Merge branch 'for-next/core' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linuxNotice: this object is not reachable from any branch.

Notice: this object is not reachable from any branch.

46 files changed, 549 insertions, 171 deletions

diff --git a/Documentation/admin-guide/perf/hisi-pmu.rst b/Documentation/admin-guide/perf/hisi-pmu.rst
index e0174d20809a18..5cc248d18c63a7 100644
--- a/Documentation/admin-guide/perf/hisi-pmu.rst
+++ b/Documentation/admin-guide/perf/hisi-pmu.rst
@@ -20,7 +20,6 @@ interrupt, and the PMU driver shall register perf PMU drivers like L3C,
 HHA and DDRC etc. The available events and configuration options shall
 be described in the sysfs, see:
 
-/sys/devices/hisi_sccl{X}_<l3c{Y}/hha{Y}/ddrc{Y}>/, or
 /sys/bus/event_source/devices/hisi_sccl{X}_<l3c{Y}/hha{Y}/ddrc{Y}>.
 The "perf list" command shall list the available events from sysfs.
 
diff --git a/Documentation/admin-guide/perf/hns3-pmu.rst b/Documentation/admin-guide/perf/hns3-pmu.rst
index 75a40846d47f5f..1195e570f2d6b5 100644
--- a/Documentation/admin-guide/perf/hns3-pmu.rst
+++ b/Documentation/admin-guide/perf/hns3-pmu.rst
@@ -16,7 +16,7 @@ HNS3 PMU driver
 
 The HNS3 PMU driver registers a perf PMU with the name of its sicl id.::
 
-  /sys/devices/hns3_pmu_sicl_<sicl_id>
+  /sys/bus/event_source/devices/hns3_pmu_sicl_<sicl_id>
 
 PMU driver provides description of available events, filter modes, format,
 identifier and cpumask in sysfs.
@@ -40,9 +40,9 @@ device.
 
 Example usage of checking event code and subevent code::
 
-  $# cat /sys/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_time
+  $# cat /sys/bus/event_source/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_time
   config=0x00204
-  $# cat /sys/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_packet_num
+  $# cat /sys/bus/event_source/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_packet_num
   config=0x10204
 
 Each performance statistic has a pair of events to get two values to
@@ -60,7 +60,7 @@ computation to calculate real performance data is:::
 
 Example usage of checking supported filter mode::
 
-  $# cat /sys/devices/hns3_pmu_sicl_0/filtermode/bw_ssu_rpu_byte_num
+  $# cat /sys/bus/event_source/devices/hns3_pmu_sicl_0/filtermode/bw_ssu_rpu_byte_num
   filter mode supported: global/port/port-tc/func/func-queue/
 
 Example usage of perf::
diff --git a/Documentation/admin-guide/perf/qcom_l2_pmu.rst b/Documentation/admin-guide/perf/qcom_l2_pmu.rst
index c130178a4a5559..c37c6be9b8d889 100644
--- a/Documentation/admin-guide/perf/qcom_l2_pmu.rst
+++ b/Documentation/admin-guide/perf/qcom_l2_pmu.rst
@@ -10,7 +10,7 @@ There is one logical L2 PMU exposed, which aggregates the results from
 the physical PMUs.
 
 The driver provides a description of its available events and configuration
-options in sysfs, see /sys/devices/l2cache_0.
+options in sysfs, see /sys/bus/event_source/devices/l2cache_0.
 
 The "format" directory describes the format of the events.
 
diff --git a/Documentation/admin-guide/perf/qcom_l3_pmu.rst b/Documentation/admin-guide/perf/qcom_l3_pmu.rst
index a3d014a46bfdb3..a66556b7e985c1 100644
--- a/Documentation/admin-guide/perf/qcom_l3_pmu.rst
+++ b/Documentation/admin-guide/perf/qcom_l3_pmu.rst
@@ -9,7 +9,7 @@ PMU with device name l3cache_<socket>_<instance>. User space is responsible
 for aggregating across slices.
 
 The driver provides a description of its available events and configuration
-options in sysfs, see /sys/devices/l3cache*. Given that these are uncore PMUs
+options in sysfs, see /sys/bus/event_source/devices/l3cache*. Given that these are uncore PMUs
 the driver also exposes a "cpumask" sysfs attribute which contains a mask
 consisting of one CPU per socket which will be used to handle all the PMU
 events on that socket.
diff --git a/Documentation/admin-guide/perf/thunderx2-pmu.rst b/Documentation/admin-guide/perf/thunderx2-pmu.rst
index 01f158238ae1ee..9255f7bf945202 100644
--- a/Documentation/admin-guide/perf/thunderx2-pmu.rst
+++ b/Documentation/admin-guide/perf/thunderx2-pmu.rst
@@ -22,7 +22,7 @@ The thunderx2_pmu driver registers per-socket perf PMUs for the DMC and
 L3C devices.  Each PMU can be used to count up to 4 (DMC/L3C) or up to 8
 (CCPI2) events simultaneously. The PMUs provide a description of their
 available events and configuration options under sysfs, see
-/sys/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id.
+/sys/bus/event_source/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id.
 
 The driver does not support sampling, therefore "perf record" will not
 work. Per-task perf sessions are also not supported.
diff --git a/Documentation/admin-guide/perf/xgene-pmu.rst b/Documentation/admin-guide/perf/xgene-pmu.rst
index 644f8ed89152d6..98ccb8e777c4d1 100644
--- a/Documentation/admin-guide/perf/xgene-pmu.rst
+++ b/Documentation/admin-guide/perf/xgene-pmu.rst
@@ -13,7 +13,7 @@ PMU (perf) driver
 
 The xgene-pmu driver registers several perf PMU drivers. Each of the perf
 driver provides description of its available events and configuration options
-in sysfs, see /sys/devices/<l3cX/iobX/mcbX/mcX>/.
+in sysfs, see /sys/bus/event_source/devices/<l3cX/iobX/mcbX/mcX>/.
 
 The "format" directory describes format of the config (event ID),
 config1 (agent ID) fields of the perf_event_attr structure. The "events"
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 7ef8de58f7f892..3a39395bd9d3b2 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -62,6 +62,7 @@ Sphinx\ [#f1]_         2.4.4            sphinx-build --version
 cpio                   any              cpio --version
 GNU tar                1.28             tar --version
 gtags (optional)       6.6.5            gtags --version
+mkimage (optional)     2017.01          mkimage --version
 ====================== ===============  ========================================
 
 .. [#f1] Sphinx is needed only to build the Kernel documentation
@@ -189,6 +190,14 @@ The kernel build requires GNU GLOBAL version 6.6.5 or later to generate
 tag files through ``make gtags``.  This is due to its use of the gtags
 ``-C (--directory)`` flag.
 
