1 /* SPDX-License-Identifier: BSD-3-Clause 2 * Copyright(c) 2010-2017 Intel Corporation 3 */ 4 5 #ifndef _RTE_ETHDEV_H_ 6 #define _RTE_ETHDEV_H_ 7 8 /** 9 * @file 10 * 11 * RTE Ethernet Device API 12 * 13 * The Ethernet Device API is composed of two parts: 14 * 15 * - The application-oriented Ethernet API that includes functions to setup 16 * an Ethernet device (configure it, setup its RX and TX queues and start it), 17 * to get its MAC address, the speed and the status of its physical link, 18 * to receive and to transmit packets, and so on. 19 * 20 * - The driver-oriented Ethernet API that exports functions allowing 21 * an Ethernet Poll Mode Driver (PMD) to allocate an Ethernet device instance, 22 * create memzone for HW rings and process registered callbacks, and so on. 23 * PMDs should include ethdev_driver.h instead of this header. 24 * 25 * By default, all the functions of the Ethernet Device API exported by a PMD 26 * are lock-free functions which assume to not be invoked in parallel on 27 * different logical cores to work on the same target object. For instance, 28 * the receive function of a PMD cannot be invoked in parallel on two logical 29 * cores to poll the same RX queue [of the same port]. Of course, this function 30 * can be invoked in parallel by different logical cores on different RX queues. 31 * It is the responsibility of the upper level application to enforce this rule. 32 * 33 * If needed, parallel accesses by multiple logical cores to shared queues 34 * shall be explicitly protected by dedicated inline lock-aware functions 35 * built on top of their corresponding lock-free functions of the PMD API. 36 * 37 * In all functions of the Ethernet API, the Ethernet device is 38 * designated by an integer >= 0 named the device port identifier. 39 * 40 * At the Ethernet driver level, Ethernet devices are represented by a generic 41 * data structure of type *rte_eth_dev*. 42 * 43 * Ethernet devices are dynamically registered during the PCI probing phase 44 * performed at EAL initialization time. 45 * When an Ethernet device is being probed, an *rte_eth_dev* structure and 46 * a new port identifier are allocated for that device. Then, the eth_dev_init() 47 * function supplied by the Ethernet driver matching the probed PCI 48 * device is invoked to properly initialize the device. 49 * 50 * The role of the device init function consists of resetting the hardware, 51 * checking access to Non-volatile Memory (NVM), reading the MAC address 52 * from NVM etc. 53 * 54 * If the device init operation is successful, the correspondence between 55 * the port identifier assigned to the new device and its associated 56 * *rte_eth_dev* structure is effectively registered. 57 * Otherwise, both the *rte_eth_dev* structure and the port identifier are 58 * freed. 59 * 60 * The functions exported by the application Ethernet API to setup a device 61 * designated by its port identifier must be invoked in the following order: 62 * - rte_eth_dev_configure() 63 * - rte_eth_tx_queue_setup() 64 * - rte_eth_rx_queue_setup() 65 * - rte_eth_dev_start() 66 * 67 * Then, the network application can invoke, in any order, the functions 68 * exported by the Ethernet API to get the MAC address of a given device, to 69 * get the speed and the status of a device physical link, to receive/transmit 70 * [burst of] packets, and so on. 71 * 72 * If the application wants to change the configuration (i.e. call 73 * rte_eth_dev_configure(), rte_eth_tx_queue_setup(), or 74 * rte_eth_rx_queue_setup()), it must call rte_eth_dev_stop() first to stop the 75 * device and then do the reconfiguration before calling rte_eth_dev_start() 76 * again. The transmit and receive functions should not be invoked when the 77 * device is stopped. 78 * 79 * Please note that some configuration is not stored between calls to 80 * rte_eth_dev_stop()/rte_eth_dev_start(). The following configuration will 81 * be retained: 82 * 83 * - MTU 84 * - flow control settings 85 * - receive mode configuration (promiscuous mode, all-multicast mode, 86 * hardware checksum mode, RSS/VMDQ settings etc.) 87 * - VLAN filtering configuration 88 * - default MAC address 89 * - MAC addresses supplied to MAC address array 90 * - flow director filtering mode (but not filtering rules) 91 * - NIC queue statistics mappings 92 * 93 * Any other configuration will not be stored and will need to be re-entered 94 * before a call to rte_eth_dev_start(). 95 * 96 * Finally, a network application can close an Ethernet device by invoking the 97 * rte_eth_dev_close() function. 98 * 99 * Each function of the application Ethernet API invokes a specific function 100 * of the PMD that controls the target device designated by its port 101 * identifier. 102 * For this purpose, all device-specific functions of an Ethernet driver are 103 * supplied through a set of pointers contained in a generic structure of type 104 * *eth_dev_ops*. 105 * The address of the *eth_dev_ops* structure is stored in the *rte_eth_dev* 106 * structure by the device init function of the Ethernet driver, which is 107 * invoked during the PCI probing phase, as explained earlier. 108 * 109 * In other words, each function of the Ethernet API simply retrieves the 110 * *rte_eth_dev* structure associated with the device port identifier and 111 * performs an indirect invocation of the corresponding driver function 112 * supplied in the *eth_dev_ops* structure of the *rte_eth_dev* structure. 113 * 114 * For performance reasons, the address of the burst-oriented RX and TX 115 * functions of the Ethernet driver are not contained in the *eth_dev_ops* 116 * structure. Instead, they are directly stored at the beginning of the 117 * *rte_eth_dev* structure to avoid an extra indirect memory access during 118 * their invocation. 119 * 120 * RTE ethernet device drivers do not use interrupts for transmitting or 121 * receiving. Instead, Ethernet drivers export Poll-Mode receive and transmit 122 * functions to applications. 123 * Both receive and transmit functions are packet-burst oriented to minimize 124 * their cost per packet through the following optimizations: 125 * 126 * - Sharing among multiple packets the incompressible cost of the 127 * invocation of receive/transmit functions. 128 * 129 * - Enabling receive/transmit functions to take advantage of burst-oriented 130 * hardware features (L1 cache, prefetch instructions, NIC head/tail 131 * registers) to minimize the number of CPU cycles per packet, for instance, 132 * by avoiding useless read memory accesses to ring descriptors, or by 133 * systematically using arrays of pointers that exactly fit L1 cache line 134 * boundaries and sizes. 135 * 136 * The burst-oriented receive function does not provide any error notification, 137 * to avoid the corresponding overhead. As a hint, the upper-level application 138 * might check the status of the device link once being systematically returned 139 * a 0 value by the receive function of the driver for a given number of tries. 140 */ 141 142 #ifdef __cplusplus 143 extern "C" { 144 #endif 145 146 #include <stdint.h> 147 148 /* Use this macro to check if LRO API is supported */ 149 #define RTE_ETHDEV_HAS_LRO_SUPPORT 150 151 /* Alias RTE_LIBRTE_ETHDEV_DEBUG for backward compatibility. */ 152 #ifdef RTE_LIBRTE_ETHDEV_DEBUG 153 #define RTE_ETHDEV_DEBUG_RX 154 #define RTE_ETHDEV_DEBUG_TX 155 #endif 156 157 #include <rte_compat.h> 158 #include <rte_log.h> 159 #include <rte_interrupts.h> 160 #include <rte_dev.h> 161 #include <rte_devargs.h> 162 #include <rte_errno.h> 163 #include <rte_common.h> 164 #include <rte_config.h> 165 #include <rte_ether.h> 166 #include <rte_power_intrinsics.h> 167 168 #include "rte_ethdev_trace_fp.h" 169 #include "rte_dev_info.h" 170 171 extern int rte_eth_dev_logtype; 172 173 #define RTE_ETHDEV_LOG(level, ...) \ 174 rte_log(RTE_LOG_ ## level, rte_eth_dev_logtype, "" __VA_ARGS__) 175 176 struct rte_mbuf; 177 178 /** 179 * Initializes a device iterator. 180 * 181 * This iterator allows accessing a list of devices matching some devargs. 182 * 183 * @param iter 184 * Device iterator handle initialized by the function. 185 * The fields bus_str and cls_str might be dynamically allocated, 186 * and could be freed by calling rte_eth_iterator_cleanup(). 187 * 188 * @param devargs 189 * Device description string. 190 * 191 * @return 192 * 0 on successful initialization, negative otherwise. 193 */ 194 int rte_eth_iterator_init(struct rte_dev_iterator *iter, const char *devargs); 195 196 /** 197 * Iterates on devices with devargs filter. 198 * The ownership is not checked. 199 * 200 * The next port id is returned, and the iterator is updated. 201 * 202 * @param iter 203 * Device iterator handle initialized by rte_eth_iterator_init(). 204 * Some fields bus_str and cls_str might be freed when no more port is found, 205 * by calling rte_eth_iterator_cleanup(). 206 * 207 * @return 208 * A port id if found, RTE_MAX_ETHPORTS otherwise. 209 */ 210 uint16_t rte_eth_iterator_next(struct rte_dev_iterator *iter); 211 212 /** 213 * Free some allocated fields of the iterator. 214 * 215 * This function is automatically called by rte_eth_iterator_next() 216 * on the last iteration (i.e. when no more matching port is found). 217 * 218 * It is safe to call this function twice; it will do nothing more. 219 * 220 * @param iter 221 * Device iterator handle initialized by rte_eth_iterator_init(). 222 * The fields bus_str and cls_str are freed if needed. 223 */ 224 void rte_eth_iterator_cleanup(struct rte_dev_iterator *iter); 225 226 /** 227 * Macro to iterate over all ethdev ports matching some devargs. 228 * 229 * If a break is done before the end of the loop, 230 * the function rte_eth_iterator_cleanup() must be called. 231 * 232 * @param id 233 * Iterated port id of type uint16_t. 234 * @param devargs 235 * Device parameters input as string of type char*. 236 * @param iter 237 * Iterator handle of type struct rte_dev_iterator, used internally. 238 */ 239 #define RTE_ETH_FOREACH_MATCHING_DEV(id, devargs, iter) \ 240 for (rte_eth_iterator_init(iter, devargs), \ 241 id = rte_eth_iterator_next(iter); \ 242 id != RTE_MAX_ETHPORTS; \ 243 id = rte_eth_iterator_next(iter)) 244 245 /** 246 * A structure used to retrieve statistics for an Ethernet port. 247 * Not all statistics fields in struct rte_eth_stats are supported 248 * by any type of network interface card (NIC). If any statistics 249 * field is not supported, its value is 0. 250 * All byte-related statistics do not include Ethernet FCS regardless 251 * of whether these bytes have been delivered to the application 252 * (see DEV_RX_OFFLOAD_KEEP_CRC). 253 */ 254 struct rte_eth_stats { 255 uint64_t ipackets; /**< Total number of successfully received packets. */ 256 uint64_t opackets; /**< Total number of successfully transmitted packets.*/ 257 uint64_t ibytes; /**< Total number of successfully received bytes. */ 258 uint64_t obytes; /**< Total number of successfully transmitted bytes. */ 259 uint64_t imissed; 260 /**< Total of RX packets dropped by the HW, 261 * because there are no available buffer (i.e. RX queues are full). 262 */ 263 uint64_t ierrors; /**< Total number of erroneous received packets. */ 264 uint64_t oerrors; /**< Total number of failed transmitted packets. */ 265 uint64_t rx_nombuf; /**< Total number of RX mbuf allocation failures. */ 266 /* Queue stats are limited to max 256 queues */ 267 uint64_t q_ipackets[RTE_ETHDEV_QUEUE_STAT_CNTRS]; 268 /**< Total number of queue RX packets. */ 269 uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS]; 270 /**< Total number of queue TX packets. */ 271 uint64_t q_ibytes[RTE_ETHDEV_QUEUE_STAT_CNTRS]; 272 /**< Total number of successfully received queue bytes. */ 273 uint64_t q_obytes[RTE_ETHDEV_QUEUE_STAT_CNTRS]; 274 /**< Total number of successfully transmitted queue bytes. */ 275 uint64_t q_errors[RTE_ETHDEV_QUEUE_STAT_CNTRS]; 276 /**< Total number of queue packets received that are dropped. */ 277 }; 278 279 /** 280 * Device supported speeds bitmap flags 281 */ 282 #define ETH_LINK_SPEED_AUTONEG (0 << 0) /**< Autonegotiate (all speeds) */ 283 #define ETH_LINK_SPEED_FIXED (1 << 0) /**< Disable autoneg (fixed speed) */ 284 #define ETH_LINK_SPEED_10M_HD (1 << 1) /**< 10 Mbps half-duplex */ 285 #define ETH_LINK_SPEED_10M (1 << 2) /**< 10 Mbps full-duplex */ 286 #define ETH_LINK_SPEED_100M_HD (1 << 3) /**< 100 Mbps half-duplex */ 287 #define ETH_LINK_SPEED_100M (1 << 4) /**< 100 Mbps full-duplex */ 288 #define ETH_LINK_SPEED_1G (1 << 5) /**< 1 Gbps */ 289 #define ETH_LINK_SPEED_2_5G (1 << 6) /**< 2.5 Gbps */ 290 #define ETH_LINK_SPEED_5G (1 << 7) /**< 5 Gbps */ 291 #define ETH_LINK_SPEED_10G (1 << 8) /**< 10 Gbps */ 292 #define ETH_LINK_SPEED_20G (1 << 9) /**< 20 Gbps */ 293 #define ETH_LINK_SPEED_25G (1 << 10) /**< 25 Gbps */ 294 #define ETH_LINK_SPEED_40G (1 << 11) /**< 40 Gbps */ 295 #define ETH_LINK_SPEED_50G (1 << 12) /**< 50 Gbps */ 296 #define ETH_LINK_SPEED_56G (1 << 13) /**< 56 Gbps */ 297 #define ETH_LINK_SPEED_100G (1 << 14) /**< 100 Gbps */ 298 #define ETH_LINK_SPEED_200G (1 << 15) /**< 200 Gbps */ 299 300 /** 301 * Ethernet numeric link speeds in Mbps 302 */ 303 #define ETH_SPEED_NUM_NONE 0 /**< Not defined */ 304 #define ETH_SPEED_NUM_10M 10 /**< 10 Mbps */ 305 #define ETH_SPEED_NUM_100M 100 /**< 100 Mbps */ 306 #define ETH_SPEED_NUM_1G 1000 /**< 1 Gbps */ 307 #define ETH_SPEED_NUM_2_5G 2500 /**< 2.5 Gbps */ 308 #define ETH_SPEED_NUM_5G 5000 /**< 5 Gbps */ 309 #define ETH_SPEED_NUM_10G 10000 /**< 10 Gbps */ 310 #define ETH_SPEED_NUM_20G 20000 /**< 20 Gbps */ 311 #define ETH_SPEED_NUM_25G 25000 /**< 25 Gbps */ 312 #define ETH_SPEED_NUM_40G 40000 /**< 40 Gbps */ 313 #define ETH_SPEED_NUM_50G 50000 /**< 50 Gbps */ 314 #define ETH_SPEED_NUM_56G 56000 /**< 56 Gbps */ 315 #define ETH_SPEED_NUM_100G 100000 /**< 100 Gbps */ 316 #define ETH_SPEED_NUM_200G 200000 /**< 200 Gbps */ 317 #define ETH_SPEED_NUM_UNKNOWN UINT32_MAX /**< Unknown */ 318 319 /** 320 * A structure used to retrieve link-level information of an Ethernet port. 321 */ 322 __extension__ 323 struct rte_eth_link { 324 uint32_t link_speed; /**< ETH_SPEED_NUM_ */ 325 uint16_t link_duplex : 1; /**< ETH_LINK_[HALF/FULL]_DUPLEX */ 326 uint16_t link_autoneg : 1; /**< ETH_LINK_[AUTONEG/FIXED] */ 327 uint16_t link_status : 1; /**< ETH_LINK_[DOWN/UP] */ 328 } __rte_aligned(8); /**< aligned for atomic64 read/write */ 329 330 /* Utility constants */ 331 #define ETH_LINK_HALF_DUPLEX 0 /**< Half-duplex connection (see link_duplex). */ 332 #define ETH_LINK_FULL_DUPLEX 1 /**< Full-duplex connection (see link_duplex). */ 333 #define ETH_LINK_DOWN 0 /**< Link is down (see link_status). */ 334 #define ETH_LINK_UP 1 /**< Link is up (see link_status). */ 335 #define ETH_LINK_FIXED 0 /**< No autonegotiation (see link_autoneg). */ 336 #define ETH_LINK_AUTONEG 1 /**< Autonegotiated (see link_autoneg). */ 337 #define RTE_ETH_LINK_MAX_STR_LEN 40 /**< Max length of default link string. */ 338 339 /** 340 * A structure used to configure the ring threshold registers of an RX/TX 341 * queue for an Ethernet port. 342 */ 343 struct rte_eth_thresh { 344 uint8_t pthresh; /**< Ring prefetch threshold. */ 345 uint8_t hthresh; /**< Ring host threshold. */ 346 uint8_t wthresh; /**< Ring writeback threshold. */ 347 }; 348 349 /** 350 * Simple flags are used for rte_eth_conf.rxmode.mq_mode. 351 */ 352 #define ETH_MQ_RX_RSS_FLAG 0x1 353 #define ETH_MQ_RX_DCB_FLAG 0x2 354 #define ETH_MQ_RX_VMDQ_FLAG 0x4 355 356 /** 357 * A set of values to identify what method is to be used to route 358 * packets to multiple queues. 359 */ 360 enum rte_eth_rx_mq_mode { 361 /** None of DCB,RSS or VMDQ mode */ 362 ETH_MQ_RX_NONE = 0, 363 364 /** For RX side, only RSS is on */ 365 ETH_MQ_RX_RSS = ETH_MQ_RX_RSS_FLAG, 366 /** For RX side,only DCB is on. */ 367 ETH_MQ_RX_DCB = ETH_MQ_RX_DCB_FLAG, 368 /** Both DCB and RSS enable */ 369 ETH_MQ_RX_DCB_RSS = ETH_MQ_RX_RSS_FLAG | ETH_MQ_RX_DCB_FLAG, 370 371 /** Only VMDQ, no RSS nor DCB */ 372 ETH_MQ_RX_VMDQ_ONLY = ETH_MQ_RX_VMDQ_FLAG, 373 /** RSS mode with VMDQ */ 374 ETH_MQ_RX_VMDQ_RSS = ETH_MQ_RX_RSS_FLAG | ETH_MQ_RX_VMDQ_FLAG, 375 /** Use VMDQ+DCB to route traffic to queues */ 376 ETH_MQ_RX_VMDQ_DCB = ETH_MQ_RX_VMDQ_FLAG | ETH_MQ_RX_DCB_FLAG, 377 /** Enable both VMDQ and DCB in VMDq */ 378 ETH_MQ_RX_VMDQ_DCB_RSS = ETH_MQ_RX_RSS_FLAG | ETH_MQ_RX_DCB_FLAG | 379 ETH_MQ_RX_VMDQ_FLAG, 380 }; 381 382 /** 383 * for rx mq mode backward compatible 384 */ 385 #define ETH_RSS ETH_MQ_RX_RSS 386 #define VMDQ_DCB ETH_MQ_RX_VMDQ_DCB 387 #define ETH_DCB_RX ETH_MQ_RX_DCB 388 389 /** 390 * A set of values to identify what method is to be used to transmit 391 * packets using multi-TCs. 392 */ 393 enum rte_eth_tx_mq_mode { 394 ETH_MQ_TX_NONE = 0, /**< It is in neither DCB nor VT mode. */ 395 ETH_MQ_TX_DCB, /**< For TX side,only DCB is on. */ 396 ETH_MQ_TX_VMDQ_DCB, /**< For TX side,both DCB and VT is on. */ 397 ETH_MQ_TX_VMDQ_ONLY, /**< Only VT on, no DCB */ 398 }; 399 400 /** 401 * for tx mq mode backward compatible 402 */ 403 #define ETH_DCB_NONE ETH_MQ_TX_NONE 404 #define ETH_VMDQ_DCB_TX ETH_MQ_TX_VMDQ_DCB 405 #define ETH_DCB_TX ETH_MQ_TX_DCB 406 407 /** 408 * A structure used to configure the RX features of an Ethernet port. 409 */ 410 struct rte_eth_rxmode { 411 /** The multi-queue packet distribution mode to be used, e.g. RSS. */ 412 enum rte_eth_rx_mq_mode mq_mode; 413 uint32_t max_rx_pkt_len; /**< Only used if JUMBO_FRAME enabled. */ 414 /** Maximum allowed size of LRO aggregated packet. */ 415 uint32_t max_lro_pkt_size; 416 uint16_t split_hdr_size; /**< hdr buf size (header_split enabled).*/ 417 /** 418 * Per-port Rx offloads to be set using DEV_RX_OFFLOAD_* flags. 419 * Only offloads set on rx_offload_capa field on rte_eth_dev_info 420 * structure are allowed to be set. 421 */ 422 uint64_t offloads; 423 424 uint64_t reserved_64s[2]; /**< Reserved for future fields */ 425 void *reserved_ptrs[2]; /**< Reserved for future fields */ 426 }; 427 428 /** 429 * VLAN types to indicate if it is for single VLAN, inner VLAN or outer VLAN. 430 * Note that single VLAN is treated the same as inner VLAN. 431 */ 432 enum rte_vlan_type { 433 ETH_VLAN_TYPE_UNKNOWN = 0, 434 ETH_VLAN_TYPE_INNER, /**< Inner VLAN. */ 435 ETH_VLAN_TYPE_OUTER, /**< Single VLAN, or outer VLAN. */ 436 ETH_VLAN_TYPE_MAX, 437 }; 438 439 /** 440 * A structure used to describe a vlan filter. 441 * If the bit corresponding to a VID is set, such VID is on. 442 */ 443 struct rte_vlan_filter_conf { 444 uint64_t ids[64]; 445 }; 446 447 /** 448 * A structure used to configure the Receive Side Scaling (RSS) feature 449 * of an Ethernet port. 450 * If not NULL, the *rss_key* pointer of the *rss_conf* structure points 451 * to an array holding the RSS key to use for hashing specific header 452 * fields of received packets. The length of this array should be indicated 453 * by *rss_key_len* below. Otherwise, a default random hash key is used by 454 * the device driver. 455 * 456 * The *rss_key_len* field of the *rss_conf* structure indicates the length 457 * in bytes of the array pointed by *rss_key*. To be compatible, this length 458 * will be checked in i40e only. Others assume 40 bytes to be used as before. 459 * 460 * The *rss_hf* field of the *rss_conf* structure indicates the different 461 * types of IPv4/IPv6 packets to which the RSS hashing must be applied. 462 * Supplying an *rss_hf* equal to zero disables the RSS feature. 463 */ 464 struct rte_eth_rss_conf { 465 uint8_t *rss_key; /**< If not NULL, 40-byte hash key. */ 466 uint8_t rss_key_len; /**< hash key length in bytes. */ 467 uint64_t rss_hf; /**< Hash functions to apply - see below. */ 468 }; 469 470 /* 471 * A packet can be identified by hardware as different flow types. Different 472 * NIC hardware may support different flow types. 473 * Basically, the NIC hardware identifies the flow type as deep protocol as 474 * possible, and exclusively. For example, if a packet is identified as 475 * 'RTE_ETH_FLOW_NONFRAG_IPV4_TCP', it will not be any of other flow types, 476 * though it is an actual IPV4 packet. 477 */ 478 #define RTE_ETH_FLOW_UNKNOWN 0 479 #define RTE_ETH_FLOW_RAW 1 480 #define RTE_ETH_FLOW_IPV4 2 481 #define RTE_ETH_FLOW_FRAG_IPV4 3 482 #define RTE_ETH_FLOW_NONFRAG_IPV4_TCP 4 483 #define RTE_ETH_FLOW_NONFRAG_IPV4_UDP 5 484 #define RTE_ETH_FLOW_NONFRAG_IPV4_SCTP 6 485 #define RTE_ETH_FLOW_NONFRAG_IPV4_OTHER 7 486 #define RTE_ETH_FLOW_IPV6 8 487 #define RTE_ETH_FLOW_FRAG_IPV6 9 488 #define RTE_ETH_FLOW_NONFRAG_IPV6_TCP 10 489 #define RTE_ETH_FLOW_NONFRAG_IPV6_UDP 11 490 #define RTE_ETH_FLOW_NONFRAG_IPV6_SCTP 12 491 #define RTE_ETH_FLOW_NONFRAG_IPV6_OTHER 13 492 #define RTE_ETH_FLOW_L2_PAYLOAD 14 493 #define RTE_ETH_FLOW_IPV6_EX 15 494 #define RTE_ETH_FLOW_IPV6_TCP_EX 16 495 #define RTE_ETH_FLOW_IPV6_UDP_EX 17 496 #define RTE_ETH_FLOW_PORT 18 497 /**< Consider device port number as a flow differentiator */ 498 #define RTE_ETH_FLOW_VXLAN 19 /**< VXLAN protocol based flow */ 499 #define RTE_ETH_FLOW_GENEVE 20 /**< GENEVE protocol based flow */ 500 #define RTE_ETH_FLOW_NVGRE 21 /**< NVGRE protocol based flow */ 501 #define RTE_ETH_FLOW_VXLAN_GPE 22 /**< VXLAN-GPE protocol based flow */ 502 #define RTE_ETH_FLOW_GTPU 23 /**< GTPU protocol based flow */ 503 #define RTE_ETH_FLOW_MAX 24 504 505 /* 506 * Below macros are defined for RSS offload types, they can be used to 507 * fill rte_eth_rss_conf.rss_hf or rte_flow_action_rss.types. 508 */ 509 #define ETH_RSS_IPV4 (1ULL << 2) 510 #define ETH_RSS_FRAG_IPV4 (1ULL << 3) 511 #define ETH_RSS_NONFRAG_IPV4_TCP (1ULL << 4) 512 #define ETH_RSS_NONFRAG_IPV4_UDP (1ULL << 5) 513 #define ETH_RSS_NONFRAG_IPV4_SCTP (1ULL << 6) 514 #define ETH_RSS_NONFRAG_IPV4_OTHER (1ULL << 7) 515 #define ETH_RSS_IPV6 (1ULL << 8) 516 #define ETH_RSS_FRAG_IPV6 (1ULL << 9) 517 #define ETH_RSS_NONFRAG_IPV6_TCP (1ULL << 10) 518 #define ETH_RSS_NONFRAG_IPV6_UDP (1ULL << 11) 519 #define ETH_RSS_NONFRAG_IPV6_SCTP (1ULL << 12) 520 #define ETH_RSS_NONFRAG_IPV6_OTHER (1ULL << 13) 521 #define ETH_RSS_L2_PAYLOAD (1ULL << 14) 522 #define ETH_RSS_IPV6_EX (1ULL << 15) 523 #define ETH_RSS_IPV6_TCP_EX (1ULL << 16) 524 #define ETH_RSS_IPV6_UDP_EX (1ULL << 17) 525 #define ETH_RSS_PORT (1ULL << 18) 526 #define ETH_RSS_VXLAN (1ULL << 19) 527 #define ETH_RSS_GENEVE (1ULL << 20) 528 #define ETH_RSS_NVGRE (1ULL << 21) 529 #define ETH_RSS_GTPU (1ULL << 23) 530 #define ETH_RSS_ETH (1ULL << 24) 531 #define ETH_RSS_S_VLAN (1ULL << 25) 532 #define ETH_RSS_C_VLAN (1ULL << 26) 533 #define ETH_RSS_ESP (1ULL << 27) 534 #define ETH_RSS_AH (1ULL << 28) 535 #define ETH_RSS_L2TPV3 (1ULL << 29) 536 #define ETH_RSS_PFCP (1ULL << 30) 537 #define ETH_RSS_PPPOE (1ULL << 31) 538 #define ETH_RSS_ECPRI (1ULL << 32) 539 #define ETH_RSS_MPLS (1ULL << 33) 540 541 /* 542 * We use the following macros to combine with above ETH_RSS_* for 543 * more specific input set selection. These bits are defined starting 544 * from the high end of the 64 bits. 545 * Note: If we use above ETH_RSS_* without SRC/DST_ONLY, it represents 546 * both SRC and DST are taken into account. If SRC_ONLY and DST_ONLY of 547 * the same level are used simultaneously, it is the same case as none of 548 * them are added. 549 */ 550 #define ETH_RSS_L3_SRC_ONLY (1ULL << 63) 551 #define ETH_RSS_L3_DST_ONLY (1ULL << 62) 552 #define ETH_RSS_L4_SRC_ONLY (1ULL << 61) 553 #define ETH_RSS_L4_DST_ONLY (1ULL << 60) 554 #define ETH_RSS_L2_SRC_ONLY (1ULL << 59) 555 #define ETH_RSS_L2_DST_ONLY (1ULL << 58) 556 557 /* 558 * Only select IPV6 address prefix as RSS input set according to 559 * https://tools.ietf.org/html/rfc6052 560 * Must be combined with ETH_RSS_IPV6, ETH_RSS_NONFRAG_IPV6_UDP, 561 * ETH_RSS_NONFRAG_IPV6_TCP, ETH_RSS_NONFRAG_IPV6_SCTP. 562 */ 563 #define RTE_ETH_RSS_L3_PRE32 (1ULL << 57) 564 #define RTE_ETH_RSS_L3_PRE40 (1ULL << 56) 565 #define RTE_ETH_RSS_L3_PRE48 (1ULL << 55) 566 #define RTE_ETH_RSS_L3_PRE56 (1ULL << 54) 567 #define RTE_ETH_RSS_L3_PRE64 (1ULL << 53) 568 #define RTE_ETH_RSS_L3_PRE96 (1ULL << 52) 569 570 /* 571 * Use the following macros to combine with the above layers 572 * to choose inner and outer layers or both for RSS computation. 573 * Bits 50 and 51 are reserved for this. 574 */ 575 576 /** 577 * level 0, requests the default behavior. 578 * Depending on the packet type, it can mean outermost, innermost, 579 * anything in between or even no RSS. 580 * It basically stands for the innermost encapsulation level RSS 581 * can be performed on according to PMD and device capabilities. 582 */ 583 #define ETH_RSS_LEVEL_PMD_DEFAULT (0ULL << 50) 584 585 /** 586 * level 1, requests RSS to be performed on the outermost packet 587 * encapsulation level. 588 */ 589 #define ETH_RSS_LEVEL_OUTERMOST (1ULL << 50) 590 591 /** 592 * level 2, requests RSS to be performed on the specified inner packet 593 * encapsulation level, from outermost to innermost (lower to higher values). 594 */ 595 #define ETH_RSS_LEVEL_INNERMOST (2ULL << 50) 596 #define ETH_RSS_LEVEL_MASK (3ULL << 50) 597 598 #define ETH_RSS_LEVEL(rss_hf) ((rss_hf & ETH_RSS_LEVEL_MASK) >> 50) 599 600 /** 601 * For input set change of hash filter, if SRC_ONLY and DST_ONLY of 602 * the same level are used simultaneously, it is the same case as 603 * none of them are added. 604 * 605 * @param rss_hf 606 * RSS types with SRC/DST_ONLY. 607 * @return 608 * RSS types. 