diff options
Diffstat (limited to 'src/dpdk/lib/librte_ether')
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_dev_info.h | 2 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_eth_ctrl.h | 12 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_ethdev.c | 712 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_ethdev.h | 605 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_ether.h | 416 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_flow.c | 159 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_flow.h | 1090 | ||||
| -rw-r--r-- | src/dpdk/lib/librte_ether/rte_flow_driver.h | 182 |
8 files changed, 2011 insertions, 1167 deletions
diff --git a/src/dpdk/lib/librte_ether/rte_dev_info.h b/src/dpdk/lib/librte_ether/rte_dev_info.h index 574683d3..aab6d1a6 100644 --- a/src/dpdk/lib/librte_ether/rte_dev_info.h +++ b/src/dpdk/lib/librte_ether/rte_dev_info.h @@ -34,6 +34,8 @@ #ifndef _RTE_DEV_INFO_H_ #define _RTE_DEV_INFO_H_ +#include <stdint.h> + /* * Placeholder for accessing device registers */ diff --git a/src/dpdk/lib/librte_ether/rte_eth_ctrl.h b/src/dpdk/lib/librte_ether/rte_eth_ctrl.h index 563e80f8..83869042 100644 --- a/src/dpdk/lib/librte_ether/rte_eth_ctrl.h +++ b/src/dpdk/lib/librte_ether/rte_eth_ctrl.h @@ -34,6 +34,10 @@ #ifndef _RTE_ETH_CTRL_H_ #define _RTE_ETH_CTRL_H_ +#include <stdint.h> +#include <rte_common.h> +#include "rte_ether.h" + /** * @file * @@ -95,6 +99,7 @@ enum rte_filter_type { RTE_ETH_FILTER_FDIR, RTE_ETH_FILTER_HASH, RTE_ETH_FILTER_L2_TUNNEL, + RTE_ETH_FILTER_GENERIC, RTE_ETH_FILTER_MAX }; @@ -420,8 +425,6 @@ struct rte_eth_l2_flow { struct rte_eth_ipv4_flow { uint32_t src_ip; /**< IPv4 source address in big endian. */ uint32_t dst_ip; /**< IPv4 destination address in big endian. */ - // TREX_PATCH (ip_id) - uint16_t ip_id; /**< IPv4 IP ID to match */ uint8_t tos; /**< Type of service to match. */ uint8_t ttl; /**< Time to live to match. */ uint8_t proto; /**< Protocol, next header in big endian. */ @@ -464,8 +467,6 @@ struct rte_eth_ipv6_flow { uint8_t tc; /**< Traffic class to match. */ uint8_t proto; /**< Protocol, next header to match. */ uint8_t hop_limits; /**< Hop limits to match. */ - // TREX_PATCH (flow_label) - uint32_t flow_label; /**<flow label to match. */ }; /** @@ -594,9 +595,6 @@ struct rte_eth_fdir_action { /**< If report_status is RTE_ETH_FDIR_REPORT_ID_FLEX_4 or RTE_ETH_FDIR_REPORT_FLEX_8, flex_off specifies where the reported flex bytes start from in flexible payload. */ - // TREX_PATCH - // Index for statistics counter that will count FDIR matches. - uint16_t stat_count_index; }; /** diff --git a/src/dpdk/lib/librte_ether/rte_ethdev.c b/src/dpdk/lib/librte_ether/rte_ethdev.c index e7bc9d6d..eb0a94a9 100644 --- a/src/dpdk/lib/librte_ether/rte_ethdev.c +++ b/src/dpdk/lib/librte_ether/rte_ethdev.c @@ -58,7 +58,6 @@ #include <rte_atomic.h> #include <rte_branch_prediction.h> #include <rte_common.h> -#include <rte_ring.h> #include <rte_mempool.h> #include <rte_malloc.h> #include <rte_mbuf.h> @@ -72,6 +71,7 @@ static const char *MZ_RTE_ETH_DEV_DATA = "rte_eth_dev_data"; struct rte_eth_dev rte_eth_devices[RTE_MAX_ETHPORTS]; static struct rte_eth_dev_data *rte_eth_dev_data; +static uint8_t eth_dev_last_created_port; static uint8_t nb_ports; /* spinlock for eth device callbacks */ @@ -189,8 +189,23 @@ rte_eth_dev_find_free_port(void) return RTE_MAX_ETHPORTS; } +static struct rte_eth_dev * +eth_dev_get(uint8_t port_id) +{ + struct rte_eth_dev *eth_dev = &rte_eth_devices[port_id]; + + eth_dev->data = &rte_eth_dev_data[port_id]; + eth_dev->attached = DEV_ATTACHED; + TAILQ_INIT(&(eth_dev->link_intr_cbs)); + + eth_dev_last_created_port = port_id; + nb_ports++; + + return eth_dev; +} + struct rte_eth_dev * -rte_eth_dev_allocate(const char *name, enum rte_eth_dev_type type) +rte_eth_dev_allocate(const char *name) { uint8_t port_id; struct rte_eth_dev *eth_dev; @@ -210,28 +225,44 @@ rte_eth_dev_allocate(const char *name, enum rte_eth_dev_type type) return NULL; } - eth_dev = &rte_eth_devices[port_id]; - eth_dev->data = &rte_eth_dev_data[port_id]; + memset(&rte_eth_dev_data[port_id], 0, sizeof(struct rte_eth_dev_data)); + eth_dev = eth_dev_get(port_id); snprintf(eth_dev->data->name, sizeof(eth_dev->data->name), "%s", name); eth_dev->data->port_id = port_id; - eth_dev->attached = DEV_ATTACHED; - eth_dev->dev_type = type; - nb_ports++; + eth_dev->data->mtu = ETHER_MTU; + return eth_dev; } -static int -rte_eth_dev_create_unique_device_name(char *name, size_t size, - struct rte_pci_device *pci_dev) +/* + * Attach to a port already registered by the primary process, which + * makes sure that the same device would have the same port id both + * in the primary and secondary process. + */ +static struct rte_eth_dev * +eth_dev_attach_secondary(const char *name) { - int ret; + uint8_t i; + struct rte_eth_dev *eth_dev; - ret = snprintf(name, size, "%d:%d.%d", - pci_dev->addr.bus, pci_dev->addr.devid, - pci_dev->addr.function); - if (ret < 0) - return ret; - return 0; + if (rte_eth_dev_data == NULL) + rte_eth_dev_data_alloc(); + + for (i = 0; i < RTE_MAX_ETHPORTS; i++) { + if (strcmp(rte_eth_dev_data[i].name, name) == 0) + break; + } + if (i == RTE_MAX_ETHPORTS) { + RTE_PMD_DEBUG_TRACE( + "device %s is not driven by the primary process\n", + name); + return NULL; + } + + eth_dev = eth_dev_get(i); + RTE_ASSERT(eth_dev->data->port_id == i); + + return eth_dev; } int @@ -245,9 +276,9 @@ rte_eth_dev_release_port(struct rte_eth_dev *eth_dev) return 0; } -static int -rte_eth_dev_init(struct rte_pci_driver *pci_drv, - struct rte_pci_device *pci_dev) +int +rte_eth_dev_pci_probe(struct rte_pci_driver *pci_drv, + struct rte_pci_device *pci_dev) { struct eth_driver *eth_drv; struct rte_eth_dev *eth_dev; @@ -257,40 +288,43 @@ rte_eth_dev_init(struct rte_pci_driver *pci_drv, eth_drv = (struct eth_driver *)pci_drv; - /* Create unique Ethernet device name using PCI address */ - rte_eth_dev_create_unique_device_name(ethdev_name, - sizeof(ethdev_name), pci_dev); - - eth_dev = rte_eth_dev_allocate(ethdev_name, RTE_ETH_DEV_PCI); - if (eth_dev == NULL) - return -ENOMEM; + rte_eal_pci_device_name(&pci_dev->addr, ethdev_name, + sizeof(ethdev_name)); if (rte_eal_process_type() == RTE_PROC_PRIMARY) { + eth_dev = rte_eth_dev_allocate(ethdev_name); + if (eth_dev == NULL) + return -ENOMEM; + eth_dev->data->dev_private = rte_zmalloc("ethdev private structure", eth_drv->dev_private_size, RTE_CACHE_LINE_SIZE); if (eth_dev->data->dev_private == NULL) rte_panic("Cannot allocate memzone for private port data\n"); + } else { + eth_dev = eth_dev_attach_secondary(ethdev_name); + if (eth_dev == NULL) { + /* + * if we failed to attach a device, it means the + * device is skipped in primary process, due to + * some errors. If so, we return a positive value, + * to let EAL skip it for the secondary process + * as well. + */ + return 1; + } } - eth_dev->pci_dev = pci_dev; + eth_dev->device = &pci_dev->device; + eth_dev->intr_handle = &pci_dev->intr_handle; eth_dev->driver = eth_drv; - eth_dev->data->rx_mbuf_alloc_failed = 0; - - /* init user callbacks */ - TAILQ_INIT(&(eth_dev->link_intr_cbs)); - - /* - * Set the default MTU. - */ - eth_dev->data->mtu = ETHER_MTU; /* Invoke PMD device initialization function */ diag = (*eth_drv->eth_dev_init)(eth_dev); if (diag == 0) return 0; - RTE_PMD_DEBUG_TRACE("driver %s: eth_dev_init(vendor_id=0x%u device_id=0x%x) failed\n", - pci_drv->name, + RTE_PMD_DEBUG_TRACE("driver %s: eth_dev_init(vendor_id=0x%x device_id=0x%x) failed\n", + pci_drv->driver.name, (unsigned) pci_dev->id.vendor_id, (unsigned) pci_dev->id.device_id); if (rte_eal_process_type() == RTE_PROC_PRIMARY) @@ -299,8 +333,8 @@ rte_eth_dev_init(struct rte_pci_driver *pci_drv, return diag; } -static int -rte_eth_dev_uninit(struct rte_pci_device *pci_dev) +int +rte_eth_dev_pci_remove(struct rte_pci_device *pci_dev) { const struct eth_driver *eth_drv; struct rte_eth_dev *eth_dev; @@ -310,9 +344,8 @@ rte_eth_dev_uninit(struct rte_pci_device *pci_dev) if (pci_dev == NULL) return -EINVAL; - /* Create unique Ethernet device name using PCI address */ - rte_eth_dev_create_unique_device_name(ethdev_name, - sizeof(ethdev_name), pci_dev); + rte_eal_pci_device_name(&pci_dev->addr, ethdev_name, + sizeof(ethdev_name)); eth_dev = rte_eth_dev_allocated(ethdev_name); if (eth_dev == NULL) @@ -333,35 +366,13 @@ rte_eth_dev_uninit(struct rte_pci_device *pci_dev) if (rte_eal_process_type() == RTE_PROC_PRIMARY) rte_free(eth_dev->data->dev_private); - eth_dev->pci_dev = NULL; + eth_dev->device = NULL; eth_dev->driver = NULL; eth_dev->data = NULL; return 0; } -/** - * Register an Ethernet [Poll Mode] driver. - * - * Function invoked by the initialization function of an Ethernet driver - * to simultaneously register itself as a PCI driver and as an Ethernet - * Poll Mode Driver. - * Invokes the rte_eal_pci_register() function to register the *pci_drv* - * structure embedded in the *eth_drv* structure, after having stored the - * address of the rte_eth_dev_init() function in the *devinit* field of - * the *pci_drv* structure. - * During the PCI probing phase, the rte_eth_dev_init() function is - * invoked for each PCI [Ethernet device] matching the embedded PCI - * identifiers provided by the driver. - */ -void -rte_eth_driver_register(struct eth_driver *eth_drv) -{ - eth_drv->pci_drv.devinit = rte_eth_dev_init; - eth_drv->pci_drv.devuninit = rte_eth_dev_uninit; - rte_eal_pci_register(ð_drv->pci_drv); -} - int rte_eth_dev_is_valid_port(uint8_t port_id) { @@ -385,27 +396,6 @@ rte_eth_dev_count(void) return nb_ports; } -static enum rte_eth_dev_type -rte_eth_dev_get_device_type(uint8_t port_id) -{ - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, RTE_ETH_DEV_UNKNOWN); - return rte_eth_devices[port_id].dev_type; -} - -static int -rte_eth_dev_get_addr_by_port(uint8_t port_id, struct rte_pci_addr *addr) -{ - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); - - if (addr == NULL) { - RTE_PMD_DEBUG_TRACE("Null pointer is specified\n"); - return -EINVAL; - } - - *addr = rte_eth_devices[port_id].pci_dev->addr; - return 0; -} - int rte_eth_dev_get_name_by_port(uint8_t port_id, char *name) { @@ -435,6 +425,9 @@ rte_eth_dev_get_port_by_name(const char *name, uint8_t *port_id) return -EINVAL; } + if (!nb_ports) + return -ENODEV; + *port_id = RTE_MAX_ETHPORTS; for (i = 0; i < RTE_MAX_ETHPORTS; i++) { @@ -450,35 +443,6 @@ rte_eth_dev_get_port_by_name(const char *name, uint8_t *port_id) return -ENODEV; } -/* TREX_PATCH removed "static" */ -int -rte_eth_dev_get_port_by_addr(const struct rte_pci_addr *addr, uint8_t *port_id) -{ - int i; - struct rte_pci_device *pci_dev = NULL; - - if (addr == NULL) { - RTE_PMD_DEBUG_TRACE("Null pointer is specified\n"); - return -EINVAL; - } - - *port_id = RTE_MAX_ETHPORTS; - - for (i = 0; i < RTE_MAX_ETHPORTS; i++) { - - pci_dev = rte_eth_devices[i].pci_dev; - - if (pci_dev && - !rte_eal_compare_pci_addr(&pci_dev->addr, addr)) { - - *port_id = i; - - return 0; - } - } - return -ENODEV; -} - static int rte_eth_dev_is_detachable(uint8_t port_id) { @@ -504,127 +468,49 @@ rte_eth_dev_is_detachable(uint8_t port_id) return 1; } -/* attach the new physical device, then store port_id of the device */ -static int -rte_eth_dev_attach_pdev(struct rte_pci_addr *addr, uint8_t *port_id) +/* attach the new device, then store port_id of the device */ +int +rte_eth_dev_attach(const char *devargs, uint8_t *port_id) { - /* re-construct pci_device_list */ - if (rte_eal_pci_scan()) - goto err; - /* Invoke probe func of the driver can handle the new device. */ - if (rte_eal_pci_probe_one(addr)) - goto err; + int ret = -1; + int current = rte_eth_dev_count(); + char *name = NULL; + char *args = NULL; - if (rte_eth_dev_get_port_by_addr(addr, port_id)) + if ((devargs == NULL) || (port_id == NULL)) { + ret = -EINVAL; goto err; + } - return 0; -err: - return -1; -} - -/* detach the new physical device, then store pci_addr of the device */ -static int -rte_eth_dev_detach_pdev(uint8_t port_id, struct rte_pci_addr *addr) -{ - struct rte_pci_addr freed_addr; - struct rte_pci_addr vp; - - /* get pci address by port id */ - if (rte_eth_dev_get_addr_by_port(port_id, &freed_addr)) + /* parse devargs, then retrieve device name and args */ + if (rte_eal_parse_devargs_str(devargs, &name, &args)) goto err; - /* Zeroed pci addr means the port comes from virtual device */ - vp.domain = vp.bus = vp.devid = vp.function = 0; - if (rte_eal_compare_pci_addr(&vp, &freed_addr) == 0) + ret = rte_eal_dev_attach(name, args); + if (ret < 0) goto err; - /* invoke devuninit func of the pci driver, - * also remove the device from pci_device_list */ - if (rte_eal_pci_detach(&freed_addr)) + /* no point looking at the port count if no port exists */ + if (!rte_eth_dev_count()) { + RTE_LOG(ERR, EAL, "No port found for device (%s)\n", name); + ret = -1; goto err; + } - *addr = freed_addr; - return 0; -err: - return -1; -} - -/* attach the new virtual device, then store port_id of the device */ -static int -rte_eth_dev_attach_vdev(const char *vdevargs, uint8_t *port_id) -{ - char *name = NULL, *args = NULL; - int ret = -1; - - /* parse vdevargs, then retrieve device name and args */ - if (rte_eal_parse_devargs_str(vdevargs, &name, &args)) - goto end; - - /* walk around dev_driver_list to find the driver of the device, - * then invoke probe function of the driver. - * rte_eal_vdev_init() updates port_id allocated after - * initialization. + /* if nothing happened, there is a bug here, since some driver told us + * it did attach a device, but did not create a port. */ - if (rte_eal_vdev_init(name, args)) - goto end; - - if (rte_eth_dev_get_port_by_name(name, port_id)) - goto end; - - ret = 0; -end: - free(name); - free(args); - - return ret; -} - -/* detach the new virtual device, then store the name of the device */ -static int -rte_eth_dev_detach_vdev(uint8_t port_id, char *vdevname) -{ - char name[RTE_ETH_NAME_MAX_LEN]; - - /* get device name by port id */ - if (rte_eth_dev_get_name_by_port(port_id, name)) - goto err; - /* walk around dev_driver_list to find the driver of the device, - * then invoke uninit function of the driver */ - if (rte_eal_vdev_uninit(name)) - goto err; - - strncpy(vdevname, name, sizeof(name)); - return 0; -err: - return -1; -} - -/* attach the new device, then store port_id of the device */ -int -rte_eth_dev_attach(const char *devargs, uint8_t *port_id) -{ - struct rte_pci_addr addr; - int ret = -1; - - if ((devargs == NULL) || (port_id == NULL)) { - ret = -EINVAL; + if (current == rte_eth_dev_count()) { + ret = -1; goto err; } - if (eal_parse_pci_DomBDF(devargs, &addr) == 0) { - ret = rte_eth_dev_attach_pdev(&addr, port_id); - if (ret < 0) - goto err; - } else { - ret = rte_eth_dev_attach_vdev(devargs, port_id); - if (ret < 0) - goto err; - } + *port_id = eth_dev_last_created_port; + ret = 0; - return 0; err: - RTE_LOG(ERR, EAL, "Driver, cannot attach the device\n"); + free(name); + free(args); return ret; } @@ -632,7 +518,6 @@ err: int rte_eth_dev_detach(uint8_t port_id, char *name) { - struct rte_pci_addr addr; int ret = -1; if (name == NULL) { @@ -640,33 +525,19 @@ rte_eth_dev_detach(uint8_t port_id, char *name) goto err; } - /* check whether the driver supports detach feature, or not */ + /* FIXME: move this to eal, once device flags are relocated there */ if (rte_eth_dev_is_detachable(port_id)) goto err; - if (rte_eth_dev_get_device_type(port_id) == RTE_ETH_DEV_PCI) { - ret = rte_eth_dev_get_addr_by_port(port_id, &addr); - if (ret < 0) - goto err; - - ret = rte_eth_dev_detach_pdev(port_id, &addr); - if (ret < 0) - goto err; - - snprintf(name, RTE_ETH_NAME_MAX_LEN, - "%04x:%02x:%02x.