#include <rte_lcore.h>
#include <rte_atomic.h>
#include <rte_branch_prediction.h>
-#include <rte_ring.h>
-#include <rte_memory.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
-#include <rte_memcpy.h>
#include <rte_interrupts.h>
#include <rte_pci.h>
#include <rte_ether.h>
#include <rte_sctp.h>
#include <rte_prefetch.h>
#include <rte_string_fns.h>
+#include <rte_flow.h>
+#include <rte_gro.h>
#include "testpmd.h"
#define IP_DEFTTL 64 /* from RFC 1340. */
uint16_t outer_l3_len;
uint8_t outer_l4_proto;
uint16_t tso_segsz;
+ uint16_t tunnel_tso_segsz;
+ uint32_t pkt_len;
};
/* simplified GRE header */
uint16_t proto;
} __attribute__((__packed__));
-static uint16_t
-get_psd_sum(void *l3_hdr, uint16_t ethertype, uint64_t ol_flags)
-{
- if (ethertype == _htons(ETHER_TYPE_IPv4))
- return rte_ipv4_phdr_cksum(l3_hdr, ol_flags);
- else /* assume ethertype == ETHER_TYPE_IPv6 */
- return rte_ipv6_phdr_cksum(l3_hdr, ol_flags);
-}
-
static uint16_t
get_udptcp_checksum(void *l3_hdr, void *l4_hdr, uint16_t ethertype)
{
info->l2_len = 0;
}
-/* modify the IPv4 or IPv4 source address of a packet */
-static void
-change_ip_addresses(void *l3_hdr, uint16_t ethertype)
-{
- struct ipv4_hdr *ipv4_hdr = l3_hdr;
- struct ipv6_hdr *ipv6_hdr = l3_hdr;
-
- if (ethertype == _htons(ETHER_TYPE_IPv4)) {
- ipv4_hdr->src_addr =
- rte_cpu_to_be_32(rte_be_to_cpu_32(ipv4_hdr->src_addr) + 1);
- } else if (ethertype == _htons(ETHER_TYPE_IPv6)) {
- ipv6_hdr->src_addr[15] = ipv6_hdr->src_addr[15] + 1;
- }
-}
-
/* if possible, calculate the checksum of a packet in hw or sw,
* depending on the testpmd command line configuration */
static uint64_t
struct tcp_hdr *tcp_hdr;
struct sctp_hdr *sctp_hdr;
uint64_t ol_flags = 0;
+ uint32_t max_pkt_len, tso_segsz = 0;
+
+ /* ensure packet is large enough to require tso */
+ if (!info->is_tunnel) {
+ max_pkt_len = info->l2_len + info->l3_len + info->l4_len +
+ info->tso_segsz;
+ if (info->tso_segsz != 0 && info->pkt_len > max_pkt_len)
+ tso_segsz = info->tso_segsz;
+ } else {
+ max_pkt_len = info->outer_l2_len + info->outer_l3_len +
+ info->l2_len + info->l3_len + info->l4_len +
+ info->tunnel_tso_segsz;
+ if (info->tunnel_tso_segsz != 0 && info->pkt_len > max_pkt_len)
+ tso_segsz = info->tunnel_tso_segsz;
+ }
if (info->ethertype == _htons(ETHER_TYPE_IPv4)) {
ipv4_hdr = l3_hdr;
ipv4_hdr->hdr_checksum = 0;
ol_flags |= PKT_TX_IPV4;
- if (info->tso_segsz != 0 && info->l4_proto == IPPROTO_TCP) {
+ if (info->l4_proto == IPPROTO_TCP && tso_segsz) {
ol_flags |= PKT_TX_IP_CKSUM;
} else {
if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM)
/* do not recalculate udp cksum if it was 0 */
if (udp_hdr->dgram_cksum != 0) {
udp_hdr->dgram_cksum = 0;
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM) {
+ if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM)
ol_flags |= PKT_TX_UDP_CKSUM;
- udp_hdr->dgram_cksum = get_psd_sum(l3_hdr,
- info->ethertype, ol_flags);
- } else {
+ else {
udp_hdr->dgram_cksum =
get_udptcp_checksum(l3_hdr, udp_hdr,
info->ethertype);
} else if (info->l4_proto == IPPROTO_TCP) {
tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + info->l3_len);
tcp_hdr->cksum = 0;
- if (info->tso_segsz != 0) {
+ if (tso_segsz)
ol_flags |= PKT_TX_TCP_SEG;
- tcp_hdr->cksum = get_psd_sum(l3_hdr, info->ethertype,
- ol_flags);