609 */ 610 static inline uint64_t 611 rte_eth_rss_hf_refine(uint64_t rss_hf) 612 { 613 if ((rss_hf & ETH_RSS_L3_SRC_ONLY) && (rss_hf & ETH_RSS_L3_DST_ONLY)) 614 rss_hf &= ~(ETH_RSS_L3_SRC_ONLY | ETH_RSS_L3_DST_ONLY); 615 616 if ((rss_hf & ETH_RSS_L4_SRC_ONLY) && (rss_hf & ETH_RSS_L4_DST_ONLY)) 617 rss_hf &= ~(ETH_RSS_L4_SRC_ONLY | ETH_RSS_L4_DST_ONLY); 618 619 return rss_hf; 620 } 621 622 #define ETH_RSS_IPV6_PRE32 ( \ 623 ETH_RSS_IPV6 | \ 624 RTE_ETH_RSS_L3_PRE32) 625 626 #define ETH_RSS_IPV6_PRE40 ( \ 627 ETH_RSS_IPV6 | \ 628 RTE_ETH_RSS_L3_PRE40) 629 630 #define ETH_RSS_IPV6_PRE48 ( \ 631 ETH_RSS_IPV6 | \ 632 RTE_ETH_RSS_L3_PRE48) 633 634 #define ETH_RSS_IPV6_PRE56 ( \ 635 ETH_RSS_IPV6 | \ 636 RTE_ETH_RSS_L3_PRE56) 637 638 #define ETH_RSS_IPV6_PRE64 ( \ 639 ETH_RSS_IPV6 | \ 640 RTE_ETH_RSS_L3_PRE64) 641 642 #define ETH_RSS_IPV6_PRE96 ( \ 643 ETH_RSS_IPV6 | \ 644 RTE_ETH_RSS_L3_PRE96) 645 646 #define ETH_RSS_IPV6_PRE32_UDP ( \ 647 ETH_RSS_NONFRAG_IPV6_UDP | \ 648 RTE_ETH_RSS_L3_PRE32) 649 650 #define ETH_RSS_IPV6_PRE40_UDP ( \ 651 ETH_RSS_NONFRAG_IPV6_UDP | \ 652 RTE_ETH_RSS_L3_PRE40) 653 654 #define ETH_RSS_IPV6_PRE48_UDP ( \ 655 ETH_RSS_NONFRAG_IPV6_UDP | \ 656 RTE_ETH_RSS_L3_PRE48) 657 658 #define ETH_RSS_IPV6_PRE56_UDP ( \ 659 ETH_RSS_NONFRAG_IPV6_UDP | \ 660 RTE_ETH_RSS_L3_PRE56) 661 662 #define ETH_RSS_IPV6_PRE64_UDP ( \ 663 ETH_RSS_NONFRAG_IPV6_UDP | \ 664 RTE_ETH_RSS_L3_PRE64) 665 666 #define ETH_RSS_IPV6_PRE96_UDP ( \ 667 ETH_RSS_NONFRAG_IPV6_UDP | \ 668 RTE_ETH_RSS_L3_PRE96) 669 670 #define ETH_RSS_IPV6_PRE32_TCP ( \ 671 ETH_RSS_NONFRAG_IPV6_TCP | \ 672 RTE_ETH_RSS_L3_PRE32) 673 674 #define ETH_RSS_IPV6_PRE40_TCP ( \ 675 ETH_RSS_NONFRAG_IPV6_TCP | \ 676 RTE_ETH_RSS_L3_PRE40) 677 678 #define ETH_RSS_IPV6_PRE48_TCP ( \ 679 ETH_RSS_NONFRAG_IPV6_TCP | \ 680 RTE_ETH_RSS_L3_PRE48) 681 682 #define ETH_RSS_IPV6_PRE56_TCP ( \ 683 ETH_RSS_NONFRAG_IPV6_TCP | \ 684 RTE_ETH_RSS_L3_PRE56) 685 686 #define ETH_RSS_IPV6_PRE64_TCP ( \ 687 ETH_RSS_NONFRAG_IPV6_TCP | \ 688 RTE_ETH_RSS_L3_PRE64) 689 690 #define ETH_RSS_IPV6_PRE96_TCP ( \ 691 ETH_RSS_NONFRAG_IPV6_TCP | \ 692 RTE_ETH_RSS_L3_PRE96) 693 694 #define ETH_RSS_IPV6_PRE32_SCTP ( \ 695 ETH_RSS_NONFRAG_IPV6_SCTP | \ 696 RTE_ETH_RSS_L3_PRE32) 697 698 #define ETH_RSS_IPV6_PRE40_SCTP ( \ 699 ETH_RSS_NONFRAG_IPV6_SCTP | \ 700 RTE_ETH_RSS_L3_PRE40) 701 702 #define ETH_RSS_IPV6_PRE48_SCTP ( \ 703 ETH_RSS_NONFRAG_IPV6_SCTP | \ 704 RTE_ETH_RSS_L3_PRE48) 705 706 #define ETH_RSS_IPV6_PRE56_SCTP ( \ 707 ETH_RSS_NONFRAG_IPV6_SCTP | \ 708 RTE_ETH_RSS_L3_PRE56) 709 710 #define ETH_RSS_IPV6_PRE64_SCTP ( \ 711 ETH_RSS_NONFRAG_IPV6_SCTP | \ 712 RTE_ETH_RSS_L3_PRE64) 713 714 #define ETH_RSS_IPV6_PRE96_SCTP ( \ 715 ETH_RSS_NONFRAG_IPV6_SCTP | \ 716 RTE_ETH_RSS_L3_PRE96) 717 718 #define ETH_RSS_IP ( \ 719 ETH_RSS_IPV4 | \ 720 ETH_RSS_FRAG_IPV4 | \ 721 ETH_RSS_NONFRAG_IPV4_OTHER | \ 722 ETH_RSS_IPV6 | \ 723 ETH_RSS_FRAG_IPV6 | \ 724 ETH_RSS_NONFRAG_IPV6_OTHER | \ 725 ETH_RSS_IPV6_EX) 726 727 #define ETH_RSS_UDP ( \ 728 ETH_RSS_NONFRAG_IPV4_UDP | \ 729 ETH_RSS_NONFRAG_IPV6_UDP | \ 730 ETH_RSS_IPV6_UDP_EX) 731 732 #define ETH_RSS_TCP ( \ 733 ETH_RSS_NONFRAG_IPV4_TCP | \ 734 ETH_RSS_NONFRAG_IPV6_TCP | \ 735 ETH_RSS_IPV6_TCP_EX) 736 737 #define ETH_RSS_SCTP ( \ 738 ETH_RSS_NONFRAG_IPV4_SCTP | \ 739 ETH_RSS_NONFRAG_IPV6_SCTP) 740 741 #define ETH_RSS_TUNNEL ( \ 742 ETH_RSS_VXLAN | \ 743 ETH_RSS_GENEVE | \ 744 ETH_RSS_NVGRE) 745 746 #define ETH_RSS_VLAN ( \ 747 ETH_RSS_S_VLAN | \ 748 ETH_RSS_C_VLAN) 749 750 /**< Mask of valid RSS hash protocols */ 751 #define ETH_RSS_PROTO_MASK ( \ 752 ETH_RSS_IPV4 | \ 753 ETH_RSS_FRAG_IPV4 | \ 754 ETH_RSS_NONFRAG_IPV4_TCP | \ 755 ETH_RSS_NONFRAG_IPV4_UDP | \ 756 ETH_RSS_NONFRAG_IPV4_SCTP | \ 757 ETH_RSS_NONFRAG_IPV4_OTHER | \ 758 ETH_RSS_IPV6 | \ 759 ETH_RSS_FRAG_IPV6 | \ 760 ETH_RSS_NONFRAG_IPV6_TCP | \ 761 ETH_RSS_NONFRAG_IPV6_UDP | \ 762 ETH_RSS_NONFRAG_IPV6_SCTP | \ 763 ETH_RSS_NONFRAG_IPV6_OTHER | \ 764 ETH_RSS_L2_PAYLOAD | \ 765 ETH_RSS_IPV6_EX | \ 766 ETH_RSS_IPV6_TCP_EX | \ 767 ETH_RSS_IPV6_UDP_EX | \ 768 ETH_RSS_PORT | \ 769 ETH_RSS_VXLAN | \ 770 ETH_RSS_GENEVE | \ 771 ETH_RSS_NVGRE | \ 772 ETH_RSS_MPLS) 773 774 /* 775 * Definitions used for redirection table entry size. 776 * Some RSS RETA sizes may not be supported by some drivers, check the 777 * documentation or the description of relevant functions for more details. 778 */ 779 #define ETH_RSS_RETA_SIZE_64 64 780 #define ETH_RSS_RETA_SIZE_128 128 781 #define ETH_RSS_RETA_SIZE_256 256 782 #define ETH_RSS_RETA_SIZE_512 512 783 #define RTE_RETA_GROUP_SIZE 64 784 785 /* Definitions used for VMDQ and DCB functionality */ 786 #define ETH_VMDQ_MAX_VLAN_FILTERS 64 /**< Maximum nb. of VMDQ vlan filters. */ 787 #define ETH_DCB_NUM_USER_PRIORITIES 8 /**< Maximum nb. of DCB priorities. */ 788 #define ETH_VMDQ_DCB_NUM_QUEUES 128 /**< Maximum nb. of VMDQ DCB queues. */ 789 #define ETH_DCB_NUM_QUEUES 128 /**< Maximum nb. of DCB queues. */ 790 791 /* DCB capability defines */ 792 #define ETH_DCB_PG_SUPPORT 0x00000001 /**< Priority Group(ETS) support. */ 793 #define ETH_DCB_PFC_SUPPORT 0x00000002 /**< Priority Flow Control support. */ 794 795 /* Definitions used for VLAN Offload functionality */ 796 #define ETH_VLAN_STRIP_OFFLOAD 0x0001 /**< VLAN Strip On/Off */ 797 #define ETH_VLAN_FILTER_OFFLOAD 0x0002 /**< VLAN Filter On/Off */ 798 #define ETH_VLAN_EXTEND_OFFLOAD 0x0004 /**< VLAN Extend On/Off */ 799 #define ETH_QINQ_STRIP_OFFLOAD 0x0008 /**< QINQ Strip On/Off */ 800 801 /* Definitions used for mask VLAN setting */ 802 #define ETH_VLAN_STRIP_MASK 0x0001 /**< VLAN Strip setting mask */ 803 #define ETH_VLAN_FILTER_MASK 0x0002 /**< VLAN Filter setting mask*/ 804 #define ETH_VLAN_EXTEND_MASK 0x0004 /**< VLAN Extend setting mask*/ 805 #define ETH_QINQ_STRIP_MASK 0x0008 /**< QINQ Strip setting mask */ 806 #define ETH_VLAN_ID_MAX 0x0FFF /**< VLAN ID is in lower 12 bits*/ 807 808 /* Definitions used for receive MAC address */ 809 #define ETH_NUM_RECEIVE_MAC_ADDR 128 /**< Maximum nb. of receive mac addr. */ 810 811 /* Definitions used for unicast hash */ 812 #define ETH_VMDQ_NUM_UC_HASH_ARRAY 128 /**< Maximum nb. of UC hash array. */ 813 814 /* Definitions used for VMDQ pool rx mode setting */ 815 #define ETH_VMDQ_ACCEPT_UNTAG 0x0001 /**< accept untagged packets. */ 816 #define ETH_VMDQ_ACCEPT_HASH_MC 0x0002 /**< accept packets in multicast table . */ 817 #define ETH_VMDQ_ACCEPT_HASH_UC 0x0004 /**< accept packets in unicast table. */ 818 #define ETH_VMDQ_ACCEPT_BROADCAST 0x0008 /**< accept broadcast packets. */ 819 #define ETH_VMDQ_ACCEPT_MULTICAST 0x0010 /**< multicast promiscuous. */ 820 821 /** Maximum nb. of vlan per mirror rule */ 822 #define ETH_MIRROR_MAX_VLANS 64 823 824 #define ETH_MIRROR_VIRTUAL_POOL_UP 0x01 /**< Virtual Pool uplink Mirroring. */ 825 #define ETH_MIRROR_UPLINK_PORT 0x02 /**< Uplink Port Mirroring. */ 826 #define ETH_MIRROR_DOWNLINK_PORT 0x04 /**< Downlink Port Mirroring. */ 827 #define ETH_MIRROR_VLAN 0x08 /**< VLAN Mirroring. */ 828 #define ETH_MIRROR_VIRTUAL_POOL_DOWN 0x10 /**< Virtual Pool downlink Mirroring. */ 829 830 /** 831 * A structure used to configure VLAN traffic mirror of an Ethernet port. 832 */ 833 struct rte_eth_vlan_mirror { 834 uint64_t vlan_mask; /**< mask for valid VLAN ID. */ 835 /** VLAN ID list for vlan mirroring. */ 836 uint16_t vlan_id[ETH_MIRROR_MAX_VLANS]; 837 }; 838 839 /** 840 * A structure used to configure traffic mirror of an Ethernet port. 841 */ 842 struct rte_eth_mirror_conf { 843 uint8_t rule_type; /**< Mirroring rule type */ 844 uint8_t dst_pool; /**< Destination pool for this mirror rule. */ 845 uint64_t pool_mask; /**< Bitmap of pool for pool mirroring */ 846 /** VLAN ID setting for VLAN mirroring. */ 847 struct rte_eth_vlan_mirror vlan; 848 }; 849 850 /** 851 * A structure used to configure 64 entries of Redirection Table of the 852 * Receive Side Scaling (RSS) feature of an Ethernet port. To configure 853 * more than 64 entries supported by hardware, an array of this structure 854 * is needed. 855 */ 856 struct rte_eth_rss_reta_entry64 { 857 uint64_t mask; 858 /**< Mask bits indicate which entries need to be updated/queried. */ 859 uint16_t reta[RTE_RETA_GROUP_SIZE]; 860 /**< Group of 64 redirection table entries. */ 861 }; 862 863 /** 864 * This enum indicates the possible number of traffic classes 865 * in DCB configurations 866 */ 867 enum rte_eth_nb_tcs { 868 ETH_4_TCS = 4, /**< 4 TCs with DCB. */ 869 ETH_8_TCS = 8 /**< 8 TCs with DCB. */ 870 }; 871 872 /** 873 * This enum indicates the possible number of queue pools 874 * in VMDQ configurations. 875 */ 876 enum rte_eth_nb_pools { 877 ETH_8_POOLS = 8, /**< 8 VMDq pools. */ 878 ETH_16_POOLS = 16, /**< 16 VMDq pools. */ 879 ETH_32_POOLS = 32, /**< 32 VMDq pools. */ 880 ETH_64_POOLS = 64 /**< 64 VMDq pools. */ 881 }; 882 883 /* This structure may be extended in future. */ 884 struct rte_eth_dcb_rx_conf { 885 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs */ 886 /** Traffic class each UP mapped to. */ 887 uint8_t dcb_tc[ETH_DCB_NUM_USER_PRIORITIES]; 888 }; 889 890 struct rte_eth_vmdq_dcb_tx_conf { 891 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools. */ 892 /** Traffic class each UP mapped to. */ 893 uint8_t dcb_tc[ETH_DCB_NUM_USER_PRIORITIES]; 894 }; 895 896 struct rte_eth_dcb_tx_conf { 897 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs. */ 898 /** Traffic class each UP mapped to. */ 899 uint8_t dcb_tc[ETH_DCB_NUM_USER_PRIORITIES]; 900 }; 901 902 struct rte_eth_vmdq_tx_conf { 903 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq mode, 64 pools. */ 904 }; 905 906 /** 907 * A structure used to configure the VMDQ+DCB feature 908 * of an Ethernet port. 909 * 910 * Using this feature, packets are routed to a pool of queues, based 911 * on the vlan id in the vlan tag, and then to a specific queue within 912 * that pool, using the user priority vlan tag field. 913 * 914 * A default pool may be used, if desired, to route all traffic which 915 * does not match the vlan filter rules. 916 */ 917 struct rte_eth_vmdq_dcb_conf { 918 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools */ 919 uint8_t enable_default_pool; /**< If non-zero, use a default pool */ 920 uint8_t default_pool; /**< The default pool, if applicable */ 921 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */ 922 struct { 923 uint16_t vlan_id; /**< The vlan id of the received frame */ 924 uint64_t pools; /**< Bitmask of pools for packet rx */ 925 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */ 926 uint8_t dcb_tc[ETH_DCB_NUM_USER_PRIORITIES]; 927 /**< Selects a queue in a pool */ 928 }; 929 930 /** 931 * A structure used to configure the VMDQ feature of an Ethernet port when 932 * not combined with the DCB feature. 933 * 934 * Using this feature, packets are routed to a pool of queues. By default, 935 * the pool selection is based on the MAC address, the vlan id in the 936 * vlan tag as specified in the pool_map array. 937 * Passing the ETH_VMDQ_ACCEPT_UNTAG in the rx_mode field allows pool 938 * selection using only the MAC address. MAC address to pool mapping is done 939 * using the rte_eth_dev_mac_addr_add function, with the pool parameter 940 * corresponding to the pool id. 941 * 942 * Queue selection within the selected pool will be done using RSS when 943 * it is enabled or revert to the first queue of the pool if not. 944 * 945 * A default pool may be used, if desired, to route all traffic which 946 * does not match the vlan filter rules or any pool MAC address. 947 */ 948 struct rte_eth_vmdq_rx_conf { 949 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq only mode, 8 or 64 pools */ 950 uint8_t enable_default_pool; /**< If non-zero, use a default pool */ 951 uint8_t default_pool; /**< The default pool, if applicable */ 952 uint8_t enable_loop_back; /**< Enable VT loop back */ 953 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */ 954 uint32_t rx_mode; /**< Flags from ETH_VMDQ_ACCEPT_* */ 955 struct { 956 uint16_t vlan_id; /**< The vlan id of the received frame */ 957 uint64_t pools; /**< Bitmask of pools for packet rx */ 958 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */ 959 }; 960 961 /** 962 * A structure used to configure the TX features of an Ethernet port. 963 */ 964 struct rte_eth_txmode { 965 enum rte_eth_tx_mq_mode mq_mode; /**< TX multi-queues mode. */ 966 /** 967 * Per-port Tx offloads to be set using DEV_TX_OFFLOAD_* flags. 968 * Only offloads set on tx_offload_capa field on rte_eth_dev_info 969 * structure are allowed to be set. 970 */ 971 uint64_t offloads; 972 973 uint16_t pvid; 974 __extension__ 975 uint8_t hw_vlan_reject_tagged : 1, 976 /**< If set, reject sending out tagged pkts */ 977 hw_vlan_reject_untagged : 1, 978 /**< If set, reject sending out untagged pkts */ 979 hw_vlan_insert_pvid : 1; 980 /**< If set, enable port based VLAN insertion */ 981 982 uint64_t reserved_64s[2]; /**< Reserved for future fields */ 983 void *reserved_ptrs[2]; /**< Reserved for future fields */ 984 }; 985 986 /** 987 * @warning 988 * @b EXPERIMENTAL: this structure may change without prior notice. 989 * 990 * A structure used to configure an Rx packet segment to split. 991 * 992 * If RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT flag is set in offloads field, 993 * the PMD will split the received packets into multiple segments 994 * according to the specification in the description array: 995 * 996 * - The first network buffer will be allocated from the memory pool, 997 * specified in the first array element, the second buffer, from the 998 * pool in the second element, and so on. 999 * 1000 * - The offsets from the segment description elements specify 1001 * the data offset from the buffer beginning except the first mbuf. 1002 * The first segment offset is added with RTE_PKTMBUF_HEADROOM. 1003 * 1004 * - The lengths in the elements define the maximal data amount 1005 * being received to each segment. The receiving starts with filling 1006 * up the first mbuf data buffer up to specified length. If the 1007 * there are data remaining (packet is longer than buffer in the first 1008 * mbuf) the following data will be pushed to the next segment 1009 * up to its own length, and so on. 1010 * 1011 * - If the length in the segment description element is zero 1012 * the actual buffer size will be deduced from the appropriate 1013 * memory pool properties. 1014 * 1015 * - If there is not enough elements to describe the buffer for entire 1016 * packet of maximal length the following parameters will be used 1017 * for the all remaining segments: 1018 * - pool from the last valid element 1019 * - the buffer size from this pool 1020 * - zero offset 1021 */ 1022 struct rte_eth_rxseg_split { 1023 struct rte_mempool *mp; /**< Memory pool to allocate segment from. */ 1024 uint16_t length; /**< Segment data length, configures split point. */ 1025 uint16_t offset; /**< Data offset from beginning of mbuf data buffer. */ 1026 uint32_t reserved; /**< Reserved field. */ 1027 }; 1028 1029 /** 1030 * @warning 1031 * @b EXPERIMENTAL: this structure may change without prior notice. 1032 * 1033 * A common structure used to describe Rx packet segment properties. 1034 */ 1035 union rte_eth_rxseg { 1036 /* The settings for buffer split offload. */ 1037 struct rte_eth_rxseg_split split; 1038 /* The other features settings should be added here. */ 1039 }; 1040 1041 /** 1042 * A structure used to configure an RX ring of an Ethernet port. 1043 */ 1044 struct rte_eth_rxconf { 1045 struct rte_eth_thresh rx_thresh; /**< RX ring threshold registers. */ 1046 uint16_t rx_free_thresh; /**< Drives the freeing of RX descriptors. */ 1047 uint8_t rx_drop_en; /**< Drop packets if no descriptors are available. */ 1048 uint8_t rx_deferred_start; /**< Do not start queue with rte_eth_dev_start(). */ 1049 uint16_t rx_nseg; /**< Number of descriptions in rx_seg array. */ 1050 /** 1051 * Per-queue Rx offloads to be set using DEV_RX_OFFLOAD_* flags. 1052 * Only offloads set on rx_queue_offload_capa or rx_offload_capa 1053 * fields on rte_eth_dev_info structure are allowed to be set. 1054 */ 1055 uint64_t offloads; 1056 /** 1057 * Points to the array of segment descriptions for an entire packet. 1058 * Array elements are properties for consecutive Rx segments. 1059 * 1060 * The supported capabilities of receiving segmentation is reported 1061 * in rte_eth_dev_info.rx_seg_capa field. 1062 */ 1063 union rte_eth_rxseg *rx_seg; 1064 1065 uint64_t reserved_64s[2]; /**< Reserved for future fields */ 1066 void *reserved_ptrs[2]; /**< Reserved for future fields */ 1067 }; 1068 1069 /** 1070 * A structure used to configure a TX ring of an Ethernet port. 1071 */ 1072 struct rte_eth_txconf { 1073 struct rte_eth_thresh tx_thresh; /**< TX ring threshold registers. */ 1074 uint16_t tx_rs_thresh; /**< Drives the setting of RS bit on TXDs. */ 1075 uint16_t tx_free_thresh; /**< Start freeing TX buffers if there are 1076 less free descriptors than this value. */ 1077 1078 uint8_t tx_deferred_start; /**< Do not start queue with rte_eth_dev_start(). */ 1079 /** 1080 * Per-queue Tx offloads to be set using DEV_TX_OFFLOAD_* flags. 1081 * Only offloads set on tx_queue_offload_capa or tx_offload_capa 1082 * fields on rte_eth_dev_info structure are allowed to be set. 1083 */ 1084 uint64_t offloads; 1085 1086 uint64_t reserved_64s[2]; /**< Reserved for future fields */ 1087 void *reserved_ptrs[2]; /**< Reserved for future fields */ 1088 }; 1089 1090 /** 1091 * @warning 1092 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 1093 * 1094 * A structure used to return the hairpin capabilities that are supported. 1095 */ 1096 struct rte_eth_hairpin_cap { 1097 /** The max number of hairpin queues (different bindings). */ 1098 uint16_t max_nb_queues; 1099 /** Max number of Rx queues to be connected to one Tx queue. */ 1100 uint16_t max_rx_2_tx; 1101 /** Max number of Tx queues to be connected to one Rx queue. */ 1102 uint16_t max_tx_2_rx; 1103 uint16_t max_nb_desc; /**< The max num of descriptors. */ 1104 }; 1105 1106 #define RTE_ETH_MAX_HAIRPIN_PEERS 32 1107 1108 /** 1109 * @warning 1110 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 1111 * 1112 * A structure used to hold hairpin peer data. 1113 */ 1114 struct rte_eth_hairpin_peer { 1115 uint16_t port; /**< Peer port. */ 1116 uint16_t queue; /**< Peer queue. */ 1117 }; 1118 1119 /** 1120 * @warning 1121 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 1122 * 1123 * A structure used to configure hairpin binding. 1124 */ 1125 struct rte_eth_hairpin_conf { 1126 uint32_t peer_count:16; /**< The number of peers. */ 1127 1128 /** 1129 * Explicit Tx flow rule mode. 1130 * One hairpin pair of queues should have the same attribute. 1131 * 1132 * - When set, the user should be responsible for inserting the hairpin 1133 * Tx part flows and removing them. 1134 * - When clear, the PMD will try to handle the Tx part of the flows, 1135 * e.g., by splitting one flow into two parts. 1136 */ 1137 uint32_t tx_explicit:1; 1138 1139 /** 1140 * Manually bind hairpin queues. 1141 * One hairpin pair of queues should have the same attribute. 1142 * 1143 * - When set, to enable hairpin, the user should call the hairpin bind 1144 * function after all the queues are set up properly and the ports are 1145 * started. Also, the hairpin unbind function should be called 1146 * accordingly before stopping a port that with hairpin configured. 1147 * - When clear, the PMD will try to enable the hairpin with the queues 1148 * configured automatically during port start. 1149 */ 1150 uint32_t manual_bind:1; 1151 uint32_t reserved:14; /**< Reserved bits. */ 1152 struct rte_eth_hairpin_peer peers[RTE_ETH_MAX_HAIRPIN_PEERS]; 1153 }; 1154 1155 /** 1156 * A structure contains information about HW descriptor ring limitations. 1157 */ 1158 struct rte_eth_desc_lim { 1159 uint16_t nb_max; /**< Max allowed number of descriptors. */ 1160 uint16_t nb_min; /**< Min allowed number of descriptors. */ 1161 uint16_t nb_align; /**< Number of descriptors should be aligned to. */ 1162 1163 /** 1164 * Max allowed number of segments per whole packet. 1165 * 1166 * - For TSO packet this is the total number of data descriptors allowed 1167 * by device. 1168 * 1169 * @see nb_mtu_seg_max 1170 */ 1171 uint16_t nb_seg_max; 1172 1173 /** 1174 * Max number of segments per one MTU. 1175 * 1176 * - For non-TSO packet, this is the maximum allowed number of segments 1177 * in a single transmit packet. 1178 * 1179 * - For TSO packet each segment within the TSO may span up to this 1180 * value. 1181 * 1182 * @see nb_seg_max 1183 */ 1184 uint16_t nb_mtu_seg_max; 1185 }; 1186 1187 /** 1188 * This enum indicates the flow control mode 1189 */ 1190 enum rte_eth_fc_mode { 1191 RTE_FC_NONE = 0, /**< Disable flow control. */ 1192 RTE_FC_RX_PAUSE, /**< RX pause frame, enable flowctrl on TX side. */ 1193 RTE_FC_TX_PAUSE, /**< TX pause frame, enable flowctrl on RX side. */ 1194 RTE_FC_FULL /**< Enable flow control on both side. */ 1195 }; 1196 1197 /** 1198 * A structure used to configure Ethernet flow control parameter. 1199 * These parameters will be configured into the register of the NIC. 1200 * Please refer to the corresponding data sheet for proper value. 1201 */ 1202 struct rte_eth_fc_conf { 1203 uint32_t high_water; /**< High threshold value to trigger XOFF */ 1204 uint32_t low_water; /**< Low threshold value to trigger XON */ 1205 uint16_t pause_time; /**< Pause quota in the Pause frame */ 1206 uint16_t send_xon; /**< Is XON frame need be sent */ 1207 enum rte_eth_fc_mode mode; /**< Link flow control mode */ 1208 uint8_t mac_ctrl_frame_fwd; /**< Forward MAC control frames */ 1209 uint8_t autoneg; /**< Use Pause autoneg */ 1210 }; 1211 1212 /** 1213 * A structure used to configure Ethernet priority flow control parameter. 1214 * These parameters will be configured into the register of the NIC. 1215 * Please refer to the corresponding data sheet for proper value. 1216 */ 1217 struct rte_eth_pfc_conf { 1218 struct rte_eth_fc_conf fc; /**< General flow control parameter. */ 1219 uint8_t priority; /**< VLAN User Priority. */ 1220 }; 1221 1222 /** 1223 * Tunnel type for device-specific classifier configuration. 1224 * @see rte_eth_udp_tunnel 1225 */ 1226 enum rte_eth_tunnel_type { 1227 RTE_TUNNEL_TYPE_NONE = 0, 1228 RTE_TUNNEL_TYPE_VXLAN, 1229 RTE_TUNNEL_TYPE_GENEVE, 1230 RTE_TUNNEL_TYPE_TEREDO, 1231 RTE_TUNNEL_TYPE_NVGRE, 1232 RTE_TUNNEL_TYPE_IP_IN_GRE, 1233 RTE_L2_TUNNEL_TYPE_E_TAG, 1234 RTE_TUNNEL_TYPE_VXLAN_GPE, 1235 RTE_TUNNEL_TYPE_ECPRI, 1236 RTE_TUNNEL_TYPE_MAX, 1237 }; 1238 1239 /* Deprecated API file for rte_eth_dev_filter_* functions */ 1240 #include "rte_eth_ctrl.h" 1241 1242 /** 1243 * Memory space that can be configured to store Flow Director filters 1244 * in the board memory. 1245 */ 1246 enum rte_fdir_pballoc_type { 1247 RTE_FDIR_PBALLOC_64K = 0, /**< 64k. */ 1248 RTE_FDIR_PBALLOC_128K, /**< 128k. */ 1249 RTE_FDIR_PBALLOC_256K, /**< 256k. */ 1250 }; 1251 1252 /** 1253 * Select report mode of FDIR hash information in RX descriptors. 1254 */ 1255 enum rte_fdir_status_mode { 1256 RTE_FDIR_NO_REPORT_STATUS = 0, /**< Never report FDIR hash. */ 1257 RTE_FDIR_REPORT_STATUS, /**< Only report FDIR hash for matching pkts. */ 1258 RTE_FDIR_REPORT_STATUS_ALWAYS, /**< Always report FDIR hash. */ 1259 }; 1260 1261 /** 1262 * A structure used to configure the Flow Director (FDIR) feature 1263 * of an Ethernet port. 1264 * 1265 * If mode is RTE_FDIR_MODE_NONE, the pballoc value is ignored. 1266 */ 1267 struct rte_fdir_conf { 1268 enum rte_fdir_mode mode; /**< Flow Director mode. */ 1269 enum rte_fdir_pballoc_type pballoc; /**< Space for FDIR filters. */ 1270 enum rte_fdir_status_mode status; /**< How to report FDIR hash. */ 1271 /** RX queue of packets matching a "drop" filter in perfect mode. */ 1272 uint8_t drop_queue; 1273 struct rte_eth_fdir_masks mask; 1274 struct rte_eth_fdir_flex_conf flex_conf; 1275 /**< Flex payload configuration. */ 1276 }; 1277 1278 /** 1279 * UDP tunneling configuration. 1280 * 1281 * Used to configure the classifier of a device, 1282 * associating an UDP port with a type of tunnel. 1283 * 1284 * Some NICs may need such configuration to properly parse a tunnel 1285 * with any standard or custom UDP port. 1286 */ 1287 struct rte_eth_udp_tunnel { 1288 uint16_t udp_port; /**< UDP port used for the tunnel. */ 1289 uint8_t prot_type; /**< Tunnel type. @see rte_eth_tunnel_type */ 1290 }; 1291 1292 /** 1293 * A structure used to enable/disable specific device interrupts. 1294 */ 1295 struct rte_intr_conf { 1296 /** enable/disable lsc interrupt. 0 (default) - disable, 1 enable */ 1297 uint32_t lsc:1; 1298 /** enable/disable rxq interrupt. 0 (default) - disable, 1 enable */ 1299 uint32_t rxq:1; 1300 /** enable/disable rmv interrupt. 0 (default) - disable, 1 enable */ 1301 uint32_t rmv:1; 1302 }; 1303 1304 /** 1305 * A structure used to configure an Ethernet port. 1306 * Depending upon the RX multi-queue mode, extra advanced 1307 * configuration settings may be needed. 1308 */ 1309 struct rte_eth_conf { 1310 uint32_t link_speeds; /**< bitmap of ETH_LINK_SPEED_XXX of speeds to be 1311 used. ETH_LINK_SPEED_FIXED disables link 1312 autonegotiation, and a unique speed shall be 1313 set. Otherwise, the bitmap defines the set of 1314 speeds to be advertised. If the special value 1315 ETH_LINK_SPEED_AUTONEG (0) is used, all speeds 1316 supported are advertised. */ 1317 struct rte_eth_rxmode rxmode; /**< Port RX configuration. */ 1318 struct rte_eth_txmode txmode; /**< Port TX configuration. */ 1319 uint32_t lpbk_mode; /**< Loopback operation mode. By default the value 1320 is 0, meaning the loopback mode is disabled. 1321 Read the datasheet of given ethernet controller 1322 for details. The possible values of this field 1323 are defined in implementation of each driver. */ 1324 struct { 1325 struct rte_eth_rss_conf rss_conf; /**< Port RSS configuration */ 1326 struct rte_eth_vmdq_dcb_conf vmdq_dcb_conf; 1327 /**< Port vmdq+dcb configuration. */ 1328 struct rte_eth_dcb_rx_conf dcb_rx_conf; 1329 /**< Port dcb RX configuration. */ 1330 struct rte_eth_vmdq_rx_conf vmdq_rx_conf; 1331 /**< Port vmdq RX configuration. */ 1332 } rx_adv_conf; /**< Port RX filtering configuration. */ 1333 union { 1334 struct rte_eth_vmdq_dcb_tx_conf vmdq_dcb_tx_conf; 1335 /**< Port vmdq+dcb TX configuration. */ 1336 struct rte_eth_dcb_tx_conf dcb_tx_conf; 1337 /**< Port dcb TX configuration. */ 1338 struct rte_eth_vmdq_tx_conf vmdq_tx_conf; 1339 /**< Port vmdq TX configuration. */ 1340 } tx_adv_conf; /**< Port TX DCB configuration (union). */ 1341 /** Currently,Priority Flow Control(PFC) are supported,if DCB with PFC 1342 is needed,and the variable must be set ETH_DCB_PFC_SUPPORT. */ 1343 uint32_t dcb_capability_en; 1344 struct rte_fdir_conf fdir_conf; /**< FDIR configuration. DEPRECATED */ 1345 struct rte_intr_conf intr_conf; /**< Interrupt mode configuration. */ 1346 }; 1347 1348 /** 1349 * RX offload capabilities of a device. 