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. */
236 #define ETH_LINK_SPEED_10G 10000 /**< alias of 10 gigabits/second. */
237 #define ETH_LINK_SPEED_20G 20000 /**< 20 gigabits/second. */
238 #define ETH_LINK_SPEED_40G 40000 /**< 40 gigabits/second. */
240 #define ETH_LINK_AUTONEG_DUPLEX 0 /**< Auto-negotiate duplex. */
241 #define ETH_LINK_HALF_DUPLEX 1 /**< Half-duplex connection. */
242 #define ETH_LINK_FULL_DUPLEX 2 /**< Full-duplex connection. */
245 * A structure used to configure the ring threshold registers of an RX/TX
246 * queue for an Ethernet port.
248 struct rte_eth_thresh {
249 uint8_t pthresh; /**< Ring prefetch threshold. */
250 uint8_t hthresh; /**< Ring host threshold. */
251 uint8_t wthresh; /**< Ring writeback threshold. */
255 * A set of values to identify what method is to be used to route
256 * packets to multiple queues.
258 enum rte_eth_rx_mq_mode {
259 ETH_MQ_RX_NONE = 0, /**< None of DCB,RSS or VMDQ mode */
261 ETH_MQ_RX_RSS, /**< For RX side, only RSS is on */
262 ETH_MQ_RX_DCB, /**< For RX side,only DCB is on. */
263 ETH_MQ_RX_DCB_RSS, /**< Both DCB and RSS enable */
265 ETH_MQ_RX_VMDQ_ONLY, /**< Only VMDQ, no RSS nor DCB */
266 ETH_MQ_RX_VMDQ_RSS, /**< RSS mode with VMDQ */
267 ETH_MQ_RX_VMDQ_DCB, /**< Use VMDQ+DCB to route traffic to queues */
268 ETH_MQ_RX_VMDQ_DCB_RSS, /**< Enable both VMDQ and DCB in VMDq */
272 * for rx mq mode backward compatible
274 #define ETH_RSS ETH_MQ_RX_RSS
275 #define VMDQ_DCB ETH_MQ_RX_VMDQ_DCB
276 #define ETH_DCB_RX ETH_MQ_RX_DCB
279 * A set of values to identify what method is to be used to transmit
280 * packets using multi-TCs.
282 enum rte_eth_tx_mq_mode {
283 ETH_MQ_TX_NONE = 0, /**< It is in neither DCB nor VT mode. */
284 ETH_MQ_TX_DCB, /**< For TX side,only DCB is on. */
285 ETH_MQ_TX_VMDQ_DCB, /**< For TX side,both DCB and VT is on. */
286 ETH_MQ_TX_VMDQ_ONLY, /**< Only VT on, no DCB */
290 * for tx mq mode backward compatible
292 #define ETH_DCB_NONE ETH_MQ_TX_NONE
293 #define ETH_VMDQ_DCB_TX ETH_MQ_TX_VMDQ_DCB
294 #define ETH_DCB_TX ETH_MQ_TX_DCB
297 * A structure used to configure the RX features of an Ethernet port.
299 struct rte_eth_rxmode {
300 /** The multi-queue packet distribution mode to be used, e.g. RSS. */
301 enum rte_eth_rx_mq_mode mq_mode;
302 uint32_t max_rx_pkt_len; /**< Only used if jumbo_frame enabled. */
303 uint16_t split_hdr_size; /**< hdr buf size (header_split enabled).*/
304 uint8_t header_split : 1, /**< Header Split enable. */
305 hw_ip_checksum : 1, /**< IP/UDP/TCP checksum offload enable. */
306 hw_vlan_filter : 1, /**< VLAN filter enable. */
307 hw_vlan_strip : 1, /**< VLAN strip enable. */
308 hw_vlan_extend : 1, /**< Extended VLAN enable. */
309 jumbo_frame : 1, /**< Jumbo Frame Receipt enable. */
310 hw_strip_crc : 1; /**< Enable CRC stripping by hardware. */
314 * A structure used to configure the Receive Side Scaling (RSS) feature
315 * of an Ethernet port.
316 * If not NULL, the *rss_key* pointer of the *rss_conf* structure points
317 * to an array holding the RSS key to use for hashing specific header
318 * fields of received packets. The length of this array should be indicated
319 * by *rss_key_len* below. Otherwise, a default random hash key is used by
322 * The *rss_key_len* field of the *rss_conf* structure indicates the length
323 * in bytes of the array pointed by *rss_key*. To be compatible, this length
324 * will be checked in i40e only. Others assume 40 bytes to be used as before.
326 * The *rss_hf* field of the *rss_conf* structure indicates the different
327 * types of IPv4/IPv6 packets to which the RSS hashing must be applied.
328 * Supplying an *rss_hf* equal to zero disables the RSS feature.
330 struct rte_eth_rss_conf {
331 uint8_t *rss_key; /**< If not NULL, 40-byte hash key. */
332 uint8_t rss_key_len; /**< hash key length in bytes. */
333 uint64_t rss_hf; /**< Hash functions to apply - see below. */
336 /* Supported RSS offloads */
338 #define ETH_RSS_IPV4_SHIFT 0
339 #define ETH_RSS_IPV4_TCP_SHIFT 1
340 #define ETH_RSS_IPV6_SHIFT 2
341 #define ETH_RSS_IPV6_EX_SHIFT 3
342 #define ETH_RSS_IPV6_TCP_SHIFT 4
343 #define ETH_RSS_IPV6_TCP_EX_SHIFT 5
344 #define ETH_RSS_IPV4_UDP_SHIFT 6
345 #define ETH_RSS_IPV6_UDP_SHIFT 7
346 #define ETH_RSS_IPV6_UDP_EX_SHIFT 8
348 #define ETH_RSS_NONF_IPV4_UDP_SHIFT 31
349 #define ETH_RSS_NONF_IPV4_TCP_SHIFT 33
350 #define ETH_RSS_NONF_IPV4_SCTP_SHIFT 34
351 #define ETH_RSS_NONF_IPV4_OTHER_SHIFT 35
352 #define ETH_RSS_FRAG_IPV4_SHIFT 36
353 #define ETH_RSS_NONF_IPV6_UDP_SHIFT 41
354 #define ETH_RSS_NONF_IPV6_TCP_SHIFT 43
355 #define ETH_RSS_NONF_IPV6_SCTP_SHIFT 44
356 #define ETH_RSS_NONF_IPV6_OTHER_SHIFT 45
357 #define ETH_RSS_FRAG_IPV6_SHIFT 46
358 #define ETH_RSS_FCOE_OX_SHIFT 48
359 #define ETH_RSS_FCOE_RX_SHIFT 49
360 #define ETH_RSS_FCOE_OTHER_SHIFT 50
361 #define ETH_RSS_L2_PAYLOAD_SHIFT 63
364 #define ETH_RSS_IPV4 ((uint16_t)1 << ETH_RSS_IPV4_SHIFT)
365 #define ETH_RSS_IPV4_TCP ((uint16_t)1 << ETH_RSS_IPV4_TCP_SHIFT)
366 #define ETH_RSS_IPV6 ((uint16_t)1 << ETH_RSS_IPV6_SHIFT)
367 #define ETH_RSS_IPV6_EX ((uint16_t)1 << ETH_RSS_IPV6_EX_SHIFT)
368 #define ETH_RSS_IPV6_TCP ((uint16_t)1 << ETH_RSS_IPV6_TCP_SHIFT)
369 #define ETH_RSS_IPV6_TCP_EX ((uint16_t)1 << ETH_RSS_IPV6_TCP_EX_SHIFT)
370 #define ETH_RSS_IPV4_UDP ((uint16_t)1 << ETH_RSS_IPV4_UDP_SHIFT)
371 #define ETH_RSS_IPV6_UDP ((uint16_t)1 << ETH_RSS_IPV6_UDP_SHIFT)
372 #define ETH_RSS_IPV6_UDP_EX ((uint16_t)1 << ETH_RSS_IPV6_UDP_EX_SHIFT)
374 #define ETH_RSS_NONF_IPV4_UDP ((uint64_t)1 << ETH_RSS_NONF_IPV4_UDP_SHIFT)
375 #define ETH_RSS_NONF_IPV4_TCP ((uint64_t)1 << ETH_RSS_NONF_IPV4_TCP_SHIFT)
376 #define ETH_RSS_NONF_IPV4_SCTP ((uint64_t)1 << ETH_RSS_NONF_IPV4_SCTP_SHIFT)
377 #define ETH_RSS_NONF_IPV4_OTHER ((uint64_t)1 << ETH_RSS_NONF_IPV4_OTHER_SHIFT)
378 #define ETH_RSS_FRAG_IPV4 ((uint64_t)1 << ETH_RSS_FRAG_IPV4_SHIFT)
379 #define ETH_RSS_NONF_IPV6_UDP ((uint64_t)1 << ETH_RSS_NONF_IPV6_UDP_SHIFT)
380 #define ETH_RSS_NONF_IPV6_TCP ((uint64_t)1 << ETH_RSS_NONF_IPV6_TCP_SHIFT)
381 #define ETH_RSS_NONF_IPV6_SCTP ((uint64_t)1 << ETH_RSS_NONF_IPV6_SCTP_SHIFT)
382 #define ETH_RSS_NONF_IPV6_OTHER ((uint64_t)1 << ETH_RSS_NONF_IPV6_OTHER_SHIFT)
383 #define ETH_RSS_FRAG_IPV6 ((uint64_t)1 << ETH_RSS_FRAG_IPV6_SHIFT)
384 #define ETH_RSS_FCOE_OX ((uint64_t)1 << ETH_RSS_FCOE_OX_SHIFT) /* not used */
385 #define ETH_RSS_FCOE_RX ((uint64_t)1 << ETH_RSS_FCOE_RX_SHIFT) /* not used */
386 #define ETH_RSS_FCOE_OTHER ((uint64_t)1 << ETH_RSS_FCOE_OTHER_SHIFT) /* not used */
387 #define ETH_RSS_L2_PAYLOAD ((uint64_t)1 << ETH_RSS_L2_PAYLOAD_SHIFT)
389 #define ETH_RSS_IP ( \
392 ETH_RSS_NONF_IPV4_OTHER | \
393 ETH_RSS_FRAG_IPV4 | \
394 ETH_RSS_NONF_IPV6_OTHER | \
396 #define ETH_RSS_UDP ( \
401 ETH_RSS_IPV6_UDP_EX | \
402 ETH_RSS_NONF_IPV4_UDP | \
403 ETH_RSS_NONF_IPV6_UDP)
404 /**< Mask of valid RSS hash protocols */
405 #define ETH_RSS_PROTO_MASK ( \
411 ETH_RSS_IPV6_TCP_EX | \
414 ETH_RSS_IPV6_UDP_EX | \
415 ETH_RSS_NONF_IPV4_UDP | \
416 ETH_RSS_NONF_IPV4_TCP | \
417 ETH_RSS_NONF_IPV4_SCTP | \
418 ETH_RSS_NONF_IPV4_OTHER | \
419 ETH_RSS_FRAG_IPV4 | \
420 ETH_RSS_NONF_IPV6_UDP | \
421 ETH_RSS_NONF_IPV6_TCP | \
422 ETH_RSS_NONF_IPV6_SCTP | \
423 ETH_RSS_NONF_IPV6_OTHER | \
424 ETH_RSS_FRAG_IPV6 | \
427 /* Definitions used for redirection table entry size */
428 #define ETH_RSS_RETA_NUM_ENTRIES 128
429 #define ETH_RSS_RETA_MAX_QUEUE 16
431 /* Definitions used for VMDQ and DCB functionality */
432 #define ETH_VMDQ_MAX_VLAN_FILTERS 64 /**< Maximum nb. of VMDQ vlan filters. */
433 #define ETH_DCB_NUM_USER_PRIORITIES 8 /**< Maximum nb. of DCB priorities. */
434 #define ETH_VMDQ_DCB_NUM_QUEUES 128 /**< Maximum nb. of VMDQ DCB queues. */
435 #define ETH_DCB_NUM_QUEUES 128 /**< Maximum nb. of DCB queues. */
437 /* DCB capability defines */
438 #define ETH_DCB_PG_SUPPORT 0x00000001 /**< Priority Group(ETS) support. */
439 #define ETH_DCB_PFC_SUPPORT 0x00000002 /**< Priority Flow Control support. */
441 /* Definitions used for VLAN Offload functionality */
442 #define ETH_VLAN_STRIP_OFFLOAD 0x0001 /**< VLAN Strip On/Off */
443 #define ETH_VLAN_FILTER_OFFLOAD 0x0002 /**< VLAN Filter On/Off */
444 #define ETH_VLAN_EXTEND_OFFLOAD 0x0004 /**< VLAN Extend On/Off */
446 /* Definitions used for mask VLAN setting */
447 #define ETH_VLAN_STRIP_MASK 0x0001 /**< VLAN Strip setting mask */
448 #define ETH_VLAN_FILTER_MASK 0x0002 /**< VLAN Filter setting mask*/
449 #define ETH_VLAN_EXTEND_MASK 0x0004 /**< VLAN Extend setting mask*/
450 #define ETH_VLAN_ID_MAX 0x0FFF /**< VLAN ID is in lower 12 bits*/
452 /* Definitions used for receive MAC address */
453 #define ETH_NUM_RECEIVE_MAC_ADDR 128 /**< Maximum nb. of receive mac addr. */
455 /* Definitions used for unicast hash */
456 #define ETH_VMDQ_NUM_UC_HASH_ARRAY 128 /**< Maximum nb. of UC hash array. */
458 /* Definitions used for VMDQ pool rx mode setting */
459 #define ETH_VMDQ_ACCEPT_UNTAG 0x0001 /**< accept untagged packets. */
460 #define ETH_VMDQ_ACCEPT_HASH_MC 0x0002 /**< accept packets in multicast table . */
461 #define ETH_VMDQ_ACCEPT_HASH_UC 0x0004 /**< accept packets in unicast table. */
462 #define ETH_VMDQ_ACCEPT_BROADCAST 0x0008 /**< accept broadcast packets. */
463 #define ETH_VMDQ_ACCEPT_MULTICAST 0x0010 /**< multicast promiscuous. */
465 /* Definitions used for VMDQ mirror rules setting */
466 #define ETH_VMDQ_NUM_MIRROR_RULE 4 /**< Maximum nb. of mirror rules. . */
468 #define ETH_VMDQ_POOL_MIRROR 0x0001 /**< Virtual Pool Mirroring. */
469 #define ETH_VMDQ_UPLINK_MIRROR 0x0002 /**< Uplink Port Mirroring. */
470 #define ETH_VMDQ_DOWNLIN_MIRROR 0x0004 /**< Downlink Port Mirroring. */
471 #define ETH_VMDQ_VLAN_MIRROR 0x0008 /**< VLAN Mirroring. */
474 * A structure used to configure VLAN traffic mirror of an Ethernet port.
476 struct rte_eth_vlan_mirror {
477 uint64_t vlan_mask; /**< mask for valid VLAN ID. */
478 uint16_t vlan_id[ETH_VMDQ_MAX_VLAN_FILTERS];
479 /** VLAN ID list for vlan mirror. */
483 * A structure used to configure traffic mirror of an Ethernet port.
485 struct rte_eth_vmdq_mirror_conf {
486 uint8_t rule_type_mask; /**< Mirroring rule type mask we want to set */
487 uint8_t dst_pool; /**< Destination pool for this mirror rule. */
488 uint64_t pool_mask; /**< Bitmap of pool for pool mirroring */
489 struct rte_eth_vlan_mirror vlan; /**< VLAN ID setting for VLAN mirroring */
493 * A structure used to configure Redirection Table of the Receive Side
494 * Scaling (RSS) feature of an Ethernet port.
496 struct rte_eth_rss_reta {
497 /** First 64 mask bits indicate which entry(s) need to updated/queried. */
499 /** Second 64 mask bits indicate which entry(s) need to updated/queried. */
501 uint8_t reta[ETH_RSS_RETA_NUM_ENTRIES]; /**< 128 RETA entries*/
505 * This enum indicates the possible number of traffic classes
506 * in DCB configratioins
508 enum rte_eth_nb_tcs {
509 ETH_4_TCS = 4, /**< 4 TCs with DCB. */
510 ETH_8_TCS = 8 /**< 8 TCs with DCB. */
514 * This enum indicates the possible number of queue pools
515 * in VMDQ configurations.
