Originally, I did not expect having to rewind a context upon
timeslicing: the point was to replace the executing context with a
non-executing one! However, given a second context that depends on
requests from the first, we may have to split the requests along the
first context to execute the second, causing us to partially replay the
first context and so have to rewind its RING_TAIL.

References: 5ba32c7b ("drm/i915/execlists: Always force a context reload when rewinding RING_TAIL")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200213140150.3639027-1-chris@chris-wilson.co.uk

Apply vast quantities of poison and not tell anyone to see if we fall
for the trap of using a stale RING_HEAD.

References: 42827350 ("drm/i915/gt: Avoid resetting ring->head outside of its timeline mutex")
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>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200211205615.1190127-2-chris@chris-wilson.co.uk

Currently on execlists, we use a local hwsp for the kernel_context,
rather than the engine's HWSP, as this is the default for execlists.
However, seqno wrap requires allocating a new HWSP cacheline, and may
require pinning a new HWSP page in the GGTT. This operation requiring
pinning in the GGTT is not allowed within the kernel_context timeline,
as doing so may require re-entering the kernel_context in order to evict
from the GGTT. As we want to avoid requiring a new HWSP for the
kernel_context, we can use the permanently pinned engine's HWSP instead.
However to do so we must prevent the use of semaphores reading the
kernel_context's HWSP, as the use of semaphores do not support rollover
onto the same cacheline. Fortunately, the kernel_context is mostly
isolated, so unlikely to give benefit to semaphores.
Reported-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200210205722.794180-5-chris@chris-wilson.co.uk

We can not require that the system process a tasklet in reasonable time
(thanks be to ksoftirqd), but we can insist that having waited
sufficiently for the error interrupt to have been raised and having
kicked the tasklet, the reset has begun and the request will be marked
as in error (if not already completed).
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200210205722.794180-3-chris@chris-wilson.co.uk

We manipulate ring->head while active in i915_request_retire underneath
the timeline manipulation. We cannot rely on a stable ring->head outside
of the timeline->mutex, in particular while setting up the context for
resume and reset.

Closes: https://gitlab.freedesktop.org/drm/intel/issues/1126
Fixes: 08819549 ("drm/i915: Introduce intel_context.pin_mutex for pin management")
Fixes: e5dadff4 ("drm/i915: Protect request retirement with timeline->mutex")
References: f3c0efc9 ("drm/i915/execlists: Leave resetting ring to intel_ring")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NAndi Shyti <andi.shyti@intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200211120131.958949-1-chris@chris-wilson.co.uk

live_preempt_hang's use of hang injection has been superseded by
live_preempt_reset's use of an non-preemptible spinner. The latter does
not require intrusive hacks into the code.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200209230838.361154-2-chris@chris-wilson.co.uk

If the heartbeat fires in the middle of the preempt-hang test, it
consumes our forced hang disrupting the test.
Reported-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200131130319.2998318-1-chris@chris-wilson.co.uk

Since PIN_GLOBAL is no longer guaranteed to be synchronous, we must not
forget to include a wait-for-vma prior to execution.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200131142610.3100998-1-chris@chris-wilson.co.uk

Now that we have offline error capture and can reset an engine from
inside an atomic context while also preserving the GPU state for
post-mortem analysis, it is time to handle error interrupts thrown by
the command parser.

This provides a much, much faster mechanism for us to detect known
problems than using heartbeats/hangchecks, and also provides a mechanism
for when those are disabled. However, it is limited to problems the HW
can detect in the CS and so not a complete solution for detecting lockups.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200128204318.4182039-2-chris@chris-wilson.co.uk

If we encounter a hang on a virtual engine, as we process the hang the
request may already have been moved back to the virtual engine (we are
processing the hang on the physical engine). We need to reclaim the
request from the virtual engine so that the locking is consistent and
local to the real engine on which we will hold the request for error
state capturing.

v2: Pull the reclamation into execlists_hold() and assert that cannot be
called from outside of the reset (i.e. with the tasklet disabled).
v3: Added selftest
v4: Drop the reference owned by the virtual engine

Fixes: 74831738 ("drm/i915/execlists: Offline error capture")
Testcase: igt/gem_exec_balancer/hang
Signed-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>
Link: https://patchwork.freedesktop.org/patch/msgid/20200122140243.495621-2-chris@chris-wilson.co.uk

Thanks to preempt-to-busy, we leave the request on the HW as we submit
the preemption request. This means that the request may complete at any
moment as we process HW events, and in particular the request may be
retired as we are planning to capture it for a preemption timeout.

