This way the driver can decide if it is valuable to evict a BO or not.

The current implementation is added as default to all existing drivers.

v2: fix some typos found during internal testing
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The current default of always using the performance power state leads
to increased power consumption of mobile devices, which have a dedicated
battery power state. Switch between the performance and battery power
state automatically, dpending on the current AC power status, when the
user asked for the balanced power state.

The user can still override this logic by asking for the performance
or battery power state explicitly.
Tested-by: NMichel Dänzer <michel.daenzer@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NLucas Stach <dev@lynxeye.de>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Update the comment to explain why we do this.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We get 4 warnings when building kernel with W=1:
drivers/gpu/drm/radeon/si.c:7850:5: warning: no previous prototype for 'si_vce_send_vcepll_ctlreq' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/radeon_dp_mst.c:226:21: warning: no previous prototype for 'radeon_mst_best_encoder' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/radeon_dp_mst.c:344:26: warning: no previous prototype for 'radeon_mst_find_connector' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/radeon_dp_mst.c:600:6: warning: no previous prototype for 'radeon_dp_mst_encoder_destroy' [-Wmissing-prototypes]

In fact, these functions are only used in the file in which they are
declared and don't need a declaration, but can be made static.
So this patch marks these functions with 'static'.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NBaoyou Xie <baoyou.xie@linaro.org>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We get a few warnings when building kernel with W=1:
drivers/gpu/drm/radeon/radeon_clocks.c:35:10: warning: no previous prototype for 'radeon_legacy_get_engine_clock' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/atombios_encoders.c:75:1: warning: no previous prototype for 'atombios_get_backlight_level' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/r600_cs.c:2268:5: warning: no previous prototype for 'r600_cs_parse' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/evergreen_cs.c:2671:5: warning: no previous prototype for 'evergreen_cs_parse' [-Wmissing-prototypes]
....

In fact, these functions are declared
in drivers/gpu/drm/radeon/radeon_asic.h,
so this patch adds missing header dependencies.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NBaoyou Xie <baoyou.xie@linaro.org>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

I plan to usurp the short name of struct fence for a core kernel struct,
and so I need to rename the specialised fence/timeline for DMA
operations to make room.

A consensus was reached in
https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html
that making clear this fence applies to DMA operations was a good thing.
Since then the patch has grown a bit as usage increases, so hopefully it
remains a good thing!

(v2...: rebase, rerun spatch)
v3: Compile on msm, spotted a manual fixup that I broke.
v4: Try again for msm, sorry Daniel

coccinelle script:
@@

@@
- struct fence
+ struct dma_fence
@@

@@
- struct fence_ops
+ struct dma_fence_ops
@@

@@
- struct fence_cb
+ struct dma_fence_cb
@@

@@
- struct fence_array
+ struct dma_fence_array
@@

@@
- enum fence_flag_bits
+ enum dma_fence_flag_bits
@@

@@
(
- fence_init
+ dma_fence_init
|
- fence_release
+ dma_fence_release
|
- fence_free
+ dma_fence_free
|
- fence_get
+ dma_fence_get
|
- fence_get_rcu
+ dma_fence_get_rcu
|
- fence_put
+ dma_fence_put
|
- fence_signal
+ dma_fence_signal
|
- fence_signal_locked
+ dma_fence_signal_locked
|
- fence_default_wait
+ dma_fence_default_wait
|
- fence_add_callback
+ dma_fence_add_callback
|
- fence_remove_callback
+ dma_fence_remove_callback
|
- fence_enable_sw_signaling
+ dma_fence_enable_sw_signaling
|
- fence_is_signaled_locked
+ dma_fence_is_signaled_locked
|
- fence_is_signaled
+ dma_fence_is_signaled
|
- fence_is_later
+ dma_fence_is_later
|
- fence_later
+ dma_fence_later
|
- fence_wait_timeout
+ dma_fence_wait_timeout
|
- fence_wait_any_timeout
+ dma_fence_wait_any_timeout
|
- fence_wait
+ dma_fence_wait
|
- fence_context_alloc
+ dma_fence_context_alloc
|
- fence_array_create
+ dma_fence_array_create
|
- to_fence_array
+ to_dma_fence_array
|
- fence_is_array
+ dma_fence_is_array
|
- trace_fence_emit
+ trace_dma_fence_emit
|
- FENCE_TRACE
+ DMA_FENCE_TRACE
|
- FENCE_WARN
+ DMA_FENCE_WARN
|
- FENCE_ERR
+ DMA_FENCE_ERR
)
 (
 ...
 )
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NGustavo Padovan <gustavo.padovan@collabora.co.uk>
Acked-by: NSumit Semwal <sumit.semwal@linaro.org>
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk

This removes the 'write' and 'force' from get_user_pages() and replaces
them with 'gup_flags' to make the use of FOLL_FORCE explicit in callers
as use of this flag can result in surprising behaviour (and hence bugs)
within the mm subsystem.
Signed-off-by: NLorenzo Stoakes <lstoakes@gmail.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Acked-by: NJesper Nilsson <jesper.nilsson@axis.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The driver needs the number of bytes per pixel, not the bpp and depth
info meant for fbdev compatibility. Use the right API.
Signed-off-by: NLaurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NArchit Taneja <architt@codeaurora.org>
Link: http://patchwork.freedesktop.org/patch/msgid/1476744081-24485-11-git-send-email-laurent.pinchart@ideasonboard.com

Ported from Rex's amdgpu change.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Required for border colors in compute shaders.
Reviewed-by: NEdward O'Callaghan <funfunctor@folklore1984.net>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NMarek Olšák <marek.olsak@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The ordering caused problems.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=98200Reviewed-and-Tested-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Port the amdgpu fixes from Grazvydas to radeon.

v2: drop unrelated whitespace change.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=98200Reviewed-and-Tested-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Pre DCE4 hw doesn't have reliable pageflip completion
interrupts, so instead polling for flip completion is
used from within the vblank irq handler to complete
page flips.

This causes a race if pageflip ioctl is called close to
vblank:

1. pageflip ioctl queues execution of radeon_flip_work_func.

2. vblank irq fires, radeon_crtc_handle_vblank checks for
   flip_status == FLIP_SUBMITTED finds none, no-ops.

3. radeon_flip_work_func runs inside vblank, decides to
   set flip_status == FLIP_SUBMITTED and programs the
   flip into hw.

4. hw executes flip immediately (because in vblank), but
   as 2 already happened, the flip completion routine only
   emits the flip completion event one refresh later ->
   wrong vblank count/timestamp for completion and no
   performance gain, as instead of delaying the flip until
   next vblank, we now delay the next flip by 1 refresh
   while waiting for the delayed flip completion event.

Given we often don't gain anything due to this race, but
lose precision, prevent the programmed flip from executing
in vblank on pre DCE4 asics to avoid this race.

On pre-AVIVO hw we can't program the hw for edge-triggered
flips, they always execute anywhere in vblank. Therefore delay
the actual flip programming until after vblank on pre-AVIVO.
Reviewed-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NMario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Pre DCE4 hardware doesn't have (reliable) pageflip completion
irqs, therefore we have to use the old polling method for flip
completion handling in vblank irq.

As vblank irqs fire a bit before start of vblank (when the
linebuffer fifo read position reaches end of scanout), we
have some fudge for flip completion handling in the last
lines of active scanout. Old code assumed the threshold to
be 99% of active scanout height, a ballpark estimate which
worked ok. Since we know since a while how to calculate the
actual threshold from linebuffer size, lets make use of it
to get a more accurate threshold.

