In order to prevent a circular locking dependency when an ext4_create
operation is racing with an ext4_fallocate, we acquire and release
i_data_sem for each multiblock request and use i_mutex to
prevent writes and truncates during the complete fallocate operation.
=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.25-rc1 #4
-------------------------------------------------------
touch/2347 is trying to acquire lock:
(&ei->i_data_sem){----}, at: [<c01cffed>] ext4_get_blocks_wrap+0x21/0xca
but task is already holding lock:
(jbd2_handle){--..}, at: [<c01ee43c>] jbd2_journal_start+0xce/0xf0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (jbd2_handle){--..}:
[<c013b2e3>] __lock_acquire+0x960/0xb13
[<c01ee43c>] jbd2_journal_start+0xce/0xf0
[<c013b502>] lock_acquire+0x6c/0x89
[<c01ee43c>] jbd2_journal_start+0xce/0xf0
[<c01ee451>] jbd2_journal_start+0xe3/0xf0
[<c01ee43c>] jbd2_journal_start+0xce/0xf0
[<c01d66c5>] ext4_journal_start_sb+0x40/0x42
[<c01dd2bd>] ext4_fallocate+0x156/0x46b
[<c01527dd>] __do_fault+0x2ea/0x324
[<c0108c60>] native_sched_clock+0x8d/0x9f
[<c0108c60>] native_sched_clock+0x8d/0x9f
[<c016531a>] fget+0x7d/0x9b
[<c016302a>] sys_fallocate+0xcc/0xf0
[<c0104992>] sysenter_past_esp+0x5f/0xa5
[<ffffffff>] 0xffffffff
-> #0 (&ei->i_data_sem){----}:
[<c013b20a>] __lock_acquire+0x887/0xb13
[<c013b502>] lock_acquire+0x6c/0x89
[<c01cffed>] ext4_get_blocks_wrap+0x21/0xca
[<c043353b>] down_read+0x30/0x6a
[<c01cffed>] ext4_get_blocks_wrap+0x21/0xca
[<c01cffed>] ext4_get_blocks_wrap+0x21/0xca
[<c01d00df>] ext4_getblk+0x49/0x18f
[<c01dde4d>] __ext4_journal_dirty_metadata+0x19/0x3c
[<c01ceff7>] ext4_mark_iloc_dirty+0x380/0x3e5
[<c01d0ed0>] ext4_bread+0x14/0x78
[<c01d3b49>] ext4_add_entry+0x483/0x775
[<c01ce4d5>] ext4_new_inode+0xa13/0xa3d
[<c043418c>] _spin_unlock+0x1d/0x20
[<c01ee451>] jbd2_journal_start+0xe3/0xf0
[<c01d43e0>] ext4_add_nondir+0x15/0x42
[<c01d48a7>] ext4_create+0xab/0xdf
[<c01d47fc>] ext4_create+0x0/0xdf
[<c016ad14>] vfs_create+0x67/0xad
[<c016cfc2>] open_namei+0x15c/0x512
[<c0162e35>] do_filp_open+0x1f/0x35
[<c0162c08>] get_unused_fd_flags+0xd4/0xde
[<c043418c>] _spin_unlock+0x1d/0x20
[<c0162e8d>] do_sys_open+0x42/0xbc
[<c0162f33>] sys_open+0x16/0x18
[<c0104992>] sysenter_past_esp+0x5f/0xa5
[<ffffffff>] 0xffffffff
other info that might help us debug this:
2 locks held by touch/2347:
#0: (&type->i_mutex_dir_key#5){--..}, at: [<c016cf35>] open_namei+0xcf/0x512
#1: (jbd2_handle){--..}, at: [<c01ee43c>] jbd2_journal_start+0xce/0xf0
stack backtrace:
Pid: 2347, comm: touch Not tainted 2.6.25-rc1 #4
[<c01394cd>] print_circular_bug_tail+0x5b/0x66
[<c013b20a>] __lock_acquire+0x887/0xb13
[<c013b502>] lock_acquire+0x6c/0x89
[<c01cffed>] ? ext4_get_blocks_wrap+0x21/0xca
[<c043353b>] down_read+0x30/0x6a
[<c01cffed>] ? ext4_get_blocks_wrap+0x21/0xca
[<c01cffed>] ext4_get_blocks_wrap+0x21/0xca
[<c01d00df>] ext4_getblk+0x49/0x18f
[<c01dde4d>] ? __ext4_journal_dirty_metadata+0x19/0x3c
[<c01ceff7>] ? ext4_mark_iloc_dirty+0x380/0x3e5
[<c01d0ed0>] ext4_bread+0x14/0x78
[<c01d3b49>] ext4_add_entry+0x483/0x775
[<c01ce4d5>] ? ext4_new_inode+0xa13/0xa3d
[<c043418c>] ? _spin_unlock+0x1d/0x20
[<c01ee451>] ? jbd2_journal_start+0xe3/0xf0
[<c01d43e0>] ext4_add_nondir+0x15/0x42
[<c01d48a7>] ext4_create+0xab/0xdf
[<c01d47fc>] ? ext4_create+0x0/0xdf
[<c016ad14>] vfs_create+0x67/0xad
[<c016cfc2>] open_namei+0x15c/0x512
[<c0162e35>] do_filp_open+0x1f/0x35
[<c0162c08>] ? get_unused_fd_flags+0xd4/0xde
[<c043418c>] ? _spin_unlock+0x1d/0x20
[<c0162e8d>] do_sys_open+0x42/0xbc
[<c0162f33>] sys_open+0x16/0x18
[<c0104992>] sysenter_past_esp+0x5f/0xa5
=======================
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
---
fs/ext4/extents.c | 10 +++-------
1 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index bc7081f..e856f66 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2623,7 +2623,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
* modify 1 super block, 1 block bitmap and 1 group descriptor.
*/
credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
- down_write((&EXT4_I(inode)->i_data_sem));
+ mutex_lock(&inode->i_mutex);
retry:
while (ret >= 0 && ret < max_blocks) {
block = block + ret;
@@ -2634,7 +2634,7 @@ retry:
break;
}
- ret = ext4_ext_get_blocks(handle, inode, block,
+ ret = ext4_get_blocks_wrap(handle, inode, block,
max_blocks, &map_bh,
EXT4_CREATE_UNINITIALIZED_EXT, 0);
WARN_ON(ret <= 0);
@@ -2680,7 +2680,6 @@ retry:
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
- up_write((&EXT4_I(inode)->i_data_sem));
/*
* Time to update the file size.
* Update only when preallocation was requested beyond the file size.
@@ -2692,21 +2691,18 @@ retry:
* if no error, we assume preallocation succeeded
* completely
*/
- mutex_lock(&inode->i_mutex);
i_size_write(inode, offset + len);
EXT4_I(inode)->i_disksize = i_size_read(inode);
- mutex_unlock(&inode->i_mutex);
} else if (ret < 0 && nblocks) {
/* Handle partial allocation scenario */
loff_t newsize;
- mutex_lock(&inode->i_mutex);
newsize = (nblocks << blkbits) + i_size_read(inode);
i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits));
EXT4_I(inode)->i_disksize = i_size_read(inode);
- mutex_unlock(&inode->i_mutex);
}
}
+ mutex_unlock(&inode->i_mutex);
return ret > 0 ? ret2 : ret;
}
--
1.5.4.1.97.g40aab-dirty
-
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
