In order to avoid accessing GPU registers while GPU is suspended cancel
the hangcheck work before calling intel_suspend_complete which actually
puts the GPU to suspend. Otherwise hangcheck might do MMIO reads to a
suspended GPU.

Placement before intel_guc_suspend is imitated from i915_drm_suspend
which cancels the work at i915_gem_suspend, to keep the functions
similar.

On VLV systems, namely BYT, this was causing an error during runtime
suspend cycle:

[drm:vlv_check_no_gt_access [i915]] *ERROR* GT register access while GT waking disabled

Testcase: igt/pm_rpm/basic-rte
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93121Signed-off-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1449669373-8588-1-git-send-email-joonas.lahtinen@linux.intel.comReviewed-by: NImre Deak <imre.deak@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NImre Deak <imre.deak@intel.com>

This patch adds support for DP MST audio in i915.

Enable audio codec when DP MST is enabled if has_audio flag is set.
Disable audio codec when DP MST is disabled if has_audio flag is set.

Another separated patches to support DP MST audio will be implemented
in audio driver.
Reviewed-by: NAnder Conselvan de Oliveira <conselvan2@gmail.com>
Signed-off-by: NLibin Yang <libin.yang@linux.intel.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449036584-105393-2-git-send-email-libin.yang@linux.intel.com

This adds code to initialise the SDP streams
for a sink in the simplest ordering.

I've no idea how you'd want to control the
ordering at this level, so don't bother
until someone comes up with a use case.
Reviewed-by: NAnder Conselvan de Oliveira <conselvan2@gmail.com>
Signed-off-by: NLibin Yang <libin.yang@linux.intel.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449036584-105393-1-git-send-email-libin.yang@linux.intel.com

All of these iterator macros require a 'temp' argument, used merely to
hold internal partial results. We can instead declare the temporary
variable inside the macro, so the caller need not provide it.

Some of the old code contained nested iterators that actually reused the
same 'temp' variable for both inner and outer instances. It's quite
surprising that this didn't introduce bugs! But it does show that the
value of 'temp' isn't required to persist during the iterated body.
Signed-off-by: NDave Gordon <david.s.gordon@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449581451-11848-2-git-send-email-david.s.gordon@intel.com

Kabylake A0 is based on Skylake H0.

v2: Don't assume revid+7 and only load the one we are sure about.

v3: Rebase on top of latest changes.

v4: Accept cleaner solution from Jani with kbl_stepping_info
    starting on H0 instead of put a hack on revid.

Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: NJani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449676319-6959-1-git-send-email-rodrigo.vivi@intel.com

We were not checking the return value of drm_encoder_init() which can
fail. And if it fails then we will be working with an uninitialized
encoder.

Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: NSudip Mukherjee <sudip@vectorindia.org>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1444312681-10149-2-git-send-email-sudipm.mukherjee@gmail.com

Userspace can pass in an offset that it presumes the object is located
at. The kernel will then do its utmost to fit the object into that
location. The assumption is that userspace is handling its own object
locations (for example along with full-ppgtt) and that the kernel will
rarely have to make space for the user's requests.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

v2: Fixed incorrect eviction found by Michal Winiarski - fix suggested by Chris
Wilson.  Fixed incorrect error paths causing crash found by Michal Winiarski.
(Not published externally)

v3: Rebased because of trivial conflict in object_bind_to_vm.  Fixed eviction
to allow eviction of soft-pinned objects when another soft-pinned object used
by a subsequent execbuffer overlaps reported by Michal Winiarski.
(Not published externally)

v4: Moved soft-pinned objects to the front of ordered_vmas so that they are
pinned first after an address conflict happens to avoid repeated conflicts in
rare cases (Suggested by Chris Wilson).  Expanded comment on
drm_i915_gem_exec_object2.offset to cover this new API.

v5: Added I915_PARAM_HAS_EXEC_SOFTPIN parameter for detecting this capability
(Kristian). Added check for multiple pinnings on eviction (Akash). Made sure
buffers are not considered misplaced without the user specifying
EXEC_OBJECT_SUPPORTS_48B_ADDRESS.  User must assume responsibility for any
addressing workarounds.  Updated object2.offset field comment again to clarify
NO_RELOC case (Chris).  checkpatch cleanup.

v6: Trivial rebase on latest drm-intel-nightly

v7: Catch attempts to pin above the max virtual address size and return
EINVAL (Tvrtko). Decouple EXEC_OBJECT_SUPPORTS_48B_ADDRESS and
EXEC_OBJECT_PINNED flags, user must pass both flags in any attempt to pin
something at an offset above 4GB (Chris, Daniel Vetter).

