Merge tag 'v4.9.138' into v4.9-rt

This is the 4.9.138 stable release

14 files changed, 112 insertions, 46 deletions

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index d7b78d531e63..398a3eddb2df 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -204,6 +204,14 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 			break;
 		if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
 			break;
+		/*
+		 * p9_client_lock_dotl overwrites flock.client_id with the
+		 * server message, free and reuse the client name
+		 */
+		if (flock.client_id != fid->clnt->name) {
+			kfree(flock.client_id);
+			flock.client_id = fid->clnt->name;
+		}
 	}
 
 	/* map 9p status to VFS status */
@@ -235,6 +243,8 @@ out_unlock:
 		locks_lock_file_wait(filp, fl);
 		fl->fl_type = fl_type;
 	}
+	if (flock.client_id != fid->clnt->name)
+		kfree(flock.client_id);
 out:
 	return res;
 }
@@ -269,7 +279,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 
 	res = p9_client_getlock_dotl(fid, &glock);
 	if (res < 0)
-		return res;
+		goto out;
 	/* map 9p lock type to os lock type */
 	switch (glock.type) {
 	case P9_LOCK_TYPE_RDLCK:
@@ -290,7 +300,9 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 			fl->fl_end = glock.start + glock.length - 1;
 		fl->fl_pid = glock.proc_id;
 	}
-	kfree(glock.client_id);
+out:
+	if (glock.client_id != fid->clnt->name)
+		kfree(glock.client_id);
 	return res;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17e143d91fa9..1b1a9e35e082 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1548,12 +1548,11 @@ out_check:
 	}
 	btrfs_release_path(path);
 
-	if (cur_offset <= end && cow_start == (u64)-1) {
+	if (cur_offset <= end && cow_start == (u64)-1)
 		cow_start = cur_offset;
-		cur_offset = end;
-	}
 
 	if (cow_start != (u64)-1) {
+		cur_offset = end;
 		ret = cow_file_range(inode, locked_page, cow_start, end, end,
 				     page_started, nr_written, 1, NULL);
 		if (ret)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index cbf512b64597..96ad2778405b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3911,9 +3911,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		goto out_unlock;
 	if (len == 0)
 		olen = len = src->i_size - off;
-	/* if we extend to eof, continue to block boundary */
-	if (off + len == src->i_size)
+	/*
+	 * If we extend to eof, continue to block boundary if and only if the
+	 * destination end offset matches the destination file's size, otherwise
+	 * we would be corrupting data by placing the eof block into the middle
+	 * of a file.
+	 */
+	if (off + len == src->i_size) {
+		if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size)
+			goto out_unlock;
 		len = ALIGN(src->i_size, bs) - off;
+	}
 
 	if (len == 0) {
 		ret = 0;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 1f754336f801..30d9d9e7057d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1077,8 +1077,12 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
-		dput(dn);
-		dn = realdn; /* note realdn contains the error */
+		dn = realdn;
+		/*
+		 * Caller should release 'dn' in the case of error.
+		 * If 'req->r_dentry' is passed to this function,
+		 * caller should leave 'req->r_dentry' untouched.
+		 */
 		goto out;
 	} else if (realdn) {
 		dout("dn %p (%d) spliced with %p (%d) "
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 314b4edac72b..fea6db1ee065 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -64,7 +64,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length)
 
 		/* back up enough to print this bus id with '/' */
 		length -= cur;
-		strncpy(buffer + length,config_item_name(p),cur);
+		memcpy(buffer + length, config_item_name(p), cur);
 		*(buffer + --length) = '/';
 	}
 }
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index bc727c393a89..3c3757ee11f0 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -124,6 +124,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 	if (!is_dx_block && type == INDEX) {
 		ext4_error_inode(inode, func, line, block,
 		       "directory leaf block found instead of index block");
+		brelse(bh);
 		return ERR_PTR(-EFSCORRUPTED);
 	}
 	if (!ext4_has_metadata_csum(inode->i_sb) ||
@@ -2842,7 +2843,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 			list_del_init(&EXT4_I(inode)->i_orphan);
 			mutex_unlock(&sbi->s_orphan_lock);
 		}
-	}
+	} else
+		brelse(iloc.bh);
+
 	jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
 	jbd_debug(4, "orphan inode %lu will point to %d\n",
 			inode->i_ino, NEXT_ORPHAN(inode));
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 1da301ee78ce..9be605c63ae1 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -442,16 +442,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 
 		BUFFER_TRACE(bh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, bh);
-		if (err)
+		if (err) {
+			brelse(bh);
 			return err;
+		}
 		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block,
 			   block - start, count2);
 		ext4_set_bits(bh->b_data, block - start, count2);
 
