Helpful for debugging GPUVM errors as we can see what
hw block and page generated the fault in the log.

v2: simplify fault decoding
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>

Helpful for debugging GPUVM errors as we can see what
hw block and page generated the fault in the log.

v2: simplify fault decoding
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>

Avoid creating temporary platform device that will lead to issue
when several radeon gpu are in same computer. Instead directly use
the radeon device for requesting firmware.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Op 10-07-13 12:03, Markus Trippelsdorf schreef:
> On 2013.07.10 at 11:56 +0200, Maarten Lankhorst wrote:
>> Op 10-07-13 11:46, Markus Trippelsdorf schreef:
>>> On 2013.07.10 at 11:29 +0200, Maarten Lankhorst wrote:
>>>> Op 10-07-13 11:22, Markus Trippelsdorf schreef:
>>>>> By simply copy/pasting a big document under LibreOffice my system hangs
>>>>> itself up. Only a hard reset gets it working again.
>>>>> see also: https://bugs.freedesktop.org/show_bug.cgi?id=66551
>>>>>
>>>>> I've bisected the issue to:
>>>>>
>>>>> commit ecff665f
>>>>> Author: Maarten Lankhorst <m.b.lankhorst@gmail.com>
>>>>> Date:   Thu Jun 27 13:48:17 2013 +0200
>>>>>
>>>>>     drm/ttm: make ttm reservation calls behave like reservation calls
>>>>>
>>>>>     This commit converts the source of the val_seq counter to
>>>>>     the ww_mutex api. The reservation objects are converted later,
>>>>>     because there is still a lockdep splat in nouveau that has to
>>>>>     resolved first.
>>>>>
>>>>>     Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
>>>>>     Reviewed-by: Jerome Glisse <jglisse@redhat.com>
>>>>>     Signed-off-by: Dave Airlie <airlied@redhat.com>
>>>> Hey,
>>>>
>>>> Can you try current head with CONFIG_PROVE_LOCKING set and post the
>>>> lockdep splat from dmesg, if any? If there is any locking issue
>>>> lockdep should warn about it.  Lockdep will turn itself off after the
>>>> first splat, so if the lockdep splat happens before running the
>>>> affected parts those will have to be fixed first.
>>> There was an unrelated EDAC lockdep splat, so I simply disabled it.

> >>> This is what I get:

>>> Jul 10 11:40:44 x4 kernel: ================================================
>>> Jul 10 11:40:44 x4 kernel: [ BUG: lock held when returning to user space! ]
>>> Jul 10 11:40:44 x4 kernel: 3.10.0-08587-g496322bc #35 Not tainted
>>> Jul 10 11:40:44 x4 kernel: ------------------------------------------------
>>> Jul 10 11:40:44 x4 kernel: X/211 is leaving the kernel with locks still held!
>>> Jul 10 11:40:44 x4 kernel: 2 locks held by X/211:
>>> Jul 10 11:40:44 x4 kernel: #0:  (reservation_ww_class_acquire){+.+.+.}, at: [<ffffffff813279f0>] radeon_bo_list_validate+0x20/0xd0
>>> Jul 10 11:40:44 x4 kernel: #1:  (reservation_ww_class_mutex){+.+.+.}, at: [<ffffffff81309306>] ttm_eu_reserve_buffers+0x126/0x4b0
>>> Jul 10 11:40:52 x4 kernel: SysRq : Emergency Sync
>>> Jul 10 11:40:53 x4 kernel: Emergency Sync complete
>>>
>> Thanks, exactly what I thought. I missed a backoff somewhere..
>>
>> Does the below patch fix it?
> Yes. Thank you for your quick reply.

8<------
If radeon_cs_parser_relocs fails ttm_eu_backoff_reservation doesn't get called.
This left open a bug where ttm_eu_reserve_buffers succeeded but the bo's were
not unlocked afterwards:

Jul 10 11:40:44 x4 kernel: ================================================
Jul 10 11:40:44 x4 kernel: [ BUG: lock held when returning to user space! ]
Jul 10 11:40:44 x4 kernel: 3.10.0-08587-g496322bc #35 Not tainted
Jul 10 11:40:44 x4 kernel: ------------------------------------------------
Jul 10 11:40:44 x4 kernel: X/211 is leaving the kernel with locks still held!
Jul 10 11:40:44 x4 kernel: 2 locks held by X/211:
Jul 10 11:40:44 x4 kernel: #0:  (reservation_ww_class_acquire){+.+.+.}, at: [<ffffffff813279f0>] radeon_bo_list_validate+0x20/0xd0
Jul 10 11:40:44 x4 kernel: #1:  (reservation_ww_class_mutex){+.+.+.}, at: [<ffffffff81309306>] ttm_eu_reserve_buffers+0x126/0x4b0
Jul 10 11:40:52 x4 kernel: SysRq : Emergency Sync
Jul 10 11:40:53 x4 kernel: Emergency Sync complete

