Better encapsulate the per-timeline stuff into fence-context. For now
there is just a single fence-context, but eventually we'll also have one
per-CRTC to enable fully explicit fencing.
Signed-off-by: Rob Clark <robdclark@gmail.com>
With drivers supporting runtime pm it's generally not a good idea to
touch the hardware when it's off. Add an option to the commit_planes
helper to support this case.
Note that the helpers already add all planes on a crtc when a modeset
happens, hence plane updates will not be lost if drivers set this to
true.
v2: Check for NULL state->crtc before chasing the pointer. Also check
both old and new crtc if there's a switch. Finally just outright
disallow switching crtcs for a plane if the plane is in active use, on
most hardware that doesn't make sense.
v3: Since commit_planes(active_only = true) is for enabling things
only after all the crtc are on we should only look at the new crtc to
decide whether to call the plane hooks - if the current CRTC isn't on
then skip. If the old crtc (when moving a plane) went down then the
plane should have been disabled as part of the pipe shutdown work
already. For which there's currently no helper really unfortunately.
Also move the check for wether a plane gets a new CRTC assigned while
still in active use out of this patch.
v4: Rebase over exynos changes.
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Thierry Reding <treding@nvidia.com>
Cc: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Tested-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
The atomic commit cannot easily undo and return an error once the
state is swapped. Change to uninterruptible wait, and ignore the
timeout error.
Signed-off-by: Wentao Xu <wentaox@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
The 'timeout' value comes from userspace (CLOCK_MONOTONIC), but
converting this directly to jiffies doesn't take into account the
initial jiffies count at boot, which may differ from the base time
of CLOCK_MONOTONIC.
TODO: add ktime_delta_jiffies() when rebasing on 4.1 and use that
instead of ktime_sub/ktime_to_timespec/timespec_to_jiffies combo (as
suggested by Arnd)
v2: switch over from 'struct timespec' to ktime_t throughout, since
'struct timespec' will be deprecated (as suggested by Arnd)
v3: minor cosmetic tweaks
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rob Clark <robdclark@gmail.com>
When the .atomic_commit() handler fails, clean up planes previoulsy
prepared by drm_atomic_helper_prepare_planes() with a call to
drm_atomic_helper_cleanup_planes().
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Rob Clark <robdclark@gmail.com>
MDP FLUSH registers could indicate if the previous flush updates
has taken effect at vsync boundary. Making use of this H/W feature
can catch the vsync that happened between CRTC atomic_flush and
*_wait_for_vblanks, to avoid unnecessary wait.
This change allows kms CRTCs to use their own *_wait_for_commit_done
functions to wait for FLUSH register cleared at vsync, before commit
completion.
Signed-off-by: Hai Li <hali@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJU/NacAAoJEHm+PkMAQRiGdUcIAJU5dHclwd9HRc7LX5iOwYN6
mN0aCsYjMD8Pjx2VcPCgJvkIoESQO5pkwYpFFWCwILup1bVEidqXfr8EPOdThzdh
kcaT0FwUvd19K+0jcKVNCX1RjKBtlUfUKONk6sS2x4RrYZpv0Ur8Gh+yXV8iMWtf
fAusNEYlxQJvEz5+NSKw86EZTr4VVcykKLNvj+/t/JrXEuue7IG8EyoAO/nLmNd2
V/TUKKttqpE6aUVBiBDmcMQl2SUVAfp5e+KJAHmizdDpSE80nU59UC1uyV8VCYdM
qwHXgttLhhKr8jBPOkvUxl4aSXW7S0QWO8TrMpNdEOeB3ZB8AKsiIuhe1JrK0ro=
=Xkue
-----END PGP SIGNATURE-----
Merge tag 'v4.0-rc3' into drm-next
Linux 4.0-rc3 backmerge to fix two i915 conflicts, and get
some mainline bug fixes needed for my testing box
Conflicts:
drivers/gpu/drm/i915/i915_drv.h
drivers/gpu/drm/i915/intel_display.c
If the atomic commit fails due to completion wait interruption the
atomic commit object is not freed and is thus leaked. Free it.
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Rob Clark <robdclark@gmail.com>
These names only make sense because of backwards compatability with
the order used by the crtc helper library. There's not really any real
requirement in the ordering here.
