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::
22 xdg-open build/doc/html/guides/rel_notes/release_20_05.html
28 .. This section should contain new features added in this release.
31 * **Add a title in the past tense with a full stop.**
33 Add a short 1-2 sentence description in the past tense.
34 The description should be enough to allow someone scanning
35 the release notes to understand the new feature.
37 If the feature adds a lot of sub-features you can use a bullet list
40 * Added feature foo to do something.
41 * Enhanced feature bar to do something else.
43 Refer to the previous release notes for examples.
45 Suggested order in release notes items:
46 * Core libs (EAL, mempool, ring, mbuf, buses)
47 * Device abstraction libs and PMDs
49 - cryptodev (lib, PMDs)
50 - eventdev (lib, PMDs)
53 * Apps, Examples, Tools (if significant)
55 This section is a comment. Do not overwrite or remove it.
56 Also, make sure to start the actual text at the margin.
57 =========================================================
59 * **Added Trace Library and Tracepoints**
61 A native implementation of ``common trace format(CTF)`` based trace library
62 has been added to provide the ability to add tracepoints in
63 application/library to get runtime trace/debug information for control and
64 fast APIs with minimum impact on fast path performance.
65 Typical trace overhead is ~20 cycles and instrumentation overhead is 1 cycle.
66 Added tracepoints in ``EAL``, ``ethdev``, ``cryptodev``, ``eventdev`` and
67 ``mempool`` libraries for important functions.
69 * **Added APIs for RCU defer queue.**
71 Added APIs to create and delete defer queue. Additional APIs are provided
72 to enqueue a deleted resource and reclaim the resource in the future.
73 These APIs help the application use lock-free data structures with
76 * **Added new API for rte_ring.**
78 * New synchronization modes for rte_ring.
80 Introduced new optional MT synchronization modes for rte_ring:
81 Relaxed Tail Sync (RTS) mode and Head/Tail Sync (HTS) mode.
82 With these mode selected, rte_ring shows significant improvements for
83 average enqueue/dequeue times on overcommitted systems.
85 * Added peek style API for rte_ring.
87 For rings with producer/consumer in RTE_RING_SYNC_ST, RTE_RING_SYNC_MT_HTS
88 mode, provide an ability to split enqueue/dequeue operation into two phases
89 (enqueue/dequeue start; enqueue/dequeue finish). That allows user to inspect
90 objects in the ring without removing them from it (aka MT safe peek).
92 * **Added flow aging support.**
94 Added flow aging support to detect and report aged-out flows, including:
96 * Added new action: ``RTE_FLOW_ACTION_TYPE_AGE`` to set the timeout
97 and the application flow context for each flow.
98 * Added new event: ``RTE_ETH_EVENT_FLOW_AGED`` for the driver to report
99 that there are new aged-out flows.
100 * Added new query: ``rte_flow_get_aged_flows`` to get the aged-out flows
101 contexts from the port.
103 * **ethdev: Added a new value to link speed for 200Gbps**
105 * **Updated Amazon ena driver.**
107 Updated ena PMD with new features and improvements, including:
109 * Added support for large LLQ (Low-latency queue) headers.
110 * Added Tx drops as new extended driver statistic.
111 * Added support for accelerated LLQ mode.
112 * Handling of the 0 length descriptors on the Rx path.
114 * **Updated Hisilicon hns3 driver.**
116 Updated Hisilicon hns3 driver with new features and improvements, including:
118 * Added support for TSO
119 * Added support for configuring promiscuous and allmulticast mode for VF
121 * **Updated Intel i40e driver.**
123 Updated i40e PMD with new features and improvements, including:
125 * Enable MAC address as FDIR input set for ipv4-other, ipv4-udp and ipv4-tcp.
126 * Added support for RSS using L3/L4 source/destination only.
127 * Added support for setting hash function in rte flow.
129 * **Updated the Intel iavf driver.**
131 Update the Intel iavf driver with new features and improvements, including:
133 * Added generic filter support.
134 * Added advanced iavf with FDIR capability.
135 * Added advanced RSS configuration for VFs.
137 * **Updated the Intel ice driver.**
139 Updated the Intel ice driver with new features and improvements, including:
141 * Added support for DCF (Device Config Function) feature.
142 * Added switch filter support for intel DCF.
144 * **Updated Marvell OCTEON TX2 ethdev driver.**
146 Updated Marvell OCTEON TX2 ethdev driver with traffic manager support with
149 * Hierarchial Scheduling with DWRR and SP.
150 * Single rate - Two color, Two rate - Three color shaping.