Be more careful while obtaining the request to capture after a
preemption timeout, and check to see if it completed before we were able
to put it on the on-hold list. If we do see it did complete just before
we capture the request, proclaim the preemption-timeout a false positive
and pardon the reset as we should hit an arbitration point momentarily
and so be able to process the preemption.

Note that even after we move the request to be on hold it may be retired
(as the reset to stop the HW comes after), so we do require to hold our
own reference as we work on the request for capture (and all of the
peeking at state within the request needs to be carefully protected).

Fixes: 32ff621f ("drm/i915/gt: Allow temporary suspension of inflight requests")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/997Signed-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/20200122140243.495621-1-chris@chris-wilson.co.uk

In order to support out-of-line error capture, we need to remove the
active request from HW and put it to one side while a worker compresses
and stores all the details associated with that request. (As that
compression may take an arbitrary user-controlled amount of time, we
want to let the engine continue running on other workloads while the
hanging request is dumped.) Not only do we need to remove the active
request, but we also have to remove its context and all requests that
were dependent on it (both in flight, queued and future submission).

Finally once the capture is complete, we need to be able to resubmit the
request and its dependents and allow them to execute.

v2: Replace stack recursion with a simple list.
v3: Check all the parents, not just the first, when searching for a
stuck ancestor!

References: https://gitlab.freedesktop.org/drm/intel/issues/738Signed-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/20200116184754.2860848-2-chris@chris-wilson.co.uk

As we already have a flags field buried within i915_request, reuse it!
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200106114234.2529613-3-chris@chris-wilson.co.uk

Avoid spinning indefinitely waiting for the request to be submitted, and
instead apply a timeout. A secondary benefit is that the error message
will show which suspect is blocked.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200106114234.2529613-2-chris@chris-wilson.co.uk

When creating the initial LRC image, we also want to clear the MI_NOOPs
and register values. Rather than use a blanket memset beforehand, apply
the clears inline, close the context image and force inhibition of the
uninitialised reminder.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200102131707.1463945-2-chris@chris-wilson.co.uk

Empirically the minimal context image we use for rcs is insufficient to
state the engine. This is demonstrated if we poison the context image
such that any uninitialised state is invalid, and so if the engine
samples beyond our defined region, will fail to start.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200102131707.1463945-1-chris@chris-wilson.co.uk

Allocate only an internal intel_context for the kernel_context, forgoing
a global GEM context for internal use as we only require a separate
address space (for our own protection).

Now having weaned GT from requiring ce->gem_context, we can stop
referencing it entirely. This also means we no longer have to create random
and unnecessary GEM contexts for internal use.

GEM contexts are now entirely for tracking GEM clients, and intel_context
the execution environment on the GPU.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Acked-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk

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

As the engine->kernel_context is used within the engine-pm barrier, we
have to be careful when emitting requests outside of the barrier, as the
strict timeline locking rules do not apply. Instead, we must ensure the
engine_park() cannot be entered as we build the request, which is
simplest by taking an explicit engine-pm wakeref around the request
construction.
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/20191125105858.1718307-1-chris@chris-wilson.co.uk

Bonded request submission is designed to allow requests to execute in
parallel as laid out by the user. If the master request is already
finished before its bonded pair is submitted, the pair were not destined
to run in parallel and we lose the information about the master engine
to dictate selection of the secondary. If the second request was
required to be run on a particular engine in a virtual set, that should
have been specified, rather than left to the whims of a random
unconnected requests!

