*/
#include <stdint.h>
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
#include <rte_malloc.h>
#include "base/i40e_prototype.h"
#include "i40e_ethdev.h"
#include "i40e_rxtx.h"
#include "i40e_rxtx_vec_common.h"
+#include "i40e_rxtx_common_avx.h"
#include <rte_vect.h>
#define RTE_I40E_DESCS_PER_LOOP_AVX 8
-static inline void
+static __rte_always_inline void
i40e_rxq_rearm(struct i40e_rx_queue *rxq)
{
int i;
rxdp = rxq->rx_ring + rxq->rxrearm_start;
+ if (unlikely(!cache))
+ return i40e_rxq_rearm_common(rxq, true);
+
/* We need to pull 'n' more MBUFs into the software ring from mempool
* We inline the mempool function here, so we can vectorize the copy
* from the cache into the shadow ring.
* - Position that bit correctly based on packet number
* - OR in the resulting bit to mbuf_flags
*/
- RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
+ RTE_BUILD_BUG_ON(RTE_MBUF_F_RX_FDIR_ID != (1 << 13));
__m256i mbuf_flag_mask = _mm256_set_epi32(0, 0, 0, 1 << 13,
0, 0, 0, 1 << 13);
__m256i desc_flag_bit = _mm256_and_si256(mbuf_flag_mask, fdir_mask);
* destination
*/
const __m256i vlan_flags_shuf = _mm256_set_epi32
- (0, 0, PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, 0,
- 0, 0, PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, 0);
+ (0, 0, RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED, 0,
+ 0, 0, RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED, 0);
/* data to be shuffled by result of flag mask, shifted down 11.
* If RSS/FDIR bits are set, shuffle moves appropriate flags in
*/
const __m256i rss_flags_shuf = _mm256_set_epi8
(0, 0, 0, 0, 0, 0, 0, 0,
- PKT_RX_RSS_HASH | PKT_RX_FDIR, PKT_RX_RSS_HASH, 0, 0,
- 0, 0, PKT_RX_FDIR, 0, /* end up 128-bits */
+ RTE_MBUF_F_RX_RSS_HASH | RTE_MBUF_F_RX_FDIR, RTE_MBUF_F_RX_RSS_HASH, 0, 0,
+ 0, 0, RTE_MBUF_F_RX_FDIR, 0, /* end up 128-bits */
0, 0, 0, 0, 0, 0, 0, 0,
- PKT_RX_RSS_HASH | PKT_RX_FDIR, PKT_RX_RSS_HASH, 0, 0,
- 0, 0, PKT_RX_FDIR, 0);
+ RTE_MBUF_F_RX_RSS_HASH | RTE_MBUF_F_RX_FDIR, RTE_MBUF_F_RX_RSS_HASH, 0, 0,
+ 0, 0, RTE_MBUF_F_RX_FDIR, 0);
/* data to be shuffled by the result of the flags mask shifted by 22
* bits. This gives use the l3_l4 flags.
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,
+ (RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_L4_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD) >> 1,
+ RTE_MBUF_F_RX_IP_CKSUM_BAD >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_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_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);
+ (RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_L4_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD) >> 1,
+ RTE_MBUF_F_RX_IP_CKSUM_BAD >> 1,
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_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);
+ (RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD);
uint16_t i, received;
* order (hi->lo): [1, 3, 5, 7, 0, 2, 4, 6]
* Then OR FDIR flags to mbuf_flags on FDIR ID hit.
