1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright 2018 The DPDK contributors
7 .. **Read this first.**
9 The text in the sections below explains how to update the release notes.
11 Use proper spelling, capitalization and punctuation in all sections.
13 Variable and config names should be quoted as fixed width text:
16 Build the docs and view the output file to ensure the changes are correct::
20 xdg-open build/doc/html/guides/rel_notes/release_19_02.html
26 .. This section should contain new features added in this release.
29 * **Add a title in the past tense with a full stop.**
31 Add a short 1-2 sentence description in the past tense.
32 The description should be enough to allow someone scanning
33 the release notes to understand the new feature.
35 If the feature adds a lot of sub-features you can use a bullet list
38 * Added feature foo to do something.
39 * Enhanced feature bar to do something else.
41 Refer to the previous release notes for examples.
43 Suggested order in release notes items:
44 * Core libs (EAL, mempool, ring, mbuf, buses)
45 * Device abstraction libs and PMDs
47 - cryptodev (lib, PMDs)
48 - eventdev (lib, PMDs)
51 * Apps, Examples, Tools (if significant)
53 This section is a comment. Do not overwrite or remove it.
54 Also, make sure to start the actual text at the margin.
55 =========================================================
57 * **Added support to free hugepages exactly as originally allocated.**
59 Some applications using memory event callbacks (especially for managing
60 RDMA memory regions) require that memory be freed back to the system
61 exactly as it was originally allocated. These applications typically
62 also require that a malloc allocation not span across two separate
63 hugepage allocations. A new ``--match-allocations`` EAL init flag has
64 been added to fulfill both of these requirements.
66 * **Added API to register external memory in DPDK.**
68 A new ``rte_extmem_register``/``rte_extmem_unregister`` API was added to allow
69 chunks of external memory to be registered with DPDK without adding them to
72 * **Support for using virtio-user without hugepages**
74 The --no-huge mode was augmented to use memfd-backed memory (on systems that
75 support memfd), to allow using virtio-user-based NICs without hugepages.
77 * **Release of the ENA PMD v2.0.0**
79 * Added Low Latency Queue v2 (LLQv2). This feature reduces the latency
80 of the packets by pushing the header directly through the PCI to the
81 device. This allows the NIC to start handle packet right after the doorbell
82 without waiting for DMA.
83 * Added independent configuration of HW Tx and Rx ring depths.
84 * Added support for up to 8k Rx descriptors per ring.
85 * Added additional doorbell check on Tx, to handle Tx more efficiently for big
87 * Added per queue statistics.
88 * Added extended statistics using xstats DPDK API.
89 * The reset routine was aligned with the DPDK API, so now it can be
90 handled as in other PMDs.
91 * Fixed out of order (OOO) completion.
92 * Fixed memory leaks due to port stops and starts in the middle of
94 * Updated documentation and features list of the PMD.
96 * **Updated mlx5 driver.**
98 Updated the mlx5 driver including the following changes:
100 * Fixed ``imissed`` counter to be reported through ``rte_eth_stats`` instead
101 of ``rte_eth_xstats``.
102 * Added packet header modification through Direct Verbs flow driver.
103 * Added ConnectX-6 PCI device ID to be proved by ``mlx5`` driver.
104 * Added flow counter support to Direct Verbs flow driver though DevX.
105 * Renamed build options for the glue layer to
106 ``CONFIG_RTE_IBVERBS_LINK_DLOPEN`` for make and ``ibverbs_link`` for meson.
107 * Added static linkage of ``mlx`` dependency.
108 * Improved stability of E-Switch flow driver.
109 * Added new make build configuration to set the cacheline size for Bluefield
110 correctly - ``arm64-bluefield-linuxapp-gcc``.
112 * **Updated the enic driver.**
114 * Added support for ``RTE_ETH_DEV_CLOSE_REMOVE`` flag.
115 * Added the handler to get firmware version string.
116 * Added support for multicast filtering.
