[PATCH v4 19/24] net/i40e: use vector SW ring for all vector paths

[Bruce Richardson <bruce.richardson@intel.com>]

The AVX-512 code path used a smaller SW ring structure only containing
the mbuf pointer, but no other fields. The other fields are only used in
the scalar code path, so update all vector driver code paths (AVX2, SSE,
Neon, Altivec) to use the smaller, faster structure.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
 drivers/net/i40e/i40e_rxtx.c             |  8 +++++---
 drivers/net/i40e/i40e_rxtx_vec_altivec.c | 12 ++++++------
 drivers/net/i40e/i40e_rxtx_vec_avx2.c    | 12 ++++++------
 drivers/net/i40e/i40e_rxtx_vec_avx512.c  | 14 ++------------
 drivers/net/i40e/i40e_rxtx_vec_common.h  |  6 ------
 drivers/net/i40e/i40e_rxtx_vec_neon.c    | 12 ++++++------
 drivers/net/i40e/i40e_rxtx_vec_sse.c     | 12 ++++++------
 7 files changed, 31 insertions(+), 45 deletions(-)

diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index 081d743e62..745c467912 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -1891,7 +1891,7 @@ i40e_dev_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 			    tx_queue_id);
 
 	txq->vector_tx = ad->tx_vec_allowed;
-	txq->vector_sw_ring = ad->tx_use_avx512;
+	txq->vector_sw_ring = txq->vector_tx;
 
 	/*
 	 * tx_queue_id is queue id application refers to, while
@@ -3550,9 +3550,11 @@ i40e_set_tx_function(struct rte_eth_dev *dev)
 		}
 	}
 
+	if (rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_128)
+		ad->tx_vec_allowed = false;
+
 	if (ad->tx_simple_allowed) {
-		if (ad->tx_vec_allowed &&
-		    rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128) {
+		if (ad->tx_vec_allowed) {
 #ifdef RTE_ARCH_X86
 			if (ad->tx_use_avx512) {
 #ifdef CC_AVX512_SUPPORT
diff --git a/drivers/net/i40e/i40e_rxtx_vec_altivec.c b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
index 500bba2cef..b6900a3e15 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_altivec.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
@@ -553,14 +553,14 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 {
 	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
 	volatile struct i40e_tx_desc *txdp;
-	struct ci_tx_entry *txep;
+	struct ci_tx_entry_vec *txep;
 	uint16_t n, nb_commit, tx_id;
 	uint64_t flags = I40E_TD_CMD;
 	uint64_t rs = I40E_TX_DESC_CMD_RS | I40E_TD_CMD;
 	int i;
 
 	if (txq->nb_tx_free < txq->tx_free_thresh)
-		i40e_tx_free_bufs(txq);
+		ci_tx_free_bufs_vec(txq, i40e_tx_desc_done, false);
 
 	nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
 	nb_commit = nb_pkts;
@@ -569,13 +569,13 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	tx_id = txq->tx_tail;
 	txdp = &txq->i40e_tx_ring[tx_id];
-	txep = &txq->sw_ring[tx_id];
+	txep = &txq->sw_ring_vec[tx_id];
 
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
 
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
-		ci_tx_backlog_entry(txep, tx_pkts, n);
+		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
 
 		for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
 			vtx1(txdp, *tx_pkts, flags);
@@ -589,10 +589,10 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 		/* avoid reach the end of ring */
 		txdp = &txq->i40e_tx_ring[tx_id];
-		txep = &txq->sw_ring[tx_id];
+		txep = &txq->sw_ring_vec[tx_id];
 	}
 
-	ci_tx_backlog_entry(txep, tx_pkts, nb_commit);
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_commit);
 
 	vtx(txdp, tx_pkts, nb_commit, flags);
 
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
index 29bef64287..2477573c01 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
@@ -745,13 +745,13 @@ i40e_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 {
 	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
 	volatile struct i40e_tx_desc *txdp;
-	struct ci_tx_entry *txep;
+	struct ci_tx_entry_vec *txep;
 	uint16_t n, nb_commit, tx_id;
 	uint64_t flags = I40E_TD_CMD;
 	uint64_t rs = I40E_TX_DESC_CMD_RS | I40E_TD_CMD;
 
 	if (txq->nb_tx_free < txq->tx_free_thresh)
-		i40e_tx_free_bufs(txq);
+		ci_tx_free_bufs_vec(txq, i40e_tx_desc_done, false);
 
 	nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
 	if (unlikely(nb_pkts == 0))
@@ -759,13 +759,13 @@ i40e_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	tx_id = txq->tx_tail;
 	txdp = &txq->i40e_tx_ring[tx_id];
-	txep = &txq->sw_ring[tx_id];
+	txep = &txq->sw_ring_vec[tx_id];
 
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
 
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
-		ci_tx_backlog_entry(txep, tx_pkts, n);
+		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
 
 		vtx(txdp, tx_pkts, n - 1, flags);
 		tx_pkts += (n - 1);
@@ -780,10 +780,10 @@ i40e_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 		/* avoid reach the end of ring */
 		txdp = &txq->i40e_tx_ring[tx_id];
-		txep = &txq->sw_ring[tx_id];
+		txep = &txq->sw_ring_vec[tx_id];
 	}
 
-	ci_tx_backlog_entry(txep, tx_pkts, nb_commit);
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_commit);
 
 	vtx(txdp, tx_pkts, nb_commit, flags);
 
