block: switch polling to be bio based

Replace the blk_poll interface that requires the caller to keep a queue
and cookie from the submissions with polling based on the bio.

Polling for the bio itself leads to a few advantages:

 - the cookie construction can made entirely private in blk-mq.c
 - the caller does not need to remember the request_queue and cookie
   separately and thus sidesteps their lifetime issues
 - keeping the device and the cookie inside the bio allows to trivially
   support polling BIOs remapping by stacking drivers
 - a lot of code to propagate the cookie back up the submission path can
   be removed entirely.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
Link: https://lore.kernel.org/r/20211012111226.760968-15-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 23 insertions, 49 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a34ffcf861c3..0860f622099f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -65,6 +65,9 @@ static int blk_mq_poll_stats_bkt(const struct request *rq)
 	return bucket;
 }
 
+#define BLK_QC_T_SHIFT		16
+#define BLK_QC_T_INTERNAL	(1U << 31)
+
 static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 		blk_qc_t qc)
 {
@@ -81,6 +84,13 @@ static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
 	return blk_mq_tag_to_rq(hctx->tags, tag);
 }
 
+static inline blk_qc_t blk_rq_to_qc(struct request *rq)
+{
+	return (rq->mq_hctx->queue_num << BLK_QC_T_SHIFT) |
+		(rq->tag != -1 ?
+		 rq->tag : (rq->internal_tag | BLK_QC_T_INTERNAL));
+}
+
 /*
  * Check if any of the ctx, dispatch list or elevator
  * have pending work in this hardware queue.
@@ -819,6 +829,8 @@ void blk_mq_start_request(struct request *rq)
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
 		q->integrity.profile->prepare_fn(rq);
 #endif
+	if (rq->bio && rq->bio->bi_opf & REQ_POLLED)
+	        WRITE_ONCE(rq->bio->bi_cookie, blk_rq_to_qc(rq));
 }
 EXPORT_SYMBOL(blk_mq_start_request);
 
@@ -2045,19 +2057,15 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 }
 
 static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
-					    struct request *rq,
-					    blk_qc_t *cookie, bool last)
+					    struct request *rq, bool last)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.last = last,
 	};
-	blk_qc_t new_cookie;
 	blk_status_t ret;
 
-	new_cookie = request_to_qc_t(hctx, rq);
-
 	/*
 	 * For OK queue, we are done. For error, caller may kill it.
 	 * Any other error (busy), just add it to our list as we
@@ -2067,7 +2075,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	switch (ret) {
 	case BLK_STS_OK:
 		blk_mq_update_dispatch_busy(hctx, false);
-		*cookie = new_cookie;
 		break;
 	case BLK_STS_RESOURCE:
 	case BLK_STS_DEV_RESOURCE:
@@ -2076,7 +2083,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 		break;
 	default:
 		blk_mq_update_dispatch_busy(hctx, false);
-		*cookie = BLK_QC_T_NONE;
 		break;
 	}
 
@@ -2085,7 +2091,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 						struct request *rq,
-						blk_qc_t *cookie,
 						bool bypass_insert, bool last)
 {
 	struct request_queue *q = rq->q;
@@ -2119,7 +2124,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		goto insert;
 	}
 
-	return __blk_mq_issue_directly(hctx, rq, cookie, last);
+	return __blk_mq_issue_directly(hctx, rq, last);
 insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
@@ -2133,7 +2138,6 @@ insert:
  * blk_mq_try_issue_directly - Try to send a request directly to device driver.
  * @hctx: Pointer of the associated hardware queue.
  * @rq: Pointer to request to be sent.
- * @cookie: Request queue cookie.
  *
  * If the device has enough resources to accept a new request now, send the
  * request directly to device driver. Else, insert at hctx->dispatch queue, so
@@ -2141,7 +2145,7 @@ insert:
  * queue have higher priority.
  */
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-		struct request *rq, blk_qc_t *cookie)
+		struct request *rq)
 {
 	blk_status_t ret;
 	int srcu_idx;
@@ -2150,7 +2154,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	hctx_lock(hctx, &srcu_idx);
 