- } else if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
+ else if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM)
ol_flags |= PKT_TX_TCP_CKSUM;
- tcp_hdr->cksum = get_psd_sum(l3_hdr, info->ethertype,
- ol_flags);
- } else {
+ else {
tcp_hdr->cksum =
get_udptcp_checksum(l3_hdr, tcp_hdr,
info->ethertype);
return ol_flags;
}
-/* Calculate the checksum of outer header (only vxlan is supported,
- * meaning IP + UDP). The caller already checked that it's a vxlan
- * packet */
+/* Calculate the checksum of outer header */
static uint64_t
process_outer_cksums(void *outer_l3_hdr, struct testpmd_offload_info *info,
- uint16_t testpmd_ol_flags)
+ uint16_t testpmd_ol_flags, int tso_enabled)
{
struct ipv4_hdr *ipv4_hdr = outer_l3_hdr;
struct ipv6_hdr *ipv6_hdr = outer_l3_hdr;
ol_flags |= PKT_TX_OUTER_IP_CKSUM;
else
ipv4_hdr->hdr_checksum = rte_ipv4_cksum(ipv4_hdr);
- } else if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM)
+ } else
ol_flags |= PKT_TX_OUTER_IPV6;
if (info->outer_l4_proto != IPPROTO_UDP)
return ol_flags;
- /* outer UDP checksum is always done in software as we have no
- * hardware supporting it today, and no API for it. */
-
udp_hdr = (struct udp_hdr *)((char *)outer_l3_hdr + info->outer_l3_len);
+
+ /* outer UDP checksum is done in software as we have no hardware
+ * supporting it today, and no API for it. In the other side, for
+ * UDP tunneling, like VXLAN or Geneve, outer UDP checksum can be
+ * set to zero.
+ *
+ * If a packet will be TSOed into small packets by NIC, we cannot
+ * set/calculate a non-zero checksum, because it will be a wrong
+ * value after the packet be split into several small packets.
+ */
+ if (tso_enabled)
+ udp_hdr->dgram_cksum = 0;
+
/* do not recalculate udp cksum if it was 0 */
if (udp_hdr->dgram_cksum != 0) {
udp_hdr->dgram_cksum = 0;
return ol_flags;
}
+/*
+ * Helper function.
+ * Performs actual copying.
+ * Returns number of segments in the destination mbuf on success,
+ * or negative error code on failure.
+ */
+static int
+mbuf_copy_split(const struct rte_mbuf *ms, struct rte_mbuf *md[],
+ uint16_t seglen[], uint8_t nb_seg)
+{
+ uint32_t dlen, slen, tlen;
+ uint32_t i, len;
+ const struct rte_mbuf *m;
+ const uint8_t *src;
+ uint8_t *dst;
+
+ dlen = 0;
+ slen = 0;
+ tlen = 0;
+
+ dst = NULL;
+ src = NULL;
+
+ m = ms;
+ i = 0;
+ while (ms != NULL && i != nb_seg) {
+
+ if (slen == 0) {
+ slen = rte_pktmbuf_data_len(ms);
+ src = rte_pktmbuf_mtod(ms, const uint8_t *);
+ }
+
+ if (dlen == 0) {
+ dlen = RTE_MIN(seglen[i], slen);
+ md[i]->data_len = dlen;
+ md[i]->next = (i + 1 == nb_seg) ? NULL : md[i + 1];
+ dst = rte_pktmbuf_mtod(md[i], uint8_t *);
+ }
+
+ len = RTE_MIN(slen, dlen);
+ memcpy(dst, src, len);
+ tlen += len;
+ slen -= len;
+ dlen -= len;
+ src += len;
+ dst += len;
+
+ if (slen == 0)
+ ms = ms->next;
+ if (dlen == 0)
+ i++;
+ }
+
+ if (ms != NULL)
+ return -ENOBUFS;
+ else if (tlen != m->pkt_len)
+ return -EINVAL;
+
+ md[0]->nb_segs = nb_seg;
+ md[0]->pkt_len = tlen;
+ md[0]->vlan_tci = m->vlan_tci;
+ md[0]->vlan_tci_outer = m->vlan_tci_outer;
+ md[0]->ol_flags = m->ol_flags;
+ md[0]->tx_offload = m->tx_offload;
+
+ return nb_seg;
+}
+
+/*
+ * Allocate a new mbuf with up to tx_pkt_nb_segs segments.
+ * Copy packet contents and offload information into then new segmented mbuf.
