Fixes sparse warning:

drivers/gpu/drm/i915/intel_dpll_mgr.c:1712:24: warning: Using plain
integer as NULL pointer

Fixes: a277ca7d ("drm/i915: Split bxt_ddi_pll_select()")
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Cc: Durgadoss R <durgadoss.r@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: NDhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473946137-1931-2-git-send-email-jani.nikula@intel.com

Fix sparse warning:

drivers/gpu/drm/i915/intel_dp.c:1527:5: warning: symbol
'intel_dp_compute_bpp' was not declared. Should it be static?

Fixes: f9bb705e ("drm/i915: Update bits per component for display info")
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: Jim Bride <jim.bride@linux.intel.com>
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473946137-1931-1-git-send-email-jani.nikula@intel.com

Read DisplayPort branch device info from through debugfs
interface.

v2: use drm_dp_helper routines to collect data
v3: cleanup to match the drm_dp_helper.c patches introduced
    earlier in this series
v4: move DP branch device info to function 'intel_dp_branch_device_info()'
v5: initial step to move debugging info from intel_dp. to drm_dp_helper.c (Daniel)
v6: read hw and sw revision without using specific drm_dp_helper routines
v7: indentation fixes (Jim Bride)
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-12-git-send-email-mika.kahola@intel.com

DisplayPort branch device may define max supported bits per
component. Update display info based on this value if bpc
is defined.

v2: cleanup to match the drm_dp_helper.c patches introduced
    earlier in this series
v3: Fill bpc for connector's display info in separate
    drm_dp_helper function (Daniel)
v4: remove updating bpc for display info as it may be overridden
    when parsing EDID. Instead, check bpc for DP branch device
    during compute_config
v5: Indentation fixes (Jim Bride)
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-11-git-send-email-mika.kahola@intel.com

Filter out a mode that exceeds the max pixel rate setting
for DP to VGA dongle. This is defined in DPCD register 0x81
if detailed cap info i.e. info field is 4 bytes long and
it is available for DP downstream port.

The register defines the pixel rate divided by 8 in MP/s.

v2: DPCD read outs and computation moved to drm (Ville, Daniel)
v3: Sink pixel rate computation moved to drm_dp_max_sink_dotclock()
    function (Daniel)
v4: Use of drm_dp_helper.c routines to compute max pixel clock (Ville)
v5: Use of intel_dp->downstream_ports to read out port capabilities.
    Code restructuring (Ville)
v6: Move DP branch device check to drm_dp_helper.c (Daniel)
v7: Cleanup as suggested by Ville
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-10-git-send-email-mika.kahola@intel.com

SW revision is mandatory field for DisplayPort branch
devices. This is defined in DPCD register fields 0x50A
and 0x50B.

v2: move drm_dp_ds_revision structure to be part of
    drm_dp_link structure (Daniel)
v3: remove dependency to drm_dp_helper but instead parse
    DPCD and print SW revision info to dmesg (Ville)
v4: commit message fix (Jim Bride)
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-9-git-send-email-mika.kahola@intel.com

HW revision is mandatory field for DisplayPort branch
devices. This is defined in DPCD register field 0x509.

v2: move drm_dp_ds_revision structure to be part of
    drm_dp_link structure (Daniel)
v3: remove dependency to drm_dp_helper but instead parse
    DPCD and print HW revision info to dmesg (Ville)
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-8-git-send-email-mika.kahola@intel.com

Let's remove reference to "struct intel_connector *connector"
in intel_dp_aux_init() function as it is no longer required.
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-7-git-send-email-mika.kahola@intel.com

Read DisplayPort branch device id string.
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Acked-by: NDave Airlie <airlied@gmail.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-6-git-send-email-mika.kahola@intel.com

Helper routine to read out maximum supported bits per
component for DisplayPort legay converters.

v2: Return early if detailed port cap info is not available.
    Replace if-else ladder with switch-case (Ville)
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Acked-by: NDave Airlie <airlied@gmail.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-5-git-send-email-mika.kahola@intel.com

Helper routine to read out maximum supported pixel rate
for DisplayPort legay VGA converter or TMDS clock rate
for other digital legacy converters. The helper returns
clock rate in kHz.

v2: Return early if detailed port cap info is not available.
    Replace if-else ladder with switch-case (Ville)
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Acked-by: NDave Airlie <airlied@gmail.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-4-git-send-email-mika.kahola@intel.com