+mkimage
+-------
+
+This tool is used when building a Flat Image Tree (FIT), commonly used on ARM
+platforms. The tool is available via the ``u-boot-tools`` package or can be
+built from the U-Boot source code. See the instructions at
+https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
+
 System utilities
 ****************
 
diff --git a/MAINTAINERS b/MAINTAINERS
index d68f1dafc626d5..e3316d38ea168a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3050,6 +3050,13 @@ F:	drivers/mmc/host/sdhci-of-arasan.c
 N:	zynq
 N:	xilinx
 
+ARM64 FIT SUPPORT
+M:	Simon Glass <sjg@chromium.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm64/boot/Makefile
+F:	scripts/make_fit.py
+
 ARM64 PORT (AARCH64 ARCHITECTURE)
 M:	Catalin Marinas <catalin.marinas@arm.com>
 M:	Will Deacon <will@kernel.org>
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 3e863e5b016909..3f0f35fd5bb7b1 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -161,6 +161,10 @@ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 # Default target when executing plain make
 boot		:= arch/arm64/boot
 
+BOOT_TARGETS	:= Image vmlinuz.efi image.fit
+
+PHONY += $(BOOT_TARGETS)
+
 ifeq ($(CONFIG_EFI_ZBOOT),)
 KBUILD_IMAGE	:= $(boot)/Image.gz
 else
@@ -169,8 +173,10 @@ endif
 
 all:	$(notdir $(KBUILD_IMAGE))
 
-vmlinuz.efi: Image
-Image vmlinuz.efi: vmlinux
+image.fit: dtbs
+
+vmlinuz.efi image.fit: Image
+$(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 Image.%: Image
@@ -222,6 +228,7 @@ virtconfig:
 define archhelp
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
   echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
+  echo  '  image.fit     - Flat Image Tree (arch/$(ARCH)/boot/image.fit)'
   echo  '  install       - Install uncompressed kernel'
   echo  '  zinstall      - Install compressed kernel'
   echo  '                  Install using (your) ~/bin/installkernel or'
diff --git a/arch/arm64/boot/.gitignore b/arch/arm64/boot/.gitignore
index af5dc61f8b4388..abaae9de1bdda2 100644
--- a/arch/arm64/boot/.gitignore
+++ b/arch/arm64/boot/.gitignore
@@ -2,3 +2,4 @@
 Image
 Image.gz
 vmlinuz*
+image.fit
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index a5a7873711173b..607a67a649c463 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -16,7 +16,8 @@
 
 OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
-targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo Image.zst
+targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo \
+	Image.zst image.fit
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
@@ -39,6 +40,9 @@ $(obj)/Image.lzo: $(obj)/Image FORCE
 $(obj)/Image.zst: $(obj)/Image FORCE
 	$(call if_changed,zstd)
 
+$(obj)/image.fit: $(obj)/Image $(obj)/dts/dtbs-list FORCE
+	$(call if_changed,fit)
+
 EFI_ZBOOT_PAYLOAD	:= Image
 EFI_ZBOOT_BFD_TARGET	:= elf64-littleaarch64
 EFI_ZBOOT_MACH_TYPE	:= ARM64
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index ab8b396428da8a..9ecd076ba08fc6 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -480,9 +480,10 @@ alternative_endif
  */
 	.macro	reset_pmuserenr_el0, tmpreg
 	mrs	\tmpreg, id_aa64dfr0_el1
-	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
-	cmp	\tmpreg, #1			// Skip if no PMU present
-	b.lt	9000f
+	ubfx	\tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	\tmpreg, #ID_AA64DFR0_EL1_PMUVer_NI
+	ccmp	\tmpreg, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
+	b.eq	9000f				// Skip if no PMU present or IMP_DEF
 	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
 9000:
 	.endm
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 52f076afeb9600..936389e9aecbc7 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,7 @@
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
+#define ARM_CPU_PART_NEOVERSE_V2	0xD4F
 
 #define APM_CPU_PART_XGENE		0x000
 #define APM_CPU_VAR_POTENZA		0x00
@@ -159,6 +160,7 @@
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
 #define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
+#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index b7afaa026842b7..e4546b29dd0cbf 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -59,13 +59,14 @@
 
 .macro __init_el2_debug
 	mrs	x1, id_aa64dfr0_el1
-	sbfx	x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
-	cmp	x0, #1
-	b.lt	.Lskip_pmu_\@			// Skip if no PMU present
+	ubfx	x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x0, #ID_AA64DFR0_EL1_PMUVer_NI
+	ccmp	x0, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
+	b.eq	.Lskip_pmu_\@			// Skip if no PMU present or IMP_DEF
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
 .Lskip_pmu_\@:
-	csel	x2, xzr, x0, lt			// all PMU counters from EL1
+	csel	x2, xzr, x0, eq			// all PMU counters from EL1
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 0a7186a93882da..d4d7451c2c129f 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -5,7 +5,6 @@
 #ifndef __ASM_IRQFLAGS_H
 #define __ASM_IRQFLAGS_H
 
-#include <asm/alternative.h>
 #include <asm/barrier.h>
 #include <asm/ptrace.h>
 #include <asm/sysreg.h>
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index dae8cac9a228f6..963cd91e376a49 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -265,9 +265,14 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
 }
 
-static inline void __set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
 {
 	WRITE_ONCE(*ptep, pte);
+}
+
+static inline void __set_pte(pte_t *ptep, pte_t pte)
+{
+	__set_pte_nosync(ptep, pte);
 
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
@@ -1009,6 +1014,8 @@ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr)
 
