On Monday 12 November 2007 16:26:37 Muli Ben-Yehuda wrote: > On Wed, Nov 07, 2007 at 04:21:06PM +0200, Amit Shah wrote: > > Of all the DMA calls, only dma_alloc_coherent might not actually > > call dma_ops->alloc_coherent. We make sure that gets called if the > > device that's being worked on is a PV device > > I always thougt that's a mess... the reason it's done this way is that > Andi Kleen preferred it for some reason at the time. How about trying > to fix it cleanly so that dma_alloc_coherent always gets called rather > than adding a hack to work around a hack? It will require auditing all > of the different x86 dma-ops but I can help with that.
Hmm, nice to know it's like that just because of "not necessary now". Fixing this along with stacking dma_ops and making 32-bit also dma_ops-ready will greatly simplify things. > > Cheers, > Muli ------------------------------------------------------------------------- This SF.net email is sponsored by: Splunk Inc. Still grepping through log files to find problems? Stop. Now Search log events and configuration files using AJAX and a browser. Download your FREE copy of Splunk now >> http://get.splunk.com/ _______________________________________________ kvm-devel mailing list kvm-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/kvm-devel
