Add display/intel_display_trace.[ch] for defining display
tracepoints. The main goal is to reduce cross-includes between gem and
display. It would be possible split up tracing even further, but that
would lead to more boilerplate.

We end up having to include intel_crtc.h in a few places because it was
pulled in implicitly via intel_de.h -> i915_trace.h -> intel_crtc.h, and
that's no longer the case.

There should be no changes to tracepoints.

v3:
- Rebase

v2:
- Define TRACE_INCLUDE_PATH relative to define_trace.h (Chris)
- Remove useless comments (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NLucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/7862ad764fbd0748d903c76bc632d3d277874e5b.1638961423.git.jani.nikula@intel.com

Changes since v2.12:
  - Release notes for v2.13:
      1. Fix for simple flip queue with DC6v
  - Release notes for v2.14:
      1. Fix for flip queue roll over cases with DC6v
      2. Enhancement for residency
      3. Workaround for 3Dlut restore issue

v2: Commit message update (Imre)
Signed-off-by: NMadhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
Reviewed-by: NLucas De Marchi <lucas.demarchi@intel.com>
Acked-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: NLucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211208213115.1919503-1-lucas.demarchi@intel.com

Supposedly we should be able to change the cdclk squasher waveform
even when many pipes are active. Make it so.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211119131348.725220-6-mika.kahola@intel.com

To calculate CD clock with squasher unit, we set CD clock ratio to fixed value of 34.
The CD clock value is read from CD clock squasher table.

BSpec: 54034

v2: Read ratio from register (Ville)
    Drop unnecessary local variable (Ville)
    Get CD clock from the given table
v3: Calculate CD clock frequency based on waveform bit pattern (Ville)
[v4: vsyrjala: Actually do a proper blind readout from the hardware]
[v5: vsyrjala: Use has_cdclk_squasher()]
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211119131348.725220-5-mika.kahola@intel.com

Set CD clock squashing registers based on selected CD clock.

v2: use slk_cdclk_decimal() to compute decimal values instead of a
    specific table (Ville)
    Set waveform based on CD clock table (Ville)
    Drop unnecessary local variable (Ville)
v3: Correct function naming (Ville)
    Correct if-else structure (Ville)
[v4: vsyrjala: Fix spaces vs. tabs]
[v5: vsyrjala: Fix cd2x divider calculation (Uma),
               Add warn to waveform lookup (Uma),
               Handle bypass freq in waveform lookup,
               Generalize waveform handling in bxt_set_cdclk()]
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211119131348.725220-4-mika.kahola@intel.com

In case of CD clock squashing the divider is always 1. We don't
need to calculate the divider in use so let's skip that for DG2.

v2: Drop unnecessary local variable (Ville)
v3: Avoid if-else structure (Ville)
[v4: vsyrjala: Fix cd2x divider calculation (Uma),
               Introduce has_cdclk_squasher()]
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211119131348.725220-3-mika.kahola@intel.com

For CD clock squashing method, we need to define corresponding CD clock table for
reference clocks, dividers and ratios for all CD clock options.

BSpec: 54034

v2: Add CD squashing waveforms as part of CD clock table (Ville)
v3: Waveform is 16 bits wide (Ville)
[v4: vsyrjala: Nuke the non-squasher based table,
               Set .divider=2 for consistency,
	       Pack intel_cdclk_vals a bit nicer]
v5: Fix error in waveform value (Swati)
v6 (Lucas): Rebase on upstream
v7 (MattR): Drop 40.8, 81.6, and 122.4 MHz frequencies to reflect new
    bspec update.
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: NStanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211119131348.725220-2-mika.kahola@intel.com

Localize HOBL and low vswing VBT lookups to a couple of small helpers,
and get rid of a bunch of local variables.
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NJosé Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211203131318.2885969-1-jani.nikula@intel.com

The mode set sequence for 128b/132b requires setting the div32 version
of MPLLB clock.

