From fccc0007b8dc952c6bc0805cdf842eb8ea06a639 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 31 Aug 2020 10:52:42 -0400 Subject: [PATCH 1/4] btrfs: fix lockdep splat in add_missing_dev Nikolay reported a lockdep splat in generic/476 that I could reproduce with btrfs/187. ====================================================== WARNING: possible circular locking dependency detected 5.9.0-rc2+ #1 Tainted: G W ------------------------------------------------------ kswapd0/100 is trying to acquire lock: ffff9e8ef38b6268 (&delayed_node->mutex){+.+.}-{3:3}, at: __btrfs_release_delayed_node.part.0+0x3f/0x330 but task is already holding lock: ffffffffa9d74700 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (fs_reclaim){+.+.}-{0:0}: fs_reclaim_acquire+0x65/0x80 slab_pre_alloc_hook.constprop.0+0x20/0x200 kmem_cache_alloc_trace+0x3a/0x1a0 btrfs_alloc_device+0x43/0x210 add_missing_dev+0x20/0x90 read_one_chunk+0x301/0x430 btrfs_read_sys_array+0x17b/0x1b0 open_ctree+0xa62/0x1896 btrfs_mount_root.cold+0x12/0xea legacy_get_tree+0x30/0x50 vfs_get_tree+0x28/0xc0 vfs_kern_mount.part.0+0x71/0xb0 btrfs_mount+0x10d/0x379 legacy_get_tree+0x30/0x50 vfs_get_tree+0x28/0xc0 path_mount+0x434/0xc00 __x64_sys_mount+0xe3/0x120 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #1 (&fs_info->chunk_mutex){+.+.}-{3:3}: __mutex_lock+0x7e/0x7e0 btrfs_chunk_alloc+0x125/0x3a0 find_free_extent+0xdf6/0x1210 btrfs_reserve_extent+0xb3/0x1b0 btrfs_alloc_tree_block+0xb0/0x310 alloc_tree_block_no_bg_flush+0x4a/0x60 __btrfs_cow_block+0x11a/0x530 btrfs_cow_block+0x104/0x220 btrfs_search_slot+0x52e/0x9d0 btrfs_lookup_inode+0x2a/0x8f __btrfs_update_delayed_inode+0x80/0x240 btrfs_commit_inode_delayed_inode+0x119/0x120 btrfs_evict_inode+0x357/0x500 evict+0xcf/0x1f0 vfs_rmdir.part.0+0x149/0x160 do_rmdir+0x136/0x1a0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #0 (&delayed_node->mutex){+.+.}-{3:3}: __lock_acquire+0x1184/0x1fa0 lock_acquire+0xa4/0x3d0 __mutex_lock+0x7e/0x7e0 __btrfs_release_delayed_node.part.0+0x3f/0x330 btrfs_evict_inode+0x24c/0x500 evict+0xcf/0x1f0 dispose_list+0x48/0x70 prune_icache_sb+0x44/0x50 super_cache_scan+0x161/0x1e0 do_shrink_slab+0x178/0x3c0 shrink_slab+0x17c/0x290 shrink_node+0x2b2/0x6d0 balance_pgdat+0x30a/0x670 kswapd+0x213/0x4c0 kthread+0x138/0x160 ret_from_fork+0x1f/0x30 other info that might help us debug this: Chain exists of: &delayed_node->mutex --> &fs_info->chunk_mutex --> fs_reclaim Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(&fs_info->chunk_mutex); lock(fs_reclaim); lock(&delayed_node->mutex); *** DEADLOCK *** 3 locks held by kswapd0/100: #0: ffffffffa9d74700 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 #1: ffffffffa9d65c50 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x115/0x290 #2: ffff9e8e9da260e0 (&type->s_umount_key#48){++++}-{3:3}, at: super_cache_scan+0x38/0x1e0 stack backtrace: CPU: 1 PID: 100 Comm: kswapd0 Tainted: G W 5.9.0-rc2+ #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 Call Trace: dump_stack+0x92/0xc8 check_noncircular+0x12d/0x150 __lock_acquire+0x1184/0x1fa0 lock_acquire+0xa4/0x3d0 ? __btrfs_release_delayed_node.part.0+0x3f/0x330 __mutex_lock+0x7e/0x7e0 ? __btrfs_release_delayed_node.part.0+0x3f/0x330 ? __btrfs_release_delayed_node.part.0+0x3f/0x330 ? lock_acquire+0xa4/0x3d0 ? btrfs_evict_inode+0x11e/0x500 ? find_held_lock+0x2b/0x80 __btrfs_release_delayed_node.part.0+0x3f/0x330 btrfs_evict_inode+0x24c/0x500 evict+0xcf/0x1f0 dispose_list+0x48/0x70 prune_icache_sb+0x44/0x50 super_cache_scan+0x161/0x1e0 do_shrink_slab+0x178/0x3c0 shrink_slab+0x17c/0x290 shrink_node+0x2b2/0x6d0 balance_pgdat+0x30a/0x670 kswapd+0x213/0x4c0 ? _raw_spin_unlock_irqrestore+0x46/0x60 ? add_wait_queue_exclusive+0x70/0x70 ? balance_pgdat+0x670/0x670 kthread+0x138/0x160 ? kthread_create_worker_on_cpu+0x40/0x40 ret_from_fork+0x1f/0x30 This is because we are holding the chunk_mutex when we call btrfs_alloc_device, which does a GFP_KERNEL allocation. We don't want to switch that to a GFP_NOFS lock because this is the only place where it matters. So instead use memalloc_nofs_save() around the allocation in order to avoid the lockdep splat. Reported-by: Nikolay Borisov CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Anand Jain Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 214856c4ccb1..117b43367629 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4,6 +4,7 @@ */ #include +#include #include #include #include @@ -6484,8 +6485,17 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices, u64 devid, u8 *dev_uuid) { struct btrfs_device *device; + unsigned int nofs_flag; + /* + * We call this under the chunk_mutex, so we want to use NOFS for this + * allocation, however we don't want to change btrfs_alloc_device() to + * always do NOFS because we use it in a lot of other GFP_KERNEL safe + * places. + */ + nofs_flag = memalloc_nofs_save(); device = btrfs_alloc_device(NULL, &devid, dev_uuid); + memalloc_nofs_restore(nofs_flag); if (IS_ERR(device)) return device; From ea57788eb76dc81f6003245427356a1dcd0ac524 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 26 Aug 2020 17:26:43 +0800 Subject: [PATCH 2/4] btrfs: require only sector size alignment for parent eb bytenr [BUG] A completely sane converted fs will cause kernel warning at balance time: [ 1557.188633] BTRFS info (device sda7): relocating block group 8162107392 flags data [ 1563.358078] BTRFS info (device sda7): found 11722 extents [ 1563.358277] BTRFS info (device sda7): leaf 7989321728 gen 95 total ptrs 213 free space 3458 owner 2 [ 1563.358280] item 0 key (7984947200 169 0) itemoff 16250 itemsize 33 [ 1563.358281] extent refs 1 gen 90 flags 2 [ 1563.358282] ref#0: tree block backref root 4 [ 1563.358285] item 1 key (7985602560 169 0) itemoff 16217 itemsize 33 [ 1563.358286] extent refs 1 gen 93 flags 258 [ 1563.358287] ref#0: shared block backref parent 7985602560 [ 1563.358288] (parent 7985602560 is NOT ALIGNED to nodesize 16384) [ 1563.358290] item 2 key (7985635328 169 0) itemoff 16184 itemsize 33 ... [ 1563.358995] BTRFS error (device sda7): eb 7989321728 invalid extent inline ref type 182 [ 1563.358996] ------------[ cut here ]------------ [ 1563.359005] WARNING: CPU: 14 PID: 2930 at 0xffffffff9f231766 Then with transaction abort, and obviously failed to balance the fs. [CAUSE] That mentioned inline ref type 182 is completely sane, it's BTRFS_SHARED_BLOCK_REF_KEY, it's some extra check making kernel to believe it's invalid. Commit 64ecdb647ddb ("Btrfs: add one more sanity check for shared ref type") introduced extra checks for backref type. One of the requirement is, parent bytenr must be aligned to node size, which is not correct. One example is like this: 0 1G 1G+4K 2G 2G+4K | |///////////////////|//| <- A chunk starts at 1G+4K | | <- A tree block get reserved at bytenr 1G+4K Then we have a valid tree block at bytenr 1G+4K, but not aligned to nodesize (16K). Such chunk is not ideal, but current kernel can handle it pretty well. We may warn about such tree block in the future, but should not reject them. [FIX] Change the alignment requirement from node size alignment to sector size alignment. Also, to make our lives a little easier, also output @iref when btrfs_get_extent_inline_ref_type() failed, so we can locate the item easier. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=205475 Fixes: 64ecdb647ddb ("Btrfs: add one more sanity check for shared ref type") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo [ update comments and messages ] Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 19 +++++++++---------- fs/btrfs/print-tree.c | 12 +++++++----- 2 files changed, 16 insertions(+), 15 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e9eedc053fc5..780b9c9a98fe 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -400,12 +400,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, if (type == BTRFS_SHARED_BLOCK_REF_KEY) { ASSERT(eb->fs_info); /* - * Every shared one has parent tree - * block, which must be aligned to - * nodesize. + * Every shared one has parent tree block, + * which must be aligned to sector size. */ if (offset && - IS_ALIGNED(offset, eb->fs_info->nodesize)) + IS_ALIGNED(offset, eb->fs_info->sectorsize)) return type; } } else if (is_data == BTRFS_REF_TYPE_DATA) { @@ -414,12 +413,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, if (type == BTRFS_SHARED_DATA_REF_KEY) { ASSERT(eb->fs_info); /* - * Every shared one has parent tree - * block, which must be aligned to - * nodesize. + * Every shared one has parent tree block, + * which must be aligned to sector size. */ if (offset && - IS_ALIGNED(offset, eb->fs_info->nodesize)) + IS_ALIGNED(offset, eb->fs_info->sectorsize)) return type; } } else { @@ -429,8 +427,9 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, } btrfs_print_leaf((struct extent_buffer *)eb); - btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d", - eb->start, type); + btrfs_err(eb->fs_info, + "eb %llu iref 0x%lx invalid extent inline ref type %d", + eb->start, (unsigned long)iref, type); WARN_ON(1); return BTRFS_REF_TYPE_INVALID; diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 61f44e78e3c9..80567c11ec12 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -95,9 +95,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) * offset is supposed to be a tree block which * must be aligned to nodesize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) - pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n", - offset, (unsigned long long)eb->fs_info->nodesize); + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) + pr_info( + "\t\t\t(parent %llu not aligned to sectorsize %u)\n", + offset, eb->fs_info->sectorsize); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = (struct btrfs_extent_data_ref *)(&iref->offset); @@ -112,8 +113,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) * must be aligned to nodesize. */ if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) - pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n", - offset, (unsigned long long)eb->fs_info->nodesize); + pr_info( + "\t\t\t(parent %llu not aligned to sectorsize %u)\n", + offset, eb->fs_info->sectorsize); break; default: pr_cont("(extent %llu has INVALID ref type %d)\n", From 9e3aa8054453d23d9f477f0cdae70a6a1ea6ec8a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 3 Sep 2020 14:29:50 -0400 Subject: [PATCH 3/4] btrfs: free data reloc tree on failed mount While testing a weird problem with -o degraded, I noticed I was getting leaked root errors BTRFS warning (device loop0): writable mount is not allowed due to too many missing devices BTRFS error (device loop0): open_ctree failed BTRFS error (device loop0): leaked root -9-0 refcount 1 This is the DATA_RELOC root, which gets read before the other fs roots, but is included in the fs roots radix tree. Handle this by adding a btrfs_drop_and_free_fs_root() on the data reloc root if it exists. This is ok to do here if we fail further up because we will only drop the ref if we delete the root from the radix tree, and all other cleanup won't be duplicated. CC: stable@vger.kernel.org # 5.8+ Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 