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, 48 insertions, 39 deletions

diff --git a/mm/internal.h b/mm/internal.h
index e6029d94bdb2..a7d9e980429a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -133,8 +133,8 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
 bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
 		loff_t end);
 long invalidate_inode_page(struct page *page);
-unsigned long invalidate_mapping_pagevec(struct address_space *mapping,
-		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec);
+unsigned long mapping_try_invalidate(struct address_space *mapping,
+		pgoff_t start, pgoff_t end, unsigned long *nr_failed);
 
 /**
  * folio_evictable - Test whether a folio is evictable.
@@ -202,10 +202,12 @@ extern char * const zone_names[MAX_NR_ZONES];
 /* perform sanity checks on struct pages being allocated or freed */
 DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
 
-static inline bool is_check_pages_enabled(void)
-{
-	return static_branch_unlikely(&check_pages_enabled);
-}
+extern int min_free_kbytes;
+
+void setup_per_zone_wmarks(void);
+void calculate_min_free_kbytes(void);
+int __meminit init_per_zone_wmark_min(void);
+void page_alloc_sysctl_init(void);
 
 /*
  * Structure for holding the mostly immutable allocation parameters passed
@@ -365,6 +367,13 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
 	return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
 }
 
+void set_zone_contiguous(struct zone *zone);
+
+static inline void clear_zone_contiguous(struct zone *zone)
+{
+	zone->contiguous = false;
+}
+
 extern int __isolate_free_page(struct page *page, unsigned int order);
 extern void __putback_isolated_page(struct page *page, unsigned int order,
 				    int mt);
@@ -372,12 +381,27 @@ extern void memblock_free_pages(struct page *page, unsigned long pfn,
 					unsigned int order);
 extern void __free_pages_core(struct page *page, unsigned int order);
 
+/*
+ * This will have no effect, other than possibly generating a warning, if the
+ * caller passes in a non-large folio.
+ */
+static inline void folio_set_order(struct folio *folio, unsigned int order)
+{
+	if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
+		return;
+
+	folio->_folio_order = order;
+#ifdef CONFIG_64BIT
+	folio->_folio_nr_pages = 1U << order;
+#endif
+}
+
 static inline void prep_compound_head(struct page *page, unsigned int order)
 {
 	struct folio *folio = (struct folio *)page;
 
-	set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
-	set_compound_order(page, order);
+	folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
+	folio_set_order(folio, order);
 	atomic_set(&folio->_entire_mapcount, -1);
 	atomic_set(&folio->_nr_pages_mapped, 0);
 	atomic_set(&folio->_pincount, 0);
@@ -410,27 +434,12 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
 			  phys_addr_t min_addr,
 			  int nid, bool exact_nid);
 
-int split_free_page(struct page *free_page,
-			unsigned int order, unsigned long split_pfn_offset);
+void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
+		unsigned long, enum meminit_context, struct vmem_altmap *, int);
 
-/*
- * This will have no effect, other than possibly generating a warning, if the
- * caller passes in a non-large folio.
- */
-static inline void folio_set_order(struct folio *folio, unsigned int order)
-{
-	if (WARN_ON_ONCE(!folio_test_large(folio)))
-		return;
 
-	folio->_folio_order = order;
-#ifdef CONFIG_64BIT
-	/*
-	 * When hugetlb dissolves a folio, we need to clear the tail
-	 * page, rather than setting nr_pages to 1.
-	 */
-	folio->_folio_nr_pages = order ? 1U << order : 0;
-#endif
-}
+int split_free_page(struct page *free_page,
+			unsigned int order, unsigned long split_pfn_offset);
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
@@ -557,8 +566,8 @@ extern long populate_vma_page_range(struct vm_area_struct *vma,
 extern long faultin_vma_page_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end,
 				   bool write, int *locked);
-extern int mlock_future_check(struct mm_struct *mm, unsigned long flags,
-			      unsigned long len);
+extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+			       unsigned long bytes);
 /*
  * mlock_vma_folio() and munlock_vma_folio():
  * should be called with vma's mmap_lock held for read or write,
@@ -1041,17 +1050,17 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 {
 
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
-	if (WARN_ON(vmi->mas.node != MAS_START && vmi->mas.index > vma->vm_start)) {
-		printk("%lu > %lu\n", vmi->mas.index, vma->vm_start);
-		printk("store of vma %lu-%lu", vma->vm_start, vma->vm_end);
-		printk("into slot    %lu-%lu", vmi->mas.index, vmi->mas.last);
-		mt_dump(vmi->mas.tree);
+	if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+			vmi->mas.index > vma->vm_start)) {
+		pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n",
+			vmi->mas.index, vma->vm_start, vma->vm_start,
+			vma->vm_end, vmi->mas.index, vmi->mas.last);
 	}
-	if (WARN_ON(vmi->mas.node != MAS_START && vmi->mas.last <  vma->vm_start)) {
-		printk("%lu < %lu\n", vmi->mas.last, vma->vm_start);
-		printk("store of vma %lu-%lu", vma->vm_start, vma->vm_end);
-		printk("into slot    %lu-%lu", vmi->mas.index, vmi->mas.last);
-		mt_dump(vmi->mas.tree);
+	if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+			vmi->mas.last <  vma->vm_start)) {
+		pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n",
+		       vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end,
+		       vmi->mas.index, vmi->mas.last);
 	}
 #endif