So rename them to something more descriptive and update the kerneldoc
a bit. Motivated in a discussion with Laurent about how to restore
plane state for dpms for drivers with runtime pm.
v2: Squash in fixup from Stephen Rothwell to fix a conflict with
tegra.
Cc: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Acked-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
The gnome-shell wayland compositor triggers a setcrtc with an fb that is
still being rendered, triggering the call to _wait_fence_interruptable().
But a NULL timeout means "don't wait, return -EBUSY if not ready", which
in turn causes the setcrtc to fail.
Signed-off-by: Rob Clark <robdclark@gmail.com>
As a result of atomic DPMS support, the various prepare/commit hooks get
called in a way that msm dislikes. We were expecting prepare/commit to
bracket a modeset, which is no longer the case. This was needed to hold
various extra clk's (such as interface clks) on while we are touching
registers, and in the case of mdp4 holding vblank enabled.
The most straightforward way to deal with this, since we already have
our own atomic_commit(), is to just handle prepare/commit internally to
the driver (with some additional vfuncs for mdp4 vs mdp5), and switch
everything over to instead use the new enable/disable hooks. It doesn't
really change too much, despite the code motion. What used to be in the
encoder/crtc dpms() fxns is split out into enable/disable.
We should be able to drop our own enable-state tracking, as the atomic
helpers should do this for us. But keeping that for the short term for
extra debugging as atomic stablizes.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Next batch of atomic work. Most important is the propertification from Rob
and the nth iteration of the actual atomic ioctl originally from Ville.
Big differences compared to earlier revisions:
- Core properties are now fully handled by the core, drivers can only
handle driver-specific properties.
- Atomic props&ioctl are opt-in per file_priv, userspace needs to
explicitly ask for it (like universal plane support).
- For now all hidden behind the atomic module option until this has
settled a bit.
- Atomic modesets are currently not possible since the exact abi for how
to handle the mode property is still under discussion.
Besides this some cleanup patches from me and the addition of per-object
state to global state backpointers to simplify drivers.
* tag 'topic/atomic-core-2015-01-05' of git://anongit.freedesktop.org/drm-intel:
drm: Ensure universal_planes is set for atomic
drm/atomic: Hide drm.ko internal interfaces
drm: Atomic modeset ioctl
drm/atomic: atomic connector properties
drm/atomic: atomic plane properties
drm: small property creation cleanup
drm/atomic: atomic_check functions
drm: add atomic properties
drm: refactor getproperties/getconnector
drm: tweak getconnector locking
drm: add atomic_get_property
drm: add atomic_set_property wrappers
drm: get rid of direct property value access
drm: store property instead of id in obj attachment
drm: allow property validation for refcnted props
drm/atomic: Introduce state->obj backpointers
drm/atomic-helper: Again check modeset *before* plane states
drm/atomic-helper: Export both plane and modeset check helpers
We can't have multiple updates pending on a given CRTC, and we don't
want a sync update to race w/ an async update that preceeded it. So
keep track of which CRTCs have updates in flight, and block later
updates that would conflict.
Signed-off-by: Rob Clark <robdclark@gmail.com>
This essentially reverts
commit 934ce1c236
Author: Rob Clark <robdclark@gmail.com>
Date: Wed Nov 19 16:41:33 2014 -0500
drm/atomic: check mode_changed *after* atomic_check
Depending upon the driver both orders (or maybe even interleaving) is
required:
- If ->atomic_check updates ->mode_changed then helper_check_modeset
must be run afters.
- If ->atomic_check depends upon accurate adjusted dotclock values for
e.g. watermarks, then helper_check_modeset must be run first.
The failure mode in the first case is usually a totally angry hw
because the pixel format switching doesn't happen. The failure mode in
the later case is usually nothing, since in most cases the old
adjusted mode from the previous modeset wont be too far off to be a
problem. So just underruns and perhaps even just suboptimal (from a
power consumption) watermarks.
Furthermore in the transitional helpers we only call ->atomic_check
after the new modeset state has been fully set up (and hence
computed).
Given that asymmetry in expected failure modes I think it's safer to
go back to the older order. So do that and give msm a special check
function to compensate.
Also update kerneldoc to explain this a bit.
v2: Actually add the missing hunk Rob spotted.
v3: Move msm_atomic_check into msm_atomic.c, requested by Rob.
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Tested-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Rob Clark