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()
  ...

2 files changed, 43 insertions, 40 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 420510f6a545..507cd4e59d07 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -538,13 +538,14 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
 	bool migration = false, young = false, dirty = false;
+	pte_t ptent = ptep_get(pte);
 
-	if (pte_present(*pte)) {
-		page = vm_normal_page(vma, addr, *pte);
-		young = pte_young(*pte);
-		dirty = pte_dirty(*pte);
-	} else if (is_swap_pte(*pte)) {
-		swp_entry_t swpent = pte_to_swp_entry(*pte);
+	if (pte_present(ptent)) {
+		page = vm_normal_page(vma, addr, ptent);
+		young = pte_young(ptent);
+		dirty = pte_dirty(ptent);
+	} else if (is_swap_pte(ptent)) {
+		swp_entry_t swpent = pte_to_swp_entry(ptent);
 
 		if (!non_swap_entry(swpent)) {
 			int mapcount;
@@ -631,14 +632,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		goto out;
 	}
 
-	if (pmd_trans_unstable(pmd))
-		goto out;
-	/*
-	 * The mmap_lock held all the way back in m_start() is what
-	 * keeps khugepaged out of here and from collapsing things
-	 * in here.
-	 */
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (; addr != end; pte++, addr += PAGE_SIZE)
 		smaps_pte_entry(pte, addr, walk);
 	pte_unmap_unlock(pte - 1, ptl);
@@ -735,11 +733,12 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = walk->vma;
 	struct page *page = NULL;
+	pte_t ptent = ptep_get(pte);
 
-	if (pte_present(*pte)) {
-		page = vm_normal_page(vma, addr, *pte);
-	} else if (is_swap_pte(*pte)) {
-		swp_entry_t swpent = pte_to_swp_entry(*pte);
+	if (pte_present(ptent)) {
+		page = vm_normal_page(vma, addr, ptent);
+	} else if (is_swap_pte(ptent)) {
+		swp_entry_t swpent = pte_to_swp_entry(ptent);
 
 		if (is_pfn_swap_entry(swpent))
 			page = pfn_swap_entry_to_page(swpent);
@@ -1108,7 +1107,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	 * Documentation/admin-guide/mm/soft-dirty.rst for full description
 	 * of how soft-dirty works.
 	 */
-	pte_t ptent = *pte;
+	pte_t ptent = ptep_get(pte);
 
 	if (pte_present(ptent)) {
 		pte_t old_pte;
@@ -1191,12 +1190,13 @@ out:
 		return 0;
 	}
 
-	if (pmd_trans_unstable(pmd))
-		return 0;
-
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
-		ptent = *pte;
+		ptent = ptep_get(pte);
 
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty(vma, addr, pte);
@@ -1538,9 +1538,6 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		spin_unlock(ptl);
 		return err;
 	}
-
-	if (pmd_trans_unstable(pmdp))
-		return 0;
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 	/*
@@ -1548,10 +1545,14 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 	 * goes beyond vma->vm_end.
 	 */
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return err;
+	}
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		pagemap_entry_t pme;
 
-		pme = pte_to_pagemap_entry(pm, vma, addr, *pte);
+		pme = pte_to_pagemap_entry(pm, vma, addr, ptep_get(pte));
 		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			break;
@@ -1689,23 +1690,23 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	/* watch out for wraparound */
 	start_vaddr = end_vaddr;
 	if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) {
+		unsigned long end;
+
 		ret = mmap_read_lock_killable(mm);
 		if (ret)
 			goto out_free;
 		start_vaddr = untagged_addr_remote(mm, svpfn << PAGE_SHIFT);
 		mmap_read_unlock(mm);
+
+		end = start_vaddr + ((count / PM_ENTRY_BYTES) << PAGE_SHIFT);
+		if (end >= start_vaddr && end < mm->task_size)
+			end_vaddr = end;
 	}
 
 	/* Ensure the address is inside the task */
 	if (start_vaddr > mm->task_size)
 		start_vaddr = end_vaddr;
 
-	/*
-	 * The odds are that this will stop walking way
-	 * before end_vaddr, because the length of the
-	 * user buffer is tracked in "pm", and the walk
-	 * will stop when we hit the end of the buffer.
-	 */
 	ret = 0;
 	while (count && (start_vaddr < end_vaddr)) {
 		int len;
@@ -1887,16 +1888,18 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		spin_unlock(ptl);
 		return 0;
 	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
 #endif
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	do {
-		struct page *page = can_gather_numa_stats(*pte, vma, addr);
+		pte_t ptent = ptep_get(pte);
+		struct page *page = can_gather_numa_stats(ptent, vma, addr);
 		if (!page)
 			continue;
-		gather_stats(page, md, pte_dirty(*pte), 1);
+		gather_stats(page, md, pte_dirty(ptent), 1);
 
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap_unlock(orig_pte, ptl);
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 0ec35072a8e5..2c8b62265981 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -51,7 +51,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		sbytes += kobjsize(mm);
 	else
 		bytes += kobjsize(mm);
-	
+
 	if (current->fs && current->fs->users > 1)
 		sbytes += kobjsize(current->fs);
 	else
@@ -69,13 +69,13 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 
 	bytes += kobjsize(current); /* includes kernel stack */
 
+	mmap_read_unlock(mm);
+
 	seq_printf(m,
 		"Mem:\t%8lu bytes\n"
 		"Slack:\t%8lu bytes\n"
 		"Shared:\t%8lu bytes\n",
 		bytes, slack, sbytes);
-
-	mmap_read_unlock(mm);
 }
 
 unsigned long task_vsize(struct mm_struct *mm)