Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

79 files changed, 404 insertions, 136 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 266862428a84..8f138e580d1a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1416,6 +1416,14 @@ config DYNAMIC_SIGFRAME
 config HAVE_ARCH_NODE_DEV_GROUP
 	bool
 
+config ARCH_HAS_NONLEAF_PMD_YOUNG
+	bool
+	help
+	  Architectures that select this option are capable of setting the
+	  accessed bit in non-leaf PMD entries when using them as part of linear
+	  address translations. Page table walkers that clear the accessed bit
+	  may use this capability to reduce their search space.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 4aa996423b0d..763929e814e9 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -76,6 +76,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 9e3653253ef2..d9a13ccf89a3 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -554,7 +554,7 @@ config ARC_BUILTIN_DTB_NAME
 
 endmenu	 # "ARC Architecture Configuration"
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "12" if ARC_HUGEPAGE_16M
 	default "11"
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 68923a69b1d4..a08c9d092a33 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1362,7 +1362,7 @@ config ARM_MODULE_PLTS
 	  Disabling this is usually safe for small single-platform
 	  configurations. If unsure, say y.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "12" if SOC_AM33XX
 	default "9" if SA1111
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 6429c4106ab5..078d61b758a9 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -31,7 +31,7 @@ CONFIG_SOC_VF610=y
 CONFIG_SMP=y
 CONFIG_ARM_PSCI=y
 CONFIG_HIGHMEM=y
-CONFIG_FORCE_MAX_ZONEORDER=14
+CONFIG_ARCH_FORCE_MAX_ORDER=14
 CONFIG_CMDLINE="noinitrd console=ttymxc0,115200"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig
index cdb505c74654..a2e25bf843cc 100644
--- a/arch/arm/configs/milbeaut_m10v_defconfig
+++ b/arch/arm/configs/milbeaut_m10v_defconfig
@@ -26,7 +26,7 @@ CONFIG_THUMB2_KERNEL=y
 # CONFIG_THUMB2_AVOID_R_ARM_THM_JUMP11 is not set
 # CONFIG_ARM_PATCH_IDIV is not set
 CONFIG_HIGHMEM=y
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
 CONFIG_EFI=y
diff --git a/arch/arm/configs/oxnas_v6_defconfig b/arch/arm/configs/oxnas_v6_defconfig
index d206c4f04490..70a67b3fc91b 100644
--- a/arch/arm/configs/oxnas_v6_defconfig
+++ b/arch/arm/configs/oxnas_v6_defconfig
@@ -12,7 +12,7 @@ CONFIG_ARCH_OXNAS=y
 CONFIG_MACH_OX820=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_SECCOMP=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 2845fae4f3cc..d60cc9cc4c21 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -21,7 +21,7 @@ CONFIG_MACH_AKITA=y
 CONFIG_MACH_BORZOI=y
 CONFIG_PXA_SYSTEMS_CPLDS=y
 CONFIG_AEABI=y
-CONFIG_FORCE_MAX_ZONEORDER=9
+CONFIG_ARCH_FORCE_MAX_ORDER=9
 CONFIG_CMDLINE="root=/dev/ram0 ro"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
index 72af50d9e48a..8f28c9d443f0 100644
--- a/arch/arm/configs/sama7_defconfig
+++ b/arch/arm/configs/sama7_defconfig
@@ -19,7 +19,7 @@ CONFIG_ATMEL_CLOCKSOURCE_TCB=y
 # CONFIG_CACHE_L2X0 is not set
 # CONFIG_ARM_PATCH_IDIV is not set
 # CONFIG_CPU_SW_DOMAIN_PAN is not set
-CONFIG_FORCE_MAX_ZONEORDER=15
+CONFIG_ARCH_FORCE_MAX_ORDER=15
 CONFIG_UACCESS_WITH_MEMCPY=y
 # CONFIG_ATAGS is not set
 CONFIG_CMDLINE="console=ttyS0,115200 earlyprintk ignore_loglevel"
diff --git a/arch/arm/configs/sp7021_defconfig b/arch/arm/configs/sp7021_defconfig
index aa7dfd670db5..5bca2eb59b86 100644
--- a/arch/arm/configs/sp7021_defconfig
+++ b/arch/arm/configs/sp7021_defconfig
@@ -17,7 +17,7 @@ CONFIG_ARCH_SUNPLUS=y
 # CONFIG_VDSO is not set
 CONFIG_SMP=y
 CONFIG_THUMB2_KERNEL=y
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_MODULES=y
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 12e0a162ece5..f6737d2f37b2 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1431,7 +1431,7 @@ config XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int
 	default "14" if ARM64_64K_PAGES
 	default "12" if ARM64_16K_PAGES
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b5df82aa99e6..71a1af42f0e8 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1082,24 +1082,13 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
  * page after fork() + CoW for pfn mappings. We don't always have a
  * hardware-managed access flag on arm64.
  */
-static inline bool arch_faults_on_old_pte(void)
-{
-	/* The register read below requires a stable CPU to make any sense */
-	cant_migrate();
-
-	return !cpu_has_hw_af();
-}
-#define arch_faults_on_old_pte		arch_faults_on_old_pte
+#define arch_has_hw_pte_young		cpu_has_hw_af
 
 /*
  * Experimentally, it's cheap to set the access flag in hardware and we
  * benefit from prefaulting mappings as 'old' to start with.
  */
-static inline bool arch_wants_old_prefaulted_pte(void)
-{
-	return !arch_faults_on_old_pte();
-}
-#define arch_wants_old_prefaulted_pte	arch_wants_old_prefaulted_pte
+#define arch_wants_old_prefaulted_pte	cpu_has_hw_af
 
 static inline bool pud_sect_supported(void)
 {
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 98d67444a5b6..27ef7ad3ffd2 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -8,9 +8,9 @@
 #include <asm/cpufeature.h>
 #include <asm/mte.h>
 
