From 60e7cd3a4ba6049ef590921e84454e6cfd9e2589 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 30 Sep 2013 14:10:43 -0400 Subject: [PATCH 1/5] Btrfs: fix transid verify errors when recovering log tree If we crash with a log, remount and recover that log, and then crash before we can commit another transaction we will get transid verify errors on the next mount. This is because we were not zero'ing out the log when we committed the transaction after recovery. This is ok as long as we commit another transaction at some point in the future, but if you abort or something else goes wrong you can end up in this weird state because the recovery stuff says that the tree log should have a generation+1 of the super generation, which won't be the case of the transaction that was started for recovery. Fix this by removing the check and _always_ zero out the log portion of the super when we commit a transaction. This fixes the transid verify issues I was seeing with my force errors tests. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/transaction.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index e7a95356df83..8c81bdc1ef9b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1838,11 +1838,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, assert_qgroups_uptodate(trans); update_super_roots(root); - if (!root->fs_info->log_root_recovering) { - btrfs_set_super_log_root(root->fs_info->super_copy, 0); - btrfs_set_super_log_root_level(root->fs_info->super_copy, 0); - } - + btrfs_set_super_log_root(root->fs_info->super_copy, 0); + btrfs_set_super_log_root_level(root->fs_info->super_copy, 0); memcpy(root->fs_info->super_for_commit, root->fs_info->super_copy, sizeof(*root->fs_info->super_copy)); From 385fe0bede52a45cd960f30c7eb8d20ad8e1e05b Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 1 Oct 2013 23:49:49 +0800 Subject: [PATCH 2/5] Btrfs: fix crash of compressed writes The crash[1] is found by xfstests/generic/208 with "-o compress", it's not reproduced everytime, but it does panic. The bug is quite interesting, it's actually introduced by a recent commit (573aecafca1cf7a974231b759197a1aebcf39c2a, Btrfs: actually limit the size of delalloc range). Btrfs implements delay allocation, so during writeback, we (1) get a page A and lock it (2) search the state tree for delalloc bytes and lock all pages within the range (3) process the delalloc range, including find disk space and create ordered extent and so on. (4) submit the page A. It runs well in normal cases, but if we're in a racy case, eg. buffered compressed writes and aio-dio writes, sometimes we may fail to lock all pages in the 'delalloc' range, in which case, we need to fall back to search the state tree again with a smaller range limit(max_bytes = PAGE_CACHE_SIZE - offset). The mentioned commit has a side effect, that is, in the fallback case, we can find delalloc bytes before the index of the page we already have locked, so we're in the case of (delalloc_end <= *start) and return with (found > 0). This ends with not locking delalloc pages but making ->writepage still process them, and the crash happens. This fixes it by just thinking that we find nothing and returning to caller as the caller knows how to deal with it properly. [1]: ------------[ cut here ]------------ kernel BUG at mm/page-writeback.c:2170! [...] CPU: 2 PID: 11755 Comm: btrfs-delalloc- Tainted: G O 3.11.0+ #8 [...] RIP: 0010:[] [] clear_page_dirty_for_io+0x1e/0x83 [...] [ 4934.248731] Stack: [ 4934.248731] ffff8801477e5dc8 ffffea00049b9f00 ffff8801869f9ce8 ffffffffa02b841a [ 4934.248731] 0000000000000000 0000000000000000 