[PATCH] net/iavf: add check for mbuf

[PATCH] net/iavf: add check for mbuf

[Mingjin Ye]

The scalar Tx path would send wrong mbuf that causes the kernel driver to
fire the MDD event.

This patch adds mbuf detection in tx_prepare to fix this issue, rte_errno
will be set to EINVAL and returned if the verification fails.

Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
Cc: stable@dpdk.org

Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
---
 drivers/net/iavf/iavf_rxtx.c | 599 +++++++++++++++++++++++++++++++++++
 1 file changed, 599 insertions(+)

diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 8d49967538..63012fdc28 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -24,12 +24,55 @@
 #include <rte_ip.h>
 #include <rte_net.h>
 #include <rte_vect.h>
+#include <rte_vxlan.h>
+#include <rte_gtp.h>
+#include <rte_geneve.h>
 
 #include "iavf.h"
 #include "iavf_rxtx.h"
 #include "iavf_ipsec_crypto.h"
 #include "rte_pmd_iavf.h"
 
+#define GRE_CHECKSUM_PRESENT	0x8000
+#define GRE_KEY_PRESENT		0x2000
+#define GRE_SEQUENCE_PRESENT	0x1000
+#define GRE_EXT_LEN		4
+#define GRE_SUPPORTED_FIELDS	(GRE_CHECKSUM_PRESENT | GRE_KEY_PRESENT |\
+				 GRE_SEQUENCE_PRESENT)
+
+#ifndef IPPROTO_IPIP
+#define IPPROTO_IPIP 4
+#endif
+#ifndef IPPROTO_GRE
+#define IPPROTO_GRE	47
+#endif
+
+static uint16_t vxlan_gpe_udp_port = RTE_VXLAN_GPE_DEFAULT_PORT;
+static uint16_t geneve_udp_port = RTE_GENEVE_DEFAULT_PORT;
+
+struct simple_gre_hdr {
+	uint16_t flags;
+	uint16_t proto;
+} __rte_packed;
+
+/* structure that caches offload info for the current packet */
+struct offload_info {
+	uint16_t ethertype;
+	uint8_t gso_enable;
+	uint16_t l2_len;
+	uint16_t l3_len;
+	uint16_t l4_len;
+	uint8_t l4_proto;
+	uint8_t is_tunnel;
+	uint16_t outer_ethertype;
+	uint16_t outer_l2_len;
+	uint16_t outer_l3_len;
+	uint8_t outer_l4_proto;
+	uint16_t tso_segsz;
+	uint16_t tunnel_tso_segsz;
+	uint32_t pkt_len;
+};
+
 /* Offset of mbuf dynamic field for protocol extraction's metadata */
 int rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
 
@@ -2949,6 +2992,555 @@ iavf_check_vlan_up2tc(struct iavf_tx_queue *txq, struct rte_mbuf *m)
 	}
 }
 
+/* Parse an IPv4 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv4(struct rte_ipv4_hdr *ipv4_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = rte_ipv4_hdr_len(ipv4_hdr);
+	info->l4_proto = ipv4_hdr->next_proto_id;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv4_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/* Parse an IPv6 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv6(struct rte_ipv6_hdr *ipv6_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = sizeof(struct rte_ipv6_hdr);
+	info->l4_proto = ipv6_hdr->proto;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv6_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/*
+ * Parse an ethernet header to fill the ethertype, l2_len, l3_len and
+ * ipproto. This function is able to recognize IPv4/IPv6 with optional VLAN
+ * headers. The l4_len argument is only set in case of TCP (useful for TSO).
+ */
+static inline void
+parse_ethernet(struct rte_ether_hdr *eth_hdr, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vlan_hdr *vlan_hdr;
+
+	info->l2_len = sizeof(struct rte_ether_hdr);
+	info->ethertype = eth_hdr->ether_type;
+
+	while (info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
+	       info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
+		vlan_hdr = (struct rte_vlan_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		info->l2_len  += sizeof(struct rte_vlan_hdr);
+		info->ethertype = vlan_hdr->eth_proto;
+	}
+
+	switch (info->ethertype) {
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV4):
+		ipv4_hdr = (struct rte_ipv4_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv4(ipv4_hdr, info);
+		break;
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV6):
+		ipv6_hdr = (struct rte_ipv6_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv6(ipv6_hdr, info);
+		break;
+	default:
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+		break;
+	}
+}
+
+/* Fill in outer layers length */
+static inline void
+update_tunnel_outer(struct offload_info *info)
+{
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+	info->outer_l4_proto = info->l4_proto;
+}
+
+/*
+ * Parse a GTP protocol header.
+ * No optional fields and next extension header type.
+ */
+static inline void
+parse_gtp(struct rte_udp_hdr *udp_hdr,
+	  struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_gtp_hdr *gtp_hdr;
+	uint8_t gtp_len = sizeof(*gtp_hdr);
+	uint8_t ip_ver;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->src_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPU_UDP_PORT))
+		return;
+
+	update_tunnel_outer(info);
+	info->l2_len = 0;
+
+	gtp_hdr = (struct rte_gtp_hdr *)((char *)udp_hdr +
+		  sizeof(struct rte_udp_hdr));
+
+	/*
+	 * Check message type. If message type is 0xff, it is
+	 * a GTP data packet. If not, it is a GTP control packet
+	 */
+	if (gtp_hdr->msg_type == 0xff) {
+		ip_ver = *(uint8_t *)((char *)udp_hdr +
+			 sizeof(struct rte_udp_hdr) +
+			 sizeof(struct rte_gtp_hdr));
+		ip_ver = (ip_ver) & 0xf0;
+
+		if (ip_ver == RTE_GTP_TYPE_IPV4) {
+			ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+			parse_ipv4(ipv4_hdr, info);
+		} else if (ip_ver == RTE_GTP_TYPE_IPV6) {
+			ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+			parse_ipv6(ipv6_hdr, info);
+		}
+	} else {
+		info->ethertype = 0;
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+	}
+
+	info->l2_len += RTE_ETHER_GTP_HLEN;
+}
+
+/* Parse a vxlan header */
+static inline void
+parse_vxlan(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+
+	/* check udp destination port, RTE_VXLAN_DEFAULT_PORT (4789) is the
+	 * default vxlan port (rfc7348) or that the rx offload flag is set
+	 * (i40e only currently)
+	 */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_VXLAN_DEFAULT_PORT))
+		return;
+
+	update_tunnel_outer(info);
+
+	eth_hdr = (struct rte_ether_hdr *)((char *)udp_hdr +
+		sizeof(struct rte_udp_hdr) +
+		sizeof(struct rte_vxlan_hdr));
+
+	parse_ethernet(eth_hdr, info);
+	info->l2_len += RTE_ETHER_VXLAN_HLEN; /* add udp + vxlan */
+}
+
+/* Parse a vxlan-gpe header */
+static inline void
+parse_vxlan_gpe(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vxlan_gpe_hdr *vxlan_gpe_hdr;
+	uint8_t vxlan_gpe_len = sizeof(*vxlan_gpe_hdr);
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(vxlan_gpe_udp_port))
+		return;
+
+	vxlan_gpe_hdr = (struct rte_vxlan_gpe_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+
+	if (!vxlan_gpe_hdr->proto || vxlan_gpe_hdr->proto ==
+	    RTE_VXLAN_GPE_TYPE_IPV4) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_IPV6) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_ETH) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)vxlan_gpe_hdr +
+			  vxlan_gpe_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+
+	info->l2_len += RTE_ETHER_VXLAN_GPE_HLEN;
+}
+
+/* Parse a geneve header */
+static inline void
+parse_geneve(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_geneve_hdr *geneve_hdr;
+	uint16_t geneve_len;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(geneve_udp_port))
+		return;
+
+	geneve_hdr = (struct rte_geneve_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+	geneve_len = sizeof(struct rte_geneve_hdr) + geneve_hdr->opt_len * 4;
+	if (!geneve_hdr->proto || geneve_hdr->proto ==
+	    rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_GENEVE_TYPE_ETH)) {
+		update_tunnel_outer(info);
+		eth_hdr = (struct rte_ether_hdr *)((char *)geneve_hdr +
+			  geneve_len);
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len +=
+		(sizeof(struct rte_udp_hdr) + sizeof(struct rte_geneve_hdr) +
+		((struct rte_geneve_hdr *)geneve_hdr)->opt_len * 4);
+}
+
+/* Parse a gre header */
+static inline void
+parse_gre(struct simple_gre_hdr *gre_hdr, struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	uint8_t gre_len = 0;
+
+	gre_len += sizeof(struct simple_gre_hdr);
+
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_KEY_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_SEQUENCE_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_CHECKSUM_PRESENT))
+		gre_len += GRE_EXT_LEN;
+
+	if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gre_hdr + gre_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_TEB)) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len += gre_len;
+}
+
+/* Parse an encapsulated ip or ipv6 header */
+static inline void
+parse_encap_ip(void *encap_ip, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr = encap_ip;
+	struct rte_ipv6_hdr *ipv6_hdr = encap_ip;
+	uint8_t ip_version;
+
+	ip_version = (ipv4_hdr->version_ihl & 0xf0) >> 4;
+
+	if (ip_version != 4 && ip_version != 6)
+		return;
+
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+
+	if (ip_version == 4) {
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+	} else {
+		parse_ipv6(ipv6_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+	}
+	info->l2_len = 0;
+}
+
+static  inline int
+check_mbuf_len(struct offload_info *info, struct rte_mbuf *m)
+{
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_l2_len != m->outer_l2_len) {
+			PMD_TX_LOG(ERR, "outer_l2_len error in mbuf. Original "
+			"length: %hu, calculated length: %u", m->outer_l2_len,
+			info->outer_l2_len);
+			return -1;
+		}
+		if (info->outer_l3_len != m->outer_l3_len) {
+			PMD_TX_LOG(ERR, "outer_l3_len error in mbuf. Original "
+			"length: %hu,calculated length: %u", m->outer_l3_len,
+			info->outer_l3_len);
+			return -1;
+		}
+	}
+
+	if (info->l2_len != m->l2_len) {
+		PMD_TX_LOG(ERR, "l2_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l2_len,
+		info->l2_len);
+		return -1;
+	}
+	if (info->l3_len != m->l3_len) {
+		PMD_TX_LOG(ERR, "l3_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l3_len,
+		info->l3_len);
+		return -1;
+	}
+	if (info->l4_len != m->l4_len) {
+		PMD_TX_LOG(ERR, "l4_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l4_len,
+		info->l4_len);
+		return -1;
+	}
+
+	return 0;
+}
+
+static  inline int
+check_ether_type(struct offload_info *info, struct rte_mbuf *m)
+{
+	int ret = 0;
+
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+			if (~(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV4` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV6` flag");
+				ret = -1;
+			}
+		} else if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+			if (~(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV6` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV4` flag");
+				ret = -1;
+			}
+		}
+	}
+
+	if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		if (~(m->ol_flags & RTE_MBUF_F_TX_IPV4)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV4` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV6) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx "
+			"offload contains wrong `RTE_MBUF_F_TX_IPV6` flag");
+			ret = -1;
+		}
+	} else if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		if (~(m->ol_flags & RTE_MBUF_F_TX_IPV6)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV6` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV4) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"contains wrong `RTE_MBUF_F_TX_IPV4` flag");
+			ret = -1;
+		}
+	}
+
+	return ret;
+}
+
+/* Check whether the parameters of mubf are correct. */
+__rte_unused static  inline int
+iavf_check_mbuf(struct rte_mbuf *m)
+{
+	struct rte_ether_hdr *eth_hdr;
+	void *l3_hdr = NULL; /* can be IPv4 or IPv6 */
+	struct offload_info info = {0};
+	uint64_t ol_flags = m->ol_flags;
+
+	eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+	parse_ethernet(eth_hdr, &info);
+	l3_hdr = (char *)eth_hdr + info.l2_len;
+	if (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info.l4_proto == IPPROTO_UDP) {
+			struct rte_udp_hdr *udp_hdr;
+
+			udp_hdr = (struct rte_udp_hdr *)
+				((char *)l3_hdr + info.l3_len);
+			parse_gtp(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_GTP)) {
+					PMD_TX_LOG(ERR, "gtp tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			parse_vxlan_gpe(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE)) {
+					PMD_TX_LOG(ERR, "vxlan gpe tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			parse_vxlan(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_VXLAN)) {
+					PMD_TX_LOG(ERR, "vxlan tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			parse_geneve(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_GENEVE)) {
+					PMD_TX_LOG(ERR, "geneve tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			/* Always keep last. */
+			if (unlikely(RTE_ETH_IS_TUNNEL_PKT(m->packet_type)
+				!= 0)) {
+				PMD_TX_LOG(ERR, "Unknown tunnel packet. UDP dst port: %hu",
+					udp_hdr->dst_port);
+					return -1;
+			}
+		} else if (info.l4_proto == IPPROTO_GRE) {
+			struct simple_gre_hdr *gre_hdr;
+
+			gre_hdr = (struct simple_gre_hdr *)((char *)l3_hdr +
+				info.l3_len);
+			parse_gre(gre_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_GRE)) {
+					PMD_TX_LOG(ERR, "gre tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+		} else if (info.l4_proto == IPPROTO_IPIP) {
+			void *encap_ip_hdr;
+
+			encap_ip_hdr = (char *)l3_hdr + info.l3_len;
+			parse_encap_ip(encap_ip_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_IPIP)) {
+					PMD_TX_LOG(ERR, "Ipip tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+		}
+	}
+
+check_len:
+	if (check_mbuf_len(&info, m) != 0)
+		return -1;
+
+	return check_ether_type(&info, m);
+}
+
 /* TX prep functions */
 uint16_t
 iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -3017,6 +3609,13 @@ iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
 				return i;
 			}
 		}
+#ifdef RTE_ETHDEV_DEBUG_TX
+		ret = iavf_check_mbuf(m);
+		if (ret != 0) {
+			rte_errno = EINVAL;
+			return i;
+		}
+#endif
 	}
 
