Replace the use of the printk based drm logging macros with the struct
drm_device based logging macros in i915/gt/intel_rps.c. This also
involves extracting the drm_i915_private device pointer from various
intel types.
This converts the instances of DRM_DEBUG_DRIVER to drm_dbg() while not
converting DRM_DEBUG() instances due to the lack of an analogous
drm_device based macro.
References: https://lists.freedesktop.org/archives/dri-devel/2020-January/253381.html
Signed-off-by: Wambui Karuga <wambui.karugax@gmail.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200314183344.17603-7-wambui.karugax@gmail.com
In order to better respond to new heartbeat intervals given via sysfs,
always reprogramme an active heartbeat upon change (i.e. use
mod_delayed_work to reschedule rather than queue_delayed_work which
ignores an already active work.)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200317163208.30010-1-chris@chris-wilson.co.uk
On Gen11 powergating half the execution units is a functional
requirement when using the VME samplers. Not fullfilling this
requirement can lead to hangs.
This unfortunately plays fairly poorly with the NOA requirements. NOA
requires a stable power configuration to maintain its configuration.
As a result using OA (and NOA feeding into it) so far has required us
to use a power configuration that can work for all contexts. The only
power configuration fullfilling this is powergating half the execution
units.
This makes performance analysis for 3D workloads somewhat pointless.
Failing to find a solution that would work for everybody, this change
introduces a new i915-perf stream open parameter that punts the
decision off to userspace. If this parameter is omitted, the existing
Gen11 behavior remains (half EU array powergating).
This change takes the initiative to move all perf related sseu
configuration into i915_perf.c
v2: Make parameter priviliged if different from default
v3: Fix context modifying its sseu config while i915-perf is enabled
v4: Always consider global sseu a privileged operation (Tvrtko)
Override req_sseu point in intel_sseu_make_rpcs() (Tvrtko)
Remove unrelated changes (Tvrtko)
v5: Some typos (Tvrtko)
Process sseu param in read_properties_unlocked() (Tvrtko)
v6: Actually commit the bits from v5...
Fixup some checkpath warnings
v7: Only compare engine uabi field (Chris)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200317132222.2638719-3-lionel.g.landwerlin@intel.com
Apparently we do try and attach a fence to an invalid vma (during
execbuf) so we cannot simply assert it never happens and report EINVAL
instead.
Fixes: dec9cf9ee8 ("drm/i915/gt: Pull restoration of GGTT fences underneath the GT")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200316205450.15843-1-chris@chris-wilson.co.uk
The residual w/a batch is causing system instablity on Ivybridge and
Baytrail under some workloads, so disable until resolved.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/1405
Fixes: 47f8253d2b ("drm/i915/gen7: Clear all EU/L3 residual contexts")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Cc: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311103640.26572-1-chris@chris-wilson.co.uk
This workaround appears under two different numbers (and with somewhat
confused stepping applicability on ICL). Ultimately it appears we
should just implement this for all stepping of ICL and EHL.
Note that this is identical to Wa_1407928979:tgl that already exists in
our driver too...yet another number referencing the same actual
workaround.
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311162300.1838847-7-matthew.d.roper@intel.com
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
The bspec description for this workaround tells us to program
0xFFFF_FFFF into both FBC_RT_BASE_ADDR_REGISTER_* registers, but we've
previously found that this leads to failures in CI. Our suspicion is
that the failures are caused by this valid turning on the "address valid
bit" even though we're intentionally supplying an invalid address.
Experimentation has shown that setting all bits _except_ for the
RT_VALID bit seems to avoid these failures.
v2:
- Mask off the RT_VALID bit. Experimentation with CI trybot indicates
that this is necessary to avoid reset failures on BCS.
v3:
- Program RT_BASE before RT_BASE_UPPER so that the valid bit is turned
off by the first write. (Chris)
Bspec: 11388
Bspec: 33451
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311162300.1838847-4-matthew.d.roper@intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
The bspec documents multiple MCR ranges; make sure they're all captured
by the driver.
Bspec: 13991, 52079
Fixes: 592a7c5e08 ("drm/i915: Extend non readable mcr range")
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311162300.1838847-2-matthew.d.roper@intel.com
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
During driver unload, we have many asserts that we have released our
bookkeeping structs and are idle. In some cases, these struct are
protected by RCU and we do not release them until after an RCU grace
period.
Reported-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: 130a95e909 ("drm/i915/gem: Consolidate ctx->engines[] release")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200312115307.16460-1-chris@chris-wilson.co.uk
Allow super long OpenCL workloads which cannot be preempted within
the default timeout to run out of the box.
v2:
* Make it stick out more and apply only to RCS. (Chris)
v3:
* Mention platform override in kconfig. (Joonas)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Michal Mrozek <michal.mrozek@intel.com>
Cc: <stable@vger.kernel.org> # v5.6+
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Michal Mrozek <Michal.mrozek@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200312115748.29970-1-tvrtko.ursulin@linux.intel.com
Record the initial active element we use when building the next ELSP
submission, so that we can compare against it latter to see if there's
no change.
Fixes: 44d0a9c05b ("drm/i915/execlists: Skip redundant resubmission")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311092624.10012-2-chris@chris-wilson.co.uk
Avoid angering kcsan by serialising the read of the pm_events with the
write in rps_disable_interrupts.
[ 6268.713419] BUG: KCSAN: data-race in intel_rps_park [i915] / rps_work [i915]
[ 6268.713437]
[ 6268.713449] write to 0xffff8881eda8efac of 4 bytes by task 1127 on cpu 3:
[ 6268.713680] intel_rps_park+0x136/0x260 [i915]
[ 6268.713905] __gt_park+0x61/0xa0 [i915]
[ 6268.714128] ____intel_wakeref_put_last+0x42/0x90 [i915]
[ 6268.714352] __intel_wakeref_put_work+0xd3/0xf0 [i915]
[ 6268.714369] process_one_work+0x3b1/0x690
[ 6268.714384] worker_thread+0x80/0x670
[ 6268.714398] kthread+0x19a/0x1e0
[ 6268.714412] ret_from_fork+0x1f/0x30
[ 6268.714423]
[ 6268.714435] read to 0xffff8881eda8efac of 4 bytes by task 950 on cpu 2:
[ 6268.714664] rps_work+0xc2/0x680 [i915]
[ 6268.714679] process_one_work+0x3b1/0x690
[ 6268.714693] worker_thread+0x80/0x670
[ 6268.714707] kthread+0x19a/0x1e0
[ 6268.714720] ret_from_fork+0x1f/0x30
v2: Mark all reads and writes of rpm->pm_events.
The flow of enabling/disabling rps is stronly ordered, so the writes and
interrupt generation are also strongly ordered -- just this may not be
visible to the compiler, so provide annotations.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311092624.10012-1-chris@chris-wilson.co.uk
Since snprintf() returns the would-be-output size instead of the
actual output size, the succeeding calls may go beyond the given
buffer limit. Fix it by replacing with scnprintf().
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200311073256.6535-1-tiwai@suse.de
As a virtual engine may change the rq->engine to point to the active
request in flight, we need to warn the compiler that an active request's
engine is volatile.
[ 95.017686] write (marked) to 0xffff8881e8386b10 of 8 bytes by interrupt on cpu 2:
[ 95.018123] execlists_dequeue+0x762/0x2150 [i915]
[ 95.018539] __execlists_submission_tasklet+0x48/0x60 [i915]
[ 95.018955] execlists_submission_tasklet+0xd3/0x170 [i915]
[ 95.018986] tasklet_action_common.isra.0+0x42/0xa0
[ 95.019016] __do_softirq+0xd7/0x2cd
[ 95.019043] irq_exit+0xbe/0xe0
[ 95.019068] irq_work_interrupt+0xf/0x20
[ 95.019491] i915_request_retire+0x2c5/0x670 [i915]
[ 95.019937] retire_requests+0xa1/0xf0 [i915]
[ 95.020348] engine_retire+0xa1/0xe0 [i915]
[ 95.020376] process_one_work+0x3b1/0x690
[ 95.020403] worker_thread+0x80/0x670
[ 95.020429] kthread+0x19a/0x1e0
[ 95.020454] ret_from_fork+0x1f/0x30
[ 95.020476]
[ 95.020498] read to 0xffff8881e8386b10 of 8 bytes by task 8909 on cpu 3:
[ 95.020918] __i915_request_commit+0x177/0x220 [i915]
[ 95.021329] i915_gem_do_execbuffer+0x38c4/0x4e50 [i915]
[ 95.021750] i915_gem_execbuffer2_ioctl+0x2c3/0x580 [i915]
[ 95.021784] drm_ioctl_kernel+0xe4/0x120
[ 95.021809] drm_ioctl+0x297/0x4c7
[ 95.021832] ksys_ioctl+0x89/0xb0
[ 95.021865] __x64_sys_ioctl+0x42/0x60
[ 95.021901] do_syscall_64+0x6e/0x2c0
[ 95.021927] entry_SYSCALL_64_after_hwframe+0x44/0xa9
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200310142403.5953-1-chris@chris-wilson.co.uk
When being used across multiple real engines inside a virtual engine,
the intel_context.inflight is updated atomically, and so we must
annotate the racy read from outside the owning context.