0000000000000fff 0000000000000620 [ 4934.248731] ffff88018db59c78 ffffea0005da8d40 ffffffffa02ff860 00000001810016c0 [ 4934.248731] Call Trace: [ 4934.248731] [] extent_range_clear_dirty_for_io+0xcf/0xf5 [btrfs] [ 4934.248731] [] compress_file_range+0x1dc/0x4cb [btrfs] [ 4934.248731] [] ? detach_if_pending+0x22/0x4b [ 4934.248731] [] async_cow_start+0x35/0x53 [btrfs] [ 4934.248731] [] worker_loop+0x14b/0x48c [btrfs] [ 4934.248731] [] ? btrfs_queue_worker+0x25c/0x25c [btrfs] [ 4934.248731] [] kthread+0x8d/0x95 [ 4934.248731] [] ? kthread_freezable_should_stop+0x43/0x43 [ 4934.248731] [] ret_from_fork+0x7c/0xb0 [ 4934.248731] [] ? kthread_freezable_should_stop+0x43/0x43 [ 4934.248731] Code: ff 85 c0 0f 94 c0 0f b6 c0 59 5b 5d c3 0f 1f 44 00 00 55 48 89 e5 41 54 53 48 89 fb e8 2c de 00 00 49 89 c4 48 8b 03 a8 01 75 02 <0f> 0b 4d 85 e4 74 52 49 8b 84 24 80 00 00 00 f6 40 20 01 75 44 [ 4934.248731] RIP [] clear_page_dirty_for_io+0x1e/0x83 [ 4934.248731] RSP [ 4934.280307] ---[ end trace 36f06d3f8750236a ]--- Signed-off-by: Liu Bo Signed-off-by: Josef Bacik --- fs/btrfs/extent_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c09a40db53db..43feb4663f5b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1614,7 +1614,7 @@ again: *start = delalloc_start; *end = delalloc_end; free_extent_state(cached_state); - return found; + return 0; } /* From 964fb15acfcd672ac691f04879b71f07ccc21e0c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 2 Oct 2013 19:39:50 +0300 Subject: [PATCH 3/5] Btrfs: eliminate races in worker stopping code The current implementation of worker threads in Btrfs has races in worker stopping code, which cause all kinds of panics and lockups when running btrfs/011 xfstest in a loop. The problem is that btrfs_stop_workers is unsynchronized with respect to check_idle_worker, check_busy_worker and __btrfs_start_workers. E.g., check_idle_worker race flow: btrfs_stop_workers(): check_idle_worker(aworker): - grabs the lock - splices the idle list into the working list - removes the first worker from the working list - releases the lock to wait for its kthread's completion - grabs the lock - if aworker is on the working list, moves aworker from the working list to the idle list - releases the lock - grabs the lock - puts the worker - removes the second worker from the working list ...... btrfs_stop_workers returns, aworker is on the idle list FS is umounted, memory is freed ...... aworker is waken up, fireworks ensue With this applied, I wasn't able to trigger the problem in 48 hours, whereas previously I could reliably reproduce at least one of these races within an hour. Reported-by: David Sterba Signed-off-by: Ilya Dryomov Signed-off-by: Josef Bacik --- fs/btrfs/async-thread.c | 25 +++++++++++++++++++------ fs/btrfs/async-thread.h | 2 ++ 2 files changed, 21 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 58b7d14b08ee..08cc08f037a6 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -107,7 +107,8 @@ static void check_idle_worker(struct btrfs_worker_thread *worker) worker->idle = 1; /* the list may be empty if the worker is just starting */ - if (!list_empty(&worker->worker_list)) { + if (!list_empty(&worker->worker_list) && + !worker->workers->stopping) { list_move(&worker->worker_list, &worker->workers->idle_list); } @@ -127,7 +128,8 @@ static void check_busy_worker(struct btrfs_worker_thread *worker) spin_lock_irqsave(&worker->workers->lock, flags); worker->idle = 0; - if (!list_empty(&worker->worker_list)) { + if (!list_empty(&worker->worker_list) && + !worker->workers->stopping) { list_move_tail(&worker->worker_list, &worker->workers->worker_list); } @@ -412,6 +414,7 @@ void btrfs_stop_workers(struct btrfs_workers *workers) int can_stop; spin_lock_irq(&workers->lock); + workers->stopping = 1; list_splice_init(&workers->idle_list, &workers->worker_list); while (!list_empty(&workers->worker_list)) { cur = workers->worker_list.next; @@ -455,6 +458,7 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max, workers->ordered = 0; workers->atomic_start_pending = 0; workers->atomic_worker_start = async_helper; + workers->stopping = 0; } /* @@ -480,15 +484,19 @@ static int __btrfs_start_workers(struct btrfs_workers *workers) atomic_set(&worker->num_pending, 0); atomic_set(&worker->refs, 1); worker->workers = workers; - worker->task = kthread_run(worker_loop, worker, - "btrfs-%s-%d", workers->name, - workers->num_workers + 1); + worker->task = kthread_create(worker_loop, worker, + "btrfs-%s-%d", workers->name, + workers->num_workers + 1); if (IS_ERR(worker->task)) { ret = PTR_ERR(worker->task); - kfree(worker); goto fail; } + spin_lock_irq(&workers->lock); + if (workers->stopping) { + spin_unlock_irq(&workers->lock); + goto fail_kthread; + } list_add_tail(&worker->worker_list, &workers->idle_list); worker->idle = 1; workers->num_workers++; @@ -496,8 +504,13 @@ static int __btrfs_start_workers(struct btrfs_workers *workers) WARN_ON(workers->num_workers_starting < 0); spin_unlock_irq(&workers->lock); + wake_up_process(worker->task); return 0; + +fail_kthread: + kthread_stop(worker->task); fail: + kfree(worker); spin_lock_irq(&workers->lock); workers->num_workers_starting--; spin_unlock_irq(&workers->lock); diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 063698b90ce2..1f26792683ed 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -107,6 +107,8 @@ struct btrfs_workers { /* extra name for this worker, used for current->name */ char *name; + + int stopping; }; void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work); From 1357272fc7deeebb7b3c5d1a071562edc273cdaf Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 2 Oct 2013 20:41:01 +0300 Subject: [PATCH 4/5] Btrfs: fix a use-after-free bug in btrfs_dev_replace_finishing free_device rcu callback, scheduled from btrfs_rm_dev_replace_srcdev, can be processed before btrfs_scratch_superblock is called, which would result in a use-after-free on btrfs_device contents. Fix this by zeroing the superblock before the rcu callback is registered. Cc: Stefan Behrens Signed-off-by: Ilya Dryomov Signed-off-by: Josef Bacik --- fs/btrfs/dev-replace.c | 5 +---- fs/btrfs/volumes.c | 7 ++++++- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5d844438b2d4..2a9bd5bd24c3 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -535,10 +535,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list); btrfs_rm_dev_replace_srcdev(fs_info, src_device); - if (src_device->bdev) { - /* zero out the old super */ - btrfs_scratch_superblock(src_device); - } + /* * this is again a consistent state where no dev_replace procedure * is running, the target device is part of the filesystem, the diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 043114749516..b0203b1322ac 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1716,6 +1716,7 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info, struct btrfs_device *srcdev) { WARN_ON(!mutex_is_locked(&fs_info->fs_devices->device_list_mutex)); + list_del_rcu(&srcdev->dev_list); list_del_rcu(&srcdev->dev_alloc_list); fs_info->fs_devices->num_devices--; @@ -1725,9 +1726,13 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info, } if (srcdev->can_discard) fs_info->fs_devices->num_can_discard--; - if (srcdev->bdev) + if (srcdev->bdev) { fs_info->fs_devices->open_devices--; + /* zero out the old super */ + btrfs_scratch_superblock(srcdev); + } + call_rcu(&srcdev->rcu, free_device); } From b208c2f7ceafacbc44f13d1b5a9fbada98226183 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 19 Sep 2013 20:37:07 -0700 Subject: [PATCH 5/5] btrfs: Fix crash due to not allocating integrity data for a bioset When btrfs creates a bioset, we must also allocate the integrity data pool. Otherwise btrfs will crash when it tries to submit a bio to a checksumming disk: BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [] mempool_alloc+0x4a/0x150 PGD 2305e4067 PUD 23063d067 PMD 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: btrfs scsi_debug xfs ext4 jbd2 ext3 jbd mbcache sch_fq_codel eeprom lpc_ich mfd_core nfsd exportfs auth_rpcgss af_packet raid6_pq xor zlib_deflate libcrc32c [last unloaded: scsi_debug] CPU: 1 PID: 4486 Comm: mount Not tainted 3.12.0-rc1-mcsum #2 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff8802451c9720 ti: ffff880230698000 task.ti: ffff880230698000 RIP: 0010:[] [] mempool_alloc+0x4a/0x150 RSP: 0018:ffff880230699688 EFLAGS: 00010286 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 00000000005f8445 RDX: 0000000000000001 RSI: 0000000000000010 RDI: 0000000000000000 RBP: ffff8802306996f8 R08: 0000000000011200 R09: 0000000000000008 R10: 0000000000000020 R11: ffff88009d6e8000 R12: 0000000000011210 R13: 0000000000000030 R14: ffff8802306996b8 R15: ffff8802451c9720 FS: 00007f25b8a16800(0000) GS:ffff88024fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000018 CR3: 0000000230576000 CR4: 00000000000007e0 Stack: ffff8802451c9720 0000000000000002 ffffffff81a97100 0000000000281250 ffffffff81a96480 ffff88024fc99150 ffff880228d18200 0000000000000000 0000000000000000 0000000000000040 ffff880230e8c2e8 ffff8802459dc900 Call Trace: [] bio_integrity_alloc+0x48/0x1b0 [] bio_integrity_prep+0xac/0x360 [] ? mempool_alloc+0x58/0x150 [] ? alloc_extent_state+0x31/0x110 [btrfs] [] blk_queue_bio+0x1c9/0x460 [] generic_make_request+0xca/0x100 [] submit_bio+0x79/0x160 [] btrfs_map_bio+0x48e/0x5b0 [btrfs] [] btree_submit_bio_hook+0xda/0x110 [btrfs] [] submit_one_bio+0x6a/0xa0 [btrfs] [] read_extent_buffer_pages+0x250/0x310 [btrfs] [] ? __radix_tree_preload+0x66/0xf0 [] ? radix_tree_insert+0x95/0x260 [] btree_read_extent_buffer_pages.constprop.128+0xb6/0x120 [btrfs] [] read_tree_block+0x3a/0x60 [btrfs] [] open_ctree+0x139d/0x2030 [btrfs] [] btrfs_mount+0x53a/0x7d0 [btrfs] [] ? pcpu_alloc+0x8eb/0x9f0 [] ? __kmalloc_track_caller+0x35/0x1e0 [] mount_fs+0x20/0xd0 [] vfs_kern_mount+0x76/0x120 [] do_mount+0x200/0xa40 [] ? strndup_user+0x5b/0x80 [] SyS_mount+0x90/0xe0 [] system_call_fastpath+0x1a/0x1f Code: 4c 8d 75 a8 4c 89 6d e8 45 89 e0 4c 8d 6f 30 48 89 5d d8 41 83 e0 af 48 89 fb 49 83 c6 18 4c 89 7d f8 65 4c 8b 3c 25 c0 b8 00 00 <48> 8b 73 18 44 89 c7 44 89 45 98 ff 53 20 48 85 c0 48 89 c2 74 RIP [] mempool_alloc+0x4a/0x150 RSP CR2: 0000000000000018 ---[ end trace 7a96042017ed21e2 ]--- Signed-off-by: Darrick J. Wong Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent_io.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 43feb4663f5b..22bda32acb89 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -145,8 +145,16 @@ int __init extent_io_init(void) offsetof(struct btrfs_io_bio, bio)); if (!btrfs_bioset) goto free_buffer_cache; + + if (bioset_integrity_create(btrfs_bioset, BIO_POOL_SIZE)) + goto free_bioset; + return 0; +free_bioset: + bioset_free(btrfs_bioset); + btrfs_bioset = NULL; + free_buffer_cache: kmem_cache_destroy(extent_buffer_cache); extent_buffer_cache = NULL;