#include <rte_ethdev.h>
#include <ethdev_driver.h>
#include <rte_malloc.h>
+#include <rte_net.h>
#include "ngbe_logs.h"
#include "base/ngbe.h"
#include "ngbe_ethdev.h"
#include "ngbe_rxtx.h"
+/* Bit Mask to indicate what bits required for building Tx context */
+static const u64 NGBE_TX_OFFLOAD_MASK = (RTE_MBUF_F_TX_IP_CKSUM |
+ RTE_MBUF_F_TX_OUTER_IPV6 |
+ RTE_MBUF_F_TX_OUTER_IPV4 |
+ RTE_MBUF_F_TX_IPV6 |
+ RTE_MBUF_F_TX_IPV4 |
+ RTE_MBUF_F_TX_L4_MASK |
+ RTE_MBUF_F_TX_TCP_SEG |
+ RTE_MBUF_F_TX_TUNNEL_MASK |
+ RTE_MBUF_F_TX_OUTER_IP_CKSUM);
+#define NGBE_TX_OFFLOAD_NOTSUP_MASK \
+ (RTE_MBUF_F_TX_OFFLOAD_MASK ^ NGBE_TX_OFFLOAD_MASK)
+
/*
* Prefetch a cache line into all cache levels.
*/
return nb_tx;
}
+static inline void
+ngbe_set_xmit_ctx(struct ngbe_tx_queue *txq,
+ volatile struct ngbe_tx_ctx_desc *ctx_txd,
+ uint64_t ol_flags, union ngbe_tx_offload tx_offload)
+{
+ union ngbe_tx_offload tx_offload_mask;
+ uint32_t type_tucmd_mlhl;
+ uint32_t mss_l4len_idx;
+ uint32_t ctx_idx;
+ uint32_t vlan_macip_lens;
+ uint32_t tunnel_seed;
+
+ ctx_idx = txq->ctx_curr;
+ tx_offload_mask.data[0] = 0;
+ tx_offload_mask.data[1] = 0;
+
+ /* Specify which HW CTX to upload. */
+ mss_l4len_idx = NGBE_TXD_IDX(ctx_idx);
+ type_tucmd_mlhl = NGBE_TXD_CTXT;
+
+ tx_offload_mask.ptid |= ~0;
+ type_tucmd_mlhl |= NGBE_TXD_PTID(tx_offload.ptid);
+
+ /* check if TCP segmentation required for this packet */
+ if (ol_flags & RTE_MBUF_F_TX_TCP_SEG) {
+ 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 |= NGBE_TXD_MSS(tx_offload.tso_segsz);
+ mss_l4len_idx |= NGBE_TXD_L4LEN(tx_offload.l4_len);
+ } else { /* no TSO, check if hardware checksum is needed */
+ if (ol_flags & RTE_MBUF_F_TX_IP_CKSUM) {
+ tx_offload_mask.l2_len |= ~0;
+ tx_offload_mask.l3_len |= ~0;
+ }
+
+ switch (ol_flags & RTE_MBUF_F_TX_L4_MASK) {
+ case RTE_MBUF_F_TX_UDP_CKSUM:
+ mss_l4len_idx |=
+ NGBE_TXD_L4LEN(sizeof(struct rte_udp_hdr));
+ tx_offload_mask.l2_len |= ~0;
+ tx_offload_mask.l3_len |= ~0;
+ break;
+ case RTE_MBUF_F_TX_TCP_CKSUM:
+ mss_l4len_idx |=
+ NGBE_TXD_L4LEN(sizeof(struct rte_tcp_hdr));
+ tx_offload_mask.l2_len |= ~0;
+ tx_offload_mask.l3_len |= ~0;
+ break;
+ case RTE_MBUF_F_TX_SCTP_CKSUM:
+ mss_l4len_idx |=
+ NGBE_TXD_L4LEN(sizeof(struct rte_sctp_hdr));
+ tx_offload_mask.l2_len |= ~0;
+ tx_offload_mask.l3_len |= ~0;
+ break;
+ default:
+ break;
+ }
+ }
+
+ vlan_macip_lens = NGBE_TXD_IPLEN(tx_offload.l3_len >> 1);
+
+ if (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+ tx_offload_mask.outer_tun_len |= ~0;
+ tx_offload_mask.outer_l2_len |= ~0;
+ tx_offload_mask.outer_l3_len |= ~0;
+ tx_offload_mask.l2_len |= ~0;
+ tunnel_seed = NGBE_TXD_ETUNLEN(tx_offload.outer_tun_len >> 1);
+ tunnel_seed |= NGBE_TXD_EIPLEN(tx_offload.outer_l3_len >> 2);
+
+ switch (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+ case RTE_MBUF_F_TX_TUNNEL_IPIP:
+ /* for non UDP / GRE tunneling, set to 0b */
+ break;
+ default:
+ PMD_TX_LOG(ERR, "Tunnel type not supported");
+ return;
+ }
+ vlan_macip_lens |= NGBE_TXD_MACLEN(tx_offload.outer_l2_len);
+ } else {
+ tunnel_seed = 0;
+ vlan_macip_lens |= NGBE_TXD_MACLEN(tx_offload.l2_len);
+ }
+
+ txq->ctx_cache[ctx_idx].flags = ol_flags;
+ txq->ctx_cache[ctx_idx].tx_offload.data[0] =
+ tx_offload_mask.data[0] & tx_offload.data[0];
+ txq->ctx_cache[ctx_idx].tx_offload.data[1] =
+ tx_offload_mask.data[1] & tx_offload.data[1];
+ txq->ctx_cache[ctx_idx].tx_offload_mask = tx_offload_mask;
+
+ ctx_txd->dw0 = rte_cpu_to_le_32(vlan_macip_lens);
+ ctx_txd->dw1 = rte_cpu_to_le_32(tunnel_seed);
+ ctx_txd->dw2 = rte_cpu_to_le_32(type_tucmd_mlhl);
+ ctx_txd->dw3 = rte_cpu_to_le_32(mss_l4len_idx);
+}
+
+/*
+ * Check which hardware context can be used. Use the existing match
+ * or create a new context descriptor.
