[PATCH v3 05/16] net: add function to get packet type from data

[Olivier Matz <olivier.matz@6wind.com>]

Introduce the function rte_net_get_ptype() that parses a mbuf and
returns its packet type. For now, the following packet types are parsed:
   L2: Ether
   L3: IPv4, IPv6
   L4: TCP, UDP, SCTP

The goal here is to provide a reference implementation for packet type
parsing. This function will be used by testpmd in next commits, allowing
to compare its result with the value given by the hardware.

This function will also be useful when implementing Rx offload support
in virtio pmd. Indeed, the virtio protocol gives the csum start and
offset, but it does not give the L4 protocol nor it tells if the
checksum is relevant for inner or outer. This information has to be
known to properly set the ol_flags in mbuf.

Signed-off-by: Didier Pallard <didier.pallard@6wind.com>
Signed-off-by: Jean Dao <jean.dao@6wind.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
---
 doc/guides/rel_notes/release_16_11.rst |   5 +
 lib/librte_net/Makefile                |   4 +-
 lib/librte_net/rte_net.c               | 235 +++++++++++++++++++++++++++++++++
 lib/librte_net/rte_net.h               |  88 ++++++++++++
 lib/librte_net/rte_net_version.map     |   3 +
 5 files changed, 334 insertions(+), 1 deletion(-)
 create mode 100644 lib/librte_net/rte_net.h

diff --git a/doc/guides/rel_notes/release_16_11.rst b/doc/guides/rel_notes/release_16_11.rst
index ae24da2..b3b9dfb 100644
--- a/doc/guides/rel_notes/release_16_11.rst
+++ b/doc/guides/rel_notes/release_16_11.rst
@@ -41,6 +41,11 @@ New Features
   Added a new function ``rte_pktmbuf_read()`` to read the packet data from an
   mbuf chain, linearizing if required.
 
+* **Added a function to get the packet type from packet data.**
+
+  Added a new function ``rte_net_get_ptype()`` to parse an Ethernet packet
+  in an mbuf chain and retrieve its packet type by software.
+
 Resolved Issues
 ---------------
 
diff --git a/lib/librte_net/Makefile b/lib/librte_net/Makefile
index a6be7ae..c16b542 100644
--- a/lib/librte_net/Makefile
+++ b/lib/librte_net/Makefile
@@ -41,7 +41,9 @@ LIBABIVER := 1
 SRCS-$(CONFIG_RTE_LIBRTE_NET) := rte_net.c
 
 # install includes
-SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include := rte_ip.h rte_tcp.h rte_udp.h rte_sctp.h rte_icmp.h rte_arp.h rte_ether.h
+SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include := rte_ip.h rte_tcp.h rte_udp.h
+SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_sctp.h rte_icmp.h rte_arp.h
+SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_ether.h rte_net.h
 
