From d815b3f2f273537cb8afaf5ab11a46851f6c03e5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 16 Nov 2021 14:50:25 +0300 Subject: btrfs: fix error pointer dereference in btrfs_ioctl_rm_dev_v2() If memdup_user() fails the error handing will crash when it tries to kfree() an error pointer. Just return directly because there is no cleanup required. Fixes: 1a15eb724aae ("btrfs: use btrfs_get_dev_args_from_path in dev removal ioctls") Reviewed-by: Josef Bacik Signed-off-by: Dan Carpenter Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 012fbfdfbebf..1b85d98df66b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3188,10 +3188,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) return -EPERM; vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) { - ret = PTR_ERR(vol_args); - goto out; - } + if (IS_ERR(vol_args)) + return PTR_ERR(vol_args); if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) { ret = -EOPNOTSUPP; -- cgit From f981fec12cc5d2c07942301744b9ea61228bf246 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 22 Nov 2021 17:04:19 -0500 Subject: btrfs: fail if fstrim_range->start == U64_MAX We've always been failing generic/260 because it's testing things we actually don't care about and thus won't fail for. However we probably should fail for fstrim_range->start == U64_MAX since we clearly can't trim anything past that. This in combination with an update to generic/260 will allow us to pass this test properly. Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3fd736a02c1e..fc4895e6a62c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6051,6 +6051,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) int dev_ret = 0; int ret = 0; + if (range->start == U64_MAX) + return -EINVAL; + /* * Check range overflow if range->len is set. * The default range->len is U64_MAX. -- cgit From c2e39305299f0118298c2201f6d6cc7d3485f29e Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 24 Nov 2021 14:14:23 -0500 Subject: btrfs: clear extent buffer uptodate when we fail to write it I got dmesg errors on generic/281 on our overnight fstests. Looking at the history this happens occasionally, with errors like this WARNING: CPU: 0 PID: 673217 at fs/btrfs/extent_io.c:6848 assert_eb_page_uptodate+0x3f/0x50 CPU: 0 PID: 673217 Comm: kworker/u4:13 Tainted: G W 5.16.0-rc2+ #469 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 Workqueue: btrfs-cache btrfs_work_helper RIP: 0010:assert_eb_page_uptodate+0x3f/0x50 RSP: 0018:ffffae598230bc60 EFLAGS: 00010246 RAX: 0017ffffc0002112 RBX: ffffebaec4100900 RCX: 0000000000001000 RDX: ffffebaec45733c7 RSI: ffffebaec4100900 RDI: ffff9fd98919f340 RBP: 0000000000000d56 R08: ffff9fd98e300000 R09: 0000000000000000 R10: 0001207370a91c50 R11: 0000000000000000 R12: 00000000000007b0 R13: ffff9fd98919f340 R14: 0000000001500000 R15: 0000000001cb0000 FS: 0000000000000000(0000) GS:ffff9fd9fbc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f549fcf8940 CR3: 0000000114908004 CR4: 0000000000370ef0 Call Trace: extent_buffer_test_bit+0x3f/0x70 free_space_test_bit+0xa6/0xc0 load_free_space_tree+0x1d6/0x430 caching_thread+0x454/0x630 ? rcu_read_lock_sched_held+0x12/0x60 ? rcu_read_lock_sched_held+0x12/0x60 ? rcu_read_lock_sched_held+0x12/0x60 ? lock_release+0x1f0/0x2d0 btrfs_work_helper+0xf2/0x3e0 ? lock_release+0x1f0/0x2d0 ? finish_task_switch.isra.0+0xf9/0x3a0 process_one_work+0x270/0x5a0 worker_thread+0x55/0x3c0 ? process_one_work+0x5a0/0x5a0 kthread+0x174/0x1a0 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x1f/0x30 This happens because we're trying to read from a extent buffer page that is !PageUptodate. This happens because we will clear the page uptodate when we have an IO error, but we don't clear the extent buffer uptodate. If we do a read later and find this extent buffer we'll think its valid and not return an error, and then trip over this warning. Fix this by also clearing uptodate on the extent buffer when