+ */
+static inline uint32_t
+what_ctx_update(struct ngbe_tx_queue *txq, uint64_t flags,
+ union ngbe_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].tx_offload.data[0] ==
+ (txq->ctx_cache[txq->ctx_curr].tx_offload_mask.data[0]
+ & tx_offload.data[0])) &&
+ (txq->ctx_cache[txq->ctx_curr].tx_offload.data[1] ==
+ (txq->ctx_cache[txq->ctx_curr].tx_offload_mask.data[1]
+ & tx_offload.data[1]))))
+ 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].tx_offload.data[0] ==
+ (txq->ctx_cache[txq->ctx_curr].tx_offload_mask.data[0]
+ & tx_offload.data[0])) &&
+ (txq->ctx_cache[txq->ctx_curr].tx_offload.data[1] ==
+ (txq->ctx_cache[txq->ctx_curr].tx_offload_mask.data[1]
+ & tx_offload.data[1]))))
+ return txq->ctx_curr;
+
+ /* Mismatch, use the previous context */
+ return NGBE_CTX_NUM;
+}
+
+static inline uint32_t
+tx_desc_cksum_flags_to_olinfo(uint64_t ol_flags)
+{
+ uint32_t tmp = 0;
+
+ if ((ol_flags & RTE_MBUF_F_TX_L4_MASK) != RTE_MBUF_F_TX_L4_NO_CKSUM) {
+ tmp |= NGBE_TXD_CC;
+ tmp |= NGBE_TXD_L4CS;
+ }
+ if (ol_flags & RTE_MBUF_F_TX_IP_CKSUM) {
+ tmp |= NGBE_TXD_CC;
+ tmp |= NGBE_TXD_IPCS;
+ }
+ if (ol_flags & RTE_MBUF_F_TX_OUTER_IP_CKSUM) {
+ tmp |= NGBE_TXD_CC;
+ tmp |= NGBE_TXD_EIPCS;
+ }
+ if (ol_flags & RTE_MBUF_F_TX_TCP_SEG) {
+ tmp |= NGBE_TXD_CC;
+ /* implies IPv4 cksum */
+ if (ol_flags & RTE_MBUF_F_TX_IPV4)
+ tmp |= NGBE_TXD_IPCS;
+ tmp |= NGBE_TXD_L4CS;
+ }
+
+ return tmp;
+}
+
+static inline uint32_t
+tx_desc_ol_flags_to_cmdtype(uint64_t ol_flags)
+{
+ uint32_t cmdtype = 0;
+
+ if (ol_flags & RTE_MBUF_F_TX_TCP_SEG)
+ cmdtype |= NGBE_TXD_TSE;
+ return cmdtype;
+}
+
+static inline uint8_t
+tx_desc_ol_flags_to_ptid(uint64_t oflags, uint32_t ptype)
+{
+ bool tun;
+
+ if (ptype)
+ return ngbe_encode_ptype(ptype);
+
+ /* Only support flags in NGBE_TX_OFFLOAD_MASK */
+ tun = !!(oflags & RTE_MBUF_F_TX_TUNNEL_MASK);
+
+ /* L2 level */
+ ptype = RTE_PTYPE_L2_ETHER;
+
+ /* L3 level */
+ if (oflags & (RTE_MBUF_F_TX_OUTER_IPV4 | RTE_MBUF_F_TX_OUTER_IP_CKSUM))
+ ptype |= RTE_PTYPE_L3_IPV4;
+ else if (oflags & (RTE_MBUF_F_TX_OUTER_IPV6))
+ ptype |= RTE_PTYPE_L3_IPV6;
+
+ if (oflags & (RTE_MBUF_F_TX_IPV4 | RTE_MBUF_F_TX_IP_CKSUM))
+ ptype |= (tun ? RTE_PTYPE_INNER_L3_IPV4 : RTE_PTYPE_L3_IPV4);
+ else if (oflags & (RTE_MBUF_F_TX_IPV6))
+ ptype |= (tun ? RTE_PTYPE_INNER_L3_IPV6 : RTE_PTYPE_L3_IPV6);
+
+ /* L4 level */
+ switch (oflags & (RTE_MBUF_F_TX_L4_MASK)) {
+ case RTE_MBUF_F_TX_TCP_CKSUM:
+ ptype |= (tun ? RTE_PTYPE_INNER_L4_TCP : RTE_PTYPE_L4_TCP);
