From 904a04a1f7205856ff30d2e8f48e50c9fefc2d76 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 9 Aug 2024 08:58:58 -0700 Subject: [PATCH] net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings BugLink: https://bugs.launchpad.net/bugs/2084005 commit 58a63729c957621f1990c3494c702711188ca347 upstream. After napi_complete_done() is called when NAPI is polling in the current process context, another NAPI may be scheduled and start running in softirq on another CPU and may ring the doorbell before the current CPU does. When combined with unnecessary rings when there is no need to arm the CQ, it triggers error paths in the hardware. This patch fixes this by calling napi_complete_done() after doorbell rings. It limits the number of unnecessary rings when there is no need to arm. MANA hardware specifies that there must be one doorbell ring every 8 CQ wraparounds. This driver guarantees one doorbell ring as soon as the number of consumed CQEs exceeds 4 CQ wraparounds. In practical workloads, the 4 CQ wraparounds proves to be big enough that it rarely exceeds this limit before all the napi weight is consumed. To implement this, add a per-CQ counter cq->work_done_since_doorbell, and make sure the CQ is armed as soon as passing 4 wraparounds of the CQ. Cc: stable@vger.kernel.org Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ") Reviewed-by: Haiyang Zhang Signed-off-by: Long Li Link: https://patch.msgid.link/1723219138-29887-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman Signed-off-by: Koichiro Den Signed-off-by: Stefan Bader --- drivers/net/ethernet/microsoft/mana/mana_en.c | 22 ++++++++++++------- include/net/mana/mana.h | 1 + 2 files changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 99dae14e2c65..3d910bb3efdd 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1779,7 +1779,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1790,16 +1789,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; + cq->work_done_since_doorbell += w; - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 4eeedf14711b..76114acfce26 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -274,6 +274,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; };