#include "ixgbe_ethdev.h"
#include "ixgbe_rxtx.h"
-#include <nmmintrin.h>
+#include <tmmintrin.h>
#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wcast-qual"
#endif
-static struct rte_mbuf mb_def = {
-
- .ol_flags = 0,
- {
- .pkt = {
- .data_len = 0,
- .pkt_len = 0,
-
- .vlan_macip = {
- .data = 0,
- },
- .hash = {
- .rss = 0,
- },
-
- .nb_segs = 1,
- .in_port = 0,
-
- .next = NULL,
- .data = NULL,
- },
- },
-};
-
static inline void
ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
{
volatile union ixgbe_adv_rx_desc *rxdp;
struct igb_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
struct rte_mbuf *mb0, *mb1;
- __m128i def_low;
__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
RTE_PKTMBUF_HEADROOM);
rxdp = rxq->rx_ring + rxq->rxrearm_start;
- def_low = _mm_load_si128((__m128i *)&(mb_def.pkt));
-
/* Initialize the mbufs in vector, process 2 mbufs in one loop */
for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
__m128i dma_addr0, dma_addr1;
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
+ /* flush mbuf with pkt template */
+ mb0->rearm_data[0] = rxq->mbuf_initializer;
+ mb1->rearm_data[0] = rxq->mbuf_initializer;
+
/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
vaddr1 = _mm_loadu_si128((__m128i *)&(mb1->buf_addr));
- /* calc va/pa of pkt data point */
- vaddr0 = _mm_add_epi64(vaddr0, hdr_room);
- vaddr1 = _mm_add_epi64(vaddr1, hdr_room);
-
/* convert pa to dma_addr hdr/data */
dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
- /* fill va into t0 def pkt template */
- vaddr0 = _mm_unpacklo_epi64(def_low, vaddr0);
- vaddr1 = _mm_unpacklo_epi64(def_low, vaddr1);
+ /* add headroom to pa values */
+ dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
+ dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
/* flush desc with pa dma_addr */
_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
-
- /* flush mbuf with pkt template */
- _mm_store_si128((__m128i *)&mb0->pkt, vaddr0);
- _mm_store_si128((__m128i *)&mb1->pkt, vaddr1);
-
- /* update refcnt per pkt */
- rte_mbuf_refcnt_set(mb0, 1);
- rte_mbuf_refcnt_set(mb1, 1);
}
rxq->rxrearm_start += RTE_IXGBE_RXQ_REARM_THRESH;
* gives improved performance, at the cost of losing the offload info
* in the received packet
*/
-#ifndef RTE_IXGBE_RX_OLFLAGS_DISABLE
+#ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
#define OLFLAGS_MASK ((uint16_t)(PKT_RX_VLAN_PKT | PKT_RX_IPV4_HDR |\
PKT_RX_IPV4_HDR_EXT | PKT_RX_IPV6_HDR |\
int pos;
uint64_t var;
__m128i shuf_msk;
- __m128i in_port;
+ __m128i crc_adjust = _mm_set_epi16(
+ 0, 0, 0, 0, /* ignore non-length fields */
+ 0, /* ignore high-16bits of pkt_len */
+ -rxq->crc_len, /* sub crc on pkt_len */
+ -rxq->crc_len, /* sub crc on data_len */
+ 0 /* ignore pkt_type field */
+ );
__m128i dd_check;
if (unlikely(nb_pkts < RTE_IXGBE_VPMD_RX_BURST))
15, 14, /* octet 14~15, low 16 bits vlan_macip */
0xFF, 0xFF, /* skip high 16 bits pkt_len, zero out */
13, 12, /* octet 12~13, low 16 bits pkt_len */
- 0xFF, 0xFF, /* skip nb_segs and in_port, zero out */
- 13, 12 /* octet 12~13, 16 bits data_len */
