Messages in this thread | | | Date | Tue, 28 Oct 2008 11:47:05 +0100 | From | Takashi Iwai <> | Subject | Re: swiotlb_alloc_coherent: allocated memory is out of range for device |
| |
At Tue, 28 Oct 2008 11:39:02 +0100, Ingo Molnar wrote: > > > * Takashi Iwai <tiwai@suse.de> wrote: > > > At Thu, 23 Oct 2008 12:15:57 +0200, > > Ingo Molnar wrote: > > > > > > > > > * Takashi Iwai <tiwai@suse.de> wrote: > > > > > > > At Thu, 23 Oct 2008 07:22:09 +0200, > > > > I wrote: > > > > > > > > > > > The current dma_alloc_coherent (asm-x86/dma-mapping.h) handles the gfp > > > > > > flags in the exact same way as the old dma_alloc_coherent > > > > > > (pci-dma.c). Neither sets GFP_DMA even if coherent_dma_mask is > > > > > > 24bits. The old code is fine because of the GFP_DMA retry > > > > > > mechanism. But if coherent_dma_mask is 24bits, there is no point to go > > > > > > into the GFP_DMA retry mechanism. We should use GFP_DMA in the first > > > > > > place. > > > > > > > > > > > > How about the following patch? > > > > > > > > > > I'll give it a try later (the machine is in my office). > > > > > > > > The patch seems working fine. Thanks! > > > > > > > > Tested-by: Takashi Iwai <tiwai@suse.de> > > > > > > thanks guys - i've queued it up in tip/core/urgent and will send a pull > > > request to Linus later today. > > > > Ingo, what is the status about these patches? > > They don't appear in rc2. > > Will send it today-ish. -rc2 was strictly for brown paperbag bugs > crashing more than half of all testsystems.
OK, thanks!
Takashi
| |