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 new API for rte_ring.**
71 * New synchronization modes for rte_ring.
73 Introduced new optional MT synchronization modes for rte_ring:
74 Relaxed Tail Sync (RTS) mode and Head/Tail Sync (HTS) mode.
75 With these mode selected, rte_ring shows significant improvements for
76 average enqueue/dequeue times on overcommitted systems.
78 * Added peek style API for rte_ring.
80 For rings with producer/consumer in RTE_RING_SYNC_ST, RTE_RING_SYNC_MT_HTS
81 mode, provide an ability to split enqueue/dequeue operation into two phases
82 (enqueue/dequeue start; enqueue/dequeue finish). That allows user to inspect
83 objects in the ring without removing them from it (aka MT safe peek).
85 * **Added flow aging support.**
87 Added flow aging support to detect and report aged-out flows, including:
89 * Added new action: ``RTE_FLOW_ACTION_TYPE_AGE`` to set the timeout
90 and the application flow context for each flow.
91 * Added new event: ``RTE_ETH_EVENT_FLOW_AGED`` for the driver to report
92 that there are new aged-out flows.
93 * Added new query: ``rte_flow_get_aged_flows`` to get the aged-out flows
94 contexts from the port.
96 * **Updated Amazon ena driver.**
98 Updated ena PMD with new features and improvements, including:
100 * Added support for large LLQ (Low-latency queue) headers.
101 * Added Tx drops as new extended driver statistic.
102 * Added support for accelerated LLQ mode.
103 * Handling of the 0 length descriptors on the Rx path.
105 * **Updated Intel i40e driver.**
107 Updated i40e PMD with new features and improvements, including:
109 * Enable MAC address as FDIR input set for ipv4-other, ipv4-udp and ipv4-tcp.
110 * Added support for RSS using L3/L4 source/destination only.
111 * Added support for setting hash function in rte flow.
113 * **Updated the Intel iavf driver.**
115 Update the Intel iavf driver with new features and improvements, including:
117 * Added generic filter support.
118 * Added advanced iavf with FDIR capability.
119 * Added advanced RSS configuration for VFs.
121 * **Updated the Intel ice driver.**
123 Updated the Intel ice driver with new features and improvements, including:
125 * Added support for DCF (Device Config Function) feature.
126 * Added switch filter support for intel DCF.
128 * **Updated Marvell OCTEON TX2 ethdev driver.**
130 Updated Marvell OCTEON TX2 ethdev driver with traffic manager support with
133 * Hierarchial Scheduling with DWRR and SP.
134 * Single rate - Two color, Two rate - Three color shaping.
136 * **Updated Mellanox mlx5 driver.**
138 Updated Mellanox mlx5 driver with new features and improvements, including:
140 * Added support for matching on IPv4 Time To Live and IPv6 Hop Limit.
141 * Added support for creating Relaxed Ordering Memory Regions.
142 * Added support for jumbo frame size (9K MTU) in Multi-Packet RQ mode.
143 * Optimized the memory consumption of flow.
145 * **Updated the AESNI MB crypto PMD.**
147 * Added support for intel-ipsec-mb version 0.54.
148 * Updated the AESNI MB PMD with AES-256 DOCSIS algorithm.
149 * Added support for synchronous Crypto burst API.
151 * **Updated the AESNI GCM crypto PMD.**
153 * Added support for intel-ipsec-mb version 0.54.
155 * **Added a new driver for Intel Foxville I225 devices.**
157 Added the new ``igc`` net driver for Intel Foxville I225 devices. See the
158 :doc:`../nics/igc` NIC guide for more details on this new driver.
160 * **Updated Broadcom bnxt driver.**
162 Updated Broadcom bnxt driver with new features and improvements, including:
164 * Added support for host based flow table management
165 * Added flow counters to extended stats
166 * Added PCI function stats to extended stats
168 * **Added handling of mixed crypto algorithms in QAT PMD for GEN2.**
170 Enabled handling of mixed algorithms in encrypted digest hash-cipher
171 (generation) and cipher-hash (verification) requests in QAT PMD
172 when running on GEN2 QAT hardware with particular firmware versions
173 (GEN3 support was added in DPDK 20.02).
175 * **Added plain SHA-1,224,256,384,512 support to QAT PMD.**
177 Added support for plain SHA-1, SHA-224, SHA-256, SHA-384 and SHA-512 hashes
180 * **Added QAT intermediate buffer too small handling in QAT compression PMD.**
182 Added a special way of buffer handling when internal QAT intermediate buffer
183 is too small for Huffman dynamic compression operation. Instead of falling
184 back to fixed compression, the operation is now split into multiple smaller
185 dynamic compression requests (possible to execute on QAT) and their results
186 are then combined and copied into the output buffer. This is not possible if
187 any checksum calculation was requested - in such case the code falls back to
188 fixed compression as before.
