#include "mlx5_defs.h"
#include "mlx5_prm.h"
-static inline int
+static __rte_always_inline int
check_cqe(volatile struct mlx5_cqe *cqe,
- unsigned int cqes_n, const uint16_t ci)
- __attribute__((always_inline));
+ unsigned int cqes_n, const uint16_t ci);
-static inline void
-txq_complete(struct txq *txq) __attribute__((always_inline));
+static __rte_always_inline void
+txq_complete(struct txq *txq);
-static inline uint32_t
-txq_mp2mr(struct txq *txq, struct rte_mempool *mp)
- __attribute__((always_inline));
+static __rte_always_inline uint32_t
+txq_mp2mr(struct txq *txq, struct rte_mempool *mp);
-static inline void
-mlx5_tx_dbrec(struct txq *txq, volatile struct mlx5_wqe *wqe)
- __attribute__((always_inline));
+static __rte_always_inline void
+mlx5_tx_dbrec(struct txq *txq, volatile struct mlx5_wqe *wqe);
-static inline uint32_t
-rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe)
- __attribute__((always_inline));
+static __rte_always_inline uint32_t
+rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe);
-static inline int
+static __rte_always_inline int
mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe *cqe,
- uint16_t cqe_cnt, uint32_t *rss_hash)
- __attribute__((always_inline));
+ uint16_t cqe_cnt, uint32_t *rss_hash);
-static inline uint32_t
-rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe *cqe)
- __attribute__((always_inline));
+static __rte_always_inline uint32_t
+rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe *cqe);
#ifndef NDEBUG
unsigned int j = 0;
unsigned int k = 0;
unsigned int max;
+ unsigned int max_inline = txq->max_inline;
+ const unsigned int inline_en = !!max_inline && txq->inline_en;
uint16_t max_wqe;
unsigned int comp;
volatile struct mlx5_wqe_v *wqe = NULL;
+ volatile struct mlx5_wqe_ctrl *last_wqe = NULL;
unsigned int segs_n = 0;
struct rte_mbuf *buf = NULL;
uint8_t *raw;
volatile rte_v128u32_t *dseg = NULL;
uint32_t length;
unsigned int ds = 0;
+ unsigned int sg = 0; /* counter of additional segs attached. */
uintptr_t addr;
uint64_t naddr;
uint16_t pkt_inline_sz = MLX5_WQE_DWORD_SIZE + 2;
#endif
/* first_seg */
- buf = *(pkts++);
+ buf = *pkts;
segs_n = buf->nb_segs;
/*
* Make sure there is enough room to store this packet and
break;
max -= segs_n;
--segs_n;
- if (!segs_n)
- --pkts_n;
if (unlikely(--max_wqe == 0))
break;
wqe = (volatile struct mlx5_wqe_v *)
tx_mlx5_wqe(txq, txq->wqe_ci);
rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
- if (pkts_n > 1)
- rte_prefetch0(*pkts);
+ if (pkts_n - i > 1)
+ rte_prefetch0(*(pkts + 1));
addr = rte_pktmbuf_mtod(buf, uintptr_t);
length = DATA_LEN(buf);
ehdr = (((uint8_t *)addr)[1] << 8) |
break;
/* Update element. */
(*txq->elts)[elts_head] = buf;
- elts_head = (elts_head + 1) & (elts_n - 1);
/* Prefetch next buffer data. */
- if (pkts_n > 1) {
- volatile void *pkt_addr;
-
- pkt_addr = rte_pktmbuf_mtod(*pkts, volatile void *);
- rte_prefetch0(pkt_addr);
- }
+ if (pkts_n - i > 1)
+ rte_prefetch0(
+ rte_pktmbuf_mtod(*(pkts + 1), volatile void *));
/* Should we enable HW CKSUM offload */
if (buf->ol_flags &
(PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM)) {
};
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->inline_en || tso) {
+ if (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 -
- (pkt_inline_sz - 2);
- uintptr_t addr_end = (addr + max_inline) &
+ unsigned int inline_room = max_inline *
+ RTE_CACHE_LINE_SIZE -
+ (pkt_inline_sz - 2);
+ uintptr_t addr_end = (addr + inline_room) &
~(RTE_CACHE_LINE_SIZE - 1);
unsigned int copy_b = (addr_end > addr) ?
