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, 46 insertions, 63 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6bc83060df9a..8e6dde68b389 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -41,6 +41,7 @@
 #include <linux/swap_slots.h>
 #include <linux/sort.h>
 #include <linux/completion.h>
+#include <linux/suspend.h>
 
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
@@ -1219,6 +1220,13 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
 }
 
 /*
+ * When we get a swap entry, if there aren't some other ways to
+ * prevent swapoff, such as the folio in swap cache is locked, page
+ * table lock is held, etc., the swap entry may become invalid because
+ * of swapoff.  Then, we need to enclose all swap related functions
+ * with get_swap_device() and put_swap_device(), unless the swap
+ * functions call get/put_swap_device() by themselves.
+ *
  * Check whether swap entry is valid in the swap device.  If so,
  * return pointer to swap_info_struct, and keep the swap entry valid
  * via preventing the swap device from being swapoff, until
@@ -1227,9 +1235,8 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
  * Notice that swapoff or swapoff+swapon can still happen before the
  * percpu_ref_tryget_live() in get_swap_device() or after the
  * percpu_ref_put() in put_swap_device() if there isn't any other way
- * to prevent swapoff, such as page lock, page table lock, etc.  The
- * caller must be prepared for that.  For example, the following
- * situation is possible.
+ * to prevent swapoff.  The caller must be prepared for that.  For
+ * example, the following situation is possible.
  *
  *   CPU1				CPU2
  *   do_swap_page()
@@ -1432,16 +1439,10 @@ void swapcache_free_entries(swp_entry_t *entries, int n)
 
 int __swap_count(swp_entry_t entry)
 {
-	struct swap_info_struct *si;
+	struct swap_info_struct *si = swp_swap_info(entry);
 	pgoff_t offset = swp_offset(entry);
-	int count = 0;
 
-	si = get_swap_device(entry);
-	if (si) {
-		count = swap_count(si->swap_map[offset]);
-		put_swap_device(si);
-	}
-	return count;
+	return swap_count(si->swap_map[offset]);
 }
 
 /*
@@ -1449,7 +1450,7 @@ int __swap_count(swp_entry_t entry)
  * This does not give an exact answer when swap count is continued,
  * but does include the high COUNT_CONTINUED flag to allow for that.
  */
-static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
+int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
 {
 	pgoff_t offset = swp_offset(entry);
 	struct swap_cluster_info *ci;
@@ -1463,24 +1464,6 @@ static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
 
 /*
  * How many references to @entry are currently swapped out?
- * This does not give an exact answer when swap count is continued,
- * but does include the high COUNT_CONTINUED flag to allow for that.
- */
-int __swp_swapcount(swp_entry_t entry)
-{
-	int count = 0;
-	struct swap_info_struct *si;
-
-	si = get_swap_device(entry);
-	if (si) {
-		count = swap_swapcount(si, entry);
-		put_swap_device(si);
-	}
-	return count;
-}
-
-/*
- * How many references to @entry are currently swapped out?
  * This considers COUNT_CONTINUED so it returns exact answer.
  */
 int swp_swapcount(swp_entry_t entry)
@@ -1762,7 +1745,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *page = folio_file_page(folio, swp_offset(entry));
 	struct page *swapcache;
 	spinlock_t *ptl;
-	pte_t *pte, new_pte;
+	pte_t *pte, new_pte, old_pte;
 	bool hwposioned = false;
 	int ret = 1;
 
@@ -1774,11 +1757,14 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		hwposioned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
+	if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
+						swp_entry_to_pte(entry)))) {
 		ret = 0;
 		goto out;
 	}
 
+	old_pte = ptep_get(pte);
+
 	if (unlikely(hwposioned || !PageUptodate(page))) {
 		swp_entry_t swp_entry;
 
