[dpdk-dev] [PATCH v4 19/62] net/cnxk: add Rx burst for cn9k

[Nithin Dabilpuram <ndabilpuram@marvell.com>]

From: Jerin Jacob <jerinj@marvell.com>

Add Rx burst scalar version for CN9K.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
---
 drivers/net/cnxk/cn9k_ethdev.h |   3 +
 drivers/net/cnxk/cn9k_rx.c     |  46 ++++++++
 drivers/net/cnxk/cn9k_rx.h     | 237 +++++++++++++++++++++++++++++++++++++++++
 drivers/net/cnxk/cnxk_ethdev.h |   3 +
 drivers/net/cnxk/meson.build   |   3 +-
 5 files changed, 291 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/cnxk/cn9k_rx.c

diff --git a/drivers/net/cnxk/cn9k_ethdev.h b/drivers/net/cnxk/cn9k_ethdev.h
index bd7bf50..bab5540 100644
--- a/drivers/net/cnxk/cn9k_ethdev.h
+++ b/drivers/net/cnxk/cn9k_ethdev.h
@@ -31,4 +31,7 @@ struct cn9k_eth_rxq {
 	uint16_t rq;
 } __plt_cache_aligned;
 
+/* Rx and Tx routines */
+void cn9k_eth_set_rx_function(struct rte_eth_dev *eth_dev);
+
 #endif /* __CN9K_ETHDEV_H__ */
diff --git a/drivers/net/cnxk/cn9k_rx.c b/drivers/net/cnxk/cn9k_rx.c
new file mode 100644
index 0000000..a4297f9
--- /dev/null
+++ b/drivers/net/cnxk/cn9k_rx.c
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2021 Marvell.
+ */
+
+#include "cn9k_ethdev.h"
+#include "cn9k_rx.h"
+
+#define R(name, f3, f2, f1, f0, flags)					       \
+	uint16_t __rte_noinline __rte_hot cn9k_nix_recv_pkts_##name(	       \
+		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts)      \
+	{                                                                      \
+		return cn9k_nix_recv_pkts(rx_queue, rx_pkts, pkts, (flags));   \
+	}
+
+NIX_RX_FASTPATH_MODES
+#undef R
+
+static inline void
+pick_rx_func(struct rte_eth_dev *eth_dev,
+	     const eth_rx_burst_t rx_burst[2][2][2][2])
+{
+	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
+
+	/* [MARK] [CKSUM] [PTYPE] [RSS] */
+	eth_dev->rx_pkt_burst = rx_burst
+		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_CHECKSUM_F)]
+		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_PTYPE_F)]
+		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_RSS_F)];
+}
+
+void
+cn9k_eth_set_rx_function(struct rte_eth_dev *eth_dev)
+{
+	const eth_rx_burst_t nix_eth_rx_burst[2][2][2][2] = {
+#define R(name, f3, f2, f1, f0, flags)					\
+	[f3][f2][f1][f0] = cn9k_nix_recv_pkts_##name,
+
+		NIX_RX_FASTPATH_MODES
+#undef R
+	};
+
+	pick_rx_func(eth_dev, nix_eth_rx_burst);
+
+	rte_mb();
+}
diff --git a/drivers/net/cnxk/cn9k_rx.h b/drivers/net/cnxk/cn9k_rx.h
index 95a1e69..92f3c7c 100644
--- a/drivers/net/cnxk/cn9k_rx.h
+++ b/drivers/net/cnxk/cn9k_rx.h
@@ -7,6 +7,243 @@
 
