Hard lock playing video on studio jammy k5.15.0-48-lowlatency

Please close as a duplicate of
https://answers.launchpad.net/ubuntu/+source/linux/+question/703608

Video stream playback usually starts ok,
Then within minutes goes to total garbage and never recovers.
Radeonsi video driver hardware decode
Older Focal driver recovers quickly even after severe stream skips

I see no option to close as duplicate

Update to kernel
5.19.0-1027-lowlatency
VLC plays an mpeg2 stream for an hour.
Stopped playback.
Plug in ssd on usb adapter.
Dd to null, 5min ok,
Hit play on VLC, instant lockup.

Reboot, turned off iommu in bios
So far no crash

In dmesg:
[Jun17 20:13] ------------[ cut here ]------------
[ +0.000008] WARNING: CPU: 3 PID: 2762 at drivers/gpu/drm/ttm/ttm_bo.c:362 ttm_bo_release+0x309/0x330 [ttm]
[ +0.000030] Modules linked in: snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio snd_hda_codec_hdmi snd_hda_intel snd_intel_dspcfg snd_intel_sdw_acpi snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq edac_mce_amd snd_seq_device snd_timer kvm_amd ccp input_leds joydev kvm snd eeepc_wmi soundcore wmi_bmof fam15h_power k10temp mac_hid binfmt_misc sch_fq_codel cuse msr parport_pc ppdev lp parport ramoops pstore_blk reed_solomon pstore_zone efi_pstore ip_tables x_tables autofs4 overlay isofs dm_mirror dm_region_hash dm_log amdgpu iommu_v2 gpu_sched hid_generic usbhid hid radeon i2c_algo_bit drm_ttm_helper ttm drm_display_helper cec rc_core crct10dif_pclmul crc32_pclmul drm_kms_helper ghash_clmulni_intel syscopyarea aesni_intel sysfillrect mfd_aaeon sysimgblt asus_wmi fb_sys_fops sparse_keymap crypto_simd mxm_wmi cryptd uas ahci r8169 video drm platform_profile usb_storage i2c_piix4 xhci_pci libahci xhci_pci_renesas realtek wmi
[ +0.000155] CPU: 3 PID: 2762 Comm: Xorg Not tainted 5.19.0-1027-lowlatency #28~22.04.1-Ubuntu
[ +0.000007] Hardware name: ASUSTeK COMPUTER INC. M51BC/M51BC, BIOS 0302 08/05/2013
[ +0.000004] RIP: 0010:ttm_bo_release+0x309/0x330 [ttm]
[ +0.000020] Code: 4c 89 e7 e8 e9 27 00 00 48 8b 7b a8 e9 76 fd ff ff be 03 00 00 00 e8 26 ce 91 c9 e9 06 fe ff ff e8 cc 0e c3 c9 e9 fc fd ff ff <0f> 0b 48 83 7b 20 00 0f 84 33 fd ff ff 0f 0b e9 2c fd ff ff 0f 0b
[ +0.000006] RSP: 0018:ffffab29c2c13c20 EFLAGS: 00010202
[ +0.000006] RAX: 0000000000000000 RBX: ffff9555b12b69c8 RCX: 0000000000000000
[ +0.000004] RDX: 0000000000000002 RSI: 0000000000000000 RDI: ffff9555b12b69c8
[ +0.000003] RBP: ffffab29c2c13c80 R08: ffff9555b12b69c8 R09: 0000000000000000
[ +0.000004] R10: 0000000000000000 R11: 0000000000000000 R12: ffff9555816f06f0
[ +0.000003] R13: ffff9555d7c8a058 R14: ffff9555b12b6878 R15: ffff9555d7c8a000
[ +0.000005] FS: 00007f8669b5ca80(0000) GS:ffff9558bfcc0000(0000) knlGS:0000000000000000
[ +0.000005] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ +0.000003] CR2: 00005564cba26db0 CR3: 000000011f050000 CR4: 00000000000406e0
[ +0.000005] Call Trace:
[ +0.000004] <TASK>
[ +0.000006] ? call_rcu+0xa6/0x2c0
[ +0.000011] ttm_bo_put+0x3d/0x70 [ttm]
[ +0.000019] radeon_bo_unref+0x1e/0x40 [radeon]
[ +0.000105] radeon_gem_object_free+0x34/0x60 [radeon]
[ +0.000188] drm_gem_object_free+0x1d/0x40 [drm]
[ +0.000103] drm_gem_dmabuf_release+0x4a/0x70 [drm]
[ +0.000098] dma_buf_release+0x4a/0xb0
[ +0.000012] __dentry_kill+0x110/0x1b0
[ +0.000010] dput+0x1d1/0x330
[ +0.000007] __fput+0xf4/0x290
[ +0.000008] ____fput+0xe/0x20
[ +0.000009] task_work_run+0x64/0xa0
[ +0.000010] exit_to_user_mode_loop+0x111/0x140
[ +0.000010] exit_to_user_mode_prepare+0xb9/0xd0
[ +0.000009] syscall_exit_to_user_mode+0x2a/0x50
[ +0.000014] do_syscall_64+0x69/0x90
[ +0.000010] ? exit_to_user_mode_prepare+0xa1/0xd0
[ +0.000009] ? syscall_exit_to_user_mode+0x2a/0x50
[ +0.000009] ? do_syscall_64+0x69/0x90
[ +0.000010] ? exit_to_user_mode_prepare+0xa1/0xd0
[ +0.000008] ? irqentry_exit_to_user_mode+0x9/0x20
[ +0.000011] ? irqentry_exit+0x43/0x50
[ +0.000007] ? exc_page_fault+0x92/0x1b0
[ +0.000008] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ +0.000007] RIP: 0033:0x7f8669573aff
[ +0.000006] Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <41> 89 c0 3d 00 f0 ff ff 77 1f 48 8b 44 24 18 64 48 2b 04 25 28 00
[ +0.000005] RSP: 002b:00007ffdef7ec6b0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[ +0.000007] RAX: 0000000000000000 RBX: 00007ffdef7ec758 RCX: 00007f8669573aff
[ +0.000004] RDX: 00007ffdef7ec758 RSI: 0000000040086409 RDI: 0000000000000014
[ +0.000004] RBP: 0000000040086409 R08: 00005564cb989c70 R09: 0000000000000000
[ +0.000003] R10: 00007f866851ad80 R11: 0000000000000246 R12: 00005564cb989c70
[ +0.000004] R13: 0000000000000014 R14: 0000000003340000 R15: 00005564caa2a6b8
[ +0.000007] </TASK>
[ +0.000003] ---[ end trace 0000000000000000 ]---

