const unsigned int elts_n = 1 << txq->elts_n;
unsigned int i = 0;
unsigned int j = 0;
+ unsigned int k = 0;
unsigned int max;
uint16_t max_wqe;
unsigned int comp;
uintptr_t addr;
uint64_t naddr;
uint16_t pkt_inline_sz = MLX5_WQE_DWORD_SIZE + 2;
+ uint16_t tso_header_sz = 0;
uint16_t ehdr;
uint8_t cs_flags = 0;
+ uint64_t tso = 0;
#ifdef MLX5_PMD_SOFT_COUNTERS
uint32_t total_length = 0;
#endif
/* Should we enable HW CKSUM offload */
if (buf->ol_flags &
(PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM)) {
- cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
+ const uint64_t is_tunneled = buf->ol_flags &
+ (PKT_TX_TUNNEL_GRE |
+ PKT_TX_TUNNEL_VXLAN);
+
+ if (is_tunneled && txq->tunnel_en) {
+ cs_flags = MLX5_ETH_WQE_L3_INNER_CSUM |
+ MLX5_ETH_WQE_L4_INNER_CSUM;
+ if (buf->ol_flags & PKT_TX_OUTER_IP_CKSUM)
+ cs_flags |= MLX5_ETH_WQE_L3_CSUM;
+ } else {
+ cs_flags = MLX5_ETH_WQE_L3_CSUM |
+ MLX5_ETH_WQE_L4_CSUM;
+ }
}
raw = ((uint8_t *)(uintptr_t)wqe) + 2 * MLX5_WQE_DWORD_SIZE;
/* Replace the Ethernet type by the VLAN if necessary. */
length -= pkt_inline_sz;
addr += pkt_inline_sz;
}
+ if (txq->tso_en) {
+ tso = buf->ol_flags & PKT_TX_TCP_SEG;
+ if (tso) {
+ uintptr_t end = (uintptr_t)
+ (((uintptr_t)txq->wqes) +
+ (1 << txq->wqe_n) *
+ MLX5_WQE_SIZE);
+ unsigned int copy_b;
+ uint8_t vlan_sz = (buf->ol_flags &
+ PKT_TX_VLAN_PKT) ? 4 : 0;
+ const uint64_t is_tunneled =
+ buf->ol_flags &
+ (PKT_TX_TUNNEL_GRE |
+ PKT_TX_TUNNEL_VXLAN);
+
+ tso_header_sz = buf->l2_len + vlan_sz +
+ buf->l3_len + buf->l4_len;
+
+ if (is_tunneled && txq->tunnel_en) {
+ tso_header_sz += buf->outer_l2_len +
+ buf->outer_l3_len;
+ }
+ if (unlikely(tso_header_sz >
+ MLX5_MAX_TSO_HEADER))
+ break;
+ copy_b = tso_header_sz - pkt_inline_sz;
+ /* First seg must contain all headers. */
+ assert(copy_b <= length);
+ raw += MLX5_WQE_DWORD_SIZE;
+ if (copy_b &&
+ ((end - (uintptr_t)raw) > copy_b)) {
+ uint16_t n = (MLX5_WQE_DS(copy_b) -
+ 1 + 3) / 4;
+
+ if (unlikely(max_wqe < n))
+ break;
+ max_wqe -= n;
+ rte_memcpy((void *)raw,
+ (void *)addr, copy_b);
+ addr += copy_b;
+ length -= copy_b;
+ pkt_inline_sz += copy_b;
+ /*
+ * Another DWORD will be added
+ * in the inline part.
+ */
+ raw += MLX5_WQE_DS(copy_b) *
+ MLX5_WQE_DWORD_SIZE -
+ MLX5_WQE_DWORD_SIZE;
+ } else {
+ /* NOP WQE. */
+ wqe->ctrl = (rte_v128u32_t){
+ htonl(txq->wqe_ci << 8),
+ htonl(txq->qp_num_8s | 1),
+ 0,
+ 0,
+ };
+ ds = 1;
+ total_length = 0;
+ pkts--;
+ pkts_n++;
+ elts_head = (elts_head - 1) &
+ (elts_n - 1);
+ k++;
+ goto next_wqe;
+ }
+ }
+ }
/* Inline if enough room. */
- if (txq->max_inline) {
+ if (txq->inline_en || tso) {
uintptr_t end = (uintptr_t)
(((uintptr_t)txq->wqes) +
(1 << txq->wqe_n) * MLX5_WQE_SIZE);
unsigned int max_inline = txq->max_inline *
RTE_CACHE_LINE_SIZE -
- MLX5_WQE_DWORD_SIZE;
+ (pkt_inline_sz - 2);
uintptr_t addr_end = (addr + max_inline) &
~(RTE_CACHE_LINE_SIZE - 1);
unsigned int copy_b = (addr_end > addr) ?
