This patch fixes a data race in commit 779750d20b93 ("shmem: split huge pages
beyond i_size under memory pressure").
Here are call traces causing race:
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
A simple explanation:
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)
We should make sure the inode is either on the global list or deleted from
any local list before iput().
Fixed by moving inodes back to global list before we put them.
Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure")
Cc: [email protected] # v4.8+
Signed-off-by: Gang Li <[email protected]>
Reviewed-by: Muchun Song <[email protected]>
Acked-by: Kirill A. Shutemov <[email protected]>
---
Changes in v5:
- Fix a compile warning
Changes in v4:
- Rework the comments
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/[email protected]/
- 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/[email protected]/
---
mm/shmem.c | 36 ++++++++++++++++++++----------------
1 file changed, 20 insertions(+), 16 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 9023103ee7d8..a6487fe0583f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -554,7 +554,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shmem_inode_info *info;
struct page *page;
unsigned long batch = sc ? sc->nr_to_scan : 128;
- int removed = 0, split = 0;
+ int split = 0;
if (list_empty(&sbinfo->shrinklist))
return SHRINK_STOP;
@@ -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;
}
@@ -577,12 +576,12 @@ 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:
+ sbinfo->shrinklist_len--;
if (!--batch)
break;
}
@@ -602,7 +601,7 @@ 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 +615,43 @@ 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:
+ /*
+ * Make sure the inode is either on the global list or deleted from
+ * any local list before iput() since it could be deleted in another
+ * thread once we put the inode (then the local list is corrupted).
+ */
+ 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