - /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -440,12 +436,9 @@ struct cgroup_subsys { void (*css_reset)(struct cgroup_subsys_state *css); void (*css_e_css_changed)(struct cgroup_subsys_state *css); - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); @@ -616,7 +609,7 @@ static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = { .val = READ_ONCE(skcd->val) }; + struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; if (sock_cgroup_prioidx(&skcd_buf) == prioidx) return; @@ -633,7 +626,7 @@ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = { .val = READ_ONCE(skcd->val) }; + struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; if (sock_cgroup_classid(&skcd_buf) == classid) return; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index a8ba1ea0ea5a2..322a284827459 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -89,6 +89,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); +void cgroup_file_notify(struct cgroup_file *cfile); char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); @@ -120,8 +121,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it); @@ -236,30 +239,39 @@ void css_task_iter_end(struct css_task_iter *it); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor + * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple - * processes. When there are multiple tasks in @tset, if a task of a - * process is in @tset, all tasks of the process are in @tset. Also, all - * are guaranteed to share the same source and destination csses. + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor + * @dst_css: the destination css * @tset: takset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ -#define cgroup_taskset_for_each_leader(leader, tset) \ - for ((leader) = cgroup_taskset_first((tset)); (leader); \ - (leader) = cgroup_taskset_next((tset))) \ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else @@ -539,19 +551,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -/** - * cgroup_file_notify - generate a file modified event for a cgroup_file - * @cfile: target cgroup_file - * - * @cfile must have been obtained by setting cftype->file_offset. - */ -static inline void cgroup_file_notify(struct cgroup_file *cfile) -{ - /* might not have been created due to one of the CFTYPE selector flags */ - if (cfile->kn) - kernfs_notify(cfile->kn); -} - #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ef4c5b1a860f5..177c7680c1a8a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -77,6 +77,7 @@ struct cpufreq_policy { unsigned int suspend_freq; /* freq to set during suspend */ unsigned int policy; /* see above */ + unsigned int last_policy; /* policy before unplug */ struct cpufreq_governor *governor; /* see below */ void *governor_data; bool governor_enabled; /* governor start/stop flag */ diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 7be22da321f38..a4cf57cd0f751 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -29,7 +29,11 @@ /* A few generic types ... taken from ses-2 */ enum enclosure_component_type { ENCLOSURE_COMPONENT_DEVICE = 0x01, + ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS = 0x07, + ENCLOSURE_COMPONENT_SCSI_TARGET_PORT = 0x14, + ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT = 0x15, ENCLOSURE_COMPONENT_ARRAY_DEVICE = 0x17, + ENCLOSURE_COMPONENT_SAS_EXPANDER = 0x18, }; /* ses-2 common element status */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 4165e9ac9e36a..294c3cdf07b3f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -447,6 +447,8 @@ void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); +int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 05f5879821b81..a5f6ce6b578c7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -621,7 +621,7 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 0e707f0c1a3ed..7c27fa1030e87 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -3,6 +3,7 @@ #include <uapi/linux/inet_diag.h> +struct net; struct sock; struct inet_hashinfo; struct nlattr; @@ -23,6 +24,10 @@ struct inet_diag_handler { void (*idiag_get_info)(struct sock *sk, struct inet_diag_msg *r, void *info); + + int (*destroy)(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req); + __u16 idiag_type; __u16 idiag_info_size; }; @@ -41,6 +46,10 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req); +struct sock *inet_diag_find_one_icsk(struct net *net, + struct inet_hashinfo *hashinfo, + const struct inet_diag_req_v2 *req); + int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); extern int inet_diag_register(const struct inet_diag_handler *handler); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index c9ae0c6ec0505..d5d798b35c1f6 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -330,6 +330,7 @@ struct rdists { }; struct irq_domain; +struct device_node; int its_cpu_init(void); int its_init(struct device_node *node, struct rdists *rdists, struct irq_domain *domain); diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8dde55974f186..0536524bb9eb6 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -5,7 +5,7 @@ * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> - * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index d0a1f99e24e3e..4894c6888bc6c 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -25,7 +25,7 @@ #ifdef CONFIG_DEBUG_KMEMLEAK -extern void kmemleak_init(void) __ref; +extern void kmemleak_init(void) __init; extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, diff --git a/include/linux/libata.h b/include/linux/libata.h index 83577f8fd15bc..600c1e0626a5f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -210,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ ATA_FLAG_PIO_LBA48 = (1 << 8), /* Host DMA engine is LBA28 only */ diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index c6916aec43b66..034117b3be5f7 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -50,9 +50,16 @@ enum { NVM_IO_DUAL_ACCESS = 0x1, NVM_IO_QUAD_ACCESS = 0x2, + /* NAND Access Modes */ NVM_IO_SUSPEND = 0x80, NVM_IO_SLC_MODE = 0x100, NVM_IO_SCRAMBLE_DISABLE = 0x200, + + /* Block Types */ + NVM_BLK_T_FREE = 0x0, + NVM_BLK_T_BAD = 0x1, + NVM_BLK_T_DEV = 0x2, + NVM_BLK_T_HOST = 0x4, }; struct nvm_id_group { @@ -176,17 +183,17 @@ struct nvm_block; typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *); -typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *); -typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32, +typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *); +typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, nvm_l2p_update_fn *, void *); typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int, nvm_bb_update_fn *, void *); -typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int); -typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *); -typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *); -typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *); +typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int); +typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *); +typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); typedef void (nvm_destroy_dma_pool_fn)(void *); -typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t, +typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, dma_addr_t *); typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 70400dc7660f7..c57e424d914b7 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -2,7 +2,7 @@ * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.txt for more details. */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7501626ab5293..d3133be12d922 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -427,6 +427,17 @@ enum { }; enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX4_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + +enum { MLX4_DEV_PMC_SUBTYPE_GUID_INFO = 0x14, MLX4_DEV_PMC_SUBTYPE_PORT_INFO = 0x15, MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE = 0x16, diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 7d3a85faefb73..df2f79ef3cac9 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -443,9 +443,12 @@ struct mlx5_init_seg { __be32 rsvd1[120]; __be32 initializing; struct health_buffer health; - __be32 rsvd2[884]; + __be32 rsvd2[880]; + __be32 internal_timer_h; + __be32 internal_timer_l; + __be32 rsrv3[2]; __be32 health_counter; - __be32 rsvd3[1019]; + __be32 rsvd4[1019]; __be64 ieee1588_clk; __be32 ieee1588_clk_type; __be32 clr_intx; @@ -601,7 +604,8 @@ struct mlx5_cqe64 { __be32 imm_inval_pkey; u8 rsvd40[4]; __be32 byte_cnt; - __be64 timestamp; + __be32 timestamp_h; + __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; u8 signature; @@ -623,6 +627,16 @@ static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe) return !!(cqe->l4_hdr_type_etc & 0x1); } +static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe) +{ + u32 hi, lo; + + hi = be32_to_cpu(cqe->timestamp_h); + lo = be32_to_cpu(cqe->timestamp_l); + + return (u64)lo | ((u64)hi << 32); +} + enum { CQE_L4_HDR_TYPE_NONE = 0x0, CQE_L4_HDR_TYPE_TCP_NO_ACK = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ac098b6b97bf9..2fd7019f69dbf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -502,6 +502,8 @@ struct mlx5_priv { struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; unsigned long pci_dev_data; + struct mlx5_flow_root_namespace *root_ns; + struct mlx5_flow_root_namespace *fdb_root_ns; }; enum mlx5_device_state { diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h new file mode 100644 index 0000000000000..bc7ad019afdef --- /dev/null +++ b/include/linux/mlx5/fs.h @@ -0,0 +1,93 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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 AUTHORS OR COPYRIGHT HOLDERS + * 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. + */ + +#ifndef _MLX5_FS_ +#define _MLX5_FS_ + +#include <linux/mlx5/driver.h> +#include <linux/mlx5/mlx5_ifc.h> + +#define MLX5_FS_DEFAULT_FLOW_TAG 0x0 + +enum mlx5_flow_namespace_type { + MLX5_FLOW_NAMESPACE_KERNEL, + MLX5_FLOW_NAMESPACE_FDB, +}; + +struct mlx5_flow_table; +struct mlx5_flow_group; +struct mlx5_flow_rule; +struct mlx5_flow_namespace; + +struct mlx5_flow_destination { + enum mlx5_flow_destination_type type; + union { + u32 tir_num; + struct mlx5_flow_table *ft; + u32 vport_num; + }; +}; + +struct mlx5_flow_namespace * +mlx5_get_flow_namespace(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type type); + +struct mlx5_flow_table * +mlx5_create_flow_table(struct mlx5_flow_namespace *ns, + int prio, + int num_flow_table_entries); +int mlx5_destroy_flow_table(struct mlx5_flow_table *ft); + +/* inbox should be set with the following values: + * start_flow_index + * end_flow_index + * match_criteria_enable + * match_criteria + */ +struct mlx5_flow_group * +mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); +void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); + +/* Single destination per rule. + * Group ID is implied by the match criteria. + */ +struct mlx5_flow_rule * +mlx5_add_flow_rule(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + u32 *match_criteria, + u32 *match_value, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest); +void mlx5_del_flow_rule(struct mlx5_flow_rule *fr); + +#endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f5d94495758a6..1780a85a87976 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -256,25 +256,27 @@ struct mlx5_ifc_flow_table_fields_supported_bits { struct mlx5_ifc_flow_table_prop_layout_bits { u8 ft_support[0x1]; - u8 reserved_0[0x1f]; + u8 reserved_0[0x2]; + u8 flow_modify_en[0x1]; + u8 reserved_1[0x1c]; - u8 reserved_1[0x2]; + u8 reserved_2[0x2]; u8 log_max_ft_size[0x6]; - u8 reserved_2[0x10]; + u8 reserved_3[0x10]; u8 max_ft_level[0x8]; - u8 reserved_3[0x20]; + u8 reserved_4[0x20]; - u8 reserved_4[0x18]; + u8 reserved_5[0x18]; u8 log_max_ft_num[0x8]; - u8 reserved_5[0x18]; + u8 reserved_6[0x18]; u8 log_max_destination[0x8]; - u8 reserved_6[0x18]; + u8 reserved_7[0x18]; u8 log_max_flow[0x8]; - u8 reserved_7[0x40]; + u8 reserved_8[0x40]; struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; @@ -827,9 +829,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_66[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_67[0xe0]; - - u8 reserved_68[0x1f]; + u8 reserved_67[0x40]; + u8 device_frequency_khz[0x20]; + u8 reserved_68[0x5f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; @@ -2843,6 +2845,13 @@ struct mlx5_ifc_set_hca_cap_in_bits { union mlx5_ifc_hca_cap_union_bits capability; }; +enum { + MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION = 0x0, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_TAG = 0x1, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST = 0x2, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS = 0x3 +}; + struct mlx5_ifc_set_fte_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; @@ -2867,11 +2876,14 @@ struct mlx5_ifc_set_fte_in_bits { u8 reserved_4[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x40]; + u8 reserved_5[0x18]; + u8 modify_enable_mask[0x8]; + + u8 reserved_6[0x20]; u8 flow_index[0x20]; - u8 reserved_6[0xe0]; + u8 reserved_7[0xe0]; struct mlx5_ifc_flow_context_bits flow_context; }; diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 877ef226f90fb..772362adf4713 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -1,6 +1,7 @@ #ifndef LINUX_MM_DEBUG_H #define LINUX_MM_DEBUG_H 1 +#include <linux/bug.h> #include <linux/stringify.h> struct page; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index f0d87347df19e..d9654f0eecb35 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -52,7 +52,7 @@ enum { NETIF_F_GSO_TUNNEL_REMCSUM_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ - NETIF_F_SCTP_CSUM_BIT, /* SCTP checksum offload */ + NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/ NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ @@ -103,7 +103,7 @@ enum { #define NETIF_F_NTUPLE __NETIF_F(NTUPLE) #define NETIF_F_RXCSUM __NETIF_F(RXCSUM) #define NETIF_F_RXHASH __NETIF_F(RXHASH) -#define NETIF_F_SCTP_CSUM __NETIF_F(SCTP_CSUM) +#define NETIF_F_SCTP_CRC __NETIF_F(SCTP_CRC) #define NETIF_F_SG __NETIF_F(SG) #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) @@ -146,10 +146,12 @@ enum { #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \ NETIF_F_TSO6 | NETIF_F_UFO) -#define NETIF_F_GEN_CSUM NETIF_F_HW_CSUM -#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM) -#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM) -#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) +/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be + * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- + * this would be contradictory + */ +#define NETIF_F_CSUM_MASK (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ + NETIF_F_HW_CSUM) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1bb21ff0fa641..c20b814e46a07 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1013,6 +1013,19 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * + * void (*ndo_add_geneve_port)(struct net_device *dev, + * sa_family_t sa_family, __be16 port); + * Called by geneve to notify a driver about the UDP port and socket + * address family that geneve is listnening to. It is called only when + * a new port starts listening. The operation is protected by the + * geneve_net->sock_lock. + * + * void (*ndo_del_geneve_port)(struct net_device *dev, + * sa_family_t sa_family, __be16 port); + * Called by geneve to notify the driver about a UDP port and socket + * address family that geneve is not listening to anymore. The operation + * is protected by the geneve_net->sock_lock. + * * void (*ndo_del_vxlan_port)(struct net_device *dev, * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket @@ -1217,7 +1230,12 @@ struct net_device_ops { void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); - + void (*ndo_add_geneve_port)(struct net_device *dev, + sa_family_t sa_family, + __be16 port); + void (*ndo_del_geneve_port)(struct net_device *dev, + sa_family_t sa_family, + __be16 port); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, @@ -2109,7 +2127,7 @@ struct pcpu_sw_netstats { }) #define netdev_alloc_pcpu_stats(type) \ - __netdev_alloc_pcpu_stats(type, GFP_KERNEL); + __netdev_alloc_pcpu_stats(type, GFP_KERNEL) enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_UNKNOWN, @@ -2522,6 +2540,71 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +struct skb_csum_offl_spec { + __u16 ipv4_okay:1, + ipv6_okay:1, + encap_okay:1, + ip_options_okay:1, + ext_hdrs_okay:1, + tcp_okay:1, + udp_okay:1, + sctp_okay:1, + vlan_okay:1, + no_encapped_ipv6:1, + no_not_encapped:1; +}; + +bool __skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help); + +static inline bool skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return false; + + return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); +} + +static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec) +{ + bool csum_encapped; + + return skb_csum_offload_chk(skb, spec, &csum_encapped, true); +} + +static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .ipv6_okay = 1, + .vlan_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + +static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + .vlan_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3691,13 +3774,37 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); + if (protocol == htons(ETH_P_FCOE)) + return !!(features & NETIF_F_FCOE_CRC); + + /* Assume this is an IP checksum (not SCTP CRC) */ + + if (features & NETIF_F_HW_CSUM) { + /* Can checksum everything */ + return true; + } + + switch (protocol) { + case htons(ETH_P_IP): + return !!(features & NETIF_F_IP_CSUM); + case htons(ETH_P_IPV6): + return !!(features & NETIF_F_IPV6_CSUM); + default: + return false; + } +} + +/* Map an ethertype into IP protocol if possible */ +static inline int eproto_to_ipproto(int eproto) +{ + switch (eproto) { + case htons(ETH_P_IP): + return IPPROTO_IP; + case htons(ETH_P_IPV6): + return IPPROTO_IPV6; + default: + return -1; + } } #ifdef CONFIG_BUG @@ -3762,15 +3869,14 @@ void linkwatch_run_queue(void); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { - if (f1 & NETIF_F_GEN_CSUM) - f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); - if (f2 & NETIF_F_GEN_CSUM) - f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); - f1 &= f2; - if (f1 & NETIF_F_GEN_CSUM) - f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if ((f1 ^ f2) & NETIF_F_HW_CSUM) { + if (f1 & NETIF_F_HW_CSUM) + f1 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + else + f2 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + } - return f1; + return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h new file mode 100644 index 0000000000000..22a16a23cd8a7 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -0,0 +1,13 @@ +#ifndef _NF_CONNTRACK_SCTP_H +#define _NF_CONNTRACK_SCTP_H +/* SCTP tracking. */ + +#include <uapi/linux/netfilter/nf_conntrack_sctp.h> + +struct ip_ct_sctp { + enum sctp_conntrack state; + + __be32 vtag[IP_CT_DIR_MAX]; +}; + +#endif /* _NF_CONNTRACK_SCTP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 249d1bb01e03b..5646b24bfc640 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -14,7 +14,7 @@ struct nfnl_callback { int (*call_rcu)(struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); - int (*call_batch)(struct sock *nl, struct sk_buff *skb, + int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); const struct nla_policy *policy; /* netlink attribute policy */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 639e9b8b0e4d9..0b41959aab9f8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -131,6 +131,7 @@ netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask) struct netlink_callback { struct sk_buff *skb; const struct nlmsghdr *nlh; + int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); @@ -153,6 +154,7 @@ struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags); struct netlink_dump_control { + int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff *skb, struct netlink_callback *); int (*done)(struct netlink_callback *); void *data; diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 039f2eec49ced..1e0deb8e84945 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -46,12 +46,14 @@ extern int of_irq_get(struct device_node *dev, int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); +extern struct device_node *of_irq_find_parent(struct device_node *child); extern struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token); extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid); extern void of_msi_configure(struct device *dev, struct device_node *np); +u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else static inline int of_irq_count(struct device_node *dev) { @@ -70,6 +72,11 @@ static inline int of_irq_to_resource_table(struct device_node *dev, { return 0; } +static inline void *of_irq_find_parent(struct device_node *child) +{ + return NULL; +} + static inline struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token) @@ -84,6 +91,11 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev static inline void of_msi_configure(struct device *dev, struct device_node *np) { } +static inline u32 of_msi_map_rid(struct device *dev, + struct device_node *msi_np, u32 rid_in) +{ + return rid_in; +} #endif #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC) @@ -93,7 +105,6 @@ static inline void of_msi_configure(struct device *dev, struct device_node *np) * so declare it here regardless of the CONFIG_OF_IRQ setting. */ extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); -u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else /* !CONFIG_OF && !CONFIG_SPARC */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, @@ -101,12 +112,6 @@ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, { return 0; } - -static inline u32 of_msi_map_rid(struct device *dev, - struct device_node *msi_np, u32 rid_in) -{ - return rid_in; -} #endif /* !CONFIG_OF */ #endif /* __OF_IRQ_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d841d33bcdc9c..f9828a48f16ad 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -697,9 +697,11 @@ struct perf_cgroup { * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) +perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { - return container_of(task_css(task, perf_event_cgrp_id), + return container_of(task_css_check(task, perf_event_cgrp_id, + ctx ? lockdep_is_held(&ctx->lock) + : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 05fde31b6dc6d..a89cb0eef911e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -589,6 +589,12 @@ struct phy_driver { int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); + /* Get statistics from the phy using ethtool */ + int (*get_sset_count)(struct phy_device *dev); + void (*get_strings)(struct phy_device *dev, u8 *data); + void (*get_stats)(struct phy_device *dev, + struct ethtool_stats *stats, u64 *data); + struct device_driver driver; }; #define to_phy_driver(d) container_of(d, struct phy_driver, driver) diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h index e2878baeb90e8..4299f4ba03bdd 100644 --- a/include/linux/platform_data/edma.h +++ b/include/linux/platform_data/edma.h @@ -72,7 +72,7 @@ struct edma_soc_info { struct edma_rsv_info *rsv; /* List of channels allocated for memcpy, terminated with -1 */ - s16 *memcpy_channels; + s32 *memcpy_channels; s8 (*queue_priority_mapping)[2]; const s16 (*xbar_chans)[2]; diff --git a/include/linux/platform_data/microread.h b/include/linux/platform_data/microread.h index cfda59b226eef..ca13992089b81 100644 --- a/include/linux/platform_data/microread.h +++ b/include/linux/platform_data/microread.h @@ -1,5 +1,5 @@ /* - * Driver include for the PN544 NFC chip. + * Driver include for the Inside Secure microread NFC Chip. * * Copyright (C) 2011 Tieto Poland * Copyright (C) 2012 Intel Corporation. All rights reserved. diff --git a/include/linux/proportions.h b/include/linux/proportions.h index 5440f64d2942a..21221338ad180 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -1,7 +1,7 @@ /* * FLoating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * This file contains the public data structure and API definitions. */ diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 6a4347639c032..1d1ba2c5ee7a2 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -9,6 +9,8 @@ #ifndef __COMMON_HSI__ #define __COMMON_HSI__ +#define CORE_SPQE_PAGE_SIZE_BYTES 4096 + #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 4 #define FW_REVISION_VERSION 2 diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index b920c3605c462..41b9049b57e24 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -111,7 +111,8 @@ static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) - (u32)p_chain->cons_idx; if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= (used / p_chain->elem_per_page); + used -= p_chain->prod_idx / p_chain->elem_per_page - + p_chain->cons_idx / p_chain->elem_per_page; return p_chain->capacity - used; } diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 843ceca9a21e5..63bd7601b6dee 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -19,6 +19,7 @@ #include <linux/atomic.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> #include <linux/list_nulls.h> @@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *old_tbl); -int rhashtable_insert_rehash(struct rhashtable *ht); +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *old_tbl); +int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl); int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); @@ -598,9 +600,11 @@ restart: new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(new_tbl)) { - err = rhashtable_insert_slow(ht, key, obj, new_tbl); - if (err == -EAGAIN) + tbl = rhashtable_insert_slow(ht, key, obj, new_tbl); + if (!IS_ERR_OR_NULL(tbl)) goto slow_path; + + err = PTR_ERR(tbl); goto out; } @@ -611,7 +615,7 @@ restart: if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht); + err = rhashtable_insert_rehash(ht, tbl); rcu_read_unlock(); if (err) return err; @@ -819,4 +823,86 @@ out: return err; } +/* Internal function, please use rhashtable_replace_fast() instead */ +static inline int __rhashtable_replace_fast( + struct rhashtable *ht, struct bucket_table *tbl, + struct rhash_head *obj_old, struct rhash_head *obj_new, + const struct rhashtable_params params) +{ + struct rhash_head __rcu **pprev; + struct rhash_head *he; + spinlock_t *lock; + unsigned int hash; + int err = -ENOENT; + + /* Minimally, the old and new objects must have same hash + * (which should mean identifiers are the same). + */ + hash = rht_head_hashfn(ht, tbl, obj_old, params); + if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) + return -EINVAL; + + lock = rht_bucket_lock(tbl, hash); + + spin_lock_bh(lock); + + pprev = &tbl->buckets[hash]; + rht_for_each(he, tbl, hash) { + if (he != obj_old) { + pprev = &he->next; + continue; + } + + rcu_assign_pointer(obj_new->next, obj_old->next); + rcu_assign_pointer(*pprev, obj_new); + err = 0; + break; + } + + spin_unlock_bh(lock); + + return err; +} + +/** + * rhashtable_replace_fast - replace an object in hash table + * @ht: hash table + * @obj_old: pointer to hash head inside object being replaced + * @obj_new: pointer to hash head inside object which is new + * @params: hash table parameters + * + * Replacing an object doesn't affect the number of elements in the hash table + * or bucket, so we don't need to worry about shrinking or expanding the + * table here. + * + * Returns zero on success, -ENOENT if the entry could not be found, + * -EINVAL if hash is not the same for the old and new objects. + */ +static inline int rhashtable_replace_fast( + struct rhashtable *ht, struct rhash_head *obj_old, + struct rhash_head *obj_new, + const struct rhashtable_params params) +{ + struct bucket_table *tbl; + int err; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + + /* Because we have already taken (and released) the bucket + * lock in old_tbl, if we find that future_tbl is not yet + * visible then that guarantees the entry to still be in + * the old tbl if it exists. + */ + while ((err = __rhashtable_replace_fast(ht, tbl, obj_old, + obj_new, params)) && + (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) + ; + + rcu_read_unlock(); + + return err; +} + #endif /* _LINUX_RHASHTABLE_H */ diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index 8c9131db2b252..f2e27e0783623 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -4,7 +4,7 @@ #include <linux/phy.h> #include <linux/if_ether.h> -enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; +enum {EDMAC_LITTLE_ENDIAN}; struct sh_eth_plat_data { int phy; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9b9b9ead7bb3e..6b6bd42d6134a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -39,11 +39,55 @@ #include <linux/in6.h> #include <net/flow.h> -/* A. Checksumming of received packets by device. +/* The interface for checksum offload between the stack and networking drivers + * is as follows... + * + * A. IP checksum related features + * + * Drivers advertise checksum offload capabilities in the features of a device. + * From the stack's point of view these are capabilities offered by the driver, + * a driver typically only advertises features that it is capable of offloading + * to its device. + * + * The checksum related features are: + * + * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv4|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. + * This flag is used only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * B. Checksumming of received packets by device. Indication of checksum + * verification is in set skb->ip_summed. Possible values are: * * CHECKSUM_NONE: * - * Device failed to checksum this packet e.g. due to lack of capabilities. + * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * @@ -53,9 +97,8 @@ * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY * if their checksums are okay. skb->csum is still undefined in this case - * though. It is a bad option, but, unfortunately, nowadays most vendors do - * this. Apparently with the secret goal to sell you new devices, when you - * will add new protocol to your host, f.e. IPv6 8) + * though. A driver or device must never modify the checksum field in the + * packet even if checksum is verified. * * CHECKSUM_UNNECESSARY is applicable to following protocols: * TCP: IPv6 and IPv4. @@ -96,40 +139,77 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * B. Checksumming on output. - * - * CHECKSUM_NONE: - * - * The skb was already checksummed by the protocol, or a checksum is not - * required. + * C. Checksumming on transmit for non-GSO. The stack requests checksum offload + * in the skb->ip_summed for a packet. Values are: * * CHECKSUM_PARTIAL: * - * The device is required to checksum the packet as seen by hard_start_xmit() + * The driver is required to checksum the packet as seen by hard_start_xmit() * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. + * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * csum_start and csum_offset values are valid values given the length and + * offset of the packet, however they should not attempt to validate that the + * checksum refers to a legitimate transport layer checksum-- it is the + * purview of the stack to validate that csum_start and csum_offset are set + * correctly. + * + * When the stack requests checksum offload for a packet, the driver MUST + * ensure that the checksum is set correctly. A driver can either offload the + * checksum calculation to the device, or call skb_checksum_help (in the case + * that the device does not support offload for a particular checksum). + * + * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of + * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * checksum offload capability. If a device has limited checksum capabilities + * (for instance can only perform NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM as + * described above) a helper function can be called to resolve + * CHECKSUM_PARTIAL. The helper functions are skb_csum_off_chk*. The helper + * function takes a spec argument that describes the protocol layer that is + * supported for checksum offload and can be called for each packet. If a + * packet does not match the specification for offload, skb_checksum_help + * is called to resolve the checksum. * - * The device must show its capabilities in dev->features, set up at device - * setup time, e.g. netdev_features.h: + * CHECKSUM_NONE: * - * NETIF_F_HW_CSUM - It's a clever device, it's able to checksum everything. - * NETIF_F_IP_CSUM - Device is dumb, it's able to checksum only TCP/UDP over - * IPv4. Sigh. Vendors like this way for an unknown reason. - * Though, see comment above about CHECKSUM_UNNECESSARY. 8) - * NETIF_F_IPV6_CSUM - About as dumb as the last one but does IPv6 instead. - * NETIF_F_... - Well, you get the picture. + * The skb was already checksummed by the protocol, or a checksum is not + * required. * * CHECKSUM_UNNECESSARY: * - * Normally, the device will do per protocol specific checksumming. Protocol - * implementations that do not want the NIC to perform the checksum - * calculation should use this flag in their outgoing skbs. - * - * NETIF_F_FCOE_CRC - This indicates that the device can do FCoE FC CRC - * offload. Correspondingly, the FCoE protocol driver - * stack should use CHECKSUM_UNNECESSARY. + * This has the same meaning on as CHECKSUM_NONE for checksum offload on + * output. * - * Any questions? No questions, good. --ANK + * CHECKSUM_COMPLETE: + * Not used in checksum output. If a driver observes a packet with this value + * set in skbuff, if should treat as CHECKSUM_NONE being set. + * + * D. Non-IP checksum (CRC) offloads + * + * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note the there is no indication in the skbuff that the + * CHECKSUM_PARTIAL refers to an SCTP checksum, a driver that supports + * both IP checksum offload and SCTP CRC offload must verify which offload + * is configured for a packet presumably by inspecting packet headers. + * + * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of + * offloading the FCOE CRC in a packet. To perform this offload the stack + * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note the there is no indication in the skbuff that the + * CHECKSUM_PARTIAL refers to an FCOE checksum, a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet presumably by inspecting packet headers. + * + * E. Checksumming on output with GSO. + * + * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the + * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * part of the GSO operation is implied. If a checksum is being offloaded + * with GSO then ip_summed is CHECKSUM_PARTIAL, csum_start and csum_offset + * are set to refer to the outermost checksum being offload (two offloaded + * checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ @@ -833,7 +913,7 @@ struct sk_buff_fclones { * skb_fclone_busy - check if fclone is busy * @skb: buffer * - * Returns true is skb is a fast clone, and its clone is not freed. + * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that this didnt happen. */ @@ -1939,6 +2019,11 @@ static inline unsigned char *skb_inner_transport_header(const struct sk_buff return skb->head + skb->inner_transport_header; } +static inline int skb_inner_transport_offset(const struct sk_buff *skb) +{ + return skb_inner_transport_header(skb) - skb->data; +} + static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { skb->inner_transport_header = skb->data - skb->head; diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index dad035c16d94f..343c13ac4f71f 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -144,17 +144,17 @@ struct knav_dma_cfg { * @psdata: Protocol specific */ struct knav_dma_desc { - u32 desc_info; - u32 tag_info; - u32 packet_info; - u32 buff_len; - u32 buff; - u32 next_desc; - u32 orig_len; - u32 orig_buff; - u32 epib[KNAV_DMA_NUM_EPIB_WORDS]; - u32 psdata[KNAV_DMA_NUM_PS_WORDS]; - u32 pad[4]; + __le32 desc_info; + __le32 tag_info; + __le32 packet_info; + __le32 buff_len; + __le32 buff; + __le32 next_desc; + __le32 orig_len; + __le32 orig_buff; + __le32 epib[KNAV_DMA_NUM_EPIB_WORDS]; + __le32 psdata[KNAV_DMA_NUM_PS_WORDS]; + __le32 pad[4]; } ____cacheline_aligned; #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA) diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index fddebc6174697..4018b48f2b3b4 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -15,6 +15,7 @@ struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); + int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); @@ -68,4 +69,5 @@ bool sock_diag_has_destroy_listeners(const struct sock *sk) } void sock_diag_broadcast_destroy(struct sock *sk); +int sock_diag_destroy(struct sock *sk, int err); #endif diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 0adedca24c5bf..0e1b1540597a4 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * grabbing every spinlock (and more). So the "read" side to such a * lock is anything which disables preemption. */ -#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) /** * stop_machine: freeze the machine on all CPUs and run this function @@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); -#else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ static inline int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) @@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return stop_machine(fn, data, cpus); } -#endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 0bdc72f369054..4a29c75b146e1 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -21,7 +21,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/errno.h> diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 1f6526c76ee84..3a375d07d0dc0 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -138,6 +138,7 @@ struct cdc_ncm_ctx { }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); +int cdc_ncm_change_mtu(struct net_device *net, int new_mtu); int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 9948c874e3f1e..1d0043dc34e42 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -47,4 +47,7 @@ /* device generates spurious wakeup, ignore remote wakeup capability */ #define USB_QUIRK_IGNORE_REMOTE_WAKEUP BIT(9) +/* device can't handle Link Power Management */ +#define USB_QUIRK_NO_LPM BIT(10) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 610a86a892b88..ddb4409753824 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,9 +44,6 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; -extern struct iommu_group *vfio_iommu_group_get(struct device *dev); -extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); - extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 5dbc8b0ee567a..3e5d9075960f6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -176,11 +176,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) #ifdef CONFIG_SMP -void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int); +void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); -void mod_zone_page_state(struct zone *, enum zone_stat_item, int); +void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); @@ -205,7 +205,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, - enum zone_stat_item item, int delta) + enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } diff --git a/include/linux/wait.h b/include/linux/wait.h index 6aa09a875fbdc..0496c31aaf066 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -166,7 +166,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } -typedef int wait_bit_action_f(struct wait_bit_key *); +typedef int wait_bit_action_f(struct wait_bit_key *, int mode); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); @@ -981,10 +981,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); } while (0) -extern int bit_wait(struct wait_bit_key *); -extern int bit_wait_io(struct wait_bit_key *); -extern int bit_wait_timeout(struct wait_bit_key *); -extern int bit_wait_io_timeout(struct wait_bit_key *); +extern int bit_wait(struct wait_bit_key *, int); +extern int bit_wait_io(struct wait_bit_key *, int); +extern int bit_wait_timeout(struct wait_bit_key *, int); +extern int bit_wait_io_timeout(struct wait_bit_key *, int); /** * wait_on_bit - wait for a bit to be cleared diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index cf3bc564ac033..2f6a3f2233edf 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -53,6 +53,8 @@ #ifndef __6LOWPAN_H__ #define __6LOWPAN_H__ +#include <linux/debugfs.h> + #include <net/ipv6.h> #include <net/net_namespace.h> @@ -98,6 +100,7 @@ enum lowpan_lltypes { struct lowpan_priv { enum lowpan_lltypes lltype; + struct dentry *iface_debugfs; /* must be last */ u8 priv[0] __aligned(sizeof(void *)); @@ -185,7 +188,12 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, *hc_ptr += len; } -void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype); +int lowpan_register_netdevice(struct net_device *dev, + enum lowpan_lltypes lltype); +int lowpan_register_netdev(struct net_device *dev, + enum lowpan_lltypes lltype); +void lowpan_unregister_netdevice(struct net_device *dev); +void lowpan_unregister_netdev(struct net_device *dev); /** * lowpan_header_decompress - replace 6LoWPAN header with IPv6 header diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 78003dfb8539b..47f52d3cd8dfb 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -87,7 +87,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, u32 banned_flags); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2); +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index cc22167276555..339ea57be4230 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -239,7 +239,6 @@ enum { HCI_LE_ENABLED, HCI_ADVERTISING, HCI_ADVERTISING_CONNECTABLE, - HCI_ADVERTISING_INSTANCE, HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LIMITED_DISCOVERABLE, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 55ce209157b10..c95e0326c41a3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -329,6 +329,9 @@ struct hci_dev { struct work_struct discov_update; struct work_struct bg_scan_update; + struct work_struct scan_update; + struct work_struct connectable_update; + struct work_struct discoverable_update; struct delayed_work le_scan_disable; struct delayed_work le_scan_restart; @@ -1432,10 +1435,8 @@ int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); void mgmt_set_powered_failed(struct hci_dev *hdev, int err); -int mgmt_powered(struct hci_dev *hdev, u8 powered); -int mgmt_update_adv_data(struct hci_dev *hdev); -void mgmt_discoverable_timeout(struct hci_dev *hdev); -void mgmt_adv_timeout_expired(struct hci_dev *hdev); +void mgmt_power_on(struct hci_dev *hdev, int err); +void __mgmt_power_off(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, @@ -1490,8 +1491,15 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 store_hint, u16 min_interval, u16 max_interval, u16 latency, u16 timeout); -void mgmt_reenable_advertising(struct hci_dev *hdev); void mgmt_smp_complete(struct hci_conn *conn, bool complete); +bool mgmt_get_connectable(struct hci_dev *hdev); +void mgmt_set_connectable_complete(struct hci_dev *hdev, u8 status); +void mgmt_set_discoverable_complete(struct hci_dev *hdev, u8 status); +u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev); +void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, + u8 instance); +void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, + u8 instance); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/checksum.h b/include/net/checksum.h index 9fcaedf994ee2..10a16b5bd1c70 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -165,7 +165,8 @@ static inline __wsum remcsum_adjust(void *ptr, __wsum csum, csum = csum_sub(csum, csum_partial(ptr, start, 0)); /* Set derived checksum in packet */ - delta = csum_sub(csum_fold(csum), *psum); + delta = csum_sub((__force __wsum)csum_fold(csum), + (__force __wsum)*psum); *psum = csum_fold(csum); return delta; diff --git a/include/net/dst.h b/include/net/dst.h index 1279f9b09791a..c7329dcd90cc0 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -322,6 +322,39 @@ static inline void skb_dst_force(struct sk_buff *skb) } } +/** + * dst_hold_safe - Take a reference on a dst if possible + * @dst: pointer to dst entry + * + * This helper returns false if it could not safely + * take a reference on a dst. + */ +static inline bool dst_hold_safe(struct dst_entry *dst) +{ + if (dst->flags & DST_NOCACHE) + return atomic_inc_not_zero(&dst->__refcnt); + dst_hold(dst); + return true; +} + +/** + * skb_dst_force_safe - makes sure skb dst is refcounted + * @skb: buffer + * + * If dst is not yet refcounted and not destroyed, grab a ref on it. + */ +static inline void skb_dst_force_safe(struct sk_buff *skb) +{ + if (skb_dst_is_noref(skb)) { + struct dst_entry *dst = skb_dst(skb); + + if (!dst_hold_safe(dst)) + dst = NULL; + + skb->_skb_refdst = (unsigned long)dst; + } +} + /** * __skb_tunnel_rx - prepare skb for rx reinsert diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 1b6b6dcb018de..43c0e771f417a 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -114,6 +114,7 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) * @flags: flags * @policy: attribute validation policy * @doit: standard command callback + * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps * @ops_list: operations list @@ -122,6 +123,7 @@ struct genl_ops { const struct nla_policy *policy; int (*doit)(struct sk_buff *skb, struct genl_info *info); + int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); diff --git a/include/net/geneve.h b/include/net/geneve.h index 3106ed6eae0d1..e6c23dc765f7e 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -62,6 +62,14 @@ struct genevehdr { struct geneve_opt options[]; }; +#if IS_ENABLED(CONFIG_GENEVE) +void geneve_get_rx_port(struct net_device *netdev); +#else +static inline void geneve_get_rx_port(struct net_device *netdev) +{ +} +#endif + #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port); diff --git a/include/net/ila.h b/include/net/ila.h new file mode 100644 index 0000000000000..9f4f43e94ae43 --- /dev/null +++ b/include/net/ila.h @@ -0,0 +1,18 @@ +/* + * ILA kernel interface + * + * Copyright (c) 2015 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + */ + +#ifndef _NET_ILA_H +#define _NET_ILA_H + +int ila_xlat_outgoing(struct sk_buff *skb); +int ila_xlat_incoming(struct sk_buff *skb); + +#endif /* _NET_ILA_H */ diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index ac42bbb37b2dd..12aac0fd6ee7c 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -99,7 +99,6 @@ struct inet_frags { void (*constructor)(struct inet_frag_queue *q, const void *arg); void (*destructor)(struct inet_frag_queue *); - void (*skb_free)(struct sk_buff *); void (*frag_expire)(unsigned long data); struct kmem_cache *frags_cachep; const char *frags_cache_name; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 2134e6d815bcb..012b1f91f3ec4 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -28,6 +28,7 @@ #include <net/request_sock.h> #include <net/netns/hash.h> #include <net/tcp_states.h> +#include <net/l3mdev.h> /** struct ip_options - IP Options * @@ -113,6 +114,19 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) return sk->sk_mark; } +static inline int inet_request_bound_dev_if(const struct sock *sk, + struct sk_buff *skb) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + struct net *net = sock_net(sk); + + if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + return l3mdev_master_ifindex_by_index(net, skb->skb_iif); +#endif + + return sk->sk_bound_dev_if; +} + struct inet_cork { unsigned int flags; __be32 addr; @@ -210,18 +224,37 @@ struct inet_sock { #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) -/* SYNACK messages might be attached to request sockets. +/** + * sk_to_full_sk - Access to a full socket + * @sk: pointer to a socket + * + * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ -static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) +static inline struct sock *sk_to_full_sk(struct sock *sk) { - struct sock *sk = skb->sk; - +#ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; +#endif return sk; } +/* sk_to_full_sk() variant with a const argument */ +static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) +{ +#ifdef CONFIG_INET + if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + sk = ((const struct request_sock *)sk)->rsk_listener; +#endif + return sk; +} + +static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) +{ + return sk_to_full_sk(skb->sk); +} + static inline struct inet_sock *inet_sk(const struct sock *sk) { return (struct inet_sock *)sk; diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 4a6009d4486b9..235c7811a86a1 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -78,6 +78,7 @@ void inet_initpeers(void) __init; static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip) { iaddr->a4.addr = ip; + iaddr->a4.vif = 0; iaddr->family = AF_INET; } diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index ff788b665277d..0d0ce0b2d8701 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -5,6 +5,7 @@ #include <linux/netdevice.h> #include <linux/if_tunnel.h> #include <linux/ip6_tunnel.h> +#include <net/ip_tunnels.h> #define IP6TUNNEL_ERR_TIMEO (30*HZ) @@ -80,25 +81,17 @@ __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, struct net *ip6_tnl_get_link_net(const struct net_device *dev); int ip6_tnl_get_iflink(const struct net_device *dev); +#ifdef CONFIG_INET static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, struct net_device *dev) { - struct net_device_stats *stats = &dev->stats; int pkt_len, err; pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); - - if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; - u64_stats_update_end(&tstats->syncp); - put_cpu_ptr(tstats); - } else { - stats->tx_errors++; - stats->tx_aborted_errors++; - } + if (unlikely(net_xmit_eval(err))) + pkt_len = -1; + iptunnel_xmit_stats(dev, pkt_len); } #endif +#endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 62a750a6a8f8c..6db96ea0144f0 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -273,32 +273,34 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, } int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto); -int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, - __be32 src, __be32 dst, u8 proto, - u8 tos, u8 ttl, __be16 df, bool xnet); +void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, + __be32 src, __be32 dst, u8 proto, + u8 tos, u8 ttl, __be16 df, bool xnet); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, int gso_type_mask); -static inline void iptunnel_xmit_stats(int err, - struct net_device_stats *err_stats, - struct pcpu_sw_netstats __percpu *stats) +static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { - if (err > 0) { - struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); + if (pkt_len > 0) { + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += err; + tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); - } else if (err < 0) { - err_stats->tx_errors++; - err_stats->tx_aborted_errors++; } else { - err_stats->tx_dropped++; + struct net_device_stats *err_stats = &dev->stats; + + if (pkt_len < 0) { + err_stats->tx_errors++; + err_stats->tx_aborted_errors++; + } else { + err_stats->tx_dropped++; + } } } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9a5c9f0137845..6570f379aba2e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -401,6 +401,21 @@ static inline void ipv6_addr_prefix(struct in6_addr *pfx, pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } +static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, + const struct in6_addr *pfx, + int plen) +{ + /* caller must guarantee 0 <= plen <= 128 */ + int o = plen >> 3, + b = plen & 0x7; + + memcpy(addr->s6_addr, pfx, o); + if (b != 0) { + addr->s6_addr[o] &= ~(0xff00 >> b); + addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); + } +} + static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 774d85b2d5d97..786226f8e77be 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -51,6 +51,24 @@ static inline int l3mdev_master_ifindex(struct net_device *dev) return ifindex; } +static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) +{ + struct net_device *dev; + int rc = 0; + + if (likely(ifindex)) { + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + rc = l3mdev_master_ifindex_rcu(dev); + + rcu_read_unlock(); + } + + return rc; +} + /* get index of an interface to use for FIB lookups. For devices * enslaved to an L3 master device FIB lookups are based on the * master index @@ -167,6 +185,11 @@ static inline int l3mdev_master_ifindex(struct net_device *dev) return 0; } +static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) +{ + return 0; +} + static inline int l3mdev_fib_oif_rcu(struct net_device *dev) { return dev ? dev->ifindex : 0; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 2dcea635ecce3..4089abc6e9c0d 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -121,6 +121,9 @@ struct net { #if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT) struct list_head nfnl_acct_list; #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + struct list_head nfct_timeout_list; +#endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index fb7da5bb76cc8..ddf162f7966fc 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -5,8 +5,7 @@ void nf_defrag_ipv6_enable(void); int nf_ct_frag6_init(void); void nf_ct_frag6_cleanup(void); -struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); -void nf_ct_frag6_consume_orig(struct sk_buff *skb); +int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); struct inet_frags_ctl; diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index f72be38860a74..5cc5e9e6171a0 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -104,7 +104,7 @@ static inline void nf_conntrack_timeout_fini(void) #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(const char *name); +extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name); extern void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout); #endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4bd7508bedc9f..b313cda491946 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -19,8 +19,6 @@ struct nft_pktinfo { const struct net_device *out; u8 pf; u8 hook; - u8 nhoff; - u8 thoff; u8 tprot; /* for x_tables compatibility */ struct xt_action_param xt; @@ -890,6 +888,38 @@ void nft_unregister_chain_type(const struct nf_chain_type *); int nft_register_expr(struct nft_expr_type *); void nft_unregister_expr(struct nft_expr_type *); +int nft_verdict_dump(struct sk_buff *skb, int type, + const struct nft_verdict *v); + +/** + * struct nft_traceinfo - nft tracing information and state + * + * @pkt: pktinfo currently processed + * @basechain: base chain currently processed + * @chain: chain currently processed + * @rule: rule that was evaluated + * @verdict: verdict given by rule + * @type: event type (enum nft_trace_types) + * @packet_dumped: packet headers sent in a previous traceinfo message + * @trace: other struct members are initialised + */ +struct nft_traceinfo { + const struct nft_pktinfo *pkt; + const struct nft_base_chain *basechain; + const struct nft_chain *chain; + const struct nft_rule *rule; + const struct nft_verdict *verdict; + enum nft_trace_types type; + bool packet_dumped; + bool trace; +}; + +void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, + const struct nft_chain *basechain); + +void nft_trace_notify(struct nft_traceinfo *info); + #define nft_dereference(p) \ nfnl_dereference(p, NFNL_SUBSYS_NFTABLES) diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index c6f400cfaac8d..a9060dd99db76 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -47,7 +47,17 @@ struct nft_payload { enum nft_registers dreg:8; }; +struct nft_payload_set { + enum nft_payload_bases base:8; + u8 offset; + u8 len; + enum nft_registers sreg:8; + u8 csum_type; + u8 csum_offset; +}; + extern const struct nft_expr_ops nft_payload_fast_ops; +extern struct static_key_false nft_trace_enabled; int nft_payload_module_init(void); void nft_payload_module_exit(void); diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 711887a09e918..d27588c8dbd9f 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -33,4 +33,7 @@ void nft_meta_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr); + #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c68926b4899c3..d75be32650ba1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -86,6 +86,9 @@ struct netns_ipv4 { int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; +#ifdef CONFIG_NET_L3_MASTER_DEV + int sysctl_tcp_l3mdev_accept; +#endif int sysctl_tcp_mtu_probing; int sysctl_tcp_base_mss; int sysctl_tcp_probe_threshold; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 8ba379f9e4678..c501d67172b12 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -89,6 +89,13 @@ struct netns_sctp { int pf_retrans; /* + * Disable Potentially-Failed feature, the feature is enabled by default + * pf_enable - 0 : disable pf + * - >0 : enable pf + */ + int pf_enable; + + /* * Policy for preforming sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index dcfcfc9c00bf5..1a3de8b34ad27 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -299,6 +299,7 @@ void nfc_driver_failure(struct nfc_dev *dev, int err); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); +int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx); struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a0dde04eb1780..f49759decb287 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -68,7 +68,7 @@ struct request_sock { u32 peer_secid; }; -static inline struct request_sock *inet_reqsk(struct sock *sk) +static inline struct request_sock *inet_reqsk(const struct sock *sk) { return (struct request_sock *)sk; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index ce13cf20f6253..835aa2ed98709 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -126,8 +126,6 @@ int sctp_primitive_ASCONF(struct net *, struct sctp_association *, void *arg); */ int sctp_rcv(struct sk_buff *skb); void sctp_v4_err(struct sk_buff *skb, u32 info); -void sctp_hash_established(struct sctp_association *); -void sctp_unhash_established(struct sctp_association *); void sctp_hash_endpoint(struct sctp_endpoint *); void sctp_unhash_endpoint(struct sctp_endpoint *); struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, @@ -143,6 +141,17 @@ void sctp_icmp_proto_unreachable(struct sock *sk, struct sctp_transport *t); void sctp_backlog_migrate(struct sctp_association *assoc, struct sock *oldsk, struct sock *newsk); +int sctp_transport_hashtable_init(void); +void sctp_transport_hashtable_destroy(void); +void sctp_hash_transport(struct sctp_transport *t); +void sctp_unhash_transport(struct sctp_transport *t); +struct sctp_transport *sctp_addrs_lookup_transport( + struct net *net, + const union sctp_addr *laddr, + const union sctp_addr *paddr); +struct sctp_transport *sctp_epaddr_lookup_transport( + const struct sctp_endpoint *ep, + const union sctp_addr *paddr); /* * sctp/proc.c @@ -519,25 +528,6 @@ static inline int sctp_ep_hashfn(struct net *net, __u16 lport) return (net_hash_mix(net) + lport) & (sctp_ep_hashsize - 1); } -/* This is the hash function for the association hash table. */ -static inline int sctp_assoc_hashfn(struct net *net, __u16 lport, __u16 rport) -{ - int h = (lport << 16) + rport + net_hash_mix(net); - h ^= h>>8; - return h & (sctp_assoc_hashsize - 1); -} - -/* This is the hash function for the association hash table. This is - * not used yet, but could be used as a better hash function when - * we have a vtag. - */ -static inline int sctp_vtag_hashfn(__u16 lport, __u16 rport, __u32 vtag) -{ - int h = (lport << 16) + rport; - h ^= vtag; - return h & (sctp_assoc_hashsize - 1); -} - #define sctp_for_each_hentry(epb, head) \ hlist_for_each_entry(epb, head, node) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 7bbb71081aeb6..20e72129be1ce 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -48,6 +48,7 @@ #define __sctp_structs_h__ #include <linux/ktime.h> +#include <linux/rhashtable.h> #include <linux/socket.h> /* linux/in.h needs this!! */ #include <linux/in.h> /* We get struct sockaddr_in. */ #include <linux/in6.h> /* We get struct in6_addr */ @@ -119,14 +120,13 @@ extern struct sctp_globals { /* This is the hash of all endpoints. */ struct sctp_hashbucket *ep_hashtable; - /* This is the hash of all associations. */ - struct sctp_hashbucket *assoc_hashtable; /* This is the sctp port control hash. */ struct sctp_bind_hashbucket *port_hashtable; + /* This is the hash of all transports. */ + struct rhashtable transport_hashtable; /* Sizes of above hashtables. */ int ep_hashsize; - int assoc_hashsize; int port_hashsize; /* Default initialization values to be applied to new associations. */ @@ -143,10 +143,9 @@ extern struct sctp_globals { #define sctp_address_families (sctp_globals.address_families) #define sctp_ep_hashsize (sctp_globals.ep_hashsize) #define sctp_ep_hashtable (sctp_globals.ep_hashtable) -#define sctp_assoc_hashsize (sctp_globals.assoc_hashsize) -#define sctp_assoc_hashtable (sctp_globals.assoc_hashtable) #define sctp_port_hashsize (sctp_globals.port_hashsize) #define sctp_port_hashtable (sctp_globals.port_hashtable) +#define sctp_transport_hashtable (sctp_globals.transport_hashtable) #define sctp_checksum_disable (sctp_globals.checksum_disable) /* SCTP Socket type: UDP or TCP style. */ @@ -753,6 +752,7 @@ static inline int sctp_packet_empty(struct sctp_packet *packet) struct sctp_transport { /* A list of transports. */ struct list_head transports; + struct rhash_head node; /* Reference counting. */ atomic_t refcnt; @@ -1493,7 +1493,8 @@ struct sctp_association { * : SACK's are not delayed (see Section 6). */ __u8 sack_needed:1, /* Do we need to sack the peer? */ - sack_generation:1; + sack_generation:1, + zero_window_announced:1; __u32 sack_cnt; __u32 adaptation_ind; /* Adaptation Code point. */ diff --git a/include/net/sock.h b/include/net/sock.h index 0ca22b014de1a..e830c10069350 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -318,6 +318,7 @@ struct cg_proto; * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 + * @sk_reuseport_cb: reuseport group container */ struct sock { /* @@ -389,7 +390,7 @@ struct sock { struct socket_wq *sk_wq_raw; }; #ifdef CONFIG_XFRM - struct xfrm_policy *sk_policy[2]; + struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; @@ -405,6 +406,7 @@ struct sock { sk_userlocks : 4, sk_protocol : 8, sk_type : 16; +#define SK_PROTOCOL_MAX U8_MAX kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; @@ -452,6 +454,7 @@ struct sock { int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); + struct sock_reuseport __rcu *sk_reuseport_cb; }; #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) @@ -736,6 +739,8 @@ enum sock_flags { SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ }; +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) { nsk->sk_flags = osk->sk_flags; @@ -810,7 +815,7 @@ void sk_stream_write_space(struct sock *sk); static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ - skb_dst_force(skb); + skb_dst_force_safe(skb); if (!sk->sk_backlog.tail) sk->sk_backlog.head = skb; @@ -1060,6 +1065,7 @@ struct proto { void (*destroy_cgroup)(struct mem_cgroup *memcg); struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); #endif + int (*diag_destroy)(struct sock *sk, int err); }; int proto_register(struct proto *prot, int alloc_slab); @@ -1791,6 +1797,15 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) sk->sk_route_caps &= ~flags; } +static inline bool sk_check_csum_caps(struct sock *sk) +{ + return (sk->sk_route_caps & NETIF_F_HW_CSUM) || + (sk->sk_family == PF_INET && + (sk->sk_route_caps & NETIF_F_IP_CSUM)) || + (sk->sk_family == PF_INET6 && + (sk->sk_route_caps & NETIF_F_IPV6_CSUM)); +} + static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h new file mode 100644 index 0000000000000..7dda3d7adba8e --- /dev/null +++ b/include/net/sock_reuseport.h @@ -0,0 +1,28 @@ +#ifndef _SOCK_REUSEPORT_H +#define _SOCK_REUSEPORT_H + +#include <linux/filter.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <net/sock.h> + +struct sock_reuseport { + struct rcu_head rcu; + + u16 max_socks; /* length of socks */ + u16 num_socks; /* elements in socks */ + struct bpf_prog __rcu *prog; /* optional BPF sock selector */ + struct sock *socks[0]; /* array of sock pointers */ +}; + +extern int reuseport_alloc(struct sock *sk); +extern int reuseport_add_sock(struct sock *sk, const struct sock *sk2); +extern void reuseport_detach_sock(struct sock *sk); +extern struct sock *reuseport_select_sock(struct sock *sk, + u32 hash, + struct sk_buff *skb, + int hdr_len); +extern struct bpf_prog *reuseport_attach_prog(struct sock *sk, + struct bpf_prog *prog); + +#endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1d22ce9f352e2..6612946167feb 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -50,6 +50,7 @@ enum switchdev_attr_id { }; struct switchdev_attr { + struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; union { @@ -68,6 +69,7 @@ enum switchdev_obj_id { }; struct switchdev_obj { + struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index f80e74c5ad18b..f33fecf4e2829 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1170,6 +1170,8 @@ void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); +int tcp_abort(struct sock *sk, int err); + static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; @@ -1618,6 +1620,18 @@ static inline void tcp_highest_sack_combine(struct sock *sk, tcp_sk(sk)->highest_sack = new; } +/* This helper checks if socket has IP_TRANSPARENT set */ +static inline bool inet_sk_transparent(const struct sock *sk) +{ + switch (sk->sk_state) { + case TCP_TIME_WAIT: + return inet_twsk(sk)->tw_transparent; + case TCP_NEW_SYN_RECV: + return inet_rsk(inet_reqsk(sk))->no_srccheck; + } + return inet_sk(sk)->transparent; +} + /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ diff --git a/include/net/udp.h b/include/net/udp.h index 6d4ed18e14278..2842541e28e71 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -191,7 +191,7 @@ static inline void udp_lib_close(struct sock *sk, long timeout) } int udp_lib_get_port(struct sock *sk, unsigned short snum, - int (*)(const struct sock *, const struct sock *), + int (*)(const struct sock *, const struct sock *, bool), unsigned int hash2_nulladdr); u32 udp_flow_hashrnd(void); @@ -258,7 +258,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, - struct udp_table *tbl); + struct udp_table *tbl, struct sk_buff *skb); struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, @@ -266,7 +266,8 @@ struct sock *udp6_lib_lookup(struct net *net, struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *tbl); + int dif, struct udp_table *tbl, + struct sk_buff *skb); /* * SNMP statistics for UDP and UDP-Lite diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index cb2f89f20f5c9..cca2ad3082c37 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -78,10 +78,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* Transmit the skb using UDP encapsulation. */ -int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 tos, __u8 ttl, - __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck); +void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 tos, __u8 ttl, + __be16 df, __be16 src_port, __be16 dst_port, + bool xnet, bool nocheck); #if IS_ENABLED(CONFIG_IPV6) int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c1c899c3a51be..0fb86442544b2 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -79,7 +79,7 @@ struct vxlanhdr { }; /* VXLAN header flags. */ -#define VXLAN_HF_RCO BIT(24) +#define VXLAN_HF_RCO BIT(21) #define VXLAN_HF_VNI BIT(27) #define VXLAN_HF_GBP BIT(31) @@ -232,7 +232,7 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4a9c21f9b4ea1..d6f6e5006ee9e 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -548,6 +548,7 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; + struct rcu_head rcu; }; static inline struct net *xp_net(const struct xfrm_policy *xp) @@ -1141,12 +1142,14 @@ static inline int xfrm6_route_forward(struct sk_buff *skb) return xfrm_route_forward(skb, AF_INET6); } -int __xfrm_sk_clone_policy(struct sock *sk); +int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); -static inline int xfrm_sk_clone_policy(struct sock *sk) +static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { - if (unlikely(sk->sk_policy[0] || sk->sk_policy[1])) - return __xfrm_sk_clone_policy(sk); + sk->sk_policy[0] = NULL; + sk->sk_policy[1] = NULL; + if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) + return __xfrm_sk_clone_policy(sk, osk); return 0; } @@ -1154,12 +1157,16 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { - if (unlikely(sk->sk_policy[0] != NULL)) { - xfrm_policy_delete(sk->sk_policy[0], XFRM_POLICY_MAX); + struct xfrm_policy *pol; + + pol = rcu_dereference_protected(sk->sk_policy[0], 1); + if (unlikely(pol != NULL)) { + xfrm_policy_delete(pol, XFRM_POLICY_MAX); sk->sk_policy[0] = NULL; } - if (unlikely(sk->sk_policy[1] != NULL)) { - xfrm_policy_delete(sk->sk_policy[1], XFRM_POLICY_MAX+1); + pol = rcu_dereference_protected(sk->sk_policy[1], 1); + if (unlikely(pol != NULL)) { + xfrm_policy_delete(pol, XFRM_POLICY_MAX+1); sk->sk_policy[1] = NULL; } } @@ -1169,7 +1176,7 @@ void xfrm_garbage_collect(struct net *net); #else static inline void xfrm_sk_free_policy(struct sock *sk) {} -static inline int xfrm_sk_clone_policy(struct sock *sk) { return 0; } +static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h index 188df91d58514..ec9b44dd3d806 100644 --- a/include/rdma/ib_mad.h +++ b/include/rdma/ib_mad.h @@ -237,6 +237,8 @@ struct ib_vendor_mad { u8 data[IB_MGMT_VENDOR_DATA]; }; +#define IB_MGMT_CLASSPORTINFO_ATTR_ID cpu_to_be16(0x0001) + struct ib_class_port_info { u8 base_version; u8 class_version; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9a68a19532ba5..120da1d7f57eb 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1271,6 +1271,7 @@ struct ib_uobject { int id; /* index into kernel idr */ struct kref ref; struct rw_semaphore mutex; /* protects .live */ + struct rcu_head rcu; /* kfree_rcu() overhead */ int live; }; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index ed527121031dd..fcfa3d7f5e7e3 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -668,6 +668,9 @@ struct Scsi_Host { unsigned use_blk_mq:1; unsigned use_cmd_list:1; + /* Host responded with short (<36 bytes) INQUIRY result */ + unsigned short_inquiry:1; + /* * Optional work queue to be utilized by the transport */ diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h index 2ae8812d7b1a3..94dc6a9772e06 100644 --- a/include/sound/hda_register.h +++ b/include/sound/hda_register.h @@ -93,6 +93,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define AZX_REG_HSW_EM4 0x100c #define AZX_REG_HSW_EM5 0x1010 +/* Skylake/Broxton display HD-A controller Extended Mode registers */ +#define AZX_REG_SKL_EM4L 0x1040 + /* PCI space */ #define AZX_PCIREG_TCSEL 0x44 diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 7855cfe46b69a..95a937eafb794 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -398,6 +398,7 @@ int snd_soc_dapm_del_routes(struct snd_soc_dapm_context *dapm, int snd_soc_dapm_weak_routes(struct snd_soc_dapm_context *dapm, const struct snd_soc_dapm_route *route, int num); void snd_soc_dapm_free_widget(struct snd_soc_dapm_widget *w); +void snd_soc_dapm_reset_cache(struct snd_soc_dapm_context *dapm); /* dapm events */ void snd_soc_dapm_stream_event(struct snd_soc_pcm_runtime *rtd, int stream, diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 5c15c2a5c1235..fb8a416683828 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -87,4 +87,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 628e6e64c2fb4..c2e5d6cb34e36 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -186,6 +186,7 @@ header-y += if_tunnel.h header-y += if_vlan.h header-y += if_x25.h header-y += igmp.h +header-y += ila.h header-y += in6.h header-y += inet_diag.h header-y += in.h diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9ea2d22fa2cb5..8bed7f1176b88 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -269,6 +269,7 @@ enum bpf_func_id { * Return: 0 on success */ BPF_FUNC_perf_event_output, + BPF_FUNC_skb_load_bytes, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index cd1629170103e..57fa39005e794 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -542,6 +542,7 @@ struct ethtool_pauseparam { * now deprecated * @ETH_SS_FEATURES: Device feature names * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names + * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -551,6 +552,7 @@ enum ethtool_stringset { ETH_SS_FEATURES, ETH_SS_RSS_HASH_FUNCS, ETH_SS_TUNABLES, + ETH_SS_PHY_STATS, }; /** @@ -1225,6 +1227,7 @@ enum ethtool_sfeatures_retval_bits { #define ETHTOOL_SRSSH 0x00000047 /* Set RX flow hash configuration */ #define ETHTOOL_GTUNABLE 0x00000048 /* Get tunable configuration */ #define ETHTOOL_STUNABLE 0x00000049 /* Set tunable configuration */ +#define ETHTOOL_GPHYSTATS 0x0000004a /* get PHY-specific statistics */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5ad57375a99fd..a30b78090594d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -218,6 +218,7 @@ enum in6_addr_gen_mode { IN6_ADDR_GEN_MODE_EUI64, IN6_ADDR_GEN_MODE_NONE, IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, }; /* Bridge section */ @@ -462,6 +463,9 @@ enum { IFLA_GENEVE_PORT, /* destination port */ IFLA_GENEVE_COLLECT_METADATA, IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 7ed9e670814ed..abde7bbd6f3b7 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -3,13 +3,35 @@ #ifndef _UAPI_LINUX_ILA_H #define _UAPI_LINUX_ILA_H +/* NETLINK_GENERIC related info */ +#define ILA_GENL_NAME "ila" +#define ILA_GENL_VERSION 0x1 + enum { ILA_ATTR_UNSPEC, ILA_ATTR_LOCATOR, /* u64 */ + ILA_ATTR_IDENTIFIER, /* u64 */ + ILA_ATTR_LOCATOR_MATCH, /* u64 */ + ILA_ATTR_IFINDEX, /* s32 */ + ILA_ATTR_DIR, /* u32 */ __ILA_ATTR_MAX, }; #define ILA_ATTR_MAX (__ILA_ATTR_MAX - 1) +enum { + ILA_CMD_UNSPEC, + ILA_CMD_ADD, + ILA_CMD_DEL, + ILA_CMD_GET, + + __ILA_CMD_MAX, +}; + +#define ILA_CMD_MAX (__ILA_CMD_MAX - 1) + +#define ILA_DIR_IN (1 << 0) +#define ILA_DIR_OUT (1 << 1) + #endif /* _UAPI_LINUX_ILA_H */ diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 79b12b004ade0..318a4828bf98c 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -196,6 +196,7 @@ struct in6_flowlabel_req { #define IPV6_IPSEC_POLICY 34 #define IPV6_XFRM_POLICY 35 +#define IPV6_HDRINCL 36 #endif /* diff --git a/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h b/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h index 6a2c038d18885..fd5024d262697 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h @@ -1,6 +1,8 @@ #ifndef _UAPI__IP_SET_BITMAP_H #define _UAPI__IP_SET_BITMAP_H +#include <linux/netfilter/ipset/ip_set.h> + /* Bitmap type specific error codes */ enum { /* The element is out of the range of the set */ diff --git a/include/uapi/linux/netfilter/ipset/ip_set_hash.h b/include/uapi/linux/netfilter/ipset/ip_set_hash.h index 352eeccdc7f20..82deeb883ac48 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set_hash.h +++ b/include/uapi/linux/netfilter/ipset/ip_set_hash.h @@ -1,6 +1,8 @@ #ifndef _UAPI__IP_SET_HASH_H #define _UAPI__IP_SET_HASH_H +#include <linux/netfilter/ipset/ip_set.h> + /* Hash type specific error codes */ enum { /* Hash is full */ diff --git a/include/uapi/linux/netfilter/ipset/ip_set_list.h b/include/uapi/linux/netfilter/ipset/ip_set_list.h index a44efaa98213e..84d4303682666 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set_list.h +++ b/include/uapi/linux/netfilter/ipset/ip_set_list.h @@ -1,6 +1,8 @@ #ifndef _UAPI__IP_SET_LIST_H #define _UAPI__IP_SET_LIST_H +#include <linux/netfilter/ipset/ip_set.h> + /* List type specific error codes */ enum { /* Set name to be added/deleted/tested does not exist. */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index ed4e776e1242f..2cbc366c3fb47 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -1,5 +1,5 @@ -#ifndef _NF_CONNTRACK_SCTP_H -#define _NF_CONNTRACK_SCTP_H +#ifndef _UAPI_NF_CONNTRACK_SCTP_H +#define _UAPI_NF_CONNTRACK_SCTP_H /* SCTP tracking. */ #include <linux/netfilter/nf_conntrack_tuple_common.h> @@ -18,10 +18,4 @@ enum sctp_conntrack { SCTP_CONNTRACK_MAX }; -struct ip_ct_sctp { - enum sctp_conntrack state; - - __be32 vtag[IP_CT_DIR_MAX]; -}; - -#endif /* _NF_CONNTRACK_SCTP_H */ +#endif /* _UAPI_NF_CONNTRACK_SCTP_H */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h b/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h index 2f6bbc5b81254..a9c3834abdd41 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h @@ -1,6 +1,9 @@ #ifndef _NF_CONNTRACK_TUPLE_COMMON_H #define _NF_CONNTRACK_TUPLE_COMMON_H +#include <linux/types.h> +#include <linux/netfilter.h> + enum ip_conntrack_dir { IP_CT_DIR_ORIGINAL, IP_CT_DIR_REPLY, diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index d8c8a7c9d88a7..b48a3ab761f8e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -83,6 +83,7 @@ enum nft_verdicts { * @NFT_MSG_DELSETELEM: delete a set element (enum nft_set_elem_attributes) * @NFT_MSG_NEWGEN: announce a new generation, only for events (enum nft_gen_attributes) * @NFT_MSG_GETGEN: get the rule-set generation (enum nft_gen_attributes) + * @NFT_MSG_TRACE: trace event (enum nft_trace_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -102,6 +103,7 @@ enum nf_tables_msg_types { NFT_MSG_DELSETELEM, NFT_MSG_NEWGEN, NFT_MSG_GETGEN, + NFT_MSG_TRACE, NFT_MSG_MAX, }; @@ -598,12 +600,26 @@ enum nft_payload_bases { }; /** + * enum nft_payload_csum_types - nf_tables payload expression checksum types + * + * @NFT_PAYLOAD_CSUM_NONE: no checksumming + * @NFT_PAYLOAD_CSUM_INET: internet checksum (RFC 791) + */ +enum nft_payload_csum_types { + NFT_PAYLOAD_CSUM_NONE, + NFT_PAYLOAD_CSUM_INET, +}; + +/** * enum nft_payload_attributes - nf_tables payload expression netlink attributes * * @NFTA_PAYLOAD_DREG: destination register to load data into (NLA_U32: nft_registers) * @NFTA_PAYLOAD_BASE: payload base (NLA_U32: nft_payload_bases) * @NFTA_PAYLOAD_OFFSET: payload offset relative to base (NLA_U32) * @NFTA_PAYLOAD_LEN: payload length (NLA_U32) + * @NFTA_PAYLOAD_SREG: source register to load data from (NLA_U32: nft_registers) + * @NFTA_PAYLOAD_CSUM_TYPE: checksum type (NLA_U32) + * @NFTA_PAYLOAD_CSUM_OFFSET: checksum offset relative to base (NLA_U32) */ enum nft_payload_attributes { NFTA_PAYLOAD_UNSPEC, @@ -611,6 +627,9 @@ enum nft_payload_attributes { NFTA_PAYLOAD_BASE, NFTA_PAYLOAD_OFFSET, NFTA_PAYLOAD_LEN, + NFTA_PAYLOAD_SREG, + NFTA_PAYLOAD_CSUM_TYPE, + NFTA_PAYLOAD_CSUM_OFFSET, __NFTA_PAYLOAD_MAX }; #define NFTA_PAYLOAD_MAX (__NFTA_PAYLOAD_MAX - 1) @@ -970,4 +989,54 @@ enum nft_gen_attributes { }; #define NFTA_GEN_MAX (__NFTA_GEN_MAX - 1) +/** + * enum nft_trace_attributes - nf_tables trace netlink attributes + * + * @NFTA_TRACE_TABLE: name of the table (NLA_STRING) + * @NFTA_TRACE_CHAIN: name of the chain (NLA_STRING) + * @NFTA_TRACE_RULE_HANDLE: numeric handle of the rule (NLA_U64) + * @NFTA_TRACE_TYPE: type of the event (NLA_U32: nft_trace_types) + * @NFTA_TRACE_VERDICT: verdict returned by hook (NLA_NESTED: nft_verdicts) + * @NFTA_TRACE_ID: pseudo-id, same for each skb traced (NLA_U32) + * @NFTA_TRACE_LL_HEADER: linklayer header (NLA_BINARY) + * @NFTA_TRACE_NETWORK_HEADER: network header (NLA_BINARY) + * @NFTA_TRACE_TRANSPORT_HEADER: transport header (NLA_BINARY) + * @NFTA_TRACE_IIF: indev ifindex (NLA_U32) + * @NFTA_TRACE_IIFTYPE: netdev->type of indev (NLA_U16) + * @NFTA_TRACE_OIF: outdev ifindex (NLA_U32) + * @NFTA_TRACE_OIFTYPE: netdev->type of outdev (NLA_U16) + * @NFTA_TRACE_MARK: nfmark (NLA_U32) + * @NFTA_TRACE_NFPROTO: nf protocol processed (NLA_U32) + * @NFTA_TRACE_POLICY: policy that decided fate of packet (NLA_U32) + */ +enum nft_trace_attibutes { + NFTA_TRACE_UNSPEC, + NFTA_TRACE_TABLE, + NFTA_TRACE_CHAIN, + NFTA_TRACE_RULE_HANDLE, + NFTA_TRACE_TYPE, + NFTA_TRACE_VERDICT, + NFTA_TRACE_ID, + NFTA_TRACE_LL_HEADER, + NFTA_TRACE_NETWORK_HEADER, + NFTA_TRACE_TRANSPORT_HEADER, + NFTA_TRACE_IIF, + NFTA_TRACE_IIFTYPE, + NFTA_TRACE_OIF, + NFTA_TRACE_OIFTYPE, + NFTA_TRACE_MARK, + NFTA_TRACE_NFPROTO, + NFTA_TRACE_POLICY, + __NFTA_TRACE_MAX +}; +#define NFTA_TRACE_MAX (__NFTA_TRACE_MAX - 1) + +enum nft_trace_types { + NFT_TRACETYPE_UNSPEC, + NFT_TRACETYPE_POLICY, + NFT_TRACETYPE_RETURN, + NFT_TRACETYPE_RULE, + __NFT_TRACETYPE_MAX +}; +#define NFT_TRACETYPE_MAX (__NFT_TRACETYPE_MAX - 1) #endif /* _LINUX_NF_TABLES_H */ diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 354a7e5e50f22..4bb8cb7730e7d 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -22,6 +22,8 @@ enum nfnetlink_groups { #define NFNLGRP_NFTABLES NFNLGRP_NFTABLES NFNLGRP_ACCT_QUOTA, #define NFNLGRP_ACCT_QUOTA NFNLGRP_ACCT_QUOTA + NFNLGRP_NFTRACE, +#define NFNLGRP_NFTRACE NFNLGRP_NFTRACE __NFNLGRP_MAX, }; #define NFNLGRP_MAX (__NFNLGRP_MAX - 1) diff --git a/include/uapi/linux/netfilter/xt_HMARK.h b/include/uapi/linux/netfilter/xt_HMARK.h index 826fc58075777..3fb48c8d8d78f 100644 --- a/include/uapi/linux/netfilter/xt_HMARK.h +++ b/include/uapi/linux/netfilter/xt_HMARK.h @@ -2,6 +2,7 @@ #define XT_HMARK_H_ #include <linux/types.h> +#include <linux/netfilter.h> enum { XT_HMARK_SADDR_MASK, diff --git a/include/uapi/linux/netfilter/xt_RATEEST.h b/include/uapi/linux/netfilter/xt_RATEEST.h index 6605e20ad8cf0..ec1b57047e03f 100644 --- a/include/uapi/linux/netfilter/xt_RATEEST.h +++ b/include/uapi/linux/netfilter/xt_RATEEST.h @@ -2,6 +2,7 @@ #define _XT_RATEEST_TARGET_H #include <linux/types.h> +#include <linux/if.h> struct xt_rateest_target_info { char name[IFNAMSIZ]; diff --git a/include/uapi/linux/netfilter/xt_TEE.h b/include/uapi/linux/netfilter/xt_TEE.h index 5c21d5c829aff..01092023404b9 100644 --- a/include/uapi/linux/netfilter/xt_TEE.h +++ b/include/uapi/linux/netfilter/xt_TEE.h @@ -1,6 +1,8 @@ #ifndef _XT_TEE_TARGET_H #define _XT_TEE_TARGET_H +#include <linux/netfilter.h> + struct xt_tee_tginfo { union nf_inet_addr gw; char oif[16]; diff --git a/include/uapi/linux/netfilter/xt_TPROXY.h b/include/uapi/linux/netfilter/xt_TPROXY.h index 902043c2073ff..8d693eefdc1f9 100644 --- a/include/uapi/linux/netfilter/xt_TPROXY.h +++ b/include/uapi/linux/netfilter/xt_TPROXY.h @@ -2,6 +2,7 @@ #define _XT_TPROXY_H #include <linux/types.h> +#include <linux/netfilter.h> /* TPROXY target is capable of marking the packet to perform * redirection. We can get rid of that whenever we get support for diff --git a/include/uapi/linux/netfilter/xt_cgroup.h b/include/uapi/linux/netfilter/xt_cgroup.h index 43acb7e175f60..1e4b37b93befd 100644 --- a/include/uapi/linux/netfilter/xt_cgroup.h +++ b/include/uapi/linux/netfilter/xt_cgroup.h @@ -2,10 +2,23 @@ #define _UAPI_XT_CGROUP_H #include <linux/types.h> +#include <linux/limits.h> -struct xt_cgroup_info { +struct xt_cgroup_info_v0 { __u32 id; __u32 invert; }; +struct xt_cgroup_info_v1 { + __u8 has_path; + __u8 has_classid; + __u8 invert_path; + __u8 invert_classid; + char path[PATH_MAX]; + __u32 classid; + + /* kernel internal data */ + void *priv __attribute__((aligned(8))); +}; + #endif /* _UAPI_XT_CGROUP_H */ diff --git a/include/uapi/linux/netfilter/xt_hashlimit.h b/include/uapi/linux/netfilter/xt_hashlimit.h index cbfc43d1af681..6db90372f09c3 100644 --- a/include/uapi/linux/netfilter/xt_hashlimit.h +++ b/include/uapi/linux/netfilter/xt_hashlimit.h @@ -2,6 +2,7 @@ #define _UAPI_XT_HASHLIMIT_H #include <linux/types.h> +#include <linux/if.h> /* timings are in milliseconds. */ #define XT_HASHLIMIT_SCALE 10000 diff --git a/include/uapi/linux/netfilter/xt_ipvs.h b/include/uapi/linux/netfilter/xt_ipvs.h index eff34ac188088..e03b9c31a39dd 100644 --- a/include/uapi/linux/netfilter/xt_ipvs.h +++ b/include/uapi/linux/netfilter/xt_ipvs.h @@ -2,6 +2,7 @@ #define _XT_IPVS_H #include <linux/types.h> +#include <linux/netfilter.h> enum { XT_IPVS_IPVS_PROPERTY = 1 << 0, /* all other options imply this one */ diff --git a/include/uapi/linux/netfilter/xt_mac.h b/include/uapi/linux/netfilter/xt_mac.h index b892cdc67e069..9a19a08a9181c 100644 --- a/include/uapi/linux/netfilter/xt_mac.h +++ b/include/uapi/linux/netfilter/xt_mac.h @@ -1,6 +1,8 @@ #ifndef _XT_MAC_H #define _XT_MAC_H +#include <linux/if_ether.h> + struct xt_mac_info { unsigned char srcaddr[ETH_ALEN]; int invert; diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index 5d66caeba3eec..e6159958b2fb0 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -20,6 +20,8 @@ #define _XT_OSF_H #include <linux/types.h> +#include <linux/ip.h> +#include <linux/tcp.h> #define MAXGENRELEN 32 diff --git a/include/uapi/linux/netfilter/xt_physdev.h b/include/uapi/linux/netfilter/xt_physdev.h index db7a2982e9c0d..ccdde87da2145 100644 --- a/include/uapi/linux/netfilter/xt_physdev.h +++ b/include/uapi/linux/netfilter/xt_physdev.h @@ -2,7 +2,7 @@ #define _UAPI_XT_PHYSDEV_H #include <linux/types.h> - +#include <linux/if.h> #define XT_PHYSDEV_OP_IN 0x01 #define XT_PHYSDEV_OP_OUT 0x02 diff --git a/include/uapi/linux/netfilter/xt_policy.h b/include/uapi/linux/netfilter/xt_policy.h index be8ead05c3164..d8a9800dce613 100644 --- a/include/uapi/linux/netfilter/xt_policy.h +++ b/include/uapi/linux/netfilter/xt_policy.h @@ -2,6 +2,8 @@ #define _XT_POLICY_H #include <linux/types.h> +#include <linux/in.h> +#include <linux/in6.h> #define XT_POLICY_MAX_ELEM 4 diff --git a/include/uapi/linux/netfilter/xt_rateest.h b/include/uapi/linux/netfilter/xt_rateest.h index d40a6196842ab..13fe50d4e4b3a 100644 --- a/include/uapi/linux/netfilter/xt_rateest.h +++ b/include/uapi/linux/netfilter/xt_rateest.h @@ -2,6 +2,7 @@ #define _XT_RATEEST_MATCH_H #include <linux/types.h> +#include <linux/if.h> enum xt_rateest_match_flags { XT_RATEEST_MATCH_INVERT = 1<<0, diff --git a/include/uapi/linux/netfilter/xt_recent.h b/include/uapi/linux/netfilter/xt_recent.h index 6ef36c113e89d..955d562031ccb 100644 --- a/include/uapi/linux/netfilter/xt_recent.h +++ b/include/uapi/linux/netfilter/xt_recent.h @@ -2,6 +2,7 @@ #define _LINUX_NETFILTER_XT_RECENT_H 1 #include <linux/types.h> +#include <linux/netfilter.h> enum { XT_RECENT_CHECK = 1 << 0, diff --git a/include/uapi/linux/netfilter/xt_sctp.h b/include/uapi/linux/netfilter/xt_sctp.h index 29287be696a26..58ffcfb7978e7 100644 --- a/include/uapi/linux/netfilter/xt_sctp.h +++ b/include/uapi/linux/netfilter/xt_sctp.h @@ -66,26 +66,26 @@ struct xt_sctp_info { #define SCTP_CHUNKMAP_IS_CLEAR(chunkmap) \ __sctp_chunkmap_is_clear((chunkmap), ARRAY_SIZE(chunkmap)) -static inline bool +static inline _Bool __sctp_chunkmap_is_clear(const __u32 *chunkmap, unsigned int n) { unsigned int i; for (i = 0; i < n; ++i) if (chunkmap[i]) - return false; - return true; + return 0; + return 1; } #define SCTP_CHUNKMAP_IS_ALL_SET(chunkmap) \ __sctp_chunkmap_is_all_set((chunkmap), ARRAY_SIZE(chunkmap)) -static inline bool +static inline _Bool __sctp_chunkmap_is_all_set(const __u32 *chunkmap, unsigned int n) { unsigned int i; for (i = 0; i < n; ++i) if (chunkmap[i] != ~0U) - return false; - return true; + return 0; + return 1; } #endif /* _XT_SCTP_H_ */ diff --git a/include/uapi/linux/netfilter_arp/arp_tables.h b/include/uapi/linux/netfilter_arp/arp_tables.h index a5a86a4db6b3f..ece3ad4eecda2 100644 --- a/include/uapi/linux/netfilter_arp/arp_tables.h +++ b/include/uapi/linux/netfilter_arp/arp_tables.h @@ -11,6 +11,7 @@ #include <linux/types.h> #include <linux/compiler.h> +#include <linux/if.