152 * **Updated Mellanox mlx5 driver.**
154 Updated Mellanox mlx5 driver with new features and improvements, including:
156 * Added support for matching on IPv4 Time To Live and IPv6 Hop Limit.
157 * Added support for creating Relaxed Ordering Memory Regions.
158 * Added support for configuring Hairpin queue data buffer size.
159 * Added support for jumbo frame size (9K MTU) in Multi-Packet RQ mode.
160 * Removed flow rules caching for memory saving and compliance with ethdev API.
161 * Optimized the memory consumption of flow.
162 * Added support for flow aging based on hardware counter.
163 * Added support for flow pattern with wildcard VLAN item (without VID value).
164 * Updated support for matching on GTP header, added match on GTP flags.
166 * **Added Chacha20-Poly1305 algorithm to Cryptodev API.**
168 Chacha20-Poly1305 AEAD algorithm can now be supported in Cryptodev.
170 * **Updated the AESNI MB crypto PMD.**
172 * Added support for intel-ipsec-mb version 0.54.
173 * Updated the AESNI MB PMD with AES-256 DOCSIS algorithm.
174 * Added support for synchronous Crypto burst API.
176 * **Updated the AESNI GCM crypto PMD.**
178 * Added support for intel-ipsec-mb version 0.54.
180 * **Updated the ZUC crypto PMD.**
182 * Added support for intel-ipsec-mb version 0.54.
183 * Updated the PMD to support Multi-buffer ZUC-EIA3,
184 improving performance significantly, when using
185 intel-ipsec-mb version 0.54
187 * **Updated the SNOW3G crypto PMD.**
189 * Added support for intel-ipsec-mb version 0.54.
191 * **Updated the KASUMI crypto PMD.**
193 * Added support for intel-ipsec-mb version 0.54.
195 * **Added a new driver for Intel Foxville I225 devices.**
197 Added the new ``igc`` net driver for Intel Foxville I225 devices. See the
198 :doc:`../nics/igc` NIC guide for more details on this new driver.
200 * **Updated Broadcom bnxt driver.**
202 Updated Broadcom bnxt driver with new features and improvements, including:
204 * Added support for host based flow table management
205 * Added flow counters to extended stats
206 * Added PCI function stats to extended stats
208 * **Added handling of mixed crypto algorithms in QAT PMD for GEN2.**
210 Enabled handling of mixed algorithms in encrypted digest hash-cipher
211 (generation) and cipher-hash (verification) requests in QAT PMD
212 when running on GEN2 QAT hardware with particular firmware versions
213 (GEN3 support was added in DPDK 20.02).
215 * **Added plain SHA-1,224,256,384,512 support to QAT PMD.**
217 Added support for plain SHA-1, SHA-224, SHA-256, SHA-384 and SHA-512 hashes
220 * **Added AES-GCM/GMAC J0 support to QAT PMD.**
222 Added support for AES-GCM/GMAC J0 to Intel QuickAssist Technology PMD. User can
223 use this feature by passing zero length IV in appropriate xform. For more
224 info please refer to rte_crypto_sym.h J0 comments.
226 * **Updated the QAT PMD for AES-256 DOCSIS.**
228 Added AES-256 DOCSIS algorithm support to QAT PMD.
230 * **Added QAT intermediate buffer too small handling in QAT compression PMD.**
232 Added a special way of buffer handling when internal QAT intermediate buffer
233 is too small for Huffman dynamic compression operation. Instead of falling
234 back to fixed compression, the operation is now split into multiple smaller
235 dynamic compression requests (possible to execute on QAT) and their results
236 are then combined and copied into the output buffer. This is not possible if
237 any checksum calculation was requested - in such case the code falls back to
238 fixed compression as before.
240 * **Updated the turbo_sw bbdev PMD.**
242 Supported large size code blocks which does not fit in one mbuf segment.
244 * **Added Intel FPGA_5GNR_FEC bbdev PMD.**
246 Added a new ``fpga_5gnr_fec`` bbdev driver for the Intel\ |reg| FPGA PAC
247 (Programmable Acceleration Card) N3000. See the
248 :doc:`../bbdevs/fpga_5gnr_fec` BBDEV guide for more details on this new driver.
250 * **Updated the DSW event device.**
252 Updated the DSW PMD with new features and improvements, including:
254 * Improved flow migration mechanism, allowing faster and more
255 accurate load balancing.
256 * Improved behavior on high-core count systems.
257 * Reduced latency in low-load situations.
258 * Extended DSW xstats with migration- and load-related statistics.
260 * **Updated ipsec-secgw sample application with following features.**
262 * Updated ipsec-secgw application to add event based packet processing.
