#define IP_HDRLEN 0x05 /* default IP header length == five 32-bits words. */
#define IP_VHL_DEF (IP_VERSION | IP_HDRLEN)
-/* we cannot use htons() from arpa/inet.h due to name conflicts, and we
- * cannot use rte_cpu_to_be_16() on a constant in a switch/case */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+/* We cannot use rte_cpu_to_be_16() on a constant in a switch/case */
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
#define _htons(x) ((uint16_t)((((x) & 0x00ffU) << 8) | (((x) & 0xff00U) >> 8)))
#else
#define _htons(x) (x)
#endif
-static inline uint16_t
-get_16b_sum(uint16_t *ptr16, uint32_t nr)
-{
- uint32_t sum = 0;
- while (nr > 1)
- {
- sum +=*ptr16;
- nr -= sizeof(uint16_t);
- ptr16++;
- if (sum > UINT16_MAX)
- sum -= UINT16_MAX;
- }
-
- /* If length is in odd bytes */
- if (nr)
- sum += *((uint8_t*)ptr16);
-
- sum = ((sum & 0xffff0000) >> 16) + (sum & 0xffff);
- sum &= 0x0ffff;
- return (uint16_t)sum;
-}
-
-static inline uint16_t
-get_ipv4_cksum(struct ipv4_hdr *ipv4_hdr)
-{
- uint16_t cksum;
- cksum = get_16b_sum((uint16_t*)ipv4_hdr, sizeof(struct ipv4_hdr));
- return (uint16_t)((cksum == 0xffff)?cksum:~cksum);
-}
-
-
-static inline uint16_t
-get_ipv4_psd_sum(struct ipv4_hdr *ip_hdr)
-{
- /* Pseudo Header for IPv4/UDP/TCP checksum */
- union ipv4_psd_header {
- struct {
- uint32_t src_addr; /* IP address of source host. */
- uint32_t dst_addr; /* IP address of destination host(s). */
- uint8_t zero; /* zero. */
- uint8_t proto; /* L4 protocol type. */
- uint16_t len; /* L4 length. */
- } __attribute__((__packed__));
- uint16_t u16_arr[0];
- } psd_hdr;
-
- psd_hdr.src_addr = ip_hdr->src_addr;
- psd_hdr.dst_addr = ip_hdr->dst_addr;
- psd_hdr.zero = 0;
- psd_hdr.proto = ip_hdr->next_proto_id;
- psd_hdr.len = rte_cpu_to_be_16((uint16_t)(rte_be_to_cpu_16(ip_hdr->total_length)
- - sizeof(struct ipv4_hdr)));
- return get_16b_sum(psd_hdr.u16_arr, sizeof(psd_hdr));
-}
-
-static inline uint16_t
-get_ipv6_psd_sum(struct ipv6_hdr *ip_hdr)
-{
- /* Pseudo Header for IPv6/UDP/TCP checksum */
- union ipv6_psd_header {
- struct {
- uint8_t src_addr[16]; /* IP address of source host. */
- uint8_t dst_addr[16]; /* IP address of destination host(s). */
- uint32_t len; /* L4 length. */
- uint32_t proto; /* L4 protocol - top 3 bytes must be zero */
- } __attribute__((__packed__));
-
- uint16_t u16_arr[0]; /* allow use as 16-bit values with safe aliasing */
- } psd_hdr;
-
- rte_memcpy(&psd_hdr.src_addr, ip_hdr->src_addr,
- sizeof(ip_hdr->src_addr) + sizeof(ip_hdr->dst_addr));
- psd_hdr.len = ip_hdr->payload_len;
- psd_hdr.proto = (ip_hdr->proto << 24);
-
- return get_16b_sum(psd_hdr.u16_arr, sizeof(psd_hdr));
-}
-
static uint16_t
-get_psd_sum(void *l3_hdr, uint16_t ethertype)
+get_psd_sum(void *l3_hdr, uint16_t ethertype, uint64_t ol_flags)
{
if (ethertype == _htons(ETHER_TYPE_IPv4))
- return get_ipv4_psd_sum(l3_hdr);
