1 files changed, 107 insertions, 82 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 555ada922cf0..8e01e4b32e10 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -28,6 +28,7 @@
 #include <linux/prefetch.h>
 #include <linux/blk-crypto.h>
 #include <linux/part_stat.h>
+#include <linux/sched/isolation.h>
 
 #include <trace/events/block.h>
 
@@ -690,6 +691,8 @@ static void blk_mq_finish_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	blk_zone_finish_request(rq);
+
 	if (rq->rq_flags & RQF_USE_SCHED) {
 		q->elevator->type->ops.finish_request(rq);
 		/*
@@ -761,36 +764,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
-static void req_bio_endio(struct request *rq, struct bio *bio,
-			  unsigned int nbytes, blk_status_t error)
-{
-	if (unlikely(error)) {
-		bio->bi_status = error;
-	} else if (req_op(rq) == REQ_OP_ZONE_APPEND) {
-		/*
-		 * Partial zone append completions cannot be supported as the
-		 * BIO fragments may end up not being written sequentially.
-		 * For such case, force the completed nbytes to be equal to
-		 * the BIO size so that bio_advance() sets the BIO remaining
-		 * size to 0 and we end up calling bio_endio() before returning.
-		 */
-		if (bio->bi_iter.bi_size != nbytes) {
-			bio->bi_status = BLK_STS_IOERR;
-			nbytes = bio->bi_iter.bi_size;
-		} else {
-			bio->bi_iter.bi_sector = rq->__sector;
-		}
-	}
-
-	bio_advance(bio, nbytes);
-
-	if (unlikely(rq->rq_flags & RQF_QUIET))
-		bio_set_flag(bio, BIO_QUIET);
-	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
-		bio_endio(bio);
-}
-
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {
@@ -850,8 +823,7 @@ static void blk_complete_request(struct request *req)
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 
-		if (req_op(req) == REQ_OP_ZONE_APPEND)
-			bio->bi_iter.bi_sector = req->__sector;
+		blk_zone_update_request_bio(req, bio);
 
 		if (!is_flush)
 			bio_endio(bio);
@@ -894,6 +866,8 @@ static void blk_complete_request(struct request *req)
 bool blk_update_request(struct request *req, blk_status_t error,
 		unsigned int nr_bytes)
 {
+	bool is_flush = req->rq_flags & RQF_FLUSH_SEQ;
+	bool quiet = req->rq_flags & RQF_QUIET;
 	int total_bytes;
 
 	trace_block_rq_complete(req, error, nr_bytes);
@@ -914,9 +888,8 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
 		__blk_crypto_rq_put_keyslot(req);
 
-	if (unlikely(error && !blk_rq_is_passthrough(req) &&
-		     !(req->rq_flags & RQF_QUIET)) &&
-		     !test_bit(GD_DEAD, &req->q->disk->state)) {
+	if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) &&
+	    !test_bit(GD_DEAD, &req->q->disk->state)) {
 		blk_print_req_error(req, error);
 		trace_block_rq_error(req, error, nr_bytes);
 	}
@@ -928,12 +901,33 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size)
+		if (unlikely(error))
+			bio->bi_status = error;
+
+		if (bio_bytes == bio->bi_iter.bi_size) {
 			req->bio = bio->bi_next;
+		} else if (bio_is_zone_append(bio) && error == BLK_STS_OK) {
+			/*
+			 * Partial zone append completions cannot be supported
+			 * as the BIO fragments may end up not being written
+			 * sequentially.
+			 */
+			bio->bi_status = BLK_STS_IOERR;
+		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
-		req_bio_endio(req, bio, bio_bytes, error);
+		if (unlikely(quiet))
+			bio_set_flag(bio, BIO_QUIET);
+
+		bio_advance(bio, bio_bytes);
+
+		/* Don't actually finish bio if it's part of flush sequence */
+		if (!bio->bi_iter.bi_size) {
+			blk_zone_update_request_bio(req, bio);
+			if (!is_flush)
+				bio_endio(bio);
+		}
 
 		total_bytes += bio_bytes;
 		nr_bytes -= bio_bytes;
@@ -1002,6 +996,8 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 		update_io_ticks(req->part, jiffies, true);
 		part_stat_inc(req->part, ios[sgrp]);
 		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -1024,6 +1020,8 @@ static inline void blk_account_io_start(struct request *req)
 
 		part_stat_lock();
 		update_io_ticks(req->part, jiffies, false);
+		part_stat_local_inc(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -1335,11 +1333,6 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 
 	blk_account_io_start(rq);
 
-	/*
-	 * As plugging can be enabled for passthrough requests on a zoned
-	 * device, directly accessing the plug instead of using blk_mq_plug()
-	 * should not have any consequences.
-	 */
 	if (current->plug && !at_head) {
 		blk_add_rq_to_plug(current->plug, rq);
 		return;
@@ -1926,19 +1919,6 @@ static void blk_mq_handle_dev_resource(struct request *rq,
 	__blk_mq_requeue_request(rq);
 }
 
