From: John Garry <john.garry@huawei.com>
To: Bart Van Assche <bvanassche@acm.org>, <axboe@kernel.dk>,
<ming.lei@redhat.com>
Cc: <linux-block@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<hch@lst.de>, <hare@suse.de>, <ppvk@codeaurora.org>,
<kashyap.desai@broadcom.com>, <linuxarm@huawei.com>
Subject: Re: [RFC PATCH v2 2/2] blk-mq: Lockout tagset iter when freeing rqs
Date: Fri, 18 Dec 2020 09:30:55 +0000 [thread overview]
Message-ID: <c1e9c7d8-e9ce-b3c5-19f5-22eb3a808c29@huawei.com> (raw)
In-Reply-To: <30c16455-6d7d-39ac-b3fc-4ee38199e683@acm.org>
On 18/12/2020 01:55, Bart Van Assche wrote:
> On 12/17/20 3:07 AM, John Garry wrote:
>> diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
>> index a6df2d5df88a..853ed5b889aa 100644
>> --- a/block/blk-mq-tag.c
>> +++ b/block/blk-mq-tag.c
>> @@ -358,10 +358,19 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
>> {
>> int i;
>>
>> for (i = 0; i < tagset->nr_hw_queues; i++) {
>> - if (tagset->tags && tagset->tags[i])
>> - __blk_mq_all_tag_iter(tagset->tags[i], fn, priv,
>> + if (tagset->tags && tagset->tags[i]) {
>> + struct blk_mq_tags *tags = tagset->tags[i];
>> +
>> + if (!atomic_inc_not_zero(&tags->iter_usage_counter))
>> + continue;
>> +
>> + __blk_mq_all_tag_iter(tags, fn, priv,
>> BT_TAG_ITER_STARTED);
>> +
>> + atomic_dec(&tags->iter_usage_counter);
>> + }
>> }
>> }
>
> Atomic operations are (a) more expensive than rcu_read_lock() /
> rcu_read_lock() and (b) do not provide the same guarantees.
> rcu_read_lock() has acquire semantics and rcu_read_unlock() has
> release semantics. Regular atomic operations do not have these
> semantics which means that the CPU is allowed to reorder certain
> regular loads and stores against atomic operations. Additionally,
> atomic operations are more expensive than the corresponding RCU
> primitives. In other words, I would be much happier if this patch
> series would use RCU instead of atomics.
>
Hi Bart,
In terms of solving the problem with RCU, can you provide more details
on how it would actually work?
I saw that you mentioned kfree_rcu() at the following, so guess it's
related:
https://lore.kernel.org/linux-block/5c3ac5af-ed81-11e4-fee3-f92175f14daf@acm.org/T/#m830071bca03af31516800c14f8cccbe63661c5db
In terms of expense of atomic operations, we're just adding these
operations around the iter function, so I can't see much impact really
on fastpath.
Thanks,
John
next prev parent reply other threads:[~2020-12-18 9:32 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-17 11:07 [RFC PATCH v2 0/2] blk-mq: Avoid use-after-free for accessing old requests John Garry
2020-12-17 11:07 ` [RFC PATCH v2 1/2] blk-mq: Clean up references to old requests when freeing rqs John Garry
2020-12-17 11:07 ` [RFC PATCH v2 2/2] blk-mq: Lockout tagset iter " John Garry
2020-12-18 1:55 ` Bart Van Assche
2020-12-18 9:30 ` John Garry [this message]
2020-12-18 3:31 ` Ming Lei
2020-12-18 10:01 ` John Garry
2020-12-18 22:43 ` Bart Van Assche
2020-12-21 12:06 ` John Garry
2020-12-21 18:09 ` Bart Van Assche
2020-12-21 18:47 ` John Garry
2020-12-22 2:13 ` Bart Van Assche
2020-12-22 11:15 ` John Garry
2020-12-22 16:16 ` Bart Van Assche
2020-12-23 11:10 ` John Garry
2020-12-23 11:40 ` John Garry
2020-12-23 15:47 ` Bart Van Assche
2021-01-04 15:33 ` John Garry
2021-01-04 17:22 ` Bart Van Assche
2021-01-04 18:43 ` John Garry
[not found] ` <760304b3-dcbc-5b9d-0c70-627b7ff5b4eb@huawei.com>
2021-02-10 14:39 ` John Garry
2020-12-22 11:22 ` John Garry
2020-12-22 13:24 ` Ming Lei
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=c1e9c7d8-e9ce-b3c5-19f5-22eb3a808c29@huawei.com \
--to=john.garry@huawei.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=kashyap.desai@broadcom.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxarm@huawei.com \
--cc=ming.lei@redhat.com \
--cc=ppvk@codeaurora.org \
/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;
as well as URLs for NNTP newsgroup(s).