[Why]
The wait_for_vblank boolean in commit_tail was passed by reference
into each stream commit, and if that commit was an asynchronous
flip, it would disable vblank waits on all subsequent flips.
This made the behaviour depend on crtc order in a non-intuitive way,
although since the asynchronous pageflip flag is only used by the
legacy IOCTLs at the moment it is never an issue
[How]
Find wait_for_vblank before doing any stream commits
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHY]
When doing split pipe, if one pipe is pending on flip, the entire
plane's status should be flip pending, otherwise corruption can occur
when OS writes to a surface prematurely.
[HOW]
Clear the flip pending bit before checking pipes, then OR the flip
pending bits from all pipes together to create the flip pending status
of the entire plane.
Signed-off-by: Wesley Chalmers <Wesley.Chalmers@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Eryk Brol <Eryk.Brol@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
AUX arbitration occurs between SW and FW components.
When AUX acquire fails, it causes engine->ddc to be NULL,
which leads to an exception when we try to release the AUX
engine.
[How]
When AUX engine acquire fails, it should return from the
function without trying to continue the operation.
The upper level will determine if it wants to retry.
i.e. dce_aux_transfer_with_retries will be used and retry.
Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Seamless boot tries to reuse planes that were enabled for the first
commit applied.
In the case where Raven is booting with two monitors connected and the
first commit contains two streams the screen corruption would occur
because the second stream was trying to re-use a tg and plane that
weren't previously enabled.
The state on the first commit looks something like the following:
TG0: enabled=1
TG1: enabled=0
TG2: enabled=0
TG3: enabled=0
New state: pipe=0, stream=0, plane=0, new_tg=0
New state: pipe=1, stream=1, plane=1, new_tg=1
New state: pipe=2, stream=NULL, plane=NULL, new_tg=NULL
New state: pipe=3, stream=NULL, plane=NULL, new_tg=NULL
Only one plane/tg is setup before we enter accelerated mode so
we really want to disabling everything but that first plane.
[How]
Check if the stream is not NULL and if the tg is enabled before
deciding whether to skip the plane disable.
Also ensure we're also disabling on the current state's pipe_ctx so
we don't overwrite the fields in the new pending state.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This change changes dc add plane logic to allow plane-less resource
reservation (pipe split).
If a free pipe_ctx (no plane_state attached) is the head pipe, and is
found with a bottom pipe attached, assign the plane to add on the bottom
pipe.
In addition, prepend dcn10 to dcn10-specific reset_back_end_for_pipe
and reset_hw_ctx_wrap
Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Driver need to poll the SURFACE_INUSE register to determine when to
start the new task and write data to the checked surface.
Implement the wait functions, and add the necessary hubbub registers.
Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Seamless boot code not working on all ASICs because of
some underflow issues caused by some uninitialized HW
state.
[How]
Keep some logical and power gating init code in hw_init.
Move some per pipe init code to enable accelerated mode
Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Make dml and integration with pplib clearer.
[How]
Change the way the dml formula is initialized to make its values more
clear. Restructure DC interface with pplib into rv_funcs.
Cap clocks received from pplib.
Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Signed-off-by: Eryk Brol <eryk.brol@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In VRR mode, keep track of the vblank count of the last
completed pageflip in amdgpu_crtc->last_flip_vblank, as
recorded in the pageflip completion handler after each
completed flip.
Use that count to prevent mmio programming a new pageflip
within the same vblank in which the last pageflip completed,
iow. to throttle pageflips to at most one flip per video
frame, while at the same time allowing to request a flip
not only before start of vblank, but also anywhere within
vblank.
The old logic did the same, and made sense for regular fixed
refresh rate flipping, but in vrr mode it prevents requesting
a flip anywhere inside the possibly huge vblank, thereby
reducing framerate in vrr mode instead of improving it, by
delaying a slightly delayed flip requests up to a maximum
vblank duration + 1 scanout duration. This would limit VRR
usefulness to only help applications with a very high GPU
demand, which can submit the flip request before start of
vblank, but then have to wait long for fences to complete.
With this method a flip can be both requested and - after
fences have completed - executed, ie. it doesn't matter if
the request (amdgpu_dm_do_flip()) gets delayed until deep
into the extended vblank due to cpu execution delays. This
also allows clients which want to regulate framerate within
the vrr range a much more fine-grained control of flip timing,
a feature that might be useful for video playback, and is
very useful for neuroscience/vision research applications.