In the selftest, I made the mistake of not ensuring the master would
overlap with its bonded pairs, meaning that it could indeed complete
before we submitted the bonds. Those bonds were then free to select any
available engine in their virtual set, and not the one expected by the
test.
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/20191122112152.660743-1-chris@chris-wilson.co.uk

Whenever we wait on a request, make sure we actually hold a reference to
it and that it cannot be retired/freed on another CPU!
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191121071044.97798-4-chris@chris-wilson.co.uk

Verify that we can execute a long chain of dependent requests from
userspace, each one slightly more important than the last.
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/20191114225736.616885-4-chris@chris-wilson.co.uk

Check that the context's ring register state still matches our
expectations prior to execution.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191102125739.24626-1-chris@chris-wilson.co.uk

An interesting observation made with our parallel selftests was that on
our small/single cpu systems we would call kthread_stop() before the
kthreads were spawned. If this happens, the kthread is never run at all;
completely bypassing the test.

A simple yield() from the parent will ensure that all children have the
opportunity to start before we reap them.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: NMatthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191101084940.31838-1-chris@chris-wilson.co.uk

Execlists uses a scheduling quantum (a timeslice) to alternate execution
between ready-to-run contexts of equal priority. This ensures that all
users (though only if they of equal importance) have the opportunity to
run and prevents livelocks where contexts may have implicit ordering due
to userspace semaphores. However, not all workloads necessarily benefit
from timeslicing and in the extreme some sysadmin may want to disable or
reduce the timeslicing granularity.

The timeslicing mechanism can be compiled out^W^W disabled (but should
DCE!) with

	./scripts/config --set-val DRM_I915_TIMESLICE_DURATION 0
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191029091632.26281-1-chris@chris-wilson.co.uk

As we use hard coded offsets for a few locations within the context
image, include those in the selftests to assert that they are valid.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191028121803.29408-1-chris@chris-wilson.co.uk

The location of RING_MI_MODE (used to stop the ring across resets) moved
for Tigerlake. Fixup the new location and include a selftest to verify
the location in the default context image.
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/20191026082220.32632-1-chris@chris-wilson.co.uk

On schedule-out (CS completion) of a banned context, scrub the context
image so that we do not replay the active payload. The intent is that we
skip banned payloads on request submission so that the timeline
advancement continues on in the background. However, if we are returning
to a preempted request, i915_request_skip() is ineffective and instead we
need to patch up the context image so that it continues from the start
of the next request.

v2: Fixup cancellation so that we only scrub the payload of the active
request and do not short-circuit the breadcrumbs (which might cause
other contexts to execute out of order).
v3: Grammar pass
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/20191023133108.21401-3-chris@chris-wilson.co.uk

If the preempted context takes too long to relinquish control, e.g. it
is stuck inside a shader with arbitration disabled, evict that context
with an engine reset. This ensures that preemptions are reasonably
responsive, providing a tighter QoS for the more important context at
the cost of flagging unresponsive contexts more frequently (i.e. instead
of using an ~10s hangcheck, we now evict at ~100ms).  The challenge of
lies in picking a timeout that can be reasonably serviced by HW for
typical workloads, balancing the existing clients against the needs for
responsiveness.

Note that coupled with timeslicing, this will lead to rapid GPU "hang"
detection with multiple active contexts vying for GPU time.

The forced preemption mechanism can be compiled out with

	./scripts/config --set-val DRM_I915_PREEMPT_TIMEOUT 0
Signed-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: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-2-chris@chris-wilson.co.uk

The actual conditions are that we know the GPU is not accessing the
context, and we hold a pin on the context image to allow CPU access. We
used a fake lock on ce->pin_mutex so that we could try and use lockdep
to assert that access is serialised, but the various different
hardirq/softirq contexts where we need to *fake* holding the pin_mutex
are causing more trouble.

