vfs: cache request_queue in struct block_device

This makes it possible to get from the inode to the request_queue with one
less cache miss. Used in followon optimization.

The livetime of the pointer is the same as the gendisk.

This assumes that the queue will always stay the same in the gendisk while
it's visible to block_devices. I think that's safe correct?

Signed-off-by: Andi Kleen <[e-mail]>
Acked-by: Jeff Moyer <[e-mail]>
Cc: Jens Axboe <[e-mail]>
Cc: Christoph Hellwig <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

fs/block_dev.c

···
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
+		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		if (!partno) {
 			struct backing_dev_info *bdi;
···
 					disk_put_part(bdev->bd_part);
 					bdev->bd_part = NULL;
 					bdev->bd_disk = NULL;
+					bdev->bd_queue = NULL;
 					mutex_unlock(&bdev->bd_mutex);
 					disk_unblock_events(disk);
 					put_disk(disk);
···
 	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
+	bdev->bd_queue = NULL;
 	bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);

include/linux/fs.h

···
 	 * must be enforced here for CRIS, to let the least significant bit
 	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
 	 */
+struct request_queue;
 
 struct block_device {
 	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
···
 	unsigned		bd_part_count;
 	int			bd_invalidated;
 	struct gendisk *	bd_disk;
+	struct request_queue *  bd_queue;
 	struct list_head	bd_list;
 	/*
 	 * Private data.  You must have bd_claim'ed the block_device