#include <rte_lcore.h>
#include <rte_atomic.h>
#include <rte_branch_prediction.h>
-#include <rte_ring.h>
#include <rte_mempool.h>
#include <rte_malloc.h>
#include <rte_mbuf.h>
#include <rte_sctp.h>
#include <rte_string_fns.h>
#include <rte_errno.h>
+#include <rte_net.h>
#include "base/vmxnet3_defs.h"
#include "vmxnet3_ring.h"
#include "vmxnet3_logs.h"
#include "vmxnet3_ethdev.h"
-#define RTE_MBUF_DATA_DMA_ADDR(mb) \
- (uint64_t) ((mb)->buf_physaddr + (mb)->data_off)
+#define VMXNET3_TX_OFFLOAD_MASK ( \
+ PKT_TX_VLAN_PKT | \
+ PKT_TX_L4_MASK | \
+ PKT_TX_TCP_SEG)
-#define RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mb) \
- (uint64_t) ((mb)->buf_physaddr + RTE_PKTMBUF_HEADROOM)
+#define VMXNET3_TX_OFFLOAD_NOTSUP_MASK \
+ (PKT_TX_OFFLOAD_MASK ^ VMXNET3_TX_OFFLOAD_MASK)
-static uint32_t rxprod_reg[2] = {VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2};
+static const uint32_t rxprod_reg[2] = {VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2};
-static inline int vmxnet3_post_rx_bufs(vmxnet3_rx_queue_t* , uint8_t);
-static inline void vmxnet3_tq_tx_complete(vmxnet3_tx_queue_t *);
+static int vmxnet3_post_rx_bufs(vmxnet3_rx_queue_t*, uint8_t);
+static void vmxnet3_tq_tx_complete(vmxnet3_tx_queue_t *);
#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER_NOT_USED
static void vmxnet3_rxq_dump(struct vmxnet3_rx_queue *);
static void vmxnet3_txq_dump(struct vmxnet3_tx_queue *);
#endif
-static inline struct rte_mbuf *
-rte_rxmbuf_alloc(struct rte_mempool *mp)
-{
- struct rte_mbuf *m;
-
- m = __rte_mbuf_raw_alloc(mp);
- __rte_mbuf_sanity_check_raw(m, 0);
- return m;
-}
-
#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER_NOT_USED
static void
vmxnet3_rxq_dump(struct vmxnet3_rx_queue *rxq)
return;
PMD_RX_LOG(DEBUG,
- "RXQ: cmd0 base : 0x%p cmd1 base : 0x%p comp ring base : 0x%p.",
+ "RXQ: cmd0 base : %p cmd1 base : %p comp ring base : %p.",
rxq->cmd_ring[0].base, rxq->cmd_ring[1].base, rxq->comp_ring.base);
PMD_RX_LOG(DEBUG,
"RXQ: cmd0 basePA : 0x%lx cmd1 basePA : 0x%lx comp ring basePA : 0x%lx.",
if (txq == NULL)
return;
- PMD_TX_LOG(DEBUG, "TXQ: cmd base : 0x%p comp ring base : 0x%p data ring base : 0x%p.",
+ PMD_TX_LOG(DEBUG, "TXQ: cmd base : %p comp ring base : %p data ring base : %p.",
txq->cmd_ring.base, txq->comp_ring.base, txq->data_ring.base);
PMD_TX_LOG(DEBUG, "TXQ: cmd basePA : 0x%lx comp ring basePA : 0x%lx data ring basePA : 0x%lx.",
(unsigned long)txq->cmd_ring.basePA,
}
#endif
-static inline void
-vmxnet3_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring)
+static void
+vmxnet3_tx_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring)
{
while (ring->next2comp != ring->next2fill) {
- /* No need to worry about tx desc ownership, device is quiesced by now. */
+ /* No need to worry about desc ownership, device is quiesced by now. */
vmxnet3_buf_info_t *buf_info = ring->buf_info + ring->next2comp;
if (buf_info->m) {
}
}
+static void
+vmxnet3_rx_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring)
+{
+ uint32_t i;
+
+ for (i = 0; i < ring->size; i++) {
+ /* No need to worry about desc ownership, device is quiesced by now. */
+ vmxnet3_buf_info_t *buf_info = &ring->buf_info[i];
+
+ if (buf_info->m) {
+ rte_pktmbuf_free_seg(buf_info->m);
+ buf_info->m = NULL;
+ buf_info->bufPA = 0;
+ buf_info->len = 0;
+ }
+ vmxnet3_cmd_ring_adv_next2comp(ring);
+ }
+}
+
static void
vmxnet3_cmd_ring_release(vmxnet3_cmd_ring_t *ring)
{
