4 * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
11 * * Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * * Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in
15 * the documentation and/or other materials provided with the
17 * * Neither the name of Intel Corporation nor the names of its
18 * contributors may be used to endorse or promote products derived
19 * from this software without specific prior written permission.
21 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
27 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
31 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 #ifndef _RTE_ETHDEV_H_
35 #define _RTE_ETHDEV_H_
40 * RTE Ethernet Device API
42 * The Ethernet Device API is composed of two parts:
44 * - The application-oriented Ethernet API that includes functions to setup
45 * an Ethernet device (configure it, setup its RX and TX queues and start it),
46 * to get its MAC address, the speed and the status of its physical link,
47 * to receive and to transmit packets, and so on.
49 * - The driver-oriented Ethernet API that exports a function allowing
50 * an Ethernet Poll Mode Driver (PMD) to simultaneously register itself as
51 * an Ethernet device driver and as a PCI driver for a set of matching PCI
52 * [Ethernet] devices classes.
54 * By default, all the functions of the Ethernet Device API exported by a PMD
55 * are lock-free functions which assume to not be invoked in parallel on
56 * different logical cores to work on the same target object. For instance,
57 * the receive function of a PMD cannot be invoked in parallel on two logical
58 * cores to poll the same RX queue [of the same port]. Of course, this function
59 * can be invoked in parallel by different logical cores on different RX queues.
60 * It is the responsibility of the upper level application to enforce this rule.
62 * If needed, parallel accesses by multiple logical cores to shared queues
63 * shall be explicitly protected by dedicated inline lock-aware functions
64 * built on top of their corresponding lock-free functions of the PMD API.
66 * In all functions of the Ethernet API, the Ethernet device is
67 * designated by an integer >= 0 named the device port identifier.
69 * At the Ethernet driver level, Ethernet devices are represented by a generic
70 * data structure of type *rte_eth_dev*.
72 * Ethernet devices are dynamically registered during the PCI probing phase
73 * performed at EAL initialization time.
74 * When an Ethernet device is being probed, an *rte_eth_dev* structure and
75 * a new port identifier are allocated for that device. Then, the eth_dev_init()
76 * function supplied by the Ethernet driver matching the probed PCI
77 * device is invoked to properly initialize the device.
79 * The role of the device init function consists of resetting the hardware,
80 * checking access to Non-volatile Memory (NVM), reading the MAC address
83 * If the device init operation is successful, the correspondence between
84 * the port identifier assigned to the new device and its associated
85 * *rte_eth_dev* structure is effectively registered.
86 * Otherwise, both the *rte_eth_dev* structure and the port identifier are
89 * The functions exported by the application Ethernet API to setup a device
90 * designated by its port identifier must be invoked in the following order:
91 * - rte_eth_dev_configure()
92 * - rte_eth_tx_queue_setup()
93 * - rte_eth_rx_queue_setup()
94 * - rte_eth_dev_start()
96 * Then, the network application can invoke, in any order, the functions
97 * exported by the Ethernet API to get the MAC address of a given device, to
98 * get the speed and the status of a device physical link, to receive/transmit
99 * [burst of] packets, and so on.
101 * If the application wants to change the configuration (i.e. call
102 * rte_eth_dev_configure(), rte_eth_tx_queue_setup(), or
103 * rte_eth_rx_queue_setup()), it must call rte_eth_dev_stop() first to stop the
104 * device and then do the reconfiguration before calling rte_eth_dev_start()
105 * again. The tramsit and receive functions should not be invoked when the
108 * Please note that some configuration is not stored between calls to
109 * rte_eth_dev_stop()/rte_eth_dev_start(). The following configuration will
112 * - flow control settings
113 * - receive mode configuration (promiscuous mode, hardware checksum mode,
114 * RSS/VMDQ settings etc.)
115 * - VLAN filtering configuration
116 * - MAC addresses supplied to MAC address array
117 * - flow director filtering mode (but not filtering rules)
118 * - NIC queue statistics mappings
120 * Any other configuration will not be stored and will need to be re-entered
121 * after a call to rte_eth_dev_start().
123 * Finally, a network application can close an Ethernet device by invoking the
124 * rte_eth_dev_close() function.
126 * Each function of the application Ethernet API invokes a specific function
127 * of the PMD that controls the target device designated by its port
129 * For this purpose, all device-specific functions of an Ethernet driver are
130 * supplied through a set of pointers contained in a generic structure of type
132 * The address of the *eth_dev_ops* structure is stored in the *rte_eth_dev*
133 * structure by the device init function of the Ethernet driver, which is
134 * invoked during the PCI probing phase, as explained earlier.
136 * In other words, each function of the Ethernet API simply retrieves the
137 * *rte_eth_dev* structure associated with the device port identifier and
138 * performs an indirect invocation of the corresponding driver function
139 * supplied in the *eth_dev_ops* structure of the *rte_eth_dev* structure.
141 * For performance reasons, the address of the burst-oriented RX and TX
142 * functions of the Ethernet driver are not contained in the *eth_dev_ops*
143 * structure. Instead, they are directly stored at the beginning of the
144 * *rte_eth_dev* structure to avoid an extra indirect memory access during
147 * RTE ethernet device drivers do not use interrupts for transmitting or
148 * receiving. Instead, Ethernet drivers export Poll-Mode receive and transmit
149 * functions to applications.
150 * Both receive and transmit functions are packet-burst oriented to minimize
151 * their cost per packet through the following optimizations:
153 * - Sharing among multiple packets the incompressible cost of the
154 * invocation of receive/transmit functions.
156 * - Enabling receive/transmit functions to take advantage of burst-oriented
157 * hardware features (L1 cache, prefetch instructions, NIC head/tail
158 * registers) to minimize the number of CPU cycles per packet, for instance,
159 * by avoiding useless read memory accesses to ring descriptors, or by
160 * systematically using arrays of pointers that exactly fit L1 cache line
161 * boundaries and sizes.
163 * The burst-oriented receive function does not provide any error notification,
164 * to avoid the corresponding overhead. As a hint, the upper-level application
165 * might check the status of the device link once being systematically returned
166 * a 0 value by the receive function of the driver for a given number of tries.
175 /* Use this macro to check if LRO API is supported */
176 #define RTE_ETHDEV_HAS_LRO_SUPPORT
179 #include <rte_interrupts.h>
182 #include <rte_devargs.h>
183 #include "rte_ether.h"
184 #include "rte_eth_ctrl.h"
189 * A structure used to retrieve statistics for an Ethernet port.
191 struct rte_eth_stats {
192 uint64_t ipackets; /**< Total number of successfully received packets. */
193 uint64_t opackets; /**< Total number of successfully transmitted packets.*/
194 uint64_t ibytes; /**< Total number of successfully received bytes. */
195 uint64_t obytes; /**< Total number of successfully transmitted bytes. */
196 uint64_t imissed; /**< Total of RX missed packets (e.g full FIFO). */
197 uint64_t ibadcrc; /**< Total of RX packets with CRC error. */
198 uint64_t ibadlen; /**< Total of RX packets with bad length. */
199 uint64_t ierrors; /**< Total number of erroneous received packets. */
200 uint64_t oerrors; /**< Total number of failed transmitted packets. */
201 uint64_t imcasts; /**< Total number of multicast received packets. */
202 uint64_t rx_nombuf; /**< Total number of RX mbuf allocation failures. */
203 uint64_t fdirmatch; /**< Total number of RX packets matching a filter. */
204 uint64_t fdirmiss; /**< Total number of RX packets not matching any filter. */
205 uint64_t tx_pause_xon; /**< Total nb. of XON pause frame sent. */
206 uint64_t rx_pause_xon; /**< Total nb. of XON pause frame received. */
207 uint64_t tx_pause_xoff; /**< Total nb. of XOFF pause frame sent. */
208 uint64_t rx_pause_xoff; /**< Total nb. of XOFF pause frame received. */
209 uint64_t q_ipackets[RTE_ETHDEV_QUEUE_STAT_CNTRS];
210 /**< Total number of queue RX packets. */
211 uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS];
212 /**< Total number of queue TX packets. */
213 uint64_t q_ibytes[RTE_ETHDEV_QUEUE_STAT_CNTRS];
214 /**< Total number of successfully received queue bytes. */
215 uint64_t q_obytes[RTE_ETHDEV_QUEUE_STAT_CNTRS];
216 /**< Total number of successfully transmitted queue bytes. */
217 uint64_t q_errors[RTE_ETHDEV_QUEUE_STAT_CNTRS];
218 /**< Total number of queue packets received that are dropped. */
220 /**< Total number of good packets received from loopback,VF Only */
222 /**< Total number of good packets transmitted to loopback,VF Only */
224 /**< Total number of good bytes received from loopback,VF Only */
226 /**< Total number of good bytes transmitted to loopback,VF Only */
230 * A structure used to retrieve link-level information of an Ethernet port.
232 struct rte_eth_link {
233 uint16_t link_speed; /**< ETH_LINK_SPEED_[10, 100, 1000, 10000] */
234 uint16_t link_duplex; /**< ETH_LINK_[HALF_DUPLEX, FULL_DUPLEX] */
235 uint8_t link_status : 1; /**< 1 -> link up, 0 -> link down */
236 }__attribute__((aligned(8))); /**< aligned for atomic64 read/write */
238 #define ETH_LINK_SPEED_AUTONEG 0 /**< Auto-negotiate link speed. */
239 #define ETH_LINK_SPEED_10 10 /**< 10 megabits/second. */
240 #define ETH_LINK_SPEED_100 100 /**< 100 megabits/second. */
241 #define ETH_LINK_SPEED_1000 1000 /**< 1 gigabits/second. */
242 #define ETH_LINK_SPEED_10000 10000 /**< 10 gigabits/second. */
243 #define ETH_LINK_SPEED_10G 10000 /**< alias of 10 gigabits/second. */
244 #define ETH_LINK_SPEED_20G 20000 /**< 20 gigabits/second. */
245 #define ETH_LINK_SPEED_40G 40000 /**< 40 gigabits/second. */
247 #define ETH_LINK_AUTONEG_DUPLEX 0 /**< Auto-negotiate duplex. */
248 #define ETH_LINK_HALF_DUPLEX 1 /**< Half-duplex connection. */
249 #define ETH_LINK_FULL_DUPLEX 2 /**< Full-duplex connection. */
252 * A structure used to configure the ring threshold registers of an RX/TX
253 * queue for an Ethernet port.
255 struct rte_eth_thresh {
256 uint8_t pthresh; /**< Ring prefetch threshold. */
257 uint8_t hthresh; /**< Ring host threshold. */
258 uint8_t wthresh; /**< Ring writeback threshold. */
262 * Simple flags are used for rte_eth_conf.rxmode.mq_mode.
264 #define ETH_MQ_RX_RSS_FLAG 0x1
265 #define ETH_MQ_RX_DCB_FLAG 0x2
266 #define ETH_MQ_RX_VMDQ_FLAG 0x4
269 * A set of values to identify what method is to be used to route
270 * packets to multiple queues.
272 enum rte_eth_rx_mq_mode {
273 /** None of DCB,RSS or VMDQ mode */
276 /** For RX side, only RSS is on */
277 ETH_MQ_RX_RSS = ETH_MQ_RX_RSS_FLAG,
278 /** For RX side,only DCB is on. */
279 ETH_MQ_RX_DCB = ETH_MQ_RX_DCB_FLAG,
280 /** Both DCB and RSS enable */
281 ETH_MQ_RX_DCB_RSS = ETH_MQ_RX_RSS_FLAG | ETH_MQ_RX_DCB_FLAG,
283 /** Only VMDQ, no RSS nor DCB */
284 ETH_MQ_RX_VMDQ_ONLY = ETH_MQ_RX_VMDQ_FLAG,
285 /** RSS mode with VMDQ */
286 ETH_MQ_RX_VMDQ_RSS = ETH_MQ_RX_RSS_FLAG | ETH_MQ_RX_VMDQ_FLAG,
287 /** Use VMDQ+DCB to route traffic to queues */
288 ETH_MQ_RX_VMDQ_DCB = ETH_MQ_RX_VMDQ_FLAG | ETH_MQ_RX_DCB_FLAG,
289 /** Enable both VMDQ and DCB in VMDq */
290 ETH_MQ_RX_VMDQ_DCB_RSS = ETH_MQ_RX_RSS_FLAG | ETH_MQ_RX_DCB_FLAG |
295 * for rx mq mode backward compatible
297 #define ETH_RSS ETH_MQ_RX_RSS
298 #define VMDQ_DCB ETH_MQ_RX_VMDQ_DCB
299 #define ETH_DCB_RX ETH_MQ_RX_DCB
302 * A set of values to identify what method is to be used to transmit
303 * packets using multi-TCs.
305 enum rte_eth_tx_mq_mode {
306 ETH_MQ_TX_NONE = 0, /**< It is in neither DCB nor VT mode. */
307 ETH_MQ_TX_DCB, /**< For TX side,only DCB is on. */
308 ETH_MQ_TX_VMDQ_DCB, /**< For TX side,both DCB and VT is on. */
309 ETH_MQ_TX_VMDQ_ONLY, /**< Only VT on, no DCB */
313 * for tx mq mode backward compatible
315 #define ETH_DCB_NONE ETH_MQ_TX_NONE
316 #define ETH_VMDQ_DCB_TX ETH_MQ_TX_VMDQ_DCB
317 #define ETH_DCB_TX ETH_MQ_TX_DCB
320 * A structure used to configure the RX features of an Ethernet port.
322 struct rte_eth_rxmode {
323 /** The multi-queue packet distribution mode to be used, e.g. RSS. */
324 enum rte_eth_rx_mq_mode mq_mode;
325 uint32_t max_rx_pkt_len; /**< Only used if jumbo_frame enabled. */
326 uint16_t split_hdr_size; /**< hdr buf size (header_split enabled).*/
327 uint16_t header_split : 1, /**< Header Split enable. */
328 hw_ip_checksum : 1, /**< IP/UDP/TCP checksum offload enable. */
329 hw_vlan_filter : 1, /**< VLAN filter enable. */
330 hw_vlan_strip : 1, /**< VLAN strip enable. */
331 hw_vlan_extend : 1, /**< Extended VLAN enable. */
332 jumbo_frame : 1, /**< Jumbo Frame Receipt enable. */
333 hw_strip_crc : 1, /**< Enable CRC stripping by hardware. */
334 enable_scatter : 1, /**< Enable scatter packets rx handler */
335 enable_lro : 1; /**< Enable LRO */
339 * A structure used to configure the Receive Side Scaling (RSS) feature
340 * of an Ethernet port.
341 * If not NULL, the *rss_key* pointer of the *rss_conf* structure points
342 * to an array holding the RSS key to use for hashing specific header
343 * fields of received packets. The length of this array should be indicated
344 * by *rss_key_len* below. Otherwise, a default random hash key is used by
347 * The *rss_key_len* field of the *rss_conf* structure indicates the length
348 * in bytes of the array pointed by *rss_key*. To be compatible, this length
349 * will be checked in i40e only. Others assume 40 bytes to be used as before.
351 * The *rss_hf* field of the *rss_conf* structure indicates the different
352 * types of IPv4/IPv6 packets to which the RSS hashing must be applied.
353 * Supplying an *rss_hf* equal to zero disables the RSS feature.
355 struct rte_eth_rss_conf {
356 uint8_t *rss_key; /**< If not NULL, 40-byte hash key. */
357 uint8_t rss_key_len; /**< hash key length in bytes. */
358 uint64_t rss_hf; /**< Hash functions to apply - see below. */
362 * The RSS offload types are defined based on flow types which are defined
363 * in rte_eth_ctrl.h. Different NIC hardwares may support different RSS offload
364 * types. The supported flow types or RSS offload types can be queried by
365 * rte_eth_dev_info_get().