 	return i;
-- 
2.25.1

[PATCH v2] net/iavf: add check for mbuf

[Mingjin Ye]

The scalar Tx path would send wrong mbuf that causes the kernel driver to
fire the MDD event.

This patch adds mbuf detection in tx_prepare to fix this issue, rte_errno
will be set to EINVAL and returned if the verification fails.

Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
Cc: stable@dpdk.org

Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
---
 drivers/net/iavf/iavf_rxtx.c | 647 +++++++++++++++++++++++++++++++++++
 1 file changed, 647 insertions(+)

diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 8d49967538..93138edf01 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -24,12 +24,55 @@
 #include <rte_ip.h>
 #include <rte_net.h>
 #include <rte_vect.h>
+#include <rte_vxlan.h>
+#include <rte_gtp.h>
+#include <rte_geneve.h>
 
 #include "iavf.h"
 #include "iavf_rxtx.h"
 #include "iavf_ipsec_crypto.h"
 #include "rte_pmd_iavf.h"
 
+#define GRE_CHECKSUM_PRESENT	0x8000
+#define GRE_KEY_PRESENT		0x2000
+#define GRE_SEQUENCE_PRESENT	0x1000
+#define GRE_EXT_LEN		4
+#define GRE_SUPPORTED_FIELDS	(GRE_CHECKSUM_PRESENT | GRE_KEY_PRESENT |\
+				 GRE_SEQUENCE_PRESENT)
+
+#ifndef IPPROTO_IPIP
+#define IPPROTO_IPIP 4
+#endif
+#ifndef IPPROTO_GRE
+#define IPPROTO_GRE	47
+#endif
+
+static uint16_t vxlan_gpe_udp_port = RTE_VXLAN_GPE_DEFAULT_PORT;
+static uint16_t geneve_udp_port = RTE_GENEVE_DEFAULT_PORT;
+
+struct simple_gre_hdr {
+	uint16_t flags;
+	uint16_t proto;
+} __rte_packed;
+
+/* structure that caches offload info for the current packet */
+struct offload_info {
+	uint16_t ethertype;
+	uint8_t gso_enable;
+	uint16_t l2_len;
+	uint16_t l3_len;
+	uint16_t l4_len;
+	uint8_t l4_proto;
+	uint8_t is_tunnel;
+	uint16_t outer_ethertype;
+	uint16_t outer_l2_len;
+	uint16_t outer_l3_len;
+	uint8_t outer_l4_proto;
+	uint16_t tso_segsz;
+	uint16_t tunnel_tso_segsz;
+	uint32_t pkt_len;
+};
+
 /* Offset of mbuf dynamic field for protocol extraction's metadata */
 int rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
 
@@ -2949,6 +2992,603 @@ iavf_check_vlan_up2tc(struct iavf_tx_queue *txq, struct rte_mbuf *m)
 	}
 }
 
+/* Parse an IPv4 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv4(struct rte_ipv4_hdr *ipv4_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = rte_ipv4_hdr_len(ipv4_hdr);
+	info->l4_proto = ipv4_hdr->next_proto_id;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv4_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/* Parse an IPv6 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv6(struct rte_ipv6_hdr *ipv6_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = sizeof(struct rte_ipv6_hdr);
+	info->l4_proto = ipv6_hdr->proto;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv6_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/*
+ * Parse an ethernet header to fill the ethertype, l2_len, l3_len and
+ * ipproto. This function is able to recognize IPv4/IPv6 with optional VLAN
+ * headers. The l4_len argument is only set in case of TCP (useful for TSO).
+ */
+static inline void
+parse_ethernet(struct rte_ether_hdr *eth_hdr, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vlan_hdr *vlan_hdr;
+
+	info->l2_len = sizeof(struct rte_ether_hdr);
+	info->ethertype = eth_hdr->ether_type;
+
+	while (info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
+	       info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
+		vlan_hdr = (struct rte_vlan_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		info->l2_len  += sizeof(struct rte_vlan_hdr);
+		info->ethertype = vlan_hdr->eth_proto;
+	}
+
+	switch (info->ethertype) {
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV4):
+		ipv4_hdr = (struct rte_ipv4_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv4(ipv4_hdr, info);
+		break;
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV6):
+		ipv6_hdr = (struct rte_ipv6_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv6(ipv6_hdr, info);
+		break;
+	default:
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+		break;
+	}
+}
+
+/* Fill in outer layers length */
+static inline void
+update_tunnel_outer(struct offload_info *info)
+{
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+	info->outer_l4_proto = info->l4_proto;
+}
+
+/*
+ * Parse a GTP protocol header.
+ * No optional fields and next extension header type.
+ */
+static inline void
+parse_gtp(struct rte_udp_hdr *udp_hdr,
+	  struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_gtp_hdr *gtp_hdr;
+	uint8_t gtp_len = sizeof(*gtp_hdr);
+	uint8_t ip_ver;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->src_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPU_UDP_PORT))
+		return;
+
+	update_tunnel_outer(info);
+	info->l2_len = 0;
+
+	gtp_hdr = (struct rte_gtp_hdr *)((char *)udp_hdr +
+		  sizeof(struct rte_udp_hdr));
+
+	/*
+	 * Check message type. If message type is 0xff, it is
+	 * a GTP data packet. If not, it is a GTP control packet
+	 */
+	if (gtp_hdr->msg_type == 0xff) {
+		ip_ver = *(uint8_t *)((char *)udp_hdr +
+			 sizeof(struct rte_udp_hdr) +
+			 sizeof(struct rte_gtp_hdr));
+		ip_ver = (ip_ver) & 0xf0;
+
+		if (ip_ver == RTE_GTP_TYPE_IPV4) {
+			ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+			parse_ipv4(ipv4_hdr, info);
+		} else if (ip_ver == RTE_GTP_TYPE_IPV6) {
+			ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+			parse_ipv6(ipv6_hdr, info);
+		}
+	} else {
+		info->ethertype = 0;
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+	}
+
+	info->l2_len += RTE_ETHER_GTP_HLEN;
+}
+
+/* Parse a vxlan header */
+static inline void
+parse_vxlan(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+
+	/* check udp destination port, RTE_VXLAN_DEFAULT_PORT (4789) is the
+	 * default vxlan port (rfc7348) or that the rx offload flag is set
+	 * (i40e only currently)
+	 */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_VXLAN_DEFAULT_PORT))
+		return;
+
+	update_tunnel_outer(info);
+
+	eth_hdr = (struct rte_ether_hdr *)((char *)udp_hdr +
+		sizeof(struct rte_udp_hdr) +
+		sizeof(struct rte_vxlan_hdr));
+
+	parse_ethernet(eth_hdr, info);
+	info->l2_len += RTE_ETHER_VXLAN_HLEN; /* add udp + vxlan */
+}
+
+/* Parse a vxlan-gpe header */
+static inline void
+parse_vxlan_gpe(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vxlan_gpe_hdr *vxlan_gpe_hdr;
+	uint8_t vxlan_gpe_len = sizeof(*vxlan_gpe_hdr);
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(vxlan_gpe_udp_port))
+		return;
+
+	vxlan_gpe_hdr = (struct rte_vxlan_gpe_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+
+	if (!vxlan_gpe_hdr->proto || vxlan_gpe_hdr->proto ==
+	    RTE_VXLAN_GPE_TYPE_IPV4) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_IPV6) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_ETH) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)vxlan_gpe_hdr +
+			  vxlan_gpe_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+
+	info->l2_len += RTE_ETHER_VXLAN_GPE_HLEN;
+}
+
+/* Parse a geneve header */
+static inline void
+parse_geneve(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_geneve_hdr *geneve_hdr;
+	uint16_t geneve_len;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(geneve_udp_port))
+		return;
+
+	geneve_hdr = (struct rte_geneve_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+	geneve_len = sizeof(struct rte_geneve_hdr) + geneve_hdr->opt_len * 4;
+	if (!geneve_hdr->proto || geneve_hdr->proto ==
+	    rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_GENEVE_TYPE_ETH)) {
+		update_tunnel_outer(info);
+		eth_hdr = (struct rte_ether_hdr *)((char *)geneve_hdr +
+			  geneve_len);
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len +=
+		(sizeof(struct rte_udp_hdr) + sizeof(struct rte_geneve_hdr) +
+		((struct rte_geneve_hdr *)geneve_hdr)->opt_len * 4);
+}
+
+/* Parse a gre header */
+static inline void
+parse_gre(struct simple_gre_hdr *gre_hdr, struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	uint8_t gre_len = 0;
+
+	gre_len += sizeof(struct simple_gre_hdr);
+
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_KEY_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_SEQUENCE_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_CHECKSUM_PRESENT))
+		gre_len += GRE_EXT_LEN;
+
+	if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gre_hdr + gre_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_TEB)) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len += gre_len;
+}
+
+/* Parse an encapsulated ip or ipv6 header */
+static inline void
+parse_encap_ip(void *encap_ip, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr = encap_ip;
+	struct rte_ipv6_hdr *ipv6_hdr = encap_ip;
+	uint8_t ip_version;
+
+	ip_version = (ipv4_hdr->version_ihl & 0xf0) >> 4;
+
+	if (ip_version != 4 && ip_version != 6)
+		return;
+
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+
+	if (ip_version == 4) {
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+	} else {
+		parse_ipv6(ipv6_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+	}
+	info->l2_len = 0;
+}
+
+static  inline int
+check_mbuf_len(struct offload_info *info, struct rte_mbuf *m)
+{
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_l2_len != m->outer_l2_len) {
+			PMD_TX_LOG(ERR, "outer_l2_len error in mbuf. Original "
+			"length: %hu, calculated length: %u", m->outer_l2_len,
+			info->outer_l2_len);
+			return -1;
+		}
+		if (info->outer_l3_len != m->outer_l3_len) {
+			PMD_TX_LOG(ERR, "outer_l3_len error in mbuf. Original "
+			"length: %hu,calculated length: %u", m->outer_l3_len,
+			info->outer_l3_len);
+			return -1;
+		}
+	}
+
+	if (info->l2_len != m->l2_len) {
+		PMD_TX_LOG(ERR, "l2_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l2_len,
+		info->l2_len);
+		return -1;
+	}
+	if (info->l3_len != m->l3_len) {
+		PMD_TX_LOG(ERR, "l3_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l3_len,
+		info->l3_len);
+		return -1;
+	}
+	if (info->l4_len != m->l4_len) {
+		PMD_TX_LOG(ERR, "l4_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l4_len,
+		info->l4_len);
+		return -1;
+	}
+
+	return 0;
+}
+
+static  inline int
+check_ether_type(struct offload_info *info, struct rte_mbuf *m)
+{
+	int ret = 0;
+
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+			if (!(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV4` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV6` flag");
+				ret = -1;
+			}
+		} else if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+			if (!(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV6` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV4` flag");
+				ret = -1;
+			}
+		}
+	}
+
+	if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		if (!(m->ol_flags & RTE_MBUF_F_TX_IPV4)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV4` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV6) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx "
+			"offload contains wrong `RTE_MBUF_F_TX_IPV6` flag");
+			ret = -1;
+		}
+	} else if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		if (!(m->ol_flags & RTE_MBUF_F_TX_IPV6)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV6` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV4) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"contains wrong `RTE_MBUF_F_TX_IPV4` flag");
+			ret = -1;
+		}
+	}
+
+	return ret;
+}
+
+/* Check whether the parameters of mubf are correct. */
+__rte_unused static  inline int
+iavf_check_mbuf(struct rte_mbuf *m)
+{
+	struct rte_ether_hdr *eth_hdr;
+	void *l3_hdr = NULL; /* can be IPv4 or IPv6 */
+	struct offload_info info = {0};
+	uint64_t ol_flags = m->ol_flags;
+	uint64_t tunnel_type = ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK;
+
+	eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+	parse_ethernet(eth_hdr, &info);
+	l3_hdr = (char *)eth_hdr + info.l2_len;
+	if (info.l4_proto == IPPROTO_UDP) {
+		struct rte_udp_hdr *udp_hdr;
+
+		udp_hdr = (struct rte_udp_hdr *)
+			((char *)l3_hdr + info.l3_len);
+		parse_gtp(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "gtp tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_GTP` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GTP) {
+				PMD_TX_LOG(ERR, "gtp tunnel packet, tx offload has wrong "
+				"`%s` flag, correct is `RTE_MBUF_F_TX_TUNNEL_GTP` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		parse_vxlan_gpe(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "vxlan gpe tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE) {
+				PMD_TX_LOG(ERR, "vxlan gpe tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		parse_vxlan(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "vxlan tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_VXLAN` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_VXLAN) {
+				PMD_TX_LOG(ERR, "vxlan tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_VXLAN` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		parse_geneve(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "geneve tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_GENEVE` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GENEVE) {
+				PMD_TX_LOG(ERR, "geneve tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_GENEVE` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		/* Always keep last. */
+		if (unlikely(RTE_ETH_IS_TUNNEL_PKT(m->packet_type)
+			!= 0)) {
+			PMD_TX_LOG(ERR, "Unknown tunnel packet. UDP dst port: %hu",
+				udp_hdr->dst_port);
+				return -1;
+		}
+	} else if (info.l4_proto == IPPROTO_GRE) {
+		struct simple_gre_hdr *gre_hdr;
+
+		gre_hdr = (struct simple_gre_hdr *)((char *)l3_hdr +
+			info.l3_len);
+		parse_gre(gre_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "gre tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_GRE` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GRE) {
+				PMD_TX_LOG(ERR, "gre tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_GRE` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+	} else if (info.l4_proto == IPPROTO_IPIP) {
+		void *encap_ip_hdr;
+
+		encap_ip_hdr = (char *)l3_hdr + info.l3_len;
+		parse_encap_ip(encap_ip_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "Ipip tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_IPIP` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_IPIP) {
+				PMD_TX_LOG(ERR, "Ipip tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_IPIP` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+	}
+
+
+
+check_len:
+	if (check_mbuf_len(&info, m) != 0)
+		return -1;
+
+	return check_ether_type(&info, m);
+}
+
 /* TX prep functions */
 uint16_t
 iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -3017,6 +3657,13 @@ iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
 				return i;
 			}
 		}
+#ifdef RTE_ETHDEV_DEBUG_TX
+		ret = iavf_check_mbuf(m);
+		if (ret != 0) {
+			rte_errno = EINVAL;
+			return i;
+		}
+#endif
 	}
 
