NVIDIA Mellanox MCX516A-GCAT SmartNIC Firmware 16.29.1016

Firmware which is added at the time of manufacturing, is used to run user programs on the device and can be thought of as the software that allows hardware to run. Embedded firmware is used to control the functions of various hardware devices and systems, much like a computer’s operating system (OS) controls the function of software applications. Firmware may be written into read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory. 

Important Notes:
- Security Hardening Enhancements: This release contains important reliability improvements and security hardening enhancements. Mellanox recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
- When upgrading or changing the configuration on multi-host adapter cards, for the changes to take effect, PCIe restart must be simultaneously sent from both hosts (servers).
- SR-IOV - Virtual Functions (VF) per Port - The maximum Virtual Functions (VF) per port is 127.
- It is recommended to enable the “above 4G decoding” BIOS setting for features that require large amount of PCIe resources. Such features are: SR-IOV with numerous VFs, PCIe Emulated Switch, and Large BAR Requests.

Changes and New Features:

- Added the option to allow applications to build their own QoS tree over the NIC hierarchy by connecting QPs to responder/requestor Queue Groups.
- Added "InfiniBand" properties set to the Network Device Function Redfish object.
- Added HW support for Flow Metering to utilize Advanced Steering Operation (ASO). HW Flow Meter allows higher scale, more accuracy, and better performance compare to the FW Flow Metering.
- Added trust level for VFs. Once the VF is trusted, it will get a set of trusted capabilities.
- Added 2 new Mini CQE formats: Responder Mini CQE With Flow Tag Layout and Responder Mini CQE With l3_l4_info Layout
- UCX can now enable AR by exposing Out-Of-Ordering bitmask per SL with "ooo_per_sl" field in the HCA_VPORT context. It can be also queried by running the QUERY_HCA_VPORT_CONTEXT command.
- Added support for steering DP hash flow groups.
- Added a new counter per vPort that counts the number of packets that reached the Ethernet RQ but cannot fit into the WQE due to their large size. Additionally, we added the option to control if such packet will cause “CQE with Error” or “CQE_MOCK”.
- PCIe Rx modifications to prevent the adapter cards from disappearing from the system.
- ignore_flow_level is now enabled by the TRUST LEVEL access registry.
- Added support for the cq_overrun counter. The counter represents the number of times CQs enter an error state due to overflow that occur when the device tries to post a CQE into a full CQ buffer.
- [Beta] Enabled the capability to allow Virtual Functions to send Pause Frames packets.
- Enabled 10/25GbE auto-sensing with 3rd party when using 10/25GbE optical cables.
- Hardware steering dump output used for debugging and troubleshooting.

Bug Fixes:

- Fixed a rare race condition that caused an erroneous write to the firmware image during certain power-down scenarios. This resulted in firmware being recognized as corrupted and prevented the adapter card from being recognized by the system due to missing valid Flash images.
- Changed the default value of DCQCN's NP parameter min_time_between_cnps to 4 on all devices to support larger scalability of cluster.
- Fixed an issue that prevented VXLAN packets with svlan/cvlan tag from being matched.
- Fixed an issue that caused the eth_wqe_too_small counter to count ODP page faults.
- When MKEY_BY_NAME is enabled by NVCONFIG and a large number of VFs are configured, VM restart (VF/PF FLR) will take longer than when MKEY_BY_NAME is disabled.
- Fixed an issue that resulted in low performance after enabling the RoCE Accelerator capability.
- On rare cases, a fatal error related to errors from the PCI transport layer might be reported during FLR.
- Fixed the chassis manager calculation for Multi-Host and Socket-Direct adapter cards to allow running NC-SI commands by the chassis manager BMC. Now the chassis manager is count as BMC with index 0, regardless of how many BMC there are.
- Fixed an issue that caused caused the device to go to dead IRISC as one of the firmware semaphores could not be released when a speed change or port state change was triggered.

About Network Adapter Drivers:

When connected, the operating system usually installs a generic driver that helps the computer to recognize the newly attached device.

However, proper software must be applied if you want to make use of all features that the network adapter has available. This task also allows computers to properly recognize all device characteristics such as manufacturer, chipset, technology, and others.

Updating the adapter's drivers and utilities version might improve overall performance and stability, increase transfer speeds, fix different compatibility problems and several network-related errors, as well as bring various other changes.

To install this release, simply get the package, extract it if necessary, run the setup, and follow the instructions displayed on-screen. When done, don't forget to perform a system restart and reconnect the network adapter to make sure that all changes take effect properly.

Without further ado, if you intend to apply this version, click the download button and install the package. Moreover, check with our website as often as possible so that you don't miss a single new release.