#pragma GCC diagnostic ignored "-Wcast-qual"
#endif
+static inline __m128i
+ice_flex_rxd_to_fdir_flags_vec(const __m128i fdir_id0_3)
+{
+#define FDID_MIS_MAGIC 0xFFFFFFFF
+ RTE_BUILD_BUG_ON(PKT_RX_FDIR != (1 << 2));
+ RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
+ const __m128i pkt_fdir_bit = _mm_set1_epi32(PKT_RX_FDIR |
+ PKT_RX_FDIR_ID);
+ /* desc->flow_id field == 0xFFFFFFFF means fdir mismatch */
+ const __m128i fdir_mis_mask = _mm_set1_epi32(FDID_MIS_MAGIC);
+ __m128i fdir_mask = _mm_cmpeq_epi32(fdir_id0_3,
+ fdir_mis_mask);
+ /* this XOR op results to bit-reverse the fdir_mask */
+ fdir_mask = _mm_xor_si128(fdir_mask, fdir_mis_mask);
+ const __m128i fdir_flags = _mm_and_si128(fdir_mask, pkt_fdir_bit);
+
+ return fdir_flags;
+}
+
static inline void
ice_rxq_rearm(struct ice_rx_queue *rxq)
{
RTE_PKTMBUF_HEADROOM);
__m128i dma_addr0, dma_addr1;
- rxdp = (union ice_rx_flex_desc *)rxq->rx_ring + rxq->rxrearm_start;
+ rxdp = rxq->rx_ring + rxq->rxrearm_start;
/* Pull 'n' more MBUFs into the software ring */
if (rte_mempool_get_bulk(rxq->mp,
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
/* Update the tail pointer on the NIC */
- ICE_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ ICE_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
}
static inline void
* bit12 for RSS indication.
* bit13 for VLAN indication.
*/
- const __m128i desc_mask = _mm_set_epi32(0x3070, 0x3070,
- 0x3070, 0x3070);
-
+ const __m128i desc_mask = _mm_set_epi32(0x30f0, 0x30f0,
+ 0x30f0, 0x30f0);
const __m128i cksum_mask = _mm_set_epi32(PKT_RX_IP_CKSUM_MASK |
PKT_RX_L4_CKSUM_MASK |
+ PKT_RX_OUTER_L4_CKSUM_MASK |
PKT_RX_EIP_CKSUM_BAD,
PKT_RX_IP_CKSUM_MASK |
PKT_RX_L4_CKSUM_MASK |
+ PKT_RX_OUTER_L4_CKSUM_MASK |
PKT_RX_EIP_CKSUM_BAD,
PKT_RX_IP_CKSUM_MASK |
PKT_RX_L4_CKSUM_MASK |
+ PKT_RX_OUTER_L4_CKSUM_MASK |
PKT_RX_EIP_CKSUM_BAD,
PKT_RX_IP_CKSUM_MASK |
PKT_RX_L4_CKSUM_MASK |
+ PKT_RX_OUTER_L4_CKSUM_MASK |
PKT_RX_EIP_CKSUM_BAD);
/* map the checksum, rss and vlan fields to the checksum, rss
* and vlan flag
*/
- const __m128i cksum_flags = _mm_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_IP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_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_IP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_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_BAD) >> 1,
- (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1);
+ const __m128i cksum_flags =
+ _mm_set_epi8((PKT_RX_OUTER_L4_CKSUM_BAD >> 20 |
+ PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ /**
+ * shift right 20 bits to use the low two bits to indicate
+ * outer checksum status
+ * shift right 1 bit to make sure it not exceed 255
+ */
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_EIP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1);
const __m128i rss_vlan_flags = _mm_set_epi8(0, 0, 0, 0,
0, 0, 0, 0,
flags = _mm_unpackhi_epi32(descs[0], descs[1]);
tmp_desc = _mm_unpackhi_epi32(descs[2], descs[3]);
tmp_desc = _mm_unpacklo_epi64(flags, tmp_desc);
- tmp_desc = _mm_and_si128(flags, desc_mask);
+ tmp_desc = _mm_and_si128(tmp_desc, desc_mask);
/* checksum flags */
tmp_desc = _mm_srli_epi32(tmp_desc, 4);
flags = _mm_shuffle_epi8(cksum_flags, tmp_desc);
/* then we shift left 1 bit */
flags = _mm_slli_epi32(flags, 1);
+
+ __m128i l4_outer_mask = _mm_set_epi32(0x6, 0x6, 0x6, 0x6);
+ __m128i l4_outer_flags = _mm_and_si128(flags, l4_outer_mask);
+ l4_outer_flags = _mm_slli_epi32(l4_outer_flags, 20);
+
+ __m128i l3_l4_mask = _mm_set_epi32(~0x6, ~0x6, ~0x6, ~0x6);
+ __m128i l3_l4_flags = _mm_and_si128(flags, l3_l4_mask);
+ flags = _mm_or_si128(l3_l4_flags, l4_outer_flags);
/* we need to mask out the reduntant bits introduced by RSS or
* VLAN fields.
