- 17 Dec, 2015 4 commits
-
-
Filipe Manana authored
If readpages() (triggered by defrag or buffered reads) is called while a direct IO write is in progress, we have a small time window where we can deadlock, resulting in traces like the following being generated: [84723.212993] INFO: task fio:2849 blocked for more than 120 seconds. [84723.214310] Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [84723.215640] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [84723.217313] fio D ffff88023ec75218 0 2849 2835 0x00000000 [84723.218778] ffff880122dfb6e8 0000000000000092 0000000000000000 ffff88023ec75200 [84723.220458] ffff88000e05d2c0 ffff880122dfc000 ffff88023ec75200 7fffffffffffffff [84723.230597] 0000000000000002 ffffffff8147891a ffff880122dfb700 ffffffff8147856a [84723.232085] Call Trace: [84723.232625] [<ffffffff8147891a>] ? bit_wait+0x3c/0x3c [84723.233529] [<ffffffff8147856a>] schedule+0x7d/0x95 [84723.234398] [<ffffffff8147baa3>] schedule_timeout+0x43/0x10b [84723.235384] [<ffffffff810f82eb>] ? time_hardirqs_on+0x15/0x28 [84723.236426] [<ffffffff8108a23d>] ? trace_hardirqs_on+0xd/0xf [84723.237502] [<ffffffff810af8a3>] ? read_seqcount_begin.constprop.20+0x57/0x6d [84723.238807] [<ffffffff8108a09b>] ? trace_hardirqs_on_caller+0x16/0x1ab [84723.242012] [<ffffffff8108a23d>] ? trace_hardirqs_on+0xd/0xf [84723.243064] [<ffffffff810af2ad>] ? timekeeping_get_ns+0xe/0x33 [84723.244116] [<ffffffff810afa2e>] ? ktime_get+0x41/0x52 [84723.245029] [<ffffffff81477cff>] io_schedule_timeout+0xb7/0x12b [84723.245942] [<ffffffff81477cff>] ? io_schedule_timeout+0xb7/0x12b [84723.246596] [<ffffffff81478953>] bit_wait_io+0x39/0x45 [84723.247503] [<ffffffff81478b93>] __wait_on_bit_lock+0x49/0x8d [84723.248540] [<ffffffff8111684f>] __lock_page+0x66/0x68 [84723.249558] [<ffffffff81081c9b>] ? autoremove_wake_function+0x3a/0x3a [84723.250844] [<ffffffff81124a04>] lock_page+0x2c/0x2f [84723.251871] [<ffffffff81124afc>] invalidate_inode_pages2_range+0xf5/0x2aa [84723.253274] [<ffffffff81117c34>] ? filemap_fdatawait_range+0x12d/0x146 [84723.254757] [<ffffffff81118191>] ? filemap_fdatawrite_range+0x13/0x15 [84723.256378] [<ffffffffa05139a2>] btrfs_get_blocks_direct+0x1b0/0x664 [btrfs] [84723.258556] [<ffffffff8119e3f9>] ? submit_page_section+0x7b/0x111 [84723.260064] [<ffffffff8119eb90>] do_blockdev_direct_IO+0x658/0xbdb [84723.261479] [<ffffffffa05137f2>] ? btrfs_page_exists_in_range+0x1a9/0x1a9 [btrfs] [84723.262961] [<ffffffffa050a8a6>] ? btrfs_writepage_start_hook+0xce/0xce [btrfs] [84723.264449] [<ffffffff8119f144>] __blockdev_direct_IO+0x31/0x33 [84723.265614] [<ffffffff8119f144>] ? __blockdev_direct_IO+0x31/0x33 [84723.266769] [<ffffffffa050a8a6>] ? btrfs_writepage_start_hook+0xce/0xce [btrfs] [84723.268264] [<ffffffffa050935d>] btrfs_direct_IO+0x1b9/0x259 [btrfs] [84723.270954] [<ffffffffa050a8a6>] ? btrfs_writepage_start_hook+0xce/0xce [btrfs] [84723.272465] [<ffffffff8111878c>] generic_file_direct_write+0xb3/0x128 [84723.273734] [<ffffffffa051955c>] btrfs_file_write_iter+0x228/0x404 [btrfs] [84723.275101] [<ffffffff8116ca6f>] __vfs_write+0x7c/0xa5 [84723.276200] [<ffffffff8116cfab>] vfs_write+0xa0/0xe4 [84723.277298] [<ffffffff8116d79d>] SyS_write+0x50/0x7e [84723.278327] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f [84723.279595] INFO: lockdep is turned off. [84723.379035] INFO: task btrfs:2923 blocked for more than 120 seconds. [84723.380323] Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [84723.381608] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [84723.383003] btrfs D ffff88023ed75218 0 2923 2859 0x00000000 [84723.384277] ffff88001311f860 0000000000000082 ffff88001311f840 ffff88023ed75200 [84723.385748] ffff88012c6751c0 ffff880013120000 ffff88012042fe68 ffff88012042fe30 [84723.387152] ffff880221571c88 0000000000000001 ffff88001311f878 ffffffff8147856a [84723.388620] Call Trace: [84723.389105] [<ffffffff8147856a>] schedule+0x7d/0x95 [84723.391882] [<ffffffffa051da32>] btrfs_start_ordered_extent+0x161/0x1fa [btrfs] [84723.393718] [<ffffffff81081c61>] ? signal_pending_state+0x31/0x31 [84723.395659] [<ffffffffa0522c5b>] __do_contiguous_readpages.constprop.21+0x81/0xdc [btrfs] [84723.397383] [<ffffffffa050ac96>] ? btrfs_submit_direct+0x3f0/0x3f0 [btrfs] [84723.398852] [<ffffffffa0522da3>] __extent_readpages.constprop.20+0xed/0x100 [btrfs] [84723.400561] [<ffffffff81123f6c>] ? __lru_cache_add+0x5d/0x72 [84723.401787] [<ffffffffa0523896>] extent_readpages+0x111/0x1a7 [btrfs] [84723.403121] [<ffffffffa050ac96>] ? btrfs_submit_direct+0x3f0/0x3f0 [btrfs] [84723.404583] [<ffffffffa05088fa>] btrfs_readpages+0x1f/0x21 [btrfs] [84723.406007] [<ffffffff811226df>] __do_page_cache_readahead+0x168/0x1f4 [84723.407502] [<ffffffff81122988>] ondemand_readahead+0x21d/0x22e [84723.408937] [<ffffffff81122988>] ? ondemand_readahead+0x21d/0x22e [84723.410487] [<ffffffff81122af1>] page_cache_sync_readahead+0x3d/0x3f [84723.411710] [<ffffffffa0535388>] btrfs_defrag_file+0x419/0xaaf [btrfs] [84723.413007] [<ffffffffa0531db0>] ? kzalloc+0xf/0x11 [btrfs] [84723.414085] [<ffffffffa0535b43>] btrfs_ioctl_defrag+0x125/0x14e [btrfs] [84723.415307] [<ffffffffa0536753>] btrfs_ioctl+0x746/0x24c6 [btrfs] [84723.416532] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [84723.417731] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [84723.418699] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [84723.421532] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [84723.422629] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [84723.423712] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [84723.424801] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [84723.425968] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [84723.427063] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [84723.428138] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f Consider the following logical and physical file layout: logical: ... [ prealloc extent A ] [ prealloc extent B ] [ extent C ] ... 4K 8K 16K physical: ... 12853248 12857344 1103101952 ... (= 12853248 + 4K) Extents A and B are physically adjacent. The following diagram shows a sequence of events that lead to the deadlock when we attempt to do a direct IO write against the file range [4K, 16K[ and a defrag is triggered simultaneously. CPU 1 CPU 2 btrfs_direct_IO() btrfs_get_blocks_direct() creates ordered extent A, covering the 4k prealloc extent A (range [4K, 8K[) btrfs_defrag_file() page_cache_sync_readahead([0K, 1M[) btrfs_readpages() extent_readpages() locks all pages in the file range [0K, 128K[ through calls to add_to_page_cache_lru() __do_contiguous_readpages() finds ordered extent A waits for it to complete btrfs_get_blocks_direct() called again lock_extent_direct(range [8K, 16K[) finds a page in range [8K, 16K[ through btrfs_page_exists_in_range() invalidate_inode_pages2_range([8K, 16K[) --> tries to lock pages that are already locked by the task at CPU 2 --> our task, running __blockdev_direct_IO(), hangs waiting to lock the pages and the submit bio callback, btrfs_submit_direct(), ends up never being called, resulting in the ordered extent A never completing (because a corresponding bio is never submitted) and CPU 2 will wait for it forever while holding the pages locked ---> deadlock! Fix this by removing the page invalidation approach when attempting to lock the range for IO from the callback btrfs_get_blocks_direct() and falling back buffered IO. This was a rare case anyway and well behaved applications do not mix concurrent direct IO writes with buffered reads anyway, being a concurrent defrag the only normal case that could lead to the deadlock. Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
Commit 61de718f ("Btrfs: fix memory corruption on failure to submit bio for direct IO") fixed problems with the error handling code after we fail to submit a bio for direct IO. However there were 2 problems that it did not address when the failure is due to memory allocation failures for direct IO writes: 1) We considered that there could be only one ordered extent for the whole IO range, which is not always true, as we can have multiple; 2) It did not set the bit BTRFS_ORDERED_IO_DONE in the ordered extent, which can make other tasks running btrfs_wait_logged_extents() hang forever, since they wait for that bit to be set. The general assumption is that regardless of an error, the BTRFS_ORDERED_IO_DONE is always set and it precedes setting the bit BTRFS_ORDERED_COMPLETE. Fix these issues by moving part of the btrfs_endio_direct_write() handler into a new helper function and having that new helper function called when we fail to allocate memory to submit the bio (and its private object) for a direct IO write. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
