From: jianchao.w.wang@oracle.com (jianchao.wang)
Subject: [PATCH 3/9] nvme: change namespaces_mutext to namespaces_rwsem
Date: Mon, 12 Feb 2018 10:33:37 +0800 [thread overview]
Message-ID: <9546c34d-36a1-1e5c-b833-d3b572ed8ea3@oracle.com> (raw)
In-Reply-To: <4170b29e-693c-9c61-1b3b-716af09e44d0@grimberg.me>
Hi Sagi
Thanks for your kindly response.
And sorry for my bad description.
On 02/11/2018 07:17 PM, Sagi Grimberg wrote:
>> namespaces_mutext is used to synchronize the operations on ctrl
>> namespaces list. Most of the time, it is a read operation. It is
>> better to change it from mutex to rwsem.
>>
>> On the other hand, the namespaces mutex could introduce circular
>> dependency easily.
>
> On the other hand of what?
>
> Also, can you give an example of such?
>
We have a lot of interface in nvme core that need to hold this
namespace_mutex and looks like we will have more.
The mutex will trouble us in following scenario.
For example:
context A context B
nvme_xxx_xxx nvme_xxx_xxx
-> hold namespace_mutex -> try to require namespace_mutex
-> sync context B
Keith's patch will incur this.
http://lists.infradead.org/pipermail/linux-nvme/2018-February/015605.html
Because I add a interface that will hold namespace_mutex, so I add this patchset here.
Thanks
Jianchao
> _______________________________________________
> Linux-nvme mailing list
> Linux-nvme at lists.infradead.org
> https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.infradead.org_mailman_listinfo_linux-2Dnvme&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=7WdAxUBeiTUTCy8v-7zXyr4qk7sx26ATvfo6QSTvZyQ&m=7MZaKEgFTQoH0JODWrGtapw7rGRwXzyRBi-OKlhNaTE&s=-L_YlxhBS6aEW6Gt5tI4bV67eWn4JdvW2Nh3HAZ111Y&e=
>
next prev parent reply other threads:[~2018-02-12 2:33 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-11 9:38 [PATCH V3 0/6]nvme-pci: fixes on nvme_timeout and nvme_dev_disable Jianchao Wang
2018-02-11 9:38 ` [PATCH 1/9] nvme: fix the dangerous reference of namespaces list Jianchao Wang
2018-02-11 11:14 ` Sagi Grimberg
2018-02-11 11:15 ` Sagi Grimberg
2018-02-11 9:38 ` [PATCH 2/9] nvme: fix the deadlock in nvme_update_formats Jianchao Wang
2018-02-11 11:16 ` Sagi Grimberg
2018-02-12 1:40 ` jianchao.wang
2018-02-11 9:38 ` [PATCH 3/9] nvme: change namespaces_mutext to namespaces_rwsem Jianchao Wang
2018-02-11 11:17 ` Sagi Grimberg
2018-02-12 2:33 ` jianchao.wang [this message]
2018-02-11 9:38 ` [PATCH 4/9] nvme-pci: quiesce IO queues prior to disabling device HMB accesses Jianchao Wang
2018-02-11 11:19 ` Sagi Grimberg
2018-02-12 2:17 ` jianchao.wang
2018-02-11 9:38 ` [PATCH 5/9] nvme-pci: suspend queues based on online_queues Jianchao Wang
2018-02-11 9:38 ` [PATCH 6/9] nvme-pci: drain the entered requests after ctrl is shutdown Jianchao Wang
2018-02-11 9:38 ` [PATCH 7/9] blk-mq: make blk_mq_rq_update_aborted_gstate a external interface Jianchao Wang
2018-02-11 9:38 ` [PATCH 8/9] nvme-pci: break up nvme_timeout and nvme_dev_disable Jianchao Wang
2018-02-11 11:36 ` Sagi Grimberg
2018-02-12 2:16 ` jianchao.wang
2018-02-12 7:51 ` jianchao.wang
2018-02-11 9:38 ` [PATCH 9/9] nvme-pci: discard wait timeout when delete cq/sq Jianchao Wang
2018-02-11 11:24 ` Sagi Grimberg
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=9546c34d-36a1-1e5c-b833-d3b572ed8ea3@oracle.com \
--to=jianchao.w.wang@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