summaryrefslogtreecommitdiffstats
path: root/fs/xfs
diff options
context:
space:
mode:
authorBrian Foster <bfoster@redhat.com>2015-10-12 16:04:13 +1100
committerDave Chinner <david@fromorbit.com>2015-10-12 16:04:13 +1100
commitdbd5c8c9a28899c6ca719eb21afc0afba9dd5574 (patch)
treebc64286e1f657b1c03ae96a8ebd07959c0df9872 /fs/xfs
parenta45086e27dfa21a4b39134f7505c8f60a3ecdec4 (diff)
downloadlinux-dbd5c8c9a28899c6ca719eb21afc0afba9dd5574.tar.bz2
xfs: pass total block res. as total xfs_bmapi_write() parameter
The total field from struct xfs_alloc_arg is a bit of an unknown commodity. It is documented as the total block requirement for the transaction and is used in this manner from most call sites by virtue of passing the total block reservation of the transaction associated with an allocation. Several xfs_bmapi_write() callers pass hardcoded values of 0 or 1 for the total block requirement, which is a historical oddity without any clear reasoning. The xfs_iomap_write_direct() caller, for example, passes 0 for the total block requirement. This has been determined to cause problems in the form of ABBA deadlocks of AGF buffers due to incorrect AG selection in the block allocator. Specifically, the xfs_alloc_space_available() function incorrectly selects an AG that doesn't actually have sufficient space for the allocation. This occurs because the args.total field is 0 and thus the remaining free space check on the AG doesn't actually consider the size of the allocation request. This locks the AGF buffer, the allocation attempt proceeds and ultimately fails (in xfs_alloc_fix_minleft()), and xfs_alloc_vexent() moves on to the next AG. In turn, this can lead to incorrect AG locking order (if the allocator wraps around, attempting to lock AG 0 after acquiring AG N) and thus deadlock if racing with another operation. This problem has been reproduced via generic/299 on smallish (1GB) ramdisk test devices. To avoid this problem, replace the undocumented hardcoded total parameters from the iomap and utility callers to pass the block reservation used for the associated transaction. This is consistent with other xfs_bmapi_write() callers throughout XFS. The assumption is that the total field allows the selection of an AG that can handle the entire operation rather than simply the allocation/range being requested (e.g., resulting btree splits, etc.). This addresses the aforementioned generic/299 hang by ensuring AG selection only occurs when the allocation can be satisfied by the AG. Reported-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_bmap_util.c2
-rw-r--r--fs/xfs/xfs_iomap.c14
2 files changed, 8 insertions, 8 deletions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 3bf4ad0d19e4..eca325e42261 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1027,7 +1027,7 @@ xfs_alloc_file_space(
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
allocatesize_fsb, alloc_type, &firstfsb,
- 0, imapp, &nimaps, &free_list);
+ resblks, imapp, &nimaps, &free_list);
if (error) {
goto error0;
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 1f86033171c8..3d9fa36d472b 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -202,8 +202,8 @@ xfs_iomap_write_direct(
xfs_bmap_init(&free_list, &firstfsb);
nimaps = 1;
error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
- XFS_BMAPI_PREALLOC, &firstfsb, 0,
- imap, &nimaps, &free_list);
+ XFS_BMAPI_PREALLOC, &firstfsb, resblks, imap,
+ &nimaps, &free_list);
if (error)
goto out_bmap_cancel;
@@ -750,9 +750,9 @@ xfs_iomap_write_allocate(
* pointer that the caller gave to us.
*/
error = xfs_bmapi_write(tp, ip, map_start_fsb,
- count_fsb, 0,
- &first_block, 1,
- imap, &nimaps, &free_list);
+ count_fsb, 0, &first_block,
+ nres, imap, &nimaps,
+ &free_list);
if (error)
goto trans_cancel;
@@ -866,8 +866,8 @@ xfs_iomap_write_unwritten(
xfs_bmap_init(&free_list, &firstfsb);
nimaps = 1;
error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
- XFS_BMAPI_CONVERT, &firstfsb,
- 1, &imap, &nimaps, &free_list);
+ XFS_BMAPI_CONVERT, &firstfsb, resblks,
+ &imap, &nimaps, &free_list);
if (error)
goto error_on_bmapi_transaction;