We don't need the AUX power for the whole duration of the detect, only
when we're doing AUX transfers. The AUX transfer function takes its own
reference on the AUX power domain already. The two places during detect
which access display core registers (not specific to a
pipe/port/transcoder) only need the power domain that is required for
that access. That power domain is equivalent to the device global power
domain on most platforms (enabled whenever we hold a runtime PM
reference) except on CHV/VLV where it's equivalent to the display power
well.
Add a new power domain that reflects the above, and use this at the two
spots accessing registers. With that we can avoid taking the AUX
reference for the whole duration of the detect function.
Put the domains asynchronously to avoid the unneeded on-off-on toggling.
Also adapt the idea from with_intel_runtime_pm et al. for making it easy
to write short sequences where a display power ref is needed.
v2: (Ville)
- Add with_intel_display_power() helper to simplify things.
- s/bool res/bool is_connected/
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190509173446.31095-8-imre.deak@intel.com
In a follow-up patch we will restrict holding the reference on the AUX
power domain to the AUX transfer function. To avoid the unnecessary
on-off-on power togglings drop the reference asynchronously.
There is no reason we couldn't do this in general and also put the
reference asynchronously in pps_unlock(); but that's a separate change
that can be done as a follow-up.
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190509173446.31095-6-imre.deak@intel.com
By disabling a power domain asynchronously we can restrict holding a
reference on that power domain to the actual code sequence that
requires the power to be on for the HW access it's doing, by also
avoiding unneeded on-off-on togglings of the power domain (since the
disabling happens with a delay).
One benefit is potential power saving due to the following two reasons:
1. The fact that we will now be holding the reference only for the
necessary duration by the end of the patchset. While simply not
delaying the disabling has the same benefit, it has the problem that
frequent on-off-on power switching has its own power cost (see the 2.
point below) and the debug trace for power well on/off events will
cause a lot of dmesg spam (see details about this further below).
2. Avoiding the power cost of freuqent on-off-on power switching. This
requires us to find the optimal disabling delay based on the measured
power cost of on->off and off->on switching of each power well vs.
the power of keeping the given power well on.
In this patchset I'm not providing this optimal delay for two
reasons:
a) I don't have the means yet to perform the measurement (with high
enough signal-to-noise ratio, or with the help of an energy
counter that takes switching into account). I'm currently looking
for a way to measure this.
b) Before reducing the disabling delay we need an alternative way for
debug tracing powerwell on/off events. Simply avoiding/throttling
the debug messages is not a solution, see further below.
Note that even in the case where we can't measure any considerable
power cost of frequent on-off switching of powerwells, it still would
make sense to do the disabling asynchronously (with 0 delay) to avoid
blocking on the disabling. On VLV I measured this disabling time
overhead to be 1ms on average with a worst case of 4ms.
In the case of the AUX power domains on ICL we would also need to keep
the sequence where we hold the power reference short, the way it would
be by the end of this patchset where we hold it only for the actual AUX
transfer. Anything else would make the locking we need for ICL TypeC
ports (whenever we hold a reference on any AUX power domain) rather
problematic, adding for instance unnecessary lockdep dependencies to
the required TypeC port lock.
I chose the disabling delay to be 100msec for now to avoid the unneeded
toggling (and so not to introduce dmesg spamming) in the DP MST sideband
signaling code. We could optimize this delay later, once we have the
means to measure the switching power cost (see above).
Note that simply removing/throttling the debug tracing for power well
on/off events is not a solution. We need to know the exact spots of
these events and cannot rely only on incorrect register accesses caught
(due to not holding a wakeref at the time of access). Incorrect
powerwell enabling/disabling could lead to other problems, for instance
we need to keep certain powerwells enabled for the duration of modesets
and AUX transfers.
v2:
- Clarify the commit log parts about power cost measurement and the
problem of simply removing/throttling debug tracing. (Chris)
- Optimize out local wakeref vars at intel_runtime_pm_put_raw() and
intel_display_power_put_async() call sites if
CONFIG_DRM_I915_DEBUG_RUNTIME_PM=n. (Chris)
- Rebased on v2 of the wakeref w/o power-on guarantee patch.