-
Filipe Manana authored
When a transaction is aborted, or its commit fails before writing the new superblock and calling btrfs_finish_extent_commit(), we leak reference counts on the block groups attached to the transaction's delete_bgs list, because btrfs_finish_extent_commit() is never called for those two cases. Fix this by dropping their references at btrfs_put_transaction(), which is called when transactions are aborted (by making the transaction kthread commit the transaction) or if their commits fail. Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
During the final phase of a device replace operation, I ran into a transaction abort that resulted in the following trace: [23919.655368] WARNING: CPU: 10 PID: 30175 at fs/btrfs/extent-tree.c:9843 btrfs_create_pending_block_groups+0x15e/0x1ab [btrfs]() [23919.664742] BTRFS: Transaction aborted (error -2) [23919.665749] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 parport psmouse acpi_cpufreq processor i2c_core evdev microcode pcspkr button serio_raw ext4 crc16 jbd2 mbcache sd_mod sg sr_mod cdrom virtio_scsi ata_generic ata_piix virtio_pci floppy virtio_ring libata e1000 virtio scsi_mod [last unloaded: btrfs] [23919.679442] CPU: 10 PID: 30175 Comm: fsstress Not tainted 4.3.0-rc5-btrfs-next-17+ #1 [23919.682392] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [23919.689151] 0000000000000000 ffff8804020cbb50 ffffffff812566f4 ffff8804020cbb98 [23919.692604] ffff8804020cbb88 ffffffff8104d0a6 ffffffffa03eea69 ffff88041b678a48 [23919.694230] ffff88042ac38000 ffff88041b678930 00000000fffffffe ffff8804020cbbf0 [23919.696716] Call Trace: [23919.698669] [<ffffffff812566f4>] dump_stack+0x4e/0x79 [23919.700597] [<ffffffff8104d0a6>] warn_slowpath_common+0x9f/0xb8 [23919.701958] [<ffffffffa03eea69>] ? btrfs_create_pending_block_groups+0x15e/0x1ab [btrfs] [23919.703612] [<ffffffff8104d107>] warn_slowpath_fmt+0x48/0x50 [23919.705047] [<ffffffffa03eea69>] btrfs_create_pending_block_groups+0x15e/0x1ab [btrfs] [23919.706967] [<ffffffffa0402097>] __btrfs_end_transaction+0x84/0x2dd [btrfs] [23919.708611] [<ffffffffa0402300>] btrfs_end_transaction+0x10/0x12 [btrfs] [23919.710099] [<ffffffffa03ef0b8>] btrfs_alloc_data_chunk_ondemand+0x121/0x28b [btrfs] [23919.711970] [<ffffffffa0413025>] btrfs_fallocate+0x7d3/0xc6d [btrfs] [23919.713602] [<ffffffff8108b78f>] ? lock_acquire+0x10d/0x194 [23919.714756] [<ffffffff81086dbc>] ? percpu_down_read+0x51/0x78 [23919.716155] [<ffffffff8116ef1d>] ? __sb_start_write+0x5f/0xb0 [23919.718918] [<ffffffff8116ef1d>] ? __sb_start_write+0x5f/0xb0 [23919.724170] [<ffffffff8116b579>] vfs_fallocate+0x170/0x1ff [23919.725482] [<ffffffff8117c1d7>] ioctl_preallocate+0x89/0x9b [23919.726790] [<ffffffff8117c5ef>] do_vfs_ioctl+0x406/0x4e6 [23919.728428] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [23919.729642] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [23919.730782] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [23919.731847] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f [23919.733330] ---[ end trace 166ef301a335832a ]--- This is due to a race between device replace and chunk allocation, which the following diagram illustrates: CPU 1 CPU 2 btrfs_dev_replace_finishing() at this point dev_replace->tgtdev->devid == BTRFS_DEV_REPLACE_DEVID (0ULL) ... btrfs_start_transaction() btrfs_commit_transaction() btrfs_fallocate() btrfs_alloc_data_chunk_ondemand() btrfs_join_transaction() --> starts a new transaction do_chunk_alloc() lock fs_info->chunk_mutex btrfs_alloc_chunk() --> creates extent map for the new chunk with em->bdev->map->stripes[i]->dev->devid == X (X > 0) --> extent map is added to fs_info->mapping_tree --> initial phase of bg A allocation completes unlock fs_info->chunk_mutex lock fs_info->chunk_mutex btrfs_dev_replace_update_device_in_mapping_tree() --> iterates fs_info->mapping_tree and replaces the device in every extent map's map->stripes[] with dev_replace->tgtdev, which still has an id of 0ULL (BTRFS_DEV_REPLACE_DEVID) btrfs_end_transaction() btrfs_create_pending_block_groups() --> starts final phase of bg A creation (update device, extent, and chunk trees, etc) btrfs_finish_chunk_alloc() btrfs_update_device() --> attempts to update a device item with ID == 0ULL (BTRFS_DEV_REPLACE_DEVID) which is the current ID of bg A's em->bdev->map->stripes[i]->dev->devid --> doesn't find such item returns -ENOENT --> the device id should have been X and not 0ULL got -ENOENT from btrfs_finish_chunk_alloc() and aborts current transaction finishes setting up the target device, namely it sets tgtdev->devid to the value of srcdev->devid, which is X (and X > 0) frees the srcdev unlock fs_info->chunk_mutex So fix this by taking the device list mutex when processing the chunk's extent map stripes to update the device items. This avoids getting the wrong device id and use-after-free problems if the task finishing a chunk allocation grabs the replaced device, which is freed while the dev replace task is holding the device list mutex. This happened while running fstest btrfs/071. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
-
- 15 Dec, 2015 3 commits
-
-
Chris Mason authored
Merge branch 'for-chris-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/fdmanana/linux into for-linus-4.4
-
Chris Mason authored
prepare_pages() may end up calling prepare_uptodate_page() twice if our write only spans a single page. But if the first call returns an error, our page will be unlocked and its not safe to call it again. This bug goes all the way back to 2011, and it's not something commonly hit. While we're here, add a more explicit check for the page being truncated away. The bare lock_page() alone is protected only by good thoughts and i_mutex, which we're sure to regret eventually. Reported-by: Dave Jones <dsj@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Chris Mason authored
Dave Jones found a warning from kasan in setup_cluster_bitmaps() ================================================================== BUG: KASAN: stack-out-of-bounds in setup_cluster_bitmap+0xc4/0x5a0 at addr ffff88039bef6828 Read of size 8 by task nfsd/1009 page:ffffea000e6fbd80 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x8000000000000000() page dumped because: kasan: bad access detected CPU: 1 PID: 1009 Comm: nfsd Tainted: G W 4.4.0-rc3-backup-debug+ #1 ffff880065647b50 000000006bb712c2 ffff88039bef6640 ffffffffa680a43e 0000004559c00000 ffff88039bef66c8 ffffffffa62638d1 ffffffffa61121c0 ffff8803a5769de8 0000000000000296 ffff8803a5769df0 0000000000046280 Call Trace: [<ffffffffa680a43e>] dump_stack+0x4b/0x6d [<ffffffffa62638d1>] kasan_report_error+0x501/0x520 [<ffffffffa61121c0>] ? debug_show_all_locks+0x1e0/0x1e0 [<ffffffffa6263948>] kasan_report+0x58/0x60 [<ffffffffa6814b00>] ? rb_last+0x10/0x40 [<ffffffffa66f8af4>] ? setup_cluster_bitmap+0xc4/0x5a0 [<ffffffffa6262ead>] __asan_load8+0x5d/0x70 [<ffffffffa66f8af4>] setup_cluster_bitmap+0xc4/0x5a0 [<ffffffffa66f675a>] ? setup_cluster_no_bitmap+0x6a/0x400 [<ffffffffa66fcd16>] btrfs_find_space_cluster+0x4b6/0x640 [<ffffffffa66fc860>] ? btrfs_alloc_from_cluster+0x4e0/0x4e0 [<ffffffffa66fc36e>] ? btrfs_return_cluster_to_free_space+0x9e/0xb0 [<ffffffffa702dc37>] ? _raw_spin_unlock+0x27/0x40 [<ffffffffa666a1a1>] find_free_extent+0xba1/0x1520 Andrey noticed this was because we were doing list_first_entry on a list that might be empty. Rework the tests a bit so we don't do that. Signed-off-by: Chris Mason <clm@fb.com> Reprorted-by: Andrey Ryabinin <ryabinin.a.a@gmail.com> Reported-by: Dave Jones <dsj@fb.com>
-
- 10 Dec, 2015 3 commits
-
-
Holger Hoffstätte authored
When an inconsistent space cache is detected during loading we log a warning that users frequently mistake as instruction to invalidate the cache manually, even though this is not required. Fix the message to indicate that the cache will be rebuilt automatically. Signed-off-by: Holger Hoffstätte <holger.hoffstaette@googlemail.com> Acked-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
If we fail to allocate a new data chunk, we were jumping to the error path without release the transaction handle we got before. Fix this by always releasing it before doing the jump. Fixes: 2c9fe835 ("btrfs: Fix lost-data-profile caused by balance bg") Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
