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.
176 #include <rte_interrupts.h>
178 #include <rte_mbuf.h>
179 #include "rte_ether.h"
182 * A structure used to retrieve statistics for an Ethernet port.
184 struct rte_eth_stats {
185 uint64_t ipackets; /**< Total number of successfully received packets. */
186 uint64_t opackets; /**< Total number of successfully transmitted packets.*/
187 uint64_t ibytes; /**< Total number of successfully received bytes. */
188 uint64_t obytes; /**< Total number of successfully transmitted bytes. */
189 uint64_t imissed; /**< Total of RX missed packets (e.g full FIFO). */
190 uint64_t ibadcrc; /**< Total of RX packets with CRC error. */
191 uint64_t ibadlen; /**< Total of RX packets with bad length. */
192 uint64_t ierrors; /**< Total number of erroneous received packets. */
193 uint64_t oerrors; /**< Total number of failed transmitted packets. */
194 uint64_t imcasts; /**< Total number of multicast received packets. */
195 uint64_t rx_nombuf; /**< Total number of RX mbuf allocation failures. */
196 uint64_t fdirmatch; /**< Total number of RX packets matching a filter. */
197 uint64_t fdirmiss; /**< Total number of RX packets not matching any filter. */
198 uint64_t tx_pause_xon; /**< Total nb. of XON pause frame sent. */
199 uint64_t rx_pause_xon; /**< Total nb. of XON pause frame received. */
200 uint64_t tx_pause_xoff; /**< Total nb. of XOFF pause frame sent. */
201 uint64_t rx_pause_xoff; /**< Total nb. of XOFF pause frame received. */
202 uint64_t q_ipackets[RTE_ETHDEV_QUEUE_STAT_CNTRS];
203 /**< Total number of queue RX packets. */
204 uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS];
205 /**< Total number of queue TX packets. */
206 uint64_t q_ibytes[RTE_ETHDEV_QUEUE_STAT_CNTRS];
207 /**< Total number of successfully received queue bytes. */
208 uint64_t q_obytes[RTE_ETHDEV_QUEUE_STAT_CNTRS];
209 /**< Total number of successfully transmitted queue bytes. */
210 uint64_t q_errors[RTE_ETHDEV_QUEUE_STAT_CNTRS];
211 /**< Total number of queue packets received that are dropped. */
213 /**< Total number of good packets received from loopback,VF Only */
215 /**< Total number of good packets transmitted to loopback,VF Only */
217 /**< Total number of good bytes received from loopback,VF Only */
219 /**< Total number of good bytes transmitted to loopback,VF Only */
223 * A structure used to retrieve link-level information of an Ethernet port.
225 struct rte_eth_link {
226 uint16_t link_speed; /**< ETH_LINK_SPEED_[10, 100, 1000, 10000] */
227 uint16_t link_duplex; /**< ETH_LINK_[HALF_DUPLEX, FULL_DUPLEX] */
228 uint8_t link_status : 1; /**< 1 -> link up, 0 -> link down */
229 }__attribute__((aligned(8))); /**< aligned for atomic64 read/write */
231 #define ETH_LINK_SPEED_AUTONEG 0 /**< Auto-negotiate link speed. */
232 #define ETH_LINK_SPEED_10 10 /**< 10 megabits/second. */
233 #define ETH_LINK_SPEED_100 100 /**< 100 megabits/second. */
234 #define ETH_LINK_SPEED_1000 1000 /**< 1 gigabits/second. */
235 #define ETH_LINK_SPEED_10000 10000 /**< 10 gigabits/second. */
237 #define ETH_LINK_AUTONEG_DUPLEX 0 /**< Auto-negotiate duplex. */
238 #define ETH_LINK_HALF_DUPLEX 1 /**< Half-duplex connection. */
239 #define ETH_LINK_FULL_DUPLEX 2 /**< Full-duplex connection. */
242 * A structure used to configure the ring threshold registers of an RX/TX
243 * queue for an Ethernet port.
245 struct rte_eth_thresh {
246 uint8_t pthresh; /**< Ring prefetch threshold. */
247 uint8_t hthresh; /**< Ring host threshold. */
248 uint8_t wthresh; /**< Ring writeback threshold. */
252 * A set of values to identify what method is to be used to route
253 * packets to multiple queues.
255 enum rte_eth_rx_mq_mode {
256 ETH_MQ_RX_NONE = 0, /**< None of DCB,RSS or VMDQ mode */
258 ETH_MQ_RX_RSS, /**< For RX side, only RSS is on */
259 ETH_MQ_RX_DCB, /**< For RX side,only DCB is on. */
260 ETH_MQ_RX_DCB_RSS, /**< Both DCB and RSS enable */
262 ETH_MQ_RX_VMDQ_ONLY, /**< Only VMDQ, no RSS nor DCB */
263 ETH_MQ_RX_VMDQ_RSS, /**< RSS mode with VMDQ */
264 ETH_MQ_RX_VMDQ_DCB, /**< Use VMDQ+DCB to route traffic to queues */
265 ETH_MQ_RX_VMDQ_DCB_RSS, /**< Enable both VMDQ and DCB in VMDq */
269 * for rx mq mode backward compatible
271 #define ETH_RSS ETH_MQ_RX_RSS
272 #define VMDQ_DCB ETH_MQ_RX_VMDQ_DCB
273 #define ETH_DCB_RX ETH_MQ_RX_DCB
276 * A set of values to identify what method is to be used to transmit
277 * packets using multi-TCs.
279 enum rte_eth_tx_mq_mode {
280 ETH_MQ_TX_NONE = 0, /**< It is in neither DCB nor VT mode. */
281 ETH_MQ_TX_DCB, /**< For TX side,only DCB is on. */
282 ETH_MQ_TX_VMDQ_DCB, /**< For TX side,both DCB and VT is on. */
283 ETH_MQ_TX_VMDQ_ONLY, /**< Only VT on, no DCB */
287 * for tx mq mode backward compatible
289 #define ETH_DCB_NONE ETH_MQ_TX_NONE
290 #define ETH_VMDQ_DCB_TX ETH_MQ_TX_VMDQ_DCB
291 #define ETH_DCB_TX ETH_MQ_TX_DCB
294 * A structure used to configure the RX features of an Ethernet port.
296 struct rte_eth_rxmode {
297 /** The multi-queue packet distribution mode to be used, e.g. RSS. */
298 enum rte_eth_rx_mq_mode mq_mode;
299 uint32_t max_rx_pkt_len; /**< Only used if jumbo_frame enabled. */
300 uint16_t split_hdr_size; /**< hdr buf size (header_split enabled).*/
301 uint8_t header_split : 1, /**< Header Split enable. */
302 hw_ip_checksum : 1, /**< IP/UDP/TCP checksum offload enable. */
303 hw_vlan_filter : 1, /**< VLAN filter enable. */
304 hw_vlan_strip : 1, /**< VLAN strip enable. */
305 hw_vlan_extend : 1, /**< Extended VLAN enable. */
306 jumbo_frame : 1, /**< Jumbo Frame Receipt enable. */
307 hw_strip_crc : 1; /**< Enable CRC stripping by hardware. */
311 * A structure used to configure the Receive Side Scaling (RSS) feature
312 * of an Ethernet port.
313 * If not NULL, the *rss_key* pointer of the *rss_conf* structure points
314 * to an array holding the RSS key to use for hashing specific header
315 * fields of received packets. The length of this array should be indicated
316 * by *rss_key_len* below. Otherwise, a default random hash key is used by
319 * The *rss_key_len* field of the *rss_conf* structure indicates the length
320 * in bytes of the array pointed by *rss_key*. To be compatible, this length
321 * will be checked in i40e only. Others assume 40 bytes to be used as before.
323 * The *rss_hf* field of the *rss_conf* structure indicates the different
324 * types of IPv4/IPv6 packets to which the RSS hashing must be applied.
325 * Supplying an *rss_hf* equal to zero disables the RSS feature.
327 struct rte_eth_rss_conf {
328 uint8_t *rss_key; /**< If not NULL, 40-byte hash key. */
329 uint8_t rss_key_len; /**< hash key length in bytes. */
330 uint64_t rss_hf; /**< Hash functions to apply - see below. */
333 /* Supported RSS offloads */
335 #define ETH_RSS_IPV4_SHIFT 0
336 #define ETH_RSS_IPV4_TCP_SHIFT 1
337 #define ETH_RSS_IPV6_SHIFT 2
338 #define ETH_RSS_IPV6_EX_SHIFT 3
339 #define ETH_RSS_IPV6_TCP_SHIFT 4
340 #define ETH_RSS_IPV6_TCP_EX_SHIFT 5
341 #define ETH_RSS_IPV4_UDP_SHIFT 6
342 #define ETH_RSS_IPV6_UDP_SHIFT 7
343 #define ETH_RSS_IPV6_UDP_EX_SHIFT 8
345 #define ETH_RSS_NONF_IPV4_UDP_SHIFT 31
346 #define ETH_RSS_NONF_IPV4_TCP_SHIFT 33
347 #define ETH_RSS_NONF_IPV4_SCTP_SHIFT 34
348 #define ETH_RSS_NONF_IPV4_OTHER_SHIFT 35
349 #define ETH_RSS_FRAG_IPV4_SHIFT 36
350 #define ETH_RSS_NONF_IPV6_UDP_SHIFT 41
351 #define ETH_RSS_NONF_IPV6_TCP_SHIFT 43
352 #define ETH_RSS_NONF_IPV6_SCTP_SHIFT 44
353 #define ETH_RSS_NONF_IPV6_OTHER_SHIFT 45
354 #define ETH_RSS_FRAG_IPV6_SHIFT 46
355 #define ETH_RSS_FCOE_OX_SHIFT 48
356 #define ETH_RSS_FCOE_RX_SHIFT 49
357 #define ETH_RSS_FCOE_OTHER_SHIFT 50
358 #define ETH_RSS_L2_PAYLOAD_SHIFT 63
361 #define ETH_RSS_IPV4 ((uint16_t)1 << ETH_RSS_IPV4_SHIFT)
362 #define ETH_RSS_IPV4_TCP ((uint16_t)1 << ETH_RSS_IPV4_TCP_SHIFT)
363 #define ETH_RSS_IPV6 ((uint16_t)1 << ETH_RSS_IPV6_SHIFT)
364 #define ETH_RSS_IPV6_EX ((uint16_t)1 << ETH_RSS_IPV6_EX_SHIFT)
365 #define ETH_RSS_IPV6_TCP ((uint16_t)1 << ETH_RSS_IPV6_TCP_SHIFT)
366 #define ETH_RSS_IPV6_TCP_EX ((uint16_t)1 << ETH_RSS_IPV6_TCP_EX_SHIFT)
367 #define ETH_RSS_IPV4_UDP ((uint16_t)1 << ETH_RSS_IPV4_UDP_SHIFT)
368 #define ETH_RSS_IPV6_UDP ((uint16_t)1 << ETH_RSS_IPV6_UDP_SHIFT)
369 #define ETH_RSS_IPV6_UDP_EX ((uint16_t)1 << ETH_RSS_IPV6_UDP_EX_SHIFT)
371 #define ETH_RSS_NONF_IPV4_UDP ((uint64_t)1 << ETH_RSS_NONF_IPV4_UDP_SHIFT)
372 #define ETH_RSS_NONF_IPV4_TCP ((uint64_t)1 << ETH_RSS_NONF_IPV4_TCP_SHIFT)
373 #define ETH_RSS_NONF_IPV4_SCTP ((uint64_t)1 << ETH_RSS_NONF_IPV4_SCTP_SHIFT)
374 #define ETH_RSS_NONF_IPV4_OTHER ((uint64_t)1 << ETH_RSS_NONF_IPV4_OTHER_SHIFT)
375 #define ETH_RSS_FRAG_IPV4 ((uint64_t)1 << ETH_RSS_FRAG_IPV4_SHIFT)
376 #define ETH_RSS_NONF_IPV6_UDP ((uint64_t)1 << ETH_RSS_NONF_IPV6_UDP_SHIFT)
377 #define ETH_RSS_NONF_IPV6_TCP ((uint64_t)1 << ETH_RSS_NONF_IPV6_TCP_SHIFT)
378 #define ETH_RSS_NONF_IPV6_SCTP ((uint64_t)1 << ETH_RSS_NONF_IPV6_SCTP_SHIFT)
379 #define ETH_RSS_NONF_IPV6_OTHER ((uint64_t)1 << ETH_RSS_NONF_IPV6_OTHER_SHIFT)
380 #define ETH_RSS_FRAG_IPV6 ((uint64_t)1 << ETH_RSS_FRAG_IPV6_SHIFT)
381 #define ETH_RSS_FCOE_OX ((uint64_t)1 << ETH_RSS_FCOE_OX_SHIFT) /* not used */
382 #define ETH_RSS_FCOE_RX ((uint64_t)1 << ETH_RSS_FCOE_RX_SHIFT) /* not used */
383 #define ETH_RSS_FCOE_OTHER ((uint64_t)1 << ETH_RSS_FCOE_OTHER_SHIFT) /* not used */
384 #define ETH_RSS_L2_PAYLOAD ((uint64_t)1 << ETH_RSS_L2_PAYLOAD_SHIFT)
386 #define ETH_RSS_IP ( \
389 ETH_RSS_NONF_IPV4_OTHER | \
390 ETH_RSS_FRAG_IPV4 | \
391 ETH_RSS_NONF_IPV6_OTHER | \
393 #define ETH_RSS_UDP ( \
398 ETH_RSS_IPV6_UDP_EX | \
399 ETH_RSS_NONF_IPV4_UDP | \
400 ETH_RSS_NONF_IPV6_UDP)
401 /**< Mask of valid RSS hash protocols */
402 #define ETH_RSS_PROTO_MASK ( \
408 ETH_RSS_IPV6_TCP_EX | \
411 ETH_RSS_IPV6_UDP_EX | \
412 ETH_RSS_NONF_IPV4_UDP | \
413 ETH_RSS_NONF_IPV4_TCP | \
414 ETH_RSS_NONF_IPV4_SCTP | \
415 ETH_RSS_NONF_IPV4_OTHER | \
416 ETH_RSS_FRAG_IPV4 | \
417 ETH_RSS_NONF_IPV6_UDP | \
418 ETH_RSS_NONF_IPV6_TCP | \
419 ETH_RSS_NONF_IPV6_SCTP | \
420 ETH_RSS_NONF_IPV6_OTHER | \
421 ETH_RSS_FRAG_IPV6 | \
424 /* Definitions used for redirection table entry size */
425 #define ETH_RSS_RETA_NUM_ENTRIES 128
426 #define ETH_RSS_RETA_MAX_QUEUE 16
428 /* Definitions used for VMDQ and DCB functionality */
429 #define ETH_VMDQ_MAX_VLAN_FILTERS 64 /**< Maximum nb. of VMDQ vlan filters. */
430 #define ETH_DCB_NUM_USER_PRIORITIES 8 /**< Maximum nb. of DCB priorities. */
431 #define ETH_VMDQ_DCB_NUM_QUEUES 128 /**< Maximum nb. of VMDQ DCB queues. */
432 #define ETH_DCB_NUM_QUEUES 128 /**< Maximum nb. of DCB queues. */
434 /* DCB capability defines */
435 #define ETH_DCB_PG_SUPPORT 0x00000001 /**< Priority Group(ETS) support. */
436 #define ETH_DCB_PFC_SUPPORT 0x00000002 /**< Priority Flow Control support. */
438 /* Definitions used for VLAN Offload functionality */
439 #define ETH_VLAN_STRIP_OFFLOAD 0x0001 /**< VLAN Strip On/Off */
440 #define ETH_VLAN_FILTER_OFFLOAD 0x0002 /**< VLAN Filter On/Off */
441 #define ETH_VLAN_EXTEND_OFFLOAD 0x0004 /**< VLAN Extend On/Off */
443 /* Definitions used for mask VLAN setting */
444 #define ETH_VLAN_STRIP_MASK 0x0001 /**< VLAN Strip setting mask */
445 #define ETH_VLAN_FILTER_MASK 0x0002 /**< VLAN Filter setting mask*/
446 #define ETH_VLAN_EXTEND_MASK 0x0004 /**< VLAN Extend setting mask*/
447 #define ETH_VLAN_ID_MAX 0x0FFF /**< VLAN ID is in lower 12 bits*/
449 /* Definitions used for receive MAC address */
450 #define ETH_NUM_RECEIVE_MAC_ADDR 128 /**< Maximum nb. of receive mac addr. */
453 /* Definitions used for unicast hash */
454 #define ETH_VMDQ_NUM_UC_HASH_ARRAY 128 /**< Maximum nb. of UC hash array. */
456 /* Definitions used for VMDQ pool rx mode setting */
457 #define ETH_VMDQ_ACCEPT_UNTAG 0x0001 /**< accept untagged packets. */
458 #define ETH_VMDQ_ACCEPT_HASH_MC 0x0002 /**< accept packets in multicast table . */
459 #define ETH_VMDQ_ACCEPT_HASH_UC 0x0004 /**< accept packets in unicast table. */
460 #define ETH_VMDQ_ACCEPT_BROADCAST 0x0008 /**< accept broadcast packets. */
461 #define ETH_VMDQ_ACCEPT_MULTICAST 0x0010 /**< multicast promiscuous. */
463 /* Definitions used for VMDQ mirror rules setting */
464 #define ETH_VMDQ_NUM_MIRROR_RULE 4 /**< Maximum nb. of mirror rules. . */
466 #define ETH_VMDQ_POOL_MIRROR 0x0001 /**< Virtual Pool Mirroring. */
467 #define ETH_VMDQ_UPLINK_MIRROR 0x0002 /**< Uplink Port Mirroring. */
468 #define ETH_VMDQ_DOWNLIN_MIRROR 0x0004 /**< Downlink Port Mirroring. */
469 #define ETH_VMDQ_VLAN_MIRROR 0x0008 /**< VLAN Mirroring. */
472 * A structure used to configure VLAN traffic mirror of an Ethernet port.
