[PATCH v3 2/3] node/kernel_rx: support receiving packets from kernel

[Vamsi Attunuru <vattunuru@marvell.com>]

Adds a node to receive packets from kernel over
a raw socket.

Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
---
 doc/guides/prog_guide/graph_lib.rst |   8 +
 lib/node/kernel_rx.c                | 276 ++++++++++++++++++++++++++++
 lib/node/kernel_rx_priv.h           |  48 +++++
 lib/node/meson.build                |   1 +
 4 files changed, 333 insertions(+)

diff --git a/doc/guides/prog_guide/graph_lib.rst b/doc/guides/prog_guide/graph_lib.rst
index fa22b014f3..4b05bcee3c 100644
--- a/doc/guides/prog_guide/graph_lib.rst
+++ b/doc/guides/prog_guide/graph_lib.rst
@@ -401,3 +401,11 @@ socket interface to transmit the packets, it uses the packet's destination
 IP address in sockaddr_in address structure and ``sendto`` function to send
 data on the raw socket. Aftering sending the burst of packets to kernel,
 this node free up the packet buffers.
+
+kernel_rx
+~~~~~~~~~
+This node is a source node which receives packets from kernel and forwards to
+any of the intermediate nodes. It uses the raw socket interface to receive
+packets from kernel. Uses ``poll`` function to poll on the socket fd for
+``POLLIN`` events to read the packets from raw socket to stream buffer and does
+``rte_node_next_stream_move()`` when there are received packets.
diff --git a/lib/node/kernel_rx.c b/lib/node/kernel_rx.c
new file mode 100644
index 0000000000..2dba7c8cc7
--- /dev/null
+++ b/lib/node/kernel_rx.c
@@ -0,0 +1,276 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2023 Marvell International Ltd.
+ */
+
+#include <fcntl.h>
+#include <poll.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#include <rte_debug.h>
+#include <rte_ethdev.h>
+#include <rte_graph.h>
+#include <rte_graph_worker.h>
+#include <rte_ip.h>
+#include <rte_malloc.h>
+#include <rte_mbuf.h>
+#include <rte_mempool.h>
+#include <rte_net.h>
+
+#include "ethdev_rx_priv.h"
+#include "kernel_rx_priv.h"
+#include "node_private.h"
+
+static inline struct rte_mbuf *
+alloc_rx_mbuf(kernel_rx_node_ctx_t *ctx)
+{
+	kernel_rx_info_t *rx = ctx->recv_info;
+
+	if (rx->idx >= rx->cnt) {
+		uint16_t cnt;
+
+		rx->idx = 0;
+		rx->cnt = 0;
+
+		cnt = rte_pktmbuf_alloc_bulk(ctx->pktmbuf_pool, rx->rx_bufs, KERN_RX_CACHE_COUNT);
+		if (cnt <= 0)
+			return NULL;
+
+		rx->cnt = cnt;
+	}
+
+	return rx->rx_bufs[rx->idx++];
+}
+
+static inline void
+mbuf_update(struct rte_mbuf **mbufs, uint16_t nb_pkts)
+{
+	struct rte_net_hdr_lens hdr_lens;
+	struct rte_mbuf *m;
+	int i;
+
+	for (i = 0; i < nb_pkts; i++) {
+		m = mbufs[i];
+
+		m->packet_type = rte_net_get_ptype(m, &hdr_lens, RTE_PTYPE_ALL_MASK);
+
+		m->ol_flags = 0;
+		m->tx_offload = 0;
+
+		m->l2_len = hdr_lens.l2_len;
+		m->l3_len = hdr_lens.l3_len;
+		m->l4_len = hdr_lens.l4_len;
+	}
+}
+
+static uint16_t
+recv_pkt_parse(void **objs, uint16_t nb_pkts)
+{
+	uint16_t pkts_left = nb_pkts;
+	struct rte_mbuf **pkts;
+	int i;
+
+	pkts = (struct rte_mbuf **)objs;
+
+	if (pkts_left >= 4) {
+		for (i = 0; i < 4; i++)
+			rte_prefetch0(rte_pktmbuf_mtod(pkts[i], void *));
+	}
+