-#define for_each_mte_vma(tsk, vma)					\
+#define for_each_mte_vma(vmi, vma)					\
 	if (system_supports_mte())					\
-		for (vma = tsk->mm->mmap; vma; vma = vma->vm_next)	\
+		for_each_vma(vmi, vma)					\
 			if (vma->vm_flags & VM_MTE)
 
 static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
@@ -81,8 +81,9 @@ Elf_Half elf_core_extra_phdrs(void)
 {
 	struct vm_area_struct *vma;
 	int vma_count = 0;
+	VMA_ITERATOR(vmi, current->mm, 0);
 
-	for_each_mte_vma(current, vma)
+	for_each_mte_vma(vmi, vma)
 		vma_count++;
 
 	return vma_count;
@@ -91,8 +92,9 @@ Elf_Half elf_core_extra_phdrs(void)
 int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, current->mm, 0);
 
-	for_each_mte_vma(current, vma) {
+	for_each_mte_vma(vmi, vma) {
 		struct elf_phdr phdr;
 
 		phdr.p_type = PT_AARCH64_MEMTAG_MTE;
@@ -116,8 +118,9 @@ size_t elf_core_extra_data_size(void)
 {
 	struct vm_area_struct *vma;
 	size_t data_size = 0;
+	VMA_ITERATOR(vmi, current->mm, 0);
 
-	for_each_mte_vma(current, vma)
+	for_each_mte_vma(vmi, vma)
 		data_size += mte_vma_tag_dump_size(vma);
 
 	return data_size;
@@ -126,8 +129,9 @@ size_t elf_core_extra_data_size(void)
 int elf_core_write_extra_data(struct coredump_params *cprm)
 {
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, current->mm, 0);
 
-	for_each_mte_vma(current, vma) {
+	for_each_mte_vma(vmi, vma) {
 		if (vma->vm_flags & VM_DONTDUMP)
 			continue;
 
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index ac93a2ee9c07..99ae81ab91a7 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -133,10 +133,11 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 {
 	struct mm_struct *mm = task->mm;
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
 	mmap_read_lock(mm);
 
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		unsigned long size = vma->vm_end - vma->vm_start;
 
 		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 0795028f017c..35e9a468d13e 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -245,7 +245,7 @@ static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
 {
 	VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
 
-	return page_folio(pfn_to_page(swp_offset(entry)));
+	return page_folio(pfn_to_page(swp_offset_pfn(entry)));
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 3cbc2dc62baf..adee6ab36862 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -332,7 +332,7 @@ config HIGHMEM
 	select KMAP_LOCAL
 	default y
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "11"
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 26ac8ea15a9e..c6e06cdc738f 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -200,7 +200,7 @@ config IA64_CYCLONE
 	  Say Y here to enable support for IBM EXA Cyclone time source.
 	  If you're unsure, answer N.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "MAX_ORDER (11 - 17)"  if !HUGETLB_PAGE
 	range 11 17  if !HUGETLB_PAGE
 	default "17" if HUGETLB_PAGE
diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
index 42ed5248fae9..84e8ce387b69 100644
--- a/arch/ia64/include/asm/sparsemem.h
+++ b/arch/ia64/include/asm/sparsemem.h
@@ -11,10 +11,10 @@
 
 #define SECTION_SIZE_BITS	(30)
 #define MAX_PHYSMEM_BITS	(50)
-#ifdef CONFIG_FORCE_MAX_ZONEORDER
-#if ((CONFIG_FORCE_MAX_ZONEORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS)
+#ifdef CONFIG_ARCH_FORCE_MAX_ORDER
+#if ((CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS)
 #undef SECTION_SIZE_BITS
-#define SECTION_SIZE_BITS (CONFIG_FORCE_MAX_ZONEORDER - 1 + PAGE_SHIFT)
+#define SECTION_SIZE_BITS (CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT)
 #endif
 #endif
 
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index cfd976065a0d..e83789b34861 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -377,7 +377,7 @@ config NODES_SHIFT
 	default "6"
 	depends on NUMA
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 14 64 if PAGE_SIZE_64KB
 	default "14" if PAGE_SIZE_64KB
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index b0504b13b089..9380f6e3bb66 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -397,7 +397,7 @@ config SINGLE_MEMORY_CHUNK
 	  order" to save memory that could be wasted for unused memory map.
 	  Say N if not sure.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order" if ADVANCED
 	depends on !SINGLE_MEMORY_CHUNK
 	default "11"
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 25dd4c5a8ef5..b26b77673c2c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2140,7 +2140,7 @@ config PAGE_SIZE_64KB
 
 endchoice
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
 	default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig
index a8b62df3c021..af070be1b583 100644
--- a/arch/mips/configs/db1xxx_defconfig
+++ b/arch/mips/configs/db1xxx_defconfig
@@ -9,7 +9,6 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_CGROUPS=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CFS_BANDWIDTH=y
diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig
index 714169e411cf..48e4e251779b 100644
--- a/arch/mips/configs/generic_defconfig
+++ b/arch/mips/configs/generic_defconfig
@@ -3,7 +3,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index 1be428663c10..c6e1fc77c996 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -103,6 +103,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 4167f1eb4cd8..a582f72104f3 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -44,7 +44,7 @@ menu "Kernel features"
 
 source "kernel/Kconfig.hz"
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 9 20
 	default "11"
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index a7ea3204a5fa..22133a6a506e 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -70,6 +70,8 @@
 #define MADV_WIPEONFORK 71		/* Zero memory on fork, child only */
 #define MADV_KEEPONFORK 72		/* Undo MADV_WIPEONFORK */
 
+#define MADV_COLLAPSE	73		/* Synchronous hugepage collapse */
+
 #define MADV_HWPOISON     100		/* poison a page for testing */
 #define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 3feb7694e0ca..1d3b8bc8a623 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -657,15 +657,20 @@ static inline unsigned long mm_total_size(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
 	unsigned long usize = 0;
+	VMA_ITERATOR(vmi, mm, 0);
 
-	for (vma = mm->mmap; vma && usize < parisc_cache_flush_threshold; vma = vma->vm_next)
+	for_each_vma(vmi, vma) {
+		if (usize >= parisc_cache_flush_threshold)
+			break;
 		usize += vma->vm_end - vma->vm_start;
+	}
 	return usize;
 }
 
 void flush_cache_mm(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
 	/*
 	 * Flushing the whole cache on each cpu takes forever on
@@ -685,7 +690,7 @@ void flush_cache_mm(struct mm_struct *mm)
 	}
 
