So it appears that commit 5427f20785 ("drm/i915: Bump wait-times for
the final CS interrupt before parking") was a little over optimistic in
its belief that it had successfully waited for all residual activity on
the engines before parking. Numerous sightings in CI since then of
<7>[ 52.542886] [IGT] core_auth: executing
<3>[ 52.561013] [drm:intel_engines_park [i915]] *ERROR* vcs0 is not idle before parking
<7>[ 52.561215] intel_engines_park vcs0
<7>[ 52.561229] intel_engines_park current seqno 98, last 98, hangcheck 0 [-247449 ms], inflight 0
<7>[ 52.561238] intel_engines_park Reset count: 0
<7>[ 52.561266] intel_engines_park Requests:
<7>[ 52.561363] intel_engines_park RING_START: 0x00000000 [0x00000000]
<7>[ 52.561377] intel_engines_park RING_HEAD: 0x00000000 [0x00000000]
<7>[ 52.561390] intel_engines_park RING_TAIL: 0x00000000 [0x00000000]
<7>[ 52.561406] intel_engines_park RING_CTL: 0x00000000
<7>[ 52.561422] intel_engines_park RING_MODE: 0x00000200 [idle]
<7>[ 52.561442] intel_engines_park ACTHD: 0x00000000_00000000
<7>[ 52.561459] intel_engines_park BBADDR: 0x00000000_00000000
<7>[ 52.561474] intel_engines_park Execlist status: 0x00000301 00000000
<7>[ 52.561489] intel_engines_park Execlist CSB read 5 [5 cached], write 5 [5 from hws], interrupt posted? no
<7>[ 52.561500] intel_engines_park ELSP[0] idle
<7>[ 52.561510] intel_engines_park ELSP[1] idle
<7>[ 52.561519] intel_engines_park HW active? 0x0
<7>[ 52.561608] intel_engines_park Idle? yes
<7>[ 52.561617] intel_engines_park
on Braswell, which indicates that the engine just needs that little bit
longer after flushing the tasklet to settle. So give it a few more
milliseconds before declaring an err and applying the emergency brake.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103479
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110112550.28909-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
intel_uncore_forcewake_reset() does forcewake puts and gets as such
we need to make sure that no-one tries to access the PUNIT->PMIC bus
(on systems where this bus is shared) while it runs, otherwise bad
things happen.
Normally this is taken care of by the i915_pmic_bus_access_notifier()
which does an intel_uncore_forcewake_get(FORCEWAKE_ALL) when some other
driver tries to access the PMIC bus, so that later forcewake gets are
no-ops (for the duration of the bus access).
But intel_uncore_forcewake_reset gets called in 3 cases:
1) Before registering the pmic_bus_access_notifier
2) After unregistering the pmic_bus_access_notifier
3) To reset forcewake state on a GPU reset
In all 3 cases the i915_pmic_bus_access_notifier() protection is
insufficient.
This commit fixes this race by calling iosf_mbi_punit_acquire() before
calling intel_uncore_forcewake_reset(). In the case where it is called
directly after unregistering the pmic_bus_access_notifier, we need to
hold the punit-lock over both calls to avoid a race where
intel_uncore_fw_release_timer() may execute between the 2 calls.
Reviewed-by: Imre Deak <imre.deak@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171019111620.26761-3-hdegoede@redhat.com
For race free unregistration drivers may need to acquire PMIC bus access
through iosf_mbi_punit_acquire() and then (un)register the notifier without
dropping the lock.
This commit adds an unlocked variant of
iosf_mbi_unregister_pmic_bus_access_notifier for this use case.
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171019111620.26761-2-hdegoede@redhat.com
In order to allow the mock breadcrumbs tests to run without device irqs
being enabled, move the intel_irqs_enabled() assert deeper to just
before we commit to enabling the HW irq.
v2: Add a FIXME explaining that placing the assertion so deep is not
ideal, but a compromise for mock breadcrumbs.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171107102003.1802-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Originally it was anticipated that timeouts would be a rare event, and
so merit a warning that the test was incomplete. However, for igt we
keep the timeout low, and hitting the timeout is intentional. It no
longer necessitates a warning, but to be expected.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110101110.12042-1-chris@chris-wilson.co.uk
Reviwed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
The lease updates missed a few bits of docs, fixed up
the wrong name on the property lookup fn as well.