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index a5eda6db8d79c..514519b47651f 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -4,6 +4,7 @@ /* bridge-specific defines for netfilter. */ +#include <linux/in.h> #include <linux/netfilter.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> diff --git a/include/uapi/linux/netfilter_bridge/ebt_arp.h b/include/uapi/linux/netfilter_bridge/ebt_arp.h index 522f3e427f49e..dd4df25330e84 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_arp.h +++ b/include/uapi/linux/netfilter_bridge/ebt_arp.h @@ -2,6 +2,7 @@ #define __LINUX_BRIDGE_EBT_ARP_H #include <linux/types.h> +#include <linux/if_ether.h> #define EBT_ARP_OPCODE 0x01 #define EBT_ARP_HTYPE 0x02 diff --git a/include/uapi/linux/netfilter_bridge/ebt_arpreply.h b/include/uapi/linux/netfilter_bridge/ebt_arpreply.h index 7e77896e1fbf0..6fee3402e3079 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_arpreply.h +++ b/include/uapi/linux/netfilter_bridge/ebt_arpreply.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_ARPREPLY_H #define __LINUX_BRIDGE_EBT_ARPREPLY_H +#include <linux/if_ether.h> + struct ebt_arpreply_info { unsigned char mac[ETH_ALEN]; int target; diff --git a/include/uapi/linux/netfilter_bridge/ebt_ip6.h b/include/uapi/linux/netfilter_bridge/ebt_ip6.h index 42b8896827217..a062f0ce95f95 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_ip6.h +++ b/include/uapi/linux/netfilter_bridge/ebt_ip6.h @@ -13,6 +13,7 @@ #define __LINUX_BRIDGE_EBT_IP6_H #include <linux/types.h> +#include <linux/in6.h> #define EBT_IP6_SOURCE 0x01 #define EBT_IP6_DEST 0x02 diff --git a/include/uapi/linux/netfilter_bridge/ebt_nat.h b/include/uapi/linux/netfilter_bridge/ebt_nat.h index 5e74e3b03bd6b..c990d74ee9666 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_nat.h +++ b/include/uapi/linux/netfilter_bridge/ebt_nat.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_NAT_H #define __LINUX_BRIDGE_EBT_NAT_H +#include <linux/if_ether.h> + #define NAT_ARP_BIT (0x00000010) struct ebt_nat_info { unsigned char mac[ETH_ALEN]; diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index fd2ee501726d6..e3cdf9f1a259c 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -12,6 +12,8 @@ #ifndef _UAPI__LINUX_BRIDGE_EFF_H #define _UAPI__LINUX_BRIDGE_EFF_H +#include <linux/types.h> +#include <linux/if.h> #include <linux/netfilter_bridge.h> #define EBT_TABLE_MAXNAMELEN 32 @@ -33,8 +35,8 @@ struct xt_match; struct xt_target; struct ebt_counter { - uint64_t pcnt; - uint64_t bcnt; + __u64 pcnt; + __u64 bcnt; }; struct ebt_replace { diff --git a/include/uapi/linux/netfilter_ipv4/ip_tables.h b/include/uapi/linux/netfilter_ipv4/ip_tables.h index f1e6ef2560342..d0da53d96d930 100644 --- a/include/uapi/linux/netfilter_ipv4/ip_tables.h +++ b/include/uapi/linux/netfilter_ipv4/ip_tables.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/compiler.h> +#include <linux/if.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter/x_tables.h> diff --git a/include/uapi/linux/netfilter_ipv6/ip6_tables.h b/include/uapi/linux/netfilter_ipv6/ip6_tables.h index 649c68062dcaf..d1b22653daf2c 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6_tables.h +++ b/include/uapi/linux/netfilter_ipv6/ip6_tables.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/compiler.h> +#include <linux/if.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter/x_tables.h> diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_rt.h b/include/uapi/linux/netfilter_ipv6/ip6t_rt.h index 7605a5ff81cd6..558f81e46fb94 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_rt.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_rt.h @@ -2,7 +2,7 @@ #define _IP6T_RT_H #include <linux/types.h> -/*#include <linux/in6.h>*/ +#include <linux/in6.h> #define IP6T_RT_HOPS 16 diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 28ccedd000f57..a27222d5b413a 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -628,7 +628,7 @@ struct ovs_action_hash { * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection * tracking mark field in the connection. - * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN + * @OVS_CT_ATTR_LABELS: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN * mask. For each bit set in the mask, the corresponding bit in the value is * copied to the connection tracking label field in the connection. * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 123a5af4e8bb5..ca764b5da86da 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -311,6 +311,7 @@ enum rtattr_type_t { RTA_PREF, RTA_ENCAP_TYPE, RTA_ENCAP, + RTA_EXPIRES, __RTA_MAX }; diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h index 49230d36f9ce7..bae2d80034d4a 100644 --- a/include/uapi/linux/sock_diag.h +++ b/include/uapi/linux/sock_diag.h @@ -4,6 +4,7 @@ #include <linux/types.h> #define SOCK_DIAG_BY_FAMILY 20 +#define SOCK_DESTROY 21 struct sock_diag_req { __u8 sdiag_family; diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h index e888b1aed69f8..8e7890b26d9ab 100644 --- a/include/uapi/linux/sockios.h +++ b/include/uapi/linux/sockios.h @@ -27,7 +27,7 @@ /* Routing table calls. */ #define SIOCADDRT 0x890B /* add routing table entry */ #define SIOCDELRT 0x890C /* delete routing table entry */ -#define SIOCRTMSG 0x890D /* call to routing system */ +#define SIOCRTMSG 0x890D /* unused */ /* Socket configuration controls. */ #define SIOCGIFNAME 0x8910 /* get iface name */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 751b69f858c80..9fd7b5d8df2fa 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -39,13 +39,6 @@ #define VFIO_SPAPR_TCE_v2_IOMMU 7 /* - * The No-IOMMU IOMMU offers no translation or isolation for devices and - * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU - * code will taint the host kernel and should be used with extreme caution. - */ -#define VFIO_NOIOMMU_IOMMU 8 - -/* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between * kernel and userspace. We therefore use the _IO() macro for these diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index 85dedca3dcfb0..eeba75395f7d1 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -343,7 +343,6 @@ struct ipu_client_platformdata { int di; int dc; int dp; - int dmfc; int dma[2]; }; diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 7d28aff605c7e..7dc685b4057d3 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -181,6 +181,20 @@ struct __name##_back_ring { \ #define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) +/* + * Get a local copy of a request. + * + * Use this in preference to RING_GET_REQUEST() so all processing is + * done on a local copy that cannot be modified by the other end. + * + * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this + * to be ineffective where _req is a struct which consists of only bitfields. + */ +#define RING_COPY_REQUEST(_r, _idx, _req) do { \ + /* Use volatile to force the copy into _req. */ \ + *(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \ +} while (0) + #define RING_GET_RESPONSE(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) diff --git a/init/Kconfig b/init/Kconfig index c24b6f767bf0f..235c7a2c0d200 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2030,13 +2030,6 @@ config INIT_ALL_POSSIBLE it was better to provide this option than to break all the archs and have several arch maintainers pursuing me down dark alleys. -config STOP_MACHINE - bool - default y - depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU - help - Need stop_machine() primitive. - source "block/Kconfig" config PREEMPT_NOTIFIERS diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 334b1bdd572c1..972d9a8e4ac4d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -306,10 +306,6 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; ARG1 = (u64) (unsigned long) ctx; - /* Registers used in classic BPF programs need to be reset first. */ - regs[BPF_REG_A] = 0; - regs[BPF_REG_X] = 0; - select_insn: goto *jumptable[insn->code]; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 34777b3746fad..c5b30fd8a3151 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -14,11 +14,15 @@ #include <linux/filter.h> #include <linux/vmalloc.h> +struct bucket { + struct hlist_head head; + raw_spinlock_t lock; +}; + struct bpf_htab { struct bpf_map map; - struct hlist_head *buckets; - raw_spinlock_t lock; - u32 count; /* number of elements in this hashtable */ + struct bucket *buckets; + atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ }; @@ -79,34 +83,35 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct hlist_head)) + htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; - if ((u64) htab->n_buckets * sizeof(struct hlist_head) + + if ((u64) htab->n_buckets * sizeof(struct bucket) + (u64) htab->elem_size * htab->map.max_entries >= U32_MAX - PAGE_SIZE) /* make sure page count doesn't overflow */ goto free_htab; - htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) + + htab->map.pages = round_up(htab->n_buckets * sizeof(struct bucket) + htab->elem_size * htab->map.max_entries, PAGE_SIZE) >> PAGE_SHIFT; err = -ENOMEM; - htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head), + htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), GFP_USER | __GFP_NOWARN); if (!htab->buckets) { - htab->buckets = vmalloc(htab->n_buckets * sizeof(struct hlist_head)); + htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket)); if (!htab->buckets) goto free_htab; } - for (i = 0; i < htab->n_buckets; i++) - INIT_HLIST_HEAD(&htab->buckets[i]); + for (i = 0; i < htab->n_buckets; i++) { + INIT_HLIST_HEAD(&htab->buckets[i].head); + raw_spin_lock_init(&htab->buckets[i].lock); + } - raw_spin_lock_init(&htab->lock); - htab->count = 0; + atomic_set(&htab->count, 0); return &htab->map; @@ -120,11 +125,16 @@ static inline u32 htab_map_hash(const void *key, u32 key_len) return jhash(key, key_len, 0); } -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) { return &htab->buckets[hash & (htab->n_buckets - 1)]; } +static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &__select_bucket(htab, hash)->head; +} + static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, void *key, u32 key_size) { @@ -227,6 +237,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old; struct hlist_head *head; + struct bucket *b; unsigned long flags; u32 key_size; int ret; @@ -248,15 +259,15 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, memcpy(l_new->key + round_up(key_size, 8), value, map->value_size); l_new->hash = htab_map_hash(l_new->key, key_size); + b = __select_bucket(htab, l_new->hash); + head = &b->head; /* bpf_map_update_elem() can be called in_irq() */ - raw_spin_lock_irqsave(&htab->lock, flags); - - head = select_bucket(htab, l_new->hash); + raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, l_new->hash, key, key_size); - if (!l_old && unlikely(htab->count >= map->max_entries)) { + if (!l_old && unlikely(atomic_read(&htab->count) >= map->max_entries)) { /* if elem with this 'key' doesn't exist and we've reached * max_entries limit, fail insertion of new elem */ @@ -284,13 +295,13 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hlist_del_rcu(&l_old->hash_node); kfree_rcu(l_old, rcu); } else { - htab->count++; + atomic_inc(&htab->count); } - raw_spin_unlock_irqrestore(&htab->lock, flags); + raw_spin_unlock_irqrestore(&b->lock, flags); return 0; err: - raw_spin_unlock_irqrestore(&htab->lock, flags); + raw_spin_unlock_irqrestore(&b->lock, flags); kfree(l_new); return ret; } @@ -300,6 +311,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_head *head; + struct bucket *b; struct htab_elem *l; unsigned long flags; u32 hash, key_size; @@ -310,21 +322,21 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) key_size = map->key_size; hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; - raw_spin_lock_irqsave(&htab->lock, flags); - - head = select_bucket(htab, hash); + raw_spin_lock_irqsave(&b->lock, flags); l = lookup_elem_raw(head, hash, key, key_size); if (l) { hlist_del_rcu(&l->hash_node); - htab->count--; + atomic_dec(&htab->count); kfree_rcu(l, rcu); ret = 0; } - raw_spin_unlock_irqrestore(&htab->lock, flags); + raw_spin_unlock_irqrestore(&b->lock, flags); return ret; } @@ -339,7 +351,7 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); - htab->count--; + atomic_dec(&htab->count); kfree(l); } } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 5a8a797d50b74..f2ece3c174a5b 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -187,11 +187,31 @@ static int bpf_mkobj(struct inode *dir, struct dentry *dentry, umode_t mode, } } +static int bpf_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry) +{ + if (bpf_dname_reserved(new_dentry)) + return -EPERM; + + return simple_link(old_dentry, dir, new_dentry); +} + +static int bpf_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + if (bpf_dname_reserved(new_dentry)) + return -EPERM; + + return simple_rename(old_dir, old_dentry, new_dir, new_dentry); +} + static const struct inode_operations bpf_dir_iops = { .lookup = simple_lookup, .mknod = bpf_mkobj, .mkdir = bpf_mkdir, .rmdir = simple_rmdir, + .rename = bpf_rename, + .link = bpf_link, .unlink = simple_unlink, }; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4f8f7927b4222..fe95970b1f799 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -98,6 +98,12 @@ static DEFINE_SPINLOCK(css_set_lock); static DEFINE_SPINLOCK(cgroup_idr_lock); /* + * Protects cgroup_file->kn for !self csses. It synchronizes notifications + * against file removal/re-creation across css hiding. + */ +static DEFINE_SPINLOCK(cgroup_file_kn_lock); + +/* * Protects cgroup_subsys->release_agent_path. Modifying it also requires * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. */ @@ -730,9 +736,11 @@ static void put_css_set_locked(struct css_set *cset) if (!atomic_dec_and_test(&cset->refcount)) return; - /* This css_set is dead. unlink it and release cgroup refcounts */ - for_each_subsys(ss, ssid) + /* This css_set is dead. unlink it and release cgroup and css refs */ + for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); + css_put(cset->subsys[ssid]); + } hash_del(&cset->hlist); css_set_count--; @@ -1032,9 +1040,13 @@ static struct css_set *find_css_set(struct css_set *old_cset, key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); - for_each_subsys(ss, ssid) + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cset->subsys[ssid]; + list_add_tail(&cset->e_cset_node[ssid], - &cset->subsys[ssid]->cgroup->e_csets[ssid]); + &css->cgroup->e_csets[ssid]); + css_get(css); + } spin_unlock_bh(&css_set_lock); @@ -1369,6 +1381,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); + + if (cft->file_offset) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); + struct cgroup_file *cfile = (void *)css + cft->file_offset; + + spin_lock_irq(&cgroup_file_kn_lock); + cfile->kn = NULL; + spin_unlock_irq(&cgroup_file_kn_lock); + } + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } @@ -1832,7 +1854,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); - INIT_LIST_HEAD(&cgrp->self.files); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); @@ -2193,6 +2214,9 @@ struct cgroup_taskset { struct list_head src_csets; struct list_head dst_csets; + /* the subsys currently being processed */ + int ssid; + /* * Fields for cgroup_taskset_*() iteration. * @@ -2255,25 +2279,29 @@ static void cgroup_taskset_add(struct task_struct *task, /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; - return cgroup_taskset_next(tset); + return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; @@ -2288,6 +2316,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; + + /* + * This function may be called both before and + * after cgroup_taskset_migrate(). The two cases + * can be distinguished by looking at whether @cset + * has its ->mg_dst_cset set. + */ + if (cset->mg_dst_cset) + *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; + else + *dst_cssp = cset->subsys[tset->ssid]; + return task; } @@ -2323,7 +2363,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, /* check that we can legitimately attach to the cgroup */ for_each_e_css(css, i, dst_cgrp) { if (css->ss->can_attach) { - ret = css->ss->can_attach(css, tset); + tset->ssid = i; + ret = css->ss->can_attach(tset); if (ret) { failed_css = css; goto out_cancel_attach; @@ -2356,9 +2397,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - for_each_e_css(css, i, dst_cgrp) - if (css->ss->attach) - css->ss->attach(css, tset); + for_each_e_css(css, i, dst_cgrp) { + if (css->ss->attach) { + tset->ssid = i; + css->ss->attach(tset); + } + } ret = 0; goto out_release_tset; @@ -2367,8 +2411,10 @@ out_cancel_attach: for_each_e_css(css, i, dst_cgrp) { if (css == failed_css) break; - if (css->ss->cancel_attach) - css->ss->cancel_attach(css, tset); + if (css->ss->cancel_attach) { + tset->ssid = i; + css->ss->cancel_attach(tset); + } } out_release_tset: spin_lock_bh(&css_set_lock); @@ -3290,9 +3336,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; - kernfs_get(kn); + spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; - list_add(&cfile->node, &css->files); + spin_unlock_irq(&cgroup_file_kn_lock); } return 0; @@ -3530,6 +3576,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) } /** + * cgroup_file_notify - generate a file modified event for a cgroup_file + * @cfile: target cgroup_file + * + * @cfile must have been obtained by setting cftype->file_offset. + */ +void cgroup_file_notify(struct cgroup_file *cfile) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_file_kn_lock, flags); + if (cfile->kn) + kernfs_notify(cfile->kn); + spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); +} + +/** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question * @@ -4590,13 +4652,9 @@ static void css_free_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; - struct cgroup_file *cfile; percpu_ref_exit(&css->refcnt); - list_for_each_entry(cfile, &css->files, node) - kernfs_put(cfile->kn); - if (ss) { /* css free path */ int id = css->id; @@ -4701,7 +4759,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css->ss = ss; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); - INIT_LIST_HEAD(&css->files); css->serial_nr = css_serial_nr_next++; if (cgroup_parent(cgrp)) { @@ -5790,7 +5847,7 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path); #if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) -spinlock_t cgroup_sk_update_lock; +DEFINE_SPINLOCK(cgroup_sk_update_lock); static bool cgroup_sk_alloc_disabled __read_mostly; void cgroup_sk_alloc_disable(void) diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index f1b30ad5dc6d9..2d3df82c54f2d 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -155,12 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css) * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ -static void freezer_attach(struct cgroup_subsys_state *new_css, - struct cgroup_taskset *tset) +static void freezer_attach(struct cgroup_taskset *tset) { - struct freezer *freezer = css_freezer(new_css); struct task_struct *task; - bool clear_frozen = false; + struct cgroup_subsys_state *new_css; mutex_lock(&freezer_mutex); @@ -174,22 +172,21 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, new_css, tset) { + struct freezer *freezer = css_freezer(new_css); + if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { freeze_task(task); - freezer->state &= ~CGROUP_FROZEN; - clear_frozen = true; + /* clear FROZEN and propagate upwards */ + while (freezer && (freezer->state & CGROUP_FROZEN)) { + freezer->state &= ~CGROUP_FROZEN; + freezer = parent_freezer(freezer); + } } } - /* propagate FROZEN clearing upwards */ - while (clear_frozen && (freezer = parent_freezer(freezer))) { - freezer->state &= ~CGROUP_FROZEN; - clear_frozen = freezer->state & CGROUP_FREEZING; - } - mutex_unlock(&freezer_mutex); } diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index cdd8df4e991c7..b50d5a167fda7 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -106,7 +106,7 @@ static void pids_uncharge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; - for (p = pids; p; p = parent_pids(p)) + for (p = pids; parent_pids(p); p = parent_pids(p)) pids_cancel(p, num); } @@ -123,7 +123,7 @@ static void pids_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; - for (p = pids; p; p = parent_pids(p)) + for (p = pids; parent_pids(p); p = parent_pids(p)) atomic64_add(num, &p->counter); } @@ -140,7 +140,7 @@ static int pids_try_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p, *q; - for (p = pids; p; p = parent_pids(p)) { + for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); /* @@ -162,13 +162,13 @@ revert: return -EAGAIN; } -static int pids_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int pids_can_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; @@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css, return 0; } -static void pids_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void pids_cancel_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; @@ -205,65 +205,28 @@ static void pids_cancel_attach(struct cgroup_subsys_state *css, } } +/* + * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies + * on threadgroup_change_begin() held by the copy_process(). + */ static int pids_can_fork(struct task_struct *task, void **priv_p) { struct cgroup_subsys_state *css; struct pids_cgroup *pids; - int err; - /* - * Use the "current" task_css for the pids subsystem as the tentative - * css. It is possible we will charge the wrong hierarchy, in which - * case we will forcefully revert/reapply the charge on the right - * hierarchy after it is committed to the task proper. - */ - css = task_get_css(current, pids_cgrp_id); + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - - err = pids_try_charge(pids, 1); - if (err) - goto err_css_put; - - *priv_p = css; - return 0; - -err_css_put: - css_put(css); - return err; + return pids_try_charge(pids, 1); } static void pids_cancel_fork(struct task_struct *task, void *priv) { - struct cgroup_subsys_state *css = priv; - struct pids_cgroup *pids = css_pids(css); - - pids_uncharge(pids, 1); - css_put(css); -} - -static void pids_fork(struct task_struct *task, void *priv) -{ struct cgroup_subsys_state *css; - struct cgroup_subsys_state *old_css = priv; struct pids_cgroup *pids; - struct pids_cgroup *old_pids = css_pids(old_css); - css = task_get_css(task, pids_cgrp_id); + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - - /* - * If the association has changed, we have to revert and reapply the - * charge/uncharge on the wrong hierarchy to the current one. Since - * the association can only change due to an organisation event, its - * okay for us to ignore the limit in this case. - */ - if (pids != old_pids) { - pids_uncharge(old_pids, 1); - pids_charge(pids, 1); - } - - css_put(css); - css_put(old_css); + pids_uncharge(pids, 1); } static void pids_free(struct task_struct *task) @@ -335,6 +298,7 @@ static struct cftype pids_files[] = { { .name = "current", .read_s64 = pids_current_read, + .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; @@ -346,7 +310,6 @@ struct cgroup_subsys pids_cgrp_subsys = { .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, - .fork = pids_fork, .free = pids_free, .legacy_cftypes = pids_files, .dfl_cftypes = pids_files, diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 10ae73611d80a..02a8ea5c99632 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpuset_can_attach(struct cgroup_taskset *tset) { - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ - cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) goto out_unlock; @@ -1467,9 +1468,14 @@ out_unlock: return ret; } -static void cpuset_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_cancel_attach(struct cgroup_taskset *tset) { + struct cgroup_subsys_state *css; + struct cpuset *cs; + + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); css_cs(css)->attach_in_progress--; mutex_unlock(&cpuset_mutex); @@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css, */ static cpumask_var_t cpus_attach; -static void cpuset_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); /* prepare for attach */ @@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, guarantee_online_mems(cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index d659487254d5d..9c418002b8c1f 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/core.c b/kernel/events/core.c index 36babfd206484..ef2d6ea10736e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * * For licensing details see kernel-base/COPYING @@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current); + cgrp = perf_cgroup_from_task(current, event->ctx); /* * Do not update time when cgroup is not active */ @@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, if (!task || !ctx->nr_cgroups) return; - cgrp = perf_cgroup_from_task(task); + cgrp = perf_cgroup_from_task(task, ctx); info = this_cpu_ptr(cgrp->info); info->timestamp = ctx->timestamp; } @@ -489,7 +489,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * we reschedule only in the presence of cgroup * constrained events. */ - rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); @@ -522,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * set cgrp before ctxsw in to allow * event_filter_match() to not have to pass * task around + * we pass the cpuctx->ctx to perf_cgroup_from_task() + * because cgorup events are only per-cpu */ - cpuctx->cgrp = perf_cgroup_from_task(task); + cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); } perf_pmu_enable(cpuctx->ctx.pmu); @@ -531,8 +532,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) } } - rcu_read_unlock(); - local_irq_restore(flags); } @@ -542,17 +541,20 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, struct perf_cgroup *cgrp1; struct perf_cgroup *cgrp2 = NULL; + rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* * next is NULL when called from perf_event_enable_on_exec() * that will systematically cause a cgroup_switch() */ if (next) - cgrp2 = perf_cgroup_from_task(next); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -561,6 +563,8 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, */ if (cgrp1 != cgrp2) perf_cgroup_switch(task, PERF_CGROUP_SWOUT); + + rcu_read_unlock(); } static inline void perf_cgroup_sched_in(struct task_struct *prev, @@ -569,13 +573,16 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, struct perf_cgroup *cgrp1; struct perf_cgroup *cgrp2 = NULL; + rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* prev can never be NULL */ - cgrp2 = perf_cgroup_from_task(prev); + cgrp2 = perf_cgroup_from_task(prev, NULL); /* * only need to schedule in cgroup events if we are changing @@ -584,6 +591,8 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, */ if (cgrp1 != cgrp2) perf_cgroup_switch(task, PERF_CGROUP_SWIN); + + rcu_read_unlock(); } static inline int perf_cgroup_connect(int fd, struct perf_event *event, @@ -4216,7 +4225,14 @@ retry: goto retry; } - __perf_event_period(&pe); + if (event->attr.freq) { + event->attr.sample_freq = value; + } else { + event->attr.sample_period = value; + event->hw.sample_period = value; + } + + local64_set(&event->hw.period_left, 0); raw_spin_unlock_irq(&ctx->lock); return 0; @@ -5667,6 +5683,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx, } static void +perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data, + struct perf_event_context *task_ctx) +{ + rcu_read_lock(); + preempt_disable(); + perf_event_aux_ctx(task_ctx, output, data); + preempt_enable(); + rcu_read_unlock(); +} + +static void perf_event_aux(perf_event_aux_output_cb output, void *data, struct perf_event_context *task_ctx) { @@ -5675,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, struct pmu *pmu; int ctxn; + /* + * If we have task_ctx != NULL we only notify + * the task context itself. The task_ctx is set + * only for EXIT events before releasing task + * context. + */ + if (task_ctx) { + perf_event_aux_task_ctx(output, data, task_ctx); + return; + } + rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); if (cpuctx->unique_pmu != pmu) goto next; perf_event_aux_ctx(&cpuctx->ctx, output, data); - if (task_ctx) - goto next; ctxn = pmu->task_ctx_nr; if (ctxn < 0) goto next; @@ -5692,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, next: put_cpu_ptr(pmu->pmu_cpu_context); } - - if (task_ctx) { - preempt_disable(); - perf_event_aux_ctx(task_ctx, output, data); - preempt_enable(); - } rcu_read_unlock(); } @@ -8787,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) struct perf_event_context *child_ctx, *clone_ctx = NULL; unsigned long flags; - if (likely(!child->perf_event_ctxp[ctxn])) { - perf_event_task(child, NULL, 0); + if (likely(!child->perf_event_ctxp[ctxn])) return; - } local_irq_save(flags); /* @@ -8874,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child) for_each_task_context_nr(ctxn) perf_event_exit_task_context(child, ctxn); + + /* + * The perf_event_exit_task_context calls perf_event_task + * with child's task_ctx, which generates EXIT events for + * child contexts and sets child->perf_event_ctxp[] to NULL. + * At this point we need to send EXIT events to cpu contexts. + */ + perf_event_task(child, NULL, 0); } static void perf_free_event(struct perf_event *event, @@ -9452,16 +9488,18 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css) static int __perf_cgroup_move(void *info) { struct task_struct *task = info; + rcu_read_lock(); perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + rcu_read_unlock(); return 0; } -static void perf_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void perf_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) task_function_call(task, __perf_cgroup_move, task); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index b5d1ea79c5953..adfdc0536117c 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4e5e9798aa0c0..7dad84913abfb 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -19,7 +19,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> diff --git a/kernel/fork.c b/kernel/fork.c index f97f2c449f5cf..fce002ee3ddff 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1368,8 +1368,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; - if (clone_flags & CLONE_THREAD) - threadgroup_change_begin(current); + threadgroup_change_begin(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1610,8 +1609,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, proc_fork_connector(p); cgroup_post_fork(p, cgrp_ss_priv); - if (clone_flags & CLONE_THREAD) - threadgroup_change_end(current); + threadgroup_change_end(current); perf_event_fork(p); trace_task_newtask(p, clone_flags); @@ -1652,8 +1650,7 @@ bad_fork_cleanup_policy: mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif - if (clone_flags & CLONE_THREAD) - threadgroup_change_end(current); + threadgroup_change_end(current); delayacct_tsk_free(p); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index cbf9fb899d929..bcf107ce08545 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. diff --git a/kernel/jump_label.c b/kernel/jump_label.c index f7dd15d537f9b..05254eeb4b4e4 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -2,7 +2,7 @@ * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> - * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index deae3907ac1ee..60ace56618f6c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * this code maps all the lock dependencies as they occur in a live kernel * and will warn about the following classes of locking bugs: diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index d83d798bef95a..dbb61a3025484 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Code for /proc/lockdep and /proc/lockdep_stats: * diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index d092a0c9c2d4e..05a37857ab551 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -93,10 +93,12 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->cpu = curr; /* - * ACQUIRE semantics, pairs with corresponding RELEASE - * in unlock() uncontended, or fastpath. + * We need both ACQUIRE (pairs with corresponding RELEASE in + * unlock() uncontended, or fastpath) and RELEASE (to publish + * the node fields we just initialised) semantics when updating + * the lock tail. */ - old = atomic_xchg_acquire(&lock->tail, curr); + old = atomic_xchg(&lock->tail, curr); if (old == OSQ_UNLOCKED_VAL) return true; diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c0a205101c231..caf4041f5b0ae 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -1,7 +1,7 @@ /* * sched_clock for unstable cpu clocks * - * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra * * Updates and enhancements: * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com> diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d568ac9319ea..732e993b564b8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1947,13 +1947,38 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) #ifdef CONFIG_SMP /* + * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be + * possible to, falsely, observe p->on_cpu == 0. + * + * One must be running (->on_cpu == 1) in order to remove oneself + * from the runqueue. + * + * [S] ->on_cpu = 1; [L] ->on_rq + * UNLOCK rq->lock + * RMB + * LOCK rq->lock + * [S] ->on_rq = 0; [L] ->on_cpu + * + * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock + * from the consecutive calls to schedule(); the first switching to our + * task, the second putting it to sleep. + */ + smp_rmb(); + + /* * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. */ while (p->on_cpu) cpu_relax(); /* - * Pairs with the smp_wmb() in finish_lock_switch(). + * Combined with the control dependency above, we have an effective + * smp_load_acquire() without the need for full barriers. + * + * Pairs with the smp_store_release() in finish_lock_switch(). + * + * This ensures that tasks getting woken will be fully ordered against + * their previous state and preserve Program Order. */ smp_rmb(); @@ -2039,7 +2064,6 @@ out: */ int wake_up_process(struct task_struct *p) { - WARN_ON(task_is_stopped_or_traced(p)); return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); @@ -5847,13 +5871,13 @@ static int init_rootdomain(struct root_domain *rd) { memset(rd, 0, sizeof(*rd)); - if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) goto out; - if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) goto free_online; - if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) goto free_dlo_mask; init_dl_bw(&rd->dl_bw); @@ -8217,12 +8241,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private) sched_move_task(task); } -static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -8235,12 +8259,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, return 0; } -static void cpu_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpu_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) sched_move_task(task); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 26a54461bf59c..05de80b48586e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -788,6 +788,9 @@ cputime_t task_gtime(struct task_struct *t) unsigned int seq; cputime_t gtime; + if (!context_tracking_is_enabled()) + return t->gtime; + do { seq = read_seqbegin(&t->vtime_seqlock); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f04fda8f669c8..90e26b11deaa1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -17,7 +17,7 @@ * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> * * Adaptive scheduling granularity, math enhancements by Peter Zijlstra - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ #include <linux/latencytop.h> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e3cc163120466..8ec86abe0ea18 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -64,7 +64,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_unlock(&rt_b->rt_runtime_lock); } -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI) static void push_irq_work_func(struct irq_work *work); #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index efd3bfc7e3472..b242775bf670e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1073,6 +1073,9 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * We must ensure this doesn't happen until the switch is completely * finished. * + * In particular, the load of prev->state in finish_task_switch() must + * happen before this. + * * Pairs with the control dependency and rmb in try_to_wake_up(). */ smp_store_release(&prev->on_cpu, 0); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 052e02672d124..f15d6b6a538a9 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -392,7 +392,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, do { prepare_to_wait(wq, &q->wait, mode); if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(&q->key); + ret = (*action)(&q->key, mode); } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); finish_wait(wq, &q->wait); return ret; @@ -431,7 +431,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait_exclusive(wq, &q->wait, mode); if (!test_bit(q->key.bit_nr, q->key.flags)) continue; - ret = action(&q->key); + ret = action(&q->key, mode); if (!ret) continue; abort_exclusive_wait(wq, &q->wait, mode, &q->key); @@ -581,44 +581,44 @@ void wake_up_atomic_t(atomic_t *p) } EXPORT_SYMBOL(wake_up_atomic_t); -__sched int bit_wait(struct wait_bit_key *word) +__sched int bit_wait(struct wait_bit_key *word, int mode) { - if (signal_pending_state(current->state, current)) - return 1; schedule(); + if (signal_pending_state(mode, current)) + return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait); -__sched int bit_wait_io(struct wait_bit_key *word) +__sched int bit_wait_io(struct wait_bit_key *word, int mode) { - if (signal_pending_state(current->state, current)) - return 1; io_schedule(); + if (signal_pending_state(mode, current)) + return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait_io); -__sched int bit_wait_timeout(struct wait_bit_key *word) +__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) { unsigned long now = READ_ONCE(jiffies); - if (signal_pending_state(current->state, current)) - return 1; if (time_after_eq(now, word->timeout)) return -EAGAIN; schedule_timeout(word->timeout - now); + if (signal_pending_state(mode, current)) + return -EINTR; return 0; } EXPORT_SYMBOL_GPL(bit_wait_timeout); -__sched int bit_wait_io_timeout(struct wait_bit_key *word) +__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) { unsigned long now = READ_ONCE(jiffies); - if (signal_pending_state(current->state, current)) - return 1; if (time_after_eq(now, word->timeout)) return -EAGAIN; io_schedule_timeout(word->timeout - now); + if (signal_pending_state(mode, current)) + return -EINTR; return 0; } EXPORT_SYMBOL_GPL(bit_wait_io_timeout); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 867bc20e1ef14..a3bbaee77c586 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -531,7 +531,7 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#ifdef CONFIG_STOP_MACHINE +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { @@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return ret ?: done.ret; } -#endif /* CONFIG_STOP_MACHINE */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index abfc903e741e8..cc9f7a9319bea 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -1,7 +1,7 @@ /* * trace event based perf event profiling/tracing * - * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com> */ diff --git a/lib/btree.c b/lib/btree.c index 4264871ea1a00..f93a945274af1 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -5,7 +5,7 @@ * * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org> * Bits and pieces stolen from Peter Zijlstra's code, which is - * Copyright 2007, Red Hat Inc. Peter Zijlstra <pzijlstr@redhat.com> + * Copyright 2007, Red Hat Inc. Peter Zijlstra * GPLv2 * * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 8855f019ebe8a..d34bd24c2c847 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1464,7 +1464,7 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, entry->type = dma_debug_coherent; entry->dev = dev; entry->pfn = page_to_pfn(virt_to_page(virt)); - entry->offset = (size_t) virt & PAGE_MASK; + entry->offset = (size_t) virt & ~PAGE_MASK; entry->size = size; entry->dev_addr = dma_addr; entry->direction = DMA_BIDIRECTIONAL; @@ -1480,7 +1480,7 @@ void debug_dma_free_coherent(struct device *dev, size_t size, .type = dma_debug_coherent, .dev = dev, .pfn = page_to_pfn(virt_to_page(virt)), - .offset = (size_t) virt & PAGE_MASK, + .offset = (size_t) virt & ~PAGE_MASK, .dev_addr = addr, .size = size, .direction = DMA_BIDIRECTIONAL, diff --git a/lib/proportions.c b/lib/proportions.c index 6f724298f67a1..efa54f259ea9d 100644 --- a/lib/proportions.c +++ b/lib/proportions.c @@ -1,7 +1,7 @@ /* * Floating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Description: * diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 0f3be3fad2b2b..cc808707d1cf5 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -386,33 +386,31 @@ static bool rhashtable_check_elasticity(struct rhashtable *ht, return false; } -int rhashtable_insert_rehash(struct rhashtable *ht) +int rhashtable_insert_rehash(struct rhashtable *ht, + struct bucket_table *tbl) { struct bucket_table *old_tbl; struct bucket_table *new_tbl; - struct bucket_table *tbl; unsigned int size; int err; old_tbl = rht_dereference_rcu(ht->tbl, ht); - tbl = rhashtable_last_table(ht, old_tbl); size = tbl->size; + err = -EBUSY; + if (rht_grow_above_75(ht, tbl)) size *= 2; /* Do not schedule more than one rehash */ else if (old_tbl != tbl) - return -EBUSY; + goto fail; + + err = -ENOMEM; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); - if (new_tbl == NULL) { - /* Schedule async resize/rehash to try allocation - * non-atomic context. - */ - schedule_work(&ht->run_work); - return -ENOMEM; - } + if (new_tbl == NULL) + goto fail; err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { @@ -423,12 +421,24 @@ int rhashtable_insert_rehash(struct rhashtable *ht) schedule_work(&ht->run_work); return err; + +fail: + /* Do not fail the insert if someone else did a rehash. */ + if (likely(rcu_dereference_raw(tbl->future_tbl))) + return 0; + + /* Schedule async rehash to retry allocation in process context. */ + if (err == -ENOMEM) + schedule_work(&ht->run_work); + + return err; } EXPORT_SYMBOL_GPL(rhashtable_insert_rehash); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *tbl) +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *tbl) { struct rhash_head *head; unsigned int hash; @@ -464,7 +474,12 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key, exit: spin_unlock(rht_bucket_lock(tbl, hash)); - return err; + if (err == 0) + return NULL; + else if (err == -EAGAIN) + return tbl; + else + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(rhashtable_insert_slow); @@ -500,10 +515,11 @@ int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter) if (!iter->walker) return -ENOMEM; - mutex_lock(&ht->mutex); - iter->walker->tbl = rht_dereference(ht->tbl, ht); + spin_lock(&ht->lock); + iter->walker->tbl = + rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock)); list_add(&iter->walker->list, &iter->walker->tbl->walkers); - mutex_unlock(&ht->mutex); + spin_unlock(&ht->lock); return 0; } @@ -517,10 +533,10 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_init); */ void rhashtable_walk_exit(struct rhashtable_iter *iter) { - mutex_lock(&iter->ht->mutex); + spin_lock(&iter->ht->lock); if (iter->walker->tbl) list_del(&iter->walker->list); - mutex_unlock(&iter->ht->mutex); + spin_unlock(&iter->ht->lock); kfree(iter->walker); } EXPORT_SYMBOL_GPL(rhashtable_walk_exit); @@ -544,14 +560,12 @@ int rhashtable_walk_start(struct rhashtable_iter *iter) { struct rhashtable *ht = iter->ht; - mutex_lock(&ht->mutex); + rcu_read_lock(); + spin_lock(&ht->lock); if (iter->walker->tbl) list_del(&iter->walker->list); - - rcu_read_lock(); - - mutex_unlock(&ht->mutex); + spin_unlock(&ht->lock); if (!iter->walker->tbl) { iter->walker->tbl = rht_dereference_rcu(ht->tbl, ht); @@ -720,9 +734,6 @@ int rhashtable_init(struct rhashtable *ht, if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT)) return -EINVAL; - if (params->nelem_hint) - size = rounded_hashtable_size(params); - memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); @@ -742,6 +753,9 @@ int rhashtable_init(struct rhashtable *ht, ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE); + if (params->nelem_hint) + size = rounded_hashtable_size(&ht->p); + /* The maximum (not average) chain length grows with the * size of the hash table, at a rate of (log N)/(log log N). * The value of 16 is selected so that even if the hash diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 10cd1860e5b04..27a7a26b1ece2 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1685,6 +1685,126 @@ static struct bpf_test tests[] = { { }, { { 0, 0x35d97ef2 } } }, + { /* Mainly checking JIT here. */ + "MOV REG64", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffffffffffffLL), + BPF_MOV64_REG(R1, R0), + BPF_MOV64_REG(R2, R1), + BPF_MOV64_REG(R3, R2), + BPF_MOV64_REG(R4, R3), + BPF_MOV64_REG(R5, R4), + BPF_MOV64_REG(R6, R5), + BPF_MOV64_REG(R7, R6), + BPF_MOV64_REG(R8, R7), + BPF_MOV64_REG(R9, R8), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_ALU64_IMM(BPF_MOV, R1, 0), + BPF_ALU64_IMM(BPF_MOV, R2, 0), + BPF_ALU64_IMM(BPF_MOV, R3, 0), + BPF_ALU64_IMM(BPF_MOV, R4, 0), + BPF_ALU64_IMM(BPF_MOV, R5, 0), + BPF_ALU64_IMM(BPF_MOV, R6, 0), + BPF_ALU64_IMM(BPF_MOV, R7, 0), + BPF_ALU64_IMM(BPF_MOV, R8, 0), + BPF_ALU64_IMM(BPF_MOV, R9, 0), + BPF_ALU64_REG(BPF_ADD, R0, R0), + BPF_ALU64_REG(BPF_ADD, R0, R1), + BPF_ALU64_REG(BPF_ADD, R0, R2), + BPF_ALU64_REG(BPF_ADD, R0, R3), + BPF_ALU64_REG(BPF_ADD, R0, R4), + BPF_ALU64_REG(BPF_ADD, R0, R5), + BPF_ALU64_REG(BPF_ADD, R0, R6), + BPF_ALU64_REG(BPF_ADD, R0, R7), + BPF_ALU64_REG(BPF_ADD, R0, R8), + BPF_ALU64_REG(BPF_ADD, R0, R9), + BPF_ALU64_IMM(BPF_ADD, R0, 0xfefe), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfefe } } + }, + { /* Mainly checking JIT here. */ + "MOV REG32", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffffffffffffLL), + BPF_MOV64_REG(R1, R0), + BPF_MOV64_REG(R2, R1), + BPF_MOV64_REG(R3, R2), + BPF_MOV64_REG(R4, R3), + BPF_MOV64_REG(R5, R4), + BPF_MOV64_REG(R6, R5), + BPF_MOV64_REG(R7, R6), + BPF_MOV64_REG(R8, R7), + BPF_MOV64_REG(R9, R8), + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_ALU32_IMM(BPF_MOV, R1, 0), + BPF_ALU32_IMM(BPF_MOV, R2, 0), + BPF_ALU32_IMM(BPF_MOV, R3, 0), + BPF_ALU32_IMM(BPF_MOV, R4, 0), + BPF_ALU32_IMM(BPF_MOV, R5, 0), + BPF_ALU32_IMM(BPF_MOV, R6, 0), + BPF_ALU32_IMM(BPF_MOV, R7, 0), + BPF_ALU32_IMM(BPF_MOV, R8, 0), + BPF_ALU32_IMM(BPF_MOV, R9, 0), + BPF_ALU64_REG(BPF_ADD, R0, R0), + BPF_ALU64_REG(BPF_ADD, R0, R1), + BPF_ALU64_REG(BPF_ADD, R0, R2), + BPF_ALU64_REG(BPF_ADD, R0, R3), + BPF_ALU64_REG(BPF_ADD, R0, R4), + BPF_ALU64_REG(BPF_ADD, R0, R5), + BPF_ALU64_REG(BPF_ADD, R0, R6), + BPF_ALU64_REG(BPF_ADD, R0, R7), + BPF_ALU64_REG(BPF_ADD, R0, R8), + BPF_ALU64_REG(BPF_ADD, R0, R9), + BPF_ALU64_IMM(BPF_ADD, R0, 0xfefe), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfefe } } + }, + { /* Mainly checking JIT here. */ + "LD IMM64", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffffffffffffLL), + BPF_MOV64_REG(R1, R0), + BPF_MOV64_REG(R2, R1), + BPF_MOV64_REG(R3, R2), + BPF_MOV64_REG(R4, R3), + BPF_MOV64_REG(R5, R4), + BPF_MOV64_REG(R6, R5), + BPF_MOV64_REG(R7, R6), + BPF_MOV64_REG(R8, R7), + BPF_MOV64_REG(R9, R8), + BPF_LD_IMM64(R0, 0x0LL), + BPF_LD_IMM64(R1, 0x0LL), + BPF_LD_IMM64(R2, 0x0LL), + BPF_LD_IMM64(R3, 0x0LL), + BPF_LD_IMM64(R4, 0x0LL), + BPF_LD_IMM64(R5, 0x0LL), + BPF_LD_IMM64(R6, 0x0LL), + BPF_LD_IMM64(R7, 0x0LL), + BPF_LD_IMM64(R8, 0x0LL), + BPF_LD_IMM64(R9, 0x0LL), + BPF_ALU64_REG(BPF_ADD, R0, R0), + BPF_ALU64_REG(BPF_ADD, R0, R1), + BPF_ALU64_REG(BPF_ADD, R0, R2), + BPF_ALU64_REG(BPF_ADD, R0, R3), + BPF_ALU64_REG(BPF_ADD, R0, R4), + BPF_ALU64_REG(BPF_ADD, R0, R5), + BPF_ALU64_REG(BPF_ADD, R0, R6), + BPF_ALU64_REG(BPF_ADD, R0, R7), + BPF_ALU64_REG(BPF_ADD, R0, R8), + BPF_ALU64_REG(BPF_ADD, R0, R9), + BPF_ALU64_IMM(BPF_ADD, R0, 0xfefe), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfefe } } + }, { "INT: ALU MIX", .u.insns_int = { diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8ed2ffd963c53..7340353f8aea0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait); * jiffies for either a BDI to exit congestion of the given @sync queue * or a write to complete. * - * In the absence of zone congestion, cond_resched() is called to yield - * the processor if necessary but otherwise does not sleep. + * In the absence of zone congestion, a short sleep or a cond_resched is + * performed to yield the processor and to allow other subsystems to make + * a forward progress. * * The return value is 0 if the sleep is for the full timeout. Otherwise, * it is the number of jiffies that were still remaining when the function @@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) */ if (atomic_read(&nr_wb_congested[sync]) == 0 || !test_bit(ZONE_CONGESTED, &zone->flags)) { - cond_resched(); + + /* + * Memory allocation/reclaim might be called from a WQ + * context and the current implementation of the WQ + * concurrency control doesn't recognize that a particular + * WQ is congested if the worker thread is looping without + * ever sleeping. Therefore we have to do a short sleep + * here rather than calling cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout(1); + else + cond_resched(); /* In case we scheduled, work out time remaining */ ret = timeout - (jiffies - start); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 827bb02a43a4e..ef6963b577fd2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -372,8 +372,10 @@ retry_locked: spin_unlock(&resv->lock); trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) + if (!trg) { + kfree(nrg); return -ENOMEM; + } spin_lock(&resv->lock); list_add(&trg->link, &resv->region_cache); @@ -483,8 +485,16 @@ static long region_del(struct resv_map *resv, long f, long t) retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { - if (rg->to <= f) + /* + * Skip regions before the range to be deleted. file_region + * ranges are normally of the form [from, to). However, there + * may be a "placeholder" entry in the map which is of the form + * (from, to) with from == to. Check for placeholder entries + * at the beginning of the range to be deleted. + */ + if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; + if (rg->from >= t) break; @@ -1886,7 +1896,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, page = __alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; - + if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { + SetPagePrivate(page); + h->resv_huge_pages--; + } spin_lock(&hugetlb_lock); list_move(&page->lru, &h->hugepage_activelist); /* Fall through */ @@ -3693,12 +3706,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); + } else { + ptep = huge_pte_alloc(mm, address, huge_page_size(h)); + if (!ptep) + return VM_FAULT_OOM; } - ptep = huge_pte_alloc(mm, address, huge_page_size(h)); - if (!ptep) - return VM_FAULT_OOM; - mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9acfb165eb52e..fc10620967c79 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -903,14 +903,20 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (prev && reclaim->generation != iter->generation) goto out_unlock; - do { + while (1) { pos = READ_ONCE(iter->position); + if (!pos || css_tryget(&pos->css)) + break; /* - * A racing update may change the position and - * put the last reference, hence css_tryget(), - * or retry to see the updated position. + * css reference reached zero, so iter->position will + * be cleared by ->css_released. However, we should not + * rely on this happening soon, because ->css_released + * is called from a work queue, and by busy-waiting we + * might block it. So we clear iter->position right + * away. */ - } while (pos && !css_tryget(&pos->css)); + (void)cmpxchg(&iter->position, pos, NULL); + } } if (pos) @@ -956,17 +962,13 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, } if (reclaim) { - if (cmpxchg(&iter->position, pos, memcg) == pos) { - if (memcg) - css_get(&memcg->css); - if (pos) - css_put(&pos->css); - } - /* - * pairs with css_tryget when dereferencing iter->position - * above. + * The position could have already been updated by a competing + * thread, so check that the value hasn't changed since we read + * it to avoid reclaiming from the same cgroup twice. */ + (void)cmpxchg(&iter->position, pos, memcg); + if (pos) css_put(&pos->css); @@ -999,6 +1001,28 @@ void mem_cgroup_iter_break(struct mem_cgroup *root, css_put(&prev->css); } +static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup *memcg = dead_memcg; + struct mem_cgroup_reclaim_iter *iter; + struct mem_cgroup_per_zone *mz; + int nid, zid; + int i; + + while ((memcg = parent_mem_cgroup(memcg))) { + for_each_node(nid) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + for (i = 0; i <= DEF_PRIORITY; i++) { + iter = &mz->iter[i]; + cmpxchg(&iter->position, + dead_memcg, NULL); + } + } + } + } +} + /* * Iteration constructs for visiting all cgroups (under a tree). If * loops are exited prematurely (break), mem_cgroup_iter_break() must @@ -2128,7 +2152,7 @@ done_restock: */ do { if (page_counter_read(&memcg->memory) > memcg->high) { - current->memcg_nr_pages_over_high += nr_pages; + current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; } @@ -4324,6 +4348,13 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) wb_memcg_offline(memcg); } +static void mem_cgroup_css_released(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + invalidate_reclaim_iterators(memcg); +} + static void mem_cgroup_css_free(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); @@ -4779,23 +4810,18 @@ static void mem_cgroup_clear_mc(void) spin_unlock(&mc.lock); } -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; struct mem_cgroup *from; struct task_struct *leader, *p; struct mm_struct *mm; unsigned long move_flags; int ret = 0; - /* - * We are now commited to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) + /* charge immigration isn't supported on the default hierarchy */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; /* @@ -4805,13 +4831,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * multiple. */ p = NULL; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { WARN_ON_ONCE(p); p = leader; + memcg = mem_cgroup_from_css(css); } if (!p) return 0; + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); + if (!move_flags) + return 0; + from = mem_cgroup_from_task(p); VM_BUG_ON(from == memcg); @@ -4842,8 +4878,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { if (mc.to) mem_cgroup_clear_mc(); @@ -4985,10 +5020,10 @@ retry: atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { - struct task_struct *p = cgroup_taskset_first(tset); + struct cgroup_subsys_state *css; + struct task_struct *p = cgroup_taskset_first(tset, &css); struct mm_struct *mm = get_task_mm(p); if (mm) { @@ -5000,17 +5035,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { } #endif @@ -5184,6 +5216,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_alloc = mem_cgroup_css_alloc, .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, + .css_released = mem_cgroup_css_released, .css_free = mem_cgroup_css_free, .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, @@ -5511,11 +5544,11 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) * mem_cgroup_replace_page - migrate a charge to another page * @oldpage: currently charged page * @newpage: page to transfer the charge to - * @lrucare: either or both pages might be on the LRU already * * Migrate the charge from @oldpage to @newpage. * * Both pages must be locked, @newpage->mapping must be set up. + * Either or both pages might be on the LRU already. */ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 67d488ab495e5..a042a9d537bb3 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1375,23 +1375,30 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) */ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) { - unsigned long pfn; + unsigned long pfn, sec_end_pfn; struct zone *zone = NULL; struct page *page; int i; - for (pfn = start_pfn; + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn); pfn < end_pfn; - pfn += MAX_ORDER_NR_PAGES) { - i = 0; - /* This is just a CONFIG_HOLES_IN_ZONE check.*/ - while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i)) - i++; - if (i == MAX_ORDER_NR_PAGES) + pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) { + /* Make sure the memory section is present first */ + if (!present_section_nr(pfn_to_section_nr(pfn))) continue; - page = pfn_to_page(pfn + i); - if (zone && page_zone(page) != zone) - return 0; - zone = page_zone(page); + for (; pfn < sec_end_pfn && pfn < end_pfn; + pfn += MAX_ORDER_NR_PAGES) { + i = 0; + /* This is just a CONFIG_HOLES_IN_ZONE check.*/ + while ((i < MAX_ORDER_NR_PAGES) && + !pfn_valid_within(pfn + i)) + i++; + if (i == MAX_ORDER_NR_PAGES) + continue; + page = pfn_to_page(pfn + i); + if (zone && page_zone(page) != zone) + return 0; + zone = page_zone(page); + } } return 1; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d13a33918fa23..c12680993ff33 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -608,6 +608,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, continue; if (unlikely(p->flags & PF_KTHREAD)) continue; + if (is_global_init(p)) + continue; if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) continue; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3e4d65445fa71..d15d88c8efa1e 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2,7 +2,7 @@ * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 17a3c66639a9c..9d666df5ef950 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3647,8 +3647,9 @@ static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { [MIGRATE_UNMOVABLE] = 'U', - [MIGRATE_RECLAIMABLE] = 'E', [MIGRATE_MOVABLE] = 'M', + [MIGRATE_RECLAIMABLE] = 'E', + [MIGRATE_HIGHATOMIC] = 'H', #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif diff --git a/mm/shmem.c b/mm/shmem.c index 9187eee4128b4..2afcdbbdb6850 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -843,14 +843,14 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) list_add_tail(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { - swap_shmem_alloc(swap); - shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); - spin_lock(&info->lock); - info->swapped++; shmem_recalc_inode(inode); + info->swapped++; spin_unlock(&info->lock); + swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); @@ -1078,7 +1078,7 @@ repeat: if (sgp != SGP_WRITE && sgp != SGP_FALLOC && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; - goto failed; + goto unlock; } if (page && sgp == SGP_WRITE) @@ -1246,11 +1246,15 @@ clear: /* Perhaps the file has been truncated since we checked */ if (sgp != SGP_WRITE && sgp != SGP_FALLOC && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + if (alloced) { + ClearPageDirty(page); + delete_from_page_cache(page); + spin_lock(&info->lock); + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + } error = -EINVAL; - if (alloced) - goto trunc; - else - goto failed; + goto unlock; } *pagep = page; return 0; @@ -1258,23 +1262,13 @@ clear: /* * Error recovery. */ -trunc: - info = SHMEM_I(inode); - ClearPageDirty(page); - delete_from_page_cache(page); - spin_lock(&info->lock); - info->alloced--; - inode->i_blocks -= BLOCKS_PER_PAGE; - spin_unlock(&info->lock); decused: - sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_add(&sbinfo->used_blocks, -1); unacct: shmem_unacct_blocks(info->flags, 1); failed: - if (swap.val && error != -EINVAL && - !shmem_confirm_swap(mapping, index, swap)) + if (swap.val && !shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { diff --git a/mm/vmstat.c b/mm/vmstat.c index 879a2be23325c..4ebc17d948cb8 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -219,7 +219,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, * particular counter cannot be updated from interrupt context. */ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) + long delta) { struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; @@ -318,8 +318,8 @@ EXPORT_SYMBOL(__dec_zone_page_state); * 1 Overstepping half of threshold * -1 Overstepping minus half of threshold */ -static inline void mod_state(struct zone *zone, - enum zone_stat_item item, int delta, int overstep_mode) +static inline void mod_state(struct zone *zone, enum zone_stat_item item, + long delta, int overstep_mode) { struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; @@ -357,7 +357,7 @@ static inline void mod_state(struct zone *zone, } void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) + long delta) { mod_state(zone, item, delta, 0); } @@ -384,7 +384,7 @@ EXPORT_SYMBOL(dec_zone_page_state); * Use interrupt disable to serialize counter updates */ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) + long delta) { unsigned long flags; @@ -921,8 +921,8 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, #ifdef CONFIG_PROC_FS static char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", - "Reclaimable", "Movable", + "Reclaimable", "HighAtomic", #ifdef CONFIG_CMA "CMA", @@ -1379,6 +1379,7 @@ static const struct file_operations proc_vmstat_file_operations = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP +static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; static cpumask_var_t cpu_stat_off; @@ -1391,7 +1392,7 @@ static void vmstat_update(struct work_struct *w) * to occur in the future. Keep on running the * update worker thread. */ - schedule_delayed_work_on(smp_processor_id(), + queue_delayed_work_on(smp_processor_id(), vmstat_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } else { @@ -1460,7 +1461,7 @@ static void vmstat_shepherd(struct work_struct *w) if (need_update(cpu) && cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - schedule_delayed_work_on(cpu, + queue_delayed_work_on(cpu, vmstat_wq, &per_cpu(vmstat_work, cpu), 0); put_online_cpus(); @@ -1549,6 +1550,7 @@ static int __init setup_vmstat(void) start_shepherd_timer(); cpu_notifier_register_done(); + vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); diff --git a/mm/zswap.c b/mm/zswap.c index 025f8dc723ded..bf14508afd645 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -541,6 +541,7 @@ static struct zswap_pool *zswap_pool_last_get(void) return last; } +/* type and compressor must be null-terminated */ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) { struct zswap_pool *pool; @@ -548,10 +549,9 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) assert_spin_locked(&zswap_pools_lock); list_for_each_entry_rcu(pool, &zswap_pools, list) { - if (strncmp(pool->tfm_name, compressor, sizeof(pool->tfm_name))) + if (strcmp(pool->tfm_name, compressor)) continue; - if (strncmp(zpool_get_type(pool->zpool), type, - sizeof(zswap_zpool_type))) + if (strcmp(zpool_get_type(pool->zpool), type)) continue; /* if we can't get it, it's about to be destroyed */ if (!zswap_pool_get(pool)) diff --git a/net/6lowpan/6lowpan_i.h b/net/6lowpan/6lowpan_i.h new file mode 100644 index 0000000000000..d16bb4b14aa1d --- /dev/null +++ b/net/6lowpan/6lowpan_i.h @@ -0,0 +1,28 @@ +#ifndef __6LOWPAN_I_H +#define __6LOWPAN_I_H + +#include <linux/netdevice.h> + +#ifdef CONFIG_6LOWPAN_DEBUGFS +int lowpan_dev_debugfs_init(struct net_device *dev); +void lowpan_dev_debugfs_exit(struct net_device *dev); + +int __init lowpan_debugfs_init(void); +void lowpan_debugfs_exit(void); +#else +static inline int lowpan_dev_debugfs_init(struct net_device *dev) +{ + return 0; +} + +static inline void lowpan_dev_debugfs_exit(struct net_device *dev) { } + +static inline int __init lowpan_debugfs_init(void) +{ + return 0; +} + +static inline void lowpan_debugfs_exit(void) { } +#endif /* CONFIG_6LOWPAN_DEBUGFS */ + +#endif /* __6LOWPAN_I_H */ diff --git a/net/6lowpan/Kconfig b/net/6lowpan/Kconfig index 7fa0f382e7d12..9c051512d14f5 100644 --- a/net/6lowpan/Kconfig +++ b/net/6lowpan/Kconfig @@ -5,12 +5,21 @@ menuconfig 6LOWPAN This enables IPv6 over Low power Wireless Personal Area Network - "6LoWPAN" which is supported by IEEE 802.15.4 or Bluetooth stacks. +config 6LOWPAN_DEBUGFS + bool "6LoWPAN debugfs support" + depends on 6LOWPAN + depends on DEBUG_FS + ---help--- + This enables 6LoWPAN debugfs support. For example to manipulate + IPHC context information at runtime. + menuconfig 6LOWPAN_NHC - tristate "Next Header Compression Support" + tristate "Next Header and Generic Header Compression Support" depends on 6LOWPAN default y ---help--- - Support for next header compression. + Support for next header and generic header compression defined in + RFC6282 and RFC7400. if 6LOWPAN_NHC @@ -58,4 +67,38 @@ config 6LOWPAN_NHC_UDP ---help--- 6LoWPAN IPv6 UDP Header compression according to RFC6282. +config 6LOWPAN_GHC_EXT_HDR_HOP + tristate "GHC Hop-by-Hop Options Header Support" + ---help--- + 6LoWPAN IPv6 Hop-by-Hop option generic header compression according + to RFC7400. + +config 6LOWPAN_GHC_UDP + tristate "GHC UDP Support" + ---help--- + 6LoWPAN IPv6 UDP generic header compression according to RFC7400. + +config 6LOWPAN_GHC_ICMPV6 + tristate "GHC ICMPv6 Support" + ---help--- + 6LoWPAN IPv6 ICMPv6 generic header compression according to RFC7400. + +config 6LOWPAN_GHC_EXT_HDR_DEST + tristate "GHC Destination Options Header Support" + ---help--- + 6LoWPAN IPv6 destination option generic header compression according + to RFC7400. + +config 6LOWPAN_GHC_EXT_HDR_FRAG + tristate "GHC Fragmentation Options Header Support" + ---help--- + 6LoWPAN IPv6 fragmentation option generic header compression + according to RFC7400. + +config 6LOWPAN_GHC_EXT_HDR_ROUTE + tristate "GHC Routing Options Header Support" + ---help--- + 6LoWPAN IPv6 routing option generic header compression according + to RFC7400. + endif diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile index c6ffc55ee0d7a..e44f3bf2dd42e 100644 --- a/net/6lowpan/Makefile +++ b/net/6lowpan/Makefile @@ -1,6 +1,7 @@ obj-$(CONFIG_6LOWPAN) += 6lowpan.o 6lowpan-y := core.o iphc.o nhc.o +6lowpan-$(CONFIG_6LOWPAN_DEBUGFS) += debugfs.o #rfc6282 nhcs obj-$(CONFIG_6LOWPAN_NHC_DEST) += nhc_dest.o @@ -10,3 +11,11 @@ obj-$(CONFIG_6LOWPAN_NHC_IPV6) += nhc_ipv6.o obj-$(CONFIG_6LOWPAN_NHC_MOBILITY) += nhc_mobility.o obj-$(CONFIG_6LOWPAN_NHC_ROUTING) += nhc_routing.o obj-$(CONFIG_6LOWPAN_NHC_UDP) += nhc_udp.o + +#rfc7400 ghcs +obj-$(CONFIG_6LOWPAN_GHC_EXT_HDR_HOP) += nhc_ghc_ext_hop.o +obj-$(CONFIG_6LOWPAN_GHC_UDP) += nhc_ghc_udp.o +obj-$(CONFIG_6LOWPAN_GHC_ICMPV6) += nhc_ghc_icmpv6.o +obj-$(CONFIG_6LOWPAN_GHC_EXT_HDR_DEST) += nhc_ghc_ext_dest.o +obj-$(CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG) += nhc_ghc_ext_frag.o +obj-$(CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE) += nhc_ghc_ext_route.o diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index 83b19e072224b..faf65baed617d 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -15,19 +15,67 @@ #include <net/6lowpan.h> -void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype) +#include "6lowpan_i.h" + +int lowpan_register_netdevice(struct net_device *dev, + enum lowpan_lltypes lltype) { + int ret; + dev->addr_len = EUI64_ADDR_LEN; dev->type = ARPHRD_6LOWPAN; dev->mtu = IPV6_MIN_MTU; dev->priv_flags |= IFF_NO_QUEUE; lowpan_priv(dev)->lltype = lltype; + + ret = register_netdevice(dev); + if (ret < 0) + return ret; + + ret = lowpan_dev_debugfs_init(dev); + if (ret < 0) + unregister_netdevice(dev); + + return ret; } -EXPORT_SYMBOL(lowpan_netdev_setup); +EXPORT_SYMBOL(lowpan_register_netdevice); + +int lowpan_register_netdev(struct net_device *dev, + enum lowpan_lltypes lltype) +{ + int ret; + + rtnl_lock(); + ret = lowpan_register_netdevice(dev, lltype); + rtnl_unlock(); + return ret; +} +EXPORT_SYMBOL(lowpan_register_netdev); + +void lowpan_unregister_netdevice(struct net_device *dev) +{ + unregister_netdevice(dev); + lowpan_dev_debugfs_exit(dev); +} +EXPORT_SYMBOL(lowpan_unregister_netdevice); + +void lowpan_unregister_netdev(struct net_device *dev) +{ + rtnl_lock(); + lowpan_unregister_netdevice(dev); + rtnl_unlock(); +} +EXPORT_SYMBOL(lowpan_unregister_netdev); static int __init lowpan_module_init(void) { + int ret; + + ret = lowpan_debugfs_init(); + if (ret < 0) + return ret; + request_module_nowait("ipv6"); request_module_nowait("nhc_dest"); @@ -40,6 +88,13 @@ static int __init lowpan_module_init(void) return 0; } + +static void __exit lowpan_module_exit(void) +{ + lowpan_debugfs_exit(); +} + module_init(lowpan_module_init); +module_exit(lowpan_module_exit); MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c new file mode 100644 index 0000000000000..88eef84df0fc1 --- /dev/null +++ b/net/6lowpan/debugfs.c @@ -0,0 +1,53 @@ +/* This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: + * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> + * Copyright (c) 2015 Nordic Semiconductor. All Rights Reserved. + */ + +#include <net/6lowpan.h> + +#include "6lowpan_i.h" + +static struct dentry *lowpan_debugfs; + +int lowpan_dev_debugfs_init(struct net_device *dev) +{ + struct lowpan_priv *lpriv = lowpan_priv(dev); + + /* creating the root */ + lpriv->iface_debugfs = debugfs_create_dir(dev->name, lowpan_debugfs); + if (!lpriv->iface_debugfs) + goto fail; + + return 0; + +fail: + return -EINVAL; +} + +void lowpan_dev_debugfs_exit(struct net_device *dev) +{ + debugfs_remove_recursive(lowpan_priv(dev)->iface_debugfs); +} + +int __init lowpan_debugfs_init(void) +{ + lowpan_debugfs = debugfs_create_dir("6lowpan", NULL); + if (!lowpan_debugfs) + return -EINVAL; + + return 0; +} + +void lowpan_debugfs_exit(void) +{ + debugfs_remove_recursive(lowpan_debugfs); +} diff --git a/net/6lowpan/nhc_ghc_ext_dest.c b/net/6lowpan/nhc_ghc_ext_dest.c new file mode 100644 index 0000000000000..9887b3a153480 --- /dev/null +++ b/net/6lowpan/nhc_ghc_ext_dest.