 	/* Flush mm */
-	for (vma = mm->mmap; vma; vma = vma->vm_next)
+	for_each_vma(vmi, vma)
 		flush_cache_pages(vma, vma->vm_start, vma->vm_end);
 }
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 81c9f895d690..699df27b0e2f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -846,7 +846,7 @@ config DATA_SHIFT
 	  in that case. If PIN_TLB is selected, it must be aligned to 8M as
 	  8M pages will be pinned.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 8 9 if PPC64 && PPC_64K_PAGES
 	default "9" if PPC64 && PPC_64K_PAGES
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index e6d878a44d33..ea719898b581 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -30,7 +30,7 @@ CONFIG_PREEMPT=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_MATH_EMULATION=y
-CONFIG_FORCE_MAX_ZONEORDER=17
+CONFIG_ARCH_FORCE_MAX_ORDER=17
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MSI=y
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index f14c6dbd7346..ab8a8c4530d9 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -41,7 +41,7 @@ CONFIG_FIXED_PHY=y
 CONFIG_FONT_8x16=y
 CONFIG_FONT_8x8=y
 CONFIG_FONTS=y
-CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_ARCH_FORCE_MAX_ORDER=13
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAME_WARN=1024
 CONFIG_FTL=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 43e38f0fa5a7..c92652575064 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -17,7 +17,6 @@ CONFIG_LOG_CPU_MAX_BUF_SHIFT=13
 CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUPS=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CPUSETS=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index a25cf2ca5c7a..7497e17ea657 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -18,7 +18,6 @@ CONFIG_LOG_CPU_MAX_BUF_SHIFT=13
 CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUPS=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CPUSETS=y
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index e1f36fd61db3..4abc01949702 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -115,18 +115,18 @@ struct vdso_data *arch_get_vdso_data(void *vvar_page)
 int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 {
 	struct mm_struct *mm = task->mm;
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 
 	mmap_read_lock(mm);
-
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		unsigned long size = vma->vm_end - vma->vm_start;
 
 		if (vma_is_special_mapping(vma, &vvar_spec))
 			zap_page_range(vma, vma->vm_start, size);
 	}
-
 	mmap_read_unlock(mm);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c
index 19f0ef950d77..9ad6b56bfec9 100644
--- a/arch/powerpc/mm/book3s32/tlb.c
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -81,14 +81,15 @@ EXPORT_SYMBOL(hash__flush_range);
 void hash__flush_tlb_mm(struct mm_struct *mm)
 {
 	struct vm_area_struct *mp;
+	VMA_ITERATOR(vmi, mm, 0);
 
 	/*
-	 * It is safe to go down the mm's list of vmas when called
-	 * from dup_mmap, holding mmap_lock.  It would also be safe from
-	 * unmap_region or exit_mmap, but not from vmtruncate on SMP -
-	 * but it seems dup_mmap is the only SMP case which gets here.
+	 * It is safe to iterate the vmas when called from dup_mmap,
+	 * holding mmap_lock.  It would also be safe from unmap_region
+	 * or exit_mmap, but not from vmtruncate on SMP - but it seems
+	 * dup_mmap is the only SMP case which gets here.
 	 */
-	for (mp = mm->mmap; mp != NULL; mp = mp->vm_next)
+	for_each_vma(vmi, mp)
 		hash__flush_range(mp->vm_mm, mp->vm_start, mp->vm_end);
 }
 EXPORT_SYMBOL(hash__flush_tlb_mm);
diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c
index 60c6ea16a972..d73b3b4176e8 100644
--- a/arch/powerpc/mm/book3s64/subpage_prot.c
+++ b/arch/powerpc/mm/book3s64/subpage_prot.c
@@ -149,24 +149,15 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
 				    unsigned long len)
 {
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, addr);
 
 	/*
 	 * We don't try too hard, we just mark all the vma in that range
 	 * VM_NOHUGEPAGE and split them.
 	 */
-	vma = find_vma(mm, addr);
-	/*
-	 * If the range is in unmapped range, just return
-	 */
-	if (vma && ((addr + len) <= vma->vm_start))
-		return;
-
-	while (vma) {
-		if (vma->vm_start >= (addr + len))
-			break;
+	for_each_vma_range(vmi, vma, addr + len) {
 		vma->vm_flags |= VM_NOHUGEPAGE;
 		walk_page_vma(vma, &subpage_walk_ops, NULL);
-		vma = vma->vm_next;
 	}
 }
 #else
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 69b05b6c181b..692e7ae3dcb8 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -114,11 +114,12 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 {
 	struct mm_struct *mm = task->mm;
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 	struct __vdso_info *vdso_info = mm->context.vdso_info;
 
 	mmap_read_lock(mm);
 
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		unsigned long size = vma->vm_end - vma->vm_start;
 
 		if (vma_is_special_mapping(vma, vdso_info->dm))
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 5075cde77b29..535099f2736d 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -69,10 +69,11 @@ static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
 int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 {
 	struct mm_struct *mm = task->mm;
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 
 	mmap_read_lock(mm);
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		unsigned long size = vma->vm_end - vma->vm_start;
 
 		if (!vma_is_special_mapping(vma, &vvar_mapping))
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index d7b3b193d108..58033dfcb6d4 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -81,8 +81,9 @@ unsigned long _copy_from_user_key(void *to, const void __user *from,
 
 	might_fault();
 	if (!should_fail_usercopy()) {
-		instrument_copy_from_user(to, from, n);
+		instrument_copy_from_user_before(to, from, n);
 		res = raw_copy_from_user_key(to, from, n, key);
+		instrument_copy_from_user_after(to, from, n, res);
 	}
 	if (unlikely(res))
 		memset(to + (n - res), 0, res);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 62758cb5872f..02d15c8dc92e 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2515,8 +2515,9 @@ static const struct mm_walk_ops thp_split_walk_ops = {
 static inline void thp_split_mm(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
-	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		vma->vm_flags &= ~VM_HUGEPAGE;
 		vma->vm_flags |= VM_NOHUGEPAGE;
 		walk_page_vma(vma, &thp_split_walk_ops, NULL);
@@ -2584,8 +2585,9 @@ int gmap_mark_unmergeable(void)
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int ret;
+	VMA_ITERATOR(vmi, mm, 0);
 
