From f35838a6930296fc1988764cfa54cb3f705c0665 Mon Sep 17 00:00:00 2001 From: Jianglei Nie Date: Thu, 9 Dec 2021 14:56:31 +0800 Subject: btrfs: fix memory leak in __add_inode_ref() Line 1169 (#3) allocates a memory chunk for victim_name by kmalloc(), but when the function returns in line 1184 (#4) victim_name allocated by line 1169 (#3) is not freed, which will lead to a memory leak. There is a similar snippet of code in this function as allocating a memory chunk for victim_name in line 1104 (#1) as well as releasing the memory in line 1116 (#2). We should kfree() victim_name when the return value of backref_in_log() is less than zero and before the function returns in line 1184 (#4). 1057 static inline int __add_inode_ref(struct btrfs_trans_handle *trans, 1058 struct btrfs_root *root, 1059 struct btrfs_path *path, 1060 struct btrfs_root *log_root, 1061 struct btrfs_inode *dir, 1062 struct btrfs_inode *inode, 1063 u64 inode_objectid, u64 parent_objectid, 1064 u64 ref_index, char *name, int namelen, 1065 int *search_done) 1066 { 1104 victim_name = kmalloc(victim_name_len, GFP_NOFS); // #1: kmalloc (victim_name-1) 1105 if (!victim_name) 1106 return -ENOMEM; 1112 ret = backref_in_log(log_root, &search_key, 1113 parent_objectid, victim_name, 1114 victim_name_len); 1115 if (ret < 0) { 1116 kfree(victim_name); // #2: kfree (victim_name-1) 1117 return ret; 1118 } else if (!ret) { 1169 victim_name = kmalloc(victim_name_len, GFP_NOFS); // #3: kmalloc (victim_name-2) 1170 if (!victim_name) 1171 return -ENOMEM; 1180 ret = backref_in_log(log_root, &search_key, 1181 parent_objectid, victim_name, 1182 victim_name_len); 1183 if (ret < 0) { 1184 return ret; // #4: missing kfree (victim_name-2) 1185 } else if (!ret) { 1241 return 0; 1242 } Fixes: d3316c8233bb ("btrfs: Properly handle backref_in_log retval") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo Reviewed-by: Filipe Manana Signed-off-by: Jianglei Nie Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3e6f14e13918..8778401665c3 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1181,6 +1181,7 @@ again: parent_objectid, victim_name, victim_name_len); if (ret < 0) { + kfree(victim_name); return ret; } else if (!ret) { ret = -ENOENT; -- cgit v1.2.3 From 33fab972497ae66822c0b6846d4f9382938575b6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 10 Dec 2021 19:02:18 +0000 Subject: btrfs: fix double free of anon_dev after failure to create subvolume When creating a subvolume, at create_subvol(), we allocate an anonymous device and later call btrfs_get_new_fs_root(), which in turn just calls btrfs_get_root_ref(). There we call btrfs_init_fs_root() which assigns the anonymous device to the root, but if after that call there's an error, when we jump to 'fail' label, we call btrfs_put_root(), which frees the anonymous device and then returns an error that is propagated back to create_subvol(). Than create_subvol() frees the anonymous device again. When this happens, if the anonymous device was not reallocated after the first time it was freed with btrfs_put_root(), we get a kernel message like the following: (...) [13950.282466] BTRFS: error (device dm-0) in create_subvol:663: errno=-5 IO failure [13950.283027] ida_free called for id=65 which is not allocated. [13950.285974] BTRFS info (device dm-0): forced readonly (...) If the anonymous device gets reallocated by another btrfs filesystem or any other kernel subsystem, then bad things can happen. So fix this by setting the root's anonymous device to 0 at btrfs_get_root_ref(), before we call btrfs_put_root(), if an error happened. Fixes: 2dfb1e43f57dd3 ("btrfs: preallocate anon block device at first phase of snapshot creation") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 847aabb30676..28449ca66dbd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1732,6 +1732,14 @@ again: } return root; fail: + /* + * If our caller provided us an anonymous device, then it's his + * responsability to free it in case we fail. So we have to set our + * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() + * and once again by our caller. + */ + if (anon_dev) + root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); } -- cgit v1.2.3 From 1b2e5e5c7feabb4f3041f637b96494944da6aeff Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 14 Dec 2021 11:29:01 +0000 Subject: btrfs: fix missing last dir item offset update when logging directory When logging a directory, once we finish processing a leaf that is full of dir items, if we find the next leaf was not modified in the current transaction, we grab the first key of that next leaf and log it as to mark the end of a key range boundary. However we did not update the value of ctx->last_dir_item_offset, which tracks the offset of the last logged key. This can result in subsequent logging of the same directory in the current transaction to not realize that key was already logged, and then add it to the middle of a batch that starts with a lower key, resulting later in a leaf with one key that is duplicated and at non-consecutive slots. When that happens we get an error later when writing out the leaf, reporting that there is a pair of keys in wrong order. The report is something like the following: Dec 13 21:44:50 kernel: BTRFS critical (device dm-0): corrupt leaf: root=18446744073709551610 block=118444032 slot=21, bad key order, prev (704687 84 4146773349) current (704687 84 1063561078) Dec 13 21:44:50 kernel: BTRFS info (device dm-0): leaf 118444032 gen 91449 total ptrs 39 free space 546 owner 18446744073709551610 Dec 13 21:44:50 kernel: item 0 key (704687 1 0) itemoff 3835 itemsize 160 Dec 13 21:44:50 kernel: inode generation 35532 size 1026 mode 40755 Dec 13 21:44:50 kernel: item 1 key (704687 12 704685) itemoff 3822 itemsize 13 Dec 13 21:44:50 kernel: item 2 key (704687 24 3817753667) itemoff 3736 itemsize 86 Dec 13 21:44:50 kernel: item 3 key (704687 60 0) itemoff 3728 itemsize 8 Dec 13 21:44:50 kernel: item 4 key (704687 72 0) itemoff 3720 itemsize 8 Dec 13 21:44:50 kernel: item 5 key (704687 84 140445108) itemoff 3666 itemsize 54 Dec 13 21:44:50 kernel: dir oid 704793 type 1 Dec 13 21:44:50 kernel: item 6 key (704687 84 298800632) itemoff 3599 itemsize 67 Dec 13 21:44:50 kernel: dir oid 707849 type 2 Dec 13 21:44:50 kernel: item 7 key (704687 84 476147658) itemoff 3532 itemsize 67 Dec 13 21:44:50 kernel: dir oid 707901 type 2 Dec 13 21:44:50 kernel: item 8 key (704687 84 633818382) itemoff 3471 itemsize 61 Dec 13 21:44:50 kernel: dir oid 704694 type 2 Dec 13 21:44:50 kernel: item 9 key (704687 84 654256665) itemoff 3403 itemsize 68 Dec 13 21:44:50 kernel: dir oid 707841 type 1 Dec 13 21:44:50 kernel: item 10 key (704687 84 995843418) itemoff 3331 itemsize 72 Dec 13 21:44:50 kernel: dir oid 2167736 type 1 Dec 13 21:44:50 kernel: item 11 key (704687 84 1063561078) itemoff 3278 itemsize 53 Dec 13 21:44:50 kernel: dir oid 704799 type 2 Dec 13 21:44:50 kernel: item 12 key (704687 84 1101156010) itemoff 3225 itemsize 53 Dec 13 21:44:50 kernel: dir oid 704696 type 1 Dec 13 21:44:50 kernel: item 13 key (704687 84 2521936574) itemoff 3173 itemsize 52 Dec 13 21:44:50 kernel: dir oid 704704 type 2 Dec 13 21:44:50 kernel: item 14 key (704687 84 2618368432) itemoff 3112 itemsize 61 Dec 13 21:44:50 kernel: dir oid 704738 type 1 Dec 13 21:44:50 kernel: item 15 key (704687 84 2676316190) itemoff 3046 itemsize 66 Dec 13 21:44:50 kernel: dir oid 2167729 type 1 Dec 13 21:44:50 kernel: item 16 key (704687 84 3319104192) itemoff 2986 itemsize 60 Dec 13 21:44:50 kernel: dir oid 704745 type 2 Dec 13 21:44:50 kernel: item 17 