Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

1 files changed, 131 insertions, 95 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fec1495859857..ae866bc9bad67 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -725,7 +725,6 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 
 #else /* CONFIG_PER_VMA_LOCK */
 
-static inline void vma_init_lock(struct vm_area_struct *vma) {}
 static inline bool vma_start_read(struct vm_area_struct *vma)
 		{ return false; }
 static inline void vma_end_read(struct vm_area_struct *vma) {}
@@ -866,11 +865,24 @@ static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
 	return mas_find(&vmi->mas, ULONG_MAX);
 }
 
+static inline
+struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi)
+{
+	return mas_next_range(&vmi->mas, ULONG_MAX);
+}
+
+
 static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
 {
 	return mas_prev(&vmi->mas, 0);
 }
 
+static inline
+struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi)
+{
+	return mas_prev_range(&vmi->mas, 0);
+}
+
 static inline unsigned long vma_iter_addr(struct vma_iterator *vmi)
 {
 	return vmi->mas.index;
@@ -1208,17 +1220,6 @@ enum compound_dtor_id {
 #endif
 	NR_COMPOUND_DTORS,
 };
-extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS];
-
-static inline void set_compound_page_dtor(struct page *page,
-		enum compound_dtor_id compound_dtor)
-{
-	struct folio *folio = (struct folio *)page;
-
-	VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page);
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	folio->_folio_dtor = compound_dtor;
-}
 
 static inline void folio_set_compound_dtor(struct folio *folio,
 		enum compound_dtor_id compound_dtor)
@@ -1229,16 +1230,6 @@ static inline void folio_set_compound_dtor(struct folio *folio,
 
 void destroy_large_folio(struct folio *folio);
 
-static inline void set_compound_order(struct page *page, unsigned int order)
-{
-	struct folio *folio = (struct folio *)page;
-
-	folio->_folio_order = order;
-#ifdef CONFIG_64BIT
-	folio->_folio_nr_pages = 1U << order;
-#endif
-}
-
 /* Returns the number of bytes in this potentially compound page. */
 static inline unsigned long page_size(struct page *page)
 {
@@ -1932,39 +1923,35 @@ static inline bool is_zero_folio(const struct folio *folio)
 	return is_zero_page(&folio->page);
 }
 
-/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
+/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */
 #ifdef CONFIG_MIGRATION
-static inline bool is_longterm_pinnable_page(struct page *page)
+static inline bool folio_is_longterm_pinnable(struct folio *folio)
 {
 #ifdef CONFIG_CMA
-	int mt = get_pageblock_migratetype(page);
+	int mt = folio_migratetype(folio);
 
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
 	/* The zero page can be "pinned" but gets special handling. */
-	if (is_zero_page(page))
+	if (is_zero_folio(folio))
 		return true;
 
 	/* Coherent device memory must always allow eviction. */
-	if (is_device_coherent_page(page))
+	if (folio_is_device_coherent(folio))
 		return false;
 
-	/* Otherwise, non-movable zone pages can be pinned. */
-	return !is_zone_movable_page(page);
+	/* Otherwise, non-movable zone folios can be pinned. */
+	return !folio_is_zone_movable(folio);
+
 }
 #else
-static inline bool is_longterm_pinnable_page(struct page *page)
+static inline bool folio_is_longterm_pinnable(struct folio *folio)
 {
 	return true;
 }
 #endif
 
-static inline bool folio_is_longterm_pinnable(struct folio *folio)
-{
-	return is_longterm_pinnable_page(&folio->page);
-}
-
 static inline void set_page_zone(struct page *page, enum zone_type zone)
 {
 	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
@@ -2375,6 +2362,9 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 	unmap_mapping_range(mapping, holebegin, holelen, 0);
 }
 
+static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
+						unsigned long addr);
+
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
@@ -2383,19 +2373,42 @@ extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
 			      void *buf, int len, unsigned int gup_flags);
 
 long get_user_pages_remote(struct mm_struct *mm,
-			    unsigned long start, unsigned long nr_pages,
-			    unsigned int gup_flags, struct page **pages,
-			    struct vm_area_struct **vmas, int *locked);
+			   unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   int *locked);
 long pin_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
-			   struct vm_area_struct **vmas, int *locked);
+			   int *locked);
+
+static inline struct page *get_user_page_vma_remote(struct mm_struct *mm,
+						    unsigned long addr,
+						    int gup_flags,
+						    struct vm_area_struct **vmap)
+{
+	struct page *page;
+	struct vm_area_struct *vma;
+	int got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL);
+
+	if (got < 0)
+		return ERR_PTR(got);
+	if (got == 0)
+		return NULL;
+
+	vma = vma_lookup(mm, addr);
+	if (WARN_ON_ONCE(!vma)) {
+		put_page(page);
+		return ERR_PTR(-EINVAL);
+	}
+
+	*vmap = vma;
+	return page;
+}
+
 long get_user_pages(unsigned long start, unsigned long nr_pages,
-			    unsigned int gup_flags, struct page **pages,
-			    struct vm_area_struct **vmas);
+		    unsigned int gup_flags, struct page **pages);
 long pin_user_pages(unsigned long start, unsigned long nr_pages,
-		    unsigned int gup_flags, struct page **pages,
-		    struct vm_area_struct **vmas);
+		    unsigned int gup_flags, struct page **pages);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
@@ -2445,6 +2458,7 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
+bool vma_needs_dirty_tracking(struct vm_area_struct *vma);
 int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
 static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma)
 {
@@ -2810,14 +2824,25 @@ static inline void pgtable_pte_page_dtor(struct page *page)
 	dec_lruvec_page_state(page, NR_PAGETABLE);
 }
 