*/
- RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
+ RTE_BUILD_BUG_ON(RTE_MBUF_F_RX_FDIR_ID != (1 << 13));
const __m256i pkt_fdir_bit = _mm256_set1_epi32(1 << 13);
const __m256i fdir_mask =
_mm256_cmpeq_epi32(fdir, fdir_id);
rx_pkts + retval, nb_pkts);
}
+static __rte_always_inline int
+i40e_tx_free_bufs_avx512(struct i40e_tx_queue *txq)
+{
+ struct i40e_vec_tx_entry *txep;
+ uint32_t n;
+ uint32_t i;
+ int nb_free = 0;
+ struct rte_mbuf *m, *free[RTE_I40E_TX_MAX_FREE_BUF_SZ];
+
+ /* check DD bits on threshold descriptor */
+ if ((txq->tx_ring[txq->tx_next_dd].cmd_type_offset_bsz &
+ rte_cpu_to_le_64(I40E_TXD_QW1_DTYPE_MASK)) !=
+ rte_cpu_to_le_64(I40E_TX_DESC_DTYPE_DESC_DONE))
+ return 0;
+
+ n = txq->tx_rs_thresh;
+
+ /* first buffer to free from S/W ring is at index
+ * tx_next_dd - (tx_rs_thresh-1)
+ */
+ txep = (void *)txq->sw_ring;
+ txep += txq->tx_next_dd - (n - 1);
+
+ if (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE && (n & 31) == 0) {
+ struct rte_mempool *mp = txep[0].mbuf->pool;
+ void **cache_objs;
+ struct rte_mempool_cache *cache = rte_mempool_default_cache(mp,
+ rte_lcore_id());
+
+ if (!cache || cache->len == 0)
+ goto normal;
+
+ cache_objs = &cache->objs[cache->len];
+
+ if (n > RTE_MEMPOOL_CACHE_MAX_SIZE) {
+ rte_mempool_ops_enqueue_bulk(mp, (void *)txep, n);
+ goto done;
+ }
+
+ /* The cache follows the following algorithm
+ * 1. Add the objects to the cache
+ * 2. Anything greater than the cache min value (if it
+ * crosses the cache flush threshold) is flushed to the ring.
+ */
+ /* Add elements back into the cache */
+ uint32_t copied = 0;
+ /* n is multiple of 32 */
+ while (copied < n) {
+ const __m512i a = _mm512_load_si512(&txep[copied]);
+ const __m512i b = _mm512_load_si512(&txep[copied + 8]);
+ const __m512i c = _mm512_load_si512(&txep[copied + 16]);
+ const __m512i d = _mm512_load_si512(&txep[copied + 24]);
+
+ _mm512_storeu_si512(&cache_objs[copied], a);
+ _mm512_storeu_si512(&cache_objs[copied + 8], b);
+ _mm512_storeu_si512(&cache_objs[copied + 16], c);
+ _mm512_storeu_si512(&cache_objs[copied + 24], d);
+ copied += 32;
+ }
+ cache->len += n;
+
+ if (cache->len >= cache->flushthresh) {
+ rte_mempool_ops_enqueue_bulk
+ (mp, &cache->objs[cache->size],
+ cache->len - cache->size);
+ cache->len = cache->size;
+ }
+ goto done;
+ }
+
+normal:
+ m = rte_pktmbuf_prefree_seg(txep[0].mbuf);
+ if (likely(m)) {
+ free[0] = m;
+ nb_free = 1;
+ for (i = 1; i < n; i++) {
+ rte_prefetch0(&txep[i + 3].mbuf->cacheline1);
+ m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+ if (likely(m)) {
+ if (likely(m->pool == free[0]->pool)) {
+ free[nb_free++] = m;
+ } else {
+ rte_mempool_put_bulk(free[0]->pool,
+ (void *)free,
+ nb_free);
+ free[0] = m;
+ nb_free = 1;
+ }
+ }
+ }
+ rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
+ } else {
+ for (i = 1; i < n; i++) {
+ m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+ if (m)
+ rte_mempool_put(m->pool, m);
+ }
+ }
+
+done:
