blk-mq: support per-distpatch_queue flush machinery

This patch supports to run one single flush machinery for
each blk-mq dispatch queue, so that:

- current init_request and exit_request callbacks can
cover flush request too, then the buggy copying way of
initializing flush request's pdu can be fixed

- flushing performance gets improved in case of multi hw-queue

In fio sync write test over virtio-blk(4 hw queues, ioengine=sync,
iodepth=64, numjobs=4, bs=4K), it is observed that througput gets
increased a lot over my test environment:
	- throughput: +70% in case of virtio-blk over null_blk
	- throughput: +30% in case of virtio-blk over SSD image

The multi virtqueue feature isn't merged to QEMU yet, and patches for
the feature can be found in below tree:

	git://kernel.ubuntu.com/ming/qemu.git  	v2.1.0-mq.4

And simply passing 'num_queues=4 vectors=5' should be enough to
enable multi queue(quad queue) feature for QEMU virtio-blk.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

include/linux/blk-mq.h

@@ -4,6 +4,7 @@
 #include <linux/blkdev.h>
 
 struct blk_mq_tags;
+struct blk_flush_queue;
 
 struct blk_mq_cpu_notifier {
 	struct list_head list;
@@ -34,6 +35,7 @@ struct blk_mq_hw_ctx {
 
 	struct request_queue	*queue;
 	unsigned int		queue_num;
+	struct blk_flush_queue	*fq;
 
 	void			*driver_data;
 
@@ -119,6 +121,10 @@ struct blk_mq_ops {
 	/*
 	 * Called for every command allocated by the block layer to allow
 	 * the driver to set up driver specific data.
+	 *
+	 * Tag greater than or equal to queue_depth is for setting up
+	 * flush request.
+	 *
 	 * Ditto for exit/teardown.
 	 */
 	init_request_fn		*init_request;