Lockup with almost the same LOC
https://gitlab.freedesktop.org/drm/amd/-/issues/1894

Another hardlock:
https://gitlab.freedesktop.org/drm/amd/-/issues/1813

warnings in 5.11.9
https://gitlab.freedesktop.org/drm/amd/-/issues/1542

regression in 5.11.9, multiple amdgpu errors in dmesg

https://gitlab.freedesktop.org/drm/amd/-/issues/1550

Some noted a commit reverted for 5.11.10?

Another lockup with iommu off,
Reboot gave same warning in dmesg.
Lockup some time from 12 to 24hrs w/o iommu

https://cdn.kernel.org/pub/linux/kernel/v5.x/ChangeLog-5.11.10
Says the warnings are unneeded,
Is this still the case?

This question was expired because it remained in the 'Open' state without activity for the last 15 days.

AMD fx: IOMMU off:
Playing video stream for several days while running prime95, no errors, but:
Stop playback
Move VLC window to smaller secondary monitor
Hit space to play, instant lockup!
Mouse moves but nothing works.
Numlock light on keyboard not responding.
Crtl-alt-f2 not working

Recent kernel changelog shows amdgpu lockup bug fixed, waiting for jammy hwe 5.19...

This question was expired because it remained in the 'Open' state without activity for the last 15 days.