From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 104825] [amdgpu] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=0x00000000) when unbinding Date: Mon, 29 Jan 2018 06:57:03 +0000 Message-ID: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1840921910==" Return-path: Received: from culpepper.freedesktop.org (culpepper.freedesktop.org [IPv6:2610:10:20:722:a800:ff:fe98:4b55]) by gabe.freedesktop.org (Postfix) with ESMTP id 895CD89C56 for ; Mon, 29 Jan 2018 06:57:05 +0000 (UTC) List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============1840921910== Content-Type: multipart/alternative; boundary="15172090250.d63AA729d.18964" Content-Transfer-Encoding: 7bit --15172090250.d63AA729d.18964 Date: Mon, 29 Jan 2018 06:57:05 +0000 MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated https://bugs.freedesktop.org/show_bug.cgi?id=3D104825 Bug ID: 104825 Summary: [amdgpu] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) when unbinding Product: DRI Version: XOrg git Hardware: x86-64 (AMD64) OS: Linux (All) Status: NEW Severity: normal Priority: medium Component: DRM/AMDgpu Assignee: dri-devel@lists.freedesktop.org Reporter: mlen@mlen.pl I use two amdgpu rx480 cards. During boot one of them is rebound to vfio-pci driver using the following script: pci_ids=3D("0000:03:00.0" "0000:03:00.1") for id in "${pci_ids[@]}"; do vendor=3D"$(cat "/sys/bus/pci/devices/$id/vendor")" device=3D"$(cat "/sys/bus/pci/devices/$id/device")" if [ -e "/sys/bus/pci/devices/$id/driver/unbind" ]; then echo "$id" >"/sys/bus/pci/devices/$id/driver/unbind" fi echo "$vendor $device" >/sys/bus/pci/drivers/vfio-pci/new_id done Starting from Linux 4.15 with amdgpu DC enabled (I wanted to use it for HDMI audio), unbind operation causes general protection failure: [ 68.011473] [drm] amdgpu: finishing device. [ 68.377945] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 68.575193] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 68.770107] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 68.971775] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 69.164265] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 69.350089] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 69.538302] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 69.729260] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (scratch(0xC040)=3D0x00000000) [ 69.729733] general protection fault: 0000 [#1] PREEMPT SMP PTI [ 69.730901] Modules linked in: [ 69.731936] CPU: 2 PID: 3934 Comm: openrc-run.sh Not tainted 4.15.0-gent= oo #2 [ 69.733009] Hardware name: ASUSTeK COMPUTER INC. Z10PE-D16 WS/Z10PE-D16 = WS, BIOS 3407 03/10/2017 [ 69.734240] RIP: 0010:dm_read_reg_func.isra.0+0x3/0xc [ 69.735314] RSP: 0018:ffffa80d8bd4fc40 EFLAGS: 00010282 [ 69.736353] RAX: ccea607dac10c354 RBX: ffff95af35bfca80 RCX: 0000000180200008 [ 69.737408] RDX: 0000000180200009 RSI: 0000000000005c02 RDI: ffff95af362b91c0 [ 69.738494] RBP: ffff95af35b75c90 R08: 0000000000000001 R09: ffffffffb30fced2 [ 69.739561] R10: ffff95af2f770a40 R11: 00000000ffffff80 R12: ffff95af35f30100 [ 69.740638] R13: 0000000000000000 R14: ffff95af358a3c20 