+ */
+static struct rte_mbuf *
+pkt_copy_split(const struct rte_mbuf *pkt)
+{
+ int32_t n, rc;
+ uint32_t i, len, nb_seg;
+ struct rte_mempool *mp;
+ uint16_t seglen[RTE_MAX_SEGS_PER_PKT];
+ struct rte_mbuf *p, *md[RTE_MAX_SEGS_PER_PKT];
+
+ mp = current_fwd_lcore()->mbp;
+
+ if (tx_pkt_split == TX_PKT_SPLIT_RND)
+ nb_seg = random() % tx_pkt_nb_segs + 1;
+ else
+ nb_seg = tx_pkt_nb_segs;
+
+ memcpy(seglen, tx_pkt_seg_lengths, nb_seg * sizeof(seglen[0]));
+
+ /* calculate number of segments to use and their length. */
+ len = 0;
+ for (i = 0; i != nb_seg && len < pkt->pkt_len; i++) {
+ len += seglen[i];
+ md[i] = NULL;
+ }
+
+ n = pkt->pkt_len - len;
+
+ /* update size of the last segment to fit rest of the packet */
+ if (n >= 0) {
+ seglen[i - 1] += n;
+ len += n;
+ }
+
+ nb_seg = i;
+ while (i != 0) {
+ p = rte_pktmbuf_alloc(mp);
+ if (p == NULL) {
+ RTE_LOG(ERR, USER1,
+ "failed to allocate %u-th of %u mbuf "
+ "from mempool: %s\n",
+ nb_seg - i, nb_seg, mp->name);
+ break;
+ }
+
+ md[--i] = p;
+ if (rte_pktmbuf_tailroom(md[i]) < seglen[i]) {
+ RTE_LOG(ERR, USER1, "mempool %s, %u-th segment: "
+ "expected seglen: %u, "
+ "actual mbuf tailroom: %u\n",
+ mp->name, i, seglen[i],
+ rte_pktmbuf_tailroom(md[i]));
+ break;
+ }
+ }
+
+ /* all mbufs successfully allocated, do copy */
+ if (i == 0) {
+ rc = mbuf_copy_split(pkt, md, seglen, nb_seg);
+ if (rc < 0)
+ RTE_LOG(ERR, USER1,
+ "mbuf_copy_split for %p(len=%u, nb_seg=%u) "
+ "into %u segments failed with error code: %d\n",
+ pkt, pkt->pkt_len, pkt->nb_segs, nb_seg, rc);
+
+ /* figure out how many mbufs to free. */
+ i = RTE_MAX(rc, 0);
+ }
+
+ /* free unused mbufs */
+ for (; i != nb_seg; i++) {
+ rte_pktmbuf_free_seg(md[i]);
+ md[i] = NULL;
+ }
+
+ return md[0];
+}
+
/*
* Receive a burst of packets, and for each packet:
* - parse packet, and try to recognize a supported packet type (1)
* - if it's not a supported packet type, don't touch the packet, else:
- * - modify the IPs in inner headers and in outer headers if any
* - reprocess the checksum of all supported layers. This is done in SW
* or HW, depending on testpmd command line configuration
* - if TSO is enabled in testpmd command line, also flag the mbuf for TCP
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
struct rte_port *txp;
- struct rte_mbuf *m;
+ struct rte_mbuf *m, *p;
struct ether_hdr *eth_hdr;
void *l3_hdr = NULL, *outer_l3_hdr = NULL; /* can be IPv4 or IPv6 */
uint16_t nb_rx;
uint16_t nb_tx;
+ uint16_t nb_prep;
uint16_t i;
- uint64_t ol_flags;
+ uint64_t rx_ol_flags, tx_ol_flags;
uint16_t testpmd_ol_flags;
+ uint32_t retry;
uint32_t rx_bad_ip_csum;
uint32_t rx_bad_l4_csum;
struct testpmd_offload_info info;
nb_pkt_per_burst);
if (unlikely(nb_rx == 0))
return;
+ if (unlikely(gro_ports[fs->rx_port].enable))
+ nb_rx = rte_gro_reassemble_burst(pkts_burst,
+ nb_rx,
+ &(gro_ports[fs->rx_port].param));
#ifdef RTE_TEST_PMD_RECORD_BURST_STATS
fs->rx_burst_stats.pkt_burst_spread[nb_rx]++;
testpmd_ol_flags = txp->tx_ol_flags;
memset(&info, 0, sizeof(info));
info.tso_segsz = txp->tso_segsz;
+ info.tunnel_tso_segsz = txp->tunnel_tso_segsz;
for (i = 0; i < nb_rx; i++) {
+ if (likely(i < nb_rx - 1))
+ rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1],
