Keep the intel_context as being the primary state for i915_request, with
the GEM context a backpointer from the low level state for the rarer
cases we need client information. Our goal is to remove such references
to clients from the backend, and leave the HW submission agnostic to
client interfaces and self-contained.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-1-chris@chris-wilson.co.uk

Since we added the context_alloc callback to intel_context_ops, we can
safely install a custom hook for the deferred virtual context allocation.
This means that all new contexts behave the same upon creation,
simplifying later code.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191219232932.189197-1-chris@chris-wilson.co.uk

Avoid adding the retire workers to the virtual engine so that we don't
end up in the unenviable situation of trying to free the virtual engine
while its worker remains active.

Fixes: dc93c9b6 ("drm/i915/gt: Schedule request retirement when signaler idles")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/867Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191219221344.161523-1-chris@chris-wilson.co.uk

When we park RPS, we set the GPU to run at minimum 'idle' frequency.
However, as the GPU is idle, we also disable the worker and RPS
interrupts - changing the RPS thresholds has no effect, it just incurs
extra changes to restore them when we unpark. So on parking, leave the
thresholds set to the current power level and so we expect them to be
valid for our restart.

References: https://gitlab.freedesktop.org/drm/intel/issues/848Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191218210545.3975426-2-chris@chris-wilson.co.uk

Use non-forcewaked writes to queue RPS register changes that will take
effect when the write buffer is flushed, rather than wake the mmio
device for immediate effect. This is so that we can avoid a slow
forcewake dance upon unparking, and at our irregular updates.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191218210545.3975426-1-chris@chris-wilson.co.uk

Knowing the round trip time of an engine is useful for tracking the
health of the system as well as providing a metric for the baseline
responsiveness of the engine. We can use the latter metric for
automatically tuning our waits in selftests and when idling so we don't
confuse a slower system with a dead one.

Upon idling the engine, we send one last pulse to switch the context
away from precious user state to the volatile kernel context. We know
the engine is idle at this point, and the pulse is non-preemptible, so
this provides us with a good measurement of the round trip time. It also
provides us with faster engine parking for ringbuffer submission, which
is a welcome bonus (e.g. softer-rc6).
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191219105043.4169050-1-chris@chris-wilson.co.uk
Link: https://patchwork.freedesktop.org/patch/msgid/20191219124353.8607-2-chris@chris-wilson.co.uk

Very similar to commit 4f88f874 ("drm/i915/gt: Schedule request
retirement when timeline idles"), but this time instead of coupling into
the execlists CS event interrupt, we couple into the breadcrumb
interrupt and queue a timeline's retirement when the last signaler is
completed. This should allow us to more rapidly park ringbuffer
submission, and so help reduce power consumption on older systems.

v2: Fixup intel_engine_add_retire() to handle concurrent callers

References: 4f88f874 ("drm/i915/gt: Schedule request retirement when timeline idles")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191219124353.8607-1-chris@chris-wilson.co.uk

Only signal the breadcrumbs from inside the irq_work, simplifying our
interface and calling conventions. The micro-optimisation here is that
by always using the irq_work interface, we know we are always inside an
irq-off critical section for the breadcrumb signaling and can ellide
save/restore of the irq flags.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217095642.3124521-7-chris@chris-wilson.co.uk

For very light workloads that frequently park, acquiring the display
power well (required to prevent the dmc from trashing the system) takes
longer than the execution. A good example is the igt_coherency selftest,
which is slowed down by an order of magnitude in the worst case with
powerwell cycling. To prevent frequent cycling, while keeping our fast
soft-rc6, use a timer to delay release of the display powerwell.