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Whenever we want to unbind a vma, we must wait on all GPU activity to
complete first. (This is what gives us the ability to do fine grained
eviction and purging by only having to wait on the VMA that we need to
unbind to proceed; though if pushed we can make it a rule that we are
only allowed to unbind already idle VMA and move the burden of the work
and organising the sleep onto the caller.) Currently, we might only
sleep if the vma is still active on the GPU, but in principle
i915_vma_unbind() always implies a sleep, so mark it up with a
might_sleep().
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
References: https://bugs.freedesktop.org/show_bug.cgi?id=103638
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109213450.13875-2-chris@chris-wilson.co.uk
vm_free_page() may call down into set_pages_array_wb() (which itself
sleeps, on x86 at least) but only if on !llc and the caches overflow.
Since this is unlikely, we only rarely trigger the error in practice,
and so to make CI detection of this sleeping bug possible we want to
mark the common vm_free_page() as a potential sleep.
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
References: https://bugs.freedesktop.org/show_bug.cgi?id=103638
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109213450.13875-1-chris@chris-wilson.co.uk
Trying to enable printk debugging for GEM is fraught with the issue of
spam; interactions with HW are very frequent and often boring. However,
one instance where they are not so boring is just before a BUG; here
ftrace provides a facility to dump its ringbuffer on an oops. So for CI
let's enable trace_printk() to capture the last exchanges with HW as a
death rattle.
For example,
[ 79.234110] ------------[ cut here ]------------
[ 79.234137] kernel BUG at drivers/gpu/drm/i915/intel_lrc.c:907!
[ 79.234145] invalid opcode: 0000 [#1] SMP
[ 79.234153] Dumping ftrace buffer:
[ 79.234158] ---------------------------------
...
[ 79.314044] gem_conc-1059 1..s1 79203443us : intel_lrc_irq_handler: bcs0 out[0]: ctx=5.2, seqno=145
[ 79.314089] gem_conc-1059 1..s. 79220800us : intel_lrc_irq_handler: bcs0 csb[1/1]: status=0x00000018:0x00000005
[ 79.314133] gem_conc-1059 1..s. 79220803us : intel_lrc_irq_handler: bcs0 out[0]: ctx=5.1, seqno=145
[ 79.314177] gem_conc-1062 2..s1 79230458us : intel_lrc_irq_handler: bcs0 in[0]: ctx=8.1, seqno=146
[ 79.314220] gem_conc-1062 2..s1 79230515us : intel_lrc_irq_handler: bcs0 in[0]: ctx=8.2, seqno=147
[ 79.314265] gem_conc-1059 1..s1 79230951us : intel_lrc_irq_handler: bcs0 csb[2/3]: status=0x00000012:0x00000008
[ 79.314309] gem_conc-1059 1..s1 79230954us : intel_lrc_irq_handler: bcs0 out[0]: ctx=8.2, seqno=147
[ 79.314353] gem_conc-1059 1..s1 79230954us : intel_lrc_irq_handler: bcs0 csb[3/3]: status=0x00008002:0x00000008
[ 79.314396] gem_conc-1059 1..s1 79230955us : intel_lrc_irq_handler: bcs0 out[0]: ctx=8.1, seqno=147
[ 79.314402] ---------------------------------
v2: Tweak the formatting to be more consistent between in/out.
v3: do {} while (0) stub macro protection
Suggested-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109143019.16568-1-chris@chris-wilson.co.uk
Eliminate a ton of pointless 'dev' variables in the DP code, and pass
around 'dev_priv' instead of 'dev'.
v2: Rebase
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109152758.32257-1-ville.syrjala@linux.intel.com
No need to pass 'dev' or 'dev_priv' when the function already takes
'intel_dp'. Also let's prefer passing 'dev_priv' instead of 'dev'
when we have to pass one or the other.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031205123.13123-10-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Replace dig_port->port with encoder->port in the BXT DPLL selection.