%d", - addr.domain, addr.bus, - addr.devid, addr.function); - } else { - ret = rte_eth_dev_detach_vdev(port_id, name); - if (ret < 0) - goto err; - } + snprintf(name, sizeof(rte_eth_devices[port_id].data->name), + "%s", rte_eth_devices[port_id].data->name); + ret = rte_eal_dev_detach(name); + if (ret < 0) + goto err; return 0; err: - RTE_LOG(ERR, EAL, "Driver, cannot detach the device\n"); return ret; } @@ -712,6 +583,9 @@ rte_eth_dev_rx_queue_config(struct rte_eth_dev *dev, uint16_t nb_queues) for (i = nb_queues; i < old_nb_queues; i++) (*dev->dev_ops->rx_queue_release)(rxq[i]); + + rte_free(dev->data->rx_queues); + dev->data->rx_queues = NULL; } dev->data->nb_rx_queues = nb_queues; return 0; @@ -863,6 +737,9 @@ rte_eth_dev_tx_queue_config(struct rte_eth_dev *dev, uint16_t nb_queues) for (i = nb_queues; i < old_nb_queues; i++) (*dev->dev_ops->tx_queue_release)(txq[i]); + + rte_free(dev->data->tx_queues); + dev->data->tx_queues = NULL; } dev->data->nb_tx_queues = nb_queues; return 0; @@ -1033,39 +910,61 @@ rte_eth_dev_configure(uint8_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, return 0; } +void +_rte_eth_dev_reset(struct rte_eth_dev *dev) +{ + if (dev->data->dev_started) { + RTE_PMD_DEBUG_TRACE( + "port %d must be stopped to allow reset\n", + dev->data->port_id); + return; + } + + rte_eth_dev_rx_queue_config(dev, 0); + rte_eth_dev_tx_queue_config(dev, 0); + + memset(&dev->data->dev_conf, 0, sizeof(dev->data->dev_conf)); +} + static void rte_eth_dev_config_restore(uint8_t port_id) { struct rte_eth_dev *dev; struct rte_eth_dev_info dev_info; - struct ether_addr addr; + struct ether_addr *addr; uint16_t i; uint32_t pool = 0; + uint64_t pool_mask; dev = &rte_eth_devices[port_id]; rte_eth_dev_info_get(port_id, &dev_info); - if (RTE_ETH_DEV_SRIOV(dev).active) - pool = RTE_ETH_DEV_SRIOV(dev).def_vmdq_idx; - - /* replay MAC address configuration */ - for (i = 0; i < dev_info.max_mac_addrs; i++) { - addr = dev->data->mac_addrs[i]; - - /* skip zero address */ - if (is_zero_ether_addr(&addr)) - continue; - - /* add address to the hardware */ - if (*dev->dev_ops->mac_addr_add && - (dev->data->mac_pool_sel[i] & (1ULL << pool))) - (*dev->dev_ops->mac_addr_add)(dev, &addr, i, pool); - else { - RTE_PMD_DEBUG_TRACE("port %d: MAC address array not supported\n", - port_id); - /* exit the loop but not return an error */ - break; + /* replay MAC address configuration including default MAC */ + addr = &dev->data->mac_addrs[0]; + if (*dev->dev_ops->mac_addr_set != NULL) + (*dev->dev_ops->mac_addr_set)(dev, addr); + else if (*dev->dev_ops->mac_addr_add != NULL) + (*dev->dev_ops->mac_addr_add)(dev, addr, 0, pool); + + if (*dev->dev_ops->mac_addr_add != NULL) { + for (i = 1; i < dev_info.max_mac_addrs; i++) { + addr = &dev->data->mac_addrs[i]; + + /* skip zero address */ + if (is_zero_ether_addr(addr)) + continue; + + pool = 0; + pool_mask = dev->data->mac_pool_sel[i]; + + do { + if (pool_mask & 1ULL) + (*dev->dev_ops->mac_addr_add)(dev, + addr, i, pool); + pool_mask >>= 1; + pool++; + } while (pool_mask); } } @@ -1191,6 +1090,7 @@ rte_eth_rx_queue_setup(uint8_t port_id, uint16_t rx_queue_id, uint32_t mbp_buf_size; struct rte_eth_dev *dev; struct rte_eth_dev_info dev_info; + void **rxq; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); @@ -1249,6 +1149,14 @@ rte_eth_rx_queue_setup(uint8_t port_id, uint16_t rx_queue_id, return -EINVAL; } + rxq = dev->data->rx_queues; + if (rxq[rx_queue_id]) { + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_release, + -ENOTSUP); + (*dev->dev_ops->rx_queue_release)(rxq[rx_queue_id]); + rxq[rx_queue_id] = NULL; + } + if (rx_conf == NULL) rx_conf = &dev_info.default_rxconf; @@ -1270,6 +1178,7 @@ rte_eth_tx_queue_setup(uint8_t port_id, uint16_t tx_queue_id, { struct rte_eth_dev *dev; struct rte_eth_dev_info dev_info; + void **txq; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); @@ -1302,6 +1211,14 @@ rte_eth_tx_queue_setup(uint8_t port_id, uint16_t tx_queue_id, return -EINVAL; } + txq = dev->data->tx_queues; + if (txq[tx_queue_id]) { + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_release, + -ENOTSUP); + (*dev->dev_ops->tx_queue_release)(txq[tx_queue_id]); + txq[tx_queue_id] = NULL; + } + if (tx_conf == NULL) tx_conf = &dev_info.default_txconf; @@ -1480,54 +1397,6 @@ rte_eth_link_get_nowait(uint8_t port_id, struct rte_eth_link *eth_link) } } -// TREX_PATCH -// return in stats, statistics starting from start, for len counters. -int -rte_eth_fdir_stats_get(uint8_t port_id, uint32_t *stats, uint32_t start, uint32_t len) -{ - struct rte_eth_dev *dev; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); - - dev = &rte_eth_devices[port_id]; - - // Only xl710 support this - i40e_trex_fdir_stats_get(dev, stats, start, len); - - return 0; -} - -// TREX_PATCH -// zero statistics counters, starting from start, for len counters. -int -rte_eth_fdir_stats_reset(uint8_t port_id, uint32_t *stats, uint32_t start, uint32_t len) -{ - struct rte_eth_dev *dev; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); - - dev = &rte_eth_devices[port_id]; - - // Only xl710 support this - i40e_trex_fdir_stats_reset(dev, stats, start, len); - - return 0; -} - -// TREX_PATCH -int -rte_eth_get_fw_ver(int port_id, uint32_t *version) -{ - struct rte_eth_dev *dev; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); - - dev = &rte_eth_devices[port_id]; - - // Only xl710 support this - return i40e_trex_get_fw_ver(dev, version); -} - int rte_eth_stats_get(uint8_t port_id, struct rte_eth_stats *stats) { @@ -1572,8 +1441,10 @@ get_xstats_count(uint8_t port_id) } else count = 0; count += RTE_NB_STATS; - count += dev->data->nb_rx_queues * RTE_NB_RXQ_STATS; - count += dev->data->nb_tx_queues * RTE_NB_TXQ_STATS; + count += RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS) * + RTE_NB_RXQ_STATS; + count += RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS) * + RTE_NB_TXQ_STATS; return count; } @@ -1587,6 +1458,7 @@ rte_eth_xstats_get_names(uint8_t port_id, int cnt_expected_entries; int cnt_driver_entries; uint32_t idx, id_queue; + uint16_t num_q; cnt_expected_entries = get_xstats_count(port_id); if (xstats_names == NULL || cnt_expected_entries < 0 || @@ -1603,7 +1475,8 @@ rte_eth_xstats_get_names(uint8_t port_id, "%s", rte_stats_strings[idx].name); cnt_used_entries++; } - for (id_queue = 0; id_queue < dev->data->nb_rx_queues; id_queue++) { + num_q = RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + for (id_queue = 0; id_queue < num_q; id_queue++) { for (idx = 0; idx < RTE_NB_RXQ_STATS; idx++) { snprintf(xstats_names[cnt_used_entries].name, sizeof(xstats_names[0].name), @@ -1613,7 +1486,8 @@ rte_eth_xstats_get_names(uint8_t port_id, } } - for (id_queue = 0; id_queue < dev->data->nb_tx_queues; id_queue++) { + num_q = RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + for (id_queue = 0; id_queue < num_q; id_queue++) { for (idx = 0; idx < RTE_NB_TXQ_STATS; idx++) { snprintf(xstats_names[cnt_used_entries].name, sizeof(xstats_names[0].name), @@ -1649,14 +1523,18 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, unsigned count = 0, i, q; signed xcount = 0; uint64_t val, *stats_ptr; + uint16_t nb_rxqs, nb_txqs; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); dev = &rte_eth_devices[port_id]; + nb_rxqs = RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + nb_txqs = RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + /* Return generic statistics */ - count = RTE_NB_STATS + (dev->data->nb_rx_queues * RTE_NB_RXQ_STATS) + - (dev->data->nb_tx_queues * RTE_NB_TXQ_STATS); + count = RTE_NB_STATS + (nb_rxqs * RTE_NB_RXQ_STATS) + + (nb_txqs * RTE_NB_TXQ_STATS); /* implemented by the driver */ if (dev->dev_ops->xstats_get != NULL) { @@ -1687,7 +1565,7 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, } /* per-rxq stats */ - for (q = 0; q < dev->data->nb_rx_queues; q++) { + for (q = 0; q < nb_rxqs; q++) { for (i = 0; i < RTE_NB_RXQ_STATS; i++) { stats_ptr = RTE_PTR_ADD(ð_stats, rte_rxq_stats_strings[i].offset + @@ -1698,7 +1576,7 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, } /* per-txq stats */ - for (q = 0; q < dev->data->nb_tx_queues; q++) { + for (q = 0; q < nb_txqs; q++) { for (i = 0; i < RTE_NB_TXQ_STATS; i++) { stats_ptr = RTE_PTR_ADD(ð_stats, rte_txq_stats_strings[i].offset + @@ -1708,8 +1586,11 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, } } - for (i = 0; i < count + xcount; i++) + for (i = 0; i < count; i++) xstats[i].id = i; + /* add an offset to driver-specific stats */ + for ( ; i < count + xcount; i++) + xstats[i].id += count; return count + xcount; } @@ -1766,6 +1647,18 @@ rte_eth_dev_set_rx_queue_stats_mapping(uint8_t port_id, uint16_t rx_queue_id, STAT_QMAP_RX); } +int +rte_eth_dev_fw_version_get(uint8_t port_id, char *fw_version, size_t fw_size) +{ + struct rte_eth_dev *dev; + + RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); + dev = &rte_eth_devices[port_id]; + + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->fw_version_get, -ENOTSUP); + return (*dev->dev_ops->fw_version_get)(dev, fw_version, fw_size); +} + void rte_eth_dev_info_get(uint8_t port_id, struct rte_eth_dev_info *dev_info) { @@ -1785,7 +1678,6 @@ rte_eth_dev_info_get(uint8_t port_id, struct rte_eth_dev_info *dev_info) RTE_FUNC_PTR_OR_RET(*dev->dev_ops->dev_infos_get); (*dev->dev_ops->dev_infos_get)(dev, dev_info); - dev_info->pci_dev = dev->pci_dev; dev_info->driver_name = dev->data->drv_name; dev_info->nb_rx_queues = dev->data->nb_rx_queues; dev_info->nb_tx_queues = dev->data->nb_tx_queues; @@ -2354,32 +2246,6 @@ rte_eth_dev_default_mac_addr_set(uint8_t port_id, struct ether_addr *addr) return 0; } -int -rte_eth_dev_set_vf_rxmode(uint8_t port_id, uint16_t vf, - uint16_t rx_mode, uint8_t on) -{ - uint16_t num_vfs; - struct rte_eth_dev *dev; - struct rte_eth_dev_info dev_info; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); - - dev = &rte_eth_devices[port_id]; - rte_eth_dev_info_get(port_id, &dev_info); - - num_vfs = dev_info.max_vfs; - if (vf > num_vfs) { - RTE_PMD_DEBUG_TRACE("set VF RX mode:invalid VF id %d\n", vf); - return -EINVAL; - } - - if (rx_mode == 0) { - RTE_PMD_DEBUG_TRACE("set VF RX mode:mode mask ca not be zero\n"); - return -EINVAL; - } - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->set_vf_rx_mode, -ENOTSUP); - return (*dev->dev_ops->set_vf_rx_mode)(dev, vf, rx_mode, on); -} /* * Returns index into MAC address array of addr. Use 00:00:00:00:00:00 to find @@ -2469,76 +2335,6 @@ rte_eth_dev_uc_all_hash_table_set(uint8_t port_id, uint8_t on) return (*dev->dev_ops->uc_all_hash_table_set)(dev, on); } -int -rte_eth_dev_set_vf_rx(uint8_t port_id, uint16_t vf, uint8_t on) -{ - uint16_t num_vfs; - struct rte_eth_dev *dev; - struct rte_eth_dev_info dev_info; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); - - dev = &rte_eth_devices[port_id]; - rte_eth_dev_info_get(port_id, &dev_info); - - num_vfs = dev_info.max_vfs; - if (vf > num_vfs) { - RTE_PMD_DEBUG_TRACE("port %d: invalid vf id\n", port_id); - return -EINVAL; - } - - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->set_vf_rx, -ENOTSUP); - return (*dev->dev_ops->set_vf_rx)(dev, vf, on); -} - -int -rte_eth_dev_set_vf_tx(uint8_t port_id, uint16_t vf, uint8_t on) -{ - uint16_t num_vfs; - struct rte_eth_dev *dev; - struct rte_eth_dev_info dev_info; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); - - dev = &rte_eth_devices[port_id]; - rte_eth_dev_info_get(port_id, &dev_info); - - num_vfs = dev_info.max_vfs; - if (vf > num_vfs) { - RTE_PMD_DEBUG_TRACE("set pool tx:invalid pool id=%d\n", vf); - return -EINVAL; - } - - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->set_vf_tx, -ENOTSUP); - return (*dev->dev_ops->set_vf_tx)(dev, vf, on); -} - -int -rte_eth_dev_set_vf_vlan_filter(uint8_t port_id, uint16_t vlan_id, - uint64_t vf_mask, uint8_t vlan_on) -{ - struct rte_eth_dev *dev; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); - - dev = &rte_eth_devices[port_id]; - - if (vlan_id > ETHER_MAX_VLAN_ID) { - RTE_PMD_DEBUG_TRACE("VF VLAN filter:invalid VLAN id=%d\n", - vlan_id); - return -EINVAL; - } - - if (vf_mask == 0) { - RTE_PMD_DEBUG_TRACE("VF VLAN filter:pool_mask can not be 0\n"); - return -EINVAL; - } - - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->set_vf_vlan_filter, -ENOTSUP); - return (*dev->dev_ops->set_vf_vlan_filter)(dev, vlan_id, - vf_mask, vlan_on); -} - int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx, uint16_t tx_rate) { @@ -2569,45 +2365,12 @@ int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx, return (*dev->dev_ops->set_queue_rate_limit)(dev, queue_idx, tx_rate); } -int rte_eth_set_vf_rate_limit(uint8_t port_id, uint16_t vf, uint16_t tx_rate, - uint64_t q_msk) -{ - struct rte_eth_dev *dev; - struct rte_eth_dev_info dev_info; - struct rte_eth_link link; - - if (q_msk == 0) - return 0; - - RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); - - dev = &rte_eth_devices[port_id]; - rte_eth_dev_info_get(port_id, &dev_info); - link = dev->data->dev_link; - - if (vf > dev_info.max_vfs) { - RTE_PMD_DEBUG_TRACE("set VF rate limit:port %d: " - "invalid vf id=%d\n", port_id, vf); - return -EINVAL; - } - - if (tx_rate > link.link_speed) { - RTE_PMD_DEBUG_TRACE("set VF rate limit:invalid tx_rate=%d, " - "bigger than link speed= %d\n", - tx_rate, link.link_speed); - return -EINVAL; - } - - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->set_vf_rate_limit, -ENOTSUP); - return (*dev->dev_ops->set_vf_rate_limit)(dev, vf, tx_rate, q_msk); -} - int rte_eth_mirror_rule_set(uint8_t port_id, struct rte_eth_mirror_conf *mirror_conf, uint8_t rule_id, uint8_t on) { - struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + struct rte_eth_dev *dev; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); if (mirror_conf->rule_type == 0) { @@ -2643,7 +2406,7 @@ rte_eth_mirror_rule_set(uint8_t port_id, int rte_eth_mirror_rule_reset(uint8_t port_id, uint8_t rule_id) { - struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + struct rte_eth_dev *dev; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); @@ -2678,14 +2441,15 @@ rte_eth_dev_callback_register(uint8_t port_id, } /* create a new callback. */ - if (user_cb == NULL) + if (user_cb == NULL) { user_cb = rte_zmalloc("INTR_USER_CALLBACK", sizeof(struct rte_eth_dev_callback), 0); - if (user_cb != NULL) { - user_cb->cb_fn = cb_fn; - user_cb->cb_arg = cb_arg; - user_cb->event = event; - TAILQ_INSERT_TAIL(&(dev->link_intr_cbs), user_cb, next); + if (user_cb != NULL) { + user_cb->cb_fn = cb_fn; + user_cb->cb_arg = cb_arg; + user_cb->event = event; + TAILQ_INSERT_TAIL(&(dev->link_intr_cbs), user_cb, next); + } } rte_spinlock_unlock(&rte_eth_dev_cb_lock); @@ -2737,7 +2501,7 @@ rte_eth_dev_callback_unregister(uint8_t port_id, void _rte_eth_dev_callback_process(struct rte_eth_dev *dev, - enum rte_eth_event_type event) + enum rte_eth_event_type event, void *cb_arg) { struct rte_eth_dev_callback *cb_lst; struct rte_eth_dev_callback dev_cb; @@ -2748,6 +2512,9 @@ _rte_eth_dev_callback_process(struct rte_eth_dev *dev, continue; dev_cb = *cb_lst; cb_lst->active = 1; + if (cb_arg != NULL) + dev_cb.cb_arg = (void *) cb_arg; + rte_spinlock_unlock(&rte_eth_dev_cb_lock); dev_cb.cb_fn(dev->data->port_id, dev_cb.event, dev_cb.cb_arg); @@ -2769,7 +2536,13 @@ rte_eth_dev_rx_intr_ctl(uint8_t port_id, int epfd, int op, void *data) RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); dev = &rte_eth_devices[port_id]; - intr_handle = &dev->pci_dev->intr_handle; + + if (!dev->intr_handle) { + RTE_PMD_DEBUG_TRACE("RX Intr handle unset\n"); + return -ENOTSUP; + } + + intr_handle = dev->intr_handle; if (!intr_handle->intr_vec) { RTE_PMD_DEBUG_TRACE("RX Intr vector unset\n"); return -EPERM; @@ -2797,7 +2570,7 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name, const struct rte_memzone *mz; snprintf(z_name, sizeof(z_name), "%s_%s_%d_%d", - dev->driver->pci_drv.name, ring_name, + dev->data->drv_name, ring_name, dev->data->port_id, queue_id); mz = rte_memzone_lookup(z_name); @@ -2829,7 +2602,12 @@ rte_eth_dev_rx_intr_ctl_q(uint8_t port_id, uint16_t queue_id, return -EINVAL; } - intr_handle = &dev->pci_dev->intr_handle; + if (!dev->intr_handle) { + RTE_PMD_DEBUG_TRACE("RX Intr handle unset\n"); + return -ENOTSUP; + } + + intr_handle = dev->intr_handle; if (!intr_handle->intr_vec) { RTE_PMD_DEBUG_TRACE("RX Intr vector unset\n"); return -EPERM; @@ -3431,15 +3209,15 @@ rte_eth_copy_pci_info(struct rte_eth_dev *eth_dev, struct rte_pci_device *pci_de return; } + eth_dev->intr_handle = &pci_dev->intr_handle; + eth_dev->data->dev_flags = 0; if (pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC) eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC; - if (pci_dev->driver->drv_flags & RTE_PCI_DRV_DETACHABLE) - eth_dev->data->dev_flags |= RTE_ETH_DEV_DETACHABLE; eth_dev->data->kdrv = pci_dev->kdrv; - eth_dev->data->numa_node = pci_dev->numa_node; - eth_dev->data->drv_name = pci_dev->driver->name; + eth_dev->data->numa_node = pci_dev->device.numa_node; + eth_dev->data->drv_name = pci_dev->driver->driver.name; } int diff --git a/src/dpdk/lib/librte_ether/rte_ethdev.h b/src/dpdk/lib/librte_ether/rte_ethdev.h index 5339d3be..c17bbda8 100644 --- a/src/dpdk/lib/librte_ether/rte_ethdev.h +++ b/src/dpdk/lib/librte_ether/rte_ethdev.h @@ -182,6 +182,7 @@ extern "C" { #include <rte_pci.h> #include <rte_dev.h> #include <rte_devargs.h> +#include <rte_errno.h> #include "rte_ether.h" #include "rte_eth_ctrl.h" #include "rte_dev_info.h" @@ -190,6 +191,9 @@ struct rte_mbuf; /** * A structure used to retrieve statistics for an Ethernet port. + * Not all statistics fields in struct rte_eth_stats are supported + * by any type of network interface card (NIC). If any statistics + * field is not supported, its value is 0. */ struct rte_eth_stats { uint64_t ipackets; /**< Total number of successfully received packets. */ @@ -198,7 +202,7 @@ struct rte_eth_stats { uint64_t obytes; /**< Total number of successfully transmitted bytes. */ uint64_t imissed; /**< Total of RX packets dropped by the HW, - * because there are no available mbufs (i.e. RX queues are full). + * because there are no available buffer (i.e. RX queues are full). */ uint64_t ierrors; /**< Total number of erroneous received packets. */ uint64_t oerrors; /**< Total number of failed transmitted packets. */ @@ -255,6 +259,7 @@ struct rte_eth_stats { /** * A structure used to retrieve link-level information of an Ethernet port. */ +__extension__ struct rte_eth_link { uint32_t link_speed; /**< ETH_SPEED_NUM_ */ uint16_t link_duplex : 1; /**< ETH_LINK_[HALF/FULL]_DUPLEX */ @@ -346,6 +351,7 @@ struct rte_eth_rxmode { enum rte_eth_rx_mq_mode mq_mode; uint32_t max_rx_pkt_len; /**< Only used if jumbo_frame enabled. */ uint16_t split_hdr_size; /**< hdr buf size (header_split enabled).*/ + __extension__ uint16_t header_split : 1, /**< Header Split enable. */ hw_ip_checksum : 1, /**< IP/UDP/TCP checksum offload enable. */ hw_vlan_filter : 1, /**< VLAN filter enable. */ @@ -645,6 +651,7 @@ struct rte_eth_txmode { /* For i40e specifically */ uint16_t pvid; + __extension__ uint8_t hw_vlan_reject_tagged : 1, /**< If set, reject sending out tagged pkts */ hw_vlan_reject_untagged : 1, @@ -696,6 +703,29 @@ struct rte_eth_desc_lim { uint16_t nb_max; /**< Max allowed number of descriptors. */ uint16_t nb_min; /**< Min allowed number of descriptors. */ uint16_t nb_align; /**< Number of descriptors should be aligned to. */ + + /** + * Max allowed number of segments per whole packet. + * + * - For TSO packet this is the total number of data descriptors allowed + * by device. + * + * @see nb_mtu_seg_max + */ + uint16_t nb_seg_max; + + /** + * Max number of segments per one MTU. + * + * - For non-TSO packet, this is the maximum allowed number of segments + * in a single transmit packet. + * + * - For TSO packet each segment within the TSO may span up to this + * value. + * + * @see nb_seg_max + */ + uint16_t nb_mtu_seg_max; }; /** @@ -767,8 +797,6 @@ struct rte_fdir_conf { struct rte_eth_fdir_masks mask; struct rte_eth_fdir_flex_conf flex_conf; /**< Flex payload configuration. */ - // TREX_PATCH - uint8_t flexbytes_offset; }; /** @@ -853,6 +881,7 @@ struct rte_eth_conf { #define DEV_RX_OFFLOAD_TCP_LRO 0x00000010 #define DEV_RX_OFFLOAD_QINQ_STRIP 0x00000020 #define DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM 0x00000040 +#define DEV_RX_OFFLOAD_MACSEC_STRIP 0x00000080 /** * TX offload capabilities of a device. @@ -866,6 +895,11 @@ struct rte_eth_conf { #define DEV_TX_OFFLOAD_UDP_TSO 0x00000040 #define DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM 0x00000080 /**< Used for tunneling packet. */ #define DEV_TX_OFFLOAD_QINQ_INSERT 0x00000100 +#define DEV_TX_OFFLOAD_VXLAN_TNL_TSO 0x00000200 /**< Used for tunneling packet. */ +#define DEV_TX_OFFLOAD_GRE_TNL_TSO 0x00000400 /**< Used for tunneling packet. */ +#define DEV_TX_OFFLOAD_IPIP_TNL_TSO 0x00000800 /**< Used for tunneling packet. */ +#define DEV_TX_OFFLOAD_GENEVE_TNL_TSO 0x00001000 /**< Used for tunneling packet. */ +#define DEV_TX_OFFLOAD_MACSEC_INSERT 0x00002000 /** * Ethernet device information @@ -930,23 +964,26 @@ struct rte_eth_txq_info { /** * An Ethernet device extended statistic structure * - * This structure is used by ethdev->eth_xstats_get() to provide - * statistics that are not provided in the generic rte_eth_stats + * This structure is used by rte_eth_xstats_get() to provide + * statistics that are not provided in the generic *rte_eth_stats* * structure. + * It maps a name id, corresponding to an index in the array returned + * by rte_eth_xstats_get_names(), to a statistic value. */ struct rte_eth_xstat { - uint64_t id; - uint64_t value; + uint64_t id; /**< The index in xstats name array. */ + uint64_t value; /**< The statistic counter value. */ }; /** - * A name-key lookup element for extended statistics. + * A name element for extended statistics. * - * This structure is used to map between names and ID numbers - * for extended ethernet statistics. + * An array of this structure is returned by rte_eth_xstats_get_names(). + * It lists the names of extended statistics for a PMD. The *rte_eth_xstat* + * structure references these names by their array index. */ struct rte_eth_xstat_name { - char name[RTE_ETH_XSTATS_NAME_SIZE]; + char name[RTE_ETH_XSTATS_NAME_SIZE]; /**< The statistic name. */ }; #define ETH_DCB_NUM_TCS 8 @@ -1142,6 +1179,10 @@ typedef uint32_t (*eth_rx_queue_count_t)(struct rte_eth_dev *dev, typedef int (*eth_rx_descriptor_done_t)(void *rxq, uint16_t offset); /**< @internal Check DD bit of specific RX descriptor */ +typedef int (*eth_fw_version_get_t)(struct rte_eth_dev *dev, + char *fw_version, size_t fw_size); +/**< @internal Get firmware information of an Ethernet device. */ + typedef void (*eth_rxq_info_get_t)(struct rte_eth_dev *dev, uint16_t rx_queue_id, struct rte_eth_rxq_info *qinfo); @@ -1183,6 +1224,11 @@ typedef uint16_t (*eth_tx_burst_t)(void *txq, uint16_t nb_pkts); /**< @internal Send output packets on a transmit queue of an Ethernet device. */ +typedef uint16_t (*eth_tx_prep_t)(void *txq, + struct rte_mbuf **tx_pkts, + uint16_t nb_pkts); +/**< @internal Prepare output packets on a transmit queue of an Ethernet device. */ + typedef int (*flow_ctrl_get_t)(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf); /**< @internal Get current flow control parameter on an Ethernet device */ @@ -1241,39 +1287,11 @@ typedef int (*eth_uc_all_hash_table_set_t)(struct rte_eth_dev *dev, uint8_t on); /**< @internal Set all Unicast Hash bitmap */ -typedef int (*eth_set_vf_rx_mode_t)(struct rte_eth_dev *dev, - uint16_t vf, - uint16_t rx_mode, - uint8_t on); -/**< @internal Set a VF receive mode */ - -typedef int (*eth_set_vf_rx_t)(struct rte_eth_dev *dev, - uint16_t vf, - uint8_t on); -/**< @internal Set a VF receive mode */ - -typedef int (*eth_set_vf_tx_t)(struct rte_eth_dev *dev, - uint16_t vf, - uint8_t on); -/**< @internal Enable or disable a VF transmit */ - -typedef int (*eth_set_vf_vlan_filter_t)(struct rte_eth_dev *dev, - uint16_t vlan, - uint64_t vf_mask, - uint8_t vlan_on); -/**< @internal Set VF VLAN pool filter */ - typedef int (*eth_set_queue_rate_limit_t)(struct rte_eth_dev *dev, uint16_t queue_idx, uint16_t tx_rate); /**< @internal Set queue TX rate */ -typedef int (*eth_set_vf_rate_limit_t)(struct rte_eth_dev *dev, - uint16_t vf, - uint16_t tx_rate, - uint64_t q_msk); -/**< @internal Set VF TX rate */ - typedef int (*eth_mirror_rule_set_t)(struct rte_eth_dev *dev, struct rte_eth_mirror_conf *mirror_conf, uint8_t rule_id, @@ -1423,11 +1441,18 @@ struct eth_dev_ops { eth_dev_set_link_up_t dev_set_link_up; /**< Device link up. */ eth_dev_set_link_down_t dev_set_link_down; /**< Device link down. */ eth_dev_close_t dev_close; /**< Close device. */ + eth_link_update_t link_update; /**< Get device link state. */ + eth_promiscuous_enable_t promiscuous_enable; /**< Promiscuous ON. */ eth_promiscuous_disable_t promiscuous_disable;/**< Promiscuous OFF. */ eth_allmulticast_enable_t allmulticast_enable;/**< RX multicast ON. */ eth_allmulticast_disable_t allmulticast_disable;/**< RX multicast OF. */ - eth_link_update_t link_update; /**< Get device link state. */ + eth_mac_addr_remove_t mac_addr_remove; /**< Remove MAC address. */ + eth_mac_addr_add_t mac_addr_add; /**< Add a MAC address. */ + eth_mac_addr_set_t mac_addr_set; /**< Set a MAC address. */ + eth_set_mc_addr_list_t set_mc_addr_list; /**< set list of mcast addrs. */ + mtu_set_t mtu_set; /**< Set MTU. */ + eth_stats_get_t stats_get; /**< Get generic device statistics. */ eth_stats_reset_t stats_reset; /**< Reset generic device statistics. */ eth_xstats_get_t xstats_get; /**< Get extended device statistics. */ @@ -1436,109 +1461,93 @@ struct eth_dev_ops { /**< Get names of extended statistics. */ eth_queue_stats_mapping_set_t queue_stats_mapping_set; /**< Configure per queue stat counter mapping. */ + eth_dev_infos_get_t dev_infos_get; /**< Get device info. */ + eth_rxq_info_get_t rxq_info_get; /**< retrieve RX queue information. */ + eth_txq_info_get_t txq_info_get; /**< retrieve TX queue information. */ + eth_fw_version_get_t fw_version_get; /**< Get firmware version. */ eth_dev_supported_ptypes_get_t dev_supported_ptypes_get; - /**< Get packet types supported and identified by device*/ - mtu_set_t mtu_set; /**< Set MTU. */ - vlan_filter_set_t vlan_filter_set; /**< Filter VLAN Setup. */ - vlan_tpid_set_t vlan_tpid_set; /**< Outer/Inner VLAN TPID Setup. */ + /**< Get packet types supported and identified by device. */ + + vlan_filter_set_t vlan_filter_set; /**< Filter VLAN Setup. */ + vlan_tpid_set_t vlan_tpid_set; /**< Outer/Inner VLAN TPID Setup. */ vlan_strip_queue_set_t vlan_strip_queue_set; /**< VLAN Stripping on queue. */ vlan_offload_set_t vlan_offload_set; /**< Set VLAN Offload. */ - vlan_pvid_set_t vlan_pvid_set; /**< Set port based TX VLAN insertion */ - eth_queue_start_t rx_queue_start;/**< Start RX for a queue.*/ - eth_queue_stop_t rx_queue_stop;/**< Stop RX for a queue.*/ - eth_queue_start_t tx_queue_start;/**< Start TX for a queue.*/ - eth_queue_stop_t tx_queue_stop;/**< Stop TX for a queue.*/ - eth_rx_queue_setup_t rx_queue_setup;/**< Set up device RX queue.*/ - eth_queue_release_t rx_queue_release;/**< Release RX queue.*/ - eth_rx_queue_count_t rx_queue_count; /**< Get Rx queue count. */ - eth_rx_descriptor_done_t rx_descriptor_done; /**< Check rxd DD bit */ - /**< Enable Rx queue interrupt. */ - eth_rx_enable_intr_t rx_queue_intr_enable; - /**< Disable Rx queue interrupt.