Merge tag 'block-5.6-2020-02-28' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Passthrough insertion fix (Ming)

 - Kill off some unused arguments (John)

 - blktrace RCU fix (Jan)

 - Dead fields removal for null_blk (Dongli)

 - NVMe polled IO fix (Bijan)

* tag 'block-5.6-2020-02-28' of git://git.kernel.dk/linux-block:
  nvme-pci: Hold cq_poll_lock while completing CQEs
  blk-mq: Remove some unused function arguments
  null_blk: remove unused fields in 'nullb_cmd'
  blktrace: Protect q->blk_trace with RCU
  blk-mq: insert passthrough request into hctx->dispatch directly

block/blk-flush.c

@@ -412,7 +412,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		blk_mq_request_bypass_insert(rq, false);
+		blk_mq_request_bypass_insert(rq, false, false);
 		return;
 	}
 

block/blk-mq-sched.c

@@ -361,13 +361,19 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 				       bool has_sched,
 				       struct request *rq)
 {
-	/* 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);
+	/*
+	 * dispatch flush and passthrough rq directly
+	 *
+	 * passthrough request has to be added to hctx->dispatch directly.
+	 * For some reason, device may be in one situation which can't
+	 * handle FS request, so STS_RESOURCE is always returned and the
+	 * FS request will be added to hctx->dispatch. However passthrough
+	 * request may be required at that time for fixing the problem. If
+	 * passthrough request is added to scheduler queue, there isn't any
+	 * chance to dispatch it given we prioritize requests in hctx->dispatch.
+	 */
+	if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq))
 		return true;
-	}
 
 	if (has_sched)
 		rq->rq_flags |= RQF_SORTED;
@@ -391,8 +397,10 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 
 	WARN_ON(e && (rq->tag != -1));
 
-	if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
+	if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) {
+		blk_mq_request_bypass_insert(rq, at_head, false);
 		goto run;
+	}
 
 	if (e && e->type->ops.insert_requests) {
 		LIST_HEAD(list);

block/blk-mq-tag.c

@@ -183,8 +183,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	return tag + tag_offset;
 }
 
-void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
-		    struct blk_mq_ctx *ctx, unsigned int tag)
+void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
+		    unsigned int tag)
 {
 	if (!blk_mq_tag_is_reserved(tags, tag)) {
 		const int real_tag = tag - tags->nr_reserved_tags;

block/blk-mq-tag.h

@@ -26,8 +26,8 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int r
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
-extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
-			   struct blk_mq_ctx *ctx, unsigned int tag);
+extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
+			   unsigned int tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);

block/blk-mq.c

@@ -477,9 +477,9 @@ static void __blk_mq_free_request(struct request *rq)
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
 	if (rq->tag != -1)
-		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
 	if (sched_tag != -1)
-		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+		blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
 }
@@ -735,7 +735,7 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * merge.
 		 */
 		if (rq->rq_flags & RQF_DONTPREP)
-			blk_mq_request_bypass_insert(rq, false);
+			blk_mq_request_bypass_insert(rq, false, false);
 		else
 			blk_mq_sched_insert_request(rq, true, false, false);
 	}
@@ -1286,7 +1286,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			q->mq_ops->commit_rqs(hctx);
 
 		spin_lock(&hctx->lock);
-		list_splice_init(list, &hctx->dispatch);
+		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
@@ -1677,12 +1677,16 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+				  bool run_queue)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	spin_lock(&hctx->lock);
-	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	if (at_head)
+		list_add(&rq->queuelist, &hctx->dispatch);
+	else
+		list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
 
 	if (run_queue)
@@ -1849,7 +1853,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, run_queue);
+	blk_mq_request_bypass_insert(rq, false, run_queue);
 	return BLK_STS_OK;
 }
 
@@ -1876,7 +1880,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
 	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		blk_mq_request_bypass_insert(rq, true);
+		blk_mq_request_bypass_insert(rq, false, true);
 	else if (ret != BLK_STS_OK)
 		blk_mq_end_request(rq, ret);
 
