[PATCH v3] shmem: fix a race between shmem_unused_huge_shrink and shmem_evict_inode

[Gang Li]

This patch fixes a data race in commit 779750d20b93 ("shmem: split huge pages
beyond i_size under memory pressure").

Here are call traces:

Call Trace 1:
	shmem_unused_huge_shrink+0x3ae/0x410
	? __list_lru_walk_one.isra.5+0x33/0x160
	super_cache_scan+0x17c/0x190
	shrink_slab.part.55+0x1ef/0x3f0
	shrink_node+0x10e/0x330
	kswapd+0x380/0x740
	kthread+0xfc/0x130
	? mem_cgroup_shrink_node+0x170/0x170
	? kthread_create_on_node+0x70/0x70
	ret_from_fork+0x1f/0x30

Call Trace 2:
	shmem_evict_inode+0xd8/0x190
	evict+0xbe/0x1c0
	do_unlinkat+0x137/0x330
	do_syscall_64+0x76/0x120
	entry_SYSCALL_64_after_hwframe+0x3d/0xa2

The simultaneous deletion of adjacent elements in the local list (@list)
by shmem_unused_huge_shrink and shmem_evict_inode will break the list.

Image there are 3 items in the local list (@list).
In the first traversal, A is not deleted from @list.

  1)    A->B->C
        ^
        |
        pos (leave)

In the second traversal, B is deleted from @list. Concurrently, A is
deleted from @list through shmem_evict_inode() since last reference counter of
inode is dropped by other thread. Then the @list is corrupted.

  2)    A->B->C
        ^  ^
        |  |
     evict pos (drop)

Fix:

We should make sure the item is either on the global list or deleted from
any local list before iput().

Fixed by moving inodes that are on @list and will not be deleted back to
global list before iput.

Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure")
Signed-off-by: Gang Li <ligang.bdlg@xxxxxxxxxxxxx>

---

Changes in v3:
- Add more comment.
- Use list_move(&info->shrinklist, &sbinfo->shrinklist) instead of 
  list_move(pos, &sbinfo->shrinklist) for consistency.

Changes in v2: https://lore.kernel.org/all/20211124030840.88455-1-ligang.bdlg@xxxxxxxxxxxxx/
- Move spinlock to the front of iput instead of changing lock type
  since iput will call evict which may cause deadlock by requesting
  shrinklist_lock.
- Add call trace in commit message.

v1: https://lore.kernel.org/lkml/20211122064126.76734-1-ligang.bdlg@xxxxxxxxxxxxx/

---
 mm/shmem.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 9023103ee7d8..ab2df692bd58 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -569,7 +569,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		/* inode is about to be evicted */
 		if (!inode) {
 			list_del_init(&info->shrinklist);
-			removed++;
 			goto next;
 		}
 
@@ -577,15 +576,16 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		if (round_up(inode->i_size, PAGE_SIZE) ==
 				round_up(inode->i_size, HPAGE_PMD_SIZE)) {
 			list_move(&info->shrinklist, &to_remove);
-			removed++;
 			goto next;
 		}
 
 		list_move(&info->shrinklist, &list);
 next:
+		removed++;
 		if (!--batch)
 			break;
 	}
+	sbinfo->shrinklist_len -= removed;
 	spin_unlock(&sbinfo->shrinklist_lock);
 
 	list_for_each_safe(pos, next, &to_remove) {
@@ -602,7 +602,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		inode = &info->vfs_inode;
 
 		if (nr_to_split && split >= nr_to_split)
-			goto leave;
+			goto move_back;
 
 		page = find_get_page(inode->i_mapping,
 				(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
@@ -616,38 +616,43 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		}
 
 		/*
-		 * Leave the inode on the list if we failed to lock
-		 * the page at this time.
+		 * Move the inode on the list back to shrinklist if we failed
+		 * to lock the page at this time.
 		 *
 		 * Waiting for the lock may lead to deadlock in the
 		 * reclaim path.
 		 */
 		if (!trylock_page(page)) {
 			put_page(page);
-			goto leave;
+			goto move_back;
 		}
 
 		ret = split_huge_page(page);
 		unlock_page(page);
 		put_page(page);
 
-		/* If split failed leave the inode on the list */
+		/* If split failed move the inode on the list back to shrinklist */
 		if (ret)
-			goto leave;
+			goto move_back;
 
 		split++;
 drop:
 		list_del_init(&info->shrinklist);
-		removed++;
-leave:
+		goto put;
+move_back:
+		/* inodes that are on @list and will not be deleted must be moved back to
+		 * global list before iput for two reasons:
+		 * 1. iput in lock: iput call shmem_evict_inode, then cause deadlock.
+		 * 2. iput before lock: shmem_evict_inode may grab the inode on @list,
+		 *    which will cause race.
+		 */
+		spin_lock(&sbinfo->shrinklist_lock);
+		list_move(&info->shrinklist, &sbinfo->shrinklist);
+		sbinfo->shrinklist_len++;
+		spin_unlock(&sbinfo->shrinklist_lock);
+put:
 		iput(inode);
 	}
 
-	spin_lock(&sbinfo->shrinklist_lock);
-	list_splice_tail(&list, &sbinfo->shrinklist);
-	sbinfo->shrinklist_len -= removed;
-	spin_unlock(&sbinfo->shrinklist_lock);
-
 	return split;
 }
 
-- 
2.20.1