- vmxnet3_cmd_ring_release_mbufs(ring);
rte_free(ring->buf_info);
ring->buf_info = NULL;
}
-
void
vmxnet3_dev_tx_queue_release(void *txq)
{
vmxnet3_tx_queue_t *tq = txq;
if (tq != NULL) {
+ /* Release mbufs */
+ vmxnet3_tx_cmd_ring_release_mbufs(&tq->cmd_ring);
/* Release the cmd_ring */
vmxnet3_cmd_ring_release(&tq->cmd_ring);
}
vmxnet3_rx_queue_t *rq = rxq;
if (rq != NULL) {
+ /* Release mbufs */
+ for (i = 0; i < VMXNET3_RX_CMDRING_SIZE; i++)
+ vmxnet3_rx_cmd_ring_release_mbufs(&rq->cmd_ring[i]);
+
/* Release both the cmd_rings */
for (i = 0; i < VMXNET3_RX_CMDRING_SIZE; i++)
vmxnet3_cmd_ring_release(&rq->cmd_ring[i]);
if (tq != NULL) {
/* Release the cmd_ring mbufs */
- vmxnet3_cmd_ring_release_mbufs(&tq->cmd_ring);
+ vmxnet3_tx_cmd_ring_release_mbufs(&tq->cmd_ring);
}
/* Tx vmxnet rings structure initialization*/
if (rq != NULL) {
/* Release both the cmd_rings mbufs */
for (i = 0; i < VMXNET3_RX_CMDRING_SIZE; i++)
- vmxnet3_cmd_ring_release_mbufs(&rq->cmd_ring[i]);
+ vmxnet3_rx_cmd_ring_release_mbufs(&rq->cmd_ring[i]);
}
ring0 = &rq->cmd_ring[0];
}
}
-static inline void
-vmxnet3_tq_tx_complete(vmxnet3_tx_queue_t *txq)
+static int
+vmxnet3_unmap_pkt(uint16_t eop_idx, vmxnet3_tx_queue_t *txq)
{
int completed = 0;
struct rte_mbuf *mbuf;
- vmxnet3_comp_ring_t *comp_ring = &txq->comp_ring;
- struct Vmxnet3_TxCompDesc *tcd = (struct Vmxnet3_TxCompDesc *)
- (comp_ring->base + comp_ring->next2proc);
- while (tcd->gen == comp_ring->gen) {
+ /* Release cmd_ring descriptor and free mbuf */
+ RTE_ASSERT(txq->cmd_ring.base[eop_idx].txd.eop == 1);
- /* Release cmd_ring descriptor and free mbuf */
-#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER
- VMXNET3_ASSERT(txq->cmd_ring.base[tcd->txdIdx].txd.eop == 1);
-#endif
- mbuf = txq->cmd_ring.buf_info[tcd->txdIdx].m;
- if (unlikely(mbuf == NULL))
- rte_panic("EOP desc does not point to a valid mbuf");
- else
- rte_pktmbuf_free(mbuf);
+ mbuf = txq->cmd_ring.buf_info[eop_idx].m;
+ if (mbuf == NULL)
+ rte_panic("EOP desc does not point to a valid mbuf");
+ rte_pktmbuf_free(mbuf);
+ txq->cmd_ring.buf_info[eop_idx].m = NULL;
- txq->cmd_ring.buf_info[tcd->txdIdx].m = NULL;
- /* Mark the txd for which tcd was generated as completed */
+ while (txq->cmd_ring.next2comp != eop_idx) {
+ /* no out-of-order completion */
+ RTE_ASSERT(txq->cmd_ring.base[txq->cmd_ring.next2comp].txd.cq == 0);
vmxnet3_cmd_ring_adv_next2comp(&txq->cmd_ring);
+ completed++;
+ }
+
+ /* Mark the txd for which tcd was generated as completed */
+ vmxnet3_cmd_ring_adv_next2comp(&txq->cmd_ring);
+
+ return completed + 1;
+}
+
+static void
+vmxnet3_tq_tx_complete(vmxnet3_tx_queue_t *txq)
+{
+ int completed = 0;
+ vmxnet3_comp_ring_t *comp_ring = &txq->comp_ring;
+ struct Vmxnet3_TxCompDesc *tcd = (struct Vmxnet3_TxCompDesc *)
+ (comp_ring->base + comp_ring->next2proc);
+
+ while (tcd->gen == comp_ring->gen) {
+ completed += vmxnet3_unmap_pkt(tcd->txdIdx, txq);
vmxnet3_comp_ring_adv_next2proc(comp_ring);
tcd = (struct Vmxnet3_TxCompDesc *)(comp_ring->base +
comp_ring->next2proc);
- completed++;
}
PMD_TX_LOG(DEBUG, "Processed %d tx comps & command descs.", completed);
}
+uint16_t
+vmxnet3_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ int32_t ret;
+ uint32_t i;
+ uint64_t ol_flags;
+ struct rte_mbuf *m;
+
+ for (i = 0; i != nb_pkts; i++) {
+ m = tx_pkts[i];
+ ol_flags = m->ol_flags;
+
+ /* Non-TSO packet cannot occupy more than
+ * VMXNET3_MAX_TXD_PER_PKT TX descriptors.