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
 				  MADV_UNMERGEABLE, &vma->vm_flags);
 		if (ret)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 10e51ef9c79a..c299a18273ff 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -237,16 +237,6 @@ int pud_huge(pud_t pud)
 	return pud_large(pud);
 }
 
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int flags)
-{
-	if (flags & FOLL_GET)
-		return NULL;
-
-	return pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)
diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig
index e699e2e04128..b52e14ccb450 100644
--- a/arch/sh/configs/ecovec24_defconfig
+++ b/arch/sh/configs/ecovec24_defconfig
@@ -8,7 +8,7 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_CPU_SUBTYPE_SH7724=y
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_MEMORY_SIZE=0x10000000
 CONFIG_FLATMEM_MANUAL=y
 CONFIG_SH_ECOVEC=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index a8662b6927ec..97b7356639ed 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -16,7 +16,6 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_MEMCG=y
-CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig
index cb2f56468fe0..be478f3148f2 100644
--- a/arch/sh/configs/urquell_defconfig
+++ b/arch/sh/configs/urquell_defconfig
@@ -14,7 +14,6 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_MEMCG=y
-CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index ba569cfb4368..411fdc0901f7 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -18,7 +18,7 @@ config PAGE_OFFSET
 	default "0x80000000" if MMU
 	default "0x00000000"
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 9 64 if PAGE_SIZE_16KB
 	default "9" if PAGE_SIZE_16KB
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 1c852bb530ec..4d3d1af90d52 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -269,7 +269,7 @@ config ARCH_SPARSEMEM_ENABLE
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y if SPARC64
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "13"
 	help
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index bc38f79ca3a3..ad449173a1a1 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -584,21 +584,19 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	struct vm_area_struct *vma = mm->mmap;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
-	while (vma != NULL) {
+	for_each_vma(vmi, vma)
 		fix_range(mm, vma->vm_start, vma->vm_end, 0);
-		vma = vma->vm_next;
-	}
 }
 
 void force_flush_all(void)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma = mm->mmap;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
-	while (vma != NULL) {
+	for_each_vma(vmi, vma)
 		fix_range(mm, vma->vm_start, vma->vm_end, 1);
-		vma = vma->vm_next;
-	}
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 088af7c84e5d..6d1879ef933a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_NONLEAF_PMD_YOUNG	if PGTABLE_LEVELS > 2
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_COPY_MC			if X86_64
 	select ARCH_HAS_SET_MEMORY
@@ -130,7 +131,9 @@ config X86
 	select CLKEVT_I8253
 	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select CLOCKSOURCE_WATCHDOG
-	select DCACHE_WORD_ACCESS
+	# Word-size accesses may read uninitialized data past the trailing \0
+	# in strings and cause false KMSAN reports.
+	select DCACHE_WORD_ACCESS		if !KMSAN
 	select DYNAMIC_SIGFRAME
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
@@ -168,6 +171,7 @@ config X86
 	select HAVE_ARCH_KASAN			if X86_64
 	select HAVE_ARCH_KASAN_VMALLOC		if X86_64
 	select HAVE_ARCH_KFENCE
+	select HAVE_ARCH_KMSAN			if X86_64
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT
@@ -328,6 +332,10 @@ config GENERIC_ISA_DMA
 	def_bool y
 	depends on ISA_DMA_API
 
+config GENERIC_CSUM
+	bool
+	default y if KMSAN || KASAN
+
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index ffec8bb01ba8..9860ca5979f8 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -12,6 +12,7 @@
 # Sanitizer runtimes are unavailable and cannot be linked for early boot code.
 KASAN_SANITIZE			:= n
 KCSAN_SANITIZE			:= n
+KMSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y
 
 # Kernel does not boot with kcov instrumentation here.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 35ce1a64068b..3a261abb6d15 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -20,6 +20,7 @@
 # Sanitizer runtimes are unavailable and cannot be linked for early boot code.
 KASAN_SANITIZE			:= n
 KCSAN_SANITIZE			:= n
+KMSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y
 
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 381d3333b996..3e88b9df8c8f 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -11,6 +11,9 @@ include $(srctree)/lib/vdso/Makefile
 
 # Sanitizer runtimes are unavailable and cannot be linked here.
 KASAN_SANITIZE			:= n
+KMSAN_SANITIZE_vclock_gettime.o := n
+KMSAN_SANITIZE_vgetcpu.o	:= n
+
 UBSAN_SANITIZE			:= n
 KCSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 1000d457c332..6292b960037b 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -127,17 +127,17 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 {
 	struct mm_struct *mm = task->mm;
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
 	mmap_read_lock(mm);
-
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		unsigned long size = vma->vm_end - vma->vm_start;
 