474 struct rte_eth_vlan_mirror {
475 uint64_t vlan_mask; /**< mask for valid VLAN ID. */
476 uint16_t vlan_id[ETH_VMDQ_MAX_VLAN_FILTERS];
477 /** VLAN ID list for vlan mirror. */
481 * A structure used to configure traffic mirror of an Ethernet port.
483 struct rte_eth_vmdq_mirror_conf {
484 uint8_t rule_type_mask; /**< Mirroring rule type mask we want to set */
485 uint8_t dst_pool; /**< Destination pool for this mirror rule. */
486 uint64_t pool_mask; /**< Bitmap of pool for pool mirroring */
487 struct rte_eth_vlan_mirror vlan; /**< VLAN ID setting for VLAN mirroring */
491 * A structure used to configure Redirection Table of the Receive Side
492 * Scaling (RSS) feature of an Ethernet port.
494 struct rte_eth_rss_reta {
495 /** First 64 mask bits indicate which entry(s) need to updated/queried. */
497 /** Second 64 mask bits indicate which entry(s) need to updated/queried. */
499 uint8_t reta[ETH_RSS_RETA_NUM_ENTRIES]; /**< 128 RETA entries*/
503 * This enum indicates the possible number of traffic classes
504 * in DCB configratioins
506 enum rte_eth_nb_tcs {
507 ETH_4_TCS = 4, /**< 4 TCs with DCB. */
508 ETH_8_TCS = 8 /**< 8 TCs with DCB. */
512 * This enum indicates the possible number of queue pools
513 * in VMDQ configurations.
515 enum rte_eth_nb_pools {
516 ETH_8_POOLS = 8, /**< 8 VMDq pools. */
517 ETH_16_POOLS = 16, /**< 16 VMDq pools. */
518 ETH_32_POOLS = 32, /**< 32 VMDq pools. */
519 ETH_64_POOLS = 64 /**< 64 VMDq pools. */
522 /* This structure may be extended in future. */
523 struct rte_eth_dcb_rx_conf {
524 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs */
525 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
526 /**< Possible DCB queue,4 or 8. */
529 struct rte_eth_vmdq_dcb_tx_conf {
530 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools. */
531 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
532 /**< Possible DCB queue,4 or 8. */
535 struct rte_eth_dcb_tx_conf {
536 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs. */
537 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
538 /**< Possible DCB queue,4 or 8. */
541 struct rte_eth_vmdq_tx_conf {
542 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq mode, 64 pools. */
546 * A structure used to configure the VMDQ+DCB feature
547 * of an Ethernet port.
549 * Using this feature, packets are routed to a pool of queues, based
550 * on the vlan id in the vlan tag, and then to a specific queue within
551 * that pool, using the user priority vlan tag field.
553 * A default pool may be used, if desired, to route all traffic which
554 * does not match the vlan filter rules.
556 struct rte_eth_vmdq_dcb_conf {
557 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools */
558 uint8_t enable_default_pool; /**< If non-zero, use a default pool */
559 uint8_t default_pool; /**< The default pool, if applicable */
560 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */
562 uint16_t vlan_id; /**< The vlan id of the received frame */
563 uint64_t pools; /**< Bitmask of pools for packet rx */
564 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */
565 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
566 /**< Selects a queue in a pool */
569 struct rte_eth_vmdq_rx_conf {
570 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq only mode, 8 or 64 pools */
571 uint8_t enable_default_pool; /**< If non-zero, use a default pool */
572 uint8_t default_pool; /**< The default pool, if applicable */
573 uint8_t enable_loop_back; /**< Enable VT loop back */
574 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */
576 uint16_t vlan_id; /**< The vlan id of the received frame */
577 uint64_t pools; /**< Bitmask of pools for packet rx */
578 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */
582 * A structure used to configure the TX features of an Ethernet port.
584 struct rte_eth_txmode {
585 enum rte_eth_tx_mq_mode mq_mode; /**< TX multi-queues mode. */
589 * A structure used to configure an RX ring of an Ethernet port.
591 struct rte_eth_rxconf {
592 struct rte_eth_thresh rx_thresh; /**< RX ring threshold registers. */
593 uint16_t rx_free_thresh; /**< Drives the freeing of RX descriptors. */
594 uint8_t rx_drop_en; /**< Drop packets if no descriptors are available. */
595 uint8_t start_rx_per_q; /**< start rx per queue. */
598 #define ETH_TXQ_FLAGS_NOMULTSEGS 0x0001 /**< nb_segs=1 for all mbufs */
599 #define ETH_TXQ_FLAGS_NOREFCOUNT 0x0002 /**< refcnt can be ignored */
600 #define ETH_TXQ_FLAGS_NOMULTMEMP 0x0004 /**< all bufs come from same mempool */
601 #define ETH_TXQ_FLAGS_NOVLANOFFL 0x0100 /**< disable VLAN offload */
602 #define ETH_TXQ_FLAGS_NOXSUMSCTP 0x0200 /**< disable SCTP checksum offload */
603 #define ETH_TXQ_FLAGS_NOXSUMUDP 0x0400 /**< disable UDP checksum offload */
604 #define ETH_TXQ_FLAGS_NOXSUMTCP 0x0800 /**< disable TCP checksum offload */
605 #define ETH_TXQ_FLAGS_NOOFFLOADS \
606 (ETH_TXQ_FLAGS_NOVLANOFFL | ETH_TXQ_FLAGS_NOXSUMSCTP | \
607 ETH_TXQ_FLAGS_NOXSUMUDP | ETH_TXQ_FLAGS_NOXSUMTCP)
609 * A structure used to configure a TX ring of an Ethernet port.
611 struct rte_eth_txconf {
612 struct rte_eth_thresh tx_thresh; /**< TX ring threshold registers. */
613 uint16_t tx_rs_thresh; /**< Drives the setting of RS bit on TXDs. */
614 uint16_t tx_free_thresh; /**< Drives the freeing of TX buffers. */
615 uint32_t txq_flags; /**< Set flags for the Tx queue */
616 uint8_t start_tx_per_q; /**< start tx per queue. */
620 * This enum indicates the flow control mode
622 enum rte_eth_fc_mode {
623 RTE_FC_NONE = 0, /**< Disable flow control. */
624 RTE_FC_RX_PAUSE, /**< RX pause frame, enable flowctrl on TX side. */
625 RTE_FC_TX_PAUSE, /**< TX pause frame, enable flowctrl on RX side. */
626 RTE_FC_FULL /**< Enable flow control on both side. */
630 * A structure used to configure Ethernet flow control parameter.
631 * These parameters will be configured into the register of the NIC.
632 * Please refer to the corresponding data sheet for proper value.
634 struct rte_eth_fc_conf {
635 uint32_t high_water; /**< High threshold value to trigger XOFF */
636 uint32_t low_water; /**< Low threshold value to trigger XON */
637 uint16_t pause_time; /**< Pause quota in the Pause frame */
638 uint16_t send_xon; /**< Is XON frame need be sent */
639 enum rte_eth_fc_mode mode; /**< Link flow control mode */
640 uint8_t mac_ctrl_frame_fwd; /**< Forward MAC control frames */
644 * A structure used to configure Ethernet priority flow control parameter.
645 * These parameters will be configured into the register of the NIC.
646 * Please refer to the corresponding data sheet for proper value.
648 struct rte_eth_pfc_conf {
649 struct rte_eth_fc_conf fc; /**< General flow control parameter. */
650 uint8_t priority; /**< VLAN User Priority. */
654 * Flow Director setting modes: none (default), signature or perfect.
657 RTE_FDIR_MODE_NONE = 0, /**< Disable FDIR support. */
658 RTE_FDIR_MODE_SIGNATURE, /**< Enable FDIR signature filter mode. */
659 RTE_FDIR_MODE_PERFECT, /**< Enable FDIR perfect filter mode. */
663 * Memory space that can be configured to store Flow Director filters
664 * in the board memory.
666 enum rte_fdir_pballoc_type {
667 RTE_FDIR_PBALLOC_64K = 0, /**< 64k. */
668 RTE_FDIR_PBALLOC_128K, /**< 128k. */
669 RTE_FDIR_PBALLOC_256K, /**< 256k. */
673 * Select report mode of FDIR hash information in RX descriptors.
675 enum rte_fdir_status_mode {
676 RTE_FDIR_NO_REPORT_STATUS = 0, /**< Never report FDIR hash. */
677 RTE_FDIR_REPORT_STATUS, /**< Only report FDIR hash for matching pkts. */
678 RTE_FDIR_REPORT_STATUS_ALWAYS, /**< Always report FDIR hash. */
682 * A structure used to configure the Flow Director (FDIR) feature
683 * of an Ethernet port.
685 * If mode is RTE_FDIR_DISABLE, the pballoc value is ignored.
687 struct rte_fdir_conf {
688 enum rte_fdir_mode mode; /**< Flow Director mode. */
689 enum rte_fdir_pballoc_type pballoc; /**< Space for FDIR filters. */
690 enum rte_fdir_status_mode status; /**< How to report FDIR hash. */
691 /** Offset of flexbytes field in RX packets (in 16-bit word units). */
692 uint8_t flexbytes_offset;
693 /** RX queue of packets matching a "drop" filter in perfect mode. */
698 * Possible l4type of FDIR filters.
701 RTE_FDIR_L4TYPE_NONE = 0, /**< None. */
702 RTE_FDIR_L4TYPE_UDP, /**< UDP. */
703 RTE_FDIR_L4TYPE_TCP, /**< TCP. */
704 RTE_FDIR_L4TYPE_SCTP, /**< SCTP. */
708 * Select IPv4 or IPv6 FDIR filters.
711 RTE_FDIR_IPTYPE_IPV4 = 0, /**< IPv4. */
712 RTE_FDIR_IPTYPE_IPV6 , /**< IPv6. */
716 * A structure used to define a FDIR packet filter.
718 struct rte_fdir_filter {
719 uint16_t flex_bytes; /**< Flex bytes value to match. */
720 uint16_t vlan_id; /**< VLAN ID value to match, 0 otherwise. */
721 uint16_t port_src; /**< Source port to match, 0 otherwise. */
722 uint16_t port_dst; /**< Destination port to match, 0 otherwise. */
724 uint32_t ipv4_addr; /**< IPv4 source address to match. */
725 uint32_t ipv6_addr[4]; /**< IPv6 source address to match. */
726 } ip_src; /**< IPv4/IPv6 source address to match (union of above). */
728 uint32_t ipv4_addr; /**< IPv4 destination address to match. */
729 uint32_t ipv6_addr[4]; /**< IPv6 destination address to match */
730 } ip_dst; /**< IPv4/IPv6 destination address to match (union of above). */
731 enum rte_l4type l4type; /**< l4type to match: NONE/UDP/TCP/SCTP. */
732 enum rte_iptype iptype; /**< IP packet type to match: IPv4 or IPv6. */
736 * A structure used to configure FDIR masks that are used by the device
737 * to match the various fields of RX packet headers.
738 * @note The only_ip_flow field has the opposite meaning compared to other
741 struct rte_fdir_masks {
742 /** When set to 1, packet l4type is \b NOT relevant in filters, and
743 source and destination port masks must be set to zero. */
744 uint8_t only_ip_flow;
745 /** If set to 1, vlan_id is relevant in filters. */
747 /** If set to 1, vlan_prio is relevant in filters. */
749 /** If set to 1, flexbytes is relevant in filters. */
751 /** If set to 1, set the IPv6 masks. Otherwise set the IPv4 masks. */
752 uint8_t set_ipv6_mask;
753 /** When set to 1, comparison of destination IPv6 address with IP6AT
754 registers is meaningful. */
755 uint8_t comp_ipv6_dst;
756 /** Mask of Destination IPv4 Address. All bits set to 1 define the
757 relevant bits to use in the destination address of an IPv4 packet
758 when matching it against FDIR filters. */
759 uint32_t dst_ipv4_mask;
760 /** Mask of Source IPv4 Address. All bits set to 1 define
761 the relevant bits to use in the source address of an IPv4 packet
762 when matching it against FDIR filters. */
763 uint32_t src_ipv4_mask;
764 /** Mask of Source IPv6 Address. All bits set to 1 define the
765 relevant BYTES to use in the source address of an IPv6 packet
766 when matching it against FDIR filters. */
767 uint16_t dst_ipv6_mask;
768 /** Mask of Destination IPv6 Address. All bits set to 1 define the
769 relevant BYTES to use in the destination address of an IPv6 packet
770 when matching it against FDIR filters. */
771 uint16_t src_ipv6_mask;
772 /** Mask of Source Port. All bits set to 1 define the relevant
773 bits to use in the source port of an IP packets when matching it
774 against FDIR filters. */
775 uint16_t src_port_mask;
776 /** Mask of Destination Port. All bits set to 1 define the relevant
777 bits to use in the destination port of an IP packet when matching it
778 against FDIR filters. */
779 uint16_t dst_port_mask;
783 * A structure used to report the status of the flow director filters in use.
785 struct rte_eth_fdir {
786 /** Number of filters with collision indication. */
788 /** Number of free (non programmed) filters. */
790 /** The Lookup hash value of the added filter that updated the value
791 of the MAXLEN field */
793 /** Longest linked list of filters in the table. */
795 /** Number of added filters. */
797 /** Number of removed filters. */
799 /** Number of failed added filters (no more space in device). */
801 /** Number of failed removed filters. */
806 * A structure used to enable/disable specific device interrupts.
808 struct rte_intr_conf {
809 /** enable/disable lsc interrupt. 0 (default) - disable, 1 enable */
814 * A structure used to configure an Ethernet port.
815 * Depending upon the RX multi-queue mode, extra advanced
816 * configuration settings may be needed.
818 struct rte_eth_conf {
820 /**< ETH_LINK_SPEED_10[0|00|000], or 0 for autonegotation */
821 uint16_t link_duplex;
822 /**< ETH_LINK_[HALF_DUPLEX|FULL_DUPLEX], or 0 for autonegotation */
823 struct rte_eth_rxmode rxmode; /**< Port RX configuration. */
824 struct rte_eth_txmode txmode; /**< Port TX configuration. */
825 uint32_t lpbk_mode; /**< Loopback operation mode. By default the value
826 is 0, meaning the loopback mode is disabled.
