CQEs are not cache line aligned, which can cause cache conflicts when
polling Rx CQs under high-PPS load.
This patch checks CQ producer/consumer indices before processing packets,
reducing cache conflicts. The added MMIO read overhead is minor
compared to the latency caused by cache conflicts, improving observed
small-packet performance.
Signed-off-by: Rong Qian <qi...@yunsilicon.com>
Signed-off-by: Renyong Wan <wa...@yunsilicon.com>
---
drivers/net/xsc/xsc_defs.h | 2 ++
drivers/net/xsc/xsc_rx.c | 18 ++++++++++++++++--
drivers/net/xsc/xsc_rx.h | 1 +
drivers/net/xsc/xsc_vfio.c | 2 +-
4 files changed, 20 insertions(+), 3 deletions(-)
diff --git a/drivers/net/xsc/xsc_defs.h b/drivers/net/xsc/xsc_defs.h
index 4b95a0521d..73941901e7 100644
--- a/drivers/net/xsc/xsc_defs.h
+++ b/drivers/net/xsc/xsc_defs.h
@@ -46,10 +46,12 @@
#define XSC_PF_TX_DB_ADDR 0x4802000
#define XSC_PF_RX_DB_ADDR 0x4804000
#define XSC_PF_CQ_DB_ADDR 0x2120000
+#define XSC_PF_CQ_PID_START_ADDR 0x2080000
#define XSC_VF_RX_DB_ADDR 0x8d4
#define XSC_VF_TX_DB_ADDR 0x8d0
#define XSC_VF_CQ_DB_ADDR 0x8c4
+#define XSC_VF_CQ_PID_START_ADDR 0x60000
#define XSC_HIF_CMDQM_VECTOR_ID_MEM_ADDR 0x1034000
diff --git a/drivers/net/xsc/xsc_rx.c b/drivers/net/xsc/xsc_rx.c
index 332ceb9606..5f8003a1f6 100644
--- a/drivers/net/xsc/xsc_rx.c
+++ b/drivers/net/xsc/xsc_rx.c
@@ -83,6 +83,16 @@ xsc_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts,
uint16_t pkts_n)
int cqe_msg_len = 0;
volatile struct xsc_cqe_u64 *cqe_u64 = NULL;
struct rte_mbuf *rep;
+ uint16_t cq_pi;
+ uint16_t cqe_pkts_n = 0;
+
+ if (rxq->cq_pi != NULL) {
+ cq_pi = (*(volatile uint32_t *)(rxq->cq_pi)) & 0xFFFF;
+ if (cq_pi == rxq->cq_ci)
+ return 0;
+ cqe_pkts_n = (uint16_t)((cq_pi - rxq->cq_ci) & 0xFFFF);
+ pkts_n = pkts_n < cqe_pkts_n ? pkts_n : cqe_pkts_n;
+ }
while (pkts_n) {
uint32_t idx = rq_ci & wqe_m;
@@ -463,12 +473,16 @@ xsc_rss_qp_create(struct xsc_ethdev_priv *priv, int
port_id)
}
rxq_data->wqes = rxq_data->rq_pas->addr;
- if (!xsc_dev_is_vf(xdev))
+ if (!xsc_dev_is_vf(xdev)) {
rxq_data->rq_db = (uint32_t *)((uint8_t
*)xdev->bar_addr +
XSC_PF_RX_DB_ADDR);
- else
+ rxq_data->cq_pi = (uint32_t *)((uint8_t
*)xdev->bar_addr +
+ XSC_PF_CQ_PID_START_ADDR +
rxq_data->cqn * 4);
+ } else {
rxq_data->rq_db = (uint32_t *)((uint8_t
*)xdev->bar_addr +
XSC_VF_RX_DB_ADDR);
+ rxq_data->cq_pi = NULL;
+ }
rxq_data->qpn = rqn_base + i;
xsc_dev_modify_qp_status(xdev, rxq_data->qpn, 1,
XSC_CMD_OP_RTR2RTS_QP);
diff --git a/drivers/net/xsc/xsc_rx.h b/drivers/net/xsc/xsc_rx.h
index 90fbb89197..59cbbb5141 100644
--- a/drivers/net/xsc/xsc_rx.h
+++ b/drivers/net/xsc/xsc_rx.h
@@ -31,6 +31,7 @@ struct __rte_cache_aligned xsc_rxq_data {
uint16_t rsv0:4;
volatile uint32_t *rq_db;
volatile uint32_t *cq_db;
+ volatile uint32_t *cq_pi;
uint32_t rq_ci;
uint32_t rq_pi;
uint16_t cq_ci;
diff --git a/drivers/net/xsc/xsc_vfio.c b/drivers/net/xsc/xsc_vfio.c
index 1650a3ab2b..c233728c5f 100644
--- a/drivers/net/xsc/xsc_vfio.c
+++ b/drivers/net/xsc/xsc_vfio.c
@@ -562,7 +562,7 @@ xsc_vfio_rx_cq_create(struct xsc_dev *xdev, struct
xsc_rx_cq_params *cq_params,
PMD_DRV_LOG(WARNING, "Port %u rxq %u: cq numa_node=%u, device
numa_node=%u",
port_id, idx, cq_params->socket_id, numa_node);
- cqe_n = cq_params->wqe_s;
+ cqe_n = cq_params->wqe_s * 2;
log_cq_sz = rte_log2_u32(cqe_n);
cqe_total_sz = cqe_n * sizeof(struct xsc_cqe);
pa_num = (cqe_total_sz + XSC_PAGE_SIZE - 1) / XSC_PAGE_SIZE;
--
2.25.1