 	return i;
-- 
2.25.1

RE: [PATCH v2] net/iavf: add check for mbuf

[Ye, MingjinX]

Hi All,

Could you please review and provide suggestions if any.

Thanks,
Mingjin

> -----Original Message-----
> From: Ye, MingjinX <mingjinx.ye@intel.com>
> Sent: 2023年2月2日 18:04
> To: dev@dpdk.org
> Cc: Yang, Qiming <qiming.yang@intel.com>; stable@dpdk.org; Zhou, YidingX
> <yidingx.zhou@intel.com>; Ye, MingjinX <mingjinx.ye@intel.com>; Wu,
> Jingjing <jingjing.wu@intel.com>; Xing, Beilei <beilei.xing@intel.com>
> Subject: [PATCH v2] net/iavf: add check for mbuf
> 
> The scalar Tx path would send wrong mbuf that causes the kernel driver to
> fire the MDD event.
> 
> This patch adds mbuf detection in tx_prepare to fix this issue, rte_errno will
> be set to EINVAL and returned if the verification fails.
> 
> Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
> Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
> Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
> ---
>  drivers/net/iavf/iavf_rxtx.c | 647
> +++++++++++++++++++++++++++++++++++
>  1 file changed, 647 insertions(+)
> 
> diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c index
> 8d49967538..93138edf01 100644
> --- a/drivers/net/iavf/iavf_rxtx.c
> +++ b/drivers/net/iavf/iavf_rxtx.c
> @@ -24,12 +24,55 @@
>  #include <rte_ip.h>
>  #include <rte_net.h>
>  #include <rte_vect.h>
> +#include <rte_vxlan.h>
> +#include <rte_gtp.h>
> +#include <rte_geneve.h>
> 
>  #include "iavf.h"
>  #include "iavf_rxtx.h"
>  #include "iavf_ipsec_crypto.h"
>  #include "rte_pmd_iavf.h"
> 
> +#define GRE_CHECKSUM_PRESENT	0x8000
> +#define GRE_KEY_PRESENT		0x2000
> +#define GRE_SEQUENCE_PRESENT	0x1000
> +#define GRE_EXT_LEN		4
> +#define GRE_SUPPORTED_FIELDS	(GRE_CHECKSUM_PRESENT |
> GRE_KEY_PRESENT |\
> +				 GRE_SEQUENCE_PRESENT)
> +
> +#ifndef IPPROTO_IPIP
> +#define IPPROTO_IPIP 4
> +#endif
> +#ifndef IPPROTO_GRE
> +#define IPPROTO_GRE	47
> +#endif
> +
> +static uint16_t vxlan_gpe_udp_port = RTE_VXLAN_GPE_DEFAULT_PORT;
> static
> +uint16_t geneve_udp_port = RTE_GENEVE_DEFAULT_PORT;
> +
> +struct simple_gre_hdr {
> +	uint16_t flags;
> +	uint16_t proto;
> +} __rte_packed;
> +
> +/* structure that caches offload info for the current packet */ struct
> +offload_info {
> +	uint16_t ethertype;
> +	uint8_t gso_enable;
> +	uint16_t l2_len;
> +	uint16_t l3_len;
> +	uint16_t l4_len;
> +	uint8_t l4_proto;
> +	uint8_t is_tunnel;
> +	uint16_t outer_ethertype;
> +	uint16_t outer_l2_len;
> +	uint16_t outer_l3_len;
> +	uint8_t outer_l4_proto;
> +	uint16_t tso_segsz;
> +	uint16_t tunnel_tso_segsz;
> +	uint32_t pkt_len;
> +};
> +
>  /* Offset of mbuf dynamic field for protocol extraction's metadata */  int
> rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
> 
> @@ -2949,6 +2992,603 @@ iavf_check_vlan_up2tc(struct iavf_tx_queue
> *txq, struct rte_mbuf *m)
>  	}
>  }
> 
> +/* Parse an IPv4 header to fill l3_len, l4_len, and l4_proto */ static
> +inline void parse_ipv4(struct rte_ipv4_hdr *ipv4_hdr, struct
> +offload_info *info) {
> +	struct rte_tcp_hdr *tcp_hdr;
> +
> +	info->l3_len = rte_ipv4_hdr_len(ipv4_hdr);
> +	info->l4_proto = ipv4_hdr->next_proto_id;
> +
> +	/* only fill l4_len for TCP, it's useful for TSO */
> +	if (info->l4_proto == IPPROTO_TCP) {
> +		tcp_hdr = (struct rte_tcp_hdr *)
> +			((char *)ipv4_hdr + info->l3_len);
> +		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
> +	} else if (info->l4_proto == IPPROTO_UDP) {
> +		info->l4_len = sizeof(struct rte_udp_hdr);
> +	} else {
> +		info->l4_len = 0;
> +	}
> +}
> +
> +/* Parse an IPv6 header to fill l3_len, l4_len, and l4_proto */ static
> +inline void parse_ipv6(struct rte_ipv6_hdr *ipv6_hdr, struct
> +offload_info *info) {
> +	struct rte_tcp_hdr *tcp_hdr;
> +
> +	info->l3_len = sizeof(struct rte_ipv6_hdr);
> +	info->l4_proto = ipv6_hdr->proto;
> +
> +	/* only fill l4_len for TCP, it's useful for TSO */
> +	if (info->l4_proto == IPPROTO_TCP) {
> +		tcp_hdr = (struct rte_tcp_hdr *)
> +			((char *)ipv6_hdr + info->l3_len);
> +		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
> +	} else if (info->l4_proto == IPPROTO_UDP) {
> +		info->l4_len = sizeof(struct rte_udp_hdr);
> +	} else {
> +		info->l4_len = 0;
> +	}
> +}
> +
> +/*
> + * Parse an ethernet header to fill the ethertype, l2_len, l3_len and
> + * ipproto. This function is able to recognize IPv4/IPv6 with optional
> +VLAN
> + * headers. The l4_len argument is only set in case of TCP (useful for TSO).
> + */
> +static inline void
> +parse_ethernet(struct rte_ether_hdr *eth_hdr, struct offload_info
> +*info) {
> +	struct rte_ipv4_hdr *ipv4_hdr;
> +	struct rte_ipv6_hdr *ipv6_hdr;
> +	struct rte_vlan_hdr *vlan_hdr;
> +
> +	info->l2_len = sizeof(struct rte_ether_hdr);
> +	info->ethertype = eth_hdr->ether_type;
> +
> +	while (info->ethertype ==
> rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
> +	       info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ))
> {
> +		vlan_hdr = (struct rte_vlan_hdr *)
> +			((char *)eth_hdr + info->l2_len);
> +		info->l2_len  += sizeof(struct rte_vlan_hdr);
> +		info->ethertype = vlan_hdr->eth_proto;
> +	}
> +
> +	switch (info->ethertype) {
> +	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV4):
> +		ipv4_hdr = (struct rte_ipv4_hdr *)
> +			((char *)eth_hdr + info->l2_len);
> +		parse_ipv4(ipv4_hdr, info);
> +		break;
> +	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV6):
> +		ipv6_hdr = (struct rte_ipv6_hdr *)
> +			((char *)eth_hdr + info->l2_len);
> +		parse_ipv6(ipv6_hdr, info);
> +		break;
> +	default:
> +		info->l4_len = 0;
> +		info->l3_len = 0;
> +		info->l4_proto = 0;
> +		break;
> +	}
> +}
> +
> +/* Fill in outer layers length */
> +static inline void
> +update_tunnel_outer(struct offload_info *info) {
> +	info->is_tunnel = 1;
> +	info->outer_ethertype = info->ethertype;
> +	info->outer_l2_len = info->l2_len;
> +	info->outer_l3_len = info->l3_len;
> +	info->outer_l4_proto = info->l4_proto; }
> +
> +/*
> + * Parse a GTP protocol header.
> + * No optional fields and next extension header type.
> + */
> +static inline void
> +parse_gtp(struct rte_udp_hdr *udp_hdr,
> +	  struct offload_info *info)
> +{
> +	struct rte_ipv4_hdr *ipv4_hdr;
> +	struct rte_ipv6_hdr *ipv6_hdr;
> +	struct rte_gtp_hdr *gtp_hdr;
> +	uint8_t gtp_len = sizeof(*gtp_hdr);
> +	uint8_t ip_ver;
> +
> +	/* Check udp destination port. */
> +	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT)
> &&
> +	    udp_hdr->src_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT)
> &&
> +	    udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPU_UDP_PORT))
> +		return;
> +
> +	update_tunnel_outer(info);
> +	info->l2_len = 0;
> +
> +	gtp_hdr = (struct rte_gtp_hdr *)((char *)udp_hdr +
> +		  sizeof(struct rte_udp_hdr));
> +
> +	/*
> +	 * Check message type. If message type is 0xff, it is
> +	 * a GTP data packet. If not, it is a GTP control packet
> +	 */
> +	if (gtp_hdr->msg_type == 0xff) {
> +		ip_ver = *(uint8_t *)((char *)udp_hdr +
> +			 sizeof(struct rte_udp_hdr) +
> +			 sizeof(struct rte_gtp_hdr));
> +		ip_ver = (ip_ver) & 0xf0;
> +
> +		if (ip_ver == RTE_GTP_TYPE_IPV4) {
> +			ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gtp_hdr +
> +				   gtp_len);
> +			info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
> +			parse_ipv4(ipv4_hdr, info);
> +		} else if (ip_ver == RTE_GTP_TYPE_IPV6) {
> +			ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gtp_hdr +
> +				   gtp_len);
> +			info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
> +			parse_ipv6(ipv6_hdr, info);