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN Extension Header compression according to RFC7400 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "nhc.h" + +#define LOWPAN_GHC_EXT_DEST_IDLEN 1 +#define LOWPAN_GHC_EXT_DEST_ID_0 0xb6 +#define LOWPAN_GHC_EXT_DEST_MASK_0 0xfe + +static void dest_ghid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_GHC_EXT_DEST_ID_0; + nhc->idmask[0] = LOWPAN_GHC_EXT_DEST_MASK_0; +} + +LOWPAN_NHC(ghc_ext_dest, "RFC7400 Destination Extension Header", NEXTHDR_DEST, + 0, dest_ghid_setup, LOWPAN_GHC_EXT_DEST_IDLEN, NULL, NULL); + +module_lowpan_nhc(ghc_ext_dest); +MODULE_DESCRIPTION("6LoWPAN generic header destination extension compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_ghc_ext_frag.c b/net/6lowpan/nhc_ghc_ext_frag.c new file mode 100644 index 0000000000000..1308b79e939db --- /dev/null +++ b/net/6lowpan/nhc_ghc_ext_frag.c @@ -0,0 +1,28 @@ +/* + * 6LoWPAN Extension Header compression according to RFC7400 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "nhc.h" + +#define LOWPAN_GHC_EXT_FRAG_IDLEN 1 +#define LOWPAN_GHC_EXT_FRAG_ID_0 0xb4 +#define LOWPAN_GHC_EXT_FRAG_MASK_0 0xfe + +static void frag_ghid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_GHC_EXT_FRAG_ID_0; + nhc->idmask[0] = LOWPAN_GHC_EXT_FRAG_MASK_0; +} + +LOWPAN_NHC(ghc_ext_frag, "RFC7400 Fragmentation Extension Header", + NEXTHDR_FRAGMENT, 0, frag_ghid_setup, + LOWPAN_GHC_EXT_FRAG_IDLEN, NULL, NULL); + +module_lowpan_nhc(ghc_ext_frag); +MODULE_DESCRIPTION("6LoWPAN generic header fragmentation extension compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_ghc_ext_hop.c b/net/6lowpan/nhc_ghc_ext_hop.c new file mode 100644 index 0000000000000..baec86fd1974c --- /dev/null +++ b/net/6lowpan/nhc_ghc_ext_hop.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN Extension Header compression according to RFC7400 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "nhc.h" + +#define LOWPAN_GHC_EXT_HOP_IDLEN 1 +#define LOWPAN_GHC_EXT_HOP_ID_0 0xb0 +#define LOWPAN_GHC_EXT_HOP_MASK_0 0xfe + +static void hop_ghid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_GHC_EXT_HOP_ID_0; + nhc->idmask[0] = LOWPAN_GHC_EXT_HOP_MASK_0; +} + +LOWPAN_NHC(ghc_ext_hop, "RFC7400 Hop-by-Hop Extension Header", NEXTHDR_HOP, 0, + hop_ghid_setup, LOWPAN_GHC_EXT_HOP_IDLEN, NULL, NULL); + +module_lowpan_nhc(ghc_ext_hop); +MODULE_DESCRIPTION("6LoWPAN generic header hop-by-hop extension compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_ghc_ext_route.c b/net/6lowpan/nhc_ghc_ext_route.c new file mode 100644 index 0000000000000..d7e5bd791c62b --- /dev/null +++ b/net/6lowpan/nhc_ghc_ext_route.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN Extension Header compression according to RFC7400 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "nhc.h" + +#define LOWPAN_GHC_EXT_ROUTE_IDLEN 1 +#define LOWPAN_GHC_EXT_ROUTE_ID_0 0xb2 +#define LOWPAN_GHC_EXT_ROUTE_MASK_0 0xfe + +static void route_ghid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_GHC_EXT_ROUTE_ID_0; + nhc->idmask[0] = LOWPAN_GHC_EXT_ROUTE_MASK_0; +} + +LOWPAN_NHC(ghc_ext_route, "RFC7400 Routing Extension Header", NEXTHDR_ROUTING, + 0, route_ghid_setup, LOWPAN_GHC_EXT_ROUTE_IDLEN, NULL, NULL); + +module_lowpan_nhc(ghc_ext_route); +MODULE_DESCRIPTION("6LoWPAN generic header routing extension compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_ghc_icmpv6.c b/net/6lowpan/nhc_ghc_icmpv6.c new file mode 100644 index 0000000000000..32e7c2c66bbc6 --- /dev/null +++ b/net/6lowpan/nhc_ghc_icmpv6.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN ICMPv6 compression according to RFC7400 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "nhc.h" + +#define LOWPAN_GHC_ICMPV6_IDLEN 1 +#define LOWPAN_GHC_ICMPV6_ID_0 0xdf +#define LOWPAN_GHC_ICMPV6_MASK_0 0xff + +static void icmpv6_ghid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_GHC_ICMPV6_ID_0; + nhc->idmask[0] = LOWPAN_GHC_ICMPV6_MASK_0; +} + +LOWPAN_NHC(ghc_icmpv6, "RFC7400 ICMPv6", NEXTHDR_ICMP, 0, + icmpv6_ghid_setup, LOWPAN_GHC_ICMPV6_IDLEN, NULL, NULL); + +module_lowpan_nhc(ghc_icmpv6); +MODULE_DESCRIPTION("6LoWPAN generic header ICMPv6 compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_ghc_udp.c b/net/6lowpan/nhc_ghc_udp.c new file mode 100644 index 0000000000000..17beefa52ca8a --- /dev/null +++ b/net/6lowpan/nhc_ghc_udp.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN UDP compression according to RFC7400 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "nhc.h" + +#define LOWPAN_GHC_UDP_IDLEN 1 +#define LOWPAN_GHC_UDP_ID_0 0xd0 +#define LOWPAN_GHC_UDP_MASK_0 0xf8 + +static void udp_ghid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_GHC_UDP_ID_0; + nhc->idmask[0] = LOWPAN_GHC_UDP_MASK_0; +} + +LOWPAN_NHC(ghc_udp, "RFC7400 UDP", NEXTHDR_UDP, 0, + udp_ghid_setup, LOWPAN_GHC_UDP_IDLEN, NULL, NULL); + +module_lowpan_nhc(ghc_udp); +MODULE_DESCRIPTION("6LoWPAN generic header UDP compression"); +MODULE_LICENSE("GPL"); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index fded86508117d..ad5e2fd1012c4 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -30,6 +30,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <net/arp.h> +#include <net/switchdev.h> #include "vlan.h" #include "vlanproc.h" @@ -542,9 +543,9 @@ static int vlan_dev_init(struct net_device *dev) (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); - dev->hw_features = NETIF_F_ALL_CSUM | NETIF_F_SG | + dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | - NETIF_F_HIGHDMA | NETIF_F_SCTP_CSUM | + NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | NETIF_F_ALL_FCOE; dev->features |= real_dev->vlan_features | NETIF_F_LLTX | @@ -774,6 +775,12 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, + .ndo_fdb_add = switchdev_port_fdb_add, + .ndo_fdb_del = switchdev_port_fdb_del, + .ndo_fdb_dump = switchdev_port_fdb_dump, + .ndo_bridge_setlink = switchdev_port_bridge_setlink, + .ndo_bridge_getlink = switchdev_port_bridge_getlink, + .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, .ndo_get_iflink = vlan_dev_get_iflink, }; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index ae3a47f9d1d52..fbd0acf80b132 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -805,6 +805,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 912d9c36fb1c9..5677169c1b98a 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1379,6 +1379,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_hardif_neigh_node *hardif_neigh = NULL; struct batadv_neigh_node *router = NULL; struct batadv_neigh_node *router_router = NULL; struct batadv_orig_node *orig_neigh_node; @@ -1423,6 +1424,13 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, goto out; } + if (is_single_hop_neigh) { + hardif_neigh = batadv_hardif_neigh_get(if_incoming, + ethhdr->h_source); + if (hardif_neigh) + hardif_neigh->last_seen = jiffies; + } + router = batadv_orig_router_get(orig_node, if_outgoing); if (router) { router_router = batadv_orig_router_get(router->orig_node, @@ -1557,6 +1565,8 @@ out: batadv_neigh_node_free_ref(router_router); if (orig_neigh_router) batadv_neigh_node_free_ref(orig_neigh_router); + if (hardif_neigh) + batadv_hardif_neigh_free_ref(hardif_neigh); kfree_skb(skb_priv); } @@ -1862,6 +1872,58 @@ next: } /** + * batadv_iv_hardif_neigh_print - print a single hop neighbour node + * @seq: neighbour table seq_file struct + * @hardif_neigh: hardif neighbour information + */ +static void +batadv_iv_hardif_neigh_print(struct seq_file *seq, + struct batadv_hardif_neigh_node *hardif_neigh) +{ + int last_secs, last_msecs; + + last_secs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen) / 1000; + last_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen) % 1000; + + seq_printf(seq, " %10s %pM %4i.%03is\n", + hardif_neigh->if_incoming->net_dev->name, + hardif_neigh->addr, last_secs, last_msecs); +} + +/** + * batadv_iv_ogm_neigh_print - print the single hop neighbour list + * @bat_priv: the bat priv with all the soft interface information + * @seq: neighbour table seq_file struct + */ +static void batadv_iv_neigh_print(struct batadv_priv *bat_priv, + struct seq_file *seq) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_hardif_neigh_node *hardif_neigh; + struct batadv_hard_iface *hard_iface; + int batman_count = 0; + + seq_printf(seq, " %10s %-13s %s\n", + "IF", "Neighbor", "last-seen"); + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != net_dev) + continue; + + hlist_for_each_entry_rcu(hardif_neigh, + &hard_iface->neigh_list, list) { + batadv_iv_hardif_neigh_print(seq, hardif_neigh); + batman_count++; + } + } + rcu_read_unlock(); + + if (batman_count == 0) + seq_puts(seq, "No batman nodes in range ...\n"); +} + +/** * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors * @neigh1: the first neighbor object of the comparison * @if_outgoing1: outgoing interface for the first neighbor @@ -1902,8 +1964,8 @@ out: } /** - * batadv_iv_ogm_neigh_is_eob - check if neigh1 is equally good or better than - * neigh2 from the metric prospective + * batadv_iv_ogm_neigh_is_sob - check if neigh1 is similarly good or better + * than neigh2 from the metric prospective * @neigh1: the first neighbor object of the comparison * @if_outgoing1: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison @@ -1913,7 +1975,7 @@ out: * the metric via neigh2, false otherwise. */ static bool -batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, +batadv_iv_ogm_neigh_is_sob(struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing1, struct batadv_neigh_node *neigh2, struct batadv_hard_iface *if_outgoing2) @@ -1953,7 +2015,8 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .bat_ogm_schedule = batadv_iv_ogm_schedule, .bat_ogm_emit = batadv_iv_ogm_emit, .bat_neigh_cmp = batadv_iv_ogm_neigh_cmp, - .bat_neigh_is_equiv_or_better = batadv_iv_ogm_neigh_is_eob, + .bat_neigh_is_similar_or_better = batadv_iv_ogm_neigh_is_sob, + .bat_neigh_print = batadv_iv_neigh_print, .bat_orig_print = batadv_iv_ogm_orig_print, .bat_orig_free = batadv_iv_ogm_orig_free, .bat_orig_add_if = batadv_iv_ogm_orig_add_if, diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 191a70290dca2..99dcae316ec89 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -260,7 +260,9 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) } /* all claims gone, initialize CRC */ + spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc = BATADV_BLA_CRC_INIT; + spin_unlock_bh(&backbone_gw->crc_lock); } /** @@ -408,6 +410,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig, entry->lasttime = jiffies; entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; + spin_lock_init(&entry->crc_lock); atomic_set(&entry->request_sent, 0); atomic_set(&entry->wait_periods, 0); ether_addr_copy(entry->orig, orig); @@ -557,7 +560,9 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, __be16 crc; memcpy(mac, batadv_announce_mac, 4); + spin_lock_bh(&backbone_gw->crc_lock); crc = htons(backbone_gw->crc); + spin_unlock_bh(&backbone_gw->crc_lock); memcpy(&mac[4], &crc, 2); batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, @@ -618,14 +623,18 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, "bla_add_claim(): changing ownership for %pM, vid %d\n", mac, BATADV_PRINT_VID(vid)); + spin_lock_bh(&claim->backbone_gw->crc_lock); claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&claim->backbone_gw->crc_lock); batadv_backbone_gw_free_ref(claim->backbone_gw); } /* set (new) backbone gw */ atomic_inc(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; + spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&backbone_gw->crc_lock); backbone_gw->lasttime = jiffies; claim_free_ref: @@ -653,7 +662,9 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, batadv_choose_claim, claim); batadv_claim_free_ref(claim); /* reference from the hash is gone */ + spin_lock_bh(&claim->backbone_gw->crc_lock); claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&claim->backbone_gw->crc_lock); /* don't need the reference from hash_find() anymore */ batadv_claim_free_ref(claim); @@ -664,7 +675,7 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, u8 *backbone_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; - u16 crc; + u16 backbone_crc, crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return 0; @@ -683,12 +694,16 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", BATADV_PRINT_VID(vid), backbone_gw->orig, crc); - if (backbone_gw->crc != crc) { + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); + + if (backbone_crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", backbone_gw->orig, BATADV_PRINT_VID(backbone_gw->vid), - backbone_gw->crc, crc); + backbone_crc, crc); batadv_bla_send_request(backbone_gw); } else { @@ -1647,6 +1662,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_head *head; + u16 backbone_crc; u32 i; bool is_own; u8 *primary_addr; @@ -1669,11 +1685,15 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(claim, head, hash_entry) { is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); + + spin_lock_bh(&claim->backbone_gw->crc_lock); + backbone_crc = claim->backbone_gw->crc; + spin_unlock_bh(&claim->backbone_gw->crc_lock); seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n", claim->addr, BATADV_PRINT_VID(claim->vid), claim->backbone_gw->orig, (is_own ? 'x' : ' '), - claim->backbone_gw->crc); + backbone_crc); } rcu_read_unlock(); } @@ -1692,6 +1712,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hard_iface *primary_if; struct hlist_head *head; int secs, msecs; + u16 backbone_crc; u32 i; bool is_own; u8 *primary_addr; @@ -1722,10 +1743,14 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) if (is_own) continue; + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); + seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n", backbone_gw->orig, BATADV_PRINT_VID(backbone_gw->vid), secs, - msecs, backbone_gw->crc); + msecs, backbone_crc); } rcu_read_unlock(); } diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index c4c1e8030ba02..037ad0a5f485e 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -262,6 +262,13 @@ static int batadv_algorithms_open(struct inode *inode, struct file *file) return single_open(file, batadv_algo_seq_print_text, NULL); } +static int neighbors_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + + return single_open(file, batadv_hardif_neigh_seq_print_text, net_dev); +} + static int batadv_originators_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; @@ -375,6 +382,7 @@ static struct batadv_debuginfo *batadv_general_debuginfos[] = { }; /* The following attributes are per soft interface */ +static BATADV_DEBUGINFO(neighbors, S_IRUGO, neighbors_open); static BATADV_DEBUGINFO(originators, S_IRUGO, batadv_originators_open); static BATADV_DEBUGINFO(gateways, S_IRUGO, batadv_gateways_open); static BATADV_DEBUGINFO(transtable_global, S_IRUGO, @@ -394,6 +402,7 @@ static BATADV_DEBUGINFO(nc_nodes, S_IRUGO, batadv_nc_nodes_open); #endif static struct batadv_debuginfo *batadv_mesh_debuginfos[] = { + &batadv_debuginfo_neighbors, &batadv_debuginfo_originators, &batadv_debuginfo_gateways, &batadv_debuginfo_transtable_global, diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 83bc1aaf5800c..a49c705fb86b8 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -566,6 +566,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) int select; batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; struct batadv_dat_candidate *res; + struct batadv_dat_entry dat; if (!bat_priv->orig_hash) return NULL; @@ -575,7 +576,9 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) if (!res) return NULL; - ip_key = (batadv_dat_addr_t)batadv_hash_dat(&ip_dst, + dat.ip = ip_dst; + dat.vid = 0; + ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat, BATADV_DAT_ADDR_MAX); batadv_dbg(BATADV_DBG_DAT, bat_priv, diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 700c96c82a151..20d9282f895b2 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -71,14 +71,14 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig_node, for (i = 0; i < BATADV_FRAG_BUFFER_COUNT; i++) { chain = &orig_node->fragments[i]; - spin_lock_bh(&orig_node->fragments[i].lock); + spin_lock_bh(&chain->lock); if (!check_cb || check_cb(chain)) { - batadv_frag_clear_chain(&orig_node->fragments[i].head); - orig_node->fragments[i].size = 0; + batadv_frag_clear_chain(&chain->head); + chain->size = 0; } - spin_unlock_bh(&orig_node->fragments[i].lock); + spin_unlock_bh(&chain->lock); } } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index a58184fdf5fdc..01acccc4d2185 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -32,6 +32,7 @@ #include <linux/rculist.h> #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/workqueue.h> #include <net/net_namespace.h> @@ -639,9 +640,12 @@ batadv_hardif_add_interface(struct net_device *net_dev) goto free_sysfs; INIT_LIST_HEAD(&hard_iface->list); + INIT_HLIST_HEAD(&hard_iface->neigh_list); INIT_WORK(&hard_iface->cleanup_work, batadv_hardif_remove_interface_finish); + spin_lock_init(&hard_iface->neigh_list_lock); + hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; if (batadv_is_wifi_netdev(net_dev)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d7f17c1aa4a4b..5dbcb2e2b497c 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -552,7 +552,7 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) !bat_algo_ops->bat_ogm_schedule || !bat_algo_ops->bat_ogm_emit || !bat_algo_ops->bat_neigh_cmp || - !bat_algo_ops->bat_neigh_is_equiv_or_better) { + !bat_algo_ops->bat_neigh_is_similar_or_better) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); return -EINVAL; @@ -908,7 +908,7 @@ end: * appropriate handlers * @bat_priv: the bat priv with all the soft interface information * @tvlv_handler: tvlv callback function handling the tvlv content - * @ogm_source: flag indicating wether the tvlv is an ogm or a unicast packet + * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet * @orig_node: orig node emitting the ogm packet * @src: source mac address of the unicast packet * @dst: destination mac address of the unicast packet @@ -961,7 +961,7 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, * batadv_tvlv_containers_process - parse the given tvlv buffer to call the * appropriate handlers * @bat_priv: the bat priv with all the soft interface information - * @ogm_source: flag indicating wether the tvlv is an ogm or a unicast packet + * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet * @orig_node: orig node emitting the ogm packet * @src: source mac address of the unicast packet * @dst: destination mac address of the unicast packet diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 7486df9ed48db..3c782a33bdac5 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -202,6 +202,47 @@ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) } /** + * batadv_hardif_neigh_free_rcu - free the hardif neigh_node + * @rcu: rcu pointer of the neigh_node + */ +static void batadv_hardif_neigh_free_rcu(struct rcu_head *rcu) +{ + struct batadv_hardif_neigh_node *hardif_neigh; + + hardif_neigh = container_of(rcu, struct batadv_hardif_neigh_node, rcu); + + spin_lock_bh(&hardif_neigh->if_incoming->neigh_list_lock); + hlist_del_init_rcu(&hardif_neigh->list); + spin_unlock_bh(&hardif_neigh->if_incoming->neigh_list_lock); + + batadv_hardif_free_ref_now(hardif_neigh->if_incoming); + kfree(hardif_neigh); +} + +/** + * batadv_hardif_neigh_free_now - decrement the hardif neighbors refcounter + * and possibly free it (without rcu callback) + * @hardif_neigh: hardif neigh neighbor to free + */ +static void +batadv_hardif_neigh_free_now(struct batadv_hardif_neigh_node *hardif_neigh) +{ + if (atomic_dec_and_test(&hardif_neigh->refcount)) + batadv_hardif_neigh_free_rcu(&hardif_neigh->rcu); +} + +/** + * batadv_hardif_neigh_free_ref - decrement the hardif neighbors refcounter + * and possibly free it + * @hardif_neigh: hardif neigh neighbor to free + */ +void batadv_hardif_neigh_free_ref(struct batadv_hardif_neigh_node *hardif_neigh) +{ + if (atomic_dec_and_test(&hardif_neigh->refcount)) + call_rcu(&hardif_neigh->rcu, batadv_hardif_neigh_free_rcu); +} + +/** * batadv_neigh_node_free_rcu - free the neigh_node * @rcu: rcu pointer of the neigh_node */ @@ -209,6 +250,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; + struct batadv_hardif_neigh_node *hardif_neigh; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; @@ -220,6 +262,14 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); } + hardif_neigh = batadv_hardif_neigh_get(neigh_node->if_incoming, + neigh_node->addr); + if (hardif_neigh) { + /* batadv_hardif_neigh_get() increases refcount too */ + batadv_hardif_neigh_free_now(hardif_neigh); + batadv_hardif_neigh_free_now(hardif_neigh); + } + if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); @@ -479,6 +529,106 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node, } /** + * batadv_hardif_neigh_create - create a hardif neighbour node + * @hard_iface: the interface this neighbour is connected to + * @neigh_addr: the interface address of the neighbour to retrieve + * + * Returns the hardif neighbour node if found or created or NULL otherwise. + */ +static struct batadv_hardif_neigh_node * +batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface, + const u8 *neigh_addr) +{ + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_hardif_neigh_node *hardif_neigh = NULL; + + spin_lock_bh(&hard_iface->neigh_list_lock); + + /* check if neighbor hasn't been added in the meantime */ + hardif_neigh = batadv_hardif_neigh_get(hard_iface, neigh_addr); + if (hardif_neigh) + goto out; + + if (!atomic_inc_not_zero(&hard_iface->refcount)) + goto out; + + hardif_neigh = kzalloc(sizeof(*hardif_neigh), GFP_ATOMIC); + if (!hardif_neigh) { + batadv_hardif_free_ref(hard_iface); + goto out; + } + + INIT_HLIST_NODE(&hardif_neigh->list); + ether_addr_copy(hardif_neigh->addr, neigh_addr); + hardif_neigh->if_incoming = hard_iface; + hardif_neigh->last_seen = jiffies; + + atomic_set(&hardif_neigh->refcount, 1); + + if (bat_priv->bat_algo_ops->bat_hardif_neigh_init) + bat_priv->bat_algo_ops->bat_hardif_neigh_init(hardif_neigh); + + hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list); + +out: + spin_unlock_bh(&hard_iface->neigh_list_lock); + return hardif_neigh; +} + +/** + * batadv_hardif_neigh_get_or_create - retrieve or create a hardif neighbour + * node + * @hard_iface: the interface this neighbour is connected to + * @neigh_addr: the interface address of the neighbour to retrieve + * + * Returns the hardif neighbour node if found or created or NULL otherwise. + */ +static struct batadv_hardif_neigh_node * +batadv_hardif_neigh_get_or_create(struct batadv_hard_iface *hard_iface, + const u8 *neigh_addr) +{ + struct batadv_hardif_neigh_node *hardif_neigh = NULL; + + /* first check without locking to avoid the overhead */ + hardif_neigh = batadv_hardif_neigh_get(hard_iface, neigh_addr); + if (hardif_neigh) + return hardif_neigh; + + return batadv_hardif_neigh_create(hard_iface, neigh_addr); +} + +/** + * batadv_hardif_neigh_get - retrieve a hardif neighbour from the list + * @hard_iface: the interface where this neighbour is connected to + * @neigh_addr: the address of the neighbour + * + * Looks for and possibly returns a neighbour belonging to this hard interface. + * Returns NULL if the neighbour is not found. + */ +struct batadv_hardif_neigh_node * +batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, + const u8 *neigh_addr) +{ + struct batadv_hardif_neigh_node *tmp_hardif_neigh, *hardif_neigh = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_hardif_neigh, + &hard_iface->neigh_list, list) { + if (!batadv_compare_eth(tmp_hardif_neigh->addr, neigh_addr)) + continue; + + if (!atomic_inc_not_zero(&tmp_hardif_neigh->refcount)) + continue; + + hardif_neigh = tmp_hardif_neigh; + break; + } + rcu_read_unlock(); + + return hardif_neigh; +} + +/** * batadv_neigh_node_new - create and init a new neigh_node object * @orig_node: originator object representing the neighbour * @hard_iface: the interface where the neighbour is connected to @@ -493,11 +643,17 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, const u8 *neigh_addr) { struct batadv_neigh_node *neigh_node; + struct batadv_hardif_neigh_node *hardif_neigh = NULL; neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); if (neigh_node) goto out; + hardif_neigh = batadv_hardif_neigh_get_or_create(hard_iface, + neigh_addr); + if (!hardif_neigh) + goto out; + neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); if (!neigh_node) goto out; @@ -523,15 +679,54 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); spin_unlock_bh(&orig_node->neigh_list_lock); + /* increment unique neighbor refcount */ + atomic_inc(&hardif_neigh->refcount); + batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", neigh_addr, orig_node->orig, hard_iface->net_dev->name); out: + if (hardif_neigh) + batadv_hardif_neigh_free_ref(hardif_neigh); return neigh_node; } /** + * batadv_hardif_neigh_seq_print_text - print the single hop neighbour list + * @seq: neighbour table seq_file struct + * @offset: not used + * + * Always returns 0. + */ +int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hard_iface *primary_if; + + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) + return 0; + + seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n", + BATADV_SOURCE_VERSION, primary_if->net_dev->name, + primary_if->net_dev->dev_addr, net_dev->name, + bat_priv->bat_algo_ops->name); + + batadv_hardif_free_ref(primary_if); + + if (!bat_priv->bat_algo_ops->bat_neigh_print) { + seq_puts(seq, + "No printing function for this routing protocol\n"); + return 0; + } + + bat_priv->bat_algo_ops->bat_neigh_print(bat_priv, seq); + return 0; +} + +/** * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object * @rcu: rcu pointer of the orig_ifinfo object */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index fa18f9bf266b0..29557753d552d 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -41,6 +41,11 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); +struct batadv_hardif_neigh_node * +batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, + const u8 *neigh_addr); +void +batadv_hardif_neigh_free_ref(struct batadv_hardif_neigh_node *hardif_neigh); struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, @@ -57,6 +62,8 @@ batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo); +int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset); + struct batadv_orig_ifinfo * batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 8d990b070a2e8..e4f2646d92463 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -497,9 +497,9 @@ batadv_find_router(struct batadv_priv *bat_priv, /* alternative candidate should be good enough to be * considered */ - if (!bao->bat_neigh_is_equiv_or_better(cand_router, - cand->if_outgoing, - router, recv_if)) + if (!bao->bat_neigh_is_similar_or_better(cand_router, + cand->if_outgoing, + router, recv_if)) goto next; /* don't use the same router twice */ @@ -836,6 +836,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, u8 *orig_addr; struct batadv_orig_node *orig_node = NULL; int check, hdr_size = sizeof(*unicast_packet); + enum batadv_subtype subtype; bool is4addr; unicast_packet = (struct batadv_unicast_packet *)skb->data; @@ -863,10 +864,20 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { if (is4addr) { - batadv_dat_inc_counter(bat_priv, - unicast_4addr_packet->subtype); - orig_addr = unicast_4addr_packet->src; - orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + subtype = unicast_4addr_packet->subtype; + batadv_dat_inc_counter(bat_priv, subtype); + + /* Only payload data should be considered for speedy + * join. For example, DAT also uses unicast 4addr + * types, but those packets should not be considered + * for speedy join, since the clients do not actually + * reside at the sending originator. + */ + if (subtype == BATADV_P_DATA) { + orig_addr = unicast_4addr_packet->src; + orig_node = batadv_orig_hash_find(bat_priv, + orig_addr); + } } if (batadv_dat_snoop_incoming_arp_request(bat_priv, skb, diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 4228b10c47ead..ec67deff16210 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -68,13 +68,15 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, unsigned short vid, const char *message, bool roaming); -/* returns 1 if they are the same mac addr */ +/* returns 1 if they are the same mac addr and vid */ static int batadv_compare_tt(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_tt_common_entry, hash_entry); + const struct batadv_tt_common_entry *tt1 = data1; + const struct batadv_tt_common_entry *tt2 = data2; - return batadv_compare_eth(data1, data2); + return (tt1->vid == tt2->vid) && batadv_compare_eth(data1, data2); } /** @@ -1427,15 +1429,21 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } /* if the client was temporary added before receiving the first - * OGM announcing it, we have to clear the TEMP flag + * OGM announcing it, we have to clear the TEMP flag. Also, + * remove the previous temporary orig node and re-add it + * if required. If the orig entry changed, the new one which + * is a non-temporary entry is preferred. */ - common->flags &= ~BATADV_TT_CLIENT_TEMP; + if (common->flags & BATADV_TT_CLIENT_TEMP) { + batadv_tt_global_del_orig_list(tt_global_entry); + common->flags &= ~BATADV_TT_CLIENT_TEMP; + } /* the change can carry possible "attribute" flags like the * TT_CLIENT_WIFI, therefore they have to be copied in the * client entry */ - tt_global_entry->common.flags |= flags; + common->flags |= flags; /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a @@ -2411,8 +2419,8 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; + int i, orig_num_vlan; u32 crc; - int i; /* check if each received CRC matches the locally stored one */ for (i = 0; i < num_vlan; i++) { @@ -2438,6 +2446,18 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, return false; } + /* check if any excess VLANs exist locally for the originator + * which are not mentioned in the TVLV from the originator. + */ + rcu_read_lock(); + orig_num_vlan = 0; + hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) + orig_num_vlan++; + rcu_read_unlock(); + + if (orig_num_vlan > num_vlan) + return false; + return true; } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index d260efd70499b..7c386dbb75f01 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -100,6 +100,8 @@ struct batadv_hard_iface_bat_iv { * @bat_iv: BATMAN IV specific per hard interface data * @cleanup_work: work queue callback item for hard interface deinit * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs + * @neigh_list: list of unique single hop neighbors via this interface + * @neigh_list_lock: lock protecting neigh_list */ struct batadv_hard_iface { struct list_head list; @@ -115,6 +117,9 @@ struct batadv_hard_iface { struct batadv_hard_iface_bat_iv bat_iv; struct work_struct cleanup_work; struct dentry *debug_dir; + struct hlist_head neigh_list; + /* neigh_list_lock protects: neigh_list */ + spinlock_t neigh_list_lock; }; /** @@ -341,6 +346,23 @@ struct batadv_gw_node { }; /** + * batadv_hardif_neigh_node - unique neighbor per hard interface + * @list: list node for batadv_hard_iface::neigh_list + * @addr: the MAC address of the neighboring interface + * @if_incoming: pointer to incoming hard interface + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in a RCU-safe manner + */ +struct batadv_hardif_neigh_node { + struct hlist_node list; + u8 addr[ETH_ALEN]; + struct batadv_hard_iface *if_incoming; + unsigned long last_seen; + atomic_t refcount; + struct rcu_head rcu; +}; + +/** * struct batadv_neigh_node - structure for single hops neighbors * @list: list node for batadv_orig_node::neigh_list * @orig_node: pointer to corresponding orig_node @@ -884,6 +906,7 @@ struct batadv_socket_packet { * backbone gateway - no bcast traffic is formwared until the situation was * resolved * @crc: crc16 checksum over all claims + * @crc_lock: lock protecting crc * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner */ @@ -897,6 +920,7 @@ struct batadv_bla_backbone_gw { atomic_t wait_periods; atomic_t request_sent; u16 crc; + spinlock_t crc_lock; /* protects crc */ atomic_t refcount; struct rcu_head rcu; }; @@ -1131,11 +1155,13 @@ struct batadv_forw_packet { * @bat_primary_iface_set: called when primary interface is selected / changed * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue * @bat_ogm_emit: send scheduled OGM + * @bat_hardif_neigh_init: called on creation of single hop entry * @bat_neigh_cmp: compare the metrics of two neighbors for their respective * outgoing interfaces - * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or better - * than neigh2 for their respective outgoing interface from the metric + * @bat_neigh_is_similar_or_better: check if neigh1 is equally similar or + * better than neigh2 for their respective outgoing interface from the metric * prospective + * @bat_neigh_print: print the single hop neighbor list (optional) * @bat_neigh_free: free the resources allocated by the routing algorithm for a * neigh_node object * @bat_orig_print: print the originator table (optional) @@ -1156,15 +1182,17 @@ struct batadv_algo_ops { void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); /* neigh_node handling API */ + void (*bat_hardif_neigh_init)(struct batadv_hardif_neigh_node *neigh); int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing1, struct batadv_neigh_node *neigh2, struct batadv_hard_iface *if_outgoing2); - bool (*bat_neigh_is_equiv_or_better) + bool (*bat_neigh_is_similar_or_better) (struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing1, struct batadv_neigh_node *neigh2, struct batadv_hard_iface *if_outgoing2); + void (*bat_neigh_print)(struct batadv_priv *priv, struct seq_file *seq); void (*bat_neigh_free)(struct batadv_neigh_node *neigh); /* orig_node handling API */ void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq, diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9e9cca3689a08..d040365ba98e7 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -825,9 +825,7 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); spin_unlock(&devices_lock); - lowpan_netdev_setup(netdev, LOWPAN_LLTYPE_BTLE); - - err = register_netdev(netdev); + err = lowpan_register_netdev(netdev, LOWPAN_LLTYPE_BTLE); if (err < 0) { BT_INFO("register_netdev failed %d", err); spin_lock(&devices_lock); @@ -890,7 +888,7 @@ static void delete_netdev(struct work_struct *work) struct lowpan_dev *entry = container_of(work, struct lowpan_dev, delete_netdev); - unregister_netdev(entry->netdev); + lowpan_unregister_netdev(entry->netdev); /* The entry pointer is deleted by the netdev destructor. */ } @@ -1348,7 +1346,7 @@ static void disconnect_devices(void) ifdown(entry->netdev); BT_DBG("Unregistering netdev %s %p", entry->netdev->name, entry->netdev); - unregister_netdev(entry->netdev); + lowpan_unregister_netdev(entry->netdev); kfree(entry); } } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 5785e8e6400e5..955eda93e66f3 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -174,20 +174,20 @@ EXPORT_SYMBOL(bt_accept_unlink); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) { - struct list_head *p, *n; + struct bt_sock *s, *n; struct sock *sk; BT_DBG("parent %p", parent); - list_for_each_safe(p, n, &bt_sk(parent)->accept_q) { - sk = (struct sock *) list_entry(p, struct bt_sock, accept_q); + list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { + sk = (struct sock *)s; lock_sock(sk); /* FIXME: Is this check still needed */ if (sk->sk_state == BT_CLOSED) { - release_sock(sk); bt_accept_unlink(sk); + release_sock(sk); continue; } @@ -388,11 +388,11 @@ EXPORT_SYMBOL(bt_sock_stream_recvmsg); static inline unsigned int bt_accept_poll(struct sock *parent) { - struct list_head *p, *n; + struct bt_sock *s, *n; struct sock *sk; - list_for_each_safe(p, n, &bt_sk(parent)->accept_q) { - sk = (struct sock *) list_entry(p, struct bt_sock, accept_q); + list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { + sk = (struct sock *)s; if (sk->sk_state == BT_CONNECTED || (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && sk->sk_state == BT_CONNECT2)) diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 1641367e54cad..fbf251fef70fe 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -608,8 +608,11 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) s->msg.msg_flags = MSG_NOSIGNAL; #ifdef CONFIG_BT_BNEP_MC_FILTER - /* Set default mc filter */ - set_bit(bnep_mc_hash(dev->broadcast), (ulong *) &s->mc_filter); + /* Set default mc filter to not filter out any mc addresses + * as defined in the BNEP specification (revision 0.95a) + * http://grouper.ieee.org/groups/802/15/Bluetooth/BNEP.pdf + */ + s->mc_filter = ~0LL; #endif #ifdef CONFIG_BT_BNEP_PROTO_FILTER diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 9a50338772f3a..46ac686c8911e 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -100,10 +100,8 @@ static void cmtp_application_del(struct cmtp_session *session, struct cmtp_appli static struct cmtp_application *cmtp_application_get(struct cmtp_session *session, int pattern, __u16 value) { struct cmtp_application *app; - struct list_head *p; - list_for_each(p, &session->applications) { - app = list_entry(p, struct cmtp_application, list); + list_for_each_entry(app, &session->applications, list) { switch (pattern) { case CMTP_MSGNUM: if (app->msgnum == value) @@ -511,14 +509,12 @@ static int cmtp_proc_show(struct seq_file *m, void *v) struct capi_ctr *ctrl = m->private; struct cmtp_session *session = ctrl->driverdata; struct cmtp_application *app; - struct list_head *p; seq_printf(m, "%s\n\n", cmtp_procinfo(ctrl)); seq_printf(m, "addr %s\n", session->name); seq_printf(m, "ctrl %d\n", session->num); - list_for_each(p, &session->applications) { - app = list_entry(p, struct cmtp_application, list); + list_for_each_entry(app, &session->applications, list) { seq_printf(m, "appl %d -> %d\n", app->appl, app->mapping); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 2d334e07fd773..32575b49f4a0c 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -668,8 +668,16 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) conn->state = BT_CLOSED; - mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, - status); + /* If the status indicates successful cancellation of + * the attempt (i.e. Unkown Connection Id) there's no point of + * notifying failure since we'll go back to keep trying to + * connect. The only exception is explicit connect requests + * where a timeout + cancel does indicate an actual failure. + */ + if (status != HCI_ERROR_UNKNOWN_CONN_ID || + (params && params->explicit_connect)) + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); hci_connect_cfm(conn, status); @@ -683,7 +691,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) /* Re-enable advertising in case this was a failed connection * attempt as a peripheral. */ - mgmt_reenable_advertising(hdev); + hci_req_reenable_advertising(hdev); } static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode) @@ -726,8 +734,12 @@ static void hci_req_add_le_create_conn(struct hci_request *req, if (hci_update_random_address(req, false, &own_addr_type)) return; + /* Set window to be the same value as the interval to enable + * continuous scanning. + */ cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); - cp.scan_window = cpu_to_le16(hdev->le_scan_window); + cp.scan_window = cp.scan_interval; + bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; cp.own_address_type = own_addr_type; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 89af7e4fac025..47bcef7547967 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1399,10 +1399,10 @@ static int hci_dev_do_open(struct hci_dev *hdev) !hci_dev_test_flag(hdev, HCI_CONFIG) && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + hci_dev_test_flag(hdev, HCI_MGMT) && hdev->dev_type == HCI_BREDR) { - hci_dev_lock(hdev); - mgmt_powered(hdev, 1); - hci_dev_unlock(hdev); + ret = __hci_req_hci_power_on(hdev); + mgmt_power_on(hdev, ret); } } else { /* Init failed, cleanup */ @@ -1537,7 +1537,6 @@ int hci_dev_do_close(struct hci_dev *hdev) flush_work(&hdev->rx_work); if (hdev->discov_timeout > 0) { - cancel_delayed_work(&hdev->discov_off); hdev->discov_timeout = 0; hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); @@ -1549,11 +1548,6 @@ int hci_dev_do_close(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_MGMT)) cancel_delayed_work_sync(&hdev->rpa_expired); - if (hdev->adv_instance_timeout) { - cancel_delayed_work_sync(&hdev->adv_instance_expire); - hdev->adv_instance_timeout = 0; - } - /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ @@ -1565,8 +1559,9 @@ int hci_dev_do_close(struct hci_dev *hdev) auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF); - if (!auto_off && hdev->dev_type == HCI_BREDR) - mgmt_powered(hdev, 0); + if (!auto_off && hdev->dev_type == HCI_BREDR && + hci_dev_test_flag(hdev, HCI_MGMT)) + __mgmt_power_off(hdev); hci_inquiry_cache_flush(hdev); hci_pend_le_actions_clear(hdev); @@ -1774,7 +1769,7 @@ static void hci_update_scan_state(struct hci_dev *hdev, u8 scan) hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) - mgmt_update_adv_data(hdev); + hci_req_update_adv_data(hdev, hdev->cur_adv_instance); mgmt_new_settings(hdev); } @@ -2019,6 +2014,16 @@ static void hci_power_on(struct work_struct *work) BT_DBG("%s", hdev->name); + if (test_bit(HCI_UP, &hdev->flags) && + hci_dev_test_flag(hdev, HCI_MGMT) && + hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { + hci_req_sync_lock(hdev); + err = __hci_req_hci_power_on(hdev); + hci_req_sync_unlock(hdev); + mgmt_power_on(hdev, err); + return; + } + err = hci_dev_do_open(hdev); if (err < 0) { hci_dev_lock(hdev); @@ -2101,28 +2106,6 @@ static void hci_error_reset(struct work_struct *work) hci_dev_do_open(hdev); } -static void hci_discov_off(struct work_struct *work) -{ - struct hci_dev *hdev; - - hdev = container_of(work, struct hci_dev, discov_off.work); - - BT_DBG("%s", hdev->name); - - mgmt_discoverable_timeout(hdev); -} - -static void hci_adv_timeout_expire(struct work_struct *work) -{ - struct hci_dev *hdev; - - hdev = container_of(work, struct hci_dev, adv_instance_expire.work); - - BT_DBG("%s", hdev->name); - - mgmt_adv_timeout_expired(hdev); -} - void hci_uuids_clear(struct hci_dev *hdev) { struct bt_uuid *uuid, *tmp; @@ -2627,9 +2610,12 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) BT_DBG("%s removing %dMR", hdev->name, instance); - if (hdev->cur_adv_instance == instance && hdev->adv_instance_timeout) { - cancel_delayed_work(&hdev->adv_instance_expire); - hdev->adv_instance_timeout = 0; + if (hdev->cur_adv_instance == instance) { + if (hdev->adv_instance_timeout) { + cancel_delayed_work(&hdev->adv_instance_expire); + hdev->adv_instance_timeout = 0; + } + hdev->cur_adv_instance = 0x00; } list_del(&adv_instance->list); @@ -2656,6 +2642,7 @@ void hci_adv_instances_clear(struct hci_dev *hdev) } hdev->adv_instance_cnt = 0; + hdev->cur_adv_instance = 0x00; } /* This function requires the caller holds hdev->lock */ @@ -2726,12 +2713,10 @@ struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, void hci_bdaddr_list_clear(struct list_head *bdaddr_list) { - struct list_head *p, *n; - - list_for_each_safe(p, n, bdaddr_list) { - struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list); + struct bdaddr_list *b, *n; - list_del(p); + list_for_each_entry_safe(b, n, bdaddr_list, list) { + list_del(&b->list); kfree(b); } } @@ -3002,8 +2987,6 @@ struct hci_dev *hci_alloc_dev(void) INIT_WORK(&hdev->error_reset, hci_error_reset); INIT_DELAYED_WORK(&hdev->power_off, hci_power_off); - INIT_DELAYED_WORK(&hdev->discov_off, hci_discov_off); - INIT_DELAYED_WORK(&hdev->adv_instance_expire, hci_adv_timeout_expire); skb_queue_head_init(&hdev->rx_q); skb_queue_head_init(&hdev->cmd_q); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d57c11c1c6b54..7554da5b7a8fd 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1183,7 +1183,7 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, hci_discovery_set_state(hdev, DISCOVERY_STOPPED); else if (!hci_dev_test_flag(hdev, HCI_LE_ADV) && hdev->discovery.state == DISCOVERY_FINDING) - mgmt_reenable_advertising(hdev); + hci_req_reenable_advertising(hdev); break; @@ -2176,7 +2176,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_send_cmd(hdev, HCI_OP_READ_REMOTE_FEATURES, sizeof(cp), &cp); - hci_update_page_scan(hdev); + hci_req_update_scan(hdev); } /* Set packet type for incoming connection */ @@ -2362,7 +2362,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (test_bit(HCI_CONN_FLUSH_KEY, &conn->flags)) hci_remove_link_key(hdev, &conn->dst); - hci_update_page_scan(hdev); + hci_req_update_scan(hdev); } params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); @@ -2401,7 +2401,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) * is timed out due to Directed Advertising." */ if (type == LE_LINK) - mgmt_reenable_advertising(hdev); + hci_req_reenable_advertising(hdev); unlock: hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index e639671f54bd0..9997c31ef9876 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -21,8 +21,11 @@ SOFTWARE IS DISCLAIMED. */ +#include <asm/unaligned.h> + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/mgmt.h> #include "smp.h" #include "hci_request.h" @@ -346,6 +349,311 @@ void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, hci_req_add_ev(req, opcode, plen, param, 0); } +void __hci_req_write_fast_connectable(struct hci_request *req, bool enable) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_write_page_scan_activity acp; + u8 type; + + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + return; + + if (hdev->hci_ver < BLUETOOTH_VER_1_2) + return; + + if (enable) { + type = PAGE_SCAN_TYPE_INTERLACED; + + /* 160 msec page scan interval */ + acp.interval = cpu_to_le16(0x0100); + } else { + type = PAGE_SCAN_TYPE_STANDARD; /* default */ + + /* default 1.28 sec page scan */ + acp.interval = cpu_to_le16(0x0800); + } + + acp.window = cpu_to_le16(0x0012); + + if (__cpu_to_le16(hdev->page_scan_interval) != acp.interval || + __cpu_to_le16(hdev->page_scan_window) != acp.window) + hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_ACTIVITY, + sizeof(acp), &acp); + + if (hdev->page_scan_type != type) + hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type); +} + +/* This function controls the background scanning based on hdev->pend_le_conns + * list. If there are pending LE connection we start the background scanning, + * otherwise we stop it. + * + * This function requires the caller holds hdev->lock. + */ +static void __hci_update_background_scan(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + + if (!test_bit(HCI_UP, &hdev->flags) || + test_bit(HCI_INIT, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG) || + hci_dev_test_flag(hdev, HCI_AUTO_OFF) || + hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return; + + /* No point in doing scanning if LE support hasn't been enabled */ + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return; + + /* If discovery is active don't interfere with it */ + if (hdev->discovery.state != DISCOVERY_STOPPED) + return; + + /* Reset RSSI and UUID filters when starting background scanning + * since these filters are meant for service discovery only. + * + * The Start Discovery and Start Service Discovery operations + * ensure to set proper values for RSSI threshold and UUID + * filter list. So it is safe to just reset them here. + */ + hci_discovery_filter_clear(hdev); + + if (list_empty(&hdev->pend_le_conns) && + list_empty(&hdev->pend_le_reports)) { + /* If there is no pending LE connections or devices + * to be scanned for, we should stop the background + * scanning. + */ + + /* If controller is not scanning we are done. */ + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) + return; + + hci_req_add_le_scan_disable(req); + + BT_DBG("%s stopping background scanning", hdev->name); + } else { + /* If there is at least one pending LE connection, we should + * keep the background scan running. + */ + + /* If controller is connecting, we should not start scanning + * since some controllers are not able to scan and connect at + * the same time. + */ + if (hci_lookup_le_connect(hdev)) + return; + + /* If controller is currently scanning, we stop it to ensure we + * don't miss any advertising (due to duplicates filter). + */ + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) + hci_req_add_le_scan_disable(req); + + hci_req_add_le_passive_scan(req); + + BT_DBG("%s starting background scanning", hdev->name); + } +} + +void __hci_req_update_name(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_write_local_name cp; + + memcpy(cp.name, hdev->dev_name, sizeof(cp.name)); + + hci_req_add(req, HCI_OP_WRITE_LOCAL_NAME, sizeof(cp), &cp); +} + +#define PNP_INFO_SVCLASS_ID 0x1200 + +static u8 *create_uuid16_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) +{ + u8 *ptr = data, *uuids_start = NULL; + struct bt_uuid *uuid; + + if (len < 4) + return ptr; + + list_for_each_entry(uuid, &hdev->uuids, list) { + u16 uuid16; + + if (uuid->size != 16) + continue; + + uuid16 = get_unaligned_le16(&uuid->uuid[12]); + if (uuid16 < 0x1100) + continue; + + if (uuid16 == PNP_INFO_SVCLASS_ID) + continue; + + if (!uuids_start) { + uuids_start = ptr; + uuids_start[0] = 1; + uuids_start[1] = EIR_UUID16_ALL; + ptr += 2; + } + + /* Stop if not enough space to put next UUID */ + if ((ptr - data) + sizeof(u16) > len) { + uuids_start[1] = EIR_UUID16_SOME; + break; + } + + *ptr++ = (uuid16 & 0x00ff); + *ptr++ = (uuid16 & 0xff00) >> 8; + uuids_start[0] += sizeof(uuid16); + } + + return ptr; +} + +static u8 *create_uuid32_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) +{ + u8 *ptr = data, *uuids_start = NULL; + struct bt_uuid *uuid; + + if (len < 6) + return ptr; + + list_for_each_entry(uuid, &hdev->uuids, list) { + if (uuid->size != 32) + continue; + + if (!uuids_start) { + uuids_start = ptr; + uuids_start[0] = 1; + uuids_start[1] = EIR_UUID32_ALL; + ptr += 2; + } + + /* Stop if not enough space to put next UUID */ + if ((ptr - data) + sizeof(u32) > len) { + uuids_start[1] = EIR_UUID32_SOME; + break; + } + + memcpy(ptr, &uuid->uuid[12], sizeof(u32)); + ptr += sizeof(u32); + uuids_start[0] += sizeof(u32); + } + + return ptr; +} + +static u8 *create_uuid128_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) +{ + u8 *ptr = data, *uuids_start = NULL; + struct bt_uuid *uuid; + + if (len < 18) + return ptr; + + list_for_each_entry(uuid, &hdev->uuids, list) { + if (uuid->size != 128) + continue; + + if (!uuids_start) { + uuids_start = ptr; + uuids_start[0] = 1; + uuids_start[1] = EIR_UUID128_ALL; + ptr += 2; + } + + /* Stop if not enough space to put next UUID */ + if ((ptr - data) + 16 > len) { + uuids_start[1] = EIR_UUID128_SOME; + break; + } + + memcpy(ptr, uuid->uuid, 16); + ptr += 16; + uuids_start[0] += 16; + } + + return ptr; +} + +static void create_eir(struct hci_dev *hdev, u8 *data) +{ + u8 *ptr = data; + size_t name_len; + + name_len = strlen(hdev->dev_name); + + if (name_len > 0) { + /* EIR Data type */ + if (name_len > 48) { + name_len = 48; + ptr[1] = EIR_NAME_SHORT; + } else + ptr[1] = EIR_NAME_COMPLETE; + + /* EIR Data length */ + ptr[0] = name_len + 1; + + memcpy(ptr + 2, hdev->dev_name, name_len); + + ptr += (name_len + 2); + } + + if (hdev->inq_tx_power != HCI_TX_POWER_INVALID) { + ptr[0] = 2; + ptr[1] = EIR_TX_POWER; + ptr[2] = (u8) hdev->inq_tx_power; + + ptr += 3; + } + + if (hdev->devid_source > 0) { + ptr[0] = 9; + ptr[1] = EIR_DEVICE_ID; + + put_unaligned_le16(hdev->devid_source, ptr + 2); + put_unaligned_le16(hdev->devid_vendor, ptr + 4); + put_unaligned_le16(hdev->devid_product, ptr + 6); + put_unaligned_le16(hdev->devid_version, ptr + 8); + + ptr += 10; + } + + ptr = create_uuid16_list(hdev, ptr, HCI_MAX_EIR_LENGTH - (ptr - data)); + ptr = create_uuid32_list(hdev, ptr, HCI_MAX_EIR_LENGTH - (ptr - data)); + ptr = create_uuid128_list(hdev, ptr, HCI_MAX_EIR_LENGTH - (ptr - data)); +} + +void __hci_req_update_eir(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_write_eir cp; + + if (!hdev_is_powered(hdev)) + return; + + if (!lmp_ext_inq_capable(hdev)) + return; + + if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) + return; + + if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) + return; + + memset(&cp, 0, sizeof(cp)); + + create_eir(hdev, cp.data); + + if (memcmp(cp.data, hdev->eir, sizeof(cp.data)) == 0) + return; + + memcpy(hdev->eir, cp.data, sizeof(cp.data)); + + hci_req_add(req, HCI_OP_WRITE_EIR, sizeof(cp), &cp); +} + void hci_req_add_le_scan_disable(struct hci_request *req) { struct hci_cp_le_set_scan_enable cp; @@ -507,6 +815,483 @@ void hci_req_add_le_passive_scan(struct hci_request *req) &enable_cp); } +static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) +{ + u8 instance = hdev->cur_adv_instance; + struct adv_info *adv_instance; + + /* Ignore instance 0 */ + if (instance == 0x00) + return 0; + + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return 0; + + /* TODO: Take into account the "appearance" and "local-name" flags here. + * These are currently being ignored as they are not supported. + */ + return adv_instance->scan_rsp_len; +} + +void __hci_req_disable_advertising(struct hci_request *req) +{ + u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + +static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance) +{ + u32 flags; + struct adv_info *adv_instance; + + if (instance == 0x00) { + /* Instance 0 always manages the "Tx Power" and "Flags" + * fields + */ + flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS; + + /* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting + * corresponds to the "connectable" instance flag. + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) + flags |= MGMT_ADV_FLAG_CONNECTABLE; + + return flags; + } + + adv_instance = hci_find_adv_instance(hdev, instance); + + /* Return 0 when we got an invalid instance identifier. */ + if (!adv_instance) + return 0; + + return adv_instance->flags; +} + +void __hci_req_enable_advertising(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_le_set_adv_param cp; + u8 own_addr_type, enable = 0x01; + bool connectable; + u32 flags; + + if (hci_conn_num(hdev, LE_LINK) > 0) + return; + + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) + __hci_req_disable_advertising(req); + + /* Clear the HCI_LE_ADV bit temporarily so that the + * hci_update_random_address knows that it's safe to go ahead + * and write a new random address. The flag will be set back on + * as soon as the SET_ADV_ENABLE HCI command completes. + */ + hci_dev_clear_flag(hdev, HCI_LE_ADV); + + flags = get_adv_instance_flags(hdev, hdev->cur_adv_instance); + + /* If the "connectable" instance flag was not set, then choose between + * ADV_IND and ADV_NONCONN_IND based on the global connectable setting. + */ + connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) || + mgmt_get_connectable(hdev); + + /* Set require_privacy to true only when non-connectable + * advertising is used. In that case it is fine to use a + * non-resolvable private address. + */ + if (hci_update_random_address(req, !connectable, &own_addr_type) < 0) + return; + + memset(&cp, 0, sizeof(cp)); + cp.min_interval = cpu_to_le16(hdev->le_adv_min_interval); + cp.max_interval = cpu_to_le16(hdev->le_adv_max_interval); + + if (connectable) + cp.type = LE_ADV_IND; + else if (get_cur_adv_instance_scan_rsp_len(hdev)) + cp.type = LE_ADV_SCAN_IND; + else + cp.type = LE_ADV_NONCONN_IND; + + cp.own_address_type = own_addr_type; + cp.channel_map = hdev->le_adv_channel_map; + + hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + +static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) +{ + u8 ad_len = 0; + size_t name_len; + + name_len = strlen(hdev->dev_name); + if (name_len > 0) { + size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2; + + if (name_len > max_len) { + name_len = max_len; + ptr[1] = EIR_NAME_SHORT; + } else + ptr[1] = EIR_NAME_COMPLETE; + + ptr[0] = name_len + 1; + + memcpy(ptr + 2, hdev->dev_name, name_len); + + ad_len += (name_len + 2); + ptr += (name_len + 2); + } + + return ad_len; +} + +static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, + u8 *ptr) +{ + struct adv_info *adv_instance; + + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return 0; + + /* TODO: Set the appropriate entries based on advertising instance flags + * here once flags other than 0 are supported. + */ + memcpy(ptr, adv_instance->scan_rsp_data, + adv_instance->scan_rsp_len); + + return adv_instance->scan_rsp_len; +} + +void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_le_set_scan_rsp_data cp; + u8 len; + + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return; + + memset(&cp, 0, sizeof(cp)); + + if (instance) + len = create_instance_scan_rsp_data(hdev, instance, cp.data); + else + len = create_default_scan_rsp_data(hdev, cp.data); + + if (hdev->scan_rsp_data_len == len && + !memcmp(cp.data, hdev->scan_rsp_data, len)) + return; + + memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + hdev->scan_rsp_data_len = len; + + cp.length = len; + + hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); +} + +static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) +{ + struct adv_info *adv_instance = NULL; + u8 ad_len = 0, flags = 0; + u32 instance_flags; + + /* Return 0 when the current instance identifier is invalid. */ + if (instance) { + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return 0; + } + + instance_flags = get_adv_instance_flags(hdev, instance); + + /* The Add Advertising command allows userspace to set both the general + * and limited discoverable flags. + */ + if (instance_flags & MGMT_ADV_FLAG_DISCOV) + flags |= LE_AD_GENERAL; + + if (instance_flags & MGMT_ADV_FLAG_LIMITED_DISCOV) + flags |= LE_AD_LIMITED; + + if (flags || (instance_flags & MGMT_ADV_FLAG_MANAGED_FLAGS)) { + /* If a discovery flag wasn't provided, simply use the global + * settings. + */ + if (!flags) + flags |= mgmt_get_adv_discov_flags(hdev); + + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + flags |= LE_AD_NO_BREDR; + + /* If flags would still be empty, then there is no need to + * include the "Flags" AD field". + */ + if (flags) { + ptr[0] = 0x02; + ptr[1] = EIR_FLAGS; + ptr[2] = flags; + + ad_len += 3; + ptr += 3; + } + } + + if (adv_instance) { + memcpy(ptr, adv_instance->adv_data, + adv_instance->adv_data_len); + ad_len += adv_instance->adv_data_len; + ptr += adv_instance->adv_data_len; + } + + /* Provide Tx Power only if we can provide a valid value for it */ + if (hdev->adv_tx_power != HCI_TX_POWER_INVALID && + (instance_flags & MGMT_ADV_FLAG_TX_POWER)) { + ptr[0] = 0x02; + ptr[1] = EIR_TX_POWER; + ptr[2] = (u8)hdev->adv_tx_power; + + ad_len += 3; + ptr += 3; + } + + return ad_len; +} + +void __hci_req_update_adv_data(struct hci_request *req, u8 instance) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_le_set_adv_data cp; + u8 len; + + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return; + + memset(&cp, 0, sizeof(cp)); + + len = create_instance_adv_data(hdev, instance, cp.data); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return; + + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + + hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); +} + +int hci_req_update_adv_data(struct hci_dev *hdev, u8 instance) +{ + struct hci_request req; + + hci_req_init(&req, hdev); + __hci_req_update_adv_data(&req, instance); + + return hci_req_run(&req, NULL); +} + +static void adv_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) +{ + BT_DBG("%s status %u", hdev->name, status); +} + +void hci_req_reenable_advertising(struct hci_dev *hdev) +{ + struct hci_request req; + + if (!hci_dev_test_flag(hdev, HCI_ADVERTISING) && + list_empty(&hdev->adv_instances)) + return; + + hci_req_init(&req, hdev); + + if (hdev->cur_adv_instance) { + __hci_req_schedule_adv_instance(&req, hdev->cur_adv_instance, + true); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + __hci_req_enable_advertising(&req); + } + + hci_req_run(&req, adv_enable_complete); +} + +static void adv_timeout_expire(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + adv_instance_expire.work); + + struct hci_request req; + u8 instance; + + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + hdev->adv_instance_timeout = 0; + + instance = hdev->cur_adv_instance; + if (instance == 0x00) + goto unlock; + + hci_req_init(&req, hdev); + + hci_req_clear_adv_instance(hdev, &req, instance, false); + + if (list_empty(&hdev->adv_instances)) + __hci_req_disable_advertising(&req); + + hci_req_run(&req, NULL); + +unlock: + hci_dev_unlock(hdev); +} + +int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, + bool force) +{ + struct hci_dev *hdev = req->hdev; + struct adv_info *adv_instance = NULL; + u16 timeout; + + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + list_empty(&hdev->adv_instances)) + return -EPERM; + + if (hdev->adv_instance_timeout) + return -EBUSY; + + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return -ENOENT; + + /* A zero timeout means unlimited advertising. As long as there is + * only one instance, duration should be ignored. We still set a timeout + * in case further instances are being added later on. + * + * If the remaining lifetime of the instance is more than the duration + * then the timeout corresponds to the duration, otherwise it will be + * reduced to the remaining instance lifetime. + */ + if (adv_instance->timeout == 0 || + adv_instance->duration <= adv_instance->remaining_time) + timeout = adv_instance->duration; + else + timeout = adv_instance->remaining_time; + + /* The remaining time is being reduced unless the instance is being + * advertised without time limit. + */ + if (adv_instance->timeout) + adv_instance->remaining_time = + adv_instance->remaining_time - timeout; + + hdev->adv_instance_timeout = timeout; + queue_delayed_work(hdev->req_workqueue, + &hdev->adv_instance_expire, + msecs_to_jiffies(timeout * 1000)); + + /* If we're just re-scheduling the same instance again then do not + * execute any HCI commands. This happens when a single instance is + * being advertised. + */ + if (!force && hdev->cur_adv_instance == instance && + hci_dev_test_flag(hdev, HCI_LE_ADV)) + return 0; + + hdev->cur_adv_instance = instance; + __hci_req_update_adv_data(req, instance); + __hci_req_update_scan_rsp_data(req, instance); + __hci_req_enable_advertising(req); + + return 0; +} + +static void cancel_adv_timeout(struct hci_dev *hdev) +{ + if (hdev->adv_instance_timeout) { + hdev->adv_instance_timeout = 0; + cancel_delayed_work(&hdev->adv_instance_expire); + } +} + +/* For a single instance: + * - force == true: The instance will be removed even when its remaining + * lifetime is not zero. + * - force == false: the instance will be deactivated but kept stored unless + * the remaining lifetime is zero. + * + * For instance == 0x00: + * - force == true: All instances will be removed regardless of their timeout + * setting. + * - force == false: Only instances that have a timeout will be removed. + */ +void hci_req_clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, + u8 instance, bool force) +{ + struct adv_info *adv_instance, *n, *next_instance = NULL; + int err; + u8 rem_inst; + + /* Cancel any timeout concerning the removed instance(s). */ + if (!instance || hdev->cur_adv_instance == instance) + cancel_adv_timeout(hdev); + + /* Get the next instance to advertise BEFORE we remove + * the current one. This can be the same instance again + * if there is only one instance. + */ + if (instance && hdev->cur_adv_instance == instance) + next_instance = hci_get_next_instance(hdev, instance); + + if (instance == 0x00) { + list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, + list) { + if (!(force || adv_instance->timeout)) + continue; + + rem_inst = adv_instance->instance; + err = hci_remove_adv_instance(hdev, rem_inst); + if (!err) + mgmt_advertising_removed(NULL, hdev, rem_inst); + } + } else { + adv_instance = hci_find_adv_instance(hdev, instance); + + if (force || (adv_instance && adv_instance->timeout && + !adv_instance->remaining_time)) { + /* Don't advertise a removed instance. */ + if (next_instance && + next_instance->instance == instance) + next_instance = NULL; + + err = hci_remove_adv_instance(hdev, instance); + if (!err) + mgmt_advertising_removed(NULL, hdev, instance); + } + } + + if (!req || !hdev_is_powered(hdev) || + hci_dev_test_flag(hdev, HCI_ADVERTISING)) + return; + + if (next_instance) + __hci_req_schedule_adv_instance(req, next_instance->instance, + false); +} + static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) { struct hci_dev *hdev = req->hdev; @@ -637,7 +1422,7 @@ static bool disconnected_whitelist_entries(struct hci_dev *hdev) return false; } -void __hci_update_page_scan(struct hci_request *req) +void __hci_req_update_scan(struct hci_request *req) { struct hci_dev *hdev = req->hdev; u8 scan; @@ -657,95 +1442,168 @@ void __hci_update_page_scan(struct hci_request *req) else scan = SCAN_DISABLED; - if (test_bit(HCI_PSCAN, &hdev->flags) == !!(scan & SCAN_PAGE)) - return; - if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) scan |= SCAN_INQUIRY; + if (test_bit(HCI_PSCAN, &hdev->flags) == !!(scan & SCAN_PAGE) && + test_bit(HCI_ISCAN, &hdev->flags) == !!