Yet another fallout from not considering DP MST hotplug. With the
previous patches we have stable indices, but it might still happen
that a connector gets added between when we allocate the array and
when we actually add a connector. Especially when we back off due to
ww mutex contention or similar issues.
So store the sizes of the arrays in struct drm_atomic_state and double
check them. We don't really care about races except that we want to
use a consistent value, so ACCESS_ONCE is all we need. And if we
indeed notice that we'd overrun the array then just give up and
restart the entire ioctl.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Otherwise the connector might have been unplugged and destroyed while
we didn't look. Yet another fallout from DP MST hotplugging that I
didn't consider.
To make sure we get this right add an appropriate WARN_ON to
drm_atomic_state_clear (obviously only when we actually have a state
to clear up). And reorder all the state_clear and backoff calls to
make it work out properly.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
For async commit, it is *intentional* that those locks are not held.
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Turned out to be much simpler on top of my latest atomic stuff than
what I've feared. Some details:
- Drop the modeset_lock_all snakeoil in drm_plane_init. Same
justification as for the equivalent change in drm_crtc_init done in
commit d0fa1af40e
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon Sep 8 09:02:49 2014 +0200
drm: Drop modeset locking from crtc init function
Without these the drm_modeset_lock_init would fall over the exact
same way.
- Since the atomic core code wraps the locking switching it to
per-plane locks was a one-line change.
- For the legacy ioctls add a plane argument to the locking helper so
that we can grab the right plane lock (cursor or primary). Since the
universal cursor plane might not be there, or someone really crazy
might forgoe the primary plane even accept NULL.
- Add some locking WARN_ON to the atomic helpers for good paranoid
measure and to check that it all works out.
Tested on my exynos atomic hackfest with full lockdep checks and ww
backoff injection.
v2: I've forgotten about the load-detect code in i915.
v3: Thierry reported that in latest 3.18-rc vmwgfx doesn't compile any
more due to
commit 21e88620aa
Author: Rob Clark <robdclark@gmail.com>
Date: Thu Oct 30 13:39:04 2014 -0400
drm/vmwgfx: fix lock breakage
Rebased and fix this up.
Cc: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
v1: original
v2: danvet's kerneldoc nitpicks
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
So my original plan was that the drm core refcounts framebuffers like
with the legacy ioctls. But that doesn't work for a bunch of reasons:
- State objects might live longer than until the next fb change
happens for a plane. For example delayed cleanup work only happens
_after_ the pageflip ioctl has completed. So this definitely doesn't
work without the plane state holding its own references.
- The other issue is transition from legacy to atomic implementations,
where the driver works under a mix of both worlds. Which means
legacy paths might not properly update the ->fb pointer under
plane->state->fb. Which is a bit a problem when then someone comes
around and _does_ try to clean it up when it's long gone.
The second issue is just a bit a transition bug, since drivers should
update plane->state->fb in all the paths that aren't converted yet.
But a bit more robustness for the transition can't hurt - we pull
similar tricks with cleaning up the old fb in the transitional helpers
already.
The pattern for drivers that transition is
if (plane->state)
drm_atomic_set_fb_for_plane(plane->state, plane->fb);
inserted after the fb update has logically completed at the end of
->set_config (or ->set_base/mode_set if using the crtc helpers),
->page_flip, ->update_plane or any other entry point which updates
plane->fb.
v2: Update kerneldoc - copypasta fail.
v3: Fix spelling in the commit message (Sean).
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
In all cases the text requires that new drivers are converted to the
atomic interfaces.
v2: Add overview for state handling.
v3: Review from Sean: Some spelling fixes and drop the misguided
hunk to remove rgba8888 from the plane helpers compat list.
Cc: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The atomic users and helpers assume that there is always a obj->state
structure around. Which means drivers need to somehow create that at
driver load time. Also it should obviously reset hardware state, so
needs to be reset upon resume.
Finally the destroy/duplicate_state functions are an awful lot of
boilerplate if the driver doesn't need anything beyond the default
state objects.
So add helper functions for all of this.
v2: Somehow the plane/connector versions got lost in the first
version.
v3: Add kerneldoc.
v4: Make duplicate_state functions a bit more robust, which is useful
for debugging state tracking issues when transitioning to atomic.
v5: Clear temporary variables in the crtc state when duplicating it,
like ->mode_changed or ->planes_changed. If we don't do this stale
values for these might pollute the next atomic modeset.
v6: Also clear crtc_state->event in case the driver didn't (yet) clear
this out.
v7: Split out wrong squashed commit. Also improve the kerneldoc to
mention that obj->state can be NULL and when. Both suggested by
Daniel Thompson.
