mb0 = rxp[0];
mb1 = rxp[1];
- /* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
- RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_physaddr) !=
+ /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
offsetof(struct rte_mbuf, buf_addr) + 8);
vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
mb2 = rxp[2];
mb3 = rxp[3];
- /* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
- RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_physaddr) !=
+ /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
offsetof(struct rte_mbuf, buf_addr) + 8);
vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
*/
const __m256i l3_l4_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
/* shift right 1 bit to make sure it not exceed 255 */
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_OUTER_IP_CKSUM_BAD |
PKT_RX_L4_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_OUTER_IP_CKSUM_BAD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
PKT_RX_IP_CKSUM_BAD >> 1,
(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1,
/* second 128-bits */
0, 0, 0, 0, 0, 0, 0, 0,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_OUTER_IP_CKSUM_BAD |
PKT_RX_L4_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_OUTER_IP_CKSUM_BAD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
PKT_RX_IP_CKSUM_BAD >> 1,
const __m256i cksum_mask =
_mm256_set1_epi32(PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
- PKT_RX_EIP_CKSUM_BAD);
+ PKT_RX_OUTER_IP_CKSUM_BAD);
RTE_SET_USED(avx_aligned); /* for 32B descriptors we don't use this */
_mm256_set_epi8
(/* first descriptor */
0xFF, 0xFF,
- 0xFF, 0xFF, /* rss not supported */
+ 0xFF, 0xFF, /* rss hash parsed separately */
11, 10, /* octet 10~11, 16 bits vlan_macip */
5, 4, /* octet 4~5, 16 bits data_len */
0xFF, 0xFF, /* skip hi 16 bits pkt_len, zero out */
0xFF, 0xFF, /*pkt_type set as unknown */
/* second descriptor */
0xFF, 0xFF,
- 0xFF, 0xFF, /* rss not supported */
+ 0xFF, 0xFF, /* rss hash parsed separately */
11, 10, /* octet 10~11, 16 bits vlan_macip */
5, 4, /* octet 4~5, 16 bits data_len */
0xFF, 0xFF, /* skip hi 16 bits pkt_len, zero out */
*/
const __m256i l3_l4_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
/* shift right 1 bit to make sure it not exceed 255 */
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_GOOD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
PKT_RX_IP_CKSUM_GOOD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
(PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
/* second 128-bits */
0, 0, 0, 0, 0, 0, 0, 0,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_GOOD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
PKT_RX_IP_CKSUM_GOOD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
const __m256i cksum_mask =
_mm256_set1_epi32(PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
- PKT_RX_EIP_CKSUM_BAD);
+ PKT_RX_OUTER_IP_CKSUM_BAD);
/**
* data to be shuffled by result of flag mask, shifted down 12.
* If RSS(bit12)/VLAN(bit13) are set,
* shuffle moves appropriate flags in place.
*/
- const __m256i rss_vlan_flags_shuf = _mm256_set_epi8(0, 0, 0, 0,
+ const __m256i rss_flags_shuf = _mm256_set_epi8(0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
- PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
- PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_RSS_HASH, 0,
PKT_RX_RSS_HASH, 0,
/* end up 128-bits */
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
- PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
- PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_RSS_HASH, 0,
PKT_RX_RSS_HASH, 0);
+ const __m256i vlan_flags_shuf = _mm256_set_epi8(0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ 0, 0,
+ /* end up 128-bits */
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ 0, 0);
+
uint16_t i, received;
for (i = 0, received = 0; i < nb_pkts;
_mm256_srli_epi32(flag_bits, 4));
l3_l4_flags = _mm256_slli_epi32(l3_l4_flags, 1);
l3_l4_flags = _mm256_and_si256(l3_l4_flags, cksum_mask);
+
/* set rss and vlan flags */
const __m256i rss_vlan_flag_bits =
_mm256_srli_epi32(flag_bits, 12);
- const __m256i rss_vlan_flags =
- _mm256_shuffle_epi8(rss_vlan_flags_shuf,
+ const __m256i rss_flags =
+ _mm256_shuffle_epi8(rss_flags_shuf,
rss_vlan_flag_bits);
+ __m256i vlan_flags = _mm256_setzero_si256();
+
+ if (rxq->rx_flags == IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG1)
+ vlan_flags =
+ _mm256_shuffle_epi8(vlan_flags_shuf,
+ rss_vlan_flag_bits);
+
+ const __m256i rss_vlan_flags =
+ _mm256_or_si256(rss_flags, vlan_flags);
+
/* merge flags */
__m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
rss_vlan_flags);
_mm256_extract_epi32(fdir_id0_7, 4);
} /* if() on fdir_enabled */
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+ /**
+ * needs to load 2nd 16B of each desc for RSS hash parsing,
+ * will cause performance drop to get into this context.