We can do this because both the master encoder and the fake MST encoders
have the same encoder->port value, whereas using dig_port->port only
worked for the master encoder since the fake encoders were't derived
from intel_digital_port. This eliminates the DP MST special case.
Do this by hand because spatch is having problems with the control
flow due to the dig_port assignment happening in two different
branches.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031205123.13123-8-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Replace crtc->config usage with the passed down crtc state.
Also take the opportunity for some s/pipe_config/crtc_state/ while at it.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031205123.13123-7-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Rather than digging through encoder->crtc and crtc->config in the
DPIO PHY functions, pass down the correct crtc state from the caller.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031205123.13123-6-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
When we close the VMA, we unbind it from the ppgtt and tear down the
page directory pointing at it. That may trigger us to return WC pages
back to the system, requiring conversion back to WB which itself may
sleep. That makes i915_vma_close() unsuitable for use inside the RCU
read lock, which we need to hold to iterate the radixtree.
The fix is quite simple, we can close all the VMA as we close the ppgtt,
we only need to do that instead of closing them during destruction of
the LUT.
v2: Order between closing the LUT and the ppgtt is important; we use the
vma inside the LUT as a means of retrieving the object, and so we must
clear the LUT before freeing the VMA when closing the ppgtt.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103638
Fixes: 547da76b57 ("drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr)")
Fixes: d1b48c1e71 ("drm/i915: Replace execbuf vma ht with an idr")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109085540.32264-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
(cherry picked from commit 94dec87159)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Apparently setting up a bunch of GT registers before we've properly
initialized the rest of the GT hardware leads to these setting being
lost. So looks like I broke HSW with commit b7048ea12f ("drm/i915:
Do .init_clock_gating() earlier to avoid it clobbering watermarks")
by doing init_clock_gating() too early. This should actually affect
other platforms as well, but apparently not to such a great degree.
What I was ultimately after in that commit was to move the
ilk_init_lp_watermarks() call earlier. So let's undo the damage and
move init_clock_gating() back to where it was, and call
ilk_init_lp_watermarks() just before the watermark state readout.
This highlights how fragile and messed up our init order really is.
I wonder why we even initialize the display before gem. The opposite
order would make much more sense to me...
v2: Keep WaRsPkgCStateDisplayPMReq:hsw early as it really must
be done before all planes might get disabled.
Cc: stable@vger.kernel.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mark Janes <mark.a.janes@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reported-by: Mark Janes <mark.a.janes@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103549
Fixes: b7048ea12f ("drm/i915: Do .init_clock_gating() earlier to avoid it clobbering watermarks")
References: https://lists.freedesktop.org/archives/intel-gfx/2017-November/145432.html
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171108133555.14091-1-ville.syrjala@linux.intel.com
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
(cherry picked from commit f72b84c677)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
The shared fence array is not autopruning and may continue to grow as an
object is shared between new timelines. Take the opportunity when we
think the object is idle (we have to confirm that any external fence is
also signaled) to decouple all the fences.
We apply a similar trick after waiting on an object, see commit
e54ca97747 ("drm/i915: Remove completed fences after a wait")
v2: No longer need to handle the batch pool as a special case.
v3: Need to trylock from within i915_vma_retire as this may be called
form the shrinker - and we may later try to allocate underneath the
reservation lock, so a deadlock is possible.
References: https://bugs.freedesktop.org/show_bug.cgi?id=102936
Fixes: d07f0e59b2 ("drm/i915: Move GEM activity tracking into a common struct reservation_object")
Fixes: 80b204bce8 ("drm/i915: Enable multiple timelines")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171107220656.5020-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
(cherry picked from commit 1ab22356b3)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
The handling of contexts are peculiar. Instead of tieing their vma to
activity, we pin the context. This means that we cannot simply unbind
the context object itself at will (which would normally cause us to wait
for the vma to be idle), but must manually idle the GPU and retire
requests first.
A consequence of this peculiarity is when doing a last desperate attempt
to recover memory. If the memory is tied up inside active context
objects, we will fail to recover any memory simply by trying to unbind
the objects without first doing a wait-for-idle.
