If the primary gets marked as disabled while the pipe is off for
instance, we should still re-enable it when the pipe is turned on,
unless the sprite covers it fully also in that configuration.
Unfortunately we do the plane visibility checks only in the sprite code,
which is executed after the primary enabling when turning the pipe off.

Ideally we should compute the plane visibility before touching the
hardware at all, but for now just set the primary_disabld flag
in intel_{enable,disable}_plane.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

If channel equalization succeeds, there's no indication something went
wrong in clock recovery (unless debug is enabled). We should shout about
the failures and fix them instead of hiding them under the carpet.

This has allowed bugs like [1] stay dormant for a long time.

[1] https://bugs.freedesktop.org/show_bug.cgi?id=70117Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

The VGACNTRL register contains a bunch of other stuff besides
the VGA_DISP_DISABLE bit. When we write the register we always set those
other bits to zero, so normally the current check would work.

However on HSW disabling and re-enabling the power well will reset the
VGACNTRL register to its default value, which has several of the other
bits set as well.

So only look at the VGA_DISP_DISABLE bit when checking whether the VGA
plane needs re-disabling.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Everyone else uses intel_PLL_is_valid(), so make VLV use it as well.

We don't have any special p and m limits on VLV, so skip those tests,
and we also need to skip the m1<=m2 test line PNV.

Reorganize the function a bit to move the n check alongside the rest of
the test for the non-derived dividers, and check the derived values
afterwards.

Note that this changes vlv_find_best_dpll() in two ways:
- The .vco comparison is now >max instead of >=max, and since we round
  down when calculating that stuff, we may now allow frequencies slightly
  above the max as we do on other platforms. The previous method
  disallowed exactly max and anything above it.
- We now check the .dot frequency against the data rate limits, which we
  didn't do before.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

If vlv_find_best_dpll() couldn't find suitable PLL settings,
just say so instead of lying to caller.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

After aligning the p1 divider limits, and removing the unused p and m
limits, intel_limits_vlv_dac and intel_limits_vlv_hdmi are identical.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

We don't use .dot_limit for anything on VLV, so don't populate it.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

We never check the p and m limits (which according to comments are
based on someone's guesswork), so just remove them.

VLV2_DPLL_mphy_hsdpll_frequency_table_ww6_rev1p1.xlsm has no p and m
limits listed.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

VLV2_DPLL_mphy_hsdpll_frequency_table_ww6_rev1p1.xlsm tells us that the
minimum p2 divider is 2. Use that limit on the code.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

According to VLV2_DPLL_mphy_hsdpll_frequency_table_ww6_rev1p1.xlsm p1
can be 2-3 always.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

For some reason there's a sort of off by one issue with the p1 divider.
The actual p1 limits according to
VLV2_DPLL_mphy_hsdpll_frequency_table_ww6_rev1p1.xlsm is 2-3, so we should
just say that instead of saying 1-3 and avoiding the 1 via the choice of
comparison operator.

I don't know why we're using different p1 limits for intel_limits_vlv_dac
and intel_limits_vlv_hdmi, but let's preserve that for now.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

We limit the maximum n divider value in order to make sure the PLL's
reference inout is at least 19.2 MHz. I assume that is done to satisfy
some hardware requirement.

However we never check whether that calculated limit is below the
maximum supoorted N divider value (7). In practice that is always true
since we only support 100 MHz reference clock, but making the code
safe against higher reference clocks seems like a reasoanble thing to
do.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

The p2 divider on VLV needs to be even when it's > 10. The current code
to make that happen is rather weird. Just make the step size adjustement
in the for loop decrement step.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Rewrite vlv_find_best_dpll() to use intel_clock_t rather than
an army of local variables.

Also extract the code to calculate the derived values into
vlv_clock().

v2: Split up the earlier fixes, extract vlv_clock()
v3: Initialize best_clock
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

We do 'bestppm - 10' in vlv_find_best_dpll() but never check whether
that might underflow. Add such a check.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Use div_u64() to make the ppm calculation in vlv_find_best_dpll() safe
against interger overflows.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Signed-off-by: NDamien Lespiau <damien.lespiau@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

The interface uses an unsigned long, and we can use the unsigned counter
throughout our code, so do so. In the process, we notice one instance
where the shrink count is based on a heuristic rather than the result,
and another where we ask for too many pages to be purged.

v2: nr_to_scan needs to be promoted to a long as well, so just use
    sc->nr_to_scan directly.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Since we are waiting upon IO completion, inform the kernel through use
of the io_schedule() call rather than the regular schedule(). This
should allow the kernel to make better decisions regarding scheduling
and power management.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

It's not really needed, rather just adds another place to hold
intermediate values that could go wrong, and it's not clear that the
training pattern set or training lane set should be written at this
point at all.
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

The user of these counters was killed in

 commit d79cdc83
 Author: Daniel Vetter <daniel.vetter@ffwll.ch>
 Date:   Thu Aug 8 15:41:32 2013 +0200

    drm: no-op out GET_STATS ioctl

so clean up the leftovers as well.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

We can get the PCI vendor and device IDs via dev->pdev. So we can drop
the duplicated information.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

drm_vblank_init() is too ugly. Make it a bit easier on the eye by
collecting all the per-crtc vblank counters, timestamps etc. to
a structure and just allocate an array of those.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

vblank_disable_allowed is only ever 0 or 1, so make it a bool.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

v2: duplicate intel_connector->edid, not uninitialized edid (Dave Airlie).
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

All drivers embed gem-objects into their own buffer objects. There is no
reason to keep drm_gem_object_alloc(), gem->driver_private and
->gem_init_object() anymore.