+ return rte_ipv4_phdr_cksum(l3_hdr, ol_flags);
else /* assume ethertype == ETHER_TYPE_IPv6 */
- return get_ipv6_psd_sum(l3_hdr);
-}
-
-static inline uint16_t
-get_ipv4_udptcp_checksum(struct ipv4_hdr *ipv4_hdr, uint16_t *l4_hdr)
-{
- uint32_t cksum;
- uint32_t l4_len;
-
- l4_len = rte_be_to_cpu_16(ipv4_hdr->total_length) - sizeof(struct ipv4_hdr);
-
- cksum = get_16b_sum(l4_hdr, l4_len);
- cksum += get_ipv4_psd_sum(ipv4_hdr);
-
- cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
- cksum = (~cksum) & 0xffff;
- if (cksum == 0)
- cksum = 0xffff;
- return (uint16_t)cksum;
-}
-
-static inline uint16_t
-get_ipv6_udptcp_checksum(struct ipv6_hdr *ipv6_hdr, uint16_t *l4_hdr)
-{
- uint32_t cksum;
- uint32_t l4_len;
-
- l4_len = rte_be_to_cpu_16(ipv6_hdr->payload_len);
-
- cksum = get_16b_sum(l4_hdr, l4_len);
- cksum += get_ipv6_psd_sum(ipv6_hdr);
-
- cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
- cksum = (~cksum) & 0xffff;
- if (cksum == 0)
- cksum = 0xffff;
-
- return (uint16_t)cksum;
+ return rte_ipv6_phdr_cksum(l3_hdr, ol_flags);
}
static uint16_t
get_udptcp_checksum(void *l3_hdr, void *l4_hdr, uint16_t ethertype)
{
if (ethertype == _htons(ETHER_TYPE_IPv4))
- return get_ipv4_udptcp_checksum(l3_hdr, l4_hdr);
+ return rte_ipv4_udptcp_cksum(l3_hdr, l4_hdr);
else /* assume ethertype == ETHER_TYPE_IPv6 */
- return get_ipv6_udptcp_checksum(l3_hdr, l4_hdr);
+ return rte_ipv6_udptcp_cksum(l3_hdr, l4_hdr);
}
/*
* Parse an ethernet header to fill the ethertype, l2_len, l3_len and
* ipproto. This function is able to recognize IPv4/IPv6 with one optional vlan
- * header.
+ * header. The l4_len argument is only set in case of TCP (useful for TSO).
*/
static void
parse_ethernet(struct ether_hdr *eth_hdr, uint16_t *ethertype, uint16_t *l2_len,
- uint16_t *l3_len, uint8_t *l4_proto)
+ uint16_t *l3_len, uint8_t *l4_proto, uint16_t *l4_len)
{
struct ipv4_hdr *ipv4_hdr;
struct ipv6_hdr *ipv6_hdr;
+ struct tcp_hdr *tcp_hdr;
*l2_len = sizeof(struct ether_hdr);
*ethertype = eth_hdr->ether_type;
*l4_proto = 0;
break;
}
+
+ if (*l4_proto == IPPROTO_TCP) {
+ tcp_hdr = (struct tcp_hdr *)((char *)eth_hdr +
+ *l2_len + *l3_len);
+ *l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+ } else
+ *l4_len = 0;
}
/* modify the IPv4 or IPv4 source address of a packet */
* depending on the testpmd command line configuration */
static uint64_t
process_inner_cksums(void *l3_hdr, uint16_t ethertype, uint16_t l3_len,
- uint8_t l4_proto, uint16_t testpmd_ol_flags)
+ uint8_t l4_proto, uint16_t tso_segsz, uint16_t testpmd_ol_flags)
{
struct ipv4_hdr *ipv4_hdr = l3_hdr;
struct udp_hdr *udp_hdr;
ipv4_hdr = l3_hdr;
ipv4_hdr->hdr_checksum = 0;
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM)
- ol_flags |= PKT_TX_IP_CKSUM;
- else
- ipv4_hdr->hdr_checksum = get_ipv4_cksum(ipv4_hdr);
-
ol_flags |= PKT_TX_IPV4;