827 Read the datasheet of given ethernet controller
828 for details. The possible values of this field
829 are defined in implementation of each driver. */
831 struct rte_eth_rss_conf rss_conf; /**< Port RSS configuration */
832 struct rte_eth_vmdq_dcb_conf vmdq_dcb_conf;
833 /**< Port vmdq+dcb configuration. */
834 struct rte_eth_dcb_rx_conf dcb_rx_conf;
835 /**< Port dcb RX configuration. */
836 struct rte_eth_vmdq_rx_conf vmdq_rx_conf;
837 /**< Port vmdq RX configuration. */
838 } rx_adv_conf; /**< Port RX filtering configuration (union). */
840 struct rte_eth_vmdq_dcb_tx_conf vmdq_dcb_tx_conf;
841 /**< Port vmdq+dcb TX configuration. */
842 struct rte_eth_dcb_tx_conf dcb_tx_conf;
843 /**< Port dcb TX configuration. */
844 struct rte_eth_vmdq_tx_conf vmdq_tx_conf;
845 /**< Port vmdq TX configuration. */
846 } tx_adv_conf; /**< Port TX DCB configuration (union). */
847 /** Currently,Priority Flow Control(PFC) are supported,if DCB with PFC
848 is needed,and the variable must be set ETH_DCB_PFC_SUPPORT. */
849 uint32_t dcb_capability_en;
850 struct rte_fdir_conf fdir_conf; /**< FDIR configuration. */
851 struct rte_intr_conf intr_conf; /**< Interrupt mode configuration. */
855 * A structure used to retrieve the contextual information of
856 * an Ethernet device, such as the controlling driver of the device,
857 * its PCI context, etc...
861 * RX offload capabilities of a device.
863 #define DEV_RX_OFFLOAD_VLAN_STRIP 0x00000001
864 #define DEV_RX_OFFLOAD_IPV4_CKSUM 0x00000002
865 #define DEV_RX_OFFLOAD_UDP_CKSUM 0x00000004
866 #define DEV_RX_OFFLOAD_TCP_CKSUM 0x00000008
867 #define DEV_RX_OFFLOAD_TCP_LRO 0x00000010
870 * TX offload capabilities of a device.
872 #define DEV_TX_OFFLOAD_VLAN_INSERT 0x00000001
873 #define DEV_TX_OFFLOAD_IPV4_CKSUM 0x00000002
874 #define DEV_TX_OFFLOAD_UDP_CKSUM 0x00000004
875 #define DEV_TX_OFFLOAD_TCP_CKSUM 0x00000008
876 #define DEV_TX_OFFLOAD_SCTP_CKSUM 0x00000010
877 #define DEV_TX_OFFLOAD_TCP_TSO 0x00000020
878 #define DEV_TX_OFFLOAD_UDP_TSO 0x00000040
880 struct rte_eth_dev_info {
881 struct rte_pci_device *pci_dev; /**< Device PCI information. */
882 const char *driver_name; /**< Device Driver name. */
883 unsigned int if_index; /**< Index to bound host interface, or 0 if none.
884 Use if_indextoname() to translate into an interface name. */
885 uint32_t min_rx_bufsize; /**< Minimum size of RX buffer. */
886 uint32_t max_rx_pktlen; /**< Maximum configurable length of RX pkt. */
887 uint16_t max_rx_queues; /**< Maximum number of RX queues. */
888 uint16_t max_tx_queues; /**< Maximum number of TX queues. */
889 uint32_t max_mac_addrs; /**< Maximum number of MAC addresses. */
890 uint32_t max_hash_mac_addrs;
891 /** Maximum number of hash MAC addresses for MTA and UTA. */
892 uint16_t max_vfs; /**< Maximum number of VFs. */
893 uint16_t max_vmdq_pools; /**< Maximum number of VMDq pools. */
894 uint32_t rx_offload_capa; /**< Device RX offload capabilities. */
895 uint32_t tx_offload_capa; /**< Device TX offload capabilities. */
900 struct rte_eth_dev_callback;
901 /** @internal Structure to keep track of registered callbacks */
902 TAILQ_HEAD(rte_eth_dev_cb_list, rte_eth_dev_callback);
904 #define TCP_UGR_FLAG 0x20
905 #define TCP_ACK_FLAG 0x10
906 #define TCP_PSH_FLAG 0x08
907 #define TCP_RST_FLAG 0x04
908 #define TCP_SYN_FLAG 0x02
909 #define TCP_FIN_FLAG 0x01
910 #define TCP_FLAG_ALL 0x3F
913 * A structure used to define an ethertype filter.
915 struct rte_ethertype_filter {
916 uint16_t ethertype; /**< little endian. */
917 uint8_t priority_en; /**< compare priority enable. */
922 * A structure used to define an syn filter.
924 struct rte_syn_filter {
925 uint8_t hig_pri; /**< 1 means higher pri than 2tuple, 5tupe,
926 and flex filter, 0 means lower pri. */
930 * A structure used to define a 2tuple filter.
932 struct rte_2tuple_filter {
933 uint16_t dst_port; /**< big endian. */
936 uint16_t priority; /**< used when more than one filter matches. */
937 uint8_t dst_port_mask:1, /**< if mask is 1b, means not compare. */
942 * A structure used to define a flex filter.
944 struct rte_flex_filter {
946 uint32_t dwords[32]; /**< flex bytes in big endian. */
947 uint8_t mask[16]; /**< if mask bit is 1b, do not compare
948 corresponding byte in dwords. */
953 * A structure used to define a 5tuple filter.
955 struct rte_5tuple_filter {
956 uint32_t dst_ip; /**< destination IP address in big endian. */
957 uint32_t src_ip; /**< source IP address in big endian. */
958 uint16_t dst_port; /**< destination port in big endian. */
959 uint16_t src_port; /**< source Port big endian. */
960 uint8_t protocol; /**< l4 protocol. */
961 uint8_t tcp_flags; /**< tcp flags. */
962 uint16_t priority; /**< seven evels (001b-111b), 111b is highest,
963 used when more than one filter matches. */
964 uint8_t dst_ip_mask:1, /**< if mask is 1b, do not compare dst ip. */
965 src_ip_mask:1, /**< if mask is 1b, do not compare src ip. */
966 dst_port_mask:1, /**< if mask is 1b, do not compare dst port. */
967 src_port_mask:1, /**< if mask is 1b, do not compare src port. */
968 protocol_mask:1; /**< if mask is 1b, do not compare protocol. */
972 * Definitions of all functions exported by an Ethernet driver through the
973 * the generic structure of type *eth_dev_ops* supplied in the *rte_eth_dev*
974 * structure associated with an Ethernet device.
977 typedef int (*eth_dev_configure_t)(struct rte_eth_dev *dev);
978 /**< @internal Ethernet device configuration. */
980 typedef int (*eth_dev_start_t)(struct rte_eth_dev *dev);
981 /**< @internal Function used to start a configured Ethernet device. */
983 typedef void (*eth_dev_stop_t)(struct rte_eth_dev *dev);
984 /**< @internal Function used to stop a configured Ethernet device. */
986 typedef int (*eth_dev_set_link_up_t)(struct rte_eth_dev *dev);
987 /**< @internal Function used to link up a configured Ethernet device. */
989 typedef int (*eth_dev_set_link_down_t)(struct rte_eth_dev *dev);
990 /**< @internal Function used to link down a configured Ethernet device. */
992 typedef void (*eth_dev_close_t)(struct rte_eth_dev *dev);
993 /**< @internal Function used to close a configured Ethernet device. */
995 typedef void (*eth_promiscuous_enable_t)(struct rte_eth_dev *dev);
996 /**< @internal Function used to enable the RX promiscuous mode of an Ethernet device. */
998 typedef void (*eth_promiscuous_disable_t)(struct rte_eth_dev *dev);
999 /**< @internal Function used to disable the RX promiscuous mode of an Ethernet device. */
1001 typedef void (*eth_allmulticast_enable_t)(struct rte_eth_dev *dev);
1002 /**< @internal Enable the receipt of all multicast packets by an Ethernet device. */
1004 typedef void (*eth_allmulticast_disable_t)(struct rte_eth_dev *dev);
1005 /**< @internal Disable the receipt of all multicast packets by an Ethernet device. */
1007 typedef int (*eth_link_update_t)(struct rte_eth_dev *dev,
1008 int wait_to_complete);
1009 /**< @internal Get link speed, duplex mode and state (up/down) of an Ethernet device. */
1011 typedef void (*eth_stats_get_t)(struct rte_eth_dev *dev,
1012 struct rte_eth_stats *igb_stats);
1013 /**< @internal Get global I/O statistics of an Ethernet device. */
1015 typedef void (*eth_stats_reset_t)(struct rte_eth_dev *dev);
1016 /**< @internal Reset global I/O statistics of an Ethernet device to 0. */
1018 typedef int (*eth_queue_stats_mapping_set_t)(struct rte_eth_dev *dev,
1022 /**< @internal Set a queue statistics mapping for a tx/rx queue of an Ethernet device. */
1024 typedef void (*eth_dev_infos_get_t)(struct rte_eth_dev *dev,
1025 struct rte_eth_dev_info *dev_info);
1026 /**< @internal Get specific informations of an Ethernet device. */
1028 typedef int (*eth_queue_start_t)(struct rte_eth_dev *dev,
1030 /**< @internal Start rx and tx of a queue of an Ethernet device. */
1032 typedef int (*eth_queue_stop_t)(struct rte_eth_dev *dev,
1034 /**< @internal Stop rx and tx of a queue of an Ethernet device. */
1036 typedef int (*eth_rx_queue_setup_t)(struct rte_eth_dev *dev,
1037 uint16_t rx_queue_id,
1038 uint16_t nb_rx_desc,
1039 unsigned int socket_id,
1040 const struct rte_eth_rxconf *rx_conf,
1041 struct rte_mempool *mb_pool);
1042 /**< @internal Set up a receive queue of an Ethernet device. */
1044 typedef int (*eth_tx_queue_setup_t)(struct rte_eth_dev *dev,
1045 uint16_t tx_queue_id,
1046 uint16_t nb_tx_desc,
1047 unsigned int socket_id,
1048 const struct rte_eth_txconf *tx_conf);
1049 /**< @internal Setup a transmit queue of an Ethernet device. */
1051 typedef void (*eth_queue_release_t)(void *queue);
1052 /**< @internal Release memory resources allocated by given RX/TX queue. */
1054 typedef uint32_t (*eth_rx_queue_count_t)(struct rte_eth_dev *dev,
1055 uint16_t rx_queue_id);
1056 /**< @Get number of available descriptors on a receive queue of an Ethernet device. */
1058 typedef int (*eth_rx_descriptor_done_t)(void *rxq, uint16_t offset);
1059 /**< @Check DD bit of specific RX descriptor */
1061 typedef int (*vlan_filter_set_t)(struct rte_eth_dev *dev,
1064 /**< @internal filtering of a VLAN Tag Identifier by an Ethernet device. */
1066 typedef void (*vlan_tpid_set_t)(struct rte_eth_dev *dev,
1068 /**< @internal set the outer VLAN-TPID by an Ethernet device. */
1070 typedef void (*vlan_offload_set_t)(struct rte_eth_dev *dev, int mask);
1071 /**< @internal set VLAN offload function by an Ethernet device. */
1073 typedef void (*vlan_strip_queue_set_t)(struct rte_eth_dev *dev,
1074 uint16_t rx_queue_id,
1076 /**< @internal VLAN stripping enable/disable by an queue of Ethernet device. */
1078 typedef uint16_t (*eth_rx_burst_t)(void *rxq,
1079 struct rte_mbuf **rx_pkts,
1081 /**< @internal Retrieve input packets from a receive queue of an Ethernet device. */
1083 typedef uint16_t (*eth_tx_burst_t)(void *txq,
1084 struct rte_mbuf **tx_pkts,
1086 /**< @internal Send output packets on a transmit queue of an Ethernet device. */
1088 typedef int (*fdir_add_signature_filter_t)(struct rte_eth_dev *dev,
1089 struct rte_fdir_filter *fdir_ftr,
1091 /**< @internal Setup a new signature filter rule on an Ethernet device */
1093 typedef int (*fdir_update_signature_filter_t)(struct rte_eth_dev *dev,
1094 struct rte_fdir_filter *fdir_ftr,
1096 /**< @internal Update a signature filter rule on an Ethernet device */
1098 typedef int (*fdir_remove_signature_filter_t)(struct rte_eth_dev *dev,
1099 struct rte_fdir_filter *fdir_ftr);
1100 /**< @internal Remove a signature filter rule on an Ethernet device */
1102 typedef void (*fdir_infos_get_t)(struct rte_eth_dev *dev,
1103 struct rte_eth_fdir *fdir);
1104 /**< @internal Get information about fdir status */
1106 typedef int (*fdir_add_perfect_filter_t)(struct rte_eth_dev *dev,
1107 struct rte_fdir_filter *fdir_ftr,
1108 uint16_t soft_id, uint8_t rx_queue,
1110 /**< @internal Setup a new perfect filter rule on an Ethernet device */
1112 typedef int (*fdir_update_perfect_filter_t)(struct rte_eth_dev *dev,
1113 struct rte_fdir_filter *fdir_ftr,
1114 uint16_t soft_id, uint8_t rx_queue,
1116 /**< @internal Update a perfect filter rule on an Ethernet device */
1118 typedef int (*fdir_remove_perfect_filter_t)(struct rte_eth_dev *dev,
1119 struct rte_fdir_filter *fdir_ftr,
1121 /**< @internal Remove a perfect filter rule on an Ethernet device */
1123 typedef int (*fdir_set_masks_t)(struct rte_eth_dev *dev,
1124 struct rte_fdir_masks *fdir_masks);
1125 /**< @internal Setup flow director masks on an Ethernet device */
1127 typedef int (*flow_ctrl_set_t)(struct rte_eth_dev *dev,
1128 struct rte_eth_fc_conf *fc_conf);
1129 /**< @internal Setup flow control parameter on an Ethernet device */
1131 typedef int (*priority_flow_ctrl_set_t)(struct rte_eth_dev *dev,
1132 struct rte_eth_pfc_conf *pfc_conf);
1133 /**< @internal Setup priority flow control parameter on an Ethernet device */
1135 typedef int (*reta_update_t)(struct rte_eth_dev *dev,
1136 struct rte_eth_rss_reta *reta_conf);
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 *reta_conf);
1141 /**< @internal Query RSS redirection table on an Ethernet device */
1143 typedef int (*rss_hash_update_t)(struct rte_eth_dev *dev,
1144 struct rte_eth_rss_conf *rss_conf);
1145 /**< @internal Update RSS hash configuration of an Ethernet device */
1147 typedef int (*rss_hash_conf_get_t)(struct rte_eth_dev *dev,
1148 struct rte_eth_rss_conf *rss_conf);
1149 /**< @internal Get current RSS hash configuration of an Ethernet device */
1151 typedef int (*eth_dev_led_on_t)(struct rte_eth_dev *dev);
1152 /**< @internal Turn on SW controllable LED on an Ethernet device */
1154 typedef int (*eth_dev_led_off_t)(struct rte_eth_dev *dev);
1155 /**< @internal Turn off SW controllable LED on an Ethernet device */
1157 typedef void (*eth_mac_addr_remove_t)(struct rte_eth_dev *dev, uint32_t index);
1158 /**< @internal Remove MAC address from receive address register */
1160 typedef void (*eth_mac_addr_add_t)(struct rte_eth_dev *dev,
1161 struct ether_addr *mac_addr,
1164 /**< @internal Set a MAC address into Receive Address Address Register */
1166 typedef int (*eth_uc_hash_table_set_t)(struct rte_eth_dev *dev,
1167 struct ether_addr *mac_addr,
1169 /**< @internal Set a Unicast Hash bitmap */
1171 typedef int (*eth_uc_all_hash_table_set_t)(struct rte_eth_dev *dev,
1173 /**< @internal Set all Unicast Hash bitmap */
