Re: [PATCH v3 net-next 08/14] mlx4: use order-0 pages for RX

On Mon, Feb 13, 2017 at 1:09 PM, Eric Dumazet [off-list ref] wrote:

On Mon, Feb 13, 2017 at 12:51 PM, Alexander Duyck
[off-list ref] wrote:

quoted

On Mon, Feb 13, 2017 at 11:58 AM, Eric Dumazet [off-list ref] wrote:

quoted

quoted

+                              PAGE_SIZE, priv->dma_dir);
                page = page_alloc->page;
                /* Revert changes done by mlx4_alloc_pages */
-               page_ref_sub(page, page_alloc->page_size /
+               page_ref_sub(page, PAGE_SIZE /
                                   priv->frag_info[i].frag_stride - 1);
                put_page(page);
                page_alloc->page = NULL;

You can probably simplify this by using __page_frag_cache_drain since
that way you can just doe the sub and test for the whole set instead
of doing N - 1 and 1.

Well, we remove this anyway in following patch ;)

Any plans to add the bulk page count updates back at some point?  I
just got around to adding it for igb in commit bd4171a5d4c2 ("igb:
update code to better handle incrementing page count").  I should have
patches for ixgbe, i40e, and i40evf here pretty soon.  That was one of
the reasons why I implemented __page_frag_cache_drain in the first
place.  As I'm sure Jesper will probably point out the atomic op for
get_page/page_ref_inc can be pretty expensive if I recall correctly.

- Alex