+ 13, 12, /* octet 12~13, 16 bits data_len */
+ 0xFF, 0xFF /* skip pkt_type field */
);
* the next 'n' mbufs into the cache */
sw_ring = &rxq->sw_ring[rxq->rx_tail];
- /* in_port, nb_seg = 1, crc_len */
- in_port = rxq->misc_info;
-
/*
* A. load 4 packet in one loop
* B. copy 4 mbuf point from swring to rx_pkts
descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
/* B.2 copy 2 mbuf point into rx_pkts */
- _mm_store_si128((__m128i *)&rx_pkts[pos], mbp1);
+ _mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);
/* B.1 load 1 mbuf point */
mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]);
descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
/* B.2 copy 2 mbuf point into rx_pkts */
- _mm_store_si128((__m128i *)&rx_pkts[pos+2], mbp2);
+ _mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
/* avoid compiler reorder optimization */
rte_compiler_barrier();
desc_to_olflags_v(descs, &rx_pkts[pos]);
/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
- pkt_mb4 = _mm_add_epi16(pkt_mb4, in_port);
- pkt_mb3 = _mm_add_epi16(pkt_mb3, in_port);
+ pkt_mb4 = _mm_add_epi16(pkt_mb4, crc_adjust);
+ pkt_mb3 = _mm_add_epi16(pkt_mb3, crc_adjust);
/* D.1 pkt 1,2 convert format from desc to pktmbuf */
pkt_mb2 = _mm_shuffle_epi8(descs[1], shuf_msk);
staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);
/* D.3 copy final 3,4 data to rx_pkts */
- _mm_storeu_si128((__m128i *)&(rx_pkts[pos+3]->pkt.data_len),
+ _mm_storeu_si128((void *)&rx_pkts[pos+3]->rx_descriptor_fields1,
pkt_mb4);
- _mm_storeu_si128((__m128i *)&(rx_pkts[pos+2]->pkt.data_len),
+ _mm_storeu_si128((void *)&rx_pkts[pos+2]->rx_descriptor_fields1,
pkt_mb3);
/* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
- pkt_mb2 = _mm_add_epi16(pkt_mb2, in_port);
- pkt_mb1 = _mm_add_epi16(pkt_mb1, in_port);
+ pkt_mb2 = _mm_add_epi16(pkt_mb2, crc_adjust);
+ pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);
/* C.3 calc avaialbe number of desc */
staterr = _mm_and_si128(staterr, dd_check);
staterr = _mm_packs_epi32(staterr, zero);
/* D.3 copy final 1,2 data to rx_pkts */
- _mm_storeu_si128((__m128i *)&(rx_pkts[pos+1]->pkt.data_len),
+ _mm_storeu_si128((void *)&rx_pkts[pos+1]->rx_descriptor_fields1,
pkt_mb2);
- _mm_storeu_si128((__m128i *)&(rx_pkts[pos]->pkt.data_len),
+ _mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
pkt_mb1);
/* C.4 calc avaialbe number of desc */
- var = _mm_popcnt_u64(_mm_cvtsi128_si64(staterr));
+ var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
nb_pkts_recd += var;
if (likely(var != RTE_IXGBE_DESCS_PER_LOOP))
break;
return nb_pkts_recd;
}
-
static inline void
vtx1(volatile union ixgbe_adv_tx_desc *txdp,
- struct rte_mbuf *pkt, __m128i flags)
+ struct rte_mbuf *pkt, uint64_t flags)
{
- __m128i t0, t1, offset, ols, ba, ctl;
-
- /* load buf_addr/buf_physaddr in t0 */
- t0 = _mm_loadu_si128((__m128i *)&(pkt->buf_addr));
- /* load data, ... pkt_len in t1 */
- t1 = _mm_loadu_si128((__m128i *)&(pkt->pkt.data));
-
- /* calc offset = (data - buf_adr) */
- offset = _mm_sub_epi64(t1, t0);
-
- /* cmd_type_len: pkt_len |= DCMD_DTYP_FLAGS */
- ctl = _mm_or_si128(t1, flags);