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Zou Nanhai <nanhai.zou@intel.com>
Cc: Kristian Høgsberg <hoegsberg@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: NMichel Thierry <michel.thierry@intel.com>
Acked-by: PDT
Signed-off-by: NThomas Daniel <thomas.daniel@intel.com>
Signed-off-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449575707-20933-1-git-send-email-thomas.daniel@intel.com

The intel_dvo_dev_ops structures are never modified, so declare them as
const.

Done with the help of Coccinelle.
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449608127-21715-1-git-send-email-Julia.Lawall@lip6.fr

GuC has no version for KBL published yet and it is not recommended
to load the Skylake one, so let's avoid loading this for now while
we don't have the proper GuC firmware for Kabylake.
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: NAlex Dai <yu.dai@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449622718-21684-1-git-send-email-rodrigo.vivi@intel.com

Let's introduce ULT and ULX Kabylake definitions and start
using it for a propper DDI buffer translation.

v2: Remove extra white space. (Paulo)
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>

As described in the code comment, I couldn't set the minimum RPS
frequency on my BYT-M B0 to the minimum allowed as reported by Punit.
Fix this by clamping the minimum value to the first one that was
accepted on my machine.

Atm this issue doesn't cause any test failures, since in igt/pm_rps we
only check the cached version of the current frequency which is the same
what has been set. In the future we'll add checks for the actual
frequency too, and for that to pass this fix is necessary.
Signed-off-by: NImre Deak <imre.deak@intel.com>
Acked-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1417711175-13271-1-git-send-email-imre.deak@intel.com

Currently we disable some parts of FDI setup after a failed link
training. But despite that we continue with the modeset as if everything
is fine. This results in tons of noise from the state checker, and
it means we're not following the proper modeset sequence for the rest of
crtc enabling, nor for crtc disabling.

Ideally we should abort the modeset and follow the proper disable
sequence to shut off everything we enabled so far, but that would
require a big rework of the modeset code. So instead just leave FDI
up and running in its untrained state, and log an error. This is
what we do on older platforms too.

v2: Fix a typo in the commit message
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449260570-14670-1-git-send-email-ville.syrjala@linux.intel.com

Currently we leave the LPT-H VGA dotclock running after turning
the pipe/fdi/port/etc. Properly disable the VGA dotclock as
specified in the modeset sequence.

v2: Fix commit message typo (Paulo)
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449260534-14551-1-git-send-email-ville.syrjala@linux.intel.com

Extract the LPT-H VGA dotclock disable to a separate function in
anticipation of further use.

While at it move the sb_lock locking inwards when enabling the VGA
dotclock, as it's only needed to protect the sideband accesses.

v2: Keep the PIXCLK_GATE_GATE name for 0 (Paulo)
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449260494-14449-1-git-send-email-ville.syrjala@linux.intel.com

Bspec modeset sequence tells us to disable the PCH transcoder and
FDI after the CRT port on LPT-H, so let's do that. And the CRT port
should be disabled after the pipe, as we do on other PCH platforms
too since
commit 1ea56e26 ("drm/i915: Disable CRT port after pipe on PCH platforms")

commit 00490c22 ("drm/i915: Consider SPLL as another shared pll, v2.")
moved the SPLL disable from the .post_disable() hook to some upper
level code, so we can just move the CRT port disabling into the
.post_disable() hook. If we still had the non-shared SPLL, it would have
needed to be moved into the .post_pll_disable() hook.

v2: Actually move the CRT port disable to the .post_disable() hook,
    and amend the commit message with more details (Paulo)
v3: Fix typos in commit message (Paulo)

Cc: Paulo Zanoni <przanoni@gmail.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449583548-11896-1-git-send-email-ville.syrjala@linux.intel.com

Bspec says we should round to closest when computing the LPT-H VGA
dotclock, so let's do that.

v2: Fix typo in commit message (Paulo)
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449260421-14243-1-git-send-email-ville.syrjala@linux.intel.com

When we want to use SPLL for FDI we want SSC, which means we have to
disable clock bending for the PCH SSC reference (bend and spread are
mutually exclusive). So let's turn off bending when we want spread.
In case the BIOS enabled clock bending for some reason we'll just turn
it off and enable the spread mode instead.