517 enum rte_eth_nb_pools {
518 ETH_8_POOLS = 8, /**< 8 VMDq pools. */
519 ETH_16_POOLS = 16, /**< 16 VMDq pools. */
520 ETH_32_POOLS = 32, /**< 32 VMDq pools. */
521 ETH_64_POOLS = 64 /**< 64 VMDq pools. */
524 /* This structure may be extended in future. */
525 struct rte_eth_dcb_rx_conf {
526 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs */
527 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
528 /**< Possible DCB queue,4 or 8. */
531 struct rte_eth_vmdq_dcb_tx_conf {
532 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools. */
533 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
534 /**< Possible DCB queue,4 or 8. */
537 struct rte_eth_dcb_tx_conf {
538 enum rte_eth_nb_tcs nb_tcs; /**< Possible DCB TCs, 4 or 8 TCs. */
539 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
540 /**< Possible DCB queue,4 or 8. */
543 struct rte_eth_vmdq_tx_conf {
544 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq mode, 64 pools. */
548 * A structure used to configure the VMDQ+DCB feature
549 * of an Ethernet port.
551 * Using this feature, packets are routed to a pool of queues, based
552 * on the vlan id in the vlan tag, and then to a specific queue within
553 * that pool, using the user priority vlan tag field.
555 * A default pool may be used, if desired, to route all traffic which
556 * does not match the vlan filter rules.
558 struct rte_eth_vmdq_dcb_conf {
559 enum rte_eth_nb_pools nb_queue_pools; /**< With DCB, 16 or 32 pools */
560 uint8_t enable_default_pool; /**< If non-zero, use a default pool */
561 uint8_t default_pool; /**< The default pool, if applicable */
562 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */
564 uint16_t vlan_id; /**< The vlan id of the received frame */
565 uint64_t pools; /**< Bitmask of pools for packet rx */
566 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */
567 uint8_t dcb_queue[ETH_DCB_NUM_USER_PRIORITIES];
568 /**< Selects a queue in a pool */
571 struct rte_eth_vmdq_rx_conf {
572 enum rte_eth_nb_pools nb_queue_pools; /**< VMDq only mode, 8 or 64 pools */
573 uint8_t enable_default_pool; /**< If non-zero, use a default pool */
574 uint8_t default_pool; /**< The default pool, if applicable */
575 uint8_t enable_loop_back; /**< Enable VT loop back */
576 uint8_t nb_pool_maps; /**< We can have up to 64 filters/mappings */
578 uint16_t vlan_id; /**< The vlan id of the received frame */
579 uint64_t pools; /**< Bitmask of pools for packet rx */
580 } pool_map[ETH_VMDQ_MAX_VLAN_FILTERS]; /**< VMDq vlan pool maps. */
584 * A structure used to configure the TX features of an Ethernet port.
586 struct rte_eth_txmode {
587 enum rte_eth_tx_mq_mode mq_mode; /**< TX multi-queues mode. */
589 /* For i40e specifically */
591 uint8_t hw_vlan_reject_tagged : 1,
592 /**< If set, reject sending out tagged pkts */
593 hw_vlan_reject_untagged : 1,
594 /**< If set, reject sending out untagged pkts */
595 hw_vlan_insert_pvid : 1;
596 /**< If set, enable port based VLAN insertion */
600 * A structure used to configure an RX ring of an Ethernet port.
602 struct rte_eth_rxconf {
603 struct rte_eth_thresh rx_thresh; /**< RX ring threshold registers. */
604 uint16_t rx_free_thresh; /**< Drives the freeing of RX descriptors. */
605 uint8_t rx_drop_en; /**< Drop packets if no descriptors are available. */
606 uint8_t start_rx_per_q; /**< start rx per queue. */
609 #define ETH_TXQ_FLAGS_NOMULTSEGS 0x0001 /**< nb_segs=1 for all mbufs */
610 #define ETH_TXQ_FLAGS_NOREFCOUNT 0x0002 /**< refcnt can be ignored */
611 #define ETH_TXQ_FLAGS_NOMULTMEMP 0x0004 /**< all bufs come from same mempool */
612 #define ETH_TXQ_FLAGS_NOVLANOFFL 0x0100 /**< disable VLAN offload */
613 #define ETH_TXQ_FLAGS_NOXSUMSCTP 0x0200 /**< disable SCTP checksum offload */
614 #define ETH_TXQ_FLAGS_NOXSUMUDP 0x0400 /**< disable UDP checksum offload */
615 #define ETH_TXQ_FLAGS_NOXSUMTCP 0x0800 /**< disable TCP checksum offload */
616 #define ETH_TXQ_FLAGS_NOOFFLOADS \
617 (ETH_TXQ_FLAGS_NOVLANOFFL | ETH_TXQ_FLAGS_NOXSUMSCTP | \
618 ETH_TXQ_FLAGS_NOXSUMUDP | ETH_TXQ_FLAGS_NOXSUMTCP)
620 * A structure used to configure a TX ring of an Ethernet port.
622 struct rte_eth_txconf {
623 struct rte_eth_thresh tx_thresh; /**< TX ring threshold registers. */
624 uint16_t tx_rs_thresh; /**< Drives the setting of RS bit on TXDs. */
625 uint16_t tx_free_thresh; /**< Drives the freeing of TX buffers. */
626 uint32_t txq_flags; /**< Set flags for the Tx queue */
627 uint8_t start_tx_per_q; /**< start tx per queue. */
631 * This enum indicates the flow control mode
633 enum rte_eth_fc_mode {
634 RTE_FC_NONE = 0, /**< Disable flow control. */
635 RTE_FC_RX_PAUSE, /**< RX pause frame, enable flowctrl on TX side. */
636 RTE_FC_TX_PAUSE, /**< TX pause frame, enable flowctrl on RX side. */
637 RTE_FC_FULL /**< Enable flow control on both side. */
641 * A structure used to configure Ethernet flow control parameter.
642 * These parameters will be configured into the register of the NIC.
643 * Please refer to the corresponding data sheet for proper value.
645 struct rte_eth_fc_conf {
646 uint32_t high_water; /**< High threshold value to trigger XOFF */
647 uint32_t low_water; /**< Low threshold value to trigger XON */
648 uint16_t pause_time; /**< Pause quota in the Pause frame */
649 uint16_t send_xon; /**< Is XON frame need be sent */
650 enum rte_eth_fc_mode mode; /**< Link flow control mode */
651 uint8_t mac_ctrl_frame_fwd; /**< Forward MAC control frames */
652 uint8_t autoneg; /**< Use Pause autoneg */
656 * A structure used to configure Ethernet priority flow control parameter.
657 * These parameters will be configured into the register of the NIC.
658 * Please refer to the corresponding data sheet for proper value.
660 struct rte_eth_pfc_conf {
661 struct rte_eth_fc_conf fc; /**< General flow control parameter. */
662 uint8_t priority; /**< VLAN User Priority. */
666 * Flow Director setting modes: none (default), signature or perfect.
669 RTE_FDIR_MODE_NONE = 0, /**< Disable FDIR support. */
670 RTE_FDIR_MODE_SIGNATURE, /**< Enable FDIR signature filter mode. */
671 RTE_FDIR_MODE_PERFECT, /**< Enable FDIR perfect filter mode. */
675 * Memory space that can be configured to store Flow Director filters
676 * in the board memory.
678 enum rte_fdir_pballoc_type {
679 RTE_FDIR_PBALLOC_64K = 0, /**< 64k. */
680 RTE_FDIR_PBALLOC_128K, /**< 128k. */
681 RTE_FDIR_PBALLOC_256K, /**< 256k. */
685 * Select report mode of FDIR hash information in RX descriptors.
687 enum rte_fdir_status_mode {
688 RTE_FDIR_NO_REPORT_STATUS = 0, /**< Never report FDIR hash. */
689 RTE_FDIR_REPORT_STATUS, /**< Only report FDIR hash for matching pkts. */
690 RTE_FDIR_REPORT_STATUS_ALWAYS, /**< Always report FDIR hash. */
694 * A structure used to configure the Flow Director (FDIR) feature
695 * of an Ethernet port.
697 * If mode is RTE_FDIR_DISABLE, the pballoc value is ignored.
699 struct rte_fdir_conf {
700 enum rte_fdir_mode mode; /**< Flow Director mode. */
701 enum rte_fdir_pballoc_type pballoc; /**< Space for FDIR filters. */
702 enum rte_fdir_status_mode status; /**< How to report FDIR hash. */
703 /** Offset of flexbytes field in RX packets (in 16-bit word units). */
704 uint8_t flexbytes_offset;
705 /** RX queue of packets matching a "drop" filter in perfect mode. */
710 * Possible l4type of FDIR filters.
713 RTE_FDIR_L4TYPE_NONE = 0, /**< None. */
714 RTE_FDIR_L4TYPE_UDP, /**< UDP. */
715 RTE_FDIR_L4TYPE_TCP, /**< TCP. */
716 RTE_FDIR_L4TYPE_SCTP, /**< SCTP. */
720 * Select IPv4 or IPv6 FDIR filters.
723 RTE_FDIR_IPTYPE_IPV4 = 0, /**< IPv4. */
724 RTE_FDIR_IPTYPE_IPV6 , /**< IPv6. */
728 * A structure used to define a FDIR packet filter.
730 struct rte_fdir_filter {
731 uint16_t flex_bytes; /**< Flex bytes value to match. */
732 uint16_t vlan_id; /**< VLAN ID value to match, 0 otherwise. */
733 uint16_t port_src; /**< Source port to match, 0 otherwise. */
734 uint16_t port_dst; /**< Destination port to match, 0 otherwise. */
736 uint32_t ipv4_addr; /**< IPv4 source address to match. */
737 uint32_t ipv6_addr[4]; /**< IPv6 source address to match. */
738 } ip_src; /**< IPv4/IPv6 source address to match (union of above). */
740 uint32_t ipv4_addr; /**< IPv4 destination address to match. */
741 uint32_t ipv6_addr[4]; /**< IPv6 destination address to match */
742 } ip_dst; /**< IPv4/IPv6 destination address to match (union of above). */
743 enum rte_l4type l4type; /**< l4type to match: NONE/UDP/TCP/SCTP. */
744 enum rte_iptype iptype; /**< IP packet type to match: IPv4 or IPv6. */
748 * A structure used to configure FDIR masks that are used by the device
749 * to match the various fields of RX packet headers.
750 * @note The only_ip_flow field has the opposite meaning compared to other
753 struct rte_fdir_masks {
754 /** When set to 1, packet l4type is \b NOT relevant in filters, and
755 source and destination port masks must be set to zero. */
756 uint8_t only_ip_flow;
757 /** If set to 1, vlan_id is relevant in filters. */
759 /** If set to 1, vlan_prio is relevant in filters. */
761 /** If set to 1, flexbytes is relevant in filters. */
763 /** If set to 1, set the IPv6 masks. Otherwise set the IPv4 masks. */
764 uint8_t set_ipv6_mask;
765 /** When set to 1, comparison of destination IPv6 address with IP6AT
766 registers is meaningful. */
767 uint8_t comp_ipv6_dst;
768 /** Mask of Destination IPv4 Address. All bits set to 1 define the
769 relevant bits to use in the destination address of an IPv4 packet
770 when matching it against FDIR filters. */
771 uint32_t dst_ipv4_mask;
772 /** Mask of Source IPv4 Address. All bits set to 1 define
773 the relevant bits to use in the source address of an IPv4 packet
774 when matching it against FDIR filters. */
775 uint32_t src_ipv4_mask;
776 /** Mask of Source IPv6 Address. All bits set to 1 define the
777 relevant BYTES to use in the source address of an IPv6 packet
778 when matching it against FDIR filters. */
779 uint16_t dst_ipv6_mask;
780 /** Mask of Destination IPv6 Address. All bits set to 1 define the
781 relevant BYTES to use in the destination address of an IPv6 packet
782 when matching it against FDIR filters. */
783 uint16_t src_ipv6_mask;
784 /** Mask of Source Port. All bits set to 1 define the relevant
785 bits to use in the source port of an IP packets when matching it
786 against FDIR filters. */
787 uint16_t src_port_mask;
788 /** Mask of Destination Port. All bits set to 1 define the relevant
789 bits to use in the destination port of an IP packet when matching it
790 against FDIR filters. */
791 uint16_t dst_port_mask;
795 * A structure used to report the status of the flow director filters in use.
797 struct rte_eth_fdir {
798 /** Number of filters with collision indication. */
800 /** Number of free (non programmed) filters. */
802 /** The Lookup hash value of the added filter that updated the value
803 of the MAXLEN field */
805 /** Longest linked list of filters in the table. */
807 /** Number of added filters. */
809 /** Number of removed filters. */
811 /** Number of failed added filters (no more space in device). */
813 /** Number of failed removed filters. */
818 * A structure used to enable/disable specific device interrupts.
820 struct rte_intr_conf {
821 /** enable/disable lsc interrupt. 0 (default) - disable, 1 enable */
826 * A structure used to configure an Ethernet port.
827 * Depending upon the RX multi-queue mode, extra advanced
828 * configuration settings may be needed.
830 struct rte_eth_conf {
832 /**< ETH_LINK_SPEED_10[0|00|000], or 0 for autonegotation */
833 uint16_t link_duplex;
834 /**< ETH_LINK_[HALF_DUPLEX|FULL_DUPLEX], or 0 for autonegotation */
835 struct rte_eth_rxmode rxmode; /**< Port RX configuration. */
836 struct rte_eth_txmode txmode; /**< Port TX configuration. */
837 uint32_t lpbk_mode; /**< Loopback operation mode. By default the value
838 is 0, meaning the loopback mode is disabled.
839 Read the datasheet of given ethernet controller
840 for details. The possible values of this field
841 are defined in implementation of each driver. */
843 struct rte_eth_rss_conf rss_conf; /**< Port RSS configuration */
844 struct rte_eth_vmdq_dcb_conf vmdq_dcb_conf;
845 /**< Port vmdq+dcb configuration. */
846 struct rte_eth_dcb_rx_conf dcb_rx_conf;
847 /**< Port dcb RX configuration. */
848 struct rte_eth_vmdq_rx_conf vmdq_rx_conf;
849 /**< Port vmdq RX configuration. */
850 } rx_adv_conf; /**< Port RX filtering configuration (union). */
852 struct rte_eth_vmdq_dcb_tx_conf vmdq_dcb_tx_conf;
853 /**< Port vmdq+dcb TX configuration. */
854 struct rte_eth_dcb_tx_conf dcb_tx_conf;
855 /**< Port dcb TX configuration. */
856 struct rte_eth_vmdq_tx_conf vmdq_tx_conf;
857 /**< Port vmdq TX configuration. */
858 } tx_adv_conf; /**< Port TX DCB configuration (union). */
859 /** Currently,Priority Flow Control(PFC) are supported,if DCB with PFC
860 is needed,and the variable must be set ETH_DCB_PFC_SUPPORT. */
861 uint32_t dcb_capability_en;
862 struct rte_fdir_conf fdir_conf; /**< FDIR configuration. */
863 struct rte_intr_conf intr_conf; /**< Interrupt mode configuration. */
867 * A structure used to retrieve the contextual information of
868 * an Ethernet device, such as the controlling driver of the device,
869 * its PCI context, etc...
873 * RX offload capabilities of a device.
875 #define DEV_RX_OFFLOAD_VLAN_STRIP 0x00000001
876 #define DEV_RX_OFFLOAD_IPV4_CKSUM 0x00000002
877 #define DEV_RX_OFFLOAD_UDP_CKSUM 0x00000004
878 #define DEV_RX_OFFLOAD_TCP_CKSUM 0x00000008
879 #define DEV_RX_OFFLOAD_TCP_LRO 0x00000010
882 * TX offload capabilities of a device.
884 #define DEV_TX_OFFLOAD_VLAN_INSERT 0x00000001
885 #define DEV_TX_OFFLOAD_IPV4_CKSUM 0x00000002
886 #define DEV_TX_OFFLOAD_UDP_CKSUM 0x00000004
887 #define DEV_TX_OFFLOAD_TCP_CKSUM 0x00000008
888 #define DEV_TX_OFFLOAD_SCTP_CKSUM 0x00000010
889 #define DEV_TX_OFFLOAD_TCP_TSO 0x00000020
890 #define DEV_TX_OFFLOAD_UDP_TSO 0x00000040
892 struct rte_eth_dev_info {
893 struct rte_pci_device *pci_dev; /**< Device PCI information. */
894 const char *driver_name; /**< Device Driver name. */
895 unsigned int if_index; /**< Index to bound host interface, or 0 if none.