RTE_MIN((addr_end - addr), length) :
naddr,
naddr >> 32,
};
- (*txq->elts)[elts_head] = buf;
elts_head = (elts_head + 1) & (elts_n - 1);
- ++j;
- --segs_n;
- if (segs_n)
+ (*txq->elts)[elts_head] = buf;
+ ++sg;
+ /* Advance counter only if all segs are successfully posted. */
+ if (sg < segs_n)
goto next_seg;
else
- --pkts_n;
+ j += sg;
next_pkt:
+ elts_head = (elts_head + 1) & (elts_n - 1);
+ ++pkts;
++i;
/* Initialize known and common part of the WQE structure. */
if (tso) {
}
next_wqe:
txq->wqe_ci += (ds + 3) / 4;
+ /* Save the last successful WQE for completion request */
+ last_wqe = (volatile struct mlx5_wqe_ctrl *)wqe;
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Increment sent bytes counter. */
txq->stats.obytes += total_length;
#endif
- } while (pkts_n);
+ } while (i < pkts_n);
/* Take a shortcut if nothing must be sent. */
if (unlikely((i + k) == 0))
return 0;
+ txq->elts_head = (txq->elts_head + i + j) & (elts_n - 1);
/* Check whether completion threshold has been reached. */
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;
-
/* Request completion on last WQE. */
- w->ctrl2 = htonl(8);
+ last_wqe->ctrl2 = htonl(8);
/* Save elts_head in unused "immediate" field of WQE. */
- w->ctrl3 = elts_head;
+ last_wqe->ctrl3 = txq->elts_head;
txq->elts_comp = 0;
} else {
txq->elts_comp = comp;
txq->stats.opackets += i;
#endif
/* Ring QP doorbell. */
- mlx5_tx_dbrec(txq, (volatile struct mlx5_wqe *)wqe);
- txq->elts_head = elts_head;
+ mlx5_tx_dbrec(txq, (volatile struct mlx5_wqe *)last_wqe);
return i;
}
&(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
unsigned int i = 0;
unsigned int rq_ci = rxq->rq_ci << sges_n;
- int len; /* keep its value across iterations. */
+ int len = 0; /* keep its value across iterations. */
while (pkts_n) {
unsigned int idx = rq_ci & wqe_cnt;
while (pkt != seg) {
assert(pkt != (*rxq->elts)[idx]);
rep = NEXT(pkt);
- rte_mbuf_refcnt_set(pkt, 0);
+ NEXT(pkt) = NULL;
+ NB_SEGS(pkt) = 1;
rte_mbuf_raw_free(pkt);
pkt = rep;
}
len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt,
&rss_hash_res);
if (!len) {
- rte_mbuf_refcnt_set(rep, 0);
rte_mbuf_raw_free(rep);
break;
}
if (unlikely(len == -1)) {
/* RX error, packet is likely too large. */
- rte_mbuf_refcnt_set(rep, 0);
rte_mbuf_raw_free(rep);
++rxq->stats.idropped;
goto skip;
mlx5_flow_mark_get(mark);
}
}
- if (rxq->csum | rxq->csum_l2tun | rxq->vlan_strip |
- rxq->crc_present) {
- if (rxq->csum) {
- pkt->packet_type =
- rxq_cq_to_pkt_type(cqe);
- pkt->ol_flags |=
- rxq_cq_to_ol_flags(rxq, cqe);
- }
- if (ntohs(cqe->hdr_type_etc) &
- MLX5_CQE_VLAN_STRIPPED) {
- pkt->ol_flags |= PKT_RX_VLAN_PKT |
- PKT_RX_VLAN_STRIPPED;
- pkt->vlan_tci = ntohs(cqe->vlan_info);
- }
- if (rxq->crc_present)
- len -= ETHER_CRC_LEN;
+ if (rxq->csum | rxq->csum_l2tun) {
+ pkt->packet_type = rxq_cq_to_pkt_type(cqe);
+ pkt->ol_flags |= rxq_cq_to_ol_flags(rxq, cqe);
+ }
+ if (rxq->vlan_strip &&
+ (cqe->hdr_type_etc &
+ htons(MLX5_CQE_VLAN_STRIPPED))) {
+ pkt->ol_flags |= PKT_RX_VLAN_PKT |
+ PKT_RX_VLAN_STRIPPED;
+ pkt->vlan_tci = ntohs(cqe->vlan_info);
}
+ if (rxq->crc_present)
+ len -= ETHER_CRC_LEN;
PKT_LEN(pkt) = len;
}
DATA_LEN(rep) = DATA_LEN(seg);