Not sure what happens if the BIOS is actually using the bend source for
HDMI at this time, but I suppose it should be no worse than what already
happens when we simply turn on the spread.

We don't currently use the bend source for anything, and only use the
PCH SSC reference for the SPLL to drive FDI (always with spread).

v2: Fix the %5 vs %10 fumble for SSCDITHPHASE (Paulo)
    Add 'WARN_ON(steps % 5 != 0)' sanity check (Paulo)
    Fix typos in commit message (Paulo)

Cc: Paulo Zanoni <przanoni@gmail.com>
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449260379-14093-1-git-send-email-ville.syrjala@linux.intel.comReviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>

WaRsDoubleRc6WrlWithCoarsePowerGating should
be enabled for all Skylakes. Make it so.

Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: NMika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: NSagar Arun Kamble <sagar.a.kamble@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449505785-20812-2-git-send-email-mika.kuoppala@intel.comSigned-off-by: NJani Nikula <jani.nikula@intel.com>

There is conflicting info between E0 and F0 steppings
for this workarounds. Trust more authoritative source and
be conservative and extend also for F0.

This prevents numerous (>50) gpu hangs with SKL GT4e
during piglit run.

References: HSD: gen9lp/2134184
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: NMika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: NSagar Arun Kamble <sagar.a.kamble@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449505785-20812-1-git-send-email-mika.kuoppala@intel.comSigned-off-by: NJani Nikula <jani.nikula@intel.com>

'commit 97173eaf ("drm/i915: PSR: Increase idle_frames")' was a mistake.
The special case it tried to cover was already being covered by
the DP_PSR_NO_TRAIN_ON_EXIT. So this ended up duplicated.

So, instead of reverting that let's take this opportunity and unify
the idle_frame definition in a single place so we standardize the access
and avoid room for that same mistake again.

Few changes with this patch:

1. Instead of just respecting the VBT we set a
global minumum with max(). So we are sure that we will avoid corner cases
in case VBT is doing something we don't understand.

2. Instead of minimum 5 we use 6. When introducing the idle_frames += 4 case
we considered that minimum was 2. All because the off-by-one issue.

v2: Unified idle_frame definition.

Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449528320-27655-1-git-send-email-rodrigo.vivi@intel.com

wait_vblank is already set in intel_plane_atomic_calc_changes
for broadwell, waiting for a double vblank is overkill.
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1447945645-32005-5-git-send-email-maarten.lankhorst@linux.intel.com

On skylake some of the registers are only writable when the correct
power wells are enabled. Because of this watermarks have to be updated
before the crtc turns off, or you get unclaimed register read and write
warnings.

This patch needs to be modified slightly to apply to -fixes.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=92181Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: stable@vger.kernel.org
Cc: Matt Roper <matthew.d.roper@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1447945645-32005-4-git-send-email-maarten.lankhorst@linux.intel.comReviewed-by: NAnder Conselvan de Oliveira <conselvan2@gmail.com>

This removes pre/post_wm_update from intel_crtc->atomic, and
creates atomic state for it in intel_crtc.

Changes since v1:
- Rebase on top of wm changes.
Changes since v2:
- Split disable_cxsr into a separate patch.
Changes since v3:
- Move some of the changes to intel_wm_need_update.
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/56603A49.5000507@linux.intel.comReviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

intel_crtc->atomic will be removed later on, move this member
to intel_crtc_state.
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1447945645-32005-2-git-send-email-maarten.lankhorst@linux.intel.comReviewed-by: NAnder Conselvan de Oliveira <conselvan2@gmail.com>

i915: Replace "hweight8(dev_priv->info.subslice_7eu[i]) != 1" with "!is_power_of_2(dev_priv->info.subslice_7eu[i])"
Signed-off-by: NZeng Zhaoxiu <zhaoxiu.zeng@gmail.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449397590-14292-1-git-send-email-zhaoxiu.zeng@gmail.com

Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

Add Skylake Intel Graphics GT4 PCI IDs

v2: Rebase
Signed-off-by: NMika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: NDamien Lespiau <damien.lespiau@intel.com>
Signed-off-by: NDamien Lespiau <damien.lespiau@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1446811876-303-1-git-send-email-mika.kuoppala@intel.com

This reverts commit 6d65ba94.