118 * **Added dynamic queues allocation support for i40e VF.**
120 Previously, available queues of VF is reserved by PF at initialize stage.
121 Now both DPDK PF and Kernel PF (>=2.1.14) will support dynamic queue
122 allocation. At runtime, when VF request more queue number exceed the initial
123 reserved amount, PF can allocate up to 16 queues as the request after a VF
126 * **Added ICE net PMD**
128 Added the new ``ice`` net driver for IntelĀ® Ethernet Network Adapters E810.
129 See the :doc:`../nics/ice` NIC guide for more details on this new driver.
131 * **Added support for SW-assisted VDPA live migration.**
133 This SW-assisted VDPA live migration facility helps VDPA devices without
134 logging capability to perform live migration, a mediated SW relay can help
135 devices to track dirty pages caused by DMA. IFC driver has enabled this
136 SW-assisted live migration mode.
138 * **Added security checks to cryptodev symmetric session operations.**
140 Added a set of security checks to the access cryptodev symmetric session.
141 The checks include the session's user data read/write check and the
142 session private data referencing status check while freeing a session.
144 * **Updated the AESNI-MB PMD.**
146 * Add support for intel-ipsec-mb version 0.52.
147 * Add AES-GMAC algorithm support.
148 * Add Plain SHA1, SHA224, SHA256, SHA384, and SHA512 algorithms support.
150 * **Added IPsec Library.**
152 Added an experimental library ``librte_ipsec`` to provide ESP tunnel and
153 transport support for IPv4 and IPv6 packets.
155 The library provides support for AES-CBC ciphering and AES-CBC with HMAC-SHA1
156 algorithm-chaining, and AES-GCM and NULL algorithms only at present. It is
157 planned to add more algorithms in future releases.
159 See :doc:`../prog_guide/ipsec_lib` for more information.
161 * **Updated the ipsec-secgw sample application.**
163 The ``ipsec-secgw`` sample application has been updated to use the new
164 ``librte_ipsec`` library also added in this release.
165 The original functionality of ipsec-secgw is retained, a new command line
166 parameter ``-l`` has been added to ipsec-secgw to use the IPsec library,
167 instead of the existing IPsec code in the application.
169 The IPsec library does not support all the functionality of the existing
170 ipsec-secgw application, its is planned to add the outstanding functionality
173 See :doc:`../sample_app_ug/ipsec_secgw` for more information.
175 * **Enabled checksum support in the ISA-L compressdev driver.**
177 Added support for both adler and crc32 checksums in the ISA-L PMD.
178 This aids data integrity across both compression and decompression.
180 * **Added a compression performance test tool.**
182 Added a new performance test tool to test the compressdev PMD. The tool tests
183 compression ratio and compression throughput.
185 * **Added intel_pstate support to Power Management library.**
187 Previously, using the power management library required the
188 disabling of the intel_pstate kernel driver, and the enabling of the
189 acpi_cpufreq kernel driver. This is no longer the case, as the use of
190 the intel_pstate kernel driver is now supported, and automatically
191 detected by the library.
197 .. This section should contain removed items in this release. Sample format:
199 * Add a short 1-2 sentence description of the removed item
202 This section is a comment. Do not overwrite or remove it.
203 Also, make sure to start the actual text at the margin.
204 =========================================================
210 .. This section should contain API changes. Sample format:
212 * sample: Add a short 1-2 sentence description of the API change
213 which was announced in the previous releases and made in this release.
214 Start with a scope label like "ethdev:".
215 Use fixed width quotes for ``function_names`` or ``struct_names``.
218 This section is a comment. Do not overwrite or remove it.
219 Also, make sure to start the actual text at the margin.
220 =========================================================
222 * eal: Function ``rte_bsf64`` in ``rte_bitmap.h`` has been renamed to
223 ``rte_bsf64_safe`` and moved to ``rte_common.h``. A new ``rte_bsf64`` function
224 has been added in ``rte_common.h`` that follows convention set by existing
225 ``rte_bsf32`` function.
227 * eal: Segment fd API on Linux now sets error code to ``ENOTSUP`` in more cases
228 where segment fd API is not expected to be supported:
230 - On attempt to get segment fd for an externally allocated memory segment
231 - In cases where memfd support would have been required to provide segment
232 fd's (such as in-memory or no-huge mode)
234 * eal: Functions ``rte_malloc_dump_stats()``, ``rte_malloc_dump_heaps()`` and
235 ``rte_malloc_get_socket_stats()`` are no longer safe to call concurrently with
236 ``rte_malloc_heap_create()`` or ``rte_malloc_heap_destroy()`` function calls.
238 * mbuf: ``RTE_MBUF_INDIRECT()``, which was deprecated in 18.05, was replaced
239 with ``RTE_MBUF_CLONED()`` and removed in 19.02.
