From: Shirley Ma <shirley.ma-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
To: "Hefty,
Sean" <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Steve Wise
<swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>,
Devesh Sharma
<devesh.sharma-laKkSmNT4hbQT0dZR+AlfA@public.gmane.org>,
Roland Dreier <roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org>
Cc: "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
"chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org"
<chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Subject: Re: [for-next 1/2] xprtrdma: take reference of rdma provider module
Date: Thu, 17 Jul 2014 11:57:59 -0700 [thread overview]
Message-ID: <53C81CB7.2030000@oracle.com> (raw)
In-Reply-To: <1828884A29C6694DAF28B7E6B8A823739933FCA3-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
On 07/17/2014 09:06 AM, Hefty, Sean wrote:
>> On 7/17/2014 9:01 AM, Devesh Sharma wrote:
>>> If verndor driver is attempted for removal while xprtrdma still has an
>>> active mount, the removal of driver may never complete and can cause
>>> unseen races or in worst case system crash.
>>>
>>> To solve this, xprtrdma module should get reference of struct ib_device
>>> structure for every mount. Reference is taken after local device address
>>> resolution is completed successfuly.
>>>
>>> reference to the struct ib_device pointer is put just before cm_id
>> destruction.
>>>
>>> Signed-off-by: Devesh Sharma <devesh.sharma-laKkSmNT4hbQT0dZR+AlfA@public.gmane.org>
>>
>> This seems like an issue with the rdma-cm or rdma core, not xprtrdma. I
>> see that user rdma applications cause a ref on the provider module here
>> in ib_uverbs_open():
>>
>> if (!try_module_get(dev->ib_dev->owner)) {
>> ret = -ENODEV;
>> goto err;
>>
>>
>> Maybe kernel applications that allocate device resources should cause a
>> ref on the provider's module.
>>
>> Sean/Roland, is there some history here as to how rdma provider module
>> removal should be handled?
>
> The kernel modules should are not expected to access the rdma devices after their remove device callback has been invoked. The rdma cm basically forwards the device removal on a per id basis. Apps are expected to destroy the id after receiving that callback. The rdma cm should block in the remove device call until all id's associated with the removed device have been destroyed.
So the rdma cm is expected to increase the driver reference count (try_module_get) for each new cm id, then deference count (module_put) when cm id is destroyed?
> - Sean
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2014-07-17 18:57 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1405605697-11583-1-git-send-email-devesh.sharma@emulex.com>
[not found] ` <1405605697-11583-1-git-send-email-devesh.sharma-laKkSmNT4hbQT0dZR+AlfA@public.gmane.org>
2014-07-17 14:01 ` [for-next 1/2] xprtrdma: take reference of rdma provider module Devesh Sharma
[not found] ` <3e39e90f-7095-4eb9-a844-516672a355ad-3RiH6ntJJkOPfaB/Gd0HpljyZtpTMMwT@public.gmane.org>
2014-07-17 15:01 ` Steve Wise
[not found] ` <53C7E546.3080008-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2014-07-17 15:05 ` Chuck Lever
[not found] ` <78A77C48-AC73-4C01-B139-A00B4F674C70-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-17 15:31 ` Devesh Sharma
2014-07-17 15:20 ` Devesh Sharma
2014-07-17 16:06 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A823739933FCA3-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2014-07-17 18:57 ` Shirley Ma [this message]
[not found] ` <53C81CB7.2030000-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-17 19:07 ` Steve Wise
2014-07-17 19:50 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A823739933FDEA-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2014-07-17 19:55 ` Steve Wise
2014-07-17 20:23 ` Shirley Ma
2014-07-17 20:08 ` Steve Wise
2014-07-17 20:41 ` Chuck Lever
[not found] ` <DF7CE85B-288D-4CC2-AD51-B326D5F1EE1A-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-17 20:59 ` Steve Wise
2014-07-18 5:05 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FE1482F-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-07-18 13:27 ` Steve Wise
2014-07-18 15:47 ` Shirley Ma
[not found] ` <53C94199.4050601-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-21 6:11 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FE1C7B7-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-07-21 11:48 ` Devesh Sharma
[not found] ` <a6345162-863d -447c-b7c2-059ced190a13@CMEXHTCAS1.ad.emulex.com>
[not found] ` <a6345162-863d-447c-b7c2-059ced190a13-3RiH6ntJJkP8BX6JNMqfyFjyZtpTMMwT@public.gmane.org>
2014-07-21 14:53 ` Chuck Lever
[not found] ` <27ACE237-161A-4CA5-AA5C-6349CC4118E3-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-21 15:03 ` Steve Wise
2014-07-21 15:20 ` Chuck Lever
[not found] ` <D88D1952-83A1-4FF9-B028-AAE7A859A 5B1@oracle.com>
[not found] ` <D88D1952-83A1-4FF9-B028-AAE7A859A5B1-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-21 15:22 ` Steve Wise
2014-07-21 17:07 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FE1D9CF-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-07-21 17:30 ` Chuck Lever
[not found] ` <0CDA5340-DDD6-42F8-8359-0069BBC9E24C-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-22 5:06 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FE1DB1D-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-07-30 18:39 ` Chuck Lever
[not found] ` <A40CDF7D-7ED2-4D67-957F-8F977D567774-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-31 5:14 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FE23695-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-08-18 9:52 ` Devesh Sharma
[not found] ` <6a71f6a5-f335-42c6-b8b7-8b4bac5aae83-3RiH6ntJJkP8BX6JNMqfyFjyZtpTMMwT@public.gmane.org>
2014-08-18 13:13 ` Chuck Lever
2014-07-21 5:23 ` Devesh Sharma
2014-07-17 21:25 ` Shirley Ma
2014-07-18 6:19 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FE1686F-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-07-18 15:27 ` Chuck Lever
[not found] ` <D9783B2E-8D18-442E-9BFE-0863F9DD6B96-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-07-21 5:40 ` Devesh Sharma
2014-07-17 14:01 ` [for-next 2/2] xprtrdma: fix deallocation sequence of pd Devesh Sharma
[not found] ` <3fdcf67f-2e90-4c61-92da-a8f7743cf54a-3RiH6ntJJkOPfaB/Gd0HpljyZtpTMMwT@public.gmane.org>
2014-07-17 15:05 ` Steve Wise
[not found] ` <53C7E64D.90501-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2014-07-17 15:35 ` Devesh Sharma
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=53C81CB7.2030000@oracle.com \
--to=shirley.ma-qhclzuegtsvqt0dzr+alfa@public.gmane.org \
--cc=chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org \
--cc=devesh.sharma-laKkSmNT4hbQT0dZR+AlfA@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org \
--cc=sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.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