6 files changed, 48 insertions, 111 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 853f92749202..bfe16d5af9f9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -693,20 +693,11 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	if (!uninit_q)
 		return NULL;
 
-	uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
-	if (!uninit_q->flush_rq)
-		goto out_cleanup_queue;
-
 	q = blk_init_allocated_queue(uninit_q, rfn, lock);
 	if (!q)
-		goto out_free_flush_rq;
-	return q;
+		blk_cleanup_queue(uninit_q);
 
-out_free_flush_rq:
-	kfree(uninit_q->flush_rq);
-out_cleanup_queue:
-	blk_cleanup_queue(uninit_q);
-	return NULL;
+	return q;
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
@@ -717,9 +708,13 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!q->flush_rq)
 		return NULL;
 
+	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+		goto fail;
+
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -742,12 +737,16 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		return NULL;
+		goto fail;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
 
 	return q;
+
+fail:
+	kfree(q->flush_rq);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index c68613bb4c79..dbf4502b1d67 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be resued after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(q, rq, at_head, true);
+		blk_mq_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 66e2b697f5db..43e6b4755e9a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -137,17 +137,20 @@ static void mq_flush_run(struct work_struct *work)
 	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
-	blk_mq_run_request(rq, true, false);
+	blk_mq_insert_request(rq, false, true, false);
 }
 
-static bool blk_flush_queue_rq(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
 	if (rq->q->mq_ops) {
 		INIT_WORK(&rq->mq_flush_work, mq_flush_run);
 		kblockd_schedule_work(rq->q, &rq->mq_flush_work);
 		return false;
 	} else {
-		list_add_tail(&rq->queuelist, &rq->q->queue_head);
+		if (add_front)
+			list_add(&rq->queuelist, &rq->q->queue_head);
+		else
+			list_add_tail(&rq->queuelist, &rq->q->queue_head);
 		return true;
 	}
 }
@@ -193,7 +196,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		queued = blk_flush_queue_rq(rq);
+		queued = blk_flush_queue_rq(rq, true);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -326,7 +329,7 @@ static bool blk_kick_flush(struct request_queue *q)
 	q->flush_rq->rq_disk = first_rq->rq_disk;
 	q->flush_rq->end_io = flush_end_io;
 
-	return blk_flush_queue_rq(q->flush_rq);
+	return blk_flush_queue_rq(q->flush_rq, false);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
@@ -411,7 +414,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_run_request(rq, false, true);
+			blk_mq_insert_request(rq, false, false, true);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 3146befb56aa..136ef8643bba 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -11,7 +11,7 @@
 #include "blk-mq.h"
 
 static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
 
 static int blk_mq_main_cpu_notify(struct notifier_block *self,
 				  unsigned long action, void *hcpu)
@@ -19,12 +19,12 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
 	unsigned int cpu = (unsigned long) hcpu;
 	struct blk_mq_cpu_notifier *notify;
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 
 	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
 		notify->notify(notify->data, action, cpu);
 
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 	return NOTIFY_OK;
 }
 
@@ -32,16 +32,16 @@ void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
 	BUG_ON(!notifier->notify);
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_del(&notifier->list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1fa9dd153fde..883f72089015 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -73,8 +73,8 @@ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
 		set_bit(ctx->index_hw, hctx->ctx_map);
 }
 
-static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
-				       bool reserved)
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+					      gfp_t gfp, bool reserved)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -193,12 +193,6 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
 }
 
-static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
-					      gfp_t gfp, bool reserved)
-{
-	return blk_mq_alloc_rq(hctx, gfp, reserved);
-}
-
 static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 						   int rw, gfp_t gfp,
 						   bool reserved)
@@ -289,38 +283,10 @@ void blk_mq_free_request(struct request *rq)
 	__blk_mq_free_request(hctx, ctx, rq);
 }
 
-static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
-{
-	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
-
-	if (unlikely(rq->cmd_flags & REQ_QUIET))
-		set_bit(BIO_QUIET, &bio->bi_flags);
-
-	/* don't actually finish bio if it's part of flush sequence */
-	if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
-		bio_endio(bio, error);
-}
-
-void blk_mq_end_io(struct request *rq, int error)
+bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes)
 {
-	struct bio *bio = rq->bio;
-	unsigned int bytes = 0;
-
-	trace_block_rq_complete(rq->q, rq);
-
-	while (bio) {
-		struct bio *next = bio->bi_next;
-
-		bio->bi_next = NULL;
-		bytes += bio->bi_iter.bi_size;
-		blk_mq_bio_endio(rq, bio, error);
-		bio = next;
-	}
-
-	blk_account_io_completion(rq, bytes);
+	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+		return true;
 
 	blk_account_io_done(rq);
 
@@ -328,8 +294,9 @@ void blk_mq_end_io(struct request *rq, int error)
 		rq->end_io(rq, error);
 	else
 		blk_mq_free_request(rq);
+	return false;
 }
-EXPORT_SYMBOL(blk_mq_end_io);
+EXPORT_SYMBOL(blk_mq_end_io_partial);
 
 static void __blk_mq_complete_request_remote(void *data)
 {
@@ -730,60 +697,27 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 	blk_mq_add_timer(rq);
 }
 
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool at_head, bool run_queue)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+		bool async)
 {
+	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
+	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
+
+	current_ctx = blk_mq_get_ctx(q);
+	if (!cpu_online(ctx->cpu))
+		rq->mq_ctx = ctx = current_ctx;
 
-	ctx = rq->mq_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
 		blk_insert_flush(rq);
 	} else {
-		current_ctx = blk_mq_get_ctx(q);
-
-		if (!cpu_online(ctx->cpu)) {
-			ctx = current_ctx;
-			hctx = q->mq_ops->map_queue(q, ctx->cpu);
-			rq->mq_ctx = ctx;
-		}
 		spin_lock(&ctx->lock);
 		__blk_mq_insert_request(hctx, rq, at_head);
 		spin_unlock(&ctx->lock);
-
-		blk_mq_put_ctx(current_ctx);
-	}
-
-	if (run_queue)
-		__blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
-{
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
-
-	current_ctx = blk_mq_get_ctx(q);
-
-	ctx = rq->mq_ctx;
-	if (!cpu_online(ctx->cpu)) {
-		ctx = current_ctx;
-		rq->mq_ctx = ctx;
 	}
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	/* ctx->cpu might be offline */
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, false);
-	spin_unlock(&ctx->lock);
 
 	blk_mq_put_ctx(current_ctx);
 
@@ -926,6 +860,8 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
+	if (is_sync)
+		rw |= REQ_SYNC;
 	trace_block_getrq(q, bio, rw);
 	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
 	if (likely(rq))
diff --git a/block/blk-mq.h b/block/blk-mq.h
index ed0035cd458e..72beba1f9d55 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -23,7 +23,6 @@ struct blk_mq_ctx {
 };
 
 void __blk_mq_complete_request(struct request *rq);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_init_flush(struct request_queue *q);
 void blk_mq_drain_queue(struct request_queue *q);