X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvmxnet3%2Fvmxnet3_ethdev.c;h=3ad1e9e0933d209acd0102e6b706a25d0a4446ac;hb=6d13ea8e8e49ab957deae2bba5ecf4a4bfe747d1;hp=ca6a89d9d8d583c3dfb3247f5a1ea1f7a16a5bd1;hpb=1089b5066da13113a68ab714bce6052088cbbdc1;p=dpdk.git diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c b/drivers/net/vmxnet3/vmxnet3_ethdev.c index ca6a89d9d8..3ad1e9e093 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethdev.c +++ b/drivers/net/vmxnet3/vmxnet3_ethdev.c @@ -1,34 +1,5 @@ -/*- - * 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) 2010-2015 Intel Corporation */ #include @@ -48,15 +19,15 @@ #include #include #include -#include +#include #include #include #include #include #include #include -#include -#include +#include +#include #include #include #include @@ -69,6 +40,26 @@ #define PROCESS_SYS_EVENTS 0 +#define VMXNET3_TX_MAX_SEG UINT8_MAX + +#define VMXNET3_TX_OFFLOAD_CAP \ + (DEV_TX_OFFLOAD_VLAN_INSERT | \ + DEV_TX_OFFLOAD_IPV4_CKSUM | \ + DEV_TX_OFFLOAD_TCP_CKSUM | \ + DEV_TX_OFFLOAD_UDP_CKSUM | \ + DEV_TX_OFFLOAD_TCP_TSO | \ + DEV_TX_OFFLOAD_MULTI_SEGS) + +#define VMXNET3_RX_OFFLOAD_CAP \ + (DEV_RX_OFFLOAD_VLAN_STRIP | \ + DEV_RX_OFFLOAD_VLAN_FILTER | \ + DEV_RX_OFFLOAD_SCATTER | \ + DEV_RX_OFFLOAD_IPV4_CKSUM | \ + DEV_RX_OFFLOAD_UDP_CKSUM | \ + DEV_RX_OFFLOAD_TCP_CKSUM | \ + DEV_RX_OFFLOAD_TCP_LRO | \ + DEV_RX_OFFLOAD_JUMBO_FRAME) + static int eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev); static int eth_vmxnet3_dev_uninit(struct rte_eth_dev *eth_dev); static int vmxnet3_dev_configure(struct rte_eth_dev *dev); @@ -80,30 +71,41 @@ static void vmxnet3_dev_promiscuous_enable(struct rte_eth_dev *dev); static void vmxnet3_dev_promiscuous_disable(struct rte_eth_dev *dev); static void vmxnet3_dev_allmulticast_enable(struct rte_eth_dev *dev); static void vmxnet3_dev_allmulticast_disable(struct rte_eth_dev *dev); +static int __vmxnet3_dev_link_update(struct rte_eth_dev *dev, + int wait_to_complete); static int vmxnet3_dev_link_update(struct rte_eth_dev *dev, - int wait_to_complete); -static void vmxnet3_dev_stats_get(struct rte_eth_dev *dev, - struct rte_eth_stats *stats); + int wait_to_complete); +static void vmxnet3_hw_stats_save(struct vmxnet3_hw *hw); +static int vmxnet3_dev_stats_get(struct rte_eth_dev *dev, + struct rte_eth_stats *stats); +static void vmxnet3_dev_stats_reset(struct rte_eth_dev *dev); +static int vmxnet3_dev_xstats_get_names(struct rte_eth_dev *dev, + struct rte_eth_xstat_name *xstats, + unsigned int n); +static int vmxnet3_dev_xstats_get(struct rte_eth_dev *dev, + struct rte_eth_xstat *xstats, unsigned int n); static void vmxnet3_dev_info_get(struct rte_eth_dev *dev, - struct rte_eth_dev_info *dev_info); + struct rte_eth_dev_info *dev_info); +static const uint32_t * +vmxnet3_dev_supported_ptypes_get(struct rte_eth_dev *dev); static int vmxnet3_dev_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vid, int on); -static void vmxnet3_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask); -static void vmxnet3_dev_vlan_offload_set_clear(struct rte_eth_dev *dev, - int mask, int clear); +static int vmxnet3_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask); +static int vmxnet3_mac_addr_set(struct rte_eth_dev *dev, + struct rte_ether_addr *mac_addr); +static void vmxnet3_interrupt_handler(void *param); + +int vmxnet3_logtype_init; +int vmxnet3_logtype_driver; -#if PROCESS_SYS_EVENTS == 1 -static void vmxnet3_process_events(struct vmxnet3_hw *); -#endif /* * The set of PCI devices this driver supports */ +#define VMWARE_PCI_VENDOR_ID 0x15AD +#define VMWARE_DEV_ID_VMXNET3 0x07B0 static const struct rte_pci_id pci_id_vmxnet3_map[] = { - -#define RTE_PCI_DEV_ID_DECL_VMXNET3(vend, dev) {RTE_PCI_DEVICE(vend, dev)}, -#include "rte_pci_dev_ids.h" - -{ .vendor_id = 0, /* sentinel */ }, + { RTE_PCI_DEVICE(VMWARE_PCI_VENDOR_ID, VMWARE_DEV_ID_VMXNET3) }, + { .vendor_id = 0, /* sentinel */ }, }; static const struct eth_dev_ops vmxnet3_eth_dev_ops = { @@ -117,7 +119,12 @@ static const struct eth_dev_ops vmxnet3_eth_dev_ops = { .allmulticast_disable = vmxnet3_dev_allmulticast_disable, .link_update = vmxnet3_dev_link_update, .stats_get = vmxnet3_dev_stats_get, + .xstats_get_names = vmxnet3_dev_xstats_get_names, + .xstats_get = vmxnet3_dev_xstats_get, + .stats_reset = vmxnet3_dev_stats_reset, + .mac_addr_set = vmxnet3_mac_addr_set, .dev_infos_get = vmxnet3_dev_info_get, + .dev_supported_ptypes_get = vmxnet3_dev_supported_ptypes_get, .vlan_filter_set = vmxnet3_dev_vlan_filter_set, .vlan_offload_set = vmxnet3_dev_vlan_offload_set, .rx_queue_setup = vmxnet3_dev_rx_queue_setup, @@ -126,90 +133,96 @@ static const struct eth_dev_ops vmxnet3_eth_dev_ops = { .tx_queue_release = vmxnet3_dev_tx_queue_release, }; +struct vmxnet3_xstats_name_off { + char name[RTE_ETH_XSTATS_NAME_SIZE]; + unsigned int offset; +}; + +/* tx_qX_ is prepended to the name string here */ +static const struct vmxnet3_xstats_name_off vmxnet3_txq_stat_strings[] = { + {"drop_total", offsetof(struct vmxnet3_txq_stats, drop_total)}, + {"drop_too_many_segs", offsetof(struct vmxnet3_txq_stats, drop_too_many_segs)}, + {"drop_tso", offsetof(struct vmxnet3_txq_stats, drop_tso)}, + {"tx_ring_full", offsetof(struct vmxnet3_txq_stats, tx_ring_full)}, +}; + +/* rx_qX_ is prepended to the name string here */ +static const struct vmxnet3_xstats_name_off vmxnet3_rxq_stat_strings[] = { + {"drop_total", offsetof(struct vmxnet3_rxq_stats, drop_total)}, + {"drop_err", offsetof(struct vmxnet3_rxq_stats, drop_err)}, + {"drop_fcs", offsetof(struct vmxnet3_rxq_stats, drop_fcs)}, + {"rx_buf_alloc_failure", offsetof(struct vmxnet3_rxq_stats, rx_buf_alloc_failure)}, +}; + static const struct rte_memzone * gpa_zone_reserve(struct rte_eth_dev *dev, uint32_t size, - const char *post_string, int socket_id, uint16_t align) + const char *post_string, int socket_id, + uint16_t align, bool reuse) { char z_name[RTE_MEMZONE_NAMESIZE]; const