*/
#include <stdint.h>
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
#include <rte_malloc.h>
+#include <rte_vect.h>
#include "base/i40e_prototype.h"
#include "base/i40e_type.h"
#include "i40e_rxtx.h"
#include "i40e_rxtx_vec_common.h"
-#include <arm_neon.h>
#pragma GCC diagnostic ignored "-Wcast-qual"
rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+ rte_io_wmb();
/* Update the tail pointer on the NIC */
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ I40E_PCI_REG_WRITE_RELAXED(rxq->qrx_tail, rx_id);
}
static inline void
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};
#define I40E_UINT16_BIT (CHAR_BIT * sizeof(uint16_t))
static inline void
-desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf **rx_pkts,
- uint32_t *ptype_tbl)
+desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf **__rte_restrict rx_pkts,
+ uint32_t *__rte_restrict ptype_tbl)
{
int i;
uint8_t ptype;
}
- /*
+/**
+ * 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 *rxq, struct rte_mbuf **rx_pkts,
+_recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict rxq,
+ struct rte_mbuf **__rte_restrict rx_pkts,
uint16_t nb_pkts, uint8_t *split_packet)
{
volatile union i40e_rx_desc *rxdp;
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);
* numbers of DD bits
*/
uint16_t
-i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+i40e_recv_pkts_vec(void *__rte_restrict rx_queue,
+ struct rte_mbuf **__rte_restrict rx_pkts, uint16_t nb_pkts)
{
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)
}
static inline void
-vtx(volatile struct i40e_tx_desc *txdp,
- struct rte_mbuf **pkt, uint16_t nb_pkts, uint64_t flags)
+vtx(volatile struct i40e_tx_desc *txdp, struct rte_mbuf **pkt,
+ uint16_t nb_pkts, uint64_t flags)
{
int i;
}
uint16_t
-i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
- uint16_t nb_pkts)
+i40e_xmit_fixed_burst_vec(void *__rte_restrict tx_queue,
+ struct rte_mbuf **__rte_restrict tx_pkts, uint16_t nb_pkts)
{
struct i40e_tx_queue *txq = (struct i40e_tx_queue *)tx_queue;
volatile struct i40e_tx_desc *txdp;
txq->tx_tail = tx_id;
- I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ rte_io_wmb();
+ I40E_PCI_REG_WRITE_RELAXED(txq->qtx_tail, tx_id);
return nb_pkts;
}
-void __attribute__((cold))
+void __rte_cold
i40e_rx_queue_release_mbufs_vec(struct i40e_rx_queue *rxq)
{
_i40e_rx_queue_release_mbufs_vec(rxq);
}
-int __attribute__((cold))
+int __rte_cold
i40e_rxq_vec_setup(struct i40e_rx_queue *rxq)
{
return i40e_rxq_vec_setup_default(rxq);
}
-int __attribute__((cold))
+int __rte_cold
i40e_txq_vec_setup(struct i40e_tx_queue __rte_unused *txq)
{
return 0;
}
-int __attribute__((cold))
+int __rte_cold
i40e_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev)
{
return i40e_rx_vec_dev_conf_condition_check_default(dev);
git.droids-corp.org / dpdk.git / blobdiff