*/
#include <stdint.h>
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
#include <rte_malloc.h>
#include <rte_vect.h>
const uint32x4_t cksum_mask = {
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,
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,
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,
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};
/* map rss and vlan type to rss hash and vlan flag */
const uint8x16_t vlan_flags = {
PKT_RX_IP_CKSUM_BAD >> 1,
(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
- (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_OUTER_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_IP_CKSUM_GOOD | PKT_RX_OUTER_IP_CKSUM_BAD |
PKT_RX_L4_CKSUM_BAD) >> 1,
- (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ (PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_BAD) >> 1,
0, 0, 0, 0, 0, 0, 0, 0};
}
- /*
+/**
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_I40E_DESCS_PER_LOOP)
+ *
* Notice:
* - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
+ * - floor align nb_pkts to a RTE_I40E_DESCS_PER_LOOP power-of-two
*/
static inline uint16_t
_recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict rxq,
0, 0, 0 /* ignore non-length fields */
};
- /* nb_pkts shall be less equal than RTE_I40E_MAX_RX_BURST */
- nb_pkts = RTE_MIN(nb_pkts, RTE_I40E_MAX_RX_BURST);
-
/* nb_pkts has to be floor-aligned to RTE_I40E_DESCS_PER_LOOP */
nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_I40E_DESCS_PER_LOOP);
/* pkt 3,4 shift the pktlen field to be 16-bit aligned*/
uint32x4_t len3 = vshlq_u32(vreinterpretq_u32_u64(descs[3]),
len_shl);
- descs[3] = vreinterpretq_u64_u32(len3);
+ descs[3] = vreinterpretq_u64_u16(vsetq_lane_u16
+ (vgetq_lane_u16(vreinterpretq_u16_u32(len3), 7),
+ vreinterpretq_u16_u64(descs[3]),
+ 7));
uint32x4_t len2 = vshlq_u32(vreinterpretq_u32_u64(descs[2]),
len_shl);
- descs[2] = vreinterpretq_u64_u32(len2);
+ descs[2] = vreinterpretq_u64_u16(vsetq_lane_u16
+ (vgetq_lane_u16(vreinterpretq_u16_u32(len2), 7),
+ vreinterpretq_u16_u64(descs[2]),
+ 7));
/* D.1 pkt 3,4 convert format from desc to pktmbuf */
pkt_mb4 = vqtbl1q_u8(vreinterpretq_u8_u64(descs[3]), shuf_msk);
/* pkt 1,2 shift the pktlen field to be 16-bit aligned*/
uint32x4_t len1 = vshlq_u32(vreinterpretq_u32_u64(descs[1]),
len_shl);
- descs[1] = vreinterpretq_u64_u32(len1);
+ descs[1] = vreinterpretq_u64_u16(vsetq_lane_u16
+ (vgetq_lane_u16(vreinterpretq_u16_u32(len1), 7),
+ vreinterpretq_u16_u64(descs[1]),
+ 7));
uint32x4_t len0 = vshlq_u32(vreinterpretq_u32_u64(descs[0]),
len_shl);
- descs[0] = vreinterpretq_u64_u32(len0);
+ descs[0] = vreinterpretq_u64_u16(vsetq_lane_u16
+ (vgetq_lane_u16(vreinterpretq_u16_u32(len0), 7),
+ vreinterpretq_u16_u64(descs[0]),
+ 7));
/* D.1 pkt 1,2 convert format from desc to pktmbuf */
pkt_mb2 = vqtbl1q_u8(vreinterpretq_u8_u64(descs[1]), shuf_msk);
return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
}
- /* vPMD receive routine that reassembles scattered packets
+/**
+ * vPMD receive routine that reassembles single burst of 32 scattered packets
+ *
* Notice:
* - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
*/
-uint16_t
-i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+static uint16_t
+i40e_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
{
struct i40e_rx_queue *rxq = rx_queue;
&split_flags[i]);
}
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > RTE_I40E_VPMD_RX_BURST) {
+ uint16_t burst;
+
+ burst = i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ RTE_I40E_VPMD_RX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < RTE_I40E_VPMD_RX_BURST)
+ return retval;
+ }
+
+ return retval + i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ nb_pkts);
+}
+
static inline void
vtx1(volatile struct i40e_tx_desc *txdp,
struct rte_mbuf *pkt, uint64_t flags)