[11142.482846] BUG: KCSAN: data-race in __execlists_submission_tasklet [i915] / __execlists_submission_tasklet [i915]
[11142.482867]
[11142.482878] write (marked) to 0xffff8881f257b5e0 of 8 bytes by interrupt on cpu 2:
[11142.483107] __execlists_submission_tasklet+0x1d33/0x2120 [i915]
[11142.483336] execlists_submission_tasklet+0xd3/0x170 [i915]
[11142.483355] tasklet_action_common.isra.0+0x42/0xa0
[11142.483371] __do_softirq+0xd7/0x2cd
[11142.483384] irq_exit+0xbe/0xe0
[11142.483401] do_IRQ+0x51/0x100
[11142.483424] ret_from_intr+0x0/0x1c
[11142.483446] do_idle+0x133/0x1f0
[11142.483465] cpu_startup_entry+0x14/0x16
[11142.483483] start_secondary+0x120/0x180
[11142.483498] secondary_startup_64+0xa4/0xb0
[11142.483512]
[11142.483528] read to 0xffff8881f257b5e0 of 8 bytes by interrupt on cpu 1:
[11142.483755] __execlists_submission_tasklet+0x14e/0x2120 [i915]
[11142.483981] execlists_submission_tasklet+0xd3/0x170 [i915]
[11142.483999] tasklet_action_common.isra.0+0x42/0xa0
[11142.484014] __do_softirq+0xd7/0x2cd
[11142.484028] do_softirq_own_stack+0x2a/0x40
[11142.484046] do_softirq.part.0+0x26/0x30
[11142.484071] __local_bh_enable_ip+0x46/0x50
[11142.484299] i915_gem_do_execbuffer+0x39c1/0x4e50 [i915]
[11142.484528] i915_gem_execbuffer2_ioctl+0x2c3/0x580 [i915]
[11142.484546] drm_ioctl_kernel+0xe4/0x120
[11142.484559] drm_ioctl+0x297/0x4c7
[11142.484572] ksys_ioctl+0x89/0xb0
[11142.484586] __x64_sys_ioctl+0x42/0x60
[11142.484610] do_syscall_64+0x6e/0x2c0
[11142.484627] entry_SYSCALL_64_after_hwframe+0x44/0xa9
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200310141320.24149-1-chris@chris-wilson.co.uk
The UNSLICE_UNIT_LEVEL_CLKGATE and UNSLICE_UNIT_LEVEL_CLKGATE2 registers
that we update in a few engine workarounds are not masked registers
(i.e., we don't have to write a mask bit in the top 16 bits when
updating one of the lower 16 bits). As such, these workarounds should
be applied via wa_write_or() rather than wa_masked_en()
v2:
- Rebase
Reported-by: Nick Desaulniers <ndesaulniers@google.com>
Reported-by: kernelci.org bot <bot@kernelci.org>
References: https://github.com/ClangBuiltLinux/linux/issues/918
Fixes: 50148a25f8 ("drm/i915/tgl: Move and restrict Wa_1408615072")
Fixes: 3551ff9287 ("drm/i915/gen11: Moving WAs to rcs_engine_wa_init()")
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200306171139.1414649-1-matthew.d.roper@intel.com
Be sure to wait for the vma to be in place before we tell the GPU to
execute from the wa batch. Since initialisation is mostly synchronous
(or rather at some point during start up we will need to sync anyway),
we can affort to do an explicit i915_vma_sync() during wa batch
construction rather than check for a required await on every context
switch. (We don't expect to change the wa bb at run time so paying the
cost once up front seems preferrable.)
Fixes: ee2413eeed ("drm/i915: Add mechanism to submit a context WA on ring submission")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200307122425.29114-1-chris@chris-wilson.co.uk
If the cacheline may still be busy, atomically mark it for future
release, and only if we can determine that it will never be used again,
immediately free it.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/1392
Fixes: ebece75392 ("drm/i915: Keep timeline HWSP allocated until idle across the system")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.2+
Link: https://patchwork.freedesktop.org/patch/msgid/20200306154647.3528345-1-chris@chris-wilson.co.uk
If we stop filling the ELSP due to an incompatible virtual engine
request, check if we should enable the timeslice on behalf of the queue.
This fixes the case where we are inspecting the last->next element when
we know that the last element is the last request in the execution queue,
and so decided we did not need to enable timeslicing despite the intent
to do so!
Fixes: 8ee36e048c ("drm/i915/execlists: Minimalistic timeslicing")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200306113012.3184606-1-chris@chris-wilson.co.uk
This workaround is to disable FF DOP Clock gating. The fix
in B0 was backed out due to timing reasons and decided to
be made permanent.
Bspec: 52890
Signed-off-by: Swathi Dhanavanthri <swathi.dhanavanthri@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200305181204.28856-1-swathi.dhanavanthri@intel.com
Check the edge case where batch_start_offset sits exactly on the batch
size.
v2: add new range_overflows variant to capture the special case where
the size is permitted to be zero, like with batch_len.
v3: other way around. the common case is the exclusive one which should
just be >=, with that we then just need to convert the three odd ball
cases that don't apply to use the new inclusive _end version.
Testcase: igt/gem_exec_params/invalid-batch-start-offset
Fixes: 0b5372727b ("drm/i915/cmdparser: Use cached vmappings")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200306094735.258285-1-matthew.auld@intel.com
On gen7 and gen7.5 devices, there could be leftover data residuals in
EU/L3 from the retiring context. This patch introduces workaround to clear
that residual contexts, by submitting a batch buffer with dedicated HW
context to the GPU with ring allocation for each context switching.
This security mitigation changes does not triggers any performance
regression. Performance is on par with current drm-tips.
v2: Add igt generated header file for CB kernel assembled with Mesa tool
and addressed use of Kernel macro for ptr_align comment.
v3: Resolve Sparse warnings with newly generated, and imported CB
kernel.
v4: Include new igt generated CB kernel for gen7 and gen7.5. Also
add code formatting and compiler warnings changes (Chris Wilson)
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Cc: Chris Wilson <chris.p.wilson@intel.com>
Cc: Balestrieri Francesco <francesco.balestrieri@intel.com>
Cc: Bloomfield Jon <jon.bloomfield@intel.com>
Cc: Dutt Sudeep <sudeep.dutt@intel.com>
Acked-by: Chris Wilson <chris@chris-wilso.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200306000957.2836150-2-chris@chris-wilson.co.uk
This patch adds framework to submit an arbitrary batchbuffer on each
context switch to clear residual state for render engine on Gen7/7.5
devices.
The idea of always emitting the context and vm setup around each request
is primary to make reset recovery easy, and not require rewriting the
ringbuffer. As each request would set up its own context, leaving it to
the HW to notice and elide no-op context switches, we could restart the
ring at any point, and reorder the requests freely.
However, to avoid emitting clear_residuals() between consecutive requests
in the ringbuffer of the same context, we do want to track the current
context in the ring. In doing so, we need to be careful to only record a
context switch when we are sure the next request will be emitted.
This security mitigation change does not trigger any performance
regression. Performance is on par with current mainline/drm-tip.
v2: Update vm_alias params to point to correct address space "vm" due to
changes made in the patch "f21613797bae98773"
v3-v4: none
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Balestrieri Francesco <francesco.balestrieri@intel.com>
Cc: Bloomfield Jon <jon.bloomfield@intel.com>
Cc: Dutt Sudeep <sudeep.dutt@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200306000957.2836150-1-chris@chris-wilson.co.uk
Enable FtrPerCtxtPreemptionGranularityControl bit and select thread-
group as the default preemption level.
v2:
* Remove register whitelisting (Rafael, Tony).
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: piotr.zdunowski@intel.com
Cc: michal.mrozek@intel.com
Cc: Tony Ye <tony.ye@intel.com>
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Acked-by: Rafael Antognolli <rafael.antognolli@intel.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Tony Ye <tony.ye@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200304153144.10675-1-tvrtko.ursulin@linux.intel.com
Trying to use i915_request_skip() prior to i915_request_add() causes us
to try and fill the ring upto request->postfix, which has not yet been
set, and so may cause us to memset() past the end of the ring.
Instead of skipping the request immediately, just flag the error on the
request (only accepting the first fatal error we see) and then clear the
request upon submission.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200304121849.2448028-1-chris@chris-wilson.co.uk
Following the changes in the previous patch
"drm/i915/gen11: Moving WAs to rcs_engine_wa_init()" also moving TGL
Wa_1408615072 to rcs_engine_wa_init() this way after a engine
reset it will be reapplied also restricting it to A0 as it is fixed in
B0 stepping.
BSpec: 52890
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200302231421.224322-2-jose.souza@intel.com
This are register of render engine, so after a render reset those
would return to the default value and init_clock_gating() is not
called for single engine reset.
So here moving it rcs_engine_wa_init() that will guarantee that this
WAs will not be lost.