Drop "VGA" from bits per component definitions as these
are also used by other standards such as DVI, HDMI,
DP++.
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Acked-by: NDave Airlie <airlied@gmail.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-3-git-send-email-mika.kahola@intel.com

Add missing DisplayPort downstream port types. The introduced
new port types are DP++ and Wireless.
Reviewed-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NMika Kahola <mika.kahola@intel.com>
Acked-by: NDave Airlie <airlied@gmail.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473419458-17080-2-git-send-email-mika.kahola@intel.com

Adding the ddb size into the devide info will avoid
platform checks while computing wm.

v2: Added comment and WARN_ON if ddb size is zero.(Jani)
v3: Added WARN_ON at the right place.(Jani)
Suggested-by: NAnder Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Signed-off-by: NDeepak M <m.deepak@intel.com>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473931870-7724-1-git-send-email-m.deepak@intel.com

Renaming to more consistent scheme, and updating comments, mostly
about i915_guc_wq_reserve(), aka i915_guc_wq_check_space().
Signed-off-by: NDave Gordon <david.s.gordon@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473711577-11454-4-git-send-email-david.s.gordon@intel.comReviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

Renaming to more consistent scheme, delete unused definitions
Signed-off-by: NDave Gordon <david.s.gordon@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473711577-11454-3-git-send-email-david.s.gordon@intel.comReviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

No functional changes; just renaming a bit, tweaking a datatype,
prettifying layout, and adding comments, in particular in the
GuC setup code that touches this data.
Signed-off-by: NDave Gordon <david.s.gordon@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473711577-11454-2-git-send-email-david.s.gordon@intel.comReviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

Commentary from Chris Wilson's original version:

> I was looking at some wait_for() timeouts on a slow system, with lots of
> debug enabled (KASAN, lockdep, mmio_debug). Thinking that we were
> mishandling the timeout, I tried to ensure that we loop at least once
> after first testing COND. However, the double test of COND either side
> of the timeout check makes that unlikely. But we can do an equivalent
> loop, that keeps the COND check after testing for timeout (required so
> that we are not preempted between testing COND and then testing for a
> timeout) without expanding COND twice.
>
> The advantage of only expanding COND once is a dramatic reduction in
> code size:
>
>    text	   data	    bss	    dec	    hex
>    1308733	   5184	   1152	1315069	 1410fd	before
>    1305341	   5184	   1152	1311677	 1403bd	after

but it turned out that due to a missing iniitialiser, gcc had "gone
wild trimming undefined code" :( This version acheives a rather more
modest (but still worthwhile) gain of ~550 bytes.
Signed-off-by: NDave Gordon <david.s.gordon@intel.com>
Original-idea-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473855033-26980-1-git-send-email-david.s.gordon@intel.comReviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

Turns out
commit a0562819 ("drm/i915: Get panel_type from OpRegion panel
details") has regressed quite a few machines. So it looks like we
can't use the panel type from OpRegion on all systems, and yet we
absolutely must use it on some specific systems.

Despite trying, I was unable to find any automagic way to determine
if the OpRegion panel type is respectable or not. The only glimmer
of hope I had was bit 8 in the SCIC response, but that turned out to
not work either (it was always 0 on both types of systems).

So, to fix the regressions without breaking the machine we know to need
the OpRegion panel type, let's just add a quirk for this. Only specific
machines known to require the OpRegion panel type will therefore use
it. Everyone else will fall bck to the VBT panel type.

The only known machine so far is a "Conrac GmbH IX45GM2". The PCI
subsystem ID on this machine is just a generic 8086:2a42, so of no use.
Instead we'll go with a DMI match.

I suspect we can now also revert
commit aeddda06 ("drm/i915: Ignore panel type from OpRegion on SKL")
but let's leave that to a separate patch.

v2: Do the DMI match in the opregion code directly, as dev_priv->quirks
    gets populated too late

