WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Xen

xen-devel

[Top] [All Lists]

[Xen-devel] Re: mthca use of dma_sync_single is bogus

To: Roland Dreier <rdreier@xxxxxxxxx>
Subject: [Xen-devel] Re: mthca use of dma_sync_single is bogus
From: Lukas Hejtmanek <xhejtman@xxxxxxxxxxx>
Date: 2007年7月10日 21:36:26 +0200
Cc: Keir Fraser <keir@xxxxxxxxxxxxx>, xen-devel@xxxxxxxxxxxxxxxxxxx, "Michael S. Tsirkin" <mst@xxxxxxxxxxxxxxxxxx>, general@xxxxxxxxxxxxxxxxxxxxx
Delivery-date: 2007年7月10日 12:33:22 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <adafy3w9i5p.fsf@xxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
References: <adalkdpxopo.fsf@xxxxxxxxx> <20070709213913.GB20052@xxxxxxxxxxxxxx> <adamyy4vjo9.fsf@xxxxxxxxx> <20070710141409.GH3885@xxxxxxxxxxx> <ada7ip8b0be.fsf@xxxxxxxxx> <20070710190018.GK3885@xxxxxxxxxxx> <adak5t89iv8.fsf@xxxxxxxxx> <20070710191639.GL3885@xxxxxxxxxxx> <adafy3w9i5p.fsf@xxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: Mutt/1.5.16 (2007年06月11日)
On Tue, Jul 10, 2007 at 12:24:02PM -0700, Roland Dreier wrote:
> Sorry, I was a little confusing. The implementations may be different
> but in general there is no real difference between consistent and
> coherent memory. Using either pci_alloc_consistent() or
> dma_alloc_coherent() will exhaust the same small pool of address space
> on powerpc 4xx for example.
I thought that consistent only refers to physically contiguous area whereas
coherent refers to memory where no barrier need to be used. But I may be
wrong.
Anyway, with my patch, I can turn off swiotlb and I'm still able to load
ib_mthca cleanly in DomU. On the other hand, Xen bug me about DMA bug in
ib_ipoib, there may be another problem with dma_sync_single().
> Seems pretty ugly, especially given that Xen is not upstream. I think
> the Xen tree should just carry such patches, at least until Xen is
> merged. Even then I'm quite dubious about having two code paths for this.
OK, I will keep it for my own.
-- 
Lukáš Hejtmánek
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
<Prev in Thread] Current Thread [Next in Thread>
Previous by Date: [Xen-devel] Re: mthca use of dma_sync_single is bogus , Lukas Hejtmanek
Next by Date: Re: [Xen-devel] [RFC][PATCH 2/2] Add hcall to probe Xen heap , Ryan Harper
Previous by Thread: [Xen-devel] Re: mthca use of dma_sync_single is bogus , Roland Dreier
Next by Thread: [Xen-devel] Re: mthca use of dma_sync_single is bogus , Michael S. Tsirkin
Indexes: [Date] [Thread] [Top] [All Lists]

Copyright ©, Citrix Systems Inc. All rights reserved. Legal and Privacy
Citrix This site is hosted by Citrix

AltStyle によって変換されたページ (->オリジナル) /