x86: pci-dma.c: use __GFP_NO_OOM instead of __GFP_NORETRY

On Wed, 2008-05-28 at 04:47 +0200, Andi Kleen wrote:
> > So...  why not just remove the setting of __GFP_NORETRY?  Why is it
> > wrong to oom-kill things in this case?
>
> When the 16MB zone overflows (which can be common in some workloads)
> calling the OOM killer is pretty useless because it has barely any
> real user data [only exception would be the "only 16MB" case Alan
> mentioned]. Killing random processes in this case is bad.
>
> I think for 16MB __GFP_NORETRY is ok because there should be
> nothing freeable in there so looping is useless. Only exception would be the
> "only 16MB total" case again but I'm not sure 2.6 supports that at all
> on x86.
>
> On the other hand d_a_c() does more allocations than just 16MB, especially
> on 64bit and the other zones need different strategies.

Okay, so how about this then ?

Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index c5ef1af8e79de6883b005cfa99d59bb9164e978c..069e843f0b9304abd4e51041c49a7e5fa50c87b8 100644 (file)
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -397,9 +397,6 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
        if (dev->dma_mask == NULL)
                return NULL;
 
-       /* Don't invoke OOM killer */
-       gfp |= __GFP_NORETRY;
-
 #ifdef CONFIG_X86_64
        /* Why <=? Even when the mask is smaller than 4GB it is often
           larger than 16MB and in this case we have a chance of
@@ -410,7 +407,9 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 #endif
 
  again:
-       page = dma_alloc_pages(dev, gfp, get_order(size));
+       /* Don't invoke OOM killer or retry in lower 16MB DMA zone */
+       page = dma_alloc_pages(dev,
+               (gfp & GFP_DMA) ? gfp | __GFP_NORETRY : gfp, get_order(size));
        if (page == NULL)
                return NULL;