In regular non-VRR mode, retain the old flip submission
behavior. This to keep flip scheduling for fullscreen X11/GLX
OpenGL clients intact, if they use the GLX_OML_sync_control
extensions glXSwapBufferMscOML(, ..., target_msc,...) function
with a specific target_msc target vblank count.
glXSwapBuffersMscOML() or DRI3/Present PresentPixmap() will
not flip at the proper target_msc for a non-zero target_msc
if VRR mode is active with this patch. They'd often flip one
frame too early. However, this limitation should not matter
much in VRR mode, as scheduling based on vblank counts is
pretty futile/unusable under variable refresh duration
anyway, so no real extra harm is done.
According to some testing already done with this patch by
Nicholas on top of my tests, IGT tests didn't report any
problems. If fixes stuttering and flickering when flipping
at rates below the minimum vrr refresh rate.
Fixes: bb47de7366 ("drm/amdgpu: Set FreeSync state using drm VRR
properties")
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: <stable@vger.kernel.org>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Michel Dänzer <michel@daenzer.net>
Tested-by: Bruno Filipe <bmilreu@gmail.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The DP 1.4 spec defines the SDP header and SDP contents for
a Picture Parameter Set (PPS) that must be sent in advance
of DSC transmission to define the encoding characteristics.
This was done in one struct, drm_dsc_pps_infoframe, which
conatined the SDP header and PPS. Because the PPS is
a property of DSC over any connector, not just DP, and because
drm drivers may have their own SDP structs they wish to use,
make the functions that initialise SDP and PPS headers take
the components they operate on, not drm_dsc_pps_infoframe,
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190221202001.28430-4-David.Francis@amd.com
Native 420 and 422 transfer modes are new in DSC1.2
In these modes, each two pixels of a slice are treated as one
pixel, so the slice width is half as large (round down) for
the purposes of calucating the groups per line and chunk size
in bytes
In native 422 mode, each pixel has four components, so the
mux component of a group is larger by one additional mux word
and one additional component
Now that there is native 422 support, the configuration option
previously called enable422 is renamed to simple_422 to avoid
confusion
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: David Francis <David.Francis@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190221202001.28430-3-David.Francis@amd.com
In the next patch, we are introducing a broad virtual engine to encompass
multiple physical engines, losing the 1:1 nature of BIT(engine->id). To
reflect the broader set of engines implied by the virtual instance, lets
store the full bitmask.
v2: Use intel_engine_mask_t (s/ring_mask/engine_mask/)
v3: Tvrtko voted for moah churn so teach everyone to not mention ring
and use $class$instance throughout.
v4: Comment upon the disparity in bspec for using VCS1,VCS2 in gen8 and
VCS[0-4] in later gen. We opt to keep the code consistent and use
0-index naming throughout.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190305180332.30900-1-chris@chris-wilson.co.uk
As we allow per-context engine allows the legacy concept of
I915_EXEC_RING no longer applies universally. We are still exposing the
unrelated exec-id in GEM_BUSY, so transition this ioctl (once more
slightly changing its ABI, but no one cares) over to only reporting the
uabi-class (not instance as we can not foreseeably fit those into the
small bitmask).
The only user of the extended ring information from GEM_BUSY is ddx/sna,
which tries to use the non-rcs business information to guide which
engine to use for subsequent operations on foreign bo. All that matters
for it is the decision between rcs and !rcs, so it is unaffected by the
change in higher bits.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190305162643.20243-1-chris@chris-wilson.co.uk
The following pixel formats are packed format that follows 4:2:2
chroma sampling. For memory represenation each component is
allocated 16 bits each. Thus each pixel occupies 32bit.
Y210: For each component, valid data occupies MSB 10 bits.
LSB 6 bits are filled with zeroes.
Y212: For each component, valid data occupies MSB 12 bits.
LSB 4 bits are filled with zeroes.
Y216: For each component valid data occupies 16 bits,
doesn't require any padding bits.
First 16 bits stores the Y value and the next 16 bits stores one
of the chroma samples alternatively. The first luma sample will
be accompanied by first U sample and second luma sample is
accompanied by the first V sample.
The following pixel formats are packed format that follows 4:4:4
chroma sampling. Channels are arranged in the order UYVA in
increasing memory order.
Y410: Each color component occupies 10 bits and X component
takes 2 bits, thus each pixel occupies 32 bits.