+ */
+ if ((ol_flags & PKT_TX_TCP_SEG) == 0 &&
+ m->nb_segs > VMXNET3_MAX_TXD_PER_PKT) {
+ rte_errno = -EINVAL;
+ return i;
+ }
+
+ /* check that only supported TX offloads are requested. */
+ if ((ol_flags & VMXNET3_TX_OFFLOAD_NOTSUP_MASK) != 0 ||
+ (ol_flags & PKT_TX_L4_MASK) ==
+ PKT_TX_SCTP_CKSUM) {
+ rte_errno = -ENOTSUP;
+ return i;
+ }
+
+#ifdef RTE_LIBRTE_ETHDEV_DEBUG
+ 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;
+}
+
uint16_t
vmxnet3_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts)
{
uint16_t nb_tx;
- Vmxnet3_TxDesc *txd = NULL;
- vmxnet3_buf_info_t *tbi = NULL;
- struct vmxnet3_hw *hw;
- struct rte_mbuf *txm;
vmxnet3_tx_queue_t *txq = tx_queue;
-
- hw = txq->hw;
+ struct vmxnet3_hw *hw = txq->hw;
+ Vmxnet3_TxQueueCtrl *txq_ctrl = &txq->shared->ctrl;
+ uint32_t deferred = rte_le_to_cpu_32(txq_ctrl->txNumDeferred);
if (unlikely(txq->stopped)) {
PMD_TX_LOG(DEBUG, "Tx queue is stopped.");
nb_tx = 0;
while (nb_tx < nb_pkts) {
-
- if (vmxnet3_cmd_ring_desc_avail(&txq->cmd_ring)) {
- int copy_size = 0;
-
- txm = tx_pkts[nb_tx];
- /* Don't support scatter packets yet, free them if met */
- if (txm->nb_segs != 1) {
- PMD_TX_LOG(DEBUG, "Don't support scatter packets yet, drop!");
- rte_pktmbuf_free(tx_pkts[nb_tx]);
- txq->stats.drop_total++;
-
- nb_tx++;
- continue;
+ Vmxnet3_GenericDesc *gdesc;
+ vmxnet3_buf_info_t *tbi;
+ uint32_t first2fill, avail, dw2;
+ struct rte_mbuf *txm = tx_pkts[nb_tx];
+ struct rte_mbuf *m_seg = txm;
+ int copy_size = 0;
+ bool tso = (txm->ol_flags & PKT_TX_TCP_SEG) != 0;
+ /* # of descriptors needed for a packet. */
+ unsigned count = txm->nb_segs;
+
+ avail = vmxnet3_cmd_ring_desc_avail(&txq->cmd_ring);
+ if (count > avail) {
+ /* Is command ring full? */
+ if (unlikely(avail == 0)) {
+ PMD_TX_LOG(DEBUG, "No free ring descriptors");
+ txq->stats.tx_ring_full++;
+ txq->stats.drop_total += (nb_pkts - nb_tx);
+ break;
}
- /* Needs to minus ether header len */
- if (txm->data_len > (hw->cur_mtu + ETHER_HDR_LEN)) {
- PMD_TX_LOG(DEBUG, "Packet data_len higher than MTU");
- rte_pktmbuf_free(tx_pkts[nb_tx]);
- txq->stats.drop_total++;
+ /* Command ring is not full but cannot handle the
+ * multi-segmented packet. Let's try the next packet
+ * in this case.