-
- /* reorder as buf_physaddr/buf_addr */
- offset = _mm_shuffle_epi32(offset, 0x4E);
-
- /* olinfo_stats: pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT */
- ols = _mm_slli_epi32(t1, IXGBE_ADVTXD_PAYLEN_SHIFT);
-
- /* buffer_addr = buf_physaddr + offset */
- ba = _mm_add_epi64(t0, offset);
-
- /* format cmd_type_len/olinfo_status */
- ctl = _mm_unpackhi_epi32(ctl, ols);
-
- /* format buf_physaddr/cmd_type_len */
- ba = _mm_unpackhi_epi64(ba, ctl);
-
- /* write desc */
- _mm_store_si128((__m128i *)&txdp->read, ba);
+ __m128i descriptor = _mm_set_epi64x((uint64_t)pkt->pkt_len << 46 |
+ flags | pkt->data_len,
+ pkt->buf_physaddr + pkt->data_off);
+ _mm_store_si128((__m128i *)&txdp->read, descriptor);
}
static inline void
vtx(volatile union ixgbe_adv_tx_desc *txdp,
- struct rte_mbuf **pkt, uint16_t nb_pkts, __m128i flags)
+ struct rte_mbuf **pkt, uint16_t nb_pkts, uint64_t flags)
{
int i;
for (i = 0; i < nb_pkts; ++i, ++txdp, ++pkt)
struct igb_tx_entry_seq *txsp;
uint32_t status;
uint32_t n, k;
-#ifdef RTE_MBUF_SCATTER_GATHER
+#ifdef RTE_MBUF_REFCNT
uint32_t i;
int nb_free = 0;
struct rte_mbuf *m, *free[RTE_IXGBE_TX_MAX_FREE_BUF_SZ];
while (n > 0) {
k = RTE_MIN(n, txsp[n-1].same_pool);
-#ifdef RTE_MBUF_SCATTER_GATHER
+#ifdef RTE_MBUF_REFCNT
for (i = 0; i < k; i++) {
m = __rte_pktmbuf_prefree_seg((txep+n-k+i)->mbuf);
if (m != NULL)
struct igb_tx_entry_v *txep;
struct igb_tx_entry_seq *txsp;
uint16_t n, nb_commit, tx_id;
- __m128i flags = _mm_set_epi32(DCMD_DTYP_FLAGS, 0, 0, 0);
- __m128i rs = _mm_set_epi32(IXGBE_ADVTXD_DCMD_RS|DCMD_DTYP_FLAGS,
- 0, 0, 0);
+ uint64_t flags = DCMD_DTYP_FLAGS;
+ uint64_t rs = IXGBE_ADVTXD_DCMD_RS|DCMD_DTYP_FLAGS;
int i;
if (unlikely(nb_pkts > RTE_IXGBE_VPMD_TX_BURST))
.reset = ixgbe_reset_tx_queue,
};
+int
+ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq)
+{
+ static struct rte_mbuf mb_def = {
+ .nb_segs = 1,
+ .data_off = RTE_PKTMBUF_HEADROOM,
+#ifdef RTE_MBUF_REFCNT
+ .refcnt = 1,
+#endif
+ };
+
+ mb_def.buf_len = rxq->mb_pool->elt_size - sizeof(struct rte_mbuf);
+ mb_def.port = rxq->port_id;
+ rxq->mbuf_initializer = *((uint64_t *)&mb_def.rearm_data);
+ return 0;
+}
+
int ixgbe_txq_vec_setup(struct igb_tx_queue *txq,
unsigned int socket_id)
{
return 0;
}
-int ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq,
- __rte_unused unsigned int socket_id)
-{
- rxq->misc_info =
- _mm_set_epi16(
- 0, 0, 0, 0, 0,
- (uint16_t)-rxq->crc_len, /* sub crc on pkt_len */
- (uint16_t)(rxq->port_id << 8 | 1),
- /* 8b port_id and 8b nb_seg*/
- (uint16_t)-rxq->crc_len /* sub crc on data_len */
- );
-
- return 0;
-}
-
int ixgbe_rx_vec_condition_check(struct rte_eth_dev *dev)
{
#ifndef RTE_LIBRTE_IEEE1588
struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
struct rte_fdir_conf *fconf = &dev->data->dev_conf.fdir_conf;
-#ifdef RTE_IXGBE_RX_OLFLAGS_DISABLE
+#ifndef RTE_IXGBE_RX_OLFLAGS_ENABLE
/* whithout rx ol_flags, no VP flag report */
if (rxmode->hw_vlan_strip != 0 ||
rxmode->hw_vlan_extend != 0)
return 0;
#else
+ RTE_SET_USED(dev);
return -1;
#endif
}
git.droids-corp.org / dpdk.git / blobdiff