From: Andrea Arcangeli <andrea@suse.de>
To: Andrew Morton <andrewm@uow.edu.au>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
Richard Henderson <rth@twiddle.net>,
linux-kernel@vger.kernel.org
Subject: Re: alpha iommu fixes
Date: Sun, 20 May 2001 16:33:23 +0200 [thread overview]
Message-ID: <20010520163323.G18119@athlon.random> (raw)
In-Reply-To: <20010518214617.A701@jurassic.park.msu.ru> <20010519155502.A16482@athlon.random> <20010519231131.A2840@jurassic.park.msu.ru>, <20010519231131.A2840@jurassic.park.msu.ru>; <20010520044013.A18119@athlon.random> <3B07AF49.5A85205F@uow.edu.au>, <3B07AF49.5A85205F@uow.edu.au>; <20010520154958.E18119@athlon.random> <3B07CF20.2ABB5468@uow.edu.au>
In-Reply-To: <3B07CF20.2ABB5468@uow.edu.au>; from andrewm@uow.edu.au on Mon, May 21, 2001 at 12:05:20AM +1000
On Mon, May 21, 2001 at 12:05:20AM +1000, Andrew Morton wrote:
> Andrea Arcangeli wrote:
> >
> > [ cc'ed to l-k ]
> >
> > > DMA-mapping.txt assumes that it cannot fail.
> >
> > DMA-mapping.txt is wrong. Both pci_map_sg and pci_map_single failed if
> > they returned zero. You either have to drop the skb or to try again later
> > if they returns zero.
> >
>
> Well this is news to me. No drivers understand this.
Yes, almost all drivers are buggy.
> How long has this been the case? What platforms?
Always and all platforms.
Just think about this, you have 2^32 of bus address space, and you
theoritically can start I/O for more than 2^32 of phys memory, see?
Whatever platform it is it will never be able to guarantee all mappings
to succeed.
> For netdevices at least, the pci_map_single() call is always close
> to the site of the skb allocation. So what we can do is to roll
> them together and use the existing oom-handling associated with alloc_skb(),
> assuming the driver has it...
Fine.
Andrea
next prev parent reply other threads:[~2001-05-20 14:34 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-05-18 17:46 alpha iommu fixes Ivan Kokshaysky
2001-05-19 2:34 ` Tom Vier
2001-05-19 10:48 ` Ivan Kokshaysky
2001-05-19 20:58 ` Tom Vier
2001-05-19 13:55 ` Andrea Arcangeli
2001-05-19 19:11 ` Ivan Kokshaysky
2001-05-20 2:40 ` Andrea Arcangeli
2001-05-20 12:12 ` Ivan Kokshaysky
2001-05-20 13:40 ` Andrea Arcangeli
2001-05-20 14:23 ` Gérard Roudier
[not found] ` <3B07AF49.5A85205F@uow.edu.au>
2001-05-20 13:49 ` Andrea Arcangeli
2001-05-20 14:05 ` Andrew Morton
2001-05-20 14:33 ` Andrea Arcangeli [this message]
2001-05-21 1:01 ` David S. Miller
2001-05-21 1:47 ` Andrea Arcangeli
2001-05-21 7:05 ` David S. Miller
2001-05-21 8:59 ` Andrea Arcangeli
2001-05-21 9:02 ` David S. Miller
2001-05-21 9:23 ` Andi Kleen
2001-05-21 9:30 ` David S. Miller
2001-05-21 9:42 ` Andi Kleen
2001-05-21 10:00 ` David S. Miller
2001-05-21 10:27 ` Andi Kleen