 DEPDIRS-$(CONFIG_RTE_LIBRTE_NET) += lib/librte_eal lib/librte_mempool
 DEPDIRS-$(CONFIG_RTE_LIBRTE_NET) += lib/librte_mbuf
diff --git a/lib/librte_net/rte_net.c b/lib/librte_net/rte_net.c
index e69de29..93e9df0 100644
--- a/lib/librte_net/rte_net.c
+++ b/lib/librte_net/rte_net.c
@@ -0,0 +1,235 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright 2016 6WIND S.A.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of 6WIND S.A. nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <stdint.h>
+
+#include <rte_mbuf.h>
+#include <rte_mbuf_ptype.h>
+#include <rte_byteorder.h>
+#include <rte_ether.h>
+#include <rte_ip.h>
+#include <rte_tcp.h>
+#include <rte_udp.h>
+#include <rte_sctp.h>
+#include <rte_net.h>
+
+/* get l3 packet type from ip6 next protocol */
+static uint32_t
+ptype_l3_ip6(uint8_t ip6_proto)
+{
+	static const uint32_t ip6_ext_proto_map[256] = {
+		[IPPROTO_HOPOPTS] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6,
+		[IPPROTO_ROUTING] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6,
+		[IPPROTO_FRAGMENT] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6,
+		[IPPROTO_ESP] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6,
+		[IPPROTO_AH] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6,
+		[IPPROTO_DSTOPTS] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6,
+	};
+
+	return RTE_PTYPE_L3_IPV6 + ip6_ext_proto_map[ip6_proto];
+}
+
+/* get l3 packet type from ip version and header length */
+static uint32_t
+ptype_l3_ip(uint8_t ipv_ihl)
+{
+	static const uint32_t ptype_l3_ip_proto_map[256] = {
+		[0x45] = RTE_PTYPE_L3_IPV4,
+		[0x46] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x47] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x48] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x49] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x4A] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x4B] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x4C] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x4D] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x4E] = RTE_PTYPE_L3_IPV4_EXT,
+		[0x4F] = RTE_PTYPE_L3_IPV4_EXT,
+	};
+
+	return ptype_l3_ip_proto_map[ipv_ihl];
+}
+
+/* get l4 packet type from proto */
+static uint32_t
+ptype_l4(uint8_t proto)
+{
+	static const uint32_t ptype_l4_proto[256] = {
+		[IPPROTO_UDP] = RTE_PTYPE_L4_UDP,
+		[IPPROTO_TCP] = RTE_PTYPE_L4_TCP,
+		[IPPROTO_SCTP] = RTE_PTYPE_L4_SCTP,
+	};
+
+	return ptype_l4_proto[proto];
+}
+
+/* get the ipv4 header length */
+static uint8_t
+ip4_hlen(const struct ipv4_hdr *hdr)
+{
+	return (hdr->version_ihl & 0xf) * 4;
+}
+
+/* parse ipv6 extended headers, update offset and return next proto */
+static uint16_t
+skip_ip6_ext(uint16_t proto, const struct rte_mbuf *m, uint32_t *off,
+	int *frag)
+{
+	struct ext_hdr {
+		uint8_t next_hdr;
+		uint8_t len;
+	};
+	const struct ext_hdr *xh;
+	struct ext_hdr xh_copy;
+	unsigned int i;
+
+	*frag = 0;
+
+#define MAX_EXT_HDRS 5
+	for (i = 0; i < MAX_EXT_HDRS; i++) {
+		switch (proto) {
+		case IPPROTO_HOPOPTS:
+		case IPPROTO_ROUTING:
+		case IPPROTO_DSTOPTS:
+			xh = rte_pktmbuf_read(m, *off, sizeof(*xh),
+				&xh_copy);
+			if (xh == NULL)
+				return 0;
+			*off += (xh->len + 1) * 8;
+			proto = xh->next_hdr;
+			break;
+		case IPPROTO_FRAGMENT:
+			xh = rte_pktmbuf_read(m, *off, sizeof(*xh),
+				&xh_copy);
+			if (xh == NULL)
+				return 0;
+			*off += 8;
+			proto = xh->next_hdr;
+			*frag = 1;
+			return proto; /* this is always the last ext hdr */
+		case IPPROTO_NONE:
+			return 0;
+		default:
+			return proto;
+		}
+	}
+	return 0;
+}
+
+/* parse mbuf data to get packet type */
+uint32_t rte_net_get_ptype(const struct rte_mbuf *m,
+	struct rte_net_hdr_lens *hdr_lens)
+{
+	struct rte_net_hdr_lens local_hdr_lens;
+	const struct ether_hdr *eh;
+	struct ether_hdr eh_copy;
+	uint32_t pkt_type = RTE_PTYPE_L2_ETHER;
+	uint32_t off = 0;
+	uint16_t proto;
+
+	if (hdr_lens == NULL)
+		hdr_lens = &local_hdr_lens;
+
+	eh = rte_pktmbuf_read(m, off, sizeof(*eh), &eh_copy);