Cc: Rob Kramer <rob@solution-space.com>
Cc: Martin van Es <martin@mrvanes.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Airlie <airlied@linux.ie>
Cc: Marco Krüger <krgsch@gmail.com>
Cc: Sean Greenslade <sean@seangreenslade.com>
Cc: Trudy Tective <bertslany@gmail.com>
Cc: Robin Müller <rm1990@gmx.de>
Cc: Alexander Kobel <a-kobel@a-kobel.de>
Cc: Alexey Shumitsky <alexey.shumitsky@gmail.com>
Cc: Emil Andersen Lauridsen <mine809@gmail.com>
Cc: oceans112@gmail.com
Cc: James Hogan <james@albanarts.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: stable@vger.kernel.org
References: https://lists.freedesktop.org/archives/intel-gfx/2016-August/105545.html
References: https://lists.freedesktop.org/archives/dri-devel/2016-August/116888.html
References: https://lists.freedesktop.org/archives/intel-gfx/2016-June/098826.html
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94825
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97060
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97443
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97363
Fixes: a0562819 ("drm/i915: Get panel_type from OpRegion panel details")
Tested-by: NMarco Krüger <krgsch@gmail.com>
Tested-by: NAlexey Shumitsky <alexey.shumitsky@gmail.com>
Tested-by: NSean Greenslade <sean@seangreenslade.com>
Tested-by: NEmil Andersen Lauridsen <mine809@gmail.com>
Tested-by: NRobin Müller <rm1990@gmx.de>
Tested-by: oceans112@gmail.com
Tested-by: NRob Kramer <rob@solution-space.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473758539-21565-1-git-send-email-ville.syrjala@linux.intel.com
References: http://patchwork.freedesktop.org/patch/msgid/1473602239-15855-1-git-send-email-adrienverge@gmail.comAcked-by: NJani Nikula <jani.nikula@intel.com>

This reverts

commit 1c80c25f
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Wed May 18 18:47:12 2016 +0200

    drm/i915/psr: Make idle_frames sensible again

There are panels that needs 4 idle frames before entering PSR,
but VBT is unproperly set.

Also lately it was identified that idle frame count calculated at HW
can be off by 1, what makes the minimum of 2, at least.

Without the current vbt+1 we are with the risk of having HW calculating
0 idle frames and entering PSR when it shouldn't. Regardless the lack
of link training.

[Jani: there is some disagreement on the explanation, but the commit
regresses so revert it is.]

References: http://marc.info/?i=20160904191153.GA2328@light.dominikbrodowski.net
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Fixes: 1c80c25f ("drm/i915/psr: Make idle_frames sensible again")
Cc: drm-intel-fixes@lists.freedesktop.org # v4.8-rc1+
Signed-off-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473295351-8766-1-git-send-email-rodrigo.vivi@intel.com

This adds support for KBL in the new function added in commit ID:
commit <f169660e> that returns a
shared pll in case of DDI platforms.
Signed-off-by: NManasi Navare <manasi.d.navare@intel.com>
Reviewed-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473728663-14355-1-git-send-email-manasi.d.navare@intel.com

drm already provides fallback versions of readq and writeq.
Signed-off-by: NMatthew Auld <matthew.auld@intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1473451373-9852-1-git-send-email-matthew.auld@intel.com

Fix the number of tries in channel euqalization link training sequence
according to DP 1.2 Spec. It returns a boolean depending on channel
equalization pass or failure.
Signed-off-by: NDhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: NManasi Navare <manasi.d.navare@intel.com>
Reviewed-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>

This function cleans up clock recovery loop in link training compliant
tp Dp Spec 1.2. It tries the clock recovery 5 times for the same voltage
or until max voltage swing is reached and removes the additional non
compliant retries. This function now returns a boolean values based on
if clock recovery passed or failed.

v3:
* Better Debug prints in case of failures (Mika Kahola)
v2:
* Rebased on top of new revision of vswing patch (Manasi Navare)
Signed-off-by: NDhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: NManasi Navare <manasi.d.navare@intel.com>
Reviewed-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>

Wrap the max. vswing check in a separate function.
This makes the clock recovery phase of DP link training cleaner

v3:
Fixed the paranthesis warning (Mika Kahola)
v2:
Fixed the Compiler warning (Mika Kahola)
Signed-off-by: NDhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: NManasi Navare <manasi.d.navare@intel.com>
Reviewed-by: NMika Kahola <mika.kahola@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>

Add the PLL selection code for HSW/BDW/BXT/SKL into a stand-alone function
in order to allow for the implementation of a platform neutral upfront
link training function.

v4:
* Removed dereferencing NULL pointer in  case of failure (Dhinakaran Pandiyan)
v3:
* Add Hooks for all DDI platforms into this standalone function

v2:
* Change the macro to use dev_priv instead of dev (David Weinehall)
Reviewed-by: NDurgadoss R <durgadoss.r@intel.com>
Signed-off-by: NManasi Navare <manasi.d.navare@intel.com>
Signed-off-by: NJim Bride <jim.bride@linux.intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>