1350 */ 1351 #define DEV_RX_OFFLOAD_VLAN_STRIP 0x00000001 1352 #define DEV_RX_OFFLOAD_IPV4_CKSUM 0x00000002 1353 #define DEV_RX_OFFLOAD_UDP_CKSUM 0x00000004 1354 #define DEV_RX_OFFLOAD_TCP_CKSUM 0x00000008 1355 #define DEV_RX_OFFLOAD_TCP_LRO 0x00000010 1356 #define DEV_RX_OFFLOAD_QINQ_STRIP 0x00000020 1357 #define DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM 0x00000040 1358 #define DEV_RX_OFFLOAD_MACSEC_STRIP 0x00000080 1359 #define DEV_RX_OFFLOAD_HEADER_SPLIT 0x00000100 1360 #define DEV_RX_OFFLOAD_VLAN_FILTER 0x00000200 1361 #define DEV_RX_OFFLOAD_VLAN_EXTEND 0x00000400 1362 #define DEV_RX_OFFLOAD_JUMBO_FRAME 0x00000800 1363 #define DEV_RX_OFFLOAD_SCATTER 0x00002000 1364 /** 1365 * Timestamp is set by the driver in RTE_MBUF_DYNFIELD_TIMESTAMP_NAME 1366 * and RTE_MBUF_DYNFLAG_RX_TIMESTAMP_NAME is set in ol_flags. 1367 * The mbuf field and flag are registered when the offload is configured. 1368 */ 1369 #define DEV_RX_OFFLOAD_TIMESTAMP 0x00004000 1370 #define DEV_RX_OFFLOAD_SECURITY 0x00008000 1371 #define DEV_RX_OFFLOAD_KEEP_CRC 0x00010000 1372 #define DEV_RX_OFFLOAD_SCTP_CKSUM 0x00020000 1373 #define DEV_RX_OFFLOAD_OUTER_UDP_CKSUM 0x00040000 1374 #define DEV_RX_OFFLOAD_RSS_HASH 0x00080000 1375 #define RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT 0x00100000 1376 1377 #define DEV_RX_OFFLOAD_CHECKSUM (DEV_RX_OFFLOAD_IPV4_CKSUM | \ 1378 DEV_RX_OFFLOAD_UDP_CKSUM | \ 1379 DEV_RX_OFFLOAD_TCP_CKSUM) 1380 #define DEV_RX_OFFLOAD_VLAN (DEV_RX_OFFLOAD_VLAN_STRIP | \ 1381 DEV_RX_OFFLOAD_VLAN_FILTER | \ 1382 DEV_RX_OFFLOAD_VLAN_EXTEND | \ 1383 DEV_RX_OFFLOAD_QINQ_STRIP) 1384 1385 /* 1386 * If new Rx offload capabilities are defined, they also must be 1387 * mentioned in rte_rx_offload_names in rte_ethdev.c file. 1388 */ 1389 1390 /** 1391 * TX offload capabilities of a device. 1392 */ 1393 #define DEV_TX_OFFLOAD_VLAN_INSERT 0x00000001 1394 #define DEV_TX_OFFLOAD_IPV4_CKSUM 0x00000002 1395 #define DEV_TX_OFFLOAD_UDP_CKSUM 0x00000004 1396 #define DEV_TX_OFFLOAD_TCP_CKSUM 0x00000008 1397 #define DEV_TX_OFFLOAD_SCTP_CKSUM 0x00000010 1398 #define DEV_TX_OFFLOAD_TCP_TSO 0x00000020 1399 #define DEV_TX_OFFLOAD_UDP_TSO 0x00000040 1400 #define DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM 0x00000080 /**< Used for tunneling packet. */ 1401 #define DEV_TX_OFFLOAD_QINQ_INSERT 0x00000100 1402 #define DEV_TX_OFFLOAD_VXLAN_TNL_TSO 0x00000200 /**< Used for tunneling packet. */ 1403 #define DEV_TX_OFFLOAD_GRE_TNL_TSO 0x00000400 /**< Used for tunneling packet. */ 1404 #define DEV_TX_OFFLOAD_IPIP_TNL_TSO 0x00000800 /**< Used for tunneling packet. */ 1405 #define DEV_TX_OFFLOAD_GENEVE_TNL_TSO 0x00001000 /**< Used for tunneling packet. */ 1406 #define DEV_TX_OFFLOAD_MACSEC_INSERT 0x00002000 1407 #define DEV_TX_OFFLOAD_MT_LOCKFREE 0x00004000 1408 /**< Multiple threads can invoke rte_eth_tx_burst() concurrently on the same 1409 * tx queue without SW lock. 1410 */ 1411 #define DEV_TX_OFFLOAD_MULTI_SEGS 0x00008000 1412 /**< Device supports multi segment send. */ 1413 #define DEV_TX_OFFLOAD_MBUF_FAST_FREE 0x00010000 1414 /**< Device supports optimization for fast release of mbufs. 1415 * When set application must guarantee that per-queue all mbufs comes from 1416 * the same mempool and has refcnt = 1. 1417 */ 1418 #define DEV_TX_OFFLOAD_SECURITY 0x00020000 1419 /** 1420 * Device supports generic UDP tunneled packet TSO. 1421 * Application must set PKT_TX_TUNNEL_UDP and other mbuf fields required 1422 * for tunnel TSO. 1423 */ 1424 #define DEV_TX_OFFLOAD_UDP_TNL_TSO 0x00040000 1425 /** 1426 * Device supports generic IP tunneled packet TSO. 1427 * Application must set PKT_TX_TUNNEL_IP and other mbuf fields required 1428 * for tunnel TSO. 1429 */ 1430 #define DEV_TX_OFFLOAD_IP_TNL_TSO 0x00080000 1431 /** Device supports outer UDP checksum */ 1432 #define DEV_TX_OFFLOAD_OUTER_UDP_CKSUM 0x00100000 1433 /** 1434 * Device sends on time read from RTE_MBUF_DYNFIELD_TIMESTAMP_NAME 1435 * if RTE_MBUF_DYNFLAG_TX_TIMESTAMP_NAME is set in ol_flags. 1436 * The mbuf field and flag are registered when the offload is configured. 1437 */ 1438 #define DEV_TX_OFFLOAD_SEND_ON_TIMESTAMP 0x00200000 1439 /* 1440 * If new Tx offload capabilities are defined, they also must be 1441 * mentioned in rte_tx_offload_names in rte_ethdev.c file. 1442 */ 1443 1444 /**@{@name Device capabilities 1445 * Non-offload capabilities reported in rte_eth_dev_info.dev_capa. 1446 */ 1447 /** Device supports Rx queue setup after device started. */ 1448 #define RTE_ETH_DEV_CAPA_RUNTIME_RX_QUEUE_SETUP 0x00000001 1449 /** Device supports Tx queue setup after device started. */ 1450 #define RTE_ETH_DEV_CAPA_RUNTIME_TX_QUEUE_SETUP 0x00000002 1451 /**@}*/ 1452 1453 /* 1454 * Fallback default preferred Rx/Tx port parameters. 1455 * These are used if an application requests default parameters 1456 * but the PMD does not provide preferred values. 1457 */ 1458 #define RTE_ETH_DEV_FALLBACK_RX_RINGSIZE 512 1459 #define RTE_ETH_DEV_FALLBACK_TX_RINGSIZE 512 1460 #define RTE_ETH_DEV_FALLBACK_RX_NBQUEUES 1 1461 #define RTE_ETH_DEV_FALLBACK_TX_NBQUEUES 1 1462 1463 /** 1464 * Preferred Rx/Tx port parameters. 1465 * There are separate instances of this structure for transmission 1466 * and reception respectively. 1467 */ 1468 struct rte_eth_dev_portconf { 1469 uint16_t burst_size; /**< Device-preferred burst size */ 1470 uint16_t ring_size; /**< Device-preferred size of queue rings */ 1471 uint16_t nb_queues; /**< Device-preferred number of queues */ 1472 }; 1473 1474 /** 1475 * Default values for switch domain id when ethdev does not support switch 1476 * domain definitions. 1477 */ 1478 #define RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID (UINT16_MAX) 1479 1480 /** 1481 * Ethernet device associated switch information 1482 */ 1483 struct rte_eth_switch_info { 1484 const char *name; /**< switch name */ 1485 uint16_t domain_id; /**< switch domain id */ 1486 uint16_t port_id; 1487 /**< 1488 * mapping to the devices physical switch port as enumerated from the 1489 * perspective of the embedded interconnect/switch. For SR-IOV enabled 1490 * device this may correspond to the VF_ID of each virtual function, 1491 * but each driver should explicitly define the mapping of switch 1492 * port identifier to that physical interconnect/switch 1493 */ 1494 }; 1495 1496 /** 1497 * @warning 1498 * @b EXPERIMENTAL: this structure may change without prior notice. 1499 * 1500 * Ethernet device Rx buffer segmentation capabilities. 1501 */ 1502 struct rte_eth_rxseg_capa { 1503 __extension__ 1504 uint32_t multi_pools:1; /**< Supports receiving to multiple pools.*/ 1505 uint32_t offset_allowed:1; /**< Supports buffer offsets. */ 1506 uint32_t offset_align_log2:4; /**< Required offset alignment. */ 1507 uint16_t max_nseg; /**< Maximum amount of segments to split. */ 1508 uint16_t reserved; /**< Reserved field. */ 1509 }; 1510 1511 /** 1512 * Ethernet device information 1513 */ 1514 1515 /** 1516 * Ethernet device representor port type. 1517 */ 1518 enum rte_eth_representor_type { 1519 RTE_ETH_REPRESENTOR_NONE, /**< not a representor. */ 1520 RTE_ETH_REPRESENTOR_VF, /**< representor of Virtual Function. */ 1521 RTE_ETH_REPRESENTOR_SF, /**< representor of Sub Function. */ 1522 RTE_ETH_REPRESENTOR_PF, /**< representor of Physical Function. */ 1523 }; 1524 1525 /** 1526 * A structure used to retrieve the contextual information of 1527 * an Ethernet device, such as the controlling driver of the 1528 * device, etc... 1529 */ 1530 struct rte_eth_dev_info { 1531 struct rte_device *device; /** Generic device information */ 1532 const char *driver_name; /**< Device Driver name. */ 1533 unsigned int if_index; /**< Index to bound host interface, or 0 if none. 1534 Use if_indextoname() to translate into an interface name. */ 1535 uint16_t min_mtu; /**< Minimum MTU allowed */ 1536 uint16_t max_mtu; /**< Maximum MTU allowed */ 1537 const uint32_t *dev_flags; /**< Device flags */ 1538 uint32_t min_rx_bufsize; /**< Minimum size of RX buffer. */ 1539 uint32_t max_rx_pktlen; /**< Maximum configurable length of RX pkt. */ 1540 /** Maximum configurable size of LRO aggregated packet. */ 1541 uint32_t max_lro_pkt_size; 1542 uint16_t max_rx_queues; /**< Maximum number of RX queues. */ 1543 uint16_t max_tx_queues; /**< Maximum number of TX queues. */ 1544 uint32_t max_mac_addrs; /**< Maximum number of MAC addresses. */ 1545 uint32_t max_hash_mac_addrs; 1546 /** Maximum number of hash MAC addresses for MTA and UTA. */ 1547 uint16_t max_vfs; /**< Maximum number of VFs. */ 1548 uint16_t max_vmdq_pools; /**< Maximum number of VMDq pools. */ 1549 struct rte_eth_rxseg_capa rx_seg_capa; /**< Segmentation capability.*/ 1550 uint64_t rx_offload_capa; 1551 /**< All RX offload capabilities including all per-queue ones */ 1552 uint64_t tx_offload_capa; 1553 /**< All TX offload capabilities including all per-queue ones */ 1554 uint64_t rx_queue_offload_capa; 1555 /**< Device per-queue RX offload capabilities. */ 1556 uint64_t tx_queue_offload_capa; 1557 /**< Device per-queue TX offload capabilities. */ 1558 uint16_t reta_size; 1559 /**< Device redirection table size, the total number of entries. */ 1560 uint8_t hash_key_size; /**< Hash key size in bytes */ 1561 /** Bit mask of RSS offloads, the bit offset also means flow type */ 1562 uint64_t flow_type_rss_offloads; 1563 struct rte_eth_rxconf default_rxconf; /**< Default RX configuration */ 1564 struct rte_eth_txconf default_txconf; /**< Default TX configuration */ 1565 uint16_t vmdq_queue_base; /**< First queue ID for VMDQ pools. */ 1566 uint16_t vmdq_queue_num; /**< Queue number for VMDQ pools. */ 1567 uint16_t vmdq_pool_base; /**< First ID of VMDQ pools. */ 1568 struct rte_eth_desc_lim rx_desc_lim; /**< RX descriptors limits */ 1569 struct rte_eth_desc_lim tx_desc_lim; /**< TX descriptors limits */ 1570 uint32_t speed_capa; /**< Supported speeds bitmap (ETH_LINK_SPEED_). */ 1571 /** Configured number of rx/tx queues */ 1572 uint16_t nb_rx_queues; /**< Number of RX queues. */ 1573 uint16_t nb_tx_queues; /**< Number of TX queues. */ 1574 /** Rx parameter recommendations */ 1575 struct rte_eth_dev_portconf default_rxportconf; 1576 /** Tx parameter recommendations */ 1577 struct rte_eth_dev_portconf default_txportconf; 1578 /** Generic device capabilities (RTE_ETH_DEV_CAPA_). */ 1579 uint64_t dev_capa; 1580 /** 1581 * Switching information for ports on a device with a 1582 * embedded managed interconnect/switch. 1583 */ 1584 struct rte_eth_switch_info switch_info; 1585 1586 uint64_t reserved_64s[2]; /**< Reserved for future fields */ 1587 void *reserved_ptrs[2]; /**< Reserved for future fields */ 1588 }; 1589 1590 /** 1591 * RX/TX queue states 1592 */ 1593 #define RTE_ETH_QUEUE_STATE_STOPPED 0 1594 #define RTE_ETH_QUEUE_STATE_STARTED 1 1595 #define RTE_ETH_QUEUE_STATE_HAIRPIN 2 1596 1597 /** 1598 * Ethernet device RX queue information structure. 1599 * Used to retrieve information about configured queue. 1600 */ 1601 struct rte_eth_rxq_info { 1602 struct rte_mempool *mp; /**< mempool used by that queue. */ 1603 struct rte_eth_rxconf conf; /**< queue config parameters. */ 1604 uint8_t scattered_rx; /**< scattered packets RX supported. */ 1605 uint8_t queue_state; /**< one of RTE_ETH_QUEUE_STATE_*. */ 1606 uint16_t nb_desc; /**< configured number of RXDs. */ 1607 uint16_t rx_buf_size; /**< hardware receive buffer size. */ 1608 } __rte_cache_min_aligned; 1609 1610 /** 1611 * Ethernet device TX queue information structure. 1612 * Used to retrieve information about configured queue. 1613 */ 1614 struct rte_eth_txq_info { 1615 struct rte_eth_txconf conf; /**< queue config parameters. */ 1616 uint16_t nb_desc; /**< configured number of TXDs. */ 1617 uint8_t queue_state; /**< one of RTE_ETH_QUEUE_STATE_*. */ 1618 } __rte_cache_min_aligned; 1619 1620 /* Generic Burst mode flag definition, values can be ORed. */ 1621 1622 /** 1623 * If the queues have different burst mode description, this bit will be set 1624 * by PMD, then the application can iterate to retrieve burst description for 1625 * all other queues. 1626 */ 1627 #define RTE_ETH_BURST_FLAG_PER_QUEUE (1ULL << 0) 1628 1629 /** 1630 * Ethernet device RX/TX queue packet burst mode information structure. 1631 * Used to retrieve information about packet burst mode setting. 1632 */ 1633 struct rte_eth_burst_mode { 1634 uint64_t flags; /**< The ORed values of RTE_ETH_BURST_FLAG_xxx */ 1635 1636 #define RTE_ETH_BURST_MODE_INFO_SIZE 1024 /**< Maximum size for information */ 1637 char info[RTE_ETH_BURST_MODE_INFO_SIZE]; /**< burst mode information */ 1638 }; 1639 1640 /** Maximum name length for extended statistics counters */ 1641 #define RTE_ETH_XSTATS_NAME_SIZE 64 1642 1643 /** 1644 * An Ethernet device extended statistic structure 1645 * 1646 * This structure is used by rte_eth_xstats_get() to provide 1647 * statistics that are not provided in the generic *rte_eth_stats* 1648 * structure. 1649 * It maps a name id, corresponding to an index in the array returned 1650 * by rte_eth_xstats_get_names(), to a statistic value. 1651 */ 1652 struct rte_eth_xstat { 1653 uint64_t id; /**< The index in xstats name array. */ 1654 uint64_t value; /**< The statistic counter value. */ 1655 }; 1656 1657 /** 1658 * A name element for extended statistics. 1659 * 1660 * An array of this structure is returned by rte_eth_xstats_get_names(). 1661 * It lists the names of extended statistics for a PMD. The *rte_eth_xstat* 1662 * structure references these names by their array index. 1663 * 1664 * The xstats should follow a common naming scheme. 1665 * Some names are standardized in rte_stats_strings. 1666 * Examples: 1667 * - rx_missed_errors 1668 * - tx_q3_bytes 1669 * - tx_size_128_to_255_packets 1670 */ 1671 struct rte_eth_xstat_name { 1672 char name[RTE_ETH_XSTATS_NAME_SIZE]; /**< The statistic name. */ 1673 }; 1674 1675 #define ETH_DCB_NUM_TCS 8 1676 #define ETH_MAX_VMDQ_POOL 64 1677 1678 /** 1679 * A structure used to get the information of queue and 1680 * TC mapping on both TX and RX paths. 1681 */ 1682 struct rte_eth_dcb_tc_queue_mapping { 1683 /** rx queues assigned to tc per Pool */ 1684 struct { 1685 uint16_t base; 1686 uint16_t nb_queue; 1687 } tc_rxq[ETH_MAX_VMDQ_POOL][ETH_DCB_NUM_TCS]; 1688 /** rx queues assigned to tc per Pool */ 1689 struct { 1690 uint16_t base; 1691 uint16_t nb_queue; 1692 } tc_txq[ETH_MAX_VMDQ_POOL][ETH_DCB_NUM_TCS]; 1693 }; 1694 1695 /** 1696 * A structure used to get the information of DCB. 1697 * It includes TC UP mapping and queue TC mapping. 1698 */ 1699 struct rte_eth_dcb_info { 1700 uint8_t nb_tcs; /**< number of TCs */ 1701 uint8_t prio_tc[ETH_DCB_NUM_USER_PRIORITIES]; /**< Priority to tc */ 1702 uint8_t tc_bws[ETH_DCB_NUM_TCS]; /**< TX BW percentage for each TC */ 1703 /** rx queues assigned to tc */ 1704 struct rte_eth_dcb_tc_queue_mapping tc_queue; 1705 }; 1706 1707 /** 1708 * This enum indicates the possible Forward Error Correction (FEC) modes 1709 * of an ethdev port. 1710 */ 1711 enum rte_eth_fec_mode { 1712 RTE_ETH_FEC_NOFEC = 0, /**< FEC is off */ 1713 RTE_ETH_FEC_AUTO, /**< FEC autonegotiation modes */ 1714 RTE_ETH_FEC_BASER, /**< FEC using common algorithm */ 1715 RTE_ETH_FEC_RS, /**< FEC using RS algorithm */ 1716 }; 1717 1718 /* Translate from FEC mode to FEC capa */ 1719 #define RTE_ETH_FEC_MODE_TO_CAPA(x) (1U << (x)) 1720 1721 /* This macro indicates FEC capa mask */ 1722 #define RTE_ETH_FEC_MODE_CAPA_MASK(x) (1U << (RTE_ETH_FEC_ ## x)) 1723 1724 /* A structure used to get capabilities per link speed */ 1725 struct rte_eth_fec_capa { 1726 uint32_t speed; /**< Link speed (see ETH_SPEED_NUM_*) */ 1727 uint32_t capa; /**< FEC capabilities bitmask */ 1728 }; 1729 1730 #define RTE_ETH_ALL RTE_MAX_ETHPORTS 1731 1732 /* Macros to check for valid port */ 1733 #define RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, retval) do { \ 1734 if (!rte_eth_dev_is_valid_port(port_id)) { \ 1735 RTE_ETHDEV_LOG(ERR, "Invalid port_id=%u\n", port_id); \ 1736 return retval; \ 1737 } \ 1738 } while (0) 1739 1740 #define RTE_ETH_VALID_PORTID_OR_RET(port_id) do { \ 1741 if (!rte_eth_dev_is_valid_port(port_id)) { \ 1742 RTE_ETHDEV_LOG(ERR, "Invalid port_id=%u\n", port_id); \ 1743 return; \ 1744 } \ 1745 } while (0) 1746 1747 /** 1748 * l2 tunnel configuration. 1749 */ 1750 1751 /**< l2 tunnel enable mask */ 1752 #define ETH_L2_TUNNEL_ENABLE_MASK 0x00000001 1753 /**< l2 tunnel insertion mask */ 1754 #define ETH_L2_TUNNEL_INSERTION_MASK 0x00000002 1755 /**< l2 tunnel stripping mask */ 1756 #define ETH_L2_TUNNEL_STRIPPING_MASK 0x00000004 1757 /**< l2 tunnel forwarding mask */ 1758 #define ETH_L2_TUNNEL_FORWARDING_MASK 0x00000008 1759 1760 /** 1761 * Function type used for RX packet processing packet callbacks. 1762 * 1763 * The callback function is called on RX with a burst of packets that have 1764 * been received on the given port and queue. 1765 * 1766 * @param port_id 1767 * The Ethernet port on which RX is being performed. 1768 * @param queue 1769 * The queue on the Ethernet port which is being used to receive the packets. 1770 * @param pkts 1771 * The burst of packets that have just been received. 1772 * @param nb_pkts 1773 * The number of packets in the burst pointed to by "pkts". 1774 * @param max_pkts 1775 * The max number of packets that can be stored in the "pkts" array. 1776 * @param user_param 1777 * The arbitrary user parameter passed in by the application when the callback 1778 * was originally configured. 1779 * @return 1780 * The number of packets returned to the user. 1781 */ 1782 typedef uint16_t (*rte_rx_callback_fn)(uint16_t port_id, uint16_t queue, 1783 struct rte_mbuf *pkts[], uint16_t nb_pkts, uint16_t max_pkts, 1784 void *user_param); 1785 1786 /** 1787 * Function type used for TX packet processing packet callbacks. 1788 * 1789 * The callback function is called on TX with a burst of packets immediately 1790 * before the packets are put onto the hardware queue for transmission. 1791 * 1792 * @param port_id 1793 * The Ethernet port on which TX is being performed. 1794 * @param queue 1795 * The queue on the Ethernet port which is being used to transmit the packets. 1796 * @param pkts 1797 * The burst of packets that are about to be transmitted. 1798 * @param nb_pkts 1799 * The number of packets in the burst pointed to by "pkts". 1800 * @param user_param 1801 * The arbitrary user parameter passed in by the application when the callback 1802 * was originally configured. 1803 * @return 1804 * The number of packets to be written to the NIC. 1805 */ 1806 typedef uint16_t (*rte_tx_callback_fn)(uint16_t port_id, uint16_t queue, 1807 struct rte_mbuf *pkts[], uint16_t nb_pkts, void *user_param); 1808 1809 /** 1810 * Possible states of an ethdev port. 1811 */ 1812 enum rte_eth_dev_state { 1813 /** Device is unused before being probed. */ 1814 RTE_ETH_DEV_UNUSED = 0, 1815 /** Device is attached when allocated in probing. */ 1816 RTE_ETH_DEV_ATTACHED, 1817 /** Device is in removed state when plug-out is detected. */ 1818 RTE_ETH_DEV_REMOVED, 1819 }; 1820 1821 struct rte_eth_dev_sriov { 1822 uint8_t active; /**< SRIOV is active with 16, 32 or 64 pools */ 1823 uint8_t nb_q_per_pool; /**< rx queue number per pool */ 1824 uint16_t def_vmdq_idx; /**< Default pool num used for PF */ 1825 uint16_t def_pool_q_idx; /**< Default pool queue start reg index */ 1826 }; 1827 #define RTE_ETH_DEV_SRIOV(dev) ((dev)->data->sriov) 1828 1829 #define RTE_ETH_NAME_MAX_LEN RTE_DEV_NAME_MAX_LEN 1830 1831 #define RTE_ETH_DEV_NO_OWNER 0 1832 1833 #define RTE_ETH_MAX_OWNER_NAME_LEN 64 1834 1835 struct rte_eth_dev_owner { 1836 uint64_t id; /**< The owner unique identifier. */ 1837 char name[RTE_ETH_MAX_OWNER_NAME_LEN]; /**< The owner name. */ 1838 }; 1839 1840 /** PMD supports thread-safe flow operations */ 1841 #define RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE 0x0001 1842 /** Device supports link state interrupt */ 1843 #define RTE_ETH_DEV_INTR_LSC 0x0002 1844 /** Device is a bonded slave */ 1845 #define RTE_ETH_DEV_BONDED_SLAVE 0x0004 1846 /** Device supports device removal interrupt */ 1847 #define RTE_ETH_DEV_INTR_RMV 0x0008 1848 /** Device is port representor */ 1849 #define RTE_ETH_DEV_REPRESENTOR 0x0010 1850 /** Device does not support MAC change after started */ 1851 #define RTE_ETH_DEV_NOLIVE_MAC_ADDR 0x0020 1852 /** 1853 * Queue xstats filled automatically by ethdev layer. 1854 * PMDs filling the queue xstats themselves should not set this flag 1855 */ 1856 #define RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS 0x0040 1857 1858 /** 1859 * Iterates over valid ethdev ports owned by a specific owner. 1860 * 1861 * @param port_id 1862 * The id of the next possible valid owned port. 1863 * @param owner_id 1864 * The owner identifier. 1865 * RTE_ETH_DEV_NO_OWNER means iterate over all valid ownerless ports. 1866 * @return 1867 * Next valid port id owned by owner_id, RTE_MAX_ETHPORTS if there is none. 1868 */ 1869 uint64_t rte_eth_find_next_owned_by(uint16_t port_id, 1870 const uint64_t owner_id); 1871 1872 /** 1873 * Macro to iterate over all enabled ethdev ports owned by a specific owner. 1874 */ 1875 #define RTE_ETH_FOREACH_DEV_OWNED_BY(p, o) \ 1876 for (p = rte_eth_find_next_owned_by(0, o); \ 1877 (unsigned int)p < (unsigned int)RTE_MAX_ETHPORTS; \ 1878 p = rte_eth_find_next_owned_by(p + 1, o)) 1879 1880 /** 1881 * Iterates over valid ethdev ports. 1882 * 1883 * @param port_id 1884 * The id of the next possible valid port. 1885 * @return 1886 * Next valid port id, RTE_MAX_ETHPORTS if there is none. 1887 */ 1888 uint16_t rte_eth_find_next(uint16_t port_id); 1889 1890 /** 1891 * Macro to iterate over all enabled and ownerless ethdev ports. 1892 */ 1893 #define RTE_ETH_FOREACH_DEV(p) \ 1894 RTE_ETH_FOREACH_DEV_OWNED_BY(p, RTE_ETH_DEV_NO_OWNER) 1895 1896 /** 1897 * Iterates over ethdev ports of a specified device. 1898 * 1899 * @param port_id_start 1900 * The id of the next possible valid port. 1901 * @param parent 1902 * The generic device behind the ports to iterate. 1903 * @return 1904 * Next port id of the device, possibly port_id_start, 1905 * RTE_MAX_ETHPORTS if there is none. 1906 */ 1907 uint16_t 1908 rte_eth_find_next_of(uint16_t port_id_start, 1909 const struct rte_device *parent); 1910 1911 /** 1912 * Macro to iterate over all ethdev ports of a specified device. 1913 * 1914 * @param port_id 1915 * The id of the matching port being iterated. 1916 * @param parent 1917 * The rte_device pointer matching the iterated ports. 1918 */ 1919 #define RTE_ETH_FOREACH_DEV_OF(port_id, parent) \ 1920 for (port_id = rte_eth_find_next_of(0, parent); \ 1921 port_id < RTE_MAX_ETHPORTS; \ 1922 port_id = rte_eth_find_next_of(port_id + 1, parent)) 1923 1924 /** 1925 * Iterates over sibling ethdev ports (i.e. sharing the same rte_device). 1926 * 1927 * @param port_id_start 1928 * The id of the next possible valid sibling port. 1929 * @param ref_port_id 1930 * The id of a reference port to compare rte_device with. 1931 * @return 1932 * Next sibling port id, possibly port_id_start or ref_port_id itself, 1933 * RTE_MAX_ETHPORTS if there is none. 1934 */ 1935 uint16_t 1936 rte_eth_find_next_sibling(uint16_t port_id_start, uint16_t ref_port_id); 1937 1938 /** 1939 * Macro to iterate over all ethdev ports sharing the same rte_device 1940 * as the specified port. 1941 * Note: the specified reference port is part of the loop iterations. 1942 * 1943 * @param port_id 1944 * The id of the matching port being iterated. 1945 * @param ref_port_id 1946 * The id of the port being compared. 1947 */ 1948 #define RTE_ETH_FOREACH_DEV_SIBLING(port_id, ref_port_id) \ 1949 for (port_id = rte_eth_find_next_sibling(0, ref_port_id); \ 1950 port_id < RTE_MAX_ETHPORTS; \ 1951 port_id = rte_eth_find_next_sibling(port_id + 1, ref_port_id)) 1952 1953 /** 1954 * @warning 1955 * @b EXPERIMENTAL: this API may change without prior notice. 1956 * 1957 * Get a new unique owner identifier. 1958 * An owner identifier is used to owns Ethernet devices by only one DPDK entity 1959 * to avoid multiple management of device by different entities. 1960 * 1961 * @param owner_id 1962 * Owner identifier pointer. 1963 * @return 1964 * Negative errno value on error, 0 on success. 1965 */ 1966 __rte_experimental 1967 int rte_eth_dev_owner_new(uint64_t *owner_id); 1968 1969 /** 1970 * @warning 1971 * @b EXPERIMENTAL: this API may change without prior notice. 1972 * 1973 * Set an Ethernet device owner. 1974 * 1975 * @param port_id 1976 * The identifier of the port to own. 1977 * @param owner 1978 * The owner pointer. 1979 * @return 1980 * Negative errno value on error, 0 on success. 1981 */ 1982 __rte_experimental 1983 int rte_eth_dev_owner_set(const uint16_t port_id, 1984 const struct rte_eth_dev_owner *owner); 1985 1986 /** 1987 * @warning 1988 * @b EXPERIMENTAL: this API may change without prior notice. 1989 * 1990 * Unset Ethernet device owner to make the device ownerless. 1991 * 1992 * @param port_id 1993 * The identifier of port to make ownerless. 1994 * @param owner_id 1995 * The owner identifier. 1996 * @return 1997 * 0 on success, negative errno value on error. 1998 */ 1999 __rte_experimental 2000 int rte_eth_dev_owner_unset(const uint16_t port_id, 2001 const uint64_t owner_id); 2002 2003 /** 2004 * @warning 2005 * @b EXPERIMENTAL: this API may change without prior notice. 2006 * 2007 * Remove owner from all Ethernet devices owned by a specific owner. 2008 * 2009 * @param owner_id 2010 * The owner identifier. 2011 * @return 2012 * 0 on success, negative errno value on error. 2013 */ 2014 __rte_experimental 2015 int rte_eth_dev_owner_delete(const uint64_t owner_id); 2016 2017 /** 2018 * @warning 2019 * @b EXPERIMENTAL: this API may change without prior notice. 2020 * 2021 * Get the owner of an Ethernet device. 2022 * 2023 * @param port_id 2024 * The port identifier. 2025 * @param owner 2026 * The owner structure pointer to fill. 2027 * @return 2028 * 0 on success, negative errno value on error.. 