Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

1 files changed, 97 insertions, 72 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aa39534898e0..f044962ad9df 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -66,12 +66,6 @@ static bool hugetlb_cma_page(struct page *page, unsigned int order)
 #endif
 static unsigned long hugetlb_cma_size __initdata;
 
-/*
- * Minimum page order among possible hugepage sizes, set to a proper value
- * at boot time.
- */
-static unsigned int minimum_order __read_mostly = UINT_MAX;
-
 __initdata LIST_HEAD(huge_boot_pages);
 
 /* for command line parsing */
@@ -1135,7 +1129,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 
 	lockdep_assert_held(&hugetlb_lock);
 	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
-		if (pin && !is_pinnable_page(page))
+		if (pin && !is_longterm_pinnable_page(page))
 			continue;
 
 		if (PageHWPoison(page))
@@ -2152,11 +2146,17 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	unsigned long pfn;
 	struct page *page;
 	int rc = 0;
+	unsigned int order;
+	struct hstate *h;
 
 	if (!hugepages_supported())
 		return rc;
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
+	order = huge_page_order(&default_hstate);
+	for_each_hstate(h)
+		order = min(order, huge_page_order(h));
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) {
 		page = pfn_to_page(pfn);
 		rc = dissolve_free_huge_page(page);
 		if (rc)
@@ -2766,8 +2766,7 @@ retry:
 		 * Fail with -EBUSY if not possible.
 		 */
 		spin_unlock_irq(&hugetlb_lock);
-		if (!isolate_huge_page(old_page, list))
-			ret = -EBUSY;
+		ret = isolate_hugetlb(old_page, list);
 		spin_lock_irq(&hugetlb_lock);
 		goto free_new;
 	} else if (!HPageFreed(old_page)) {
@@ -2843,7 +2842,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
 	if (hstate_is_gigantic(h))
 		return -ENOMEM;
 
-	if (page_count(head) && isolate_huge_page(head, list))
+	if (page_count(head) && !isolate_hugetlb(head, list))
 		ret = 0;
 	else if (!page_count(head))
 		ret = alloc_and_dissolve_huge_page(h, head, list);
@@ -3149,9 +3148,6 @@ static void __init hugetlb_init_hstates(void)
 	struct hstate *h, *h2;
 
 	for_each_hstate(h) {
-		if (minimum_order > huge_page_order(h))
-			minimum_order = huge_page_order(h);
-
 		/* oversize hugepages were init'ed in early boot */
 		if (!hstate_is_gigantic(h))
 			hugetlb_hstate_alloc_pages(h);
@@ -3176,7 +3172,6 @@ static void __init hugetlb_init_hstates(void)
 				h->demote_order = h2->order;
 		}
 	}
-	VM_BUG_ON(minimum_order == UINT_MAX);
 }
 
 static void __init report_hugepages(void)
@@ -4482,22 +4477,20 @@ int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 			     nid, h->surplus_huge_pages_node[nid]);
 }
 
-void hugetlb_show_meminfo(void)
+void hugetlb_show_meminfo_node(int nid)
 {
 	struct hstate *h;
-	int nid;
 
 	if (!hugepages_supported())
 		return;
 
-	for_each_node_state(nid, N_MEMORY)
-		for_each_hstate(h)
-			pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
-				nid,
-				h->nr_huge_pages_node[nid],
-				h->free_huge_pages_node[nid],
-				h->surplus_huge_pages_node[nid],
-				huge_page_size(h) / SZ_1K);
+	for_each_hstate(h)
+		printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
+			nid,
+			h->nr_huge_pages_node[nid],
+			h->free_huge_pages_node[nid],
+			h->surplus_huge_pages_node[nid],
+			huge_page_size(h) / SZ_1K);
 }
 
 void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
@@ -4732,6 +4725,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	unsigned long npages = pages_per_huge_page(h);
 	struct address_space *mapping = src_vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
+	unsigned long last_addr_mask;
 	int ret = 0;
 
 	if (cow) {
@@ -4751,11 +4745,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		i_mmap_lock_read(mapping);
 	}
 
