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, 39 insertions, 94 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index a37b8c062daa..18e01474cf6b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/pgtable.h>
 #include <linux/kasan.h>
+#include <linux/memremap.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -427,7 +428,6 @@ extern unsigned int kobjsize(const void *objp);
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
  */
-extern pgprot_t protection_map[16];
 
 /*
  * The default fault flags that should be used by most of the
@@ -858,7 +858,7 @@ static inline struct folio *virt_to_folio(const void *x)
 	return page_folio(page);
 }
 
-void __put_page(struct page *page);
+void __folio_put(struct folio *folio);
 
 void put_pages_list(struct list_head *pages);
 
@@ -895,11 +895,7 @@ static inline void set_compound_page_dtor(struct page *page,
 	page[1].compound_dtor = compound_dtor;
 }
 
-static inline void destroy_compound_page(struct page *page)
-{
-	VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page);
-	compound_page_dtors[page[1].compound_dtor](page);
-}
+void destroy_large_folio(struct folio *folio);
 
 static inline int head_compound_pincount(struct page *head)
 {
@@ -1052,84 +1048,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
  *   back into memory.
  */
 
-/*
- * 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;
-}
-
 #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
 DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
 
@@ -1204,7 +1122,7 @@ static inline __must_check bool try_get_page(struct page *page)
 static inline void folio_put(struct folio *folio)
 {
 	if (folio_put_testzero(folio))
-		__put_page(&folio->page);
+		__folio_put(folio);
 }
 
 /**
@@ -1224,7 +1142,26 @@ static inline void folio_put(struct folio *folio)
 static inline void folio_put_refs(struct folio *folio, int refs)
 {
 	if (folio_ref_sub_and_test(folio, refs))
-		__put_page(&folio->page);
+		__folio_put(folio);
+}
+
+void release_pages(struct page **pages, int nr);
+
+/**
+ * folios_put - Decrement the reference count on an array of folios.
+ * @folios: The folios.
+ * @nr: How many folios there are.
+ *
+ * Like folio_put(), but for an array of folios.  This is more efficient
+ * than writing the loop yourself as it will optimise the locks which
+ * need to be taken if the folios are freed.
+ *
+ * Context: May be called in process or interrupt context, but not in NMI
+ * context.  May be called while holding a spinlock.
+ */
+static inline void folios_put(struct folio **folios, unsigned int nr)
+{
+	release_pages((struct page **)folios, nr);
 }
 
 static inline void put_page(struct page *page)
@@ -1599,7 +1536,7 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 
 /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
 #ifdef CONFIG_MIGRATION
-static inline bool is_pinnable_page(struct page *page)
+static inline bool is_longterm_pinnable_page(struct page *page)
 {
 #ifdef CONFIG_CMA
 	int mt = get_pageblock_migratetype(page);
@@ -1607,18 +1544,20 @@ static inline bool is_pinnable_page(struct page *page)
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page));
+	return !(is_device_coherent_page(page) ||
+		 is_zone_movable_page(page) ||
+		 is_zero_pfn(page_to_pfn(page)));
 }
 #else
-static inline bool is_pinnable_page(struct page *page)
+static inline bool is_longterm_pinnable_page(struct page *page)
 {
 	return true;
 }
 #endif
 
-static inline bool folio_is_pinnable(struct folio *folio)
+static inline bool folio_is_longterm_pinnable(struct folio *folio)
 {
-	return is_pinnable_page(&folio->page);
+	return is_longterm_pinnable_page(&folio->page);
 }
 
 static inline void set_page_zone(struct page *page, enum zone_type zone)
@@ -1969,8 +1908,12 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
  * for now all the callers are only use one of the flags at the same
  * time.
  */
-/* Whether we should allow dirty bit accounting */
-#define  MM_CP_DIRTY_ACCT                  (1UL << 0)
+/*
+ * Whether we should manually check if we can map individual PTEs writable,
+ * because something (e.g., COW, uffd-wp) blocks that from happening for all
+ * PTEs automatically in a writable mapping.
+ */
+#define  MM_CP_TRY_CHANGE_WRITABLE	   (1UL << 0)
 /* Whether this protection change is for NUMA hints */
 #define  MM_CP_PROT_NUMA                   (1UL << 1)
 /* Whether this change is for write protecting */
@@ -3241,6 +3184,8 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
 };
+int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
+		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);