btrfs: move the dio_sem higher up the callchain

[mirror_ubuntu-bionic-kernel.git] / fs / btrfs / file.c

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4368033593be0d024191bfeccba01b605a9daa37..3c839a7b68bb48e86c0631c8a6aeecfffa138022 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2079,6 +2079,14 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
                goto out;
 
        inode_lock(inode);
+
+       /*
+        * We take the dio_sem here because the tree log stuff can race with
+        * lockless dio writes and get an extent map logged for an extent we
+        * never waited on.  We need it this high up for lockdep reasons.
+        */
+       down_write(&BTRFS_I(inode)->dio_sem);
+
        atomic_inc(&root->log_batch);
        full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
                             &BTRFS_I(inode)->runtime_flags);
@@ -2130,6 +2138,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
                ret = start_ordered_ops(inode, start, end);
        }
        if (ret) {
+               up_write(&BTRFS_I(inode)->dio_sem);
                inode_unlock(inode);
                goto out;
        }
@@ -2185,6 +2194,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
                 * checked called fsync.
                 */
                ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err);
+               up_write(&BTRFS_I(inode)->dio_sem);
                inode_unlock(inode);
                goto out;
        }
@@ -2209,6 +2219,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
        trans = btrfs_start_transaction(root, 0);
        if (IS_ERR(trans)) {
                ret = PTR_ERR(trans);
+               up_write(&BTRFS_I(inode)->dio_sem);
                inode_unlock(inode);
                goto out;
        }
@@ -2230,6 +2241,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
         * file again, but that will end up using the synchronization
         * inside btrfs_sync_log to keep things safe.
         */
+       up_write(&BTRFS_I(inode)->dio_sem);
        inode_unlock(inode);
 
        /*