367 #define ETH_RSS_IPV4 (1ULL << RTE_ETH_FLOW_IPV4)
368 #define ETH_RSS_FRAG_IPV4 (1ULL << RTE_ETH_FLOW_FRAG_IPV4)
369 #define ETH_RSS_NONFRAG_IPV4_TCP (1ULL << RTE_ETH_FLOW_NONFRAG_IPV4_TCP)
370 #define ETH_RSS_NONFRAG_IPV4_UDP (1ULL << RTE_ETH_FLOW_NONFRAG_IPV4_UDP)
371 #define ETH_RSS_NONFRAG_IPV4_SCTP (1ULL << RTE_ETH_FLOW_NONFRAG_IPV4_SCTP)
372 #define ETH_RSS_NONFRAG_IPV4_OTHER (1ULL << RTE_ETH_FLOW_NONFRAG_IPV4_OTHER)
373 #define ETH_RSS_IPV6 (1ULL << RTE_ETH_FLOW_IPV6)
374 #define ETH_RSS_FRAG_IPV6 (1ULL << RTE_ETH_FLOW_FRAG_IPV6)
375 #define ETH_RSS_NONFRAG_IPV6_TCP (1ULL << RTE_ETH_FLOW_NONFRAG_IPV6_TCP)
376 #define ETH_RSS_NONFRAG_IPV6_UDP (1ULL << RTE_ETH_FLOW_NONFRAG_IPV6_UDP)
377 #define ETH_RSS_NONFRAG_IPV6_SCTP (1ULL << RTE_ETH_FLOW_NONFRAG_IPV6_SCTP)
378 #define ETH_RSS_NONFRAG_IPV6_OTHER (1ULL << RTE_ETH_FLOW_NONFRAG_IPV6_OTHER)
379 #define ETH_RSS_L2_PAYLOAD (1ULL << RTE_ETH_FLOW_L2_PAYLOAD)
380 #define ETH_RSS_IPV6_EX (1ULL << RTE_ETH_FLOW_IPV6_EX)
381 #define ETH_RSS_IPV6_TCP_EX (1ULL << RTE_ETH_FLOW_IPV6_TCP_EX)
382 #define ETH_RSS_IPV6_UDP_EX (1ULL << RTE_ETH_FLOW_IPV6_UDP_EX)
384 #define ETH_RSS_IP ( \
386 ETH_RSS_FRAG_IPV4 | \
387 ETH_RSS_NONFRAG_IPV4_OTHER | \
389 ETH_RSS_FRAG_IPV6 | \
390 ETH_RSS_NONFRAG_IPV6_OTHER | \
393 #define ETH_RSS_UDP ( \
394 ETH_RSS_NONFRAG_IPV4_UDP | \
395 ETH_RSS_NONFRAG_IPV6_UDP | \
398 #define ETH_RSS_TCP ( \
399 ETH_RSS_NONFRAG_IPV4_TCP | \
400 ETH_RSS_NONFRAG_IPV6_TCP | \
403 #define ETH_RSS_SCTP ( \
404 ETH_RSS_NONFRAG_IPV4_SCTP | \
405 ETH_RSS_NONFRAG_IPV6_SCTP)
407 /**< Mask of valid RSS hash protocols */
408 #define ETH_RSS_PROTO_MASK ( \
410 ETH_RSS_FRAG_IPV4 | \
411 ETH_RSS_NONFRAG_IPV4_TCP | \
412 ETH_RSS_NONFRAG_IPV4_UDP | \
413 ETH_RSS_NONFRAG_IPV4_SCTP | \
414 ETH_RSS_NONFRAG_IPV4_OTHER | \
416 ETH_RSS_FRAG_IPV6 | \
417 ETH_RSS_NONFRAG_IPV6_TCP | \
418 ETH_RSS_NONFRAG_IPV6_UDP | \
419 ETH_RSS_NONFRAG_IPV6_SCTP | \
420 ETH_RSS_NONFRAG_IPV6_OTHER | \
421 ETH_RSS_L2_PAYLOAD | \
423 ETH_RSS_IPV6_TCP_EX | \
427 * Definitions used for redirection table entry size.
428 * Some RSS RETA sizes may not be supported by some drivers, check the
429 * documentation or the description of relevant functions for more details.
431 #define ETH_RSS_RETA_SIZE_64 64
432 #define ETH_RSS_RETA_SIZE_128 128
433 #define ETH_RSS_RETA_SIZE_512 512
434 #define RTE_RETA_GROUP_SIZE 64
436 /* Definitions used for VMDQ and DCB functionality */
437 #define ETH_VMDQ_MAX_VLAN_FILTERS 64 /**< Maximum nb. of VMDQ vlan filters. */
438 #define ETH_DCB_NUM_USER_PRIORITIES 8 /**< Maximum nb. of DCB priorities. */
439 #define ETH_VMDQ_DCB_NUM_QUEUES 128 /**< Maximum nb. of VMDQ DCB queues. */
440 #define ETH_DCB_NUM_QUEUES 128 /**< Maximum nb. of DCB queues. */
442 /* DCB capability defines */
443 #define ETH_DCB_PG_SUPPORT 0x00000001 /**< Priority Group(ETS) support. */
444 #define ETH_DCB_PFC_SUPPORT 0x00000002 /**< Priority Flow Control support. */
446 /* Definitions used for VLAN Offload functionality */
447 #define ETH_VLAN_STRIP_OFFLOAD 0x0001 /**< VLAN Strip On/Off */
448 #define ETH_VLAN_FILTER_OFFLOAD 0x0002 /**< VLAN Filter On/Off */
449 #define ETH_VLAN_EXTEND_OFFLOAD 0x0004 /**< VLAN Extend On/Off */
451 /* Definitions used for mask VLAN setting */
452 #define ETH_VLAN_STRIP_MASK 0x0001 /**< VLAN Strip setting mask */
453 #define ETH_VLAN_FILTER_MASK 0x0002 /**< VLAN Filter setting mask*/
454 #define ETH_VLAN_EXTEND_MASK 0x0004 /**< VLAN Extend setting mask*/
455 #define ETH_VLAN_ID_MAX 0x0FFF /**< VLAN ID is in lower 12 bits*/
457 /* Definitions used for receive MAC address */
458 #define ETH_NUM_RECEIVE_MAC_ADDR 128 /**< Maximum nb. of receive mac addr. */
460 /* Definitions used for unicast hash */
461 #define ETH_VMDQ_NUM_UC_HASH_ARRAY 128 /**< Maximum nb. of UC hash array. */
463 /* Definitions used for VMDQ pool rx mode setting */
464 #define ETH_VMDQ_ACCEPT_UNTAG 0x0001 /**< accept untagged packets. */
465 #define ETH_VMDQ_ACCEPT_HASH_MC 0x0002 /**< accept packets in multicast table . */
466 #define ETH_VMDQ_ACCEPT_HASH_UC 0x0004 /**< accept packets in unicast table. */
467 #define ETH_VMDQ_ACCEPT_BROADCAST 0x0008 /**< accept broadcast packets. */
468 #define ETH_VMDQ_ACCEPT_MULTICAST 0x0010 /**< multicast promiscuous. */
470 /* Definitions used for VMDQ mirror rules setting */
471 #define ETH_VMDQ_NUM_MIRROR_RULE 4 /**< Maximum nb. of mirror rules. . */
473 #define ETH_VMDQ_POOL_MIRROR 0x0001 /**< Virtual Pool Mirroring. */
474 #define ETH_VMDQ_UPLINK_MIRROR 0x0002 /**< Uplink Port Mirroring. */
475 #define ETH_VMDQ_DOWNLIN_MIRROR 0x0004 /**< Downlink Port Mirroring. */
476 #define ETH_VMDQ_VLAN_MIRROR 0x0008 /**< VLAN Mirroring. */
479 * A structure used to configure VLAN traffic mirror of an Ethernet port.
481 struct rte_eth_vlan_mirror {
482 uint64_t vlan_mask; /**< mask for valid VLAN ID. */
483 uint16_t vlan_id[ETH_VMDQ_MAX_VLAN_FILTERS];
484 /** VLAN ID list for vlan mirror. */
488 * A structure used to configure traffic mirror of an Ethernet port.
490 struct rte_eth_vmdq_mirror_conf {
491 uint8_t rule_type_mask; /**< Mirroring rule type mask we want to set */
492 uint8_t dst_pool; /**< Destination pool for this mirror rule. */
493 uint64_t pool_mask; /**< Bitmap of pool for pool mirroring */
494 struct rte_eth_vlan_mirror vlan; /**< VLAN ID setting for VLAN mirroring */
498 * A structure used to configure 64 entries of Redirection Table of the
499 * Receive Side Scaling (RSS) feature of an Ethernet port. To configure
500 * more than 64 entries supported by hardware, an array of this structure
503 struct rte_eth_rss_reta_entry64 {
505 /**< Mask bits indicate which entries need to be updated/queried. */
506 uint8_t reta[RTE_RETA_GROUP_SIZE];
507 /**< Group of 64 redirection table entries. */
511 * This enum indicates the possible number of traffic classes
512 * in DCB configratioins
514 enum rte_eth_nb_tcs {
515 ETH_4_TCS = 4, /**< 4 TCs with DCB. */
516 ETH_8_TCS = 8 /**< 8 TCs with DCB. */
520 * This enum indicates the possible number of queue pools
521 * in VMDQ configurations.
523 enum rte_eth_nb_pools {
524 ETH_8_POOLS = 8, /**< 8 VMDq pools. */
525 ETH_16_POOLS = 16, /**< 16 VMDq pools. */
526 ETH_32_POOLS = 32, /**< 32 VMDq pools. */
527 ETH_64_POOLS = 64 /**< 64 VMDq pools. */
530 /* This structure may be extended in future. */
531 struct rte_eth_dcb_rx_conf {
532 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs */
533 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
534 /**< Possible DCB queue,4 or 8. */
537 struct rte_eth_vmdq_dcb_tx_conf {
538 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools. */
539 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
540 /**< Possible DCB queue,4 or 8. */
543 struct rte_eth_dcb_tx_conf {
544 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs. */
545 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
546 /**< Possible DCB queue,4 or 8. */
549 struct rte_eth_vmdq_tx_conf {
550 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq mode, 64 pools. */
554 * A structure used to configure the VMDQ+DCB feature
555 * of an Ethernet port.
557 * Using this feature, packets are routed to a pool of queues, based
558 * on the vlan id in the vlan tag, and then to a specific queue within
559 * that pool, using the user priority vlan tag field.
561 * A default pool may be used, if desired, to route all traffic which
562 * does not match the vlan filter rules.
564 struct rte_eth_vmdq_dcb_conf {
565 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools */
566 uint8_t enable_default_pool; /**< If non-zero, use a default pool */
567 uint8_t default_pool; /**< The default pool, if applicable */
568 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */
570 uint16_t vlan_id; /**< The vlan id of the received frame */
571 uint64_t pools; /**< Bitmask of pools for packet rx */
572 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */
573 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
574 /**< Selects a queue in a pool */
577 struct rte_eth_vmdq_rx_conf {
578 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq only mode, 8 or 64 pools */
579 uint8_t enable_default_pool; /**< If non-zero, use a default pool */
580 uint8_t default_pool; /**< The default pool, if applicable */
581 uint8_t enable_loop_back; /**< Enable VT loop back */
582 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */
583 uint32_t rx_mode; /**< Flags from ETH_VMDQ_ACCEPT_* */
585 uint16_t vlan_id; /**< The vlan id of the received frame */
586 uint64_t pools; /**< Bitmask of pools for packet rx */
587 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */
591 * A structure used to configure the TX features of an Ethernet port.
593 struct rte_eth_txmode {
594 enum rte_eth_tx_mq_mode mq_mode; /**< TX multi-queues mode. */
596 /* For i40e specifically */
598 uint8_t hw_vlan_reject_tagged : 1,
599 /**< If set, reject sending out tagged pkts */
600 hw_vlan_reject_untagged : 1,
601 /**< If set, reject sending out untagged pkts */
602 hw_vlan_insert_pvid : 1;
603 /**< If set, enable port based VLAN insertion */
607 * A structure used to configure an RX ring of an Ethernet port.
609 struct rte_eth_rxconf {
610 struct rte_eth_thresh rx_thresh; /**< RX ring threshold registers. */
611 uint16_t rx_free_thresh; /**< Drives the freeing of RX descriptors. */
612 uint8_t rx_drop_en; /**< Drop packets if no descriptors are available. */
613 uint8_t rx_deferred_start; /**< Do not start queue with rte_eth_dev_start(). */
616 #define ETH_TXQ_FLAGS_NOMULTSEGS 0x0001 /**< nb_segs=1 for all mbufs */
617 #define ETH_TXQ_FLAGS_NOREFCOUNT 0x0002 /**< refcnt can be ignored */
618 #define ETH_TXQ_FLAGS_NOMULTMEMP 0x0004 /**< all bufs come from same mempool */
619 #define ETH_TXQ_FLAGS_NOVLANOFFL 0x0100 /**< disable VLAN offload */
620 #define ETH_TXQ_FLAGS_NOXSUMSCTP 0x0200 /**< disable SCTP checksum offload */
621 #define ETH_TXQ_FLAGS_NOXSUMUDP 0x0400 /**< disable UDP checksum offload */
622 #define ETH_TXQ_FLAGS_NOXSUMTCP 0x0800 /**< disable TCP checksum offload */
623 #define ETH_TXQ_FLAGS_NOOFFLOADS \
624 (ETH_TXQ_FLAGS_NOVLANOFFL | ETH_TXQ_FLAGS_NOXSUMSCTP | \
625 ETH_TXQ_FLAGS_NOXSUMUDP | ETH_TXQ_FLAGS_NOXSUMTCP)
626 #define ETH_TXQ_FLAGS_NOXSUMS \
627 (ETH_TXQ_FLAGS_NOXSUMSCTP | ETH_TXQ_FLAGS_NOXSUMUDP | \
628 ETH_TXQ_FLAGS_NOXSUMTCP)
630 * A structure used to configure a TX ring of an Ethernet port.
632 struct rte_eth_txconf {
633 struct rte_eth_thresh tx_thresh; /**< TX ring threshold registers. */
634 uint16_t tx_rs_thresh; /**< Drives the setting of RS bit on TXDs. */
635 uint16_t tx_free_thresh; /**< Drives the freeing of TX buffers. */
636 uint32_t txq_flags; /**< Set flags for the Tx queue */
637 uint8_t tx_deferred_start; /**< Do not start queue with rte_eth_dev_start(). */
641 * This enum indicates the flow control mode
643 enum rte_eth_fc_mode {
644 RTE_FC_NONE = 0, /**< Disable flow control. */
645 RTE_FC_RX_PAUSE, /**< RX pause frame, enable flowctrl on TX side. */
646 RTE_FC_TX_PAUSE, /**< TX pause frame, enable flowctrl on RX side. */
647 RTE_FC_FULL /**< Enable flow control on both side. */
651 * A structure used to configure Ethernet flow control parameter.
652 * These parameters will be configured into the register of the NIC.
653 * Please refer to the corresponding data sheet for proper value.
655 struct rte_eth_fc_conf {
656 uint32_t high_water; /**< High threshold value to trigger XOFF */
657 uint32_t low_water; /**< Low threshold value to trigger XON */
658 uint16_t pause_time; /**< Pause quota in the Pause frame */
659 uint16_t send_xon; /**< Is XON frame need be sent */
660 enum rte_eth_fc_mode mode; /**< Link flow control mode */
661 uint8_t mac_ctrl_frame_fwd; /**< Forward MAC control frames */
662 uint8_t autoneg; /**< Use Pause autoneg */
666 * A structure used to configure Ethernet priority flow control parameter.
667 * These parameters will be configured into the register of the NIC.
668 * Please refer to the corresponding data sheet for proper value.
670 struct rte_eth_pfc_conf {
671 struct rte_eth_fc_conf fc; /**< General flow control parameter. */
672 uint8_t priority; /**< VLAN User Priority. */
676 * Memory space that can be configured to store Flow Director filters
677 * in the board memory.
679 enum rte_fdir_pballoc_type {
680 RTE_FDIR_PBALLOC_64K = 0, /**< 64k. */
681 RTE_FDIR_PBALLOC_128K, /**< 128k. */
682 RTE_FDIR_PBALLOC_256K, /**< 256k. */
686 * Select report mode of FDIR hash information in RX descriptors.
688 enum rte_fdir_status_mode {
689 RTE_FDIR_NO_REPORT_STATUS = 0, /**< Never report FDIR hash. */
690 RTE_FDIR_REPORT_STATUS, /**< Only report FDIR hash for matching pkts. */
691 RTE_FDIR_REPORT_STATUS_ALWAYS, /**< Always report FDIR hash. */
695 * A structure used to configure the Flow Director (FDIR) feature
696 * of an Ethernet port.
698 * If mode is RTE_FDIR_DISABLE, the pballoc value is ignored.
700 struct rte_fdir_conf {
701 enum rte_fdir_mode mode; /**< Flow Director mode. */
702 enum rte_fdir_pballoc_type pballoc; /**< Space for FDIR filters. */
703 enum rte_fdir_status_mode status; /**< How to report FDIR hash. */
704 /** RX queue of packets matching a "drop" filter in perfect mode. */
706 struct rte_eth_fdir_masks mask;
707 struct rte_eth_fdir_flex_conf flex_conf;
708 /**< Flex payload configuration. */
712 * UDP tunneling configuration.
714 struct rte_eth_udp_tunnel {
720 * Possible l4type of FDIR filters.
723 RTE_FDIR_L4TYPE_NONE = 0, /**< None. */
724 RTE_FDIR_L4TYPE_UDP, /**< UDP. */
725 RTE_FDIR_L4TYPE_TCP, /**< TCP. */
726 RTE_FDIR_L4TYPE_SCTP, /**< SCTP. */
730 * Select IPv4 or IPv6 FDIR filters.
733 RTE_FDIR_IPTYPE_IPV4 = 0, /**< IPv4. */
734 RTE_FDIR_IPTYPE_IPV6 , /**< IPv6. */
738 * A structure used to define a FDIR packet filter.
740 struct rte_fdir_filter {
741 uint16_t flex_bytes; /**< Flex bytes value to match. */
742 uint16_t vlan_id; /**< VLAN ID value to match, 0 otherwise. */
743 uint16_t port_src; /**< Source port to match, 0 otherwise. */
744 uint16_t port_dst; /**< Destination port to match, 0 otherwise. */
746 uint32_t ipv4_addr; /**< IPv4 source address to match. */
747 uint32_t ipv6_addr[4]; /**< IPv6 source address to match. */
748 } ip_src; /**< IPv4/IPv6 source address to match (union of above). */
750 uint32_t ipv4_addr; /**< IPv4 destination address to match. */
751 uint32_t ipv6_addr[4]; /**< IPv6 destination address to match */
752 } ip_dst; /**< IPv4/IPv6 destination address to match (union of above). */
753 enum rte_l4type l4type; /**< l4type to match: NONE/UDP/TCP/SCTP. */
754 enum rte_iptype iptype; /**< IP packet type to match: IPv4 or IPv6. */
758 * A structure used to configure FDIR masks that are used by the device
759 * to match the various fields of RX packet headers.