A side-effect of removing the call to shrinker_lock_uninterruptible()
from i915_gem_shrinker_oom() was that we removed an unlocked
wait-for-idle, and so lost the "natural" shrinkage of context objects.
By replacing that with a locked wait from inside i915_gem_shrink(), we
not only replace it with the ability to recover all context objects, but
do so for all i915_gem_shrink_all() callers.
v2: Switching requires request allocation, which is not permitted from
inside the shrinker as it only uses ordinary allocations.
References: https://bugs.freedesktop.org/show_bug.cgi?id=102936
Fixes: f2123818ff ("drm/i915: Move dev_priv->mm.[un]bound_list to its own lock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171108094400.1386-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
(cherry picked from commit 2f6a378383)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
The watermarks it should calculate against are the old optimal watermarks.
The currently active crtc watermarks are pure fiction, and are invalid in
case of a nonblocking modeset, page flip enabling/disabling planes or any
other reason.
When the crtc is disabled or during a modeset the intermediate watermarks
don't need to be programmed separately, and could be directly assigned
to the optimal watermarks.
Changes since v1:
- Use intel_atomic_get_old_crtc_state. (ville)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171019151341.4579-2-maarten.lankhorst@linux.intel.com
[mlankhorst: Add cc stable and bugzilla link, since previous patch doesn't fix issue by itself]
Cc: stable@vger.kernel.org #v4.8+
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102373
(cherry picked from commit b6b178a772)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
When running under virtualization (vGPU active), we must disable
the lazy PPGTT page table initialization optimization introduced by
commit 1482667324 ("drm/i915: Only initialize partially filled
pagetables").
We must do this because GVT-g makes unduly assumptions about guest
behaviour, which this optimization breaks. This results in following
looking errors in the host:
ERROR gvt: guest page write error -22, gfn 0x7ada8, pa 0x7ada89a8, var 0x6, len 1
The real fix is to not to depend on i915 driver behaviour, but instead
either rely on only the contracts that i915 has with the hardware, or
add some paravirtualization. While the real fix is en route, it won't
be finished in time for 4.15, so the best option is to disable the
optimization for now when vGPU is active to avoid breaking 4.15 guests
in existing VM environments.
Fixes: 1482667324 ("drm/i915: Only initialize partially filled pagetables")
Suggested-by: Xiaolin Zhang <xiaolin.zhang@intel.com>
Signed-off-by: Xiaolin Zhang <xiaolin.zhang@intel.com>
[Joonas: Rewrote the commit message and added tags.]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023153209.10527-1-joonas.lahtinen@linux.intel.com
(cherry picked from commit 22a8a4fc93)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Originally we set the priority to max upon inserting the request into
the execlists queue (and removing it from the scheduler lists). We could
then use the prio==INT_MAX as a shortcut within execlists_schedule() to
detect the end of the dependency chain. Since commit 1f181225f8
("drm/i915/execlists: Keep request->priority for its lifetime") this is
no longer true as we use the request completion as an indicator the
schedule dependency chain is complete instead. (This allows us to then
reschedule requests even when its context is in flight.) However, this
makes the GEM_BUG_ON() inside execlists_schedule() racy as we may change
the rq->prio at the same time. As the assertion is useful, let's keep
the assertion and remove the micro-optimisation.
Fixes: 1f181225f8 ("drm/i915/execlists: Keep request->priority for its lifetime")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024115501.21033-1-chris@chris-wilson.co.uk
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
(cherry picked from commit 64b80085dd)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Back in commit a4b2b01523 ("drm/i915: Don't mark an execlists
context-switch when idle") we noticed the presence of late
context-switch interrupts. We were able to filter those out by looking
at whether the ELSP remained active, but in commit beecec9017
("drm/i915/execlists: Preemption!") that became problematic as we now
anticipate receiving a context-switch event for preemption while ELSP
may be empty. To restore the spurious interrupt suppression, add a
counter for the expected number of pending context-switches and skip if
we do not need to handle this interrupt to make forward progress.
v2: Don't forget to switch on for preempt.
v3: Reduce the counter to a on/off boolean tracker. Declare the HW as
active when we first submit, and idle after the final completion event
(with which we confirm the HW says it is idle), and track each source
of activity separately. With a finite number of sources, it should aide
us in debugging which gets stuck.