+ void *));
- ol_flags = 0;
- info.is_tunnel = 0;
m = pkts_burst[i];
+ info.is_tunnel = 0;
+ info.pkt_len = rte_pktmbuf_pkt_len(m);
+ tx_ol_flags = 0;
+ rx_ol_flags = m->ol_flags;
/* Update the L3/L4 checksum error packet statistics */
- rx_bad_ip_csum += ((m->ol_flags & PKT_RX_IP_CKSUM_BAD) != 0);
- rx_bad_l4_csum += ((m->ol_flags & PKT_RX_L4_CKSUM_BAD) != 0);
+ if ((rx_ol_flags & PKT_RX_IP_CKSUM_MASK) == PKT_RX_IP_CKSUM_BAD)
+ rx_bad_ip_csum += 1;
+ if ((rx_ol_flags & PKT_RX_L4_CKSUM_MASK) == PKT_RX_L4_CKSUM_BAD)
+ rx_bad_l4_csum += 1;
/* step 1: dissect packet, parsing optional vlan, ip4/ip6, vxlan
* and inner headers */
if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_PARSE_TUNNEL) {
if (info.l4_proto == IPPROTO_UDP) {
struct udp_hdr *udp_hdr;
+
udp_hdr = (struct udp_hdr *)((char *)l3_hdr +
info.l3_len);
parse_vxlan(udp_hdr, &info, m->packet_type);
+ if (info.is_tunnel)
+ tx_ol_flags |= PKT_TX_TUNNEL_VXLAN;
} 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)
+ tx_ol_flags |= PKT_TX_TUNNEL_GRE;
} 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)
+ tx_ol_flags |= PKT_TX_TUNNEL_IPIP;
}
}
l3_hdr = (char *)l3_hdr + info.outer_l3_len + info.l2_len;
}
- /* step 2: change all source IPs (v4 or v6) so we need
- * to recompute the chksums even if they were correct */
-
- change_ip_addresses(l3_hdr, info.ethertype);
- if (info.is_tunnel == 1)
- change_ip_addresses(outer_l3_hdr, info.outer_ethertype);
-
- /* step 3: depending on user command line configuration,
+ /* step 2: depending on user command line configuration,
* recompute checksum either in software or flag the
* mbuf to offload the calculation to the NIC. If TSO
* is configured, prepare the mbuf for TCP segmentation. */
/* process checksums of inner headers first */
- ol_flags |= process_inner_cksums(l3_hdr, &info, testpmd_ol_flags);
+ tx_ol_flags |= process_inner_cksums(l3_hdr, &info,
+ testpmd_ol_flags);
/* Then process outer headers if any. Note that the software
* checksum will be wrong if one of the inner checksums is
* processed in hardware. */
if (info.is_tunnel == 1) {
- ol_flags |= process_outer_cksums(outer_l3_hdr, &info,
- testpmd_ol_flags);
+ tx_ol_flags |= process_outer_cksums(outer_l3_hdr, &info,
+ testpmd_ol_flags,
+ !!(tx_ol_flags & PKT_TX_TCP_SEG));
}
- /* step 4: fill the mbuf meta data (flags and header lengths) */
+ /* step 3: fill the mbuf meta data (flags and header lengths) */
if (info.is_tunnel == 1) {
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) {
+ if (info.tunnel_tso_segsz ||
+ (testpmd_ol_flags &
+ TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) ||
+ (tx_ol_flags & PKT_TX_OUTER_IPV6)) {
m->outer_l2_len = info.outer_l2_len;
m->outer_l3_len = info.outer_l3_len;
m->l2_len = info.l2_len;
m->l3_len = info.l3_len;
m->l4_len = info.l4_len;
+ m->tso_segsz = info.tunnel_tso_segsz;
}
else {
/* if there is a outer UDP cksum
m->l2_len = info.l2_len;
m->l3_len = info.l3_len;
m->l4_len = info.l4_len;
+ m->tso_segsz = info.tso_segsz;
+ }
+ m->ol_flags = tx_ol_flags;
+
+ /* Do split & copy for the packet. */
+ if (tx_pkt_split != TX_PKT_SPLIT_OFF) {
+ p = pkt_copy_split(m);
+ if (p != NULL) {
+ rte_pktmbuf_free(m);
+ m = p;
