From: Leon Romanovsky <leon@kernel.org>
To: Christoph Hellwig <hch@lst.de>, Jason Gunthorpe <jgg@nvidia.com>
Cc: Doug Ledford <dledford@redhat.com>,
Avihai Horon <avihaih@nvidia.com>,
linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org,
Bart Van Assche <bvanassche@acm.org>, Tom Talpey <tom@talpey.com>,
Santosh Shilimkar <santosh.shilimkar@oracle.com>,
Chuck Lever III <chuck.lever@oracle.com>,
Keith Busch <kbusch@kernel.org>,
David Laight <David.Laight@aculab.com>,
Honggang LI <honli@redhat.com>,
Max Gurtovoy <mgurtovoy@nvidia.com>
Subject: Re: [PATCH v2 rdma-next] RDMA/mlx5: Enable Relaxed Ordering by default for kernel ULPs
Date: Thu, 10 Jun 2021 10:44:55 +0300 [thread overview]
Message-ID: <YMHC93U12rgLlQCx@unreal> (raw)
In-Reply-To: <20210609135924.GA6510@lst.de>
On Wed, Jun 09, 2021 at 03:59:24PM +0200, Christoph Hellwig wrote:
> On Wed, Jun 09, 2021 at 04:53:23PM +0300, Leon Romanovsky wrote:
> > Sure, did you have in mind some concrete place? Or will new file in the
> > Documentation/infiniband/ folder be good enough too?
>
> Maybe add a kerneldoc comment for the map_mr_sg() ib_device_ops method?
I hope that this hunk from the previous cover letter is good enough.
Jason, do you want v3? or you can fold this into v2?
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 9423e70a881c..aaf63a6643d6 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2468,6 +2468,13 @@ struct ib_device_ops {
enum ib_uverbs_advise_mr_advice advice, u32 flags,
struct ib_sge *sg_list, u32 num_sge,
struct uverbs_attr_bundle *attrs);
+ /*
+ * Kernel users should universally support relaxed ordering (RO),
+ * as they are designed to read data only after observing the CQE
+ * and use the DMA API correctly.
+ *
+ * Some drivers implicitly enable RO if platform supports it.
+ */
int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
unsigned int *sg_offset);
int (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
next prev parent reply other threads:[~2021-06-10 7:45 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-09 11:05 [PATCH v2 rdma-next] RDMA/mlx5: Enable Relaxed Ordering by default for kernel ULPs Leon Romanovsky
2021-06-09 12:52 ` Christoph Hellwig
2021-06-09 13:53 ` Leon Romanovsky
2021-06-09 13:59 ` Christoph Hellwig
2021-06-10 7:44 ` Leon Romanovsky [this message]
2021-06-09 14:10 ` David Laight
2021-06-09 14:37 ` Chuck Lever III
2021-06-09 15:05 ` David Laight
2021-06-09 15:09 ` Jason Gunthorpe
2021-06-09 15:48 ` David Laight
2021-06-21 18:02 ` Jason Gunthorpe
2021-06-21 20:20 ` Christoph Hellwig
2021-06-21 23:18 ` Jason Gunthorpe
2021-06-22 6:20 ` Leon Romanovsky
2021-06-23 23:06 ` Max Gurtovoy
2021-06-24 6:38 ` Leon Romanovsky
2021-06-24 7:39 ` Max Gurtovoy
2021-06-24 11:36 ` Jason Gunthorpe
2021-06-27 7:32 ` Leon Romanovsky
2021-06-27 7:30 ` Leon Romanovsky
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=YMHC93U12rgLlQCx@unreal \
--to=leon@kernel.org \
--cc=David.Laight@aculab.com \
--cc=avihaih@nvidia.com \
--cc=bvanassche@acm.org \
--cc=chuck.lever@oracle.com \
--cc=dledford@redhat.com \
--cc=hch@lst.de \
--cc=honli@redhat.com \
--cc=jgg@nvidia.com \
--cc=kbusch@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mgurtovoy@nvidia.com \
--cc=santosh.shilimkar@oracle.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