struct rte_mbuf *mb0, *mb1;
__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
RTE_PKTMBUF_HEADROOM);
+ __m128i dma_addr0, dma_addr1;
+
+ rxdp = rxq->rx_ring + rxq->rxrearm_start;
/* Pull 'n' more MBUFs into the software ring */
if (rte_mempool_get_bulk(rxq->mb_pool,
- (void *)rxep, RTE_IXGBE_RXQ_REARM_THRESH) < 0)
+ (void *)rxep,
+ RTE_IXGBE_RXQ_REARM_THRESH) < 0) {
+ if (rxq->rxrearm_nb + RTE_IXGBE_RXQ_REARM_THRESH >=
+ rxq->nb_rx_desc) {
+ dma_addr0 = _mm_setzero_si128();
+ for (i = 0; i < RTE_IXGBE_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_IXGBE_RXQ_REARM_THRESH;
return;
-
- rxdp = rxq->rx_ring + rxq->rxrearm_start;
+ }
/* 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;
__m128i vaddr0, vaddr1;
+ uintptr_t p0, p1;
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;
+ /*
+ * Flush mbuf with pkt template.
+ * Data to be rearmed is 6 bytes long.
+ * Though, RX will overwrite ol_flags that are coming next
+ * anyway. So overwrite whole 8 bytes with one load:
+ * 6 bytes of rearm_data plus first 2 bytes of ol_flags.
+ */
+ p0 = (uintptr_t)&mb0->rearm_data;
+ *(uint64_t *)p0 = rxq->mbuf_initializer;
+ p1 = (uintptr_t)&mb1->rearm_data;
+ *(uint64_t *)p1 = rxq->mbuf_initializer;
/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
* numbers of DD bit
* - don't support ol_flags for rss and csum err
*/
-uint16_t
-ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+static inline uint16_t
+_recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, uint8_t *split_packet)
{
volatile union ixgbe_adv_rx_desc *rxdp;
- struct igb_rx_queue *rxq = rx_queue;
struct igb_rx_entry *sw_ring;
uint16_t nb_pkts_recd;
int pos;
-rxq->crc_len, /* sub crc on data_len */
0 /* ignore pkt_type field */
);
- __m128i dd_check;
+ __m128i dd_check, eop_check;
if (unlikely(nb_pkts < RTE_IXGBE_VPMD_RX_BURST))
return 0;
/* 4 packets DD mask */
dd_check = _mm_set_epi64x(0x0000000100000001LL, 0x0000000100000001LL);
+ /* 4 packets EOP mask */
+ eop_check = _mm_set_epi64x(0x0000000200000002LL, 0x0000000200000002LL);
+
/* mask to shuffle from desc. to mbuf */
shuf_msk = _mm_set_epi8(
7, 6, 5, 4, /* octet 4~7, 32bits rss */
0xFF, 0xFF /* skip pkt_type field */
);
-
/* Cache is empty -> need to scan the buffer rings, but first move
* the next 'n' mbufs into the cache */
sw_ring = &rxq->sw_ring[rxq->rx_tail];
* A. load 4 packet in one loop
* B. copy 4 mbuf point from swring to rx_pkts
* C. calc the number of DD bits among the 4 packets
+ * [C*. extract the end-of-packet bit, if requested]
* D. fill info. from desc to mbuf
*/
for (pos = 0, nb_pkts_recd = 0; pos < RTE_IXGBE_VPMD_RX_BURST;
__m128i zero, staterr, sterr_tmp1, sterr_tmp2;
__m128i mbp1, mbp2; /* two mbuf pointer in one XMM reg. */
+ if (split_packet) {
+ rte_prefetch0(&rx_pkts[pos]->cacheline1);
+ rte_prefetch0(&rx_pkts[pos + 1]->cacheline1);
+ rte_prefetch0(&rx_pkts[pos + 2]->cacheline1);
+ rte_prefetch0(&rx_pkts[pos + 3]->cacheline1);
+ }
+
/* B.1 load 1 mbuf point */
mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
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 */
+ /* C* extract and record EOP bit */
+ if (split_packet) {
+ __m128i eop_shuf_mask = _mm_set_epi8(
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0x04, 0x0C, 0x00, 0x08
+ );
+
+ /* and with mask to extract bits, flipping 1-0 */
+ __m128i eop_bits = _mm_andnot_si128(staterr, eop_check);
+ /* the staterr values are not in order, as the count
+ * count of dd bits doesn't care. However, for end of
+ * packet tracking, we do care, so shuffle. This also
+ * compresses the 32-bit values to 8-bit */
+ eop_bits = _mm_shuffle_epi8(eop_bits, eop_shuf_mask);
+ /* store the resulting 32-bit value */
+ *(int *)split_packet = _mm_cvtsi128_si32(eop_bits);
+ split_packet += RTE_IXGBE_DESCS_PER_LOOP;
+
+ /* zero-out next pointers */
+ rx_pkts[pos]->next = NULL;
+ rx_pkts[pos + 1]->next = NULL;
+ rx_pkts[pos + 2]->next = NULL;
+ rx_pkts[pos + 3]->next = NULL;
+ }
+
+ /* C.3 calc available number of desc */
staterr = _mm_and_si128(staterr, dd_check);
staterr = _mm_packs_epi32(staterr, zero);
return nb_pkts_recd;
}
+
+/*
+ * vPMD receive routine, now only accept (nb_pkts == RTE_IXGBE_VPMD_RX_BURST)
+ * in one loop
+ *
+ * Notice:
+ * - nb_pkts < RTE_IXGBE_VPMD_RX_BURST, just return no packet
