/* Configure how many packets ahead to prefetch, when reading packets */
#define PREFETCH_OFFSET 3
+#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
+
enum pkt_type {
PKT_TYPE_PLAIN_IPV4 = 1,
PKT_TYPE_IPSEC_IPV4,
} __rte_cache_aligned;
void ipsec_poll_mode_worker(void);
+void ipsec_poll_mode_wrkr_inl_pr(void);
+void ipsec_poll_mode_wrkr_inl_pr_ss(void);
int ipsec_launch_one_lcore(void *args);
}
}
-static inline void
+static __rte_always_inline void
adjust_ipv4_pktlen(struct rte_mbuf *m, const struct rte_ipv4_hdr *iph,
uint32_t l2_len)
{
}
}
-static inline void
+static __rte_always_inline void
adjust_ipv6_pktlen(struct rte_mbuf *m, const struct rte_ipv6_hdr *iph,
uint32_t l2_len)
{
}
}
-static inline void
-prepare_one_packet(struct rte_mbuf *pkt, struct ipsec_traffic *t)
+static __rte_always_inline void
+prepare_one_packet(struct rte_security_ctx *ctx, struct rte_mbuf *pkt,
+ struct ipsec_traffic *t)
{
+ uint32_t ptype = pkt->packet_type;
const struct rte_ether_hdr *eth;
const struct rte_ipv4_hdr *iph4;
const struct rte_ipv6_hdr *iph6;
- const struct rte_udp_hdr *udp;
- uint16_t ip4_hdr_len;
- uint16_t nat_port;
+ uint32_t tun_type, l3_type;
+ uint64_t tx_offload;
+ uint16_t l3len;
- eth = rte_pktmbuf_mtod(pkt, const struct rte_ether_hdr *);
- if (eth->ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+ tun_type = ptype & RTE_PTYPE_TUNNEL_MASK;
+ l3_type = ptype & RTE_PTYPE_L3_MASK;
+ eth = rte_pktmbuf_mtod(pkt, const struct rte_ether_hdr *);
+ if (RTE_ETH_IS_IPV4_HDR(l3_type)) {
iph4 = (const struct rte_ipv4_hdr *)rte_pktmbuf_adj(pkt,
RTE_ETHER_HDR_LEN);
adjust_ipv4_pktlen(pkt, iph4, 0);
- switch (iph4->next_proto_id) {
- case IPPROTO_ESP:
+ if (tun_type == RTE_PTYPE_TUNNEL_ESP) {
t->ipsec.pkts[(t->ipsec.num)++] = pkt;
- break;
- case IPPROTO_UDP:
- if (app_sa_prm.udp_encap == 1) {
- ip4_hdr_len = ((iph4->version_ihl &
- RTE_IPV4_HDR_IHL_MASK) *
- RTE_IPV4_IHL_MULTIPLIER);
- udp = rte_pktmbuf_mtod_offset(pkt,
- struct rte_udp_hdr *, ip4_hdr_len);
- nat_port = rte_cpu_to_be_16(IPSEC_NAT_T_PORT);
- if (udp->src_port == nat_port ||
- udp->dst_port == nat_port){
- t->ipsec.pkts[(t->ipsec.num)++] = pkt;
- pkt->packet_type |=
- MBUF_PTYPE_TUNNEL_ESP_IN_UDP;
- break;
- }
- }
- /* Fall through */
- default:
+ } else {
t->ip4.data[t->ip4.num] = &iph4->next_proto_id;
t->ip4.pkts[(t->ip4.num)++] = pkt;
}
- pkt->l2_len = 0;
- pkt->l3_len = sizeof(*iph4);
- pkt->packet_type |= RTE_PTYPE_L3_IPV4;
- if (pkt->packet_type & RTE_PTYPE_L4_TCP)
- pkt->l4_len = sizeof(struct rte_tcp_hdr);
- else if (pkt->packet_type & RTE_PTYPE_L4_UDP)
- pkt->l4_len = sizeof(struct rte_udp_hdr);
- } else if (eth->ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+ tx_offload = sizeof(*iph4) << RTE_MBUF_L2_LEN_BITS;
+ } else if (RTE_ETH_IS_IPV6_HDR(l3_type)) {
int next_proto;
- size_t l3len, ext_len;
+ size_t ext_len;
uint8_t *p;
/* get protocol type */
RTE_ETHER_HDR_LEN);