As of my previous change titled "Btrfs: fix scrub preventing unused block groups from being deleted", the following warning at extent-tree.c:btrfs_delete_unused_bgs() can be hit when we mount the a filesysten with "-o discard": 10263 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) 10264 { (...) 10405 if (trimming) { 10406 WARN_ON(!list_empty(&block_group->bg_list)); 10407 spin_lock(&trans->transaction->deleted_bgs_lock); 10408 list_move(&block_group->bg_list, 10409 &trans->transaction->deleted_bgs); 10410 spin_unlock(&trans->transaction->deleted_bgs_lock); 10411 btrfs_get_block_group(block_group); 10412 } (...) This happens because scrub can now add back the block group to the list of unused block groups (fs_info->unused_bgs). This is dangerous because we are moving the block group from the unused block groups list to the list of deleted block groups without holding the lock that protects the source list (fs_info->unused_bgs_lock). The following diagram illustrates how this happens: CPU 1 CPU 2 cleaner_kthread() btrfs_delete_unused_bgs() sees bg X in list fs_info->unused_bgs deletes bg X from list fs_info->unused_bgs scrub_enumerate_chunks() searches device tree using its commit root finds device extent for block group X gets block group X from the tree fs_info->block_group_cache_tree (via btrfs_lookup_block_group()) sets bg X to RO (again) scrub_chunk(bg X) sets bg X back to RW mode adds bg X to the list fs_info->unused_bgs again, since it's still unused and currently not in that list sets bg X to RO mode btrfs_remove_chunk(bg X) --> discard is enabled and bg X is in the fs_info->unused_bgs list again so the warning is triggered --> we move it from that list into the transaction's delete_bgs list, but we can have another task currently manipulating the first list (fs_info->unused_bgs) Fix this by using the same lock (fs_info->unused_bgs_lock) to protect both the list of unused block groups and the list of deleted block groups. This makes it safe and there's not much worry for more lock contention, as this lock is seldom used and only the cleaner kthread adds elements to the list of deleted block groups. The warning goes away too, as this was previously an impossible case (and would have been better a BUG_ON/ASSERT) but it's not impossible anymore. Reproduced with fstest btrfs/073 (using MOUNT_OPTIONS="-o discard"). Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
- 25 Nov, 2015 14 commits
-
-
Holger Hoffstätte authored
There's a regression in 4.4-rc since commit bc309467 (btrfs: extend balance filter usage to take minimum and maximum) in that existing (non-ranged) balance with -dusage=x no longer works; all chunks are skipped. After staring at the code for a while and wondering why a non-ranged balance would even need min and max thresholds (..which then were not set correctly, leading to the bug) I realized that the only problem was the fact that the filter functions were named wrong, thanks to patching copypasta. Simply renaming both functions lets the existing btrfs-progs call balance with -dusage=x and now the non-ranged filter function is invoked, properly using only a single chunk limit. Signed-off-by: Holger Hoffstätte <holger.hoffstaette@googlemail.com> Fixes: bc309467 ("btrfs: extend balance filter usage to take minimum and maximum") Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Mark Fasheh authored
Commit 0ed4792a ('btrfs: qgroup: Switch to new extent-oriented qgroup mechanism.') removed our qgroup accounting during btrfs_drop_snapshot(). Predictably, this results in qgroup numbers going bad shortly after a snapshot is removed. Fix this by adding a dirty extent record when we encounter extents during our shared subtree walk. This effectively restores the functionality we had with the original shared subtree walking code in 1152651a (btrfs: qgroup: account shared subtrees during snapshot delete). The idea with the original patch (and this one) is that shared subtrees can get skipped during drop_snapshot. The shared subtree walk then allows us a chance to visit those extents and add them to the qgroup work for later processing. This ultimately makes the accounting for drop snapshot work. The new qgroup code nicely handles all the other extents during the tree walk via the ref dec/inc functions so we don't have to add actions beyond what we had originally. Signed-off-by: Mark Fasheh <mfasheh@suse.de> Signed-off-by: Chris Mason <clm@fb.com>
-
Josef Bacik authored
The backref code will look up the fs_root we're trying to resolve our indirect refs for, unfortunately we use btrfs_read_fs_root_no_name, which returns -ENOENT if the ref is 0. This isn't helpful for the qgroup stuff with snapshot delete as it won't be able to search down the snapshot we are deleting, which will cause us to miss roots. So use btrfs_get_fs_root and send false for check_ref so we can always get the root we're looking for. Thanks, Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Mark Fasheh <mfasheh@suse.de> Signed-off-by: Chris Mason <clm@fb.com>
-
Justin Maggard authored
There's a race condition that leads to a NULL pointer dereference if you disable quotas while a quota rescan is running. To fix this, we just need to wait for the quota rescan worker to actually exit before tearing down the quota structures. Signed-off-by: Justin Maggard <jmaggard@netgear.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Filipe Manana authored
When a block group becomes unused and the cleaner kthread is currently running, we can end up getting the current transaction aborted with error -ENOENT when we try to commit the transaction, leading to the following trace: [59779.258768] WARNING: CPU: 3 PID: 5990 at fs/btrfs/extent-tree.c:3740 btrfs_write_dirty_block_groups+0x17c/0x214 [btrfs]() [59779.272594] BTRFS: Transaction aborted (error -2) (...) [59779.291137] Call Trace: [59779.291621] [<ffffffff812566f4>] dump_stack+0x4e/0x79 [59779.292543] [<ffffffff8104d0a6>] warn_slowpath_common+0x9f/0xb8 [59779.293435] [<ffffffffa04cb81f>] ? btrfs_write_dirty_block_groups+0x17c/0x214 [btrfs] [59779.295000] [<ffffffff8104d107>] warn_slowpath_fmt+0x48/0x50 [59779.296138] [<ffffffffa04c2721>] ? write_one_cache_group.isra.32+0x77/0x82 [btrfs] [59779.297663] [<ffffffffa04cb81f>] btrfs_write_dirty_block_groups+0x17c/0x214 [btrfs] [59779.299141] [<ffffffffa0549b0d>] commit_cowonly_roots+0x1de/0x261 [btrfs] [59779.300359] [<ffffffffa04dd5b6>] btrfs_commit_transaction+0x4c4/0x99c [btrfs] [59779.301805] [<ffffffffa04b5df4>] btrfs_sync_fs+0x145/0x1ad [btrfs] [59779.302893] [<ffffffff81196634>] sync_filesystem+0x7f/0x93 (...) [59779.318186] ---[ end trace 577e2daff90da33a ]--- The following diagram illustrates a sequence of steps leading to this problem: CPU 1 CPU 2 <at transaction N> adds bg A to list fs_info->unused_bgs adds bg B to list fs_info->unused_bgs <transaction kthread commits transaction N and wakes up the cleaner kthread> cleaner kthread delete_unused_bgs() sees bg A in list fs_info->unused_bgs btrfs_start_transaction() <transaction N + 1 starts> deletes bg A update_block_group(bg C) --> adds bg C to list fs_info->unused_bgs deletes bg B sees bg C in the list fs_info->unused_bgs btrfs_remove_chunk(bg C) btrfs_remove_block_group(bg C) --> checks if the block group is in a dirty list, and because it isn't now, it does nothing --> the block group item is deleted from the extent tree --> adds bg C to list transaction->dirty_bgs some task calls btrfs_commit_transaction(t N + 1) commit_cowonly_roots() btrfs_write_dirty_block_groups() --> sees bg C in cur_trans->dirty_bgs --> calls write_one_cache_group() which returns -ENOENT because it did not find the block group item in the extent tree --> transaction aborte with -ENOENT because write_one_cache_group() returned that error So fix this by adding a block group to the list of dirty block groups before adding it to the list of unused block groups. This happened on a stress test using fsstress plus concurrent calls to fallocate 20G and truncate (releasing part of the space allocated with fallocate). Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Filipe Manana authored