- Add missing docbook headers.
v3:
- Checkpatch spelling/missing-empty-line fix.
v4:
- Fix unintended local wakeref var optimization when using
call-arguments with side-effects, by using inline funcs instead of
macros. In this patch in particular this will fix the
intel_display_power_grab_async_put_ref()->intel_runtime_pm_put_raw()
call).
No size change in practice (would be the same disregarding the
corresponding change in intel_display_power_grab_async_put_ref()):
$ size i915-macro.ko
text data bss dec hex filename
2455190 105890 10272 2571352 273c58 i915-macro.ko
$ size i915-inline.ko
text data bss dec hex filename
2455195 105890 10272 2571357 273c5d i915-inline.ko
Kudos to Stan for reporting the raw-wakeref WARNs this issue caused. His
config has CONFIG_DRM_I915_DEBUG_RUNTIME_PM=n, which I didn't retest
after v1, and we are also not testing this config in CI.
Now tested both with CONFIG_DRM_I915_DEBUG_RUNTIME_PM=y/n on ICL,
connecting both Chamelium and regular DP, HDMI sinks.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190513192533.12586-1-imre.deak@intel.com
There is no reason why we couldn't verify the power domains state during
suspend in all cases, so do that. I overlooked this when originally
adding the check.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190509173446.31095-4-imre.deak@intel.com
Make sure we print and drop the wakeref tracking info during pm_cleanup
even if there are wakeref holders (either raw-wakeref or wakelock
holders). Dropping the wakeref tracking means that a late put on the ref
will WARN since the wakeref will be unknown, but that is rightly so,
since the put is late and we want to catch that case.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190509173446.31095-3-imre.deak@intel.com
It's useful to track runtime PM refs that don't guarantee a device
power-on state to the rest of the driver. One such case is holding a
reference that will be put asynchronously, during which normal users
without their own reference shouldn't access the HW. A follow-up patch
will add support for disabling display power domains asynchronously
which needs this.
For this we can split wakeref_count into a low half-word tracking
all references (raw-wakerefs) and a high half-word tracking
references guaranteeing a power-on state (wakelocks).
Follow-up patches will make use of the API added here.
While at it add the missing docbook header for the unchecked
display-power and runtime_pm put functions.
No functional changes, except for printing leaked raw-wakerefs
and wakelocks separately in intel_runtime_pm_cleanup().
v2:
- Track raw wakerefs/wakelocks in the low/high half-word of
wakeref_count, instead of adding a new counter. (Chris)
v3:
- Add a struct_member(T, m) helper instead of open-coding it. (Chris)
- Checkpatch indentation formatting fix.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190509173446.31095-2-imre.deak@intel.com
Adjust the get transcoder timings for mipi dsi as per the
set timing calculations.
v2: Use the existing intel_get_pipe_timings and do the dsi
specific adjustments in the encoder get_config hook.(Ville, Jani)
v3: Exclude VBLANK and HBLANK registers for dsi transcoder.
v4: Fix the incomplete conditional logic.
Signed-off-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1556809862-31203-1-git-send-email-vandita.kulkarni@intel.com
In all likelihood, the priority and node are already in the CPU cache
and by checking them first, we can avoid having to chase the
*request->hwsp for the current breadcrumb.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190513120102.29660-3-chris@chris-wilson.co.uk
To simplify the next patch, update bump_priority and schedule to accept
the internal i915_sched_ndoe directly and not expect a request pointer.
add/remove: 0/0 grow/shrink: 2/1 up/down: 8/-15 (-7)
Function old new delta
i915_schedule_bump_priority 109 113 +4
i915_schedule 50 54 +4
__i915_schedule 922 907 -15
v2: Adopt node for the old rq local, since it no longer is a request but
the origin node.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190513120102.29660-2-chris@chris-wilson.co.uk
Convert the HSW pch_pfit.force_thru to a proper state variable
with readout and accompanying pipe conf check. Makes the logic
a bit more straightforward, and hopefully prevents some
breakage in the future.
