From 2d3ff9307218c556857790633776827494228022 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 16 Sep 2019 11:30:54 -0700 Subject: btrfs: don't prematurely free work in end_workqueue_fn() [ Upstream commit 9be490f1e15c34193b1aae17da58e14dd9f55a95 ] Currently, end_workqueue_fn() frees the end_io_wq entry (which embeds the work item) and then calls bio_endio(). This is another potential instance of the bug in "btrfs: don't prematurely free work in run_ordered_work()". In particular, the endio call may depend on other work items. For example, btrfs_end_dio_bio() can call btrfs_subio_endio_read() -> __btrfs_correct_data_nocsum() -> dio_read_error() -> submit_dio_repair_bio(), which submits a bio that is also completed through a end_workqueue_fn() work item. However, __btrfs_correct_data_nocsum() waits for the newly submitted bio to complete, thus it depends on another work item. This example currently usually works because we use different workqueue helper functions for BTRFS_WQ_ENDIO_DATA and BTRFS_WQ_ENDIO_DIO_REPAIR. However, it may deadlock with stacked filesystems and is fragile overall. The proper fix is to free the work item at the very end of the work function, so let's do that. Reviewed-by: Johannes Thumshirn Signed-off-by: Omar Sandoval Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9d3352fe8dc9..b37519241eb1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1712,8 +1712,8 @@ static void end_workqueue_fn(struct btrfs_work *work) bio->bi_error = end_io_wq->error; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; - kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); bio_endio(bio); + kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); } static int cleaner_kthread(void *arg) -- cgit v1.2.3 From fb8c812141f978fc5f1f851c2fe2af23ab818a99 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 10 Oct 2019 10:39:25 +0800 Subject: btrfs: use bool argument in free_root_pointers() [ Upstream commit 4273eaff9b8d5e141113a5bdf9628c02acf3afe5 ] We don't need int argument bool shall do in free_root_pointers(). And rename the argument as it confused two people. Reviewed-by: Qu Wenruo Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b37519241eb1..eab5a9065f09 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2104,7 +2104,7 @@ static void free_root_extent_buffers(struct btrfs_root *root) } /* helper to cleanup tree roots */ -static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) +static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) { free_root_extent_buffers(info->tree_root); @@ -2113,7 +2113,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) free_root_extent_buffers(info->csum_root); free_root_extent_buffers(info->quota_root); free_root_extent_buffers(info->uuid_root); - if (chunk_root) + if (free_chunk_root) free_root_extent_buffers(info->chunk_root); free_root_extent_buffers(info->free_space_root); } @@ -3136,7 +3136,7 @@ fail_block_groups: btrfs_free_block_groups(fs_info); fail_tree_roots: - free_root_pointers(fs_info, 1); + free_root_pointers(fs_info, true); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); fail_sb_buffer: @@ -3165,7 +3165,7 @@ recovery_tree_root: if (!btrfs_test_opt(tree_root->fs_info, USEBACKUPROOT)) goto fail_tree_roots; - free_root_pointers(fs_info, 0); + free_root_pointers(fs_info, false); /* don't use the log in recovery mode, it won't be valid */ btrfs_set_super_log_root(disk_super, 0); @@ -3862,7 +3862,7 @@ void close_ctree(struct btrfs_root *root) btrfs_stop_all_workers(fs_info); clear_bit(BTRFS_FS_OPEN, &fs_info->flags); - free_root_pointers(fs_info, 1); + free_root_pointers(fs_info, true); iput(fs_info->btree_inode); -- cgit v1.2.3 From 24e9e6bf5b6fea63124df0009d2ffa21c6a34392 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 22 Jan 2020 12:23:20 +0000 Subject: Btrfs: fix race between adding and putting tree mod seq elements and nodes [ Upstream commit 7227ff4de55d931bbdc156c8ef0ce4f100c78a5b ] There is a race between adding and removing elements to the tree mod log list and rbtree that can lead to use-after-free problems. Consider the following example that explains how/why the problems happens: 1) Task A has mod log element with sequence number 200. It currently