+ */
+ PMD_TX_LOG(DEBUG, "Running out of ring descriptors "
+ "(avail %d needed %d)", avail, count);
+ txq->stats.drop_total++;
+ if (tso)
+ txq->stats.drop_tso++;
+ rte_pktmbuf_free(txm);
+ nb_tx++;
+ continue;
+ }
- nb_tx++;
- continue;
- }
+ /* Drop non-TSO packet that is excessively fragmented */
+ if (unlikely(!tso && count > VMXNET3_MAX_TXD_PER_PKT)) {
+ PMD_TX_LOG(ERR, "Non-TSO packet cannot occupy more than %d tx "
+ "descriptors. Packet dropped.", VMXNET3_MAX_TXD_PER_PKT);
+ txq->stats.drop_too_many_segs++;
+ txq->stats.drop_total++;
+ rte_pktmbuf_free(txm);
+ nb_tx++;
+ continue;
+ }
- txd = (Vmxnet3_TxDesc *)(txq->cmd_ring.base + txq->cmd_ring.next2fill);
- if (rte_pktmbuf_pkt_len(txm) <= VMXNET3_HDR_COPY_SIZE) {
- struct Vmxnet3_TxDataDesc *tdd;
+ if (txm->nb_segs == 1 &&
+ rte_pktmbuf_pkt_len(txm) <= VMXNET3_HDR_COPY_SIZE) {
+ struct Vmxnet3_TxDataDesc *tdd;
- tdd = txq->data_ring.base + txq->cmd_ring.next2fill;
- copy_size = rte_pktmbuf_pkt_len(txm);
- rte_memcpy(tdd->data, rte_pktmbuf_mtod(txm, char *), copy_size);
- }
+ tdd = txq->data_ring.base + txq->cmd_ring.next2fill;
+ copy_size = rte_pktmbuf_pkt_len(txm);
+ rte_memcpy(tdd->data, rte_pktmbuf_mtod(txm, char *), copy_size);
+ }
- /* Fill the tx descriptor */
+ /* use the previous gen bit for the SOP desc */
+ dw2 = (txq->cmd_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
+ first2fill = txq->cmd_ring.next2fill;
+ do {
+ /* Remember the transmit buffer for cleanup */
tbi = txq->cmd_ring.buf_info + txq->cmd_ring.next2fill;
- tbi->bufPA = RTE_MBUF_DATA_DMA_ADDR(txm);
+
+ /* NB: the following assumes that VMXNET3 maximum
+ * transmit buffer size (16K) is greater than
+ * maximum size of mbuf segment size.
+ */
+ gdesc = txq->cmd_ring.base + txq->cmd_ring.next2fill;
if (copy_size)
- txd->addr = rte_cpu_to_le_64(txq->data_ring.basePA +
- txq->cmd_ring.next2fill *
- sizeof(struct Vmxnet3_TxDataDesc));
+ gdesc->txd.addr = rte_cpu_to_le_64(txq->data_ring.basePA +
+ txq->cmd_ring.next2fill *
+ sizeof(struct Vmxnet3_TxDataDesc));
else
- txd->addr = tbi->bufPA;
- txd->len = txm->data_len;
+ gdesc->txd.addr = rte_mbuf_data_dma_addr(m_seg);
- /* Mark the last descriptor as End of Packet. */
- txd->cq = 1;
- txd->eop = 1;
-
- /* Add VLAN tag if requested */
- if (txm->ol_flags & PKT_TX_VLAN_PKT) {
- txd->ti = 1;
- txd->tci = rte_cpu_to_le_16(txm->vlan_tci);
- }
+ gdesc->dword[2] = dw2 | m_seg->data_len;
+ gdesc->dword[3] = 0;
- /* Record current mbuf for freeing it later in tx complete */
-#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER
- VMXNET3_ASSERT(txm);
-#endif
- tbi->m = txm;
+ /* move to the next2fill descriptor */
+ vmxnet3_cmd_ring_adv_next2fill(&txq->cmd_ring);
- /* Set the offloading mode to default */
- txd->hlen = 0;
- txd->om = VMXNET3_OM_NONE;
- txd->msscof = 0;
+ /* use the right gen for non-SOP desc */
+ dw2 = txq->cmd_ring.gen << VMXNET3_TXD_GEN_SHIFT;
+ } while ((m_seg = m_seg->next) != NULL);
- /* finally flip the GEN bit of the SOP desc */
- txd->gen = txq->cmd_ring.gen;
- txq->shared->ctrl.txNumDeferred++;
+ /* set the last buf_info for the pkt */
+ tbi->m = txm;
+ /* Update the EOP descriptor */
+ gdesc->dword[3] |= VMXNET3_TXD_EOP | VMXNET3_TXD_CQ;
- /* move to the next2fill descriptor */
