X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=sidebyside;f=lib%2Flibrte_pmd_ixgbe%2Fixgbe_rxtx.c;h=3c61d1c43d24c7a831f1d8b58db93f605c4e605a;hb=927318e854e805b6c5aab6152c3d5da41fbe5ad2;hp=e7cb269a039f8af0174a63e74489a974c249c23f;hpb=6ee7676169c5040063273cbef2d89a38dd51e5a3;p=dpdk.git diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c index e7cb269a03..3c61d1c43d 100644 --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c @@ -1,40 +1,39 @@ /*- * BSD LICENSE - * - * Copyright(c) 2010-2013 Intel Corporation. All rights reserved. + * + * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. + * Copyright 2014 6WIND S.A. * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions * are met: - * - * * Redistributions of source code must retain the above copyright + * + * * Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * */ #include -#include #include #include #include @@ -54,7 +53,6 @@ #include #include #include -#include #include #include #include @@ -72,19 +70,22 @@ #include #include #include +#include #include "ixgbe_logs.h" #include "ixgbe/ixgbe_api.h" #include "ixgbe/ixgbe_vf.h" #include "ixgbe_ethdev.h" #include "ixgbe/ixgbe_dcb.h" +#include "ixgbe/ixgbe_common.h" +#include "ixgbe_rxtx.h" - -#define RTE_PMD_IXGBE_TX_MAX_BURST 32 - -#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC -#define RTE_PMD_IXGBE_RX_MAX_BURST 32 -#endif +/* Bit Mask to indicate what bits required for building TX context */ +#define IXGBE_TX_OFFLOAD_MASK ( \ + PKT_TX_VLAN_PKT | \ + PKT_TX_IP_CKSUM | \ + PKT_TX_L4_MASK | \ + PKT_TX_TCP_SEG) static inline struct rte_mbuf * rte_rxmbuf_alloc(struct rte_mempool *mp) @@ -92,118 +93,10 @@ rte_rxmbuf_alloc(struct rte_mempool *mp) struct rte_mbuf *m; m = __rte_mbuf_raw_alloc(mp); - __rte_mbuf_sanity_check_raw(m, RTE_MBUF_PKT, 0); + __rte_mbuf_sanity_check_raw(m, 0); return (m); } -#define RTE_MBUF_DATA_DMA_ADDR(mb) \ - (uint64_t) ((mb)->buf_physaddr + (uint64_t)((char *)((mb)->pkt.data) - \ - (char *)(mb)->buf_addr)) - -#define RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mb) \ - (uint64_t) ((mb)->buf_physaddr + RTE_PKTMBUF_HEADROOM) - -/** - * Structure associated with each descriptor of the RX ring of a RX queue. - */ -struct igb_rx_entry { - struct rte_mbuf *mbuf; /**< mbuf associated with RX descriptor. */ -}; - -/** - * Structure associated with each descriptor of the TX ring of a TX queue. - */ -struct igb_tx_entry { - struct rte_mbuf *mbuf; /**< mbuf associated with TX desc, if any. */ - uint16_t next_id; /**< Index of next descriptor in ring. */ - uint16_t last_id; /**< Index of last scattered descriptor. */ -}; - -/** - * Structure associated with each RX queue. - */ -struct igb_rx_queue { - struct rte_mempool *mb_pool; /**< mbuf pool to populate RX ring. */ - volatile union ixgbe_adv_rx_desc *rx_ring; /**< RX ring virtual address. */ - uint64_t rx_ring_phys_addr; /**< RX ring DMA address. */ - volatile uint32_t *rdt_reg_addr; /**< RDT register address. */ - volatile uint32_t *rdh_reg_addr; /**< RDH register address. */ - struct igb_rx_entry *sw_ring; /**< address of RX software ring. */ - struct rte_mbuf *pkt_first_seg; /**< First segment of current packet. */ - struct rte_mbuf *pkt_last_seg; /**< Last segment of current packet. */ - uint16_t nb_rx_desc; /**< number of RX descriptors. */ - uint16_t rx_tail; /**< current value of RDT register. */ - uint16_t nb_rx_hold; /**< number of held free RX desc. */ -#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC - uint16_t rx_nb_avail; /**< nr of staged pkts ready to ret to app */ - uint16_t rx_next_avail; /**< idx of next staged pkt to ret to app */ - uint16_t rx_free_trigger; /**< triggers rx buffer allocation */ -#endif - uint16_t rx_free_thresh; /**< max free RX desc to hold. */ - uint16_t queue_id; /**< RX queue index. */ - uint8_t port_id; /**< Device port identifier. */ - uint8_t crc_len; /**< 0 if CRC stripped, 4 otherwise. */ - uint8_t drop_en; /**< If not 0, set SRRCTL.Drop_En. */ -#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC - /** need to alloc dummy mbuf, for wraparound when scanning hw ring */ - struct rte_mbuf fake_mbuf; - /** hold packets to return to application */ - struct rte_mbuf *rx_stage[RTE_PMD_IXGBE_RX_MAX_BURST*2]; -#endif -}; - -/** - * IXGBE CTX Constants - */ -enum ixgbe_advctx_num { - IXGBE_CTX_0 = 0, /**< CTX0 */ - IXGBE_CTX_1 = 1, /**< CTX1 */ - IXGBE_CTX_NUM = 2, /**< CTX NUMBER */ -}; - -/** - * Structure to check if new context need be built - */ - -struct ixgbe_advctx_info { - uint16_t flags; /**< ol_flags for context build. */ - uint32_t cmp_mask; /**< compare mask for vlan_macip_lens */ - union rte_vlan_macip vlan_macip_lens; /**< vlan, mac ip length. */ -}; - -/** - * Structure associated with each TX queue. - */ -struct igb_tx_queue { - /** TX ring virtual address. */ - volatile union ixgbe_adv_tx_desc *tx_ring; - uint64_t tx_ring_phys_addr; /**< TX ring DMA address. */ - struct igb_tx_entry *sw_ring; /**< virtual address of SW ring. */ - volatile uint32_t *tdt_reg_addr; /**< Address of TDT register. */ - uint16_t nb_tx_desc; /**< number of TX descriptors. */ - uint16_t tx_tail; /**< current value of TDT reg. */ - uint16_t tx_free_thresh;/**< minimum TX before freeing. */ - /** Number of TX descriptors to use before RS bit is set. */ - uint16_t tx_rs_thresh; - /** Number of TX descriptors used since RS bit was set. */ - uint16_t nb_tx_used; - /** Index to last TX descriptor to have been cleaned. */ - uint16_t last_desc_cleaned; - /** Total number of TX descriptors ready to be allocated. */ - uint16_t nb_tx_free; - uint16_t tx_next_dd; /**< next desc to scan for DD bit */ - uint16_t tx_next_rs; /**< next desc to set RS bit */ - uint16_t queue_id; /**< TX queue index. */ - uint8_t port_id; /**< Device port identifier. */ - uint8_t pthresh; /**< Prefetch threshold register. */ - uint8_t hthresh; /**< Host threshold register. */ - uint8_t wthresh; /**< Write-back threshold reg. */ - uint32_t txq_flags; /**< Holds flags for this TXq */ - uint32_t ctx_curr; /**< Hardware context states. */ - /** Hardware context0 history. */ - struct ixgbe_advctx_info ctx_cache[IXGBE_CTX_NUM]; -}; - #if 1 #define RTE_PMD_USE_PREFETCH @@ -218,40 +111,20 @@ struct igb_tx_queue { #define rte_ixgbe_prefetch(p) do {} while(0) #endif -#ifdef RTE_PMD_PACKET_PREFETCH -#define rte_packet_prefetch(p) rte_prefetch1(p) -#else -#define rte_packet_prefetch(p) do {} while(0) -#endif - /********************************************************************* * * TX functions * **********************************************************************/ -/* - * The "simple" TX queue functions require that the following - * flags are set when the TX queue is configured: - * - ETH_TXQ_FLAGS_NOMULTSEGS - * - ETH_TXQ_FLAGS_NOVLANOFFL - * - ETH_TXQ_FLAGS_NOXSUMSCTP - * - ETH_TXQ_FLAGS_NOXSUMUDP - * - ETH_TXQ_FLAGS_NOXSUMTCP - * and that the RS bit threshold (tx_rs_thresh) is at least equal to - * RTE_PMD_IXGBE_TX_MAX_BURST. - */ -#define IXGBE_SIMPLE_FLAGS ((uint32_t)ETH_TXQ_FLAGS_NOMULTSEGS | \ - ETH_TXQ_FLAGS_NOOFFLOADS) - /* * Check for descriptors with their DD bit set and free mbufs. * Return the total number of buffers freed. */ static inline int __attribute__((always_inline)) -ixgbe_tx_free_bufs(struct igb_tx_queue *txq) +ixgbe_tx_free_bufs(struct ixgbe_tx_queue *txq) { - struct igb_tx_entry *txep; + struct ixgbe_tx_entry *txep; uint32_t status; int i; @@ -266,13 +139,10 @@ ixgbe_tx_free_bufs(struct igb_tx_queue *txq) */ txep = &(txq->sw_ring[txq->tx_next_dd - (txq->tx_rs_thresh - 1)]); - /* prefetch the mbufs that are about to be freed */ - for (i = 0; i < txq->tx_rs_thresh; ++i) - rte_prefetch0((txep + i)->mbuf); - /* free buffers one at a time */ if ((txq->txq_flags & (uint32_t)ETH_TXQ_FLAGS_NOREFCOUNT) != 0) { for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) { + txep->mbuf->next = NULL; rte_mempool_put(txep->mbuf->pool, txep->mbuf); txep->mbuf = NULL; } @@ -292,19 +162,6 @@ ixgbe_tx_free_bufs(struct igb_tx_queue *txq) return txq->tx_rs_thresh; } -/* - * Populate descriptors with the following info: - * 1.) buffer_addr = phys_addr + headroom - * 2.) cmd_type_len = DCMD_DTYP_FLAGS | pkt_len - * 3.) olinfo_status = pkt_len << PAYLEN_SHIFT - */ - -/* Defines for Tx descriptor */ -#define DCMD_DTYP_FLAGS (IXGBE_ADVTXD_DTYP_DATA |\ - IXGBE_ADVTXD_DCMD_IFCS |\ - IXGBE_ADVTXD_DCMD_DEXT |\ - IXGBE_ADVTXD_DCMD_EOP) - /* Populate 4 descriptors with data from 4 mbufs */ static inline void tx4(volatile union ixgbe_adv_tx_desc *txdp, struct rte_mbuf **pkts) @@ -315,7 +172,7 @@ tx4(volatile union ixgbe_adv_tx_desc *txdp, struct rte_mbuf **pkts) for (i = 0; i < 4; ++i, ++txdp, ++pkts) { buf_dma_addr = RTE_MBUF_DATA_DMA_ADDR(*pkts); - pkt_len = (*pkts)->pkt.data_len; + pkt_len = (*pkts)->data_len; /* write data to descriptor */ txdp->read.buffer_addr = buf_dma_addr; @@ -323,6 +180,7 @@ tx4(volatile union ixgbe_adv_tx_desc *txdp, struct rte_mbuf **pkts) ((uint32_t)DCMD_DTYP_FLAGS | pkt_len); txdp->read.olinfo_status = (pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); + rte_prefetch0(&(*pkts)->pool); } } @@ -334,7 +192,7 @@ tx1(volatile union ixgbe_adv_tx_desc *txdp, struct rte_mbuf **pkts) uint32_t pkt_len; buf_dma_addr = RTE_MBUF_DATA_DMA_ADDR(*pkts); - pkt_len = (*pkts)->pkt.data_len; + pkt_len = (*pkts)->data_len; /* write data to descriptor */ txdp->read.buffer_addr = buf_dma_addr; @@ -342,6 +200,7 @@ tx1(volatile union ixgbe_adv_tx_desc *txdp, struct rte_mbuf **pkts) ((uint32_t)DCMD_DTYP_FLAGS | pkt_len); txdp->read.olinfo_status = (pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); + rte_prefetch0(&(*pkts)->pool); } /* @@ -349,11 +208,11 @@ tx1(volatile union ixgbe_adv_tx_desc *txdp, struct rte_mbuf **pkts) * Copy mbuf pointers to the S/W ring. */ static inline void -ixgbe_tx_fill_hw_ring(struct igb_tx_queue *txq, struct rte_mbuf **pkts, +ixgbe_tx_fill_hw_ring(struct ixgbe_tx_queue *txq, struct rte_mbuf **pkts, uint16_t nb_pkts) { volatile union ixgbe_adv_tx_desc *txdp = &(txq->tx_ring[txq->tx_tail]); - struct igb_tx_entry *txep = &(txq->sw_ring[txq->tx_tail]); + struct ixgbe_tx_entry *txep = &(txq->sw_ring[txq->tx_tail]); const int N_PER_LOOP = 4; const int N_PER_LOOP_MASK = N_PER_LOOP-1; int mainpart, leftover; @@ -385,7 +244,7 @@ static inline uint16_t tx_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) { - struct igb_tx_queue *txq = (struct igb_tx_queue *)tx_queue; + struct ixgbe_tx_queue *txq = (struct ixgbe_tx_queue *)tx_queue; volatile union ixgbe_adv_tx_desc *tx_r = txq->tx_ring; uint16_t n = 0; @@ -493,61 +352,86 @@ ixgbe_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts, } static inline void -ixgbe_set_xmit_ctx(struct igb_tx_queue* txq, +ixgbe_set_xmit_ctx(struct ixgbe_tx_queue *txq, volatile struct ixgbe_adv_tx_context_desc *ctx_txd, - uint16_t ol_flags, uint32_t vlan_macip_lens) + uint64_t ol_flags, union ixgbe_tx_offload tx_offload) { uint32_t type_tucmd_mlhl; - uint32_t mss_l4len_idx; + uint32_t mss_l4len_idx = 0; uint32_t ctx_idx; - uint32_t cmp_mask; + uint32_t vlan_macip_lens; + union ixgbe_tx_offload tx_offload_mask; ctx_idx = txq->ctx_curr; - cmp_mask = 0; + tx_offload_mask.data = 0; type_tucmd_mlhl = 0; + /* Specify which HW CTX to upload. */ + mss_l4len_idx |= (ctx_idx << IXGBE_ADVTXD_IDX_SHIFT); + if (ol_flags & PKT_TX_VLAN_PKT) { - cmp_mask |= TX_VLAN_CMP_MASK; + tx_offload_mask.vlan_tci |= ~0; } - if (ol_flags & PKT_TX_IP_CKSUM) { - type_tucmd_mlhl = IXGBE_ADVTXD_TUCMD_IPV4; - cmp_mask |= TX_MAC_LEN_CMP_MASK; - } + /* check if TCP segmentation required for this packet */ + if (ol_flags & PKT_TX_TCP_SEG) { + /* implies IP cksum and TCP cksum */ + type_tucmd_mlhl = IXGBE_ADVTXD_TUCMD_IPV4 | + IXGBE_ADVTXD_TUCMD_L4T_TCP | + IXGBE_ADVTXD_DTYP_CTXT | IXGBE_ADVTXD_DCMD_DEXT; + + tx_offload_mask.l2_len |= ~0; + tx_offload_mask.l3_len |= ~0; + tx_offload_mask.l4_len |= ~0; + tx_offload_mask.tso_segsz |= ~0; + mss_l4len_idx |= tx_offload.tso_segsz << IXGBE_ADVTXD_MSS_SHIFT; + mss_l4len_idx |= tx_offload.l4_len << IXGBE_ADVTXD_L4LEN_SHIFT; + } else { /* no TSO, check if hardware checksum is needed */ + if (ol_flags & PKT_TX_IP_CKSUM) { + type_tucmd_mlhl = IXGBE_ADVTXD_TUCMD_IPV4; + tx_offload_mask.l2_len |= ~0; + tx_offload_mask.l3_len |= ~0; + } - /* Specify which HW CTX to upload. */ - mss_l4len_idx = (ctx_idx << IXGBE_ADVTXD_IDX_SHIFT); - switch (ol_flags & PKT_TX_L4_MASK) { - case PKT_TX_UDP_CKSUM: - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_UDP | + switch (ol_flags & PKT_TX_L4_MASK) { + case PKT_TX_UDP_CKSUM: + type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_UDP | IXGBE_ADVTXD_DTYP_CTXT | IXGBE_ADVTXD_DCMD_DEXT; - mss_l4len_idx |= sizeof(struct udp_hdr) << IXGBE_ADVTXD_L4LEN_SHIFT; - cmp_mask |= TX_MACIP_LEN_CMP_MASK; - break; - case PKT_TX_TCP_CKSUM: - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP | + mss_l4len_idx |= sizeof(struct udp_hdr) << IXGBE_ADVTXD_L4LEN_SHIFT; + tx_offload_mask.l2_len |= ~0; + tx_offload_mask.l3_len |= ~0; + break; + case PKT_TX_TCP_CKSUM: + type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP | IXGBE_ADVTXD_DTYP_CTXT | IXGBE_ADVTXD_DCMD_DEXT; - mss_l4len_idx |= sizeof(struct tcp_hdr) << IXGBE_ADVTXD_L4LEN_SHIFT; - cmp_mask |= TX_MACIP_LEN_CMP_MASK; - break; - case PKT_TX_SCTP_CKSUM: - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_SCTP | + mss_l4len_idx |= sizeof(struct tcp_hdr) << IXGBE_ADVTXD_L4LEN_SHIFT; + tx_offload_mask.l2_len |= ~0; + tx_offload_mask.l3_len |= ~0; + tx_offload_mask.l4_len |= ~0; + break; + case PKT_TX_SCTP_CKSUM: + type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_SCTP | IXGBE_ADVTXD_DTYP_CTXT | IXGBE_ADVTXD_DCMD_DEXT; - mss_l4len_idx |= sizeof(struct sctp_hdr) << IXGBE_ADVTXD_L4LEN_SHIFT; - cmp_mask |= TX_MACIP_LEN_CMP_MASK; - break; - default: - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_RSV | + mss_l4len_idx |= sizeof(struct sctp_hdr) << IXGBE_ADVTXD_L4LEN_SHIFT; + tx_offload_mask.l2_len |= ~0; + tx_offload_mask.l3_len |= ~0; + break; + default: + type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_RSV | IXGBE_ADVTXD_DTYP_CTXT | IXGBE_ADVTXD_DCMD_DEXT; - break; + break; + } } txq->ctx_cache[ctx_idx].flags = ol_flags; - txq->ctx_cache[ctx_idx].cmp_mask = cmp_mask; - txq->ctx_cache[ctx_idx].vlan_macip_lens.data = - vlan_macip_lens & cmp_mask; + txq->ctx_cache[ctx_idx].tx_offload.data = + tx_offload_mask.data & tx_offload.data; + txq->ctx_cache[ctx_idx].tx_offload_mask = tx_offload_mask; ctx_txd->type_tucmd_mlhl = rte_cpu_to_le_32(type_tucmd_mlhl); + vlan_macip_lens = tx_offload.l3_len; + vlan_macip_lens |= (tx_offload.l2_len << IXGBE_ADVTXD_MACLEN_SHIFT); + vlan_macip_lens |= ((uint32_t)tx_offload.vlan_tci << IXGBE_ADVTXD_VLAN_SHIFT); ctx_txd->vlan_macip_lens = rte_cpu_to_le_32(vlan_macip_lens); ctx_txd->mss_l4len_idx = rte_cpu_to_le_32(mss_l4len_idx); ctx_txd->seqnum_seed = 0; @@ -558,21 +442,21 @@ ixgbe_set_xmit_ctx(struct igb_tx_queue* txq, * or create a new context descriptor. */ static inline uint32_t -what_advctx_update(struct igb_tx_queue *txq, uint16_t flags, - uint32_t vlan_macip_lens) +what_advctx_update(struct ixgbe_tx_queue *txq, uint64_t flags, + union ixgbe_tx_offload tx_offload) { /* If match with the current used context */ if (likely((txq->ctx_cache[txq->ctx_curr].flags == flags) && - (txq->ctx_cache[txq->ctx_curr].vlan_macip_lens.data == - (txq->ctx_cache[txq->ctx_curr].cmp_mask & vlan_macip_lens)))) { + (txq->ctx_cache[txq->ctx_curr].tx_offload.data == + (txq->ctx_cache[txq->ctx_curr].tx_offload_mask.data & tx_offload.data)))) { return txq->ctx_curr; } /* What if match with the next context */ txq->ctx_curr ^= 1; if (likely((txq->ctx_cache[txq->ctx_curr].flags == flags) && - (txq->ctx_cache[txq->ctx_curr].vlan_macip_lens.data == - (txq->ctx_cache[txq->ctx_curr].cmp_mask & vlan_macip_lens)))) { + (txq->ctx_cache[txq->ctx_curr].tx_offload.data == + (txq->ctx_cache[txq->ctx_curr].tx_offload_mask.data & tx_offload.data)))) { return txq->ctx_curr; } @@ -581,22 +465,27 @@ what_advctx_update(struct igb_tx_queue *txq, uint16_t flags, } static inline uint32_t -tx_desc_cksum_flags_to_olinfo(uint16_t ol_flags) +tx_desc_cksum_flags_to_olinfo(uint64_t ol_flags) { - static const uint32_t l4_olinfo[2] = {0, IXGBE_ADVTXD_POPTS_TXSM}; - static const uint32_t l3_olinfo[2] = {0, IXGBE_ADVTXD_POPTS_IXSM}; - uint32_t tmp; - - tmp = l4_olinfo[(ol_flags & PKT_TX_L4_MASK) != PKT_TX_L4_NO_CKSUM]; - tmp |= l3_olinfo[(ol_flags & PKT_TX_IP_CKSUM) != 0]; + uint32_t tmp = 0; + if ((ol_flags & PKT_TX_L4_MASK) != PKT_TX_L4_NO_CKSUM) + tmp |= IXGBE_ADVTXD_POPTS_TXSM; + if (ol_flags & PKT_TX_IP_CKSUM) + tmp |= IXGBE_ADVTXD_POPTS_IXSM; + if (ol_flags & PKT_TX_TCP_SEG) + tmp |= IXGBE_ADVTXD_POPTS_TXSM; return tmp; } static inline uint32_t -tx_desc_vlan_flags_to_cmdtype(uint16_t ol_flags) +tx_desc_ol_flags_to_cmdtype(uint64_t ol_flags) { - static const uint32_t vlan_cmd[2] = {0, IXGBE_ADVTXD_DCMD_VLE}; - return vlan_cmd[(ol_flags & PKT_TX_VLAN_PKT) != 0]; + uint32_t cmdtype = 0; + if (ol_flags & PKT_TX_VLAN_PKT) + cmdtype |= IXGBE_ADVTXD_DCMD_VLE; + if (ol_flags & PKT_TX_TCP_SEG) + cmdtype |= IXGBE_ADVTXD_DCMD_TSE; + return cmdtype; } /* Default RS bit threshold values */ @@ -609,9 +498,9 @@ tx_desc_vlan_flags_to_cmdtype(uint16_t ol_flags) /* Reset transmit descriptors after they have been used */ static inline int -ixgbe_xmit_cleanup(struct igb_tx_queue *txq) +ixgbe_xmit_cleanup(struct ixgbe_tx_queue *txq) { - struct igb_tx_entry *sw_ring = txq->sw_ring; + struct ixgbe_tx_entry *sw_ring = txq->sw_ring; volatile union ixgbe_adv_tx_desc *txr = txq->tx_ring; uint16_t last_desc_cleaned = txq->last_desc_cleaned; uint16_t nb_tx_desc = txq->nb_tx_desc; @@ -670,9 +559,9 @@ uint16_t ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) { - struct igb_tx_queue *txq; - struct igb_tx_entry *sw_ring; - struct igb_tx_entry *txe, *txn; + struct ixgbe_tx_queue *txq; + struct ixgbe_tx_entry *sw_ring; + struct ixgbe_tx_entry *txe, *txn; volatile union ixgbe_adv_tx_desc *txr; volatile union ixgbe_adv_tx_desc *txd; struct rte_mbuf *tx_pkt; @@ -682,15 +571,15 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint32_t cmd_type_len; uint32_t pkt_len; uint16_t slen; - uint16_t ol_flags; + uint64_t ol_flags; uint16_t tx_id; uint16_t tx_last; uint16_t nb_tx; uint16_t nb_used; - uint16_t tx_ol_req; - uint32_t vlan_macip_lens; + uint64_t tx_ol_req; uint32_t ctx = 0; uint32_t new_ctx; + union ixgbe_tx_offload tx_offload = {0}; txq = tx_queue; sw_ring = txq->sw_ring; @@ -703,27 +592,32 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, ixgbe_xmit_cleanup(txq); } + rte_prefetch0(&txe->mbuf->pool); + /* TX loop */ for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) { new_ctx = 0; tx_pkt = *tx_pkts++; - pkt_len = tx_pkt->pkt.pkt_len; - - RTE_MBUF_PREFETCH_TO_FREE(txe->mbuf); + pkt_len = tx_pkt->pkt_len; /* * Determine how many (if any) context descriptors * are needed for offload functionality. */ ol_flags = tx_pkt->ol_flags; - vlan_macip_lens = tx_pkt->pkt.vlan_macip.data; /* If hardware offload required */ - tx_ol_req = (uint16_t)(ol_flags & PKT_TX_OFFLOAD_MASK); + tx_ol_req = ol_flags & IXGBE_TX_OFFLOAD_MASK; if (tx_ol_req) { + tx_offload.l2_len = tx_pkt->l2_len; + tx_offload.l3_len = tx_pkt->l3_len; + tx_offload.l4_len = tx_pkt->l4_len; + tx_offload.vlan_tci = tx_pkt->vlan_tci; + tx_offload.tso_segsz = tx_pkt->tso_segsz; + /* If new context need be built or reuse the exist ctx. */ ctx = what_advctx_update(txq, tx_ol_req, - vlan_macip_lens); + tx_offload); /* Only allocate context descriptor if required*/ new_ctx = (ctx == IXGBE_CTX_NUM); ctx = txq->ctx_curr; @@ -734,7 +628,7 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, * This will always be the number of segments + the number of * Context descriptors required to transmit the packet */ - nb_used = (uint16_t)(tx_pkt->pkt.nb_segs + new_ctx); + nb_used = (uint16_t)(tx_pkt->nb_segs + new_ctx); /* * The number of descriptors that must be allocated for a @@ -751,7 +645,7 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, tx_last = (uint16_t) (tx_last - txq->nb_tx_desc); PMD_TX_LOG(DEBUG, "port_id=%u queue_id=%u pktlen=%u" - " tx_first=%u tx_last=%u\n", + " tx_first=%u tx_last=%u", (unsigned) txq->port_id, (unsigned) txq->queue_id, (unsigned) pkt_len, @@ -838,13 +732,22 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, */ cmd_type_len = IXGBE_ADVTXD_DTYP_DATA | IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT; - olinfo_status = (pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); + #ifdef RTE_LIBRTE_IEEE1588 if (ol_flags & PKT_TX_IEEE1588_TMST) cmd_type_len |= IXGBE_ADVTXD_MAC_1588; #endif + olinfo_status = 0; if (tx_ol_req) { + + if (ol_flags & PKT_TX_TCP_SEG) { + /* when TSO is on, paylen in descriptor is the + * not the packet len but the tcp payload len */ + pkt_len -= (tx_offload.l2_len + + tx_offload.l3_len + tx_offload.l4_len); + } + /* * Setup the TX Advanced Context Descriptor if required */ @@ -857,7 +760,7 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, &txr[tx_id]; txn = &sw_ring[txe->next_id]; - RTE_MBUF_PREFETCH_TO_FREE(txn->mbuf); + rte_prefetch0(&txn->mbuf->pool); if (txe->mbuf != NULL) { rte_pktmbuf_free_seg(txe->mbuf); @@ -865,7 +768,7 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, } ixgbe_set_xmit_ctx(txq, ctx_txd, tx_ol_req, - vlan_macip_lens); + tx_offload); txe->last_id = tx_last; tx_id = txe->next_id; @@ -877,15 +780,18 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, * This path will go through * whatever new/reuse the context descriptor */ - cmd_type_len |= tx_desc_vlan_flags_to_cmdtype(ol_flags); + cmd_type_len |= tx_desc_ol_flags_to_cmdtype(ol_flags); olinfo_status |= tx_desc_cksum_flags_to_olinfo(ol_flags); olinfo_status |= ctx << IXGBE_ADVTXD_IDX_SHIFT; } + olinfo_status |= (pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); + m_seg = tx_pkt; do { txd = &txr[tx_id]; txn = &sw_ring[txe->next_id]; + rte_prefetch0(&txn->mbuf->pool); if (txe->mbuf != NULL) rte_pktmbuf_free_seg(txe->mbuf); @@ -894,7 +800,7 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, /* * Set up Transmit Data Descriptor. */ - slen = m_seg->pkt.data_len; + slen = m_seg->data_len; buf_dma_addr = RTE_MBUF_DATA_DMA_ADDR(m_seg); txd->read.buffer_addr = rte_cpu_to_le_64(buf_dma_addr); @@ -905,7 +811,7 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, txe->last_id = tx_last; tx_id = txe->next_id; txe = txn; - m_seg = m_seg->pkt.next; + m_seg = m_seg->next; } while (m_seg != NULL); /* @@ -949,19 +855,19 @@ end_of_tx: * RX functions * **********************************************************************/ -static inline uint16_t +static inline uint64_t rx_desc_hlen_type_rss_to_pkt_flags(uint32_t hl_tp_rs) { - uint16_t pkt_flags; + uint64_t pkt_flags; - static uint16_t ip_pkt_types_map[16] = { + static const uint64_t ip_pkt_types_map[16] = { 0, PKT_RX_IPV4_HDR, PKT_RX_IPV4_HDR_EXT, PKT_RX_IPV4_HDR_EXT, PKT_RX_IPV6_HDR, 0, 0, 0, PKT_RX_IPV6_HDR_EXT, 0, 0, 0, PKT_RX_IPV6_HDR_EXT, 0, 0, 0, }; - static uint16_t ip_rss_types_map[16] = { + static const uint64_t ip_rss_types_map[16] = { 0, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, 0, 0, 0, @@ -969,50 +875,49 @@ rx_desc_hlen_type_rss_to_pkt_flags(uint32_t hl_tp_rs) }; #ifdef RTE_LIBRTE_IEEE1588 - static uint32_t ip_pkt_etqf_map[8] = { + static uint64_t ip_pkt_etqf_map[8] = { 0, 0, 0, PKT_RX_IEEE1588_PTP, 0, 0, 0, 0, }; - pkt_flags = (uint16_t) ((hl_tp_rs & IXGBE_RXDADV_PKTTYPE_ETQF) ? - ip_pkt_etqf_map[(hl_tp_rs >> 4) & 0x07] : - ip_pkt_types_map[(hl_tp_rs >> 4) & 0x0F]); + pkt_flags = (hl_tp_rs & IXGBE_RXDADV_PKTTYPE_ETQF) ? + ip_pkt_etqf_map[(hl_tp_rs >> 4) & 0x07] : + ip_pkt_types_map[(hl_tp_rs >> 4) & 0x0F]; #else - pkt_flags = (uint16_t) ((hl_tp_rs & IXGBE_RXDADV_PKTTYPE_ETQF) ? 0 : - ip_pkt_types_map[(hl_tp_rs >> 4) & 0x0F]); + pkt_flags = (hl_tp_rs & IXGBE_RXDADV_PKTTYPE_ETQF) ? 0 : + ip_pkt_types_map[(hl_tp_rs >> 4) & 0x0F]; #endif - return (uint16_t)(pkt_flags | ip_rss_types_map[hl_tp_rs & 0xF]); + return pkt_flags | ip_rss_types_map[hl_tp_rs & 0xF]; } -static inline uint16_t +static inline uint64_t rx_desc_status_to_pkt_flags(uint32_t rx_status) { - uint16_t pkt_flags; + uint64_t pkt_flags; /* * Check if VLAN present only. * Do not check whether L3/L4 rx checksum done by NIC or not, * That can be found from rte_eth_rxmode.hw_ip_checksum flag */ - pkt_flags = (uint16_t)((rx_status & IXGBE_RXD_STAT_VP) ? - PKT_RX_VLAN_PKT : 0); + pkt_flags = (rx_status & IXGBE_RXD_STAT_VP) ? PKT_RX_VLAN_PKT : 0; #ifdef RTE_LIBRTE_IEEE1588 if (rx_status & IXGBE_RXD_STAT_TMST) - pkt_flags = (uint16_t)(pkt_flags | PKT_RX_IEEE1588_TMST); + pkt_flags = pkt_flags | PKT_RX_IEEE1588_TMST; #endif return pkt_flags; } -static inline uint16_t +static inline uint64_t rx_desc_error_to_pkt_flags(uint32_t rx_status) { /* * Bit 31: IPE, IPv4 checksum error * Bit 30: L4I, L4I integrity error */ - static uint16_t error_to_pkt_flags_map[4] = { + static uint64_t error_to_pkt_flags_map[4] = { 0, PKT_RX_L4_CKSUM_BAD, PKT_RX_IP_CKSUM_BAD, PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD }; @@ -1023,7 +928,7 @@ rx_desc_error_to_pkt_flags(uint32_t rx_status) #ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC /* * LOOK_AHEAD defines how many desc statuses to check beyond the - * current descriptor. + * current descriptor. * It must be a pound define for optimal performance. * Do not change the value of LOOK_AHEAD, as the ixgbe_rx_scan_hw_ring * function only works with LOOK_AHEAD=8. @@ -1033,12 +938,13 @@ rx_desc_error_to_pkt_flags(uint32_t rx_status) #error "PMD IXGBE: LOOK_AHEAD must be 8\n" #endif static inline int -ixgbe_rx_scan_hw_ring(struct igb_rx_queue *rxq) +ixgbe_rx_scan_hw_ring(struct ixgbe_rx_queue *rxq) { volatile union ixgbe_adv_rx_desc *rxdp; - struct igb_rx_entry *rxep; + struct ixgbe_rx_entry *rxep; struct rte_mbuf *mb; uint16_t pkt_len; + uint64_t pkt_flags; int s[LOOK_AHEAD], nb_dd; int i, j, nb_rx = 0; @@ -1062,32 +968,38 @@ ixgbe_rx_scan_hw_ring(struct igb_rx_queue *rxq) for (j = LOOK_AHEAD-1; j >= 0; --j) s[j] = rxdp[j].wb.upper.status_error; - /* Clear everything but the status bits (LSB) */ + /* Compute how many status bits were set */ + nb_dd = 0; for (j = 0; j < LOOK_AHEAD; ++j) - s[j] &= IXGBE_RXDADV_STAT_DD; + nb_dd += s[j] & IXGBE_RXDADV_STAT_DD; - /* Compute how many status bits were set */ - nb_dd = s[0]+s[1]+s[2]+s[3]+s[4]+s[5]+s[6]+s[7]; nb_rx += nb_dd; /* Translate descriptor info to mbuf format */ for (j = 0; j < nb_dd; ++j) { mb = rxep[j].mbuf; - pkt_len = (uint16_t)(rxdp[j].wb.upper.length - - rxq->crc_len); - mb->pkt.data_len = pkt_len; - mb->pkt.pkt_len = pkt_len; - mb->pkt.vlan_macip.f.vlan_tci = rxdp[j].wb.upper.vlan; - mb->pkt.hash.rss = rxdp[j].wb.lower.hi_dword.rss; + pkt_len = (uint16_t)(rxdp[j].wb.upper.length - rxq->crc_len); + mb->data_len = pkt_len; + mb->pkt_len = pkt_len; + mb->vlan_tci = rxdp[j].wb.upper.vlan; + mb->vlan_tci = rte_le_to_cpu_16(rxdp[j].wb.upper.vlan); /* convert descriptor fields to rte mbuf flags */ - mb->ol_flags = rx_desc_hlen_type_rss_to_pkt_flags( + pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags( rxdp[j].wb.lower.lo_dword.data); /* reuse status field from scan list */ - mb->ol_flags = (uint16_t)(mb->ol_flags | - rx_desc_status_to_pkt_flags(s[j])); - mb->ol_flags = (uint16_t)(mb->ol_flags | - rx_desc_error_to_pkt_flags(s[j])); + pkt_flags |= rx_desc_status_to_pkt_flags(s[j]); + pkt_flags |= rx_desc_error_to_pkt_flags(s[j]); + mb->ol_flags = pkt_flags; + + if (likely(pkt_flags & PKT_RX_RSS_HASH)) + mb->hash.rss = rxdp[j].wb.lower.hi_dword.rss; + else if (pkt_flags & PKT_RX_FDIR) { + mb->hash.fdir.hash = + (uint16_t)((rxdp[j].wb.lower.hi_dword.csum_ip.csum) + & IXGBE_ATR_HASH_MASK); + mb->hash.fdir.id = rxdp[j].wb.lower.hi_dword.csum_ip.ip_id; + } } /* Move mbuf pointers from the S/W ring to the stage */ @@ -1110,18 +1022,17 @@ ixgbe_rx_scan_hw_ring(struct igb_rx_queue *rxq) } static inline int -ixgbe_rx_alloc_bufs(struct igb_rx_queue *rxq) +ixgbe_rx_alloc_bufs(struct ixgbe_rx_queue *rxq, bool reset_mbuf) { volatile union ixgbe_adv_rx_desc *rxdp; - struct igb_rx_entry *rxep; + struct ixgbe_rx_entry *rxep; struct rte_mbuf *mb; uint16_t alloc_idx; - uint64_t dma_addr; + __le64 dma_addr; int diag, i; /* allocate buffers in bulk directly into the S/W ring */ - alloc_idx = (uint16_t)(rxq->rx_free_trigger - - (rxq->rx_free_thresh - 1)); + alloc_idx = rxq->rx_free_trigger - (rxq->rx_free_thresh - 1); rxep = &rxq->sw_ring[alloc_idx]; diag = rte_mempool_get_bulk(rxq->mb_pool, (void *)rxep, rxq->rx_free_thresh); @@ -1132,35 +1043,32 @@ ixgbe_rx_alloc_bufs(struct igb_rx_queue *rxq) for (i = 0; i < rxq->rx_free_thresh; ++i) { /* populate the static rte mbuf fields */ mb = rxep[i].mbuf; + if (reset_mbuf) { + mb->next = NULL; + mb->nb_segs = 1; + mb->port = rxq->port_id; + } + rte_mbuf_refcnt_set(mb, 1); - mb->type = RTE_MBUF_PKT; - mb->pkt.next = NULL; - mb->pkt.data = (char *)mb->buf_addr + RTE_PKTMBUF_HEADROOM; - mb->pkt.nb_segs = 1; - mb->pkt.in_port = rxq->port_id; + mb->data_off = RTE_PKTMBUF_HEADROOM; /* populate the descriptors */ - dma_addr = (uint64_t)mb->buf_physaddr + RTE_PKTMBUF_HEADROOM; + dma_addr = rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mb)); rxdp[i].read.hdr_addr = dma_addr; rxdp[i].read.pkt_addr = dma_addr; } - /* update tail pointer */ - rte_wmb(); - IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rxq->rx_free_trigger); - /* update state of internal queue structure */ - rxq->rx_free_trigger = (uint16_t)(rxq->rx_free_trigger + - rxq->rx_free_thresh); + rxq->rx_free_trigger = rxq->rx_free_trigger + rxq->rx_free_thresh; if (rxq->rx_free_trigger >= rxq->nb_rx_desc) - rxq->rx_free_trigger = (uint16_t)(rxq->rx_free_thresh - 1); + rxq->rx_free_trigger = rxq->rx_free_thresh - 1; /* no errors */ return 0; } static inline uint16_t -ixgbe_rx_fill_from_stage(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts, +ixgbe_rx_fill_from_stage(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) { struct rte_mbuf **stage = &rxq->rx_stage[rxq->rx_next_avail]; @@ -1184,7 +1092,7 @@ static inline uint16_t rx_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) { - struct igb_rx_queue *rxq = (struct igb_rx_queue *)rx_queue; + struct ixgbe_rx_queue *rxq = (struct ixgbe_rx_queue *)rx_queue; uint16_t nb_rx = 0; /* Any previously recv'd pkts will be returned from the Rx stage */ @@ -1201,10 +1109,12 @@ rx_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, /* if required, allocate new buffers to replenish descriptors */ if (rxq->rx_tail > rxq->rx_free_trigger) { - if (ixgbe_rx_alloc_bufs(rxq) != 0) { + uint16_t cur_free_trigger = rxq->rx_free_trigger; + + if (ixgbe_rx_alloc_bufs(rxq, true) != 0) { int i, j; PMD_RX_LOG(DEBUG, "RX mbuf alloc failed port_id=%u " - "queue_id=%u\n", (unsigned) rxq->port_id, + "queue_id=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id); rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed += @@ -1221,6 +1131,10 @@ rx_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, return 0; } + + /* update tail pointer */ + rte_wmb(); + IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, cur_free_trigger); } if (rxq->rx_tail >= rxq->nb_rx_desc) @@ -1234,7 +1148,7 @@ rx_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, } /* split requests into chunks of size RTE_PMD_IXGBE_RX_MAX_BURST */ -uint16_t +static uint16_t ixgbe_recv_pkts_bulk_alloc(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) { @@ -1260,17 +1174,34 @@ ixgbe_recv_pkts_bulk_alloc(void *rx_queue, struct rte_mbuf **rx_pkts, return nb_rx; } + +#else + +/* Stub to avoid extra ifdefs */ +static uint16_t +ixgbe_recv_pkts_bulk_alloc(__rte_unused void *rx_queue, + __rte_unused struct rte_mbuf **rx_pkts, __rte_unused uint16_t nb_pkts) +{ + return 0; +} + +static inline int +ixgbe_rx_alloc_bufs(__rte_unused struct ixgbe_rx_queue *rxq, + __rte_unused bool reset_mbuf) +{ + return -ENOMEM; +} #endif /* RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC */ uint16_t ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) { - struct igb_rx_queue *rxq; + struct ixgbe_rx_queue *rxq; volatile union ixgbe_adv_rx_desc *rx_ring; volatile union ixgbe_adv_rx_desc *rxdp; - struct igb_rx_entry *sw_ring; - struct igb_rx_entry *rxe; + struct ixgbe_rx_entry *sw_ring; + struct ixgbe_rx_entry *rxe; struct rte_mbuf *rxm; struct rte_mbuf *nmb; union ixgbe_adv_rx_desc rxd; @@ -1281,7 +1212,7 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t rx_id; uint16_t nb_rx; uint16_t nb_hold; - uint16_t pkt_flags; + uint64_t pkt_flags; nb_rx = 0; nb_hold = 0; @@ -1331,7 +1262,7 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, * frames to its peer(s). */ PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_id=%u " - "ext_err_stat=0x%08x pkt_len=%u\n", + "ext_err_stat=0x%08x pkt_len=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id, (unsigned) rx_id, (unsigned) staterr, (unsigned) rte_le_to_cpu_16(rxd.wb.upper.length)); @@ -1339,7 +1270,7 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, nmb = rte_rxmbuf_alloc(rxq->mb_pool); if (nmb == NULL) { PMD_RX_LOG(DEBUG, "RX mbuf alloc failed port_id=%u " - "queue_id=%u\n", (unsigned) rxq->port_id, + "queue_id=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id); rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed++; break; @@ -1386,33 +1317,30 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, */ pkt_len = (uint16_t) (rte_le_to_cpu_16(rxd.wb.upper.length) - rxq->crc_len); - rxm->pkt.data = (char*) rxm->buf_addr + RTE_PKTMBUF_HEADROOM; - rte_packet_prefetch(rxm->pkt.data); - rxm->pkt.nb_segs = 1; - rxm->pkt.next = NULL; - rxm->pkt.pkt_len = pkt_len; - rxm->pkt.data_len = pkt_len; - rxm->pkt.in_port = rxq->port_id; + rxm->data_off = RTE_PKTMBUF_HEADROOM; + rte_packet_prefetch((char *)rxm->buf_addr + rxm->data_off); + rxm->nb_segs = 1; + rxm->next = NULL; + rxm->pkt_len = pkt_len; + rxm->data_len = pkt_len; + rxm->port = rxq->port_id; hlen_type_rss = rte_le_to_cpu_32(rxd.wb.lower.lo_dword.data); /* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */ - rxm->pkt.vlan_macip.f.vlan_tci = - rte_le_to_cpu_16(rxd.wb.upper.vlan); + rxm->vlan_tci = rte_le_to_cpu_16(rxd.wb.upper.vlan); pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss); - pkt_flags = (uint16_t)(pkt_flags | - rx_desc_status_to_pkt_flags(staterr)); - pkt_flags = (uint16_t)(pkt_flags | - rx_desc_error_to_pkt_flags(staterr)); + pkt_flags = pkt_flags | rx_desc_status_to_pkt_flags(staterr); + pkt_flags = pkt_flags | rx_desc_error_to_pkt_flags(staterr); rxm->ol_flags = pkt_flags; if (likely(pkt_flags & PKT_RX_RSS_HASH)) - rxm->pkt.hash.rss = rxd.wb.lower.hi_dword.rss; + rxm->hash.rss = rxd.wb.lower.hi_dword.rss; else if (pkt_flags & PKT_RX_FDIR) { - rxm->pkt.hash.fdir.hash = + rxm->hash.fdir.hash = (uint16_t)((rxd.wb.lower.hi_dword.csum_ip.csum) & IXGBE_ATR_HASH_MASK); - rxm->pkt.hash.fdir.id = rxd.wb.lower.hi_dword.csum_ip.ip_id; + rxm->hash.fdir.id = rxd.wb.lower.hi_dword.csum_ip.ip_id; } /* * Store the mbuf address into the next entry of the array @@ -1434,7 +1362,7 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, nb_hold = (uint16_t) (nb_hold + rxq->nb_rx_hold); if (nb_hold > rxq->rx_free_thresh) { PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_tail=%u " - "nb_hold=%u nb_rx=%u\n", + "nb_hold=%u nb_rx=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id, (unsigned) rx_id, (unsigned) nb_hold, (unsigned) nb_rx); @@ -1447,15 +1375,362 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, return (nb_rx); } +/** + * Detect an RSC descriptor. + */ +static inline uint32_t +ixgbe_rsc_count(union ixgbe_adv_rx_desc *rx) +{ + return (rte_le_to_cpu_32(rx->wb.lower.lo_dword.data) & + IXGBE_RXDADV_RSCCNT_MASK) >> IXGBE_RXDADV_RSCCNT_SHIFT; +} + +/** + * ixgbe_fill_cluster_head_buf - fill the first mbuf of the returned packet + * + * Fill the following info in the HEAD buffer of the Rx cluster: + * - RX port identifier + * - hardware offload data, if any: + * - RSS flag & hash + * - IP checksum flag + * - VLAN TCI, if any + * - error flags + * @head HEAD of the packet cluster + * @desc HW descriptor to get data from + * @port_id Port ID of the Rx queue + */ +static inline void +ixgbe_fill_cluster_head_buf( + struct rte_mbuf *head, + union ixgbe_adv_rx_desc *desc, + uint8_t port_id, + uint32_t staterr) +{ + uint32_t hlen_type_rss; + uint64_t pkt_flags; + + head->port = port_id; + + /* + * The vlan_tci field is only valid when PKT_RX_VLAN_PKT is + * set in the pkt_flags field. + */ + head->vlan_tci = rte_le_to_cpu_16(desc->wb.upper.vlan); + hlen_type_rss = rte_le_to_cpu_32(desc->wb.lower.lo_dword.data); + pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss); + pkt_flags |= rx_desc_status_to_pkt_flags(staterr); + pkt_flags |= rx_desc_error_to_pkt_flags(staterr); + head->ol_flags = pkt_flags; + + if (likely(pkt_flags & PKT_RX_RSS_HASH)) + head->hash.rss = rte_le_to_cpu_32(desc->wb.lower.hi_dword.rss); + else if (pkt_flags & PKT_RX_FDIR) { + head->hash.fdir.hash = + rte_le_to_cpu_16(desc->wb.lower.hi_dword.csum_ip.csum) + & IXGBE_ATR_HASH_MASK; + head->hash.fdir.id = + rte_le_to_cpu_16(desc->wb.lower.hi_dword.csum_ip.ip_id); + } +} + +/** + * ixgbe_recv_pkts_lro - receive handler for and LRO case. + * + * @rx_queue Rx queue handle + * @rx_pkts table of received packets + * @nb_pkts size of rx_pkts table + * @bulk_alloc if TRUE bulk allocation is used for a HW ring refilling + * + * Handles the Rx HW ring completions when RSC feature is configured. Uses an + * additional ring of ixgbe_rsc_entry's that will hold the relevant RSC info. + * + * We use the same logic as in Linux and in FreeBSD ixgbe drivers: + * 1) When non-EOP RSC completion arrives: + * a) Update the HEAD of the current RSC aggregation cluster with the new + * segment's data length. + * b) Set the "next" pointer of the current segment to point to the segment + * at the NEXTP index. + * c) Pass the HEAD of RSC aggregation cluster on to the next NEXTP entry + * in the sw_rsc_ring. + * 2) When EOP arrives we just update the cluster's total length and offload + * flags and deliver the cluster up to the upper layers. In our case - put it + * in the rx_pkts table. + * + * Returns the number of received packets/clusters (according to the "bulk + * receive" interface). + */ +static inline uint16_t +ixgbe_recv_pkts_lro(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts, + bool bulk_alloc) +{ + struct ixgbe_rx_queue *rxq = rx_queue; + volatile union ixgbe_adv_rx_desc *rx_ring = rxq->rx_ring; + struct ixgbe_rx_entry *sw_ring = rxq->sw_ring; + struct ixgbe_rsc_entry *sw_rsc_ring = rxq->sw_rsc_ring; + uint16_t rx_id = rxq->rx_tail; + uint16_t nb_rx = 0; + uint16_t nb_hold = rxq->nb_rx_hold; + uint16_t prev_id = rxq->rx_tail; + + while (nb_rx < nb_pkts) { + bool eop; + struct ixgbe_rx_entry *rxe; + struct ixgbe_rsc_entry *rsc_entry; + struct ixgbe_rsc_entry *next_rsc_entry; + struct ixgbe_rx_entry *next_rxe; + struct rte_mbuf *first_seg; + struct rte_mbuf *rxm; + struct rte_mbuf *nmb; + union ixgbe_adv_rx_desc rxd; + uint16_t data_len; + uint16_t next_id; + volatile union ixgbe_adv_rx_desc *rxdp; + uint32_t staterr; + +next_desc: + /* + * The code in this whole file uses the volatile pointer to + * ensure the read ordering of the status and the rest of the + * descriptor fields (on the compiler level only!!!). This is so + * UGLY - why not to just use the compiler barrier instead? DPDK + * even has the rte_compiler_barrier() for that. + * + * But most importantly this is just wrong because this doesn't + * ensure memory ordering in a general case at all. For + * instance, DPDK is supposed to work on Power CPUs where + * compiler barrier may just not be enough! + * + * I tried to write only this function properly to have a + * starting point (as a part of an LRO/RSC series) but the + * compiler cursed at me when I tried to cast away the + * "volatile" from rx_ring (yes, it's volatile too!!!). So, I'm + * keeping it the way it is for now. + * + * The code in this file is broken in so many other places and + * will just not work on a big endian CPU anyway therefore the + * lines below will have to be revisited together with the rest + * of the ixgbe PMD. + * + * TODO: + * - Get rid of "volatile" crap and let the compiler do its + * job. + * - Use the proper memory barrier (rte_rmb()) to ensure the + * memory ordering below. + */ + rxdp = &rx_ring[rx_id]; + staterr = rte_le_to_cpu_32(rxdp->wb.upper.status_error); + + if (!(staterr & IXGBE_RXDADV_STAT_DD)) + break; + + rxd = *rxdp; + + PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_id=%u " + "staterr=0x%x data_len=%u", + rxq->port_id, rxq->queue_id, rx_id, staterr, + rte_le_to_cpu_16(rxd.wb.upper.length)); + + if (!bulk_alloc) { + nmb = rte_rxmbuf_alloc(rxq->mb_pool); + if (nmb == NULL) { + PMD_RX_LOG(DEBUG, "RX mbuf alloc failed " + "port_id=%u queue_id=%u", + rxq->port_id, rxq->queue_id); + + rte_eth_devices[rxq->port_id].data-> + rx_mbuf_alloc_failed++; + break; + } + } else if (nb_hold > rxq->rx_free_thresh) { + uint16_t next_rdt = rxq->rx_free_trigger; + + if (!ixgbe_rx_alloc_bufs(rxq, false)) { + rte_wmb(); + IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, + next_rdt); + nb_hold -= rxq->rx_free_thresh; + } else { + PMD_RX_LOG(DEBUG, "RX bulk alloc failed " + "port_id=%u queue_id=%u", + rxq->port_id, rxq->queue_id); + + rte_eth_devices[rxq->port_id].data-> + rx_mbuf_alloc_failed++; + break; + } + } + + nb_hold++; + rxe = &sw_ring[rx_id]; + eop = staterr & IXGBE_RXDADV_STAT_EOP; + + next_id = rx_id + 1; + if (next_id == rxq->nb_rx_desc) + next_id = 0; + + /* Prefetch next mbuf while processing current one. */ + rte_ixgbe_prefetch(sw_ring[next_id].mbuf); + + /* + * When next RX descriptor is on a cache-line boundary, + * prefetch the next 4 RX descriptors and the next 4 pointers + * to mbufs. + */ + if ((next_id & 0x3) == 0) { + rte_ixgbe_prefetch(&rx_ring[next_id]); + rte_ixgbe_prefetch(&sw_ring[next_id]); + } + + rxm = rxe->mbuf; + + if (!bulk_alloc) { + __le64 dma = + rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(nmb)); + /* + * Update RX descriptor with the physical address of the + * new data buffer of the new allocated mbuf. + */ + rxe->mbuf = nmb; + + rxm->data_off = RTE_PKTMBUF_HEADROOM; + rxdp->read.hdr_addr = dma; + rxdp->read.pkt_addr = dma; + } else + rxe->mbuf = NULL; + + /* + * Set data length & data buffer address of mbuf. + */ + data_len = rte_le_to_cpu_16(rxd.wb.upper.length); + rxm->data_len = data_len; + + if (!eop) { + uint16_t nextp_id; + /* + * Get next descriptor index: + * - For RSC it's in the NEXTP field. + * - For a scattered packet - it's just a following + * descriptor. + */ + if (ixgbe_rsc_count(&rxd)) + nextp_id = + (staterr & IXGBE_RXDADV_NEXTP_MASK) >> + IXGBE_RXDADV_NEXTP_SHIFT; + else + nextp_id = next_id; + + next_rsc_entry = &sw_rsc_ring[nextp_id]; + next_rxe = &sw_ring[nextp_id]; + rte_ixgbe_prefetch(next_rxe); + } + + rsc_entry = &sw_rsc_ring[rx_id]; + first_seg = rsc_entry->fbuf; + rsc_entry->fbuf = NULL; + + /* + * If this is the first buffer of the received packet, + * set the pointer to the first mbuf of the packet and + * initialize its context. + * Otherwise, update the total length and the number of segments + * of the current scattered packet, and update the pointer to + * the last mbuf of the current packet. + */ + if (first_seg == NULL) { + first_seg = rxm; + first_seg->pkt_len = data_len; + first_seg->nb_segs = 1; + } else { + first_seg->pkt_len += data_len; + first_seg->nb_segs++; + } + + prev_id = rx_id; + rx_id = next_id; + + /* + * If this is not the last buffer of the received packet, update + * the pointer to the first mbuf at the NEXTP entry in the + * sw_rsc_ring and continue to parse the RX ring. + */ + if (!eop) { + rxm->next = next_rxe->mbuf; + next_rsc_entry->fbuf = first_seg; + goto next_desc; + } + + /* + * This is the last buffer of the received packet - return + * the current cluster to the user. + */ + rxm->next = NULL; + + /* Initialize the first mbuf of the returned packet */ + ixgbe_fill_cluster_head_buf(first_seg, &rxd, rxq->port_id, + staterr); + + /* Prefetch data of first segment, if configured to do so. */ + rte_packet_prefetch((char *)first_seg->buf_addr + + first_seg->data_off); + + /* + * Store the mbuf address into the next entry of the array + * of returned packets. + */ + rx_pkts[nb_rx++] = first_seg; + } + + /* + * Record index of the next RX descriptor to probe. + */ + rxq->rx_tail = rx_id; + + /* + * If the number of free RX descriptors is greater than the RX free + * threshold of the queue, advance the Receive Descriptor Tail (RDT) + * register. + * Update the RDT with the value of the last processed RX descriptor + * minus 1, to guarantee that the RDT register is never equal to the + * RDH register, which creates a "full" ring situtation from the + * hardware point of view... + */ + if (!bulk_alloc && nb_hold > rxq->rx_free_thresh) { + PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_tail=%u " + "nb_hold=%u nb_rx=%u", + rxq->port_id, rxq->queue_id, rx_id, nb_hold, nb_rx); + + rte_wmb(); + IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, prev_id); + nb_hold = 0; + } + + rxq->nb_rx_hold = nb_hold; + return nb_rx; +} + +uint16_t +ixgbe_recv_pkts_lro_single_alloc(void *rx_queue, struct rte_mbuf **rx_pkts, + uint16_t nb_pkts) +{ + return ixgbe_recv_pkts_lro(rx_queue, rx_pkts, nb_pkts, false); +} + +uint16_t +ixgbe_recv_pkts_lro_bulk_alloc(void *rx_queue, struct rte_mbuf **rx_pkts, + uint16_t nb_pkts) +{ + return ixgbe_recv_pkts_lro(rx_queue, rx_pkts, nb_pkts, true); +} + uint16_t ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) { - struct igb_rx_queue *rxq; + struct ixgbe_rx_queue *rxq; volatile union ixgbe_adv_rx_desc *rx_ring; volatile union ixgbe_adv_rx_desc *rxdp; - struct igb_rx_entry *sw_ring; - struct igb_rx_entry *rxe; + struct ixgbe_rx_entry *sw_ring; + struct ixgbe_rx_entry *rxe; struct rte_mbuf *first_seg; struct rte_mbuf *last_seg; struct rte_mbuf *rxm; @@ -1463,12 +1738,10 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, union ixgbe_adv_rx_desc rxd; uint64_t dma; /* Physical address of mbuf data buffer */ uint32_t staterr; - uint32_t hlen_type_rss; uint16_t rx_id; uint16_t nb_rx; uint16_t nb_hold; uint16_t data_len; - uint16_t pkt_flags; nb_rx = 0; nb_hold = 0; @@ -1521,8 +1794,8 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, * to happen by sending specific "back-pressure" flow control * frames to its peer(s). */ - PMD_RX_LOG(DEBUG, "\nport_id=%u queue_id=%u rx_id=%u " - "staterr=0x%x data_len=%u\n", + PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_id=%u " + "staterr=0x%x data_len=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id, (unsigned) rx_id, (unsigned) staterr, (unsigned) rte_le_to_cpu_16(rxd.wb.upper.length)); @@ -1530,7 +1803,7 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, nmb = rte_rxmbuf_alloc(rxq->mb_pool); if (nmb == NULL) { PMD_RX_LOG(DEBUG, "RX mbuf alloc failed port_id=%u " - "queue_id=%u\n", (unsigned) rxq->port_id, + "queue_id=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id); rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed++; break; @@ -1569,8 +1842,8 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, * Set data length & data buffer address of mbuf. */ data_len = rte_le_to_cpu_16(rxd.wb.upper.length); - rxm->pkt.data_len = data_len; - rxm->pkt.data = (char*) rxm->buf_addr + RTE_PKTMBUF_HEADROOM; + rxm->data_len = data_len; + rxm->data_off = RTE_PKTMBUF_HEADROOM; /* * If this is the first buffer of the received packet, @@ -1582,13 +1855,13 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, */ if (first_seg == NULL) { first_seg = rxm; - first_seg->pkt.pkt_len = data_len; - first_seg->pkt.nb_segs = 1; + first_seg->pkt_len = data_len; + first_seg->nb_segs = 1; } else { - first_seg->pkt.pkt_len = (uint16_t)(first_seg->pkt.pkt_len + first_seg->pkt_len = (uint16_t)(first_seg->pkt_len + data_len); - first_seg->pkt.nb_segs++; - last_seg->pkt.next = rxm; + first_seg->nb_segs++; + last_seg->next = rxm; } /* @@ -1611,67 +1884,37 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, * mbuf, subtract the length of that CRC part from the * data length of the previous mbuf. */ - rxm->pkt.next = NULL; + rxm->next = NULL; if (unlikely(rxq->crc_len > 0)) { - first_seg->pkt.pkt_len -= ETHER_CRC_LEN; + first_seg->pkt_len -= ETHER_CRC_LEN; if (data_len <= ETHER_CRC_LEN) { rte_pktmbuf_free_seg(rxm); - first_seg->pkt.nb_segs--; - last_seg->pkt.data_len = (uint16_t) - (last_seg->pkt.data_len - + first_seg->nb_segs--; + last_seg->data_len = (uint16_t) + (last_seg->data_len - (ETHER_CRC_LEN - data_len)); - last_seg->pkt.next = NULL; + last_seg->next = NULL; } else - rxm->pkt.data_len = + rxm->data_len = (uint16_t) (data_len - ETHER_CRC_LEN); } + /* Initialize the first mbuf of the returned packet */ + ixgbe_fill_cluster_head_buf(first_seg, &rxd, rxq->port_id, + staterr); + + /* Prefetch data of first segment, if configured to do so. */ + rte_packet_prefetch((char *)first_seg->buf_addr + + first_seg->data_off); + /* - * Initialize the first mbuf of the returned packet: - * - RX port identifier, - * - hardware offload data, if any: - * - RSS flag & hash, - * - IP checksum flag, - * - VLAN TCI, if any, - * - error flags. + * Store the mbuf address into the next entry of the array + * of returned packets. */ - first_seg->pkt.in_port = rxq->port_id; + rx_pkts[nb_rx++] = first_seg; /* - * The vlan_tci field is only valid when PKT_RX_VLAN_PKT is - * set in the pkt_flags field. - */ - first_seg->pkt.vlan_macip.f.vlan_tci = - rte_le_to_cpu_16(rxd.wb.upper.vlan); - hlen_type_rss = rte_le_to_cpu_32(rxd.wb.lower.lo_dword.data); - pkt_flags = rx_desc_hlen_type_rss_to_pkt_flags(hlen_type_rss); - pkt_flags = (uint16_t)(pkt_flags | - rx_desc_status_to_pkt_flags(staterr)); - pkt_flags = (uint16_t)(pkt_flags | - rx_desc_error_to_pkt_flags(staterr)); - first_seg->ol_flags = pkt_flags; - - if (likely(pkt_flags & PKT_RX_RSS_HASH)) - first_seg->pkt.hash.rss = rxd.wb.lower.hi_dword.rss; - else if (pkt_flags & PKT_RX_FDIR) { - first_seg->pkt.hash.fdir.hash = - (uint16_t)((rxd.wb.lower.hi_dword.csum_ip.csum) - & IXGBE_ATR_HASH_MASK); - first_seg->pkt.hash.fdir.id = - rxd.wb.lower.hi_dword.csum_ip.ip_id; - } - - /* Prefetch data of first segment, if configured to do so. */ - rte_packet_prefetch(first_seg->pkt.data); - - /* - * Store the mbuf address into the next entry of the array - * of returned packets. - */ - rx_pkts[nb_rx++] = first_seg; - - /* - * Setup receipt context for a new packet. + * Setup receipt context for a new packet. */ first_seg = NULL; } @@ -1699,7 +1942,7 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, nb_hold = (uint16_t) (nb_hold + rxq->nb_rx_hold); if (nb_hold > rxq->rx_free_thresh) { PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_tail=%u " - "nb_hold=%u nb_rx=%u\n", + "nb_hold=%u nb_rx=%u", (unsigned) rxq->port_id, (unsigned) rxq->queue_id, (unsigned) rx_id, (unsigned) nb_hold, (unsigned) nb_rx); @@ -1734,7 +1977,7 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, * descriptors should meet the following condition: * (num_ring_desc * sizeof(rx/tx descriptor)) % 128 == 0 */ -#define IXGBE_MIN_RING_DESC 64 +#define IXGBE_MIN_RING_DESC 32 #define IXGBE_MAX_RING_DESC 4096 /* @@ -1749,7 +1992,7 @@ ring_dma_zone_reserve(struct rte_eth_dev *dev, const char *ring_name, char z_name[RTE_MEMZONE_NAMESIZE]; const struct rte_memzone *mz; - rte_snprintf(z_name, sizeof(z_name), "%s_%s_%d_%d", + snprintf(z_name, sizeof(z_name), "%s_%s_%d_%d", dev->driver->pci_drv.name, ring_name, dev->data->port_id, queue_id); @@ -1757,12 +2000,17 @@ ring_dma_zone_reserve(struct rte_eth_dev *dev, const char *ring_name, if (mz) return mz; +#ifdef RTE_LIBRTE_XEN_DOM0 + return rte_memzone_reserve_bounded(z_name, ring_size, + socket_id, 0, IXGBE_ALIGN, RTE_PGSIZE_2M); +#else return rte_memzone_reserve_aligned(z_name, ring_size, - socket_id, 0, IXGBE_ALIGN); + socket_id, 0, IXGBE_ALIGN); +#endif } static void -ixgbe_tx_queue_release_mbufs(struct igb_tx_queue *txq) +ixgbe_tx_queue_release_mbufs(struct ixgbe_tx_queue *txq) { unsigned i; @@ -1777,11 +2025,19 @@ ixgbe_tx_queue_release_mbufs(struct igb_tx_queue *txq) } static void -ixgbe_tx_queue_release(struct igb_tx_queue *txq) +ixgbe_tx_free_swring(struct ixgbe_tx_queue *txq) { - if (txq != NULL) { - ixgbe_tx_queue_release_mbufs(txq); + if (txq != NULL && + txq->sw_ring != NULL) rte_free(txq->sw_ring); +} + +static void +ixgbe_tx_queue_release(struct ixgbe_tx_queue *txq) +{ + if (txq != NULL && txq->ops != NULL) { + txq->ops->release_mbufs(txq); + txq->ops->free_swring(txq); rte_free(txq); } } @@ -1792,16 +2048,17 @@ ixgbe_dev_tx_queue_release(void *txq) ixgbe_tx_queue_release(txq); } -/* (Re)set dynamic igb_tx_queue fields to defaults */ +/* (Re)set dynamic ixgbe_tx_queue fields to defaults */ static void -ixgbe_reset_tx_queue(struct igb_tx_queue *txq) +ixgbe_reset_tx_queue(struct ixgbe_tx_queue *txq) { - struct igb_tx_entry *txe = txq->sw_ring; + static const union ixgbe_adv_tx_desc zeroed_desc = {{0}}; + struct ixgbe_tx_entry *txe = txq->sw_ring; uint16_t prev, i; /* Zero out HW ring memory */ - for (i = 0; i < sizeof(union ixgbe_adv_tx_desc) * txq->nb_tx_desc; i++) { - ((volatile char *)txq->tx_ring)[i] = 0; + for (i = 0; i < txq->nb_tx_desc; i++) { + txq->tx_ring[i] = zeroed_desc; } /* Initialize SW ring entries */ @@ -1831,6 +2088,46 @@ ixgbe_reset_tx_queue(struct igb_tx_queue *txq) IXGBE_CTX_NUM * sizeof(struct ixgbe_advctx_info)); } +static const struct ixgbe_txq_ops def_txq_ops = { + .release_mbufs = ixgbe_tx_queue_release_mbufs, + .free_swring = ixgbe_tx_free_swring, + .reset = ixgbe_reset_tx_queue, +}; + +/* Takes an ethdev and a queue and sets up the tx function to be used based on + * the queue parameters. Used in tx_queue_setup by primary process and then + * in dev_init by secondary process when attaching to an existing ethdev. + */ +void +ixgbe_set_tx_function(struct rte_eth_dev *dev, struct ixgbe_tx_queue *txq) +{ + /* Use a simple Tx queue (no offloads, no multi segs) if possible */ + if (((txq->txq_flags & IXGBE_SIMPLE_FLAGS) == IXGBE_SIMPLE_FLAGS) + && (txq->tx_rs_thresh >= RTE_PMD_IXGBE_TX_MAX_BURST)) { + PMD_INIT_LOG(INFO, "Using simple tx code path"); +#ifdef RTE_IXGBE_INC_VECTOR + if (txq->tx_rs_thresh <= RTE_IXGBE_TX_MAX_FREE_BUF_SZ && + (rte_eal_process_type() != RTE_PROC_PRIMARY || + ixgbe_txq_vec_setup(txq) == 0)) { + PMD_INIT_LOG(INFO, "Vector tx enabled."); + dev->tx_pkt_burst = ixgbe_xmit_pkts_vec; + } else +#endif + dev->tx_pkt_burst = ixgbe_xmit_pkts_simple; + } else { + PMD_INIT_LOG(INFO, "Using full-featured tx code path"); + PMD_INIT_LOG(INFO, + " - txq_flags = %lx " "[IXGBE_SIMPLE_FLAGS=%lx]", + (unsigned long)txq->txq_flags, + (unsigned long)IXGBE_SIMPLE_FLAGS); + PMD_INIT_LOG(INFO, + " - tx_rs_thresh = %lu " "[RTE_PMD_IXGBE_TX_MAX_BURST=%lu]", + (unsigned long)txq->tx_rs_thresh, + (unsigned long)RTE_PMD_IXGBE_TX_MAX_BURST); + dev->tx_pkt_burst = ixgbe_xmit_pkts; + } +} + int ixgbe_dev_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, @@ -1839,7 +2136,7 @@ ixgbe_dev_tx_queue_setup(struct rte_eth_dev *dev, const struct rte_eth_txconf *tx_conf) { const struct rte_memzone *tz; - struct igb_tx_queue *txq; + struct ixgbe_tx_queue *txq; struct ixgbe_hw *hw; uint16_t tx_rs_thresh, tx_free_thresh; @@ -1882,33 +2179,36 @@ ixgbe_dev_tx_queue_setup(struct rte_eth_dev *dev, tx_free_thresh = (uint16_t)((tx_conf->tx_free_thresh) ? tx_conf->tx_free_thresh : DEFAULT_TX_FREE_THRESH); if (tx_rs_thresh >= (nb_desc - 2)) { - RTE_LOG(ERR, PMD, "tx_rs_thresh must be less than the number " - "of TX descriptors minus 2. (tx_rs_thresh=%u port=%d " - "queue=%d)\n", (unsigned int)tx_rs_thresh, - (int)dev->data->port_id, (int)queue_idx); + PMD_INIT_LOG(ERR, "tx_rs_thresh must be less than the number " + "of TX descriptors minus 2. (tx_rs_thresh=%u " + "port=%d queue=%d)", (unsigned int)tx_rs_thresh, + (int)dev->data->port_id, (int)queue_idx); return -(EINVAL); } if (tx_free_thresh >= (nb_desc - 3)) { - RTE_LOG(ERR, PMD, "tx_rs_thresh must be less than the " - "tx_free_thresh must be less than the number of TX " - "descriptors minus 3. (tx_free_thresh=%u port=%d " - "queue=%d)\n", (unsigned int)tx_free_thresh, - (int)dev->data->port_id, (int)queue_idx); + PMD_INIT_LOG(ERR, "tx_rs_thresh must be less than the " + "tx_free_thresh must be less than the number of " + "TX descriptors minus 3. (tx_free_thresh=%u " + "port=%d queue=%d)", + (unsigned int)tx_free_thresh, + (int)dev->data->port_id, (int)queue_idx); return -(EINVAL); } if (tx_rs_thresh > tx_free_thresh) { - RTE_LOG(ERR, PMD, "tx_rs_thresh must be less than or equal to " - "tx_free_thresh. (tx_free_thresh=%u tx_rs_thresh=%u " - "port=%d queue=%d)\n", (unsigned int)tx_free_thresh, - (unsigned int)tx_rs_thresh, (int)dev->data->port_id, - (int)queue_idx); + PMD_INIT_LOG(ERR, "tx_rs_thresh must be less than or equal to " + "tx_free_thresh. (tx_free_thresh=%u " + "tx_rs_thresh=%u port=%d queue=%d)", + (unsigned int)tx_free_thresh, + (unsigned int)tx_rs_thresh, + (int)dev->data->port_id, + (int)queue_idx); return -(EINVAL); } if ((nb_desc % tx_rs_thresh) != 0) { - RTE_LOG(ERR, PMD, "tx_rs_thresh must be a divisor of the " - "number of TX descriptors. (tx_rs_thresh=%u port=%d " - "queue=%d)\n", (unsigned int)tx_rs_thresh, - (int)dev->data->port_id, (int)queue_idx); + PMD_INIT_LOG(ERR, "tx_rs_thresh must be a divisor of the " + "number of TX descriptors. (tx_rs_thresh=%u " + "port=%d queue=%d)", (unsigned int)tx_rs_thresh, + (int)dev->data->port_id, (int)queue_idx); return -(EINVAL); } @@ -1919,20 +2219,22 @@ ixgbe_dev_tx_queue_setup(struct rte_eth_dev *dev, * accumulates WTHRESH descriptors. */ if ((tx_rs_thresh > 1) && (tx_conf->tx_thresh.wthresh != 0)) { - RTE_LOG(ERR, PMD, "TX WTHRESH must be set to 0 if " - "tx_rs_thresh is greater than 1. (tx_rs_thresh=%u " - "port=%d queue=%d)\n", (unsigned int)tx_rs_thresh, - (int)dev->data->port_id, (int)queue_idx); + PMD_INIT_LOG(ERR, "TX WTHRESH must be set to 0 if " + "tx_rs_thresh is greater than 1. (tx_rs_thresh=%u " + "port=%d queue=%d)", (unsigned int)tx_rs_thresh, + (int)dev->data->port_id, (int)queue_idx); return -(EINVAL); } /* Free memory prior to re-allocation if needed... */ - if (dev->data->tx_queues[queue_idx] != NULL) + if (dev->data->tx_queues[queue_idx] != NULL) { ixgbe_tx_queue_release(dev->data->tx_queues[queue_idx]); + dev->data->tx_queues[queue_idx] = NULL; + } /* First allocate the tx queue data structure */ - txq = rte_zmalloc_socket("ethdev TX queue", sizeof(struct igb_tx_queue), - CACHE_LINE_SIZE, socket_id); + txq = rte_zmalloc_socket("ethdev TX queue", sizeof(struct ixgbe_tx_queue), + RTE_CACHE_LINE_SIZE, socket_id); if (txq == NULL) return (-ENOMEM); @@ -1956,52 +2258,79 @@ ixgbe_dev_tx_queue_setup(struct rte_eth_dev *dev, txq->hthresh = tx_conf->tx_thresh.hthresh; txq->wthresh = tx_conf->tx_thresh.wthresh; txq->queue_id = queue_idx; + txq->reg_idx = (uint16_t)((RTE_ETH_DEV_SRIOV(dev).active == 0) ? + queue_idx : RTE_ETH_DEV_SRIOV(dev).def_pool_q_idx + queue_idx); txq->port_id = dev->data->port_id; txq->txq_flags = tx_conf->txq_flags; + txq->ops = &def_txq_ops; + txq->tx_deferred_start = tx_conf->tx_deferred_start; /* * Modification to set VFTDT for virtual function if vf is detected */ - if (hw->mac.type == ixgbe_mac_82599_vf) + if (hw->mac.type == ixgbe_mac_82599_vf || + hw->mac.type == ixgbe_mac_X540_vf || + hw->mac.type == ixgbe_mac_X550_vf || + hw->mac.type == ixgbe_mac_X550EM_x_vf) txq->tdt_reg_addr = IXGBE_PCI_REG_ADDR(hw, IXGBE_VFTDT(queue_idx)); else - txq->tdt_reg_addr = IXGBE_PCI_REG_ADDR(hw, IXGBE_TDT(queue_idx)); - + txq->tdt_reg_addr = IXGBE_PCI_REG_ADDR(hw, IXGBE_TDT(txq->reg_idx)); +#ifndef RTE_LIBRTE_XEN_DOM0 txq->tx_ring_phys_addr = (uint64_t) tz->phys_addr; +#else + txq->tx_ring_phys_addr = rte_mem_phy2mch(tz->memseg_id, tz->phys_addr); +#endif txq->tx_ring = (union ixgbe_adv_tx_desc *) tz->addr; /* Allocate software ring */ txq->sw_ring = rte_zmalloc_socket("txq->sw_ring", - sizeof(struct igb_tx_entry) * nb_desc, - CACHE_LINE_SIZE, socket_id); + sizeof(struct ixgbe_tx_entry) * nb_desc, + RTE_CACHE_LINE_SIZE, socket_id); if (txq->sw_ring == NULL) { ixgbe_tx_queue_release(txq); return (-ENOMEM); } - PMD_INIT_LOG(DEBUG, "sw_ring=%p hw_ring=%p dma_addr=0x%"PRIx64"\n", + PMD_INIT_LOG(DEBUG, "sw_ring=%p hw_ring=%p dma_addr=0x%"PRIx64, txq->sw_ring, txq->tx_ring, txq->tx_ring_phys_addr); - ixgbe_reset_tx_queue(txq); + /* set up vector or scalar TX function as appropriate */ + ixgbe_set_tx_function(dev, txq); + + txq->ops->reset(txq); dev->data->tx_queues[queue_idx] = txq; - /* Use a simple Tx queue (no offloads, no multi segs) if possible */ - if (((txq->txq_flags & IXGBE_SIMPLE_FLAGS) == IXGBE_SIMPLE_FLAGS) && - (txq->tx_rs_thresh >= RTE_PMD_IXGBE_TX_MAX_BURST)) { - PMD_INIT_LOG(INFO, "Using simple tx code path\n"); - dev->tx_pkt_burst = ixgbe_xmit_pkts_simple; - } else { - PMD_INIT_LOG(INFO, "Using full-featured tx code path\n"); - PMD_INIT_LOG(INFO, " - txq_flags = %lx [IXGBE_SIMPLE_FLAGS=%lx]\n", (long unsigned)txq->txq_flags, (long unsigned)IXGBE_SIMPLE_FLAGS); - PMD_INIT_LOG(INFO, " - tx_rs_thresh = %lu [RTE_PMD_IXGBE_TX_MAX_BURST=%lu]\n", (long unsigned)txq->tx_rs_thresh, (long unsigned)RTE_PMD_IXGBE_TX_MAX_BURST); - dev->tx_pkt_burst = ixgbe_xmit_pkts; - } return (0); } +/** + * ixgbe_free_rsc_cluster - free the not-yet-completed RSC cluster + * + * The "next" pointer of the last segment of (not-yet-completed) RSC clusters + * in the sw_rsc_ring is not set to NULL but rather points to the next + * mbuf of this RSC aggregation (that has not been completed yet and still + * resides on the HW ring). So, instead of calling for rte_pktmbuf_free() we + * will just free first "nb_segs" segments of the cluster explicitly by calling + * an rte_pktmbuf_free_seg(). + * + * @m RSC cluster head + */ +static void +ixgbe_free_rsc_cluster(struct rte_mbuf *m) +{ + uint8_t i, nb_segs = m->nb_segs; + struct rte_mbuf *next_seg; + + for (i = 0; i < nb_segs; i++) { + next_seg = m->next; + rte_pktmbuf_free_seg(m); + m = next_seg; + } +} + static void -ixgbe_rx_queue_release_mbufs(struct igb_rx_queue *rxq) +ixgbe_rx_queue_release_mbufs(struct ixgbe_rx_queue *rxq) { unsigned i; @@ -2023,14 +2352,22 @@ ixgbe_rx_queue_release_mbufs(struct igb_rx_queue *rxq) } #endif } + + if (rxq->sw_rsc_ring) + for (i = 0; i < rxq->nb_rx_desc; i++) + if (rxq->sw_rsc_ring[i].fbuf) { + ixgbe_free_rsc_cluster(rxq->sw_rsc_ring[i].fbuf); + rxq->sw_rsc_ring[i].fbuf = NULL; + } } static void -ixgbe_rx_queue_release(struct igb_rx_queue *rxq) +ixgbe_rx_queue_release(struct ixgbe_rx_queue *rxq) { if (rxq != NULL) { ixgbe_rx_queue_release_mbufs(rxq); rte_free(rxq->sw_ring); + rte_free(rxq->sw_rsc_ring); rte_free(rxq); } } @@ -2051,9 +2388,9 @@ ixgbe_dev_rx_queue_release(void *rxq) */ static inline int #ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC -check_rx_burst_bulk_alloc_preconditions(struct igb_rx_queue *rxq) +check_rx_burst_bulk_alloc_preconditions(struct ixgbe_rx_queue *rxq) #else -check_rx_burst_bulk_alloc_preconditions(__rte_unused struct igb_rx_queue *rxq) +check_rx_burst_bulk_alloc_preconditions(__rte_unused struct ixgbe_rx_queue *rxq) #endif { int ret = 0; @@ -2068,15 +2405,34 @@ check_rx_burst_bulk_alloc_preconditions(__rte_unused struct igb_rx_queue *rxq) * outside of this function. */ #ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC - if (! (rxq->rx_free_thresh >= RTE_PMD_IXGBE_RX_MAX_BURST)) + if (!(rxq->rx_free_thresh >= RTE_PMD_IXGBE_RX_MAX_BURST)) { + PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions: " + "rxq->rx_free_thresh=%d, " + "RTE_PMD_IXGBE_RX_MAX_BURST=%d", + rxq->rx_free_thresh, RTE_PMD_IXGBE_RX_MAX_BURST); ret = -EINVAL; - else if (! (rxq->rx_free_thresh < rxq->nb_rx_desc)) + } else if (!(rxq->rx_free_thresh < rxq->nb_rx_desc)) { + PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions: " + "rxq->rx_free_thresh=%d, " + "rxq->nb_rx_desc=%d", + rxq->rx_free_thresh, rxq->nb_rx_desc); ret = -EINVAL; - else if (! ((rxq->nb_rx_desc % rxq->rx_free_thresh) == 0)) + } else if (!((rxq->nb_rx_desc % rxq->rx_free_thresh) == 0)) { + PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions: " + "rxq->nb_rx_desc=%d, " + "rxq->rx_free_thresh=%d", + rxq->nb_rx_desc, rxq->rx_free_thresh); ret = -EINVAL; - else if (! (rxq->nb_rx_desc < - (IXGBE_MAX_RING_DESC - RTE_PMD_IXGBE_RX_MAX_BURST))) + } else if (!(rxq->nb_rx_desc < + (IXGBE_MAX_RING_DESC - RTE_PMD_IXGBE_RX_MAX_BURST))) { + PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions: " + "rxq->nb_rx_desc=%d, " + "IXGBE_MAX_RING_DESC=%d, " + "RTE_PMD_IXGBE_RX_MAX_BURST=%d", + rxq->nb_rx_desc, IXGBE_MAX_RING_DESC, + RTE_PMD_IXGBE_RX_MAX_BURST); ret = -EINVAL; + } #else ret = -EINVAL; #endif @@ -2084,12 +2440,13 @@ check_rx_burst_bulk_alloc_preconditions(__rte_unused struct igb_rx_queue *rxq) return ret; } -/* Reset dynamic igb_rx_queue fields back to defaults */ +/* Reset dynamic ixgbe_rx_queue fields back to defaults */ static void -ixgbe_reset_rx_queue(struct igb_rx_queue *rxq) +ixgbe_reset_rx_queue(struct ixgbe_hw *hw, struct ixgbe_rx_queue *rxq) { + static const union ixgbe_adv_rx_desc zeroed_desc = {{0}}; unsigned i; - uint16_t len; + uint16_t len = rxq->nb_rx_desc; /* * By default, the Rx queue setup function allocates enough memory for @@ -2101,22 +2458,17 @@ ixgbe_reset_rx_queue(struct igb_rx_queue *rxq) * constraints here to see if we need to zero out memory after the end * of the H/W descriptor ring. */ -#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC - if (check_rx_burst_bulk_alloc_preconditions(rxq) == 0) + if (hw->rx_bulk_alloc_allowed) /* zero out extra memory */ - len = (uint16_t)(rxq->nb_rx_desc + RTE_PMD_IXGBE_RX_MAX_BURST); - else -#endif - /* do not zero out extra memory */ - len = rxq->nb_rx_desc; + len += RTE_PMD_IXGBE_RX_MAX_BURST; /* * Zero out HW ring memory. Zero out extra memory at the end of * the H/W ring so look-ahead logic in Rx Burst bulk alloc function * reads extra memory as zeros. */ - for (i = 0; i < len * sizeof(union ixgbe_adv_rx_desc); i++) { - ((volatile char *)rxq->rx_ring)[i] = 0; + for (i = 0; i < len; i++) { + rxq->rx_ring[i] = zeroed_desc; } #ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC @@ -2125,8 +2477,8 @@ ixgbe_reset_rx_queue(struct igb_rx_queue *rxq) * entries is always allocated */ memset(&rxq->fake_mbuf, 0x0, sizeof(rxq->fake_mbuf)); - for (i = 0; i < RTE_PMD_IXGBE_RX_MAX_BURST; ++i) { - rxq->sw_ring[rxq->nb_rx_desc + i].mbuf = &rxq->fake_mbuf; + for (i = rxq->nb_rx_desc; i < len; ++i) { + rxq->sw_ring[i].mbuf = &rxq->fake_mbuf; } rxq->rx_nb_avail = 0; @@ -2137,6 +2489,7 @@ ixgbe_reset_rx_queue(struct igb_rx_queue *rxq) rxq->nb_rx_hold = 0; rxq->pkt_first_seg = NULL; rxq->pkt_last_seg = NULL; + rxq->rsc_en = 0; } int @@ -2148,10 +2501,17 @@ ixgbe_dev_rx_queue_setup(struct rte_eth_dev *dev, struct rte_mempool *mp) { const struct rte_memzone *rz; - struct igb_rx_queue *rxq; + struct ixgbe_rx_queue *rxq; struct ixgbe_hw *hw; - int use_def_burst_func = 1; uint16_t len; + struct rte_eth_dev_info dev_info = { 0 }; + struct rte_eth_rxmode *dev_rx_mode = &dev->data->dev_conf.rxmode; + bool rsc_requested = false; + + dev->dev_ops->dev_infos_get(dev, &dev_info); + if ((dev_info.rx_offload_capa & DEV_RX_OFFLOAD_TCP_LRO) && + dev_rx_mode->enable_lro) + rsc_requested = true; PMD_INIT_FUNC_TRACE(); hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); @@ -2168,22 +2528,27 @@ ixgbe_dev_rx_queue_setup(struct rte_eth_dev *dev, } /* Free memory prior to re-allocation if needed... */ - if (dev->data->rx_queues[queue_idx] != NULL) + if (dev->data->rx_queues[queue_idx] != NULL) { ixgbe_rx_queue_release(dev->data->rx_queues[queue_idx]); + dev->data->rx_queues[queue_idx] = NULL; + } /* First allocate the rx queue data structure */ - rxq = rte_zmalloc_socket("ethdev RX queue", sizeof(struct igb_rx_queue), - CACHE_LINE_SIZE, socket_id); + rxq = rte_zmalloc_socket("ethdev RX queue", sizeof(struct ixgbe_rx_queue), + RTE_CACHE_LINE_SIZE, socket_id); if (rxq == NULL) return (-ENOMEM); rxq->mb_pool = mp; rxq->nb_rx_desc = nb_desc; rxq->rx_free_thresh = rx_conf->rx_free_thresh; rxq->queue_id = queue_idx; + rxq->reg_idx = (uint16_t)((RTE_ETH_DEV_SRIOV(dev).active == 0) ? + queue_idx : RTE_ETH_DEV_SRIOV(dev).def_pool_q_idx + queue_idx); rxq->port_id = dev->data->port_id; rxq->crc_len = (uint8_t) ((dev->data->dev_conf.rxmode.hw_strip_crc) ? 