Some of our commands (MI_FLUSH_DW / PIPE_CONTROL) require a post-sync write
operation to be performed. Currently we're using dedicated VMA for
PIPE_CONTROL and global HWSP for MI_FLUSH_DW.
On execlists platforms, each of our contexts has an area that can be
used as scratch space. Let's use that instead.
Signed-off-by: Michał Winiarski <michal.winiarski@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/20190926133142.2838-2-chris@chris-wilson.co.uk
Having decided that we only care about the promotion predicate, we can
simplify gen12_csb_parse to simply check whether we need to jump to a
new queue.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925130845.17952-1-chris@chris-wilson.co.uk
Before we submit the first context to HW, we need to construct a valid
image of the register state. This layout is defined by the HW and should
match the layout generated by HW when it saves the context image.
Asserting that this should be equivalent should help avoid any undefined
behaviour and verify that we haven't missed anything important!
Of course, having insisted that the initial register state within the
LRC should match that returned by HW, we need to ensure that it does.
v2: Drop the RELATIVE_MMIO flag from gen11, we ignore it for
constructing the lrc image.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924145950.3011-1-chris@chris-wilson.co.uk
Force bonded requests to run on distinct engines so that they cannot be
shuffled onto the same engine where timeslicing will reverse the order.
A bonded request will often wait on a semaphore signaled by its master,
creating an implicit dependency -- if we ignore that implicit dependency
and allow the bonded request to run on the same engine and before its
master, we will cause a GPU hang. [Whether it will hang the GPU is
debatable, we should keep on timeslicing and each timeslice should be
"accidentally" counted as forward progress, in which case it should run
but at one-half to one-third speed.]
We can prevent this inversion by restricting which engines we allow
ourselves to jump to upon preemption, i.e. baking in the arrangement
established at first execution. (We should also consider capturing the
implicit dependency using i915_sched_add_dependency(), but first we need
to think about the constraints that requires on the execution/retirement
ordering.)
Fixes: 8ee36e048c ("drm/i915/execlists: Minimalistic timeslicing")
References: ee1136908e ("drm/i915/execlists: Virtual engine bonding")
Testcase: igt/gem_exec_balancer/bonded-slice
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/20190923152844.8914-3-chris@chris-wilson.co.uk
Due to the nature of preempt-to-busy the execlists active tracking and
the schedule queue may become temporarily desync'ed (between resubmission
to HW and its ack from HW). This means that we may have unwound a
request and passed it back to the virtual engine, but it is still
inflight on the HW and may even result in a GPU hang. If we detect that
GPU hang and try to reset, the hanging request->engine will no longer
match the current engine, which means that the request is not on the
execlists active list and we should not try to find an older incomplete
request. Given that we have deduced this must be a request on a virtual
engine, it is the single active request in the context and so must be
guilty (as the context is still inflight, it is prevented from being
executed on another engine as we process the reset).
Fixes: 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>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-2-chris@chris-wilson.co.uk
As preempt-to-busy leaves the request on the HW as the resubmission is
processed, that request may complete in the background and even cause a
second virtual request to enter queue. This second virtual request
breaks our "single request in the virtual pipeline" assumptions.
Furthermore, as the virtual request may be completed and retired, we
lose the reference the virtual engine assumes is held. Normally, just
removing the request from the scheduler queue removes it from the
engine, but the virtual engine keeps track of its singleton request via
its ve->request. This pointer needs protecting with a reference.
v2: Drop unnecessary motion of rq->engine = owner
Fixes: 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>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-1-chris@chris-wilson.co.uk
Pull setting -EIO on the hung requests into its own utility function.
Having allowed ourselves to short-circuit submission of completed
requests, we can now do the mark_eio() prior to submission and avoid
some redundant operations.
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/20190923110056.15176-4-chris@chris-wilson.co.uk
If we are asked to submit a completed request, just move it onto the
active-list without modifying it's payload. If we try to emit the
modified payload of a completed request, we risk racing with the
ring->head update during retirement which may advance the head past our
breadcrumb and so we generate a warning for the emission being behind
the RING_HEAD.
v2: Commentary for the sneaky, shared responsibility between functions.
v3: Spelling mistakes and bonus assertion
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/20190923110056.15176-3-chris@chris-wilson.co.uk
Since amalgamating the queued and active lists in commit 422d7df4f0
("drm/i915: Replace engine->timeline with a plain list"), performing a
i915_request_submit() will remove the request from the execlists
priority queue.