Still it would be nice if we did have a way to reassure ourselves that
the direct update to the context image is serialised with GPU execution.
In the meantime, stop lockdep complaining about false irq inversions.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111923Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191022122845.25038-1-chris@chris-wilson.co.uk

Normally, we try and skip submission if ELSP[1] is filled. However, we
may desire to enable timeslicing due to the queue priority, even if
ELSP[1] itself does not require timeslicing. That is the queue is equal
priority to ELSP[0] and higher priority then ELSP[1]. Previously, we
would wait until the context switch to preempt the current ELSP[1], but
with timeslicing, we want to preempt ELSP[0] and replace it with the
queue.

In writing the test case, it become quickly apparent that we were also
suppressing the tasklet during promotion and so failing to notice when
the queue started requiring timeslicing.

Fixes: 2229adc8 ("drm/i915/execlist: Trim immediate timeslice expiry")
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/20191018072027.31948-1-chris@chris-wilson.co.uk

Where the function, or code segment, operates on intel_gt, we need to
start passing it instead of i915 to for_each_engine(_masked).

This is another partial step in migration of i915->engines[] to
gt->engines[].
Signed-off-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
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/20191017094500.21831-2-tvrtko.ursulin@linux.intel.com

The execlists selftests are hardware centric and so want to use the gt
as its target.
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/20191016120249.22714-1-chris@chris-wilson.co.uk

A lately added test was missed when applying the struct_mutex removal
patches. Do so now.
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/20191015085911.10317-1-chris@chris-wilson.co.uk

We want the general purpose registers to be clear in all new contexts so
that we can be confident that no information is leaked from one to the
next.
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/20191014090757.32111-7-chris@chris-wilson.co.uk

Check the logical ring context by asserting that the registers hold
expected start during execution. (It's a bit chicken-and-egg for how
could we manage to execute our request if the registers were not being
updated. Still, it's nice to verify that the HW is working as expected.)
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/20191014090757.32111-6-chris@chris-wilson.co.uk

Make sure that we copy across the registers from one engine to the next,
as we hop around a virtual engine.
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/20191010110252.17289-1-chris@chris-wilson.co.uk

Disable irqs around updating the context image to keep lockdep happy:

<4>[  673.483340] WARNING: possible irq lock inversion dependency detected
<4>[  673.483342] 5.4.0-rc1-CI-Trybot_5118+ #1 Tainted: G     U
<4>[  673.483342] --------------------------------------------------------
<4>[  673.483343] swapper/2/0 just changed the state of lock:
<4>[  673.483344] ffff88845db885a0 (&i915_request_get(rq)->submit/1){-...}, at: __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.483387] but this lock took another, HARDIRQ-unsafe lock in the past:
<4>[  673.483388]  (&ce->pin_mutex/2){+...}
<4>[  673.483389]

                  and interrupts could create inverse lock ordering between them.

<4>[  673.483390]
                  other info that might help us debug this:
<4>[  673.483390] Chain exists of:
                    &i915_request_get(rq)->submit/1 --> &engine->active.lock --> &ce->pin_mutex/2

<4>[  673.483392]  Possible interrupt unsafe locking scenario:

<4>[  673.483392]        CPU0                    CPU1
<4>[  673.483393]        ----                    ----
<4>[  673.483393]   lock(&ce->pin_mutex/2);
<4>[  673.483394]                                local_irq_disable();
<4>[  673.483395]                                lock(&i915_request_get(rq)->submit/1);
<4>[  673.483396]                                lock(&engine->active.lock);
<4>[  673.483396]   <Interrupt>
<4>[  673.483397]     lock(&i915_request_get(rq)->submit/1);
<4>[  673.483398]
                   *** DEADLOCK ***