0 : ETHER_CRC_LEN); rxq->drop_en = rx_conf->rx_drop_en; + rxq->rx_deferred_start = rx_conf->rx_deferred_start; /* * Allocate RX ring hardware descriptors. A memzone large enough to @@ -2191,117 +2556,171 @@ ixgbe_dev_rx_queue_setup(struct rte_eth_dev *dev, * resizing in later calls to the queue setup function. */ rz = ring_dma_zone_reserve(dev, "rx_ring", queue_idx, - IXGBE_MAX_RING_DESC * sizeof(union ixgbe_adv_rx_desc), - socket_id); + RX_RING_SZ, socket_id); if (rz == NULL) { ixgbe_rx_queue_release(rxq); return (-ENOMEM); } + /* - * Modified to setup VFRDT for Virtual Function + * Zero init all the descriptors in the ring. */ - if (hw->mac.type == ixgbe_mac_82599_vf) - rxq->rdt_reg_addr = IXGBE_PCI_REG_ADDR(hw, IXGBE_VFRDT(queue_idx)); - else - rxq->rdt_reg_addr = IXGBE_PCI_REG_ADDR(hw, IXGBE_RDT(queue_idx)); + memset (rz->addr, 0, RX_RING_SZ); + /* + * Modified to setup VFRDT for Virtual Function + */ + if (hw->mac.type == ixgbe_mac_82599_vf || + hw->mac.type == ixgbe_mac_X540_vf || + hw->mac.type == ixgbe_mac_X550_vf || + hw->mac.type == ixgbe_mac_X550EM_x_vf) { + rxq->rdt_reg_addr = + IXGBE_PCI_REG_ADDR(hw, IXGBE_VFRDT(queue_idx)); + rxq->rdh_reg_addr = + IXGBE_PCI_REG_ADDR(hw, IXGBE_VFRDH(queue_idx)); + } + else { + rxq->rdt_reg_addr = + IXGBE_PCI_REG_ADDR(hw, IXGBE_RDT(rxq->reg_idx)); + rxq->rdh_reg_addr = + IXGBE_PCI_REG_ADDR(hw, IXGBE_RDH(rxq->reg_idx)); + } +#ifndef RTE_LIBRTE_XEN_DOM0 rxq->rx_ring_phys_addr = (uint64_t) rz->phys_addr; +#else + rxq->rx_ring_phys_addr = rte_mem_phy2mch(rz->memseg_id, rz->phys_addr); +#endif rxq->rx_ring = (union ixgbe_adv_rx_desc *) rz->addr; /* - * Allocate software ring. Allow for space at the end of the + * Certain constraints must be met in order to use the bulk buffer + * allocation Rx burst function. If any of Rx queues doesn't meet them + * the feature should be disabled for the whole port. + */ + if (check_rx_burst_bulk_alloc_preconditions(rxq)) { + PMD_INIT_LOG(DEBUG, "queue[%d] doesn't meet Rx Bulk Alloc " + "preconditions - canceling the feature for " + "the whole port[%d]", + rxq->queue_id, rxq->port_id); + hw->rx_bulk_alloc_allowed = false; + } + + /* + * Allocate software ring. Allow for space at the end of the * S/W ring to make sure look-ahead logic in bulk alloc Rx burst * function does not access an invalid memory region. */ -#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC - len = (uint16_t)(nb_desc + RTE_PMD_IXGBE_RX_MAX_BURST); -#else len = nb_desc; -#endif + if (hw->rx_bulk_alloc_allowed) + len += RTE_PMD_IXGBE_RX_MAX_BURST; + rxq->sw_ring = rte_zmalloc_socket("rxq->sw_ring", - sizeof(struct igb_rx_entry) * len, - CACHE_LINE_SIZE, socket_id); - if (rxq->sw_ring == NULL) { + sizeof(struct ixgbe_rx_entry) * len, + RTE_CACHE_LINE_SIZE, socket_id); + if (!rxq->sw_ring) { ixgbe_rx_queue_release(rxq); return (-ENOMEM); } - PMD_INIT_LOG(DEBUG, "sw_ring=%p hw_ring=%p dma_addr=0x%"PRIx64"\n", - rxq->sw_ring, rxq->rx_ring, rxq->rx_ring_phys_addr); - /* - * Certain constaints must be met in order to use the bulk buffer - * allocation Rx burst function. - */ - use_def_burst_func = check_rx_burst_bulk_alloc_preconditions(rxq); + if (rsc_requested) { + rxq->sw_rsc_ring = + rte_zmalloc_socket("rxq->sw_rsc_ring", + sizeof(struct ixgbe_rsc_entry) * len, + RTE_CACHE_LINE_SIZE, socket_id); + if (!rxq->sw_rsc_ring) { + ixgbe_rx_queue_release(rxq); + return (-ENOMEM); + } + } else + rxq->sw_rsc_ring = NULL; + + PMD_INIT_LOG(DEBUG, "sw_ring=%p sw_rsc_ring=%p hw_ring=%p " + "dma_addr=0x%"PRIx64, + rxq->sw_ring, rxq->sw_rsc_ring, rxq->rx_ring, + rxq->rx_ring_phys_addr); + + if (!rte_is_power_of_2(nb_desc)) { + PMD_INIT_LOG(DEBUG, "queue[%d] doesn't meet Vector Rx " + "preconditions - canceling the feature for " + "the whole port[%d]", + rxq->queue_id, rxq->port_id); + hw->rx_vec_allowed = false; + } else + ixgbe_rxq_vec_setup(rxq); - /* Check if pre-conditions are satisfied, and no Scattered Rx */ - if (!use_def_burst_func && !dev->data->scattered_rx) { -#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC - PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are " - "satisfied. Rx Burst Bulk Alloc function will be " - "used on port=%d, queue=%d.\n", - rxq->port_id, rxq->queue_id); - dev->rx_pkt_burst = ixgbe_recv_pkts_bulk_alloc; -#endif - } else { - PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions " - "are not satisfied, Scattered Rx is requested, " - "or RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC is not " - "enabled (port=%d, queue=%d).\n", - rxq->port_id, rxq->queue_id); - } dev->data->rx_queues[queue_idx] = rxq; - ixgbe_reset_rx_queue(rxq); + ixgbe_reset_rx_queue(hw, rxq); return 0; } -uint32_t ixgbe_dev_rx_queue_count(struct rte_eth_dev *dev, - uint16_t rx_queue_id) +uint32_t +ixgbe_dev_rx_queue_count(struct rte_eth_dev *dev, uint16_t rx_queue_id) { - struct igb_rx_queue *rxq; - uint32_t nb_pkts_available; - uint32_t rx_rdh; - uint32_t rx_id; +#define IXGBE_RXQ_SCAN_INTERVAL 4 + volatile union ixgbe_adv_rx_desc *rxdp; + struct ixgbe_rx_queue *rxq; + uint32_t desc = 0; if (rx_queue_id >= dev->data->nb_rx_queues) { - PMD_RX_LOG(DEBUG,"Invalid RX queue_id=%d\n", rx_queue_id); - return 0; + PMD_RX_LOG(ERR, "Invalid RX queue id=%d", rx_queue_id); + return 0; } rxq = dev->data->rx_queues[rx_queue_id]; - rx_id = (uint16_t)((rxq->rx_tail == 0) ? - (rxq->nb_rx_desc - 1) : (rxq->rx_tail - 1)); - rx_rdh = IXGBE_PCI_REG(rxq->rdh_reg_addr); - if (rx_rdh > rx_id) - nb_pkts_available = rx_rdh - rx_id; - else - nb_pkts_available = rx_rdh - rx_id + rxq->nb_rx_desc; - - return (nb_pkts_available); + rxdp = &(rxq->rx_ring[rxq->rx_tail]); + + while ((desc < rxq->nb_rx_desc) && + (rxdp->wb.upper.status_error & IXGBE_RXDADV_STAT_DD)) { + desc += IXGBE_RXQ_SCAN_INTERVAL; + rxdp += IXGBE_RXQ_SCAN_INTERVAL; + if (rxq->rx_tail + desc >= rxq->nb_rx_desc) + rxdp = &(rxq->rx_ring[rxq->rx_tail + + desc - rxq->nb_rx_desc]); + } + + return desc; +} + +int +ixgbe_dev_rx_descriptor_done(void *rx_queue, uint16_t offset) +{ + volatile union ixgbe_adv_rx_desc *rxdp; + struct ixgbe_rx_queue *rxq = rx_queue; + uint32_t desc; + + if (unlikely(offset >= rxq->nb_rx_desc)) + return 0; + desc = rxq->rx_tail + offset; + if (desc >= rxq->nb_rx_desc) + desc -= rxq->nb_rx_desc; + + rxdp = &rxq->rx_ring[desc]; + return !!(rxdp->wb.upper.status_error & IXGBE_RXDADV_STAT_DD); } void ixgbe_dev_clear_queues(struct rte_eth_dev *dev) { unsigned i; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); PMD_INIT_FUNC_TRACE(); for (i = 0; i < dev->data->nb_tx_queues; i++) { - struct igb_tx_queue *txq = dev->data->tx_queues[i]; + struct ixgbe_tx_queue *txq = dev->data->tx_queues[i]; if (txq != NULL) { - ixgbe_tx_queue_release_mbufs(txq); - ixgbe_reset_tx_queue(txq); + txq->ops->release_mbufs(txq); + txq->ops->reset(txq); } } for (i = 0; i < dev->data->nb_rx_queues; i++) { - struct igb_rx_queue *rxq = dev->data->rx_queues[i]; + struct ixgbe_rx_queue *rxq = dev->data->rx_queues[i]; if (rxq != NULL) { ixgbe_rx_queue_release_mbufs(rxq); - ixgbe_reset_rx_queue(rxq); + ixgbe_reset_rx_queue(hw, rxq); } } } @@ -2355,70 +2774,177 @@ ixgbe_rss_disable(struct rte_eth_dev *dev) } static void -ixgbe_rss_configure(struct rte_eth_dev *dev) +ixgbe_hw_rss_hash_set(struct ixgbe_hw *hw, struct rte_eth_rss_conf *rss_conf) { - struct ixgbe_hw *hw; - uint8_t *hash_key; - uint32_t rss_key; + uint8_t *hash_key; uint32_t mrqc; - uint32_t reta; - uint16_t rss_hf; + uint32_t rss_key; + uint64_t rss_hf; uint16_t i; - uint16_t j; - - PMD_INIT_FUNC_TRACE(); - hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - - rss_hf = dev->data->dev_conf.rx_adv_conf.rss_conf.rss_hf; - if (rss_hf == 0) { /* Disable RSS */ - ixgbe_rss_disable(dev); - return; - } - hash_key = dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key; - if (hash_key == NULL) - hash_key = rss_intel_key; /* Default hash key */ - - /* Fill in RSS hash key */ - for (i = 0; i < 10; i++) { - rss_key = hash_key[(i * 4)]; - rss_key |= hash_key[(i * 4) + 1] << 8; - rss_key |= hash_key[(i * 4) + 2] << 16; - rss_key |= hash_key[(i * 4) + 3] << 24; - IXGBE_WRITE_REG_ARRAY(hw, IXGBE_RSSRK(0), i, rss_key); - } - /* Fill in redirection table */ - reta = 0; - for (i = 0, j = 0; i < 128; i++, j++) { - if (j == dev->data->nb_rx_queues) j = 0; - reta = (reta << 8) | j; - if ((i & 3) == 3) - IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), rte_bswap32(reta)); + hash_key = rss_conf->rss_key; + if (hash_key != NULL) { + /* Fill in RSS hash key */ + for (i = 0; i < 10; i++) { + rss_key = hash_key[(i * 4)]; + rss_key |= hash_key[(i * 4) + 1] << 8; + rss_key |= hash_key[(i * 4) + 2] << 16; + rss_key |= hash_key[(i * 4) + 3] << 24; + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_RSSRK(0), i, rss_key); + } } - /* Set configured hashing functions in MRQC register */ - mrqc = IXGBE_MRQC_RSSEN; /* RSS enable */ + /* Set configured hashing protocols in MRQC register */ + rss_hf = rss_conf->rss_hf; + mrqc = IXGBE_MRQC_RSSEN; /* Enable RSS */ if (rss_hf & ETH_RSS_IPV4) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4; - if (rss_hf & ETH_RSS_IPV4_TCP) + if (rss_hf & ETH_RSS_NONFRAG_IPV4_TCP) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_TCP; if (rss_hf & ETH_RSS_IPV6) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6; if (rss_hf & ETH_RSS_IPV6_EX) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_EX; - if (rss_hf & ETH_RSS_IPV6_TCP) + if (rss_hf & ETH_RSS_NONFRAG_IPV6_TCP) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_TCP; if (rss_hf & ETH_RSS_IPV6_TCP_EX) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_EX_TCP; - if (rss_hf & ETH_RSS_IPV4_UDP) + if (rss_hf & ETH_RSS_NONFRAG_IPV4_UDP) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP; - if (rss_hf & ETH_RSS_IPV6_UDP) + if (rss_hf & ETH_RSS_NONFRAG_IPV6_UDP) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; if (rss_hf & ETH_RSS_IPV6_UDP_EX) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_EX_UDP; IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); } +int +ixgbe_dev_rss_hash_update(struct rte_eth_dev *dev, + struct rte_eth_rss_conf *rss_conf) +{ + struct ixgbe_hw *hw; + uint32_t mrqc; + uint64_t rss_hf; + + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + /* + * Excerpt from section 7.1.2.8 Receive-Side Scaling (RSS): + * "RSS enabling cannot be done dynamically while it must be + * preceded by a software reset" + * Before changing anything, first check that the update RSS operation + * does not attempt to disable RSS, if RSS was enabled at + * initialization time, or does not attempt to enable RSS, if RSS was + * disabled at initialization time. + */ + rss_hf = rss_conf->rss_hf & IXGBE_RSS_OFFLOAD_ALL; + mrqc = IXGBE_READ_REG(hw, IXGBE_MRQC); + if (!(mrqc & IXGBE_MRQC_RSSEN)) { /* RSS disabled */ + if (rss_hf != 0) /* Enable RSS */ + return -(EINVAL); + return 0; /* Nothing to do */ + } + /* RSS enabled */ + if (rss_hf == 0) /* Disable RSS */ + return -(EINVAL); + ixgbe_hw_rss_hash_set(hw, rss_conf); + return 0; +} + +int +ixgbe_dev_rss_hash_conf_get(struct rte_eth_dev *dev, + struct rte_eth_rss_conf *rss_conf) +{ + struct ixgbe_hw *hw; + uint8_t *hash_key; + uint32_t mrqc; + uint32_t rss_key; + uint64_t rss_hf; + uint16_t i; + + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + hash_key = rss_conf->rss_key; + if (hash_key != NULL) { + /* Return RSS hash key */ + for (i = 0; i < 10; i++) { + rss_key = IXGBE_READ_REG_ARRAY(hw, IXGBE_RSSRK(0), i); + hash_key[(i * 4)] = rss_key & 0x000000FF; + hash_key[(i * 4) + 1] = (rss_key >> 8) & 0x000000FF; + hash_key[(i * 4) + 2] = (rss_key >> 16) & 0x000000FF; + hash_key[(i * 4) + 3] = (rss_key >> 24) & 0x000000FF; + } + } + + /* Get RSS functions configured in MRQC register */ + mrqc = IXGBE_READ_REG(hw, IXGBE_MRQC); + if ((mrqc & IXGBE_MRQC_RSSEN) == 0) { /* RSS is disabled */ + rss_conf->rss_hf = 0; + return 0; + } + rss_hf = 0; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV4) + rss_hf |= ETH_RSS_IPV4; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV4_TCP) + rss_hf |= ETH_RSS_NONFRAG_IPV4_TCP; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV6) + rss_hf |= ETH_RSS_IPV6; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV6_EX) + rss_hf |= ETH_RSS_IPV6_EX; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV6_TCP) + rss_hf |= ETH_RSS_NONFRAG_IPV6_TCP; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV6_EX_TCP) + rss_hf |= ETH_RSS_IPV6_TCP_EX; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV4_UDP) + rss_hf |= ETH_RSS_NONFRAG_IPV4_UDP; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV6_UDP) + rss_hf |= ETH_RSS_NONFRAG_IPV6_UDP; + if (mrqc & IXGBE_MRQC_RSS_FIELD_IPV6_EX_UDP) + rss_hf |= ETH_RSS_IPV6_UDP_EX; + rss_conf->rss_hf = rss_hf; + return 0; +} + +static void +ixgbe_rss_configure(struct rte_eth_dev *dev) +{ + struct rte_eth_rss_conf rss_conf; + struct ixgbe_hw *hw; + uint32_t reta; + uint16_t i; + uint16_t j; + + PMD_INIT_FUNC_TRACE(); + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + /* + * Fill in redirection table + * The byte-swap is needed because NIC registers are in + * little-endian order. + */ + reta = 0; + for (i = 0, j = 0; i < 128; i++, j++) { + if (j == dev->data->nb_rx_queues) + j = 0; + reta = (reta << 8) | j; + if ((i & 3) == 3) + IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), + rte_bswap32(reta)); + } + + /* + * Configure the RSS key and the RSS protocols used to compute + * the RSS hash of input packets. + */ + rss_conf = dev->data->dev_conf.rx_adv_conf.rss_conf; + if ((rss_conf.rss_hf & IXGBE_RSS_OFFLOAD_ALL) == 0) { + ixgbe_rss_disable(dev); + return; + } + if (rss_conf.rss_key == NULL) + rss_conf.rss_key = rss_intel_key; /* Default hash key */ + ixgbe_hw_rss_hash_set(hw, &rss_conf); +} + #define NUM_VFTA_REGISTERS 128 #define NIC_RX_BUFFER_SIZE 0x200 @@ -2477,6 +3003,7 @@ ixgbe_vmdq_dcb_configure(struct rte_eth_dev *dev) } else { vt_ctl |= IXGBE_VT_CTL_DIS_DEFPL; } + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vt_ctl); /* RTRUP2TC: mapping user priorities to traffic classes (TCs) */ @@ -2533,13 +3060,13 @@ ixgbe_vmdq_dcb_configure(struct rte_eth_dev *dev) * @hw: pointer to hardware structure * @dcb_config: pointer to ixgbe_dcb_config structure */ -static void +static void ixgbe_dcb_tx_hw_config(struct ixgbe_hw *hw, struct ixgbe_dcb_config *dcb_config) { uint32_t reg; uint32_t q; - + PMD_INIT_FUNC_TRACE(); if (hw->mac.type != ixgbe_mac_82598EB) { /* Disable the Tx desc arbiter so that MTQC can be changed */ @@ -2587,21 +3114,21 @@ ixgbe_vmdq_dcb_hw_tx_config(struct rte_eth_dev *dev, { struct rte_eth_vmdq_dcb_tx_conf *vmdq_tx_conf = &dev->data->dev_conf.tx_adv_conf.vmdq_dcb_tx_conf; - struct ixgbe_hw *hw = + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - + PMD_INIT_FUNC_TRACE(); - if (hw->mac.type != ixgbe_mac_82598EB) + if (hw->mac.type != ixgbe_mac_82598EB) /*PF VF Transmit Enable*/ IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), vmdq_tx_conf->nb_queue_pools == ETH_16_POOLS ? 