(scan & SCAN_INQUIRY)) + return; + hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } -void hci_update_page_scan(struct hci_dev *hdev) +static int update_scan(struct hci_request *req, unsigned long opt) { - struct hci_request req; + hci_dev_lock(req->hdev); + __hci_req_update_scan(req); + hci_dev_unlock(req->hdev); + return 0; +} - hci_req_init(&req, hdev); - __hci_update_page_scan(&req); - hci_req_run(&req, NULL); +static void scan_update_work(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, scan_update); + + hci_req_sync(hdev, update_scan, 0, HCI_CMD_TIMEOUT, NULL); } -/* This function controls the background scanning based on hdev->pend_le_conns - * list. If there are pending LE connection we start the background scanning, - * otherwise we stop it. - * - * This function requires the caller holds hdev->lock. - */ -static void __hci_update_background_scan(struct hci_request *req) +static int connectable_update(struct hci_request *req, unsigned long opt) { struct hci_dev *hdev = req->hdev; - if (!test_bit(HCI_UP, &hdev->flags) || - test_bit(HCI_INIT, &hdev->flags) || - hci_dev_test_flag(hdev, HCI_SETUP) || - hci_dev_test_flag(hdev, HCI_CONFIG) || - hci_dev_test_flag(hdev, HCI_AUTO_OFF) || - hci_dev_test_flag(hdev, HCI_UNREGISTER)) + hci_dev_lock(hdev); + + __hci_req_update_scan(req); + + /* If BR/EDR is not enabled and we disable advertising as a + * by-product of disabling connectable, we need to update the + * advertising flags. + */ + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + __hci_req_update_adv_data(req, hdev->cur_adv_instance); + + /* Update the advertising parameters if necessary */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + !list_empty(&hdev->adv_instances)) + __hci_req_enable_advertising(req); + + __hci_update_background_scan(req); + + hci_dev_unlock(hdev); + + return 0; +} + +static void connectable_update_work(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + connectable_update); + u8 status; + + hci_req_sync(hdev, connectable_update, 0, HCI_CMD_TIMEOUT, &status); + mgmt_set_connectable_complete(hdev, status); +} + +static u8 get_service_classes(struct hci_dev *hdev) +{ + struct bt_uuid *uuid; + u8 val = 0; + + list_for_each_entry(uuid, &hdev->uuids, list) + val |= uuid->svc_hint; + + return val; +} + +void __hci_req_update_class(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + u8 cod[3]; + + BT_DBG("%s", hdev->name); + + if (!hdev_is_powered(hdev)) return; - /* No point in doing scanning if LE support hasn't been enabled */ - if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) return; - /* If discovery is active don't interfere with it */ - if (hdev->discovery.state != DISCOVERY_STOPPED) + if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) return; - /* Reset RSSI and UUID filters when starting background scanning - * since these filters are meant for service discovery only. - * - * The Start Discovery and Start Service Discovery operations - * ensure to set proper values for RSSI threshold and UUID - * filter list. So it is safe to just reset them here. - */ - hci_discovery_filter_clear(hdev); + cod[0] = hdev->minor_class; + cod[1] = hdev->major_class; + cod[2] = get_service_classes(hdev); - if (list_empty(&hdev->pend_le_conns) && - list_empty(&hdev->pend_le_reports)) { - /* If there is no pending LE connections or devices - * to be scanned for, we should stop the background - * scanning. - */ + if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) + cod[1] |= 0x20; - /* If controller is not scanning we are done. */ - if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) - return; + if (memcmp(cod, hdev->dev_class, 3) == 0) + return; - hci_req_add_le_scan_disable(req); + hci_req_add(req, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod); +} - BT_DBG("%s stopping background scanning", hdev->name); +static void write_iac(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_write_current_iac_lap cp; + + if (!hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) + return; + + if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) { + /* Limited discoverable mode */ + cp.num_iac = min_t(u8, hdev->num_iac, 2); + cp.iac_lap[0] = 0x00; /* LIAC */ + cp.iac_lap[1] = 0x8b; + cp.iac_lap[2] = 0x9e; + cp.iac_lap[3] = 0x33; /* GIAC */ + cp.iac_lap[4] = 0x8b; + cp.iac_lap[5] = 0x9e; } else { - /* If there is at least one pending LE connection, we should - * keep the background scan running. - */ + /* General discoverable mode */ + cp.num_iac = 1; + cp.iac_lap[0] = 0x33; /* GIAC */ + cp.iac_lap[1] = 0x8b; + cp.iac_lap[2] = 0x9e; + } - /* If controller is connecting, we should not start scanning - * since some controllers are not able to scan and connect at - * the same time. - */ - if (hci_lookup_le_connect(hdev)) - return; + hci_req_add(req, HCI_OP_WRITE_CURRENT_IAC_LAP, + (cp.num_iac * 3) + 1, &cp); +} - /* If controller is currently scanning, we stop it to ensure we - * don't miss any advertising (due to duplicates filter). - */ - if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) - hci_req_add_le_scan_disable(req); +static int discoverable_update(struct hci_request *req, unsigned long opt) +{ + struct hci_dev *hdev = req->hdev; - hci_req_add_le_passive_scan(req); + hci_dev_lock(hdev); - BT_DBG("%s starting background scanning", hdev->name); + if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { + write_iac(req); + __hci_req_update_scan(req); + __hci_req_update_class(req); } + + /* Advertising instances don't use the global discoverable setting, so + * only update AD if advertising was enabled using Set Advertising. + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) + __hci_req_update_adv_data(req, 0x00); + + hci_dev_unlock(hdev); + + return 0; +} + +static void discoverable_update_work(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + discoverable_update); + u8 status; + + hci_req_sync(hdev, discoverable_update, 0, HCI_CMD_TIMEOUT, &status); + mgmt_set_discoverable_complete(hdev, status); } void __hci_abort_conn(struct hci_request *req, struct hci_conn *conn, @@ -1024,14 +1882,6 @@ unlock: hci_dev_unlock(hdev); } -static void cancel_adv_timeout(struct hci_dev *hdev) -{ - if (hdev->adv_instance_timeout) { - hdev->adv_instance_timeout = 0; - cancel_delayed_work(&hdev->adv_instance_expire); - } -} - static void disable_advertising(struct hci_request *req) { u8 enable = 0x00; @@ -1266,12 +2116,134 @@ static void discov_update(struct work_struct *work) } } +static void discov_off(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + discov_off.work); + + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + /* When discoverable timeout triggers, then just make sure + * the limited discoverable flag is cleared. Even in the case + * of a timeout triggered from general discoverable, it is + * safe to unconditionally clear the flag. + */ + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); + hdev->discov_timeout = 0; + + hci_dev_unlock(hdev); + + hci_req_sync(hdev, discoverable_update, 0, HCI_CMD_TIMEOUT, NULL); + mgmt_new_settings(hdev); +} + +static int powered_update_hci(struct hci_request *req, unsigned long opt) +{ + struct hci_dev *hdev = req->hdev; + u8 link_sec; + + hci_dev_lock(hdev); + + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && + !lmp_host_ssp_capable(hdev)) { + u8 mode = 0x01; + + hci_req_add(req, HCI_OP_WRITE_SSP_MODE, sizeof(mode), &mode); + + if (bredr_sc_enabled(hdev) && !lmp_host_sc_capable(hdev)) { + u8 support = 0x01; + + hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT, + sizeof(support), &support); + } + } + + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED) && + lmp_bredr_capable(hdev)) { + struct hci_cp_write_le_host_supported cp; + + cp.le = 0x01; + cp.simul = 0x00; + + /* Check first if we already have the right + * host state (host features set) + */ + if (cp.le != lmp_host_le_capable(hdev) || + cp.simul != lmp_host_le_br_capable(hdev)) + hci_req_add(req, HCI_OP_WRITE_LE_HOST_SUPPORTED, + sizeof(cp), &cp); + } + + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { + /* Make sure the controller has a good default for + * advertising data. This also applies to the case + * where BR/EDR was toggled during the AUTO_OFF phase. + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + list_empty(&hdev->adv_instances)) { + __hci_req_update_adv_data(req, 0x00); + __hci_req_update_scan_rsp_data(req, 0x00); + + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) + __hci_req_enable_advertising(req); + } else if (!list_empty(&hdev->adv_instances)) { + struct adv_info *adv_instance; + + adv_instance = list_first_entry(&hdev->adv_instances, + struct adv_info, list); + __hci_req_schedule_adv_instance(req, + adv_instance->instance, + true); + } + } + + link_sec = hci_dev_test_flag(hdev, HCI_LINK_SECURITY); + if (link_sec != test_bit(HCI_AUTH, &hdev->flags)) + hci_req_add(req, HCI_OP_WRITE_AUTH_ENABLE, + sizeof(link_sec), &link_sec); + + if (lmp_bredr_capable(hdev)) { + if (hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE)) + __hci_req_write_fast_connectable(req, true); + else + __hci_req_write_fast_connectable(req, false); + __hci_req_update_scan(req); + __hci_req_update_class(req); + __hci_req_update_name(req); + __hci_req_update_eir(req); + } + + hci_dev_unlock(hdev); + return 0; +} + +int __hci_req_hci_power_on(struct hci_dev *hdev) +{ + /* Register the available SMP channels (BR/EDR and LE) only when + * successfully powering on the controller. This late + * registration is required so that LE SMP can clearly decide if + * the public address or static address is used. + */ + smp_register(hdev); + + return __hci_req_sync(hdev, powered_update_hci, 0, HCI_CMD_TIMEOUT, + NULL); +} + void hci_request_setup(struct hci_dev *hdev) { INIT_WORK(&hdev->discov_update, discov_update); INIT_WORK(&hdev->bg_scan_update, bg_scan_update); + INIT_WORK(&hdev->scan_update, scan_update_work); + INIT_WORK(&hdev->connectable_update, connectable_update_work); + INIT_WORK(&hdev->discoverable_update, discoverable_update_work); + INIT_DELAYED_WORK(&hdev->discov_off, discov_off); INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable_work); INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart_work); + INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire); } void hci_request_cancel_all(struct hci_dev *hdev) @@ -1280,6 +2252,15 @@ void hci_request_cancel_all(struct hci_dev *hdev) cancel_work_sync(&hdev->discov_update); cancel_work_sync(&hdev->bg_scan_update); + cancel_work_sync(&hdev->scan_update); + cancel_work_sync(&hdev->connectable_update); + cancel_work_sync(&hdev->discoverable_update); + cancel_delayed_work_sync(&hdev->discov_off); cancel_delayed_work_sync(&hdev->le_scan_disable); cancel_delayed_work_sync(&hdev->le_scan_restart); + + if (hdev->adv_instance_timeout) { + cancel_delayed_work_sync(&hdev->adv_instance_expire); + hdev->adv_instance_timeout = 0; + } } diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 6b9e59f7f7a96..64ff8c040d50f 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -55,14 +55,38 @@ void hci_req_sync_cancel(struct hci_dev *hdev, int err); struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param); +int __hci_req_hci_power_on(struct hci_dev *hdev); + +void __hci_req_write_fast_connectable(struct hci_request *req, bool enable); +void __hci_req_update_name(struct hci_request *req); +void __hci_req_update_eir(struct hci_request *req); + void hci_req_add_le_scan_disable(struct hci_request *req); void hci_req_add_le_passive_scan(struct hci_request *req); +void hci_req_reenable_advertising(struct hci_dev *hdev); +void __hci_req_enable_advertising(struct hci_request *req); +void __hci_req_disable_advertising(struct hci_request *req); +void __hci_req_update_adv_data(struct hci_request *req, u8 instance); +int hci_req_update_adv_data(struct hci_dev *hdev, u8 instance); +void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance); + +int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, + bool force); +void hci_req_clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, + u8 instance, bool force); + +void __hci_req_update_class(struct hci_request *req); + /* Returns true if HCI commands were queued */ bool hci_req_stop_discovery(struct hci_request *req); -void hci_update_page_scan(struct hci_dev *hdev); -void __hci_update_page_scan(struct hci_request *req); +static inline void hci_req_update_scan(struct hci_dev *hdev) +{ + queue_work(hdev->req_workqueue, &hdev->scan_update); +} + +void __hci_req_update_scan(struct hci_request *req); int hci_update_random_address(struct hci_request *req, bool require_privacy, u8 *own_addr_type); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 3d9d2e4839c5d..621f6fdd0dd14 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -719,116 +719,6 @@ static u32 get_current_settings(struct hci_dev *hdev) return settings; } -#define PNP_INFO_SVCLASS_ID 0x1200 - -static u8 *create_uuid16_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) -{ - u8 *ptr = data, *uuids_start = NULL; - struct bt_uuid *uuid; - - if (len < 4) - return ptr; - - list_for_each_entry(uuid, &hdev->uuids, list) { - u16 uuid16; - - if (uuid->size != 16) - continue; - - uuid16 = get_unaligned_le16(&uuid->uuid[12]); - if (uuid16 < 0x1100) - continue; - - if (uuid16 == PNP_INFO_SVCLASS_ID) - continue; - - if (!uuids_start) { - uuids_start = ptr; - uuids_start[0] = 1; - uuids_start[1] = EIR_UUID16_ALL; - ptr += 2; - } - - /* Stop if not enough space to put next UUID */ - if ((ptr - data) + sizeof(u16) > len) { - uuids_start[1] = EIR_UUID16_SOME; - break; - } - - *ptr++ = (uuid16 & 0x00ff); - *ptr++ = (uuid16 & 0xff00) >> 8; - uuids_start[0] += sizeof(uuid16); - } - - return ptr; -} - -static u8 *create_uuid32_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) -{ - u8 *ptr = data, *uuids_start = NULL; - struct bt_uuid *uuid; - - if (len < 6) - return ptr; - - list_for_each_entry(uuid, &hdev->uuids, list) { - if (uuid->size != 32) - continue; - - if (!uuids_start) { - uuids_start = ptr; - uuids_start[0] = 1; - uuids_start[1] = EIR_UUID32_ALL; - ptr += 2; - } - - /* Stop if not enough space to put next UUID */ - if ((ptr - data) + sizeof(u32) > len) { - uuids_start[1] = EIR_UUID32_SOME; - break; - } - - memcpy(ptr, &uuid->uuid[12], sizeof(u32)); - ptr += sizeof(u32); - uuids_start[0] += sizeof(u32); - } - - return ptr; -} - -static u8 *create_uuid128_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) -{ - u8 *ptr = data, *uuids_start = NULL; - struct bt_uuid *uuid; - - if (len < 18) - return ptr; - - list_for_each_entry(uuid, &hdev->uuids, list) { - if (uuid->size != 128) - continue; - - if (!uuids_start) { - uuids_start = ptr; - uuids_start[0] = 1; - uuids_start[1] = EIR_UUID128_ALL; - ptr += 2; - } - - /* Stop if not enough space to put next UUID */ - if ((ptr - data) + 16 > len) { - uuids_start[1] = EIR_UUID128_SOME; - break; - } - - memcpy(ptr, uuid->uuid, 16); - ptr += 16; - uuids_start[0] += 16; - } - - return ptr; -} - static struct mgmt_pending_cmd *pending_find(u16 opcode, struct hci_dev *hdev) { return mgmt_pending_find(HCI_CHANNEL_CONTROL, opcode, hdev); @@ -841,98 +731,7 @@ static struct mgmt_pending_cmd *pending_find_data(u16 opcode, return mgmt_pending_find_data(HCI_CHANNEL_CONTROL, opcode, hdev, data); } -static u8 get_current_adv_instance(struct hci_dev *hdev) -{ - /* The "Set Advertising" setting supersedes the "Add Advertising" - * setting. Here we set the advertising data based on which - * setting was set. When neither apply, default to the global settings, - * represented by instance "0". - */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) && - !hci_dev_test_flag(hdev, HCI_ADVERTISING)) - return hdev->cur_adv_instance; - - return 0x00; -} - -static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) -{ - u8 ad_len = 0; - size_t name_len; - - name_len = strlen(hdev->dev_name); - if (name_len > 0) { - size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2; - - if (name_len > max_len) { - name_len = max_len; - ptr[1] = EIR_NAME_SHORT; - } else - ptr[1] = EIR_NAME_COMPLETE; - - ptr[0] = name_len + 1; - - memcpy(ptr + 2, hdev->dev_name, name_len); - - ad_len += (name_len + 2); - ptr += (name_len + 2); - } - - return ad_len; -} - -static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, - u8 *ptr) -{ - struct adv_info *adv_instance; - - adv_instance = hci_find_adv_instance(hdev, instance); - if (!adv_instance) - return 0; - - /* TODO: Set the appropriate entries based on advertising instance flags - * here once flags other than 0 are supported. - */ - memcpy(ptr, adv_instance->scan_rsp_data, - adv_instance->scan_rsp_len); - - return adv_instance->scan_rsp_len; -} - -static void update_inst_scan_rsp_data(struct hci_request *req, u8 instance) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_rsp_data cp; - u8 len; - - if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) - return; - - memset(&cp, 0, sizeof(cp)); - - if (instance) - len = create_instance_scan_rsp_data(hdev, instance, cp.data); - else - len = create_default_scan_rsp_data(hdev, cp.data); - - if (hdev->scan_rsp_data_len == len && - !memcmp(cp.data, hdev->scan_rsp_data, len)) - return; - - memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); - hdev->scan_rsp_data_len = len; - - cp.length = len; - - hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); -} - -static void update_scan_rsp_data(struct hci_request *req) -{ - update_inst_scan_rsp_data(req, get_current_adv_instance(req->hdev)); -} - -static u8 get_adv_discov_flags(struct hci_dev *hdev) +u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev) { struct mgmt_pending_cmd *cmd; @@ -956,7 +755,7 @@ static u8 get_adv_discov_flags(struct hci_dev *hdev) return 0; } -static bool get_connectable(struct hci_dev *hdev) +bool mgmt_get_connectable(struct hci_dev *hdev) { struct mgmt_pending_cmd *cmd; @@ -973,344 +772,6 @@ static bool get_connectable(struct hci_dev *hdev) return hci_dev_test_flag(hdev, HCI_CONNECTABLE); } -static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance) -{ - u32 flags; - struct adv_info *adv_instance; - - if (instance == 0x00) { - /* Instance 0 always manages the "Tx Power" and "Flags" - * fields - */ - flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS; - - /* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting - * corresponds to the "connectable" instance flag. - */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) - flags |= MGMT_ADV_FLAG_CONNECTABLE; - - return flags; - } - - adv_instance = hci_find_adv_instance(hdev, instance); - - /* Return 0 when we got an invalid instance identifier. */ - if (!adv_instance) - return 0; - - return adv_instance->flags; -} - -static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) -{ - u8 instance = get_current_adv_instance(hdev); - struct adv_info *adv_instance; - - /* Ignore instance 0 */ - if (instance == 0x00) - return 0; - - adv_instance = hci_find_adv_instance(hdev, instance); - if (!adv_instance) - return 0; - - /* TODO: Take into account the "appearance" and "local-name" flags here. - * These are currently being ignored as they are not supported. - */ - return adv_instance->scan_rsp_len; -} - -static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) -{ - struct adv_info *adv_instance = NULL; - u8 ad_len = 0, flags = 0; - u32 instance_flags; - - /* Return 0 when the current instance identifier is invalid. */ - if (instance) { - adv_instance = hci_find_adv_instance(hdev, instance); - if (!adv_instance) - return 0; - } - - instance_flags = get_adv_instance_flags(hdev, instance); - - /* The Add Advertising command allows userspace to set both the general - * and limited discoverable flags. - */ - if (instance_flags & MGMT_ADV_FLAG_DISCOV) - flags |= LE_AD_GENERAL; - - if (instance_flags & MGMT_ADV_FLAG_LIMITED_DISCOV) - flags |= LE_AD_LIMITED; - - if (flags || (instance_flags & MGMT_ADV_FLAG_MANAGED_FLAGS)) { - /* If a discovery flag wasn't provided, simply use the global - * settings. - */ - if (!flags) - flags |= get_adv_discov_flags(hdev); - - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) - flags |= LE_AD_NO_BREDR; - - /* If flags would still be empty, then there is no need to - * include the "Flags" AD field". - */ - if (flags) { - ptr[0] = 0x02; - ptr[1] = EIR_FLAGS; - ptr[2] = flags; - - ad_len += 3; - ptr += 3; - } - } - - if (adv_instance) { - memcpy(ptr, adv_instance->adv_data, - adv_instance->adv_data_len); - ad_len += adv_instance->adv_data_len; - ptr += adv_instance->adv_data_len; - } - - /* Provide Tx Power only if we can provide a valid value for it */ - if (hdev->adv_tx_power != HCI_TX_POWER_INVALID && - (instance_flags & MGMT_ADV_FLAG_TX_POWER)) { - ptr[0] = 0x02; - ptr[1] = EIR_TX_POWER; - ptr[2] = (u8)hdev->adv_tx_power; - - ad_len += 3; - ptr += 3; - } - - return ad_len; -} - -static void update_inst_adv_data(struct hci_request *req, u8 instance) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_data cp; - u8 len; - - if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) - return; - - memset(&cp, 0, sizeof(cp)); - - len = create_instance_adv_data(hdev, instance, cp.data); - - /* There's nothing to do if the data hasn't changed */ - if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) - return; - - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); - hdev->adv_data_len = len; - - cp.length = len; - - hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); -} - -static void update_adv_data(struct hci_request *req) -{ - update_inst_adv_data(req, get_current_adv_instance(req->hdev)); -} - -int mgmt_update_adv_data(struct hci_dev *hdev) -{ - struct hci_request req; - - hci_req_init(&req, hdev); - update_adv_data(&req); - - return hci_req_run(&req, NULL); -} - -static void create_eir(struct hci_dev *hdev, u8 *data) -{ - u8 *ptr = data; - size_t name_len; - - name_len = strlen(hdev->dev_name); - - if (name_len > 0) { - /* EIR Data type */ - if (name_len > 48) { - name_len = 48; - ptr[1] = EIR_NAME_SHORT; - } else - ptr[1] = EIR_NAME_COMPLETE; - - /* EIR Data length */ - ptr[0] = name_len + 1; - - memcpy(ptr + 2, hdev->dev_name, name_len); - - ptr += (name_len + 2); - } - - if (hdev->inq_tx_power != HCI_TX_POWER_INVALID) { - ptr[0] = 2; - ptr[1] = EIR_TX_POWER; - ptr[2] = (u8) hdev->inq_tx_power; - - ptr += 3; - } - - if (hdev->devid_source > 0) { - ptr[0] = 9; - ptr[1] = EIR_DEVICE_ID; - - put_unaligned_le16(hdev->devid_source, ptr + 2); - put_unaligned_le16(hdev->devid_vendor, ptr + 4); - put_unaligned_le16(hdev->devid_product, ptr + 6); - put_unaligned_le16(hdev->devid_version, ptr + 8); - - ptr += 10; - } - - ptr = create_uuid16_list(hdev, ptr, HCI_MAX_EIR_LENGTH - (ptr - data)); - ptr = create_uuid32_list(hdev, ptr, HCI_MAX_EIR_LENGTH - (ptr - data)); - ptr = create_uuid128_list(hdev, ptr, HCI_MAX_EIR_LENGTH - (ptr - data)); -} - -static void update_eir(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_write_eir cp; - - if (!hdev_is_powered(hdev)) - return; - - if (!lmp_ext_inq_capable(hdev)) - return; - - if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) - return; - - if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) - return; - - memset(&cp, 0, sizeof(cp)); - - create_eir(hdev, cp.data); - - if (memcmp(cp.data, hdev->eir, sizeof(cp.data)) == 0) - return; - - memcpy(hdev->eir, cp.data, sizeof(cp.data)); - - hci_req_add(req, HCI_OP_WRITE_EIR, sizeof(cp), &cp); -} - -static u8 get_service_classes(struct hci_dev *hdev) -{ - struct bt_uuid *uuid; - u8 val = 0; - - list_for_each_entry(uuid, &hdev->uuids, list) - val |= uuid->svc_hint; - - return val; -} - -static void update_class(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - u8 cod[3]; - - BT_DBG("%s", hdev->name); - - if (!hdev_is_powered(hdev)) - return; - - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) - return; - - if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) - return; - - cod[0] = hdev->minor_class; - cod[1] = hdev->major_class; - cod[2] = get_service_classes(hdev); - - if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) - cod[1] |= 0x20; - - if (memcmp(cod, hdev->dev_class, 3) == 0) - return; - - hci_req_add(req, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod); -} - -static void disable_advertising(struct hci_request *req) -{ - u8 enable = 0x00; - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - -static void enable_advertising(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_param cp; - u8 own_addr_type, enable = 0x01; - bool connectable; - u8 instance; - u32 flags; - - if (hci_conn_num(hdev, LE_LINK) > 0) - return; - - if (hci_dev_test_flag(hdev, HCI_LE_ADV)) - disable_advertising(req); - - /* Clear the HCI_LE_ADV bit temporarily so that the - * hci_update_random_address knows that it's safe to go ahead - * and write a new random address. The flag will be set back on - * as soon as the SET_ADV_ENABLE HCI command completes. - */ - hci_dev_clear_flag(hdev, HCI_LE_ADV); - - instance = get_current_adv_instance(hdev); - flags = get_adv_instance_flags(hdev, instance); - - /* If the "connectable" instance flag was not set, then choose between - * ADV_IND and ADV_NONCONN_IND based on the global connectable setting. - */ - connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) || - get_connectable(hdev); - - /* Set require_privacy to true only when non-connectable - * advertising is used. In that case it is fine to use a - * non-resolvable private address. - */ - if (hci_update_random_address(req, !connectable, &own_addr_type) < 0) - return; - - memset(&cp, 0, sizeof(cp)); - cp.min_interval = cpu_to_le16(hdev->le_adv_min_interval); - cp.max_interval = cpu_to_le16(hdev->le_adv_max_interval); - - if (connectable) - cp.type = LE_ADV_IND; - else if (get_cur_adv_instance_scan_rsp_len(hdev)) - cp.type = LE_ADV_SCAN_IND; - else - cp.type = LE_ADV_NONCONN_IND; - - cp.own_address_type = own_addr_type; - cp.channel_map = hdev->le_adv_channel_map; - - hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - static void service_cache_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -1324,8 +785,8 @@ static void service_cache_off(struct work_struct *work) hci_dev_lock(hdev); - update_eir(&req); - update_class(&req); + __hci_req_update_eir(&req); + __hci_req_update_class(&req); hci_dev_unlock(hdev); @@ -1346,10 +807,11 @@ static void rpa_expired(struct work_struct *work) return; /* The generation of a new RPA and programming it into the - * controller happens in the enable_advertising() function. + * controller happens in the hci_req_enable_advertising() + * function. */ hci_req_init(&req, hdev); - enable_advertising(&req); + __hci_req_enable_advertising(&req); hci_req_run(&req, NULL); } @@ -1417,8 +879,7 @@ static void clean_up_hci_complete(struct hci_dev *hdev, u8 status, u16 opcode) } } -static void advertising_added(struct sock *sk, struct hci_dev *hdev, - u8 instance) +void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance) { struct mgmt_ev_advertising_added ev; @@ -1427,8 +888,8 @@ static void advertising_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_ADVERTISING_ADDED, hdev, &ev, sizeof(ev), sk); } -static void advertising_removed(struct sock *sk, struct hci_dev *hdev, - u8 instance) +void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, + u8 instance) { struct mgmt_ev_advertising_removed ev; @@ -1437,65 +898,6 @@ static void advertising_removed(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_ADVERTISING_REMOVED, hdev, &ev, sizeof(ev), sk); } -static int schedule_adv_instance(struct hci_request *req, u8 instance, - bool force) { - struct hci_dev *hdev = req->hdev; - struct adv_info *adv_instance = NULL; - u16 timeout; - - if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || - !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) - return -EPERM; - - if (hdev->adv_instance_timeout) - return -EBUSY; - - adv_instance = hci_find_adv_instance(hdev, instance); - if (!adv_instance) - return -ENOENT; - - /* A zero timeout means unlimited advertising. As long as there is - * only one instance, duration should be ignored. We still set a timeout - * in case further instances are being added later on. - * - * If the remaining lifetime of the instance is more than the duration - * then the timeout corresponds to the duration, otherwise it will be - * reduced to the remaining instance lifetime. - */ - if (adv_instance->timeout == 0 || - adv_instance->duration <= adv_instance->remaining_time) - timeout = adv_instance->duration; - else - timeout = adv_instance->remaining_time; - - /* The remaining time is being reduced unless the instance is being - * advertised without time limit. - */ - if (adv_instance->timeout) - adv_instance->remaining_time = - adv_instance->remaining_time - timeout; - - hdev->adv_instance_timeout = timeout; - queue_delayed_work(hdev->workqueue, - &hdev->adv_instance_expire, - msecs_to_jiffies(timeout * 1000)); - - /* If we're just re-scheduling the same instance again then do not - * execute any HCI commands. This happens when a single instance is - * being advertised. - */ - if (!force && hdev->cur_adv_instance == instance && - hci_dev_test_flag(hdev, HCI_LE_ADV)) - return 0; - - hdev->cur_adv_instance = instance; - update_adv_data(req); - update_scan_rsp_data(req); - enable_advertising(req); - - return 0; -} - static void cancel_adv_timeout(struct hci_dev *hdev) { if (hdev->adv_instance_timeout) { @@ -1504,76 +906,6 @@ static void cancel_adv_timeout(struct hci_dev *hdev) } } -/* For a single instance: - * - force == true: The instance will be removed even when its remaining - * lifetime is not zero. - * - force == false: the instance will be deactivated but kept stored unless - * the remaining lifetime is zero. - * - * For instance == 0x00: - * - force == true: All instances will be removed regardless of their timeout - * setting. - * - force == false: Only instances that have a timeout will be removed. - */ -static void clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, - u8 instance, bool force) -{ - struct adv_info *adv_instance, *n, *next_instance = NULL; - int err; - u8 rem_inst; - - /* Cancel any timeout concerning the removed instance(s). */ - if (!instance || hdev->cur_adv_instance == instance) - cancel_adv_timeout(hdev); - - /* Get the next instance to advertise BEFORE we remove - * the current one. This can be the same instance again - * if there is only one instance. - */ - if (instance && hdev->cur_adv_instance == instance) - next_instance = hci_get_next_instance(hdev, instance); - - if (instance == 0x00) { - list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, - list) { - if (!(force || adv_instance->timeout)) - continue; - - rem_inst = adv_instance->instance; - err = hci_remove_adv_instance(hdev, rem_inst); - if (!err) - advertising_removed(NULL, hdev, rem_inst); - } - hdev->cur_adv_instance = 0x00; - } else { - adv_instance = hci_find_adv_instance(hdev, instance); - - if (force || (adv_instance && adv_instance->timeout && - !adv_instance->remaining_time)) { - /* Don't advertise a removed instance. */ - if (next_instance && - next_instance->instance == instance) - next_instance = NULL; - - err = hci_remove_adv_instance(hdev, instance); - if (!err) - advertising_removed(NULL, hdev, instance); - } - } - - if (list_empty(&hdev->adv_instances)) { - hdev->cur_adv_instance = 0x00; - hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE); - } - - if (!req || !hdev_is_powered(hdev) || - hci_dev_test_flag(hdev, HCI_ADVERTISING)) - return; - - if (next_instance) - schedule_adv_instance(req, next_instance->instance, false); -} - static int clean_up_hci_state(struct hci_dev *hdev) { struct hci_request req; @@ -1589,10 +921,10 @@ static int clean_up_hci_state(struct hci_dev *hdev) hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } - clear_adv_instance(hdev, NULL, 0x00, false); + hci_req_clear_adv_instance(hdev, NULL, 0x00, false); if (hci_dev_test_flag(hdev, HCI_LE_ADV)) - disable_advertising(&req); + __hci_req_disable_advertising(&req); discov_stopped = hci_req_stop_discovery(&req); @@ -1629,17 +961,6 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { - cancel_delayed_work(&hdev->power_off); - - if (cp->val) { - mgmt_pending_add(sk, MGMT_OP_SET_POWERED, hdev, - data, len); - err = mgmt_powered(hdev, 1); - goto failed; - } - } - if (!!cp->val == hdev_is_powered(hdev)) { err = send_settings_rsp(sk, MGMT_OP_SET_POWERED, hdev); goto failed; @@ -1763,13 +1084,9 @@ static u8 mgmt_le_support(struct hci_dev *hdev) return MGMT_STATUS_SUCCESS; } -static void set_discoverable_complete(struct hci_dev *hdev, u8 status, - u16 opcode) +void mgmt_set_discoverable_complete(struct hci_dev *hdev, u8 status) { struct mgmt_pending_cmd *cmd; - struct mgmt_mode *cp; - struct hci_request req; - bool changed; BT_DBG("status 0x%02x", status); @@ -1786,33 +1103,14 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status, goto remove_cmd; } - cp = cmd->param; - if (cp->val) { - changed = !hci_dev_test_and_set_flag(hdev, HCI_DISCOVERABLE); - - if (hdev->discov_timeout > 0) { - int to = msecs_to_jiffies(hdev->discov_timeout * 1000); - queue_delayed_work(hdev->workqueue, &hdev->discov_off, - to); - } - } else { - changed = hci_dev_test_and_clear_flag(hdev, HCI_DISCOVERABLE); + if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE) && + hdev->discov_timeout > 0) { + int to = msecs_to_jiffies(hdev->discov_timeout * 1000); + queue_delayed_work(hdev->req_workqueue, &hdev->discov_off, to); } send_settings_rsp(cmd->sk, MGMT_OP_SET_DISCOVERABLE, hdev); - - if (changed) - new_settings(hdev, cmd->sk); - - /* When the discoverable mode gets changed, make sure - * that class of device has the limited discoverable - * bit correctly set. Also update page scan based on whitelist - * entries. - */ - hci_req_init(&req, hdev); - __hci_update_page_scan(&req); - update_class(&req); - hci_req_run(&req, NULL); + new_settings(hdev, cmd->sk); remove_cmd: mgmt_pending_remove(cmd); @@ -1826,9 +1124,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, { struct mgmt_cp_set_discoverable *cp = data; struct mgmt_pending_cmd *cmd; - struct hci_request req; u16 timeout; - u8 scan; int err; BT_DBG("request for %s", hdev->name); @@ -1907,8 +1203,8 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->val && hdev->discov_timeout > 0) { int to = msecs_to_jiffies(hdev->discov_timeout * 1000); - queue_delayed_work(hdev->workqueue, &hdev->discov_off, - to); + queue_delayed_work(hdev->req_workqueue, + &hdev->discov_off, to); } err = send_settings_rsp(sk, MGMT_OP_SET_DISCOVERABLE, hdev); @@ -1928,105 +1224,28 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, cancel_delayed_work(&hdev->discov_off); hdev->discov_timeout = timeout; + if (cp->val) + hci_dev_set_flag(hdev, HCI_DISCOVERABLE); + else + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); + /* Limited discoverable mode */ if (cp->val == 0x02) hci_dev_set_flag(hdev, HCI_LIMITED_DISCOVERABLE); else hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); - hci_req_init(&req, hdev); - - /* The procedure for LE-only controllers is much simpler - just - * update the advertising data. - */ - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) - goto update_ad; - - scan = SCAN_PAGE; - - if (cp->val) { - struct hci_cp_write_current_iac_lap hci_cp; - - if (cp->val == 0x02) { - /* Limited discoverable mode */ - hci_cp.num_iac = min_t(u8, hdev->num_iac, 2); - hci_cp.iac_lap[0] = 0x00; /* LIAC */ - hci_cp.iac_lap[1] = 0x8b; - hci_cp.iac_lap[2] = 0x9e; - hci_cp.iac_lap[3] = 0x33; /* GIAC */ - hci_cp.iac_lap[4] = 0x8b; - hci_cp.iac_lap[5] = 0x9e; - } else { - /* General discoverable mode */ - hci_cp.num_iac = 1; - hci_cp.iac_lap[0] = 0x33; /* GIAC */ - hci_cp.iac_lap[1] = 0x8b; - hci_cp.iac_lap[2] = 0x9e; - } - - hci_req_add(&req, HCI_OP_WRITE_CURRENT_IAC_LAP, - (hci_cp.num_iac * 3) + 1, &hci_cp); - - scan |= SCAN_INQUIRY; - } else { - hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); - } - - hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, sizeof(scan), &scan); - -update_ad: - update_adv_data(&req); - - err = hci_req_run(&req, set_discoverable_complete); - if (err < 0) - mgmt_pending_remove(cmd); + queue_work(hdev->req_workqueue, &hdev->discoverable_update); + err = 0; failed: hci_dev_unlock(hdev); return err; } -static void write_fast_connectable(struct hci_request *req, bool enable) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_write_page_scan_activity acp; - u8 type; - - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) - return; - - if (hdev->hci_ver < BLUETOOTH_VER_1_2) - return; - - if (enable) { - type = PAGE_SCAN_TYPE_INTERLACED; - - /* 160 msec page scan interval */ - acp.interval = cpu_to_le16(0x0100); - } else { - type = PAGE_SCAN_TYPE_STANDARD; /* default */ - - /* default 1.28 sec page scan */ - acp.interval = cpu_to_le16(0x0800); - } - - acp.window = cpu_to_le16(0x0012); - - if (__cpu_to_le16(hdev->page_scan_interval) != acp.interval || - __cpu_to_le16(hdev->page_scan_window) != acp.window) - hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_ACTIVITY, - sizeof(acp), &acp); - - if (hdev->page_scan_type != type) - hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type); -} - -static void set_connectable_complete(struct hci_dev *hdev, u8 status, - u16 opcode) +void mgmt_set_connectable_complete(struct hci_dev *hdev, u8 status) { struct mgmt_pending_cmd *cmd; - struct mgmt_mode *cp; - bool conn_changed, discov_changed; BT_DBG("status 0x%02x", status); @@ -2042,27 +1261,8 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status, goto remove_cmd; } - cp = cmd->param; - if (cp->val) { - conn_changed = !hci_dev_test_and_set_flag(hdev, - HCI_CONNECTABLE); - discov_changed = false; - } else { - conn_changed = hci_dev_test_and_clear_flag(hdev, - HCI_CONNECTABLE); - discov_changed = hci_dev_test_and_clear_flag(hdev, - HCI_DISCOVERABLE); - } - send_settings_rsp(cmd->sk, MGMT_OP_SET_CONNECTABLE, hdev); - - if (conn_changed || discov_changed) { - new_settings(hdev, cmd->sk); - hci_update_page_scan(hdev); - if (discov_changed) - mgmt_update_adv_data(hdev); - hci_update_background_scan(hdev); - } + new_settings(hdev, cmd->sk); remove_cmd: mgmt_pending_remove(cmd); @@ -2092,7 +1292,7 @@ static int set_connectable_update_settings(struct hci_dev *hdev, return err; if (changed) { - hci_update_page_scan(hdev); + hci_req_update_scan(hdev); hci_update_background_scan(hdev); return new_settings(hdev, sk); } @@ -2105,8 +1305,6 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, { struct mgmt_mode *cp = data; struct mgmt_pending_cmd *cmd; - struct hci_request req; - u8 scan; int err; BT_DBG("request for %s", hdev->name); @@ -2140,57 +1338,19 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - hci_req_init(&req, hdev); - - /* If BR/EDR is not enabled and we disable advertising as a - * by-product of disabling connectable, we need to update the - * advertising flags. - */ - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { - if (!cp->val) { - hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); - hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); - } - update_adv_data(&req); - } else if (cp->val != test_bit(HCI_PSCAN, &hdev->flags)) { - if (cp->val) { - scan = SCAN_PAGE; - } else { - /* If we don't have any whitelist entries just - * disable all scanning. If there are entries - * and we had both page and inquiry scanning - * enabled then fall back to only page scanning. - * Otherwise no changes are needed. - */ - if (list_empty(&hdev->whitelist)) - scan = SCAN_DISABLED; - else if (test_bit(HCI_ISCAN, &hdev->flags)) - scan = SCAN_PAGE; - else - goto no_scan_update; - - if (test_bit(HCI_ISCAN, &hdev->flags) && - hdev->discov_timeout > 0) - cancel_delayed_work(&hdev->discov_off); - } + if (cp->val) { + hci_dev_set_flag(hdev, HCI_CONNECTABLE); + } else { + if (hdev->discov_timeout > 0) + cancel_delayed_work(&hdev->discov_off); - hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_CONNECTABLE); } -no_scan_update: - /* Update the advertising parameters if necessary */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || - hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) - enable_advertising(&req); - - err = hci_req_run(&req, set_connectable_complete); - if (err < 0) { - mgmt_pending_remove(cmd); - if (err == -ENODATA) - err = set_connectable_update_settings(hdev, sk, - cp->val); - goto failed; - } + queue_work(hdev->req_workqueue, &hdev->connectable_update); + err = 0; failed: hci_dev_unlock(hdev); @@ -2466,8 +1626,8 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) struct hci_request req; hci_req_init(&req, hdev); - update_adv_data(&req); - update_scan_rsp_data(&req); + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); hci_req_run(&req, NULL); hci_update_background_scan(hdev); } @@ -2518,7 +1678,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) enabled = lmp_host_le_capable(hdev); if (!val) - clear_adv_instance(hdev, NULL, 0x00, true); + hci_req_clear_adv_instance(hdev, NULL, 0x00, true); if (!hdev_is_powered(hdev) || val == enabled) { bool changed = false; @@ -2565,7 +1725,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_cp.simul = 0x00; } else { if (hci_dev_test_flag(hdev, HCI_LE_ADV)) - disable_advertising(&req); + __hci_req_disable_advertising(&req); } hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp), @@ -2680,8 +1840,8 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_req_init(&req, hdev); - update_class(&req); - update_eir(&req); + __hci_req_update_class(&req); + __hci_req_update_eir(&req); err = hci_req_run(&req, add_uuid_complete); if (err < 0) { @@ -2780,8 +1940,8 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, update_class: hci_req_init(&req, hdev); - update_class(&req); - update_eir(&req); + __hci_req_update_class(&req); + __hci_req_update_eir(&req); err = hci_req_run(&req, remove_uuid_complete); if (err < 0) { @@ -2856,10 +2016,10 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_unlock(hdev); cancel_delayed_work_sync(&hdev->service_cache); hci_dev_lock(hdev); - update_eir(&req); + __hci_req_update_eir(&req); } - update_class(&req); + __hci_req_update_class(&req); err = hci_req_run(&req, set_class_complete); if (err < 0) { @@ -3760,16 +2920,6 @@ static int user_passkey_neg_reply(struct sock *sk, struct hci_dev *hdev, HCI_OP_USER_PASSKEY_NEG_REPLY, 0); } -static void update_name(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_write_local_name cp; - - memcpy(cp.name, hdev->dev_name, sizeof(cp.name)); - - hci_req_add(req, HCI_OP_WRITE_LOCAL_NAME, sizeof(cp), &cp); -} - static void set_name_complete(struct hci_dev *hdev, u8 status, u16 opcode) { struct mgmt_cp_set_local_name *cp; @@ -3848,15 +2998,15 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, hci_req_init(&req, hdev); if (lmp_bredr_capable(hdev)) { - update_name(&req); - update_eir(&req); + __hci_req_update_name(&req); + __hci_req_update_eir(&req); } /* The name is stored in the scan response data and so * no need to udpate the advertising data here. */ if (lmp_le_capable(hdev)) - update_scan_rsp_data(&req); + __hci_req_update_scan_rsp_data(&req, hdev->cur_adv_instance); err = hci_req_run(&req, set_name_complete); if (err < 0) @@ -4534,7 +3684,7 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data, NULL, 0); hci_req_init(&req, hdev); - update_eir(&req); + __hci_req_update_eir(&req); hci_req_run(&req, NULL); hci_dev_unlock(hdev); @@ -4584,7 +3734,6 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status, * set up earlier, then re-enable multi-instance advertising. */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || - !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) || list_empty(&hdev->adv_instances)) goto unlock; @@ -4600,7 +3749,7 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status, hci_req_init(&req, hdev); - err = schedule_adv_instance(&req, instance, true); + err = __hci_req_schedule_adv_instance(&req, instance, true); if (!err) err = hci_req_run(&req, enable_advertising_instance); @@ -4650,6 +3799,7 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, bool changed; if (cp->val) { + hdev->cur_adv_instance = 0x00; changed = !hci_dev_test_and_set_flag(hdev, HCI_ADVERTISING); if (cp->val == 0x02) hci_dev_set_flag(hdev, HCI_ADVERTISING_CONNECTABLE); @@ -4697,11 +3847,12 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, * We cannot use update_[adv|scan_rsp]_data() here as the * HCI_ADVERTISING flag is not yet set. */ - update_inst_adv_data(&req, 0x00); - update_inst_scan_rsp_data(&req, 0x00); - enable_advertising(&req); + hdev->cur_adv_instance = 0x00; + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + __hci_req_enable_advertising(&req); } else { - disable_advertising(&req); + __hci_req_disable_advertising(&req); } err = hci_req_run(&req, set_advertising_complete); @@ -4898,7 +4049,7 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); - write_fast_connectable(&req, cp->val); + __hci_req_write_fast_connectable(&req, cp->val); err = hci_req_run(&req, fast_connectable_complete); if (err < 0) { @@ -5033,20 +4184,20 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto unlock; } - /* We need to flip the bit already here so that update_adv_data - * generates the correct flags. + /* We need to flip the bit already here so that + * hci_req_update_adv_data generates the correct flags. */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); hci_req_init(&req, hdev); - write_fast_connectable(&req, false); - __hci_update_page_scan(&req); + __hci_req_write_fast_connectable(&req, false); + __hci_req_update_scan(&req); /* Since only the advertising data flags will change, there * is no need to update the scan response data. */ - update_adv_data(&req); + __hci_req_update_adv_data(&req, hdev->cur_adv_instance); err = hci_req_run(&req, set_bredr_complete); if (err < 0) @@ -5927,7 +5078,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, if (err) goto unlock; - hci_update_page_scan(hdev); + hci_req_update_scan(hdev); goto added; } @@ -6024,7 +5175,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - hci_update_page_scan(hdev); + hci_req_update_scan(hdev); device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); @@ -6089,7 +5240,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, kfree(b); } - hci_update_page_scan(hdev); + hci_req_update_scan(hdev); list_for_each_entry_safe(p, tmp, &hdev->le_conn_params, list) { if (p->auto_connect == HCI_AUTO_CONN_DISABLED) @@ -6583,7 +5734,7 @@ static int read_local_oob_ext_data(struct sock *sk, struct hci_dev *hdev, rand, sizeof(rand)); } - flags = get_adv_discov_flags(hdev); + flags = mgmt_get_adv_discov_flags(hdev); if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) flags |= LE_AD_NO_BREDR; @@ -6638,10 +5789,10 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, { struct mgmt_rp_read_adv_features *rp; size_t rp_len; - int err, i; - bool instance; + int err; struct adv_info *adv_instance; u32 supported_flags; + u8 *instance; BT_DBG("%s", hdev->name); @@ -6651,12 +5802,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); - rp_len = sizeof(*rp); - - instance = hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE); - if (instance) - rp_len += hdev->adv_instance_cnt; - + rp_len = sizeof(*rp) + hdev->adv_instance_cnt; rp = kmalloc(rp_len, GFP_ATOMIC); if (!rp) { hci_dev_unlock(hdev); @@ -6669,19 +5815,12 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, rp->max_adv_data_len = HCI_MAX_AD_LENGTH; rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH; rp->max_instances = HCI_MAX_ADV_INSTANCES; + rp->num_instances = hdev->adv_instance_cnt; - if (instance) { - i = 0; - list_for_each_entry(adv_instance, &hdev->adv_instances, list) { - if (i >= hdev->adv_instance_cnt) - break; - - rp->instance[i] = adv_instance->instance; - i++; - } - rp->num_instances = hdev->adv_instance_cnt; - } else { - rp->num_instances = 0; + instance = rp->instance; + list_for_each_entry(adv_instance, &hdev->adv_instances, list) { + *instance = adv_instance->instance; + instance++; } hci_dev_unlock(hdev); @@ -6754,9 +5893,6 @@ static void add_advertising_complete(struct hci_dev *hdev, u8 status, cmd = pending_find(MGMT_OP_ADD_ADVERTISING, hdev); - if (status) - hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE); - list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) { if (!adv_instance->pending) continue; @@ -6772,7 +5908,7 @@ static void add_advertising_complete(struct hci_dev *hdev, u8 status, cancel_adv_timeout(hdev); hci_remove_adv_instance(hdev, instance); - advertising_removed(cmd ? cmd->sk : NULL, hdev, instance); + mgmt_advertising_removed(cmd ? cmd->sk : NULL, hdev, instance); } if (!cmd) @@ -6794,31 +5930,6 @@ unlock: hci_dev_unlock(hdev); } -void mgmt_adv_timeout_expired(struct hci_dev *hdev) -{ - u8 instance; - struct hci_request req; - - hdev->adv_instance_timeout = 0; - - instance = get_current_adv_instance(hdev); - if (instance == 0x00) - return; - - hci_dev_lock(hdev); - hci_req_init(&req, hdev); - - clear_adv_instance(hdev, &req, instance, false); - - if (list_empty(&hdev->adv_instances)) - disable_advertising(&req); - - if (!skb_queue_empty(&req.cmd_q)) - hci_req_run(&req, NULL); - - hci_dev_unlock(hdev); -} - static int add_advertising(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { @@ -6897,9 +6008,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, * actually added. */ if (hdev->adv_instance_cnt > prev_instance_cnt) - advertising_added(sk, hdev, cp->instance); - - hci_dev_set_flag(hdev, HCI_ADVERTISING_INSTANCE); + mgmt_advertising_added(sk, hdev, cp->instance); if (hdev->cur_adv_instance == cp->instance) { /* If the currently advertised instance is being changed then @@ -6944,7 +6053,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); - err = schedule_adv_instance(&req, schedule_instance, true); + err = __hci_req_schedule_adv_instance(&req, schedule_instance, true); if (!err) err = hci_req_run(&req, add_advertising_complete); @@ -7016,7 +6125,7 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (!hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) { + if (list_empty(&hdev->adv_instances)) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); goto unlock; @@ -7024,10 +6133,10 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); - clear_adv_instance(hdev, &req, cp->instance, true); + hci_req_clear_adv_instance(hdev, &req, cp->instance, true); if (list_empty(&hdev->adv_instances)) - disable_advertising(&req); + __hci_req_disable_advertising(&req); /* If no HCI commands have been collected so far or the HCI_ADVERTISING * flag is set or the device isn't powered then we have no HCI @@ -7298,138 +6407,33 @@ static void restart_le_actions(struct hci_dev *hdev) } } -static void powered_complete(struct hci_dev *hdev, u8 status, u16 opcode) +void mgmt_power_on(struct hci_dev *hdev, int err) { struct cmd_lookup match = { NULL, hdev }; - BT_DBG("status 0x%02x", status); + BT_DBG("err %d", err); - if (!status) { + hci_dev_lock(hdev); + + if (!err) { restart_le_actions(hdev); hci_update_background_scan(hdev); } - hci_dev_lock(hdev); - mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); new_settings(hdev, match.sk); - hci_dev_unlock(hdev); - if (match.sk) sock_put(match.sk); -} - -static int powered_update_hci(struct hci_dev *hdev) -{ - struct hci_request req; - struct adv_info *adv_instance; - u8 link_sec; - - hci_req_init(&req, hdev); - - if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && - !lmp_host_ssp_capable(hdev)) { - u8 mode = 0x01; - - hci_req_add(&req, HCI_OP_WRITE_SSP_MODE, sizeof(mode), &mode); - - if (bredr_sc_enabled(hdev) && !lmp_host_sc_capable(hdev)) { - u8 support = 0x01; - - hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT, - sizeof(support), &support); - } - } - - if (hci_dev_test_flag(hdev, HCI_LE_ENABLED) && - lmp_bredr_capable(hdev)) { - struct hci_cp_write_le_host_supported cp; - - cp.le = 0x01; - cp.simul = 0x00; - /* Check first if we already have the right - * host state (host features set) - */ - if (cp.le != lmp_host_le_capable(hdev) || - cp.simul != lmp_host_le_br_capable(hdev)) - hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, - sizeof(cp), &cp); - } - - if (lmp_le_capable(hdev)) { - /* Make sure the controller has a good default for - * advertising data. This also applies to the case - * where BR/EDR was toggled during the AUTO_OFF phase. - */ - if (hci_dev_test_flag(hdev, HCI_LE_ENABLED) && - (hci_dev_test_flag(hdev, HCI_ADVERTISING) || - !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE))) { - update_adv_data(&req); - update_scan_rsp_data(&req); - } - - if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) && - hdev->cur_adv_instance == 0x00 && - !list_empty(&hdev->adv_instances)) { - adv_instance = list_first_entry(&hdev->adv_instances, - struct adv_info, list); - hdev->cur_adv_instance = adv_instance->instance; - } - - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) - enable_advertising(&req); - else if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) && - hdev->cur_adv_instance) - schedule_adv_instance(&req, hdev->cur_adv_instance, - true); - } - - link_sec = hci_dev_test_flag(hdev, HCI_LINK_SECURITY); - if (link_sec != test_bit(HCI_AUTH, &hdev->flags)) - hci_req_add(&req, HCI_OP_WRITE_AUTH_ENABLE, - sizeof(link_sec), &link_sec); - - if (lmp_bredr_capable(hdev)) { - if (hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE)) - write_fast_connectable(&req, true); - else - write_fast_connectable(&req, false); - __hci_update_page_scan(&req); - update_class(&req); - update_name(&req); - update_eir(&req); - } - - return hci_req_run(&req, powered_complete); + hci_dev_unlock(hdev); } -int mgmt_powered(struct hci_dev *hdev, u8 powered) +void __mgmt_power_off(struct hci_dev *hdev) { struct cmd_lookup match = { NULL, hdev }; u8 status, zero_cod[] = { 0, 0, 0 }; - int err; - - if (!hci_dev_test_flag(hdev, HCI_MGMT)) - return 0; - - if (powered) { - /* Register the available SMP channels (BR/EDR and LE) only - * when successfully powering on the controller. This late - * registration is required so that LE SMP can clearly - * decide if the public address or static address is used. - */ - smp_register(hdev); - - if (powered_update_hci(hdev) == 0) - return 0; - - mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, - &match); - goto new_settings; - } mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); @@ -7451,13 +6455,10 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, zero_cod, sizeof(zero_cod), NULL); -new_settings: - err = new_settings(hdev, match.sk); + new_settings(hdev, match.sk); if (match.sk) sock_put(match.sk); - - return err; } void mgmt_set_powered_failed(struct hci_dev *hdev, int err) @@ -7479,43 +6480,6 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err) mgmt_pending_remove(cmd); } -void mgmt_discoverable_timeout(struct hci_dev *hdev) -{ - struct hci_request req; - - hci_dev_lock(hdev); - - /* When discoverable timeout triggers, then just make sure - * the limited discoverable flag is cleared. Even in the case - * of a timeout triggered from general discoverable, it is - * safe to unconditionally clear the flag. - */ - hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); - hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); - - hci_req_init(&req, hdev); - if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { - u8 scan = SCAN_PAGE; - hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, - sizeof(scan), &scan); - } - update_class(&req); - - /* Advertising instances don't use the global discoverable setting, so - * only update AD if advertising was enabled using Set Advertising. - */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) - update_adv_data(&req); - - hci_req_run(&req, NULL); - - hdev->discov_timeout = 0; - - new_settings(hdev, NULL); - - hci_dev_unlock(hdev); -} - void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent) { @@ -8058,7 +7022,7 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) hci_req_add(&req, HCI_OP_WRITE_SSP_DEBUG_MODE, sizeof(enable), &enable); - update_eir(&req); + __hci_req_update_eir(&req); } else { clear_eir(&req); } @@ -8352,35 +7316,6 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering) mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL); } -static void adv_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) -{ - BT_DBG("%s status %u", hdev->name, status); -} - -void mgmt_reenable_advertising(struct hci_dev *hdev) -{ - struct hci_request req; - u8 instance; - - if (!hci_dev_test_flag(hdev, HCI_ADVERTISING) && - !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) - return; - - instance = get_current_adv_instance(hdev); - - hci_req_init(&req, hdev); - - if (instance) { - schedule_adv_instance(&req, instance, true); - } else { - update_adv_data(&req); - update_scan_rsp_data(&req); - enable_advertising(&req); - } - - hci_req_run(&req, adv_enable_complete); -} - static struct hci_mgmt_chan chan = { .channel = HCI_CHANNEL_CONTROL, .handler_count = ARRAY_SIZE(mgmt_handlers), diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 29709fbfd1f50..f7eb02f09b540 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -692,11 +692,9 @@ static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s) static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst) { - struct rfcomm_session *s; - struct list_head *p, *n; + struct rfcomm_session *s, *n; struct l2cap_chan *chan; - list_for_each_safe(p, n, &session_list) { - s = list_entry(p, struct rfcomm_session, list); + list_for_each_entry_safe(s, n, &session_list, list) { chan = l2cap_pi(s->sock->sk)->chan; if ((!bacmp(src, BDADDR_ANY) || !bacmp(&chan->src, src)) && @@ -709,16 +707,14 @@ static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst) static struct rfcomm_session *rfcomm_session_close(struct rfcomm_session *s, int err) { - struct rfcomm_dlc *d; - struct list_head *p, *n; + struct rfcomm_dlc *d, *n; s->state = BT_CLOSED; BT_DBG("session %p state %ld err %d", s, s->state, err); /* Close all dlcs */ - list_for_each_safe(p, n, &s->dlcs) { - d = list_entry(p, struct rfcomm_dlc, list); + list_for_each_entry_safe(d, n, &s->dlcs, list) { d->state = BT_CLOSED; __rfcomm_dlc_close(d, err); } @@ -1771,13 +1767,11 @@ static struct rfcomm_session *rfcomm_recv_frame(struct rfcomm_session *s, static void rfcomm_process_connect(struct rfcomm_session *s) { - struct rfcomm_dlc *d; - struct list_head *p, *n; + struct rfcomm_dlc *d, *n; BT_DBG("session %p state %ld", s, s->state); - list_for_each_safe(p, n, &s->dlcs) { - d = list_entry(p, struct rfcomm_dlc, list); + list_for_each_entry_safe(d, n, &s->dlcs, list) { if (d->state == BT_CONFIG) { d->mtu = s->mtu; if (rfcomm_check_security(d)) { @@ -1843,14 +1837,11 @@ static int rfcomm_process_tx(struct rfcomm_dlc *d) static void rfcomm_process_dlcs(struct rfcomm_session *s) { - struct rfcomm_dlc *d; - struct list_head *p, *n; + struct rfcomm_dlc *d, *n; BT_DBG("session %p state %ld", s, s->state); - list_for_each_safe(p, n, &s->dlcs) { - d = list_entry(p, struct rfcomm_dlc, list); - + list_for_each_entry_safe(d, n, &s->dlcs, list) { if (test_bit(RFCOMM_TIMED_OUT, &d->flags)) { __rfcomm_dlc_close(d, ETIMEDOUT); continue; @@ -1985,14 +1976,11 @@ static struct rfcomm_session *rfcomm_check_connection(struct rfcomm_session *s) static void rfcomm_process_sessions(void) { - struct list_head *p, *n; + struct rfcomm_session *s, *n; rfcomm_lock(); - list_for_each_safe(p, n, &session_list) { - struct rfcomm_session *s; - s = list_entry(p, struct rfcomm_session, list); - + list_for_each_entry_safe(s, n, &session_list, list) { if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); @@ -2075,15 +2063,12 @@ failed: static void rfcomm_kill_listener(void) { - struct rfcomm_session *s; - struct list_head *p, *n; + struct rfcomm_session *s, *n; BT_DBG(""); - list_for_each_safe(p, n, &session_list) { - s = list_entry(p, struct rfcomm_session, list); + list_for_each_entry_safe(s, n, &session_list, list) rfcomm_session_del(s); - } } static int rfcomm_run(void *unused) @@ -2113,8 +2098,7 @@ static int rfcomm_run(void *unused) static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) { struct rfcomm_session *s; - struct rfcomm_dlc *d; - struct list_head *p, *n; + struct rfcomm_dlc *d, *n; BT_DBG("conn %p status 0x%02x encrypt 0x%02x", conn, status, encrypt); @@ -2122,9 +2106,7 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) if (!s) return; - list_for_each_safe(p, n, &s->dlcs) { - d = list_entry(p, struct rfcomm_dlc, list); - + list_for_each_entry_safe(d, n, &s->dlcs, list) { if (test_and_clear_bit(RFCOMM_SEC_PENDING, &d->flags)) { rfcomm_dlc_clear_timer(d); if (status || encrypt == 0x00) { diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index fe129663bd3f7..f52bcbf2e58cd 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -526,6 +526,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_BLUETOOTH) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_sco)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != BT_OPEN) { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index a642bb829d09c..82e3e97050173 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -135,6 +135,7 @@ static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) { struct switchdev_obj_port_fdb fdb = { .obj = { + .orig_dev = f->dst->dev, .id = SWITCHDEV_OBJ_ID_PORT_FDB, .flags = SWITCHDEV_F_DEFER, }, diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 5f3f645531792..b3cca126b103d 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -40,6 +40,7 @@ void br_log_state(const struct net_bridge_port *p) void br_set_state(struct net_bridge_port *p, unsigned int state) { struct switchdev_attr attr = { + .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, .flags = SWITCHDEV_F_DEFER, .u.stp_state = state, @@ -570,6 +571,7 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) { struct switchdev_attr attr = { + .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.ageing_time = ageing_time, diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 5396ff08af321..905cedd37a053 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -37,9 +37,10 @@ static inline port_id br_make_port_id(__u8 priority, __u16 port_no) void br_init_port(struct net_bridge_port *p) { struct switchdev_attr attr = { + .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP | SWITCHDEV_F_DEFER, - .u.ageing_time = p->br->ageing_time, + .u.ageing_time = jiffies_to_clock_t(p->br->ageing_time), }; int err; diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 8365bd53c4217..6b8091407ca31 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -22,7 +22,6 @@ #include "br_private.h" -#define to_dev(obj) container_of(obj, struct device, kobj) #define to_bridge(cd) ((struct net_bridge *)netdev_priv(to_net_dev(cd))) /* @@ -814,7 +813,7 @@ static ssize_t brforward_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { - struct device *dev = to_dev(kobj); + struct device *dev = kobj_to_dev(kobj); struct net_bridge *br = to_bridge(dev); int n; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 1394da63614a1..66c4549efbbb3 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -73,6 +73,7 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, u16 vid, u16 flags) { struct switchdev_obj_port_vlan v = { + .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = flags, .vid_begin = vid, @@ -120,6 +121,7 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, u16 vid) { struct switchdev_obj_port_vlan v = { + .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid_begin = vid, .vid_end = vid, diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c index 17fd5f2cb4b89..98de6e7fd86d5 100644 --- a/net/bridge/netfilter/ebt_ip6.c +++ b/net/bridge/netfilter/ebt_ip6.c @@ -65,8 +65,8 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO)) return false; - if (!(info->bitmask & ( EBT_IP6_DPORT | - EBT_IP6_SPORT | EBT_IP6_ICMP6))) + if (!(info->bitmask & (EBT_IP6_DPORT | + EBT_IP6_SPORT | EBT_IP6_ICMP6))) return true; /* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */ diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 0ad639a961426..152300d164acd 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -36,14 +36,12 @@ static int ebt_log_tg_check(const struct xt_tgchk_param *par) return 0; } -struct tcpudphdr -{ +struct tcpudphdr { __be16 src; __be16 dst; }; -struct arppayload -{ +struct arppayload { unsigned char mac_src[ETH_ALEN]; unsigned char ip_src[4]; unsigned char mac_dst[ETH_ALEN]; @@ -152,7 +150,8 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ntohs(ah->ar_op)); /* If it's for Ethernet and the lengths are OK, - * then log the ARP payload */ + * then log the ARP payload + */ if (ah->ar_hrd == htons(1) && ah->ar_hln == ETH_ALEN && ah->ar_pln == sizeof(__be32)) { diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 0c40570069ba2..6b731e12ecfa2 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -41,7 +41,7 @@ struct stp_config_pdu { #define NR32(p) ((p[0] << 24) | (p[1] << 16) | (p[2] << 8) | p[3]) static bool ebt_filter_config(const struct ebt_stp_info *info, - const struct stp_config_pdu *stpc) + const struct stp_config_pdu *stpc) { const struct ebt_stp_config_info *c; uint16_t v16; diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c index 6185688881285..98c221dbf0596 100644 --- a/net/bridge/netfilter/ebt_vlan.c +++ b/net/bridge/netfilter/ebt_vlan.c @@ -66,7 +66,8 @@ ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par) * - Canonical Format Indicator (CFI). The Canonical Format Indicator * (CFI) is a single bit flag value. Currently ignored. * - VLAN Identifier (VID). The VID is encoded as - * an unsigned binary number. */ + * an unsigned binary number. + */ id = TCI & VLAN_VID_MASK; prio = (TCI >> 13) & 0x7; @@ -98,7 +99,8 @@ static int ebt_vlan_mt_check(const struct xt_mtchk_param *par) } /* Check for bitmask range - * True if even one bit is out of mask */ + * True if even one bit is out of mask + */ if (info->bitmask & ~EBT_VLAN_MASK) { pr_debug("bitmask %2X is out of mask (%2X)\n", info->bitmask, EBT_VLAN_MASK); @@ -117,7 +119,8 @@ static int ebt_vlan_mt_check(const struct xt_mtchk_param *par) * 0 - The null VLAN ID. * 1 - The default Port VID (PVID) * 0x0FFF - Reserved for implementation use. - * if_vlan.h: VLAN_N_VID 4096. */ + * if_vlan.h: VLAN_N_VID 4096. + */ if (GET_BITMASK(EBT_VLAN_ID)) { if (!!info->id) { /* if id!=0 => check vid range */ if (info->id > VLAN_N_VID) { @@ -128,7 +131,8 @@ static int ebt_vlan_mt_check(const struct xt_mtchk_param *par) /* Note: This is valid VLAN-tagged frame point. * Any value of user_priority are acceptable, * but should be ignored according to 802.1Q Std. - * So we just drop the prio flag. */ + * So we just drop the prio flag. + */ info->bitmask &= ~EBT_VLAN_PRIO; } /* Else, id=0 (null VLAN ID) => user_priority range (any?) */ @@ -143,7 +147,8 @@ static int ebt_vlan_mt_check(const struct xt_mtchk_param *par) } /* Check for encapsulated proto range - it is possible to be * any value for u_short range. - * if_ether.h: ETH_ZLEN 60 - Min. octets in frame sans FCS */ + * if_ether.h: ETH_ZLEN 60 - Min. octets in frame sans FCS + */ if (GET_BITMASK(EBT_VLAN_ENCAP)) { if ((unsigned short) ntohs(info->encap) < ETH_ZLEN) { pr_debug("encap frame length %d is less than " diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 32eccd101f268..593a1bdc079e8 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -12,7 +12,7 @@ #include <linux/module.h> #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \ - (1 << NF_BR_LOCAL_OUT)) + (1 << NF_BR_LOCAL_OUT)) static struct ebt_entries initial_chains[] = { { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index ec55358f00c8a..eb33919821ee1 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -12,7 +12,7 @@ #include <linux/module.h> #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ - (1 << NF_BR_POST_ROUTING)) + (1 << NF_BR_POST_ROUTING)) static struct ebt_entries initial_chains[] = { { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f46ca417bf2d1..67b2e27999aa2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -35,8 +35,7 @@ "report to author: "format, ## args) /* #define BUGPRINT(format, args...) */ -/* - * Each cpu has its own set of counters, so there is no need for write_lock in +/* Each cpu has its own set of counters, so there is no need for write_lock in * the softirq * For reading or updating the counters, the user context needs to * get a write_lock @@ -46,7 +45,7 @@ #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) #define COUNTER_OFFSET(n) (SMP_ALIGN(n * sizeof(struct ebt_counter))) #define COUNTER_BASE(c, n, cpu) ((struct ebt_counter *)(((char *)c) + \ - COUNTER_OFFSET(n) * cpu)) + COUNTER_OFFSET(n) * cpu)) @@ -126,7 +125,7 @@ ebt_dev_check(const char *entry, const struct net_device *device) /* process standard matches */ static inline int ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, - const struct net_device *in, const struct net_device *out) + const struct net_device *in, const struct net_device *out) { const struct ethhdr *h = eth_hdr(skb); const struct net_bridge_port *p; @@ -162,7 +161,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, for (i = 0; i < 6; i++) verdict |= (h->h_source[i] ^ e->sourcemac[i]) & e->sourcemsk[i]; - if (FWINV2(verdict != 0, EBT_ISOURCE) ) + if (FWINV2(verdict != 0, EBT_ISOURCE)) return 1; } if (e->bitmask & EBT_DESTMAC) { @@ -170,7 +169,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, for (i = 0; i < 6; i++) verdict |= (h->h_dest[i] ^ e->destmac[i]) & e->destmsk[i]; - if (FWINV2(verdict != 0, EBT_IDEST) ) + if (FWINV2(verdict != 0, EBT_IDEST)) return 1; } return 0; @@ -237,7 +236,8 @@ unsigned int ebt_do_table(struct sk_buff *skb, (*(counter_base + i)).bcnt += skb->len; /* these should only watch: not modify, nor tell us - what to do with the packet */ + * what to do with the packet + */ EBT_WATCHER_ITERATE(point, ebt_do_watcher, skb, &acpar); t = (struct ebt_entry_target *) @@ -323,7 +323,7 @@ letscontinue: /* If it succeeds, returns element and locks mutex */ static inline void * find_inlist_lock_noload(struct list_head *head, const char *name, int *error, - struct mutex *mutex) + struct mutex *mutex) { struct { struct list_head list; @@ -342,7 +342,7 @@ find_inlist_lock_noload(struct list_head *head, const char *name, int *error, static void * find_inlist_lock(struct list_head *head, const char *name, const char *prefix, - int *error, struct mutex *mutex) + int *error, struct mutex *mutex) { return try_then_request_module( find_inlist_lock_noload(head, name, error, mutex), @@ -451,7 +451,8 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, if (i != NF_BR_NUMHOOKS || !(e->bitmask & EBT_ENTRY_OR_ENTRIES)) { if (e->bitmask != 0) { /* we make userspace set this right, - so there is no misunderstanding */ + * so there is no misunderstanding + */ BUGPRINT("EBT_ENTRY_OR_ENTRIES shouldn't be set " "in distinguisher\n"); return -EINVAL; @@ -487,15 +488,14 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, return 0; } -/* - * this one is very careful, as it is the first function +/* this one is very careful, as it is the first function * to parse the userspace data */ static inline int ebt_check_entry_size_and_hooks(const struct ebt_entry *e, - const struct ebt_table_info *newinfo, - unsigned int *n, unsigned int *cnt, - unsigned int *totalcnt, unsigned int *udc_cnt) + const struct ebt_table_info *newinfo, + unsigned int *n, unsigned int *cnt, + unsigned int *totalcnt, unsigned int *udc_cnt) { int i; @@ -504,10 +504,12 @@ ebt_check_entry_size_and_hooks(const struct ebt_entry *e, break; } /* beginning of a new chain - if i == NF_BR_NUMHOOKS it must be a user defined chain */ + * if i == NF_BR_NUMHOOKS it must be a user defined chain + */ if (i != NF_BR_NUMHOOKS || !e->bitmask) { /* this checks if the previous chain has as many entries - as it said it has */ + * as it said it has + */ if (*n != *cnt) { BUGPRINT("nentries does not equal the nr of entries " "in the chain\n"); @@ -549,20 +551,18 @@ ebt_check_entry_size_and_hooks(const struct ebt_entry *e, return 0; } -struct ebt_cl_stack -{ +struct ebt_cl_stack { struct ebt_chainstack cs; int from; unsigned int hookmask; }; -/* - * we need these positions to check that the jumps to a different part of the +/* We need these positions to check that the jumps to a different part of the * entries is a jump to the beginning of a new chain. */ static inline int ebt_get_udc_positions(struct ebt_entry *e, struct ebt_table_info *newinfo, - unsigned int *n, struct ebt_cl_stack *udc) + unsigned int *n, struct ebt_cl_stack *udc) { int i; @@ -649,9 +649,9 @@ ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) static inline int ebt_check_entry(struct ebt_entry *e, struct net *net, - const struct ebt_table_info *newinfo, - const char *name, unsigned int *cnt, - struct ebt_cl_stack *cl_s, unsigned int udc_cnt) + const struct ebt_table_info *newinfo, + const char *name, unsigned int *cnt, + struct ebt_cl_stack *cl_s, unsigned int udc_cnt) { struct ebt_entry_target *t; struct xt_target *target; @@ -673,7 +673,7 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, BUGPRINT("Unknown flag for inv bitmask\n"); return -EINVAL; } - if ( (e->bitmask & EBT_NOPROTO) && (e->bitmask & EBT_802_3) ) { + if ((e->bitmask & EBT_NOPROTO) && (e->bitmask & EBT_802_3)) { BUGPRINT("NOPROTO & 802_3 not allowed\n"); return -EINVAL; } @@ -687,7 +687,8 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, break; } /* (1 << NF_BR_NUMHOOKS) tells the check functions the rule is on - a base chain */ + * a base chain + */ if (i < NF_BR_NUMHOOKS) hookmask = (1 << hook) | (1 << NF_BR_NUMHOOKS); else { @@ -758,13 +759,12 @@ cleanup_matches: return ret; } -/* - * checks for loops and sets the hook mask for udc +/* checks for loops and sets the hook mask for udc * the hook mask for udc tells us from which base chains the udc can be * accessed. This mask is a parameter to the check() functions of the extensions */ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack *cl_s, - unsigned int udc_cnt, unsigned int hooknr, char *base) + unsigned int udc_cnt, unsigned int hooknr, char *base) { int i, chain_nr = -1, pos = 0, nentries = chain->nentries, verdict; const struct ebt_entry *e = (struct ebt_entry *)chain->data; @@ -853,7 +853,8 @@ static int translate_table(struct net *net, const char *name, return -EINVAL; } /* make sure chains are ordered after each other in same order - as their corresponding hooks */ + * as their corresponding hooks + */ for (j = i + 1; j < NF_BR_NUMHOOKS; j++) { if (!newinfo->hook_entry[j]) continue; @@ -868,7 +869,8 @@ static int translate_table(struct net *net, const char *name, i = 0; /* holds the expected nr. of entries for the chain */ j = 0; /* holds the up to now counted entries for the chain */ k = 0; /* holds the total nr. of entries, should equal - newinfo->nentries afterwards */ + * newinfo->nentries afterwards + */ udc_cnt = 0; /* will hold the nr. of user defined chains (udc) */ ret = EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, ebt_check_entry_size_and_hooks, newinfo, @@ -888,10 +890,12 @@ static int translate_table(struct net *net, const char *name, } /* get the location of the udc, put them in an array - while we're at it, allocate the chainstack */ + * while we're at it, allocate the chainstack + */ if (udc_cnt) { /* this will get free'd in do_replace()/ebt_register_table() - if an error occurs */ + * if an error occurs + */ newinfo->chainstack = vmalloc(nr_cpu_ids * sizeof(*(newinfo->chainstack))); if (!newinfo->chainstack) @@ -932,14 +936,15 @@ static int translate_table(struct net *net, const char *name, } /* we now know the following (along with E=mc²): - - the nr of entries in each chain is right - - the size of the allocated space is right - - all valid hooks have a corresponding chain - - there are no loops - - wrong data can still be on the level of a single entry - - could be there are jumps to places that are not the - beginning of a chain. This can only occur in chains that - are not accessible from any base chains, so we don't care. */ + * - the nr of entries in each chain is right + * - the size of the allocated space is right + * - all valid hooks have a corresponding chain + * - there are no loops + * - wrong data can still be on the level of a single entry + * - could be there are jumps to places that are not the + * beginning of a chain. This can only occur in chains that + * are not accessible from any base chains, so we don't care. + */ /* used to know what we need to clean up if something goes wrong */ i = 0; @@ -955,7 +960,7 @@ static int translate_table(struct net *net, const char *name, /* called under write_lock */ static void get_counters(const struct ebt_counter *oldcounters, - struct ebt_counter *counters, unsigned int nentries) + struct ebt_counter *counters, unsigned int nentries) { int i, cpu; struct ebt_counter *counter_base; @@ -986,7 +991,8 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, struct ebt_table *t; /* the user wants counters back - the check on the size is done later, when we have the lock */ + * the check on the size is done later, when we have the lock + */ if (repl->num_counters) { unsigned long size = repl->num_counters * sizeof(*counterstmp); counterstmp = vmalloc(size); @@ -1038,9 +1044,10 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, write_unlock_bh(&t->lock); mutex_unlock(&ebt_mutex); /* so, a user can change the chains while having messed up her counter - allocation. Only reason why this is done is because this way the lock - is held only once, while this doesn't bring the kernel into a - dangerous state. */ + * allocation. Only reason why this is done is because this way the lock + * is held only once, while this doesn't bring the kernel into a + * dangerous state. + */ if (repl->num_counters && copy_to_user(repl->counters, counterstmp, repl->num_counters * sizeof(struct ebt_counter))) { @@ -1342,13 +1349,14 @@ static int update_counters(struct net *net, const void __user *user, } static inline int ebt_make_matchname(const struct ebt_entry_match *m, - const char *base, char __user *ubase) + const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)m - base); char name[EBT_FUNCTION_MAXNAMELEN] = {}; /* ebtables expects 32 bytes long names but xt_match names are 29 bytes - long. Copy 29 bytes and fill remaining bytes with zeroes. */ + * long. Copy 29 bytes and fill remaining bytes with zeroes. + */ strlcpy(name, m->u.match->name, sizeof(name)); if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; @@ -1356,19 +1364,19 @@ static inline int ebt_make_matchname(const struct ebt_entry_match *m, } static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, - const char *base, char __user *ubase) + const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)w - base); char name[EBT_FUNCTION_MAXNAMELEN] = {}; strlcpy(name, w->u.watcher->name, sizeof(name)); - if (copy_to_user(hlp , name, EBT_FUNCTION_MAXNAMELEN)) + if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } -static inline int -ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) +static inline int ebt_make_names(struct ebt_entry *e, const char *base, + char __user *ubase) { int ret; char __user *hlp; @@ -1394,9 +1402,9 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) } static int copy_counters_to_user(struct ebt_table *t, - const struct ebt_counter *oldcounters, - void __user *user, unsigned int num_counters, - unsigned int nentries) + const struct ebt_counter *oldcounters, + void __user *user, unsigned int num_counters, + unsigned int nentries) { struct ebt_counter *counterstmp; int ret = 0; @@ -1427,7 +1435,7 @@ static int copy_counters_to_user(struct ebt_table *t, /* called with ebt_mutex locked */ static int copy_everything_to_user(struct ebt_table *t, void __user *user, - const int *len, int cmd) + const int *len, int cmd) { struct ebt_replace tmp; const struct ebt_counter *oldcounters; @@ -1595,8 +1603,7 @@ static int ebt_compat_entry_padsize(void) static int ebt_compat_match_offset(const struct xt_match *match, unsigned int userlen) { - /* - * ebt_among needs special handling. The kernel .matchsize is + /* ebt_among needs special handling. The kernel .matchsize is * set to -1 at registration time; at runtime an EBT_ALIGN()ed * value is expected. * Example: userspace sends 4500, ebt_among.c wants 4504. @@ -1966,8 +1973,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, return off + match_size; } -/* - * return size of all matches, watchers or target, including necessary +/* return size of all matches, watchers or target, including necessary * alignment and padding. */ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, @@ -2070,8 +2076,7 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, if (ret < 0) return ret; buf_start = (char *) entry; - /* - * 0: matches offset, always follows ebt_entry. + /* 0: matches offset, always follows ebt_entry. * 1: watchers offset, from ebt_entry structure * 2: target offset, from ebt_entry structure * 3: next ebt_entry offset, from ebt_entry structure @@ -2115,8 +2120,7 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, return 0; } -/* - * repl->entries_size is the size of the ebt_entry blob in userspace. +/* repl->entries_size is the size of the ebt_entry blob in userspace. * It might need more memory when copied to a 64 bit kernel in case * userspace is 32-bit. So, first task: find out how much memory is needed. * @@ -2305,7 +2309,7 @@ static int compat_do_ebt_set_ctl(struct sock *sk, break; default: ret = -EINVAL; - } + } return ret; } @@ -2360,8 +2364,7 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, break; case EBT_SO_GET_ENTRIES: case EBT_SO_GET_INIT_ENTRIES: - /* - * try real handler first in case of userland-side padding. + /* try real handler first in case of userland-side padding. * in case we are dealing with an 'ordinary' 32 bit binary * without 64bit compatibility padding, this will fail right * after copy_from_user when the *len argument is validated. diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index a21269b83f16e..4b901d9f2e7cf 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -84,6 +84,7 @@ static const struct nft_expr_ops nft_meta_bridge_set_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_set_eval, .init = nft_meta_set_init, + .