[dpdk-dev] [PATCH v4 5/6] net/cnxk: enable TSO processing in vector Tx

[<pbhagavatula@marvell.com>]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Enable TSO offload in vector Tx burst function.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 drivers/net/cnxk/cn10k_tx.c     |  2 +-
 drivers/net/cnxk/cn10k_tx.h     | 97 +++++++++++++++++++++++++++++++++
 drivers/net/cnxk/cn10k_tx_vec.c |  5 +-
 drivers/net/cnxk/cn9k_tx.c      |  2 +-
 drivers/net/cnxk/cn9k_tx.h      | 94 ++++++++++++++++++++++++++++++++
 drivers/net/cnxk/cn9k_tx_vec.c  |  5 +-
 6 files changed, 199 insertions(+), 6 deletions(-)

diff --git a/drivers/net/cnxk/cn10k_tx.c b/drivers/net/cnxk/cn10k_tx.c
index c4c3e6570..d06879163 100644
--- a/drivers/net/cnxk/cn10k_tx.c
+++ b/drivers/net/cnxk/cn10k_tx.c
@@ -67,7 +67,7 @@ cn10k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
 #undef T
 	};
 
-	if (dev->scalar_ena || (dev->tx_offload_flags & NIX_TX_OFFLOAD_TSO_F))
+	if (dev->scalar_ena)
 		pick_tx_func(eth_dev, nix_eth_tx_burst);
 	else
 		pick_tx_func(eth_dev, nix_eth_tx_vec_burst);
diff --git a/drivers/net/cnxk/cn10k_tx.h b/drivers/net/cnxk/cn10k_tx.h
index 8af6799ff..26797581e 100644
--- a/drivers/net/cnxk/cn10k_tx.h
+++ b/drivers/net/cnxk/cn10k_tx.h
@@ -689,6 +689,46 @@ cn10k_nix_xmit_pkts_mseg(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 #if defined(RTE_ARCH_ARM64)
 
+static __rte_always_inline void
+cn10k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
+		      union nix_send_ext_w0_u *w0, uint64_t ol_flags,
+		      const uint64_t flags, const uint64_t lso_tun_fmt)
+{
+	uint16_t lso_sb;
+	uint64_t mask;
+
+	if (!(ol_flags & PKT_TX_TCP_SEG))
+		return;
+
+	mask = -(!w1->il3type);
+	lso_sb = (mask & w1->ol4ptr) + (~mask & w1->il4ptr) + m->l4_len;
+
+	w0->u |= BIT(14);
+	w0->lso_sb = lso_sb;
+	w0->lso_mps = m->tso_segsz;
+	w0->lso_format = NIX_LSO_FORMAT_IDX_TSOV4 + !!(ol_flags & PKT_TX_IPV6);
+	w1->ol4type = NIX_SENDL4TYPE_TCP_CKSUM;
+
+	/* Handle tunnel tso */
+	if ((flags & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F) &&
+	    (ol_flags & PKT_TX_TUNNEL_MASK)) {
+		const uint8_t is_udp_tun =
+			(CNXK_NIX_UDP_TUN_BITMASK >>
+			 ((ol_flags & PKT_TX_TUNNEL_MASK) >> 45)) &
+			0x1;
+		uint8_t shift = is_udp_tun ? 32 : 0;
+
+		shift += (!!(ol_flags & PKT_TX_OUTER_IPV6) << 4);
+		shift += (!!(ol_flags & PKT_TX_IPV6) << 3);
+
+		w1->il4type = NIX_SENDL4TYPE_TCP_CKSUM;
+		w1->ol4type = is_udp_tun ? NIX_SENDL4TYPE_UDP_CKSUM : 0;
+		/* Update format for UDP tunneled packet */
+
+		w0->lso_format = (lso_tun_fmt >> shift);
+	}
+}
+
 #define NIX_DESCS_PER_LOOP 4
 static __rte_always_inline uint16_t
 cn10k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -723,6 +763,11 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	/* Reduce the cached count */
 	txq->fc_cache_pkts -= pkts;
+	/* Perform header writes before barrier for TSO */
+	if (flags & NIX_TX_OFFLOAD_TSO_F) {
+		for (i = 0; i < pkts; i++)
+			cn10k_nix_xmit_prepare_tso(tx_pkts[i], flags);
+	}
 
 	senddesc01_w0 = vld1q_dup_u64(&txq->send_hdr_w0);
 	senddesc23_w0 = senddesc01_w0;
@@ -781,6 +826,13 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 			sendmem23_w1 = sendmem01_w1;
 		}
 