896 Use if_indextoname() to translate into an interface name. */
897 uint32_t min_rx_bufsize; /**< Minimum size of RX buffer. */
898 uint32_t max_rx_pktlen; /**< Maximum configurable length of RX pkt. */
899 uint16_t max_rx_queues; /**< Maximum number of RX queues. */
900 uint16_t max_tx_queues; /**< Maximum number of TX queues. */
901 uint32_t max_mac_addrs; /**< Maximum number of MAC addresses. */
902 uint32_t max_hash_mac_addrs;
903 /** Maximum number of hash MAC addresses for MTA and UTA. */
904 uint16_t max_vfs; /**< Maximum number of VFs. */
905 uint16_t max_vmdq_pools; /**< Maximum number of VMDq pools. */
906 uint32_t rx_offload_capa; /**< Device RX offload capabilities. */
907 uint32_t tx_offload_capa; /**< Device TX offload capabilities. */
912 struct rte_eth_dev_callback;
913 /** @internal Structure to keep track of registered callbacks */
914 TAILQ_HEAD(rte_eth_dev_cb_list, rte_eth_dev_callback);
916 #define TCP_UGR_FLAG 0x20
917 #define TCP_ACK_FLAG 0x10
918 #define TCP_PSH_FLAG 0x08
919 #define TCP_RST_FLAG 0x04
920 #define TCP_SYN_FLAG 0x02
921 #define TCP_FIN_FLAG 0x01
922 #define TCP_FLAG_ALL 0x3F
925 * A structure used to define an ethertype filter.
927 struct rte_ethertype_filter {
928 uint16_t ethertype; /**< little endian. */
929 uint8_t priority_en; /**< compare priority enable. */
934 * A structure used to define an syn filter.
936 struct rte_syn_filter {
937 uint8_t hig_pri; /**< 1 means higher pri than 2tuple, 5tupe,
938 and flex filter, 0 means lower pri. */
942 * A structure used to define a 2tuple filter.
944 struct rte_2tuple_filter {
945 uint16_t dst_port; /**< big endian. */
948 uint16_t priority; /**< used when more than one filter matches. */
949 uint8_t dst_port_mask:1, /**< if mask is 1b, means not compare. */
954 * A structure used to define a flex filter.
956 struct rte_flex_filter {
958 uint32_t dwords[32]; /**< flex bytes in big endian. */
959 uint8_t mask[16]; /**< if mask bit is 1b, do not compare
960 corresponding byte in dwords. */
965 * A structure used to define a 5tuple filter.
967 struct rte_5tuple_filter {
968 uint32_t dst_ip; /**< destination IP address in big endian. */
969 uint32_t src_ip; /**< source IP address in big endian. */
970 uint16_t dst_port; /**< destination port in big endian. */
971 uint16_t src_port; /**< source Port big endian. */
972 uint8_t protocol; /**< l4 protocol. */
973 uint8_t tcp_flags; /**< tcp flags. */
974 uint16_t priority; /**< seven evels (001b-111b), 111b is highest,
975 used when more than one filter matches. */
976 uint8_t dst_ip_mask:1, /**< if mask is 1b, do not compare dst ip. */
977 src_ip_mask:1, /**< if mask is 1b, do not compare src ip. */
978 dst_port_mask:1, /**< if mask is 1b, do not compare dst port. */
979 src_port_mask:1, /**< if mask is 1b, do not compare src port. */
980 protocol_mask:1; /**< if mask is 1b, do not compare protocol. */
984 * Definitions of all functions exported by an Ethernet driver through the
985 * the generic structure of type *eth_dev_ops* supplied in the *rte_eth_dev*
986 * structure associated with an Ethernet device.
989 typedef int (*eth_dev_configure_t)(struct rte_eth_dev *dev);
990 /**< @internal Ethernet device configuration. */
992 typedef int (*eth_dev_start_t)(struct rte_eth_dev *dev);
993 /**< @internal Function used to start a configured Ethernet device. */
995 typedef void (*eth_dev_stop_t)(struct rte_eth_dev *dev);
996 /**< @internal Function used to stop a configured Ethernet device. */
998 typedef int (*eth_dev_set_link_up_t)(struct rte_eth_dev *dev);
999 /**< @internal Function used to link up a configured Ethernet device. */
1001 typedef int (*eth_dev_set_link_down_t)(struct rte_eth_dev *dev);
1002 /**< @internal Function used to link down a configured Ethernet device. */
1004 typedef void (*eth_dev_close_t)(struct rte_eth_dev *dev);
1005 /**< @internal Function used to close a configured Ethernet device. */
1007 typedef void (*eth_promiscuous_enable_t)(struct rte_eth_dev *dev);
1008 /**< @internal Function used to enable the RX promiscuous mode of an Ethernet device. */
1010 typedef void (*eth_promiscuous_disable_t)(struct rte_eth_dev *dev);
1011 /**< @internal Function used to disable the RX promiscuous mode of an Ethernet device. */
1013 typedef void (*eth_allmulticast_enable_t)(struct rte_eth_dev *dev);
1014 /**< @internal Enable the receipt of all multicast packets by an Ethernet device. */
1016 typedef void (*eth_allmulticast_disable_t)(struct rte_eth_dev *dev);
1017 /**< @internal Disable the receipt of all multicast packets by an Ethernet device. */
1019 typedef int (*eth_link_update_t)(struct rte_eth_dev *dev,
1020 int wait_to_complete);
1021 /**< @internal Get link speed, duplex mode and state (up/down) of an Ethernet device. */
1023 typedef void (*eth_stats_get_t)(struct rte_eth_dev *dev,
1024 struct rte_eth_stats *igb_stats);
1025 /**< @internal Get global I/O statistics of an Ethernet device. */
1027 typedef void (*eth_stats_reset_t)(struct rte_eth_dev *dev);
1028 /**< @internal Reset global I/O statistics of an Ethernet device to 0. */
1030 typedef int (*eth_queue_stats_mapping_set_t)(struct rte_eth_dev *dev,
1034 /**< @internal Set a queue statistics mapping for a tx/rx queue of an Ethernet device. */
1036 typedef void (*eth_dev_infos_get_t)(struct rte_eth_dev *dev,
1037 struct rte_eth_dev_info *dev_info);
1038 /**< @internal Get specific informations of an Ethernet device. */
1040 typedef int (*eth_queue_start_t)(struct rte_eth_dev *dev,
1042 /**< @internal Start rx and tx of a queue of an Ethernet device. */
1044 typedef int (*eth_queue_stop_t)(struct rte_eth_dev *dev,
1046 /**< @internal Stop rx and tx of a queue of an Ethernet device. */
1048 typedef int (*eth_rx_queue_setup_t)(struct rte_eth_dev *dev,
1049 uint16_t rx_queue_id,
1050 uint16_t nb_rx_desc,
1051 unsigned int socket_id,
1052 const struct rte_eth_rxconf *rx_conf,
1053 struct rte_mempool *mb_pool);
1054 /**< @internal Set up a receive queue of an Ethernet device. */
1056 typedef int (*eth_tx_queue_setup_t)(struct rte_eth_dev *dev,
1057 uint16_t tx_queue_id,
1058 uint16_t nb_tx_desc,
1059 unsigned int socket_id,
1060 const struct rte_eth_txconf *tx_conf);
1061 /**< @internal Setup a transmit queue of an Ethernet device. */
1063 typedef void (*eth_queue_release_t)(void *queue);
1064 /**< @internal Release memory resources allocated by given RX/TX queue. */
1066 typedef uint32_t (*eth_rx_queue_count_t)(struct rte_eth_dev *dev,
1067 uint16_t rx_queue_id);
1068 /**< @Get number of available descriptors on a receive queue of an Ethernet device. */
1070 typedef int (*eth_rx_descriptor_done_t)(void *rxq, uint16_t offset);
1071 /**< @Check DD bit of specific RX descriptor */
1073 typedef int (*vlan_filter_set_t)(struct rte_eth_dev *dev,
1076 /**< @internal filtering of a VLAN Tag Identifier by an Ethernet device. */
1078 typedef void (*vlan_tpid_set_t)(struct rte_eth_dev *dev,
1080 /**< @internal set the outer VLAN-TPID by an Ethernet device. */
1082 typedef void (*vlan_offload_set_t)(struct rte_eth_dev *dev, int mask);
1083 /**< @internal set VLAN offload function by an Ethernet device. */
1085 typedef int (*vlan_pvid_set_t)(struct rte_eth_dev *dev,
1088 /**< @internal set port based TX VLAN insertion by an Ethernet device. */
1090 typedef void (*vlan_strip_queue_set_t)(struct rte_eth_dev *dev,
1091 uint16_t rx_queue_id,
1093 /**< @internal VLAN stripping enable/disable by an queue of Ethernet device. */
1095 typedef uint16_t (*eth_rx_burst_t)(void *rxq,
1096 struct rte_mbuf **rx_pkts,
1098 /**< @internal Retrieve input packets from a receive queue of an Ethernet device. */
1100 typedef uint16_t (*eth_tx_burst_t)(void *txq,
1101 struct rte_mbuf **tx_pkts,
1103 /**< @internal Send output packets on a transmit queue of an Ethernet device. */
1105 typedef int (*fdir_add_signature_filter_t)(struct rte_eth_dev *dev,
1106 struct rte_fdir_filter *fdir_ftr,
1108 /**< @internal Setup a new signature filter rule on an Ethernet device */
1110 typedef int (*fdir_update_signature_filter_t)(struct rte_eth_dev *dev,
1111 struct rte_fdir_filter *fdir_ftr,
1113 /**< @internal Update a signature filter rule on an Ethernet device */
1115 typedef int (*fdir_remove_signature_filter_t)(struct rte_eth_dev *dev,
1116 struct rte_fdir_filter *fdir_ftr);
1117 /**< @internal Remove a signature filter rule on an Ethernet device */
1119 typedef void (*fdir_infos_get_t)(struct rte_eth_dev *dev,
1120 struct rte_eth_fdir *fdir);
1121 /**< @internal Get information about fdir status */
1123 typedef int (*fdir_add_perfect_filter_t)(struct rte_eth_dev *dev,
1124 struct rte_fdir_filter *fdir_ftr,
1125 uint16_t soft_id, uint8_t rx_queue,
1127 /**< @internal Setup a new perfect filter rule on an Ethernet device */
1129 typedef int (*fdir_update_perfect_filter_t)(struct rte_eth_dev *dev,
1130 struct rte_fdir_filter *fdir_ftr,
1131 uint16_t soft_id, uint8_t rx_queue,
1133 /**< @internal Update a perfect filter rule on an Ethernet device */
1135 typedef int (*fdir_remove_perfect_filter_t)(struct rte_eth_dev *dev,
1136 struct rte_fdir_filter *fdir_ftr,
1138 /**< @internal Remove a perfect filter rule on an Ethernet device */
1140 typedef int (*fdir_set_masks_t)(struct rte_eth_dev *dev,
1141 struct rte_fdir_masks *fdir_masks);
1142 /**< @internal Setup flow director masks on an Ethernet device */
1144 typedef int (*flow_ctrl_get_t)(struct rte_eth_dev *dev,
1145 struct rte_eth_fc_conf *fc_conf);
1146 /**< @internal Get current flow control parameter on an Ethernet device */
1148 typedef int (*flow_ctrl_set_t)(struct rte_eth_dev *dev,
1149 struct rte_eth_fc_conf *fc_conf);
1150 /**< @internal Setup flow control parameter on an Ethernet device */
1152 typedef int (*priority_flow_ctrl_set_t)(struct rte_eth_dev *dev,
1153 struct rte_eth_pfc_conf *pfc_conf);
1154 /**< @internal Setup priority flow control parameter on an Ethernet device */
1156 typedef int (*reta_update_t)(struct rte_eth_dev *dev,
1157 struct rte_eth_rss_reta *reta_conf);
1158 /**< @internal Update RSS redirection table on an Ethernet device */
1160 typedef int (*reta_query_t)(struct rte_eth_dev *dev,
1161 struct rte_eth_rss_reta *reta_conf);
1162 /**< @internal Query RSS redirection table on an Ethernet device */
1164 typedef int (*rss_hash_update_t)(struct rte_eth_dev *dev,
1165 struct rte_eth_rss_conf *rss_conf);
1166 /**< @internal Update RSS hash configuration of an Ethernet device */
1168 typedef int (*rss_hash_conf_get_t)(struct rte_eth_dev *dev,
1169 struct rte_eth_rss_conf *rss_conf);
1170 /**< @internal Get current RSS hash configuration of an Ethernet device */
1172 typedef int (*eth_dev_led_on_t)(struct rte_eth_dev *dev);
1173 /**< @internal Turn on SW controllable LED on an Ethernet device */
1175 typedef int (*eth_dev_led_off_t)(struct rte_eth_dev *dev);
1176 /**< @internal Turn off SW controllable LED on an Ethernet device */
1178 typedef void (*eth_mac_addr_remove_t)(struct rte_eth_dev *dev, uint32_t index);
1179 /**< @internal Remove MAC address from receive address register */
1181 typedef void (*eth_mac_addr_add_t)(struct rte_eth_dev *dev,
1182 struct ether_addr *mac_addr,
1185 /**< @internal Set a MAC address into Receive Address Address Register */
1187 typedef int (*eth_uc_hash_table_set_t)(struct rte_eth_dev *dev,
1188 struct ether_addr *mac_addr,
1190 /**< @internal Set a Unicast Hash bitmap */
1192 typedef int (*eth_uc_all_hash_table_set_t)(struct rte_eth_dev *dev,
1194 /**< @internal Set all Unicast Hash bitmap */
1196 typedef int (*eth_set_vf_rx_mode_t)(struct rte_eth_dev *dev,
1200 /**< @internal Set a VF receive mode */
1202 typedef int (*eth_set_vf_rx_t)(struct rte_eth_dev *dev,
1205 /**< @internal Set a VF receive mode */
1207 typedef int (*eth_set_vf_tx_t)(struct rte_eth_dev *dev,
1210 /**< @internal Enable or disable a VF transmit */
1212 typedef int (*eth_set_vf_vlan_filter_t)(struct rte_eth_dev *dev,
1216 /**< @internal Set VF VLAN pool filter */
1218 typedef int (*eth_set_queue_rate_limit_t)(struct rte_eth_dev *dev,
1221 /**< @internal Set queue TX rate */
1223 typedef int (*eth_set_vf_rate_limit_t)(struct rte_eth_dev *dev,
1227 /**< @internal Set VF TX rate */
1229 typedef int (*eth_mirror_rule_set_t)(struct rte_eth_dev *dev,
1230 struct rte_eth_vmdq_mirror_conf *mirror_conf,
1233 /**< @internal Add a traffic mirroring rule on an Ethernet device */
1235 typedef int (*eth_mirror_rule_reset_t)(struct rte_eth_dev *dev,
1237 /**< @internal Remove a traffic mirroring rule on an Ethernet device */
1239 #ifdef RTE_NIC_BYPASS
1242 RTE_BYPASS_MODE_NONE,
1243 RTE_BYPASS_MODE_NORMAL,
1244 RTE_BYPASS_MODE_BYPASS,
1245 RTE_BYPASS_MODE_ISOLATE,
1246 RTE_BYPASS_MODE_NUM,
1249 #define RTE_BYPASS_MODE_VALID(x) \
1250 ((x) > RTE_BYPASS_MODE_NONE && (x) < RTE_BYPASS_MODE_NUM)
1253 RTE_BYPASS_EVENT_NONE,
1254 RTE_BYPASS_EVENT_START,
1255 RTE_BYPASS_EVENT_OS_ON = RTE_BYPASS_EVENT_START,
1256 RTE_BYPASS_EVENT_POWER_ON,
1257 RTE_BYPASS_EVENT_OS_OFF,
1258 RTE_BYPASS_EVENT_POWER_OFF,
1259 RTE_BYPASS_EVENT_TIMEOUT,
1260 RTE_BYPASS_EVENT_NUM
1263 #define RTE_BYPASS_EVENT_VALID(x) \
1264 ((x) > RTE_BYPASS_EVENT_NONE && (x) < RTE_BYPASS_MODE_NUM)
1267 RTE_BYPASS_TMT_OFF, /* timeout disabled. */
1268 RTE_BYPASS_TMT_1_5_SEC, /* timeout for 1.5 seconds */