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, }; diff --git a/net/core/Makefile b/net/core/Makefile index 086b01fbe1bd8..0b835de04de3d 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ - sock_diag.o dev_ioctl.o tso.o + sock_diag.o dev_ioctl.o tso.o sock_reuseport.o obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o diff --git a/net/core/dev.c b/net/core/dev.c index 8f705fcedb94b..914b4a24c6543 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -138,6 +138,7 @@ #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_ingress.h> +#include <linux/sctp.h> #include "net-sysfs.h" @@ -2471,6 +2472,141 @@ out: } EXPORT_SYMBOL(skb_checksum_help); +/* skb_csum_offload_check - Driver helper function to determine if a device + * with limited checksum offload capabilities is able to offload the checksum + * for a given packet. + * + * Arguments: + * skb - sk_buff for the packet in question + * spec - contains the description of what device can offload + * csum_encapped - returns true if the checksum being offloaded is + * encpasulated. That is it is checksum for the transport header + * in the inner headers. + * checksum_help - when set indicates that helper function should + * call skb_checksum_help if offload checks fail + * + * Returns: + * true: Packet has passed the checksum checks and should be offloadable to + * the device (a driver may still need to check for additional + * restrictions of its device) + * false: Checksum is not offloadable. If checksum_help was set then + * skb_checksum_help was called to resolve checksum for non-GSO + * packets and when IP protocol is not SCTP + */ +bool __skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help) +{ + struct iphdr *iph; + struct ipv6hdr *ipv6; + void *nhdr; + int protocol; + u8 ip_proto; + + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) { + if (!spec->vlan_okay) + goto need_help; + } + + /* We check whether the checksum refers to a transport layer checksum in + * the outermost header or an encapsulated transport layer checksum that + * corresponds to the inner headers of the skb. If the checksum is for + * something else in the packet we need help. + */ + if (skb_checksum_start_offset(skb) == skb_transport_offset(skb)) { + /* Non-encapsulated checksum */ + protocol = eproto_to_ipproto(vlan_get_protocol(skb)); + nhdr = skb_network_header(skb); + *csum_encapped = false; + if (spec->no_not_encapped) + goto need_help; + } else if (skb->encapsulation && spec->encap_okay && + skb_checksum_start_offset(skb) == + skb_inner_transport_offset(skb)) { + /* Encapsulated checksum */ + *csum_encapped = true; + switch (skb->inner_protocol_type) { + case ENCAP_TYPE_ETHER: + protocol = eproto_to_ipproto(skb->inner_protocol); + break; + case ENCAP_TYPE_IPPROTO: + protocol = skb->inner_protocol; + break; + } + nhdr = skb_inner_network_header(skb); + } else { + goto need_help; + } + + switch (protocol) { + case IPPROTO_IP: + if (!spec->ipv4_okay) + goto need_help; + iph = nhdr; + ip_proto = iph->protocol; + if (iph->ihl != 5 && !spec->ip_options_okay) + goto need_help; + break; + case IPPROTO_IPV6: + if (!spec->ipv6_okay) + goto need_help; + if (spec->no_encapped_ipv6 && *csum_encapped) + goto need_help; + ipv6 = nhdr; + nhdr += sizeof(*ipv6); + ip_proto = ipv6->nexthdr; + break; + default: + goto need_help; + } + +ip_proto_again: + switch (ip_proto) { + case IPPROTO_TCP: + if (!spec->tcp_okay || + skb->csum_offset != offsetof(struct tcphdr, check)) + goto need_help; + break; + case IPPROTO_UDP: + if (!spec->udp_okay || + skb->csum_offset != offsetof(struct udphdr, check)) + goto need_help; + break; + case IPPROTO_SCTP: + if (!spec->sctp_okay || + skb->csum_offset != offsetof(struct sctphdr, checksum)) + goto cant_help; + break; + case NEXTHDR_HOP: + case NEXTHDR_ROUTING: + case NEXTHDR_DEST: { + u8 *opthdr = nhdr; + + if (protocol != IPPROTO_IPV6 || !spec->ext_hdrs_okay) + goto need_help; + + ip_proto = opthdr[0]; + nhdr += (opthdr[1] + 1) << 3; + + goto ip_proto_again; + } + default: + goto need_help; + } + + /* Passed the tests for offloading checksum */ + return true; + +need_help: + if (csum_help && !skb_shinfo(skb)->gso_size) + skb_checksum_help(skb); +cant_help: + return false; +} +EXPORT_SYMBOL(__skb_csum_offload_chk); + __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; @@ -2645,7 +2781,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { - features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_CSUM_MASK; } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } @@ -2792,7 +2928,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); - if (!(features & NETIF_F_ALL_CSUM) && + if (!(features & NETIF_F_CSUM_MASK) && skb_checksum_help(skb)) goto out_kfree_skb; } @@ -6467,9 +6603,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, /* UFO needs SG and checksumming */ if (features & NETIF_F_UFO) { /* maybe split UFO into V4 and V6? */ - if (!((features & NETIF_F_GEN_CSUM) || - (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) - == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + if (!(features & NETIF_F_HW_CSUM) && + ((features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) != + (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) { netdev_dbg(dev, "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; @@ -7571,16 +7707,16 @@ static int dev_cpu_callback(struct notifier_block *nfb, netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { - if (mask & NETIF_F_GEN_CSUM) - mask |= NETIF_F_ALL_CSUM; + if (mask & NETIF_F_HW_CSUM) + mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; - all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ - if (all & NETIF_F_GEN_CSUM) - all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if (all & NETIF_F_HW_CSUM) + all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 29edf74846fc9..daf04709dd3c6 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -87,7 +87,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", - [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", + [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", [NETIF_F_RXHASH_BIT] = "rx-hashing", @@ -191,6 +191,23 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) return ret; } +static int phy_get_sset_count(struct phy_device *phydev) +{ + int ret; + + if (phydev->drv->get_sset_count && + phydev->drv->get_strings && + phydev->drv->get_stats) { + mutex_lock(&phydev->lock); + ret = phydev->drv->get_sset_count(phydev); + mutex_unlock(&phydev->lock); + + return ret; + } + + return -EOPNOTSUPP; +} + static int __ethtool_get_sset_count(struct net_device *dev, int sset) { const struct ethtool_ops *ops = dev->ethtool_ops; @@ -204,6 +221,13 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_TUNABLES) return ARRAY_SIZE(tunable_strings); + if (sset == ETH_SS_PHY_STATS) { + if (dev->phydev) + return phy_get_sset_count(dev->phydev); + else + return -EOPNOTSUPP; + } + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else @@ -223,7 +247,17 @@ static void __ethtool_get_strings(struct net_device *dev, sizeof(rss_hash_func_strings)); else if (stringset == ETH_SS_TUNABLES) memcpy(data, tunable_strings, sizeof(tunable_strings)); - else + else if (stringset == ETH_SS_PHY_STATS) { + struct phy_device *phydev = dev->phydev; + + if (phydev) { + mutex_lock(&phydev->lock); + phydev->drv->get_strings(phydev, data); + mutex_unlock(&phydev->lock); + } else { + return; + } + } else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); } @@ -235,7 +269,7 @@ static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) switch (eth_cmd) { case ETHTOOL_GTXCSUM: case ETHTOOL_STXCSUM: - return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM; + return NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC; case ETHTOOL_GRXCSUM: case ETHTOOL_SRXCSUM: return NETIF_F_RXCSUM; @@ -1401,6 +1435,47 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) return ret; } +static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_stats stats; + struct phy_device *phydev = dev->phydev; + u64 *data; + int ret, n_stats; + + if (!phydev) + return -EOPNOTSUPP; + + n_stats = phy_get_sset_count(phydev); + + if (n_stats < 0) + return n_stats; + WARN_ON(n_stats == 0); + + if (copy_from_user(&stats, useraddr, sizeof(stats))) + return -EFAULT; + + stats.n_stats = n_stats; + data = kmalloc_array(n_stats, sizeof(u64), GFP_USER); + if (!data) + return -ENOMEM; + + mutex_lock(&phydev->lock); + phydev->drv->get_stats(phydev, &stats, data); + mutex_unlock(&phydev->lock); + + ret = -EFAULT; + if (copy_to_user(useraddr, &stats, sizeof(stats))) + goto out; + useraddr += sizeof(stats); + if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64))) + goto out; + ret = 0; + + out: + kfree(data); + return ret; +} + static int ethtool_get_perm_addr(struct net_device *dev, void __user *useraddr) { struct ethtool_perm_addr epaddr; @@ -1779,6 +1854,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GSSET_INFO: case ETHTOOL_GSTRINGS: case ETHTOOL_GSTATS: + case ETHTOOL_GPHYSTATS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: case ETHTOOL_GUFO: @@ -1991,6 +2067,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_STUNABLE: rc = ethtool_set_tunable(dev, useraddr); break; + case ETHTOOL_GPHYSTATS: + rc = ethtool_get_phy_stats(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/filter.c b/net/core/filter.c index 672eefbfbe99f..35e6fed287093 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -50,6 +50,7 @@ #include <net/cls_cgroup.h> #include <net/dst_metadata.h> #include <net/dst.h> +#include <net/sock_reuseport.h> /** * sk_filter - run a packet through a socket filter @@ -348,12 +349,6 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * jump offsets, 2nd pass remapping: * new_prog = kmalloc(sizeof(struct bpf_insn) * new_len); * bpf_convert_filter(old_prog, old_len, new_prog, &new_len); - * - * User BPF's register A is mapped to our BPF register 6, user BPF - * register X is mapped to BPF register 7; frame pointer is always - * register 10; Context 'void *ctx' is stored in register 1, that is, - * for socket filters: ctx == 'struct sk_buff *', for seccomp: - * ctx == 'struct seccomp_data *'. */ static int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_insn *new_prog, int *new_len) @@ -381,9 +376,22 @@ do_pass: new_insn = new_prog; fp = prog; - if (new_insn) - *new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); - new_insn++; + /* Classic BPF related prologue emission. */ + if (new_insn) { + /* Classic BPF expects A and X to be reset first. These need + * to be guaranteed to be the first two instructions. + */ + *new_insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); + *new_insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_X, BPF_REG_X); + + /* All programs must keep CTX in callee saved BPF_REG_CTX. + * In eBPF case it's done by the compiler, here we need to + * do this ourself. Initial CTX is present in BPF_REG_ARG1. + */ + *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); + } else { + new_insn += 3; + } for (i = 0; i < len; fp++, i++) { struct bpf_insn tmp_insns[6] = { }; @@ -1160,17 +1168,32 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return 0; } -/** - * sk_attach_filter - attach a socket filter - * @fprog: the filter program - * @sk: the socket to use - * - * Attach the user's filter code. We first run some sanity checks on - * it to make sure it does not explode on us later. If an error - * occurs or there is insufficient memory for the filter a negative - * errno code is returned. On success the return is zero. - */ -int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk) +{ + struct bpf_prog *old_prog; + int err; + + if (bpf_prog_size(prog->len) > sysctl_optmem_max) + return -ENOMEM; + + if (sk_unhashed(sk)) { + err = reuseport_alloc(sk); + if (err) + return err; + } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { + /* The socket wasn't bound with SO_REUSEPORT */ + return -EINVAL; + } + + old_prog = reuseport_attach_prog(sk, prog); + if (old_prog) + bpf_prog_destroy(old_prog); + + return 0; +} + +static +struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { unsigned int fsize = bpf_classic_proglen(fprog); unsigned int bpf_fsize = bpf_prog_size(fprog->len); @@ -1178,19 +1201,19 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) - return -EPERM; + return ERR_PTR(-EPERM); /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) - return -EINVAL; + return ERR_PTR(-EINVAL); prog = bpf_prog_alloc(bpf_fsize, 0); if (!prog) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (copy_from_user(prog->insns, fprog->filter, fsize)) { __bpf_prog_free(prog); - return -EFAULT; + return ERR_PTR(-EFAULT); } prog->len = fprog->len; @@ -1198,13 +1221,30 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) err = bpf_prog_store_orig_filter(prog, fprog); if (err) { __bpf_prog_free(prog); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - prog = bpf_prepare_filter(prog, NULL); + return bpf_prepare_filter(prog, NULL); +} + +/** + * sk_attach_filter - attach a socket filter + * @fprog: the filter program + * @sk: the socket to use + * + * Attach the user's filter code. We first run some sanity checks on + * it to make sure it does not explode on us later. If an error + * occurs or there is insufficient memory for the filter a negative + * errno code is returned. On success the return is zero. + */ +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +{ + struct bpf_prog *prog = __get_filter(fprog, sk); + int err; + if (IS_ERR(prog)) return PTR_ERR(prog); @@ -1218,23 +1258,50 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) } EXPORT_SYMBOL_GPL(sk_attach_filter); -int sk_attach_bpf(u32 ufd, struct sock *sk) +int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { - struct bpf_prog *prog; + struct bpf_prog *prog = __get_filter(fprog, sk); int err; + if (IS_ERR(prog)) + return PTR_ERR(prog); + + err = __reuseport_attach_prog(prog, sk); + if (err < 0) { + __bpf_prog_release(prog); + return err; + } + + return 0; +} + +static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) +{ + struct bpf_prog *prog; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) - return -EPERM; + return ERR_PTR(-EPERM); prog = bpf_prog_get(ufd); if (IS_ERR(prog)) - return PTR_ERR(prog); + return prog; if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); - return -EINVAL; + return ERR_PTR(-EINVAL); } + return prog; +} + +int sk_attach_bpf(u32 ufd, struct sock *sk) +{ + struct bpf_prog *prog = __get_bpf(ufd, sk); + int err; + + if (IS_ERR(prog)) + return PTR_ERR(prog); + err = __sk_attach_prog(prog, sk); if (err < 0) { bpf_prog_put(prog); @@ -1244,7 +1311,25 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return 0; } +int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) +{ + struct bpf_prog *prog = __get_bpf(ufd, sk); + int err; + + if (IS_ERR(prog)) + return PTR_ERR(prog); + + err = __reuseport_attach_prog(prog, sk); + if (err < 0) { + bpf_prog_put(prog); + return err; + } + + return 0; +} + #define BPF_RECOMPUTE_CSUM(flags) ((flags) & 1) +#define BPF_LDST_LEN 16U static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) { @@ -1252,7 +1337,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) int offset = (int) r2; void *from = (void *) (long) r3; unsigned int len = (unsigned int) r4; - char buf[16]; + char buf[BPF_LDST_LEN]; void *ptr; /* bpf verifier guarantees that: @@ -1299,6 +1384,36 @@ const struct bpf_func_proto bpf_skb_store_bytes_proto = { .arg5_type = ARG_ANYTHING, }; +static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; + int offset = (int) r2; + void *to = (void *)(unsigned long) r3; + unsigned int len = (unsigned int) r4; + void *ptr; + + if (unlikely((u32) offset > 0xffff || len > BPF_LDST_LEN)) + return -EFAULT; + + ptr = skb_header_pointer(skb, offset, len, to); + if (unlikely(!ptr)) + return -EFAULT; + if (ptr != to) + memcpy(to, ptr, len); + + return 0; +} + +const struct bpf_func_proto bpf_skb_load_bytes_proto = { + .func = bpf_skb_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_STACK, + .arg4_type = ARG_CONST_STACK_SIZE, +}; + #define BPF_HEADER_FIELD_SIZE(flags) ((flags) & 0x0f) #define BPF_IS_PSEUDO_HEADER(flags) ((flags) & 0x10) @@ -1654,6 +1769,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f88a62ab019d2..b6c8a6629b397 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -471,6 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev, if (dev_isalive(netdev)) { struct switchdev_attr attr = { + .orig_dev = netdev, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; @@ -1452,8 +1453,8 @@ static void netdev_release(struct device *d) static const void *net_namespace(struct device *d) { - struct net_device *dev; - dev = container_of(d, struct net_device, dev); + struct net_device *dev = to_net_dev(d); + return dev_net(dev); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 04257a0e35343..0260c84ed83c4 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -84,9 +84,11 @@ static void update_classid(struct cgroup_subsys_state *css, void *v) css_task_iter_end(&it); } -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cgrp_attach(struct cgroup_taskset *tset) { + struct cgroup_subsys_state *css; + + cgroup_taskset_first(tset, &css); update_classid(css, (void *)(unsigned long)css_cls_state(css)->classid); } diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 053d60c33395e..f1efbc39ef6be 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -233,13 +233,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n) return 0; } -static void net_prio_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; - void *v = (void *)(unsigned long)css->cgroup->id; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(p, css, tset) { + void *v = (void *)(unsigned long)css->cgroup->id; - cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index de8d5cc5eb240..2be144498bcf0 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2898,7 +2898,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; - } else if (odev->features & NETIF_F_V4_CSUM) { + } else if (odev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; udp4_hwcsum(skb, iph->saddr, iph->daddr); @@ -3032,7 +3032,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; - } else if (odev->features & NETIF_F_V6_CSUM) { + } else if (odev->features & (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM)) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 34ba7a08876de..baf49cb2f23df 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1027,6 +1027,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; struct switchdev_attr attr = { + .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; @@ -2563,7 +2564,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u16 vid, u32 pid, u32 seq, int type, unsigned int flags, - int nlflags) + int nlflags, u16 ndm_state) { struct nlmsghdr *nlh; struct ndmsg *ndm; @@ -2579,7 +2580,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, ndm->ndm_flags = flags; ndm->ndm_type = 0; ndm->ndm_ifindex = dev->ifindex; - ndm->ndm_state = NUD_PERMANENT; + ndm->ndm_state = ndm_state; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; @@ -2600,7 +2601,8 @@ static inline size_t rtnl_fdb_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); } -static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type) +static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, + u16 ndm_state) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2611,7 +2613,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type) goto errout; err = nlmsg_populate_fdb_fill(skb, dev, addr, vid, - 0, 0, type, NTF_SELF, 0); + 0, 0, type, NTF_SELF, 0, ndm_state); if (err < 0) { kfree_skb(skb); goto errout; @@ -2746,7 +2748,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) nlh->nlmsg_flags); if (!err) { - rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH); + rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH, + ndm->ndm_state); ndm->ndm_flags &= ~NTF_SELF; } } @@ -2847,7 +2850,8 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid); if (!err) { - rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH); + rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH, + ndm->ndm_state); ndm->ndm_flags &= ~NTF_SELF; } } @@ -2875,7 +2879,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0, portid, seq, RTM_NEWNEIGH, NTF_SELF, - NLM_F_MULTI); + NLM_F_MULTI, NUD_PERMANENT); if (err < 0) return err; skip: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 152b9c70e2525..b2df375ec9c21 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3643,7 +3643,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_info = tstype; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) serr->ee.ee_data -= sk->sk_tskey; } @@ -4268,7 +4269,7 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len, + memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, 2 * ETH_ALEN); skb->mac_header += VLAN_HLEN; return skb; diff --git a/net/core/sock.c b/net/core/sock.c index 1278d7b7bd9a8..51270238e2692 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -134,6 +134,7 @@ #include <linux/sock_diag.h> #include <linux/filter.h> +#include <net/sock_reuseport.h> #include <trace/events/sock.h> @@ -433,8 +434,6 @@ static bool sock_needs_netstamp(const struct sock *sk) } } -#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) - static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { @@ -874,7 +873,8 @@ set_rcvbuf: if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) { if (sk->sk_state != TCP_ESTABLISHED) { ret = -EINVAL; break; @@ -933,6 +933,32 @@ set_rcvbuf: } break; + case SO_ATTACH_REUSEPORT_CBPF: + ret = -EINVAL; + if (optlen == sizeof(struct sock_fprog)) { + struct sock_fprog fprog; + + ret = -EFAULT; + if (copy_from_user(&fprog, optval, sizeof(fprog))) + break; + + ret = sk_reuseport_attach_filter(&fprog, sk); + } + break; + + case SO_ATTACH_REUSEPORT_EBPF: + ret = -EINVAL; + if (optlen == sizeof(u32)) { + u32 ufd; + + ret = -EFAULT; + if (copy_from_user(&ufd, optval, sizeof(ufd))) + break; + + ret = sk_reuseport_attach_bpf(ufd, sk); + } + break; + case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; @@ -1444,6 +1470,8 @@ void sk_destruct(struct sock *sk) sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); @@ -1543,7 +1571,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ is_charged = sk_filter_charge(newsk, filter); - if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) { + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 0c1d58d43f67c..a996ce8c8fb25 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -214,7 +214,7 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld) } EXPORT_SYMBOL_GPL(sock_diag_unregister); -static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; struct sock_diag_req *req = nlmsg_data(nlh); @@ -234,8 +234,12 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) hndl = sock_diag_handlers[req->sdiag_family]; if (hndl == NULL) err = -ENOENT; - else + else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) err = hndl->dump(skb, nlh); + else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy) + err = hndl->destroy(skb, nlh); + else + err = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return err; @@ -261,7 +265,8 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return ret; case SOCK_DIAG_BY_FAMILY: - return __sock_diag_rcv_msg(skb, nlh); + case SOCK_DESTROY: + return __sock_diag_cmd(skb, nlh); default: return -EINVAL; } @@ -295,6 +300,18 @@ static int sock_diag_bind(struct net *net, int group) return 0; } +int sock_diag_destroy(struct sock *sk, int err) +{ + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + if (!sk->sk_prot->diag_destroy) + return -EOPNOTSUPP; + + return sk->sk_prot->diag_destroy(sk, err); +} +EXPORT_SYMBOL_GPL(sock_diag_destroy); + static int __net_init diag_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c new file mode 100644 index 0000000000000..1df98c5574402 --- /dev/null +++ b/net/core/sock_reuseport.c @@ -0,0 +1,251 @@ +/* + * To speed up listener socket lookup, create an array to store all sockets + * listening on the same port. This allows a decision to be made after finding + * the first socket. An optional BPF program can also be configured for + * selecting the socket index from the array of available sockets. + */ + +#include <net/sock_reuseport.h> +#include <linux/bpf.h> +#include <linux/rcupdate.h> + +#define INIT_SOCKS 128 + +static DEFINE_SPINLOCK(reuseport_lock); + +static struct sock_reuseport *__reuseport_alloc(u16 max_socks) +{ + size_t size = sizeof(struct sock_reuseport) + + sizeof(struct sock *) * max_socks; + struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); + + if (!reuse) + return NULL; + + reuse->max_socks = max_socks; + + RCU_INIT_POINTER(reuse->prog, NULL); + return reuse; +} + +int reuseport_alloc(struct sock *sk) +{ + struct sock_reuseport *reuse; + + /* bh lock used since this function call may precede hlist lock in + * soft irq of receive path or setsockopt from process context + */ + spin_lock_bh(&reuseport_lock); + WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)), + "multiple allocations for the same socket"); + reuse = __reuseport_alloc(INIT_SOCKS); + if (!reuse) { + spin_unlock_bh(&reuseport_lock); + return -ENOMEM; + } + + reuse->socks[0] = sk; + reuse->num_socks = 1; + rcu_assign_pointer(sk->sk_reuseport_cb, reuse); + + spin_unlock_bh(&reuseport_lock); + + return 0; +} +EXPORT_SYMBOL(reuseport_alloc); + +static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) +{ + struct sock_reuseport *more_reuse; + u32 more_socks_size, i; + + more_socks_size = reuse->max_socks * 2U; + if (more_socks_size > U16_MAX) + return NULL; + + more_reuse = __reuseport_alloc(more_socks_size); + if (!more_reuse) + return NULL; + + more_reuse->max_socks = more_socks_size; + more_reuse->num_socks = reuse->num_socks; + more_reuse->prog = reuse->prog; + + memcpy(more_reuse->socks, reuse->socks, + reuse->num_socks * sizeof(struct sock *)); + + for (i = 0; i < reuse->num_socks; ++i) + rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, + more_reuse); + + /* Note: we use kfree_rcu here instead of reuseport_free_rcu so + * that reuse and more_reuse can temporarily share a reference + * to prog. + */ + kfree_rcu(reuse, rcu); + return more_reuse; +} + +/** + * reuseport_add_sock - Add a socket to the reuseport group of another. + * @sk: New socket to add to the group. + * @sk2: Socket belonging to the existing reuseport group. + * May return ENOMEM and not add socket to group under memory pressure. + */ +int reuseport_add_sock(struct sock *sk, const struct sock *sk2) +{ + struct sock_reuseport *reuse; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)), + WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)), + "socket already in reuseport group"); + + if (reuse->num_socks == reuse->max_socks) { + reuse = reuseport_grow(reuse); + if (!reuse) { + spin_unlock_bh(&reuseport_lock); + return -ENOMEM; + } + } + + reuse->socks[reuse->num_socks] = sk; + /* paired with smp_rmb() in reuseport_select_sock() */ + smp_wmb(); + reuse->num_socks++; + rcu_assign_pointer(sk->sk_reuseport_cb, reuse); + + spin_unlock_bh(&reuseport_lock); + + return 0; +} +EXPORT_SYMBOL(reuseport_add_sock); + +static void reuseport_free_rcu(struct rcu_head *head) +{ + struct sock_reuseport *reuse; + + reuse = container_of(head, struct sock_reuseport, rcu); + if (reuse->prog) + bpf_prog_destroy(reuse->prog); + kfree(reuse); +} + +void reuseport_detach_sock(struct sock *sk) +{ + struct sock_reuseport *reuse; + int i; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + rcu_assign_pointer(sk->sk_reuseport_cb, NULL); + + for (i = 0; i < reuse->num_socks; i++) { + if (reuse->socks[i] == sk) { + reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; + reuse->num_socks--; + if (reuse->num_socks == 0) + call_rcu(&reuse->rcu, reuseport_free_rcu); + break; + } + } + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_detach_sock); + +static struct sock *run_bpf(struct sock_reuseport *reuse, u16 socks, + struct bpf_prog *prog, struct sk_buff *skb, + int hdr_len) +{ + struct sk_buff *nskb = NULL; + u32 index; + + if (skb_shared(skb)) { + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return NULL; + skb = nskb; + } + + /* temporarily advance data past protocol header */ + if (!pskb_pull(skb, hdr_len)) { + kfree_skb(nskb); + return NULL; + } + index = bpf_prog_run_save_cb(prog, skb); + __skb_push(skb, hdr_len); + + consume_skb(nskb); + + if (index >= socks) + return NULL; + + return reuse->socks[index]; +} + +/** + * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. + * @sk: First socket in the group. + * @hash: When no BPF filter is available, use this hash to select. + * @skb: skb to run through BPF filter. + * @hdr_len: BPF filter expects skb data pointer at payload data. If + * the skb does not yet point at the payload, this parameter represents + * how far the pointer needs to advance to reach the payload. + * Returns a socket that should receive the packet (or NULL on error). + */ +struct sock *reuseport_select_sock(struct sock *sk, + u32 hash, + struct sk_buff *skb, + int hdr_len) +{ + struct sock_reuseport *reuse; + struct bpf_prog *prog; + struct sock *sk2 = NULL; + u16 socks; + + rcu_read_lock(); + reuse = rcu_dereference(sk->sk_reuseport_cb); + + /* if memory allocation failed or add call is not yet complete */ + if (!reuse) + goto out; + + prog = rcu_dereference(reuse->prog); + socks = READ_ONCE(reuse->num_socks); + if (likely(socks)) { + /* paired with smp_wmb() in reuseport_add_sock() */ + smp_rmb(); + + if (prog && skb) + sk2 = run_bpf(reuse, socks, prog, skb, hdr_len); + else + sk2 = reuse->socks[reciprocal_scale(hash, socks)]; + } + +out: + rcu_read_unlock(); + return sk2; +} +EXPORT_SYMBOL(reuseport_select_sock); + +struct bpf_prog * +reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) +{ + struct sock_reuseport *reuse; + struct bpf_prog *old_prog; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + old_prog = rcu_dereference_protected(reuse->prog, + lockdep_is_held(&reuseport_lock)); + rcu_assign_pointer(reuse->prog, prog); + spin_unlock_bh(&reuseport_lock); + + return old_prog; +} +EXPORT_SYMBOL(reuseport_attach_prog); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index eebf5ac8ce18a..13d6b1a6e0fc2 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 20c49c724ba04..737c87a2a41e0 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -161,9 +161,7 @@ static int lowpan_newlink(struct net *src_net, struct net_device *ldev, wdev->needed_headroom; ldev->needed_tailroom = wdev->needed_tailroom; - lowpan_netdev_setup(ldev, LOWPAN_LLTYPE_IEEE802154); - - ret = register_netdevice(ldev); + ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154); if (ret < 0) { dev_put(wdev); return ret; @@ -180,7 +178,7 @@ static void lowpan_dellink(struct net_device *ldev, struct list_head *head) ASSERT_RTNL(); wdev->ieee802154_ptr->lowpan_dev = NULL; - unregister_netdevice(ldev); + lowpan_unregister_netdevice(ldev); dev_put(wdev); } diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 6b437e8760d31..30d875dff6b54 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -624,7 +624,6 @@ int __init lowpan_net_frag_init(void) lowpan_frags.hashfn = lowpan_hashfn; lowpan_frags.constructor = lowpan_frag_init; lowpan_frags.destructor = NULL; - lowpan_frags.skb_free = NULL; lowpan_frags.qsize = sizeof(struct frag_queue); lowpan_frags.match = lowpan_frag_match; lowpan_frags.frag_expire = lowpan_frag_expire; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 416dfa004cfb1..c22920525e5d8 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -436,6 +436,19 @@ config INET_UDP_DIAG Support for UDP socket monitoring interface used by the ss tool. If unsure, say Y. +config INET_DIAG_DESTROY + bool "INET: allow privileged process to administratively close sockets" + depends on INET_DIAG + default n + ---help--- + Provides a SOCK_DESTROY operation that allows privileged processes + (e.g., a connection manager or a network administration tool such as + ss) to close sockets opened by other processes. Closing a socket in + this way interrupts any blocking read/write/connect operations on + the socket and causes future socket calls to behave as if the socket + had been disconnected. + If unsure, say N. + menuconfig TCP_CONG_ADVANCED bool "TCP: advanced congestion control" ---help--- diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 11c4ca13ec3b0..5c5db6636704d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -257,6 +257,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cc8f3e506cded..4734475930601 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1155,6 +1155,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info; struct in_device *in_dev; struct net *net = dev_net(dev); unsigned int flags; @@ -1193,6 +1194,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo case NETDEV_CHANGEMTU: rt_cache_flush(net); break; + case NETDEV_CHANGEUPPER: + info = ptr; + /* flush all routes if dev is linked to or unlinked from + * an L3 master device (e.g., VRF) + */ + if (info->upper_dev && netif_is_l3_master(info->upper_dev)) + fib_disable_ip(dev, NETDEV_DOWN, true); + break; } return NOTIFY_DONE; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index e0fcbbbcfe54d..bd903fe0f7508 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -24,6 +24,7 @@ struct fou { u16 type; struct udp_offload udp_offloads; struct list_head list; + struct rcu_head rcu; }; #define FOU_F_REMCSUM_NOPARTIAL BIT(0) @@ -417,7 +418,7 @@ static void fou_release(struct fou *fou) list_del(&fou->list); udp_tunnel_sock_release(sock); - kfree(fou); + kfree_rcu(fou, rcu); } static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ab9f8a66615d0..8bb8e7ad85483 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -350,17 +350,12 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, nlmsg_flags, unlh); } -int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct sk_buff *in_skb, - const struct nlmsghdr *nlh, - const struct inet_diag_req_v2 *req) +struct sock *inet_diag_find_one_icsk(struct net *net, + struct inet_hashinfo *hashinfo, + const struct inet_diag_req_v2 *req) { - struct net *net = sock_net(in_skb->sk); - struct sk_buff *rep; struct sock *sk; - int err; - err = -EINVAL; if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], @@ -375,15 +370,33 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, req->id.idiag_if); #endif else - goto out_nosk; + return ERR_PTR(-EINVAL); - err = -ENOENT; if (!sk) - goto out_nosk; + return ERR_PTR(-ENOENT); - err = sock_diag_check_cookie(sk, req->id.idiag_cookie); - if (err) - goto out; + if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { + sock_gen_put(sk); + return ERR_PTR(-ENOENT); + } + + return sk; +} +EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); + +int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, + struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req) +{ + struct net *net = sock_net(in_skb->sk); + struct sk_buff *rep; + struct sock *sk; + int err; + + sk = inet_diag_find_one_icsk(net, hashinfo, req); + if (IS_ERR(sk)) + return PTR_ERR(sk); rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { @@ -409,12 +422,11 @@ out: if (sk) sock_gen_put(sk); -out_nosk: return err; } EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); -static int inet_diag_get_exact(struct sk_buff *in_skb, +static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { @@ -424,8 +436,12 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, handler = inet_diag_lock_handler(req->sdiag_protocol); if (IS_ERR(handler)) err = PTR_ERR(handler); - else + else if (cmd == SOCK_DIAG_BY_FAMILY) err = handler->dump_one(in_skb, nlh, req); + else if (cmd == SOCK_DESTROY && handler->destroy) + err = handler->destroy(in_skb, req); + else + err = -EOPNOTSUPP; inet_diag_unlock_handler(handler); return err; @@ -938,7 +954,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, req.idiag_states = rc->idiag_states; req.id = rc->id; - return inet_diag_get_exact(in_skb, nlh, &req); + return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, &req); } static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -972,7 +988,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) return inet_diag_get_exact_compat(skb, nlh); } -static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct inet_diag_req_v2); struct net *net = sock_net(skb->sk); @@ -980,7 +996,8 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) if (nlmsg_len(h) < hdrlen) return -EINVAL; - if (h->nlmsg_flags & NLM_F_DUMP) { + if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY && + h->nlmsg_flags & NLM_F_DUMP) { if (nlmsg_attrlen(h, hdrlen)) { struct nlattr *attr; @@ -999,7 +1016,7 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } } - return inet_diag_get_exact(skb, h, nlmsg_data(h)); + return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h)); } static @@ -1050,14 +1067,16 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) static const struct sock_diag_handler inet_diag_handler = { .family = AF_INET, - .dump = inet_diag_handler_dump, + .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, + .destroy = inet_diag_handler_cmd, }; static const struct sock_diag_handler inet6_diag_handler = { .family = AF_INET6, - .dump = inet_diag_handler_dump, + .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, + .destroy = inet_diag_handler_cmd, }; int inet_diag_register(const struct inet_diag_handler *h) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index fe144dae7372d..3a88b0c737972 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -285,14 +285,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) } EXPORT_SYMBOL(inet_frag_kill); -static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb) -{ - if (f->skb_free) - f->skb_free(skb); - kfree_skb(skb); -} - void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) { struct sk_buff *fp; @@ -309,7 +301,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) struct sk_buff *xp = fp->next; sum_truesize += fp->truesize; - frag_kfree_skb(nf, f, fp); + kfree_skb(fp); fp = xp; } sum = sum_truesize + f->qsize; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 1fe55ae817818..3f00810b72889 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -891,7 +891,6 @@ void __init ipfrag_init(void) ip4_frags.hashfn = ip4_hashfn; ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; - ip4_frags.skb_free = NULL; ip4_frags.qsize = sizeof(struct ipq); ip4_frags.match = ip4_frag_match; ip4_frags.frag_expire = ip_expire; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 04a48c0159cca..7c51c4e1661f9 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -561,10 +561,9 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) tunnel_id_to_key(tun_info->key.tun_id), 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; - err = iptunnel_xmit(skb->sk, rt, skb, fl.saddr, - key->u.ipv4.dst, IPPROTO_GRE, - key->tos, key->ttl, df, false); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + + iptunnel_xmit(skb->sk, rt, skb, fl.saddr, key->u.ipv4.dst, IPPROTO_GRE, + key->tos, key->ttl, df, false); return; err_free_rt: diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e0b94cd843d7f..568e2bc0d93d1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -911,7 +911,7 @@ static int __ip_append_data(struct sock *sk, */ if (transhdrlen && length + fragheaderlen <= mtu && - rt->dst.dev->features & NETIF_F_V4_CSUM && + rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && !(flags & MSG_MORE) && !exthdrlen) csummode = CHECKSUM_PARTIAL; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0f6e9ee031c4b..c7bd72e9b5448 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -656,7 +656,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; - int err; bool connected; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); @@ -794,10 +793,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, return; } - err = iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, - tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); - + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, + df, !net_eq(tunnel->net, dev_net(dev))); return; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 1db8418aa62e6..eb52ce950c27b 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -47,12 +47,13 @@ #include <net/rtnetlink.h> #include <net/dst_metadata.h> -int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 proto, - __u8 tos, __u8 ttl, __be16 df, bool xnet) +void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 proto, + __u8 tos, __u8 ttl, __be16 df, bool xnet) { int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); + struct net_device *dev = skb->dev; struct iphdr *iph; int err; @@ -81,7 +82,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, err = ip_local_out(net, sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; - return pkt_len; + iptunnel_xmit_stats(dev, pkt_len); } EXPORT_SYMBOL_GPL(iptunnel_xmit); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 02d9c21e2953b..5cf10b777b7e4 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -199,7 +199,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = skb->len; - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; tx_error_icmp: diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 1f067294cbc53..4044da61e7479 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -252,9 +252,6 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) p.i_key = p.o_key = 0; p.i_flags = p.o_flags = 0; - if (p.iph.ttl) - p.iph.frag_off |= htons(IP_DF); - err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index a355841765356..c187c60e3e0c7 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -60,6 +60,7 @@ config NFT_REJECT_IPV4 config NFT_DUP_IPV4 tristate "IPv4 nf_tables packet duplication support" + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 help This module enables IPv4 packet duplication support for nf_tables. diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 5075b7ecd26d4..61c7cc22ea684 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -132,7 +132,8 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { + (!skb->dev || skb->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index c747b2d9eb770..b6ea57ec5e141 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -14,7 +14,6 @@ #include <net/netfilter/ipv4/nf_reject.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> -#include <net/netfilter/ipv4/nf_reject.h> const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 4cbe9f0a42817..643a86c490208 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -351,7 +351,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->snt_synack.v64 = 0; treq->tfo_listener = false; - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -371,7 +371,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark, + flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a0bd7a55193e3..41ff1f87dfd75 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -915,6 +915,17 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "tcp_l3mdev_accept", + .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82cca18c90fb..7bb1b091efd17 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1018,7 +1018,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, ssize_t res; if (!(sk->sk_route_caps & NETIF_F_SG) || - !(sk->sk_route_caps & NETIF_F_ALL_CSUM)) + !sk_check_csum_caps(sk)) return sock_no_sendpage(sk->sk_socket, page, offset, size, flags); @@ -1175,7 +1175,7 @@ new_segment: /* * Check whether we can use HW checksum. */ - if (sk->sk_route_caps & NETIF_F_ALL_CSUM) + if (sk_check_csum_caps(sk)) skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); @@ -3080,6 +3080,52 @@ void tcp_done(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_done); +int tcp_abort(struct sock *sk, int err) +{ + if (!sk_fullsock(sk)) { + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + + local_bh_disable(); + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + local_bh_enable(); + return 0; + } + sock_gen_put(sk); + return -EOPNOTSUPP; + } + + /* Don't race with userspace socket closes such as tcp_close. */ + lock_sock(sk); + + if (sk->sk_state == TCP_LISTEN) { + tcp_set_state(sk, TCP_CLOSE); + inet_csk_listen_stop(sk); + } + + /* Don't race with BH socket closes such as inet_csk_listen_stop. */ + local_bh_disable(); + bh_lock_sock(sk); + + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_err = err; + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); + sk->sk_error_report(sk); + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_done(sk); + } + + bh_unlock_sock(sk); + local_bh_enable(); + release_sock(sk); + sock_put(sk); + return 0; +} +EXPORT_SYMBOL_GPL(tcp_abort); + extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index b31604086edd6..4d610934fb391 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -10,6 +10,8 @@ */ #include <linux/module.h> +#include <linux/net.h> +#include <linux/sock_diag.h> #include <linux/inet_diag.h> #include <linux/tcp.h> @@ -46,12 +48,29 @@ static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); } +#ifdef CONFIG_INET_DIAG_DESTROY +static int tcp_diag_destroy(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req) +{ + struct net *net = sock_net(in_skb->sk); + struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + + if (IS_ERR(sk)) + return PTR_ERR(sk); + + return sock_diag_destroy(sk, ECONNABORTED); +} +#endif + static const struct inet_diag_handler tcp_diag_handler = { .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, .idiag_type = IPPROTO_TCP, .idiag_info_size = sizeof(struct tcp_info), +#ifdef CONFIG_INET_DIAG_DESTROY + .destroy = tcp_diag_destroy, +#endif }; static int __init tcp_diag_init(void) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d656eef7f8e1..7b1fddc470191 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6204,7 +6204,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init(req, &tmp_opt, skb, sk); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ - inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; + inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); af_ops->init_req(req, sk, skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db003438aaf5f..fc4f726867050 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -587,7 +587,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) } rep; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; + struct tcp_md5sig_key *key = NULL; const __u8 *hash_location = NULL; unsigned char newhash[16]; int genhash; @@ -627,7 +627,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (!sk && hash_location) { + if (sk && sk_fullsock(sk)) { + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, AF_INET); + } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -651,10 +654,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; - } else { - key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, - AF_INET) : NULL; } if (key) { @@ -675,7 +674,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; - arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. @@ -683,6 +683,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; + BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != + offsetof(struct inet_timewait_sock, tw_bound_dev_if)); + arg.tos = ip_hdr(skb)->tos; ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -1276,6 +1279,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, ireq = inet_rsk(req); sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); + newsk->sk_bound_dev_if = ireq->ir_iif; newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = ireq->opt; rcu_assign_pointer(newinet->inet_opt, inet_opt); @@ -1493,7 +1497,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (likely(sk->sk_rx_dst)) skb_dst_drop(skb); else - skb_dst_force(skb); + skb_dst_force_safe(skb); __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; @@ -1705,7 +1709,9 @@ do_time_wait: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: - goto no_tcp_socket; + tcp_v4_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; @@ -1721,8 +1727,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { - dst_hold(dst); + if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } @@ -2342,6 +2347,7 @@ struct proto tcp_prot = { .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, #endif + .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ac6b1961ffeb3..75632a9258242 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -131,7 +131,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, goto kill; if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt)) - goto kill_with_rst; + return TCP_TW_RST; /* Dup ACK? */ if (!th->ack || @@ -145,11 +145,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * reset. */ if (!th->fin || - TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { -kill_with_rst: - inet_twsk_deschedule_put(tw); + TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) return TCP_TW_RST; - } /* FIN arrived, enter true time-wait state. */ tw->tw_substate = TCP_TIME_WAIT; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a800cee880357..412a920fe0ec0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3150,7 +3150,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, err = 0, copied; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; struct sk_buff *syn_data; @@ -3188,17 +3188,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); - copied = copy_from_iter(skb_put(syn_data, space), space, - &fo->data->msg_iter); - if (unlikely(!copied)) { - kfree_skb(syn_data); - goto fallback; - } - if (copied != space) { - skb_trim(syn_data, copied); - space = copied; + if (space) { + int copied = copy_from_iter(skb_put(syn_data, space), space, + &fo->data->msg_iter); + if (unlikely(!copied)) { + kfree_skb(syn_data); + goto fallback; + } + if (copied != space) { + skb_trim(syn_data, copied); + space = copied; + } } - /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0c7b0e61b9171..3a66731e3af6d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -113,6 +113,7 @@ #include <trace/events/skb.h> #include <net/busy_poll.h> #include "udp_impl.h" +#include <net/sock_reuseport.h> struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); @@ -137,7 +138,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2), + const struct sock *sk2, + bool match_wildcard), unsigned int log) { struct sock *sk2; @@ -152,8 +154,9 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (!sk2->sk_reuseport || !sk->sk_reuseport || + rcu_access_pointer(sk->sk_reuseport_cb) || !uid_eq(uid, sock_i_uid(sk2))) && - saddr_comp(sk, sk2)) { + saddr_comp(sk, sk2, true)) { if (!bitmap) return 1; __set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap); @@ -170,7 +173,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, struct udp_hslot *hslot2, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2)) + const struct sock *sk2, + bool match_wildcard)) { struct sock *sk2; struct hlist_nulls_node *node; @@ -186,8 +190,9 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (!sk2->sk_reuseport || !sk->sk_reuseport || + rcu_access_pointer(sk->sk_reuseport_cb) || !uid_eq(uid, sock_i_uid(sk2))) && - saddr_comp(sk, sk2)) { + saddr_comp(sk, sk2, true)) { res = 1; break; } @@ -196,6 +201,35 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, return res; } +static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot, + int (*saddr_same)(const struct sock *sk1, + const struct sock *sk2, + bool match_wildcard)) +{ + struct net *net = sock_net(sk); + struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); + struct sock *sk2; + + sk_nulls_for_each(sk2, node, &hslot->head) { + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + sk2->sk_family == sk->sk_family && + ipv6_only_sock(sk2) == ipv6_only_sock(sk) && + (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) && + (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && + (*saddr_same)(sk, sk2, false)) { + return reuseport_add_sock(sk, sk2); + } + } + + /* Initial allocation may have already happened via setsockopt */ + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return reuseport_alloc(sk); + return 0; +} + /** * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * @@ -207,7 +241,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, */ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2), + const struct sock *sk2, + bool match_wildcard), unsigned int hash2_nulladdr) { struct udp_hslot *hslot, *hslot2; @@ -290,6 +325,14 @@ found: udp_sk(sk)->udp_port_hash = snum; udp_sk(sk)->udp_portaddr_hash ^= snum; if (sk_unhashed(sk)) { + if (sk->sk_reuseport && + udp_reuseport_add_sock(sk, hslot, saddr_comp)) { + inet_sk(sk)->inet_num = 0; + udp_sk(sk)->udp_port_hash = 0; + udp_sk(sk)->udp_portaddr_hash ^= snum; + goto fail_unlock; + } + sk_nulls_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -309,13 +352,22 @@ fail: } EXPORT_SYMBOL(udp_lib_get_port); -static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses + * match_wildcard == false: addresses must be exactly the same, i.e. + * 0.0.0.0 only equals to 0.0.0.0 + */ +static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2, + bool match_wildcard) { struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); - return (!ipv6_only_sock(sk2) && - (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr || - inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); + if (!ipv6_only_sock(sk2)) { + if (inet1->inet_rcv_saddr == inet2->inet_rcv_saddr) + return 1; + if (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr) + return match_wildcard; + } + return 0; } static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr, @@ -441,7 +493,8 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2) + struct udp_hslot *hslot2, unsigned int slot2, + struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; @@ -459,8 +512,15 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { + struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + goto found; + } matches = 1; } } else if (score == badness && reuseport) { @@ -478,6 +538,7 @@ begin: if (get_nulls_value(node) != slot2) goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -494,7 +555,7 @@ begin: */ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, - int dif, struct udp_table *udptable) + int dif, struct udp_table *udptable, struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; @@ -514,7 +575,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); if (!result) { hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; @@ -524,7 +585,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, htonl(INADDR_ANY), hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); } rcu_read_unlock(); return result; @@ -540,8 +601,15 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { + struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + goto found; + } matches = 1; } } else if (score == badness && reuseport) { @@ -560,6 +628,7 @@ begin: goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, @@ -581,13 +650,14 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - udptable); + udptable, skb); } struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { - return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); + return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, + &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp4_lib_lookup); @@ -635,7 +705,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) struct net *net = dev_net(skb->dev); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, - iph->saddr, uh->source, skb->dev->ifindex, udptable); + iph->saddr, uh->source, skb->dev->ifindex, udptable, + NULL); if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; /* No socket for error */ @@ -772,7 +843,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, else if (skb_is_gso(skb)) uh->check = ~udp_v4_check(len, saddr, daddr, 0); else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { + (skb_dst(skb)->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); @@ -1270,6 +1342,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); + bool checksum_valid = false; bool slow; if (flags & MSG_ERRQUEUE) @@ -1295,11 +1368,12 @@ try_again: */ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + checksum_valid = !udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) + if (checksum_valid || skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), msg, copied); else { @@ -1395,6 +1469,8 @@ void udp_lib_unhash(struct sock *sk) hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock_bh(&hslot->lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); if (sk_nulls_del_node_init_rcu(sk)) { hslot->count--; inet_sk(sk)->inet_num = 0; @@ -1422,22 +1498,28 @@ void udp_lib_rehash(struct sock *sk, u16 newhash) hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; - if (hslot2 != nhslot2) { + + if (hslot2 != nhslot2 || + rcu_access_pointer(sk->sk_reuseport_cb)) { hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); - - spin_lock(&hslot2->lock); - hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); - hslot2->count--; - spin_unlock(&hslot2->lock); - - spin_lock(&nhslot2->lock); - hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, - &nhslot2->head); - nhslot2->count++; - spin_unlock(&nhslot2->lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); + + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + } spin_unlock_bh(&hslot->lock); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 6116604bf6e8f..df1966f3b6ecc 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -44,7 +44,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, - req->id.idiag_if, tbl); + req->id.idiag_if, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) sk = __udp6_lib_lookup(net, @@ -52,7 +52,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, - req->id.idiag_if, tbl); + req->id.idiag_if, tbl, NULL); #endif else goto out_nosk; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f9386160cbee0..130042660181d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -60,8 +60,9 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, /* Try to offload checksum if possible */ offload_csum = !!(need_csum && - (skb->dev->features & - (is_ipv6 ? NETIF_F_V6_CSUM : NETIF_F_V4_CSUM))); + ((skb->dev->features & NETIF_F_HW_CSUM) || + (skb->dev->features & (is_ipv6 ? + NETIF_F_IPV6_CSUM : NETIF_F_IP_CSUM)))); /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & features; diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index aba428626b529..0ec08814f37d9 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -74,10 +74,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); -int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 tos, __u8 ttl, - __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck) +void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 tos, __u8 ttl, + __be16 df, __be16 src_port, __be16 dst_port, + bool xnet, bool nocheck) { struct udphdr *uh; @@ -91,8 +91,7 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, udp_set_csum(nocheck, skb, src, dst, skb->len); - return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, - tos, ttl, df, xnet); + iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1e0c3c835a634..7b0edb37a1150 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -259,7 +259,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xfrm_dst_ifdown(dst, dev); } -static struct dst_ops xfrm4_dst_ops = { +static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, @@ -273,7 +273,7 @@ static struct dst_ops xfrm4_dst_ops = { static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .family = AF_INET, - .dst_ops = &xfrm4_dst_ops, + .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .decode_session = _decode_session4, @@ -295,7 +295,7 @@ static struct ctl_table xfrm4_policy_table[] = { { } }; -static int __net_init xfrm4_net_init(struct net *net) +static int __net_init xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -323,7 +323,7 @@ err_alloc: return -ENOMEM; } -static void __net_exit xfrm4_net_exit(struct net *net) +static void __net_exit xfrm4_net_sysctl_exit(struct net *net) { struct ctl_table *table; @@ -335,12 +335,44 @@ static void __net_exit xfrm4_net_exit(struct net *net) if (!net_eq(net, &init_net)) kfree(table); } +#else /* CONFIG_SYSCTL */ +static int inline xfrm4_net_sysctl_init(struct net *net) +{ + return 0; +} + +static void inline xfrm4_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm4_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, + sizeof(xfrm4_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); + if (ret) + return ret; + + ret = xfrm4_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); + + return ret; +} + +static void __net_exit xfrm4_net_exit(struct net *net) +{ + xfrm4_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); +} static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; -#endif static void __init xfrm4_policy_init(void) { @@ -349,13 +381,9 @@ static void __init xfrm4_policy_init(void) void __init xfrm4_init(void) { - dst_entries_init(&xfrm4_dst_ops); - xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); -#ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm4_net_ops); -#endif } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 983bb999738c4..bb7dabe2ebbf8 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -94,6 +94,7 @@ config IPV6_MIP6 config IPV6_ILA tristate "IPv6: Identifier Locator Addressing (ILA)" + depends on NETFILTER select LWTUNNEL ---help--- Support for IPv6 Identifier Locator Addressing (ILA). diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 2c900c7b7eb1c..2fbd90bf8d33d 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -34,7 +34,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o obj-$(CONFIG_IPV6_MIP6) += mip6.o -obj-$(CONFIG_IPV6_ILA) += ila.o +obj-$(CONFIG_IPV6_ILA) += ila/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_VTI) += ip6_vti.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5e9111da449d3..8697551b16a8a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -70,7 +70,7 @@ #include <net/sock.h> #include <net/snmp.h> -#include <net/af_ieee802154.h> +#include <net/6lowpan.h> #include <net/firewire.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -350,6 +350,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) setup_timer(&ndev->rs_timer, addrconf_rs_timer, (unsigned long)ndev); memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); + + if (ndev->cnf.stable_secret.initialized) + ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + else + ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64; + ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); @@ -1947,9 +1953,9 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) { - if (dev->addr_len != IEEE802154_ADDR_LEN) + if (dev->addr_len != EUI64_ADDR_LEN) return -1; - memcpy(eui, dev->dev_addr, 8); + memcpy(eui, dev->dev_addr, EUI64_ADDR_LEN); eui[0] ^= 2; return 0; } @@ -2041,7 +2047,6 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) case ARPHRD_IPGRE: return addrconf_ifid_gre(eui, dev); case ARPHRD_6LOWPAN: - case ARPHRD_IEEE802154: return addrconf_ifid_eui64(eui, dev); case ARPHRD_IEEE1394: return addrconf_ifid_ieee1394(eui, dev); @@ -2314,6 +2319,12 @@ static void manage_tempaddrs(struct inet6_dev *idev, } } +static bool is_addr_mode_generate_stable(struct inet6_dev *idev) +{ + return idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY || + idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM; +} + void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; @@ -2427,8 +2438,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; - } else if (in6_dev->addr_gen_mode == - IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + } else if (is_addr_mode_generate_stable(in6_dev) && !ipv6_generate_stable_address(&addr, 0, in6_dev)) { addr_flags |= IFA_F_STABLE_PRIVACY; @@ -2455,7 +2465,7 @@ ok: #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && !net->ipv6.devconf_all->forwarding && sllao) - addr_flags = IFA_F_OPTIMISTIC; + addr_flags |= IFA_F_OPTIMISTIC; #endif /* Do not allow to create too much of autoconfigured @@ -3028,6 +3038,17 @@ retry: return 0; } +static void ipv6_gen_mode_random_init(struct inet6_dev *idev) +{ + struct ipv6_stable_secret *s = &idev->cnf.stable_secret; + + if (s->initialized) + return; + s = &idev->cnf.stable_secret; + get_random_bytes(&s->secret, sizeof(s->secret)); + s->initialized = true; +} + static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { struct in6_addr addr; @@ -3038,13 +3059,18 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { + switch (idev->addr_gen_mode) { + case IN6_ADDR_GEN_MODE_RANDOM: + ipv6_gen_mode_random_init(idev); + /* fallthrough */ + case IN6_ADDR_GEN_MODE_STABLE_PRIVACY: if (!ipv6_generate_stable_address(&addr, 0, idev)) addrconf_add_linklocal(idev, &addr, IFA_F_STABLE_PRIVACY); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); - } else if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { + break; + case IN6_ADDR_GEN_MODE_EUI64: /* addrconf_add_linklocal also adds a prefix_route and we * only need to care about prefix routes if ipv6_generate_eui64 * couldn't generate one. @@ -3053,6 +3079,11 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + break; + case IN6_ADDR_GEN_MODE_NONE: + default: + /* will not add any link local address */ + break; } } @@ -3066,10 +3097,10 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_FDDI) && (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && - (dev->type != ARPHRD_IEEE802154) && (dev->type != ARPHRD_IEEE1394) && (dev->type != ARPHRD_TUNNEL6) && - (dev->type != ARPHRD_6LOWPAN)) { + (dev->type != ARPHRD_6LOWPAN) && + (dev->type != ARPHRD_NONE)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -3078,6 +3109,11 @@ static void addrconf_dev_config(struct net_device *dev) if (IS_ERR(idev)) return; + /* this device type has no EUI support */ + if (dev->type == ARPHRD_NONE && + idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) + idev->addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; + addrconf_addr_gen(idev, false); } @@ -4922,7 +4958,8 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) if (mode != IN6_ADDR_GEN_MODE_EUI64 && mode != IN6_ADDR_GEN_MODE_NONE && - mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY) + mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + mode != IN6_ADDR_GEN_MODE_RANDOM) return -EINVAL; if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && @@ -5378,13 +5415,10 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, goto out; } - if (!write) { - err = snprintf(str, sizeof(str), "%pI6", - &secret->secret); - if (err >= sizeof(str)) { - err = -EIO; - goto out; - } + err = snprintf(str, sizeof(str), "%pI6", &secret->secret); + if (err >= sizeof(str)) { + err = -EIO; + goto out; } err = proc_dostring(&lctl, write, buffer, lenp, ppos); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 882124ebb438b..a8f6986dcbe5e 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -552,7 +552,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) rcu_read_lock(); p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && ip6addrlbl_hold(p)) + if (p && !ip6addrlbl_hold(p)) p = NULL; lseq = ip6addrlbl_table.seq; rcu_read_unlock(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8ec0df75f1c4f..9f5137cd604e5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; diff --git a/net/ipv6/ila/Makefile b/net/ipv6/ila/Makefile new file mode 100644 index 0000000000000..4b32e5921e5ce --- /dev/null +++ b/net/ipv6/ila/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for ILA module +# + +obj-$(CONFIG_IPV6_ILA) += ila.o + +ila-objs := ila_common.o ila_lwt.o ila_xlat.o diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h new file mode 100644 index 0000000000000..28542cb2b3871 --- /dev/null +++ b/net/ipv6/ila/ila.h @@ -0,0 +1,48 @@ +/* + * Copyright (c) 2015 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + * + */ + +#ifndef __ILA_H +#define __ILA_H + +#include <linux/errno.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/socket.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ip.h> +#include <net/protocol.h> +#include <uapi/linux/ila.h> + +struct ila_params { + __be64 locator; + __be64 locator_match; + __wsum csum_diff; +}; + +static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) +{ + __be32 diff[] = { + ~from[0], ~from[1], to[0], to[1], + }; + + return csum_partial(diff, sizeof(diff), 0); +} + +void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p); + +int ila_lwt_init(void); +void ila_lwt_fini(void); +int ila_xlat_init(void); +void ila_xlat_fini(void); + +#endif /* __ILA_H */ diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c new file mode 100644 index 0000000000000..32dc9aab7297b --- /dev/null +++ b/net/ipv6/ila/ila_common.c @@ -0,0 +1,103 @@ +#include <linux/errno.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ip.h> +#include <net/ip6_fib.h> +#include <net/lwtunnel.h> +#include <net/protocol.h> +#include <uapi/linux/ila.h> +#include "ila.h" + +static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +{ + if (*(__be64 *)&ip6h->daddr == p->locator_match) + return p->csum_diff; + else + return compute_csum_diff8((__be32 *)&ip6h->daddr, + (__be32 *)&p->locator); +} + +void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) +{ + __wsum diff; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + size_t nhoff = sizeof(struct ipv6hdr); + + /* First update checksum */ + switch (ip6h->nexthdr) { + case NEXTHDR_TCP: + if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) { + struct tcphdr *th = (struct tcphdr *) + (skb_network_header(skb) + nhoff); + + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&th->check, skb, + diff, true); + } + break; + case NEXTHDR_UDP: + if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) { + struct udphdr *uh = (struct udphdr *) + (skb_network_header(skb) + nhoff); + + if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&uh->check, skb, + diff, true); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + } + break; + case NEXTHDR_ICMP: + if (likely(pskb_may_pull(skb, + nhoff + sizeof(struct icmp6hdr)))) { + struct icmp6hdr *ih = (struct icmp6hdr *) + (skb_network_header(skb) + nhoff); + + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, + diff, true); + } + break; + } + + /* Now change destination address */ + *(__be64 *)&ip6h->daddr = p->locator; +} + +static int __init ila_init(void) +{ + int ret; + + ret = ila_lwt_init(); + + if (ret) + goto fail_lwt; + + ret = ila_xlat_init(); + if (ret) + goto fail_xlat; + + return 0; +fail_xlat: + ila_lwt_fini(); +fail_lwt: + return ret; +} + +static void __exit ila_fini(void) +{ + ila_xlat_fini(); + ila_lwt_fini(); +} + +module_init(ila_init); +module_exit(ila_fini); +MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila.c b/net/ipv6/ila/ila_lwt.c index 1a6852e1ac69e..2ae3c4fd8aabc 100644 --- a/net/ipv6/ila.c +++ b/net/ipv6/ila/ila_lwt.c @@ -11,12 +11,7 @@ #include <net/lwtunnel.h> #include <net/protocol.h> #include <uapi/linux/ila.h> - -struct ila_params { - __be64 locator; - __be64 locator_match; - __wsum csum_diff; -}; +#include "ila.h" static inline struct ila_params *ila_params_lwtunnel( struct lwtunnel_state *lwstate) @@ -24,73 +19,6 @@ static inline struct ila_params *ila_params_lwtunnel( return (struct ila_params *)lwstate->data; } -static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) -{ - __be32 diff[] = { - ~from[0], ~from[1], to[0], to[1], - }; - - return csum_partial(diff, sizeof(diff), 0); -} - -static inline __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) -{ - if (*(__be64 *)&ip6h->daddr == p->locator_match) - return p->csum_diff; - else - return compute_csum_diff8((__be32 *)&ip6h->daddr, - (__be32 *)&p->locator); -} - -static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) -{ - __wsum diff; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - size_t nhoff = sizeof(struct ipv6hdr); - - /* First update checksum */ - switch (ip6h->nexthdr) { - case NEXTHDR_TCP: - if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) { - struct tcphdr *th = (struct tcphdr *) - (skb_network_header(skb) + nhoff); - - diff = get_csum_diff(ip6h, p); - inet_proto_csum_replace_by_diff(&th->check, skb, - diff, true); - } - break; - case NEXTHDR_UDP: - if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) { - struct udphdr *uh = (struct udphdr *) - (skb_network_header(skb) + nhoff); - - if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { - diff = get_csum_diff(ip6h, p); - inet_proto_csum_replace_by_diff(&uh->check, skb, - diff, true); - if (!uh->check) - uh->check = CSUM_MANGLED_0; - } - } - break; - case NEXTHDR_ICMP: - if (likely(pskb_may_pull(skb, - nhoff + sizeof(struct icmp6hdr)))) { - struct icmp6hdr *ih = (struct icmp6hdr *) - (skb_network_header(skb) + nhoff); - - diff = get_csum_diff(ip6h, p); - inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, - diff, true); - } - break; - } - - /* Now change destination address */ - *(__be64 *)&ip6h->daddr = p->locator; -} - static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -213,17 +141,12 @@ static const struct lwtunnel_encap_ops ila_encap_ops = { .cmp_encap = ila_encap_cmp, }; -static int __init ila_init(void) +int ila_lwt_init(void) { return lwtunnel_encap_add_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); } -static void __exit ila_fini(void) +void ila_lwt_fini(void) { lwtunnel_encap_del_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); } - -module_init(ila_init); -module_exit(ila_fini); -MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); -MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c new file mode 100644 index 0000000000000..295ca29a23c3a --- /dev/null +++ b/net/ipv6/ila/ila_xlat.c @@ -0,0 +1,680 @@ +#include <linux/jhash.h> +#include <linux/netfilter.h> +#include <linux/rcupdate.h> +#include <linux/rhashtable.h> +#include <linux/vmalloc.h> +#include <net/genetlink.h> +#include <net/ila.h> +#include <net/netns/generic.h> +#include <uapi/linux/genetlink.h> +#include "ila.h" + +struct ila_xlat_params { + struct ila_params ip; + __be64 identifier; + int ifindex; + unsigned int dir; +}; + +struct ila_map { + struct ila_xlat_params p; + struct rhash_head node; + struct ila_map __rcu *next; + struct rcu_head rcu; +}; + +static unsigned int ila_net_id; + +struct ila_net { + struct rhashtable rhash_table; + spinlock_t *locks; /* Bucket locks for entry manipulation */ + unsigned int locks_mask; + bool hooks_registered; +}; + +#define LOCKS_PER_CPU 10 + +static int alloc_ila_locks(struct ila_net *ilan) +{ + unsigned int i, size; + unsigned int nr_pcpus = num_possible_cpus(); + + nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); + size = roundup_pow_of_two(nr_pcpus * LOCKS_PER_CPU); + + if (sizeof(spinlock_t) != 0) { +#ifdef CONFIG_NUMA + if (size * sizeof(spinlock_t) > PAGE_SIZE) + ilan->locks = vmalloc(size * sizeof(spinlock_t)); + else +#endif + ilan->locks = kmalloc_array(size, sizeof(spinlock_t), + GFP_KERNEL); + if (!ilan->locks) + return -ENOMEM; + for (i = 0; i < size; i++) + spin_lock_init(&ilan->locks[i]); + } + ilan->locks_mask = size - 1; + + return 0; +} + +static u32 hashrnd __read_mostly; +static __always_inline void __ila_hash_secret_init(void) +{ + net_get_random_once(&hashrnd, sizeof(hashrnd)); +} + +static inline u32 ila_identifier_hash(__be64 identifier) +{ + u32 *v = (u32 *)&identifier; + + return jhash_2words(v[0], v[1], hashrnd); +} + +static inline spinlock_t *ila_get_lock(struct ila_net *ilan, __be64 identifier) +{ + return &ilan->locks[ila_identifier_hash(identifier) & ilan->locks_mask]; +} + +static inline int ila_cmp_wildcards(struct ila_map *ila, __be64 loc, + int ifindex, unsigned int dir) +{ + return (ila->p.ip.locator_match && ila->p.ip.locator_match != loc) || + (ila->p.ifindex && ila->p.ifindex != ifindex) || + !