> +		}
> +	} else {
> +		info->ethertype = 0;
> +		info->l4_len = 0;
> +		info->l3_len = 0;
> +		info->l4_proto = 0;
> +	}
> +
> +	info->l2_len += RTE_ETHER_GTP_HLEN;
> +}
> +
> +/* Parse a vxlan header */
> +static inline void
> +parse_vxlan(struct rte_udp_hdr *udp_hdr,
> +	    struct offload_info *info)
> +{
> +	struct rte_ether_hdr *eth_hdr;
> +
> +	/* check udp destination port, RTE_VXLAN_DEFAULT_PORT (4789) is
> the
> +	 * default vxlan port (rfc7348) or that the rx offload flag is set
> +	 * (i40e only currently)
> +	 */
> +	if (udp_hdr->dst_port !=
> rte_cpu_to_be_16(RTE_VXLAN_DEFAULT_PORT))
> +		return;
> +
> +	update_tunnel_outer(info);
> +
> +	eth_hdr = (struct rte_ether_hdr *)((char *)udp_hdr +
> +		sizeof(struct rte_udp_hdr) +
> +		sizeof(struct rte_vxlan_hdr));
> +
> +	parse_ethernet(eth_hdr, info);
> +	info->l2_len += RTE_ETHER_VXLAN_HLEN; /* add udp + vxlan */ }
> +
> +/* Parse a vxlan-gpe header */
> +static inline void
> +parse_vxlan_gpe(struct rte_udp_hdr *udp_hdr,
> +	    struct offload_info *info)
> +{
> +	struct rte_ether_hdr *eth_hdr;
> +	struct rte_ipv4_hdr *ipv4_hdr;
> +	struct rte_ipv6_hdr *ipv6_hdr;
> +	struct rte_vxlan_gpe_hdr *vxlan_gpe_hdr;
> +	uint8_t vxlan_gpe_len = sizeof(*vxlan_gpe_hdr);
> +
> +	/* Check udp destination port. */
> +	if (udp_hdr->dst_port != rte_cpu_to_be_16(vxlan_gpe_udp_port))
> +		return;
> +
> +	vxlan_gpe_hdr = (struct rte_vxlan_gpe_hdr *)((char *)udp_hdr +
> +				sizeof(struct rte_udp_hdr));
> +
> +	if (!vxlan_gpe_hdr->proto || vxlan_gpe_hdr->proto ==
> +	    RTE_VXLAN_GPE_TYPE_IPV4) {
> +		update_tunnel_outer(info);
> +
> +		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)vxlan_gpe_hdr +
> +			   vxlan_gpe_len);
> +
> +		parse_ipv4(ipv4_hdr, info);
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
> +		info->l2_len = 0;
> +
> +	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_IPV6) {
> +		update_tunnel_outer(info);
> +
> +		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)vxlan_gpe_hdr +
> +			   vxlan_gpe_len);
> +
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
> +		parse_ipv6(ipv6_hdr, info);
> +		info->l2_len = 0;
> +
> +	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_ETH) {
> +		update_tunnel_outer(info);
> +
> +		eth_hdr = (struct rte_ether_hdr *)((char *)vxlan_gpe_hdr +
> +			  vxlan_gpe_len);
> +
> +		parse_ethernet(eth_hdr, info);
> +	} else {
> +		return;
> +	}
> +
> +
> +	info->l2_len += RTE_ETHER_VXLAN_GPE_HLEN; }
> +
> +/* Parse a geneve header */
> +static inline void
> +parse_geneve(struct rte_udp_hdr *udp_hdr,
> +	    struct offload_info *info)
> +{
> +	struct rte_ether_hdr *eth_hdr;
> +	struct rte_ipv4_hdr *ipv4_hdr;
> +	struct rte_ipv6_hdr *ipv6_hdr;
> +	struct rte_geneve_hdr *geneve_hdr;
> +	uint16_t geneve_len;
> +
> +	/* Check udp destination port. */
> +	if (udp_hdr->dst_port != rte_cpu_to_be_16(geneve_udp_port))
> +		return;
> +
> +	geneve_hdr = (struct rte_geneve_hdr *)((char *)udp_hdr +
> +				sizeof(struct rte_udp_hdr));
> +	geneve_len = sizeof(struct rte_geneve_hdr) + geneve_hdr->opt_len
> * 4;
> +	if (!geneve_hdr->proto || geneve_hdr->proto ==
> +	    rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
> +		update_tunnel_outer(info);
> +		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)geneve_hdr +
> +			   geneve_len);
> +		parse_ipv4(ipv4_hdr, info);
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
> +		info->l2_len = 0;
> +	} else if (geneve_hdr->proto ==
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
> +		update_tunnel_outer(info);
> +		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)geneve_hdr +
> +			   geneve_len);
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
> +		parse_ipv6(ipv6_hdr, info);
> +		info->l2_len = 0;
> +
> +	} else if (geneve_hdr->proto ==
> rte_cpu_to_be_16(RTE_GENEVE_TYPE_ETH)) {
> +		update_tunnel_outer(info);
> +		eth_hdr = (struct rte_ether_hdr *)((char *)geneve_hdr +
> +			  geneve_len);
> +		parse_ethernet(eth_hdr, info);
> +	} else {
> +		return;
> +	}
> +
> +	info->l2_len +=
> +		(sizeof(struct rte_udp_hdr) + sizeof(struct rte_geneve_hdr)
> +
> +		((struct rte_geneve_hdr *)geneve_hdr)->opt_len * 4); }
> +
> +/* Parse a gre header */
> +static inline void
> +parse_gre(struct simple_gre_hdr *gre_hdr, struct offload_info *info) {
> +	struct rte_ether_hdr *eth_hdr;
> +	struct rte_ipv4_hdr *ipv4_hdr;
> +	struct rte_ipv6_hdr *ipv6_hdr;
> +	uint8_t gre_len = 0;
> +
> +	gre_len += sizeof(struct simple_gre_hdr);
> +
> +	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_KEY_PRESENT))
> +		gre_len += GRE_EXT_LEN;
> +	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_SEQUENCE_PRESENT))
> +		gre_len += GRE_EXT_LEN;
> +	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_CHECKSUM_PRESENT))
> +		gre_len += GRE_EXT_LEN;
> +
> +	if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
> +		update_tunnel_outer(info);
> +
> +		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gre_hdr + gre_len);
> +
> +		parse_ipv4(ipv4_hdr, info);
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
> +		info->l2_len = 0;
> +
> +	} else if (gre_hdr->proto ==
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
> +		update_tunnel_outer(info);
> +
> +		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gre_hdr + gre_len);
> +
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
> +		parse_ipv6(ipv6_hdr, info);
> +		info->l2_len = 0;
> +
> +	} else if (gre_hdr->proto ==
> rte_cpu_to_be_16(RTE_ETHER_TYPE_TEB)) {
> +		update_tunnel_outer(info);
> +
> +		eth_hdr = (struct rte_ether_hdr *)((char *)gre_hdr +
> gre_len);
> +
> +		parse_ethernet(eth_hdr, info);
> +	} else {
> +		return;
> +	}
> +
> +	info->l2_len += gre_len;
> +}
> +
> +/* Parse an encapsulated ip or ipv6 header */ static inline void
> +parse_encap_ip(void *encap_ip, struct offload_info *info) {
> +	struct rte_ipv4_hdr *ipv4_hdr = encap_ip;
> +	struct rte_ipv6_hdr *ipv6_hdr = encap_ip;
> +	uint8_t ip_version;
> +
> +	ip_version = (ipv4_hdr->version_ihl & 0xf0) >> 4;
> +
> +	if (ip_version != 4 && ip_version != 6)
> +		return;
> +
> +	info->is_tunnel = 1;
> +	info->outer_ethertype = info->ethertype;
> +	info->outer_l2_len = info->l2_len;
> +	info->outer_l3_len = info->l3_len;
> +
> +	if (ip_version == 4) {
> +		parse_ipv4(ipv4_hdr, info);
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
> +	} else {
> +		parse_ipv6(ipv6_hdr, info);
> +		info->ethertype =
> rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
> +	}
> +	info->l2_len = 0;
> +}
> +
> +static  inline int
> +check_mbuf_len(struct offload_info *info, struct rte_mbuf *m) {
> +	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
> +		if (info->outer_l2_len != m->outer_l2_len) {
> +			PMD_TX_LOG(ERR, "outer_l2_len error in mbuf.
> Original "
> +			"length: %hu, calculated length: %u", m-
> >outer_l2_len,
> +			info->outer_l2_len);
> +			return -1;
> +		}
> +		if (info->outer_l3_len != m->outer_l3_len) {
> +			PMD_TX_LOG(ERR, "outer_l3_len error in mbuf.
> Original "
> +			"length: %hu,calculated length: %u", m-
> >outer_l3_len,
> +			info->outer_l3_len);
> +			return -1;
> +		}
> +	}
> +
> +	if (info->l2_len != m->l2_len) {
> +		PMD_TX_LOG(ERR, "l2_len error in mbuf. Original "
> +		"length: %hu, calculated length: %u", m->l2_len,
> +		info->l2_len);
> +		return -1;
> +	}
> +	if (info->l3_len != m->l3_len) {
> +		PMD_TX_LOG(ERR, "l3_len error in mbuf. Original "
> +		"length: %hu, calculated length: %u", m->l3_len,
> +		info->l3_len);
> +		return -1;
> +	}
> +	if (info->l4_len != m->l4_len) {
