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, 106 insertions, 78 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 93d5a6f793d20..2ec925e5fa6a9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -23,10 +23,9 @@
  * inode->i_rwsem	(while writing or truncating, not reading or faulting)
  *   mm->mmap_lock
  *     mapping->invalidate_lock (in filemap_fault)
- *       page->flags PG_locked (lock_page)   * (see hugetlbfs below)
- *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
+ *       page->flags PG_locked (lock_page)
+ *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below)
  *           mapping->i_mmap_rwsem
- *             hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
  *             anon_vma->rwsem
  *               mm->page_table_lock or pte_lock
  *                 swap_lock (in swap_duplicate, swap_info_get)
@@ -46,10 +45,11 @@
  *   ->tasklist_lock
  *     pte map lock
  *
- * * hugetlbfs PageHuge() pages take locks in this order:
- *         mapping->i_mmap_rwsem
- *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
- *             page->flags PG_locked (lock_page)
+ * hugetlbfs PageHuge() take locks in this order:
+ *   hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
+ *     vma_lock (hugetlb specific lock for pmd_sharing)
+ *       mapping->i_mmap_rwsem (also used for hugetlb pmd sharing)
+ *         page->flags PG_locked (lock_page)
  */
 
 #include <linux/mm.h>
@@ -489,16 +489,16 @@ void __init anon_vma_init(void)
  * if there is a mapcount, we can dereference the anon_vma after observing
  * those.
  */
-struct anon_vma *page_get_anon_vma(struct page *page)
+struct anon_vma *folio_get_anon_vma(struct folio *folio)
 {
 	struct anon_vma *anon_vma = NULL;
 	unsigned long anon_mapping;
 
 	rcu_read_lock();
-	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
+	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
 	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
 		goto out;
-	if (!page_mapped(page))
+	if (!folio_mapped(folio))
 		goto out;
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
@@ -508,13 +508,13 @@ struct anon_vma *page_get_anon_vma(struct page *page)
 	}
 
 	/*
-	 * If this page is still mapped, then its anon_vma cannot have been
+	 * If this folio is still mapped, then its anon_vma cannot have been
 	 * freed.  But if it has been unmapped, we have no security against the
 	 * anon_vma structure being freed and reused (for another anon_vma:
 	 * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero()
 	 * above cannot corrupt).
 	 */
-	if (!page_mapped(page)) {
+	if (!folio_mapped(folio)) {
 		rcu_read_unlock();
 		put_anon_vma(anon_vma);
 		return NULL;
@@ -526,11 +526,11 @@ out:
 }
 
 /*
- * Similar to page_get_anon_vma() except it locks the anon_vma.
+ * Similar to folio_get_anon_vma() except it locks the anon_vma.
  *
  * Its a little more complex as it tries to keep the fast path to a single
  * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
- * reference like with page_get_anon_vma() and then block on the mutex
+ * reference like with folio_get_anon_vma() and then block on the mutex
  * on !rwc->try_lock case.
  */
 struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
@@ -602,11 +602,6 @@ out:
 	return anon_vma;
 }
 
-void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
-{
-	anon_vma_unlock_read(anon_vma);
-}
-
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
@@ -770,13 +765,17 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 	return vma_address(page, vma);
 }
 
+/*
+ * Returns the actual pmd_t* where we expect 'address' to be mapped from, or
+ * NULL if it doesn't exist.  No guarantees / checks on what the pmd_t*
+ * represents.
+ */
 pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd = NULL;
-	pmd_t pmde;
 
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
@@ -791,15 +790,6 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 		goto out;
 
 	pmd = pmd_offset(pud, address);
-	/*
-	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
-	 * without holding anon_vma lock for write.  So when looking for a
-	 * genuine pmde (in which to find pte), test present and !THP together.
-	 */
-	pmde = *pmd;
-	barrier();
-	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
-		pmd = NULL;
 out:
 	return pmd;
 }
@@ -833,6 +823,12 @@ static bool folio_referenced_one(struct folio *folio,
 		}
 
 		if (pvmw.pte) {
+			if (lru_gen_enabled() && pte_young(*pvmw.pte) &&
+			    !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))) {
+				lru_gen_look_around(&pvmw);
+				referenced++;
+			}
+
 			if (ptep_clear_flush_young_notify(vma, address,
 						pvmw.pte)) {
 				/*
@@ -1101,22 +1097,20 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
  */
 void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
 {
-	struct anon_vma *anon_vma = vma->anon_vma;
-	struct page *subpage = page;
-
-	page = compound_head(page);
+	void *anon_vma = vma->anon_vma;
+	struct folio *folio = page_folio(page);
 
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_VMA(!anon_vma, vma);
 
-	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+	anon_vma += PAGE_MAPPING_ANON;
 	/*
 	 * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written
 	 * simultaneously, so a concurrent reader (eg folio_referenced()'s
 	 * folio_test_anon()) will not see one without the other.
 	 */
-	WRITE_ONCE(page->mapping, (struct address_space *) anon_vma);
-	SetPageAnonExclusive(subpage);
+	WRITE_ONCE(folio->mapping, anon_vma);
+	SetPageAnonExclusive(page);
 }
 
