aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2009-08-17 22:17:20 -0400
committerTheodore Ts'o <tytso@mit.edu>2009-08-17 22:17:20 -0400
commit487caeef9fc08c0565e082c40a8aaf58dad92bbb (patch)
tree69920293cfe3a50bdbbf845be785350e7c203a2b /fs/ext4/inode.c
parent9599b0e597d810be9b8f759ea6e9619c4f983c5e (diff)
downloadkernel_samsung_smdk4412-487caeef9fc08c0565e082c40a8aaf58dad92bbb.zip
kernel_samsung_smdk4412-487caeef9fc08c0565e082c40a8aaf58dad92bbb.tar.gz
kernel_samsung_smdk4412-487caeef9fc08c0565e082c40a8aaf58dad92bbb.tar.bz2
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>
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c23
1 files changed, 19 insertions, 4 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9a4c929..d61fb52 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);