-#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
-({							\
-	spinlock_t *__ptl = pte_lockptr(mm, pmd);	\
-	pte_t *__pte = pte_offset_map(pmd, address);	\
-	*(ptlp) = __ptl;				\
-	spin_lock(__ptl);				\
-	__pte;						\
-})
+pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
+static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr)
+{
+	return __pte_offset_map(pmd, addr, NULL);
+}
+
+pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, spinlock_t **ptlp);
+static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, spinlock_t **ptlp)
+{
+	pte_t *pte;
+
+	__cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp));
+	return pte;
+}
+
+pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, spinlock_t **ptlp);
 
 #define pte_unmap_unlock(pte, ptl)	do {		\
 	spin_unlock(ptl);				\
@@ -2938,7 +2963,8 @@ extern unsigned long free_reserved_area(void *start, void *end,
 
 extern void adjust_managed_page_count(struct page *page, long count);
 
-extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
+extern void reserve_bootmem_region(phys_addr_t start,
+				   phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
 static inline void free_reserved_page(struct page *page)
@@ -3017,12 +3043,6 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_range(unsigned long, int, unsigned long,
-		unsigned long, unsigned long, enum meminit_context,
-		struct vmem_altmap *, int migratetype);
-extern void setup_per_zone_wmarks(void);
-extern void calculate_min_free_kbytes(void);
-extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
 
@@ -3043,11 +3063,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...);
 
 extern void setup_per_cpu_pageset(void);
 
-/* page_alloc.c */
-extern int min_free_kbytes;
-extern int watermark_boost_factor;
-extern int watermark_scale_factor;
-
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
 extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
@@ -3494,9 +3509,58 @@ static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
 	if (debug_pagealloc_enabled_static())
 		__kernel_map_pages(page, numpages, 0);
 }
+
+extern unsigned int _debug_guardpage_minorder;
+DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
+
+static inline unsigned int debug_guardpage_minorder(void)
+{
+	return _debug_guardpage_minorder;
+}
+
+static inline bool debug_guardpage_enabled(void)
+{
+	return static_branch_unlikely(&_debug_guardpage_enabled);
+}
+
+static inline bool page_is_guard(struct page *page)
+{
+	if (!debug_guardpage_enabled())
+		return false;
+
+	return PageGuard(page);
+}
+
+bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order,
+		      int migratetype);
+static inline bool set_page_guard(struct zone *zone, struct page *page,
+				  unsigned int order, int migratetype)
+{
+	if (!debug_guardpage_enabled())
+		return false;
+	return __set_page_guard(zone, page, order, migratetype);
+}
+
+void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order,
+			int migratetype);
+static inline void clear_page_guard(struct zone *zone, struct page *page,
+				    unsigned int order, int migratetype)
+{
+	if (!debug_guardpage_enabled())
+		return;
+	__clear_page_guard(zone, page, order, migratetype);
+}
+
 #else	/* CONFIG_DEBUG_PAGEALLOC */
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
 static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
+static inline unsigned int debug_guardpage_minorder(void) { return 0; }
+static inline bool debug_guardpage_enabled(void) { return false; }
+static inline bool page_is_guard(struct page *page) { return false; }
+static inline bool set_page_guard(struct zone *zone, struct page *page,
+			unsigned int order, int migratetype) { return false; }
+static inline void clear_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype) {}
 #endif	/* CONFIG_DEBUG_PAGEALLOC */
 
 #ifdef __HAVE_ARCH_GATE_AREA
@@ -3609,6 +3673,10 @@ extern void shake_page(struct page *p);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
 #ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Sysfs entries for memory failure handling statistics.
+ */
+extern const struct attribute_group memory_failure_attr_group;
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 					bool *migratable_cleared);
@@ -3701,11 +3769,6 @@ enum mf_action_page_type {
 	MF_MSG_UNKNOWN,
 };
 
-/*
- * Sysfs entries for memory failure handling statistics.
- */
-extern const struct attribute_group memory_failure_attr_group;
-
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
 extern void clear_huge_page(struct page *page,
 			    unsigned long addr_hint,
@@ -3735,33 +3798,6 @@ static inline bool vma_is_special_huge(const struct vm_area_struct *vma)
 
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-extern unsigned int _debug_guardpage_minorder;
-DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
-
-static inline unsigned int debug_guardpage_minorder(void)
-{
-	return _debug_guardpage_minorder;
-}
-
-static inline bool debug_guardpage_enabled(void)
-{
-	return static_branch_unlikely(&_debug_guardpage_enabled);
-}
-
-static inline bool page_is_guard(struct page *page)
-{
-	if (!debug_guardpage_enabled())
-		return false;
-
-	return PageGuard(page);
-}
-#else
-static inline unsigned int debug_guardpage_minorder(void) { return 0; }
-static inline bool debug_guardpage_enabled(void) { return false; }
-static inline bool page_is_guard(struct page *page) { return false; }
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
 #if MAX_NUMNODES > 1
 void __init setup_nr_node_ids(void);
 #else