-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * 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
- * 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
- * distribution.
- * * 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
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
*/
#include <sys/queue.h>
#include <rte_log.h>
#include <rte_debug.h>
#include <rte_pci.h>
+#include <rte_bus_pci.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_memzone.h>
#include <rte_malloc.h>
#include <rte_mbuf.h>
#include <rte_ether.h>
-#include <rte_ethdev.h>
+#include <ethdev_driver.h>
#include <rte_prefetch.h>
#include <rte_ip.h>
#include <rte_udp.h>
#include <rte_tcp.h>
#include <rte_sctp.h>
+#include <rte_net.h>
#include <rte_string_fns.h>
#include "e1000_logs.h"
#define E1000_RXDCTL_GRAN 0x01000000 /* RXDCTL Granularity */
+#define E1000_TX_OFFLOAD_MASK (RTE_MBUF_F_TX_IPV6 | \
+ RTE_MBUF_F_TX_IPV4 | \
+ RTE_MBUF_F_TX_IP_CKSUM | \
+ RTE_MBUF_F_TX_L4_MASK | \
+ RTE_MBUF_F_TX_VLAN)
+
+#define E1000_TX_OFFLOAD_NOTSUP_MASK \
+ (RTE_MBUF_F_TX_OFFLOAD_MASK ^ E1000_TX_OFFLOAD_MASK)
+
+/* PCI offset for querying configuration status register */
+#define PCI_CFG_STATUS_REG 0x06
+#define FLUSH_DESC_REQUIRED 0x100
+
+
/**
* Structure associated with each descriptor of the RX ring of a RX queue.
*/
struct em_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. */
+ uint64_t offloads; /**< Offloads of RTE_ETH_RX_OFFLOAD_* */
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. */
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. */
+ uint16_t port_id; /**< Device port identifier. */
uint8_t pthresh; /**< Prefetch threshold register. */
uint8_t hthresh; /**< Host threshold register. */
uint8_t wthresh; /**< Write-back threshold register. */
uint8_t crc_len; /**< 0 if CRC stripped, 4 otherwise. */
+ const struct rte_memzone *mz;
};
/**
struct em_ctx_info {
uint64_t flags; /**< ol_flags related to context build. */
uint32_t cmp_mask; /**< compare mask */
- union em_vlan_macip hdrlen; /**< L2 and L3 header lenghts */
+ union em_vlan_macip hdrlen; /**< L2 and L3 header lengths */
};
/**
/** Total number of TX descriptors ready to be allocated. */
uint16_t nb_tx_free;
uint16_t queue_id; /**< TX queue index. */
- uint8_t port_id; /**< Device port identifier. */
+ uint16_t port_id; /**< Device port identifier. */
uint8_t pthresh; /**< Prefetch threshold register. */
uint8_t hthresh; /**< Host threshold register. */
uint8_t wthresh; /**< Write-back threshold register. */
struct em_ctx_info ctx_cache;
/**< Hardware context history.*/
+ uint64_t offloads; /**< offloads of RTE_ETH_TX_OFFLOAD_* */
+ const struct rte_memzone *mz;
};
#if 1
/* setup IPCS* fields */
ctx.lower_setup.ip_fields.ipcss = (uint8_t)l2len;
ctx.lower_setup.ip_fields.ipcso = (uint8_t)(l2len +
- offsetof(struct ipv4_hdr, hdr_checksum));
+ offsetof(struct rte_ipv4_hdr, hdr_checksum));
/*
* When doing checksum or TCP segmentation with IPv6 headers,
* IPCSE field should be set t0 0.
