Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:

 - Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
   was initially a fork of CFQ, but subsequently changed to implement
   fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
   to be used on desktop type single drives, providing good fairness.
   From Paolo.

 - Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
   using a scalable token based algorithm that throttles IO based on
   live completion IO stats, similary to blk-wbt. From Omar.

 - A series from Jan, moving users to separately allocated backing
   devices. This continues the work of separating backing device life
   times, solving various problems with hot removal.

 - A series of updates for lightnvm, mostly from Javier. Includes a
   'pblk' target that exposes an open channel SSD as a physical block
   device.

 - A series of fixes and improvements for nbd from Josef.

 - A series from Omar, removing queue sharing between devices on mostly
   legacy drivers. This helps us clean up other bits, if we know that a
   queue only has a single device backing. This has been overdue for
   more than a decade.

 - Fixes for the blk-stats, and improvements to unify the stats and user
   windows. This both improves blk-wbt, and enables other users to
   register a need to receive IO stats for a device. From Omar.

 - blk-throttle improvements from Shaohua. This provides a scalable
   framework for implementing scalable priotization - particularly for
   blk-mq, but applicable to any type of block device. The interface is
   marked experimental for now.

 - Bucketized IO stats for IO polling from Stephen Bates. This improves
   efficiency of polled workloads in the presence of mixed block size
   IO.

 - A few fixes for opal, from Scott.

 - A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
   From a variety of folks, mostly Sagi and James Smart.

 - A series from Bart, improving our exposed info and capabilities from
   the blk-mq debugfs support.

 - A series from Christoph, cleaning up how handle WRITE_ZEROES.

 - A series from Christoph, cleaning up the block layer handling of how
   we track errors in a request. On top of being a nice cleanup, it also
   shrinks the size of struct request a bit.

 - Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
   never used by platforms, and the latter has outlived it's usefulness.

 - Various little bug fixes and cleanups from a wide variety of folks.

* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
  block: hide badblocks attribute by default
  blk-mq: unify hctx delay_work and run_work
  block: add kblock_mod_delayed_work_on()
  blk-mq: unify hctx delayed_run_work and run_work
  nbd: fix use after free on module unload
  MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
  blk-mq-sched: alloate reserved tags out of normal pool
  mtip32xx: use runtime tag to initialize command header
  scsi: Implement blk_mq_ops.show_rq()
  blk-mq: Add blk_mq_ops.show_rq()
  blk-mq: Show operation, cmd_flags and rq_flags names
  blk-mq: Make blk_flags_show() callers append a newline character
  blk-mq: Move the "state" debugfs attribute one level down
  blk-mq: Unregister debugfs attributes earlier
  blk-mq: Only unregister hctxs for which registration succeeded
  blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
  blk-mq: Let blk_mq_debugfs_register() look up the queue name
  blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
  ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
  ide-pm: always pass 0 error to __blk_end_request_all
  ..

1 files changed, 48 insertions, 55 deletions

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index c974a1bbf4cb..8b361e192e8a 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -30,43 +30,6 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
 
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
-				int (*init)(struct blk_mq_hw_ctx *),
-				void (*exit)(struct blk_mq_hw_ctx *))
-{
-	struct blk_mq_hw_ctx *hctx;
-	int ret;
-	int i;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
-		if (!hctx->sched_data) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (init) {
-			ret = init(hctx);
-			if (ret) {
-				/*
-				 * We don't want to give exit() a partially
-				 * initialized sched_data. init() must clean up
-				 * if it fails.
-				 */
-				kfree(hctx->sched_data);
-				hctx->sched_data = NULL;
-				goto error;
-			}
-		}
-	}
-
-	return 0;
-error:
-	blk_mq_sched_free_hctx_data(q, exit);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
-
 static void __blk_mq_sched_assign_ioc(struct request_queue *q,
 				      struct request *rq,
 				      struct bio *bio,
@@ -119,7 +82,11 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 
-	if (e) {
+	/*
+	 * For a reserved tag, allocate a normal request since we might
+	 * have driver dependencies on the value of the internal tag.
+	 */
+	if (e && !(data->flags & BLK_MQ_REQ_RESERVED)) {
 		data->flags |= BLK_MQ_REQ_INTERNAL;
 
 		/*
@@ -227,22 +194,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	}
 }
 
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
-				   struct list_head *rq_list,
-				   struct request *(*get_rq)(struct blk_mq_hw_ctx *))
-{
-	do {
-		struct request *rq;
-
-		rq = get_rq(hctx);
-		if (!rq)
-			break;
-
-		list_add_tail(&rq->queuelist, rq_list);
-	} while (1);
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
-
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 			    struct request **merged_request)
 {
@@ -508,11 +459,24 @@ int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 			   unsigned int hctx_idx)
 {
 	struct elevator_queue *e = q->elevator;
+	int ret;
 
 	if (!e)
 		return 0;
 
-	return blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+	ret = blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+	if (ret)
+		return ret;
+
+	if (e->type->ops.mq.init_hctx) {
+		ret = e->type->ops.mq.init_hctx(hctx, hctx_idx);
+		if (ret) {
+			blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+			return ret;
+		}
+	}
+
+	return 0;
 }
 
 void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
@@ -523,12 +487,18 @@ void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 	if (!e)
 		return;
 
+	if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
+		e->type->ops.mq.exit_hctx(hctx, hctx_idx);
+		hctx->sched_data = NULL;
+	}
+
 	blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
 }
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 {
 	struct blk_mq_hw_ctx *hctx;
+	struct elevator_queue *eq;
 	unsigned int i;
 	int ret;
 
@@ -553,6 +523,18 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	if (ret)
 		goto err;
 
+	if (e->ops.mq.init_hctx) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			ret = e->ops.mq.init_hctx(hctx, i);
+			if (ret) {
+				eq = q->elevator;
+				blk_mq_exit_sched(q, eq);
+				kobject_put(&eq->kobj);
+				return ret;
+			}
+		}
+	}
+
 	return 0;
 
 err:
@@ -563,6 +545,17 @@ err:
 
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 {
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	if (e->type->ops.mq.exit_hctx) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			if (hctx->sched_data) {
+				e->type->ops.mq.exit_hctx(hctx, i);
+				hctx->sched_data = NULL;
+			}
+		}
+	}
 	if (e->type->ops.mq.exit_sched)
 		e->type->ops.mq.exit_sched(e);
 	blk_mq_sched_tags_teardown(q);