+		if (flags & NIX_TX_OFFLOAD_TSO_F) {
+			/* Clear the LSO enable bit. */
+			sendext01_w0 = vbicq_u64(sendext01_w0,
+						 vdupq_n_u64(BIT_ULL(14)));
+			sendext23_w0 = sendext01_w0;
+		}
+
 		/* Move mbufs to iova */
 		mbuf0 = (uint64_t *)tx_pkts[0];
 		mbuf1 = (uint64_t *)tx_pkts[1];
@@ -1430,6 +1482,51 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 			cmd3[3] = vzip2q_u64(sendmem23_w0, sendmem23_w1);
 		}
 
+		if (flags & NIX_TX_OFFLOAD_TSO_F) {
+			const uint64_t lso_fmt = txq->lso_tun_fmt;
+			uint64_t sx_w0[NIX_DESCS_PER_LOOP];
+			uint64_t sd_w1[NIX_DESCS_PER_LOOP];
+
+			/* Extract SD W1 as we need to set L4 types. */
+			vst1q_u64(sd_w1, senddesc01_w1);
+			vst1q_u64(sd_w1 + 2, senddesc23_w1);
+
+			/* Extract SX W0 as we need to set LSO fields. */
+			vst1q_u64(sx_w0, sendext01_w0);
+			vst1q_u64(sx_w0 + 2, sendext23_w0);
+
+			/* Extract ol_flags. */
+			xtmp128 = vzip1q_u64(len_olflags0, len_olflags1);
+			ytmp128 = vzip1q_u64(len_olflags2, len_olflags3);
+
+			/* Prepare individual mbufs. */
+			cn10k_nix_prepare_tso(tx_pkts[0],
+				(union nix_send_hdr_w1_u *)&sd_w1[0],
+				(union nix_send_ext_w0_u *)&sx_w0[0],
+				vgetq_lane_u64(xtmp128, 0), flags, lso_fmt);
+
+			cn10k_nix_prepare_tso(tx_pkts[1],
+				(union nix_send_hdr_w1_u *)&sd_w1[1],
+				(union nix_send_ext_w0_u *)&sx_w0[1],
+				vgetq_lane_u64(xtmp128, 1), flags, lso_fmt);
+
+			cn10k_nix_prepare_tso(tx_pkts[2],
+				(union nix_send_hdr_w1_u *)&sd_w1[2],
+				(union nix_send_ext_w0_u *)&sx_w0[2],
+				vgetq_lane_u64(ytmp128, 0), flags, lso_fmt);
+
+			cn10k_nix_prepare_tso(tx_pkts[3],
+				(union nix_send_hdr_w1_u *)&sd_w1[3],
+				(union nix_send_ext_w0_u *)&sx_w0[3],
+				vgetq_lane_u64(ytmp128, 1), flags, lso_fmt);
+
+			senddesc01_w1 = vld1q_u64(sd_w1);
+			senddesc23_w1 = vld1q_u64(sd_w1 + 2);
+
+			sendext01_w0 = vld1q_u64(sx_w0);
+			sendext23_w0 = vld1q_u64(sx_w0 + 2);
+		}
+
 		if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) {
 			/* Set don't free bit if reference count > 1 */
 			xmask01 = vdupq_n_u64(0);
diff --git a/drivers/net/cnxk/cn10k_tx_vec.c b/drivers/net/cnxk/cn10k_tx_vec.c
index 0b4a4c7ba..34e373750 100644
--- a/drivers/net/cnxk/cn10k_tx_vec.c
+++ b/drivers/net/cnxk/cn10k_tx_vec.c
@@ -13,8 +13,9 @@
 	{                                                                      \
 		uint64_t cmd[sz];                                              \
 									       \
-		/* TSO is not supported by vec */                              \
-		if ((flags) & NIX_TX_OFFLOAD_TSO_F)			       \
+		/* For TSO inner checksum is a must */                         \
+		if (((flags) & NIX_TX_OFFLOAD_TSO_F) &&			       \
+		    !((flags) & NIX_TX_OFFLOAD_L3_L4_CSUM_F))		       \
 			return 0;                                              \
 		return cn10k_nix_xmit_pkts_vector(tx_queue, tx_pkts, pkts, cmd,\
 						  (flags));                    \
diff --git a/drivers/net/cnxk/cn9k_tx.c b/drivers/net/cnxk/cn9k_tx.c
index c32681ed4..735e21cc6 100644
--- a/drivers/net/cnxk/cn9k_tx.c
+++ b/drivers/net/cnxk/cn9k_tx.c
@@ -66,7 +66,7 @@ cn9k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
 #undef T
 	};
 
