block: improve layout of struct request

It's been a while since this was analyzed, move some members around to
better flow with the use case. Initial state up top, and queued state
after that. This improves my peak case by about 1.5%, from 7750K to
7900K IOPS.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

include/linux/blk-mq.h

@@ -83,6 +83,8 @@ struct request {
 	int tag;
 	int internal_tag;
 
+	unsigned int timeout;
+
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
 	sector_t __sector;		/* sector cursor */
@@ -95,49 +97,6 @@ struct request {
 		struct request *rq_next;
 	};
 
-	/*
-	 * The hash is used inside the scheduler, and killed once the
-	 * request reaches the dispatch list. The ipi_list is only used
-	 * to queue the request for softirq completion, which is long
-	 * after the request has been unhashed (and even removed from
-	 * the dispatch list).
-	 */
-	union {
-		struct hlist_node hash;	/* merge hash */
-		struct llist_node ipi_list;
-	};
-
-	/*
-	 * The rb_node is only used inside the io scheduler, requests
-	 * are pruned when moved to the dispatch queue. So let the
-	 * completion_data share space with the rb_node.
-	 */
-	union {
-		struct rb_node rb_node;	/* sort/lookup */
-		struct bio_vec special_vec;
-		void *completion_data;
-		int error_count; /* for legacy drivers, don't use */
-	};
-
-	/*
-	 * Three pointers are available for the IO schedulers, if they need
-	 * more they have to dynamically allocate it.  Flush requests are
-	 * never put on the IO scheduler. So let the flush fields share
-	 * space with the elevator data.
-	 */
-	union {
-		struct {
-			struct io_cq		*icq;
-			void			*priv[2];
-		} elv;
-
-		struct {
-			unsigned int		seq;
-			struct list_head	list;
-			rq_end_io_fn		*saved_end_io;
-		} flush;
-	};
-
 	struct gendisk *rq_disk;
 	struct block_device *part;
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
@@ -180,9 +139,52 @@ struct request {
 	enum mq_rq_state state;
 	refcount_t ref;
 
-	unsigned int timeout;
 	unsigned long deadline;
 
+	/*
+	 * The hash is used inside the scheduler, and killed once the
+	 * request reaches the dispatch list. The ipi_list is only used
+	 * to queue the request for softirq completion, which is long
+	 * after the request has been unhashed (and even removed from
+	 * the dispatch list).
+	 */
+	union {
+		struct hlist_node hash;	/* merge hash */
+		struct llist_node ipi_list;
+	};
+
+	/*
+	 * The rb_node is only used inside the io scheduler, requests
+	 * are pruned when moved to the dispatch queue. So let the
+	 * completion_data share space with the rb_node.
+	 */
+	union {
+		struct rb_node rb_node;	/* sort/lookup */
+		struct bio_vec special_vec;
+		void *completion_data;
+		int error_count; /* for legacy drivers, don't use */
+	};
+
+
+	/*
+	 * Three pointers are available for the IO schedulers, if they need
+	 * more they have to dynamically allocate it.  Flush requests are
+	 * never put on the IO scheduler. So let the flush fields share
+	 * space with the elevator data.
+	 */
+	union {
+		struct {
+			struct io_cq		*icq;
+			void			*priv[2];
+		} elv;
+
+		struct {
+			unsigned int		seq;
+			struct list_head	list;
+			rq_end_io_fn		*saved_end_io;
+		} flush;
+	};
+
 	union {
 		struct __call_single_data csd;
 		u64 fifo_time;