'force_thru' is probably not the best name for this, but I
didn't manage to come up with anything better either, so I
left it alone.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190425162906.5242-2-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
On HSW the pipe A panel fitter lives inside the display power well,
and the input MUX for the EDP transcoder needs to be configured
appropriately to route the data through the power well as needed.
Changing the MUX setting is not allowed while the pipe is active,
so we need to force a full modeset whenever we need to change it.
Currently we may end up doing a fastset which won't change the
MUX settings, but it will drop the power well reference, and that
kills the pipe.
Cc: stable@vger.kernel.org
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: d19f958db2 ("drm/i915: Enable fastset for non-boot modesets.")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190425162906.5242-1-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
On many (all?) the Gemini Lake systems we work with, there is frequent
momentary graphical corruption at the top of the screen, and it seems
that disabling framebuffer compression can avoid this.
The ticket was reported 6 months ago and has already affected a
multitude of users, without any real progress being made. So, lets
disable framebuffer compression on GeminiLake until a solution is found.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108085
Fixes: fd7d6c5c8f ("drm/i915: enable FBC on gen9+ too")
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: <stable@vger.kernel.org> # v4.11+
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Drake <drake@endlessm.com>
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190423092810.28359-1-jian-hong@endlessm.com
DRM HDCP SRM revocation check services are used from I915 for HDCP1.4
and 2.2 revocation check during the respective authentication flow.
v2:
Rebased.
v3:
%s/*_ksvs_revocated/*_check_ksvs_revoked [Daniel]
unwanted noise is removed.
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507162745.25600-6-ramalingam.c@intel.com
Existing functions for converting a 3bytes(be24) of big endian value
into u32 of little endian and vice versa are renamed as
s/drm_hdcp2_seq_num_to_u32/drm_hdcp_be24_to_cpu
s/drm_hdcp2_u32_to_seq_num/drm_hdcp_cpu_to_be24
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Suggested-by: Daniel Vetter <daniel@ffwll.ch>
cc: Tomas Winkler <tomas.winkler@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507162745.25600-4-ramalingam.c@intel.com
Adding the HDCP2.2 capability of HDCP src and sink info into debugfs
entry "i915_hdcp_sink_capability"
This helps the userspace tests to skip the HDCP2.2 test on non HDCP2.2
sinks.
v2:
Rebased.
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507162745.25600-3-ramalingam.c@intel.com
Currently there is an underlying assumption that i915_request_unsubmit()
is synchronous wrt the GPU -- that is the request is no longer in flight
as we remove it. In the near future that may change, and this may upset
our signaling as we can process an interrupt for that request while it
is no longer in flight.
CPU0 CPU1
intel_engine_breadcrumbs_irq
(queue request completion)
i915_request_cancel_signaling
... ...
i915_request_enable_signaling
dma_fence_signal
Hence in the time it took us to drop the lock to signal the request, a
preemption event may have occurred and re-queued the request. In the
process, that request would have seen I915_FENCE_FLAG_SIGNAL clear and
so reused the rq->signal_link that was in use on CPU0, leading to bad
pointer chasing in intel_engine_breadcrumbs_irq.
A related issue was that if someone started listening for a signal on a
completed but no longer in-flight request, we missed the opportunity to
immediately signal that request.
Furthermore, as intel_contexts may be immediately released during
request retirement, in order to be entirely sure that
intel_engine_breadcrumbs_irq may no longer dereference the intel_context
(ce->signals and ce->signal_link), we must wait for irq spinlock.
In order to prevent the race, we use a bit in the fence.flags to signal
the transfer onto the signal list inside intel_engine_breadcrumbs_irq.
