4 .. **Read this first.**
6 The text in the sections below explains how to update the release notes.
8 Use proper spelling, capitalization and punctuation in all sections.
10 Variable and config names should be quoted as fixed width text:
13 Build the docs and view the output file to ensure the changes are correct::
17 xdg-open build/doc/html/guides/rel_notes/release_18_05.html
23 .. This section should contain new features added in this release. Sample
26 * **Add a title in the past tense with a full stop.**
28 Add a short 1-2 sentence description in the past tense. The description
29 should be enough to allow someone scanning the release notes to
30 understand the new feature.
32 If the feature adds a lot of sub-features you can use a bullet list like
35 * Added feature foo to do something.
36 * Enhanced feature bar to do something else.
38 Refer to the previous release notes for examples.
40 This section is a comment. Do not overwrite or remove it.
41 Also, make sure to start the actual text at the margin.
42 =========================================================
44 * **Added bucket mempool driver.**
46 Added bucket mempool driver which provides a way to allocate contiguous
48 Number of objects in the block depends on how many objects fit in
49 RTE_DRIVER_MEMPOOL_BUCKET_SIZE_KB memory chunk which is build time option.
50 The number may be obtained using rte_mempool_ops_get_info() API.
51 Contiguous blocks may be allocated using rte_mempool_get_contig_blocks() API.
53 * **Added PMD-recommended Tx and Rx parameters**
55 Applications can now query drivers for device-tuned values of
56 ring sizes, burst sizes, and number of queues.
58 * **Added RSS hash and key update to CXGBE PMD.**
60 Support to update RSS hash and key has been added to CXGBE PMD.
62 * **Added CXGBE VF PMD.**
64 CXGBE VF Poll Mode Driver has been added to run DPDK over Chelsio
65 T5/T6 NIC VF instances.
67 * **Updated Solarflare network PMD.**
69 Updated the sfc_efx driver including the following changes:
71 * Added support for Solarflare XtremeScale X2xxx family adapters.
72 * Added support for NVGRE, VXLAN and GENEVE filters in flow API.
73 * Added support for DROP action in flow API.
75 * **Added Ethernet poll mode driver for AMD XGBE devices.**
77 Added the new ``axgbe`` ethernet poll mode driver for AMD XGBE devices.
78 See the :doc:`../nics/axgbe` nic driver guide for more details on this
81 * **Updated szedata2 PMD.**
83 Added support for new NFB-200G2QL card.
85 * **Added support for Broadcom NetXtreme-S (BCM58800) family of controllers (aka Stingray)**
87 The BCM58800 devices feature a NetXtreme E-Series advanced network controller, a high-performance
88 ARM CPU block, PCI Express (PCIe) Gen3 interfaces, key accelerators for compute offload and a high-
89 speed memory subsystem including L3 cache and DDR4 interfaces, all interconnected by a coherent
90 Network-on-chip (NOC) fabric.
92 The ARM CPU subsystem features eight ARMv8 Cortex-A72 CPUs at 3.0 GHz, arranged in a multi-cluster
95 * **Added IFCVF vDPA driver.**
97 Added IFCVF vDPA driver to support Intel FPGA 100G VF device. IFCVF works
98 as a HW vhost data path accelerator, it supports live migration and is
99 compatible with virtio 0.95 and 1.0. This driver registers ifcvf vDPA driver
100 to vhost lib, when virtio connected, with the help of the registered vDPA
101 driver the assigned VF gets configured to Rx/Tx directly to VM's virtio
104 * **Added support for virtio-user server mode.**
105 In a container environment if the vhost-user backend restarts, there's no way
106 for it to reconnect to virtio-user. To address this, support for server mode
107 is added. In this mode the socket file is created by virtio-user, which the
108 backend connects to. This means that if the backend restarts, it can reconnect
109 to virtio-user and continue communications.
111 * **Added crypto workload support to vhost library.**
113 New APIs are introduced in vhost library to enable virtio crypto support
114 including session creation/deletion handling and translating virtio-crypto
115 request into DPDK crypto operations. A sample application is also introduced.
117 * **Added virtio crypto PMD.**
119 Added a new poll mode driver for virtio crypto devices, which provides
120 AES-CBC ciphering and AES-CBC with HMAC-SHA1 algorithm-chaining. See the
121 :doc:`../cryptodevs/virtio` crypto driver guide for more details on
124 * **Added AMD CCP Crypto PMD.**
126 Added the new ``ccp`` crypto driver for AMD CCP devices. See the
127 :doc:`../cryptodevs/ccp` crypto driver guide for more details on
130 * **Updated AESNI MB PMD.**
132 The AESNI MB PMD has been updated with additional support for:
134 * AES-CMAC (128-bit key).
136 * **Added the Event Timer Adapter Library.**
138 The Event Timer Adapter Library extends the event-based model by introducing
139 APIs that allow applications to arm/cancel event timers that generate
140 timer expiry events. This new type of event is scheduled by an event device
141 along with existing types of events.