*/
- if (flags & PKT_TX_IP_CKSUM) {
+ if (flags & RTE_MBUF_F_TX_IP_CKSUM) {
ctx.lower_setup.ip_fields.ipcse =
(uint16_t)rte_cpu_to_le_16(ipcse - 1);
cmd_len |= E1000_TXD_CMD_IP;
ctx.upper_setup.tcp_fields.tucss = (uint8_t)ipcse;
ctx.upper_setup.tcp_fields.tucse = 0;
- switch (flags & PKT_TX_L4_MASK) {
- case PKT_TX_UDP_CKSUM:
+ switch (flags & RTE_MBUF_F_TX_L4_MASK) {
+ case RTE_MBUF_F_TX_UDP_CKSUM:
ctx.upper_setup.tcp_fields.tucso = (uint8_t)(ipcse +
- offsetof(struct udp_hdr, dgram_cksum));
+ offsetof(struct rte_udp_hdr, dgram_cksum));
cmp_mask |= TX_MACIP_LEN_CMP_MASK;
break;
- case PKT_TX_TCP_CKSUM:
+ case RTE_MBUF_F_TX_TCP_CKSUM:
ctx.upper_setup.tcp_fields.tucso = (uint8_t)(ipcse +
- offsetof(struct tcp_hdr, cksum));
+ offsetof(struct rte_tcp_hdr, cksum));
cmd_len |= E1000_TXD_CMD_TCP;
cmp_mask |= TX_MACIP_LEN_CMP_MASK;
break;
desc_to_clean_to = sw_ring[desc_to_clean_to].last_id;
if (! (txr[desc_to_clean_to].upper.fields.status & E1000_TXD_STAT_DD))
{
- PMD_TX_FREE_LOG(DEBUG,
- "TX descriptor %4u is not done"
- "(port=%d queue=%d)", desc_to_clean_to,
- txq->port_id, txq->queue_id);
+ PMD_TX_LOG(DEBUG,
+ "TX descriptor %4u is not done"
+ "(port=%d queue=%d)", desc_to_clean_to,
+ txq->port_id, txq->queue_id);
/* Failed to clean any descriptors, better luck next time */
return -(1);
}
nb_tx_to_clean = (uint16_t)(desc_to_clean_to -
last_desc_cleaned);
- PMD_TX_FREE_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);
+ 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
static const uint32_t l3_olinfo[2] = {0, E1000_TXD_POPTS_IXSM << 8};
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];
+ tmp = l4_olinfo[(ol_flags & RTE_MBUF_F_TX_L4_MASK) != RTE_MBUF_F_TX_L4_NO_CKSUM];
+ tmp |= l3_olinfo[(ol_flags & RTE_MBUF_F_TX_IP_CKSUM) != 0];
return tmp;
}
ol_flags = tx_pkt->ol_flags;
/* If hardware offload required */
- tx_ol_req = (ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_L4_MASK));
+ tx_ol_req = (ol_flags & (RTE_MBUF_F_TX_IP_CKSUM | RTE_MBUF_F_TX_L4_MASK));
if (tx_ol_req) {
hdrlen.f.vlan_tci = tx_pkt->vlan_tci;
hdrlen.f.l2_len = tx_pkt->l2_len;
* nb_used better be less than or equal to txq->tx_rs_thresh
*/
while (unlikely (nb_used > txq->nb_tx_free)) {
- PMD_TX_FREE_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);
+ 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 (em_xmit_cleanup(txq) != 0) {
/* Could not clean any descriptors */
popts_spec = 0;
/* Set VLAN Tag offload fields. */
- if (ol_flags & PKT_TX_VLAN_PKT) {
+ if (ol_flags & RTE_MBUF_F_TX_VLAN) {
cmd_type_len |= E1000_TXD_CMD_VLE;
popts_spec = tx_pkt->vlan_tci << E1000_TXD_VLAN_SHIFT;
}
* Set up Transmit Data Descriptor.
