From 0465337c5599bbe360cdcff452992a1a6b7ed2d4 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 30 Jun 2020 14:53:02 -0400 Subject: btrfs: reset tree root pointer after error in init_tree_roots Eric reported an issue where mounting -o recovery with a fuzzed fs resulted in a kernel panic. This is because we tried to free the tree node, except it was an error from the read. Fix this by properly resetting the tree_root->node == NULL in this case. The panic was the following BTRFS warning (device loop0): failed to read tree root BUG: kernel NULL pointer dereference, address: 000000000000001f RIP: 0010:free_extent_buffer+0xe/0x90 [btrfs] Call Trace: free_root_extent_buffers.part.0+0x11/0x30 [btrfs] free_root_pointers+0x1a/0xa2 [btrfs] open_ctree+0x1776/0x18a5 [btrfs] btrfs_mount_root.cold+0x13/0xfa [btrfs] ? selinux_fs_context_parse_param+0x37/0x80 legacy_get_tree+0x27/0x40 vfs_get_tree+0x25/0xb0 fc_mount+0xe/0x30 vfs_kern_mount.part.0+0x71/0x90 btrfs_mount+0x147/0x3e0 [btrfs] ? cred_has_capability+0x7c/0x120 ? legacy_get_tree+0x27/0x40 legacy_get_tree+0x27/0x40 vfs_get_tree+0x25/0xb0 do_mount+0x735/0xa40 __x64_sys_mount+0x8e/0xd0 do_syscall_64+0x4d/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Nik says: this is problematic only if we fail on the last iteration of the loop as this results in init_tree_roots returning err value with tree_root->node = -ERR. Subsequently the caller does: fail_tree_roots which calls free_root_pointers on the bogus value. Reported-by: Eric Sandeen Fixes: b8522a1e5f42 ("btrfs: Factor out tree roots initialization during mount") CC: stable@vger.kernel.org # 5.5+ Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik Reviewed-by: David Sterba [ add details how the pointer gets dereferenced ] Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f8ec2d8606fd..3d4bb77680e7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2595,10 +2595,12 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) !extent_buffer_uptodate(tree_root->node)) { handle_error = true; - if (IS_ERR(tree_root->node)) + if (IS_ERR(tree_root->node)) { ret = PTR_ERR(tree_root->node); - else if (!extent_buffer_uptodate(tree_root->node)) + tree_root->node = NULL; + } else if (!extent_buffer_uptodate(tree_root->node)) { ret = -EUCLEAN; + } btrfs_warn(fs_info, "failed to read tree root"); continue; -- cgit From 21cf866145047f8bfecb38ec8d2fed64464c074f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:22 +0200 Subject: writeback: remove bdi->congested_fn Except for pktdvd, the only places setting congested bits are file systems that allocate their own backing_dev_info structures. And pktdvd is a deprecated driver that isn't useful in stack setup either. So remove the dead congested_fn stacking infrastructure. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: David Sterba [axboe: fixup unused variables in bcache/request.c] Signed-off-by: Jens Axboe --- fs/btrfs/disk-io.c | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7c6f0bbb54a5..eb5f2506cede 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1616,27 +1616,6 @@ fail: return ERR_PTR(ret); } -static int btrfs_congested_fn(void *congested_data, int bdi_bits) -{ - struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; - int ret = 0; - struct btrfs_device *device; - struct backing_dev_info *bdi; - - rcu_read_lock(); - list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - bdi = device->bdev->bd_bdi; - if (bdi_congested(bdi, bdi_bits)) { - ret = 1; - break; - } - } - rcu_read_unlock(); - return ret; -} - /* * called by the kthread helper functions to finally call the bio end_io * functions. This is where read checksum verification actually happens @@ -3051,8 +3030,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sb_buffer; } - sb->s_bdi->congested_fn = btrfs_congested_fn; - sb->s_bdi->congested_data = fs_info; sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; sb->s_bdi->ra_pages = VM_READAHEAD_PAGES; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); -- cgit From 5958253cf65de42493f17f36877a901486a90365 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 10 Jun 2020 09:04:44 +0800 Subject: btrfs: qgroup: catch reserved space leaks at unmount time Before this patch, qgroup completely relies on per-inode extent io tree to detect reserved data space leak. However previous bug has already shown how release page before btrfs_finish_ordered_io() could lead to leak, and since it's QGROUP_RESERVED bit cleared without triggering qgroup rsv, it can't be detected by per-inode extent io tree. So this patch adds another (and hopefully the final) safety net to catch qgroup data reserved space leak. At least the new safety net catches all the leaks during development, so it should be pretty useful in the real world. Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b1a148058773..a9cf6152d175 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4058,6 +4058,11 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) ASSERT(list_empty(&fs_info->delayed_iputs)); set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); + if (btrfs_check_quota_leak(fs_info)) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + btrfs_err(fs_info, "qgroup reserved space leaked"); + } + btrfs_free_qgroup_config(fs_info); ASSERT(list_empty(&fs_info->delalloc_roots)); -- cgit From 923eb5236597c90b11114926025e0c04e4c1da32 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 23 Jun 2020 17:40:07 +0900 Subject: btrfs: use free_root_extent_buffer to free root In btrfs_put_root() we're freeing a btrfs_root's 'node' and 'commit_root' extent buffers manually via kfree(), while we're using free_root_extent_buffers() in the free_root_pointers() function above. free_root_extent_buffers() also NULLs the pointers after freeing, which mitigates potential double frees. Reviewed-by: Anand Jain Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a9cf6152d175..b5b7055b7953 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2001,8 +2001,7 @@ void btrfs_put_root(struct btrfs_root *root) if (root->anon_dev) free_anon_bdev(root->anon_dev); btrfs_drew_lock_destroy(&root->snapshot_lock); - free_extent_buffer(root->node); - free_extent_buffer(root->commit_root); + free_root_extent_buffers(root); kfree(root->free_ino_ctl); kfree(root->free_ino_pinned); #ifdef CONFIG_BTRFS_DEBUG -- cgit From a2570ef330b959eb37e3a437b9884d9cc4b6a3d9 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 23 Jun 2020 21:23:54 +0200 Subject: btrfs: remove unused btrfs_root::defrag_trans_start Last touched in 2013 by commit de78b51a2852 ("btrfs: remove cache only arguments from defrag path") that was the only code that used the value. Now it's only set but never used for anything, so we can remove it. Reviewed-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b5b7055b7953..dbf90cd49513 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1141,10 +1141,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); memset(&root->defrag_progress, 0, sizeof(root->defrag_progress)); - if (!dummy) - root->defrag_trans_start = fs_info->generation; - else - root->defrag_trans_start = 0; root->root_key.objectid = objectid; root->anon_dev = 0; -- cgit From 851fd730a743e072badaf67caf39883e32439431 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 16 Jun 2020 10:17:34 +0800 Subject: btrfs: don't allocate anonymous block device for user invisible roots [BUG] When a lot of subvolumes are created, there is a user report about transaction aborted: BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] The error is EMFILE (Too many files open) and comes from the anonymous block device allocation. The ids are in a shared pool of size 1<<20. The ids are assigned to live subvolumes, ie. the root structure exists in memory (eg. after creation or after the root appears in some path). The pool could be exhausted if the numbers are not reclaimed fast enough, after subvolume deletion or if other system component uses the anon block devices. [WORKAROUND] Since it's not possible to completely solve the problem, we can only minimize the time the id is allocated to a subvolume root. Firstly, we can reduce the use of anon_dev by trees that are not subvolume roots, like data reloc tree. This patch will do extra check on root objectid, to skip roots that don't need anon_dev. Currently it's only data reloc tree and orphan roots. Reported-by: Greed Rong Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+=tHJX7nb9DPw@mail.gmail.com/ CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dbf90cd49513..c90edf04a9db 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1424,9 +1424,16 @@ static int btrfs_init_fs_root(struct btrfs_root *root) spin_lock_init(&root->ino_cache_lock); init_waitqueue_head(&root->ino_cache_wait); - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + /* + * Don't assign anonymous block device to roots that are not exposed to + * userspace, the id pool is limited to 1M + */ + if (is_fstree(root->root_key.objectid) && + btrfs_root_refs(&root->root_item) > 0) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } mutex_lock(&root->objectid_mutex); ret = btrfs_find_highest_objectid(root, -- cgit From 2dfb1e43f57dd3aeaa66f7cf05d068db2d4c8788 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 16 Jun 2020 10:17:36 +0800 Subject: btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+=tHJX7nb9DPw@mail.gmail.com/ CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 64 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c90edf04a9db..9b307034d32c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1391,7 +1391,12 @@ alloc_fail: goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root) */ if (is_fstree(root->root_key.objectid) && btrfs_root_refs(&root->root_item) > 0) { - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } } mutex_lock(&root->objectid_mutex); @@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1586,7 +1616,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1619,6 +1649,33 @@ fail: return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; -- cgit From c53e9653605dbf708f5be02902de51831be4b009 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 13 Jul 2020 18:50:48 +0800 Subject: btrfs: qgroup: try to flush qgroup space when we get -EDQUOT [PROBLEM] There are known problem related to how btrfs handles qgroup reserved space. One of the most obvious case is the the test case btrfs/153, which do fallocate, then write into the preallocated range. btrfs/153 1s ... - output mismatch (see xfstests-dev/results//btrfs/153.out.bad) --- tests/btrfs/153.out 2019-10-22 15:18:14.068965341 +0800 +++ xfstests-dev/results//btrfs/153.out.bad 2020-07-01 20:24:40.730000089 +0800 @@ -1,2 +1,5 @@ QA output created by 153 +pwrite: Disk quota exceeded +/mnt/scratch/testfile2: Disk quota exceeded +/mnt/scratch/testfile2: Disk quota exceeded Silence is golden ... (Run 'diff -u xfstests-dev/tests/btrfs/153.out xfstests-dev/results//btrfs/153.out.bad' to see the entire diff) [CAUSE] Since commit c6887cd11149 ("Btrfs: don't do nocow check unless we have to"), we always reserve space no matter if it's COW or not. Such behavior change is mostly for performance, and reverting it is not a good idea anyway. For preallcoated extent, we reserve qgroup data space for it already, and since we also reserve data space for qgroup at buffered write time, it needs twice the space for us to write into preallocated space. This leads to the -EDQUOT in buffered write routine. And we can't follow the same solution, unlike data/meta space check, qgroup reserved space is shared between data/metadata. The EDQUOT can happen at the metadata reservation, so doing NODATACOW check after qgroup reservation failure is not a solution. [FIX] To solve the problem, we don't return -EDQUOT directly, but every time we got a -EDQUOT, we try to flush qgroup space: - Flush all inodes of the root NODATACOW writes will free the qgroup reserved at run_dealloc_range(). However we don't have the infrastructure to only flush NODATACOW inodes, here we flush all inodes anyway. - Wait for ordered extents This would convert the preallocated metadata space into per-trans metadata, which can be freed in later transaction commit. - Commit transaction This will free all per-trans metadata space. Also we don't want to trigger flush multiple times, so here we introduce a per-root wait list and a new root status, to ensure only one thread starts the flushing. Fixes: c6887cd11149 ("Btrfs: don't do nocow check unless we have to") Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- 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 9b307034d32c..4360937acc2f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1116,6 +1116,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, mutex_init(&root->log_mutex); mutex_init(&root->ordered_extent_mutex); mutex_init(&root->delalloc_mutex); + init_waitqueue_head(&root->qgroup_flush_wait); init_waitqueue_head(&root->log_writer_wait); init_waitqueue_head(&root->log_commit_wait[0]); init_waitqueue_head(&root->log_commit_wait[1]); -- cgit From adca4d945c8dca28a85df45c5b117e6dac2e77f1 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 13 Jul 2020 18:50:49 +0800 Subject: btrfs: qgroup: remove ASYNC_COMMIT mechanism in favor of reserve retry-after-EDQUOT commit a514d63882c3 ("btrfs: qgroup: Commit transaction in advance to reduce early EDQUOT") tries to reduce the early EDQUOT problems by checking the qgroup free against threshold and tries to wake up commit kthread to free some space. The problem of that mechanism is, it can only free qgroup per-trans metadata space, can't do anything to data, nor prealloc qgroup space. Now since we have the ability to flush qgroup space, and implemented retry-after-EDQUOT behavior, such mechanism can be completely replaced. So this patch will cleanup such mechanism in favor of retry-after-EDQUOT. Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- 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 4360937acc2f..c850d7f44fbe 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1810,7 +1810,6 @@ static int transaction_kthread(void *arg) now = ktime_get_seconds(); if (cur->state < TRANS_STATE_COMMIT_START && - !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) && (now < cur->start_time || now - cur->start_time < fs_info->commit_interval)) { spin_unlock(&fs_info->trans_lock); -- cgit