1269 RTE_BYPASS_TMT_2_SEC, /* timeout for 2 seconds */
1270 RTE_BYPASS_TMT_3_SEC, /* timeout for 3 seconds */
1271 RTE_BYPASS_TMT_4_SEC, /* timeout for 4 seconds */
1272 RTE_BYPASS_TMT_8_SEC, /* timeout for 8 seconds */
1273 RTE_BYPASS_TMT_16_SEC, /* timeout for 16 seconds */
1274 RTE_BYPASS_TMT_32_SEC, /* timeout for 32 seconds */
1278 #define RTE_BYPASS_TMT_VALID(x) \
1279 ((x) == RTE_BYPASS_TMT_OFF || \
1280 ((x) > RTE_BYPASS_TMT_OFF && (x) < RTE_BYPASS_TMT_NUM))
1282 typedef void (*bypass_init_t)(struct rte_eth_dev *dev);
1283 typedef int32_t (*bypass_state_set_t)(struct rte_eth_dev *dev, uint32_t *new_state);
1284 typedef int32_t (*bypass_state_show_t)(struct rte_eth_dev *dev, uint32_t *state);
1285 typedef int32_t (*bypass_event_set_t)(struct rte_eth_dev *dev, uint32_t state, uint32_t event);
1286 typedef int32_t (*bypass_event_show_t)(struct rte_eth_dev *dev, uint32_t event_shift, uint32_t *event);
1287 typedef int32_t (*bypass_wd_timeout_set_t)(struct rte_eth_dev *dev, uint32_t timeout);
1288 typedef int32_t (*bypass_wd_timeout_show_t)(struct rte_eth_dev *dev, uint32_t *wd_timeout);
1289 typedef int32_t (*bypass_ver_show_t)(struct rte_eth_dev *dev, uint32_t *ver);
1290 typedef int32_t (*bypass_wd_reset_t)(struct rte_eth_dev *dev);
1293 typedef int (*eth_add_syn_filter_t)(struct rte_eth_dev *dev,
1294 struct rte_syn_filter *filter, uint16_t rx_queue);
1295 /**< @internal add syn filter rule on an Ethernet device */
1297 typedef int (*eth_remove_syn_filter_t)(struct rte_eth_dev *dev);
1298 /**< @internal remove syn filter rule on an Ethernet device */
1300 typedef int (*eth_get_syn_filter_t)(struct rte_eth_dev *dev,
1301 struct rte_syn_filter *filter, uint16_t *rx_queue);
1302 /**< @internal Get syn filter rule on an Ethernet device */
1304 typedef int (*eth_add_ethertype_filter_t)(struct rte_eth_dev *dev,
1305 uint16_t index, struct rte_ethertype_filter *filter,
1307 /**< @internal Setup a new ethertype filter rule on an Ethernet device */
1309 typedef int (*eth_remove_ethertype_filter_t)(struct rte_eth_dev *dev,
1311 /**< @internal Remove an ethertype filter rule on an Ethernet device */
1313 typedef int (*eth_get_ethertype_filter_t)(struct rte_eth_dev *dev,
1314 uint16_t index, struct rte_ethertype_filter *filter,
1315 uint16_t *rx_queue);
1316 /**< @internal Get an ethertype filter rule on an Ethernet device */
1318 typedef int (*eth_add_2tuple_filter_t)(struct rte_eth_dev *dev,
1319 uint16_t index, struct rte_2tuple_filter *filter,
1321 /**< @internal Setup a new 2tuple filter rule on an Ethernet device */
1323 typedef int (*eth_remove_2tuple_filter_t)(struct rte_eth_dev *dev,
1325 /**< @internal Remove a 2tuple filter rule on an Ethernet device */
1327 typedef int (*eth_get_2tuple_filter_t)(struct rte_eth_dev *dev,
1328 uint16_t index, struct rte_2tuple_filter *filter,
1329 uint16_t *rx_queue);
1330 /**< @internal Get a 2tuple filter rule on an Ethernet device */
1332 typedef int (*eth_add_5tuple_filter_t)(struct rte_eth_dev *dev,
1333 uint16_t index, struct rte_5tuple_filter *filter,
1335 /**< @internal Setup a new 5tuple filter rule on an Ethernet device */
1337 typedef int (*eth_remove_5tuple_filter_t)(struct rte_eth_dev *dev,
1339 /**< @internal Remove a 5tuple filter rule on an Ethernet device */
1341 typedef int (*eth_get_5tuple_filter_t)(struct rte_eth_dev *dev,
1342 uint16_t index, struct rte_5tuple_filter *filter,
1343 uint16_t *rx_queue);
1344 /**< @internal Get a 5tuple filter rule on an Ethernet device */
1346 typedef int (*eth_add_flex_filter_t)(struct rte_eth_dev *dev,
1347 uint16_t index, struct rte_flex_filter *filter,
1349 /**< @internal Setup a new flex filter rule on an Ethernet device */
1351 typedef int (*eth_remove_flex_filter_t)(struct rte_eth_dev *dev,
1353 /**< @internal Remove a flex filter rule on an Ethernet device */
1355 typedef int (*eth_get_flex_filter_t)(struct rte_eth_dev *dev,
1356 uint16_t index, struct rte_flex_filter *filter,
1357 uint16_t *rx_queue);
1358 /**< @internal Get a flex filter rule on an Ethernet device */
1361 * @internal A structure containing the functions exported by an Ethernet driver.
1363 struct eth_dev_ops {
1364 eth_dev_configure_t dev_configure; /**< Configure device. */
1365 eth_dev_start_t dev_start; /**< Start device. */
1366 eth_dev_stop_t dev_stop; /**< Stop device. */
1367 eth_dev_set_link_up_t dev_set_link_up; /**< Device link up. */
1368 eth_dev_set_link_down_t dev_set_link_down; /**< Device link down. */
1369 eth_dev_close_t dev_close; /**< Close device. */
1370 eth_promiscuous_enable_t promiscuous_enable; /**< Promiscuous ON. */
1371 eth_promiscuous_disable_t promiscuous_disable;/**< Promiscuous OFF. */
1372 eth_allmulticast_enable_t allmulticast_enable;/**< RX multicast ON. */
1373 eth_allmulticast_disable_t allmulticast_disable;/**< RX multicast OF. */
1374 eth_link_update_t link_update; /**< Get device link state. */
1375 eth_stats_get_t stats_get; /**< Get device statistics. */
1376 eth_stats_reset_t stats_reset; /**< Reset device statistics. */
1377 eth_queue_stats_mapping_set_t queue_stats_mapping_set;
1378 /**< Configure per queue stat counter mapping. */
1379 eth_dev_infos_get_t dev_infos_get; /**< Get device info. */
1380 vlan_filter_set_t vlan_filter_set; /**< Filter VLAN Setup. */
1381 vlan_tpid_set_t vlan_tpid_set; /**< Outer VLAN TPID Setup. */
1382 vlan_strip_queue_set_t vlan_strip_queue_set; /**< VLAN Stripping on queue. */
1383 vlan_offload_set_t vlan_offload_set; /**< Set VLAN Offload. */
1384 vlan_pvid_set_t vlan_pvid_set; /**< Set port based TX VLAN insertion */
1385 eth_queue_start_t rx_queue_start;/**< Start RX for a queue.*/
1386 eth_queue_stop_t rx_queue_stop;/**< Stop RX for a queue.*/
1387 eth_queue_start_t tx_queue_start;/**< Start TX for a queue.*/
1388 eth_queue_stop_t tx_queue_stop;/**< Stop TX for a queue.*/
1389 eth_rx_queue_setup_t rx_queue_setup;/**< Set up device RX queue.*/
1390 eth_queue_release_t rx_queue_release;/**< Release RX queue.*/
1391 eth_rx_queue_count_t rx_queue_count; /**< Get Rx queue count. */
1392 eth_rx_descriptor_done_t rx_descriptor_done; /**< Check rxd DD bit */
1393 eth_tx_queue_setup_t tx_queue_setup;/**< Set up device TX queue.*/
1394 eth_queue_release_t tx_queue_release;/**< Release TX queue.*/
1395 eth_dev_led_on_t dev_led_on; /**< Turn on LED. */
1396 eth_dev_led_off_t dev_led_off; /**< Turn off LED. */
1397 flow_ctrl_get_t flow_ctrl_get; /**< Get flow control. */
1398 flow_ctrl_set_t flow_ctrl_set; /**< Setup flow control. */
1399 priority_flow_ctrl_set_t priority_flow_ctrl_set; /**< Setup priority flow control.*/
1400 eth_mac_addr_remove_t mac_addr_remove; /**< Remove MAC address */
1401 eth_mac_addr_add_t mac_addr_add; /**< Add a MAC address */
1402 eth_uc_hash_table_set_t uc_hash_table_set; /**< Set Unicast Table Array */
1403 eth_uc_all_hash_table_set_t uc_all_hash_table_set; /**< Set Unicast hash bitmap */
1404 eth_mirror_rule_set_t mirror_rule_set; /**< Add a traffic mirror rule.*/
1405 eth_mirror_rule_reset_t mirror_rule_reset; /**< reset a traffic mirror rule.*/
1406 eth_set_vf_rx_mode_t set_vf_rx_mode; /**< Set VF RX mode */
1407 eth_set_vf_rx_t set_vf_rx; /**< enable/disable a VF receive */
1408 eth_set_vf_tx_t set_vf_tx; /**< enable/disable a VF transmit */
1409 eth_set_vf_vlan_filter_t set_vf_vlan_filter; /**< Set VF VLAN filter */
1410 eth_set_queue_rate_limit_t set_queue_rate_limit; /**< Set queue rate limit */
1411 eth_set_vf_rate_limit_t set_vf_rate_limit; /**< Set VF rate limit */
1413 /** Add a signature filter. */
1414 fdir_add_signature_filter_t fdir_add_signature_filter;
1415 /** Update a signature filter. */
1416 fdir_update_signature_filter_t fdir_update_signature_filter;
1417 /** Remove a signature filter. */
1418 fdir_remove_signature_filter_t fdir_remove_signature_filter;
1419 /** Get information about FDIR status. */
1420 fdir_infos_get_t fdir_infos_get;
1421 /** Add a perfect filter. */
1422 fdir_add_perfect_filter_t fdir_add_perfect_filter;
1423 /** Update a perfect filter. */
1424 fdir_update_perfect_filter_t fdir_update_perfect_filter;
1425 /** Remove a perfect filter. */
1426 fdir_remove_perfect_filter_t fdir_remove_perfect_filter;
1427 /** Setup masks for FDIR filtering. */
1428 fdir_set_masks_t fdir_set_masks;
1429 /** Update redirection table. */
1430 reta_update_t reta_update;
1431 /** Query redirection table. */
1432 reta_query_t reta_query;
1433 /* bypass control */
1434 #ifdef RTE_NIC_BYPASS
1435 bypass_init_t bypass_init;
1436 bypass_state_set_t bypass_state_set;
1437 bypass_state_show_t bypass_state_show;
1438 bypass_event_set_t bypass_event_set;
1439 bypass_event_show_t bypass_event_show;
1440 bypass_wd_timeout_set_t bypass_wd_timeout_set;
1441 bypass_wd_timeout_show_t bypass_wd_timeout_show;
1442 bypass_ver_show_t bypass_ver_show;
1443 bypass_wd_reset_t bypass_wd_reset;
1446 /** Configure RSS hash protocols. */
1447 rss_hash_update_t rss_hash_update;
1448 /** Get current RSS hash configuration. */
1449 rss_hash_conf_get_t rss_hash_conf_get;
1450 eth_add_syn_filter_t add_syn_filter; /**< add syn filter. */
1451 eth_remove_syn_filter_t remove_syn_filter; /**< remove syn filter. */
1452 eth_get_syn_filter_t get_syn_filter; /**< get syn filter. */
1453 eth_add_ethertype_filter_t add_ethertype_filter; /**< add ethertype filter. */
1454 eth_remove_ethertype_filter_t remove_ethertype_filter; /**< remove ethertype filter. */
1455 eth_get_ethertype_filter_t get_ethertype_filter; /**< get ethertype filter. */
1456 eth_add_2tuple_filter_t add_2tuple_filter; /**< add 2tuple filter. */
1457 eth_remove_2tuple_filter_t remove_2tuple_filter; /**< remove 2tuple filter. */
1458 eth_get_2tuple_filter_t get_2tuple_filter; /**< get 2tuple filter. */
1459 eth_add_5tuple_filter_t add_5tuple_filter; /**< add 5tuple filter. */
1460 eth_remove_5tuple_filter_t remove_5tuple_filter; /**< remove 5tuple filter. */
1461 eth_get_5tuple_filter_t get_5tuple_filter; /**< get 5tuple filter. */
1462 eth_add_flex_filter_t add_flex_filter; /**< add flex filter. */
1463 eth_remove_flex_filter_t remove_flex_filter; /**< remove flex filter. */
1464 eth_get_flex_filter_t get_flex_filter; /**< get flex filter. */
1469 * The generic data structure associated with each ethernet device.
1471 * Pointers to burst-oriented packet receive and transmit functions are
1472 * located at the beginning of the structure, along with the pointer to
1473 * where all the data elements for the particular device are stored in shared
1474 * memory. This split allows the function pointer and driver data to be per-
1475 * process, while the actual configuration data for the device is shared.
1477 struct rte_eth_dev {
1478 eth_rx_burst_t rx_pkt_burst; /**< Pointer to PMD receive function. */
1479 eth_tx_burst_t tx_pkt_burst; /**< Pointer to PMD transmit function. */
1480 struct rte_eth_dev_data *data; /**< Pointer to device data */
1481 const struct eth_driver *driver;/**< Driver for this device */
1482 struct eth_dev_ops *dev_ops; /**< Functions exported by PMD */
1483 struct rte_pci_device *pci_dev; /**< PCI info. supplied by probing */
1484 struct rte_eth_dev_cb_list callbacks; /**< User application callbacks */
1487 struct rte_eth_dev_sriov {
1488 uint8_t active; /**< SRIOV is active with 16, 32 or 64 pools */
1489 uint8_t nb_q_per_pool; /**< rx queue number per pool */
1490 uint16_t def_vmdq_idx; /**< Default pool num used for PF */
1491 uint16_t def_pool_q_idx; /**< Default pool queue start reg index */
1493 #define RTE_ETH_DEV_SRIOV(dev) ((dev)->data->sriov)
1497 * The data part, with no function pointers, associated with each ethernet device.
1499 * This structure is safe to place in shared memory to be common among different
1500 * processes in a multi-process configuration.
1502 struct rte_eth_dev_data {
1503 void **rx_queues; /**< Array of pointers to RX queues. */
1504 void **tx_queues; /**< Array of pointers to TX queues. */
1505 uint16_t nb_rx_queues; /**< Number of RX queues. */
1506 uint16_t nb_tx_queues; /**< Number of TX queues. */
1508 struct rte_eth_dev_sriov sriov; /**< SRIOV data */
1510 void *dev_private; /**< PMD-specific private data */
1512 struct rte_eth_link dev_link;
1513 /**< Link-level information & status */
1515 struct rte_eth_conf dev_conf; /**< Configuration applied to device. */
1516 uint16_t max_frame_size; /**< Default is ETHER_MAX_LEN (1518). */
1518 uint32_t min_rx_buf_size;
1519 /**< Common rx buffer size handled by all queues */
1521 uint64_t rx_mbuf_alloc_failed; /**< RX ring mbuf allocation failures. */
1522 struct ether_addr* mac_addrs;/**< Device Ethernet Link address. */
1523 uint64_t mac_pool_sel[ETH_NUM_RECEIVE_MAC_ADDR];
1524 /** bitmap array of associating Ethernet MAC addresses to pools */
1525 struct ether_addr* hash_mac_addrs;
1526 /** Device Ethernet MAC addresses of hash filtering. */
1527 uint8_t port_id; /**< Device [external] port identifier. */
1528 uint8_t promiscuous : 1, /**< RX promiscuous mode ON(1) / OFF(0). */
1529 scattered_rx : 1, /**< RX of scattered packets is ON(1) / OFF(0) */
1530 all_multicast : 1, /**< RX all multicast mode ON(1) / OFF(0). */
1531 dev_started : 1; /**< Device state: STARTED(1) / STOPPED(0). */
1536 * The pool of *rte_eth_dev* structures. The size of the pool
1537 * is configured at compile-time in the <rte_ethdev.c> file.