- vmxnet3_cmd_ring_adv_next2fill(&txq->cmd_ring);
- nb_tx++;
+ /* Add VLAN tag if present */
+ gdesc = txq->cmd_ring.base + first2fill;
+ if (txm->ol_flags & PKT_TX_VLAN_PKT) {
+ gdesc->txd.ti = 1;
+ gdesc->txd.tci = txm->vlan_tci;
+ }
+ if (tso) {
+ uint16_t mss = txm->tso_segsz;
+
+ RTE_ASSERT(mss > 0);
+
+ gdesc->txd.hlen = txm->l2_len + txm->l3_len + txm->l4_len;
+ gdesc->txd.om = VMXNET3_OM_TSO;
+ gdesc->txd.msscof = mss;
+
+ deferred += (rte_pktmbuf_pkt_len(txm) - gdesc->txd.hlen + mss - 1) / mss;
+ } else if (txm->ol_flags & PKT_TX_L4_MASK) {
+ gdesc->txd.om = VMXNET3_OM_CSUM;
+ gdesc->txd.hlen = txm->l2_len + txm->l3_len;
+
+ switch (txm->ol_flags & PKT_TX_L4_MASK) {
+ case PKT_TX_TCP_CKSUM:
+ gdesc->txd.msscof = gdesc->txd.hlen + offsetof(struct tcp_hdr, cksum);
+ break;
+ case PKT_TX_UDP_CKSUM:
+ gdesc->txd.msscof = gdesc->txd.hlen + offsetof(struct udp_hdr, dgram_cksum);
+ break;
+ default:
+ PMD_TX_LOG(WARNING, "requested cksum offload not supported %#llx",
+ txm->ol_flags & PKT_TX_L4_MASK);
+ abort();
+ }
+ deferred++;
} else {
- PMD_TX_LOG(DEBUG, "No free tx cmd desc(s)");
- txq->stats.drop_total += (nb_pkts - nb_tx);
- break;
+ gdesc->txd.hlen = 0;
+ gdesc->txd.om = VMXNET3_OM_NONE;
+ gdesc->txd.msscof = 0;
+ deferred++;
}
- }
- PMD_TX_LOG(DEBUG, "vmxnet3 txThreshold: %u", txq->shared->ctrl.txThreshold);
+ /* flip the GEN bit on the SOP */
+ rte_compiler_barrier();
+ gdesc->dword[2] ^= VMXNET3_TXD_GEN;
- if (txq->shared->ctrl.txNumDeferred >= txq->shared->ctrl.txThreshold) {
+ txq_ctrl->txNumDeferred = rte_cpu_to_le_32(deferred);
+ nb_tx++;
+ }
- txq->shared->ctrl.txNumDeferred = 0;
+ PMD_TX_LOG(DEBUG, "vmxnet3 txThreshold: %u", rte_le_to_cpu_32(txq_ctrl->txThreshold));
+
+ if (deferred >= rte_le_to_cpu_32(txq_ctrl->txThreshold)) {
+ txq_ctrl->txNumDeferred = 0;
/* Notify vSwitch that packets are available. */
VMXNET3_WRITE_BAR0_REG(hw, (VMXNET3_REG_TXPROD + txq->queue_id * VMXNET3_REG_ALIGN),
txq->cmd_ring.next2fill);
/*
* Allocates mbufs and clusters. Post rx descriptors with buffer details
* so that device can receive packets in those buffers.
- * Ring layout:
- * Among the two rings, 1st ring contains buffers of type 0 and type1.
+ * Ring layout:
+ * Among the two rings, 1st ring contains buffers of type 0 and type 1.
* bufs_per_pkt is set such that for non-LRO cases all the buffers required
* by a frame will fit in 1st ring (1st buf of type0 and rest of type1).
* 2nd ring contains buffers of type 1 alone. Second ring mostly be used
* only for LRO.
- *
*/
-static inline int
+static int
vmxnet3_post_rx_bufs(vmxnet3_rx_queue_t *rxq, uint8_t ring_id)
{
int err = 0;
rxd = (struct Vmxnet3_RxDesc *)(ring->base + ring->next2fill);
/* Allocate blank mbuf for the current Rx Descriptor */
- mbuf = rte_rxmbuf_alloc(rxq->mp);
+ mbuf = rte_mbuf_raw_alloc(rxq->mp);
if (unlikely(mbuf == NULL)) {
- PMD_RX_LOG(ERR, "Error allocating mbuf in %s", __func__);
+ PMD_RX_LOG(ERR, "Error allocating mbuf");
rxq->stats.rx_buf_alloc_failure++;
err = ENOMEM;
break;
buf_info->m = mbuf;
buf_info->len = (uint16_t)(mbuf->buf_len -
RTE_PKTMBUF_HEADROOM);
- buf_info->bufPA = RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mbuf);
+ buf_info->bufPA = rte_mbuf_data_dma_addr_default(mbuf);
/* Load Rx Descriptor with the buffer's GPA */