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx512.c b/drivers/net/i40e/i40e_rxtx_vec_avx512.c
index c555c3491d..2497e6a8f0 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx512.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx512.c
@@ -807,16 +807,6 @@ vtx(volatile struct i40e_tx_desc *txdp,
 	}
 }
 
-static __rte_always_inline void
-tx_backlog_entry_avx512(struct ci_tx_entry_vec *txep,
-			struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
-{
-	int i;
-
-	for (i = 0; i < (int)nb_pkts; ++i)
-		txep[i].mbuf = tx_pkts[i];
-}
-
 static inline uint16_t
 i40e_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 				 uint16_t nb_pkts)
@@ -844,7 +834,7 @@ i40e_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
-		tx_backlog_entry_avx512(txep, tx_pkts, n);
+		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
 
 		vtx(txdp, tx_pkts, n - 1, flags);
 		tx_pkts += (n - 1);
@@ -862,7 +852,7 @@ i40e_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 		txep = (void *)txq->sw_ring;
 	}
 
-	tx_backlog_entry_avx512(txep, tx_pkts, nb_commit);
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_commit);
 
 	vtx(txdp, tx_pkts, nb_commit, flags);
 
diff --git a/drivers/net/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h
index 907d32dd0b..733dc797cd 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_common.h
+++ b/drivers/net/i40e/i40e_rxtx_vec_common.h
@@ -24,12 +24,6 @@ i40e_tx_desc_done(struct ci_tx_queue *txq, uint16_t idx)
 				rte_cpu_to_le_64(I40E_TX_DESC_DTYPE_DESC_DONE);
 }
 
-static __rte_always_inline int
-i40e_tx_free_bufs(struct ci_tx_queue *txq)
-{
-	return ci_tx_free_bufs(txq, i40e_tx_desc_done);
-}
-
 static inline void
 _i40e_rx_queue_release_mbufs_vec(struct i40e_rx_queue *rxq)
 {
diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index c97f337e43..b398d66154 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -681,14 +681,14 @@ i40e_xmit_fixed_burst_vec(void *__rte_restrict tx_queue,
 {
 	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
 	volatile struct i40e_tx_desc *txdp;
-	struct ci_tx_entry *txep;
+	struct ci_tx_entry_vec *txep;
 	uint16_t n, nb_commit, tx_id;
 	uint64_t flags = I40E_TD_CMD;
 	uint64_t rs = I40E_TX_DESC_CMD_RS | I40E_TD_CMD;
 	int i;
 
 	if (txq->nb_tx_free < txq->tx_free_thresh)
-		i40e_tx_free_bufs(txq);
+		ci_tx_free_bufs_vec(txq, i40e_tx_desc_done, false);
 
 	nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
 	if (unlikely(nb_pkts == 0))
@@ -696,13 +696,13 @@ i40e_xmit_fixed_burst_vec(void *__rte_restrict tx_queue,
 
 	tx_id = txq->tx_tail;
 	txdp = &txq->i40e_tx_ring[tx_id];
-	txep = &txq->sw_ring[tx_id];
+	txep = &txq->sw_ring_vec[tx_id];
 
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
 
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
-		ci_tx_backlog_entry(txep, tx_pkts, n);
+		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
 
 		for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
 			vtx1(txdp, *tx_pkts, flags);
@@ -716,10 +716,10 @@ i40e_xmit_fixed_burst_vec(void *__rte_restrict tx_queue,
 
 		/* avoid reach the end of ring */
 		txdp = &txq->i40e_tx_ring[tx_id];
-		txep = &txq->sw_ring[tx_id];
+		txep = &txq->sw_ring_vec[tx_id];
 	}
 
-	ci_tx_backlog_entry(txep, tx_pkts, nb_commit);
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_commit);
 
 	vtx(txdp, tx_pkts, nb_commit, flags);
 
diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index 2c467e2089..90c57e59d0 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c
@@ -700,14 +700,14 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 {
 	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
 	volatile struct i40e_tx_desc *txdp;
-	struct ci_tx_entry *txep;
+	struct ci_tx_entry_vec *txep;
 	uint16_t n, nb_commit, tx_id;
 	uint64_t flags = I40E_TD_CMD;
 	uint64_t rs = I40E_TX_DESC_CMD_RS | I40E_TD_CMD;
 	int i;
 
 	if (txq->nb_tx_free < txq->tx_free_thresh)
-		i40e_tx_free_bufs(txq);
+		ci_tx_free_bufs_vec(txq, i40e_tx_desc_done, false);
 
 	nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
 	if (unlikely(nb_pkts == 0))
@@ -715,13 +715,13 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	tx_id = txq->tx_tail;
 	txdp = &txq->i40e_tx_ring[tx_id];
-	txep = &txq->sw_ring[tx_id];
+	txep = &txq->sw_ring_vec[tx_id];
 
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
 
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
-		ci_tx_backlog_entry(txep, tx_pkts, n);
+		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
 
 		for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
 			vtx1(txdp, *tx_pkts, flags);
@@ -735,10 +735,10 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 		/* avoid reach the end of ring */
 		txdp = &txq->i40e_tx_ring[tx_id];
-		txep = &txq->sw_ring[tx_id];
+		txep = &txq->sw_ring_vec[tx_id];
 	}
 
-	ci_tx_backlog_entry(txep, tx_pkts, nb_commit);
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_commit);
 
 	vtx(txdp, tx_pkts, nb_commit, flags);
 
-- 
2.43.0