block: make blk_poll() take a parameter on whether to spin or not

blk_poll() has always kept spinning until it found an IO. This is
fine for SYNC polling, since we need to find one request we have
pending, but in preparation for ASYNC polling it can be beneficial
to just check if we have any entries available or not.

Existing callers are converted to pass in 'spin == true', to retain
the old behavior.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

8 files changed, 18 insertions, 15 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 03c4202b69bf..9af56dbb84f1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1277,19 +1277,22 @@ EXPORT_SYMBOL(submit_bio);
  * blk_poll - poll for IO completions
  * @q:  the queue
  * @cookie: cookie passed back at IO submission time
+ * @spin: whether to spin for completions
  *
  * Description:
  *    Poll for completions on the passed in queue. Returns number of
- *    completed entries found.
+ *    completed entries found. If @spin is true, then blk_poll will continue
+ *    looping until at least one completion is found, unless the task is
+ *    otherwise marked running (or we need to reschedule).
  */
-int blk_poll(struct request_queue *q, blk_qc_t cookie)
+int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 {
 	if (!q->poll_fn || !blk_qc_t_valid(cookie))
 		return 0;
 
 	if (current->plug)
 		blk_flush_plug_list(current->plug, false);
-	return q->poll_fn(q, cookie);
+	return q->poll_fn(q, cookie, spin);
 }
 EXPORT_SYMBOL_GPL(blk_poll);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b66cca3ce1e5..c2751f0a3ccc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -38,7 +38,7 @@
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
 
-static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
+static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
@@ -3352,7 +3352,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
 	return blk_mq_poll_hybrid_sleep(q, hctx, rq);
 }
 
-static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
+static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 {
 	struct blk_mq_hw_ctx *hctx;
 	long state;
@@ -3392,7 +3392,7 @@ static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 
 		if (current->state == TASK_RUNNING)
 			return 1;
-		if (ret < 0)
+		if (ret < 0 || !spin)
 			break;
 		cpu_relax();
 	}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f9eeb3b58632..ffebdd0ae34b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -220,7 +220,7 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 	return ret;
 }
 
-static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
+static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc, bool spin)
 {
 	struct nvme_ns_head *head = q->queuedata;
 	struct nvme_ns *ns;
@@ -230,7 +230,7 @@ static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = srcu_dereference(head->current_path[numa_node_id()], &head->srcu);
 	if (likely(ns && nvme_path_is_optimized(ns)))
-		found = ns->queue->poll_fn(q, qc);
+		found = ns->queue->poll_fn(q, qc, spin);
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return found;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 64ba27b8b754..d233a59ea364 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -243,7 +243,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 			break;
 
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc))
+		    !blk_poll(bdev_get_queue(bdev), qc, true))
 			io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -423,7 +423,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 			break;
 
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc))
+		    !blk_poll(bdev_get_queue(bdev), qc, true))
 			io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ea07d5a34317..a5a4e5a1423e 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -518,7 +518,7 @@ static struct bio *dio_await_one(struct dio *dio)
 		dio->waiter = current;
 		spin_unlock_irqrestore(&dio->bio_lock, flags);
 		if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(dio->bio_disk->queue, dio->bio_cookie))
+		    !blk_poll(dio->bio_disk->queue, dio->bio_cookie, true))
 			io_schedule();
 		/* wake up sets us TASK_RUNNING */
 		spin_lock_irqsave(&dio->bio_lock, flags);
diff --git a/fs/iomap.c b/fs/iomap.c
index c5df035ace6f..74c1f37f0fd6 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1896,7 +1896,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!(iocb->ki_flags & IOCB_HIPRI) ||
 			    !dio->submit.last_queue ||
 			    !blk_poll(dio->submit.last_queue,
-					 dio->submit.cookie))
+					 dio->submit.cookie, true))
 				io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f3015e9b5ae3..e3c0a8ec16a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -283,7 +283,7 @@ static inline unsigned short req_get_ioprio(struct request *req)
 struct blk_queue_ctx;
 
 typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
-typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t);
+typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t, bool spin);
 
 struct bio_vec;
 typedef int (dma_drain_needed_fn)(struct request *);
@@ -867,7 +867,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
 
-int blk_poll(struct request_queue *q, blk_qc_t cookie);
+int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
diff --git a/mm/page_io.c b/mm/page_io.c
index a7271fa481f6..5bdfd21c1bd9 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -410,7 +410,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!blk_poll(disk->queue, qc))
+		if (!blk_poll(disk->queue, qc, true))
 			break;
 	}
 	__set_current_state(TASK_RUNNING);