Linux block layer
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Hannes Reinecke <hare@suse.com>,
	James Smart <james.smart@broadcom.com>,
	Ming Lei <ming.lei@redhat.com>,
	Dongli Zhang <dongli.zhang@oracle.com>,
	Bart Van Assche <bart.vanassche@wdc.com>,
	linux-scsi@vger.kernel.org,
	"Martin K . Petersen" <martin.petersen@oracle.com>,
	Christoph Hellwig <hch@lst.de>,
	"James E . J . Bottomley" <jejb@linux.vnet.ibm.com>
Subject: [PATCH V9 4/7] blk-mq: split blk_mq_alloc_and_init_hctx into two parts
Date: Tue, 30 Apr 2019 09:52:26 +0800	[thread overview]
Message-ID: <20190430015229.23141-5-ming.lei@redhat.com> (raw)
In-Reply-To: <20190430015229.23141-1-ming.lei@redhat.com>

Split blk_mq_alloc_and_init_hctx into two parts, and one is
blk_mq_alloc_hctx() for allocating all hctx resources, another
is blk_mq_init_hctx() for initializing hctx, which serves as
counter-part of blk_mq_exit_hctx().

Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: James Smart <james.smart@broadcom.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: linux-scsi@vger.kernel.org
Cc: Martin K . Petersen <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq.c | 139 +++++++++++++++++++++++++++++++--------------------------
 1 file changed, 75 insertions(+), 64 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d98cb9614dfa..11efca3534ad 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2284,15 +2284,65 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
+			   __alignof__(struct blk_mq_hw_ctx)) !=
+		     sizeof(struct blk_mq_hw_ctx));
+
+	if (tag_set->flags & BLK_MQ_F_BLOCKING)
+		hw_ctx_size += sizeof(struct srcu_struct);
+
+	return hw_ctx_size;
+}
+
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
-	int node;
+	hctx->queue_num = hctx_idx;
+
+	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
+
+	hctx->tags = set->tags[hctx_idx];
+
+	if (set->ops->init_hctx &&
+	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
+		goto unregister_cpu_notifier;
 
-	node = hctx->numa_node;
+	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
+				hctx->numa_node))
+		goto exit_hctx;
+	return 0;
+
+ exit_hctx:
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+ unregister_cpu_notifier:
+	blk_mq_remove_cpuhp(hctx);
+	return -1;
+}
+
+static struct blk_mq_hw_ctx *
+blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
+		int node)
+{
+	struct blk_mq_hw_ctx *hctx;
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
+
+	hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node);
+	if (!hctx)
+		goto fail_alloc_hctx;
+
+	if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node))
+		goto free_hctx;
+
+	atomic_set(&hctx->nr_active, 0);
 	if (node == NUMA_NO_NODE)
-		node = hctx->numa_node = set->numa_node;
+		node = set->numa_node;
+	hctx->numa_node = node;
 
 	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
@@ -2300,58 +2350,45 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	hctx->queue = q;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
-
-	hctx->tags = set->tags[hctx_idx];
-
 	/*
 	 * Allocate space for all possible cpus to avoid allocation at
 	 * runtime
 	 */
 	hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node);
+			gfp, node);
 	if (!hctx->ctxs)
-		goto unregister_cpu_notifier;
+		goto free_cpumask;
 
 	if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8),
-				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node))
+				gfp, node))
 		goto free_ctxs;
-
 	hctx->nr_ctx = 0;
 
 	spin_lock_init(&hctx->dispatch_wait_lock);
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
-	if (set->ops->init_hctx &&
-	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto free_bitmap;
-
 	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
+			gfp);
 	if (!hctx->fq)
-		goto exit_hctx;
-
-	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
-		goto free_fq;
+		goto free_bitmap;
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
 		init_srcu_struct(hctx->srcu);
+	blk_mq_hctx_kobj_init(hctx);
 
-	return 0;
+	return hctx;
 