Currently scrub can race with the cleaner kthread when the later attempts to delete an unused block group, and the result is preventing the cleaner kthread from ever deleting later the block group - unless the block group becomes used and unused again. The following diagram illustrates that race: CPU 1 CPU 2 cleaner kthread btrfs_delete_unused_bgs() gets block group X from fs_info->unused_bgs and removes it from that list scrub_enumerate_chunks() searches device tree using its commit root finds device extent for block group X gets block group X from the tree fs_info->block_group_cache_tree (via btrfs_lookup_block_group()) sets bg X to RO sees the block group is already RO and therefore doesn't delete it nor adds it back to unused list So fix this by making scrub add the block group again to the list of unused block groups if the block group is still unused when it finished scrubbing it and it hasn't been removed already. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Filipe Manana authored
Scrub can race with the cleaner kthread deleting block groups that are unused (and with relocation too) leading to a failure with error -EINVAL that gets returned to user space. The following diagram illustrates how it happens: CPU 1 CPU 2 cleaner kthread btrfs_delete_unused_bgs() gets block group X from fs_info->unused_bgs sets block group to RO btrfs_remove_chunk(bg X) deletes device extents scrub_enumerate_chunks() searches device tree using its commit root finds device extent for block group X gets block group X from the tree fs_info->block_group_cache_tree (via btrfs_lookup_block_group()) sets bg X to RO (again) btrfs_remove_block_group(bg X) deletes block group from fs_info->block_group_cache_tree removes extent map from fs_info->mapping_tree scrub_chunk(offset X) searches fs_info->mapping_tree for extent map starting at offset X --> doesn't find any such extent map --> returns -EINVAL and scrub errors out to userspace with -EINVAL Fix this by dealing with an extent map lookup failure as an indicator of block group deletion. Issue reproduced with fstest btrfs/071. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
David Sterba authored
The test btrfs/011 triggers a rcu warning Reviewed-by: Anand Jain <anand.jain@oracle.com> =============================== [ INFO: suspicious RCU usage. ] 4.4.0-rc1-default+ #286 Tainted: G W ------------------------------- fs/btrfs/volumes.c:1977 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 4 locks held by btrfs/28786: 0: (&fs_info->dev_replace.lock_finishing_cancel_unmount){+.+...}, at: [<ffffffffa00bc785>] btrfs_dev_replace_finishing+0x45/0xa00 [btrfs] 1: (uuid_mutex){+.+.+.}, at: [<ffffffffa00bc84f>] btrfs_dev_replace_finishing+0x10f/0xa00 [btrfs] 2: (&fs_devs->device_list_mutex){+.+.+.}, at: [<ffffffffa00bc868>] btrfs_dev_replace_finishing+0x128/0xa00 [btrfs] 3: (&fs_info->chunk_mutex){+.+...}, at: [<ffffffffa00bc87d>] btrfs_dev_replace_finishing+0x13d/0xa00 [btrfs] stack backtrace: CPU: 0 PID: 28786 Comm: btrfs Tainted: G W 4.4.0-rc1-default+ #286 Hardware name: Intel Corporation SandyBridge Platform/To be filled by O.E.M., BIOS ASNBCPT1.86C.0031.B00.1006301607 06/30/2010 0000000000000001 ffff8800a07dfb48 ffffffff8141d47b 0000000000000001 0000000000000001 0000000000000000 ffff8801464a4f00 ffff8800a07dfb78 ffffffff810cd883 ffff880146eb9400 ffff8800a3698600 ffff8800a33fe220 Call Trace: [<ffffffff8141d47b>] dump_stack+0x4f/0x74 [<ffffffff810cd883>] lockdep_rcu_suspicious+0x103/0x140 [<ffffffffa0071261>] btrfs_rm_dev_replace_remove_srcdev+0x111/0x130 [btrfs] [<ffffffff810d354d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff81449536>] ? __percpu_counter_sum+0x66/0x80 [<ffffffffa00bcc15>] btrfs_dev_replace_finishing+0x4d5/0xa00 [btrfs] [<ffffffffa00bc96e>] ? btrfs_dev_replace_finishing+0x22e/0xa00 [btrfs] [<ffffffffa00a8795>] ? btrfs_scrub_dev+0x415/0x6d0 [btrfs] [<ffffffffa003ea69>] ? btrfs_start_transaction+0x9/0x20 [btrfs] [<ffffffffa00bda79>] btrfs_dev_replace_start+0x339/0x590 [btrfs] [<ffffffff81196aa5>] ? __might_fault+0x95/0xa0 [<ffffffffa0078638>] btrfs_ioctl_dev_replace+0x118/0x160 [btrfs] [<ffffffff811409c6>] ? stack_trace_call+0x46/0x70 [<ffffffffa007c914>] ? btrfs_ioctl+0x24/0x1770 [btrfs] [<ffffffffa007ce43>] btrfs_ioctl+0x553/0x1770 [btrfs] [<ffffffff811409c6>] ? stack_trace_call+0x46/0x70 [<ffffffff811d6eb1>] ? do_vfs_ioctl+0x21/0x5a0 [<ffffffff811d6f1c>] do_vfs_ioctl+0x8c/0x5a0 [<ffffffff811e3336>] ? __fget_light+0x86/0xb0 [<ffffffff811e3369>] ? __fdget+0x9/0x20 [<ffffffff811d7451>] ? SyS_ioctl+0x21/0x80 [<ffffffff811d7483>] SyS_ioctl+0x53/0x80 [<ffffffff81b1efd7>] entry_SYSCALL_64_fastpath+0x12/0x6f This is because of unprotected use of rcu_dereference in btrfs_scratch_superblocks. We can't add rcu locks around the whole function because we read the superblock. The fix will use the rcu string buffer directly without the rcu locking. Thi is safe as the device will not go away in the meantime. We're holding the device list mutexes. Restructuring the code to narrow down the rcu section turned out to be impossible, we need to call filp_open (through update_dev_time) on the buffer and this could call kmalloc/__might_sleep. We could call kstrdup with GFP_ATOMIC but it's not absolutely necessary. Fixes: 12b1c263 (Btrfs: enhance btrfs_scratch_superblock to scratch all superblocks) Signed-off-by: David Sterba <dsterba@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhaolei authored
xfstests/011 failed in node with small_size filesystem. Can be reproduced by following script: DEV_LIST="/dev/vdd /dev/vde" DEV_REPLACE="/dev/vdf" do_test() { local mkfs_opt="$1" local size="$2" dmesg -c >/dev/null umount $SCRATCH_MNT &>/dev/null echo mkfs.btrfs -f $mkfs_opt "${DEV_LIST[*]}" mkfs.btrfs -f $mkfs_opt "${DEV_LIST[@]}" || return 1 mount "${DEV_LIST[0]}" $SCRATCH_MNT echo -n "Writing big files" dd if=/dev/urandom of=$SCRATCH_MNT/t0 bs=1M count=1 >/dev/null 2>&1 for ((i = 1; i <= size; i++)); do echo -n . /bin/cp $SCRATCH_MNT/t0 $SCRATCH_MNT/t$i || return 1 done echo echo Start replace btrfs replace start -Bf "${DEV_LIST[0]}" "$DEV_REPLACE" $SCRATCH_MNT || { dmesg return 1 } return 0 } # Set size to value near fs size # for example, 1897 can trigger this bug in 2.6G device. # ./do_test "-d raid1 -m raid1" 1897 System will report replace fail with following warning in dmesg: [ 134.710853] BTRFS: dev_replace from /dev/vdd (devid 1) to /dev/vdf started [ 135.542390] BTRFS: btrfs_scrub_dev(/dev/vdd, 1, /dev/vdf) failed -28 [ 135.543505] ------------[ cut here ]------------ [ 135.544127] WARNING: CPU: 0 PID: 4080 at fs/btrfs/dev-replace.c:428 btrfs_dev_replace_start+0x398/0x440() [ 135.545276] Modules linked in: [ 135.545681] CPU: 0 PID: 4080 Comm: btrfs Not tainted 4.3.0 #256 [ 135.546439] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014 [ 135.547798] ffffffff81c5bfcf ffff88003cbb3d28 ffffffff817fe7b5 0000000000000000 [ 135.548774] ffff88003cbb3d60 ffffffff810a88f1 ffff88002b030000 00000000ffffffe4 [ 135.549774] ffff88003c080000 ffff88003c082588 ffff88003c28ab60 ffff88003cbb3d70 [ 135.550758] Call Trace: [ 135.551086] [<ffffffff817fe7b5>] dump_stack+0x44/0x55 [ 135.551737] [<ffffffff810a88f1>] warn_slowpath_common+0x81/0xc0 [ 135.552487] [<ffffffff810a89e5>] warn_slowpath_null+0x15/0x20 [ 135.553211] [<ffffffff81448c88>] btrfs_dev_replace_start+0x398/0x440 [ 135.554051] [<ffffffff81412c3e>] btrfs_ioctl+0x1d2e/0x25c0 [ 135.554722] [<ffffffff8114c7ba>] ? __audit_syscall_entry+0xaa/0xf0 [ 135.555506] [<ffffffff8111ab36>] ? current_kernel_time64+0x56/0xa0 [ 135.556304] [<ffffffff81201e3d>] do_vfs_ioctl+0x30d/0x580 [ 135.557009] [<ffffffff8114c7ba>] ? __audit_syscall_entry+0xaa/0xf0 [ 135.557855] [<ffffffff810011d1>] ? do_audit_syscall_entry+0x61/0x70 [ 135.558669] [<ffffffff8120d1c1>] ? __fget_light+0x61/0x90 [ 135.559374] [<ffffffff81202124>] SyS_ioctl+0x74/0x80 [ 135.559987] [<ffffffff81809857>] entry_SYSCALL_64_fastpath+0x12/0x6f [ 135.560842] ---[ end trace 2a5c1fc3205abbdd ]--- Reason: When big data writen to fs, the whole free space will be allocated for data chunk. And operation as scrub need to set_block_ro(), and when there is only one metadata chunk in system(or other metadata chunks are all full), the function will try to allocate a new chunk, and failed because no space in device. Fix: When set_block_ro failed for metadata chunk, it is not a problem because scrub_lock paused commit_trancaction in same time, and metadata are always cowed, so the on-the-fly writepages will not write data into same place with scrub/replace. Let replace continue in this case is no problem. Tested by above script, and xfstests/011, plus 100 times xfstests/070. Changelog v1->v2: 1: Add detail comments in source and commit-message. 2: Add dmesg detail into commit-message. 3: Limit return value of -ENOSPC to be passed. All suggested by: Filipe Manana <fdmanana@gmail.com> Suggested-by: Filipe Manana <fdmanana@gmail.com> Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
