From: Jes Sorensen <jes@sgi.com>
To: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: akepner@sgi.com, Randy Dunlap <randy.dunlap@oracle.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
rdreier@cisco.com, linux-ia64 <linux-ia64@vger.kernel.org>
Subject: Re: [PATCH 2/3] dma: override "dma_flags_set_dmaflush" for sn-ia64
Date: Wed, 22 Aug 2007 07:39:36 +0000 [thread overview]
Message-ID: <46CBE838.4000302@sgi.com> (raw)
In-Reply-To: <1187745249.18410.67.camel@localhost.localdomain>
James Bottomley wrote:
> On Tue, 2007-08-21 at 17:34 -0700, akepner@sgi.com wrote:
>> The term "posted DMA" is used to describe this behavior in the Altix
>> Device Driver Writer's Guide, but it may be confusing things here.
>> Maybe a better term will suggest itself if I can clarify....
>
> OK, but posted DMA has a pretty specific meaning in terms of PCI, hence
> the confusion.
Maybe it would be more better to refer to this as 'out of order DMA'?
>> On Altix, DMA from a device isn't guaranteed to arrive in host memory
>> in the order it was sent from the device. This reordering can happen
>> in the NUMA interconnect (it's specifically not a PCI reordering.)
>
> This is mmiowb and read_relaxed() again, isn't it?
I believe it's the same problem, except this time it's when exposing
structures to userland.
Cheers,
Jes
WARNING: multiple messages have this Message-ID (diff)
From: Jes Sorensen <jes@sgi.com>
To: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: akepner@sgi.com, Randy Dunlap <randy.dunlap@oracle.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
rdreier@cisco.com, linux-ia64 <linux-ia64@vger.kernel.org>
Subject: Re: [PATCH 2/3] dma: override "dma_flags_set_dmaflush" for sn-ia64
Date: Wed, 22 Aug 2007 09:39:36 +0200 [thread overview]
Message-ID: <46CBE838.4000302@sgi.com> (raw)
In-Reply-To: <1187745249.18410.67.camel@localhost.localdomain>
James Bottomley wrote:
> On Tue, 2007-08-21 at 17:34 -0700, akepner@sgi.com wrote:
>> The term "posted DMA" is used to describe this behavior in the Altix
>> Device Driver Writer's Guide, but it may be confusing things here.
>> Maybe a better term will suggest itself if I can clarify....
>
> OK, but posted DMA has a pretty specific meaning in terms of PCI, hence
> the confusion.
Maybe it would be more better to refer to this as 'out of order DMA'?
>> On Altix, DMA from a device isn't guaranteed to arrive in host memory
>> in the order it was sent from the device. This reordering can happen
>> in the NUMA interconnect (it's specifically not a PCI reordering.)
>
> This is mmiowb and read_relaxed() again, isn't it?
I believe it's the same problem, except this time it's when exposing
structures to userland.
Cheers,
Jes
next prev parent reply other threads:[~2007-08-22 7:39 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-18 0:27 [PATCH 2/3] dma: override "dma_flags_set_dmaflush" for sn-ia64 akepner
2007-08-20 8:24 ` Jes Sorensen
2007-08-20 8:24 ` Jes Sorensen
2007-08-20 16:07 ` akepner
2007-08-20 16:07 ` akepner
2007-08-21 19:35 ` akepner
2007-08-21 19:35 ` akepner
2007-08-21 20:05 ` Randy Dunlap
2007-08-21 20:05 ` Randy Dunlap
2007-08-21 20:55 ` James Bottomley
2007-08-21 20:55 ` James Bottomley
2007-08-22 0:34 ` akepner
2007-08-22 0:34 ` akepner
2007-08-22 1:14 ` James Bottomley
2007-08-22 1:14 ` James Bottomley
2007-08-22 7:39 ` Jes Sorensen [this message]
2007-08-22 7:39 ` Jes Sorensen
2007-08-22 14:02 ` James Bottomley
2007-08-22 14:02 ` James Bottomley
2007-08-22 16:03 ` Jesse Barnes
2007-08-22 16:03 ` Jesse Barnes
2007-08-22 16:44 ` James Bottomley
2007-08-22 16:44 ` James Bottomley
2007-08-22 16:51 ` Jesse Barnes
2007-08-22 16:51 ` Jesse Barnes
2007-08-22 17:04 ` James Bottomley
2007-08-22 17:04 ` James Bottomley
2007-08-22 17:03 ` Jes Sorensen
2007-08-22 17:03 ` Jes Sorensen
2007-08-22 18:10 ` James Bottomley
2007-08-22 18:10 ` James Bottomley
2007-08-23 8:45 ` Jes Sorensen
2007-08-23 8:45 ` Jes Sorensen
2007-08-22 17:17 ` Jesse Barnes
2007-08-22 17:17 ` Jesse Barnes
2007-08-22 18:13 ` James Bottomley
2007-08-22 18:13 ` James Bottomley
2007-08-22 18:44 ` akepner
2007-08-22 18:44 ` akepner
2007-08-23 5:58 ` Jeremy Higdon
2007-08-23 5:58 ` Jeremy Higdon
2007-08-22 15:54 ` akepner
2007-08-22 15:54 ` akepner
2007-08-21 20:16 ` Matthew Wilcox
2007-08-21 20:16 ` Matthew Wilcox
2007-08-21 21:37 ` akepner
2007-08-21 21:37 ` akepner
2007-08-22 7:44 ` Jes Sorensen
2007-08-22 7:44 ` Jes Sorensen
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=46CBE838.4000302@sgi.com \
--to=jes@sgi.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=akepner@sgi.com \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=randy.dunlap@oracle.com \
--cc=rdreier@cisco.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.