0xFFFF : 0xFFFFFFFF); - + /*Configure general DCB TX parameters*/ ixgbe_dcb_tx_hw_config(hw,dcb_config); return; } -static void +static void ixgbe_vmdq_dcb_rx_config(struct rte_eth_dev *dev, struct ixgbe_dcb_config *dcb_config) { @@ -2628,15 +3155,15 @@ ixgbe_vmdq_dcb_rx_config(struct rte_eth_dev *dev, } } -static void +static void ixgbe_dcb_vt_tx_config(struct rte_eth_dev *dev, struct ixgbe_dcb_config *dcb_config) -{ +{ struct rte_eth_vmdq_dcb_tx_conf *vmdq_tx_conf = &dev->data->dev_conf.tx_adv_conf.vmdq_dcb_tx_conf; struct ixgbe_dcb_tc_config *tc; uint8_t i,j; - + /* convert rte_eth_conf.rx_adv_conf to struct ixgbe_dcb_config */ if (vmdq_tx_conf->nb_queue_pools == ETH_16_POOLS ) { dcb_config->num_tcs.pg_tcs = ETH_8_TCS; @@ -2657,7 +3184,7 @@ ixgbe_dcb_vt_tx_config(struct rte_eth_dev *dev, return; } -static void +static void ixgbe_dcb_rx_config(struct rte_eth_dev *dev, struct ixgbe_dcb_config *dcb_config) { @@ -2668,8 +3195,8 @@ ixgbe_dcb_rx_config(struct rte_eth_dev *dev, dcb_config->num_tcs.pg_tcs = (uint8_t)rx_conf->nb_tcs; dcb_config->num_tcs.pfc_tcs = (uint8_t)rx_conf->nb_tcs; - - /* User Priority to Traffic Class mapping */ + + /* User Priority to Traffic Class mapping */ for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++) { j = rx_conf->dcb_queue[i]; tc = &dcb_config->tc_config[j]; @@ -2678,7 +3205,7 @@ ixgbe_dcb_rx_config(struct rte_eth_dev *dev, } } -static void +static void ixgbe_dcb_tx_config(struct rte_eth_dev *dev, struct ixgbe_dcb_config *dcb_config) { @@ -2689,8 +3216,8 @@ ixgbe_dcb_tx_config(struct rte_eth_dev *dev, dcb_config->num_tcs.pg_tcs = (uint8_t)tx_conf->nb_tcs; dcb_config->num_tcs.pfc_tcs = (uint8_t)tx_conf->nb_tcs; - - /* User Priority to Traffic Class mapping */ + + /* User Priority to Traffic Class mapping */ for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++) { j = tx_conf->dcb_queue[i]; tc = &dcb_config->tc_config[j]; @@ -2750,7 +3277,7 @@ ixgbe_dcb_rx_hw_config(struct ixgbe_hw *hw, vlanctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); vlanctrl |= IXGBE_VLNCTRL_VFE ; /* enable vlan filters */ IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlanctrl); - + /* VFTA - enable all vlan filters */ for (i = 0; i < NUM_VFTA_REGISTERS; i++) { IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), 0xFFFFFFFF); @@ -2762,11 +3289,11 @@ ixgbe_dcb_rx_hw_config(struct ixgbe_hw *hw, */ reg = IXGBE_RTRPCS_RRM | IXGBE_RTRPCS_RAC; IXGBE_WRITE_REG(hw, IXGBE_RTRPCS, reg); - + return; } -static void +static void ixgbe_dcb_hw_arbite_rx_config(struct ixgbe_hw *hw, uint16_t *refill, uint16_t *max,uint8_t *bwg_id, uint8_t *tsa, uint8_t *map) { @@ -2776,6 +3303,8 @@ ixgbe_dcb_hw_arbite_rx_config(struct ixgbe_hw *hw, uint16_t *refill, break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max, bwg_id, tsa, map); break; @@ -2784,7 +3313,7 @@ ixgbe_dcb_hw_arbite_rx_config(struct ixgbe_hw *hw, uint16_t *refill, } } -static void +static void ixgbe_dcb_hw_arbite_tx_config(struct ixgbe_hw *hw, uint16_t *refill, uint16_t *max, uint8_t *bwg_id, uint8_t *tsa, uint8_t *map) { @@ -2795,6 +3324,8 @@ ixgbe_dcb_hw_arbite_tx_config(struct ixgbe_hw *hw, uint16_t *refill, uint16_t *m break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max, bwg_id,tsa); ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max, bwg_id,tsa, map); break; @@ -2807,7 +3338,7 @@ ixgbe_dcb_hw_arbite_tx_config(struct ixgbe_hw *hw, uint16_t *refill, uint16_t *m #define DCB_TX_CONFIG 1 #define DCB_TX_PB 1024 /** - * ixgbe_dcb_hw_configure - Enable DCB and configure + * ixgbe_dcb_hw_configure - Enable DCB and configure * general DCB in VT mode and non-VT mode parameters * @dev: pointer to rte_eth_dev structure * @dcb_config: pointer to ixgbe_dcb_config structure @@ -2827,17 +3358,17 @@ ixgbe_dcb_hw_configure(struct rte_eth_dev *dev, uint16_t max[IXGBE_DCB_MAX_TRAFFIC_CLASS] = {0}; uint8_t map[IXGBE_DCB_MAX_TRAFFIC_CLASS] = {0}; struct ixgbe_dcb_tc_config *tc; - uint32_t max_frame = dev->data->max_frame_size; - struct ixgbe_hw *hw = + uint32_t max_frame = dev->data->mtu + ETHER_HDR_LEN + ETHER_CRC_LEN; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); switch(dev->data->dev_conf.rxmode.mq_mode){ - case ETH_VMDQ_DCB: + case ETH_MQ_RX_VMDQ_DCB: dcb_config->vt_mode = true; if (hw->mac.type != ixgbe_mac_82598EB) { config_dcb_rx = DCB_RX_CONFIG; /* - *get dcb and VT rx configuration parameters + *get dcb and VT rx configuration parameters *from rte_eth_conf */ ixgbe_vmdq_dcb_rx_config(dev,dcb_config); @@ -2845,7 +3376,7 @@ ixgbe_dcb_hw_configure(struct rte_eth_dev *dev, ixgbe_vmdq_dcb_configure(dev); } break; - case ETH_DCB_RX: + case ETH_MQ_RX_DCB: dcb_config->vt_mode = false; config_dcb_rx = DCB_RX_CONFIG; /* Get dcb TX configuration parameters from rte_eth_conf */ @@ -2854,11 +3385,11 @@ ixgbe_dcb_hw_configure(struct rte_eth_dev *dev, ixgbe_dcb_rx_hw_config(hw, dcb_config); break; default: - PMD_INIT_LOG(ERR, "Incorrect DCB RX mode configuration\n"); + PMD_INIT_LOG(ERR, "Incorrect DCB RX mode configuration"); break; } switch (dev->data->dev_conf.txmode.mq_mode) { - case ETH_VMDQ_DCB_TX: + case ETH_MQ_TX_VMDQ_DCB: dcb_config->vt_mode = true; config_dcb_tx = DCB_TX_CONFIG; /* get DCB and VT TX configuration parameters from rte_eth_conf */ @@ -2867,16 +3398,16 @@ ixgbe_dcb_hw_configure(struct rte_eth_dev *dev, ixgbe_vmdq_dcb_hw_tx_config(dev,dcb_config); break; - case ETH_DCB_TX: + case ETH_MQ_TX_DCB: dcb_config->vt_mode = false; - config_dcb_tx = DCB_RX_CONFIG; + config_dcb_tx = DCB_TX_CONFIG; /*get DCB TX configuration parameters from rte_eth_conf*/ ixgbe_dcb_tx_config(dev,dcb_config); /*Configure general DCB TX parameters*/ ixgbe_dcb_tx_hw_config(hw, dcb_config); break; default: - PMD_INIT_LOG(ERR, "Incorrect DCB TX mode configuration\n"); + PMD_INIT_LOG(ERR, "Incorrect DCB TX mode configuration"); break; } @@ -2887,7 +3418,7 @@ ixgbe_dcb_hw_configure(struct rte_eth_dev *dev, /* Avoid un-configured priority mapping to TC0 */ uint8_t j = 4; uint8_t mask = 0xFF; - for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES - 4; i++) + for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES - 4; i++) mask = (uint8_t)(mask & (~ (1 << map[i]))); for (i = 0; mask && (i < IXGBE_DCB_MAX_TRAFFIC_CLASS); i++) { if ((mask & 0x1) && (j < ETH_DCB_NUM_USER_PRIORITIES)) @@ -2995,74 +3526,696 @@ ixgbe_dcb_hw_configure(struct rte_eth_dev *dev, void ixgbe_configure_dcb(struct rte_eth_dev *dev) { struct ixgbe_dcb_config *dcb_cfg = - IXGBE_DEV_PRIVATE_TO_DCB_CFG(dev->data->dev_private); - - PMD_INIT_FUNC_TRACE(); - /** Configure DCB hardware **/ - if(((dev->data->dev_conf.rxmode.mq_mode != ETH_RSS) && - (dev->data->nb_rx_queues == ETH_DCB_NUM_QUEUES))|| - ((dev->data->dev_conf.txmode.mq_mode != ETH_DCB_NONE) && - (dev->data->nb_tx_queues == ETH_DCB_NUM_QUEUES))) { - ixgbe_dcb_hw_configure(dev,dcb_cfg); - } - return; -} + IXGBE_DEV_PRIVATE_TO_DCB_CFG(dev->data->dev_private); + struct rte_eth_conf *dev_conf = &(dev->data->dev_conf); -static int -ixgbe_alloc_rx_queue_mbufs(struct igb_rx_queue *rxq) -{ - struct igb_rx_entry *rxe = rxq->sw_ring; - uint64_t dma_addr; - unsigned i; + PMD_INIT_FUNC_TRACE(); - /* Initialize software ring entries */ - for (i = 0; i < rxq->nb_rx_desc; i++) { - volatile union ixgbe_adv_rx_desc *rxd; - struct rte_mbuf *mbuf = rte_rxmbuf_alloc(rxq->mb_pool); - if (mbuf == NULL) { - PMD_INIT_LOG(ERR, "RX mbuf alloc failed queue_id=%u\n", - (unsigned) rxq->queue_id); - return (-ENOMEM); - } + /* check support mq_mode for DCB */ + if ((dev_conf->rxmode.mq_mode != ETH_MQ_RX_VMDQ_DCB) && + (dev_conf->rxmode.mq_mode != ETH_MQ_RX_DCB)) + return; - rte_mbuf_refcnt_set(mbuf, 1); - mbuf->type = RTE_MBUF_PKT; - mbuf->pkt.next = NULL; - mbuf->pkt.data = (char *)mbuf->buf_addr + RTE_PKTMBUF_HEADROOM; - mbuf->pkt.nb_segs = 1; - mbuf->pkt.in_port = rxq->port_id; + if (dev->data->nb_rx_queues != ETH_DCB_NUM_QUEUES) + return; - dma_addr = - rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mbuf)); - rxd = &rxq->rx_ring[i]; - rxd->read.hdr_addr = dma_addr; - rxd->read.pkt_addr = dma_addr; - rxe[i].mbuf = mbuf; - } + /** Configure DCB hardware **/ + ixgbe_dcb_hw_configure(dev,dcb_cfg); - return 0; + return; } /* - * Initializes Receive Unit. + * VMDq only support for 10 GbE NIC. */ -int -ixgbe_dev_rx_init(struct rte_eth_dev *dev) +static void +ixgbe_vmdq_rx_hw_configure(struct rte_eth_dev *dev) { - struct ixgbe_hw *hw; - struct igb_rx_queue *rxq; - struct rte_pktmbuf_pool_private *mbp_priv; - uint64_t bus_addr; - uint32_t rxctrl; - uint32_t fctrl; - uint32_t hlreg0; - uint32_t maxfrs; - uint32_t srrctl; - uint32_t rdrxctl; - uint32_t rxcsum; - uint16_t buf_size; + struct rte_eth_vmdq_rx_conf *cfg; + struct ixgbe_hw *hw; + enum rte_eth_nb_pools num_pools; + uint32_t mrqc, vt_ctl, vlanctrl; + uint32_t vmolr = 0; + int i; + + PMD_INIT_FUNC_TRACE(); + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + cfg = &dev->data->dev_conf.rx_adv_conf.vmdq_rx_conf; + num_pools = cfg->nb_queue_pools; + + ixgbe_rss_disable(dev); + + /* MRQC: enable vmdq */ + mrqc = IXGBE_MRQC_VMDQEN; + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); + + /* PFVTCTL: turn on virtualisation and set the default pool */ + vt_ctl = IXGBE_VT_CTL_VT_ENABLE | IXGBE_VT_CTL_REPLEN; + if (cfg->enable_default_pool) + vt_ctl |= (cfg->default_pool << IXGBE_VT_CTL_POOL_SHIFT); + else + vt_ctl |= IXGBE_VT_CTL_DIS_DEFPL; + + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vt_ctl); + + for (i = 0; i < (int)num_pools; i++) { + vmolr = ixgbe_convert_vm_rx_mask_to_val(cfg->rx_mode, vmolr); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(i), vmolr); + } + + /* VLNCTRL: enable vlan filtering and allow all vlan tags through */ + vlanctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlanctrl |= IXGBE_VLNCTRL_VFE ; /* enable vlan filters */ + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlanctrl); + + /* VFTA - enable all vlan filters */ + for (i = 0; i < NUM_VFTA_REGISTERS; i++) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), UINT32_MAX); + + /* VFRE: pool enabling for receive - 64 */ + IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), UINT32_MAX); + if (num_pools == ETH_64_POOLS) + IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), UINT32_MAX); + + /* + * MPSAR - allow pools to read specific mac addresses + * In this case, all pools should be able to read from mac addr 0 + */ + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(0), UINT32_MAX); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(0), UINT32_MAX); + + /* PFVLVF, PFVLVFB: set up filters for vlan tags as configured */ + for (i = 0; i < cfg->nb_pool_maps; i++) { + /* set vlan id in VF register and set the valid bit */ + IXGBE_WRITE_REG(hw, IXGBE_VLVF(i), (IXGBE_VLVF_VIEN | \ + (cfg->pool_map[i].vlan_id & IXGBE_RXD_VLAN_ID_MASK))); + /* + * Put the allowed pools in VFB reg. As we only have 16 or 64 + * pools, we only need to use the first half of the register + * i.e. bits 0-31 + */ + if (((cfg->pool_map[i].pools >> 32) & UINT32_MAX) == 0) + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(i*2), \ + (cfg->pool_map[i].pools & UINT32_MAX)); + else + IXGBE_WRITE_REG(hw, IXGBE_VLVFB((i*2+1)), \ + ((cfg->pool_map[i].pools >> 32) \ + & UINT32_MAX)); + + } + + /* PFDMA Tx General Switch Control Enables VMDQ loopback */ + if (cfg->enable_loop_back) { + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + for (i = 0; i < RTE_IXGBE_VMTXSW_REGISTER_COUNT; i++) + IXGBE_WRITE_REG(hw, IXGBE_VMTXSW(i), UINT32_MAX); + } + + IXGBE_WRITE_FLUSH(hw); +} + +/* + * ixgbe_dcb_config_tx_hw_config - Configure general VMDq TX parameters + * @hw: pointer to hardware structure + */ +static void +ixgbe_vmdq_tx_hw_configure(struct ixgbe_hw *hw) +{ + uint32_t reg; + uint32_t q; + + PMD_INIT_FUNC_TRACE(); + /*PF VF Transmit Enable*/ + IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), UINT32_MAX); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), UINT32_MAX); + + /* Disable the Tx desc arbiter so that MTQC can be changed */ + reg = IXGBE_READ_REG(hw, IXGBE_RTTDCS); + reg |= IXGBE_RTTDCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, reg); + + reg = IXGBE_MTQC_VT_ENA | IXGBE_MTQC_64VF; + IXGBE_WRITE_REG(hw, IXGBE_MTQC, reg); + + /* Disable drop for all queues */ + for (q = 0; q < IXGBE_MAX_RX_QUEUE_NUM; q++) + IXGBE_WRITE_REG(hw, IXGBE_QDE, + (IXGBE_QDE_WRITE | (q << IXGBE_QDE_IDX_SHIFT))); + + /* Enable the Tx desc arbiter */ + reg = IXGBE_READ_REG(hw, IXGBE_RTTDCS); + reg &= ~IXGBE_RTTDCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, reg); + + IXGBE_WRITE_FLUSH(hw); + + return; +} + +static int +ixgbe_alloc_rx_queue_mbufs(struct ixgbe_rx_queue *rxq) +{ + struct ixgbe_rx_entry *rxe = rxq->sw_ring; + uint64_t dma_addr; + unsigned i; + + /* Initialize software ring entries */ + for (i = 0; i < rxq->nb_rx_desc; i++) { + volatile union ixgbe_adv_rx_desc *rxd; + struct rte_mbuf *mbuf = rte_rxmbuf_alloc(rxq->mb_pool); + if (mbuf == NULL) { + PMD_INIT_LOG(ERR, "RX mbuf alloc failed queue_id=%u", + (unsigned) rxq->queue_id); + return (-ENOMEM); + } + + rte_mbuf_refcnt_set(mbuf, 1); + mbuf->next = NULL; + mbuf->data_off = RTE_PKTMBUF_HEADROOM; + mbuf->nb_segs = 1; + mbuf->port = rxq->port_id; + + dma_addr = + rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mbuf)); + rxd = &rxq->rx_ring[i]; + rxd->read.hdr_addr = dma_addr; + rxd->read.pkt_addr = dma_addr; + rxe[i].mbuf = mbuf; + } + + return 0; +} + +static int +ixgbe_config_vf_rss(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw; + uint32_t mrqc; + + ixgbe_rss_configure(dev); + + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + /* MRQC: enable VF RSS */ + mrqc = IXGBE_READ_REG(hw, IXGBE_MRQC); + mrqc &= ~IXGBE_MRQC_MRQE_MASK; + switch (RTE_ETH_DEV_SRIOV(dev).active) { + case ETH_64_POOLS: + mrqc |= IXGBE_MRQC_VMDQRSS64EN; + break; + + case ETH_32_POOLS: + mrqc |= IXGBE_MRQC_VMDQRSS32EN; + break; + + default: + PMD_INIT_LOG(ERR, "Invalid pool number in IOV mode with VMDQ RSS"); + return -EINVAL; + } + + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); + + return 0; +} + +static int +ixgbe_config_vf_default(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + switch (RTE_ETH_DEV_SRIOV(dev).active) { + case ETH_64_POOLS: + IXGBE_WRITE_REG(hw, IXGBE_MRQC, + IXGBE_MRQC_VMDQEN); + break; + + case ETH_32_POOLS: + IXGBE_WRITE_REG(hw, IXGBE_MRQC, + IXGBE_MRQC_VMDQRT4TCEN); + break; + + case ETH_16_POOLS: + IXGBE_WRITE_REG(hw, IXGBE_MRQC, + IXGBE_MRQC_VMDQRT8TCEN); + break; + default: + PMD_INIT_LOG(ERR, + "invalid pool number in IOV mode"); + break; + } + return 0; +} + +static int +ixgbe_dev_mq_rx_configure(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (hw->mac.type == ixgbe_mac_82598EB) + return 0; + + if (RTE_ETH_DEV_SRIOV(dev).active == 0) { + /* + * SRIOV inactive scheme + * any DCB/RSS w/o VMDq multi-queue setting + */ + switch (dev->data->dev_conf.rxmode.mq_mode) { + case ETH_MQ_RX_RSS: + ixgbe_rss_configure(dev); + break; + + case ETH_MQ_RX_VMDQ_DCB: + ixgbe_vmdq_dcb_configure(dev); + break; + + case ETH_MQ_RX_VMDQ_ONLY: + ixgbe_vmdq_rx_hw_configure(dev); + break; + + case ETH_MQ_RX_NONE: + /* if mq_mode is none, disable rss mode.