(ila->p.dir & dir); +} + +static inline int ila_cmp_params(struct ila_map *ila, struct ila_xlat_params *p) +{ + return (ila->p.ip.locator_match != p->ip.locator_match) || + (ila->p.ifindex != p->ifindex) || + (ila->p.dir != p->dir); +} + +static int ila_cmpfn(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct ila_map *ila = obj; + + return (ila->p.identifier != *(__be64 *)arg->key); +} + +static inline int ila_order(struct ila_map *ila) +{ + int score = 0; + + if (ila->p.ip.locator_match) + score += 1 << 0; + + if (ila->p.ifindex) + score += 1 << 1; + + return score; +} + +static const struct rhashtable_params rht_params = { + .nelem_hint = 1024, + .head_offset = offsetof(struct ila_map, node), + .key_offset = offsetof(struct ila_map, p.identifier), + .key_len = sizeof(u64), /* identifier */ + .max_size = 1048576, + .min_size = 256, + .automatic_shrinking = true, + .obj_cmpfn = ila_cmpfn, +}; + +static struct genl_family ila_nl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = ILA_GENL_NAME, + .version = ILA_GENL_VERSION, + .maxattr = ILA_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, +}; + +static struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { + [ILA_ATTR_IDENTIFIER] = { .type = NLA_U64, }, + [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, + [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, + [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, + [ILA_ATTR_DIR] = { .type = NLA_U32, }, +}; + +static int parse_nl_config(struct genl_info *info, + struct ila_xlat_params *p) +{ + memset(p, 0, sizeof(*p)); + + if (info->attrs[ILA_ATTR_IDENTIFIER]) + p->identifier = (__force __be64)nla_get_u64( + info->attrs[ILA_ATTR_IDENTIFIER]); + + if (info->attrs[ILA_ATTR_LOCATOR]) + p->ip.locator = (__force __be64)nla_get_u64( + info->attrs[ILA_ATTR_LOCATOR]); + + if (info->attrs[ILA_ATTR_LOCATOR_MATCH]) + p->ip.locator_match = (__force __be64)nla_get_u64( + info->attrs[ILA_ATTR_LOCATOR_MATCH]); + + if (info->attrs[ILA_ATTR_IFINDEX]) + p->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); + + if (info->attrs[ILA_ATTR_DIR]) + p->dir = nla_get_u32(info->attrs[ILA_ATTR_DIR]); + + return 0; +} + +/* Must be called with rcu readlock */ +static inline struct ila_map *ila_lookup_wildcards(__be64 id, __be64 loc, + int ifindex, + unsigned int dir, + struct ila_net *ilan) +{ + struct ila_map *ila; + + ila = rhashtable_lookup_fast(&ilan->rhash_table, &id, rht_params); + while (ila) { + if (!ila_cmp_wildcards(ila, loc, ifindex, dir)) + return ila; + ila = rcu_access_pointer(ila->next); + } + + return NULL; +} + +/* Must be called with rcu readlock */ +static inline struct ila_map *ila_lookup_by_params(struct ila_xlat_params *p, + struct ila_net *ilan) +{ + struct ila_map *ila; + + ila = rhashtable_lookup_fast(&ilan->rhash_table, &p->identifier, + rht_params); + while (ila) { + if (!ila_cmp_params(ila, p)) + return ila; + ila = rcu_access_pointer(ila->next); + } + + return NULL; +} + +static inline void ila_release(struct ila_map *ila) +{ + kfree_rcu(ila, rcu); +} + +static void ila_free_cb(void *ptr, void *arg) +{ + struct ila_map *ila = (struct ila_map *)ptr, *next; + + /* Assume rcu_readlock held */ + while (ila) { + next = rcu_access_pointer(ila->next); + ila_release(ila); + ila = next; + } +} + +static int ila_xlat_addr(struct sk_buff *skb, int dir); + +static unsigned int +ila_nf_input(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + ila_xlat_addr(skb, ILA_DIR_IN); + return NF_ACCEPT; +} + +static struct nf_hook_ops ila_nf_hook_ops[] __read_mostly = { + { + .hook = ila_nf_input, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = -1, + }, +}; + +static int ila_add_mapping(struct net *net, struct ila_xlat_params *p) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + struct ila_map *ila, *head; + spinlock_t *lock = ila_get_lock(ilan, p->identifier); + int err = 0, order; + + if (!ilan->hooks_registered) { + /* We defer registering net hooks in the namespace until the + * first mapping is added. + */ + err = nf_register_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); + if (err) + return err; + + ilan->hooks_registered = true; + } + + ila = kzalloc(sizeof(*ila), GFP_KERNEL); + if (!ila) + return -ENOMEM; + + ila->p = *p; + + if (p->ip.locator_match) { + /* Precompute checksum difference for translation since we + * know both the old identifier and the new one. + */ + ila->p.ip.csum_diff = compute_csum_diff8( + (__be32 *)&p->ip.locator_match, + (__be32 *)&p->ip.locator); + } + + order = ila_order(ila); + + spin_lock(lock); + + head = rhashtable_lookup_fast(&ilan->rhash_table, &p->identifier, + rht_params); + if (!head) { + /* New entry for the rhash_table */ + err = rhashtable_lookup_insert_fast(&ilan->rhash_table, + &ila->node, rht_params); + } else { + struct ila_map *tila = head, *prev = NULL; + + do { + if (!ila_cmp_params(tila, p)) { + err = -EEXIST; + goto out; + } + + if (order > ila_order(tila)) + break; + + prev = tila; + tila = rcu_dereference_protected(tila->next, + lockdep_is_held(lock)); + } while (tila); + + if (prev) { + /* Insert in sub list of head */ + RCU_INIT_POINTER(ila->next, tila); + rcu_assign_pointer(prev->next, ila); + } else { + /* Make this ila new head */ + RCU_INIT_POINTER(ila->next, head); + err = rhashtable_replace_fast(&ilan->rhash_table, + &head->node, + &ila->node, rht_params); + if (err) + goto out; + } + } + +out: + spin_unlock(lock); + + if (err) + kfree(ila); + + return err; +} + +static int ila_del_mapping(struct net *net, struct ila_xlat_params *p) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + struct ila_map *ila, *head, *prev; + spinlock_t *lock = ila_get_lock(ilan, p->identifier); + int err = -ENOENT; + + spin_lock(lock); + + head = rhashtable_lookup_fast(&ilan->rhash_table, + &p->identifier, rht_params); + ila = head; + + prev = NULL; + + while (ila) { + if (ila_cmp_params(ila, p)) { + prev = ila; + ila = rcu_dereference_protected(ila->next, + lockdep_is_held(lock)); + continue; + } + + err = 0; + + if (prev) { + /* Not head, just delete from list */ + rcu_assign_pointer(prev->next, ila->next); + } else { + /* It is the head. If there is something in the + * sublist we need to make a new head. + */ + head = rcu_dereference_protected(ila->next, + lockdep_is_held(lock)); + if (head) { + /* Put first entry in the sublist into the + * table + */ + err = rhashtable_replace_fast( + &ilan->rhash_table, &ila->node, + &head->node, rht_params); + if (err) + goto out; + } else { + /* Entry no longer used */ + err = rhashtable_remove_fast(&ilan->rhash_table, + &ila->node, + rht_params); + } + } + + ila_release(ila); + + break; + } + +out: + spin_unlock(lock); + + return err; +} + +static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_xlat_params p; + int err; + + err = parse_nl_config(info, &p); + if (err) + return err; + + return ila_add_mapping(net, &p); +} + +static int ila_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_xlat_params p; + int err; + + err = parse_nl_config(info, &p); + if (err) + return err; + + ila_del_mapping(net, &p); + + return 0; +} + +static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) +{ + if (nla_put_u64(msg, ILA_ATTR_IDENTIFIER, + (__force u64)ila->p.identifier) || + nla_put_u64(msg, ILA_ATTR_LOCATOR, + (__force u64)ila->p.ip.locator) || + nla_put_u64(msg, ILA_ATTR_LOCATOR_MATCH, + (__force u64)ila->p.ip.locator_match) || + nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->p.ifindex) || + nla_put_u32(msg, ILA_ATTR_DIR, ila->p.dir)) + return -1; + + return 0; +} + +static int ila_dump_info(struct ila_map *ila, + u32 portid, u32 seq, u32 flags, + struct sk_buff *skb, u8 cmd) +{ + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &ila_nl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + if (ila_fill_info(ila, skb) < 0) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ila_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_net *ilan = net_generic(net, ila_net_id); + struct sk_buff *msg; + struct ila_xlat_params p; + struct ila_map *ila; + int ret; + + ret = parse_nl_config(info, &p); + if (ret) + return ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rcu_read_lock(); + + ila = ila_lookup_by_params(&p, ilan); + if (ila) { + ret = ila_dump_info(ila, + info->snd_portid, + info->snd_seq, 0, msg, + info->genlhdr->cmd); + } + + rcu_read_unlock(); + + if (ret < 0) + goto out_free; + + return genlmsg_reply(msg, info); + +out_free: + nlmsg_free(msg); + return ret; +} + +struct ila_dump_iter { + struct rhashtable_iter rhiter; +}; + +static int ila_nl_dump_start(struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct ila_net *ilan = net_generic(net, ila_net_id); + struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; + + return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter); +} + +static int ila_nl_dump_done(struct netlink_callback *cb) +{ + struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; + + rhashtable_walk_exit(&iter->rhiter); + + return 0; +} + +static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; + struct rhashtable_iter *rhiter = &iter->rhiter; + struct ila_map *ila; + int ret; + + ret = rhashtable_walk_start(rhiter); + if (ret && ret != -EAGAIN) + goto done; + + for (;;) { + ila = rhashtable_walk_next(rhiter); + + if (IS_ERR(ila)) { + if (PTR_ERR(ila) == -EAGAIN) + continue; + ret = PTR_ERR(ila); + goto done; + } else if (!ila) { + break; + } + + while (ila) { + ret = ila_dump_info(ila, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, ILA_CMD_GET); + if (ret) + goto done; + + ila = rcu_access_pointer(ila->next); + } + } + + ret = skb->len; + +done: + rhashtable_walk_stop(rhiter); + return ret; +} + +static const struct genl_ops ila_nl_ops[] = { + { + .cmd = ILA_CMD_ADD, + .doit = ila_nl_cmd_add_mapping, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_DEL, + .doit = ila_nl_cmd_del_mapping, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_GET, + .doit = ila_nl_cmd_get_mapping, + .start = ila_nl_dump_start, + .dumpit = ila_nl_dump, + .done = ila_nl_dump_done, + .policy = ila_nl_policy, + }, +}; + +#define ILA_HASH_TABLE_SIZE 1024 + +static __net_init int ila_init_net(struct net *net) +{ + int err; + struct ila_net *ilan = net_generic(net, ila_net_id); + + err = alloc_ila_locks(ilan); + if (err) + return err; + + rhashtable_init(&ilan->rhash_table, &rht_params); + + return 0; +} + +static __net_exit void ila_exit_net(struct net *net) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + + rhashtable_free_and_destroy(&ilan->rhash_table, ila_free_cb, NULL); + + kvfree(ilan->locks); + + if (ilan->hooks_registered) + nf_unregister_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); +} + +static struct pernet_operations ila_net_ops = { + .init = ila_init_net, + .exit = ila_exit_net, + .id = &ila_net_id, + .size = sizeof(struct ila_net), +}; + +static int ila_xlat_addr(struct sk_buff *skb, int dir) +{ + struct ila_map *ila; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ila_net *ilan = net_generic(net, ila_net_id); + __be64 identifier, locator_match; + size_t nhoff; + + /* Assumes skb contains a valid IPv6 header that is pulled */ + + identifier = *(__be64 *)&ip6h->daddr.in6_u.u6_addr8[8]; + locator_match = *(__be64 *)&ip6h->daddr.in6_u.u6_addr8[0]; + nhoff = sizeof(struct ipv6hdr); + + rcu_read_lock(); + + ila = ila_lookup_wildcards(identifier, locator_match, + skb->dev->ifindex, dir, ilan); + if (ila) + update_ipv6_locator(skb, &ila->p.ip); + + rcu_read_unlock(); + + return 0; +} + +int ila_xlat_incoming(struct sk_buff *skb) +{ + return ila_xlat_addr(skb, ILA_DIR_IN); +} +EXPORT_SYMBOL(ila_xlat_incoming); + +int ila_xlat_outgoing(struct sk_buff *skb) +{ + return ila_xlat_addr(skb, ILA_DIR_OUT); +} +EXPORT_SYMBOL(ila_xlat_outgoing); + +int ila_xlat_init(void) +{ + int ret; + + ret = register_pernet_device(&ila_net_ops); + if (ret) + goto exit; + + ret = genl_register_family_with_ops(&ila_nl_family, + ila_nl_ops); + if (ret < 0) + goto unregister; + + return 0; + +unregister: + unregister_pernet_device(&ila_net_ops); +exit: + return ret; +} + +void ila_xlat_fini(void) +{ + genl_unregister_family(&ila_nl_family); + unregister_pernet_device(&ila_net_ops); +} diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index a7ca2cde2ecbc..36c3f0155010b 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -51,12 +51,12 @@ int inet6_csk_bind_conflict(const struct sock *sk, (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid((struct sock *)sk2))))) { - if (ipv6_rcv_saddr_equal(sk, sk2)) + if (ipv6_rcv_saddr_equal(sk, sk2, true)) break; } if (!relax && reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN && - ipv6_rcv_saddr_equal(sk, sk2)) + ipv6_rcv_saddr_equal(sk, sk2, true)) break; } } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 938d03ce5e4b7..f37f18b6b40c9 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1570,13 +1570,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return -EEXIST; } else { t = nt; - - ip6gre_tunnel_unlink(ign, t); - ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); - ip6gre_tunnel_link(ign, t); - netdev_state_change(dev); } + ip6gre_tunnel_unlink(ign, t); + ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6gre_tunnel_link(ign, t); return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e6a7bd15b9b71..2f748452b4aaa 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1322,7 +1322,7 @@ emsgsize: headersize == sizeof(struct ipv6hdr) && length < mtu - headersize && !(flags & MSG_MORE) && - rt->dst.dev->features & NETIF_F_V6_CSUM) + rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d6161e1c48c86..84afb9a772784 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1183,7 +1183,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) */ if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, - NULL, 0)) { + in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); @@ -1337,7 +1337,7 @@ skip_linkparms: #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, - NULL, 0)) { + in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index f6a024e141e59..e10a04c9cdc7b 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -49,6 +49,7 @@ config NFT_REJECT_IPV6 config NFT_DUP_IPV6 tristate "IPv6 nf_tables packet duplication support" + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV6 help This module enables IPv6 packet duplication support for nf_tables. diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index bab4441ed4e43..e4347aeb2e653 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -56,7 +56,6 @@ struct nf_ct_frag6_skb_cb { struct inet6_skb_parm h; int offset; - struct sk_buff *orig; }; #define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb)) @@ -170,12 +169,6 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q) return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } -static void nf_skb_free(struct sk_buff *skb) -{ - if (NFCT_FRAG6_CB(skb)->orig) - kfree_skb(NFCT_FRAG6_CB(skb)->orig); -} - static void nf_ct_frag6_expire(unsigned long data) { struct frag_queue *fq; @@ -369,17 +362,18 @@ err: /* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. + * + * returns true if *prev skb has been transformed into the reassembled + * skb, false otherwise. */ -static struct sk_buff * -nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) +static bool +nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) { - struct sk_buff *fp, *op, *head = fq->q.fragments; + struct sk_buff *fp, *head = fq->q.fragments; int payload_len; u8 ecn; @@ -390,22 +384,21 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) - goto out_fail; + return false; /* Unfragmented part is taken from the first segment. */ payload_len = ((head->data - skb_network_header(head)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) { - pr_debug("payload len is too large.\n"); - goto out_oversize; + net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", + payload_len); + return false; } /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) { - pr_debug("skb is cloned but can't expand head"); - goto out_oom; - } + if (skb_unclone(head, GFP_ATOMIC)) + return false; /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part @@ -416,7 +409,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone = alloc_skb(0, GFP_ATOMIC); if (clone == NULL) - goto out_oom; + return false; clone->next = head->next; head->next = clone; @@ -430,10 +423,41 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->csum = 0; clone->ip_summed = head->ip_summed; - NFCT_FRAG6_CB(clone)->orig = NULL; add_frag_mem_limit(fq->q.net, clone->truesize); } + /* morph head into last received skb: prev. + * + * This allows callers of ipv6 conntrack defrag to continue + * to use the last skb(frag) passed into the reasm engine. + * The last skb frag 'silently' turns into the full reassembled skb. + * + * Since prev is also part of q->fragments we have to clone it first. + */ + if (head != prev) { + struct sk_buff *iter; + + fp = skb_clone(prev, GFP_ATOMIC); + if (!fp) + return false; + + fp->next = prev->next; + + iter = head; + while (iter) { + if (iter->next == prev) { + iter->next = fp; + break; + } + iter = iter->next; + } + + skb_morph(prev, head); + prev->next = head->next; + consume_skb(head); + head = prev; + } + /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; @@ -474,31 +498,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) fq->q.fragments = NULL; fq->q.fragments_tail = NULL; - /* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */ - fp = skb_shinfo(head)->frag_list; - if (fp && NFCT_FRAG6_CB(fp)->orig == NULL) - /* at above code, head skb is divided into two skbs. */ - fp = fp->next; - - op = NFCT_FRAG6_CB(head)->orig; - for (; fp; fp = fp->next) { - struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig; - - op->next = orig; - op = orig; - NFCT_FRAG6_CB(fp)->orig = NULL; - } - - return head; - -out_oversize: - net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", - payload_len); - goto out_fail; -out_oom: - net_dbg_ratelimited("nf_ct_frag6_reasm: no memory for reassembly\n"); -out_fail: - return NULL; + return true; } /* @@ -564,89 +564,61 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) +int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { - struct sk_buff *clone; struct net_device *dev = skb->dev; + int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; - int fhoff, nhoff; u8 prevhdr; - struct sk_buff *ret_skb = NULL; /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); - return skb; + return -EINVAL; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) - return skb; + return -EINVAL; - clone = skb_clone(skb, GFP_ATOMIC); - if (clone == NULL) { - pr_debug("Can't clone skb\n"); - return skb; - } + if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) + return -ENOMEM; - NFCT_FRAG6_CB(clone)->orig = skb; - - if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) { - pr_debug("message is too short.\n"); - goto ret_orig; - } - - skb_set_transport_header(clone, fhoff); - hdr = ipv6_hdr(clone); - fhdr = (struct frag_hdr *)skb_transport_header(clone); + skb_set_transport_header(skb, fhoff); + hdr = ipv6_hdr(skb); + fhdr = (struct frag_hdr *)skb_transport_header(skb); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); - goto ret_orig; + return -ENOMEM; } spin_lock_bh(&fq->q.lock); - if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) { - spin_unlock_bh(&fq->q.lock); - pr_debug("Can't insert skb to queue\n"); - inet_frag_put(&fq->q, &nf_frags); - goto ret_orig; + if (nf_ct_frag6_queue(fq, skb, fhdr, nhoff) < 0) { + ret = -EINVAL; + goto out_unlock; } + /* after queue has assumed skb ownership, only 0 or -EINPROGRESS + * must be returned. + */ + ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) { - ret_skb = nf_ct_frag6_reasm(fq, dev); - if (ret_skb == NULL) - pr_debug("Can't reassemble fragmented packets\n"); - } - spin_unlock_bh(&fq->q.lock); + fq->q.meat == fq->q.len && + nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; +out_unlock: + spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q, &nf_frags); - return ret_skb; - -ret_orig: - kfree_skb(clone); - return skb; + return ret; } EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); -void nf_ct_frag6_consume_orig(struct sk_buff *skb) -{ - struct sk_buff *s, *s2; - - for (s = NFCT_FRAG6_CB(skb)->orig; s;) { - s2 = s->next; - s->next = NULL; - consume_skb(s); - s = s2; - } -} -EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig); - static int nf_ct_net_init(struct net *net) { int res; @@ -681,7 +653,6 @@ int nf_ct_frag6_init(void) nf_frags.hashfn = nf_hashfn; nf_frags.constructor = ip6_frag_init; nf_frags.destructor = NULL; - nf_frags.skb_free = nf_skb_free; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 4fdbed5ebfb6b..f7aab5ab93a55 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -55,7 +55,7 @@ static unsigned int ipv6_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - struct sk_buff *reasm; + int err; #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Previously seen (loopback)? */ @@ -63,23 +63,13 @@ static unsigned int ipv6_defrag(void *priv, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(state->net, skb, - nf_ct6_defrag_user(state->hook, skb)); + err = nf_ct_frag6_gather(state->net, skb, + nf_ct6_defrag_user(state->hook, skb)); /* queued */ - if (reasm == NULL) + if (err == -EINPROGRESS) return NF_STOLEN; - /* error occurred or not fragmented */ - if (reasm == skb) - return NF_ACCEPT; - - nf_ct_frag6_consume_orig(reasm); - - NF_HOOK_THRESH(NFPROTO_IPV6, state->hook, state->net, state->sk, reasm, - state->in, state->out, - state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); - - return NF_STOLEN; + return NF_ACCEPT; } static struct nf_hook_ops ipv6_defrag_ops[] = { diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 238e70c3f7b7b..6ce3099288416 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -136,7 +136,8 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt6i_flags & RTF_LOCAL) && - (!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) { + (!skb->dev || skb->dev->features & + (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index e0f922b777e3d..4709f657b7b6b 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -14,7 +14,6 @@ #include <net/netfilter/ipv6/nf_reject.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> -#include <net/netfilter/ipv6/nf_reject.h> const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *otcph, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 99140986e8871..fa59dd7a427e8 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -972,6 +972,11 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, return -EFAULT; switch (optname) { + case IPV6_HDRINCL: + if (sk->sk_type != SOCK_RAW) + return -EINVAL; + inet_sk(sk)->hdrincl = !!val; + return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { @@ -1016,7 +1021,8 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1037,7 +1043,8 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return compat_ipv6_setsockopt(sk, level, optname, @@ -1057,6 +1064,9 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; switch (optname) { + case IPV6_HDRINCL: + val = inet_sk(sk)->hdrincl; + break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level @@ -1094,7 +1104,8 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); @@ -1115,7 +1126,8 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return compat_ipv6_getsockopt(sk, level, optname, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 45f5ae51de65c..18f3498a6c805 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -755,7 +755,6 @@ int __init ipv6_frag_init(void) ip6_frags.hashfn = ip6_hashfn; ip6_frags.constructor = ip6_frag_init; ip6_frags.destructor = NULL; - ip6_frags.skb_free = NULL; ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.match = ip6_frag_match; ip6_frags.frag_expire = ip6_frag_expire; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c83b6a5b3604d..3c8834bc822d2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2709,6 +2709,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, + [RTA_EXPIRES] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2809,6 +2810,15 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP_TYPE]) cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + if (tb[RTA_EXPIRES]) { + unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); + + if (addrconf_finite_timeout(timeout)) { + cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); + cfg->fc_flags |= RTF_EXPIRES; + } + } + err = 0; errout: return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index dcccae86190f2..e794ef66a4013 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -820,7 +820,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, const struct in6_addr *addr6; int addr_type; u8 ttl; - int err; u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); @@ -983,10 +982,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, IPPROTO_IPV6); - err = iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, - protocol, tos, ttl, df, - !net_eq(tunnel->net, dev_net(dev))); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, + df, !net_eq(tunnel->net, dev_net(dev))); return NETDEV_TX_OK; tx_error_icmp: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index eaf7ac496d506..2906ef20795e4 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -193,7 +193,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->pktopts = skb; } - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) @@ -224,7 +224,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_oif = ireq->ir_iif; fl6.flowi6_mark = ireq->ir_mark; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c16e3fbf68547..9ecb012291cf1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { + if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); @@ -855,7 +854,9 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (!sk && hash_location) { + if (sk && sk_fullsock(sk)) { + key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr); + } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -878,8 +879,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; - } else { - key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL; } #endif @@ -1517,7 +1516,9 @@ do_time_wait: break; case TCP_TW_RST: tcp_v6_restore_cb(skb); - goto no_tcp_socket; + tcp_v6_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; case TCP_TW_SUCCESS: ; } @@ -1890,6 +1891,7 @@ struct proto tcpv6_prot = { .proto_cgroup = tcp_proto_cgroup, #endif .clear_sk = tcp_v6_clear_sk, + .diag_destroy = tcp_abort, }; static const struct inet6_protocol tcpv6_protocol = { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9da3287a39237..5d2c2afffe7b2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -47,6 +47,7 @@ #include <net/xfrm.h> #include <net/inet6_hashtables.h> #include <net/busy_poll.h> +#include <net/sock_reuseport.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -76,7 +77,14 @@ static u32 udp6_ehashfn(const struct net *net, udp_ipv6_hash_secret + net_hash_mix(net)); } -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) +/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 + * only, and any IPv4 addresses if not IPv6 only + * match_wildcard == false: addresses must be exactly the same, i.e. + * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, + * and 0.0.0.0 equals to 0.0.0.0 only + */ +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard) { const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); int sk2_ipv6only = inet_v6_ipv6only(sk2); @@ -84,16 +92,24 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) - return (!sk2_ipv6only && - (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr || - sk->sk_rcv_saddr == sk2->sk_rcv_saddr)); + if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { + if (!sk2_ipv6only) { + if (sk->sk_rcv_saddr == sk2->sk_rcv_saddr) + return 1; + if (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr) + return match_wildcard; + } + return 0; + } - if (addr_type2 == IPV6_ADDR_ANY && + if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) + return 1; + + if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return 1; - if (addr_type == IPV6_ADDR_ANY && + if (addr_type == IPV6_ADDR_ANY && match_wildcard && !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) return 1; @@ -235,7 +251,8 @@ static inline int compute_score2(struct sock *sk, struct net *net, static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2) + struct udp_hslot *hslot2, unsigned int slot2, + struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; @@ -253,8 +270,15 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { + struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + goto found; + } matches = 1; } } else if (score == badness && reuseport) { @@ -273,6 +297,7 @@ begin: goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -287,7 +312,8 @@ begin: struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *udptable) + int dif, struct udp_table *udptable, + struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; @@ -307,7 +333,7 @@ struct sock *__udp6_lib_lookup(struct net *net, result = udp6_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); if (!result) { hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); slot2 = hash2 & udptable->mask; @@ -317,7 +343,7 @@ struct sock *__udp6_lib_lookup(struct net *net, result = udp6_lib_lookup2(net, saddr, sport, &in6addr_any, hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); } rcu_read_unlock(); return result; @@ -332,8 +358,15 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { + struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + goto found; + } matches = 1; } } else if (score == badness && reuseport) { @@ -352,6 +385,7 @@ begin: goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score(result, net, hnum, saddr, sport, @@ -377,13 +411,13 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, return sk; return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - udptable); + udptable, skb); } struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { - return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); + return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp6_lib_lookup); @@ -402,6 +436,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); + bool checksum_valid = false; int is_udp4; bool slow; @@ -433,11 +468,12 @@ try_again: */ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + checksum_valid = !udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) + if (checksum_valid || skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), msg, copied); else { @@ -547,8 +583,8 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int err; struct net *net = dev_net(skb->dev); - sk = __udp6_lib_lookup(net, daddr, uh->dest, - saddr, uh->source, inet6_iif(skb), udptable); + sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, + inet6_iif(skb), udptable, skb); if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 5643423fe67a2..c074771a10f76 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -279,7 +279,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xfrm_dst_ifdown(dst, dev); } -static struct dst_ops xfrm6_dst_ops = { +static struct dst_ops xfrm6_dst_ops_template = { .family = AF_INET6, .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, @@ -293,7 +293,7 @@ static struct dst_ops xfrm6_dst_ops = { static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .family = AF_INET6, - .dst_ops = &xfrm6_dst_ops, + .dst_ops = &xfrm6_dst_ops_template, .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, @@ -325,7 +325,7 @@ static struct ctl_table xfrm6_policy_table[] = { { } }; -static int __net_init xfrm6_net_init(struct net *net) +static int __net_init xfrm6_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -353,7 +353,7 @@ err_alloc: return -ENOMEM; } -static void __net_exit xfrm6_net_exit(struct net *net) +static void __net_exit xfrm6_net_sysctl_exit(struct net *net) { struct ctl_table *table; @@ -365,24 +365,52 @@ static void __net_exit xfrm6_net_exit(struct net *net) if (!net_eq(net, &init_net)) kfree(table); } +#else /* CONFIG_SYSCTL */ +static int inline xfrm6_net_sysctl_init(struct net *net) +{ + return 0; +} + +static void inline xfrm6_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm6_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template, + sizeof(xfrm6_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops); + if (ret) + return ret; + + ret = xfrm6_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); + + return ret; +} + +static void __net_exit xfrm6_net_exit(struct net *net) +{ + xfrm6_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); +} static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, }; -#endif int __init xfrm6_init(void) { int ret; - dst_entries_init(&xfrm6_dst_ops); - ret = xfrm6_policy_init(); - if (ret) { - dst_entries_destroy(&xfrm6_dst_ops); + if (ret) goto out; - } ret = xfrm6_state_init(); if (ret) goto out_policy; @@ -391,9 +419,7 @@ int __init xfrm6_init(void) if (ret) goto out_state; -#ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm6_net_ops); -#endif out: return ret; out_state: @@ -405,11 +431,8 @@ out_policy: void xfrm6_fini(void) { -#ifdef CONFIG_SYSCTL unregister_pernet_subsys(&xfrm6_net_ops); -#endif xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); - dst_entries_destroy(&xfrm6_dst_ops); } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index e6aa48b5395c6..923abd6b30640 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1086,6 +1086,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; struct irda_sock *self; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (net != &init_net) return -EAFNOSUPPORT; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 3ea4c98d94dce..ef50a94d3eb72 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1031,7 +1031,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); struct sk_buff *skb; - struct iucv_message txmsg; + struct iucv_message txmsg = {0}; struct cmsghdr *cmsg; int cmsg_done; long timeo; @@ -2084,11 +2084,7 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) return NET_RX_SUCCESS; } - /* write stuff from iucv_msg to skb cb */ - if (skb->len < sizeof(struct af_iucv_trans_hdr)) { - kfree_skb(skb); - return NET_RX_SUCCESS; - } + /* write stuff from iucv_msg to skb cb */ skb_pull(skb, sizeof(struct af_iucv_trans_hdr)); skb_reset_transport_header(skb); skb_reset_network_header(skb); @@ -2119,6 +2115,20 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, char nullstring[8]; int err = 0; + if (skb->len < (ETH_HLEN + sizeof(struct af_iucv_trans_hdr))) { + WARN_ONCE(1, "AF_IUCV too short skb, len=%d, min=%d", + (int)skb->len, + (int)(ETH_HLEN + sizeof(struct af_iucv_trans_hdr))); + kfree_skb(skb); + return NET_RX_SUCCESS; + } + if (skb_headlen(skb) < (ETH_HLEN + sizeof(struct af_iucv_trans_hdr))) + if (skb_linearize(skb)) { + WARN_ONCE(1, "AF_IUCV skb_linearize failed, len=%d", + (int)skb->len); + kfree_skb(skb); + return NET_RX_SUCCESS; + } skb_pull(skb, ETH_HLEN); trans_hdr = (struct af_iucv_trans_hdr *)skb->data; EBCASC(trans_hdr->destAppName, sizeof(trans_hdr->destAppName)); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index d93f113cb522a..652c250b9a3b8 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -230,26 +230,11 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; + l2tp_dbg(session, PPPOL2TP_MSG_DATA, "%s: recv %d byte data frame, passing to ppp\n", session->name, data_len); - /* We need to forget all info related to the L2TP packet - * gathered in the skb as we are going to reuse the same - * skb for the inner packet. - * Namely we need to: - * - reset xfrm (IPSec) information as it applies to - * the outer L2TP packet and not to the inner one - * - release the dst to force a route lookup on the inner - * IP packet since skb->dst currently points to the dst - * of the UDP tunnel - * - reset netfilter information as it doesn't apply - * to the inner packet either - */ - secpath_reset(skb); - skb_dst_drop(skb); - nf_reset(skb); - po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2d1c4c35186d2..166a29fe6c35f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1169,8 +1169,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, * rc isn't initialized here yet, so ignore it */ __ieee80211_vht_handle_opmode(sdata, sta, - params->opmode_notif, - band, false); + params->opmode_notif, band); } if (ieee80211_vif_is_mesh(&sdata->vif)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c30b6842ed9f9..b84f6aa32c083 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1716,10 +1716,10 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta); void ieee80211_sta_set_rx_nss(struct sta_info *sta); u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only); + enum ieee80211_band band); void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only); + enum ieee80211_band band); void ieee80211_apply_vhtcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap); void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 123b26d177e80..1c342e2592c4a 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1379,21 +1379,26 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, */ if (has_80211h_pwr && (!has_cisco_pwr || pwr_level_80211h <= pwr_level_cisco)) { + new_ap_level = pwr_level_80211h; + + if (sdata->ap_power_level == new_ap_level) + return 0; + sdata_dbg(sdata, "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n", pwr_level_80211h, chan_pwr, pwr_reduction_80211h, sdata->u.mgd.bssid); - new_ap_level = pwr_level_80211h; } else { /* has_cisco_pwr is always true here. */ + new_ap_level = pwr_level_cisco; + + if (sdata->ap_power_level == new_ap_level) + return 0; + sdata_dbg(sdata, "Limiting TX power to %d dBm as advertised by %pM\n", pwr_level_cisco, sdata->u.mgd.bssid); - new_ap_level = pwr_level_cisco; } - if (sdata->ap_power_level == new_ap_level) - return 0; - sdata->ap_power_level = new_ap_level; if (__ieee80211_recalc_txpower(sdata)) return BSS_CHANGED_TXPOWER; @@ -3577,7 +3582,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (sta && elems.opmode_notif) ieee80211_vht_handle_opmode(sdata, sta, *elems.opmode_notif, - rx_status->band, true); + rx_status->band); mutex_unlock(&local->sta_mtx); changed |= ieee80211_handle_pwr_constr(sdata, chan, mgmt, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1f827539d828b..bc081850ac0e5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2735,8 +2735,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; ieee80211_vht_handle_opmode(rx->sdata, rx->sta, - opmode, status->band, - false); + opmode, status->band); goto handled; } default: diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 08af2b3079458..3943d4bf289c2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1644,6 +1644,29 @@ void ieee80211_stop_device(struct ieee80211_local *local) drv_stop(local); } +static void ieee80211_flush_completed_scan(struct ieee80211_local *local, + bool aborted) +{ + /* It's possible that we don't handle the scan completion in + * time during suspend, so if it's still marked as completed + * here, queue the work and flush it to clean things up. + * Instead of calling the worker function directly here, we + * really queue it to avoid potential races with other flows + * scheduling the same work. + */ + if (test_bit(SCAN_COMPLETED, &local->scanning)) { + /* If coming from reconfiguration failure, abort the scan so + * we don't attempt to continue a partial HW scan - which is + * possible otherwise if (e.g.) the 2.4 GHz portion was the + * completed scan, and a 5 GHz portion is still pending. + */ + if (aborted) + set_bit(SCAN_ABORTED, &local->scanning); + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); + flush_delayed_work(&local->scan_work); + } +} + static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; @@ -1663,6 +1686,8 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) local->suspended = false; local->in_reconfig = false; + ieee80211_flush_completed_scan(local, true); + /* scheduled scan clearly can't be running any more, but tell * cfg80211 and clear local state */ @@ -1701,6 +1726,27 @@ static void ieee80211_assign_chanctx(struct ieee80211_local *local, mutex_unlock(&local->chanctx_mtx); } +static void ieee80211_reconfig_stations(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + /* add STAs back */ + mutex_lock(&local->sta_mtx); + list_for_each_entry(sta, &local->sta_list, list) { + enum ieee80211_sta_state state; + + if (!sta->uploaded || sta->sdata != sdata) + continue; + + for (state = IEEE80211_STA_NOTEXIST; + state < sta->sta_state; state++) + WARN_ON(drv_sta_state(local, sta->sdata, sta, state, + state + 1)); + } + mutex_unlock(&local->sta_mtx); +} + int ieee80211_reconfig(struct ieee80211_local *local) { struct ieee80211_hw *hw = &local->hw; @@ -1836,50 +1882,11 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(drv_add_chanctx(local, ctx)); mutex_unlock(&local->chanctx_mtx); - list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata)) - continue; - ieee80211_assign_chanctx(local, sdata); - } - sdata = rtnl_dereference(local->monitor_sdata); if (sdata && ieee80211_sdata_running(sdata)) ieee80211_assign_chanctx(local, sdata); } - /* add STAs back */ - mutex_lock(&local->sta_mtx); - list_for_each_entry(sta, &local->sta_list, list) { - enum ieee80211_sta_state state; - - if (!sta->uploaded) - continue; - - /* AP-mode stations will be added later */ - if (sta->sdata->vif.type == NL80211_IFTYPE_AP) - continue; - - for (state = IEEE80211_STA_NOTEXIST; - state < sta->sta_state; state++) - WARN_ON(drv_sta_state(local, sta->sdata, sta, state, - state + 1)); - } - mutex_unlock(&local->sta_mtx); - - /* reconfigure tx conf */ - if (hw->queues >= IEEE80211_NUM_ACS) { - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MONITOR || - !ieee80211_sdata_running(sdata)) - continue; - - for (i = 0; i < IEEE80211_NUM_ACS; i++) - drv_conf_tx(local, sdata, i, - &sdata->tx_conf[i]); - } - } - /* reconfigure hardware */ ieee80211_hw_config(local, ~0); @@ -1892,6 +1899,22 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!ieee80211_sdata_running(sdata)) continue; + ieee80211_assign_chanctx(local, sdata); + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + break; + default: + ieee80211_reconfig_stations(sdata); + /* fall through */ + case NL80211_IFTYPE_AP: /* AP stations are handled later */ + for (i = 0; i < IEEE80211_NUM_ACS; i++) + drv_conf_tx(local, sdata, i, + &sdata->tx_conf[i]); + break; + } + /* common change flags for all interface types */ changed = BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_ERP_PREAMBLE | @@ -2077,17 +2100,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mb(); local->resuming = false; - /* It's possible that we don't handle the scan completion in - * time during suspend, so if it's still marked as completed - * here, queue the work and flush it to clean things up. - * Instead of calling the worker function directly here, we - * really queue it to avoid potential races with other flows - * scheduling the same work. - */ - if (test_bit(SCAN_COMPLETED, &local->scanning)) { - ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); - flush_delayed_work(&local->scan_work); - } + ieee80211_flush_completed_scan(local, false); if (local->open_count && !reconfig_due_to_wowlan) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ff1c798921a6a..c38b2f07a919e 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -378,7 +378,7 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only) + enum ieee80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; @@ -401,9 +401,6 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, changed |= IEEE80211_RC_NSS_CHANGED; } - if (nss_only) - return changed; - switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) { case IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_20; @@ -430,13 +427,12 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only) + enum ieee80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; - u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, - band, nss_only); + u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, band); if (changed > 0) rate_control_rate_update(local, sband, sta, changed); diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h index 0550f3365e330..fd9daf2ecec97 100644 --- a/net/mac802154/driver-ops.h +++ b/net/mac802154/driver-ops.h @@ -18,9 +18,6 @@ drv_xmit_async(struct ieee802154_local *local, struct sk_buff *skb) static inline int drv_xmit_sync(struct ieee802154_local *local, struct sk_buff *skb) { - /* don't allow other operations while sync xmit */ - ASSERT_RTNL(); - might_sleep(); return local->ops->xmit_sync(&local->hw, skb); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 3827f359b336d..7e253455f9dd0 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -38,12 +38,6 @@ void ieee802154_xmit_worker(struct work_struct *work) struct net_device *dev = skb->dev; int res; - rtnl_lock(); - - /* check if ifdown occurred while schedule */ - if (!netif_running(dev)) - goto err_tx; - res = drv_xmit_sync(local, skb); if (res) goto err_tx; @@ -53,14 +47,11 @@ void ieee802154_xmit_worker(struct work_struct *work) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - rtnl_unlock(); - return; err_tx: /* Restart the netif queue on each sub_if_data object. */ ieee802154_wake_queue(&local->hw); - rtnl_unlock(); kfree_skb(skb); netdev_dbg(dev, "transmission failed\n"); } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 4b3b9b310c3a0..b18c5ed42d956 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -27,6 +27,8 @@ */ #define MAX_MP_SELECT_LABELS 4 +#define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) + static int zero = 0; static int label_limit = (1 << 20) - 1; @@ -341,7 +343,13 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, } } - err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb); + /* If via wasn't specified then send out using device address */ + if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) + err = neigh_xmit(NEIGH_LINK_TABLE, out_dev, + out_dev->dev_addr, skb); + else + err = neigh_xmit(nh->nh_via_table, out_dev, + mpls_nh_via(rt, nh), skb); if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); @@ -559,6 +567,10 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, if (!mpls_dev_get(dev)) goto errout; + if ((nh->nh_via_table == NEIGH_LINK_TABLE) && + (dev->addr_len != nh->nh_via_alen)) + goto errout; + RCU_INIT_POINTER(nh->nh_dev, dev); if (!(dev->flags & IFF_UP)) { @@ -630,10 +642,14 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt, goto errout; } - err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, - __mpls_nh_via(rt, nh)); - if (err) - goto errout; + if (via) { + err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, + __mpls_nh_via(rt, nh)); + if (err) + goto errout; + } else { + nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC; + } err = mpls_nh_assign_dev(net, rt, nh, oif); if (err) @@ -715,9 +731,6 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST); } - if (!nla_via) - goto errout; - err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, rtnh->rtnh_ifindex, nla_via, nla_newdst); if (err) @@ -1227,6 +1240,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; + cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; @@ -1340,7 +1354,8 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; - if (nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && + nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = rtnl_dereference(nh->nh_dev); @@ -1381,7 +1396,8 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, nh->nh_labels, nh->nh_label)) goto nla_put_failure; - if (nla_put_via(skb, nh->nh_via_table, + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && + nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; @@ -1448,7 +1464,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) if (nh->nh_dev) payload += nla_total_size(4); /* RTA_OIF */ - payload += nla_total_size(2 + nh->nh_via_alen); /* RTA_VIA */ + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) /* RTA_VIA */ + payload += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) /* RTA_NEWDST */ payload += nla_total_size(nh->nh_labels * 4); } else { @@ -1457,7 +1474,9 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) for_nexthops(rt) { nhsize += nla_total_size(sizeof(struct rtnexthop)); - nhsize += nla_total_size(2 + nh->nh_via_alen); + /* RTA_VIA */ + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) + nhsize += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) nhsize += nla_total_size(nh->nh_labels * 4); } endfor_nexthops(rt); diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 67591aef9cae6..fb31aa87de817 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -37,7 +37,7 @@ static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) return en->labels * sizeof(struct mpls_shim_hdr); } -int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct mpls_iptunnel_encap *tun_encap_info; struct mpls_shim_hdr *hdr; @@ -54,10 +54,10 @@ int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) unsigned int ttl; /* Obtain the ttl */ - if (skb->protocol == htons(ETH_P_IP)) { + if (dst->ops->family == AF_INET) { ttl = ip_hdr(skb)->ttl; rt = (struct rtable *)dst; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (dst->ops->family == AF_INET6) { ttl = ipv6_hdr(skb)->hop_limit; rt6 = (struct rt6_info *)dst; } else { diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 7638c36b498cc..22934846b5d15 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -67,7 +67,7 @@ obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o # nf_tables -nf_tables-objs += nf_tables_core.o nf_tables_api.o +nf_tables-objs += nf_tables_core.o nf_tables_api.o nf_tables_trace.o nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nft_dynset.o nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 010ddeec135f5..d952d67f904d1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -169,7 +169,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, /* Only update csum if we really have to */ if (sctph->dest != cp->dport || payload_csum || (skb->ip_summed == CHECKSUM_PARTIAL && - !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CSUM))) { + !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index acf5c7b3f378c..278927ab09483 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -596,11 +596,18 @@ static int exp_proc_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_PROCFS struct proc_dir_entry *proc; + kuid_t root_uid; + kgid_t root_gid; proc = proc_create("nf_conntrack_expect", 0440, net->proc_net, &exp_file_ops); if (!proc) return -ENOMEM; + + root_uid = make_kuid(net->user_ns, 0); + root_gid = make_kgid(net->user_ns, 0); + if (uid_valid(root_uid) && gid_valid(root_gid)) + proc_set_user(proc, root_uid, root_gid); #endif /* CONFIG_NF_CONNTRACK_PROCFS */ return 0; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 1fb3cacc04e16..0f1a45bcacb24 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -392,11 +392,18 @@ static const struct file_operations ct_cpu_seq_fops = { static int nf_conntrack_standalone_init_proc(struct net *net) { struct proc_dir_entry *pde; + kuid_t root_uid; + kgid_t root_gid; pde = proc_create("nf_conntrack", 0440, net->proc_net, &ct_file_ops); if (!pde) goto out_nf_conntrack; + root_uid = make_kuid(net->user_ns, 0); + root_gid = make_kgid(net->user_ns, 0); + if (uid_valid(root_uid) && gid_valid(root_gid)) + proc_set_user(pde, root_uid, root_gid); + pde = proc_create("nf_conntrack", S_IRUGO, net->proc_net_stat, &ct_cpu_seq_fops); if (!pde) diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index 93da609d9d299..26e742006c48c 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -25,7 +25,7 @@ #include <net/netfilter/nf_conntrack_timeout.h> struct ctnl_timeout * -(*nf_ct_timeout_find_get_hook)(const char *name) __read_mostly; +(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name) __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook); void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 93cc4737018fd..4a23f77c363a3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -89,6 +89,7 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload) } static void nft_ctx_init(struct nft_ctx *ctx, + struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, struct nft_af_info *afi, @@ -96,7 +97,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, struct nft_chain *chain, const struct nlattr * const *nla) { - ctx->net = sock_net(skb->sk); + ctx->net = net; ctx->afi = afi; ctx->table = table; ctx->chain = chain; @@ -672,15 +673,14 @@ err: return ret; } -static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newtable(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nlattr *name; struct nft_af_info *afi; struct nft_table *table; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; u32 flags = 0; struct nft_ctx ctx; @@ -706,7 +706,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); return nf_tables_updtable(&ctx); } @@ -730,7 +730,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, INIT_LIST_HEAD(&table->sets); table->flags = flags; - nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) goto err3; @@ -810,18 +810,17 @@ out: return err; } -static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_deltable(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; struct nft_table *table; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_ctx ctx; - nft_ctx_init(&ctx, skb, nlh, NULL, NULL, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, NULL, NULL, NULL, nla); if (family == AF_UNSPEC || nla[NFTA_TABLE_NAME] == NULL) return nft_flush(&ctx, family); @@ -1221,8 +1220,8 @@ static void nf_tables_chain_destroy(struct nft_chain *chain) } } -static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newchain(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -1232,7 +1231,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, struct nft_chain *chain; struct nft_base_chain *basechain = NULL; struct nlattr *ha[NFTA_HOOK_MAX + 1]; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct net_device *dev = NULL; u8 policy = NF_ACCEPT; @@ -1313,7 +1311,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, return PTR_ERR(stats); } - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); if (trans == NULL) { @@ -1461,7 +1459,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (err < 0) goto err1; - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN); if (err < 0) goto err2; @@ -1476,15 +1474,14 @@ err1: return err; } -static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delchain(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_ctx ctx; @@ -1506,7 +1503,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, if (chain->use > 0) return -EBUSY; - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); return nft_delchain(&ctx); } @@ -2010,13 +2007,12 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static struct nft_expr_info *info; -static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newrule(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; - struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule, *old_rule = NULL; @@ -2075,7 +2071,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, return PTR_ERR(old_rule); } - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); n = 0; size = 0; @@ -2176,13 +2172,12 @@ err1: return err; } -static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delrule(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; - struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_chain *chain = NULL; struct nft_rule *rule; @@ -2205,7 +2200,7 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, return PTR_ERR(chain); } - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { @@ -2344,12 +2339,11 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_SIZE] = { .type = NLA_U32 }, }; -static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, +static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { - struct net *net = sock_net(skb->sk); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi = NULL; struct nft_table *table = NULL; @@ -2371,7 +2365,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, return -ENOENT; } - nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla); return 0; } @@ -2623,6 +2617,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + struct net *net = sock_net(skb->sk); const struct nft_set *set; struct nft_ctx ctx; struct sk_buff *skb2; @@ -2630,7 +2625,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, int err; /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla); if (err < 0) return err; @@ -2693,14 +2688,13 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx, return 0; } -static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newset(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nft_set_ops *ops; struct nft_af_info *afi; - struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; @@ -2798,7 +2792,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(table)) return PTR_ERR(table); - nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) { @@ -2882,8 +2876,8 @@ static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set nft_set_destroy(set); } -static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delset(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -2896,7 +2890,7 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla); if (err < 0) return err; @@ -3024,7 +3018,7 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; -static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, +static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -3033,7 +3027,6 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; struct nft_table *table; - struct net *net = sock_net(skb->sk); afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false); if (IS_ERR(afi)) @@ -3045,7 +3038,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, if (!trans && (table->flags & NFT_TABLE_INACTIVE)) return -ENOENT; - nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla); return 0; } @@ -3135,6 +3128,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); const struct nft_set *set; struct nft_set_dump_args args; struct nft_ctx ctx; @@ -3150,8 +3144,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (err < 0) return err; - err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla, - false); + err = nft_ctx_init_from_elemattr(&ctx, net, cb->skb, cb->nlh, + (void *)nla, false); if (err < 0) return err; @@ -3212,11 +3206,12 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + struct net *net = sock_net(skb->sk); const struct nft_set *set; struct nft_ctx ctx; int err; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false); if (err < 0) return err; @@ -3528,11 +3523,10 @@ err1: return err; } -static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { - struct net *net = sock_net(skb->sk); const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -3541,7 +3535,7 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, true); if (err < 0) return err; @@ -3623,8 +3617,8 @@ err1: return err; } -static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nlattr *attr; @@ -3635,7 +3629,7 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false); if (err < 0) return err; @@ -4030,7 +4024,8 @@ static int nf_tables_abort(struct sk_buff *skb) struct nft_trans *trans, *next; struct nft_trans_elem *te; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { @@ -4446,22 +4441,22 @@ static void nft_verdict_uninit(const struct nft_data *data) } } -static int nft_verdict_dump(struct sk_buff *skb, const struct nft_data *data) +int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v) { struct nlattr *nest; - nest = nla_nest_start(skb, NFTA_DATA_VERDICT); + nest = nla_nest_start(skb, type); if (!nest) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict.code))) + if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(v->code))) goto nla_put_failure; - switch (data->verdict.code) { + switch (v->code) { case NFT_JUMP: case NFT_GOTO: if (nla_put_string(skb, NFTA_VERDICT_CHAIN, - data->verdict.chain->name)) + v->chain->name)) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -4572,7 +4567,7 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, err = nft_value_dump(skb, data, len); break; case NFT_DATA_VERDICT: - err = nft_verdict_dump(skb, data); + err = nft_verdict_dump(skb, NFTA_DATA_VERDICT, &data->verdict); break; default: err = -EINVAL; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index f3695a4974086..e9f8dffcc2445 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -16,22 +16,17 @@ #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/netfilter.h> +#include <linux/static_key.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> -enum nft_trace { - NFT_TRACE_RULE, - NFT_TRACE_RETURN, - NFT_TRACE_POLICY, -}; - -static const char *const comments[] = { - [NFT_TRACE_RULE] = "rule", - [NFT_TRACE_RETURN] = "return", - [NFT_TRACE_POLICY] = "policy", +static const char *const comments[__NFT_TRACETYPE_MAX] = { + [NFT_TRACETYPE_POLICY] = "policy", + [NFT_TRACETYPE_RETURN] = "return", + [NFT_TRACETYPE_RULE] = "rule", }; static struct nf_loginfo trace_loginfo = { @@ -44,22 +39,36 @@ static struct nf_loginfo trace_loginfo = { }, }; -static void __nft_trace_packet(const struct nft_pktinfo *pkt, - const struct nft_chain *chain, - int rulenum, enum nft_trace type) +static noinline void __nft_trace_packet(struct nft_traceinfo *info, + const struct nft_chain *chain, + int rulenum, enum nft_trace_types type) { + const struct nft_pktinfo *pkt = info->pkt; + + if (!info->trace || !pkt->skb->nf_trace) + return; + + info->chain = chain; + info->type = type; + + nft_trace_notify(info); + nf_log_trace(pkt->net, pkt->pf, pkt->hook, pkt->skb, pkt->in, pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", chain->table->name, chain->name, comments[type], rulenum); } -static inline void nft_trace_packet(const struct nft_pktinfo *pkt, +static inline void nft_trace_packet(struct nft_traceinfo *info, const struct nft_chain *chain, - int rulenum, enum nft_trace type) + const struct nft_rule *rule, + int rulenum, + enum nft_trace_types type) { - if (unlikely(pkt->skb->nf_trace)) - __nft_trace_packet(pkt, chain, rulenum, type); + if (static_branch_unlikely(&nft_trace_enabled)) { + info->rule = rule; + __nft_trace_packet(info, chain, rulenum, type); + } } static void nft_cmp_fast_eval(const struct nft_expr *expr, @@ -121,7 +130,11 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) struct nft_stats *stats; int rulenum; unsigned int gencursor = nft_genmask_cur(net); + struct nft_traceinfo info; + info.trace = false; + if (static_branch_unlikely(&nft_trace_enabled)) + nft_trace_init(&info, pkt, ®s.verdict, basechain); do_chain: rulenum = 0; rule = list_entry(&chain->rules, struct nft_rule, list); @@ -151,7 +164,8 @@ next_rule: regs.verdict.code = NFT_CONTINUE; continue; case NFT_CONTINUE: - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + nft_trace_packet(&info, chain, rule, + rulenum, NFT_TRACETYPE_RULE); continue; } break; @@ -161,7 +175,8 @@ next_rule: case NF_ACCEPT: case NF_DROP: case NF_QUEUE: - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + nft_trace_packet(&info, chain, rule, + rulenum, NFT_TRACETYPE_RULE); return regs.verdict.code; } @@ -174,7 +189,8 @@ next_rule: stackptr++; /* fall through */ case NFT_GOTO: - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + nft_trace_packet(&info, chain, rule, + rulenum, NFT_TRACETYPE_RULE); chain = regs.verdict.chain; goto do_chain; @@ -182,7 +198,8 @@ next_rule: rulenum++; /* fall through */ case NFT_RETURN: - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN); + nft_trace_packet(&info, chain, rule, + rulenum, NFT_TRACETYPE_RETURN); break; default: WARN_ON(1); @@ -196,7 +213,8 @@ next_rule: goto next_rule; } - nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY); + nft_trace_packet(&info, basechain, NULL, -1, + NFT_TRACETYPE_POLICY); rcu_read_lock_bh(); stats = this_cpu_ptr(rcu_dereference(nft_base_chain(basechain)->stats)); diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 7b9c053ba7507..edb3502f20161 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -94,7 +94,7 @@ nft_do_chain_netdev(void *priv, struct sk_buff *skb, { struct nft_pktinfo pkt; - switch (eth_hdr(skb)->h_proto) { + switch (skb->protocol) { case htons(ETH_P_IP): nft_netdev_set_pktinfo_ipv4(&pkt, skb, state); break; diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c new file mode 100644 index 0000000000000..e9e959f65d917 --- /dev/null +++ b/net/netfilter/nf_tables_trace.c @@ -0,0 +1,275 @@ +/* + * (C) 2015 Red Hat GmbH + * Author: Florian Westphal <fw@strlen.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/static_key.h> +#include <linux/hash.h> +#include <linux/jhash.h> +#include <linux/if_vlan.h> +#include <linux/init.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_tables.h> + +#define NFT_TRACETYPE_LL_HSIZE 20 +#define NFT_TRACETYPE_NETWORK_HSIZE 40 +#define NFT_TRACETYPE_TRANSPORT_HSIZE 20 + +DEFINE_STATIC_KEY_FALSE(nft_trace_enabled); +EXPORT_SYMBOL_GPL(nft_trace_enabled); + +static int trace_fill_id(struct sk_buff *nlskb, struct sk_buff *skb) +{ + __be32 id; + + /* using skb address as ID results in a limited number of + * values (and quick reuse). + * + * So we attempt to use as many skb members that will not + * change while skb is with netfilter. + */ + id = (__be32)jhash_2words(hash32_ptr(skb), skb_get_hash(skb), + skb->skb_iif); + + return nla_put_be32(nlskb, NFTA_TRACE_ID, id); +} + +static int trace_fill_header(struct sk_buff *nlskb, u16 type, + const struct sk_buff *skb, + int off, unsigned int len) +{ + struct nlattr *nla; + + if (len == 0) + return 0; + + nla = nla_reserve(nlskb, type, len); + if (!nla || skb_copy_bits(skb, off, nla_data(nla), len)) + return -1; + + return 0; +} + +static int nf_trace_fill_ll_header(struct sk_buff *nlskb, + const struct sk_buff *skb) +{ + struct vlan_ethhdr veth; + int off; + + BUILD_BUG_ON(sizeof(veth) > NFT_TRACETYPE_LL_HSIZE); + + off = skb_mac_header(skb) - skb->data; + if (off != -ETH_HLEN) + return -1; + + if (skb_copy_bits(skb, off, &veth, ETH_HLEN)) + return -1; + + veth.h_vlan_proto = skb->vlan_proto; + veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); + veth.h_vlan_encapsulated_proto = skb->protocol; + + return nla_put(nlskb, NFTA_TRACE_LL_HEADER, sizeof(veth), &veth); +} + +static int nf_trace_fill_dev_info(struct sk_buff *nlskb, + const struct net_device *indev, + const struct net_device *outdev) +{ + if (indev) { + if (nla_put_be32(nlskb, NFTA_TRACE_IIF, + htonl(indev->ifindex))) + return -1; + + if (nla_put_be16(nlskb, NFTA_TRACE_IIFTYPE, + htons(indev->type))) + return -1; + } + + if (outdev) { + if (nla_put_be32(nlskb, NFTA_TRACE_OIF, + htonl(outdev->ifindex))) + return -1; + + if (nla_put_be16(nlskb, NFTA_TRACE_OIFTYPE, + htons(outdev->type))) + return -1; + } + + return 0; +} + +static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, + const struct nft_pktinfo *pkt) +{ + const struct sk_buff *skb = pkt->skb; + unsigned int len = min_t(unsigned int, + pkt->xt.thoff - skb_network_offset(skb), + NFT_TRACETYPE_NETWORK_HSIZE); + int off = skb_network_offset(skb); + + if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) + return -1; + + len = min_t(unsigned int, skb->len - pkt->xt.thoff, + NFT_TRACETYPE_TRANSPORT_HSIZE); + + if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, + pkt->xt.thoff, len)) + return -1; + + if (!skb_mac_header_was_set(skb)) + return 0; + + if (skb_vlan_tag_get(skb)) + return nf_trace_fill_ll_header(nlskb, skb); + + off = skb_mac_header(skb) - skb->data; + len = min_t(unsigned int, -off, NFT_TRACETYPE_LL_HSIZE); + return trace_fill_header(nlskb, NFTA_TRACE_LL_HEADER, + skb, off, len); +} + +static int nf_trace_fill_rule_info(struct sk_buff *nlskb, + const struct nft_traceinfo *info) +{ + if (!info->rule) + return 0; + + /* a continue verdict with ->type == RETURN means that this is + * an implicit return (end of chain reached). + * + * Since no rule matched, the ->rule pointer is invalid. + */ + if (info->type == NFT_TRACETYPE_RETURN && + info->verdict->code == NFT_CONTINUE) + return 0; + + return nla_put_be64(nlskb, NFTA_TRACE_RULE_HANDLE, + cpu_to_be64(info->rule->handle)); +} + +void nft_trace_notify(struct nft_traceinfo *info) +{ + const struct nft_pktinfo *pkt = info->pkt; + struct nfgenmsg *nfmsg; + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned int size; + int event = (NFNL_SUBSYS_NFTABLES << 8) | NFT_MSG_TRACE; + + if (!nfnetlink_has_listeners(pkt->net, NFNLGRP_NFTRACE)) + return; + + size = nlmsg_total_size(sizeof(struct nfgenmsg)) + + nla_total_size(NFT_TABLE_MAXNAMELEN) + + nla_total_size(NFT_CHAIN_MAXNAMELEN) + + nla_total_size(sizeof(__be64)) + /* rule handle */ + nla_total_size(sizeof(__be32)) + /* trace type */ + nla_total_size(0) + /* VERDICT, nested */ + nla_total_size(sizeof(u32)) + /* verdict code */ + nla_total_size(NFT_CHAIN_MAXNAMELEN) + /* jump target */ + nla_total_size(sizeof(u32)) + /* id */ + nla_total_size(NFT_TRACETYPE_LL_HSIZE) + + nla_total_size(NFT_TRACETYPE_NETWORK_HSIZE) + + nla_total_size(NFT_TRACETYPE_TRANSPORT_HSIZE) + + nla_total_size(sizeof(u32)) + /* iif */ + nla_total_size(sizeof(__be16)) + /* iiftype */ + nla_total_size(sizeof(u32)) + /* oif */ + nla_total_size(sizeof(__be16)) + /* oiftype */ + nla_total_size(sizeof(u32)) + /* mark */ + nla_total_size(sizeof(u32)) + /* nfproto */ + nla_total_size(sizeof(u32)); /* policy */ + + skb = nlmsg_new(size, GFP_ATOMIC); + if (!skb) + return; + + nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct nfgenmsg), 0); + if (!nlh) + goto nla_put_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = info->basechain->type->family; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(pkt->pf))) + goto nla_put_failure; + + if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type))) + goto nla_put_failure; + + if (trace_fill_id(skb, pkt->skb)) + goto nla_put_failure; + + if (info->chain) { + if (nla_put_string(skb, NFTA_TRACE_CHAIN, + info->chain->name)) + goto nla_put_failure; + if (nla_put_string(skb, NFTA_TRACE_TABLE, + info->chain->table->name)) + goto nla_put_failure; + } + + if (nf_trace_fill_rule_info(skb, info)) + goto nla_put_failure; + + switch (info->type) { + case NFT_TRACETYPE_UNSPEC: + case __NFT_TRACETYPE_MAX: + break; + case NFT_TRACETYPE_RETURN: + case NFT_TRACETYPE_RULE: + if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, info->verdict)) + goto nla_put_failure; + break; + case NFT_TRACETYPE_POLICY: + if (nla_put_be32(skb, NFTA_TRACE_POLICY, + info->basechain->policy)) + goto nla_put_failure; + break; + } + + if (pkt->skb->mark && + nla_put_be32(skb, NFTA_TRACE_MARK, htonl(pkt->skb->mark))) + goto nla_put_failure; + + if (!info->packet_dumped) { + if (nf_trace_fill_dev_info(skb, pkt->in, pkt->out)) + goto nla_put_failure; + + if (nf_trace_fill_pkt_info(skb, pkt)) + goto nla_put_failure; + info->packet_dumped = true; + } + + nlmsg_end(skb, nlh); + nfnetlink_send(skb, pkt->net, 0, NFNLGRP_NFTRACE, 0, GFP_ATOMIC); + return; + + nla_put_failure: + WARN_ON_ONCE(1); + kfree_skb(skb); +} + +void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, + const struct nft_chain *chain) +{ + info->basechain = nft_base_chain(chain); + info->trace = true; + info->packet_dumped = false; + info->pkt = pkt; + info->verdict = verdict; +} diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 46453ab318db0..9ed4534651675 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -33,6 +33,10 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); +#define nfnl_dereference_protected(id) \ + rcu_dereference_protected(table[(id)].subsys, \ + lockdep_nfnl_is_held((id))) + static char __initdata nfversion[] = "0.30"; static struct { @@ -49,6 +53,7 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, + [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, }; void nfnl_lock(__u8 subsys_id) @@ -207,8 +212,7 @@ replay: } else { rcu_read_unlock(); nfnl_lock(subsys_id); - if (rcu_dereference_protected(table[subsys_id].subsys, - lockdep_is_held(&table[subsys_id].mutex)) != ss || + if (nfnl_dereference_protected(subsys_id) != ss || nfnetlink_find_client(type, ss) != nc) err = -EAGAIN; else if (nc->call) @@ -295,18 +299,14 @@ replay: if (!skb) return netlink_ack(oskb, nlh, -ENOMEM); - skb->sk = oskb->sk; - nfnl_lock(subsys_id); - ss = rcu_dereference_protected(table[subsys_id].subsys, - lockdep_is_held(&table[subsys_id].mutex)); + ss = nfnl_dereference_protected(subsys_id); if (!ss) { #ifdef CONFIG_MODULES nfnl_unlock(subsys_id); request_module("nfnetlink-subsys-%d", subsys_id); nfnl_lock(subsys_id); - ss = rcu_dereference_protected(table[subsys_id].subsys, - lockdep_is_held(&table[subsys_id].mutex)); + ss = nfnl_dereference_protected(subsys_id); if (!ss) #endif { @@ -381,7 +381,7 @@ replay: goto ack; if (nc->call_batch) { - err = nc->call_batch(net->nfnl, skb, nlh, + err = nc->call_batch(net, net->nfnl, skb, nlh, (const struct nlattr **)cda); } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index c7a2d0e1c462c..3921d544f5ba1 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -38,8 +38,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("cttimeout: Extended Netfilter Connection Tracking timeout tuning"); -static LIST_HEAD(cttimeout_list); - static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { [CTA_TIMEOUT_NAME] = { .type = NLA_NUL_STRING, .len = CTNL_TIMEOUT_NAME_MAX - 1}, @@ -90,7 +88,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); - list_for_each_entry(timeout, &cttimeout_list, head) { + list_for_each_entry(timeout, &net->nfct_timeout_list, head) { if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; @@ -145,7 +143,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, timeout->l3num = l3num; timeout->l4proto = l4proto; atomic_set(&timeout->refcnt, 1); - list_add_tail_rcu(&timeout->head, &cttimeout_list); + list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list); return 0; err: @@ -209,6 +207,7 @@ nla_put_failure: static int ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct ctnl_timeout *cur, *last; if (cb->args[2]) @@ -219,7 +218,7 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->args[1] = 0; rcu_read_lock(); - list_for_each_entry_rcu(cur, &cttimeout_list, head) { + list_for_each_entry_rcu(cur, &net->nfct_timeout_list, head) { if (last) { if (cur != last) continue; @@ -245,6 +244,7 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(skb->sk); int ret = -ENOENT; char *name; struct ctnl_timeout *cur; @@ -260,7 +260,7 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, return -EINVAL; name = nla_data(cda[CTA_TIMEOUT_NAME]); - list_for_each_entry(cur, &cttimeout_list, head) { + list_for_each_entry(cur, &net->nfct_timeout_list, head) { struct sk_buff *skb2; if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) @@ -301,17 +301,17 @@ static void untimeout(struct nf_conntrack_tuple_hash *i, RCU_INIT_POINTER(timeout_ext->timeout, NULL); } -static void ctnl_untimeout(struct ctnl_timeout *timeout) +static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) { struct nf_conntrack_tuple_hash *h; const struct hlist_nulls_node *nn; int i; local_bh_disable(); - for (i = 0; i < init_net.ct.htable_size; i++) { + for (i = 0; i < net->ct.htable_size; i++) { spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); - if (i < init_net.ct.htable_size) { - hlist_nulls_for_each_entry(h, nn, &init_net.ct.hash[i], hnnode) + if (i < net->ct.htable_size) { + hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) untimeout(h, timeout); } spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); @@ -320,7 +320,7 @@ static void ctnl_untimeout(struct ctnl_timeout *timeout) } /* try to delete object, fail if it is still in use. */ -static int ctnl_timeout_try_del(struct ctnl_timeout *timeout) +static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { int ret = 0; @@ -329,7 +329,7 @@ static int ctnl_timeout_try_del(struct ctnl_timeout *timeout) /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); - ctnl_untimeout(timeout); + ctnl_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { /* still in use, restore reference counter. */ @@ -344,23 +344,24 @@ cttimeout_del_timeout(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(skb->sk); char *name; struct ctnl_timeout *cur; int ret = -ENOENT; if (!cda[CTA_TIMEOUT_NAME]) { - list_for_each_entry(cur, &cttimeout_list, head) - ctnl_timeout_try_del(cur); + list_for_each_entry(cur, &net->nfct_timeout_list, head) + ctnl_timeout_try_del(net, cur); return 0; } name = nla_data(cda[CTA_TIMEOUT_NAME]); - list_for_each_entry(cur, &cttimeout_list, head) { + list_for_each_entry(cur, &net->nfct_timeout_list, head) { if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; - ret = ctnl_timeout_try_del(cur); + ret = ctnl_timeout_try_del(net, cur); if (ret < 0) return ret; @@ -511,12 +512,13 @@ err: } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -static struct ctnl_timeout *ctnl_timeout_find_get(const char *name) +static struct ctnl_timeout * +ctnl_timeout_find_get(struct net *net, const char *name) { struct ctnl_timeout *timeout, *matching = NULL; rcu_read_lock(); - list_for_each_entry_rcu(timeout, &cttimeout_list, head) { + list_for_each_entry_rcu(timeout, &net->nfct_timeout_list, head) { if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; @@ -569,10 +571,39 @@ static const struct nfnetlink_subsystem cttimeout_subsys = { MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_TIMEOUT); +static int __net_init cttimeout_net_init(struct net *net) +{ + INIT_LIST_HEAD(&net->nfct_timeout_list); + + return 0; +} + +static void __net_exit cttimeout_net_exit(struct net *net) +{ + struct ctnl_timeout *cur, *tmp; + + ctnl_untimeout(net, NULL); + + list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { + list_del_rcu(&cur->head); + nf_ct_l4proto_put(cur->l4proto); + kfree_rcu(cur, rcu_head); + } +} + +static struct pernet_operations cttimeout_ops = { + .init = cttimeout_net_init, + .exit = cttimeout_net_exit, +}; + static int __init cttimeout_init(void) { int ret; + ret = register_pernet_subsys(&cttimeout_ops); + if (ret < 0) + return ret; + ret = nfnetlink_subsys_register(&cttimeout_subsys); if (ret < 0) { pr_err("cttimeout_init: cannot register cttimeout with " @@ -586,28 +617,17 @@ static int __init cttimeout_init(void) return 0; err_out: + unregister_pernet_subsys(&cttimeout_ops); return ret; } static void __exit cttimeout_exit(void) { - struct ctnl_timeout *cur, *tmp; - pr_info("cttimeout: unregistering from nfnetlink.