*/
slen = m_seg->data_len;
- buf_dma_addr = rte_mbuf_data_dma_addr(m_seg);
+ buf_dma_addr = rte_mbuf_data_iova(m_seg);
txd->buffer_addr = rte_cpu_to_le_64(buf_dma_addr);
txd->lower.data = rte_cpu_to_le_32(cmd_type_len | slen);
/* Set RS bit only on threshold packets' last descriptor */
if (txq->nb_tx_used >= txq->tx_rs_thresh) {
- PMD_TX_FREE_LOG(DEBUG,
- "Setting RS bit on TXD id=%4u "
- "(port=%d queue=%d)",
- tx_last, txq->port_id, txq->queue_id);
+ PMD_TX_LOG(DEBUG,
+ "Setting RS bit on TXD id=%4u "
+ "(port=%d queue=%d)",
+ tx_last, txq->port_id, txq->queue_id);
cmd_type_len |= E1000_TXD_CMD_RS;
PMD_TX_LOG(DEBUG, "port_id=%u queue_id=%u tx_tail=%u nb_tx=%u",
(unsigned) txq->port_id, (unsigned) txq->queue_id,
(unsigned) tx_id, (unsigned) nb_tx);
- E1000_PCI_REG_WRITE(txq->tdt_reg_addr, tx_id);
+ E1000_PCI_REG_WRITE_RELAXED(txq->tdt_reg_addr, tx_id);
txq->tx_tail = tx_id;
return nb_tx;
}
+/*********************************************************************
+ *
+ * TX prep functions
+ *
+ **********************************************************************/
+uint16_t
+eth_em_prep_pkts(__rte_unused void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ int i, ret;
+ struct rte_mbuf *m;
+
+ for (i = 0; i < nb_pkts; i++) {
+ m = tx_pkts[i];
+
+ if (m->ol_flags & E1000_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
/* Check if VLAN present */
pkt_flags = ((rx_status & E1000_RXD_STAT_VP) ?
- PKT_RX_VLAN_PKT | PKT_RX_VLAN_STRIPPED : 0);
+ RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED : 0);
return pkt_flags;
}
uint64_t pkt_flags = 0;
if (rx_error & E1000_RXD_ERR_IPE)
- pkt_flags |= PKT_RX_IP_CKSUM_BAD;
+ pkt_flags |= RTE_MBUF_F_RX_IP_CKSUM_BAD;
if (rx_error & E1000_RXD_ERR_TCPE)
- pkt_flags |= PKT_RX_L4_CKSUM_BAD;
+ pkt_flags |= RTE_MBUF_F_RX_L4_CKSUM_BAD;
return pkt_flags;
}
rxm = rxe->mbuf;
rxe->mbuf = nmb;
dma_addr =
- rte_cpu_to_le_64(rte_mbuf_data_dma_addr_default(nmb));
+ rte_cpu_to_le_64(rte_mbuf_data_iova_default(nmb));
rxdp->buffer_addr = dma_addr;
rxdp->status = 0;
rxm->ol_flags = rxm->ol_flags |
rx_desc_error_to_pkt_flags(rxd.errors);
- /* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */
+ /* Only valid if RTE_MBUF_F_RX_VLAN set in pkt_flags */
rxm->vlan_tci = rte_le_to_cpu_16(rxd.special);
/*
* 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
+ * RDH register, which creates a "full" ring situation from the
* hardware point of view...
*/
nb_hold = (uint16_t) (nb_hold + rxq->nb_rx_hold);
*/
rxm = rxe->mbuf;
rxe->mbuf = nmb;
- dma = rte_cpu_to_le_64(rte_mbuf_data_dma_addr_default(nmb));
+ dma = rte_cpu_to_le_64(rte_mbuf_data_iova_default(nmb));
rxdp->buffer_addr = dma;
rxdp->status = 0;
*/
rxm->next = NULL;
if (unlikely(rxq->crc_len > 0)) {
- first_seg->pkt_len -= ETHER_CRC_LEN;
- if (data_len <= ETHER_CRC_LEN) {
+ first_seg->pkt_len -= RTE_ETHER_CRC_LEN;
+ if (data_len <= RTE_ETHER_CRC_LEN) {
rte_pktmbuf_free_seg(rxm);
first_seg->nb_segs--;
last_seg->data_len = (uint16_t)
(last_seg->data_len -
- (ETHER_CRC_LEN - data_len));
+ (RTE_ETHER_CRC_LEN - data_len));
last_seg->next = NULL;
} else
- rxm->data_len =
- (uint16_t) (data_len - ETHER_CRC_LEN);
+ rxm->data_len = (uint16_t)
+ (data_len - RTE_ETHER_CRC_LEN);
}
/*
first_seg->ol_flags = first_seg->ol_flags |
rx_desc_error_to_pkt_flags(rxd.errors);
- /* Only valid if PKT_RX_VLAN_PKT set in pkt_flags */
+ /* Only valid if RTE_MBUF_F_RX_VLAN set in pkt_flags */
rxm->vlan_tci = rte_le_to_cpu_16(rxd.special);
/* Prefetch data of first segment, if configured to do so. */
* 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
+ * RDH register, which creates a "full" ring situation from the
* hardware point of view...