References: 422d7df4f0 ("drm/i915: Replace engine->timeline with a plain list")
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/20190923110056.15176-2-chris@chris-wilson.co.uk
A gpu hang can occur at any time, given a sufficiently angry gpu. An
example is when it forgets to perform a context-switch at the end of a
request, leaving us with a hanging GPU on a completed request. Here, we
may retire the request, only leaving its context alive via the active
barrier. When we reset the GPU on a completed request, we do not modify
its context image (just updating the ring state) and can safely defer
the assertion that we have the image pinned and ready to modify.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111639
Fixes: dffa8feb30 ("drm/i915/perf: Assert locking for i915_init_oa_perf_state()")
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/20190923110056.15176-1-chris@chris-wilson.co.uk
The request->timeline is only valid until the request is retired (i.e.
before it is completed). Upon retiring the request, the context may be
unpinned and freed, and along with it the timeline may be freed. We
therefore need to be very careful when chasing rq->timeline that the
pointer does not disappear beneath us. The vast majority of users are in
a protected context, either during request construction or retirement,
where the timeline->mutex is held and the timeline cannot disappear. It
is those few off the beaten path (where we access a second timeline) that
need extra scrutiny -- to be added in the next patch after first adding
the warnings about dangerous access.
One complication, where we cannot use the timeline->mutex itself, is
during request submission onto hardware (under spinlocks). Here, we want
to check on the timeline to finalize the breadcrumb, and so we need to
impose a second rule to ensure that the request->timeline is indeed
valid. As we are submitting the request, it's context and timeline must
be pinned, as it will be used by the hardware. Since it is pinned, we
know the request->timeline must still be valid, and we cannot submit the
idle barrier until after we release the engine->active.lock, ergo while
submitting and holding that spinlock, a second thread cannot release the
timeline.
v2: Don't be lazy inside selftests; hold the timeline->mutex for as long
as we need it, and tidy up acquiring the timeline with a bit of
refactoring (i915_active_add_request)
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/20190919111912.21631-1-chris@chris-wilson.co.uk
Before we execute a batch, we must first issue any and all TLB
invalidations so that batch picks up the new page table entries.
Tigerlake's preparser is weakening our post-sync CS_STALL inside the
invalidate pipe-control and allowing the loading of the batch buffer
before we have setup its page table (and so it loads the wrong page and
executes indefinitely).
The igt_cs_tlb indicates that this issue can only be observed on rcs,
even though the preparser is common to all engines. Alternatively, we
could do TLB shootdown via mmio on updating the GTT.
By inserting the pre-parser disable inside EMIT_INVALIDATE, we will also
accidentally fixup execution that writes into subsequent batches, such
as gem_exec_whisper and even relocations performed on the GPU. We should
be careful not to allow this disable to become baked into the uABI! The
issue is that if userspace relies on our disabling of the HW
optimisation, when we are ready to enable that optimisation, userspace
will then be broken...
Testcase: igt/i915_selftests/live_gtt/igt_cs_tlb
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111753
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919151811.9526-1-chris@chris-wilson.co.uk
On Tigerlake, MI_SEMAPHORE_WAIT grew an extra dword, so be sure to
update the length field and emit that extra parameter and any padding
noop as required.
v2: Define the token shift while we are adding the updated MI_SEMAPHORE_WAIT
v3: Use int instead of bool in the addition so that readers are not left
wondering about the intricacies of the C spec. Now they just have to
worry what the integer value of a boolean operation is...
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190917123055.28965-1-chris@chris-wilson.co.uk
We see failures where the context continues executing past a
preemption event, eventually leading to situations where a request has
executed before we have event submitted it to HW! It seems like tgl is
ignoring our RING_TAIL updates, but more likely is that there is a
missing update required for our semaphore waits around preemption.
v2: And disable internal semaphore usage
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912132313.12751-1-chris@chris-wilson.co.uk
After we manipulate the context to allow replay after a GPU reset, force
that context to be reloaded. This should be a layer of paranoia, for if
the GPU was reset, the context will no longer be resident!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912092933.4729-2-chris@chris-wilson.co.uk
After a GPU reset, we need to drain all the CS events so that we have an
accurate picture of the execlists state at the time of the reset. Be
paranoid and force a read of the CSB write pointer from memory.
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/20190912092933.4729-1-chris@chris-wilson.co.uk
During reset, we try to ensure no forward progress of the CS prior to
the reset by setting the STOP_RING bit in RING_MI_MODE. Since gen9, this
register is context saved and do we end up in the odd situation where we
save the STOP_RING bit and so try to stop the engine again immediately
upon resume. This is quite unexpected and causes us to complain about an
early CS completion event!
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111514
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/20190910080208.4223-1-chris@chris-wilson.co.uk
As we may unwind incomplete requests (for preemption) prior to
processing the CSB and the schedule-out events, we may update rq->engine
(resetting it to point back to the parent virtual engine) prior to
calling execlists_schedule_out(), invalidating the assertion that the
request still points to the inflight engine. (The likelihood of this is
increased if the CSB interrupt processing is pushed to the ksoftirqd for
being too slow and direct submission overtakes it.)