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (unlikely(err))
 			return err;
-		brelse(bh);
 	}
 
 	return 0;
@@ -588,7 +590,6 @@ handle_bb:
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 		overhead = ext4_group_overhead_blocks(sb, group);
@@ -600,9 +601,9 @@ handle_bb:
 		ext4_mark_bitmap_end(group_data[i].blocks_count,
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 
 handle_ib:
 		if (bg_flags[i] & EXT4_BG_INODE_UNINIT)
@@ -617,18 +618,16 @@ handle_ib:
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 
 		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 	}
-	bh = NULL;
 
 	/* Mark group tables in block bitmap */
 	for (j = 0; j < GROUP_TABLE_COUNT; j++) {
@@ -659,7 +658,6 @@ handle_ib:
 	}
 
 out:
-	brelse(bh);
 	err2 = ext4_journal_stop(handle);
 	if (err2 && !err)
 		err = err2;
@@ -846,6 +844,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
 	if (unlikely(err)) {
 		ext4_std_error(sb, err);
+		iloc.bh = NULL;
 		goto exit_inode;
 	}
 	brelse(dind);
@@ -897,6 +896,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 				     sizeof(struct buffer_head *),
 				     GFP_NOFS);
 	if (!n_group_desc) {
+		brelse(gdb_bh);
 		err = -ENOMEM;
 		ext4_warning(sb, "not enough memory for %lu groups",
 			     gdb_num + 1);
@@ -912,8 +912,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 	kvfree(o_group_desc);
 	BUFFER_TRACE(gdb_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, gdb_bh);
-	if (unlikely(err))
-		brelse(gdb_bh);
 	return err;
 }
 
@@ -1095,8 +1093,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data,
 			   backup_block, backup_block -
 			   ext4_group_first_block_no(sb, group));
 		BUFFER_TRACE(bh, "get_write_access");
-		if ((err = ext4_journal_get_write_access(handle, bh)))
+		if ((err = ext4_journal_get_write_access(handle, bh))) {
+			brelse(bh);
 			break;
+		}
 		lock_buffer(bh);
 		memcpy(bh->b_data, data, size);
 		if (rest)
@@ -1991,7 +1991,7 @@ retry:
 
 	err = ext4_alloc_flex_bg_array(sb, n_group + 1);
 	if (err)
-		return err;
+		goto out;
 
 	err = ext4_mb_alloc_groupinfo(sb, n_group + 1);
 	if (err)
@@ -2027,6 +2027,10 @@ retry:
 		n_blocks_count_retry = 0;
 		free_flex_gd(flex_gd);
 		flex_gd = NULL;
+		if (resize_inode) {
+			iput(resize_inode);
+			resize_inode = NULL;
+		}
 		goto retry;
 	}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f88d4804c3a8..75177eb498ed 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3897,6 +3897,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_groups_count = blocks_count;
 	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
+	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+		ret = -EINVAL;
+		goto failed_mount;
+	}
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
 	if (ext4_has_feature_meta_bg(sb)) {
@@ -3916,14 +3924,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		ret = -ENOMEM;
 		goto failed_mount;
 	}
-	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
-	    le32_to_cpu(es->s_inodes_count)) {
-		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
-			 le32_to_cpu(es->s_inodes_count),
-			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
-		ret = -EINVAL;
-		goto failed_mount;
-	}
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
@@ -4305,6 +4305,7 @@ failed_mount6:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 38385bcb9148..22f765069655 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1221,6 +1221,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 		} else if (error == -ENOSPC) {
 			if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
+				brelse(bs.bh);
+				bs.bh = NULL;
 				error = ext4_xattr_block_find(inode, &i, &bs);
 				if (error)
 					goto cleanup;
@@ -1391,6 +1393,8 @@ out:
 	kfree(buffer);
 	if (is)
 		brelse(is->iloc.bh);
+	if (bs)
+		brelse(bs->bh);
 	kfree(is);
 	kfree(bs);
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c94bab6103f5..b4253181b5d4 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -383,12 +383,19 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 	if (test_bit(FR_BACKGROUND, &req->flags)) {
 		spin_lock(&fc->lock);
 		clear_bit(FR_BACKGROUND, &req->flags);
-		if (fc->num_background == fc->max_background)
+		if (fc->num_background == fc->max_background) {
 			fc->blocked = 0;
-
-		/* Wake up next waiter, if any */
-		if (!fc->blocked && waitqueue_active(&fc->blocked_waitq))
 			wake_up(&fc->blocked_waitq);
+		} else if (!fc->blocked) {
+			/*
+			 * Wake up next waiter, if any.  It's okay to use
+			 * waitqueue_active(), as we've already synced up
+			 * fc->blocked with waiters with the wake_up() call
+			 * above.
+			 */
+			if (waitqueue_active(&fc->blocked_waitq))
+				wake_up(&fc->blocked_waitq);
+		}
 