> +		PMD_TX_LOG(ERR, "l4_len error in mbuf. Original "
> +		"length: %hu, calculated length: %u", m->l4_len,
> +		info->l4_len);
> +		return -1;
> +	}
> +
> +	return 0;
> +}
> +
> +static  inline int
> +check_ether_type(struct offload_info *info, struct rte_mbuf *m) {
> +	int ret = 0;
> +
> +	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
> +		if (info->outer_ethertype ==
> +			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
> +			if (!(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4)) {
> +				PMD_TX_LOG(ERR, "Outer ethernet type is
> ipv4, "
> +				"tx offload missing
> `RTE_MBUF_F_TX_OUTER_IPV4` flag.");
> +				ret = -1;
> +			}
> +			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6) {
> +				PMD_TX_LOG(ERR, "Outer ethernet type is
> ipv4, tx "
> +				"offload contains wrong
> `RTE_MBUF_F_TX_OUTER_IPV6` flag");
> +				ret = -1;
> +			}
> +		} else if (info->outer_ethertype ==
> +			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
> +			if (!(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6)) {
> +				PMD_TX_LOG(ERR, "Outer ethernet type is
> ipv6, "
> +				"tx offload missing
> `RTE_MBUF_F_TX_OUTER_IPV6` flag.");
> +				ret = -1;
> +			}
> +			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4) {
> +				PMD_TX_LOG(ERR, "Outer ethernet type is
> ipv6, tx "
> +				"offload contains wrong
> `RTE_MBUF_F_TX_OUTER_IPV4` flag");
> +				ret = -1;
> +			}
> +		}
> +	}
> +
> +	if (info->ethertype ==
> +		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
> +		if (!(m->ol_flags & RTE_MBUF_F_TX_IPV4)) {
> +			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx offload
> "
> +			"missing `RTE_MBUF_F_TX_IPV4` flag.");
> +			ret = -1;
> +		}
> +		if (m->ol_flags & RTE_MBUF_F_TX_IPV6) {
> +			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx "
> +			"offload contains wrong `RTE_MBUF_F_TX_IPV6`
> flag");
> +			ret = -1;
> +		}
> +	} else if (info->ethertype ==
> +		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
> +		if (!(m->ol_flags & RTE_MBUF_F_TX_IPV6)) {
> +			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload
> "
> +			"missing `RTE_MBUF_F_TX_IPV6` flag.");
> +			ret = -1;
> +		}
> +		if (m->ol_flags & RTE_MBUF_F_TX_IPV4) {
> +			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload
> "
> +			"contains wrong `RTE_MBUF_F_TX_IPV4` flag");
> +			ret = -1;
> +		}
> +	}
> +
> +	return ret;
> +}
> +
> +/* Check whether the parameters of mubf are correct. */ __rte_unused
> +static  inline int iavf_check_mbuf(struct rte_mbuf *m) {
> +	struct rte_ether_hdr *eth_hdr;
> +	void *l3_hdr = NULL; /* can be IPv4 or IPv6 */
> +	struct offload_info info = {0};
> +	uint64_t ol_flags = m->ol_flags;
> +	uint64_t tunnel_type = ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK;
> +
> +	eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
> +	parse_ethernet(eth_hdr, &info);
> +	l3_hdr = (char *)eth_hdr + info.l2_len;
> +	if (info.l4_proto == IPPROTO_UDP) {
> +		struct rte_udp_hdr *udp_hdr;
> +
> +		udp_hdr = (struct rte_udp_hdr *)
> +			((char *)l3_hdr + info.l3_len);
> +		parse_gtp(udp_hdr, &info);
> +		if (info.is_tunnel) {
> +			if (!tunnel_type) {
> +				PMD_TX_LOG(ERR, "gtp tunnel packet
> missing tx "
> +				"offload missing
> `RTE_MBUF_F_TX_TUNNEL_GTP` flag.");
> +				return -1;
> +			}
> +			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GTP) {
> +				PMD_TX_LOG(ERR, "gtp tunnel packet, tx
> offload has wrong "
> +				"`%s` flag, correct is
> `RTE_MBUF_F_TX_TUNNEL_GTP` flag",
> +				rte_get_tx_ol_flag_name(tunnel_type));
> +				return -1;
> +			}
> +			goto check_len;
> +		}
> +		parse_vxlan_gpe(udp_hdr, &info);
> +		if (info.is_tunnel) {
> +			if (!tunnel_type) {
> +				PMD_TX_LOG(ERR, "vxlan gpe tunnel packet
> missing tx "
> +				"offload missing
> `RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE` flag.");
> +				return -1;
> +			}
> +			if (tunnel_type !=
> RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE) {
> +				PMD_TX_LOG(ERR, "vxlan gpe tunnel packet,
> tx offload has "
> +				"wrong `%s` flag, correct is "
> +				"`RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE`
> flag",
> +				rte_get_tx_ol_flag_name(tunnel_type));
> +				return -1;
> +			}
> +			goto check_len;
> +		}
> +		parse_vxlan(udp_hdr, &info);
> +		if (info.is_tunnel) {
> +			if (!tunnel_type) {
> +				PMD_TX_LOG(ERR, "vxlan tunnel packet
> missing tx "
> +				"offload missing
> `RTE_MBUF_F_TX_TUNNEL_VXLAN` flag.");
> +				return -1;
> +			}
> +			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_VXLAN)
> {
> +				PMD_TX_LOG(ERR, "vxlan tunnel packet, tx
> offload has "
> +				"wrong `%s` flag, correct is "
> +				"`RTE_MBUF_F_TX_TUNNEL_VXLAN` flag",
> +				rte_get_tx_ol_flag_name(tunnel_type));
> +				return -1;
> +			}
> +			goto check_len;
> +		}
> +		parse_geneve(udp_hdr, &info);
> +		if (info.is_tunnel) {
> +			if (!tunnel_type) {
> +				PMD_TX_LOG(ERR, "geneve tunnel packet
> missing tx "
> +				"offload missing
> `RTE_MBUF_F_TX_TUNNEL_GENEVE` flag.");
> +				return -1;
> +			}
> +			if (tunnel_type !=
> RTE_MBUF_F_TX_TUNNEL_GENEVE) {
> +				PMD_TX_LOG(ERR, "geneve tunnel packet,
> tx offload has "
> +				"wrong `%s` flag, correct is "
> +				"`RTE_MBUF_F_TX_TUNNEL_GENEVE` flag",
> +				rte_get_tx_ol_flag_name(tunnel_type));
> +				return -1;
> +			}
> +			goto check_len;
> +		}
> +		/* Always keep last. */
> +		if (unlikely(RTE_ETH_IS_TUNNEL_PKT(m->packet_type)
> +			!= 0)) {
> +			PMD_TX_LOG(ERR, "Unknown tunnel packet. UDP
> dst port: %hu",
> +				udp_hdr->dst_port);
> +				return -1;
> +		}
> +	} else if (info.l4_proto == IPPROTO_GRE) {
> +		struct simple_gre_hdr *gre_hdr;
> +
> +		gre_hdr = (struct simple_gre_hdr *)((char *)l3_hdr +
> +			info.l3_len);
> +		parse_gre(gre_hdr, &info);
> +		if (info.is_tunnel) {
> +			if (!tunnel_type) {
> +				PMD_TX_LOG(ERR, "gre tunnel packet
> missing tx "
> +				"offload missing
> `RTE_MBUF_F_TX_TUNNEL_GRE` flag.");
> +				return -1;
> +			}
> +			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GRE) {
> +				PMD_TX_LOG(ERR, "gre tunnel packet, tx
> offload has "
> +				"wrong `%s` flag, correct is "
> +				"`RTE_MBUF_F_TX_TUNNEL_GRE` flag",
> +				rte_get_tx_ol_flag_name(tunnel_type));
> +				return -1;
> +			}
> +			goto check_len;
> +		}
> +	} else if (info.l4_proto == IPPROTO_IPIP) {
> +		void *encap_ip_hdr;
> +
> +		encap_ip_hdr = (char *)l3_hdr + info.l3_len;
> +		parse_encap_ip(encap_ip_hdr, &info);
> +		if (info.is_tunnel) {
> +			if (!tunnel_type) {
> +				PMD_TX_LOG(ERR, "Ipip tunnel packet
> missing tx "
> +				"offload missing
> `RTE_MBUF_F_TX_TUNNEL_IPIP` flag.");
> +				return -1;
> +			}
> +			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_IPIP) {
> +				PMD_TX_LOG(ERR, "Ipip tunnel packet, tx
> offload has "
> +				"wrong `%s` flag, correct is "
> +				"`RTE_MBUF_F_TX_TUNNEL_IPIP` flag",
> +				rte_get_tx_ol_flag_name(tunnel_type));
> +				return -1;
> +			}
> +			goto check_len;
> +		}
> +	}
> +
> +
> +
> +check_len:
> +	if (check_mbuf_len(&info, m) != 0)
> +		return -1;
> +
> +	return check_ether_type(&info, m);
> +}
> +
>  /* TX prep functions */
>  uint16_t
>  iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
> @@ -3017,6 +3657,13 @@ iavf_prep_pkts(__rte_unused void *tx_queue,
> struct rte_mbuf **tx_pkts,
>  				return i;
>  			}
>  		}
> +#ifdef RTE_ETHDEV_DEBUG_TX
> +		ret = iavf_check_mbuf(m);
> +		if (ret != 0) {
> +			rte_errno = EINVAL;
> +			return i;
> +		}
> +#endif
>  	}
> 
>  	return i;
> --
> 2.25.1