This completion path is still prone to some races in corner
cases, especially on pre-AVIVO hardware, so document them
a bit better in the code comments.
Acked-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NMario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We have the drm_display_info for storing information about the sink, so
let's move dvi_dual and max_tmds_clock in there.

v2: Deal with superfluous code shuffling
    Document dvi_dual and max_tmds_clock too

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1475070703-6435-5-git-send-email-ville.syrjala@linux.intel.com

We generally store clocks in kHz, so let's do that for the
HDMI max TMDS clock value as well. Less surpising.

v2: Deal with superfluous code shuffling

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1475070703-6435-4-git-send-email-ville.syrjala@linux.intel.com

We can't properly detect all hypervisors and we
need this to properly tear down the hardware.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Used the wrong index to setup the phase shedding mask.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Add clock quirks for Jet parts.
Reviewed-by: NSonny Jiang <sonny.jiang@amd.com>
Tested-by: NSonny Jiang <sonny.jiang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

On PX systems, if the platform supports hotplug events ATIF while the
dGPU is powered down, handle the event and alert userspace.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Some ATPX laptops implement special circuitry to generate
display hotplug events via ACPI when the dGPU is powered off.
Check if this is supported.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Only needed on CIK+ due to the way pci reset is handled
by the GPU.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

This is not necessary as pointed out by Lukas Wunner.

This reverts commit 5e0b1617.

Rather than using "struct file*", use "struct drm_file*" as tag VM tag for
BOs. This will pave the way for "struct drm_file*" without any "struct
file*" back-pointer.
Signed-off-by: NDavid Herrmann <dh.herrmann@gmail.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20160901124837.680-3-dh.herrmann@gmail.com

We get 2 warnings when building kernel with W=1:
drivers/gpu/drm/radeon/radeon_device.c:1961:5: warning: no previous prototype for 'radeon_debugfs_init' [-Wmissing-prototypes]
drivers/gpu/drm/radeon/radeon_device.c:1966:6: warning: no previous prototype for 'radeon_debugfs_cleanup' [-Wmissing-prototypes]

In fact, these functions are dummy, but can be removed,
so this patch removes them.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NBaoyou Xie <baoyou.xie@linaro.org>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Remove unneeded variables and assignments.
Reviewed-by: NGustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: NMasahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: NSean Paul <seanpaul@chromium.org>
Link: http://patchwork.freedesktop.org/patch/msgid/1473863952-7658-3-git-send-email-yamada.masahiro@socionext.com

Ported from nouveau.

v2: re-enable runtime autosuspend in the error case
Acked-by: NEdward O'Callaghan <funfunctor@folklore1984.net>
Reviewed-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Normally on shutdown or reboot we don't care about necessarily
making sure the hw is in a good state because the system is about
to be powered down or reset.  However, after a shutdown or reboot
in a VM, it's best to tear down the hw properly otherwise there
can be problems with the next VM use.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NEdward O'Callaghan <funfunctor@folklore1984.net>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Close was not handled correctly.
Reviewed-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Need to fix the error paths.
Reviewed-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Missed this case previously. No need to do anything if the
device is already off.  runtime pm will handle it.
Acked-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The sbios always powers up the dGPU on resume.
Acked-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Replace packet2's with packet0 writes to UVD_NO_OP.  The
value written to UVD_NO_OP does not matter.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Writes to this register are the preferred way to do NOPs.

Bump the driver version as well.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

In an if block for (running == 0) running cannot be non-zero.

v2: agd: remove unused variable
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NHeinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

In an if block for (running == 0) running cannot be non-zero.

v2: agd: remove unused variable
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NHeinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This bug seems to be present for a very long time.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Looks like some RV6xx have problems with that.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=97099Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Signed-off-by: NEric Engestrom <eric.engestrom@imgtec.com>
Reviewed-by: NJani Nikula <jani.nikula@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Signed-off-by: NEric Engestrom <eric@engestrom.ch>
[danvet: Clarify that the returned pointer must be freed with
kfree().]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>