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200302231421.224322-1-jose.souza@intel.com
Static code analysis tool identified struct lrc_timestamp data as being
uninitialized and then data.ce[] is being checked for NULL/negative
value in the error path. Initializing data variable fixes the issue.
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Aditya Swarup <aditya.swarup@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200303142347.15696-1-aditya.swarup@intel.com
As we have pinned the timeline (using tl->active_count), we can safely
drop the tl->mutex as we wait for what we believe to be the final
request on that timeline. This is useful for ensuring that we do not
block the engine heartbeat by hogging the kernel_context's timeline on a
dead GPU.
References: https://gitlab.freedesktop.org/drm/intel/issues/1364
Fixes: 058179e72e ("drm/i915/gt: Replace hangcheck by heartbeats")
Fixes: f33a8a5160 ("drm/i915: Merge wait_for_timelines with retire_request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200303140009.1494819-1-chris@chris-wilson.co.uk
Add intel_vgpu_register() abstraction, rename i915_detect_vgpu() to
intel_vgpu_detect() to match other function naming, un-inline
intel_vgpu_active(), intel_vgpu_has_full_ppgtt() and
intel_vgpu_has_huge_gtt() to reduce header interdependencies.
The i915_vgpu.[ch] filename and intel_vgpu_ prefix discrepancy remains.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227144408.24345-1-jani.nikula@intel.com
Update to the latest available TGL HuC, which includes changes required
by the media team.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tony Ye <tony.ye@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Tony Ye <tony.ye@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200229012042.27487-1-daniele.ceraolospurio@intel.com
Different issues with the same fix, so justing adding
Wa_1409142259, Wa_1409252684, Wa_1409217633, Wa_1409207793,
Wa_1409178076 and 1408979724 to the comment so other devs can check if
this Was were implemetend with a simple grep.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227220101.321671-8-jose.souza@intel.com
According to BSpec. Wa_1606931601 applies for all TGL steppings.
This patch moves the WA implementation out of A0 only block of
rcs_engine_wa_init().
The WA is has also been referred to by an alternate name
Wa_1607090982.
Bspec: 46045, 52890
Fixes: 3873fd1a43 ("drm/i915: Use engine wa list for Wa_1607090982")
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227220101.321671-4-jose.souza@intel.com
Disable Push Constant buffer addition for TGL.
v2: typos, add additional Wa reference
v3: use REG_BIT macro, move to rcs_engine_wa_init, clean up commit
message.
Bspec: 52890
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227220101.321671-3-jose.souza@intel.com
This will whitelist the HIZ_CHICKEN register so mesa can disable the
optimizations and avoid hang when using D16_UNORM.
v2: moved to the right place and used the right function() (Chris)
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227220101.321671-2-jose.souza@intel.com
This workaround the CS not done issue on PIPE_CONTROL.
v2:
- replaced BIT() by REG_BIT() in all GEN7_ROW_CHICKEN2() bits
- shortened the name of the new bit
BSpec: 52890
BSpec: 46218
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227220101.321671-1-jose.souza@intel.com
We monitor the health of the system via periodic heartbeat pulses. The
pulses also provide the opportunity to perform garbage collection.
However, we interpret an incomplete pulse (a missed heartbeat) as an
indication that the system is no longer responsive, i.e. hung, and
perform an engine or full GPU reset. Given that the preemption
granularity can be very coarse on a system, we let the sysadmin override
our legacy timeouts which were "optimised" for desktop applications.
The heartbeat interval can be adjusted per-engine using,
/sys/class/drm/card?/engine/*/heartbeat_interval_ms
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-7-chris@chris-wilson.co.uk
After initialising a preemption request, we give the current resident a
small amount of time to vacate the GPU. The preemption request is for a
higher priority context and should be immediate to maintain high
quality of service (and avoid priority inversion). However, the
preemption granularity of the GPU can be quite coarse and so we need a
compromise.
The preempt timeout can be adjusted per-engine using,
/sys/class/drm/card?/engine/*/preempt_timeout_ms
and can be disabled by setting it to 0.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-6-chris@chris-wilson.co.uk
When we allow ourselves to sleep before a GPU reset after disabling
submission, even for a few milliseconds, gives an innocent context the
opportunity to clear the GPU before the reset occurs. However, how long
to sleep depends on the typical non-preemptible duration (a similar
problem to determining the ideal preempt-reset timeout or even the
heartbeat interval). As this seems of a hard policy decision, punt it to
userspace.
The timeout can be adjusted using
/sys/class/drm/card?/engine/*/stop_timeout_ms
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-5-chris@chris-wilson.co.uk
We busywait on an inflight request (one that is currently executing on
HW, and so might complete quickly) prior to setting up an interrupt and
sleeping. The trade off is that we keep an expensive CPU core busy in
order to avoid wake up latency: where that trade off should lie is best
left to the sysadmin.
The busywait mechanism can be compiled out with
./scripts/config --set-val DRM_I915_SPIN_REQUEST 0
The maximum busywait duration can be adjusted per-engine using,
/sys/class/drm/card?/engine/*/ms_busywait_duration_ns
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-4-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.
The timeslicing mechanism can be compiled out with
./scripts/config --set-val DRM_I915_TIMESLICE_DURATION 0
The timeslice duration can be adjusted per-engine using,
/sys/class/drm/card?/engine/*/timeslice_duration_ms
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-3-chris@chris-wilson.co.uk
Use the per-engine sysfs directory to let userspace discover the
mmio_base of each engine. Prior to recent generations, the user
accessible registers on each engine are at a fixed offset relative to
each engine -- but require absolute addressing. As the absolute address
depends on the actual physical engine, this is not always possible to
determine from userspace (for example icl may expose vcs1 or vcs2 as the
second vcs engine). Make this easy for userspace to discover by
providing the mmio_base in sysfs.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-2-chris@chris-wilson.co.uk
Preliminary stub to add engines underneath /sys/class/drm/cardN/, so
that we can expose properties on each engine to the sysadmin.
To start with we have basic analogues of the i915_query ioctl so that we
can pretty print engine discovery from the shell, and flesh out the
directory structure. Later we will add writeable sysadmin properties such
as per-engine timeout controls.
An example tree of the engine properties on Braswell:
/sys/class/drm/card0
└── engine
├── bcs0
│ ├── capabilities
│ ├── class
│ ├── instance
│ ├── known_capabilities
│ └── name
├── rcs0
│ ├── capabilities
│ ├── class
│ ├── instance
│ ├── known_capabilities
│ └── name
├── vcs0
│ ├── capabilities
│ ├── class
│ ├── instance
│ ├── known_capabilities
│ └── name
└── vecs0
├── capabilities
├── class
├── instance
├── known_capabilities
└── name
v2: Include stringified capabilities
v3: Include all known capabilities for futureproofing.
v4: Combine the two caps loops into one
v5: Hide underneath Kconfig.unstable for wider discussion
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Tested-by: Steve Carbonari <steven.carbonari@intel.com>
Reviewed-by: Steve Carbonari <steven.carbonari@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200228131716.3243616-1-chris@chris-wilson.co.uk
Check that we can recover if the LRC is totally corrupted. Based on a
very simple theory that anything that can be adjusted via the context
(i.e. on behalf of the user), should be under the purview of the
per-engine-reset.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227085723.1961649-13-chris@chris-wilson.co.uk
Pull the final atomic_dec of vm->open (marking the vm as closed)
underneath the same vm->mutex as used to close it. This is required to
correctly serialise with attempting to reuse the vma as the vm is closed
by a second thread.
References: 00de702c6c ("drm/i915: Check that the vma hasn't been closed before we insert it")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227085723.1961649-10-chris@chris-wilson.co.uk
On TGL, bits 2-4 in the GGTT PTE are not ignored anymore and are
instead used for some extra VT-d capabilities. We don't (yet?) have
support for those capabilities, but, given that we shared the pte_encode
function betweed GGTT and PPGTT, we still set those bits to the PPGTT
PPAT values. The DMA engine gets very confused when those bits are
set while the iommu is enabled, leading to errors. E.g. when loading
the GuC we get:
[ 9.796218] DMAR: DRHD: handling fault status reg 2
[ 9.796235] DMAR: [DMA Write] Request device [00:02.0] PASID ffffffff fault addr 0 [fault reason 02] Present bit in context entry is clear
[ 9.899215] [drm:intel_guc_fw_upload [i915]] *ERROR* GuC firmware signature verification failed
To fix this, just have dedicated gen8_pte_encode function per type of
gtt. Also, explicitly set vm->pte_encode for gen8_ppgtt, even if we
don't use it, to make sure we don't accidentally assign it to the GGTT
one, like we do for gen6_ppgtt, in case we need it in the future.
Reported-by: "Sodhi, Vunny" <vunny.sodhi@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200226185657.26445-1-daniele.ceraolospurio@intel.com
Wa_1608008084 is an additional WA that applies to writes on FF_MODE2
register. We can't read it back either from CPU or GPU. Since the other
bits should be 0, recommendation to handle Wa_1604555607 is to actually
just write the timer value.
