Commit graph

16551 commits

Author SHA1 Message Date
Thomas Wood 3a5f87c286 drm: fix plane rotation when restoring fbdev configuration
Make sure plane rotation is reset correctly when restoring the fbdev
configuration by using drm_mode_plane_set_obj_prop which calls the
driver's set_property callback.

The rotation reset feature was introduced in commit 9783de2 (drm:
Resetting rotation property) and the callback issue was originally
addressed in a previous version of the patch, but the fix was not
present in the final version.

v2: Fix documentation warning
    Add some more details to the commit message (Daniel Vetter)

Testcase: igt/kms_rotation_crc
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=82236
Cc: Sonika Jindal <sonika.jindal@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thomas Wood <thomas.wood@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:19:27 +02:00
Damien Lespiau fd639ac6dc drm/i915/bdw: Disable execlists by default
We still have a few missing bits and pieces to have execlists enabled by
default eg. the error capture or the render state initialization and so
it wouldn't be wise to enable it by default on BDW just yet.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Tested-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=82740
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:52 +02:00
Oscar Mateo d7f621e507 drm/i915/bdw: Enable Logical Ring Contexts (hence, Execlists)
The time has come, the Walrus said, to talk of many things.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:52 +02:00
Oscar Mateo 73e4d07f8a drm/i915/bdw: Document Logical Rings, LR contexts and Execlists
Add theory of operation notes to intel_lrc.c and comments to externally
visible functions.

v2: Add notes on logical ring context creation.

v3: Use kerneldoc.

v4: Integrate it in the DocBook template.

Signed-off-by: Thomas Daniel <thomas.daniel@intel.com> (v1)
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com> (v2, v3)
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Drop hunk about render ring init function since that's not
yet merged.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:51 +02:00
Ben Widawsky c0ab1ae902 drm/i915/bdw: Print context state in debugfs
This has turned out to be really handy in debug so far.

Update:
Since writing this patch, I've gotten similar code upstream for error
state. I've used it quite a bit in debugfs however, and I'd like to keep
it here at least until preemption is working.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>

This patch was accidentally dropped in the first Execlists version, and
it has been very useful indeed. Put it back again, but as a standalone
debugfs file.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>

v2: Take the device struct_mutex rather than mode_config mutex for
atomic state capture.

Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:51 +02:00
Oscar Mateo c9fe99bd4c drm/i915/bdw: Display context backing obj & ringbuffer info in debugfs
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:50 +02:00
Oscar Mateo 4ba70e448b drm/i915/bdw: Display execlists info in debugfs
v2: Warn and return if LRCs are not enabled.

v3: Grab the Execlists spinlock (noticed by Daniel Vetter).

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>

v4: Lock the struct mutex for atomic state capture

Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:49 +02:00
Oscar Mateo 71386ef900 drm/i915/bdw: Disable semaphores for Execlists
Up until recently, semaphores weren't enabled in BDW so we didn't care
about them. But then Rodrigo came and enabled them:

   commit 521e62e49a
   Author: Rodrigo Vivi <rodrigo.vivi@intel.com>

      drm/i915: Enable semaphores on BDW

So now we have to explicitly disable them for Execlists until both
features play nicely.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:49 +02:00
Oscar Mateo cc9130be80 drm/i915/bdw: Make sure gpu reset still works with Execlists
If we reset a ring after a hang, we have to make sure that we clear
out all queued Execlists requests.

v2: The ring is, at this point, already being correctly re-programmed
for Execlists, and the hangcheck counters cleared.

v3: Daniel suggests to drop the "if (execlists)" because the Execlists
queue should be empty in legacy mode (which is true, if we do the
INIT_LIST_HEAD).

v4: Do the pending intel_runtime_pm_put

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:48 +02:00
Oscar Mateo b7c71823f1 drm/i915/bdw: Don't write PDP in the legacy way when using LRCs
This is mostly for correctness so that we know we are running the LR
context correctly (this is, the PDPs are contained inside the context
object).

v2: Move the check to inside the enable PPGTT function. The switch
happens in two places: the legacy context switch (that we won't hit
when Execlists are enabled) and the PPGTT enable, which unfortunately
we need. This would look much nicer if the ppgtt->enable was part of
the ring init, where it logically belongs.

v3: Move the check to the start of the enable PPGTT function.  None
of the legacy PPGTT enabling is required when using LRCs as the
PPGTT is enabled in the context descriptor and the PDPs are written
in the LRC.

v4: Clarify comment based on review feedback.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Resolve conflicts with ppgtt_enable rework.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-20 17:17:48 +02:00
Alex Deucher b738ca5d68 Revert "drm/radeon: Use write-combined CPU mappings of ring buffers with PCIe"
This reverts commit 1490434f0d.

Several people have reported regressions with this patch on kabini.
2014-08-19 12:01:50 -04:00
Alex Deucher 52da51f0f9 drm/radeon: fix active_cu mask on SI and CIK after re-init (v3)
Need to initialize the mask to 0 on init, otherwise it
keeps increasing.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=82581

v2: also fix cu count
v3: split count fix into separate patch

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Cc: stable@vger.kernel.org
2014-08-19 12:01:49 -04:00
Alex Deucher 6101b3ae94 drm/radeon: fix active cu count for SI and CIK
This fixes the CU count reported to userspace for
OpenCL.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=82581

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Cc: stable@vger.kernel.org
2014-08-19 12:01:48 -04:00
Alex Deucher cd1c9c1a4b drm/radeon: re-enable selective GPUVM flushing
Now that the PFP and ME synchronization is fixed, we
can enable this again reliably.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
2014-08-19 11:48:30 -04:00
Christian König 86302eeade drm/radeon: Sync ME and PFP after CP semaphore waits v4
Fixes lockups due to CP read GPUVM faults when running piglit on Cape
Verde.

v2 (chk): apply the fix to R600+ as well, on CIK only the GFX CP has
	  a PFP, add more comments to R600 code, enable flushing again
v3: (agd5f): only apply to 7xx+.  r6xx does not have the packet.
v4: (agd5f): split flush change into a separate patch, fix formatting

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
2014-08-19 11:44:47 -04:00
Alex Deucher 73ef0e0d62 drm/radeon: fix display handling in radeon_gpu_reset
If the display hw was reset or a hard reset was used,
we need to re-init some of the common display hardware as well.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-08-19 11:29:22 -04:00
Alex Deucher c940b4476f drm/radeon: fix pm handling in radeon_gpu_reset
pm_suspend is handled in the radeon_suspend callbacks.
pm_resume has special handling depending on whether
dpm or legacy pm is enabled.  Change radeon_gpu_reset
to mirror the behavior in the suspend and resume
pathes.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org
2014-08-19 11:29:21 -04:00
Michel Dänzer 1538a9e0e0 drm/radeon: Only flush HDP cache for indirect buffers from userspace
It isn't necessary for command streams generated by the kernel (at least
not while we aren't storing ring or indirect buffers in VRAM).