 		if (vma_is_special_mapping(vma, &vvar_mapping))
 			zap_page_range(vma, vma->vm_start, size);
 	}
-
 	mmap_read_unlock(mm);
+
 	return 0;
 }
 #else
@@ -354,6 +354,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
 	mmap_write_lock(mm);
 	/*
@@ -363,7 +364,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 	 * We could search vma near context.vdso, but it's a slowpath,
 	 * so let's explicitly check all VMAs to be completely sure.
 	 */
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	for_each_vma(vmi, vma) {
 		if (vma_is_special_mapping(vma, &vdso_mapping) ||
 				vma_is_special_mapping(vma, &vvar_mapping)) {
 			mmap_write_unlock(mm);
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index bca625a60186..6df6ece8a28e 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -1,9 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
-#define HAVE_CSUM_COPY_USER
-#define _HAVE_ARCH_CSUM_AND_COPY
-#ifdef CONFIG_X86_32
-# include <asm/checksum_32.h>
+#ifdef CONFIG_GENERIC_CSUM
+# include <asm-generic/checksum.h>
 #else
-# include <asm/checksum_64.h>
+# define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
+# define HAVE_CSUM_COPY_USER
+# define _HAVE_ARCH_CSUM_AND_COPY
+# ifdef CONFIG_X86_32
+#  include <asm/checksum_32.h>
+# else
+#  include <asm/checksum_64.h>
+# endif
 #endif
diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h
new file mode 100644
index 000000000000..8fa6ac0e2d76
--- /dev/null
+++ b/arch/x86/include/asm/kmsan.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * x86 KMSAN support.
+ *
+ * Copyright (C) 2022, Google LLC
+ * Author: Alexander Potapenko <glider@google.com>
+ */
+
+#ifndef _ASM_X86_KMSAN_H
+#define _ASM_X86_KMSAN_H
+
+#ifndef MODULE
+
+#include <asm/cpu_entry_area.h>
+#include <asm/processor.h>
+#include <linux/mmzone.h>
+
+DECLARE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_shadow);
+DECLARE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_origin);
+
+/*
+ * Functions below are declared in the header to make sure they are inlined.
+ * They all are called from kmsan_get_metadata() for every memory access in
+ * the kernel, so speed is important here.
+ */
+
+/*
+ * Compute metadata addresses for the CPU entry area on x86.
+ */
+static inline void *arch_kmsan_get_meta_or_null(void *addr, bool is_origin)
+{
+	unsigned long addr64 = (unsigned long)addr;
+	char *metadata_array;
+	unsigned long off;
+	int cpu;
+
+	if ((addr64 < CPU_ENTRY_AREA_BASE) ||
+	    (addr64 >= (CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE)))
+		return NULL;
+	cpu = (addr64 - CPU_ENTRY_AREA_BASE) / CPU_ENTRY_AREA_SIZE;
+	off = addr64 - (unsigned long)get_cpu_entry_area(cpu);
+	if ((off < 0) || (off >= CPU_ENTRY_AREA_SIZE))
+		return NULL;
+	metadata_array = is_origin ? cpu_entry_area_origin :
+				     cpu_entry_area_shadow;
+	return &per_cpu(metadata_array[off], cpu);
+}
+
+/*
+ * Taken from arch/x86/mm/physaddr.h to avoid using an instrumented version.
+ */
+static inline bool kmsan_phys_addr_valid(unsigned long addr)
+{
+	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT))
+		return !(addr >> boot_cpu_data.x86_phys_bits);
+	else
+		return true;
+}
+
+/*
+ * Taken from arch/x86/mm/physaddr.c to avoid using an instrumented version.
+ */
+static inline bool kmsan_virt_addr_valid(void *addr)
+{
+	unsigned long x = (unsigned long)addr;
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* use the carry flag to determine if x was < __START_KERNEL_map */
+	if (unlikely(x > y)) {
+		x = y + phys_base;
+
+		if (y >= KERNEL_IMAGE_SIZE)
+			return false;
+	} else {
+		x = y + (__START_KERNEL_map - PAGE_OFFSET);
+
+		/* carry flag will be set if starting x was >= PAGE_OFFSET */
+		if ((x > y) || !kmsan_phys_addr_valid(x))
+			return false;
+	}
+
+	return pfn_valid(x >> PAGE_SHIFT);
+}
+
+#endif /* !MODULE */
+
+#endif /* _ASM_X86_KMSAN_H */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index baa70451b8df..198e03e59ca1 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -8,6 +8,8 @@
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
+#include <linux/kmsan-checks.h>
+
 /* duplicated to the one in bootmem.h */
 extern unsigned long max_pfn;
 extern unsigned long phys_base;
@@ -47,6 +49,11 @@ void clear_page_erms(void *page);
 
 static inline void clear_page(void *page)
 {
+	/*
+	 * Clean up KMSAN metadata for the page being cleared. The assembly call
+	 * below clobbers @page, so we perform unpoisoning before it.
+	 */
+	kmsan_unpoison_memory(page, PAGE_SIZE);
 	alternative_call_2(clear_page_orig,
 			   clear_page_rep, X86_FEATURE_REP_GOOD,
 			   clear_page_erms, X86_FEATURE_ERMS,
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index e896ebef8c24..28421a887209 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -256,10 +256,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 /* We always extract/encode the offset by shifting it all the way up, and then down again */
 #define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
 
-#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
-#define __swp_type(x)			(((x).val) & 0x1f)
-#define __swp_offset(x)			((x).val >> 5)
-#define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+#define __swp_type(x)			(((x).val) & ((1UL << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)			((x).val >> SWP_TYPE_BITS)
+#define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << SWP_TYPE_BITS})
 
 /*
  * Normally, __swp_entry() converts from arch-independent swp_entry_t to
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 44e2d6f1dbaa..5059799bebe3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -815,7 +815,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) !=
+	       (_KERNPG_TABLE & ~_PAGE_ACCESSED);
 }
 
 static inline unsigned long pages_to_mb(unsigned long npg)
@@ -1431,10 +1432,10 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
-#define arch_faults_on_old_pte arch_faults_on_old_pte
-static inline bool arch_faults_on_old_pte(void)
+#define arch_has_hw_pte_young arch_has_hw_pte_young
+static inline bool arch_has_hw_pte_young(void)
 {
-	return false;
+	return true;
 }
 