Bspec: 53880, 54128
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211202144456.2541305-1-jani.nikula@intel.com

Enable Pipe Degamma for XE_LPD. Extend the legacy implementation
to incorparate the extended lut size for XE_LPD.

v2: Added a helper for degamma lut size (Ville)
Signed-off-by: NUma Shankar <uma.shankar@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211207071135.3660332-3-uma.shankar@intel.com

Enable pipe color support for Display 13 platforms. Currently
limit to just 10bit gamma and later extend it for logarithmic
gamma, once the new UAPI is agreed by community and implemented
by a userspace consumer.

v2: Updated dev_priv to i915 (Ville)
Signed-off-by: NUma Shankar <uma.shankar@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211207071135.3660332-2-uma.shankar@intel.com

Increase the max size of DMC on ADL-P to account for support of new
features in the current/upcoming DMC versions.
Signed-off-by: NMadhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
Reviewed-by: NLucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: NLucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211207023718.322349-1-madhumitha.tolakanahalli.pradeep@intel.com

From VBT, ddc pin info suggests the following mapping:
    VBT                                    DRIVER
    DDI TC1->ddc_pin=3 should translate to PORT_TC1->0x9
    DDI TC2->ddc_pin=4 should translate to PORT_TC2->0xa
    DDI TC3->ddc_pin=5 should translate to PORT_TC3->0xb
    DDI TC4->ddc_pin=6 should translate to PORT_TC4->0xc

Adding pin map to facilitate this translation as we cannot use existing
icl ddc pin map due to conflict with DDI C and DDI TC1 info.

Bspec:20124

v2:
  - Changed Author to Tejas Upadhyay

Cc: Clinton Taylor <Clinton.A.Taylor@intel.com>
Cc: Matt Atwood <matthew.s.atwood@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Acked-by: NImre Deak <imre.deak@intel.com>
Signed-off-by: NLee Shawn C <shawn.c.lee@intel.com>
Signed-off-by: NTejas Upadhyay <tejaskumarx.surendrakumar.upadhyay@intel.com>
Signed-off-by: NRaviteja Goud Talla <ravitejax.goud.talla@intel.com>
Signed-off-by: NLucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211203073720.3823371-1-ravitejax.goud.talla@intel.com

Replace the "sizes are 0 based" stuff with just straight
up -1 where needed. Less confusing all around.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211201152552.7821-4-ville.syrjala@linux.intel.comReviewed-by: NJosé Roberto de Souza <jose.souza@intel.com>

Now that each plane tracks its own no_fbc_reason we can print that
out in debugfs, and we can also show which plane is currently
selected for FBC duty.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-21-ville.syrjala@linux.intel.comReviewed-by: NJani Nikula <jani.nikula@intel.com>

FBC and double wide pipe are mutually exclusive. Disable FBC when
we have to resort to double wide.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-20-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Rename the 'params' to just fbc state.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-19-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Currently we track the FBC plane as a pointer under intel_fbc
and also as a i9xx_plane_id under intel_fbc_state. Just store
the pointer once in the fbc state.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-18-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

fbc->state_cache has now become useless. We can simply update
the reg params directly from the plane/crtc states during
__intel_fbc_enable().
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-17-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Currently a FIFO underrun just causes FBC to be deactivated,
and later checks then prevent it from being reactivated. We
can simpify our lives a bit by logically disabling FBC on
FIFO underruns. This avoids the funny intermediate state where
FBC is logically enabled but can't actually be activated.

v2: intel_wait_for_vblank() is no more
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-16-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Don't really see a good reason why we can't just do the vgpu and
modparam checks already in intel_fbc_check_plane().
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-15-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

In the future we may have more than one FBC instance on some
platforms. So let's just allocate it dynamically. This also
lets us fully hide the implementation from prying eyes.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-14-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

In order to better encapsulate the FBC implementation
introduce a small helper to do the plane<->FBC instance
association.