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-18 17:09:44 -04:00
Christian König 701e1e7891 drm/radeon: properly document reloc priority mask
Instead of hard coding the value properly document
that this is an userspace interface.

No intended functional change.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-08-18 17:09:43 -04:00
Imre Deak 1a125d8a2c drm/i915: don't try to retrain a DP link on an inactive CRTC
Atm we may retrain the DP link even if the CRTC is inactive through
HPD work->intel_dp_check_link_status(). This in turn can lock up the PHY
(at least on BYT), since the DP port is disabled.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=81948
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: stable@vger.kernel.org (3.16+)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 16:51:35 +03:00
Imre Deak 07f9cd0b38 drm/i915: make sure VDD is turned off during system suspend
Atm we may leave eDP VDD enabled during system suspend after the CRTCs
are disabled through an HPD->DPCD read event. So disable VDD during
suspend at a point when no HPDs can occur.

Note that runtime suspend doesn't have the same problem, since there the
RPM ref held by VDD provides already the needed serialization.

v2:
- add note to commit message about the runtime suspend path (Ville)
- use edp_panel_vdd_off_sync(), so we can keep the WARN in
  edp_panel_vdd_off() (Ville)
v3:
- rebased on -fixes (for_each_intel_encoder()->list_for_each_entry())
  (Imre)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (v2)
Cc: stable@vger.kernel.org (3.16+)
[Jani: fix sparse warning reported by Fengguang Wu]
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 16:49:36 +03:00
Imre Deak 1d0d343abb drm/i915: cancel hotplug and dig_port work during suspend and unload
Make sure these work handlers don't run after we system suspend or
unload the driver. Note that we don't cancel the handlers during runtime
suspend. That could lead to a lockup, since we take a runtime PM ref
from the handlers themselves. Fortunaltely canceling there is not needed
since the RPM ref itself provides for the needed serialization.

v2:
- fix the order of canceling dig_port_work wrt. hotplug_work (Ville)
- zero out {long,short}_hpd_port_mask and hpd_event_bits for speed
  (Ville)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: stable@vger.kernel.org (3.16+)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 16:16:03 +03:00
Imre Deak 6323751d28 drm/i915: fix HPD IRQ reenable work cancelation
Atm, the HPD IRQ reenable timer can get rearmed right after it's
canceled. Also to access the HPD IRQ mask registers we need to wake up
the HW.

Solve both issues by converting the reenable timer to a delayed work and
grabbing a runtime PM reference in the work. By this we can also forgo
canceling the timer during runtime suspend, since the only important
thing there is that the HW is awake when we write the registers and
that's ensured by the RPM ref. So do the cancelation only during driver
unload time; this is also a requirement for an upcoming patch where we
want to cancel all HPD related works only during system suspend and
driver unload time, but not during runtime suspend.

Note that there is still a race between the HPD IRQ reenable work and
drm_irq_uninstall() during driver unload, where the work can reenable
the HPD IRQs disabled by drm_irq_uninstall(). This isn't a problem since
the HPD IRQs will still be effectively masked by the first level
interrupt mask.

v2-3:
- unchanged
v4:
- use proper API for changing the expiration time for an already pending
  delayed work (Jani)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (v2)
Cc: stable@vger.kernel.org (3.16+)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 16:16:00 +03:00
Imre Deak 1c767b339b drm/i915: take display port power domain in DP HPD handler
Ville noticed that we can call ibx_digital_port_connected() which accesses
the HW without holding any power well/runtime pm reference. Fix this by
holding a display port power domain reference around the whole hpd_pulse
handler.

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Cc: stable@vger.kernel.org (3.16+)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 16:15:57 +03:00
Dave Airlie c39502c550 Merge branch 'drm-fixes-3.17' of git://people.freedesktop.org/~agd5f/linux
radeon fixes for 3.17, kind of all over the place (dpm, GPUVM, etc.)
* 'drm-fixes-3.17' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon: Remove duplicate include from Makefile
  drm/radeon/dpm: select the appropriate vce power state for KV/KB/ML
  drm/radeon: Add ability to get and change dpm state when radeon PX card is turned off
  drm/radeon: Add missing lines to ci_set_thermal_temperature_range
  drm/radeon: Always flush VM again on < CIK
  drm/radeon: add a check for allocation failure (v2)
  drm/radeon: use pfp for all vm_flush related updates
  drm/radeon: add bapm module parameter
2014-08-18 23:07:45 +10:00
Ville Syrjälä 1add143caf drm/i915: Don't try to enable cursor from setplane when crtc is disabled
Make sure the cursor gets fully clipped when enabling it on a disabled
crtc via setplane. This will prevent the lower level code from
attempting to enable the cursor in hardware.

Cc: Paulo Zanoni <przanoni@gmail.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 10:42:42 +03:00
Ville Syrjälä a459249c73 drm/i915: Skip load detect when intel_crtc->new_enable==true
During suspend we turn off the crtcs, but leave the staged config in
place so that we can restore the display(s) to their previous state on
resume.

During resume when we attempt to apply the force pipe A quirk we use the
load detect mechanism. That doesn't check whether there was an already
staged configuration for the crtc since that's not even possible during
normal runtime load detection. But during resume it is possible, and if
we just blindly go and overwrite the staged crtc configuration for the
load detection we can no longer restore the display to the correct
state.

