Update BF2 BFB image and NIC Firmware

Accelerated Computing Aerial Forum
1

I am using HPE ProLiant DL380 Gen10 with Intel Xeon Gold 6248 CPU.
GPU and NIC information is as follows.

yogurt@134servwe:~$ lspci | grep -i nvidia
37:00.0 3D controller: NVIDIA Corporation GV100GL [Tesla V100 PCIe 32GB] (rev a1)
86:00.0 3D controller: NVIDIA Corporation GV100GL [Tesla V100 PCIe 32GB] (rev a1)
yogurt@134servwe:~$ lspci | grep -i mellanox
12:00.0 Ethernet controller: Mellanox Technologies MT2892 Family [ConnectX-6 Dx]
12:00.1 Ethernet controller: Mellanox Technologies MT2892 Family [ConnectX-6 Dx]
d8:00.0 Ethernet controller: Mellanox Technologies MT42822 BlueField-2 integrated ConnectX-6 Dx network controller (rev 01)
d8:00.1 Ethernet controller: Mellanox Technologies MT42822 BlueField-2 integrated ConnectX-6 Dx network controller (rev 01)
d8:00.2 DMA controller: Mellanox Technologies MT42822 BlueField-2 SoC Management Interface (rev 01)

How do I have to update BF2 BFB image and NIC Firmware.
Can I follow the instructions in “1.4.2.18 Update A100X BFB Image and NIC Firmware” of “Aerial CUDA-Accelerated RAN 24-2.1” version?

2

When I follow instructions in “1.4.2.18 Update A100X BFB Image and NIC Firmware” of “Aerial CUDA-Accelerated RAN 24-2.1”, The following error occurred during NIC firmware update.
I found the firmware suitable for MT_0000000738 and did the update.

-E- PSID mismatch. The PSID on flash (MT_0000000738) differs from the PSID in the given image (NVD0000000015).

3

@twoheons

yes, you can follow that instruction for updating the NIC FW.
did you download the image for PSID for MT_0000000738? please run the follow two command and shar the outputs of the sudo flint -d mlx5_0 q
$ sudo mst start
$ sudo flint -d mlx5_0 q

Thanks

4

I received the image below from the site below.

the log is here.
yogurt@134servwe:~$ sudo mst start
[sudo] password for yogurt:
Starting MST (Mellanox Software Tools) driver set
Loading MST PCI module - Success
[warn] mst_pciconf is already loaded, skipping
Create devices
Unloading MST PCI module (unused) - Success
yogurt@134servwe:~$
yogurt@134servwe:~$ sudo flint -d mlx5_0 q
Image type: FS4
FW Version: 22.29.1016
FW Release Date: 31.12.2020
Product Version: 22.29.1016
Rom Info: type=UEFI version=14.22.14 cpu=AMD64,AARCH64
type=PXE version=3.6.204 cpu=AMD64
Description: UID GuidsNumber
Base GUID: 043f720300ecf862 4
Base MAC: 043f72ecf862 4
Image VSD: N/A
Device VSD: N/A
PSID: MT_0000000606
Security Attributes: N/A

5

I added logs.
Could you check if there is an issue with NIC FW on the server?

yogurt@134servwe:~$ sudo mst status -v
MST modules:
------------
    MST PCI module is not loaded
    MST PCI configuration module loaded
PCI devices:
------------
DEVICE_TYPE             MST                           PCI       RDMA            NET                                     NUMA
BlueField2(rev:1)       /dev/mst/mt41686_pciconf0.1   d8:00.1   mlx5_3          net-aerial01                            1

BlueField2(rev:1)       /dev/mst/mt41686_pciconf0     d8:00.0   mlx5_2          net-aerial00                            1

ConnectX6DX(rev:0)      /dev/mst/mt4125_pciconf0.1    12:00.1   mlx5_1          net-ens3f1np1                           0

ConnectX6DX(rev:0)      /dev/mst/mt4125_pciconf0      12:00.0   mlx5_0          net-ens3f0np0                           0

yogurt@134servwe:~$ sudo flint -d mlx5_2 q
Image type:            FS4
FW Version:            24.39.3560
FW Release Date:       24.6.2024
Product Version:       24.39.3560
Rom Info:              type=UEFI Virtio net version=21.4.13 cpu=AMD64,AARCH64
                       type=UEFI Virtio blk version=22.4.12 cpu=AMD64,AARCH64
                       type=UEFI version=14.32.17 cpu=AMD64,AARCH64
                       type=PXE version=3.7.300 cpu=AMD64
Description:           UID                GuidsNumber
Base GUID:             1070fd03004a5e8c        16
Base MAC:              1070fd4a5e8c            16
Image VSD:             N/A
Device VSD:            N/A
PSID:                  MT_0000000738
Security Attributes:   secure-fw

yogurt@134servwe:~$ sudo flint -d mlx5_0 q
Image type:            FS4
FW Version:            22.29.1016
FW Release Date:       31.12.2020
Product Version:       22.29.1016
Rom Info:              type=UEFI version=14.22.14 cpu=AMD64,AARCH64
                       type=PXE version=3.6.204 cpu=AMD64
Description:           UID                GuidsNumber
Base GUID:             043f720300ecf862        4
Base MAC:              043f72ecf862            4
Image VSD:             N/A
Device VSD:            N/A
PSID:                  MT_0000000606
Security Attributes:   N/A
6

Hi @twoheons
thanks for capturing the info. Can you try a different version of FW such as 24.39.2048 https://www.mellanox.com/downloads/firmware/fw-BlueField-2-rel-24_39_2048-MBF2H516C-CESO_Ax-NVME-20.4.1-UEFI-21.4.13-UEFI-22.4.12-UEFI-14.32.17-FlexBoot-3.7.300.signed.bin.zip? Please capture and share the logs if it still fails while updating the FW.