is the only element in the mod log list; 2) Task A calls btrfs_put_tree_mod_seq() because it no longer needs to access the tree mod log. When it enters the function, it initializes 'min_seq' to (u64)-1. Then it acquires the lock 'tree_mod_seq_lock' before checking if there are other elements in the mod seq list. Since the list it empty, 'min_seq' remains set to (u64)-1. Then it unlocks the lock 'tree_mod_seq_lock'; 3) Before task A acquires the lock 'tree_mod_log_lock', task B adds itself to the mod seq list through btrfs_get_tree_mod_seq() and gets a sequence number of 201; 4) Some other task, name it task C, modifies a btree and because there elements in the mod seq list, it adds a tree mod elem to the tree mod log rbtree. That node added to the mod log rbtree is assigned a sequence number of 202; 5) Task B, which is doing fiemap and resolving indirect back references, calls btrfs get_old_root(), with 'time_seq' == 201, which in turn calls tree_mod_log_search() - the search returns the mod log node from the rbtree with sequence number 202, created by task C; 6) Task A now acquires the lock 'tree_mod_log_lock', starts iterating the mod log rbtree and finds the node with sequence number 202. Since 202 is less than the previously computed 'min_seq', (u64)-1, it removes the node and frees it; 7) Task B still has a pointer to the node with sequence number 202, and it dereferences the pointer itself and through the call to __tree_mod_log_rewind(), resulting in a use-after-free problem. This issue can be triggered sporadically with the test case generic/561 from fstests, and it happens more frequently with a higher number of duperemove processes. When it happens to me, it either freezes the VM or it produces a trace like the following before crashing: [ 1245.321140] general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [ 1245.321200] CPU: 1 PID: 26997 Comm: pool Not tainted 5.5.0-rc6-btrfs-next-52 #1 [ 1245.321235] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014 [ 1245.321287] RIP: 0010:rb_next+0x16/0x50 [ 1245.321307] Code: .... [ 1245.321372] RSP: 0018:ffffa151c4d039b0 EFLAGS: 00010202 [ 1245.321388] RAX: 6b6b6b6b6b6b6b6b RBX: ffff8ae221363c80 RCX: 6b6b6b6b6b6b6b6b [ 1245.321409] RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff8ae221363c80 [ 1245.321439] RBP: ffff8ae20fcc4688 R08: 0000000000000002 R09: 0000000000000000 [ 1245.321475] R10: ffff8ae20b120910 R11: 00000000243f8bb1 R12: 0000000000000038 [ 1245.321506] R13: ffff8ae221363c80 R14: 000000000000075f R15: ffff8ae223f762b8 [ 1245.321539] FS: 00007fdee1ec7700(0000) GS:ffff8ae236c80000(0000) knlGS:0000000000000000 [ 1245.321591] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1245.321614] CR2: 00007fded4030c48 CR3: 000000021da16003 CR4: 00000000003606e0 [ 1245.321642] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1245.321668] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1245.321706] Call Trace: [ 1245.321798] __tree_mod_log_rewind+0xbf/0x280 [btrfs] [ 1245.321841] btrfs_search_old_slot+0x105/0xd00 [btrfs] [ 1245.321877] resolve_indirect_refs+0x1eb/0xc60 [btrfs] [ 1245.321912] find_parent_nodes+0x3dc/0x11b0 [btrfs] [ 1245.321947] btrfs_check_shared+0x115/0x1c0 [btrfs] [ 1245.321980] ? extent_fiemap+0x59d/0x6d0 [btrfs] [ 1245.322029] extent_fiemap+0x59d/0x6d0 [btrfs] [ 1245.322066] do_vfs_ioctl+0x45a/0x750 [ 1245.322081] ksys_ioctl+0x70/0x80 [ 1245.322092] ? trace_hardirqs_off_thunk+0x1a/0x1c [ 1245.322113] __x64_sys_ioctl+0x16/0x20 [ 1245.322126] do_syscall_64+0x5c/0x280 [ 1245.322139] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1245.322155] RIP: 0033:0x7fdee3942dd7 [ 1245.322177] Code: .... [ 1245.322258] RSP: 002b:00007fdee1ec6c88 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 1245.322294] RAX: ffffffffffffffda RBX: 00007fded40210d8 RCX: 00007fdee3942dd7 [ 1245.322314] RDX: 00007fded40210d8 RSI: 00000000c020660b RDI: 0000000000000004 [ 1245.322337] RBP: 0000562aa89e7510 R08: 0000000000000000 R09: 00007fdee1ec6d44 [ 1245.322369] R10: 0000000000000073 R11: 0000000000000246 R12: 00007fdee1ec6d48 [ 1245.322390] R13: 00007fdee1ec6d40 R14: 00007fded40210d0 R15: 00007fdee1ec6d50 [ 1245.322423] Modules linked in: .... [ 1245.323443] ---[ end