David Sterba authored
I've accidentally picked an already used number for the enhanced usage filter represented by BTRFS_BALANCE_ARGS_USAGE_RANGE, clashing with BTRFS_BALANCE_ARGS_CONVERT. Introduced during the development phase, no backward compatibility issues. Reported-by: Holger Hoffstätte <holger.hoffstaette@googlemail.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Fixes: bc309467 ("btrfs: extend balance filter usage to take minimum and maximum") Signed-off-by: David Sterba <dsterba@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Filipe Manana authored
We were using only 1 transaction unit when attempting to delete an unused block group but in reality we need 3 + N units, where N corresponds to the number of stripes. We were accounting only for the addition of the orphan item (for the block group's free space cache inode) but we were not accounting that we need to delete one block group item from the extent tree, one free space item from the tree of tree roots and N device extent items from the device tree. While one unit is not enough, it worked most of the time because for each single unit we are too pessimistic and assume an entire tree path, with the highest possible heigth (8), needs to be COWed with eventual node splits at every possible level in the tree, so there was usually enough reserved space for removing all the items and adding the orphan item. However after adding the orphan item, writepages() can by called by the VM subsystem against the btree inode when we are under memory pressure, which causes writeback to start for the nodes we COWed before, this forces the operation to remove the free space item to COW again some (or all of) the same nodes (in the tree of tree roots). Even without writepages() being called, we could fail with ENOSPC because these items are located in multiple trees and one of them might have a higher heigth and require node/leaf splits at many levels, exhausting all the reserved space before removing all the items and adding the orphan. In the kernel 4.0 release, commit 3d84be79 ("Btrfs: fix BUG_ON in btrfs_orphan_add() when delete unused block group"), we attempted to fix a BUG_ON due to ENOSPC when trying to add the orphan item by making the cleaner kthread reserve one transaction unit before attempting to remove the block group, but this was not enough. We had a couple user reports still hitting the same BUG_ON after 4.0, like Stefan Priebe's report on a 4.2-rc6 kernel for example: http://www.spinics.net/lists/linux-btrfs/msg46070.html So fix this by reserving all the necessary units of metadata. Reported-by: Stefan Priebe <s.priebe@profihost.ag> Fixes: 3d84be79 ("Btrfs: fix BUG_ON in btrfs_orphan_add() when delete unused block group") Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Filipe Manana authored
It's possible to reach a state where the cleaner kthread isn't able to start a transaction to delete an unused block group due to lack of enough free metadata space and due to lack of unallocated device space to allocate a new metadata block group as well. If this happens try to use space from the global block group reserve just like we do for unlink operations, so that we don't reach a permanent state where starting a transaction for filesystem operations (file creation, renames, etc) keeps failing with -ENOSPC. Such an unfortunate state was observed on a machine where over a dozen unused data block groups existed and the cleaner kthread was failing to delete them due to ENOSPC error when attempting to start a transaction, and even running balance with a -dusage=0 filter failed with ENOSPC as well. Also unmounting and mounting again the filesystem didn't help. Allowing the cleaner kthread to use the global block reserve to delete the unused data block groups fixed the problem. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Dan Carpenter authored
btrfs_alloc_dummy_root() return an error pointer on failure, it never returns NULL. Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
David Sterba authored
The calculation of range length in btrfs_sync_file leads to signed overflow. This was caught by PaX gcc SIZE_OVERFLOW plugin. https://forums.grsecurity.net/viewtopic.php?f=1&t=4284 The fsync call passes 0 and LLONG_MAX, the range length does not fit to loff_t and overflows, but the value is converted to u64 so it silently works as expected. The minimal fix is a typecast to u64, switching functions to take (start, end) instead of (start, len) would be more intrusive. Coccinelle script found that there's one more opencoded calculation of the length. <smpl> @@ loff_t start, end; @@ * end - start </smpl> CC: stable@vger.kernel.org Signed-off-by: David Sterba <dsterba@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
-
- 11 Nov, 2015 9 commits
-
-
Zhao Lei authored
No need to use root->fs_info in btrfs_delete_unused_bgs(), use fs_info directly instead. Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
Reproduce: (In integration-4.3 branch) TEST_DEV=(/dev/vdg /dev/vdh) TEST_DIR=/mnt/tmp umount "$TEST_DEV" >/dev/null mkfs.btrfs -f -d raid1 "${TEST_DEV[@]}" mount -o nospace_cache "$TEST_DEV" "$TEST_DIR" btrfs balance start -dusage=0 $TEST_DIR btrfs filesystem usage $TEST_DIR dd if=/dev/zero of="$TEST_DIR"/file count=100 btrfs filesystem usage $TEST_DIR Result: We can see "no data chunk" in first "btrfs filesystem usage": # btrfs filesystem usage $TEST_DIR Overall: ... Metadata,single: Size:8.00MiB, Used:0.00B /dev/vdg 8.00MiB Metadata,RAID1: Size:122.88MiB, Used:112.00KiB /dev/vdg 122.88MiB /dev/vdh 122.88MiB System,single: Size:4.00MiB, Used:0.00B /dev/vdg 4.00MiB System,RAID1: Size:8.00MiB, Used:16.00KiB /dev/vdg 8.00MiB /dev/vdh 8.00MiB Unallocated: /dev/vdg 1.06GiB /dev/vdh 1.07GiB And "data chunks changed from raid1 to single" in second "btrfs filesystem usage": # btrfs filesystem usage $TEST_DIR Overall: ... Data,single: Size:256.00MiB, Used:0.00B /dev/vdh 256.00MiB Metadata,single: Size:8.00MiB, Used:0.00B /dev/vdg 8.00MiB Metadata,RAID1: Size:122.88MiB, Used:112.00KiB /dev/vdg 122.88MiB /dev/vdh 122.88MiB System,single: Size:4.00MiB, Used:0.00B /dev/vdg 4.00MiB System,RAID1: Size:8.00MiB, Used:16.00KiB /dev/vdg 8.00MiB /dev/vdh 8.00MiB Unallocated: /dev/vdg 1.06GiB /dev/vdh 841.92MiB Reason: btrfs balance delete last data chunk in case of no data in the filesystem, then we can see "no data chunk" by "fi usage" command. And when we do write operation to fs, the only available data profile is 0x0, result is all new chunks are allocated single type. Fix: Allocate a data chunk explicitly to ensure we don't lose the raid profile for data. Test: Test by above script, and confirmed the logic by debug output. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
Reproduce: (In integration-4.3 branch) TEST_DEV=(/dev/vdg /dev/vdh) TEST_DIR=/mnt/tmp umount "$TEST_DEV" >/dev/null mkfs.btrfs -f -d raid1 "${TEST_DEV[@]}" mount -o nospace_cache "$TEST_DEV" "$TEST_DIR" umount "$TEST_DEV" mount -o nospace_cache "$TEST_DEV" "$TEST_DIR" btrfs filesystem usage $TEST_DIR We can see the data chunk changed from raid1 to single: # btrfs filesystem usage $TEST_DIR Data,single: Size:8.00MiB, Used:0.00B /dev/vdg 8.00MiB # Reason: When a empty filesystem mount with -o nospace_cache, the last data blockgroup will be auto-removed in umount. Then if we mount it again, there is no data chunk in the filesystem, so the only available data profile is 0x0, result is all new chunks are created as single type. Fix: Don't auto-delete last blockgroup for a raid type. Test: Test by above script, and confirmed the logic by debug output. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
It is useless. Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
We don't need pass so many arguments for recheck sblock now, this patch cleans them. Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
We can use existing scrub_checksum_data() and scrub_checksum_tree_block() for scrub_recheck_block_checksum(), instead of write duplicated code. Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
We should reset sblock->xxx_error stats before calling scrub_recheck_block_checksum(). Current code run correctly because all sblock are allocated by k[cz]alloc(), and the error stats are not got changed. Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
