From: Akinobu Mita <akinobu.mita@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: Akinobu Mita <akinobu.mita@gmail.com>,
Jens Axboe <axboe@kernel.dk>, Ming Lei <tom.leiming@gmail.com>,
Christoph Hellwig <hch@lst.de>,
Wanpeng Li <wanpeng.li@hotmail.com>
Subject: [PATCH v4 7/7] blk-mq: fix deadlock when reading cpu_list
Date: Sun, 27 Sep 2015 02:09:25 +0900 [thread overview]
Message-ID: <1443287365-4244-8-git-send-email-akinobu.mita@gmail.com> (raw)
In-Reply-To: <1443287365-4244-1-git-send-email-akinobu.mita@gmail.com>
CPU hotplug handling for blk-mq (blk_mq_queue_reinit) acquires
all_q_mutex in blk_mq_queue_reinit_notify() and then removes sysfs
entries by blk_mq_sysfs_unregister(). Removing sysfs entry needs to
be blocked until the active reference of the kernfs_node to be zero.
On the other hand, reading blk_mq_hw_sysfs_cpu sysfs entry (e.g.
/sys/block/nullb0/mq/0/cpu_list) acquires all_q_mutex in
blk_mq_hw_sysfs_cpus_show().
If these happen at the same time, a deadlock can happen. Because one
can wait for the active reference to be zero with holding all_q_mutex,
and the other tries to acquire all_q_mutex with holding the active
reference.
The reason that all_q_mutex is acquired in blk_mq_hw_sysfs_cpus_show()
is to avoid reading an imcomplete hctx->cpumask. Since reading sysfs
entry for blk-mq needs to acquire q->sysfs_lock, we can avoid deadlock
and reading an imcomplete hctx->cpumask by protecting q->sysfs_lock
while hctx->cpumask is being updated.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Ming Lei <tom.leiming@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
---
block/blk-mq-sysfs.c | 4 ----
block/blk-mq.c | 7 +++++++
2 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index ffc2443..9cbbb2a 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -229,8 +229,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
unsigned int i, first = 1;
ssize_t ret = 0;
- blk_mq_disable_hotplug();
-
for_each_cpu(i, hctx->cpumask) {
if (first)
ret += sprintf(ret + page, "%u", i);
@@ -240,8 +238,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
first = 0;
}
- blk_mq_enable_hotplug();
-
ret += sprintf(ret + page, "\n");
return ret;
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c2bb513..d529f05 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1805,6 +1805,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
+ /*
+ * Avoid others reading imcomplete hctx->cpumask through sysfs
+ */
+ mutex_lock(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
@@ -1824,6 +1829,8 @@ static void blk_mq_map_swqueue(struct request_queue *q,
hctx->ctxs[hctx->nr_ctx++] = ctx;
}
+ mutex_unlock(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i) {
struct blk_mq_ctxmap *map = &hctx->ctx_map;
--
1.9.1
next prev parent reply other threads:[~2015-09-26 17:10 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-26 17:09 [PATCH v4 0/7] blk-mq: fix race conditions on cpu hotplug handling Akinobu Mita
2015-09-26 17:09 ` [PATCH v4 1/7] blk-mq: avoid setting hctx->tags->cpumask before allocation Akinobu Mita
2015-09-26 18:12 ` Christoph Hellwig
2015-09-26 17:09 ` [PATCH v4 2/7] blk-mq: fix sysfs registration/unregistration race Akinobu Mita
2015-09-29 6:51 ` Christoph Hellwig
2015-09-26 17:09 ` [PATCH v4 3/7] blk-mq: Fix use after of free q->mq_map Akinobu Mita
2015-09-29 6:52 ` Christoph Hellwig
2015-10-05 23:50 ` Akinobu Mita
2015-10-06 9:43 ` Christoph Hellwig
2015-09-26 17:09 ` [PATCH v4 4/7] blk-mq: fix q->mq_usage_counter access race Akinobu Mita
2015-09-29 6:53 ` Christoph Hellwig
2015-09-26 17:09 ` [PATCH v4 5/7] blk-mq: avoid inserting requests before establishing new mapping Akinobu Mita
2015-09-29 6:54 ` Christoph Hellwig
2015-09-26 17:09 ` [PATCH v4 6/7] blk-mq: fix freeze queue race Akinobu Mita
2015-09-26 17:32 ` Tejun Heo
2015-09-27 13:06 ` Akinobu Mita
2015-09-28 14:48 ` Tejun Heo
2015-09-29 6:55 ` Christoph Hellwig
2015-09-29 15:01 ` Jens Axboe
2015-09-29 15:03 ` Tejun Heo
2015-09-29 21:50 ` Tejun Heo
2015-09-30 10:32 ` Akinobu Mita
2015-09-26 17:09 ` Akinobu Mita [this message]
2015-09-29 6:58 ` [PATCH v4 7/7] blk-mq: fix deadlock when reading cpu_list Christoph Hellwig
2015-09-29 17:31 ` [PATCH v4 0/7] blk-mq: fix race conditions on cpu hotplug handling 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=1443287365-4244-8-git-send-email-akinobu.mita@gmail.com \
--to=akinobu.mita@gmail.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-kernel@vger.kernel.org \
--cc=tom.leiming@gmail.com \
--cc=wanpeng.li@hotmail.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
all inboxes | Powered by JetHome®