This is a regression caused by commit ecff665f.
"drm/ttm: make ttm reservation calls behave like reservation calls"
Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Tested-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Lighter weight than using the 3D engine.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Lighter weight than using the 3D engine.

v2: fix ring count
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

They still seem to cause instability on some r6xx parts.
As a follow up, we can switch to using CP DMA for bo
moves on r6xx as a lighter weight alternative to using
the 3D engine.

A version of this patch should also go to stable kernels.
Tested-by: J.N. <golden.fleeced@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Gfx PG doesn't seem to work properly when UVD is initialized
on certain PALM boards.  Disable gfx PG for now until we sort
out a proper fix.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Prevents a segfault if an afmt block is not assigned to the
encoder such as in the LVDS or eDP case.

Fixes:
https://bugs.freedesktop.org/show_bug.cgi?id=66714Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

A few more DPM fixes based on user testing.

* 'drm-next-3.11' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon/dpm: implement vblank_too_short callback for si
  drm/radeon/dpm: implement vblank_too_short callback for cayman
  drm/radeon/dpm: implement vblank_too_short callback for btc
  drm/radeon/dpm: implement vblank_too_short callback for evergreen
  drm/radeon/dpm: implement vblank_too_short callback for 7xx
  drm/radeon/dpm: add checks against vblank time
  drm/radeon/dpm: add helper to calculate vblank time
  drm/radeon: remove stray line in old pm code
  drm/radeon/dpm: fix display_gap programming on rv7xx
  drm/radeon/dpm: implement force performance level for TN
  drm/radeon/dpm: implement force performance level for ON/LN
  drm/radeon/dpm: implement force performance level for SI
  drm/radeon/dpm: implement force performance level for cayman
  drm/radeon/dpm: implement force performance levels for 7xx/eg/btc
  drm/radeon/dpm: add infrastructure to force performance levels
  drm/radeon: fix surface setup on r1xx
  drm/radeon: add support for 3d perf states on older asics
  drm/radeon: set default clocks for SI when DPM is disabled

Merge branch 'drm-nouveau-next' of git://anongit.freedesktop.org/git/nouveau/linux-2.6 into drm-next

Two minor fixes for regressions.

* 'drm-nouveau-next' of git://anongit.freedesktop.org/git/nouveau/linux-2.6:
  drm/nvc0/gr: fix gpc firmware regression
  drm/nouveau: fix minor thinko causing bo moves to not be async on kepler

Check if we can switch the mclk during the vblank time otherwise
we may get artifacts on the screen when the mclk changes.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Check if we can switch the mclk during the vblank time otherwise
we may get artifacts on the screen when the mclk changes.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Check if we can switch the mclk during the vblank time otherwise
we may get artifacts on the screen when the mclk changes.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Check if we can switch the mclk during the vblank time otherwise
we may get artifacts on the screen when the mclk changes.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Check if we can switch the mclk during the vblank time otherwise
we may get artifacts on the screen when the mclk changes.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

If the vblank time is too short to adjust mclk,
assume multiple displays (no mclk adjustments).
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Required for checking vblank time for mclk changes.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Looks like a remnant from an old rebase.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Check the driver state rather than the register as the
crtc registers may not be enabled yet.

Should fix:
https://bugzilla.kernel.org/show_bug.cgi?id=60510
https://bugs.freedesktop.org/show_bug.cgi?id=66651Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

"drm/nve0-/gr: some new gpc registers can have multiple copies"
5ee86c41 caused a regression for nvc0, because the bit indicating last
transfer has occured was no longer set, resulting in random system lockups.
Reported-by: Ronald Uitermark <ronald645@gmail.com>
Tested-by: Ronald Uitermark <ronald645@gmail.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

Reported-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

Allows you to force the selected performance level via sysfs.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Allows you to force the selected performance level via sysfs.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Allows you to force the selected performance level via sysfs.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Allows you to force a performance level via sysfs.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Allows you to limit the selected power levels via sysfs.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This allows you to force specific power levels within a power
state.  Due to hardware restrictions between generations, the
interface is limited to the following 3 selections:

auto: all levels enabled
low: forced to the lowest power level
high: forced to the highest power level
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

r1xx asics have a slightly different surface register
setup compared to newer asics.  There is no specific
enable bit for macro tiling, rather, to disable macro
tiling, you need to set the surface pitch to 0.