scrub_setup_recheck_block() isn't setup all necessary fields for sblock_to_check because history reason. So current code need more arguments in severial functions, and more local variables, just to passing these lacked values to necessary place. This patch setup above fields to sblock_to_check in scrub_setup_recheck_block(), for: 1: more cleanup for function arg, local variable 2: to make sblock_to_check complete, then we can use sblock_to_check without concern about some uninitialized member. Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
Zhao Lei authored
It is better to show error stats to user when we found tree block spanning stripes. On a btrfs created by old version of btrfs-convert: Before patch: # btrfs scrub start -B /dev/vdh scrub done for 8b342d35-2904-41ab-b3cb-2f929709cf47 scrub started at Tue Aug 25 21:19:09 2015 and finished after 00:00:00 total bytes scrubbed: 53.54MiB with 0 errors # dmesg ... [ 128.711434] BTRFS error (device vdh): scrub: tree block 27054080 spanning stripes, ignored. logical=27000832 [ 128.712744] BTRFS error (device vdh): scrub: tree block 27054080 spanning stripes, ignored. logical=27066368 ... After patch: # btrfs scrub start -B /dev/vdh scrub done for ff7f844b-7a4e-4b1a-88a9-8252ab25be1b scrub started at Tue Aug 25 21:42:29 2015 and finished after 00:00:00 total bytes scrubbed: 53.60MiB with 2 errors error details: corrected errors: 0, uncorrectable errors: 2, unverified errors: 0 ERROR: There are uncorrectable errors. # dmesg ...omit... # Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
-
- 09 Nov, 2015 2 commits
-
-
Filipe Manana authored
When listing a inode's xattrs we have a time window where we race against a concurrent operation for adding a new hard link for our inode that makes us not return any xattr to user space. In order for this to happen, the first xattr of our inode needs to be at slot 0 of a leaf and the previous leaf must still have room for an inode ref (or extref) item, and this can happen because an inode's listxattrs callback does not lock the inode's i_mutex (nor does the VFS does it for us), but adding a hard link to an inode makes the VFS lock the inode's i_mutex before calling the inode's link callback. If we have the following leafs: Leaf X (has N items) Leaf Y [ ... (257 INODE_ITEM 0) (257 INODE_REF 256) ] [ (257 XATTR_ITEM 12345), ... ] slot N - 2 slot N - 1 slot 0 The race illustrated by the following sequence diagram is possible: CPU 1 CPU 2 btrfs_listxattr() searches for key (257 XATTR_ITEM 0) gets path with path->nodes[0] == leaf X and path->slots[0] == N because path->slots[0] is >= btrfs_header_nritems(leaf X), it calls btrfs_next_leaf() btrfs_next_leaf() releases the path adds key (257 INODE_REF 666) to the end of leaf X (slot N), and leaf X now has N + 1 items searches for the key (257 INODE_REF 256), with path->keep_locks == 1, because that is the last key it saw in leaf X before releasing the path ends up at leaf X again and it verifies that the key (257 INODE_REF 256) is no longer the last key in leaf X, so it returns with path->nodes[0] == leaf X and path->slots[0] == N, pointing to the new item with key (257 INODE_REF 666) btrfs_listxattr's loop iteration sees that the type of the key pointed by the path is different from the type BTRFS_XATTR_ITEM_KEY and so it breaks the loop and stops looking for more xattr items --> the application doesn't get any xattr listed for our inode So fix this by breaking the loop only if the key's type is greater than BTRFS_XATTR_ITEM_KEY and skip the current key if its type is smaller. Cc: stable@vger.kernel.org Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
If we are using the NO_HOLES feature, we have a tiny time window when running delalloc for a nodatacow inode where we can race with a concurrent link or xattr add operation leading to a BUG_ON. This happens because at run_delalloc_nocow() we end up casting a leaf item of type BTRFS_INODE_[REF|EXTREF]_KEY or of type BTRFS_XATTR_ITEM_KEY to a file extent item (struct btrfs_file_extent_item) and then analyse its extent type field, which won't match any of the expected extent types (values BTRFS_FILE_EXTENT_[REG|PREALLOC|INLINE]) and therefore trigger an explicit BUG_ON(1). The following sequence diagram shows how the race happens when running a no-cow dellaloc range [4K, 8K[ for inode 257 and we have the following neighbour leafs: Leaf X (has N items) Leaf Y [ ... (257 INODE_ITEM 0) (257 INODE_REF 256) ] [ (257 EXTENT_DATA 8192), ... ] slot N - 2 slot N - 1 slot 0 (Note the implicit hole for inode 257 regarding the [0, 8K[ range) CPU 1 CPU 2 run_dealloc_nocow() btrfs_lookup_file_extent() --> searches for a key with value (257 EXTENT_DATA 4096) in the fs/subvol tree --> returns us a path with path->nodes[0] == leaf X and path->slots[0] == N because path->slots[0] is >= btrfs_header_nritems(leaf X), it calls btrfs_next_leaf() btrfs_next_leaf() --> releases the path hard link added to our inode, with key (257 INODE_REF 500) added to the end of leaf X, so leaf X now has N + 1 keys --> searches for the key (257 INODE_REF 256), because it was the last key in leaf X before it released the path, with path->keep_locks set to 1 --> ends up at leaf X again and it verifies that the key (257 INODE_REF 256) is no longer the last key in the leaf, so it returns with path->nodes[0] == leaf X and path->slots[0] == N, pointing to the new item with key (257 INODE_REF 500) the loop iteration of run_dealloc_nocow() does not break out the loop and continues because the key referenced in the path at path->nodes[0] and path->slots[0] is for inode 257, its type is < BTRFS_EXTENT_DATA_KEY and its offset (500) is less then our delalloc range's end (8192) the item pointed by the path, an inode reference item, is (incorrectly) interpreted as a file extent item and we get an invalid extent type, leading to the BUG_ON(1): if (extent_type == BTRFS_FILE_EXTENT_REG || extent_type == BTRFS_FILE_EXTENT_PREALLOC) { (...) } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { (...) } else { BUG_ON(1) } The same can happen if a xattr is added concurrently and ends up having a key with an offset smaller then the delalloc's range end. So fix this by skipping keys with a type smaller than BTRFS_EXTENT_DATA_KEY. Cc: stable@vger.kernel.org Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
- 08 Nov, 2015 1 commit
-
-
Filipe Manana authored
While running a stress test I got the following warning triggered: [191627.672810] ------------[ cut here ]------------ [191627.673949] WARNING: CPU: 8 PID: 8447 at fs/btrfs/file.c:779 __btrfs_drop_extents+0x391/0xa50 [btrfs]() (...) [191627.701485] Call Trace: [191627.702037] [<ffffffff8145f077>] dump_stack+0x4f/0x7b [191627.702992] [<ffffffff81095de5>] ? console_unlock+0x356/0x3a2 [191627.704091] [<ffffffff8104b3b0>] warn_slowpath_common+0xa1/0xbb [191627.705380] [<ffffffffa0664499>] ? __btrfs_drop_extents+0x391/0xa50 [btrfs] [191627.706637] [<ffffffff8104b46d>] warn_slowpath_null+0x1a/0x1c [191627.707789] [<ffffffffa0664499>] __btrfs_drop_extents+0x391/0xa50 [btrfs] [191627.709155] [<ffffffff8115663c>] ? cache_alloc_debugcheck_after.isra.32+0x171/0x1d0 [191627.712444] [<ffffffff81155007>] ? kmemleak_alloc_recursive.constprop.40+0x16/0x18 [191627.714162] [<ffffffffa06570c9>] insert_reserved_file_extent.constprop.40+0x83/0x24e [btrfs] [191627.715887] [<ffffffffa065422b>] ? start_transaction+0x3bb/0x610 [btrfs] [191627.717287] [<ffffffffa065b604>] btrfs_finish_ordered_io+0x273/0x4e2 [btrfs] [191627.728865] [<ffffffffa065b888>] finish_ordered_fn+0x15/0x17 [btrfs] [191627.730045] [<ffffffffa067d688>] normal_work_helper+0x14c/0x32c [btrfs] [191627.731256] [<ffffffffa067d96a>] btrfs_endio_write_helper+0x12/0x14 [btrfs] [191627.732661] [<ffffffff81061119>] process_one_work+0x24c/0x4ae [191627.733822] [<ffffffff810615b0>] worker_thread+0x206/0x2c2 [191627.734857] [<ffffffff810613aa>] ? process_scheduled_works+0x2f/0x2f [191627.736052] [<ffffffff810613aa>] ? process_scheduled_works+0x2f/0x2f [191627.737349] [<ffffffff810669a6>] kthread+0xef/0xf7 [191627.738267] [<ffffffff810f3b3a>] ? time_hardirqs_on+0x15/0x28 [191627.739330] [<ffffffff810668b7>] ? __kthread_parkme+0xad/0xad [191627.741976] [<ffffffff81465592>] ret_from_fork+0x42/0x70 [191627.743080] [<ffffffff810668b7>] ? __kthread_parkme+0xad/0xad [191627.744206] ---[ end trace bbfddacb7aaada8d ]--- $ cat -n fs/btrfs/file.c 691 int __btrfs_drop_extents(struct btrfs_trans_handle *trans, (...) 