Recently I have been applying an optimisation to avoid stalling and
clflushing GGTT objects based on their current binding. That is we only
set-to-gtt-domain upon first bind. However, on hibernation the objects
remain bound, but they are in the CPU domain. Currently (since commit
975f7ff4 ("drm/i915: Lazily migrate the objects after hibernation"))
we only flush scanout objects as all other objects are expected to be
flushed prior to use. That breaks down in the face of the runtime
optimisation above - and we need to flush all GGTT pinned objects
(essentially ringbuffers).

To reduce the burden of extra clflushes, we only flush those objects we
cannot discard from the GGTT. Everything pinned to the scanout, or
current contexts or ringbuffers will be flushed and rebound. Other
objects, such as inactive contexts, will be left unbound and in the CPU
domain until first use after resuming.

Fixes: 7abc98fa ("drm/i915: Only change the context object's domain...")
Fixes: 57e88531 ("drm/i915: Use VMA for ringbuffer tracking")
References: https://bugs.freedesktop.org/show_bug.cgi?id=94722Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: David Weinehall <david.weinehall@intel.com>
Reviewed-by: NMatthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909201957.2499-1-chris@chris-wilson.co.uk

In an attempt to keep the hibernation image as same as possible, let's
try and discard any unwanted pages and our own page arrays.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909190218.16831-1-chris@chris-wilson.co.uk

Now that we can wait upon fences before emitting the request, it becomes
trivial to wait upon any implicit fence provided by the dma-buf
reservation object.

To protect against failure, we force any asynchronous waits on a foreign
fence to timeout after 10s - so that a stall in another driver does not
permanently cripple ourselves. Still unpleasant though!

Testcase: igt/prime_vgem/fence-wait
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJohn Harrison <john.c.harrison@intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-21-chris@chris-wilson.co.uk

Now that we have fences in place to drive request submission, we can
employ those to queue requests after their dependencies as opposed to
stalling in the middle of an execbuf ioctl. (However, we still choose to
spin before enabling the IRQ as that is faster - though contentious.)

v2: Do the fence ordering first, where we can still fail.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-20-chris@chris-wilson.co.uk

If we are waiting upon an external fence, from the pov of hangcheck the
engine is stuck on the last submitted seqno. Currently we give a small
increment to the hangcheck score in order to catch a stuck waiter /
driver. Now that we both have an independent wait hangcheck and may be
stuck waiting on an external fence, resetting the GPU has little effect
on that external fence. As we cannot advance by resetting, skip
incrementing the hangcheck score.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-19-chris@chris-wilson.co.uk

If we find a ring waiting on a semaphore for another assigned but not yet
emitted request, treat it as valid and waiting.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-18-chris@chris-wilson.co.uk

Currently the presumption is that the request construction and its
submission to the GuC are all under the same holding of struct_mutex. We
wish to relax this to separate the request construction and the later
submission to the GuC. This requires us to reserve some space in the
GuC command queue for the future submission. For flexibility to handle
out-of-order request submission we do not preallocate the next slot in
the GuC command queue during request construction, just ensuring that
there is enough space later.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-17-chris@chris-wilson.co.uk

We are about to specialize object synchronisation to enable nonblocking
execbuf submission. First we make a copy of the current object
synchronisation for execbuffer. The general i915_gem_object_sync() will
be removed following the removal of CS flips in the near future.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJohn Harrison <john.c.harrison@intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-16-chris@chris-wilson.co.uk

Let's avoid mixing sealing the hardware commands for the request and
adding the request to the software tracking.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-15-chris@chris-wilson.co.uk

Drive final request submission from a callback from the fence. This way
the request is queued until all dependencies are resolved, at which
point it is handed to the backend for queueing to hardware. At this
point, no dependencies are set on the request, so the callback is
immediate.

A side-effect of imposing a heavier-irqsafe spinlock for execlist
submission is that we lose the softirq enabling after scheduling the
execlists tasklet. To compensate, we manually kickstart the softirq by
disabling and enabling the bh around the fence signaling.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: NJohn Harrison <john.c.harrison@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-14-chris@chris-wilson.co.uk

Update reset path in preparation for engine reset which requires
identification of incomplete requests and associated context and fixing
their state so that engine can resume correctly after reset.