struct rte_memzone *mz; - snprintf(z_name, sizeof(z_name), "%s_%d_%s", - dev->driver->pci_drv.name, dev->data->port_id, post_string); + snprintf(z_name, sizeof(z_name), "eth_p%d_%s", + dev->data->port_id, post_string); mz = rte_memzone_lookup(z_name); + if (!reuse) { + if (mz) + rte_memzone_free(mz); + return rte_memzone_reserve_aligned(z_name, size, socket_id, + RTE_MEMZONE_IOVA_CONTIG, align); + } + if (mz) return mz; - return rte_memzone_reserve_aligned(z_name, size, - socket_id, 0, align); -} - -/** - * Atomically reads the link status information from global - * structure rte_eth_dev. - * - * @param dev - * - Pointer to the structure rte_eth_dev to read from. - * - Pointer to the buffer to be saved with the link status. - * - * @return - * - On success, zero. - * - On failure, negative value. - */ + return rte_memzone_reserve_aligned(z_name, size, socket_id, + RTE_MEMZONE_IOVA_CONTIG, align); +} -static int -vmxnet3_dev_atomic_read_link_status(struct rte_eth_dev *dev, - struct rte_eth_link *link) +/* + * This function is based on vmxnet3_disable_intr() + */ +static void +vmxnet3_disable_intr(struct vmxnet3_hw *hw) { - struct rte_eth_link *dst = link; - struct rte_eth_link *src = &(dev->data->dev_link); + int i; - if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst, - *(uint64_t *)src) == 0) - return -1; + PMD_INIT_FUNC_TRACE(); - return 0; + hw->shared->devRead.intrConf.intrCtrl |= VMXNET3_IC_DISABLE_ALL; + for (i = 0; i < hw->num_intrs; i++) + VMXNET3_WRITE_BAR0_REG(hw, VMXNET3_REG_IMR + i * 8, 1); } -/** - * Atomically writes the link status information into global - * structure rte_eth_dev. - * - * @param dev - * - Pointer to the structure rte_eth_dev to write to. - * - Pointer to the buffer to be saved with the link status. - * - * @return - * - On success, zero. - * - On failure, negative value. - */ -static int -vmxnet3_dev_atomic_write_link_status(struct rte_eth_dev *dev, - struct rte_eth_link *link) +static void +vmxnet3_enable_intr(struct vmxnet3_hw *hw) { - struct rte_eth_link *dst = &(dev->data->dev_link); - struct rte_eth_link *src = link; + int i; - if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst, - *(uint64_t *)src) == 0) - return -1; + PMD_INIT_FUNC_TRACE(); - return 0; + hw->shared->devRead.intrConf.intrCtrl &= ~VMXNET3_IC_DISABLE_ALL; + for (i = 0; i < hw->num_intrs; i++) + VMXNET3_WRITE_BAR0_REG(hw, VMXNET3_REG_IMR + i * 8, 0); } /* - * This function is based on vmxnet3_disable_intr() + * Gets tx data ring descriptor size. */ -static void -vmxnet3_disable_intr(struct vmxnet3_hw *hw) +static uint16_t +eth_vmxnet3_txdata_get(struct vmxnet3_hw *hw) { - int i; + uint16 txdata_desc_size; - PMD_INIT_FUNC_TRACE(); + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_TXDATA_DESC_SIZE); + txdata_desc_size = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_CMD); - hw->shared->devRead.intrConf.intrCtrl |= VMXNET3_IC_DISABLE_ALL; - for (i = 0; i < VMXNET3_MAX_INTRS; i++) - VMXNET3_WRITE_BAR0_REG(hw, VMXNET3_REG_IMR + i * 8, 1); + return (txdata_desc_size < VMXNET3_TXDATA_DESC_MIN_SIZE || + txdata_desc_size > VMXNET3_TXDATA_DESC_MAX_SIZE || + txdata_desc_size & VMXNET3_TXDATA_DESC_SIZE_MASK) ? + sizeof(struct Vmxnet3_TxDataDesc) : txdata_desc_size; } /* @@ -221,13 +234,15 @@ eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev) struct rte_pci_device *pci_dev; struct vmxnet3_hw *hw = eth_dev->data->dev_private; uint32_t mac_hi, mac_lo, ver; + struct rte_eth_link link; PMD_INIT_FUNC_TRACE(); eth_dev->dev_ops = &vmxnet3_eth_dev_ops; eth_dev->rx_pkt_burst = &vmxnet3_recv_pkts; eth_dev->tx_pkt_burst = &vmxnet3_xmit_pkts; - pci_dev = eth_dev->pci_dev; + eth_dev->tx_pkt_prepare = vmxnet3_prep_pkts; + pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev); /* * for secondary processes, we don't initialize any further as primary @@ -251,13 +266,30 @@ eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev) /* Check h/w version compatibility with driver. */ ver = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_VRRS); PMD_INIT_LOG(DEBUG, "Hardware version : %d", ver); - if (ver & 0x1) - VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_VRRS, 1); - else { - PMD_INIT_LOG(ERR, "Incompatible h/w version, should be 0x1"); + + if (ver & (1 << VMXNET3_REV_4)) { + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_4); + hw->version = VMXNET3_REV_4 + 1; + } else if (ver & (1 << VMXNET3_REV_3)) { + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_3); + hw->version = VMXNET3_REV_3 + 1; + } else if (ver & (1 << VMXNET3_REV_2)) { + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_2); + hw->version = VMXNET3_REV_2 + 1; + } else if (ver & (1 << VMXNET3_REV_1)) { + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_1); + hw->version = VMXNET3_REV_1 + 1; + } else { + PMD_INIT_LOG(ERR, "Incompatible hardware version: %d", ver); return -EIO; } + PMD_INIT_LOG(DEBUG, "Using device version %d\n", hw->version); + /* Check UPT version compatibility with driver. */ ver = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_UVRS); PMD_INIT_LOG(DEBUG, "UPT hardware version : %d", ver); @@ -271,8 +303,8 @@ eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev) /* Getting MAC Address */ mac_lo = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_MACL); mac_hi = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_MACH); - memcpy(hw->perm_addr , &mac_lo, 4); - memcpy(hw->perm_addr+4, &mac_hi, 2); + memcpy(hw->perm_addr, &mac_lo, 4); + memcpy(hw->perm_addr + 4, &mac_hi, 2); /* Allocate memory for storing MAC addresses */ eth_dev->data->mac_addrs = rte_zmalloc("vmxnet3", ETHER_ADDR_LEN * @@ -284,16 +316,45 @@ eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev) return -ENOMEM; } /* Copy the permanent MAC address */ - ether_addr_copy((struct ether_addr *) hw->perm_addr, + ether_addr_copy((struct rte_ether_addr *)hw->perm_addr, ð_dev->data->mac_addrs[0]); PMD_INIT_LOG(DEBUG, "MAC