X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fi40e%2Fi40e_rxtx_vec_neon.c;h=f094de69ae8dc9e2d31639b91ee632c52ff7508d;hb=92c87229a9b096a53a5a9763bfee0198d20a91ea;hp=5555e9b5cf91b6e3c6f7d76464ef61974d9eb20b;hpb=78b50591c8e7ae3d010e8f4005e0e95c17800941;p=dpdk.git diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c index 5555e9b5cf..f094de69ae 100644 --- a/drivers/net/i40e/i40e_rxtx_vec_neon.c +++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "base/i40e_prototype.h" #include "base/i40e_type.h" @@ -13,7 +14,6 @@ #include "i40e_rxtx.h" #include "i40e_rxtx_vec_common.h" -#include #pragma GCC diagnostic ignored "-Wcast-qual" @@ -72,8 +72,9 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq) 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 @@ -171,8 +172,8 @@ desc_to_olflags_v(struct i40e_rx_queue *rxq, uint64x2_t descs[4], #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; @@ -186,14 +187,16 @@ desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf **rx_pkts, } - /* +/** + * 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; @@ -228,9 +231,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts, 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); @@ -307,9 +307,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts, rte_mbuf_prefetch_part2(rx_pkts[pos + 3]); } - /* avoid compiler reorder optimization */ - rte_compiler_barrier(); - /* pkt 3,4 shift the pktlen field to be 16-bit aligned*/ uint32x4_t len3 = vshlq_u32(vreinterpretq_u32_u64(descs[3]), len_shl); @@ -434,21 +431,21 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts, * 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; @@ -477,11 +474,38 @@ i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts, i++; if (i == nb_bufs) return nb_bufs; + rxq->pkt_first_seg = rx_pkts[i]; } return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i, &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) @@ -495,8 +519,8 @@ vtx1(volatile struct i40e_tx_desc *txdp, } 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; @@ -505,8 +529,8 @@ vtx(volatile struct i40e_tx_desc *txdp, } 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; @@ -566,30 +590,31 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts, 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);