Mika Kuoppala traced down a use-after-free crash in module unload to
this commit, because ring->last_context is leaked beyond when the
context gets destroyed. Mika submitted a quick fix to patch that up in
the context destruction code, but that's too much of a hack.

The right fix is instead for the ring to hold a full reference onto
it's last context, like we do for legacy contexts.

Since this is causing a regression in BAT it gets reverted before we
can close this.

Cc: Nick Hoath <nicholas.hoath@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Gordon <david.s.gordon@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Alex Dai <yu.dai@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93248Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@intel.com>

The reference clock for BXT is 19.2 MHz not 19.5 MHz, updating the
correct value here.
Signed-off-by: NDeepak M <m.deepak@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449238659-12473-2-git-send-email-m.deepak@intel.com

This was broken in

commit 6a8beeff
Author: Wayne Boyer <wayne.boyer@intel.com>
Date:   Wed Dec 2 13:28:14 2015 -0800

    drm/i915: Clean up device info structure definitions

and I didn't spot this while reviewing. We really need that CI farm up
asap!
Reported-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Wayne Boyer <wayne.boyer@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@intel.com>

In commit 2e1b8730 [v4.2]
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Mon Apr 27 13:41:22 2015 +0100

    drm/i915: Convert RPS tracking to a intel_rps_client struct

we converted the __i915_wait_request() to take a new intel_rps_client
struct (rather than having to pass fake drm_i915_file_private structs).
However, due to use of passing a void pointer, I didn't spot one
callsite in wait-ioctl was passing the wrong pointer.

Fwiw, the impact of this bug is zero. Along the rps path, we always
first call list_empty(rps) which when we pass in the wrong pointer
always evaluates to false and we return early and never chase the
invalid pointers.

The user visible impact is then wait-ioctl doesn't get the same
waitboosting as the other interfaces (set-domain, throttle), which is a
performance concern for the *very* few users of the wait interface.
There is also a libdrm_intel patch to use the wait-ioctl for
drm_intel_bo_wait_rendering() if anyone feels inclined to review
libdrm_intel patches.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
[danvet: Add Chris' explanation for why the impact of this is pretty
close to 0.]
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This reverts commit 89f41f4f.

It's possible that ->crtc is NULL in here. Noticed by Ville.
Signed-off-by: NDaniel Vetter <daniel.vetter@intel.com>

Beginning with gen7, newer devices repetitively redefine values
for the device info structure members.  This patch simplifies the
structure definitions by grouping member value definitions into the
existing GEN7_FEATURES #define and into the new GEN7_LP_FEATURES
and HSW_FEATURES #defines.

Specifically, GEN_DEFAULT_PIPEOFFSETS and IVB_CURSOR_OFFSETS are
added to GEN7_FEATURES and subsequent IVB definitions are simplified.

VLV_FEATURES is defined to differentiate and simplify the
gen7 low power (LP) devices.

HSW_FEATURES is defined and used to simplify all HSW+ devices
except for LP.

v2: Use VLV_FEATURES for the gen7 low power devices. (Jani)

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: NWayne Boyer <wayne.boyer@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449091694-7681-1-git-send-email-wayne.boyer@intel.com

to_intel_crtc() always returns a non-NULL pointer.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1448986198-3488-2-git-send-email-tiwai@suse.de

As the comment indicates this can only fail gracefully when
called from compute_config. Fortunately this is now what's happening,
so the fixme can be removed and the DRM_ERROR downgraded.

