Riallto on Linux: Module installed successfully but seeing "loading /lib/firmware/amdnpu/1502_00/npu.sbin failed with error -22"

[LakshyAAAgrawal]

[This is a duplicate of https://github.com/amd/xdna-driver/issues/282]

Hi,

I am following the guide at https://github.com/AMDResearch/Riallto/tree/main/scripts/linux to install this driver on a Minisforum UM790 Pro device. The machine has Ubuntu 24.04, with kernel 6.10.

$ uname -r
6.10.0-061000rc2-generic

I have ensured from the bios that:

1. Secure boot is disabled
2. IPU Device is enabled

The build and installation (./setup_riallto_linux.sh <your license file> command the above link) go through successfully. After that, when I try to run the next step "launch_jupyter.sh ", I see the following error:

docker: Error response from daemon: error gathering device information while adding custom device "/dev/accel/accel0": no such file or directory.

And the output of dmesg:

$ sudo dmesg | grep "xdna"
[    1.632845] amdxdna: loading out-of-tree module taints kernel.
[    1.632849] amdxdna: module verification failed: signature and/or required key missing - tainting kernel
[    1.638560] amdxdna 0000:c5:00.1: Direct firmware load for amdnpu/1502_00/npu.sbin failed with error -2
[    1.638565] amdxdna 0000:c5:00.1: aie2_init: failed to request_firmware amdnpu/1502_00/npu.sbin, ret -2
[    1.638569] amdxdna 0000:c5:00.1: amdxdna_probe: Hardware init failed, ret -2
[    1.638572] amdxdna 0000:c5:00.1: probe with driver amdxdna failed with error -2
[    3.699877]  snd_rawmidi drm_buddy drm_suballoc_helper crypto_simd iwlwifi drm_ttm_helper snd_pcm cryptd snd_seq ttm snd_seq_device rapl drm_display_helper snd_pci_acp5x snd_timer cec snd_rn_pci_acp3x snd cfg80211 snd_acp_config amdxdna(OE) rc_core snd_soc_acpi i2c_algo_bit ccp snd_pci_acp3x soundcore gpu_sched k10temp i2c_piix4 amd_pmc input_leds mac_hid serio_raw sch_fq_codel msr parport_pc ppdev lp parport efi_pstore nfnetlink dmi_sysfs ip_tables x_tables autofs4 nvme thunderbolt crc32_pclmul nvme_core r8169 xhci_pci xhci_pci_renesas nvme_auth realtek video i2c_hid_acpi wmi i2c_hid hid
[ 4060.683744] amdxdna 0000:c5:00.1: loading /lib/firmware/amdnpu/1502_00/npu.sbin failed with error -22
[ 4060.683749] amdxdna 0000:c5:00.1: Direct firmware load for amdnpu/1502_00/npu.sbin failed with error -22
[ 4060.683751] amdxdna 0000:c5:00.1: aie2_init: failed to request_firmware amdnpu/1502_00/npu.sbin, ret -22
[ 4060.683754] amdxdna 0000:c5:00.1: amdxdna_probe: Hardware init failed, ret -22
[ 4060.683756] amdxdna 0000:c5:00.1: probe with driver amdxdna failed with error -22

When generating the license file, I have tried using the MAC for both my wifi device and ethernet device. MAC was entered in "XXXXXXXXXXXX" format, where all characters are capital, and without ":" or "-".

Could you please help me understand what might the issue be?

Additional debug info:

$ sudo lspci -vd 1022:1502
c5:00.1 Signal processing controller: Advanced Micro Devices, Inc. [AMD] AMD IPU Device
        Subsystem: Device 1f4c:b002
        Flags: fast devsel, IRQ 255, IOMMU group 24
        Memory at dc900000 (32-bit, non-prefetchable) [disabled] [size=512K]
        Memory at dc9c0000 (32-bit, non-prefetchable) [disabled] [size=8K]
        Memory at 7c10900000 (64-bit, prefetchable) [disabled] [size=256K]
        Memory at dc980000 (32-bit, non-prefetchable) [disabled] [size=256K]
        Capabilities: [48] Vendor Specific Information: Len=08 <?>
        Capabilities: [50] Power Management version 3
        Capabilities: [64] Express Endpoint, MSI 00
        Capabilities: [a0] MSI: Enable- Count=1/16 Maskable- 64bit+
        Capabilities: [c0] MSI-X: Enable- Count=16 Masked-
        Capabilities: [100] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?>
        Capabilities: [150] Advanced Error Reporting
        Capabilities: [2a0] Access Control Services
        Capabilities: [2d0] Process Address Space ID (PASID)
        Kernel modules: amdxdna

$ ls -lah /lib/firmware/amdnpu/1502_00/
total 8.0K
drwxr-xr-x 2 root root 4.0K Oct  9 12:05 .
drwxr-xr-x 3 root root 4.0K Oct  8 18:45 ..
-rw-r--r-- 1 root root    0 Oct  9 11:55 npu.sbin

As can be seen above, the installed firmware is zero in size. What could be causing this?

[mariodruiz]

Hi @LakshyAAAgrawal, thank you for reporting this.

There is a PR open with some fixes to this flow. Would you be able to try #54?