+	while (pkts_left >= 12) {
+		/* Prefetch next-next mbufs */
+		rte_prefetch0(pkts[8]);
+		rte_prefetch0(pkts[9]);
+		rte_prefetch0(pkts[10]);
+		rte_prefetch0(pkts[11]);
+
+		/* Prefetch next mbuf data */
+		rte_prefetch0(rte_pktmbuf_mtod(pkts[4], void *));
+		rte_prefetch0(rte_pktmbuf_mtod(pkts[5], void *));
+		rte_prefetch0(rte_pktmbuf_mtod(pkts[6], void *));
+		rte_prefetch0(rte_pktmbuf_mtod(pkts[7], void *));
+
+		/* Extract ptype of mbufs */
+		mbuf_update(pkts, 4);
+
+		pkts += 4;
+		pkts_left -= 4;
+	}
+
+	if (pkts_left > 0)
+		mbuf_update(pkts, pkts_left);
+
+	return nb_pkts;
+}
+
+static uint16_t
+kernel_rx_node_do(struct rte_graph *graph, struct rte_node *node, kernel_rx_node_ctx_t *ctx)
+{
+	kernel_rx_info_t *rx;
+	uint16_t next_index;
+	int fd;
+
+	rx = ctx->recv_info;
+	next_index = rx->node_next;
+
+	fd = rx->sock;
+	if (fd > 0) {
+		struct rte_mbuf **mbufs;
+		uint16_t len = 0, count = 0;
+		int nb_cnt, i;
+
+		nb_cnt = (node->size >= RTE_GRAPH_BURST_SIZE) ? RTE_GRAPH_BURST_SIZE : node->size;
+
+		mbufs = (struct rte_mbuf **)node->objs;
+		for (i = 0; i < nb_cnt; i++) {
+			struct rte_mbuf *m = alloc_rx_mbuf(ctx);
+
+			if (!m)
+				break;
+
+			len = read(fd, rte_pktmbuf_mtod(m, char *), rte_pktmbuf_tailroom(m));
+			if (len == 0 || len == 0xFFFF) {
+				rte_pktmbuf_free(m);
+				if (rx->idx <= 0)
+					node_dbg("kernel_rx", "rx_mbuf array is empty\n");
+				rx->idx--;
+				break;
+			}
+			*mbufs++ = m;
+
+			m->port = node->id;
+			rte_pktmbuf_data_len(m) = len;
+
+			count++;
+		}
+
+		if (count) {
+			recv_pkt_parse(node->objs, count);
+			node->idx = count;
+
+			/* Enqueue to next node */
+			rte_node_next_stream_move(graph, node, next_index);
+		}
+
+		return count;
+	}
+
+	return 0;
+}
+
+static uint16_t
+kernel_rx_node_process(struct rte_graph *graph, struct rte_node *node, void **objs,
+			 uint16_t nb_objs)
+{
+	kernel_rx_node_ctx_t *ctx = (kernel_rx_node_ctx_t *)node->ctx;
+	int fd;
+
+	RTE_SET_USED(objs);
+	RTE_SET_USED(nb_objs);
+
+	if (!ctx)
+		return 0;
+
+	fd = ctx->recv_info->sock;
+	if (fd > 0) {
+		struct pollfd fds = {.fd = fd, .events = POLLIN};
+
+		if (poll(&fds, 1, 0) > 0) {
+			if (fds.revents & POLLIN)
+				return kernel_rx_node_do(graph, node, ctx);
+		}
+	}
+
+	return 0;
+}
+
+static int
+kernel_rx_node_init(const struct rte_graph *graph, struct rte_node *node)
+{
+	struct kernel_rx_node_main *rx_node_main = kernel_rx_node_data_get();
+	kernel_rx_node_ctx_t *ctx = (kernel_rx_node_ctx_t *)node->ctx;
+	kernel_rx_node_elem_t *elem = rx_node_main->head;
+	kernel_rx_info_t *recv_info;
+	int sock;
+
+	while (elem) {
+		if (elem->nid == node->id) {
+			/* Update node specific context */
+			memcpy(ctx, &elem->ctx, sizeof(kernel_rx_node_ctx_t));
+			break;
+		}
+		elem = elem->next;
+	}
+
+	RTE_VERIFY(elem != NULL);
+
+	if (ctx->pktmbuf_pool == NULL) {
+		node_err("kernel_rx", "Invalid mbuf pool on graph %s\n", graph->name);
+		return -EINVAL;
+	}
+
+	recv_info = rte_zmalloc_socket("kernel_rx_info", sizeof(kernel_rx_info_t),
+				       RTE_CACHE_LINE_SIZE, graph->socket);
+	if (!recv_info) {
+		node_err("kernel_rx", "Kernel recv_info is NULL\n");