 #include <rte_ether.h>
 
+#define NIX_RX_OFFLOAD_NONE	     (0)
+#define NIX_RX_OFFLOAD_RSS_F	     BIT(0)
 #define NIX_RX_OFFLOAD_PTYPE_F	     BIT(1)
+#define NIX_RX_OFFLOAD_CHECKSUM_F    BIT(2)
+#define NIX_RX_OFFLOAD_MARK_UPDATE_F BIT(3)
+
+/* Flags to control cqe_to_mbuf conversion function.
+ * Defining it from backwards to denote its been
+ * not used as offload flags to pick function
+ */
+#define NIX_RX_MULTI_SEG_F BIT(15)
+
+#define CNXK_NIX_CQ_ENTRY_SZ 128
+#define NIX_DESCS_PER_LOOP   4
+#define CQE_CAST(x)	     ((struct nix_cqe_hdr_s *)(x))
+#define CQE_SZ(x)	     ((x) * CNXK_NIX_CQ_ENTRY_SZ)
+
+union mbuf_initializer {
+	struct {
+		uint16_t data_off;
+		uint16_t refcnt;
+		uint16_t nb_segs;
+		uint16_t port;
+	} fields;
+	uint64_t value;
+};
+
+static __rte_always_inline uint64_t
+nix_clear_data_off(uint64_t oldval)
+{
+	union mbuf_initializer mbuf_init = {.value = oldval};
+
+	mbuf_init.fields.data_off = 0;
+	return mbuf_init.value;
+}
+
+static __rte_always_inline struct rte_mbuf *
+nix_get_mbuf_from_cqe(void *cq, const uint64_t data_off)
+{
+	rte_iova_t buff;
+
+	/* Skip CQE, NIX_RX_PARSE_S and SG HDR(9 DWORDs) and peek buff addr */
+	buff = *((rte_iova_t *)((uint64_t *)cq + 9));
+	return (struct rte_mbuf *)(buff - data_off);
+}
+
+static __rte_always_inline uint32_t
+nix_ptype_get(const void *const lookup_mem, const uint64_t in)
+{
+	const uint16_t *const ptype = lookup_mem;
+	const uint16_t lh_lg_lf = (in & 0xFFF0000000000000) >> 52;
+	const uint16_t tu_l2 = ptype[(in & 0x000FFFF000000000) >> 36];
+	const uint16_t il4_tu = ptype[PTYPE_NON_TUNNEL_ARRAY_SZ + lh_lg_lf];
+
+	return (il4_tu << PTYPE_NON_TUNNEL_WIDTH) | tu_l2;
+}
+
+static __rte_always_inline uint32_t
+nix_rx_olflags_get(const void *const lookup_mem, const uint64_t in)
+{
+	const uint32_t *const ol_flags =
+		(const uint32_t *)((const uint8_t *)lookup_mem +
+				   PTYPE_ARRAY_SZ);
+
+	return ol_flags[(in & 0xfff00000) >> 20];
+}
+
+static inline uint64_t
+nix_update_match_id(const uint16_t match_id, uint64_t ol_flags,
+		    struct rte_mbuf *mbuf)
+{
+	/* There is no separate bit to check match_id
+	 * is valid or not? and no flag to identify it is an
+	 * RTE_FLOW_ACTION_TYPE_FLAG vs RTE_FLOW_ACTION_TYPE_MARK
+	 * action. The former case addressed through 0 being invalid
+	 * value and inc/dec match_id pair when MARK is activated.
+	 * The later case addressed through defining
+	 * CNXK_FLOW_MARK_DEFAULT as value for
+	 * RTE_FLOW_ACTION_TYPE_MARK.
+	 * This would translate to not use
+	 * CNXK_FLOW_ACTION_FLAG_DEFAULT - 1 and
+	 * CNXK_FLOW_ACTION_FLAG_DEFAULT for match_id.
+	 * i.e valid mark_id's are from
+	 * 0 to CNXK_FLOW_ACTION_FLAG_DEFAULT - 2
+	 */
+	if (likely(match_id)) {
+		ol_flags |= PKT_RX_FDIR;
+		if (match_id != CNXK_FLOW_ACTION_FLAG_DEFAULT) {
+			ol_flags |= PKT_RX_FDIR_ID;
+			mbuf->hash.fdir.hi = match_id - 1;
+		}
+	}
+
+	return ol_flags;
+}
+
+static __rte_always_inline void
+cn9k_nix_cqe_to_mbuf(const struct nix_cqe_hdr_s *cq, const uint32_t tag,
+		     struct rte_mbuf *mbuf, const void *lookup_mem,
+		     const uint64_t val, const uint16_t flag)
+{
+	const union nix_rx_parse_u *rx =
+		(const union nix_rx_parse_u *)((const uint64_t *)cq + 1);
+	const uint16_t len = rx->cn9k.pkt_lenm1 + 1;
+	const uint64_t w1 = *(const uint64_t *)rx;
+	uint64_t ol_flags = 0;
+
+	/* Mark mempool obj as "get" as it is alloc'ed by NIX */
+	__mempool_check_cookies(mbuf->pool, (void **)&mbuf, 1, 1);
+
+	if (flag & NIX_RX_OFFLOAD_PTYPE_F)
+		mbuf->packet_type = nix_ptype_get(lookup_mem, w1);
+	else
+		mbuf->packet_type = 0;
+
+	if (flag & NIX_RX_OFFLOAD_RSS_F) {
+		mbuf->hash.rss = tag;
+		ol_flags |= PKT_RX_RSS_HASH;
+	}
+