adjust_ipv6_pktlen(pkt, iph6, 0);
- next_proto = iph6->proto;
-
- /* determine l3 header size up to ESP extension */
l3len = sizeof(struct ip6_hdr);
- p = rte_pktmbuf_mtod(pkt, uint8_t *);
- while (next_proto != IPPROTO_ESP && l3len < pkt->data_len &&
- (next_proto = rte_ipv6_get_next_ext(p + l3len,
- next_proto, &ext_len)) >= 0)
- l3len += ext_len;
- /* drop packet when IPv6 header exceeds first segment length */
- if (unlikely(l3len > pkt->data_len)) {
- free_pkts(&pkt, 1);
- return;
- }
-
- switch (next_proto) {
- case IPPROTO_ESP:
+ if (tun_type == RTE_PTYPE_TUNNEL_ESP) {
t->ipsec.pkts[(t->ipsec.num)++] = pkt;
- break;
- case IPPROTO_UDP:
- if (app_sa_prm.udp_encap == 1) {
- udp = rte_pktmbuf_mtod_offset(pkt,
- struct rte_udp_hdr *, l3len);
- nat_port = rte_cpu_to_be_16(IPSEC_NAT_T_PORT);
- if (udp->src_port == nat_port ||
- udp->dst_port == nat_port){
- t->ipsec.pkts[(t->ipsec.num)++] = pkt;
- pkt->packet_type |=
- MBUF_PTYPE_TUNNEL_ESP_IN_UDP;
- break;
- }
- }
- /* Fall through */
- default:
+ } else {
t->ip6.data[t->ip6.num] = &iph6->proto;
t->ip6.pkts[(t->ip6.num)++] = pkt;
}
- pkt->l2_len = 0;
- pkt->l3_len = l3len;
- pkt->packet_type |= RTE_PTYPE_L3_IPV6;
+
+ /* Determine l3 header size up to ESP extension by walking
+ * through extension headers.
+ */
+ if (l3_type == RTE_PTYPE_L3_IPV6_EXT ||
+ l3_type == RTE_PTYPE_L3_IPV6_EXT_UNKNOWN) {
+ p = rte_pktmbuf_mtod(pkt, uint8_t *);
+ next_proto = iph6->proto;
+ while (next_proto != IPPROTO_ESP &&
+ l3len < pkt->data_len &&
+ (next_proto = rte_ipv6_get_next_ext(p + l3len,
+ next_proto, &ext_len)) >= 0)
+ l3len += ext_len;
+
+ /* Drop pkt when IPv6 header exceeds first seg size */
+ if (unlikely(l3len > pkt->data_len)) {
+ free_pkts(&pkt, 1);
+ return;
+ }
+ }
+ tx_offload = l3len << RTE_MBUF_L2_LEN_BITS;
} else {
/* Unknown/Unsupported type, drop the packet */
RTE_LOG(ERR, IPSEC, "Unsupported packet type 0x%x\n",
return;
}
+ if ((ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_TCP)
+ tx_offload |= (sizeof(struct rte_tcp_hdr) <<
+ (RTE_MBUF_L2_LEN_BITS + RTE_MBUF_L3_LEN_BITS));
+ else if ((ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP)
+ tx_offload |= (sizeof(struct rte_udp_hdr) <<
+ (RTE_MBUF_L2_LEN_BITS + RTE_MBUF_L3_LEN_BITS));
+ pkt->tx_offload = tx_offload;
+
/* Check if the packet has been processed inline. For inline protocol
* processed packets, the metadata in the mbuf can be used to identify
* the security processing done on the packet. The metadata will be
* with the security session.
*/
- if (pkt->ol_flags & RTE_MBUF_F_RX_SEC_OFFLOAD &&
- rte_security_dynfield_is_registered()) {
+ if (ctx && pkt->ol_flags & RTE_MBUF_F_RX_SEC_OFFLOAD) {
struct ipsec_sa *sa;
struct ipsec_mbuf_metadata *priv;
- struct rte_security_ctx *ctx = (struct rte_security_ctx *)
- rte_eth_dev_get_sec_ctx(
- pkt->port);
/* Retrieve the userdata registered. Here, the userdata
* registered is the SA pointer.
