linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sagi Grimberg <sagig-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
To: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>,
	dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	Liran Liss <liranl-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH 10/11] IB: only keep a single key in struct ib_mr
Date: Tue, 22 Dec 2015 11:17:54 +0200	[thread overview]
Message-ID: <56791542.6020604@dev.mellanox.co.il> (raw)
In-Reply-To: <1448214409-7729-11-git-send-email-hch-jcswGhMUV9g@public.gmane.org>

Hi Christoph,

> While IB supports the notion of returning separate local and remote keys
> from a memory registration, the iWarp spec doesn't and neither does any
> of our in-tree HCA drivers [1] nor consumers.  Consolidate the in-kernel
> API to provide only a single key and make everyones life easier.

What makes me worried here is that the IB/RoCE specification really
defines different keys for local and remote access. I'm less concerned
about our consumers but more about our providers. We keep seeing new
providers come along and its not impossible that a specific HW will
*rely* on this distinction. In such a case we'd need to revert this
patch altogether in that very moment.

I think we're better off working on proper abstractions to help ULPs
get it right (and simple!), without risking future devices support.

Sagi.
--
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

  parent reply	other threads:[~2015-12-22  9:17 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-22 17:46 memory registration updates Christoph Hellwig
     [not found] ` <1448214409-7729-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2015-11-22 17:46   ` [PATCH 01/11] IB: start documenting device capabilities Christoph Hellwig
2015-11-22 17:46   ` [PATCH 02/11] IB: remove ib_query_mr Christoph Hellwig
2015-11-22 17:46   ` [PATCH 03/11] IB: remove support for phys MRs Christoph Hellwig
     [not found]     ` <1448214409-7729-4-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2015-11-24 12:01       ` Devesh Sharma
2015-11-22 17:46   ` [PATCH 04/11] IB: remove in-kernel support for memory windows Christoph Hellwig
2015-11-22 17:46   ` [PATCH 05/11] cxgb3: simplify iwch_get_dma_wr Christoph Hellwig
2015-11-22 17:46   ` [PATCH 06/11] nes: simplify nes_reg_phys_mr calling conventions Christoph Hellwig
2015-11-22 17:46   ` [PATCH 07/11] amso1100: fold c2_reg_phys_mr into c2_get_dma_mr Christoph Hellwig
2015-11-22 17:46   ` [PATCH 08/11] ehca: stop using struct ib_phys_buf Christoph Hellwig
2015-11-22 17:46   ` [PATCH 09/11] IB: remove the struct ib_phys_buf definition Christoph Hellwig
2015-11-22 17:46   ` [PATCH 10/11] IB: only keep a single key in struct ib_mr Christoph Hellwig
     [not found]     ` <1448214409-7729-11-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2015-11-23 19:41       ` Jason Gunthorpe
     [not found]         ` <20151123194124.GF32085-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-11-23 19:48           ` Christoph Hellwig
2015-12-22  9:17       ` Sagi Grimberg [this message]
     [not found]         ` <56791542.6020604-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-12-22 13:13           ` Christoph Hellwig
     [not found]             ` <20151222131326.GA25267-jcswGhMUV9g@public.gmane.org>
2015-12-22 13:50               ` Sagi Grimberg
     [not found]                 ` <56795514.9090704-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-12-22 13:59                   ` Christoph Hellwig
     [not found]                     ` <20151222135927.GA26311-jcswGhMUV9g@public.gmane.org>
2015-12-22 16:58                       ` Sagi Grimberg
     [not found]                         ` <56798126.9000003-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-12-22 21:09                           ` Jason Gunthorpe
     [not found]                             ` <7sikrilf3ik3fjsgppqxh9gn.1451043246057@email.android.com>
     [not found]                               ` <CAMHdiBDv9mScD+5o90OQ_tmAKw9o48_jfao6W+EBOZkUg+wReA@mail.gmail.com>
     [not found]                                 ` <CAMHdiBDv9mScD+5o90OQ_tmAKw9o48_jfao6W+EBOZkUg+wReA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-12-25 16:46                                   ` Liran Liss
     [not found]                                     ` <CAMHdiBC75n+u9BSMsKxJwcaBnGL68_3UBeQQtHp_CD5KGcUTnQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-01-05 17:46                                       ` Jason Gunthorpe
     [not found]                                         ` <20160105174636.GD16269-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2016-01-06  6:08                                           ` Christoph Hellwig
     [not found]                                             ` <20160106060806.GA16509-jcswGhMUV9g@public.gmane.org>
2016-01-06 15:10                                               ` Sagi Grimberg
     [not found]                                                 ` <568D2E4E.5020806-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2016-01-06 16:59                                                   ` Jason Gunthorpe
2015-11-22 17:46   ` [PATCH 11/11] IB: provide better access flags for fast registrations Christoph Hellwig
     [not found]     ` <1448214409-7729-12-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2015-11-23 15:09       ` Chuck Lever
     [not found]         ` <EE465F12-A5F6-4C95-A77C-199DFF8F77BD-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2015-11-23 15:49           ` Christoph Hellwig
2015-11-23 18:58       ` Jason Gunthorpe
     [not found]         ` <20151123185829.GE32085-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-11-23 19:44           ` Christoph Hellwig
2015-11-23  9:03   ` memory registration updates Sagi Grimberg
     [not found]     ` <5652D66E.5070600-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-11-23 14:16       ` Christoph Hellwig
     [not found]         ` <20151123141650.GA11116-jcswGhMUV9g@public.gmane.org>
2015-11-23 15:17           ` Sagi Grimberg
     [not found]             ` <56532E0A.20907-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2015-11-23 19:43               ` Christoph Hellwig
2015-11-23 15:06   ` Steve Wise

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=56791542.6020604@dev.mellanox.co.il \
    --to=sagig-ldsdmyg8hgv8yrgs2mwiifqbs+8scbdb@public.gmane.org \
    --cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=hch-jcswGhMUV9g@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=liranl-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 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).