[Nouveau] CCACHE and VFETCH FAULTs causing lockups

[Maarten Maathuis]

On Tue, Mar 1, 2011 at 9:08 PM, Maarten Maathuis <madman2003 at gmail.com> wrote:
> Mar  1 18:21:23 madman kernel: [ 1697.116256] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_VFETCH FAULT
> Mar  1 18:21:23 madman kernel: [ 1697.116275] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_VFETCH 00f00000 0000fe0c 00000000 00000000
> Mar  1 18:21:23 madman kernel: [ 1697.116283] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_CCACHE FAULT
> Mar  1 18:21:23 madman kernel: [ 1697.116299] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_CCACHE 00000080 00000000 00000000 00000000
> 00000000 00000004 00000000
> Mar  1 18:21:23 madman kernel: [ 1697.116306] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP
> Mar  1 18:21:23 madman kernel: [ 1697.116318] [drm] nouveau
> 0000:01:00.0: PGRAPH - ch 3 (0x00018f3000) subc 7 class 0x8297 mthd
> 0x15e0 data 0x00000000
> Mar  1 18:21:23 madman kernel: [ 1697.116330] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_VFETCH FAULT
> Mar  1 18:21:23 madman kernel: [ 1697.116342] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_VFETCH 00f00000 0000fe0c 00000000 00000000
> Mar  1 18:21:23 madman kernel: [ 1697.116349] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_CCACHE FAULT
> Mar  1 18:21:23 madman kernel: [ 1697.116363] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_CCACHE 00000080 00000000 00000000 00000000
> 00000000 00000004 00080000
> Mar  1 18:21:23 madman kernel: [ 1697.116371] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP
> Mar  1 18:21:23 madman kernel: [ 1697.116380] [drm] nouveau
> 0000:01:00.0: PGRAPH - ch 3 (0x00018f3000) subc 7 class 0x8297 mthd
> 0x1084 data 0x219d6fff
> Mar  1 18:21:23 madman kernel: [ 1697.116392] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_VFETCH FAULT
> Mar  1 18:21:23 madman kernel: [ 1697.116404] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP_VFETCH 00f00000 0000fe0c 00000000 00000000
> Mar  1 18:21:23 madman kernel: [ 1697.116410] [drm] nouveau
> 0000:01:00.0: PGRAPH - TRAP
> Mar  1 18:21:23 madman kernel: [ 1697.116420] [drm] nouveau
> 0000:01:00.0: PGRAPH - ch 3 (0x00018f3000) subc 7 class 0x8297 mthd
> 0x15e0 data 0x00000000
> Mar  1 18:21:29 madman kernel: [ 1703.981014] [drm] nouveau
> 0000:01:00.0: Failed to idle channel 3.
> Mar  1 18:21:31 madman kernel: [ 1705.601034] [drm] nouveau
> 0000:01:00.0: Ctxprog is still running
>
> Those come after 15-30 minutes of running warzone2100, i haven't
> played any games for a while, so no idea how long this has been going
> on.
> I also got a TRAP_CCACHE on channel 2 a little while ago, it takes
> much longer to trigger (a few hours). I'm using todays "nouveau
> kernel" git.
>
> I'm guessing something is being unmapped too early or without reason,
> or some cache is stale. But it isn't obvious what exactly it is.
>
> Because i don't remember having these lockups before I'm inclined to
> guess that this commit is involved
> http://cgit.freedesktop.org/nouveau/linux-2.6/commit/?id=6330d8f5ecc4a19fd2ad3c7fa128b2f4c2ce3360
>
> Any ideas?
>
> Maarten.
>
> --
> Far away from the primal instinct, the song seems to fade away, the
> river get wider between your thoughts and the things we do and say.
>

This is the "DDX" trap:

Mar  1 22:19:48 madman kernel: [ 1499.376769] [drm] nouveau
0000:01:00.0: PGRAPH - TRAP_CCACHE FAULT
Mar  1 22:19:48 madman kernel: [ 1499.376782] [drm] nouveau
0000:01:00.0: PGRAPH - TRAP_CCACHE 00000080 00000000 00000000 00000000
00000000 00000004 00000000
Mar  1 22:19:48 madman kernel: [ 1499.376785] [drm] nouveau
0000:01:00.0: PGRAPH - TRAP
Mar  1 22:19:48 madman kernel: [ 1499.376790] [drm] nouveau
0000:01:00.0: PGRAPH - ch 2 (0x0000840000) subc 5 class 0x8297 mthd
0x0f04 data 0x00000000

-- 
Far away from the primal instinct, the song seems to fade away, the
river get wider between your thoughts and the things we do and say.