}
}
-static inline void
-prepare_traffic(struct rte_mbuf **pkts, struct ipsec_traffic *t,
- uint16_t nb_pkts)
+static __rte_always_inline void
+prepare_traffic(struct rte_security_ctx *ctx, struct rte_mbuf **pkts,
+ struct ipsec_traffic *t, uint16_t nb_pkts)
{
int32_t i;
for (i = 0; i < (nb_pkts - PREFETCH_OFFSET); i++) {
rte_prefetch0(rte_pktmbuf_mtod(pkts[i + PREFETCH_OFFSET],
void *));
- prepare_one_packet(pkts[i], t);
+ prepare_one_packet(ctx, pkts[i], t);
}
/* Process left packets */
for (; i < nb_pkts; i++)
- prepare_one_packet(pkts[i], t);
-}
-
-static inline void
-prepare_tx_pkt(struct rte_mbuf *pkt, uint16_t port,
- const struct lcore_conf *qconf)
-{
- struct ip *ip;
- struct rte_ether_hdr *ethhdr;
-
- ip = rte_pktmbuf_mtod(pkt, struct ip *);
-
- ethhdr = (struct rte_ether_hdr *)
- rte_pktmbuf_prepend(pkt, RTE_ETHER_HDR_LEN);
-
- if (ip->ip_v == IPVERSION) {
- pkt->ol_flags |= qconf->outbound.ipv4_offloads;
- pkt->l3_len = sizeof(struct ip);
- pkt->l2_len = RTE_ETHER_HDR_LEN;
-
- ip->ip_sum = 0;
-
- /* calculate IPv4 cksum in SW */
- if ((pkt->ol_flags & RTE_MBUF_F_TX_IP_CKSUM) == 0)
- ip->ip_sum = rte_ipv4_cksum((struct rte_ipv4_hdr *)ip);
-
- ethhdr->ether_type = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
- } else {
- pkt->ol_flags |= qconf->outbound.ipv6_offloads;
- pkt->l3_len = sizeof(struct ip6_hdr);
- pkt->l2_len = RTE_ETHER_HDR_LEN;
-
- ethhdr->ether_type = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
- }
-
- memcpy(ðhdr->src_addr, ðaddr_tbl[port].src,
- sizeof(struct rte_ether_addr));
- memcpy(ðhdr->dst_addr, ðaddr_tbl[port].dst,
- sizeof(struct rte_ether_addr));
-}
-
-static inline void
-prepare_tx_burst(struct rte_mbuf *pkts[], uint16_t nb_pkts, uint16_t port,
- const struct lcore_conf *qconf)
-{
- int32_t i;
- const int32_t prefetch_offset = 2;
-
- for (i = 0; i < (nb_pkts - prefetch_offset); i++) {
- rte_mbuf_prefetch_part2(pkts[i + prefetch_offset]);
- prepare_tx_pkt(pkts[i], port, qconf);
- }
- /* Process left packets */
- for (; i < nb_pkts; i++)
- prepare_tx_pkt(pkts[i], port, qconf);
+ prepare_one_packet(ctx, pkts[i], t);
}
/* Send burst of packets on an output interface */
-static inline int32_t
+static __rte_always_inline int32_t
send_burst(struct lcore_conf *qconf, uint16_t n, uint16_t port)
{
struct rte_mbuf **m_table;
queueid = qconf->tx_queue_id[port];
m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table;
- prepare_tx_burst(m_table, n, port, qconf);
-
ret = rte_eth_tx_burst(port, queueid, m_table, n);
core_stats_update_tx(ret);
/*
* Helper function to fragment and queue for TX one packet.
*/
-static inline uint32_t
+static __rte_always_inline uint32_t
send_fragment_packet(struct lcore_conf *qconf, struct rte_mbuf *m,
uint16_t port, uint8_t proto)
{
+ struct rte_ether_hdr *ethhdr;
+ struct rte_ipv4_hdr *ip;
+ struct rte_mbuf *pkt;
struct buffer *tbl;
- uint32_t len, n;
+ uint32_t len, n, i;
int32_t rc;
tbl = qconf->tx_mbufs + port;
n = RTE_DIM(tbl->m_table) - len;
+ /* Strip the ethernet header that was prepended earlier */
+ rte_pktmbuf_adj(m, RTE_ETHER_HDR_LEN);
+
if (proto == IPPROTO_IP)
rc = rte_ipv4_fragment_packet(m, tbl->m_table + len,
n, mtu_size, m->pool, qconf->frag.pool_indir);
rc = rte_ipv6_fragment_packet(m, tbl->m_table + len,
n, mtu_size, m->pool, qconf->frag.pool_indir);
- if (rc >= 0)
- len += rc;
- else
+ if (rc < 0) {
RTE_LOG(ERR, IPSEC,
