Messages in this thread Patch in this message | | | Subject | Re: [RFC 0/2] fix dma_map_sg not to do barriers for each buffer | From | Catalin Marinas <> | Date | Thu, 11 Feb 2010 10:53:05 +0000 |
| |
On Thu, 2010-02-11 at 10:45 +0000, Catalin Marinas wrote: > On Wed, 2010-02-10 at 21:21 +0000, Russell King - ARM Linux wrote: > > @@ -345,6 +347,7 @@ static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, > > BUG_ON(!valid_dma_direction(dir)); > > > > __dma_single_cpu_to_dev(cpu_addr, size, dir); > > + __dma_barrier(dir); > > > > return virt_to_dma(dev, cpu_addr); > > } > > The ___dma_single_cpu_to_dev() covers both inner and outer caches but I > haven't seen it touched by this patch (nor the other you posted). When > you clean the L1 cache, you need to make sure that there is a barrier > (DSB) so that it completes before cleaning the L2, otherwise you clean > the L2 but data keeps coming from L1.
Actually after L2 maintenance we don't even need the __dma_barrier(), we need an outer_cache.sync() function.
I can do the outer cache optimisations together with a few others for PL310 (which does not require the cache_wait() call for line operations).
-- Catalin
| |