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)
to use the smaller, faster structure.
Signed-off-by: Bruce Richardson <bruce.richard...@intel.com>
---
drivers/net/iavf/iavf_rxtx.c | 7 -------
drivers/net/iavf/iavf_rxtx_vec_avx2.c | 12 ++++++------
drivers/net/iavf/iavf_rxtx_vec_avx512.c | 8 --------
drivers/net/iavf/iavf_rxtx_vec_common.h | 6 ------
drivers/net/iavf/iavf_rxtx_vec_sse.c | 14 +++++++-------
5 files changed, 13 insertions(+), 34 deletions(-)
diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index f0ab881ac5..6692f6992b 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -4193,14 +4193,7 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
txq = dev->data->tx_queues[i];
if (!txq)
continue;
-#ifdef CC_AVX512_SUPPORT
- if (use_avx512)
- iavf_txq_vec_setup_avx512(txq);
- else
- iavf_txq_vec_setup(txq);
-#else
iavf_txq_vec_setup(txq);
-#endif
}
if (no_poll_on_link_down) {
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
index fdb98b417a..b847886081 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
@@ -1736,14 +1736,14 @@ iavf_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 iavf_tx_desc *txdp;
- struct ci_tx_entry *txep;
+ struct ci_tx_entry_vec *txep;
uint16_t n, nb_commit, tx_id;
/* bit2 is reserved and must be set to 1 according to Spec */
uint64_t flags = IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_ICRC;
uint64_t rs = IAVF_TX_DESC_CMD_RS | flags;
if (txq->nb_tx_free < txq->tx_free_thresh)
- iavf_tx_free_bufs(txq);
+ ci_tx_free_bufs_vec(txq, iavf_tx_desc_done, false);
nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
if (unlikely(nb_pkts == 0))
@@ -1752,13 +1752,13 @@ iavf_xmit_fixed_burst_vec_avx2(void *tx_queue, struct
rte_mbuf **tx_pkts,
tx_id = txq->tx_tail;
txdp = &txq->iavf_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);
iavf_vtx(txdp, tx_pkts, n - 1, flags, offload);
tx_pkts += (n - 1);
@@ -1773,10 +1773,10 @@ iavf_xmit_fixed_burst_vec_avx2(void *tx_queue, struct
rte_mbuf **tx_pkts,
/* avoid reach the end of ring */
txdp = &txq->iavf_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);
iavf_vtx(txdp, tx_pkts, nb_commit, flags, offload);
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx512.c
b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
index 007759e451..641f3311eb 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx512.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
@@ -2357,14 +2357,6 @@ iavf_xmit_pkts_vec_avx512(void *tx_queue, struct
rte_mbuf **tx_pkts,
return iavf_xmit_pkts_vec_avx512_cmn(tx_queue, tx_pkts, nb_pkts, false);
}
-int __rte_cold
-iavf_txq_vec_setup_avx512(struct ci_tx_queue *txq)
-{
- txq->vector_tx = true;
- txq->vector_sw_ring = true;
- return 0;
-}
-
uint16_t
iavf_xmit_pkts_vec_avx512_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts)
diff --git a/drivers/net/iavf/iavf_rxtx_vec_common.h
b/drivers/net/iavf/iavf_rxtx_vec_common.h
index 6f94587eee..c69399a173 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_common.h
+++ b/drivers/net/iavf/iavf_rxtx_vec_common.h
@@ -24,12 +24,6 @@ iavf_tx_desc_done(struct ci_tx_queue *txq, uint16_t idx)
rte_cpu_to_le_64(IAVF_TX_DESC_DTYPE_DESC_DONE);
}
-static __rte_always_inline int
-iavf_tx_free_bufs(struct ci_tx_queue *txq)
-{
- return ci_tx_free_bufs(txq, iavf_tx_desc_done);
-}
-
static inline void
_iavf_rx_queue_release_mbufs_vec(struct iavf_rx_queue *rxq)
{
diff --git a/drivers/net/iavf/iavf_rxtx_vec_sse.c
b/drivers/net/iavf/iavf_rxtx_vec_sse.c
index 3adf2a59e4..9f7db80bfd 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_sse.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_sse.c
@@ -1368,14 +1368,14 @@ iavf_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 iavf_tx_desc *txdp;
- struct ci_tx_entry *txep;
+ struct ci_tx_entry_vec *txep;
uint16_t n, nb_commit, tx_id;
uint64_t flags = IAVF_TX_DESC_CMD_EOP | 0x04; /* bit 2 must be set */
uint64_t rs = IAVF_TX_DESC_CMD_RS | flags;
int i;
if (txq->nb_tx_free < txq->tx_free_thresh)
- iavf_tx_free_bufs(txq);
+ ci_tx_free_bufs_vec(txq, iavf_tx_desc_done, false);
nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
if (unlikely(nb_pkts == 0))
@@ -1384,13 +1384,13 @@ iavf_xmit_fixed_burst_vec(void *tx_queue, struct
rte_mbuf **tx_pkts,
tx_id = txq->tx_tail;
txdp = &txq->iavf_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);
@@ -1404,10 +1404,10 @@ iavf_xmit_fixed_burst_vec(void *tx_queue, struct
rte_mbuf **tx_pkts,
/* avoid reach the end of ring */
txdp = &txq->iavf_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);
iavf_vtx(txdp, tx_pkts, nb_commit, flags);
@@ -1462,7 +1462,7 @@ int __rte_cold
iavf_txq_vec_setup(struct ci_tx_queue *txq)
{
txq->vector_tx = true;
- txq->vector_sw_ring = false;
+ txq->vector_sw_ring = txq->vector_tx;
return 0;
}
--
2.43.0
