From: Grant Grundler <iod00d@hp.com>
To: David Brownell <david-b@pacbell.net>
Cc: davidm@hpl.hp.com, Greg KH <greg@kroah.com>,
vojtech@suse.cz, linux-usb-devel@lists.sourceforge.net,
linux-kernel@vger.kernel.org, linux-ia64@vger.kernel.org,
pochini@shiny.it
Subject: Re: [linux-usb-devel] Re: serious 2.6 bug in USB subsystem?
Date: Sun, 7 Mar 2004 22:18:02 -0800 [thread overview]
Message-ID: <20040308061802.GA25960@cup.hp.com> (raw)
In-Reply-To: <4049FE57.2060809@pacbell.net>
On Sat, Mar 06, 2004 at 08:37:43AM -0800, David Brownell wrote:
> DMA-coherent memory is defined as "memory for which a write by either
> the device or the processor can immediately be read by the processor
> or device without having to worry about caching effects."
The use of "immediate" here means no other sync function needs to
be called to access the data - ie don't need to call pci_sync_single().
In general, the accesses are ordered following PCI ordering rules.
But every architecture (including x86) has issues with "inflight" DMA.
Line based Interrupts are delivered on a different path than DMA
and thus ordering can't be enforced.
For example, the code around the following comment in drivers/net/tg3.c:
/*
* Flush PCI write. This also guarantees that our
* status block has been flushed to host memory.
*/
> `Such a
> write-buffering mechanism is clearly a type of (write-)caching effect,
No - the data is still in flight and in some deterministic time frame
will become visible to the CPU.
Calling it a "caching effect" confuses the issues even worse.
> and readl() would be a kind of dma_rmb(), if you will.
Yes, that's correct - but it's orthogonal to "cache coherent".
> I suspect the docs are wrong about what dma-coherent means.
Not "wrong", just misunderstood. ;^)
hth,
grant
next prev parent reply other threads:[~2004-03-08 6:18 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-10-27 22:35 serious 2.6 bug in USB subsystem? David Mosberger
2003-10-28 1:30 ` Greg KH
2003-10-28 3:00 ` David Mosberger
2003-10-30 15:11 ` [linux-usb-devel] " David Brownell
2003-10-30 20:15 ` David Mosberger
[not found] ` <16289.55171.278494.17172@napali.hpl.hp.com>
2003-10-31 16:23 ` David Brownell
2003-10-31 18:34 ` David Mosberger
2003-10-31 18:50 ` Valdis.Kletnieks
2003-10-31 19:28 ` David Brownell
2003-10-31 19:50 ` David Mosberger
2003-10-31 20:06 ` David S. Miller
2004-03-06 2:08 ` David Mosberger
2004-03-06 2:13 ` David Mosberger
2004-03-06 4:55 ` David Brownell
2004-03-06 5:49 ` David Mosberger
2004-03-06 7:21 ` David Mosberger
2004-03-06 8:39 ` David Mosberger
2004-03-06 16:37 ` David Brownell
2004-03-08 6:18 ` Grant Grundler [this message]
2004-03-08 18:58 ` David Mosberger
2004-03-08 21:48 ` David Brownell
2004-03-09 9:15 ` David Mosberger
2004-03-09 17:36 ` David Brownell
2004-03-09 17:58 ` David Mosberger
2004-03-09 20:39 ` David Brownell
2004-03-09 23:32 ` David Mosberger
2004-03-10 2:53 ` David Brownell
2004-03-10 6:11 ` David Mosberger
2004-03-10 6:59 ` David Mosberger
2004-03-10 7:52 ` Wouter Lueks
2004-03-10 16:49 ` David Mosberger
2004-03-10 19:49 ` Wouter Lueks
2004-03-10 16:22 ` David Brownell
2004-03-10 18:04 ` David Mosberger
2004-03-11 2:43 ` David Brownell
2004-03-11 5:35 ` David Mosberger
2004-03-10 19:29 ` Colin Leroy
2004-03-06 9:17 ` [linux-usb-devel] " David Mosberger
2004-03-06 17:30 ` David Brownell
2004-03-07 13:48 ` Matthias Andree
2004-03-08 18:49 ` David Mosberger
2003-11-03 3:46 ` David Brownell
2003-11-03 21:25 ` David Mosberger
2004-03-03 12:33 ` Wouter Lueks
2004-03-03 15:30 ` Wouter Lueks
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=20040308061802.GA25960@cup.hp.com \
--to=iod00d@hp.com \
--cc=david-b@pacbell.net \
--cc=davidm@hpl.hp.com \
--cc=greg@kroah.com \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-usb-devel@lists.sourceforge.net \
--cc=pochini@shiny.it \
--cc=vojtech@suse.cz \
/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).