Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round for this release. This contains:

   - Add support for zoned storage to ublk (Andreas, Ming)

   - Series improving performance for drivers that mark themselves as
     needing a blocking context for issue (Bart)

   - Cleanup the flush logic (Chengming)

   - sed opal keyring support (Greg)

   - Fixes and improvements to the integrity support (Jinyoung)

   - Add some exports for bcachefs that we can hopefully delete again in
     the future (Kent)

   - deadline throttling fix (Zhiguo)

   - Series allowing building the kernel without buffer_head support
     (Christoph)

   - Sanitize the bio page adding flow (Christoph)

   - Write back cache fixes (Christoph)

   - MD updates via Song:
      - Fix perf regression for raid0 large sequential writes (Jan)
      - Fix split bio iostat for raid0 (David)
      - Various raid1 fixes (Heinz, Xueshi)
      - raid6test build fixes (WANG)
      - Deprecate bitmap file support (Christoph)
      - Fix deadlock with md sync thread (Yu)
      - Refactor md io accounting (Yu)
      - Various non-urgent fixes (Li, Yu, Jack)

   - Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li,
     Ming, Nitesh, Ruan, Tejun, Thomas, Xu)"

* tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits)
  block: use strscpy() to instead of strncpy()
  block: sed-opal: keyring support for SED keys
  block: sed-opal: Implement IOC_OPAL_REVERT_LSP
  block: sed-opal: Implement IOC_OPAL_DISCOVERY
  blk-mq: prealloc tags when increase tagset nr_hw_queues
  blk-mq: delete redundant tagset map update when fallback
  blk-mq: fix tags leak when shrink nr_hw_queues
  ublk: zoned: support REQ_OP_ZONE_RESET_ALL
  md: raid0: account for split bio in iostat accounting
  md/raid0: Fix performance regression for large sequential writes
  md/raid0: Factor out helper for mapping and submitting a bio
  md raid1: allow writebehind to work on any leg device set WriteMostly
  md/raid1: hold the barrier until handle_read_error() finishes
  md/raid1: free the r1bio before waiting for blocked rdev
  md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io()
  blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
  drivers/rnbd: restore sysfs interface to rnbd-client
  md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
  raid6: test: only check for Altivec if building on powerpc hosts
  raid6: test: make sure all intermediate and artifact files are .gitignored
  ...

1 files changed, 31 insertions, 14 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 953f08354c8c..ec922c6bccbe 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -43,6 +43,7 @@
 #include "blk-ioprio.h"
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
+static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
 
 static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
 static void blk_mq_request_bypass_insert(struct request *rq,
@@ -1174,15 +1175,11 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 
 static void blk_mq_complete_send_ipi(struct request *rq)
 {
-	struct llist_head *list;
 	unsigned int cpu;
 
 	cpu = rq->mq_ctx->cpu;
-	list = &per_cpu(blk_cpu_done, cpu);
-	if (llist_add(&rq->ipi_list, list)) {
-		INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq);
-		smp_call_function_single_async(cpu, &rq->csd);
-	}
+	if (llist_add(&rq->ipi_list, &per_cpu(blk_cpu_done, cpu)))
+		smp_call_function_single_async(cpu, &per_cpu(blk_cpu_csd, cpu));
 }
 
 static void blk_mq_raise_softirq(struct request *rq)
@@ -1343,7 +1340,7 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 	}
 
 	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
-	blk_mq_run_hw_queue(hctx, false);
+	blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 
@@ -2242,6 +2239,8 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 	 */
 	WARN_ON_ONCE(!async && in_interrupt());
 
+	might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
+
 	/*
 	 * When queue is quiesced, we may be switching io scheduler, or
 	 * updating nr_hw_queues, or other things, and we can't run queue
@@ -2257,8 +2256,7 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 	if (!need_run)
 		return;
 
-	if (async || (hctx->flags & BLK_MQ_F_BLOCKING) ||
-	    !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
+	if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
 		blk_mq_delay_run_hw_queue(hctx, 0);
 		return;
 	}
@@ -2393,7 +2391,7 @@ void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
 
-	blk_mq_run_hw_queue(hctx, false);
+	blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING);
 }
 EXPORT_SYMBOL(blk_mq_start_hw_queue);
 
@@ -2423,7 +2421,8 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
 	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_start_stopped_hw_queue(hctx, async);
+		blk_mq_start_stopped_hw_queue(hctx, async ||
+					(hctx->flags & BLK_MQ_F_BLOCKING));
 }
 EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
 
@@ -2481,6 +2480,8 @@ static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx,
 	list_for_each_entry(rq, list, queuelist) {
 		BUG_ON(rq->mq_ctx != ctx);
 		trace_block_rq_insert(rq);
+		if (rq->cmd_flags & REQ_NOWAIT)
+			run_queue_async = true;
 	}
 
 	spin_lock(&ctx->lock);
@@ -2641,7 +2642,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) {
 		blk_mq_insert_request(rq, 0);
-		blk_mq_run_hw_queue(hctx, false);
+		blk_mq_run_hw_queue(hctx, rq->cmd_flags & REQ_NOWAIT);
 		return;
 	}
 
@@ -4402,9 +4403,13 @@ static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
 				       int new_nr_hw_queues)
 {
 	struct blk_mq_tags **new_tags;
+	int i;
 
-	if (set->nr_hw_queues >= new_nr_hw_queues)
+	if (set->nr_hw_queues >= new_nr_hw_queues) {
+		for (i = new_nr_hw_queues; i < set->nr_hw_queues; i++)
+			__blk_mq_free_map_and_rqs(set, i);
 		goto done;
+	}
 
 	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
 				GFP_KERNEL, set->numa_node);
@@ -4416,6 +4421,16 @@ static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
 		       sizeof(*set->tags));
 	kfree(set->tags);
 	set->tags = new_tags;
+
+	for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) {
+		if (!__blk_mq_alloc_map_and_rqs(set, i)) {
+			while (--i >= set->nr_hw_queues)
+				__blk_mq_free_map_and_rqs(set, i);
+			return -ENOMEM;
+		}
+		cond_resched();
+	}
+
 done:
 	set->nr_hw_queues = new_nr_hw_queues;
 	return 0;
@@ -4749,7 +4764,6 @@ fallback:
 				__blk_mq_free_map_and_rqs(set, i);
 
 			set->nr_hw_queues = prev_nr_hw_queues;
-			blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
 			goto fallback;
 		}
 		blk_mq_map_swqueue(q);
@@ -4853,6 +4867,9 @@ static int __init blk_mq_init(void)
 
 	for_each_possible_cpu(i)
 		init_llist_head(&per_cpu(blk_cpu_done, i));
+	for_each_possible_cpu(i)
+		INIT_CSD(&per_cpu(blk_cpu_csd, i),
+			 __blk_mq_complete_request_remote, NULL);
 	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
 
 	cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,