f2fs_quota_sync is calling f2fs_lock_op, in an attempt to prevent
an AB/BA type deadlock with quota_sem locking in block_operation.
However, rwsem in Linux is not recursive. As a result, the following
deadlock may occur:
f2fs_quota_sync
down_read(cp_rwsem) // f2fs_lock_op
filemap_fdatawrite
f2fs_write_data_pages
...
block_opertaion
down_write(cp_rwsem) - marks rwsem as "writer pending"
down_read_trylock(cp_rwsem) - fails as there is
a writer pending.
Code keeps on trying.
We solve this by creating a new rwsem, used specifically to
synchronize this case, instead of attempting to reuse an existing lock
for this
---
fs/f2fs/f2fs.h | 3 +++
fs/f2fs/super.c | 13 +++++++++++--
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index cb700d797296..b3e55137be7f 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1448,6 +1448,7 @@ struct f2fs_sb_info {
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
+ struct rw_semaphore cp_quota_rwsem; /* blocking quota sync operations */
struct rw_semaphore node_write; /* locking node writes */
struct rw_semaphore node_change; /* locking node change */
wait_queue_head_t cp_wait;
@@ -1961,12 +1962,14 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
+ down_write(&sbi->cp_quota_rwsem);
down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
up_write(&sbi->cp_rwsem);
+ up_write(&sbi->cp_quota_rwsem);
}
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 00eff2f51807..5ce61147d7e5 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2209,8 +2209,16 @@ int f2fs_quota_sync(struct super_block *sb, int type)
* f2fs_dquot_commit
* block_operation
* down_read(quota_sem)
+ *
+ * However, we cannot use the cp_rwsem to prevent this
+ * deadlock, as the cp_rwsem is taken for read inside the
+ * f2fs_dquot_commit code, and rwsem is not recursive.
+ *
+ * We therefore use a special lock to synchronize
+ * f2fs_quota_sync with block_operations, as this is the only
+ * place where such recurrsion occurs.
*/
- f2fs_lock_op(sbi);
+ down_read(&sbi->cp_quota_rwsem);
down_read(&sbi->quota_sem);
ret = dquot_writeback_dquots(sb, type);
@@ -2251,7 +2259,7 @@ int f2fs_quota_sync(struct super_block *sb, int type)
if (ret)
set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
up_read(&sbi->quota_sem);
- f2fs_unlock_op(sbi);
+ up_read(&sbi->cp_quota_rwsem);
return ret;
}
@@ -3599,6 +3607,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
init_rwsem(&sbi->cp_rwsem);
init_rwsem(&sbi->quota_sem);
+ init_rwsem(&sbi->cp_quota_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
--
2.29.2