[lkml]   [2011]   [Apr]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH] OMAP: iommu flush page table entries from L1 and L2 cache
On Fri, Apr 15, 2011 at 11:24:16AM +0900, KyongHo Cho wrote:
> That means we need to translate logical to physical address and it is
> sometimes not trivial.

What do you mean "sometimes not trivial" ? The DMA does nothing more
than virt_to_phys(virt) to get the physical address. It's _that_ simple.

If virt_to_phys(virt) is likely to fail, there's protection in the DMA API
to BUG_ON() in that case.

> Finally, the kernel will contain many similar routines that do same thing.

So when we get coherent DMA, you won't care that the DMA API functions
start doing nothing with caches?

 \ /
  Last update: 2011-04-15 10:15    [W:0.506 / U:1.332 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site