The throttle path doesn't take cleaner_delayed_iput_mutex, which means
we could think we're done flushing iputs in the data space reservation
path when we could have a throttler doing an iput. There's no real
reason to serialize the delayed iput flushing, so instead of taking the
cleaner_delayed_iput_mutex whenever we flush the delayed iputs just
replace it with an atomic counter and a waitqueue. This removes the
short (or long depending on how big the inode is) window where we think
there are no more pending iputs when there really are some.
Signed-off-by: Josef Bacik <jo...@toxicpanda.com>
---
fs/btrfs/ctree.h | 4 +++-
fs/btrfs/disk-io.c | 5 ++---
fs/btrfs/extent-tree.c | 9 +++++----
fs/btrfs/inode.c | 21 +++++++++++++++++++++
4 files changed, 31 insertions(+), 8 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e40356ca0295..1ef0b1649cad 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -894,7 +894,8 @@ struct btrfs_fs_info {
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
- struct mutex cleaner_delayed_iput_mutex;
+ atomic_t nr_delayed_iputs;
+ wait_queue_head_t delayed_iputs_wait;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
@@ -3212,6 +3213,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root);
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
void btrfs_add_delayed_iput(struct inode *inode);
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_prealloc_file_range(struct inode *inode, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 51b2a5bf25e5..3dce9ff72e41 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1692,9 +1692,7 @@ static int cleaner_kthread(void *arg)
goto sleep;
}
- mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(fs_info);
- mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&fs_info->cleaner_mutex);
@@ -2677,7 +2675,6 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
- mutex_init(&fs_info->cleaner_delayed_iput_mutex);
seqlock_init(&fs_info->profiles_lock);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
@@ -2699,6 +2696,7 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->defrag_running, 0);
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
+ atomic_set(&fs_info->nr_delayed_iputs, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
@@ -2776,6 +2774,7 @@ int open_ctree(struct super_block *sb,
init_waitqueue_head(&fs_info->transaction_wait);
init_waitqueue_head(&fs_info->transaction_blocked_wait);
init_waitqueue_head(&fs_info->async_submit_wait);
+ init_waitqueue_head(&fs_info->delayed_iputs_wait);
INIT_LIST_HEAD(&fs_info->pinned_chunks);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a7ba0d0e8de1..77bc53ad84e9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4258,8 +4258,9 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode
*inode, u64 bytes)
* operations. Wait for it to finish so that
* more space is released.
*/
-
mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
-
mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+ ret = btrfs_wait_on_delayed_iputs(fs_info);
+ if (ret)
+ return ret;
goto again;
} else {
btrfs_end_transaction(trans);
@@ -4829,9 +4830,9 @@ static int may_commit_transaction(struct btrfs_fs_info
*fs_info,
* pinned space, so make sure we run the iputs before we do our pinned
* bytes check below.
*/
- mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(fs_info);
- mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+ wait_event(fs_info->delayed_iputs_wait,
+ atomic_read(&fs_info->nr_delayed_iputs) == 0);
trans = btrfs_join_transaction(fs_info->extent_root);
if (IS_ERR(trans))
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0a1671fb03bf..ab8242b10601 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3319,6 +3319,7 @@ void btrfs_add_delayed_iput(struct inode *inode)
if (atomic_add_unless(&inode->i_count, -1, 1))
return;
+ atomic_inc(&fs_info->nr_delayed_iputs);
spin_lock(&fs_info->delayed_iput_lock);
ASSERT(list_empty(&binode->delayed_iput));
list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
@@ -3338,11 +3339,31 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info
*fs_info)
list_del_init(&inode->delayed_iput);
spin_unlock(&fs_info->delayed_iput_lock);
iput(&inode->vfs_inode);
+ if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
+ wake_up(&fs_info->delayed_iputs_wait);
spin_lock(&fs_info->delayed_iput_lock);
}
spin_unlock(&fs_info->delayed_iput_lock);
}
+/**
+ * btrfs_wait_on_delayed_iputs - wait on the delayed iputs to be done running
+ * @fs_info - the fs_info for this fs
+ * @return - EINTR if we were killed, 0 if nothing's pending
+ *
+ * This will wait on any delayed iputs that are currently running with KILLABLE
+ * set. Once they are all done running we will return, unless we are killed in
+ * which case we return EINTR.
+ */
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info)
+{
+ int ret = wait_event_killable(fs_info->delayed_iputs_wait,
+ atomic_read(&fs_info->nr_delayed_iputs) == 0);
+ if (ret)
+ return -EINTR;
+ return 0;
+}
+
/*
* This creates an orphan entry for the given inode in case something goes
wrong
* in the middle of an unlink.
--
2.14.3