*/
/* merge the flags */
flags = _mm_or_si128(flags, rss_vlan);
+ if (rxq->fdir_enabled) {
+ const __m128i fdir_id0_1 =
+ _mm_unpackhi_epi32(descs[0], descs[1]);
+
+ const __m128i fdir_id2_3 =
+ _mm_unpackhi_epi32(descs[2], descs[3]);
+
+ const __m128i fdir_id0_3 =
+ _mm_unpackhi_epi64(fdir_id0_1, fdir_id2_3);
+
+ const __m128i fdir_flags =
+ ice_flex_rxd_to_fdir_flags_vec(fdir_id0_3);
+
+ /* merge with fdir_flags */
+ flags = _mm_or_si128(flags, fdir_flags);
+
+ /* write fdir_id to mbuf */
+ rx_pkts[0]->hash.fdir.hi =
+ _mm_extract_epi32(fdir_id0_3, 0);
+
+ rx_pkts[1]->hash.fdir.hi =
+ _mm_extract_epi32(fdir_id0_3, 1);
+
+ rx_pkts[2]->hash.fdir.hi =
+ _mm_extract_epi32(fdir_id0_3, 2);
+
+ rx_pkts[3]->hash.fdir.hi =
+ _mm_extract_epi32(fdir_id0_3, 3);
+ } /* if() on fdir_enabled */
+
/**
* At this point, we have the 4 sets of flags in the low 16-bits
* of each 32-bit value in flags.
* appropriate flags means that we have to do a shift and blend for
* each mbuf before we do the write.
*/
- rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(flags, 8), 0x10);
- rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(flags, 4), 0x10);
- rearm2 = _mm_blend_epi16(mbuf_init, flags, 0x10);
- rearm3 = _mm_blend_epi16(mbuf_init, _mm_srli_si128(flags, 4), 0x10);
+ rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(flags, 8), 0x30);
+ rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(flags, 4), 0x30);
+ rearm2 = _mm_blend_epi16(mbuf_init, flags, 0x30);
+ rearm3 = _mm_blend_epi16(mbuf_init, _mm_srli_si128(flags, 4), 0x30);
/* write the rearm data and the olflags in one write */
RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
ice_rx_desc_to_ptype_v(__m128i descs[4], struct rte_mbuf **rx_pkts,
uint32_t *ptype_tbl)
{
- const __m128i ptype_mask = _mm_set_epi16(0, ICE_RX_FLEX_DESC_PTYPE_M,
- 0, ICE_RX_FLEX_DESC_PTYPE_M,
- 0, ICE_RX_FLEX_DESC_PTYPE_M,
- 0, ICE_RX_FLEX_DESC_PTYPE_M);
+ const __m128i ptype_mask = _mm_set_epi16(ICE_RX_FLEX_DESC_PTYPE_M, 0,
+ ICE_RX_FLEX_DESC_PTYPE_M, 0,
+ ICE_RX_FLEX_DESC_PTYPE_M, 0,
+ ICE_RX_FLEX_DESC_PTYPE_M, 0);
__m128i ptype_01 = _mm_unpacklo_epi32(descs[0], descs[1]);
__m128i ptype_23 = _mm_unpacklo_epi32(descs[2], descs[3]);
__m128i ptype_all = _mm_unpacklo_epi64(ptype_01, ptype_23);
}
/**
+ * vPMD raw receive routine, only accept(nb_pkts >= ICE_DESCS_PER_LOOP)
+ *
* Notice:
* - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > ICE_VPMD_RX_BURST, only scan ICE_VPMD_RX_BURST
- * numbers of DD bits
+ * - floor align nb_pkts to a ICE_DESCS_PER_LOOP power-of-two
*/
static inline uint16_t
_ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
const __m128i zero = _mm_setzero_si128();
/* mask to shuffle from desc. to mbuf */
const __m128i shuf_msk = _mm_set_epi8
- (0xFF, 0xFF, 0xFF, 0xFF, /* rss not supported */
+ (0xFF, 0xFF,