-	if (dev->scalar_ena || (dev->tx_offload_flags & NIX_TX_OFFLOAD_TSO_F))
+	if (dev->scalar_ena)
 		pick_tx_func(eth_dev, nix_eth_tx_burst);
 	else
 		pick_tx_func(eth_dev, nix_eth_tx_vec_burst);
diff --git a/drivers/net/cnxk/cn9k_tx.h b/drivers/net/cnxk/cn9k_tx.h
index cb574a1c1..dca732a9f 100644
--- a/drivers/net/cnxk/cn9k_tx.h
+++ b/drivers/net/cnxk/cn9k_tx.h
@@ -545,6 +545,43 @@ cn9k_nix_xmit_pkts_mseg(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 #if defined(RTE_ARCH_ARM64)
 
+static __rte_always_inline void
+cn9k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
+		     union nix_send_ext_w0_u *w0, uint64_t ol_flags,
+		     uint64_t flags)
+{
+	uint16_t lso_sb;
+	uint64_t mask;
+
+	if (!(ol_flags & PKT_TX_TCP_SEG))
+		return;
+
+	mask = -(!w1->il3type);
+	lso_sb = (mask & w1->ol4ptr) + (~mask & w1->il4ptr) + m->l4_len;
+
+	w0->u |= BIT(14);
+	w0->lso_sb = lso_sb;
+	w0->lso_mps = m->tso_segsz;
+	w0->lso_format = NIX_LSO_FORMAT_IDX_TSOV4 + !!(ol_flags & PKT_TX_IPV6);
+	w1->ol4type = NIX_SENDL4TYPE_TCP_CKSUM;
+
+	/* Handle tunnel tso */
+	if ((flags & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F) &&
+	    (ol_flags & PKT_TX_TUNNEL_MASK)) {
+		const uint8_t is_udp_tun =
+			(CNXK_NIX_UDP_TUN_BITMASK >>
+			 ((ol_flags & PKT_TX_TUNNEL_MASK) >> 45)) &
+			0x1;
+
+		w1->il4type = NIX_SENDL4TYPE_TCP_CKSUM;
+		w1->ol4type = is_udp_tun ? NIX_SENDL4TYPE_UDP_CKSUM : 0;
+		/* Update format for UDP tunneled packet */
+		w0->lso_format += is_udp_tun ? 2 : 6;
+
+		w0->lso_format += !!(ol_flags & PKT_TX_OUTER_IPV6) << 1;
+	}
+}
+
 #define NIX_DESCS_PER_LOOP 4
 static __rte_always_inline uint16_t
 cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -580,6 +617,12 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 	/* Reduce the cached count */
 	txq->fc_cache_pkts -= pkts;
 
+	/* Perform header writes before barrier for TSO */
+	if (flags & NIX_TX_OFFLOAD_TSO_F) {
+		for (i = 0; i < pkts; i++)
+			cn9k_nix_xmit_prepare_tso(tx_pkts[i], flags);
+	}
+
 	/* Lets commit any changes in the packet here as no further changes
 	 * to the packet will be done unless no fast free is enabled.
 	 */
@@ -637,6 +680,13 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 			sendmem23_w1 = sendmem01_w1;
 		}
 