+ pkts_burst[i] = m;
+ }
}
- m->tso_segsz = info.tso_segsz;
- m->ol_flags = ol_flags;
/* if verbose mode is enabled, dump debug info */
if (verbose_level > 0) {
- struct {
- uint64_t flag;
- uint64_t mask;
- } tx_flags[] = {
- { PKT_TX_IP_CKSUM, PKT_TX_IP_CKSUM },
- { PKT_TX_UDP_CKSUM, PKT_TX_L4_MASK },
- { PKT_TX_TCP_CKSUM, PKT_TX_L4_MASK },
- { PKT_TX_SCTP_CKSUM, PKT_TX_L4_MASK },
- { PKT_TX_IPV4, PKT_TX_IPV4 },
- { PKT_TX_IPV6, PKT_TX_IPV6 },
- { PKT_TX_OUTER_IP_CKSUM, PKT_TX_OUTER_IP_CKSUM },
- { PKT_TX_OUTER_IPV4, PKT_TX_OUTER_IPV4 },
- { PKT_TX_OUTER_IPV6, PKT_TX_OUTER_IPV6 },
- { PKT_TX_TCP_SEG, PKT_TX_TCP_SEG },
- };
- unsigned j;
- const char *name;
+ char buf[256];
printf("-----------------\n");
+ printf("port=%u, mbuf=%p, pkt_len=%u, nb_segs=%u:\n",
+ fs->rx_port, m, m->pkt_len, m->nb_segs);
/* dump rx parsed packet info */
+ rte_get_rx_ol_flag_list(rx_ol_flags, buf, sizeof(buf));
printf("rx: l2_len=%d ethertype=%x l3_len=%d "
- "l4_proto=%d l4_len=%d\n",
+ "l4_proto=%d l4_len=%d flags=%s\n",
info.l2_len, rte_be_to_cpu_16(info.ethertype),
- info.l3_len, info.l4_proto, info.l4_len);
+ info.l3_len, info.l4_proto, info.l4_len, buf);
+ if (rx_ol_flags & PKT_RX_LRO)
+ printf("rx: m->lro_segsz=%u\n", m->tso_segsz);
if (info.is_tunnel == 1)
printf("rx: outer_l2_len=%d outer_ethertype=%x "
"outer_l3_len=%d\n", info.outer_l2_len,
printf("tx: m->l2_len=%d m->l3_len=%d "
"m->l4_len=%d\n",
m->l2_len, m->l3_len, m->l4_len);
- if ((info.is_tunnel == 1) &&
- (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM))
- printf("tx: m->outer_l2_len=%d m->outer_l3_len=%d\n",
- m->outer_l2_len, m->outer_l3_len);
- if (info.tso_segsz != 0)
+ if (info.is_tunnel == 1) {
+ if ((testpmd_ol_flags &
+ TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) ||
+ (tx_ol_flags & PKT_TX_OUTER_IPV6))
+ printf("tx: m->outer_l2_len=%d "
+ "m->outer_l3_len=%d\n",
+ m->outer_l2_len,
+ m->outer_l3_len);
+ if (info.tunnel_tso_segsz != 0 &&
+ (m->ol_flags & PKT_TX_TCP_SEG))
+ printf("tx: m->tso_segsz=%d\n",
+ m->tso_segsz);
+ } else if (info.tso_segsz != 0 &&
+ (m->ol_flags & PKT_TX_TCP_SEG))
printf("tx: m->tso_segsz=%d\n", m->tso_segsz);
- printf("tx: flags=");
- for (j = 0; j < sizeof(tx_flags)/sizeof(*tx_flags); j++) {
- name = rte_get_tx_ol_flag_name(tx_flags[j].flag);
- if ((m->ol_flags & tx_flags[j].mask) ==
- tx_flags[j].flag)
- printf("%s ", name);
- }
+ rte_get_tx_ol_flag_list(m->ol_flags, buf, sizeof(buf));
+ printf("tx: flags=%s", buf);
printf("\n");
}
}
- nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
+
+ nb_prep = rte_eth_tx_prepare(fs->tx_port, fs->tx_queue,
+ pkts_burst, nb_rx);
+ if (nb_prep != nb_rx)
+ printf("Preparing packet burst to transmit failed: %s\n",
+ rte_strerror(rte_errno));
+
+ nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst,
+ nb_prep);
+
+ /*
+ * Retry if necessary
+ */
+ if (unlikely(nb_tx < nb_rx) && fs->retry_enabled) {
+ retry = 0;
+ while (nb_tx < nb_rx && retry++ < burst_tx_retry_num) {
+ rte_delay_us(burst_tx_delay_time);
+ nb_tx += rte_eth_tx_burst(fs->tx_port, fs->tx_queue,
+ &pkts_burst[nb_tx], nb_rx - nb_tx);
+ }
+ }
fs->tx_packets += nb_tx;
fs->rx_bad_ip_csum += rx_bad_ip_csum;
fs->rx_bad_l4_csum += rx_bad_l4_csum;