*/ + default: ixgbe_rss_disable(dev); + } + } else { + /* + * SRIOV active scheme + * Support RSS together with VMDq & SRIOV + */ + switch (dev->data->dev_conf.rxmode.mq_mode) { + case ETH_MQ_RX_RSS: + case ETH_MQ_RX_VMDQ_RSS: + ixgbe_config_vf_rss(dev); + break; + + /* FIXME if support DCB/RSS together with VMDq & SRIOV */ + case ETH_MQ_RX_VMDQ_DCB: + case ETH_MQ_RX_VMDQ_DCB_RSS: + PMD_INIT_LOG(ERR, + "Could not support DCB with VMDq & SRIOV"); + return -1; + default: + ixgbe_config_vf_default(dev); + break; + } + } + + return 0; +} + +static int +ixgbe_dev_mq_tx_configure(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t mtqc; + uint32_t rttdcs; + + if (hw->mac.type == ixgbe_mac_82598EB) + return 0; + + /* disable arbiter before setting MTQC */ + rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS); + rttdcs |= IXGBE_RTTDCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); + + if (RTE_ETH_DEV_SRIOV(dev).active == 0) { + /* + * SRIOV inactive scheme + * any DCB w/o VMDq multi-queue setting + */ + if (dev->data->dev_conf.txmode.mq_mode == ETH_MQ_TX_VMDQ_ONLY) + ixgbe_vmdq_tx_hw_configure(hw); + else { + mtqc = IXGBE_MTQC_64Q_1PB; + IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); + } + } else { + switch (RTE_ETH_DEV_SRIOV(dev).active) { + + /* + * SRIOV active scheme + * FIXME if support DCB together with VMDq & SRIOV + */ + case ETH_64_POOLS: + mtqc = IXGBE_MTQC_VT_ENA | IXGBE_MTQC_64VF; + break; + case ETH_32_POOLS: + mtqc = IXGBE_MTQC_VT_ENA | IXGBE_MTQC_32VF; + break; + case ETH_16_POOLS: + mtqc = IXGBE_MTQC_VT_ENA | IXGBE_MTQC_RT_ENA | + IXGBE_MTQC_8TC_8TQ; + break; + default: + mtqc = IXGBE_MTQC_64Q_1PB; + PMD_INIT_LOG(ERR, "invalid pool number in IOV mode"); + } + IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); + } + + /* re-enable arbiter */ + rttdcs &= ~IXGBE_RTTDCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); + + return 0; +} + +/** + * ixgbe_get_rscctl_maxdesc - Calculate the RSCCTL[n].MAXDESC for PF + * + * Return the RSCCTL[n].MAXDESC for 82599 and x540 PF devices according to the + * spec rev. 3.0 chapter 8.2.3.8.13. + * + * @pool Memory pool of the Rx queue + */ +static inline uint32_t +ixgbe_get_rscctl_maxdesc(struct rte_mempool *pool) +{ + struct rte_pktmbuf_pool_private *mp_priv = rte_mempool_get_priv(pool); + + /* MAXDESC * SRRCTL.BSIZEPKT must not exceed 64 KB minus one */ + uint16_t maxdesc = + IPV4_MAX_PKT_LEN / + (mp_priv->mbuf_data_room_size - RTE_PKTMBUF_HEADROOM); + + if (maxdesc >= 16) + return IXGBE_RSCCTL_MAXDESC_16; + else if (maxdesc >= 8) + return IXGBE_RSCCTL_MAXDESC_8; + else if (maxdesc >= 4) + return IXGBE_RSCCTL_MAXDESC_4; + else + return IXGBE_RSCCTL_MAXDESC_1; +} + +/** + * ixgbe_set_ivar - Setup the correct IVAR register for a particular MSIX + * interrupt + * + * (Taken from FreeBSD tree) + * (yes this is all very magic and confusing :) + * + * @dev port handle + * @entry the register array entry + * @vector the MSIX vector for this queue + * @type RX/TX/MISC + */ +static void +ixgbe_set_ivar(struct rte_eth_dev *dev, u8 entry, u8 vector, s8 type) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + u32 ivar, index; + + vector |= IXGBE_IVAR_ALLOC_VAL; + + switch (hw->mac.type) { + + case ixgbe_mac_82598EB: + if (type == -1) + entry = IXGBE_IVAR_OTHER_CAUSES_INDEX; + else + entry += (type * 64); + index = (entry >> 2) & 0x1F; + ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index)); + ivar &= ~(0xFF << (8 * (entry & 0x3))); + ivar |= (vector << (8 * (entry & 0x3))); + IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar); + break; + + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + if (type == -1) { /* MISC IVAR */ + index = (entry & 1) * 8; + ivar = IXGBE_READ_REG(hw, IXGBE_IVAR_MISC); + ivar &= ~(0xFF << index); + ivar |= (vector << index); + IXGBE_WRITE_REG(hw, IXGBE_IVAR_MISC, ivar); + } else { /* RX/TX IVARS */ + index = (16 * (entry & 1)) + (8 * type); + ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(entry >> 1)); + ivar &= ~(0xFF << index); + ivar |= (vector << index); + IXGBE_WRITE_REG(hw, IXGBE_IVAR(entry >> 1), ivar); + } + + break; + + default: + break; + } +} + +void ixgbe_set_rx_function(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + /* + * In order to allow Vector Rx there are a few configuration + * conditions to be met and Rx Bulk Allocation should be allowed. + */ + if (ixgbe_rx_vec_dev_conf_condition_check(dev) || + !hw->rx_bulk_alloc_allowed) { + PMD_INIT_LOG(DEBUG, "Port[%d] doesn't meet Vector Rx " + "preconditions or RTE_IXGBE_INC_VECTOR is " + "not enabled", + dev->data->port_id); + + hw->rx_vec_allowed = false; + } + + /* + * Initialize the appropriate LRO callback. + * + * If all queues satisfy the bulk allocation preconditions + * (hw->rx_bulk_alloc_allowed is TRUE) then we may use bulk allocation. + * Otherwise use a single allocation version. + */ + if (dev->data->lro) { + if (hw->rx_bulk_alloc_allowed) { + PMD_INIT_LOG(INFO, "LRO is requested. Using a bulk " + "allocation version"); + dev->rx_pkt_burst = ixgbe_recv_pkts_lro_bulk_alloc; + } else { + PMD_INIT_LOG(INFO, "LRO is requested. Using a single " + "allocation version"); + dev->rx_pkt_burst = ixgbe_recv_pkts_lro_single_alloc; + } + } else if (dev->data->scattered_rx) { + /* + * Set the non-LRO scattered callback: there are Vector and + * single allocation versions. + */ + if (hw->rx_vec_allowed) { + PMD_INIT_LOG(DEBUG, "Using Vector Scattered Rx " + "callback (port=%d).", + dev->data->port_id); + + dev->rx_pkt_burst = ixgbe_recv_scattered_pkts_vec; + } else { + PMD_INIT_LOG(DEBUG, "Using Regualr (non-vector) " + "Scattered Rx callback " + "(port=%d).", + dev->data->port_id); + + dev->rx_pkt_burst = ixgbe_recv_scattered_pkts; + } + /* + * Below we set "simple" callbacks according to port/queues parameters. + * If parameters allow we are going to choose between the following + * callbacks: + * - Vector + * - Bulk Allocation + * - Single buffer allocation (the simplest one) + */ + } else if (hw->rx_vec_allowed) { + PMD_INIT_LOG(INFO, "Vector rx enabled, please make sure RX " + "burst size no less than 32."); + + dev->rx_pkt_burst = ixgbe_recv_pkts_vec; + } else if (hw->rx_bulk_alloc_allowed) { + PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are " + "satisfied. Rx Burst Bulk Alloc function " + "will be used on port=%d.", + dev->data->port_id); + + dev->rx_pkt_burst = ixgbe_recv_pkts_bulk_alloc; + } else { + PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are not " + "satisfied, or Scattered Rx is requested, " + "or RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC " + "is not enabled (port=%d).", + dev->data->port_id); + + dev->rx_pkt_burst = ixgbe_recv_pkts; + } +} + +/** + * ixgbe_set_rsc - configure RSC related port HW registers + * + * Configures the port's RSC related registers according to the 4.6.7.2 chapter + * of 82599 Spec (x540 configuration is virtually the same). + * + * @dev port handle + * + * Returns 0 in case of success or a non-zero error code + */ +static int +ixgbe_set_rsc(struct rte_eth_dev *dev) +{ + struct rte_eth_rxmode *rx_conf = &dev->data->dev_conf.rxmode; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct rte_eth_dev_info dev_info = { 0 }; + bool rsc_capable = false; + uint16_t i; + uint32_t rdrxctl; + + /* Sanity check */ + dev->dev_ops->dev_infos_get(dev, &dev_info); + if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_TCP_LRO) + rsc_capable = true; + + if (!rsc_capable && rx_conf->enable_lro) { + PMD_INIT_LOG(CRIT, "LRO is requested on HW that doesn't " + "support it"); + return -EINVAL; + } + + /* RSC global configuration (chapter 4.6.7.2.1 of 82599 Spec) */ + + if (!rx_conf->hw_strip_crc && rx_conf->enable_lro) { + /* + * According to chapter of 4.6.7.2.1 of the Spec Rev. + * 3.0 RSC configuration requires HW CRC stripping being + * enabled. If user requested both HW CRC stripping off + * and RSC on - return an error. + */ + PMD_INIT_LOG(CRIT, "LRO can't be enabled when HW CRC " + "is disabled"); + return -EINVAL; + } + + /* RFCTL configuration */ + if (rsc_capable) { + uint32_t rfctl = IXGBE_READ_REG(hw, IXGBE_RFCTL); + if (rx_conf->enable_lro) + /* + * Since NFS packets coalescing is not supported - clear + * RFCTL.NFSW_DIS and RFCTL.NFSR_DIS when RSC is + * enabled. + */ + rfctl &= ~(IXGBE_RFCTL_RSC_DIS | IXGBE_RFCTL_NFSW_DIS | + IXGBE_RFCTL_NFSR_DIS); + else + rfctl |= IXGBE_RFCTL_RSC_DIS; + + IXGBE_WRITE_REG(hw, IXGBE_RFCTL, rfctl); + } + + /* If LRO hasn't been requested - we are done here. */ + if (!rx_conf->enable_lro) + return 0; + + /* Set RDRXCTL.RSCACKC bit */ + rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL); + rdrxctl |= IXGBE_RDRXCTL_RSCACKC; + IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl); + + /* Per-queue RSC configuration (chapter 4.6.7.2.2 of 82599 Spec) */ + for (i = 0; i < dev->data->nb_rx_queues; i++) { + struct ixgbe_rx_queue *rxq = dev->data->rx_queues[i]; + uint32_t srrctl = + IXGBE_READ_REG(hw, IXGBE_SRRCTL(rxq->reg_idx)); + uint32_t rscctl = + IXGBE_READ_REG(hw, IXGBE_RSCCTL(rxq->reg_idx)); + uint32_t psrtype = + IXGBE_READ_REG(hw, IXGBE_PSRTYPE(rxq->reg_idx)); + uint32_t eitr = + IXGBE_READ_REG(hw, IXGBE_EITR(rxq->reg_idx)); + + /* + * ixgbe PMD doesn't support header-split at the moment. + * + * Following the 4.6.7.2.1 chapter of the 82599/x540 + * Spec if RSC is enabled the SRRCTL[n].BSIZEHEADER + * should be configured even if header split is not + * enabled. We will configure it 128 bytes following the + * recommendation in the spec. + */ + srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK; + srrctl |= (128 << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & + IXGBE_SRRCTL_BSIZEHDR_MASK; + + /* + * TODO: Consider setting the Receive Descriptor Minimum + * Threshold Size for an RSC case. This is not an obviously + * beneficiary option but the one worth considering... + */ + + rscctl |= IXGBE_RSCCTL_RSCEN; + rscctl |= ixgbe_get_rscctl_maxdesc(rxq->mb_pool); + psrtype |= IXGBE_PSRTYPE_TCPHDR; + + /* + * RSC: Set ITR interval corresponding to 2K ints/s. + * + * Full-sized RSC aggregations for a 10Gb/s link will + * arrive at about 20K aggregation/s rate. + * + * 2K inst/s rate will make only 10% of the + * aggregations to be closed due to the interrupt timer + * expiration for a streaming at wire-speed case. + * + * For a sparse streaming case this setting will yield + * at most 500us latency for a single RSC aggregation. + */ + eitr &= ~IXGBE_EITR_ITR_INT_MASK; + eitr |= IXGBE_EITR_INTERVAL_US(500) | IXGBE_EITR_CNT_WDIS; + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(rxq->reg_idx), srrctl); + IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(rxq->reg_idx), rscctl); + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(rxq->reg_idx), psrtype); + IXGBE_WRITE_REG(hw, IXGBE_EITR(rxq->reg_idx), eitr); + + /* + * RSC requires the mapping of the queue to the + * interrupt vector. + */ + ixgbe_set_ivar(dev, rxq->reg_idx, i, 0); + + rxq->rsc_en = 1; + } + + dev->data->lro = 1; + + PMD_INIT_LOG(INFO, "enabling LRO mode"); + + return 0; +} + +/* + * Initializes Receive Unit. + */ +int +ixgbe_dev_rx_init(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw; + struct ixgbe_rx_queue *rxq; + struct rte_pktmbuf_pool_private *mbp_priv; + uint64_t bus_addr; + uint32_t rxctrl; + uint32_t fctrl; + uint32_t hlreg0; + uint32_t maxfrs; + uint32_t srrctl; + uint32_t rdrxctl; + uint32_t rxcsum; + uint16_t buf_size; uint16_t i; - int ret; + struct rte_eth_rxmode *rx_conf = &dev->data->dev_conf.rxmode; + int rc; PMD_INIT_FUNC_TRACE(); hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); @@ -3085,7 +4238,7 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev) * Configure CRC stripping, if any. */ hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); - if (dev->data->dev_conf.rxmode.hw_strip_crc) + if (rx_conf->hw_strip_crc) hlreg0 |= IXGBE_HLREG0_RXCRCSTRP; else hlreg0 &= ~IXGBE_HLREG0_RXCRCSTRP; @@ -3093,51 +4246,53 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev) /* * Configure jumbo frame support, if any. */ - if (dev->data->dev_conf.rxmode.jumbo_frame == 1) { + if (rx_conf->jumbo_frame == 1) { hlreg0 |= IXGBE_HLREG0_JUMBOEN; maxfrs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); maxfrs &= 0x0000FFFF; - maxfrs |= (dev->data->dev_conf.rxmode.max_rx_pkt_len << 16); + maxfrs |= (rx_conf->max_rx_pkt_len << 16); IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, maxfrs); } else hlreg0 &= ~IXGBE_HLREG0_JUMBOEN; + /* + * If loopback mode is configured for 82599, set LPBK bit. + */ + if (hw->mac.type == ixgbe_mac_82599EB && + dev->data->dev_conf.lpbk_mode == IXGBE_LPBK_82599_TX_RX) + hlreg0 |= IXGBE_HLREG0_LPBK; + else + hlreg0 &= ~IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); /* Setup RX queues */ for (i = 0; i < dev->data->nb_rx_queues; i++) { rxq = dev->data->rx_queues[i]; - /* Allocate buffers for descriptor rings */ - ret = ixgbe_alloc_rx_queue_mbufs(rxq); - if (ret) - return ret; - /* * Reset crc_len in case it was changed after queue setup by a * call to configure. */ - rxq->crc_len = (uint8_t) - ((dev->data->dev_conf.rxmode.hw_strip_crc) ? 0 : - ETHER_CRC_LEN); + rxq->crc_len = rx_conf->hw_strip_crc ? 0 : ETHER_CRC_LEN; /* Setup the Base and Length of the Rx Descriptor Rings */ bus_addr = rxq->rx_ring_phys_addr; - IXGBE_WRITE_REG(hw, IXGBE_RDBAL(i), + IXGBE_WRITE_REG(hw, IXGBE_RDBAL(rxq->reg_idx), (uint32_t)(bus_addr & 0x00000000ffffffffULL)); - IXGBE_WRITE_REG(hw, IXGBE_RDBAH(i), + IXGBE_WRITE_REG(hw, IXGBE_RDBAH(rxq->reg_idx), (uint32_t)(bus_addr >> 32)); - IXGBE_WRITE_REG(hw, IXGBE_RDLEN(i), + IXGBE_WRITE_REG(hw, IXGBE_RDLEN(rxq->reg_idx), rxq->nb_rx_desc * sizeof(union ixgbe_adv_rx_desc)); - IXGBE_WRITE_REG(hw, IXGBE_RDH(i), 0); - IXGBE_WRITE_REG(hw, IXGBE_RDT(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_RDH(rxq->reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_RDT(rxq->reg_idx), 0); /* Configure the SRRCTL register */ #ifdef RTE_HEADER_SPLIT_ENABLE /* * Configure Header Split */ - if (dev->data->dev_conf.rxmode.header_split) { + if (rx_conf->header_split) { if (hw->mac.type == ixgbe_mac_82599EB) { /* Must setup the PSRTYPE register */ uint32_t psrtype; @@ -3145,12 +4300,12 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev) IXGBE_PSRTYPE_UDPHDR | IXGBE_PSRTYPE_IPV4HDR | IXGBE_PSRTYPE_IPV6HDR; - IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(i), psrtype); + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(rxq->reg_idx), psrtype); } - srrctl = ((dev->data->dev_conf.rxmode.split_hdr_size << - IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & - IXGBE_SRRCTL_BSIZEHDR_MASK); - srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; + srrctl = ((rx_conf->split_hdr_size << + IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & + IXGBE_SRRCTL_BSIZEHDR_MASK); + srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; } else #endif srrctl = IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; @@ -3165,44 +4320,30 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev) * The value is in 1 KB resolution. Valid values can be from * 1 KB to 16 KB. */ - mbp_priv = (struct rte_pktmbuf_pool_private *) - ((char *)rxq->mb_pool + sizeof(struct rte_mempool)); + mbp_priv = rte_mempool_get_priv(rxq->mb_pool); buf_size = (uint16_t) (mbp_priv->mbuf_data_room_size - RTE_PKTMBUF_HEADROOM); srrctl |= ((buf_size >> IXGBE_SRRCTL_BSIZEPKT_SHIFT) & IXGBE_SRRCTL_BSIZEPKT_MASK); - IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(i), srrctl); + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(rxq->reg_idx), srrctl); buf_size = (uint16_t) ((srrctl & IXGBE_SRRCTL_BSIZEPKT_MASK) << IXGBE_SRRCTL_BSIZEPKT_SHIFT); /* It adds dual VLAN length for supporting dual VLAN */ - if ((dev->data->dev_conf.rxmode.max_rx_pkt_len + - 2 * IXGBE_VLAN_TAG_SIZE) > buf_size){ + if (dev->data->dev_conf.rxmode.max_rx_pkt_len + + 2 * IXGBE_VLAN_TAG_SIZE > buf_size) dev->data->scattered_rx = 1; - dev->rx_pkt_burst = ixgbe_recv_scattered_pkts; - } } + if (rx_conf->enable_scatter) + dev->data->scattered_rx = 1; + /* - * Configure RSS if device configured with multiple RX queues. + * Device configured with multiple RX queues. */ - if (hw->mac.type == ixgbe_mac_82599EB) { - if (dev->data->nb_rx_queues > 1) - switch (dev->data->dev_conf.rxmode.mq_mode) { - case ETH_RSS: - ixgbe_rss_configure(dev); - break; - - case ETH_VMDQ_DCB: - ixgbe_vmdq_dcb_configure(dev); - break; - - default: ixgbe_rss_disable(dev); - } - else - ixgbe_rss_disable(dev); - } + ixgbe_dev_mq_rx_configure(dev); /* * Setup the Checksum Register. @@ -3211,16 +4352,17 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev) */ rxcsum = IXGBE_READ_REG(hw, IXGBE_RXCSUM); rxcsum |= IXGBE_RXCSUM_PCSD; - if (dev->data->dev_conf.rxmode.hw_ip_checksum) + if (rx_conf->hw_ip_checksum) rxcsum |= IXGBE_RXCSUM_IPPCSE; else rxcsum &= ~IXGBE_RXCSUM_IPPCSE; IXGBE_WRITE_REG(hw, IXGBE_RXCSUM, rxcsum); - if (hw->mac.type == ixgbe_mac_82599EB) { + if (hw->mac.type == ixgbe_mac_82599EB || + hw->mac.type == ixgbe_mac_X540) { rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL); - if (dev->data->dev_conf.rxmode.hw_strip_crc) + if (rx_conf->hw_strip_crc) rdrxctl |= IXGBE_RDRXCTL_CRCSTRIP; else rdrxctl &= ~IXGBE_RDRXCTL_CRCSTRIP; @@ -3228,6 +4370,12 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev) IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl); } + rc = ixgbe_set_rsc(dev); + if (rc) + return rc; + + ixgbe_set_rx_function(dev); + return 0; } @@ -3238,19 +4386,19 @@ void ixgbe_dev_tx_init(struct rte_eth_dev *dev) { struct ixgbe_hw *hw; - struct igb_tx_queue *txq; + struct ixgbe_tx_queue *txq; uint64_t bus_addr; uint32_t hlreg0; uint32_t txctrl; - uint32_t rttdcs; uint16_t i; PMD_INIT_FUNC_TRACE(); hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - /* Enable TX CRC (checksum offload requirement) */ + /* Enable TX CRC (checksum offload requirement) and hw padding + * (TSO requirement) */ hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); - hlreg0 |= IXGBE_HLREG0_TXCRCEN; + hlreg0 |= (IXGBE_HLREG0_TXCRCEN | IXGBE_HLREG0_TXPADEN); IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); /* Setup