2029 */ 2030 __rte_experimental 2031 int rte_eth_dev_owner_get(const uint16_t port_id, 2032 struct rte_eth_dev_owner *owner); 2033 2034 /** 2035 * Get the number of ports which are usable for the application. 2036 * 2037 * These devices must be iterated by using the macro 2038 * ``RTE_ETH_FOREACH_DEV`` or ``RTE_ETH_FOREACH_DEV_OWNED_BY`` 2039 * to deal with non-contiguous ranges of devices. 2040 * 2041 * @return 2042 * The count of available Ethernet devices. 2043 */ 2044 uint16_t rte_eth_dev_count_avail(void); 2045 2046 /** 2047 * Get the total number of ports which are allocated. 2048 * 2049 * Some devices may not be available for the application. 2050 * 2051 * @return 2052 * The total count of Ethernet devices. 2053 */ 2054 uint16_t rte_eth_dev_count_total(void); 2055 2056 /** 2057 * Convert a numerical speed in Mbps to a bitmap flag that can be used in 2058 * the bitmap link_speeds of the struct rte_eth_conf 2059 * 2060 * @param speed 2061 * Numerical speed value in Mbps 2062 * @param duplex 2063 * ETH_LINK_[HALF/FULL]_DUPLEX (only for 10/100M speeds) 2064 * @return 2065 * 0 if the speed cannot be mapped 2066 */ 2067 uint32_t rte_eth_speed_bitflag(uint32_t speed, int duplex); 2068 2069 /** 2070 * Get DEV_RX_OFFLOAD_* flag name. 2071 * 2072 * @param offload 2073 * Offload flag. 2074 * @return 2075 * Offload name or 'UNKNOWN' if the flag cannot be recognised. 2076 */ 2077 const char *rte_eth_dev_rx_offload_name(uint64_t offload); 2078 2079 /** 2080 * Get DEV_TX_OFFLOAD_* flag name. 2081 * 2082 * @param offload 2083 * Offload flag. 2084 * @return 2085 * Offload name or 'UNKNOWN' if the flag cannot be recognised. 2086 */ 2087 const char *rte_eth_dev_tx_offload_name(uint64_t offload); 2088 2089 /** 2090 * Configure an Ethernet device. 2091 * This function must be invoked first before any other function in the 2092 * Ethernet API. This function can also be re-invoked when a device is in the 2093 * stopped state. 2094 * 2095 * @param port_id 2096 * The port identifier of the Ethernet device to configure. 2097 * @param nb_rx_queue 2098 * The number of receive queues to set up for the Ethernet device. 2099 * @param nb_tx_queue 2100 * The number of transmit queues to set up for the Ethernet device. 2101 * @param eth_conf 2102 * The pointer to the configuration data to be used for the Ethernet device. 2103 * The *rte_eth_conf* structure includes: 2104 * - the hardware offload features to activate, with dedicated fields for 2105 * each statically configurable offload hardware feature provided by 2106 * Ethernet devices, such as IP checksum or VLAN tag stripping for 2107 * example. 2108 * The Rx offload bitfield API is obsolete and will be deprecated. 2109 * Applications should set the ignore_bitfield_offloads bit on *rxmode* 2110 * structure and use offloads field to set per-port offloads instead. 2111 * - Any offloading set in eth_conf->[rt]xmode.offloads must be within 2112 * the [rt]x_offload_capa returned from rte_eth_dev_info_get(). 2113 * Any type of device supported offloading set in the input argument 2114 * eth_conf->[rt]xmode.offloads to rte_eth_dev_configure() is enabled 2115 * on all queues and it can't be disabled in rte_eth_[rt]x_queue_setup() 2116 * - the Receive Side Scaling (RSS) configuration when using multiple RX 2117 * queues per port. Any RSS hash function set in eth_conf->rss_conf.rss_hf 2118 * must be within the flow_type_rss_offloads provided by drivers via 2119 * rte_eth_dev_info_get() API. 2120 * 2121 * Embedding all configuration information in a single data structure 2122 * is the more flexible method that allows the addition of new features 2123 * without changing the syntax of the API. 2124 * @return 2125 * - 0: Success, device configured. 2126 * - <0: Error code returned by the driver configuration function. 2127 */ 2128 int rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_queue, 2129 uint16_t nb_tx_queue, const struct rte_eth_conf *eth_conf); 2130 2131 /** 2132 * @warning 2133 * @b EXPERIMENTAL: this API may change without prior notice. 2134 * 2135 * Check if an Ethernet device was physically removed. 2136 * 2137 * @param port_id 2138 * The port identifier of the Ethernet device. 2139 * @return 2140 * 1 when the Ethernet device is removed, otherwise 0. 2141 */ 2142 __rte_experimental 2143 int 2144 rte_eth_dev_is_removed(uint16_t port_id); 2145 2146 /** 2147 * Allocate and set up a receive queue for an Ethernet device. 2148 * 2149 * The function allocates a contiguous block of memory for *nb_rx_desc* 2150 * receive descriptors from a memory zone associated with *socket_id* 2151 * and initializes each receive descriptor with a network buffer allocated 2152 * from the memory pool *mb_pool*. 2153 * 2154 * @param port_id 2155 * The port identifier of the Ethernet device. 2156 * @param rx_queue_id 2157 * The index of the receive queue to set up. 2158 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 2159 * to rte_eth_dev_configure(). 2160 * @param nb_rx_desc 2161 * The number of receive descriptors to allocate for the receive ring. 2162 * @param socket_id 2163 * The *socket_id* argument is the socket identifier in case of NUMA. 2164 * The value can be *SOCKET_ID_ANY* if there is no NUMA constraint for 2165 * the DMA memory allocated for the receive descriptors of the ring. 2166 * @param rx_conf 2167 * The pointer to the configuration data to be used for the receive queue. 2168 * NULL value is allowed, in which case default RX configuration 2169 * will be used. 2170 * The *rx_conf* structure contains an *rx_thresh* structure with the values 2171 * of the Prefetch, Host, and Write-Back threshold registers of the receive 2172 * ring. 2173 * In addition it contains the hardware offloads features to activate using 2174 * the DEV_RX_OFFLOAD_* flags. 2175 * If an offloading set in rx_conf->offloads 2176 * hasn't been set in the input argument eth_conf->rxmode.offloads 2177 * to rte_eth_dev_configure(), it is a new added offloading, it must be 2178 * per-queue type and it is enabled for the queue. 2179 * No need to repeat any bit in rx_conf->offloads which has already been 2180 * enabled in rte_eth_dev_configure() at port level. An offloading enabled 2181 * at port level can't be disabled at queue level. 2182 * The configuration structure also contains the pointer to the array 2183 * of the receiving buffer segment descriptions, see rx_seg and rx_nseg 2184 * fields, this extended configuration might be used by split offloads like 2185 * RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT. If mb_pool is not NULL, 2186 * the extended configuration fields must be set to NULL and zero. 2187 * @param mb_pool 2188 * The pointer to the memory pool from which to allocate *rte_mbuf* network 2189 * memory buffers to populate each descriptor of the receive ring. There are 2190 * two options to provide Rx buffer configuration: 2191 * - single pool: 2192 * mb_pool is not NULL, rx_conf.rx_nseg is 0. 2193 * - multiple segments description: 2194 * mb_pool is NULL, rx_conf.rx_seg is not NULL, rx_conf.rx_nseg is not 0. 2195 * Taken only if flag RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT is set in offloads. 2196 * 2197 * @return 2198 * - 0: Success, receive queue correctly set up. 2199 * - -EIO: if device is removed. 2200 * - -ENODEV: if *port_id* is invalid. 2201 * - -EINVAL: The memory pool pointer is null or the size of network buffers 2202 * which can be allocated from this memory pool does not fit the various 2203 * buffer sizes allowed by the device controller. 2204 * - -ENOMEM: Unable to allocate the receive ring descriptors or to 2205 * allocate network memory buffers from the memory pool when 2206 * initializing receive descriptors. 2207 */ 2208 int rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id, 2209 uint16_t nb_rx_desc, unsigned int socket_id, 2210 const struct rte_eth_rxconf *rx_conf, 2211 struct rte_mempool *mb_pool); 2212 2213 /** 2214 * @warning 2215 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 2216 * 2217 * Allocate and set up a hairpin receive queue for an Ethernet device. 2218 * 2219 * The function set up the selected queue to be used in hairpin. 2220 * 2221 * @param port_id 2222 * The port identifier of the Ethernet device. 2223 * @param rx_queue_id 2224 * The index of the receive queue to set up. 2225 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 2226 * to rte_eth_dev_configure(). 2227 * @param nb_rx_desc 2228 * The number of receive descriptors to allocate for the receive ring. 2229 * 0 means the PMD will use default value. 2230 * @param conf 2231 * The pointer to the hairpin configuration. 2232 * 2233 * @return 2234 * - (0) if successful. 2235 * - (-ENODEV) if *port_id* is invalid. 2236 * - (-ENOTSUP) if hardware doesn't support. 2237 * - (-EINVAL) if bad parameter. 2238 * - (-ENOMEM) if unable to allocate the resources. 2239 */ 2240 __rte_experimental 2241 int rte_eth_rx_hairpin_queue_setup 2242 (uint16_t port_id, uint16_t rx_queue_id, uint16_t nb_rx_desc, 2243 const struct rte_eth_hairpin_conf *conf); 2244 2245 /** 2246 * Allocate and set up a transmit queue for an Ethernet device. 2247 * 2248 * @param port_id 2249 * The port identifier of the Ethernet device. 2250 * @param tx_queue_id 2251 * The index of the transmit queue to set up. 2252 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 2253 * to rte_eth_dev_configure(). 2254 * @param nb_tx_desc 2255 * The number of transmit descriptors to allocate for the transmit ring. 2256 * @param socket_id 2257 * The *socket_id* argument is the socket identifier in case of NUMA. 2258 * Its value can be *SOCKET_ID_ANY* if there is no NUMA constraint for 2259 * the DMA memory allocated for the transmit descriptors of the ring. 2260 * @param tx_conf 2261 * The pointer to the configuration data to be used for the transmit queue. 2262 * NULL value is allowed, in which case default TX configuration 2263 * will be used. 2264 * The *tx_conf* structure contains the following data: 2265 * - The *tx_thresh* structure with the values of the Prefetch, Host, and 2266 * Write-Back threshold registers of the transmit ring. 2267 * When setting Write-Back threshold to the value greater then zero, 2268 * *tx_rs_thresh* value should be explicitly set to one. 2269 * - The *tx_free_thresh* value indicates the [minimum] number of network 2270 * buffers that must be pending in the transmit ring to trigger their 2271 * [implicit] freeing by the driver transmit function. 2272 * - The *tx_rs_thresh* value indicates the [minimum] number of transmit 2273 * descriptors that must be pending in the transmit ring before setting the 2274 * RS bit on a descriptor by the driver transmit function. 2275 * The *tx_rs_thresh* value should be less or equal then 2276 * *tx_free_thresh* value, and both of them should be less then 2277 * *nb_tx_desc* - 3. 2278 * - The *offloads* member contains Tx offloads to be enabled. 2279 * If an offloading set in tx_conf->offloads 2280 * hasn't been set in the input argument eth_conf->txmode.offloads 2281 * to rte_eth_dev_configure(), it is a new added offloading, it must be 2282 * per-queue type and it is enabled for the queue. 2283 * No need to repeat any bit in tx_conf->offloads which has already been 2284 * enabled in rte_eth_dev_configure() at port level. An offloading enabled 2285 * at port level can't be disabled at queue level. 2286 * 2287 * Note that setting *tx_free_thresh* or *tx_rs_thresh* value to 0 forces 2288 * the transmit function to use default values. 2289 * @return 2290 * - 0: Success, the transmit queue is correctly set up. 2291 * - -ENOMEM: Unable to allocate the transmit ring descriptors. 2292 */ 2293 int rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, 2294 uint16_t nb_tx_desc, unsigned int socket_id, 2295 const struct rte_eth_txconf *tx_conf); 2296 2297 /** 2298 * @warning 2299 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 2300 * 2301 * Allocate and set up a transmit hairpin queue for an Ethernet device. 2302 * 2303 * @param port_id 2304 * The port identifier of the Ethernet device. 2305 * @param tx_queue_id 2306 * The index of the transmit queue to set up. 2307 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 2308 * to rte_eth_dev_configure(). 2309 * @param nb_tx_desc 2310 * The number of transmit descriptors to allocate for the transmit ring. 2311 * 0 to set default PMD value. 2312 * @param conf 2313 * The hairpin configuration. 2314 * 2315 * @return 2316 * - (0) if successful. 2317 * - (-ENODEV) if *port_id* is invalid. 2318 * - (-ENOTSUP) if hardware doesn't support. 2319 * - (-EINVAL) if bad parameter. 2320 * - (-ENOMEM) if unable to allocate the resources. 2321 */ 2322 __rte_experimental 2323 int rte_eth_tx_hairpin_queue_setup 2324 (uint16_t port_id, uint16_t tx_queue_id, uint16_t nb_tx_desc, 2325 const struct rte_eth_hairpin_conf *conf); 2326 2327 /** 2328 * @warning 2329 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 2330 * 2331 * Get all the hairpin peer Rx / Tx ports of the current port. 2332 * The caller should ensure that the array is large enough to save the ports 2333 * list. 2334 * 2335 * @param port_id 2336 * The port identifier of the Ethernet device. 2337 * @param peer_ports 2338 * Pointer to the array to store the peer ports list. 2339 * @param len 2340 * Length of the array to store the port identifiers. 2341 * @param direction 2342 * Current port to peer port direction 2343 * positive - current used as Tx to get all peer Rx ports. 2344 * zero - current used as Rx to get all peer Tx ports. 2345 * 2346 * @return 2347 * - (0 or positive) actual peer ports number. 2348 * - (-EINVAL) if bad parameter. 2349 * - (-ENODEV) if *port_id* invalid 2350 * - (-ENOTSUP) if hardware doesn't support. 2351 * - Others detailed errors from PMD drivers. 2352 */ 2353 __rte_experimental 2354 int rte_eth_hairpin_get_peer_ports(uint16_t port_id, uint16_t *peer_ports, 2355 size_t len, uint32_t direction); 2356 2357 /** 2358 * @warning 2359 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 2360 * 2361 * Bind all hairpin Tx queues of one port to the Rx queues of the peer port. 2362 * It is only allowed to call this function after all hairpin queues are 2363 * configured properly and the devices are in started state. 2364 * 2365 * @param tx_port 2366 * The identifier of the Tx port. 2367 * @param rx_port 2368 * The identifier of peer Rx port. 2369 * RTE_MAX_ETHPORTS is allowed for the traversal of all devices. 2370 * Rx port ID could have the same value as Tx port ID. 2371 * 2372 * @return 2373 * - (0) if successful. 2374 * - (-ENODEV) if Tx port ID is invalid. 2375 * - (-EBUSY) if device is not in started state. 2376 * - (-ENOTSUP) if hardware doesn't support. 2377 * - Others detailed errors from PMD drivers. 2378 */ 2379 __rte_experimental 2380 int rte_eth_hairpin_bind(uint16_t tx_port, uint16_t rx_port); 2381 2382 /** 2383 * @warning 2384 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 2385 * 2386 * Unbind all hairpin Tx queues of one port from the Rx queues of the peer port. 2387 * This should be called before closing the Tx or Rx devices, if the bind 2388 * function is called before. 2389 * After unbinding the hairpin ports pair, it is allowed to bind them again. 2390 * Changing queues configuration should be after stopping the device(s). 2391 * 2392 * @param tx_port 2393 * The identifier of the Tx port. 2394 * @param rx_port 2395 * The identifier of peer Rx port. 2396 * RTE_MAX_ETHPORTS is allowed for traversal of all devices. 2397 * Rx port ID could have the same value as Tx port ID. 2398 * 2399 * @return 2400 * - (0) if successful. 2401 * - (-ENODEV) if Tx port ID is invalid. 2402 * - (-EBUSY) if device is in stopped state. 2403 * - (-ENOTSUP) if hardware doesn't support. 2404 * - Others detailed errors from PMD drivers. 2405 */ 2406 __rte_experimental 2407 int rte_eth_hairpin_unbind(uint16_t tx_port, uint16_t rx_port); 2408 2409 /** 2410 * Return the NUMA socket to which an Ethernet device is connected 2411 * 2412 * @param port_id 2413 * The port identifier of the Ethernet device 2414 * @return 2415 * The NUMA socket id to which the Ethernet device is connected or 2416 * a default of zero if the socket could not be determined. 2417 * -1 is returned is the port_id value is out of range. 2418 */ 2419 int rte_eth_dev_socket_id(uint16_t port_id); 2420 2421 /** 2422 * Check if port_id of device is attached 2423 * 2424 * @param port_id 2425 * The port identifier of the Ethernet device 2426 * @return 2427 * - 0 if port is out of range or not attached 2428 * - 1 if device is attached 2429 */ 2430 int rte_eth_dev_is_valid_port(uint16_t port_id); 2431 2432 /** 2433 * Start specified RX queue of a port. It is used when rx_deferred_start 2434 * flag of the specified queue is true. 2435 * 2436 * @param port_id 2437 * The port identifier of the Ethernet device 2438 * @param rx_queue_id 2439 * The index of the rx queue to update the ring. 2440 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 2441 * to rte_eth_dev_configure(). 2442 * @return 2443 * - 0: Success, the receive queue is started. 2444 * - -ENODEV: if *port_id* is invalid. 2445 * - -EINVAL: The queue_id out of range or belong to hairpin. 2446 * - -EIO: if device is removed. 2447 * - -ENOTSUP: The function not supported in PMD driver. 2448 */ 2449 int rte_eth_dev_rx_queue_start(uint16_t port_id, uint16_t rx_queue_id); 2450 2451 /** 2452 * Stop specified RX queue of a port 2453 * 2454 * @param port_id 2455 * The port identifier of the Ethernet device 2456 * @param rx_queue_id 2457 * The index of the rx queue to update the ring. 2458 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 2459 * to rte_eth_dev_configure(). 2460 * @return 2461 * - 0: Success, the receive queue is stopped. 2462 * - -ENODEV: if *port_id* is invalid. 2463 * - -EINVAL: The queue_id out of range or belong to hairpin. 2464 * - -EIO: if device is removed. 2465 * - -ENOTSUP: The function not supported in PMD driver. 2466 */ 2467 int rte_eth_dev_rx_queue_stop(uint16_t port_id, uint16_t rx_queue_id); 2468 2469 /** 2470 * Start TX for specified queue of a port. It is used when tx_deferred_start 2471 * flag of the specified queue is true. 2472 * 2473 * @param port_id 2474 * The port identifier of the Ethernet device 2475 * @param tx_queue_id 2476 * The index of the tx queue to update the ring. 2477 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 2478 * to rte_eth_dev_configure(). 2479 * @return 2480 * - 0: Success, the transmit queue is started. 2481 * - -ENODEV: if *port_id* is invalid. 2482 * - -EINVAL: The queue_id out of range or belong to hairpin. 2483 * - -EIO: if device is removed. 2484 * - -ENOTSUP: The function not supported in PMD driver. 2485 */ 2486 int rte_eth_dev_tx_queue_start(uint16_t port_id, uint16_t tx_queue_id); 2487 2488 /** 2489 * Stop specified TX queue of a port 2490 * 2491 * @param port_id 2492 * The port identifier of the Ethernet device 2493 * @param tx_queue_id 2494 * The index of the tx queue to update the ring. 2495 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 2496 * to rte_eth_dev_configure(). 2497 * @return 2498 * - 0: Success, the transmit queue is stopped. 2499 * - -ENODEV: if *port_id* is invalid. 2500 * - -EINVAL: The queue_id out of range or belong to hairpin. 2501 * - -EIO: if device is removed. 2502 * - -ENOTSUP: The function not supported in PMD driver. 2503 */ 2504 int rte_eth_dev_tx_queue_stop(uint16_t port_id, uint16_t tx_queue_id); 2505 2506 /** 2507 * Start an Ethernet device. 2508 * 2509 * The device start step is the last one and consists of setting the configured 2510 * offload features and in starting the transmit and the receive units of the 2511 * device. 2512 * 2513 * Device RTE_ETH_DEV_NOLIVE_MAC_ADDR flag causes MAC address to be set before 2514 * PMD port start callback function is invoked. 2515 * 2516 * On success, all basic functions exported by the Ethernet API (link status, 2517 * receive/transmit, and so on) can be invoked. 2518 * 2519 * @param port_id 2520 * The port identifier of the Ethernet device. 2521 * @return 2522 * - 0: Success, Ethernet device started. 2523 * - <0: Error code of the driver device start function. 2524 */ 2525 int rte_eth_dev_start(uint16_t port_id); 2526 2527 /** 2528 * Stop an Ethernet device. The device can be restarted with a call to 2529 * rte_eth_dev_start() 2530 * 2531 * @param port_id 2532 * The port identifier of the Ethernet device. 2533 * @return 2534 * - 0: Success, Ethernet device stopped. 2535 * - <0: Error code of the driver device stop function. 2536 */ 2537 int rte_eth_dev_stop(uint16_t port_id); 2538 2539 /** 2540 * Link up an Ethernet device. 2541 * 2542 * Set device link up will re-enable the device rx/tx 2543 * functionality after it is previously set device linked down. 2544 * 2545 * @param port_id 2546 * The port identifier of the Ethernet device. 2547 * @return 2548 * - 0: Success, Ethernet device linked up. 2549 * - <0: Error code of the driver device link up function. 2550 */ 2551 int rte_eth_dev_set_link_up(uint16_t port_id); 2552 2553 /** 2554 * Link down an Ethernet device. 2555 * The device rx/tx functionality will be disabled if success, 2556 * and it can be re-enabled with a call to 2557 * rte_eth_dev_set_link_up() 2558 * 2559 * @param port_id 2560 * The port identifier of the Ethernet device. 2561 */ 2562 int rte_eth_dev_set_link_down(uint16_t port_id); 2563 2564 /** 2565 * Close a stopped Ethernet device. The device cannot be restarted! 2566 * The function frees all port resources. 2567 * 2568 * @param port_id 2569 * The port identifier of the Ethernet device. 2570 * @return 2571 * - Zero if the port is closed successfully. 2572 * - Negative if something went wrong. 2573 */ 2574 int rte_eth_dev_close(uint16_t port_id); 2575 2576 /** 2577 * Reset a Ethernet device and keep its port id. 2578 * 2579 * When a port has to be reset passively, the DPDK application can invoke 2580 * this function. For example when a PF is reset, all its VFs should also 2581 * be reset. Normally a DPDK application can invoke this function when 2582 * RTE_ETH_EVENT_INTR_RESET event is detected, but can also use it to start 2583 * a port reset in other circumstances. 2584 * 2585 * When this function is called, it first stops the port and then calls the 2586 * PMD specific dev_uninit( ) and dev_init( ) to return the port to initial 2587 * state, in which no Tx and Rx queues are setup, as if the port has been 2588 * reset and not started. The port keeps the port id it had before the 2589 * function call. 2590 * 2591 * After calling rte_eth_dev_reset( ), the application should use 2592 * rte_eth_dev_configure( ), rte_eth_rx_queue_setup( ), 2593 * rte_eth_tx_queue_setup( ), and rte_eth_dev_start( ) 2594 * to reconfigure the device as appropriate. 2595 * 2596 * Note: To avoid unexpected behavior, the application should stop calling 2597 * Tx and Rx functions before calling rte_eth_dev_reset( ). For thread 2598 * safety, all these controlling functions should be called from the same 2599 * thread. 2600 * 2601 * @param port_id 2602 * The port identifier of the Ethernet device. 2603 * 2604 * @return 2605 * - (0) if successful. 2606 * - (-ENODEV) if *port_id* is invalid. 2607 * - (-ENOTSUP) if hardware doesn't support this function. 2608 * - (-EPERM) if not ran from the primary process. 2609 * - (-EIO) if re-initialisation failed or device is removed. 2610 * - (-ENOMEM) if the reset failed due to OOM. 2611 * - (-EAGAIN) if the reset temporarily failed and should be retried later. 2612 */ 2613 int rte_eth_dev_reset(uint16_t port_id); 2614 2615 /** 2616 * Enable receipt in promiscuous mode for an Ethernet device. 2617 * 2618 * @param port_id 2619 * The port identifier of the Ethernet device. 2620 * @return 2621 * - (0) if successful. 2622 * - (-ENOTSUP) if support for promiscuous_enable() does not exist 2623 * for the device. 2624 * - (-ENODEV) if *port_id* invalid. 2625 */ 2626 int rte_eth_promiscuous_enable(uint16_t port_id); 2627 2628 /** 2629 * Disable receipt in promiscuous mode for an Ethernet device. 2630 * 2631 * @param port_id 2632 * The port identifier of the Ethernet device. 2633 * @return 2634 * - (0) if successful. 2635 * - (-ENOTSUP) if support for promiscuous_disable() does not exist 2636 * for the device. 2637 * - (-ENODEV) if *port_id* invalid. 2638 */ 2639 int rte_eth_promiscuous_disable(uint16_t port_id); 2640 2641 /** 2642 * Return the value of promiscuous mode for an Ethernet device. 2643 * 2644 * @param port_id 2645 * The port identifier of the Ethernet device. 2646 * @return 2647 * - (1) if promiscuous is enabled 2648 * - (0) if promiscuous is disabled. 2649 * - (-1) on error 2650 */ 2651 int rte_eth_promiscuous_get(uint16_t port_id); 2652 2653 /** 2654 * Enable the receipt of any multicast frame by an Ethernet device. 2655 * 2656 * @param port_id 2657 * The port identifier of the Ethernet device. 2658 * @return 2659 * - (0) if successful. 2660 * - (-ENOTSUP) if support for allmulticast_enable() does not exist 2661 * for the device. 2662 * - (-ENODEV) if *port_id* invalid. 2663 */ 2664 int rte_eth_allmulticast_enable(uint16_t port_id); 2665 2666 /** 2667 * Disable the receipt of all multicast frames by an Ethernet device. 2668 * 2669 * @param port_id 2670 * The port identifier of the Ethernet device. 2671 * @return 2672 * - (0) if successful. 2673 * - (-ENOTSUP) if support for allmulticast_disable() does not exist 2674 * for the device. 2675 * - (-ENODEV) if *port_id* invalid. 2676 */ 2677 int rte_eth_allmulticast_disable(uint16_t port_id); 2678 2679 /** 2680 * Return the value of allmulticast mode for an Ethernet device. 2681 * 2682 * @param port_id 2683 * The port identifier of the Ethernet device. 2684 * @return 2685 * - (1) if allmulticast is enabled 2686 * - (0) if allmulticast is disabled. 2687 * - (-1) on error 2688 */ 2689 int rte_eth_allmulticast_get(uint16_t port_id); 2690 2691 /** 2692 * Retrieve the link status (up/down), the duplex mode (half/full), 2693 * the negotiation (auto/fixed), and if available, the speed (Mbps). 