<4>[  673.483398] 2 locks held by swapper/2/0:
<4>[  673.483399]  #0: ffff8883f61ac9b0 (&(&gt->irq_lock)->rlock){-.-.}, at: gen11_gt_irq_handler+0x42/0x280 [i915]
<4>[  673.483433]  #1: ffff88845db8c418 (&(&rq->lock)->rlock){-.-.}, at: intel_engine_breadcrumbs_irq+0x34a/0x5a0 [i915]
<4>[  673.483463]
                  the shortest dependencies between 2nd lock and 1st lock:
<4>[  673.483466]   -> (&ce->pin_mutex/2){+...} ops: 614520 {
<4>[  673.483468]      HARDIRQ-ON-W at:
<4>[  673.483471]                         lock_acquire+0xa7/0x1c0
<4>[  673.483501]                         live_unlite_restore+0x1d8/0x6c0 [i915]
<4>[  673.483543]                         __i915_subtests+0xb8/0x210 [i915]
<4>[  673.483581]                         __run_selftests+0x112/0x170 [i915]
<4>[  673.483615]                         i915_live_selftests+0x2c/0x60 [i915]
<4>[  673.483644]                         i915_pci_probe+0x93/0x1b0 [i915]
<4>[  673.483646]                         pci_device_probe+0x9e/0x120
<4>[  673.483648]                         really_probe+0xea/0x420
<4>[  673.483649]                         driver_probe_device+0x10b/0x120
<4>[  673.483651]                         device_driver_attach+0x4a/0x50
<4>[  673.483652]                         __driver_attach+0x97/0x130
<4>[  673.483653]                         bus_for_each_dev+0x74/0xc0
<4>[  673.483654]                         bus_add_driver+0x142/0x220
<4>[  673.483655]                         driver_register+0x56/0xf0
<4>[  673.483657]                         do_one_initcall+0x58/0x2ff
<4>[  673.483659]                         do_init_module+0x56/0x1f8
<4>[  673.483660]                         load_module+0x243e/0x29f0
<4>[  673.483661]                         __do_sys_finit_module+0xe9/0x110
<4>[  673.483662]                         do_syscall_64+0x4f/0x210
<4>[  673.483665]                         entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.483665]      INITIAL USE at:
<4>[  673.483667]                        lock_acquire+0xa7/0x1c0
<4>[  673.483698]                        live_unlite_restore+0x1d8/0x6c0 [i915]
<4>[  673.483733]                        __i915_subtests+0xb8/0x210 [i915]
<4>[  673.483764]                        __run_selftests+0x112/0x170 [i915]
<4>[  673.483793]                        i915_live_selftests+0x2c/0x60 [i915]
<4>[  673.483821]                        i915_pci_probe+0x93/0x1b0 [i915]
<4>[  673.483822]                        pci_device_probe+0x9e/0x120
<4>[  673.483824]                        really_probe+0xea/0x420
<4>[  673.483825]                        driver_probe_device+0x10b/0x120
<4>[  673.483826]                        device_driver_attach+0x4a/0x50
<4>[  673.483827]                        __driver_attach+0x97/0x130
<4>[  673.483828]                        bus_for_each_dev+0x74/0xc0
<4>[  673.483829]                        bus_add_driver+0x142/0x220
<4>[  673.483830]                        driver_register+0x56/0xf0
<4>[  673.483831]                        do_one_initcall+0x58/0x2ff
<4>[  673.483833]                        do_init_module+0x56/0x1f8
<4>[  673.483834]                        load_module+0x243e/0x29f0
<4>[  673.483835]                        __do_sys_finit_module+0xe9/0x110
<4>[  673.483836]                        do_syscall_64+0x4f/0x210
<4>[  673.483837]                        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.483838]    }
<4>[  673.483868]    ... key      at: [<ffffffffa0a8f132>] __key.70113+0x2/0xffffffffffef2ed0 [i915]
<4>[  673.483869]    ... acquired at:
<4>[  673.483935]    __execlists_reset+0xfb/0xc20 [i915]
<4>[  673.483965]    execlists_reset+0x3d/0x50 [i915]
<4>[  673.483995]    intel_engine_reset+0xdf/0x230 [i915]
<4>[  673.484022]    live_preempt_hang+0x1d7/0x2e0 [i915]
<4>[  673.484064]    __i915_subtests+0xb8/0x210 [i915]
<4>[  673.484130]    __run_selftests+0x112/0x170 [i915]
<4>[  673.484163]    i915_live_selftests+0x2c/0x60 [i915]
<4>[  673.484193]    i915_pci_probe+0x93/0x1b0 [i915]
<4>[  673.484194]    pci_device_probe+0x9e/0x120
<4>[  673.484195]    really_probe+0xea/0x420
<4>[  673.484196]    driver_probe_device+0x10b/0x120
<4>[  673.484197]    device_driver_attach+0x4a/0x50
<4>[  673.484198]    __driver_attach+0x97/0x130
<4>[  673.484199]    bus_for_each_dev+0x74/0xc0
<4>[  673.484200]    bus_add_driver+0x142/0x220
<4>[  673.484202]    driver_register+0x56/0xf0
<4>[  673.484203]    do_one_initcall+0x58/0x2ff
<4>[  673.484204]    do_init_module+0x56/0x1f8
<4>[  673.484205]    load_module+0x243e/0x29f0
<4>[  673.484206]    __do_sys_finit_module+0xe9/0x110
<4>[  673.484207]    do_syscall_64+0x4f/0x210
<4>[  673.484208]    entry_SYSCALL_64_after_hwframe+0x49/0xbe