+ */
+ if (rxq->vsi->adapter->eth_dev->data->dev_conf.rxmode.offloads &
+ DEV_RX_OFFLOAD_RSS_HASH ||
+ rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+ /* load bottom half of every 32B desc */
+ const __m128i raw_desc_bh7 =
+ _mm_load_si128
+ ((void *)(&rxdp[7].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh6 =
+ _mm_load_si128
+ ((void *)(&rxdp[6].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh5 =
+ _mm_load_si128
+ ((void *)(&rxdp[5].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh4 =
+ _mm_load_si128
+ ((void *)(&rxdp[4].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh3 =
+ _mm_load_si128
+ ((void *)(&rxdp[3].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh2 =
+ _mm_load_si128
+ ((void *)(&rxdp[2].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh1 =
+ _mm_load_si128
+ ((void *)(&rxdp[1].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh0 =
+ _mm_load_si128
+ ((void *)(&rxdp[0].wb.status_error1));
+
+ __m256i raw_desc_bh6_7 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh6),
+ raw_desc_bh7, 1);
+ __m256i raw_desc_bh4_5 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh4),
+ raw_desc_bh5, 1);
+ __m256i raw_desc_bh2_3 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh2),
+ raw_desc_bh3, 1);
+ __m256i raw_desc_bh0_1 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh0),
+ raw_desc_bh1, 1);
+
+ if (rxq->vsi->adapter->eth_dev->data->dev_conf.rxmode.offloads &
+ DEV_RX_OFFLOAD_RSS_HASH) {
+ /**
+ * to shift the 32b RSS hash value to the
+ * highest 32b of each 128b before mask
+ */
+ __m256i rss_hash6_7 =
+ _mm256_slli_epi64(raw_desc_bh6_7, 32);
+ __m256i rss_hash4_5 =
+ _mm256_slli_epi64(raw_desc_bh4_5, 32);
+ __m256i rss_hash2_3 =
+ _mm256_slli_epi64(raw_desc_bh2_3, 32);
+ __m256i rss_hash0_1 =
+ _mm256_slli_epi64(raw_desc_bh0_1, 32);
+
+ const __m256i rss_hash_msk =
+ _mm256_set_epi32(0xFFFFFFFF, 0, 0, 0,
+ 0xFFFFFFFF, 0, 0, 0);
+
+ rss_hash6_7 = _mm256_and_si256
+ (rss_hash6_7, rss_hash_msk);
+ rss_hash4_5 = _mm256_and_si256
+ (rss_hash4_5, rss_hash_msk);
+ rss_hash2_3 = _mm256_and_si256
+ (rss_hash2_3, rss_hash_msk);
+ rss_hash0_1 = _mm256_and_si256
+ (rss_hash0_1, rss_hash_msk);
+
+ mb6_7 = _mm256_or_si256(mb6_7, rss_hash6_7);
+ mb4_5 = _mm256_or_si256(mb4_5, rss_hash4_5);
+ mb2_3 = _mm256_or_si256(mb2_3, rss_hash2_3);
+ mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1);
+ }
+
+ if (rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+ /* merge the status/error-1 bits into one register */
+ const __m256i status1_4_7 =
+ _mm256_unpacklo_epi32(raw_desc_bh6_7,
+ raw_desc_bh4_5);
+ const __m256i status1_0_3 =
+ _mm256_unpacklo_epi32(raw_desc_bh2_3,