+		return -ENOMEM;
+	}
+
+	sock = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
+	if (sock < 0) {
+		node_err("kernel_rx", "Unable to open RAW socket\n");
+		return sock;
+	}
+
+	recv_info->sock = sock;
+	ctx->recv_info = recv_info;
+
+	return 0;
+}
+
+static void
+kernel_rx_node_fini(const struct rte_graph *graph __rte_unused, struct rte_node *node)
+{
+	kernel_rx_node_ctx_t *ctx = (kernel_rx_node_ctx_t *)node->ctx;
+
+	if (ctx->recv_info) {
+		close(ctx->recv_info->sock);
+		ctx->recv_info->sock = -1;
+		rte_free(ctx->recv_info);
+	}
+
+	ctx->recv_info = NULL;
+}
+
+struct kernel_rx_node_main *
+kernel_rx_node_data_get(void)
+{
+	static struct kernel_rx_node_main kernel_rx_main;
+
+	return &kernel_rx_main;
+}
+
+static struct rte_node_register kernel_rx_node_base = {
+	.process = kernel_rx_node_process,
+	.flags = RTE_NODE_SOURCE_F,
+	.name = "kernel_rx",
+
+	.init = kernel_rx_node_init,
+	.fini = kernel_rx_node_fini,
+
+	.nb_edges = KERNEL_RX_NEXT_MAX,
+	.next_nodes = {
+			[KERNEL_RX_NEXT_PKT_CLS] = "pkt_cls",
+			[KERNEL_RX_NEXT_IP4_LOOKUP] = "ip4_lookup",
+	},
+};
+
+struct rte_node_register *
+kernel_rx_node_get(void)
+{
+	return &kernel_rx_node_base;
+}
+
+RTE_NODE_REGISTER(kernel_rx_node_base);
diff --git a/lib/node/kernel_rx_priv.h b/lib/node/kernel_rx_priv.h
new file mode 100644
index 0000000000..f1aa2344d7
--- /dev/null
+++ b/lib/node/kernel_rx_priv.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2023 Marvell International Ltd.
+ */
+
+#ifndef __KERNEL_RX_PRIV_H__
+#define __KERNEL_RX_PRIV_H__
+
+#define KERN_RX_CACHE_COUNT 64
+
+typedef struct kernel_rx_info {
+	struct rte_mbuf *rx_bufs[KERN_RX_CACHE_COUNT];
+	uint16_t node_next;
+	uint16_t idx;
+	uint16_t cnt;
+	int sock;
+} kernel_rx_info_t;
+
+/* kernel_rx node context structure */
+typedef struct kernel_rx_node_ctx {
+	struct rte_mempool *pktmbuf_pool;
+	kernel_rx_info_t *recv_info;
+} kernel_rx_node_ctx_t;
+
+/* kernel_rx node list element structure */
+typedef struct kernel_rx_node_elem {
+	struct kernel_rx_node_elem *next; /* Pointer to the next node element. */
+	struct kernel_rx_node_ctx ctx;    /* kernel_rx node context. */
+	rte_node_t nid;			  /* Node identifier of the kernel_rx node. */
+} kernel_rx_node_elem_t;
+
+enum kernel_rx_next_nodes {
+	KERNEL_RX_NEXT_PKT_CLS,
+	KERNEL_RX_NEXT_IP4_LOOKUP,
+	KERNEL_RX_NEXT_MAX,
+};
+
+/* kernel_rx node main structure */
+struct kernel_rx_node_main {
+	kernel_rx_node_elem_t *head; /* Pointer to the head node element. */
+};
+
+/* Get the pointer of kernel_rx node data */
+struct kernel_rx_node_main *kernel_rx_node_data_get(void);
+
+/* Get the pointer of kernel_rx node register structure */
+struct rte_node_register *kernel_rx_node_get(void);
+
+#endif /* __KERNEL_RX_PRIV_H__ */
diff --git a/lib/node/meson.build b/lib/node/meson.build
index 0520be23ff..1f04fd1d7e 100644
--- a/lib/node/meson.build
+++ b/lib/node/meson.build
@@ -13,6 +13,7 @@ sources = files(
         'ethdev_tx.c',
         'ip4_lookup.c',
         'ip4_rewrite.c',
+        'kernel_rx.c',
         'kernel_tx.c',
         'log.c',
         'null.c',
-- 
2.25.1