760 * @note The only_ip_flow field has the opposite meaning compared to other
763 struct rte_fdir_masks {
764 /** When set to 1, packet l4type is \b NOT relevant in filters, and
765 source and destination port masks must be set to zero. */
766 uint8_t only_ip_flow;
767 /** If set to 1, vlan_id is relevant in filters. */
769 /** If set to 1, vlan_prio is relevant in filters. */
771 /** If set to 1, flexbytes is relevant in filters. */
773 /** If set to 1, set the IPv6 masks. Otherwise set the IPv4 masks. */
774 uint8_t set_ipv6_mask;
775 /** When set to 1, comparison of destination IPv6 address with IP6AT
776 registers is meaningful. */
777 uint8_t comp_ipv6_dst;
778 /** Mask of Destination IPv4 Address. All bits set to 1 define the
779 relevant bits to use in the destination address of an IPv4 packet
780 when matching it against FDIR filters. */
781 uint32_t dst_ipv4_mask;
782 /** Mask of Source IPv4 Address. All bits set to 1 define
783 the relevant bits to use in the source address of an IPv4 packet
784 when matching it against FDIR filters. */
785 uint32_t src_ipv4_mask;
786 /** Mask of Source IPv6 Address. All bits set to 1 define the
787 relevant BYTES to use in the source address of an IPv6 packet
788 when matching it against FDIR filters. */
789 uint16_t dst_ipv6_mask;
790 /** Mask of Destination IPv6 Address. All bits set to 1 define the
791 relevant BYTES to use in the destination address of an IPv6 packet
792 when matching it against FDIR filters. */
793 uint16_t src_ipv6_mask;
794 /** Mask of Source Port. All bits set to 1 define the relevant
795 bits to use in the source port of an IP packets when matching it
796 against FDIR filters. */
797 uint16_t src_port_mask;
798 /** Mask of Destination Port. All bits set to 1 define the relevant
799 bits to use in the destination port of an IP packet when matching it
800 against FDIR filters. */
801 uint16_t dst_port_mask;
805 * A structure used to report the status of the flow director filters in use.
807 struct rte_eth_fdir {
808 /** Number of filters with collision indication. */
810 /** Number of free (non programmed) filters. */
812 /** The Lookup hash value of the added filter that updated the value
813 of the MAXLEN field */
815 /** Longest linked list of filters in the table. */
817 /** Number of added filters. */
819 /** Number of removed filters. */
821 /** Number of failed added filters (no more space in device). */
823 /** Number of failed removed filters. */
828 * A structure used to enable/disable specific device interrupts.
830 struct rte_intr_conf {
831 /** enable/disable lsc interrupt. 0 (default) - disable, 1 enable */
836 * A structure used to configure an Ethernet port.
837 * Depending upon the RX multi-queue mode, extra advanced
838 * configuration settings may be needed.
840 struct rte_eth_conf {
842 /**< ETH_LINK_SPEED_10[0|00|000], or 0 for autonegotation */
843 uint16_t link_duplex;
844 /**< ETH_LINK_[HALF_DUPLEX|FULL_DUPLEX], or 0 for autonegotation */
845 struct rte_eth_rxmode rxmode; /**< Port RX configuration. */
846 struct rte_eth_txmode txmode; /**< Port TX configuration. */
847 uint32_t lpbk_mode; /**< Loopback operation mode. By default the value
848 is 0, meaning the loopback mode is disabled.
849 Read the datasheet of given ethernet controller
850 for details. The possible values of this field
851 are defined in implementation of each driver. */
853 struct rte_eth_rss_conf rss_conf; /**< Port RSS configuration */
854 struct rte_eth_vmdq_dcb_conf vmdq_dcb_conf;
855 /**< Port vmdq+dcb configuration. */
856 struct rte_eth_dcb_rx_conf dcb_rx_conf;
857 /**< Port dcb RX configuration. */
858 struct rte_eth_vmdq_rx_conf vmdq_rx_conf;
859 /**< Port vmdq RX configuration. */
860 } rx_adv_conf; /**< Port RX filtering configuration (union). */
862 struct rte_eth_vmdq_dcb_tx_conf vmdq_dcb_tx_conf;
863 /**< Port vmdq+dcb TX configuration. */
864 struct rte_eth_dcb_tx_conf dcb_tx_conf;
865 /**< Port dcb TX configuration. */
866 struct rte_eth_vmdq_tx_conf vmdq_tx_conf;
867 /**< Port vmdq TX configuration. */
868 } tx_adv_conf; /**< Port TX DCB configuration (union). */
869 /** Currently,Priority Flow Control(PFC) are supported,if DCB with PFC
870 is needed,and the variable must be set ETH_DCB_PFC_SUPPORT. */
871 uint32_t dcb_capability_en;
872 struct rte_fdir_conf fdir_conf; /**< FDIR configuration. */
873 struct rte_intr_conf intr_conf; /**< Interrupt mode configuration. */
877 * A structure used to retrieve the contextual information of
878 * an Ethernet device, such as the controlling driver of the device,
879 * its PCI context, etc...
883 * RX offload capabilities of a device.
885 #define DEV_RX_OFFLOAD_VLAN_STRIP 0x00000001
886 #define DEV_RX_OFFLOAD_IPV4_CKSUM 0x00000002
887 #define DEV_RX_OFFLOAD_UDP_CKSUM 0x00000004
888 #define DEV_RX_OFFLOAD_TCP_CKSUM 0x00000008
889 #define DEV_RX_OFFLOAD_TCP_LRO 0x00000010
892 * TX offload capabilities of a device.
894 #define DEV_TX_OFFLOAD_VLAN_INSERT 0x00000001
895 #define DEV_TX_OFFLOAD_IPV4_CKSUM 0x00000002
896 #define DEV_TX_OFFLOAD_UDP_CKSUM 0x00000004
897 #define DEV_TX_OFFLOAD_TCP_CKSUM 0x00000008
898 #define DEV_TX_OFFLOAD_SCTP_CKSUM 0x00000010
899 #define DEV_TX_OFFLOAD_TCP_TSO 0x00000020
900 #define DEV_TX_OFFLOAD_UDP_TSO 0x00000040
901 #define DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM 0x00000080 /**< Used for tunneling packet. */
903 struct rte_eth_dev_info {
904 struct rte_pci_device *pci_dev; /**< Device PCI information. */
905 const char *driver_name; /**< Device Driver name. */
906 unsigned int if_index; /**< Index to bound host interface, or 0 if none.
907 Use if_indextoname() to translate into an interface name. */
908 uint32_t min_rx_bufsize; /**< Minimum size of RX buffer. */
909 uint32_t max_rx_pktlen; /**< Maximum configurable length of RX pkt. */
910 uint16_t max_rx_queues; /**< Maximum number of RX queues. */
911 uint16_t max_tx_queues; /**< Maximum number of TX queues. */
912 uint32_t max_mac_addrs; /**< Maximum number of MAC addresses. */
913 uint32_t max_hash_mac_addrs;
914 /** Maximum number of hash MAC addresses for MTA and UTA. */
915 uint16_t max_vfs; /**< Maximum number of VFs. */
916 uint16_t max_vmdq_pools; /**< Maximum number of VMDq pools. */
917 uint32_t rx_offload_capa; /**< Device RX offload capabilities. */
918 uint32_t tx_offload_capa; /**< Device TX offload capabilities. */
920 /**< Device redirection table size, the total number of entries. */
921 /** Bit mask of RSS offloads, the bit offset also means flow type */
922 uint64_t flow_type_rss_offloads;
923 struct rte_eth_rxconf default_rxconf; /**< Default RX configuration */
924 struct rte_eth_txconf default_txconf; /**< Default TX configuration */
925 uint16_t vmdq_queue_base; /**< First queue ID for VMDQ pools. */
926 uint16_t vmdq_queue_num; /**< Queue number for VMDQ pools. */
927 uint16_t vmdq_pool_base; /**< First ID of VMDQ pools. */
930 /** Maximum name length for extended statistics counters */
931 #define RTE_ETH_XSTATS_NAME_SIZE 64
934 * An Ethernet device extended statistic structure
936 * This structure is used by ethdev->eth_xstats_get() to provide
937 * statistics that are not provided in the generic rte_eth_stats
940 struct rte_eth_xstats {
941 char name[RTE_ETH_XSTATS_NAME_SIZE];
947 struct rte_eth_dev_callback;
948 /** @internal Structure to keep track of registered callbacks */
949 TAILQ_HEAD(rte_eth_dev_cb_list, rte_eth_dev_callback);
952 * Definitions of all functions exported by an Ethernet driver through the
953 * the generic structure of type *eth_dev_ops* supplied in the *rte_eth_dev*
954 * structure associated with an Ethernet device.
957 typedef int (*eth_dev_configure_t)(struct rte_eth_dev *dev);
958 /**< @internal Ethernet device configuration. */
960 typedef int (*eth_dev_start_t)(struct rte_eth_dev *dev);
961 /**< @internal Function used to start a configured Ethernet device. */
963 typedef void (*eth_dev_stop_t)(struct rte_eth_dev *dev);
964 /**< @internal Function used to stop a configured Ethernet device. */
966 typedef int (*eth_dev_set_link_up_t)(struct rte_eth_dev *dev);
967 /**< @internal Function used to link up a configured Ethernet device. */
969 typedef int (*eth_dev_set_link_down_t)(struct rte_eth_dev *dev);
970 /**< @internal Function used to link down a configured Ethernet device. */
972 typedef void (*eth_dev_close_t)(struct rte_eth_dev *dev);
973 /**< @internal Function used to close a configured Ethernet device. */
975 typedef void (*eth_promiscuous_enable_t)(struct rte_eth_dev *dev);
976 /**< @internal Function used to enable the RX promiscuous mode of an Ethernet device. */
978 typedef void (*eth_promiscuous_disable_t)(struct rte_eth_dev *dev);
979 /**< @internal Function used to disable the RX promiscuous mode of an Ethernet device. */
981 typedef void (*eth_allmulticast_enable_t)(struct rte_eth_dev *dev);
982 /**< @internal Enable the receipt of all multicast packets by an Ethernet device. */
984 typedef void (*eth_allmulticast_disable_t)(struct rte_eth_dev *dev);
985 /**< @internal Disable the receipt of all multicast packets by an Ethernet device. */
987 typedef int (*eth_link_update_t)(struct rte_eth_dev *dev,
988 int wait_to_complete);
989 /**< @internal Get link speed, duplex mode and state (up/down) of an Ethernet device. */
991 typedef void (*eth_stats_get_t)(struct rte_eth_dev *dev,
992 struct rte_eth_stats *igb_stats);
993 /**< @internal Get global I/O statistics of an Ethernet device. */
995 typedef void (*eth_stats_reset_t)(struct rte_eth_dev *dev);
996 /**< @internal Reset global I/O statistics of an Ethernet device to 0. */
998 typedef int (*eth_xstats_get_t)(struct rte_eth_dev *dev,
999 struct rte_eth_xstats *stats, unsigned n);
1000 /**< @internal Get extended stats of an Ethernet device. */
1002 typedef void (*eth_xstats_reset_t)(struct rte_eth_dev *dev);
1003 /**< @internal Reset extended stats of an Ethernet device. */
1005 typedef int (*eth_queue_stats_mapping_set_t)(struct rte_eth_dev *dev,
1009 /**< @internal Set a queue statistics mapping for a tx/rx queue of an Ethernet device. */
1011 typedef void (*eth_dev_infos_get_t)(struct rte_eth_dev *dev,
1012 struct rte_eth_dev_info *dev_info);
1013 /**< @internal Get specific informations of an Ethernet device. */
1015 typedef int (*eth_queue_start_t)(struct rte_eth_dev *dev,
1017 /**< @internal Start rx and tx of a queue of an Ethernet device. */
1019 typedef int (*eth_queue_stop_t)(struct rte_eth_dev *dev,
1021 /**< @internal Stop rx and tx of a queue of an Ethernet device. */
1023 typedef int (*eth_rx_queue_setup_t)(struct rte_eth_dev *dev,
1024 uint16_t rx_queue_id,
1025 uint16_t nb_rx_desc,
1026 unsigned int socket_id,
1027 const struct rte_eth_rxconf *rx_conf,
1028 struct rte_mempool *mb_pool);
1029 /**< @internal Set up a receive queue of an Ethernet device. */
1031 typedef int (*eth_tx_queue_setup_t)(struct rte_eth_dev *dev,
1032 uint16_t tx_queue_id,
1033 uint16_t nb_tx_desc,
1034 unsigned int socket_id,
1035 const struct rte_eth_txconf *tx_conf);
1036 /**< @internal Setup a transmit queue of an Ethernet device. */
1038 typedef void (*eth_queue_release_t)(void *queue);
1039 /**< @internal Release memory resources allocated by given RX/TX queue. */
1041 typedef uint32_t (*eth_rx_queue_count_t)(struct rte_eth_dev *dev,
1042 uint16_t rx_queue_id);
1043 /**< @Get number of available descriptors on a receive queue of an Ethernet device. */
1045 typedef int (*eth_rx_descriptor_done_t)(void *rxq, uint16_t offset);
1046 /**< @Check DD bit of specific RX descriptor */
1048 typedef int (*mtu_set_t)(struct rte_eth_dev *dev, uint16_t mtu);
1049 /**< @internal Set MTU. */
1051 typedef int (*vlan_filter_set_t)(struct rte_eth_dev *dev,
1054 /**< @internal filtering of a VLAN Tag Identifier by an Ethernet device. */
1056 typedef void (*vlan_tpid_set_t)(struct rte_eth_dev *dev,
1058 /**< @internal set the outer VLAN-TPID by an Ethernet device. */
1060 typedef void (*vlan_offload_set_t)(struct rte_eth_dev *dev, int mask);
1061 /**< @internal set VLAN offload function by an Ethernet device. */
1063 typedef int (*vlan_pvid_set_t)(struct rte_eth_dev *dev,
1066 /**< @internal set port based TX VLAN insertion by an Ethernet device. */
1068 typedef void (*vlan_strip_queue_set_t)(struct rte_eth_dev *dev,
1069 uint16_t rx_queue_id,
1071 /**< @internal VLAN stripping enable/disable by an queue of Ethernet device. */
1073 typedef uint16_t (*eth_rx_burst_t)(void *rxq,
1074 struct rte_mbuf **rx_pkts,
1076 /**< @internal Retrieve input packets from a receive queue of an Ethernet device. */
1078 typedef uint16_t (*eth_tx_burst_t)(void *txq,
1079 struct rte_mbuf **tx_pkts,
1081 /**< @internal Send output packets on a transmit queue of an Ethernet device. */
1083 typedef int (*fdir_add_signature_filter_t)(struct rte_eth_dev *dev,
1084 struct rte_fdir_filter *fdir_ftr,
1086 /**< @internal Setup a new signature filter rule on an Ethernet device */
1088 typedef int (*fdir_update_signature_filter_t)(struct rte_eth_dev *dev,
1089 struct rte_fdir_filter *fdir_ftr,
1091 /**< @internal Update a signature filter rule on an Ethernet device */
1093 typedef int (*fdir_remove_signature_filter_t)(struct rte_eth_dev *dev,
1094 struct rte_fdir_filter *fdir_ftr);
1095 /**< @internal Remove a signature filter rule on an Ethernet device */
1097 typedef void (*fdir_infos_get_t)(struct rte_eth_dev *dev,
1098 struct rte_eth_fdir *fdir);
1099 /**< @internal Get information about fdir status */
1101 typedef int (*fdir_add_perfect_filter_t)(struct rte_eth_dev *dev,
1102 struct rte_fdir_filter *fdir_ftr,
1103 uint16_t soft_id, uint8_t rx_queue,
1105 /**< @internal Setup a new perfect filter rule on an Ethernet device */
1107 typedef int (*fdir_update_perfect_filter_t)(struct rte_eth_dev *dev,
1108 struct rte_fdir_filter *fdir_ftr,
1109 uint16_t soft_id, uint8_t rx_queue,
1111 /**< @internal Update a perfect filter rule on an Ethernet device */
1113 typedef int (*fdir_remove_perfect_filter_t)(struct rte_eth_dev *dev,
1114 struct rte_fdir_filter *fdir_ftr,
1116 /**< @internal Remove a perfect filter rule on an Ethernet device */
1118 typedef int (*fdir_set_masks_t)(struct rte_eth_dev *dev,
1119 struct rte_fdir_masks *fdir_masks);
1120 /**< @internal Setup flow director masks on an Ethernet device */
1122 typedef int (*flow_ctrl_get_t)(struct rte_eth_dev *dev,
1123 struct rte_eth_fc_conf *fc_conf);
1124 /**< @internal Get current flow control parameter on an Ethernet device */
1126 typedef int (*flow_ctrl_set_t)(struct rte_eth_dev *dev,
1127 struct rte_eth_fc_conf *fc_conf);
1128 /**< @internal Setup flow control parameter on an Ethernet device */
1130 typedef int (*priority_flow_ctrl_set_t)(struct rte_eth_dev *dev,
1131 struct rte_eth_pfc_conf *pfc_conf);
