1 files changed, 48 insertions, 59 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index f5b5c1f3dcd7..b577fbb98d4b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1304,6 +1304,10 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	int ret = SWAP_AGAIN;
 	enum ttu_flags flags = (enum ttu_flags)arg;
 
+	/* munlock has nothing to gain from examining un-locked vmas */
+	if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
+		goto out;
+
 	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
 		goto out;
@@ -1314,9 +1318,12 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	 * skipped over this mm) then we should reactivate it.
 	 */
 	if (!(flags & TTU_IGNORE_MLOCK)) {
-		if (vma->vm_flags & VM_LOCKED)
-			goto out_mlock;
-
+		if (vma->vm_flags & VM_LOCKED) {
+			/* Holding pte lock, we do *not* need mmap_sem here */
+			mlock_vma_page(page);
+			ret = SWAP_MLOCK;
+			goto out_unmap;
+		}
 		if (flags & TTU_MUNLOCK)
 			goto out_unmap;
 	}
@@ -1352,7 +1359,9 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	update_hiwater_rss(mm);
 
 	if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
-		if (!PageHuge(page)) {
+		if (PageHuge(page)) {
+			hugetlb_count_sub(1 << compound_order(page), mm);
+		} else {
 			if (PageAnon(page))
 				dec_mm_counter(mm, MM_ANONPAGES);
 			else
@@ -1370,47 +1379,44 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			dec_mm_counter(mm, MM_ANONPAGES);
 		else
 			dec_mm_counter(mm, MM_FILEPAGES);
+	} else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) {
+		swp_entry_t entry;
+		pte_t swp_pte;
+		/*
+		 * Store the pfn of the page in a special migration
+		 * pte. do_swap_page() will wait until the migration
+		 * pte is removed and then restart fault handling.
+		 */
+		entry = make_migration_entry(page, pte_write(pteval));
+		swp_pte = swp_entry_to_pte(entry);
+		if (pte_soft_dirty(pteval))
+			swp_pte = pte_swp_mksoft_dirty(swp_pte);
+		set_pte_at(mm, address, pte, swp_pte);
 	} else if (PageAnon(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
 		pte_t swp_pte;
-
-		if (PageSwapCache(page)) {
-			/*
-			 * Store the swap location in the pte.
-			 * See handle_pte_fault() ...
-			 */
-			if (swap_duplicate(entry) < 0) {
-				set_pte_at(mm, address, pte, pteval);
-				ret = SWAP_FAIL;
-				goto out_unmap;
-			}
-			if (list_empty(&mm->mmlist)) {
-				spin_lock(&mmlist_lock);
-				if (list_empty(&mm->mmlist))
-					list_add(&mm->mmlist, &init_mm.mmlist);
-				spin_unlock(&mmlist_lock);
-			}
-			dec_mm_counter(mm, MM_ANONPAGES);
-			inc_mm_counter(mm, MM_SWAPENTS);
-		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
-			/*
-			 * Store the pfn of the page in a special migration
-			 * pte. do_swap_page() will wait until the migration
-			 * pte is removed and then restart fault handling.
-			 */
-			BUG_ON(!(flags & TTU_MIGRATION));
-			entry = make_migration_entry(page, pte_write(pteval));
+		/*
+		 * Store the swap location in the pte.
+		 * See handle_pte_fault() ...
+		 */
+		VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+		if (swap_duplicate(entry) < 0) {
+			set_pte_at(mm, address, pte, pteval);
+			ret = SWAP_FAIL;
+			goto out_unmap;
+		}
+		if (list_empty(&mm->mmlist)) {
+			spin_lock(&mmlist_lock);
+			if (list_empty(&mm->mmlist))
+				list_add(&mm->mmlist, &init_mm.mmlist);
+			spin_unlock(&mmlist_lock);
 		}
+		dec_mm_counter(mm, MM_ANONPAGES);
+		inc_mm_counter(mm, MM_SWAPENTS);
 		swp_pte = swp_entry_to_pte(entry);
 		if (pte_soft_dirty(pteval))
 			swp_pte = pte_swp_mksoft_dirty(swp_pte);
 		set_pte_at(mm, address, pte, swp_pte);
-	} else if (IS_ENABLED(CONFIG_MIGRATION) &&
-		   (flags & TTU_MIGRATION)) {
-		/* Establish migration entry for a file page */
-		swp_entry_t entry;
-		entry = make_migration_entry(page, pte_write(pteval));
-		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
 	} else
 		dec_mm_counter(mm, MM_FILEPAGES);
 
@@ -1419,31 +1425,10 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
-	if (ret != SWAP_FAIL && !(flags & TTU_MUNLOCK))
+	if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK))
 		mmu_notifier_invalidate_page(mm, address);
 out:
 	return ret;
-
-out_mlock:
-	pte_unmap_unlock(pte, ptl);
-
-
-	/*
-	 * We need mmap_sem locking, Otherwise VM_LOCKED check makes
-	 * unstable result and race. Plus, We can't wait here because
-	 * we now hold anon_vma->rwsem or mapping->i_mmap_rwsem.
-	 * if trylock failed, the page remain in evictable lru and later
-	 * vmscan could retry to move the page to unevictable lru if the
-	 * page is actually mlocked.
-	 */
-	if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
-		if (vma->vm_flags & VM_LOCKED) {
-			mlock_vma_page(page);
-			ret = SWAP_MLOCK;
-		}
-		up_read(&vma->vm_mm->mmap_sem);
-	}
-	return ret;
 }
 
 bool is_vma_temporary_stack(struct vm_area_struct *vma)
@@ -1607,6 +1592,8 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 		struct vm_area_struct *vma = avc->vma;
 		unsigned long address = vma_address(page, vma);
 
+		cond_resched();
+
 		if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
 			continue;
 
@@ -1656,6 +1643,8 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
 		unsigned long address = vma_address(page, vma);
 
+		cond_resched();
+
 		if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
 			continue;