 /**
@@ -1560,33 +1554,45 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			 * To call huge_pmd_unshare, i_mmap_rwsem must be
 			 * held in write mode.  Caller needs to explicitly
 			 * do this outside rmap routines.
+			 *
+			 * We also must hold hugetlb vma_lock in write mode.
+			 * Lock order dictates acquiring vma_lock BEFORE
+			 * i_mmap_rwsem.  We can only try lock here and fail
+			 * if unsuccessful.
 			 */
-			VM_BUG_ON(!anon && !(flags & TTU_RMAP_LOCKED));
-			if (!anon && huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
-				flush_tlb_range(vma, range.start, range.end);
-				mmu_notifier_invalidate_range(mm, range.start,
-							      range.end);
-
-				/*
-				 * The ref count of the PMD page was dropped
-				 * which is part of the way map counting
-				 * is done for shared PMDs.  Return 'true'
-				 * here.  When there is no other sharing,
-				 * huge_pmd_unshare returns false and we will
-				 * unmap the actual page and drop map count
-				 * to zero.
-				 */
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+			if (!anon) {
+				VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+				if (!hugetlb_vma_trylock_write(vma)) {
+					page_vma_mapped_walk_done(&pvmw);
+					ret = false;
+					break;
+				}
+				if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
+					hugetlb_vma_unlock_write(vma);
+					flush_tlb_range(vma,
+						range.start, range.end);
+					mmu_notifier_invalidate_range(mm,
+						range.start, range.end);
+					/*
+					 * The ref count of the PMD page was
+					 * dropped which is part of the way map
+					 * counting is done for shared PMDs.
+					 * Return 'true' here.  When there is
+					 * no other sharing, huge_pmd_unshare
+					 * returns false and we will unmap the
+					 * actual page and drop map count
+					 * to zero.
+					 */
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
+				hugetlb_vma_unlock_write(vma);
 			}
 			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
 		} else {
 			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
-			/*
-			 * Nuke the page table entry. When having to clear
-			 * PageAnonExclusive(), we always have to flush.
-			 */
-			if (should_defer_flush(mm, flags) && !anon_exclusive) {
+			/* Nuke the page table entry. */
+			if (should_defer_flush(mm, flags)) {
 				/*
 				 * We clear the PTE but do not flush so potentially
 				 * a remote CPU could still be writing to the folio.
@@ -1717,6 +1723,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
+
+			/* See page_try_share_anon_rmap(): clear PTE first. */
 			if (anon_exclusive &&
 			    page_try_share_anon_rmap(subpage)) {
 				swap_free(entry);
@@ -1936,26 +1944,41 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 * To call huge_pmd_unshare, i_mmap_rwsem must be
 			 * held in write mode.  Caller needs to explicitly
 			 * do this outside rmap routines.
+			 *
+			 * We also must hold hugetlb vma_lock in write mode.
+			 * Lock order dictates acquiring vma_lock BEFORE
+			 * i_mmap_rwsem.  We can only try lock here and
+			 * fail if unsuccessful.
 			 */
-			VM_BUG_ON(!anon && !(flags & TTU_RMAP_LOCKED));
-			if (!anon && huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
-				flush_tlb_range(vma, range.start, range.end);
-				mmu_notifier_invalidate_range(mm, range.start,
-							      range.end);
-
-				/*
-				 * The ref count of the PMD page was dropped
-				 * which is part of the way map counting
-				 * is done for shared PMDs.  Return 'true'
-				 * here.  When there is no other sharing,
-				 * huge_pmd_unshare returns false and we will
-				 * unmap the actual page and drop map count
-				 * to zero.
-				 */
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+			if (!anon) {
+				VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+				if (!hugetlb_vma_trylock_write(vma)) {
+					page_vma_mapped_walk_done(&pvmw);
+					ret = false;
+					break;
+				}
+				if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
+					hugetlb_vma_unlock_write(vma);
+					flush_tlb_range(vma,
+						range.start, range.end);
+					mmu_notifier_invalidate_range(mm,
+						range.start, range.end);
+
+					/*
+					 * The ref count of the PMD page was
+					 * dropped which is part of the way map
+					 * counting is done for shared PMDs.
+					 * Return 'true' here.  When there is
+					 * no other sharing, huge_pmd_unshare
+					 * returns false and we will unmap the
+					 * actual page and drop map count
+					 * to zero.
+					 */
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
+				hugetlb_vma_unlock_write(vma);
 			}
-
 			/* Nuke the hugetlb page table entry */
 			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
 		} else {
@@ -2048,6 +2071,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			}
 			VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) &&
 				       !anon_exclusive, subpage);
+
+			/* See page_try_share_anon_rmap(): clear PTE first. */
 			if (anon_exclusive &&
 			    page_try_share_anon_rmap(subpage)) {
 				if (folio_test_hugetlb(folio))
@@ -2073,7 +2098,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			else
 				entry = make_readable_migration_entry(
 							page_to_pfn(subpage));
-
+			if (pte_young(pteval))
+				entry = make_migration_entry_young(entry);
+			if (pte_dirty(pteval))
+				entry = make_migration_entry_dirty(entry);
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);