For simplicity, we use the DMA_FENCE_FLAG_SIGNALED_BIT as it then
quickly signals to any outside observer that the fence is indeed signaled.
v2: Sketch out potential dma-fence API for manual signaling
v3: And the test_and_set_bit()
Fixes: 52c0fdb25c ("drm/i915: Replace global breadcrumbs with per-context interrupt tracking")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190508112452.18942-1-chris@chris-wilson.co.uk
After realising we need to sample RING_START to detect context switches
from preemption events that do not allow for the seqno to advance, we
can also realise that the seqno itself is just a distance along the ring
and so can be replaced by sampling RING_HEAD.
v2: Bonus comment for the mystery separate CS_STALL before MI_USER_INTERRUPT
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190508080704.24223-1-chris@chris-wilson.co.uk
If the HW fails to ack a change in forcewake status, the machine is as
good as dead -- it may recover, but in reality it missed the mmio
updates and is now in a very inconsistent state. If it happens, we can't
trust the CI results (or at least the fails may be genuine but due to
the HW being dead and not the actual test!) so reboot the machine (CI
checks for a kernel taint in between each test and reboots if the
machine is tainted).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190508115245.27790-1-chris@chris-wilson.co.uk
There is a bug in hdmi_deep_color_possible() - we compare pipe_bpp
<= 8*3 which returns true every time for hdmi_deep_color_possible 12 bit
deep color mode test in intel_hdmi_compute_config().(Even when the
requested color mode is 10 bit through max bpc property)
Comparing pipe_bpp with bpc * 3 takes care of this condition where
requested max bpc is 10 bit, so hdmi_deep_color_possible with 12 bit
returns false when requested max bpc is 10.(Ville)
v2:Add suggested by Ville Syrjälä
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Aditya Swarup <aditya.swarup@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Clinton Taylor <Clinton.A.Taylor@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507181856.16091-1-aditya.swarup@intel.com
For us KBP is 100% identical to SPT. Kill the redundant enum
value. Also bspec doesn't talk about KBP either, so this might
avoid some confusion when cross checking the code against the
spec.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190506152627.20283-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
If we couple the scheduler more tightly with the execlists policy, we
can apply the preemption policy to the question of whether we need to
kick the tasklet at all for this priority bump.
v2: Rephrase it as a core i915 policy and not an execlists foible.
v3: Pull the kick together.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507122544.12698-1-chris@chris-wilson.co.uk
If the user is racing a call to debugfs/i915_drop_caches with ongoing
submission from another thread/process, we may never end up idling the
GPU and be uninterruptibly spinning in debugfs/i915_drop_caches trying
to catch an idle moment.
Just flush the work once, that should be enough to park the system under
correct conditions. Outside of those we either have a driver bug or the
user is racing themselves. Sadly, because the user may be provoking the
unwanted situation we can't put a warn here to attract attention to a
probable bug.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507121108.18377-4-chris@chris-wilson.co.uk
Replace the racy continuation check within retire_work with a definite
kill-switch on idling. The race was being exposed by gem_concurrent_blit
where the retire_worker would be terminated too early leaving us
spinning in debugfs/i915_drop_caches with nothing flushing the
retirement queue.
Although that the igt is trying to idle from one child while submitting
from another may be a contributing factor as to why it runs so slowly...
v2: Use the non-sync version of cancel_delayed_work(), we only need to
stop it from being scheduled as we independently check whether now is
the right time to be parking.
Testcase: igt/gem_concurrent_blit
Fixes: 79ffac8599 ("drm/i915: Invert the GEM wakeref hierarchy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507121108.18377-3-chris@chris-wilson.co.uk
The original intent for the delay before running the idle_work was to
provide a hysteresis to avoid ping-ponging the device runtime-pm. Since
then we have also pulled in some memory management and general device
management for parking. But with the inversion of the wakeref handling,
GEM is no longer responsible for the wakeref and by the time we call the
idle_work, the device is asleep. It seems appropriate now to drop the
delay and just run the worker immediately to flush the cached GEM state
before sleeping.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507121108.18377-2-chris@chris-wilson.co.uk
To complete the idle worker, we must complete 2 passes of wait-for-idle.
At the end of the first pass, we queue a switch-to-kernel-context and
may only idle after waiting for its completion. Speed up the flush_work
by doing the wait explicitly, which then allows us to remove the
unbounded loop trying to complete the flush_work in the next patch.
References: 79ffac8599 ("drm/i915: Invert the GEM wakeref hierarchy")
Testcase: igt/gem_ppgtt/flind-and-close-vma-leak
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190507121108.18377-1-chris@chris-wilson.co.uk
v2: Fix commit msg to reflect why issue occurs(Jani)
Set GCP_COLOR_INDICATION only when we set 10/12 bit deep color.