this happens, so that we get an error when we do a btrfs_search_slot() and find this block later. CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4e03a6d3aa32..dcdb97d9205d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4313,6 +4313,12 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) return; + /* + * A read may stumble upon this buffer later, make sure that it gets an + * error and knows there was an error. + */ + clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + /* * If we error out, we should add back the dirty_metadata_bytes * to make it consistent. -- cgit From 68b85589ba8114514d83ae87dd6f3fe9b315cae0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 24 Nov 2021 14:14:25 -0500 Subject: btrfs: call mapping_set_error() on btree inode with a write error generic/484 fails sometimes with compression on because the write ends up small enough that it goes into the btree. This means that we never call mapping_set_error() on the inode itself, because the page gets marked as fine when we inline it into the metadata. When the metadata writeback happens we see it and abort the transaction properly and mark the fs as readonly, however we don't do the mapping_set_error() on anything. In syncfs() we will simply return 0 if the sb is marked read-only, so we can't check for this in our syncfs callback. The only way the error gets returned if we called mapping_set_error() on something. Fix this by calling mapping_set_error() on the btree inode mapping. This allows us to properly return an error on syncfs and pass generic/484 with compression on. Reviewed-by: Nikolay Borisov 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 dcdb97d9205d..3258b6f01e85 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4319,6 +4319,14 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) */ clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + /* + * We need to set the mapping with the io error as well because a write + * error will flip the file system readonly, and then syncfs() will + * return a 0 because we are readonly if we don't modify the err seq for + * the superblock. + */ + mapping_set_error(page->mapping, -EIO); + /* * If we error out, we should add back the dirty_metadata_bytes * to make it consistent. -- cgit From 84c25448929942edacba905cecc0474e91114e7a Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 30 Nov 2021 12:40:21 +0900 Subject: btrfs: fix re-dirty process of tree-log nodes There is a report of a transaction abort of -EAGAIN with the following script. #!/bin/sh for d in sda sdb; do mkfs.btrfs -d single -m single -f /dev/\${d} done mount /dev/sda /mnt/test mount /dev/sdb /mnt/scratch for dir in test scratch; do echo 3 >/proc/sys/vm/drop_caches fio --directory=/mnt/\${dir} --name=fio.\${dir} --rw=read --size=50G --bs=64m \ --numjobs=$(nproc) --time_based --ramp_time=5 --runtime=480 \ --group_reporting |& tee /dev/shm/fio.\${dir} echo 3 >/proc/sys/vm/drop_caches done for d in sda sdb; do umount /dev/\${d} done The stack trace is shown in below. [3310.967991] BTRFS: error (device sda) in btrfs_commit_transaction:2341: errno=-11 unknown (Error while writing out transaction) [3310.968060] BTRFS info (device sda): forced readonly [3310.968064] BTRFS warning (device sda): Skipping commit of aborted transaction. [3310.968065] ------------[ cut here ]------------ [3310.968066] BTRFS: Transaction aborted (error -11) [3310.968074] WARNING: CPU: 14 PID: 1684 at fs/btrfs/transaction.c:1946 btrfs_commit_transaction.cold+0x209/0x2c8 [3310.968131] CPU: 14 PID: 1684 Comm: fio Not tainted 5.14.10-300.fc35.x86_64 #1 [3310.968135] Hardware name: DIAWAY Tartu/Tartu, BIOS V2.01.B10 04/08/2021 [3310.968137] RIP: 0010:btrfs_commit_transaction.cold+0x209/0x2c8 [3310.968144] RSP: 0018:ffffb284ce393e10 EFLAGS: 00010282 [3310.968147] RAX: 0000000000000026 RBX: ffff973f147b0f60 RCX: 0000000000000027 [3310.968149] RDX: ffff974ecf098a08 RSI: 0000000000000001 