key (704687 84 3908046265) itemoff 2929 itemsize 57 Dec 13 21:44:50 kernel: dir oid 2167734 type 1 Dec 13 21:44:50 kernel: item 18 key (704687 84 3945713089) itemoff 2857 itemsize 72 Dec 13 21:44:50 kernel: dir oid 2167730 type 1 Dec 13 21:44:50 kernel: item 19 key (704687 84 4077169308) itemoff 2795 itemsize 62 Dec 13 21:44:50 kernel: dir oid 704688 type 1 Dec 13 21:44:50 kernel: item 20 key (704687 84 4146773349) itemoff 2727 itemsize 68 Dec 13 21:44:50 kernel: dir oid 707892 type 1 Dec 13 21:44:50 kernel: item 21 key (704687 84 1063561078) itemoff 2674 itemsize 53 Dec 13 21:44:50 kernel: dir oid 704799 type 2 Dec 13 21:44:50 kernel: item 22 key (704687 96 2) itemoff 2612 itemsize 62 Dec 13 21:44:50 kernel: item 23 key (704687 96 6) itemoff 2551 itemsize 61 Dec 13 21:44:50 kernel: item 24 key (704687 96 7) itemoff 2498 itemsize 53 Dec 13 21:44:50 kernel: item 25 key (704687 96 12) itemoff 2446 itemsize 52 Dec 13 21:44:50 kernel: item 26 key (704687 96 14) itemoff 2385 itemsize 61 Dec 13 21:44:50 kernel: item 27 key (704687 96 18) itemoff 2325 itemsize 60 Dec 13 21:44:50 kernel: item 28 key (704687 96 24) itemoff 2271 itemsize 54 Dec 13 21:44:50 kernel: item 29 key (704687 96 28) itemoff 2218 itemsize 53 Dec 13 21:44:50 kernel: item 30 key (704687 96 62) itemoff 2150 itemsize 68 Dec 13 21:44:50 kernel: item 31 key (704687 96 66) itemoff 2083 itemsize 67 Dec 13 21:44:50 kernel: item 32 key (704687 96 75) itemoff 2015 itemsize 68 Dec 13 21:44:50 kernel: item 33 key (704687 96 79) itemoff 1948 itemsize 67 Dec 13 21:44:50 kernel: item 34 key (704687 96 82) itemoff 1882 itemsize 66 Dec 13 21:44:50 kernel: item 35 key (704687 96 83) itemoff 1810 itemsize 72 Dec 13 21:44:50 kernel: item 36 key (704687 96 85) itemoff 1753 itemsize 57 Dec 13 21:44:50 kernel: item 37 key (704687 96 87) itemoff 1681 itemsize 72 Dec 13 21:44:50 kernel: item 38 key (704694 1 0) itemoff 1521 itemsize 160 Dec 13 21:44:50 kernel: inode generation 35534 size 30 mode 40755 Dec 13 21:44:50 kernel: BTRFS error (device dm-0): block=118444032 write time tree block corruption detected So fix that by adding the missing update of ctx->last_dir_item_offset with the offset of the boundary key. Reported-by: Chris Murphy Link: https://lore.kernel.org/linux-btrfs/CAJCQCtT+RSzpUjbMq+UfzNUMe1X5+1G+DnAGbHC=OZ=iRS24jg@mail.gmail.com/ Fixes: dc2872247ec0ca ("btrfs: keep track of the last logged keys when logging a directory") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8778401665c3..6993dcdba6f1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3978,6 +3978,7 @@ search: goto done; } if (btrfs_header_generation(path->nodes[0]) != trans->transid) { + ctx->last_dir_item_offset = min_key.offset; ret = overwrite_item(trans, log, dst_path, path->nodes[0], path->slots[0], &min_key); -- cgit v1.2.3 From 651740a502411793327e2f0741104749c4eedcd1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 13 Dec 2021 14:22:33 -0500 Subject: btrfs: check WRITE_ERR when trying to read an extent buffer Filipe reported a hang when we have errors on btrfs. This turned out to be a side-effect of my fix c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it") which made it so we clear EXTENT_BUFFER_UPTODATE on an eb when we fail to write it out. Below is a paste of Filipe's analysis he got from using drgn to debug the hang """ btree readahead code calls read_extent_buffer_pages(), sets ->io_pages to a value while writeback of all pages has not yet completed: --> writeback for the first 3 pages finishes, we clear EXTENT_BUFFER_UPTODATE from eb on the first page when we get an error. --> at this point eb->io_pages is 1 and we cleared Uptodate bit from the first 3 pages --> read_extent_buffer_pages() does not see EXTENT_BUFFER_UPTODATE() so it continues, it's able to lock the pages since