diff options
| author | Jaegeuk Kim <jaegeuk@kernel.org> | 2014-12-18 19:32:36 -0800 |
|---|---|---|
| committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2015-01-09 17:02:25 -0800 |
| commit | dd802406e396c22dfb5aa0d16196f04d515be49e (patch) | |
| tree | dd7c8361203983936bc6ef5f6c61234a69eadfd0 | |
| parent | db9f7c1a9561e998d6227bcc1c19bc4c1fbbca1b (diff) | |
f2fs: avoid double lock for cp_rwsem
The __f2fs_add_link is covered by cp_rwsem all the time.
This calls init_inode_metadata, which conducts some acl operations including
memory allocation with GFP_KERNEL previously.
But, under memory pressure, f2fs_write_data_page can be called, which also
grabs cp_rwsem too.
In this case, this incurs a deadlock pointed by Chao.
Thread #1 Thread #2
down_read
down_write
down_read
-> here down_read should wait forever.
Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
| -rw-r--r-- | fs/f2fs/acl.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 1ccb26bc2a0b..7f12d28ad94c 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) if (count == 0) return NULL; - acl = posix_acl_alloc(count, GFP_KERNEL); + acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); @@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size) int i; f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count * - sizeof(struct f2fs_acl_entry), GFP_KERNEL); + sizeof(struct f2fs_acl_entry), GFP_NOFS); if (!f2fs_acl) return ERR_PTR(-ENOMEM); |