Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

1 files changed, 131 insertions, 72 deletions

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 4ab69435708c..c117bd8fd1f6 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -81,20 +81,103 @@ static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	} else
 		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
-	if (blk_mq_hctx_has_pending(hctx)) {
-		blk_mq_run_hw_queue(hctx, true);
-		return true;
-	}
+	return blk_mq_run_hw_queue(hctx, true);
+}
 
-	return false;
+/*
+ * Only SCSI implements .get_budget and .put_budget, and SCSI restarts
+ * its queue by itself in its completion handler, so we don't need to
+ * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
+ */
+static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct elevator_queue *e = q->elevator;
+	LIST_HEAD(rq_list);
+
+	do {
+		struct request *rq;
+
+		if (e->type->ops.mq.has_work &&
+				!e->type->ops.mq.has_work(hctx))
+			break;
+
+		if (!blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		rq = e->type->ops.mq.dispatch_request(hctx);
+		if (!rq) {
+			blk_mq_put_dispatch_budget(hctx);
+			break;
+		}
+
+		/*
+		 * Now this rq owns the budget which has to be released
+		 * if this rq won't be queued to driver via .queue_rq()
+		 * in blk_mq_dispatch_rq_list().
+		 */
+		list_add(&rq->queuelist, &rq_list);
+	} while (blk_mq_dispatch_rq_list(q, &rq_list, true));
 }
 
+static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
+					  struct blk_mq_ctx *ctx)
+{
+	unsigned idx = ctx->index_hw;
+
+	if (++idx == hctx->nr_ctx)
+		idx = 0;
+
+	return hctx->ctxs[idx];
+}
+
+/*
+ * Only SCSI implements .get_budget and .put_budget, and SCSI restarts
+ * its queue by itself in its completion handler, so we don't need to
+ * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
+ */
+static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	LIST_HEAD(rq_list);
+	struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from);
+
+	do {
+		struct request *rq;
+
+		if (!sbitmap_any_bit_set(&hctx->ctx_map))
+			break;
+
+		if (!blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		rq = blk_mq_dequeue_from_ctx(hctx, ctx);
+		if (!rq) {
+			blk_mq_put_dispatch_budget(hctx);
+			break;
+		}
+
+		/*
+		 * Now this rq owns the budget which has to be released
+		 * if this rq won't be queued to driver via .queue_rq()
+		 * in blk_mq_dispatch_rq_list().
+		 */
+		list_add(&rq->queuelist, &rq_list);
+
+		/* round robin for fair dispatch */
+		ctx = blk_mq_next_ctx(hctx, rq->mq_ctx);
+
+	} while (blk_mq_dispatch_rq_list(q, &rq_list, true));
+
+	WRITE_ONCE(hctx->dispatch_from, ctx);
+}
+
+/* return true if hw queue need to be run again */
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
 	struct elevator_queue *e = q->elevator;
 	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
-	bool did_work = false;
 	LIST_HEAD(rq_list);
 
 	/* RCU or SRCU read lock is needed before checking quiesced flag */
@@ -122,29 +205,34 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 * scheduler, we can no longer merge or sort them. So it's best to
 	 * leave them there for as long as we can. Mark the hw queue as
 	 * needing a restart in that case.
+	 *
+	 * We want to dispatch from the scheduler if there was nothing
+	 * on the dispatch list or we were able to dispatch from the
+	 * dispatch list.
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
-		did_work = blk_mq_dispatch_rq_list(q, &rq_list);
-	} else if (!has_sched_dispatch) {
+		if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {
+			if (has_sched_dispatch)
+				blk_mq_do_dispatch_sched(hctx);
+			else
+				blk_mq_do_dispatch_ctx(hctx);
+		}
+	} else if (has_sched_dispatch) {
+		blk_mq_do_dispatch_sched(hctx);
+	} else if (q->mq_ops->get_budget) {
+		/*
+		 * If we need to get budget before queuing request, we
+		 * dequeue request one by one from sw queue for avoiding
+		 * to mess up I/O merge when dispatch runs out of resource.
+		 *
+		 * TODO: get more budgets, and dequeue more requests in
+		 * one time.
+		 */
+		blk_mq_do_dispatch_ctx(hctx);
+	} else {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
-		blk_mq_dispatch_rq_list(q, &rq_list);
-	}
-
-	/*
-	 * We want to dispatch from the scheduler if we had no work left
-	 * on the dispatch list, OR if we did have work but weren't able
-	 * to make progress.
-	 */
-	if (!did_work && has_sched_dispatch) {
-		do {
-			struct request *rq;
-
-			rq = e->type->ops.mq.dispatch_request(hctx);
-			if (!rq)
-				break;
-			list_add(&rq->queuelist, &rq_list);
-		} while (blk_mq_dispatch_rq_list(q, &rq_list));
+		blk_mq_dispatch_rq_list(q, &rq_list, false);
 	}
 }
 