2694 * 2695 * It might need to wait up to 9 seconds. 2696 * @see rte_eth_link_get_nowait. 2697 * 2698 * @param port_id 2699 * The port identifier of the Ethernet device. 2700 * @param link 2701 * Link information written back. 2702 * @return 2703 * - (0) if successful. 2704 * - (-ENOTSUP) if the function is not supported in PMD driver. 2705 * - (-ENODEV) if *port_id* invalid. 2706 * - (-EINVAL) if bad parameter. 2707 */ 2708 int rte_eth_link_get(uint16_t port_id, struct rte_eth_link *link); 2709 2710 /** 2711 * Retrieve the link status (up/down), the duplex mode (half/full), 2712 * the negotiation (auto/fixed), and if available, the speed (Mbps). 2713 * 2714 * @param port_id 2715 * The port identifier of the Ethernet device. 2716 * @param link 2717 * Link information written back. 2718 * @return 2719 * - (0) if successful. 2720 * - (-ENOTSUP) if the function is not supported in PMD driver. 2721 * - (-ENODEV) if *port_id* invalid. 2722 * - (-EINVAL) if bad parameter. 2723 */ 2724 int rte_eth_link_get_nowait(uint16_t port_id, struct rte_eth_link *link); 2725 2726 /** 2727 * @warning 2728 * @b EXPERIMENTAL: this API may change without prior notice. 2729 * 2730 * The function converts a link_speed to a string. It handles all special 2731 * values like unknown or none speed. 2732 * 2733 * @param link_speed 2734 * link_speed of rte_eth_link struct 2735 * @return 2736 * Link speed in textual format. It's pointer to immutable memory. 2737 * No free is required. 2738 */ 2739 __rte_experimental 2740 const char *rte_eth_link_speed_to_str(uint32_t link_speed); 2741 2742 /** 2743 * @warning 2744 * @b EXPERIMENTAL: this API may change without prior notice. 2745 * 2746 * The function converts a rte_eth_link struct representing a link status to 2747 * a string. 2748 * 2749 * @param str 2750 * A pointer to a string to be filled with textual representation of 2751 * device status. At least ETH_LINK_MAX_STR_LEN bytes should be allocated to 2752 * store default link status text. 2753 * @param len 2754 * Length of available memory at 'str' string. 2755 * @param eth_link 2756 * Link status returned by rte_eth_link_get function 2757 * @return 2758 * Number of bytes written to str array or -EINVAL if bad parameter. 2759 */ 2760 __rte_experimental 2761 int rte_eth_link_to_str(char *str, size_t len, 2762 const struct rte_eth_link *eth_link); 2763 2764 /** 2765 * Retrieve the general I/O statistics of an Ethernet device. 2766 * 2767 * @param port_id 2768 * The port identifier of the Ethernet device. 2769 * @param stats 2770 * A pointer to a structure of type *rte_eth_stats* to be filled with 2771 * the values of device counters for the following set of statistics: 2772 * - *ipackets* with the total of successfully received packets. 2773 * - *opackets* with the total of successfully transmitted packets. 2774 * - *ibytes* with the total of successfully received bytes. 2775 * - *obytes* with the total of successfully transmitted bytes. 2776 * - *ierrors* with the total of erroneous received packets. 2777 * - *oerrors* with the total of failed transmitted packets. 2778 * @return 2779 * Zero if successful. Non-zero otherwise. 2780 */ 2781 int rte_eth_stats_get(uint16_t port_id, struct rte_eth_stats *stats); 2782 2783 /** 2784 * Reset the general I/O statistics of an Ethernet device. 2785 * 2786 * @param port_id 2787 * The port identifier of the Ethernet device. 2788 * @return 2789 * - (0) if device notified to reset stats. 2790 * - (-ENOTSUP) if hardware doesn't support. 2791 * - (-ENODEV) if *port_id* invalid. 2792 * - (<0): Error code of the driver stats reset function. 2793 */ 2794 int rte_eth_stats_reset(uint16_t port_id); 2795 2796 /** 2797 * Retrieve names of extended statistics of an Ethernet device. 2798 * 2799 * There is an assumption that 'xstat_names' and 'xstats' arrays are matched 2800 * by array index: 2801 * xstats_names[i].name => xstats[i].value 2802 * 2803 * And the array index is same with id field of 'struct rte_eth_xstat': 2804 * xstats[i].id == i 2805 * 2806 * This assumption makes key-value pair matching less flexible but simpler. 2807 * 2808 * @param port_id 2809 * The port identifier of the Ethernet device. 2810 * @param xstats_names 2811 * An rte_eth_xstat_name array of at least *size* elements to 2812 * be filled. If set to NULL, the function returns the required number 2813 * of elements. 2814 * @param size 2815 * The size of the xstats_names array (number of elements). 2816 * @return 2817 * - A positive value lower or equal to size: success. The return value 2818 * is the number of entries filled in the stats table. 2819 * - A positive value higher than size: error, the given statistics table 2820 * is too small. The return value corresponds to the size that should 2821 * be given to succeed. The entries in the table are not valid and 2822 * shall not be used by the caller. 2823 * - A negative value on error (invalid port id). 2824 */ 2825 int rte_eth_xstats_get_names(uint16_t port_id, 2826 struct rte_eth_xstat_name *xstats_names, 2827 unsigned int size); 2828 2829 /** 2830 * Retrieve extended statistics of an Ethernet device. 2831 * 2832 * There is an assumption that 'xstat_names' and 'xstats' arrays are matched 2833 * by array index: 2834 * xstats_names[i].name => xstats[i].value 2835 * 2836 * And the array index is same with id field of 'struct rte_eth_xstat': 2837 * xstats[i].id == i 2838 * 2839 * This assumption makes key-value pair matching less flexible but simpler. 2840 * 2841 * @param port_id 2842 * The port identifier of the Ethernet device. 2843 * @param xstats 2844 * A pointer to a table of structure of type *rte_eth_xstat* 2845 * to be filled with device statistics ids and values. 2846 * This parameter can be set to NULL if n is 0. 2847 * @param n 2848 * The size of the xstats array (number of elements). 2849 * @return 2850 * - A positive value lower or equal to n: success. The return value 2851 * is the number of entries filled in the stats table. 2852 * - A positive value higher than n: error, the given statistics table 2853 * is too small. The return value corresponds to the size that should 2854 * be given to succeed. The entries in the table are not valid and 2855 * shall not be used by the caller. 2856 * - A negative value on error (invalid port id). 2857 */ 2858 int rte_eth_xstats_get(uint16_t port_id, struct rte_eth_xstat *xstats, 2859 unsigned int n); 2860 2861 /** 2862 * Retrieve names of extended statistics of an Ethernet device. 2863 * 2864 * @param port_id 2865 * The port identifier of the Ethernet device. 2866 * @param xstats_names 2867 * An rte_eth_xstat_name array of at least *size* elements to 2868 * be filled. If set to NULL, the function returns the required number 2869 * of elements. 2870 * @param ids 2871 * IDs array given by app to retrieve specific statistics 2872 * @param size 2873 * The size of the xstats_names array (number of elements). 2874 * @return 2875 * - A positive value lower or equal to size: success. The return value 2876 * is the number of entries filled in the stats table. 2877 * - A positive value higher than size: error, the given statistics table 2878 * is too small. The return value corresponds to the size that should 2879 * be given to succeed. The entries in the table are not valid and 2880 * shall not be used by the caller. 2881 * - A negative value on error (invalid port id). 2882 */ 2883 int 2884 rte_eth_xstats_get_names_by_id(uint16_t port_id, 2885 struct rte_eth_xstat_name *xstats_names, unsigned int size, 2886 uint64_t *ids); 2887 2888 /** 2889 * Retrieve extended statistics of an Ethernet device. 2890 * 2891 * @param port_id 2892 * The port identifier of the Ethernet device. 2893 * @param ids 2894 * A pointer to an ids array passed by application. This tells which 2895 * statistics values function should retrieve. This parameter 2896 * can be set to NULL if size is 0. In this case function will retrieve 2897 * all available statistics. 2898 * @param values 2899 * A pointer to a table to be filled with device statistics values. 2900 * @param size 2901 * The size of the ids array (number of elements). 2902 * @return 2903 * - A positive value lower or equal to size: success. The return value 2904 * is the number of entries filled in the stats table. 2905 * - A positive value higher than size: error, the given statistics table 2906 * is too small. The return value corresponds to the size that should 2907 * be given to succeed. The entries in the table are not valid and 2908 * shall not be used by the caller. 2909 * - A negative value on error (invalid port id). 2910 */ 2911 int rte_eth_xstats_get_by_id(uint16_t port_id, const uint64_t *ids, 2912 uint64_t *values, unsigned int size); 2913 2914 /** 2915 * Gets the ID of a statistic from its name. 2916 * 2917 * This function searches for the statistics using string compares, and 2918 * as such should not be used on the fast-path. For fast-path retrieval of 2919 * specific statistics, store the ID as provided in *id* from this function, 2920 * and pass the ID to rte_eth_xstats_get() 2921 * 2922 * @param port_id The port to look up statistics from 2923 * @param xstat_name The name of the statistic to return 2924 * @param[out] id A pointer to an app-supplied uint64_t which should be 2925 * set to the ID of the stat if the stat exists. 2926 * @return 2927 * 0 on success 2928 * -ENODEV for invalid port_id, 2929 * -EIO if device is removed, 2930 * -EINVAL if the xstat_name doesn't exist in port_id 2931 * -ENOMEM if bad parameter. 2932 */ 2933 int rte_eth_xstats_get_id_by_name(uint16_t port_id, const char *xstat_name, 2934 uint64_t *id); 2935 2936 /** 2937 * Reset extended statistics of an Ethernet device. 2938 * 2939 * @param port_id 2940 * The port identifier of the Ethernet device. 2941 * @return 2942 * - (0) if device notified to reset extended stats. 2943 * - (-ENOTSUP) if pmd doesn't support both 2944 * extended stats and basic stats reset. 2945 * - (-ENODEV) if *port_id* invalid. 2946 * - (<0): Error code of the driver xstats reset function. 2947 */ 2948 int rte_eth_xstats_reset(uint16_t port_id); 2949 2950 /** 2951 * Set a mapping for the specified transmit queue to the specified per-queue 2952 * statistics counter. 2953 * 2954 * @param port_id 2955 * The port identifier of the Ethernet device. 2956 * @param tx_queue_id 2957 * The index of the transmit queue for which a queue stats mapping is required. 2958 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 2959 * to rte_eth_dev_configure(). 2960 * @param stat_idx 2961 * The per-queue packet statistics functionality number that the transmit 2962 * queue is to be assigned. 2963 * The value must be in the range [0, RTE_ETHDEV_QUEUE_STAT_CNTRS - 1]. 2964 * Max RTE_ETHDEV_QUEUE_STAT_CNTRS being 256. 2965 * @return 2966 * Zero if successful. Non-zero otherwise. 2967 */ 2968 int rte_eth_dev_set_tx_queue_stats_mapping(uint16_t port_id, 2969 uint16_t tx_queue_id, uint8_t stat_idx); 2970 2971 /** 2972 * Set a mapping for the specified receive queue to the specified per-queue 2973 * statistics counter. 2974 * 2975 * @param port_id 2976 * The port identifier of the Ethernet device. 2977 * @param rx_queue_id 2978 * The index of the receive queue for which a queue stats mapping is required. 2979 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 2980 * to rte_eth_dev_configure(). 2981 * @param stat_idx 2982 * The per-queue packet statistics functionality number that the receive 2983 * queue is to be assigned. 2984 * The value must be in the range [0, RTE_ETHDEV_QUEUE_STAT_CNTRS - 1]. 2985 * Max RTE_ETHDEV_QUEUE_STAT_CNTRS being 256. 2986 * @return 2987 * Zero if successful. Non-zero otherwise. 2988 */ 2989 int rte_eth_dev_set_rx_queue_stats_mapping(uint16_t port_id, 2990 uint16_t rx_queue_id, 2991 uint8_t stat_idx); 2992 2993 /** 2994 * Retrieve the Ethernet address of an Ethernet device. 2995 * 2996 * @param port_id 2997 * The port identifier of the Ethernet device. 2998 * @param mac_addr 2999 * A pointer to a structure of type *ether_addr* to be filled with 3000 * the Ethernet address of the Ethernet device. 3001 * @return 3002 * - (0) if successful 3003 * - (-ENODEV) if *port_id* invalid. 3004 * - (-EINVAL) if bad parameter. 3005 */ 3006 int rte_eth_macaddr_get(uint16_t port_id, struct rte_ether_addr *mac_addr); 3007 3008 /** 3009 * Retrieve the contextual information of an Ethernet device. 3010 * 3011 * As part of this function, a number of of fields in dev_info will be 3012 * initialized as follows: 3013 * 3014 * rx_desc_lim = lim 3015 * tx_desc_lim = lim 3016 * 3017 * Where lim is defined within the rte_eth_dev_info_get as 3018 * 3019 * const struct rte_eth_desc_lim lim = { 3020 * .nb_max = UINT16_MAX, 3021 * .nb_min = 0, 3022 * .nb_align = 1, 3023 * .nb_seg_max = UINT16_MAX, 3024 * .nb_mtu_seg_max = UINT16_MAX, 3025 * }; 3026 * 3027 * device = dev->device 3028 * min_mtu = RTE_ETHER_MIN_MTU 3029 * max_mtu = UINT16_MAX 3030 * 3031 * The following fields will be populated if support for dev_infos_get() 3032 * exists for the device and the rte_eth_dev 'dev' has been populated 3033 * successfully with a call to it: 3034 * 3035 * driver_name = dev->device->driver->name 3036 * nb_rx_queues = dev->data->nb_rx_queues 3037 * nb_tx_queues = dev->data->nb_tx_queues 3038 * dev_flags = &dev->data->dev_flags 3039 * 3040 * @param port_id 3041 * The port identifier of the Ethernet device. 3042 * @param dev_info 3043 * A pointer to a structure of type *rte_eth_dev_info* to be filled with 3044 * the contextual information of the Ethernet device. 3045 * @return 3046 * - (0) if successful. 3047 * - (-ENOTSUP) if support for dev_infos_get() does not exist for the device. 3048 * - (-ENODEV) if *port_id* invalid. 3049 * - (-EINVAL) if bad parameter. 3050 */ 3051 int rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info); 3052 3053 /** 3054 * Retrieve the firmware version of a device. 3055 * 3056 * @param port_id 3057 * The port identifier of the device. 3058 * @param fw_version 3059 * A pointer to a string array storing the firmware version of a device, 3060 * the string includes terminating null. This pointer is allocated by caller. 3061 * @param fw_size 3062 * The size of the string array pointed by fw_version, which should be 3063 * large enough to store firmware version of the device. 3064 * @return 3065 * - (0) if successful. 3066 * - (-ENOTSUP) if operation is not supported. 3067 * - (-ENODEV) if *port_id* invalid. 3068 * - (-EIO) if device is removed. 3069 * - (-EINVAL) if bad parameter. 3070 * - (>0) if *fw_size* is not enough to store firmware version, return 3071 * the size of the non truncated string. 3072 */ 3073 int rte_eth_dev_fw_version_get(uint16_t port_id, 3074 char *fw_version, size_t fw_size); 3075 3076 /** 3077 * Retrieve the supported packet types of an Ethernet device. 3078 * 3079 * When a packet type is announced as supported, it *must* be recognized by 3080 * the PMD. For instance, if RTE_PTYPE_L2_ETHER, RTE_PTYPE_L2_ETHER_VLAN 3081 * and RTE_PTYPE_L3_IPV4 are announced, the PMD must return the following 3082 * packet types for these packets: 3083 * - Ether/IPv4 -> RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4 3084 * - Ether/Vlan/IPv4 -> RTE_PTYPE_L2_ETHER_VLAN | RTE_PTYPE_L3_IPV4 3085 * - Ether/[anything else] -> RTE_PTYPE_L2_ETHER 3086 * - Ether/Vlan/[anything else] -> RTE_PTYPE_L2_ETHER_VLAN 3087 * 3088 * When a packet is received by a PMD, the most precise type must be 3089 * returned among the ones supported. However a PMD is allowed to set 3090 * packet type that is not in the supported list, at the condition that it 3091 * is more precise. Therefore, a PMD announcing no supported packet types 3092 * can still set a matching packet type in a received packet. 3093 * 3094 * @note 3095 * Better to invoke this API after the device is already started or rx burst 3096 * function is decided, to obtain correct supported ptypes. 3097 * @note 3098 * if a given PMD does not report what ptypes it supports, then the supported 3099 * ptype count is reported as 0. 3100 * @param port_id 3101 * The port identifier of the Ethernet device. 3102 * @param ptype_mask 3103 * A hint of what kind of packet type which the caller is interested in. 3104 * @param ptypes 3105 * An array pointer to store adequate packet types, allocated by caller. 3106 * @param num 3107 * Size of the array pointed by param ptypes. 3108 * @return 3109 * - (>=0) Number of supported ptypes. If the number of types exceeds num, 3110 * only num entries will be filled into the ptypes array, but the full 3111 * count of supported ptypes will be returned. 3112 * - (-ENODEV) if *port_id* invalid. 3113 * - (-EINVAL) if bad parameter. 3114 */ 3115 int rte_eth_dev_get_supported_ptypes(uint16_t port_id, uint32_t ptype_mask, 3116 uint32_t *ptypes, int num); 3117 /** 3118 * Inform Ethernet device about reduced range of packet types to handle. 3119 * 3120 * Application can use this function to set only specific ptypes that it's 3121 * interested. This information can be used by the PMD to optimize Rx path. 3122 * 3123 * The function accepts an array `set_ptypes` allocated by the caller to 3124 * store the packet types set by the driver, the last element of the array 3125 * is set to RTE_PTYPE_UNKNOWN. The size of the `set_ptype` array should be 3126 * `rte_eth_dev_get_supported_ptypes() + 1` else it might only be filled 3127 * partially. 3128 * 3129 * @param port_id 3130 * The port identifier of the Ethernet device. 3131 * @param ptype_mask 3132 * The ptype family that application is interested in should be bitwise OR of 3133 * RTE_PTYPE_*_MASK or 0. 3134 * @param set_ptypes 3135 * An array pointer to store set packet types, allocated by caller. The 3136 * function marks the end of array with RTE_PTYPE_UNKNOWN. 3137 * @param num 3138 * Size of the array pointed by param ptypes. 3139 * Should be rte_eth_dev_get_supported_ptypes() + 1 to accommodate the 3140 * set ptypes. 3141 * @return 3142 * - (0) if Success. 3143 * - (-ENODEV) if *port_id* invalid. 3144 * - (-EINVAL) if *ptype_mask* is invalid (or) set_ptypes is NULL and 3145 * num > 0. 3146 */ 3147 int rte_eth_dev_set_ptypes(uint16_t port_id, uint32_t ptype_mask, 3148 uint32_t *set_ptypes, unsigned int num); 3149 3150 /** 3151 * Retrieve the MTU of an Ethernet device. 3152 * 3153 * @param port_id 3154 * The port identifier of the Ethernet device. 3155 * @param mtu 3156 * A pointer to a uint16_t where the retrieved MTU is to be stored. 3157 * @return 3158 * - (0) if successful. 3159 * - (-ENODEV) if *port_id* invalid. 3160 * - (-EINVAL) if bad parameter. 3161 */ 3162 int rte_eth_dev_get_mtu(uint16_t port_id, uint16_t *mtu); 3163 3164 /** 3165 * Change the MTU of an Ethernet device. 3166 * 3167 * @param port_id 3168 * The port identifier of the Ethernet device. 3169 * @param mtu 3170 * A uint16_t for the MTU to be applied. 3171 * @return 3172 * - (0) if successful. 3173 * - (-ENOTSUP) if operation is not supported. 3174 * - (-ENODEV) if *port_id* invalid. 3175 * - (-EIO) if device is removed. 3176 * - (-EINVAL) if *mtu* invalid, validation of mtu can occur within 3177 * rte_eth_dev_set_mtu if dev_infos_get is supported by the device or 3178 * when the mtu is set using dev->dev_ops->mtu_set. 3179 * - (-EBUSY) if operation is not allowed when the port is running 3180 */ 3181 int rte_eth_dev_set_mtu(uint16_t port_id, uint16_t mtu); 3182 3183 /** 3184 * Enable/Disable hardware filtering by an Ethernet device of received 3185 * VLAN packets tagged with a given VLAN Tag Identifier. 3186 * 3187 * @param port_id 3188 * The port identifier of the Ethernet device. 3189 * @param vlan_id 3190 * The VLAN Tag Identifier whose filtering must be enabled or disabled. 3191 * @param on 3192 * If > 0, enable VLAN filtering of VLAN packets tagged with *vlan_id*. 3193 * Otherwise, disable VLAN filtering of VLAN packets tagged with *vlan_id*. 3194 * @return 3195 * - (0) if successful. 3196 * - (-ENOTSUP) if hardware-assisted VLAN filtering not configured. 3197 * - (-ENODEV) if *port_id* invalid. 3198 * - (-EIO) if device is removed. 3199 * - (-ENOSYS) if VLAN filtering on *port_id* disabled. 3200 * - (-EINVAL) if *vlan_id* > 4095. 3201 */ 3202 int rte_eth_dev_vlan_filter(uint16_t port_id, uint16_t vlan_id, int on); 3203 3204 /** 3205 * Enable/Disable hardware VLAN Strip by a rx queue of an Ethernet device. 3206 * 3207 * @param port_id 3208 * The port identifier of the Ethernet device. 3209 * @param rx_queue_id 3210 * The index of the receive queue for which a queue stats mapping is required. 3211 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 3212 * to rte_eth_dev_configure(). 3213 * @param on 3214 * If 1, Enable VLAN Stripping of the receive queue of the Ethernet port. 3215 * If 0, Disable VLAN Stripping of the receive queue of the Ethernet port. 3216 * @return 3217 * - (0) if successful. 3218 * - (-ENOTSUP) if hardware-assisted VLAN stripping not configured. 3219 * - (-ENODEV) if *port_id* invalid. 3220 * - (-EINVAL) if *rx_queue_id* invalid. 3221 */ 3222 int rte_eth_dev_set_vlan_strip_on_queue(uint16_t port_id, uint16_t rx_queue_id, 3223 int on); 3224 3225 /** 3226 * Set the Outer VLAN Ether Type by an Ethernet device, it can be inserted to 3227 * the VLAN header. 3228 * 3229 * @param port_id 3230 * The port identifier of the Ethernet device. 3231 * @param vlan_type 3232 * The vlan type. 3233 * @param tag_type 3234 * The Tag Protocol ID 3235 * @return 3236 * - (0) if successful. 3237 * - (-ENOTSUP) if hardware-assisted VLAN TPID setup is not supported. 3238 * - (-ENODEV) if *port_id* invalid. 3239 * - (-EIO) if device is removed. 3240 */ 3241 int rte_eth_dev_set_vlan_ether_type(uint16_t port_id, 3242 enum rte_vlan_type vlan_type, 3243 uint16_t tag_type); 3244 3245 /** 3246 * Set VLAN offload configuration on an Ethernet device. 3247 * 3248 * @param port_id 3249 * The port identifier of the Ethernet device. 3250 * @param offload_mask 3251 * The VLAN Offload bit mask can be mixed use with "OR" 3252 * ETH_VLAN_STRIP_OFFLOAD 3253 * ETH_VLAN_FILTER_OFFLOAD 3254 * ETH_VLAN_EXTEND_OFFLOAD 3255 * ETH_QINQ_STRIP_OFFLOAD 3256 * @return 3257 * - (0) if successful. 3258 * - (-ENOTSUP) if hardware-assisted VLAN filtering not configured. 3259 * - (-ENODEV) if *port_id* invalid. 3260 * - (-EIO) if device is removed. 3261 */ 3262 int rte_eth_dev_set_vlan_offload(uint16_t port_id, int offload_mask); 3263 3264 /** 3265 * Read VLAN Offload configuration from an Ethernet device 3266 * 3267 * @param port_id 3268 * The port identifier of the Ethernet device. 3269 * @return 3270 * - (>0) if successful. Bit mask to indicate 3271 * ETH_VLAN_STRIP_OFFLOAD 3272 * ETH_VLAN_FILTER_OFFLOAD 3273 * ETH_VLAN_EXTEND_OFFLOAD 3274 * ETH_QINQ_STRIP_OFFLOAD 3275 * - (-ENODEV) if *port_id* invalid. 3276 */ 3277 int rte_eth_dev_get_vlan_offload(uint16_t port_id); 3278 3279 /** 3280 * Set port based TX VLAN insertion on or off. 3281 * 3282 * @param port_id 3283 * The port identifier of the Ethernet device. 3284 * @param pvid 3285 * Port based TX VLAN identifier together with user priority. 3286 * @param on 3287 * Turn on or off the port based TX VLAN insertion. 3288 * 3289 * @return 3290 * - (0) if successful. 3291 * - negative if failed. 3292 */ 3293 int rte_eth_dev_set_vlan_pvid(uint16_t port_id, uint16_t pvid, int on); 3294 3295 typedef void (*buffer_tx_error_fn)(struct rte_mbuf **unsent, uint16_t count, 3296 void *userdata); 3297 3298 /** 3299 * Structure used to buffer packets for future TX 3300 * Used by APIs rte_eth_tx_buffer and rte_eth_tx_buffer_flush 3301 */ 3302 struct rte_eth_dev_tx_buffer { 3303 buffer_tx_error_fn error_callback; 3304 void *error_userdata; 3305 uint16_t size; /**< Size of buffer for buffered tx */ 3306 uint16_t length; /**< Number of packets in the array */ 3307 struct rte_mbuf *pkts[]; 3308 /**< Pending packets to be sent on explicit flush or when full */ 3309 }; 3310 3311 /** 3312 * Calculate the size of the tx buffer. 3313 * 3314 * @param sz 3315 * Number of stored packets. 3316 */ 3317 #define RTE_ETH_TX_BUFFER_SIZE(sz) \ 3318 (sizeof(struct rte_eth_dev_tx_buffer) + (sz) * sizeof(struct rte_mbuf *)) 3319 3320 /** 3321 * Initialize default values for buffered transmitting 3322 * 3323 * @param buffer 3324 * Tx buffer to be initialized. 3325 * @param size 3326 * Buffer size 3327 * @return 3328 * 0 if no error 3329 */ 3330 int 3331 rte_eth_tx_buffer_init(struct rte_eth_dev_tx_buffer *buffer, uint16_t size); 3332 3333 /** 3334 * Configure a callback for buffered packets which cannot be sent 3335 * 3336 * Register a specific callback to be called when an attempt is made to send 3337 * all packets buffered on an ethernet port, but not all packets can 3338 * successfully be sent. The callback registered here will be called only 3339 * from calls to rte_eth_tx_buffer() and rte_eth_tx_buffer_flush() APIs. 3340 * The default callback configured for each queue by default just frees the 3341 * packets back to the calling mempool. If additional behaviour is required, 3342 * for example, to count dropped packets, or to retry transmission of packets 3343 * which cannot be sent, this function should be used to register a suitable 3344 * callback function to implement the desired behaviour. 3345 * The example callback "rte_eth_count_unsent_packet_callback()" is also 3346 * provided as reference. 3347 * 3348 * @param buffer 3349 * The port identifier of the Ethernet device. 3350 * @param callback 3351 * The function to be used as the callback. 3352 * @param userdata 3353 * Arbitrary parameter to be passed to the callback function 3354 * @return 3355 * 0 on success, or -EINVAL if bad parameter 3356 */ 3357 int 3358 rte_eth_tx_buffer_set_err_callback(struct rte_eth_dev_tx_buffer *buffer, 3359 buffer_tx_error_fn callback, void *userdata); 3360 3361 /** 3362 * Callback function for silently dropping unsent buffered packets. 3363 * 3364 * This function can be passed to rte_eth_tx_buffer_set_err_callback() to 3365 * adjust the default behavior when buffered packets cannot be sent. This 3366 * function drops any unsent packets silently and is used by tx buffered 3367 * operations as default behavior. 