 		if (fc->num_background == fc->congestion_threshold &&
 		    fc->connected && fc->bdi_initialized) {
@@ -1303,12 +1310,14 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 		goto out_end;
 	}
 	list_move_tail(&req->list, &fpq->processing);
-	spin_unlock(&fpq->lock);
+	__fuse_get_request(req);
 	set_bit(FR_SENT, &req->flags);
+	spin_unlock(&fpq->lock);
 	/* matches barrier in request_wait_answer() */
 	smp_mb__after_atomic();
 	if (test_bit(FR_INTERRUPTED, &req->flags))
 		queue_interrupt(fiq, req);
+	fuse_put_request(fc, req);
 
 	return reqsize;
 
@@ -1706,8 +1715,10 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 	req->in.args[1].size = total_len;
 
 	err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique);
-	if (err)
+	if (err) {
 		fuse_retrieve_end(fc, req);
+		fuse_put_request(fc, req);
+	}
 
 	return err;
 }
@@ -1866,16 +1877,20 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 
 	/* Is it an interrupt reply? */
 	if (req->intr_unique == oh.unique) {
+		__fuse_get_request(req);
 		spin_unlock(&fpq->lock);
 
 		err = -EINVAL;
-		if (nbytes != sizeof(struct fuse_out_header))
+		if (nbytes != sizeof(struct fuse_out_header)) {
+			fuse_put_request(fc, req);
 			goto err_finish;
+		}
 
 		if (oh.error == -ENOSYS)
 			fc->no_interrupt = 1;
 		else if (oh.error == -EAGAIN)
 			queue_interrupt(&fc->iq, req);
+		fuse_put_request(fc, req);
 
 		fuse_copy_finish(cs);
 		return nbytes;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 4408abf6675b..1cd46e667e3d 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2900,10 +2900,12 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	if (io->async) {
+		bool blocking = io->blocking;
+
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
 
 		/* we have a non-extending, async request, so return */
-		if (!io->blocking)
+		if (!blocking)
 			return -EIOCBQUEUED;
 
 		wait_for_completion(&wait);
diff --git a/fs/namespace.c b/fs/namespace.c
index 4935d21d5d0c..201329f8474b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1603,8 +1603,13 @@ static int do_umount(struct mount *mnt, int flags)
 
 	namespace_lock();
 	lock_mount_hash();
-	event++;
 
+	/* Recheck MNT_LOCKED with the locks held */
+	retval = -EINVAL;
+	if (mnt->mnt.mnt_flags & MNT_LOCKED)
+		goto out;
+
+	event++;
 	if (flags & MNT_DETACH) {
 		if (!list_empty(&mnt->mnt_list))
 			umount_tree(mnt, UMOUNT_PROPAGATE);
@@ -1618,6 +1623,7 @@ static int do_umount(struct mount *mnt, int flags)
 			retval = 0;
 		}
 	}
+out:
 	unlock_mount_hash();
 	namespace_unlock();
 	return retval;
@@ -1708,7 +1714,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 		goto dput_and_out;
 	if (!check_mnt(mnt))
 		goto dput_and_out;
-	if (mnt->mnt.mnt_flags & MNT_LOCKED)
+	if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */
 		goto dput_and_out;
 	retval = -EPERM;
 	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
@@ -1786,8 +1792,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 		for (s = r; s; s = next_mnt(s, r)) {
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
-				s = skip_mnt_tree(s);
-				continue;
+				if (s->mnt.mnt_flags & MNT_LOCKED) {
+					/* Both unbindable and locked. */
+					q = ERR_PTR(-EPERM);
+					goto out;
+				} else {
+					s = skip_mnt_tree(s);
+					continue;
+				}
 			}
 			if (!(flag & CL_COPY_MNT_NS_FILE) &&
 			    is_mnt_ns_file(s->mnt.mnt_root)) {
@@ -1840,7 +1852,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();
 	lock_mount_hash();
-	umount_tree(real_mount(mnt), UMOUNT_SYNC);
+	umount_tree(real_mount(mnt), 0);
 	unlock_mount_hash();
 	namespace_unlock();
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index e9495516527d..66985a6a7047 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1016,6 +1016,9 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 
+	if (!cstate->save_fh.fh_dentry)
+		return nfserr_nofilehandle;
+
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
 					    src_stateid, RD_STATE, src, NULL);
 	if (status) {
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 3ecb9f337b7d..20e610419501 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -1896,8 +1896,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
-				brelse(bh);
-				continue;
+				break;
 			}
 			if (le64_to_cpu(de->inode)) {
 				unsigned char d_type = DT_UNKNOWN;