+	if (flag & NIX_RX_OFFLOAD_CHECKSUM_F)
+		ol_flags |= nix_rx_olflags_get(lookup_mem, w1);
+
+	if (flag & NIX_RX_OFFLOAD_MARK_UPDATE_F)
+		ol_flags =
+			nix_update_match_id(rx->cn9k.match_id, ol_flags, mbuf);
+
+	mbuf->ol_flags = ol_flags;
+	*(uint64_t *)(&mbuf->rearm_data) = val;
+	mbuf->pkt_len = len;
+
+	mbuf->data_len = len;
+	mbuf->next = NULL;
+}
+
+static inline uint16_t
+nix_rx_nb_pkts(struct cn9k_eth_rxq *rxq, const uint64_t wdata,
+	       const uint16_t pkts, const uint32_t qmask)
+{
+	uint32_t available = rxq->available;
+
+	/* Update the available count if cached value is not enough */
+	if (unlikely(available < pkts)) {
+		uint64_t reg, head, tail;
+
+		/* Use LDADDA version to avoid reorder */
+		reg = roc_atomic64_add_sync(wdata, rxq->cq_status);
+		/* CQ_OP_STATUS operation error */
+		if (reg & BIT_ULL(NIX_CQ_OP_STAT_OP_ERR) ||
+		    reg & BIT_ULL(NIX_CQ_OP_STAT_CQ_ERR))
+			return 0;
+
+		tail = reg & 0xFFFFF;
+		head = (reg >> 20) & 0xFFFFF;
+		if (tail < head)
+			available = tail - head + qmask + 1;
+		else
+			available = tail - head;
+
+		rxq->available = available;
+	}
+
+	return RTE_MIN(pkts, available);
+}
+
+static __rte_always_inline uint16_t
+cn9k_nix_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts,
+		   const uint16_t flags)
+{
+	struct cn9k_eth_rxq *rxq = rx_queue;
+	const uint64_t mbuf_init = rxq->mbuf_initializer;
+	const void *lookup_mem = rxq->lookup_mem;
+	const uint64_t data_off = rxq->data_off;
+	const uintptr_t desc = rxq->desc;
+	const uint64_t wdata = rxq->wdata;
+	const uint32_t qmask = rxq->qmask;
+	uint16_t packets = 0, nb_pkts;
+	uint32_t head = rxq->head;
+	struct nix_cqe_hdr_s *cq;
+	struct rte_mbuf *mbuf;
+
+	nb_pkts = nix_rx_nb_pkts(rxq, wdata, pkts, qmask);
+
+	while (packets < nb_pkts) {
+		/* Prefetch N desc ahead */
+		rte_prefetch_non_temporal(
+			(void *)(desc + (CQE_SZ((head + 2) & qmask))));
+		cq = (struct nix_cqe_hdr_s *)(desc + CQE_SZ(head));
+
+		mbuf = nix_get_mbuf_from_cqe(cq, data_off);
+
+		cn9k_nix_cqe_to_mbuf(cq, cq->tag, mbuf, lookup_mem, mbuf_init,
+				     flags);
+		rx_pkts[packets++] = mbuf;
+		roc_prefetch_store_keep(mbuf);
+		head++;
+		head &= qmask;
+	}
+
+	rxq->head = head;
+	rxq->available -= nb_pkts;
+
+	/* Free all the CQs that we've processed */
+	plt_write64((wdata | nb_pkts), rxq->cq_door);
+
+	return nb_pkts;
+}
+
+#define RSS_F	  NIX_RX_OFFLOAD_RSS_F
+#define PTYPE_F	  NIX_RX_OFFLOAD_PTYPE_F
+#define CKSUM_F	  NIX_RX_OFFLOAD_CHECKSUM_F
+#define MARK_F	  NIX_RX_OFFLOAD_MARK_UPDATE_F
+
+/* [MARK] [CKSUM] [PTYPE] [RSS] */
+#define NIX_RX_FASTPATH_MODES					       \
+R(no_offload,			0, 0, 0, 0, NIX_RX_OFFLOAD_NONE)       \
+R(rss,				0, 0, 0, 1, RSS_F)		       \
+R(ptype,			0, 0, 1, 0, PTYPE_F)		       \
+R(ptype_rss,			0, 0, 1, 1, PTYPE_F | RSS_F)	       \
+R(cksum,			0, 1, 0, 0, CKSUM_F)		       \
+R(cksum_rss,			0, 1, 0, 1, CKSUM_F | RSS_F)	       \
+R(cksum_ptype,			0, 1, 1, 0, CKSUM_F | PTYPE_F)	       \
+R(cksum_ptype_rss,		0, 1, 1, 1, CKSUM_F | PTYPE_F | RSS_F) \
+R(mark,				1, 0, 0, 0, MARK_F)		       \
+R(mark_rss,			1, 0, 0, 1, MARK_F | RSS_F)	       \
+R(mark_ptype,			1, 0, 1, 0, MARK_F | PTYPE_F)	       \
+R(mark_ptype_rss,		1, 0, 1, 1, MARK_F | PTYPE_F | RSS_F)  \
+R(mark_cksum,			1, 1, 0, 0, MARK_F | CKSUM_F)	       \
+R(mark_cksum_rss,		1, 1, 0, 1, MARK_F | CKSUM_F | RSS_F)  \
+R(mark_cksum_ptype,		1, 1, 1, 0, MARK_F | CKSUM_F | PTYPE_F)\
+R(mark_cksum_ptype_rss,		1, 1, 1, 1, MARK_F | CKSUM_F | PTYPE_F | RSS_F)
+
+#define R(name, f3, f2, f1, f0, flags)					       \
+	uint16_t __rte_noinline __rte_hot cn9k_nix_recv_pkts_##name(           \
+		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts);
+
+NIX_RX_FASTPATH_MODES
+#undef R
 