[PATCH v3] net/iavf: add debug checks for mbuf

[Mingjin Ye]

The scalar Tx path would send wrong mbuf that causes the kernel driver to
fire the MDD event.

This patch adds mbuf detection in tx_prepare and enables it by defining
`RTE_ETHDEV_DEBUG_TX` macro to fix this issue. If validation fails,
rte_errno will be set to EINVAL and returned.

Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
Cc: stable@dpdk.org

Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
---
 drivers/net/iavf/iavf_rxtx.c | 645 +++++++++++++++++++++++++++++++++++
 1 file changed, 645 insertions(+)

diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 8d49967538..6a2ddf2aca 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -24,12 +24,55 @@
 #include <rte_ip.h>
 #include <rte_net.h>
 #include <rte_vect.h>
+#include <rte_vxlan.h>
+#include <rte_gtp.h>
+#include <rte_geneve.h>
 
 #include "iavf.h"
 #include "iavf_rxtx.h"
 #include "iavf_ipsec_crypto.h"
 #include "rte_pmd_iavf.h"
 
+#define GRE_CHECKSUM_PRESENT	0x8000
+#define GRE_KEY_PRESENT		0x2000
+#define GRE_SEQUENCE_PRESENT	0x1000
+#define GRE_EXT_LEN		4
+#define GRE_SUPPORTED_FIELDS	(GRE_CHECKSUM_PRESENT | GRE_KEY_PRESENT |\
+				 GRE_SEQUENCE_PRESENT)
+
+#ifndef IPPROTO_IPIP
+#define IPPROTO_IPIP 4
+#endif
+#ifndef IPPROTO_GRE
+#define IPPROTO_GRE	47
+#endif
+
+static uint16_t vxlan_gpe_udp_port = RTE_VXLAN_GPE_DEFAULT_PORT;
+static uint16_t geneve_udp_port = RTE_GENEVE_DEFAULT_PORT;
+
+struct simple_gre_hdr {
+	uint16_t flags;
+	uint16_t proto;
+} __rte_packed;
+
+/* structure that caches offload info for the current packet */
+struct offload_info {
+	uint16_t ethertype;
+	uint8_t gso_enable;
+	uint16_t l2_len;
+	uint16_t l3_len;
+	uint16_t l4_len;
+	uint8_t l4_proto;
+	uint8_t is_tunnel;
+	uint16_t outer_ethertype;
+	uint16_t outer_l2_len;
+	uint16_t outer_l3_len;
+	uint8_t outer_l4_proto;
+	uint16_t tso_segsz;
+	uint16_t tunnel_tso_segsz;
+	uint32_t pkt_len;
+};
+
 /* Offset of mbuf dynamic field for protocol extraction's metadata */
 int rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
 
@@ -2949,6 +2992,600 @@ iavf_check_vlan_up2tc(struct iavf_tx_queue *txq, struct rte_mbuf *m)
 	}
 }
 
+/* Parse an IPv4 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv4(struct rte_ipv4_hdr *ipv4_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = rte_ipv4_hdr_len(ipv4_hdr);
+	info->l4_proto = ipv4_hdr->next_proto_id;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv4_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/* Parse an IPv6 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv6(struct rte_ipv6_hdr *ipv6_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = sizeof(struct rte_ipv6_hdr);
+	info->l4_proto = ipv6_hdr->proto;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv6_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/*
+ * Parse an ethernet header to fill the ethertype, l2_len, l3_len and
+ * ipproto. This function is able to recognize IPv4/IPv6 with optional VLAN
+ * headers. The l4_len argument is only set in case of TCP (useful for TSO).
+ */
+static inline void
+parse_ethernet(struct rte_ether_hdr *eth_hdr, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vlan_hdr *vlan_hdr;
+
+	info->l2_len = sizeof(struct rte_ether_hdr);
+	info->ethertype = eth_hdr->ether_type;
+
+	while (info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
+	       info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
+		vlan_hdr = (struct rte_vlan_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		info->l2_len  += sizeof(struct rte_vlan_hdr);
+		info->ethertype = vlan_hdr->eth_proto;
+	}
+
+	switch (info->ethertype) {
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV4):
+		ipv4_hdr = (struct rte_ipv4_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv4(ipv4_hdr, info);
+		break;
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV6):
+		ipv6_hdr = (struct rte_ipv6_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv6(ipv6_hdr, info);
+		break;
+	default:
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+		break;
+	}
+}
+
+/* Fill in outer layers length */
+static inline void
+update_tunnel_outer(struct offload_info *info)
+{
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+	info->outer_l4_proto = info->l4_proto;
+}
+
+/*
+ * Parse a GTP protocol header.
+ * No optional fields and next extension header type.
+ */
+static inline void
+parse_gtp(struct rte_udp_hdr *udp_hdr,
+	  struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_gtp_hdr *gtp_hdr;
+	uint8_t gtp_len = sizeof(*gtp_hdr);
+	uint8_t ip_ver;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->src_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPU_UDP_PORT))
+		return;
+
+	update_tunnel_outer(info);
+	info->l2_len = 0;
+
+	gtp_hdr = (struct rte_gtp_hdr *)((char *)udp_hdr +
+		  sizeof(struct rte_udp_hdr));
+
+	/*
+	 * Check message type. If message type is 0xff, it is
+	 * a GTP data packet. If not, it is a GTP control packet
+	 */
+	if (gtp_hdr->msg_type == 0xff) {
+		ip_ver = *(uint8_t *)((char *)udp_hdr +
+			 sizeof(struct rte_udp_hdr) +
+			 sizeof(struct rte_gtp_hdr));
+		ip_ver = (ip_ver) & 0xf0;
+
+		if (ip_ver == RTE_GTP_TYPE_IPV4) {
+			ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+			parse_ipv4(ipv4_hdr, info);
+		} else if (ip_ver == RTE_GTP_TYPE_IPV6) {
+			ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+			parse_ipv6(ipv6_hdr, info);
+		}
+	} else {
+		info->ethertype = 0;
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+	}
+
+	info->l2_len += RTE_ETHER_GTP_HLEN;
+}
+
+/* Parse a vxlan header */
+static inline void
+parse_vxlan(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+
+	/* check udp destination port, RTE_VXLAN_DEFAULT_PORT (4789) is the
+	 * default vxlan port (rfc7348) or that the rx offload flag is set
+	 * (i40e only currently)
+	 */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_VXLAN_DEFAULT_PORT))
+		return;
+
+	update_tunnel_outer(info);
+
+	eth_hdr = (struct rte_ether_hdr *)((char *)udp_hdr +
+		sizeof(struct rte_udp_hdr) +
+		sizeof(struct rte_vxlan_hdr));
+
+	parse_ethernet(eth_hdr, info);
+	info->l2_len += RTE_ETHER_VXLAN_HLEN; /* add udp + vxlan */
+}
+
+/* Parse a vxlan-gpe header */
+static inline void
+parse_vxlan_gpe(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vxlan_gpe_hdr *vxlan_gpe_hdr;
+	uint8_t vxlan_gpe_len = sizeof(*vxlan_gpe_hdr);
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(vxlan_gpe_udp_port))
+		return;
+
+	vxlan_gpe_hdr = (struct rte_vxlan_gpe_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+
+	if (!vxlan_gpe_hdr->proto || vxlan_gpe_hdr->proto ==
+	    RTE_VXLAN_GPE_TYPE_IPV4) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_IPV6) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_ETH) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)vxlan_gpe_hdr +
+			  vxlan_gpe_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len += RTE_ETHER_VXLAN_GPE_HLEN;
+}
+
+/* Parse a geneve header */
+static inline void
+parse_geneve(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_geneve_hdr *geneve_hdr;
+	uint16_t geneve_len;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(geneve_udp_port))
+		return;
+
+	geneve_hdr = (struct rte_geneve_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+	geneve_len = sizeof(struct rte_geneve_hdr) + geneve_hdr->opt_len * 4;
+	if (!geneve_hdr->proto || geneve_hdr->proto ==
+	    rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_GENEVE_TYPE_ETH)) {
+		update_tunnel_outer(info);
+		eth_hdr = (struct rte_ether_hdr *)((char *)geneve_hdr +
+			  geneve_len);
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len +=
+		(sizeof(struct rte_udp_hdr) + sizeof(struct rte_geneve_hdr) +
+		((struct rte_geneve_hdr *)geneve_hdr)->opt_len * 4);
+}
+
+/* Parse a gre header */
+static inline void
+parse_gre(struct simple_gre_hdr *gre_hdr, struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	uint8_t gre_len = 0;
+
+	gre_len += sizeof(struct simple_gre_hdr);
+
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_KEY_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_SEQUENCE_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_CHECKSUM_PRESENT))
+		gre_len += GRE_EXT_LEN;
+
+	if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gre_hdr + gre_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_TEB)) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len += gre_len;
+}
+
+/* Parse an encapsulated ip or ipv6 header */
+static inline void
+parse_encap_ip(void *encap_ip, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr = encap_ip;
+	struct rte_ipv6_hdr *ipv6_hdr = encap_ip;
+	uint8_t ip_version;
+
+	ip_version = (ipv4_hdr->version_ihl & 0xf0) >> 4;
+
+	if (ip_version != 4 && ip_version != 6)
+		return;
+
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+
+	if (ip_version == 4) {
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+	} else {
+		parse_ipv6(ipv6_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+	}
+	info->l2_len = 0;
+}
+
+static  inline int
+check_mbuf_len(struct offload_info *info, struct rte_mbuf *m)
+{
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_l2_len != m->outer_l2_len) {
+			PMD_TX_LOG(ERR, "outer_l2_len error in mbuf. Original "
+			"length: %hu, calculated length: %u", m->outer_l2_len,
+			info->outer_l2_len);
+			return -1;
+		}
+		if (info->outer_l3_len != m->outer_l3_len) {
+			PMD_TX_LOG(ERR, "outer_l3_len error in mbuf. Original "
+			"length: %hu,calculated length: %u", m->outer_l3_len,
+			info->outer_l3_len);
+			return -1;
+		}
+	}
+
+	if (info->l2_len != m->l2_len) {
+		PMD_TX_LOG(ERR, "l2_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l2_len,
+		info->l2_len);
+		return -1;
+	}
+	if (info->l3_len != m->l3_len) {
+		PMD_TX_LOG(ERR, "l3_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l3_len,
+		info->l3_len);
+		return -1;
+	}
+	if (info->l4_len != m->l4_len) {
+		PMD_TX_LOG(ERR, "l4_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l4_len,
+		info->l4_len);
+		return -1;
+	}
+
+	return 0;
+}
+
+static  inline int
+check_ether_type(struct offload_info *info, struct rte_mbuf *m)
+{
+	int ret = 0;
+
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+			if (!(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV4` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV6` flag");
+				ret = -1;
+			}
+		} else if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+			if (!(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV6` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV4` flag");
+				ret = -1;
+			}
+		}
+	}
+
+	if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		if (!(m->ol_flags & RTE_MBUF_F_TX_IPV4)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV4` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV6) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx "
+			"offload contains wrong `RTE_MBUF_F_TX_IPV6` flag");
+			ret = -1;
+		}
+	} else if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		if (!(m->ol_flags & RTE_MBUF_F_TX_IPV6)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV6` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV4) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"contains wrong `RTE_MBUF_F_TX_IPV4` flag");
+			ret = -1;
+		}
+	}
+
+	return ret;
+}
+
+/* Check whether the parameters of mubf are correct. */
+__rte_unused static  inline int
+iavf_check_mbuf(struct rte_mbuf *m)
+{
+	struct rte_ether_hdr *eth_hdr;
+	void *l3_hdr = NULL; /* can be IPv4 or IPv6 */
+	struct offload_info info = {0};
+	uint64_t ol_flags = m->ol_flags;
+	uint64_t tunnel_type = ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK;
+
+	eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+	parse_ethernet(eth_hdr, &info);
+	l3_hdr = (char *)eth_hdr + info.l2_len;
+	if (info.l4_proto == IPPROTO_UDP) {
+		struct rte_udp_hdr *udp_hdr;
+
+		udp_hdr = (struct rte_udp_hdr *)
+			((char *)l3_hdr + info.l3_len);
+		parse_gtp(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "gtp tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_GTP` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GTP) {
+				PMD_TX_LOG(ERR, "gtp tunnel packet, tx offload has wrong "
+				"`%s` flag, correct is `RTE_MBUF_F_TX_TUNNEL_GTP` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		parse_vxlan_gpe(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "vxlan gpe tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE) {
+				PMD_TX_LOG(ERR, "vxlan gpe tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		parse_vxlan(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "vxlan tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_VXLAN` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_VXLAN) {
+				PMD_TX_LOG(ERR, "vxlan tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_VXLAN` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		parse_geneve(udp_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "geneve tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_GENEVE` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GENEVE) {
+				PMD_TX_LOG(ERR, "geneve tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_GENEVE` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+		/* Always keep last. */
+		if (unlikely(RTE_ETH_IS_TUNNEL_PKT(m->packet_type)
+			!= 0)) {
+			PMD_TX_LOG(ERR, "Unknown tunnel packet. UDP dst port: %hu",
+				udp_hdr->dst_port);
+				return -1;
+		}
+	} else if (info.l4_proto == IPPROTO_GRE) {
+		struct simple_gre_hdr *gre_hdr;
+
+		gre_hdr = (struct simple_gre_hdr *)((char *)l3_hdr +
+			info.l3_len);
+		parse_gre(gre_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "gre tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_GRE` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_GRE) {
+				PMD_TX_LOG(ERR, "gre tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_GRE` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+	} else if (info.l4_proto == IPPROTO_IPIP) {
+		void *encap_ip_hdr;
+
+		encap_ip_hdr = (char *)l3_hdr + info.l3_len;
+		parse_encap_ip(encap_ip_hdr, &info);
+		if (info.is_tunnel) {
+			if (!tunnel_type) {
+				PMD_TX_LOG(ERR, "Ipip tunnel packet missing tx "
+				"offload missing `RTE_MBUF_F_TX_TUNNEL_IPIP` flag.");
+				return -1;
+			}
+			if (tunnel_type != RTE_MBUF_F_TX_TUNNEL_IPIP) {
+				PMD_TX_LOG(ERR, "Ipip tunnel packet, tx offload has "
+				"wrong `%s` flag, correct is "
+				"`RTE_MBUF_F_TX_TUNNEL_IPIP` flag",
+				rte_get_tx_ol_flag_name(tunnel_type));
+				return -1;
+			}
+			goto check_len;
+		}
+	}
+
+check_len:
+	if (check_mbuf_len(&info, m) != 0)
+		return -1;
+
+	return check_ether_type(&info, m);
+}
+
 /* TX prep functions */
 uint16_t
 iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -3017,6 +3654,14 @@ iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
 				return i;
 			}
 		}
+
+#ifdef RTE_ETHDEV_DEBUG_TX
+		ret = iavf_check_mbuf(m);
+		if (ret != 0) {
+			rte_errno = EINVAL;
+			return i;
+		}
+#endif
 	}
 
