summaryrefslogtreecommitdiff
path: root/fs/btrfs/free-space-cache.c
diff options
context:
space:
mode:
authorJosef Bacik <josef@toxicpanda.com>2022-08-08 23:10:26 +0300
committerDavid Sterba <dsterba@suse.com>2022-09-26 13:27:58 +0300
commit8a1ae2781dee9fc21ca82db682d37bea4bd074ad (patch)
treead7fcd5c6b086a5d56dd525ca1c8d569ed528d3a /fs/btrfs/free-space-cache.c
parent331cd9461412e103d07595a10289de90004ac890 (diff)
downloadlinux-8a1ae2781dee9fc21ca82db682d37bea4bd074ad.tar.xz
btrfs: call __btrfs_remove_free_space_cache_locked on cache load failure
Now that lockdep is staying enabled through our entire CI runs I started seeing the following stack in generic/475 ------------[ cut here ]------------ WARNING: CPU: 1 PID: 2171864 at fs/btrfs/discard.c:604 btrfs_discard_update_discardable+0x98/0xb0 CPU: 1 PID: 2171864 Comm: kworker/u4:0 Not tainted 5.19.0-rc8+ #789 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:btrfs_discard_update_discardable+0x98/0xb0 RSP: 0018:ffffb857c2f7bad0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8c85c605c200 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffffff86807c5b RDI: ffffffff868a831e RBP: ffff8c85c4c54000 R08: 0000000000000000 R09: 0000000000000000 R10: ffff8c85c66932f0 R11: 0000000000000001 R12: ffff8c85c3899010 R13: ffff8c85d5be4f40 R14: ffff8c85c4c54000 R15: ffff8c86114bfa80 FS: 0000000000000000(0000) GS:ffff8c863bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2e7f168160 CR3: 000000010289a004 CR4: 0000000000370ee0 Call Trace: __btrfs_remove_free_space_cache+0x27/0x30 load_free_space_cache+0xad2/0xaf0 caching_thread+0x40b/0x650 ? lock_release+0x137/0x2d0 btrfs_work_helper+0xf2/0x3e0 ? lock_is_held_type+0xe2/0x140 process_one_work+0x271/0x590 ? process_one_work+0x590/0x590 worker_thread+0x52/0x3b0 ? process_one_work+0x590/0x590 kthread+0xf0/0x120 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 This is the code ctl = block_group->free_space_ctl; discard_ctl = &block_group->fs_info->discard_ctl; lockdep_assert_held(&ctl->tree_lock); We have a temporary free space ctl for loading the free space cache in order to avoid having allocations happening while we're loading the cache. When we hit an error we free it all up, however this also calls btrfs_discard_update_discardable, which requires block_group->free_space_ctl->tree_lock to be held. However this is our temporary ctl so this lock isn't held. Fix this by calling __btrfs_remove_free_space_cache_locked instead so that we only clean up the entries and do not mess with the discardable stats. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/free-space-cache.c')
-rw-r--r--fs/btrfs/free-space-cache.c53
1 files changed, 33 insertions, 20 deletions
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 81d9fe33672f..f2a6dd033623 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -48,6 +48,25 @@ static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, u64 offset,
u64 bytes, bool update_stats);
+static void __btrfs_remove_free_space_cache_locked(
+ struct btrfs_free_space_ctl *ctl)
+{
+ struct btrfs_free_space *info;
+ struct rb_node *node;
+
+ while ((node = rb_last(&ctl->free_space_offset)) != NULL) {
+ info = rb_entry(node, struct btrfs_free_space, offset_index);
+ if (!info->bitmap) {
+ unlink_free_space(ctl, info, true);
+ kmem_cache_free(btrfs_free_space_cachep, info);
+ } else {
+ free_bitmap(ctl, info);
+ }
+
+ cond_resched_lock(&ctl->tree_lock);
+ }
+}
+
static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
struct btrfs_path *path,
u64 offset)
@@ -878,7 +897,14 @@ out:
return ret;
free_cache:
io_ctl_drop_pages(&io_ctl);
- __btrfs_remove_free_space_cache(ctl);
+
+ /*
+ * We need to call the _locked variant so we don't try to update the
+ * discard counters.
+ */
+ spin_lock(&ctl->tree_lock);
+ __btrfs_remove_free_space_cache_locked(ctl);
+ spin_unlock(&ctl->tree_lock);
goto out;
}
@@ -1014,7 +1040,13 @@ int load_free_space_cache(struct btrfs_block_group *block_group)
if (ret == 0)
ret = 1;
} else {
+ /*
+ * We need to call the _locked variant so we don't try to update
+ * the discard counters.
+ */
+ spin_lock(&tmp_ctl.tree_lock);
__btrfs_remove_free_space_cache(&tmp_ctl);
+ spin_unlock(&tmp_ctl.tree_lock);
btrfs_warn(fs_info,
"block group %llu has wrong amount of free space",
block_group->start);
@@ -2978,25 +3010,6 @@ static void __btrfs_return_cluster_to_free_space(
btrfs_put_block_group(block_group);
}
-static void __btrfs_remove_free_space_cache_locked(
- struct btrfs_free_space_ctl *ctl)
-{
- struct btrfs_free_space *info;
- struct rb_node *node;
-
- while ((node = rb_last(&ctl->free_space_offset)) != NULL) {
- info = rb_entry(node, struct btrfs_free_space, offset_index);
- if (!info->bitmap) {
- unlink_free_space(ctl, info, true);
- kmem_cache_free(btrfs_free_space_cachep, info);
- } else {
- free_bitmap(ctl, info);
- }
-
- cond_resched_lock(&ctl->tree_lock);
- }
-}
-
void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
{
spin_lock(&ctl->tree_lock);