Even worse, we don't even clear all the staged connector->encoder->crtc
links so we may end up using a cloned setup for the load detection, and
after we're done we just clear the links related to the VGA output
leaving the links for the other outputs in place. This will eventually
result in calling intel_set_mode() with mode==NULL but with valid
connector->encoder->crtc links which will result in dereferencing the
NULL mode since the code thinks it will have to a modeset.

To avoid these problems don't use any crtc with new_enabled==true for
load detection.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org (for 3.16)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 10:42:41 +03:00
Ville Syrjälä 208bf9fdcd drm/i915: Fix locking for intel_enable_pipe_a()
intel_enable_pipe_a() gets called with all the modeset locks already
held (by drm_modeset_lock_all()), so trying to grab the same
locks using another drm_modeset_acquire_ctx is going to fail miserably.

Move most of the drm_modeset_acquire_ctx handling (init/drop/fini)
out from intel_{get,release}_load_detect_pipe() into the callers
(intel_{crt,tv}_detect()). Only the actual locking and backoff
handling is left in intel_get_load_detect_pipe(). And in
intel_enable_pipe_a() we just share the mode_config.acquire_ctx from
drm_modeset_lock_all() which is already holding all the relevant locks.

It's perfectly legal to lock the same ww_mutex multiple times using the
same ww_acquire_ctx. drm_modeset_lock() will convert the returned
-EALREADY into 0, so the caller doesn't need to do antyhing special.

Fixes a hang on resume on my 830.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2014-08-18 10:42:40 +03:00
Linus Torvalds d22af68bd7 Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux
Pull drm fixes (mostly nouveau) from Dave Airlie:
 "One doc buidling fixes for a file that moved, along with a bunch of
  nouveau fixes, one a build problem on ARM"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/doc: Refer to proper source file
  drm/nouveau/platform: fix compilation error
  drm/nouveau/gk20a: add LTC device
  drm/nouveau: warn if we fail to re-pin fb on resume
  drm/nouveau/nvif: fix dac load detect method definition
  drm/gf100-/gr: fix -ENOSPC detection when allocating zbc table entries
  drm/nouveau/nvif: return null pointers on failure, in addition to ret != 0
  drm/nouveau/ltc: fix tag base address getting truncated if above 4GiB
  drm/nvc0-/fb/ram: fix use of non-existant ram if partitions aren't uniform
  drm/nouveau/bar: behave better if ioremap failed
  drm/nouveau/kms: nouveau_fbcon_accel_fini can be static
  drm/nouveau: kill unused variable warning if !__OS_HAS_AGP
  drm/nouveau/nvif: fix a number of notify thinkos
2014-08-15 17:57:49 -06:00
Andreas Ruprecht c8ad8b563c drm/radeon: Remove duplicate include from Makefile
In the Makefile, radeon_uvd.o is added to radeon-y twice.

As it belongs to the UVD block marked with a comment, the other include
from the block of includes labelled as "KMS driver" is deleted.

Signed-off-by: Andreas Ruprecht <rupran@einserver.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-15 00:58:20 -04:00
Alex Deucher c83dec3bb6 drm/radeon/dpm: select the appropriate vce power state for KV/KB/ML
Compare the clock in the limits table to the requested evclk rather
than just taking the first value.  Improves vce performance in certain
cases.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-08-15 00:58:19 -04:00
Pali Rohár b07a657e3a drm/radeon: Add ability to get and change dpm state when radeon PX card is turned off
This fixing commit 4f2f203976

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=76321

Signed-off-by: Pali Rohár <pali.rohar@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-08-15 00:58:19 -04:00
Oleg Chernovskiy 6bce8d9772 drm/radeon: Add missing lines to ci_set_thermal_temperature_range
Properly set the thermal min and max temp on CI.
Otherwise, we end up setting the thermal ranges
to 0 on resume and end up in the lowest power state.

Signed-off-by: Oleg Chernovskiy <algonkvel@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-08-15 00:58:18 -04:00
Michel Dänzer 6f28ef4797 drm/radeon: Always flush VM again on < CIK
Not doing this causes piglit hangs[0] on my Cape Verde card. No issues on
Bonaire and Kaveri though.

[0] Same symptoms as those fixed on CIK by 'drm/radeon: set VM base addr
using the PFP v2'.

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-15 00:58:17 -04:00
Dan Carpenter 68b1ea30e4 drm/radeon: add a check for allocation failure (v2)
We can easily return -ENOMEM here if kzalloc() fails.

v2: agd5f: drop the vm mutex

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-15 00:58:17 -04:00
Alex Deucher 4fb0bbd5d0 drm/radeon: use pfp for all vm_flush related updates
May fix hangs in some cases.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-15 00:58:09 -04:00
Alex Deucher 6e909f74db drm/radeon: add bapm module parameter
Add a module paramter to enable bapm on APUs.  It's disabled
by default on certain APUs due to stability issues.  This
option makes it easier to test and to enable it on systems that
are stable.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=81021

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-08-15 00:57:27 -04:00
Dave Airlie 83d45f234d Merge branch 'linux-3.17' of git://anongit.freedesktop.org/git/nouveau/linux-2.6 into drm-fixes
A couple of thinkos from the -next merge, some random fixes from a
coverity scan, fix for (at least) GK106 accidentally using
non-existent vram on some board configurations, and better behaviour
of the instmem allocations if vmalloc space runs out.

