btrfs: Fix NO_SPACE bug caused by delayed-iput

Steps to reproduce:
  while true; do
    dd if=/dev/zero of=/btrfs_dir/file count=[fs_size * 75%]
    rm /btrfs_dir/file
    sync
  done

  And we'll see dd failed because btrfs return NO_SPACE.

Reason:
  Normally, btrfs_commit_transaction() call btrfs_run_delayed_iputs()
  in end to free fs space for next write, but sometimes it hadn't
  done work on time, because btrfs-cleaner thread get delayed-iputs
  from list before, but do iput() after next write.

  This is log:
  [ 2569.050776] comm=btrfs-cleaner func=btrfs_evict_inode() begin

  [ 2569.084280] comm=sync func=btrfs_commit_transaction() call btrfs_run_delayed_iputs()
  [ 2569.085418] comm=sync func=btrfs_commit_transaction() done btrfs_run_delayed_iputs()
  [ 2569.087554] comm=sync func=btrfs_commit_transaction() end

  [ 2569.191081] comm=dd begin
  [ 2569.790112] comm=dd func=__btrfs_buffered_write() ret=-28

  [ 2569.847479] comm=btrfs-cleaner func=add_pinned_bytes() 0 + 32677888 = 32677888
  [ 2569.849530] comm=btrfs-cleaner func=add_pinned_bytes() 32677888 + 23834624 = 56512512
  ...
  [ 2569.903893] comm=btrfs-cleaner func=add_pinned_bytes() 943976448 + 21762048 = 965738496
  [ 2569.908270] comm=btrfs-cleaner func=btrfs_evict_inode() end

Fix:
  Make btrfs_commit_transaction() wait current running btrfs-cleaner's
  delayed-iputs() done in end.

Test:
  Use script similar to above(more complex),
  before patch:
    7 failed in 100 * 20 loop.
  after patch:
    0 failed in 100 * 20 loop.

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 10b6a75ab7e62c4ffc675fb53e8de1b069c458d7..d48b22f3118286e504f7b12ee5cd70090a9f0bcb 100644 (file)
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1538,6 +1538,7 @@ struct btrfs_fs_info {
 
        spinlock_t delayed_iput_lock;
        struct list_head delayed_iputs;
+       struct rw_semaphore delayed_iput_sem;
 
        /* this protects tree_mod_seq_list */
        spinlock_t tree_mod_seq_lock;

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 62cd3b63190d97d68b11f9bc11ddb9577b24337b..2ef9a4b72d06e46d4f3a19c73e94796cb8397347 100644 (file)
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2487,11 +2487,12 @@ int open_ctree(struct super_block *sb,
        spin_lock_init(&fs_info->qgroup_op_lock);
        spin_lock_init(&fs_info->buffer_lock);
        spin_lock_init(&fs_info->unused_bgs_lock);
-       mutex_init(&fs_info->unused_bg_unpin_mutex);
        rwlock_init(&fs_info->tree_mod_log_lock);
+       mutex_init(&fs_info->unused_bg_unpin_mutex);
        mutex_init(&fs_info->reloc_mutex);
        mutex_init(&fs_info->delalloc_root_mutex);
        seqlock_init(&fs_info->profiles_lock);
+       init_rwsem(&fs_info->delayed_iput_sem);
 
        init_completion(&fs_info->kobj_unregister);
        INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index be4a79a69ed12ce7ec6a1136ac21ce583d979772..46cb1d4149124a138391617a0e7ca28e099c1a88 100644 (file)
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3950,6 +3950,12 @@ commit_trans:
                                ret = btrfs_commit_transaction(trans, root);
                                if (ret)
                                        return ret;
+                               /*
+                                * make sure that all running delayed iput are
+                                * done
+                                */
+                               down_write(&root->fs_info->delayed_iput_sem);
+                               up_write(&root->fs_info->delayed_iput_sem);
                                goto again;
                        } else {
                                btrfs_end_transaction(trans, root);

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 141df0ce6f9318be05e24864934e2421013d5de7..6ef97c184c7b3742ae5e35cd57ae0849c6930830 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3111,6 +3111,8 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
        if (empty)
                return;
 
+       down_read(&fs_info->delayed_iput_sem);
+
        spin_lock(&fs_info->delayed_iput_lock);
        list_splice_init(&fs_info->delayed_iputs, &list);
        spin_unlock(&fs_info->delayed_iput_lock);
@@ -3121,6 +3123,8 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
                iput(delayed->inode);
                kfree(delayed);
        }
+
+       up_read(&root->fs_info->delayed_iput_sem);
 }
 
 /*