Changing settings from 10/12 bit deep color to 8 bit(& vice versa)
doesn't work correctly using xrandr max bpc property. When we
connect a monitor which supports deep color, the highest deep color
setting is selected; which sets GCP_COLOR_INDICATION. When we change
the setting to 8 bit color, we still set GCP_COLOR_INDICATION which
doesn't allow the switch back to 8 bit color.
v3,4: Add comments & drop changes in intel_hdmi_compute_config(Ville)
Since HSW+, GCP_COLOR_INDICATION is not required for 8bpc.
Drop the changes in intel_hdmi_compute_config as desired_bpp
is needed to change values for pipe_bpp based on bw_constrained flag.
v5: Fix missing logical && in condition for setting GCP_COLOR_INDICATION.
v6: Fix comment formatting (Ville)
v7: Add reviewed by Ville
v8: Set GCP_COLOR_INDICATION based on spec:
For Gen 7.5 or later platforms, indicate color depth only for deep
color modes. Bspec: 8135,7751,50524
Pre DDI platforms, indicate color depth if deep color is supported
by sink. Bspec: 7854
Exception: CHERRYVIEW behaves like Pre DDI platforms.
Bspec: 15975
Check pipe_bpp is less than bpp * 3 in hdmi_deep_color_possible,
to not set 12 bit deep color for every modeset. This fixes the issue
where 12 bit color was selected even when user selected 10 bit.(Ville)
v9: Maintain a consistent behavior for all platforms and support
GCP_COLOR_INDICATION only when we are in deep color mode. Remove
hdmi_sink_is_deep_color() - no longer needed as checking pipe_bpp > 24
takes care of the deep color mode scenario.
Separate patch for fixing switch from 12 bit to 10 bit deep color
mode.
Co-developed-by: Aditya Swarup <aditya.swarup@intel.com>
Signed-off-by: Clinton Taylor <Clinton.A.Taylor@intel.com>
Signed-off-by: Aditya Swarup <aditya.swarup@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190429230811.9983-1-aditya.swarup@intel.com
Due to the asynchronous tasklet and recursive GT wakeref, it may happen
that we submit to the engine (underneath it's own wakeref) prior to the
central wakeref being marked as taken. Switch to checking the local wakeref
for greater consistency.
Fixes: 79ffac8599 ("drm/i915: Invert the GEM wakeref hierarchy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503115225.30831-3-chris@chris-wilson.co.uk
The counter goes to zero at the start of the parking cycle, but the
wakeref itself is held until the end. Likewise, the counter becomes one
at the end of the unparking, but the wakeref is taken first. If we check
the wakeref instead of the counter, we include the unpark/unparking time
as intel_wakeref_is_active(), and do not spuriously declare inactive if
we fail to park (i.e. the parking and wakeref drop is postponed).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503115225.30831-2-chris@chris-wilson.co.uk
Inside the signal handler, we expect the requests to be ordered by their
breadcrumb such that no later request may be complete if we find an
earlier incomplete. Add an assert to check that the next breadcrumb
should not be logically before the current.
v2: Move the overhanging line into its own function and reuse it after
doing the insertion.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503152214.26517-1-chris@chris-wilson.co.uk
Acquiring the signaler's timeline takes an active reference to their
HWSP that we would like to avoid if possible, so take it after
performing all of our allocations required to set up the fencing. The
acquisition also provides the final check that the target has not
already signaled allowing us to avoid the semaphore at the last moment.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503140239.32668-1-chris@chris-wilson.co.uk
hsw_enable_pc8()/hsw_disable_pc8() are more less equivalent to
the display core init/unit functions of later platforms. Relocate
the hsw/bdw code into intel_runtime_pm.c so that it sits next to
its cousins.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503193143.28240-2-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
Move the w/a to disable IPC on SKL closer to the actual code
that implements IPS. Otherwise I just end up confused as to
what is excluding SKL from considerations.