3368 * 3369 * NOTE: this function should not be called directly, instead it should be used 3370 * as a callback for packet buffering. 3371 * 3372 * NOTE: when configuring this function as a callback with 3373 * rte_eth_tx_buffer_set_err_callback(), the final, userdata parameter 3374 * should point to an uint64_t value. 3375 * 3376 * @param pkts 3377 * The previously buffered packets which could not be sent 3378 * @param unsent 3379 * The number of unsent packets in the pkts array 3380 * @param userdata 3381 * Not used 3382 */ 3383 void 3384 rte_eth_tx_buffer_drop_callback(struct rte_mbuf **pkts, uint16_t unsent, 3385 void *userdata); 3386 3387 /** 3388 * Callback function for tracking unsent buffered packets. 3389 * 3390 * This function can be passed to rte_eth_tx_buffer_set_err_callback() to 3391 * adjust the default behavior when buffered packets cannot be sent. This 3392 * function drops any unsent packets, but also updates a user-supplied counter 3393 * to track the overall number of packets dropped. The counter should be an 3394 * uint64_t variable. 3395 * 3396 * NOTE: this function should not be called directly, instead it should be used 3397 * as a callback for packet buffering. 3398 * 3399 * NOTE: when configuring this function as a callback with 3400 * rte_eth_tx_buffer_set_err_callback(), the final, userdata parameter 3401 * should point to an uint64_t value. 3402 * 3403 * @param pkts 3404 * The previously buffered packets which could not be sent 3405 * @param unsent 3406 * The number of unsent packets in the pkts array 3407 * @param userdata 3408 * Pointer to an uint64_t value, which will be incremented by unsent 3409 */ 3410 void 3411 rte_eth_tx_buffer_count_callback(struct rte_mbuf **pkts, uint16_t unsent, 3412 void *userdata); 3413 3414 /** 3415 * Request the driver to free mbufs currently cached by the driver. The 3416 * driver will only free the mbuf if it is no longer in use. It is the 3417 * application's responsibility to ensure rte_eth_tx_buffer_flush(..) is 3418 * called if needed. 3419 * 3420 * @param port_id 3421 * The port identifier of the Ethernet device. 3422 * @param queue_id 3423 * The index of the transmit queue through which output packets must be 3424 * sent. 3425 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 3426 * to rte_eth_dev_configure(). 3427 * @param free_cnt 3428 * Maximum number of packets to free. Use 0 to indicate all possible packets 3429 * should be freed. Note that a packet may be using multiple mbufs. 3430 * @return 3431 * Failure: < 0 3432 * -ENODEV: Invalid interface 3433 * -EIO: device is removed 3434 * -ENOTSUP: Driver does not support function 3435 * Success: >= 0 3436 * 0-n: Number of packets freed. More packets may still remain in ring that 3437 * are in use. 3438 */ 3439 int 3440 rte_eth_tx_done_cleanup(uint16_t port_id, uint16_t queue_id, uint32_t free_cnt); 3441 3442 /** 3443 * Subtypes for IPsec offload event(@ref RTE_ETH_EVENT_IPSEC) raised by 3444 * eth device. 3445 */ 3446 enum rte_eth_event_ipsec_subtype { 3447 RTE_ETH_EVENT_IPSEC_UNKNOWN = 0, 3448 /**< Unknown event type */ 3449 RTE_ETH_EVENT_IPSEC_ESN_OVERFLOW, 3450 /**< Sequence number overflow */ 3451 RTE_ETH_EVENT_IPSEC_SA_TIME_EXPIRY, 3452 /**< Soft time expiry of SA */ 3453 RTE_ETH_EVENT_IPSEC_SA_BYTE_EXPIRY, 3454 /**< Soft byte expiry of SA */ 3455 RTE_ETH_EVENT_IPSEC_MAX 3456 /**< Max value of this enum */ 3457 }; 3458 3459 /** 3460 * Descriptor for @ref RTE_ETH_EVENT_IPSEC event. Used by eth dev to send extra 3461 * information of the IPsec offload event. 3462 */ 3463 struct rte_eth_event_ipsec_desc { 3464 enum rte_eth_event_ipsec_subtype subtype; 3465 /**< Type of RTE_ETH_EVENT_IPSEC_* event */ 3466 uint64_t metadata; 3467 /**< Event specific metadata 3468 * 3469 * For the following events, *userdata* registered 3470 * with the *rte_security_session* would be returned 3471 * as metadata, 3472 * 3473 * - @ref RTE_ETH_EVENT_IPSEC_ESN_OVERFLOW 3474 * - @ref RTE_ETH_EVENT_IPSEC_SA_TIME_EXPIRY 3475 * - @ref RTE_ETH_EVENT_IPSEC_SA_BYTE_EXPIRY 3476 * 3477 * @see struct rte_security_session_conf 3478 * 3479 */ 3480 }; 3481 3482 /** 3483 * The eth device event type for interrupt, and maybe others in the future. 3484 */ 3485 enum rte_eth_event_type { 3486 RTE_ETH_EVENT_UNKNOWN, /**< unknown event type */ 3487 RTE_ETH_EVENT_INTR_LSC, /**< lsc interrupt event */ 3488 RTE_ETH_EVENT_QUEUE_STATE, 3489 /**< queue state event (enabled/disabled) */ 3490 RTE_ETH_EVENT_INTR_RESET, 3491 /**< reset interrupt event, sent to VF on PF reset */ 3492 RTE_ETH_EVENT_VF_MBOX, /**< message from the VF received by PF */ 3493 RTE_ETH_EVENT_MACSEC, /**< MACsec offload related event */ 3494 RTE_ETH_EVENT_INTR_RMV, /**< device removal event */ 3495 RTE_ETH_EVENT_NEW, /**< port is probed */ 3496 RTE_ETH_EVENT_DESTROY, /**< port is released */ 3497 RTE_ETH_EVENT_IPSEC, /**< IPsec offload related event */ 3498 RTE_ETH_EVENT_FLOW_AGED,/**< New aged-out flows is detected */ 3499 RTE_ETH_EVENT_MAX /**< max value of this enum */ 3500 }; 3501 3502 typedef int (*rte_eth_dev_cb_fn)(uint16_t port_id, 3503 enum rte_eth_event_type event, void *cb_arg, void *ret_param); 3504 /**< user application callback to be registered for interrupts */ 3505 3506 /** 3507 * Register a callback function for port event. 3508 * 3509 * @param port_id 3510 * Port id. 3511 * RTE_ETH_ALL means register the event for all port ids. 3512 * @param event 3513 * Event interested. 3514 * @param cb_fn 3515 * User supplied callback function to be called. 3516 * @param cb_arg 3517 * Pointer to the parameters for the registered callback. 3518 * 3519 * @return 3520 * - On success, zero. 3521 * - On failure, a negative value. 3522 */ 3523 int rte_eth_dev_callback_register(uint16_t port_id, 3524 enum rte_eth_event_type event, 3525 rte_eth_dev_cb_fn cb_fn, void *cb_arg); 3526 3527 /** 3528 * Unregister a callback function for port event. 3529 * 3530 * @param port_id 3531 * Port id. 3532 * RTE_ETH_ALL means unregister the event for all port ids. 3533 * @param event 3534 * Event interested. 3535 * @param cb_fn 3536 * User supplied callback function to be called. 3537 * @param cb_arg 3538 * Pointer to the parameters for the registered callback. -1 means to 3539 * remove all for the same callback address and same event. 3540 * 3541 * @return 3542 * - On success, zero. 3543 * - On failure, a negative value. 3544 */ 3545 int rte_eth_dev_callback_unregister(uint16_t port_id, 3546 enum rte_eth_event_type event, 3547 rte_eth_dev_cb_fn cb_fn, void *cb_arg); 3548 3549 /** 3550 * When there is no rx packet coming in Rx Queue for a long time, we can 3551 * sleep lcore related to RX Queue for power saving, and enable rx interrupt 3552 * to be triggered when Rx packet arrives. 3553 * 3554 * The rte_eth_dev_rx_intr_enable() function enables rx queue 3555 * interrupt on specific rx queue of a port. 3556 * 3557 * @param port_id 3558 * The port identifier of the Ethernet device. 3559 * @param queue_id 3560 * The index of the receive queue from which to retrieve input packets. 3561 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 3562 * to rte_eth_dev_configure(). 3563 * @return 3564 * - (0) if successful. 3565 * - (-ENOTSUP) if underlying hardware OR driver doesn't support 3566 * that operation. 3567 * - (-ENODEV) if *port_id* invalid. 3568 * - (-EIO) if device is removed. 3569 */ 3570 int rte_eth_dev_rx_intr_enable(uint16_t port_id, uint16_t queue_id); 3571 3572 /** 3573 * When lcore wakes up from rx interrupt indicating packet coming, disable rx 3574 * interrupt and returns to polling mode. 3575 * 3576 * The rte_eth_dev_rx_intr_disable() function disables rx queue 3577 * interrupt on specific rx queue of a port. 3578 * 3579 * @param port_id 3580 * The port identifier of the Ethernet device. 3581 * @param queue_id 3582 * The index of the receive queue from which to retrieve input packets. 3583 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 3584 * to rte_eth_dev_configure(). 3585 * @return 3586 * - (0) if successful. 3587 * - (-ENOTSUP) if underlying hardware OR driver doesn't support 3588 * that operation. 3589 * - (-ENODEV) if *port_id* invalid. 3590 * - (-EIO) if device is removed. 3591 */ 3592 int rte_eth_dev_rx_intr_disable(uint16_t port_id, uint16_t queue_id); 3593 3594 /** 3595 * RX Interrupt control per port. 3596 * 3597 * @param port_id 3598 * The port identifier of the Ethernet device. 3599 * @param epfd 3600 * Epoll instance fd which the intr vector associated to. 3601 * Using RTE_EPOLL_PER_THREAD allows to use per thread epoll instance. 3602 * @param op 3603 * The operation be performed for the vector. 3604 * Operation type of {RTE_INTR_EVENT_ADD, RTE_INTR_EVENT_DEL}. 3605 * @param data 3606 * User raw data. 3607 * @return 3608 * - On success, zero. 3609 * - On failure, a negative value. 3610 */ 3611 int rte_eth_dev_rx_intr_ctl(uint16_t port_id, int epfd, int op, void *data); 3612 3613 /** 3614 * RX Interrupt control per queue. 3615 * 3616 * @param port_id 3617 * The port identifier of the Ethernet device. 3618 * @param queue_id 3619 * The index of the receive queue from which to retrieve input packets. 3620 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 3621 * to rte_eth_dev_configure(). 3622 * @param epfd 3623 * Epoll instance fd which the intr vector associated to. 3624 * Using RTE_EPOLL_PER_THREAD allows to use per thread epoll instance. 3625 * @param op 3626 * The operation be performed for the vector. 3627 * Operation type of {RTE_INTR_EVENT_ADD, RTE_INTR_EVENT_DEL}. 3628 * @param data 3629 * User raw data. 3630 * @return 3631 * - On success, zero. 3632 * - On failure, a negative value. 3633 */ 3634 int rte_eth_dev_rx_intr_ctl_q(uint16_t port_id, uint16_t queue_id, 3635 int epfd, int op, void *data); 3636 3637 /** 3638 * Get interrupt fd per Rx queue. 3639 * 3640 * @param port_id 3641 * The port identifier of the Ethernet device. 3642 * @param queue_id 3643 * The index of the receive queue from which to retrieve input packets. 3644 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 3645 * to rte_eth_dev_configure(). 3646 * @return 3647 * - (>=0) the interrupt fd associated to the requested Rx queue if 3648 * successful. 3649 * - (-1) on error. 3650 */ 3651 int 3652 rte_eth_dev_rx_intr_ctl_q_get_fd(uint16_t port_id, uint16_t queue_id); 3653 3654 /** 3655 * Turn on the LED on the Ethernet device. 3656 * This function turns on the LED on the Ethernet device. 3657 * 3658 * @param port_id 3659 * The port identifier of the Ethernet device. 3660 * @return 3661 * - (0) if successful. 3662 * - (-ENOTSUP) if underlying hardware OR driver doesn't support 3663 * that operation. 3664 * - (-ENODEV) if *port_id* invalid. 3665 * - (-EIO) if device is removed. 3666 */ 3667 int rte_eth_led_on(uint16_t port_id); 3668 3669 /** 3670 * Turn off the LED on the Ethernet device. 3671 * This function turns off the LED on the Ethernet device. 3672 * 3673 * @param port_id 3674 * The port identifier of the Ethernet device. 3675 * @return 3676 * - (0) if successful. 3677 * - (-ENOTSUP) if underlying hardware OR driver doesn't support 3678 * that operation. 3679 * - (-ENODEV) if *port_id* invalid. 3680 * - (-EIO) if device is removed. 3681 */ 3682 int rte_eth_led_off(uint16_t port_id); 3683 3684 /** 3685 * @warning 3686 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 3687 * 3688 * Get Forward Error Correction(FEC) capability. 3689 * 3690 * @param port_id 3691 * The port identifier of the Ethernet device. 3692 * @param speed_fec_capa 3693 * speed_fec_capa is out only with per-speed capabilities. 3694 * If set to NULL, the function returns the required number 3695 * of required array entries. 3696 * @param num 3697 * a number of elements in an speed_fec_capa array. 3698 * 3699 * @return 3700 * - A non-negative value lower or equal to num: success. The return value 3701 * is the number of entries filled in the fec capa array. 3702 * - A non-negative value higher than num: error, the given fec capa array 3703 * is too small. The return value corresponds to the num that should 3704 * be given to succeed. The entries in fec capa array are not valid and 3705 * shall not be used by the caller. 3706 * - (-ENOTSUP) if underlying hardware OR driver doesn't support. 3707 * that operation. 3708 * - (-EIO) if device is removed. 3709 * - (-ENODEV) if *port_id* invalid. 3710 * - (-EINVAL) if *num* or *speed_fec_capa* invalid 3711 */ 3712 __rte_experimental 3713 int rte_eth_fec_get_capability(uint16_t port_id, 3714 struct rte_eth_fec_capa *speed_fec_capa, 3715 unsigned int num); 3716 3717 /** 3718 * @warning 3719 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 3720 * 3721 * Get current Forward Error Correction(FEC) mode. 3722 * If link is down and AUTO is enabled, AUTO is returned, otherwise, 3723 * configured FEC mode is returned. 3724 * If link is up, current FEC mode is returned. 3725 * 3726 * @param port_id 3727 * The port identifier of the Ethernet device. 3728 * @param fec_capa 3729 * A bitmask of enabled FEC modes. If AUTO bit is set, other 3730 * bits specify FEC modes which may be negotiated. If AUTO 3731 * bit is clear, specify FEC modes to be used (only one valid 3732 * mode per speed may be set). 3733 * @return 3734 * - (0) if successful. 3735 * - (-ENOTSUP) if underlying hardware OR driver doesn't support. 3736 * that operation. 3737 * - (-EIO) if device is removed. 3738 * - (-ENODEV) if *port_id* invalid. 3739 */ 3740 __rte_experimental 3741 int rte_eth_fec_get(uint16_t port_id, uint32_t *fec_capa); 3742 3743 /** 3744 * @warning 3745 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 3746 * 3747 * Set Forward Error Correction(FEC) mode. 3748 * 3749 * @param port_id 3750 * The port identifier of the Ethernet device. 3751 * @param fec_capa 3752 * A bitmask of allowed FEC modes. If AUTO bit is set, other 3753 * bits specify FEC modes which may be negotiated. If AUTO 3754 * bit is clear, specify FEC modes to be used (only one valid 3755 * mode per speed may be set). 3756 * @return 3757 * - (0) if successful. 3758 * - (-EINVAL) if the FEC mode is not valid. 3759 * - (-ENOTSUP) if underlying hardware OR driver doesn't support. 3760 * - (-EIO) if device is removed. 3761 * - (-ENODEV) if *port_id* invalid. 3762 */ 3763 __rte_experimental 3764 int rte_eth_fec_set(uint16_t port_id, uint32_t fec_capa); 3765 3766 /** 3767 * Get current status of the Ethernet link flow control for Ethernet device 3768 * 3769 * @param port_id 3770 * The port identifier of the Ethernet device. 3771 * @param fc_conf 3772 * The pointer to the structure where to store the flow control parameters. 3773 * @return 3774 * - (0) if successful. 3775 * - (-ENOTSUP) if hardware doesn't support flow control. 3776 * - (-ENODEV) if *port_id* invalid. 3777 * - (-EIO) if device is removed. 3778 * - (-EINVAL) if bad parameter. 3779 */ 3780 int rte_eth_dev_flow_ctrl_get(uint16_t port_id, 3781 struct rte_eth_fc_conf *fc_conf); 3782 3783 /** 3784 * Configure the Ethernet link flow control for Ethernet device 3785 * 3786 * @param port_id 3787 * The port identifier of the Ethernet device. 3788 * @param fc_conf 3789 * The pointer to the structure of the flow control parameters. 3790 * @return 3791 * - (0) if successful. 3792 * - (-ENOTSUP) if hardware doesn't support flow control mode. 3793 * - (-ENODEV) if *port_id* invalid. 3794 * - (-EINVAL) if bad parameter 3795 * - (-EIO) if flow control setup failure or device is removed. 3796 */ 3797 int rte_eth_dev_flow_ctrl_set(uint16_t port_id, 3798 struct rte_eth_fc_conf *fc_conf); 3799 3800 /** 3801 * Configure the Ethernet priority flow control under DCB environment 3802 * for Ethernet device. 3803 * 3804 * @param port_id 3805 * The port identifier of the Ethernet device. 3806 * @param pfc_conf 3807 * The pointer to the structure of the priority flow control parameters. 3808 * @return 3809 * - (0) if successful. 3810 * - (-ENOTSUP) if hardware doesn't support priority flow control mode. 3811 * - (-ENODEV) if *port_id* invalid. 3812 * - (-EINVAL) if bad parameter 3813 * - (-EIO) if flow control setup failure or device is removed. 3814 */ 3815 int rte_eth_dev_priority_flow_ctrl_set(uint16_t port_id, 3816 struct rte_eth_pfc_conf *pfc_conf); 3817 3818 /** 3819 * Add a MAC address to the set used for filtering incoming packets. 3820 * 3821 * @param port_id 3822 * The port identifier of the Ethernet device. 3823 * @param mac_addr 3824 * The MAC address to add. 3825 * @param pool 3826 * VMDq pool index to associate address with (if VMDq is enabled). If VMDq is 3827 * not enabled, this should be set to 0. 3828 * @return 3829 * - (0) if successfully added or *mac_addr* was already added. 3830 * - (-ENOTSUP) if hardware doesn't support this feature. 3831 * - (-ENODEV) if *port* is invalid. 3832 * - (-EIO) if device is removed. 3833 * - (-ENOSPC) if no more MAC addresses can be added. 3834 * - (-EINVAL) if MAC address is invalid. 3835 */ 3836 int rte_eth_dev_mac_addr_add(uint16_t port_id, struct rte_ether_addr *mac_addr, 3837 uint32_t pool); 3838 3839 /** 3840 * Remove a MAC address from the internal array of addresses. 3841 * 3842 * @param port_id 3843 * The port identifier of the Ethernet device. 3844 * @param mac_addr 3845 * MAC address to remove. 3846 * @return 3847 * - (0) if successful, or *mac_addr* didn't exist. 3848 * - (-ENOTSUP) if hardware doesn't support. 3849 * - (-ENODEV) if *port* invalid. 3850 * - (-EADDRINUSE) if attempting to remove the default MAC address. 3851 * - (-EINVAL) if MAC address is invalid. 3852 */ 3853 int rte_eth_dev_mac_addr_remove(uint16_t port_id, 3854 struct rte_ether_addr *mac_addr); 3855 3856 /** 3857 * Set the default MAC address. 3858 * 3859 * @param port_id 3860 * The port identifier of the Ethernet device. 3861 * @param mac_addr 3862 * New default MAC address. 3863 * @return 3864 * - (0) if successful, or *mac_addr* didn't exist. 3865 * - (-ENOTSUP) if hardware doesn't support. 3866 * - (-ENODEV) if *port* invalid. 3867 * - (-EINVAL) if MAC address is invalid. 3868 */ 3869 int rte_eth_dev_default_mac_addr_set(uint16_t port_id, 3870 struct rte_ether_addr *mac_addr); 3871 3872 /** 3873 * Update Redirection Table(RETA) of Receive Side Scaling of Ethernet device. 3874 * 3875 * @param port_id 3876 * The port identifier of the Ethernet device. 3877 * @param reta_conf 3878 * RETA to update. 3879 * @param reta_size 3880 * Redirection table size. The table size can be queried by 3881 * rte_eth_dev_info_get(). 3882 * @return 3883 * - (0) if successful. 3884 * - (-ENODEV) if *port_id* is invalid. 3885 * - (-ENOTSUP) if hardware doesn't support. 3886 * - (-EINVAL) if bad parameter. 3887 * - (-EIO) if device is removed. 3888 */ 3889 int rte_eth_dev_rss_reta_update(uint16_t port_id, 3890 struct rte_eth_rss_reta_entry64 *reta_conf, 3891 uint16_t reta_size); 3892 3893 /** 3894 * Query Redirection Table(RETA) of Receive Side Scaling of Ethernet device. 3895 * 3896 * @param port_id 3897 * The port identifier of the Ethernet device. 3898 * @param reta_conf 3899 * RETA to query. For each requested reta entry, corresponding bit 3900 * in mask must be set. 3901 * @param reta_size 3902 * Redirection table size. The table size can be queried by 3903 * rte_eth_dev_info_get(). 3904 * @return 3905 * - (0) if successful. 3906 * - (-ENODEV) if *port_id* is invalid. 3907 * - (-ENOTSUP) if hardware doesn't support. 3908 * - (-EINVAL) if bad parameter. 3909 * - (-EIO) if device is removed. 3910 */ 3911 int rte_eth_dev_rss_reta_query(uint16_t port_id, 3912 struct rte_eth_rss_reta_entry64 *reta_conf, 3913 uint16_t reta_size); 3914 3915 /** 3916 * Updates unicast hash table for receiving packet with the given destination 3917 * MAC address, and the packet is routed to all VFs for which the RX mode is 3918 * accept packets that match the unicast hash table. 3919 * 3920 * @param port_id 3921 * The port identifier of the Ethernet device. 3922 * @param addr 3923 * Unicast MAC address. 3924 * @param on 3925 * 1 - Set an unicast hash bit for receiving packets with the MAC address. 3926 * 0 - Clear an unicast hash bit. 3927 * @return 3928 * - (0) if successful. 3929 * - (-ENOTSUP) if hardware doesn't support. 3930 * - (-ENODEV) if *port_id* invalid. 3931 * - (-EIO) if device is removed. 3932 * - (-EINVAL) if bad parameter. 3933 */ 3934 int rte_eth_dev_uc_hash_table_set(uint16_t port_id, struct rte_ether_addr *addr, 3935 uint8_t on); 3936 3937 /** 3938 * Updates all unicast hash bitmaps for receiving packet with any Unicast 3939 * Ethernet MAC addresses,the packet is routed to all VFs for which the RX 3940 * mode is accept packets that match the unicast hash table. 3941 * 3942 * @param port_id 3943 * The port identifier of the Ethernet device. 3944 * @param on 3945 * 1 - Set all unicast hash bitmaps for receiving all the Ethernet 3946 * MAC addresses 3947 * 0 - Clear all unicast hash bitmaps 3948 * @return 3949 * - (0) if successful. 3950 * - (-ENOTSUP) if hardware doesn't support. 3951 * - (-ENODEV) if *port_id* invalid. 3952 * - (-EIO) if device is removed. 3953 * - (-EINVAL) if bad parameter. 3954 */ 3955 int rte_eth_dev_uc_all_hash_table_set(uint16_t port_id, uint8_t on); 3956 3957 /** 3958 * Set a traffic mirroring rule on an Ethernet device 3959 * 3960 * @param port_id 3961 * The port identifier of the Ethernet device. 3962 * @param mirror_conf 3963 * The pointer to the traffic mirroring structure describing the mirroring rule. 3964 * The *rte_eth_vm_mirror_conf* structure includes the type of mirroring rule, 3965 * destination pool and the value of rule if enable vlan or pool mirroring. 3966 * 3967 * @param rule_id 3968 * The index of traffic mirroring rule, we support four separated rules. 3969 * @param on 3970 * 1 - Enable a mirroring rule. 3971 * 0 - Disable a mirroring rule. 3972 * @return 3973 * - (0) if successful. 3974 * - (-ENOTSUP) if hardware doesn't support this feature. 3975 * - (-ENODEV) if *port_id* invalid. 3976 * - (-EIO) if device is removed. 3977 * - (-EINVAL) if the mr_conf information is not correct. 3978 */ 3979 int rte_eth_mirror_rule_set(uint16_t port_id, 3980 struct rte_eth_mirror_conf *mirror_conf, 3981 uint8_t rule_id, 3982 uint8_t on); 3983 3984 /** 3985 * Reset a traffic mirroring rule on an Ethernet device. 3986 * 3987 * @param port_id 3988 * The port identifier of the Ethernet device. 3989 * @param rule_id 3990 * The index of traffic mirroring rule, we support four separated rules. 3991 * @return 3992 * - (0) if successful. 3993 * - (-ENOTSUP) if hardware doesn't support this feature. 3994 * - (-ENODEV) if *port_id* invalid. 3995 * - (-EIO) if device is removed. 3996 * - (-EINVAL) if bad parameter. 3997 */ 3998 int rte_eth_mirror_rule_reset(uint16_t port_id, 3999 uint8_t rule_id); 4000 4001 /** 4002 * Set the rate limitation for a queue on an Ethernet device. 4003 * 4004 * @param port_id 4005 * The port identifier of the Ethernet device. 4006 * @param queue_idx 4007 * The queue id. 4008 * @param tx_rate 4009 * The tx rate in Mbps. Allocated from the total port link speed. 4010 * @return 4011 * - (0) if successful. 4012 * - (-ENOTSUP) if hardware doesn't support this feature. 4013 * - (-ENODEV) if *port_id* invalid. 4014 * - (-EIO) if device is removed. 4015 * - (-EINVAL) if bad parameter. 4016 */ 4017 int rte_eth_set_queue_rate_limit(uint16_t port_id, uint16_t queue_idx, 4018 uint16_t tx_rate); 4019 4020 /** 4021 * Configuration of Receive Side Scaling hash computation of Ethernet device. 4022 * 4023 * @param port_id 4024 * The port identifier of the Ethernet device. 4025 * @param rss_conf 4026 * The new configuration to use for RSS hash computation on the port. 4027 * @return 4028 * - (0) if successful. 4029 * - (-ENODEV) if port identifier is invalid. 4030 * - (-EIO) if device is removed. 4031 * - (-ENOTSUP) if hardware doesn't support. 4032 * - (-EINVAL) if bad parameter. 4033 */ 4034 int rte_eth_dev_rss_hash_update(uint16_t port_id, 4035 struct rte_eth_rss_conf *rss_conf); 4036 4037 /** 4038 * Retrieve current configuration of Receive Side Scaling hash computation 4039 * of Ethernet device. 4040 * 4041 * @param port_id 4042 * The port identifier of the Ethernet device. 4043 * @param rss_conf 4044 * Where to store the current RSS hash configuration of the Ethernet device. 4045 * @return 4046 * - (0) if successful. 4047 * - (-ENODEV) if port identifier is invalid. 4048 * - (-EIO) if device is removed. 4049 * - (-ENOTSUP) if hardware doesn't support RSS. 4050 * - (-EINVAL) if bad parameter. 4051 */ 4052 int 4053 rte_eth_dev_rss_hash_conf_get(uint16_t port_id, 4054 struct rte_eth_rss_conf *rss_conf); 4055 4056 /** 4057 * Add UDP tunneling port for a type of tunnel. 4058 * 4059 * Some NICs may require such configuration to properly parse a tunnel 4060 * with any standard or custom UDP port. 4061 * The packets with this UDP port will be parsed for this type of tunnel. 4062 * The device parser will also check the rest of the tunnel headers 4063 * before classifying the packet. 4064 * 4065 * With some devices, this API will affect packet classification, i.e.: 4066 * - mbuf.packet_type reported on Rx 4067 * - rte_flow rules with tunnel items 4068 * 4069 * @param port_id 4070 * The port identifier of the Ethernet device. 4071 * @param tunnel_udp 4072 * UDP tunneling configuration. 4073 * 4074 * @return 4075 * - (0) if successful. 4076 * - (-ENODEV) if port identifier is invalid. 4077 * - (-EIO) if device is removed. 4078 * - (-ENOTSUP) if hardware doesn't support tunnel type. 4079 */ 4080 int 4081 rte_eth_dev_udp_tunnel_port_add(uint16_t port_id, 4082 struct rte_eth_udp_tunnel *tunnel_udp); 4083 4084 /** 4085 * Delete UDP tunneling port for a type of tunnel. 4086 * 4087 * The packets with this UDP port will not be classified as this type of tunnel 4088 * anymore if the device use such mapping for tunnel packet classification. 4089 * 4090 * @see rte_eth_dev_udp_tunnel_port_add 4091 * 4092 * @param port_id 4093 * The port identifier of the Ethernet device. 4094 * @param tunnel_udp 4095 * UDP tunneling configuration. 4096 * 4097 * @return 4098 * - (0) if successful. 