190 * **Updated the turbo_sw bbdev PMD.**
192 Supported large size code blocks which does not fit in one mbuf segment.
194 * **Added Intel FPGA_5GNR_FEC bbdev PMD.**
196 Added a new ``fpga_5gnr_fec`` bbdev driver for the Intel\ |reg| FPGA PAC
197 (Programmable Acceleration Card) N3000. See the
198 :doc:`../bbdevs/fpga_5gnr_fec` BBDEV guide for more details on this new driver.
200 * **Updated ipsec-secgw sample application with following features.**
202 * Updated ipsec-secgw application to add event based packet processing.
203 The worker thread(s) would receive events and submit them back to the
204 event device after the processing. This way, multicore scaling and HW
205 assisted scheduling is achieved by making use of the event device
206 capabilities. The event mode currently supports only inline IPsec
209 * Updated ipsec-secgw application to support key sizes for AES-192-CBC,
210 AES-192-GCM, AES-256-GCM algorithms.
212 * Added IPsec inbound load-distribution support for ipsec-secgw application
213 using NIC load distribution feature(Flow Director).
215 * **Added rte_graph library.**
217 Graph architecture abstracts the data processing functions as a ``node`` and
218 ``links`` them together to create a complex ``graph`` to enable reusable/modular
219 data processing functions. The graph library provides API to enable graph
220 framework operations such as create, lookup, dump and destroy on graph and node
221 operations such as clone, edge update, and edge shrink, etc.
222 The API also allows to create the stats cluster to monitor per graph and per node stats.
224 * **Added rte_node library which consists of a set of packet processing nodes.**
226 The rte_node library that consists of nodes used by rte_graph library. Each
227 node performs a specific packet processing function based on application
228 configuration. The following nodes are added:
230 * Null node: Skeleton node that defines the general structure of a node.
231 * Ethernet device node: Consists of ethernet Rx/Tx nodes as well as ethernet
233 * IPv4 lookup node: Consists of ipv4 extract and lpm lookup node. Routes can
234 be configured by the application through ``rte_node_ip4_route_add`` function.
235 * IPv4 rewrite node: Consists of ipv4 and ethernet header rewrite functionality
236 that can be configured through ``rte_node_ip4_rewrite_add`` function.
237 * Packet drop node: Frees the packets received to their respective mempool.
239 * **Added new l3fwd-graph sample application.**
241 Added an example application ``l3fwd-graph``. It demonstrates the usage of graph
242 library and node library for packet processing. In addition to the library usage
243 demonstration, this application can use for performance comparison with existing
244 ``l3fwd`` (The static code without any nodes) with the modular ``l3fwd-graph``
251 .. This section should contain removed items in this release. Sample format:
253 * Add a short 1-2 sentence description of the removed item
256 This section is a comment. Do not overwrite or remove it.
257 Also, make sure to start the actual text at the margin.
258 =========================================================
264 .. This section should contain API changes. Sample format:
266 * sample: Add a short 1-2 sentence description of the API change
267 which was announced in the previous releases and made in this release.
268 Start with a scope label like "ethdev:".
269 Use fixed width quotes for ``function_names`` or ``struct_names``.
272 This section is a comment. Do not overwrite or remove it.
273 Also, make sure to start the actual text at the margin.
274 =========================================================
276 * mempool: The API of ``rte_mempool_populate_iova()`` and
277 ``rte_mempool_populate_virt()`` changed to return 0 instead of -EINVAL
278 when there is not enough room to store one object.
284 .. This section should contain ABI changes. Sample format:
286 * sample: Add a short 1-2 sentence description of the ABI change
287 which was announced in the previous releases and made in this release.
288 Start with a scope label like "ethdev:".
289 Use fixed width quotes for ``function_names`` or ``struct_names``.
292 This section is a comment. Do not overwrite or remove it.
293 Also, make sure to start the actual text at the margin.
294 =========================================================
296 * No ABI change that would break compatibility with DPDK 20.02 and 19.11.
302 .. This section should contain new known issues in this release. Sample format:
304 * **Add title in present tense with full stop.**
306 Add a short 1-2 sentence description of the known issue
307 in the present tense. Add information on any known workarounds.
309 This section is a comment. Do not overwrite or remove it.
310 Also, make sure to start the actual text at the margin.
311 =========================================================
317 .. This section should contain a list of platforms that were tested
322 * <vendor> platform with <vendor> <type of devices> combinations
327 * Other relevant details...
329 This section is a comment. Do not overwrite or remove it.
330 Also, make sure to start the actual text at the margin.
331 =========================================================