We'll also try to structure the plane init code such
that introducing multiple FBC instances will be easier
down the line.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-13-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

In order to encapsulate FBC harder let's just move the debugfs
stuff into intel_fbc.c.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-12-ville.syrjala@linux.intel.comAcked-by: NJani Nikula <jani.nikula@intel.com>

The underrun code doesn't need to know any details about FBC, so
just pass in the whole device rather than a specific FBC instance.
We could make this a bit more fine grained by also passing in the
pipe to intel_fbc_handle_fifo_underrun_irq() and letting the FBC
code figure which FBC instance (if any) is active on said pipe.
But that seems a bit overkill for this so don't bother.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-11-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Use an early return to flatten most of __intel_fbc_pre_update().
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-10-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

In the future we may have multiple planes on the same pipe
capable of using FBC. Prepare for that by tracking FBC usage
per-plane rather than per-crtc.

v2: s/intel_get_crtc_for_pipe/intel_crtc_for_pipe/
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-9-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Pass the FBC instance instead of the crtc to a bunch of places.

We also adjust intel_fbc_post_update() to do the
intel_fbc_get_reg_params() things instead of doing it from the lower
level function (which also gets called for front buffer tracking).
Nothing in there will change during front buffer updates.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-8-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

The FBC state cache and params are now nearly identical. Just
use the same structure for both.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-7-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

There isn't a good reason why we'd have to cache all this
plane state stuff in the FBC state. Instead we can just
pre-calculate what FBC will really need.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-6-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Move intel_fbc_override_cfb_stride() next to its cousins.
Helps with later patches.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-5-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

There's no need to store all this stuff in intel_fbc_state_cache.
Just check it all against the plane/crtc states and store only
what we need. Probably more should get nuked still, but this
is a start.

So what we'll do is:
- each plane will check its own state and update its local
  no_fbc_reason
- the per-plane no_fbc_reason (if any) then gets propagated
  to the cache->no_fbc_reason while doing the actual update
- fbc->no_fbc_reason gets updated in the end with either
  the value from the cache or directly from frontbuffer
  tracking

It's still a bit messy, but should hopefuly get cleaned up
more in the future. At least now we can observe each plane's
reasons for rejecting FBC now more consistently, and we don't
have so mcuh redundant state store all over the place.

v2: store no_fbc_reason per-plane instead of per-pipe
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-4-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

No reason to burden the caller with the details on how the minimum
compression limit is calculated, so just pass in the whole plane
state instead of just the cpp value.
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211124113652.22090-3-ville.syrjala@linux.intel.comReviewed-by: NMika Kahola <mika.kahola@intel.com>

Rename the PLANE_CUS_CTL Y plane selection bits to actually
say "Y plane".
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211201152552.7821-6-ville.syrjala@linux.intel.comReviewed-by: NJosé Roberto de Souza <jose.souza@intel.com>

Rename the YUV byte order bits to be a bit more consistent.

v2: Deal with gvt
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211201152552.7821-3-ville.syrjala@linux.intel.comReviewed-by: NJosé Roberto de Souza <jose.souza@intel.com>

Let's just stick to 32bit mmio accesses so we can get rid
of the bare "uncore" reg access in display code. The register
are defined as 32bit in the spec anyway.

We could define a 64bit "de" variant I suppose, but doesn't
really make much sense just for this one case, and when we
start to use the DSB for this stuff we'd also need another
64bit variant for that. Just easier to do 32bit always.

While at it we can reorder stuff a bit so that we write the
registers in order of increasing offset (more or less).
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211201152552.7821-2-ville.syrjala@linux.intel.comReviewed-by: NJosé Roberto de Souza <jose.souza@intel.com>

Break the dependency on i915_drv.h.
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ee740f494e416d875e057c2eda585f4e66d65500.1638366969.git.jani.nikula@intel.com

Avoid looking into the guts of struct drm_i915_private in
headers. Again, converting an inline function to a macro is less than
ideal, but avoids having to pull in i915_drv.h just for the to_i915()
part.
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ed6c43455d13c90ebfed442b196625af5e6ede88.1638366969.git.jani.nikula@intel.com

It's not the ideal location, but a better alternative than
i915_drv.h. The goal is to break the intel_display_types.h to i915_drv.h
dependency.
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/9f882eff78cdc6b28c18e73f5e53f57e413240dc.1638366969.git.jani.nikula@intel.com

This is far from ideal, but it reduces the i915_drv.h dependency from
intel_display_types.h. Maybe in the future we'll need a better split.
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/c6c60d9a8f6dcd1fa2f4b187000c5bb6843a1371.1638366969.git.jani.nikula@intel.com