Re: [PATCH net-next 3/3] net: stmmac: Introducing support for Page Pool

[Ilias Apalodimas]

On Thu, Jul 04, 2019 at 10:13:37AM +0000, Jose Abreu wrote:
> From: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
> 
> > The page_pool DMA mapping cannot be "kept" when page traveling into the
> > network stack attached to an SKB.  (Ilias and I have a long term plan[1]
> > to allow this, but you cannot do it ATM).
> 
> The reason I recycle the page is this previous call to:
> 
> 	skb_copy_to_linear_data()
> 
> So, technically, I'm syncing to CPU the page(s) and then memcpy to a 
> previously allocated SKB ... So it's safe to just recycle the mapping I 
> think.
> 
> Its kind of using bounce buffers and I do see performance gain in this 
> (I think the reason is because my setup uses swiotlb for DMA mapping).

Maybe. Have you tested this on big/small packets?
Can you do a test with 64b/128b and 1024b for example?
The memcpy might be cheap for the small sized packets (and cheaper than the dma
map/unmap)

> 
> Anyway, I'm open to some suggestions on how to improve this ...
> 
> > Also remember that the page_pool requires you driver to do the DMA-sync
> > operation.  I see a dma_sync_single_for_cpu(), but I didn't see a
> > dma_sync_single_for_device() (well, I noticed one getting removed).
> > (For some HW Ilias tells me that the dma_sync_single_for_device can be
> > elided, so maybe this can still be correct for you).
> 
> My HW just needs descriptors refilled which are in different coherent 
> region so I don't see any reason for dma_sync_single_for_device() ...
I am abit overloaded at the moment. I'll try to have a look at this and get back
to you

Cheers
/Ilias