Do a write only and don't try to read it, neither before or after
the WA is applied.
Fixes: ff690b2111 ("drm/i915/tgl: Implement Wa_1604555607")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200224191258.15668-1-lucas.demarchi@intel.com
The #include has been splattered all over the place, but there are
precious few places, all .c files, that actually need it.
v2: remove leftover double newlines
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200225133131.3301-1-jani.nikula@intel.com
Some DSI and VBT pending patches from Hans will apply
cleanly and with less ugly conflicts if they are rebuilt
on top of other patches that recently landed on drm-next.
Reference: https://patchwork.freedesktop.org/series/70952/
Cc: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com
Variable dw is being initialized with a value that is never read,
it is assigned a new value later on. The assignment is redundant
and can be removed.
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200222134755.134209-1-colin.king@canonical.com
Upon unregistering the user interface, we mark the GPU as wedged to
ensure we push no new work to the GPU, and to flush all current work
from the GPU. Move this call to the GT backend.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200221235135.2883006-1-chris@chris-wilson.co.uk
We are quite trigger happy in cleaning up the firmware blobs, as we do
so from several error/fini paths in GuC/HuC/uC code. We do have the
__uc_cleanup_firmwares cleanup function, which unwinds
__uc_fetch_firmwares and is already called both from the error path of
gem_init and from gem_driver_release, so let's stop cleaning up from
all the other paths.
The fact that we're not cleaning the firmware immediately means that
we can't consider firmware availability as an indication of
initialization success. A "LOADABLE" status has been added to
indicate that the initialization was successful, to be used to
selectively load HuC only if HuC init has completed (HuC init failure
is not considered a fatal error).
v2: s/ready_to_load/loadable (Michal), only run guc/huc_fini if the
fw is in loadable state
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com> #v1
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-9-daniele.ceraolospurio@intel.com
Now that we can differentiate wants vs uses GuC/HuC, intel_uc_init is
restricted to running only if we have successfully fetched the required
blob(s) and are committed to using the microcontroller(s).
The only remaining thing that can go wrong in uc_init is the allocation
of GuC/HuC related objects; if we get such a failure better to bail out
immediately instead of wedging later, like we do for e.g.
intel_engines_init, since without objects we can't use the HW, including
not being able to attempt the firmware load.
While at it, remove the unneeded fw_cleanup call (this is handled
outside of gt_init) and add a probe failure injection point for testing.
Also, update the logs for <g/h>uc_init failures to probe_failure() since
they will cause the driver load to fail.
Signed-off-by: Daniele 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: Fernando Pacheco <fernando.pacheco@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-8-daniele.ceraolospurio@intel.com
To be able to differentiate the before and after of our commitment to
GuC submission, which will be used in follow-up patches to early set-up
the submission structures.
v2: move functions to guc_submission.h (Michal)
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-7-daniele.ceraolospurio@intel.com
To be able to setup GuC submission functions during engine init we need
to commit to using GuC as soon as possible.
Currently, the only thing that can stop us from using the
microcontrollers once we've fetched the blobs is a fundamental
error (e.g. OOM); given that if we hit such an error we can't really
fall-back to anything, we can "officialize" the FW fetching completion
as the moment at which we're committing to using GuC.
To better differentiate this case, the uses_guc check, which indicates
that GuC is supported and was selected in modparam, is renamed to
wants_guc and a new uses_guc is introduced to represent the case were
we're committed to using the GuC. Note that uses_guc does still not imply
that the blob is actually loaded on the HW (is_running is the check for
that). Also, since we need to have attempted the fetch for the result
of uses_guc to be meaningful, we need to make sure we've moved away
from INTEL_UC_FIRMWARE_SELECTED.
All the GuC changes have been mirrored on the HuC for coherency.
v2: split fetch return changes and new macros to their own patches,
support HuC only if GuC is wanted, improve "used" state
description (Michal)
v3: s/wants_huc/uses_huc in uc_init_wopcm
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.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: Fernando Pacheco <fernando.pacheco@intel.com> #v1
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-6-daniele.ceraolospurio@intel.com
We want to map uC-level checks to GuC/HuC-level ones. The mapping from
the uC state to the GuC/HuC one follows the same pattern for all the
functions:
uc_xxx_guc() -> guc_is_yyy()
So we can easily use a macro to autogenerate the functions via macros by
passing in the 2 mapped states.
v2: Split this change to its own patch (Michal)
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-5-daniele.ceraolospurio@intel.com
In a follow up patch we will rely on the fact that the status always
moves away from "SELECTED" after the fetch is attempted to decide what
to do with the GuC.
v2: Split this change to its own patch (Michal)
Signed-off-by: Daniele 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: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-4-daniele.ceraolospurio@intel.com
use intel_uc_uses_guc_submission() directly instead, to be consistent in
the way we check what we want to do with the GuC.
v2: do not go through ctx->vm->gt, use i915->gt instead
Signed-off-by: Daniele 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: Michal Wajdeczko <michal.wajdeczko@intel.com> #v1
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-3-daniele.ceraolospurio@intel.com
use intel_uc_uses_guc() directly instead, to be consistent in the way we
check what we want to do with the GuC.
v2: split guc_log_info changes to their own patch (Michal)
Signed-off-by: Daniele 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: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218223327.11058-2-daniele.ceraolospurio@intel.com
While we know that the waiters cannot disappear as we walk our list
(only that they might be added), the same cannot be said for our
signalers as they may be completed by the HW and retired as we process
this request. Ergo we need to use rcu to protect the list iteration and
remember to mark up the list_del_rcu.
v2: Mark the deps as safe-for-rcu
Fixes: 793c226173 ("drm/i915/gt: Protect execlists_hold/unhold from new waiters")
Fixes: 32ff621fd7 ("drm/i915/gt: Allow temporary suspension of inflight requests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200220075025.1539375-1-chris@chris-wilson.co.uk
For dgfx, we do not need to reconfigure the IA/ring frequencies of the
main processors as they are distinct devices.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200219130119.1457693-1-chris@chris-wilson.co.uk
Currently, we check that a new context has a clear set of general
purpose registers. Add a little bit of hostility by preempting our new
context and re-poisoning the GPR to ensure that there is no context
leakage from preemption.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200219123418.1447428-1-chris@chris-wilson.co.uk
On dgfx, we only use l3cc and not mocs, but we share the table
containing both register definitions with Tigerlake. This confuses our
selftest that verifies that both sets of registers do contain the values
in our tables after various events (idling, reset, activity etc).
When constructing the table of register definitions, also include the
flags for which registers are valid so that information is computed
centrally and available to all callers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Brian Welty <brian.welty@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218162150.1300405-10-chris@chris-wilson.co.uk
Always flush the tasklet if we have pending submissions in
wait_for_submit(), so that even if we see the HW has started before we
process its ack, when we return the execlists state is well defined.
Fixes: 06289949b8 ("drm/i915/selftests: Check for any sign of request starting in wait_for_submit()")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218211215.1336341-1-chris@chris-wilson.co.uk
We only want to wait until the request has been submitted at least once;
that is it is either in flight, or has been.
References: fcf7df7aae ("drm/i915/selftests: Check for the error interrupt before we wait!")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200218141305.1258394-1-chris@chris-wilson.co.uk
It's not clear whether this workaround is final yet, but the BSpec
indicates that userspace needs to set bit 9 of this register on demand:
"To avoid sporadic corruptions “Set 0x7010[9] when Depth Buffer
Surface Format is D16_UNORM , surface type is not NULL & 1X_MSAA"
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2501
Signed-off-by: Rafael Antognolli <rafael.antognolli@intel.com>
[mattrope: Tweaked comment while applying]
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200212191728.25227-1-rafael.antognolli@intel.com
Without selftests enabled, I915_SELFTEST_ONLY becomes a dummy,
generating a bare '0'. This causes the compiler to complain about a
useless line, and while we could use I915_SELFTEST_DECLARE instead, it
is a bit messier. Move the selftest-only code to a helper and make that
conditional on having selftests enabled.
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200217095835.599827-1-chris@chris-wilson.co.uk
GPU saves accumulated context runtime (in CS timestamp units) in PPHWSP
which will be useful for us in cases when we are not able to track context
busyness ourselves (like with GuC). Keep a copy of this in struct
intel_context from where it can be easily read even if the context is not
pinned.
v2:
(Chris)
* Do not store pphwsp address in intel_context.
* Log CS wrap-around.
* Simplify calculation by relying on integer wraparound.
v3:
* Include total/avg in traces and error state for debugging
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200216133620.394962-1-chris@chris-wilson.co.uk
Sometimes the error interrupt can fire even before we have seen the
request go active -- in which case, we end up waiting until the timeout
as the request is already completed. Double check for this case!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200214120659.3888735-1-chris@chris-wilson.co.uk
-----BEGIN PGP SIGNATURE-----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=BZol
-----END PGP SIGNATURE-----
Merge tag 'drm-intel-next-fixes-2020-02-13' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes
drm/i915 fixes for v5.6-rc2
Most of these were aimed at a "next fixes" pull already during the merge
window, but there were issues with the baseline I used, which resulted
in a lot of issues in CI. I've regenerated this stuff piecemeal now,
adding gradually to it, and it seems healthy now.
