1 files changed, 76 insertions, 48 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 283963032eff..928ae18b1c13 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -688,7 +688,6 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			transparent_hugepage_use_zero_page()) {
 		pgtable_t pgtable;
 		struct page *zero_page;
-		bool set;
 		int ret;
 		pgtable = pte_alloc_one(vma->vm_mm, haddr);
 		if (unlikely(!pgtable))
@@ -701,25 +700,25 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		}
 		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 		ret = 0;
-		set = false;
 		if (pmd_none(*vmf->pmd)) {
 			ret = check_stable_address_space(vma->vm_mm);
 			if (ret) {
 				spin_unlock(vmf->ptl);
+				pte_free(vma->vm_mm, pgtable);
 			} else if (userfaultfd_missing(vma)) {
 				spin_unlock(vmf->ptl);
+				pte_free(vma->vm_mm, pgtable);
 				ret = handle_userfault(vmf, VM_UFFD_MISSING);
 				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			} else {
 				set_huge_zero_page(pgtable, vma->vm_mm, vma,
 						   haddr, vmf->pmd, zero_page);
 				spin_unlock(vmf->ptl);
-				set = true;
 			}
-		} else
+		} else {
 			spin_unlock(vmf->ptl);
-		if (!set)
 			pte_free(vma->vm_mm, pgtable);
+		}
 		return ret;
 	}
 	gfp = alloc_hugepage_direct_gfpmask(vma);
@@ -1368,13 +1367,12 @@ out_unlock:
 }
 
 /*
- * FOLL_FORCE can write to even unwritable pmd's, but only
- * after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE or a forced COW break can write even to unwritable pmd's,
+ * but only after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
 {
-	return pmd_write(pmd) ||
-	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+	return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd));
 }
 
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1626,7 +1624,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 * If other processes are mapping this page, we couldn't discard
 	 * the page unless they all do MADV_FREE so let's skip the page.
 	 */
-	if (page_mapcount(page) != 1)
+	if (total_mapcount(page) != 1)
 		goto out;
 
 	if (!trylock_page(page))
@@ -2078,7 +2076,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		put_page(page);
 		add_mm_counter(mm, MM_FILEPAGES, -HPAGE_PMD_NR);
 		return;
-	} else if (is_huge_zero_pmd(*pmd)) {
+	} else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
 		return __split_huge_zero_page_pmd(vma, haddr, pmd);
 	}
 
@@ -2131,27 +2129,33 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, entry);
-		atomic_inc(&page[i]._mapcount);
-		pte_unmap(pte);
-	}
-
-	/*
-	 * Set PG_double_map before dropping compound_mapcount to avoid
-	 * false-negative page_mapped().
-	 */
-	if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
-		for (i = 0; i < HPAGE_PMD_NR; i++)
+		if (!pmd_migration)
 			atomic_inc(&page[i]._mapcount);
+		pte_unmap(pte);
 	}
 
-	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
-		/* Last compound_mapcount is gone. */
-		__dec_node_page_state(page, NR_ANON_THPS);
-		if (TestClearPageDoubleMap(page)) {
-			/* No need in mapcount reference anymore */
+	if (!pmd_migration) {
+		/*
+		 * Set PG_double_map before dropping compound_mapcount to avoid
+		 * false-negative page_mapped().
+		 */
+		if (compound_mapcount(page) > 1 &&
+		    !TestSetPageDoubleMap(page)) {
 			for (i = 0; i < HPAGE_PMD_NR; i++)
-				atomic_dec(&page[i]._mapcount);
+				atomic_inc(&page[i]._mapcount);
+		}
+
+		lock_page_memcg(page);
+		if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+			/* Last compound_mapcount is gone. */
+			__dec_lruvec_page_state(page, NR_ANON_THPS);
+			if (TestClearPageDoubleMap(page)) {
+				/* No need in mapcount reference anymore */
+				for (i = 0; i < HPAGE_PMD_NR; i++)
+					atomic_dec(&page[i]._mapcount);
+			}
 		}
+		unlock_page_memcg(page);
 	}
 
 	smp_wmb(); /* make pte visible before pmd */
@@ -2193,6 +2197,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
+	bool do_unlock_page = false;
+	pmd_t _pmd;
 
 	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
 	ptl = pmd_lock(mm, pmd);
@@ -2202,11 +2208,41 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	 * pmd against. Otherwise we can end up replacing wrong page.
 	 */
 	VM_BUG_ON(freeze && !page);
-	if (page && page != pmd_page(*pmd))
-	        goto out;
+	if (page) {
+		VM_WARN_ON_ONCE(!PageLocked(page));
+		if (page != pmd_page(*pmd))
+			goto out;
+	}
 
+repeat:
 	if (pmd_trans_huge(*pmd)) {
-		page = pmd_page(*pmd);
+		if (!page) {
+			page = pmd_page(*pmd);
+			/*
+			 * An anonymous page must be locked, to ensure that a
+			 * concurrent reuse_swap_page() sees stable mapcount;
+			 * but reuse_swap_page() is not used on shmem or file,
+			 * and page lock must not be taken when zap_pmd_range()
+			 * calls __split_huge_pmd() while i_mmap_lock is held.
+			 */
+			if (PageAnon(page)) {
+				if (unlikely(!trylock_page(page))) {
+					get_page(page);
+					_pmd = *pmd;
+					spin_unlock(ptl);
+					lock_page(page);
+					spin_lock(ptl);
+					if (unlikely(!pmd_same(*pmd, _pmd))) {
+						unlock_page(page);
+						put_page(page);
+						page = NULL;
+						goto repeat;
+					}
+					put_page(page);
+				}
+				do_unlock_page = true;
+			}
+		}
 		if (PageMlocked(page))
 			clear_page_mlock(page);
 	} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
@@ -2214,6 +2250,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	__split_huge_pmd_locked(vma, pmd, haddr, freeze);
 out:
 	spin_unlock(ptl);
+	if (do_unlock_page)
+		unlock_page(page);
 	mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
 }
 
@@ -2286,16 +2324,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
-		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
-	bool unmap_success;
+		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_SPLIT_FREEZE;
 
-	unmap_success = try_to_unmap(page, ttu_flags);
-	VM_BUG_ON_PAGE(!unmap_success, page);
+	try_to_unmap(page, ttu_flags);
+
+	VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
 }
 
 static void remap_page(struct page *page)
@@ -2548,7 +2586,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
-	int count, mapcount, extra_pins, ret;
+	int extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
 	pgoff_t end;
@@ -2610,7 +2648,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	mlocked = PageMlocked(page);
 	unmap_page(head);
-	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */
 	if (mlocked)
@@ -2636,9 +2673,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
 	spin_lock(&pgdata->split_queue_lock);
-	count = page_count(head);
-	mapcount = total_mapcount(head);
-	if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+	if (page_ref_freeze(head, 1 + extra_pins)) {
 		if (!list_empty(page_deferred_list(head))) {
 			pgdata->split_queue_len--;
 			list_del(page_deferred_list(head));
@@ -2654,16 +2689,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		} else
 			ret = 0;
 	} else {
-		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-			pr_alert("total_mapcount: %u, page_count(): %u\n",
-					mapcount, count);
-			if (PageTail(page))
-				dump_page(head, NULL);
-			dump_page(page, "total_mapcount(head) > 0");
-			BUG();
-		}
 		spin_unlock(&pgdata->split_queue_lock);
-fail:		if (mapping)
+fail:
+		if (mapping)
 			spin_unlock(&mapping->tree_lock);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 		remap_page(head);