465bc8372e09..9fe9ec6aab71 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3441,6 +3441,8 @@ fail_block_groups: btrfs_put_block_group_cache(fs_info); fail_tree_roots: + if (fs_info->data_reloc_root) + btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root); free_root_pointers(fs_info, true); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); From 2d892ccdc163a3d2e08c5ed1cea8b61bf7e4f531 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 4 Sep 2020 17:22:57 +0100 Subject: [PATCH 4/4] btrfs: fix NULL pointer dereference after failure to create snapshot When trying to get a new fs root for a snapshot during the transaction at transaction.c:create_pending_snapshot(), if btrfs_get_new_fs_root() fails we leave "pending->snap" pointing to an error pointer, and then later at ioctl.c:create_snapshot() we dereference that pointer, resulting in a crash: [12264.614689] BUG: kernel NULL pointer dereference, address: 00000000000007c4 [12264.615650] #PF: supervisor write access in kernel mode [12264.616487] #PF: error_code(0x0002) - not-present page [12264.617436] PGD 0 P4D 0 [12264.618328] Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [12264.619150] CPU: 0 PID: 2310635 Comm: fsstress Tainted: G W 5.9.0-rc3-btrfs-next-67 #1 [12264.619960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [12264.621769] RIP: 0010:btrfs_mksubvol+0x438/0x4a0 [btrfs] [12264.622528] Code: bc ef ff ff (...) [12264.624092] RSP: 0018:ffffaa6fc7277cd8 EFLAGS: 00010282 [12264.624669] RAX: 00000000fffffff4 RBX: ffff9d3e8f151a60 RCX: 0000000000000000 [12264.625249] RDX: 0000000000000001 RSI: ffffffff9d56c9be RDI: fffffffffffffff4 [12264.625830] RBP: ffff9d3e8f151b48 R08: 0000000000000000 R09: 0000000000000000 [12264.626413] R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffff4 [12264.626994] R13: ffff9d3ede380538 R14: ffff9d3ede380500 R15: ffff9d3f61b2eeb8 [12264.627582] FS: 00007f140d5d8200(0000) GS:ffff9d3fb5e00000(0000) knlGS:0000000000000000 [12264.628176] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12264.628773] CR2: 00000000000007c4 CR3: 000000020f8e8004 CR4: 00000000003706f0 [12264.629379] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [12264.629994] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [12264.630594] Call Trace: [12264.631227] btrfs_mksnapshot+0x7b/0xb0 [btrfs] [12264.631840] __btrfs_ioctl_snap_create+0x16f/0x1a0 [btrfs] [12264.632458] btrfs_ioctl_snap_create_v2+0xb0/0xf0 [btrfs] [12264.633078] btrfs_ioctl+0x1864/0x3130 [btrfs] [12264.633689] ? do_sys_openat2+0x1a7/0x2d0 [12264.634295] ? kmem_cache_free+0x147/0x3a0 [12264.634899] ? __x64_sys_ioctl+0x83/0xb0 [12264.635488] __x64_sys_ioctl+0x83/0xb0 [12264.636058] do_syscall_64+0x33/0x80 [12264.636616] entry_SYSCALL_64_after_hwframe+0x44/0xa9 (gdb) list *(btrfs_mksubvol+0x438) 0x7c7b8 is in btrfs_mksubvol (fs/btrfs/ioctl.c:858). 853 ret = 0; 854 pending_snapshot->anon_dev = 0; 855 fail: 856 /* Prevent double freeing of anon_dev */ 857 if (ret && pending_snapshot->snap) 858 pending_snapshot->snap->anon_dev = 0; 859 btrfs_put_root(pending_snapshot->snap); 860 btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv); 861 free_pending: 862 if (pending_snapshot->anon_dev) So fix this by setting "pending->snap" to NULL if we get an error from the call to btrfs_get_new_fs_root() at transaction.c:create_pending_snapshot(). Fixes: 2dfb1e43f57dd3 ("btrfs: preallocate anon block device at first phase of snapshot creation") Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 20c6ac1a5de7..d2fc292ac61b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1636,6 +1636,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); + pending->snap = NULL; btrfs_abort_transaction(trans, ret); goto fail; }