Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "I've split out the big send/receive update from my last pull request
  and now have just the fixes in my for-linus branch.  The send/recv
  branch will wander over to linux-next shortly though.

  The largest patches in this pull are Josef's patches to fix DIO
  locking problems and his patch to fix a crash during balance.  They
  are both well tested.

  The rest are smaller fixes that we've had queued.  The last rc came
  out while I was hacking new and exciting ways to recover from a
  misplaced rm -rf on my dev box, so these missed rc3."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (25 commits)
  Btrfs: fix that repair code is spuriously executed for transid failures
  Btrfs: fix ordered extent leak when failing to start a transaction
  Btrfs: fix a dio write regression
  Btrfs: fix deadlock with freeze and sync V2
  Btrfs: revert checksum error statistic which can cause a BUG()
  Btrfs: remove superblock writing after fatal error
  Btrfs: allow delayed refs to be merged
  Btrfs: fix enospc problems when deleting a subvol
  Btrfs: fix wrong mtime and ctime when creating snapshots
  Btrfs: fix race in run_clustered_refs
  Btrfs: don't run __tree_mod_log_free_eb on leaves
  Btrfs: increase the size of the free space cache
  Btrfs: barrier before waitqueue_active
  Btrfs: fix deadlock in wait_for_more_refs
  btrfs: fix second lock in btrfs_delete_delayed_items()
  Btrfs: don't allocate a seperate csums array for direct reads
  Btrfs: do not strdup non existent strings
  Btrfs: do not use missing devices when showing devname
  Btrfs: fix that error value is changed by mistake
  Btrfs: lock extents as we map them in DIO
  ...

1 files changed, 14 insertions, 39 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 62e0cafd6e25..22e98e04c2ea 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -377,9 +377,13 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
                 ret = read_extent_buffer_pages(io_tree, eb, start,
                                                WAIT_COMPLETE,
                                                btree_get_extent, mirror_num);
-                if (!ret && !verify_parent_transid(io_tree, eb,
+                if (!ret) {
+                        if (!verify_parent_transid(io_tree, eb,
                                                    parent_transid, 0))
-                        break;
+                                break;
+                        else
+                                ret = -EIO;
+                }
 
                 /*
                  * This buffer's crc is fine, but its contents are corrupted, so
@@ -754,9 +758,7 @@ static void run_one_async_done(struct btrfs_work *work)
         limit = btrfs_async_submit_limit(fs_info);
         limit = limit * 2 / 3;
 
-        atomic_dec(&fs_info->nr_async_submits);
-
-        if (atomic_read(&fs_info->nr_async_submits) < limit &&
+        if (atomic_dec_return(&fs_info->nr_async_submits) < limit &&
             waitqueue_active(&fs_info->async_submit_wait))
                 wake_up(&fs_info->async_submit_wait);
 
@@ -2032,8 +2034,6 @@ int open_ctree(struct super_block *sb,
         fs_info->free_chunk_space = 0;
         fs_info->tree_mod_log = RB_ROOT;
 
-        init_waitqueue_head(&fs_info->tree_mod_seq_wait);
-
         /* readahead state */
         INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
         spin_lock_init(&fs_info->reada_lock);
@@ -2528,8 +2528,7 @@ retry_root_backup:
                 goto fail_trans_kthread;
 
         /* do not make disk changes in broken FS */
-        if (btrfs_super_log_root(disk_super) != 0 &&
-            !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) {
+        if (btrfs_super_log_root(disk_super) != 0) {
                 u64 bytenr = btrfs_super_log_root(disk_super);
 
                 if (fs_devices->rw_devices == 0) {
@@ -3189,30 +3188,14 @@ int close_ctree(struct btrfs_root *root)
         /* clear out the rbtree of defraggable inodes */
         btrfs_run_defrag_inodes(fs_info);
 
-        /*
-         * Here come 2 situations when btrfs is broken to flip readonly:
-         *
-         * 1. when btrfs flips readonly somewhere else before
-         * btrfs_commit_super, sb->s_flags has MS_RDONLY flag,
-         * and btrfs will skip to write sb directly to keep
-         * ERROR state on disk.
-         *
-         * 2. when btrfs flips readonly just in btrfs_commit_super,
-         * and in such case, btrfs cannot write sb via btrfs_commit_super,
-         * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
-         * btrfs will cleanup all FS resources first and write sb then.
-         */
         if (!(fs_info->sb->s_flags & MS_RDONLY)) {
                 ret = btrfs_commit_super(root);
                 if (ret)
                         printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
         }
 
-        if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
-                ret = btrfs_error_commit_super(root);
-                if (ret)
-                        printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
-        }
+        if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+                btrfs_error_commit_super(root);
 
         btrfs_put_block_group_cache(fs_info);
 
@@ -3434,18 +3417,11 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
         if (read_only)
                 return 0;
 
-        if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
-                printk(KERN_WARNING "warning: mount fs with errors, "
-                       "running btrfsck is recommended\n");
-        }
-
         return 0;
 }
 
-int btrfs_error_commit_super(struct btrfs_root *root)
+void btrfs_error_commit_super(struct btrfs_root *root)
 {
-        int ret;
-
         mutex_lock(&root->fs_info->cleaner_mutex);
         btrfs_run_delayed_iputs(root);
         mutex_unlock(&root->fs_info->cleaner_mutex);
@@ -3455,10 +3431,6 @@ int btrfs_error_commit_super(struct btrfs_root *root)
 
         /* cleanup FS via transaction */
         btrfs_cleanup_transaction(root);
-
-        ret = write_ctree_super(NULL, root, 0);
-
-        return ret;
 }
 
 static void btrfs_destroy_ordered_operations(struct btrfs_root *root)
@@ -3782,14 +3754,17 @@ int btrfs_cleanup_transaction(struct btrfs_root *root)
                 /* FIXME: cleanup wait for commit */
                 t->in_commit = 1;
                 t->blocked = 1;
+                smp_mb();
                 if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
                         wake_up(&root->fs_info->transaction_blocked_wait);
 
                 t->blocked = 0;
+                smp_mb();
                 if (waitqueue_active(&root->fs_info->transaction_wait))
                         wake_up(&root->fs_info->transaction_wait);
 
                 t->commit_done = 1;
+                smp_mb();
                 if (waitqueue_active(&t->commit_wait))
                         wake_up(&t->commit_wait);