From da4e8648079eb6f26f3a88d8c34270a057e2bfe6 Mon Sep 17 00:00:00 2001 From: Long Li Date: Mon, 17 Jul 2023 12:35:38 -0700 Subject: [PATCH] net: mana: Batch ringing RX queue doorbell on receiving packets It's inefficient to ring the doorbell page every time a WQE is posted to the received queue. Excessive MMIO writes result in CPU spending more time waiting on LOCK instructions (atomic operations), resulting in poor scaling performance. Move the code for ringing doorbell page to where after we have posted all WQEs to the receive queue during a callback from napi_poll(). With this change, tests showed an improvement from 120G/s to 160G/s on a 200G physical link, with 16 or 32 hardware queues. Tests showed no regression in network latency benchmarks on single connection. Reviewed-by: Haiyang Zhang Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1689622539-5334-2-git-send-email-longli@linuxonhyperv.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a499e46..ac2acc9 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1386,8 +1386,8 @@ static void mana_post_pkt_rxq(struct mana_rxq *rxq) recv_buf_oob = &rxq->rx_oobs[curr_index]; - err = mana_gd_post_and_ring(rxq->gdma_rq, &recv_buf_oob->wqe_req, - &recv_buf_oob->wqe_inf); + err = mana_gd_post_work_request(rxq->gdma_rq, &recv_buf_oob->wqe_req, + &recv_buf_oob->wqe_inf); if (WARN_ON_ONCE(err)) return; @@ -1657,6 +1657,12 @@ static void mana_poll_rx_cq(struct mana_cq *cq) mana_process_rx_cqe(rxq, cq, &comp[i]); } + if (comp_read > 0) { + struct gdma_context *gc = rxq->gdma_rq->gdma_dev->gdma_context; + + mana_gd_wq_ring_doorbell(gc, rxq->gdma_rq); + } + if (rxq->xdp_flush) xdp_do_flush(); } -- 2.7.4