*/ - eth_rx_disable_intr_t rx_queue_intr_disable; - eth_tx_queue_setup_t tx_queue_setup;/**< Set up device TX queue.*/ - eth_queue_release_t tx_queue_release;/**< Release TX queue.*/ + vlan_pvid_set_t vlan_pvid_set; /**< Set port based TX VLAN insertion. */ + + eth_queue_start_t rx_queue_start;/**< Start RX for a queue. */ + eth_queue_stop_t rx_queue_stop; /**< Stop RX for a queue. */ + eth_queue_start_t tx_queue_start;/**< Start TX for a queue. */ + eth_queue_stop_t tx_queue_stop; /**< Stop TX for a queue. */ + eth_rx_queue_setup_t rx_queue_setup;/**< Set up device RX queue. */ + eth_queue_release_t rx_queue_release; /**< Release RX queue. */ + eth_rx_queue_count_t rx_queue_count;/**< Get Rx queue count. */ + eth_rx_descriptor_done_t rx_descriptor_done; /**< Check rxd DD bit. */ + eth_rx_enable_intr_t rx_queue_intr_enable; /**< Enable Rx queue interrupt. */ + eth_rx_disable_intr_t rx_queue_intr_disable; /**< Disable Rx queue interrupt. */ + eth_tx_queue_setup_t tx_queue_setup;/**< Set up device TX queue. */ + eth_queue_release_t tx_queue_release; /**< Release TX queue. */ + eth_dev_led_on_t dev_led_on; /**< Turn on LED. */ eth_dev_led_off_t dev_led_off; /**< Turn off LED. */ + flow_ctrl_get_t flow_ctrl_get; /**< Get flow control. */ flow_ctrl_set_t flow_ctrl_set; /**< Setup flow control. */ - priority_flow_ctrl_set_t priority_flow_ctrl_set; /**< Setup priority flow control.*/ - eth_mac_addr_remove_t mac_addr_remove; /**< Remove MAC address */ - eth_mac_addr_add_t mac_addr_add; /**< Add a MAC address */ - eth_mac_addr_set_t mac_addr_set; /**< Set a MAC address */ - eth_uc_hash_table_set_t uc_hash_table_set; /**< Set Unicast Table Array */ - eth_uc_all_hash_table_set_t uc_all_hash_table_set; /**< Set Unicast hash bitmap */ - eth_mirror_rule_set_t mirror_rule_set; /**< Add a traffic mirror rule.*/ - eth_mirror_rule_reset_t mirror_rule_reset; /**< reset a traffic mirror rule.*/ - eth_set_vf_rx_mode_t set_vf_rx_mode; /**< Set VF RX mode */ - eth_set_vf_rx_t set_vf_rx; /**< enable/disable a VF receive */ - eth_set_vf_tx_t set_vf_tx; /**< enable/disable a VF transmit */ - eth_set_vf_vlan_filter_t set_vf_vlan_filter; /**< Set VF VLAN filter */ - /** Add UDP tunnel port. */ - eth_udp_tunnel_port_add_t udp_tunnel_port_add; - /** Del UDP tunnel port. */ - eth_udp_tunnel_port_del_t udp_tunnel_port_del; - eth_set_queue_rate_limit_t set_queue_rate_limit; /**< Set queue rate limit */ - eth_set_vf_rate_limit_t set_vf_rate_limit; /**< Set VF rate limit */ - /** Update redirection table. */ - reta_update_t reta_update; - /** Query redirection table. */ - reta_query_t reta_query; - - eth_get_reg_t get_reg; - /**< Get registers */ - eth_get_eeprom_length_t get_eeprom_length; - /**< Get eeprom length */ - eth_get_eeprom_t get_eeprom; - /**< Get eeprom data */ - eth_set_eeprom_t set_eeprom; - /**< Set eeprom */ - /* bypass control */ + priority_flow_ctrl_set_t priority_flow_ctrl_set; /**< Setup priority flow control. */ + + eth_uc_hash_table_set_t uc_hash_table_set; /**< Set Unicast Table Array. */ + eth_uc_all_hash_table_set_t uc_all_hash_table_set; /**< Set Unicast hash bitmap. */ + + eth_mirror_rule_set_t mirror_rule_set; /**< Add a traffic mirror rule. */ + eth_mirror_rule_reset_t mirror_rule_reset; /**< reset a traffic mirror rule. */ + + eth_udp_tunnel_port_add_t udp_tunnel_port_add; /** Add UDP tunnel port. */ + eth_udp_tunnel_port_del_t udp_tunnel_port_del; /** Del UDP tunnel port. */ + eth_l2_tunnel_eth_type_conf_t l2_tunnel_eth_type_conf; + /** Config ether type of l2 tunnel. */ + eth_l2_tunnel_offload_set_t l2_tunnel_offload_set; + /** Enable/disable l2 tunnel offload functions. */ + + eth_set_queue_rate_limit_t set_queue_rate_limit; /**< Set queue rate limit. */ + + rss_hash_update_t rss_hash_update; /** Configure RSS hash protocols. */ + rss_hash_conf_get_t rss_hash_conf_get; /** Get current RSS hash configuration. */ + reta_update_t reta_update; /** Update redirection table. */ + reta_query_t reta_query; /** Query redirection table. */ + + eth_get_reg_t get_reg; /**< Get registers. */ + eth_get_eeprom_length_t get_eeprom_length; /**< Get eeprom length. */ + eth_get_eeprom_t get_eeprom; /**< Get eeprom data. */ + eth_set_eeprom_t set_eeprom; /**< Set eeprom. */ + + /* bypass control */ #ifdef RTE_NIC_BYPASS - bypass_init_t bypass_init; - bypass_state_set_t bypass_state_set; - bypass_state_show_t bypass_state_show; - bypass_event_set_t bypass_event_set; - bypass_event_show_t bypass_event_show; - bypass_wd_timeout_set_t bypass_wd_timeout_set; - bypass_wd_timeout_show_t bypass_wd_timeout_show; - bypass_ver_show_t bypass_ver_show; - bypass_wd_reset_t bypass_wd_reset; + bypass_init_t bypass_init; + bypass_state_set_t bypass_state_set; + bypass_state_show_t bypass_state_show; + bypass_event_set_t bypass_event_set; + bypass_event_show_t bypass_event_show; + bypass_wd_timeout_set_t bypass_wd_timeout_set; + bypass_wd_timeout_show_t bypass_wd_timeout_show; + bypass_ver_show_t bypass_ver_show; + bypass_wd_reset_t bypass_wd_reset; #endif - /** Configure RSS hash protocols. */ - rss_hash_update_t rss_hash_update; - /** Get current RSS hash configuration. */ - rss_hash_conf_get_t rss_hash_conf_get; - eth_filter_ctrl_t filter_ctrl; - /**< common filter control. */ - eth_set_mc_addr_list_t set_mc_addr_list; /**< set list of mcast addrs */ - eth_rxq_info_get_t rxq_info_get; - /**< retrieve RX queue information. */ - eth_txq_info_get_t txq_info_get; - /**< retrieve TX queue information. */ + eth_filter_ctrl_t filter_ctrl; /**< common filter control. */ + + eth_get_dcb_info get_dcb_info; /** Get DCB information. */ + + eth_timesync_enable_t timesync_enable; /** Turn IEEE1588/802.1AS timestamping on. */ - eth_timesync_enable_t timesync_enable; + eth_timesync_disable_t timesync_disable; /** Turn IEEE1588/802.1AS timestamping off. */ - eth_timesync_disable_t timesync_disable; - /** Read the IEEE1588/802.1AS RX timestamp. */ eth_timesync_read_rx_timestamp_t timesync_read_rx_timestamp; - /** Read the IEEE1588/802.1AS TX timestamp. */ + /** Read the IEEE1588/802.1AS RX timestamp. */ eth_timesync_read_tx_timestamp_t timesync_read_tx_timestamp; - - /** Get DCB information */ - eth_get_dcb_info get_dcb_info; - /** Adjust the device clock.*/ - eth_timesync_adjust_time timesync_adjust_time; - /** Get the device clock time. */ - eth_timesync_read_time timesync_read_time; - /** Set the device clock time. */ - eth_timesync_write_time timesync_write_time; - /** Config ether type of l2 tunnel */ - eth_l2_tunnel_eth_type_conf_t l2_tunnel_eth_type_conf; - /** Enable/disable l2 tunnel offload functions */ - eth_l2_tunnel_offload_set_t l2_tunnel_offload_set; + /** Read the IEEE1588/802.1AS TX timestamp. */ + eth_timesync_adjust_time timesync_adjust_time; /** Adjust the device clock. */ + eth_timesync_read_time timesync_read_time; /** Get the device clock time. */ + eth_timesync_write_time timesync_write_time; /** Set the device clock time. */ }; /** @@ -1605,17 +1614,6 @@ struct rte_eth_rxtx_callback { }; /** - * The eth device type. - */ -enum rte_eth_dev_type { - RTE_ETH_DEV_UNKNOWN, /**< unknown device type */ - RTE_ETH_DEV_PCI, - /**< Physical function and Virtual function of PCI devices */ - RTE_ETH_DEV_VIRTUAL, /**< non hardware device */ - RTE_ETH_DEV_MAX /**< max value of this enum */ -}; - -/** * @internal * The generic data structure associated with each ethernet device. * @@ -1628,10 +1626,12 @@ enum rte_eth_dev_type { struct rte_eth_dev { eth_rx_burst_t rx_pkt_burst; /**< Pointer to PMD receive function. */ eth_tx_burst_t tx_pkt_burst; /**< Pointer to PMD transmit function. */ + eth_tx_prep_t tx_pkt_prepare; /**< Pointer to PMD transmit prepare function. */ struct rte_eth_dev_data *data; /**< Pointer to device data */ const struct eth_driver *driver;/**< Driver for this device */ const struct eth_dev_ops *dev_ops; /**< Functions exported by PMD */ - struct rte_pci_device *pci_dev; /**< PCI info. supplied by probing */ + struct rte_device *device; /**< Backing device */ + struct rte_intr_handle *intr_handle; /**< Device interrupt handle */ /** User application callbacks for NIC interrupts */ struct rte_eth_dev_cb_list link_intr_cbs; /** @@ -1645,7 +1645,6 @@ struct rte_eth_dev { */ struct rte_eth_rxtx_callback *pre_tx_burst_cbs[RTE_MAX_QUEUES_PER_PORT]; uint8_t attached; /**< Flag indicating the port is attached */ - enum rte_eth_dev_type dev_type; /**< Flag indicating the device type */ } __rte_cache_aligned; struct rte_eth_dev_sriov { @@ -1693,6 +1692,7 @@ struct rte_eth_dev_data { struct ether_addr* hash_mac_addrs; /** Device Ethernet MAC addresses of hash filtering. */ uint8_t port_id; /**< Device [external] port identifier. */ + __extension__ uint8_t promiscuous : 1, /**< RX promiscuous mode ON(1) / OFF(0). */ scattered_rx : 1, /**< RX of scattered packets is ON(1) / OFF(0) */ all_multicast : 1, /**< RX all multicast mode ON(1) / OFF(0). */ @@ -1758,8 +1758,7 @@ struct rte_eth_dev *rte_eth_dev_allocated(const char *name); * @return * - Slot in the rte_dev_devices array for a new device; */ -struct rte_eth_dev *rte_eth_dev_allocate(const char *name, - enum rte_eth_dev_type type); +struct rte_eth_dev *rte_eth_dev_allocate(const char *name); /** * @internal @@ -1778,7 +1777,7 @@ int rte_eth_dev_release_port(struct rte_eth_dev *eth_dev); * @param devargs * A pointer to a strings array describing the new device * to be attached. The strings should be a pci address like - * '0000:01:00.0' or virtual device name like 'eth_pcap0'. + * '0000:01:00.0' or virtual device name like 'net_pcap0'. * @param port_id * A pointer to a port identifier actually attached. * @return @@ -1873,18 +1872,6 @@ struct eth_driver { }; /** - * @internal - * A function invoked by the initialization function of an Ethernet driver - * to simultaneously register itself as a PCI driver and as an Ethernet - * Poll Mode Driver (PMD). - * - * @param eth_drv - * The pointer to the *eth_driver* structure associated with - * the Ethernet driver. - */ -void rte_eth_driver_register(struct eth_driver *eth_drv); - -/** * Convert a numerical speed in Mbps to a bitmap flag that can be used in * the bitmap link_speeds of the struct rte_eth_conf * @@ -1930,6 +1917,19 @@ int rte_eth_dev_configure(uint8_t port_id, uint16_t nb_rx_queue, uint16_t nb_tx_queue, const struct rte_eth_conf *eth_conf); /** + * @internal + * Release device queues and clear its configuration to force the user + * application to reconfigure it. It is for internal use only. + * + * @param dev + * Pointer to struct rte_eth_dev. + * + * @return + * void + */ +void _rte_eth_dev_reset(struct rte_eth_dev *dev); + +/** * Allocate and set up a receive queue for an Ethernet device. * * The function allocates a contiguous block of memory for *nb_rx_desc* @@ -2288,18 +2288,19 @@ void rte_eth_stats_reset(uint8_t port_id); * @param port_id * The port identifier of the Ethernet device. * @param xstats_names - * Block of memory to insert names into. Must be at least size in capacity. - * If set to NULL, function returns required capacity. + * An rte_eth_xstat_name array of at least *size* elements to + * be filled. If set to NULL, the function returns the required number + * of elements. * @param size - * Capacity of xstats_names (number of names). + * The size of the xstats_names array (number of elements). * @return - * - positive value lower or equal to size: success. The return value + * - A positive value lower or equal to size: success. The return value * is the number of entries filled in the stats table. - * - positive value higher than size: error, the given statistics table + * - A positive value higher than size: error, the given statistics table * is too small. The return value corresponds to the size that should * be given to succeed. The entries in the table are not valid and * shall not be used by the caller. - * - negative value on error (invalid port id) + * - A negative value on error (invalid port id). */ int rte_eth_xstats_get_names(uint8_t port_id, struct rte_eth_xstat_name *xstats_names, @@ -2312,19 +2313,20 @@ int rte_eth_xstats_get_names(uint8_t port_id, * The port identifier of the Ethernet device. * @param xstats * A pointer to a table of structure of type *rte_eth_xstat* - * to be filled with device statistics ids and values. + * to be filled with device statistics ids and values: id is the + * index of the name string in xstats_names (see rte_eth_xstats_get_names()), + * and value is the statistic counter. * This parameter can be set to NULL if n is 0. * @param n - * The size of the stats table, which should be large enough to store - * all the statistics of the device. + * The size of the xstats array (number of elements). * @return - * - positive value lower or equal to n: success. The return value + * - A positive value lower or equal to n: success. The return value * is the number of entries filled in the stats table. - * - positive value higher than n: error, the given statistics table + * - A positive value higher than n: error, the given statistics table * is too small. The return value corresponds to the size that should * be given to succeed. The entries in the table are not valid and * shall not be used by the caller. - * - negative value on error (invalid port id) + * - A negative value on error (invalid port id). */ int rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, unsigned n); @@ -2401,6 +2403,27 @@ void rte_eth_macaddr_get(uint8_t port_id, struct ether_addr *mac_addr); void rte_eth_dev_info_get(uint8_t port_id, struct rte_eth_dev_info *dev_info); /** + * Retrieve the firmware version of a device. + * + * @param port_id + * The port identifier of the device. + * @param fw_version + * A pointer to a string array storing the firmware version of a device, + * the string includes terminating null. This pointer is allocated by caller. + * @param fw_size + * The size of the string array pointed by fw_version, which should be + * large enough to store firmware version of the device. + * @return + * - (0) if successful. + * - (-ENOTSUP) if operation is not supported. + * - (-ENODEV) if *port_id* invalid. + * - (>0) if *fw_size* is not enough to store firmware version, return + * the size of the non truncated string. + */ +int rte_eth_dev_fw_version_get(uint8_t port_id, + char *fw_version, size_t fw_size); + +/** * Retrieve the supported packet types of an Ethernet device. * * When