Due to the issues this is much bigger than I'd like. But it was
obviously necessary to take the time to ensure it's not garbage...
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/878sl6yfrn.fsf@intel.com
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: 5ba32c7be8 ("drm/i915/execlists: Always force a context reload when rewinding RING_TAIL")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200213140150.3639027-1-chris@chris-wilson.co.uk
With debugging turned off, we have to tell the compiler not to warn
about the unused debug locals.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200213081217.3107410-1-chris@chris-wilson.co.uk
This is in mcr range of register, thus we can only verify
it through mmio. Use engine wa list with mcr range verification
skip.
Fixes: 0db1a5f870 ("drm/i915: Implement Wa_1607090982")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200212165707.11143-1-mika.kuoppala@linux.intel.com
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: ad18ba7b5e ("drm/i915/execlists: Offline error capture")
Testcase: igt/gem_exec_balancer/hang
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200122140243.495621-2-chris@chris-wilson.co.uk
(cherry picked from commit 989df3a7bd)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
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: c3f1ed90e6 ("drm/i915/gt: Allow temporary suspension of inflight requests")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/997
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200122140243.495621-1-chris@chris-wilson.co.uk
(cherry picked from commit 4ba5c086a1)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Currently, we skip error capture upon forced preemption. We apply forced
preemption when there is a higher priority request that should be
running but is being blocked, and we skip inline error capture so that
the preemption request is not further delayed by a user controlled
capture -- extending the denial of service.
However, preemption reset is also used for heartbeats and regular GPU
hangs. By skipping the error capture, we remove the ability to debug GPU
hangs.
In order to capture the error without delaying the preemption request
further, we can do an out-of-line capture by removing the guilty request
from the execution queue and scheduling a worker to dump that request.
When removing a request, we need to remove the entire context and all
descendants from the execution queue, so that they do not jump past.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/738
Fixes: 3a7a92aba8 ("drm/i915/execlists: Force preemption")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-3-chris@chris-wilson.co.uk
(cherry picked from commit 748317386a)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
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/738
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-2-chris@chris-wilson.co.uk
(cherry picked from commit 32ff621fd7)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
If we keep track of when the i915_request.sched.link is on the HW
runlist, or in the priority queue we can simplify our interactions with
the request (such as during rescheduling). This also simplifies the next
patch where we introduce a new in-between list, for requests that are
ready but neither on the run list or in the queue.
v2: Update i915_sched_node.link explanation for current usage where it
is a link on both the queue and on the runlists.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-1-chris@chris-wilson.co.uk
(cherry picked from commit 672c368f93)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Apply vast quantities of poison and not tell anyone to see if we fall
for the trap of using a stale RING_HEAD.
References: 42827350f7 ("drm/i915/gt: Avoid resetting ring->head outside of its timeline mutex")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika 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: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika 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: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika 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: 0881954965 ("drm/i915: Introduce intel_context.pin_mutex for pin management")
Fixes: e5dadff4b0 ("drm/i915: Protect request retirement with timeline->mutex")
References: f3c0efc9fe ("drm/i915/execlists: Leave resetting ring to intel_ring")
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: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200211120131.958949-1-chris@chris-wilson.co.uk
We need to allow concurrent intel_context_unpin, which means avoiding
doing destructive operations like intel_ring_reset(). This was already
fixed for intel_ring_unpin() in commit 0725d9a318 ("drm/i915/gt: Make
intel_ring_unpin() safe for concurrent pint"), but I overlooked that
execlists_context_unpin() also made the same mistake.
Reported-by: Matthew Brost <matthew.brost@intel.com>
Fixes: 8413502238 ("drm/i915/gt: Drop mutex serialisation between context pin/unpin")
References: 0725d9a318 ("drm/i915/gt: Make intel_ring_unpin() safe for concurrent pint")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200115175829.2761329-1-chris@chris-wilson.co.uk
(cherry picked from commit f3c0efc9fe)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
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: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200209230838.361154-2-chris@chris-wilson.co.uk
In converting over to using set_bit()/test_bit(), when manually
inspecting the rq->fence.flags, we need to use BIT().
Fixes: e1c31fb5dd ("drm/i915: Merge i915_request.flags with i915_request.fence.flags")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200115122509.2673075-1-chris@chris-wilson.co.uk
(cherry picked from commit 72ff2b8d5f)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Add a i915_vma to the mock_engine/mock_ring so that the core code can
always assume the presence of ring->vma.
Fixes: 8ccfc20a7d ("drm/i915/gt: Mark ring->vma as active while pinned")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200114160030.2468927-1-chris@chris-wilson.co.uk
(cherry picked from commit b63b4feaef)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Recording the frequent inspection of CSB head/tail when there is
expected to be no update adds noise to the debug trace. (Not entirely
useless, but since we know the sequence of function calls, we can
surmise the function was called -- so redundant.)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200209131922.180287-2-chris@chris-wilson.co.uk
In eliminating the recursion from walking the tree of signalers/waiters
for processing the hold/unhold operations, a crucial error crept in
where we looked at the parent request and not the list element when
processing the list.
Brown paper bag, much?
Closes: https://gitlab.freedesktop.org/drm/intel/issues/1166
Fixes: 32ff621fd7 ("drm/i915/gt: Allow temporary suspension of inflight requests")
Fixes: 748317386a ("drm/i915/execlists: Offline error capture")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200209131922.180287-1-chris@chris-wilson.co.uk
We have switched from tail manipulation to forced context restore
to implement WaIdleLiteRestore. Remove the old defines and comments.
Note: we still do emit the WA tail, and use it as our first attempt to
avoid forcing a full-restore instead of a lite-restore, we just have a
much stronger backup mechanism for repeated preemptions.
References: f26a9e959a ("drm/i915/gt: Detect if we miss WaIdleLiteRestore")
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200203163312.15475-1-mika.kuoppala@linux.intel.com
If we rewind the RING_TAIL on a context, due to a preemption event, we
must force the context restore for the RING_TAIL update to be properly
handled. Rather than note which preemption events may cause us to rewind
the tail, compare the new request's tail with the previously submitted
RING_TAIL, as it turns out that timeslicing was causing unexpected
rewinds.
<idle>-0 0d.s2 1280851190us : __execlists_submission_tasklet: 0000:00:02.0 rcs0: expired last=130:4698, prio=3, hint=3
<idle>-0 0d.s2 1280851192us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 66:119966, current 119964
<idle>-0 0d.s2 1280851195us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4698, current 4695
<idle>-0 0d.s2 1280851198us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4696, current 4695
^---- Note we unwind 2 requests from the same context
<idle>-0 0d.s2 1280851208us : __i915_request_submit: 0000:00:02.0 rcs0: fence 130:4696, current 4695
<idle>-0 0d.s2 1280851213us : __i915_request_submit: 0000:00:02.0 rcs0: fence 134:1508, current 1506
^---- But to apply the new timeslice, we have to replay the first request
before the new client can start -- the unexpected RING_TAIL rewind
<idle>-0 0d.s2 1280851219us : trace_ports: 0000:00:02.0 rcs0: submit { 130:4696*, 134:1508 }
synmark2-5425 2..s. 1280851239us : process_csb: 0000:00:02.0 rcs0: cs-irq head=5, tail=0
synmark2-5425 2..s. 1280851240us : process_csb: 0000:00:02.0 rcs0: csb[0]: status=0x00008002:0x00000000
^---- Preemption event for the ELSP update; note the lite-restore
synmark2-5425 2..s. 1280851243us : trace_ports: 0000:00:02.0 rcs0: preempted { 130:4698, 66:119966 }
synmark2-5425 2..s. 1280851246us : trace_ports: 0000:00:02.0 rcs0: promote { 130:4696*, 134:1508 }
synmark2-5425 2.... 1280851462us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4700, current 4695
synmark2-5425 2.... 1280852111us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4702, current 4695
synmark2-5425 2.Ns1 1280852296us : process_csb: 0000:00:02.0 rcs0: cs-irq head=0, tail=2
synmark2-5425 2.Ns1 1280852297us : process_csb: 0000:00:02.0 rcs0: csb[1]: status=0x00000814:0x00000000
synmark2-5425 2.Ns1 1280852299us : trace_ports: 0000:00:02.0 rcs0: completed { 130:4696!, 134:1508 }
synmark2-5425 2.Ns1 1280852301us : process_csb: 0000:00:02.0 rcs0: csb[2]: status=0x00000818:0x00000040
synmark2-5425 2.Ns1 1280852302us : trace_ports: 0000:00:02.0 rcs0: completed { 134:1508, 0:0 }
synmark2-5425 2.Ns1 1280852313us : process_csb: process_csb:2336 GEM_BUG_ON(!i915_request_completed(*execlists->active) && !reset_in_progress(execlists))
Fixes: 8ee36e048c ("drm/i915/execlists: Minimalistic timeslicing")
Referenecs: 82c69bf586 ("drm/i915/gt: Detect if we miss WaIdleLiteRestore")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Link: https://patchwork.freedesktop.org/patch/msgid/20200207211452.2860634-1-chris@chris-wilson.co.uk
If a request is being re-run after an innocent reset, it is marked as
-EAGAIN. So only skip an engine reset if the request is marked as -EIO.