IMO this makes more sense anyway since the hw does have the
feature, we're just not supposed to use it.
And this also makes us actually disable IPC in case eg. the
BIOS enabled it when it shouldn't have.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503173807.10834-3-ville.syrjala@linux.intel.com
Asking the GPU to busywait on a memory address, perhaps not unexpectedly
in hindsight for a shared system, leads to bus contention that affects
CPU programs trying to concurrently access memory. This can manifest as
a drop in transcode throughput on highly over-saturated workloads.
The only clue offered by perf, is that the bus-cycles (perf stat -e
bus-cycles) jumped by 50% when enabling semaphores. This corresponds
with extra CPU active cycles being attributed to intel_idle's mwait.
This patch introduces a heuristic to try and detect when more than one
client is submitting to the GPU pushing it into an oversaturated state.
As we already keep track of when the semaphores are signaled, we can
inspect their state on submitting the busywait batch and if we planned
to use a semaphore but were too late, conclude that the GPU is
overloaded and not try to use semaphores in future requests. In
practice, this means we optimistically try to use semaphores for the
first frame of a transcode job split over multiple engines, and fail if
there are multiple clients active and continue not to use semaphores for
the subsequent frames in the sequence. Periodically, we try to
optimistically switch semaphores back on whenever the client waits to
catch up with the transcode results.
With 1 client, on Broxton J3455, with the relative fps normalized by %cpu:
x no semaphores
+ drm-tip
* patched
+------------------------------------------------------------------------+
| * |
| *+ |
| **+ |
| **+ x |
| x * +**+ x |
| x x * * +***x xx |
| x x * * *+***x *x |
| x x* + * * *****x *x x |
| + x xx+x* + *** * ********* x * |
| + x xx+x* * *** +** ********* xx * |
| * + ++++* + x*x****+*+* ***+*************+x* * |
|*+ +** *+ + +* + *++****** *xxx**********x***+*****************+*++ *|
| |__________A_____M_____| |
| |_______________A____M_________| |
| |____________A___M________| |
+------------------------------------------------------------------------+
N Min Max Median Avg Stddev
x 120 2.60475 3.50941 3.31123 3.2143953 0.21117399
+ 120 2.3826 3.57077 3.25101 3.1414161 0.28146407
Difference at 95.0% confidence
-0.0729792 +/- 0.0629585
-2.27039% +/- 1.95864%
(Student's t, pooled s = 0.248814)
* 120 2.35536 3.66713 3.2849 3.2059917 0.24618565
No difference proven at 95.0% confidence
With 10 clients over-saturating the pipeline:
x no semaphores
+ drm-tip
* patched
+------------------------------------------------------------------------+
| ++ ** |
| ++ ** |
| ++ ** |
| ++ ** |
| ++ xx *** |
| ++ xx *** |
| ++ xxx*** |
| ++ xxx*** |
| +++ xxx*** |
| +++ xx**** |
| +++ xx**** |
| +++ xx**** |
| +++ xx**** |
| ++++ xx**** |
| +++++ xx**** |
| +++++ x x****** |
| ++++++ xxx******* |
| ++++++ xxx******* |
| ++++++ xxx******* |
| ++++++ xx******** |
| ++++++ xxxx******** |
| ++++++ xxxx******** |
| ++++++++ xxxxx********* |
|+ + + + ++++++++ xxx*xx**********x* *|
| |__A__| |
| |__AM__| |
| |__A_| |
+------------------------------------------------------------------------+
N Min Max Median Avg Stddev
x 120 2.47855 2.8972 2.72376 2.7193402 0.074604933
+ 120 1.17367 1.77459 1.71977 1.6966782 0.085850697
Difference at 95.0% confidence
-1.02266 +/- 0.0203502
-37.607% +/- 0.748352%
(Student's t, pooled s = 0.0804246)
* 120 2.57868 3.00821 2.80142 2.7923878 0.058646477
Difference at 95.0% confidence
0.0730476 +/- 0.0169791
2.68622% +/- 0.624383%
(Student's t, pooled s = 0.0671018)
Indicating that we've recovered the regression from enabling semaphores
on this saturated setup, with a hint towards an overall improvement.