+ break;
+ case RTE_MBUF_F_TX_UDP_CKSUM:
+ ptype |= (tun ? RTE_PTYPE_INNER_L4_UDP : RTE_PTYPE_L4_UDP);
+ break;
+ case RTE_MBUF_F_TX_SCTP_CKSUM:
+ ptype |= (tun ? RTE_PTYPE_INNER_L4_SCTP : RTE_PTYPE_L4_SCTP);
+ break;
+ }
+
+ if (oflags & RTE_MBUF_F_TX_TCP_SEG)
+ ptype |= (tun ? RTE_PTYPE_INNER_L4_TCP : RTE_PTYPE_L4_TCP);
+
+ /* Tunnel */
+ switch (oflags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+ case RTE_MBUF_F_TX_TUNNEL_IPIP:
+ case RTE_MBUF_F_TX_TUNNEL_IP:
+ ptype |= RTE_PTYPE_L2_ETHER |
+ RTE_PTYPE_L3_IPV4 |
+ RTE_PTYPE_TUNNEL_IP;
+ break;
+ }
+
+ return ngbe_encode_ptype(ptype);
+}
+
+/* Reset transmit descriptors after they have been used */
+static inline int
+ngbe_xmit_cleanup(struct ngbe_tx_queue *txq)
+{
+ struct ngbe_tx_entry *sw_ring = txq->sw_ring;
+ volatile struct ngbe_tx_desc *txr = txq->tx_ring;
+ uint16_t last_desc_cleaned = txq->last_desc_cleaned;
+ uint16_t nb_tx_desc = txq->nb_tx_desc;
+ uint16_t desc_to_clean_to;
+ uint16_t nb_tx_to_clean;
+ uint32_t status;
+
+ /* Determine the last descriptor needing to be cleaned */
+ desc_to_clean_to = (uint16_t)(last_desc_cleaned + txq->tx_free_thresh);
+ if (desc_to_clean_to >= nb_tx_desc)
+ desc_to_clean_to = (uint16_t)(desc_to_clean_to - nb_tx_desc);
+
+ /* Check to make sure the last descriptor to clean is done */
+ desc_to_clean_to = sw_ring[desc_to_clean_to].last_id;
+ status = txr[desc_to_clean_to].dw3;
+ if (!(status & rte_cpu_to_le_32(NGBE_TXD_DD))) {
+ PMD_TX_LOG(DEBUG,
+ "Tx descriptor %4u is not done"
+ "(port=%d queue=%d)",
+ desc_to_clean_to,
+ txq->port_id, txq->queue_id);
+ if (txq->nb_tx_free >> 1 < txq->tx_free_thresh)
+ ngbe_set32_masked(txq->tdc_reg_addr,
+ NGBE_TXCFG_FLUSH, NGBE_TXCFG_FLUSH);
+ /* Failed to clean any descriptors, better luck next time */
+ return -(1);
+ }
+
+ /* Figure out how many descriptors will be cleaned */
+ if (last_desc_cleaned > desc_to_clean_to)
+ nb_tx_to_clean = (uint16_t)((nb_tx_desc - last_desc_cleaned) +
+ desc_to_clean_to);
+ else
+ nb_tx_to_clean = (uint16_t)(desc_to_clean_to -
+ last_desc_cleaned);
+
+ PMD_TX_LOG(DEBUG,
+ "Cleaning %4u Tx descriptors: %4u to %4u (port=%d queue=%d)",
+ nb_tx_to_clean, last_desc_cleaned, desc_to_clean_to,
+ txq->port_id, txq->queue_id);
+
+ /*
+ * The last descriptor to clean is done, so that means all the
+ * descriptors from the last descriptor that was cleaned
+ * up to the last descriptor with the RS bit set
+ * are done. Only reset the threshold descriptor.