Testcase: igt/gem_ctx_exec/basic-nohangcheck
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200207161602.2838218-1-chris@chris-wilson.co.uk
SIMD16 with Src0 scalar might conflict between Src1/Src2 and cause
GRF read issue. Workaround this issue by setting bit 14 in 0xe4f4
which will disable early read/src swap of Src0.
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200207155138.30978-2-mika.kuoppala@linux.intel.com
We set up a dummy ring in order to measure the size we require for our
breadcrumb emission, so that we don't have to manually count dwords! We
can pass in the kernel_context to use for this so that if required it is
known for the breadcrumb emitter, and we can reuse some details from the
kernel_context to reduce the number of temporaries we have to mock.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200207125827.2787472-1-chris@chris-wilson.co.uk
We are sanitizing firmware status and old mmio message, but
we forget to sanitize CT status.
Fixes: e85de17703 ("drm/i915/guc: Introduce guc_is_ready")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200207131938.2787828-1-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
As we may add new waiters to a request as it is being run, we need to
mark the list iteration as being safe for concurrent addition.
v2: Mika spotted that we used the same trick for signalers_list, so warn
the compiler about the lockless walk there as well.
Fixes: 32ff621fd7 ("drm/i915/gt: Allow temporary suspension of inflight requests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200207110213.2734386-1-chris@chris-wilson.co.uk
Virtual engines are fleeting. They carry a reference count and may be freed
when their last request is retired. This makes them unsuitable for the
task of housing engine->retire.work so assert that it is not used.
Tvrtko tracked down an instance where we did indeed violate this rule.
In virtual_submit_request, we flush a completed request directly with
__i915_request_submit and this causes us to queue that request on the
veng's breadcrumb list and signal it. Leading us down a path where we
should not attach the retire.
Reported-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: dc93c9b693 ("drm/i915/gt: Schedule request retirement when signaler idles")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200206204915.2636606-1-chris@chris-wilson.co.uk
Always prime the page table registers before starting the ring. Even
though we will update these to the per-context page tables during
dispatch, it is prudent to ensure that the registers always point to a
valid PD.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200206014439.2137800-2-chris@chris-wilson.co.uk
As only the display codes tries to pin its preallocated framebuffer into
an exact location in the GGTT, remove the convenience function and make
the pin management explicit in the display code. Then throughout the
display management, we track the framebuffer and its plane->vma; with
less single purpose code and ready for first class i915_vma.
In doing so, this should fix the BUG_ON(vma->pages) on fi-kbl-soraka.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200204094801.877288-2-chris@chris-wilson.co.uk
Exercise the seqno wrap paths on the kernel context to provide a small
amount of sanity checking and ensure that they are visible to lockdep.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200204094102.876636-1-chris@chris-wilson.co.uk
On seqno rollover, we need to allocate ourselves a new cacheline. This
might incur grabbing a new page and pinning it into the GGTT, with some
rather unfortunate lockdep implications.
To avoid a mutex, and more specifically pinning in the GGTT from inside
the kernel context being used to flush the GGTT in emergencies, we will
likely need to lift the next-cacheline allocation to a pre-reservation.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200203094152.4150550-3-chris@chris-wilson.co.uk
Now that intel_engine_apply_workarounds is called on all gens, we can
use the engine workaround lists for pre-gen8 workarounds as well to be
consistent in the way we handle and dump the WAs.
v2: Ignore the sanity check of MI_MODE on Broadwater, for whatever reason
it is not sticking.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200201194004.3622493-1-chris@chris-wilson.co.uk
A masked register does not need rmw to update, and it is best not to use
such a sequence.
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200131235035.3522102-1-chris@chris-wilson.co.uk
The workarounds are a common "feature" across gens and submission
mechanisms and we already call the other WA related functions from
common engine ones (<setup/cleanup>_common), so it makes sense to
do the same with WA application. Medium-term, This will help us
reduce the duplication once the GuC resume function is added, but short
term it will also allow us to use the workaround lists for pre-gen8
engine workarounds.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200131075716.2212299-2-chris@chris-wilson.co.uk
We already have guc_is_running function, but it only reflects
firmware status, while to fully use GuC we need to know if we've
already established communication with it.
v2: also s/intel_guc_is_running/intel_guc_is_fw_running (Chris)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200131153706.109528-1-michal.wajdeczko@intel.com
In the rare cases where we are using the global GGTT for execution in
the selftests, we have marked them with PIN_USER knowing that they will
be bound as PIN_GLOBAL as well. However, we need to catch the extra flag
in deciding to use the async worker for such binds as well.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200131081543.2251298-1-chris@chris-wilson.co.uk
On Braswell and Broxton (also known as Valleyview and Apollolake), we
need to serialise updates of the GGTT using the big stop_machine()
hammer. This has the side effect of appearing to lockdep as a possible
reclaim (since it uses the cpuhp mutex and that is tainted by per-cpu
allocations). However, we want to use vm->mutex (including ggtt->mutex)
from within the shrinker and so must avoid such possible taints. For this
purpose, we introduced the asynchronous vma binding and we can apply it
to the PIN_GLOBAL so long as take care to add the necessary waits for
the worker afterwards.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/211
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200130181710.2030251-3-chris@chris-wilson.co.uk
The i915_ggtt now sits beneath gt/ outside of the auspices of gem/ and
should be given a fresh name to reflect that. We also want to give it a
name that reflects its role in the system suspend/resume, with the
intention of pulling together all the GGTT operations (e.g. restoring
the fence registers once they are pulled under gt/intel_ggtt_detiler.c)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Rreviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200130181710.2030251-2-chris@chris-wilson.co.uk
uapi:
- dma-buf heaps added (and fixed)
- command line add support for panel oreientation
- command line allow overriding penguin count
drm:
- mipi dsi definition updates
- lockdep annotations for dma_resv
- remove dma-buf kmap/kunmap support
- constify fb_ops in all fbdev drivers
- MST fix for daisy chained hotplug-
- CTA-861-G modes with VIC >= 193 added
- fix drm_panel_of_backlight export
- LVDS decoder support
- more device based logging support
- scanline alighment for dumb buffers
- MST DSC helpers
scheduler:
- documentation fixes
- job distribution improvements
panel:
- Logic PD type 28 panel support
- Jimax8729d MIPI-DSI
- igenic JZ4770
- generic DSI devicetree bindings
- sony acx424AKP panel
- Leadtek LTK500HD1829
- xinpeng XPP055C272
- AUO B116XAK01
- GiantPlus GPM940B0
- BOE NV140FHM-N49
- Satoz SAT050AT40H12R2
- Sharp LS020B1DD01D panels.
ttm:
- use blocking WW lock
i915:
- hw/uapi state separation
- Lock annotation improvements
- selftest improvements
- ICL/TGL DSI VDSC support
- VBT parsing improvments
- Display refactoring
- DSI updates + fixes
- HDCP 2.2 for CFL
- CML PCI ID fixes
- GLK+ fbc fix
- PSR fixes
- GEN/GT refactor improvments
- DP MST fixes
- switch context id alloc to xarray
- workaround updates
- LMEM debugfs support
- tiled monitor fixes
- ICL+ clock gating programming removed
- DP MST disable sequence fixed
- LMEM discontiguous object maps
- prefaulting for discontiguous objects
- use LMEM for dumb buffers if possible
- add LMEM mmap support
amdgpu:
- enable sync object timelines for vulkan
- MST atomic routines
- enable MST DSC support
- add DMCUB display microengine support
- DC OEM i2c support
- Renoir DC fixes
- Initial HDCP 2.x support
- BACO support for Arcturus
- Use BACO for runtime PM power save
- gfxoff on navi10
- gfx10 golden updates and fixes
- DCN support on POWER
- GFXOFF for raven1 refresh
- MM engine idle handlers cleanup
- 10bpc EDP panel fixes
- renoir watermark fixes
- SR-IOV fixes
- Arcturus VCN fixes
- GDDR6 training fixes
- freesync fixes
- Pollock support
amdkfd:
- unify more codepath with amdgpu
- use KIQ to setup HIQ rather than MMIO
radeon:
- fix vma fault handler race
- PPC DMA fix
- register check fixes for r100/r200
nouveau:
- mmap_sem vs dma_resv fix
- rewrite the ACR secure boot code for Turing
- TU10x graphics engine support (TU11x pending)
- Page kind mapping for turing
- 10-bit LUT support
- GP10B Tegra fixes
- HD audio regression fix
hisilicon/hibmc:
- use generic fbdev code and helpers
rockchip:
- dsi/px30 support
virtio:
- fb damage support
- static some functions
vc4:
- use dma_resv lock wrappers
msm:
- use dma_resv lock wrappers
- sc7180 display + DSI support
- a618 support
- UBWC support improvements
vmwgfx:
- updates + new logging uapi
exynos:
- enable/disable callback cleanups
etnaviv:
- use dma_resv lock wrappers
atmel-hlcdc:
- clock fixes
mediatek:
- cmdq support
- non-smooth cursor fixes
- ctm property support
sun4i:
- suspend support
- A64 mipi dsi support
rcar-du:
- Color management module support
- LVDS encoder dual-link support
- R8A77980 support
analogic:
- add support for an6345
ast:
- atomic modeset support
- primary plane garbage fix
arcgpu:
- fixes for fourcc handling
tegra:
- minor fixes and improvments
mcde:
- vblank support
meson:
- OSD1 plane AFBC commit
gma500:
- add pageflip support
- reomve global drm_dev
komeda:
- tweak debugfs output
- d32 support
- runtime PM suppotr
udl:
- use generic shmem helpers
- cleanup and fixes
-----BEGIN PGP SIGNATURE-----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=oFrI
-----END PGP SIGNATURE-----
Merge tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Davbe Airlie:
"This is the main pull request for graphics for 5.6. Usual selection of
changes all over.