we obviously don't hold the pages locked during writeback --> read_extent_buffer_pages() then computes 'num_reads' as 3, and sets eb->io_pages to 3, since only the first page does not have Uptodate bit set at this point --> writeback for the remaining page completes, we ended decrementing eb->io_pages by 1, resulting in eb->io_pages == 2, and therefore never calling end_extent_buffer_writeback(), so EXTENT_BUFFER_WRITEBACK remains in the eb's flags --> of course, when the read bio completes, it doesn't and shouldn't call end_extent_buffer_writeback() --> we should clear EXTENT_BUFFER_UPTODATE only after all pages of the eb finished writeback? or maybe make the read pages code wait for writeback of all pages of the eb to complete before checking which pages need to be read, touch ->io_pages, submit read bio, etc writeback bit never cleared means we can hang when aborting a transaction, at: btrfs_cleanup_one_transaction() btrfs_destroy_marked_extents() wait_on_extent_buffer_writeback() """ This is a problem because our writes are not synchronized with reads in any way. We clear the UPTODATE flag and then we can easily come in and try to read the EB while we're still waiting on other bio's to complete. We have two options here, we could lock all the pages, and then check to see if eb->io_pages != 0 to know if we've already got an outstanding write on the eb. Or we can simply check to see if we have WRITE_ERR set on this extent buffer. We set this bit _before_ we clear UPTODATE, so if the read gets triggered because we aren't UPTODATE because of a write error we're guaranteed to have WRITE_ERR set, and in this case we can simply return -EIO. This will fix the reported hang. Reported-by: Filipe Manana Fixes: c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- 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 3258b6f01e85..9234d96a7fd5 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -6611,6 +6611,14 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; + /* + * We could have had EXTENT_BUFFER_UPTODATE cleared by the write + * operation, which could potentially still be in flight. In this case + * we simply want to return an error. + */ + if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))) + return -EIO; + if (eb->fs_info->sectorsize < PAGE_SIZE) return read_extent_buffer_subpage(eb, wait, mirror_num); -- cgit v1.2.3 From 7a1636089acfee7562fe79aff7d1b4c57869896d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 13 Dec 2021 08:45:12 +0000 Subject: btrfs: fix invalid delayed ref after subvolume creation failure When creating a subvolume, at ioctl.c:create_subvol(), if we fail to insert the new root's root item into the root tree, we are freeing the metadata extent we reserved for the new root to prevent a metadata extent leak, as we don't abort the transaction at that point (since there is nothing at that point that is irreversible). However we allocated the metadata extent for the new root which we are creating for the new subvolume, so its delayed reference refers to the ID of this new root. But when we free the metadata extent we pass the root of the subvolume where the new subvolume is located to btrfs_free_tree_block() - this is incorrect because this will generate a delayed reference that refers to the ID of the parent subvolume's root, and not to ID of the new root. This results in a failure when running delayed references that leads to a transaction abort and a trace like the following: [3868.738042] RIP: 0010:__btrfs_free_extent+0x709/0x950 [btrfs] [3868.739857] Code: 68 0f 85 e6 fb ff (...) [3868.742963] RSP: 0018:ffffb0e9045cf910 EFLAGS: 00010246 [3868.743908] RAX: 00000000fffffffe RBX: 00000000fffffffe RCX: 0000000000000002 [3868.745312] RDX: 00000000fffffffe RSI: 0000000000000002 RDI: ffff90b0cd793b88 [3868.746643] RBP: 000000000e5d8000 R08: 0000000000000000 R09: ffff90b0cd793b88 [3868.747979] R10: 0000000000000002 R11: 00014ded97944d68 R12: 0000000000000000 [3868.749373] R13: ffff90b09afe4a28 R14: 0000000000000000 R15: ffff90b0cd793b88 [3868.750725] FS: 00007f281c4a8b80(0000) GS:ffff90b3ada00000(0000) knlGS:0000000000000000 [3868.752275] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [3868.753515] CR2: 00007f281c6a5000 CR3: 0000000108a42006 CR4: 0000000000370ee0 [3868.754869] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [3868.756228] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [3868.757803] Call Trace: [3868.758281] [3868.758655] ? btrfs_merge_delayed_refs+0x178/0x1c0 [btrfs] [3868.759827] __btrfs_run_delayed_refs+0x2b1/0x1250 [btrfs] [3868.761047] btrfs_run_delayed_refs+0x86/0x210 [btrfs] [3868.762069] ? lock_acquired+0x19f/0x420 [3868.762829] btrfs_commit_transaction+0x69/0xb20 [btrfs] [3868.763860] ? _raw_spin_unlock+0x29/0x40 [3868.764614] ? btrfs_block_rsv_release+0x1c2/0x1e0 [btrfs] [3868.765870] create_subvol+0x1d8/0x9a0 [btrfs] [3868.766766] btrfs_mksubvol+0x447/0x4c0 [btrfs] [3868.767669] ? preempt_count_add+0x49/0xa0 [3868.768444] __btrfs_ioctl_snap_create+0x123/0x190 [btrfs] [3868.769639] ? _copy_from_user+0x66/0xa0 [3868.770391] btrfs_ioctl_snap_create_v2+0xbb/0x140 [btrfs] [3868.771495] btrfs_ioctl+0xd1e/0x35c0 [btrfs] [3868.772364] ? __slab_free+0x10a/0x360 [3868.773198] ? rcu_read_lock_sched_held+0x12/0x60 [3868.774121] ? lock_release+0x223/0x4a0 [3868.774863] ? lock_acquired+0x19f/0x420 [3868.775634] ? rcu_read_lock_sched_held+0x12/0x60 [3868.776530] ? trace_hardirqs_on+0x1b/0xe0 [3868.777373] ? _raw_spin_unlock_irqrestore+0x3e/0x60 [3868.778280] ? kmem_cache_free+0x321/0x3c0 [3868.779011] ? __x64_sys_ioctl+0x83/0xb0 [3868.779718] __x64_sys_ioctl+0x83/0xb0 [3868.780387] do_syscall_64+0x3b/0xc0 [3868.781059] entry_SYSCALL_64_after_hwframe+0x44/0xae [3868.781953] RIP: 0033:0x7f281c59e957 [3868.782585] Code: 3c 1c 48 f7 d8 4c (...) [3868.785867] RSP: 002b:00007ffe1f83e2b8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 [3868.787198] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281c59e957 [3868.788450] RDX: 00007ffe1f83e2c0 RSI: 0000000050009418 RDI: 0000000000000003 [3868.789748] RBP: 00007ffe1f83f300 R08: 0000000000000000 R09: 00007ffe1f83fe36 [3868.791214] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000003 [3868.792468] R13: 0000000000000003 R14: 00007ffe1f83e2c0 R15: 00000000000003cc [3868.793765] [3868.794037] irq event stamp: 0 [3868.794548] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [3868.795670] hardirqs last disabled at (0): [] copy_process+0x934/0x2040 [3868.797086] softirqs last enabled at (0): [] copy_process+0x934/0x2040 [3868.798309] softirqs last disabled at (0): [<0000000000000000>] 0x0 [3868.799284] ---[ end trace be24c7002fe27747 ]--- [3868.799928] BTRFS info (device dm-0): leaf 241188864 gen 1268 total ptrs 214 free space 469 owner 2 [3868.801133] BTRFS info (device dm-0): refs 2 lock_owner 225627 current 225627 [3868.802056] item 0 key (237436928 169 0) itemoff 16250 itemsize 33 [3868.802863] extent refs 1 gen 1265 flags 2 [3868.803447] ref#0: tree block backref root 1610 (...) [3869.064354] item 114 key (241008640 169 0) itemoff 12488 itemsize 33 [3869.065421] extent refs 1 gen 1268 flags 2 [3869.066115] ref#0: tree block backref root 1689 (...) [3869.403834] BTRFS error (device dm-0): unable to find ref byte nr 241008640 parent 0 root 1622 owner 0 offset 0 [3869.405641] BTRFS: error (device dm-0) in __btrfs_free_extent:3076: errno=-2 No such entry [3869.407138] BTRFS: error (device dm-0) in btrfs_run_delayed_refs:2159: errno=-2 No such entry Fix this by passing the new subvolume's root ID to btrfs_free_tree_block(). This requires