+* **Added support for GCC 11 and clang 12.**
+
+ Added support for building with GCC 11.1.1 and clang 12.0.0.
+
+* **Added support for Alpine Linux with musl libc.**
+
+ Added initial support for building DPDK, without modification,
+ on Alpine Linux using musl libc and busybox.
+
+* **Added phase-fair lock.**
+
+ Added support for a Phase-fair lock. This provides fairness guarantees.
+ It has two ticket pools, one for readers and one for writers.
+
+* **Added support for Marvell CN10K SoC drivers.**
+
+ Added Marvell CN10K SoC support. Marvell CN10K SoCs are based on the Octeon 10
+ family of ARM64 processors with the ARM Neoverse N2 core with accelerators for
+ packet processing, timers, cryptography, etc.
+
+ * Added common/cnxk driver consisting of a common API to be used by
+ net, crypto and event PMDs.
+ * Added mempool/cnxk driver which provides the support for the integrated
+ mempool device.
+ * Added event/cnxk driver which provides the support for the integrated event
+ device.
+
+* **Added enhanced ethdev representor syntax.**
+
+ * Introduced representor type of VF, SF and PF.
+ * Added support for sub-function and multi-host in representor syntax::
+
+ representor=# [0,2-4] /* Legacy VF compatible. */
+ representor=[[c#]pf#]vf# c1pf2vf3 /* VF 3 on PF 2 of controller 1. */
+ representor=[[c#]pf#]sf# sf[0,2-1023] /* 1023 SFs. */
+ representor=[c#]pf# c2pf[0,1] /* 2 PFs on controller 2. */
+
+* **Added queue state in queried Rx/Tx queue info.**
+
+ * Added new field ``queue_state`` to the ``rte_eth_rxq_info`` structure to
+ provide the indicated Rx queue state.
+ * Added new field ``queue_state`` to the ``rte_eth_txq_info`` structure to
+ provide the indicated Tx queue state.
+
+* **Updated meter API.**
+
+ * Added packet mode in the meter profile parameters data structures
+ to support metering traffic by packet per second (PPS),
+ in addition to the initial bytes per second (BPS) mode (value 0).
+ * Added support for pre-defined meter policy via flow action list per color.
+
+* **Added packet integrity match to flow rules.**
+
+ * Added ``RTE_FLOW_ITEM_TYPE_INTEGRITY`` flow item.
+ * Added ``rte_flow_item_integrity`` data structure.
+
+* **Added TCP connection tracking offload in flow API.**
+
+ * Added conntrack item and action for stateful connection offload.
+
+* **Updated Amazon ENA PMD.**
+
+ The new driver version (v2.3.0) introduced bug fixes and improvements,
+ including:
+
+ * Changed ``memcpy()`` mapping to the dpdk-optimized version.
+ * Updated ena_com (HAL) to the latest version.
+ * Added indication of the RSS hash presence in the mbuf.
+
+* **Updated Arkville PMD driver.**
+
+ Updated Arkville net driver with new features and improvements, including:
+
+ * Generalized passing meta data between PMD and FPGA, allowing up to 20
+ bytes of user specified information in RX and TX paths.
+
+ * Updated dynamic PMD extensions API using standardized names.
+
+ * Added support for new Atomic Rules PCI device IDs ``0x100f, 0x1010, 0x1017,
+ 0x1018, 0x1019``.
+
+* **Updated Broadcom bnxt driver.**
+
+ * Updated HWRM structures to 1.10.2.15 version.
+
+* **Updated Hisilicon hns3 driver.**
+
+ * Added support for module EEPROM dumping.
+ * Added support for freeing Tx mbuf on demand.
+ * Added support for copper port in Kunpeng930.
+ * Added support for runtime config to select IO burst function.
+ * Added support for outer UDP checksum in Kunpeng930.
+ * Added support for query Tx descriptor status.
+ * Added support for query Rx descriptor status.
+ * Added support for IEEE 1588 PTP.
+
+* **Updated Intel iavf driver.**
+
+ Updated the Intel iavf driver with new features and improvements, including:
+
+ * Added flow filter to support GTPU inner L3/L4 field matching.
+ * In AVX512 code, added the new RX and TX paths to use the HW offload
+ features. When the HW offload features are configured to be used, the
+ offload paths are chosen automatically. In parallel the support for HW
+ offload features was removed from the legacy AVX512 paths.
+
+* **Updated Intel ice driver.**
+
+ * Added Intel ice support on Windows.
+ * Added GTPU TEID support for DCF switch filter.
+ * Added flow priority support for DCF switch filter.
+
+* **Updated Marvell OCTEON TX2 ethdev driver.**
+
+ * Added support for flow action port id.
+
+* **Updated Mellanox mlx5 driver.**
+
+ Updated the Mellanox mlx5 driver with new features and improvements, including:
+
+ * Added support for matching on packet integrity status.
+ * Added support for VXLAN and NVGRE encap as sample actions.
+ * Added support for flow COUNT action handle.
+ * Support push VLAN on ingress traffic and pop VLAN on egress traffic in E-Switch mode.
+ * Added support for pre-defined meter policy API.
+ * Added support for ASO (Advanced Steering Operation) meter.
+ * Added support for ASO metering by PPS (packet per second).
+ * Added support for the monitor policy of Power Management API.
+ * Added support for connection tracking.
+ * Added support for Sub-Function representors.
+
+* **Updated NXP DPAA driver.**
+
+ * Added support for shared ethernet interface.
+ * Added support for external buffers in Tx.
+
+* **Updated NXP DPAA2 driver.**
+
+ * Added support for traffic management.
+ * Added support for configurable Tx confirmation.
+ * Added support for external buffers in Tx.
+
+* **Updated Wangxun txgbe driver.**
+
+ * Added support for txgbevf PMD.
+ * Support device arguments to handle AN training for backplane NICs.
+ * Added support for VXLAN-GPE.
+
+* **Enabled vmxnet3 PMD on Windows.**
+
+* **Enabled libpcap-based PMD on Windows.**
+
+ Enabled libpcap-based PMD support on Windows.
+ A libpcap distribution, such as Npcap or WinPcap, is required to run the PMD.
+
+* **Updated the AF_XDP driver.**
+
+ * Added support for preferred busy polling.
+
+* **Added support for vhost async packed ring data path.**
+
+ Added packed ring support for async vhost.
+
+* **Added support of multiple data-units in the cryptodev API.**
+
+ The cryptodev library has been enhanced to allow operations on multiple
+ data-units for the AES-XTS algorithm. The data-unit length should be set in the
+ transformation. A capability for it was added too.
+
+* **Added a cryptodev feature flag to support cipher wrapped keys.**
+
+ A new feature flag has been added to allow applications to provide
+ cipher wrapped keys in session xforms.
+
+* **Updated the OCTEON TX crypto PMD.**
+
+ * Added support for ``DIGEST_ENCRYPTED`` mode in the OCTEON TX crypto PMD.
+
+* **Updated the OCTEON TX2 crypto PMD.**
+
+ * Added support for ``DIGEST_ENCRYPTED`` mode in OCTEON TX2 crypto PMD.
+ * Added support in lookaside protocol offload mode for IPsec with
+ UDP encapsulation support for NAT Traversal.
+ * Added support in lookaside protocol offload mode for IPsec with
+ IPv4 transport mode.
+
+* **Updated Intel QuickAssist compression PMD.**
+
+ * The compression is now available on all QAT GEN3 devices
+ that support it in hardware.
+
+* **Updated Mellanox RegEx PMD.**
+
+ * Added support for multi-segments mbuf.
+
+* **Introduced period timer mode in eventdev timer adapter.**
+
+ * Added support for periodic timer mode in eventdev timer adapter.
+ * Added support for periodic timer mode in octeontx2 event device driver.
+
+* **Added event device vector capability.**
+
+ * Added the ``rte_event_vector`` data structure which is capable of holding
+ multiple ``uintptr_t`` of the same flow thereby allowing applications
+ to vectorize their pipelines and also reduce the complexity of pipelining
+ the events across multiple stages.
+ * This also reduced the scheduling overhead on a event device.
+
+* **Enhanced crypto adapter forward mode.**
+
+ * Added ``rte_event_crypto_adapter_enqueue()`` API to enqueue events to the
+ crypto adapter if forward mode is supported by the driver.
+ * Added support for crypto adapter forward mode in octeontx2 event and crypto
+ device driver.
+
+* **Updated Intel DLB2 driver.**
+
+ * Added support for the DLB v2.5 device.
+
+* **Added Predictable RSS functionality to the Toeplitz hash library.**
+
+ Added feature for finding collisions of the Toeplitz hash function -
+ the hash function used in NICs to spread the traffic among the queues.
+ It can be used to get predictable mapping of the flows.
+