if (unlikely(max_wqe < n))
break;
max_wqe -= n;
+ if (tso) {
+ uint32_t inl =
+ htonl(copy_b | MLX5_INLINE_SEG);
+
+ pkt_inline_sz =
+ MLX5_WQE_DS(tso_header_sz) *
+ MLX5_WQE_DWORD_SIZE;
+ rte_memcpy((void *)raw,
+ (void *)&inl, sizeof(inl));
+ raw += sizeof(inl);
+ pkt_inline_sz += sizeof(inl);
+ }
rte_memcpy((void *)raw, (void *)addr, copy_b);
addr += copy_b;
length -= copy_b;
next_pkt:
++i;
/* Initialize known and common part of the WQE structure. */
- wqe->ctrl = (rte_v128u32_t){
- htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND),
- htonl(txq->qp_num_8s | ds),
- 0,
- 0,
- };
- wqe->eseg = (rte_v128u32_t){
- 0,
- cs_flags,
- 0,
- (ehdr << 16) | htons(pkt_inline_sz),
- };
+ if (tso) {
+ wqe->ctrl = (rte_v128u32_t){
+ htonl((txq->wqe_ci << 8) | MLX5_OPCODE_TSO),
+ htonl(txq->qp_num_8s | ds),
+ 0,
+ 0,
+ };
+ wqe->eseg = (rte_v128u32_t){
+ 0,
+ cs_flags | (htons(buf->tso_segsz) << 16),
+ 0,
+ (ehdr << 16) | htons(tso_header_sz),
+ };
+ } else {
+ wqe->ctrl = (rte_v128u32_t){
+ htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND),
+ htonl(txq->qp_num_8s | ds),
+ 0,
+ 0,
+ };
+ wqe->eseg = (rte_v128u32_t){
+ 0,
+ cs_flags,
+ 0,
+ (ehdr << 16) | htons(pkt_inline_sz),
+ };
+ }
+next_wqe:
txq->wqe_ci += (ds + 3) / 4;
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Increment sent bytes counter. */
#endif
} while (pkts_n);
/* Take a shortcut if nothing must be sent. */
- if (unlikely(i == 0))
+ if (unlikely((i + k) == 0))
return 0;
/* Check whether completion threshold has been reached. */
- comp = txq->elts_comp + i + j;
+ comp = txq->elts_comp + i + j + k;
if (comp >= MLX5_TX_COMP_THRESH) {
volatile struct mlx5_wqe_ctrl *w =
(volatile struct mlx5_wqe_ctrl *)wqe;
pkt->hash.rss = rss_hash_res;
pkt->ol_flags = PKT_RX_RSS_HASH;
}
- if (rxq->mark &&
- ((cqe->sop_drop_qpn !=
- htonl(MLX5_FLOW_MARK_INVALID)) &&
- (cqe->sop_drop_qpn !=
- htonl(MLX5_FLOW_MARK_DEFAULT)))) {
- pkt->hash.fdir.hi =
- mlx5_flow_mark_get(cqe->sop_drop_qpn);
- pkt->ol_flags &= ~PKT_RX_RSS_HASH;
- pkt->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
+ if (rxq->mark && (cqe->sop_drop_qpn !=
+ htonl(MLX5_FLOW_MARK_INVALID))) {
+ pkt->ol_flags |= PKT_RX_FDIR;
+ if (cqe->sop_drop_qpn !=
+ htonl(MLX5_FLOW_MARK_DEFAULT)) {
+ uint32_t mark = cqe->sop_drop_qpn;
+
+ pkt->ol_flags |= PKT_RX_FDIR_ID;
+ pkt->hash.fdir.hi =
+ mlx5_flow_mark_get(mark);
+ }
}
if (rxq->csum | rxq->csum_l2tun | rxq->vlan_strip |
rxq->crc_present) {
git.droids-corp.org / dpdk.git / blobdiff