4 .. **Read this first.**
6 The text 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: ``LIKE_THIS``.
12 Build the docs and view the output file to ensure the changes are correct::
16 firefox build/doc/html/guides/rel_notes/release_16_07.html
22 .. This section should contain new features added in this release. Sample format:
24 * **Add a title in the past tense with a full stop.**
26 Add a short 1-2 sentence description in the past tense. The description
27 should be enough to allow someone scanning the release notes to understand
30 If the feature adds a lot of sub-features you can use a bullet list like this.
32 * Added feature foo to do something.
33 * Enhanced feature bar to do something else.
35 Refer to the previous release notes for examples.
37 * **Removed mempool cache if not needed.**
39 The size of the mempool structure is reduced if the per-lcore cache is disabled.
41 * **Added mempool external cache for non-EAL thread.**
43 Added new functions to create, free or flush a user-owned mempool
44 cache for non-EAL threads. Previously, cache was always disabled
47 * **Changed the memory allocation in mempool library.**
49 * Added ability to allocate a large mempool in virtually fragmented memory.
50 * Added new APIs to populate a mempool with memory.
51 * Added an API to free a mempool.
52 * Modified the API of rte_mempool_obj_iter() function.
53 * Dropped specific Xen Dom0 code.
54 * Dropped specific anonymous mempool code in testpmd.
56 * **Added new driver for Broadcom NetXtreme-C devices.**
58 Added the new bnxt driver for Broadcom NetXtreme-C devices. See the
59 "Network Interface Controller Drivers" document for more details on this
62 * **Added new driver for ThunderX nicvf device.**
64 * **Added mailbox interrupt support for ixgbe and igb VFs.**
66 When the physical NIC link comes down or up, the PF driver will send a
67 mailbox message to notify each VF. To handle this link up/down event,
68 add mailbox interrupts support to receive the message and allow the app to
69 register a callback for it.
71 * **Updated the ixgbe base driver.**
73 The ixgbe base driver was updated with changes including the
76 * Added sgmii link for X550.
77 * Added mac link setup for X550a SFP and SFP+.
78 * Added KR support for X550em_a.
79 * Added new phy definitions for M88E1500.
80 * Added support for the VLVF to be bypassed when adding/removing a VFTA entry.
81 * Added X550a flow control auto negotiation support.
83 * **Updated the i40e base driver.**
85 Updated the i40e base driver, which includes support for new devices IDs.
87 * **Updated the enic driver.**
89 The enic driver was updated with changes including the following:
91 * Optimized the Tx function.
92 * Added Scattered Rx capability.
93 * Improved packet type identification.
94 * Added MTU update in non Scattered Rx mode and enabled MTU of up to 9208
95 with UCS Software release 2.2 on 1300 series VICs.
97 * **Supported virtio on IBM POWER8.**
99 The ioports are mapped in memory when using Linux UIO.
101 * **Virtio support for containers.**
103 Add a new virtual device, named virtio_user, to support virtio for containers.
107 * Control queue and multi-queue are not supported yet.
108 * Cannot work with --huge-unlink.
109 * Cannot work with --no-huge.
110 * Cannot work when there are more than VHOST_MEMORY_MAX_NREGIONS(8) hugepages.
111 * Root privilege is a must for sorting hugepages by physical address.
112 * Can only be used with vhost user backend.
114 * **Added vhost-user client mode.**
116 DPDK vhost-user could be the server as well as the client. It supports
117 server mode only before, now it also supports client mode. Client mode
118 is enabled when ``RTE_VHOST_USER_CLIENT`` flag is set while calling
119 ``rte_vhost_driver_register``.
121 When DPDK vhost-user restarts from normal or abnormal quit (say crash),
122 the client mode would allow DPDK to establish the connect again. Note
123 that a brand new QEMU version (v2.7 or above) is needed, otherwise, the
124 reconnect won't work.
126 DPDK vhost-user will also try to reconnect by default when
128 * the first connect fails (when QEMU is not started yet)
129 * the connection is broken (when QEMU restarts)
131 It can be turned off if flag ``RTE_VHOST_USER_NO_RECONNECT`` is set.
133 * **Added NSH packet recognition in i40e.**
135 * **Added AES-CTR support to AESNI MB PMD.**
137 Now AESNI MB PMD supports 128/192/256-bit counter mode AES encryption and
140 * **Added support of AES counter mode for Intel QuickAssist devices.**
142 Enabled support for the AES CTR algorithm for Intel QuickAssist devices.
143 Provided support for algorithm-chaining operations.
145 * **Added KASUMI SW PMD.**
147 A new Crypto PMD has been added, which provides KASUMI F8 (UEA1) ciphering
148 and KASUMI F9 (UIA1) hashing.
150 * **Added multi-writer support for RTE Hash with Intel TSX.**
152 The following features/modifications have been added to rte_hash library:
154 * Enabled application developers to use an extra flag for rte_hash creation
155 to specify default behavior (multi-thread safe/unsafe) with rte_hash_add_key
157 * Changed Cuckoo search algorithm to breadth first search for multi-writer
158 routine and split Cuckoo Search and Move operations in order to reduce
159 transactional code region and improve TSX performance.
160 * Added a hash multi-writer test case for test app.
162 * **Improved IP Pipeline Application.**
164 The following features have been added to ip_pipeline application:
166 * Configure the MAC address in the routing pipeline and automatic routes
167 updates with change in link state.
168 * Enable RSS per network interface through the configuration file.
169 * Streamline the CLI code.
171 * **Added keepalive enhancements.**
173 Adds support for reporting of core states other than dead to
174 monitoring applications, enabling the support of broader liveness
175 reporting to external processes.
177 * **Added packet capture framework.**
179 * A new library ``librte_pdump`` is added to provide packet capture API.
180 * A new ``app/pdump`` tool is added to capture packets in DPDK.
183 * **Added floating VEB support for i40e PF driver.**
185 A "floating VEB" is a special Virtual Ethernet Bridge (VEB) which does not
186 have an upload port, but instead is used for switching traffic between
187 virtual functions (VFs) on a port.
189 For information on this feature, please see the "I40E Poll Mode Driver"
190 section of the "Network Interface Controller Drivers" document.
196 .. This section should contain bug fixes added to the relevant sections. Sample format:
198 * **code/section Fixed issue in the past tense with a full stop.**
200 Add a short 1-2 sentence description of the resolved issue in the past tense.
201 The title should contain the code/lib section like a commit message.
202 Add the entries in alphabetic order in the relevant sections below.
208 * **igb_uio: Fixed possible mmap failure for Linux >= 4.5.**
210 mmaping the iomem range of the PCI device fails for kernels that
211 enabled CONFIG_IO_STRICT_DEVMEM option:
213 EAL: pci_map_resource():
214 cannot mmap(39, 0x7f1c51800000, 0x100000, 0x0):
215 Invalid argument (0xffffffffffffffff)
217 CONFIG_IO_STRICT_DEVMEM is introduced in Linux v4.5
219 Updated igb_uio to stop reserving PCI memory resources, from
220 kernel point of view iomem region looks like idle and mmap worked
221 again. This matches uio_pci_generic usage.
227 * **i40e: Fixed vlan stripping from inner header.**
229 Previously, for tunnel packets, such as VXLAN/NVGRE, the vlan
230 tags of the inner header will be stripped without putting vlan
232 Now this issue is fixed by disabling vlan stripping from inner header.
234 * **i40e: Fixed the type issue of a single VLAN type.**
236 Currently, if a single VLAN header is added in a packet, it's treated
237 as inner VLAN. But generally, a single VLAN header is treated as the
239 This issue is fixed by changing corresponding register for single VLAN.
241 * **enic: Fixed several issues when stopping then restarting ports and queues.**
243 Fixed several crashes related to stopping then restarting ports and queues.
244 Fixed possible crash when re-configuring the number of Rx queue descriptors.
246 * **enic: Fixed Rx data mis-alignment if mbuf data offset modified.**
248 Fixed possible Rx corruption when mbufs were returned to a pool with data
249 offset other than RTE_PKTMBUF_HEADROOM.
251 * **enic: Fixed Tx IP/UDP/TCP checksum offload and VLAN insertion.**
253 * **enic: Fixed Rx error and missed counters.**
259 * **mbuf: Fixed refcnt update when detaching.**
261 Fix the ``rte_pktmbuf_detach()`` function to decrement the direct
262 mbuf's reference counter. The previous behavior was not to affect
263 the reference counter. It lead a memory leak of the direct mbuf.
277 .. This section should contain new known issues in this release. Sample format:
279 * **Add title in present tense with full stop.**
281 Add a short 1-2 sentence description of the known issue in the present
282 tense. Add information on any known workarounds.
288 .. This section should contain API changes. Sample format:
290 * Add a short 1-2 sentence description of the API change. Use fixed width
291 quotes for ``rte_function_names`` or ``rte_struct_names``. Use the past tense.
293 * The following counters are removed from ``rte_eth_stats`` structure:
294 ibadcrc, ibadlen, imcasts, fdirmatch, fdirmiss,
295 tx_pause_xon, rx_pause_xon, tx_pause_xoff, rx_pause_xoff.
297 * The extended statistics are fetched by ids with ``rte_eth_xstats_get``
298 after a lookup by name ``rte_eth_xstats_get_names``.
300 * The function ``rte_eth_dev_info_get`` fill the new fields ``nb_rx_queues``
301 and ``nb_tx_queues`` in the structure ``rte_eth_dev_info``.
303 * The vhost function ``rte_vring_available_entries`` is renamed to
304 ``rte_vhost_avail_entries``.
306 * All existing vhost APIs and callbacks with ``virtio_net`` struct pointer
307 as the parameter have been changed due to the ABI refactoring mentioned
308 below: it's replaced by ``int vid``.
310 * The function ``rte_vhost_enqueue_burst`` no longer supports concurrent enqueuing
311 packets to the same queue.
313 * The function ``rte_eth_dev_set_mtu`` adds a new return value ``-EBUSY``, which
314 indicates the operation is forbidden because the port is running.
320 .. * Add a short 1-2 sentence description of the ABI change that was announced in
321 the previous releases and made in this release. Use fixed width quotes for
322 ``rte_function_names`` or ``rte_struct_names``. Use the past tense.
324 * The ``rte_port_source_params`` structure has new fields to support PCAP file.
325 It was already in release 16.04 with ``RTE_NEXT_ABI`` flag.
327 * The ``rte_eth_dev_info`` structure has new fields ``nb_rx_queues`` and ``nb_tx_queues``
328 to support number of queues configured by software.
330 * vhost ABI refactoring has been made: ``virtio_net`` structure is never
331 exported to application any more. Instead, a handle, ``vid``, has been
332 used to represent this structure internally.
335 Shared Library Versions
336 -----------------------
338 .. Update any library version updated in this release and prepend with a ``+`` sign.
340 The libraries prepended with a plus sign were incremented in this version.
348 librte_distributor.so.1
358 + librte_mempool.so.2
377 .. This section should contain a list of platforms that were tested with this
391 .. This section should contain a list of NICs that were tested with this release.