Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

1 files changed, 131 insertions, 28 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aab70355d64f..e24b40c52468 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -355,15 +355,18 @@ enum zone_watermarks {
 };
 
 /*
- * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional
- * for pageblock size for THP if configured.
+ * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list
+ * for THP which will usually be GFP_MOVABLE. Even if it is another type,
+ * it should not contribute to serious fragmentation causing THP allocation
+ * failures.
  */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define NR_PCP_THP 1
 #else
 #define NR_PCP_THP 0
 #endif
-#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP))
+#define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1))
+#define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP)
 
 /*
  * Shift to encode migratetype and order in the same integer, with order
@@ -379,6 +382,7 @@ enum zone_watermarks {
 
 /* Fields and list protected by pagesets local_lock in page_alloc.c */
 struct per_cpu_pages {
+	spinlock_t lock;	/* Protects lists field */
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */
 	int batch;		/* chunk size for buddy add/remove */
@@ -389,7 +393,7 @@ struct per_cpu_pages {
 
 	/* Lists of pages, one per migrate type stored on the pcp-lists */
 	struct list_head lists[NR_PCP_LISTS];
-};
+} ____cacheline_aligned_in_smp;
 
 struct per_cpu_zonestat {
 #ifdef CONFIG_SMP
@@ -591,8 +595,8 @@ struct zone {
 	 * give them a chance of being in the same cacheline.
 	 *
 	 * Write access to present_pages at runtime should be protected by
-	 * mem_hotplug_begin/end(). Any reader who can't tolerant drift of
-	 * present_pages should get_online_mems() to get a stable value.
+	 * mem_hotplug_begin/done(). Any reader who can't tolerant drift of
+	 * present_pages should use get_online_mems() to get a stable value.
 	 */
 	atomic_long_t		managed_pages;
 	unsigned long		spanned_pages;
@@ -730,6 +734,86 @@ static inline bool zone_is_empty(struct zone *zone)
 	return zone->spanned_pages == 0;
 }
 
+#ifndef BUILD_VDSO32_64
+/*
+ * The zone field is never updated after free_area_init_core()
+ * sets it, so none of the operations on it need to be atomic.
+ */
+
+/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */
+#define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
+#define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
+#define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
+#define LAST_CPUPID_PGOFF	(ZONES_PGOFF - LAST_CPUPID_WIDTH)
+#define KASAN_TAG_PGOFF		(LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
+
+/*
+ * Define the bit shifts to access each section.  For non-existent
+ * sections we define the shift as 0; that plus a 0 mask ensures
+ * the compiler will optimise away reference to them.
+ */
+#define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
+#define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
+#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
+#define LAST_CPUPID_PGSHIFT	(LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0))
+#define KASAN_TAG_PGSHIFT	(KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0))
+
+/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+#define ZONEID_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT)
+#define ZONEID_PGOFF		((SECTIONS_PGOFF < ZONES_PGOFF) ? \
+						SECTIONS_PGOFF : ZONES_PGOFF)
+#else
+#define ZONEID_SHIFT		(NODES_SHIFT + ZONES_SHIFT)
+#define ZONEID_PGOFF		((NODES_PGOFF < ZONES_PGOFF) ? \
+						NODES_PGOFF : ZONES_PGOFF)
+#endif
+
+#define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))
+
+#define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
+#define NODES_MASK		((1UL << NODES_WIDTH) - 1)
+#define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
+#define LAST_CPUPID_MASK	((1UL << LAST_CPUPID_SHIFT) - 1)
+#define KASAN_TAG_MASK		((1UL << KASAN_TAG_WIDTH) - 1)
+#define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
+
+static inline enum zone_type page_zonenum(const struct page *page)
+{
+	ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
+	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
+}
+
+static inline enum zone_type folio_zonenum(const struct folio *folio)
+{
+	return page_zonenum(&folio->page);
+}
+
+#ifdef CONFIG_ZONE_DEVICE
+static inline bool is_zone_device_page(const struct page *page)
+{
+	return page_zonenum(page) == ZONE_DEVICE;
+}
+extern void memmap_init_zone_device(struct zone *, unsigned long,
+				    unsigned long, struct dev_pagemap *);
+#else
+static inline bool is_zone_device_page(const struct page *page)
+{
+	return false;
+}
+#endif
+
+static inline bool folio_is_zone_device(const struct folio *folio)
+{
+	return is_zone_device_page(&folio->page);
+}
+
+static inline bool is_zone_movable_page(const struct page *page)
+{
+	return page_zonenum(page) == ZONE_MOVABLE;
+}
+#endif
+
 /*
  * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
  * intersection with the given zone
@@ -870,7 +954,7 @@ typedef struct pglist_data {
 	unsigned long nr_reclaim_start;	/* nr pages written while throttled
 					 * when throttling started. */
 	struct task_struct *kswapd;	/* Protected by
-					   mem_hotplug_begin/end() */
+					   mem_hotplug_begin/done() */
 	int kswapd_order;
 	enum zone_type kswapd_highest_zoneidx;
 