 static inline bool pgtable_l5_enabled(void) { return false; }
 
+#define p4d_index(addr)		(((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
+
 /* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */
 #define p4d_set_fixmap(addr)		NULL
 #define p4d_set_fixmap_offset(p4dp, addr)	((p4d_t *)p4dp)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index a75de2665d8445..95fbc8c0560798 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -142,17 +142,24 @@ static inline unsigned long get_trans_granule(void)
  * EL1, Inner Shareable".
  *
  */
-#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl)			\
-	({									\
-		unsigned long __ta = (baddr);					\
-		unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0;		\
-		__ta &= GENMASK_ULL(36, 0);					\
-		__ta |= __ttl << 37;						\
-		__ta |= (unsigned long)(num) << 39;				\
-		__ta |= (unsigned long)(scale) << 44;				\
-		__ta |= get_trans_granule() << 46;				\
-		__ta |= (unsigned long)(asid) << 48;				\
-		__ta;								\
+#define TLBIR_ASID_MASK		GENMASK_ULL(63, 48)
+#define TLBIR_TG_MASK		GENMASK_ULL(47, 46)
+#define TLBIR_SCALE_MASK	GENMASK_ULL(45, 44)
+#define TLBIR_NUM_MASK		GENMASK_ULL(43, 39)
+#define TLBIR_TTL_MASK		GENMASK_ULL(38, 37)
+#define TLBIR_BADDR_MASK	GENMASK_ULL(36,  0)
+
+#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl)		\
+	({								\
+		unsigned long __ta = 0;					\
+		unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0;	\
+		__ta |= FIELD_PREP(TLBIR_BADDR_MASK, baddr);		\
+		__ta |= FIELD_PREP(TLBIR_TTL_MASK, __ttl);		\
+		__ta |= FIELD_PREP(TLBIR_NUM_MASK, num);		\
+		__ta |= FIELD_PREP(TLBIR_SCALE_MASK, scale);		\
+		__ta |= FIELD_PREP(TLBIR_TG_MASK, get_trans_granule());	\
+		__ta |= FIELD_PREP(TLBIR_ASID_MASK, asid);		\
+		__ta;							\
 	})
 
 /* These macros are used by the TLBI RANGE feature. */
@@ -439,11 +446,11 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
 	 * When not uses TLB range ops, we can handle up to
 	 * (MAX_DVM_OPS - 1) pages;
 	 * When uses TLB range ops, we can handle up to
-	 * (MAX_TLBI_RANGE_PAGES - 1) pages.
+	 * MAX_TLBI_RANGE_PAGES pages.
 	 */
 	if ((!system_supports_tlb_range() &&
 	     (end - start) >= (MAX_DVM_OPS * stride)) ||
-	    pages >= MAX_TLBI_RANGE_PAGES) {
+	    pages > MAX_TLBI_RANGE_PAGES) {
 		flush_tlb_mm(vma->vm_mm);
 		return;
 	}
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index dba8fcec7f33d6..e0e7b93c16cc43 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -26,6 +26,7 @@
 #include <linux/libfdt.h>
 #include <linux/smp.h>
 #include <linux/serial_core.h>
+#include <linux/suspend.h>
 #include <linux/pgtable.h>
 
 #include <acpi/ghes.h>
@@ -227,6 +228,15 @@ done:
 		if (earlycon_acpi_spcr_enable)
 			early_init_dt_scan_chosen_stdout();
 	} else {
+#ifdef CONFIG_HIBERNATION
+		struct acpi_table_header *facs = NULL;
+		acpi_get_table(ACPI_SIG_FACS, 1, &facs);
+		if (facs) {
+			swsusp_hardware_signature =
+				((struct acpi_table_facs *)facs)->hardware_signature;
+			acpi_put_table(facs);
+		}
+#endif
 		acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
 		if (IS_ENABLED(CONFIG_ACPI_BGRT))
 			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 495b732d5af36f..c927e9312f102e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -109,28 +109,12 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 static phys_addr_t __init early_pgtable_alloc(int shift)
 {
 	phys_addr_t phys;
-	void *ptr;
 
 	phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0,
 					 MEMBLOCK_ALLOC_NOLEAKTRACE);
 	if (!phys)
 		panic("Failed to allocate page table page\n");
 
-	/*
-	 * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
-	 * slot will be free, so we can (ab)use the FIX_PTE slot to initialise
-	 * any level of table.
-	 */
-	ptr = pte_set_fixmap(phys);
-
-	memset(ptr, 0, PAGE_SIZE);
-
-	/*
-	 * Implicit barriers also ensure the zeroed page is visible to the page
-	 * table walker
-	 */
-	pte_clear_fixmap();
-
 	return phys;
 }
 
@@ -172,16 +156,25 @@ bool pgattr_change_is_safe(u64 old, u64 new)
 	return ((old ^ new) & ~mask) == 0;
 }
 
-static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
-		     phys_addr_t phys, pgprot_t prot)
+static void init_clear_pgtable(void *table)
 {
-	pte_t *ptep;
+	clear_page(table);
 
-	ptep = pte_set_fixmap_offset(pmdp, addr);
+	/* Ensure the zeroing is observed by page table walks. */
+	dsb(ishst);
+}
+
+static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
+		     phys_addr_t phys, pgprot_t prot)
+{
 	do {
 		pte_t old_pte = __ptep_get(ptep);
 
-		__set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		/*
+		 * Required barriers to make this visible to the table walker
+		 * are deferred to the end of alloc_init_cont_pte().
+		 */
+		__set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
@@ -192,8 +185,6 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 		phys += PAGE_SIZE;
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	pte_clear_fixmap();
 }
 
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
@@ -204,6 +195,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 {
 	unsigned long next;
 	pmd_t pmd = READ_ONCE(*pmdp);
+	pte_t *ptep;
 
 	BUG_ON(pmd_sect(pmd));
 	if (pmd_none(pmd)) {
@@ -214,10 +206,14 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 			pmdval |= PMD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc(PAGE_SHIFT);
+		ptep = pte_set_fixmap(pte_phys);
+		init_clear_pgtable(ptep);
+		ptep += pte_index(addr);
 		__pmd_populate(pmdp, pte_phys, pmdval);
-		pmd = READ_ONCE(*pmdp);
+	} else {
+		BUG_ON(pmd_bad(pmd));
+		ptep = pte_set_fixmap_offset(pmdp, addr);
 	}
-	BUG_ON(pmd_bad(pmd));
 
 	do {
 		pgprot_t __prot = prot;
@@ -229,20 +225,26 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pte(pmdp, addr, next, phys, __prot);
+		init_pte(ptep, addr, next, phys, __prot);
 
+		ptep += pte_index(next) - pte_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	/*
+	 * Note: barriers and maintenance necessary to clear the fixmap slot
+	 * ensure that all previous pgtable writes are visible to the table
+	 * walker.
+	 */
+	pte_clear_fixmap();
 }
 
-static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
+static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
 		     phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
-	pmd_t *pmdp;
 
-	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
 		pmd_t old_pmd = READ_ONCE(*pmdp);
 
@@ -268,8 +270,6 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		}
 		phys += next - addr;
 	} while (pmdp++, addr = next, addr != end);
-
-	pmd_clear_fixmap();
 }
 
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
@@ -279,6 +279,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
+	pmd_t *pmdp;
 