I've got one outstanding vmwgfx pull that touches mm so kept it
separate until after all of this lands. I'll try and get it to you
soon after this, but it might be early next week (nothing wrong with
code, just my schedule is messy)
This also hits a lot of fbdev drivers with some cleanups.
Other notables:
- vulkan timeline semaphore support added to syncobjs
- nouveau turing secureboot/graphics support
- Displayport MST display stream compression support
Detailed summary:
uapi:
- dma-buf heaps added (and fixed)
- command line add support for panel oreientation
- command line allow overriding penguin count
drm:
- mipi dsi definition updates
- lockdep annotations for dma_resv
- remove dma-buf kmap/kunmap support
- constify fb_ops in all fbdev drivers
- MST fix for daisy chained hotplug-
- CTA-861-G modes with VIC >= 193 added
- fix drm_panel_of_backlight export
- LVDS decoder support
- more device based logging support
- scanline alighment for dumb buffers
- MST DSC helpers
scheduler:
- documentation fixes
- job distribution improvements
panel:
- Logic PD type 28 panel support
- Jimax8729d MIPI-DSI
- igenic JZ4770
- generic DSI devicetree bindings
- sony acx424AKP panel
- Leadtek LTK500HD1829
- xinpeng XPP055C272
- AUO B116XAK01
- GiantPlus GPM940B0
- BOE NV140FHM-N49
- Satoz SAT050AT40H12R2
- Sharp LS020B1DD01D panels.
ttm:
- use blocking WW lock
i915:
- hw/uapi state separation
- Lock annotation improvements
- selftest improvements
- ICL/TGL DSI VDSC support
- VBT parsing improvments
- Display refactoring
- DSI updates + fixes
- HDCP 2.2 for CFL
- CML PCI ID fixes
- GLK+ fbc fix
- PSR fixes
- GEN/GT refactor improvments
- DP MST fixes
- switch context id alloc to xarray
- workaround updates
- LMEM debugfs support
- tiled monitor fixes
- ICL+ clock gating programming removed
- DP MST disable sequence fixed
- LMEM discontiguous object maps
- prefaulting for discontiguous objects
- use LMEM for dumb buffers if possible
- add LMEM mmap support
amdgpu:
- enable sync object timelines for vulkan
- MST atomic routines
- enable MST DSC support
- add DMCUB display microengine support
- DC OEM i2c support
- Renoir DC fixes
- Initial HDCP 2.x support
- BACO support for Arcturus
- Use BACO for runtime PM power save
- gfxoff on navi10
- gfx10 golden updates and fixes
- DCN support on POWER
- GFXOFF for raven1 refresh
- MM engine idle handlers cleanup
- 10bpc EDP panel fixes
- renoir watermark fixes
- SR-IOV fixes
- Arcturus VCN fixes
- GDDR6 training fixes
- freesync fixes
- Pollock support
amdkfd:
- unify more codepath with amdgpu
- use KIQ to setup HIQ rather than MMIO
radeon:
- fix vma fault handler race
- PPC DMA fix
- register check fixes for r100/r200
nouveau:
- mmap_sem vs dma_resv fix
- rewrite the ACR secure boot code for Turing
- TU10x graphics engine support (TU11x pending)
- Page kind mapping for turing
- 10-bit LUT support
- GP10B Tegra fixes
- HD audio regression fix
hisilicon/hibmc:
- use generic fbdev code and helpers
rockchip:
- dsi/px30 support
virtio:
- fb damage support
- static some functions
vc4:
- use dma_resv lock wrappers
msm:
- use dma_resv lock wrappers
- sc7180 display + DSI support
- a618 support
- UBWC support improvements
vmwgfx:
- updates + new logging uapi
exynos:
- enable/disable callback cleanups
etnaviv:
- use dma_resv lock wrappers
atmel-hlcdc:
- clock fixes
mediatek:
- cmdq support
- non-smooth cursor fixes
- ctm property support
sun4i:
- suspend support
- A64 mipi dsi support
rcar-du:
- Color management module support
- LVDS encoder dual-link support
- R8A77980 support
analogic:
- add support for an6345
ast:
- atomic modeset support
- primary plane garbage fix
arcgpu:
- fixes for fourcc handling
tegra:
- minor fixes and improvments
mcde:
- vblank support
meson:
- OSD1 plane AFBC commit
gma500:
- add pageflip support
- reomve global drm_dev
komeda:
- tweak debugfs output
- d32 support
- runtime PM suppotr
udl:
- use generic shmem helpers
- cleanup and fixes"
* tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm: (1998 commits)
drm/nouveau/fb/gp102-: allow module to load even when scrubber binary is missing
drm/nouveau/acr: return error when registering LSF if ACR not supported
drm/nouveau/disp/gv100-: not all channel types support reporting error codes
drm/nouveau/disp/nv50-: prevent oops when no channel method map provided
drm/nouveau: support synchronous pushbuf submission
drm/nouveau: signal pending fences when channel has been killed
drm/nouveau: reject attempts to submit to dead channels
drm/nouveau: zero vma pointer even if we only unreference it rather than free
drm/nouveau: Add HD-audio component notifier support
drm/nouveau: fix build error without CONFIG_IOMMU_API
drm/nouveau/kms/nv04: remove set but not used variable 'width'
drm/nouveau/kms/nv50: remove set but not unused variable 'nv_connector'
drm/nouveau/mmu: fix comptag memory leak
drm/nouveau/gr/gp10b: Use gp100_grctx and gp100_gr_zbc
drm/nouveau/pmu/gm20b,gp10b: Fix Falcon bootstrapping
drm/exynos: Rename Exynos to lowercase
drm/exynos: change callback names
drm/mst: Don't do atomic checks over disabled managers
drm/amdgpu: add the lost mutex_init back
drm/amd/display: skip opp blank or unblank if test pattern enabled
...
VT'd on Broxton and on Braswell require serialisation of GGTT updates.
However, it seems to only be required for insertion, so drop the
complication and heavyweight stop_machine() for clears. The range will
be serialised again before use.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200130092239.1743672-1-chris@chris-wilson.co.uk
Manual conversion of the printk based logging macros to the new struct
drm_based logging macros in drm/i915/gt/intel_ggtt.c.
Also includes extracting the struct drm_i915_private device from various
intel types to use in the new macros.
Signed-off-by: Wambui Karuga <wambui.karugax@gmail.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200128071437.9284-3-wambui.karugax@gmail.com
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: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200128204318.4182039-2-chris@chris-wilson.co.uk
We write to execlists->pending[0] in process_csb() to acknowledge the
completion of the ESLP update, outside of the main spinlock. When we
check the current status of the previous submission in
__execlists_submission_tasklet() we should therefore use READ_ONCE() to
reflect and document the unsynchronized read.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200128171614.3845825-1-chris@chris-wilson.co.uk
The user (e.g. gem_eio) can manipulate the driver into wedging itself,
allowing the user to trigger voluminous logging of inconsequential
details. If we lift the dump to direct calls to intel_gt_set_wedged(),
out of the intel_reset failure handling, we keep the detail logging for
what we expect are true HW or test failures without being tricked.
Reported-by: Tomi Sarvela <tomi.p.sarvela@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tomi Sarvela <tomi.p.sarvela@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200127231540.3302516-6-chris@chris-wilson.co.uk
We always use a deferred bottom-half (either tasklet or irq_work) for
processing the response to an interrupt which means we can recombine the
GT irq ack+handler into one. This simplicity is important in later
patches as we will need to handle and then ack multiple interrupt levels
before acking the GT and master interrupts.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200127231540.3302516-2-chris@chris-wilson.co.uk
We should never BUG_ON on any corruption in CTB descriptor as
data there can be also modified by the GuC. Instead we can
use flag "is_in_error" to indicate that we will not process
any further messages over this CTB (until reset).