RDI: ffff974ecf098a00 [3310.968150] RBP: ffff973f147b0f08 R08: 0000000000000000 R09: ffffb284ce393c48 [3310.968151] R10: ffffb284ce393c40 R11: ffffffff84f47468 R12: ffff973f101bfc00 [3310.968153] R13: ffff971f20cf2000 R14: 00000000fffffff5 R15: ffff973f147b0e58 [3310.968154] FS: 00007efe65468740(0000) GS:ffff974ecf080000(0000) knlGS:0000000000000000 [3310.968157] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [3310.968158] CR2: 000055691bcbe260 CR3: 000000105cfa4001 CR4: 0000000000770ee0 [3310.968160] PKRU: 55555554 [3310.968161] Call Trace: [3310.968167] ? dput+0xd4/0x300 [3310.968174] btrfs_sync_file+0x3f1/0x490 [3310.968180] __x64_sys_fsync+0x33/0x60 [3310.968185] do_syscall_64+0x3b/0x90 [3310.968190] entry_SYSCALL_64_after_hwframe+0x44/0xae [3310.968194] RIP: 0033:0x7efe6557329b [3310.968200] RSP: 002b:00007ffe0236ebc0 EFLAGS: 00000293 ORIG_RAX: 000000000000004a [3310.968203] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007efe6557329b [3310.968204] RDX: 0000000000000000 RSI: 00007efe58d77010 RDI: 0000000000000006 [3310.968205] RBP: 0000000004000000 R08: 0000000000000000 R09: 00007efe58d77010 [3310.968207] R10: 0000000016cacc0c R11: 0000000000000293 R12: 00007efe5ce95980 [3310.968208] R13: 0000000000000000 R14: 00007efe6447c790 R15: 0000000c80000000 [3310.968212] ---[ end trace 1a346f4d3c0d96ba ]--- [3310.968214] BTRFS: error (device sda) in cleanup_transaction:1946: errno=-11 unknown The abort occurs because of a write hole while writing out freeing tree nodes of a tree-log tree. For zoned btrfs, we re-dirty a freed tree node to ensure btrfs can write the region and does not leave a hole on write on a zoned device. The current code fails to re-dirty a node when the tree-log tree's depth is greater or equal to 2. That leads to a transaction abort with -EAGAIN. Fix the issue by properly re-dirtying a node on walking up the tree. Fixes: d3575156f662 ("btrfs: zoned: redirty released extent buffers") CC: stable@vger.kernel.org # 5.12+ Link: https://github.com/kdave/btrfs-progs/issues/415 Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota 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 8ab33caf016f..3e6f14e13918 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2908,6 +2908,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, path->nodes[*level]->len); if (ret) return ret; + btrfs_redirty_list_add(trans->transaction, + next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -2988,6 +2990,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, next->start, next->len); if (ret) goto out; + btrfs_redirty_list_add(trans->transaction, next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -3438,8 +3441,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); extent_io_tree_release(&log->log_csum_range); - if (trans && log->node) - btrfs_redirty_list_add(trans->transaction, log->node); btrfs_put_root(log); } -- cgit From da5e817d9d75422eaaa05490d0b9a5e328fc1a51 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Fri, 3 Dec 2021 02:55:33 -0800 Subject: btrfs: free exchange changeset on failures Fstests runs on my VMs have show several kmemleak reports like the following. unreferenced object 0xffff88811ae59080 (size 64): comm "xfs_io", pid 12124, jiffies 4294987392 (age 6.368s) hex dump (first 32 bytes): 00 c0 1c 00 00 00 00 00 ff cf 1c 00 00 00 00 00 ................ 90 97 e5 1a 81 88 ff ff 90 97 e5 1a 81 88 ff ff ................ backtrace: [<00000000ac0176d2>] ulist_add_merge+0x60/0x150 [btrfs] [<0000000076e9f312>] set_state_bits+0x86/0xc0 [btrfs] [<0000000014fe73d6>] set_extent_bit+0x270/0x690 [btrfs] [<000000004f675208>] set_record_extent_bits+0x19/0x20 [btrfs] [<00000000b96137b1>] qgroup_reserve_data+0x274/0x310 [btrfs] [<0000000057e9dcbb>] btrfs_check_data_free_space+0x5c/0xa0 [btrfs] [<0000000019c4511d>] btrfs_delalloc_reserve_space+0x1b/0xa0 [btrfs] [<000000006d37e007>] btrfs_dio_iomap_begin+0x415/0x970 [btrfs] [<00000000fb8a74b8>] iomap_iter+0x161/0x1e0 [<0000000071dff6ff>] __iomap_dio_rw+0x1df/0x700 [<000000002567ba53>] iomap_dio_rw+0x5/0x20 [<0000000072e555f8>] btrfs_file_write_iter+0x290/0x530 [btrfs] [<000000005eb3d845>] new_sync_write+0x106/0x180 [<000000003fb505bf>] vfs_write+0x24d/0x2f0 [<000000009bb57d37>] __x64_sys_pwrite64+0x69/0xa0 [<000000003eba3fdf>] do_syscall_64+0x43/0x90 In case brtfs_qgroup_reserve_data() or btrfs_delalloc_reserve_metadata() fail the allocated extent_changeset will not be freed. So in btrfs_check_data_free_space() and btrfs_delalloc_reserve_space() free the allocated extent_changeset to get rid of the allocated memory. The issue currently only happens in the direct IO write path, but only after 65b3c08606e5 ("btrfs: fix ENOSPC failure when attempting direct IO write into NOCOW range"), and also at defrag_one_locked_target(). Every other place is always calling extent_changeset_free() even if its call to btrfs_delalloc_reserve_space() or btrfs_check_data_free_space() has failed. CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Filipe Manana Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/delalloc-space.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 2059d1504149..40c4d6ba3fb9 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -143,10 +143,13 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode, /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); - if (ret < 0) + if (ret < 0) { btrfs_free_reserved_data_space_noquota(fs_info, len); - else + extent_changeset_free(*reserved); + *reserved = NULL; + } else { ret = 0; + } return ret; } @@ -452,8 +455,11 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(inode, len); - if (ret < 0) + if (ret < 0) { btrfs_free_reserved_data_space(inode, *reserved, start, len); + extent_changeset_free(*reserved); + *reserved = NULL; + } return ret; } -- cgit From 5911f5382022aff2b817cb88f276756af229664d Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 2 Dec 2021 00:47:14 -0800 Subject: btrfs: zoned: clear data relocation bg on zone finish When finishing a zone that is used by a dedicated data relocation block group, also remove its reference from fs_info, so we're not trying to use a full block group for allocations during data relocation, which will always fail. The result is we're not making any forward progress and end up in a deadlock situation. Fixes: c2707a255623 ("btrfs: zoned: add a dedicated data relocation block group") Reviewed-by: Naohiro Aota Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 67d932d70798..678a29469511 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1860,6 +1860,7 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; btrfs_clear_treelog_bg(block_group); + btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, @@ -1942,6 +1943,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 len ASSERT(block_group->alloc_offset == block_group->zone_capacity); ASSERT(block_group->free_space_ctl->free_space == 0); btrfs_clear_treelog_bg(block_group); + btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); map = block_group->physical_map; -- cgit From 8289ed9f93bef2762f9184e136d994734b16d997 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 1 Dec 2021 19:56:17 +0800 Subject: btrfs: replace the BUG_ON in btrfs_del_root_ref with proper error handling I hit the BUG_ON() with generic/475 test case, and to my surprise, all callers of btrfs_del_root_ref() are already aborting transaction, thus there is not need for such BUG_ON(), just go to @out label and caller will properly handle the error. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/root-tree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 702dc5441f03..db37a3799649 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -336,7 +336,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - BUG_ON(ret < 0); + if (ret < 0) + goto out; if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], -- cgit