Bug Fixes History

Warning

This section includes history of bug fixes of 3 major releases back. For older releases history, please refer to the relevant firmware versions Release Notes inhttps://docs.mellanox.com/category/adapterfw.

Internal Ref.

Issue

2648336

Description: Disabled the CNP counter “rp_cnp_ignored " (triggered by OOS (out-of-sequence)) when all ports are IB.

Note: For mixed IB/ETH scenario, the behavior depends on the RoCE configuration, the counter on the IB port may still increase but will not affect the regular use.

Keywords: CNP counter, IB

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2178949

Description: Improved PortXmitWait IB counter accuracy.

Keywords: Counters

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2641734

Description: Fixed the rate select mechanism in QSFP modules.

Keywords: Cables

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2600783

Description: Fixed classification issues for "Passive" cables to be more robust.

Keywords: Cables

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2574322

Description: Fixed an issue that occasionally caused some performance issues related to RC QPs using E2E-credits (not connected to SRQ and doing send/receive traffic) when the ROCE_ACCL tx_window was enabled.

Keywords: Bandwidth, performance

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2391109

Description: Fixed an issue that caused a fatal error, and eventually resulted in the HCA hanging when a packet was larger than a strided receive WQE that was being scattered.

Keywords: Strided RQ, MTU

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2569999

Description: Fixed a rare issue that caused RX pipe to hang.

Keywords: RX pipe

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2621704

Description: Fixed the resource number size (a 64 bit number) to avoid a scenario where it overwrote it with a 32 bit number and erased the high bits when de-allocating the resource number.

In this scenario, when two resource numbers had identical low 32 bits, and because the high bits were cleared, it resulted in the same idx. Consequently, when two idxes were identical, then it freed the same idx twice.

Keywords: Resource number size, free_4k page

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2619161

Description: Initialized the rate table in the static configuration so it will be configured at the link-not-up scenarios.

Keywords: RoCE, static configuration, rate table

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2589430

Description: CRT_DCR with index larger than 1 << 21 can collide with the CRT_SW_RESERVED address.

Keywords: DCR

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2447160

Description: In InfiniBand non-virtualization system, due to a corrupted steering root, traffic fails after a warm reboot.

Keywords: Steering, Traffic

Discovered in Version: 20.30.1004

Fixed in Release: 20.31.1014

2684071

Description: Changing the default host chaining buffer size or WQE size (HOST_CHAINING_DESCRIPTORS, HOST_CHAINING_TOTAL_BUFFER_SIZE) using NVconfig might result in driver initialization failure.

Keywords: Host chaining

Discovered in Version: 20.29.2002

Fixed in Release: 20.30.1004

2507096

Description: Removed the option to create unnecessary internal CNP operation for the Lossy ADP retransmission feature.

Keywords: RoCE, Lossy, Adp_retrans

Discovered in Version: 20.29.1016

Fixed in Release: 20.30.1004

2447334

Description: Fixed an issue related to unused port LEDs when no cable is connected to the adapter card.

Keywords: Cables, LEDs

Discovered in Version: 20.29.1016

Fixed in Release: 20.30.1004

2444837

Description: Set the cap to 0 for high index functions to avoid too many parallel VF NODNIC functions.

Keywords: NODNIC, VF, ETH PXE

Discovered in Version: 20.29.1016

Fixed in Release: 20.30.1004

2292837

Description: Added to firmware the option to have an adaptive VL mapping based on the configuration of the remote peer.

Keywords: adaptive VL mapping

Discovered in Version: 20.29.1016

Fixed in Release: 20.29.2002

2411542

Description: Multi-APP QoS is not supported when LAG is configured.

Keywords: Multi-APP QoS, LAG

Discovered in Version: 20.29.1016

Fixed in Release: 20.29.2002

2339971

Description: Fixed an issue that prevented MCAM from reporting support for MFBA, MFBE, MFPA registry keys although they were available through the CMDIF interface.

Keywords: MCAM

Discovered in Version: 20.29.1016

Fixed in Release: 20.29.2002

2434292

Description: Fixed an issue with the MFS1S00-HxxxE cable that resulted in invalid firmware version display.

Keywords: Cables

Discovered in Version: 20.29.1016

Fixed in Release: 20.29.2002

2410395

Description: Fixed an issue that prevented a SFP28 cable from linking up in a 25GbE speed.

Keywords: Cables

Discovered in Version: 20.29.1016

Fixed in Release: 20.29.2002

2385117

Description: Modified the calculation of NUM_VF_MSIX to take into account NVME, Virtio Net/Blk, HotPlug PFs & VFs. Since max_total_msix is the maximum number used for all PFs and VFs (Port, NVME. Virtio Net/Blk, HotPlug), if there are not enough MSIX for all the devices, the number of port VF MSIX may be lowered (less than NUM_VF_MSIX) in order to not exceed the max_total_msix.

Note: In case of compatibility issues with ab old driver requiring more than 4 MSI-X, you should consider lowering number of PFs/VFs on any of the configurable functions (NVME. Virtio Net/Blk).

Keywords: MSIX

Discovered in Version: 20.29.1016

Fixed in Release: 20.29.2002

2360496

Description: Changed the default value of DCQCN's NP parameter min_time_between_cnps to 4 on all devices to support larger scalability of cluster.

Keywords: RoCE, Congestion control, DCQCN

Discovered in Version: 20.28.1002

Fixed in Release: 20.29.1016

2245422

Description: 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.

Keywords: SR-IOV

Discovered in Version: 20.28.1002

Fixed in Release: 20.29.1016

2200824

Description: Fixed an issue that prevented VXLAN packets with svlan/cvlan tag from being matched.

Keywords: VXLAN

Discovered in Version: 20.28.4000

Fixed in Release: 20.29.1016

2355328

Description: Fixed an issue that caused the eth_wqe_too_small counter to count ODP page faults.

Keywords: Counters

Discovered in Version: 20.28.4000

Fixed in Release: 20.29.1016

2281266

Description: Fixed an issue related to raising 100GbE link on ConnectX-6 VPI 100Gb/s adapter cards.

Keywords: Link up

Discovered in Version: 20.28.2006

Fixed in Release: 20.29.1016

2245422

Description: 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.

Keywords: SR-IOV

Discovered in Version: 20.28.1002

Fixed in Release: 20.29.1016

2282225/2241765

Description: Fixed an issue that resulted in low performance after enabling the RoCE Accelerator capability.

Note: The fix is available when all ports are set as Ethernet.

Keywords: Performance, RoCE

Discovered in Version: 20.28.1002

Fixed in Release: 20.29.1016

2330700

Description: Effective BER may be observed when connecting to SN3700 switch system which can impact the link up time to be up to 97sec.

Keywords: Effective BER

Discovered in Version: 20.28.4000

Fixed in Release: 20.29.1016

2199939

Description: High linkup time may be experienced when connecting to an H3C switch using 25GbE\50GbE\100GbE link speeds.

Keywords: Linkup time, switch

Discovered in Version: 20.28.1002

Fixed in Release: 20.29.1016

2252559

Description: On rare cases, a fatal error related to errors from the PCI transport layer might be reported during FLR.

Keywords: FLR, PCI transport layer, errors

Discovered in Version: 20.26.1040

Fixed in Release: 20.29.1016

2321713

Description: 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.

Keywords: IRISC, firmware semaphore,

Discovered in Version: 20.28.1002

Fixed in Release: 20.28.4000

2200443

Description: On very rare occasions, a raw BER of 10e-12 might be experienced.

Keywords: Raw BER

Discovered in Version: 20.28.1002

Fixed in Release: 20.28.4000

2244412

Description: ConnectX-6 Lx does not support phyless reset.

Keywords: Phyless reset

Discovered in Version: 20.28.1002

Fixed in Release: 20.28.4000

2215104

Description: Updated the following Mellanox OEM NC-SI commands to fix an issue that caused the "Port swap" capability not to function properly:

  • Get Temperature

  • Get Module Serial Data

  • Set Module Serial Data

Keywords: Port swap

Discovered in Version: 20.28.1002

Fixed in Release: 20.28.2006

2080917

Description: Fixed and issue that resulted in driver startup failure when working in pass-through mode and dual port devices.

Keywords: Pass-through mode, dual port devices

Discovered in Version: 20.28.1002

Fixed in Release: 20.28.2006

2073222

Description: In rare cases, HDR active copper cable link up time might be higher than expected (up to 2 minutes).

Keywords: Cables

Discovered in Version: 20.27.1016

Fixed in Release: 20.28.1002

2149674

Description: Fixed an issue that caused packets to get stuck when the Rate Limiter was enabled.

Keywords: Rate Limiter

Discovered in Version: 20.27.6008

Fixed in Release: 20.28.1002

2197232

Description: Active SHARP SAT QPs (QP with packet-based e2e credits) can break the live-FW-patch flow and result in firmware getting stuck.

Keywords: SHARP SAT QPs

Discovered in Version: 20.27.6008

Fixed in Release: 20.28.1002

2113608

Description: Fixed an issue that prevented a QP with ATS buffer from being using by the NVMF offload.

Keywords: ATS, NVMF offload

Discovered in Version: 20.27.6008

Fixed in Release: 20.28.1002

© Copyright 2023, NVIDIA. Last updated on May 23, 2023.