Performance improvement: use a write combining store
instead of a regular mmio write to update queue tail
registers.
Signed-off-by: Radu Nicolau <radu.nico...@intel.com>
Acked-by: Bruce Richardson <bruce.richard...@intel.com>
---
v4: include ack
drivers/net/i40e/base/i40e_osdep.h | 6 ++++++
drivers/net/i40e/i40e_rxtx.c | 8 ++++----
drivers/net/i40e/i40e_rxtx_vec_avx2.c | 4 ++--
drivers/net/i40e/i40e_rxtx_vec_sse.c | 4 ++--
4 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/net/i40e/base/i40e_osdep.h
b/drivers/net/i40e/base/i40e_osdep.h
index 58be396..df414fd 100644
--- a/drivers/net/i40e/base/i40e_osdep.h
+++ b/drivers/net/i40e/base/i40e_osdep.h
@@ -138,6 +138,12 @@ static inline uint32_t i40e_read_addr(volatile void *addr)
#define I40E_PCI_REG_WRITE_RELAXED(reg, value) \
rte_write32_relaxed((rte_cpu_to_le_32(value)), reg)
+#define I40E_PCI_REG_WC_WRITE(queue, reg, value) \
+ rte_write32_wc((rte_cpu_to_le_32(value)), reg)
+#define I40E_PCI_REG_WC_WRITE_RELAXED(queue, reg, value) \
+ rte_write32_wc_relaxed((rte_cpu_to_le_32(value)), reg)
+
+
#define I40E_WRITE_FLUSH(a) I40E_READ_REG(a, I40E_GLGEN_STAT)
#define I40EVF_WRITE_FLUSH(a) I40E_READ_REG(a, I40E_VFGEN_RSTAT)
diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index 840b6f3..64e43ac 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -760,7 +760,7 @@ i40e_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts)
if (nb_hold > rxq->rx_free_thresh) {
rx_id = (uint16_t) ((rx_id == 0) ?
(rxq->nb_rx_desc - 1) : (rx_id - 1));
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ I40E_PCI_REG_WC_WRITE(rxq, rxq->qrx_tail, rx_id);
nb_hold = 0;
}
rxq->nb_rx_hold = nb_hold;
@@ -938,7 +938,7 @@ i40e_recv_scattered_pkts(void *rx_queue,
if (nb_hold > rxq->rx_free_thresh) {
rx_id = (uint16_t)(rx_id == 0 ?
(rxq->nb_rx_desc - 1) : (rx_id - 1));
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ I40E_PCI_REG_WC_WRITE(rxq, rxq->qrx_tail, rx_id);
nb_hold = 0;
}
rxq->nb_rx_hold = nb_hold;
@@ -1249,7 +1249,7 @@ i40e_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts)
(unsigned) tx_id, (unsigned) nb_tx);
rte_cio_wmb();
- I40E_PCI_REG_WRITE_RELAXED(txq->qtx_tail, tx_id);
+ I40E_PCI_REG_WC_WRITE_RELAXED(txq, txq->qtx_tail, tx_id);
txq->tx_tail = tx_id;
return nb_tx;
@@ -1400,7 +1400,7 @@ tx_xmit_pkts(struct i40e_tx_queue *txq,
txq->tx_tail = 0;
/* Update the tx tail register */
- I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ I40E_PCI_REG_WC_WRITE(txq, txq->qtx_tail, txq->tx_tail);
return nb_pkts;
}
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
index 3bcef13..294c1c4 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
@@ -134,7 +134,7 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
/* Update the tail pointer on the NIC */
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ I40E_PCI_REG_WC_WRITE(rxq, rxq->qrx_tail, rx_id);
}
#ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
@@ -921,7 +921,7 @@ i40e_xmit_fixed_burst_vec_avx2(void *tx_queue, struct
rte_mbuf **tx_pkts,
txq->tx_tail = tx_id;
- I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ I40E_PCI_REG_WC_WRITE(txq, txq->qtx_tail, txq->tx_tail);
return nb_pkts;
}
diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c
b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index 6985183..a4635e0 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c
@@ -86,7 +86,7 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
/* Update the tail pointer on the NIC */
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ I40E_PCI_REG_WC_WRITE(rxq, rxq->qrx_tail, rx_id);
}
#ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
@@ -733,7 +733,7 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf
**tx_pkts,
txq->tx_tail = tx_id;
- I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ I40E_PCI_REG_WC_WRITE(txq, txq->qtx_tail, txq->tx_tail);
return nb_pkts;
}
--
2.7.4