+ */
+ txr[desc_to_clean_to].dw3 = 0;
+
+ /* Update the txq to reflect the last descriptor that was cleaned */
+ txq->last_desc_cleaned = desc_to_clean_to;
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + nb_tx_to_clean);
+
+ /* No Error */
+ return 0;
+}
+
+uint16_t
+ngbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ struct ngbe_tx_queue *txq;
+ struct ngbe_tx_entry *sw_ring;
+ struct ngbe_tx_entry *txe, *txn;
+ volatile struct ngbe_tx_desc *txr;
+ volatile struct ngbe_tx_desc *txd;
+ struct rte_mbuf *tx_pkt;
+ struct rte_mbuf *m_seg;
+ uint64_t buf_dma_addr;
+ uint32_t olinfo_status;
+ uint32_t cmd_type_len;
+ uint32_t pkt_len;
+ uint16_t slen;
+ uint64_t ol_flags;
+ uint16_t tx_id;
+ uint16_t tx_last;
+ uint16_t nb_tx;
+ uint16_t nb_used;
+ uint64_t tx_ol_req;
+ uint32_t ctx = 0;
+ uint32_t new_ctx;
+ union ngbe_tx_offload tx_offload;
+
+ tx_offload.data[0] = 0;
+ tx_offload.data[1] = 0;
+ txq = tx_queue;
+ sw_ring = txq->sw_ring;
+ txr = txq->tx_ring;
+ tx_id = txq->tx_tail;
+ txe = &sw_ring[tx_id];
+
+ /* Determine if the descriptor ring needs to be cleaned. */
+ if (txq->nb_tx_free < txq->tx_free_thresh)
+ ngbe_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_len;
+
+ /*
+ * Determine how many (if any) context descriptors
+ * are needed for offload functionality.
+ */
+ ol_flags = tx_pkt->ol_flags;
+
+ /* If hardware offload required */
+ tx_ol_req = ol_flags & NGBE_TX_OFFLOAD_MASK;
+ if (tx_ol_req) {
+ tx_offload.ptid = tx_desc_ol_flags_to_ptid(tx_ol_req,
+ tx_pkt->packet_type);
+ 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.tso_segsz = tx_pkt->tso_segsz;
+ tx_offload.outer_l2_len = tx_pkt->outer_l2_len;
+ tx_offload.outer_l3_len = tx_pkt->outer_l3_len;
+ tx_offload.outer_tun_len = 0;
+
+ /* If new context need be built or reuse the exist ctx*/
+ ctx = what_ctx_update(txq, tx_ol_req, tx_offload);
+ /* Only allocate context descriptor if required */
+ new_ctx = (ctx == NGBE_CTX_NUM);
+ ctx = txq->ctx_curr;
+ }
+
+ /*
+ * Keep track of how many descriptors are used this loop
+ * This will always be the number of segments + the number of
+ * Context descriptors required to transmit the packet
+ */
+ nb_used = (uint16_t)(tx_pkt->nb_segs + new_ctx);
+
+ /*
+ * The number of descriptors that must be allocated for a
+ * packet is the number of segments of that packet, plus 1
+ * Context Descriptor for the hardware offload, if any.
+ * Determine the last Tx descriptor to allocate in the Tx ring
+ * for the packet, starting from the current position (tx_id)
+ * in the ring.
+ */
+ tx_last = (uint16_t)(tx_id + nb_used - 1);
+
+ /* Circular ring */
+ if (tx_last >= txq->nb_tx_desc)
+ 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",
+ (uint16_t)txq->port_id,
+ (uint16_t)txq->queue_id,
+ (uint32_t)pkt_len,
+ (uint16_t)tx_id,
+ (uint16_t)tx_last);
+
+ /*
+ * Make sure there are enough Tx descriptors available to
+ * transmit the entire packet.
+ * nb_used better be less than or equal to txq->tx_free_thresh
+ */
+ if (nb_used > txq->nb_tx_free) {
+ PMD_TX_LOG(DEBUG,
+ "Not enough free Tx descriptors "
+ "nb_used=%4u nb_free=%4u "
+ "(port=%d queue=%d)",
+ nb_used, txq->nb_tx_free,
+ txq->port_id, txq->queue_id);
+
+ if (ngbe_xmit_cleanup(txq) != 0) {
+ /* Could not clean any descriptors */
+ if (nb_tx == 0)
+ return 0;
+ goto end_of_tx;
+ }
+
+ /* nb_used better be <= txq->tx_free_thresh */
+ if (unlikely(nb_used > txq->tx_free_thresh)) {
+ PMD_TX_LOG(DEBUG,
+ "The number of descriptors needed to "
+ "transmit the packet exceeds the "
+ "RS bit threshold. This will impact "
+ "performance."
+ "nb_used=%4u nb_free=%4u "
+ "tx_free_thresh=%4u. "
+ "(port=%d queue=%d)",
+ nb_used, txq->nb_tx_free,
+ txq->tx_free_thresh,
+ txq->port_id, txq->queue_id);
+ /*
+ * Loop here until there are enough Tx
+ * descriptors or until the ring cannot be
+ * cleaned.
+ */
+ while (nb_used > txq->nb_tx_free) {
+ if (ngbe_xmit_cleanup(txq) != 0) {
+ /*
+ * Could not clean any
+ * descriptors
+ */
+ if (nb_tx == 0)
+ return 0;
+ goto end_of_tx;
+ }
+ }
+ }
+ }
+
+ /*
+ * By now there are enough free Tx descriptors to transmit
+ * the packet.
+ */
+
+ /*
+ * Set common flags of all Tx Data Descriptors.
