From: Jason Gunthorpe <jgg@nvidia.com>
To: Bob Pearson <rpearsonhpe@gmail.com>
Cc: zyjzyj2000@gmail.com, lizhijian@fujitsu.com, jhack@hpe.com,
linux-rdma@vger.kernel.org
Subject: Re: [PATCH for-next] RDMA/rxe: Guard mr state against race conditions
Date: Fri, 23 Sep 2022 15:40:05 -0300 [thread overview]
Message-ID: <Yy39hbAqAaKsIsH6@nvidia.com> (raw)
In-Reply-To: <20220802212731.2313-1-rpearsonhpe@gmail.com>
On Tue, Aug 02, 2022 at 04:27:32PM -0500, Bob Pearson wrote:
> Currently the rxe driver does not guard changes to the mr state
> against race conditions which can arise from races between
> local operations and remote invalidate operations. This patch
> adds a spinlock to the mr object and makes these state changes
> atomic. It also introduces parameters to count the number of
> active dma transfers and indicate that an invalidate operation
> is pending.
>
> Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
> ---
> v2
> Addressed issues raised by Jason Gunthorpe regarding preventing
> access to memory after a local or remote invalidate operation
> is carried out. The patch was updated to busy wait the invalidate
> operation until recent memcpy operations complete while blocking
> additional dma operations from starting.
> ---
> drivers/infiniband/sw/rxe/rxe_loc.h | 6 +-
> drivers/infiniband/sw/rxe/rxe_mr.c | 149 +++++++++++++------
> drivers/infiniband/sw/rxe/rxe_req.c | 8 +-
> drivers/infiniband/sw/rxe/rxe_resp.c | 200 ++++++++++++--------------
> drivers/infiniband/sw/rxe/rxe_verbs.h | 10 +-
> 5 files changed, 204 insertions(+), 169 deletions(-)
Applied to rdma-core
Thanks,
Jason
next prev parent reply other threads:[~2022-09-23 18:40 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-02 21:27 [PATCH for-next] RDMA/rxe: Guard mr state against race conditions Bob Pearson
2022-08-02 21:31 ` Pearson, Robert B
2022-08-31 9:42 ` Li Zhijian
2022-08-31 15:21 ` Pearson, Robert B
2022-09-23 18:40 ` Jason Gunthorpe [this message]
2022-09-23 19:15 ` Bob Pearson
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=Yy39hbAqAaKsIsH6@nvidia.com \
--to=jgg@nvidia.com \
--cc=jhack@hpe.com \
--cc=linux-rdma@vger.kernel.org \
--cc=lizhijian@fujitsu.com \
--cc=rpearsonhpe@gmail.com \
--cc=zyjzyj2000@gmail.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