 #ifdef CONFIG_PAGE_TABLE_CHECK
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 70e360a2e5fb..04f36063ad54 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -139,7 +139,52 @@ extern unsigned int ptrs_per_p4d;
 # define VMEMMAP_START		__VMEMMAP_BASE_L4
 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
-#define VMALLOC_END		(VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)
+/*
+ * End of the region for which vmalloc page tables are pre-allocated.
+ * For non-KMSAN builds, this is the same as VMALLOC_END.
+ * For KMSAN builds, VMALLOC_START..VMEMORY_END is 4 times bigger than
+ * VMALLOC_START..VMALLOC_END (see below).
+ */
+#define VMEMORY_END		(VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)
+
+#ifndef CONFIG_KMSAN
+#define VMALLOC_END		VMEMORY_END
+#else
+/*
+ * In KMSAN builds vmalloc area is four times smaller, and the remaining 3/4
+ * are used to keep the metadata for virtual pages. The memory formerly
+ * belonging to vmalloc area is now laid out as follows:
+ *
+ * 1st quarter: VMALLOC_START to VMALLOC_END - new vmalloc area
+ * 2nd quarter: KMSAN_VMALLOC_SHADOW_START to
+ *              VMALLOC_END+KMSAN_VMALLOC_SHADOW_OFFSET - vmalloc area shadow
+ * 3rd quarter: KMSAN_VMALLOC_ORIGIN_START to
+ *              VMALLOC_END+KMSAN_VMALLOC_ORIGIN_OFFSET - vmalloc area origins
+ * 4th quarter: KMSAN_MODULES_SHADOW_START to KMSAN_MODULES_ORIGIN_START
+ *              - shadow for modules,
+ *              KMSAN_MODULES_ORIGIN_START to
+ *              KMSAN_MODULES_ORIGIN_START + MODULES_LEN - origins for modules.
+ */
+#define VMALLOC_QUARTER_SIZE	((VMALLOC_SIZE_TB << 40) >> 2)
+#define VMALLOC_END		(VMALLOC_START + VMALLOC_QUARTER_SIZE - 1)
+
+/*
+ * vmalloc metadata addresses are calculated by adding shadow/origin offsets
+ * to vmalloc address.
+ */
+#define KMSAN_VMALLOC_SHADOW_OFFSET	VMALLOC_QUARTER_SIZE
+#define KMSAN_VMALLOC_ORIGIN_OFFSET	(VMALLOC_QUARTER_SIZE << 1)
+
+#define KMSAN_VMALLOC_SHADOW_START	(VMALLOC_START + KMSAN_VMALLOC_SHADOW_OFFSET)
+#define KMSAN_VMALLOC_ORIGIN_START	(VMALLOC_START + KMSAN_VMALLOC_ORIGIN_OFFSET)
+
+/*
+ * The shadow/origin for modules are placed one by one in the last 1/4 of
+ * vmalloc space.
+ */
+#define KMSAN_MODULES_SHADOW_START	(VMALLOC_END + KMSAN_VMALLOC_ORIGIN_OFFSET + 1)
+#define KMSAN_MODULES_ORIGIN_START	(KMSAN_MODULES_SHADOW_START + MODULES_LEN)
+#endif /* CONFIG_KMSAN */
 
 #define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 6a9ccc1b2be5..64df897c0ee3 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_SPARSEMEM_H
 #define _ASM_X86_SPARSEMEM_H
 
+#include <linux/types.h>
+
 #ifdef CONFIG_SPARSEMEM
 /*
  * generic non-linear memory support:
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 6e450827f677..3b87d889b6e1 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -11,11 +11,23 @@
    function. */
 
 #define __HAVE_ARCH_MEMCPY 1
+#if defined(__SANITIZE_MEMORY__)
+#undef memcpy
+void *__msan_memcpy(void *dst, const void *src, size_t size);
+#define memcpy __msan_memcpy
+#else
 extern void *memcpy(void *to, const void *from, size_t len);
+#endif
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #define __HAVE_ARCH_MEMSET
+#if defined(__SANITIZE_MEMORY__)
+extern void *__msan_memset(void *s, int c, size_t n);
+#undef memset
+#define memset __msan_memset
+#else
 void *memset(void *s, int c, size_t n);
+#endif
 void *__memset(void *s, int c, size_t n);
 
 #define __HAVE_ARCH_MEMSET16
@@ -55,7 +67,13 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 }
 
 #define __HAVE_ARCH_MEMMOVE
+#if defined(__SANITIZE_MEMORY__)
+#undef memmove
+void *__msan_memmove(void *dest, const void *src, size_t len);
+#define memmove __msan_memmove
+#else
 void *memmove(void *dest, const void *src, size_t count);
+#endif
 void *__memmove(void *dest, const void *src, size_t count);
 
 int memcmp(const void *cs, const void *ct, size_t count);
@@ -64,8 +82,7 @@ char *strcpy(char *dest, const char *src);
 char *strcat(char *dest, const char *src);
 int strcmp(const char *cs, const char *ct);
 
-#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
-
+#if (defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__))
 /*
  * For files that not instrumented (e.g. mm/slub.c) we
  * should use not instrumented version of mem* functions.
@@ -73,7 +90,9 @@ int strcmp(const char *cs, const char *ct);
 
 #undef memcpy
 #define memcpy(dst, src, len) __memcpy(dst, src, len)
+#undef memmove
 #define memmove(dst, src, len) __memmove(dst, src, len)
+#undef memset
 #define memset(s, c, n) __memset(s, c, n)
 
 #ifndef __NO_FORTIFY
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1ec6a9ea2328..8bc614cfe21b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -5,6 +5,7 @@
  * User space memory access functions
  */
 #include <linux/compiler.h>
+#include <linux/instrumented.h>
 #include <linux/kasan-checks.h>
 #include <linux/string.h>
 #include <asm/asm.h>
@@ -103,6 +104,7 @@ extern int __get_user_bad(void);
 		     : "=a" (__ret_gu), "=r" (__val_gu),		\
 			ASM_CALL_CONSTRAINT				\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
+	instrument_get_user(__val_gu);					\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
 	__builtin_expect(__ret_gu, 0);					\
 })
@@ -192,9 +194,11 @@ extern void __put_user_nocheck_8(void);
 	int __ret_pu;							\
 	void __user *__ptr_pu;						\
 	register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX);		\
-	__chk_user_ptr(ptr);						\
-	__ptr_pu = (ptr);						\
-	__val_pu = (x);							\
+	__typeof__(*(ptr)) __x = (x); /* eval x once */			\
+	__typeof__(ptr) __ptr = (ptr); /* eval ptr once */		\
+	__chk_user_ptr(__ptr);						\
+	__ptr_pu = __ptr;						\
+	__val_pu = __x;							\
 	asm volatile("call __" #fn "_%P[size]"				\
 		     : "=c" (__ret_pu),					\
 			ASM_CALL_CONSTRAINT				\
@@ -202,6 +206,7 @@ extern void __put_user_nocheck_8(void);
 		       "r" (__val_pu),					\
 		       [size] "i" (sizeof(*(ptr)))			\
 		     :"ebx");						\
+	instrument_put_user(__x, __ptr, sizeof(*(ptr)));		\
 	__builtin_expect(__ret_pu, 0);					\
 })
 