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200120191817.50164-1-michal.wajdeczko@intel.com
Using a clear page for scratch means that we have relatively benign
errors in case it is accidentally used, but that can be rather too
benign for debugging. If we poison the scratch, ideally it quickly
results in an obvious error.
v2: Set each page individually just in case we are using highmem for our
scratch page.
v3: Pick a new scratch register as MI_STORE_REGISTER_MEM does not work
with GPR0 on gen7, unbelievably.
v4: Haswell still considers 3DPRIM a privileged register!
Suggested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200124115133.53360-1-chris@chris-wilson.co.uk
Due to the asynchronous nature of releasing our wakerefs, we can signal
the main GT wakeref as complete before the individual engines have
cleared their own wakerefs. During shutdown we assert that the engines
are indeed parked before we release them, but for this to be always true
we need to flush their workers as well.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200124143339.140988-1-chris@chris-wilson.co.uk
Include the current RC6 residency counter in the error message, so that
if we fail to park and manually enter RC6 we can see if the counter has
a particularly suspect value (such as 0).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200123145755.1420622-1-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: 748317386a ("drm/i915/execlists: Offline error capture")
Testcase: igt/gem_exec_balancer/hang
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko 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: 32ff621fd7 ("drm/i915/gt: Allow temporary suspension of inflight requests")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/997
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200122140243.495621-1-chris@chris-wilson.co.uk
We have two trace messages that rely on the function name for
distinction. However, if gcc inlines the function, the two traces end up
with the same function name and are indistinguishable. Add a different
message to each to clarify which one we hit, i.e. which phase of engine
parking we are processing.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200122124154.483444-1-chris@chris-wilson.co.uk
In our ABI we have defined I915_ENGINE_CLASS_INVALID_NONE and
I915_ENGINE_CLASS_INVALID_VIRTUAL as negative values which creates
implicit coupling with type widths used in, also ABI, struct
i915_engine_class_instance.
One place where we export engine->uabi_class
I915_ENGINE_CLASS_INVALID_VIRTUAL is from our our tracepoints. Because the
type of the former is u8 in contrast to u16 defined in the ABI, 254 will
be returned instead of 65534 which userspace would legitimately expect.
Another place is I915_CONTEXT_PARAM_ENGINES.
Therefore we need to align the type used to store engine ABI class and
instance.
v2:
* Update the commit message mentioning get_engines and cc stable.
(Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 6d06779e86 ("drm/i915: Load balancing across a virtual engine")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: <stable@vger.kernel.org> # v5.3+
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116134508.25211-1-tvrtko.ursulin@linux.intel.com
(cherry picked from commit 0b3bd0cdc3)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
In our ABI we have defined I915_ENGINE_CLASS_INVALID_NONE and
I915_ENGINE_CLASS_INVALID_VIRTUAL as negative values which creates
implicit coupling with type widths used in, also ABI, struct
i915_engine_class_instance.
One place where we export engine->uabi_class
I915_ENGINE_CLASS_INVALID_VIRTUAL is from our our tracepoints. Because the
type of the former is u8 in contrast to u16 defined in the ABI, 254 will
be returned instead of 65534 which userspace would legitimately expect.
Another place is I915_CONTEXT_PARAM_ENGINES.
Therefore we need to align the type used to store engine ABI class and
instance.
v2:
* Update the commit message mentioning get_engines and cc stable.
(Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 6d06779e86 ("drm/i915: Load balancing across a virtual engine")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: <stable@vger.kernel.org> # v5.3+
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116134508.25211-1-tvrtko.ursulin@linux.intel.com
core mst:
- serialize down messages and clear timeslots are on unplug
amdgpu:
- Update golden settings for renoir
- eDP fix
i915:
- uAPI fix: Remove dash and colon from PMU names to comply with tools/perf
- Fix for include file that was indirectly included
- Two fixes to make sure VMA are marked active for error capture
virtio:
- maintain obj reservation lock when submitting cmds
rockchip:
- increase link rate var size to accommodate rates
-----BEGIN PGP SIGNATURE-----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=Vwa3
-----END PGP SIGNATURE-----
Merge tag 'drm-fixes-2020-01-19' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Dave Airlie:
"Back from LCA2020, fixes wasn't too busy last week, seems to have
quieten down appropriately, some amdgpu, i915, then a core mst fix and
one fix for virtio-gpu and one for rockchip:
core mst:
- serialize down messages and clear timeslots are on unplug
amdgpu:
- Update golden settings for renoir
- eDP fix
i915:
- uAPI fix: Remove dash and colon from PMU names to comply with
tools/perf
- Fix for include file that was indirectly included
- Two fixes to make sure VMA are marked active for error capture
virtio:
- maintain obj reservation lock when submitting cmds
rockchip:
- increase link rate var size to accommodate rates"
* tag 'drm-fixes-2020-01-19' of git://anongit.freedesktop.org/drm/drm:
drm/amd/display: Reorder detect_edp_sink_caps before link settings read.
drm/amdgpu: update goldensetting for renoir
drm/dp_mst: Have DP_Tx send one msg at a time
drm/dp_mst: clear time slots for ports invalid
drm/i915/pmu: Do not use colons or dashes in PMU names
drm/rockchip: fix integer type used for storing dp data rate
drm/i915/gt: Mark ring->vma as active while pinned
drm/i915/gt: Mark context->state vma as active while pinned
drm/i915/gt: Skip trying to unbind in restore_ggtt_mappings
drm/i915: Add missing include file <linux/math64.h>
drm/virtio: add missing virtio_gpu_array_lock_resv call
If we create a rather large userptr object(e.g 1ULL << 32) we might
shift past the type-width of num_pages: (int)num_pages << PAGE_SHIFT,
resulting in a totally bogus sg_table, which fortunately will eventually
manifest as:
gen8_ppgtt_insert_huge:463 GEM_BUG_ON(iter->sg->length < page_size)
kernel BUG at drivers/gpu/drm/i915/gt/gen8_ppgtt.c:463!
v2: more unsigned long
prefer I915_GTT_PAGE_SIZE
Fixes: 5cc9ed4b9a ("drm/i915: Introduce mapping of user pages into video memory (userptr) ioctl")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117132413.1170563-2-matthew.auld@intel.com
Since commit 22b7a426bb ("drm/i915/execlists: Preempt-to-busy"), we
prune the engine->active.requests list prior to preemption, thus
removing the trace of the currently executing request. If that request
hangs rather than be preempted, we conclude that no active request was
on the GPU. Fortunately, this only impacts our debugging, and not our
means of hang detection or recovery.
v2: Use from to check the current iterator before continuing, and report
active as NULL if the current request is already completed.
References: 22b7a426bb ("drm/i915/execlists: Preempt-to-busy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117113259.3023890-1-chris@chris-wilson.co.uk
As we now have "ct" available almost in all functions we can
start using dev variants of logs also for debug.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117082039.65644-6-michal.wajdeczko@intel.com
As we now have "ct" available in ct_read function we can switch
from generic DRM_ERROR to our custom CT_ERROR.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117082039.65644-5-michal.wajdeczko@intel.com
Since we only have one RECV buffer we don't need to explicitly pass
it to the read function.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117082039.65644-4-michal.wajdeczko@intel.com
Since we only have one SEND buffer we don't need to explicitly pass
it to the write function.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117082039.65644-3-michal.wajdeczko@intel.com
We should never BUG_ON on any corruption in CTB descriptor as
data there can be also modified by the GuC. Instead we can
use flag "is_in_error" to indicate that we will not process
any further messages over this CTB (until reset). While here
move descriptor error reporting to the function that actually
touches that descriptor.
Note that unexpected content of the specific CT messages, that
still complies with generic CT message format, shall not trigger
disabling whole CTB, as that might just indicate new unsupported
message types.
v2: drop redundant message (Daniele)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117082039.65644-2-michal.wajdeczko@intel.com
Currently, we skip error capture upon forced preemption. We apply forced
preemption when there is a higher priority request that should be
running but is being blocked, and we skip inline error capture so that
the preemption request is not further delayed by a user controlled
capture -- extending the denial of service.
However, preemption reset is also used for heartbeats and regular GPU
hangs. By skipping the error capture, we remove the ability to debug GPU
hangs.
In order to capture the error without delaying the preemption request
further, we can do an out-of-line capture by removing the guilty request
from the execution queue and scheduling a worker to dump that request.
When removing a request, we need to remove the entire context and all
descendants from the execution queue, so that they do not jump past.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/738
Fixes: 3a7a92aba8 ("drm/i915/execlists: Force preemption")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-3-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/738
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-2-chris@chris-wilson.co.uk
If we keep track of when the i915_request.sched.link is on the HW
runlist, or in the priority queue we can simplify our interactions with
the request (such as during rescheduling). This also simplifies the next
patch where we introduce a new in-between list, for requests that are
ready but neither on the run list or in the queue.
v2: Update i915_sched_node.link explanation for current usage where it
is a link on both the queue and on the runlists.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-1-chris@chris-wilson.co.uk
