Merge tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Christoph:
      - Small improvements to the logging functionality (Amit Engel)
      - Authentication cleanups (Hannes Reinecke)
      - Cleanup and optimize the DMA mapping cod in the PCIe driver
        (Keith Busch)
      - Work around the command effects for Format NVM (Keith Busch)
      - Misc cleanups (Keith Busch, Christoph Hellwig)
      - Fix and cleanup freeing single sgl (Keith Busch)

 - MD updates via Song:
      - Fix a rare crash during the takeover process
      - Don't update recovery_cp when curr_resync is ACTIVE
      - Free writes_pending in md_stop
      - Change active_io to percpu

 - Updates to drbd, inching us closer to unifying the out-of-tree driver
   with the in-tree one (Andreas, Christoph, Lars, Robert)

 - BFQ update adding support for multi-actuator drives (Paolo, Federico,
   Davide)

 - Make brd compliant with REQ_NOWAIT (me)

 - Fix for IOPOLL and queue entering, fixing stalled IO waiting on
   timeouts (me)

 - Fix for REQ_NOWAIT with multiple bios (me)

 - Fix memory leak in blktrace cleanup (Greg)

 - Clean up sbitmap and fix a potential hang (Kemeng)

 - Clean up some bits in BFQ, and fix a bug in the request injection
   (Kemeng)

 - Clean up the request allocation and issue code, and fix some bugs
   related to that (Kemeng)

 - ublk updates and fixes:
      - Add support for unprivileged ublk (Ming)
      - Improve device deletion handling (Ming)
      - Misc (Liu, Ziyang)

 - s390 dasd fixes (Alexander, Qiheng)

 - Improve utility of request caching and fixes (Anuj, Xiao)

 - zoned cleanups (Pankaj)

 - More constification for kobjs (Thomas)

 - blk-iocost cleanups (Yu)

 - Remove bio splitting from drivers that don't need it (Christoph)

 - Switch blk-cgroups to use struct gendisk. Some of this is now
   incomplete as select late reverts were done. (Christoph)

 - Add bvec initialization helpers, and convert callers to use that
   rather than open-coding it (Christoph)

 - Misc fixes and cleanups (Jinke, Keith, Arnd, Bart, Li, Martin,
   Matthew, Ulf, Zhong)

* tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux: (169 commits)
  brd: use radix_tree_maybe_preload instead of radix_tree_preload
  block: use proper return value from bio_failfast()
  block: bio-integrity: Copy flags when bio_integrity_payload is cloned
  block: Fix io statistics for cgroup in throttle path
  brd: mark as nowait compatible
  brd: check for REQ_NOWAIT and set correct page allocation mask
  brd: return 0/-error from brd_insert_page()
  block: sync mixed merged request's failfast with 1st bio's
  Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"
  Revert "blk-cgroup: pass a gendisk to blkg_lookup"
  Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"
  Revert "blk-cgroup: delay calling blkcg_exit_disk until disk_release"
  Revert "blk-cgroup: move the cgroup information to struct gendisk"
  nvme-pci: remove iod use_sgls
  nvme-pci: fix freeing single sgl
  block: ublk: check IO buffer based on flag need_get_data
  s390/dasd: Fix potential memleak in dasd_eckd_init()
  s390/dasd: sort out physical vs virtual pointers usage
  block: Remove the ALLOC_CACHE_SLACK constant
  block: make kobj_type structures constant
  ...

1 files changed, 69 insertions, 83 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9c8dc70020bc..d3494a796ba8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -658,7 +658,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	 * allocator for this for the rare use case of a command tied to
 	 * a specific queue.
 	 */
-	if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED))))
+	if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) ||
+	    WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED)))
 		return ERR_PTR(-EINVAL);
 
 	if (hctx_idx >= q->nr_hw_queues)
@@ -1825,12 +1826,13 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
+	struct sbitmap_queue *sbq;
 	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
+	    !(blk_mq_is_shared_tags(hctx->flags))) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 
 		/*
@@ -1848,6 +1850,10 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
+	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag))
+		sbq = &hctx->tags->breserved_tags;
+	else
+		sbq = &hctx->tags->bitmap_tags;
 	wq = &bt_wait_ptr(sbq, hctx)->wait;
 