263 The worker thread(s) would receive events and submit them back to the
264 event device after the processing. This way, multicore scaling and HW
265 assisted scheduling is achieved by making use of the event device
266 capabilities. The event mode currently supports only inline IPsec
269 * Updated ipsec-secgw application to support key sizes for AES-192-CBC,
270 AES-192-GCM, AES-256-GCM algorithms.
272 * Added IPsec inbound load-distribution support for ipsec-secgw application
273 using NIC load distribution feature(Flow Director).
275 * **Updated Telemetry Library.**
277 The updated Telemetry library has many improvements on the original version
278 to make it more accessible and scalable:
280 * It enables DPDK libraries and applications provide their own specific
281 telemetry information, rather than being limited to what could be reported
282 through the metrics library.
284 * It is no longer dependent on the external Jansson library, which allows
285 Telemetry be enabled by default.
287 * The socket handling has been simplified making it easier for clients to
288 connect and retrieve information.
290 * **Added rte_graph library.**
292 Graph architecture abstracts the data processing functions as a ``node`` and
293 ``links`` them together to create a complex ``graph`` to enable reusable/modular
294 data processing functions. The graph library provides API to enable graph
295 framework operations such as create, lookup, dump and destroy on graph and node
296 operations such as clone, edge update, and edge shrink, etc.
297 The API also allows to create the stats cluster to monitor per graph and per node stats.
299 * **Added rte_node library which consists of a set of packet processing nodes.**
301 The rte_node library that consists of nodes used by rte_graph library. Each
302 node performs a specific packet processing function based on application
303 configuration. The following nodes are added:
305 * Null node: Skeleton node that defines the general structure of a node.
306 * Ethernet device node: Consists of ethernet Rx/Tx nodes as well as ethernet
308 * IPv4 lookup node: Consists of ipv4 extract and lpm lookup node. Routes can
309 be configured by the application through ``rte_node_ip4_route_add`` function.
310 * IPv4 rewrite node: Consists of ipv4 and ethernet header rewrite functionality
311 that can be configured through ``rte_node_ip4_rewrite_add`` function.
312 * Packet drop node: Frees the packets received to their respective mempool.
314 * **Added new l3fwd-graph sample application.**
316 Added an example application ``l3fwd-graph``. It demonstrates the usage of graph
317 library and node library for packet processing. In addition to the library usage
318 demonstration, this application can use for performance comparison with existing
319 ``l3fwd`` (The static code without any nodes) with the modular ``l3fwd-graph``
322 * **Updated testpmd application.**
324 * Added a new cmdline option ``--rx-mq-mode`` which can be used to test PMD's
325 behaviour on handling Rx mq mode.
327 * **Added support for GCC 10.**
329 Added support for building with GCC 10.1.
335 .. This section should contain removed items in this release. Sample format:
337 * Add a short 1-2 sentence description of the removed item
340 This section is a comment. Do not overwrite or remove it.
341 Also, make sure to start the actual text at the margin.
342 =========================================================
348 .. This section should contain API changes. Sample format:
350 * sample: Add a short 1-2 sentence description of the API change
351 which was announced in the previous releases and made in this release.
352 Start with a scope label like "ethdev:".
353 Use fixed width quotes for ``function_names`` or ``struct_names``.
356 This section is a comment. Do not overwrite or remove it.
357 Also, make sure to start the actual text at the margin.
358 =========================================================
360 * mempool: The API of ``rte_mempool_populate_iova()`` and
361 ``rte_mempool_populate_virt()`` changed to return 0 instead of -EINVAL
362 when there is not enough room to store one object.
368 .. This section should contain ABI changes. Sample format:
370 * sample: Add a short 1-2 sentence description of the ABI change
371 which was announced in the previous releases and made in this release.
372 Start with a scope label like "ethdev:".
373 Use fixed width quotes for ``function_names`` or ``struct_names``.
376 This section is a comment. Do not overwrite or remove it.
377 Also, make sure to start the actual text at the margin.
378 =========================================================
380 * No ABI change that would break compatibility with DPDK 20.02 and 19.11.
386 .. This section should contain new known issues in this release. Sample format:
388 * **Add title in present tense with full stop.**
390 Add a short 1-2 sentence description of the known issue
391 in the present tense. Add information on any known workarounds.
393 This section is a comment. Do not overwrite or remove it.
394 Also, make sure to start the actual text at the margin.
395 =========================================================
401 .. This section should contain a list of platforms that were tested
406 * <vendor> platform with <vendor> <type of devices> combinations
411 * Other relevant details...
413 This section is a comment. Do not overwrite or remove it.
414 Also, make sure to start the actual text at the margin.
415 =========================================================