From e89166990f11c3f21e1649d760dd35f9e410321c Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 25 Jan 2018 11:02:50 -0700 Subject: [PATCH 01/10] Btrfs: fix deadlock in run_delalloc_nocow @cur_offset is not set back to what it should be (@cow_start) if btrfs_next_leaf() returns something wrong, and the range [cow_start, cur_offset) remains locked forever. cc: Signed-off-by: Liu Bo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c5f31817778b..a68a4acd16e5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1334,8 +1334,11 @@ next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); - if (ret < 0) + if (ret < 0) { + if (cow_start != (u64)-1) + cur_offset = cow_start; goto error; + } if (ret > 0) break; leaf = path->nodes[0]; From 1846430c24d66e85cc58286b3319c82cd54debb2 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 25 Jan 2018 11:02:51 -0700 Subject: [PATCH 02/10] Btrfs: fix crash due to not cleaning up tree log block's dirty bits In cases that the whole fs flips into readonly status due to failures in critical sections, then log tree's blocks are still dirty, and this leads to a crash during umount time, the crash is about use-after-free, umount -> close_ctree -> stop workers -> iput(btree_inode) -> iput_final -> write_inode_now -> ... -> queue job on stop'd workers cc: v3.12+ Fixes: 681ae50917df ("Btrfs: cleanup reserved space when freeing tree log on error") Signed-off-by: Liu Bo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ee1aaed1330e..1920c2149f88 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2471,6 +2471,9 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(root_owner != @@ -2551,6 +2554,9 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID); @@ -2629,6 +2635,9 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(log->root_key.objectid != From 55237a5f2431a72435e3ed39e4306e973c0446b7 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 25 Jan 2018 11:02:52 -0700 Subject: [PATCH 03/10] Btrfs: fix extent state leak from tree log It's possible that btrfs_sync_log() bails out after one of the two btrfs_write_marked_extents() which convert extent state's state bit into EXTENT_NEED_WAIT from EXTENT_DIRTY/EXTENT_NEW, however only EXTENT_DIRTY and EXTENT_NEW are searched by free_log_tree() so that those extent states with EXTENT_NEED_WAIT lead to memory leak. cc: Signed-off-by: Liu Bo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1920c2149f88..79af4ae042ae 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3026,13 +3026,14 @@ static void free_log_tree(struct btrfs_trans_handle *trans, while (1) { ret = find_first_extent_bit(&log->dirty_log_pages, - 0, &start, &end, EXTENT_DIRTY | EXTENT_NEW, + 0, &start, &end, + EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT, NULL); if (ret) break; clear_extent_bits(&log->dirty_log_pages, start, end, - EXTENT_DIRTY | EXTENT_NEW); + EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); } /* From e8f1bc1493855e32b7a2a019decc3c353d94daf6 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 25 Jan 2018 11:02:53 -0700 Subject: [PATCH 04/10] Btrfs: fix btrfs_evict_inode to handle abnormal inodes correctly This regression is introduced in commit 3d48d9810de4 ("btrfs: Handle uninitialised inode eviction"). There are two problems, a) it is ->destroy_inode() that does the final free on inode, not ->evict_inode(), b) clear_inode() must be called before ->evict_inode() returns. This could end up hitting BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); in evict() because I_CLEAR is set in clear_inode(). Fixes: commit 3d48d9810de4 ("btrfs: Handle uninitialised inode eviction") Cc: # v4.7-rc6+ Signed-off-by: Liu Bo Reviewed-by: Nikolay