Btrfs: be more precise on errors when getting an inode from disk

When we attempt to read an inode from disk, we end up always returning an
-ESTALE error to the caller regardless of the actual failure reason, which
can be an out of memory problem (when allocating a path), some error found
when reading from the fs/subvolume btree (like a genuine IO error) or the
inode does not exists. So lets start returning the real error code to the
callers so that they don't treat all -ESTALE errors as meaning that the
inode does not exists (such as during orphan cleanup). This will also be
needed for a subsequent patch in the same series dealing with a special
fsync case.

Signed-off-by: Filipe Manana <fdmanana@suse.com>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3e61bd1..f968654 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3428,10 +3428,10 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                found_key.offset = 0;
                inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
                ret = PTR_ERR_OR_ZERO(inode);
-               if (ret && ret != -ESTALE)
+               if (ret && ret != -ENOENT)
                        goto out;
 
-               if (ret == -ESTALE && root == root->fs_info->tree_root) {
+               if (ret == -ENOENT && root == root->fs_info->tree_root) {
                        struct btrfs_root *dead_root;
                        struct btrfs_fs_info *fs_info = root->fs_info;
                        int is_dead_root = 0;
@@ -3467,7 +3467,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                 * Inode is already gone but the orphan item is still there,
                 * kill the orphan item.
                 */
-               if (ret == -ESTALE) {
+               if (ret == -ENOENT) {
                        trans = btrfs_start_transaction(root, 1);
                        if (IS_ERR(trans)) {
                                ret = PTR_ERR(trans);
@@ -3626,7 +3626,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 /*
  * read an inode from the btree into the in-memory inode
  */
-static void btrfs_read_locked_inode(struct inode *inode)
+static int btrfs_read_locked_inode(struct inode *inode)
 {
        struct btrfs_path *path;
        struct extent_buffer *leaf;
@@ -3645,14 +3645,19 @@ static void btrfs_read_locked_inode(struct inode *inode)
                filled = true;
 
        path = btrfs_alloc_path();
-       if (!path)
+       if (!path) {
+               ret = -ENOMEM;
                goto make_bad;
+       }
 
        memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
        ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
-       if (ret)
+       if (ret) {
+               if (ret > 0)
+                       ret = -ENOENT;
                goto make_bad;
+       }
 
        leaf = path->nodes[0];
 
@@ -3805,11 +3810,12 @@ cache_acl:
        }
 
        btrfs_update_iflags(inode);
-       return;
+       return 0;
 
 make_bad:
        btrfs_free_path(path);
        make_bad_inode(inode);
+       return ret;
 }
 
 /*
@@ -5595,7 +5601,9 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
                return ERR_PTR(-ENOMEM);
 
        if (inode->i_state & I_NEW) {
-               btrfs_read_locked_inode(inode);
+               int ret;
+
+               ret = btrfs_read_locked_inode(inode);
                if (!is_bad_inode(inode)) {
                        inode_tree_add(inode);
                        unlock_new_inode(inode);
@@ -5604,7 +5612,8 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
                } else {
                        unlock_new_inode(inode);
                        iput(inode);
-                       inode = ERR_PTR(-ESTALE);
+                       ASSERT(ret < 0);
+                       inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
                }
        }