* 'linux-3.17' of git://anongit.freedesktop.org/git/nouveau/linux-2.6:
  drm/nouveau/platform: fix compilation error
  drm/nouveau/gk20a: add LTC device
  drm/nouveau: warn if we fail to re-pin fb on resume
  drm/nouveau/nvif: fix dac load detect method definition
  drm/gf100-/gr: fix -ENOSPC detection when allocating zbc table entries
  drm/nouveau/nvif: return null pointers on failure, in addition to ret != 0
  drm/nouveau/ltc: fix tag base address getting truncated if above 4GiB
  drm/nvc0-/fb/ram: fix use of non-existant ram if partitions aren't uniform
  drm/nouveau/bar: behave better if ioremap failed
  drm/nouveau/kms: nouveau_fbcon_accel_fini can be static
  drm/nouveau: kill unused variable warning if !__OS_HAS_AGP
  drm/nouveau/nvif: fix a number of notify thinkos
2014-08-15 09:29:35 +10:00
Alexandre Courbot 4898ac046d drm/nouveau/platform: fix compilation error
nouveau_platform.c was still using the old nouveau_dev() macro,
triggering a compilation error. Fix this.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Alexandre Courbot 5d6d94f761 drm/nouveau/gk20a: add LTC device
LTC device is now required for PGRAPH to work, add it.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Ben Skeggs c9a6fd9733 drm/nouveau: warn if we fail to re-pin fb on resume
Spotted by Coverity.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Ben Skeggs 8bd62a8327 drm/nouveau/nvif: fix dac load detect method definition
A thinko made me turn this into a u16 when cleaning up.

Spotted by coverity.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Ben Skeggs da7c74ea2b drm/gf100-/gr: fix -ENOSPC detection when allocating zbc table entries
Spotted by Coverity.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Ben Skeggs ef07ceae02 drm/nouveau/nvif: return null pointers on failure, in addition to ret != 0
Reported by Coverity.  The intention is that the return value is
checked, but let's be more paranoid and make it extremely obvious
if something forgets to.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Ben Skeggs 147ed897e8 drm/nouveau/ltc: fix tag base address getting truncated if above 4GiB
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:39 +10:00
Ben Skeggs 3d9e3921f4 drm/nvc0-/fb/ram: fix use of non-existant ram if partitions aren't uniform
Likely a large part of the GK106 woes..

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:38 +10:00
Ben Skeggs e7d96929a7 drm/nouveau/bar: behave better if ioremap failed
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:38 +10:00
Fengguang Wu e715396ae3 drm/nouveau/kms: nouveau_fbcon_accel_fini can be static
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:38 +10:00
Ben Skeggs 5c13cac149 drm/nouveau: kill unused variable warning if !__OS_HAS_AGP
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:38 +10:00
Ben Skeggs 7caa63c040 drm/nouveau/nvif: fix a number of notify thinkos
Note to self: more sleep

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-08-15 07:58:38 +10:00
Daniel Vetter 4ed9109688 drm/i915: Track cursor changes as frontbuffer tracking flushes
We treat other plane updates in the same fashion. Spotted because
Rodrigo kept reporting a bug in the PSR code where the frontbuffer was
eternally stuck with a dirty cursor bit set.

The psr testcase should have caught this, but that i-g-t is kaputt.
Rodrigo is signed up to fix that.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Tested-by-and-Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:49:47 +02:00
Oscar Mateo f1ad5a1fd4 drm/i915/bdw: Help out the ctx switch interrupt handler
If we receive a storm of requests for the same context (see gem_storedw_loop_*)
we might end up iterating over too many elements in interrupt time, looking for
contexts to squash together. Instead, share the burden by giving more
intelligence to the queue function. At most, the interrupt will iterate over
three elements.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:44:04 +02:00
Oscar Mateo e1fee72c2e drm/i915/bdw: Avoid non-lite-restore preemptions
In the current Execlists feeding mechanism, full preemption is not
supported yet: only lite-restores are allowed (this is: the GPU
simply samples a new tail pointer for the context currently in
execution).

But we have identified an scenario in which a full preemption occurs:
1) We submit two contexts for execution (A & B).
2) The GPU finishes with the first one (A), switches to the second one
(B) and informs us.
3) We submit B again (hoping to cause a lite restore) together with C,
but in the time we spend writing to the ELSP, the GPU finishes B.
4) The GPU start executing B again (since we told it so).
5) We receive a B finished interrupt and, mistakenly, we submit C (again)
and D, causing a full preemption of B.

The race is avoided by keeping track of how many times a context has been
submitted to the hardware and by better discriminating the received context
switch interrupts: in the example, when we have submitted B twice, we won´t
submit C and D as soon as we receive the notification that B is completed
because we were expecting to get a LITE_RESTORE and we didn´t, so we know a
second completion will be received shortly.

Without this explicit checking, somehow, the batch buffer execution order
gets messed with. This can be verified with the IGT test I sent together with
the series. I don´t know the exact mechanism by which the pre-emption messes
with the execution order but, since other people is working on the Scheduler
+ Preemption on Execlists, I didn´t try to fix it. In these series, only Lite
Restores are supported (other kind of preemptions WARN).

v2: elsp_submitted belongs in the new intel_ctx_submit_request. Several
rebase changes.

v3: Clarify how the race is avoided, as requested by Daniel.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Align function parameters ...]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:43:58 +02:00
Thomas Daniel e981e7b17f drm/i915/bdw: Handle context switch events
Handle all context status events in the context status buffer on every
context switch interrupt. We only remove work from the execlist queue
after a context status buffer reports that it has completed and we only
attempt to schedule new contexts on interrupt when a previously submitted
context completes (unless no contexts are queued, which means the GPU is
free).

We canot call intel_runtime_pm_get() in an interrupt (or with a spinlock
grabbed, FWIW), because it might sleep, which is not a nice thing to do.
Instead, do the runtime_pm get/put together with the create/destroy request,
and handle the forcewake get/put directly.

Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>

v2: Unreferencing the context when we are freeing the request might free
the backing bo, which requires the struct_mutex to be grabbed, so defer
unreferencing and freeing to a bottom half.

v3:
- Ack the interrupt inmediately, before trying to handle it (fix for
missing interrupts by Bob Beckett <robert.beckett@intel.com>).
- Update the Context Status Buffer Read Pointer, just in case (spotted
by Damien Lespiau).

v4: New namespace and multiple rebase changes.

v5: Squash with "drm/i915/bdw: Do not call intel_runtime_pm_get() in an
interrupt", as suggested by Daniel.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch ...]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:43:47 +02:00
Michel Thierry acdd884a2e drm/i915/bdw: Two-stage execlist submit process
Context switch (and execlist submission) should happen only when
other contexts are not active, otherwise pre-emption occurs.