1132 /**< @internal Setup priority flow control parameter on an Ethernet device */
1134 typedef int (*reta_update_t)(struct rte_eth_dev *dev,
1135 struct rte_eth_rss_reta_entry64 *reta_conf,
1136 uint16_t reta_size);
1137 /**< @internal Update RSS redirection table on an Ethernet device */
1139 typedef int (*reta_query_t)(struct rte_eth_dev *dev,
1140 struct rte_eth_rss_reta_entry64 *reta_conf,
1141 uint16_t reta_size);
1142 /**< @internal Query RSS redirection table on an Ethernet device */
1144 typedef int (*rss_hash_update_t)(struct rte_eth_dev *dev,
1145 struct rte_eth_rss_conf *rss_conf);
1146 /**< @internal Update RSS hash configuration of an Ethernet device */
1148 typedef int (*rss_hash_conf_get_t)(struct rte_eth_dev *dev,
1149 struct rte_eth_rss_conf *rss_conf);
1150 /**< @internal Get current RSS hash configuration of an Ethernet device */
1152 typedef int (*eth_dev_led_on_t)(struct rte_eth_dev *dev);
1153 /**< @internal Turn on SW controllable LED on an Ethernet device */
1155 typedef int (*eth_dev_led_off_t)(struct rte_eth_dev *dev);
1156 /**< @internal Turn off SW controllable LED on an Ethernet device */
1158 typedef void (*eth_mac_addr_remove_t)(struct rte_eth_dev *dev, uint32_t index);
1159 /**< @internal Remove MAC address from receive address register */
1161 typedef void (*eth_mac_addr_add_t)(struct rte_eth_dev *dev,
1162 struct ether_addr *mac_addr,
1165 /**< @internal Set a MAC address into Receive Address Address Register */
1167 typedef void (*eth_mac_addr_set_t)(struct rte_eth_dev *dev,
1168 struct ether_addr *mac_addr);
1169 /**< @internal Set a MAC address into Receive Address Address Register */
1171 typedef int (*eth_uc_hash_table_set_t)(struct rte_eth_dev *dev,
1172 struct ether_addr *mac_addr,
1174 /**< @internal Set a Unicast Hash bitmap */
1176 typedef int (*eth_uc_all_hash_table_set_t)(struct rte_eth_dev *dev,
1178 /**< @internal Set all Unicast Hash bitmap */
1180 typedef int (*eth_set_vf_rx_mode_t)(struct rte_eth_dev *dev,
1184 /**< @internal Set a VF receive mode */
1186 typedef int (*eth_set_vf_rx_t)(struct rte_eth_dev *dev,
1189 /**< @internal Set a VF receive mode */
1191 typedef int (*eth_set_vf_tx_t)(struct rte_eth_dev *dev,
1194 /**< @internal Enable or disable a VF transmit */
1196 typedef int (*eth_set_vf_vlan_filter_t)(struct rte_eth_dev *dev,
1200 /**< @internal Set VF VLAN pool filter */
1202 typedef int (*eth_set_queue_rate_limit_t)(struct rte_eth_dev *dev,
1205 /**< @internal Set queue TX rate */
1207 typedef int (*eth_set_vf_rate_limit_t)(struct rte_eth_dev *dev,
1211 /**< @internal Set VF TX rate */
1213 typedef int (*eth_mirror_rule_set_t)(struct rte_eth_dev *dev,
1214 struct rte_eth_vmdq_mirror_conf *mirror_conf,
1217 /**< @internal Add a traffic mirroring rule on an Ethernet device */
1219 typedef int (*eth_mirror_rule_reset_t)(struct rte_eth_dev *dev,
1221 /**< @internal Remove a traffic mirroring rule on an Ethernet device */
1223 typedef int (*eth_udp_tunnel_add_t)(struct rte_eth_dev *dev,
1224 struct rte_eth_udp_tunnel *tunnel_udp);
1225 /**< @internal Add tunneling UDP info */
1227 typedef int (*eth_udp_tunnel_del_t)(struct rte_eth_dev *dev,
1228 struct rte_eth_udp_tunnel *tunnel_udp);
1229 /**< @internal Delete tunneling UDP info */
1231 typedef int (*eth_set_mc_addr_list_t)(struct rte_eth_dev *dev,
1232 struct ether_addr *mc_addr_set,
1233 uint32_t nb_mc_addr);
1234 /**< @internal set the list of multicast addresses on an Ethernet device */
1236 #ifdef RTE_NIC_BYPASS
1239 RTE_BYPASS_MODE_NONE,
1240 RTE_BYPASS_MODE_NORMAL,
1241 RTE_BYPASS_MODE_BYPASS,
1242 RTE_BYPASS_MODE_ISOLATE,
1243 RTE_BYPASS_MODE_NUM,
1246 #define RTE_BYPASS_MODE_VALID(x) \
1247 ((x) > RTE_BYPASS_MODE_NONE && (x) < RTE_BYPASS_MODE_NUM)
1250 RTE_BYPASS_EVENT_NONE,
1251 RTE_BYPASS_EVENT_START,
1252 RTE_BYPASS_EVENT_OS_ON = RTE_BYPASS_EVENT_START,
1253 RTE_BYPASS_EVENT_POWER_ON,
1254 RTE_BYPASS_EVENT_OS_OFF,
1255 RTE_BYPASS_EVENT_POWER_OFF,
1256 RTE_BYPASS_EVENT_TIMEOUT,
1257 RTE_BYPASS_EVENT_NUM
1260 #define RTE_BYPASS_EVENT_VALID(x) \
1261 ((x) > RTE_BYPASS_EVENT_NONE && (x) < RTE_BYPASS_MODE_NUM)
1264 RTE_BYPASS_TMT_OFF, /* timeout disabled. */
1265 RTE_BYPASS_TMT_1_5_SEC, /* timeout for 1.5 seconds */
1266 RTE_BYPASS_TMT_2_SEC, /* timeout for 2 seconds */
1267 RTE_BYPASS_TMT_3_SEC, /* timeout for 3 seconds */
1268 RTE_BYPASS_TMT_4_SEC, /* timeout for 4 seconds */
1269 RTE_BYPASS_TMT_8_SEC, /* timeout for 8 seconds */
1270 RTE_BYPASS_TMT_16_SEC, /* timeout for 16 seconds */
1271 RTE_BYPASS_TMT_32_SEC, /* timeout for 32 seconds */
1275 #define RTE_BYPASS_TMT_VALID(x) \
1276 ((x) == RTE_BYPASS_TMT_OFF || \
1277 ((x) > RTE_BYPASS_TMT_OFF && (x) < RTE_BYPASS_TMT_NUM))
1279 typedef void (*bypass_init_t)(struct rte_eth_dev *dev);
1280 typedef int32_t (*bypass_state_set_t)(struct rte_eth_dev *dev, uint32_t *new_state);
1281 typedef int32_t (*bypass_state_show_t)(struct rte_eth_dev *dev, uint32_t *state);
1282 typedef int32_t (*bypass_event_set_t)(struct rte_eth_dev *dev, uint32_t state, uint32_t event);
1283 typedef int32_t (*bypass_event_show_t)(struct rte_eth_dev *dev, uint32_t event_shift, uint32_t *event);
1284 typedef int32_t (*bypass_wd_timeout_set_t)(struct rte_eth_dev *dev, uint32_t timeout);
1285 typedef int32_t (*bypass_wd_timeout_show_t)(struct rte_eth_dev *dev, uint32_t *wd_timeout);
1286 typedef int32_t (*bypass_ver_show_t)(struct rte_eth_dev *dev, uint32_t *ver);
1287 typedef int32_t (*bypass_wd_reset_t)(struct rte_eth_dev *dev);
1290 typedef int (*eth_filter_ctrl_t)(struct rte_eth_dev *dev,
1291 enum rte_filter_type filter_type,
1292 enum rte_filter_op filter_op,
1294 /**< @internal Take operations to assigned filter type on an Ethernet device */
1297 * @internal A structure containing the functions exported by an Ethernet driver.
1299 struct eth_dev_ops {
1300 eth_dev_configure_t dev_configure; /**< Configure device. */
1301 eth_dev_start_t dev_start; /**< Start device. */
1302 eth_dev_stop_t dev_stop; /**< Stop device. */
1303 eth_dev_set_link_up_t dev_set_link_up; /**< Device link up. */
1304 eth_dev_set_link_down_t dev_set_link_down; /**< Device link down. */
1305 eth_dev_close_t dev_close; /**< Close device. */
1306 eth_promiscuous_enable_t promiscuous_enable; /**< Promiscuous ON. */
1307 eth_promiscuous_disable_t promiscuous_disable;/**< Promiscuous OFF. */
1308 eth_allmulticast_enable_t allmulticast_enable;/**< RX multicast ON. */
1309 eth_allmulticast_disable_t allmulticast_disable;/**< RX multicast OF. */
1310 eth_link_update_t link_update; /**< Get device link state. */
1311 eth_stats_get_t stats_get; /**< Get generic device statistics. */
1312 eth_stats_reset_t stats_reset; /**< Reset generic device statistics. */
1313 eth_xstats_get_t xstats_get; /**< Get extended device statistics. */
1314 eth_xstats_reset_t xstats_reset; /**< Reset extended device statistics. */
1315 eth_queue_stats_mapping_set_t queue_stats_mapping_set;
1316 /**< Configure per queue stat counter mapping. */
1317 eth_dev_infos_get_t dev_infos_get; /**< Get device info. */
1318 mtu_set_t mtu_set; /**< Set MTU. */
1319 vlan_filter_set_t vlan_filter_set; /**< Filter VLAN Setup. */
1320 vlan_tpid_set_t vlan_tpid_set; /**< Outer VLAN TPID Setup. */
1321 vlan_strip_queue_set_t vlan_strip_queue_set; /**< VLAN Stripping on queue. */
1322 vlan_offload_set_t vlan_offload_set; /**< Set VLAN Offload. */
1323 vlan_pvid_set_t vlan_pvid_set; /**< Set port based TX VLAN insertion */
1324 eth_queue_start_t rx_queue_start;/**< Start RX for a queue.*/
1325 eth_queue_stop_t rx_queue_stop;/**< Stop RX for a queue.*/
1326 eth_queue_start_t tx_queue_start;/**< Start TX for a queue.*/
1327 eth_queue_stop_t tx_queue_stop;/**< Stop TX for a queue.*/
1328 eth_rx_queue_setup_t rx_queue_setup;/**< Set up device RX queue.*/
1329 eth_queue_release_t rx_queue_release;/**< Release RX queue.*/
1330 eth_rx_queue_count_t rx_queue_count; /**< Get Rx queue count. */
1331 eth_rx_descriptor_done_t rx_descriptor_done; /**< Check rxd DD bit */
1332 eth_tx_queue_setup_t tx_queue_setup;/**< Set up device TX queue.*/
1333 eth_queue_release_t tx_queue_release;/**< Release TX queue.*/
1334 eth_dev_led_on_t dev_led_on; /**< Turn on LED. */
1335 eth_dev_led_off_t dev_led_off; /**< Turn off LED. */
1336 flow_ctrl_get_t flow_ctrl_get; /**< Get flow control. */
1337 flow_ctrl_set_t flow_ctrl_set; /**< Setup flow control. */
1338 priority_flow_ctrl_set_t priority_flow_ctrl_set; /**< Setup priority flow control.*/
1339 eth_mac_addr_remove_t mac_addr_remove; /**< Remove MAC address */
1340 eth_mac_addr_add_t mac_addr_add; /**< Add a MAC address */
1341 eth_mac_addr_set_t mac_addr_set; /**< Set a MAC address */
1342 eth_uc_hash_table_set_t uc_hash_table_set; /**< Set Unicast Table Array */
1343 eth_uc_all_hash_table_set_t uc_all_hash_table_set; /**< Set Unicast hash bitmap */
1344 eth_mirror_rule_set_t mirror_rule_set; /**< Add a traffic mirror rule.*/
1345 eth_mirror_rule_reset_t mirror_rule_reset; /**< reset a traffic mirror rule.*/
1346 eth_set_vf_rx_mode_t set_vf_rx_mode; /**< Set VF RX mode */
1347 eth_set_vf_rx_t set_vf_rx; /**< enable/disable a VF receive */
1348 eth_set_vf_tx_t set_vf_tx; /**< enable/disable a VF transmit */
1349 eth_set_vf_vlan_filter_t set_vf_vlan_filter; /**< Set VF VLAN filter */
1350 eth_udp_tunnel_add_t udp_tunnel_add;
1351 eth_udp_tunnel_del_t udp_tunnel_del;
1352 eth_set_queue_rate_limit_t set_queue_rate_limit; /**< Set queue rate limit */
1353 eth_set_vf_rate_limit_t set_vf_rate_limit; /**< Set VF rate limit */
1355 /** Add a signature filter. */
1356 fdir_add_signature_filter_t fdir_add_signature_filter;
1357 /** Update a signature filter. */
1358 fdir_update_signature_filter_t fdir_update_signature_filter;
1359 /** Remove a signature filter. */
1360 fdir_remove_signature_filter_t fdir_remove_signature_filter;
1361 /** Get information about FDIR status. */
1362 fdir_infos_get_t fdir_infos_get;
1363 /** Add a perfect filter. */
1364 fdir_add_perfect_filter_t fdir_add_perfect_filter;
1365 /** Update a perfect filter. */
1366 fdir_update_perfect_filter_t fdir_update_perfect_filter;
1367 /** Remove a perfect filter. */
1368 fdir_remove_perfect_filter_t fdir_remove_perfect_filter;
1369 /** Setup masks for FDIR filtering. */
1370 fdir_set_masks_t fdir_set_masks;
1371 /** Update redirection table. */
1372 reta_update_t reta_update;
1373 /** Query redirection table. */
1374 reta_query_t reta_query;
1375 /* bypass control */
1376 #ifdef RTE_NIC_BYPASS
1377 bypass_init_t bypass_init;
1378 bypass_state_set_t bypass_state_set;
1379 bypass_state_show_t bypass_state_show;
1380 bypass_event_set_t bypass_event_set;
1381 bypass_event_show_t bypass_event_show;
1382 bypass_wd_timeout_set_t bypass_wd_timeout_set;
1383 bypass_wd_timeout_show_t bypass_wd_timeout_show;
1384 bypass_ver_show_t bypass_ver_show;
1385 bypass_wd_reset_t bypass_wd_reset;
1388 /** Configure RSS hash protocols. */
1389 rss_hash_update_t rss_hash_update;
1390 /** Get current RSS hash configuration. */
1391 rss_hash_conf_get_t rss_hash_conf_get;
1392 eth_filter_ctrl_t filter_ctrl; /**< common filter control*/
1393 eth_set_mc_addr_list_t set_mc_addr_list; /**< set list of mcast addrs */
1397 * Function type used for RX packet processing packet callbacks.
1399 * The callback function is called on RX with a burst of packets that have
1400 * been received on the given port and queue.
1403 * The Ethernet port on which RX is being performed.
1405 * The queue on the Ethernet port which is being used to receive the packets.
1407 * The burst of packets that have just been received.
1409 * The number of packets in the burst pointed to by "pkts".
1411 * The max number of packets that can be stored in the "pkts" array.
1413 * The arbitrary user parameter passed in by the application when the callback
1414 * was originally configured.
1416 * The number of packets returned to the user.
1418 typedef uint16_t (*rte_rx_callback_fn)(uint8_t port, uint16_t queue,
1419 struct rte_mbuf *pkts[], uint16_t nb_pkts, uint16_t max_pkts,
1423 * Function type used for TX packet processing packet callbacks.
1425 * The callback function is called on TX with a burst of packets immediately
1426 * before the packets are put onto the hardware queue for transmission.
1429 * The Ethernet port on which TX is being performed.
1431 * The queue on the Ethernet port which is being used to transmit the packets.
1433 * The burst of packets that are about to be transmitted.
1435 * The number of packets in the burst pointed to by "pkts".
1437 * The arbitrary user parameter passed in by the application when the callback
1438 * was originally configured.
1440 * The number of packets to be written to the NIC.
1442 typedef uint16_t (*rte_tx_callback_fn)(uint8_t port, uint16_t queue,
1443 struct rte_mbuf *pkts[], uint16_t nb_pkts, void *user_param);
1447 * Structure used to hold information about the callbacks to be called for a
1448 * queue on RX and TX.
1450 struct rte_eth_rxtx_callback {
1451 struct rte_eth_rxtx_callback *next;
1453 rte_rx_callback_fn rx;
1454 rte_tx_callback_fn tx;
1460 * The eth device type
1462 enum rte_eth_dev_type {
1463 RTE_ETH_DEV_UNKNOWN, /**< unknown device type */
1465 /**< Physical function and Virtual function of PCI devices */
1466 RTE_ETH_DEV_VIRTUAL, /**< non hardware device */
1467 RTE_ETH_DEV_MAX /**< max value of this enum */
1472 * The generic data structure associated with each ethernet device.
1474 * Pointers to burst-oriented packet receive and transmit functions are
1475 * located at the beginning of the structure, along with the pointer to
1476 * where all the data elements for the particular device are stored in shared
1477 * memory. This split allows the function pointer and driver data to be per-
1478 * process, while the actual configuration data for the device is shared.
1480 struct rte_eth_dev {
1481 eth_rx_burst_t rx_pkt_burst; /**< Pointer to PMD receive function. */
1482 eth_tx_burst_t tx_pkt_burst; /**< Pointer to PMD transmit function. */
1483 struct rte_eth_dev_data *data; /**< Pointer to device data */
1484 const struct eth_driver *driver;/**< Driver for this device */
1485 const struct eth_dev_ops *dev_ops; /**< Functions exported by PMD */
1486 struct rte_pci_device *pci_dev; /**< PCI info. supplied by probing */
1487 /** User application callbacks for NIC interrupts */
1488 struct rte_eth_dev_cb_list link_intr_cbs;
1490 * User-supplied functions called from rx_burst to post-process
1491 * received packets before passing them to the user
1493 struct rte_eth_rxtx_callback *post_rx_burst_cbs[RTE_MAX_QUEUES_PER_PORT];
1495 * User-supplied functions called from tx_burst to pre-process
1496 * received packets before passing them to the driver for transmission.
