*/
#include <stdint.h>
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
#include <rte_malloc.h>
#include "base/i40e_prototype.h"
#include "i40e_rxtx.h"
#include "i40e_rxtx_vec_common.h"
-#include <x86intrin.h>
+#include <rte_vect.h>
#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wcast-qual"
#endif
-static inline void
+static __rte_always_inline void
i40e_rxq_rearm(struct i40e_rx_queue *rxq)
{
- int i;
- uint16_t rx_id;
- volatile union i40e_rx_desc *rxdp;
- struct i40e_rx_entry *rxep = &rxq->sw_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,
- (void *)rxep,
- RTE_I40E_RXQ_REARM_THRESH) < 0) {
- if (rxq->rxrearm_nb + RTE_I40E_RXQ_REARM_THRESH >=
- rxq->nb_rx_desc) {
- __m128i dma_addr0;
- dma_addr0 = _mm_setzero_si128();
- for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) {
- rxep[i].mbuf = &rxq->fake_mbuf;
- _mm_store_si128((__m128i *)&rxdp[i].read,
- dma_addr0);
- }
- }
- rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
- RTE_I40E_RXQ_REARM_THRESH;
- return;
- }
-
-#ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
- struct rte_mbuf *mb0, *mb1;
- __m128i dma_addr0, dma_addr1;
- __m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
- RTE_PKTMBUF_HEADROOM);
- /* Initialize the mbufs in vector, process 2 mbufs in one loop */
- for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; i += 2, rxep += 2) {
- __m128i vaddr0, vaddr1;
-
- mb0 = rxep[0].mbuf;
- mb1 = rxep[1].mbuf;
-
- /* 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);
-
- /* convert pa to dma_addr hdr/data */
- dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
- dma_addr1 = _mm_unpackhi_epi64(vaddr1, 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);
- }
-#else
- struct rte_mbuf *mb0, *mb1, *mb2, *mb3;
- __m256i dma_addr0_1, dma_addr2_3;
- __m256i hdr_room = _mm256_set1_epi64x(RTE_PKTMBUF_HEADROOM);
- /* Initialize the mbufs in vector, process 4 mbufs in one loop */
- for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH;
- i += 4, rxep += 4, rxdp += 4) {
- __m128i vaddr0, vaddr1, vaddr2, vaddr3;
- __m256i vaddr0_1, vaddr2_3;
-
- mb0 = rxep[0].mbuf;
- mb1 = rxep[1].mbuf;
- mb2 = rxep[2].mbuf;
- mb3 = rxep[3].mbuf;
-
- /* 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);
- vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr);
- vaddr3 = _mm_loadu_si128((__m128i *)&mb3->buf_addr);
-
- /*
- * merge 0 & 1, by casting 0 to 256-bit and inserting 1
- * into the high lanes. Similarly for 2 & 3
- */
- vaddr0_1 = _mm256_inserti128_si256(
- _mm256_castsi128_si256(vaddr0), vaddr1, 1);
- vaddr2_3 = _mm256_inserti128_si256(
- _mm256_castsi128_si256(vaddr2), vaddr3, 1);
-
- /* convert pa to dma_addr hdr/data */
- dma_addr0_1 = _mm256_unpackhi_epi64(vaddr0_1, vaddr0_1);
- dma_addr2_3 = _mm256_unpackhi_epi64(vaddr2_3, vaddr2_3);
-
- /* add headroom to pa values */
- dma_addr0_1 = _mm256_add_epi64(dma_addr0_1, hdr_room);
- dma_addr2_3 = _mm256_add_epi64(dma_addr2_3, hdr_room);
-
- /* flush desc with pa dma_addr */
- _mm256_store_si256((__m256i *)&rxdp->read, dma_addr0_1);
- _mm256_store_si256((__m256i *)&(rxdp + 2)->read, dma_addr2_3);
- }
-
-#endif
-
- rxq->rxrearm_start += RTE_I40E_RXQ_REARM_THRESH;
- if (rxq->rxrearm_start >= rxq->nb_rx_desc)
- rxq->rxrearm_start = 0;
-
- rxq->rxrearm_nb -= RTE_I40E_RXQ_REARM_THRESH;
-
- rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
- (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
-
- /* Update the tail pointer on the NIC */
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ return i40e_rxq_rearm_common(rxq, false);
}
#ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
*/
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_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_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_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,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (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_BAD) >> 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_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_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_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);
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (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_BAD) >> 1,
+ (PKT_RX_L4_CKSUM_GOOD | 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);
RTE_SET_USED(avx_aligned); /* for 32B descriptors we don't use this */
txq->tx_tail = tx_id;
- I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ I40E_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
return nb_pkts;
}
git.droids-corp.org / dpdk.git / blobdiff