 	spin_lock_irq(&wq->lock);
@@ -1917,16 +1923,6 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
 static void blk_mq_handle_dev_resource(struct request *rq,
 				       struct list_head *list)
 {
-	struct request *next =
-		list_first_entry_or_null(list, struct request, queuelist);
-
-	/*
-	 * If an I/O scheduler has been configured and we got a driver tag for
-	 * the next request already, free it.
-	 */
-	if (next)
-		blk_mq_put_driver_tag(next);
-
 	list_add(&rq->queuelist, list);
 	__blk_mq_requeue_request(rq);
 }
@@ -2002,6 +1998,23 @@ static void blk_mq_release_budgets(struct request_queue *q,
 }
 
 /*
+ * blk_mq_commit_rqs will notify driver using bd->last that there is no
+ * more requests. (See comment in struct blk_mq_ops for commit_rqs for
+ * details)
+ * Attention, we should explicitly call this in unusual cases:
+ *  1) did not queue everything initially scheduled to queue
+ *  2) the last attempt to queue a request failed
+ */
+static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued,
+			      bool from_schedule)
+{
+	if (hctx->queue->mq_ops->commit_rqs && queued) {
+		trace_block_unplug(hctx->queue, queued, !from_schedule);
+		hctx->queue->mq_ops->commit_rqs(hctx);
+	}
+}
+
+/*
  * Returns true if we did some work AND can potentially do more.
  */
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
@@ -2009,8 +2022,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 {
 	enum prep_dispatch prep;
 	struct request_queue *q = hctx->queue;
-	struct request *rq, *nxt;
-	int errors, queued;
+	struct request *rq;
+	int queued;
 	blk_status_t ret = BLK_STS_OK;
 	LIST_HEAD(zone_list);
 	bool needs_resource = false;
@@ -2021,7 +2034,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	/*
 	 * Now process all the entries, sending them to the driver.
 	 */
-	errors = queued = 0;
+	queued = 0;
 	do {
 		struct blk_mq_queue_data bd;
 
@@ -2035,17 +2048,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
-
-		/*
-		 * Flag last if we have no more requests, or if we have more
-		 * but can't assign a driver tag to it.
-		 */
-		if (list_empty(list))
-			bd.last = true;
-		else {
-			nxt = list_first_entry(list, struct request, queuelist);
-			bd.last = !blk_mq_get_driver_tag(nxt);
-		}
+		bd.last = list_empty(list);
 
 		/*
 		 * once the request is queued to lld, no need to cover the
@@ -2074,7 +2077,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			needs_resource = true;
 			break;
 		default:
-			errors++;
 			blk_mq_end_request(rq, ret);
 		}
 	} while (!list_empty(list));
@@ -2085,9 +2087,9 @@ out:
 	/* 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.
 	 */
-	if ((!list_empty(list) || errors || needs_resource ||
-	     ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued)
-		q->mq_ops->commit_rqs(hctx);
+	if (!list_empty(list) || ret != BLK_STS_OK)
+		blk_mq_commit_rqs(hctx, queued, false);
+
 	/*
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
 	 * that is where we will continue on next queue run.
@@ -2096,7 +2098,8 @@ out:
 		bool needs_restart;
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
-			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
+			((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) ||
+			blk_mq_is_shared_tags(hctx->flags));
 
 		if (nr_budgets)
 			blk_mq_release_budgets(q, list);
@@ -2151,10 +2154,10 @@ out:
 
 		blk_mq_update_dispatch_busy(hctx, true);
 		return false;
-	} else
-		blk_mq_update_dispatch_busy(hctx, false);
+	}
 
-	return (queued + errors) != 0;
+	blk_mq_update_dispatch_busy(hctx, false);
+	return true;
 }
 
 /**
@@ -2548,16 +2551,6 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	spin_unlock(&ctx->lock);
 }
 
-static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int *queued,
-			      bool from_schedule)
-{
-	if (hctx->queue->mq_ops->commit_rqs) {
-		trace_block_unplug(hctx->queue, *queued, !from_schedule);
-		hctx->queue->mq_ops->commit_rqs(hctx);
-	}
-	*queued = 0;
-}
-
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 		unsigned int nr_segs)
 {
@@ -2681,20 +2674,21 @@ static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 	return __blk_mq_try_issue_directly(rq->mq_hctx, rq, true, last);
 }
 
-static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule)
+static void blk_mq_plug_issue_direct(struct blk_plug *plug)
 {
 	struct blk_mq_hw_ctx *hctx = NULL;
 	struct request *rq;
 	int queued = 0;
-	int errors = 0;
+	blk_status_t ret = BLK_STS_OK;
 
 	while ((rq = rq_list_pop(&plug->mq_list))) {
 		bool last = rq_list_empty(plug->mq_list);
-		blk_status_t ret;
 
 		if (hctx != rq->mq_hctx) {
-			if (hctx)
-				blk_mq_commit_rqs(hctx, &queued, from_schedule);
+			if (hctx) {
+				blk_mq_commit_rqs(hctx, queued, false);
+				queued = 0;
+			}
 			hctx = rq->mq_hctx;
 		}
 
@@ -2706,21 +2700,16 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule)
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_request_bypass_insert(rq, false, true);
-			blk_mq_commit_rqs(hctx, &queued, from_schedule);
-			return;
+			goto out;
 		default:
 			blk_mq_end_request(rq, ret);
-			errors++;
 			break;
 		}
 	}
 
-	/*
-	 * 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.
-	 */
-	if (errors)
-		blk_mq_commit_rqs(hctx, &queued, from_schedule);
+out:
+	if (ret != BLK_STS_OK)
+		blk_mq_commit_rqs(hctx, queued, false);
 }
 
 static void __blk_mq_flush_plug_list(struct request_queue *q,
@@ -2791,7 +2780,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		}
 
 		blk_mq_run_dispatch_ops(q,
-				blk_mq_plug_issue_direct(plug, false));
+				blk_mq_plug_issue_direct(plug));
 		if (rq_list_empty(plug->mq_list))
 			return;
 	}
@@ -2805,36 +2794,32 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
 	int queued = 0;
-	int errors = 0;
+	blk_status_t ret = BLK_STS_OK;
 
 	while (!list_empty(list)) {
-		blk_status_t ret;
 		struct request *rq = list_first_entry(list, struct request,
 				queuelist);
 
 		list_del_init(&rq->queuelist);
 		ret = blk_mq_request_issue_directly(rq, list_empty(list));
-		if (ret != BLK_STS_OK) {
-			errors++;
-			if (ret == BLK_STS_RESOURCE ||
-					ret == BLK_STS_DEV_RESOURCE) {
-				blk_mq_request_bypass_insert(rq, false,
-							list_empty(list));
-				break;
-			}
-			blk_mq_end_request(rq, ret);
-		} else
+		switch (ret) {
+		case BLK_STS_OK:
 			queued++;
+			break;
+		case BLK_STS_RESOURCE:
+		case BLK_STS_DEV_RESOURCE:
+			blk_mq_request_bypass_insert(rq, false,
+						     list_empty(list));
+			goto out;
+		default:
+			blk_mq_end_request(rq, ret);
+			break;
+		}
 	}
 
-	/*
-	 * 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.
-	 */
-	if ((!list_empty(list) || errors) &&
-	     hctx->queue->mq_ops->commit_rqs && queued)
-		hctx->queue->mq_ops->commit_rqs(hctx);
+out:
+	if (ret != BLK_STS_OK)
+		blk_mq_commit_rqs(hctx, queued, false);
 }
 
 static bool blk_mq_attempt_bio_merge(struct request_queue *q,
@@ -2894,15 +2879,16 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 
 	if (!plug)
 		return NULL;
-	rq = rq_list_peek(&plug->cached_rq);
-	if (!rq || rq->q != q)
-		return NULL;
 
 	if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) {
 		*bio = NULL;
 		return NULL;
 	}
 
+	rq = rq_list_peek(&plug->cached_rq);
+	if (!rq || rq->q != q)
+		return NULL;
+
 	type = blk_mq_get_hctx_type((*bio)->bi_opf);
 	hctx_type = rq->mq_hctx->type;
 	if (type != hctx_type &&