+ 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 high 16 bits pkt_len, zero out */
const __m128i eop_check = _mm_set_epi64x(0x0000000200000002LL,
0x0000000200000002LL);
- /* nb_pkts shall be less equal than ICE_MAX_RX_BURST */
- nb_pkts = RTE_MIN(nb_pkts, ICE_MAX_RX_BURST);
-
/* nb_pkts has to be floor-aligned to ICE_DESCS_PER_LOOP */
nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, ICE_DESCS_PER_LOOP);
/* Just the act of getting into the function from the application is
* going to cost about 7 cycles
*/
- rxdp = (union ice_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
+ rxdp = rxq->rx_ring + rxq->rx_tail;
rte_prefetch0(rxdp);
pos += ICE_DESCS_PER_LOOP,
rxdp += ICE_DESCS_PER_LOOP) {
__m128i descs[ICE_DESCS_PER_LOOP];
- __m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+ __m128i pkt_mb0, pkt_mb1, pkt_mb2, pkt_mb3;
__m128i staterr, sterr_tmp1, sterr_tmp2;
/* 2 64 bit or 4 32 bit mbuf pointers in one XMM reg. */
__m128i mbp1;
rte_compiler_barrier();
/* D.1 pkt 3,4 convert format from desc to pktmbuf */
- pkt_mb4 = _mm_shuffle_epi8(descs[3], shuf_msk);
- pkt_mb3 = _mm_shuffle_epi8(descs[2], shuf_msk);
+ pkt_mb3 = _mm_shuffle_epi8(descs[3], shuf_msk);
+ pkt_mb2 = _mm_shuffle_epi8(descs[2], shuf_msk);
+
+ /* D.1 pkt 1,2 convert format from desc to pktmbuf */
+ pkt_mb1 = _mm_shuffle_epi8(descs[1], shuf_msk);
+ pkt_mb0 = _mm_shuffle_epi8(descs[0], shuf_msk);
/* C.1 4=>2 filter staterr info only */
sterr_tmp2 = _mm_unpackhi_epi32(descs[3], descs[2]);
ice_rx_desc_to_olflags_v(rxq, descs, &rx_pkts[pos]);
/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
- pkt_mb4 = _mm_add_epi16(pkt_mb4, crc_adjust);
pkt_mb3 = _mm_add_epi16(pkt_mb3, crc_adjust);
+ pkt_mb2 = _mm_add_epi16(pkt_mb2, crc_adjust);
- /* D.1 pkt 1,2 convert format from desc to pktmbuf */
- pkt_mb2 = _mm_shuffle_epi8(descs[1], shuf_msk);
- pkt_mb1 = _mm_shuffle_epi8(descs[0], shuf_msk);
+ /* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
+ pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);
+ pkt_mb0 = _mm_add_epi16(pkt_mb0, crc_adjust);
+
+#ifndef RTE_LIBRTE_ICE_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) {
+ /* load bottom half of every 32B desc */
+ 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));
+
+ /**
+ * to shift the 32b RSS hash value to the
+ * highest 32b of each 128b before mask
+ */
+ __m128i rss_hash3 =
+ _mm_slli_epi64(raw_desc_bh3, 32);
+ __m128i rss_hash2 =
+ _mm_slli_epi64(raw_desc_bh2, 32);
+ __m128i rss_hash1 =
+ _mm_slli_epi64(raw_desc_bh1, 32);
+ __m128i rss_hash0 =
+ _mm_slli_epi64(raw_desc_bh0, 32);
+
+ __m128i rss_hash_msk =
+ _mm_set_epi32(0xFFFFFFFF, 0, 0, 0);
+
+ rss_hash3 = _mm_and_si128
+ (rss_hash3, rss_hash_msk);
+ rss_hash2 = _mm_and_si128
+ (rss_hash2, rss_hash_msk);
+ rss_hash1 = _mm_and_si128
+ (rss_hash1, rss_hash_msk);
+ rss_hash0 = _mm_and_si128