+ *
+ * The following bits must be set in the first Data Descriptor
+ * and are ignored in the other ones:
+ * - NGBE_TXD_FCS
+ *
+ * The following bits must only be set in the last Data
+ * Descriptor:
+ * - NGBE_TXD_EOP
+ */
+ cmd_type_len = NGBE_TXD_FCS;
+
+ olinfo_status = 0;
+ if (tx_ol_req) {
+ if (ol_flags & RTE_MBUF_F_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);
+ pkt_len -=
+ (tx_pkt->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK)
+ ? tx_offload.outer_l2_len +
+ tx_offload.outer_l3_len : 0;
+ }
+
+ /*
+ * Setup the Tx Context Descriptor if required
+ */
+ if (new_ctx) {
+ volatile struct ngbe_tx_ctx_desc *ctx_txd;
+
+ ctx_txd = (volatile struct ngbe_tx_ctx_desc *)
+ &txr[tx_id];
+
+ txn = &sw_ring[txe->next_id];
+ rte_prefetch0(&txn->mbuf->pool);
+
+ if (txe->mbuf != NULL) {
+ rte_pktmbuf_free_seg(txe->mbuf);
+ txe->mbuf = NULL;
+ }
+
+ ngbe_set_xmit_ctx(txq, ctx_txd, tx_ol_req,
+ tx_offload);
+
+ txe->last_id = tx_last;
+ tx_id = txe->next_id;
+ txe = txn;
+ }
+
+ /*
+ * Setup the Tx Data Descriptor,
+ * This path will go through
+ * whatever new/reuse the context descriptor
+ */
+ cmd_type_len |= tx_desc_ol_flags_to_cmdtype(ol_flags);
+ olinfo_status |=
+ tx_desc_cksum_flags_to_olinfo(ol_flags);
+ olinfo_status |= NGBE_TXD_IDX(ctx);
+ }
+
+ olinfo_status |= NGBE_TXD_PAYLEN(pkt_len);
+
+ 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);
+ txe->mbuf = m_seg;
+
+ /*
+ * Set up Transmit Data Descriptor.
+ */
+ slen = m_seg->data_len;
+ buf_dma_addr = rte_mbuf_data_iova(m_seg);
+ txd->qw0 = rte_cpu_to_le_64(buf_dma_addr);
+ txd->dw2 = rte_cpu_to_le_32(cmd_type_len | slen);
+ txd->dw3 = rte_cpu_to_le_32(olinfo_status);
+ txe->last_id = tx_last;
+ tx_id = txe->next_id;
+ txe = txn;
+ m_seg = m_seg->next;
+ } while (m_seg != NULL);
+
+ /*
+ * The last packet data descriptor needs End Of Packet (EOP)
+ */
+ cmd_type_len |= NGBE_TXD_EOP;
+ txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_used);
+
+ txd->dw2 |= rte_cpu_to_le_32(cmd_type_len);
+ }
+
+end_of_tx:
+
+ rte_wmb();
+
+ /*
+ * Set the Transmit Descriptor Tail (TDT)
+ */
+ PMD_TX_LOG(DEBUG, "port_id=%u queue_id=%u tx_tail=%u nb_tx=%u",
+ (uint16_t)txq->port_id, (uint16_t)txq->queue_id,
+ (uint16_t)tx_id, (uint16_t)nb_tx);
+ ngbe_set32_relaxed(txq->tdt_reg_addr, tx_id);
+ txq->tx_tail = tx_id;
+
+ return nb_tx;
+}
+
+/*********************************************************************
+ *
+ * Tx prep functions
+ *
+ **********************************************************************/
+uint16_t
+ngbe_prep_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ int i, ret;
+ uint64_t ol_flags;
+ struct rte_mbuf *m;
+ struct ngbe_tx_queue *txq = (struct ngbe_tx_queue *)tx_queue;
+
+ for (i = 0; i < nb_pkts; i++) {
+ m = tx_pkts[i];
+ ol_flags = m->ol_flags;
+
+ /**
+ * Check if packet meets requirements for number of segments
+ *
+ * NOTE: for ngbe it's always (40 - WTHRESH) for both TSO and
+ * non-TSO
+ */
+
+ if (m->nb_segs > NGBE_TX_MAX_SEG - txq->wthresh) {
+ rte_errno = -EINVAL;
+ return i;
+ }
+
+ if (ol_flags & NGBE_TX_OFFLOAD_NOTSUP_MASK) {
+ rte_errno = -ENOTSUP;
+ return i;
+ }
+
+#ifdef RTE_ETHDEV_DEBUG_TX
+ ret = rte_validate_tx_offload(m);
+ if (ret != 0) {
+ rte_errno = ret;
+ return i;
+ }
+#endif
+ ret = rte_net_intel_cksum_prepare(m);
+ if (ret != 0) {
+ rte_errno = ret;
+ return i;
+ }
+ }
+
+ return i;
+}
+
/*********************************************************************
*
* Rx functions
return ngbe_decode_ptype(ptid);
}
+static inline uint64_t
+rx_desc_error_to_pkt_flags(uint32_t rx_status)
+{
+ uint64_t pkt_flags = 0;
+
+ /* checksum offload can't be disabled */
+ if (rx_status & NGBE_RXD_STAT_IPCS)
+ pkt_flags |= (rx_status & NGBE_RXD_ERR_IPCS
+ ? RTE_MBUF_F_RX_IP_CKSUM_BAD : RTE_MBUF_F_RX_IP_CKSUM_GOOD);
+
+ if (rx_status & NGBE_RXD_STAT_L4CS)
+ pkt_flags |= (rx_status & NGBE_RXD_ERR_L4CS
+ ? RTE_MBUF_F_RX_L4_CKSUM_BAD : RTE_MBUF_F_RX_L4_CKSUM_GOOD);
+
+ if (rx_status & NGBE_RXD_STAT_EIPCS &&
+ rx_status & NGBE_RXD_ERR_EIPCS)
+ pkt_flags |= RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD;
+
+ return pkt_flags;
+}
+
/*
* LOOK_AHEAD defines how many desc statuses to check beyond the
* current descriptor.