rxd->addr = buf_info->bufPA;
return i;
}
+
+/* Receive side checksum and other offloads */
+static void
+vmxnet3_rx_offload(const Vmxnet3_RxCompDesc *rcd, struct rte_mbuf *rxm)
+{
+ /* Check for RSS */
+ if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE) {
+ rxm->ol_flags |= PKT_RX_RSS_HASH;
+ rxm->hash.rss = rcd->rssHash;
+ }
+
+ /* Check packet type, checksum errors, etc. Only support IPv4 for now. */
+ if (rcd->v4) {
+ struct ether_hdr *eth = rte_pktmbuf_mtod(rxm, struct ether_hdr *);
+ struct ipv4_hdr *ip = (struct ipv4_hdr *)(eth + 1);
+
+ if (((ip->version_ihl & 0xf) << 2) > (int)sizeof(struct ipv4_hdr))
+ rxm->packet_type = RTE_PTYPE_L3_IPV4_EXT;
+ else
+ rxm->packet_type = RTE_PTYPE_L3_IPV4;
+
+ if (!rcd->cnc) {
+ if (!rcd->ipc)
+ rxm->ol_flags |= PKT_RX_IP_CKSUM_BAD;
+
+ if ((rcd->tcp || rcd->udp) && !rcd->tuc)
+ rxm->ol_flags |= PKT_RX_L4_CKSUM_BAD;
+ }
+ }
+}
+
/*
* Process the Rx Completion Ring of given vmxnet3_rx_queue
* for nb_pkts burst and return the number of packets received
idx = rcd->rxdIdx;
ring_idx = (uint8_t)((rcd->rqID == rxq->qid1) ? 0 : 1);
rxd = (Vmxnet3_RxDesc *)rxq->cmd_ring[ring_idx].base + idx;
+ RTE_SET_USED(rxd); /* used only for assert when enabled */
rbi = rxq->cmd_ring[ring_idx].buf_info + idx;
- if (unlikely(rcd->sop != 1 || rcd->eop != 1)) {
- rte_pktmbuf_free_seg(rbi->m);
- PMD_RX_LOG(DEBUG, "Packet spread across multiple buffers\n)");
- goto rcd_done;
- }
-
PMD_RX_LOG(DEBUG, "rxd idx: %d ring idx: %d.", idx, ring_idx);
-#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER
- VMXNET3_ASSERT(rcd->len <= rxd->len);
- VMXNET3_ASSERT(rbi->m);
-#endif
- if (unlikely(rcd->len == 0)) {
- PMD_RX_LOG(DEBUG, "Rx buf was skipped. rxring[%d][%d]\n)",
- ring_idx, idx);
-#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER
- VMXNET3_ASSERT(rcd->sop && rcd->eop);
-#endif
- rte_pktmbuf_free_seg(rbi->m);
- goto rcd_done;
- }
+ RTE_ASSERT(rcd->len <= rxd->len);
+ RTE_ASSERT(rbi->m);
- /* Assuming a packet is coming in a single packet buffer */
- if (unlikely(rxd->btype != VMXNET3_RXD_BTYPE_HEAD)) {
- PMD_RX_LOG(DEBUG,
- "Alert : Misbehaving device, incorrect "
- " buffer type used. iPacket dropped.");
- rte_pktmbuf_free_seg(rbi->m);
- goto rcd_done;
- }
-#ifdef RTE_LIBRTE_VMXNET3_DEBUG_DRIVER
- VMXNET3_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_HEAD);
-#endif
/* Get the packet buffer pointer from buf_info */
rxm = rbi->m;
rxq->cmd_ring[ring_idx].next2comp = idx;
/* For RCD with EOP set, check if there is frame error */
- if (unlikely(rcd->err)) {
+ if (unlikely(rcd->eop && rcd->err)) {
rxq->stats.drop_total++;
rxq->stats.drop_err++;
goto rcd_done;
}
- /* Check for hardware stripped VLAN tag */
- if (rcd->ts) {
- PMD_RX_LOG(DEBUG, "Received packet with vlan ID: %d.",
- rcd->tci);
- rxm->ol_flags = PKT_RX_VLAN_PKT;
- /* Copy vlan tag in packet buffer */
- rxm->vlan_tci = rte_le_to_cpu_16((uint16_t)rcd->tci);
- } else {
- rxm->ol_flags = 0;
- rxm->vlan_tci = 0;
- }
-
/* Initialize newly received packet buffer */
rxm->port = rxq->port_id;
rxm->nb_segs = 1;
rxm->pkt_len = (uint16_t)rcd->len;
rxm->data_len = (uint16_t)rcd->len;
rxm->data_off = RTE_PKTMBUF_HEADROOM;
+ rxm->ol_flags = 0;
+ rxm->vlan_tci = 0;
- /* Check packet type, checksum errors, etc. Only support IPv4 for now. */
