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, 13 insertions, 33 deletions

diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index d30c9de60b0d..8365158460ed 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -83,9 +83,6 @@ again:
 		if (is_huge_zero_page(page)) {
 			spin_unlock(ptl);
 			split_huge_pmd(vma, pmdp, addr);
-			if (pmd_trans_unstable(pmdp))
-				return migrate_vma_collect_skip(start, end,
-								walk);
 		} else {
 			int ret;
 
@@ -100,16 +97,12 @@ again:
 			if (ret)
 				return migrate_vma_collect_skip(start, end,
 								walk);
-			if (pmd_none(*pmdp))
-				return migrate_vma_collect_hole(start, end, -1,
-								walk);
 		}
 	}
 
-	if (unlikely(pmd_bad(*pmdp)))
-		return migrate_vma_collect_skip(start, end, walk);
-
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	arch_enter_lazy_mmu_mode();
 
 	for (; addr < end; addr += PAGE_SIZE, ptep++) {
@@ -118,7 +111,7 @@ again:
 		swp_entry_t entry;
 		pte_t pte;
 
-		pte = *ptep;
+		pte = ptep_get(ptep);
 
 		if (pte_none(pte)) {
 			if (vma_is_anonymous(vma)) {
@@ -201,7 +194,7 @@ again:
 			bool anon_exclusive;
 			pte_t swp_pte;
 
-			flush_cache_page(vma, addr, pte_pfn(*ptep));
+			flush_cache_page(vma, addr, pte_pfn(pte));
 			anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
 			if (anon_exclusive) {
 				pte = ptep_clear_flush(vma, addr, ptep);
@@ -383,7 +376,7 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns,
 		/* ZONE_DEVICE pages are not on LRU */
 		if (!is_zone_device_page(page)) {
 			if (!PageLRU(page) && allow_drain) {
-				/* Drain CPU's pagevec */
+				/* Drain CPU's lru cache */
 				lru_add_drain_all();
 				allow_drain = false;
 			}
@@ -580,6 +573,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
+	pte_t orig_pte;
 
 	/* Only allow populating anonymous memory */
 	if (!vma_is_anonymous(vma))
@@ -595,27 +589,10 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	pmdp = pmd_alloc(mm, pudp, addr);
 	if (!pmdp)
 		goto abort;
-
 	if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp))
 		goto abort;
-
-	/*
-	 * Use pte_alloc() instead of pte_alloc_map().  We can't run
-	 * pte_offset_map() on pmds where a huge pmd might be created
-	 * from a different thread.
-	 *
-	 * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
-	 * parallel threads are excluded by other means.
-	 *
-	 * Here we only have mmap_read_lock(mm).
-	 */
 	if (pte_alloc(mm, pmdp))
 		goto abort;
-
-	/* See the comment in pte_alloc_one_map() */
-	if (unlikely(pmd_trans_unstable(pmdp)))
-		goto abort;
-
 	if (unlikely(anon_vma_prepare(vma)))
 		goto abort;
 	if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
@@ -650,17 +627,20 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	}
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto abort;
+	orig_pte = ptep_get(ptep);
 
 	if (check_stable_address_space(mm))
 		goto unlock_abort;
 
-	if (pte_present(*ptep)) {
-		unsigned long pfn = pte_pfn(*ptep);
+	if (pte_present(orig_pte)) {
+		unsigned long pfn = pte_pfn(orig_pte);
 
 		if (!is_zero_pfn(pfn))
 			goto unlock_abort;
 		flush = true;
-	} else if (!pte_none(*ptep))
+	} else if (!pte_none(orig_pte))
 		goto unlock_abort;
 
 	/*
@@ -677,7 +657,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	get_page(page);
 
 	if (flush) {
-		flush_cache_page(vma, addr, pte_pfn(*ptep));
+		flush_cache_page(vma, addr, pte_pfn(orig_pte));
 		ptep_clear_flush_notify(vma, addr, ptep);
 		set_pte_at_notify(mm, addr, ptep, entry);
 		update_mmu_cache(vma, addr, ptep);