 #endif /* __CN9K_RX_H__ */
diff --git a/drivers/net/cnxk/cnxk_ethdev.h b/drivers/net/cnxk/cnxk_ethdev.h
index 5a52489..a6f5d36 100644
--- a/drivers/net/cnxk/cnxk_ethdev.h
+++ b/drivers/net/cnxk/cnxk_ethdev.h
@@ -91,6 +91,9 @@
 #define RSS_SCTP_INDEX 4
 #define RSS_DMAC_INDEX 5
 
+/* Default mark value used when none is provided. */
+#define CNXK_FLOW_ACTION_FLAG_DEFAULT 0xffff
+
 #define PTYPE_NON_TUNNEL_WIDTH	  16
 #define PTYPE_TUNNEL_WIDTH	  12
 #define PTYPE_NON_TUNNEL_ARRAY_SZ BIT(PTYPE_NON_TUNNEL_WIDTH)
diff --git a/drivers/net/cnxk/meson.build b/drivers/net/cnxk/meson.build
index 5bc0bb5..7a44001 100644
--- a/drivers/net/cnxk/meson.build
+++ b/drivers/net/cnxk/meson.build
@@ -15,7 +15,8 @@ sources = files('cnxk_ethdev.c',
 		'cnxk_lookup.c')
 
 # CN9K
-sources += files('cn9k_ethdev.c')
+sources += files('cn9k_ethdev.c',
+		 'cn9k_rx.c')
 # CN10K
 sources += files('cn10k_ethdev.c')
 
-- 
2.8.4