Borisov Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a68a4acd16e5..44a152d8f32f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5281,7 +5281,7 @@ void btrfs_evict_inode(struct inode *inode) trace_btrfs_inode_evict(inode); if (!root) { - kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode)); + clear_inode(inode); return; } From 1a932ef4e47984dee227834667b5ff5a334e4805 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 25 Jan 2018 11:02:54 -0700 Subject: [PATCH 05/10] Btrfs: fix use-after-free on root->orphan_block_rsv I got these from running generic/475, WARNING: CPU: 0 PID: 26384 at fs/btrfs/inode.c:3326 btrfs_orphan_commit_root+0x1ac/0x2b0 [btrfs] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: btrfs_block_rsv_release+0x1c/0x70 [btrfs] Call Trace: btrfs_orphan_release_metadata+0x9f/0x200 [btrfs] btrfs_orphan_del+0x10d/0x170 [btrfs] btrfs_setattr+0x500/0x640 [btrfs] notify_change+0x7ae/0x870 do_truncate+0xca/0x130 vfs_truncate+0x2ee/0x3d0 do_sys_truncate+0xaf/0xf0 SyS_truncate+0xe/0x10 entry_SYSCALL_64_fastpath+0x1f/0x96 The race is between btrfs_orphan_commit_root and btrfs_orphan_del, t1 t2 btrfs_orphan_commit_root btrfs_orphan_del spin_lock check (&root->orphan_inodes) root->orphan_block_rsv = NULL; spin_unlock atomic_dec(&root->orphan_inodes); access root->orphan_block_rsv Accessing root->orphan_block_rsv must be done before decreasing root->orphan_inodes. cc: v3.12+ Fixes: 703c88e03524 ("Btrfs: fix tracking of orphan inode count") Signed-off-by: Liu Bo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 44a152d8f32f..29b491328f4e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3387,6 +3387,11 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, ret = btrfs_orphan_reserve_metadata(trans, inode); ASSERT(!ret); if (ret) { + /* + * dec doesn't need spin_lock as ->orphan_block_rsv + * would be released only if ->orphan_inodes is + * zero. + */ atomic_dec(&root->orphan_inodes); clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); @@ -3401,12 +3406,17 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, if (insert >= 1) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret) { - atomic_dec(&root->orphan_inodes); if (reserve) { clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); btrfs_orphan_release_metadata(inode); } + /* + * btrfs_orphan_commit_root may race with us and set + * ->orphan_block_rsv to zero, in order to avoid that, + * decrease ->orphan_inodes after everything is done. + */ + atomic_dec(&root->orphan_inodes); if (ret != -EEXIST) { clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &inode->runtime_flags); @@ -3438,29 +3448,27 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; int delete_item = 0; - int release_rsv = 0; int ret = 0; - spin_lock(&root->orphan_lock); if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &inode->runtime_flags)) delete_item = 1; + if (delete_item && trans) + ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); + if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags)) - release_rsv = 1; - spin_unlock(&root->orphan_lock); - - if (delete_item) { - atomic_dec(&root->orphan_inodes); - if (trans) - ret = btrfs_del_orphan_item(trans, root, - btrfs_ino(inode)); - } - - if (release_rsv) btrfs_orphan_release_metadata(inode); + /* + * btrfs_orphan_commit_root may race with us and set ->orphan_block_rsv + * to zero, in order to avoid that, decrease ->orphan_inodes after + * everything is done. + */ + if (delete_item) + atomic_dec(&root->orphan_inodes); + return ret; } From 900c9981680067573671ecc5cbfa7c5770be3a40 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 25 Jan 2018 11:02:56 -0700 Subject: [PATCH 06/10] Btrfs: fix unexpected -EEXIST when creating