+ if (tso_segsz != 0 && l4_proto == IPPROTO_TCP) {
+ ol_flags |= PKT_TX_IP_CKSUM;
+ } else {
+ if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_IP_CKSUM)
+ ol_flags |= PKT_TX_IP_CKSUM;
+ else
+ ipv4_hdr->hdr_checksum =
+ rte_ipv4_cksum(ipv4_hdr);
+ }
} else if (ethertype == _htons(ETHER_TYPE_IPv6))
ol_flags |= PKT_TX_IPV6;
else
if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM) {
ol_flags |= PKT_TX_UDP_CKSUM;
udp_hdr->dgram_cksum = get_psd_sum(l3_hdr,
- ethertype);
+ ethertype, ol_flags);
} else {
udp_hdr->dgram_cksum =
get_udptcp_checksum(l3_hdr, udp_hdr,
} else if (l4_proto == IPPROTO_TCP) {
tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + l3_len);
tcp_hdr->cksum = 0;
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
+ if (tso_segsz != 0) {
+ ol_flags |= PKT_TX_TCP_SEG;
+ tcp_hdr->cksum = get_psd_sum(l3_hdr, ethertype, ol_flags);
+ } else if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
ol_flags |= PKT_TX_TCP_CKSUM;
- tcp_hdr->cksum = get_psd_sum(l3_hdr, ethertype);
+ tcp_hdr->cksum = get_psd_sum(l3_hdr, ethertype, ol_flags);
} else {
tcp_hdr->cksum =
get_udptcp_checksum(l3_hdr, tcp_hdr, ethertype);
struct udp_hdr *udp_hdr;
uint64_t ol_flags = 0;
- if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM)
- ol_flags |= PKT_TX_VXLAN_CKSUM;
-
if (outer_ethertype == _htons(ETHER_TYPE_IPv4)) {
ipv4_hdr->hdr_checksum = 0;
+ ol_flags |= PKT_TX_OUTER_IPV4;
- if ((testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM) == 0)
- ipv4_hdr->hdr_checksum = get_ipv4_cksum(ipv4_hdr);
- }
+ if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_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_VXLAN_CKSUM)
+ ol_flags |= PKT_TX_OUTER_IPV6;
udp_hdr = (struct udp_hdr *)((char *)outer_l3_hdr + outer_l3_len);
/* 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_VXLAN_CKSUM) == 0) {
- if (outer_ethertype == _htons(ETHER_TYPE_IPv4))
- udp_hdr->dgram_cksum =
- get_ipv4_udptcp_checksum(ipv4_hdr,
- (uint16_t *)udp_hdr);
- else
- udp_hdr->dgram_cksum =
- get_ipv6_udptcp_checksum(ipv6_hdr,
- (uint16_t *)udp_hdr);
- }
+ if (outer_ethertype == _htons(ETHER_TYPE_IPv4))
+ udp_hdr->dgram_cksum =
+ rte_ipv4_udptcp_cksum(ipv4_hdr, udp_hdr);
+ else
+ udp_hdr->dgram_cksum =
+ rte_ipv6_udptcp_cksum(ipv6_hdr, udp_hdr);
}
return ol_flags;
* - 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
+ * segmentation offload (this implies HW TCP checksum)
* Then transmit packets on the output port.
*
* (1) Supported packets are:
* TESTPMD_TX_OFFLOAD_* in ports[tx_port].tx_ol_flags. They control
* wether a checksum must be calculated in software or in hardware. The
* IP, UDP, TCP and SCTP flags always concern the inner layer. The
- * VxLAN flag concerns the outer IP and UDP layer (if packet is
- * recognized as a vxlan packet).
+ * VxLAN flag concerns the outer IP (if packet is recognized as a vxlan packet).
