From: Christoph Hellwig <hch@lst.de>
To: axboe@fb.com, tglx@linutronix.de
Cc: agordeev@redhat.com, keith.busch@intel.com,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH 07/13] blk-mq: only allocate a single mq_map per tag_set
Date: Wed, 14 Sep 2016 16:18:53 +0200 [thread overview]
Message-ID: <1473862739-15032-8-git-send-email-hch@lst.de> (raw)
In-Reply-To: <1473862739-15032-1-git-send-email-hch@lst.de>
The mapping is identical for all queues in a tag_set, so stop wasting
memory for building multiple. Note that for now I've kept the mq_map
pointer in the request_queue, but we'll need to investigate if we can
remove it without suffering too much from the additional pointer chasing.
The same would apply to the mq_ops pointer as well.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-mq.c | 22 ++++++++++++++--------
include/linux/blk-mq.h | 1 +
2 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b29e7b2..15c36c1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1963,7 +1963,6 @@ void blk_mq_release(struct request_queue *q)
kfree(hctx);
}
- kfree(q->mq_map);
q->mq_map = NULL;
kfree(q->queue_hw_ctx);
@@ -2062,9 +2061,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
if (!q->queue_hw_ctx)
goto err_percpu;
- q->mq_map = blk_mq_make_queue_map(set);
- if (!q->mq_map)
- goto err_map;
+ q->mq_map = set->mq_map;
blk_mq_realloc_hw_ctxs(set, q);
if (!q->nr_hw_queues)
@@ -2114,8 +2111,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
return q;
err_hctxs:
- kfree(q->mq_map);
-err_map:
kfree(q->queue_hw_ctx);
err_percpu:
free_percpu(q->queue_ctx);
@@ -2337,14 +2332,22 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
if (!set->tags)
return -ENOMEM;
+ set->mq_map = blk_mq_make_queue_map(set);
+ if (!set->mq_map)
+ goto out_free_tags;
+
if (blk_mq_alloc_rq_maps(set))
- goto enomem;
+ goto out_free_mq_map;
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
-enomem:
+
+out_free_mq_map:
+ kfree(set->mq_map);
+ set->mq_map = NULL;
+out_free_tags:
kfree(set->tags);
set->tags = NULL;
return -ENOMEM;
@@ -2360,6 +2363,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
blk_mq_free_rq_map(set, set->tags[i], i);
}
+ kfree(set->mq_map);
+ set->mq_map = NULL;
+
kfree(set->tags);
set->tags = NULL;
}
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e43bbff..a572227 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -65,6 +65,7 @@ struct blk_mq_hw_ctx {
};
struct blk_mq_tag_set {
+ unsigned int *mq_map;
struct blk_mq_ops *ops;
unsigned int nr_hw_queues;
unsigned int queue_depth; /* max hw supported */
--
2.1.4
next prev parent reply other threads:[~2016-09-14 14:22 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-14 14:18 blk-mq: allow passing in an external queue mapping V3 Christoph Hellwig
2016-09-14 14:18 ` [PATCH 01/13] genirq/msi: Add cpumask allocation to alloc_msi_entry Christoph Hellwig
2016-09-15 19:00 ` [tip:irq/core] " tip-bot for Thomas Gleixner
2016-09-19 7:30 ` [PATCH 01/13] " Alexander Gordeev
2016-09-19 13:50 ` Christoph Hellwig
2016-09-20 7:06 ` Alexander Gordeev
2016-09-20 8:58 ` Thomas Gleixner
2016-09-14 14:18 ` [PATCH 02/13] genirq/affinity: Provide smarter irq spreading infrastructure Christoph Hellwig
2016-09-15 19:01 ` [tip:irq/core] " tip-bot for Thomas Gleixner
2016-09-21 12:29 ` [PATCH 02/13] " Alexander Gordeev
2016-09-22 21:14 ` Thomas Gleixner
2016-09-14 14:18 ` [PATCH 03/13] genirq/msi: Switch to new " Christoph Hellwig
2016-09-15 19:01 ` [tip:irq/core] " tip-bot for Thomas Gleixner
2016-09-21 12:23 ` [PATCH 03/13] " Alexander Gordeev
2016-09-22 8:51 ` Alexander Gordeev
2016-09-14 14:18 ` [PATCH 04/13] genirq/affinity: Remove old irq spread infrastructure Christoph Hellwig
2016-09-15 19:02 ` [tip:irq/core] " tip-bot for Thomas Gleixner
2016-09-14 14:18 ` [PATCH 05/13] pci/msi: Retrieve affinity for a vector Christoph Hellwig
2016-09-15 19:02 ` [tip:irq/core] " tip-bot for Thomas Gleixner
2016-09-14 14:18 ` [PATCH 06/13] blk-mq: don't redistribute hardware queues on a CPU hotplug event Christoph Hellwig
2016-09-14 14:18 ` Christoph Hellwig [this message]
2016-09-14 14:18 ` [PATCH 08/13] blk-mq: remove ->map_queue Christoph Hellwig
2016-09-14 14:18 ` [PATCH 09/13] blk-mq: allow the driver to pass in a queue mapping Christoph Hellwig
2016-09-14 14:18 ` [PATCH 10/13] blk-mq: provide a default queue mapping for PCI device Christoph Hellwig
2016-09-19 7:33 ` Alexander Gordeev
2016-09-19 13:49 ` Christoph Hellwig
2016-09-14 14:18 ` [PATCH 11/13] nvme: switch to use pci_alloc_irq_vectors Christoph Hellwig
2016-09-23 22:21 ` Sagi Grimberg
2016-09-26 15:09 ` Christoph Hellwig
2016-09-14 14:18 ` [PATCH 12/13] nvme: remove the post_scan callout Christoph Hellwig
2016-09-14 14:18 ` [PATCH 13/13] blk-mq: get rid of the cpumask in struct blk_mq_tags Christoph Hellwig
2016-09-15 14:44 ` Christoph Hellwig
2016-09-15 14:46 ` Jens Axboe
2016-09-15 14:40 ` blk-mq: allow passing in an external queue mapping V3 Keith Busch
2016-09-15 14:32 ` Christoph Hellwig
2016-09-15 14:34 ` Jens Axboe
2016-09-15 14:42 ` Christoph Hellwig
2016-09-15 14:44 ` 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=1473862739-15032-8-git-send-email-hch@lst.de \
--to=hch@lst.de \
--cc=agordeev@redhat.com \
--cc=axboe@fb.com \
--cc=keith.busch@intel.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
/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
all inboxes | Powered by JetHome®