2001-05-21 10:34 ` David S. Miller
2001-05-21 10:42 ` Andi Kleen
2001-05-21 10:55 ` David S. Miller
2001-05-21 11:08 ` Andi Kleen
2001-05-21 11:36 ` David S. Miller
2001-05-21 11:41 ` Andi Kleen
2001-05-21 22:22 ` Jens Axboe
2001-05-21 10:02 ` Andrea Arcangeli
2001-05-21 10:17 ` Alan Cox
2001-05-21 9:56 ` Andrea Arcangeli
2001-05-21 10:11 ` David S. Miller
2001-05-21 10:19 ` David S. Miller
2001-05-21 11:00 ` Andrea Arcangeli
2001-05-21 11:04 ` David S. Miller
2001-05-21 11:27 ` Andrea Arcangeli
2001-05-21 12:16 ` Peter Rival
2001-05-21 13:55 ` Jonathan Lundell
2001-05-21 14:17 ` Ivan Kokshaysky
2001-05-21 15:47 ` Jonathan Lundell
2001-05-22 11:12 ` Chris Wedgwood
2001-05-22 17:51 ` Jonathan Lundell
2001-05-21 10:50 ` Andrea Arcangeli
2001-05-21 10:59 ` David S. Miller
2001-05-21 11:19 ` Andrea Arcangeli
2001-05-21 11:51 ` Ivan Kokshaysky
2001-05-21 17:53 ` Richard Henderson
2001-05-22 0:56 ` Andrea Arcangeli
2001-05-22 14:29 ` Andrea Arcangeli
2001-05-22 14:44 ` Ivan Kokshaysky
2001-05-22 15:00 ` Andrea Arcangeli
2001-05-22 20:28 ` Richard Henderson
2001-05-22 20:40 ` Jeff Garzik
2001-05-22 20:52 ` Andrea Arcangeli
2001-05-22 20:57 ` Richard Henderson
2001-05-22 21:09 ` Alan Cox
2001-05-22 20:48 ` Jonathan Lundell
2001-05-22 21:02 ` Richard Henderson
2001-05-22 21:10 ` Alan Cox
2001-05-22 21:17 ` Jonathan Lundell
2001-05-22 21:24 ` Alan Cox
2001-05-22 21:34 ` Jonathan Lundell
2001-05-22 21:08 ` Alan Cox
2001-05-22 15:18 ` Andrea Arcangeli
2001-05-22 15:55 ` Ivan Kokshaysky
2001-05-22 16:06 ` Andrea Arcangeli
2001-05-22 13:22 ` Andrea Arcangeli
2001-05-21 9:50 ` Gerd Knorr
2001-05-21 1:00 ` David S. Miller
2001-05-21 7:47 ` Alan Cox
2001-05-21 7:53 ` David S. Miller
2001-05-21 8:03 ` Alan Cox
2001-05-21 8:11 ` David S. Miller
2001-05-20 16:18 ` Andrea Arcangeli
2001-05-20 16:21 ` Andrew Morton
2001-05-20 16:44 ` Andrea Arcangeli
2001-05-20 16:54 ` Andrew Morton
2001-05-20 17:12 ` Andrea Arcangeli
2001-05-21 1:07 ` David S. Miller
2001-05-21 1:37 ` Andrea Arcangeli
2001-05-21 6:53 ` David S. Miller
2001-05-21 7:59 ` Alan Cox
2001-05-21 8:09 ` David S. Miller
2001-05-21 8:09 ` Alan Cox
2001-05-21 8:06 ` Chris Wedgwood
2001-05-23 0:05 ` Albert D. Cahalan
2001-05-22 13:11 ` Pavel Machek
2001-05-22 23:02 ` David S. Miller
2001-05-20 17:16 ` Jeff Garzik
2001-05-20 17:37 ` Andrea Arcangeli
2001-05-21 1:03 ` David S. Miller
2001-05-21 1:58 ` Richard Henderson
2001-05-20 1:11 ` Richard Henderson
2001-05-20 12:05 ` Ivan Kokshaysky
2001-05-21 0:37 ` Richard Henderson
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=20010520163323.G18119@athlon.random \
--to=andrea@suse.de \
--cc=andrewm@uow.edu.au \
--cc=ink@jurassic.park.msu.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=rth@twiddle.net \
/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