From: Matthew Dharm <mdharm-kernel@one-eyed-alien.net>
To: Pete Zaitcev <zaitcev@redhat.com>
Cc: "David S. Miller" <davem@redhat.com>,
Scott Wood <scott@timesys.com>,
oliver@neukum.org, greg@kroah.com, arjanv@redhat.com,
jgarzik@redhat.com, tburke@redhat.com,
linux-kernel@vger.kernel.org, stern@rowland.harvard.edu,
david-b@pacbell.net
Subject: Re: drivers/block/ub.c
Date: Mon, 28 Jun 2004 16:52:34 -0700 [thread overview]
Message-ID: <20040628235234.GD8502@one-eyed-alien.net> (raw)
In-Reply-To: <20040628140157.5813bc73@lembas.zaitcev.lan>
[-- Attachment #1: Type: text/plain, Size: 2242 bytes --]
On Mon, Jun 28, 2004 at 02:01:57PM -0700, Pete Zaitcev wrote:
> On Mon, 28 Jun 2004 13:50:58 -0700
> Matthew Dharm <mdharm-kernel@one-eyed-alien.net> wrote:
>
> > > struct txd {
> > > u32 dma_addr;
> > > u32 length;
> > > };
> > >
> > > It is just total and utter madness to put a packed or the proposed
> > > __nopadding__ attribute on that structure. Yet this seems to be
> > > what was suggested now and at the beginning of this thread.
> >
> > I guess, in the end, what this comes down to is the fact that we're all
> > going to get bitten on the ass when we finally get to a platform where the
> > default alignment is 64-bits, which would then (by default) add padding to
> > the above structure.
> >
> > How long until that time comes? Likely within my lifetime, and I'd rather
> > not have to re-write working code into more working code because I couldn't
> > express to the compiler what I needed it to do.
>
> I, for one, am not engaging into such flights of fancy as a platform
> with larger than natural alignment requirements. Would you even read
> what you're writing? The whole freaking world abandons silly platforms
> and moves to x86 extensions and you're fantasizing about a return
> to Cray-1. It just ain't happening!
Actually, I've been working with a controller for the last several months
(the "latest and greatest", state-of-the-art technology), which can only to
loads/stores in 64-byte units at a minimum.
Yes, I mean "byte". 128-bits wide * 4 DDR beats (2 dobule-edged clocks).
There are no DM pins on the memory interface, so any write less than that
size must be a read-modify-write.
And, I was just having a conversation with a compiler group which was
considering moving to 64-byte alignment as a speed optimization for this
platform, or at least 16-byte (64 bit), which also aligns well with the
native load/store of the CPU involved.
I only wish I was fantasizing about this.
Matt
--
Matthew Dharm Home: mdharm-usb@one-eyed-alien.net
Maintainer, Linux USB Mass Storage Driver
P: Nine more messages in admin.policy.
M: I know, I'm typing as fast as I can!
-- Pitr and Mike
User Friendly, 11/27/97
[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]
next prev parent reply other threads:[~2004-06-28 23:52 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-06-26 20:06 drivers/block/ub.c Pete Zaitcev
2004-06-26 20:12 ` drivers/block/ub.c Matthew Dharm
2004-06-27 2:08 ` drivers/block/ub.c Pete Zaitcev
2004-06-27 3:30 ` drivers/block/ub.c Matthew Dharm
2004-07-12 0:10 ` [usb-storage] drivers/block/ub.c Pat LaVarre
2004-06-26 20:35 ` drivers/block/ub.c Oliver Neukum
2004-06-26 21:41 ` drivers/block/ub.c David S. Miller
2004-06-26 21:56 ` drivers/block/ub.c Oliver Neukum
2004-06-26 22:07 ` drivers/block/ub.c David S. Miller
2004-06-26 22:36 ` drivers/block/ub.c Oliver Neukum
2004-06-26 23:20 ` drivers/block/ub.c David S. Miller
2004-06-27 4:31 ` drivers/block/ub.c Oliver Neukum