+	last_addr_mask = hugetlb_mask_last_page(h);
 	for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr, sz);
-		if (!src_pte)
+		if (!src_pte) {
+			addr |= last_addr_mask;
 			continue;
+		}
 		dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
@@ -4772,8 +4769,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		 * after taking the lock below.
 		 */
 		dst_entry = huge_ptep_get(dst_pte);
-		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) {
+			addr |= last_addr_mask;
 			continue;
+		}
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
@@ -4808,12 +4807,11 @@ again:
 				entry = swp_entry_to_pte(swp_entry);
 				if (userfaultfd_wp(src_vma) && uffd_wp)
 					entry = huge_pte_mkuffd_wp(entry);
-				set_huge_swap_pte_at(src, addr, src_pte,
-						     entry, sz);
+				set_huge_pte_at(src, addr, src_pte, entry);
 			}
 			if (!userfaultfd_wp(dst_vma) && uffd_wp)
 				entry = huge_pte_clear_uffd_wp(entry);
-			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
+			set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else if (unlikely(is_pte_marker(entry))) {
 			/*
 			 * We copy the pte marker only if the dst vma has
@@ -4880,7 +4878,7 @@ again:
 				 * table protection not changing it to point
 				 * to a new page.
 				 *
-				 * See Documentation/vm/mmu_notifier.rst
+				 * See Documentation/mm/mmu_notifier.rst
 				 */
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 				entry = huge_pte_wrprotect(entry);
@@ -4939,7 +4937,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	unsigned long sz = huge_page_size(h);
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long old_end = old_addr + len;
-	unsigned long old_addr_copy;
+	unsigned long last_addr_mask;
 	pte_t *src_pte, *dst_pte;
 	struct mmu_notifier_range range;
 	bool shared_pmd = false;
@@ -4954,23 +4952,23 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	flush_cache_range(vma, range.start, range.end);
 
 	mmu_notifier_invalidate_range_start(&range);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	/* Prevent race with file truncation */
 	i_mmap_lock_write(mapping);
 	for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
 		src_pte = huge_pte_offset(mm, old_addr, sz);
-		if (!src_pte)
+		if (!src_pte) {
+			old_addr |= last_addr_mask;
+			new_addr |= last_addr_mask;
 			continue;
+		}
 		if (huge_pte_none(huge_ptep_get(src_pte)))
 			continue;
 
-		/* old_addr arg to huge_pmd_unshare() is a pointer and so the
-		 * arg may be modified. Pass a copy instead to preserve the
-		 * value in old_addr.
-		 */
-		old_addr_copy = old_addr;
-
-		if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) {
+		if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) {
 			shared_pmd = true;
+			old_addr |= last_addr_mask;
+			new_addr |= last_addr_mask;
 			continue;
 		}
 
@@ -5004,6 +5002,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mmu_notifier_range range;
+	unsigned long last_addr_mask;
 	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
@@ -5024,17 +5023,21 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 				end);
 	adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
 	mmu_notifier_invalidate_range_start(&range);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	address = start;
 	for (; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address, sz);
-		if (!ptep)
+		if (!ptep) {
+			address |= last_addr_mask;
 			continue;
+		}
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, address, ptep)) {
 			spin_unlock(ptl);
 			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
 			force_flush = true;
+			address |= last_addr_mask;
 			continue;
 		}
 
@@ -5714,7 +5717,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait_huge(vma, mm, ptep);
+			migration_entry_wait_huge(vma, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
@@ -6052,8 +6055,6 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 	set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
-	(void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte,
-					dst_vma->vm_flags & VM_WRITE);
 	hugetlb_count_add(pages_per_huge_page(h), dst_mm);
 
 	/* No need to invalidate - it was non-present before */
@@ -6305,6 +6306,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	unsigned long pages = 0, psize = huge_page_size(h);
 	bool shared_pmd = false;
 	struct mmu_notifier_range range;
+	unsigned long last_addr_mask;
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
@@ -6321,14 +6323,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, range.start, range.end);
 