\n"); nfnetlink_subsys_unregister(&cttimeout_subsys); - /* Make sure no conntrack objects refer to custom timeouts anymore. */ - ctnl_untimeout(NULL); - - list_for_each_entry_safe(cur, tmp, &cttimeout_list, head) { - list_del_rcu(&cur->head); - /* We are sure that our objects have no clients at this point, - * it's safe to release them all without checking refcnt. - */ - nf_ct_l4proto_put(cur->l4proto); - kfree_rcu(cur, rcu_head); - } + unregister_pernet_subsys(&cttimeout_ops); #ifdef CONFIG_NF_CONNTRACK_TIMEOUT RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL); RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 740cce4685acf..70b6bd3b781e4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -293,24 +293,20 @@ nfulnl_set_nlbufsiz(struct nfulnl_instance *inst, u_int32_t nlbufsiz) return status; } -static int +static void nfulnl_set_timeout(struct nfulnl_instance *inst, u_int32_t timeout) { spin_lock_bh(&inst->lock); inst->flushtimeout = timeout; spin_unlock_bh(&inst->lock); - - return 0; } -static int +static void nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh) { spin_lock_bh(&inst->lock); inst->qthreshold = qthresh; spin_unlock_bh(&inst->lock); - - return 0; } static int @@ -1064,15 +1060,26 @@ static int __net_init nfnl_log_net_init(struct net *net) { unsigned int i; struct nfnl_log_net *log = nfnl_log_pernet(net); +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc; + kuid_t root_uid; + kgid_t root_gid; +#endif for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&log->instance_table[i]); spin_lock_init(&log->instances_lock); #ifdef CONFIG_PROC_FS - if (!proc_create("nfnetlink_log", 0440, - net->nf.proc_netfilter, &nful_file_ops)) + proc = proc_create("nfnetlink_log", 0440, + net->nf.proc_netfilter, &nful_file_ops); + if (!proc) return -ENOMEM; + + root_uid = make_kuid(net->user_ns, 0); + root_gid = make_kgid(net->user_ns, 0); + if (uid_valid(root_uid) && gid_valid(root_gid)) + proc_set_user(proc, root_uid, root_gid); #endif return 0; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7d81d280cb4ff..861c6615253bf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -365,8 +365,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, break; } + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (queue->flags & NFQA_CFG_F_CONNTRACK) { - nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) { ct = nfnl_ct->get_ct(entskb, &ctinfo); if (ct != NULL) @@ -1064,9 +1065,10 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; + /* rcu lock already held from nfnl->call_rcu. */ + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (nfqa[NFQA_CT]) { - /* rcu lock already held from nfnl->call_rcu. */ - nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) ct = nfqnl_ct_parse(nfnl_ct, nlh, nfqa, entry, &ctinfo); } @@ -1417,6 +1419,7 @@ static int __init nfnetlink_queue_init(void) cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_queue_net_ops); out: return status; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 8cbca3432f903..939921532764a 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -366,6 +366,7 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; switch (priv->key) { + case NFT_CT_L3PROTOCOL: case NFT_CT_PROTOCOL: case NFT_CT_SRC: case NFT_CT_DST: diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 1915cab7f32d3..fe885bf271c5d 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -18,12 +18,16 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/smp.h> +#include <linux/static_key.h> #include <net/dst.h> #include <net/sock.h> #include <net/tcp_states.h> /* for TCP_TIME_WAIT */ #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nft_meta.h> +#include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ + void nft_meta_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -188,6 +192,13 @@ err: } EXPORT_SYMBOL_GPL(nft_meta_get_eval); +/* don't change or set _LOOPBACK, _USER, etc. */ +static bool pkt_type_ok(u32 p) +{ + return p == PACKET_HOST || p == PACKET_BROADCAST || + p == PACKET_MULTICAST || p == PACKET_OTHERHOST; +} + void nft_meta_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -203,6 +214,11 @@ void nft_meta_set_eval(const struct nft_expr *expr, case NFT_META_PRIORITY: skb->priority = value; break; + case NFT_META_PKTTYPE: + if (skb->pkt_type != value && + pkt_type_ok(value) && pkt_type_ok(skb->pkt_type)) + skb->pkt_type = value; + break; case NFT_META_NFTRACE: skb->nf_trace = 1; break; @@ -271,6 +287,24 @@ int nft_meta_get_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_meta_get_init); +static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) +{ + unsigned int hooks; + + switch (ctx->afi->family) { + case NFPROTO_BRIDGE: + hooks = 1 << NF_BR_PRE_ROUTING; + break; + case NFPROTO_NETDEV: + hooks = 1 << NF_NETDEV_INGRESS; + break; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); +} + int nft_meta_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -288,6 +322,12 @@ int nft_meta_set_init(const struct nft_ctx *ctx, case NFT_META_NFTRACE: len = sizeof(u8); break; + case NFT_META_PKTTYPE: + err = nft_meta_set_init_pkttype(ctx); + if (err) + return err; + len = sizeof(u8); + break; default: return -EOPNOTSUPP; } @@ -297,6 +337,9 @@ int nft_meta_set_init(const struct nft_ctx *ctx, if (err < 0) return err; + if (priv->key == NFT_META_NFTRACE) + static_branch_inc(&nft_trace_enabled); + return 0; } EXPORT_SYMBOL_GPL(nft_meta_set_init); @@ -334,6 +377,16 @@ nla_put_failure: } EXPORT_SYMBOL_GPL(nft_meta_set_dump); +void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + + if (priv->key == NFT_META_NFTRACE) + static_branch_dec(&nft_trace_enabled); +} +EXPORT_SYMBOL_GPL(nft_meta_set_destroy); + static struct nft_expr_type nft_meta_type; static const struct nft_expr_ops nft_meta_get_ops = { .type = &nft_meta_type, @@ -348,6 +401,7 @@ static const struct nft_expr_ops nft_meta_set_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_set_eval, .init = nft_meta_set_init, + .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, }; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 09b4b07eb6764..12cd4bf16d17d 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -107,10 +107,13 @@ err: } static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { - [NFTA_PAYLOAD_DREG] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_BASE] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_OFFSET] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_LEN] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_SREG] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_DREG] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_BASE] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_OFFSET] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_LEN] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_CSUM_OFFSET] = { .type = NLA_U32 }, }; static int nft_payload_init(const struct nft_ctx *ctx, @@ -160,6 +163,118 @@ const struct nft_expr_ops nft_payload_fast_ops = { .dump = nft_payload_dump, }; +static void nft_payload_set_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_payload_set *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + const u32 *src = ®s->data[priv->sreg]; + int offset, csum_offset; + __wsum fsum, tsum; + __sum16 sum; + + switch (priv->base) { + case NFT_PAYLOAD_LL_HEADER: + if (!skb_mac_header_was_set(skb)) + goto err; + offset = skb_mac_header(skb) - skb->data; + break; + case NFT_PAYLOAD_NETWORK_HEADER: + offset = skb_network_offset(skb); + break; + case NFT_PAYLOAD_TRANSPORT_HEADER: + offset = pkt->xt.thoff; + break; + default: + BUG(); + } + + csum_offset = offset + priv->csum_offset; + offset += priv->offset; + + if (priv->csum_type == NFT_PAYLOAD_CSUM_INET && + (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER || + skb->ip_summed != CHECKSUM_PARTIAL)) { + if (skb_copy_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) + goto err; + + fsum = skb_checksum(skb, offset, priv->len, 0); + tsum = csum_partial(src, priv->len, 0); + sum = csum_fold(csum_add(csum_sub(~csum_unfold(sum), fsum), + tsum)); + if (sum == 0) + sum = CSUM_MANGLED_0; + + if (!skb_make_writable(skb, csum_offset + sizeof(sum)) || + skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) + goto err; + } + + if (!skb_make_writable(skb, max(offset + priv->len, 0)) || + skb_store_bits(skb, offset, src, priv->len) < 0) + goto err; + + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static int nft_payload_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_payload_set *priv = nft_expr_priv(expr); + + priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); + priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); + priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + priv->sreg = nft_parse_register(tb[NFTA_PAYLOAD_SREG]); + + if (tb[NFTA_PAYLOAD_CSUM_TYPE]) + priv->csum_type = + ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); + if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) + priv->csum_offset = + ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET])); + + switch (priv->csum_type) { + case NFT_PAYLOAD_CSUM_NONE: + case NFT_PAYLOAD_CSUM_INET: + break; + default: + return -EOPNOTSUPP; + } + + return nft_validate_register_load(priv->sreg, priv->len); +} + +static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_payload_set *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_PAYLOAD_SREG, priv->sreg) || + nla_put_be32(skb, NFTA_PAYLOAD_BASE, htonl(priv->base)) || + nla_put_be32(skb, NFTA_PAYLOAD_OFFSET, htonl(priv->offset)) || + nla_put_be32(skb, NFTA_PAYLOAD_LEN, htonl(priv->len)) || + nla_put_be32(skb, NFTA_PAYLOAD_CSUM_TYPE, htonl(priv->csum_type)) || + nla_put_be32(skb, NFTA_PAYLOAD_CSUM_OFFSET, + htonl(priv->csum_offset))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_expr_ops nft_payload_set_ops = { + .type = &nft_payload_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_payload_set)), + .eval = nft_payload_set_eval, + .init = nft_payload_set_init, + .dump = nft_payload_set_dump, +}; + static const struct nft_expr_ops * nft_payload_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -167,8 +282,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, enum nft_payload_bases base; unsigned int offset, len; - if (tb[NFTA_PAYLOAD_DREG] == NULL || - tb[NFTA_PAYLOAD_BASE] == NULL || + if (tb[NFTA_PAYLOAD_BASE] == NULL || tb[NFTA_PAYLOAD_OFFSET] == NULL || tb[NFTA_PAYLOAD_LEN] == NULL) return ERR_PTR(-EINVAL); @@ -183,6 +297,15 @@ nft_payload_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EOPNOTSUPP); } + if (tb[NFTA_PAYLOAD_SREG] != NULL) { + if (tb[NFTA_PAYLOAD_DREG] != NULL) + return ERR_PTR(-EINVAL); + return &nft_payload_set_ops; + } + + if (tb[NFTA_PAYLOAD_DREG] == NULL) + return ERR_PTR(-EINVAL); + offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d4aaad747ea99..c8a0b7da5ff46 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -26,6 +26,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/audit.h> +#include <linux/user_namespace.h> #include <net/net_namespace.h> #include <linux/netfilter/x_tables.h> @@ -1226,6 +1227,8 @@ int xt_proto_init(struct net *net, u_int8_t af) #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; struct proc_dir_entry *proc; + kuid_t root_uid; + kgid_t root_gid; #endif if (af >= ARRAY_SIZE(xt_prefix)) @@ -1233,12 +1236,17 @@ int xt_proto_init(struct net *net, u_int8_t af) #ifdef CONFIG_PROC_FS + root_uid = make_kuid(net->user_ns, 0); + root_gid = make_kgid(net->user_ns, 0); + strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); proc = proc_create_data(buf, 0440, net->proc_net, &xt_table_ops, (void *)(unsigned long)af); if (!proc) goto out; + if (uid_valid(root_uid) && gid_valid(root_gid)) + proc_set_user(proc, root_uid, root_gid); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); @@ -1246,6 +1254,8 @@ int xt_proto_init(struct net *net, u_int8_t af) (void *)(unsigned long)af); if (!proc) goto out_remove_tables; + if (uid_valid(root_uid) && gid_valid(root_gid)) + proc_set_user(proc, root_uid, root_gid); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); @@ -1253,6 +1263,8 @@ int xt_proto_init(struct net *net, u_int8_t af) (void *)(unsigned long)af); if (!proc) goto out_remove_matches; + if (uid_valid(root_uid) && gid_valid(root_gid)) + proc_set_user(proc, root_uid, root_gid); #endif return 0; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index e7ac07e53b592..6669e68d589ee 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -143,7 +143,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, goto out; } - timeout = timeout_find_get(timeout_name); + timeout = timeout_find_get(par->net, timeout_name); if (timeout == NULL) { ret = -ENOENT; pr_info("No such timeout policy \"%s\"\n", timeout_name); diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 54eaeb45ce996..a086a914865f7 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -24,9 +24,9 @@ MODULE_DESCRIPTION("Xtables: process control group matching"); MODULE_ALIAS("ipt_cgroup"); MODULE_ALIAS("ip6t_cgroup"); -static int cgroup_mt_check(const struct xt_mtchk_param *par) +static int cgroup_mt_check_v0(const struct xt_mtchk_param *par) { - struct xt_cgroup_info *info = par->matchinfo; + struct xt_cgroup_info_v0 *info = par->matchinfo; if (info->invert & ~1) return -EINVAL; @@ -34,10 +34,41 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par) return 0; } +static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_cgroup_info_v1 *info = par->matchinfo; + struct cgroup *cgrp; + + if ((info->invert_path & ~1) || (info->invert_classid & ~1)) + return -EINVAL; + + if (!info->has_path && !info->has_classid) { + pr_info("xt_cgroup: no path or classid specified\n"); + return -EINVAL; + } + + if (info->has_path && info->has_classid) { + pr_info("xt_cgroup: both path and classid specified\n"); + return -EINVAL; + } + + if (info->has_path) { + cgrp = cgroup_get_from_path(info->path); + if (IS_ERR(cgrp)) { + pr_info("xt_cgroup: invalid path, errno=%ld\n", + PTR_ERR(cgrp)); + return -EINVAL; + } + info->priv = cgrp; + } + + return 0; +} + static bool -cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) +cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { - const struct xt_cgroup_info *info = par->matchinfo; + const struct xt_cgroup_info_v0 *info = par->matchinfo; if (skb->sk == NULL || !sk_fullsock(skb->sk)) return false; @@ -46,27 +77,67 @@ cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) info->invert; } -static struct xt_match cgroup_mt_reg __read_mostly = { - .name = "cgroup", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = cgroup_mt_check, - .match = cgroup_mt, - .matchsize = sizeof(struct xt_cgroup_info), - .me = THIS_MODULE, - .hooks = (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_IN), +static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_cgroup_info_v1 *info = par->matchinfo; + struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; + struct cgroup *ancestor = info->priv; + + if (!skb->sk || !sk_fullsock(skb->sk)) + return false; + + if (ancestor) + return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ + info->invert_path; + else + return (info->classid == sock_cgroup_classid(skcd)) ^ + info->invert_classid; +} + +static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) +{ + struct xt_cgroup_info_v1 *info = par->matchinfo; + + if (info->priv) + cgroup_put(info->priv); +} + +static struct xt_match cgroup_mt_reg[] __read_mostly = { + { + .name = "cgroup", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = cgroup_mt_check_v0, + .match = cgroup_mt_v0, + .matchsize = sizeof(struct xt_cgroup_info_v0), + .me = THIS_MODULE, + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + }, + { + .name = "cgroup", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = cgroup_mt_check_v1, + .match = cgroup_mt_v1, + .matchsize = sizeof(struct xt_cgroup_info_v1), + .destroy = cgroup_mt_destroy_v1, + .me = THIS_MODULE, + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + }, }; static int __init cgroup_mt_init(void) { - return xt_register_match(&cgroup_mt_reg); + return xt_register_matches(cgroup_mt_reg, ARRAY_SIZE(cgroup_mt_reg)); } static void __exit cgroup_mt_exit(void) { - xt_unregister_match(&cgroup_mt_reg); + xt_unregister_matches(cgroup_mt_reg, ARRAY_SIZE(cgroup_mt_reg)); } module_init(cgroup_mt_init); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 59651af8cc270..81dc1bb6e0168 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2915,6 +2915,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); + cb->start = control->start; cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; @@ -2927,6 +2928,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, mutex_unlock(nlk->cb_mutex); + if (cb->start) + cb->start(cb); + ret = netlink_dump(sk); sock_put(sk); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index bc0e504f33a68..8e63662c6fb0f 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -513,6 +513,20 @@ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, } EXPORT_SYMBOL(genlmsg_put); +static int genl_lock_start(struct netlink_callback *cb) +{ + /* our ops are always const - netlink API doesn't propagate that */ + const struct genl_ops *ops = cb->data; + int rc = 0; + + if (ops->start) { + genl_lock(); + rc = ops->start(cb); + genl_unlock(); + } + return rc; +} + static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { /* our ops are always const - netlink API doesn't propagate that */ @@ -577,6 +591,7 @@ static int genl_family_rcv_msg(struct genl_family *family, .module = family->module, /* we have const, but the netlink API doesn't */ .data = (void *)ops, + .start = genl_lock_start, .dump = genl_lock_dumpit, .done = genl_lock_done, }; @@ -588,6 +603,7 @@ static int genl_family_rcv_msg(struct genl_family *family, } else { struct netlink_dump_control c = { .module = family->module, + .start = ops->start, .dump = ops->dumpit, .done = ops->done, }; diff --git a/net/nfc/core.c b/net/nfc/core.c index 1fe3d3b362c0c..122bb81da9181 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -953,6 +953,19 @@ out: } EXPORT_SYMBOL(nfc_se_transaction); +int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx) +{ + int rc; + + pr_debug("connectivity: %x\n", se_idx); + + device_lock(&dev->dev); + rc = nfc_genl_se_connectivity(dev, se_idx); + device_unlock(&dev->dev); + return rc; +} +EXPORT_SYMBOL(nfc_se_connectivity); + static void nfc_release(struct device *d) { struct nfc_dev *dev = to_nfc_dev(d); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 23c2a118ac9f9..dd9003f388225 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -20,7 +20,8 @@ #include "digital.h" #define DIGITAL_PROTO_NFCA_RF_TECH \ - (NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK | NFC_PROTO_NFC_DEP_MASK) + (NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK | \ + NFC_PROTO_NFC_DEP_MASK | NFC_PROTO_ISO14443_MASK) #define DIGITAL_PROTO_NFCB_RF_TECH NFC_PROTO_ISO14443_B_MASK diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 10c99a5784212..fbb7a2b57b443 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -610,14 +610,14 @@ int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type, struct nci_core_conn_create_cmd *cmd; struct core_conn_create_data data; + if (!number_destination_params) + return -EINVAL; + data.length = params_len + sizeof(struct nci_core_conn_create_cmd); cmd = kzalloc(data.length, GFP_KERNEL); if (!cmd) return -ENOMEM; - if (!number_destination_params) - return -EINVAL; - cmd->destination_type = destination_type; cmd->number_destination_params = number_destination_params; memcpy(cmd->params, params, params_len); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 2aedac15cb592..a0ab26d535dca 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -676,7 +676,7 @@ int nci_hci_connect_gate(struct nci_dev *ndev, break; default: pipe = nci_hci_create_pipe(ndev, dest_host, dest_gate, &r); - if (pipe < 0) + if (pipe == NCI_HCI_INVALID_PIPE) return r; pipe_created = true; break; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f58c1fba10268..ea023b35f1c24 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -552,6 +552,43 @@ free_msg: return -EMSGSIZE; } +int nfc_genl_se_connectivity(struct nfc_dev *dev, u8 se_idx) +{ + struct nfc_se *se; + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_SE_CONNECTIVITY); + if (!hdr) + goto free_msg; + + se = nfc_find_se(dev, se_idx); + if (!se) + goto free_msg; + + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || + nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || + nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, u32 portid, u32 seq, struct netlink_callback *cb, diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index c20b784ad7206..6c6f76b370b1e 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -105,6 +105,7 @@ int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx); int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); +int nfc_genl_se_connectivity(struct nfc_dev *dev, u8 se_idx); struct nfc_dev *nfc_get_device(unsigned int idx); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c2cc11168fd5e..ee6ff8ffc12d9 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -53,6 +53,8 @@ struct ovs_conntrack_info { struct md_labels labels; }; +static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); + static u16 key_to_nfproto(const struct sw_flow_key *key) { switch (ntohs(key->eth.type)) { @@ -141,6 +143,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, * previously sent the packet to conntrack via the ct action. */ static void ovs_ct_update_key(const struct sk_buff *skb, + const struct ovs_conntrack_info *info, struct sw_flow_key *key, bool post_ct) { const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; @@ -158,13 +161,15 @@ static void ovs_ct_update_key(const struct sk_buff *skb, zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; + if (info) + zone = &info->zone; } __ovs_ct_update_key(key, state, zone, ct); } void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { - ovs_ct_update_key(skb, key, false); + ovs_ct_update_key(skb, NULL, key, false); } int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) @@ -300,10 +305,10 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, struct sk_buff *skb) { struct ovs_skb_cb ovs_cb = *OVS_CB(skb); + int err; if (key->eth.type == htons(ETH_P_IP)) { enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - int err; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); err = ip_defrag(net, skb, user); @@ -314,28 +319,13 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - struct sk_buff *reasm; memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - reasm = nf_ct_frag6_gather(net, skb, user); - if (!reasm) - return -EINPROGRESS; - - if (skb == reasm) { - kfree_skb(skb); - return -EINVAL; - } - - /* Don't free 'skb' even though it is one of the original - * fragments, as we're going to morph it into the head. - */ - skb_get(skb); - nf_ct_frag6_consume_orig(reasm); + err = nf_ct_frag6_gather(net, skb, user); + if (err) + return err; - key->ip.proto = ipv6_hdr(reasm)->nexthdr; - skb_morph(skb, reasm); - skb->next = reasm->next; - consume_skb(reasm); + key->ip.proto = ipv6_hdr(skb)->nexthdr; ovs_cb.mru = IP6CB(skb)->frag_max_size; #endif } else { @@ -418,7 +408,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, } } - ovs_ct_update_key(skb, key, true); + ovs_ct_update_key(skb, info, key, true); return 0; } @@ -693,6 +683,10 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, OVS_NLERR(log, "Failed to allocate conntrack template"); return -ENOMEM; } + + __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); + nf_conntrack_get(&ct_info.ct->ct_general); + if (helper) { err = ovs_ct_add_helper(&ct_info, helper, key, log); if (err) @@ -704,11 +698,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (err) goto err_free_ct; - __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: - nf_conntrack_free(ct_info.ct); + __ovs_ct_free_action(&ct_info); return err; } @@ -750,6 +742,11 @@ void ovs_ct_free_action(const struct nlattr *a) { struct ovs_conntrack_info *ct_info = nla_data(a); + __ovs_ct_free_action(ct_info); +} + +static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) +{ if (ct_info->helper) module_put(ct_info->helper->me); if (ct_info->ct) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 907d6fd28ede6..d1bd4a45ca2d6 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2434,7 +2434,10 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ovs_nla_put_tunnel_info(skb, tun_info); + err = ip_tun_to_nlattr(skb, &tun_info->key, + ip_tunnel_info_opts(tun_info), + tun_info->options_len, + ip_tunnel_info_af(tun_info)); if (err) return err; nla_nest_end(skb, start); diff --git a/net/rds/page.c b/net/rds/page.c index 9005a2c920ee6..5a14e6d6a926a 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -179,37 +179,18 @@ out: } EXPORT_SYMBOL_GPL(rds_page_remainder_alloc); -static int rds_page_remainder_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +void rds_page_exit(void) { - struct rds_page_remainder *rem; - long cpu = (long)hcpu; + unsigned int cpu; - rem = &per_cpu(rds_page_remainders, cpu); + for_each_possible_cpu(cpu) { + struct rds_page_remainder *rem; - rdsdebug("cpu %ld action 0x%lx\n", cpu, action); + rem = &per_cpu(rds_page_remainders, cpu); + rdsdebug("cpu %u\n", cpu); - switch (action) { - case CPU_DEAD: if (rem->r_page) __free_page(rem->r_page); rem->r_page = NULL; - break; } - - return 0; -} - -static struct notifier_block rds_page_remainder_nb = { - .notifier_call = rds_page_remainder_cpu_notify, -}; - -void rds_page_exit(void) -{ - int i; - - for_each_possible_cpu(i) - rds_page_remainder_cpu_notify(&rds_page_remainder_nb, - (unsigned long)CPU_DEAD, - (void *)(long)i); } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index b41e9ea2ffff4..f53bf3b6558b0 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -49,7 +49,6 @@ struct rfkill { spinlock_t lock; - const char *name; enum rfkill_type type; unsigned long state; @@ -73,6 +72,7 @@ struct rfkill { struct delayed_work poll_work; struct work_struct uevent_work; struct work_struct sync_work; + char name[]; }; #define to_rfkill(d) container_of(d, struct rfkill, dev) @@ -876,14 +876,14 @@ struct rfkill * __must_check rfkill_alloc(const char *name, if (WARN_ON(type == RFKILL_TYPE_ALL || type >= NUM_RFKILL_TYPES)) return NULL; - rfkill = kzalloc(sizeof(*rfkill), GFP_KERNEL); + rfkill = kzalloc(sizeof(*rfkill) + strlen(name) + 1, GFP_KERNEL); if (!rfkill) return NULL; spin_lock_init(&rfkill->lock); INIT_LIST_HEAD(&rfkill->node); rfkill->type = type; - rfkill->name = name; + strcpy(rfkill->name, name); rfkill->ops = ops; rfkill->data = ops_data; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7ec667dd4ce1d..b5c2cf2aa6d4b 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -950,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, } lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) - sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 559afd0ee7de0..2bf8ec92dde48 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -383,6 +383,7 @@ void sctp_association_free(struct sctp_association *asoc) list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); list_del_rcu(pos); + sctp_unhash_transport(transport); sctp_transport_free(transport); } @@ -500,6 +501,8 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, /* Remove this peer from the list. */ list_del_rcu(&peer->transports); + /* Remove this peer from the transport hashtable */ + sctp_unhash_transport(peer); /* Get the first transport of asoc. */ pos = asoc->peer.transport_addr_list.next; @@ -699,6 +702,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; + /* Add this peer into the transport hashtable */ + sctp_hash_transport(peer); /* If we do not yet have a primary path, set one. */ if (!asoc->peer.primary_path) { diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 9da76ba4d10fe..52838eaa15821 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -314,21 +314,16 @@ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, } /* Find the association that goes with this chunk. - * We do a linear search of the associations for this endpoint. - * We return the matching transport address too. + * We lookup the transport from hashtable at first, then get association + * through t->assoc. */ -static struct sctp_association *__sctp_endpoint_lookup_assoc( +struct sctp_association *sctp_endpoint_lookup_assoc( const struct sctp_endpoint *ep, const union sctp_addr *paddr, struct sctp_transport **transport) { struct sctp_association *asoc = NULL; - struct sctp_association *tmp; - struct sctp_transport *t = NULL; - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; - int hash; - int rport; + struct sctp_transport *t; *transport = NULL; @@ -337,45 +332,16 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( */ if (!ep->base.bind_addr.port) goto out; + t = sctp_epaddr_lookup_transport(ep, paddr); + if (!t || t->asoc->temp) + goto out; - rport = ntohs(paddr->v4.sin_port); - - hash = sctp_assoc_hashfn(sock_net(ep->base.sk), ep->base.bind_addr.port, - rport); - head = &sctp_assoc_hashtable[hash]; - read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - tmp = sctp_assoc(epb); - if (tmp->ep != ep || rport != tmp->peer.port) - continue; - - t = sctp_assoc_lookup_paddr(tmp, paddr); - if (t) { - asoc = tmp; - *transport = t; - break; - } - } - read_unlock(&head->lock); + *transport = t; + asoc = t->asoc; out: return asoc; } -/* Lookup association on an endpoint based on a peer address. BH-safe. */ -struct sctp_association *sctp_endpoint_lookup_assoc( - const struct sctp_endpoint *ep, - const union sctp_addr *paddr, - struct sctp_transport **transport) -{ - struct sctp_association *asoc; - - local_bh_disable(); - asoc = __sctp_endpoint_lookup_assoc(ep, paddr, transport); - local_bh_enable(); - - return asoc; -} - /* Look for any peeled off association from the endpoint that matches the * given peer address. */ diff --git a/net/sctp/input.c b/net/sctp/input.c index b6493b3f11a97..d9a6e66c5c8a5 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -782,65 +782,135 @@ hit: return ep; } -/* Insert association into the hash table. */ -static void __sctp_hash_established(struct sctp_association *asoc) +/* rhashtable for transport */ +struct sctp_hash_cmp_arg { + const union sctp_addr *laddr; + const union sctp_addr *paddr; + const struct net *net; +}; + +static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - struct net *net = sock_net(asoc->base.sk); - struct sctp_ep_common *epb; - struct sctp_hashbucket *head; + const struct sctp_hash_cmp_arg *x = arg->key; + const struct sctp_transport *t = ptr; + struct sctp_association *asoc = t->asoc; + const struct net *net = x->net; - epb = &asoc->base; + if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port)) + return 1; + if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) + return 1; + if (!net_eq(sock_net(asoc->base.sk), net)) + return 1; + if (!sctp_bind_addr_match(&asoc->base.bind_addr, + x->laddr, sctp_sk(asoc->base.sk))) + return 1; - /* Calculate which chain this entry will belong to. */ - epb->hashent = sctp_assoc_hashfn(net, epb->bind_addr.port, - asoc->peer.port); + return 0; +} - head = &sctp_assoc_hashtable[epb->hashent]; +static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct sctp_transport *t = data; + const union sctp_addr *paddr = &t->ipaddr; + const struct net *net = sock_net(t->asoc->base.sk); + u16 lport = htons(t->asoc->base.bind_addr.port); + u32 addr; + + if (paddr->sa.sa_family == AF_INET6) + addr = jhash(&paddr->v6.sin6_addr, 16, seed); + else + addr = paddr->v4.sin_addr.s_addr; - write_lock(&head->lock); - hlist_add_head(&epb->node, &head->chain); - write_unlock(&head->lock); + return jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 | + (__force __u32)lport, net_hash_mix(net), seed); } -/* Add an association to the hash. Local BH-safe. */ -void sctp_hash_established(struct sctp_association *asoc) +static inline u32 sctp_hash_key(const void *data, u32 len, u32 seed) { - if (asoc->temp) - return; + const struct sctp_hash_cmp_arg *x = data; + const union sctp_addr *paddr = x->paddr; + const struct net *net = x->net; + u16 lport = x->laddr->v4.sin_port; + u32 addr; + + if (paddr->sa.sa_family == AF_INET6) + addr = jhash(&paddr->v6.sin6_addr, 16, seed); + else + addr = paddr->v4.sin_addr.s_addr; - local_bh_disable(); - __sctp_hash_established(asoc); - local_bh_enable(); + return jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 | + (__force __u32)lport, net_hash_mix(net), seed); } -/* Remove association from the hash table. */ -static void __sctp_unhash_established(struct sctp_association *asoc) +static const struct rhashtable_params sctp_hash_params = { + .head_offset = offsetof(struct sctp_transport, node), + .hashfn = sctp_hash_key, + .obj_hashfn = sctp_hash_obj, + .obj_cmpfn = sctp_hash_cmp, + .automatic_shrinking = true, +}; + +int sctp_transport_hashtable_init(void) { - struct net *net = sock_net(asoc->base.sk); - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; + return rhashtable_init(&sctp_transport_hashtable, &sctp_hash_params); +} - epb = &asoc->base; +void sctp_transport_hashtable_destroy(void) +{ + rhashtable_destroy(&sctp_transport_hashtable); +} - epb->hashent = sctp_assoc_hashfn(net, epb->bind_addr.port, - asoc->peer.port); +void sctp_hash_transport(struct sctp_transport *t) +{ + struct sctp_sockaddr_entry *addr; + struct sctp_hash_cmp_arg arg; + + addr = list_entry(t->asoc->base.bind_addr.address_list.next, + struct sctp_sockaddr_entry, list); + arg.laddr = &addr->a; + arg.paddr = &t->ipaddr; + arg.net = sock_net(t->asoc->base.sk); + +reinsert: + if (rhashtable_lookup_insert_key(&sctp_transport_hashtable, &arg, + &t->node, sctp_hash_params) == -EBUSY) + goto reinsert; +} - head = &sctp_assoc_hashtable[epb->hashent]; +void sctp_unhash_transport(struct sctp_transport *t) +{ + rhashtable_remove_fast(&sctp_transport_hashtable, &t->node, + sctp_hash_params); +} - write_lock(&head->lock); - hlist_del_init(&epb->node); - write_unlock(&head->lock); +struct sctp_transport *sctp_addrs_lookup_transport( + struct net *net, + const union sctp_addr *laddr, + const union sctp_addr *paddr) +{ + struct sctp_hash_cmp_arg arg = { + .laddr = laddr, + .paddr = paddr, + .net = net, + }; + + return rhashtable_lookup_fast(&sctp_transport_hashtable, &arg, + sctp_hash_params); } -/* Remove association from the hash table. Local BH-safe. */ -void sctp_unhash_established(struct sctp_association *asoc) +struct sctp_transport *sctp_epaddr_lookup_transport( + const struct sctp_endpoint *ep, + const union sctp_addr *paddr) { - if (asoc->temp) - return; + struct sctp_sockaddr_entry *addr; + struct net *net = sock_net(ep->base.sk); - local_bh_disable(); - __sctp_unhash_established(asoc); - local_bh_enable(); + addr = list_entry(ep->base.bind_addr.address_list.next, + struct sctp_sockaddr_entry, list); + + return sctp_addrs_lookup_transport(net, &addr->a, paddr); } /* Look up an association. */ @@ -850,38 +920,19 @@ static struct sctp_association *__sctp_lookup_association( const union sctp_addr *peer, struct sctp_transport **pt) { - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; - struct sctp_association *asoc; - struct sctp_transport *transport; - int hash; + struct sctp_transport *t; - /* Optimize here for direct hit, only listening connections can - * have wildcards anyways. - */ - hash = sctp_assoc_hashfn(net, ntohs(local->v4.sin_port), - ntohs(peer->v4.sin_port)); - head = &sctp_assoc_hashtable[hash]; - read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - asoc = sctp_assoc(epb); - transport = sctp_assoc_is_match(asoc, net, local, peer); - if (transport) - goto hit; - } - - read_unlock(&head->lock); + t = sctp_addrs_lookup_transport(net, local, peer); + if (!t || t->dead || t->asoc->temp) + return NULL; - return NULL; + sctp_association_hold(t->asoc); + *pt = t; -hit: - *pt = transport; - sctp_association_hold(asoc); - read_unlock(&head->lock); - return asoc; + return t->asoc; } -/* Look up an association. BH-safe. */ +/* Look up an association. protected by RCU read lock */ static struct sctp_association *sctp_lookup_association(struct net *net, const union sctp_addr *laddr, @@ -890,9 +941,9 @@ struct sctp_association *sctp_lookup_association(struct net *net, { struct sctp_association *asoc; - local_bh_disable(); + rcu_read_lock(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp); - local_bh_enable(); + rcu_read_unlock(); return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index acb45b8c2a9d6..ec529121f38a0 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -323,14 +323,13 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } } } - rcu_read_unlock(); - if (baddr) { fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); dst = ip6_dst_lookup_flow(sk, fl6, final_p); } + rcu_read_unlock(); out: if (!IS_ERR_OR_NULL(dst)) { @@ -642,6 +641,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; + struct ipv6_txoptions *opt; newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); if (!newsk) @@ -661,6 +661,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); + /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() * and getpeername(). */ diff --git a/net/sctp/output.c b/net/sctp/output.c index abe7c2db24120..9d610eddd19ef 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -534,7 +534,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + if (!(dst->dev->features & NETIF_F_SCTP_CRC) || (dst_xfrm(dst) != NULL) || packet->ipfragok) { sh->checksum = sctp_compute_cksum(nskb, 0); } else { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 7e8f0a117106c..c0380cfb16ae4 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -324,6 +324,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk) sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); + sctp_chunk_hold(chunk); sctp_outq_tail_data(q, chunk); if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); @@ -1251,6 +1252,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) */ sack_a_rwnd = ntohl(sack->a_rwnd); + asoc->peer.zero_window_announced = !sack_a_rwnd; outstanding = q->outstanding_bytes; if (outstanding < sack_a_rwnd) diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 0697eda5aed8f..dfa7eeccb5373 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -281,88 +281,136 @@ void sctp_eps_proc_exit(struct net *net) remove_proc_entry("eps", net->sctp.proc_net_sctp); } +struct sctp_ht_iter { + struct seq_net_private p; + struct rhashtable_iter hti; +}; -static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) +static struct sctp_transport *sctp_transport_get_next(struct seq_file *seq) { - if (*pos >= sctp_assoc_hashsize) - return NULL; + struct sctp_ht_iter *iter = seq->private; + struct sctp_transport *t; - if (*pos < 0) - *pos = 0; + t = rhashtable_walk_next(&iter->hti); + for (; t; t = rhashtable_walk_next(&iter->hti)) { + if (IS_ERR(t)) { + if (PTR_ERR(t) == -EAGAIN) + continue; + break; + } - if (*pos == 0) - seq_printf(seq, " ASSOC SOCK STY SST ST HBKT " - "ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " - "RPORT LADDRS <-> RADDRS " - "HBINT INS OUTS MAXRT T1X T2X RTXC " - "wmema wmemq sndbuf rcvbuf\n"); + if (net_eq(sock_net(t->asoc->base.sk), seq_file_net(seq)) && + t->asoc->peer.primary_path == t) + break; + } - return (void *)pos; + return t; } -static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) +static struct sctp_transport *sctp_transport_get_idx(struct seq_file *seq, + loff_t pos) +{ + void *obj; + + while (pos && (obj = sctp_transport_get_next(seq)) && !IS_ERR(obj)) + pos--; + + return obj; +} + +static int sctp_transport_walk_start(struct seq_file *seq) { + struct sctp_ht_iter *iter = seq->private; + int err; + + err = rhashtable_walk_init(&sctp_transport_hashtable, &iter->hti); + if (err) + return err; + + err = rhashtable_walk_start(&iter->hti); + + return err == -EAGAIN ? 0 : err; } +static void sctp_transport_walk_stop(struct seq_file *seq) +{ + struct sctp_ht_iter *iter = seq->private; + + rhashtable_walk_stop(&iter->hti); + rhashtable_walk_exit(&iter->hti); +} + +static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) +{ + int err = sctp_transport_walk_start(seq); + + if (err) + return ERR_PTR(err); + + return *pos ? sctp_transport_get_idx(seq, *pos) : SEQ_START_TOKEN; +} + +static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) +{ + sctp_transport_walk_stop(seq); +} static void *sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (++*pos >= sctp_assoc_hashsize) - return NULL; + ++*pos; - return pos; + return sctp_transport_get_next(seq); } /* Display sctp associations (/proc/net/sctp/assocs). */ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) { - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; + struct sctp_transport *transport; struct sctp_association *assoc; + struct sctp_ep_common *epb; struct sock *sk; - int hash = *(loff_t *)v; - - if (hash >= sctp_assoc_hashsize) - return -ENOMEM; - head = &sctp_assoc_hashtable[hash]; - local_bh_disable(); - read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - assoc = sctp_assoc(epb); - sk = epb->sk; - if (!net_eq(sock_net(sk), seq_file_net(seq))) - continue; - seq_printf(seq, - "%8pK %8pK %-3d %-3d %-2d %-4d " - "%4d %8d %8d %7u %5lu %-5d %5d ", - assoc, sk, sctp_sk(sk)->type, sk->sk_state, - assoc->state, hash, - assoc->assoc_id, - assoc->sndbuf_used, - atomic_read(&assoc->rmem_alloc), - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), - sock_i_ino(sk), - epb->bind_addr.port, - assoc->peer.port); - seq_printf(seq, " "); - sctp_seq_dump_local_addrs(seq, epb); - seq_printf(seq, "<-> "); - sctp_seq_dump_remote_addrs(seq, assoc); - seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " - "%8d %8d %8d %8d", - assoc->hbinterval, assoc->c.sinit_max_instreams, - assoc->c.sinit_num_ostreams, assoc->max_retrans, - assoc->init_retries, assoc->shutdown_retries, - assoc->rtx_data_chunks, - atomic_read(&sk->sk_wmem_alloc), - sk->sk_wmem_queued, - sk->sk_sndbuf, - sk->sk_rcvbuf); - seq_printf(seq, "\n"); + if (v == SEQ_START_TOKEN) { + seq_printf(seq, " ASSOC SOCK STY SST ST HBKT " + "ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " + "RPORT LADDRS <-> RADDRS " + "HBINT INS OUTS MAXRT T1X T2X RTXC " + "wmema wmemq sndbuf rcvbuf\n"); + return 0; } - read_unlock(&head->lock); - local_bh_enable(); + + transport = (struct sctp_transport *)v; + assoc = transport->asoc; + epb = &assoc->base; + sk = epb->sk; + + seq_printf(seq, + "%8pK %8pK %-3d %-3d %-2d %-4d " + "%4d %8d %8d %7u %5lu %-5d %5d ", + assoc, sk, sctp_sk(sk)->type, sk->sk_state, + assoc->state, 0, + assoc->assoc_id, + assoc->sndbuf_used, + atomic_read(&assoc->rmem_alloc), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), + sock_i_ino(sk), + epb->bind_addr.port, + assoc->peer.port); + seq_printf(seq, " "); + sctp_seq_dump_local_addrs(seq, epb); + seq_printf(seq, "<-> "); + sctp_seq_dump_remote_addrs(seq, assoc); + seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " + "%8d %8d %8d %8d", + assoc->hbinterval, assoc->c.sinit_max_instreams, + assoc->c.sinit_num_ostreams, assoc->max_retrans, + assoc->init_retries, assoc->shutdown_retries, + assoc->rtx_data_chunks, + atomic_read(&sk->sk_wmem_alloc), + sk->sk_wmem_queued, + sk->sk_sndbuf, + sk->sk_rcvbuf); + seq_printf(seq, "\n"); return 0; } @@ -378,7 +426,7 @@ static const struct seq_operations sctp_assoc_ops = { static int sctp_assocs_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &sctp_assoc_ops, - sizeof(struct seq_net_private)); + sizeof(struct sctp_ht_iter)); } static const struct file_operations sctp_assocs_seq_fops = { @@ -409,112 +457,94 @@ void sctp_assocs_proc_exit(struct net *net) static void *sctp_remaddr_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos >= sctp_assoc_hashsize) - return NULL; - - if (*pos < 0) - *pos = 0; + int err = sctp_transport_walk_start(seq); - if (*pos == 0) - seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " - "REM_ADDR_RTX START STATE\n"); + if (err) + return ERR_PTR(err); - return (void *)pos; + return *pos ? sctp_transport_get_idx(seq, *pos) : SEQ_START_TOKEN; } static void *sctp_remaddr_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (++*pos >= sctp_assoc_hashsize) - return NULL; + ++*pos; - return pos; + return sctp_transport_get_next(seq); } static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v) { + sctp_transport_walk_stop(seq); } static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) { - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; struct sctp_association *assoc; struct sctp_transport *tsp; - int hash = *(loff_t *)v; - if (hash >= sctp_assoc_hashsize) - return -ENOMEM; + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " + "REM_ADDR_RTX START STATE\n"); + return 0; + } - head = &sctp_assoc_hashtable[hash]; - local_bh_disable(); - read_lock(&head->lock); - rcu_read_lock(); - sctp_for_each_hentry(epb, &head->chain) { - if (!net_eq(sock_net(epb->sk), seq_file_net(seq))) + tsp = (struct sctp_transport *)v; + assoc = tsp->asoc; + + list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, + transports) { + if (tsp->dead) continue; - assoc = sctp_assoc(epb); - list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, - transports) { - if (tsp->dead) - continue; + /* + * The remote address (ADDR) + */ + tsp->af_specific->seq_dump_addr(seq, &tsp->ipaddr); + seq_printf(seq, " "); + /* + * The association ID (ASSOC_ID) + */ + seq_printf(seq, "%d ", tsp->asoc->assoc_id); + + /* + * If the Heartbeat is active (HB_ACT) + * Note: 1 = Active, 0 = Inactive + */ + seq_printf(seq, "%d ", timer_pending(&tsp->hb_timer)); + + /* + * Retransmit time out (RTO) + */ + seq_printf(seq, "%lu ", tsp->rto); + + /* + * Maximum path retransmit count (PATH_MAX_RTX) + */ + seq_printf(seq, "%d ", tsp->pathmaxrxt); + + /* + * remote address retransmit count (REM_ADDR_RTX) + * Note: We don't have a way to tally this at the moment + * so lets just leave it as zero for the moment + */ + seq_puts(seq, "0 "); + + /* + * remote address start time (START). This is also not + * currently implemented, but we can record it with a + * jiffies marker in a subsequent patch + */ + seq_puts(seq, "0 "); + + /* + * The current state of this destination. I.e. + * SCTP_ACTIVE, SCTP_INACTIVE, ... + */ + seq_printf(seq, "%d", tsp->state); - /* - * The remote address (ADDR) - */ - tsp->af_specific->seq_dump_addr(seq, &tsp->ipaddr); - seq_printf(seq, " "); - - /* - * The association ID (ASSOC_ID) - */ - seq_printf(seq, "%d ", tsp->asoc->assoc_id); - - /* - * If the Heartbeat is active (HB_ACT) - * Note: 1 = Active, 0 = Inactive - */ - seq_printf(seq, "%d ", timer_pending(&tsp->hb_timer)); - - /* - * Retransmit time out (RTO) - */ - seq_printf(seq, "%lu ", tsp->rto); - - /* - * Maximum path retransmit count (PATH_MAX_RTX) - */ - seq_printf(seq, "%d ", tsp->pathmaxrxt); - - /* - * remote address retransmit count (REM_ADDR_RTX) - * Note: We don't have a way to tally this at the moment - * so lets just leave it as zero for the moment - */ - seq_puts(seq, "0 "); - - /* - * remote address start time (START). This is also not - * currently implemented, but we can record it with a - * jiffies marker in a subsequent patch - */ - seq_puts(seq, "0 "); - - /* - * The current state of this destination. I.e. - * SCTP_ACTIVE, SCTP_INACTIVE, ... - */ - seq_printf(seq, "%d", tsp->state); - - seq_printf(seq, "\n"); - } + seq_printf(seq, "\n"); } - rcu_read_unlock(); - read_unlock(&head->lock); - local_bh_enable(); - return 0; - } static const struct seq_operations sctp_remaddr_ops = { @@ -533,7 +563,7 @@ void sctp_remaddr_proc_exit(struct net *net) static int sctp_remaddr_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &sctp_remaddr_ops, - sizeof(struct seq_net_private)); + sizeof(struct sctp_ht_iter)); } static const struct file_operations sctp_remaddr_seq_fops = { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 3d9ea9a48289a..ab0d538a74ed5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1223,6 +1223,9 @@ static int __net_init sctp_defaults_init(struct net *net) /* Max.Burst - 4 */ net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST; + /* Enable pf state by default */ + net->sctp.pf_enable = 1; + /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) * Max.Init.Retransmits - 8 attempts @@ -1413,24 +1416,6 @@ static __init int sctp_init(void) for (order = 0; (1UL << order) < goal; order++) ; - do { - sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_hashbucket); - if ((sctp_assoc_hashsize > (64 * 1024)) && order > 0) - continue; - sctp_assoc_hashtable = (struct sctp_hashbucket *) - __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); - } while (!sctp_assoc_hashtable && --order > 0); - if (!sctp_assoc_hashtable) { - pr_err("Failed association hash alloc\n"); - status = -ENOMEM; - goto err_ahash_alloc; - } - for (i = 0; i < sctp_assoc_hashsize; i++) { - rwlock_init(&sctp_assoc_hashtable[i].lock); - INIT_HLIST_HEAD(&sctp_assoc_hashtable[i].chain); - } - /* Allocate and initialize the endpoint hash table. */ sctp_ep_hashsize = 64; sctp_ep_hashtable = @@ -1452,7 +1437,7 @@ static __init int sctp_init(void) if ((sctp_port_hashsize > (64 * 1024)) && order > 0) continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); + __get_free_pages(GFP_KERNEL | __GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); @@ -1464,8 +1449,10 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } - pr_info("Hash tables configured (established %d bind %d)\n", - sctp_assoc_hashsize, sctp_port_hashsize); + if (sctp_transport_hashtable_init()) + goto err_thash_alloc; + + pr_info("Hash tables configured (bind %d)\n", sctp_port_hashsize); sctp_sysctl_register(); @@ -1518,12 +1505,10 @@ err_register_defaults: get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); err_bhash_alloc: + sctp_transport_hashtable_destroy(); +err_thash_alloc: kfree(sctp_ep_hashtable); err_ehash_alloc: - free_pages((unsigned long)sctp_assoc_hashtable, - get_order(sctp_assoc_hashsize * - sizeof(struct sctp_hashbucket))); -err_ahash_alloc: percpu_counter_destroy(&sctp_sockets_allocated); err_percpu_counter_init: kmem_cache_destroy(sctp_chunk_cachep); @@ -1557,13 +1542,11 @@ static __exit void sctp_exit(void) sctp_sysctl_unregister(); - free_pages((unsigned long)sctp_assoc_hashtable, - get_order(sctp_assoc_hashsize * - sizeof(struct sctp_hashbucket))); - kfree(sctp_ep_hashtable); free_pages((unsigned long)sctp_port_hashtable, get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); + kfree(sctp_ep_hashtable); + sctp_transport_hashtable_destroy(); percpu_counter_destroy(&sctp_sockets_allocated); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 763e06a55155b..5d6a03fad3789 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, /* Set an expiration time for the cookie. */ cookie->c.expiration = ktime_add(asoc->cookie_life, - ktime_get()); + ktime_get_real()); /* Copy the peer's init packet. */ memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr, @@ -1780,7 +1780,7 @@ no_hmac: if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) kt = skb_get_ktime(skb); else - kt = ktime_get(); + kt = ktime_get_real(); if (!asoc && ktime_before(bear_cookie->expiration, kt)) { /* diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 6098d4c42fa91..4f170ad38ff4f 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -477,6 +477,8 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, struct sctp_transport *transport, int is_hb) { + struct net *net = sock_net(asoc->base.sk); + /* The check for association's overall error counter exceeding the * threshold is done in the state function. */ @@ -503,7 +505,8 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, * is SCTP_ACTIVE, then mark this transport as Partially Failed, * see SCTP Quick Failover Draft, section 5.1 */ - if ((transport->state == SCTP_ACTIVE) && + if (net->sctp.pf_enable && + (transport->state == SCTP_ACTIVE) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { @@ -863,7 +866,6 @@ static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, (!asoc->temp) && (sk->sk_shutdown != SHUTDOWN_MASK)) return; - sctp_unhash_established(asoc); sctp_association_free(asoc); } @@ -1266,7 +1268,6 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, asoc = cmd->obj.asoc; BUG_ON(asoc->peer.primary_path == NULL); sctp_endpoint_add_asoc(ep, asoc); - sctp_hash_established(asoc); break; case SCTP_CMD_UPDATE_ASSOC: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 6f46aa16cb769..22c2bf367d7e8 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort( retval = SCTP_DISPOSITION_CONSUME; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); /* Even if we can't send the ABORT due to low memory delete the * TCB. This is a departure from our typical NOMEM handling. @@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort( SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); retval = SCTP_DISPOSITION_CONSUME; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); @@ -5412,7 +5414,8 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_T3_RTX_EXPIREDS); if (asoc->overall_error_count >= asoc->max_retrans) { - if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { + if (asoc->peer.zero_window_announced && + asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { /* * We are here likely because the receiver had its rwnd * closed for a while and we have not been able to diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 106bb09636f1c..9bb80ec4c08ff 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1228,7 +1228,6 @@ out_free: * To the hash table, try to unhash it, just in case, its a noop * if it wasn't hashed so we're safe */ - sctp_unhash_established(asoc); sctp_association_free(asoc); } return err; @@ -1301,8 +1300,9 @@ static int __sctp_setsockopt_connectx(struct sock *sk, int addrs_size, sctp_assoc_t *assoc_id) { - int err = 0; struct sockaddr *kaddrs; + gfp_t gfp = GFP_KERNEL; + int err = 0; pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, addrs, addrs_size); @@ -1315,7 +1315,9 @@ static int __sctp_setsockopt_connectx(struct sock *sk, return -EFAULT; /* Alloc space for the address array in kernel memory. */ - kaddrs = kmalloc(addrs_size, GFP_KERNEL); + if (sk->sk_socket->file) + gfp = GFP_USER | __GFP_NOWARN; + kaddrs = kmalloc(addrs_size, gfp); if (unlikely(!kaddrs)) return -ENOMEM; @@ -1501,7 +1503,6 @@ static void sctp_close(struct sock *sk, long timeout) * ABORT or SHUTDOWN based on the linger options. */ if (sctp_state(asoc, CLOSED)) { - sctp_unhash_established(asoc); sctp_association_free(asoc); continue; } @@ -1513,8 +1514,7 @@ static void sctp_close(struct sock *sk, long timeout) struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); - if (chunk) - sctp_primitive_ABORT(net, asoc, chunk); + sctp_primitive_ABORT(net, asoc, chunk); } else sctp_primitive_SHUTDOWN(net, asoc, NULL); } @@ -1952,8 +1952,6 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* Now send the (possibly) fragmented message. */ list_for_each_entry(chunk, &datamsg->chunks, frag_list) { - sctp_chunk_hold(chunk); - /* Do accounting for the write space. */ sctp_set_owner_w(chunk); @@ -1966,15 +1964,13 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) * breaks. */ err = sctp_primitive_SEND(net, asoc, datamsg); + sctp_datamsg_put(datamsg); /* Did the lower layer accept the chunk? */ - if (err) { - sctp_datamsg_free(datamsg); + if (err) goto out_free; - } pr_debug("%s: we sent primitively\n", __func__); - sctp_datamsg_put(datamsg); err = msg_len; if (unlikely(wait_connect)) { @@ -1988,10 +1984,8 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_unlock; out_free: - if (new_asoc) { - sctp_unhash_established(asoc); + if (new_asoc) sctp_association_free(asoc); - } out_unlock: release_sock(sk); @@ -5777,7 +5771,7 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, len = sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num; - ids = kmalloc(len, GFP_KERNEL); + ids = kmalloc(len, GFP_USER | __GFP_NOWARN); if (unlikely(!ids)) return -ENOMEM; @@ -7167,6 +7161,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; newsk->sk_flags = sk->sk_flags; + newsk->sk_tsflags = sk->sk_tsflags; newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; @@ -7199,6 +7194,11 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; + + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); + + security_sk_clone(sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 26d50c565f542..ccbfc93fb8fec 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -308,6 +308,13 @@ static struct ctl_table sctp_net_table[] = { .extra1 = &max_autoclose_min, .extra2 = &max_autoclose_max, }, + { + .procname = "pf_enable", + .data = &init_net.sctp.pf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { /* sentinel */ } }; diff --git a/net/socket.c b/net/socket.c index 456fadb3d8193..d730ef9dfbf02 100644 --- a/net/socket.c +++ b/net/socket.c @@ -257,6 +257,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb) } init_waitqueue_head(&wq->wait); wq->fasync_list = NULL; + wq->flags = 0; RCU_INIT_POINTER(ei->socket.wq, wq); ei->socket.state = SS_UNCONNECTED; @@ -1695,6 +1696,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_name = addr ? (struct sockaddr *)&address : NULL; /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; + msg.msg_iocb = NULL; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags); diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 95f82d8d48887..229956bf84577 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -353,20 +353,12 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) { struct rpc_xprt *xprt = req->rq_xprt; struct svc_serv *bc_serv = xprt->bc_serv; - struct xdr_buf *rq_rcv_buf = &req->rq_rcv_buf; spin_lock(&xprt->bc_pa_lock); list_del(&req->rq_bc_pa_list); xprt_dec_alloc_count(xprt, 1); spin_unlock(&xprt->bc_pa_lock); - if (copied <= rq_rcv_buf->head[0].iov_len) { - rq_rcv_buf->head[0].iov_len = copied; - rq_rcv_buf->page_len = 0; - } else { - rq_rcv_buf->page_len = copied - rq_rcv_buf->head[0].iov_len; - } - req->rq_private_buf.len = copied; set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index f14f24ee99834..73ad57a59989c 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -250,11 +250,11 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue) } EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); -static int rpc_wait_bit_killable(struct wait_bit_key *key) +static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 7fccf9675df8c..cc9852897395c 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1363,7 +1363,19 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg)); memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res)); + + /* Adjust the argument buffer length */ rqstp->rq_arg.len = req->rq_private_buf.len; + if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) { + rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len; + rqstp->rq_arg.page_len = 0; + } else if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len + + rqstp->rq_arg.page_len) + rqstp->rq_arg.page_len = rqstp->rq_arg.len - + rqstp->rq_arg.head[0].iov_len; + else + rqstp->rq_arg.len = rqstp->rq_arg.head[0].iov_len + + rqstp->rq_arg.page_len; /* reset result send buffer "put" position */ resv->iov_len = 0; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index f34e535e93bdf..df790d3385a22 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -723,6 +723,7 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, u32 filter_mask) { struct switchdev_vlan_dump dump = { + .vlan.obj.orig_dev = dev, .vlan.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .skb = skb, .filter_mask = filter_mask, @@ -757,6 +758,7 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int nlflags) { struct switchdev_attr attr = { + .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u16 mode = BRIDGE_MODE_UNDEF; @@ -778,6 +780,7 @@ static int switchdev_port_br_setflag(struct net_device *dev, unsigned long brport_flag) { struct switchdev_attr attr = { + .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u8 flag = nla_get_u8(nlattr); @@ -853,6 +856,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, struct nlattr *attr; struct bridge_vlan_info *vinfo; struct switchdev_obj_port_vlan vlan = { + .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, }; int rem; @@ -975,6 +979,7 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], u16 vid, u16 nlm_flags) { struct switchdev_obj_port_fdb fdb = { + .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .vid = vid, }; @@ -1000,6 +1005,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], u16 vid) { struct switchdev_obj_port_fdb fdb = { + .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .vid = vid, }; @@ -1077,6 +1083,7 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *filter_dev, int idx) { struct switchdev_fdb_dump dump = { + .fdb.obj.orig_dev = dev, .fdb.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .dev = dev, .skb = skb, @@ -1135,6 +1142,7 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) if (!dev) return NULL; + attr.orig_dev = dev; if (switchdev_port_attr_get(dev, &attr)) return NULL; @@ -1194,6 +1202,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; + ipv4_fib.obj.orig_dev = dev; err = switchdev_port_obj_add(dev, &ipv4_fib.obj); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -1238,6 +1247,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; + ipv4_fib.obj.orig_dev = dev; err = switchdev_port_obj_del(dev, &ipv4_fib.obj); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; @@ -1270,10 +1280,12 @@ static bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct switchdev_attr a_attr = { + .orig_dev = a, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; struct switchdev_attr b_attr = { + .orig_dev = b, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 6af78c6276b4b..d63a911e7fe29 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -182,15 +182,9 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, goto tx_error; } ttl = ip4_dst_hoplimit(&rt->dst); - err = udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, - src->ipv4.s_addr, - dst->ipv4.s_addr, 0, ttl, 0, - src->udp_port, dst->udp_port, - false, true); - if (err < 0) { - ip_rt_put(rt); - goto tx_error; - } + udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr, + dst->ipv4.s_addr, 0, ttl, 0, src->udp_port, + dst->udp_port, false, true); #if IS_ENABLED(CONFIG_IPV6) } else { struct dst_entry *ndst; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1c3c1f3a3ec4f..b1314c0994175 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2263,14 +2263,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ - err = mutex_lock_interruptible(&u->readlock); - if (unlikely(err)) { - /* recvmsg() in non blocking mode is supposed to return -EAGAIN - * sk_rcvtimeo is not honored by mutex_lock_interruptible() - */ - err = noblock ? -EAGAIN : -ERESTARTSYS; - goto out; - } + mutex_lock(&u->readlock); if (flags & MSG_PEEK) skip = sk_peek_offset(sk, flags); @@ -2314,12 +2307,12 @@ again: timeo = unix_stream_data_wait(sk, timeo, last, last_len); - if (signal_pending(current) || - mutex_lock_interruptible(&u->readlock)) { + if (signal_pending(current)) { err = sock_intr_errno(timeo); goto out; } + mutex_lock(&u->readlock); continue; unlock: unix_state_unlock(sk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 72de6989dd124..d4786f2802aa3 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7973,8 +7973,10 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) { if (!(rdev->wiphy.features & NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) || - !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) + !