1 files changed, 81 insertions, 67 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6f8d46d107b4..a55fb1dcd224 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -19,6 +19,7 @@
 #include <linux/rcupdate_wait.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
+#include <linux/dax.h>
 #include <linux/ksm.h>
 
 #include <asm/tlb.h>
@@ -346,7 +347,7 @@ struct attribute_group khugepaged_attr_group = {
 #endif /* CONFIG_SYSFS */
 
 int hugepage_madvise(struct vm_area_struct *vma,
-		     unsigned long *vm_flags, int advice)
+		     vm_flags_t *vm_flags, int advice)
 {
 	switch (advice) {
 	case MADV_HUGEPAGE:
@@ -469,7 +470,7 @@ void __khugepaged_enter(struct mm_struct *mm)
 }
 
 void khugepaged_enter_vma(struct vm_area_struct *vma,
-			  unsigned long vm_flags)
+			  vm_flags_t vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
 	    hugepage_pmd_enabled()) {
@@ -547,19 +548,6 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte,
 	}
 }
 
-static bool is_refcount_suitable(struct folio *folio)
-{
-	int expected_refcount = folio_mapcount(folio);
-
-	if (!folio_test_anon(folio) || folio_test_swapcache(folio))
-		expected_refcount += folio_nr_pages(folio);
-
-	if (folio_test_private(folio))
-		expected_refcount++;
-
-	return folio_ref_count(folio) == expected_refcount;
-}
-
 static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long address,
 					pte_t *pte,
@@ -606,7 +594,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio);
 
 		/* See hpage_collapse_scan_pmd(). */
-		if (folio_likely_mapped_shared(folio)) {
+		if (folio_maybe_mapped_shared(folio)) {
 			++shared;
 			if (cc->is_khugepaged &&
 			    shared > khugepaged_max_ptes_shared) {
@@ -651,7 +639,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 * but not from this process. The other process cannot write to
 		 * the page, only trigger CoW.
 		 */
-		if (!is_refcount_suitable(folio)) {
+		if (folio_expected_ref_count(folio) != folio_ref_count(folio)) {
 			folio_unlock(folio);
 			result = SCAN_PAGE_COUNT;
 			goto out;
@@ -695,13 +683,13 @@ next:
 		result = SCAN_LACK_REFERENCED_PAGE;
 	} else {
 		result = SCAN_SUCCEED;
-		trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero,
+		trace_mm_collapse_huge_page_isolate(folio, none_or_zero,
 						    referenced, writable, result);
 		return result;
 	}
 out:
 	release_pte_pages(pte, _pte, compound_pagelist);
-	trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero,
+	trace_mm_collapse_huge_page_isolate(folio, none_or_zero,
 					    referenced, writable, result);
 	return result;
 }
@@ -745,7 +733,7 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 			ptep_clear(vma->vm_mm, address, _pte);
 			folio_remove_rmap_pte(src, src_page, vma);
 			spin_unlock(ptl);
-			free_page_and_swap_cache(src_page);
+			free_folio_and_swap_cache(src);
 		}
 	}
 
@@ -947,30 +935,40 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	return SCAN_SUCCEED;
 }
 
-static int find_pmd_or_thp_or_none(struct mm_struct *mm,
-				   unsigned long address,
-				   pmd_t **pmd)
+static inline int check_pmd_state(pmd_t *pmd)
 {
-	pmd_t pmde;
-
-	*pmd = mm_find_pmd(mm, address);
-	if (!*pmd)
-		return SCAN_PMD_NULL;
+	pmd_t pmde = pmdp_get_lockless(pmd);
 
-	pmde = pmdp_get_lockless(*pmd);
 	if (pmd_none(pmde))
 		return SCAN_PMD_NONE;
+
+	/*
+	 * The folio may be under migration when khugepaged is trying to
+	 * collapse it. Migration success or failure will eventually end
+	 * up with a present PMD mapping a folio again.
+	 */
+	if (is_pmd_migration_entry(pmde))
+		return SCAN_PMD_MAPPED;
 	if (!pmd_present(pmde))
 		return SCAN_PMD_NULL;
 	if (pmd_trans_huge(pmde))
 		return SCAN_PMD_MAPPED;
-	if (pmd_devmap(pmde))
-		return SCAN_PMD_NULL;
 	if (pmd_bad(pmde))
 		return SCAN_PMD_NULL;
 	return SCAN_SUCCEED;
 }
 