To assure this, we place context switch requests in a queue and those
request are later consumed when the right context switch interrupt is
received (still TODO).

v2: Use a spinlock, do not remove the requests on unqueue (wait for
context switch completion).

Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>

v3: Several rebases and code changes. Use unique ID.

v4:
- Move the queue/lock init to the late ring initialization.
- Damien's kmalloc review comments: check return, use sizeof(*req),
do not cast.

v5:
- Do not reuse drm_i915_gem_request. Instead, create our own.
- New namespace.

Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v1)
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com> (v2-v5)
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[davnet: Checkpatch + wash-up s/BUG_ON/WARN_ON/.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:10:59 +02:00
Oscar Mateo ae1250b9da drm/i915/bdw: Write the tail pointer, LRC style
Each logical ring context has the tail pointer in the context object,
so update it before submission.

v2: New namespace.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:03:09 +02:00
Ben Widawsky 84b790f80e drm/i915/bdw: Implement context switching (somewhat)
A context switch occurs by submitting a context descriptor to the
ExecList Submission Port. Given that we can now initialize a context,
it's possible to begin implementing the context switch by creating the
descriptor and submitting it to ELSP (actually two, since the ELSP
has two ports).

The context object must be mapped in the GGTT, which means it must exist
in the 0-4GB graphics VA range.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>

v2: This code has changed quite a lot in various rebases. Of particular
importance is that now we use the globally unique Submission ID to send
to the hardware. Also, context pages are now pinned unconditionally to
GGTT, so there is no need to bind them.

v3: Use LRCA[31:12] as hwCtxId[19:0]. This guarantees that the HW context
ID we submit to the ELSP is globally unique and != 0 (Bspec requirements
of the software use-only bits of the Context ID in the Context Descriptor
Format) without the hassle of the previous submission Id construction.
Also, re-add the ELSP porting read (it was dropped somewhere during the
rebases).

v4:
- Squash with "drm/i915/bdw: Add forcewake lock around ELSP writes" (BSPEC
  says: "SW must set Force Wakeup bit to prevent GT from entering C6 while
  ELSP writes are in progress") as noted by Thomas Daniel
  (thomas.daniel@intel.com).
- Rename functions and use an execlists/intel_execlists_ namespace.
- The BUG_ON only checked that the LRCA was <32 bits, but it didn't make
  sure that it was properly aligned. Spotted by Alistair Mcaulay
  <alistair.mcaulay@intel.com>.

v5:
- Improved source code comments as suggested by Chris Wilson.
- No need to abstract submit_ctx away, as pointed by Brad Volkin.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch. Sigh.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:03:03 +02:00
Oscar Mateo 48e29f5535 drm/i915/bdw: Emission of requests with logical rings
On a previous iteration of this patch, I created an Execlists
version of __i915_add_request and asbtracted it away as a
vfunc. Daniel Vetter wondered then why that was needed:

"with the clean split in command submission I expect every
function to know wether it'll submit to an lrc (everything in
intel_lrc.c) or wether it'll submit to a legacy ring (existing
code), so I don't see a need for an add_request vfunc."

The honest, hairy truth is that this patch is the glue keeping
the whole logical ring puzzle together:

- i915_add_request is used by intel_ring_idle, which in turn is
  used by i915_gpu_idle, which in turn is used in several places
  inside the eviction and gtt codes.
- Also, it is used by i915_gem_check_olr, which is littered all
  over i915_gem.c
- ...

If I were to duplicate all the code that directly or indirectly
uses __i915_add_request, I'll end up creating a separate driver.

To show the differences between the existing legacy version and
the new Execlists one, this time I have special-cased
__i915_add_request instead of adding an add_request vfunc. I
hope this helps to untangle this Gordian knot.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Adjust to ringbuf->FIXME_lrc_ctx per the discussion with
Thomas Daniel.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 22:02:55 +02:00
Damien Lespiau 14f476fa24 drm: Use the type of the array element when reallocating
Static analysers find it 'suspicious', that we're trying to allocate memory for
elements of size sizeof(struct drm_fb_helper_connector) when the array is
defined as struct drm_fb_helper_connector **.

Use sizeof(struct drm_fb_helper_connector *) instead.

Note that the structure being defined as:

struct drm_fb_helper_connector {
	struct drm_connector *connector;
};

This was still doing the right thing, but may not in the future if
additional fields are added.

Cc: Todd Previte <tprevite@gmail.com>
Cc: Dave Airlie <airlied@redhat.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 21:24:30 +02:00
Damien Lespiau c11cda5219 drm: Don't return 0 for a value used as a denominator
Static analysis will be unhappy if a function can theoretically return
0 and we're trying to divide by that value.

Mark that case that cannot occur as a BUG() instead.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 21:24:29 +02:00
Daniel Vetter 295ee85316 drm: Docbook fixes
Bunch of small leftovers spotted by looking at the make htmldocs output.

I've left out dp mst, there's too much amiss there.

v2: Also add the missing parameter docbook in the dp mst code - Dave
Airlie correctly pointed out that we don't actually want kerneldoc for
the missing structure members in header files.

Cc: Dave Airlie <airlied@gmail.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 21:24:17 +02:00
Oscar Mateo 582d67f0b1 drm/i915: Add temporary ring->ctx backpointer
The execlist patches have a bit a convoluted and long history and due
to that have the actual submission still misplaced deeply burried in
the low-level ringbuffer handling code. This design goes back to the
legacy ringbuffer code with its tricky lazy request and simple work
submissiion using ring tail writes. For that reason they need a
ring->ctx backpointer.

The goal is to unburry that code and move it up into a level where the
full execlist context is available so that we can ditch this
backpointer. Until that's done make it really obvious that there's
work still to be done.

Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Thomas Daniel <thomas.daniel@intel.com>
Acked-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 18:42:59 +02:00
Chris Wilson 3a44873490 drm/i915: Print captured bo for all VM in error state
The current error state harks back to the era of just a single VM. For
full-ppgtt, we capture every bo on every VM. It behoves us to then print
every bo for every VM, which we currently fail to do and so miss vital
information in the error state.

v2: Use the vma address rather than -1!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 16:52:41 +02:00
Sagar Kamble 016970beb0 drm/i915: Sharing platform specific sequence between runtime and system suspend/ resume paths
On VLV, post S0i3 during i915_drm_thaw following issue is observed during ring
initialization.

[ 335.604039] [drm:stop_ring] ERROR render ring :timed out trying to stop ring
[ 336.607340] [drm:stop_ring] ERROR render ring :timed out trying to stop ring
[ 336.607345] [drm:init_ring_common] ERROR failed to set render ring head to zero ctl 00000000 head 00000000 tail 00000000 start 00000000
[ 337.610645] [drm:stop_ring] ERROR bsd ring :timed out trying to stop ring
[ 338.613952] [drm:stop_ring] ERROR bsd ring :timed out trying to stop ring
[ 338.613956] [drm:init_ring_common] ERROR failed to set bsd ring head to zero ctl 00000000 head 00000000 tail 00000000 start 00000000
[ 339.617256] [drm:stop_ring] ERROR render ring :timed out trying to stop ring
[ 339.617258] -----------[ cut here ]-----------
[ 339.617267] WARNING: CPU: 0 PID: 6 at drivers/gpu/drm/i915/intel_ringbuffer.c:1666 intel_cleanup_ring+0xe6/0xf0()
[ 339.617396] --[ end trace 5ef5ed1a3c92e2a6 ]--
[ 339.617428] [drm:__i915_drm_thaw] ERROR failed to re-initialize GPU, declaring wedged!

This is happening since wake is not enabled and Gunit registers are not restored.
For this system suspend/resume paths need to follow save/restore and additional
platform specific setup in suspend_complete and resume_prepare.

suspend_complete is shared unconditionaly for VLV, HSW, BDW. resume_prepare for
HSW and BDW has pc8 disabling which is needed during thaw_early so sharing
uncondtionally. For VLV and SNB runtime resume specific sequence exists.

Cc: Imre Deak <imre.deak@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Goel, Akash <akash.goel@intel.com>
Signed-off-by: Sagar Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 16:13:34 +02:00
Sagar Kamble ebc3282409 drm/i915: Created common handler for platform specific suspend/resume
With this change, intel_runtime_suspend and intel_runtime_resume functions
become completely platform agnostic. Platform specific suspend/resume
changes are moved to intel_suspend_complete and intel_resume_prepare.

Cc: Imre Deak <imre.deak@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Goel, Akash <akash.goel@intel.com>
Signed-off-by: Sagar Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-14 16:12:42 +02:00
Chris Wilson 82e3b8c130 drm/i915: Localise the fbdev console lock frobbing
Rather than take and release the console_lock() around a non-existent
DRM_I915_FBDEV, move the lock acquisation into the callee where it will
be compiled out by the config option entirely. This includes moving the
deferred fb_set_suspend() dance and encapsulating it entirely within
intel_fbdev.c.

v2: Use an integral work item so that we can explicitly flush the work
upon suspend/unload.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
[danvet: Add the flush_work in fbdev_fini per the mailing list
discussion. And s/BUG_ON/WARN_ON/ because.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 15:39:23 +02:00
Chris Wilson 7312e2ddec drm/i915: Replace __I915__ with typesafe variant
Ville pointed out the GCCism __builtin_types_compatible_p() that we
could use to replace our heavily casted presumption __I915__ macro that
was based on comparing struct sizes.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:39 +02:00
Ville Syrjälä dc41c154ff drm/i915: Add support for variable cursor size on 845/865
845/865 support different cursor sizes as well, albeit a bit differently
than later platforms. Add the necessary code to make them work.

Untested due to lack of hardware.

v2: Warn but accept invalid stride (Chris)
    Rewrite the cursor size checks for other platforms (Chris)
v3: More polish and magic to the cursor size checks (Chris)
v4: Moar polish and a comment (Chris)

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:38 +02:00
Ville Syrjälä 8ac5466926 drm/i915: Unify ivb_update_cursor() and i9xx_update_cursor()
Ever since
 commit 5efb3e2838
 Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
 Date:   Wed Apr 9 13:28:53 2014 +0300

    drm/i915/chv: Add cursor pipe offsets

the only difference between i9xx_update_cursor() and ivb_update_cursor()
was the hsw+ pipe csc handling. Let's unify them and we can rid
outselves of some duplicated code.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:37 +02:00
Ville Syrjälä d7ce484eee drm/i915: Move CURSIZE setup to i845_update_cursor()
CURSIZE register exists on 845/865 only, so move it to
i845_update_cursor(). Changes to cursor size must be done only when the
cursor is disabled, so do the write just before enabling the cursor.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:37 +02:00
Ville Syrjälä a08a42ad44 drm/i915: Don't try to enable cursor from setplane when crtc is disabled
Make sure the cursor gets fully clipped when enabling it on a disabled
crtc via setplane. This will prevent the lower level code from
attempting to enable the cursor in hardware.

Cc: Paulo Zanoni <przanoni@gmail.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:36 +02:00
Daniel Vetter 70e32544aa drm/i915: Cleanup aliasging ppgtt alongside the global gtt
Also remove related WARN_ONs which seem to have been hit since a rather
long time. But apperently no one noticed since our module reload is
already WARNING-infested :(

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:35 +02:00
Daniel Vetter 90d0a0e8d0 drm/i915: Extract commmon global gtt cleanup code
We want to move the aliasing ppgtt cleanup back into the global
gtt cleanup code for symmetry, but first we need to create such
a place.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:35 +02:00
Daniel Vetter 19dd120cee drm/i915: Extract common cleanup into i915_ppgtt_release
Address space cleanup isn't really a job for the low-level cleanup
callbacks. Without this change we can't reuse the low-level cleanup
callback for the aliasing ppgtt cleanup.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:34 +02:00
Daniel Vetter d624d86e1e drm/i915: Drop create_vm argument to i915_gem_create_context
Now that all the flow is streamlined the rule is simple: We create
a new ppgtt for a new context when we have full ppgtt enabled.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:33 +02:00
Daniel Vetter ae6c480692 drm/i915: Only track real ppgtt for a context
There's a bit a confusion since we track the global gtt,
the aliasing and real ppgtt in the ctx->vm pointer. And not
all callers really bother to check for the different cases and just
presume that it points to a real ppgtt.