 	return i;
-- 
2.25.1

RE: [PATCH v3] net/iavf: add debug checks for mbuf

[Zhang, Qi Z]

> -----Original Message-----
> From: Mingjin Ye <mingjinx.ye@intel.com>
> Sent: Monday, February 13, 2023 4:32 PM
> To: dev@dpdk.org
> Cc: Yang, Qiming <qiming.yang@intel.com>; stable@dpdk.org; Zhou, YidingX
> <yidingx.zhou@intel.com>; Ye, MingjinX <mingjinx.ye@intel.com>; Wu,
> Jingjing <jingjing.wu@intel.com>; Xing, Beilei <beilei.xing@intel.com>
> Subject: [PATCH v3] net/iavf: add debug checks for mbuf
> 
> The scalar Tx path would send wrong mbuf that causes the kernel driver to
> fire the MDD event.
> 
> This patch adds mbuf detection in tx_prepare and enables it by defining
> `RTE_ETHDEV_DEBUG_TX` macro to fix this issue. If validation fails, rte_errno

This is a debug utility but not a fix, enable this check will significantly downgrade the performance
Removed  "to fix this issue"

> will be set to EINVAL and returned.
> 
> Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
> Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
> Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")

Removed all the fix lines

> Cc: stable@dpdk.org
> 
> Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>

Acked-by: Qi Zhang <qi.z.zhang@intel.com>

Applied to dpdk-next-net-intel after apply above change.

Thanks
Qi

Re: [PATCH v3] net/iavf: add debug checks for mbuf

[Thomas Monjalon]

19/02/2023 09:30, Zhang, Qi Z:
> From: Mingjin Ye <mingjinx.ye@intel.com>
> > 
> > The scalar Tx path would send wrong mbuf that causes the kernel driver to
> > fire the MDD event.
> > 
> > This patch adds mbuf detection in tx_prepare and enables it by defining
> > `RTE_ETHDEV_DEBUG_TX` macro to fix this issue. If validation fails, rte_errno
> 
> This is a debug utility but not a fix, enable this check will significantly downgrade the performance
> Removed  "to fix this issue"
> 
> > will be set to EINVAL and returned.
> > 
> > Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
> > Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
> > Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
> 
> Removed all the fix lines
> 
> > Cc: stable@dpdk.org

I think the "stable line" should be removed as well.
It is a new debug feature, we should not try to backport it.

[PATCH] net/iavf: add check for mbuf

[Mingjin Ye]

The scalar Tx path would send wrong mbuf that causes the kernel driver to
fire the MDD event.

This patch adds mbuf detection in tx_prepare to fix this issue, rte_errno
will be set to EINVAL and returned if the verification fails.

Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
Cc: stable@dpdk.org

Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
---
 drivers/net/iavf/iavf_rxtx.c | 592 +++++++++++++++++++++++++++++++++++
 1 file changed, 592 insertions(+)

diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 8d49967538..e1f2ced990 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -24,12 +24,48 @@
 #include <rte_ip.h>
 #include <rte_net.h>
 #include <rte_vect.h>
+#include <rte_vxlan.h>
+#include <rte_gtp.h>
+#include <rte_geneve.h>
 
 #include "iavf.h"
 #include "iavf_rxtx.h"
 #include "iavf_ipsec_crypto.h"
 #include "rte_pmd_iavf.h"
 
+#define GRE_CHECKSUM_PRESENT	0x8000
+#define GRE_KEY_PRESENT		0x2000
+#define GRE_SEQUENCE_PRESENT	0x1000
+#define GRE_EXT_LEN		4
+#define GRE_SUPPORTED_FIELDS	(GRE_CHECKSUM_PRESENT | GRE_KEY_PRESENT |\
+				 GRE_SEQUENCE_PRESENT)
+
+static uint16_t vxlan_gpe_udp_port = RTE_VXLAN_GPE_DEFAULT_PORT;
+static uint16_t geneve_udp_port = RTE_GENEVE_DEFAULT_PORT;
+
+struct simple_gre_hdr {
+	uint16_t flags;
+	uint16_t proto;
+} __rte_packed;
+
+/* structure that caches offload info for the current packet */
+struct offload_info {
+	uint16_t ethertype;
+	uint8_t gso_enable;
+	uint16_t l2_len;
+	uint16_t l3_len;
+	uint16_t l4_len;
+	uint8_t l4_proto;
+	uint8_t is_tunnel;
+	uint16_t outer_ethertype;
+	uint16_t outer_l2_len;
+	uint16_t outer_l3_len;
+	uint8_t outer_l4_proto;
+	uint16_t tso_segsz;
+	uint16_t tunnel_tso_segsz;
+	uint32_t pkt_len;
+};
+
 /* Offset of mbuf dynamic field for protocol extraction's metadata */
 int rte_pmd_ifd_dynfield_proto_xtr_metadata_offs = -1;
 
@@ -2949,6 +2985,555 @@ iavf_check_vlan_up2tc(struct iavf_tx_queue *txq, struct rte_mbuf *m)
 	}
 }
 