4099 * - (-ENODEV) if port identifier is invalid. 4100 * - (-EIO) if device is removed. 4101 * - (-ENOTSUP) if hardware doesn't support tunnel type. 4102 */ 4103 int 4104 rte_eth_dev_udp_tunnel_port_delete(uint16_t port_id, 4105 struct rte_eth_udp_tunnel *tunnel_udp); 4106 4107 /** 4108 * Get DCB information on an Ethernet device. 4109 * 4110 * @param port_id 4111 * The port identifier of the Ethernet device. 4112 * @param dcb_info 4113 * dcb information. 4114 * @return 4115 * - (0) if successful. 4116 * - (-ENODEV) if port identifier is invalid. 4117 * - (-EIO) if device is removed. 4118 * - (-ENOTSUP) if hardware doesn't support. 4119 * - (-EINVAL) if bad parameter. 4120 */ 4121 int rte_eth_dev_get_dcb_info(uint16_t port_id, 4122 struct rte_eth_dcb_info *dcb_info); 4123 4124 struct rte_eth_rxtx_callback; 4125 4126 /** 4127 * Add a callback to be called on packet RX on a given port and queue. 4128 * 4129 * This API configures a function to be called for each burst of 4130 * packets received on a given NIC port queue. The return value is a pointer 4131 * that can be used to later remove the callback using 4132 * rte_eth_remove_rx_callback(). 4133 * 4134 * Multiple functions are called in the order that they are added. 4135 * 4136 * @param port_id 4137 * The port identifier of the Ethernet device. 4138 * @param queue_id 4139 * The queue on the Ethernet device on which the callback is to be added. 4140 * @param fn 4141 * The callback function 4142 * @param user_param 4143 * A generic pointer parameter which will be passed to each invocation of the 4144 * callback function on this port and queue. Inter-thread synchronization 4145 * of any user data changes is the responsibility of the user. 4146 * 4147 * @return 4148 * NULL on error. 4149 * On success, a pointer value which can later be used to remove the callback. 4150 */ 4151 const struct rte_eth_rxtx_callback * 4152 rte_eth_add_rx_callback(uint16_t port_id, uint16_t queue_id, 4153 rte_rx_callback_fn fn, void *user_param); 4154 4155 /** 4156 * Add a callback that must be called first on packet RX on a given port 4157 * and queue. 4158 * 4159 * This API configures a first function to be called for each burst of 4160 * packets received on a given NIC port queue. The return value is a pointer 4161 * that can be used to later remove the callback using 4162 * rte_eth_remove_rx_callback(). 4163 * 4164 * Multiple functions are called in the order that they are added. 4165 * 4166 * @param port_id 4167 * The port identifier of the Ethernet device. 4168 * @param queue_id 4169 * The queue on the Ethernet device on which the callback is to be added. 4170 * @param fn 4171 * The callback function 4172 * @param user_param 4173 * A generic pointer parameter which will be passed to each invocation of the 4174 * callback function on this port and queue. Inter-thread synchronization 4175 * of any user data changes is the responsibility of the user. 4176 * 4177 * @return 4178 * NULL on error. 4179 * On success, a pointer value which can later be used to remove the callback. 4180 */ 4181 const struct rte_eth_rxtx_callback * 4182 rte_eth_add_first_rx_callback(uint16_t port_id, uint16_t queue_id, 4183 rte_rx_callback_fn fn, void *user_param); 4184 4185 /** 4186 * Add a callback to be called on packet TX on a given port and queue. 4187 * 4188 * This API configures a function to be called for each burst of 4189 * packets sent on a given NIC port queue. The return value is a pointer 4190 * that can be used to later remove the callback using 4191 * rte_eth_remove_tx_callback(). 4192 * 4193 * Multiple functions are called in the order that they are added. 4194 * 4195 * @param port_id 4196 * The port identifier of the Ethernet device. 4197 * @param queue_id 4198 * The queue on the Ethernet device on which the callback is to be added. 4199 * @param fn 4200 * The callback function 4201 * @param user_param 4202 * A generic pointer parameter which will be passed to each invocation of the 4203 * callback function on this port and queue. Inter-thread synchronization 4204 * of any user data changes is the responsibility of the user. 4205 * 4206 * @return 4207 * NULL on error. 4208 * On success, a pointer value which can later be used to remove the callback. 4209 */ 4210 const struct rte_eth_rxtx_callback * 4211 rte_eth_add_tx_callback(uint16_t port_id, uint16_t queue_id, 4212 rte_tx_callback_fn fn, void *user_param); 4213 4214 /** 4215 * Remove an RX packet callback from a given port and queue. 4216 * 4217 * This function is used to removed callbacks that were added to a NIC port 4218 * queue using rte_eth_add_rx_callback(). 4219 * 4220 * Note: the callback is removed from the callback list but it isn't freed 4221 * since the it may still be in use. The memory for the callback can be 4222 * subsequently freed back by the application by calling rte_free(): 4223 * 4224 * - Immediately - if the port is stopped, or the user knows that no 4225 * callbacks are in flight e.g. if called from the thread doing RX/TX 4226 * on that queue. 4227 * 4228 * - After a short delay - where the delay is sufficient to allow any 4229 * in-flight callbacks to complete. Alternately, the RCU mechanism can be 4230 * used to detect when data plane threads have ceased referencing the 4231 * callback memory. 4232 * 4233 * @param port_id 4234 * The port identifier of the Ethernet device. 4235 * @param queue_id 4236 * The queue on the Ethernet device from which the callback is to be removed. 4237 * @param user_cb 4238 * User supplied callback created via rte_eth_add_rx_callback(). 4239 * 4240 * @return 4241 * - 0: Success. Callback was removed. 4242 * - -ENODEV: If *port_id* is invalid. 4243 * - -ENOTSUP: Callback support is not available. 4244 * - -EINVAL: The queue_id is out of range, or the callback 4245 * is NULL or not found for the port/queue. 4246 */ 4247 int rte_eth_remove_rx_callback(uint16_t port_id, uint16_t queue_id, 4248 const struct rte_eth_rxtx_callback *user_cb); 4249 4250 /** 4251 * Remove a TX packet callback from a given port and queue. 4252 * 4253 * This function is used to removed callbacks that were added to a NIC port 4254 * queue using rte_eth_add_tx_callback(). 4255 * 4256 * Note: the callback is removed from the callback list but it isn't freed 4257 * since the it may still be in use. The memory for the callback can be 4258 * subsequently freed back by the application by calling rte_free(): 4259 * 4260 * - Immediately - if the port is stopped, or the user knows that no 4261 * callbacks are in flight e.g. if called from the thread doing RX/TX 4262 * on that queue. 4263 * 4264 * - After a short delay - where the delay is sufficient to allow any 4265 * in-flight callbacks to complete. Alternately, the RCU mechanism can be 4266 * used to detect when data plane threads have ceased referencing the 4267 * callback memory. 4268 * 4269 * @param port_id 4270 * The port identifier of the Ethernet device. 4271 * @param queue_id 4272 * The queue on the Ethernet device from which the callback is to be removed. 4273 * @param user_cb 4274 * User supplied callback created via rte_eth_add_tx_callback(). 4275 * 4276 * @return 4277 * - 0: Success. Callback was removed. 4278 * - -ENODEV: If *port_id* is invalid. 4279 * - -ENOTSUP: Callback support is not available. 4280 * - -EINVAL: The queue_id is out of range, or the callback 4281 * is NULL or not found for the port/queue. 4282 */ 4283 int rte_eth_remove_tx_callback(uint16_t port_id, uint16_t queue_id, 4284 const struct rte_eth_rxtx_callback *user_cb); 4285 4286 /** 4287 * Retrieve information about given port's RX queue. 4288 * 4289 * @param port_id 4290 * The port identifier of the Ethernet device. 4291 * @param queue_id 4292 * The RX queue on the Ethernet device for which information 4293 * will be retrieved. 4294 * @param qinfo 4295 * A pointer to a structure of type *rte_eth_rxq_info_info* to be filled with 4296 * the information of the Ethernet device. 4297 * 4298 * @return 4299 * - 0: Success 4300 * - -ENODEV: If *port_id* is invalid. 4301 * - -ENOTSUP: routine is not supported by the device PMD. 4302 * - -EINVAL: The queue_id is out of range, or the queue 4303 * is hairpin queue. 4304 */ 4305 int rte_eth_rx_queue_info_get(uint16_t port_id, uint16_t queue_id, 4306 struct rte_eth_rxq_info *qinfo); 4307 4308 /** 4309 * Retrieve information about given port's TX queue. 4310 * 4311 * @param port_id 4312 * The port identifier of the Ethernet device. 4313 * @param queue_id 4314 * The TX queue on the Ethernet device for which information 4315 * will be retrieved. 4316 * @param qinfo 4317 * A pointer to a structure of type *rte_eth_txq_info_info* to be filled with 4318 * the information of the Ethernet device. 4319 * 4320 * @return 4321 * - 0: Success 4322 * - -ENODEV: If *port_id* is invalid. 4323 * - -ENOTSUP: routine is not supported by the device PMD. 4324 * - -EINVAL: The queue_id is out of range, or the queue 4325 * is hairpin queue. 4326 */ 4327 int rte_eth_tx_queue_info_get(uint16_t port_id, uint16_t queue_id, 4328 struct rte_eth_txq_info *qinfo); 4329 4330 /** 4331 * Retrieve information about the Rx packet burst mode. 4332 * 4333 * @param port_id 4334 * The port identifier of the Ethernet device. 4335 * @param queue_id 4336 * The Rx queue on the Ethernet device for which information 4337 * will be retrieved. 4338 * @param mode 4339 * A pointer to a structure of type *rte_eth_burst_mode* to be filled 4340 * with the information of the packet burst mode. 4341 * 4342 * @return 4343 * - 0: Success 4344 * - -ENODEV: If *port_id* is invalid. 4345 * - -ENOTSUP: routine is not supported by the device PMD. 4346 * - -EINVAL: The queue_id is out of range. 4347 */ 4348 int rte_eth_rx_burst_mode_get(uint16_t port_id, uint16_t queue_id, 4349 struct rte_eth_burst_mode *mode); 4350 4351 /** 4352 * Retrieve information about the Tx packet burst mode. 4353 * 4354 * @param port_id 4355 * The port identifier of the Ethernet device. 4356 * @param queue_id 4357 * The Tx queue on the Ethernet device for which information 4358 * will be retrieved. 4359 * @param mode 4360 * A pointer to a structure of type *rte_eth_burst_mode* to be filled 4361 * with the information of the packet burst mode. 4362 * 4363 * @return 4364 * - 0: Success 4365 * - -ENODEV: If *port_id* is invalid. 4366 * - -ENOTSUP: routine is not supported by the device PMD. 4367 * - -EINVAL: The queue_id is out of range. 4368 */ 4369 int rte_eth_tx_burst_mode_get(uint16_t port_id, uint16_t queue_id, 4370 struct rte_eth_burst_mode *mode); 4371 4372 /** 4373 * @warning 4374 * @b EXPERIMENTAL: this API may change without prior notice. 4375 * 4376 * Retrieve the monitor condition for a given receive queue. 4377 * 4378 * @param port_id 4379 * The port identifier of the Ethernet device. 4380 * @param queue_id 4381 * The Rx queue on the Ethernet device for which information 4382 * will be retrieved. 4383 * @param pmc 4384 * The pointer to power-optimized monitoring condition structure. 4385 * 4386 * @return 4387 * - 0: Success. 4388 * -ENOTSUP: Operation not supported. 4389 * -EINVAL: Invalid parameters. 4390 * -ENODEV: Invalid port ID. 4391 */ 4392 __rte_experimental 4393 int rte_eth_get_monitor_addr(uint16_t port_id, uint16_t queue_id, 4394 struct rte_power_monitor_cond *pmc); 4395 4396 /** 4397 * Retrieve device registers and register attributes (number of registers and 4398 * register size) 4399 * 4400 * @param port_id 4401 * The port identifier of the Ethernet device. 4402 * @param info 4403 * Pointer to rte_dev_reg_info structure to fill in. If info->data is 4404 * NULL the function fills in the width and length fields. If non-NULL 4405 * the registers are put into the buffer pointed at by the data field. 4406 * @return 4407 * - (0) if successful. 4408 * - (-ENOTSUP) if hardware doesn't support. 4409 * - (-EINVAL) if bad parameter. 4410 * - (-ENODEV) if *port_id* invalid. 4411 * - (-EIO) if device is removed. 4412 * - others depends on the specific operations implementation. 4413 */ 4414 int rte_eth_dev_get_reg_info(uint16_t port_id, struct rte_dev_reg_info *info); 4415 4416 /** 4417 * Retrieve size of device EEPROM 4418 * 4419 * @param port_id 4420 * The port identifier of the Ethernet device. 4421 * @return 4422 * - (>=0) EEPROM size if successful. 4423 * - (-ENOTSUP) if hardware doesn't support. 4424 * - (-ENODEV) if *port_id* invalid. 4425 * - (-EIO) if device is removed. 4426 * - others depends on the specific operations implementation. 4427 */ 4428 int rte_eth_dev_get_eeprom_length(uint16_t port_id); 4429 4430 /** 4431 * Retrieve EEPROM and EEPROM attribute 4432 * 4433 * @param port_id 4434 * The port identifier of the Ethernet device. 4435 * @param info 4436 * The template includes buffer for return EEPROM data and 4437 * EEPROM attributes to be filled. 4438 * @return 4439 * - (0) if successful. 4440 * - (-ENOTSUP) if hardware doesn't support. 4441 * - (-EINVAL) if bad parameter. 4442 * - (-ENODEV) if *port_id* invalid. 4443 * - (-EIO) if device is removed. 4444 * - others depends on the specific operations implementation. 4445 */ 4446 int rte_eth_dev_get_eeprom(uint16_t port_id, struct rte_dev_eeprom_info *info); 4447 4448 /** 4449 * Program EEPROM with provided data 4450 * 4451 * @param port_id 4452 * The port identifier of the Ethernet device. 4453 * @param info 4454 * The template includes EEPROM data for programming and 4455 * EEPROM attributes to be filled 4456 * @return 4457 * - (0) if successful. 4458 * - (-ENOTSUP) if hardware doesn't support. 4459 * - (-ENODEV) if *port_id* invalid. 4460 * - (-EINVAL) if bad parameter. 4461 * - (-EIO) if device is removed. 4462 * - others depends on the specific operations implementation. 4463 */ 4464 int rte_eth_dev_set_eeprom(uint16_t port_id, struct rte_dev_eeprom_info *info); 4465 4466 /** 4467 * @warning 4468 * @b EXPERIMENTAL: this API may change without prior notice. 4469 * 4470 * Retrieve the type and size of plugin module EEPROM 4471 * 4472 * @param port_id 4473 * The port identifier of the Ethernet device. 4474 * @param modinfo 4475 * The type and size of plugin module EEPROM. 4476 * @return 4477 * - (0) if successful. 4478 * - (-ENOTSUP) if hardware doesn't support. 4479 * - (-ENODEV) if *port_id* invalid. 4480 * - (-EINVAL) if bad parameter. 4481 * - (-EIO) if device is removed. 4482 * - others depends on the specific operations implementation. 4483 */ 4484 __rte_experimental 4485 int 4486 rte_eth_dev_get_module_info(uint16_t port_id, 4487 struct rte_eth_dev_module_info *modinfo); 4488 4489 /** 4490 * @warning 4491 * @b EXPERIMENTAL: this API may change without prior notice. 4492 * 4493 * Retrieve the data of plugin module EEPROM 4494 * 4495 * @param port_id 4496 * The port identifier of the Ethernet device. 4497 * @param info 4498 * The template includes the plugin module EEPROM attributes, and the 4499 * buffer for return plugin module EEPROM data. 4500 * @return 4501 * - (0) if successful. 4502 * - (-ENOTSUP) if hardware doesn't support. 4503 * - (-EINVAL) if bad parameter. 4504 * - (-ENODEV) if *port_id* invalid. 4505 * - (-EIO) if device is removed. 4506 * - others depends on the specific operations implementation. 4507 */ 4508 __rte_experimental 4509 int 4510 rte_eth_dev_get_module_eeprom(uint16_t port_id, 4511 struct rte_dev_eeprom_info *info); 4512 4513 /** 4514 * Set the list of multicast addresses to filter on an Ethernet device. 4515 * 4516 * @param port_id 4517 * The port identifier of the Ethernet device. 4518 * @param mc_addr_set 4519 * The array of multicast addresses to set. Equal to NULL when the function 4520 * is invoked to flush the set of filtered addresses. 4521 * @param nb_mc_addr 4522 * The number of multicast addresses in the *mc_addr_set* array. Equal to 0 4523 * when the function is invoked to flush the set of filtered addresses. 4524 * @return 4525 * - (0) if successful. 4526 * - (-ENODEV) if *port_id* invalid. 4527 * - (-EIO) if device is removed. 4528 * - (-ENOTSUP) if PMD of *port_id* doesn't support multicast filtering. 4529 * - (-ENOSPC) if *port_id* has not enough multicast filtering resources. 4530 * - (-EINVAL) if bad parameter. 4531 */ 4532 int rte_eth_dev_set_mc_addr_list(uint16_t port_id, 4533 struct rte_ether_addr *mc_addr_set, 4534 uint32_t nb_mc_addr); 4535 4536 /** 4537 * Enable IEEE1588/802.1AS timestamping for an Ethernet device. 4538 * 4539 * @param port_id 4540 * The port identifier of the Ethernet device. 4541 * 4542 * @return 4543 * - 0: Success. 4544 * - -ENODEV: The port ID is invalid. 4545 * - -EIO: if device is removed. 4546 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4547 */ 4548 int rte_eth_timesync_enable(uint16_t port_id); 4549 4550 /** 4551 * Disable IEEE1588/802.1AS timestamping for an Ethernet device. 4552 * 4553 * @param port_id 4554 * The port identifier of the Ethernet device. 4555 * 4556 * @return 4557 * - 0: Success. 4558 * - -ENODEV: The port ID is invalid. 4559 * - -EIO: if device is removed. 4560 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4561 */ 4562 int rte_eth_timesync_disable(uint16_t port_id); 4563 4564 /** 4565 * Read an IEEE1588/802.1AS RX timestamp from an Ethernet device. 4566 * 4567 * @param port_id 4568 * The port identifier of the Ethernet device. 4569 * @param timestamp 4570 * Pointer to the timestamp struct. 4571 * @param flags 4572 * Device specific flags. Used to pass the RX timesync register index to 4573 * i40e. Unused in igb/ixgbe, pass 0 instead. 4574 * 4575 * @return 4576 * - 0: Success. 4577 * - -EINVAL: No timestamp is available. 4578 * - -ENODEV: The port ID is invalid. 4579 * - -EIO: if device is removed. 4580 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4581 */ 4582 int rte_eth_timesync_read_rx_timestamp(uint16_t port_id, 4583 struct timespec *timestamp, uint32_t flags); 4584 4585 /** 4586 * Read an IEEE1588/802.1AS TX timestamp from an Ethernet device. 4587 * 4588 * @param port_id 4589 * The port identifier of the Ethernet device. 4590 * @param timestamp 4591 * Pointer to the timestamp struct. 4592 * 4593 * @return 4594 * - 0: Success. 4595 * - -EINVAL: No timestamp is available. 4596 * - -ENODEV: The port ID is invalid. 4597 * - -EIO: if device is removed. 4598 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4599 */ 4600 int rte_eth_timesync_read_tx_timestamp(uint16_t port_id, 4601 struct timespec *timestamp); 4602 4603 /** 4604 * Adjust the timesync clock on an Ethernet device. 4605 * 4606 * This is usually used in conjunction with other Ethdev timesync functions to 4607 * synchronize the device time using the IEEE1588/802.1AS protocol. 4608 * 4609 * @param port_id 4610 * The port identifier of the Ethernet device. 4611 * @param delta 4612 * The adjustment in nanoseconds. 4613 * 4614 * @return 4615 * - 0: Success. 4616 * - -ENODEV: The port ID is invalid. 4617 * - -EIO: if device is removed. 4618 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4619 */ 4620 int rte_eth_timesync_adjust_time(uint16_t port_id, int64_t delta); 4621 4622 /** 4623 * Read the time from the timesync clock on an Ethernet device. 4624 * 4625 * This is usually used in conjunction with other Ethdev timesync functions to 4626 * synchronize the device time using the IEEE1588/802.1AS protocol. 4627 * 4628 * @param port_id 4629 * The port identifier of the Ethernet device. 4630 * @param time 4631 * Pointer to the timespec struct that holds the time. 4632 * 4633 * @return 4634 * - 0: Success. 4635 * - -EINVAL: Bad parameter. 4636 */ 4637 int rte_eth_timesync_read_time(uint16_t port_id, struct timespec *time); 4638 4639 /** 4640 * Set the time of the timesync clock on an Ethernet device. 4641 * 4642 * This is usually used in conjunction with other Ethdev timesync functions to 4643 * synchronize the device time using the IEEE1588/802.1AS protocol. 4644 * 4645 * @param port_id 4646 * The port identifier of the Ethernet device. 4647 * @param time 4648 * Pointer to the timespec struct that holds the time. 4649 * 4650 * @return 4651 * - 0: Success. 4652 * - -EINVAL: No timestamp is available. 4653 * - -ENODEV: The port ID is invalid. 4654 * - -EIO: if device is removed. 4655 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4656 */ 4657 int rte_eth_timesync_write_time(uint16_t port_id, const struct timespec *time); 4658 4659 /** 4660 * @warning 4661 * @b EXPERIMENTAL: this API may change without prior notice. 4662 * 4663 * Read the current clock counter of an Ethernet device 4664 * 4665 * This returns the current raw clock value of an Ethernet device. It is 4666 * a raw amount of ticks, with no given time reference. 4667 * The value returned here is from the same clock than the one 4668 * filling timestamp field of Rx packets when using hardware timestamp 4669 * offload. Therefore it can be used to compute a precise conversion of 4670 * the device clock to the real time. 4671 * 4672 * E.g, a simple heuristic to derivate the frequency would be: 4673 * uint64_t start, end; 4674 * rte_eth_read_clock(port, start); 4675 * rte_delay_ms(100); 4676 * rte_eth_read_clock(port, end); 4677 * double freq = (end - start) * 10; 4678 * 4679 * Compute a common reference with: 4680 * uint64_t base_time_sec = current_time(); 4681 * uint64_t base_clock; 4682 * rte_eth_read_clock(port, base_clock); 4683 * 4684 * Then, convert the raw mbuf timestamp with: 4685 * base_time_sec + (double)(*timestamp_dynfield(mbuf) - base_clock) / freq; 4686 * 4687 * This simple example will not provide a very good accuracy. One must 4688 * at least measure multiple times the frequency and do a regression. 4689 * To avoid deviation from the system time, the common reference can 4690 * be repeated from time to time. The integer division can also be 4691 * converted by a multiplication and a shift for better performance. 4692 * 4693 * @param port_id 4694 * The port identifier of the Ethernet device. 4695 * @param clock 4696 * Pointer to the uint64_t that holds the raw clock value. 4697 * 4698 * @return 4699 * - 0: Success. 4700 * - -ENODEV: The port ID is invalid. 4701 * - -ENOTSUP: The function is not supported by the Ethernet driver. 4702 * - -EINVAL: if bad parameter. 4703 */ 4704 __rte_experimental 4705 int 4706 rte_eth_read_clock(uint16_t port_id, uint64_t *clock); 4707 4708 /** 4709 * Get the port id from device name. The device name should be specified 4710 * as below: 4711 * - PCIe address (Domain:Bus:Device.Function), for example- 0000:2:00.0 4712 * - SoC device name, for example- fsl-gmac0 4713 * - vdev dpdk name, for example- net_[pcap0|null0|tap0] 4714 * 4715 * @param name 4716 * pci address or name of the device 4717 * @param port_id 4718 * pointer to port identifier of the device 4719 * @return 4720 * - (0) if successful and port_id is filled. 4721 * - (-ENODEV or -EINVAL) on failure. 4722 */ 4723 int 4724 rte_eth_dev_get_port_by_name(const char *name, uint16_t *port_id); 4725 4726 /** 4727 * Get the device name from port id. The device name is specified as below: 4728 * - PCIe address (Domain:Bus:Device.Function), for example- 0000:02:00.0 4729 * - SoC device name, for example- fsl-gmac0 4730 * - vdev dpdk name, for example- net_[pcap0|null0|tun0|tap0] 4731 * 4732 * @param port_id 4733 * Port identifier of the device. 4734 * @param name 4735 * Buffer of size RTE_ETH_NAME_MAX_LEN to store the name. 4736 * @return 4737 * - (0) if successful. 4738 * - (-ENODEV) if *port_id* is invalid. 4739 * - (-EINVAL) on failure. 4740 */ 4741 int 4742 rte_eth_dev_get_name_by_port(uint16_t port_id, char *name); 4743 4744 /** 4745 * Check that numbers of Rx and Tx descriptors satisfy descriptors limits from 4746 * the ethernet device information, otherwise adjust them to boundaries. 4747 * 4748 * @param port_id 4749 * The port identifier of the Ethernet device. 4750 * @param nb_rx_desc 4751 * A pointer to a uint16_t where the number of receive 4752 * descriptors stored. 4753 * @param nb_tx_desc 4754 * A pointer to a uint16_t where the number of transmit 4755 * descriptors stored. 4756 * @return 4757 * - (0) if successful. 4758 * - (-ENOTSUP, -ENODEV or -EINVAL) on failure. 4759 */ 4760 int rte_eth_dev_adjust_nb_rx_tx_desc(uint16_t port_id, 4761 uint16_t *nb_rx_desc, 4762 uint16_t *nb_tx_desc); 4763 4764 /** 4765 * Test if a port supports specific mempool ops. 4766 * 4767 * @param port_id 4768 * Port identifier of the Ethernet device. 4769 * @param [in] pool 4770 * The name of the pool operations to test. 4771 * @return 4772 * - 0: best mempool ops choice for this port. 4773 * - 1: mempool ops are supported for this port. 4774 * - -ENOTSUP: mempool ops not supported for this port. 4775 * - -ENODEV: Invalid port Identifier. 4776 * - -EINVAL: Pool param is null. 4777 */ 4778 int 4779 rte_eth_dev_pool_ops_supported(uint16_t port_id, const char *pool); 4780 4781 /** 4782 * Get the security context for the Ethernet device. 4783 * 4784 * @param port_id 4785 * Port identifier of the Ethernet device 4786 * @return 4787 * - NULL on error. 4788 * - pointer to security context on success. 4789 */ 4790 void * 4791 rte_eth_dev_get_sec_ctx(uint16_t port_id); 4792 4793 /** 4794 * @warning 4795 * @b EXPERIMENTAL: this API may change, or be removed, without prior notice 4796 * 4797 * Query the device hairpin capabilities. 4798 * 4799 * @param port_id 4800 * The port identifier of the Ethernet device. 4801 * @param cap 4802 * Pointer to a structure that will hold the hairpin capabilities. 4803 * @return 4804 * - (0) if successful. 4805 * - (-ENOTSUP) if hardware doesn't support. 4806 * - (-EINVAL) if bad parameter. 4807 */ 4808 __rte_experimental 4809 int rte_eth_dev_hairpin_capability_get(uint16_t port_id, 4810 struct rte_eth_hairpin_cap *cap); 4811 4812 /** 4813 * @warning 4814 * @b EXPERIMENTAL: this structure may change without prior notice. 4815 * 4816 * ethernet device representor ID range entry 4817 */ 4818 struct rte_eth_representor_range { 4819 enum rte_eth_representor_type type; /**< Representor type */ 4820 int controller; /**< Controller index */ 4821 int pf; /**< Physical function index */ 4822 __extension__ 4823 union { 4824 int vf; /**< VF start index */ 4825 int sf; /**< SF start index */ 4826 }; 4827 uint32_t id_base; /**< Representor ID start index */ 4828 uint32_t id_end; /**< Representor ID end index */ 4829 char name[RTE_DEV_NAME_MAX_LEN]; /**< Representor name */ 4830 }; 4831 4832 /** 4833 * @warning 4834 * @b EXPERIMENTAL: this structure may change without prior notice. 