Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1498204

Re: igb driver can cause cache invalidation of non-owned memory?

Show all headers | View raw

>> With this scheme, page used for Rx is completely dma_map()ed at
>> allocation time, split into two buffers, and individual buffer is
>> sync_to_cpu()ed AND PASSED TO NETWORK STACK via skb_add_rx_frag() -
>> while driver driver still uses other buffer. Later, when driver decides
>> to no longer use this page, it will dma_unmap() it completely - which on
>> archs with non-coherent caches means cache invalidation. This cache
>> invalidation will include area that is already passed elsewhere.
> 
> This should happen only if the device wrote into that piece of the
> memory which it absolutely should not.

Hmm...  I'm not about device writing to memory.


Sequence in igb driver is:

dma_map(full_page)
  <device writes here>
sync_to_cpu(half_page);
skb_add_rx_frag(skb, half_page);
napi_gro_receive(skb);
  ...
dma_unmap(full_page)

What I'm concerned about is - same area is first passed up to network
stack, and _later_ dma_unmap()ed.  Is this indeed safe?


Nikita

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-10 11:00 +0200
  Re: igb driver can cause cache invalidation of non-owned memory? David Miller <davem@davemloft.net> - 2016-10-10 11:10 +0200
    Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-10 12:00 +0200
      Re: igb driver can cause cache invalidation of non-owned memory? David Miller <davem@davemloft.net> - 2016-10-10 14:00 +0200
        Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-10 14:30 +0200
          Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-10 14:40 +0200
          Re: igb driver can cause cache invalidation of non-owned memory? Alexander Duyck <alexander.duyck@gmail.com> - 2016-10-10 17:20 +0200
            Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-10 19:10 +0200
              Re: igb driver can cause cache invalidation of non-owned memory? Alexander Duyck <alexander.duyck@gmail.com> - 2016-10-10 19:50 +0200
                Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-12 09:00 +0200
                Re: igb driver can cause cache invalidation of non-owned memory? Alexander Duyck <alexander.duyck@gmail.com> - 2016-10-12 17:40 +0200
                RE: igb driver can cause cache invalidation of non-owned memory? David Laight <David.Laight@ACULAB.COM> - 2016-10-12 18:10 +0200
                Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-12 18:40 +0200
                Re: igb driver can cause cache invalidation of non-owned memory? Alexander Duyck <alexander.duyck@gmail.com> - 2016-10-12 20:10 +0200
                Re: igb driver can cause cache invalidation of non-owned memory? Nikita Yushchenko <nikita.yoush@cogentembedded.com> - 2016-10-12 20:30 +0200
                Re: igb driver can cause cache invalidation of non-owned memory? Alexander Duyck <alexander.duyck@gmail.com> - 2016-10-12 20:40 +0200

csiph-web