- if (rcd->v4) {
- struct ether_hdr *eth = rte_pktmbuf_mtod(rxm, struct ether_hdr *);
- struct ipv4_hdr *ip = (struct ipv4_hdr *)(eth + 1);
+ /*
+ * If this is the first buffer of the received packet,
+ * set the pointer to the first mbuf of the packet
+ * 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 (rcd->sop) {
+ RTE_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_HEAD);
- if (((ip->version_ihl & 0xf) << 2) > (int)sizeof(struct ipv4_hdr))
- rxm->ol_flags |= PKT_RX_IPV4_HDR_EXT;
- else
- rxm->ol_flags |= PKT_RX_IPV4_HDR;
+ if (unlikely(rcd->len == 0)) {
+ RTE_ASSERT(rcd->eop);
- if (!rcd->cnc) {
- if (!rcd->ipc)
- rxm->ol_flags |= PKT_RX_IP_CKSUM_BAD;
+ PMD_RX_LOG(DEBUG,
+ "Rx buf was skipped. rxring[%d][%d])",
+ ring_idx, idx);
+ rte_pktmbuf_free_seg(rxm);
+ goto rcd_done;
+ }
+
+ rxq->start_seg = rxm;
+ vmxnet3_rx_offload(rcd, rxm);
+ } else {
+ struct rte_mbuf *start = rxq->start_seg;
+
+ RTE_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_BODY);
+
+ start->pkt_len += rxm->data_len;
+ start->nb_segs++;
- if ((rcd->tcp || rcd->udp) && !rcd->tuc)
- rxm->ol_flags |= PKT_RX_L4_CKSUM_BAD;
+ rxq->last_seg->next = rxm;
+ }
+ rxq->last_seg = rxm;
+
+ if (rcd->eop) {
+ struct rte_mbuf *start = rxq->start_seg;
+
+ /* Check for hardware stripped VLAN tag */
+ if (rcd->ts) {
+ start->ol_flags |= (PKT_RX_VLAN_PKT | PKT_RX_VLAN_STRIPPED);
+ start->vlan_tci = rte_le_to_cpu_16((uint16_t)rcd->tci);
}
+
+ rx_pkts[nb_rx++] = start;
+ rxq->start_seg = NULL;
}
- rx_pkts[nb_rx++] = rxm;
rcd_done:
rxq->cmd_ring[ring_idx].next2comp = idx;
- VMXNET3_INC_RING_IDX_ONLY(rxq->cmd_ring[ring_idx].next2comp, rxq->cmd_ring[ring_idx].size);
+ VMXNET3_INC_RING_IDX_ONLY(rxq->cmd_ring[ring_idx].next2comp,
+ rxq->cmd_ring[ring_idx].size);
/* It's time to allocate some new buf and renew descriptors */
vmxnet3_post_rx_bufs(rxq, ring_idx);
rcd = &rxq->comp_ring.base[rxq->comp_ring.next2proc].rcd;
nb_rxd++;
if (nb_rxd > rxq->cmd_ring[0].size) {
- PMD_RX_LOG(ERR,
- "Used up quota of receiving packets,"
+ PMD_RX_LOG(ERR, "Used up quota of receiving packets,"
" relinquish control.");
break;
}
const struct rte_memzone *mz;
snprintf(z_name, sizeof(z_name), "%s_%s_%d_%d",
- dev->driver->pci_drv.name, ring_name,
- dev->data->port_id, queue_id);
+ dev->driver->pci_drv.driver.name, ring_name,
+ dev->data->port_id, queue_id);
mz = rte_memzone_lookup(z_name);
if (mz)
return mz;
return rte_memzone_reserve_aligned(z_name, ring_size,
- socket_id, 0, VMXNET3_RING_BA_ALIGN);
+ socket_id, 0, VMXNET3_RING_BA_ALIGN);
}
int
uint16_t queue_idx,
uint16_t nb_desc,
unsigned int socket_id,
- __attribute__((unused)) const struct rte_eth_txconf *tx_conf)
+ __rte_unused const struct rte_eth_txconf *tx_conf)
{
struct vmxnet3_hw *hw = dev->data->dev_private;
const struct rte_memzone *mz;
PMD_INIT_FUNC_TRACE();
- if ((tx_conf->txq_flags & ETH_TXQ_FLAGS_NOMULTSEGS) !=
- ETH_TXQ_FLAGS_NOMULTSEGS) {
- PMD_INIT_LOG(ERR, "TX Multi segment not support yet");
+ if ((tx_conf->txq_flags & ETH_TXQ_FLAGS_NOXSUMSCTP) !=
+ ETH_TXQ_FLAGS_NOXSUMSCTP) {
+ PMD_INIT_LOG(ERR, "SCTP checksum offload not supported");
return -EINVAL;
}
- if ((tx_conf->txq_flags & ETH_TXQ_FLAGS_NOXSUMS) !=
- ETH_TXQ_FLAGS_NOXSUMS) {
- PMD_INIT_LOG(ERR, "TX no support for checksum offload yet");
