[RFC PATCH v3] arm DMA: Fix allocation from CMA for coherent DMA

On Mon, Jun 29, 2015 at 11:37:37AM +0100, Catalin Marinas wrote:

I forgot about the arm_dma_mmap fix here:

https://lkml.org/lkml/2015/5/7/512

So we either fix both cases by changing __get_dma_pgprot() or just go
for Mike's and your patches as above. It's up to Russell.

I'd prefer the "least code" option. :)

At some point, we could do with some more clean-up in the dma-mapping.c.
For example, both __alloc_simple_buffer() and __alloc_from_contiguous()
end up calling __dma_clear_buffer() even when not necessary (cacheable
mapping). Not too bad though as this is only done when setting up the
buffer.

The reason we always clear the buffer is that we can't be sure that a
driver will not map a buffer allocated by dma_alloc_coherent() into
userspace without it first being initialised.  There have been drivers
which do this (ALSA in particular.)  I haven't checked whether this
instance still does this, but it used to - and the problem is once
one instance exists, it gets copied...

If it isn't initialised, userspace gets access to whatever data was in
that page prior to the allocation, which could be something like your
root password, or bank details, some other sensitive data.

So, removing the clearing probably opens a rather large security hole.

-- 
FTTC broadband for 0.8mile line: currently at 10.5Mbps down 400kbps up
according to speedtest.net.