trace 01de1e9ec5dff3cd ]--- Fix this by ensuring that btrfs_put_tree_mod_seq() computes the minimum sequence number and iterates the rbtree while holding the lock 'tree_mod_log_lock' in write mode. Also get rid of the 'tree_mod_seq_lock' lock, since it is now redundant. Fixes: bd989ba359f2ac ("Btrfs: add tree modification log functions") Fixes: 097b8a7c9e48e2 ("Btrfs: join tree mod log code with the code holding back delayed refs") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Reviewed-by: Nikolay Borisov Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index eab5a9065f09..e3524ecce3d7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2519,7 +2519,6 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->free_chunk_lock); - spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->buffer_lock); -- cgit v1.2.3 From 66ada407dd6a58dbb4e51ea4489af009e886a31b Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 5 Feb 2020 17:12:16 +0100 Subject: btrfs: print message when tree-log replay starts [ Upstream commit e8294f2f6aa6208ed0923aa6d70cea3be178309a ] There's no logged information about tree-log replay although this is something that points to previous unclean unmount. Other filesystems report that as well. Suggested-by: Chris Murphy CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Anand Jain Reviewed-by: Johannes Thumshirn Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e3524ecce3d7..390053557d4d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2979,6 +2979,7 @@ retry_root_backup: /* do not make disk changes in broken FS or nologreplay is given */ if (btrfs_super_log_root(disk_super) != 0 && !btrfs_test_opt(tree_root->fs_info, NOLOGREPLAY)) { + btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); if (ret) { err = ret; -- cgit v1.2.3 From 68a417b5befc2aa2c52052511624f1bb7ef7fe6a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 28 Feb 2020 13:04:36 +0000 Subject: Btrfs: fix crash during unmount due to race with delayed inode workers [ Upstream commit f0cc2cd70164efe8f75c5d99560f0f69969c72e4 ] During unmount we can have a job from the delayed inode items work queue still running, that can lead to at least two bad things: 1) A crash, because the worker can try to create a transaction just after the fs roots were freed; 2) A transaction leak, because the worker can create a transaction before the fs roots are freed and just after we committed the last transaction and after we stopped the transaction kthread. A stack trace example of the crash: [79011.691214] kernel BUG at lib/radix-tree.c:982! [79011.692056] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [79011.693180] CPU: 3 PID: 1394 Comm: kworker/u8:2 Tainted: G W 5.6.0-rc2-btrfs-next-54 #2 (...) [79011.696789] Workqueue: btrfs-delayed-meta btrfs_work_helper [btrfs] [79011.697904] RIP: 0010:radix_tree_tag_set+0xe7/0x170 (...) [79011.702014] RSP: 0018:ffffb3c84a317ca0 EFLAGS: 00010293 [79011.702949] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [79011.704202] RDX: ffffb3c84a317cb0 RSI: ffffb3c84a317ca8 RDI: ffff8db3931340a0 [79011.705463] RBP: 0000000000000005 R08: 0000000000000005 R09: ffffffff974629d0 [79011.706756] R10: ffffb3c84a317bc0 R11: 0000000000000001 R12: ffff8db393134000 [79011.708010] R13: ffff8db3931340a0 R14: ffff8db393134068 R15: 0000000000000001 [79011.709270] FS: 0000000000000000(0000) GS:ffff8db3b6a00000(0000) knlGS:0000000000000000 [79011.710699] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [79011.711710] CR2: 00007f22c2a0a000 CR3: 0000000232ad4005 CR4: 00000000003606e0 [79011.712958] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [79011.714205] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [79011.715448] Call Trace: [79011.715925] record_root_in_trans+0x72/0xf0 [btrfs] [79011.716819] btrfs_record_root_in_trans+0x4b/0x70 [btrfs] [79011.717925] start_transaction+0xdd/0x5c0 [btrfs] [79011.718829] btrfs_async_run_delayed_root+0x17e/0x2b0 [btrfs] [79011.719915] btrfs_work_helper+0xaa/0x720 [btrfs] [79011.720773] process_one_work+0x26d/0x6a0 [79011.721497] worker_thread+0x4f/0x3e0 [79011.722153] ? process_one_work+0x6a0/0x6a0 [79011.722901] kthread+0x103/0x140 [79011.723481] ? kthread_create_worker_on_cpu+0x70/0x70 [79011.724379] ret_from_fork+0x3a/0x50 (...) The following diagram shows a sequence of steps that lead to the crash during ummount of the filesystem: CPU 1 CPU 2 CPU 3 btrfs_punch_hole() btrfs_btree_balance_dirty() btrfs_balance_delayed_items() --> sees fs_info->delayed_root->items with value 200, which is greater than BTRFS_DELAYED_BACKGROUND (128) and smaller than BTRFS_DELAYED_WRITEBACK (512) btrfs_wq_run_delayed_node() --> queues a job for fs_info->delayed_workers to run btrfs_async_run_delayed_root() btrfs_async_run_delayed_root() --> job queued by CPU 1 --> starts picking and running delayed nodes from the prepare_list list close_ctree() btrfs_delete_unused_bgs() btrfs_commit_super() btrfs_join_transaction() --> gets transaction N btrfs_commit_transaction(N) --> set transaction state to TRANTS_STATE_COMMIT_START btrfs_first_prepared_delayed_node() --> picks delayed node X through the prepared_list list btrfs_run_delayed_items() btrfs_first_delayed_node() --> also picks delayed node X but through the node_list list __btrfs_commit_inode_delayed_items() --> runs all delayed items from this node and drops the node's item count to 0 through call to btrfs_release_delayed_inode() --> finishes running any remaining delayed nodes --> finishes transaction commit --> stops cleaner and transaction threads btrfs_free_fs_roots() --> frees all roots and removes them from the radix tree fs_info->fs_roots_radix btrfs_join_transaction() start_transaction() btrfs_record_root_in_trans() record_root_in_trans() radix_tree_tag_set() --> crashes because the root is not in the radix tree anymore If the worker is able to call btrfs_join_transaction() before the unmount task frees the fs roots, we end up leaking a transaction and all its resources, since after the call to btrfs_commit_super() and stopping the transaction kthread, we don't expect to have any transaction open anymore. When this situation happens the worker has a delayed node that has no more items to run, since the task calling btrfs_run_delayed_items(), which is doing a transaction commit, picks the same node and runs all its items first. We can not wait for the worker to complete when running delayed items through btrfs_run_delayed_items(), because we call that function in several phases of a transaction commit, and that could cause a deadlock because the worker calls btrfs_join_transaction() and the task doing the transaction commit may have already set the transaction state to TRANS_STATE_COMMIT_DOING. Also it's not possible to get into a situation where only some of the items of a delayed node are added to the fs/subvolume tree in the current transaction and the remaining ones in the next transaction, because when running the items of a delayed inode we lock its mutex, effectively waiting for the worker if the worker is running the items of the delayed node already. Since this can only cause issues when unmounting a filesystem, fix it in a simple way by waiting for any jobs on the delayed workers queue before calling btrfs_commit_supper() at close_ctree(). This works because at this point no one can call btrfs_btree_balance_dirty() or btrfs_balance_delayed_items(), and if we end up waiting for any worker to complete, btrfs_commit_super() will commit the transaction created by the worker. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 390053557d4d..1de017051928 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3825,6 +3825,19 @@ void close_ctree(struct btrfs_root *root) */ btrfs_delete_unused_bgs(root->fs_info); + /* + * There might be existing delayed inode workers still running + * and holding an empty delayed inode item. We must wait for + * them to complete first because they can create a transaction. + * This happens when someone calls btrfs_balance_delayed_items() + * and then a transaction commit runs the same delayed nodes + * before any delayed worker has done something with the nodes. + * We must wait for any worker here and not at transaction + * commit time since that could cause a deadlock. + * This is a very rare case. + */ + btrfs_flush_workqueue(fs_info->delayed_workers); + ret = btrfs_commit_super(root); if (ret) btrfs_err(fs_info, "commit super ret %d", ret); -- cgit v1.2.3