new inode The highest objectid, which is assigned to new inode, is decided at the time of initializing fs roots. However, in cases where log replay gets processed, the btree which fs root owns might be changed, so we have to search it again for the highest objectid, otherwise creating new inode would end up with -EEXIST. cc: v4.4-rc6+ Fixes: f32e48e92596 ("Btrfs: Initialize btrfs_root->highest_objectid when loading tree root and subvolume roots") Signed-off-by: Liu Bo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 79af4ae042ae..61f20c367aaf 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -28,6 +28,7 @@ #include "hash.h" #include "compression.h" #include "qgroup.h" +#include "inode-map.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -5685,6 +5686,23 @@ again: path); } + if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { + struct btrfs_root *root = wc.replay_dest; + + btrfs_release_path(path); + + /* + * We have just replayed everything, and the highest + * objectid of fs roots probably has changed in case + * some inode_item's got replayed. + * + * root->objectid_mutex is not acquired as log replay + * could only happen during mount. + */ + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + } + key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); From 952bd3db0dada9994fa7edd891178075abcc045d Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 29 Jan 2018 15:53:01 +0200 Subject: [PATCH 07/10] btrfs: Ignore errors from btrfs_qgroup_trace_extent_post Running generic/019 with qgroups on the scratch device enabled is almost guaranteed to trigger the BUG_ON in btrfs_free_tree_block. It's supposed to trigger only on -ENOMEM, in reality, however, it's possible to get -EIO from btrfs_qgroup_trace_extent_post. This function just finds the roots of the extent being tracked and sets the qrecord->old_roots list. If this operation fails nothing critical happens except the quota accounting can be considered wrong. In such case just set the INCONSISTENT flag for the quota and print a warning, rather than killing off the system. Additionally, it's possible to trigger a BUG_ON in btrfs_truncate_inode_items as well. Signed-off-by: Nikolay Borisov Reviewed-by: Qu Wenruo [ error message adjustments ] Signed-off-by: David Sterba --- fs/btrfs/delayed-ref.c | 3 ++- fs/btrfs/qgroup.c | 9 +++++++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index a1a40cf382e3..7ab5e0128f0c 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -821,7 +821,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, spin_unlock(&delayed_refs->lock); if (qrecord_inserted) - return btrfs_qgroup_trace_extent_post(fs_info, record); + btrfs_qgroup_trace_extent_post(fs_info, record); + return 0; free_head_ref: diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9e61dd624f7b..aa259d6986e1 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1442,8 +1442,13 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, int ret; ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false); - if (ret < 0) - return ret; + if (ret < 0) { + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + btrfs_warn(fs_info, +"error accounting new delayed refs extent (err code: %d), quota inconsistent", + ret); + return 0; + } /* * Here we don't need to get the lock of From c8195a7b1ad5648857ce20ba24f384faed8512bc Mon Sep 17 00:00:00 2001 From: Zygo Blaxell Date: Tue, 23 Jan 2018 22:22:09 -0500 Subject: [PATCH 08/10] btrfs: remove spurious WARN_ON(ref->count < 0) in find_parent_nodes Until v4.14, this warning was very infrequent: WARNING: CPU: 3 PID: 18172 at fs/btrfs/backref.c:1391 find_parent_nodes+0xc41/0x14e0 Modules linked in: [...] CPU: 3 PID: 18172 Comm: bees Tainted: G D W L 4.11.9-zb64+ #1 Hardware name: System manufacturer System Product Name/M5A78L-M/USB3, BIOS 2101 12/02/2014 Call Trace: dump_stack+0x85/0xc2 __warn+0xd1/0xf0 warn_slowpath_null+0x1d/0x20 find_parent_nodes+0xc41/0x14e0 __btrfs_find_all_roots+0xad/0x120 ? extent_same_check_offsets+0x70/0x70 iterate_extent_inodes+0x168/0x300 iterate_inodes_from_logical+0x87/0xb0 ? iterate_inodes_from_logical+0x87/0xb0 ? extent_same_check_offsets+0x70/0x70 btrfs_ioctl+0x8ac/0x2820 ? lock_acquire+0xc2/0x200 do_vfs_ioctl+0x91/0x700 ? __fget+0x112/0x200 SyS_ioctl+0x79/0x90 entry_SYSCALL_64_fastpath+0x23/0xc6 ? trace_hardirqs_off_caller+0x1f/0x140 Starting with v4.14 (specifically 86d5f9944252 ("btrfs: convert prelimary reference tracking to use rbtrees")) the WARN_ON occurs three orders of magnitude more frequently--almost once per second while running workloads like bees. Replace the WARN_ON() with a comment rationale for its removal. The rationale is paraphrased from an explanation by Edmund Nadolski on the linux-btrfs mailing list. Fixes: 8da6d5815c59 ("Btrfs: added btrfs_find_all_roots()") Signed-off-by: Zygo Blaxell Reviewed-by: Lu Fengqi Signed-off-by: David Sterba --- fs/btrfs/backref.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e4054e533f6d..f94b2d8c744a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1264,7 +1264,16 @@ again: while (node) { ref = rb_entry(node, struct prelim_ref, rbnode); node = rb_next(&ref->rbnode); - WARN_ON(ref->count < 0); + /* + * ref->count < 0 can happen here if there are delayed + * refs with a node->action of BTRFS_DROP_DELAYED_REF. + * prelim_ref_insert() relies on this when merging + * identical refs to keep the overall count correct. + * prelim_ref_insert() will merge only those refs + * which compare identically. Any refs having + * e.g. different offsets would not be merged, + * and would retain their original ref->count < 0. + */ if (roots && ref->count && ref->root_id && ref->parent == 0) { if (sc && sc->root_objectid && ref->root_id != sc->root_objectid) { From 627e08738e4315458c5df06358ce7a65cfdd635d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 30 Jan 2018 18:40:22 +0000 Subject: [PATCH 09/10] Btrfs: fix null pointer dereference when replacing missing device When we are replacing a missing device we mount the filesystem with the degraded mode option in which case we are allowed to have a btrfs device structure without a backing device member (its bdev member is NULL) and therefore we can't dereference that member. Commit 38b5f68e9811 ("btrfs: drop btrfs_device::can_discard to query directly") started to dereference that member when discarding extents, resulting in a null pointer dereference: [ 3145.322257] BTRFS warning (device sdf): devid 2 uuid 4d922414-58eb-4880-8fed-9c3840f6c5d5 is missing [ 3145.364116] BTRFS info (device sdf): dev_replace from (devid 2) to /dev/sdg started [ 3145.413489] BUG: unable to handle kernel NULL pointer dereference at 00000000000000e0 [ 3145.415085] IP: btrfs_discard_extent+0x6a/0xf8 [btrfs] [ 3145.415085] PGD 0 P4D 0 [ 3145.415085] Oops: 0000 [#1] PREEMPT SMP PTI [ 3145.415085] Modules linked in: ppdev ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd glue_helper evdev psmouse parport_pc serio_raw i2c_piix4 i2 [ 3145.415085] CPU: 0 PID: 11989 Comm: btrfs Tainted: G W 4.15.0-rc9-btrfs-next-55+ #1 [ 3145.415085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014 [ 3145.415085] RIP: 0010:btrfs_discard_extent+0x6a/0xf8 [btrfs] [ 3145.415085] RSP: 0018:ffffc90004813c60 EFLAGS: 00010293 [ 3145.415085] RAX: ffff88020d39cc00 RBX: ffff88020c4ea2a0 RCX: 0000000000000002 [ 3145.415085] RDX: 0000000000000000 RSI: ffff88020c4ea240 RDI: 0000000000000000 [ 