kernel.git/fs/btrfs/ctree.c, branch linux-3.14.y

Btrfs: make xattr replace operations atomic

2015-07-04T02:49:05Z

commit 5f5bc6b1e2d5a6f827bc860ef2dc5b6f365d1339 upstream. Replacing a xattr consists of doing a lookup for its existing value, delete the current value from the respective leaf, release the search path and then finally insert the new value. This leaves a time window where readers (getxattr, listxattrs) won't see any value for the xattr. Xattrs are used to store ACLs, so this has security implications. This change also fixes 2 other existing issues which were: *) Deleting the old xattr value without verifying first if the new xattr will fit in the existing leaf item (in case multiple xattrs are packed in the same item due to name hash collision); *) Returning -EEXIST when the flag XATTR_CREATE is given and the xattr doesn't exist but we have have an existing item that packs muliple xattrs with the same name hash as the input xattr. In this case we should return ENOSPC. A test case for xfstests follows soon. Thanks to Alexandre Oliva for reporting the non-atomicity of the xattr replace implementation. Reported-by: Alexandre Oliva Signed-off-by: Filipe Manana Signed-off-by: Chris Mason Signed-off-by: Greg Kroah-Hartman

btrfs: fix leak of path in btrfs_find_item

2015-03-06T22:43:32Z

commit 381cf6587f8a8a8e981bc0c1aaaa8859b51dc756 upstream. If btrfs_find_item is called with NULL path it allocates one locally but does not free it. Affected paths are inserting an orphan item for a file and for a subvol root. Move the path allocation to the callers. Fixes: 3f870c289900 ("btrfs: expand btrfs_find_item() to include find_orphan_item functionality") Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman

Btrfs: fix btrfs_search_slot_for_read backwards iteration

2014-01-29T15:06:28Z

If the current path's leaf slot is 0, we do search for the previous leaf (via btrfs_prev_leaf) and set the new path's leaf slot to a value corresponding to the number of items - 1 of the former leaf. Fix this by using the slot set by btrfs_prev_leaf, decrementing it by 1 if it's equal to the leaf's number of items. Use of btrfs_search_slot_for_read() for backward iteration is used in particular by the send feature, which could miss items when the input leaf has less items than its previous leaf. This could be reproduced by running btrfs/007 from xfstests in a loop. Signed-off-by: Filipe David Borba Manana Signed-off-by: Chris Mason

Btrfs: fix to search previous metadata extent item since skinny metadata

2014-01-28T21:20:33Z

There is a bug that using btrfs_previous_item() to search metadata extent item. This is because in btrfs_previous_item(), we need type match, however, since skinny metada was introduced by josef, we may mix this two types. So just use btrfs_previous_item() is not working right. To keep btrfs_previous_item() like normal tree search, i introduce another function btrfs_previous_extent_item(). Signed-off-by: Wang Shilong Signed-off-by: Josef Bacik Signed-off-by: Chris Mason

Btrfs: reduce btree node locking duration on item update

2014-01-28T21:20:11Z

If we do a btree search with the goal of updating an existing item without changing its size (ins_len == 0 and cow == 1), then we never need to hold locks on upper level nodes (even when slot == 0) after we COW their child nodes/leaves, as we won't have node splits or merges in this scenario (that is, no key additions, removals or shifts on any nodes or leaves). Therefore release the locks immediately after COWing the child nodes/leaves while navigating the btree, even if their parent slot is 0, instead of returning a path to the caller with those nodes locked, which would get released only when the caller releases or frees the path (or if it calls btrfs_unlock_up_safe). This is a common scenario, for example when updating inode items in fs trees and block group items in the extent tree. The following benchmarks were performed on a quad core machine with 32Gb of ram, using a leaf/node size of 4Kb (to generate deeper fs trees more quickly). sysbench --test=fileio --file-num=131072 --file-total-size=8G \ --file-test-mode=seqwr --num-threads=512 --file-block-size=8192 \ --max-requests=100000 --file-io-mode=sync [prepare|run] Before this change: 49.85Mb/s (average of 5 runs) After this change: 50.38Mb/s (average of 5 runs) Signed-off-by: Filipe David Borba Manana Signed-off-by: Josef Bacik Signed-off-by: Chris Mason

Btrfs: convert printk to btrfs_ and fix BTRFS prefix

2014-01-28T21:20:05Z

Convert all applicable cases of printk and pr_* to the btrfs_* macros. Fix all uses of the BTRFS prefix. Signed-off-by: Frank Holton Signed-off-by: Josef Bacik Signed-off-by: Chris Mason