@@ -1810,7 +1796,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		 * call and have the page locked.
 		 */
 		VM_BUG_ON_PAGE(PageWriteback(page), page);
-		if (pte_swp_exclusive(*pte))
+		if (pte_swp_exclusive(old_pte))
 			rmap_flags |= RMAP_EXCLUSIVE;
 
 		page_add_anon_rmap(page, vma, addr, rmap_flags);
@@ -1819,15 +1805,16 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	}
 	new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot));
-	if (pte_swp_soft_dirty(*pte))
+	if (pte_swp_soft_dirty(old_pte))
 		new_pte = pte_mksoft_dirty(new_pte);
-	if (pte_swp_uffd_wp(*pte))
+	if (pte_swp_uffd_wp(old_pte))
 		new_pte = pte_mkuffd_wp(new_pte);
 setpte:
 	set_pte_at(vma->vm_mm, addr, pte, new_pte);
 	swap_free(entry);
 out:
-	pte_unmap_unlock(pte, ptl);
+	if (pte)
+		pte_unmap_unlock(pte, ptl);
 	if (page != swapcache) {
 		unlock_page(page);
 		put_page(page);
@@ -1839,27 +1826,37 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned int type)
 {
-	swp_entry_t entry;
-	pte_t *pte;
+	pte_t *pte = NULL;
 	struct swap_info_struct *si;
-	int ret = 0;
 
 	si = swap_info[type];
-	pte = pte_offset_map(pmd, addr);
 	do {
 		struct folio *folio;
 		unsigned long offset;
 		unsigned char swp_count;
+		swp_entry_t entry;
+		int ret;
+		pte_t ptent;
+
+		if (!pte++) {
+			pte = pte_offset_map(pmd, addr);
+			if (!pte)
+				break;
+		}
+
+		ptent = ptep_get_lockless(pte);
 
-		if (!is_swap_pte(*pte))
+		if (!is_swap_pte(ptent))
 			continue;
 
-		entry = pte_to_swp_entry(*pte);
+		entry = pte_to_swp_entry(ptent);
 		if (swp_type(entry) != type)
 			continue;
 
 		offset = swp_offset(entry);
 		pte_unmap(pte);
+		pte = NULL;
+
 		folio = swap_cache_get_folio(entry, vma, addr);
 		if (!folio) {
 			struct page *page;
@@ -1878,8 +1875,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		if (!folio) {
 			swp_count = READ_ONCE(si->swap_map[offset]);
 			if (swp_count == 0 || swp_count == SWAP_MAP_BAD)
-				goto try_next;
-
+				continue;
 			return -ENOMEM;
 		}
 
@@ -1889,20 +1885,17 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		if (ret < 0) {
 			folio_unlock(folio);
 			folio_put(folio);
-			goto out;
+			return ret;
 		}
 
 		folio_free_swap(folio);
 		folio_unlock(folio);
 		folio_put(folio);
-try_next:
-		pte = pte_offset_map(pmd, addr);
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
+	} while (addr += PAGE_SIZE, addr != end);
 
-	ret = 0;
-out:
-	return ret;
+	if (pte)
+		pte_unmap(pte);
+	return 0;
 }
 
 static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -1917,8 +1910,6 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	do {
 		cond_resched();
 		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
-			continue;
 		ret = unuse_pte_range(vma, pmd, addr, next, type);
 		if (ret)
 			return ret;
@@ -3288,9 +3279,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 	unsigned char has_cache;
 	int err;
 
-	p = get_swap_device(entry);
-	if (!p)
-		return -EINVAL;
+	p = swp_swap_info(entry);
 
 	offset = swp_offset(entry);
 	ci = lock_cluster_or_swap_info(p, offset);
@@ -3337,7 +3326,6 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 
 unlock_out:
 	unlock_cluster_or_swap_info(p, ci);
-	put_swap_device(p);
 	return err;
 }
 
@@ -3468,11 +3456,6 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 		goto out;
 	}
 
-	/*
-	 * We are fortunate that although vmalloc_to_page uses pte_offset_map,
-	 * no architecture is using highmem pages for kernel page tables: so it
-	 * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps.
-	 */
 	head = vmalloc_to_page(si->swap_map + offset);
 	offset &= ~PAGE_MASK;