/* 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 vaddr0, vaddr1;
- uintptr_t p0, p1;
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
- /*
- * 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));
vaddr1 = _mm_loadu_si128((__m128i *)&(mb1->buf_addr));
IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id);
}
-/* Handling the offload flags (olflags) field takes computation
- * time when receiving packets. Therefore we provide a flag to disable
- * the processing of the olflags field when they are not needed. This
- * gives improved performance, at the cost of losing the offload info
- * in the received packet
- */
-#ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
-
static inline void
-desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags,
+desc_to_olflags_v(__m128i descs[4], __m128i mbuf_init, uint8_t vlan_flags,
struct rte_mbuf **rx_pkts)
{
__m128i ptype0, ptype1, vtag0, vtag1, csum;
- union {
- uint16_t e[4];
- uint64_t dword;
- } vol;
+ __m128i rearm0, rearm1, rearm2, rearm3;
/* mask everything except rss type */
const __m128i rsstype_msk = _mm_set_epi16(
0x0000, 0x0000, 0x0000, 0x0000,
0x000F, 0x000F, 0x000F, 0x000F);
+ /* mask the lower byte of ol_flags */
+ const __m128i ol_flags_msk = _mm_set_epi16(
+ 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x00FF, 0x00FF, 0x00FF, 0x00FF);
+
/* map rss type to rss hash flag */
const __m128i rss_flags = _mm_set_epi8(PKT_RX_FDIR, 0, 0, 0,
0, 0, 0, PKT_RX_RSS_HASH,
IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP);
/* map vlan present (0x8), IPE (0x2), L4E (0x1) to ol_flags */
- const __m128i vlan_csum_map = _mm_set_epi8(
+ const __m128i vlan_csum_map_lo = _mm_set_epi8(
0, 0, 0, 0,
vlan_flags | PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
vlan_flags | PKT_RX_IP_CKSUM_BAD,
- vlan_flags | PKT_RX_L4_CKSUM_BAD,
- vlan_flags,
+ vlan_flags | PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD,
+ vlan_flags | PKT_RX_IP_CKSUM_GOOD,
0, 0, 0, 0,
PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
PKT_RX_IP_CKSUM_BAD,
- PKT_RX_L4_CKSUM_BAD,
- 0);
+ PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD,
+ PKT_RX_IP_CKSUM_GOOD);
+
+ const __m128i vlan_csum_map_hi = _mm_set_epi8(
+ 0, 0, 0, 0,
+ 0, PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t),
+ 0, 0, 0, 0,
+ 0, PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t));
ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]);
ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]);
vtag1 = _mm_or_si128(csum, vtag1);
/* convert VP, IPE, L4E to ol_flags */
- vtag1 = _mm_shuffle_epi8(vlan_csum_map, vtag1);
+ vtag0 = _mm_shuffle_epi8(vlan_csum_map_hi, vtag1);
+ vtag0 = _mm_slli_epi16(vtag0, sizeof(uint8_t));
+
+ vtag1 = _mm_shuffle_epi8(vlan_csum_map_lo, vtag1);
+ vtag1 = _mm_and_si128(vtag1, ol_flags_msk);
+ vtag1 = _mm_or_si128(vtag0, vtag1);
vtag1 = _mm_or_si128(ptype0, vtag1);
- vol.dword = _mm_cvtsi128_si64(vtag1);
- rx_pkts[0]->ol_flags = vol.e[0];
- rx_pkts[1]->ol_flags = vol.e[1];
- rx_pkts[2]->ol_flags = vol.e[2];
- rx_pkts[3]->ol_flags = vol.e[3];
-}
+ /*
+ * At this point, we have the 4 sets of flags in the low 64-bits
+ * of vtag1 (4x16).
+ * We want to extract these, and merge them with the mbuf init data
+ * so we can do a single 16-byte write to the mbuf to set the flags
+ * and all the other initialization fields. Extracting the
+ * appropriate flags means that we have to do a shift and blend for
+ * each mbuf before we do the write.
+ */
+#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
+
+ rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 8), 0x10);
+ rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 6), 0x10);
+ rearm2 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 4), 0x10);
+ rearm3 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 2), 0x10);
+
#else
-#define desc_to_olflags_v(desc, vlan_flags, rx_pkts) do { \
- RTE_SET_USED(vlan_flags); \
- } while (0)
-#endif
+ rearm0 = _mm_slli_si128(vtag1, 14);
+ rearm1 = _mm_slli_si128(vtag1, 12);
+ rearm2 = _mm_slli_si128(vtag1, 10);
+ rearm3 = _mm_slli_si128(vtag1, 8);
+
+ rearm0 = _mm_or_si128(mbuf_init, _mm_srli_epi64(rearm0, 48));
+ rearm1 = _mm_or_si128(mbuf_init, _mm_srli_epi64(rearm1, 48));
+ rearm2 = _mm_or_si128(mbuf_init, _mm_srli_epi64(rearm2, 48));
+ rearm3 = _mm_or_si128(mbuf_init, _mm_srli_epi64(rearm3, 48));
+
+#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+
+ _mm_store_si128((__m128i *)&rx_pkts[0]->rearm_data, rearm0);
+ _mm_store_si128((__m128i *)&rx_pkts[1]->rearm_data, rearm1);
+ _mm_store_si128((__m128i *)&rx_pkts[2]->rearm_data, rearm2);
+ _mm_store_si128((__m128i *)&rx_pkts[3]->rearm_data, rearm3);
+}
/*
* vPMD raw receive routine, only accept(nb_pkts >= RTE_IXGBE_DESCS_PER_LOOP)
0, 0 /* ignore pkt_type field */
);
__m128i dd_check, eop_check;
+ __m128i mbuf_init;
uint8_t vlan_flags;
/* nb_pkts shall be less equal than RTE_IXGBE_MAX_RX_BURST */
0xFF, 0xFF
);
+ mbuf_init = _mm_set_epi64x(0, rxq->mbuf_initializer);
+
/* Cache is empty -> need to scan the buffer rings, but first move
* the next 'n' mbufs into the cache
*/
/* Read desc statuses backwards to avoid race condition */
/* A.1 load 4 pkts desc */
descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+ rte_compiler_barrier();
/* B.2 copy 2 mbuf point into rx_pkts */
_mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);
mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]);
descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+ rte_compiler_barrier();
/* B.1 load 2 mbuf point */
descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+ rte_compiler_barrier();
descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
/* B.2 copy 2 mbuf point into rx_pkts */
sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
/* set ol_flags with vlan packet type */
- desc_to_olflags_v(descs, vlan_flags, &rx_pkts[pos]);
+ desc_to_olflags_v(descs, mbuf_init, vlan_flags, &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);
/* 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 */
}
uint16_t
-ixgbe_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
- uint16_t nb_pkts)
+ixgbe_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
{
struct ixgbe_tx_queue *txq = (struct ixgbe_tx_queue *)tx_queue;
volatile union ixgbe_adv_tx_desc *txdp;
git.droids-corp.org / dpdk.git / blobdiff