1175 typedef int (*eth_set_vf_rx_mode_t)(struct rte_eth_dev *dev,
1179 /**< @internal Set a VF receive mode */
1181 typedef int (*eth_set_vf_rx_t)(struct rte_eth_dev *dev,
1184 /**< @internal Set a VF receive mode */
1186 typedef int (*eth_set_vf_tx_t)(struct rte_eth_dev *dev,
1189 /**< @internal Enable or disable a VF transmit */
1191 typedef int (*eth_set_vf_vlan_filter_t)(struct rte_eth_dev *dev,
1195 /**< @internal Set VF VLAN pool filter */
1197 typedef int (*eth_set_queue_rate_limit_t)(struct rte_eth_dev *dev,
1200 /**< @internal Set queue TX rate */
1202 typedef int (*eth_set_vf_rate_limit_t)(struct rte_eth_dev *dev,
1206 /**< @internal Set VF TX rate */
1208 typedef int (*eth_mirror_rule_set_t)(struct rte_eth_dev *dev,
1209 struct rte_eth_vmdq_mirror_conf *mirror_conf,
1212 /**< @internal Add a traffic mirroring rule on an Ethernet device */
1214 typedef int (*eth_mirror_rule_reset_t)(struct rte_eth_dev *dev,
1216 /**< @internal Remove a traffic mirroring rule on an Ethernet device */
1218 #ifdef RTE_NIC_BYPASS
1221 RTE_BYPASS_MODE_NONE,
1222 RTE_BYPASS_MODE_NORMAL,
1223 RTE_BYPASS_MODE_BYPASS,
1224 RTE_BYPASS_MODE_ISOLATE,
1225 RTE_BYPASS_MODE_NUM,
1228 #define RTE_BYPASS_MODE_VALID(x) \
1229 ((x) > RTE_BYPASS_MODE_NONE && (x) < RTE_BYPASS_MODE_NUM)
1232 RTE_BYPASS_EVENT_NONE,
1233 RTE_BYPASS_EVENT_START,
1234 RTE_BYPASS_EVENT_OS_ON = RTE_BYPASS_EVENT_START,
1235 RTE_BYPASS_EVENT_POWER_ON,
1236 RTE_BYPASS_EVENT_OS_OFF,
1237 RTE_BYPASS_EVENT_POWER_OFF,
1238 RTE_BYPASS_EVENT_TIMEOUT,
1239 RTE_BYPASS_EVENT_NUM
1242 #define RTE_BYPASS_EVENT_VALID(x) \
1243 ((x) > RTE_BYPASS_EVENT_NONE && (x) < RTE_BYPASS_MODE_NUM)
1246 RTE_BYPASS_TMT_OFF, /* timeout disabled. */
1247 RTE_BYPASS_TMT_1_5_SEC, /* timeout for 1.5 seconds */
1248 RTE_BYPASS_TMT_2_SEC, /* timeout for 2 seconds */
1249 RTE_BYPASS_TMT_3_SEC, /* timeout for 3 seconds */
1250 RTE_BYPASS_TMT_4_SEC, /* timeout for 4 seconds */
1251 RTE_BYPASS_TMT_8_SEC, /* timeout for 8 seconds */
1252 RTE_BYPASS_TMT_16_SEC, /* timeout for 16 seconds */
1253 RTE_BYPASS_TMT_32_SEC, /* timeout for 32 seconds */
1257 #define RTE_BYPASS_TMT_VALID(x) \
1258 ((x) == RTE_BYPASS_TMT_OFF || \
1259 ((x) > RTE_BYPASS_TMT_OFF && (x) < RTE_BYPASS_TMT_NUM))
1261 typedef void (*bypass_init_t)(struct rte_eth_dev *dev);
1262 typedef int32_t (*bypass_state_set_t)(struct rte_eth_dev *dev, uint32_t *new_state);
1263 typedef int32_t (*bypass_state_show_t)(struct rte_eth_dev *dev, uint32_t *state);
1264 typedef int32_t (*bypass_event_set_t)(struct rte_eth_dev *dev, uint32_t state, uint32_t event);
1265 typedef int32_t (*bypass_event_show_t)(struct rte_eth_dev *dev, uint32_t event_shift, uint32_t *event);
1266 typedef int32_t (*bypass_wd_timeout_set_t)(struct rte_eth_dev *dev, uint32_t timeout);
1267 typedef int32_t (*bypass_wd_timeout_show_t)(struct rte_eth_dev *dev, uint32_t *wd_timeout);
1268 typedef int32_t (*bypass_ver_show_t)(struct rte_eth_dev *dev, uint32_t *ver);
1269 typedef int32_t (*bypass_wd_reset_t)(struct rte_eth_dev *dev);
1272 typedef int (*eth_add_syn_filter_t)(struct rte_eth_dev *dev,
1273 struct rte_syn_filter *filter, uint16_t rx_queue);
1274 /**< @internal add syn filter rule on an Ethernet device */
1276 typedef int (*eth_remove_syn_filter_t)(struct rte_eth_dev *dev);
1277 /**< @internal remove syn filter rule on an Ethernet device */
1279 typedef int (*eth_get_syn_filter_t)(struct rte_eth_dev *dev,
1280 struct rte_syn_filter *filter, uint16_t *rx_queue);
1281 /**< @internal Get syn filter rule on an Ethernet device */
1283 typedef int (*eth_add_ethertype_filter_t)(struct rte_eth_dev *dev,
1284 uint16_t index, struct rte_ethertype_filter *filter,
1286 /**< @internal Setup a new ethertype filter rule on an Ethernet device */
1288 typedef int (*eth_remove_ethertype_filter_t)(struct rte_eth_dev *dev,
1290 /**< @internal Remove an ethertype filter rule on an Ethernet device */
1292 typedef int (*eth_get_ethertype_filter_t)(struct rte_eth_dev *dev,
1293 uint16_t index, struct rte_ethertype_filter *filter,
1294 uint16_t *rx_queue);
1295 /**< @internal Get an ethertype filter rule on an Ethernet device */
1297 typedef int (*eth_add_2tuple_filter_t)(struct rte_eth_dev *dev,
1298 uint16_t index, struct rte_2tuple_filter *filter,
1300 /**< @internal Setup a new 2tuple filter rule on an Ethernet device */
1302 typedef int (*eth_remove_2tuple_filter_t)(struct rte_eth_dev *dev,
1304 /**< @internal Remove a 2tuple filter rule on an Ethernet device */
1306 typedef int (*eth_get_2tuple_filter_t)(struct rte_eth_dev *dev,
1307 uint16_t index, struct rte_2tuple_filter *filter,
1308 uint16_t *rx_queue);
1309 /**< @internal Get a 2tuple filter rule on an Ethernet device */
1311 typedef int (*eth_add_5tuple_filter_t)(struct rte_eth_dev *dev,
1312 uint16_t index, struct rte_5tuple_filter *filter,
1314 /**< @internal Setup a new 5tuple filter rule on an Ethernet device */
1316 typedef int (*eth_remove_5tuple_filter_t)(struct rte_eth_dev *dev,
1318 /**< @internal Remove a 5tuple filter rule on an Ethernet device */
1320 typedef int (*eth_get_5tuple_filter_t)(struct rte_eth_dev *dev,
1321 uint16_t index, struct rte_5tuple_filter *filter,
1322 uint16_t *rx_queue);
1323 /**< @internal Get a 5tuple filter rule on an Ethernet device */
1325 typedef int (*eth_add_flex_filter_t)(struct rte_eth_dev *dev,
1326 uint16_t index, struct rte_flex_filter *filter,
1328 /**< @internal Setup a new flex filter rule on an Ethernet device */
1330 typedef int (*eth_remove_flex_filter_t)(struct rte_eth_dev *dev,
1332 /**< @internal Remove a flex filter rule on an Ethernet device */
1334 typedef int (*eth_get_flex_filter_t)(struct rte_eth_dev *dev,
1335 uint16_t index, struct rte_flex_filter *filter,
1336 uint16_t *rx_queue);
1337 /**< @internal Get a flex filter rule on an Ethernet device */
1340 * @internal A structure containing the functions exported by an Ethernet driver.
1342 struct eth_dev_ops {
1343 eth_dev_configure_t dev_configure; /**< Configure device. */
1344 eth_dev_start_t dev_start; /**< Start device. */
1345 eth_dev_stop_t dev_stop; /**< Stop device. */
1346 eth_dev_set_link_up_t dev_set_link_up; /**< Device link up. */
1347 eth_dev_set_link_down_t dev_set_link_down; /**< Device link down. */
1348 eth_dev_close_t dev_close; /**< Close device. */
1349 eth_promiscuous_enable_t promiscuous_enable; /**< Promiscuous ON. */
1350 eth_promiscuous_disable_t promiscuous_disable;/**< Promiscuous OFF. */
1351 eth_allmulticast_enable_t allmulticast_enable;/**< RX multicast ON. */
1352 eth_allmulticast_disable_t allmulticast_disable;/**< RX multicast OF. */
1353 eth_link_update_t link_update; /**< Get device link state. */
1354 eth_stats_get_t stats_get; /**< Get device statistics. */
1355 eth_stats_reset_t stats_reset; /**< Reset device statistics. */
1356 eth_queue_stats_mapping_set_t queue_stats_mapping_set;
1357 /**< Configure per queue stat counter mapping. */
1358 eth_dev_infos_get_t dev_infos_get; /**< Get device info. */
1359 vlan_filter_set_t vlan_filter_set; /**< Filter VLAN Setup. */
1360 vlan_tpid_set_t vlan_tpid_set; /**< Outer VLAN TPID Setup. */
1361 vlan_strip_queue_set_t vlan_strip_queue_set; /**< VLAN Stripping on queue. */
1362 vlan_offload_set_t vlan_offload_set; /**< Set VLAN Offload. */
1363 eth_queue_start_t rx_queue_start;/**< Start RX for a queue.*/
1364 eth_queue_stop_t rx_queue_stop;/**< Stop RX for a queue.*/
1365 eth_queue_start_t tx_queue_start;/**< Start TX for a queue.*/
1366 eth_queue_stop_t tx_queue_stop;/**< Stop TX for a queue.*/
1367 eth_rx_queue_setup_t rx_queue_setup;/**< Set up device RX queue.*/
1368 eth_queue_release_t rx_queue_release;/**< Release RX queue.*/
1369 eth_rx_queue_count_t rx_queue_count; /**< Get Rx queue count. */
1370 eth_rx_descriptor_done_t rx_descriptor_done; /**< Check rxd DD bit */
1371 eth_tx_queue_setup_t tx_queue_setup;/**< Set up device TX queue.*/
1372 eth_queue_release_t tx_queue_release;/**< Release TX queue.*/
1373 eth_dev_led_on_t dev_led_on; /**< Turn on LED. */
1374 eth_dev_led_off_t dev_led_off; /**< Turn off LED. */
1375 flow_ctrl_set_t flow_ctrl_set; /**< Setup flow control. */
1376 priority_flow_ctrl_set_t priority_flow_ctrl_set; /**< Setup priority flow control.*/
1377 eth_mac_addr_remove_t mac_addr_remove; /**< Remove MAC address */
1378 eth_mac_addr_add_t mac_addr_add; /**< Add a MAC address */
1379 eth_uc_hash_table_set_t uc_hash_table_set; /**< Set Unicast Table Array */
1380 eth_uc_all_hash_table_set_t uc_all_hash_table_set; /**< Set Unicast hash bitmap */
1381 eth_mirror_rule_set_t mirror_rule_set; /**< Add a traffic mirror rule.*/
1382 eth_mirror_rule_reset_t mirror_rule_reset; /**< reset a traffic mirror rule.*/
1383 eth_set_vf_rx_mode_t set_vf_rx_mode; /**< Set VF RX mode */
1384 eth_set_vf_rx_t set_vf_rx; /**< enable/disable a VF receive */
1385 eth_set_vf_tx_t set_vf_tx; /**< enable/disable a VF transmit */
1386 eth_set_vf_vlan_filter_t set_vf_vlan_filter; /**< Set VF VLAN filter */
1387 eth_set_queue_rate_limit_t set_queue_rate_limit; /**< Set queue rate limit */
1388 eth_set_vf_rate_limit_t set_vf_rate_limit; /**< Set VF rate limit */
1390 /** Add a signature filter. */
1391 fdir_add_signature_filter_t fdir_add_signature_filter;
1392 /** Update a signature filter. */
1393 fdir_update_signature_filter_t fdir_update_signature_filter;
1394 /** Remove a signature filter. */
1395 fdir_remove_signature_filter_t fdir_remove_signature_filter;
1396 /** Get information about FDIR status. */
1397 fdir_infos_get_t fdir_infos_get;
1398 /** Add a perfect filter. */
1399 fdir_add_perfect_filter_t fdir_add_perfect_filter;
1400 /** Update a perfect filter. */
1401 fdir_update_perfect_filter_t fdir_update_perfect_filter;
1402 /** Remove a perfect filter. */
1403 fdir_remove_perfect_filter_t fdir_remove_perfect_filter;
1404 /** Setup masks for FDIR filtering. */
1405 fdir_set_masks_t fdir_set_masks;
1406 /** Update redirection table. */
1407 reta_update_t reta_update;
1408 /** Query redirection table. */
1409 reta_query_t reta_query;
1410 /* bypass control */
1411 #ifdef RTE_NIC_BYPASS
1412 bypass_init_t bypass_init;
1413 bypass_state_set_t bypass_state_set;
1414 bypass_state_show_t bypass_state_show;
1415 bypass_event_set_t bypass_event_set;
1416 bypass_event_show_t bypass_event_show;
1417 bypass_wd_timeout_set_t bypass_wd_timeout_set;
1418 bypass_wd_timeout_show_t bypass_wd_timeout_show;
1419 bypass_ver_show_t bypass_ver_show;
1420 bypass_wd_reset_t bypass_wd_reset;
1423 /** Configure RSS hash protocols. */
1424 rss_hash_update_t rss_hash_update;
1425 /** Get current RSS hash configuration. */
1426 rss_hash_conf_get_t rss_hash_conf_get;
1427 eth_add_syn_filter_t add_syn_filter; /**< add syn filter. */
1428 eth_remove_syn_filter_t remove_syn_filter; /**< remove syn filter. */
1429 eth_get_syn_filter_t get_syn_filter; /**< get syn filter. */
1430 eth_add_ethertype_filter_t add_ethertype_filter; /**< add ethertype filter. */
1431 eth_remove_ethertype_filter_t remove_ethertype_filter; /**< remove ethertype filter. */
1432 eth_get_ethertype_filter_t get_ethertype_filter; /**< get ethertype filter. */
1433 eth_add_2tuple_filter_t add_2tuple_filter; /**< add 2tuple filter. */
1434 eth_remove_2tuple_filter_t remove_2tuple_filter; /**< remove 2tuple filter. */
1435 eth_get_2tuple_filter_t get_2tuple_filter; /**< get 2tuple filter. */
1436 eth_add_5tuple_filter_t add_5tuple_filter; /**< add 5tuple filter. */
1437 eth_remove_5tuple_filter_t remove_5tuple_filter; /**< remove 5tuple filter. */
1438 eth_get_5tuple_filter_t get_5tuple_filter; /**< get 5tuple filter. */
1439 eth_add_flex_filter_t add_flex_filter; /**< add flex filter. */
1440 eth_remove_flex_filter_t remove_flex_filter; /**< remove flex filter. */
1441 eth_get_flex_filter_t get_flex_filter; /**< get flex filter. */
1446 * The generic data structure associated with each ethernet device.
1448 * Pointers to burst-oriented packet receive and transmit functions are
1449 * located at the beginning of the structure, along with the pointer to
1450 * where all the data elements for the particular device are stored in shared
1451 * memory. This split allows the function pointer and driver data to be per-
1452 * process, while the actual configuration data for the device is shared.
1454 struct rte_eth_dev {
1455 eth_rx_burst_t rx_pkt_burst; /**< Pointer to PMD receive function. */
1456 eth_tx_burst_t tx_pkt_burst; /**< Pointer to PMD transmit function. */
1457 struct rte_eth_dev_data *data; /**< Pointer to device data */
1458 const struct eth_driver *driver;/**< Driver for this device */
1459 struct eth_dev_ops *dev_ops; /**< Functions exported by PMD */
1460 struct rte_pci_device *pci_dev; /**< PCI info. supplied by probing */
1461 struct rte_eth_dev_cb_list callbacks; /**< User application callbacks */
1464 struct rte_eth_dev_sriov {
1465 uint8_t active; /**< SRIOV is active with 16, 32 or 64 pools */
1466 uint8_t nb_q_per_pool; /**< rx queue number per pool */
1467 uint16_t def_vmdq_idx; /**< Default pool num used for PF */
1468 uint16_t def_pool_q_idx; /**< Default pool queue start reg index */
1470 #define RTE_ETH_DEV_SRIOV(dev) ((dev)->data->sriov)
1474 * The data part, with no function pointers, associated with each ethernet device.
1476 * This structure is safe to place in shared memory to be common among different
1477 * processes in a multi-process configuration.
