#define RXEFLAG_SHIFT (13)
/* IPE/L4E flag shift */
#define L3L4EFLAG_SHIFT (14)
+/* shift PKT_RX_L4_CKSUM_GOOD into one byte by 1 bit */
+#define CKSUM_SHIFT (1)
static inline void
fm10k_desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
0x0000, 0x0000, 0x0000, 0x0000,
0x0001, 0x0001, 0x0001, 0x0001);
+ /* mask the lower byte of ol_flags */
+ const __m128i ol_flags_msk = _mm_set_epi16(
+ 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x00FF, 0x00FF, 0x00FF, 0x00FF);
+
const __m128i l3l4cksum_flag = _mm_set_epi8(0, 0, 0, 0,
0, 0, 0, 0,
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_BAD | PKT_RX_L4_CKSUM_BAD) >> CKSUM_SHIFT,
+ (PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD) >> CKSUM_SHIFT,
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> CKSUM_SHIFT,
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> CKSUM_SHIFT);
const __m128i rxe_flag = _mm_set_epi8(0, 0, 0, 0,
0, 0, 0, 0,
/* Process L4/L3 checksum error flags */
cksumflag = _mm_srli_epi16(cksumflag, L3L4EFLAG_SHIFT);
cksumflag = _mm_shuffle_epi8(l3l4cksum_flag, cksumflag);
+
+ /* clean the higher byte and shift back the flag bits */
+ cksumflag = _mm_and_si128(cksumflag, ol_flags_msk);
+ cksumflag = _mm_slli_epi16(cksumflag, CKSUM_SHIFT);
vtag1 = _mm_or_si128(cksumflag, vtag1);
vol.dword = _mm_cvtsi128_si64(vtag1);
if (fconf->mode != RTE_FDIR_MODE_NONE)
return -1;
- /* - no csum error report support
- * - no header split support
- */
- if (rxmode->hw_ip_checksum == 1 ||
- rxmode->header_split == 1)
+ /* no header split support */
+ if (rxmode->header_split == 1)
return -1;
return 0;
/* 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;
/* Read desc statuses backwards to avoid race condition */
/* A.1 load 4 pkts desc */
descs0[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 *)&mbufp[pos+2]);
descs0[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+ rte_compiler_barrier();
/* B.1 load 2 mbuf point */
descs0[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+ rte_compiler_barrier();
descs0[0] = _mm_loadu_si128((__m128i *)(rxdp));
/* B.2 copy 2 mbuf point into rx_pkts */
* next_dd - (rs_thresh-1)
*/
txep = &txq->sw_ring[txq->next_dd - (n - 1)];
- m = __rte_pktmbuf_prefree_seg(txep[0]);
+ m = rte_pktmbuf_prefree_seg(txep[0]);
if (likely(m != NULL)) {
free[0] = m;
nb_free = 1;
for (i = 1; i < n; i++) {
- m = __rte_pktmbuf_prefree_seg(txep[i]);
+ m = rte_pktmbuf_prefree_seg(txep[i]);
if (likely(m != NULL)) {
if (likely(m->pool == free[0]->pool))
free[nb_free++] = m;
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]);
+ m = rte_pktmbuf_prefree_seg(txep[i]);
if (m != NULL)
rte_mempool_put(m->pool, m);
}
}
uint16_t
-fm10k_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
- uint16_t nb_pkts)
+fm10k_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
{
struct fm10k_tx_queue *txq = (struct fm10k_tx_queue *)tx_queue;
volatile struct fm10k_tx_desc *txdp;