Fixes: 31177017 ("drm/i915/gt: Schedule request retirement when timeline idles")
References: https://gitlab.freedesktop.org/drm/intel/issues/848Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191218093504.3477048-1-chris@chris-wilson.co.uk

The Gen11+ and the legacy function differ in the register and value
written to interrupt the GuC. However, while on older gen the value
matches a bit on the register, on Gen11+ the value is a SW defined
payload that is sent to the FW. Since the FW behaves the same no matter
what value we pass to it, we can just write the same thing on all gens
and get rid of the function pointer by saving the register offset.
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217012316.13271-6-daniele.ceraolospurio@intel.com

Since we started using CT buffers on all gens, the function pointers can
only be set to either the _nop() or the _ct() functions. Since the
_nop() case applies to when the CT are disabled, we can just handle that
case in the _ct() functions and call them directly.

v2: keep intel_guc_send() and make the CT send/receive functions work on
    intel_guc_ct. (Michal)
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217012316.13271-5-daniele.ceraolospurio@intel.com

For better isolation of the request tracking from the rest of the
CT-related data.

v2: split to separate patch, move next_fence to substructure (Michal)
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217012316.13271-4-daniele.ceraolospurio@intel.com

The GuC supports having multiple CT buffer pairs and we designed our
implementation with that in mind. However, the different channels are not
processed in parallel within the GuC, so there is very little advantage
in having multiple channels (independent locks?), compared to the
drawbacks (one channel can starve the other if messages keep being
submitted to it). Given this, it is unlikely we'll ever add a second
channel and therefore we can simplify our code by removing the
flexibility.

v2: split substructure grouping to separate patch, improve docs (Michal)
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217012316.13271-3-daniele.ceraolospurio@intel.com

We track the status of the GuC much more closely now and we expect the
enable/disable functions to be correctly called only once. If this isn't
true we do want to flag it as a flow failure (via the BUG_ON in the ctch
functions) and not silently ignore the call.
Suggested-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217012316.13271-2-daniele.ceraolospurio@intel.com

The only difference from the GuC POV between guc_communication_stop and
guc_communication_disable is that the former can be called after GuC
has been reset. Instead of having two separate paths, we can just skip
the call into GuC in the disabling path and re-use that.

Note that by using the disable() path instead of the stop() one there
are two additional changes in SW side for the stop path:

- interrupts are now disabled before disabling the CT, which is ok
  because we do not want interrupts with CT disabled;
- guc_get_mmio_msg() is called in the stop case as well, which is ok
  because if there are errors before the reset we do want to record
  them.
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217012316.13271-1-daniele.ceraolospurio@intel.com

As we stash a pointer to the HWSP cacheline on the request, when reading
it we only need confirm that the cacheline is still valid by checking
that the request and timeline are still intact.

v2: Protect hwsp_cachline with RCU
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217011659.3092130-1-chris@chris-wilson.co.uk

Sandybridge is the gen that didn't handle multiple registers in a single
LRI packet. Don't forget it!

Fixes: 902eb748 ("drm/i915/gt: Tidy up full-ppgtt on Ivybridge")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Tested-by: NTomi Sarvela <tomi.p.sarvela@intel.com>
Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217091328.3093551-1-chris@chris-wilson.co.uk

With a couple more memory barriers dotted around the place we can
significantly reduce the MTBF on Ivybridge. Still doesn't really help
Haswell though.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191216142409.2605211-1-chris@chris-wilson.co.uk

typecheck() macro creates an huge stack size causing
issues with static analysis with coverity, addressing
this with creating a local pointer.

Fixes: 639f2f24 ("drm/i915: Introduce new macros for tracing")
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: NVenkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191216185332.83289-1-venkata.s.dhanalakota@intel.com

Add two helpers that for reading the actual GT's frequency. The
two helpers are:

 - intel_rps_read_cagf: reads the frequency and returns it not
   normalized

 - intel_rps_read_actual_frequency: provides the frequency in Hz.

Use the above helpers in sysfs and debugfs.
Signed-off-by: NAndi Shyti <andi.shyti@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191213183736.31992-2-andi@etezian.org

While not good behaviour, it is, however, established behaviour that we
can punt EAGAIN to userspace if we need to retry the ioctl. When trying
to acquire a mutex, prefer to use EAGAIN to propagate losing the race
so that if it does end up back in userspace, we try again.

Fixes: c81471f5 ("drm/i915: Copy across scheduler behaviour flags across submit fences")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/800Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191213160347.1789004-1-chris@chris-wilson.co.uk

New macros ENGINE_TRACE(), CE_TRACE(), RQ_TRACE() and
GT_TRACE() are introduce to tag device name and engine
name with contexts and requests tracing in i915.

