Merge tag 'v4.4.44' into linux-linaro-lsk-v4.4

 This is the 4.4.44 stable release

10 files changed, 82 insertions, 42 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2af08c3de775..2a2e370399ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2520,11 +2520,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		if (ref && ref->seq &&
 		    btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
 			spin_unlock(&locked_ref->lock);
-			btrfs_delayed_ref_unlock(locked_ref);
 			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
 			delayed_refs->num_heads_ready++;
 			spin_unlock(&delayed_refs->lock);
+			btrfs_delayed_ref_unlock(locked_ref);
 			locked_ref = NULL;
 			cond_resched();
 			count++;
@@ -2570,7 +2570,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 					 */
 					if (must_insert_reserved)
 						locked_ref->must_insert_reserved = 1;
+					spin_lock(&delayed_refs->lock);
 					locked_ref->processing = 0;
+					delayed_refs->num_heads_ready++;
+					spin_unlock(&delayed_refs->lock);
 					btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
 					btrfs_delayed_ref_unlock(locked_ref);
 					return ret;
diff --git a/fs/dcache.c b/fs/dcache.c
index 71b6056ad35d..849c1c1e787b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1322,8 +1322,11 @@ int d_set_mounted(struct dentry *dentry)
 	}
 	spin_lock(&dentry->d_lock);
 	if (!d_unlinked(dentry)) {
-		dentry->d_flags |= DCACHE_MOUNTED;
-		ret = 0;
+		ret = -EBUSY;
+		if (!d_mountpoint(dentry)) {
+			dentry->d_flags |= DCACHE_MOUNTED;
+			ret = 0;
+		}
 	}
  	spin_unlock(&dentry->d_lock);
 out:
diff --git a/fs/namespace.c b/fs/namespace.c
index 5be02a0635be..da98a1bbd8b5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -743,26 +743,50 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
 	return NULL;
 }
 
-static struct mountpoint *new_mountpoint(struct dentry *dentry)
+static struct mountpoint *get_mountpoint(struct dentry *dentry)
 {
-	struct hlist_head *chain = mp_hash(dentry);
-	struct mountpoint *mp;
+	struct mountpoint *mp, *new = NULL;
 	int ret;
 
-	mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
-	if (!mp)
+	if (d_mountpoint(dentry)) {
+mountpoint:
+		read_seqlock_excl(&mount_lock);
+		mp = lookup_mountpoint(dentry);
+		read_sequnlock_excl(&mount_lock);
+		if (mp)
+			goto done;
+	}
+
+	if (!new)
+		new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
+	if (!new)
 		return ERR_PTR(-ENOMEM);
 
+
+	/* Exactly one processes may set d_mounted */
 	ret = d_set_mounted(dentry);
-	if (ret) {
-		kfree(mp);
-		return ERR_PTR(ret);
-	}
 
-	mp->m_dentry = dentry;
-	mp->m_count = 1;
-	hlist_add_head(&mp->m_hash, chain);
-	INIT_HLIST_HEAD(&mp->m_list);
+	/* Someone else set d_mounted? */
+	if (ret == -EBUSY)
+		goto mountpoint;
+
+	/* The dentry is not available as a mountpoint? */
+	mp = ERR_PTR(ret);
+	if (ret)
+		goto done;
+
+	/* Add the new mountpoint to the hash table */
+	read_seqlock_excl(&mount_lock);
+	new->m_dentry = dentry;
+	new->m_count = 1;
+	hlist_add_head(&new->m_hash, mp_hash(dentry));
+	INIT_HLIST_HEAD(&new->m_list);
+	read_sequnlock_excl(&mount_lock);
+
+	mp = new;
+	new = NULL;
+done:
+	kfree(new);
 	return mp;
 }
 
@@ -1557,11 +1581,11 @@ void __detach_mounts(struct dentry *dentry)
 	struct mount *mnt;
 
 	namespace_lock();
+	lock_mount_hash();
 	mp = lookup_mountpoint(dentry);
 	if (IS_ERR_OR_NULL(mp))
 		goto out_unlock;
 
-	lock_mount_hash();
 	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
@@ -1571,9 +1595,9 @@ void __detach_mounts(struct dentry *dentry)
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
-	unlock_mount_hash();
 	put_mountpoint(mp);
 out_unlock:
+	unlock_mount_hash();
 	namespace_unlock();
 }
 