@@ -260,21 +348,21 @@ void blk_mq_sched_request_inserted(struct request *rq)
 EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
 
 static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
+				       bool has_sched,
 				       struct request *rq)
 {
-	if (rq->tag == -1) {
-		rq->rq_flags |= RQF_SORTED;
-		return false;
+	/* dispatch flush rq directly */
+	if (rq->rq_flags & RQF_FLUSH_SEQ) {
+		spin_lock(&hctx->lock);
+		list_add(&rq->queuelist, &hctx->dispatch);
+		spin_unlock(&hctx->lock);
+		return true;
 	}
 
-	/*
-	 * If we already have a real request tag, send directly to
-	 * the dispatch list.
-	 */
-	spin_lock(&hctx->lock);
-	list_add(&rq->queuelist, &hctx->dispatch);
-	spin_unlock(&hctx->lock);
-	return true;
+	if (has_sched)
+		rq->rq_flags |= RQF_SORTED;
+
+	return false;
 }
 
 /**
@@ -339,21 +427,6 @@ done:
 	}
 }
 
-/*
- * Add flush/fua to the queue. If we fail getting a driver tag, then
- * punt to the requeue list. Requeue will re-invoke us from a context
- * that's safe to block from.
- */
-static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx,
-				      struct request *rq, bool can_block)
-{
-	if (blk_mq_get_driver_tag(rq, &hctx, can_block)) {
-		blk_insert_flush(rq);
-		blk_mq_run_hw_queue(hctx, true);
-	} else
-		blk_mq_add_to_requeue_list(rq, false, true);
-}
-
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 				 bool run_queue, bool async, bool can_block)
 {
@@ -362,12 +435,15 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
 
-	if (rq->tag == -1 && op_is_flush(rq->cmd_flags)) {
-		blk_mq_sched_insert_flush(hctx, rq, can_block);
-		return;
+	/* flush rq in flush machinery need to be dispatched directly */
+	if (!(rq->rq_flags & RQF_FLUSH_SEQ) && op_is_flush(rq->cmd_flags)) {
+		blk_insert_flush(rq);
+		goto run;
 	}
 
-	if (e && blk_mq_sched_bypass_insert(hctx, rq))
+	WARN_ON(e && (rq->tag != -1));
+
+	if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
 		goto run;
 
 	if (e && e->type->ops.mq.insert_requests) {
@@ -393,23 +469,6 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
 	struct elevator_queue *e = hctx->queue->elevator;
 
-	if (e) {
-		struct request *rq, *next;
-
-		/*
-		 * We bypass requests that already have a driver tag assigned,
-		 * which should only be flushes. Flushes are only ever inserted
-		 * as single requests, so we shouldn't ever hit the
-		 * WARN_ON_ONCE() below (but let's handle it just in case).
-		 */
-		list_for_each_entry_safe(rq, next, list, queuelist) {
-			if (WARN_ON_ONCE(rq->tag != -1)) {
-				list_del_init(&rq->queuelist);
-				blk_mq_sched_bypass_insert(hctx, rq);
-			}
-		}
-	}
-
 	if (e && e->type->ops.mq.insert_requests)
 		e->type->ops.mq.insert_requests(hctx, list, false);
 	else