On Wed, Jun 22, 2022 at 4:15 AM Ciara Loftus <ciara.loftus@xxxxxxxxx> wrote:
>
> Similar to how it's done in the ice driver since 'eb087cd82864 ("ice:
> propagate xdp_ring onto rx_ring")', read the XDP program once per NAPI
> instead of once per descriptor cleaned. I measured an improvement in
> throughput of 2% for the AF_XDP xdpsock l2fwd benchmark in busy polling
> mode on my platform.
>
Should the same improvement be made to i40e_run_xdp/i40e_clean_rx_irq for the
non-AF_XDP case?
> Signed-off-by: Ciara Loftus <ciara.loftus@xxxxxxxxx>
> ---
> drivers/net/ethernet/intel/i40e/i40e_xsk.c | 16 +++++++++-------
> 1 file changed, 9 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> index af3e7e6afc85..2f422c61ac11 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> @@ -146,17 +146,13 @@ int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
> *
> * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
> **/
> -static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
> +static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp,
> + struct bpf_prog *xdp_prog)
> {
> int err, result = I40E_XDP_PASS;
> struct i40e_ring *xdp_ring;
> - struct bpf_prog *xdp_prog;
> u32 act;
>
> - /* NB! xdp_prog will always be !NULL, due to the fact that
> - * this path is enabled by setting an XDP program.
> - */
> - xdp_prog = READ_ONCE(rx_ring->xdp_prog);
> act = bpf_prog_run_xdp(xdp_prog, xdp);
>
> if (likely(act == XDP_REDIRECT)) {
> @@ -339,9 +335,15 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
> u16 next_to_clean = rx_ring->next_to_clean;
> u16 count_mask = rx_ring->count - 1;
> unsigned int xdp_res, xdp_xmit = 0;
> + struct bpf_prog *xdp_prog;
> bool failure = false;
> u16 cleaned_count;
>
> + /* NB! xdp_prog will always be !NULL, due to the fact that
> + * this path is enabled by setting an XDP program.
> + */
> + xdp_prog = READ_ONCE(rx_ring->xdp_prog);
> +
> while (likely(total_rx_packets < (unsigned int)budget)) {
> union i40e_rx_desc *rx_desc;
> unsigned int rx_packets;
> @@ -378,7 +380,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
> xsk_buff_set_size(bi, size);
> xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
>
> - xdp_res = i40e_run_xdp_zc(rx_ring, bi);
> + xdp_res = i40e_run_xdp_zc(rx_ring, bi, xdp_prog);
> i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
> &rx_bytes, size, xdp_res, &failure);
> if (failure)
> --
> 2.25.1
>