New drivers are highly encouraged to do the same. There is no benefit in
allocating gem-objects separately.

Cc: Dave Airlie <airlied@gmail.com>
Cc: Alex Deucher <alexdeucher@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Inki Dae <inki.dae@samsung.com>
Cc: Ben Skeggs <skeggsb@gmail.com>
Cc: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Signed-off-by: NDavid Herrmann <dh.herrmann@gmail.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

When booting with i915.fastboot=1, we always take tha code path and end
up undoing what we're trying to do with adjusted_mode.

Hopefully, as the fastboot hardware readout code is using adjusted_mode
as well, it should be equivalent.
Signed-off-by: NDamien Lespiau <damien.lespiau@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Instead of it just being on the mailing list, let's put Jesse's
explanation next to the code in question.
Signed-off-by: NDamien Lespiau <damien.lespiau@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

During system boot up, by default, the power gate for render, media and
display well still power gated.  Normally, BIOS will turn off the power
gate.  In the BIOS-less system, the driver need to turn off the power
gate very early during driver load.

v2: Move this to intel_uncore_sanitize to allow it to get call during
resume path. (Daniel)
v3: Remove redundant write 0 to DPIO_CTL, and use DPIO_RESET instead of
just 0x1 (Ville)
    Add turn of power gate for display 2d/render well/media well.
v4: Remove toggle cmnreset in intel_uncore_sanitize.  Cmnreset should
toggle after CRI clock source has been selected.  Jesse DPIO reset patch
which toggle the cmnreset in intel_modeset_init_hw() should handle it.
(Ville)
Signed-off-by: NChon Ming Lee <chon.ming.lee@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

DPIO needs to have common reset de-asserted on soft resets like boot and
S3.  In some cases, the BIOS will have done this for us, but it should
be safe to do at runtime as well, as long as we do it when the pipes are
otherwise off.

v2: update bit name to match docs better (Ville)
    reset after CRI clock select (Ville)

References: https://bugs.freedesktop.org/show_bug.cgi?id=69166Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

for igt test case.

v2: remove trailing spaces and fix conflicts
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@gmail.com>
[danvet:
- make it comipile
- s/IS_HASWELL/HAS_PSR/]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

After applying wait-boost we often find ourselves stuck at higher clocks
than required. The current threshold value requires the GPU to be
continuously and completely idle for 313ms before it is dropped by one
bin. Conversely, we require the GPU to be busy for an average of 90% over
a 84ms period before we upclock. So the current thresholds almost never
downclock the GPU, and respond very slowly to sudden demands for more
power. It is easy to observe that we currently lock into the wrong bin
and both underperform in benchmarks and consume more power than optimal
(just by repeating the task and measuring the different results).

An alternative approach, as discussed in the bspec, is to use a
continuous threshold for upclocking, and an average value for downclocking.
This is good for quickly detecting and reacting to state changes within a
frame, however it fails with the common throttling method of waiting
upon the outstanding frame - at least it is difficult to choose a
threshold that works well at 15,000fps and at 60fps. So continue to use
average busy/idle loads to determine frequency change.

v2: Use 3 power zones to keep frequencies low in steady-state mostly
idle (e.g. scrolling, interactive 2D drawing), and frequencies high
for demanding games. In between those end-states, we use a
fast-reclocking algorithm to converge more quickly on the desired bin.

v3: Bug fixes - make sure we reset adj after switching power zones.

v4: Tune - drop the continuous busy thresholds as it prevents us from
choosing the right frequency for glxgears style swap benchmarks. Instead
the goal is to be able to find the right clocks irrespective of the
wait-boost.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Stéphane Marchesin <stephane.marchesin@gmail.com>
Cc: Owen Taylor <otaylor@redhat.com>
Cc: "Meng, Mengmeng" <mengmeng.meng@intel.com>
Cc: "Zhuang, Lena" <lena.zhuang@intel.com>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

If we encounter a situation where the CPU blocks waiting for results
from the GPU, give the GPU a kick to boost its the frequency.

This should work to reduce user interface stalls and to quickly promote
mesa to high frequencies - but the cost is that our requested frequency
stalls high (as we do not idle for long enough before rc6 to start
reducing frequencies, nor are we aggressive at down clocking an
underused GPU). However, this should be mitigated by rc6 itself powering
off the GPU when idle, and that energy use is dependent upon the workload
of the GPU in addition to its frequency (e.g. the math or sampler
functions only consume power when used). Still, this is likely to
adversely affect light workloads.