@@ -1053,15 +1137,6 @@ static inline int is_highmem_idx(enum zone_type idx)
 #endif
 }
 
-#ifdef CONFIG_ZONE_DMA
-bool has_managed_dma(void);
-#else
-static inline bool has_managed_dma(void)
-{
-	return false;
-}
-#endif
-
 /**
  * is_highmem - helper function to quickly check if a struct zone is a
  *              highmem zone or not.  This is an attempt to keep references
@@ -1071,12 +1146,17 @@ static inline bool has_managed_dma(void)
  */
 static inline int is_highmem(struct zone *zone)
 {
-#ifdef CONFIG_HIGHMEM
 	return is_highmem_idx(zone_idx(zone));
+}
+
+#ifdef CONFIG_ZONE_DMA
+bool has_managed_dma(void);
 #else
-	return 0;
-#endif
+static inline bool has_managed_dma(void)
+{
+	return false;
 }
+#endif
 
 /* These two functions are used to setup the per zone pages min values */
 struct ctl_table;
@@ -1418,16 +1498,32 @@ extern size_t mem_section_usage_size(void);
  *      (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the
  *      worst combination is powerpc with 256k pages,
  *      which results in PFN_SECTION_SHIFT equal 6.
- * To sum it up, at least 6 bits are available.
+ * To sum it up, at least 6 bits are available on all architectures.
+ * However, we can exceed 6 bits on some other architectures except
+ * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available
+ * with the worst case of 64K pages on arm64) if we make sure the
+ * exceeded bit is not applicable to powerpc.
  */
-#define SECTION_MARKED_PRESENT		(1UL<<0)
-#define SECTION_HAS_MEM_MAP		(1UL<<1)
-#define SECTION_IS_ONLINE		(1UL<<2)
-#define SECTION_IS_EARLY		(1UL<<3)
-#define SECTION_TAINT_ZONE_DEVICE	(1UL<<4)
-#define SECTION_MAP_LAST_BIT		(1UL<<5)
-#define SECTION_MAP_MASK		(~(SECTION_MAP_LAST_BIT-1))
-#define SECTION_NID_SHIFT		6
+enum {
+	SECTION_MARKED_PRESENT_BIT,
+	SECTION_HAS_MEM_MAP_BIT,
+	SECTION_IS_ONLINE_BIT,
+	SECTION_IS_EARLY_BIT,
+#ifdef CONFIG_ZONE_DEVICE
+	SECTION_TAINT_ZONE_DEVICE_BIT,
+#endif
+	SECTION_MAP_LAST_BIT,
+};
+
+#define SECTION_MARKED_PRESENT		BIT(SECTION_MARKED_PRESENT_BIT)
+#define SECTION_HAS_MEM_MAP		BIT(SECTION_HAS_MEM_MAP_BIT)
+#define SECTION_IS_ONLINE		BIT(SECTION_IS_ONLINE_BIT)
+#define SECTION_IS_EARLY		BIT(SECTION_IS_EARLY_BIT)
+#ifdef CONFIG_ZONE_DEVICE
+#define SECTION_TAINT_ZONE_DEVICE	BIT(SECTION_TAINT_ZONE_DEVICE_BIT)
+#endif
+#define SECTION_MAP_MASK		(~(BIT(SECTION_MAP_LAST_BIT) - 1))
+#define SECTION_NID_SHIFT		SECTION_MAP_LAST_BIT
 
 static inline struct page *__section_mem_map_addr(struct mem_section *section)
 {
@@ -1466,12 +1562,19 @@ static inline int online_section(struct mem_section *section)
 	return (section && (section->section_mem_map & SECTION_IS_ONLINE));
 }
 
+#ifdef CONFIG_ZONE_DEVICE
 static inline int online_device_section(struct mem_section *section)
 {
 	unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE;
 
 	return section && ((section->section_mem_map & flags) == flags);
 }
+#else
+static inline int online_device_section(struct mem_section *section)
+{
+	return 0;
+}
+#endif
 
 static inline int online_section_nr(unsigned long nr)
 {