Cc: Sudeep Dutt <sudeep.dutt@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: NVenkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191213155152.69182-2-venkata.s.dhanalakota@intel.com

drivers/gpu/drm/i915/gt/intel_rps.c:1726:24: error: incompatible types in comparison expression (different address spaces):
drivers/gpu/drm/i915/gt/intel_rps.c:1726:24:    struct drm_i915_private [noderef] <asn:4> *
drivers/gpu/drm/i915/gt/intel_rps.c:1726:24:    struct drm_i915_private *
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NVenkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191212140459.1307617-7-chris@chris-wilson.co.uk

The gen7 cmdparser is primarily a promotion-based system to allow access
to additional registers beyond the HW validation, and allows fallback to
normal execution of the user batch buffer if valid and requires
chaining. In the next patch, we will do the cmdparser validation in the
pipeline asynchronously and so at the point of request construction we
will not know if we want to execute the privileged and validated batch,
or the original user batch. The solution employed here is to execute
both batches, one with raised privileges and one as normal. This is
because the gen7 MI_BATCH_BUFFER_START command cannot change privilege
level within a batch and must strictly use the current privilege level
(or undefined behaviour kills the GPU). So in order to execute the
original batch, we need a second non-priviledged batch buffer chain from
the ring, i.e. we need to emit two batches for each user batch. Inside
the two batches we determine which one should actually execute, we
provide a conditional trampoline to call the original batch.

Implementation-wise, we create a single buffer and write the shadow and
the trampoline inside it at different offsets; and bind the buffer into
both the kernel GGTT for the privileged execution of the shadow and into
the user ppGTT for the non-privileged execution of the trampoline and
original batch. One buffer, two batches and two vma.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191211230858.599030-1-chris@chris-wilson.co.uk

An oversight in that we use rc6->ctl_enable to disable rc6 on gen9 and
so it does not simply indicate indirect control via a PCU. Switch the
rc6->ctl_enable check for a platform-based check.

Fixes: 972745fd ("drm/i915/gt: Disable manual rc6 for Braswell/Baytrail")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Acked-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191212072737.884335-2-chris@chris-wilson.co.uk

Declutter the calling interface by reducing the parameters to the
i915_vma and associated offsets.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191211110437.4082687-2-chris@chris-wilson.co.uk

The initial investigated showed that while the PCU on Braswell/Baytrail
controlled RC6 itself. setting the software RC6 request made no
difference. Further testing reveals though that it causes a delay in the
PCU on enabling RC6.

Closes: https://gitlab.freedesktop.org/drm/intel/issues/763
Fixes: 730eaeb5 ("drm/i915/gt: Manual rc6 entry upon parking")
Testcase: igt/perf/rc6-disable
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Acked-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191210180111.3958558-1-chris@chris-wilson.co.uk

There is no need to pass explicit ggtt since we already have
a trick to get parent gt from uc_fw, we only need to use it.
Signed-off-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191211124549.59516-4-michal.wajdeczko@intel.com

There is no need to pass explicit gt since we already have
a trick to get parent gt from uc_fw, we only need to use it.
Signed-off-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191211124549.59516-3-michal.wajdeczko@intel.com

There is no need to pass explicit i915 since we already have
a debug trick to get parent gt from uc_fw, we only need to
make this trick available on non-debug builds.
Signed-off-by: NMichal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191211124549.59516-2-michal.wajdeczko@intel.com

Check that we own the global pointer before deregistering.
Reported-by: NVenkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: NVenkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191210153620.3929372-1-chris@chris-wilson.co.uk

Currently the variable sum is not uninitialized and hence will cause an
incorrect result in the summation values.  Fix this by initializing
sum to the first item in the summation.

Addresses-Coverity: ("Uninitialized scalar variable")
Fixes: 3c7a44bb ("drm/i915/selftests: Perform some basic cycle counting of MI ops")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191210143205.338308-1-colin.king@canonical.com

In order to avoid confusing the HW, we must never submit an empty ring
during lite-restore, that is we should always advance the RING_TAIL
before submitting to stay ahead of the RING_HEAD.