 	/*
 	 * Check for initial section mappings in the pgd/pud.
@@ -292,10 +293,14 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 			pudval |= PUD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc(PMD_SHIFT);
+		pmdp = pmd_set_fixmap(pmd_phys);
+		init_clear_pgtable(pmdp);
+		pmdp += pmd_index(addr);
 		__pud_populate(pudp, pmd_phys, pudval);
-		pud = READ_ONCE(*pudp);
+	} else {
+		BUG_ON(pud_bad(pud));
+		pmdp = pmd_set_fixmap_offset(pudp, addr);
 	}
-	BUG_ON(pud_bad(pud));
 
 	do {
 		pgprot_t __prot = prot;
@@ -307,10 +312,13 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
+		init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
 
+		pmdp += pmd_index(next) - pmd_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	pmd_clear_fixmap();
 }
 
 static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
@@ -330,12 +338,15 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 			p4dval |= P4D_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc(PUD_SHIFT);
+		pudp = pud_set_fixmap(pud_phys);
+		init_clear_pgtable(pudp);
+		pudp += pud_index(addr);
 		__p4d_populate(p4dp, pud_phys, p4dval);
-		p4d = READ_ONCE(*p4dp);
+	} else {
+		BUG_ON(p4d_bad(p4d));
+		pudp = pud_set_fixmap_offset(p4dp, addr);
 	}
-	BUG_ON(p4d_bad(p4d));
 
-	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
 
@@ -385,12 +396,15 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 			pgdval |= PGD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		p4d_phys = pgtable_alloc(P4D_SHIFT);
+		p4dp = p4d_set_fixmap(p4d_phys);
+		init_clear_pgtable(p4dp);
+		p4dp += p4d_index(addr);
 		__pgd_populate(pgdp, p4d_phys, pgdval);
-		pgd = READ_ONCE(*pgdp);
+	} else {
+		BUG_ON(pgd_bad(pgd));
+		p4dp = p4d_set_fixmap_offset(pgdp, addr);
 	}
-	BUG_ON(pgd_bad(pgd));
 
-	p4dp = p4d_set_fixmap_offset(pgdp, addr);
 	do {
 		p4d_t old_p4d = READ_ONCE(*p4dp);
 
@@ -457,11 +471,10 @@ void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
 
 static phys_addr_t __pgd_pgtable_alloc(int shift)
 {
-	void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL);
-	BUG_ON(!ptr);
+	/* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */
+	void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL & ~__GFP_ZERO);
 
-	/* Ensure the zeroed page is visible to the page table walker */
-	dsb(ishst);
+	BUG_ON(!ptr);
 	return __pa(ptr);
 }
 
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 44267a92bce5e2..3c126c6d306b06 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -315,23 +315,19 @@ void acpi_tb_parse_fadt(void)
 				       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
 				       NULL, FALSE, TRUE, &acpi_gbl_dsdt_index);
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (!acpi_gbl_reduced_hardware) {
-		if (acpi_gbl_FADT.facs) {
-			acpi_tb_install_standard_table((acpi_physical_address)
-						       acpi_gbl_FADT.facs,
-						       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
-						       NULL, FALSE, TRUE,
-						       &acpi_gbl_facs_index);
-		}
-		if (acpi_gbl_FADT.Xfacs) {
-			acpi_tb_install_standard_table((acpi_physical_address)
-						       acpi_gbl_FADT.Xfacs,
-						       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
-						       NULL, FALSE, TRUE,
-						       &acpi_gbl_xfacs_index);
-		}
+	if (acpi_gbl_FADT.facs) {
+		acpi_tb_install_standard_table((acpi_physical_address)
+					       acpi_gbl_FADT.facs,
+					       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
+					       NULL, FALSE, TRUE,
+					       &acpi_gbl_facs_index);
+	}
+	if (acpi_gbl_FADT.Xfacs) {
+		acpi_tb_install_standard_table((acpi_physical_address)
+					       acpi_gbl_FADT.Xfacs,
+					       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
+					       NULL, FALSE, TRUE,
+					       &acpi_gbl_xfacs_index);
 	}
 }
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index bb4a56e5673a5f..15fa68a5ea6e25 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -36,12 +36,7 @@ acpi_status acpi_tb_initialize_facs(void)
 {
 	struct acpi_table_facs *facs;
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (acpi_gbl_reduced_hardware) {
-		acpi_gbl_FACS = NULL;
-		return (AE_OK);
-	} else if (acpi_gbl_FADT.Xfacs &&
+	if (acpi_gbl_FADT.Xfacs &&
 		   (!acpi_gbl_FADT.facs
 		    || !acpi_gbl_use32_bit_facs_addresses)) {
 		(void)acpi_get_table_by_index(acpi_gbl_xfacs_index,
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index a9277dcf90ce0c..89dd38343f93ce 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -709,6 +709,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev)
 
 	drw_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= ali_drw_pmu_event_init,
 		.add		= ali_drw_pmu_add,
@@ -746,18 +747,14 @@ static int ali_drw_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct ali_drw_pmu_irq *irq;
 	struct ali_drw_pmu *drw_pmu;
 	unsigned int target;
-	int ret;
-	cpumask_t node_online_cpus;
 
 	irq = hlist_entry_safe(node, struct ali_drw_pmu_irq, node);
 	if (cpu != irq->cpu)
 		return 0;
 
-	ret = cpumask_and(&node_online_cpus,
-			  cpumask_of_node(cpu_to_node(cpu)), cpu_online_mask);
-	if (ret)
-		target = cpumask_any_but(&node_online_cpus, cpu);
-	else
+	target = cpumask_any_and_but(cpumask_of_node(cpu_to_node(cpu)),
+				     cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids)
diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c
index bbc7285fd934a3..07446d784a1a64 100644
--- a/drivers/perf/amlogic/meson_ddr_pmu_core.c
+++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c
@@ -492,6 +492,7 @@ int meson_ddr_pmu_create(struct platform_device *pdev)
 	*pmu = (struct ddr_pmu) {
 		.pmu = {
 			.module		= THIS_MODULE,
+			.parent		= &pdev->dev,
 			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 			.task_ctx_nr	= perf_invalid_context,
 			.attr_groups	= attr_groups,
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 6be03f81ae5db7..a7fd806779197f 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1409,6 +1409,7 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 
 	cci_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.name		= cci_pmu->model->name,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= cci_pmu_enable,
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 641471bd5eff40..f4495ff6525f65 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1265,6 +1265,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	/* Perf driver registration */
 	ccn->dt.pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent = ccn->dev,
 		.attr_groups = arm_ccn_pmu_attr_groups,
 		.task_ctx_nr = perf_invalid_context,
 		.event_init = arm_ccn_pmu_event_init,
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 7ef9c7e4836b72..e26ad1d3ed0bb7 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -1950,20 +1950,20 @@ static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_no
 	struct arm_cmn *cmn;
 	unsigned int target;
 	int node;
-	cpumask_t mask;
 
 	cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
 	if (cpu != cmn->cpu)
 		return 0;
 
 	node = dev_to_node(cmn->dev);
-	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
+
 	if (target < nr_cpu_ids)
 		arm_cmn_migrate(cmn, target);
+
 	return 0;
 }
 