Link: http://patchwork.freedesktop.org/patch/msgid/1448360945-5723-3-git-send-email-maarten.lankhorst@linux.intel.comSigned-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>

In intel_prepare_plane_fb, if fb is backed by dma-buf, wait for exclusive
fence

v2: First commit
v3: Remove object_name_lock acquire
    Move wait from intel_atomic_commit() to intel_prepare_plane_fb()
v4: Wait only on exclusive fences, interruptible with no timeout
v5: Style tweaks to more closely match rest of file
v6: Properly handle interrupted waits
v7: No change
v8: No change

Link: https://patchwork.kernel.org/patch/7704181/Signed-off-by: NAlex Goins <agoins@nvidia.com>
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>

If a buffer is backed by dmabuf, wait on its reservation object's exclusive
fence before flipping.

v2: First commit
v3: Remove object_name_lock acquire
v4: Move wait ahead of mark_page_flip_active
    Use crtc->primary->fb to get GEM object instead of pending_flip_obj
    use_mmio_flip() return true when exclusive fence is attached
    Wait only on exclusive fences, interruptible with no timeout
v5: Move wait from do_mmio_flip to mmio_flip_work_func
    Style tweaks to more closely match rest of file
v6: Change back to unintteruptible wait to match __i915_wait_request due to
    inability to properly handle interrupted wait.
    Warn on error code from waiting.
v7: No change
v8: Test for !reservation_object_signaled_rcu(test_all=FALSE) instead of
    obj->base.dma_buf->resv->fence_excl

Link: https://patchwork.kernel.org/patch/7704181/Signed-off-by: NAlex Goins <agoins@nvidia.com>
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>

Use the first retired request on a new context to unpin
the old context. This ensures that the hw context remains
bound until it has been written back to by the GPU.
Now that the context is pinned until later in the request/context
lifecycle, it no longer needs to be pinned from context_queue to
retire_requests.
This fixes an issue with GuC submission where the GPU might not
have finished writing back the context before it is unpinned. This
results in a GPU hang.

v2: Moved the new pin to cover GuC submission (Alex Dai)
    Moved the new unpin to request_retire to fix coverage leak
v3: Added switch to default context if freeing a still pinned
    context just in case the hw was actually still using it
v4: Unwrapped context unpin to allow calling without a request
v5: Only create a switch to idle context if the ring doesn't
    already have a request pending on it (Alex Dai)
    Rename unsaved to dirty to avoid double negatives (Dave Gordon)
    Changed _no_req postfix to __ prefix for consistency (Dave Gordon)
    Split out per engine cleanup from context_free as it
    was getting unwieldy
    Corrected locking (Dave Gordon)
v6: Removed some bikeshedding (Mika Kuoppala)
    Added explanation of the GuC hang that this fixes (Daniel Vetter)
v7: Removed extra per request pinning from ring reset code (Alex Dai)
    Added forced ring unpin/clean in error case in context free (Alex Dai)
Signed-off-by: NNick Hoath <nicholas.hoath@intel.com>
Issue: VIZ-4277
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Gordon <david.s.gordon@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Alex Dai <yu.dai@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NAlex Dai <yu.dai@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

For now, remove the spinlocks that protected the GuC's
statistics block and work queue; they are only accessed
by code that already holds the global struct_mutex, and
so are redundant (until the big struct_mutex rewrite!).

The specific problem that the spinlocks caused was that
if the work queue was full, the driver would try to
spinwait for one jiffy, but with interrupts disabled the
jiffy count would not advance, leading to a system hang.
The issue was found using test case igt/gem_close_race.

The new version will usleep() instead, still holding
the struct_mutex but without any spinlocks.

v4: Reorganize commit message (Dave Gordon)
v3: Remove unnecessary whitespace churn
v2: Clean up wq_lock too
v1: Clean up host2guc lock as well
Signed-off-by: NAlex Dai <yu.dai@intel.com>
Reviewed-by: NDave Gordon <david.s.gordon@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1449104189-27591-1-git-send-email-yu.dai@intel.comSigned-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

There's no need to stop and restart FBC, which is quite expensive as
we have to revalidate the CRTC state. After flushing a drawing
operation we know the CRTC state hasn't changed, so a nuke
(recompress) should be fine.

v2: Make it simpler (Chris).
v3: Rewrite the patch again due to patch order changes.
v4: Rewrite commit message (Chris).
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/