Skip to content

amdgpu: smu firmware loading failed on any kernel newer then longterm 5.10.x (5.10.154 working)

Hardware description:

  • CPU: Intel(R) Core(TM) i7-10700K CPU @ 3.80GHz
  • GPU: 03:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Device [1002:7319] (rev 40)
  • System Memory: 32725236
  • Display(s): 1 or 2
  • iMac Intel 2020 27" 5700XT

System information:

  • Distro name and Version: Fedora 37
  • Kernel version: uname -a 6.1.0-rc2-x86_64
  • Custom kernel: amd-staging-drm-next
  • AMD official driver version: none

How to reproduce the issue:

Any kernel other than branch LTS 5.10, also any distributions (gentoo, ubuntu, fedora)

dmesg when not working:

[drm] amdgpu kernel modesetting enabled.
[    2.498203] amdgpu: CRAT table not found
[    2.498211] amdgpu: Virtual CRAT table created for CPU
[    2.498222] amdgpu: Topology: Add CPU node
[    2.498451] amdgpu 0000:03:00.0: vgaarb: deactivate vga console
[    2.500735] amdgpu 0000:03:00.0: amdgpu: Fetched VBIOS from VFCT
[    2.500739] amdgpu: ATOM BIOS: 113-D182A2XT-012
[    2.500751] amdgpu 0000:03:00.0: amdgpu: Trusted Memory Zone (TMZ) feature disabled as experimental (default)
[    2.500802] amdgpu 0000:03:00.0: BAR 2: releasing [mem 0xb0000000-0xb01fffff 64bit pref]
[    2.500806] amdgpu 0000:03:00.0: BAR 0: releasing [mem 0xa0000000-0xafffffff 64bit pref]
[    2.500847] amdgpu 0000:03:00.0: BAR 0: assigned [mem 0x4400000000-0x47ffffffff 64bit pref]
[    2.500855] amdgpu 0000:03:00.0: BAR 2: assigned [mem 0x4200000000-0x42001fffff 64bit pref]
[    2.500914] amdgpu 0000:03:00.0: amdgpu: VRAM: 16368M 0x0000008000000000 - 0x00000083FEFFFFFF (16368M used)
[    2.500917] amdgpu 0000:03:00.0: amdgpu: GART: 512M 0x0000000000000000 - 0x000000001FFFFFFF
[    2.500920] amdgpu 0000:03:00.0: amdgpu: AGP: 267894784M 0x0000008400000000 - 0x0000FFFFFFFFFFFF
[    2.500984] [drm] amdgpu: 16368M of VRAM memory ready
[    2.500987] [drm] amdgpu: 15976M of GTT memory ready.
[    2.509221] amdgpu 0000:03:00.0: amdgpu: PSP runtime database doesn't exist
[    2.509230] amdgpu 0000:03:00.0: amdgpu: PSP runtime database doesn't exist
[    2.536166] amdgpu 0000:03:00.0: amdgpu: Will use PSP to load VCN firmware
[    2.674460] amdgpu 0000:03:00.0: amdgpu: RAS: optional ras ta ucode is not available
[    2.685964] amdgpu 0000:03:00.0: amdgpu: RAP: optional rap ta ucode is not available
[    2.685970] amdgpu 0000:03:00.0: amdgpu: SECUREDISPLAY: securedisplay ta ucode is not available
****[   2.685976] amdgpu: smu firmware loading failed
[    2.685980] amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_init failed****
[    2.685985] amdgpu 0000:03:00.0: amdgpu: Fatal error during GPU init
[    2.685989] amdgpu 0000:03:00.0: amdgpu: amdgpu: finishing device.
[    2.702122] amdgpu 0000:03:00.0: amdgpu: free PSP TMR buffer
[    2.736859] amdgpu: probe of 0000:03:00.0 failed with error -95
[    2.737015]  amdgpu_fence_driver_sw_fini+0xc4/0xd0 [amdgpu]
[    2.737531]  amdgpu_device_fini_sw+0x17/0x3c0 [amdgpu]
[    2.737984]  amdgpu_driver_release_kms+0x12/0x30 [amdgpu]

With LTS :