Address : %02x:%02x:%02x:%02x:%02x:%02x", hw->perm_addr[0], hw->perm_addr[1], hw->perm_addr[2], hw->perm_addr[3], hw->perm_addr[4], hw->perm_addr[5]); + /* Flag to call rte_eth_dev_release_port() in rte_eth_dev_close(). */ + eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE; + /* Put device in Quiesce Mode */ VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_QUIESCE_DEV); + /* allow untagged pkts */ + VMXNET3_SET_VFTABLE_ENTRY(hw->shadow_vfta, 0); + + hw->txdata_desc_size = VMXNET3_VERSION_GE_3(hw) ? + eth_vmxnet3_txdata_get(hw) : sizeof(struct Vmxnet3_TxDataDesc); + + hw->rxdata_desc_size = VMXNET3_VERSION_GE_3(hw) ? + VMXNET3_DEF_RXDATA_DESC_SIZE : 0; + RTE_ASSERT((hw->rxdata_desc_size & ~VMXNET3_RXDATA_DESC_SIZE_MASK) == + hw->rxdata_desc_size); + + /* clear shadow stats */ + memset(hw->saved_tx_stats, 0, sizeof(hw->saved_tx_stats)); + memset(hw->saved_rx_stats, 0, sizeof(hw->saved_rx_stats)); + + /* clear snapshot stats */ + memset(hw->snapshot_tx_stats, 0, sizeof(hw->snapshot_tx_stats)); + memset(hw->snapshot_rx_stats, 0, sizeof(hw->snapshot_rx_stats)); + + /* set the initial link status */ + memset(&link, 0, sizeof(link)); + link.link_duplex = ETH_LINK_FULL_DUPLEX; + link.link_speed = ETH_SPEED_NUM_10G; + link.link_autoneg = ETH_LINK_FIXED; + rte_eth_linkstatus_set(eth_dev, &link); + return 0; } @@ -307,44 +368,38 @@ eth_vmxnet3_dev_uninit(struct rte_eth_dev *eth_dev) if (rte_eal_process_type() != RTE_PROC_PRIMARY) return 0; - if (hw->adapter_stopped == 0) - vmxnet3_dev_close(eth_dev); + if (hw->adapter_stopped == 0) { + PMD_INIT_LOG(DEBUG, "Device has not been closed."); + return -EBUSY; + } eth_dev->dev_ops = NULL; eth_dev->rx_pkt_burst = NULL; eth_dev->tx_pkt_burst = NULL; - - rte_free(eth_dev->data->mac_addrs); - eth_dev->data->mac_addrs = NULL; + eth_dev->tx_pkt_prepare = NULL; return 0; } -static struct eth_driver rte_vmxnet3_pmd = { - .pci_drv = { - .name = "rte_vmxnet3_pmd", - .id_table = pci_id_vmxnet3_map, - .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_DETACHABLE, - }, - .eth_dev_init = eth_vmxnet3_dev_init, - .eth_dev_uninit = eth_vmxnet3_dev_uninit, - .dev_private_size = sizeof(struct vmxnet3_hw), -}; - -/* - * Driver initialization routine. - * Invoked once at EAL init time. - * Register itself as the [Poll Mode] Driver of Virtual PCI VMXNET3 devices. - */ -static int -rte_vmxnet3_pmd_init(const char *name __rte_unused, const char *param __rte_unused) +static int eth_vmxnet3_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, + struct rte_pci_device *pci_dev) { - PMD_INIT_FUNC_TRACE(); + return rte_eth_dev_pci_generic_probe(pci_dev, + sizeof(struct vmxnet3_hw), eth_vmxnet3_dev_init); +} - rte_eth_driver_register(&rte_vmxnet3_pmd); - return 0; +static int eth_vmxnet3_pci_remove(struct rte_pci_device *pci_dev) +{ + return rte_eth_dev_pci_generic_remove(pci_dev, eth_vmxnet3_dev_uninit); } +static struct rte_pci_driver rte_vmxnet3_pmd = { + .id_table = pci_id_vmxnet3_map, + .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC, + .probe = eth_vmxnet3_pci_probe, + .remove = eth_vmxnet3_pci_remove, +}; + static int vmxnet3_dev_configure(struct rte_eth_dev *dev) { @@ -354,9 +409,16 @@ vmxnet3_dev_configure(struct rte_eth_dev *dev) PMD_INIT_FUNC_TRACE(); - if (dev->data->nb_rx_queues > UINT8_MAX || - dev->data->nb_tx_queues > UINT8_MAX) + if (dev->data->nb_tx_queues > VMXNET3_MAX_TX_QUEUES || + dev->data->nb_rx_queues > VMXNET3_MAX_RX_QUEUES) { + PMD_INIT_LOG(ERR, "ERROR: Number of queues not supported"); return -EINVAL; + } + + if (!rte_is_power_of_2(dev->data->nb_rx_queues)) { + PMD_INIT_LOG(ERR, "ERROR: Number of rx queues not power of 2"); + return -EINVAL; + } size = dev->data->nb_rx_queues * sizeof(struct Vmxnet3_TxQueueDesc) + dev->data->nb_tx_queues * sizeof(struct Vmxnet3_RxQueueDesc); @@ -372,7 +434,7 @@ vmxnet3_dev_configure(struct rte_eth_dev *dev) * on current socket */ mz = gpa_zone_reserve(dev, sizeof(struct Vmxnet3_DriverShared), - "shared", rte_socket_id(), 8); + "shared", rte_socket_id(), 8, 1); if (mz == NULL) { PMD_INIT_LOG(ERR, "ERROR: Creating shared zone"); @@ -381,14 +443,18 @@ vmxnet3_dev_configure(struct rte_eth_dev *dev) memset(mz->addr, 0, mz->len); hw->shared = mz->addr; - hw->sharedPA = mz->phys_addr; + hw->sharedPA = mz->iova; /* * Allocate a memzone for Vmxnet3_RxQueueDesc - Vmxnet3_TxQueueDesc - * on current socket + * on current socket. + * + * We cannot reuse this memzone from previous allocation as its size + * depends on the number of tx and rx queues, which could be different + * from one config to another. */ - mz = gpa_zone_reserve(dev, size, "queuedesc", - rte_socket_id(), VMXNET3_QUEUE_DESC_ALIGN); + mz = gpa_zone_reserve(dev, size, "queuedesc", rte_socket_id(), + VMXNET3_QUEUE_DESC_ALIGN, 0); if (mz == NULL) { PMD_INIT_LOG(ERR, "ERROR: Creating queue descriptors zone"); return -ENOMEM; @@ -398,14 +464,14 @@ vmxnet3_dev_configure(struct rte_eth_dev *dev) hw->tqd_start = (Vmxnet3_TxQueueDesc *)mz->addr; hw->rqd_start = (Vmxnet3_RxQueueDesc *)(hw->tqd_start + hw->num_tx_queues); - hw->queueDescPA = mz->phys_addr; + hw->queueDescPA = mz->iova; hw->queue_desc_len = (uint16_t)size; if (dev->data->dev_conf.rxmode.mq_mode == ETH_MQ_RX_RSS) { - /* Allocate memory structure for UPT1_RSSConf and configure */ - mz = gpa_zone_reserve(dev, sizeof(struct VMXNET3_RSSConf), "rss_conf", - rte_socket_id(), RTE_CACHE_LINE_SIZE); + mz = gpa_zone_reserve(dev, sizeof(struct VMXNET3_RSSConf), + "rss_conf", rte_socket_id(), + RTE_CACHE_LINE_SIZE, 1); if (mz == NULL) { PMD_INIT_LOG(ERR, "ERROR: Creating rss_conf structure zone"); @@ -414,35 +480,140 @@ vmxnet3_dev_configure(struct rte_eth_dev *dev) memset(mz->addr, 0, mz->len); hw->rss_conf = mz->addr; - hw->rss_confPA = mz->phys_addr; + hw->rss_confPA = mz->iova; } return 0; } +static void +vmxnet3_write_mac(struct vmxnet3_hw *hw, const uint8_t *addr) +{ + uint32_t val; + + PMD_INIT_LOG(DEBUG, + "Writing MAC Address : %02x:%02x:%02x:%02x:%02x:%02x", + addr[0], addr[1], addr[2], + addr[3], addr[4], addr[5]); + + memcpy(&val, addr, 4); + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_MACL, val); + + memcpy(&val, addr + 4, 2); + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_MACH, val); +} + +static int +vmxnet3_dev_setup_memreg(struct rte_eth_dev *dev) +{ + struct vmxnet3_hw *hw = dev->data->dev_private; + Vmxnet3_DriverShared *shared = hw->shared; + Vmxnet3_CmdInfo *cmdInfo; + struct rte_mempool *mp[VMXNET3_MAX_RX_QUEUES]; + uint8_t index[VMXNET3_MAX_RX_QUEUES + VMXNET3_MAX_TX_QUEUES]; + uint32_t num, i, j, size; + + if (hw->memRegsPA == 0) { + const struct rte_memzone *mz; + + size = sizeof(Vmxnet3_MemRegs) + + (VMXNET3_MAX_RX_QUEUES + VMXNET3_MAX_TX_QUEUES) * + sizeof(Vmxnet3_MemoryRegion); + + mz = gpa_zone_reserve(dev, size, "memRegs", rte_socket_id(), 8, + 1); + if (mz == NULL) { + PMD_INIT_LOG(ERR, "ERROR: Creating memRegs zone"); + return -ENOMEM; + } + memset(mz->addr, 0, mz->len); + hw->memRegs = mz->addr; + hw->memRegsPA = mz->iova; + } + + num = hw->num_rx_queues; + + for (i = 0; i < num; i++) { + vmxnet3_rx_queue_t *rxq = dev->data->rx_queues[i]; + + mp[i] = rxq->mp; + index[i] = 1 << i; + } + + /* + * The same mempool could be used by multiple queues. In such a case, + * remove duplicate mempool entries. Only one entry is kept with + * bitmask indicating queues that are using this mempool. + */ + for (i = 1; i < num; i++) { + for (j = 0; j < i; j++) { + if (mp[i] == mp[j]) { + mp[i] = NULL; + index[j] |= 1 << i; + break; + } + } + } + + j = 0; + for (i = 0; i < num; i++) { + if (mp[i] == NULL) + continue; + + Vmxnet3_MemoryRegion *mr = &hw->memRegs->memRegs[j]; + + mr->startPA = + (uintptr_t)STAILQ_FIRST(&mp[i]->mem_list)->iova; + mr->length = STAILQ_FIRST(&mp[i]->mem_list)->len <= INT32_MAX ? + STAILQ_FIRST(&mp[i]->mem_list)->len : INT32_MAX; + mr->txQueueBits = index[i]; + mr->rxQueueBits = index[i]; + + PMD_INIT_LOG(INFO, + "index: %u startPA: %" PRIu64 " length: %u, " + "rxBits: %x", + j, mr->startPA, mr->length, mr->rxQueueBits); + j++; + } + hw->memRegs->numRegs = j; + PMD_INIT_LOG(INFO, "numRegs: %u", j); + + size = sizeof(Vmxnet3_MemRegs) + + (j - 1) * sizeof(Vmxnet3_MemoryRegion); + + cmdInfo = &shared->cu.cmdInfo; + cmdInfo->varConf.confVer = 1; + cmdInfo->varConf.confLen = size; + cmdInfo->varConf.confPA = hw->memRegsPA; + + return 0; +} + static int vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) { struct rte_eth_conf port_conf = dev->data->dev_conf; struct vmxnet3_hw *hw = dev->data->dev_private; + uint32_t mtu = dev->data->mtu; Vmxnet3_DriverShared *shared = hw->shared; Vmxnet3_DSDevRead *devRead = &shared->devRead; - uint32_t *mac_ptr; - uint32_t val, i; - int ret, mask; + uint64_t rx_offloads = dev->data->dev_conf.rxmode.offloads; + uint32_t i; + int ret; + + hw->mtu = mtu; shared->magic = VMXNET3_REV1_MAGIC; devRead->misc.driverInfo.version = VMXNET3_DRIVER_VERSION_NUM; /* Setting up Guest OS information */ devRead->misc.driverInfo.gos.gosBits = sizeof(void *) == 4 ? - VMXNET3_GOS_BITS_32 : - VMXNET3_GOS_BITS_64; + VMXNET3_GOS_BITS_32 : VMXNET3_GOS_BITS_64; devRead->misc.driverInfo.gos.gosType = VMXNET3_GOS_TYPE_LINUX; devRead->misc.driverInfo.vmxnet3RevSpt = 1; devRead->misc.driverInfo.uptVerSpt = 1; - devRead->misc.mtu = rte_le_to_cpu_32(dev->data->mtu); + devRead->misc.mtu = rte_le_to_cpu_32(mtu); devRead->misc.queueDescPA = hw->queueDescPA; devRead->misc.queueDescLen = hw->queue_desc_len; devRead->misc.numTxQueues = hw->num_tx_queues; @@ -450,17 +621,19 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) /* * Set number of interrupts to 1 - * PMD disables all the interrupts but this is MUST to activate device - * It needs at least one interrupt for link events to handle - * So we'll disable it later after device activation if needed + * PMD by default disables all the interrupts but this is MUST + * to activate device. It needs at least one interrupt for + * link events to handle */ - devRead->intrConf.numIntrs = 1; + hw->num_intrs = devRead->intrConf.numIntrs = 1; devRead->intrConf.intrCtrl |= VMXNET3_IC_DISABLE_ALL; for (i = 0; i < hw->num_tx_queues; i++) { Vmxnet3_TxQueueDesc *tqd = &hw->tqd_start[i]; vmxnet3_tx_queue_t *txq = dev->data->tx_queues[i]; + txq->shared = &hw->tqd_start[i]; + tqd->ctrl.txNumDeferred = 0; tqd->ctrl.txThreshold = 1; tqd->conf.txRingBasePA = txq->cmd_ring.basePA; @@ -470,6 +643,7 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) tqd->conf.txRingSize = txq->cmd_ring.size; tqd->conf.compRingSize = txq->comp_ring.size; tqd->conf.dataRingSize = txq->data_ring.size; + tqd->conf.txDataRingDescSize = txq->txdata_desc_size; tqd->conf.intrIdx = txq->comp_ring.intr_idx; tqd->status.stopped = TRUE; tqd->status.error = 0; @@ -480,6 +654,8 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) Vmxnet3_RxQueueDesc *rqd = &hw->rqd_start[i]; vmxnet3_rx_queue_t *rxq = dev->data->rx_queues[i]; + rxq->shared = &hw->rqd_start[i]; + rqd->conf.rxRingBasePA[0] = rxq->cmd_ring[0].basePA; rqd->conf.rxRingBasePA[1] = rxq->cmd_ring[1].basePA; rqd->conf.compRingBasePA = rxq->comp_ring.basePA; @@ -488,6 +664,10 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) rqd->conf.rxRingSize[1] = rxq->cmd_ring[1].size; rqd->conf.compRingSize = rxq->comp_ring.size; rqd->conf.intrIdx = rxq->comp_ring.intr_idx; + if (VMXNET3_VERSION_GE_3(hw)) { + rqd->conf.rxDataRingBasePA = rxq->data_ring.basePA; + rqd->conf.rxDataRingDescSize = rxq->data_desc_size; + } rqd->status.stopped = TRUE; rqd->status.error = 0; memset(&rqd->stats, 0, sizeof(rqd->stats)); @@ -497,9 +677,14 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) devRead->rxFilterConf.rxMode = 0; /* Setting up feature flags */ - if (dev->data->dev_conf.rxmode.hw_ip_checksum) + if (rx_offloads & DEV_RX_OFFLOAD_CHECKSUM) devRead->misc.uptFeatures |= VMXNET3_F_RXCSUM; + if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO) { + devRead->misc.uptFeatures |= VMXNET3_F_LRO; + devRead->misc.maxNumRxSG = 0; + } + if (port_conf.rxmode.mq_mode == ETH_MQ_RX_RSS) { ret = vmxnet3_rss_configure(dev); if (ret != VMXNET3_SUCCESS) @@ -511,27 +696,12 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) devRead->rssConfDesc.confPA = hw->rss_confPA; } - mask = 0; - if (dev->data->dev_conf.rxmode.hw_vlan_strip) - mask |= ETH_VLAN_STRIP_MASK; - - if (dev->data->dev_conf.rxmode.hw_vlan_filter) - mask |= ETH_VLAN_FILTER_MASK; - - vmxnet3_dev_vlan_offload_set_clear(dev, mask, 1); - - PMD_INIT_LOG(DEBUG, - "Writing MAC Address : %02x:%02x:%02x:%02x:%02x:%02x", - hw->perm_addr[0], hw->perm_addr[1], hw->perm_addr[2], - hw->perm_addr[3], hw->perm_addr[4], hw->perm_addr[5]); - - /* Write MAC Address back to device */ - mac_ptr = (uint32_t *)hw->perm_addr; - val = *mac_ptr; - VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_MACL, val); + ret = vmxnet3_dev_vlan_offload_set(dev, + ETH_VLAN_STRIP_MASK | ETH_VLAN_FILTER_MASK); + if (ret) + return ret; - val = (hw->perm_addr[5] << 8) | hw->perm_addr[4]; - VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_MACH, val); + vmxnet3_write_mac(hw, dev->data->mac_addrs->addr_bytes); return VMXNET3_SUCCESS; } @@ -544,15 +714,32 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev) static int vmxnet3_dev_start(struct rte_eth_dev *dev) { - int status, ret; + int ret; struct vmxnet3_hw *hw = dev->data->dev_private; PMD_INIT_FUNC_TRACE(); + /* Save stats before it is reset by CMD_ACTIVATE */ + vmxnet3_hw_stats_save(hw); + ret = vmxnet3_setup_driver_shared(dev); if (ret != VMXNET3_SUCCESS) return ret; + /* check if lsc interrupt feature is enabled */ + if (dev->data->dev_conf.intr_conf.lsc) { + struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device); + + /* Setup interrupt callback */ + rte_intr_callback_register(&pci_dev->intr_handle, + vmxnet3_interrupt_handler, dev); + + if (rte_intr_enable(&pci_dev->intr_handle) < 0) { + PMD_INIT_LOG(ERR, "interrupt enable failed"); + return -EIO; + } + } + /* Exchange shared data with device */ VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_DSAL, VMXNET3_GET_ADDR_LO(hw->sharedPA)); @@ -561,11 +748,34 @@ vmxnet3_dev_start(struct rte_eth_dev *dev) /* Activate device by register write */ VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_ACTIVATE_DEV); - status = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_CMD); + ret = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_CMD); - if (status != 0) { + if (ret != 0) { PMD_INIT_LOG(ERR, "Device activation: UNSUCCESSFUL"); - return -1; + return -EINVAL; + } + + /* Setup memory region for rx buffers */ + ret = vmxnet3_dev_setup_memreg(dev); + if (ret == 0) { + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, + VMXNET3_CMD_REGISTER_MEMREGS); + ret = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_CMD); + if (ret != 0) + PMD_INIT_LOG(DEBUG, + "Failed in setup memory region cmd\n"); + ret = 0; + } else { + PMD_INIT_LOG(DEBUG, "Failed to setup memory region\n"); + } + + if (VMXNET3_VERSION_GE_4(hw)) { + /* Check for additional RSS */ + ret = vmxnet3_v4_rss_configure(dev); + if (ret != VMXNET3_SUCCESS) { + PMD_INIT_LOG(ERR, "Failed to configure v4 RSS"); + return ret; + } } /* Disable interrupts */ @@ -577,22 +787,29 @@ vmxnet3_dev_start(struct rte_eth_dev *dev) */ ret = vmxnet3_dev_rxtx_init(dev); if (ret != VMXNET3_SUCCESS) { - PMD_INIT_LOG(ERR, "Device receive init: UNSUCCESSFUL"); + PMD_INIT_LOG(ERR, "Device queue init: UNSUCCESSFUL"); return ret; } + hw->adapter_stopped = FALSE; + /* Setting proper Rx Mode and issue Rx Mode Update command */ vmxnet3_dev_set_rxmode(hw, VMXNET3_RXM_UCAST | VMXNET3_RXM_BCAST, 1); - /* - * Don't need to handle events for now - */ -#if PROCESS_SYS_EVENTS == 1 - events = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_ECR); - PMD_INIT_LOG(DEBUG, "Reading events: 0x%X", events); - vmxnet3_process_events(hw); -#endif - return status; + if (dev->data->dev_conf.intr_conf.lsc) { + vmxnet3_enable_intr(hw); + + /* + * Update link state from device since this won't be + * done upon starting with lsc in use. This is done + * only after enabling interrupts to avoid any race + * where the link state could change without an + * interrupt being fired. + */ + __vmxnet3_dev_link_update(dev, 0); + } + + return VMXNET3_SUCCESS; } /* @@ -607,13 +824,22 @@ vmxnet3_dev_stop(struct rte_eth_dev *dev) PMD_INIT_FUNC_TRACE(); if (hw->adapter_stopped == 1) { - PMD_INIT_LOG(DEBUG, "Device already closed."); + PMD_INIT_LOG(DEBUG, "Device already stopped."); return; } /* disable interrupts */ vmxnet3_disable_intr(hw); + if (dev->data->dev_conf.intr_conf.lsc) { + struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device); + + rte_intr_disable(&pci_dev->intr_handle); + + rte_intr_callback_unregister(&pci_dev->intr_handle, + vmxnet3_interrupt_handler, dev); + } + /* quiesce the device first */ VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_QUIESCE_DEV); VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_DSAL, 0); @@ -622,13 +848,39 @@ vmxnet3_dev_stop(struct rte_eth_dev *dev) /* reset the device */ VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_RESET_DEV); PMD_INIT_LOG(DEBUG, "Device reset."); - hw->adapter_stopped = 0; vmxnet3_dev_clear_queues(dev); /* Clear recorded link status */ memset(&link, 0, sizeof(link)); - vmxnet3_dev_atomic_write_link_status(dev, &link); + link.link_duplex = ETH_LINK_FULL_DUPLEX; + link.link_speed = ETH_SPEED_NUM_10G; + link.link_autoneg = ETH_LINK_FIXED; + rte_eth_linkstatus_set(dev, &link); + + hw->adapter_stopped = 1; +} + +static void +vmxnet3_free_queues(struct rte_eth_dev *dev) +{ + int i; + + PMD_INIT_FUNC_TRACE(); + + for (i = 0; i < dev->data->nb_rx_queues; i++) { + void *rxq = dev->data->rx_queues[i]; + + vmxnet3_dev_rx_queue_release(rxq); + } + dev->data->nb_rx_queues = 0; + + for (i = 0; i < dev->data->nb_tx_queues; i++) { + void *txq = dev->data->tx_queues[i]; + + vmxnet3_dev_tx_queue_release(txq); + } + dev->data->nb_tx_queues = 0; } /* @@ -637,74 +889,287 @@ vmxnet3_dev_stop(struct rte_eth_dev *dev) static void vmxnet3_dev_close(struct rte_eth_dev *dev) { - struct vmxnet3_hw *hw = dev->data->dev_private; - PMD_INIT_FUNC_TRACE(); vmxnet3_dev_stop(dev); - hw->adapter_stopped = 1; + vmxnet3_free_queues(dev); +} + +static void +vmxnet3_hw_tx_stats_get(struct vmxnet3_hw *hw, unsigned int q, + struct UPT1_TxStats *res) +{ +#define VMXNET3_UPDATE_TX_STAT(h, i, f, r) \ + ((r)->f = (h)->tqd_start[(i)].stats.f + \ + (h)->saved_tx_stats[(i)].f) + + VMXNET3_UPDATE_TX_STAT(hw, q, ucastPktsTxOK, res); + VMXNET3_UPDATE_TX_STAT(hw, q, mcastPktsTxOK, res); + VMXNET3_UPDATE_TX_STAT(hw, q, bcastPktsTxOK, res); + VMXNET3_UPDATE_TX_STAT(hw, q, ucastBytesTxOK, res); + VMXNET3_UPDATE_TX_STAT(hw, q, mcastBytesTxOK, res); + VMXNET3_UPDATE_TX_STAT(hw, q, bcastBytesTxOK, res); + VMXNET3_UPDATE_TX_STAT(hw, q, pktsTxError, res); + VMXNET3_UPDATE_TX_STAT(hw, q, pktsTxDiscard, res); + +#undef VMXNET3_UPDATE_TX_STAT } static void +vmxnet3_hw_rx_stats_get(struct vmxnet3_hw *hw, unsigned int q, + struct UPT1_RxStats *res) +{ +#define VMXNET3_UPDATE_RX_STAT(h, i, f, r) \ + ((r)->f = (h)->rqd_start[(i)].stats.f + \ + (h)->saved_rx_stats[(i)].f) + + VMXNET3_UPDATE_RX_STAT(hw, q, ucastPktsRxOK, res); + VMXNET3_UPDATE_RX_STAT(hw, q, mcastPktsRxOK, res); + VMXNET3_UPDATE_RX_STAT(hw, q, bcastPktsRxOK, res); + VMXNET3_UPDATE_RX_STAT(hw, q, ucastBytesRxOK, res); + VMXNET3_UPDATE_RX_STAT(hw, q, mcastBytesRxOK, res); + VMXNET3_UPDATE_RX_STAT(hw, q, bcastBytesRxOK, res); + VMXNET3_UPDATE_RX_STAT(hw, q, pktsRxError, res); + VMXNET3_UPDATE_RX_STAT(hw, q, pktsRxOutOfBuf, res); + +#undef VMXNET3_UPDATE_RX_STAT +} + +static void +vmxnet3_tx_stats_get(struct vmxnet3_hw *hw, unsigned int q, + struct UPT1_TxStats *res) +{ + vmxnet3_hw_tx_stats_get(hw, q, res); + +#define VMXNET3_REDUCE_SNAPSHOT_TX_STAT(h, i, f, r) \ + ((r)->f -= (h)->snapshot_tx_stats[(i)].f) + + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, ucastPktsTxOK, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, mcastPktsTxOK, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, bcastPktsTxOK, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, ucastBytesTxOK, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, mcastBytesTxOK, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, bcastBytesTxOK, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, pktsTxError, res); + VMXNET3_REDUCE_SNAPSHOT_TX_STAT(hw, q, pktsTxDiscard, res); + +#undef VMXNET3_REDUCE_SNAPSHOT_TX_STAT +} + +static void +vmxnet3_rx_stats_get(struct vmxnet3_hw *hw, unsigned int q, + struct UPT1_RxStats *res) +{ + vmxnet3_hw_rx_stats_get(hw, q, res); + +#define VMXNET3_REDUCE_SNAPSHOT_RX_STAT(h, i, f, r) \ + ((r)->f -= (h)->snapshot_rx_stats[(i)].f) + + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, ucastPktsRxOK, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, mcastPktsRxOK, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, bcastPktsRxOK, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, ucastBytesRxOK, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, mcastBytesRxOK, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, bcastBytesRxOK, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, pktsRxError, res); + VMXNET3_REDUCE_SNAPSHOT_RX_STAT(hw, q, pktsRxOutOfBuf, res); + +#undef VMXNET3_REDUCE_SNAPSHOT_RX_STAT +} + +static void +vmxnet3_hw_stats_save(struct vmxnet3_hw *hw) +{ + unsigned int i; + + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + + RTE_BUILD_BUG_ON(RTE_ETHDEV_QUEUE_STAT_CNTRS < VMXNET3_MAX_TX_QUEUES); + + for (i = 0; i < hw->num_tx_queues; i++) + vmxnet3_hw_tx_stats_get(hw, i, &hw->saved_tx_stats[i]); + for (i = 0; i < hw->num_rx_queues; i++) + vmxnet3_hw_rx_stats_get(hw, i, &hw->saved_rx_stats[i]); +} + +static int +vmxnet3_dev_xstats_get_names(struct rte_eth_dev *dev, + struct rte_eth_xstat_name *xstats_names, + unsigned int n) +{ + unsigned int i, t, count = 0; + unsigned int nstats = + dev->data->nb_tx_queues * RTE_DIM(vmxnet3_txq_stat_strings) + + dev->data->nb_rx_queues * RTE_DIM(vmxnet3_rxq_stat_strings); + + if (!xstats_names || n < nstats) + return nstats; + + for (i = 0; i < dev->data->nb_rx_queues; i++) { + if (!dev->data->rx_queues[i]) + continue; + + for (t = 0; t < RTE_DIM(vmxnet3_rxq_stat_strings); t++) { + snprintf(xstats_names[count].name, + sizeof(xstats_names[count].name), + "rx_q%u_%s", i, + vmxnet3_rxq_stat_strings[t].name); + count++; + } + } + + for (i = 0; i < dev->data->nb_tx_queues; i++) { + if (!dev->data->tx_queues[i]) + continue; + + for (t = 0; t < RTE_DIM(vmxnet3_txq_stat_strings); t++) { + snprintf(xstats_names[count].name, + sizeof(xstats_names[count].name), + "tx_q%u_%s", i, + vmxnet3_txq_stat_strings[t].name); + count++; + } + } + + return count; +} + +static int +vmxnet3_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, + unsigned int n) +{ + unsigned int i, t, count = 0; + unsigned int nstats = + dev->data->nb_tx_queues * RTE_DIM(vmxnet3_txq_stat_strings) + + dev->data->nb_rx_queues * RTE_DIM(vmxnet3_rxq_stat_strings); + + if (n < nstats) + return nstats; + + for (i = 0; i < dev->data->nb_rx_queues; i++) { + struct vmxnet3_rx_queue *rxq = dev->data->rx_queues[i]; + + if (rxq == NULL) + continue; + + for (t = 0; t < RTE_DIM(vmxnet3_rxq_stat_strings); t++) { + xstats[count].value = *(uint64_t *)(((char *)&rxq->stats) + + vmxnet3_rxq_stat_strings[t].offset); + xstats[count].id = count; + count++; + } + } + + for (i = 0; i < dev->data->nb_tx_queues; i++) { + struct vmxnet3_tx_queue *txq = dev->data->tx_queues[i]; + + if (txq == NULL) + continue; + + for (t = 0; t < RTE_DIM(vmxnet3_txq_stat_strings); t++) { + xstats[count].value = *(uint64_t *)(((char *)&txq->stats) + + vmxnet3_txq_stat_strings[t].offset); + xstats[count].id = count; + count++; + } + } + + return