*/
nb_hold = (uint16_t) (nb_hold + rxq->nb_rx_hold);
if (txq != NULL) {
em_tx_queue_release_mbufs(txq);
rte_free(txq->sw_ring);
+ rte_memzone_free(txq->mz);
rte_free(txq);
}
}
void
-eth_em_tx_queue_release(void *txq)
+eth_em_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
{
- em_tx_queue_release(txq);
+ em_tx_queue_release(dev->data->tx_queues[qid]);
}
/* (Re)set dynamic em_tx_queue fields to defaults */
memset((void*)&txq->ctx_cache, 0, sizeof (txq->ctx_cache));
}
+uint64_t
+em_get_tx_port_offloads_capa(struct rte_eth_dev *dev)
+{
+ uint64_t tx_offload_capa;
+
+ RTE_SET_USED(dev);
+ tx_offload_capa =
+ RTE_ETH_TX_OFFLOAD_MULTI_SEGS |
+ RTE_ETH_TX_OFFLOAD_VLAN_INSERT |
+ RTE_ETH_TX_OFFLOAD_IPV4_CKSUM |
+ RTE_ETH_TX_OFFLOAD_UDP_CKSUM |
+ RTE_ETH_TX_OFFLOAD_TCP_CKSUM;
+
+ return tx_offload_capa;
+}
+
+uint64_t
+em_get_tx_queue_offloads_capa(struct rte_eth_dev *dev)
+{
+ uint64_t tx_queue_offload_capa;
+
+ /*
+ * As only one Tx queue can be used, let per queue offloading
+ * capability be same to per port queue offloading capability
+ * for better convenience.
+ */
+ tx_queue_offload_capa = em_get_tx_port_offloads_capa(dev);
+
+ return tx_queue_offload_capa;
+}
+
int
eth_em_tx_queue_setup(struct rte_eth_dev *dev,
uint16_t queue_idx,
struct e1000_hw *hw;
uint32_t tsize;
uint16_t tx_rs_thresh, tx_free_thresh;
+ uint64_t offloads;
hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+ offloads = tx_conf->offloads | dev->data->dev_conf.txmode.offloads;
+
/*
* Validate number of transmit descriptors.
* It must not exceed hardware maximum, and must be multiple
RTE_CACHE_LINE_SIZE)) == NULL)
return -ENOMEM;
+ txq->mz = tz;
/* Allocate software ring */
if ((txq->sw_ring = rte_zmalloc("txq->sw_ring",
sizeof(txq->sw_ring[0]) * nb_desc,
txq->port_id = dev->data->port_id;
txq->tdt_reg_addr = E1000_PCI_REG_ADDR(hw, E1000_TDT(queue_idx));
- txq->tx_ring_phys_addr = rte_mem_phy2mch(tz->memseg_id, tz->phys_addr);
+ txq->tx_ring_phys_addr = tz->iova;
txq->tx_ring = (struct e1000_data_desc *) tz->addr;
PMD_INIT_LOG(DEBUG, "sw_ring=%p hw_ring=%p dma_addr=0x%"PRIx64,
em_reset_tx_queue(txq);
dev->data->tx_queues[queue_idx] = txq;
+ txq->offloads = offloads;
return 0;
}
if (rxq != NULL) {
em_rx_queue_release_mbufs(rxq);
rte_free(rxq->sw_ring);
+ rte_memzone_free(rxq->mz);
rte_free(rxq);
}
}
void
-eth_em_rx_queue_release(void *rxq)
+eth_em_rx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
{
- em_rx_queue_release(rxq);
+ em_rx_queue_release(dev->data->rx_queues[qid]);
}
/* Reset dynamic em_rx_queue fields back to defaults */
rxq->pkt_last_seg = NULL;
}
+uint64_t
+em_get_rx_port_offloads_capa(void)
+{
+ uint64_t rx_offload_capa;
+
+ rx_offload_capa =
+ RTE_ETH_RX_OFFLOAD_VLAN_STRIP |
+ RTE_ETH_RX_OFFLOAD_VLAN_FILTER |
+ 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 rx_offload_capa;
+}
+
+uint64_t
+em_get_rx_queue_offloads_capa(void)
+{
+ uint64_t rx_queue_offload_capa;
+
+ /*
+ * As only one Rx queue can be used, let per queue offloading
+ * capability be same to per port queue offloading capability
+ * for better convenience.