1498 struct rte_eth_rxtx_callback *pre_tx_burst_cbs[RTE_MAX_QUEUES_PER_PORT];
1499 uint8_t attached; /**< Flag indicating the port is attached */
1500 enum rte_eth_dev_type dev_type; /**< Flag indicating the device type */
1503 struct rte_eth_dev_sriov {
1504 uint8_t active; /**< SRIOV is active with 16, 32 or 64 pools */
1505 uint8_t nb_q_per_pool; /**< rx queue number per pool */
1506 uint16_t def_vmdq_idx; /**< Default pool num used for PF */
1507 uint16_t def_pool_q_idx; /**< Default pool queue start reg index */
1509 #define RTE_ETH_DEV_SRIOV(dev) ((dev)->data->sriov)
1511 #define RTE_ETH_NAME_MAX_LEN (32)
1515 * The data part, with no function pointers, associated with each ethernet device.
1517 * This structure is safe to place in shared memory to be common among different
1518 * processes in a multi-process configuration.
1520 struct rte_eth_dev_data {
1521 char name[RTE_ETH_NAME_MAX_LEN]; /**< Unique identifier name */
1523 void **rx_queues; /**< Array of pointers to RX queues. */
1524 void **tx_queues; /**< Array of pointers to TX queues. */
1525 uint16_t nb_rx_queues; /**< Number of RX queues. */
1526 uint16_t nb_tx_queues; /**< Number of TX queues. */
1528 struct rte_eth_dev_sriov sriov; /**< SRIOV data */
1530 void *dev_private; /**< PMD-specific private data */
1532 struct rte_eth_link dev_link;
1533 /**< Link-level information & status */
1535 struct rte_eth_conf dev_conf; /**< Configuration applied to device. */
1536 uint16_t mtu; /**< Maximum Transmission Unit. */
1538 uint32_t min_rx_buf_size;
1539 /**< Common rx buffer size handled by all queues */
1541 uint64_t rx_mbuf_alloc_failed; /**< RX ring mbuf allocation failures. */
1542 struct ether_addr* mac_addrs;/**< Device Ethernet Link address. */
1543 uint64_t mac_pool_sel[ETH_NUM_RECEIVE_MAC_ADDR];
1544 /** bitmap array of associating Ethernet MAC addresses to pools */
1545 struct ether_addr* hash_mac_addrs;
1546 /** Device Ethernet MAC addresses of hash filtering. */
1547 uint8_t port_id; /**< Device [external] port identifier. */
1548 uint8_t promiscuous : 1, /**< RX promiscuous mode ON(1) / OFF(0). */
1549 scattered_rx : 1, /**< RX of scattered packets is ON(1) / OFF(0) */
1550 lro : 1, /**< RX LRO is ON(1) / OFF(0) */
1551 all_multicast : 1, /**< RX all multicast mode ON(1) / OFF(0). */
1552 dev_started : 1; /**< Device state: STARTED(1) / STOPPED(0). */
1557 * The pool of *rte_eth_dev* structures. The size of the pool
1558 * is configured at compile-time in the <rte_ethdev.c> file.
1560 extern struct rte_eth_dev rte_eth_devices[];
1563 * Get the total number of Ethernet devices that have been successfully
1564 * initialized by the [matching] Ethernet driver during the PCI probing phase.
1565 * All devices whose port identifier is in the range
1566 * [0, rte_eth_dev_count() - 1] can be operated on by network applications
1567 * immediately after invoking rte_eal_init().
1568 * If the application unplugs a port using hotplug function, The enabled port
1569 * numbers may be noncontiguous. In the case, the applications need to manage
1570 * enabled port by themselves.
1573 * - The total number of usable Ethernet devices.
1575 extern uint8_t rte_eth_dev_count(void);
1578 * Function for internal use by port hotplug functions.
1579 * Returns a ethdev slot specified by the unique identifier name.
1581 * The pointer to the Unique identifier name for each Ethernet device
1583 * - The pointer to the ethdev slot, on success. NULL on error
1585 extern struct rte_eth_dev *rte_eth_dev_allocated(const char *name);
1588 * Function for internal use by dummy drivers primarily, e.g. ring-based
1590 * Allocates a new ethdev slot for an ethernet device and returns the pointer
1591 * to that slot for the driver to use.
1593 * @param name Unique identifier name for each Ethernet device
1594 * @param type Device type of this Ethernet device
1596 * - Slot in the rte_dev_devices array for a new device;
1598 struct rte_eth_dev *rte_eth_dev_allocate(const char *name,
1599 enum rte_eth_dev_type type);
1602 * Function for internal use by dummy drivers primarily, e.g. ring-based
1604 * Release the specified ethdev port.
1607 * The *eth_dev* pointer is the address of the *rte_eth_dev* structure.
1609 * - 0 on success, negative on error
1611 int rte_eth_dev_release_port(struct rte_eth_dev *eth_dev);
1614 * Attach a new Ethernet device specified by aruguments.
1617 * A pointer to a strings array describing the new device
1618 * to be attached. The strings should be a pci address like
1619 * '0000:01:00.0' or virtual device name like 'eth_pcap0'.
1621 * A pointer to a port identifier actually attached.
1623 * 0 on success and port_id is filled, negative on error
1625 int rte_eth_dev_attach(const char *devargs, uint8_t *port_id);
1628 * Detach a Ethernet device specified by port identifier.
1631 * The port identifier of the device to detach.
1633 * A pointer to a device name actually detached.
1635 * 0 on success and devname is filled, negative on error
1637 int rte_eth_dev_detach(uint8_t port_id, char *devname);
1642 * Initialization function of an Ethernet driver invoked for each matching
1643 * Ethernet PCI device detected during the PCI probing phase.
1646 * The *eth_dev* pointer is the address of the *rte_eth_dev* structure
1647 * associated with the matching device and which have been [automatically]
1648 * allocated in the *rte_eth_devices* array.
1649 * The *eth_dev* structure is supplied to the driver initialization function
1650 * with the following fields already initialized:
1652 * - *pci_dev*: Holds the pointers to the *rte_pci_device* structure which
1653 * contains the generic PCI information of the matching device.
1655 * - *driver*: Holds the pointer to the *eth_driver* structure.
1657 * - *dev_private*: Holds a pointer to the device private data structure.
1659 * - *mtu*: Contains the default Ethernet maximum frame length (1500).
1661 * - *port_id*: Contains the port index of the device (actually the index
1662 * of the *eth_dev* structure in the *rte_eth_devices* array).
1665 * - 0: Success, the device is properly initialized by the driver.
1666 * In particular, the driver MUST have set up the *dev_ops* pointer
1667 * of the *eth_dev* structure.
1668 * - <0: Error code of the device initialization failure.
1670 typedef int (*eth_dev_init_t)(struct rte_eth_dev *eth_dev);
1674 * Finalization function of an Ethernet driver invoked for each matching
1675 * Ethernet PCI device detected during the PCI closing phase.
1678 * The *eth_dev* pointer is the address of the *rte_eth_dev* structure
1679 * associated with the matching device and which have been [automatically]
1680 * allocated in the *rte_eth_devices* array.
1682 * - 0: Success, the device is properly finalized by the driver.
1683 * In particular, the driver MUST free the *dev_ops* pointer
1684 * of the *eth_dev* structure.
1685 * - <0: Error code of the device initialization failure.
1687 typedef int (*eth_dev_uninit_t)(struct rte_eth_dev *eth_dev);
1691 * The structure associated with a PMD Ethernet driver.
1693 * Each Ethernet driver acts as a PCI driver and is represented by a generic
1694 * *eth_driver* structure that holds:
1696 * - An *rte_pci_driver* structure (which must be the first field).
1698 * - The *eth_dev_init* function invoked for each matching PCI device.
1700 * - The *eth_dev_uninit* function invoked for each matching PCI device.
1702 * - The size of the private data to allocate for each matching device.
1705 struct rte_pci_driver pci_drv; /**< The PMD is also a PCI driver. */
1706 eth_dev_init_t eth_dev_init; /**< Device init function. */
1707 eth_dev_uninit_t eth_dev_uninit; /**< Device uninit function. */
1708 unsigned int dev_private_size; /**< Size of device private data. */
1713 * A function invoked by the initialization function of an Ethernet driver
1714 * to simultaneously register itself as a PCI driver and as an Ethernet
1715 * Poll Mode Driver (PMD).
1718 * The pointer to the *eth_driver* structure associated with
1719 * the Ethernet driver.
1721 extern void rte_eth_driver_register(struct eth_driver *eth_drv);
1724 * Configure an Ethernet device.
1725 * This function must be invoked first before any other function in the
1726 * Ethernet API. This function can also be re-invoked when a device is in the
1730 * The port identifier of the Ethernet device to configure.
1731 * @param nb_rx_queue
1732 * The number of receive queues to set up for the Ethernet device.
1733 * @param nb_tx_queue
1734 * The number of transmit queues to set up for the Ethernet device.
1736 * The pointer to the configuration data to be used for the Ethernet device.
1737 * The *rte_eth_conf* structure includes:
1738 * - the hardware offload features to activate, with dedicated fields for
1739 * each statically configurable offload hardware feature provided by
1740 * Ethernet devices, such as IP checksum or VLAN tag stripping for
1742 * - the Receive Side Scaling (RSS) configuration when using multiple RX
1745 * Embedding all configuration information in a single data structure
1746 * is the more flexible method that allows the addition of new features
1747 * without changing the syntax of the API.
1749 * - 0: Success, device configured.
1750 * - <0: Error code returned by the driver configuration function.
1752 extern int rte_eth_dev_configure(uint8_t port_id,
1753 uint16_t nb_rx_queue,
1754 uint16_t nb_tx_queue,
1755 const struct rte_eth_conf *eth_conf);
1758 * Allocate and set up a receive queue for an Ethernet device.
1760 * The function allocates a contiguous block of memory for *nb_rx_desc*
1761 * receive descriptors from a memory zone associated with *socket_id*
1762 * and initializes each receive descriptor with a network buffer allocated
1763 * from the memory pool *mb_pool*.
1766 * The port identifier of the Ethernet device.
1767 * @param rx_queue_id
1768 * The index of the receive queue to set up.
1769 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1770 * to rte_eth_dev_configure().
1772 * The number of receive descriptors to allocate for the receive ring.
1774 * The *socket_id* argument is the socket identifier in case of NUMA.
1775 * The value can be *SOCKET_ID_ANY* if there is no NUMA constraint for
1776 * the DMA memory allocated for the receive descriptors of the ring.
1778 * The pointer to the configuration data to be used for the receive queue.
1779 * NULL value is allowed, in which case default RX configuration
1781 * The *rx_conf* structure contains an *rx_thresh* structure with the values
1782 * of the Prefetch, Host, and Write-Back threshold registers of the receive
1785 * The pointer to the memory pool from which to allocate *rte_mbuf* network
1786 * memory buffers to populate each descriptor of the receive ring.
1788 * - 0: Success, receive queue correctly set up.
1789 * - -EINVAL: The size of network buffers which can be allocated from the
1790 * memory pool does not fit the various buffer sizes allowed by the
1791 * device controller.
1792 * - -ENOMEM: Unable to allocate the receive ring descriptors or to
1793 * allocate network memory buffers from the memory pool when
1794 * initializing receive descriptors.
1796 extern int rte_eth_rx_queue_setup(uint8_t port_id, uint16_t rx_queue_id,
1797 uint16_t nb_rx_desc, unsigned int socket_id,
1798 const struct rte_eth_rxconf *rx_conf,
1799 struct rte_mempool *mb_pool);
1802 * Allocate and set up a transmit queue for an Ethernet device.
1805 * The port identifier of the Ethernet device.
1806 * @param tx_queue_id
1807 * The index of the transmit queue to set up.
1808 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1809 * to rte_eth_dev_configure().
1811 * The number of transmit descriptors to allocate for the transmit ring.
1813 * The *socket_id* argument is the socket identifier in case of NUMA.
1814 * Its value can be *SOCKET_ID_ANY* if there is no NUMA constraint for
1815 * the DMA memory allocated for the transmit descriptors of the ring.
1817 * The pointer to the configuration data to be used for the transmit queue.
1818 * NULL value is allowed, in which case default RX configuration
1820 * The *tx_conf* structure contains the following data:
1821 * - The *tx_thresh* structure with the values of the Prefetch, Host, and
1822 * Write-Back threshold registers of the transmit ring.
1823 * When setting Write-Back threshold to the value greater then zero,
1824 * *tx_rs_thresh* value should be explicitly set to one.
1825 * - The *tx_free_thresh* value indicates the [minimum] number of network
1826 * buffers that must be pending in the transmit ring to trigger their
1827 * [implicit] freeing by the driver transmit function.
1828 * - The *tx_rs_thresh* value indicates the [minimum] number of transmit
1829 * descriptors that must be pending in the transmit ring before setting the
1830 * RS bit on a descriptor by the driver transmit function.
1831 * The *tx_rs_thresh* value should be less or equal then
1832 * *tx_free_thresh* value, and both of them should be less then
1834 * - The *txq_flags* member contains flags to pass to the TX queue setup
1835 * function to configure the behavior of the TX queue. This should be set
1836 * to 0 if no special configuration is required.
1838 * Note that setting *tx_free_thresh* or *tx_rs_thresh* value to 0 forces
1839 * the transmit function to use default values.
1841 * - 0: Success, the transmit queue is correctly set up.
1842 * - -ENOMEM: Unable to allocate the transmit ring descriptors.
1844 extern int rte_eth_tx_queue_setup(uint8_t port_id, uint16_t tx_queue_id,
1845 uint16_t nb_tx_desc, unsigned int socket_id,
1846 const struct rte_eth_txconf *tx_conf);
1849 * Return the NUMA socket to which an Ethernet device is connected
1852 * The port identifier of the Ethernet device
1854 * The NUMA socket id to which the Ethernet device is connected or
1855 * a default of zero if the socket could not be determined.
1856 * -1 is returned is the port_id value is out of range.
1858 extern int rte_eth_dev_socket_id(uint8_t port_id);
1861 * Allocate mbuf from mempool, setup the DMA physical address
1862 * and then start RX for specified queue of a port. It is used
1863 * when rx_deferred_start flag of the specified queue is true.
1866 * The port identifier of the Ethernet device
1867 * @param rx_queue_id
1868 * The index of the rx queue to update the ring.
1869 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1870 * to rte_eth_dev_configure().
1872 * - 0: Success, the transmit queue is correctly set up.
1873 * - -EINVAL: The port_id or the queue_id out of range.
1874 * - -ENOTSUP: The function not supported in PMD driver.
1876 extern int rte_eth_dev_rx_queue_start(uint8_t port_id, uint16_t rx_queue_id);
1879 * Stop specified RX queue of a port
1882 * The port identifier of the Ethernet device
1883 * @param rx_queue_id
1884 * The index of the rx queue to update the ring.
1885 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1886 * to rte_eth_dev_configure().
1888 * - 0: Success, the transmit queue is correctly set up.
1889 * - -EINVAL: The port_id or the queue_id out of range.
1890 * - -ENOTSUP: The function not supported in PMD driver.
1892 extern int rte_eth_dev_rx_queue_stop(uint8_t port_id, uint16_t rx_queue_id);
1895 * Start TX for specified queue of a port. It is used when tx_deferred_start
1896 * flag of the specified queue is true.
1899 * The port identifier of the Ethernet device
1900 * @param tx_queue_id
1901 * The index of the tx queue to update the ring.
1902 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1903 * to rte_eth_dev_configure().
1905 * - 0: Success, the transmit queue is correctly set up.
1906 * - -EINVAL: The port_id or the queue_id out of range.
1907 * - -ENOTSUP: The function not supported in PMD driver.
1909 extern int rte_eth_dev_tx_queue_start(uint8_t port_id, uint16_t tx_queue_id);
1912 * Stop specified TX queue of a port
1915 * The port identifier of the Ethernet device
1916 * @param tx_queue_id
1917 * The index of the tx queue to update the ring.
1918 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1919 * to rte_eth_dev_configure().
1921 * - 0: Success, the transmit queue is correctly set up.
1922 * - -EINVAL: The port_id or the queue_id out of range.
1923 * - -ENOTSUP: The function not supported in PMD driver.
1925 extern int rte_eth_dev_tx_queue_stop(uint8_t port_id, uint16_t tx_queue_id);
1930 * Start an Ethernet device.
1932 * The device start step is the last one and consists of setting the configured
1933 * offload features and in starting the transmit and the receive units of the
1935 * On success, all basic functions exported by the Ethernet API (link status,
1936 * receive/transmit, and so on) can be invoked.
1939 * The port identifier of the Ethernet device.
1941 * - 0: Success, Ethernet device started.
1942 * - <0: Error code of the driver device start function.
1944 extern int rte_eth_dev_start(uint8_t port_id);
1947 * Stop an Ethernet device. The device can be restarted with a call to
1948 * rte_eth_dev_start()
1951 * The port identifier of the Ethernet device.
1953 extern void rte_eth_dev_stop(uint8_t port_id);
1957 * Link up an Ethernet device.
1959 * Set device link up will re-enable the device rx/tx
1960 * functionality after it is previously set device linked down.
1963 * The port identifier of the Ethernet device.
1965 * - 0: Success, Ethernet device linked up.
1966 * - <0: Error code of the driver device link up function.
1968 extern int rte_eth_dev_set_link_up(uint8_t port_id);
1971 * Link down an Ethernet device.
1972 * The device rx/tx functionality will be disabled if success,
1973 * and it can be re-enabled with a call to
1974 * rte_eth_dev_set_link_up()
1977 * The port identifier of the Ethernet device.