@@ -2482,6 +2482,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
 	cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
 	cmn->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent = cmn->dev,
 		.attr_groups = arm_cmn_attr_groups,
 		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 		.task_ctx_nr = perf_invalid_context,
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index b9a252272f1e9f..ba0cf2f466ef00 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -1206,6 +1206,7 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
 	cspmu->pmu = (struct pmu){
 		.task_ctx_nr	= perf_invalid_context,
 		.module		= cspmu->impl.module,
+		.parent		= cspmu->dev,
 		.pmu_enable	= arm_cspmu_enable,
 		.pmu_disable	= arm_cspmu_disable,
 		.event_init	= arm_cspmu_event_init,
@@ -1322,8 +1323,7 @@ static int arm_cspmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 {
-	int dst;
-	struct cpumask online_supported;
+	unsigned int dst;
 
 	struct arm_cspmu *cspmu =
 		hlist_entry_safe(node, struct arm_cspmu, cpuhp_node);
@@ -1333,9 +1333,8 @@ static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	/* Choose a new CPU to migrate ownership of the PMU to */
-	cpumask_and(&online_supported, &cspmu->associated_cpus,
-		    cpu_online_mask);
-	dst = cpumask_any_but(&online_supported, cpu);
+	dst = cpumask_any_and_but(&cspmu->associated_cpus,
+				  cpu_online_mask, cpu);
 	if (dst >= nr_cpu_ids)
 		return 0;
 
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 8a81be2dd5ecf5..2ec96e204c403e 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -673,6 +673,7 @@ static int dmc620_pmu_device_probe(struct platform_device *pdev)
 
 	dmc620_pmu->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent		= &pdev->dev,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= dmc620_pmu_event_init,
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index bae3ca37f846ee..92248a24a1aabe 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -230,15 +230,6 @@ static const struct attribute_group *dsu_pmu_attr_groups[] = {
 	NULL,
 };
 
-static int dsu_pmu_get_online_cpu_any_but(struct dsu_pmu *dsu_pmu, int cpu)
-{
-	struct cpumask online_supported;
-
-	cpumask_and(&online_supported,
-			 &dsu_pmu->associated_cpus, cpu_online_mask);
-	return cpumask_any_but(&online_supported, cpu);
-}
-
 static inline bool dsu_pmu_counter_valid(struct dsu_pmu *dsu_pmu, u32 idx)
 {
 	return (idx < dsu_pmu->num_counters) ||
@@ -751,6 +742,7 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 
 	dsu_pmu->pmu = (struct pmu) {
 		.task_ctx_nr	= perf_invalid_context,
+		.parent		= &pdev->dev,
 		.module		= THIS_MODULE,
 		.pmu_enable	= dsu_pmu_enable,
 		.pmu_disable	= dsu_pmu_disable,
@@ -827,14 +819,16 @@ static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int dsu_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 {
-	int dst;
-	struct dsu_pmu *dsu_pmu = hlist_entry_safe(node, struct dsu_pmu,
-						   cpuhp_node);
+	struct dsu_pmu *dsu_pmu;
+	unsigned int dst;
+
+	dsu_pmu = hlist_entry_safe(node, struct dsu_pmu, cpuhp_node);
 
 	if (!cpumask_test_and_clear_cpu(cpu, &dsu_pmu->active_cpu))
 		return 0;
 
-	dst = dsu_pmu_get_online_cpu_any_but(dsu_pmu, cpu);
+	dst = cpumask_any_and_but(&dsu_pmu->associated_cpus,
+				  cpu_online_mask, cpu);
 	/* If there are no active CPUs in the DSU, leave IRQ disabled */
 	if (dst >= nr_cpu_ids)
 		return 0;
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 3596db36cbff4f..4b1a9a92ea117b 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -196,6 +196,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	if (!pmu)
 		return -ENOMEM;
 
+	pmu->pmu.parent = &pdev->dev;
 	pmu->plat_device = pdev;
 
 	ret = pmu_parse_irqs(pmu);
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 719aa953a1c4d6..d5fa92ba837397 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -860,6 +860,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 	smmu_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= smmu_pmu_enable,
 		.pmu_disable	= smmu_pmu_disable,
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 35f0de03416fc0..9100d82bfabc0d 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -932,6 +932,7 @@ static int arm_spe_pmu_perf_init(struct arm_spe_pmu *spe_pmu)
 
 	spe_pmu->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent		= &spe_pmu->pdev->dev,
 		.capabilities	= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE,
 		.attr_groups	= arm_spe_pmu_attr_groups,
 		/*
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
index 957058ad0099e2..c5e328f2384194 100644
--- a/drivers/perf/dwc_pcie_pmu.c
+++ b/drivers/perf/dwc_pcie_pmu.c
@@ -690,9 +690,8 @@ static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_n
 {
 	struct dwc_pcie_pmu *pcie_pmu;
 	struct pci_dev *pdev;
-	int node;
-	cpumask_t mask;
 	unsigned int target;
+	int node;
 
 	pcie_pmu = hlist_entry_safe(cpuhp_node, struct dwc_pcie_pmu, cpuhp_node);
 	/* Nothing to do if this CPU doesn't own the PMU */
@@ -702,10 +701,9 @@ static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_n
 	pcie_pmu->on_cpu = -1;
 	pdev = pcie_pmu->pdev;
 	node = dev_to_node(&pdev->dev);
-	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids) {
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 4e8fa5a48fcfe0..1bbdb29743c442 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -651,6 +651,7 @@ static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,
 	*pmu = (struct ddr_pmu) {
 		.pmu = (struct pmu) {
 			.module	      = THIS_MODULE,
+			.parent      = dev,
 			.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 			.task_ctx_nr = perf_invalid_context,
 			.attr_groups = attr_groups,
diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c
index 5d1f0e9fdb08d2..b1e4739fbdb0a9 100644
--- a/drivers/perf/hisilicon/hisi_pcie_pmu.c
+++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c
@@ -673,7 +673,6 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node);
 	unsigned int target;
-	cpumask_t mask;
 	int numa_node;
 