1479 struct rte_eth_dev_data {
1480 void **rx_queues; /**< Array of pointers to RX queues. */
1481 void **tx_queues; /**< Array of pointers to TX queues. */
1482 uint16_t nb_rx_queues; /**< Number of RX queues. */
1483 uint16_t nb_tx_queues; /**< Number of TX queues. */
1485 struct rte_eth_dev_sriov sriov; /**< SRIOV data */
1487 void *dev_private; /**< PMD-specific private data */
1489 struct rte_eth_link dev_link;
1490 /**< Link-level information & status */
1492 struct rte_eth_conf dev_conf; /**< Configuration applied to device. */
1493 uint16_t max_frame_size; /**< Default is ETHER_MAX_LEN (1518). */
1495 uint64_t rx_mbuf_alloc_failed; /**< RX ring mbuf allocation failures. */
1496 struct ether_addr* mac_addrs;/**< Device Ethernet Link address. */
1497 uint64_t mac_pool_sel[ETH_NUM_RECEIVE_MAC_ADDR];
1498 /** bitmap array of associating Ethernet MAC addresses to pools */
1499 struct ether_addr* hash_mac_addrs;
1500 /** Device Ethernet MAC addresses of hash filtering. */
1501 uint8_t port_id; /**< Device [external] port identifier. */
1502 uint8_t promiscuous : 1, /**< RX promiscuous mode ON(1) / OFF(0). */
1503 scattered_rx : 1, /**< RX of scattered packets is ON(1) / OFF(0) */
1504 all_multicast : 1, /**< RX all multicast mode ON(1) / OFF(0). */
1505 dev_started : 1; /**< Device state: STARTED(1) / STOPPED(0). */
1510 * The pool of *rte_eth_dev* structures. The size of the pool
1511 * is configured at compile-time in the <rte_ethdev.c> file.
1513 extern struct rte_eth_dev rte_eth_devices[];
1516 * Get the total number of Ethernet devices that have been successfully
1517 * initialized by the [matching] Ethernet driver during the PCI probing phase.
1518 * All devices whose port identifier is in the range
1519 * [0, rte_eth_dev_count() - 1] can be operated on by network applications.
1522 * - The total number of usable Ethernet devices.
1524 extern uint8_t rte_eth_dev_count(void);
1527 * Function for internal use by dummy drivers primarily, e.g. ring-based
1529 * Allocates a new ethdev slot for an ethernet device and returns the pointer
1530 * to that slot for the driver to use.
1533 * - Slot in the rte_dev_devices array for a new device;
1535 struct rte_eth_dev *rte_eth_dev_allocate(void);
1540 * Initialization function of an Ethernet driver invoked for each matching
1541 * Ethernet PCI device detected during the PCI probing phase.
1544 * The pointer to the [matching] Ethernet driver structure supplied by
1545 * the PMD when it registered itself.
1547 * The *eth_dev* pointer is the address of the *rte_eth_dev* structure
1548 * associated with the matching device and which have been [automatically]
1549 * allocated in the *rte_eth_devices* array.
1550 * The *eth_dev* structure is supplied to the driver initialization function
1551 * with the following fields already initialized:
1553 * - *pci_dev*: Holds the pointers to the *rte_pci_device* structure which
1554 * contains the generic PCI information of the matching device.
1556 * - *dev_private*: Holds a pointer to the device private data structure.
1558 * - *max_frame_size*: Contains the default Ethernet maximum frame length
1561 * - *port_id*: Contains the port index of the device (actually the index
1562 * of the *eth_dev* structure in the *rte_eth_devices* array).
1565 * - 0: Success, the device is properly initialized by the driver.
1566 * In particular, the driver MUST have set up the *dev_ops* pointer
1567 * of the *eth_dev* structure.
1568 * - <0: Error code of the device initialization failure.
1570 typedef int (*eth_dev_init_t)(struct eth_driver *eth_drv,
1571 struct rte_eth_dev *eth_dev);
1575 * The structure associated with a PMD Ethernet driver.
1577 * Each Ethernet driver acts as a PCI driver and is represented by a generic
1578 * *eth_driver* structure that holds:
1580 * - An *rte_pci_driver* structure (which must be the first field).
1582 * - The *eth_dev_init* function invoked for each matching PCI device.
1584 * - The size of the private data to allocate for each matching device.
1587 struct rte_pci_driver pci_drv; /**< The PMD is also a PCI driver. */
1588 eth_dev_init_t eth_dev_init; /**< Device init function. */
1589 unsigned int dev_private_size; /**< Size of device private data. */
1594 * A function invoked by the initialization function of an Ethernet driver
1595 * to simultaneously register itself as a PCI driver and as an Ethernet
1596 * Poll Mode Driver (PMD).
1599 * The pointer to the *eth_driver* structure associated with
1600 * the Ethernet driver.
1602 extern void rte_eth_driver_register(struct eth_driver *eth_drv);
1605 * Configure an Ethernet device.
1606 * This function must be invoked first before any other function in the
1607 * Ethernet API. This function can also be re-invoked when a device is in the
1611 * The port identifier of the Ethernet device to configure.
1612 * @param nb_rx_queue
1613 * The number of receive queues to set up for the Ethernet device.
1614 * @param nb_tx_queue
1615 * The number of transmit queues to set up for the Ethernet device.
1617 * The pointer to the configuration data to be used for the Ethernet device.
1618 * The *rte_eth_conf* structure includes:
1619 * - the hardware offload features to activate, with dedicated fields for
1620 * each statically configurable offload hardware feature provided by
1621 * Ethernet devices, such as IP checksum or VLAN tag stripping for
1623 * - the Receive Side Scaling (RSS) configuration when using multiple RX
1626 * Embedding all configuration information in a single data structure
1627 * is the more flexible method that allows the addition of new features
1628 * without changing the syntax of the API.
1630 * - 0: Success, device configured.
1631 * - <0: Error code returned by the driver configuration function.
1633 extern int rte_eth_dev_configure(uint8_t port_id,
1634 uint16_t nb_rx_queue,
1635 uint16_t nb_tx_queue,
1636 const struct rte_eth_conf *eth_conf);
1639 * Allocate and set up a receive queue for an Ethernet device.
1641 * The function allocates a contiguous block of memory for *nb_rx_desc*
1642 * receive descriptors from a memory zone associated with *socket_id*
1643 * and initializes each receive descriptor with a network buffer allocated
1644 * from the memory pool *mb_pool*.
1647 * The port identifier of the Ethernet device.
1648 * @param rx_queue_id
1649 * The index of the receive queue to set up.
1650 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1651 * to rte_eth_dev_configure().
1653 * The number of receive descriptors to allocate for the receive ring.
1655 * The *socket_id* argument is the socket identifier in case of NUMA.
1656 * The value can be *SOCKET_ID_ANY* if there is no NUMA constraint for
1657 * the DMA memory allocated for the receive descriptors of the ring.
1659 * The pointer to the configuration data to be used for the receive queue.
1660 * The *rx_conf* structure contains an *rx_thresh* structure with the values
1661 * of the Prefetch, Host, and Write-Back threshold registers of the receive
1664 * The pointer to the memory pool from which to allocate *rte_mbuf* network
1665 * memory buffers to populate each descriptor of the receive ring.
1667 * - 0: Success, receive queue correctly set up.
1668 * - -EINVAL: The size of network buffers which can be allocated from the
1669 * memory pool does not fit the various buffer sizes allowed by the
1670 * device controller.
1671 * - -ENOMEM: Unable to allocate the receive ring descriptors or to
1672 * allocate network memory buffers from the memory pool when
1673 * initializing receive descriptors.
1675 extern int rte_eth_rx_queue_setup(uint8_t port_id, uint16_t rx_queue_id,
1676 uint16_t nb_rx_desc, unsigned int socket_id,
1677 const struct rte_eth_rxconf *rx_conf,
1678 struct rte_mempool *mb_pool);
1681 * Allocate and set up a transmit queue for an Ethernet device.
1684 * The port identifier of the Ethernet device.
1685 * @param tx_queue_id
1686 * The index of the transmit queue to set up.
1687 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1688 * to rte_eth_dev_configure().
1690 * The number of transmit descriptors to allocate for the transmit ring.
1692 * The *socket_id* argument is the socket identifier in case of NUMA.
1693 * Its value can be *SOCKET_ID_ANY* if there is no NUMA constraint for
1694 * the DMA memory allocated for the transmit descriptors of the ring.
1696 * The pointer to the configuration data to be used for the transmit queue.
1697 * The *tx_conf* structure contains the following data:
1698 * - The *tx_thresh* structure with the values of the Prefetch, Host, and
1699 * Write-Back threshold registers of the transmit ring.
1700 * When setting Write-Back threshold to the value greater then zero,
1701 * *tx_rs_thresh* value should be explicitly set to one.
1702 * - The *tx_free_thresh* value indicates the [minimum] number of network
1703 * buffers that must be pending in the transmit ring to trigger their
1704 * [implicit] freeing by the driver transmit function.
1705 * - The *tx_rs_thresh* value indicates the [minimum] number of transmit
1706 * descriptors that must be pending in the transmit ring before setting the
1707 * RS bit on a descriptor by the driver transmit function.
1708 * The *tx_rs_thresh* value should be less or equal then
1709 * *tx_free_thresh* value, and both of them should be less then
1711 * - The *txq_flags* member contains flags to pass to the TX queue setup
1712 * function to configure the behavior of the TX queue. This should be set
1713 * to 0 if no special configuration is required.
1715 * Note that setting *tx_free_thresh* or *tx_rs_thresh* value to 0 forces
1716 * the transmit function to use default values.
1718 * - 0: Success, the transmit queue is correctly set up.
1719 * - -ENOMEM: Unable to allocate the transmit ring descriptors.
1721 extern int rte_eth_tx_queue_setup(uint8_t port_id, uint16_t tx_queue_id,
1722 uint16_t nb_tx_desc, unsigned int socket_id,
1723 const struct rte_eth_txconf *tx_conf);
1726 * Return the NUMA socket to which an Ethernet device is connected
1729 * The port identifier of the Ethernet device
1731 * The NUMA socket id to which the Ethernet device is connected or
1732 * a default of zero if the socket could not be determined.
1733 * -1 is returned is the port_id value is out of range.
1735 extern int rte_eth_dev_socket_id(uint8_t port_id);
1738 * Start specified RX queue of a port
1741 * The port identifier of the Ethernet device
1742 * @param rx_queue_id
1743 * The index of the rx queue to update the ring.
1744 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1745 * to rte_eth_dev_configure().
1747 * - 0: Success, the transmit queue is correctly set up.
1748 * - -EINVAL: The port_id or the queue_id out of range.
1749 * - -ENOTSUP: The function not supported in PMD driver.
1751 extern int rte_eth_dev_rx_queue_start(uint8_t port_id, uint16_t rx_queue_id);
1754 * Stop specified RX queue of a port
1757 * The port identifier of the Ethernet device
1758 * @param rx_queue_id
1759 * The index of the rx queue to update the ring.
1760 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1761 * to rte_eth_dev_configure().
1763 * - 0: Success, the transmit queue is correctly set up.
1764 * - -EINVAL: The port_id or the queue_id out of range.
1765 * - -ENOTSUP: The function not supported in PMD driver.
1767 extern int rte_eth_dev_rx_queue_stop(uint8_t port_id, uint16_t rx_queue_id);
1770 * Start specified TX queue of a port
1773 * The port identifier of the Ethernet device
1774 * @param tx_queue_id
1775 * The index of the tx queue to update the ring.
1776 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1777 * to rte_eth_dev_configure().
1779 * - 0: Success, the transmit queue is correctly set up.
1780 * - -EINVAL: The port_id or the queue_id out of range.
1781 * - -ENOTSUP: The function not supported in PMD driver.
1783 extern int rte_eth_dev_tx_queue_start(uint8_t port_id, uint16_t tx_queue_id);
1786 * Stop specified TX queue of a port
1789 * The port identifier of the Ethernet device
1790 * @param tx_queue_id
1791 * The index of the tx queue to update the ring.
1792 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1793 * to rte_eth_dev_configure().
1795 * - 0: Success, the transmit queue is correctly set up.
1796 * - -EINVAL: The port_id or the queue_id out of range.
1797 * - -ENOTSUP: The function not supported in PMD driver.
1799 extern int rte_eth_dev_tx_queue_stop(uint8_t port_id, uint16_t tx_queue_id);
1804 * Start an Ethernet device.
1806 * The device start step is the last one and consists of setting the configured
1807 * offload features and in starting the transmit and the receive units of the
1809 * On success, all basic functions exported by the Ethernet API (link status,
1810 * receive/transmit, and so on) can be invoked.
1813 * The port identifier of the Ethernet device.
1815 * - 0: Success, Ethernet device started.
1816 * - <0: Error code of the driver device start function.
1818 extern int rte_eth_dev_start(uint8_t port_id);
1821 * Stop an Ethernet device. The device can be restarted with a call to
1822 * rte_eth_dev_start()
1825 * The port identifier of the Ethernet device.
1827 extern void rte_eth_dev_stop(uint8_t port_id);
1831 * Link up an Ethernet device.
1833 * Set device link up will re-enable the device rx/tx
1834 * functionality after it is previously set device linked down.
1837 * The port identifier of the Ethernet device.
1839 * - 0: Success, Ethernet device linked up.
1840 * - <0: Error code of the driver device link up function.
1842 extern int rte_eth_dev_set_link_up(uint8_t port_id);
1845 * Link down an Ethernet device.
1846 * The device rx/tx functionality will be disabled if success,
1847 * and it can be re-enabled with a call to
1848 * rte_eth_dev_set_link_up()
1851 * The port identifier of the Ethernet device.
1853 extern int rte_eth_dev_set_link_down(uint8_t port_id);
1856 * Close an Ethernet device. The device cannot be restarted!
1859 * The port identifier of the Ethernet device.
1861 extern void rte_eth_dev_close(uint8_t port_id);
1864 * Enable receipt in promiscuous mode for an Ethernet device.
1867 * The port identifier of the Ethernet device.
1869 extern void rte_eth_promiscuous_enable(uint8_t port_id);
1872 * Disable receipt in promiscuous mode for an Ethernet device.
1875 * The port identifier of the Ethernet device.
1877 extern void rte_eth_promiscuous_disable(uint8_t port_id);
1880 * Return the value of promiscuous mode for an Ethernet device.
1883 * The port identifier of the Ethernet device.
1885 * - (1) if promiscuous is enabled
1886 * - (0) if promiscuous is disabled.
1889 extern int rte_eth_promiscuous_get(uint8_t port_id);
1892 * Enable the receipt of any multicast frame by an Ethernet device.
1895 * The port identifier of the Ethernet device.
1897 extern void rte_eth_allmulticast_enable(uint8_t port_id);
1900 * Disable the receipt of all multicast frames by an Ethernet device.
1903 * The port identifier of the Ethernet device.
1905 extern void rte_eth_allmulticast_disable(uint8_t port_id);
1908 * Return the value of allmulticast mode for an Ethernet device.
1911 * The port identifier of the Ethernet device.
1913 * - (1) if allmulticast is enabled
1914 * - (0) if allmulticast is disabled.
1917 extern int rte_eth_allmulticast_get(uint8_t port_id);
1920 * Retrieve the status (ON/OFF), the speed (in Mbps) and the mode (HALF-DUPLEX
1921 * or FULL-DUPLEX) of the physical link of an Ethernet device. It might need
1922 * to wait up to 9 seconds in it.
1925 * The port identifier of the Ethernet device.
1927 * A pointer to an *rte_eth_link* structure to be filled with
1928 * the status, the speed and the mode of the Ethernet device link.
1930 extern void rte_eth_link_get(uint8_t port_id, struct rte_eth_link *link);
1933 * Retrieve the status (ON/OFF), the speed (in Mbps) and the mode (HALF-DUPLEX
1934 * or FULL-DUPLEX) of the physical link of an Ethernet device. It is a no-wait
1935 * version of rte_eth_link_get().
1938 * The port identifier of the Ethernet device.
1940 * A pointer to an *rte_eth_link* structure to be filled with
1941 * the status, the speed and the mode of the Ethernet device link.
1943 extern void rte_eth_link_get_nowait(uint8_t port_id,
1944 struct rte_eth_link *link);
1947 * Retrieve the general I/O statistics of an Ethernet device.
1950 * The port identifier of the Ethernet device.