3145.415085] RBP: 0000000000000000 R08: 0000000000004000 R09: 0000000000000000 [ 3145.415085] R10: ffffc90004813ae8 R11: 0000000000000000 R12: 0000000000000000 [ 3145.415085] R13: ffff88020c418000 R14: 0000000000000000 R15: 0000000000000000 [ 3145.415085] FS: 00007f565681f8c0(0000) GS:ffff88023fc00000(0000) knlGS:0000000000000000 [ 3145.415085] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3145.415085] CR2: 00000000000000e0 CR3: 000000020d208006 CR4: 00000000001606f0 [ 3145.415085] Call Trace: [ 3145.415085] btrfs_finish_extent_commit+0x9a/0x1be [btrfs] [ 3145.415085] btrfs_commit_transaction+0x649/0x7a0 [btrfs] [ 3145.415085] ? start_transaction+0x2b0/0x3b3 [btrfs] [ 3145.415085] btrfs_dev_replace_start+0x274/0x30c [btrfs] [ 3145.415085] btrfs_dev_replace_by_ioctl+0x45/0x59 [btrfs] [ 3145.415085] btrfs_ioctl+0x1a91/0x1d62 [btrfs] [ 3145.415085] ? lock_acquire+0x16a/0x1af [ 3145.415085] ? vfs_ioctl+0x1b/0x28 [ 3145.415085] ? trace_hardirqs_on_caller+0x14c/0x1a6 [ 3145.415085] vfs_ioctl+0x1b/0x28 [ 3145.415085] do_vfs_ioctl+0x5a9/0x5e0 [ 3145.415085] ? _raw_spin_unlock_irq+0x34/0x46 [ 3145.415085] ? entry_SYSCALL_64_fastpath+0x5/0x8b [ 3145.415085] ? trace_hardirqs_on_caller+0x14c/0x1a6 [ 3145.415085] SyS_ioctl+0x52/0x76 [ 3145.415085] entry_SYSCALL_64_fastpath+0x1e/0x8b [ 3145.415085] RIP: 0033:0x7f56558b3c47 [ 3145.415085] RSP: 002b:00007ffdcfac4c58 EFLAGS: 00000202 [ 3145.415085] Code: be 02 00 00 00 4c 89 ef e8 b9 e7 03 00 85 c0 89 c5 75 75 48 8b 44 24 08 45 31 f6 48 8d 58 60 eb 52 48 8b 03 48 8b b8 a0 00 00 00 <48> 8b 87 e0 00 [ 3145.415085] RIP: btrfs_discard_extent+0x6a/0xf8 [btrfs] RSP: ffffc90004813c60 [ 3145.415085] CR2: 00000000000000e0 [ 3145.458185] ---[ end trace 06302e7ac31902bf ]--- This is trivially reproduced by running the test btrfs/027 from fstests like this: $ MOUNT_OPTIONS="-o discard" ./check btrfs/027 Fix this by skipping devices without a backing device before attempting to discard. Fixes: 38b5f68e9811 ("btrfs: drop btrfs_device::can_discard to query directly") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 05751a677da4..c1618ab9fecf 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2147,6 +2147,10 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 bytes; struct request_queue *req_q; + if (!stripe->dev->bdev) { + ASSERT(btrfs_test_opt(fs_info, DEGRADED)); + continue; + } req_q = bdev_get_queue(stripe->dev->bdev); if (!blk_queue_discard(req_q)) continue; From fd649f10c3d21ee9d7542c609f29978bdf73ab94 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 30 Jan 2018 16:07:37 +0200 Subject: [PATCH 10/10] btrfs: Fix use-after-free when cleaning up fs_devs with a single stale device Commit 4fde46f0cc71 ("Btrfs: free the stale device") introduced btrfs_free_stale_device which iterates the device lists for all registered btrfs filesystems and deletes those devices which aren't mounted. In a btrfs_devices structure has only 1 device attached to it and it is unused then btrfs_free_stale_devices will proceed to also free the btrfs_fs_devices struct itself. Currently this leads to a use after free since list_for_each_entry will try to perform a check on the already freed memory to see if it has to terminate the loop. The fix is to use 'break' when we know we are freeing the current fs_devs. Fixes: 4fde46f0cc71 ("Btrfs: free the stale device") Signed-off-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b5036bd69e6a..2ceb924ca0d6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -645,6 +645,7 @@ static void btrfs_free_stale_devices(const char *path, btrfs_sysfs_remove_fsid(fs_devs); list_del(&fs_devs->list); free_fs_devices(fs_devs); + break; } else { fs_devs->num_devices--; list_del(&dev->dev_list);