-	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
+	ret = __blk_mq_try_issue_directly(hctx, rq, false, true);
 	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
 		blk_mq_request_bypass_insert(rq, false, true);
 	else if (ret != BLK_STS_OK)
@@ -2163,11 +2167,10 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 {
 	blk_status_t ret;
 	int srcu_idx;
-	blk_qc_t unused_cookie;
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	hctx_lock(hctx, &srcu_idx);
-	ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
+	ret = __blk_mq_try_issue_directly(hctx, rq, true, last);
 	hctx_unlock(hctx, srcu_idx);
 
 	return ret;
@@ -2247,10 +2250,8 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
  *
  * It will not queue the request if there is an error with the bio, or at the
  * request creation.
- *
- * Returns: Request queue cookie.
  */
-blk_qc_t blk_mq_submit_bio(struct bio *bio)
+void blk_mq_submit_bio(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -2259,9 +2260,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	unsigned int nr_segs;
-	blk_qc_t cookie;
 	blk_status_t ret;
-	bool hipri;
 
 	blk_queue_bounce(q, &bio);
 	__blk_queue_split(&bio, &nr_segs);
@@ -2278,8 +2277,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_throttle(q, bio);
 
-	hipri = bio->bi_opf & REQ_POLLED;
-
 	plug = blk_mq_plug(q, bio);
 	if (plug && plug->cached_rq) {
 		rq = plug->cached_rq;
@@ -2310,8 +2307,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_track(q, rq, bio);
 
-	cookie = request_to_qc_t(rq->mq_hctx, rq);
-
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
 	ret = blk_crypto_init_request(rq);
@@ -2319,7 +2314,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		bio->bi_status = ret;
 		bio_endio(bio);
 		blk_mq_free_request(rq);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (unlikely(is_flush_fua)) {
@@ -2375,7 +2370,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		if (same_queue_rq) {
 			trace_block_unplug(q, 1, true);
 			blk_mq_try_issue_directly(same_queue_rq->mq_hctx,
-						  same_queue_rq, &cookie);
+						  same_queue_rq);
 		}
 	} else if ((q->nr_hw_queues > 1 && is_sync) ||
 		   !rq->mq_hctx->dispatch_busy) {
@@ -2383,18 +2378,15 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		 * There is no scheduler and we can try to send directly
 		 * to the hardware.
 		 */
-		blk_mq_try_issue_directly(rq->mq_hctx, rq, &cookie);
+		blk_mq_try_issue_directly(rq->mq_hctx, rq);
 	} else {
 		/* Default case. */
 		blk_mq_sched_insert_request(rq, false, true, true);
 	}
 
-	if (!hipri)
-		return BLK_QC_T_NONE;
-	return cookie;
+	return;
 queue_exit:
 	blk_queue_exit(q);
-	return BLK_QC_T_NONE;
 }
 
 static size_t order_to_size(unsigned int order)
@@ -4084,25 +4076,8 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
 	return 0;
 }
 
-/**
- * blk_poll - poll for IO completions
- * @q:  the queue
- * @cookie: cookie passed back at IO submission time
- * @flags: BLK_POLL_* flags that control the behavior
- *
- * Description:
- *    Poll for completions on the passed in queue. Returns number of
- *    completed entries found.
- */
-int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
 {
-	if (cookie == BLK_QC_T_NONE ||
-	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
-		return 0;
-
-	if (current->plug)
-		blk_flush_plug_list(current->plug, false);
-
 	if (!(flags & BLK_POLL_NOSLEEP) &&
 	    q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
 		if (blk_mq_poll_hybrid(q, cookie))
@@ -4110,7 +4085,6 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
 	}
 	return blk_mq_poll_classic(q, cookie, flags);
 }
-EXPORT_SYMBOL_GPL(blk_poll);
 
 unsigned int blk_mq_rq_cpu(struct request *rq)
 {