Btrfs: fix tree mod logging

2014-01-28T21:20:04Z

While running the test btrfs/004 from xfstests in a loop, it failed about 1 time out of 20 runs in my desktop. The failure happened in the backref walking part of the test, and the test's error message was like this: btrfs/004 93s ... [failed, exit status 1] - output mismatch (see /home/fdmanana/git/hub/xfstests_2/results//btrfs/004.out.bad) --- tests/btrfs/004.out 2013-11-26 18:25:29.263333714 +0000 +++ /home/fdmanana/git/hub/xfstests_2/results//btrfs/004.out.bad 2013-12-10 15:25:10.327518516 +0000 @@ -1,3 +1,8 @@ QA output created by 004 *** test backref walking -*** done +unexpected output from + /home/fdmanana/git/hub/btrfs-progs/btrfs inspect-internal logical-resolve -P 141512704 /home/fdmanana/btrfs-tests/scratch_1 +expected inum: 405, expected address: 454656, file: /home/fdmanana/btrfs-tests/scratch_1/snap1/p0/d6/d3d/d156/fce, got: + ... (Run 'diff -u tests/btrfs/004.out /home/fdmanana/git/hub/xfstests_2/results//btrfs/004.out.bad' to see the entire diff) Ran: btrfs/004 Failures: btrfs/004 Failed 1 of 1 tests But immediately after the test finished, the btrfs inspect-internal command returned the expected output: $ btrfs inspect-internal logical-resolve -P 141512704 /home/fdmanana/btrfs-tests/scratch_1 inode 405 offset 454656 root 258 inode 405 offset 454656 root 5 It turned out this was because the btrfs_search_old_slot() calls performed during backref walking (backref.c:__resolve_indirect_ref) were not finding anything. The reason for this turned out to be that the tree mod logging code was not logging some node multi-step operations atomically, therefore btrfs_search_old_slot() callers iterated often over an incomplete tree that wasn't fully consistent with any tree state from the past. Besides missing items, this often (but not always) resulted in -EIO errors during old slot searches, reported in dmesg like this: [ 4299.933936] ------------[ cut here ]------------ [ 4299.933949] WARNING: CPU: 0 PID: 23190 at fs/btrfs/ctree.c:1343 btrfs_search_old_slot+0x57b/0xab0 [btrfs]() [ 4299.933950] Modules linked in: btrfs raid6_pq xor pci_stub vboxpci(O) vboxnetadp(O) vboxnetflt(O) vboxdrv(O) bnep rfcomm bluetooth parport_pc ppdev binfmt_misc joydev snd_hda_codec_h [ 4299.933977] CPU: 0 PID: 23190 Comm: btrfs Tainted: G W O 3.12.0-fdm-btrfs-next-16+ #70 [ 4299.933978] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./Z77 Pro4, BIOS P1.50 09/04/2012 [ 4299.933979] 000000000000053f ffff8806f3fd98f8 ffffffff8176d284 0000000000000007 [ 4299.933982] 0000000000000000 ffff8806f3fd9938 ffffffff8104a81c ffff880659c64b70 [ 4299.933984] ffff880659c643d0 ffff8806599233d8 ffff880701e2e938 0000160000000000 [ 4299.933987] Call Trace: [ 4299.933991] [] dump_stack+0x55/0x76 [ 4299.933994] [] warn_slowpath_common+0x8c/0xc0 [ 4299.933997] [] warn_slowpath_null+0x1a/0x20 [ 4299.934003] [] btrfs_search_old_slot+0x57b/0xab0 [btrfs] [ 4299.934005] [] ? _raw_read_unlock+0x2b/0x50 [ 4299.934010] [] ? __tree_mod_log_search+0x81/0xc0 [btrfs] [ 4299.934019] [] __resolve_indirect_refs+0x130/0x5f0 [btrfs] [ 4299.934027] [] ? free_extent_buffer+0x61/0xc0 [btrfs] [ 4299.934034] [] find_parent_nodes+0x1fc/0xe40 [btrfs] [ 4299.934042] [] ? defrag_lookup_extent+0xe0/0xe0 [btrfs] [ 4299.934048] [] ? defrag_lookup_extent+0xe0/0xe0 [btrfs] [ 4299.934056] [] iterate_extent_inodes+0xe0/0x250 [btrfs] [ 4299.934058] [] ? _raw_spin_unlock+0x2b/0x50 [ 4299.934065] [] iterate_inodes_from_logical+0x92/0xb0 [btrfs] [ 4299.934071] [] ? defrag_lookup_extent+0xe0/0xe0 [btrfs] [ 4299.934078] [] btrfs_ioctl+0xf65/0x1f60 [btrfs] [ 4299.934080] [] ? handle_mm_fault+0x278/0xb00 [ 4299.934083] [] ? up_read+0x23/0x40 [ 4299.934085] [] ? __do_page_fault+0x20c/0x5a0 [ 4299.934088] [] do_vfs_ioctl+0x96/0x570 [ 4299.934090] [] ? error_sti+0x5/0x6 [ 4299.934093] [] ? trace_hardirqs_off_caller+0x28/0xd0 [ 4299.934096] [] ? retint_swapgs+0xe/0x13 [ 4299.934098] [] SyS_ioctl+0x91/0xb0 [ 4299.934100] [] ? trace_hardirqs_on_thunk+0x3a/0x3f [ 4299.934102] [] system_call_fastpath+0x16/0x1b [ 4299.934102] [] system_call_fastpath+0x16/0x1b [ 4299.934104] ---[ end trace 48f0cfc902491414 ]--- [ 4299.934378] btrfs bad fsid on block 0 These tree mod log operations that must be performed atomically, tree_mod_log_free_eb, tree_mod_log_eb_copy, tree_mod_log_insert_root and tree_mod_log_insert_move, used to be performed atomically before the following commit: c8cc6341653721b54760480b0d0d9b5f09b46741 (Btrfs: stop using GFP_ATOMIC for the tree mod log allocations) That change removed the atomicity of such operations. This patch restores the atomicity while still not doing the GFP_ATOMIC allocations of tree_mod_elem structures, so it has to do the allocations using GFP_NOFS before acquiring the mod log lock. This issue has been experienced by several users recently, such as for example: http://www.spinics.net/lists/linux-btrfs/msg28574.html After running the btrfs/004 test for 679 consecutive iterations with this patch applied, I didn't ran into the issue anymore. Cc: stable@vger.kernel.org Signed-off-by: Filipe David Borba Manana Signed-off-by: Josef Bacik Signed-off-by: Chris Mason

