From: santosh.shilimkar@oracle.com
To: Max Gurtovoy <maxg@mellanox.com>,
Sagi Grimberg <sagi@grimberg.me>, Tom Talpey <tom@talpey.com>,
Aron Silverton <aron.silverton@oracle.com>
Cc: bvanassche@acm.org, Jason Gunthorpe <jgg@mellanox.com>,
linux-rdma@vger.kernel.org, dledford@redhat.com, leon@kernel.org,
israelr@mellanox.com, shlomin@mellanox.com
Subject: Re: [PATCH 0/8 v1] Remove FMR support from RDMA drivers
Date: Mon, 18 May 2020 09:34:44 -0700 [thread overview]
Message-ID: <a01abcf6-64a5-5a66-4ee7-ac0b3aa9c83d@oracle.com> (raw)
In-Reply-To: <3e4c0d12-d0f9-87f4-a256-ebe7d881de08@mellanox.com>
On 5/17/20 3:51 AM, Max Gurtovoy wrote:
>
> On 5/15/2020 9:59 PM, Sagi Grimberg wrote:
>>
>>> It's not only the fmr_pools. The FMR API operates on a page granularity,
>>> so a sub-page registration, or a non-page-aligned one, ends up exposing
>>> data outside the buffer. This is done silently, and is a significant
>>> vulnerability for most upper layers.
>>
>> You're right Tom, I forgot about that...
>> I guess I'd vote to remove it altogether then...
>
> Santosh,
>
> I don't really understand the mechanism you use from user/kernel
> regarding the registration.
>
> But I saw you use wait_event and wait for completing the
> FRWR/INVALIDATION. For sure this is not optimal.
>
> But can't really say what is the bottleneck in your case.
>
> Can you share the numbers you get for FMR/FRWR benchmarks ?
>
The upstream code for FRWR is behind the optimal code we have
been using. The invalidation path is removed from datapath
with proxy QP within the PD.
Anyway, please bounce your patches for me to review to make sure
nothing breaks. From various responses, it seems to be aligned to
move ahead with the patch-set, so lets go with it.
Regards,
Santosh
next prev parent reply other threads:[~2020-05-18 16:35 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-14 12:02 [PATCH 0/8 v1] Remove FMR support from RDMA drivers Max Gurtovoy
2020-05-14 12:02 ` [PATCH 1/8] RDMA/mlx4: remove FMR support for memory registration Max Gurtovoy
2020-05-14 12:02 ` [PATCH 2/8] RDMA/rds: " Max Gurtovoy
2020-05-14 12:03 ` [PATCH 3/8] RDMA/mthca: " Max Gurtovoy
2020-05-14 12:03 ` [PATCH 4/8] RDMA/rdmavt: remove FMR " Max Gurtovoy
2020-05-14 12:03 ` [PATCH 5/8] RDMA/iser: Remove support for " Max Gurtovoy
2020-05-14 12:03 ` [PATCH 6/8] RDMA/srp: remove " Max Gurtovoy
2020-05-14 14:02 ` Bart Van Assche
2020-05-14 12:03 ` [PATCH 7/8] RDMA/core: remove FMR pool API Max Gurtovoy
2020-05-14 12:03 ` [PATCH 8/8] RDMA/core: remove FMR device ops Max Gurtovoy
2020-05-14 15:13 ` [PATCH 0/8 v1] Remove FMR support from RDMA drivers Aron Silverton
2020-05-14 18:18 ` santosh.shilimkar
2020-05-14 19:42 ` Max Gurtovoy
2020-05-14 22:23 ` Sagi Grimberg
2020-05-14 23:41 ` santosh.shilimkar
2020-05-15 16:52 ` Tom Talpey
2020-05-15 18:59 ` Sagi Grimberg
2020-05-17 10:51 ` Max Gurtovoy
2020-05-18 16:34 ` santosh.shilimkar [this message]
2020-05-15 0:37 ` Max Gurtovoy
2020-05-14 16:00 ` Gal Pressman
2020-05-17 10:37 ` Max Gurtovoy
2020-05-18 15:20 ` Dennis Dalessandro
2020-05-18 18:10 ` Jason Gunthorpe
2020-05-19 13:43 ` Dennis Dalessandro
2020-05-19 13:53 ` Jason Gunthorpe
2020-05-19 14:19 ` Leon Romanovsky
2020-05-19 14:26 ` Dennis Dalessandro
2020-05-19 14:30 ` Jason Gunthorpe
2020-05-19 14:37 ` Dennis Dalessandro
2020-05-23 22:08 ` Jason Gunthorpe
2020-05-24 1:27 ` Tom Talpey
2020-05-26 15:38 ` Dennis Dalessandro
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=a01abcf6-64a5-5a66-4ee7-ac0b3aa9c83d@oracle.com \
--to=santosh.shilimkar@oracle.com \
--cc=aron.silverton@oracle.com \
--cc=bvanassche@acm.org \
--cc=dledford@redhat.com \
--cc=israelr@mellanox.com \
--cc=jgg@mellanox.com \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=maxg@mellanox.com \
--cc=sagi@grimberg.me \
--cc=shlomin@mellanox.com \
--cc=tom@talpey.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;
as well as URLs for NNTP newsgroup(s).