*/
static void
pkt_burst_checksum_forward(struct fwd_stream *fs)
uint16_t i;
uint64_t ol_flags;
uint16_t testpmd_ol_flags;
- uint8_t l4_proto;
+ uint8_t l4_proto, l4_tun_len = 0;
uint16_t ethertype = 0, outer_ethertype = 0;
- uint16_t l2_len = 0, l3_len = 0, outer_l2_len = 0, outer_l3_len = 0;
+ uint16_t l2_len = 0, l3_len = 0, l4_len = 0;
+ uint16_t outer_l2_len = 0, outer_l3_len = 0;
+ uint16_t tso_segsz;
int tunnel = 0;
uint32_t rx_bad_ip_csum;
uint32_t rx_bad_l4_csum;
txp = &ports[fs->tx_port];
testpmd_ol_flags = txp->tx_ol_flags;
+ tso_segsz = txp->tso_segsz;
for (i = 0; i < nb_rx; i++) {
ol_flags = 0;
tunnel = 0;
+ l4_tun_len = 0;
m = pkts_burst[i];
/* Update the L3/L4 checksum error packet statistics */
* and inner headers */
eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
- parse_ethernet(eth_hdr, ðertype, &l2_len, &l3_len, &l4_proto);
+ parse_ethernet(eth_hdr, ðertype, &l2_len, &l3_len,
+ &l4_proto, &l4_len);
l3_hdr = (char *)eth_hdr + l2_len;
/* check if it's a supported tunnel (only vxlan for now) */
if (l4_proto == IPPROTO_UDP) {
udp_hdr = (struct udp_hdr *)((char *)l3_hdr + l3_len);
+ /* check udp destination port, 4789 is the default
+ * vxlan port (rfc7348) */
+ if (udp_hdr->dst_port == _htons(4789)) {
+ l4_tun_len = ETHER_VXLAN_HLEN;
+ tunnel = 1;
+
/* currently, this flag is set by i40e only if the
* packet is vxlan */
- if (((m->ol_flags & PKT_RX_TUNNEL_IPV4_HDR) ||
- (m->ol_flags & PKT_RX_TUNNEL_IPV6_HDR)))
- tunnel = 1;
- /* else check udp destination port, 4789 is the default
- * vxlan port (rfc7348) */
- else if (udp_hdr->dst_port == _htons(4789))
+ } else if (m->ol_flags & (PKT_RX_TUNNEL_IPV4_HDR |
+ PKT_RX_TUNNEL_IPV6_HDR))
tunnel = 1;
if (tunnel == 1) {
sizeof(struct vxlan_hdr));
parse_ethernet(eth_hdr, ðertype, &l2_len,
- &l3_len, &l4_proto);
+ &l3_len, &l4_proto, &l4_len);
l3_hdr = (char *)eth_hdr + l2_len;
}
}
/* step 3: depending on user command line configuration,
* recompute checksum either in software or flag the
- * mbuf to offload the calculation to the NIC */
+ * 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, ethertype,
- l3_len, l4_proto, testpmd_ol_flags);
+ l3_len, l4_proto, tso_segsz, testpmd_ol_flags);
/* Then process outer headers if any. Note that the software
* checksum will be wrong if one of the inner checksums is
if (tunnel == 1) {
if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM) {
- m->l2_len = outer_l2_len;
- m->l3_len = outer_l3_len;
- m->inner_l2_len = l2_len;
- m->inner_l3_len = l3_len;
+ m->outer_l2_len = outer_l2_len;
+ m->outer_l3_len = outer_l3_len;
+ m->l2_len = l4_tun_len + l2_len;
+ m->l3_len = l3_len;
}
else {
/* if we don't do vxlan cksum in hw,
sizeof(struct udp_hdr) +
sizeof(struct vxlan_hdr) + l2_len;
m->l3_len = l3_len;
+ m->l4_len = l4_len;
}
} else {
/* this is only useful if an offload flag is
* case */
m->l2_len = l2_len;
m->l3_len = l3_len;
+ m->l4_len = l4_len;
}
+ m->tso_segsz = 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;
+
+ printf("-----------------\n");
+ /* dump rx parsed packet info */
+ printf("rx: l2_len=%d ethertype=%x l3_len=%d "
+ "l4_proto=%d l4_len=%d\n",
+ l2_len, rte_be_to_cpu_16(ethertype),
+ l3_len, l4_proto, l4_len);
+ if (tunnel == 1)
+ printf("rx: outer_l2_len=%d outer_ethertype=%x "
+ "outer_l3_len=%d\n", outer_l2_len,
+ rte_be_to_cpu_16(outer_ethertype),
+ 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)) ||
+ 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 ((tunnel == 1) &&
+ (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_VXLAN_CKSUM))
+ printf("tx: m->outer_l2_len=%d m->outer_l3_len=%d\n",
+ m->outer_l2_len, m->outer_l3_len);
+ if (tso_segsz != 0)
+ 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);
+ }
+ printf("\n");
+ }
}
nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
fs->tx_packets += nb_tx;
git.droids-corp.org / dpdk.git / blobdiff