Fixes: beecec9017 ("drm/i915/execlists: Preemption!")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023213237.26536-3-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
(cherry picked from commit 4a118ecbe9)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
When we close the VMA, we unbind it from the ppgtt and tear down the
page directory pointing at it. That may trigger us to return WC pages
back to the system, requiring conversion back to WB which itself may
sleep. That makes i915_vma_close() unsuitable for use inside the RCU
read lock, which we need to hold to iterate the radixtree.
The fix is quite simple, we can close all the VMA as we close the ppgtt,
we only need to do that instead of closing them during destruction of
the LUT.
v2: Order between closing the LUT and the ppgtt is important; we use the
vma inside the LUT as a means of retrieving the object, and so we must
clear the LUT before freeing the VMA when closing the ppgtt.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103638
Fixes: 547da76b57 ("drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr)")
Fixes: d1b48c1e71 ("drm/i915: Replace execbuf vma ht with an idr")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109085540.32264-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
4.15 merge window fixes, round 2:
randconfig fix from Arnd, plus the vblank WARN_ON fix from Ville.
* tag 'drm-misc-next-fixes-2017-11-08' of git://anongit.freedesktop.org/drm/drm-misc:
drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
drm/rockchip: add CONFIG_OF dependency for lvds
A few more fixes for 4.15.
* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux:
drm/amdgpu: use irq-safe lock for kiq->ring_lock
drm/amdgpu: bypass lru touch for KIQ ring submission
drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
drm/amd/powerplay: initialize a variable before using it
drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
This lock is used during register accessing in SRIOV guest.
The register accessing could happen both in irq enabled and
irq disabled cases. Always use irq-safe lock.
Signed-off-by: Pixel Ding <Pixel.Ding@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
KIQ ring submission is used for register accessing on SRIOV
VF that could happen both in irq enabled and irq disabled cases.
Inversion lock could happen on adev->ring_lru_list_lock, while
this operation is useless and just adds overhead in this use
case.
Signed-off-by: Pixel Ding <Pixel.Ding@amd.com>
Reviewed-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
After commit ea09729c93 ("drm/amdgpu: rework page directory filling
v2") then it becomes a lot harder to verify that "r" is initialized. My
static checker complains and so I've reviewed the code. It does look
like it might be buggy... Anyway, it doesn't hurt to set "r" to zero
at the start.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
We shifted some code around in commit 9cca0b8e5d ("drm/amdgpu: move
amdgpu_cs_sysvm_access_required into find_mapping") and now my static
checker complains that "r" might not be initialized at the end of the
function. I've reviewed the code, and that seems possible, but it's
also possible I may have missed something.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
We can program GUC_SHIM_CONTROL register with all expected
bits without use of extra macro defined in fwif.h
v2: rebased without pre-prod code
v3: fixed typo
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171103151816.62048-4-michal.wajdeczko@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We don't keep the workarounds for pre-production hardware
(see intel_detect_preproduction_hw) thus we can drop some
extra steps during firmware upload needed only for unsupported
platforms.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171103151816.62048-3-michal.wajdeczko@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We silently assumed that DMA transfer will be completed
within assumed timeout and thus we were waiting only at
last step for GuC to become ready. Add intermediate wait
to catch unexpected delays in DMA transfer.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171103151816.62048-2-michal.wajdeczko@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Transfer of GuC firmware requires few steps that currently
are implemented in two large functions. Split this code into
smaller functions to make these steps small and clear.
Also be prepared for potential DMA xfer step failure.
v2: rename function steps (Sagar)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171103151816.62048-1-michal.wajdeczko@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The workaround for this is described as:
"if RenderSurfaceState.Num_Multisamples > 1, disable RCC clock gating if
RenderSurfaceState.Num_Multisamples == 1, set 0x7010[14] = 1"
Further documentation in the internal bug referenced by the bspec
suggest that any of the above suggestions should suffice to fix the
issue. We are going with disabling RCC clock gating.
Unfortunately, what we are doing doesn't match the name of the
workaround, but at least it matches its description.