+		if (flags & NIX_TX_OFFLOAD_TSO_F) {
+			/* Clear the LSO enable bit. */
+			sendext01_w0 = vbicq_u64(sendext01_w0,
+						 vdupq_n_u64(BIT_ULL(14)));
+			sendext23_w0 = sendext01_w0;
+		}
+
 		/* Move mbufs to iova */
 		mbuf0 = (uint64_t *)tx_pkts[0];
 		mbuf1 = (uint64_t *)tx_pkts[1];
@@ -1286,6 +1336,50 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 			cmd3[3] = vzip2q_u64(sendmem23_w0, sendmem23_w1);
 		}
 
+		if (flags & NIX_TX_OFFLOAD_TSO_F) {
+			uint64_t sx_w0[NIX_DESCS_PER_LOOP];
+			uint64_t sd_w1[NIX_DESCS_PER_LOOP];
+
+			/* Extract SD W1 as we need to set L4 types. */
+			vst1q_u64(sd_w1, senddesc01_w1);
+			vst1q_u64(sd_w1 + 2, senddesc23_w1);
+
+			/* Extract SX W0 as we need to set LSO fields. */
+			vst1q_u64(sx_w0, sendext01_w0);
+			vst1q_u64(sx_w0 + 2, sendext23_w0);
+
+			/* Extract ol_flags. */
+			xtmp128 = vzip1q_u64(len_olflags0, len_olflags1);
+			ytmp128 = vzip1q_u64(len_olflags2, len_olflags3);
+
+			/* Prepare individual mbufs. */
+			cn9k_nix_prepare_tso(tx_pkts[0],
+				(union nix_send_hdr_w1_u *)&sd_w1[0],
+				(union nix_send_ext_w0_u *)&sx_w0[0],
+				vgetq_lane_u64(xtmp128, 0), flags);
+
+			cn9k_nix_prepare_tso(tx_pkts[1],
+				(union nix_send_hdr_w1_u *)&sd_w1[1],
+				(union nix_send_ext_w0_u *)&sx_w0[1],
+				vgetq_lane_u64(xtmp128, 1), flags);
+
+			cn9k_nix_prepare_tso(tx_pkts[2],
+				(union nix_send_hdr_w1_u *)&sd_w1[2],
+				(union nix_send_ext_w0_u *)&sx_w0[2],
+				vgetq_lane_u64(ytmp128, 0), flags);
+
+			cn9k_nix_prepare_tso(tx_pkts[3],
+				(union nix_send_hdr_w1_u *)&sd_w1[3],
+				(union nix_send_ext_w0_u *)&sx_w0[3],
+				vgetq_lane_u64(ytmp128, 1), flags);
+
+			senddesc01_w1 = vld1q_u64(sd_w1);
+			senddesc23_w1 = vld1q_u64(sd_w1 + 2);
+
+			sendext01_w0 = vld1q_u64(sx_w0);
+			sendext23_w0 = vld1q_u64(sx_w0 + 2);
+		}
+
 		if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) {
 			/* Set don't free bit if reference count > 1 */
 			xmask01 = vdupq_n_u64(0);
diff --git a/drivers/net/cnxk/cn9k_tx_vec.c b/drivers/net/cnxk/cn9k_tx_vec.c
index 9ade66db2..56a3e2514 100644
--- a/drivers/net/cnxk/cn9k_tx_vec.c
+++ b/drivers/net/cnxk/cn9k_tx_vec.c
@@ -13,8 +13,9 @@
 	{                                                                      \
 		uint64_t cmd[sz];                                              \
 									       \
-		/* TSO is not supported by vec */                              \
-		if ((flags) & NIX_TX_OFFLOAD_TSO_F)			       \
+		/* For TSO inner checksum is a must */                         \
+		if (((flags) & NIX_TX_OFFLOAD_TSO_F) &&                        \
+		    !((flags) & NIX_TX_OFFLOAD_L3_L4_CSUM_F))                  \
 			return 0;                                              \
 		return cn9k_nix_xmit_pkts_vector(tx_queue, tx_pkts, pkts, cmd, \
 						 (flags));		       \
-- 
2.17.1