Normally this is prevented by keeping a couple of spare NOPs in the
request->wa_tail so that on resubmission we can advance the tail. This
relies on the request only being resubmitted once, which is the normal
condition as it is seen once for ELSP[1] and then later in ELSP[0]. On
preemption, the requests are unwound and the tail reset back to the
normal end point (as we know the request is incomplete and therefore its
RING_HEAD is even earlier).

However, if this w/a should fail we would try and resubmit the request
with the RING_TAIL already set to the location of this request's wa_tail
potentially causing a GPU hang. We can spot when we do try and
incorrectly resubmit without advancing the RING_TAIL and spare any
embarrassment by forcing the context restore.

In the case of preempt-to-busy, we leave the requests running on the HW
while we unwind. As the ring is still live, we cannot rewind our
rq->tail without forcing a reload so leave it set to rq->wa_tail and
only force a reload if we resubmit after a lite-restore. (Normally, the
forced reload will be a part of the preemption event.)

Fixes: 22b7a426 ("drm/i915/execlists: Preempt-to-busy")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/673Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: stable@kernel.vger.org
Link: https://patchwork.freedesktop.org/patch/msgid/20191209023215.3519970-1-chris@chris-wilson.co.uk

We now only use 1 client without any plan to add more. The client is
also only holding information about the WQ and the process desc, so we
can just move those in the intel_guc structure and always use stage_id
0.

v2: fix comment (John)
v3: fix the comment for real, fix kerneldoc
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NJohn Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191205220243.27403-4-daniele.ceraolospurio@intel.com

Instead of relying on the workqueue, the upcoming reworked GuC
submission flow will offer the host driver indipendent control over
the execution status of each context submitted to GuC. As part of this,
the doorbell usage model has been reworked, with each doorbell being
paired to a single lrc and a doorbell ring representing new work
available for that specific context. This mechanism, however, limits
the number of contexts that can be registered with GuC to the number of
doorbells, which is an undesired limitation. To avoid this limitation,
we requested the GuC team to also provide a H2G that will allow the host
to notify the GuC of work available for a specified lrc, so we can use
that mechanism instead of relying on the doorbells. We can therefore drop
the doorbell code we currently have, also given the fact that in the
unlikely case we'd want to switch back to using doorbells we'd have to
heavily rework it.
The workqueue will still have a use in the new interface to pass special
commands, so that code has been retained for now.

With the doorbells gone and the GuC client becoming even simpler, the
existing GuC selftests don't give us any meaningful coverage so we can
remove them as well. Some selftests might come with the new code, but
they will look different from what we have now so if doesn't seem worth
it to keep the file around in the meantime.

v2: fix comments and commit message (John)
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NJohn Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191205220243.27403-3-daniele.ceraolospurio@intel.com

We already have a couple of use-cases in the code and another one will
come in one of the later patches in the series.

v2: use the new function for the CT object as well
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> #v1
Reviewed-by: NJohn Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191205220243.27403-2-daniele.ceraolospurio@intel.com

Remove unused enums and ctx_save_restore_disabled() function, leftover
from the legacy preemption removal.
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191205220243.27403-1-daniele.ceraolospurio@intel.com

"Have you tried switching it off and on again?"

Set the size of the mm to 0 to disable all PD cachelines, before
enabling the whole mm again. Let's see if that tricks the TLB into
reloading.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191208143648.2986669-1-chris@chris-wilson.co.uk

The preferred way to access the uncore is through the GT structure.
Update the GuC function, flush_ggtt_writes, to use this path.
Signed-off-by: NMatthew Brost <matthew.brost@intel.com>
Signed-off-by: NJohn Harrison <john.c.harrison@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191207010033.24667-1-John.C.Harrison@Intel.com

Get rid of the last remaining I915_WRITEs and replace them with
intel_uncore_write().
Signed-off-by: NAndi Shyti <andi.shyti@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191206212417.20178-1-andi@etezian.org