ext4: Fix possible deadlock between ext4_truncate() and ext4_get_blocks()

During truncate we are sometimes forced to start a new transaction as
the amount of blocks to be journaled is both quite large and hard to
predict. So far we restarted a transaction while holding i_data_sem
and that violates lock ordering because i_data_sem ranks below a
transaction start (and it can lead to a real deadlock with
ext4_get_blocks() mapping blocks in some page while having a
transaction open).

We fix the problem by dropping the i_data_sem before restarting the
transaction and acquire it afterwards. It's slightly subtle that this
works:

1) By the time ext4_truncate() is called, all the page cache for the
truncated part of the file is dropped so get_block() should not be
called on it (we only have to invalidate extent cache after we
reacquire i_data_sem because some extent from not-truncated part could
extend also into the part we are going to truncate).

2) Writes, migrate or defrag hold i_mutex so they are stopped for all
the time of the truncate.

This bug has been found and analyzed by Theodore Tso <tytso@mit.edu>.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

3 files changed, 32 insertions, 7 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2e9a2036c114..fb21663ffe54 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1370,6 +1370,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_can_truncate(struct inode *inode);
 extern void ext4_truncate(struct inode *);
+extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern int ext4_alloc_da_blocks(struct inode *inode);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 13db43408533..8c20caf4aa5c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -93,7 +93,9 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
         ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
 }
 
-static int ext4_ext_journal_restart(handle_t *handle, int needed)
+static int ext4_ext_truncate_extend_restart(handle_t *handle,
+                                            struct inode *inode,
+                                            int needed)
 {
         int err;
 
@@ -104,7 +106,14 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed)
         err = ext4_journal_extend(handle, needed);
         if (err <= 0)
                 return err;
-        return ext4_journal_restart(handle, needed);
+        err = ext4_truncate_restart_trans(handle, inode, needed);
+        /*
+         * We have dropped i_data_sem so someone might have cached again
+         * an extent we are going to truncate.
+         */
+        ext4_ext_invalidate_cache(inode);
+
+        return err;
 }
 
 /*
@@ -2150,7 +2159,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                 }
                 credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
 
-                err = ext4_ext_journal_restart(handle, credits);
+                err = ext4_ext_truncate_extend_restart(handle, inode, credits);
                 if (err)
                         goto out;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9a4c929b16dc..d61fb523308f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -192,11 +192,24 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
  * so before we call here everything must be consistently dirtied against
  * this transaction.
  */
-static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
+ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+                                 int nblocks)
 {
+        int ret;
+
+        /*
+         * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this
+         * moment, get_block can be called only for blocks inside i_size since
+         * page cache has been already dropped and writes are blocked by
+         * i_mutex. So we can safely drop the i_data_sem here.
+         */
         BUG_ON(EXT4_JOURNAL(inode) == NULL);
         jbd_debug(2, "restarting handle %p\n", handle);
-        return ext4_journal_restart(handle, blocks_for_truncate(inode));
+        up_write(&EXT4_I(inode)->i_data_sem);
+        ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
+        down_write(&EXT4_I(inode)->i_data_sem);
+
+        return ret;
 }
 
 /*
@@ -3658,7 +3671,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
                         ext4_handle_dirty_metadata(handle, inode, bh);
                 }
                 ext4_mark_inode_dirty(handle, inode);
-                ext4_journal_test_restart(handle, inode);
+                ext4_truncate_restart_trans(handle, inode,
+                                            blocks_for_truncate(inode));
                 if (bh) {
                         BUFFER_TRACE(bh, "retaking write access");
                         ext4_journal_get_write_access(handle, bh);
@@ -3869,7 +3883,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
                                 return;
                         if (try_to_extend_transaction(handle, inode)) {
                                 ext4_mark_inode_dirty(handle, inode);
-                                ext4_journal_test_restart(handle, inode);
+                                ext4_truncate_restart_trans(handle, inode,
+                                            blocks_for_truncate(inode));
                         }
 
                         ext4_free_blocks(handle, inode, nr, 1, 1);