@@ -248,23 +253,25 @@ extern void __put_user_nocheck_8(void);
 
 #define __put_user_size(x, ptr, size, label)				\
 do {									\
+	__typeof__(*(ptr)) __x = (x); /* eval x once */			\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__put_user_goto(x, ptr, "b", "iq", label);		\
+		__put_user_goto(__x, ptr, "b", "iq", label);		\
 		break;							\
 	case 2:								\
-		__put_user_goto(x, ptr, "w", "ir", label);		\
+		__put_user_goto(__x, ptr, "w", "ir", label);		\
 		break;							\
 	case 4:								\
-		__put_user_goto(x, ptr, "l", "ir", label);		\
+		__put_user_goto(__x, ptr, "l", "ir", label);		\
 		break;							\
 	case 8:								\
-		__put_user_goto_u64(x, ptr, label);			\
+		__put_user_goto_u64(__x, ptr, label);			\
 		break;							\
 	default:							\
 		__put_user_bad();					\
 	}								\
+	instrument_put_user(__x, ptr, size);				\
 } while (0)
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
@@ -305,6 +312,7 @@ do {									\
 	default:							\
 		(x) = __get_user_bad();					\
 	}								\
+	instrument_get_user(x);						\
 } while (0)
 
 #define __get_user_asm(x, addr, itype, ltype, label)			\
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f4479f6415d7..f901658d9f7c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,8 @@ KASAN_SANITIZE_sev.o					:= n
 # With some compiler versions the generated code results in boot hangs, caused
 # by several compilation units. To be safe, disable all instrumentation.
 KCSAN_SANITIZE := n
+KMSAN_SANITIZE_head$(BITS).o				:= n
+KMSAN_SANITIZE_nmi.o					:= n
 
 # If instrumentation of this dir is enabled, boot hangs during first second.
 # Probably could be more selective here, but note that files related to irqs,
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 9661e3e802be..f10a921ee756 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -12,6 +12,7 @@ endif
 # If these files are instrumented, boot hangs during the first second.
 KCOV_INSTRUMENT_common.o := n
 KCOV_INSTRUMENT_perf_event.o := n
+KMSAN_SANITIZE_common.o := n
 
 # As above, instrumenting secondary CPU boot code causes boot hangs.
 KCSAN_SANITIZE_common.o := n
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b3dba35f466e..0bf6779187dd 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -177,6 +177,12 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
 	}
 }
 
+/*
+ * This function reads pointers from the stack and dereferences them. The
+ * pointers may not have their KMSAN shadow set up properly, which may result
+ * in false positive reports. Disable instrumentation to avoid those.
+ */
+__no_kmsan_checks
 static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, const char *log_lvl)
 {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 1962008fe743..6b3418bff326 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -553,6 +553,7 @@ void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32)
  * Kprobes not supported here. Set the probe on schedule instead.
  * Function graph tracer not supported too.
  */
+__no_kmsan_checks
 __visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 3bacd935f840..4c1bcb6053fc 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -95,7 +95,7 @@ void __init tboot_probe(void)
 
 static pgd_t *tboot_pg_dir;
 static struct mm_struct tboot_mm = {
-	.mm_rb          = RB_ROOT,
+	.mm_mt          = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, tboot_mm.mmap_lock),
 	.pgd            = swapper_pg_dir,
 	.mm_users       = ATOMIC_INIT(2),
 	.mm_count       = ATOMIC_INIT(1),
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 8e1c50c86e5d..d8ba93778ae3 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -183,6 +183,16 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp)
 }
 #endif
 
+/*
+ * While walking the stack, KMSAN may stomp on stale locals from other
+ * functions that were marked as uninitialized upon function exit, and
+ * now hold the call frame information for the current function (e.g. the frame
+ * pointer). Because KMSAN does not specifically mark call frames as
+ * initialized, false positive reports are possible. To prevent such reports,
+ * we mark the functions scanning the stack (here and below) with
+ * __no_kmsan_checks.
+ */
+__no_kmsan_checks
 static bool update_stack_state(struct unwind_state *state,
 			       unsigned long *next_bp)
 {
@@ -250,6 +260,7 @@ static bool update_stack_state(struct unwind_state *state,
 	return true;
 }
 
+__no_kmsan_checks
 bool unwind_next_frame(struct unwind_state *state)
 {
 	struct pt_regs *regs;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f76747862bd2..7ba5f61d7273 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -65,7 +65,9 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y)
 endif
 else
         obj-y += iomap_copy_64.o
+ifneq ($(CONFIG_GENERIC_CSUM),y)
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
+endif
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index 3e2f33fc33de..e0411a3774d4 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -1,6 +1,7 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/kmsan-checks.h>
 
 #define movs(type,to,from) \
 	asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory")
@@ -37,6 +38,8 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si
 		n-=2;
 	}
 	rep_movs(to, (const void *)from, n);
+	/* KMSAN must treat values read from devices as initialized. */
+	kmsan_unpoison_memory(to, n);
 }
 
 static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
@@ -44,6 +47,8 @@ static void string_memcpy_toio(volatile void __iomem *to, const void *from, size
 	if (unlikely(!n))
 		return;
 
+	/* Make sure uninitialized memory isn't copied to devices. */
+	kmsan_check_memory(from, n);
 	/* Align any unaligned destination IO */
 	if (unlikely(1 & (unsigned long)to)) {
 		movs("b", to, from);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 829c1409ffbd..c80febc44cd2 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -14,6 +14,8 @@ KASAN_SANITIZE_pgprot.o		:= n
 # Disable KCSAN entirely, because otherwise we get warnings that some functions
 # reference __initdata sections.
 KCSAN_SANITIZE := n
+# Avoid recursion by not calling KMSAN hooks for CEA code.
+KMSAN_SANITIZE_cpu_entry_area.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_mem_encrypt.o		= -pg
@@ -44,6 +46,9 @@ obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 KASAN_SANITIZE_kasan_init_$(BITS).o := n
 obj-$(CONFIG_KASAN)		+= kasan_init_$(BITS).o
 