4835 * 4836 * Ethernet device representor information 4837 */ 4838 struct rte_eth_representor_info { 4839 uint16_t controller; /**< Controller ID of caller device. */ 4840 uint16_t pf; /**< Physical function ID of caller device. */ 4841 uint32_t nb_ranges_alloc; /**< Size of the ranges array. */ 4842 uint32_t nb_ranges; /**< Number of initialized ranges. */ 4843 struct rte_eth_representor_range ranges[];/**< Representor ID range. */ 4844 }; 4845 4846 /** 4847 * Retrieve the representor info of the device. 4848 * 4849 * Get device representor info to be able to calculate a unique 4850 * representor ID. @see rte_eth_representor_id_get helper. 4851 * 4852 * @param port_id 4853 * The port identifier of the device. 4854 * @param info 4855 * A pointer to a representor info structure. 4856 * NULL to return number of range entries and allocate memory 4857 * for next call to store detail. 4858 * The number of ranges that were written into this structure 4859 * will be placed into its nb_ranges field. This number cannot be 4860 * larger than the nb_ranges_alloc that by the user before calling 4861 * this function. It can be smaller than the value returned by the 4862 * function, however. 4863 * @return 4864 * - (-ENOTSUP) if operation is not supported. 4865 * - (-ENODEV) if *port_id* invalid. 4866 * - (-EIO) if device is removed. 4867 * - (>=0) number of available representor range entries. 4868 */ 4869 __rte_experimental 4870 int rte_eth_representor_info_get(uint16_t port_id, 4871 struct rte_eth_representor_info *info); 4872 4873 #include <rte_ethdev_core.h> 4874 4875 /** 4876 * 4877 * Retrieve a burst of input packets from a receive queue of an Ethernet 4878 * device. The retrieved packets are stored in *rte_mbuf* structures whose 4879 * pointers are supplied in the *rx_pkts* array. 4880 * 4881 * The rte_eth_rx_burst() function loops, parsing the RX ring of the 4882 * receive queue, up to *nb_pkts* packets, and for each completed RX 4883 * descriptor in the ring, it performs the following operations: 4884 * 4885 * - Initialize the *rte_mbuf* data structure associated with the 4886 * RX descriptor according to the information provided by the NIC into 4887 * that RX descriptor. 4888 * 4889 * - Store the *rte_mbuf* data structure into the next entry of the 4890 * *rx_pkts* array. 4891 * 4892 * - Replenish the RX descriptor with a new *rte_mbuf* buffer 4893 * allocated from the memory pool associated with the receive queue at 4894 * initialization time. 4895 * 4896 * When retrieving an input packet that was scattered by the controller 4897 * into multiple receive descriptors, the rte_eth_rx_burst() function 4898 * appends the associated *rte_mbuf* buffers to the first buffer of the 4899 * packet. 4900 * 4901 * The rte_eth_rx_burst() function returns the number of packets 4902 * actually retrieved, which is the number of *rte_mbuf* data structures 4903 * effectively supplied into the *rx_pkts* array. 4904 * A return value equal to *nb_pkts* indicates that the RX queue contained 4905 * at least *rx_pkts* packets, and this is likely to signify that other 4906 * received packets remain in the input queue. Applications implementing 4907 * a "retrieve as much received packets as possible" policy can check this 4908 * specific case and keep invoking the rte_eth_rx_burst() function until 4909 * a value less than *nb_pkts* is returned. 4910 * 4911 * This receive method has the following advantages: 4912 * 4913 * - It allows a run-to-completion network stack engine to retrieve and 4914 * to immediately process received packets in a fast burst-oriented 4915 * approach, avoiding the overhead of unnecessary intermediate packet 4916 * queue/dequeue operations. 4917 * 4918 * - Conversely, it also allows an asynchronous-oriented processing 4919 * method to retrieve bursts of received packets and to immediately 4920 * queue them for further parallel processing by another logical core, 4921 * for instance. However, instead of having received packets being 4922 * individually queued by the driver, this approach allows the caller 4923 * of the rte_eth_rx_burst() function to queue a burst of retrieved 4924 * packets at a time and therefore dramatically reduce the cost of 4925 * enqueue/dequeue operations per packet. 4926 * 4927 * - It allows the rte_eth_rx_burst() function of the driver to take 4928 * advantage of burst-oriented hardware features (CPU cache, 4929 * prefetch instructions, and so on) to minimize the number of CPU 4930 * cycles per packet. 4931 * 4932 * To summarize, the proposed receive API enables many 4933 * burst-oriented optimizations in both synchronous and asynchronous 4934 * packet processing environments with no overhead in both cases. 4935 * 4936 * @note 4937 * Some drivers using vector instructions require that *nb_pkts* is 4938 * divisible by 4 or 8, depending on the driver implementation. 4939 * 4940 * The rte_eth_rx_burst() function does not provide any error 4941 * notification to avoid the corresponding overhead. As a hint, the 4942 * upper-level application might check the status of the device link once 4943 * being systematically returned a 0 value for a given number of tries. 4944 * 4945 * @param port_id 4946 * The port identifier of the Ethernet device. 4947 * @param queue_id 4948 * The index of the receive queue from which to retrieve input packets. 4949 * The value must be in the range [0, nb_rx_queue - 1] previously supplied 4950 * to rte_eth_dev_configure(). 4951 * @param rx_pkts 4952 * The address of an array of pointers to *rte_mbuf* structures that 4953 * must be large enough to store *nb_pkts* pointers in it. 4954 * @param nb_pkts 4955 * The maximum number of packets to retrieve. 4956 * The value must be divisible by 8 in order to work with any driver. 4957 * @return 4958 * The number of packets actually retrieved, which is the number 4959 * of pointers to *rte_mbuf* structures effectively supplied to the 4960 * *rx_pkts* array. 4961 */ 4962 static inline uint16_t 4963 rte_eth_rx_burst(uint16_t port_id, uint16_t queue_id, 4964 struct rte_mbuf **rx_pkts, const uint16_t nb_pkts) 4965 { 4966 struct rte_eth_dev *dev = &rte_eth_devices[port_id]; 4967 uint16_t nb_rx; 4968 4969 #ifdef RTE_ETHDEV_DEBUG_RX 4970 RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, 0); 4971 RTE_FUNC_PTR_OR_ERR_RET(*dev->rx_pkt_burst, 0); 4972 4973 if (queue_id >= dev->data->nb_rx_queues) { 4974 RTE_ETHDEV_LOG(ERR, "Invalid RX queue_id=%u\n", queue_id); 4975 return 0; 4976 } 4977 #endif 4978 nb_rx = (*dev->rx_pkt_burst)(dev->data->rx_queues[queue_id], 4979 rx_pkts, nb_pkts); 4980 4981 #ifdef RTE_ETHDEV_RXTX_CALLBACKS 4982 struct rte_eth_rxtx_callback *cb; 4983 4984 /* __ATOMIC_RELEASE memory order was used when the 4985 * call back was inserted into the list. 4986 * Since there is a clear dependency between loading 4987 * cb and cb->fn/cb->next, __ATOMIC_ACQUIRE memory order is 4988 * not required. 4989 */ 4990 cb = __atomic_load_n(&dev->post_rx_burst_cbs[queue_id], 4991 __ATOMIC_RELAXED); 4992 4993 if (unlikely(cb != NULL)) { 4994 do { 4995 nb_rx = cb->fn.rx(port_id, queue_id, rx_pkts, nb_rx, 4996 nb_pkts, cb->param); 4997 cb = cb->next; 4998 } while (cb != NULL); 4999 } 5000 #endif 5001 5002 rte_ethdev_trace_rx_burst(port_id, queue_id, (void **)rx_pkts, nb_rx); 5003 return nb_rx; 5004 } 5005 5006 /** 5007 * Get the number of used descriptors of a rx queue 5008 * 5009 * @param port_id 5010 * The port identifier of the Ethernet device. 5011 * @param queue_id 5012 * The queue id on the specific port. 5013 * @return 5014 * The number of used descriptors in the specific queue, or: 5015 * - (-ENODEV) if *port_id* is invalid. 5016 * (-EINVAL) if *queue_id* is invalid 5017 * (-ENOTSUP) if the device does not support this function 5018 */ 5019 static inline int 5020 rte_eth_rx_queue_count(uint16_t port_id, uint16_t queue_id) 5021 { 5022 struct rte_eth_dev *dev; 5023 5024 RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); 5025 dev = &rte_eth_devices[port_id]; 5026 RTE_FUNC_PTR_OR_ERR_RET(*dev->rx_queue_count, -ENOTSUP); 5027 if (queue_id >= dev->data->nb_rx_queues || 5028 dev->data->rx_queues[queue_id] == NULL) 5029 return -EINVAL; 5030 5031 return (int)(*dev->rx_queue_count)(dev, queue_id); 5032 } 5033 5034 /** 5035 * Check if the DD bit of the specific RX descriptor in the queue has been set 5036 * 5037 * @param port_id 5038 * The port identifier of the Ethernet device. 5039 * @param queue_id 5040 * The queue id on the specific port. 5041 * @param offset 5042 * The offset of the descriptor ID from tail. 5043 * @return 5044 * - (1) if the specific DD bit is set. 5045 * - (0) if the specific DD bit is not set. 5046 * - (-ENODEV) if *port_id* invalid. 5047 * - (-ENOTSUP) if the device does not support this function 5048 */ 5049 __rte_deprecated 5050 static inline int 5051 rte_eth_rx_descriptor_done(uint16_t port_id, uint16_t queue_id, uint16_t offset) 5052 { 5053 struct rte_eth_dev *dev = &rte_eth_devices[port_id]; 5054 RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); 5055 RTE_FUNC_PTR_OR_ERR_RET(*dev->rx_descriptor_done, -ENOTSUP); 5056 return (*dev->rx_descriptor_done)(dev->data->rx_queues[queue_id], offset); 5057 } 5058 5059 #define RTE_ETH_RX_DESC_AVAIL 0 /**< Desc available for hw. */ 5060 #define RTE_ETH_RX_DESC_DONE 1 /**< Desc done, filled by hw. */ 5061 #define RTE_ETH_RX_DESC_UNAVAIL 2 /**< Desc used by driver or hw. */ 5062 5063 /** 5064 * Check the status of a Rx descriptor in the queue 5065 * 5066 * It should be called in a similar context than the Rx function: 5067 * - on a dataplane core 5068 * - not concurrently on the same queue 5069 * 5070 * Since it's a dataplane function, no check is performed on port_id and 5071 * queue_id. The caller must therefore ensure that the port is enabled 5072 * and the queue is configured and running. 5073 * 5074 * Note: accessing to a random descriptor in the ring may trigger cache 5075 * misses and have a performance impact. 5076 * 5077 * @param port_id 5078 * A valid port identifier of the Ethernet device which. 5079 * @param queue_id 5080 * A valid Rx queue identifier on this port. 5081 * @param offset 5082 * The offset of the descriptor starting from tail (0 is the next 5083 * packet to be received by the driver). 5084 * 5085 * @return 5086 * - (RTE_ETH_RX_DESC_AVAIL): Descriptor is available for the hardware to 5087 * receive a packet. 5088 * - (RTE_ETH_RX_DESC_DONE): Descriptor is done, it is filled by hw, but 5089 * not yet processed by the driver (i.e. in the receive queue). 5090 * - (RTE_ETH_RX_DESC_UNAVAIL): Descriptor is unavailable, either hold by 5091 * the driver and not yet returned to hw, or reserved by the hw. 5092 * - (-EINVAL) bad descriptor offset. 5093 * - (-ENOTSUP) if the device does not support this function. 5094 * - (-ENODEV) bad port or queue (only if compiled with debug). 5095 */ 5096 static inline int 5097 rte_eth_rx_descriptor_status(uint16_t port_id, uint16_t queue_id, 5098 uint16_t offset) 5099 { 5100 struct rte_eth_dev *dev; 5101 void *rxq; 5102 5103 #ifdef RTE_ETHDEV_DEBUG_RX 5104 RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); 5105 #endif 5106 dev = &rte_eth_devices[port_id]; 5107 #ifdef RTE_ETHDEV_DEBUG_RX 5108 if (queue_id >= dev->data->nb_rx_queues) 5109 return -ENODEV; 5110 #endif 5111 RTE_FUNC_PTR_OR_ERR_RET(*dev->rx_descriptor_status, -ENOTSUP); 5112 rxq = dev->data->rx_queues[queue_id]; 5113 5114 return (*dev->rx_descriptor_status)(rxq, offset); 5115 } 5116 5117 #define RTE_ETH_TX_DESC_FULL 0 /**< Desc filled for hw, waiting xmit. */ 5118 #define RTE_ETH_TX_DESC_DONE 1 /**< Desc done, packet is transmitted. */ 5119 #define RTE_ETH_TX_DESC_UNAVAIL 2 /**< Desc used by driver or hw. */ 5120 5121 /** 5122 * Check the status of a Tx descriptor in the queue. 5123 * 5124 * It should be called in a similar context than the Tx function: 5125 * - on a dataplane core 5126 * - not concurrently on the same queue 5127 * 5128 * Since it's a dataplane function, no check is performed on port_id and 5129 * queue_id. The caller must therefore ensure that the port is enabled 5130 * and the queue is configured and running. 5131 * 5132 * Note: accessing to a random descriptor in the ring may trigger cache 5133 * misses and have a performance impact. 5134 * 5135 * @param port_id 5136 * A valid port identifier of the Ethernet device which. 5137 * @param queue_id 5138 * A valid Tx queue identifier on this port. 5139 * @param offset 5140 * The offset of the descriptor starting from tail (0 is the place where 5141 * the next packet will be send). 5142 * 5143 * @return 5144 * - (RTE_ETH_TX_DESC_FULL) Descriptor is being processed by the hw, i.e. 5145 * in the transmit queue. 5146 * - (RTE_ETH_TX_DESC_DONE) Hardware is done with this descriptor, it can 5147 * be reused by the driver. 5148 * - (RTE_ETH_TX_DESC_UNAVAIL): Descriptor is unavailable, reserved by the 5149 * driver or the hardware. 5150 * - (-EINVAL) bad descriptor offset. 5151 * - (-ENOTSUP) if the device does not support this function. 5152 * - (-ENODEV) bad port or queue (only if compiled with debug). 5153 */ 5154 static inline int rte_eth_tx_descriptor_status(uint16_t port_id, 5155 uint16_t queue_id, uint16_t offset) 5156 { 5157 struct rte_eth_dev *dev; 5158 void *txq; 5159 5160 #ifdef RTE_ETHDEV_DEBUG_TX 5161 RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); 5162 #endif 5163 dev = &rte_eth_devices[port_id]; 5164 #ifdef RTE_ETHDEV_DEBUG_TX 5165 if (queue_id >= dev->data->nb_tx_queues) 5166 return -ENODEV; 5167 #endif 5168 RTE_FUNC_PTR_OR_ERR_RET(*dev->tx_descriptor_status, -ENOTSUP); 5169 txq = dev->data->tx_queues[queue_id]; 5170 5171 return (*dev->tx_descriptor_status)(txq, offset); 5172 } 5173 5174 /** 5175 * Send a burst of output packets on a transmit queue of an Ethernet device. 5176 * 5177 * The rte_eth_tx_burst() function is invoked to transmit output packets 5178 * on the output queue *queue_id* of the Ethernet device designated by its 5179 * *port_id*. 5180 * The *nb_pkts* parameter is the number of packets to send which are 5181 * supplied in the *tx_pkts* array of *rte_mbuf* structures, each of them 5182 * allocated from a pool created with rte_pktmbuf_pool_create(). 5183 * The rte_eth_tx_burst() function loops, sending *nb_pkts* packets, 5184 * up to the number of transmit descriptors available in the TX ring of the 5185 * transmit queue. 5186 * For each packet to send, the rte_eth_tx_burst() function performs 5187 * the following operations: 5188 * 5189 * - Pick up the next available descriptor in the transmit ring. 5190 * 5191 * - Free the network buffer previously sent with that descriptor, if any. 5192 * 5193 * - Initialize the transmit descriptor with the information provided 5194 * in the *rte_mbuf data structure. 5195 * 5196 * In the case of a segmented packet composed of a list of *rte_mbuf* buffers, 5197 * the rte_eth_tx_burst() function uses several transmit descriptors 5198 * of the ring. 5199 * 5200 * The rte_eth_tx_burst() function returns the number of packets it 5201 * actually sent. A return value equal to *nb_pkts* means that all packets 5202 * have been sent, and this is likely to signify that other output packets 5203 * could be immediately transmitted again. Applications that implement a 5204 * "send as many packets to transmit as possible" policy can check this 5205 * specific case and keep invoking the rte_eth_tx_burst() function until 5206 * a value less than *nb_pkts* is returned. 5207 * 5208 * It is the responsibility of the rte_eth_tx_burst() function to 5209 * transparently free the memory buffers of packets previously sent. 5210 * This feature is driven by the *tx_free_thresh* value supplied to the 5211 * rte_eth_dev_configure() function at device configuration time. 5212 * When the number of free TX descriptors drops below this threshold, the 5213 * rte_eth_tx_burst() function must [attempt to] free the *rte_mbuf* buffers 5214 * of those packets whose transmission was effectively completed. 5215 * 5216 * If the PMD is DEV_TX_OFFLOAD_MT_LOCKFREE capable, multiple threads can 5217 * invoke this function concurrently on the same tx queue without SW lock. 5218 * @see rte_eth_dev_info_get, struct rte_eth_txconf::offloads 5219 * 5220 * @see rte_eth_tx_prepare to perform some prior checks or adjustments 5221 * for offloads. 5222 * 5223 * @param port_id 5224 * The port identifier of the Ethernet device. 5225 * @param queue_id 5226 * The index of the transmit queue through which output packets must be 5227 * sent. 5228 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 5229 * to rte_eth_dev_configure(). 5230 * @param tx_pkts 5231 * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures 5232 * which contain the output packets. 5233 * @param nb_pkts 5234 * The maximum number of packets to transmit. 5235 * @return 5236 * The number of output packets actually stored in transmit descriptors of 5237 * the transmit ring. The return value can be less than the value of the 5238 * *tx_pkts* parameter when the transmit ring is full or has been filled up. 5239 */ 5240 static inline uint16_t 5241 rte_eth_tx_burst(uint16_t port_id, uint16_t queue_id, 5242 struct rte_mbuf **tx_pkts, uint16_t nb_pkts) 5243 { 5244 struct rte_eth_dev *dev = &rte_eth_devices[port_id]; 5245 5246 #ifdef RTE_ETHDEV_DEBUG_TX 5247 RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, 0); 5248 RTE_FUNC_PTR_OR_ERR_RET(*dev->tx_pkt_burst, 0); 5249 5250 if (queue_id >= dev->data->nb_tx_queues) { 5251 RTE_ETHDEV_LOG(ERR, "Invalid TX queue_id=%u\n", queue_id); 5252 return 0; 5253 } 5254 #endif 5255 5256 #ifdef RTE_ETHDEV_RXTX_CALLBACKS 5257 struct rte_eth_rxtx_callback *cb; 5258 5259 /* __ATOMIC_RELEASE memory order was used when the 5260 * call back was inserted into the list. 5261 * Since there is a clear dependency between loading 5262 * cb and cb->fn/cb->next, __ATOMIC_ACQUIRE memory order is 5263 * not required. 5264 */ 5265 cb = __atomic_load_n(&dev->pre_tx_burst_cbs[queue_id], 5266 __ATOMIC_RELAXED); 5267 5268 if (unlikely(cb != NULL)) { 5269 do { 5270 nb_pkts = cb->fn.tx(port_id, queue_id, tx_pkts, nb_pkts, 5271 cb->param); 5272 cb = cb->next; 5273 } while (cb != NULL); 5274 } 5275 #endif 5276 5277 rte_ethdev_trace_tx_burst(port_id, queue_id, (void **)tx_pkts, 5278 nb_pkts); 5279 return (*dev->tx_pkt_burst)(dev->data->tx_queues[queue_id], tx_pkts, nb_pkts); 5280 } 5281 5282 /** 5283 * Process a burst of output packets on a transmit queue of an Ethernet device. 5284 * 5285 * The rte_eth_tx_prepare() function is invoked to prepare output packets to be 5286 * transmitted on the output queue *queue_id* of the Ethernet device designated 5287 * by its *port_id*. 5288 * The *nb_pkts* parameter is the number of packets to be prepared which are 5289 * supplied in the *tx_pkts* array of *rte_mbuf* structures, each of them 5290 * allocated from a pool created with rte_pktmbuf_pool_create(). 5291 * For each packet to send, the rte_eth_tx_prepare() function performs 5292 * the following operations: 5293 * 5294 * - Check if packet meets devices requirements for tx offloads. 5295 * 5296 * - Check limitations about number of segments. 5297 * 5298 * - Check additional requirements when debug is enabled. 5299 * 5300 * - Update and/or reset required checksums when tx offload is set for packet. 5301 * 5302 * Since this function can modify packet data, provided mbufs must be safely 5303 * writable (e.g. modified data cannot be in shared segment). 5304 * 5305 * The rte_eth_tx_prepare() function returns the number of packets ready to be 5306 * sent. A return value equal to *nb_pkts* means that all packets are valid and 5307 * ready to be sent, otherwise stops processing on the first invalid packet and 5308 * leaves the rest packets untouched. 5309 * 5310 * When this functionality is not implemented in the driver, all packets are 5311 * are returned untouched. 5312 * 5313 * @param port_id 5314 * The port identifier of the Ethernet device. 5315 * The value must be a valid port id. 5316 * @param queue_id 5317 * The index of the transmit queue through which output packets must be 5318 * sent. 5319 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 5320 * to rte_eth_dev_configure(). 5321 * @param tx_pkts 5322 * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures 5323 * which contain the output packets. 5324 * @param nb_pkts 5325 * The maximum number of packets to process. 5326 * @return 5327 * The number of packets correct and ready to be sent. The return value can be 5328 * less than the value of the *tx_pkts* parameter when some packet doesn't 5329 * meet devices requirements with rte_errno set appropriately: 5330 * - EINVAL: offload flags are not correctly set 5331 * - ENOTSUP: the offload feature is not supported by the hardware 5332 * - ENODEV: if *port_id* is invalid (with debug enabled only) 5333 * 5334 */ 5335 5336 #ifndef RTE_ETHDEV_TX_PREPARE_NOOP 5337 5338 static inline uint16_t 5339 rte_eth_tx_prepare(uint16_t port_id, uint16_t queue_id, 5340 struct rte_mbuf **tx_pkts, uint16_t nb_pkts) 5341 { 5342 struct rte_eth_dev *dev; 5343 5344 #ifdef RTE_ETHDEV_DEBUG_TX 5345 if (!rte_eth_dev_is_valid_port(port_id)) { 5346 RTE_ETHDEV_LOG(ERR, "Invalid TX port_id=%u\n", port_id); 5347 rte_errno = ENODEV; 5348 return 0; 5349 } 5350 #endif 5351 5352 dev = &rte_eth_devices[port_id]; 5353 5354 #ifdef RTE_ETHDEV_DEBUG_TX 5355 if (queue_id >= dev->data->nb_tx_queues) { 5356 RTE_ETHDEV_LOG(ERR, "Invalid TX queue_id=%u\n", queue_id); 5357 rte_errno = EINVAL; 5358 return 0; 5359 } 5360 #endif 5361 5362 if (!dev->tx_pkt_prepare) 5363 return nb_pkts; 5364 5365 return (*dev->tx_pkt_prepare)(dev->data->tx_queues[queue_id], 5366 tx_pkts, nb_pkts); 5367 } 5368 5369 #else 5370 5371 /* 5372 * Native NOOP operation for compilation targets which doesn't require any 5373 * preparations steps, and functional NOOP may introduce unnecessary performance 5374 * drop. 5375 * 5376 * Generally this is not a good idea to turn it on globally and didn't should 5377 * be used if behavior of tx_preparation can change. 5378 */ 5379 5380 static inline uint16_t 5381 rte_eth_tx_prepare(__rte_unused uint16_t port_id, 5382 __rte_unused uint16_t queue_id, 5383 __rte_unused struct rte_mbuf **tx_pkts, uint16_t nb_pkts) 5384 { 5385 return nb_pkts; 5386 } 5387 5388 #endif 5389 5390 /** 5391 * Send any packets queued up for transmission on a port and HW queue 5392 * 5393 * This causes an explicit flush of packets previously buffered via the 5394 * rte_eth_tx_buffer() function. It returns the number of packets successfully 5395 * sent to the NIC, and calls the error callback for any unsent packets. Unless 5396 * explicitly set up otherwise, the default callback simply frees the unsent 5397 * packets back to the owning mempool. 5398 * 5399 * @param port_id 5400 * The port identifier of the Ethernet device. 5401 * @param queue_id 5402 * The index of the transmit queue through which output packets must be 5403 * sent. 5404 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 5405 * to rte_eth_dev_configure(). 5406 * @param buffer 5407 * Buffer of packets to be transmit. 5408 * @return 5409 * The number of packets successfully sent to the Ethernet device. The error 5410 * callback is called for any packets which could not be sent. 5411 */ 5412 static inline uint16_t 5413 rte_eth_tx_buffer_flush(uint16_t port_id, uint16_t queue_id, 5414 struct rte_eth_dev_tx_buffer *buffer) 5415 { 5416 uint16_t sent; 5417 uint16_t to_send = buffer->length; 5418 5419 if (to_send == 0) 5420 return 0; 5421 5422 sent = rte_eth_tx_burst(port_id, queue_id, buffer->pkts, to_send); 5423 5424 buffer->length = 0; 5425 5426 /* All packets sent, or to be dealt with by callback below */ 5427 if (unlikely(sent != to_send)) 5428 buffer->error_callback(&buffer->pkts[sent], 5429 (uint16_t)(to_send - sent), 5430 buffer->error_userdata); 5431 5432 return sent; 5433 } 5434 5435 /** 5436 * Buffer a single packet for future transmission on a port and queue 5437 * 5438 * This function takes a single mbuf/packet and buffers it for later 5439 * transmission on the particular port and queue specified. Once the buffer is 5440 * full of packets, an attempt will be made to transmit all the buffered 5441 * packets. In case of error, where not all packets can be transmitted, a 5442 * callback is called with the unsent packets as a parameter. If no callback 5443 * is explicitly set up, the unsent packets are just freed back to the owning 5444 * mempool. The function returns the number of packets actually sent i.e. 5445 * 0 if no buffer flush occurred, otherwise the number of packets successfully 5446 * flushed 5447 * 5448 * @param port_id 5449 * The port identifier of the Ethernet device. 5450 * @param queue_id 5451 * The index of the transmit queue through which output packets must be 5452 * sent. 5453 * The value must be in the range [0, nb_tx_queue - 1] previously supplied 5454 * to rte_eth_dev_configure(). 5455 * @param buffer 5456 * Buffer used to collect packets to be sent. 5457 * @param tx_pkt 5458 * Pointer to the packet mbuf to be sent. 5459 * @return 5460 * 0 = packet has been buffered for later transmission 5461 * N > 0 = packet has been buffered, and the buffer was subsequently flushed, 5462 * causing N packets to be sent, and the error callback to be called for 5463 * the rest. 5464 */ 5465 static __rte_always_inline uint16_t 5466 rte_eth_tx_buffer(uint16_t port_id, uint16_t queue_id, 5467 struct rte_eth_dev_tx_buffer *buffer, struct rte_mbuf *tx_pkt) 5468 { 5469 buffer->pkts[buffer->length++] = tx_pkt; 5470 if (buffer->length < buffer->size) 5471 return 0; 5472 5473 return rte_eth_tx_buffer_flush(port_id, queue_id, buffer); 5474 } 5475 5476 #ifdef __cplusplus 5477 } 5478 #endif 5479 5480 #endif /* _RTE_ETHDEV_H_ */ 5481