+ /* buffers were freed, update counters */
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_rs_thresh);
+ txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_rs_thresh);
+ if (txq->tx_next_dd >= txq->nb_tx_desc)
+ txq->tx_next_dd = (uint16_t)(txq->tx_rs_thresh - 1);
+
+ return txq->tx_rs_thresh;
+}
+
static inline void
vtx1(volatile struct i40e_tx_desc *txdp, struct rte_mbuf *pkt, uint64_t flags)
{
const uint64_t hi_qw_tmpl = (I40E_TX_DESC_DTYPE_DATA |
((uint64_t)flags << I40E_TXD_QW1_CMD_SHIFT));
- /* if unaligned on 32-bit boundary, do one to align */
- if (((uintptr_t)txdp & 0x1F) != 0 && nb_pkts != 0) {
- vtx1(txdp, *pkt, flags);
- nb_pkts--, txdp++, pkt++;
- }
-
- /* do two at a time while possible, in bursts */
for (; nb_pkts > 3; txdp += 4, pkt += 4, nb_pkts -= 4) {
uint64_t hi_qw3 =
hi_qw_tmpl |
((uint64_t)pkt[0]->data_len <<
I40E_TXD_QW1_TX_BUF_SZ_SHIFT);
- __m256i desc2_3 = _mm256_set_epi64x
+ __m512i desc0_3 =
+ _mm512_set_epi64
(hi_qw3, pkt[3]->buf_iova + pkt[3]->data_off,
- hi_qw2, pkt[2]->buf_iova + pkt[2]->data_off);
- __m256i desc0_1 = _mm256_set_epi64x
- (hi_qw1, pkt[1]->buf_iova + pkt[1]->data_off,
+ hi_qw2, pkt[2]->buf_iova + pkt[2]->data_off,
+ hi_qw1, pkt[1]->buf_iova + pkt[1]->data_off,
hi_qw0, pkt[0]->buf_iova + pkt[0]->data_off);
- _mm256_store_si256((void *)(txdp + 2), desc2_3);
- _mm256_store_si256((void *)txdp, desc0_1);
+ _mm512_storeu_si512((void *)txdp, desc0_3);
}
/* do any last ones */
}
}
+static __rte_always_inline void
+tx_backlog_entry_avx512(struct i40e_vec_tx_entry *txep,
+ struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ int i;
+
+ for (i = 0; i < (int)nb_pkts; ++i)
+ txep[i].mbuf = tx_pkts[i];
+}
+
static inline uint16_t
i40e_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts)
{
struct i40e_tx_queue *txq = (struct i40e_tx_queue *)tx_queue;
volatile struct i40e_tx_desc *txdp;
- struct i40e_tx_entry *txep;
+ struct i40e_vec_tx_entry *txep;
uint16_t n, nb_commit, tx_id;
uint64_t flags = I40E_TD_CMD;
uint64_t rs = I40E_TX_DESC_CMD_RS | I40E_TD_CMD;
nb_pkts = RTE_MIN(nb_pkts, txq->tx_rs_thresh);
if (txq->nb_tx_free < txq->tx_free_thresh)
- i40e_tx_free_bufs(txq);
+ i40e_tx_free_bufs_avx512(txq);
nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
if (unlikely(nb_pkts == 0))
tx_id = txq->tx_tail;
txdp = &txq->tx_ring[tx_id];
- txep = &txq->sw_ring[tx_id];
+ txep = (void *)txq->sw_ring;
+ txep += tx_id;
txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
n = (uint16_t)(txq->nb_tx_desc - tx_id);
if (nb_commit >= n) {
- tx_backlog_entry(txep, tx_pkts, n);
+ tx_backlog_entry_avx512(txep, tx_pkts, n);
vtx(txdp, tx_pkts, n - 1, flags);
tx_pkts += (n - 1);
txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
/* avoid reach the end of ring */
- txdp = &txq->tx_ring[tx_id];
- txep = &txq->sw_ring[tx_id];
+ txdp = txq->tx_ring;
+ txep = (void *)txq->sw_ring;
}
- tx_backlog_entry(txep, tx_pkts, nb_commit);
+ tx_backlog_entry_avx512(txep, tx_pkts, nb_commit);
vtx(txdp, tx_pkts, nb_commit, flags);