+ */
+ rx_queue_offload_capa = em_get_rx_port_offloads_capa();
+
+ return rx_queue_offload_capa;
+}
+
int
eth_em_rx_queue_setup(struct rte_eth_dev *dev,
uint16_t queue_idx,
struct em_rx_queue *rxq;
struct e1000_hw *hw;
uint32_t rsize;
+ uint64_t offloads;
hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+ offloads = rx_conf->offloads | dev->data->dev_conf.rxmode.offloads;
+
/*
* Validate number of receive descriptors.
* It must not exceed hardware maximum, and must be multiple
}
/*
- * EM devices don't support drop_en functionality
+ * EM devices don't support drop_en functionality.
+ * It's an optimization that does nothing on single-queue devices,
+ * so just log the issue and carry on.
*/
if (rx_conf->rx_drop_en) {
- PMD_INIT_LOG(ERR, "drop_en functionality not supported by "
+ PMD_INIT_LOG(NOTICE, "drop_en functionality not supported by "
"device");
- return -EINVAL;
}
/* Free memory prior to re-allocation if needed. */
RTE_CACHE_LINE_SIZE)) == NULL)
return -ENOMEM;
+ rxq->mz = rz;
/* Allocate software ring. */
if ((rxq->sw_ring = rte_zmalloc("rxq->sw_ring",
sizeof (rxq->sw_ring[0]) * nb_desc,
rxq->rx_free_thresh = rx_conf->rx_free_thresh;
rxq->queue_id = 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);
+ 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->rdt_reg_addr = E1000_PCI_REG_ADDR(hw, E1000_RDT(queue_idx));
rxq->rdh_reg_addr = E1000_PCI_REG_ADDR(hw, E1000_RDH(queue_idx));
- rxq->rx_ring_phys_addr = rte_mem_phy2mch(rz->memseg_id, rz->phys_addr);
+ rxq->rx_ring_phys_addr = rz->iova;
rxq->rx_ring = (struct e1000_rx_desc *) rz->addr;
PMD_INIT_LOG(DEBUG, "sw_ring=%p hw_ring=%p dma_addr=0x%"PRIx64,
dev->data->rx_queues[queue_idx] = rxq;
em_reset_rx_queue(rxq);
+ rxq->offloads = offloads;
return 0;
}
uint32_t
-eth_em_rx_queue_count(struct rte_eth_dev *dev, uint16_t rx_queue_id)
+eth_em_rx_queue_count(void *rx_queue)
{
#define EM_RXQ_SCAN_INTERVAL 4
volatile struct e1000_rx_desc *rxdp;
struct em_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", rx_queue_id);
- return 0;
- }
-
- rxq = dev->data->rx_queues[rx_queue_id];
+ rxq = rx_queue;
rxdp = &(rxq->rx_ring[rxq->rx_tail]);
while ((desc < rxq->nb_rx_desc) &&
}
int
-eth_em_rx_descriptor_done(void *rx_queue, uint16_t offset)
+eth_em_rx_descriptor_status(void *rx_queue, uint16_t offset)
{
- volatile struct e1000_rx_desc *rxdp;
struct em_rx_queue *rxq = rx_queue;
+ volatile uint8_t *status;
uint32_t desc;
if (unlikely(offset >= rxq->nb_rx_desc))
- return 0;
+ return -EINVAL;
+
+ if (offset >= rxq->nb_rx_desc - rxq->nb_rx_hold)
+ return RTE_ETH_RX_DESC_UNAVAIL;
+
desc = rxq->rx_tail + offset;
if (desc >= rxq->nb_rx_desc)
desc -= rxq->nb_rx_desc;
- rxdp = &rxq->rx_ring[desc];
- return !!(rxdp->status & E1000_RXD_STAT_DD);
+ status = &rxq->rx_ring[desc].status;
+ if (*status & E1000_RXD_STAT_DD)
+ return RTE_ETH_RX_DESC_DONE;
+
+ return RTE_ETH_RX_DESC_AVAIL;
+}
+
+int
+eth_em_tx_descriptor_status(void *tx_queue, uint16_t offset)
+{
+ struct em_tx_queue *txq = tx_queue;
+ volatile uint8_t *status;
+ uint32_t desc;
+
+ if (unlikely(offset >= txq->nb_tx_desc))
+ return -EINVAL;
+
+ desc = txq->tx_tail + offset;
+ /* go to next desc that has the RS bit */
+ desc = ((desc + txq->tx_rs_thresh - 1) / txq->tx_rs_thresh) *