+static int find_pmd_or_thp_or_none(struct mm_struct *mm,
+				   unsigned long address,
+				   pmd_t **pmd)
+{
+	*pmd = mm_find_pmd(mm, address);
+	if (!*pmd)
+		return SCAN_PMD_NULL;
+
+	return check_pmd_state(*pmd);
+}
+
 static int check_pmd_still_valid(struct mm_struct *mm,
 				 unsigned long address,
 				 pmd_t *pmd)
@@ -1234,7 +1232,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	__folio_mark_uptodate(folio);
 	pgtable = pmd_pgtable(_pmd);
 
-	_pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot);
+	_pmd = folio_mk_pmd(folio, vma->vm_page_prot);
 	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
 
 	spin_lock(pmd_ptl);
@@ -1354,11 +1352,9 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 
 		/*
 		 * We treat a single page as shared if any part of the THP
-		 * is shared. "False negatives" from
-		 * folio_likely_mapped_shared() are not expected to matter
-		 * much in practice.
+		 * is shared.
 		 */
-		if (folio_likely_mapped_shared(folio)) {
+		if (folio_maybe_mapped_shared(folio)) {
 			++shared;
 			if (cc->is_khugepaged &&
 			    shared > khugepaged_max_ptes_shared) {
@@ -1399,7 +1395,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		 * has excessive GUP pins (i.e. 512).  Anyway the same check
 		 * will be done again later the risk seems low.
 		 */
-		if (!is_refcount_suitable(folio)) {
+		if (folio_expected_ref_count(folio) != folio_ref_count(folio)) {
 			result = SCAN_PAGE_COUNT;
 			goto out_unmap;
 		}
@@ -1432,7 +1428,7 @@ out_unmap:
 		*mmap_locked = false;
 	}
 out:
-	trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced,
+	trace_mm_khugepaged_scan_pmd(mm, folio, writable, referenced,
 				     none_or_zero, result, unmapped);
 	return result;
 }
@@ -1461,10 +1457,9 @@ static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot)
 	}
 }
 
-#ifdef CONFIG_SHMEM
-/* hpage must be locked, and mmap_lock must be held */
+/* folio must be locked, and mmap_lock must be held */
 static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
-			pmd_t *pmdp, struct page *hpage)
+			pmd_t *pmdp, struct folio *folio, struct page *page)
 {
 	struct vm_fault vmf = {
 		.vma = vma,
@@ -1473,13 +1468,12 @@ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
 		.pmd = pmdp,
 	};
 
-	VM_BUG_ON(!PageTransHuge(hpage));
 	mmap_assert_locked(vma->vm_mm);
 
-	if (do_set_pmd(&vmf, hpage))
+	if (do_set_pmd(&vmf, folio, page))
 		return SCAN_FAIL;
 
-	get_page(hpage);
+	folio_get(folio);
 	return SCAN_SUCCEED;
 }
 
@@ -1686,7 +1680,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 maybe_install_pmd:
 	/* step 5: install pmd entry */
 	result = install_pmd
-			? set_huge_pmd(vma, haddr, pmd, &folio->page)
+			? set_huge_pmd(vma, haddr, pmd, folio, &folio->page)
 			: SCAN_SUCCEED;
 	goto drop_folio;
 abort:
@@ -1720,7 +1714,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		pmd_t *pmd, pgt_pmd;
 		spinlock_t *pml;
 		spinlock_t *ptl;
-		bool skipped_uffd = false;
+		bool success = false;
 
 		/*
 		 * Check vma->anon_vma to exclude MAP_PRIVATE mappings that
@@ -1757,6 +1751,19 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		mmu_notifier_invalidate_range_start(&range);
 
 		pml = pmd_lock(mm, pmd);
+		/*
+		 * The lock of new_folio is still held, we will be blocked in
+		 * the page fault path, which prevents the pte entries from
+		 * being set again. So even though the old empty PTE page may be
+		 * concurrently freed and a new PTE page is filled into the pmd
+		 * entry, it is still empty and can be removed.
+		 *
+		 * So here we only need to recheck if the state of pmd entry
+		 * still meets our requirements, rather than checking pmd_same()
+		 * like elsewhere.
+		 */
+		if (check_pmd_state(pmd) != SCAN_SUCCEED)
+			goto drop_pml;
 		ptl = pte_lockptr(mm, pmd);
 		if (ptl != pml)
 			spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
@@ -1770,20 +1777,20 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * repeating the anon_vma check protects from one category,
 		 * and repeating the userfaultfd_wp() check from another.
 		 */
-		if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) {
-			skipped_uffd = true;
-		} else {
+		if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) {
 			pgt_pmd = pmdp_collapse_flush(vma, addr, pmd);
 			pmdp_get_lockless_sync();
+			success = true;
 		}
 
 		if (ptl != pml)
 			spin_unlock(ptl);
+drop_pml:
 		spin_unlock(pml);
 
 		mmu_notifier_invalidate_range_end(&range);
 