R15: ffff95bf2d5f9c20 [ 69.742007] FS: 00007fe7530af740(0000) GS:ffff95af3da00000(0000) knlGS:0000000000000000 [ 69.743083] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 69.744134] CR2: 000000c420870008 CR3: 0000001027426003 CR4: 00000000003606e0 [ 69.745190] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 69.746246] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 69.747320] Call Trace: [ 69.748359] destroy+0x21/0x9c [ 69.749395] dal_i2caux_destruct+0x6f/0xab [ 69.750459] destroy+0x15/0x27 [ 69.751495] dal_i2caux_destroy+0x26/0x2f [ 69.752537] destruct+0x86/0xfd [ 69.753571] dc_destroy+0x11/0x22 [ 69.754626] dm_hw_fini+0x1e/0x22 [ 69.755632] amdgpu_fini+0xf3/0x2d6 [ 69.756616] amdgpu_device_fini+0x5c/0x158 [ 69.757597] amdgpu_driver_unload_kms+0x6b/0x7e [ 69.758601] drm_dev_unregister+0x4c/0xc6 [ 69.759584] amdgpu_pci_remove+0x19/0x37 [ 69.760576] pci_device_remove+0x3b/0x8b [ 69.761563] device_release_driver_internal+0x125/0x1f9 [ 69.762580] unbind_store+0x60/0x90 [ 69.763568] kernfs_fop_write+0x111/0x159 [ 69.764557] __vfs_write+0x33/0xd7 [ 69.765543] ? preempt_count_sub+0x8b/0x94 [ 69.766552] ? __sb_start_write+0xc0/0x180 [ 69.767525] vfs_write+0xa5/0xe2 [ 69.768490] SyS_write+0x5f/0xa3 [ 69.769439] do_syscall_64+0x72/0x81 [ 69.770419] entry_SYSCALL64_slow_path+0x25/0x25 [ 69.771373] RIP: 0033:0x7fe7529a1408 [ 69.772324] RSP: 002b:00007ffe1885c200 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 69.773300] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fe7529a1408 [ 69.774290] RDX: 000000000000000d RSI: 0000558994641890 RDI: 0000000000000001 [ 69.775290] RBP: 0000558994641890 R08: 000000000000000a R09: 00005589946475f0 [ 69.776260] R10: 000000000000009b R11: 0000000000000246 R12: 000000000000000d [ 69.777248] R13: 0000000000000001 R14: 00007fe752c6e740 R15: 000000000000000d [ 69.778244] Code: f7 74 24 04 89 43 5c 48 8b 4c 24 08 65 48 33 0c 25 28 = 00 00 00 4c 89 e0 74 05 e8 39 58 9e ff 48 83 c4 10 5b 5d 41 5c c3 48 8b 07 <48= > 8b 40 30 e9 03 4a 70 00 0f 1f 44 00 00 48 8b 47 30 8b 70 04=20 [ 69.779406] RIP: dm_read_reg_func.isra.0+0x3/0xc RSP: ffffa80d8bd4fc40 [ 69.780491] ---[ end trace 6aa4681ba3a43ec3 ]--- [ 71.815503] [drm:amdgpu_fill_buffer] *ERROR* Trying to clear memory with ring turned off. [ 71.899258] amdgpu 0000:03:00.0: vgaarb: changed VGA decodes: olddecodes=3Dio+mem,decodes=3Dnone:owns=3Dnone [ 71.899263] amdgpu 0000:02:00.0: vgaarb: changed VGA decodes: olddecodes=3Dio+mem,decodes=3Dnone:owns=3Dnone [ 72.217918] [drm:amdgpu_fill_buffer] *ERROR* Trying to clear memory with ring turned off. --=20 You are receiving this mail because: You are the assignee for the bug.= --15172090250.d63AA729d.18964 Date: Mon, 29 Jan 2018 06:57:05 +0000 MIME-Version: 1.0 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated
Bug ID 104825
Summary [amdgpu] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed (= scratch(0xC040)=3D0x00000000) when unbinding
Product DRI
Version XOrg git
Hardware x86-64 (AMD64)
OS Linux (All)
Status NEW
Severity normal
Priority medium
Component DRM/AMDgpu
Assignee dri-devel@lists.freedesktop.org
Reporter mlen@mlen.pl 