In particular, this nearly eliminates the highly noticeable wake-up lag
in animations from idle. For example, expose or workspace transitions.
(However, given the situation where we fail to downclock, our requested
frequency is almost always the maximum, except for Baytrail where we
manually downclock upon idling. This often masks the latency of
upclocking after being idle, so animations are typically smooth - at the
cost of increased power consumption.)

Stéphane raised the concern that this will punish good applications and
reward bad applications - but due to the nature of how mesa performs its
client throttling, I believe all mesa applications will be roughly
equally affected. To address this concern, and to prevent applications
like compositors from permanently boosting the RPS state, we ratelimit the
frequency of the wait-boosts each client recieves.

Unfortunately, this techinique is ineffective with Ironlake - which also
has dynamic render power states and suffers just as dramatically. For
Ironlake, the thermal/power headroom is shared with the CPU through
Intelligent Power Sharing and the intel-ips module. This leaves us with
no GPU boost frequencies available when coming out of idle, and due to
hardware limitations we cannot change the arbitration between the CPU and
GPU quickly enough to be effective.

v2: Limit each client to receiving a single boost for each active period.
    Tested by QA to only marginally increase power, and to demonstrably
    increase throughput in games. No latency measurements yet.

v3: Cater for front-buffer rendering with manual throttling.

v4: Tidy up.

v5: Sadly the compositor needs frequent boosts as it may never idle, but
due to its picking mechanism (using ReadPixels) may require frequent
waits. Those waits, along with the waits for the vrefresh swap, conspire
to keep the GPU at low frequencies despite the interactive latency. To
overcome this we ditch the one-boost-per-active-period and just ratelimit
the number of wait-boosts each client can receive.
Reported-and-tested-by: NPaul Neumann <paul104x@yahoo.de>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68716Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Stéphane Marchesin <stephane.marchesin@gmail.com>
Cc: Owen Taylor <otaylor@redhat.com>
Cc: "Meng, Mengmeng" <mengmeng.meng@intel.com>
Cc: "Zhuang, Lena" <lena.zhuang@intel.com>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
[danvet: No extern for function prototypes in headers.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

When we switched to always using a timeout in conjunction with
wait_seqno, we lost the ability to detect missed interrupts. Since, we
have had issues with interrupts on a number of generations, and they are
required to be delivered in a timely fashion for a smooth UX, it is
important that we do log errors found in the wild and prevent the
display stalling for upwards of 1s every time the seqno interrupt is
missed.

Rather than continue to fix up the timeouts to work around the interface
impedence in wait_event_*(), open code the combination of
wait_event[_interruptible][_timeout], and use the exposed timer to
poll for seqno should we detect a lost interrupt.

v2: In order to satisfy the debug requirement of logging missed
interrupts with the real world requirments of making machines work even
if interrupts are hosed, we revert to polling after detecting a missed
interrupt.

v3: Throw in a debugfs interface to simulate broken hw not reporting
interrupts.

v4: s/EGAIN/EAGAIN/ (Imre)
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NImre Deak <imre.deak@intel.com>
[danvet: Don't use the struct typedef in new code.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

We missed adding a few cleanup steps for recent additions.

Reviewer:  Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@gmail.com>
Reviewed-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This patch attempts to clean up the ring/IA scaling programming in the
following ways.
1. Fix the comment about the DDR frequency. The math is 266MHz, not
133MHz. Formula was right, docs are wrong.

2. Mask the DCLK register since I don't know how it is defined on future
platforms.

3. use mult_frac instead of magic math.

This helps for future platform enabling.

v2: Actually use the right patch. The v1 was a mix of things, none of
which was right. Note that due to rounding, we actually get different
values (slightly higher) for the effective ring frequency.

v3: Use 1.25 instead of 1.33 as the original code did. (Jesse)

CC: Jesse Barnes <jbarnes@virtuousgeek.org>
CC: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

If we ever end up doing the retry loop due to bandwidth constraints, we
would rewrite pipe_src_{w,n} based on adjusted_mode timings. But by that
time the encoder may have already replaced the adjusted_mode with a
fixed panel mode, which would then corrupt pipe_src_{w,h}.

v2: Use requested_mode and slap on a big comment from Daniel
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This workaround is described in the mode set sequence documentation.
When enabling planes for the second pipe, we need to wait for 2
vblanks on the first pipe. This should solve "a flash of screen
corruption if planes are enabled on second/third pipe during the time
that big FIFO mode is exiting". Watermarks are fun :)

v2: Save indentation levels
Signed-off-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Refactor the plane enabling/disabling into helper functions and move
the calls to happen as the first thing during .crtc_disable, and the
last thing during .crtc_enable.

Those are the two clear points where we are sure that the pipe is
actually running regardless of the encoder type or hardware
generation.

v2: Made by Paulo:
  Remove the code touching everything but the Haswell functions. We
  need this change on Haswell right now since it fixes a FIFO underrun
  that we get on pipe A while we enable pipe B (see the workaround
  notes on the Haswell mode set sequence documentation). We can bring
  back the code to gens 2-7 later, once they're tested.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>