From: Yishai Hadas <yishaih-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
To: "Hefty,
Sean" <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
"dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org"
<dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: Yishai Hadas <yishaih-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
"linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
"jackm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org"
<jackm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
"raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org"
<raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
liranl-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org
Subject: Re: [RESEND PATCH V3 for-next 0/3] HW Device hot-removal support
Date: Thu, 14 May 2015 14:28:10 +0300 [thread overview]
Message-ID: <555486CA.8080409@dev.mellanox.co.il> (raw)
In-Reply-To: <1828884A29C6694DAF28B7E6B8A82373A8FDA36D-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
On 5/13/2015 11:55 PM, Hefty, Sean wrote:
> Please look at ib_user_mad and how it handles device removal with active clients. We should be able to follow the same model that doesn't require driving changes down into every driver.
>
The ib_uverbs code does follow the same model in the sense that the
context (uverbs_device) associated with the fd remains open until the
app closes it, while all references to the HW device are removed
immediately. However, in contrast to the umad API, which does *not*
expose direct HW access and thus can be managed in a device-independent
manner, ib_uverbs does provide user-space direct HW access.
Therefore, detaching a ib_uverbs context from a HW device does require
device-specific logic.
The amount of code depends on the specific driver. The proposed
framework provides any driver a chance to do proper cleanup when devices
are removed.
--
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:[~2015-05-14 11:28 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-13 11:10 [RESEND PATCH V3 for-next 0/3] HW Device hot-removal support Yishai Hadas
[not found] ` <1431515438-24042-1-git-send-email-yishaih-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-05-13 11:10 ` [PATCH V3 for-next 1/3] IB/uverbs: Enable device removal when there are active user space applications Yishai Hadas
[not found] ` <1431515438-24042-2-git-send-email-yishaih-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-05-25 16:54 ` Jason Gunthorpe
[not found] ` <20150525165449.GA4379-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-05-27 16:04 ` Doug Ledford
[not found] ` <1432742669.28905.228.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-05-27 17:43 ` Jason Gunthorpe
[not found] ` <20150527174332.GC9909-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-05-27 21:36 ` Or Gerlitz
[not found] ` <CAJ3xEMiYbrr2mkXuywNcyYu1v0dqeM+6Lks-CL0U6fSnx=DQ+Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-05-28 0:51 ` Doug Ledford
2015-05-27 20:47 ` Yishai Hadas
[not found] ` <55662D63.3030806-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-05-28 6:19 ` Jason Gunthorpe
[not found] ` <20150528061923.GA4054-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-05-29 10:30 ` Shachar Raindel
[not found] ` <AM3PR05MB0935AB183EA8764FD83C36A0DCC90-LOZWmgKjnYgQouBfZGh8ttqRiQSDpxhJvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2015-05-29 17:06 ` Jason Gunthorpe
2015-05-13 11:10 ` [PATCH V3 for-next 2/3] IB/mlx4_ib: Disassociate support Yishai Hadas
2015-05-13 11:10 ` [PATCH V3 for-next 3/3] IB/ucma: HW Device hot-removal support Yishai Hadas
2015-05-13 20:55 ` [RESEND PATCH V3 for-next 0/3] " Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A82373A8FDA36D-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2015-05-14 11:28 ` Yishai Hadas [this message]
[not found] ` <555486CA.8080409-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-05-14 16:50 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A82373A8FDA931-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2015-05-17 10:33 ` Yishai Hadas
[not found] ` <55586E5D.1030801-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-05-18 18:21 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A82373A8FDC9A4-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2015-05-19 16:17 ` Liran Liss
[not found] ` <HE1PR05MB1418D0CE0E031DA35E3DDEBAB1C30-eBadYZ65MZ87O8BmmlM1zNqRiQSDpxhJvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2015-05-25 14:01 ` Yishai Hadas
2015-05-27 16:12 ` Doug Ledford
[not found] ` <1432743174.28905.231.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-05-28 15:58 ` Liran Liss
2015-05-28 16:08 ` Liran Liss
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=555486CA.8080409@dev.mellanox.co.il \
--to=yishaih-ldsdmyg8hgv8yrgs2mwiifqbs+8scbdb@public.gmane.org \
--cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=jackm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=liranl-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=yishaih-VPRAkNaXOzVWk0Htik3J/w@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.