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently there is no way to implement async flips using atomic, that
essentially requires us to be able to cancel pending requests
mid-flight.
To be able to do that (and I guess we want this since vblank synced
updates which opportunistically cancel still pending updates seem to be
wanted) we'd need to add a mandatory cancellation mode. Depending upon
the exact semantics we decide upon that could mean that userspace will
not get completion events, or will get them all stacked up.
So reject async updates for now. Also async updates usually means not
vblank synced at all, and I guess for drivers which want to support
this they should simply add a special pageflip handler (since usually
you need a special flip cmd to achieve this). That kind of async flip
is pretty much exclusively just used for games and benchmarks where
dropping just one frame means you'll get a headshot or something bad
like that ... And so slight amounts of tearing is acceptable.
v2: Fixup kerneldoc, reported by Paulo.
v3: Use the set_crtc_for_plane function to assign the crtc, since
otherwise the book-keeping is off.
v4: Update crtc->primary->fb since ->page_flip is the only driver
callback where the core won't do this itself. We might want to fix
this inconsistency eventually.
v5: Use set_crtc_for_connector as suggested by Sean.
v6: Daniel Thompson noticed that my error handling is inconsistent
and that in a few cases I didn't handle fatal errors (i.e. not
-EDEADLK). Fix this by consolidate the ww mutex backoff handling
into one check in the fail: block and flatten the error control
flow everywhere else.
v7: Fix spelling mistake in the commit message (Sean).
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Paulo Zanoni <przanoni@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
No helper function to do it all yet provided since no driver has
support for driver core fences yet. Which we'd need to make the
implementation really generic.
v2: Clarify async howto a bit per the discussion With Rob Clark.
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch is for enabling async commits. It replaces an earlier
approach which added an async boolean paramter to the ->prepare_fb
callbacks. The idea is that prepare_fb picks up the right fence to
synchronize against, which is then used by the synchronous commit
helper. For async commits drivers can either register a callback to
the fence or simply do the synchronous wait in their async work queue.
v2: Remove unused variable.
v3: Only wait for fences after the point of no return in the part
of the commit function which can be run asynchronously. This is after
the atomic state has been swapped in, hence now check
plane->state->fence.
Also add a WARN_ON to make sure we don't try to wait on a fence when
there's no fb, just as a sanity check.
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Well, except page_flip since that requires async commit, which isn't
there yet.
For the functions which changes planes there's a bit of trickery
involved to keep the fb refcounting working. But otherwise fairly
straight-forward atomic updates.
The property setting functions are still a bit incomplete. Once we
have generic properties (e.g. rotation, but also all the properties
needed by the atomic ioctl) we need to filter those out and parse them
in the helper. Preferrably with the same function as used by the real
atomic ioctl implementation.
v2: Fixup kerneldoc, reported by Paulo.
v3: Add missing EXPORT_SYMBOL.
v4: We need to look at the crtc of the modeset, not some random
leftover one from a previous loop when udpating the connector->crtc
routing. Also push some local variables into inner loops to avoid
these kinds of bugs.
v5: Adjust semantics - drivers now own the atomic state upon
successfully synchronous commit.
v6: Use the set_crtc_for_plane function to assign the crtc, since
otherwise the book-keeping is off.
v7:
- Improve comments.
- Filter out the crtc of the ->set_config call when recomputing
crtc_state->enabled: We should compute the same state, but not doing
so will give us a good chance to catch bugs and inconsistencies -
the atomic helper's atomic_check function re-validates this again.
- Fix the set_config implementation logic when disabling the crtc: We
still need to update the output routing to disable all the
connectors properly in the state. Caught by the atomic_check
functions, so at least that part worked ;-) Also add some WARN_ONs
to ensure ->set_config preconditions all apply.
v8: Fixup an embarrassing h/vdisplay mixup.
v9: Shuffled bad squash to the right patch, spotted by Daniel
v10: Use set_crtc_for_connector as suggested by Sean.
v11: Daniel Thompson noticed that my error handling is inconsistent
and that in a few cases I didn't handle fatal errors (i.e. not
-EDEADLK). Fix this by consolidate the ww mutex backoff handling
into one check in the fail: block and flatten the error control
flow everywhere else.
v12: Review and discussion with Sean:
- One spelling fix.