 	/* Nothing to do if this CPU doesn't own the PMU */
@@ -684,10 +683,10 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 
 	/* Choose a local CPU from all online cpus. */
 	numa_node = dev_to_node(&pcie_pmu->pdev->dev);
-	if (cpumask_and(&mask, cpumask_of_node(numa_node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(numa_node),
+				     cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids) {
@@ -807,6 +806,7 @@ static int hisi_pcie_alloc_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_
 	pcie_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.event_init	= hisi_pcie_pmu_event_init,
 		.pmu_enable	= hisi_pcie_pmu_enable,
 		.pmu_disable	= hisi_pcie_pmu_disable,
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 04031450d5feca..a60e4c96609876 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -504,7 +504,6 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu,
 						     node);
-	cpumask_t pmu_online_cpus;
 	unsigned int target;
 
 	if (!cpumask_test_and_clear_cpu(cpu, &hisi_pmu->associated_cpus))
@@ -518,9 +517,8 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	hisi_pmu->on_cpu = -1;
 
 	/* Choose a new CPU to migrate ownership of the PMU to */
-	cpumask_and(&pmu_online_cpus, &hisi_pmu->associated_cpus,
-		    cpu_online_mask);
-	target = cpumask_any_but(&pmu_online_cpus, cpu);
+	target = cpumask_any_and_but(&hisi_pmu->associated_cpus,
+				     cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 
@@ -538,6 +536,7 @@ void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module)
 	struct pmu *pmu = &hisi_pmu->pmu;
 
 	pmu->module             = module;
+	pmu->parent             = hisi_pmu->dev;
 	pmu->task_ctx_nr        = perf_invalid_context;
 	pmu->event_init         = hisi_uncore_pmu_event_init;
 	pmu->pmu_enable         = hisi_uncore_pmu_enable;
diff --git a/drivers/perf/hisilicon/hns3_pmu.c b/drivers/perf/hisilicon/hns3_pmu.c
index 16869bf5bf4cca..5236acdcc2e18f 100644
--- a/drivers/perf/hisilicon/hns3_pmu.c
+++ b/drivers/perf/hisilicon/hns3_pmu.c
@@ -1419,6 +1419,7 @@ static int hns3_pmu_alloc_pmu(struct pci_dev *pdev, struct hns3_pmu *hns3_pmu)
 	hns3_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.event_init	= hns3_pmu_event_init,
 		.pmu_enable	= hns3_pmu_enable,
 		.pmu_disable	= hns3_pmu_disable,
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 148df5ae8ef832..980e3051edd725 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -801,9 +801,8 @@ static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
 
 static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	struct cluster_pmu *cluster;
 	struct l2cache_pmu *l2cache_pmu;
-	cpumask_t cluster_online_cpus;
+	struct cluster_pmu *cluster;
 	unsigned int target;
 
 	l2cache_pmu = hlist_entry_safe(node, struct l2cache_pmu, node);
@@ -820,9 +819,8 @@ static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	cluster->on_cpu = -1;
 
 	/* Any other CPU for this cluster which is still online */
-	cpumask_and(&cluster_online_cpus, &cluster->cluster_cpus,
-		    cpu_online_mask);
-	target = cpumask_any_but(&cluster_online_cpus, cpu);
+	target = cpumask_any_and_but(&cluster->cluster_cpus,
+				     cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids) {
 		disable_irq(cluster->irq);
 		return 0;
@@ -904,6 +902,7 @@ static int l2_cache_pmu_probe(struct platform_device *pdev)
 	l2cache_pmu->pmu = (struct pmu) {
 		/* suffix is instance id for future use with multiple sockets */
 		.name		= "l2cache_0",
+		.parent		= &pdev->dev,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= l2_cache_pmu_enable,
 		.pmu_disable	= l2_cache_pmu_disable,
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index f16783d03db7b6..37786e88514e8c 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -748,6 +748,7 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	l3pmu->pmu = (struct pmu) {
+		.parent		= &pdev->dev,
 		.task_ctx_nr	= perf_invalid_context,
 
 		.pmu_enable	= qcom_l3_cache__pmu_enable,
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index fa0bccf4edf2ea..04487ad7fba0b5 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -136,6 +136,7 @@ static int pmu_legacy_device_probe(struct platform_device *pdev)
 	pmu = riscv_pmu_alloc();
 	if (!pmu)
 		return -ENOMEM;
+	pmu->pmu.parent = &pdev->dev;
 	pmu_legacy_init(pmu);
 
 	return 0;
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 8cbe6e5f9c39a6..82636273d72659 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -1043,7 +1043,6 @@ static struct ctl_table sbi_pmu_sysctl_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int pmu_sbi_device_probe(struct platform_device *pdev)
@@ -1081,6 +1080,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	}
 
 	pmu->pmu.attr_groups = riscv_pmu_attr_groups;
+	pmu->pmu.parent = &pdev->dev;
 	pmu->cmask = cmask;
 	pmu->ctr_start = pmu_sbi_ctr_start;
 	pmu->ctr_stop = pmu_sbi_ctr_stop;
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index e16d10c763de19..faf763d2c95cb8 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -504,24 +504,19 @@ static void tx2_uncore_event_update(struct perf_event *event)
 
 static enum tx2_uncore_type get_tx2_pmu_type(struct acpi_device *adev)
 {
-	int i = 0;
-	struct acpi_tx2_pmu_device {
-		__u8 id[ACPI_ID_LEN];
-		enum tx2_uncore_type type;
-	} devices[] = {
+	struct acpi_device_id devices[] = {
 		{"CAV901D", PMU_TYPE_L3C},
 		{"CAV901F", PMU_TYPE_DMC},
 		{"CAV901E", PMU_TYPE_CCPI2},
-		{"", PMU_TYPE_INVALID}
+		{}
 	};
+	const struct acpi_device_id *id;
 
-	while (devices[i].type != PMU_TYPE_INVALID) {
-		if (!strcmp(acpi_device_hid(adev), devices[i].id))
-			break;
-		i++;
-	}
+	id = acpi_match_acpi_device(devices, adev);
+	if (!id)
+		return PMU_TYPE_INVALID;
 