"%s: failed to fragment packet with size %u, "
"error code: %d\n",
__func__, m->pkt_len, rte_errno);
+ rc = 0;
+ }
+
+ i = len;
+ len += rc;
+ for (; i < len; i++) {
+ pkt = tbl->m_table[i];
+
+ /* Update Ethernet header */
+ ethhdr = (struct rte_ether_hdr *)
+ rte_pktmbuf_prepend(pkt, RTE_ETHER_HDR_LEN);
+ pkt->l2_len = RTE_ETHER_HDR_LEN;
+
+ if (proto == IPPROTO_IP) {
+ ethhdr->ether_type =
+ rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+ /* Update minimum offload data */
+ pkt->l3_len = sizeof(struct rte_ipv4_hdr);
+ pkt->ol_flags |= qconf->outbound.ipv4_offloads;
+
+ ip = (struct rte_ipv4_hdr *)(ethhdr + 1);
+ ip->hdr_checksum = 0;
+
+ /* calculate IPv4 cksum in SW */
+ if ((pkt->ol_flags & RTE_MBUF_F_TX_IP_CKSUM) == 0)
+ ip->hdr_checksum = rte_ipv4_cksum(ip);
+ } else {
+ ethhdr->ether_type =
+ rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+
+ /* Update minimum offload data */
+ pkt->l3_len = sizeof(struct rte_ipv6_hdr);
+ pkt->ol_flags |= qconf->outbound.ipv6_offloads;
+ }
+
+ memcpy(ðhdr->src_addr, ðaddr_tbl[port].src,
+ sizeof(struct rte_ether_addr));
+ memcpy(ðhdr->dst_addr, ðaddr_tbl[port].dst,
+ sizeof(struct rte_ether_addr));
+ }
free_pkts(&m, 1);
return len;
}
/* Enqueue a single packet, and send burst if queue is filled */
-static inline int32_t
+static __rte_always_inline int32_t
send_single_packet(struct rte_mbuf *m, uint16_t port, uint8_t proto)
{
uint32_t lcore_id;
qconf = &lcore_conf[lcore_id];
len = qconf->tx_mbufs[port].len;
- if (m->pkt_len <= mtu_size) {
+ /* L2 header is already part of packet */
+ if (m->pkt_len - RTE_ETHER_HDR_LEN <= mtu_size) {
qconf->tx_mbufs[port].m_table[len] = m;
len++;
return 0;
}
-static inline void
+static __rte_always_inline void
inbound_sp_sa(struct sp_ctx *sp, struct sa_ctx *sa, struct traffic_type *ip,
uint16_t lim, struct ipsec_spd_stats *stats)
{
ip->num = j;
}
-static inline int32_t
+static __rte_always_inline int32_t
get_hop_for_offload_pkt(struct rte_mbuf *pkt, int is_ipv6)
{
struct ipsec_mbuf_metadata *priv;
return 0;
}
-static inline void
-route4_pkts(struct rt_ctx *rt_ctx, struct rte_mbuf *pkts[], uint8_t nb_pkts)
+static __rte_always_inline void
+route4_pkts(struct rt_ctx *rt_ctx, struct rte_mbuf *pkts[],
+ uint8_t nb_pkts, uint64_t tx_offloads, bool ip_cksum)
{
uint32_t hop[MAX_PKT_BURST * 2];
uint32_t dst_ip[MAX_PKT_BURST * 2];
+ struct rte_ether_hdr *ethhdr;
int32_t pkt_hop = 0;
uint16_t i, offset;
uint16_t lpm_pkts = 0;
unsigned int lcoreid = rte_lcore_id();
+ struct rte_mbuf *pkt;
+ uint16_t port;
if (nb_pkts == 0)
return;
*/
for (i = 0; i < nb_pkts; i++) {
- if (!(pkts[i]->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD)) {
+ pkt = pkts[i];
+ if (!(pkt->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD)) {
/* Security offload not enabled. So an LPM lookup is
* required to get the hop
*/
offset = offsetof(struct ip, ip_dst);
- dst_ip[lpm_pkts] = *rte_pktmbuf_mtod_offset(pkts[i],
+ dst_ip[lpm_pkts] = *rte_pktmbuf_mtod_offset(pkt,
uint32_t *, offset);
dst_ip[lpm_pkts] = rte_be_to_cpu_32(dst_ip[lpm_pkts]);
lpm_pkts++;
lpm_pkts = 0;
for (i = 0; i < nb_pkts; i++) {
- if (pkts[i]->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD) {
+ pkt = pkts[i];
+ if (pkt->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD) {
/* Read hop from the SA */
- pkt_hop = get_hop_for_offload_pkt(pkts[i], 0);
+ pkt_hop = get_hop_for_offload_pkt(pkt, 0);