- Correctly skip the crtc from the set_config set when recomputing
->enable state. That should allow us to catch any bugs in higher
levels in computing that state (which is supplied to the
->set_config implementation). I've screwed this up and Sean spotted
that the current code is pointless.
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Paulo Zanoni <przanoni@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
So this is finally the integration of the crtc and plane helper
interfaces into the atomic helper functions.
In the check function we now have a few steps:
- First we update the output routing and figure out which crtcs need a
full mode set. Suitable encoders are selected using ->best_encoder,
with the same semantics as the crtc helpers of implicitly disabling
all connectors currently using the encoder.
- Then we pull all other connectors into the state update which feed
from a crtc which changes. This must be done do catch mode changes
and similar updates - atomic updates are differences on top of the
current state.
- Then we call all the various ->mode_fixup to compute the adjusted
mode. Note that here we have a slight semantic difference compared
to the crtc helpers: We have not yet updated the encoder->crtc link
when calling the encoder's ->mode_fixup function. But that's a
requirement when converting to atomic since we want to prepare the
entire state completely contained with the over drm_atomic_state
structure. So this must be carefully checked when converting drivers
over to atomic helpers.
- Finally we do call the atomic_check functions on planes and crtcs.
The commit function is also quite a beast:
- The only step that can fail is done first, namely pinning the
framebuffers. After that we cross the point of no return, an async
commit would push all that into the worker thread.
- The disabling of encoders and connectors is a bit tricky, since
depending upon the final state we need to select different crtc
helper functions.
- Software tracking is a bit clarified compared to the crtc helpers:
We commit the software state before starting to touch the hardware,
like crtc helpers. But since we just swap them we still have the old
state (i.e. the current hw state) around, which is really handy to
write simple disable functions. So no more
drm_crtc_helper_disable_all_unused_functions kind of fun because
we're leaving unused crtcs/encoders behind. Everything gets shut
down in-order now, which is one of the key differences of the i915
helpers compared to crtc helpers and a really nice additional
guarantee.
- Like with the plane helpers the atomic commit function waits for one
vblank to pass before calling the framebuffer cleanup function.
Compared to Rob's helper approach there's a bunch of upsides:
- All the interfaces which can fail are called in the ->check hook
(i.e. ->best_match and the various ->mode_fixup hooks). This means
that drivers can just reuse those functions and don't need to move
everything into ->atomic_check callbacks. If drivers have no need
for additional constraint checking beyong their existing crtc
helper callbacks they don't need to do anything.
- The actual commit operation is properly stage: First we prepare
framebuffers, which can potentially still fail (due to memory
exhausting). This is important for the async case, where this must
be done synchronously to correctly return errors.
- The output configuration changes (done with crtc helper functions)
and the plane update (using atomic plane helpers) are correctly
interleaved: First we shut down any crtcs that need changing, then
we update planes and finally we enable everything again. Hardware
without GO bits must be more careful with ordering, which this
sequence enables.
- Also for hardware with shared output resources (like display PLLs)
we first must shut down the old configuration before we can enable
the new one. Otherwise we can hit an impossible intermediate state
where there's not enough PLLs (which is the point behind atomic
updates).
v2:
- Ensure that users of ->check update crtc_state->enable correctly.
- Update the legacy state in crtc/plane structures. Eventually we want
to remove that, but for now the drm core still expects this (especially
the plane->fb pointer).
v3: A few changes for better async handling:
- Reorder the software side state commit so that it happens all before
we touch the hardware. This way async support becomes very easy
since we can punt all the actual hw touching to a worker thread. And
as long as we synchronize with that thread (flushing or cancelling,
depending upon what the driver can handle) before we commit the next
software state there's no need for any locking in the worker thread
at all. Which greatly simplifies things.
And as long as we synchronize with all relevant threads we can have
a lot of them (e.g. per-crtc for per-crtc updates) running in
parallel.
- Expose pre/post plane commit steps separately. We need to expose the
actual hw commit step anyway for drivers to be able to implement
asynchronous commit workers. But if we expose pre/post and plane
commit steps individually we allow drivers to selectively use atomic
helpers.
- I've forgotten to call encoder/bridge ->mode_set functions, fix
this.
v4: Add debug output and fix a mixup between current and new state
that resulted in crtcs not getting updated correctly. And in an
Oops ...
v5:
- Be kind to driver writers in the vblank wait functions.. if thing
aren't working yet, and vblank irq will never come, then let's not
block forever.. especially under console-lock.
