summaryrefslogtreecommitdiff
path: root/fs/mbcache.c
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2022-11-23 20:39:50 +0100
committerTheodore Ts'o <tytso@mit.edu>2022-12-08 21:49:25 -0500
commita44e84a9b7764c72896f7241a0ec9ac7e7ef38dd (patch)
tree0a18a9c3bd8140b6ea41ae09af135a424148829c /fs/mbcache.c
parentb40ebaf63851b3a401b0dc9263843538f64f5ce6 (diff)
ext4: fix deadlock due to mbcache entry corruption
When manipulating xattr blocks, we can deadlock infinitely looping inside ext4_xattr_block_set() where we constantly keep finding xattr block for reuse in mbcache but we are unable to reuse it because its reference count is too big. This happens because cache entry for the xattr block is marked as reusable (e_reusable set) although its reference count is too big. When this inconsistency happens, this inconsistent state is kept indefinitely and so ext4_xattr_block_set() keeps retrying indefinitely. The inconsistent state is caused by non-atomic update of e_reusable bit. e_reusable is part of a bitfield and e_reusable update can race with update of e_referenced bit in the same bitfield resulting in loss of one of the updates. Fix the problem by using atomic bitops instead. This bug has been around for many years, but it became *much* easier to hit after commit 65f8b80053a1 ("ext4: fix race when reusing xattr blocks"). Cc: stable@vger.kernel.org Fixes: 6048c64b2609 ("mbcache: add reusable flag to cache entries") Fixes: 65f8b80053a1 ("ext4: fix race when reusing xattr blocks") Reported-and-tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com> Reported-by: Thilo Fromm <t-lo@linux.microsoft.com> Link: https://lore.kernel.org/r/c77bf00f-4618-7149-56f1-b8d1664b9d07@linux.microsoft.com/ Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20221123193950.16758-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Diffstat (limited to 'fs/mbcache.c')
-rw-r--r--fs/mbcache.c14
1 files changed, 8 insertions, 6 deletions
diff --git a/fs/mbcache.c b/fs/mbcache.c
index e272ad738faf..2a4b8b549e93 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -100,8 +100,9 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
atomic_set(&entry->e_refcnt, 2);
entry->e_key = key;
entry->e_value = value;
- entry->e_reusable = reusable;
- entry->e_referenced = 0;
+ entry->e_flags = 0;
+ if (reusable)
+ set_bit(MBE_REUSABLE_B, &entry->e_flags);
head = mb_cache_entry_head(cache, key);
hlist_bl_lock(head);
hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
@@ -165,7 +166,8 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
while (node) {
entry = hlist_bl_entry(node, struct mb_cache_entry,
e_hash_list);
- if (entry->e_key == key && entry->e_reusable &&
+ if (entry->e_key == key &&
+ test_bit(MBE_REUSABLE_B, &entry->e_flags) &&
atomic_inc_not_zero(&entry->e_refcnt))
goto out;
node = node->next;
@@ -284,7 +286,7 @@ EXPORT_SYMBOL(mb_cache_entry_delete_or_get);
void mb_cache_entry_touch(struct mb_cache *cache,
struct mb_cache_entry *entry)
{
- entry->e_referenced = 1;
+ set_bit(MBE_REFERENCED_B, &entry->e_flags);
}
EXPORT_SYMBOL(mb_cache_entry_touch);
@@ -309,9 +311,9 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache,
entry = list_first_entry(&cache->c_list,
struct mb_cache_entry, e_list);
/* Drop initial hash reference if there is no user */
- if (entry->e_referenced ||
+ if (test_bit(MBE_REFERENCED_B, &entry->e_flags) ||
atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) {
- entry->e_referenced = 0;
+ clear_bit(MBE_REFERENCED_B, &entry->e_flags);
list_move_tail(&entry->e_list, &cache->c_list);
continue;
}