`dmesg |grep amdgpu

[    0.000000] Command line: BOOT_IMAGE=(hd5,gpt6)/vmlinuz-5.10.154-x86_64+ root=UUID=432aea97-6593-48a5-9f9c-62077714f67e ro amdgpu.aspm=0 amdgpu.dpm=0 vga=788 rhgb quiet intel_iommu=on iommu=pt pcie_ports=compat
[    0.061356] Kernel command line: BOOT_IMAGE=(hd5,gpt6)/vmlinuz-5.10.154-x86_64+ root=UUID=432aea97-6593-48a5-9f9c-62077714f67e ro amdgpu.aspm=0 amdgpu.dpm=0 vga=788 rhgb quiet intel_iommu=on iommu=pt pcie_ports=compat
[    1.461999] [drm] amdgpu kernel modesetting enabled.
[    1.462112] amdgpu: Topology: Add CPU node
[    1.462161] fb0: switching to amdgpudrmfb from EFI VGA
[    1.462198] amdgpu 0000:03:00.0: vgaarb: deactivate vga console
[    1.462350] amdgpu 0000:03:00.0: amdgpu: Trusted Memory Zone (TMZ) feature disabled as experimental (default)
[    1.463956] amdgpu 0000:03:00.0: amdgpu: Fetched VBIOS from VFCT
[    1.463957] amdgpu: ATOM BIOS: 113-D182A2XT-012
[    1.463984] amdgpu 0000:03:00.0: BAR 2: releasing [mem 0xb0000000-0xb01fffff 64bit pref]
[    1.463985] amdgpu 0000:03:00.0: BAR 0: releasing [mem 0xa0000000-0xafffffff 64bit pref]
[    1.464016] amdgpu 0000:03:00.0: BAR 0: assigned [mem 0x4400000000-0x47ffffffff 64bit pref]
[    1.464022] amdgpu 0000:03:00.0: BAR 2: assigned [mem 0x4200000000-0x42001fffff 64bit pref]
[    1.464057] amdgpu 0000:03:00.0: amdgpu: VRAM: 16368M 0x0000008000000000 - 0x00000083FEFFFFFF (16368M used)
[    1.464058] amdgpu 0000:03:00.0: amdgpu: GART: 512M 0x0000000000000000 - 0x000000001FFFFFFF
[    1.464153] [drm] amdgpu: 16368M of VRAM memory ready
[    1.464155] [drm] amdgpu: 16368M of GTT memory ready.
[    1.502254] amdgpu 0000:03:00.0: amdgpu: Will use PSP to load VCN firmware
[    2.131359] amdgpu 0000:03:00.0: amdgpu: RAS: optional ras ta ucode is not available
[    2.151366] amdgpu 0000:03:00.0: amdgpu: RAP: optional rap ta ucode is not available
[    2.151396] amdgpu 0000:03:00.0: amdgpu: smu driver if version = 0x00000036, smu fw if version = 0x00000037, smu fw version = 0x002a4100 (42.65.0)
[    2.151398] amdgpu 0000:03:00.0: amdgpu: SMU driver if version not matched
[    2.450565] amdgpu: Topology: Add dGPU node [0x7319:0x1002]
[    2.450568] amdgpu 0000:03:00.0: amdgpu: SE 2, SH per SE 2, CU per SH 10, active_cu_number 40
[    2.454447] fbcon: amdgpudrmfb (fb0) is primary device
[    2.454449] amdgpu 0000:03:00.0: [drm] fb0: amdgpudrmfb frame buffer device
[    2.471461] amdgpu 0000:03:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[    2.471463] amdgpu 0000:03:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[    2.471463] amdgpu 0000:03:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[    2.471464] amdgpu 0000:03:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 5 on hub 0
[    2.471464] amdgpu 0000:03:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 6 on hub 0
[    2.471465] amdgpu 0000:03:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 7 on hub 0
[    2.471465] amdgpu 0000:03:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 8 on hub 0
[    2.471466] amdgpu 0000:03:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 9 on hub 0
[    2.471466] amdgpu 0000:03:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 10 on hub 0
[    2.471467] amdgpu 0000:03:00.0: amdgpu: ring kiq_2.1.0 uses VM inv eng 11 on hub 0
[    2.471467] amdgpu 0000:03:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[    2.471468] amdgpu 0000:03:00.0: amdgpu: ring sdma1 uses VM inv eng 13 on hub 0
[    2.471468] amdgpu 0000:03:00.0: amdgpu: ring vcn_dec uses VM inv eng 0 on hub 1
[    2.471469] amdgpu 0000:03:00.0: amdgpu: ring vcn_enc0 uses VM inv eng 1 on hub 1
[    2.471469] amdgpu 0000:03:00.0: amdgpu: ring vcn_enc1 uses VM inv eng 4 on hub 1
[    2.471470] amdgpu 0000:03:00.0: amdgpu: ring jpeg_dec uses VM inv eng 5 on hub 1
[    2.472464] [drm] Initialized amdgpu 3.40.0 20150101 for 0000:03:00.0 on minor 0
[    3.702954] snd_hda_intel 0000:03:00.1: bound 0000:03:00.0 (ops __SCT__tp_func_amdgpu_dc_performance [amdgpu])

Try with enable and disable option in kernel :