- Correctly clear connector_state->best_encoder when disabling.
Spotted while trying to understand a report from Rob Clark.
- Only steal encoder if it actually changed, otherwise hilarity ensues
if we steal from the current connector and so set the ->crtc pointer
unexpectedly to NULL. Reported by Rob Clark.
- Bail out in disable_outputs if an output currently doesn't have a
best_encoder - this means it's already disabled.
v6: Fixupe kerneldoc as reported by Paulo. And also fix up kerneldoc
in drm_crtc.h.
v7: Take ownership of the atomic state and clean it up with
drm_atomic_state_free().
v8 Various improvements all over:
- Polish code comments and kerneldoc.
- Improve debug output to make sure all failure cases are logged.
- Treat enabled crtc with no connectors as invalid input from userspace.
- Don't ignore the return value from mode_fixup().
v9:
- Improve debug output for crtc_state->mode_changed.
v10:
- Fixup the vblank waiting code to properly balance the vblank_get/put
calls.
- Better comments when checking/computing crtc->mode_changed
v11: Fixup the encoder stealing logic: We can't look at encoder->crtc
since that's not in the atomic state structures and might be updated
asynchronously in and async commit. Instead we need to inspect all the
connector states and check whether the encoder is currently in used
and if so, on which crtc.
v12: Review from Sean:
- A few spelling fixes.
- Flatten control flow indent by converting if blocks to early
continue/return in 2 places.
- Capture connectors_for_crtc return value in int num_connectors
instead of bool has_connectors and do an explicit int->bool
conversion with !!. I think the helper is more useful for drivers if
it returns the number of connectors (e.g. to detect cloning
configurations), so decided to keep that return value.
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Paulo Zanoni <przanoni@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is the first cut of atomic helper code. As-is it's only useful to
implement a pure atomic interface for plane updates.
Later patches will integrate this with the crtc helpers so that full
atomic updates are possible. We also need a pile of helpers to aid
drivers in transitioning from the legacy world to the shiny new atomic
age. Finally we need helpers to implement legacy ioctls on top of the
atomic interface.
The design of the overall helpers<->driver interaction is fairly
simple, but has an unfortunate large interface:
- We have ->atomic_check callbacks for crtcs and planes. The idea is
that connectors don't need any checking, and if they do they can
adjust the relevant crtc driver-private state. So no connector hooks
should be needed. Also the crtc helpers integration will do the
->best_encoder checks, so no need for that.
- Framebuffer pinning needs to be done before we can commit to the hw
state. This is especially important for async updates where we must
pin all buffers before returning to userspace, so that really only
hw failures can happen in the asynchronous worker.
Hence we add ->prepare_fb and ->cleanup_fb hooks for this resources
management.
- The actual atomic plane commit can't fail (except hw woes), so has
void return type. It has three stages:
1. Prepare all affected crtcs with crtc->atomic_begin. Drivers can
use this to unset the GO bit or similar latches to prevent plane
updates.
2. Update plane state by looping over all changed planes and calling
plane->atomic_update. Presuming the hardware is sane and has GO
bits drivers can simply bash the state into the hardware in this
function. Other drivers might use this to precompute hw state for
the final step.
3. Finally latch the update for the next vblank with
crtc->atomic_flush. Note that this function doesn't need to wait
for the vblank to happen even for the synchronous case.
v2: Clear drm_<obj>_state->state to NULL when swapping in state.
v3: Add TODO that we don't short-circuit plane updates for now. Likely
no one will care.
v4: Squash in a bit of polish that somehow landed in the wrong (later)
patche.
v5: Integrate atomic functions into the drm docbook and fixup the
kerneldoc.
v6: Fixup fixup patch squashing fumble.
v7: Don't touch the legacy plane state plane->fb and plane->crtc. This
is only used by the legacy ioctl code in the drm core, and that code
already takes care of updating the pointers in all relevant cases.
This is in stark contrast to connector->encoder->crtc links on the
modeset side, which we still need to set since the core doesn't touch
them.
Also some more kerneldoc polish.
v8: Drop outdated comment.
v9: Handle the state->state pointer correctly: Only clearing the
->state pointer when assigning the state to the kms object isn't good
enough. We also need to re-link the swapped out state into the
drm_atomic_state structure.
v10: Shuffle the misplaced docbook template hunk around that Sean spotted.
Cc: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>