+ txq->tx_rs_thresh;
+ if (desc >= txq->nb_tx_desc) {
+ desc -= txq->nb_tx_desc;
+ if (desc >= txq->nb_tx_desc)
+ desc -= txq->nb_tx_desc;
+ }
+
+ status = &txq->tx_ring[desc].upper.fields.status;
+ if (*status & E1000_TXD_STAT_DD)
+ return RTE_ETH_TX_DESC_DONE;
+
+ return RTE_ETH_TX_DESC_FULL;
}
void
uint16_t i;
for (i = 0; i < dev->data->nb_rx_queues; i++) {
- eth_em_rx_queue_release(dev->data->rx_queues[i]);
+ eth_em_rx_queue_release(dev, i);
dev->data->rx_queues[i] = NULL;
}
dev->data->nb_rx_queues = 0;
for (i = 0; i < dev->data->nb_tx_queues; i++) {
- eth_em_tx_queue_release(dev->data->tx_queues[i]);
+ eth_em_tx_queue_release(dev, i);
dev->data->tx_queues[i] = NULL;
}
dev->data->nb_tx_queues = 0;
}
dma_addr =
- rte_cpu_to_le_64(rte_mbuf_data_dma_addr_default(mbuf));
+ rte_cpu_to_le_64(rte_mbuf_data_iova_default(mbuf));
/* Clear HW ring memory */
rxq->rx_ring[i] = rxd_init;
{
struct e1000_hw *hw;
struct em_rx_queue *rxq;
+ struct rte_eth_rxmode *rxmode;
uint32_t rctl;
uint32_t rfctl;
uint32_t rxcsum;
int ret;
hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+ rxmode = &dev->data->dev_conf.rxmode;
/*
* Make sure receives are disabled while setting
* 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);
+ 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;
bus_addr = rxq->rx_ring_phys_addr;
E1000_WRITE_REG(hw, E1000_RDLEN(i),
* to avoid splitting packets that don't fit into
* one buffer.
*/
- if (dev->data->dev_conf.rxmode.jumbo_frame ||
- rctl_bsize < ETHER_MAX_LEN) {
+ if (dev->data->mtu > RTE_ETHER_MTU ||
+ rctl_bsize < RTE_ETHER_MAX_LEN) {
if (!dev->data->scattered_rx)
PMD_INIT_LOG(DEBUG, "forcing scatter mode");
dev->rx_pkt_burst =
}
}
- if (dev->data->dev_conf.rxmode.enable_scatter) {
+ if (dev->data->dev_conf.rxmode.offloads & RTE_ETH_RX_OFFLOAD_SCATTER) {
if (!dev->data->scattered_rx)
PMD_INIT_LOG(DEBUG, "forcing scatter mode");
dev->rx_pkt_burst = eth_em_recv_scattered_pkts;
*/
rxcsum = E1000_READ_REG(hw, E1000_RXCSUM);
- if (dev->data->dev_conf.rxmode.hw_ip_checksum)
+ if (rxmode->offloads & RTE_ETH_RX_OFFLOAD_CHECKSUM)
rxcsum |= E1000_RXCSUM_IPOFL;
else
rxcsum &= ~E1000_RXCSUM_IPOFL;
if ((hw->mac.type == e1000_ich9lan ||
hw->mac.type == e1000_pch2lan ||
hw->mac.type == e1000_ich10lan) &&
- dev->data->dev_conf.rxmode.jumbo_frame == 1) {
+ dev->data->mtu > RTE_ETHER_MTU) {
u32 rxdctl = E1000_READ_REG(hw, E1000_RXDCTL(0));
E1000_WRITE_REG(hw, E1000_RXDCTL(0), rxdctl | 3);
E1000_WRITE_REG(hw, E1000_ERT, 0x100 | (1 << 13));
}
if (hw->mac.type == e1000_pch2lan) {
- if (dev->data->dev_conf.rxmode.jumbo_frame == 1)
+ if (dev->data->mtu > RTE_ETHER_MTU)
e1000_lv_jumbo_workaround_ich8lan(hw, TRUE);
else
e1000_lv_jumbo_workaround_ich8lan(hw, FALSE);
}
/* Setup the Receive Control Register. */
- if (dev->data->dev_conf.rxmode.hw_strip_crc)
- rctl |= E1000_RCTL_SECRC; /* Strip Ethernet CRC. */
- else
+ if (dev->data->dev_conf.rxmode.offloads & RTE_ETH_RX_OFFLOAD_KEEP_CRC)
rctl &= ~E1000_RCTL_SECRC; /* Do not Strip Ethernet CRC. */
+ else
+ rctl |= E1000_RCTL_SECRC; /* Strip Ethernet CRC. */
rctl &= ~(3 << E1000_RCTL_MO_SHIFT);
rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | E1000_RCTL_LBM_NO |
/*
* Configure support of jumbo frames, if any.
