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)
 #de