- return -EINVAL;
- }
-
- txq = rte_zmalloc("ethdev_tx_queue", sizeof(struct vmxnet3_tx_queue), RTE_CACHE_LINE_SIZE);
+ txq = rte_zmalloc("ethdev_tx_queue", sizeof(struct vmxnet3_tx_queue),
+ RTE_CACHE_LINE_SIZE);
if (txq == NULL) {
PMD_INIT_LOG(ERR, "Can not allocate tx queue structure");
return -ENOMEM;
uint16_t queue_idx,
uint16_t nb_desc,
unsigned int socket_id,
- __attribute__((unused)) const struct rte_eth_rxconf *rx_conf,
+ __rte_unused const struct rte_eth_rxconf *rx_conf,
struct rte_mempool *mp)
{
const struct rte_memzone *mz;
struct vmxnet3_rx_queue *rxq;
- struct vmxnet3_hw *hw = dev->data->dev_private;
+ struct vmxnet3_hw *hw = dev->data->dev_private;
struct vmxnet3_cmd_ring *ring0, *ring1, *ring;
struct vmxnet3_comp_ring *comp_ring;
int size;
uint8_t i;
char mem_name[32];
- uint16_t buf_size;
PMD_INIT_FUNC_TRACE();
- buf_size = rte_pktmbuf_data_room_size(mp) -
- RTE_PKTMBUF_HEADROOM;
-
- if (dev->data->dev_conf.rxmode.max_rx_pkt_len > buf_size) {
- PMD_INIT_LOG(ERR, "buf_size = %u, max_pkt_len = %u, "
- "VMXNET3 don't support scatter packets yet",
- buf_size, dev->data->dev_conf.rxmode.max_rx_pkt_len);
- return -EINVAL;
- }
-
- rxq = rte_zmalloc("ethdev_rx_queue", sizeof(struct vmxnet3_rx_queue), RTE_CACHE_LINE_SIZE);
+ rxq = rte_zmalloc("ethdev_rx_queue", sizeof(struct vmxnet3_rx_queue),
+ RTE_CACHE_LINE_SIZE);
if (rxq == NULL) {
PMD_INIT_LOG(ERR, "Can not allocate rx queue structure");
return -ENOMEM;
ring->rid = i;
snprintf(mem_name, sizeof(mem_name), "rx_ring_%d_buf_info", i);
- ring->buf_info = rte_zmalloc(mem_name, ring->size * sizeof(vmxnet3_buf_info_t), RTE_CACHE_LINE_SIZE);
+ ring->buf_info = rte_zmalloc(mem_name,
+ ring->size * sizeof(vmxnet3_buf_info_t),
+ RTE_CACHE_LINE_SIZE);
if (ring->buf_info == NULL) {
PMD_INIT_LOG(ERR, "ERROR: Creating rx_buf_info structure");
return -ENOMEM;
/* Passing 0 as alloc_num will allocate full ring */
ret = vmxnet3_post_rx_bufs(rxq, j);
if (ret <= 0) {
- PMD_INIT_LOG(ERR, "ERROR: Posting Rxq: %d buffers ring: %d", i, j);
+ PMD_INIT_LOG(ERR,
+ "ERROR: Posting Rxq: %d buffers ring: %d",
+ i, j);
return -ret;
}
- /* Updating device with the index:next2fill to fill the mbufs for coming packets */
+ /*
+ * Updating device with the index:next2fill to fill the
+ * mbufs for coming packets.
+ */
if (unlikely(rxq->shared->ctrl.updateRxProd)) {
VMXNET3_WRITE_BAR0_REG(hw, rxprod_reg[j] + (rxq->queue_id * VMXNET3_REG_ALIGN),
rxq->cmd_ring[j].next2fill);
}
}
rxq->stopped = FALSE;
+ rxq->start_seg = NULL;
}
for (i = 0; i < dev->data->nb_tx_queues; i++) {
dev_rss_conf->hashFunc = VMXNET3_RSS_HASH_FUNC_TOEPLITZ;
/* loading hashKeySize */
dev_rss_conf->hashKeySize = VMXNET3_RSS_MAX_KEY_SIZE;
- /* loading indTableSize : Must not exceed VMXNET3_RSS_MAX_IND_TABLE_SIZE (128)*/
+ /* loading indTableSize: Must not exceed VMXNET3_RSS_MAX_IND_TABLE_SIZE (128)*/
dev_rss_conf->indTableSize = (uint16_t)(hw->num_rx_queues * 4);
if (port_rss_conf->rss_key == NULL) {
}
/* loading hashKey */
- memcpy(&dev_rss_conf->hashKey[0], port_rss_conf->rss_key, dev_rss_conf->hashKeySize);
+ memcpy(&dev_rss_conf->hashKey[0], port_rss_conf->rss_key,
+ dev_rss_conf->hashKeySize);
/* loading indTable */
for (i = 0, j = 0; i < dev_rss_conf->indTableSize; i++, j++) {