struct ngbe_rx_entry *rxep;
struct rte_mbuf *mb;
uint16_t pkt_len;
+ uint64_t pkt_flags;
int nb_dd;
uint32_t s[LOOK_AHEAD];
uint32_t pkt_info[LOOK_AHEAD];
/* Translate descriptor info to mbuf format */
for (j = 0; j < nb_dd; ++j) {
mb = rxep[j].mbuf;
- pkt_len = rte_le_to_cpu_16(rxdp[j].qw1.hi.len);
+ pkt_len = rte_le_to_cpu_16(rxdp[j].qw1.hi.len) -
+ rxq->crc_len;
mb->data_len = pkt_len;
mb->pkt_len = pkt_len;
+ /* convert descriptor fields to rte mbuf flags */
+ pkt_flags = rx_desc_error_to_pkt_flags(s[j]);
+ mb->ol_flags = pkt_flags;
mb->packet_type =
ngbe_rxd_pkt_info_to_pkt_type(pkt_info[j],
NGBE_PTID_MASK);
uint16_t rx_id;
uint16_t nb_rx;
uint16_t nb_hold;
+ uint64_t pkt_flags;
nb_rx = 0;
nb_hold = 0;
/*
* Initialize the returned mbuf.
- * setup generic mbuf fields:
+ * 1) setup generic mbuf fields:
* - number of segments,
* - next segment,
* - packet length,
* - Rx port identifier.
+ * 2) integrate hardware offload data, if any:
+ * - IP checksum flag,
+ * - error flags.
*/
- pkt_len = (uint16_t)(rte_le_to_cpu_16(rxd.qw1.hi.len));
+ pkt_len = (uint16_t)(rte_le_to_cpu_16(rxd.qw1.hi.len) -
+ rxq->crc_len);
rxm->data_off = RTE_PKTMBUF_HEADROOM;
rte_packet_prefetch((char *)rxm->buf_addr + rxm->data_off);
rxm->nb_segs = 1;
rxm->port = rxq->port_id;
pkt_info = rte_le_to_cpu_32(rxd.qw0.dw0);
+ pkt_flags = rx_desc_error_to_pkt_flags(staterr);
+ rxm->ol_flags = pkt_flags;
rxm->packet_type = ngbe_rxd_pkt_info_to_pkt_type(pkt_info,
NGBE_PTID_MASK);
return nb_rx;
}
+/**
+ * ngbe_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:
+ * - IP checksum flag
+ * - error flags
+ * @head HEAD of the packet cluster
+ * @desc HW descriptor to get data from
+ * @rxq Pointer to the Rx queue
+ */
static inline void
ngbe_fill_cluster_head_buf(struct rte_mbuf *head, struct ngbe_rx_desc *desc,
struct ngbe_rx_queue *rxq, uint32_t staterr)
{
uint32_t pkt_info;
+ uint64_t pkt_flags;
- RTE_SET_USED(staterr);
head->port = rxq->port_id;
pkt_info = rte_le_to_cpu_32(desc->qw0.dw0);
+ pkt_flags = rx_desc_error_to_pkt_flags(staterr);
+ head->ol_flags = pkt_flags;
head->packet_type = ngbe_rxd_pkt_info_to_pkt_type(pkt_info,
NGBE_PTID_MASK);
}
/* Initialize the first mbuf of the returned packet */
ngbe_fill_cluster_head_buf(first_seg, &rxd, rxq, staterr);
+ /* Deal with the case, when HW CRC srip is disabled. */
+ first_seg->pkt_len -= rxq->crc_len;
+ if (unlikely(rxm->data_len <= rxq->crc_len)) {
+ struct rte_mbuf *lp;
+
+ for (lp = first_seg; lp->next != rxm; lp = lp->next)
+ ;
+
+ first_seg->nb_segs--;
+ lp->data_len -= rxq->crc_len - rxm->data_len;
+ lp->next = NULL;
+ rte_pktmbuf_free_seg(rxm);
+ } else {
+ rxm->data_len -= rxq->crc_len;
+ }
+
/* Prefetch data of first segment, if configured to do so. */
rte_packet_prefetch((char *)first_seg->buf_addr +
first_seg->data_off);
.reset = ngbe_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
+ngbe_set_tx_function(struct rte_eth_dev *dev, struct ngbe_tx_queue *txq)
+{
+ /* Use a simple Tx queue (no offloads, no multi segs) if possible */