+KMSAN_SANITIZE_kmsan_shadow.o	:= n
+obj-$(CONFIG_KMSAN)		+= kmsan_shadow.o
+
 obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a498ae1fbe66..7b0d4ab894c8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -260,7 +260,7 @@ static noinline int vmalloc_fault(unsigned long address)
 }
 NOKPROBE_SYMBOL(vmalloc_fault);
 
-void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+static void __arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
 
@@ -284,6 +284,27 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 	}
 }
 
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+{
+	__arch_sync_kernel_mappings(start, end);
+#ifdef CONFIG_KMSAN
+	/*
+	 * KMSAN maintains two additional metadata page mappings for the
+	 * [VMALLOC_START, VMALLOC_END) range. These mappings start at
+	 * KMSAN_VMALLOC_SHADOW_START and KMSAN_VMALLOC_ORIGIN_START and
+	 * have to be synced together with the vmalloc memory mapping.
+	 */
+	if (start >= VMALLOC_START && end < VMALLOC_END) {
+		__arch_sync_kernel_mappings(
+			start - VMALLOC_START + KMSAN_VMALLOC_SHADOW_START,
+			end - VMALLOC_START + KMSAN_VMALLOC_SHADOW_START);
+		__arch_sync_kernel_mappings(
+			start - VMALLOC_START + KMSAN_VMALLOC_ORIGIN_START,
+			end - VMALLOC_START + KMSAN_VMALLOC_ORIGIN_START);
+	}
+#endif
+}
+
 static bool low_pfn(unsigned long pfn)
 {
 	return pfn < max_low_pfn;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 82a042c03824..9121bc1b9453 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1054,7 +1054,7 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 }
 
 #ifdef CONFIG_SWAP
-unsigned long max_swapfile_size(void)
+unsigned long arch_max_swapfile_size(void)
 {
 	unsigned long pages;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7ea7d4745681..3f040c6e5d13 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1288,7 +1288,7 @@ static void __init preallocate_vmalloc_pages(void)
 	unsigned long addr;
 	const char *lvl;
 
-	for (addr = VMALLOC_START; addr <= VMALLOC_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+	for (addr = VMALLOC_START; addr <= VMEMORY_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
 		pgd_t *pgd = pgd_offset_k(addr);
 		p4d_t *p4d;
 		pud_t *pud;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 1ad0228f8ceb..78c5bc654cff 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -17,6 +17,7 @@
 #include <linux/cc_platform.h>
 #include <linux/efi.h>
 #include <linux/pgtable.h>
+#include <linux/kmsan.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -479,6 +480,8 @@ void iounmap(volatile void __iomem *addr)
 		return;
 	}
 
+	kmsan_iounmap_page_range((unsigned long)addr,
+		(unsigned long)addr + get_vm_area_size(p));
 	memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p));
 
 	/* Finally remove it */
diff --git a/arch/x86/mm/kmsan_shadow.c b/arch/x86/mm/kmsan_shadow.c
new file mode 100644
index 000000000000..bee2ec4a3bfa
--- /dev/null
+++ b/arch/x86/mm/kmsan_shadow.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86-specific bits of KMSAN shadow implementation.
+ *
+ * Copyright (C) 2022 Google LLC
+ * Author: Alexander Potapenko <glider@google.com>
+ */
+
+#include <asm/cpu_entry_area.h>
+#include <linux/percpu-defs.h>
+
+/*
+ * Addresses within the CPU entry area (including e.g. exception stacks) do not
+ * have struct page entries corresponding to them, so they need separate
+ * handling.
+ * arch_kmsan_get_meta_or_null() (declared in the header) maps the addresses in
+ * CPU entry area to addresses in cpu_entry_area_shadow/cpu_entry_area_origin.
+ */
+DEFINE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_shadow);
+DEFINE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_origin);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a932d7712d85..8525f2876fb4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -550,7 +550,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	return ret;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pmd_t *pmdp)
 {
@@ -562,6 +562,9 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 
 	return ret;
 }
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int pudp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pud_t *pudp)
 {
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index 83f1b6a56449..f614009d3e4e 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -10,6 +10,7 @@
 # Sanitizer runtimes are unavailable and cannot be linked here.
 KASAN_SANITIZE			:= n
 KCSAN_SANITIZE			:= n
+KMSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y
 
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 12ac277282ba..bcb0c5d2abc2 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -771,7 +771,7 @@ config HIGHMEM
 
 	  If unsure, say Y.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "11"
 	help
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 7966a58af472..1ff0c858544f 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -111,6 +111,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index 201356faa7e6..b3c2450d6f23 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -58,6 +58,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct vm_area_struct *vmm;
+	struct vma_iterator vmi;
 
 	if (flags & MAP_FIXED) {
 		/* We do not accept a shared mapping if it would violate
@@ -79,15 +80,20 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	else
 		addr = PAGE_ALIGN(addr);
 
-	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
-		/* At this point:  (!vmm || addr < vmm->vm_end). */
-		if (TASK_SIZE - len < addr)
-			return -ENOMEM;
-		if (!vmm || addr + len <= vm_start_gap(vmm))
-			return addr;
+	vma_iter_init(&vmi, current->mm, addr);
+	for_each_vma(vmi, vmm) {
+		/* At this point:  (addr < vmm->vm_end). */
+		if (addr + len <= vm_start_gap(vmm))
+			break;
+
 		addr = vmm->vm_end;
 		if (flags & MAP_SHARED)
 			addr = COLOUR_ALIGN(addr, pgoff);
 	}
+
+	if (TASK_SIZE - len < addr)
+		return -ENOMEM;
+
+	return addr;
 }
 #endif