New Features
------------
-* **Introduce ARMv7 architecture**
+* **Introduce ARMv7 and ARMv8 architectures**
- It is now possible to build DPDK for the ARMv7 platform and test with
- virtual PMD drivers.
+ * It is now possible to build DPDK for the ARMv7 and ARMv8 platforms.
+ * ARMv7 can be tested with virtual PMD drivers.
+ * ARMv8 can be tested with virtual and physical PMD drivers.
* **Enabled freeing of ring.**
New function rte_ring_free() allows the user to free a ring
if it was created with rte_ring_create().
+* **Added keepalive support to EAL and example application.**
+
+* **Added experimental cryptodev API**
+
+ The cryptographic processing of packet is provided as a preview
+ with two drivers for:
+
+ * Intel QuickAssist devices
+ * Intel AES-NI multi-buffer library
+
+ Due to its experimental state, the API may change without prior notice.
+
* **Added ethdev API to support IEEE1588.**
Added functions to read, write and adjust system time in the NIC.
Like mlx4, this PMD is only available for Linux and is disabled by default
due to external dependencies (libibverbs and libmlx5).
+* **Added driver for Netronome nfp-6xxx card.**
+
+ Support for using Netronome nfp-6xxx with PCI VFs.
+
+* **Added virtual szedata2 driver for COMBO cards.**
+
+ Added virtual PMD for COMBO-100G and COMBO-80G cards.
+ PMD is disabled in default configuration.
+
* **Enhanced support for virtio driver.**
* Virtio ring layout optimization (fixed avail ring)
* **Added port hotplug support to xenvirt.**
+* **Added ethtool shim and sample application.**
+
+* **Added experimental performance thread example application.**
+
+ The application demonstrates L3 fowarding with different threading
+ models: pthreads, cgroups, or lighweight threads. The example inludes
+ a simple cooperative scheduler.
+
+ Due to its experimental state this application may change without notice.
+ The application is supported only for Linux x86_64.
+
Resolved Issues
---------------
VF needs the PF interrupt support initialized even if not started.
+* **igb: Fixed VF MAC address when using with DPDK PF.**
+
+ Assign a random MAC address in VF when not assigned by PF.
+
* **ixgbe: Fixed issue with X550 DCB.**
Fixed a DCB issue with x550 where for 8 TCs (Traffic Classes), if a packet
Fixed the issue of not freeing memzone in the call to free the memory for
adminq DMA.
+* **mlx: Fixed driver loading.**
+
+ The mlx drivers were unable to load when built as a shared library,
+ due to a missing symbol in mempool library.
+
* **vhost: Fixed Qemu shutdown.**
Fixed issue with libvirt ``virsh destroy`` not killing the VM.
Examples
~~~~~~~~
+* **l3fwd: Fixed crash with IPv6.**
+
+* **vhost_xen: Fixed compile error.**
+
Other
~~~~~
Known Issues
------------
+* Some drivers do not fill the packet type when receiving.
+ As the l3fwd example application requires this info, the i40e vector
+ driver must be disabled to benefit of the packet type with i40e.
+
API Changes
-----------
structures: rte_eth_dcb_rx_conf, rte_eth_dcb_tx_conf,
rte_eth_vmdq_dcb_conf, rte_eth_vmdq_dcb_tx_conf.
+* The rte_eth_rx_queue_count() function now returns "int" instead of "uint32_t"
+ to allow the use of negative values as error codes on return.
+
* The function rte_eal_pci_close_one() is removed.
It was replaced by rte_eal_pci_detach().
* The devargs union field virtual is renamed to virt for C++ compatibility.
-
ABI Changes
-----------
* The new fields rx_desc_lim and tx_desc_lim are added into rte_eth_dev_info
structure.
+* For debug builds, the functions rte_eth_rx_burst(), rte_eth_tx_burst()
+ rte_eth_rx_descriptor_done() and rte_eth_rx_queue_count() will
+ no longer be separate functions in the DPDK libraries. Instead, they will
+ only be present in the rte_ethdev.h header file.
+
* The maximum number of queues per port CONFIG_RTE_MAX_QUEUES_PER_PORT is
increased to 1024.
* librte_table LPM: A new parameter to hold the table name will be added to
the LPM table parameter structure.
+* librte_table hash: The key mask parameter is added to the hash table
+ parameter structure for 8-byte key and 16-byte key extendible bucket
+ and LRU tables.
+
* librte_port: Macros to access the packet meta-data stored within the packet
buffer has been adjusted to cover the packet mbuf structure.
+ librte_mbuf.so.2
librte_mempool.so.1
librte_meter.so.1
- librte_pipeline.so.1
+ + librte_pipeline.so.2
librte_pmd_bond.so.1
+ librte_pmd_ring.so.2
+ librte_port.so.2