changing the root argument of btrfs_free_tree_block() from struct btrfs_root * to a u64, since at this point during the subvolume creation we have not yet created the struct btrfs_root for the new subvolume, and btrfs_free_tree_block() only needs a root ID and nothing else from a struct btrfs_root. This was triggered by test case generic/475 from fstests. Fixes: 67addf29004c5b ("btrfs: fix metadata extent leak after failure to create subvolume") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Nikolay Borisov Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 17 +++++++++-------- fs/btrfs/ctree.h | 7 ++++++- fs/btrfs/extent-tree.c | 13 +++++++------ fs/btrfs/free-space-tree.c | 4 ++-- fs/btrfs/ioctl.c | 9 +++++---- fs/btrfs/qgroup.c | 3 ++- 6 files changed, 31 insertions(+), 22 deletions(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 74c8e18f3720..64599625c7d7 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -462,8 +462,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, BUG_ON(ret < 0); rcu_assign_pointer(root->node, cow); - btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + btrfs_free_tree_block(trans, btrfs_root_id(root), buf, + parent_start, last_ref); free_extent_buffer(buf); add_root_to_dirty_list(root); } else { @@ -484,8 +484,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } } - btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + btrfs_free_tree_block(trans, btrfs_root_id(root), buf, + parent_start, last_ref); } if (unlock_orig) btrfs_tree_unlock(buf); @@ -926,7 +926,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, free_extent_buffer(mid); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); /* once for the root ptr */ free_extent_buffer_stale(mid); return 0; @@ -985,7 +985,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_tree_unlock(right); del_ptr(root, path, level + 1, pslot + 1); root_sub_used(root, right->len); - btrfs_free_tree_block(trans, root, right, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), right, + 0, 1); free_extent_buffer_stale(right); right = NULL; } else { @@ -1030,7 +1031,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_tree_unlock(mid); del_ptr(root, path, level + 1, pslot); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); free_extent_buffer_stale(mid); mid = NULL; } else { @@ -4031,7 +4032,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); atomic_inc(&leaf->refs); - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1); free_extent_buffer_stale(leaf); } /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7553e9dc5f93..5fe5eccb3c87 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2257,6 +2257,11 @@ static inline bool btrfs_root_dead(const struct btrfs_root *root) return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0; } +static inline u64 btrfs_root_id(const struct btrfs_root *root) +{ + return root->root_key.objectid; +} + /* struct btrfs_root_backup */ BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup, tree_root, 64); @@ -2719,7 +2724,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, u64 empty_size, enum btrfs_lock_nesting nest); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref); int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index fc4895e6a62c..25ef6e3fd306 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3275,20 +3275,20 @@ out_delayed_unlock: } void btrfs_free_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_ref generic_ref = { 0 }; int ret; btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, buf->start, buf->len, parent); btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), - root->root_key.objectid, 0, false); + root_id, 0, false); - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + if (root_id != BTRFS_TREE_LOG_OBJECTID) { btrfs_ref_tree_mod(fs_info, &generic_ref); ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); BUG_ON(ret); /* -ENOMEM */ @@ -3298,7 +3298,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; bool must_pin = false; - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + if (root_id != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); if (!ret) { btrfs_redirty_list_add(trans->transaction, buf); @@ -5472,7 +5472,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, goto owner_mismatch; } - btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent, + wc->refs[level] == 1); out: wc->refs[level] = 0; wc->flags[level] = 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index a33bca94d133..3abec44c6255 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1256,8 +1256,8 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_tree_lock(free_space_root->node); btrfs_clean_tree_block(free_space_root->node); btrfs_tree_unlock(free_space_root->node); - btrfs_free_tree_block(trans, free_space_root, free_space_root->node, - 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(free_space_root), + free_space_root->node, 0, 1); btrfs_put_root(free_space_root); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1b85d98df66b..a7533416370a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -617,11 +617,12 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, * Since we don't abort the transaction in this case, free the * tree block so that we don't leak space and leave the * filesystem in an inconsistent state (an extent item in the - * extent tree without backreferences). Also no need to have - * the tree block locked since it is not in any tree at this - * point, so no other task can find it and use it. + * extent tree with a backreference for a root that does not + * exists). Also no need to have the tree block locked since it + * is not in any tree at this point, so no other task can find + * it and use it. */ - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, objectid, leaf, 0, 1); free_extent_buffer(leaf); goto fail; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index db680f5be745..6c037f1252b7 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1219,7 +1219,8 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_tree_lock(quota_root->node); btrfs_clean_tree_block(quota_root->node); btrfs_tree_unlock(quota_root->node); - btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(quota_root), + quota_root->node, 0, 1); btrfs_put_root(quota_root); -- cgit v1.2.3 From 212a58fda9b9077e0efc20200a4feb76afacfd95 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 13 Dec 2021 08:45:13 +0000 Subject: btrfs: fix warning when freeing leaf after subvolume creation failure When creating a subvolume, at ioctl.c:create_subvol(), if we fail to insert the root item for the new subvolume into the root tree, we can trigger the following warning: [78961.741046] WARNING: CPU: 0 PID: 4079814 at fs/btrfs/extent-tree.c:3357 btrfs_free_tree_block+0x2af/0x310 [btrfs] [78961.743344] Modules linked in: [78961.749440] dm_snapshot dm_thin_pool (...) [78961.773648] CPU: 0 PID: 4079814 Comm: fsstress Not tainted 5.16.0-rc4-btrfs-next-108 #1 [78961.775198] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [78961.777266] RIP: 0010:btrfs_free_tree_block+0x2af/0x310 [btrfs] [78961.778398] Code: 17 00 48 85 (...) [78961.781067] RSP: 0018:ffffaa4001657b28 EFLAGS: 00010202 [78961.781877] RAX: 0000000000000213 RBX: ffff897f8a796910 RCX: 0000000000000000 [78961.782780] RDX: 0000000000000000 RSI: 0000000011004000 RDI: 00000000ffffffff [78961.783764] RBP: ffff8981f490e800 R08: 0000000000000001 R09: 0000000000000000 [78961.784740] R10: 0000000000000000 R11: 0000000000000001 R12: ffff897fc963fcc8 [78961.785665] R13: 0000000000000001 R14: ffff898063548000 R15: ffff898063548000 [78961.786620] FS: 00007f31283c6b80(0000) GS:ffff8982ace00000(0000) knlGS:0000000000000000 [78961.787717] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78961.788598] CR2: 00007f31285c3000 CR3: 000000023fcc8003 CR4: 0000000000370ef0 [78961.789568] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78961.790585] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78961.791684] Call Trace: [78961.792082] [78961.792359] create_subvol+0x5d1/0x9a0 [btrfs] [78961.793054] btrfs_mksubvol+0x447/0x4c0 [btrfs] [78961.794009] ? preempt_count_add+0x49/0xa0 [78961.794705] __btrfs_ioctl_snap_create+0x123/0x190 [btrfs] [78961.795712] ? _copy_from_user+0x66/0xa0 [78961.796382] btrfs_ioctl_snap_create_v2+0xbb/0x140 [btrfs] [78961.797392] btrfs_ioctl+0xd1e/0x35c0 [btrfs] [78961.798172] ? __slab_free+0x10a/0x360 [78961.798820] ? rcu_read_lock_sched_held+0x12/0x60 [78961.799664] ? lock_release+0x223/0x4a0 [78961.800321] ? lock_acquired+0x19f/0x420 [78961.800992] ? rcu_read_lock_sched_held+0x12/0x60 [78961.801796] ? trace_hardirqs_on+0x1b/0xe0 [78961.802495] ? _raw_spin_unlock_irqrestore+0x3e/0x60 [78961.803358] ? kmem_cache_free+0x321/0x3c0 [78961.804071] ? __x64_sys_ioctl+0x83/0xb0 [78961.804711] __x64_sys_ioctl+0x83/0xb0 [78961.805348] do_syscall_64+0x3b/0xc0 [78961.805969] entry_SYSCALL_64_after_hwframe+0x44/0xae [78961.806830] RIP: 0033:0x7f31284bc957 [78961.807517] Code: 3c 1c 48 f7 d8 (...) This is because we are calling btrfs_free_tree_block() on an extent buffer that is dirty. Fix that by cleaning the extent buffer, with btrfs_clean_tree_block(), before freeing it. This was triggered by test case generic/475 from fstests. Fixes: 67addf29004c5b ("btrfs: fix metadata extent leak after failure to create subvolume") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Nikolay Borisov Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a7533416370a..8a442b59eee0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -618,10 +618,11 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, * tree block so that we don't leak space and leave the * filesystem in an inconsistent state (an extent item in the * extent tree with a backreference for a root that does not - * exists). Also no need to have the tree block locked since it - * is not in any tree at this point, so no other task can find - * it and use it. + * exists). */ + btrfs_tree_lock(leaf); + btrfs_clean_tree_block(leaf); + btrfs_tree_unlock(leaf); btrfs_free_tree_block(trans, objectid, leaf, 0, 1); free_extent_buffer(leaf); goto fail; -- cgit v1.2.3 From 4989d4a0aed3fb30f5b48787a689d7090de6f86d Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Wed, 15 Dec 2021 19:38:43 +0900 Subject: btrfs: fix missing blkdev_put() call in btrfs_scan_one_device() The function btrfs_scan_one_device() calls blkdev_get_by_path() and blkdev_put() to get and release its target block device. However, when btrfs_sb_log_location_bdev() fails, blkdev_put() is not called and the block device is left without clean up. This triggered failure of fstests generic/085. Fix the failure path of btrfs_sb_log_location_bdev() to call blkdev_put(). Fixes: 12659251ca5df ("btrfs: implement log-structured superblock for ZONED mode") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Nikolay Borisov Signed-off-by: Shin'ichiro Kawasaki Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cc80f2a97a0b..b4da58fd0e1a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1370,8 +1370,10 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, bytenr_orig = btrfs_sb_offset(0); ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr); - if (ret) - return ERR_PTR(ret); + if (ret) { + device = ERR_PTR(ret); + goto error_bdev_put; + } disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig); if (IS_ERR(disk_super)) { -- cgit v1.2.3