linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: chas williams <chas@cmf.nrl.navy.mil>
To: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
Cc: davem@redhat.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH][ATM] assorted he driver cleanup
Date: Thu, 29 May 2003 12:31:17 -0400	[thread overview]
Message-ID: <200305291632.h4TGWwsG022510@ginger.cmf.nrl.navy.mil> (raw)
In-Reply-To: Your message of "Thu, 29 May 2003 13:21:26 -0300." <20030529162125.GU24054@conectiva.com.br>

In message <20030529162125.GU24054@conectiva.com.br>,Arnaldo Carvalho de Melo w
rites:
>> @@ -189,7 +187,7 @@
>>  #define HE_SPIN_LOCK(dev, flags)	spin_lock_irqsave(&(dev)->global_lock, 
>flags)
>>  #define HE_SPIN_UNLOCK(dev, flags)	spin_unlock_irqrestore(&(dev)->global_l
>ock, flags)
>
>Is the above really needed?

well, according to the programmer's guide:

8.1.7   PCI Transaction Ordering Error

PROBLEM: The PCI Bus Controller, in addition to bus master and general
target functionality, acts as a bridge to a local bus. If a read is
issued to the local bus and the read COMPLETES on the local bus but is
not yet completed on the PCI bus, a subsequent write to the local bus
that completes on the PCI bus will cause the write data to be written
to the last local bus read address.

RESOLUTION: In an environment where PCI bus bridge settings cannot be
controlled, card drivers must lock read and write access to the ATM
Network Controller and the SONET Framer device. In an environment where
PCI bus bridge settings can be controlled, features that allow reordering
of reads and writes from separate processors (i.e., Posted memory write
features) should be disabled.

  reply	other threads:[~2003-05-29 16:19 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-05-29 16:09 [PATCH][ATM] assorted he driver cleanup chas williams
2003-05-29 16:19 ` Christoph Hellwig
2003-05-29 16:32   ` chas williams
2003-05-29 16:21 ` Arnaldo Carvalho de Melo
2003-05-29 16:31   ` chas williams [this message]
2003-05-29 17:06     ` Arnaldo Carvalho de Melo
2003-05-29 17:12       ` chas williams
2003-05-29 17:36         ` Arnaldo Carvalho de Melo
2003-06-01 18:57           ` chas williams
2003-06-01 20:00             ` Alan Cox
2003-06-01 22:58               ` chas williams
2003-06-02  1:42                 ` David S. Miller
2003-06-02  1:47                   ` Arnaldo Carvalho de Melo
2003-06-02  2:34                   ` chas williams
2003-06-02 13:50                     ` Alan Cox
2003-06-02  1:32             ` David S. Miller
2003-05-29 18:08   ` chas williams
2003-05-29 18:34     ` Arnaldo Carvalho de Melo
2003-05-30  3:01 ` David S. Miller
2003-05-30  8:57   ` Dave Jones
2003-05-30 13:36     ` Jeff Garzik
2003-05-30 13:46   ` chas williams
2003-05-30 14:00     ` chas williams
     [not found]       ` <200305301431.h4UEVesG003572@ginger.cmf.nrl.navy.mil>
2003-06-04  4:51         ` David S. Miller
2003-06-01 22:42 ` Francois Romieu
2003-06-18 21:08   ` chas williams
2003-06-19  1:05     ` David S. Miller

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=200305291632.h4TGWwsG022510@ginger.cmf.nrl.navy.mil \
    --to=chas@cmf.nrl.navy.mil \
    --cc=acme@conectiva.com.br \
    --cc=davem@redhat.com \
    --cc=linux-kernel@vger.kernel.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).