All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joachim Fenkes <fenkes@de.ibm.com>
To: Roland Dreier <rdreier@cisco.com>
Cc: Arnd Bergmann <arnd@arndb.de>,
	LKML <linux-kernel@vger.kernel.org>,
	OF-EWG <ewg@lists.openfabrics.org>,
	linuxppc-dev@ozlabs.org, Christoph Raisch <raisch@de.ibm.com>,
	Marcus Eder <meder@de.ibm.com>,
	OF-General <general@lists.openfabrics.org>,
	Stefan Roscher <stefan.roscher@de.ibm.com>
Subject: Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5
Date: Mon, 10 Dec 2007 18:41:29 +0100	[thread overview]
Message-ID: <200712101841.30010.fenkes@de.ibm.com> (raw)
In-Reply-To: <adaodcza1xc.fsf@cisco.com>

On Monday 10 December 2007 00:22, Roland Dreier wrote:
> Fair enough... according to Documentation/infiniband/core_locking.txt,
> the only driver methods that cannot sleep are:
> 
>     [...]
>     map_phys_fmr

In fact, we do use hCalls there. Our hardware doesn't actually support FMRs,
so we translate a "map FMR" into a "reallocate PMR", which doesn't work
without hCalls. What's more, the hCalls involved (e.g. H_FREE_RESOURCE)
might well return H_LONG_BUSY, so the whole operation might sleep; no way
around it.

How should we deal with this?

Thanks,
  Joachim

WARNING: multiple messages have this Message-ID (diff)
From: Joachim Fenkes <fenkes@de.ibm.com>
To: Roland Dreier <rdreier@cisco.com>
Cc: Arnd Bergmann <arnd@arndb.de>,
	linuxppc-dev@ozlabs.org, LKML <linux-kernel@vger.kernel.org>,
	OF-EWG <ewg@lists.openfabrics.org>,
	Christoph Raisch <raisch@de.ibm.com>,
	Marcus Eder <meder@de.ibm.com>,
	OF-General <general@lists.openfabrics.org>,
	Stefan Roscher <stefan.roscher@de.ibm.com>
Subject: Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5
Date: Mon, 10 Dec 2007 18:41:29 +0100	[thread overview]
Message-ID: <200712101841.30010.fenkes@de.ibm.com> (raw)
In-Reply-To: <adaodcza1xc.fsf@cisco.com>

On Monday 10 December 2007 00:22, Roland Dreier wrote:
> Fair enough... according to Documentation/infiniband/core_locking.txt,
> the only driver methods that cannot sleep are:
> 
>     [...]
>     map_phys_fmr

In fact, we do use hCalls there. Our hardware doesn't actually support FMRs,
so we translate a "map FMR" into a "reallocate PMR", which doesn't work
without hCalls. What's more, the hCalls involved (e.g. H_FREE_RESOURCE)
might well return H_LONG_BUSY, so the whole operation might sleep; no way
around it.

How should we deal with this?

Thanks,
  Joachim


  reply	other threads:[~2007-12-10 17:42 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-12-06 15:07 [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5 Joachim Fenkes
2007-12-06 15:07 ` Joachim Fenkes
2007-12-06 15:48 ` Arnd Bergmann
2007-12-06 15:48   ` Arnd Bergmann
2007-12-06 18:27   ` Roland Dreier
2007-12-06 18:27     ` Roland Dreier
2007-12-07  9:58     ` Arnd Bergmann
2007-12-07  9:58       ` Arnd Bergmann
2007-12-09 23:22       ` Roland Dreier
2007-12-09 23:22         ` Roland Dreier
2007-12-10 17:41         ` Joachim Fenkes [this message]
2007-12-10 17:41           ` Joachim Fenkes
2007-12-10 21:47           ` Roland Dreier
2007-12-10 21:47             ` Roland Dreier
2007-12-11  8:38             ` Joachim Fenkes
2007-12-11  8:38               ` Joachim Fenkes
2007-12-12 12:14               ` [ewg] " Or Gerlitz
2007-12-12 12:14                 ` Or Gerlitz
2007-12-12 16:02                 ` Christoph Raisch
2007-12-12 16:02                   ` Christoph Raisch
2007-12-12 19:09                 ` Roland Dreier
2007-12-12 19:09                   ` Roland Dreier
2007-12-13  8:30                   ` Or Gerlitz
2007-12-13  8:30                     ` Or Gerlitz
2007-12-13 19:22                     ` [ofa-general] " Caitlin Bestler
2007-12-13 19:22                       ` Caitlin Bestler
2007-12-13 20:59                       ` Joachim Fenkes
2007-12-13 20:59                         ` Joachim Fenkes
2007-12-13 21:08                         ` Caitlin Bestler
2007-12-13 21:08                           ` Caitlin Bestler
2007-12-13 21:35                           ` Joachim Fenkes
2007-12-13 21:35                             ` Joachim Fenkes
2007-12-13 21:48                           ` [ofa-general] Re: [ewg] Re: [PATCH] IB/ehca: SerializeHCA-related " Sean Hefty
2007-12-13 21:48                             ` Sean Hefty
2007-12-07 16:25     ` [PATCH] IB/ehca: Serialize HCA-related " Joachim Fenkes
2007-12-07 16:25       ` Joachim Fenkes
     [not found] <OF85E31FAA.DADA6039-ONC12573AA.005439C8-C12573AA.005A132E@LocalDomain>
2007-12-10 17:59 ` Joachim Fenkes
2007-12-10 17:59   ` Joachim Fenkes

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=200712101841.30010.fenkes@de.ibm.com \
    --to=fenkes@de.ibm.com \
    --cc=arnd@arndb.de \
    --cc=ewg@lists.openfabrics.org \
    --cc=general@lists.openfabrics.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=meder@de.ibm.com \
    --cc=raisch@de.ibm.com \
    --cc=rdreier@cisco.com \
    --cc=stefan.roscher@de.ibm.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 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.