*/
- if (dev->data->dev_conf.rxmode.jumbo_frame == 1)
+ if (dev->data->mtu > RTE_ETHER_MTU)
rctl |= E1000_RCTL_LPE;
else
rctl &= ~E1000_RCTL_LPE;
tctl |= (E1000_TCTL_PSP | E1000_TCTL_RTLC | E1000_TCTL_EN |
(E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT));
+ /* SPT and CNP Si errata workaround to avoid data corruption */
+ if (hw->mac.type == e1000_pch_spt) {
+ uint32_t reg_val;
+ reg_val = E1000_READ_REG(hw, E1000_IOSFPC);
+ reg_val |= E1000_RCTL_RDMTS_HEX;
+ E1000_WRITE_REG(hw, E1000_IOSFPC, reg_val);
+
+ /* Dropping the number of outstanding requests from
+ * 3 to 2 in order to avoid a buffer overrun.
+ */
+ reg_val = E1000_READ_REG(hw, E1000_TARC(0));
+ reg_val &= ~E1000_TARC0_CB_MULTIQ_3_REQ;
+ reg_val |= E1000_TARC0_CB_MULTIQ_2_REQ;
+ E1000_WRITE_REG(hw, E1000_TARC(0), reg_val);
+ }
+
/* This write will effectively turn on the transmit unit. */
E1000_WRITE_REG(hw, E1000_TCTL, tctl);
}
qinfo->scattered_rx = dev->data->scattered_rx;
qinfo->nb_desc = rxq->nb_rx_desc;
qinfo->conf.rx_free_thresh = rxq->rx_free_thresh;
+ qinfo->conf.offloads = rxq->offloads;
}
void
qinfo->conf.tx_thresh.wthresh = txq->wthresh;
qinfo->conf.tx_free_thresh = txq->tx_free_thresh;
qinfo->conf.tx_rs_thresh = txq->tx_rs_thresh;
+ qinfo->conf.offloads = txq->offloads;
+}
+
+static void
+e1000_flush_tx_ring(struct rte_eth_dev *dev)
+{
+ struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+ volatile struct e1000_data_desc *tx_desc;
+ volatile uint32_t *tdt_reg_addr;
+ uint32_t tdt, tctl, txd_lower = E1000_TXD_CMD_IFCS;
+ uint16_t size = 512;
+ struct em_tx_queue *txq;
+ int i;
+
+ if (dev->data->tx_queues == NULL)
+ return;
+ tctl = E1000_READ_REG(hw, E1000_TCTL);
+ E1000_WRITE_REG(hw, E1000_TCTL, tctl | E1000_TCTL_EN);
+ for (i = 0; i < dev->data->nb_tx_queues &&
+ i < E1000_I219_MAX_TX_QUEUE_NUM; i++) {
+ txq = dev->data->tx_queues[i];
+ tdt = E1000_READ_REG(hw, E1000_TDT(i));
+ if (tdt != txq->tx_tail)
+ return;
+ tx_desc = &txq->tx_ring[txq->tx_tail];
+ tx_desc->buffer_addr = rte_cpu_to_le_64(txq->tx_ring_phys_addr);
+ tx_desc->lower.data = rte_cpu_to_le_32(txd_lower | size);
+ tx_desc->upper.data = 0;
+
+ rte_io_wmb();
+ txq->tx_tail++;
+ if (txq->tx_tail == txq->nb_tx_desc)
+ txq->tx_tail = 0;
+ tdt_reg_addr = E1000_PCI_REG_ADDR(hw, E1000_TDT(i));
+ E1000_PCI_REG_WRITE(tdt_reg_addr, txq->tx_tail);
+ usec_delay(250);
+ }
+}
+
+static void
+e1000_flush_rx_ring(struct rte_eth_dev *dev)