1539 extern struct rte_eth_dev rte_eth_devices[];
1542 * Get the total number of Ethernet devices that have been successfully
1543 * initialized by the [matching] Ethernet driver during the PCI probing phase.
1544 * All devices whose port identifier is in the range
1545 * [0, rte_eth_dev_count() - 1] can be operated on by network applications.
1548 * - The total number of usable Ethernet devices.
1550 extern uint8_t rte_eth_dev_count(void);
1553 * Function for internal use by dummy drivers primarily, e.g. ring-based
1555 * Allocates a new ethdev slot for an ethernet device and returns the pointer
1556 * to that slot for the driver to use.
1559 * - Slot in the rte_dev_devices array for a new device;
1561 struct rte_eth_dev *rte_eth_dev_allocate(void);
1566 * Initialization function of an Ethernet driver invoked for each matching
1567 * Ethernet PCI device detected during the PCI probing phase.
1570 * The pointer to the [matching] Ethernet driver structure supplied by
1571 * the PMD when it registered itself.
1573 * The *eth_dev* pointer is the address of the *rte_eth_dev* structure
1574 * associated with the matching device and which have been [automatically]
1575 * allocated in the *rte_eth_devices* array.
1576 * The *eth_dev* structure is supplied to the driver initialization function
1577 * with the following fields already initialized:
1579 * - *pci_dev*: Holds the pointers to the *rte_pci_device* structure which
1580 * contains the generic PCI information of the matching device.
1582 * - *dev_private*: Holds a pointer to the device private data structure.
1584 * - *max_frame_size*: Contains the default Ethernet maximum frame length
1587 * - *port_id*: Contains the port index of the device (actually the index
1588 * of the *eth_dev* structure in the *rte_eth_devices* array).
1591 * - 0: Success, the device is properly initialized by the driver.
1592 * In particular, the driver MUST have set up the *dev_ops* pointer
1593 * of the *eth_dev* structure.
1594 * - <0: Error code of the device initialization failure.
1596 typedef int (*eth_dev_init_t)(struct eth_driver *eth_drv,
1597 struct rte_eth_dev *eth_dev);
1601 * The structure associated with a PMD Ethernet driver.
1603 * Each Ethernet driver acts as a PCI driver and is represented by a generic
1604 * *eth_driver* structure that holds:
1606 * - An *rte_pci_driver* structure (which must be the first field).
1608 * - The *eth_dev_init* function invoked for each matching PCI device.
1610 * - The size of the private data to allocate for each matching device.
1613 struct rte_pci_driver pci_drv; /**< The PMD is also a PCI driver. */
1614 eth_dev_init_t eth_dev_init; /**< Device init function. */
1615 unsigned int dev_private_size; /**< Size of device private data. */
1620 * A function invoked by the initialization function of an Ethernet driver
1621 * to simultaneously register itself as a PCI driver and as an Ethernet
1622 * Poll Mode Driver (PMD).
1625 * The pointer to the *eth_driver* structure associated with
1626 * the Ethernet driver.
1628 extern void rte_eth_driver_register(struct eth_driver *eth_drv);
1631 * Configure an Ethernet device.
1632 * This function must be invoked first before any other function in the
1633 * Ethernet API. This function can also be re-invoked when a device is in the
1637 * The port identifier of the Ethernet device to configure.
1638 * @param nb_rx_queue
1639 * The number of receive queues to set up for the Ethernet device.
1640 * @param nb_tx_queue
1641 * The number of transmit queues to set up for the Ethernet device.
1643 * The pointer to the configuration data to be used for the Ethernet device.
1644 * The *rte_eth_conf* structure includes:
1645 * - the hardware offload features to activate, with dedicated fields for
1646 * each statically configurable offload hardware feature provided by
1647 * Ethernet devices, such as IP checksum or VLAN tag stripping for
1649 * - the Receive Side Scaling (RSS) configuration when using multiple RX
1652 * Embedding all configuration information in a single data structure
1653 * is the more flexible method that allows the addition of new features
1654 * without changing the syntax of the API.
1656 * - 0: Success, device configured.
1657 * - <0: Error code returned by the driver configuration function.
1659 extern int rte_eth_dev_configure(uint8_t port_id,
1660 uint16_t nb_rx_queue,
1661 uint16_t nb_tx_queue,
1662 const struct rte_eth_conf *eth_conf);
1665 * Allocate and set up a receive queue for an Ethernet device.
1667 * The function allocates a contiguous block of memory for *nb_rx_desc*
1668 * receive descriptors from a memory zone associated with *socket_id*
1669 * and initializes each receive descriptor with a network buffer allocated
1670 * from the memory pool *mb_pool*.
1673 * The port identifier of the Ethernet device.
1674 * @param rx_queue_id
1675 * The index of the receive queue to set up.
1676 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1677 * to rte_eth_dev_configure().
1679 * The number of receive descriptors to allocate for the receive ring.
1681 * The *socket_id* argument is the socket identifier in case of NUMA.
1682 * The value can be *SOCKET_ID_ANY* if there is no NUMA constraint for
1683 * the DMA memory allocated for the receive descriptors of the ring.
1685 * The pointer to the configuration data to be used for the receive queue.
1686 * The *rx_conf* structure contains an *rx_thresh* structure with the values
1687 * of the Prefetch, Host, and Write-Back threshold registers of the receive
1690 * The pointer to the memory pool from which to allocate *rte_mbuf* network
1691 * memory buffers to populate each descriptor of the receive ring.
1693 * - 0: Success, receive queue correctly set up.
1694 * - -EINVAL: The size of network buffers which can be allocated from the
1695 * memory pool does not fit the various buffer sizes allowed by the
1696 * device controller.
1697 * - -ENOMEM: Unable to allocate the receive ring descriptors or to
1698 * allocate network memory buffers from the memory pool when
1699 * initializing receive descriptors.
1701 extern int rte_eth_rx_queue_setup(uint8_t port_id, uint16_t rx_queue_id,
1702 uint16_t nb_rx_desc, unsigned int socket_id,
1703 const struct rte_eth_rxconf *rx_conf,
1704 struct rte_mempool *mb_pool);
1707 * Allocate and set up a transmit queue for an Ethernet device.
1710 * The port identifier of the Ethernet device.
1711 * @param tx_queue_id
1712 * The index of the transmit queue to set up.
1713 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1714 * to rte_eth_dev_configure().
1716 * The number of transmit descriptors to allocate for the transmit ring.
1718 * The *socket_id* argument is the socket identifier in case of NUMA.
1719 * Its value can be *SOCKET_ID_ANY* if there is no NUMA constraint for
1720 * the DMA memory allocated for the transmit descriptors of the ring.
1722 * The pointer to the configuration data to be used for the transmit queue.
1723 * The *tx_conf* structure contains the following data:
1724 * - The *tx_thresh* structure with the values of the Prefetch, Host, and
1725 * Write-Back threshold registers of the transmit ring.
1726 * When setting Write-Back threshold to the value greater then zero,
1727 * *tx_rs_thresh* value should be explicitly set to one.
1728 * - The *tx_free_thresh* value indicates the [minimum] number of network
1729 * buffers that must be pending in the transmit ring to trigger their
1730 * [implicit] freeing by the driver transmit function.
1731 * - The *tx_rs_thresh* value indicates the [minimum] number of transmit
1732 * descriptors that must be pending in the transmit ring before setting the
1733 * RS bit on a descriptor by the driver transmit function.
1734 * The *tx_rs_thresh* value should be less or equal then
1735 * *tx_free_thresh* value, and both of them should be less then
1737 * - The *txq_flags* member contains flags to pass to the TX queue setup
1738 * function to configure the behavior of the TX queue. This should be set
1739 * to 0 if no special configuration is required.
1741 * Note that setting *tx_free_thresh* or *tx_rs_thresh* value to 0 forces
1742 * the transmit function to use default values.
1744 * - 0: Success, the transmit queue is correctly set up.
1745 * - -ENOMEM: Unable to allocate the transmit ring descriptors.
1747 extern int rte_eth_tx_queue_setup(uint8_t port_id, uint16_t tx_queue_id,
1748 uint16_t nb_tx_desc, unsigned int socket_id,
1749 const struct rte_eth_txconf *tx_conf);
1752 * Return the NUMA socket to which an Ethernet device is connected
1755 * The port identifier of the Ethernet device
1757 * The NUMA socket id to which the Ethernet device is connected or
1758 * a default of zero if the socket could not be determined.
1759 * -1 is returned is the port_id value is out of range.
1761 extern int rte_eth_dev_socket_id(uint8_t port_id);
1764 * Start specified RX queue of a port
1767 * The port identifier of the Ethernet device
1768 * @param rx_queue_id
1769 * The index of the rx queue to update the ring.
1770 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1771 * to rte_eth_dev_configure().
1773 * - 0: Success, the transmit queue is correctly set up.
1774 * - -EINVAL: The port_id or the queue_id out of range.
1775 * - -ENOTSUP: The function not supported in PMD driver.
1777 extern int rte_eth_dev_rx_queue_start(uint8_t port_id, uint16_t rx_queue_id);
1780 * Stop specified RX queue of a port
1783 * The port identifier of the Ethernet device
1784 * @param rx_queue_id
1785 * The index of the rx queue to update the ring.
1786 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
1787 * to rte_eth_dev_configure().
1789 * - 0: Success, the transmit queue is correctly set up.
1790 * - -EINVAL: The port_id or the queue_id out of range.
1791 * - -ENOTSUP: The function not supported in PMD driver.
1793 extern int rte_eth_dev_rx_queue_stop(uint8_t port_id, uint16_t rx_queue_id);
1796 * Start specified TX queue of a port
1799 * The port identifier of the Ethernet device
1800 * @param tx_queue_id
1801 * The index of the tx queue to update the ring.
1802 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1803 * to rte_eth_dev_configure().
1805 * - 0: Success, the transmit queue is correctly set up.
1806 * - -EINVAL: The port_id or the queue_id out of range.
1807 * - -ENOTSUP: The function not supported in PMD driver.
1809 extern int rte_eth_dev_tx_queue_start(uint8_t port_id, uint16_t tx_queue_id);
1812 * Stop specified TX queue of a port
1815 * The port identifier of the Ethernet device
1816 * @param tx_queue_id
1817 * The index of the tx queue to update the ring.
1818 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
1819 * to rte_eth_dev_configure().
1821 * - 0: Success, the transmit queue is correctly set up.
1822 * - -EINVAL: The port_id or the queue_id out of range.
1823 * - -ENOTSUP: The function not supported in PMD driver.
1825 extern int rte_eth_dev_tx_queue_stop(uint8_t port_id, uint16_t tx_queue_id);
1830 * Start an Ethernet device.
1832 * The device start step is the last one and consists of setting the configured
1833 * offload features and in starting the transmit and the receive units of the
1835 * On success, all basic functions exported by the Ethernet API (link status,
1836 * receive/transmit, and so on) can be invoked.
1839 * The port identifier of the Ethernet device.
1841 * - 0: Success, Ethernet device started.
1842 * - <0: Error code of the driver device start function.
1844 extern int rte_eth_dev_start(uint8_t port_id);
1847 * Stop an Ethernet device. The device can be restarted with a call to
1848 * rte_eth_dev_start()
1851 * The port identifier of the Ethernet device.
1853 extern void rte_eth_dev_stop(uint8_t port_id);
1857 * Link up an Ethernet device.
1859 * Set device link up will re-enable the device rx/tx
1860 * functionality after it is previously set device linked down.
1863 * The port identifier of the Ethernet device.
1865 * - 0: Success, Ethernet device linked up.
1866 * - <0: Error code of the driver device link up function.
1868 extern int rte_eth_dev_set_link_up(uint8_t port_id);
1871 * Link down an Ethernet device.
1872 * The device rx/tx functionality will be disabled if success,
1873 * and it can be re-enabled with a call to
1874 * rte_eth_dev_set_link_up()
1877 * The port identifier of the Ethernet device.
1879 extern int rte_eth_dev_set_link_down(uint8_t port_id);
1882 * Close an Ethernet device. The device cannot be restarted!
1885 * The port identifier of the Ethernet device.
1887 extern void rte_eth_dev_close(uint8_t port_id);
1890 * Enable receipt in promiscuous mode for an Ethernet device.
1893 * The port identifier of the Ethernet device.
1895 extern void rte_eth_promiscuous_enable(uint8_t port_id);
1898 * Disable receipt in promiscuous mode for an Ethernet device.
1901 * The port identifier of the Ethernet device.
1903 extern void rte_eth_promiscuous_disable(uint8_t port_id);
1906 * Return the value of promiscuous mode for an Ethernet device.
1909 * The port identifier of the Ethernet device.
1911 * - (1) if promiscuous is enabled
1912 * - (0) if promiscuous is disabled.
1915 extern int rte_eth_promiscuous_get(uint8_t port_id);
1918 * Enable the receipt of any multicast frame by an Ethernet device.
1921 * The port identifier of the Ethernet device.
1923 extern void rte_eth_allmulticast_enable(uint8_t port_id);
1926 * Disable the receipt of all multicast frames by an Ethernet device.
1929 * The port identifier of the Ethernet device.
1931 extern void rte_eth_allmulticast_disable(uint8_t port_id);
1934 * Return the value of allmulticast mode for an Ethernet device.
1937 * The port identifier of the Ethernet device.
1939 * - (1) if allmulticast is enabled
1940 * - (0) if allmulticast is disabled.
1943 extern int rte_eth_allmulticast_get(uint8_t port_id);
1946 * Retrieve the status (ON/OFF), the speed (in Mbps) and the mode (HALF-DUPLEX
1947 * or FULL-DUPLEX) of the physical link of an Ethernet device. It might need
1948 * to wait up to 9 seconds in it.
1951 * The port identifier of the Ethernet device.
1953 * A pointer to an *rte_eth_link* structure to be filled with
1954 * the status, the speed and the mode of the Ethernet device link.
1956 extern void rte_eth_link_get(uint8_t port_id, struct rte_eth_link *link);
1959 * Retrieve the status (ON/OFF), the speed (in Mbps) and the mode (HALF-DUPLEX
1960 * or FULL-DUPLEX) of the physical link of an Ethernet device. It is a no-wait
1961 * version of rte_eth_link_get().
1964 * The port identifier of the Ethernet device.
1966 * A pointer to an *rte_eth_link* structure to be filled with
1967 * the status, the speed and the mode of the Ethernet device link.
1969 extern void rte_eth_link_get_nowait(uint8_t port_id,
1970 struct rte_eth_link *link);
1973 * Retrieve the general I/O statistics of an Ethernet device.
1976 * The port identifier of the Ethernet device.
1978 * A pointer to a structure of type *rte_eth_stats* to be filled with
1979 * the values of device counters for the following set of statistics:
1980 * - *ipackets* with the total of successfully received packets.
1981 * - *opackets* with the total of successfully transmitted packets.
1982 * - *ibytes* with the total of successfully received bytes.
1983 * - *obytes* with the total of successfully transmitted bytes.
1984 * - *ierrors* with the total of erroneous received packets.
1985 * - *oerrors* with the total of failed transmitted packets.
1987 extern void rte_eth_stats_get(uint8_t port_id, struct rte_eth_stats *stats);
1990 * Reset the general I/O statistics of an Ethernet device.
1993 * The port identifier of the Ethernet device.
1995 extern void rte_eth_stats_reset(uint8_t port_id);
1998 * Set a mapping for the specified transmit queue to the specified per-queue
1999 * statistics counter.
2002 * The port identifier of the Ethernet device.
2003 * @param tx_queue_id
2004 * The index of the transmit queue for which a queue stats mapping is required.
2005 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
2006 * to rte_eth_dev_configure().
2008 * The per-queue packet statistics functionality number that the transmit
2009 * queue is to be assigned.
2010 * The value must be in the range [0, RTE_MAX_ETHPORT_QUEUE_STATS_MAPS - 1].
2012 * Zero if successful. Non-zero otherwise.
2014 extern int rte_eth_dev_set_tx_queue_stats_mapping(uint8_t port_id,
2015 uint16_t tx_queue_id,
2019 * Set a mapping for the specified receive queue to the specified per-queue
2020 * statistics counter.
2023 * The port identifier of the Ethernet device.
2024 * @param rx_queue_id
2025 * The index of the receive queue for which a queue stats mapping is required.
2026 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2027 * to rte_eth_dev_configure().
2029 * The per-queue packet statistics functionality number that the receive
2030 * queue is to be assigned.
2031 * The value must be in the range [0, RTE_MAX_ETHPORT_QUEUE_STATS_MAPS - 1].
2033 * Zero if successful. Non-zero otherwise.
2035 extern int rte_eth_dev_set_rx_queue_stats_mapping(uint8_t port_id,
2036 uint16_t rx_queue_id,
2040 * Retrieve the Ethernet address of an Ethernet device.
2043 * The port identifier of the Ethernet device.
2045 * A pointer to a structure of type *ether_addr* to be filled with
2046 * the Ethernet address of the Ethernet device.
2048 extern void rte_eth_macaddr_get(uint8_t port_id, struct ether_addr *mac_addr);
2051 * Retrieve the contextual information of an Ethernet device.
2054 * The port identifier of the Ethernet device.
2056 * A pointer to a structure of type *rte_eth_dev_info* to be filled with
2057 * the contextual information of the Ethernet device.
2059 extern void rte_eth_dev_info_get(uint8_t port_id,
2060 struct rte_eth_dev_info *dev_info);
2063 * Enable/Disable hardware filtering by an Ethernet device of received
2064 * VLAN packets tagged with a given VLAN Tag Identifier.
2067 * The port identifier of the Ethernet device.
2069 * The VLAN Tag Identifier whose filtering must be enabled or disabled.
2071 * If > 0, enable VLAN filtering of VLAN packets tagged with *vlan_id*.
2072 * Otherwise, disable VLAN filtering of VLAN packets tagged with *vlan_id*.
2074 * - (0) if successful.
2075 * - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
2076 * - (-ENODEV) if *port_id* invalid.
2077 * - (-ENOSYS) if VLAN filtering on *port_id* disabled.
2078 * - (-EINVAL) if *vlan_id* > 4095.
2080 extern int rte_eth_dev_vlan_filter(uint8_t port_id, uint16_t vlan_id , int on);
2083 * Enable/Disable hardware VLAN Strip by a rx queue of an Ethernet device.
2084 * 82599/X540 can support VLAN stripping at the rx queue level
2087 * The port identifier of the Ethernet device.
2088 * @param rx_queue_id
2089 * The index of the receive queue for which a queue stats mapping is required.
2090 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2091 * to rte_eth_dev_configure().
2093 * If 1, Enable VLAN Stripping of the receive queue of the Ethernet port.
2094 * If 0, Disable VLAN Stripping of the receive queue of the Ethernet port.
2096 * - (0) if successful.
2097 * - (-ENOSUP) if hardware-assisted VLAN stripping not configured.
2098 * - (-ENODEV) if *port_id* invalid.
2099 * - (-EINVAL) if *rx_queue_id* invalid.
2101 extern int rte_eth_dev_set_vlan_strip_on_queue(uint8_t port_id,
2102 uint16_t rx_queue_id, int on);
2105 * Set the Outer VLAN Ether Type by an Ethernet device, it can be inserted to
2106 * the VLAN Header. This is a register setup available on some Intel NIC, not
2107 * but all, please check the data sheet for availability.
2110 * The port identifier of the Ethernet device.
2112 * The Tag Protocol ID
2114 * - (0) if successful.
2115 * - (-ENOSUP) if hardware-assisted VLAN TPID setup is not supported.
2116 * - (-ENODEV) if *port_id* invalid.
2118 extern int rte_eth_dev_set_vlan_ether_type(uint8_t port_id, uint16_t tag_type);
2121 * Set VLAN offload configuration on an Ethernet device
2122 * Enable/Disable Extended VLAN by an Ethernet device, This is a register setup
2123 * available on some Intel NIC, not but all, please check the data sheet for
2125 * Enable/Disable VLAN Strip can be done on rx queue for certain NIC, but here
2126 * the configuration is applied on the port level.
2129 * The port identifier of the Ethernet device.
2130 * @param offload_mask
2131 * The VLAN Offload bit mask can be mixed use with "OR"
2132 * ETH_VLAN_STRIP_OFFLOAD
2133 * ETH_VLAN_FILTER_OFFLOAD
2134 * ETH_VLAN_EXTEND_OFFLOAD
2136 * - (0) if successful.
2137 * - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
2138 * - (-ENODEV) if *port_id* invalid.
2140 extern int rte_eth_dev_set_vlan_offload(uint8_t port_id, int offload_mask);
2143 * Read VLAN Offload configuration from an Ethernet device
2146 * The port identifier of the Ethernet device.
2148 * - (>0) if successful. Bit mask to indicate
2149 * ETH_VLAN_STRIP_OFFLOAD
2150 * ETH_VLAN_FILTER_OFFLOAD
2151 * ETH_VLAN_EXTEND_OFFLOAD
2152 * - (-ENODEV) if *port_id* invalid.
2154 extern int rte_eth_dev_get_vlan_offload(uint8_t port_id);
2157 * Set port based TX VLAN insersion on or off.
2160 * The port identifier of the Ethernet device.
2162 * Port based TX VLAN identifier togeth with user priority.
2164 * Turn on or off the port based TX VLAN insertion.
2167 * - (0) if successful.
2168 * - negative if failed.
2170 extern int rte_eth_dev_set_vlan_pvid(uint8_t port_id, uint16_t pvid, int on);
2174 * Retrieve a burst of input packets from a receive queue of an Ethernet
2175 * device. The retrieved packets are stored in *rte_mbuf* structures whose
2176 * pointers are supplied in the *rx_pkts* array.
2178 * The rte_eth_rx_burst() function loops, parsing the RX ring of the
2179 * receive queue, up to *nb_pkts* packets, and for each completed RX
2180 * descriptor in the ring, it performs the following operations:
2182 * - Initialize the *rte_mbuf* data structure associated with the
2183 * RX descriptor according to the information provided by the NIC into
2184 * that RX descriptor.
2186 * - Store the *rte_mbuf* data structure into the next entry of the
2189 * - Replenish the RX descriptor with a new *rte_mbuf* buffer
2190 * allocated from the memory pool associated with the receive queue at
2191 * initialization time.
2193 * When retrieving an input packet that was scattered by the controller
2194 * into multiple receive descriptors, the rte_eth_rx_burst() function
2195 * appends the associated *rte_mbuf* buffers to the first buffer of the
2198 * The rte_eth_rx_burst() function returns the number of packets
2199 * actually retrieved, which is the number of *rte_mbuf* data structures
2200 * effectively supplied into the *rx_pkts* array.
2201 * A return value equal to *nb_pkts* indicates that the RX queue contained
2202 * at least *rx_pkts* packets, and this is likely to signify that other
2203 * received packets remain in the input queue. Applications implementing
2204 * a "retrieve as much received packets as possible" policy can check this
2205 * specific case and keep invoking the rte_eth_rx_burst() function until
2206 * a value less than *nb_pkts* is returned.
2208 * This receive method has the following advantages:
2210 * - It allows a run-to-completion network stack engine to retrieve and
2211 * to immediately process received packets in a fast burst-oriented
2212 * approach, avoiding the overhead of unnecessary intermediate packet
2213 * queue/dequeue operations.
2215 * - Conversely, it also allows an asynchronous-oriented processing
2216 * method to retrieve bursts of received packets and to immediately
2217 * queue them for further parallel processing by another logical core,
2218 * for instance. However, instead of having received packets being
2219 * individually queued by the driver, this approach allows the invoker
2220 * of the rte_eth_rx_burst() function to queue a burst of retrieved
2221 * packets at a time and therefore dramatically reduce the cost of
2222 * enqueue/dequeue operations per packet.
2224 * - It allows the rte_eth_rx_burst() function of the driver to take
2225 * advantage of burst-oriented hardware features (CPU cache,
2226 * prefetch instructions, and so on) to minimize the number of CPU
2227 * cycles per packet.
2229 * To summarize, the proposed receive API enables many
2230 * burst-oriented optimizations in both synchronous and asynchronous
2231 * packet processing environments with no overhead in both cases.
2233 * The rte_eth_rx_burst() function does not provide any error
2234 * notification to avoid the corresponding overhead. As a hint, the
2235 * upper-level application might check the status of the device link once
2236 * being systematically returned a 0 value for a given number of tries.
2239 * The port identifier of the Ethernet device.
2241 * The index of the receive queue from which to retrieve input packets.
2242 * The value must be in the range [0, nb_rx_queue - 1] previously supplied
2243 * to rte_eth_dev_configure().
2245 * The address of an array of pointers to *rte_mbuf* structures that
2246 * must be large enough to store *nb_pkts* pointers in it.
2248 * The maximum number of packets to retrieve.
2250 * The number of packets actually retrieved, which is the number
2251 * of pointers to *rte_mbuf* structures effectively supplied to the
2254 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2255 extern uint16_t rte_eth_rx_burst(uint8_t port_id, uint16_t queue_id,
2256 struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
2258 static inline uint16_t
2259 rte_eth_rx_burst(uint8_t port_id, uint16_t queue_id,
2260 struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
2262 struct rte_eth_dev *dev;
2264 dev = &rte_eth_devices[port_id];
2265 return (*dev->rx_pkt_burst)(dev->data->rx_queues[queue_id], rx_pkts, nb_pkts);
2270 * Get the number of used descriptors in a specific queue
2273 * The port identifier of the Ethernet device.
2275 * The queue id on the specific port.
2277 * The number of used descriptors in the specific queue.
2279 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2280 extern uint32_t rte_eth_rx_queue_count(uint8_t port_id, uint16_t queue_id);
2282 static inline uint32_t
2283 rte_eth_rx_queue_count(uint8_t port_id, uint16_t queue_id)
2285 struct rte_eth_dev *dev;
2287 dev = &rte_eth_devices[port_id];
2288 return (*dev->dev_ops->rx_queue_count)(dev, queue_id);
2293 * Check if the DD bit of the specific RX descriptor in the queue has been set
2296 * The port identifier of the Ethernet device.
2298 * The queue id on the specific port.
2300 * The offset of the descriptor ID from tail.
2302 * - (1) if the specific DD bit is set.
2303 * - (0) if the specific DD bit is not set.
2304 * - (-ENODEV) if *port_id* invalid.
2306 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2307 extern int rte_eth_rx_descriptor_done(uint8_t port_id,
2312 rte_eth_rx_descriptor_done(uint8_t port_id, uint16_t queue_id, uint16_t offset)
2314 struct rte_eth_dev *dev;
2316 dev = &rte_eth_devices[port_id];
2317 return (*dev->dev_ops->rx_descriptor_done)( \
2318 dev->data->rx_queues[queue_id], offset);
2323 * Send a burst of output packets on a transmit queue of an Ethernet device.
2325 * The rte_eth_tx_burst() function is invoked to transmit output packets
2326 * on the output queue *queue_id* of the Ethernet device designated by its
2328 * The *nb_pkts* parameter is the number of packets to send which are
2329 * supplied in the *tx_pkts* array of *rte_mbuf* structures.
2330 * The rte_eth_tx_burst() function loops, sending *nb_pkts* packets,
2331 * up to the number of transmit descriptors available in the TX ring of the
2333 * For each packet to send, the rte_eth_tx_burst() function performs
2334 * the following operations:
2336 * - Pick up the next available descriptor in the transmit ring.
2338 * - Free the network buffer previously sent with that descriptor, if any.
2340 * - Initialize the transmit descriptor with the information provided
2341 * in the *rte_mbuf data structure.
2343 * In the case of a segmented packet composed of a list of *rte_mbuf* buffers,
2344 * the rte_eth_tx_burst() function uses several transmit descriptors
2347 * The rte_eth_tx_burst() function returns the number of packets it
2348 * actually sent. A return value equal to *nb_pkts* means that all packets
2349 * have been sent, and this is likely to signify that other output packets
2350 * could be immediately transmitted again. Applications that implement a
2351 * "send as many packets to transmit as possible" policy can check this
2352 * specific case and keep invoking the rte_eth_tx_burst() function until
2353 * a value less than *nb_pkts* is returned.
2355 * It is the responsibility of the rte_eth_tx_burst() function to
2356 * transparently free the memory buffers of packets previously sent.
2357 * This feature is driven by the *tx_free_thresh* value supplied to the
2358 * rte_eth_dev_configure() function at device configuration time.
2359 * When the number of previously sent packets reached the "minimum transmit
2360 * packets to free" threshold, the rte_eth_tx_burst() function must
2361 * [attempt to] free the *rte_mbuf* buffers of those packets whose
2362 * transmission was effectively completed.
2365 * The port identifier of the Ethernet device.
2367 * The index of the transmit queue through which output packets must be
2369 * The value must be in the range [0, nb_tx_queue - 1] previously supplied
2370 * to rte_eth_dev_configure().
2372 * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures
2373 * which contain the output packets.
2375 * The maximum number of packets to transmit.
2377 * The number of output packets actually stored in transmit descriptors of
2378 * the transmit ring. The return value can be less than the value of the
2379 * *tx_pkts* parameter when the transmit ring is full or has been filled up.
2381 #ifdef RTE_LIBRTE_ETHDEV_DEBUG
2382 extern uint16_t rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id,
2383 struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
2385 static inline uint16_t
2386 rte_eth_tx_burst(uint8_t port_id, uint16_t queue_id,
2387 struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
2389 struct rte_eth_dev *dev;
2391 dev = &rte_eth_devices[port_id];
2392 return (*dev->tx_pkt_burst)(dev->data->tx_queues[queue_id], tx_pkts, nb_pkts);
2397 * Setup a new signature filter rule on an Ethernet device
2400 * The port identifier of the Ethernet device.
2401 * @param fdir_filter
2402 * The pointer to the fdir filter structure describing the signature filter
2404 * The *rte_fdir_filter* structure includes the values of the different fields
2405 * to match: source and destination IP addresses, vlan id, flexbytes, source
2406 * and destination ports, and so on.
2408 * The index of the RX queue where to store RX packets matching the added
2409 * signature filter defined in fdir_filter.
2411 * - (0) if successful.
2412 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2413 * - (-ENODEV) if *port_id* invalid.
2414 * - (-ENOSYS) if the FDIR mode is not configured in signature mode
2416 * - (-EINVAL) if the fdir_filter information is not correct.
2418 int rte_eth_dev_fdir_add_signature_filter(uint8_t port_id,
2419 struct rte_fdir_filter *fdir_filter,
2423 * Update a signature filter rule on an Ethernet device.
2424 * If the rule doesn't exits, it is created.
2427 * The port identifier of the Ethernet device.
2429 * The pointer to the structure describing the signature filter rule.
2430 * The *rte_fdir_filter* structure includes the values of the different fields
2431 * to match: source and destination IP addresses, vlan id, flexbytes, source
2432 * and destination ports, and so on.
2434 * The index of the RX queue where to store RX packets matching the added
2435 * signature filter defined in fdir_ftr.
2437 * - (0) if successful.
2438 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2439 * - (-ENODEV) if *port_id* invalid.
2440 * - (-ENOSYS) if the flow director mode is not configured in signature mode
2442 * - (-EINVAL) if the fdir_filter information is not correct.
2444 int rte_eth_dev_fdir_update_signature_filter(uint8_t port_id,
2445 struct rte_fdir_filter *fdir_ftr,
2449 * Remove a signature filter rule on an Ethernet device.
2452 * The port identifier of the Ethernet device.
2454 * The pointer to the structure describing the signature filter rule.
2455 * The *rte_fdir_filter* structure includes the values of the different fields
2456 * to match: source and destination IP addresses, vlan id, flexbytes, source
2457 * and destination ports, and so on.
2459 * - (0) if successful.
2460 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2461 * - (-ENODEV) if *port_id* invalid.
2462 * - (-ENOSYS) if the flow director mode is not configured in signature mode
2464 * - (-EINVAL) if the fdir_filter information is not correct.
2466 int rte_eth_dev_fdir_remove_signature_filter(uint8_t port_id,
2467 struct rte_fdir_filter *fdir_ftr);
2470 * Retrieve the flow director information of an Ethernet device.
2473 * The port identifier of the Ethernet device.
2475 * A pointer to a structure of type *rte_eth_dev_fdir* to be filled with
2476 * the flow director information of the Ethernet device.
2478 * - (0) if successful.
2479 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2480 * - (-ENODEV) if *port_id* invalid.
2481 * - (-ENOSYS) if the flow director mode is not configured on *port_id*.
2483 int rte_eth_dev_fdir_get_infos(uint8_t port_id, struct rte_eth_fdir *fdir);
2486 * Add a new perfect filter rule on an Ethernet device.
2489 * The port identifier of the Ethernet device.
2490 * @param fdir_filter
2491 * The pointer to the structure describing the perfect filter rule.
2492 * The *rte_fdir_filter* structure includes the values of the different fields
2493 * to match: source and destination IP addresses, vlan id, flexbytes, source
2494 * and destination ports, and so on.
2495 * IPv6 are not supported.
2497 * The 16-bit value supplied in the field hash.fdir.id of mbuf for RX
2498 * packets matching the perfect filter.
2500 * The index of the RX queue where to store RX packets matching the added
2501 * perfect filter defined in fdir_filter.
2503 * If drop is set to 1, matching RX packets are stored into the RX drop
2504 * queue defined in the rte_fdir_conf.
2506 * - (0) if successful.
2507 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2508 * - (-ENODEV) if *port_id* invalid.
2509 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2511 * - (-EINVAL) if the fdir_filter information is not correct.
2513 int rte_eth_dev_fdir_add_perfect_filter(uint8_t port_id,
2514 struct rte_fdir_filter *fdir_filter,
2515 uint16_t soft_id, uint8_t rx_queue,
2519 * Update a perfect filter rule on an Ethernet device.
2520 * If the rule doesn't exits, it is created.
2523 * The port identifier of the Ethernet device.
2524 * @param fdir_filter
2525 * The pointer to the structure describing the perfect filter rule.
2526 * The *rte_fdir_filter* structure includes the values of the different fields
2527 * to match: source and destination IP addresses, vlan id, flexbytes, source
2528 * and destination ports, and so on.
2529 * IPv6 are not supported.
2531 * The 16-bit value supplied in the field hash.fdir.id of mbuf for RX
2532 * packets matching the perfect filter.
2534 * The index of the RX queue where to store RX packets matching the added
2535 * perfect filter defined in fdir_filter.
2537 * If drop is set to 1, matching RX packets are stored into the RX drop
2538 * queue defined in the rte_fdir_conf.
2540 * - (0) if successful.
2541 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2542 * - (-ENODEV) if *port_id* invalid.
2543 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2545 * - (-EINVAL) if the fdir_filter information is not correct.
2547 int rte_eth_dev_fdir_update_perfect_filter(uint8_t port_id,
2548 struct rte_fdir_filter *fdir_filter,
2549 uint16_t soft_id, uint8_t rx_queue,
2553 * Remove a perfect filter rule on an Ethernet device.
2556 * The port identifier of the Ethernet device.
2557 * @param fdir_filter
2558 * The pointer to the structure describing the perfect filter rule.
2559 * The *rte_fdir_filter* structure includes the values of the different fields
2560 * to match: source and destination IP addresses, vlan id, flexbytes, source
2561 * and destination ports, and so on.
2562 * IPv6 are not supported.
2564 * The soft_id value provided when adding/updating the removed filter.
2566 * - (0) if successful.
2567 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2568 * - (-ENODEV) if *port_id* invalid.
2569 * - (-ENOSYS) if the flow director mode is not configured in perfect mode
2571 * - (-EINVAL) if the fdir_filter information is not correct.
2573 int rte_eth_dev_fdir_remove_perfect_filter(uint8_t port_id,
2574 struct rte_fdir_filter *fdir_filter,
2577 * Configure globally the masks for flow director mode for an Ethernet device.
2578 * For example, the device can match packets with only the first 24 bits of
2579 * the IPv4 source address.
2581 * The following fields can be masked: IPv4 addresses and L4 port numbers.
2582 * The following fields can be either enabled or disabled completely for the
2583 * matching functionality: VLAN ID tag; VLAN Priority + CFI bit; Flexible 2-byte
2585 * IPv6 masks are not supported.
2587 * All filters must comply with the masks previously configured.
2588 * For example, with a mask equal to 255.255.255.0 for the source IPv4 address,
2589 * all IPv4 filters must be created with a source IPv4 address that fits the
2592 * This function flushes all filters that have been previously added in
2596 * The port identifier of the Ethernet device.
2598 * The pointer to the fdir mask structure describing relevant headers fields
2599 * and relevant bits to use when matching packets addresses and ports.
2600 * IPv6 masks are not supported.
2602 * - (0) if successful.
2603 * - (-ENOTSUP) if hardware doesn't support flow director mode.
2604 * - (-ENODEV) if *port_id* invalid.
2605 * - (-ENOSYS) if the flow director mode is not configured in perfect
2606 * mode on *port_id*.
2607 * - (-EINVAL) if the fdir_filter information is not correct
2609 int rte_eth_dev_fdir_set_masks(uint8_t port_id,
2610 struct rte_fdir_masks *fdir_mask);
2613 * The eth device event type for interrupt, and maybe others in the future.
2615 enum rte_eth_event_type {
2616 RTE_ETH_EVENT_UNKNOWN, /**< unknown event type */
2617 RTE_ETH_EVENT_INTR_LSC, /**< lsc interrupt event */
2618 RTE_ETH_EVENT_MAX /**< max value of this enum */
2621 typedef void (*rte_eth_dev_cb_fn)(uint8_t port_id, \
2622 enum rte_eth_event_type event, void *cb_arg);
2623 /**< user application callback to be registered for interrupts */
2628 * Register a callback function for specific port id.
2635 * User supplied callback function to be called.
2637 * Pointer to the parameters for the registered callback.
2640 * - On success, zero.
2641 * - On failure, a negative value.
2643 int rte_eth_dev_callback_register(uint8_t port_id,
2644 enum rte_eth_event_type event,
2645 rte_eth_dev_cb_fn cb_fn, void *cb_arg);
2648 * Unregister a callback function for specific port id.
2655 * User supplied callback function to be called.
2657 * Pointer to the parameters for the registered callback. -1 means to
2658 * remove all for the same callback address and same event.
2661 * - On success, zero.
2662 * - On failure, a negative value.
2664 int rte_eth_dev_callback_unregister(uint8_t port_id,
2665 enum rte_eth_event_type event,
2666 rte_eth_dev_cb_fn cb_fn, void *cb_arg);
2669 * @internal Executes all the user application registered callbacks for
2670 * the specific device. It is for DPDK internal user only. User
2671 * application should not call it directly.
2674 * Pointer to struct rte_eth_dev.
2676 * Eth device interrupt event type.
2681 void _rte_eth_dev_callback_process(struct rte_eth_dev *dev,
2682 enum rte_eth_event_type event);
2685 * Turn on the LED on the Ethernet device.
2686 * This function turns on the LED on the Ethernet device.
2689 * The port identifier of the Ethernet device.
2691 * - (0) if successful.
2692 * - (-ENOTSUP) if underlying hardware OR driver doesn't support
2694 * - (-ENODEV) if *port_id* invalid.
2696 int rte_eth_led_on(uint8_t port_id);
2699 * Turn off the LED on the Ethernet device.
2700 * This function turns off the LED on the Ethernet device.
2703 * The port identifier of the Ethernet device.
2705 * - (0) if successful.
2706 * - (-ENOTSUP) if underlying hardware OR driver doesn't support
2708 * - (-ENODEV) if *port_id* invalid.
2710 int rte_eth_led_off(uint8_t port_id);
2713 * Get current status of the Ethernet link flow control for Ethernet device
2716 * The port identifier of the Ethernet device.
2718 * The pointer to the structure where to store the flow control parameters.
2720 * - (0) if successful.
2721 * - (-ENOTSUP) if hardware doesn't support flow control.
2722 * - (-ENODEV) if *port_id* invalid.
2724 int rte_eth_dev_flow_ctrl_get(uint8_t port_id,
2725 struct rte_eth_fc_conf *fc_conf);
2728 * Configure the Ethernet link flow control for Ethernet device
2731 * The port identifier of the Ethernet device.
2733 * The pointer to the structure of the flow control parameters.
2735 * - (0) if successful.
2736 * - (-ENOTSUP) if hardware doesn't support flow control mode.
2737 * - (-ENODEV) if *port_id* invalid.
2738 * - (-EINVAL) if bad parameter
2739 * - (-EIO) if flow control setup failure
2741 int rte_eth_dev_flow_ctrl_set(uint8_t port_id,
2742 struct rte_eth_fc_conf *fc_conf);
2745 * Configure the Ethernet priority flow control under DCB environment
2746 * for Ethernet device.
2749 * The port identifier of the Ethernet device.
2751 * The pointer to the structure of the priority flow control parameters.
2753 * - (0) if successful.
2754 * - (-ENOTSUP) if hardware doesn't support priority flow control mode.
2755 * - (-ENODEV) if *port_id* invalid.
2756 * - (-EINVAL) if bad parameter
2757 * - (-EIO) if flow control setup failure
2759 int rte_eth_dev_priority_flow_ctrl_set(uint8_t port_id,
2760 struct rte_eth_pfc_conf *pfc_conf);
2763 * Add a MAC address to an internal array of addresses used to enable whitelist
2764 * filtering to accept packets only if the destination MAC address matches.
2767 * The port identifier of the Ethernet device.
2769 * The MAC address to add.
2771 * VMDq pool index to associate address with (if VMDq is enabled). If VMDq is
2772 * not enabled, this should be set to 0.
2774 * - (0) if successfully added or *mac_addr" was already added.
2775 * - (-ENOTSUP) if hardware doesn't support this feature.
2776 * - (-ENODEV) if *port* is invalid.
2777 * - (-ENOSPC) if no more MAC addresses can be added.
2778 * - (-EINVAL) if MAC address is invalid.
2780 int rte_eth_dev_mac_addr_add(uint8_t port, struct ether_addr *mac_addr,
2784 * Remove a MAC address from the internal array of addresses.
2787 * The port identifier of the Ethernet device.
2789 * MAC address to remove.
2791 * - (0) if successful, or *mac_addr* didn't exist.
2792 * - (-ENOTSUP) if hardware doesn't support.
2793 * - (-ENODEV) if *port* invalid.
2794 * - (-EADDRINUSE) if attempting to remove the default MAC address
2796 int rte_eth_dev_mac_addr_remove(uint8_t port, struct ether_addr *mac_addr);
2799 * Update Redirection Table(RETA) of Receive Side Scaling of Ethernet device.
2802 * The port identifier of the Ethernet device.
2806 * - (0) if successful.
2807 * - (-ENOTSUP) if hardware doesn't support.
2808 * - (-EINVAL) if bad parameter.
2810 int rte_eth_dev_rss_reta_update(uint8_t port,
2811 struct rte_eth_rss_reta *reta_conf);
2814 * Query Redirection Table(RETA) of Receive Side Scaling of Ethernet device.
2817 * The port identifier of the Ethernet device.
2821 * - (0) if successful.
2822 * - (-ENOTSUP) if hardware doesn't support.
2823 * - (-EINVAL) if bad parameter.
2825 int rte_eth_dev_rss_reta_query(uint8_t port,
2826 struct rte_eth_rss_reta *reta_conf);
2829 * Updates unicast hash table for receiving packet with the given destination
2830 * MAC address, and the packet is routed to all VFs for which the RX mode is
2831 * accept packets that match the unicast hash table.
2834 * The port identifier of the Ethernet device.
2836 * Unicast MAC address.
2838 * 1 - Set an unicast hash bit for receiving packets with the MAC address.
2839 * 0 - Clear an unicast hash bit.
2841 * - (0) if successful.
2842 * - (-ENOTSUP) if hardware doesn't support.
2843 * - (-ENODEV) if *port_id* invalid.
2844 * - (-EINVAL) if bad parameter.
2846 int rte_eth_dev_uc_hash_table_set(uint8_t port,struct ether_addr *addr,
2850 * Updates all unicast hash bitmaps for receiving packet with any Unicast
2851 * Ethernet MAC addresses,the packet is routed to all VFs for which the RX
2852 * mode is accept packets that match the unicast hash table.
2855 * The port identifier of the Ethernet device.
2857 * 1 - Set all unicast hash bitmaps for receiving all the Ethernet
2859 * 0 - Clear all unicast hash bitmaps
2861 * - (0) if successful.
2862 * - (-ENOTSUP) if hardware doesn't support.
2863 * - (-ENODEV) if *port_id* invalid.
2864 * - (-EINVAL) if bad parameter.
2866 int rte_eth_dev_uc_all_hash_table_set(uint8_t port,uint8_t on);
2869 * Set RX L2 Filtering mode of a VF of an Ethernet device.
2872 * The port identifier of the Ethernet device.
2876 * The RX mode mask, which is one or more of accepting Untagged Packets,
2877 * packets that match the PFUTA table, Broadcast and Multicast Promiscuous.
2878 * ETH_VMDQ_ACCEPT_UNTAG,ETH_VMDQ_ACCEPT_HASH_UC,
2879 * ETH_VMDQ_ACCEPT_BROADCAST and ETH_VMDQ_ACCEPT_MULTICAST will be used
2882 * 1 - Enable a VF RX mode.
2883 * 0 - Disable a VF RX mode.
2885 * - (0) if successful.
2886 * - (-ENOTSUP) if hardware doesn't support.
2887 * - (-ENOTSUP) if hardware doesn't support.
2888 * - (-EINVAL) if bad parameter.
2890 int rte_eth_dev_set_vf_rxmode(uint8_t port, uint16_t vf, uint16_t rx_mode,
2894 * Enable or disable a VF traffic transmit of the Ethernet device.
2897 * The port identifier of the Ethernet device.
2901 * 1 - Enable a VF traffic transmit.
2902 * 0 - Disable a VF traffic transmit.
2904 * - (0) if successful.
2905 * - (-ENODEV) if *port_id* invalid.
2906 * - (-ENOTSUP) if hardware doesn't support.
2907 * - (-EINVAL) if bad parameter.
2910 rte_eth_dev_set_vf_tx(uint8_t port,uint16_t vf, uint8_t on);
2913 * Enable or disable a VF traffic receive of an Ethernet device.
2916 * The port identifier of the Ethernet device.
2920 * 1 - Enable a VF traffic receive.
2921 * 0 - Disable a VF traffic receive.
2923 * - (0) if successful.
2924 * - (-ENOTSUP) if hardware doesn't support.
2925 * - (-ENODEV) if *port_id* invalid.
2926 * - (-EINVAL) if bad parameter.
2929 rte_eth_dev_set_vf_rx(uint8_t port,uint16_t vf, uint8_t on);
2932 * Enable/Disable hardware VF VLAN filtering by an Ethernet device of
2933 * received VLAN packets tagged with a given VLAN Tag Identifier.
2936 * The port identifier of the Ethernet device.
2938 * The VLAN Tag Identifier whose filtering must be enabled or disabled.
2940 * Bitmap listing which VFs participate in the VLAN filtering.
2942 * 1 - Enable VFs VLAN filtering.
2943 * 0 - Disable VFs VLAN filtering.
2945 * - (0) if successful.
2946 * - (-ENOTSUP) if hardware doesn't support.
2947 * - (-ENODEV) if *port_id* invalid.
2948 * - (-EINVAL) if bad parameter.
2951 rte_eth_dev_set_vf_vlan_filter(uint8_t port, uint16_t vlan_id,
2956 * Set a traffic mirroring rule on an Ethernet device
2959 * The port identifier of the Ethernet device.
2960 * @param mirror_conf
2961 * The pointer to the traffic mirroring structure describing the mirroring rule.
2962 * The *rte_eth_vm_mirror_conf* structure includes the type of mirroring rule,
2963 * destination pool and the value of rule if enable vlan or pool mirroring.
2966 * The index of traffic mirroring rule, we support four separated rules.
2968 * 1 - Enable a mirroring rule.
2969 * 0 - Disable a mirroring rule.
2971 * - (0) if successful.
2972 * - (-ENOTSUP) if hardware doesn't support this feature.
2973 * - (-ENODEV) if *port_id* invalid.