143 * **Added device event monitor framework.**
145 Added a general device event monitor framework at EAL, for device dynamic management.
146 Such as device hotplug awareness and actions adopted accordingly. The list of new APIs:
148 * ``rte_dev_event_monitor_start`` and ``rte_dev_event_monitor_stop`` are for
149 the event monitor enable and disable.
150 * ``rte_dev_event_callback_register`` and ``rte_dev_event_callback_unregister``
151 are for the user's callbacks register and unregister.
153 Linux uevent is supported as backend of this device event notification framework.
155 * **Added support for procinfo and pdump on eth vdev.**
157 For ethernet virtual devices (like tap, pcap, etc), with this feature, we can get
158 stats/xstats on shared memory from secondary process, and also pdump packets on
159 those virtual devices.
165 .. This section should contain API changes. Sample format:
167 * Add a short 1-2 sentence description of the API change. Use fixed width
168 quotes for ``rte_function_names`` or ``rte_struct_names``. Use the past
171 This section is a comment. Do not overwrite or remove it.
172 Also, make sure to start the actual text at the margin.
173 =========================================================
175 * service cores: no longer marked as experimental.
177 The service cores functions are no longer marked as experimental, and have
178 become part of the normal DPDK API and ABI. Any future ABI changes will be
179 announced at least one release before the ABI change is made. There are no
180 ABI breaking changes planned.
182 * eal: ``rte_lcore_has_role()`` return value changed.
184 This function now returns true or false, respectively,
185 rather than 0 or <0 for success or failure.
186 It makes use of the function more intuitive.
188 * mempool: capability flags and related functions have been removed.
190 Flags ``MEMPOOL_F_CAPA_PHYS_CONTIG`` and
191 ``MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS`` were used by octeontx mempool
192 driver to customize generic mempool library behaviour.
193 Now the new driver callbacks ``calc_mem_size`` and ``populate`` may be
194 used to achieve it without specific knowledge in the generic code.
196 * mempool: xmem functions have been deprecated:
198 - ``rte_mempool_xmem_create``
199 - ``rte_mempool_xmem_size``
200 - ``rte_mempool_xmem_usage``
201 - ``rte_mempool_populate_iova_tab``
203 * mbuf: The control mbuf API has been removed in v18.05. The impacted
204 functions and macros are:
206 - ``rte_ctrlmbuf_init()``
207 - ``rte_ctrlmbuf_alloc()``
208 - ``rte_ctrlmbuf_free()``
209 - ``rte_ctrlmbuf_data()``
210 - ``rte_ctrlmbuf_len()``
211 - ``rte_is_ctrlmbuf()``
214 The packet mbuf API should be used as a replacement.
216 * meter: updated to accommodate configuration profiles.
218 The meter API is changed to support meter configuration profiles. The
219 configuration profile represents the set of configuration parameters
220 for a given meter object, such as the rates and sizes for the token
221 buckets. These configuration parameters were previously the part of meter
222 object internal data strcuture. The separation of the configuration
223 parameters from meter object data structure results in reducing its
224 memory footprint which helps in better cache utilization when large number
225 of meter objects are used.
227 * ethdev: The function ``rte_eth_dev_count``, often mis-used to iterate
228 over ports, is deprecated and replaced by ``rte_eth_dev_count_avail``.
229 There is also a new function ``rte_eth_dev_count_total`` to get the
230 total number of allocated ports, available or not.
231 The hotplug-proof applications should use ``RTE_ETH_FOREACH_DEV`` or
232 ``RTE_ETH_FOREACH_DEV_OWNED_BY`` as port iterators.
234 * ethdev, in struct ``struct rte_eth_dev_info``, field ``rte_pci_device *pci_dev``
235 replaced with field ``struct rte_device *device``.
237 * **Changes to semantics of rte_eth_dev_configure() parameters.**
239 If both the ``nb_rx_q`` and ``nb_tx_q`` parameters are zero,
240 ``rte_eth_dev_configure`` will now use PMD-recommended queue sizes, or if
241 recommendations are not provided by the PMD the function will use ethdev
242 fall-back values. Previously setting both of the parameters to zero would
243 have resulted in ``-EINVAL`` being returned.
245 * **Changes to semantics of rte_eth_rx_queue_setup() parameters.**
247 If the ``nb_rx_desc`` parameter is zero, ``rte_eth_rx_queue_setup`` will
248 now use the PMD-recommended Rx ring size, or in the case where the PMD
249 does not provide a recommendation, will use an ethdev-provided
250 fall-back value. Previously, setting ``nb_rx_desc`` to zero would have
251 resulted in an error.
253 * **Changes to semantics of rte_eth_tx_queue_setup() parameters.**
255 If the ``nb_tx_desc`` parameter is zero, ``rte_eth_tx_queue_setup`` will
256 now use the PMD-recommended Tx ring size, or in the case where the PMD
257 does not provide a recoomendation, will use an ethdev-provided
258 fall-back value. Previously, setting ``nb_tx_desc`` to zero would have
259 resulted in an error.
261 * ethdev: several changes were made to the flow API.
263 * Unused DUP action was removed.
264 * Actions semantics in flow rules: list order now matters ("first
265 to last" instead of "all simultaneously"), repeated actions are now
266 all performed, and they do not individually have (non-)terminating
268 * Flow rules are now always terminating unless a PASSTHRU action is
270 * C99-style flexible arrays were replaced with standard pointers in RSS
271 action and in RAW pattern item structures due to compatibility issues.
272 * The RSS action was modified to not rely on external
273 ``struct rte_eth_rss_conf`` anymore to instead expose its own and more
274 appropriately named configuration fields directly
275 (``rss_conf->rss_key`` => ``key``,
276 ``rss_conf->rss_key_len`` => ``key_len``,
277 ``rss_conf->rss_hf`` => ``types``,
278 ``num`` => ``queue_num``), and the addition of missing RSS parameters
279 (``func`` for RSS hash function to apply and ``level`` for the
280 encapsulation level).
286 .. This section should contain ABI changes. Sample format:
288 * Add a short 1-2 sentence description of the ABI change that was announced
289 in the previous releases and made in this release. Use fixed width quotes
290 for ``rte_function_names`` or ``rte_struct_names``. Use the past tense.
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 * ring: the alignment constraints on the ring structure has been relaxed
297 to one cache line instead of two, and an empty cache line padding is
298 added between the producer and consumer structures. The size of the
299 structure and the offset of the fields remains the same on platforms
300 with 64B cache line, but change on other platforms.
302 * mempool: ops have changed.
304 A new callback ``calc_mem_size`` has been added to ``rte_mempool_ops``
305 to allow to customize required memory size calculation.
306 A new callback ``populate`` has been added to ``rte_mempool_ops``
307 to allow to customize objects population.
308 Callback ``get_capabilities`` has been removed from ``rte_mempool_ops``
309 since its features are covered by ``calc_mem_size`` and ``populate``
311 Callback ``register_memory_area`` has been removed from ``rte_mempool_ops``
312 since the new callback ``populate`` may be used instead of it.
314 * **Additional fields in rte_eth_dev_info.**
316 The ``rte_eth_dev_info`` structure has had two extra entries appended to the
317 end of it: ``default_rxportconf`` and ``default_txportconf``. Each of these
318 in turn are ``rte_eth_dev_portconf`` structures containing three fields of
319 type ``uint16_t``: ``burst_size``, ``ring_size``, and ``nb_queues``. These
320 are parameter values recommended for use by the PMD.
322 * ethdev: ABI for all flow API functions was updated.
324 This includes functions ``rte_flow_copy``, ``rte_flow_create``,
325 ``rte_flow_destroy``, ``rte_flow_error_set``, ``rte_flow_flush``,
326 ``rte_flow_isolate``, ``rte_flow_query`` and ``rte_flow_validate``, due to
327 changes in error type definitions (``enum rte_flow_error_type``), removal
328 of the unused DUP action (``enum rte_flow_action_type``), modified
329 behavior for flow rule actions (see API changes), removal of C99 flexible
330 array from RAW pattern item (``struct rte_flow_item_raw``) and complete
331 rework of the RSS action definition (``struct rte_flow_action_rss``).
337 .. This section should contain removed items in this release. Sample format:
339 * Add a short 1-2 sentence description of the removed item in the past
342 This section is a comment. Do not overwrite or remove it.
343 Also, make sure to start the actual text at the margin.
344 =========================================================
350 .. This section should contain new known issues in this release. Sample format:
352 * **Add title in present tense with full stop.**
354 Add a short 1-2 sentence description of the known issue in the present
355 tense. Add information on any known workarounds.
357 This section is a comment. Do not overwrite or remove it.
358 Also, make sure to start the actual text at the margin.
359 =========================================================
361 * **pdump is not compatible with old applications.**
363 As we changed to use generic multi-process communication for pdump negotiation
364 instead of previous dedicated unix socket way, pdump applications, including
365 dpdk-pdump example and any other applications using librte_pdump, cannot work
366 with older version DPDK primary applications.
369 Shared Library Versions
370 -----------------------
372 .. Update any library version updated in this release and prepend with a ``+``
376 + librte_cfgfile.so.2
379 This section is a comment. Do not overwrite or remove it.
380 =========================================================
383 The libraries prepended with a plus sign were incremented in this version.
389 librte_bitratestats.so.2
391 librte_bus_fslmc.so.1
396 + librte_common_octeontx.so.1
397 librte_cryptodev.so.4
398 librte_distributor.so.1
402 librte_flow_classify.so.1
410 librte_latencystats.so.1
413 + librte_mempool.so.4
423 librte_pmd_ixgbe.so.2
425 librte_pmd_softnic.so.1
426 librte_pmd_vhost.so.2
442 .. This section should contain a list of platforms that were tested with this
447 * <vendor> platform with <vendor> <type of devices> combinations
452 * Other relevant details...
454 This section is a comment. Do not overwrite or remove it.
455 Also, make sure to start the actual text at the margin.
456 =========================================================