+{
+ uint32_t rctl, rxdctl;
+ struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+ int i;
+
+ rctl = E1000_READ_REG(hw, E1000_RCTL);
+ E1000_WRITE_REG(hw, E1000_RCTL, rctl & ~E1000_RCTL_EN);
+ E1000_WRITE_FLUSH(hw);
+ usec_delay(150);
+
+ for (i = 0; i < dev->data->nb_rx_queues &&
+ i < E1000_I219_MAX_RX_QUEUE_NUM; i++) {
+ rxdctl = E1000_READ_REG(hw, E1000_RXDCTL(i));
+ /* zero the lower 14 bits (prefetch and host thresholds) */
+ rxdctl &= 0xffffc000;
+
+ /* update thresholds: prefetch threshold to 31,
+ * host threshold to 1 and make sure the granularity
+ * is "descriptors" and not "cache lines"
+ */
+ rxdctl |= (0x1F | (1UL << 8) | E1000_RXDCTL_THRESH_UNIT_DESC);
+
+ E1000_WRITE_REG(hw, E1000_RXDCTL(i), rxdctl);
+ }
+ /* momentarily enable the RX ring for the changes to take effect */
+ E1000_WRITE_REG(hw, E1000_RCTL, rctl | E1000_RCTL_EN);
+ E1000_WRITE_FLUSH(hw);
+ usec_delay(150);
+ E1000_WRITE_REG(hw, E1000_RCTL, rctl & ~E1000_RCTL_EN);
+}
+
+/**
+ * em_flush_desc_rings - remove all descriptors from the descriptor rings
+ *
+ * In i219, the descriptor rings must be emptied before resetting/closing the
+ * HW. Failure to do this will cause the HW to enter a unit hang state which
+ * can only be released by PCI reset on the device
+ *
+ */
+
+void
+em_flush_desc_rings(struct rte_eth_dev *dev)
+{
+ uint32_t fextnvm11, tdlen;
+ struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+ struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
+ uint16_t pci_cfg_status = 0;
+ int ret;
+
+ fextnvm11 = E1000_READ_REG(hw, E1000_FEXTNVM11);
+ E1000_WRITE_REG(hw, E1000_FEXTNVM11,
+ fextnvm11 | E1000_FEXTNVM11_DISABLE_MULR_FIX);
+ tdlen = E1000_READ_REG(hw, E1000_TDLEN(0));
+ ret = rte_pci_read_config(pci_dev, &pci_cfg_status,
+ sizeof(pci_cfg_status), PCI_CFG_STATUS_REG);
+ if (ret < 0) {
+ PMD_DRV_LOG(ERR, "Failed to read PCI offset 0x%x",
+ PCI_CFG_STATUS_REG);
+ return;
+ }
+
+ /* do nothing if we're not in faulty state, or if the queue is empty */
+ if ((pci_cfg_status & FLUSH_DESC_REQUIRED) && tdlen) {
+ /* flush desc ring */
+ e1000_flush_tx_ring(dev);
+ ret = rte_pci_read_config(pci_dev, &pci_cfg_status,
+ sizeof(pci_cfg_status), PCI_CFG_STATUS_REG);
+ if (ret < 0) {
+ PMD_DRV_LOG(ERR, "Failed to read PCI offset 0x%x",
+ PCI_CFG_STATUS_REG);
+ return;
+ }
+
+ if (pci_cfg_status & FLUSH_DESC_REQUIRED)
+ e1000_flush_rx_ring(dev);
+ }
}