@@ -1962,9 +1986,7 @@ retry:
 	namespace_lock();
 	mnt = lookup_mnt(path);
 	if (likely(!mnt)) {
-		struct mountpoint *mp = lookup_mountpoint(dentry);
-		if (!mp)
-			mp = new_mountpoint(dentry);
+		struct mountpoint *mp = get_mountpoint(dentry);
 		if (IS_ERR(mp)) {
 			namespace_unlock();
 			mutex_unlock(&dentry->d_inode->i_mutex);
@@ -1983,7 +2005,11 @@ retry:
 static void unlock_mount(struct mountpoint *where)
 {
 	struct dentry *dentry = where->m_dentry;
+
+	read_seqlock_excl(&mount_lock);
 	put_mountpoint(where);
+	read_sequnlock_excl(&mount_lock);
+
 	namespace_unlock();
 	mutex_unlock(&dentry->d_inode->i_mutex);
 }
@@ -3055,9 +3081,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	/* A moved mount should not expire automatically */
 	list_del_init(&new_mnt->mnt_expire);
+	put_mountpoint(root_mp);
 	unlock_mount_hash();
 	chroot_fs_refs(&root, &new);
-	put_mountpoint(root_mp);
 	error = 0;
 out4:
 	unlock_mount(old_mp);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 46cfed63d229..52ee0b73ab4a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -462,7 +462,7 @@ void nfs_force_use_readdirplus(struct inode *dir)
 {
 	if (!list_empty(&NFS_I(dir)->open_files)) {
 		nfs_advise_use_readdirplus(dir);
-		nfs_zap_mapping(dir, dir->i_mapping);
+		invalidate_mapping_pages(dir->i_mapping, 0, -1);
 	}
 }
 
@@ -847,17 +847,6 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
 	goto out;
 }
 
-static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
-{
-	struct nfs_inode *nfsi = NFS_I(dir);
-
-	if (nfs_attribute_cache_expired(dir))
-		return true;
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
-		return true;
-	return false;
-}
-
 /* The file offset position represents the dirent entry number.  A
    last cookie cache takes care of the common case of reading the
    whole directory.
@@ -890,7 +879,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
 
 	nfs_block_sillyrename(dentry);
-	if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
+	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
 	if (res < 0)
 		goto out;
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 4946ef40ba87..85ef38f9765f 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -283,7 +283,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
 out_test_devid:
-	if (filelayout_test_devid_unavailable(devid))
+	if (ret->ds_clp == NULL ||
+	    filelayout_test_devid_unavailable(devid))
 		ret = NULL;
 out:
 	return ret;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5cd3568eea06..3cae0726c1b1 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1185,13 +1185,11 @@ bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
 	 * i_lock */
         spin_lock(&ino->i_lock);
         lo = nfsi->layout;
-        if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+        if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+                rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
                 sleep = true;
+	}
         spin_unlock(&ino->i_lock);
-
-        if (sleep)
-                rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
-
         return sleep;
 }
 
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b002acf50203..60a5f1548cd9 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3321,6 +3321,16 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	mlog(ML_BASTS, "lockres %s, level %d => %d\n", lockres->l_name,
 	     lockres->l_level, new_level);
 
+	/*
+	 * On DLM_LKF_VALBLK, fsdlm behaves differently with o2cb. It always
+	 * expects DLM_LKF_VALBLK being set if the LKB has LVB, so that
+	 * we can recover correctly from node failure. Otherwise, we may get
+	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
+	 */
+	if (!ocfs2_is_o2cb_active() &&
+	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
+		lvb = 1;
+
 	if (lvb)
 		dlm_flags |= DLM_LKF_VALBLK;
 
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 5d965e83bd43..783bcdce5666 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -48,6 +48,12 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
  */
 static struct ocfs2_stack_plugin *active_stack;
 
+inline int ocfs2_is_o2cb_active(void)
+{
+	return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB);
+}
+EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active);
+
 static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name)
 {
 	struct ocfs2_stack_plugin *p;
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 66334a30cea8..e1b30931974d 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,4 +298,7 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+/* In ocfs2_downconvert_lock(), we need to know which stack we are using */
+int ocfs2_is_o2cb_active(void);
+
 #endif  /* STACKGLUE_H */
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index fe5b6e6c4671..4dbe1e2daeca 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -703,7 +703,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 	ctl_dir = container_of(head, struct ctl_dir, header);
 
 	if (!dir_emit_dots(file, ctx))
-		return 0;
+		goto out;
 
 	pos = 2;
 
@@ -713,6 +713,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		}
 	}
+out:
 	sysctl_head_finish(head);
 	return 0;
 }