1952 * A pointer to a structure of type *rte_eth_stats* to be filled with
1953 * the values of device counters for the following set of statistics:
1954 * - *ipackets* with the total of successfully received packets.
1955 * - *opackets* with the total of successfully transmitted packets.
1956 * - *ibytes* with the total of successfully received bytes.
1957 * - *obytes* with the total of successfully transmitted bytes.
1958 * - *ierrors* with the total of erroneous received packets.
1959 * - *oerrors* with the total of failed transmitted packets.
1961 extern void rte_eth_stats_get(uint8_t port_id, struct rte_eth_stats *stats);
1964 * Reset the general I/O statistics of an Ethernet device.
1967 * The port identifier of the Ethernet device.
1969 extern void rte_eth_stats_reset(uint8_t port_id);
1972 * Set a mapping for the specified transmit queue to the specified per-queue
1973 * statistics counter.
1976 * The port identifier of the Ethernet device.
1977 * @param tx_queue_id
1978 * The index of the transmit queue for which a queue stats mapping is required.
1979 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1980 * to rte_eth_dev_configure().
1982 * The per-queue packet statistics functionality number that the transmit
1983 * queue is to be assigned.
1984 * The value must be in the range [0, RTE_MAX_ETHPORT_QUEUE_STATS_MAPS - 1].
1986 * Zero if successful. Non-zero otherwise.
1988 extern int rte_eth_dev_set_tx_queue_stats_mapping(uint8_t port_id,
1989 uint16_t tx_queue_id,
1993 * Set a mapping for the specified receive queue to the specified per-queue
1994 * statistics counter.
1997 * The port identifier of the Ethernet device.
1998 * @param rx_queue_id
1999 * The index of the receive queue for which a queue stats mapping is required.
2000 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2001 * to rte_eth_dev_configure().
2003 * The per-queue packet statistics functionality number that the receive
2004 * queue is to be assigned.
2005 * The value must be in the range [0, RTE_MAX_ETHPORT_QUEUE_STATS_MAPS - 1].
2007 * Zero if successful. Non-zero otherwise.
2009 extern int rte_eth_dev_set_rx_queue_stats_mapping(uint8_t port_id,
2010 uint16_t rx_queue_id,
2014 * Retrieve the Ethernet address of an Ethernet device.
2017 * The port identifier of the Ethernet device.
2019 * A pointer to a structure of type *ether_addr* to be filled with
2020 * the Ethernet address of the Ethernet device.
2022 extern void rte_eth_macaddr_get(uint8_t port_id, struct ether_addr *mac_addr);
2025 * Retrieve the contextual information of an Ethernet device.
2028 * The port identifier of the Ethernet device.
2030 * A pointer to a structure of type *rte_eth_dev_info* to be filled with
2031 * the contextual information of the Ethernet device.
2033 extern void rte_eth_dev_info_get(uint8_t port_id,
2034 struct rte_eth_dev_info *dev_info);
2037 * Enable/Disable hardware filtering by an Ethernet device of received
2038 * VLAN packets tagged with a given VLAN Tag Identifier.
2041 * The port identifier of the Ethernet device.
2043 * The VLAN Tag Identifier whose filtering must be enabled or disabled.
2045 * If > 0, enable VLAN filtering of VLAN packets tagged with *vlan_id*.
2046 * Otherwise, disable VLAN filtering of VLAN packets tagged with *vlan_id*.
2048 * - (0) if successful.
2049 * - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
2050 * - (-ENODEV) if *port_id* invalid.
2051 * - (-ENOSYS) if VLAN filtering on *port_id* disabled.
2052 * - (-EINVAL) if *vlan_id* > 4095.
2054 extern int rte_eth_dev_vlan_filter(uint8_t port_id, uint16_t vlan_id , int on);
2057 * Enable/Disable hardware VLAN Strip by a rx queue of an Ethernet device.
2058 * 82599/X540 can support VLAN stripping at the rx queue level
2061 * The port identifier of the Ethernet device.
2062 * @param rx_queue_id
2063 * The index of the receive queue for which a queue stats mapping is required.
2064 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2065 * to rte_eth_dev_configure().
2067 * If 1, Enable VLAN Stripping of the receive queue of the Ethernet port.
2068 * If 0, Disable VLAN Stripping of the receive queue of the Ethernet port.
2070 * - (0) if successful.
2071 * - (-ENOSUP) if hardware-assisted VLAN stripping not configured.
2072 * - (-ENODEV) if *port_id* invalid.
2073 * - (-EINVAL) if *rx_queue_id* invalid.
2075 extern int rte_eth_dev_set_vlan_strip_on_queue(uint8_t port_id,
2076 uint16_t rx_queue_id, int on);
2079 * Set the Outer VLAN Ether Type by an Ethernet device, it can be inserted to
2080 * the VLAN Header. This is a register setup available on some Intel NIC, not
2081 * but all, please check the data sheet for availability.
2084 * The port identifier of the Ethernet device.
2086 * The Tag Protocol ID
2088 * - (0) if successful.
2089 * - (-ENOSUP) if hardware-assisted VLAN TPID setup is not supported.
2090 * - (-ENODEV) if *port_id* invalid.
2092 extern int rte_eth_dev_set_vlan_ether_type(uint8_t port_id, uint16_t tag_type);
2095 * Set VLAN offload configuration on an Ethernet device
2096 * Enable/Disable Extended VLAN by an Ethernet device, This is a register setup
2097 * available on some Intel NIC, not but all, please check the data sheet for
2099 * Enable/Disable VLAN Strip can be done on rx queue for certain NIC, but here
2100 * the configuration is applied on the port level.
2103 * The port identifier of the Ethernet device.
2104 * @param offload_mask
2105 * The VLAN Offload bit mask can be mixed use with "OR"
2106 * ETH_VLAN_STRIP_OFFLOAD
2107 * ETH_VLAN_FILTER_OFFLOAD
2108 * ETH_VLAN_EXTEND_OFFLOAD
2110 * - (0) if successful.
2111 * - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
2112 * - (-ENODEV) if *port_id* invalid.
2114 extern int rte_eth_dev_set_vlan_offload(uint8_t port_id, int offload_mask);
2117 * Read VLAN Offload configuration from an Ethernet device
2120 * The port identifier of the Ethernet device.
2122 * - (>0) if successful. Bit mask to indicate
2123 * ETH_VLAN_STRIP_OFFLOAD
2124 * ETH_VLAN_FILTER_OFFLOAD
2125 * ETH_VLAN_EXTEND_OFFLOAD
2126 * - (-ENODEV) if *port_id* invalid.
2128 extern int rte_eth_dev_get_vlan_offload(uint8_t port_id);
2132 * Retrieve a burst of input packets from a receive queue of an Ethernet
2133 * device. The retrieved packets are stored in *rte_mbuf* structures whose
2134 * pointers are supplied in the *rx_pkts* array.
2136 * The rte_eth_rx_burst() function loops, parsing the RX ring of the
2137 * receive queue, up to *nb_pkts* packets, and for each completed RX
2138 * descriptor in the ring, it performs the following operations:
2140 * - Initialize the *rte_mbuf* data structure associated with the
2141 * RX descriptor according to the information provided by the NIC into
2142 * that RX descriptor.
2144 * - Store the *rte_mbuf* data structure into the next entry of the
2147 * - Replenish the RX descriptor with a new *rte_mbuf* buffer
2148 * allocated from the memory pool associated with the receive queue at
2149 * initialization time.
2151 * When retrieving an input packet that was scattered by the controller
2152 * into multiple receive descriptors, the rte_eth_rx_burst() function
2153 * appends the associated *rte_mbuf* buffers to the first buffer of the
2156 * The rte_eth_rx_burst() function returns the number of packets
2157 * actually retrieved, which is the number of *rte_mbuf* data structures
2158 * effectively supplied into the *rx_pkts* array.
2159 * A return value equal to *nb_pkts* indicates that the RX queue contained
2160 * at least *rx_pkts* packets, and this is likely to signify that other
2161 * received packets remain in the input queue. Applications implementing
2162 * a "retrieve as much received packets as possible" policy can check this
2163 * specific case and keep invoking the rte_eth_rx_burst() function until
2164 * a value less than *nb_pkts* is returned.
2166 * This receive method has the following advantages:
2168 * - It allows a run-to-completion network stack engine to retrieve and
2169 * to immediately process received packets in a fast burst-oriented
2170 * approach, avoiding the overhead of unnecessary intermediate packet
2171 * queue/dequeue operations.
2173 * - Conversely, it also allows an asynchronous-oriented processing
2174 * method to retrieve bursts of received packets and to immediately
2175 * queue them for further parallel processing by another logical core,
2176 * for instance. However, instead of having received packets being
2177 * individually queued by the driver, this approach allows the invoker
2178 * of the rte_eth_rx_burst() function to queue a burst of retrieved
2179 * packets at a time and therefore dramatically reduce the cost of
2180 * enqueue/dequeue operations per packet.
2182 * - It allows the rte_eth_rx_burst() function of the driver to take
2183 * advantage of burst-oriented hardware features (CPU cache,
2184 * prefetch instructions, and so on) to minimize the number of CPU
2185 * cycles per packet.
2187 * To summarize, the proposed receive API enables many
2188 * burst-oriented optimizations in both synchronous and asynchronous
2189 * packet processing environments with no overhead in both cases.
2191 * The rte_eth_rx_burst() function does not provide any error
2192 * notification to avoid the corresponding overhead. As a hint, the
2193 * upper-level application might check the status of the device link once
2194 * being systematically returned a 0 value for a given number of tries.
2197 * The port identifier of the Ethernet device.
2199 * The index of the receive queue from which to retrieve input packets.
2200 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2201 * to rte_eth_dev_configure().
2203 * The address of an array of pointers to *rte_mbuf* structures that
2204 * must be large enough to store *nb_pkts* pointers in it.
2206 * The maximum number of packets to retrieve.
2208 * The number of packets actually retrieved, which is the number
2209 * of pointers to *rte_mbuf* structures effectively supplied to the
2212 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2213 extern uint16_t rte_eth_rx_burst(uint8_t port_id, uint16_t queue_id,
2214 struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
2216 static inline uint16_t
2217 rte_eth_rx_burst(uint8_t port_id, uint16_t queue_id,
2218 struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
2220 struct rte_eth_dev *dev;
2222 dev = &rte_eth_devices[port_id];
2223 return (*dev->rx_pkt_burst)(dev->data->rx_queues[queue_id], rx_pkts, nb_pkts);
2228 * Get the number of used descriptors in a specific queue
2231 * The port identifier of the Ethernet device.
2233 * The queue id on the specific port.
2235 * The number of used descriptors in the specific queue.
2237 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2238 extern uint32_t rte_eth_rx_queue_count(uint8_t port_id, uint16_t queue_id);
2240 static inline uint32_t
2241 rte_eth_rx_queue_count(uint8_t port_id, uint16_t queue_id)
2243 struct rte_eth_dev *dev;
2245 dev = &rte_eth_devices[port_id];
2246 return (*dev->dev_ops->rx_queue_count)(dev, queue_id);
2251 * Check if the DD bit of the specific RX descriptor in the queue has been set
2254 * The port identifier of the Ethernet device.
2256 * The queue id on the specific port.
2258 * The offset of the descriptor ID from tail.
2260 * - (1) if the specific DD bit is set.
2261 * - (0) if the specific DD bit is not set.
2262 * - (-ENODEV) if *port_id* invalid.
2264 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2265 extern int rte_eth_rx_descriptor_done(uint8_t port_id,
2270 rte_eth_rx_descriptor_done(uint8_t port_id, uint16_t queue_id, uint16_t offset)
2272 struct rte_eth_dev *dev;
2274 dev = &rte_eth_devices[port_id];
2275 return (*dev->dev_ops->rx_descriptor_done)( \
2276 dev->data->rx_queues[queue_id], offset);
2281 * Send a burst of output packets on a transmit queue of an Ethernet device.
2283 * The rte_eth_tx_burst() function is invoked to transmit output packets
2284 * on the output queue *queue_id* of the Ethernet device designated by its
2286 * The *nb_pkts* parameter is the number of packets to send which are
2287 * supplied in the *tx_pkts* array of *rte_mbuf* structures.
2288 * The rte_eth_tx_burst() function loops, sending *nb_pkts* packets,
2289 * up to the number of transmit descriptors available in the TX ring of the
2291 * For each packet to send, the rte_eth_tx_burst() function performs
2292 * the following operations:
2294 * - Pick up the next available descriptor in the transmit ring.
2296 * - Free the network buffer previously sent with that descriptor, if any.
2298 * - Initialize the transmit descriptor with the information provided
2299 * in the *rte_mbuf data structure.
2301 * In the case of a segmented packet composed of a list of *rte_mbuf* buffers,
2302 * the rte_eth_tx_burst() function uses several transmit descriptors
2305 * The rte_eth_tx_burst() function returns the number of packets it
2306 * actually sent. A return value equal to *nb_pkts* means that all packets
2307 * have been sent, and this is likely to signify that other output packets
2308 * could be immediately transmitted again. Applications that implement a
2309 * "send as many packets to transmit as possible" policy can check this
2310 * specific case and keep invoking the rte_eth_tx_burst() function until
2311 * a value less than *nb_pkts* is returned.
2313 * It is the responsibility of the rte_eth_tx_burst() function to
2314 * transparently free the memory buffers of packets previously sent.
2315 * This feature is driven by the *tx_free_thresh* value supplied to the
2316 * rte_eth_dev_configure() function at device configuration time.
2317 * When the number of previously sent packets reached the "minimum transmit
2318 * packets to free" threshold, the rte_eth_tx_burst() function must
2319 * [attempt to] free the *rte_mbuf* buffers of those packets whose
2320 * transmission was effectively completed.
2323 * The port identifier of the Ethernet device.
2325 * The index of the transmit queue through which output packets must be
2327 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
2328 * to rte_eth_dev_configure().
2330 * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures
2331 * which contain the output packets.
2333 * The maximum number of packets to transmit.
2335 * The number of output packets actually stored in transmit descriptors of
2336 * the transmit ring. The return value can be less than the value of the
2337 * *tx_pkts* parameter when the transmit ring is full or has been filled up.
2339 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2340 extern uint16_t rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id,
2341 struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
2343 static inline uint16_t
2344 rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id,
2345 struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
2347 struct rte_eth_dev *dev;
2349 dev = &rte_eth_devices[port_id];
2350 return (*dev->tx_pkt_burst)(dev->data->tx_queues[queue_id], tx_pkts, nb_pkts);
2355 * Setup a new signature filter rule on an Ethernet device
2358 * The port identifier of the Ethernet device.
2359 * @param fdir_filter
2360 * The pointer to the fdir filter structure describing the signature filter
2362 * The *rte_fdir_filter* structure includes the values of the different fields
2363 * to match: source and destination IP addresses, vlan id, flexbytes, source
2364 * and destination ports, and so on.
2366 * The index of the RX queue where to store RX packets matching the added
2367 * signature filter defined in fdir_filter.
2369 * - (0) if successful.
2370 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2371 * - (-ENODEV) if *port_id* invalid.
2372 * - (-ENOSYS) if the FDIR mode is not configured in signature mode
2374 * - (-EINVAL) if the fdir_filter information is not correct.
2376 int rte_eth_dev_fdir_add_signature_filter(uint8_t port_id,
2377 struct rte_fdir_filter *fdir_filter,
2381 * Update a signature filter rule on an Ethernet device.
2382 * If the rule doesn't exits, it is created.
2385 * The port identifier of the Ethernet device.
2387 * The pointer to the structure describing the signature filter rule.
2388 * The *rte_fdir_filter* structure includes the values of the different fields
2389 * to match: source and destination IP addresses, vlan id, flexbytes, source
2390 * and destination ports, and so on.
2392 * The index of the RX queue where to store RX packets matching the added
2393 * signature filter defined in fdir_ftr.
2395 * - (0) if successful.
2396 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2397 * - (-ENODEV) if *port_id* invalid.
2398 * - (-ENOSYS) if the flow director mode is not configured in signature mode
2400 * - (-EINVAL) if the fdir_filter information is not correct.
2402 int rte_eth_dev_fdir_update_signature_filter(uint8_t port_id,
2403 struct rte_fdir_filter *fdir_ftr,
2407 * Remove a signature filter rule on an Ethernet device.
