net/mlx5e: Poll XDP TX CQ before RX CQ

Handle XDP TX completions before handling RX packets, to make sure more
free space is available for XDP TX packets a moment before handling
RX packets.

Performance improvement:
System: Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz

Test case              Before     Now      improvement
---------------------------------------------------------------
XDP Drop (1 core)      16.9Mpps  16.9Mpps    No change
XDP TX   (1 core)      12Mpps    13Mpps      8%

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 9beeb4a1212f4852bbbb212b405102e639372986..c880022bb21af915a956e45beecf3924fba7a534 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -118,12 +118,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
        for (i = 0; i < c->num_tc; i++)
                busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
-       work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
-       busy |= work_done == budget;
-
        if (c->xdp)
                busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
 
+       work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
+       busy |= work_done == budget;
+
        mlx5e_poll_ico_cq(&c->icosq.cq);
 
        busy |= mlx5e_post_rx_wqes(&c->rq);