Btrfs: return immediately if tree log mod is not necessary

2014-01-28T21:19:56Z

In ctree.c:tree_mod_log_set_node_key() we were calling __tree_mod_log_insert_key() even when the modification doesn't need to be logged. This would allocate a tree_mod_elem structure, fill it and pass it to __tree_mod_log_insert(), which would just acquire the tree mod log write lock and then free the tree_mod_elem structure and return (that is, a no-op). Therefore call tree_mod_log_insert() instead of __tree_mod_log_insert() which just returns immediately if the modification doesn't need to be logged (without allocating the structure, fill it, acquire write lock, free structure). Signed-off-by: Filipe David Borba Manana Signed-off-by: Josef Bacik Signed-off-by: Chris Mason

Btrfs: more efficient push_leaf_right

2014-01-28T21:19:53Z

Currently when finding the leaf to insert a key into a btree, if the leaf doesn't have enough space to store the item we attempt to move off some items from our leaf to its right neighbor leaf, and if this fails to create enough free space in our leaf, we try to move off more items to the left neighbor leaf as well. When trying to move off items to the right neighbor leaf, if it has enough room to store the new key but not not enough room to move off at least one item from our target leaf, __push_leaf_right returns 1 and we have to attempt to move items to the left neighbor (push_leaf_left function) without touching the right neighbor leaf. For the case where the right leaf has enough room to store at least 1 item from our leaf, we end up modifying (and dirtying) both our leaf and the right leaf. This is non-optimal for the case where the new key is greater than any key in our target leaf because it can be inserted at slot 0 of the right neighbor leaf and we don't need to touch our leaf at all nor to attempt to move off items to the left neighbor leaf. Therefore this change just selects the right neighbor leaf as our new target leaf if it has enough room for the new key without modifying our initial target leaf - we do this only if the new key is higher than any key in the initial target leaf. While running the following test, push_leaf_right was called by split_leaf 4802 times. Out of those 4802 calls, for 2571 calls (53.5%) we hit this special case (right leaf has enough room and new key is higher than any key in the initial target leaf). Test: sysbench --test=fileio --file-num=512 --file-total-size=5G \ --file-test-mode=[seqwr|rndwr] --num-threads=512 --file-block-size=8192 \ --max-requests=100000 --file-io-mode=sync [prepare|run] Results: sequential writes Throughput before this change: 65.71Mb/sec (average of 10 runs) Throughput after this change: 66.58Mb/sec (average of 10 runs) random writes Throughput before this change: 10.75Mb/sec (average of 10 runs) Throughput after this change: 11.56Mb/sec (average of 10 runs) Signed-off-by: Filipe David Borba Manana Reviewed-by: Liu Bo Signed-off-by: Josef Bacik Signed-off-by: Chris Mason

Btrfs: try harder to avoid btree node splits

2014-01-28T21:19:46Z

When attempting to move items from our target leaf to its neighbor leaves (right and left), we only need to free data_size - free_space bytes from our leaf in order to add the new item (which has size of data_size bytes). Therefore attempt to move items to the right and left leaves if they have at least data_size - free_space bytes free, instead of data_size bytes free. After 5 runs of the following test, I got a smaller number of btree node splits overall: sysbench --test=fileio --file-num=512 --file-total-size=5G \ --file-test-mode=seqwr --num-threads=512 \ --file-block-size=8192 --max-requests=100000 --file-io-mode=sync Before this change: * 6171 splits (average of 5 test runs) * 61.508Mb/sec of throughput (average of 5 test runs) After this change: * 6036 splits (average of 5 test runs) * 63.533Mb/sec of throughput (average of 5 test runs) An ideal test would not just have multiple threads/processes writing to a file (insertion of file extent items) but also do other operations that result in insertion of items with varied sizes, like file/directory creations, creation of links, symlinks, xattrs, etc. Signed-off-by: Filipe David Borba Manana Signed-off-by: Josef Bacik Signed-off-by: Chris Mason