-		if (!skipped_uffd) {
+		if (success) {
 			mm_dec_nr_ptes(mm);
 			page_table_check_pte_clear_range(mm, addr, pgt_pmd);
 			pte_free_defer(mm, pmd_pgtable(pgt_pmd));
@@ -1837,6 +1844,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
 	if (result != SCAN_SUCCEED)
 		goto out;
 
+	mapping_set_update(&xas, mapping);
+
 	__folio_set_locked(new_folio);
 	if (is_shmem)
 		__folio_set_swapbacked(new_folio);
@@ -2277,6 +2286,17 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 			continue;
 		}
 
+		if (!folio_try_get(folio)) {
+			xas_reset(&xas);
+			continue;
+		}
+
+		if (unlikely(folio != xas_reload(&xas))) {
+			folio_put(folio);
+			xas_reset(&xas);
+			continue;
+		}
+
 		if (folio_order(folio) == HPAGE_PMD_ORDER &&
 		    folio->index == start) {
 			/* Maybe PMD-mapped */
@@ -2287,23 +2307,27 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 			 * it's safe to skip LRU and refcount checks before
 			 * returning.
 			 */
+			folio_put(folio);
 			break;
 		}
 
 		node = folio_nid(folio);
 		if (hpage_collapse_scan_abort(node, cc)) {
 			result = SCAN_SCAN_ABORT;
+			folio_put(folio);
 			break;
 		}
 		cc->node_load[node]++;
 
 		if (!folio_test_lru(folio)) {
 			result = SCAN_PAGE_LRU;
+			folio_put(folio);
 			break;
 		}
 
-		if (!is_refcount_suitable(folio)) {
+		if (folio_expected_ref_count(folio) + 1 != folio_ref_count(folio)) {
 			result = SCAN_PAGE_COUNT;
+			folio_put(folio);
 			break;
 		}
 
@@ -2315,6 +2339,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 		 */
 
 		present += folio_nr_pages(folio);
+		folio_put(folio);
 
 		if (need_resched()) {
 			xas_pause(&xas);
@@ -2336,14 +2361,6 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 	trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result);
 	return result;
 }
-#else
-static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
-				    struct file *file, pgoff_t start,
-				    struct collapse_control *cc)
-{
-	BUILD_BUG();
-}
-#endif
 
 static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 					    struct collapse_control *cc)
@@ -2419,7 +2436,7 @@ skip:
 			VM_BUG_ON(khugepaged_scan.address < hstart ||
 				  khugepaged_scan.address + HPAGE_PMD_SIZE >
 				  hend);
-			if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
+			if (!vma_is_anonymous(vma)) {
 				struct file *file = get_file(vma->vm_file);
 				pgoff_t pgoff = linear_page_index(vma,
 						khugepaged_scan.address);
@@ -2718,8 +2735,8 @@ static int madvise_collapse_errno(enum scan_result r)
 	}
 }
 
-int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
-		     unsigned long start, unsigned long end)
+int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end, bool *lock_dropped)
 {
 	struct collapse_control *cc;
 	struct mm_struct *mm = vma->vm_mm;
@@ -2730,8 +2747,6 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	BUG_ON(vma->vm_start > start);
 	BUG_ON(vma->vm_end < end);
 
-	*prev = vma;
-
 	if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER))
 		return -EINVAL;
 
@@ -2765,7 +2780,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		mmap_assert_locked(mm);
 		memset(cc->node_load, 0, sizeof(cc->node_load));
 		nodes_clear(cc->alloc_nmask);
-		if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
+		if (!vma_is_anonymous(vma)) {
 			struct file *file = get_file(vma->vm_file);
 			pgoff_t pgoff = linear_page_index(vma, addr);
 
@@ -2779,7 +2794,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 							 &mmap_locked, cc);
 		}
 		if (!mmap_locked)
-			*prev = NULL;  /* Tell caller we dropped mmap_lock */
+			*lock_dropped = true;
 
 handle_result:
 		switch (result) {
@@ -2789,7 +2804,6 @@ handle_result:
 			break;
 		case SCAN_PTE_MAPPED_HUGEPAGE:
 			BUG_ON(mmap_locked);
-			BUG_ON(*prev);
 			mmap_read_lock(mm);
 			result = collapse_pte_mapped_thp(mm, addr, true);
 			mmap_read_unlock(mm);