1979 extern int rte_eth_dev_set_link_down(uint8_t port_id);
1982 * Close an Ethernet device. The device cannot be restarted!
1985 * The port identifier of the Ethernet device.
1987 extern void rte_eth_dev_close(uint8_t port_id);
1990 * Enable receipt in promiscuous mode for an Ethernet device.
1993 * The port identifier of the Ethernet device.
1995 extern void rte_eth_promiscuous_enable(uint8_t port_id);
1998 * Disable receipt in promiscuous mode for an Ethernet device.
2001 * The port identifier of the Ethernet device.
2003 extern void rte_eth_promiscuous_disable(uint8_t port_id);
2006 * Return the value of promiscuous mode for an Ethernet device.
2009 * The port identifier of the Ethernet device.
2011 * - (1) if promiscuous is enabled
2012 * - (0) if promiscuous is disabled.
2015 extern int rte_eth_promiscuous_get(uint8_t port_id);
2018 * Enable the receipt of any multicast frame by an Ethernet device.
2021 * The port identifier of the Ethernet device.
2023 extern void rte_eth_allmulticast_enable(uint8_t port_id);
2026 * Disable the receipt of all multicast frames by an Ethernet device.
2029 * The port identifier of the Ethernet device.
2031 extern void rte_eth_allmulticast_disable(uint8_t port_id);
2034 * Return the value of allmulticast mode for an Ethernet device.
2037 * The port identifier of the Ethernet device.
2039 * - (1) if allmulticast is enabled
2040 * - (0) if allmulticast is disabled.
2043 extern int rte_eth_allmulticast_get(uint8_t port_id);
2046 * Retrieve the status (ON/OFF), the speed (in Mbps) and the mode (HALF-DUPLEX
2047 * or FULL-DUPLEX) of the physical link of an Ethernet device. It might need
2048 * to wait up to 9 seconds in it.
2051 * The port identifier of the Ethernet device.
2053 * A pointer to an *rte_eth_link* structure to be filled with
2054 * the status, the speed and the mode of the Ethernet device link.
2056 extern void rte_eth_link_get(uint8_t port_id, struct rte_eth_link *link);
2059 * Retrieve the status (ON/OFF), the speed (in Mbps) and the mode (HALF-DUPLEX
2060 * or FULL-DUPLEX) of the physical link of an Ethernet device. It is a no-wait
2061 * version of rte_eth_link_get().
2064 * The port identifier of the Ethernet device.
2066 * A pointer to an *rte_eth_link* structure to be filled with
2067 * the status, the speed and the mode of the Ethernet device link.
2069 extern void rte_eth_link_get_nowait(uint8_t port_id,
2070 struct rte_eth_link *link);
2073 * Retrieve the general I/O statistics of an Ethernet device.
2076 * The port identifier of the Ethernet device.
2078 * A pointer to a structure of type *rte_eth_stats* to be filled with
2079 * the values of device counters for the following set of statistics:
2080 * - *ipackets* with the total of successfully received packets.
2081 * - *opackets* with the total of successfully transmitted packets.
2082 * - *ibytes* with the total of successfully received bytes.
2083 * - *obytes* with the total of successfully transmitted bytes.
2084 * - *ierrors* with the total of erroneous received packets.
2085 * - *oerrors* with the total of failed transmitted packets.
2087 * Zero if successful. Non-zero otherwise.
2089 extern int rte_eth_stats_get(uint8_t port_id, struct rte_eth_stats *stats);
2092 * Reset the general I/O statistics of an Ethernet device.
2095 * The port identifier of the Ethernet device.
2097 extern void rte_eth_stats_reset(uint8_t port_id);
2100 * Retrieve extended statistics of an Ethernet device.
2103 * The port identifier of the Ethernet device.
2105 * A pointer to a table of structure of type *rte_eth_xstats*
2106 * to be filled with device statistics names and values.
2107 * This parameter can be set to NULL if n is 0.
2109 * The size of the stats table, which should be large enough to store
2110 * all the statistics of the device.
2112 * - positive value lower or equal to n: success. The return value
2113 * is the number of entries filled in the stats table.
2114 * - positive value higher than n: error, the given statistics table
2115 * is too small. The return value corresponds to the size that should
2116 * be given to succeed. The entries in the table are not valid and
2117 * shall not be used by the caller.
2118 * - negative value on error (invalid port id)
2120 extern int rte_eth_xstats_get(uint8_t port_id,
2121 struct rte_eth_xstats *xstats, unsigned n);
2124 * Reset extended statistics of an Ethernet device.
2127 * The port identifier of the Ethernet device.
2129 extern void rte_eth_xstats_reset(uint8_t port_id);
2132 * Set a mapping for the specified transmit queue to the specified per-queue
2133 * statistics counter.
2136 * The port identifier of the Ethernet device.
2137 * @param tx_queue_id
2138 * The index of the transmit queue for which a queue stats mapping is required.
2139 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
2140 * to rte_eth_dev_configure().
2142 * The per-queue packet statistics functionality number that the transmit
2143 * queue is to be assigned.
2144 * The value must be in the range [0, RTE_MAX_ETHPORT_QUEUE_STATS_MAPS - 1].
2146 * Zero if successful. Non-zero otherwise.
2148 extern int rte_eth_dev_set_tx_queue_stats_mapping(uint8_t port_id,
2149 uint16_t tx_queue_id,
2153 * Set a mapping for the specified receive queue to the specified per-queue
2154 * statistics counter.
2157 * The port identifier of the Ethernet device.
2158 * @param rx_queue_id
2159 * The index of the receive queue for which a queue stats mapping is required.
2160 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2161 * to rte_eth_dev_configure().
2163 * The per-queue packet statistics functionality number that the receive
2164 * queue is to be assigned.
2165 * The value must be in the range [0, RTE_MAX_ETHPORT_QUEUE_STATS_MAPS - 1].
2167 * Zero if successful. Non-zero otherwise.
2169 extern int rte_eth_dev_set_rx_queue_stats_mapping(uint8_t port_id,
2170 uint16_t rx_queue_id,
2174 * Retrieve the Ethernet address of an Ethernet device.
2177 * The port identifier of the Ethernet device.
2179 * A pointer to a structure of type *ether_addr* to be filled with
2180 * the Ethernet address of the Ethernet device.
2182 extern void rte_eth_macaddr_get(uint8_t port_id, struct ether_addr *mac_addr);
2185 * Retrieve the contextual information of an Ethernet device.
2188 * The port identifier of the Ethernet device.
2190 * A pointer to a structure of type *rte_eth_dev_info* to be filled with
2191 * the contextual information of the Ethernet device.
2193 extern void rte_eth_dev_info_get(uint8_t port_id,
2194 struct rte_eth_dev_info *dev_info);
2197 * Retrieve the MTU of an Ethernet device.
2200 * The port identifier of the Ethernet device.
2202 * A pointer to a uint16_t where the retrieved MTU is to be stored.
2204 * - (0) if successful.
2205 * - (-ENODEV) if *port_id* invalid.
2207 extern int rte_eth_dev_get_mtu(uint8_t port_id, uint16_t *mtu);
2210 * Change the MTU of an Ethernet device.
2213 * The port identifier of the Ethernet device.
2215 * A uint16_t for the MTU to be applied.
2217 * - (0) if successful.
2218 * - (-ENOTSUP) if operation is not supported.
2219 * - (-ENODEV) if *port_id* invalid.
2220 * - (-EINVAL) if *mtu* invalid.
2222 extern int rte_eth_dev_set_mtu(uint8_t port_id, uint16_t mtu);
2225 * Enable/Disable hardware filtering by an Ethernet device of received
2226 * VLAN packets tagged with a given VLAN Tag Identifier.
2229 * The port identifier of the Ethernet device.
2231 * The VLAN Tag Identifier whose filtering must be enabled or disabled.
2233 * If > 0, enable VLAN filtering of VLAN packets tagged with *vlan_id*.
2234 * Otherwise, disable VLAN filtering of VLAN packets tagged with *vlan_id*.
2236 * - (0) if successful.
2237 * - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
2238 * - (-ENODEV) if *port_id* invalid.
2239 * - (-ENOSYS) if VLAN filtering on *port_id* disabled.
2240 * - (-EINVAL) if *vlan_id* > 4095.
2242 extern int rte_eth_dev_vlan_filter(uint8_t port_id, uint16_t vlan_id , int on);
2245 * Enable/Disable hardware VLAN Strip by a rx queue of an Ethernet device.
2246 * 82599/X540/X550 can support VLAN stripping at the rx queue level
2249 * The port identifier of the Ethernet device.
2250 * @param rx_queue_id
2251 * The index of the receive queue for which a queue stats mapping is required.
2252 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2253 * to rte_eth_dev_configure().
2255 * If 1, Enable VLAN Stripping of the receive queue of the Ethernet port.
2256 * If 0, Disable VLAN Stripping of the receive queue of the Ethernet port.
2258 * - (0) if successful.
2259 * - (-ENOSUP) if hardware-assisted VLAN stripping not configured.
2260 * - (-ENODEV) if *port_id* invalid.
2261 * - (-EINVAL) if *rx_queue_id* invalid.
2263 extern int rte_eth_dev_set_vlan_strip_on_queue(uint8_t port_id,
2264 uint16_t rx_queue_id, int on);
2267 * Set the Outer VLAN Ether Type by an Ethernet device, it can be inserted to
2268 * the VLAN Header. This is a register setup available on some Intel NIC, not
2269 * but all, please check the data sheet for availability.
2272 * The port identifier of the Ethernet device.
2274 * The Tag Protocol ID
2276 * - (0) if successful.
2277 * - (-ENOSUP) if hardware-assisted VLAN TPID setup is not supported.
2278 * - (-ENODEV) if *port_id* invalid.
2280 extern int rte_eth_dev_set_vlan_ether_type(uint8_t port_id, uint16_t tag_type);
2283 * Set VLAN offload configuration on an Ethernet device
2284 * Enable/Disable Extended VLAN by an Ethernet device, This is a register setup
2285 * available on some Intel NIC, not but all, please check the data sheet for
2287 * Enable/Disable VLAN Strip can be done on rx queue for certain NIC, but here
2288 * the configuration is applied on the port level.
2291 * The port identifier of the Ethernet device.
2292 * @param offload_mask
2293 * The VLAN Offload bit mask can be mixed use with "OR"
2294 * ETH_VLAN_STRIP_OFFLOAD
2295 * ETH_VLAN_FILTER_OFFLOAD
2296 * ETH_VLAN_EXTEND_OFFLOAD
2298 * - (0) if successful.
2299 * - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
2300 * - (-ENODEV) if *port_id* invalid.
2302 extern int rte_eth_dev_set_vlan_offload(uint8_t port_id, int offload_mask);
2305 * Read VLAN Offload configuration from an Ethernet device
2308 * The port identifier of the Ethernet device.
2310 * - (>0) if successful. Bit mask to indicate
2311 * ETH_VLAN_STRIP_OFFLOAD
2312 * ETH_VLAN_FILTER_OFFLOAD
2313 * ETH_VLAN_EXTEND_OFFLOAD
2314 * - (-ENODEV) if *port_id* invalid.
2316 extern int rte_eth_dev_get_vlan_offload(uint8_t port_id);
2319 * Set port based TX VLAN insersion on or off.
2322 * The port identifier of the Ethernet device.
2324 * Port based TX VLAN identifier togeth with user priority.
2326 * Turn on or off the port based TX VLAN insertion.
2329 * - (0) if successful.
2330 * - negative if failed.
2332 extern int rte_eth_dev_set_vlan_pvid(uint8_t port_id, uint16_t pvid, int on);
2336 * Retrieve a burst of input packets from a receive queue of an Ethernet
2337 * device. The retrieved packets are stored in *rte_mbuf* structures whose
2338 * pointers are supplied in the *rx_pkts* array.
2340 * The rte_eth_rx_burst() function loops, parsing the RX ring of the
2341 * receive queue, up to *nb_pkts* packets, and for each completed RX
2342 * descriptor in the ring, it performs the following operations:
2344 * - Initialize the *rte_mbuf* data structure associated with the
2345 * RX descriptor according to the information provided by the NIC into
2346 * that RX descriptor.
2348 * - Store the *rte_mbuf* data structure into the next entry of the
2351 * - Replenish the RX descriptor with a new *rte_mbuf* buffer
2352 * allocated from the memory pool associated with the receive queue at
2353 * initialization time.
2355 * When retrieving an input packet that was scattered by the controller
2356 * into multiple receive descriptors, the rte_eth_rx_burst() function
2357 * appends the associated *rte_mbuf* buffers to the first buffer of the
2360 * The rte_eth_rx_burst() function returns the number of packets
2361 * actually retrieved, which is the number of *rte_mbuf* data structures
2362 * effectively supplied into the *rx_pkts* array.
2363 * A return value equal to *nb_pkts* indicates that the RX queue contained
2364 * at least *rx_pkts* packets, and this is likely to signify that other
2365 * received packets remain in the input queue. Applications implementing
2366 * a "retrieve as much received packets as possible" policy can check this
2367 * specific case and keep invoking the rte_eth_rx_burst() function until
2368 * a value less than *nb_pkts* is returned.
2370 * This receive method has the following advantages:
2372 * - It allows a run-to-completion network stack engine to retrieve and
2373 * to immediately process received packets in a fast burst-oriented
2374 * approach, avoiding the overhead of unnecessary intermediate packet
2375 * queue/dequeue operations.
2377 * - Conversely, it also allows an asynchronous-oriented processing
2378 * method to retrieve bursts of received packets and to immediately
2379 * queue them for further parallel processing by another logical core,
2380 * for instance. However, instead of having received packets being
2381 * individually queued by the driver, this approach allows the invoker
2382 * of the rte_eth_rx_burst() function to queue a burst of retrieved
2383 * packets at a time and therefore dramatically reduce the cost of
2384 * enqueue/dequeue operations per packet.
2386 * - It allows the rte_eth_rx_burst() function of the driver to take
2387 * advantage of burst-oriented hardware features (CPU cache,
2388 * prefetch instructions, and so on) to minimize the number of CPU
2389 * cycles per packet.
2391 * To summarize, the proposed receive API enables many
2392 * burst-oriented optimizations in both synchronous and asynchronous
2393 * packet processing environments with no overhead in both cases.
2395 * The rte_eth_rx_burst() function does not provide any error
2396 * notification to avoid the corresponding overhead. As a hint, the
2397 * upper-level application might check the status of the device link once
2398 * being systematically returned a 0 value for a given number of tries.
2401 * The port identifier of the Ethernet device.
2403 * The index of the receive queue from which to retrieve input packets.
2404 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2405 * to rte_eth_dev_configure().
2407 * The address of an array of pointers to *rte_mbuf* structures that
2408 * must be large enough to store *nb_pkts* pointers in it.
2410 * The maximum number of packets to retrieve.
2412 * The number of packets actually retrieved, which is the number
2413 * of pointers to *rte_mbuf* structures effectively supplied to the
2416 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2417 extern uint16_t rte_eth_rx_burst(uint8_t port_id, uint16_t queue_id,
2418 struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
2420 static inline uint16_t
2421 rte_eth_rx_burst(uint8_t port_id, uint16_t queue_id,
2422 struct rte_mbuf **rx_pkts, const uint16_t nb_pkts)
2424 struct rte_eth_dev *dev;
2426 dev = &rte_eth_devices[port_id];
2428 int16_t nb_rx = (*dev->rx_pkt_burst)(dev->data->rx_queues[queue_id],
2431 #ifdef RTE_ETHDEV_RXTX_CALLBACKS
2432 struct rte_eth_rxtx_callback *cb = dev->post_rx_burst_cbs[queue_id];
2434 if (unlikely(cb != NULL)) {
2436 nb_rx = cb->fn.rx(port_id, queue_id, rx_pkts, nb_rx,
2437 nb_pkts, cb->param);
2439 } while (cb != NULL);
2448 * Get the number of used descriptors in a specific queue
2451 * The port identifier of the Ethernet device.
2453 * The queue id on the specific port.
2455 * The number of used descriptors in the specific queue.
2457 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2458 extern uint32_t rte_eth_rx_queue_count(uint8_t port_id, uint16_t queue_id);
2460 static inline uint32_t
2461 rte_eth_rx_queue_count(uint8_t port_id, uint16_t queue_id)
2463 struct rte_eth_dev *dev;
2465 dev = &rte_eth_devices[port_id];
2466 return (*dev->dev_ops->rx_queue_count)(dev, queue_id);
2471 * Check if the DD bit of the specific RX descriptor in the queue has been set
2474 * The port identifier of the Ethernet device.
2476 * The queue id on the specific port.
2478 * The offset of the descriptor ID from tail.
2480 * - (1) if the specific DD bit is set.
2481 * - (0) if the specific DD bit is not set.
2482 * - (-ENODEV) if *port_id* invalid.
2484 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2485 extern int rte_eth_rx_descriptor_done(uint8_t port_id,
2490 rte_eth_rx_descriptor_done(uint8_t port_id, uint16_t queue_id, uint16_t offset)
2492 struct rte_eth_dev *dev;
2494 dev = &rte_eth_devices[port_id];
2495 return (*dev->dev_ops->rx_descriptor_done)( \
2496 dev->data->rx_queues[queue_id], offset);
2501 * Send a burst of output packets on a transmit queue of an Ethernet device.
2503 * The rte_eth_tx_burst() function is invoked to transmit output packets
2504 * on the output queue *queue_id* of the Ethernet device designated by its
2506 * The *nb_pkts* parameter is the number of packets to send which are
2507 * supplied in the *tx_pkts* array of *rte_mbuf* structures.
