#include <rte_cycles.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
-#include <rte_memzone.h>
#include <rte_launch.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_atomic.h>
#include <rte_branch_prediction.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 <rte_gso.h>
+
#include "testpmd.h"
#define IP_DEFTTL 64 /* from RFC 1340. */
/* structure that caches offload info for the current packet */
struct testpmd_offload_info {
uint16_t ethertype;
+ uint8_t gso_enable;
uint16_t l2_len;
uint16_t l3_len;
uint16_t l4_len;
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)
{
* depending on the testpmd command line configuration */
static uint64_t
process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
- uint16_t testpmd_ol_flags)
+ uint64_t tx_offloads)
{
struct ipv4_hdr *ipv4_hdr = l3_hdr;
struct udp_hdr *udp_hdr;
if (!info->is_tunnel) {
max_pkt_len = info->l2_len + info->l3_len + info->l4_len +
info->tso_segsz;
- if (info->tunnel_tso_segsz != 0 && info->pkt_len > max_pkt_len)
+ 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 +
ipv4_hdr->hdr_checksum = 0;
ol_flags |= PKT_TX_IPV4;
- if (info->l4_proto == IPPROTO_TCP &&
- ((info->is_tunnel && info->tunnel_tso_segsz != 0) ||
- (!info->is_tunnel && info->tso_segsz != 0))) {
+ if (info->l4_proto == IPPROTO_TCP && tso_segsz) {
ol_flags |= PKT_TX_IP_CKSUM;
} else {
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM)
+ if (tx_offloads & DEV_TX_OFFLOAD_IPV4_CKSUM)
ol_flags |= PKT_TX_IP_CKSUM;
else
ipv4_hdr->hdr_checksum =
/* 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 (tx_offloads & DEV_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 (tso_segsz) {
+ 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 (tx_offloads & DEV_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);
}
+ if (info->gso_enable)
+ ol_flags |= PKT_TX_TCP_SEG;
} else if (info->l4_proto == IPPROTO_SCTP) {
sctp_hdr = (struct sctp_hdr *)((char *)l3_hdr + info->l3_len);
sctp_hdr->cksum = 0;
/* sctp payload must be a multiple of 4 to be
* offloaded */
- if ((testpmd_ol_flags & TESTPMD_TX_OFFLOAD_SCTP_CKSUM) &&
+ if ((tx_offloads & DEV_TX_OFFLOAD_SCTP_CKSUM) &&
((ipv4_hdr->total_length & 0x3) == 0)) {
ol_flags |= PKT_TX_SCTP_CKSUM;
} else {
/* 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, int tso_enabled)
+ uint64_t tx_offloads, int tso_enabled)
{
struct ipv4_hdr *ipv4_hdr = outer_l3_hdr;
struct ipv6_hdr *ipv6_hdr = outer_l3_hdr;
ipv4_hdr->hdr_checksum = 0;
ol_flags |= PKT_TX_OUTER_IPV4;
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM)
+ if (tx_offloads & DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM)
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)
while (i != 0) {
p = rte_pktmbuf_alloc(mp);
if (p == NULL) {
- RTE_LOG(ERR, USER1,
+ TESTPMD_LOG(ERR,
"failed to allocate %u-th of %u mbuf "
"from mempool: %s\n",
nb_seg - i, nb_seg, mp->name);
md[--i] = p;
if (rte_pktmbuf_tailroom(md[i]) < seglen[i]) {
- RTE_LOG(ERR, USER1, "mempool %s, %u-th segment: "
+ TESTPMD_LOG(ERR, "mempool %s, %u-th segment: "
"expected seglen: %u, "
"actual mbuf tailroom: %u\n",
mp->name, i, seglen[i],
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=%hhu) "
+ TESTPMD_LOG(ERR,
+ "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);
pkt_burst_checksum_forward(struct fwd_stream *fs)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+ struct rte_mbuf *gso_segments[GSO_MAX_PKT_BURST];
+ struct rte_gso_ctx *gso_ctx;
+ struct rte_mbuf **tx_pkts_burst;
struct rte_port *txp;
struct rte_mbuf *m, *p;
struct ether_hdr *eth_hdr;
void *l3_hdr = NULL, *outer_l3_hdr = NULL; /* can be IPv4 or IPv6 */
+ void **gro_ctx;
+ uint16_t gro_pkts_num;
+ uint8_t gro_enable;
uint16_t nb_rx;
uint16_t nb_tx;
+ uint16_t nb_prep;
uint16_t i;
uint64_t rx_ol_flags, tx_ol_flags;
- uint16_t testpmd_ol_flags;
+ uint64_t tx_offloads;
uint32_t retry;
uint32_t rx_bad_ip_csum;
uint32_t rx_bad_l4_csum;
struct testpmd_offload_info info;
+ uint16_t nb_segments = 0;
+ int ret;
#ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES
uint64_t start_tsc;
nb_pkt_per_burst);
if (unlikely(nb_rx == 0))
return;
-
#ifdef RTE_TEST_PMD_RECORD_BURST_STATS
fs->rx_burst_stats.pkt_burst_spread[nb_rx]++;
