Merge branch 'for-3.18/core' of git://git.kernel.dk/linux-block

Pull core block layer changes from Jens Axboe:
 "This is the core block IO pull request for 3.18.  Apart from the new
  and improved flush machinery for blk-mq, this is all mostly bug fixes
  and cleanups.

   - blk-mq timeout updates and fixes from Christoph.

   - Removal of REQ_END, also from Christoph.  We pass it through the
     ->queue_rq() hook for blk-mq instead, freeing up one of the request
     bits.  The space was overly tight on 32-bit, so Martin also killed
     REQ_KERNEL since it's no longer used.

   - blk integrity updates and fixes from Martin and Gu Zheng.

   - Update to the flush machinery for blk-mq from Ming Lei.  Now we
     have a per hardware context flush request, which both cleans up the
     code should scale better for flush intensive workloads on blk-mq.

   - Improve the error printing, from Rob Elliott.

   - Backing device improvements and cleanups from Tejun.

   - Fixup of a misplaced rq_complete() tracepoint from Hannes.

   - Make blk_get_request() return error pointers, fixing up issues
     where we NULL deref when a device goes bad or missing.  From Joe
     Lawrence.

   - Prep work for drastically reducing the memory consumption of dm
     devices from Junichi Nomura.  This allows creating clone bio sets
     without preallocating a lot of memory.

   - Fix a blk-mq hang on certain combinations of queue depths and
     hardware queues from me.

   - Limit memory consumption for blk-mq devices for crash dump
     scenarios and drivers that use crazy high depths (certain SCSI
     shared tag setups).  We now just use a single queue and limited
     depth for that"

* 'for-3.18/core' of git://git.kernel.dk/linux-block: (58 commits)
  block: Remove REQ_KERNEL
  blk-mq: allocate cpumask on the home node
  bio-integrity: remove the needless fail handle of bip_slab creating
  block: include func name in __get_request prints
  block: make blk_update_request print prefix match ratelimited prefix
  blk-merge: don't compute bi_phys_segments from bi_vcnt for cloned bio
  block: fix alignment_offset math that assumes io_min is a power-of-2
  blk-mq: Make bt_clear_tag() easier to read
  blk-mq: fix potential hang if rolling wakeup depth is too high
  block: add bioset_create_nobvec()
  block: use bio_clone_fast() in blk_rq_prep_clone()
  block: misplaced rq_complete tracepoint
  sd: Honor block layer integrity handling flags
  block: Replace strnicmp with strncasecmp
  block: Add T10 Protection Information functions
  block: Don't merge requests if integrity flags differ
  block: Integrity checksum flag
  block: Relocate bio integrity flags
  block: Add a disk flag to block integrity profile
  block: Add prefix to block integrity profile flags
  ...

drivers/scsi/scsi_lib.c

@@ -221,7 +221,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	int ret = DRIVER_ERROR << 24;
 
 	req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);
-	if (!req)
+	if (IS_ERR(req))
 		return ret;
 	blk_rq_set_block_pc(req);
 
@@ -715,7 +715,7 @@ static bool scsi_end_request(struct request *req, int error,
 
 	if (req->mq_ctx) {
 		/*
-		 * In the MQ case the command gets freed by __blk_mq_end_io,
+		 * In the MQ case the command gets freed by __blk_mq_end_request,
 		 * so we have to do all cleanup that depends on it earlier.
 		 *
 		 * We also can't kick the queues from irq context, so we
@@ -723,7 +723,7 @@ static bool scsi_end_request(struct request *req, int error,
 		 */
 		scsi_mq_uninit_cmd(cmd);
 
-		__blk_mq_end_io(req, error);
+		__blk_mq_end_request(req, error);
 
 		if (scsi_target(sdev)->single_lun ||
 		    !list_empty(&sdev->host->starved_list))
@@ -1847,6 +1847,8 @@ static int scsi_mq_prep_fn(struct request *req)
 		next_rq->special = bidi_sdb;
 	}
 
+	blk_mq_start_request(req);
+
 	return scsi_setup_cmnd(sdev, req);
 }
 
@@ -1856,7 +1858,8 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)
 	blk_mq_complete_request(cmd->request);
 }
 
-static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
+static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
+		bool last)
 {
 	struct request_queue *q = req->q;
 	struct scsi_device *sdev = q->queuedata;
@@ -1880,11 +1883,14 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	if (!scsi_host_queue_ready(q, shost, sdev))
 		goto out_dec_target_busy;
 
+
 	if (!(req->cmd_flags & REQ_DONTPREP)) {
 		ret = prep_to_mq(scsi_mq_prep_fn(req));
 		if (ret)
 			goto out_dec_host_busy;
 		req->cmd_flags |= REQ_DONTPREP;
+	} else {
+		blk_mq_start_request(req);
 	}
 
 	scsi_init_cmd_errh(cmd);
@@ -1931,6 +1937,14 @@ out:
 	return ret;
 }
 
+static enum blk_eh_timer_return scsi_timeout(struct request *req,
+		bool reserved)
+{
+	if (reserved)
+		return BLK_EH_RESET_TIMER;
+	return scsi_times_out(req);
+}
+
 static int scsi_init_request(void *data, struct request *rq,
 		unsigned int hctx_idx, unsigned int request_idx,
 		unsigned int numa_node)
@@ -2042,7 +2056,7 @@ static struct blk_mq_ops scsi_mq_ops = {
 	.map_queue	= blk_mq_map_queue,
 	.queue_rq	= scsi_queue_rq,
 	.complete	= scsi_softirq_done,
-	.timeout	= scsi_times_out,
+	.timeout	= scsi_timeout,
 	.init_request	= scsi_init_request,
 	.exit_request	= scsi_exit_request,
 };