 	mmu_notifier_invalidate_range_start(&range);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (; address < end; address += psize) {
 		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address, psize);
-		if (!ptep)
+		if (!ptep) {
+			address |= last_addr_mask;
 			continue;
+		}
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, address, ptep)) {
 			/*
 			 * When uffd-wp is enabled on the vma, unshare
 			 * shouldn't happen at all.  Warn about it if it
@@ -6338,6 +6343,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			pages++;
 			spin_unlock(ptl);
 			shared_pmd = true;
+			address |= last_addr_mask;
 			continue;
 		}
 		pte = huge_ptep_get(ptep);
@@ -6363,8 +6369,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 					newpte = pte_swp_mkuffd_wp(newpte);
 				else if (uffd_wp_resolve)
 					newpte = pte_swp_clear_uffd_wp(newpte);
-				set_huge_swap_pte_at(mm, address, ptep,
-						     newpte, psize);
+				set_huge_pte_at(mm, address, ptep, newpte);
 				pages++;
 			}
 			spin_unlock(ptl);
@@ -6415,7 +6420,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * No need to call mmu_notifier_invalidate_range() we are downgrading
 	 * page table protection not changing it to point to a new page.
 	 *
-	 * See Documentation/vm/mmu_notifier.rst
+	 * See Documentation/mm/mmu_notifier.rst
 	 */
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	mmu_notifier_invalidate_range_end(&range);
@@ -6761,11 +6766,11 @@ out:
  *	    0 the underlying pte page is not shared, or it is the last user
  */
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
-					unsigned long *addr, pte_t *ptep)
+					unsigned long addr, pte_t *ptep)
 {
-	pgd_t *pgd = pgd_offset(mm, *addr);
-	p4d_t *p4d = p4d_offset(pgd, *addr);
-	pud_t *pud = pud_offset(p4d, *addr);
+	pgd_t *pgd = pgd_offset(mm, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 
 	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
@@ -6775,14 +6780,6 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 	pud_clear(pud);
 	put_page(virt_to_page(ptep));
 	mm_dec_nr_pmds(mm);
-	/*
-	 * This update of passed address optimizes loops sequentially
-	 * processing addresses in increments of huge page size (PMD_SIZE
-	 * in this case).  By clearing the pud, a PUD_SIZE area is unmapped.
-	 * Update address to the 'last page' in the cleared area so that
-	 * calling loop can move to first page past this area.
-	 */
-	*addr |= PUD_SIZE - PMD_SIZE;
 	return 1;
 }
 
@@ -6794,7 +6791,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
-				unsigned long *addr, pte_t *ptep)
+				unsigned long addr, pte_t *ptep)
 {
 	return 0;
 }
@@ -6877,6 +6874,37 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return (pte_t *)pmd;
 }
 
+/*
+ * Return a mask that can be used to update an address to the last huge
+ * page in a page table page mapping size.  Used to skip non-present
+ * page table entries when linearly scanning address ranges.  Architectures
+ * with unique huge page to page table relationships can define their own
+ * version of this routine.
+ */
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	if (hp_size == PUD_SIZE)
+		return P4D_SIZE - PUD_SIZE;
+	else if (hp_size == PMD_SIZE)
+		return PUD_SIZE - PMD_SIZE;
+	else
+		return 0UL;
+}
+
+#else
+
+/* See description above.  Architectures can provide their own version. */
+__weak unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+	if (huge_page_size(h) == PMD_SIZE)
+		return PUD_SIZE - PMD_SIZE;
+#endif
+	return 0UL;
+}
+
 #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 
 /*
@@ -6940,7 +6968,7 @@ retry:
 	} else {
 		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
-			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
+			__migration_entry_wait_huge((pte_t *)pmd, ptl);
 			goto retry;
 		}
 		/*
@@ -6972,15 +7000,15 @@ follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int fla
 	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
 }
 
-bool isolate_huge_page(struct page *page, struct list_head *list)
+int isolate_hugetlb(struct page *page, struct list_head *list)
 {
-	bool ret = true;
+	int ret = 0;
 
 	spin_lock_irq(&hugetlb_lock);
 	if (!PageHeadHuge(page) ||
 	    !HPageMigratable(page) ||
 	    !get_page_unless_zero(page)) {
-		ret = false;
+		ret = -EBUSY;
 		goto unlock;
 	}
 	ClearHPageMigratable(page);
@@ -7100,21 +7128,18 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	mmu_notifier_invalidate_range_start(&range);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (address = start; address < end; address += PUD_SIZE) {
-		unsigned long tmp = address;
-
 		ptep = huge_pte_offset(mm, address, sz);
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);
-		/* We don't want 'address' to be changed */
-		huge_pmd_unshare(mm, vma, &tmp, ptep);
+		huge_pmd_unshare(mm, vma, address, ptep);
 		spin_unlock(ptl);
 	}
 	flush_hugetlb_tlb_range(vma, start, end);
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	/*
 	 * No need to call mmu_notifier_invalidate_range(), see
-	 * Documentation/vm/mmu_notifier.rst.
+	 * Documentation/mm/mmu_notifier.rst.
 	 */
 	mmu_notifier_invalidate_range_end(&range);
 }