#endif
fs->rx_packets += nb_rx;
rx_bad_ip_csum = 0;
rx_bad_l4_csum = 0;
+ gro_enable = gro_ports[fs->rx_port].enable;
txp = &ports[fs->tx_port];
- testpmd_ol_flags = txp->tx_ol_flags;
+ tx_offloads = txp->dev_conf.txmode.offloads;
memset(&info, 0, sizeof(info));
info.tso_segsz = txp->tso_segsz;
info.tunnel_tso_segsz = txp->tunnel_tso_segsz;
+ if (gso_ports[fs->tx_port].enable)
+ info.gso_enable = 1;
for (i = 0; i < nb_rx; i++) {
if (likely(i < nb_rx - 1))
rx_ol_flags = m->ol_flags;
/* Update the L3/L4 checksum error packet statistics */
- rx_bad_ip_csum += ((rx_ol_flags & PKT_RX_IP_CKSUM_BAD) != 0);
- rx_bad_l4_csum += ((rx_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 */
l3_hdr = (char *)eth_hdr + info.l2_len;
/* check if it's a supported tunnel */
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_PARSE_TUNNEL) {
+ if (txp->parse_tunnel) {
if (info.l4_proto == IPPROTO_UDP) {
struct udp_hdr *udp_hdr;
/* process checksums of inner headers first */
tx_ol_flags |= process_inner_cksums(l3_hdr, &info,
- testpmd_ol_flags);
+ tx_offloads);
/* 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) {
tx_ol_flags |= process_outer_cksums(outer_l3_hdr, &info,
- testpmd_ol_flags,
+ tx_offloads,
!!(tx_ol_flags & PKT_TX_TCP_SEG));
}
if (info.is_tunnel == 1) {
if (info.tunnel_tso_segsz ||
- testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) {
+ (tx_offloads &
+ DEV_TX_OFFLOAD_OUTER_IPV4_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;
char buf[256];
printf("-----------------\n");
- printf("port=%u, mbuf=%p, pkt_len=%u, nb_segs=%hhu:\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));
"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, 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,
rte_be_to_cpu_16(info.outer_ethertype),
info.outer_l3_len);
/* dump tx packet info */
- if ((testpmd_ol_flags & (TESTPMD_TX_OFFLOAD_IP_CKSUM |
- TESTPMD_TX_OFFLOAD_UDP_CKSUM |
- TESTPMD_TX_OFFLOAD_TCP_CKSUM |
- TESTPMD_TX_OFFLOAD_SCTP_CKSUM)) ||
+ if ((tx_offloads & (DEV_TX_OFFLOAD_IPV4_CKSUM |
+ DEV_TX_OFFLOAD_UDP_CKSUM |
+ DEV_TX_OFFLOAD_TCP_CKSUM |
+ DEV_TX_OFFLOAD_SCTP_CKSUM)) ||
info.tso_segsz != 0)
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) {
- if (testpmd_ol_flags &
- TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM)
+ if ((tx_offloads &
+ DEV_TX_OFFLOAD_OUTER_IPV4_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,
printf("\n");
}
}
- nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
+
+ if (unlikely(gro_enable)) {
+ if (gro_flush_cycles == GRO_DEFAULT_FLUSH_CYCLES) {
+ nb_rx = rte_gro_reassemble_burst(pkts_burst, nb_rx,
+ &(gro_ports[fs->rx_port].param));
+ } else {
+ gro_ctx = current_fwd_lcore()->gro_ctx;
+ nb_rx = rte_gro_reassemble(pkts_burst, nb_rx, gro_ctx);
+
+ if (++fs->gro_times >= gro_flush_cycles) {
+ gro_pkts_num = rte_gro_get_pkt_count(gro_ctx);
+ if (gro_pkts_num > MAX_PKT_BURST - nb_rx)
+ gro_pkts_num = MAX_PKT_BURST - nb_rx;
+
+ nb_rx += rte_gro_timeout_flush(gro_ctx, 0,
+ RTE_GRO_TCP_IPV4,
+ &pkts_burst[nb_rx],
+ gro_pkts_num);
+ fs->gro_times = 0;
+ }
+ }
+ }
+
+ if (gso_ports[fs->tx_port].enable == 0)
+ tx_pkts_burst = pkts_burst;
+ else {
+ gso_ctx = &(current_fwd_lcore()->gso_ctx);
+ gso_ctx->gso_size = gso_max_segment_size;
+ for (i = 0; i < nb_rx; i++) {
+ ret = rte_gso_segment(pkts_burst[i], gso_ctx,
+ &gso_segments[nb_segments],
+ GSO_MAX_PKT_BURST - nb_segments);
+ if (ret >= 0)
+ nb_segments += ret;
+ else {
+ TESTPMD_LOG(DEBUG, "Unable to segment packet");
+ rte_pktmbuf_free(pkts_burst[i]);
+ }
+ }
+
+ tx_pkts_burst = gso_segments;
+ nb_rx = nb_segments;
+ }
+
+ nb_prep = rte_eth_tx_prepare(fs->tx_port, fs->tx_queue,
+ tx_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, tx_pkts_burst,
+ nb_prep);
+
/*
* Retry if necessary
*/
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);
+ &tx_pkts_burst[nb_tx], nb_rx - nb_tx);
}
}
fs->tx_packets += nb_tx;
if (unlikely(nb_tx < nb_rx)) {
fs->fwd_dropped += (nb_rx - nb_tx);
do {
- rte_pktmbuf_free(pkts_burst[nb_tx]);
+ rte_pktmbuf_free(tx_pkts_burst[nb_tx]);
} while (++nb_tx < nb_rx);
}
+
#ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES
end_tsc = rte_rdtsc();
core_cycles = (end_tsc - start_tsc);