count; +} + +static int vmxnet3_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) { unsigned int i; struct vmxnet3_hw *hw = dev->data->dev_private; + struct UPT1_TxStats txStats; + struct UPT1_RxStats rxStats; VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); RTE_BUILD_BUG_ON(RTE_ETHDEV_QUEUE_STAT_CNTRS < VMXNET3_MAX_TX_QUEUES); for (i = 0; i < hw->num_tx_queues; i++) { - struct UPT1_TxStats *txStats = &hw->tqd_start[i].stats; + vmxnet3_tx_stats_get(hw, i, &txStats); + + stats->q_opackets[i] = txStats.ucastPktsTxOK + + txStats.mcastPktsTxOK + + txStats.bcastPktsTxOK; - stats->q_opackets[i] = txStats->ucastPktsTxOK + - txStats->mcastPktsTxOK + - txStats->bcastPktsTxOK; - stats->q_obytes[i] = txStats->ucastBytesTxOK + - txStats->mcastBytesTxOK + - txStats->bcastBytesTxOK; + stats->q_obytes[i] = txStats.ucastBytesTxOK + + txStats.mcastBytesTxOK + + txStats.bcastBytesTxOK; stats->opackets += stats->q_opackets[i]; stats->obytes += stats->q_obytes[i]; - stats->oerrors += txStats->pktsTxError + - txStats->pktsTxDiscard; + stats->oerrors += txStats.pktsTxError + txStats.pktsTxDiscard; } RTE_BUILD_BUG_ON(RTE_ETHDEV_QUEUE_STAT_CNTRS < VMXNET3_MAX_RX_QUEUES); for (i = 0; i < hw->num_rx_queues; i++) { - struct UPT1_RxStats *rxStats = &hw->rqd_start[i].stats; + vmxnet3_rx_stats_get(hw, i, &rxStats); - stats->q_ipackets[i] = rxStats->ucastPktsRxOK + - rxStats->mcastPktsRxOK + - rxStats->bcastPktsRxOK; + stats->q_ipackets[i] = rxStats.ucastPktsRxOK + + rxStats.mcastPktsRxOK + + rxStats.bcastPktsRxOK; - stats->q_ibytes[i] = rxStats->ucastBytesRxOK + - rxStats->mcastBytesRxOK + - rxStats->bcastBytesRxOK; + stats->q_ibytes[i] = rxStats.ucastBytesRxOK + + rxStats.mcastBytesRxOK + + rxStats.bcastBytesRxOK; stats->ipackets += stats->q_ipackets[i]; stats->ibytes += stats->q_ibytes[i]; - stats->q_errors[i] = rxStats->pktsRxError; - stats->ierrors += rxStats->pktsRxError; - stats->imcasts += rxStats->mcastPktsRxOK; - stats->rx_nombuf += rxStats->pktsRxOutOfBuf; + stats->q_errors[i] = rxStats.pktsRxError; + stats->ierrors += rxStats.pktsRxError; + stats->imissed += rxStats.pktsRxOutOfBuf; + } + + return 0; +} + +static void +vmxnet3_dev_stats_reset(struct rte_eth_dev *dev) +{ + unsigned int i; + struct vmxnet3_hw *hw = dev->data->dev_private; + struct UPT1_TxStats txStats; + struct UPT1_RxStats rxStats; + + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + + RTE_BUILD_BUG_ON(RTE_ETHDEV_QUEUE_STAT_CNTRS < VMXNET3_MAX_TX_QUEUES); + + for (i = 0; i < hw->num_tx_queues; i++) { + vmxnet3_hw_tx_stats_get(hw, i, &txStats); + memcpy(&hw->snapshot_tx_stats[i], &txStats, + sizeof(hw->snapshot_tx_stats[0])); + } + for (i = 0; i < hw->num_rx_queues; i++) { + vmxnet3_hw_rx_stats_get(hw, i, &rxStats); + memcpy(&hw->snapshot_rx_stats[i], &rxStats, + sizeof(hw->snapshot_rx_stats[0])); } } static void -vmxnet3_dev_info_get(__attribute__((unused))struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) +vmxnet3_dev_info_get(struct rte_eth_dev *dev __rte_unused, + struct rte_eth_dev_info *dev_info) { + struct vmxnet3_hw *hw = dev->data->dev_private; + dev_info->max_rx_queues = VMXNET3_MAX_RX_QUEUES; dev_info->max_tx_queues = VMXNET3_MAX_TX_QUEUES; dev_info->min_rx_bufsize = 1518 + RTE_PKTMBUF_HEADROOM; dev_info->max_rx_pktlen = 16384; /* includes CRC, cf MAXFRS register */ + dev_info->speed_capa = ETH_LINK_SPEED_10G; dev_info->max_mac_addrs = VMXNET3_MAX_MAC_ADDRS; - dev_info->default_txconf.txq_flags = ETH_TXQ_FLAGS_NOMULTSEGS | - ETH_TXQ_FLAGS_NOOFFLOADS; dev_info->flow_type_rss_offloads = VMXNET3_RSS_OFFLOAD_ALL; + if (VMXNET3_VERSION_GE_4(hw)) { + dev_info->flow_type_rss_offloads |= VMXNET3_V4_RSS_MASK; + } + dev_info->rx_desc_lim = (struct rte_eth_desc_lim) { .nb_max = VMXNET3_RX_RING_MAX_SIZE, .nb_min = VMXNET3_DEF_RX_RING_SIZE, @@ -715,41 +1180,77 @@ vmxnet3_dev_info_get(__attribute__((unused))struct rte_eth_dev *dev, struct rte_ .nb_max = VMXNET3_TX_RING_MAX_SIZE, .nb_min = VMXNET3_DEF_TX_RING_SIZE, .nb_align = 1, + .nb_seg_max = VMXNET3_TX_MAX_SEG, + .nb_mtu_seg_max = VMXNET3_MAX_TXD_PER_PKT, }; + + dev_info->rx_offload_capa = VMXNET3_RX_OFFLOAD_CAP; + dev_info->rx_queue_offload_capa = 0; + dev_info->tx_offload_capa = VMXNET3_TX_OFFLOAD_CAP; + dev_info->tx_queue_offload_capa = 0; +} + +static const uint32_t * +vmxnet3_dev_supported_ptypes_get(struct rte_eth_dev *dev) +{ + static const uint32_t ptypes[] = { + RTE_PTYPE_L3_IPV4_EXT, + RTE_PTYPE_L3_IPV4, + RTE_PTYPE_UNKNOWN + }; + + if (dev->rx_pkt_burst == vmxnet3_recv_pkts) + return ptypes; + return NULL; +} + +static int +vmxnet3_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr) +{ + struct vmxnet3_hw *hw = dev->data->dev_private; + + ether_addr_copy(mac_addr, (struct rte_ether_addr *)(hw->perm_addr)); + vmxnet3_write_mac(hw, mac_addr->addr_bytes); + return 0; } /* return 0 means link status changed, -1 means not changed */ static int -vmxnet3_dev_link_update(struct rte_eth_dev *dev, __attribute__((unused)) int wait_to_complete) +__vmxnet3_dev_link_update(struct rte_eth_dev *dev, + __rte_unused int wait_to_complete) { struct vmxnet3_hw *hw = dev->data->dev_private; - struct rte_eth_link old, link; + struct rte_eth_link link; uint32_t ret; - if (dev->data->dev_started == 0) - return -1; /* Link status doesn't change for stopped dev */ - memset(&link, 0, sizeof(link)); - vmxnet3_dev_atomic_read_link_status(dev, &old); VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_GET_LINK); ret = VMXNET3_READ_BAR1_REG(hw, VMXNET3_REG_CMD); - if (ret & 0x1) { - link.link_status = 1; - link.link_duplex = ETH_LINK_FULL_DUPLEX; - link.link_speed = ETH_LINK_SPEED_10000; - } + if (ret & 0x1) + link.link_status = ETH_LINK_UP; + link.link_duplex = ETH_LINK_FULL_DUPLEX; + link.link_speed = ETH_SPEED_NUM_10G; + link.link_autoneg = ETH_LINK_FIXED; + + return rte_eth_linkstatus_set(dev, &link); +} - vmxnet3_dev_atomic_write_link_status(dev, &link); +static int +vmxnet3_dev_link_update(struct rte_eth_dev *dev, int wait_to_complete) +{ + /* Link status doesn't change for stopped dev */ + if (dev->data->dev_started == 0) + return -1; - return (old.link_status == link.link_status) ? -1 : 0; + return __vmxnet3_dev_link_update(dev, wait_to_complete); } /* Updating rxmode through Vmxnet3_DriverShared structure in adapter */ static void -vmxnet3_dev_set_rxmode(struct vmxnet3_hw *hw, uint32_t feature, int set) { - +vmxnet3_dev_set_rxmode(struct vmxnet3_hw *hw, uint32_t feature, int set) +{ struct Vmxnet3_RxFilterConf *rxConf = &hw->shared->devRead.rxFilterConf; if (set) @@ -780,8 +1281,12 @@ vmxnet3_dev_promiscuous_disable(struct rte_eth_dev *dev) { struct vmxnet3_hw *hw = dev->data->dev_private; uint32_t *vf_table = hw->shared->devRead.rxFilterConf.vfTable; + uint64_t rx_offloads = dev->data->dev_conf.rxmode.offloads; - memcpy(vf_table, hw->shadow_vfta, VMXNET3_VFT_TABLE_SIZE); + if (rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER) + memcpy(vf_table, hw->shadow_vfta, VMXNET3_VFT_TABLE_SIZE); + else + memset(vf_table, 0xff, VMXNET3_VFT_TABLE_SIZE); vmxnet3_dev_set_rxmode(hw, VMXNET3_RXM_PROMISC, 0); VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_UPDATE_VLAN_FILTERS); @@ -834,57 +1339,45 @@ vmxnet3_dev_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vid, int on) return 0; } -static void -vmxnet3_dev_vlan_offload_set_clear(struct rte_eth_dev *dev, - int mask, int clear) +static int +vmxnet3_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask) { struct vmxnet3_hw *hw = dev->data->dev_private; Vmxnet3_DSDevRead *devRead = &hw->shared->devRead; uint32_t *vf_table = devRead->rxFilterConf.vfTable; + uint64_t rx_offloads = dev->data->dev_conf.rxmode.offloads; - if (mask & ETH_VLAN_STRIP_MASK) - devRead->misc.uptFeatures |= UPT1_F_RXVLAN; - else - devRead->misc.uptFeatures &= ~UPT1_F_RXVLAN; + if (mask & ETH_VLAN_STRIP_MASK) { + if (rx_offloads & DEV_RX_OFFLOAD_VLAN_STRIP) + devRead->misc.uptFeatures |= UPT1_F_RXVLAN; + else + devRead->misc.uptFeatures &= ~UPT1_F_RXVLAN; - VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_FEATURE); + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_FEATURE); + } if (mask & ETH_VLAN_FILTER_MASK) { - if (clear) { - memset(hw->shadow_vfta, 0, - VMXNET3_VFT_TABLE_SIZE); - /* allow untagged pkts */ - VMXNET3_SET_VFTABLE_ENTRY(hw->shadow_vfta, 0); - } - memcpy(vf_table, hw->shadow_vfta, VMXNET3_VFT_TABLE_SIZE); - } else { - /* allow any pkts -- no filtering */ - if (clear) - memset(hw->shadow_vfta, 0xff, VMXNET3_VFT_TABLE_SIZE); - memset(vf_table, 0xff, VMXNET3_VFT_TABLE_SIZE); - } + if (rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER) + memcpy(vf_table, hw->shadow_vfta, VMXNET3_VFT_TABLE_SIZE); + else + memset(vf_table, 0xff, VMXNET3_VFT_TABLE_SIZE); - VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_VLAN_FILTERS); -} + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); + } -static void -vmxnet3_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask) -{ - vmxnet3_dev_vlan_offload_set_clear(dev, mask, 0); + return 0; } -#if PROCESS_SYS_EVENTS == 1 static void -vmxnet3_process_events(struct vmxnet3_hw *hw) +vmxnet3_process_events(struct rte_eth_dev *dev) { + struct vmxnet3_hw *hw = dev->data->dev_private; uint32_t events = hw->shared->ecr; - if (!events) { - PMD_INIT_LOG(ERR, "No events to process"); + if (!events) return; - } /* * ECR bits when written with 1b are cleared. Hence write @@ -893,20 +1386,25 @@ vmxnet3_process_events(struct vmxnet3_hw *hw) VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_ECR, events); /* Check if link state has changed */ - if (events & VMXNET3_ECR_LINK) - PMD_INIT_LOG(ERR, - "Process events in %s(): VMXNET3_ECR_LINK event", __func__); + if (events & VMXNET3_ECR_LINK) { + PMD_DRV_LOG(DEBUG, "Process events: VMXNET3_ECR_LINK event"); + if (vmxnet3_dev_link_update(dev, 0) == 0) + _rte_eth_dev_callback_process(dev, + RTE_ETH_EVENT_INTR_LSC, + NULL); + } /* Check if there is an error on xmit/recv queues */ if (events & (VMXNET3_ECR_TQERR | VMXNET3_ECR_RQERR)) { - VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, VMXNET3_CMD_GET_QUEUE_STATUS); + VMXNET3_WRITE_BAR1_REG(hw, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_QUEUE_STATUS); if (hw->tqd_start->status.stopped) - PMD_INIT_LOG(ERR, "tq error 0x%x", - hw->tqd_start->status.error); + PMD_DRV_LOG(ERR, "tq error 0x%x", + hw->tqd_start->status.error); if (hw->rqd_start->status.stopped) - PMD_INIT_LOG(ERR, "rq error 0x%x", + PMD_DRV_LOG(ERR, "rq error 0x%x", hw->rqd_start->status.error); /* Reset the device */ @@ -914,17 +1412,34 @@ vmxnet3_process_events(struct vmxnet3_hw *hw) } if (events & VMXNET3_ECR_DIC) - PMD_INIT_LOG(ERR, "Device implementation change event."); + PMD_DRV_LOG(DEBUG, "Device implementation change event."); if (events & VMXNET3_ECR_DEBUG) - PMD_INIT_LOG(ERR, "Debug event generated by device."); + PMD_DRV_LOG(DEBUG, "Debug event generated by device."); +} + +static void +vmxnet3_interrupt_handler(void *param) +{ + struct rte_eth_dev *dev = param; + struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device); + vmxnet3_process_events(dev); + + if (rte_intr_enable(&pci_dev->intr_handle) < 0) + PMD_DRV_LOG(ERR, "interrupt enable failed"); } -#endif -static struct rte_driver rte_vmxnet3_driver = { - .type = PMD_PDEV, - .init = rte_vmxnet3_pmd_init, -}; +RTE_PMD_REGISTER_PCI(net_vmxnet3, rte_vmxnet3_pmd); +RTE_PMD_REGISTER_PCI_TABLE(net_vmxnet3, pci_id_vmxnet3_map); +RTE_PMD_REGISTER_KMOD_DEP(net_vmxnet3, "* igb_uio | uio_pci_generic | vfio-pci"); -PMD_REGISTER_DRIVER(rte_vmxnet3_driver); +RTE_INIT(vmxnet3_init_log) +{ + vmxnet3_logtype_init = rte_log_register("pmd.net.vmxnet3.init"); + if (vmxnet3_logtype_init >= 0) + rte_log_set_level(vmxnet3_logtype_init, RTE_LOG_NOTICE); + vmxnet3_logtype_driver = rte_log_register("pmd.net.vmxnet3.driver"); + if (vmxnet3_logtype_driver >= 0) + rte_log_set_level(vmxnet3_logtype_driver, RTE_LOG_NOTICE); +}