Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

1 files changed, 33 insertions, 27 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 9ff51650f4f0..2baa93ca2310 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -59,6 +59,7 @@ static int madvise_need_mmap_write(int behavior)
 	case MADV_FREE:
 	case MADV_POPULATE_READ:
 	case MADV_POPULATE_WRITE:
+	case MADV_COLLAPSE:
 		return 0;
 	default:
 		/* be safe, default to 1. list exceptions explicitly */
@@ -600,6 +601,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	spinlock_t *ptl;
 	pte_t *orig_pte, *pte, ptent;
+	struct folio *folio;
 	struct page *page;
 	int nr_swap = 0;
 	unsigned long next;
@@ -644,56 +646,56 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page || is_zone_device_page(page))
 			continue;
+		folio = page_folio(page);
 
 		/*
-		 * If pmd isn't transhuge but the page is THP and
+		 * If pmd isn't transhuge but the folio is large and
 		 * is owned by only this process, split it and
 		 * deactivate all pages.
 		 */
-		if (PageTransCompound(page)) {
-			if (page_mapcount(page) != 1)
+		if (folio_test_large(folio)) {
+			if (folio_mapcount(folio) != 1)
 				goto out;
-			get_page(page);
-			if (!trylock_page(page)) {
-				put_page(page);
+			folio_get(folio);
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
 				goto out;
 			}
 			pte_unmap_unlock(orig_pte, ptl);
-			if (split_huge_page(page)) {
-				unlock_page(page);
-				put_page(page);
+			if (split_folio(folio)) {
+				folio_unlock(folio);
+				folio_put(folio);
 				orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 				goto out;
 			}
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
+			folio_put(folio);
 			orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 			pte--;
 			addr -= PAGE_SIZE;
 			continue;
 		}
 
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
-
-		if (PageSwapCache(page) || PageDirty(page)) {
-			if (!trylock_page(page))
+		if (folio_test_swapcache(folio) || folio_test_dirty(folio)) {
+			if (!folio_trylock(folio))
 				continue;
 			/*
-			 * If page is shared with others, we couldn't clear
-			 * PG_dirty of the page.
+			 * If folio is shared with others, we mustn't clear
+			 * the folio's dirty flag.
 			 */
-			if (page_mapcount(page) != 1) {
-				unlock_page(page);
+			if (folio_mapcount(folio) != 1) {
+				folio_unlock(folio);
 				continue;
 			}
 
-			if (PageSwapCache(page) && !try_to_free_swap(page)) {
-				unlock_page(page);
+			if (folio_test_swapcache(folio) &&
+			    !folio_free_swap(folio)) {
+				folio_unlock(folio);
 				continue;
 			}
 
-			ClearPageDirty(page);
-			unlock_page(page);
+			folio_clear_dirty(folio);
+			folio_unlock(folio);
 		}
 
 		if (pte_young(ptent) || pte_dirty(ptent)) {
@@ -711,7 +713,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 			set_pte_at(mm, addr, pte, ptent);
 			tlb_remove_tlb_entry(tlb, pte, addr);
 		}
-		mark_page_lazyfree(page);
+		mark_page_lazyfree(&folio->page);
 	}
 out:
 	if (nr_swap) {
@@ -1060,6 +1062,8 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 		if (error)
 			goto out;
 		break;
+	case MADV_COLLAPSE:
+		return madvise_collapse(vma, prev, start, end);
 	}
 
 	anon_name = anon_vma_name(vma);
@@ -1153,6 +1157,7 @@ madvise_behavior_valid(int behavior)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	case MADV_HUGEPAGE:
 	case MADV_NOHUGEPAGE:
+	case MADV_COLLAPSE:
 #endif
 	case MADV_DONTDUMP:
 	case MADV_DODUMP:
@@ -1169,13 +1174,13 @@ madvise_behavior_valid(int behavior)
 	}
 }
 
-static bool
-process_madvise_behavior_valid(int behavior)
+static bool process_madvise_behavior_valid(int behavior)
 {
 	switch (behavior) {
 	case MADV_COLD:
 	case MADV_PAGEOUT:
 	case MADV_WILLNEED:
+	case MADV_COLLAPSE:
 		return true;
 	default:
 		return false;
@@ -1241,7 +1246,7 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start,
 		if (start >= end)
 			break;
 		if (prev)
-			vma = prev->vm_next;
+			vma = find_vma(mm, prev->vm_end);
 		else	/* madvise_remove dropped mmap_lock */
 			vma = find_vma(mm, start);
 	}
@@ -1342,6 +1347,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
  *  MADV_NOHUGEPAGE - mark the given range as not worth being backed by
  *		transparent huge pages so the existing pages will not be
  *		coalesced into THP and new pages will not be allocated as THP.
+ *  MADV_COLLAPSE - synchronously coalesce pages into new THP.
  *  MADV_DONTDUMP - the application wants to prevent pages in the given range
  *		from being included in its core dump.
  *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.