12 files changed, 75 insertions, 33 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 2d3e32ebfd15..8729cf68d2fe 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1552,7 +1552,6 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 {
         int ret;
         int type;
-        struct btrfs_tree_block_info *info;
         struct btrfs_extent_inline_ref *eiref;
 
         if (*ptr == (unsigned long)-1)
@@ -1573,9 +1572,17 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
         }
 
         /* we can treat both ref types equally here */
-        info = (struct btrfs_tree_block_info *)(ei + 1);
         *out_root = btrfs_extent_inline_ref_offset(eb, eiref);
-        *out_level = btrfs_tree_block_level(eb, info);
+
+        if (key->type == BTRFS_EXTENT_ITEM_KEY) {
+                struct btrfs_tree_block_info *info;
+
+                info = (struct btrfs_tree_block_info *)(ei + 1);
+                *out_level = btrfs_tree_block_level(eb, info);
+        } else {
+                ASSERT(key->type == BTRFS_METADATA_ITEM_KEY);
+                *out_level = (u8)key->offset;
+        }
 
         if (ret == 1)
                 *ptr = (unsigned long)-1;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 054577bddaf2..de4e70fb3cbb 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1857,6 +1857,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode)
 {
         struct btrfs_delayed_node *delayed_node;
 
+        /*
+         * we don't do delayed inode updates during log recovery because it
+         * leads to enospc problems.  This means we also can't do
+         * delayed inode refs
+         */
+        if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+                return -EAGAIN;
+
         delayed_node = btrfs_get_or_create_delayed_node(inode);
         if (IS_ERR(delayed_node))
                 return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a80b97100d90..15116585e714 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3139,9 +3139,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
         struct extent_buffer *leaf;
 
         ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
-        if (ret < 0)
+        if (ret) {
+                if (ret > 0)
+                        ret = -ENOENT;
                 goto fail;
-        BUG_ON(ret); /* Corruption */
+        }
 
         leaf = path->nodes[0];
         bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
@@ -3149,11 +3151,9 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
         btrfs_mark_buffer_dirty(leaf);
         btrfs_release_path(path);
 fail:
-        if (ret) {
+        if (ret)
                 btrfs_abort_transaction(trans, root, ret);
-                return ret;
-        }
-        return 0;
+        return ret;
 
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e687bb0dc73a..8bf326affb94 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6255,8 +6255,10 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 out_fail:
         btrfs_end_transaction(trans, root);
-        if (drop_on_err)
+        if (drop_on_err) {
+                inode_dec_link_count(inode);
                 iput(inode);
+        }
         btrfs_balance_delayed_items(root);
         btrfs_btree_balance_dirty(root);
         return err;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f2bb13a23f86..9e1569ffbf6e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2607,9 +2607,9 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
                 ret = scrub_pages_for_parity(sparity, logical, l, physical, dev,
                                              flags, gen, mirror_num,
                                              have_csum ? csum : NULL);
-skip:
                 if (ret)
                         return ret;
+skip:
                 len -= l;
                 logical += l;
                 physical += l;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f5013d92a7e6..c81c0e004588 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1416,7 +1416,7 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
                 }
         }
 
-        dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+        dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
              inode, ceph_vinop(inode), len, locked_page);
 
         if (len > 0) {
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 99d440a4a6ba..ee85cd4e136a 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,14 +740,15 @@ static int __init fcntl_init(void)
          * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
          * is defined as O_NONBLOCK on some platforms and not on others.
          */
-        BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+        BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
                 O_RDONLY        | O_WRONLY      | O_RDWR        |
                 O_CREAT         | O_EXCL        | O_NOCTTY      |
                 O_TRUNC         | O_APPEND      | /* O_NONBLOCK | */
                 __O_SYNC        | O_DSYNC       | FASYNC        |
                 O_DIRECT        | O_LARGEFILE   | O_DIRECTORY   |
                 O_NOFOLLOW      | O_NOATIME     | O_CLOEXEC     |
-                __FMODE_EXEC    | O_PATH        | __O_TMPFILE
+                __FMODE_EXEC    | O_PATH        | __O_TMPFILE   |
+                __FMODE_NONOTIFY
                 ));
 
         fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/locks.c b/fs/locks.c
index 735b8d3fa78c..59e2f905e4ff 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1702,7 +1702,7 @@ static int generic_delete_lease(struct file *filp)
                         break;
         }
         trace_generic_delete_lease(inode, fl);
-        if (fl)
+        if (fl && IS_LEASE(fl))
                 error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
         spin_unlock(&inode->i_lock);
         locks_dispose_list(&dispose);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3550a9c87616..c06a1ba80d73 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3897,11 +3897,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
                 status = nfs4_setlease(dp);
                 goto out;
         }
-        atomic_inc(&fp->fi_delegees);
         if (fp->fi_had_conflict) {
                 status = -EAGAIN;
                 goto out_unlock;
         }
+        atomic_inc(&fp->fi_delegees);
         hash_delegation_locked(dp, fp);
         status = 0;
 out_unlock:
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index c991616acca9..bff8567aa42d 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -259,16 +259,15 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
         struct fsnotify_event *kevent;
         char __user *start;
         int ret;
-        DEFINE_WAIT(wait);
+        DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
         start = buf;
         group = file->private_data;
 
         pr_debug("%s: group=%p\n", __func__, group);
 