Now looking closely we don't actually need ->vm to always point at an
address space - the only place that cares actually has fixup code
already to decide whether to look at the per-proces or the global
address space.

So switch to just tracking the ppgtt directly and ditch all the
extraneous code.

v2: Fixup the ppgtt debugfs file to not oops on a NULL ctx->ppgtt.
Also drop the early exit - without aliasing ppgtt we want to dump all
the ppgtts of the contexts if we have full ppgtt.

v3: Actually git add the compile fix.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Cc: "Thierry, Michel" <michel.thierry@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
OTC-Jira: VIZ-3724
[danvet: Resolve conflicts with execlist patches while applying.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:33 +02:00
Daniel Vetter fa76da3499 drm/i915: Initialize the aliasing ppgtt as part of global gtt
Stuffing this into the context setup code doesn't make a lot of sense.
Also reusing the real ppgtt setup code makes even less sense since the
aliasing ppgtt isn't a real address space. Leaving all that stuff
unitialized will make sure that we catch any abusers promptly.

This is also a prep work to clean up the context->ppgtt link.

v2: Fix up the logic fail, I've fumbled it so badly to completely
disable ppgtt on gen6. Spotted by Ville and Michel. Also move around
the pde write into the gen6 init function, since otherwise it won't
work at all.

v3: Only initialize the aliasing ppgtt when we actually enable it.

Cc: "Thierry, Michel" <michel.thierry@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
[danvet: Squash in fixup from Fengguang Wu.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:32 +02:00
Daniel Vetter 82460d9724 drm/i915: Rework ppgtt init to no require an aliasing ppgtt
Currently we abuse the aliasing ppgtt to set up the ppgtt support in
general. Which is a bit backwards since with full ppgtt we don't ever
need the aliasing ppgtt.

So untangle this and separate the ppgtt init from the aliasing
ppgtt. While at it drag it out of the context enabling (which just
does a switch to the default context).

Note that we still have the differentiation between synchronous and
asynchronous ppgtt setup, but that will soon vanish. So also correctly
wire up the return value handling to be prepared for when ->switch_mm
drops the synchronous parameter and could start to fail.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:31 +02:00
Daniel Vetter 896ab1a5d5 drm/i915: Fix up checks for aliasing ppgtt
A subsequent patch will no longer initialize the aliasing ppgtt if we
have full ppgtt enabled, since we simply don't need that any more.

Unfortunately a few places check for the aliasing ppgtt instead of
checking for ppgtt in general. Fix them up.

One special case are the gtt offset and size macros, which have some
code to remap the aliasing ppgtt to the global gtt. The aliasing ppgtt
is _not_ a logical address space, so passing that in as the vm is
plain and simple a bug. So just WARN about it and carry on - we have a
gracefully fall-through anyway if we can't find the vma.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:31 +02:00
Daniel Vetter 6c5566a82c drm/i915: Allow i915_gem_setup_global_gtt to fail
We already needs this just as a safety check in case the preallocation
reservation dance fails. But we definitely need this to be able to
move tha aliasing ppgtt setup back out of the context code to this
place, where it belongs.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:30 +02:00
Daniel Vetter 5dc383b05a drm/i915: Add proper prefix to obj_to_ggtt
Stuff in headers really aught to have this.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:29 +02:00
Daniel Vetter 841cd77375 drm/i915: Only refcount ppgtt if it actually is one
This essentially unbreaks non-ppgtt operation where we'd scribble over
random memory.

While at it give the vm_to_ppgtt function a proper prefix and make it
a bit more paranoid.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:29 +02:00
Daniel Vetter 4d884705da drm/i915: Track file_priv, not ctx in the ppgtt structure
Hardware contexts reference a ppgtt, not the other way round. And the
only user of this (in debugfs) actually only cares about which file
the ppgtt is associated with. So give it what it wants.

While at it give the ppgtt create function a proper name&place.

Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-13 14:23:28 +02:00
Benoit Taine 9baa3c34ac PCI: Remove DEFINE_PCI_DEVICE_TABLE macro use
We should prefer `struct pci_device_id` over `DEFINE_PCI_DEVICE_TABLE` to
meet kernel coding style guidelines.  This issue was reported by checkpatch.

A simplified version of the semantic patch that makes this change is as
follows (http://coccinelle.lip6.fr/):

// <smpl>

@@
identifier i;
declarer name DEFINE_PCI_DEVICE_TABLE;
initializer z;
@@

- DEFINE_PCI_DEVICE_TABLE(i)
+ const struct pci_device_id i[]
= z;

// </smpl>

[bhelgaas: add semantic patch]
Signed-off-by: Benoit Taine <benoit.taine@lip6.fr>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2014-08-12 12:15:14 -06:00
Daniel Vetter ee960be7bb drm/i915: Some cleanups for the ppgtt lifetime handling
So when reviewing Michel's patch I've noticed a few things and cleaned
them up:
- The early checks in ppgtt_release are now redundant: The inactive
  list should always be empty now, so we can ditch these checks. Even
  for the aliasing ppgtt (though that's a different confusion) since
  we tear that down after all the objects are gone.
- The ppgtt handling functions are splattered all over. Consolidate
  them in i915_gem_gtt.c, give them OCD prefixes and add wrappers for
  get/put.
- There was a bit a confusion in ppgtt_release about whether it cares
  about the active or inactive list. It should care about them both,
  so augment the WARNINGs to check for both.

There's still create_vm_for_ctx left to do, put that is blocked on the
removal of ppgtt->ctx. Once that's done we can rename it to
i915_ppgtt_create and move it to its siblings for handling ppgtts.

v2: Move the ppgtt checks into the inline get/put functions as
suggested by Chris.

v3: Inline the now redundant ppgtt local variable.

Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-12 15:24:04 +02:00
Michel Thierry b9d06dd9d1 drm/i915: vma/ppgtt lifetime rules
VMAs should take a reference of the address space they use.

Now, when the fd is closed, it will release the ref that the context was
holding, but it will still be referenced by any vmas that are still
active.

ppgtt_release() should then only be called when the last thing referencing
it releases the ref, and it can just call the base cleanup and free the
ppgtt.

Note that with this we will extend the lifetime of ppgtts which
contain shared objects. But all the non-shared objects will get
removed as soon as they drop of the active list and for the shared
ones the shrinker can eventually reap them. Since we currently can't
evict ppgtt pagetables either I don't think that temporary leak is
important.

Signed-off-by: Michel Thierry <michel.thierry@intel.com>
[danvet: Add note about potential ppgtt leak with this approach.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-12 15:22:26 +02:00
Oscar Mateo 14bf993e83 drm/i915/bdw: Always use MMIO flips with Execlists
The normal flip function places things in the ring in the legacy
way, so we either fix that or force MMIO flips always as we do in
this patch.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch. Fucking again.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 23:25:49 +02:00
Oscar Mateo ba8b7ccb19 drm/i915/bdw: Workload submission mechanism for Execlists
This is what i915_gem_do_execbuffer calls when it wants to execute some
worload in an Execlists world.

v2: Check arguments before doing stuff in intel_execlists_submission. Also,
get rel_constants parsing right.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Drop the chipset flush, that's pre-gen6. And appease
checkpatch a bit .... again!]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 23:18:38 +02:00
Oscar Mateo 1564858526 drm/i915/bdw: GEN-specific logical ring emit batchbuffer start
Dispatch_execbuffer's evil twin.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Ditch the check for aliasing ppgtt. It'll break soon and
execlists requires full ppgtt anyway.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 23:12:34 +02:00
Oscar Mateo 73d477f6bb drm/i915/bdw: Interrupts with logical rings
We need to attend context switch interrupts from all rings. Also, fixed writing
IMR/IER and added HWSTAM at ring init time.

Notice that, if added to irq_enable_mask, the context switch interrupts would
be incorrectly masked out when the user interrupts are due to no users waiting
on a sequence number. Therefore, this commit adds a bitmask of interrupts to
be kept unmasked at all times.

v2: Disable HWSTAM, as suggested by Damien (nobody listens to these interrupts,
anyway).

v3: Add new get/put_irq functions.

Signed-off-by: Thomas Daniel <thomas.daniel@intel.com> (v1)
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com> (v2 & v3)
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Drop the GEN8_ prefix from the context switch interrupt
define and move it to its brethren.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 23:06:58 +02:00
Oscar Mateo 9832b9dae8 drm/i915/bdw: Ring idle and stop with logical rings
This is a hard one, since there is no direct hardware ring to
control when in Execlists.

We reuse intel_ring_idle here, but it should be fine as long
as i915_add_request does the ring thing.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 22:57:38 +02:00
Oscar Mateo 4712274c36 drm/i915/bdw: GEN-specific logical ring emit flush
Same as the legacy-style ring->flush.

v2: The BSD invalidate bit still exists in GEN8! Add it for the VCS
rings (but still consolidate the blt and bsd ring flushes into one).
This was noticed by Brad Volkin.

v3: The command for BSD and for other rings is slightly different:
get it exactly the same as in gen6_ring_flush + gen6_bsd_ring_flush

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 22:44:37 +02:00
Oscar Mateo 4da46e1e5b drm/i915/bdw: GEN-specific logical ring emit request
Very similar to the legacy add_request, only modified to account for
logical ringbuffer.

v2: Use MI_GLOBAL_GTT, as suggested by Brad Volkin.

v3: Unify render and non-render in the same function, as noticed by
Brad Volkin.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 22:42:49 +02:00
Oscar Mateo 82e104cc26 drm/i915/bdw: New logical ring submission mechanism
Well, new-ish: if all this code looks familiar, that's because it's
a clone of the existing submission mechanism (with some modifications
here and there to adapt it to LRCs and Execlists).

And why did we do this instead of reusing code, one might wonder?
Well, there are some fears that the differences are big enough that
they will end up breaking all platforms.

Also, Execlists offer several advantages, like control over when the
GPU is done with a given workload, that can help simplify the
submission mechanism, no doubt. I am interested in getting Execlists
to work first and foremost, but in the future this parallel submission
mechanism will help us to fine tune the mechanism without affecting
old gens.

v2: Pass the ringbuffer only (whenever possible).

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Appease checkpatch. Again. And drop the legacy sarea gunk
that somehow crept in.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 22:42:36 +02:00
Ville Syrjälä 26fbb77445 drm/i915: Make hpd debug messages less cryptic
Don't print raw numbers, use port_name() and tell the user whether it's
long or short without having to figure out what the other magic number
means.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 19:32:15 +02:00
Oscar Mateo e94e37ad19 drm/i915/bdw: GEN-specific logical ring set/get seqno
No mistery here: the seqno is still retrieved from the engine's
HW status page (the one in the default context. For the moment,
I see no reason to worry about other context's HWS page).

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-11 17:05:17 +02:00
Christian König bd645e4314 drm/radeon: allow userptr write access under certain conditions
It needs to be anonymous memory (no file mappings)
and we are requried to install an MMU notifier.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-11 11:04:26 -04:00
Christian König 341cb9e426 drm/radeon: add userptr flag to register MMU notifier v3
Whenever userspace mapping related to our userptr change
we wait for it to become idle and unmap it from GTT.

v2: rebased, fix mutex unlock in error path
v3: improve commit message

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-11 11:04:26 -04:00
Christian König 2a84a4476d drm/radeon: add userptr flag to directly validate the BO to GTT
This way we test userptr availability at BO creation time instead of first use.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-11 11:04:25 -04:00
Christian König ddd00e33e1 drm/radeon: add userptr flag to limit it to anonymous memory v2
Avoid problems with writeback by limiting userptr to anonymous memory.

v2: add commit and code comments

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-11 11:04:24 -04:00