758 btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); 759 if (key.objectid > ino || 760 key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) 761 break; 762 763 fi = btrfs_item_ptr(leaf, path->slots[0], 764 struct btrfs_file_extent_item); 765 extent_type = btrfs_file_extent_type(leaf, fi); 766 767 if (extent_type == BTRFS_FILE_EXTENT_REG || 768 extent_type == BTRFS_FILE_EXTENT_PREALLOC) { (...) 774 } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { (...) 778 } else { 779 WARN_ON(1); 780 extent_end = search_start; 781 } (...) This happened because the item we were processing did not match a file extent item (its key type != BTRFS_EXTENT_DATA_KEY), and even on this case we cast the item to a struct btrfs_file_extent_item pointer and then find a type field value that does not match any of the expected values (BTRFS_FILE_EXTENT_[REG|PREALLOC|INLINE]). This scenario happens due to a tiny time window where a race can happen as exemplified below. For example, consider the following scenario where we're using the NO_HOLES feature and we have the following two neighbour leafs: Leaf X (has N items) Leaf Y [ ... (257 INODE_ITEM 0) (257 INODE_REF 256) ] [ (257 EXTENT_DATA 8192), ... ] slot N - 2 slot N - 1 slot 0 Our inode 257 has an implicit hole in the range [0, 8K[ (implicit rather than explicit because NO_HOLES is enabled). Now if our inode has an ordered extent for the range [4K, 8K[ that is finishing, the following can happen: CPU 1 CPU 2 btrfs_finish_ordered_io() insert_reserved_file_extent() __btrfs_drop_extents() Searches for the key (257 EXTENT_DATA 4096) through btrfs_lookup_file_extent() Key not found and we get a path where path->nodes[0] == leaf X and path->slots[0] == N Because path->slots[0] is >= btrfs_header_nritems(leaf X), we call btrfs_next_leaf() btrfs_next_leaf() releases the path inserts key (257 INODE_REF 4096) at the end of leaf X, leaf X now has N + 1 keys, and the new key is at slot N btrfs_next_leaf() searches for key (257 INODE_REF 256), with path->keep_locks set to 1, because it was the last key it saw in leaf X finds it in leaf X again and notices it's no longer the last key of the leaf, so it returns 0 with path->nodes[0] == leaf X and path->slots[0] == N (which is now < btrfs_header_nritems(leaf X)), pointing to the new key (257 INODE_REF 4096) __btrfs_drop_extents() casts the item at path->nodes[0], slot path->slots[0], to a struct btrfs_file_extent_item - it does not skip keys for the target inode with a type less than BTRFS_EXTENT_DATA_KEY (BTRFS_INODE_REF_KEY < BTRFS_EXTENT_DATA_KEY) sees a bogus value for the type field triggering the WARN_ON in the trace shown above, and sets extent_end = search_start (4096) does the if-then-else logic to fixup 0 length extent items created by a past bug from hole punching: if (extent_end == key.offset && extent_end >= search_start) goto delete_extent_item; that evaluates to true and it ends up deleting the key pointed to by path->slots[0], (257 INODE_REF 4096), from leaf X The same could happen for example for a xattr that ends up having a key with an offset value that matches search_start (very unlikely but not impossible). So fix this by ensuring that keys smaller than BTRFS_EXTENT_DATA_KEY are skipped, never casted to struct btrfs_file_extent_item and never deleted by accident. Also protect against the unexpected case of getting a key for a lower inode number by skipping that key and issuing a warning. Cc: stable@vger.kernel.org Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
- 05 Nov, 2015 4 commits
-
-
Filipe Manana authored
We are holding a btree path with spinning locks and then we attempt to clone an extent buffer, which calls kmem_cache_alloc() and this function can sleep, causing the following trace to be reported on a debug kernel: [107118.218536] BUG: sleeping function called from invalid context at mm/slab.c:2871 [107118.224110] in_atomic(): 1, irqs_disabled(): 0, pid: 19148, name: kworker/u32:3 [107118.226120] INFO: lockdep is turned off. [107118.226843] Preemption disabled at:[<ffffffffa05ffa22>] btrfs_clear_lock_blocking_rw+0x96/0xea [btrfs] [107118.229175] CPU: 3 PID: 19148 Comm: kworker/u32:3 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [107118.231326] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [107118.233687] Workqueue: btrfs-qgroup-rescan btrfs_qgroup_rescan_helper [btrfs] [107118.236835] 0000000000000000 ffff880424bf3b78 ffffffff812566f4 0000000000000000 [107118.238369] ffff880424bf3ba0 ffffffff81070664 ffffffff817f1cd5 0000000000000b37 [107118.239769] 0000000000000000 ffff880424bf3bc8 ffffffff8107070a 0000000000008850 [107118.241244] Call Trace: [107118.241729] [<ffffffff812566f4>] dump_stack+0x4e/0x79 [107118.242602] [<ffffffff81070664>] ___might_sleep+0x23a/0x241 [107118.243586] [<ffffffff8107070a>] __might_sleep+0x9f/0xa6 [107118.244532] [<ffffffff8115af70>] cache_alloc_debugcheck_before+0x25/0x36 [107118.245939] [<ffffffff8115d52b>] kmem_cache_alloc+0x50/0x215 [107118.246930] [<ffffffffa05e627e>] __alloc_extent_buffer+0x2a/0x11f [btrfs] [107118.248121] [<ffffffffa05ecb1a>] btrfs_clone_extent_buffer+0x3d/0xdd [btrfs] [107118.249451] [<ffffffffa06239ea>] btrfs_qgroup_rescan_worker+0x16d/0x434 [btrfs] [107118.250755] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [107118.251754] [<ffffffffa05f7952>] normal_work_helper+0x14c/0x32a [btrfs] [107118.252899] [<ffffffffa05f7952>] ? normal_work_helper+0x14c/0x32a [btrfs] [107118.254195] [<ffffffffa05f7c82>] btrfs_qgroup_rescan_helper+0x12/0x14 [btrfs] [107118.255436] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac [107118.263690] [<ffffffff81064285>] worker_thread+0x206/0x2c2 [107118.264888] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb [107118.267413] [<ffffffff8106904d>] kthread+0xef/0xf7 [107118.268417] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24 [107118.269505] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70 [107118.270491] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24 So just use blocking locks for our path to solve this. This fixes the patch titled: "btrfs: qgroup: Don't copy extent buffer to do qgroup rescan" Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
We were initializing the completion (fs_info->qgroup_rescan_completion) object after releasing the qgroup rescan lock, which gives a small time window for a rescan waiter to not actually wait for the rescan worker to finish. Example: CPU 1 CPU 2 fs_info->qgroup_rescan_completion->done is 0 btrfs_qgroup_rescan_worker() complete_all(&fs_info->qgroup_rescan_completion) sets fs_info->qgroup_rescan_completion->done to UINT_MAX / 2 ... do some other stuff .... qgroup_rescan_init() mutex_lock(&fs_info->qgroup_rescan_lock) set flag BTRFS_QGROUP_STATUS_FLAG_RESCAN in fs_info->qgroup_flags mutex_unlock(&fs_info->qgroup_rescan_lock) btrfs_qgroup_wait_for_completion() mutex_lock(&fs_info->qgroup_rescan_lock) sees flag BTRFS_QGROUP_STATUS_FLAG_RESCAN in fs_info->qgroup_flags mutex_unlock(&fs_info->qgroup_rescan_lock) wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion) fs_info->qgroup_rescan_completion->done is > 0 so it returns immediately init_completion(&fs_info->qgroup_rescan_completion) sets fs_info->qgroup_rescan_completion->done to 0 So fix this by initializing the completion object while holding the mutex fs_info->qgroup_rescan_lock. Signed-off-by: Filipe Manana <fdmanana@suse.com>
-
Justin Maggard authored
I was hitting a consistent NULL pointer dereference during shutdown that showed the trace running through end_workqueue_bio(). I traced it back to the endio_meta_workers workqueue being poked after it had already been destroyed. Eventually I found that the root cause was a qgroup rescan that was still in progress while we were stopping all the btrfs workers. Currently we explicitly pause balance and scrub operations in close_ctree(), but we do nothing to stop the qgroup rescan. We should probably be doing the same for qgroup rescan, but that's a much larger change. This small change is good enough to allow me to unmount without crashing. Signed-off-by: Justin Maggard <jmaggard@netgear.com> Reviewed-by: Filipe Manana <fdmanana@suse.com>
-
Filipe Manana authored