+ raw_desc_bh0_1);
+
+ const __m256i status1_0_7 =
+ _mm256_unpacklo_epi64(status1_4_7,
+ status1_0_3);
+
+ const __m256i l2tag2p_flag_mask =
+ _mm256_set1_epi32
+ (1 << IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S);
+
+ __m256i l2tag2p_flag_bits =
+ _mm256_and_si256
+ (status1_0_7, l2tag2p_flag_mask);
+
+ l2tag2p_flag_bits =
+ _mm256_srli_epi32(l2tag2p_flag_bits,
+ IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S);
+
+ const __m256i l2tag2_flags_shuf =
+ _mm256_set_epi8(0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ /* end up 128-bits */
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0,
+ PKT_RX_VLAN |
+ PKT_RX_VLAN_STRIPPED,
+ 0);
+
+ vlan_flags =
+ _mm256_shuffle_epi8(l2tag2_flags_shuf,
+ l2tag2p_flag_bits);
+
+ /* merge with vlan_flags */
+ mbuf_flags = _mm256_or_si256
+ (mbuf_flags, vlan_flags);
+
+ /* L2TAG2_2 */
+ __m256i vlan_tci6_7 =
+ _mm256_slli_si256(raw_desc_bh6_7, 4);
+ __m256i vlan_tci4_5 =
+ _mm256_slli_si256(raw_desc_bh4_5, 4);
+ __m256i vlan_tci2_3 =
+ _mm256_slli_si256(raw_desc_bh2_3, 4);
+ __m256i vlan_tci0_1 =
+ _mm256_slli_si256(raw_desc_bh0_1, 4);
+
+ const __m256i vlan_tci_msk =
+ _mm256_set_epi32(0, 0xFFFF0000, 0, 0,
+ 0, 0xFFFF0000, 0, 0);
+
+ vlan_tci6_7 = _mm256_and_si256
+ (vlan_tci6_7, vlan_tci_msk);
+ vlan_tci4_5 = _mm256_and_si256
+ (vlan_tci4_5, vlan_tci_msk);
+ vlan_tci2_3 = _mm256_and_si256
+ (vlan_tci2_3, vlan_tci_msk);
+ vlan_tci0_1 = _mm256_and_si256
+ (vlan_tci0_1, vlan_tci_msk);
+
+ mb6_7 = _mm256_or_si256(mb6_7, vlan_tci6_7);
+ mb4_5 = _mm256_or_si256(mb4_5, vlan_tci4_5);
+ mb2_3 = _mm256_or_si256(mb2_3, vlan_tci2_3);
+ mb0_1 = _mm256_or_si256(mb0_1, vlan_tci0_1);
+ }
+ } /* if() on RSS hash parsing */
+#endif
+
/**
* At this point, we have the 8 sets of flags in the low 16-bits
* of each 32-bit value in vlan0.
((uint64_t)pkt->data_len << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT));
__m128i descriptor = _mm_set_epi64x(high_qw,
- pkt->buf_physaddr + pkt->data_off);
+ pkt->buf_iova + pkt->data_off);
_mm_store_si128((__m128i *)txdp, descriptor);
}
__m256i desc2_3 =
_mm256_set_epi64x
(hi_qw3,
- pkt[3]->buf_physaddr + pkt[3]->data_off,
+ pkt[3]->buf_iova + pkt[3]->data_off,
hi_qw2,
- pkt[2]->buf_physaddr + pkt[2]->data_off);
+ pkt[2]->buf_iova + pkt[2]->data_off);
__m256i desc0_1 =
_mm256_set_epi64x
(hi_qw1,
- pkt[1]->buf_physaddr + pkt[1]->data_off,
+ pkt[1]->buf_iova + pkt[1]->data_off,
hi_qw0,
- pkt[0]->buf_physaddr + pkt[0]->data_off);
+ pkt[0]->buf_iova + pkt[0]->data_off);
_mm256_store_si256((void *)(txdp + 2), desc2_3);
_mm256_store_si256((void *)txdp, desc0_1);
}
git.droids-corp.org / dpdk.git / blobdiff