2004-06-27 6:34 ` drivers/block/ub.c David S. Miller
2004-06-27 10:42 ` drivers/block/ub.c Oliver Neukum
2004-06-27 21:26 ` drivers/block/ub.c David S. Miller
2004-06-28 14:15 ` drivers/block/ub.c Scott Wood
2004-06-28 20:25 ` drivers/block/ub.c David S. Miller
2004-06-28 20:48 ` drivers/block/ub.c Scott Wood
2004-06-28 20:58 ` drivers/block/ub.c David S. Miller
2004-06-28 20:50 ` drivers/block/ub.c Matthew Dharm
2004-06-28 20:59 ` drivers/block/ub.c David S. Miller
2004-06-28 21:01 ` drivers/block/ub.c Pete Zaitcev
2004-06-28 23:52 ` Matthew Dharm [this message]
2004-06-28 20:57 ` drivers/block/ub.c Oliver Neukum
2004-06-28 21:03 ` drivers/block/ub.c David S. Miller
2004-06-28 21:18 ` drivers/block/ub.c Scott Wood
2004-06-28 22:22 ` drivers/block/ub.c David S. Miller
2004-06-28 22:31 ` drivers/block/ub.c Scott Wood
2004-06-28 22:40 ` drivers/block/ub.c Roland Dreier
2004-06-29 1:54 ` drivers/block/ub.c Robert White
2004-06-29 2:15 ` drivers/block/ub.c David S. Miller
2004-06-29 2:49 ` drivers/block/ub.c Robert White
2004-06-29 18:31 ` drivers/block/ub.c Andy Isaacson
2004-07-05 10:01 ` drivers/block/ub.c Roman Zippel
2004-06-29 7:12 ` drivers/block/ub.c Vojtech Pavlik
2004-06-29 1:39 ` drivers/block/ub.c Robert White
2004-06-29 17:02 ` drivers/block/ub.c Kurt Garloff
2004-06-26 22:54 ` drivers/block/ub.c Andries Brouwer
2004-06-26 22:59 ` drivers/block/ub.c Oliver Neukum
2004-06-26 23:08 ` drivers/block/ub.c Andries Brouwer
2004-06-27 5:04 ` drivers/block/ub.c Oliver Neukum
2004-06-27 14:08 ` drivers/block/ub.c Andries Brouwer
2004-06-27 14:24 ` drivers/block/ub.c Oliver Neukum
2004-06-27 15:19 ` drivers/block/ub.c Alan Stern
2004-06-27 15:45 ` drivers/block/ub.c Andries Brouwer
2004-06-28 23:58 ` drivers/block/ub.c Jeff Garzik
2004-06-28 0:10 ` drivers/block/ub.c Pete Zaitcev
2004-06-28 16:01 ` drivers/block/ub.c Alan Stern
2004-06-27 15:23 ` drivers/block/ub.c Andries Brouwer
2004-06-27 16:11 ` drivers/block/ub.c Oliver Neukum
2004-06-26 22:46 ` drivers/block/ub.c Oliver Neukum
2004-06-27 3:52 ` drivers/block/ub.c Alan Stern
2004-06-27 4:05 ` drivers/block/ub.c Alan Stern
2004-06-27 5:02 ` drivers/block/ub.c Greg KH
2004-06-27 15:23 ` drivers/block/ub.c Alan Stern
2004-06-27 20:29 ` drivers/block/ub.c Pete Zaitcev
2004-06-27 21:03 ` drivers/block/ub.c Matthew Dharm
2004-06-28 15:40 ` drivers/block/ub.c Alan Stern
2004-06-28 16:42 ` drivers/block/ub.c Oliver Neukum
2004-06-28 19:50 ` drivers/block/ub.c Alan Stern
2004-06-27 5:35 ` drivers/block/ub.c Matthew Dharm
2004-06-27 15:28 ` drivers/block/ub.c Alan Stern
2004-06-27 22:56 ` drivers/block/ub.c David Brownell
2004-06-27 23:43 ` drivers/block/ub.c Pete Zaitcev
2004-06-28 15:05 ` drivers/block/ub.c David Brownell
2004-06-28 15:56 ` drivers/block/ub.c Alan Stern
2004-06-28 16:23 ` drivers/block/ub.c David Brownell
2004-06-28 16:46 ` drivers/block/ub.c Oliver Neukum
2004-06-28 17:13 ` drivers/block/ub.c David Brownell
[not found] ` <mailman.1088290201.14081.linux-kernel2news@redhat.com>
2004-06-27 23:57 ` drivers/block/ub.c Pete Zaitcev
2004-06-29 11:05 ` drivers/block/ub.c Jeff Garzik
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=20040628235234.GD8502@one-eyed-alien.net \
--to=mdharm-kernel@one-eyed-alien.net \
--cc=arjanv@redhat.com \
--cc=davem@redhat.com \
--cc=david-b@pacbell.net \
--cc=greg@kroah.com \
--cc=jgarzik@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=oliver@neukum.org \
--cc=scott@timesys.com \
--cc=stern@rowland.harvard.edu \
--cc=tburke@redhat.com \
--cc=zaitcev@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox