1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright 2020 The DPDK contributors
4 .. include:: <isonum.txt>
9 .. **Read this first.**
11 The text in the sections below explains how to update the release notes.
13 Use proper spelling, capitalization and punctuation in all sections.
15 Variable and config names should be quoted as fixed width text:
18 Build the docs and view the output file to ensure the changes are correct::
21 xdg-open build/doc/html/guides/rel_notes/release_20_11.html
27 .. This section should contain new features added in this release.
30 * **Add a title in the past tense with a full stop.**
32 Add a short 1-2 sentence description in the past tense.
33 The description should be enough to allow someone scanning
34 the release notes to understand the new feature.
36 If the feature adds a lot of sub-features you can use a bullet list
39 * Added feature foo to do something.
40 * Enhanced feature bar to do something else.
42 Refer to the previous release notes for examples.
44 Suggested order in release notes items:
45 * Core libs (EAL, mempool, ring, mbuf, buses)
46 * Device abstraction libs and PMDs
48 - cryptodev (lib, PMDs)
49 - eventdev (lib, PMDs)
52 * Apps, Examples, Tools (if significant)
54 This section is a comment. Do not overwrite or remove it.
55 Also, make sure to start the actual text at the margin.
56 =======================================================
58 * **Added write combining store APIs.**
60 Added ``rte_write32_wc`` and ``rte_write32_wc_relaxed`` APIs
61 that enable write combining stores (depending on architecture).
62 The functions are provided as a generic stubs and
63 x86 specific implementation.
65 * **Added prefetch with intention to write APIs.**
67 Added new prefetch function variants e.g. ``rte_prefetch0_write``,
68 which allow the programmer to prefetch a cache line and also indicate
69 the intention to write.
71 * **Added the rte_cldemote API.**
73 Added a hardware hint CLDEMOTE, which is similar to prefetch in reverse.
74 CLDEMOTE moves the cache line to the more remote cache, where it expects
75 sharing to be efficient. Moving the cache line to a level more distant from
76 the processor helps to accelerate core-to-core communication.
77 This API is specific to x86 and implemented as a stub for other
80 * **Added support for limiting maximum SIMD bitwidth.**
82 Added a new EAL config setting ``max_simd_bitwidth`` to limit the vector
83 path selection at runtime. This value can be set by apps using the
84 ``rte_vect_set_max_simd_bitwidth`` function, or by the user with EAL flag
85 ``--force-max-simd-bitwidth``.
87 * **Added zero copy APIs for rte_ring.**
89 For rings with producer/consumer in ``RTE_RING_SYNC_ST``, ``RTE_RING_SYNC_MT_HTS``
90 modes, these APIs split enqueue/dequeue operation into three phases
91 (enqueue/dequeue start, copy data to/from ring, enqueue/dequeue finish).
92 Along with the advantages of the peek APIs, these provide the ability to
93 copy the data to the ring memory directly without the need for temporary
96 * **Updated CRC modules of the net library.**
98 * Added runtime selection of the optimal architecture-specific CRC path.
99 * Added optimized implementations of CRC32-Ethernet and CRC16-CCITT
100 using the AVX512 and VPCLMULQDQ instruction sets.
102 * **Introduced extended buffer description for receiving.**
104 Added the extended Rx buffer description for Rx queue setup routine
105 providing the individual settings for each Rx segment with maximal size,
106 buffer offset and memory pool to allocate data buffers from.
108 * **Added the FEC API, for a generic FEC query and config.**
110 Added the FEC API which provides functions for query FEC capabilities and
111 current FEC mode from device. Also, API for configuring FEC mode is also provided.
113 * **Added thread safety to rte_flow functions.**
115 Added ``RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE`` device flag to indicate
116 whether PMD supports thread safe operations. If PMD doesn't set the flag,
117 rte_flow API level functions will protect the flow operations with mutex.
119 * **Added flow-based traffic sampling support.**
121 Added new action: ``RTE_FLOW_ACTION_TYPE_SAMPLE`` to duplicate the matching
122 packets with specified ratio, and apply with own set of actions with a fate
123 action. When the ratio is set to 1 then the packets will be 100% mirrored.
125 * **Added support of shared action in flow API.**
127 Added shared action support to utilize single flow action in multiple flow
128 rules. An update of shared action configuration alters the behavior of all
131 * Added new action: ``RTE_FLOW_ACTION_TYPE_SHARED`` to use shared action
133 * Added new flow APIs to create/update/destroy/query shared action.
135 * **Flow rules allowed to use private PMD items / actions.**
137 * Flow rule verification was updated to accept private PMD
140 * **Added generic API to offload tunneled traffic and restore missed packet.**
142 * Added a new hardware independent helper to flow API that
143 offloads tunneled traffic and restores missed packets.
145 * **Updated the ethdev library to support hairpin between two ports.**
147 New APIs are introduced to support binding / unbinding 2 ports hairpin.
148 Hairpin Tx part flow rules can be inserted explicitly.
149 New API is added to get the hairpin peer ports list.
151 * **Updated Broadcom bnxt driver.**
153 Updated the Broadcom bnxt driver with new features and improvements, including:
155 * Added support for 200G PAM4 link speed.
156 * Added support for RSS hash level selection.
157 * Updated HWRM structures to 1.10.1.70 version.
158 * Added TRUFLOW support for Stingray devices.
159 * Added support for representors on MAIA cores of SR.
160 * Added support for VXLAN decap offload using rte_flow.
161 * Added support to indicate native rte_flow API thread safety.
163 * **Updated Cisco enic driver.**
165 * Added support for VF representors with single-queue Tx/Rx and flow API
166 * Added support for egress PORT_ID action
167 * Added support for non-zero priorities for group 0 flows
168 * Added support for VXLAN decap combined with VLAN pop
170 * **Added hns3 FEC PMD, for supporting query and config FEC mode.**
172 Added the FEC PMD which provides functions for query FEC capabilities and
173 current FEC mode from device. Also, PMD for configuring FEC mode is also provided.
175 * **Updated Intel iavf driver.**
177 * Added support of AVX512 instructions in Rx and Tx path.
179 * **Updated Intel ice driver.**
181 * Used write combining stores.
182 * Added ACL filter support for Intel DCF.
184 * **Updated Mellanox mlx5 driver.**
186 Updated Mellanox mlx5 driver with new features and improvements, including:
188 * Added support for matching on fragmented/non-fragmented IPv4/IPv6 packets.
189 * Added support for QinQ packets matching.
190 * Added support for the new VLAN fields ``has_vlan`` in the Ethernet item
191 and ``has_more_vlan`` in the VLAN item.
192 * Updated the supported timeout for Age action to the maximal value supported
194 * Added support of Age action query.
195 * Added support of multi-ports hairpin.
197 * **Updated Solarflare network PMD.**
199 Updated the Solarflare ``sfc_efx`` driver with changes including:
201 * Added SR-IOV PF support
202 * Added Alveo SN1000 SmartNICs (EF100 architecture) support including
203 flow API transfer rules for switch HW offload
205 * **Added Wangxun txgbe PMD.**
207 Added a new PMD driver for Wangxun 10 Gigabit Ethernet NICs.
209 See the :doc:`../nics/txgbe` for more details.
211 * **Updated Virtio driver.**
213 * Added support for Vhost-vDPA backend to Virtio-user PMD.
214 * Changed default link speed to unknown.
215 * Added support for 200G link speed.
217 * **Updated Intel i40e driver.**
219 Updated the Intel i40e driver to use write combining stores.
221 * **Updated Intel ixgbe driver.**
223 Updated the Intel ixgbe driver to use write combining stores.
225 * **Updated Intel qat driver.**
227 Updated the Intel qat driver to use write combining stores.
229 * **Updated Memif PMD.**
231 * Added support for abstract socket address.
232 * Changed default socket address type to abstract.
234 * **Added Ice Lake (Gen4) support for Intel NTB.**
236 Added NTB device support (4th generation) for Intel Ice Lake platform.
238 * **Added UDP/IPv4 GRO support for VxLAN and non-VxLAN packets.**
240 For VxLAN packets, added inner UDP/IPv4 support.
241 For non-VxLAN packets, added UDP/IPv4 support.
243 * **Extended flow-perf application.**
245 * Started supporting user order instead of bit mask:
246 Now the user can create any structure of rte_flow
247 using flow performance application with any order,
248 moreover the app also now starts to support inner
249 items matching as well.
250 * Added header modify actions.
252 * Added raw encap/decap actions.
253 * Added VXLAN encap/decap actions.
254 * Added ICMP(code/type/identifier/sequence number) and ICMP6(code/type) matching items.
255 * Added option to set port mask for insertion/deletion:
257 where N represents the hexadecimal bitmask of ports used.
259 * **Added raw data-path APIs for cryptodev library.**
261 Cryptodev is added with raw data-path APIs to accelerate external
262 libraries or applications which need to avail fast cryptodev
263 enqueue/dequeue operations but does not necessarily depends on
264 mbufs and cryptodev operation mempools.
266 * **Updated the aesni_mb crypto PMD.**
268 * Added support for AES-ECB 128, 192 and 256.
269 * Added support for ZUC-EEA3/EIA3 algorithms.
270 * Added support for SNOW3G-UEA2/UIA2 algorithms.
271 * Added support for KASUMI-F8/F9 algorithms.
272 * Added support for Chacha20-Poly1305.
273 * Added support for AES-256 CCM algorithm.
275 * **Updated the aesni_gcm crypto PMD.**
277 * Added SGL support for AES-GMAC.
279 * **Added Broadcom BCMFS symmetric crypto PMD.**
281 Added a symmetric crypto PMD for Broadcom FlexSparc crypto units.
282 See :doc:`../cryptodevs/bcmfs` guide for more details on this new PMD.
284 * **Updated DPAA2_SEC crypto PMD.**
286 * Added DES-CBC support for cipher_only, chain and ipsec protocol.
287 * Added support for non-HMAC auth algorithms
288 (MD5, SHA1, SHA224, SHA256, SHA384, SHA512).
290 * **Updated Marvell NITROX symmetric crypto PMD.**
292 * Added AES-GCM support.
293 * Added cipher only offload support.
295 * **Updated the OCTEON TX2 crypto PMD.**
297 * Updated the OCTEON TX2 crypto PMD lookaside protocol offload for IPsec with
300 * **Updated QAT crypto PMD.**
302 * Added Raw Data-path APIs support.
304 * **Added Intel ACC100 bbdev PMD.**
306 Added a new ``acc100`` bbdev driver for the Intel\ |reg| ACC100 accelerator
307 also known as Mount Bryce. See the
308 :doc:`../bbdevs/acc100` BBDEV guide for more details on this new driver.
310 * **Updated rte_security library to support SDAP.**
312 ``rte_security_pdcp_xform`` in ``rte_security`` lib is updated to enable
313 5G NR processing of SDAP header in PMDs.
315 * **Added Marvell OCTEON TX2 regex PMD.**
317 Added a new PMD driver for hardware regex offload block for OCTEON TX2 SoC.
319 See the :doc:`../regexdevs/octeontx2` for more details.
321 * **Updated Software Eventdev driver.**
323 Added performance tuning arguments to allow tuning the scheduler for
324 better throughtput in high core count use cases.
326 * **Added a new driver for the Intel Dynamic Load Balancer v1.0 device.**
328 Added the new ``dlb`` eventdev driver for the Intel DLB V1.0 device. See the
329 :doc:`../eventdevs/dlb` eventdev guide for more details on this new driver.
331 * **Added a new driver for the Intel Dynamic Load Balancer v2.0 device.**
333 Added the new ``dlb2`` eventdev driver for the Intel DLB V2.0 device. See the
334 :doc:`../eventdevs/dlb2` eventdev guide for more details on this new driver.
336 * **Updated ioat rawdev driver**
338 The ioat rawdev driver has been updated and enhanced. Changes include:
340 * Added support for Intel\ |reg| Data Streaming Accelerator hardware.
341 For more information, see https://01.org/blogs/2019/introducing-intel-data-streaming-accelerator
342 * Added support for the fill operation via the API ``rte_ioat_enqueue_fill()``,
343 where the hardware fills an area of memory with a repeating pattern.
344 * Added a per-device configuration flag to disable management
345 of user-provided completion handles.
346 * Renamed the ``rte_ioat_do_copies()`` API to ``rte_ioat_perform_ops()``,
347 and renamed the ``rte_ioat_completed_copies()`` API to ``rte_ioat_completed_ops()``
348 to better reflect the APIs' purposes, and remove the implication that
349 they are limited to copy operations only.
350 [Note: The old API is still provided but marked as deprecated in the code]
351 * Added a new API ``rte_ioat_fence()`` to add a fence between operations.
352 This API replaces the ``fence`` flag parameter in the ``rte_ioat_enqueue_copies()`` function,
353 and is clearer as there is no ambiguity as to whether the flag should be
354 set on the last operation before the fence or the first operation after it.
356 * **Updated the pipeline library for alignment with the P4 language.**
358 Added new Software Switch (SWX) pipeline type that provides more
359 flexibility through API and feature alignment with the P4 language.
361 * The packet headers, meta-data, actions, tables and pipelines are
362 dynamically defined instead of selected from pre-defined set.
363 * The actions and the pipeline are defined with instructions.
364 * Extern objects and functions can be plugged into the pipeline.
365 * Transaction-oriented table updates.
367 * **Add new AVX512 specific classify algorithms for ACL library.**
369 * Added new ``RTE_ACL_CLASSIFY_AVX512X16`` vector implementation,
370 which can process up to 16 flows in parallel. Requires AVX512 support.
372 * Added new ``RTE_ACL_CLASSIFY_AVX512X32`` vector implementation,
373 which can process up to 32 flows in parallel. Requires AVX512 support.
375 * **Added AVX512 lookup implementation for FIB.**
377 Added a AVX512 lookup functions implementation into FIB and FIB6 libraries.
379 * **Added support to update subport bandwidth dynamically.**
381 * Added new API ``rte_sched_port_subport_profile_add`` to add new
382 subport bandwidth profile to subport porfile table at runtime.
384 * Added support to update subport rate dynamically.
386 * **Updated FIPS validation sample application.**
388 * Added scatter gather support.
389 * Added NIST GCMVS complaint GMAC test method support.
391 * **Updated l3wfd-acl sample application.**
393 * Added new optional parameter ``--eth-dest`` for the ``l3fwd-acl`` to allow
394 the user to specify the destination mac address for each ethernet port
396 * Replaced ``--scalar`` command-line option with ``--alg=<value>``, to allow
397 the user to select the desired classify method.
399 * **Updated vhost sample application.**
401 Added vhost asynchronous APIs support, which demonstrated how the application
402 leverage IOAT DMA channel with vhost asynchronous APIs.
403 See the :doc:`../sample_app_ug/vhost` for more details.
409 .. This section should contain removed items in this release. Sample format:
411 * Add a short 1-2 sentence description of the removed item
414 This section is a comment. Do not overwrite or remove it.
415 Also, make sure to start the actual text at the margin.
416 =======================================================
418 * build: Support for the Make build system was removed for compiling DPDK,
419 Meson is now the primary build system.
420 Sample applications can still be built with Make standalone, using pkg-config.
422 * vhost: Dequeue zero-copy support has been removed.
424 * kernel: The module ``igb_uio`` has been moved to the git repository
425 ``dpdk-kmods`` in a new directory ``linux/igb_uio``.
427 * Removed Python 2 support since it was EOL'd in January 2020.
429 * Removed TEP termination sample application.
435 .. This section should contain API changes. Sample format:
437 * sample: Add a short 1-2 sentence description of the API change
438 which was announced in the previous releases and made in this release.
439 Start with a scope label like "ethdev:".
440 Use fixed width quotes for ``function_names`` or ``struct_names``.
443 This section is a comment. Do not overwrite or remove it.
444 Also, make sure to start the actual text at the margin.
445 =======================================================
447 * build macros: The macros defining ``RTE_MACHINE_CPUFLAG_*`` are removed.
448 The information provided by these macros is available through standard
451 * eal: Replaced the function ``rte_get_master_lcore()`` to
452 ``rte_get_main_lcore()``. The old function is deprecated.
454 The iterator for worker lcores is also changed:
455 ``RTE_LCORE_FOREACH_SLAVE`` is replaced with
456 ``RTE_LCORE_FOREACH_WORKER``.
458 * eal: The ``rte_logs`` struct and global symbol was made private
459 and is no longer part of the API.
461 * eal: Made the ``rte_dev_event`` structure private to the EAL as no public API
464 * eal: ``rte_cio_rmb()`` and ``rte_cio_wmb()`` were deprecated since 20.08
465 and are removed in this release.
467 * mem: Removed the unioned field ``phys_addr`` from
468 the structures ``rte_memseg`` and ``rte_memzone``.
469 The field ``iova`` is remaining from the old unions.
471 * mempool: Removed the unioned fields ``phys_addr`` and ``physaddr`` from
472 the structures ``rte_mempool_memhdr`` and ``rte_mempool_objhdr``.
473 The field ``iova`` is remaining from the old unions.
474 The flag name ``MEMPOOL_F_NO_PHYS_CONTIG`` is removed,
475 while the aliased flag ``MEMPOOL_F_NO_IOVA_CONTIG`` is kept.
477 * mbuf: Removed the functions ``rte_mbuf_data_dma_addr*``
478 and the macros ``rte_pktmbuf_mtophys*``.
479 The same functionality is still available with the functions and macros
480 having ``iova`` in their names instead of ``dma_addr`` or ``mtophys``.
482 * mbuf: Removed the unioned field ``buf_physaddr`` from ``rte_mbuf``.
483 The field ``buf_iova`` is remaining from the old union.
485 * mbuf: Removed the unioned field ``refcnt_atomic`` from
486 the structures ``rte_mbuf`` and ``rte_mbuf_ext_shared_info``.
487 The field ``refcnt`` is remaining from the old unions.
489 * mbuf: Removed the unioned fields ``userdata`` and ``udata64``
490 from the structure ``rte_mbuf``. It is replaced with dynamic fields.
492 * mbuf: Removed the field ``seqn`` from the structure ``rte_mbuf``.
493 It is replaced with dynamic fields.
495 * mbuf: Removed the field ``timestamp`` from the structure ``rte_mbuf``.
496 It is replaced with the dynamic field RTE_MBUF_DYNFIELD_TIMESTAMP_NAME
497 which was previously used only for Tx.
499 * pci: Removed the ``rte_kernel_driver`` enum defined in rte_dev.h and
500 replaced with a private enum in the PCI subsystem.
502 * pci: Removed the PCI resources map API from the public API
503 (``pci_map_resource`` and ``pci_unmap_resource``) and moved it to the
504 PCI bus driver along with the PCI resources lists and associated structures
505 (``pci_map``, ``pci_msix_table``, ``mapped_pci_resource`` and
506 ``mapped_pci_res_list``).
508 * ethdev: Removed the ``kdrv`` field in the ethdev ``rte_eth_dev_data``
509 structure as it gave no useful abstracted information to the applications.
511 * ethdev: ``rte_eth_rx_descriptor_done()`` API has been deprecated.
513 * ethdev: Renamed basic statistics per queue. An underscore is inserted
514 between the queue number and the rest of the xstat name:
516 * ``rx_qN*`` -> ``rx_qN_*``
517 * ``tx_qN*`` -> ``tx_qN_*``
519 * ethdev: Added capability to query age flow action.
521 * ethdev: Changed ``rte_eth_dev_stop`` return value from ``void`` to
522 ``int`` to provide a way to report various error conditions.
524 * ethdev: Added ``int`` return type to ``rte_eth_dev_close()``.
526 * ethdev: Renamed internal functions:
528 * ``_rte_eth_dev_callback_process()`` -> ``rte_eth_dev_callback_process()``
529 * ``_rte_eth_dev_reset`` -> ``rte_eth_dev_internal_reset()``
531 * ethdev: Modified field type of ``base`` and ``nb_queue`` in struct
532 ``rte_eth_dcb_tc_queue_mapping`` from ``uint8_t`` to ``uint16_t``.
533 As the data of ``uint8_t`` will be truncated when queue number under
534 a TC is greater than 256.
536 * vhost: Moved vDPA APIs from experimental to stable.
538 * vhost: Add a new function ``rte_vhost_crypto_driver_start`` to be called
539 instead of ``rte_vhost_driver_start`` by crypto applications.
541 * cryptodev: The structure ``rte_crypto_sym_vec`` is updated to support both
542 cpu_crypto synchrounous operation and asynchronous raw data-path APIs.
544 * cryptodev: ``RTE_CRYPTO_AEAD_LIST_END`` from ``enum rte_crypto_aead_algorithm``,
545 ``RTE_CRYPTO_CIPHER_LIST_END`` from ``enum rte_crypto_cipher_algorithm`` and
546 ``RTE_CRYPTO_AUTH_LIST_END`` from ``enum rte_crypto_auth_algorithm``
547 are removed to avoid future ABI breakage while adding new algorithms.
549 * scheduler: Renamed functions ``rte_cryptodev_scheduler_slave_attach``,
550 ``rte_cryptodev_scheduler_slave_detach`` and
551 ``rte_cryptodev_scheduler_slaves_get`` to
552 ``rte_cryptodev_scheduler_worker_attach``,
553 ``rte_cryptodev_scheduler_worker_detach`` and
554 ``rte_cryptodev_scheduler_workers_get`` accordingly.
556 * scheduler: Renamed the configuration value
557 ``RTE_CRYPTODEV_SCHEDULER_MAX_NB_SLAVES`` to
558 ``RTE_CRYPTODEV_SCHEDULER_MAX_NB_WORKERS``.
560 * security: ``hfn_ovrd`` field in ``rte_security_pdcp_xform`` is changed from
561 ``uint32_t`` to ``uint8_t`` so that a new field ``sdap_enabled`` can be added
564 * security: The API ``rte_security_session_create`` is updated to take two
565 mempool objects one for session and other for session private data.
566 So the application need to create two mempools and get the size of session
567 private data using API ``rte_security_session_get_size`` for private session
570 * ipsec: ``RTE_SATP_LOG2_NUM`` has been dropped from ``enum`` and
571 subsequently moved ``rte_ipsec`` lib from experimental to stable.
573 * baseband/fpga_lte_fec: Renamed function ``fpga_lte_fec_configure`` to
574 ``rte_fpga_lte_fec_configure`` and structure ``fpga_lte_fec_conf`` to
575 ``rte_fpga_lte_fec_conf``.
577 * baseband/fpga_5gnr_fec: Renamed function ``fpga_5gnr_fec_configure`` to
578 ``rte_fpga_5gnr_fec_configure`` and structure ``fpga_5gnr_fec_conf`` to
579 ``rte_fpga_5gnr_fec_conf``.
581 * rawdev: Added a structure size parameter to the functions
582 ``rte_rawdev_queue_setup()``, ``rte_rawdev_queue_conf_get()``,
583 ``rte_rawdev_info_get()`` and ``rte_rawdev_configure()``,
584 allowing limited driver type-checking and ABI compatibility.
586 * rawdev: Changed the return type of the function ``rte_dev_info_get()``
587 and the function ``rte_rawdev_queue_conf_get()``
588 from ``void`` to ``int`` allowing the return of error codes from drivers.
590 * rawdev: The running of a drivers ``selftest()`` function can now be done
591 using the ``rawdev_autotest`` command in the ``dpdk-test`` binary. This
592 command now calls the self-test function for each rawdev found on the
593 system, and does not require a specific command per device type.
594 Following this change, the ``ioat_rawdev_autotest`` command has been
595 removed as no longer needed.
597 * raw/ioat: As noted above, the ``rte_ioat_do_copies()`` and
598 ``rte_ioat_completed_copies()`` functions have been renamed to
599 ``rte_ioat_perform_ops()`` and ``rte_ioat_completed_ops()`` respectively.
601 * stack: the experimental tag has been dropped from the stack library, and its
602 interfaces are considered stable as of DPDK 20.11.
604 * bpf: ``RTE_BPF_XTYPE_NUM`` has been dropped from ``rte_bpf_xtype``.
606 * gso: Changed ``rte_gso_segment`` behaviour and return value:
608 * ``pkt`` is not saved to ``pkts_out[0]`` if not GSOed.
609 * Return 0 instead of 1 for the above case.
610 * ``pkt`` is not freed, no matter whether it is GSOed, leaving to the caller.
612 * acl: ``RTE_ACL_CLASSIFY_NUM`` enum value has been removed.
613 This enum value was not used inside DPDK, while it prevented to add new
614 classify algorithms without causing an ABI breakage.
616 * sched: Added ``subport_profile_id`` as argument
617 to function ``rte_sched_subport_config``.
619 * sched: Removed ``tb_rate``, ``tc_rate``, ``tc_period`` and ``tb_size``
620 from ``struct rte_sched_subport_params``.
626 .. This section should contain ABI changes. Sample format:
628 * sample: Add a short 1-2 sentence description of the ABI change
629 which was announced in the previous releases and made in this release.
630 Start with a scope label like "ethdev:".
631 Use fixed width quotes for ``function_names`` or ``struct_names``.
634 This section is a comment. Do not overwrite or remove it.
635 Also, make sure to start the actual text at the margin.
636 =======================================================
638 * eal: Removed the not implemented function ``rte_dump_registers()``.
642 * Following device operation function pointers moved
643 from ``struct eth_dev_ops`` to ``struct rte_eth_dev``:
645 * ``eth_rx_queue_count_t rx_queue_count;``
646 * ``eth_rx_descriptor_done_t rx_descriptor_done;``
647 * ``eth_rx_descriptor_status_t rx_descriptor_status;``
648 * ``eth_tx_descriptor_status_t tx_descriptor_status;``
650 * ``struct eth_dev_ops`` is no more accessible by applications,
651 which was already internal data structure.
653 * ``ethdev`` internal functions are marked with ``__rte_internal`` tag.
655 * Added extensions' attributes to struct ``rte_flow_item_ipv6``.
656 A set of additional values added to struct, indicating the existence of
657 every defined extension header type.
658 Applications should use the new values for identification of existing
659 extensions in the packet header.
661 * Added fields ``rx_seg`` and ``rx_nseg`` to ``rte_eth_rxconf`` structure
662 to provide extended description of the receiving buffer.
664 * ``struct rte_eth_hairpin_conf`` has two new members:
666 * ``uint32_t tx_explicit:1;``
667 * ``uint32_t manual_bind:1;``
669 * Added new field ``has_vlan`` to structure ``rte_flow_item_eth``,
670 indicating that packet header contains at least one VLAN.
672 * Added new field ``has_more_vlan`` to structure
673 ``rte_flow_item_vlan``, indicating that packet header contains
674 at least one more VLAN, after this VLAN.
676 * eventdev: Following structures are modified to support DLB/DLB2 PMDs
677 and future extensions:
679 * ``rte_event_dev_info``
680 * ``rte_event_dev_config``
681 * ``rte_event_port_conf``
683 * sched: Added new fields to ``struct rte_sched_subport_port_params``.
685 * lpm: Removed fields other than ``tbl24`` and ``tbl8`` from the struct
686 ``rte_lpm``. The removed fields were made internal.
692 .. This section should contain new known issues in this release. Sample format:
694 * **Add title in present tense with full stop.**
696 Add a short 1-2 sentence description of the known issue
697 in the present tense. Add information on any known workarounds.
699 This section is a comment. Do not overwrite or remove it.
700 Also, make sure to start the actual text at the margin.
701 =======================================================
707 .. This section should contain a list of platforms that were tested
712 * <vendor> platform with <vendor> <type of devices> combinations
717 * Other relevant details...
719 This section is a comment. Do not overwrite or remove it.
720 Also, make sure to start the actual text at the margin.
721 =======================================================