+	if (unlikely(eh == NULL))
+		return 0;
+	proto = eh->ether_type;
+	off = sizeof(*eh);
+	hdr_lens->l2_len = off;
+
+	if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) {
+		const struct ipv4_hdr *ip4h;
+		struct ipv4_hdr ip4h_copy;
+
+		ip4h = rte_pktmbuf_read(m, off, sizeof(*ip4h), &ip4h_copy);
+		if (unlikely(ip4h == NULL))
+			return pkt_type;
+
+		pkt_type |= ptype_l3_ip(ip4h->version_ihl);
+		hdr_lens->l3_len = ip4_hlen(ip4h);
+		off += hdr_lens->l3_len;
+		if (ip4h->fragment_offset &
+				rte_cpu_to_be_16(IPV4_HDR_OFFSET_MASK |
+					IPV4_HDR_MF_FLAG)) {
+			pkt_type |= RTE_PTYPE_L4_FRAG;
+			hdr_lens->l4_len = 0;
+			return pkt_type;
+		}
+		proto = ip4h->next_proto_id;
+		pkt_type |= ptype_l4(proto);
+	} else if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) {
+		const struct ipv6_hdr *ip6h;
+		struct ipv6_hdr ip6h_copy;
+		int frag = 0;
+
+		ip6h = rte_pktmbuf_read(m, off, sizeof(*ip6h), &ip6h_copy);
+		if (unlikely(ip6h == NULL))
+			return pkt_type;
+
+		proto = ip6h->proto;
+		hdr_lens->l3_len = sizeof(*ip6h);
+		off += hdr_lens->l3_len;
+		pkt_type |= ptype_l3_ip6(proto);
+		if ((pkt_type & RTE_PTYPE_L3_MASK) == RTE_PTYPE_L3_IPV6_EXT) {
+			proto = skip_ip6_ext(proto, m, &off, &frag);
+			hdr_lens->l3_len = off - hdr_lens->l2_len;
+		}
+		if (proto == 0)
+			return pkt_type;
+		if (frag) {
+			pkt_type |= RTE_PTYPE_L4_FRAG;
+			hdr_lens->l4_len = 0;
+			return pkt_type;
+		}
+		pkt_type |= ptype_l4(proto);
+	}
+
+	if ((pkt_type & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP) {
+		hdr_lens->l4_len = sizeof(struct udp_hdr);
+	} else if ((pkt_type & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_TCP) {
+		const struct tcp_hdr *th;
+		struct tcp_hdr th_copy;
+
+		th = rte_pktmbuf_read(m, off, sizeof(*th), &th_copy);
+		if (unlikely(th == NULL))
+			return pkt_type & (RTE_PTYPE_L2_MASK |
+				RTE_PTYPE_L3_MASK);
+		hdr_lens->l4_len = (th->data_off & 0xf0) >> 2;
+	} else if ((pkt_type & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_SCTP) {
+		hdr_lens->l4_len = sizeof(struct sctp_hdr);
+	} else {
+		hdr_lens->l4_len = 0;
+	}
+
+	return pkt_type;
+}
diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h
new file mode 100644
index 0000000..81979f1
--- /dev/null
+++ b/lib/librte_net/rte_net.h
@@ -0,0 +1,88 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright 2016 6WIND S.A.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_NET_PTYPE_H_
+#define _RTE_NET_PTYPE_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Structure containing header lengths associated to a packet, filled
+ * by rte_net_get_ptype().
+ */
+struct rte_net_hdr_lens {
+	uint8_t l2_len;
+	uint8_t l3_len;
+	uint8_t l4_len;
+	uint8_t tunnel_len;
+	uint8_t inner_l2_len;
+	uint8_t inner_l3_len;
+	uint8_t inner_l4_len;
+};
+
+/**
+ * Parse an Ethernet packet to get its packet type.
+ *
+ * This function parses the network headers in mbuf data and return its
+ * packet type.
+ *
+ * If it is provided by the user, it also fills a rte_net_hdr_lens
+ * structure that contains the lengths of the parsed network
+ * headers. Each length field is valid only if the associated packet
+ * type is set. For instance, hdr_lens->l2_len is valid only if
+ * (retval & RTE_PTYPE_L2_MASK) != RTE_PTYPE_UNKNOWN.
+ *
+ * Supported packet types are:
+ *   L2: Ether
+ *   L3: IPv4, IPv6
+ *   L4: TCP, UDP, SCTP
+ *
+ * @param m
+ *   The packet mbuf to be parsed.
+ * @param hdr_lens
+ *   A pointer to a structure where the header lengths will be returned,
+ *   or NULL.
+ * @return
+ *   The packet type of the packet.
+ */
+uint32_t rte_net_get_ptype(const struct rte_mbuf *m,
+	struct rte_net_hdr_lens *hdr_lens);
+
+#ifdef __cplusplus
+}
+#endif
+
+
+#endif /* _RTE_NET_PTYPE_H_ */
diff --git a/lib/librte_net/rte_net_version.map b/lib/librte_net/rte_net_version.map
index cc5829e..3b15e65 100644
--- a/lib/librte_net/rte_net_version.map
+++ b/lib/librte_net/rte_net_version.map
@@ -1,3 +1,6 @@
 DPDK_16.11 {
+	global:
+	rte_net_get_ptype;
+
 	local: *;
 };
-- 
2.8.1