2508 * The rte_eth_tx_burst() function loops, sending *nb_pkts* packets,
2509 * up to the number of transmit descriptors available in the TX ring of the
2511 * For each packet to send, the rte_eth_tx_burst() function performs
2512 * the following operations:
2514 * - Pick up the next available descriptor in the transmit ring.
2516 * - Free the network buffer previously sent with that descriptor, if any.
2518 * - Initialize the transmit descriptor with the information provided
2519 * in the *rte_mbuf data structure.
2521 * In the case of a segmented packet composed of a list of *rte_mbuf* buffers,
2522 * the rte_eth_tx_burst() function uses several transmit descriptors
2525 * The rte_eth_tx_burst() function returns the number of packets it
2526 * actually sent. A return value equal to *nb_pkts* means that all packets
2527 * have been sent, and this is likely to signify that other output packets
2528 * could be immediately transmitted again. Applications that implement a
2529 * "send as many packets to transmit as possible" policy can check this
2530 * specific case and keep invoking the rte_eth_tx_burst() function until
2531 * a value less than *nb_pkts* is returned.
2533 * It is the responsibility of the rte_eth_tx_burst() function to
2534 * transparently free the memory buffers of packets previously sent.
2535 * This feature is driven by the *tx_free_thresh* value supplied to the
2536 * rte_eth_dev_configure() function at device configuration time.
2537 * When the number of previously sent packets reached the "minimum transmit
2538 * packets to free" threshold, the rte_eth_tx_burst() function must
2539 * [attempt to] free the *rte_mbuf* buffers of those packets whose
2540 * transmission was effectively completed.
2543 * The port identifier of the Ethernet device.
2545 * The index of the transmit queue through which output packets must be
2547 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
2548 * to rte_eth_dev_configure().
2550 * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures
2551 * which contain the output packets.
2553 * The maximum number of packets to transmit.
2555 * The number of output packets actually stored in transmit descriptors of
2556 * the transmit ring. The return value can be less than the value of the
2557 * *tx_pkts* parameter when the transmit ring is full or has been filled up.
2559 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2560 extern uint16_t rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id,
2561 struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
2563 static inline uint16_t
2564 rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id,
2565 struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
2567 struct rte_eth_dev *dev;
2569 dev = &rte_eth_devices[port_id];
2571 #ifdef RTE_ETHDEV_RXTX_CALLBACKS
2572 struct rte_eth_rxtx_callback *cb = dev->pre_tx_burst_cbs[queue_id];
2574 if (unlikely(cb != NULL)) {
2576 nb_pkts = cb->fn.tx(port_id, queue_id, tx_pkts, nb_pkts,
2579 } while (cb != NULL);
2583 return (*dev->tx_pkt_burst)(dev->data->tx_queues[queue_id], tx_pkts, nb_pkts);
2588 * Setup a new signature filter rule on an Ethernet device
2591 * The port identifier of the Ethernet device.
2592 * @param fdir_filter
2593 * The pointer to the fdir filter structure describing the signature filter
2595 * The *rte_fdir_filter* structure includes the values of the different fields
2596 * to match: source and destination IP addresses, vlan id, flexbytes, source
2597 * and destination ports, and so on.
2599 * The index of the RX queue where to store RX packets matching the added
2600 * signature filter defined in fdir_filter.
2602 * - (0) if successful.
2603 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2604 * - (-ENODEV) if *port_id* invalid.
2605 * - (-ENOSYS) if the FDIR mode is not configured in signature mode
2607 * - (-EINVAL) if the fdir_filter information is not correct.
2609 int rte_eth_dev_fdir_add_signature_filter(uint8_t port_id,
2610 struct rte_fdir_filter *fdir_filter,
2614 * Update a signature filter rule on an Ethernet device.
2615 * If the rule doesn't exits, it is created.
2618 * The port identifier of the Ethernet device.
2620 * The pointer to the structure describing the signature filter rule.
2621 * The *rte_fdir_filter* structure includes the values of the different fields
2622 * to match: source and destination IP addresses, vlan id, flexbytes, source
2623 * and destination ports, and so on.
2625 * The index of the RX queue where to store RX packets matching the added
2626 * signature filter defined in fdir_ftr.
2628 * - (0) if successful.
2629 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2630 * - (-ENODEV) if *port_id* invalid.
2631 * - (-ENOSYS) if the flow director mode is not configured in signature mode
2633 * - (-EINVAL) if the fdir_filter information is not correct.
2635 int rte_eth_dev_fdir_update_signature_filter(uint8_t port_id,
2636 struct rte_fdir_filter *fdir_ftr,
2640 * Remove a signature filter rule on an Ethernet device.
2643 * The port identifier of the Ethernet device.
2645 * The pointer to the structure describing the signature filter rule.
2646 * The *rte_fdir_filter* structure includes the values of the different fields
2647 * to match: source and destination IP addresses, vlan id, flexbytes, source
2648 * and destination ports, and so on.
2650 * - (0) if successful.
2651 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2652 * - (-ENODEV) if *port_id* invalid.
2653 * - (-ENOSYS) if the flow director mode is not configured in signature mode
2655 * - (-EINVAL) if the fdir_filter information is not correct.
2657 int rte_eth_dev_fdir_remove_signature_filter(uint8_t port_id,
2658 struct rte_fdir_filter *fdir_ftr);
2661 * Retrieve the flow director information of an Ethernet device.
2664 * The port identifier of the Ethernet device.
2666 * A pointer to a structure of type *rte_eth_dev_fdir* to be filled with
2667 * the flow director information of the Ethernet device.
2669 * - (0) if successful.
2670 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2671 * - (-ENODEV) if *port_id* invalid.
2672 * - (-ENOSYS) if the flow director mode is not configured on *port_id*.
2674 int rte_eth_dev_fdir_get_infos(uint8_t port_id, struct rte_eth_fdir *fdir);
2677 * Add a new perfect filter rule on an Ethernet device.
2680 * The port identifier of the Ethernet device.
2681 * @param fdir_filter
2682 * The pointer to the structure describing the perfect filter rule.
2683 * The *rte_fdir_filter* structure includes the values of the different fields
2684 * to match: source and destination IP addresses, vlan id, flexbytes, source
2685 * and destination ports, and so on.
2686 * IPv6 are not supported.
2688 * The 16-bit value supplied in the field hash.fdir.id of mbuf for RX
2689 * packets matching the perfect filter.
2691 * The index of the RX queue where to store RX packets matching the added
2692 * perfect filter defined in fdir_filter.
2694 * If drop is set to 1, matching RX packets are stored into the RX drop
2695 * queue defined in the rte_fdir_conf.
2697 * - (0) if successful.
2698 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2699 * - (-ENODEV) if *port_id* invalid.
2700 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2702 * - (-EINVAL) if the fdir_filter information is not correct.
2704 int rte_eth_dev_fdir_add_perfect_filter(uint8_t port_id,
2705 struct rte_fdir_filter *fdir_filter,
2706 uint16_t soft_id, uint8_t rx_queue,
2710 * Update a perfect filter rule on an Ethernet device.
2711 * If the rule doesn't exits, it is created.
2714 * The port identifier of the Ethernet device.
2715 * @param fdir_filter
2716 * The pointer to the structure describing the perfect filter rule.
2717 * The *rte_fdir_filter* structure includes the values of the different fields
2718 * to match: source and destination IP addresses, vlan id, flexbytes, source
2719 * and destination ports, and so on.
2720 * IPv6 are not supported.
2722 * The 16-bit value supplied in the field hash.fdir.id of mbuf for RX
2723 * packets matching the perfect filter.
2725 * The index of the RX queue where to store RX packets matching the added
2726 * perfect filter defined in fdir_filter.
2728 * If drop is set to 1, matching RX packets are stored into the RX drop
2729 * queue defined in the rte_fdir_conf.
2731 * - (0) if successful.
2732 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2733 * - (-ENODEV) if *port_id* invalid.
2734 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2736 * - (-EINVAL) if the fdir_filter information is not correct.
2738 int rte_eth_dev_fdir_update_perfect_filter(uint8_t port_id,
2739 struct rte_fdir_filter *fdir_filter,
2740 uint16_t soft_id, uint8_t rx_queue,
2744 * Remove a perfect filter rule on an Ethernet device.
2747 * The port identifier of the Ethernet device.
2748 * @param fdir_filter
2749 * The pointer to the structure describing the perfect filter rule.
2750 * The *rte_fdir_filter* structure includes the values of the different fields
2751 * to match: source and destination IP addresses, vlan id, flexbytes, source
2752 * and destination ports, and so on.
2753 * IPv6 are not supported.
2755 * The soft_id value provided when adding/updating the removed filter.
2757 * - (0) if successful.
2758 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2759 * - (-ENODEV) if *port_id* invalid.
2760 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2762 * - (-EINVAL) if the fdir_filter information is not correct.
2764 int rte_eth_dev_fdir_remove_perfect_filter(uint8_t port_id,
2765 struct rte_fdir_filter *fdir_filter,
2768 * Configure globally the masks for flow director mode for an Ethernet device.
2769 * For example, the device can match packets with only the first 24 bits of
2770 * the IPv4 source address.
2772 * The following fields can be masked: IPv4 addresses and L4 port numbers.
2773 * The following fields can be either enabled or disabled completely for the
2774 * matching functionality: VLAN ID tag; VLAN Priority + CFI bit; Flexible 2-byte
2776 * IPv6 masks are not supported.
2778 * All filters must comply with the masks previously configured.
2779 * For example, with a mask equal to 255.255.255.0 for the source IPv4 address,
2780 * all IPv4 filters must be created with a source IPv4 address that fits the
2783 * This function flushes all filters that have been previously added in
2787 * The port identifier of the Ethernet device.
2789 * The pointer to the fdir mask structure describing relevant headers fields
2790 * and relevant bits to use when matching packets addresses and ports.
2791 * IPv6 masks are not supported.
2793 * - (0) if successful.
2794 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2795 * - (-ENODEV) if *port_id* invalid.
2796 * - (-ENOSYS) if the flow director mode is not configured in perfect
2797 * mode on *port_id*.
2798 * - (-EINVAL) if the fdir_filter information is not correct
2800 int rte_eth_dev_fdir_set_masks(uint8_t port_id,
2801 struct rte_fdir_masks *fdir_mask);
2804 * The eth device event type for interrupt, and maybe others in the future.
2806 enum rte_eth_event_type {
2807 RTE_ETH_EVENT_UNKNOWN, /**< unknown event type */
2808 RTE_ETH_EVENT_INTR_LSC, /**< lsc interrupt event */
2809 RTE_ETH_EVENT_MAX /**< max value of this enum */
2812 typedef void (*rte_eth_dev_cb_fn)(uint8_t port_id, \
2813 enum rte_eth_event_type event, void *cb_arg);
2814 /**< user application callback to be registered for interrupts */
2819 * Register a callback function for specific port id.
2826 * User supplied callback function to be called.
2828 * Pointer to the parameters for the registered callback.
2831 * - On success, zero.
2832 * - On failure, a negative value.
2834 int rte_eth_dev_callback_register(uint8_t port_id,
2835 enum rte_eth_event_type event,
2836 rte_eth_dev_cb_fn cb_fn, void *cb_arg);
2839 * Unregister a callback function for specific port id.
2846 * User supplied callback function to be called.
2848 * Pointer to the parameters for the registered callback. -1 means to
2849 * remove all for the same callback address and same event.
2852 * - On success, zero.
2853 * - On failure, a negative value.
2855 int rte_eth_dev_callback_unregister(uint8_t port_id,
2856 enum rte_eth_event_type event,
2857 rte_eth_dev_cb_fn cb_fn, void *cb_arg);
2860 * @internal Executes all the user application registered callbacks for
2861 * the specific device. It is for DPDK internal user only. User
2862 * application should not call it directly.
2865 * Pointer to struct rte_eth_dev.
2867 * Eth device interrupt event type.
2872 void _rte_eth_dev_callback_process(struct rte_eth_dev *dev,
2873 enum rte_eth_event_type event);
2876 * Turn on the LED on the Ethernet device.
2877 * This function turns on the LED on the Ethernet device.
2880 * The port identifier of the Ethernet device.
2882 * - (0) if successful.
2883 * - (-ENOTSUP) if underlying hardware OR driver doesn't support
2885 * - (-ENODEV) if *port_id* invalid.
2887 int rte_eth_led_on(uint8_t port_id);
2890 * Turn off the LED on the Ethernet device.
2891 * This function turns off the LED on the Ethernet device.
2894 * The port identifier of the Ethernet device.
2896 * - (0) if successful.
2897 * - (-ENOTSUP) if underlying hardware OR driver doesn't support
2899 * - (-ENODEV) if *port_id* invalid.
2901 int rte_eth_led_off(uint8_t port_id);
2904 * Get current status of the Ethernet link flow control for Ethernet device
2907 * The port identifier of the Ethernet device.
2909 * The pointer to the structure where to store the flow control parameters.
2911 * - (0) if successful.
2912 * - (-ENOTSUP) if hardware doesn't support flow control.
2913 * - (-ENODEV) if *port_id* invalid.
2915 int rte_eth_dev_flow_ctrl_get(uint8_t port_id,
2916 struct rte_eth_fc_conf *fc_conf);
2919 * Configure the Ethernet link flow control for Ethernet device
2922 * The port identifier of the Ethernet device.
2924 * The pointer to the structure of the flow control parameters.
2926 * - (0) if successful.
2927 * - (-ENOTSUP) if hardware doesn't support flow control mode.
2928 * - (-ENODEV) if *port_id* invalid.
2929 * - (-EINVAL) if bad parameter
2930 * - (-EIO) if flow control setup failure
2932 int rte_eth_dev_flow_ctrl_set(uint8_t port_id,
2933 struct rte_eth_fc_conf *fc_conf);
2936 * Configure the Ethernet priority flow control under DCB environment
2937 * for Ethernet device.
2940 * The port identifier of the Ethernet device.
2942 * The pointer to the structure of the priority flow control parameters.
2944 * - (0) if successful.
2945 * - (-ENOTSUP) if hardware doesn't support priority flow control mode.
2946 * - (-ENODEV) if *port_id* invalid.
2947 * - (-EINVAL) if bad parameter
2948 * - (-EIO) if flow control setup failure
2950 int rte_eth_dev_priority_flow_ctrl_set(uint8_t port_id,
2951 struct rte_eth_pfc_conf *pfc_conf);
2954 * Add a MAC address to an internal array of addresses used to enable whitelist
2955 * filtering to accept packets only if the destination MAC address matches.
2958 * The port identifier of the Ethernet device.
2960 * The MAC address to add.
2962 * VMDq pool index to associate address with (if VMDq is enabled). If VMDq is
2963 * not enabled, this should be set to 0.
2965 * - (0) if successfully added or *mac_addr" was already added.
2966 * - (-ENOTSUP) if hardware doesn't support this feature.
2967 * - (-ENODEV) if *port* is invalid.
2968 * - (-ENOSPC) if no more MAC addresses can be added.
2969 * - (-EINVAL) if MAC address is invalid.
2971 int rte_eth_dev_mac_addr_add(uint8_t port, struct ether_addr *mac_addr,
2975 * Remove a MAC address from the internal array of addresses.
2978 * The port identifier of the Ethernet device.
2980 * MAC address to remove.
2982 * - (0) if successful, or *mac_addr* didn't exist.
2983 * - (-ENOTSUP) if hardware doesn't support.
2984 * - (-ENODEV) if *port* invalid.
2985 * - (-EADDRINUSE) if attempting to remove the default MAC address
2987 int rte_eth_dev_mac_addr_remove(uint8_t port, struct ether_addr *mac_addr);
2990 * Update Redirection Table(RETA) of Receive Side Scaling of Ethernet device.
2993 * The port identifier of the Ethernet device.
2997 * Redirection table size. The table size can be queried by
2998 * rte_eth_dev_info_get().
3000 * - (0) if successful.
3001 * - (-ENOTSUP) if hardware doesn't support.
3002 * - (-EINVAL) if bad parameter.
3004 int rte_eth_dev_rss_reta_update(uint8_t port,
3005 struct rte_eth_rss_reta_entry64 *reta_conf,
3006 uint16_t reta_size);
3009 * Query Redirection Table(RETA) of Receive Side Scaling of Ethernet device.
3012 * The port identifier of the Ethernet device.
3016 * Redirection table size. The table size can be queried by
3017 * rte_eth_dev_info_get().
3019 * - (0) if successful.
3020 * - (-ENOTSUP) if hardware doesn't support.
3021 * - (-EINVAL) if bad parameter.
3023 int rte_eth_dev_rss_reta_query(uint8_t port,
3024 struct rte_eth_rss_reta_entry64 *reta_conf,
3025 uint16_t reta_size);
3028 * Updates unicast hash table for receiving packet with the given destination
3029 * MAC address, and the packet is routed to all VFs for which the RX mode is
3030 * accept packets that match the unicast hash table.
3033 * The port identifier of the Ethernet device.
3035 * Unicast MAC address.
3037 * 1 - Set an unicast hash bit for receiving packets with the MAC address.
3038 * 0 - Clear an unicast hash bit.
3040 * - (0) if successful.
3041 * - (-ENOTSUP) if hardware doesn't support.
3042 * - (-ENODEV) if *port_id* invalid.
3043 * - (-EINVAL) if bad parameter.
3045 int rte_eth_dev_uc_hash_table_set(uint8_t port,struct ether_addr *addr,
3049 * Updates all unicast hash bitmaps for receiving packet with any Unicast
3050 * Ethernet MAC addresses,the packet is routed to all VFs for which the RX
3051 * mode is accept packets that match the unicast hash table.
3054 * The port identifier of the Ethernet device.
3056 * 1 - Set all unicast hash bitmaps for receiving all the Ethernet
3058 * 0 - Clear all unicast hash bitmaps
3060 * - (0) if successful.
3061 * - (-ENOTSUP) if hardware doesn't support.
3062 * - (-ENODEV) if *port_id* invalid.
3063 * - (-EINVAL) if bad parameter.
3065 int rte_eth_dev_uc_all_hash_table_set(uint8_t port,uint8_t on);
3068 * Set RX L2 Filtering mode of a VF of an Ethernet device.
3071 * The port identifier of the Ethernet device.
3075 * The RX mode mask, which is one or more of accepting Untagged Packets,
3076 * packets that match the PFUTA table, Broadcast and Multicast Promiscuous.
3077 * ETH_VMDQ_ACCEPT_UNTAG,ETH_VMDQ_ACCEPT_HASH_UC,
3078 * ETH_VMDQ_ACCEPT_BROADCAST and ETH_VMDQ_ACCEPT_MULTICAST will be used
3081 * 1 - Enable a VF RX mode.
3082 * 0 - Disable a VF RX mode.
3084 * - (0) if successful.
3085 * - (-ENOTSUP) if hardware doesn't support.
3086 * - (-ENOTSUP) if hardware doesn't support.
3087 * - (-EINVAL) if bad parameter.
3089 int rte_eth_dev_set_vf_rxmode(uint8_t port, uint16_t vf, uint16_t rx_mode,
3093 * Enable or disable a VF traffic transmit of the Ethernet device.
3096 * The port identifier of the Ethernet device.
3100 * 1 - Enable a VF traffic transmit.
3101 * 0 - Disable a VF traffic transmit.
3103 * - (0) if successful.
3104 * - (-ENODEV) if *port_id* invalid.
3105 * - (-ENOTSUP) if hardware doesn't support.
3106 * - (-EINVAL) if bad parameter.
3109 rte_eth_dev_set_vf_tx(uint8_t port,uint16_t vf, uint8_t on);
3112 * Enable or disable a VF traffic receive of an Ethernet device.
3115 * The port identifier of the Ethernet device.
3119 * 1 - Enable a VF traffic receive.
3120 * 0 - Disable a VF traffic receive.
3122 * - (0) if successful.
3123 * - (-ENOTSUP) if hardware doesn't support.
3124 * - (-ENODEV) if *port_id* invalid.
3125 * - (-EINVAL) if bad parameter.
3128 rte_eth_dev_set_vf_rx(uint8_t port,uint16_t vf, uint8_t on);
3131 * Enable/Disable hardware VF VLAN filtering by an Ethernet device of
3132 * received VLAN packets tagged with a given VLAN Tag Identifier.
3135 * The port identifier of the Ethernet device.
3137 * The VLAN Tag Identifier whose filtering must be enabled or disabled.
3139 * Bitmap listing which VFs participate in the VLAN filtering.
3141 * 1 - Enable VFs VLAN filtering.
3142 * 0 - Disable VFs VLAN filtering.
3144 * - (0) if successful.
3145 * - (-ENOTSUP) if hardware doesn't support.
3146 * - (-ENODEV) if *port_id* invalid.
3147 * - (-EINVAL) if bad parameter.
3150 rte_eth_dev_set_vf_vlan_filter(uint8_t port, uint16_t vlan_id,
3155 * Set a traffic mirroring rule on an Ethernet device
3158 * The port identifier of the Ethernet device.
3159 * @param mirror_conf
3160 * The pointer to the traffic mirroring structure describing the mirroring rule.
3161 * The *rte_eth_vm_mirror_conf* structure includes the type of mirroring rule,
3162 * destination pool and the value of rule if enable vlan or pool mirroring.
3165 * The index of traffic mirroring rule, we support four separated rules.
3167 * 1 - Enable a mirroring rule.
3168 * 0 - Disable a mirroring rule.
3170 * - (0) if successful.
3171 * - (-ENOTSUP) if hardware doesn't support this feature.
3172 * - (-ENODEV) if *port_id* invalid.
3173 * - (-EINVAL) if the mr_conf information is not correct.
3175 int rte_eth_mirror_rule_set(uint8_t port_id,
3176 struct rte_eth_vmdq_mirror_conf *mirror_conf,
3181 * Reset a traffic mirroring rule on an Ethernet device.
3184 * The port identifier of the Ethernet device.
3186 * The index of traffic mirroring rule, we support four separated rules.
3188 * - (0) if successful.
3189 * - (-ENOTSUP) if hardware doesn't support this feature.
3190 * - (-ENODEV) if *port_id* invalid.
3191 * - (-EINVAL) if bad parameter.
3193 int rte_eth_mirror_rule_reset(uint8_t port_id,
3197 * Set the rate limitation for a queue on an Ethernet device.
3200 * The port identifier of the Ethernet device.
3204 * The tx rate allocated from the total link speed for this queue.
3206 * - (0) if successful.
3207 * - (-ENOTSUP) if hardware doesn't support this feature.
3208 * - (-ENODEV) if *port_id* invalid.
3209 * - (-EINVAL) if bad parameter.
3211 int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx,
3215 * Set the rate limitation for a vf on an Ethernet device.
3218 * The port identifier of the Ethernet device.
3222 * The tx rate allocated from the total link speed for this VF id.
3224 * The queue mask which need to set the rate.
3226 * - (0) if successful.
3227 * - (-ENOTSUP) if hardware doesn't support this feature.
3228 * - (-ENODEV) if *port_id* invalid.
3229 * - (-EINVAL) if bad parameter.
3231 int rte_eth_set_vf_rate_limit(uint8_t port_id, uint16_t vf,
3232 uint16_t tx_rate, uint64_t q_msk);
3235 * Initialize bypass logic. This function needs to be called before
3236 * executing any other bypass API.
3239 * The port identifier of the Ethernet device.
3241 * - (0) if successful.
3242 * - (-ENOTSUP) if hardware doesn't support.
3243 * - (-EINVAL) if bad parameter.
3245 int rte_eth_dev_bypass_init(uint8_t port);
3248 * Return bypass state.
3251 * The port identifier of the Ethernet device.
3253 * The return bypass state.
3256 * - (3) Isolate mode
3258 * - (0) if successful.
3259 * - (-ENOTSUP) if hardware doesn't support.
3260 * - (-EINVAL) if bad parameter.
3262 int rte_eth_dev_bypass_state_show(uint8_t port, uint32_t *state);
3268 * The port identifier of the Ethernet device.
3270 * The current bypass state.
3273 * - (3) Isolate mode
3275 * - (0) if successful.
3276 * - (-ENOTSUP) if hardware doesn't support.
3277 * - (-EINVAL) if bad parameter.
3279 int rte_eth_dev_bypass_state_set(uint8_t port, uint32_t *new_state);
3282 * Return bypass state when given event occurs.
3285 * The port identifier of the Ethernet device.
3288 * - (1) Main power on (power button is pushed)
3289 * - (2) Auxiliary power on (power supply is being plugged)
3290 * - (3) Main power off (system shutdown and power supply is left plugged in)
3291 * - (4) Auxiliary power off (power supply is being unplugged)
3292 * - (5) Display or set the watchdog timer
3294 * The bypass state when given event occurred.
3297 * - (3) Isolate mode
3299 * - (0) if successful.
3300 * - (-ENOTSUP) if hardware doesn't support.
3301 * - (-EINVAL) if bad parameter.
3303 int rte_eth_dev_bypass_event_show(uint8_t port, uint32_t event, uint32_t *state);
3306 * Set bypass state when given event occurs.
3309 * The port identifier of the Ethernet device.
3312 * - (1) Main power on (power button is pushed)
3313 * - (2) Auxiliary power on (power supply is being plugged)
3314 * - (3) Main power off (system shutdown and power supply is left plugged in)
3315 * - (4) Auxiliary power off (power supply is being unplugged)
3316 * - (5) Display or set the watchdog timer
3318 * The assigned state when given event occurs.
3321 * - (3) Isolate mode
3323 * - (0) if successful.
3324 * - (-ENOTSUP) if hardware doesn't support.
3325 * - (-EINVAL) if bad parameter.
3327 int rte_eth_dev_bypass_event_store(uint8_t port, uint32_t event, uint32_t state);
3330 * Set bypass watchdog timeout count.
3333 * The port identifier of the Ethernet device.
3335 * The timeout to be set.
3336 * - (0) 0 seconds (timer is off)
3345 * - (0) if successful.
3346 * - (-ENOTSUP) if hardware doesn't support.
3347 * - (-EINVAL) if bad parameter.
3349 int rte_eth_dev_wd_timeout_store(uint8_t port, uint32_t timeout);
3352 * Get bypass firmware version.
3355 * The port identifier of the Ethernet device.
3357 * The firmware version
3359 * - (0) if successful.
3360 * - (-ENOTSUP) if hardware doesn't support.
3361 * - (-EINVAL) if bad parameter.
3363 int rte_eth_dev_bypass_ver_show(uint8_t port, uint32_t *ver);
3366 * Return bypass watchdog timeout in seconds
3369 * The port identifier of the Ethernet device.
3371 * The return watchdog timeout. "0" represents timer expired
3372 * - (0) 0 seconds (timer is off)
3381 * - (0) if successful.
3382 * - (-ENOTSUP) if hardware doesn't support.
3383 * - (-EINVAL) if bad parameter.
3385 int rte_eth_dev_bypass_wd_timeout_show(uint8_t port, uint32_t *wd_timeout);
3388 * Reset bypass watchdog timer
3391 * The port identifier of the Ethernet device.
3393 * - (0) if successful.
3394 * - (-ENOTSUP) if hardware doesn't support.
3395 * - (-EINVAL) if bad parameter.
3397 int rte_eth_dev_bypass_wd_reset(uint8_t port);
3400 * Configuration of Receive Side Scaling hash computation of Ethernet device.
3403 * The port identifier of the Ethernet device.
3405 * The new configuration to use for RSS hash computation on the port.
3407 * - (0) if successful.
3408 * - (-ENODEV) if port identifier is invalid.
3409 * - (-ENOTSUP) if hardware doesn't support.
3410 * - (-EINVAL) if bad parameter.
3412 int rte_eth_dev_rss_hash_update(uint8_t port_id,
3413 struct rte_eth_rss_conf *rss_conf);
3416 * Retrieve current configuration of Receive Side Scaling hash computation
3417 * of Ethernet device.
3420 * The port identifier of the Ethernet device.
3422 * Where to store the current RSS hash configuration of the Ethernet device.
3424 * - (0) if successful.
3425 * - (-ENODEV) if port identifier is invalid.
3426 * - (-ENOTSUP) if hardware doesn't support RSS.
3429 rte_eth_dev_rss_hash_conf_get(uint8_t port_id,
3430 struct rte_eth_rss_conf *rss_conf);
3433 * Add UDP tunneling port of an Ethernet device for filtering a specific
3434 * tunneling packet by UDP port number.
3437 * The port identifier of the Ethernet device.
3439 * UDP tunneling configuration.
3442 * - (0) if successful.
3443 * - (-ENODEV) if port identifier is invalid.
3444 * - (-ENOTSUP) if hardware doesn't support tunnel type.
3447 rte_eth_dev_udp_tunnel_add(uint8_t port_id,
3448 struct rte_eth_udp_tunnel *tunnel_udp);
3451 * Detete UDP tunneling port configuration of Ethernet device
3454 * The port identifier of the Ethernet device.
3456 * UDP tunneling configuration.
3459 * - (0) if successful.
3460 * - (-ENODEV) if port identifier is invalid.
3461 * - (-ENOTSUP) if hardware doesn't support tunnel type.
3464 rte_eth_dev_udp_tunnel_delete(uint8_t port_id,
3465 struct rte_eth_udp_tunnel *tunnel_udp);
3468 * Check whether the filter type is supported on an Ethernet device.
3469 * All the supported filter types are defined in 'rte_eth_ctrl.h'.
3472 * The port identifier of the Ethernet device.
3473 * @param filter_type
3476 * - (0) if successful.
3477 * - (-ENOTSUP) if hardware doesn't support this filter type.
3478 * - (-ENODEV) if *port_id* invalid.
3480 int rte_eth_dev_filter_supported(uint8_t port_id, enum rte_filter_type filter_type);
3483 * Take operations to assigned filter type on an Ethernet device.
3484 * All the supported operations and filter types are defined in 'rte_eth_ctrl.h'.
3487 * The port identifier of the Ethernet device.
3488 * @param filter_type
3491 * Type of operation.
3493 * A pointer to arguments defined specifically for the operation.
3495 * - (0) if successful.
3496 * - (-ENOTSUP) if hardware doesn't support.
3497 * - (-ENODEV) if *port_id* invalid.
3498 * - others depends on the specific operations implementation.
3500 int rte_eth_dev_filter_ctrl(uint8_t port_id, enum rte_filter_type filter_type,
3501 enum rte_filter_op filter_op, void *arg);
3504 * Add a callback to be called on packet RX on a given port and queue.
3506 * This API configures a function to be called for each burst of
3507 * packets received on a given NIC port queue. The return value is a pointer
3508 * that can be used to later remove the callback using
3509 * rte_eth_remove_rx_callback().
3512 * The port identifier of the Ethernet device.
3514 * The queue on the Ethernet device on which the callback is to be added.
3516 * The callback function
3518 * A generic pointer parameter which will be passed to each invocation of the
3519 * callback function on this port and queue.
3523 * On success, a pointer value which can later be used to remove the callback.
3525 void *rte_eth_add_rx_callback(uint8_t port_id, uint16_t queue_id,
3526 rte_rx_callback_fn fn, void *user_param);
3529 * Add a callback to be called on packet TX on a given port and queue.
3531 * This API configures a function to be called for each burst of
3532 * packets sent on a given NIC port queue. The return value is a pointer
3533 * that can be used to later remove the callback using
3534 * rte_eth_remove_tx_callback().
3537 * The port identifier of the Ethernet device.
3539 * The queue on the Ethernet device on which the callback is to be added.
3541 * The callback function
3543 * A generic pointer parameter which will be passed to each invocation of the
3544 * callback function on this port and queue.
3548 * On success, a pointer value which can later be used to remove the callback.
3550 void *rte_eth_add_tx_callback(uint8_t port_id, uint16_t queue_id,
3551 rte_tx_callback_fn fn, void *user_param);
3554 * Remove an RX packet callback from a given port and queue.
3556 * This function is used to removed callbacks that were added to a NIC port
3557 * queue using rte_eth_add_rx_callback().
3559 * Note: the callback is removed from the callback list but it isn't freed
3560 * since the it may still be in use. The memory for the callback can be
3561 * subsequently freed back by the application by calling rte_free():
3563 * - Immediately - if the port is stopped, or the user knows that no
3564 * callbacks are in flight e.g. if called from the thread doing RX/TX
3567 * - After a short delay - where the delay is sufficient to allow any
3568 * in-flight callbacks to complete.
3571 * The port identifier of the Ethernet device.
3573 * The queue on the Ethernet device from which the callback is to be removed.
3575 * User supplied callback created via rte_eth_add_rx_callback().
3578 * - 0: Success. Callback was removed.
3579 * - -ENOTSUP: Callback support is not available.
3580 * - -EINVAL: The port_id or the queue_id is out of range, or the callback
3581 * is NULL or not found for the port/queue.
3583 int rte_eth_remove_rx_callback(uint8_t port_id, uint16_t queue_id,
3584 struct rte_eth_rxtx_callback *user_cb);
3587 * Remove a TX packet callback from a given port and queue.
3589 * This function is used to removed callbacks that were added to a NIC port
3590 * queue using rte_eth_add_tx_callback().
3592 * Note: the callback is removed from the callback list but it isn't freed
3593 * since the it may still be in use. The memory for the callback can be
3594 * subsequently freed back by the application by calling rte_free():
3596 * - Immediately - if the port is stopped, or the user knows that no
3597 * callbacks are in flight e.g. if called from the thread doing RX/TX
3600 * - After a short delay - where the delay is sufficient to allow any
3601 * in-flight callbacks to complete.
3604 * The port identifier of the Ethernet device.
3606 * The queue on the Ethernet device from which the callback is to be removed.
3608 * User supplied callback created via rte_eth_add_tx_callback().
3611 * - 0: Success. Callback was removed.
3612 * - -ENOTSUP: Callback support is not available.
3613 * - -EINVAL: The port_id or the queue_id is out of range, or the callback
3614 * is NULL or not found for the port/queue.
3616 int rte_eth_remove_tx_callback(uint8_t port_id, uint16_t queue_id,
3617 struct rte_eth_rxtx_callback *user_cb);
3624 * Set the list of multicast addresses to filter on an Ethernet device.
3627 * The port identifier of the Ethernet device.
3628 * @param mc_addr_set
3629 * The array of multicast addresses to set. Equal to NULL when the function
3630 * is invoked to flush the set of filtered addresses.
3632 * The number of multicast addresses in the *mc_addr_set* array. Equal to 0
3633 * when the function is invoked to flush the set of filtered addresses.
3635 * - (0) if successful.
3636 * - (-ENODEV) if *port_id* invalid.
3637 * - (-ENOTSUP) if PMD of *port_id* doesn't support multicast filtering.
3638 * - (-ENOSPC) if *port_id* has not enough multicast filtering resources.
3640 int rte_eth_dev_set_mc_addr_list(uint8_t port_id,
3641 struct ether_addr *mc_addr_set,
3642 uint32_t nb_mc_addr);
3644 #endif /* _RTE_ETHDEV_H_ */