From: Joerg Roedel <joro@8bytes.org>
To: Prarit Bhargava <prarit@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
jbarnes@virtuousgeek.org, fujita.tomonori@lab.ntt.co.jp
Subject: Re: [PATCH]: PCI: GART iommu alignment fixes [v2]
Date: Thu, 24 Jul 2008 00:10:33 +0200 [thread overview]
Message-ID: <20080723221033.GD13662@8bytes.org> (raw)
In-Reply-To: <20080723111928.15828.42561.sendpatchset@prarit.bos.redhat.com>
On Wed, Jul 23, 2008 at 07:19:43AM -0400, Prarit Bhargava wrote:
> pci_alloc_consistent/dma_alloc_coherent does not return size aligned
> addresses.
>
> >From Documentation/DMA-mapping.txt:
>
> "pci_alloc_consistent returns two values: the virtual address which you
> can use to access it from the CPU and dma_handle which you pass to the
> card.
>
> The cpu return address and the DMA bus master address are both
> guaranteed to be aligned to the smallest PAGE_SIZE order which
> is greater than or equal to the requested size. This invariant
> exists (for example) to guarantee that if you allocate a chunk
> which is smaller than or equal to 64 kilobytes, the extent of the
> buffer you receive will not cross a 64K boundary."
Interesting. Have you experienced any problems because of that
misbehavior in the GART code? AMD IOMMU currently also violates this
requirement. I will send a patch to fix that there too.
Joerg
next prev parent reply other threads:[~2008-07-23 22:10 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-23 11:19 [PATCH]: PCI: GART iommu alignment fixes [v2] Prarit Bhargava
2008-07-23 22:10 ` Joerg Roedel [this message]
2008-07-23 23:14 ` FUJITA Tomonori
2008-07-23 23:47 ` Prarit Bhargava
2008-07-24 7:46 ` Joerg Roedel
2008-07-24 10:09 ` Prarit Bhargava
2008-07-24 10:34 ` FUJITA Tomonori
2008-07-24 12:37 ` Joerg Roedel
2008-07-24 12:49 ` Prarit Bhargava
2008-07-24 13:32 ` FUJITA Tomonori
2008-07-24 14:31 ` Prarit Bhargava
2008-07-24 14:40 ` FUJITA Tomonori
2008-07-24 15:13 ` Prarit Bhargava
2008-07-24 14:45 ` Prarit Bhargava
2008-07-28 22:23 ` Jesse Barnes
2008-07-29 14:24 ` Prarit Bhargava
2008-07-29 17:08 ` Jesse Barnes
2008-07-30 0:43 ` FUJITA Tomonori
2008-08-06 12:29 ` Prarit Bhargava
2008-08-06 13:23 ` Prarit Bhargava
2008-08-06 13:35 ` FUJITA Tomonori
2008-08-06 14:32 ` Prarit Bhargava
2008-08-07 17:03 ` Jesse Barnes
2008-08-07 17:41 ` Prarit Bhargava
2008-08-08 7:12 ` Muli Ben-Yehuda
2008-08-08 15:18 ` Prarit Bhargava
2008-08-08 16:15 ` Jesse Barnes
2008-08-08 21:13 ` FUJITA Tomonori
2008-08-09 1:40 ` Prarit Bhargava
2008-08-09 3:50 ` FUJITA Tomonori
2008-08-15 16:16 ` Ingo Molnar
2008-08-15 18:00 ` Ingo Molnar
2008-08-15 20:39 ` Prarit Bhargava
2008-08-15 21:20 ` Ingo Molnar
2008-08-16 1:15 ` FUJITA Tomonori
2008-08-17 12:56 ` Ingo Molnar
2008-08-17 15:36 ` FUJITA Tomonori
2008-08-17 15:42 ` Ingo Molnar
2008-08-17 15:48 ` FUJITA Tomonori
2008-08-17 15:54 ` FUJITA Tomonori
2008-08-07 17:45 ` Prarit Bhargava
2008-07-23 23:23 ` FUJITA Tomonori
2008-07-23 23:24 ` Prarit Bhargava
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=20080723221033.GD13662@8bytes.org \
--to=joro@8bytes.org \
--cc=fujita.tomonori@lab.ntt.co.jp \
--cc=jbarnes@virtuousgeek.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=prarit@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 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.