+ * - nb_pkts > RTE_IXGBE_VPMD_RX_BURST, only scan RTE_IXGBE_VPMD_RX_BURST
+ * numbers of DD bit
+ * - don't support ol_flags for rss and csum err
+ */
+uint16_t
+ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
+}
+
+static inline uint16_t
+reassemble_packets(struct igb_rx_queue *rxq, struct rte_mbuf **rx_bufs,
+ uint16_t nb_bufs, uint8_t *split_flags)
+{
+ struct rte_mbuf *pkts[RTE_IXGBE_VPMD_RX_BURST]; /*finished pkts*/
+ struct rte_mbuf *start = rxq->pkt_first_seg;
+ struct rte_mbuf *end = rxq->pkt_last_seg;
+ unsigned pkt_idx, buf_idx;
+
+
+ for (buf_idx = 0, pkt_idx = 0; buf_idx < nb_bufs; buf_idx++) {
+ if (end != NULL) {
+ /* processing a split packet */
+ end->next = rx_bufs[buf_idx];
+ rx_bufs[buf_idx]->data_len += rxq->crc_len;
+
+ start->nb_segs++;
+ start->pkt_len += rx_bufs[buf_idx]->data_len;
+ end = end->next;
+
+ if (!split_flags[buf_idx]) {
+ /* it's the last packet of the set */
+ start->hash = end->hash;
+ start->ol_flags = end->ol_flags;
+ /* we need to strip crc for the whole packet */
+ start->pkt_len -= rxq->crc_len;
+ if (end->data_len > rxq->crc_len)
+ end->data_len -= rxq->crc_len;
+ else {
+ /* free up last mbuf */
+ struct rte_mbuf *secondlast = start;
+ while (secondlast->next != end)
+ secondlast = secondlast->next;
+ secondlast->data_len -= (rxq->crc_len -
+ end->data_len);
+ secondlast->next = NULL;
+ rte_pktmbuf_free_seg(end);
+ end = secondlast;
+ }
+ pkts[pkt_idx++] = start;
+ start = end = NULL;
+ }
+ } else {
+ /* not processing a split packet */
+ if (!split_flags[buf_idx]) {
+ /* not a split packet, save and skip */
+ pkts[pkt_idx++] = rx_bufs[buf_idx];
+ continue;
+ }
+ end = start = rx_bufs[buf_idx];
+ rx_bufs[buf_idx]->data_len += rxq->crc_len;
+ rx_bufs[buf_idx]->pkt_len += rxq->crc_len;
+ }
+ }
+
+ /* save the partial packet for next time */
+ rxq->pkt_first_seg = start;
+ rxq->pkt_last_seg = end;
+ memcpy(rx_bufs, pkts, pkt_idx * (sizeof(*pkts)));
+ return pkt_idx;
+}
+
+/*
+ * vPMD receive routine that reassembles scattered packets
+ *
+ * Notice:
+ * - don't support ol_flags for rss and csum err
+ * - now only accept (nb_pkts == RTE_IXGBE_VPMD_RX_BURST)
+ */
+uint16_t
+ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ struct igb_rx_queue *rxq = rx_queue;
+ uint8_t split_flags[RTE_IXGBE_VPMD_RX_BURST] = {0};
+
+ /* get some new buffers */
+ uint16_t nb_bufs = _recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,
+ split_flags);
+ if (nb_bufs == 0)
+ return 0;
+
+ /* happy day case, full burst + no packets to be joined */
+ const uint32_t *split_fl32 = (uint32_t *)split_flags;
+ if (rxq->pkt_first_seg == NULL &&
+ split_fl32[0] == 0 && split_fl32[1] == 0 &&
+ split_fl32[2] == 0 && split_fl32[3] == 0)
+ return nb_bufs;
+
+ /* reassemble any packets that need reassembly*/
+ unsigned i = 0;
+ if (rxq->pkt_first_seg == NULL) {
+ /* find the first split flag, and only reassemble then*/
+ while (i < nb_bufs && !split_flags[i])
+ i++;
+ if (i == nb_bufs)
+ return nb_bufs;
+ }
+ return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
+ &split_flags[i]);
+}
+
static inline void
vtx1(volatile union ixgbe_adv_tx_desc *txdp,
struct rte_mbuf *pkt, uint64_t flags)
*/
txep = &((struct igb_tx_entry_v *)txq->sw_ring)[txq->tx_next_dd -
(n - 1)];
-#ifdef RTE_MBUF_REFCNT
m = __rte_pktmbuf_prefree_seg(txep[0].mbuf);
-#else
- m = txep[0].mbuf;
-#endif
if (likely(m != NULL)) {
free[0] = m;
nb_free = 1;
for (i = 1; i < n; i++) {
-#ifdef RTE_MBUF_REFCNT
m = __rte_pktmbuf_prefree_seg(txep[i].mbuf);
-#else
- m = txep[i]->mbuf;
-#endif
if (likely(m != NULL)) {
if (likely(m->pool == free[0]->pool))
free[nb_free++] = m;
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
- };
+ uintptr_t p;
+ struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
- mb_def.buf_len = rxq->mb_pool->elt_size - sizeof(struct rte_mbuf);
+ mb_def.nb_segs = 1;
+ mb_def.data_off = RTE_PKTMBUF_HEADROOM;
mb_def.port = rxq->port_id;
- rxq->mbuf_initializer = *((uint64_t *)&mb_def.rearm_data);
+ rte_mbuf_refcnt_set(&mb_def, 1);
+
+ /* prevent compiler reordering: rearm_data covers previous fields */
+ rte_compiler_barrier();
+ p = (uintptr_t)&mb_def.rearm_data;
+ rxq->mbuf_initializer = *(uint64_t *)p;
return 0;
}
git.droids-corp.org / dpdk.git / blobdiff