When doing a write using direct IO we can end up not doing the whole write operation using the direct IO path, in that case we fallback to a buffered write to do the remaining IO. This happens for example if the range we are writing to contains a compressed extent. When we do a partial write and fallback to buffered IO, due to the existence of a compressed extent for example, we end up not adjusting the outstanding extents counter of our inode which ends up getting decremented twice, once by the DIO ordered extent for the partial write and once again by btrfs_direct_IO(), resulting in an arithmetic underflow at extent-tree.c:drop_outstanding_extent(). For example if we have: extents [ prealloc extent ] [ compressed extent ] offsets A B C D E and at the moment our inode's outstanding extents counter is 0, if we do a direct IO write against the range [B, D[ (which has a length smaller than 128Mb), we end up bumping our inode's outstanding extents counter to 1, we create a DIO ordered extent for the range [B, C[ and then fallback to a buffered write for the range [C, D[. The direct IO handler (inode.c:btrfs_direct_IO()) decrements the outstanding extents counter by 1, leaving it with a value of 0, through a call to btrfs_delalloc_release_space() and then shortly after the DIO ordered extent finishes and calls btrfs_delalloc_release_metadata() which ends up to attempt to decrement the inode's outstanding extents counter by 1, resulting in an assertion failure at drop_outstanding_extent() because the operation would result in an arithmetic underflow (0 - 1). This produces the following trace: [125471.336838] BTRFS: assertion failed: BTRFS_I(inode)->outstanding_extents >= num_extents, file: fs/btrfs/extent-tree.c, line: 5526 [125471.338844] ------------[ cut here ]------------ [125471.340745] kernel BUG at fs/btrfs/ctree.h:4173! [125471.340745] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [125471.340745] Modules linked in: btrfs f2fs xfs libcrc32c dm_flakey dm_mod crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc acpi_cpufreq psmouse i2c_piix4 parport pcspkr serio_raw microcode processor evdev i2c_core button ext4 crc16 jbd2 mbcache sd_mod sg sr_mod cdrom ata_generic virtio_scsi ata_piix virtio_pci virtio_ring floppy libata virtio e1000 scsi_mod [last unloaded: btrfs] [125471.340745] CPU: 10 PID: 23649 Comm: kworker/u32:1 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [125471.340745] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [125471.340745] Workqueue: btrfs-endio-write btrfs_endio_write_helper [btrfs] [125471.340745] task: ffff8804244fcf80 ti: ffff88040a118000 task.ti: ffff88040a118000 [125471.340745] RIP: 0010:[<ffffffffa0550da1>] [<ffffffffa0550da1>] assfail.constprop.46+0x1e/0x20 [btrfs] [125471.340745] RSP: 0018:ffff88040a11bc78 EFLAGS: 00010296 [125471.340745] RAX: 0000000000000075 RBX: 0000000000005000 RCX: 0000000000000000 [125471.340745] RDX: ffffffff81098f93 RSI: ffffffff8147c619 RDI: 00000000ffffffff [125471.340745] RBP: ffff88040a11bc78 R08: 0000000000000001 R09: 0000000000000000 [125471.340745] R10: ffff88040a11bc08 R11: ffffffff81651000 R12: ffff8803efb4a000 [125471.340745] R13: ffff8803efb4a000 R14: 0000000000000000 R15: ffff8802f8e33c88 [125471.340745] FS: 0000000000000000(0000) GS:ffff88043dd40000(0000) knlGS:0000000000000000 [125471.340745] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [125471.340745] CR2: 00007fae7ca86095 CR3: 0000000001a0b000 CR4: 00000000000006e0 [125471.340745] Stack: [125471.340745] ffff88040a11bc88 ffffffffa04ca0cd ffff88040a11bcc8 ffffffffa04ceeb1 [125471.340745] ffff8802f8e33940 ffff8802c93eadb0 ffff8802f8e0bf50 ffff8803efb4a000 [125471.340745] 0000000000000000 ffff8802f8e33c88 ffff88040a11bd38 ffffffffa04eccfa [125471.340745] Call Trace: [125471.340745] [<ffffffffa04ca0cd>] drop_outstanding_extent+0x3d/0x6d [btrfs] [125471.340745] [<ffffffffa04ceeb1>] btrfs_delalloc_release_metadata+0x51/0xdd [btrfs] [125471.340745] [<ffffffffa04eccfa>] btrfs_finish_ordered_io+0x420/0x4eb [btrfs] [125471.340745] [<ffffffffa04ecdda>] finish_ordered_fn+0x15/0x17 [btrfs] [125471.340745] [<ffffffffa050e6e8>] normal_work_helper+0x14c/0x32a [btrfs] [125471.340745] [<ffffffffa050e9c8>] btrfs_endio_write_helper+0x12/0x14 [btrfs] [125471.340745] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac [125471.340745] [<ffffffff81064285>] worker_thread+0x206/0x2c2 [125471.340745] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb [125471.340745] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb [125471.340745] [<ffffffff8106904d>] kthread+0xef/0xf7 [125471.340745] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24 [125471.340745] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70 [125471.340745] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24 [125471.340745] Code: a5 55 a0 48 89 e5 e8 42 50 bc e0 0f 0b 55 89 f1 48 c7 c2 f0 a8 55 a0 48 89 fe 31 c0 48 c7 c7 14 aa 55 a0 48 89 e5 e8 22 50 bc e0 <0f> 0b 0f 1f 44 00 00 55 31 c9 ba 18 00 00 00 48 89 e5 41 56 41 [125471.340745] RIP [<ffffffffa0550da1>] assfail.constprop.46+0x1e/0x20 [btrfs] [125471.340745] RSP <ffff88040a11bc78> [125471.539620] ---[ end trace 144259f7838b4aa4 ]--- So fix this by ensuring we adjust the outstanding extents counter when we do the fallback just like we do for the case where the whole write can be done through the direct IO path. We were also adjusting the outstanding extents counter by a constant value of 1, which is incorrect because we were ignorning that we account extents in BTRFS_MAX_EXTENT_SIZE units, o fix that as well. The following test case for fstests reproduces this issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter # real QA test starts here _need_to_be_root _supported_fs btrfs _supported_os Linux _require_scratch _require_xfs_io_command "falloc" rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount "-o compress" # Create a compressed extent covering the range [700K, 800K[. $XFS_IO_PROG -f -s -c "pwrite -S 0xaa -b 100K 700K 100K" \ $SCRATCH_MNT/foo | _filter_xfs_io # Create prealloc extent covering the range [600K, 700K[. $XFS_IO_PROG -c "falloc 600K 100K" $SCRATCH_MNT/foo # Write 80K of data to the range [640K, 720K[ using direct IO. This # range covers both the prealloc extent and the compressed extent. # Because there's a compressed extent in the range we are writing to, # the DIO write code path ends up only writing the first 60k of data, # which goes to the prealloc extent, and then falls back to buffered IO # for writing the remaining 20K of data - because that remaining data # maps to a file range containing a compressed extent. # When falling back to buffered IO, we used to trigger an assertion when # releasing reserved space due to bad accounting of the inode's # outstanding extents counter, which was set to 1 but we ended up # decrementing it by 1 twice, once through the ordered extent for the # 60K of data we wrote using direct IO, and once through the main direct # IO handler (inode.cbtrfs_direct_IO()) because the direct IO write # wrote less than 80K of data (60K). $XFS_IO_PROG -d -c "pwrite -S 0xbb -b 80K 640K 80K" \ $SCRATCH_MNT/foo | _filter_xfs_io # Now similar test as above but for very large write operations. This # triggers special cases for an inode's outstanding extents accounting, # as internally btrfs logically splits extents into 128Mb units. $XFS_IO_PROG -f -s \ -c "pwrite -S 0xaa -b 128M 258M 128M" \ -c "falloc 0 258M" \ $SCRATCH_MNT/bar | _filter_xfs_io $XFS_IO_PROG -d -c "pwrite -S 0xbb -b 256M 3M 256M" $SCRATCH_MNT/bar \ | _filter_xfs_io # Now verify the file contents are correct and that they are the same # even after unmounting and mounting the fs again (or evicting the page # cache). # # For file foo, all bytes in the range [0, 640K[ must have a value of # 0x00, all bytes in the range [640K, 720K[ must have a value of 0xbb # and all bytes in the range [720K, 800K[ must have a value of 0xaa. # # For file bar, all bytes in the range [0, 3M[ must havea value of 0x00, # all bytes in the range [3M, 259M[ must have a value of 0xbb and all # bytes in the range [259M, 386M[ must have a value of 0xaa. # echo "File digests before remounting the file system:" md5sum $SCRATCH_MNT/foo | _filter_scratch md5sum $SCRATCH_MNT/bar | _filter_scratch _scratch_remount echo "File digests after remounting the file system:" md5sum $SCRATCH_MNT/foo | _filter_scratch md5sum $SCRATCH_MNT/bar | _filter_scratch status=0 exit Fixes: e1cbbfa5 ("Btrfs: fix outstanding_extents accounting in DIO") Fixes: 3e05bde8 ("Btrfs: only adjust outstanding_extents when we do a short write") Signed-off-by: Filipe Manana <fdmanana@suse.com>
-