I use two amdgpu rx480 cards. During boot one of them is rebou=
nd to vfio-pci
driver using the following script:

pci_ids=3D("0000:03:00.0" "0000:03:00.1")

for id in "${pci_ids[@]}"; do
  vendor=3D"$(cat "/sys/bus/pci/devices/$id/vendor")"
  device=3D"$(cat "/sys/bus/pci/devices/$id/device")"

  if [ -e "/sys/bus/pci/devices/$id/driver/unbind" ]; then
    echo "$id" >"/sys/bus/pci/devices/$id/driver/unbind&q=
uot;
  fi

  echo "$vendor $device" >/sys/bus/pci/drivers/vfio-pci/new_id
done

Starting from Linux 4.15 with amdgpu DC enabled (I wanted to use it for HDMI
audio), unbind operation causes general protection failure:

[   68.011473] [drm] amdgpu: finishing device.
[   68.377945] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   68.575193] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   68.770107] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   68.971775] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   69.164265] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   69.350089] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   69.538302] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   69.729260] [drm:gfx_v8_0_hw_fini] *ERROR* KCQ disabled failed
(scratch(0xC040)=3D0x00000000)
[   69.729733] general protection fault: 0000 [#1] PREEMPT SMP PTI
[   69.730901] Modules linked in:
[   69.731936] CPU: 2 PID: 3934 Comm: openrc-run.sh Not tainted 4.15.0-gent=
oo
#2
[   69.733009] Hardware name: ASUSTeK COMPUTER INC. Z10PE-D16 WS/Z10PE-D16 =
WS,
BIOS 3407 03/10/2017
[   69.734240] RIP: 0010:dm_read_reg_func.isra.0+0x3/0xc
[   69.735314] RSP: 0018:ffffa80d8bd4fc40 EFLAGS: 00010282
[   69.736353] RAX: ccea607dac10c354 RBX: ffff95af35bfca80 RCX:
0000000180200008
[   69.737408] RDX: 0000000180200009 RSI: 0000000000005c02 RDI:
ffff95af362b91c0
[   69.738494] RBP: ffff95af35b75c90 R08: 0000000000000001 R09:
ffffffffb30fced2
[   69.739561] R10: ffff95af2f770a40 R11: 00000000ffffff80 R12:
ffff95af35f30100
[   69.740638] R13: 0000000000000000 R14: ffff95af358a3c20 R15:
ffff95bf2d5f9c20
[   69.742007] FS:  00007fe7530af740(0000) GS:ffff95af3da00000(0000)
knlGS:0000000000000000
[   69.743083] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   69.744134] CR2: 000000c420870008 CR3: 0000001027426003 CR4:
00000000003606e0
[   69.745190] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[   69.746246] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[   69.747320] Call Trace:
[   69.748359]  destroy+0x21/0x9c
[   69.749395]  dal_i2caux_destruct+0x6f/0xab
[   69.750459]  destroy+0x15/0x27
[   69.751495]  dal_i2caux_destroy+0x26/0x2f
[   69.752537]  destruct+0x86/0xfd
[   69.753571]  dc_destroy+0x11/0x22
[   69.754626]  dm_hw_fini+0x1e/0x22
[   69.755632]  amdgpu_fini+0xf3/0x2d6
[   69.756616]  amdgpu_device_fini+0x5c/0x158
[   69.757597]  amdgpu_driver_unload_kms+0x6b/0x7e
[   69.758601]  drm_dev_unregister+0x4c/0xc6
[   69.759584]  amdgpu_pci_remove+0x19/0x37
[   69.760576]  pci_device_remove+0x3b/0x8b
[   69.761563]  device_release_driver_internal+0x125/0x1f9
[   69.762580]  unbind_store+0x60/0x90
[   69.763568]  kernfs_fop_write+0x111/0x159
[   69.764557]  __vfs_write+0x33/0xd7
[   69.765543]  ? preempt_count_sub+0x8b/0x94
[   69.766552]  ? __sb_start_write+0xc0/0x180
[   69.767525]  vfs_write+0xa5/0xe2
[   69.768490]  SyS_write+0x5f/0xa3
[   69.769439]  do_syscall_64+0x72/0x81
[   69.770419]  entry_SYSCALL64_slow_path+0x25/0x25
[   69.771373] RIP: 0033:0x7fe7529a1408
[   69.772324] RSP: 002b:00007ffe1885c200 EFLAGS: 00000246 ORIG_RAX:
0000000000000001
[   69.773300] RAX: ffffffffffffffda RBX: 000000000000000d RCX:
00007fe7529a1408
[   69.774290] RDX: 000000000000000d RSI: 0000558994641890 RDI:
0000000000000001
[   69.775290] RBP: 0000558994641890 R08: 000000000000000a R09:
00005589946475f0
[   69.776260] R10: 000000000000009b R11: 0000000000000246 R12:
000000000000000d
[   69.777248] R13: 0000000000000001 R14: 00007fe752c6e740 R15:
000000000000000d
[   69.778244] Code: f7 74 24 04 89 43 5c 48 8b 4c 24 08 65 48 33 0c 25 28 =
00
00 00 4c 89 e0 74 05 e8 39 58 9e ff 48 83 c4 10 5b 5d 41 5c c3 48 8b 07 <=
;48> 8b
40 30 e9 03 4a 70 00 0f 1f 44 00 00 48 8b 47 30 8b 70 04=20
[   69.779406] RIP: dm_read_reg_func.isra.0+0x3/0xc RSP: ffffa80d8bd4fc40
[   69.780491] ---[ end trace 6aa4681ba3a43ec3 ]---
[   71.815503] [drm:amdgpu_fill_buffer] *ERROR* Trying to clear memory with
ring turned off.
[   71.899258] amdgpu 0000:03:00.0: vgaarb: changed VGA decodes:
olddecodes=3Dio+mem,decodes=3Dnone:owns=3Dnone
[   71.899263] amdgpu 0000:02:00.0: vgaarb: changed VGA decodes:
olddecodes=3Dio+mem,decodes=3Dnone:owns=3Dnone
[   72.217918] [drm:amdgpu_fill_buffer] *ERROR* Trying to clear memory with
ring turned off.

You are receiving this mail because:
  • You are the assignee for the bug.
= --15172090250.d63AA729d.18964-- --===============1840921910== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVsCg== --===============1840921910==--