-static void blk_mq_handle_zone_resource(struct request *rq,
-					struct list_head *zone_list)
-{
-	/*
-	 * If we end up here it is because we cannot dispatch a request to a
-	 * specific zone due to LLD level zone-write locking or other zone
-	 * related resource not being available. In this case, set the request
-	 * aside in zone_list for retrying it later.
-	 */
-	list_add(&rq->queuelist, zone_list);
-	__blk_mq_requeue_request(rq);
-}
-
 enum prep_dispatch {
 	PREP_DISPATCH_OK,
 	PREP_DISPATCH_NO_TAG,
@@ -2024,7 +2004,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	struct request *rq;
 	int queued;
 	blk_status_t ret = BLK_STS_OK;
-	LIST_HEAD(zone_list);
 	bool needs_resource = false;
 
 	if (list_empty(list))
@@ -2066,23 +2045,11 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_handle_dev_resource(rq, list);
 			goto out;
-		case BLK_STS_ZONE_RESOURCE:
-			/*
-			 * Move the request to zone_list and keep going through
-			 * the dispatch list to find more requests the drive can
-			 * accept.
-			 */
-			blk_mq_handle_zone_resource(rq, &zone_list);
-			needs_resource = true;
-			break;
 		default:
 			blk_mq_end_request(rq, ret);
 		}
 	} while (!list_empty(list));
 out:
-	if (!list_empty(&zone_list))
-		list_splice_tail_init(&zone_list, list);
-
 	/* If we didn't flush the entire list, we could have told the driver
 	 * there was more coming, but that turned out to be a lie.
 	 */
@@ -2169,6 +2136,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
 }
 
 /*
+ * ->next_cpu is always calculated from hctx->cpumask, so simply use
+ * it for speeding up the check
+ */
+static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)
+{
+        return hctx->next_cpu >= nr_cpu_ids;
+}
+
+/*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.
  * For now we just round-robin here, switching for every
@@ -2179,7 +2155,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 	bool tried = false;
 	int next_cpu = hctx->next_cpu;
 
-	if (hctx->queue->nr_hw_queues == 1)
+	/* Switch to unbound if no allowable CPUs in this hctx */
+	if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
@@ -2953,22 +2930,37 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 void blk_mq_submit_bio(struct bio *bio)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct blk_plug *plug = blk_mq_plug(bio);
+	struct blk_plug *plug = current->plug;
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int nr_segs = 1;
 	struct request *rq;
 	blk_status_t ret;
 
+	/*
+	 * If the plug has a cached request for this queue, try to use it.
+	 */
+	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+
+	/*
+	 * A BIO that was released from a zone write plug has already been
+	 * through the preparation in this function, already holds a reference
+	 * on the queue usage counter, and is the only write BIO in-flight for
+	 * the target zone. Go straight to preparing a request for it.
+	 */
+	if (bio_zone_write_plugging(bio)) {
+		nr_segs = bio->__bi_nr_segments;
+		if (rq)
+			blk_queue_exit(q);
+		goto new_request;
+	}
+
 	bio = blk_queue_bounce(bio, q);
 
 	/*
-	 * If the plug has a cached request for this queue, try use it.
-	 *
 	 * The cached request already holds a q_usage_counter reference and we
 	 * don't have to acquire a new one if we use it.
 	 */
-	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
 	if (!rq) {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
@@ -2985,6 +2977,10 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 		goto queue_exit;
 
+	if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs))
+		goto queue_exit;
+
+new_request:
 	if (!rq) {
 		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
 		if (unlikely(!rq))
@@ -3007,6 +3003,9 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
+	if (bio_zone_write_plugging(bio))
+		blk_zone_write_plug_init_request(rq);
+
 	if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
 		return;
 
@@ -3488,14 +3487,30 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
 	return data.has_rq;
 }
 
-static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
-		struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
+		unsigned int this_cpu)
 {
-	if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu)
-		return false;
-	if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
-		return false;
-	return true;
+	enum hctx_type type = hctx->type;
+	int cpu;
+
+	/*
+	 * hctx->cpumask has to rule out isolated CPUs, but userspace still
+	 * might submit IOs on these isolated CPUs, so use the queue map to
+	 * check if all CPUs mapped to this hctx are offline
+	 */
+	for_each_online_cpu(cpu) {
+		struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,
+				type, cpu);
+
+		if (h != hctx)
+			continue;
+
+		/* this hctx has at least one online CPU */
+		if (this_cpu != cpu)
+			return true;
+	}
+
+	return false;
 }
 
 static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
@@ -3503,8 +3518,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
-	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
-	    !blk_mq_last_cpu_in_hctx(cpu, hctx))
+	if (blk_mq_hctx_has_online_cpu(hctx, cpu))
 		return 0;
 
 	/*
@@ -3912,6 +3926,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
+		int cpu;
+
 		/*
 		 * If no software queues are mapped to this hardware queue,
 		 * disable it and free the request entries.
@@ -3939,6 +3955,15 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
 
 		/*
+		 * Rule out isolated CPUs from hctx->cpumask to avoid
+		 * running block kworker on isolated CPUs
+		 */
+		for_each_cpu(cpu, hctx->cpumask) {
+			if (cpu_is_isolated(cpu))
+				cpumask_clear_cpu(cpu, hctx->cpumask);
+		}
+
+		/*
 		 * Initialize batch roundrobin counts
 		 */
 		hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);