+ if (txq->offloads == 0 &&
+ txq->tx_free_thresh >= RTE_PMD_NGBE_TX_MAX_BURST) {
+ PMD_INIT_LOG(DEBUG, "Using simple tx code path");
+ dev->tx_pkt_burst = ngbe_xmit_pkts_simple;
+ dev->tx_pkt_prepare = NULL;
+ } else {
+ PMD_INIT_LOG(DEBUG, "Using full-featured tx code path");
+ PMD_INIT_LOG(DEBUG,
+ " - offloads = 0x%" PRIx64,
+ txq->offloads);
+ PMD_INIT_LOG(DEBUG,
+ " - tx_free_thresh = %lu [RTE_PMD_NGBE_TX_MAX_BURST=%lu]",
+ (unsigned long)txq->tx_free_thresh,
+ (unsigned long)RTE_PMD_NGBE_TX_MAX_BURST);
+ dev->tx_pkt_burst = ngbe_xmit_pkts;
+ dev->tx_pkt_prepare = ngbe_prep_pkts;
+ }
+}
+
+static const struct {
+ eth_tx_burst_t pkt_burst;
+ const char *info;
+} ngbe_tx_burst_infos[] = {
+ { ngbe_xmit_pkts_simple, "Scalar Simple"},
+ { ngbe_xmit_pkts, "Scalar"},
+};
+
+int
+ngbe_tx_burst_mode_get(struct rte_eth_dev *dev, __rte_unused uint16_t queue_id,
+ struct rte_eth_burst_mode *mode)
+{
+ eth_tx_burst_t pkt_burst = dev->tx_pkt_burst;
+ int ret = -EINVAL;
+ unsigned int i;
+
+ for (i = 0; i < RTE_DIM(ngbe_tx_burst_infos); ++i) {
+ if (pkt_burst == ngbe_tx_burst_infos[i].pkt_burst) {
+ snprintf(mode->info, sizeof(mode->info), "%s",
+ ngbe_tx_burst_infos[i].info);
+ ret = 0;
+ break;
+ }
+ }
+
+ return ret;
+}
+
+uint64_t
+ngbe_get_tx_port_offloads(struct rte_eth_dev *dev)
+{
+ uint64_t tx_offload_capa;
+
+ RTE_SET_USED(dev);
+
+ tx_offload_capa =
+ RTE_ETH_TX_OFFLOAD_IPV4_CKSUM |
+ RTE_ETH_TX_OFFLOAD_UDP_CKSUM |
+ RTE_ETH_TX_OFFLOAD_TCP_CKSUM |
+ RTE_ETH_TX_OFFLOAD_SCTP_CKSUM |
+ RTE_ETH_TX_OFFLOAD_OUTER_IPV4_CKSUM |
+ RTE_ETH_TX_OFFLOAD_TCP_TSO |
+ RTE_ETH_TX_OFFLOAD_UDP_TSO |
+ RTE_ETH_TX_OFFLOAD_UDP_TNL_TSO |
+ RTE_ETH_TX_OFFLOAD_IP_TNL_TSO |
+ RTE_ETH_TX_OFFLOAD_IPIP_TNL_TSO |
+ RTE_ETH_TX_OFFLOAD_MULTI_SEGS;
+
+ return tx_offload_capa;
+}
+
int
ngbe_dev_tx_queue_setup(struct rte_eth_dev *dev,
uint16_t queue_idx,
struct ngbe_tx_queue *txq;
struct ngbe_hw *hw;
uint16_t tx_free_thresh;
+ uint64_t offloads;
PMD_INIT_FUNC_TRACE();
hw = ngbe_dev_hw(dev);
+ offloads = tx_conf->offloads | dev->data->dev_conf.txmode.offloads;
+
/*
* The Tx descriptor ring will be cleaned after txq->tx_free_thresh
* descriptors are used or if the number of descriptors required
txq->queue_id = queue_idx;
txq->reg_idx = queue_idx;
txq->port_id = dev->data->port_id;
+ txq->offloads = offloads;
txq->ops = &def_txq_ops;
txq->tx_deferred_start = tx_conf->tx_deferred_start;
"sw_ring=%p hw_ring=%p dma_addr=0x%" PRIx64,
txq->sw_ring, txq->tx_ring, txq->tx_ring_phys_addr);
+ /* set up scalar Tx function as appropriate */
+ ngbe_set_tx_function(dev, txq);
+
txq->ops->reset(txq);
dev->data->tx_queues[queue_idx] = txq;
uint64_t
ngbe_get_rx_port_offloads(struct rte_eth_dev *dev __rte_unused)
{
- return RTE_ETH_RX_OFFLOAD_SCATTER;
+ uint64_t offloads;
+
+ offloads = RTE_ETH_RX_OFFLOAD_IPV4_CKSUM |
+ RTE_ETH_RX_OFFLOAD_UDP_CKSUM |
+ RTE_ETH_RX_OFFLOAD_TCP_CKSUM |
+ RTE_ETH_RX_OFFLOAD_KEEP_CRC |
+ RTE_ETH_RX_OFFLOAD_SCATTER;
+
+ return offloads;
}
int
rxq->queue_id = queue_idx;