<4>[  673.484209]  -> (&engine->active.lock){..-.} ops: 972791 {
<4>[  673.484211]     IN-SOFTIRQ-W at:
<4>[  673.484213]                       lock_acquire+0xa7/0x1c0
<4>[  673.484214]                       _raw_spin_lock_irqsave+0x33/0x50
<4>[  673.484244]                       execlists_submission_tasklet+0xaf/0x100 [i915]
<4>[  673.484246]                       tasklet_action_common.isra.18+0x6c/0x1c0
<4>[  673.484247]                       __do_softirq+0xdf/0x47f
<4>[  673.484248]                       irq_exit+0xba/0xc0
<4>[  673.484249]                       do_IRQ+0x83/0x160
<4>[  673.484250]                       ret_from_intr+0x0/0x1d
<4>[  673.484252]                       cpuidle_enter_state+0xb2/0x450
<4>[  673.484253]                       cpuidle_enter+0x24/0x40
<4>[  673.484254]                       do_idle+0x1e7/0x250
<4>[  673.484256]                       cpu_startup_entry+0x14/0x20
<4>[  673.484257]                       start_secondary+0x15f/0x1b0
<4>[  673.484258]                       secondary_startup_64+0xa4/0xb0
<4>[  673.484259]     INITIAL USE at:
<4>[  673.484261]                      lock_acquire+0xa7/0x1c0
<4>[  673.484290]                      intel_engine_init_active+0x7e/0xb0 [i915]
<4>[  673.484305]                      intel_engines_setup+0x1cd/0x3b0 [i915]
<4>[  673.484305]                      i915_gem_init+0x12d/0x900 [i915]
<4>[  673.484305]                      i915_driver_probe+0xb70/0x15d0 [i915]
<4>[  673.484305]                      i915_pci_probe+0x43/0x1b0 [i915]
<4>[  673.484305]                      pci_device_probe+0x9e/0x120
<4>[  673.484305]                      really_probe+0xea/0x420
<4>[  673.484305]                      driver_probe_device+0x10b/0x120
<4>[  673.484305]                      device_driver_attach+0x4a/0x50
<4>[  673.484305]                      __driver_attach+0x97/0x130
<4>[  673.484305]                      bus_for_each_dev+0x74/0xc0
<4>[  673.484305]                      bus_add_driver+0x142/0x220
<4>[  673.484305]                      driver_register+0x56/0xf0
<4>[  673.484305]                      do_one_initcall+0x58/0x2ff
<4>[  673.484305]                      do_init_module+0x56/0x1f8
<4>[  673.484305]                      load_module+0x243e/0x29f0
<4>[  673.484305]                      __do_sys_finit_module+0xe9/0x110
<4>[  673.484305]                      do_syscall_64+0x4f/0x210
<4>[  673.484305]                      entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.484305]   }
<4>[  673.484305]   ... key      at: [<ffffffffa0a8f160>] __key.70307+0x0/0xffffffffffef2ea0 [i915]
<4>[  673.484305]   ... acquired at:
<4>[  673.484305]    _raw_spin_lock_irqsave+0x33/0x50
<4>[  673.484305]    execlists_submit_request+0x2b/0x1e0 [i915]
<4>[  673.484305]    submit_notify+0xa8/0x13c [i915]
<4>[  673.484305]    __i915_sw_fence_complete+0x81/0x250 [i915]
<4>[  673.484305]    i915_sw_fence_wake+0x51/0x70 [i915]
<4>[  673.484305]    __i915_sw_fence_complete+0x1ee/0x250 [i915]
<4>[  673.484305]    dma_i915_sw_fence_wake+0x1b/0x30 [i915]
<4>[  673.484305]    dma_fence_signal_locked+0x9e/0x1b0
<4>[  673.484305]    dma_fence_signal+0x1f/0x40
<4>[  673.484305]    fence_work+0x28/0x80 [i915]
<4>[  673.484305]    process_one_work+0x26a/0x620
<4>[  673.484305]    worker_thread+0x37/0x380
<4>[  673.484305]    kthread+0x119/0x130
<4>[  673.484305]    ret_from_fork+0x24/0x50