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) { + kzfree(connkeys); return -EINVAL; + } connect.flags |= ASSOC_REQ_USE_RRM; } @@ -9535,6 +9537,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) if (new_triggers.tcp && new_triggers.tcp->sock) sock_release(new_triggers.tcp->sock); kfree(new_triggers.tcp); + kfree(new_triggers.nd_config); return err; } #endif diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0a4f5481ab836..3b0ce1c484a3d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3011,6 +3011,7 @@ int set_regdom(const struct ieee80211_regdomain *rd, break; default: WARN(1, "invalid initiator %d\n", lr->initiator); + kfree(rd); return -EINVAL; } @@ -3203,8 +3204,10 @@ int __init regulatory_init(void) /* We always try to get an update for the static regdomain */ err = regulatory_hint_core(cfg80211_world_regdom->alpha2); if (err) { - if (err == -ENOMEM) + if (err == -ENOMEM) { + platform_device_unregister(reg_pdev); return err; + } /* * N.B. kobject_uevent_env() can fail mainly for when we're out * memory which is handled and propagated appropriately above diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 09bfcbac63bb3..b5e665b3cfb05 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -303,6 +303,14 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) } EXPORT_SYMBOL(xfrm_policy_alloc); +static void xfrm_policy_destroy_rcu(struct rcu_head *head) +{ + struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu); + + security_xfrm_policy_free(policy->security); + kfree(policy); +} + /* Destroy xfrm_policy: descendant resources must be released to this moment. */ void xfrm_policy_destroy(struct xfrm_policy *policy) @@ -312,8 +320,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); - security_xfrm_policy_free(policy->security); - kfree(policy); + call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); @@ -1214,8 +1221,10 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, struct xfrm_policy *pol; struct net *net = sock_net(sk); + rcu_read_lock(); read_lock_bh(&net->xfrm.xfrm_policy_lock); - if ((pol = sk->sk_policy[dir]) != NULL) { + pol = rcu_dereference(sk->sk_policy[dir]); + if (pol != NULL) { bool match = xfrm_selector_match(&pol->selector, fl, sk->sk_family); int err = 0; @@ -1239,6 +1248,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, } out: read_unlock_bh(&net->xfrm.xfrm_policy_lock); + rcu_read_unlock(); return pol; } @@ -1307,13 +1317,14 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) #endif write_lock_bh(&net->xfrm.xfrm_policy_lock); - old_pol = sk->sk_policy[dir]; - sk->sk_policy[dir] = pol; + old_pol = rcu_dereference_protected(sk->sk_policy[dir], + lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { pol->curlft.add_time = get_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } + rcu_assign_pointer(sk->sk_policy[dir], pol); if (old_pol) { if (pol) xfrm_policy_requeue(old_pol, pol); @@ -1361,17 +1372,26 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) return newp; } -int __xfrm_sk_clone_policy(struct sock *sk) +int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { - struct xfrm_policy *p0 = sk->sk_policy[0], - *p1 = sk->sk_policy[1]; + const struct xfrm_policy *p; + struct xfrm_policy *np; + int i, ret = 0; - sk->sk_policy[0] = sk->sk_policy[1] = NULL; - if (p0 && (sk->sk_policy[0] = clone_policy(p0, 0)) == NULL) - return -ENOMEM; - if (p1 && (sk->sk_policy[1] = clone_policy(p1, 1)) == NULL) - return -ENOMEM; - return 0; + rcu_read_lock(); + for (i = 0; i < 2; i++) { + p = rcu_dereference(osk->sk_policy[i]); + if (p) { + np = clone_policy(p, i); + if (unlikely(!np)) { + ret = -ENOMEM; + break; + } + rcu_assign_pointer(sk->sk_policy[i], np); + } + } + rcu_read_unlock(); + return ret; } static int @@ -2198,6 +2218,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, xdst = NULL; route = NULL; + sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); @@ -2477,6 +2498,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } pol = NULL; + sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl); if (IS_ERR(pol)) { @@ -2804,7 +2826,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { - struct net *net; int err = 0; if (unlikely(afinfo == NULL)) return -EINVAL; @@ -2835,26 +2856,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) } spin_unlock(&xfrm_policy_afinfo_lock); - rtnl_lock(); - for_each_net(net) { - struct dst_ops *xfrm_dst_ops; - - switch (afinfo->family) { - case AF_INET: - xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops; - break; -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops; - break; -#endif - default: - BUG(); - } - *xfrm_dst_ops = *afinfo->dst_ops; - } - rtnl_unlock(); - return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); @@ -2890,22 +2891,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); -static void __net_init xfrm_dst_ops_init(struct net *net) -{ - struct xfrm_policy_afinfo *afinfo; - - rcu_read_lock(); - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]); - if (afinfo) - net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; -#if IS_ENABLED(CONFIG_IPV6) - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]); - if (afinfo) - net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; -#endif - rcu_read_unlock(); -} - static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -3054,7 +3039,6 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; - xfrm_dst_ops_init(net); rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 1a10d8ac81620..dacf71a43ad41 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -62,7 +62,7 @@ vmlinux_link() -Wl,--start-group \ ${KBUILD_VMLINUX_MAIN} \ -Wl,--end-group \ - -lutil ${1} + -lutil -lrt ${1} rm -f linux fi } diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 698768bdc5815..301d70b0174f3 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -48,12 +48,17 @@ static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ -static void *ehdr_curr; /* current ElfXX_Ehdr * for resource cleanup */ static char gpfx; /* prefix for global symbol name (sometimes '_') */ static struct stat sb; /* Remember .st_size, etc. */ static jmp_buf jmpenv; /* setjmp/longjmp per-file error escape */ static const char *altmcount; /* alternate mcount symbol name */ static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */ +static void *file_map; /* pointer of the mapped file */ +static void *file_end; /* pointer to the end of the mapped file */ +static int file_updated; /* flag to state file was changed */ +static void *file_ptr; /* current file pointer location */ +static void *file_append; /* added to the end of the file */ +static size_t file_append_size; /* how much is added to end of file */ /* setjmp() return values */ enum { @@ -67,10 +72,14 @@ static void cleanup(void) { if (!mmap_failed) - munmap(ehdr_curr, sb.st_size); + munmap(file_map, sb.st_size); else - free(ehdr_curr); - close(fd_map); + free(file_map); + file_map = NULL; + free(file_append); + file_append = NULL; + file_append_size = 0; + file_updated = 0; } static void __attribute__((noreturn)) @@ -92,12 +101,22 @@ succeed_file(void) static off_t ulseek(int const fd, off_t const offset, int const whence) { - off_t const w = lseek(fd, offset, whence); - if (w == (off_t)-1) { - perror("lseek"); + switch (whence) { + case SEEK_SET: + file_ptr = file_map + offset; + break; + case SEEK_CUR: + file_ptr += offset; + break; + case SEEK_END: + file_ptr = file_map + (sb.st_size - offset); + break; + } + if (file_ptr < file_map) { + fprintf(stderr, "lseek: seek before file\n"); fail_file(); } - return w; + return file_ptr - file_map; } static size_t @@ -114,12 +133,38 @@ uread(int const fd, void *const buf, size_t const count) static size_t uwrite(int const fd, void const *const buf, size_t const count) { - size_t const n = write(fd, buf, count); - if (n != count) { - perror("write"); - fail_file(); + size_t cnt = count; + off_t idx = 0; + + file_updated = 1; + + if (file_ptr + count >= file_end) { + off_t aoffset = (file_ptr + count) - file_end; + + if (aoffset > file_append_size) { + file_append = realloc(file_append, aoffset); + file_append_size = aoffset; + } + if (!file_append) { + perror("write"); + fail_file(); + } + if (file_ptr < file_end) { + cnt = file_end - file_ptr; + } else { + cnt = 0; + idx = aoffset - count; + } } - return n; + + if (cnt) + memcpy(file_ptr, buf, cnt); + + if (cnt < count) + memcpy(file_append + idx, buf + cnt, count - cnt); + + file_ptr += count; + return count; } static void * @@ -192,9 +237,7 @@ static int make_nop_arm64(void *map, size_t const offset) */ static void *mmap_file(char const *fname) { - void *addr; - - fd_map = open(fname, O_RDWR); + fd_map = open(fname, O_RDONLY); if (fd_map < 0 || fstat(fd_map, &sb) < 0) { perror(fname); fail_file(); @@ -203,15 +246,58 @@ static void *mmap_file(char const *fname) fprintf(stderr, "not a regular file: %s\n", fname); fail_file(); } - addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE, - fd_map, 0); + file_map = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE, + fd_map, 0); mmap_failed = 0; - if (addr == MAP_FAILED) { + if (file_map == MAP_FAILED) { mmap_failed = 1; - addr = umalloc(sb.st_size); - uread(fd_map, addr, sb.st_size); + file_map = umalloc(sb.st_size); + uread(fd_map, file_map, sb.st_size); + } + close(fd_map); + + file_end = file_map + sb.st_size; + + return file_map; +} + +static void write_file(const char *fname) +{ + char tmp_file[strlen(fname) + 4]; + size_t n; + + if (!file_updated) + return; + + sprintf(tmp_file, "%s.rc", fname); + + /* + * After reading the entire file into memory, delete it + * and write it back, to prevent weird side effects of modifying + * an object file in place. + */ + fd_map = open(tmp_file, O_WRONLY | O_TRUNC | O_CREAT, sb.st_mode); + if (fd_map < 0) { + perror(fname); + fail_file(); + } + n = write(fd_map, file_map, sb.st_size); + if (n != sb.st_size) { + perror("write"); + fail_file(); + } + if (file_append_size) { + n = write(fd_map, file_append, file_append_size); + if (n != file_append_size) { + perror("write"); + fail_file(); + } + } + close(fd_map); + if (rename(tmp_file, fname) < 0) { + perror(fname); + fail_file(); } - return addr; } /* w8rev, w8nat, ...: Handle endianness. */ @@ -318,7 +404,6 @@ do_file(char const *const fname) Elf32_Ehdr *const ehdr = mmap_file(fname); unsigned int reltype = 0; - ehdr_curr = ehdr; w = w4nat; w2 = w2nat; w8 = w8nat; @@ -441,6 +526,7 @@ do_file(char const *const fname) } } /* end switch */ + write_file(fname); cleanup(); } @@ -493,11 +579,14 @@ main(int argc, char *argv[]) case SJ_SETJMP: /* normal sequence */ /* Avoid problems if early cleanup() */ fd_map = -1; - ehdr_curr = NULL; mmap_failed = 1; + file_map = NULL; + file_ptr = NULL; + file_updated = 0; do_file(file); break; case SJ_FAIL: /* error in do_file or below */ + sprintf("%s: failed\n", file); ++n_error; break; case SJ_SUCCEED: /* premature success */ diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index fb111eafcb893..1c3872aeed14a 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -751,16 +751,16 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) /* the key is probably readable - now try to read it */ can_read_key: - ret = key_validate(key); - if (ret == 0) { - ret = -EOPNOTSUPP; - if (key->type->read) { - /* read the data with the semaphore held (since we - * might sleep) */ - down_read(&key->sem); + ret = -EOPNOTSUPP; + if (key->type->read) { + /* Read the data with the semaphore held (since we might sleep) + * to protect against the key being updated or revoked. + */ + down_read(&key->sem); + ret = key_validate(key); + if (ret == 0) ret = key->type->read(key, buffer, buflen); - up_read(&key->sem); - } + up_read(&key->sem); } error2: diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 963f82430938a..3b36582970702 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -355,6 +355,8 @@ enum { ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c)) +#define IS_BROXTON(pci) ((pci)->device == 0x5a98) + static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", [AZX_DRIVER_PCH] = "HDA Intel PCH", @@ -506,15 +508,36 @@ static void azx_init_pci(struct azx *chip) } } +/* + * In BXT-P A0, HD-Audio DMA requests is later than expected, + * and makes an audio stream sensitive to system latencies when + * 24/32 bits are playing. + * Adjusting threshold of DMA fifo to force the DMA request + * sooner to improve latency tolerance at the expense of power. + */ +static void bxt_reduce_dma_latency(struct azx *chip) +{ + u32 val; + + val = azx_readl(chip, SKL_EM4L); + val &= (0x3 << 20); + azx_writel(chip, SKL_EM4L, val); +} + static void hda_intel_init_chip(struct azx *chip, bool full_reset) { struct hdac_bus *bus = azx_bus(chip); + struct pci_dev *pci = chip->pci; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); azx_init_chip(chip, full_reset); if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, false); + + /* reduce dma latency to avoid noise */ + if (IS_BROXTON(pci)) + bxt_reduce_dma_latency(chip); } /* calculate runtime delay from LPIB */ @@ -931,6 +954,36 @@ static int azx_resume(struct device *dev) } #endif /* CONFIG_PM_SLEEP || SUPPORT_VGA_SWITCHEROO */ +#ifdef CONFIG_PM_SLEEP +/* put codec down to D3 at hibernation for Intel SKL+; + * otherwise BIOS may still access the codec and screw up the driver + */ +#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) +#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) +#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) + +static int azx_freeze_noirq(struct device *dev) +{ + struct pci_dev *pci = to_pci_dev(dev); + + if (IS_SKL_PLUS(pci)) + pci_set_power_state(pci, PCI_D3hot); + + return 0; +} + +static int azx_thaw_noirq(struct device *dev) +{ + struct pci_dev *pci = to_pci_dev(dev); + + if (IS_SKL_PLUS(pci)) + pci_set_power_state(pci, PCI_D0); + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + #ifdef CONFIG_PM static int azx_runtime_suspend(struct device *dev) { @@ -1040,6 +1093,10 @@ static int azx_runtime_idle(struct device *dev) static const struct dev_pm_ops azx_pm = { SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume) +#ifdef CONFIG_PM_SLEEP + .freeze_noirq = azx_freeze_noirq, + .thaw_noirq = azx_thaw_noirq, +#endif SET_RUNTIME_PM_OPS(azx_runtime_suspend, azx_runtime_resume, azx_runtime_idle) }; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index f8a12ca477f1a..4ef2259f88cae 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -778,7 +778,8 @@ static const struct hda_pintbl alienware_pincfgs[] = { }; static const struct snd_pci_quirk ca0132_quirks[] = { - SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15", QUIRK_ALIENWARE), + SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE), + SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE), {} }; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index c8b8ef5246a6f..ef198903c0c3e 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -955,6 +955,7 @@ static int patch_conexant_auto(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_conexant[] = { + HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto), @@ -972,9 +973,9 @@ static const struct hda_device_id snd_hda_id_conexant[] = { HDA_CODEC_ENTRY(0x14f150ac, "CX20652", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f150b8, "CX20664", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f150b9, "CX20665", patch_conexant_auto), - HDA_CODEC_ENTRY(0x14f150f1, "CX20721", patch_conexant_auto), + HDA_CODEC_ENTRY(0x14f150f1, "CX21722", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f150f2, "CX20722", patch_conexant_auto), - HDA_CODEC_ENTRY(0x14f150f3, "CX20723", patch_conexant_auto), + HDA_CODEC_ENTRY(0x14f150f3, "CX21724", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f150f4, "CX20724", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f1510f, "CX20751/2", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15110, "CX20751/2", patch_conexant_auto), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index bdb6f226d0068..4b6fb668c91cd 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2352,6 +2352,12 @@ static void intel_pin_eld_notify(void *audio_ptr, int port) struct hda_codec *codec = audio_ptr; int pin_nid = port + 0x04; + /* skip notification during system suspend (but not in runtime PM); + * the state will be updated at resume + */ + if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0) + return; + check_presence_and_report(codec, pin_nid); } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 9bedf7c85e295..fe96428aa4034 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -111,6 +111,7 @@ struct alc_spec { void (*power_hook)(struct hda_codec *codec); #endif void (*shutup)(struct hda_codec *codec); + void (*reboot_notify)(struct hda_codec *codec); int init_amp; int codec_variant; /* flag for other variants */ @@ -773,6 +774,25 @@ static inline void alc_shutup(struct hda_codec *codec) snd_hda_shutup_pins(codec); } +static void alc_reboot_notify(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + + if (spec && spec->reboot_notify) + spec->reboot_notify(codec); + else + alc_shutup(codec); +} + +/* power down codec to D3 at reboot/shutdown; set as reboot_notify ops */ +static void alc_d3_at_reboot(struct hda_codec *codec) +{ + snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3); + snd_hda_codec_write(codec, codec->core.afg, 0, + AC_VERB_SET_POWER_STATE, AC_PWRST_D3); + msleep(10); +} + #define alc_free snd_hda_gen_free #ifdef CONFIG_PM @@ -818,7 +838,7 @@ static const struct hda_codec_ops alc_patch_ops = { .suspend = alc_suspend, .check_power_status = snd_hda_gen_check_power_status, #endif - .reboot_notify = alc_shutup, + .reboot_notify = alc_reboot_notify, }; @@ -1755,6 +1775,7 @@ enum { ALC889_FIXUP_MBA11_VREF, ALC889_FIXUP_MBA21_VREF, ALC889_FIXUP_MP11_VREF, + ALC889_FIXUP_MP41_VREF, ALC882_FIXUP_INV_DMIC, ALC882_FIXUP_NO_PRIMARY_HP, ALC887_FIXUP_ASUS_BASS, @@ -1843,7 +1864,7 @@ static void alc889_fixup_mbp_vref(struct hda_codec *codec, const struct hda_fixup *fix, int action) { struct alc_spec *spec = codec->spec; - static hda_nid_t nids[2] = { 0x14, 0x15 }; + static hda_nid_t nids[3] = { 0x14, 0x15, 0x19 }; int i; if (action != HDA_FIXUP_ACT_INIT) @@ -2133,6 +2154,12 @@ static const struct hda_fixup alc882_fixups[] = { .chained = true, .chain_id = ALC885_FIXUP_MACPRO_GPIO, }, + [ALC889_FIXUP_MP41_VREF] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc889_fixup_mbp_vref, + .chained = true, + .chain_id = ALC885_FIXUP_MACPRO_GPIO, + }, [ALC882_FIXUP_INV_DMIC] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_inv_dmic, @@ -2215,7 +2242,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x3f00, "Macbook 5,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4000, "MacbookPro 5,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4100, "Macmini 3,1", ALC889_FIXUP_IMAC91_VREF), - SND_PCI_QUIRK(0x106b, 0x4200, "Mac Pro 5,1", ALC885_FIXUP_MACPRO_GPIO), + SND_PCI_QUIRK(0x106b, 0x4200, "Mac Pro 4,1/5,1", ALC889_FIXUP_MP41_VREF), SND_PCI_QUIRK(0x106b, 0x4300, "iMac 9,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4600, "MacbookPro 5,2", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4900, "iMac 9,1 Aluminum", ALC889_FIXUP_IMAC91_VREF), @@ -4198,6 +4225,8 @@ static void alc_fixup_tpt440_dock(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->shutup = alc_no_shutup; /* reduce click noise */ + spec->reboot_notify = alc_d3_at_reboot; /* reduce noise */ spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; codec->power_save_node = 0; /* avoid click noises */ snd_hda_apply_pincfgs(codec, pincfgs); @@ -4578,6 +4607,7 @@ enum { ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC, ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_FIXUP_TPT440_DOCK, + ALC292_FIXUP_TPT440, ALC283_FIXUP_BXBT2807_MIC, ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, ALC282_FIXUP_ASPIRE_V5_PINS, @@ -4593,9 +4623,11 @@ enum { ALC288_FIXUP_DISABLE_AAMIX, ALC292_FIXUP_DELL_E7X, ALC292_FIXUP_DISABLE_AAMIX, + ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK, ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, ALC275_FIXUP_DELL_XPS, ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, + ALC293_FIXUP_LENOVO_SPK_NOISE, }; static const struct hda_fixup alc269_fixups[] = { @@ -5050,6 +5082,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST }, + [ALC292_FIXUP_TPT440] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC292_FIXUP_TPT440_DOCK, + }, [ALC283_FIXUP_BXBT2807_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -5149,6 +5187,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE }, + [ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC293_FIXUP_DELL1_MIC_NO_PRESENCE + }, [ALC292_FIXUP_DELL_E7X] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_dell_xps13, @@ -5187,6 +5231,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE }, + [ALC293_FIXUP_LENOVO_SPK_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5221,11 +5271,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0x1028, 0x06db, "Dell", ALC292_FIXUP_DISABLE_AAMIX), - SND_PCI_QUIRK(0x1028, 0x06dd, "Dell", ALC292_FIXUP_DISABLE_AAMIX), - SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC292_FIXUP_DISABLE_AAMIX), - SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC292_FIXUP_DISABLE_AAMIX), - SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC292_FIXUP_DISABLE_AAMIX), + SND_PCI_QUIRK(0x1028, 0x06db, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), + SND_PCI_QUIRK(0x1028, 0x06dd, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), + SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), + SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), + SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -5325,15 +5375,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x2203, "Thinkpad X230 Tablet", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x2208, "Thinkpad T431s", ALC269_FIXUP_LENOVO_DOCK), - SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440), SND_PCI_QUIRK(0x17aa, 0x220e, "Thinkpad T440p", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2210, "Thinkpad T540p", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2211, "Thinkpad W541", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad X240", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -5343,6 +5395,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), @@ -5423,6 +5476,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"}, {.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"}, {.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"}, + {.id = ALC292_FIXUP_TPT440, .name = "tpt440"}, {} }; @@ -6409,6 +6463,7 @@ static const struct hda_fixup alc662_fixups[] = { static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1019, 0x9087, "ECS", ALC662_FIXUP_ASUS_MODE2), SND_PCI_QUIRK(0x1025, 0x022f, "Acer Aspire One", ALC662_FIXUP_INV_DMIC), + SND_PCI_QUIRK(0x1025, 0x0241, "Packard Bell DOTS", ALC662_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x0308, "Acer Aspire 8942G", ALC662_FIXUP_ASPIRE), SND_PCI_QUIRK(0x1025, 0x031c, "Gateway NV79", ALC662_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x1025, 0x0349, "eMachines eM250", ALC662_FIXUP_INV_DMIC), diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c index 714df906249ea..41c31db650390 100644 --- a/sound/pci/rme96.c +++ b/sound/pci/rme96.c @@ -741,10 +741,11 @@ snd_rme96_playback_setrate(struct rme96 *rme96, { /* change to/from double-speed: reset the DAC (if available) */ snd_rme96_reset_dac(rme96); + return 1; /* need to restore volume */ } else { writel(rme96->wcreg, rme96->iobase + RME96_IO_CONTROL_REGISTER); + return 0; } - return 0; } static int @@ -980,6 +981,7 @@ snd_rme96_playback_hw_params(struct snd_pcm_substream *substream, struct rme96 *rme96 = snd_pcm_substream_chip(substream); struct snd_pcm_runtime *runtime = substream->runtime; int err, rate, dummy; + bool apply_dac_volume = false; runtime->dma_area = (void __force *)(rme96->iobase + RME96_IO_PLAY_BUFFER); @@ -993,24 +995,26 @@ snd_rme96_playback_hw_params(struct snd_pcm_substream *substream, { /* slave clock */ if ((int)params_rate(params) != rate) { - spin_unlock_irq(&rme96->lock); - return -EIO; - } - } else if ((err = snd_rme96_playback_setrate(rme96, params_rate(params))) < 0) { - spin_unlock_irq(&rme96->lock); - return err; - } - if ((err = snd_rme96_playback_setformat(rme96, params_format(params))) < 0) { - spin_unlock_irq(&rme96->lock); - return err; + err = -EIO; + goto error; + } + } else { + err = snd_rme96_playback_setrate(rme96, params_rate(params)); + if (err < 0) + goto error; + apply_dac_volume = err > 0; /* need to restore volume later? */ } + + err = snd_rme96_playback_setformat(rme96, params_format(params)); + if (err < 0) + goto error; snd_rme96_setframelog(rme96, params_channels(params), 1); if (rme96->capture_periodsize != 0) { if (params_period_size(params) << rme96->playback_frlog != rme96->capture_periodsize) { - spin_unlock_irq(&rme96->lock); - return -EBUSY; + err = -EBUSY; + goto error; } } rme96->playback_periodsize = @@ -1021,9 +1025,16 @@ snd_rme96_playback_hw_params(struct snd_pcm_substream *substream, rme96->wcreg &= ~(RME96_WCR_PRO | RME96_WCR_DOLBY | RME96_WCR_EMP); writel(rme96->wcreg |= rme96->wcreg_spdif_stream, rme96->iobase + RME96_IO_CONTROL_REGISTER); } + + err = 0; + error: spin_unlock_irq(&rme96->lock); - - return 0; + if (apply_dac_volume) { + usleep_range(3000, 10000); + snd_rme96_apply_dac_volume(rme96); + } + + return err; } static int diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index 9929efc6b9aaa..b3ea24d64c500 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -1023,24 +1023,18 @@ void arizona_init_dvfs(struct arizona_priv *priv) } EXPORT_SYMBOL_GPL(arizona_init_dvfs); -static unsigned int arizona_sysclk_48k_rates[] = { +static unsigned int arizona_opclk_ref_48k_rates[] = { 6144000, 12288000, 24576000, 49152000, - 73728000, - 98304000, - 147456000, }; -static unsigned int arizona_sysclk_44k1_rates[] = { +static unsigned int arizona_opclk_ref_44k1_rates[] = { 5644800, 11289600, 22579200, 45158400, - 67737600, - 90316800, - 135475200, }; static int arizona_set_opclk(struct snd_soc_codec *codec, unsigned int clk, @@ -1065,11 +1059,11 @@ static int arizona_set_opclk(struct snd_soc_codec *codec, unsigned int clk, } if (refclk % 8000) - rates = arizona_sysclk_44k1_rates; + rates = arizona_opclk_ref_44k1_rates; else - rates = arizona_sysclk_48k_rates; + rates = arizona_opclk_ref_48k_rates; - for (ref = 0; ref < ARRAY_SIZE(arizona_sysclk_48k_rates) && + for (ref = 0; ref < ARRAY_SIZE(arizona_opclk_ref_48k_rates) && rates[ref] <= refclk; ref++) { div = 1; while (rates[ref] / div >= freq && div < 32) { diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c index 969e337dc17c1..afa6c5db9dccc 100644 --- a/sound/soc/codecs/es8328.c +++ b/sound/soc/codecs/es8328.c @@ -85,7 +85,15 @@ static const DECLARE_TLV_DB_SCALE(pga_tlv, 0, 300, 0); static const DECLARE_TLV_DB_SCALE(bypass_tlv, -1500, 300, 0); static const DECLARE_TLV_DB_SCALE(mic_tlv, 0, 300, 0); -static const int deemph_settings[] = { 0, 32000, 44100, 48000 }; +static const struct { + int rate; + unsigned int val; +} deemph_settings[] = { + { 0, ES8328_DACCONTROL6_DEEMPH_OFF }, + { 32000, ES8328_DACCONTROL6_DEEMPH_32k }, + { 44100, ES8328_DACCONTROL6_DEEMPH_44_1k }, + { 48000, ES8328_DACCONTROL6_DEEMPH_48k }, +}; static int es8328_set_deemph(struct snd_soc_codec *codec) { @@ -97,21 +105,22 @@ static int es8328_set_deemph(struct snd_soc_codec *codec) * rate. */ if (es8328->deemph) { - best = 1; - for (i = 2; i < ARRAY_SIZE(deemph_settings); i++) { - if (abs(deemph_settings[i] - es8328->playback_fs) < - abs(deemph_settings[best] - es8328->playback_fs)) + best = 0; + for (i = 1; i < ARRAY_SIZE(deemph_settings); i++) { + if (abs(deemph_settings[i].rate - es8328->playback_fs) < + abs(deemph_settings[best].rate - es8328->playback_fs)) best = i; } - val = best << 1; + val = deemph_settings[best].val; } else { - val = 0; + val = ES8328_DACCONTROL6_DEEMPH_OFF; } dev_dbg(codec->dev, "Set deemphasis %d\n", val); - return snd_soc_update_bits(codec, ES8328_DACCONTROL6, 0x6, val); + return snd_soc_update_bits(codec, ES8328_DACCONTROL6, + ES8328_DACCONTROL6_DEEMPH_MASK, val); } static int es8328_get_deemph(struct snd_kcontrol *kcontrol, @@ -205,18 +214,18 @@ static const struct snd_kcontrol_new es8328_right_line_controls = /* Left Mixer */ static const struct snd_kcontrol_new es8328_left_mixer_controls[] = { - SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 8, 1, 0), - SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 7, 1, 0), - SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 8, 1, 0), - SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 7, 1, 0), + SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 7, 1, 0), + SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 6, 1, 0), + SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 7, 1, 0), + SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 6, 1, 0), }; /* Right Mixer */ static const struct snd_kcontrol_new es8328_right_mixer_controls[] = { - SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 8, 1, 0), - SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 7, 1, 0), - SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 8, 1, 0), - SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 7, 1, 0), + SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 7, 1, 0), + SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 6, 1, 0), + SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 7, 1, 0), + SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 6, 1, 0), }; static const char * const es8328_pga_sel[] = { diff --git a/sound/soc/codecs/es8328.h b/sound/soc/codecs/es8328.h index cb36afe10c0ec..156c748c89c7e 100644 --- a/sound/soc/codecs/es8328.h +++ b/sound/soc/codecs/es8328.h @@ -153,6 +153,7 @@ int es8328_probe(struct device *dev, struct regmap *regmap); #define ES8328_DACCONTROL6_CLICKFREE (1 << 3) #define ES8328_DACCONTROL6_DAC_INVR (1 << 4) #define ES8328_DACCONTROL6_DAC_INVL (1 << 5) +#define ES8328_DACCONTROL6_DEEMPH_MASK (3 << 6) #define ES8328_DACCONTROL6_DEEMPH_OFF (0 << 6) #define ES8328_DACCONTROL6_DEEMPH_32k (1 << 6) #define ES8328_DACCONTROL6_DEEMPH_44_1k (2 << 6) diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 7fc7b4e3f4442..c1b87c5800b1d 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -1271,6 +1271,36 @@ static int nau8825_i2c_remove(struct i2c_client *client) return 0; } +#ifdef CONFIG_PM_SLEEP +static int nau8825_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct nau8825 *nau8825 = dev_get_drvdata(dev); + + disable_irq(client->irq); + regcache_cache_only(nau8825->regmap, true); + regcache_mark_dirty(nau8825->regmap); + + return 0; +} + +static int nau8825_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct nau8825 *nau8825 = dev_get_drvdata(dev); + + regcache_cache_only(nau8825->regmap, false); + regcache_sync(nau8825->regmap); + enable_irq(client->irq); + + return 0; +} +#endif + +static const struct dev_pm_ops nau8825_pm = { + SET_SYSTEM_SLEEP_PM_OPS(nau8825_suspend, nau8825_resume) +}; + static const struct i2c_device_id nau8825_i2c_ids[] = { { "nau8825", 0 }, { } @@ -1297,6 +1327,7 @@ static struct i2c_driver nau8825_driver = { .name = "nau8825", .of_match_table = of_match_ptr(nau8825_of_ids), .acpi_match_table = ACPI_PTR(nau8825_acpi_match), + .pm = &nau8825_pm, }, .probe = nau8825_i2c_probe, .remove = nau8825_i2c_remove, diff --git a/sound/soc/codecs/rl6231.c b/sound/soc/codecs/rl6231.c index aca479fa76702..1dc68ab08a179 100644 --- a/sound/soc/codecs/rl6231.c +++ b/sound/soc/codecs/rl6231.c @@ -80,8 +80,10 @@ int rl6231_calc_dmic_clk(int rate) } for (i = 0; i < ARRAY_SIZE(div); i++) { - /* find divider that gives DMIC frequency below 3MHz */ - if (3000000 * div[i] >= rate) + if ((div[i] % 3) == 0) + continue; + /* find divider that gives DMIC frequency below 3.072MHz */ + if (3072000 * div[i] >= rate) return i; } diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 28132375e4274..ef76940f9dcb6 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -245,7 +245,7 @@ struct rt5645_priv { struct snd_soc_jack *hp_jack; struct snd_soc_jack *mic_jack; struct snd_soc_jack *btn_jack; - struct delayed_work jack_detect_work; + struct delayed_work jack_detect_work, rcclock_work; struct regulator_bulk_data supplies[ARRAY_SIZE(rt5645_supply_names)]; struct rt5645_eq_param_s *eq_param; @@ -565,12 +565,33 @@ static int rt5645_hweq_put(struct snd_kcontrol *kcontrol, .put = rt5645_hweq_put \ } +static int rt5645_spk_put_volsw(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); + struct rt5645_priv *rt5645 = snd_soc_component_get_drvdata(component); + int ret; + + cancel_delayed_work_sync(&rt5645->rcclock_work); + + regmap_update_bits(rt5645->regmap, RT5645_MICBIAS, + RT5645_PWR_CLK25M_MASK, RT5645_PWR_CLK25M_PU); + + ret = snd_soc_put_volsw(kcontrol, ucontrol); + + queue_delayed_work(system_power_efficient_wq, &rt5645->rcclock_work, + msecs_to_jiffies(200)); + + return ret; +} + static const struct snd_kcontrol_new rt5645_snd_controls[] = { /* Speaker Output Volume */ SOC_DOUBLE("Speaker Channel Switch", RT5645_SPK_VOL, RT5645_VOL_L_SFT, RT5645_VOL_R_SFT, 1, 1), - SOC_DOUBLE_TLV("Speaker Playback Volume", RT5645_SPK_VOL, - RT5645_L_VOL_SFT, RT5645_R_VOL_SFT, 39, 1, out_vol_tlv), + SOC_DOUBLE_EXT_TLV("Speaker Playback Volume", RT5645_SPK_VOL, + RT5645_L_VOL_SFT, RT5645_R_VOL_SFT, 39, 1, snd_soc_get_volsw, + rt5645_spk_put_volsw, out_vol_tlv), /* ClassD modulator Speaker Gain Ratio */ SOC_SINGLE_TLV("Speaker ClassD Playback Volume", RT5645_SPO_CLSD_RATIO, @@ -1498,7 +1519,7 @@ static void hp_amp_power(struct snd_soc_codec *codec, int on) regmap_write(rt5645->regmap, RT5645_PR_BASE + RT5645_MAMP_INT_REG2, 0xfc00); snd_soc_write(codec, RT5645_DEPOP_M2, 0x1140); - msleep(40); + msleep(70); rt5645->hp_on = true; } else { /* depop parameters */ @@ -3122,6 +3143,15 @@ static void rt5645_jack_detect_work(struct work_struct *work) SND_JACK_BTN_2 | SND_JACK_BTN_3); } +static void rt5645_rcclock_work(struct work_struct *work) +{ + struct rt5645_priv *rt5645 = + container_of(work, struct rt5645_priv, rcclock_work.work); + + regmap_update_bits(rt5645->regmap, RT5645_MICBIAS, + RT5645_PWR_CLK25M_MASK, RT5645_PWR_CLK25M_PD); +} + static irqreturn_t rt5645_irq(int irq, void *data) { struct rt5645_priv *rt5645 = data; @@ -3348,6 +3378,27 @@ static const struct dmi_system_id dmi_platform_intel_braswell[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Reks"), }, }, + { + .ident = "Google Edgar", + .callback = strago_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"), + }, + }, + { + .ident = "Google Wizpig", + .callback = strago_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Wizpig"), + }, + }, + { + .ident = "Google Terra", + .callback = strago_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Terra"), + }, + }, { } }; @@ -3587,6 +3638,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c, } INIT_DELAYED_WORK(&rt5645->jack_detect_work, rt5645_jack_detect_work); + INIT_DELAYED_WORK(&rt5645->rcclock_work, rt5645_rcclock_work); if (rt5645->i2c->irq) { ret = request_threaded_irq(rt5645->i2c->irq, NULL, rt5645_irq, @@ -3621,6 +3673,7 @@ static int rt5645_i2c_remove(struct i2c_client *i2c) free_irq(i2c->irq, rt5645); cancel_delayed_work_sync(&rt5645->jack_detect_work); + cancel_delayed_work_sync(&rt5645->rcclock_work); snd_soc_unregister_codec(&i2c->dev); regulator_bulk_disable(ARRAY_SIZE(rt5645->supplies), rt5645->supplies); diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h index dc2b46236c5cb..3f1b0f1df8097 100644 --- a/sound/soc/codecs/rt5670.h +++ b/sound/soc/codecs/rt5670.h @@ -973,12 +973,12 @@ #define RT5670_SCLK_SRC_MCLK (0x0 << 14) #define RT5670_SCLK_SRC_PLL1 (0x1 << 14) #define RT5670_SCLK_SRC_RCCLK (0x2 << 14) /* 15MHz */ -#define RT5670_PLL1_SRC_MASK (0x3 << 12) -#define RT5670_PLL1_SRC_SFT 12 -#define RT5670_PLL1_SRC_MCLK (0x0 << 12) -#define RT5670_PLL1_SRC_BCLK1 (0x1 << 12) -#define RT5670_PLL1_SRC_BCLK2 (0x2 << 12) -#define RT5670_PLL1_SRC_BCLK3 (0x3 << 12) +#define RT5670_PLL1_SRC_MASK (0x7 << 11) +#define RT5670_PLL1_SRC_SFT 11 +#define RT5670_PLL1_SRC_MCLK (0x0 << 11) +#define RT5670_PLL1_SRC_BCLK1 (0x1 << 11) +#define RT5670_PLL1_SRC_BCLK2 (0x2 << 11) +#define RT5670_PLL1_SRC_BCLK3 (0x3 << 11) #define RT5670_PLL1_PD_MASK (0x1 << 3) #define RT5670_PLL1_PD_SFT 3 #define RT5670_PLL1_PD_1 (0x0 << 3) diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index b4cd7e3bf5f89..69d987a9935c9 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -1386,90 +1386,90 @@ static const struct snd_kcontrol_new rt5677_dac_r_mix[] = { }; static const struct snd_kcontrol_new rt5677_sto1_dac_l_mix[] = { - SOC_DAPM_SINGLE("ST L Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("ST L Switch", RT5677_STO1_DAC_MIXER, RT5677_M_ST_DAC1_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER, RT5677_M_DAC1_L_STO_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC2 L Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC2 L Switch", RT5677_STO1_DAC_MIXER, RT5677_M_DAC2_L_STO_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER, RT5677_M_DAC1_R_STO_L_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_sto1_dac_r_mix[] = { - SOC_DAPM_SINGLE("ST R Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("ST R Switch", RT5677_STO1_DAC_MIXER, RT5677_M_ST_DAC1_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER, RT5677_M_DAC1_R_STO_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC2 R Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC2 R Switch", RT5677_STO1_DAC_MIXER, RT5677_M_DAC2_R_STO_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER, RT5677_M_DAC1_L_STO_R_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_mono_dac_l_mix[] = { - SOC_DAPM_SINGLE("ST L Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("ST L Switch", RT5677_MONO_DAC_MIXER, RT5677_M_ST_DAC2_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC1 L Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC1 L Switch", RT5677_MONO_DAC_MIXER, RT5677_M_DAC1_L_MONO_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER, RT5677_M_DAC2_L_MONO_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER, RT5677_M_DAC2_R_MONO_L_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_mono_dac_r_mix[] = { - SOC_DAPM_SINGLE("ST R Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("ST R Switch", RT5677_MONO_DAC_MIXER, RT5677_M_ST_DAC2_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC1 R Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC1 R Switch", RT5677_MONO_DAC_MIXER, RT5677_M_DAC1_R_MONO_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER, RT5677_M_DAC2_R_MONO_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER, RT5677_M_DAC2_L_MONO_R_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_dd1_l_mix[] = { - SOC_DAPM_SINGLE("Sto DAC Mix L Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix L Switch", RT5677_DD1_MIXER, RT5677_M_STO_L_DD1_L_SFT, 1, 1), - SOC_DAPM_SINGLE("Mono DAC Mix L Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix L Switch", RT5677_DD1_MIXER, RT5677_M_MONO_L_DD1_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC3 L Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC3 L Switch", RT5677_DD1_MIXER, RT5677_M_DAC3_L_DD1_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC3 R Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC3 R Switch", RT5677_DD1_MIXER, RT5677_M_DAC3_R_DD1_L_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_dd1_r_mix[] = { - SOC_DAPM_SINGLE("Sto DAC Mix R Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix R Switch", RT5677_DD1_MIXER, RT5677_M_STO_R_DD1_R_SFT, 1, 1), - SOC_DAPM_SINGLE("Mono DAC Mix R Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix R Switch", RT5677_DD1_MIXER, RT5677_M_MONO_R_DD1_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC3 R Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC3 R Switch", RT5677_DD1_MIXER, RT5677_M_DAC3_R_DD1_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC3 L Switch", RT5677_DD1_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC3 L Switch", RT5677_DD1_MIXER, RT5677_M_DAC3_L_DD1_R_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_dd2_l_mix[] = { - SOC_DAPM_SINGLE("Sto DAC Mix L Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix L Switch", RT5677_DD2_MIXER, RT5677_M_STO_L_DD2_L_SFT, 1, 1), - SOC_DAPM_SINGLE("Mono DAC Mix L Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix L Switch", RT5677_DD2_MIXER, RT5677_M_MONO_L_DD2_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC4 L Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC4 L Switch", RT5677_DD2_MIXER, RT5677_M_DAC4_L_DD2_L_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC4 R Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC4 R Switch", RT5677_DD2_MIXER, RT5677_M_DAC4_R_DD2_L_SFT, 1, 1), }; static const struct snd_kcontrol_new rt5677_dd2_r_mix[] = { - SOC_DAPM_SINGLE("Sto DAC Mix R Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix R Switch", RT5677_DD2_MIXER, RT5677_M_STO_R_DD2_R_SFT, 1, 1), - SOC_DAPM_SINGLE("Mono DAC Mix R Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix R Switch", RT5677_DD2_MIXER, RT5677_M_MONO_R_DD2_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC4 R Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC4 R Switch", RT5677_DD2_MIXER, RT5677_M_DAC4_R_DD2_R_SFT, 1, 1), - SOC_DAPM_SINGLE("DAC4 L Switch", RT5677_DD2_MIXER, + SOC_DAPM_SINGLE_AUTODISABLE("DAC4 L Switch", RT5677_DD2_MIXER, RT5677_M_DAC4_L_DD2_R_SFT, 1, 1), }; @@ -2596,6 +2596,21 @@ static int rt5677_vref_event(struct snd_soc_dapm_widget *w, return 0; } +static int rt5677_filter_power_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + switch (event) { + case SND_SOC_DAPM_POST_PMU: + msleep(50); + break; + + default: + return 0; + } + + return 0; +} + static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("PLL1", RT5677_PWR_ANLG2, RT5677_PWR_PLL1_BIT, 0, rt5677_set_pll1_event, SND_SOC_DAPM_PRE_PMU | @@ -3072,19 +3087,26 @@ static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = { /* DAC Mixer */ SND_SOC_DAPM_SUPPLY("dac stereo1 filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_S1F_BIT, 0, NULL, 0), + RT5677_PWR_DAC_S1F_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("dac mono2 left filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_M2F_L_BIT, 0, NULL, 0), + RT5677_PWR_DAC_M2F_L_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("dac mono2 right filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_M2F_R_BIT, 0, NULL, 0), + RT5677_PWR_DAC_M2F_R_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("dac mono3 left filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_M3F_L_BIT, 0, NULL, 0), + RT5677_PWR_DAC_M3F_L_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("dac mono3 right filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_M3F_R_BIT, 0, NULL, 0), + RT5677_PWR_DAC_M3F_R_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("dac mono4 left filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_M4F_L_BIT, 0, NULL, 0), + RT5677_PWR_DAC_M4F_L_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("dac mono4 right filter", RT5677_PWR_DIG2, - RT5677_PWR_DAC_M4F_R_BIT, 0, NULL, 0), + RT5677_PWR_DAC_M4F_R_BIT, 0, rt5677_filter_power_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_MIXER("Stereo DAC MIXL", SND_SOC_NOPM, 0, 0, rt5677_sto1_dac_l_mix, ARRAY_SIZE(rt5677_sto1_dac_l_mix)), diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index f540f82b1f271..08b40460663c2 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -189,6 +189,7 @@ static int power_vag_event(struct snd_soc_dapm_widget *w, case SND_SOC_DAPM_POST_PMU: snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER, SGTL5000_VAG_POWERUP, SGTL5000_VAG_POWERUP); + msleep(400); break; case SND_SOC_DAPM_PRE_PMD: diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index 056375339ea32..5380798883b5d 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -229,7 +229,7 @@ SOC_DOUBLE_R_TLV("Capture Volume", WM8960_LINVOL, WM8960_RINVOL, SOC_DOUBLE_R("Capture Volume ZC Switch", WM8960_LINVOL, WM8960_RINVOL, 6, 1, 0), SOC_DOUBLE_R("Capture Switch", WM8960_LINVOL, WM8960_RINVOL, - 7, 1, 0), + 7, 1, 1), SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume", WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv), diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 39ebd7bf4f530..a7e79784fc16c 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -365,8 +365,8 @@ static const struct reg_default wm8962_reg[] = { { 16924, 0x0059 }, /* R16924 - HDBASS_PG_1 */ { 16925, 0x999A }, /* R16925 - HDBASS_PG_0 */ - { 17048, 0x0083 }, /* R17408 - HPF_C_1 */ - { 17049, 0x98AD }, /* R17409 - HPF_C_0 */ + { 17408, 0x0083 }, /* R17408 - HPF_C_1 */ + { 17409, 0x98AD }, /* R17409 - HPF_C_0 */ { 17920, 0x007F }, /* R17920 - ADCL_RETUNE_C1_1 */ { 17921, 0xFFFF }, /* R17921 - ADCL_RETUNE_C1_0 */ diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c index 0a60677397b3d..4c29bd2ae75cf 100644 --- a/sound/soc/codecs/wm8974.c +++ b/sound/soc/codecs/wm8974.c @@ -574,6 +574,7 @@ static const struct regmap_config wm8974_regmap = { .max_register = WM8974_MONOMIX, .reg_defaults = wm8974_reg_defaults, .num_reg_defaults = ARRAY_SIZE(wm8974_reg_defaults), + .cache_type = REGCACHE_FLAT, }; static int wm8974_probe(struct snd_soc_codec *codec) diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 4495a40a94680..2ccb8bccc9d4c 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -223,8 +223,8 @@ static void mcasp_start_tx(struct davinci_mcasp *mcasp) /* wait for XDATA to be cleared */ cnt = 0; - while (!(mcasp_get_reg(mcasp, DAVINCI_MCASP_TXSTAT_REG) & - ~XRDATA) && (cnt < 100000)) + while ((mcasp_get_reg(mcasp, DAVINCI_MCASP_TXSTAT_REG) & XRDATA) && + (cnt < 100000)) cnt++; /* Release TX state machine */ @@ -681,8 +681,8 @@ static int davinci_mcasp_set_tdm_slot(struct snd_soc_dai *dai, } mcasp->tdm_slots = slots; - mcasp->tdm_mask[SNDRV_PCM_STREAM_PLAYBACK] = rx_mask; - mcasp->tdm_mask[SNDRV_PCM_STREAM_CAPTURE] = tx_mask; + mcasp->tdm_mask[SNDRV_PCM_STREAM_PLAYBACK] = tx_mask; + mcasp->tdm_mask[SNDRV_PCM_STREAM_CAPTURE] = rx_mask; mcasp->slot_width = slot_width; return davinci_mcasp_set_ch_constraints(mcasp); @@ -908,6 +908,14 @@ static int mcasp_i2s_hw_param(struct davinci_mcasp *mcasp, int stream, mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD); mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG, FSRMOD(total_slots), FSRMOD(0x1FF)); + /* + * If McASP is set to be TX/RX synchronous and the playback is + * not running already we need to configure the TX slots in + * order to have correct FSX on the bus + */ + if (mcasp_is_synchronous(mcasp) && !mcasp->channels) + mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG, + FSXMOD(total_slots), FSXMOD(0x1FF)); } return 0; diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 19c302b0d7639..14dfdee05fd5a 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -283,6 +283,8 @@ config SND_SOC_IMX_MC13783 config SND_SOC_FSL_ASOC_CARD tristate "Generic ASoC Sound Card with ASRC support" depends on OF && I2C + # enforce SND_SOC_FSL_ASOC_CARD=m if SND_AC97_CODEC=m: + depends on SND_AC97_CODEC || SND_AC97_CODEC=n select SND_SOC_IMX_AUDMUX select SND_SOC_IMX_PCM_DMA select SND_SOC_FSL_ESAI diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index a4435f5e3be91..08b460ba06efc 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -454,7 +454,8 @@ static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd, * Rx sync with Tx clocks: Clear SYNC for Tx, set it for Rx. * Tx sync with Rx clocks: Clear SYNC for Rx, set it for Tx. */ - regmap_update_bits(sai->regmap, FSL_SAI_TCR2, FSL_SAI_CR2_SYNC, 0); + regmap_update_bits(sai->regmap, FSL_SAI_TCR2, FSL_SAI_CR2_SYNC, + sai->synchronous[TX] ? FSL_SAI_CR2_SYNC : 0); regmap_update_bits(sai->regmap, FSL_SAI_RCR2, FSL_SAI_CR2_SYNC, sai->synchronous[RX] ? FSL_SAI_CR2_SYNC : 0); @@ -504,6 +505,24 @@ static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd, FSL_SAI_CSR_FR, FSL_SAI_CSR_FR); regmap_update_bits(sai->regmap, FSL_SAI_RCSR, FSL_SAI_CSR_FR, FSL_SAI_CSR_FR); + + /* + * For sai master mode, after several open/close sai, + * there will be no frame clock, and can't recover + * anymore. Add software reset to fix this issue. + * This is a hardware bug, and will be fix in the + * next sai version. + */ + if (!sai->is_slave_mode) { + /* Software Reset for both Tx and Rx */ + regmap_write(sai->regmap, + FSL_SAI_TCSR, FSL_SAI_CSR_SR); + regmap_write(sai->regmap, + FSL_SAI_RCSR, FSL_SAI_CSR_SR); + /* Clear SR bit to finish the reset */ + regmap_write(sai->regmap, FSL_SAI_TCSR, 0); + regmap_write(sai->regmap, FSL_SAI_RCSR, 0); + } } break; default: diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index 7b778ab85f8b4..d430ef5a4f388 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -144,7 +144,7 @@ config SND_SOC_INTEL_SKYLAKE config SND_SOC_INTEL_SKL_RT286_MACH tristate "ASoC Audio driver for SKL with RT286 I2S mode" - depends on X86 && ACPI + depends on X86 && ACPI && I2C select SND_SOC_INTEL_SST select SND_SOC_INTEL_SKYLAKE select SND_SOC_RT286 diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index a7854c8fc523e..ffea427aeca8e 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -1240,6 +1240,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus) */ ret = snd_soc_tplg_component_load(&platform->component, &skl_tplg_ops, fw, 0); + release_firmware(fw); if (ret < 0) { dev_err(bus->dev, "tplg component load failed%d\n", ret); return -EINVAL; diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c index a38a3029062c8..5a806da89f42b 100644 --- a/sound/soc/rockchip/rockchip_spdif.c +++ b/sound/soc/rockchip/rockchip_spdif.c @@ -152,8 +152,10 @@ static int rk_spdif_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: ret = regmap_update_bits(spdif->regmap, SPDIF_DMACR, - SPDIF_DMACR_TDE_ENABLE, - SPDIF_DMACR_TDE_ENABLE); + SPDIF_DMACR_TDE_ENABLE | + SPDIF_DMACR_TDL_MASK, + SPDIF_DMACR_TDE_ENABLE | + SPDIF_DMACR_TDL(16)); if (ret != 0) return ret; @@ -280,7 +282,7 @@ static int rk_spdif_probe(struct platform_device *pdev) int ret; match = of_match_node(rk_spdif_match, np); - if ((int) match->data == RK_SPDIF_RK3288) { + if (match->data == (void *)RK_SPDIF_RK3288) { struct regmap *grf; grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf"); diff --git a/sound/soc/rockchip/rockchip_spdif.h b/sound/soc/rockchip/rockchip_spdif.h index 07f86a21046a5..3ef12770ae124 100644 --- a/sound/soc/rockchip/rockchip_spdif.h +++ b/sound/soc/rockchip/rockchip_spdif.h @@ -28,9 +28,9 @@ #define SPDIF_CFGR_VDW(x) (x << SPDIF_CFGR_VDW_SHIFT) #define SDPIF_CFGR_VDW_MASK (0xf << SPDIF_CFGR_VDW_SHIFT) -#define SPDIF_CFGR_VDW_16 SPDIF_CFGR_VDW(0x00) -#define SPDIF_CFGR_VDW_20 SPDIF_CFGR_VDW(0x01) -#define SPDIF_CFGR_VDW_24 SPDIF_CFGR_VDW(0x10) +#define SPDIF_CFGR_VDW_16 SPDIF_CFGR_VDW(0x0) +#define SPDIF_CFGR_VDW_20 SPDIF_CFGR_VDW(0x1) +#define SPDIF_CFGR_VDW_24 SPDIF_CFGR_VDW(0x2) /* * DMACR @@ -42,7 +42,7 @@ #define SPDIF_DMACR_TDL_SHIFT 0 #define SPDIF_DMACR_TDL(x) ((x) << SPDIF_DMACR_TDL_SHIFT) -#define SPDIF_DMACR_TDL_MASK (0x1f << SDPIF_DMACR_TDL_SHIFT) +#define SPDIF_DMACR_TDL_MASK (0x1f << SPDIF_DMACR_TDL_SHIFT) /* * XFER diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c index 76da7620904c9..edcf4cc2e84fa 100644 --- a/sound/soc/sh/rcar/gen.c +++ b/sound/soc/sh/rcar/gen.c @@ -235,7 +235,7 @@ static int rsnd_gen2_probe(struct platform_device *pdev, RSND_GEN_S_REG(SCU_SYS_STATUS0, 0x1c8), RSND_GEN_S_REG(SCU_SYS_INT_EN0, 0x1cc), RSND_GEN_S_REG(SCU_SYS_STATUS1, 0x1d0), - RSND_GEN_S_REG(SCU_SYS_INT_EN1, 0x1c4), + RSND_GEN_S_REG(SCU_SYS_INT_EN1, 0x1d4), RSND_GEN_M_REG(SRC_SWRSR, 0x200, 0x40), RSND_GEN_M_REG(SRC_SRCIR, 0x204, 0x40), RSND_GEN_M_REG(SRC_ADINR, 0x214, 0x40), diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index 261b50217c48d..68b439ed22d7f 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -923,6 +923,7 @@ static int rsnd_src_pcm_new_gen2(struct rsnd_mod *mod, struct snd_soc_pcm_runtime *rtd) { struct rsnd_dai *rdai = rsnd_io_to_rdai(io); + struct rsnd_mod *dvc = rsnd_io_to_mod_dvc(io); struct rsnd_src *src = rsnd_mod_to_src(mod); int ret; @@ -937,6 +938,12 @@ static int rsnd_src_pcm_new_gen2(struct rsnd_mod *mod, return 0; /* + * SRC In doesn't work if DVC was enabled + */ + if (dvc && !rsnd_io_is_play(io)) + return 0; + + /* * enable sync convert */ ret = rsnd_kctrl_new_s(mod, io, rtd, diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 24b096066a072..a1305f827a98f 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -795,12 +795,12 @@ static void soc_resume_deferred(struct work_struct *work) dev_dbg(card->dev, "ASoC: resume work completed\n"); - /* userspace can access us now we are back as we were before */ - snd_power_change_state(card->snd_card, SNDRV_CTL_POWER_D0); - /* Recheck all endpoints too, their state is affected by suspend */ dapm_mark_endpoints_dirty(card); snd_soc_dapm_sync(&card->dapm); + + /* userspace can access us now we are back as we were before */ + snd_power_change_state(card->snd_card, SNDRV_CTL_POWER_D0); } /* powers up audio subsystem after a suspend */ diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 016eba10b1ec2..7d009428934ac 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2293,6 +2293,12 @@ void snd_soc_dapm_free_widget(struct snd_soc_dapm_widget *w) kfree(w); } +void snd_soc_dapm_reset_cache(struct snd_soc_dapm_context *dapm) +{ + dapm->path_sink_cache.widget = NULL; + dapm->path_source_cache.widget = NULL; +} + /* free all dapm widgets and resources */ static void dapm_free_widgets(struct snd_soc_dapm_context *dapm) { @@ -2303,6 +2309,7 @@ static void dapm_free_widgets(struct snd_soc_dapm_context *dapm) continue; snd_soc_dapm_free_widget(w); } + snd_soc_dapm_reset_cache(dapm); } static struct snd_soc_dapm_widget *dapm_find_widget( diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index ecd38e52285a9..2f67ba6d7a8fd 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -404,7 +404,7 @@ EXPORT_SYMBOL_GPL(snd_soc_get_volsw_sx); /** * snd_soc_put_volsw_sx - double mixer set callback * @kcontrol: mixer control - * @uinfo: control element information + * @ucontrol: control element information * * Callback to set the value of a double mixer control that spans 2 registers. * diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 8d7ec80af51b4..6963ba20991c1 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -531,7 +531,7 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr, /* TLV bytes controls need standard kcontrol info handler, * TLV callback and extended put/get handlers. */ - k->info = snd_soc_bytes_info; + k->info = snd_soc_bytes_info_ext; k->tlv.c = snd_soc_bytes_tlv_callback; ext_ops = tplg->bytes_ext_ops; @@ -1805,6 +1805,7 @@ void snd_soc_tplg_widget_remove_all(struct snd_soc_dapm_context *dapm, snd_soc_tplg_widget_remove(w); snd_soc_dapm_free_widget(w); } + snd_soc_dapm_reset_cache(dapm); } EXPORT_SYMBOL_GPL(snd_soc_tplg_widget_remove_all); diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c index 843f037a317da..5c2bc53f0a9b7 100644 --- a/sound/soc/sti/uniperif_player.c +++ b/sound/soc/sti/uniperif_player.c @@ -669,6 +669,7 @@ static int uni_player_startup(struct snd_pcm_substream *substream, { struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai); struct uniperif *player = priv->dai_data.uni; + player->substream = substream; player->clk_adj = 0; @@ -950,6 +951,8 @@ static void uni_player_shutdown(struct snd_pcm_substream *substream, if (player->state != UNIPERIF_STATE_STOPPED) /* Stop the player */ uni_player_stop(player); + + player->substream = NULL; } static int uni_player_parse_dt_clk_glue(struct platform_device *pdev, @@ -989,7 +992,7 @@ static int uni_player_parse_dt(struct platform_device *pdev, if (!info) return -ENOMEM; - if (of_property_read_u32(pnode, "version", &player->ver) || + if (of_property_read_u32(pnode, "st,version", &player->ver) || player->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) { dev_err(dev, "Unknown uniperipheral version "); return -EINVAL; @@ -998,13 +1001,13 @@ static int uni_player_parse_dt(struct platform_device *pdev, if (player->ver >= SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0) info->underflow_enabled = 1; - if (of_property_read_u32(pnode, "uniperiph-id", &info->id)) { + if (of_property_read_u32(pnode, "st,uniperiph-id", &info->id)) { dev_err(dev, "uniperipheral id not defined"); return -EINVAL; } /* Read the device mode property */ - if (of_property_read_string(pnode, "mode", &mode)) { + if (of_property_read_string(pnode, "st,mode", &mode)) { dev_err(dev, "uniperipheral mode not defined"); return -EINVAL; } diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c index f791239a30872..8a0eb20501694 100644 --- a/sound/soc/sti/uniperif_reader.c +++ b/sound/soc/sti/uniperif_reader.c @@ -316,7 +316,7 @@ static int uni_reader_parse_dt(struct platform_device *pdev, if (!info) return -ENOMEM; - if (of_property_read_u32(node, "version", &reader->ver) || + if (of_property_read_u32(node, "st,version", &reader->ver) || reader->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) { dev_err(&pdev->dev, "Unknown uniperipheral version "); return -EINVAL; @@ -346,7 +346,6 @@ int uni_reader_init(struct platform_device *pdev, reader->hw = &uni_reader_pcm_hw; reader->dai_ops = &uni_reader_dai_ops; - dev_err(reader->dev, "%s: enter\n", __func__); ret = uni_reader_parse_dt(pdev, reader); if (ret < 0) { dev_err(reader->dev, "Failed to parse DeviceTree"); diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c index bcbf4da168b63..1bb896d78d098 100644 --- a/sound/soc/sunxi/sun4i-codec.c +++ b/sound/soc/sunxi/sun4i-codec.c @@ -2,6 +2,7 @@ * Copyright 2014 Emilio López <emilio@elopez.com.ar> * Copyright 2014 Jon Smirl <jonsmirl@gmail.com> * Copyright 2015 Maxime Ripard <maxime.ripard@free-electrons.com> + * Copyright 2015 Adam Sampson <ats@offog.org> * * Based on the Allwinner SDK driver, released under the GPL. * @@ -404,7 +405,7 @@ static const struct snd_kcontrol_new sun4i_codec_pa_mute = static DECLARE_TLV_DB_SCALE(sun4i_codec_pa_volume_scale, -6300, 100, 1); static const struct snd_kcontrol_new sun4i_codec_widgets[] = { - SOC_SINGLE_TLV("PA Volume", SUN4I_CODEC_DAC_ACTL, + SOC_SINGLE_TLV("Power Amplifier Volume", SUN4I_CODEC_DAC_ACTL, SUN4I_CODEC_DAC_ACTL_PA_VOL, 0x3F, 0, sun4i_codec_pa_volume_scale), }; @@ -452,12 +453,12 @@ static const struct snd_soc_dapm_widget sun4i_codec_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("Mixer Enable", SUN4I_CODEC_DAC_ACTL, SUN4I_CODEC_DAC_ACTL_MIXEN, 0, NULL, 0), - /* Pre-Amplifier */ - SND_SOC_DAPM_MIXER("Pre-Amplifier", SUN4I_CODEC_ADC_ACTL, + /* Power Amplifier */ + SND_SOC_DAPM_MIXER("Power Amplifier", SUN4I_CODEC_ADC_ACTL, SUN4I_CODEC_ADC_ACTL_PA_EN, 0, sun4i_codec_pa_mixer_controls, ARRAY_SIZE(sun4i_codec_pa_mixer_controls)), - SND_SOC_DAPM_SWITCH("Pre-Amplifier Mute", SND_SOC_NOPM, 0, 0, + SND_SOC_DAPM_SWITCH("Power Amplifier Mute", SND_SOC_NOPM, 0, 0, &sun4i_codec_pa_mute), SND_SOC_DAPM_OUTPUT("HP Right"), @@ -480,16 +481,16 @@ static const struct snd_soc_dapm_route sun4i_codec_dapm_routes[] = { { "Left Mixer", NULL, "Mixer Enable" }, { "Left Mixer", "Left DAC Playback Switch", "Left DAC" }, - /* Pre-Amplifier Mixer Routes */ - { "Pre-Amplifier", "Mixer Playback Switch", "Left Mixer" }, - { "Pre-Amplifier", "Mixer Playback Switch", "Right Mixer" }, - { "Pre-Amplifier", "DAC Playback Switch", "Left DAC" }, - { "Pre-Amplifier", "DAC Playback Switch", "Right DAC" }, + /* Power Amplifier Routes */ + { "Power Amplifier", "Mixer Playback Switch", "Left Mixer" }, + { "Power Amplifier", "Mixer Playback Switch", "Right Mixer" }, + { "Power Amplifier", "DAC Playback Switch", "Left DAC" }, + { "Power Amplifier", "DAC Playback Switch", "Right DAC" }, - /* PA -> HP path */ - { "Pre-Amplifier Mute", "Switch", "Pre-Amplifier" }, - { "HP Right", NULL, "Pre-Amplifier Mute" }, - { "HP Left", NULL, "Pre-Amplifier Mute" }, + /* Headphone Output Routes */ + { "Power Amplifier Mute", "Switch", "Power Amplifier" }, + { "HP Right", NULL, "Power Amplifier Mute" }, + { "HP Left", NULL, "Power Amplifier Mute" }, }; static struct snd_soc_codec_driver sun4i_codec_codec = { diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index f494dced3c11e..4f85757009b3e 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1354,6 +1354,8 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc, } } + snd_usb_mixer_fu_apply_quirk(state->mixer, cval, unitid, kctl); + range = (cval->max - cval->min) / cval->res; /* * Are there devices with volume range more than 255? I use a bit more diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 6a803eff87f71..ddca6547399b0 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -348,13 +348,6 @@ static struct usbmix_name_map bose_companion5_map[] = { { 0 } /* terminator */ }; -/* Dragonfly DAC 1.2, the dB conversion factor is 1 instead of 256 */ -static struct usbmix_dB_map dragonfly_1_2_dB = {0, 5000}; -static struct usbmix_name_map dragonfly_1_2_map[] = { - { 7, NULL, .dB = &dragonfly_1_2_dB }, - { 0 } /* terminator */ -}; - /* * Control map entries */ @@ -470,11 +463,6 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x05a7, 0x1020), .map = bose_companion5_map, }, - { - /* Dragonfly DAC 1.2 */ - .id = USB_ID(0x21b4, 0x0081), - .map = dragonfly_1_2_map, - }, { 0 } /* terminator */ }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index fe91184ce8324..0ce888dceed0e 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -37,6 +37,7 @@ #include <sound/control.h> #include <sound/hwdep.h> #include <sound/info.h> +#include <sound/tlv.h> #include "usbaudio.h" #include "mixer.h" @@ -1825,3 +1826,39 @@ void snd_usb_mixer_rc_memory_change(struct usb_mixer_interface *mixer, } } +static void snd_dragonfly_quirk_db_scale(struct usb_mixer_interface *mixer, + struct snd_kcontrol *kctl) +{ + /* Approximation using 10 ranges based on output measurement on hw v1.2. + * This seems close to the cubic mapping e.g. alsamixer uses. */ + static const DECLARE_TLV_DB_RANGE(scale, + 0, 1, TLV_DB_MINMAX_ITEM(-5300, -4970), + 2, 5, TLV_DB_MINMAX_ITEM(-4710, -4160), + 6, 7, TLV_DB_MINMAX_ITEM(-3884, -3710), + 8, 14, TLV_DB_MINMAX_ITEM(-3443, -2560), + 15, 16, TLV_DB_MINMAX_ITEM(-2475, -2324), + 17, 19, TLV_DB_MINMAX_ITEM(-2228, -2031), + 20, 26, TLV_DB_MINMAX_ITEM(-1910, -1393), + 27, 31, TLV_DB_MINMAX_ITEM(-1322, -1032), + 32, 40, TLV_DB_MINMAX_ITEM(-968, -490), + 41, 50, TLV_DB_MINMAX_ITEM(-441, 0), + ); + + usb_audio_info(mixer->chip, "applying DragonFly dB scale quirk\n"); + kctl->tlv.p = scale; + kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ; + kctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK; +} + +void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer, + struct usb_mixer_elem_info *cval, int unitid, + struct snd_kcontrol *kctl) +{ + switch (mixer->chip->usb_id) { + case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */ + if (unitid == 7 && cval->min == 0 && cval->max == 50) + snd_dragonfly_quirk_db_scale(mixer, kctl); + break; + } +} + diff --git a/sound/usb/mixer_quirks.h b/sound/usb/mixer_quirks.h index bdbfab093816a..177c329cd4ddb 100644 --- a/sound/usb/mixer_quirks.h +++ b/sound/usb/mixer_quirks.h @@ -9,5 +9,9 @@ void snd_emuusb_set_samplerate(struct snd_usb_audio *chip, void snd_usb_mixer_rc_memory_change(struct usb_mixer_interface *mixer, int unitid); +void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer, + struct usb_mixer_elem_info *cval, int unitid, + struct snd_kcontrol *kctl); + #endif /* SND_USB_MIXER_QUIRKS_H */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 7016ad8981873..b6c0c8e3b450c 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1125,6 +1125,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ + case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ return true; } return false; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 40ab4476c80a2..51cf8256c6cda 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -420,8 +420,7 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr) static int nfit_test0_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_table_nfit) - + sizeof(struct acpi_nfit_system_address) * NUM_SPA + size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA + sizeof(struct acpi_nfit_memory_map) * NUM_MEM + sizeof(struct acpi_nfit_control_region) * NUM_DCR + sizeof(struct acpi_nfit_data_region) * NUM_BDW @@ -471,8 +470,7 @@ static int nfit_test0_alloc(struct nfit_test *t) static int nfit_test1_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_table_nfit) - + sizeof(struct acpi_nfit_system_address) + size_t nfit_size = sizeof(struct acpi_nfit_system_address) + sizeof(struct acpi_nfit_memory_map) + sizeof(struct acpi_nfit_control_region); @@ -488,39 +486,24 @@ static int nfit_test1_alloc(struct nfit_test *t) return 0; } -static void nfit_test_init_header(struct acpi_table_nfit *nfit, size_t size) -{ - memcpy(nfit->header.signature, ACPI_SIG_NFIT, 4); - nfit->header.length = size; - nfit->header.revision = 1; - memcpy(nfit->header.oem_id, "LIBND", 6); - memcpy(nfit->header.oem_table_id, "TEST", 5); - nfit->header.oem_revision = 1; - memcpy(nfit->header.asl_compiler_id, "TST", 4); - nfit->header.asl_compiler_revision = 1; -} - static void nfit_test0_setup(struct nfit_test *t) { struct nvdimm_bus_descriptor *nd_desc; struct acpi_nfit_desc *acpi_desc; struct acpi_nfit_memory_map *memdev; void *nfit_buf = t->nfit_buf; - size_t size = t->nfit_size; struct acpi_nfit_system_address *spa; struct acpi_nfit_control_region *dcr; struct acpi_nfit_data_region *bdw; struct acpi_nfit_flush_address *flush; unsigned int offset; - nfit_test_init_header(nfit_buf, size); - /* * spa0 (interleave first half of dimm0 and dimm1, note storage * does not actually alias the related block-data-window * regions) */ - spa = nfit_buf + sizeof(struct acpi_table_nfit); + spa = nfit_buf; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); @@ -533,7 +516,7 @@ static void nfit_test0_setup(struct nfit_test *t) * does not actually alias the related block-data-window * regions) */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa); + spa = nfit_buf + sizeof(*spa); spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); @@ -542,7 +525,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = SPA1_SIZE; /* spa2 (dcr0) dimm0 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 2; + spa = nfit_buf + sizeof(*spa) * 2; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); @@ -551,7 +534,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DCR_SIZE; /* spa3 (dcr1) dimm1 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 3; + spa = nfit_buf + sizeof(*spa) * 3; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); @@ -560,7 +543,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DCR_SIZE; /* spa4 (dcr2) dimm2 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 4; + spa = nfit_buf + sizeof(*spa) * 4; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); @@ -569,7 +552,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DCR_SIZE; /* spa5 (dcr3) dimm3 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 5; + spa = nfit_buf + sizeof(*spa) * 5; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); @@ -578,7 +561,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DCR_SIZE; /* spa6 (bdw for dcr0) dimm0 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 6; + spa = nfit_buf + sizeof(*spa) * 6; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); @@ -587,7 +570,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DIMM_SIZE; /* spa7 (bdw for dcr1) dimm1 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 7; + spa = nfit_buf + sizeof(*spa) * 7; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); @@ -596,7 +579,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DIMM_SIZE; /* spa8 (bdw for dcr2) dimm2 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 8; + spa = nfit_buf + sizeof(*spa) * 8; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); @@ -605,7 +588,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->length = DIMM_SIZE; /* spa9 (bdw for dcr3) dimm3 */ - spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 9; + spa = nfit_buf + sizeof(*spa) * 9; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; spa->header.length = sizeof(*spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); @@ -613,7 +596,7 @@ static void nfit_test0_setup(struct nfit_test *t) spa->address = t->dimm_dma[3]; spa->length = DIMM_SIZE; - offset = sizeof(struct acpi_table_nfit) + sizeof(*spa) * 10; + offset = sizeof(*spa) * 10; /* mem-region0 (spa0, dimm0) */ memdev = nfit_buf + offset; memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP; @@ -1100,15 +1083,13 @@ static void nfit_test0_setup(struct nfit_test *t) static void nfit_test1_setup(struct nfit_test *t) { - size_t size = t->nfit_size, offset; + size_t offset; void *nfit_buf = t->nfit_buf; struct acpi_nfit_memory_map *memdev; struct acpi_nfit_control_region *dcr; struct acpi_nfit_system_address *spa; - nfit_test_init_header(nfit_buf, size); - - offset = sizeof(struct acpi_table_nfit); + offset = 0; /* spa0 (flat range with no bdw aliasing) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 00326629d4af8..6fb23366b2584 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,3 +1,4 @@ socket psock_fanout psock_tpacket +reuseport_bpf diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index fac4782c51d84..41449b5ad0a98 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -4,7 +4,7 @@ CFLAGS = -Wall -O2 -g CFLAGS += -I../../../../usr/include/ -NET_PROGS = socket psock_fanout psock_tpacket +NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf all: $(NET_PROGS) %: %.c diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c new file mode 100644 index 0000000000000..bec1b5dd25305 --- /dev/null +++ b/tools/testing/selftests/net/reuseport_bpf.c @@ -0,0 +1,514 @@ +/* + * Test functionality of BPF filters for SO_REUSEPORT. The tests below will use + * a BPF program (both classic and extended) to read the first word from an + * incoming packet (expected to be in network byte-order), calculate a modulus + * of that number, and then dispatch the packet to the Nth socket using the + * result. These tests are run for each supported address family and protocol. + * Additionally, a few edge cases in the implementation are tested. + */ + +#include <errno.h> +#include <error.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/unistd.h> +#include <netinet/in.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/epoll.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <unistd.h> + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) +#endif + +struct test_params { + int recv_family; + int send_family; + int protocol; + size_t recv_socks; + uint16_t recv_port; + uint16_t send_port_min; +}; + +static size_t sockaddr_size(void) +{ + return sizeof(struct sockaddr_storage); +} + +static struct sockaddr *new_any_sockaddr(int family, uint16_t port) +{ + struct sockaddr_storage *addr; + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + + addr = malloc(sizeof(struct sockaddr_storage)); + memset(addr, 0, sizeof(struct sockaddr_storage)); + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + addr4->sin_family = AF_INET; + addr4->sin_addr.s_addr = htonl(INADDR_ANY); + addr4->sin_port = htons(port); + break; + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + addr6->sin6_family = AF_INET6; + addr6->sin6_addr = in6addr_any; + addr6->sin6_port = htons(port); + break; + default: + error(1, 0, "Unsupported family %d", family); + } + return (struct sockaddr *)addr; +} + +static struct sockaddr *new_loopback_sockaddr(int family, uint16_t port) +{ + struct sockaddr *addr = new_any_sockaddr(family, port); + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + break; + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + addr6->sin6_addr = in6addr_loopback; + break; + default: + error(1, 0, "Unsupported family %d", family); + } + return addr; +} + +static void attach_ebpf(int fd, uint16_t mod) +{ + static char bpf_log_buf[65536]; + static const char bpf_license[] = "GPL"; + + int bpf_fd; + const struct bpf_insn prog[] = { + /* BPF_MOV64_REG(BPF_REG_6, BPF_REG_1) */ + { BPF_ALU64 | BPF_MOV | BPF_X, BPF_REG_6, BPF_REG_1, 0, 0 }, + /* BPF_LD_ABS(BPF_W, 0) R0 = (uint32_t)skb[0] */ + { BPF_LD | BPF_ABS | BPF_W, 0, 0, 0, 0 }, + /* BPF_ALU64_IMM(BPF_MOD, BPF_REG_0, mod) */ + { BPF_ALU64 | BPF_MOD | BPF_K, BPF_REG_0, 0, 0, mod }, + /* BPF_EXIT_INSN() */ + { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } + }; + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insn_cnt = ARRAY_SIZE(prog); + attr.insns = (uint64_t)prog; + attr.license = (uint64_t)bpf_license; + attr.log_buf = (uint64_t)bpf_log_buf; + attr.log_size = sizeof(bpf_log_buf); + attr.log_level = 1; + attr.kern_version = 0; + + bpf_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + if (bpf_fd < 0) + error(1, errno, "ebpf error. log:\n%s\n", bpf_log_buf); + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &bpf_fd, + sizeof(bpf_fd))) + error(1, errno, "failed to set SO_ATTACH_REUSEPORT_EBPF"); + + close(bpf_fd); +} + +static void attach_cbpf(int fd, uint16_t mod) +{ + struct sock_filter code[] = { + /* A = (uint32_t)skb[0] */ + { BPF_LD | BPF_W | BPF_ABS, 0, 0, 0 }, + /* A = A % mod */ + { BPF_ALU | BPF_MOD, 0, 0, mod }, + /* return A */ + { BPF_RET | BPF_A, 0, 0, 0 }, + }; + struct sock_fprog p = { + .len = ARRAY_SIZE(code), + .filter = code, + }; + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_CBPF, &p, sizeof(p))) + error(1, errno, "failed to set SO_ATTACH_REUSEPORT_CBPF"); +} + +static void build_recv_group(const struct test_params p, int fd[], uint16_t mod, + void (*attach_bpf)(int, uint16_t)) +{ + struct sockaddr * const addr = + new_any_sockaddr(p.recv_family, p.recv_port); + int i, opt; + + for (i = 0; i < p.recv_socks; ++i) { + fd[i] = socket(p.recv_family, p.protocol, 0); + if (fd[i] < 0) + error(1, errno, "failed to create recv %d", i); + + opt = 1; + if (setsockopt(fd[i], SOL_SOCKET, SO_REUSEPORT, &opt, + sizeof(opt))) + error(1, errno, "failed to set SO_REUSEPORT on %d", i); + + if (i == 0) + attach_bpf(fd[i], mod); + + if (bind(fd[i], addr, sockaddr_size())) + error(1, errno, "failed to bind recv socket %d", i); + + if (p.protocol == SOCK_STREAM) + if (listen(fd[i], p.recv_socks * 10)) + error(1, errno, "failed to listen on socket"); + } + free(addr); +} + +static void send_from(struct test_params p, uint16_t sport, char *buf, + size_t len) +{ + struct sockaddr * const saddr = new_any_sockaddr(p.send_family, sport); + struct sockaddr * const daddr = + new_loopback_sockaddr(p.send_family, p.recv_port); + const int fd = socket(p.send_family, p.protocol, 0); + + if (fd < 0) + error(1, errno, "failed to create send socket"); + + if (bind(fd, saddr, sockaddr_size())) + error(1, errno, "failed to bind send socket"); + if (connect(fd, daddr, sockaddr_size())) + error(1, errno, "failed to connect"); + + if (send(fd, buf, len, 0) < 0) + error(1, errno, "failed to send message"); + + close(fd); + free(saddr); + free(daddr); +} + +static void test_recv_order(const struct test_params p, int fd[], int mod) +{ + char recv_buf[8], send_buf[8]; + struct msghdr msg; + struct iovec recv_io = { recv_buf, 8 }; + struct epoll_event ev; + int epfd, conn, i, sport, expected; + uint32_t data, ndata; + + epfd = epoll_create(1); + if (epfd < 0) + error(1, errno, "failed to create epoll"); + for (i = 0; i < p.recv_socks; ++i) { + ev.events = EPOLLIN; + ev.data.fd = fd[i]; + if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd[i], &ev)) + error(1, errno, "failed to register sock %d epoll", i); + } + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = &recv_io; + msg.msg_iovlen = 1; + + for (data = 0; data < p.recv_socks * 2; ++data) { + sport = p.send_port_min + data; + ndata = htonl(data); + memcpy(send_buf, &ndata, sizeof(ndata)); + send_from(p, sport, send_buf, sizeof(ndata)); + + i = epoll_wait(epfd, &ev, 1, -1); + if (i < 0) + error(1, errno, "epoll wait failed"); + + if (p.protocol == SOCK_STREAM) { + conn = accept(ev.data.fd, NULL, NULL); + if (conn < 0) + error(1, errno, "error accepting"); + i = recvmsg(conn, &msg, 0); + close(conn); + } else { + i = recvmsg(ev.data.fd, &msg, 0); + } + if (i < 0) + error(1, errno, "recvmsg error"); + if (i != sizeof(ndata)) + error(1, 0, "expected size %zd got %d", + sizeof(ndata), i); + + for (i = 0; i < p.recv_socks; ++i) + if (ev.data.fd == fd[i]) + break; + memcpy(&ndata, recv_buf, sizeof(ndata)); + fprintf(stderr, "Socket %d: %d\n", i, ntohl(ndata)); + + expected = (sport % mod); + if (i != expected) + error(1, 0, "expected socket %d", expected); + } +} + +static void test_reuseport_ebpf(const struct test_params p) +{ + int i, fd[p.recv_socks]; + + fprintf(stderr, "Testing EBPF mod %zd...\n", p.recv_socks); + build_recv_group(p, fd, p.recv_socks, attach_ebpf); + test_recv_order(p, fd, p.recv_socks); + + fprintf(stderr, "Reprograming, testing mod %zd...\n", p.recv_socks / 2); + attach_ebpf(fd[0], p.recv_socks / 2); + test_recv_order(p, fd, p.recv_socks / 2); + + for (i = 0; i < p.recv_socks; ++i) + close(fd[i]); +} + +static void test_reuseport_cbpf(const struct test_params p) +{ + int i, fd[p.recv_socks]; + + fprintf(stderr, "Testing CBPF mod %zd...\n", p.recv_socks); + build_recv_group(p, fd, p.recv_socks, attach_cbpf); + test_recv_order(p, fd, p.recv_socks); + + fprintf(stderr, "Reprograming, testing mod %zd...\n", p.recv_socks / 2); + attach_cbpf(fd[0], p.recv_socks / 2); + test_recv_order(p, fd, p.recv_socks / 2); + + for (i = 0; i < p.recv_socks; ++i) + close(fd[i]); +} + +static void test_extra_filter(const struct test_params p) +{ + struct sockaddr * const addr = + new_any_sockaddr(p.recv_family, p.recv_port); + int fd1, fd2, opt; + + fprintf(stderr, "Testing too many filters...\n"); + fd1 = socket(p.recv_family, p.protocol, 0); + if (fd1 < 0) + error(1, errno, "failed to create socket 1"); + fd2 = socket(p.recv_family, p.protocol, 0); + if (fd2 < 0) + error(1, errno, "failed to create socket 2"); + + opt = 1; + if (setsockopt(fd1, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt))) + error(1, errno, "failed to set SO_REUSEPORT on socket 1"); + if (setsockopt(fd2, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt))) + error(1, errno, "failed to set SO_REUSEPORT on socket 2"); + + attach_ebpf(fd1, 10); + attach_ebpf(fd2, 10); + + if (bind(fd1, addr, sockaddr_size())) + error(1, errno, "failed to bind recv socket 1"); + + if (!bind(fd2, addr, sockaddr_size()) && errno != EADDRINUSE) + error(1, errno, "bind socket 2 should fail with EADDRINUSE"); + + free(addr); +} + +static void test_filter_no_reuseport(const struct test_params p) +{ + struct sockaddr * const addr = + new_any_sockaddr(p.recv_family, p.recv_port); + const char bpf_license[] = "GPL"; + struct bpf_insn ecode[] = { + { BPF_ALU64 | BPF_MOV | BPF_K, BPF_REG_0, 0, 0, 10 }, + { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } + }; + struct sock_filter ccode[] = {{ BPF_RET | BPF_A, 0, 0, 0 }}; + union bpf_attr eprog; + struct sock_fprog cprog; + int fd, bpf_fd; + + fprintf(stderr, "Testing filters on non-SO_REUSEPORT socket...\n"); + + memset(&eprog, 0, sizeof(eprog)); + eprog.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + eprog.insn_cnt = ARRAY_SIZE(ecode); + eprog.insns = (uint64_t)ecode; + eprog.license = (uint64_t)bpf_license; + eprog.kern_version = 0; + + memset(&cprog, 0, sizeof(cprog)); + cprog.len = ARRAY_SIZE(ccode); + cprog.filter = ccode; + + + bpf_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &eprog, sizeof(eprog)); + if (bpf_fd < 0) + error(1, errno, "ebpf error"); + fd = socket(p.recv_family, p.protocol, 0); + if (fd < 0) + error(1, errno, "failed to create socket 1"); + + if (bind(fd, addr, sockaddr_size())) + error(1, errno, "failed to bind recv socket 1"); + + errno = 0; + if (!setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &bpf_fd, + sizeof(bpf_fd)) || errno != EINVAL) + error(1, errno, "setsockopt should have returned EINVAL"); + + errno = 0; + if (!setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_CBPF, &cprog, + sizeof(cprog)) || errno != EINVAL) + error(1, errno, "setsockopt should have returned EINVAL"); + + free(addr); +} + +static void test_filter_without_bind(void) +{ + int fd1, fd2; + + fprintf(stderr, "Testing filter add without bind...\n"); + fd1 = socket(AF_INET, SOCK_DGRAM, 0); + if (fd1 < 0) + error(1, errno, "failed to create socket 1"); + fd2 = socket(AF_INET, SOCK_DGRAM, 0); + if (fd2 < 0) + error(1, errno, "failed to create socket 2"); + + attach_ebpf(fd1, 10); + attach_cbpf(fd2, 10); + + close(fd1); + close(fd2); +} + + +int main(void) +{ + fprintf(stderr, "---- IPv4 UDP ----\n"); + /* NOTE: UDP socket lookups traverse a different code path when there + * are > 10 sockets in a group. Run the bpf test through both paths. + */ + test_reuseport_ebpf((struct test_params) { + .recv_family = AF_INET, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 10, + .recv_port = 8000, + .send_port_min = 9000}); + test_reuseport_ebpf((struct test_params) { + .recv_family = AF_INET, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 20, + .recv_port = 8000, + .send_port_min = 9000}); + test_reuseport_cbpf((struct test_params) { + .recv_family = AF_INET, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 10, + .recv_port = 8001, + .send_port_min = 9020}); + test_reuseport_cbpf((struct test_params) { + .recv_family = AF_INET, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 20, + .recv_port = 8001, + .send_port_min = 9020}); + test_extra_filter((struct test_params) { + .recv_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_port = 8002}); + test_filter_no_reuseport((struct test_params) { + .recv_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_port = 8008}); + + fprintf(stderr, "---- IPv6 UDP ----\n"); + test_reuseport_ebpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET6, + .protocol = SOCK_DGRAM, + .recv_socks = 10, + .recv_port = 8003, + .send_port_min = 9040}); + test_reuseport_ebpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET6, + .protocol = SOCK_DGRAM, + .recv_socks = 20, + .recv_port = 8003, + .send_port_min = 9040}); + test_reuseport_cbpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET6, + .protocol = SOCK_DGRAM, + .recv_socks = 10, + .recv_port = 8004, + .send_port_min = 9060}); + test_reuseport_cbpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET6, + .protocol = SOCK_DGRAM, + .recv_socks = 20, + .recv_port = 8004, + .send_port_min = 9060}); + test_extra_filter((struct test_params) { + .recv_family = AF_INET6, + .protocol = SOCK_DGRAM, + .recv_port = 8005}); + test_filter_no_reuseport((struct test_params) { + .recv_family = AF_INET6, + .protocol = SOCK_DGRAM, + .recv_port = 8009}); + + fprintf(stderr, "---- IPv6 UDP w/ mapped IPv4 ----\n"); + test_reuseport_ebpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 20, + .recv_port = 8006, + .send_port_min = 9080}); + test_reuseport_ebpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 10, + .recv_port = 8006, + .send_port_min = 9080}); + test_reuseport_cbpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 10, + .recv_port = 8007, + .send_port_min = 9100}); + test_reuseport_cbpf((struct test_params) { + .recv_family = AF_INET6, + .send_family = AF_INET, + .protocol = SOCK_DGRAM, + .recv_socks = 20, + .recv_port = 8007, + .send_port_min = 9100}); + + + test_filter_without_bind(); + + fprintf(stderr, "SUCCESS\n"); + return 0; +} diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 0a3da64638ced..4db7d5691ba71 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -110,4 +110,10 @@ static inline void free_page(unsigned long addr) (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) +/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */ +#define list_add_tail(a, b) do {} while (0) +#define list_del(a) do {} while (0) +#define list_for_each_entry(a, b, c) while (0) +/* end of stubs */ + #endif /* KERNEL_H */ diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index a3e07016a4401..ee125e714053a 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -3,12 +3,6 @@ #include <linux/scatterlist.h> #include <linux/kernel.h> -/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */ -#define list_add_tail(a, b) do {} while (0) -#define list_del(a) do {} while (0) -#define list_for_each_entry(a, b, c) while (0) -/* end of stubs */ - struct virtio_device { void *dev; u64 features; diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 806d683ab1078..57a6964a1e355 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -40,33 +40,39 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev, #define virtio_has_feature(dev, feature) \ (__virtio_test_bit((dev), feature)) +static inline bool virtio_is_little_endian(struct virtio_device *vdev) +{ + return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || + virtio_legacy_is_little_endian(); +} + +/* Memory accessors */ static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val) { - return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val) { - return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(virtio_is_little_endian(vdev), val); } static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val) { - return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val) { - return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(virtio_is_little_endian(vdev), val); } static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val) { - return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) { - return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } - diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 65461f821a75a..7a2f449bd85d0 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1114,7 +1114,7 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map) return true; } - return dist_active_irq(vcpu); + return vgic_irq_is_active(vcpu, map->virt_irq); } /* |