Y412: Each color component is 16 bits where valid data
occupies MSB 12 bits. LSB 4 bits are filled with zeroes.
Thus, each pixel occupies 64 bits.
Y416: Each color component occupies 16 bits for valid data,
doesn't require any padding bits. Thus, each pixel
occupies 64 bits.
v3: fixed missing tab for XYUV8888 (JP)
Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Vidya Srinivas <vidya.srinivas@intel.com>
Reviewed-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1551700595-21481-5-git-send-email-swati2.sharma@intel.com
In VRR mode, keep track of the vblank count of the last
completed pageflip in amdgpu_crtc->last_flip_vblank, as
recorded in the pageflip completion handler after each
completed flip.
Use that count to prevent mmio programming a new pageflip
within the same vblank in which the last pageflip completed,
iow. to throttle pageflips to at most one flip per video
frame, while at the same time allowing to request a flip
not only before start of vblank, but also anywhere within
vblank.
The old logic did the same, and made sense for regular fixed
refresh rate flipping, but in vrr mode it prevents requesting
a flip anywhere inside the possibly huge vblank, thereby
reducing framerate in vrr mode instead of improving it, by
delaying a slightly delayed flip requests up to a maximum
vblank duration + 1 scanout duration. This would limit VRR
usefulness to only help applications with a very high GPU
demand, which can submit the flip request before start of
vblank, but then have to wait long for fences to complete.
With this method a flip can be both requested and - after
fences have completed - executed, ie. it doesn't matter if
the request (amdgpu_dm_do_flip()) gets delayed until deep
into the extended vblank due to cpu execution delays. This
also allows clients which want to regulate framerate within
the vrr range a much more fine-grained control of flip timing,
a feature that might be useful for video playback, and is
very useful for neuroscience/vision research applications.
In regular non-VRR mode, retain the old flip submission
behavior. This to keep flip scheduling for fullscreen X11/GLX
OpenGL clients intact, if they use the GLX_OML_sync_control
extensions glXSwapBufferMscOML(, ..., target_msc,...) function
with a specific target_msc target vblank count.
glXSwapBuffersMscOML() or DRI3/Present PresentPixmap() will
not flip at the proper target_msc for a non-zero target_msc
if VRR mode is active with this patch. They'd often flip one
frame too early. However, this limitation should not matter
much in VRR mode, as scheduling based on vblank counts is
pretty futile/unusable under variable refresh duration
anyway, so no real extra harm is done.
According to some testing already done with this patch by
Nicholas on top of my tests, IGT tests didn't report any
problems. If fixes stuttering and flickering when flipping
at rates below the minimum vrr refresh rate.
Fixes: bb47de7366 ("drm/amdgpu: Set FreeSync state using drm VRR
properties")
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: <stable@vger.kernel.org>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Michel Dänzer <michel@daenzer.net>
Tested-by: Bruno Filipe <bmilreu@gmail.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The ptr_to_compat() call takes a "void __user *", so cast
the compat drm calls that use it to avoid the following
warnings from sparse:
drivers/gpu/drm/drm_ioc32.c:188:39: warning: incorrect type in argument 1 (different address spaces)
drivers/gpu/drm/drm_ioc32.c:188:39: expected void [noderef] <asn:1>*uptr
drivers/gpu/drm/drm_ioc32.c:188:39: got void *[addressable] [assigned] handle
drivers/gpu/drm/drm_ioc32.c:529:41: warning: incorrect type in argument 1 (different address spaces)
drivers/gpu/drm/drm_ioc32.c:529:41: expected void [noderef] <asn:1>*uptr
drivers/gpu/drm/drm_ioc32.c:529:41: got void *[addressable] [assigned] handle
Cc: stable@vger.kernel.org
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20190301120046.26961-1-ben.dooks@codethink.co.uk
This protects device resources from use after device removal.
There are 3 ways for driver-device unbinding to happen:
- The driver module is unloaded causing the driver to be unregistered.
This can't happen as long as there are open file handles because a
reference is taken on the module.
- The device is removed (Device Tree overlay unloading).
This can happen at any time.
- The driver sysfs unbind file can be used to unbind the driver from the
device. This can happen any time.
v2: Since drm_atomic_helper_shutdown() has to be called after
drm_dev_unplug() we don't want do block ->disable after unplug.
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190225144232.20761-8-noralf@tronnes.org