<4>[  673.484305] -> (&i915_request_get(rq)->submit/1){-...} ops: 857694 {
<4>[  673.484305]    IN-HARDIRQ-W at:
<4>[  673.484305]                     lock_acquire+0xa7/0x1c0
<4>[  673.484305]                     _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]                     __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]                     intel_engine_breadcrumbs_irq+0x3d0/0x5a0 [i915]
<4>[  673.484305]                     cs_irq_handler+0x39/0x50 [i915]
<4>[  673.484305]                     gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  673.484305]                     gen11_irq_handler+0x54/0xf0 [i915]
<4>[  673.484305]                     __handle_irq_event_percpu+0x41/0x2c0
<4>[  673.484305]                     handle_irq_event_percpu+0x2b/0x70
<4>[  673.484305]                     handle_irq_event+0x2f/0x50
<4>[  673.484305]                     handle_edge_irq+0x99/0x1b0
<4>[  673.484305]                     do_IRQ+0x7e/0x160
<4>[  673.484305]                     ret_from_intr+0x0/0x1d
<4>[  673.484305]                     cpuidle_enter_state+0xb2/0x450
<4>[  673.484305]                     cpuidle_enter+0x24/0x40
<4>[  673.484305]                     do_idle+0x1e7/0x250
<4>[  673.484305]                     cpu_startup_entry+0x14/0x20
<4>[  673.484305]                     start_secondary+0x15f/0x1b0
<4>[  673.484305]                     secondary_startup_64+0xa4/0xb0
<4>[  673.484305]    INITIAL USE at:
<4>[  673.484305]                    lock_acquire+0xa7/0x1c0
<4>[  673.484305]                    _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]                    __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]                    __engine_park+0x233/0x420 [i915]
<4>[  673.484305]                    ____intel_wakeref_put_last+0x1c/0x70 [i915]
<4>[  673.484305]                    intel_gt_resume+0x202/0x2c0 [i915]
<4>[  673.484305]                    i915_gem_init+0x36e/0x900 [i915]
<4>[  673.484305]                    i915_driver_probe+0xb70/0x15d0 [i915]
<4>[  673.484305]                    i915_pci_probe+0x43/0x1b0 [i915]
<4>[  673.484305]                    pci_device_probe+0x9e/0x120
<4>[  673.484305]                    really_probe+0xea/0x420
<4>[  673.484305]                    driver_probe_device+0x10b/0x120
<4>[  673.484305]                    device_driver_attach+0x4a/0x50
<4>[  673.484305]                    __driver_attach+0x97/0x130
<4>[  673.484305]                    bus_for_each_dev+0x74/0xc0
<4>[  673.484305]                    bus_add_driver+0x142/0x220
<4>[  673.484305]                    driver_register+0x56/0xf0
<4>[  673.484305]                    do_one_initcall+0x58/0x2ff
<4>[  673.484305]                    do_init_module+0x56/0x1f8
<4>[  673.484305]                    load_module+0x243e/0x29f0
<4>[  673.484305]                    __do_sys_finit_module+0xe9/0x110
<4>[  673.484305]                    do_syscall_64+0x4f/0x210
<4>[  673.484305]                    entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.484305]  }
<4>[  673.484305]  ... key      at: [<ffffffffa0a8f6a1>] __key.80173+0x1/0xffffffffffef2960 [i915]
<4>[  673.484305]  ... acquired at:
<4>[  673.484305]    mark_lock+0x382/0x500
<4>[  673.484305]    __lock_acquire+0x7e1/0x15d0
<4>[  673.484305]    lock_acquire+0xa7/0x1c0
<4>[  673.484305]    _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]    __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]    intel_engine_breadcrumbs_irq+0x3d0/0x5a0 [i915]
<4>[  673.484305]    cs_irq_handler+0x39/0x50 [i915]
<4>[  673.484305]    gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  673.484305]    gen11_irq_handler+0x54/0xf0 [i915]
<4>[  673.484305]    __handle_irq_event_percpu+0x41/0x2c0
<4>[  673.484305]    handle_irq_event_percpu+0x2b/0x70
<4>[  673.484305]    handle_irq_event+0x2f/0x50
<4>[  673.484305]    handle_edge_irq+0x99/0x1b0
<4>[  673.484305]    do_IRQ+0x7e/0x160
<4>[  673.484305]    ret_from_intr+0x0/0x1d
<4>[  673.484305]    cpuidle_enter_state+0xb2/0x450
<4>[  673.484305]    cpuidle_enter+0x24/0x40
<4>[  673.484305]    do_idle+0x1e7/0x250
<4>[  673.484305]    cpu_startup_entry+0x14/0x20
<4>[  673.484305]    start_secondary+0x15f/0x1b0
<4>[  673.484305]    secondary_startup_64+0xa4/0xb0

