On Thu, May 22, 2025 at 2:43 PM Tariq Toukan <tariqt@xxxxxxxxxx> wrote:
>
> From: Dragos Tatulea <dtatulea@xxxxxxxxxx>
>
> Allow drivers that have moved over to netmem to do fragment coalescing.
>
> Signed-off-by: Dragos Tatulea <dtatulea@xxxxxxxxxx>
> Signed-off-by: Cosmin Ratiu <cratiu@xxxxxxxxxx>
> Signed-off-by: Tariq Toukan <tariqt@xxxxxxxxxx>
> ---
> include/linux/skbuff.h | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
>
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index 5520524c93bf..e8e2860183b4 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -3887,6 +3887,18 @@ static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
> return false;
> }
>
> +static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i,
> + const netmem_ref netmem, int off)
> +{
> + if (i) {
> + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
> +
> + return netmem == skb_frag_netmem(frag) &&
> + off == skb_frag_off(frag) + skb_frag_size(frag);
> + }
> + return false;
> +}
> +
Can we limit the code duplication by changing skb_can_coalesce to call
skb_can_coalesce_netmem? Or is that too bad for perf?
static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const
struct page *page, int off) {
skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off);
}
It's always safe to cast a page to netmem.
--
Thanks,
Mina