241 * sched: As result of the new format of the mbuf sched field, the
242 functions ``rte_sched_port_pkt_write()`` and
243 ``rte_sched_port_pkt_read_tree_path()`` got an additional parameter of
244 type ``struct rte_sched_port``.
246 * pdump: The ``rte_pdump_set_socket_dir()``, the parameter ``path`` of
247 ``rte_pdump_init()`` and enum ``rte_pdump_socktype`` were deprecated
248 since 18.05 and are removed in this release.
250 * cryptodev: The parameter ``session_pool`` in the function
251 ``rte_cryptodev_queue_pair_setup()`` is removed.
253 * cryptodev: a new function ``rte_cryptodev_sym_session_pool_create()`` is
254 introduced. This function is now mandatory when creating symmetric session
255 header mempool. Please note all crypto applications are required to use this
256 function from now on. Failed to do so will cause
257 ``rte_cryptodev_sym_session_create()`` function call return error.
263 .. This section should contain ABI changes. Sample format:
265 * sample: Add a short 1-2 sentence description of the ABI change
266 which was announced in the previous releases and made in this release.
267 Start with a scope label like "ethdev:".
268 Use fixed width quotes for ``function_names`` or ``struct_names``.
271 This section is a comment. Do not overwrite or remove it.
272 Also, make sure to start the actual text at the margin.
273 =========================================================
275 * mbuf: The format of the sched field of ``rte_mbuf`` has been changed
276 to include the following fields: ``queue ID``, ``traffic class``, ``color``.
278 * cryptodev: as shown in the the 18.11 deprecation notice, the structure
279 ``rte_cryptodev_qp_conf`` has been added two parameters of symmetric session
280 mempool and symmetric session private data mempool.
282 * cryptodev: as shown in the the 18.11 deprecation notice, the structure
283 ``rte_cryptodev_sym_session`` has been updated to contain more information
284 to ensure safely accessing the session and session private data.
286 * security: New field ``uint64_t opaque_data`` is added into
287 ``rte_security_session`` structure. That would allow upper layer to easily
288 associate/de-associate some user defined data with the security session.
291 Shared Library Versions
292 -----------------------
294 .. Update any library version updated in this release
295 and prepend with a ``+`` sign, like this:
301 This section is a comment. Do not overwrite or remove it.
302 =========================================================
304 The libraries prepended with a plus sign were incremented in this version.
310 librte_bitratestats.so.2
313 librte_bus_fslmc.so.2
314 librte_bus_ifpga.so.2
317 librte_bus_vmbus.so.2
320 librte_compressdev.so.1
321 + librte_cryptodev.so.6
322 librte_distributor.so.1
327 librte_flow_classify.so.1
335 librte_latencystats.so.1
349 librte_pmd_ixgbe.so.2
350 librte_pmd_dpaa2_qdma.so.1
352 librte_pmd_softnic.so.1
353 librte_pmd_vhost.so.2
360 + librte_security.so.2
369 .. This section should contain new known issues in this release. Sample format:
371 * **Add title in present tense with full stop.**
373 Add a short 1-2 sentence description of the known issue
374 in the present tense. Add information on any known workarounds.
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 * ``AVX-512`` support has been disabled for ``GCC`` builds when ``binutils 2.30``
381 is detected [1] because of a crash [2]. This can affect ``native`` machine type
382 build targets on the platforms that support ``AVX512F`` like ``Intel Skylake``
383 processors, and can cause a possible performance drop. The immediate workaround
384 is to use ``clang`` compiler on these platforms.
385 Initial workaround in DPDK v18.11 was to disable ``AVX-512`` support for ``GCC``
386 completely, but based on information on defect submitted to GCC community [3],
387 issue has been identified as ``binutils 2.30`` issue. Since currently only GCC
388 generates ``AVX-512`` instructions, the scope is limited to ``GCC`` and
391 - [1]: Commit ("mk: fix scope of disabling AVX512F support")
392 - [2]: https://bugs.dpdk.org/show_bug.cgi?id=97
393 - [3]: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88096
399 .. This section should contain a list of platforms that were tested
404 * <vendor> platform with <vendor> <type of devices> combinations
409 * Other relevant details...
411 This section is a comment. Do not overwrite or remove it.
412 Also, make sure to start the actual text at the margin.
413 =========================================================
415 * Intel(R) platforms with Intel(R) NICs combinations
419 * Intel(R) Atom(TM) CPU C3758 @ 2.20GHz
420 * Intel(R) Xeon(R) CPU D-1541 @ 2.10GHz
421 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
422 * Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz
423 * Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz
424 * Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz
425 * Intel(R) Xeon(R) Gold 6139 CPU @ 2.30GHz
435 * Red Hat Enterprise Linux Server release 7.4
436 * Red Hat Enterprise Linux Server release 7.5
447 * Intel(R) 82599ES 10 Gigabit Ethernet Controller
449 * Firmware version: 0x61bf0001
450 * Device id (pf/vf): 8086:10fb / 8086:10ed
451 * Driver version: 5.2.3 (ixgbe)
453 * Intel(R) Corporation Ethernet Connection X552/X557-AT 10GBASE-T
455 * Firmware version: 0x800003e7
456 * Device id (pf/vf): 8086:15ad / 8086:15a8
457 * Driver version: 4.4.6 (ixgbe)
459 * Intel(R) Ethernet Converged Network Adapter X710-DA4 (4x10G)
461 * Firmware version: 6.80 0x80003cc1
462 * Device id (pf/vf): 8086:1572 / 8086:154c
463 * Driver version: 2.7.26 (i40e)
465 * Intel(R) Corporation Ethernet Connection X722 for 10GbE SFP+ (4x10G)
467 * Firmware version: 3.33 0x80000fd5 0.0.0
468 * Device id (pf/vf): 8086:37d0 / 8086:37cd
469 * Driver version: 2.7.26 (i40e)
471 * Intel(R) Ethernet Converged Network Adapter XXV710-DA2 (2x25G)
473 * Firmware version: 6.80 0x80003d05
474 * Device id (pf/vf): 8086:158b / 8086:154c
475 * Driver version: 2.7.26 (i40e)
477 * Intel(R) Ethernet Converged Network Adapter XL710-QDA2 (2X40G)
479 * Firmware version: 6.80 0x80003cfb
480 * Device id (pf/vf): 8086:1583 / 8086:154c
481 * Driver version: 2.7.26 (i40e)
483 * Intel(R) Corporation I350 Gigabit Network Connection
485 * Firmware version: 1.63, 0x80000dda
486 * Device id (pf/vf): 8086:1521 / 8086:1520
487 * Driver version: 5.4.0-k (igb)
489 * Intel(R) platforms with Mellanox(R) NICs combinations
493 * Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
494 * Intel(R) Xeon(R) CPU E5-2697A v4 @ 2.60GHz
495 * Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
496 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
497 * Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
498 * Intel(R) Xeon(R) CPU E5-2640 @ 2.50GHz
499 * Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
503 * Red Hat Enterprise Linux Server release 7.6 (Maipo)
504 * Red Hat Enterprise Linux Server release 7.5 (Maipo)
505 * Red Hat Enterprise Linux Server release 7.4 (Maipo)
506 * Red Hat Enterprise Linux Server release 7.3 (Maipo)
507 * Red Hat Enterprise Linux Server release 7.2 (Maipo)
512 * SUSE Linux Enterprise Server 15
514 * MLNX_OFED: 4.4-2.0.1.0
515 * MLNX_OFED: 4.5-1.0.1.0
519 * Mellanox(R) ConnectX(R)-3 Pro 40G MCX354A-FCC_Ax (2x40G)
521 * Host interface: PCI Express 3.0 x8
522 * Device ID: 15b3:1007
523 * Firmware version: 2.42.5000
525 * Mellanox(R) ConnectX(R)-4 10G MCX4111A-XCAT (1x10G)
527 * Host interface: PCI Express 3.0 x8
528 * Device ID: 15b3:1013
529 * Firmware version: 12.24.1000 and above
531 * Mellanox(R) ConnectX(R)-4 10G MCX4121A-XCAT (2x10G)
533 * Host interface: PCI Express 3.0 x8
534 * Device ID: 15b3:1013
535 * Firmware version: 12.24.1000 and above
537 * Mellanox(R) ConnectX(R)-4 25G MCX4111A-ACAT (1x25G)
539 * Host interface: PCI Express 3.0 x8
540 * Device ID: 15b3:1013
541 * Firmware version: 12.24.1000 and above
543 * Mellanox(R) ConnectX(R)-4 25G MCX4121A-ACAT (2x25G)
545 * Host interface: PCI Express 3.0 x8
546 * Device ID: 15b3:1013
547 * Firmware version: 12.24.1000 and above
549 * Mellanox(R) ConnectX(R)-4 40G MCX4131A-BCAT/MCX413A-BCAT (1x40G)
551 * Host interface: PCI Express 3.0 x8
552 * Device ID: 15b3:1013
553 * Firmware version: 12.24.1000 and above
555 * Mellanox(R) ConnectX(R)-4 40G MCX415A-BCAT (1x40G)
557 * Host interface: PCI Express 3.0 x16
558 * Device ID: 15b3:1013
559 * Firmware version: 12.24.1000 and above
561 * Mellanox(R) ConnectX(R)-4 50G MCX4131A-GCAT/MCX413A-GCAT (1x50G)
563 * Host interface: PCI Express 3.0 x8
564 * Device ID: 15b3:1013
565 * Firmware version: 12.24.1000 and above
567 * Mellanox(R) ConnectX(R)-4 50G MCX414A-BCAT (2x50G)
569 * Host interface: PCI Express 3.0 x8
570 * Device ID: 15b3:1013
571 * Firmware version: 12.24.1000 and above
573 * Mellanox(R) ConnectX(R)-4 50G MCX415A-GCAT/MCX416A-BCAT/MCX416A-GCAT (2x50G)
575 * Host interface: PCI Express 3.0 x16
576 * Device ID: 15b3:1013
577 * Firmware version: 12.24.1000 and above
578 * Firmware version: 12.24.1000 and above
580 * Mellanox(R) ConnectX(R)-4 50G MCX415A-CCAT (1x100G)
582 * Host interface: PCI Express 3.0 x16
583 * Device ID: 15b3:1013
584 * Firmware version: 12.24.1000 and above
586 * Mellanox(R) ConnectX(R)-4 100G MCX416A-CCAT (2x100G)
588 * Host interface: PCI Express 3.0 x16
589 * Device ID: 15b3:1013
590 * Firmware version: 12.24.1000 and above
592 * Mellanox(R) ConnectX(R)-4 Lx 10G MCX4121A-XCAT (2x10G)
594 * Host interface: PCI Express 3.0 x8
595 * Device ID: 15b3:1015
596 * Firmware version: 14.24.1000 and above
598 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
600 * Host interface: PCI Express 3.0 x8
601 * Device ID: 15b3:1015
602 * Firmware version: 14.24.1000 and above
604 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
606 * Host interface: PCI Express 3.0 x16
607 * Device ID: 15b3:1017
608 * Firmware version: 16.24.1000 and above
610 * Mellanox(R) ConnectX(R)-5 Ex EN 100G MCX516A-CDAT (2x100G)
612 * Host interface: PCI Express 4.0 x16
613 * Device ID: 15b3:1019
614 * Firmware version: 16.24.1000 and above
616 * ARM platforms with Mellanox(R) NICs combinations
620 * Qualcomm ARM 1.1 2500MHz
624 * Red Hat Enterprise Linux Server release 7.5 (Maipo)
628 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
630 * Host interface: PCI Express 3.0 x8
631 * Device ID: 15b3:1015
632 * Firmware version: 14.24.0220
634 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
636 * Host interface: PCI Express 3.0 x16
637 * Device ID: 15b3:1017
638 * Firmware version: 16.24.0220
640 * Mellanox(R) BlueField SmartNIC
642 * Mellanox(R) BlueField SmartNIC MT416842 (2x25G)
644 * Host interface: PCI Express 3.0 x16
645 * Device ID: 15b3:a2d2
646 * Firmware version: 18.24.0328
648 * SoC ARM cores running OS:
650 * CentOS Linux release 7.4.1708 (AltArch)
651 * MLNX_OFED 4.4-2.5.9.0
653 * DPDK application running on ARM cores inside SmartNIC
655 * Power 9 platforms with Mellanox(R) NICs combinations
659 * POWER9 2.2 (pvr 004e 1202) 2300MHz
663 * Ubuntu 18.04.1 LTS (Bionic Beaver)
667 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
669 * Host interface: PCI Express 3.0 x16
670 * Device ID: 15b3:1017
671 * Firmware version: 16.23.1020
675 * MLNX_OFED_LINUX-4.5-1.0.1.0