2410 * The port identifier of the Ethernet device.
2412 * The pointer to the structure describing the signature filter rule.
2413 * The *rte_fdir_filter* structure includes the values of the different fields
2414 * to match: source and destination IP addresses, vlan id, flexbytes, source
2415 * and destination ports, and so on.
2417 * - (0) if successful.
2418 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2419 * - (-ENODEV) if *port_id* invalid.
2420 * - (-ENOSYS) if the flow director mode is not configured in signature mode
2422 * - (-EINVAL) if the fdir_filter information is not correct.
2424 int rte_eth_dev_fdir_remove_signature_filter(uint8_t port_id,
2425 struct rte_fdir_filter *fdir_ftr);
2428 * Retrieve the flow director information of an Ethernet device.
2431 * The port identifier of the Ethernet device.
2433 * A pointer to a structure of type *rte_eth_dev_fdir* to be filled with
2434 * the flow director information of the Ethernet device.
2436 * - (0) if successful.
2437 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2438 * - (-ENODEV) if *port_id* invalid.
2439 * - (-ENOSYS) if the flow director mode is not configured on *port_id*.
2441 int rte_eth_dev_fdir_get_infos(uint8_t port_id, struct rte_eth_fdir *fdir);
2444 * Add a new perfect filter rule on an Ethernet device.
2447 * The port identifier of the Ethernet device.
2448 * @param fdir_filter
2449 * The pointer to the structure describing the perfect filter rule.
2450 * The *rte_fdir_filter* structure includes the values of the different fields
2451 * to match: source and destination IP addresses, vlan id, flexbytes, source
2452 * and destination ports, and so on.
2453 * IPv6 are not supported.
2455 * The 16-bit value supplied in the field hash.fdir.id of mbuf for RX
2456 * packets matching the perfect filter.
2458 * The index of the RX queue where to store RX packets matching the added
2459 * perfect filter defined in fdir_filter.
2461 * If drop is set to 1, matching RX packets are stored into the RX drop
2462 * queue defined in the rte_fdir_conf.
2464 * - (0) if successful.
2465 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2466 * - (-ENODEV) if *port_id* invalid.
2467 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2469 * - (-EINVAL) if the fdir_filter information is not correct.
2471 int rte_eth_dev_fdir_add_perfect_filter(uint8_t port_id,
2472 struct rte_fdir_filter *fdir_filter,
2473 uint16_t soft_id, uint8_t rx_queue,
2477 * Update a perfect filter rule on an Ethernet device.
2478 * If the rule doesn't exits, it is created.
2481 * The port identifier of the Ethernet device.
2482 * @param fdir_filter
2483 * The pointer to the structure describing the perfect filter rule.
2484 * The *rte_fdir_filter* structure includes the values of the different fields
2485 * to match: source and destination IP addresses, vlan id, flexbytes, source
2486 * and destination ports, and so on.
2487 * IPv6 are not supported.
2489 * The 16-bit value supplied in the field hash.fdir.id of mbuf for RX
2490 * packets matching the perfect filter.
2492 * The index of the RX queue where to store RX packets matching the added
2493 * perfect filter defined in fdir_filter.
2495 * If drop is set to 1, matching RX packets are stored into the RX drop
2496 * queue defined in the rte_fdir_conf.
2498 * - (0) if successful.
2499 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2500 * - (-ENODEV) if *port_id* invalid.
2501 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2503 * - (-EINVAL) if the fdir_filter information is not correct.
2505 int rte_eth_dev_fdir_update_perfect_filter(uint8_t port_id,
2506 struct rte_fdir_filter *fdir_filter,
2507 uint16_t soft_id, uint8_t rx_queue,
2511 * Remove a perfect filter rule on an Ethernet device.
2514 * The port identifier of the Ethernet device.
2515 * @param fdir_filter
2516 * The pointer to the structure describing the perfect filter rule.
2517 * The *rte_fdir_filter* structure includes the values of the different fields
2518 * to match: source and destination IP addresses, vlan id, flexbytes, source
2519 * and destination ports, and so on.
2520 * IPv6 are not supported.
2522 * The soft_id value provided when adding/updating the removed filter.
2524 * - (0) if successful.
2525 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2526 * - (-ENODEV) if *port_id* invalid.
2527 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2529 * - (-EINVAL) if the fdir_filter information is not correct.
2531 int rte_eth_dev_fdir_remove_perfect_filter(uint8_t port_id,
2532 struct rte_fdir_filter *fdir_filter,
2535 * Configure globally the masks for flow director mode for an Ethernet device.
2536 * For example, the device can match packets with only the first 24 bits of
2537 * the IPv4 source address.
2539 * The following fields can be masked: IPv4 addresses and L4 port numbers.
2540 * The following fields can be either enabled or disabled completely for the
2541 * matching functionality: VLAN ID tag; VLAN Priority + CFI bit; Flexible 2-byte
2543 * IPv6 masks are not supported.
2545 * All filters must comply with the masks previously configured.
2546 * For example, with a mask equal to 255.255.255.0 for the source IPv4 address,
2547 * all IPv4 filters must be created with a source IPv4 address that fits the
2550 * This function flushes all filters that have been previously added in
2554 * The port identifier of the Ethernet device.
2556 * The pointer to the fdir mask structure describing relevant headers fields
2557 * and relevant bits to use when matching packets addresses and ports.
2558 * IPv6 masks are not supported.
2560 * - (0) if successful.
2561 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2562 * - (-ENODEV) if *port_id* invalid.
2563 * - (-ENOSYS) if the flow director mode is not configured in perfect
2564 * mode on *port_id*.
2565 * - (-EINVAL) if the fdir_filter information is not correct
2567 int rte_eth_dev_fdir_set_masks(uint8_t port_id,
2568 struct rte_fdir_masks *fdir_mask);
2571 * The eth device event type for interrupt, and maybe others in the future.
2573 enum rte_eth_event_type {
2574 RTE_ETH_EVENT_UNKNOWN, /**< unknown event type */
2575 RTE_ETH_EVENT_INTR_LSC, /**< lsc interrupt event */
2576 RTE_ETH_EVENT_MAX /**< max value of this enum */
2579 typedef void (*rte_eth_dev_cb_fn)(uint8_t port_id, \
2580 enum rte_eth_event_type event, void *cb_arg);
2581 /**< user application callback to be registered for interrupts */
2586 * Register a callback function for specific port id.
2593 * User supplied callback function to be called.
2595 * Pointer to the parameters for the registered callback.
2598 * - On success, zero.
2599 * - On failure, a negative value.
2601 int rte_eth_dev_callback_register(uint8_t port_id,
2602 enum rte_eth_event_type event,
2603 rte_eth_dev_cb_fn cb_fn, void *cb_arg);
2606 * Unregister a callback function for specific port id.
2613 * User supplied callback function to be called.
2615 * Pointer to the parameters for the registered callback. -1 means to
2616 * remove all for the same callback address and same event.
2619 * - On success, zero.
2620 * - On failure, a negative value.
2622 int rte_eth_dev_callback_unregister(uint8_t port_id,
2623 enum rte_eth_event_type event,
2624 rte_eth_dev_cb_fn cb_fn, void *cb_arg);
2627 * @internal Executes all the user application registered callbacks for
2628 * the specific device. It is for DPDK internal user only. User
2629 * application should not call it directly.
2632 * Pointer to struct rte_eth_dev.
2634 * Eth device interrupt event type.
2639 void _rte_eth_dev_callback_process(struct rte_eth_dev *dev,
2640 enum rte_eth_event_type event);
2643 * Turn on the LED on the Ethernet device.
2644 * This function turns on the LED on the Ethernet device.
2647 * The port identifier of the Ethernet device.
2649 * - (0) if successful.
2650 * - (-ENOTSUP) if underlying hardware OR driver doesn't support
2652 * - (-ENODEV) if *port_id* invalid.
2654 int rte_eth_led_on(uint8_t port_id);
2657 * Turn off the LED on the Ethernet device.
2658 * This function turns off the LED on the Ethernet device.
2661 * The port identifier of the Ethernet device.
2663 * - (0) if successful.
2664 * - (-ENOTSUP) if underlying hardware OR driver doesn't support
2666 * - (-ENODEV) if *port_id* invalid.
2668 int rte_eth_led_off(uint8_t port_id);
2671 * Configure the Ethernet link flow control for Ethernet device
2674 * The port identifier of the Ethernet device.
2676 * The pointer to the structure of the flow control parameters.
2678 * - (0) if successful.
2679 * - (-ENOTSUP) if hardware doesn't support flow control mode.
2680 * - (-ENODEV) if *port_id* invalid.
2681 * - (-EINVAL) if bad parameter
2682 * - (-EIO) if flow control setup failure
2684 int rte_eth_dev_flow_ctrl_set(uint8_t port_id,
2685 struct rte_eth_fc_conf *fc_conf);
2688 * Configure the Ethernet priority flow control under DCB environment
2689 * for Ethernet device.
2692 * The port identifier of the Ethernet device.
2694 * The pointer to the structure of the priority flow control parameters.
2696 * - (0) if successful.
2697 * - (-ENOTSUP) if hardware doesn't support priority flow control mode.
2698 * - (-ENODEV) if *port_id* invalid.
2699 * - (-EINVAL) if bad parameter
2700 * - (-EIO) if flow control setup failure
2702 int rte_eth_dev_priority_flow_ctrl_set(uint8_t port_id,
2703 struct rte_eth_pfc_conf *pfc_conf);
2706 * Add a MAC address to an internal array of addresses used to enable whitelist
2707 * filtering to accept packets only if the destination MAC address matches.
2710 * The port identifier of the Ethernet device.
2712 * The MAC address to add.
2714 * VMDq pool index to associate address with (if VMDq is enabled). If VMDq is
2715 * not enabled, this should be set to 0.
2717 * - (0) if successfully added or *mac_addr" was already added.
2718 * - (-ENOTSUP) if hardware doesn't support this feature.
2719 * - (-ENODEV) if *port* is invalid.
2720 * - (-ENOSPC) if no more MAC addresses can be added.
2721 * - (-EINVAL) if MAC address is invalid.
2723 int rte_eth_dev_mac_addr_add(uint8_t port, struct ether_addr *mac_addr,
2727 * Remove a MAC address from the internal array of addresses.
2730 * The port identifier of the Ethernet device.
2732 * MAC address to remove.
2734 * - (0) if successful, or *mac_addr* didn't exist.
2735 * - (-ENOTSUP) if hardware doesn't support.
2736 * - (-ENODEV) if *port* invalid.
2737 * - (-EADDRINUSE) if attempting to remove the default MAC address
2739 int rte_eth_dev_mac_addr_remove(uint8_t port, struct ether_addr *mac_addr);
2742 * Update Redirection Table(RETA) of Receive Side Scaling of Ethernet device.
2745 * The port identifier of the Ethernet device.
2749 * - (0) if successful.
2750 * - (-ENOTSUP) if hardware doesn't support.
2751 * - (-EINVAL) if bad parameter.
2753 int rte_eth_dev_rss_reta_update(uint8_t port,
2754 struct rte_eth_rss_reta *reta_conf);
2757 * Query Redirection Table(RETA) of Receive Side Scaling of Ethernet device.
2760 * The port identifier of the Ethernet device.
2764 * - (0) if successful.
2765 * - (-ENOTSUP) if hardware doesn't support.
2766 * - (-EINVAL) if bad parameter.
2768 int rte_eth_dev_rss_reta_query(uint8_t port,
2769 struct rte_eth_rss_reta *reta_conf);
2772 * Updates unicast hash table for receiving packet with the given destination
2773 * MAC address, and the packet is routed to all VFs for which the RX mode is
2774 * accept packets that match the unicast hash table.
2777 * The port identifier of the Ethernet device.
2779 * Unicast MAC address.
2781 * 1 - Set an unicast hash bit for receiving packets with the MAC address.
2782 * 0 - Clear an unicast hash bit.
2784 * - (0) if successful.
2785 * - (-ENOTSUP) if hardware doesn't support.
2786 * - (-ENODEV) if *port_id* invalid.
2787 * - (-EINVAL) if bad parameter.
2789 int rte_eth_dev_uc_hash_table_set(uint8_t port,struct ether_addr *addr,
2793 * Updates all unicast hash bitmaps for receiving packet with any Unicast
2794 * Ethernet MAC addresses,the packet is routed to all VFs for which the RX
2795 * mode is accept packets that match the unicast hash table.
2798 * The port identifier of the Ethernet device.
2800 * 1 - Set all unicast hash bitmaps for receiving all the Ethernet
2802 * 0 - Clear all unicast hash bitmaps
2804 * - (0) if successful.
2805 * - (-ENOTSUP) if hardware doesn't support.
2806 * - (-ENODEV) if *port_id* invalid.
2807 * - (-EINVAL) if bad parameter.
2809 int rte_eth_dev_uc_all_hash_table_set(uint8_t port,uint8_t on);
2812 * Set RX L2 Filtering mode of a VF of an Ethernet device.
2815 * The port identifier of the Ethernet device.
2819 * The RX mode mask, which is one or more of accepting Untagged Packets,
2820 * packets that match the PFUTA table, Broadcast and Multicast Promiscuous.
2821 * ETH_VMDQ_ACCEPT_UNTAG,ETH_VMDQ_ACCEPT_HASH_UC,
2822 * ETH_VMDQ_ACCEPT_BROADCAST and ETH_VMDQ_ACCEPT_MULTICAST will be used
2825 * 1 - Enable a VF RX mode.
2826 * 0 - Disable a VF RX mode.
2828 * - (0) if successful.
2829 * - (-ENOTSUP) if hardware doesn't support.
2830 * - (-ENOTSUP) if hardware doesn't support.
2831 * - (-EINVAL) if bad parameter.
2833 int rte_eth_dev_set_vf_rxmode(uint8_t port, uint16_t vf, uint16_t rx_mode,
2837 * Enable or disable a VF traffic transmit of the Ethernet device.
2840 * The port identifier of the Ethernet device.
2844 * 1 - Enable a VF traffic transmit.
2845 * 0 - Disable a VF traffic transmit.
2847 * - (0) if successful.
2848 * - (-ENODEV) if *port_id* invalid.
2849 * - (-ENOTSUP) if hardware doesn't support.
2850 * - (-EINVAL) if bad parameter.
2853 rte_eth_dev_set_vf_tx(uint8_t port,uint16_t vf, uint8_t on);
2856 * Enable or disable a VF traffic receive of an Ethernet device.
2859 * The port identifier of the Ethernet device.
2863 * 1 - Enable a VF traffic receive.
2864 * 0 - Disable a VF traffic receive.
2866 * - (0) if successful.
2867 * - (-ENOTSUP) if hardware doesn't support.
2868 * - (-ENODEV) if *port_id* invalid.
2869 * - (-EINVAL) if bad parameter.
2872 rte_eth_dev_set_vf_rx(uint8_t port,uint16_t vf, uint8_t on);
2875 * Enable/Disable hardware VF VLAN filtering by an Ethernet device of
2876 * received VLAN packets tagged with a given VLAN Tag Identifier.
2879 * The port identifier of the Ethernet device.
2881 * The VLAN Tag Identifier whose filtering must be enabled or disabled.
2883 * Bitmap listing which VFs participate in the VLAN filtering.
2885 * 1 - Enable VFs VLAN filtering.
2886 * 0 - Disable VFs VLAN filtering.
2888 * - (0) if successful.
2889 * - (-ENOTSUP) if hardware doesn't support.
2890 * - (-ENODEV) if *port_id* invalid.
2891 * - (-EINVAL) if bad parameter.
2894 rte_eth_dev_set_vf_vlan_filter(uint8_t port, uint16_t vlan_id,
2899 * Set a traffic mirroring rule on an Ethernet device
2902 * The port identifier of the Ethernet device.
2903 * @param mirror_conf
2904 * The pointer to the traffic mirroring structure describing the mirroring rule.
2905 * The *rte_eth_vm_mirror_conf* structure includes the type of mirroring rule,
2906 * destination pool and the value of rule if enable vlan or pool mirroring.
2909 * The index of traffic mirroring rule, we support four separated rules.
2911 * 1 - Enable a mirroring rule.
2912 * 0 - Disable a mirroring rule.
2914 * - (0) if successful.
2915 * - (-ENOTSUP) if hardware doesn't support this feature.
2916 * - (-ENODEV) if *port_id* invalid.