-	return devices[i].type;
+	return (enum tx2_uncore_type)id->driver_data;
 }
 
 static bool tx2_uncore_validate_event(struct pmu *pmu,
@@ -729,6 +724,7 @@ static int tx2_uncore_pmu_register(
 	/* Perf event registration */
 	tx2_pmu->pmu = (struct pmu) {
 		.module         = THIS_MODULE,
+		.parent		= tx2_pmu->dev,
 		.attr_groups	= tx2_pmu->attr_groups,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= tx2_uncore_event_init,
@@ -932,9 +928,8 @@ static int tx2_uncore_pmu_online_cpu(unsigned int cpu,
 static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 		struct hlist_node *hpnode)
 {
-	int new_cpu;
 	struct tx2_uncore_pmu *tx2_pmu;
-	struct cpumask cpu_online_mask_temp;
+	unsigned int new_cpu;
 
 	tx2_pmu = hlist_entry_safe(hpnode,
 			struct tx2_uncore_pmu, hpnode);
@@ -945,11 +940,8 @@ static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 	if (tx2_pmu->hrtimer_callback)
 		hrtimer_cancel(&tx2_pmu->hrtimer);
 
-	cpumask_copy(&cpu_online_mask_temp, cpu_online_mask);
-	cpumask_clear_cpu(cpu, &cpu_online_mask_temp);
-	new_cpu = cpumask_any_and(
-			cpumask_of_node(tx2_pmu->node),
-			&cpu_online_mask_temp);
+	new_cpu = cpumask_any_and_but(cpumask_of_node(tx2_pmu->node),
+				      cpu_online_mask, cpu);
 
 	tx2_pmu->cpu = new_cpu;
 	if (new_cpu >= nr_cpu_ids)
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 0d49343d704b7c..8823b4c6b55613 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1102,6 +1102,7 @@ static int xgene_init_perf(struct xgene_pmu_dev *pmu_dev, char *name)
 
 	/* Perf driver registration */
 	pmu_dev->pmu = (struct pmu) {
+		.parent		= pmu_dev->parent->dev,
 		.attr_groups	= pmu_dev->attr_groups,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= xgene_perf_pmu_enable,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 04536a29f10fc4..2b1bb52ea3df2e 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -389,6 +389,29 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 
 /**
+ * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
+ *
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static inline
+unsigned int cpumask_any_and_but(const struct cpumask *mask1,
+				 const struct cpumask *mask2,
+				 unsigned int cpu)
+{
+	unsigned int i;
+
+	cpumask_check(cpu);
+	i = cpumask_first_and(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_and(cpu, mask1, mask2);
+}
+
+/**
  * cpumask_nth - get the Nth cpu in a cpumask
  * @srcp: the cpumask pointer
  * @cpu: the Nth cpu to find, starting from 0
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index d1d51e38b55d7a..20e76d89c1864d 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -504,6 +504,22 @@ quiet_cmd_uimage = UIMAGE  $@
 			-a $(UIMAGE_LOADADDR) -e $(UIMAGE_ENTRYADDR) \
 			-n '$(UIMAGE_NAME)' -d $< $@
 
