On Mon, 2017-05-29 at 17:27 +0200, Paolo Abeni wrote:
> when udp_recvmsg() is executed, on x86_64 and other archs, most skb
> fields are on cold cachelines.
> If the skb are linear and the kernel don't need to compute the udp
> csum, only a handful of skb fields are required by udp_recvmsg().
> Since we already use skb->dev_scratch to cache hot data, and
> there are 32 bits unused on 64 bit archs, use such field to cache
> as much data as we can, and try to prefetch on dequeue the relevant
> fields that are left out.
>
> This can save up to 2 cache miss per packet.
okay ;)
>
> Signed-off-by: Paolo Abeni <pab...@redhat.com>
> ---
> net/ipv4/udp.c | 114
> +++++++++++++++++++++++++++++++++++++++++++++++++++------
> 1 file changed, 103 insertions(+), 11 deletions(-)
>
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 53fa48d..616132e 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -1163,6 +1163,83 @@ int udp_sendpage(struct sock *sk, struct page *page,
> int offset,
> return ret;
> }
>
> +/* Copy as much information as possible into skb->dev_scratch to avoid
> + * possibly multiple cache miss on dequeue();
> + */
> +#if BITS_PER_LONG == 64
> +
> +/* we can store multiple info here: truesize, len and the bit needed to
> + * compute skb_csum_unnecessary will be on cold cache lines at recvmsg
> + * time.
> + * skb->len can be stored on 16 bits since the udp header has been already
> + * validated and pulled.
> + */
> +struct udp_dev_scratch {
> + __u32 truesize;
> + __u16 len;
> + __u16 is_linear:1;
> + __u16 csum_unnecessary:1;
What about
u32 truesize;
u16 len;
bool is_linear;
bool csum_unnecessary;
I do not believe the __ prefix is necessary for a local structure (not
uapi)
Also a plain bool or u8 is faster than a bit field (shorter
instructions)
Thanks.