+ (rss_hash0, rss_hash_msk);
+
+ pkt_mb3 = _mm_or_si128(pkt_mb3, rss_hash3);
+ pkt_mb2 = _mm_or_si128(pkt_mb2, rss_hash2);
+ pkt_mb1 = _mm_or_si128(pkt_mb1, rss_hash1);
+ pkt_mb0 = _mm_or_si128(pkt_mb0, rss_hash0);
+ } /* if() on RSS hash parsing */
+#endif
/* C.2 get 4 pkts staterr value */
staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);
/* D.3 copy final 3,4 data to rx_pkts */
_mm_storeu_si128
((void *)&rx_pkts[pos + 3]->rx_descriptor_fields1,
- pkt_mb4);
+ pkt_mb3);
_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, crc_adjust);
- pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);
+ pkt_mb2);
/* C* extract and record EOP bit */
if (split_packet) {
/* D.3 copy final 1,2 data to rx_pkts */
_mm_storeu_si128
((void *)&rx_pkts[pos + 1]->rx_descriptor_fields1,
- pkt_mb2);
+ pkt_mb1);
_mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
- pkt_mb1);
+ pkt_mb0);
ice_rx_desc_to_ptype_v(descs, &rx_pkts[pos], ptype_tbl);
/* C.4 calc avaialbe number of desc */
var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
return _ice_recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
}
-/* vPMD receive routine that reassembles scattered packets
+/**
+ * vPMD receive routine that reassembles single burst of 32 scattered packets
+ *
* Notice:
* - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > ICE_VPMD_RX_BURST, only scan ICE_VPMD_RX_BURST
- * numbers of DD bits
*/
-uint16_t
-ice_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+static uint16_t
+ice_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
{
struct ice_rx_queue *rxq = rx_queue;
uint8_t split_flags[ICE_VPMD_RX_BURST] = {0};
&split_flags[i]);
}
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+ice_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > ICE_VPMD_RX_BURST) {
+ uint16_t burst;
+
+ burst = ice_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ ICE_VPMD_RX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < ICE_VPMD_RX_BURST)
+ return retval;
+ }
+
+ return retval + ice_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ nb_pkts);
+}
+
static inline void
ice_vtx1(volatile struct ice_tx_desc *txdp, struct rte_mbuf *pkt,
uint64_t flags)
txq->tx_tail = tx_id;
- ICE_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
return nb_pkts;
}
return nb_tx;
}
-int __attribute__((cold))
+int __rte_cold
ice_rxq_vec_setup(struct ice_rx_queue *rxq)
{
if (!rxq)
return ice_rxq_vec_setup_default(rxq);
}
-int __attribute__((cold))
+int __rte_cold
ice_txq_vec_setup(struct ice_tx_queue __rte_unused *txq)
{
if (!txq)
return 0;
}
-int __attribute__((cold))
+int __rte_cold
ice_rx_vec_dev_check(struct rte_eth_dev *dev)
{
return ice_rx_vec_dev_check_default(dev);
}
-int __attribute__((cold))
+int __rte_cold
ice_tx_vec_dev_check(struct rte_eth_dev *dev)
{
return ice_tx_vec_dev_check_default(dev);