This change improves CNL stability by avoiding some of the hangs seen in
the platform.
v2: Only disable RCC clock gating.
Signed-off-by: Rafael Antognolli <rafael.antognolli@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171103183027.5051-1-rafael.antognolli@intel.com
Apparently setting up a bunch of GT registers before we've properly
initialized the rest of the GT hardware leads to these setting being
lost. So looks like I broke HSW with commit b7048ea12f ("drm/i915:
Do .init_clock_gating() earlier to avoid it clobbering watermarks")
by doing init_clock_gating() too early. This should actually affect
other platforms as well, but apparently not to such a great degree.
What I was ultimately after in that commit was to move the
ilk_init_lp_watermarks() call earlier. So let's undo the damage and
move init_clock_gating() back to where it was, and call
ilk_init_lp_watermarks() just before the watermark state readout.
This highlights how fragile and messed up our init order really is.
I wonder why we even initialize the display before gem. The opposite
order would make much more sense to me...
v2: Keep WaRsPkgCStateDisplayPMReq:hsw early as it really must
be done before all planes might get disabled.
Cc: stable@vger.kernel.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mark Janes <mark.a.janes@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reported-by: Mark Janes <mark.a.janes@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103549
Fixes: b7048ea12f ("drm/i915: Do .init_clock_gating() earlier to avoid it clobbering watermarks")
References: https://lists.freedesktop.org/archives/intel-gfx/2017-November/145432.html
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171108133555.14091-1-ville.syrjala@linux.intel.com
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
The shared fence array is not autopruning and may continue to grow as an
object is shared between new timelines. Take the opportunity when we
think the object is idle (we have to confirm that any external fence is
also signaled) to decouple all the fences.
We apply a similar trick after waiting on an object, see commit
e54ca97747 ("drm/i915: Remove completed fences after a wait")
v2: No longer need to handle the batch pool as a special case.
v3: Need to trylock from within i915_vma_retire as this may be called
form the shrinker - and we may later try to allocate underneath the
reservation lock, so a deadlock is possible.
References: https://bugs.freedesktop.org/show_bug.cgi?id=102936
Fixes: d07f0e59b2 ("drm/i915: Move GEM activity tracking into a common struct reservation_object")
Fixes: 80b204bce8 ("drm/i915: Enable multiple timelines")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171107220656.5020-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
The handling of contexts are peculiar. Instead of tieing their vma to
activity, we pin the context. This means that we cannot simply unbind
the context object itself at will (which would normally cause us to wait
for the vma to be idle), but must manually idle the GPU and retire
requests first.
A consequence of this peculiarity is when doing a last desperate attempt
to recover memory. If the memory is tied up inside active context
objects, we will fail to recover any memory simply by trying to unbind
the objects without first doing a wait-for-idle.
A side-effect of removing the call to shrinker_lock_uninterruptible()
from i915_gem_shrinker_oom() was that we removed an unlocked
wait-for-idle, and so lost the "natural" shrinkage of context objects.
By replacing that with a locked wait from inside i915_gem_shrink(), we
not only replace it with the ability to recover all context objects, but
do so for all i915_gem_shrink_all() callers.
v2: Switching requires request allocation, which is not permitted from
inside the shrinker as it only uses ordinary allocations.
References: https://bugs.freedesktop.org/show_bug.cgi?id=102936
Fixes: f2123818ff ("drm/i915: Move dev_priv->mm.[un]bound_list to its own lock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171108094400.1386-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Function vega10_apply_state_adjust_rules() only initializes
stable_pstate_sclk_dpm_percentage when
data->registry_data.stable_pstate_sclk_dpm_percentage is not between 1
and 100. The variable is then used to compute stable_pstate_sclk, which
therefore uses an uninitialized value.
Fix this by initializing stable_pstate_sclk_dpm_percentage to
data->registry_data.stable_pstate_sclk_dpm_percentage.
This issue has been found while building the kernel with clang. The
compiler reported a -Wsometimes-uninitialized warning.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Fixes: f83a999164 ("drm/amd/powerplay: add Vega10 powerplay support (v5)")
Signed-off-by: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Evan Quan <evan.quan@amd.com>
Tested-and-Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chris Wilson