- free_fq:
-	blk_free_flush_queue(hctx->fq);
- exit_hctx:
-	if (set->ops->exit_hctx)
-		set->ops->exit_hctx(hctx, hctx_idx);
  free_bitmap:
 	sbitmap_free(&hctx->ctx_map);
  free_ctxs:
 	kfree(hctx->ctxs);
- unregister_cpu_notifier:
-	blk_mq_remove_cpuhp(hctx);
-	return -1;
+ free_cpumask:
+	free_cpumask_var(hctx->cpumask);
+ free_hctx:
+	kfree(hctx);
+ fail_alloc_hctx:
+	return NULL;
 }
 
 static void blk_mq_init_cpu_queues(struct request_queue *q,
@@ -2697,51 +2734,25 @@ struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
 }
 EXPORT_SYMBOL(blk_mq_init_sq_queue);
 
-static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
-{
-	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
-
-	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
-			   __alignof__(struct blk_mq_hw_ctx)) !=
-		     sizeof(struct blk_mq_hw_ctx));
-
-	if (tag_set->flags & BLK_MQ_F_BLOCKING)
-		hw_ctx_size += sizeof(struct srcu_struct);
-
-	return hw_ctx_size;
-}
-
 static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
 		struct blk_mq_tag_set *set, struct request_queue *q,
 		int hctx_idx, int node)
 {
 	struct blk_mq_hw_ctx *hctx;
 
-	hctx = kzalloc_node(blk_mq_hw_ctx_size(set),
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-			node);
+	hctx = blk_mq_alloc_hctx(q, set, node);
 	if (!hctx)
-		return NULL;
-
-	if (!zalloc_cpumask_var_node(&hctx->cpumask,
-				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-				node)) {
-		kfree(hctx);
-		return NULL;
-	}
-
-	atomic_set(&hctx->nr_active, 0);
-	hctx->numa_node = node;
-	hctx->queue_num = hctx_idx;
+		goto fail;
 
-	if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) {
-		free_cpumask_var(hctx->cpumask);
-		kfree(hctx);
-		return NULL;
-	}
-	blk_mq_hctx_kobj_init(hctx);
+	if (blk_mq_init_hctx(q, set, hctx, hctx_idx))
+		goto free_hctx;
 
 	return hctx;
+
+ free_hctx:
+	kobject_put(&hctx->kobj);
+ fail:
+	return NULL;
 }
 
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
-- 
2.9.5


  parent reply	other threads:[~2019-04-30  1:52 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-30  1:52 [PATCH V9 0/7] blk-mq: fix races related with freeing queue Ming Lei
2019-04-30  1:52 ` [PATCH V9 1/7] blk-mq: grab .q_usage_counter when queuing request from plug code path Ming Lei
2019-04-30  2:15   ` Bart Van Assche
2019-04-30  1:52 ` [PATCH V9 2/7] blk-mq: move cancel of requeue_work into blk_mq_release Ming Lei
2019-04-30  1:52 ` [PATCH V9 3/7] blk-mq: free hw queue's resource in hctx's release handler Ming Lei
2019-04-30  1:52 ` Ming Lei [this message]
2019-04-30  1:52 ` [PATCH V9 5/7] blk-mq: always free hctx after request queue is freed Ming Lei
2019-04-30  1:52 ` [PATCH V9 6/7] blk-mq: move cancel of hctx->run_work into blk_mq_hw_sysfs_release Ming Lei
2019-04-30  1:52 ` [PATCH V9 7/7] block: don't drain in-progress dispatch in blk_cleanup_queue() Ming Lei
2019-05-04 13:24 ` [PATCH V9 0/7] blk-mq: fix races related with freeing queue Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190430015229.23141-5-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=bart.vanassche@wdc.com \
    --cc=dongli.zhang@oracle.com \
    --cc=hare@suse.com \
    --cc=hch@lst.de \
    --cc=james.smart@broadcom.com \
    --cc=jejb@linux.vnet.ibm.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox