Bug Fixes in This Version
Ref # | Issue |
4469496 |
Description: On some environments, when an application deletes all flow rules from a template table and then attempted to read flow rules to the same table, an error with |
Keyword: Flow rules | |
Detected in version: 2.9.2 | |
4391384 | Description: The UCX package is built without GDR copy support due to an unintended change in the build system that excluded CUDA. As a result, applications relying on GDR functionality in UCX are unable to use it. |
Keyword: GDR support; CUDA missing; build environment | |
Detected in version: 2.9.2 | |
4403063 |
Description: When the package |
Keyword: MFT; firmware | |
Detected in version: 2.9.2 | |
4259675 | Description: In rare cases, systems using shared receive queues (shared_rxq) may experience incorrect packet handling during high-throughput traffic. |
Keyword: Shared RXQ; packet corruption; routing error | |
Detected in version: 2.9.2 | |
4410028 | Description: On SLES 15 SP5 with kernel version 5.14.21-150500.55.68-default or later, installation of mlnx-ofa_kernel drivers fails to use weak-modules, causing the system to fall back to inbox OFED modules. This occurs because the kernel used to build the drivers (5.14.21-150500.53-default) did not include the mana_ib driver, while newer kernels do—triggering a weak-modules sanity check failure due to the missing replacement. |
Keyword: Weak modules; Kernel version mismatch; inbox driver conflict | |
Detected in version: 2.9.0 |
Ref # | Issue Description |
4728634 / 4648210 | Description: Fixed an issue preventing DNF/YUM upgrades of rebuilt mlnx-ofa_kernel-devel packages (via doca-kernel-support) due to version sorting errors. The rebuilt package now appends ".1" and the kernel version to ensure proper RPM comparison and smooth upgrades. |
Keywords: mlnx-ofa_kernel-devel package | |
Reported in version: 2.9.3 |
Ref # | Issue Description |
4403055 | Description: Repeated power cycles cause corruption in the EXT4 file system. |
Keywords: Power cycle; FS corruption | |
Reported in version: |
Ref # | Issue |
N/A | Description: N/A |
Reported in version: N/A |
| Internal Ref. | Issue |
| 4527750 / 4400949 | Description: Fixed an issue where the MCTP context was incorrectly cleared when a new message arrived over a different transport. |
| Keywords: MCTP | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4774378 / 3921355 | Description: Fixed a deadlock seen during stress traffic with small packets and modify actions, which could hang the SoC (e.g., testpmd with three SFs and hardware offload disabled). |
| Keywords: Firmware deadlock, small packets | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4507527 / 4518004 / 4633348 / 4662213 | Description: Fixed an issue where, after installing the fw-bundle, the DOCA installer could not query BMC/CEC versions, so doca-installer --show-running-fw failed to display that version information.. |
| Keywords: fw-bundle installation, BMC/CEC | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4507527 | Description: Fixed an issue where multiple "NCSI Error" messages could appear in the DPU BMC journalctl logs during boot. These messages have no functional impact. |
| Keywords: BMC | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4566988 / 4570720 | Description: Fixed an issue where the mlxconfig reset command resets the user's TLVs by swapping between NV_DATA0 and NV_DATA1 flash partitions, causing unnecessary flash wear. The reset now invalidates the TLVs directly, using the same approach as when resetting a single TLV. |
| Keywords: mlxconfig rese | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4719936 / 4731957 / 4575884 | Description: Fixed an issue where NV Config operations could hang or produce untracked register errors, and where flash operations longer than 2 seconds could trigger an unnecessary assert. Debug information has been added to help detect stuck NV Config operations and register access errors. |
| Keywords: Stability and diagnostic | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4370695 / 4656353 / 4739817 | Description: Fixed a corner case during warm reboot that could cause some TX lane elastic buffers to lose synchronization during link training. |
| Keywords: TX lane elastic buffers | |
| Discovered in Version: 32.43.2566 | |
| Fixed in Release: 32.43.4100 | |
| 4507579 / 4498670 | Description: Fixed an issue where destroying two emulation objects with the same VHCA ID could result in one destroy command returning syndrome 0xF3F880 due to a race condition. |
| Keywords: VHCA ID, syndrome 0xF3F880 | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4640489 | Description: Fixed an issue where the TX precoding state was changed to OFF during link cycle tests. TX precoding for LPO is now forced to remain ON. |
| Keywords: TX precoding state | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4641440 / 4636590 | Description: Fixed a bug that could trigger assert 0x8cad when ROCE_CC_STEERING_EXT is enabled and roce_cc_shaper_coalescing is set to DEST_IP or 5_TUPLE. |
| Keywords: assert 0x8cad | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 | |
| 4711949 / 4773333 / 4773334 | Description: Fixed an issue where, in older versions and under specific configurations, the MEMIC BAR size could be unaligned to 64 bytes. The software now treats the address as aligned down to a 64-byte boundary. |
| Keywords: MEMIC BAR size | |
| Discovered in Version: 32.43.2566 | |
| Fixed in Release: 32.43.4100 | |
| 4508525 / 4480427 | Description: Fixed incorrect calculation of start address and mode for the CQE buffer in DPA CQ, which could cause CQEs to be written to the wrong address when the buffer is not 4K-aligned and spans a second page boundary. |
| Keywords: CQ, CQE Buffer, DPA | |
| Discovered in Version: 32.43.2566 | |
| Fixed in Release: 32.43.4100 | |
| 4261968 | Description: Performing a FW reactivation when there is no pending image on the flash will cause the PLDM upgrade to fail on the first attempt. |
| Keywords: PLDM | |
| Discovered in Version: 32.43.2566 | |
| Fixed in Release: 32.43.4100 | |
| 4507527 / 4508401 | Description: During DPU BMC boot, users may observe multiple "NCSI Error" messages in the DPU BMC journalctl logs. These messages have no functional impact. |
| Keywords: BMC | |
| Discovered in Version: 32.43.3608 | |
| Fixed in Release: 32.43.4100 |
No bug fixes