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
  ...

9 files changed, 197 insertions, 24 deletions

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)			\