+        add_wait_queue(&group->notification_waitq, &wait);
         while (1) {
-                prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
                 mutex_lock(&group->notification_mutex);
                 kevent = get_one_event(group, count);
                 mutex_unlock(&group->notification_mutex);
@@ -289,7 +288,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 
                         if (start != buf)
                                 break;
-                        schedule();
+
+                        wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
                         continue;
                 }
 
@@ -318,8 +318,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
                 buf += ret;
                 count -= ret;
         }
+        remove_wait_queue(&group->notification_waitq, &wait);
 
-        finish_wait(&group->notification_waitq, &wait);
         if (start != buf && ret != -EFAULT)
                 ret = buf - start;
         return ret;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 79b5af5e6a7b..cecd875653e4 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2023,11 +2023,8 @@ leave:
         dlm_lockres_drop_inflight_ref(dlm, res);
         spin_unlock(&res->spinlock);
 
-        if (ret < 0) {
+        if (ret < 0)
                 mlog_errno(ret);
-                if (newlock)
-                        dlm_lock_put(newlock);
-        }
 
         return ret;
 }
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b931e04e3388..914c121ec890 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
                                      struct inode *inode,
                                      const char *symname);
 
+static int ocfs2_double_lock(struct ocfs2_super *osb,
+                             struct buffer_head **bh1,
+                             struct inode *inode1,
+                             struct buffer_head **bh2,
+                             struct inode *inode2,
+                             int rename);
+
+static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
 
@@ -678,8 +686,10 @@ static int ocfs2_link(struct dentry *old_dentry,
 {
         handle_t *handle;
         struct inode *inode = old_dentry->d_inode;
+        struct inode *old_dir = old_dentry->d_parent->d_inode;
         int err;
         struct buffer_head *fe_bh = NULL;
+        struct buffer_head *old_dir_bh = NULL;
         struct buffer_head *parent_fe_bh = NULL;
         struct ocfs2_dinode *fe = NULL;
         struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
@@ -696,19 +706,33 @@ static int ocfs2_link(struct dentry *old_dentry,
 
         dquot_initialize(dir);
 
-        err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT);
+        err = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
+                        &parent_fe_bh, dir, 0);
         if (err < 0) {
                 if (err != -ENOENT)
                         mlog_errno(err);
                 return err;
         }
 
+        /* make sure both dirs have bhs
+         * get an extra ref on old_dir_bh if old==new */
+        if (!parent_fe_bh) {
+                if (old_dir_bh) {
+                        parent_fe_bh = old_dir_bh;
+                        get_bh(parent_fe_bh);
+                } else {
+                        mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str);
+                        err = -EIO;
+                        goto out;
+                }
+        }
+
         if (!dir->i_nlink) {
                 err = -ENOENT;
                 goto out;
         }
 
-        err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+        err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name,
                         old_dentry->d_name.len, &old_de_ino);
         if (err) {
                 err = -ENOENT;
@@ -801,10 +825,11 @@ out_unlock_inode:
         ocfs2_inode_unlock(inode, 1);
 
 out:
-        ocfs2_inode_unlock(dir, 1);
+        ocfs2_double_unlock(old_dir, dir);
 
         brelse(fe_bh);
         brelse(parent_fe_bh);
+        brelse(old_dir_bh);
 
         ocfs2_free_dir_lookup_result(&lookup);
 
@@ -1072,14 +1097,15 @@ static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
 }
 
 /*
- * The only place this should be used is rename!
+ * The only place this should be used is rename and link!
  * if they have the same id, then the 1st one is the only one locked.
  */
 static int ocfs2_double_lock(struct ocfs2_super *osb,
                              struct buffer_head **bh1,
                              struct inode *inode1,
                              struct buffer_head **bh2,
-                             struct inode *inode2)
+                             struct inode *inode2,
+                             int rename)
 {
         int status;
         int inode1_is_ancestor, inode2_is_ancestor;
@@ -1127,7 +1153,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
                 }
                 /* lock id2 */
                 status = ocfs2_inode_lock_nested(inode2, bh2, 1,
-                                                 OI_LS_RENAME1);
+                                rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT);
                 if (status < 0) {
                         if (status != -ENOENT)
                                 mlog_errno(status);
@@ -1136,7 +1162,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
         }
 
         /* lock id1 */
-        status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2);
+        status = ocfs2_inode_lock_nested(inode1, bh1, 1,
+                        rename == 1 ?  OI_LS_RENAME2 : OI_LS_PARENT);
         if (status < 0) {
                 /*
                  * An error return must mean that no cluster locks
@@ -1252,7 +1279,7 @@ static int ocfs2_rename(struct inode *old_dir,
 
         /* if old and new are the same, this'll just do one lock. */
         status = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
-                                   &new_dir_bh, new_dir);
+                                   &new_dir_bh, new_dir, 1);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;