nbd: fsync and kill block device on shutdown

commit 3a2d63f8 upstream.

There are two problems with shutdown in the NBD driver.

1: Receiving the NBD_DISCONNECT ioctl does not sync the filesystem.

   This patch adds the sync operation into __nbd_ioctl()'s
   NBD_DISCONNECT handler.  This is useful because BLKFLSBUF is restricted
   to processes that have CAP_SYS_ADMIN, and the NBD client may not
   possess it (fsync of the block device does not sync the filesystem,
   either).

2: Once we clear the socket we have no guarantee that later reads will
   come from the same backing storage.

   The patch adds calls to kill_bdev() in __nbd_ioctl()'s socket
   clearing code so the page cache is cleaned, lest reads that hit on the
   page cache will return stale data from the previously-accessible disk.

Example:

    # qemu-nbd -r -c/dev/nbd0 /dev/sr0
    # file -s /dev/nbd0
    /dev/stdin: # UDF filesystem data (version 1.5) etc.
    # qemu-nbd -d /dev/nbd0
    # qemu-nbd -r -c/dev/nbd0 /dev/sda
    # file -s /dev/nbd0
    /dev/stdin: # UDF filesystem data (version 1.5) etc.

While /dev/sda has:

    # file -s /dev/sda
    /dev/sda: x86 boot sector; etc.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Paul Clements <Paul.Clements@steeleye.com>
Cc: Alex Bligh <alex@alex.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2:
 - Adjusted context
 - s/\bnbd\b/lo/
 - Incorporate export of kill_bdev() from commit ff01bb48
   ('fs: move code out of buffer.c')]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

drivers/block/nbd.c

@@ -584,12 +584,20 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		struct request sreq;
 
 		dev_info(disk_to_dev(lo->disk), "NBD_DISCONNECT\n");
+		if (!lo->sock)
+			return -EINVAL;
 
+		mutex_unlock(&lo->tx_lock);
+		fsync_bdev(bdev);
+		mutex_lock(&lo->tx_lock);
 		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
+
+		/* Check again after getting mutex back.  */
 		if (!lo->sock)
 			return -EINVAL;
+
 		nbd_send_req(lo, &sreq);
                 return 0;
 	}
@@ -603,6 +611,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		nbd_clear_que(lo);
 		BUG_ON(!list_empty(&lo->queue_head));
 		BUG_ON(!list_empty(&lo->waiting_queue));
+		kill_bdev(bdev);
 		if (file)
 			fput(file);
 		return 0;
@@ -683,6 +692,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		lo->file = NULL;
 		nbd_clear_que(lo);
 		dev_warn(disk_to_dev(lo->disk), "queue cleared\n");
+		kill_bdev(bdev);
 		if (file)
 			fput(file);
 		lo->bytesize = 0;

fs/block_dev.c

@@ -82,13 +82,14 @@ sector_t blkdev_max_block(struct block_device *bdev)
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
-static void kill_bdev(struct block_device *bdev)
+void kill_bdev(struct block_device *bdev)
 {
 	if (bdev->bd_inode->i_mapping->nrpages == 0)
 		return;
 	invalidate_bh_lrus();
 	truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
 }	
+EXPORT_SYMBOL(kill_bdev);
 
 int set_blocksize(struct block_device *bdev, int size)
 {

include/linux/fs.h

@@ -2103,6 +2103,7 @@ extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
 extern void invalidate_bdev(struct block_device *);
 extern int sync_blockdev(struct block_device *bdev);
+extern void kill_bdev(struct block_device *);
 extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
@@ -2110,6 +2111,7 @@ extern int fsync_bdev(struct block_device *);
 #else
 static inline void bd_forget(struct inode *inode) {}
 static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline void kill_bdev(struct block_device *bdev) {}
 static inline void invalidate_bdev(struct block_device *bdev) {}
 
 static inline struct super_block *freeze_bdev(struct block_device *sb)