@@ -1910,7 +1914,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		if (ret != BLK_STS_OK) {
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
-				blk_mq_request_bypass_insert(rq,
+				blk_mq_request_bypass_insert(rq, false,
 							list_empty(list));
 				break;
 			}
@@ -3398,7 +3402,6 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
 }
 
 static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
-				       struct blk_mq_hw_ctx *hctx,
 				       struct request *rq)
 {
 	unsigned long ret = 0;
@@ -3431,7 +3434,6 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
 }
 
 static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
-				     struct blk_mq_hw_ctx *hctx,
 				     struct request *rq)
 {
 	struct hrtimer_sleeper hs;
@@ -3451,7 +3453,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 	if (q->poll_nsec > 0)
 		nsecs = q->poll_nsec;
 	else
-		nsecs = blk_mq_poll_nsecs(q, hctx, rq);
+		nsecs = blk_mq_poll_nsecs(q, rq);
 
 	if (!nsecs)
 		return false;
@@ -3506,7 +3508,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
 			return false;
 	}
 
-	return blk_mq_poll_hybrid_sleep(q, hctx, rq);
+	return blk_mq_poll_hybrid_sleep(q, rq);
 }
 
 /**

block/blk-mq.h

@@ -66,7 +66,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+				  bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 
@@ -199,7 +200,7 @@ static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
 static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 					   struct request *rq)
 {
-	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
+	blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag);
 	rq->tag = -1;
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT) {

drivers/block/null_blk.h

@@ -14,9 +14,6 @@
 #include <linux/fault-inject.h>
 
 struct nullb_cmd {
-	struct list_head list;
-	struct llist_node ll_list;
-	struct __call_single_data csd;
 	struct request *rq;
 	struct bio *bio;
 	unsigned int tag;

drivers/block/null_blk_main.c

@@ -1518,8 +1518,6 @@ static int setup_commands(struct nullb_queue *nq)
 
 	for (i = 0; i < nq->queue_depth; i++) {
 		cmd = &nq->cmds[i];
-		INIT_LIST_HEAD(&cmd->list);
-		cmd->ll_list.next = NULL;
 		cmd->tag = -1U;
 	}
 

drivers/nvme/host/pci.c

@@ -1078,9 +1078,9 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx)
 
 	spin_lock(&nvmeq->cq_poll_lock);
 	found = nvme_process_cq(nvmeq, &start, &end, -1);
+	nvme_complete_cqes(nvmeq, start, end);
 	spin_unlock(&nvmeq->cq_poll_lock);
 
-	nvme_complete_cqes(nvmeq, start, end);
 	return found;
 }
 

include/linux/blkdev.h

@@ -524,7 +524,7 @@ struct request_queue {
 	unsigned int		sg_reserved_size;
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
-	struct blk_trace	*blk_trace;
+	struct blk_trace __rcu	*blk_trace;
 	struct mutex		blk_trace_mutex;
 #endif
 	/*

include/linux/blktrace_api.h

@@ -51,20 +51,28 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f
  **/
 #define blk_add_cgroup_trace_msg(q, cg, fmt, ...)			\
 	do {								\
-		struct blk_trace *bt = (q)->blk_trace;			\
+		struct blk_trace *bt;					\
+									\
+		rcu_read_lock();					\
+		bt = rcu_dereference((q)->blk_trace);			\
 		if (unlikely(bt))					\
 			__trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\
+		rcu_read_unlock();					\
 	} while (0)
 #define blk_add_trace_msg(q, fmt, ...)					\
 	blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__)
 #define BLK_TN_MAX_MSG		128
 
 static inline bool blk_trace_note_message_enabled(struct request_queue *q)
 {
-	struct blk_trace *bt = q->blk_trace;
-	if (likely(!bt))
-		return false;
-	return bt->act_mask & BLK_TC_NOTIFY;
+	struct blk_trace *bt;
+	bool ret;
+
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	ret = bt && (bt->act_mask & BLK_TC_NOTIFY);
+	rcu_read_unlock();
+	return ret;
 }
 
 extern void blk_add_driver_data(struct request_queue *q, struct request *rq,