a packet type is announced as supported, it *must* be recognized by @@ -2835,6 +2858,115 @@ rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id, return (*dev->tx_pkt_burst)(dev->data->tx_queues[queue_id], tx_pkts, nb_pkts); } +/** + * @warning + * @b EXPERIMENTAL: this API may change without prior notice + * + * Process a burst of output packets on a transmit queue of an Ethernet device. + * + * The rte_eth_tx_prepare() function is invoked to prepare output packets to be + * transmitted on the output queue *queue_id* of the Ethernet device designated + * by its *port_id*. + * The *nb_pkts* parameter is the number of packets to be prepared which are + * supplied in the *tx_pkts* array of *rte_mbuf* structures, each of them + * allocated from a pool created with rte_pktmbuf_pool_create(). + * For each packet to send, the rte_eth_tx_prepare() function performs + * the following operations: + * + * - Check if packet meets devices requirements for tx offloads. + * + * - Check limitations about number of segments. + * + * - Check additional requirements when debug is enabled. + * + * - Update and/or reset required checksums when tx offload is set for packet. + * + * Since this function can modify packet data, provided mbufs must be safely + * writable (e.g. modified data cannot be in shared segment). + * + * The rte_eth_tx_prepare() function returns the number of packets ready to be + * sent. A return value equal to *nb_pkts* means that all packets are valid and + * ready to be sent, otherwise stops processing on the first invalid packet and + * leaves the rest packets untouched. + * + * When this functionality is not implemented in the driver, all packets are + * are returned untouched. + * + * @param port_id + * The port identifier of the Ethernet device. + * The value must be a valid port id. + * @param queue_id + * The index of the transmit queue through which output packets must be + * sent. + * The value must be in the range [0, nb_tx_queue - 1] previously supplied + * to rte_eth_dev_configure(). + * @param tx_pkts + * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures + * which contain the output packets. + * @param nb_pkts + * The maximum number of packets to process. + * @return + * The number of packets correct and ready to be sent. The return value can be + * less than the value of the *tx_pkts* parameter when some packet doesn't + * meet devices requirements with rte_errno set appropriately: + * - -EINVAL: offload flags are not correctly set + * - -ENOTSUP: the offload feature is not supported by the hardware + * + */ + +#ifndef RTE_ETHDEV_TX_PREPARE_NOOP + +static inline uint16_t +rte_eth_tx_prepare(uint8_t port_id, uint16_t queue_id, + struct rte_mbuf **tx_pkts, uint16_t nb_pkts) +{ + struct rte_eth_dev *dev; + +#ifdef RTE_LIBRTE_ETHDEV_DEBUG + if (!rte_eth_dev_is_valid_port(port_id)) { + RTE_PMD_DEBUG_TRACE("Invalid TX port_id=%d\n", port_id); + rte_errno = -EINVAL; + return 0; + } +#endif + + dev = &rte_eth_devices[port_id]; + +#ifdef RTE_LIBRTE_ETHDEV_DEBUG + if (queue_id >= dev->data->nb_tx_queues) { + RTE_PMD_DEBUG_TRACE("Invalid TX queue_id=%d\n", queue_id); + rte_errno = -EINVAL; + return 0; + } +#endif + + if (!dev->tx_pkt_prepare) + return nb_pkts; + + return (*dev->tx_pkt_prepare)(dev->data->tx_queues[queue_id], + tx_pkts, nb_pkts); +} + +#else + +/* + * Native NOOP operation for compilation targets which doesn't require any + * preparations steps, and functional NOOP may introduce unnecessary performance + * drop. + * + * Generally this is not a good idea to turn it on globally and didn't should + * be used if behavior of tx_preparation can change. + */ + +static inline uint16_t +rte_eth_tx_prepare(__rte_unused uint8_t port_id, __rte_unused uint16_t queue_id, + __rte_unused struct rte_mbuf **tx_pkts, uint16_t nb_pkts) +{ + return nb_pkts; +} + +#endif + typedef void (*buffer_tx_error_fn)(struct rte_mbuf **unsent, uint16_t count, void *userdata); @@ -3049,6 +3181,8 @@ enum rte_eth_event_type { /**< queue state event (enabled/disabled) */ RTE_ETH_EVENT_INTR_RESET, /**< reset interrupt event, sent to VF on PF reset */ + RTE_ETH_EVENT_VF_MBOX, /**< message from the VF received by PF */ + RTE_ETH_EVENT_MACSEC, /**< MACsec offload related event */ RTE_ETH_EVENT_MAX /**< max value of this enum */ }; @@ -3070,6 +3204,11 @@ typedef void (*rte_eth_dev_cb_fn)(uint8_t port_id, \ * @param cb_arg * Pointer to the parameters for the registered callback. * + * The user data is overwritten in the case of RTE_ETH_EVENT_VF_MBOX. + * This even occurs when a message from the VF is received by the PF. + * The user data is overwritten with struct rte_pmd_ixgbe_mb_event_param. + * This struct is defined in rte_pmd_ixgbe.h. + * * @return * - On success, zero. * - On failure, a negative value. @@ -3108,12 +3247,16 @@ int rte_eth_dev_callback_unregister(uint8_t port_id, * Pointer to struct rte_eth_dev. * @param event * Eth device interrupt event type. + * @param cb_arg + * Update callback parameter to pass data back to user application. + * This allows the user application to decide if a particular function + * is permitted or not. * * @return * void */ void _rte_eth_dev_callback_process(struct rte_eth_dev *dev, - enum rte_eth_event_type event); + enum rte_eth_event_type event, void *cb_arg); /** * When there is no rx packet coming in Rx Queue for a long time, we can @@ -3409,93 +3552,6 @@ int rte_eth_dev_uc_hash_table_set(uint8_t port,struct ether_addr *addr, */ int rte_eth_dev_uc_all_hash_table_set(uint8_t port,uint8_t on); - /** - * Set RX L2 Filtering mode of a VF of an Ethernet device. - * - * @param port - * The port identifier of the Ethernet device. - * @param vf - * VF id. - * @param rx_mode - * The RX mode mask, which is one or more of accepting Untagged Packets, - * packets that match the PFUTA table, Broadcast and Multicast Promiscuous. - * ETH_VMDQ_ACCEPT_UNTAG,ETH_VMDQ_ACCEPT_HASH_UC, - * ETH_VMDQ_ACCEPT_BROADCAST and ETH_VMDQ_ACCEPT_MULTICAST will be used - * in rx_mode. - * @param on - * 1 - Enable a VF RX mode. - * 0 - Disable a VF RX mode. - * @return - * - (0) if successful. - * - (-ENOTSUP) if hardware doesn't support. - * - (-ENOTSUP) if hardware doesn't support. - * - (-EINVAL) if bad parameter. - */ -int rte_eth_dev_set_vf_rxmode(uint8_t port, uint16_t vf, uint16_t rx_mode, - uint8_t on); - -/** -* Enable or disable a VF traffic transmit of the Ethernet device. -* -* @param port -* The port identifier of the Ethernet device. -* @param vf -* VF id. -* @param on -* 1 - Enable a VF traffic transmit. -* 0 - Disable a VF traffic transmit. -* @return -* - (0) if successful. -* - (-ENODEV) if *port_id* invalid. -* - (-ENOTSUP) if hardware doesn't support. -* - (-EINVAL) if bad parameter. -*/ -int -rte_eth_dev_set_vf_tx(uint8_t port,uint16_t vf, uint8_t on); - -/** -* Enable or disable a VF traffic receive of an Ethernet device. -* -* @param port -* The port identifier of the Ethernet device. -* @param vf -* VF id. -* @param on -* 1 - Enable a VF traffic receive. -* 0 - Disable a VF traffic receive. -* @return -* - (0) if successful. -* - (-ENOTSUP) if hardware doesn't support. -* - (-ENODEV) if *port_id* invalid. -* - (-EINVAL) if bad parameter. -*/ -int -rte_eth_dev_set_vf_rx(uint8_t port,uint16_t vf, uint8_t on); - -/** -* Enable/Disable hardware VF VLAN filtering by an Ethernet device of -* received VLAN packets tagged with a given VLAN Tag Identifier. -* -* @param port id -* The port identifier of the Ethernet device. -* @param vlan_id -* The VLAN Tag Identifier whose filtering must be enabled or disabled. -* @param vf_mask -* Bitmap listing which VFs participate in the VLAN filtering. -* @param vlan_on -* 1 - Enable VFs VLAN filtering. -* 0 - Disable VFs VLAN filtering. -* @return -* - (0) if successful. -* - (-ENOTSUP) if hardware doesn't support. -* - (-ENODEV) if *port_id* invalid. -* - (-EINVAL) if bad parameter. -*/ -int -rte_eth_dev_set_vf_vlan_filter(uint8_t port, uint16_t vlan_id, - uint64_t vf_mask, - uint8_t vlan_on); - /** * Set a traffic mirroring rule on an Ethernet device * @@ -3557,26 +3613,6 @@ int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx, uint16_t tx_rate); /** - * Set the rate limitation for a vf on an Ethernet device. - * - * @param port_id - * The port identifier of the Ethernet device. - * @param vf - * VF id. - * @param tx_rate - * The tx rate allocated from the total link speed for this VF id. - * @param q_msk - * The queue mask which need to set the rate. - * @return - * - (0) if successful. - * - (-ENOTSUP) if hardware doesn't support this feature. - * - (-ENODEV) if *port_id* invalid. - * - (-EINVAL) if bad parameter. - */ -int rte_eth_set_vf_rate_limit(uint8_t port_id, uint16_t vf, - uint16_t tx_rate, uint64_t q_msk); - -/** * Initialize bypass logic. This function needs to be called before * executing any other bypass API. * @@ -4343,7 +4379,7 @@ rte_eth_dev_l2_tunnel_offload_set(uint8_t port_id, /** * Get the port id from pci adrress or device name -* Ex: 0000:2:00.0 or vdev name eth_pcap0 +* Ex: 0000:2:00.0 or vdev name net_pcap0 * * @param name * pci address or name of the device @@ -4370,6 +4406,21 @@ rte_eth_dev_get_port_by_name(const char *name, uint8_t *port_id); int rte_eth_dev_get_name_by_port(uint8_t port_id, char *name); +/** + * @internal + * Wrapper for use by pci drivers as a .probe function to attach to a ethdev + * interface. + */ +int rte_eth_dev_pci_probe(struct rte_pci_driver *pci_drv, + struct rte_pci_device *pci_dev); + +/** + * @internal + * Wrapper for use by pci drivers as a .remove function to detach a ethdev + * interface. + */ +int rte_eth_dev_pci_remove(struct rte_pci_device *pci_dev); + #ifdef __cplusplus } #endif diff --git a/src/dpdk/lib/librte_ether/rte_ether.h b/src/dpdk/lib/librte_ether/rte_ether.h deleted file mode 100644 index 1d62d8e5..00000000 --- a/src/dpdk/lib/librte_ether/rte_ether.h +++ /dev/null @@ -1,416 +0,0 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2014 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. - */ - -#ifndef _RTE_ETHER_H_ -#define _RTE_ETHER_H_ - -/** - * @file - * - * Ethernet Helpers in RTE - */ - -#ifdef __cplusplus -extern "C" { -#endif - -#include <stdint.h> -#include <stdio.h> - -#include <rte_memcpy.h> -#include <rte_random.h> -#include <rte_mbuf.h> -#include <rte_byteorder.h> - -#define ETHER_ADDR_LEN 6 /**< Length of Ethernet address. */ -#define ETHER_TYPE_LEN 2 /**< Length of Ethernet type field. */ -#define ETHER_CRC_LEN 4 /**< Length of Ethernet CRC. */ -#define ETHER_HDR_LEN \ - (ETHER_ADDR_LEN * 2 + ETHER_TYPE_LEN) /**< Length of Ethernet header. */ -#define ETHER_MIN_LEN 64 /**< Minimum frame len, including CRC. */ -#define ETHER_MAX_LEN 1518 /**< Maximum frame len, including CRC. */ -#define ETHER_MTU \ - (ETHER_MAX_LEN - ETHER_HDR_LEN - ETHER_CRC_LEN) /**< Ethernet MTU. */ - -#define ETHER_MAX_VLAN_FRAME_LEN \ - (ETHER_MAX_LEN + 4) /**< Maximum VLAN frame length, including CRC. */ - -#define ETHER_MAX_JUMBO_FRAME_LEN \ - 0x3F00 /**< Maximum Jumbo frame length, including CRC. */ - -#define ETHER_MAX_VLAN_ID 4095 /**< Maximum VLAN ID. */ - -#define ETHER_MIN_MTU 68 /**< Minimum MTU for IPv4 packets, see RFC 791. */ - -/** - * Ethernet address: - * A universally administered address is uniquely assigned to a device by its - * manufacturer. The first three octets (in transmission order) contain the - * Organizationally Unique Identifier (OUI). The following three (MAC-48 and - * EUI-48) octets are assigned by that organization with the only constraint - * of uniqueness. - * A locally administered address is assigned to a device by a network - * administrator and does not contain OUIs. - * See http://standards.ieee.org/regauth/groupmac/tutorial.html - */ -struct ether_addr { - uint8_t addr_bytes[ETHER_ADDR_LEN]; /**< Address bytes in transmission order */ -} __attribute__((__packed__)); - -#define ETHER_LOCAL_ADMIN_ADDR 0x02 /**< Locally assigned Eth. address. */ -#define ETHER_GROUP_ADDR 0x01 /**< Multicast or broadcast Eth. address. */ - -/** - * Check if two Ethernet addresses are the same. - * - * @param ea1 - * A pointer to the first ether_addr structure containing - * the ethernet address. - * @param ea2 - * A pointer to the second ether_addr structure containing - * the ethernet address. - * - * @return - * True (1) if the given two ethernet address are the same; - * False (0) otherwise. - */ -static inline int is_same_ether_addr(const struct ether_addr *ea1, - const struct ether_addr *ea2) -{ - int i; - for (i = 0; i < ETHER_ADDR_LEN; i++) - if (ea1->addr_bytes[i] != ea2->addr_bytes[i]) - return 0; - return 1; -} - -/** - * Check if an Ethernet address is filled with zeros. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is filled with zeros; - * false (0) otherwise. - */ -static inline int is_zero_ether_addr(const struct ether_addr *ea) -{ - int i; - for (i = 0; i < ETHER_ADDR_LEN; i++) - if (ea->addr_bytes[i] != 0x00) - return 0; - return 1; -} - -/** - * Check if an Ethernet address is a unicast address. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is a unicast address; - * false (0) otherwise. - */ -static inline int is_unicast_ether_addr(const struct ether_addr *ea) -{ - return (ea->addr_bytes[0] & ETHER_GROUP_ADDR) == 0; -} - -/** - * Check if an Ethernet address is a multicast address. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is a multicast address; - * false (0) otherwise. - */ -static inline int is_multicast_ether_addr(const struct ether_addr *ea) -{ - return ea->addr_bytes[0] & ETHER_GROUP_ADDR; -} - -/** - * Check if an Ethernet address is a broadcast address. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is a broadcast address; - * false (0) otherwise. - */ -static inline int is_broadcast_ether_addr(const struct ether_addr *ea) -{ - const unaligned_uint16_t *ea_words = (const unaligned_uint16_t *)ea; - - return (ea_words[0] == 0xFFFF && ea_words[1] == 0xFFFF && - ea_words[2] == 0xFFFF); -} - -/** - * Check if an Ethernet address is a universally assigned address. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is a universally assigned address; - * false (0) otherwise. - */ -static inline int is_universal_ether_addr(const struct ether_addr *ea) -{ - return (ea->addr_bytes[0] & ETHER_LOCAL_ADMIN_ADDR) == 0; -} - -/** - * Check if an Ethernet address is a locally assigned address. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is a locally assigned address; - * false (0) otherwise. - */ -static inline int is_local_admin_ether_addr(const struct ether_addr *ea) -{ - return (ea->addr_bytes[0] & ETHER_LOCAL_ADMIN_ADDR) != 0; -} - -/** - * Check if an Ethernet address is a valid address. Checks that the address is a - * unicast address and is not filled with zeros. - * - * @param ea - * A pointer to a ether_addr structure containing the ethernet address - * to check. - * @return - * True (1) if the given ethernet address is valid; - * false (0) otherwise. - */ -static inline int is_valid_assigned_ether_addr(const struct ether_addr *ea) -{ - return is_unicast_ether_addr(ea) && (! is_zero_ether_addr(ea)); -} - -/** - * Generate a random Ethernet address that is locally administered - * and not multicast. - * @param addr - * A pointer to Ethernet address. - */ -static inline void eth_random_addr(uint8_t *addr) -{ - uint64_t rand = rte_rand(); - uint8_t *p = (uint8_t*)&rand; - - rte_memcpy(addr, p, ETHER_ADDR_LEN); - addr[0] &= ~ETHER_GROUP_ADDR; /* clear multicast bit */ - addr[0] |= ETHER_LOCAL_ADMIN_ADDR; /* set local assignment bit */ -} - -/** - * Fast copy an Ethernet address. - * - * @param ea_from - * A pointer to a ether_addr structure holding the Ethernet address to copy. - * @param ea_to - * A pointer to a ether_addr structure where to copy the Ethernet address. - */ -static inline void ether_addr_copy(const struct ether_addr *ea_from, - struct ether_addr *ea_to) -{ -#ifdef __INTEL_COMPILER - uint16_t *from_words = (uint16_t *)(ea_from->addr_bytes); - uint16_t *to_words = (uint16_t *)(ea_to->addr_bytes); - - to_words[0] = from_words[0]; - to_words[1] = from_words[1]; - to_words[2] = from_words[2]; -#else - /* - * Use the common way, because of a strange gcc warning. - */ - *ea_to = *ea_from; -#endif -} - -#define ETHER_ADDR_FMT_SIZE 18 -/** - * Format 48bits Ethernet address in pattern xx:xx:xx:xx:xx:xx. - * - * @param buf - * A pointer to buffer contains the formatted MAC address. - * @param size - * The format buffer size. - * @param eth_addr - * A pointer to a ether_addr structure. - */ -static inline void -ether_format_addr(char *buf, uint16_t size, - const struct ether_addr *eth_addr) -{ - snprintf(buf, size, "%02X:%02X:%02X:%02X:%02X:%02X", - eth_addr->addr_bytes[0], - eth_addr->addr_bytes[1], - eth_addr->addr_bytes[2], - eth_addr->addr_bytes[3], - eth_addr->addr_bytes[4], - eth_addr->addr_bytes[5]); -} - -/** - * Ethernet header: Contains the destination address, source address - * and frame type. - */ -struct ether_hdr { - struct ether_addr d_addr; /**< Destination address. */ - struct ether_addr s_addr; /**< Source address. */ - uint16_t ether_type; /**< Frame type. */ -} __attribute__((__packed__)); - -/** - * Ethernet VLAN Header. - * Contains the 16-bit VLAN Tag Control Identifier and the Ethernet type - * of the encapsulated frame. - */ -struct vlan_hdr { - uint16_t vlan_tci; /**< Priority (3) + CFI (1) + Identifier Code (12) */ - uint16_t eth_proto;/**< Ethernet type of encapsulated frame. */ -} __attribute__((__packed__)); - -/** - * VXLAN protocol header. - * Contains the 8-bit flag, 24-bit VXLAN Network Identifier and - * Reserved fields (24 bits and 8 bits) - */ -struct vxlan_hdr { - uint32_t vx_flags; /**< flag (8) + Reserved (24). */ - uint32_t vx_vni; /**< VNI (24) + Reserved (8). */ -} __attribute__((__packed__)); - -/* Ethernet frame types */ -#define ETHER_TYPE_IPv4 0x0800 /**< IPv4 Protocol. */ -#define ETHER_TYPE_IPv6 0x86DD /**< IPv6 Protocol. */ -#define ETHER_TYPE_ARP 0x0806 /**< Arp Protocol. */ -#define ETHER_TYPE_RARP 0x8035 /**< Reverse Arp Protocol. */ -#define ETHER_TYPE_VLAN 0x8100 /**< IEEE 802.1Q VLAN tagging. */ -#define ETHER_TYPE_1588 0x88F7 /**< IEEE 802.1AS 1588 Precise Time Protocol. */ -#define ETHER_TYPE_SLOW 0x8809 /**< Slow protocols (LACP and Marker). */ -#define ETHER_TYPE_TEB 0x6558 /**< Transparent Ethernet Bridging. */ - -#define ETHER_VXLAN_HLEN (sizeof(struct udp_hdr) + sizeof(struct vxlan_hdr)) -/**< VXLAN tunnel header length. */ - -/** - * Extract VLAN tag information into mbuf - * - * Software version of VLAN stripping - * - * @param m - * The packet mbuf. - * @return - * - 0: Success - * - 1: not a vlan packet - */ -static inline int rte_vlan_strip(struct rte_mbuf *m) -{ - struct ether_hdr *eh - = rte_pktmbuf_mtod(m, struct ether_hdr *); - - if (eh->ether_type != rte_cpu_to_be_16(ETHER_TYPE_VLAN)) - return -1; - - struct vlan_hdr *vh = (struct vlan_hdr *)(eh + 1); - m->ol_flags |= PKT_RX_VLAN_PKT; - m->vlan_tci = rte_be_to_cpu_16(vh->vlan_tci); - - /* Copy ether header over rather than moving whole packet */ - memmove(rte_pktmbuf_adj(m, sizeof(struct vlan_hdr)), - eh, 2 * ETHER_ADDR_LEN); - - return 0; -} - -/** - * Insert VLAN tag into mbuf. - * - * Software version of VLAN unstripping - * - * @param m - * The packet mbuf. - * @return - * - 0: On success - * -EPERM: mbuf is is shared overwriting would be unsafe - * -ENOSPC: not enough headroom in mbuf - */ -static inline int rte_vlan_insert(struct rte_mbuf **m) -{ - struct ether_hdr *oh, *nh; - struct vlan_hdr *vh; - - /* Can't insert header if mbuf is shared */ - if (rte_mbuf_refcnt_read(*m) > 1) { - struct rte_mbuf *copy; - - copy = rte_pktmbuf_clone(*m, (*m)->pool); - if (unlikely(copy == NULL)) - return -ENOMEM; - rte_pktmbuf_free(*m); - *m = copy; - } - - oh = rte_pktmbuf_mtod(*m, struct ether_hdr *); - nh = (struct ether_hdr *) - rte_pktmbuf_prepend(*m, sizeof(struct vlan_hdr)); - if (nh == NULL) - return -ENOSPC; - - memmove(nh, oh, 2 * ETHER_ADDR_LEN); - nh->ether_type = rte_cpu_to_be_16(ETHER_TYPE_VLAN); - - vh = (struct vlan_hdr *) (nh + 1); - vh->vlan_tci = rte_cpu_to_be_16((*m)->vlan_tci); - - return 0; -} - -#ifdef __cplusplus -} -#endif - -#endif /* _RTE_ETHER_H_ */ diff --git a/src/dpdk/lib/librte_ether/rte_flow.c b/src/dpdk/lib/librte_ether/rte_flow.c new file mode 100644 index 00000000..aaa70d68 --- /dev/null +++ b/src/dpdk/lib/librte_ether/rte_flow.c @@ -0,0 +1,159 @@ +/*- + * BSD LICENSE + * + * Copyright 2016 6WIND S.A. + * Copyright 2016 Mellanox. + * + * 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 6WIND S.A. 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. + */ + +#include <stdint.h> + +#include <rte_errno.h> +#include <rte_branch_prediction.h> +#include "rte_ethdev.h" +#include "rte_flow_driver.h" +#include "rte_flow.h" + +/* Get generic flow operations structure from a port. */ +const struct rte_flow_ops * +rte_flow_ops_get(uint8_t port_id, struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops; + int code; + + if (unlikely(!rte_eth_dev_is_valid_port(port_id))) + code = ENODEV; + else if (unlikely(!dev->dev_ops->filter_ctrl || + dev->dev_ops->filter_ctrl(dev, + RTE_ETH_FILTER_GENERIC, + RTE_ETH_FILTER_GET, + &ops) || + !ops)) + code = ENOSYS; + else + return ops; + rte_flow_error_set(error, code, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(code)); + return NULL; +} + +/* Check whether a flow rule can be created on a given port. */ +int +rte_flow_validate(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error) +{ + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + + if (unlikely(!ops)) + return -rte_errno; + if (likely(!!ops->validate)) + return ops->validate(dev, attr, pattern, actions, error); + return -rte_flow_error_set(error, ENOSYS, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); +} + +/* Create a flow rule on a given port. */ +struct rte_flow * +rte_flow_create(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (unlikely(!ops)) + return NULL; + if (likely(!!ops->create)) + return ops->create(dev, attr, pattern, actions, error); + rte_flow_error_set(error, ENOSYS, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); + return NULL; +} + +/* Destroy a flow rule on a given port. */ +int +rte_flow_destroy(uint8_t port_id, + struct rte_flow *flow, + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (unlikely(!ops)) + return -rte_errno; + if (likely(!!ops->destroy)) + return ops->destroy(dev, flow, error); + return -rte_flow_error_set(error, ENOSYS, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); +} + +/* Destroy all flow rules associated with a port. */ +int +rte_flow_flush(uint8_t port_id, + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (unlikely(!ops)) + return -rte_errno; + if (likely(!!ops->flush)) + return ops->flush(dev, error); + return -rte_flow_error_set(error, ENOSYS, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); +} + +/* Query an existing flow rule. */ +int +rte_flow_query(uint8_t port_id, + struct rte_flow *flow, + enum rte_flow_action_type action, + void *data, + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (!ops) + return -rte_errno; + if (likely(!!ops->query)) + return ops->query(dev, flow, action, data, error); + return -rte_flow_error_set(error, ENOSYS, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); +} diff --git a/src/dpdk/lib/librte_ether/rte_flow.h b/src/dpdk/lib/librte_ether/rte_flow.h new file mode 100644 index 00000000..171a5698 --- /dev/null +++ b/src/dpdk/lib/librte_ether/rte_flow.h @@ -0,0 +1,1090 @@ +/*- + * BSD LICENSE + * + * Copyright 2016 6WIND S.A. + * Copyright 2016 Mellanox. + * + * 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 6WIND S.A. 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. + */ + +#ifndef RTE_FLOW_H_ +#define RTE_FLOW_H_ + +/** + * @file + * RTE generic flow API + * + * This interface provides the ability to program packet matching and + * associated actions in hardware through flow rules. + */ + +#include <rte_arp.h> +#include <rte_ether.h> +#include <rte_icmp.h> +#include <rte_ip.h> +#include <rte_sctp.h> +#include <rte_tcp.h> +#include <rte_udp.h> + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * Flow rule attributes. + * + * Priorities are set on two levels: per group and per rule within groups. + * + * Lower values denote higher priority, the highest priority for both levels + * is 0, so that a rule with priority 0 in group 8 is always matched after a + * rule with priority 8 in group 0. + * + * Although optional, applications are encouraged to group similar rules as + * much as possible to fully take advantage of hardware capabilities + * (e.g. optimized matching) and work around limitations (e.g. a single + * pattern type possibly allowed in a given group). + * + * Group and priority levels are arbitrary and up to the application, they + * do not need to be contiguous nor start from 0, however the maximum number + * varies between devices and may be affected by existing flow rules. + * + * If a packet is matched by several rules of a given group for a given + * priority level, the outcome is undefined. It can take any path, may be + * duplicated or even cause unrecoverable errors. + * + * Note that support for more than a single group and priority level is not + * guaranteed. + * + * Flow rules can apply to inbound and/or outbound traffic (ingress/egress). + * + * Several pattern items and actions are valid and can be used in both + * directions. Those valid for only one direction are described as such. + * + * At least one direction must be specified. + * + * Specifying both directions at once for a given rule is not recommended + * but may be valid in a few cases (e.g. shared counter). + */ +struct rte_flow_attr { + uint32_t group; /**< Priority group. */ + uint32_t priority; /**< Priority level within group. */ + uint32_t ingress:1; /**< Rule applies to ingress traffic. */ + uint32_t egress:1; /**< Rule applies to egress traffic. */ + uint32_t reserved:30; /**< Reserved, must be zero. */ +}; + +/** + * Matching pattern item types. + * + * Pattern items fall in two categories: + * + * - Matching protocol headers and packet data (ANY, RAW, ETH, VLAN, IPV4, + * IPV6, ICMP, UDP, TCP, SCTP, VXLAN and so on), usually associated with a + * specification structure. These must be stacked in the same order as the + * protocol layers to match, starting from the lowest. + * + * - Matching meta-data or affecting pattern processing (END, VOID, INVERT, + * PF, VF, PORT and so on), often without a specification structure. Since + * they do not match packet contents, these can be specified anywhere + * within item lists without affecting others. + * + * See the description of individual types for more information. Those + * marked with [META] fall into the second category. + */ +enum rte_flow_item_type { + /** + * [META] + * + * End marker for item lists. Prevents further processing of items, + * thereby ending the pattern. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_END, + + /** + * [META] + * + * Used as a placeholder for convenience. It is ignored and simply + * discarded by PMDs. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_VOID, + + /** + * [META] + * + * Inverted matching, i.e. process packets that do not match the + * pattern. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_INVERT, + + /** + * Matches any protocol in place of the current layer, a single ANY + * may also stand for several protocol layers. + * + * See struct rte_flow_item_any. + */ + RTE_FLOW_ITEM_TYPE_ANY, + + /** + * [META] + * + * Matches packets addressed to the physical function of the device. + * + * If the underlying device function differs from the one that would + * normally receive the matched traffic, specifying this item + * prevents it from reaching that device unless the flow rule + * contains a PF action. Packets are not duplicated between device + * instances by default. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_PF, + + /** + * [META] + * + * Matches packets addressed to a virtual function ID of the device. + * + * If the underlying device function differs from the one that would + * normally receive the matched traffic, specifying this item + * prevents it from reaching that device unless the flow rule + * contains a VF action. Packets are not duplicated between device + * instances by default. + * + * See struct rte_flow_item_vf. + */ + RTE_FLOW_ITEM_TYPE_VF, + + /** + * [META] + * + * Matches packets coming from the specified physical port of the + * underlying device. + * + * The first PORT item overrides the physical port normally + * associated with the specified DPDK input port (port_id). This + * item can be provided several times to match additional physical + * ports. + * + * See struct rte_flow_item_port. + */ + RTE_FLOW_ITEM_TYPE_PORT, + + /** + * Matches a byte string of a given length at a given offset. + * + * See struct rte_flow_item_raw. + */ + RTE_FLOW_ITEM_TYPE_RAW, + + /** + * Matches an Ethernet header. + * + * See struct rte_flow_item_eth. + */ + RTE_FLOW_ITEM_TYPE_ETH, + + /** + * Matches an 802.1Q/ad VLAN tag. + * + * See struct rte_flow_item_vlan. + */ + RTE_FLOW_ITEM_TYPE_VLAN, + + /** + * Matches an IPv4 header. + * + * See struct rte_flow_item_ipv4. + */ + RTE_FLOW_ITEM_TYPE_IPV4, + + /** + * Matches an IPv6 header. + * + * See struct rte_flow_item_ipv6. + */ + RTE_FLOW_ITEM_TYPE_IPV6, + + /** + * Matches an ICMP header. + * + * See struct rte_flow_item_icmp. + */ + RTE_FLOW_ITEM_TYPE_ICMP, + + /** + * Matches a UDP header. + * + * See struct rte_flow_item_udp. + */ + RTE_FLOW_ITEM_TYPE_UDP, + + /** + * Matches a TCP header. + * + * See struct rte_flow_item_tcp. + */ + RTE_FLOW_ITEM_TYPE_TCP, + + /** + * Matches a SCTP header. + * + * See struct rte_flow_item_sctp. + */ + RTE_FLOW_ITEM_TYPE_SCTP, + + /** + * Matches a VXLAN header. + * + * See struct rte_flow_item_vxlan. + */ + RTE_FLOW_ITEM_TYPE_VXLAN, + + /** + * Matches a E_TAG header. + * + * See struct rte_flow_item_e_tag. + */ + RTE_FLOW_ITEM_TYPE_E_TAG, + + /** + * Matches a NVGRE header. + * + * See struct rte_flow_item_nvgre. + */ + RTE_FLOW_ITEM_TYPE_NVGRE, +}; + +/** + * RTE_FLOW_ITEM_TYPE_ANY + * + * Matches any protocol in place of the current layer, a single ANY may also + * stand for several protocol layers. + * + * This is usually specified as the first pattern item when looking for a + * protocol anywhere in a packet. + * + * A zeroed mask stands for any number of layers. + */ +struct rte_flow_item_any { + uint32_t num; /**< Number of layers covered. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_ANY. */ +static const struct rte_flow_item_any rte_flow_item_any_mask = { + .num = 0x00000000, +}; + +/** + * RTE_FLOW_ITEM_TYPE_VF + * + * Matches packets addressed to a virtual function ID of the device. + * + * If the underlying device function differs from the one that would + * normally receive the matched traffic, specifying this item prevents it + * from reaching that device unless the flow rule contains a VF + * action. Packets are not duplicated between device instances by default. + * + * - Likely to return an error or never match any traffic if this causes a + * VF device to match traffic addressed to a different VF. + * - Can be specified multiple times to match traffic addressed to several + * VF IDs. + * - Can be combined with a PF item to match both PF and VF traffic. + * + * A zeroed mask can be used to match any VF ID. + */ +struct rte_flow_item_vf { + uint32_t id; /**< Destination VF ID. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_VF. */ +static const struct rte_flow_item_vf rte_flow_item_vf_mask = { + .id = 0x00000000, +}; + +/** + * RTE_FLOW_ITEM_TYPE_PORT + * + * Matches packets coming from the specified physical port of the underlying + * device. + * + * The first PORT item overrides the physical port normally associated with + * the specified DPDK input port (port_id). This item can be provided + * several times to match additional physical ports. + * + * Note that physical ports are not necessarily tied to DPDK input ports + * (port_id) when those are not under DPDK control. Possible values are + * specific to each device, they are not necessarily indexed from zero and + * may not be contiguous. + * + * As a device property, the list of allowed values as well as the value + * associated with a port_id should be retrieved by other means. + * + * A zeroed mask can be used to match any port index. + */ +struct rte_flow_item_port { + uint32_t index; /**< Physical port index. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_PORT. */ +static const struct rte_flow_item_port rte_flow_item_port_mask = { + .index = 0x00000000, +}; + +/** + * RTE_FLOW_ITEM_TYPE_RAW + * + * Matches a byte string of a given length at a given offset. + * + * Offset is either absolute (using the start of the packet) or relative to + * the end of the previous matched item in the stack, in which case negative + * values are allowed. + * + * If search is enabled, offset is used as the starting point. The search + * area can be delimited by setting limit to a nonzero value, which is the + * maximum number of bytes after offset where the pattern may start. + * + * Matching a zero-length pattern is allowed, doing so resets the relative + * offset for subsequent items. + * + * This type does not support ranges (struct rte_flow_item.last). + */ +struct rte_flow_item_raw { + uint32_t relative:1; /**< Look for pattern after the previous item. */ + uint32_t search:1; /**< Search pattern from offset (see also limit). */ + uint32_t reserved:30; /**< Reserved, must be set to zero. */ + int32_t offset; /**< Absolute or relative offset for pattern. */ + uint16_t limit; /**< Search area limit for start of pattern. */ + uint16_t length; /**< Pattern length. */ + uint8_t pattern[]; /**< Byte string to look for. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_RAW. */ +static const struct rte_flow_item_raw rte_flow_item_raw_mask = { + .relative = 1, + .search = 1, + .reserved = 0x3fffffff, + .offset = 0xffffffff, + .limit = 0xffff, + .length = 0xffff, +}; + +/** + * RTE_FLOW_ITEM_TYPE_ETH + * + * Matches an Ethernet header. + */ +struct rte_flow_item_eth { + struct ether_addr dst; /**< Destination MAC. */ + struct ether_addr src; /**< Source MAC. */ + uint16_t type; /**< EtherType. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_ETH. */ +static const struct rte_flow_item_eth rte_flow_item_eth_mask = { + .dst.addr_bytes = "\xff\xff\xff\xff\xff\xff", + .src.addr_bytes = "\xff\xff\xff\xff\xff\xff", + .type = 0x0000, +}; + +/** + * RTE_FLOW_ITEM_TYPE_VLAN + * + * Matches an 802.1Q/ad VLAN tag. + * + * This type normally follows either RTE_FLOW_ITEM_TYPE_ETH or + * RTE_FLOW_ITEM_TYPE_VLAN. + */ +struct rte_flow_item_vlan { + uint16_t tpid; /**< Tag protocol identifier. */ + uint16_t tci; /**< Tag control information. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_VLAN. */ +static const struct rte_flow_item_vlan rte_flow_item_vlan_mask = { + .tpid = 0x0000, + .tci = 0xffff, +}; + +/** + * RTE_FLOW_ITEM_TYPE_IPV4 + * + * Matches an IPv4 header. + * + * Note: IPv4 options are handled by dedicated pattern items. + */ +struct rte_flow_item_ipv4 { + struct ipv4_hdr hdr; /**< IPv4 header definition. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_IPV4. */ +static const struct rte_flow_item_ipv4 rte_flow_item_ipv4_mask = { + .hdr = { + .src_addr = 0xffffffff, + .dst_addr = 0xffffffff, + }, +}; + +/** + * RTE_FLOW_ITEM_TYPE_IPV6. + * + * Matches an IPv6 header. + * + * Note: IPv6 options are handled by dedicated pattern items. + */ +struct rte_flow_item_ipv6 { + struct ipv6_hdr hdr; /**< IPv6 header definition. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_IPV6. */ +static const struct rte_flow_item_ipv6 rte_flow_item_ipv6_mask = { + .hdr = { + .src_addr = + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff", + .dst_addr = + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff", + }, +}; + +/** + * RTE_FLOW_ITEM_TYPE_ICMP. + * + * Matches an ICMP header. + */ +struct rte_flow_item_icmp { + struct icmp_hdr hdr; /**< ICMP header definition. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_ICMP. */ +static const struct rte_flow_item_icmp rte_flow_item_icmp_mask = { + .hdr = { + .icmp_type = 0xff, + .icmp_code = 0xff, + }, +}; + +/** + * RTE_FLOW_ITEM_TYPE_UDP. + * + * Matches a UDP header. + */ +struct rte_flow_item_udp { + struct udp_hdr hdr; /**< UDP header definition. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_UDP. */ +static const struct rte_flow_item_udp rte_flow_item_udp_mask = { + .hdr = { + .src_port = 0xffff, + .dst_port = 0xffff, + }, +}; + +/** + * RTE_FLOW_ITEM_TYPE_TCP. + * + * Matches a TCP header. + */ +struct rte_flow_item_tcp { + struct tcp_hdr hdr; /**< TCP header definition. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_TCP. */ +static const struct rte_flow_item_tcp rte_flow_item_tcp_mask = { + .hdr = { + .src_port = 0xffff, + .dst_port = 0xffff, + }, +}; + +/** + * RTE_FLOW_ITEM_TYPE_SCTP. + * + * Matches a SCTP header. + */ +struct rte_flow_item_sctp { + struct sctp_hdr hdr; /**< SCTP header definition. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_SCTP. */ +static const struct rte_flow_item_sctp rte_flow_item_sctp_mask = { + .hdr = { + .src_port = 0xffff, + .dst_port = 0xffff, + }, +}; + +/** + * RTE_FLOW_ITEM_TYPE_VXLAN. + * + * Matches a VXLAN header (RFC 7348). + */ +struct rte_flow_item_vxlan { + uint8_t flags; /**< Normally 0x08 (I flag). */ + uint8_t rsvd0[3]; /**< Reserved, normally 0x000000. */ + uint8_t vni[3]; /**< VXLAN identifier. */ + uint8_t rsvd1; /**< Reserved, normally 0x00. */ +}; + +/** Default mask for RTE_FLOW_ITEM_TYPE_VXLAN. */ +static const struct rte_flow_item_vxlan rte_flow_item_vxlan_mask = { + .vni = "\xff\xff\xff", +}; + +/** + * RTE_FLOW_ITEM_TYPE_E_TAG. + * + * Matches a E-tag header. + */ +struct rte_flow_item_e_tag { + uint16_t tpid; /**< Tag protocol identifier (0x893F). */ + /** + * E-Tag control information (E-TCI). + * E-PCP (3b), E-DEI (1b), ingress E-CID base (12b). + */ + uint16_t epcp_edei_in_ecid_b; + /** Reserved (2b), GRP (2b), E-CID base (12b). */ + uint16_t rsvd_grp_ecid_b; + uint8_t in_ecid_e; /**< Ingress E-CID ext. */ + uint8_t ecid_e; /**< E-CID ext. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_NVGRE. + * + * Matches a NVGRE header. + */ +struct rte_flow_item_nvgre { + /** + * Checksum (1b), undefined (1b), key bit (1b), sequence number (1b), + * reserved 0 (9b), version (3b). + * + * c_k_s_rsvd0_ver must have value 0x2000 according to RFC 7637. + */ + uint16_t c_k_s_rsvd0_ver; + uint16_t protocol; /**< Protocol type (0x6558). */ + uint8_t tni[3]; /**< Virtual subnet ID. */ + uint8_t flow_id; /**< Flow ID. */ +}; + +/** + * Matching pattern item definition. + * + * A pattern is formed by stacking items starting from the lowest protocol + * layer to match. This stacking restriction does not apply to meta items + * which can be placed anywhere in the stack without affecting the meaning + * of the resulting pattern. + * + * Patterns are terminated by END items. + * + * The spec field should be a valid pointer to a structure of the related + * item type. It may remain unspecified (NULL) in many cases to request + * broad (nonspecific) matching. In such cases, last and mask must also be + * set to NULL. + * + * Optionally, last can point to a structure of the same type to define an + * inclusive range. This is mostly supported by integer and address fields, + * may cause errors otherwise. Fields that do not support ranges must be set + * to 0 or to the same value as the corresponding fields in spec. + * + * Only the fields defined to nonzero values in the default masks (see + * rte_flow_item_{name}_mask constants) are considered relevant by + * default. This can be overridden by providing a mask structure of the + * same type with applicable bits set to one. It can also be used to + * partially filter out specific fields (e.g. as an alternate mean to match + * ranges of IP addresses). + * + * Mask is a simple bit-mask applied before interpreting the contents of + * spec and last, which may yield unexpected results if not used + * carefully. For example, if for an IPv4 address field, spec provides + * 10.1.2.3, last provides 10.3.4.5 and mask provides 255.255.0.0, the + * effective range becomes 10.1.0.0 to 10.3.255.255. + */ +struct rte_flow_item { + enum rte_flow_item_type type; /**< Item type. */ + const void *spec; /**< Pointer to item specification structure. */ + const void *last; /**< Defines an inclusive range (spec to last). */ + const void *mask; /**< Bit-mask applied to spec and last. */ +}; + +/** + * Action types. + * + * Each possible action is represented by a type. Some have associated + * configuration structures. Several actions combined in a list can be + * affected to a flow rule. That list is not ordered. + * + * They fall in three categories: + * + * - Terminating actions (such as QUEUE, DROP, RSS, PF, VF) that prevent + * processing matched packets by subsequent flow rules, unless overridden + * with PASSTHRU. + * + * - Non terminating actions (PASSTHRU, DUP) that leave matched packets up + * for additional processing by subsequent flow rules. + * + * - Other non terminating meta actions that do not affect the fate of + * packets (END, VOID, MARK, FLAG, COUNT). + * + * When several actions are combined in a flow rule, they should all have + * different types (e.g. dropping a packet twice is not possible). + * + * Only the last action of a given type is taken into account. PMDs still + * perform error checking on the entire list. + * + * Note that PASSTHRU is the only action able to override a terminating + * rule. + */ +enum rte_flow_action_type { + /** + * [META] + * + * End marker for action lists. Prevents further processing of + * actions, thereby ending the list. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_END, + + /** + * [META] + * + * Used as a placeholder for convenience. It is ignored and simply + * discarded by PMDs. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_VOID, + + /** + * Leaves packets up for additional processing by subsequent flow + * rules. This is the default when a rule does not contain a + * terminating action, but can be specified to force a rule to + * become non-terminating. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_PASSTHRU, + + /** + * [META] + * + * Attaches an integer value to packets and sets PKT_RX_FDIR and + * PKT_RX_FDIR_ID mbuf flags. + * + * See struct rte_flow_action_mark. + */ + RTE_FLOW_ACTION_TYPE_MARK, + + /** + * [META] + * + * Flags packets. Similar to MARK without a specific value; only + * sets the PKT_RX_FDIR mbuf flag. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_FLAG, + + /** + * Assigns packets to a given queue index. + * + * See struct rte_flow_action_queue. + */ + RTE_FLOW_ACTION_TYPE_QUEUE, + + /** + * Drops packets. + * + * PASSTHRU overrides this action if both are specified. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_DROP, + + /** + * [META] + * + * Enables counters for this rule. + * + * These counters can be retrieved and reset through rte_flow_query(), + * see struct rte_flow_query_count. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_COUNT, + + /** + * Duplicates packets to a given queue index. + * + * This is normally combined with QUEUE, however when used alone, it + * is actually similar to QUEUE + PASSTHRU. + * + * See struct rte_flow_action_dup. + */ + RTE_FLOW_ACTION_TYPE_DUP, + + /** + * Similar to QUEUE, except RSS is additionally performed on packets + * to spread them among several queues according to the provided + * parameters. + * + * See struct rte_flow_action_rss. + */ + RTE_FLOW_ACTION_TYPE_RSS, + + /** + * Redirects packets to the physical function (PF) of the current + * device. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_PF, + + /** + * Redirects packets to the virtual function (VF) of the current + * device with the specified ID. + * + * See struct rte_flow_action_vf. + */ + RTE_FLOW_ACTION_TYPE_VF, +}; + +/** + * RTE_FLOW_ACTION_TYPE_MARK + * + * Attaches an integer value to packets and sets PKT_RX_FDIR and + * PKT_RX_FDIR_ID mbuf flags. + * + * This value is arbitrary and application-defined. Maximum allowed value + * depends on the underlying implementation. It is returned in the + * hash.fdir.hi mbuf field. + */ +struct rte_flow_action_mark { + uint32_t id; /**< Integer value to return with packets. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_QUEUE + * + * Assign packets to a given queue index. + * + * Terminating by default. + */ +struct rte_flow_action_queue { + uint16_t index; /**< Queue index to use. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_COUNT (query) + * + * Query structure to retrieve and reset flow rule counters. + */ +struct rte_flow_query_count { + uint32_t reset:1; /**< Reset counters after query [in]. */ + uint32_t hits_set:1; /**< hits field is set [out]. */ + uint32_t bytes_set:1; /**< bytes field is set [out]. */ + uint32_t reserved:29; /**< Reserved, must be zero [in, out]. */ + uint64_t hits; /**< Number of hits for this rule [out]. */ + uint64_t bytes; /**< Number of bytes through this rule [out]. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_DUP + * + * Duplicates packets to a given queue index. + * + * This is normally combined with QUEUE, however when used alone, it is + * actually similar to QUEUE + PASSTHRU. + * + * Non-terminating by default. + */ +struct rte_flow_action_dup { + uint16_t index; /**< Queue index to duplicate packets to. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_RSS + * + * Similar to QUEUE, except RSS is additionally performed on packets to + * spread them among several queues according to the provided parameters. + * + * Note: RSS hash result is stored in the hash.rss mbuf field which overlaps + * hash.fdir.lo. Since the MARK action sets the hash.fdir.hi field only, + * both can be requested simultaneously. + * + * Terminating by default. + */ +struct rte_flow_action_rss { + const struct rte_eth_rss_conf *rss_conf; /**< RSS parameters. */ + uint16_t num; /**< Number of entries in queue[]. */ + uint16_t queue[]; /**< Queues indices to use. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_VF + * + * Redirects packets to a virtual function (VF) of the current device. + * + * Packets matched by a VF pattern item can be redirected to their original + * VF ID instead of the specified one. This parameter may not be available + * and is not guaranteed to work properly if the VF part is matched by a + * prior flow rule or if packets are not addressed to a VF in the first + * place. + * + * Terminating by default. + */ +struct rte_flow_action_vf { + uint32_t original:1; /**< Use original VF ID if possible. */ + uint32_t reserved:31; /**< Reserved, must be zero. */ + uint32_t id; /**< VF ID to redirect packets to. */ +}; + +/** + * Definition of a single action. + * + * A list of actions is terminated by a END action. + * + * For simple actions without a configuration structure, conf remains NULL. + */ +struct rte_flow_action { + enum rte_flow_action_type type; /**< Action type. */ + const void *conf; /**< Pointer to action configuration structure. */ +}; + +/** + * Opaque type returned after successfully creating a flow. + * + * This handle can be used to manage and query the related flow (e.g. to + * destroy it or retrieve counters). + */ +struct rte_flow; + +/** + * Verbose error types. + * + * Most of them provide the type of the object referenced by struct + * rte_flow_error.cause. + */ +enum rte_flow_error_type { + RTE_FLOW_ERROR_TYPE_NONE, /**< No error. */ + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */ + RTE_FLOW_ERROR_TYPE_HANDLE, /**< Flow rule (handle). */ + RTE_FLOW_ERROR_TYPE_ATTR_GROUP, /**< Group field. */ + RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, /**< Priority field. */ + RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, /**< Ingress field. */ + RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, /**< Egress field. */ + RTE_FLOW_ERROR_TYPE_ATTR, /**< Attributes structure. */ + RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */ + RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */ + RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */ + RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */ +}; + +/** + * Verbose error structure definition. + * + * This object is normally allocated by applications and set by PMDs, the + * message points to a constant string which does not need to be freed by + * the application, however its pointer can be considered valid only as long + * as its associated DPDK port remains configured. Closing the underlying + * device or unloading the PMD invalidates it. + * + * Both cause and message may be NULL regardless of the error type. + */ +struct rte_flow_error { + enum rte_flow_error_type type; /**< Cause field and error types. */ + const void *cause; /**< Object responsible for the error. */ + const char *message; /**< Human-readable error message. */ +}; + +/** + * Check whether a flow rule can be created on a given port. + * + * While this function has no effect on the target device, the flow rule is + * validated against its current configuration state and the returned value + * should be considered valid by the caller for that state only. + * + * The returned value is guaranteed to remain valid only as long as no + * successful calls to rte_flow_create() or rte_flow_destroy() are made in + * the meantime and no device parameter affecting flow rules in any way are + * modified, due to possible collisions or resource limitations (although in + * such cases EINVAL should not be returned). + * + * @param port_id + * Port identifier of Ethernet device. + * @param[in] attr + * Flow rule attributes. + * @param[in] pattern + * Pattern specification (list terminated by the END pattern item). + * @param[in] actions + * Associated actions (list terminated by the END action). + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * 0 if flow rule is valid and can be created. A negative errno value + * otherwise (rte_errno is also set), the following errors are defined: + * + * -ENOSYS: underlying device does not support this functionality. + * + * -EINVAL: unknown or invalid rule specification. + * + * -ENOTSUP: valid but unsupported rule specification (e.g. partial + * bit-masks are unsupported). + * + * -EEXIST: collision with an existing rule. + * + * -ENOMEM: not enough resources. + * + * -EBUSY: action cannot be performed due to busy device resources, may + * succeed if the affected queues or even the entire port are in a stopped + * state (see rte_eth_dev_rx_queue_stop() and rte_eth_dev_stop()). + */ +int +rte_flow_validate(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error); + +/** + * Create a flow rule on a given port. + * + * @param port_id + * Port identifier of Ethernet device. + * @param[in] attr + * Flow rule attributes. + * @param[in] pattern + * Pattern specification (list terminated by the END pattern item). + * @param[in] actions + * Associated actions (list terminated by the END action). + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * A valid handle in case of success, NULL otherwise and rte_errno is set + * to the positive version of one of the error codes defined for + * rte_flow_validate(). + */ +struct rte_flow * +rte_flow_create(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error); + +/** + * Destroy a flow rule on a given port. + * + * Failure to destroy a flow rule handle may occur when other flow rules + * depend on it, and destroying it would result in an inconsistent state. + * + * This function is only guaranteed to succeed if handles are destroyed in + * reverse order of their creation. + * + * @param port_id + * Port identifier of Ethernet device. + * @param flow + * Flow rule handle to destroy. + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +rte_flow_destroy(uint8_t port_id, + struct rte_flow *flow, + struct rte_flow_error *error); + +/** + * Destroy all flow rules associated with a port. + * + * In the unlikely event of failure, handles are still considered destroyed + * and no longer valid but the port must be assumed to be in an inconsistent + * state. + * + * @param port_id + * Port identifier of Ethernet device. + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +rte_flow_flush(uint8_t port_id, + struct rte_flow_error *error); + +/** + * Query an existing flow rule. + * + * This function allows retrieving flow-specific data such as counters. + * Data is gathered by special actions which must be present in the flow + * rule definition. + * + * \see RTE_FLOW_ACTION_TYPE_COUNT + * + * @param port_id + * Port identifier of Ethernet device. + * @param flow + * Flow rule handle to query. + * @param action + * Action type to query. + * @param[in, out] data + * Pointer to storage for the associated query data type. + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +rte_flow_query(uint8_t port_id, + struct rte_flow *flow, + enum rte_flow_action_type action, + void *data, + struct rte_flow_error *error); + +#ifdef __cplusplus +} +#endif + +#endif /* RTE_FLOW_H_ */ diff --git a/src/dpdk/lib/librte_ether/rte_flow_driver.h b/src/dpdk/lib/librte_ether/rte_flow_driver.h new file mode 100644 index 00000000..da5749d5 --- /dev/null +++ b/src/dpdk/lib/librte_ether/rte_flow_driver.h @@ -0,0 +1,182 @@ +/*- + * BSD LICENSE + * + * Copyright 2016 6WIND S.A. + * Copyright 2016 Mellanox. + * + * 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 6WIND S.A. 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. + */ + +#ifndef RTE_FLOW_DRIVER_H_ +#define RTE_FLOW_DRIVER_H_ + +/** + * @file + * RTE generic flow API (driver side) + * + * This file provides implementation helpers for internal use by PMDs, they + * are not intended to be exposed to applications and are not subject to ABI + * versioning. + */ + +#include <stdint.h> + +#include <rte_errno.h> +#include "rte_ethdev.h" +#include "rte_flow.h" + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * Generic flow operations structure implemented and returned by PMDs. + * + * To implement this API, PMDs must handle the RTE_ETH_FILTER_GENERIC filter + * type in their .filter_ctrl callback function (struct eth_dev_ops) as well + * as the RTE_ETH_FILTER_GET filter operation. + * + * If successful, this operation must result in a pointer to a PMD-specific + * struct rte_flow_ops written to the argument address as described below: + * + * \code + * + * // PMD filter_ctrl callback + * + * static const struct rte_flow_ops pmd_flow_ops = { ... }; + * + * switch (filter_type) { + * case RTE_ETH_FILTER_GENERIC: + * if (filter_op != RTE_ETH_FILTER_GET) + * return -EINVAL; + * *(const void **)arg = &pmd_flow_ops; + * return 0; + * } + * + * \endcode + * + * See also rte_flow_ops_get(). + * + * These callback functions are not supposed to be used by applications + * directly, which must rely on the API defined in rte_flow.h. + * + * Public-facing wrapper functions perform a few consistency checks so that + * unimplemented (i.e. NULL) callbacks simply return -ENOTSUP. These + * callbacks otherwise only differ by their first argument (with port ID + * already resolved to a pointer to struct rte_eth_dev). + */ +struct rte_flow_ops { + /** See rte_flow_validate(). */ + int (*validate) + (struct rte_eth_dev *, + const struct rte_flow_attr *, + const struct rte_flow_item [], + const struct rte_flow_action [], + struct rte_flow_error *); + /** See rte_flow_create(). */ + struct rte_flow *(*create) + (struct rte_eth_dev *, + const struct rte_flow_attr *, + const struct rte_flow_item [], + const struct rte_flow_action [], + struct rte_flow_error *); + /** See rte_flow_destroy(). */ + int (*destroy) + (struct rte_eth_dev *, + struct rte_flow *, + struct rte_flow_error *); + /** See rte_flow_flush(). */ + int (*flush) + (struct rte_eth_dev *, + struct rte_flow_error *); + /** See rte_flow_query(). */ + int (*query) + (struct rte_eth_dev *, + struct rte_flow *, + enum rte_flow_action_type, + void *, + struct rte_flow_error *); +}; + +/** + * Initialize generic flow error structure. + * + * This function also sets rte_errno to a given value. + * + * @param[out] error + * Pointer to flow error structure (may be NULL). + * @param code + * Related error code (rte_errno). + * @param type + * Cause field and error types. + * @param cause + * Object responsible for the error. + * @param message + * Human-readable error message. + * + * @return + * Error code. + */ +static inline int +rte_flow_error_set(struct rte_flow_error *error, + int code, + enum rte_flow_error_type type, + const void *cause, + const char *message) +{ + if (error) { + *error = (struct rte_flow_error){ + .type = type, + .cause = cause, + .message = message, + }; + } + rte_errno = code; + return code; +} + +/** + * Get generic flow operations structure from a port. + * + * @param port_id + * Port identifier to query. + * @param[out] error + * Pointer to flow error structure. + * + * @return + * The flow operations structure associated with port_id, NULL in case of + * error, in which case rte_errno is set and the error structure contains + * additional details. + */ +const struct rte_flow_ops * +rte_flow_ops_get(uint8_t port_id, struct rte_flow_error *error); + +#ifdef __cplusplus +} +#endif + +#endif /* RTE_FLOW_DRIVER_H_ */ |