the Base and Length of the Tx Descriptor Rings */ @@ -3258,15 +4406,15 @@ ixgbe_dev_tx_init(struct rte_eth_dev *dev) txq = dev->data->tx_queues[i]; bus_addr = txq->tx_ring_phys_addr; - IXGBE_WRITE_REG(hw, IXGBE_TDBAL(i), + IXGBE_WRITE_REG(hw, IXGBE_TDBAL(txq->reg_idx), (uint32_t)(bus_addr & 0x00000000ffffffffULL)); - IXGBE_WRITE_REG(hw, IXGBE_TDBAH(i), + IXGBE_WRITE_REG(hw, IXGBE_TDBAH(txq->reg_idx), (uint32_t)(bus_addr >> 32)); - IXGBE_WRITE_REG(hw, IXGBE_TDLEN(i), + IXGBE_WRITE_REG(hw, IXGBE_TDLEN(txq->reg_idx), txq->nb_tx_desc * sizeof(union ixgbe_adv_tx_desc)); /* Setup the HW Tx Head and TX Tail descriptor pointers */ - IXGBE_WRITE_REG(hw, IXGBE_TDH(i), 0); - IXGBE_WRITE_REG(hw, IXGBE_TDT(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_TDH(txq->reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_TDT(txq->reg_idx), 0); /* * Disable Tx Head Writeback RO bit, since this hoses @@ -3275,53 +4423,72 @@ ixgbe_dev_tx_init(struct rte_eth_dev *dev) switch (hw->mac.type) { case ixgbe_mac_82598EB: txctrl = IXGBE_READ_REG(hw, - IXGBE_DCA_TXCTRL(i)); + IXGBE_DCA_TXCTRL(txq->reg_idx)); txctrl &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), + IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(txq->reg_idx), txctrl); break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: default: txctrl = IXGBE_READ_REG(hw, - IXGBE_DCA_TXCTRL_82599(i)); + IXGBE_DCA_TXCTRL_82599(txq->reg_idx)); txctrl &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), + IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(txq->reg_idx), txctrl); break; } } - if (hw->mac.type != ixgbe_mac_82598EB) { - /* disable arbiter before setting MTQC */ - rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS); - rttdcs |= IXGBE_RTTDCS_ARBDIS; - IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); + /* Device configured with multiple TX queues. */ + ixgbe_dev_mq_tx_configure(dev); +} - IXGBE_WRITE_REG(hw, IXGBE_MTQC, IXGBE_MTQC_64Q_1PB); +/* + * Set up link for 82599 loopback mode Tx->Rx. + */ +static inline void +ixgbe_setup_loopback_link_82599(struct ixgbe_hw *hw) +{ + PMD_INIT_FUNC_TRACE(); - /* re-enable arbiter */ - rttdcs &= ~IXGBE_RTTDCS_ARBDIS; - IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); + if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM) != + IXGBE_SUCCESS) { + PMD_INIT_LOG(ERR, "Could not enable loopback mode"); + /* ignore error */ + return; + } } + + /* Restart link */ + IXGBE_WRITE_REG(hw, + IXGBE_AUTOC, + IXGBE_AUTOC_LMS_10G_LINK_NO_AN | IXGBE_AUTOC_FLU); + ixgbe_reset_pipeline_82599(hw); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + msec_delay(50); } + /* * Start Transmit and Receive Units. */ -void +int ixgbe_dev_rxtx_start(struct rte_eth_dev *dev) { struct ixgbe_hw *hw; - struct igb_tx_queue *txq; - struct igb_rx_queue *rxq; + struct ixgbe_tx_queue *txq; + struct ixgbe_rx_queue *rxq; uint32_t txdctl; uint32_t dmatxctl; - uint32_t rxdctl; uint32_t rxctrl; uint16_t i; - int poll_ms; + int ret = 0; PMD_INIT_FUNC_TRACE(); hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); @@ -3329,11 +4496,11 @@ ixgbe_dev_rxtx_start(struct rte_eth_dev *dev) for (i = 0; i < dev->data->nb_tx_queues; i++) { txq = dev->data->tx_queues[i]; /* Setup Transmit Threshold Registers */ - txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(txq->reg_idx)); txdctl |= txq->pthresh & 0x7F; txdctl |= ((txq->hthresh & 0x7F) << 8); txdctl |= ((txq->wthresh & 0x7F) << 16); - IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(i), txdctl); + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(txq->reg_idx), txdctl); } if (hw->mac.type != ixgbe_mac_82598EB) { @@ -3343,49 +4510,225 @@ ixgbe_dev_rxtx_start(struct rte_eth_dev *dev) } for (i = 0; i < dev->data->nb_tx_queues; i++) { - txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); - txdctl |= IXGBE_TXDCTL_ENABLE; - IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(i), txdctl); - - /* Wait until TX Enable ready */ - if (hw->mac.type == ixgbe_mac_82599EB) { - poll_ms = 10; - do { - rte_delay_ms(1); - txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); - } while (--poll_ms && !(txdctl & IXGBE_TXDCTL_ENABLE)); - if (!poll_ms) - PMD_INIT_LOG(ERR, "Could not enable " - "Tx Queue %d\n", i); + txq = dev->data->tx_queues[i]; + if (!txq->tx_deferred_start) { + ret = ixgbe_dev_tx_queue_start(dev, i); + if (ret < 0) + return ret; } } + for (i = 0; i < dev->data->nb_rx_queues; i++) { rxq = dev->data->rx_queues[i]; - rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i)); + if (!rxq->rx_deferred_start) { + ret = ixgbe_dev_rx_queue_start(dev, i); + if (ret < 0) + return ret; + } + } + + /* Enable Receive engine */ + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + if (hw->mac.type == ixgbe_mac_82598EB) + rxctrl |= IXGBE_RXCTRL_DMBYPS; + rxctrl |= IXGBE_RXCTRL_RXEN; + hw->mac.ops.enable_rx_dma(hw, rxctrl); + + /* If loopback mode is enabled for 82599, set up the link accordingly */ + if (hw->mac.type == ixgbe_mac_82599EB && + dev->data->dev_conf.lpbk_mode == IXGBE_LPBK_82599_TX_RX) + ixgbe_setup_loopback_link_82599(hw); + + return 0; +} + +/* + * Start Receive Units for specified queue. + */ +int +ixgbe_dev_rx_queue_start(struct rte_eth_dev *dev, uint16_t rx_queue_id) +{ + struct ixgbe_hw *hw; + struct ixgbe_rx_queue *rxq; + uint32_t rxdctl; + int poll_ms; + + PMD_INIT_FUNC_TRACE(); + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (rx_queue_id < dev->data->nb_rx_queues) { + rxq = dev->data->rx_queues[rx_queue_id]; + + /* Allocate buffers for descriptor rings */ + if (ixgbe_alloc_rx_queue_mbufs(rxq) != 0) { + PMD_INIT_LOG(ERR, "Could not alloc mbuf for queue:%d", + rx_queue_id); + return -1; + } + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(rxq->reg_idx)); rxdctl |= IXGBE_RXDCTL_ENABLE; - IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(i), rxdctl); + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(rxq->reg_idx), rxdctl); /* Wait until RX Enable ready */ - poll_ms = 10; + poll_ms = RTE_IXGBE_REGISTER_POLL_WAIT_10_MS; do { rte_delay_ms(1); - rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i)); + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(rxq->reg_idx)); } while (--poll_ms && !(rxdctl & IXGBE_RXDCTL_ENABLE)); if (!poll_ms) - PMD_INIT_LOG(ERR, "Could not enable " - "Rx Queue %d\n", i); + PMD_INIT_LOG(ERR, "Could not enable Rx Queue %d", + rx_queue_id); rte_wmb(); - IXGBE_WRITE_REG(hw, IXGBE_RDT(i), rxq->nb_rx_desc - 1); - } + IXGBE_WRITE_REG(hw, IXGBE_RDH(rxq->reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_RDT(rxq->reg_idx), rxq->nb_rx_desc - 1); + } else + return -1; - /* Enable Receive engine */ - rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); - if (hw->mac.type == ixgbe_mac_82598EB) - rxctrl |= IXGBE_RXCTRL_DMBYPS; - rxctrl |= IXGBE_RXCTRL_RXEN; - hw->mac.ops.enable_rx_dma(hw, rxctrl); + return 0; +} + +/* + * Stop Receive Units for specified queue. + */ +int +ixgbe_dev_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rx_queue_id) +{ + struct ixgbe_hw *hw; + struct ixgbe_rx_queue *rxq; + uint32_t rxdctl; + int poll_ms; + + PMD_INIT_FUNC_TRACE(); + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (rx_queue_id < dev->data->nb_rx_queues) { + rxq = dev->data->rx_queues[rx_queue_id]; + + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(rxq->reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(rxq->reg_idx), rxdctl); + + /* Wait until RX Enable ready */ + poll_ms = RTE_IXGBE_REGISTER_POLL_WAIT_10_MS; + do { + rte_delay_ms(1); + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(rxq->reg_idx)); + } while (--poll_ms && (rxdctl | IXGBE_RXDCTL_ENABLE)); + if (!poll_ms) + PMD_INIT_LOG(ERR, "Could not disable Rx Queue %d", + rx_queue_id); + + rte_delay_us(RTE_IXGBE_WAIT_100_US); + + ixgbe_rx_queue_release_mbufs(rxq); + ixgbe_reset_rx_queue(hw, rxq); + } else + return -1; + + return 0; +} + + +/* + * Start Transmit Units for specified queue. + */ +int +ixgbe_dev_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id) +{ + struct ixgbe_hw *hw; + struct ixgbe_tx_queue *txq; + uint32_t txdctl; + int poll_ms; + + PMD_INIT_FUNC_TRACE(); + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (tx_queue_id < dev->data->nb_tx_queues) { + txq = dev->data->tx_queues[tx_queue_id]; + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(txq->reg_idx)); + txdctl |= IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(txq->reg_idx), txdctl); + + /* Wait until TX Enable ready */ + if (hw->mac.type == ixgbe_mac_82599EB) { + poll_ms = RTE_IXGBE_REGISTER_POLL_WAIT_10_MS; + do { + rte_delay_ms(1); + txdctl = IXGBE_READ_REG(hw, + IXGBE_TXDCTL(txq->reg_idx)); + } while (--poll_ms && !(txdctl & IXGBE_TXDCTL_ENABLE)); + if (!poll_ms) + PMD_INIT_LOG(ERR, "Could not enable " + "Tx Queue %d", tx_queue_id); + } + rte_wmb(); + IXGBE_WRITE_REG(hw, IXGBE_TDH(txq->reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_TDT(txq->reg_idx), 0); + } else + return -1; + + return 0; } +/* + * Stop Transmit Units for specified queue. + */ +int +ixgbe_dev_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id) +{ + struct ixgbe_hw *hw; + struct ixgbe_tx_queue *txq; + uint32_t txdctl; + uint32_t txtdh, txtdt; + int poll_ms; + + PMD_INIT_FUNC_TRACE(); + hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (tx_queue_id < dev->data->nb_tx_queues) { + txq = dev->data->tx_queues[tx_queue_id]; + + /* Wait until TX queue is empty */ + if (hw->mac.type == ixgbe_mac_82599EB) { + poll_ms = RTE_IXGBE_REGISTER_POLL_WAIT_10_MS; + do { + rte_delay_us(RTE_IXGBE_WAIT_100_US); + txtdh = IXGBE_READ_REG(hw, + IXGBE_TDH(txq->reg_idx)); + txtdt = IXGBE_READ_REG(hw, + IXGBE_TDT(txq->reg_idx)); + } while (--poll_ms && (txtdh != txtdt)); + if (!poll_ms) + PMD_INIT_LOG(ERR, "Tx Queue %d is not empty " + "when stopping.", tx_queue_id); + } + + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(txq->reg_idx)); + txdctl &= ~IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(txq->reg_idx), txdctl); + + /* Wait until TX Enable ready */ + if (hw->mac.type == ixgbe_mac_82599EB) { + poll_ms = RTE_IXGBE_REGISTER_POLL_WAIT_10_MS; + do { + rte_delay_ms(1); + txdctl = IXGBE_READ_REG(hw, + IXGBE_TXDCTL(txq->reg_idx)); + } while (--poll_ms && (txdctl | IXGBE_TXDCTL_ENABLE)); + if (!poll_ms) + PMD_INIT_LOG(ERR, "Could not disable " + "Tx Queue %d", tx_queue_id); + } + + if (txq->ops != NULL) { + txq->ops->release_mbufs(txq); + txq->ops->reset(txq); + } + } else + return -1; + + return 0; +} /* * [VF] Initializes Receive Unit. @@ -3394,10 +4737,10 @@ int ixgbevf_dev_rx_init(struct rte_eth_dev *dev) { struct ixgbe_hw *hw; - struct igb_rx_queue *rxq; + struct ixgbe_rx_queue *rxq; struct rte_pktmbuf_pool_private *mbp_priv; uint64_t bus_addr; - uint32_t srrctl; + uint32_t srrctl, psrtype = 0; uint16_t buf_size; uint16_t i; int ret; @@ -3405,6 +4748,36 @@ ixgbevf_dev_rx_init(struct rte_eth_dev *dev) PMD_INIT_FUNC_TRACE(); hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + if (rte_is_power_of_2(dev->data->nb_rx_queues) == 0) { + PMD_INIT_LOG(ERR, "The number of Rx queue invalid, " + "it should be power of 2"); + return -1; + } + + if (dev->data->nb_rx_queues > hw->mac.max_rx_queues) { + PMD_INIT_LOG(ERR, "The number of Rx queue invalid, " + "it should be equal to or less than %d", + hw->mac.max_rx_queues); + return -1; + } + + /* + * When the VF driver issues a IXGBE_VF_RESET request, the PF driver + * disables the VF receipt of packets if the PF MTU is > 1500. + * This is done to deal with 82599 limitations that imposes + * the PF and all VFs to share the same MTU. + * Then, the PF driver enables again the VF receipt of packet when + * the VF driver issues a IXGBE_VF_SET_LPE request. + * In the meantime, the VF device cannot be used, even if the VF driver + * and the Guest VM network stack are ready to accept packets with a + * size up to the PF MTU. + * As a work-around to this PF behaviour, force the call to + * ixgbevf_rlpml_set_vf even if jumbo frames are not used. This way, + * VF packets received can work in all cases. + */ + ixgbevf_rlpml_set_vf(hw, + (uint16_t)dev->data->dev_conf.rxmode.max_rx_pkt_len); + /* Setup RX queues */ dev->rx_pkt_burst = ixgbe_recv_pkts; for (i = 0; i < dev->data->nb_rx_queues; i++) { @@ -3434,20 +4807,10 @@ ixgbevf_dev_rx_init(struct rte_eth_dev *dev) * Configure Header Split */ if (dev->data->dev_conf.rxmode.header_split) { - - /* Must setup the PSRTYPE register */ - uint32_t psrtype; - psrtype = IXGBE_PSRTYPE_TCPHDR | - IXGBE_PSRTYPE_UDPHDR | - IXGBE_PSRTYPE_IPV4HDR | - IXGBE_PSRTYPE_IPV6HDR; - - IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE(i), psrtype); - srrctl = ((dev->data->dev_conf.rxmode.split_hdr_size << - IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & - IXGBE_SRRCTL_BSIZEHDR_MASK); - srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; + IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & + IXGBE_SRRCTL_BSIZEHDR_MASK); + srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; } else #endif srrctl = IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; @@ -3462,8 +4825,7 @@ ixgbevf_dev_rx_init(struct rte_eth_dev *dev) * The value is in 1 KB resolution. Valid values can be from * 1 KB to 16 KB. */ - mbp_priv = (struct rte_pktmbuf_pool_private *) - ((char *)rxq->mb_pool + sizeof(struct rte_mempool)); + mbp_priv = rte_mempool_get_priv(rxq->mb_pool); buf_size = (uint16_t) (mbp_priv->mbuf_data_room_size - RTE_PKTMBUF_HEADROOM); srrctl |= ((buf_size >> IXGBE_SRRCTL_BSIZEPKT_SHIFT) & @@ -3477,14 +4839,37 @@ ixgbevf_dev_rx_init(struct rte_eth_dev *dev) buf_size = (uint16_t) ((srrctl & IXGBE_SRRCTL_BSIZEPKT_MASK) << IXGBE_SRRCTL_BSIZEPKT_SHIFT); - /* It adds dual VLAN length for supporting dual VLAN */ - if ((dev->data->dev_conf.rxmode.max_rx_pkt_len + + if (dev->data->dev_conf.rxmode.enable_scatter || + /* It adds dual VLAN length for supporting dual VLAN */ + (dev->data->dev_conf.rxmode.max_rx_pkt_len + 2 * IXGBE_VLAN_TAG_SIZE) > buf_size) { + if (!dev->data->scattered_rx) + PMD_INIT_LOG(DEBUG, "forcing scatter mode"); dev->data->scattered_rx = 1; - dev->rx_pkt_burst = ixgbe_recv_scattered_pkts; +#ifdef RTE_IXGBE_INC_VECTOR + if (rte_is_power_of_2(rxq->nb_rx_desc)) + dev->rx_pkt_burst = + ixgbe_recv_scattered_pkts_vec; + else +#endif + dev->rx_pkt_burst = ixgbe_recv_scattered_pkts; } } +#ifdef RTE_HEADER_SPLIT_ENABLE + if (dev->data->dev_conf.rxmode.header_split) + /* Must setup the PSRTYPE register */ + psrtype = IXGBE_PSRTYPE_TCPHDR | + IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | + IXGBE_PSRTYPE_IPV6HDR; +#endif + + /* Set RQPL for VF RSS according to max Rx queue */ + psrtype |= (dev->data->nb_rx_queues >> 1) << + IXGBE_PSRTYPE_RQPL_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype); + return 0; } @@ -3495,7 +4880,7 @@ void ixgbevf_dev_tx_init(struct rte_eth_dev *dev) { struct ixgbe_hw *hw; - struct igb_tx_queue *txq; + struct ixgbe_tx_queue *txq; uint64_t bus_addr; uint32_t txctrl; uint16_t i; @@ -3536,8 +4921,8 @@ void ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev) { struct ixgbe_hw *hw; - struct igb_tx_queue *txq; - struct igb_rx_queue *rxq; + struct ixgbe_tx_queue *txq; + struct ixgbe_rx_queue *rxq; uint32_t txdctl; uint32_t rxdctl; uint16_t i; @@ -3569,8 +4954,7 @@ ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev) txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i)); } while (--poll_ms && !(txdctl & IXGBE_TXDCTL_ENABLE)); if (!poll_ms) - PMD_INIT_LOG(ERR, "Could not enable " - "Tx Queue %d\n", i); + PMD_INIT_LOG(ERR, "Could not enable Tx Queue %d", i); } for (i = 0; i < dev->data->nb_rx_queues; i++) { @@ -3587,10 +4971,40 @@ ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev) rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i)); } while (--poll_ms && !(rxdctl & IXGBE_RXDCTL_ENABLE)); if (!poll_ms) - PMD_INIT_LOG(ERR, "Could not enable " - "Rx Queue %d\n", i); + PMD_INIT_LOG(ERR, "Could not enable Rx Queue %d", i); rte_wmb(); IXGBE_WRITE_REG(hw, IXGBE_VFRDT(i), rxq->nb_rx_desc - 1); } } + +/* Stubs needed for linkage when CONFIG_RTE_IXGBE_INC_VECTOR is set to 'n' */ +int __attribute__((weak)) +ixgbe_rx_vec_dev_conf_condition_check(struct rte_eth_dev __rte_unused *dev) +{ + return -1; +} + +uint16_t __attribute__((weak)) +ixgbe_recv_pkts_vec( + void __rte_unused *rx_queue, + struct rte_mbuf __rte_unused **rx_pkts, + uint16_t __rte_unused nb_pkts) +{ + return 0; +} + +uint16_t __attribute__((weak)) +ixgbe_recv_scattered_pkts_vec( + void __rte_unused *rx_queue, + struct rte_mbuf __rte_unused **rx_pkts, + uint16_t __rte_unused nb_pkts) +{ + return 0; +} + +int __attribute__((weak)) +ixgbe_rxq_vec_setup(struct ixgbe_rx_queue __rte_unused *rxq) +{ + return -1; +}