rxq->reg_idx = queue_idx;
rxq->port_id = dev->data->port_id;
+ if (dev->data->dev_conf.rxmode.offloads & RTE_ETH_RX_OFFLOAD_KEEP_CRC)
+ rxq->crc_len = RTE_ETHER_CRC_LEN;
+ else
+ rxq->crc_len = 0;
rxq->drop_en = rx_conf->rx_drop_en;
rxq->rx_deferred_start = rx_conf->rx_deferred_start;
}
}
+static const struct {
+ eth_rx_burst_t pkt_burst;
+ const char *info;
+} ngbe_rx_burst_infos[] = {
+ { ngbe_recv_pkts_sc_single_alloc, "Scalar Scattered"},
+ { ngbe_recv_pkts_sc_bulk_alloc, "Scalar Scattered Bulk Alloc"},
+ { ngbe_recv_pkts_bulk_alloc, "Scalar Bulk Alloc"},
+ { ngbe_recv_pkts, "Scalar"},
+};
+
+int
+ngbe_rx_burst_mode_get(struct rte_eth_dev *dev, __rte_unused uint16_t queue_id,
+ struct rte_eth_burst_mode *mode)
+{
+ eth_rx_burst_t pkt_burst = dev->rx_pkt_burst;
+ int ret = -EINVAL;
+ unsigned int i;
+
+ for (i = 0; i < RTE_DIM(ngbe_rx_burst_infos); ++i) {
+ if (pkt_burst == ngbe_rx_burst_infos[i].pkt_burst) {
+ snprintf(mode->info, sizeof(mode->info), "%s",
+ ngbe_rx_burst_infos[i].info);
+ ret = 0;
+ break;
+ }
+ }
+
+ return ret;
+}
+
/*
* Initializes Receive Unit.
*/
uint32_t fctrl;
uint32_t hlreg0;
uint32_t srrctl;
+ uint32_t rdrxctl;
+ uint32_t rxcsum;
uint16_t buf_size;
uint16_t i;
struct rte_eth_rxmode *rx_conf = &dev->data->dev_conf.rxmode;
fctrl |= NGBE_PSRCTL_BCA;
wr32(hw, NGBE_PSRCTL, fctrl);
+ /*
+ * Configure CRC stripping, if any.
+ */
hlreg0 = rd32(hw, NGBE_SECRXCTL);
+ if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_KEEP_CRC)
+ hlreg0 &= ~NGBE_SECRXCTL_CRCSTRIP;
+ else
+ hlreg0 |= NGBE_SECRXCTL_CRCSTRIP;
hlreg0 &= ~NGBE_SECRXCTL_XDSA;
wr32(hw, NGBE_SECRXCTL, hlreg0);
+ /*
+ * Configure jumbo frame support, if any.
+ */
wr32m(hw, NGBE_FRMSZ, NGBE_FRMSZ_MAX_MASK,
- NGBE_FRMSZ_MAX(NGBE_FRAME_SIZE_DFT));
+ NGBE_FRMSZ_MAX(dev->data->mtu + NGBE_ETH_OVERHEAD));
/* Setup Rx queues */
for (i = 0; i < dev->data->nb_rx_queues; i++) {
rxq = dev->data->rx_queues[i];
+ /*
+ * Reset crc_len in case it was changed after queue setup by a
+ * call to configure.
+ */
+ if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_KEEP_CRC)
+ rxq->crc_len = RTE_ETHER_CRC_LEN;
+ else
+ rxq->crc_len = 0;
+
/* Setup the Base and Length of the Rx Descriptor Rings */
bus_addr = rxq->rx_ring_phys_addr;
wr32(hw, NGBE_RXBAL(rxq->reg_idx),
if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_SCATTER)
dev->data->scattered_rx = 1;
+ /*
+ * Setup the Checksum Register.
+ * Enable IP/L4 checksum computation by hardware if requested to do so.
+ */
+ rxcsum = rd32(hw, NGBE_PSRCTL);
+ rxcsum |= NGBE_PSRCTL_PCSD;
+ if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_CHECKSUM)
+ rxcsum |= NGBE_PSRCTL_L4CSUM;
+ else
+ rxcsum &= ~NGBE_PSRCTL_L4CSUM;
+
+ wr32(hw, NGBE_PSRCTL, rxcsum);
+
+ if (hw->is_pf) {
+ rdrxctl = rd32(hw, NGBE_SECRXCTL);
+ if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_KEEP_CRC)
+ rdrxctl &= ~NGBE_SECRXCTL_CRCSTRIP;
+ else
+ rdrxctl |= NGBE_SECRXCTL_CRCSTRIP;
+ wr32(hw, NGBE_SECRXCTL, rdrxctl);
+ }
ngbe_set_rx_function(dev);