+# Flat Image Tree (FIT)
+# This allows for packaging of a kernel and all devicetrees files, using
+# compression.
+# ---------------------------------------------------------------------------
+
+MAKE_FIT := $(srctree)/scripts/make_fit.py
+
+# Use this to override the compression algorithm
+FIT_COMPRESSION ?= gzip
+
+quiet_cmd_fit = FIT     $@
+      cmd_fit = $(MAKE_FIT) -o $@ --arch $(UIMAGE_ARCH) --os linux \
+		--name '$(UIMAGE_NAME)' \
+		$(if $(findstring 1,$(KBUILD_VERBOSE)),-v) \
+		--compress $(FIT_COMPRESSION) -k $< @$(word 2,$^)
+
 # XZ
 # ---------------------------------------------------------------------------
 # Use xzkern to compress the kernel image and xzmisc to compress other things.
diff --git a/scripts/make_fit.py b/scripts/make_fit.py
new file mode 100755
index 00000000000000..3de90c5a094b7a
--- /dev/null
+++ b/scripts/make_fit.py
@@ -0,0 +1,290 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Copyright 2024 Google LLC
+# Written by Simon Glass <sjg@chromium.org>
+#
+
+"""Build a FIT containing a lot of devicetree files
+
+Usage:
+    make_fit.py -A arm64 -n 'Linux-6.6' -O linux
+        -o arch/arm64/boot/image.fit -k /tmp/kern/arch/arm64/boot/image.itk
+        @arch/arm64/boot/dts/dtbs-list -E -c gzip
+
+Creates a FIT containing the supplied kernel and a set of devicetree files,
+either specified individually or listed in a file (with an '@' prefix).
+
+Use -E to generate an external FIT (where the data is placed after the
+FIT data structure). This allows parsing of the data without loading
+the entire FIT.
+
+Use -c to compress the data, using bzip2, gzip, lz4, lzma, lzo and
+zstd algorithms.
+
+The resulting FIT can be booted by bootloaders which support FIT, such
+as U-Boot, Linuxboot, Tianocore, etc.
+
+Note that this tool does not yet support adding a ramdisk / initrd.
+"""
+
+import argparse
+import collections
+import os
+import subprocess
+import sys
+import tempfile
+import time
+
+import libfdt
+
+
+# Tool extension and the name of the command-line tools
+CompTool = collections.namedtuple('CompTool', 'ext,tools')
+
+COMP_TOOLS = {
+    'bzip2': CompTool('.bz2', 'bzip2'),
+    'gzip': CompTool('.gz', 'pigz,gzip'),
+    'lz4': CompTool('.lz4', 'lz4'),
+    'lzma': CompTool('.lzma', 'lzma'),
+    'lzo': CompTool('.lzo', 'lzop'),
+    'zstd': CompTool('.zstd', 'zstd'),
+}
+
+
+def parse_args():
+    """Parse the program ArgumentParser
+
+    Returns:
+        Namespace object containing the arguments
+    """
+    epilog = 'Build a FIT from a directory tree containing .dtb files'
+    parser = argparse.ArgumentParser(epilog=epilog, fromfile_prefix_chars='@')
+    parser.add_argument('-A', '--arch', type=str, required=True,
+          help='Specifies the architecture')
+    parser.add_argument('-c', '--compress', type=str, default='none',
+          help='Specifies the compression')
+    parser.add_argument('-E', '--external', action='store_true',
+          help='Convert the FIT to use external data')
+    parser.add_argument('-n', '--name', type=str, required=True,
+          help='Specifies the name')
+    parser.add_argument('-o', '--output', type=str, required=True,
+          help='Specifies the output file (.fit)')
+    parser.add_argument('-O', '--os', type=str, required=True,
+          help='Specifies the operating system')
+    parser.add_argument('-k', '--kernel', type=str, required=True,
+          help='Specifies the (uncompressed) kernel input file (.itk)')
+    parser.add_argument('-v', '--verbose', action='store_true',
+                        help='Enable verbose output')
+    parser.add_argument('dtbs', type=str, nargs='*',
+          help='Specifies the devicetree files to process')
+
+    return parser.parse_args()
+
+
+def setup_fit(fsw, name):
+    """Make a start on writing the FIT
+
+    Outputs the root properties and the 'images' node
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        name (str): Name of kernel image
+    """
+    fsw.INC_SIZE = 65536
+    fsw.finish_reservemap()
+    fsw.begin_node('')
+    fsw.property_string('description', f'{name} with devicetree set')
+    fsw.property_u32('#address-cells', 1)
+
+    fsw.property_u32('timestamp', int(time.time()))
+    fsw.begin_node('images')
+
+
+def write_kernel(fsw, data, args):
+    """Write out the kernel image
+
+    Writes a kernel node along with the required properties
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        data (bytes): Data to write (possibly compressed)
+        args (Namespace): Contains necessary strings:
+            arch: FIT architecture, e.g. 'arm64'
+            fit_os: Operating Systems, e.g. 'linux'
+            name: Name of OS, e.g. 'Linux-6.6.0-rc7'
+            compress: Compression algorithm to use, e.g. 'gzip'
+    """
+    with fsw.add_node('kernel'):
+        fsw.property_string('description', args.name)
+        fsw.property_string('type', 'kernel_noload')
+        fsw.property_string('arch', args.arch)
+        fsw.property_string('os', args.os)
+        fsw.property_string('compression', args.compress)
+        fsw.property('data', data)
+        fsw.property_u32('load', 0)
+        fsw.property_u32('entry', 0)
+
+
+def finish_fit(fsw, entries):
+    """Finish the FIT ready for use
+
+    Writes the /configurations node and subnodes
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        entries (list of tuple): List of configurations:
+            str: Description of model
+            str: Compatible stringlist
+    """
+    fsw.end_node()
+    seq = 0
+    with fsw.add_node('configurations'):
+        for model, compat in entries:
+            seq += 1
+            with fsw.add_node(f'conf-{seq}'):
+                fsw.property('compatible', bytes(compat))
+                fsw.property_string('description', model)
+                fsw.property_string('fdt', f'fdt-{seq}')
+                fsw.property_string('kernel', 'kernel')
+    fsw.end_node()
+
+
+def compress_data(inf, compress):
+    """Compress data using a selected algorithm
+
+    Args:
+        inf (IOBase): Filename containing the data to compress
+        compress (str): Compression algorithm, e.g. 'gzip'
+
+    Return:
+        bytes: Compressed data
+    """
+    if compress == 'none':
+        return inf.read()
+
+    comp = COMP_TOOLS.get(compress)
+    if not comp:
+        raise ValueError(f"Unknown compression algorithm '{compress}'")
+
+    with tempfile.NamedTemporaryFile() as comp_fname:
+        with open(comp_fname.name, 'wb') as outf:
+            done = False
+            for tool in comp.tools.split(','):
+                try:
+                    subprocess.call([tool, '-c'], stdin=inf, stdout=outf)
+                    done = True
+                    break
+                except FileNotFoundError:
+                    pass
+            if not done:
+                raise ValueError(f'Missing tool(s): {comp.tools}\n')
+            with open(comp_fname.name, 'rb') as compf:
+                comp_data = compf.read()
+    return comp_data
+
+
+def output_dtb(fsw, seq, fname, arch, compress):
+    """Write out a single devicetree to the FIT
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        seq (int): Sequence number (1 for first)
+        fmame (str): Filename containing the DTB
+        arch: FIT architecture, e.g. 'arm64'
+        compress (str): Compressed algorithm, e.g. 'gzip'
+
+    Returns:
+        tuple:
+            str: Model name
+            bytes: Compatible stringlist
+    """
+    with fsw.add_node(f'fdt-{seq}'):
+        # Get the compatible / model information
+        with open(fname, 'rb') as inf:
+            data = inf.read()
+        fdt = libfdt.FdtRo(data)
+        model = fdt.getprop(0, 'model').as_str()
+        compat = fdt.getprop(0, 'compatible')
+
+        fsw.property_string('description', model)
+        fsw.property_string('type', 'flat_dt')
+        fsw.property_string('arch', arch)
+        fsw.property_string('compression', compress)
+        fsw.property('compatible', bytes(compat))
+
+        with open(fname, 'rb') as inf:
+            compressed = compress_data(inf, compress)
+        fsw.property('data', compressed)
+    return model, compat
+
+
+def build_fit(args):
+    """Build the FIT from the provided files and arguments
+
+    Args:
+        args (Namespace): Program arguments
+
+    Returns:
+        tuple:
+            bytes: FIT data
+            int: Number of configurations generated
+            size: Total uncompressed size of data
+    """
+    seq = 0
+    size = 0
+    fsw = libfdt.FdtSw()
+    setup_fit(fsw, args.name)
+    entries = []
+
+    # Handle the kernel
+    with open(args.kernel, 'rb') as inf:
+        comp_data = compress_data(inf, args.compress)
+    size += os.path.getsize(args.kernel)
+    write_kernel(fsw, comp_data, args)
+
+    for fname in args.dtbs:
+        # Ignore overlay (.dtbo) files
+        if os.path.splitext(fname)[1] == '.dtb':
+            seq += 1
+            size += os.path.getsize(fname)
+            model, compat = output_dtb(fsw, seq, fname, args.arch, args.compress)
+            entries.append([model, compat])
+
+    finish_fit(fsw, entries)
+
+    # Include the kernel itself in the returned file count
+    return fsw.as_fdt().as_bytearray(), seq + 1, size
+
+
+def run_make_fit():
+    """Run the tool's main logic"""
+    args = parse_args()
+
+    out_data, count, size = build_fit(args)
+    with open(args.output, 'wb') as outf:
+        outf.write(out_data)
+
+    ext_fit_size = None
+    if args.external:
+        mkimage = os.environ.get('MKIMAGE', 'mkimage')
+        subprocess.check_call([mkimage, '-E', '-F', args.output],
+                              stdout=subprocess.DEVNULL)
+
+        with open(args.output, 'rb') as inf:
+            data = inf.read()
+        ext_fit = libfdt.FdtRo(data)
+        ext_fit_size = ext_fit.totalsize()
+
+    if args.verbose:
+        comp_size = len(out_data)
+        print(f'FIT size {comp_size:#x}/{comp_size / 1024 / 1024:.1f} MB',
+              end='')
+        if ext_fit_size:
+            print(f', header {ext_fit_size:#x}/{ext_fit_size / 1024:.1f} KB',
+                  end='')
+        print(f', {count} files, uncompressed {size / 1024 / 1024:.1f} MB')
+
+
+if __name__ == "__main__":
+    sys.exit(run_make_fit())