+/* Parse an IPv4 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv4(struct rte_ipv4_hdr *ipv4_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = rte_ipv4_hdr_len(ipv4_hdr);
+	info->l4_proto = ipv4_hdr->next_proto_id;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv4_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/* Parse an IPv6 header to fill l3_len, l4_len, and l4_proto */
+static inline void
+parse_ipv6(struct rte_ipv6_hdr *ipv6_hdr, struct offload_info *info)
+{
+	struct rte_tcp_hdr *tcp_hdr;
+
+	info->l3_len = sizeof(struct rte_ipv6_hdr);
+	info->l4_proto = ipv6_hdr->proto;
+
+	/* only fill l4_len for TCP, it's useful for TSO */
+	if (info->l4_proto == IPPROTO_TCP) {
+		tcp_hdr = (struct rte_tcp_hdr *)
+			((char *)ipv6_hdr + info->l3_len);
+		info->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+	} else if (info->l4_proto == IPPROTO_UDP) {
+		info->l4_len = sizeof(struct rte_udp_hdr);
+	} else {
+		info->l4_len = 0;
+	}
+}
+
+/*
+ * Parse an ethernet header to fill the ethertype, l2_len, l3_len and
+ * ipproto. This function is able to recognize IPv4/IPv6 with optional VLAN
+ * headers. The l4_len argument is only set in case of TCP (useful for TSO).
+ */
+static inline void
+parse_ethernet(struct rte_ether_hdr *eth_hdr, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vlan_hdr *vlan_hdr;
+
+	info->l2_len = sizeof(struct rte_ether_hdr);
+	info->ethertype = eth_hdr->ether_type;
+
+	while (info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
+	       info->ethertype == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
+		vlan_hdr = (struct rte_vlan_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		info->l2_len  += sizeof(struct rte_vlan_hdr);
+		info->ethertype = vlan_hdr->eth_proto;
+	}
+
+	switch (info->ethertype) {
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV4):
+		ipv4_hdr = (struct rte_ipv4_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv4(ipv4_hdr, info);
+		break;
+	case RTE_STATIC_BSWAP16(RTE_ETHER_TYPE_IPV6):
+		ipv6_hdr = (struct rte_ipv6_hdr *)
+			((char *)eth_hdr + info->l2_len);
+		parse_ipv6(ipv6_hdr, info);
+		break;
+	default:
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+		break;
+	}
+}
+
+/* Fill in outer layers length */
+static inline void
+update_tunnel_outer(struct offload_info *info)
+{
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+	info->outer_l4_proto = info->l4_proto;
+}
+
+/*
+ * Parse a GTP protocol header.
+ * No optional fields and next extension header type.
+ */
+static inline void
+parse_gtp(struct rte_udp_hdr *udp_hdr,
+	  struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_gtp_hdr *gtp_hdr;
+	uint8_t gtp_len = sizeof(*gtp_hdr);
+	uint8_t ip_ver;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->src_port != rte_cpu_to_be_16(RTE_GTPC_UDP_PORT) &&
+	    udp_hdr->dst_port != rte_cpu_to_be_16(RTE_GTPU_UDP_PORT))
+		return;
+
+	update_tunnel_outer(info);
+	info->l2_len = 0;
+
+	gtp_hdr = (struct rte_gtp_hdr *)((char *)udp_hdr +
+		  sizeof(struct rte_udp_hdr));
+
+	/*
+	 * Check message type. If message type is 0xff, it is
+	 * a GTP data packet. If not, it is a GTP control packet
+	 */
+	if (gtp_hdr->msg_type == 0xff) {
+		ip_ver = *(uint8_t *)((char *)udp_hdr +
+			 sizeof(struct rte_udp_hdr) +
+			 sizeof(struct rte_gtp_hdr));
+		ip_ver = (ip_ver) & 0xf0;
+
+		if (ip_ver == RTE_GTP_TYPE_IPV4) {
+			ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+			parse_ipv4(ipv4_hdr, info);
+		} else if (ip_ver == RTE_GTP_TYPE_IPV6) {
+			ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gtp_hdr +
+				   gtp_len);
+			info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+			parse_ipv6(ipv6_hdr, info);
+		}
+	} else {
+		info->ethertype = 0;
+		info->l4_len = 0;
+		info->l3_len = 0;
+		info->l4_proto = 0;
+	}
+
+	info->l2_len += RTE_ETHER_GTP_HLEN;
+}
+
+/* Parse a vxlan header */
+static inline void
+parse_vxlan(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+
+	/* check udp destination port, RTE_VXLAN_DEFAULT_PORT (4789) is the
+	 * default vxlan port (rfc7348) or that the rx offload flag is set
+	 * (i40e only currently)
+	 */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(RTE_VXLAN_DEFAULT_PORT))
+		return;
+
+	update_tunnel_outer(info);
+
+	eth_hdr = (struct rte_ether_hdr *)((char *)udp_hdr +
+		sizeof(struct rte_udp_hdr) +
+		sizeof(struct rte_vxlan_hdr));
+
+	parse_ethernet(eth_hdr, info);
+	info->l2_len += RTE_ETHER_VXLAN_HLEN; /* add udp + vxlan */
+}
+
+/* Parse a vxlan-gpe header */
+static inline void
+parse_vxlan_gpe(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_vxlan_gpe_hdr *vxlan_gpe_hdr;
+	uint8_t vxlan_gpe_len = sizeof(*vxlan_gpe_hdr);
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(vxlan_gpe_udp_port))
+		return;
+
+	vxlan_gpe_hdr = (struct rte_vxlan_gpe_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+
+	if (!vxlan_gpe_hdr->proto || vxlan_gpe_hdr->proto ==
+	    RTE_VXLAN_GPE_TYPE_IPV4) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_IPV6) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)vxlan_gpe_hdr +
+			   vxlan_gpe_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (vxlan_gpe_hdr->proto == RTE_VXLAN_GPE_TYPE_ETH) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)vxlan_gpe_hdr +
+			  vxlan_gpe_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+
+	info->l2_len += RTE_ETHER_VXLAN_GPE_HLEN;
+}
+
+/* Parse a geneve header */
+static inline void
+parse_geneve(struct rte_udp_hdr *udp_hdr,
+	    struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_geneve_hdr *geneve_hdr;
+	uint16_t geneve_len;
+
+	/* Check udp destination port. */
+	if (udp_hdr->dst_port != rte_cpu_to_be_16(geneve_udp_port))
+		return;
+
+	geneve_hdr = (struct rte_geneve_hdr *)((char *)udp_hdr +
+				sizeof(struct rte_udp_hdr));
+	geneve_len = sizeof(struct rte_geneve_hdr) + geneve_hdr->opt_len * 4;
+	if (!geneve_hdr->proto || geneve_hdr->proto ==
+	    rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)geneve_hdr +
+			   geneve_len);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (geneve_hdr->proto == rte_cpu_to_be_16(RTE_GENEVE_TYPE_ETH)) {
+		update_tunnel_outer(info);
+		eth_hdr = (struct rte_ether_hdr *)((char *)geneve_hdr +
+			  geneve_len);
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len +=
+		(sizeof(struct rte_udp_hdr) + sizeof(struct rte_geneve_hdr) +
+		((struct rte_geneve_hdr *)geneve_hdr)->opt_len * 4);
+}
+
+/* Parse a gre header */
+static inline void
+parse_gre(struct simple_gre_hdr *gre_hdr, struct offload_info *info)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	uint8_t gre_len = 0;
+
+	gre_len += sizeof(struct simple_gre_hdr);
+
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_KEY_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_SEQUENCE_PRESENT))
+		gre_len += GRE_EXT_LEN;
+	if (gre_hdr->flags & rte_cpu_to_be_16(GRE_CHECKSUM_PRESENT))
+		gre_len += GRE_EXT_LEN;
+
+	if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		update_tunnel_outer(info);
+
+		ipv4_hdr = (struct rte_ipv4_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		update_tunnel_outer(info);
+
+		ipv6_hdr = (struct rte_ipv6_hdr *)((char *)gre_hdr + gre_len);
+
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+		parse_ipv6(ipv6_hdr, info);
+		info->l2_len = 0;
+
+	} else if (gre_hdr->proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_TEB)) {
+		update_tunnel_outer(info);
+
+		eth_hdr = (struct rte_ether_hdr *)((char *)gre_hdr + gre_len);
+
+		parse_ethernet(eth_hdr, info);
+	} else {
+		return;
+	}
+
+	info->l2_len += gre_len;
+}
+
+/* Parse an encapsulated ip or ipv6 header */
+static inline void
+parse_encap_ip(void *encap_ip, struct offload_info *info)
+{
+	struct rte_ipv4_hdr *ipv4_hdr = encap_ip;
+	struct rte_ipv6_hdr *ipv6_hdr = encap_ip;
+	uint8_t ip_version;
+
+	ip_version = (ipv4_hdr->version_ihl & 0xf0) >> 4;
+
+	if (ip_version != 4 && ip_version != 6)
+		return;
+
+	info->is_tunnel = 1;
+	info->outer_ethertype = info->ethertype;
+	info->outer_l2_len = info->l2_len;
+	info->outer_l3_len = info->l3_len;
+
+	if (ip_version == 4) {
+		parse_ipv4(ipv4_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+	} else {
+		parse_ipv6(ipv6_hdr, info);
+		info->ethertype = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+	}
+	info->l2_len = 0;
+}
+
+static  inline int
+check_mbuf_len(struct offload_info *info, struct rte_mbuf *m)
+{
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_l2_len != m->outer_l2_len) {
+			PMD_TX_LOG(ERR, "outer_l2_len error in mbuf. Original "
+			"length: %hu, calculated length: %u", m->outer_l2_len,
+			info->outer_l2_len);
+			return -1;
+		}
+		if (info->outer_l3_len != m->outer_l3_len) {
+			PMD_TX_LOG(ERR, "outer_l3_len error in mbuf. Original "
+			"length: %hu,calculated length: %u", m->outer_l3_len,
+			info->outer_l3_len);
+			return -1;
+		}
+	}
+
+	if (info->l2_len != m->l2_len) {
+		PMD_TX_LOG(ERR, "l2_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l2_len,
+		info->l2_len);
+		return -1;
+	}
+	if (info->l3_len != m->l3_len) {
+		PMD_TX_LOG(ERR, "l3_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l3_len,
+		info->l3_len);
+		return -1;
+	}
+	if (info->l4_len != m->l4_len) {
+		PMD_TX_LOG(ERR, "l4_len error in mbuf. Original "
+		"length: %hu, calculated length: %u", m->l4_len,
+		info->l4_len);
+		return -1;
+	}
+
+	return 0;
+}
+
+static  inline int
+check_ether_type(struct offload_info *info, struct rte_mbuf *m)
+{
+	int ret = 0;
+
+	if (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+			if (~(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV4` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv4, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV6` flag");
+				ret = -1;
+			}
+		} else if (info->outer_ethertype ==
+			rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+			if (~(m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV6)) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, "
+				"tx offload missing `RTE_MBUF_F_TX_OUTER_IPV6` flag.");
+				ret = -1;
+			}
+			if (m->ol_flags & RTE_MBUF_F_TX_OUTER_IPV4) {
+				PMD_TX_LOG(ERR, "Outer ethernet type is ipv6, tx "
+				"offload contains wrong `RTE_MBUF_F_TX_OUTER_IPV4` flag");
+				ret = -1;
+			}
+		}
+	}
+
+	if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+		if (~(m->ol_flags & RTE_MBUF_F_TX_IPV4)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV4` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV6) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv4, tx "
+			"offload contains wrong `RTE_MBUF_F_TX_IPV6` flag");
+			ret = -1;
+		}
+	} else if (info->ethertype ==
+		rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+		if (~(m->ol_flags & RTE_MBUF_F_TX_IPV6)) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"missing `RTE_MBUF_F_TX_IPV6` flag.");
+			ret = -1;
+		}
+		if (m->ol_flags & RTE_MBUF_F_TX_IPV4) {
+			PMD_TX_LOG(ERR, "Ethernet type is ipv6, tx offload "
+			"contains wrong `RTE_MBUF_F_TX_IPV4` flag");
+			ret = -1;
+		}
+	}
+
+	return ret;
+}
+
+/* Check whether the parameters of mubf are correct. */
+__rte_unused static  inline int
+iavf_check_mbuf(struct rte_mbuf *m)
+{
+	struct rte_ether_hdr *eth_hdr;
+	void *l3_hdr = NULL; /* can be IPv4 or IPv6 */
+	struct offload_info info = {0};
+	uint64_t ol_flags = m->ol_flags;
+
+	eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+	parse_ethernet(eth_hdr, &info);
+	l3_hdr = (char *)eth_hdr + info.l2_len;
+	if (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		if (info.l4_proto == IPPROTO_UDP) {
+			struct rte_udp_hdr *udp_hdr;
+
+			udp_hdr = (struct rte_udp_hdr *)
+				((char *)l3_hdr + info.l3_len);
+			parse_gtp(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_GTP)) {
+					PMD_TX_LOG(ERR, "gtp tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			parse_vxlan_gpe(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE)) {
+					PMD_TX_LOG(ERR, "vxlan gpe tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			parse_vxlan(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_VXLAN)) {
+					PMD_TX_LOG(ERR, "vxlan tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			parse_geneve(udp_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_GENEVE)) {
+					PMD_TX_LOG(ERR, "geneve tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+			/* Always keep last. */
+			if (unlikely(RTE_ETH_IS_TUNNEL_PKT(m->packet_type)
+				!= 0)) {
+				PMD_TX_LOG(ERR, "Unknown tunnel packet. UDP dst port: %hu",
+					udp_hdr->dst_port);
+					return -1;
+			}
+		} else if (info.l4_proto == IPPROTO_GRE) {
+			struct simple_gre_hdr *gre_hdr;
+
+			gre_hdr = (struct simple_gre_hdr *)((char *)l3_hdr +
+				info.l3_len);
+			parse_gre(gre_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_GRE)) {
+					PMD_TX_LOG(ERR, "gre tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+		} else if (info.l4_proto == IPPROTO_IPIP) {
+			void *encap_ip_hdr;
+
+			encap_ip_hdr = (char *)l3_hdr + info.l3_len;
+			parse_encap_ip(encap_ip_hdr, &info);
+			if (info.is_tunnel) {
+				if (!(ol_flags & RTE_MBUF_F_TX_TUNNEL_IPIP)) {
+					PMD_TX_LOG(ERR, "Ipip tunnel packet missing tx flag");
+					return -1;
+				}
+				goto check_len;
+			}
+		}
+	}
+
+check_len:
+	if (check_mbuf_len(&info, m) != 0)
+		return -1;
+
+	return check_ether_type(&info, m);
+}
+
 /* TX prep functions */
 uint16_t
 iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -3017,6 +3602,13 @@ iavf_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
 				return i;
 			}
 		}
+#ifdef RTE_ETHDEV_DEBUG_TX
+		ret = iavf_check_mbuf(m);
+		if (ret != 0) {
+			rte_errno = EINVAL;
+			return i;
+		}
+#endif
 	}
 
 	return i;
-- 
2.25.1

RE: [PATCH] net/iavf: add check for mbuf

[Xing, Beilei]

> -----Original Message-----
> From: Ye, MingjinX <mingjinx.ye@intel.com>
> Sent: Tuesday, January 31, 2023 1:20 PM
> To: dev@dpdk.org
> Cc: Yang, Qiming <qiming.yang@intel.com>; Zhou, YidingX
> <yidingx.zhou@intel.com>; Ye, MingjinX <mingjinx.ye@intel.com>;
> stable@dpdk.org; Wu, Jingjing <jingjing.wu@intel.com>; Xing, Beilei
> <beilei.xing@intel.com>
> Subject: [PATCH] net/iavf: add check for mbuf
> 
> The scalar Tx path would send wrong mbuf that causes the kernel driver to fire
> the MDD event.
> 
> This patch adds mbuf detection in tx_prepare to fix this issue, rte_errno will be
> set to EINVAL and returned if the verification fails.
 
I don't think PMD needs to check all packets contents, there're so many protocols supported.
It depends on HW capability, or application and user should make sure packets accuracy.

> 
> Fixes: 3fd32df381f8 ("net/iavf: check Tx packet with correct UP and queue")
> Fixes: 12b435bf8f2f ("net/iavf: support flex desc metadata extraction")
> Fixes: f28fbd1e6b50 ("net/iavf: check max SIMD bitwidth")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>