<4>[  673.484305]
                  stack backtrace:
<4>[  673.484305] CPU: 2 PID: 0 Comm: swapper/2 Tainted: G     U            5.4.0-rc1-CI-Trybot_5118+ #1
<4>[  673.484305] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4>[  673.484305] Call Trace:
<4>[  673.484305]  <IRQ>
<4>[  673.484305]  dump_stack+0x67/0x9b
<4>[  673.484305]  check_usage_forwards+0x13c/0x150
<4>[  673.484305]  ? mark_lock+0x382/0x500
<4>[  673.484305]  mark_lock+0x382/0x500
<4>[  673.484305]  ? check_usage_backwards+0x140/0x140
<4>[  673.484305]  __lock_acquire+0x7e1/0x15d0
<4>[  673.484305]  ? debug_object_deactivate+0x17e/0x190
<4>[  673.484305]  lock_acquire+0xa7/0x1c0
<4>[  673.484305]  ? __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]  _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]  ? __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]  __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]  intel_engine_breadcrumbs_irq+0x3d0/0x5a0 [i915]
<4>[  673.484305]  cs_irq_handler+0x39/0x50 [i915]
<4>[  673.484305]  gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  673.484305]  gen11_irq_handler+0x54/0xf0 [i915]
<4>[  673.484305]  __handle_irq_event_percpu+0x41/0x2c0
<4>[  673.484305]  handle_irq_event_percpu+0x2b/0x70
<4>[  673.484305]  handle_irq_event+0x2f/0x50
<4>[  673.484305]  handle_edge_irq+0x99/0x1b0
<4>[  673.484305]  do_IRQ+0x7e/0x160
<4>[  673.484305]  common_interrupt+0xf/0xf
<4>[  673.484305]  </IRQ>
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/20191004203121.31138-1-chris@chris-wilson.co.uk

We no longer need struct_mutex to serialise request emission, so remove
it from the gt selftests.
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/20191004134015.13204-20-chris@chris-wilson.co.uk

Keep track of the GEM contexts underneath i915->gem.contexts and assign
them their own lock for the purposes of list management.

v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex
v3: Correct split with removal of logical HW ID
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/20191004134015.13204-15-chris@chris-wilson.co.uk