Very similar, but of smaller magnitude, results are observed on both
Skylake(gt2) and Kabylake(gt4). This may be due to the reduced impact of
bus-cycles, where we see a 50% hit on Broxton, it is only 10% on the big
core, in this particular test.
One observation to make here is that for a greedy client trying to
maximise its own throughput, using semaphores is the right choice. It is
only the holistic system-wide view that semaphores of one client
impacts another and reduces the overall throughput where we would choose
to disable semaphores.
The most noticeable negactive impact this has is on the no-op
microbenchmarks, which are also very notable for having no cpu bus load.
In particular, this increases the runtime and energy consumption of
gem_exec_whisper.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Dmitry Ermilov <dmitry.ermilov@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190504070707.30902-1-chris@chris-wilson.co.uk
Turns out the cursor is compatible with the pipe "HDR mode". It's
only the actual SDR planes that get entirely bypassed during
blending. So let's ignore the cursor when checking if we have
any planes active that aren't HDR compatible. This fixes the
regressions in the kms_cursor_crc and kms_plane_cursor tests.
Cc: Uma Shankar <uma.shankar@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110579
Fixes: 09b25812db ("drm/i915: Enable pipe HDR mode on ICL if only HDR planes are used")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190502200607.14504-2-ville.syrjala@linux.intel.com
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
I fumbled the PIPEMISC write into the wrong place. It only gets
called for fastsets, but since value needs to be updated based on
the set of active planes it needs to be done for all plane updates.
Move it to the correct spot.
The symptoms include SDR planes never showing up if a previous
modeset/fastset left the pipe in HDR mode. This was immediately
obvious when running the kms_plane pixel format tests. Unfortunately
the test didn't realize it was scanning out pure black all the time
and declared success anyway.
Cc: Uma Shankar <uma.shankar@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Fixes: 09b25812db ("drm/i915: Enable pipe HDR mode on ICL if only HDR planes are used")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190502200607.14504-1-ville.syrjala@linux.intel.com
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Currently we submit the semaphore busywait as soon as the signaler is
submitted to HW. However, we may submit the signaler as the tail of a
batch of requests, and even not as the first context in the HW list,
i.e. the busywait may start spinning far in advance of the signaler even
starting.
If we wait until the request before the signaler is completed before
submitting the busywait, we prevent the busywait from starting too
early, if the signaler is not first in submission port.
To handle the case where the signaler is at the start of the second (or
later) submission port, we will need to delay the execution callback
until we know the context is promoted to port0. A challenge for later.
Fixes: e886196469 ("drm/i915: Use HW semaphores for inter-engine synchroni
sation on gen8+")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190501114541.10077-9-chris@chris-wilson.co.uk
Given sufficient preemption, we may see a busy system that doesn't
advance seqno while performing work across multiple contexts, and given
sufficient pathology not even notice a change in ACTHD. What does change
between the preempting contexts is their RING, so take note of that and
treat a change in the ring address as being an indication of forward
progress.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190501114541.10077-1-chris@chris-wilson.co.uk
Drop the check in GEM parking that the engines were already parked. The
intention here was that before we dropped the GT wakeref, we were sure
that no more interrupts could be raised -- however, we have already
dropped the wakeref by this point and the warning is no longer valid.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190502150024.16636-2-chris@chris-wilson.co.uk
Tidy up the cleanup sequence by always ensure that the tasklet is
flushed on parking (before we cleanup). The parking provides a
convenient point to ensure that the backend is truly idle.
v2: Do the full check for idleness before parking, to be sure we flush
any residual interrupt.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190503080942.30151-1-chris@chris-wilson.co.uk
We are not allowed to rpm_get() inside the runtime-suspend callback, so
split the intel_uc_suspend() into the core that assumes the caller holds
the wakeref (intel_uc_runtime_suspend), and one that acquires the wakeref
as necessary (intel_uc_suspend).
Reported-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Fixes: 79ffac8599 ("drm/i915: Invert the GEM wakeref hierarchy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190502203009.15727-1-chris@chris-wilson.co.uk