With this fixed, the special rn50 handling can go.
Noticed-by: Mark Kettenis <mark.kettenis@xs4all.nl>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Certain older rv770 asics have both a performance and
a 3D performance state rather than just multiple performance
levels in the state power state.  The current code would
select the performance state rather than the 3D performance
state when the "performance" profile was selected.  This change
switches to the "balanced" profile by default which ends up being
the internal performance profile.  When the user selects the
"performance" profile, it selects the internal 3D performance
state so the user can select the higher performance modes.

For most asics this changes nothing.  For certain rv770 asics
with static performance and 3D performance states, this allows
you to select between then using by selecting the "balanced"
and "performance" dpm profiles.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Fix patching of vddc values for SI and enable manually forcing
clocks to default levels as per NI.

This improves the out of the box performance with SI asics.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Merge branch 'drm-nouveau-next' of git://anongit.freedesktop.org/git/nouveau/linux-2.6 into drm-next

- GF117 acceleration support
- GK110 acceleration-with-blob-ucode support, and initial work towards
fixing our own ucode to be suitable.
- Large cleanups of fermi/kepler context handling

* 'drm-nouveau-next' of git://anongit.freedesktop.org/git/nouveau/linux-2.6: (22 commits)
  drm/nva3/disp: Fix HDMI audio regression
  drm/nv50-/disp: Use output specific mask in interrupt
  drm/nouveau: use vmalloc for pgt allocation
  drm/nvc0-/gr: remove some more of the hardcoded register writes
  drm/nvc0-/gr: factor out yet more unknown magic into versioned functions
  drm/nvd7/devinit: use fermi class, not tesla
  drm/nvf0-/gr: ctxsw scratch reg count got bumped to 16
  drm/nvc0-/gr: remove hardcoding of UNK count/mask in GPCCS ucode
  drm/nvf0/gr: build cs ucode for GK110
  drm/nvc0-/gr: extend one of the magic calculations for >4 GPCs
  drm/nvf0/gr: fix ddx shaders locking up on me
  drm/nvc0/devinit: minor typo
  drm/nvf0/gr: enable support, if external cs ucode is available
  drm/nvf0/gr: magic sequence that makes PGRAPH come out of hiding
  drm/nvf0/ce: enable support
  drm/nvf0/fifo: enable support
  drm/nvd7/gr: initial support
  drm/nvc0-/gr: generate cs register lists from grctx data
  drm/nvc0-/gr: tpc regs a subset of gpc, add separate list for gpc/unk regs
  drm/nve0-/gr: some new gpc registers can have multiple copies
  ...

We can use prime helpers instead.
Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

Instead of using the dma_buf functionality for GEM CMA, we can use prime
helpers if we can provide low-level hook functions for GEM CMA.
Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

This adds to call low-level mmap() from prime helpers.
Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

The drm_gem_map_detach() can be called with sgt is NULL.
Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

Merge branch 'exynos-drm-next' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos into drm-next

 This is final pull request for 3.11. This resolves some memory leak
   issues, and includes some code and dt document file cleanups; just
   removed unnecessary descriptions.

   And the patch work for enhancing hdmiphy driver isn't in progress so
   this patch may go to 3.12.

* 'exynos-drm-next' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos:
  drm/exynos: remove duplicated error routine and unnecessary assign
  drm/exynos: fix pages allocation size in lowlevel_buffer_allocate
  drm/exynos: use drm_calloc_large when allocates pointer array
  drm/exynos: add error check routine in exynos_drm_open
  drm/exynos: initialize the buf_num in vp_video_buffer
  drm/exynos: remove dead code in vidi_power_on
  drm/exynos: fix not to remain exynos_gem_obj as a leak
  of/documentation: Update hpd gpio property for exynos_hdmi

The DU requires a 16 pixels pitch alignement. Make sure dumb buffers are
allocated with the correct pitch, and validate the pitch when creating
frame buffers.
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

Handle error cases correctly.
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

This is the nva3 counterpart to commit beba44b1 (drm/nv84/disp: Fix
HDMI audio regression). The regression happened as a result of
refactoring in commit 8e9e3d2d (drm/nv84/disp: move hdmi control into
core).
Reported-and-tested-by: Max Baldwin <archerseven@gmail.com>
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Cc: stable@vger.kernel.org