} else {
/* Need to use hop returned by lookup */
pkt_hop = hop[lpm_pkts++];
if ((pkt_hop & RTE_LPM_LOOKUP_SUCCESS) == 0) {
core_statistics[lcoreid].lpm4.miss++;
- free_pkts(&pkts[i], 1);
+ free_pkts(&pkt, 1);
continue;
}
- send_single_packet(pkts[i], pkt_hop & 0xff, IPPROTO_IP);
+
+ port = pkt_hop & 0xff;
+
+ /* Update minimum offload data */
+ pkt->l3_len = sizeof(struct rte_ipv4_hdr);
+ pkt->l2_len = RTE_ETHER_HDR_LEN;
+ pkt->ol_flags |= RTE_MBUF_F_TX_IPV4;
+
+ /* Update Ethernet header */
+ ethhdr = (struct rte_ether_hdr *)
+ rte_pktmbuf_prepend(pkt, RTE_ETHER_HDR_LEN);
+
+ if (ip_cksum) {
+ struct rte_ipv4_hdr *ip;
+
+ pkt->ol_flags |= tx_offloads;
+
+ ip = (struct rte_ipv4_hdr *)(ethhdr + 1);
+ ip->hdr_checksum = 0;
+
+ /* calculate IPv4 cksum in SW */
+ if ((pkt->ol_flags & RTE_MBUF_F_TX_IP_CKSUM) == 0)
+ ip->hdr_checksum = rte_ipv4_cksum(ip);
+ }
+
+ ethhdr->ether_type = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4);
+ memcpy(ðhdr->src_addr, ðaddr_tbl[port].src,
+ sizeof(struct rte_ether_addr));
+ memcpy(ðhdr->dst_addr, ðaddr_tbl[port].dst,
+ sizeof(struct rte_ether_addr));
+
+ send_single_packet(pkt, port, IPPROTO_IP);
}
}
-static inline void
+static __rte_always_inline void
route6_pkts(struct rt_ctx *rt_ctx, struct rte_mbuf *pkts[], uint8_t nb_pkts)
{
int32_t hop[MAX_PKT_BURST * 2];
uint8_t dst_ip[MAX_PKT_BURST * 2][16];
+ struct rte_ether_hdr *ethhdr;
uint8_t *ip6_dst;
int32_t pkt_hop = 0;
uint16_t i, offset;
uint16_t lpm_pkts = 0;
unsigned int lcoreid = rte_lcore_id();
+ struct rte_mbuf *pkt;
+ uint16_t port;
if (nb_pkts == 0)
return;
*/
for (i = 0; i < nb_pkts; i++) {
- if (!(pkts[i]->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD)) {
+ pkt = pkts[i];
+ if (!(pkt->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD)) {
/* Security offload not enabled. So an LPM lookup is
* required to get the hop
*/
offset = offsetof(struct ip6_hdr, ip6_dst);
- ip6_dst = rte_pktmbuf_mtod_offset(pkts[i], uint8_t *,
+ ip6_dst = rte_pktmbuf_mtod_offset(pkt, uint8_t *,
offset);
memcpy(&dst_ip[lpm_pkts][0], ip6_dst, 16);
lpm_pkts++;
lpm_pkts = 0;
for (i = 0; i < nb_pkts; i++) {
- if (pkts[i]->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD) {
+ pkt = pkts[i];
+ if (pkt->ol_flags & RTE_MBUF_F_TX_SEC_OFFLOAD) {
/* Read hop from the SA */
- pkt_hop = get_hop_for_offload_pkt(pkts[i], 1);
+ pkt_hop = get_hop_for_offload_pkt(pkt, 1);
} else {
/* Need to use hop returned by lookup */
pkt_hop = hop[lpm_pkts++];
if (pkt_hop == -1) {
core_statistics[lcoreid].lpm6.miss++;
- free_pkts(&pkts[i], 1);
+ free_pkts(&pkt, 1);
continue;
}
- send_single_packet(pkts[i], pkt_hop & 0xff, IPPROTO_IPV6);
+
+ port = pkt_hop & 0xff;
+
+ /* Update minimum offload data */
+ pkt->ol_flags |= RTE_MBUF_F_TX_IPV6;
+ pkt->l3_len = sizeof(struct ip6_hdr);
+ pkt->l2_len = RTE_ETHER_HDR_LEN;
+
+ /* Update Ethernet header */
+ ethhdr = (struct rte_ether_hdr *)
+ rte_pktmbuf_prepend(pkt, RTE_ETHER_HDR_LEN);
+
+ ethhdr->ether_type = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6);
+ memcpy(ðhdr->src_addr, ðaddr_tbl[port].src,
+ sizeof(struct rte_ether_addr));
+ memcpy(ðhdr->dst_addr, ðaddr_tbl[port].dst,
+ sizeof(struct rte_ether_addr));
+
+ send_single_packet(pkt, port, IPPROTO_IPV6);
}
}
-static inline void
+static __rte_always_inline void
drain_tx_buffers(struct lcore_conf *qconf)
{
struct buffer *buf;