2917 * - (-EINVAL) if the mr_conf information is not correct.
2919 int rte_eth_mirror_rule_set(uint8_t port_id,
2920 struct rte_eth_vmdq_mirror_conf *mirror_conf,
2925 * Reset a traffic mirroring rule on an Ethernet device.
2928 * The port identifier of the Ethernet device.
2930 * The index of traffic mirroring rule, we support four separated rules.
2932 * - (0) if successful.
2933 * - (-ENOTSUP) if hardware doesn't support this feature.
2934 * - (-ENODEV) if *port_id* invalid.
2935 * - (-EINVAL) if bad parameter.
2937 int rte_eth_mirror_rule_reset(uint8_t port_id,
2941 * Set the rate limitation for a queue on an Ethernet device.
2944 * The port identifier of the Ethernet device.
2948 * The tx rate allocated from the total link speed for this queue.
2950 * - (0) if successful.
2951 * - (-ENOTSUP) if hardware doesn't support this feature.
2952 * - (-ENODEV) if *port_id* invalid.
2953 * - (-EINVAL) if bad parameter.
2955 int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx,
2959 * Set the rate limitation for a vf on an Ethernet device.
2962 * The port identifier of the Ethernet device.
2966 * The tx rate allocated from the total link speed for this VF id.
2968 * The queue mask which need to set the rate.
2970 * - (0) if successful.
2971 * - (-ENOTSUP) if hardware doesn't support this feature.
2972 * - (-ENODEV) if *port_id* invalid.
2973 * - (-EINVAL) if bad parameter.
2975 int rte_eth_set_vf_rate_limit(uint8_t port_id, uint16_t vf,
2976 uint16_t tx_rate, uint64_t q_msk);
2979 * Initialize bypass logic. This function needs to be called before
2980 * executing any other bypass API.
2983 * The port identifier of the Ethernet device.
2985 * - (0) if successful.
2986 * - (-ENOTSUP) if hardware doesn't support.
2987 * - (-EINVAL) if bad parameter.
2989 int rte_eth_dev_bypass_init(uint8_t port);
2992 * Return bypass state.
2995 * The port identifier of the Ethernet device.
2997 * The return bypass state.
3000 * - (3) Isolate mode
3002 * - (0) if successful.
3003 * - (-ENOTSUP) if hardware doesn't support.
3004 * - (-EINVAL) if bad parameter.
3006 int rte_eth_dev_bypass_state_show(uint8_t port, uint32_t *state);
3012 * The port identifier of the Ethernet device.
3014 * The current bypass state.
3017 * - (3) Isolate mode
3019 * - (0) if successful.
3020 * - (-ENOTSUP) if hardware doesn't support.
3021 * - (-EINVAL) if bad parameter.
3023 int rte_eth_dev_bypass_state_set(uint8_t port, uint32_t *new_state);
3026 * Return bypass state when given event occurs.
3029 * The port identifier of the Ethernet device.
3032 * - (1) Main power on (power button is pushed)
3033 * - (2) Auxiliary power on (power supply is being plugged)
3034 * - (3) Main power off (system shutdown and power supply is left plugged in)
3035 * - (4) Auxiliary power off (power supply is being unplugged)
3036 * - (5) Display or set the watchdog timer
3038 * The bypass state when given event occurred.
3041 * - (3) Isolate mode
3043 * - (0) if successful.
3044 * - (-ENOTSUP) if hardware doesn't support.
3045 * - (-EINVAL) if bad parameter.
3047 int rte_eth_dev_bypass_event_show(uint8_t port, uint32_t event, uint32_t *state);
3050 * Set bypass state when given event occurs.
3053 * The port identifier of the Ethernet device.
3056 * - (1) Main power on (power button is pushed)
3057 * - (2) Auxiliary power on (power supply is being plugged)
3058 * - (3) Main power off (system shutdown and power supply is left plugged in)
3059 * - (4) Auxiliary power off (power supply is being unplugged)
3060 * - (5) Display or set the watchdog timer
3062 * The assigned state when given event occurs.
3065 * - (3) Isolate mode
3067 * - (0) if successful.
3068 * - (-ENOTSUP) if hardware doesn't support.
3069 * - (-EINVAL) if bad parameter.
3071 int rte_eth_dev_bypass_event_store(uint8_t port, uint32_t event, uint32_t state);
3074 * Set bypass watchdog timeout count.
3077 * The port identifier of the Ethernet device.
3079 * The timeout to be set.
3080 * - (0) 0 seconds (timer is off)
3089 * - (0) if successful.
3090 * - (-ENOTSUP) if hardware doesn't support.
3091 * - (-EINVAL) if bad parameter.
3093 int rte_eth_dev_wd_timeout_store(uint8_t port, uint32_t timeout);
3096 * Get bypass firmware version.
3099 * The port identifier of the Ethernet device.
3101 * The firmware version
3103 * - (0) if successful.
3104 * - (-ENOTSUP) if hardware doesn't support.
3105 * - (-EINVAL) if bad parameter.
3107 int rte_eth_dev_bypass_ver_show(uint8_t port, uint32_t *ver);
3110 * Return bypass watchdog timeout in seconds
3113 * The port identifier of the Ethernet device.
3115 * The return watchdog timeout. "0" represents timer expired
3116 * - (0) 0 seconds (timer is off)
3125 * - (0) if successful.
3126 * - (-ENOTSUP) if hardware doesn't support.
3127 * - (-EINVAL) if bad parameter.
3129 int rte_eth_dev_bypass_wd_timeout_show(uint8_t port, uint32_t *wd_timeout);
3132 * Reset bypass watchdog timer
3135 * The port identifier of the Ethernet device.
3137 * - (0) if successful.
3138 * - (-ENOTSUP) if hardware doesn't support.
3139 * - (-EINVAL) if bad parameter.
3141 int rte_eth_dev_bypass_wd_reset(uint8_t port);
3144 * Configuration of Receive Side Scaling hash computation of Ethernet device.
3147 * The port identifier of the Ethernet device.
3149 * The new configuration to use for RSS hash computation on the port.
3151 * - (0) if successful.
3152 * - (-ENODEV) if port identifier is invalid.
3153 * - (-ENOTSUP) if hardware doesn't support.
3154 * - (-EINVAL) if bad parameter.
3156 int rte_eth_dev_rss_hash_update(uint8_t port_id,
3157 struct rte_eth_rss_conf *rss_conf);
3160 * Retrieve current configuration of Receive Side Scaling hash computation
3161 * of Ethernet device.
3164 * The port identifier of the Ethernet device.
3166 * Where to store the current RSS hash configuration of the Ethernet device.
3168 * - (0) if successful.
3169 * - (-ENODEV) if port identifier is invalid.
3170 * - (-ENOTSUP) if hardware doesn't support RSS.
3173 rte_eth_dev_rss_hash_conf_get(uint8_t port_id,
3174 struct rte_eth_rss_conf *rss_conf);
3180 * The port identifier of the Ethernet device.
3182 * The index of RX queue where to store RX packets matching the syn filter.
3184 * The pointer to the structure describing the syn filter rule.
3186 * - (0) if successful.
3187 * - (-ENOTSUP) if hardware doesn't support.
3188 * - (-EINVAL) if bad parameter.
3190 int rte_eth_dev_add_syn_filter(uint8_t port_id,
3191 struct rte_syn_filter *filter, uint16_t rx_queue);
3197 * The port identifier of the Ethernet device.
3199 * - (0) if successful.
3200 * - (-ENOTSUP) if hardware doesn't support.
3201 * - (-EINVAL) if bad parameter.
3203 int rte_eth_dev_remove_syn_filter(uint8_t port_id);
3209 * The port identifier of the Ethernet device.
3211 * The pointer to the structure describing the syn filter.
3213 * A pointer to get the queue index of syn filter.
3215 * - (0) if successful.
3216 * - (-ENOTSUP) if hardware doesn't support.
3217 * - (-EINVAL) if bad parameter.
3219 int rte_eth_dev_get_syn_filter(uint8_t port_id,
3220 struct rte_syn_filter *filter, uint16_t *rx_queue);
3223 * Add a new ethertype filter rule on an Ethernet device.
3226 * The port identifier of the Ethernet device.
3228 * The identifier of ethertype filter.
3230 * The pointer to the structure describing the ethertype filter rule.
3231 * The *rte_ethertype_filter* structure includes the values of the different
3232 * fields to match: ethertype and priority in vlan tag.
3233 * priority in vlan tag is not supported for E1000 dev.
3235 * The index of the RX queue where to store RX packets matching the added
3238 * - (0) if successful.
3239 * - (-ENOTSUP) if hardware doesn't support ethertype filter.
3240 * - (-ENODEV) if *port_id* invalid.
3241 * - (-EINVAL) if the filter information is not correct.
3243 int rte_eth_dev_add_ethertype_filter(uint8_t port_id, uint16_t index,
3244 struct rte_ethertype_filter *filter, uint16_t rx_queue);
3247 * remove an ethertype filter rule on an Ethernet device.
3250 * The port identifier of the Ethernet device.
3252 * The identifier of ethertype filter.
3254 * - (0) if successful.
3255 * - (-ENOTSUP) if hardware doesn't support ethertype filter.
3256 * - (-ENODEV) if *port_id* invalid.
3257 * - (-EINVAL) if the filter information is not correct.
3259 int rte_eth_dev_remove_ethertype_filter(uint8_t port_id,
3263 * Get an ethertype filter rule on an Ethernet device.
3266 * The port identifier of the Ethernet device.
3268 * The identifier of ethertype filter.
3270 * A pointer to a structure of type *rte_ethertype_filter* to be filled with
3271 * the information of the Ethertype filter.
3273 * A pointer to get the queue index.
3275 * - (0) if successful.
3276 * - (-ENOTSUP) if hardware doesn't support ethertype filter.
3277 * - (-ENODEV) if *port_id* invalid.
3278 * - (-EINVAL) if the filter information is not correct.
3279 * - (-ENOENT) if no enabled filter in this index.
3281 int rte_eth_dev_get_ethertype_filter(uint8_t port_id, uint16_t index,
3282 struct rte_ethertype_filter *filter, uint16_t *rx_queue);
3285 * Add a new 2tuple filter rule on an Ethernet device.
3288 * The port identifier of the Ethernet device.
3290 * The identifier of 2tuple filter.
3292 * The pointer to the structure describing the 2tuple filter rule.
3293 * The *rte_2tuple_filter* structure includes the values of the different
3294 * fields to match: protocol, dst_port and
3295 * tcp_flags if the protocol is tcp type.
3297 * The index of the RX queue where to store RX packets matching the added
3300 * - (0) if successful.
3301 * - (-ENOTSUP) if hardware doesn't support 2tuple filter.
3302 * - (-ENODEV) if *port_id* invalid.
3303 * - (-EINVAL) if the filter information is not correct.
3305 int rte_eth_dev_add_2tuple_filter(uint8_t port_id, uint16_t index,
3306 struct rte_2tuple_filter *filter, uint16_t rx_queue);
3309 * remove a 2tuple filter rule on an Ethernet device.
3312 * The port identifier of the Ethernet device.
3314 * The identifier of 2tuple filter.
3316 * - (0) if successful.
3317 * - (-ENOTSUP) if hardware doesn't support 2tuple filter.
3318 * - (-ENODEV) if *port_id* invalid.
3319 * - (-EINVAL) if the filter information is not correct.
3321 int rte_eth_dev_remove_2tuple_filter(uint8_t port_id, uint16_t index);
3324 * Get an 2tuple filter rule on an Ethernet device.
3327 * The port identifier of the Ethernet device.
3329 * The identifier of 2tuple filter.
3331 * A pointer to a structure of type *rte_2tuple_filter* to be filled with
3332 * the information of the 2tuple filter.
3334 * A pointer to get the queue index.
3336 * - (0) if successful.
3337 * - (-ENOTSUP) if hardware doesn't support 2tuple filter.
3338 * - (-ENODEV) if *port_id* invalid.
3339 * - (-EINVAL) if the filter information is not correct.
3340 * - (-ENOENT) if no enabled filter in this index.
3342 int rte_eth_dev_get_2tuple_filter(uint8_t port_id, uint16_t index,
3343 struct rte_2tuple_filter *filter, uint16_t *rx_queue);
3346 * Add a new 5tuple filter rule on an Ethernet device.
3349 * The port identifier of the Ethernet device.
3351 * The identifier of 5tuple filter.
3353 * The pointer to the structure describing the 5tuple filter rule.
3354 * The *rte_5tuple_filter* structure includes the values of the different
3355 * fields to match: dst src IP, dst src port, protocol and relative masks
3357 * The index of the RX queue where to store RX packets matching the added
3360 * - (0) if successful.
3361 * - (-ENOTSUP) if hardware doesn't support 5tuple filter.
3362 * - (-ENODEV) if *port_id* invalid.
3363 * - (-EINVAL) if the filter information is not correct.
3365 int rte_eth_dev_add_5tuple_filter(uint8_t port_id, uint16_t index,
3366 struct rte_5tuple_filter *filter, uint16_t rx_queue);
3369 * remove a 5tuple filter rule on an Ethernet device.
3372 * The port identifier of the Ethernet device.
3374 * The identifier of 5tuple filter.
3376 * - (0) if successful.
3377 * - (-ENOTSUP) if hardware doesn't support 5tuple filter.
3378 * - (-ENODEV) if *port_id* invalid.
3379 * - (-EINVAL) if the filter information is not correct.
3381 int rte_eth_dev_remove_5tuple_filter(uint8_t port_id, uint16_t index);
3384 * Get an 5tuple filter rule on an Ethernet device.
3387 * The port identifier of the Ethernet device.
3389 * The identifier of 5tuple filter.
3391 * A pointer to a structure of type *rte_5tuple_filter* to be filled with
3392 * the information of the 5tuple filter.
3394 * A pointer to get the queue index.
3396 * - (0) if successful.
3397 * - (-ENOTSUP) if hardware doesn't support 5tuple filter.
3398 * - (-ENODEV) if *port_id* invalid.
3399 * - (-EINVAL) if the filter information is not correct.
3401 int rte_eth_dev_get_5tuple_filter(uint8_t port_id, uint16_t index,
3402 struct rte_5tuple_filter *filter, uint16_t *rx_queue);
3405 * Add a new flex filter rule on an Ethernet device.
3408 * The port identifier of the Ethernet device.
3410 * The identifier of flex filter.
3412 * The pointer to the structure describing the flex filter rule.
3413 * The *rte_flex_filter* structure includes the values of the different fields
3414 * to match: the dwords (first len bytes of packet ) and relative masks.
3416 * The index of the RX queue where to store RX packets matching the added
3419 * - (0) if successful.
3420 * - (-ENOTSUP) if hardware doesn't support flex filter.
3421 * - (-ENODEV) if *port_id* invalid.
3422 * - (-EINVAL) if the filter information is not correct.
3423 * - (-ENOENT) if no enabled filter in this index.
3425 int rte_eth_dev_add_flex_filter(uint8_t port_id, uint16_t index,
3426 struct rte_flex_filter *filter, uint16_t rx_queue);
3429 * remove a flex filter rule on an Ethernet device.
3432 * The port identifier of the Ethernet device.
3434 * The identifier of flex filter.
3436 * - (0) if successful.
3437 * - (-ENOTSUP) if hardware doesn't support flex filter.
3438 * - (-ENODEV) if *port_id* invalid.
3439 * - (-EINVAL) if the filter information is not correct.
3441 int rte_eth_dev_remove_flex_filter(uint8_t port_id, uint16_t index);
3444 * Get an flex filter rule on an Ethernet device.
3447 * The port identifier of the Ethernet device.
3449 * The identifier of flex filter.
3451 * A pointer to a structure of type *rte_flex_filter* to be filled with
3452 * the information of the flex filter.
3454 * A pointer to get the queue index.
3456 * - (0) if successful.
3457 * - (-ENOTSUP) if hardware doesn't support flex filter.
3458 * - (-ENODEV) if *port_id* invalid.
3459 * - (-EINVAL) if the filter information is not correct.
3460 * - (-ENOENT) if no enabled filter in this index.
3462 int rte_eth_dev_get_flex_filter(uint8_t port_id, uint16_t index,
3463 struct rte_flex_filter *filter, uint16_t *rx_queue);
3469 #endif /* _RTE_ETHDEV_H_ */