The request that caused the hang will be skipped and head is reset to the
start of breadcrumb. This allows us to resume from where we left-off.
Since this request didn't complete normally we also need to cleanup elsp
queue manually. This is vital if we employ nonblocking request
submission where we may have a web of dependencies upon the hung request
and so advancing the seqno manually is no longer trivial.

ABI: gem_reset_stats / DRM_IOCTL_I915_GET_RESET_STATS

We change the way we count pending batches. Only the active context
involved in the reset is marked as either innocent or guilty, and not
mark the entire world as pending. By inspection this only affects
igt/gem_reset_stats (which assumes implementation details) and not
piglit.

ARB_robustness gives this guide on how we expect the user of this
interface to behave:

 * Provide a mechanism for an OpenGL application to learn about
   graphics resets that affect the context.  When a graphics reset
   occurs, the OpenGL context becomes unusable and the application
   must create a new context to continue operation. Detecting a
   graphics reset happens through an inexpensive query.

And with regards to the actual meaning of the reset values:

   Certain events can result in a reset of the GL context. Such a reset
   causes all context state to be lost. Recovery from such events
   requires recreation of all objects in the affected context. The
   current status of the graphics reset state is returned by

	enum GetGraphicsResetStatusARB();

   The symbolic constant returned indicates if the GL context has been
   in a reset state at any point since the last call to
   GetGraphicsResetStatusARB. NO_ERROR indicates that the GL context
   has not been in a reset state since the last call.
   GUILTY_CONTEXT_RESET_ARB indicates that a reset has been detected
   that is attributable to the current GL context.
   INNOCENT_CONTEXT_RESET_ARB indicates a reset has been detected that
   is not attributable to the current GL context.
   UNKNOWN_CONTEXT_RESET_ARB indicates a detected graphics reset whose
   cause is unknown.

The language here is explicit in that we must mark up the guilty batch,
but is loose enough for us to relax the innocent (i.e. pending)
accounting as only the active batches are involved with the reset.

In the future, we are looking towards single engine resetting (with
minimal locking), where it seems inappropriate to mark the entire world
as innocent since the reset occurred on a different engine. Reducing the
information available means we only have to encounter the pain once, and
also reduces the information leaking from one context to another.

v2: Legacy ringbuffer submission required a reset following hibernation,
or else we restore stale values to the RING_HEAD and walked over
stolen garbage.

v3: GuC requires replaying the requests after a reset.

v4: Restore engine IRQ after reset (so waiters will be woken!)
    Rearm hangcheck if resetting with a waiter.

Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-13-chris@chris-wilson.co.uk

Since we have a cooperative mode now with a direct reset, we can avoid
the contention on struct_mutex and instead try then sleep on the
I915_RESET_IN_PROGRESS bit. If the mutex is held and that bit is
cleared, all is fine. Otherwise, we sleep for a bit and try again. In
the worst case we sleep for an extra second waiting for the mutex to be
released (no one touching the GPU is allowed the struct_mutex whilst the
I915_RESET_IN_PROGRESS bit is set). But when we have a direct reset,
this allows us to clean up the reset worker faster.

v2: Remember to call wake_up_bit() after changing (for the faster wakeup
as promised)
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-12-chris@chris-wilson.co.uk

If a waiter is holding the struct_mutex, then the reset worker cannot
reset the GPU until the waiter returns. We do not want to return -EAGAIN
form i915_wait_request as that breaks delicate operations like
i915_vma_unbind() which often cannot be restarted easily, and returning
-EIO is just as useless (and has in the past proven dangerous). The
remaining WARN_ON(i915_wait_request) serve as a valuable reminder that
handling errors from an indefinite wait are tricky.

We can keep the current semantic that knowing after a reset is complete,
so is the request, by performing the reset ourselves if we hold the
mutex.

uevent emission is still handled by the reset worker, so it may appear
slightly out of order with respect to the actual reset (and concurrent
use of the device).
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-11-chris@chris-wilson.co.uk

In the next patch we want to handle reset directly by a locked waiter in
order to avoid issues with returning before the reset is handled. To
handle the reset, we must first know whether we hold the struct_mutex.
If we do not hold the struct_mtuex we can not perform the reset, but we do
not block the reset worker either (and so we can just continue to wait for
request completion) - otherwise we must relinquish the mutex.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-10-chris@chris-wilson.co.uk