2974 * - (-EINVAL) if the mr_conf information is not correct.
2976 int rte_eth_mirror_rule_set(uint8_t port_id,
2977 struct rte_eth_vmdq_mirror_conf *mirror_conf,
2982 * Reset a traffic mirroring rule on an Ethernet device.
2985 * The port identifier of the Ethernet device.
2987 * The index of traffic mirroring rule, we support four separated rules.
2989 * - (0) if successful.
2990 * - (-ENOTSUP) if hardware doesn't support this feature.
2991 * - (-ENODEV) if *port_id* invalid.
2992 * - (-EINVAL) if bad parameter.
2994 int rte_eth_mirror_rule_reset(uint8_t port_id,
2998 * Set the rate limitation for a queue on an Ethernet device.
3001 * The port identifier of the Ethernet device.
3005 * The tx rate allocated from the total link speed for this queue.
3007 * - (0) if successful.
3008 * - (-ENOTSUP) if hardware doesn't support this feature.
3009 * - (-ENODEV) if *port_id* invalid.
3010 * - (-EINVAL) if bad parameter.
3012 int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx,
3016 * Set the rate limitation for a vf on an Ethernet device.
3019 * The port identifier of the Ethernet device.
3023 * The tx rate allocated from the total link speed for this VF id.
3025 * The queue mask which need to set the rate.
3027 * - (0) if successful.
3028 * - (-ENOTSUP) if hardware doesn't support this feature.
3029 * - (-ENODEV) if *port_id* invalid.
3030 * - (-EINVAL) if bad parameter.
3032 int rte_eth_set_vf_rate_limit(uint8_t port_id, uint16_t vf,
3033 uint16_t tx_rate, uint64_t q_msk);
3036 * Initialize bypass logic. This function needs to be called before
3037 * executing any other bypass API.
3040 * The port identifier of the Ethernet device.
3042 * - (0) if successful.
3043 * - (-ENOTSUP) if hardware doesn't support.
3044 * - (-EINVAL) if bad parameter.
3046 int rte_eth_dev_bypass_init(uint8_t port);
3049 * Return bypass state.
3052 * The port identifier of the Ethernet device.
3054 * The return bypass state.
3057 * - (3) Isolate mode
3059 * - (0) if successful.
3060 * - (-ENOTSUP) if hardware doesn't support.
3061 * - (-EINVAL) if bad parameter.
3063 int rte_eth_dev_bypass_state_show(uint8_t port, uint32_t *state);
3069 * The port identifier of the Ethernet device.
3071 * The current bypass state.
3074 * - (3) Isolate mode
3076 * - (0) if successful.
3077 * - (-ENOTSUP) if hardware doesn't support.
3078 * - (-EINVAL) if bad parameter.
3080 int rte_eth_dev_bypass_state_set(uint8_t port, uint32_t *new_state);
3083 * Return bypass state when given event occurs.
3086 * The port identifier of the Ethernet device.
3089 * - (1) Main power on (power button is pushed)
3090 * - (2) Auxiliary power on (power supply is being plugged)
3091 * - (3) Main power off (system shutdown and power supply is left plugged in)
3092 * - (4) Auxiliary power off (power supply is being unplugged)
3093 * - (5) Display or set the watchdog timer
3095 * The bypass state when given event occurred.
3098 * - (3) Isolate mode
3100 * - (0) if successful.
3101 * - (-ENOTSUP) if hardware doesn't support.
3102 * - (-EINVAL) if bad parameter.
3104 int rte_eth_dev_bypass_event_show(uint8_t port, uint32_t event, uint32_t *state);
3107 * Set bypass state when given event occurs.
3110 * The port identifier of the Ethernet device.
3113 * - (1) Main power on (power button is pushed)
3114 * - (2) Auxiliary power on (power supply is being plugged)
3115 * - (3) Main power off (system shutdown and power supply is left plugged in)
3116 * - (4) Auxiliary power off (power supply is being unplugged)
3117 * - (5) Display or set the watchdog timer
3119 * The assigned state when given event occurs.
3122 * - (3) Isolate mode
3124 * - (0) if successful.
3125 * - (-ENOTSUP) if hardware doesn't support.
3126 * - (-EINVAL) if bad parameter.
3128 int rte_eth_dev_bypass_event_store(uint8_t port, uint32_t event, uint32_t state);
3131 * Set bypass watchdog timeout count.
3134 * The port identifier of the Ethernet device.
3136 * The timeout to be set.
3137 * - (0) 0 seconds (timer is off)
3146 * - (0) if successful.
3147 * - (-ENOTSUP) if hardware doesn't support.
3148 * - (-EINVAL) if bad parameter.
3150 int rte_eth_dev_wd_timeout_store(uint8_t port, uint32_t timeout);
3153 * Get bypass firmware version.
3156 * The port identifier of the Ethernet device.
3158 * The firmware version
3160 * - (0) if successful.
3161 * - (-ENOTSUP) if hardware doesn't support.
3162 * - (-EINVAL) if bad parameter.
3164 int rte_eth_dev_bypass_ver_show(uint8_t port, uint32_t *ver);
3167 * Return bypass watchdog timeout in seconds
3170 * The port identifier of the Ethernet device.
3172 * The return watchdog timeout. "0" represents timer expired
3173 * - (0) 0 seconds (timer is off)
3182 * - (0) if successful.
3183 * - (-ENOTSUP) if hardware doesn't support.
3184 * - (-EINVAL) if bad parameter.
3186 int rte_eth_dev_bypass_wd_timeout_show(uint8_t port, uint32_t *wd_timeout);
3189 * Reset bypass watchdog timer
3192 * The port identifier of the Ethernet device.
3194 * - (0) if successful.
3195 * - (-ENOTSUP) if hardware doesn't support.
3196 * - (-EINVAL) if bad parameter.
3198 int rte_eth_dev_bypass_wd_reset(uint8_t port);
3201 * Configuration of Receive Side Scaling hash computation of Ethernet device.
3204 * The port identifier of the Ethernet device.
3206 * The new configuration to use for RSS hash computation on the port.
3208 * - (0) if successful.
3209 * - (-ENODEV) if port identifier is invalid.
3210 * - (-ENOTSUP) if hardware doesn't support.
3211 * - (-EINVAL) if bad parameter.
3213 int rte_eth_dev_rss_hash_update(uint8_t port_id,
3214 struct rte_eth_rss_conf *rss_conf);
3217 * Retrieve current configuration of Receive Side Scaling hash computation
3218 * of Ethernet device.
3221 * The port identifier of the Ethernet device.
3223 * Where to store the current RSS hash configuration of the Ethernet device.
3225 * - (0) if successful.
3226 * - (-ENODEV) if port identifier is invalid.
3227 * - (-ENOTSUP) if hardware doesn't support RSS.
3230 rte_eth_dev_rss_hash_conf_get(uint8_t port_id,
3231 struct rte_eth_rss_conf *rss_conf);
3237 * The port identifier of the Ethernet device.
3239 * The index of RX queue where to store RX packets matching the syn filter.
3241 * The pointer to the structure describing the syn filter rule.
3243 * - (0) if successful.
3244 * - (-ENOTSUP) if hardware doesn't support.
3245 * - (-EINVAL) if bad parameter.
3247 int rte_eth_dev_add_syn_filter(uint8_t port_id,
3248 struct rte_syn_filter *filter, uint16_t rx_queue);
3254 * The port identifier of the Ethernet device.
3256 * - (0) if successful.
3257 * - (-ENOTSUP) if hardware doesn't support.
3258 * - (-EINVAL) if bad parameter.
3260 int rte_eth_dev_remove_syn_filter(uint8_t port_id);
3266 * The port identifier of the Ethernet device.
3268 * The pointer to the structure describing the syn filter.
3270 * A pointer to get the queue index of syn filter.
3272 * - (0) if successful.
3273 * - (-ENOTSUP) if hardware doesn't support.
3274 * - (-EINVAL) if bad parameter.
3276 int rte_eth_dev_get_syn_filter(uint8_t port_id,
3277 struct rte_syn_filter *filter, uint16_t *rx_queue);
3280 * Add a new ethertype filter rule on an Ethernet device.
3283 * The port identifier of the Ethernet device.
3285 * The identifier of ethertype filter.
3287 * The pointer to the structure describing the ethertype filter rule.
3288 * The *rte_ethertype_filter* structure includes the values of the different
3289 * fields to match: ethertype and priority in vlan tag.
3290 * priority in vlan tag is not supported for E1000 dev.
3292 * The index of the RX queue where to store RX packets matching the added
3295 * - (0) if successful.
3296 * - (-ENOTSUP) if hardware doesn't support ethertype filter.
3297 * - (-ENODEV) if *port_id* invalid.
3298 * - (-EINVAL) if the filter information is not correct.
3300 int rte_eth_dev_add_ethertype_filter(uint8_t port_id, uint16_t index,
3301 struct rte_ethertype_filter *filter, uint16_t rx_queue);
3304 * remove an ethertype filter rule on an Ethernet device.
3307 * The port identifier of the Ethernet device.
3309 * The identifier of ethertype filter.
3311 * - (0) if successful.
3312 * - (-ENOTSUP) if hardware doesn't support ethertype filter.
3313 * - (-ENODEV) if *port_id* invalid.
3314 * - (-EINVAL) if the filter information is not correct.
3316 int rte_eth_dev_remove_ethertype_filter(uint8_t port_id,
3320 * Get an ethertype filter rule on an Ethernet device.
3323 * The port identifier of the Ethernet device.
3325 * The identifier of ethertype filter.
3327 * A pointer to a structure of type *rte_ethertype_filter* to be filled with
3328 * the information of the Ethertype filter.
3330 * A pointer to get the queue index.
3332 * - (0) if successful.
3333 * - (-ENOTSUP) if hardware doesn't support ethertype filter.
3334 * - (-ENODEV) if *port_id* invalid.
3335 * - (-EINVAL) if the filter information is not correct.
3336 * - (-ENOENT) if no enabled filter in this index.
3338 int rte_eth_dev_get_ethertype_filter(uint8_t port_id, uint16_t index,
3339 struct rte_ethertype_filter *filter, uint16_t *rx_queue);
3342 * Add a new 2tuple filter rule on an Ethernet device.
3345 * The port identifier of the Ethernet device.
3347 * The identifier of 2tuple filter.
3349 * The pointer to the structure describing the 2tuple filter rule.
3350 * The *rte_2tuple_filter* structure includes the values of the different
3351 * fields to match: protocol, dst_port and
3352 * tcp_flags if the protocol is tcp type.
3354 * The index of the RX queue where to store RX packets matching the added
3357 * - (0) if successful.
3358 * - (-ENOTSUP) if hardware doesn't support 2tuple filter.
3359 * - (-ENODEV) if *port_id* invalid.
3360 * - (-EINVAL) if the filter information is not correct.
3362 int rte_eth_dev_add_2tuple_filter(uint8_t port_id, uint16_t index,
3363 struct rte_2tuple_filter *filter, uint16_t rx_queue);
3366 * remove a 2tuple filter rule on an Ethernet device.
3369 * The port identifier of the Ethernet device.
3371 * The identifier of 2tuple filter.
3373 * - (0) if successful.
3374 * - (-ENOTSUP) if hardware doesn't support 2tuple filter.
3375 * - (-ENODEV) if *port_id* invalid.
3376 * - (-EINVAL) if the filter information is not correct.
3378 int rte_eth_dev_remove_2tuple_filter(uint8_t port_id, uint16_t index);
3381 * Get an 2tuple filter rule on an Ethernet device.
3384 * The port identifier of the Ethernet device.
3386 * The identifier of 2tuple filter.
3388 * A pointer to a structure of type *rte_2tuple_filter* to be filled with
3389 * the information of the 2tuple filter.
3391 * A pointer to get the queue index.
3393 * - (0) if successful.
3394 * - (-ENOTSUP) if hardware doesn't support 2tuple filter.
3395 * - (-ENODEV) if *port_id* invalid.
3396 * - (-EINVAL) if the filter information is not correct.
3397 * - (-ENOENT) if no enabled filter in this index.
3399 int rte_eth_dev_get_2tuple_filter(uint8_t port_id, uint16_t index,
3400 struct rte_2tuple_filter *filter, uint16_t *rx_queue);
3403 * Add a new 5tuple filter rule on an Ethernet device.
3406 * The port identifier of the Ethernet device.
3408 * The identifier of 5tuple filter.
3410 * The pointer to the structure describing the 5tuple filter rule.
3411 * The *rte_5tuple_filter* structure includes the values of the different
3412 * fields to match: dst src IP, dst src port, protocol and relative masks
3414 * The index of the RX queue where to store RX packets matching the added
3417 * - (0) if successful.
3418 * - (-ENOTSUP) if hardware doesn't support 5tuple filter.
3419 * - (-ENODEV) if *port_id* invalid.
3420 * - (-EINVAL) if the filter information is not correct.
3422 int rte_eth_dev_add_5tuple_filter(uint8_t port_id, uint16_t index,
3423 struct rte_5tuple_filter *filter, uint16_t rx_queue);
3426 * remove a 5tuple filter rule on an Ethernet device.
3429 * The port identifier of the Ethernet device.
3431 * The identifier of 5tuple filter.
3433 * - (0) if successful.
3434 * - (-ENOTSUP) if hardware doesn't support 5tuple filter.
3435 * - (-ENODEV) if *port_id* invalid.
3436 * - (-EINVAL) if the filter information is not correct.
3438 int rte_eth_dev_remove_5tuple_filter(uint8_t port_id, uint16_t index);
3441 * Get an 5tuple filter rule on an Ethernet device.
3444 * The port identifier of the Ethernet device.
3446 * The identifier of 5tuple filter.
3448 * A pointer to a structure of type *rte_5tuple_filter* to be filled with
3449 * the information of the 5tuple filter.
3451 * A pointer to get the queue index.
3453 * - (0) if successful.
3454 * - (-ENOTSUP) if hardware doesn't support 5tuple filter.
3455 * - (-ENODEV) if *port_id* invalid.
3456 * - (-EINVAL) if the filter information is not correct.
3458 int rte_eth_dev_get_5tuple_filter(uint8_t port_id, uint16_t index,
3459 struct rte_5tuple_filter *filter, uint16_t *rx_queue);
3462 * Add a new flex filter rule on an Ethernet device.
3465 * The port identifier of the Ethernet device.
3467 * The identifier of flex filter.
3469 * The pointer to the structure describing the flex filter rule.
3470 * The *rte_flex_filter* structure includes the values of the different fields
3471 * to match: the dwords (first len bytes of packet ) and relative masks.
3473 * The index of the RX queue where to store RX packets matching the added
3476 * - (0) if successful.
3477 * - (-ENOTSUP) if hardware doesn't support flex filter.
3478 * - (-ENODEV) if *port_id* invalid.
3479 * - (-EINVAL) if the filter information is not correct.
3480 * - (-ENOENT) if no enabled filter in this index.
3482 int rte_eth_dev_add_flex_filter(uint8_t port_id, uint16_t index,
3483 struct rte_flex_filter *filter, uint16_t rx_queue);
3486 * remove a flex filter rule on an Ethernet device.
3489 * The port identifier of the Ethernet device.
3491 * The identifier of flex filter.
3493 * - (0) if successful.
3494 * - (-ENOTSUP) if hardware doesn't support flex filter.
3495 * - (-ENODEV) if *port_id* invalid.
3496 * - (-EINVAL) if the filter information is not correct.
3498 int rte_eth_dev_remove_flex_filter(uint8_t port_id, uint16_t index);
3501 * Get an flex filter rule on an Ethernet device.
3504 * The port identifier of the Ethernet device.
3506 * The identifier of flex filter.
3508 * A pointer to a structure of type *rte_flex_filter* to be filled with
3509 * the information of the flex filter.
3511 * A pointer to get the queue index.
3513 * - (0) if successful.
3514 * - (-ENOTSUP) if hardware doesn't support flex filter.
3515 * - (-ENODEV) if *port_id* invalid.
3516 * - (-EINVAL) if the filter information is not correct.
3517 * - (-ENOENT) if no enabled filter in this index.
3519 int rte_eth_dev_get_flex_filter(uint8_t port_id, uint16_t index,
3520 struct rte_flex_filter *filter, uint16_t *rx_queue);
3526 #endif /* _RTE_ETHDEV_H_ */