Tvrtko summarised it as:
"So unwind from direct submission resets rq->engine and races with
process_csb from the tasklet which notices request has actually
completed."
Reported-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Fixes: df40306902 ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
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: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190907105046.19934-1-chris@chris-wilson.co.uk
Gen12 has subtle changes in the reg state context offsets (some fields
are gone, some are in a different location), compared to previous Gens.
The simplest approach seems to be keeping Gen12 (and future platform)
changes apart from the previous gens, while keeping the registers that
are contiguous in functions we can reuse.
v2: alias, virtual engine, rpcs, prune unused regs
v3: use engine base (Daniele), take ctx_bb for all
Bspec: 46255
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Tested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
[ickle: Tweaked the GEM_WARN_ON after settling on a compromise with
Daniele]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190906122314.2146-2-mika.kuoppala@linux.intel.com
Daniele pointed out that relative mmio works differently in
on context restore. Instead of adding the engine mmio base to offset,
it masks out the base and adds bits [12:2] to current engine base.
This should allow us to construct context register state to be
applicable to all instances, including virtual. And avoid the trouble
of updating the registers on virtual instances when submitting work.
v2: only enable for gen12 for now (Mika)
v3: make enabling readable (Chris)
Bspec: 20206
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
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/20190906134957.25909-1-mika.kuoppala@linux.intel.com
We use the context->pin_mutex to serialise updates to the OA config and
the registers values written into each new context. Document this
relationship and assert we do hold the context->pin_mutex as used by
gen8_configure_all_contexts() to serialise updates to the OA config
itself.
v2: Add a white-lie for when we call intel_gt_resume() from init.
v3: Lie while we have the context pinned inside atomic reset.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20190830181929.18663-1-chris@chris-wilson.co.uk
With the upcoming change in timing (dramatically reducing the latency
between manipulating the ppGTT and execution), no amount of tweaking
could save Cherryview, it would always fail to invalidate its TLB.
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/20190830180000.24608-2-chris@chris-wilson.co.uk
The addition of the DC_FLUSH failed to ensure sanctity of the post-sync
write as CI immediately got a completion CS-event before the breadcrumb
was coherent. So let's try the other idea of moving the post-sync write
into the CS_STALL.
References: https://bugs.freedesktop.org/show_bug.cgi?id=111514
References: e8f6b4952e ("drm/i915/execlists: Flush the post-sync breadcrumb write harder")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829081150.10271-2-chris@chris-wilson.co.uk
Quite rarely we see that the CS completion event fires before the
breadcrumb is coherent, which presumably is a result of the CS_STALL not
waiting for the post-sync operation. Try throwing in a DC_FLUSH into
the following pipecontrol to see if that makes any difference.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827120615.31390-1-chris@chris-wilson.co.uk
The CS pre-parser can pre-fetch commands across memory sync points and
starting from gen12 it is able to pre-fetch across BB_START and BB_END
boundaries as well, so when we emit gpu relocs the pre-parser might
fetch the target location of the reloc before the memory write lands.
The parser can't pre-fetch across the ctx switch, so we use a separate
context to guarantee that the memory is synchronized before the parser
can get to it.
Note that there is no risk of the CS doing a lite restore from the reloc
context to the user context, even if the two have the same hw_id,
because since gen11 the CS also checks the LRCA when deciding if it can
lite-restore.
v2: limit new context to gen12+, release in eb_destroy, add a comment
in emit_fini_breadcrumb (Chris).
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: 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/20190827185805.21799-1-daniele.ceraolospurio@intel.com
Since we now run process_csb() outside of the engine->active.lock, we
can process a CS-event immediately upon our ELSP write. As we currently
inspect the pending queue *after* the ELSP write, there is an
opportunity for a CS-event to update the pending queue before we can
read it, making ourselves chases an invalid pointer.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111427
Fixes: df40306902 ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
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/20190821142336.21609-1-chris@chris-wilson.co.uk
Add empty workaround hooks for Tiger Lake. The workarounds will be added
on separate patches. We were already applying
WaRsForcewakeAddDelayForAck, which is indeed still valid, so also update
the comment.
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190817093902.2171-21-lucas.demarchi@intel.com
The CSB format has been reworked for Gen12 to include information on
both the context we're switching away from and the context we're
switching to. After the change, some of the events don't have their
own bit anymore and need to be inferred from other values in the csb.
One of the context IDs (0x7FF) has also been reserved to indicate
the invalid ctx, i.e. engine idle.
Note that the full context ID includes the SW counter as well, but since
we currently only care if the context is valid or not we can ignore that
part.
v2: fix mask size, fix and expand comments (Tvrtko),
use if-ladder (Chris)
Bspec: 45555, 46144
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: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-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/20190820102201.29849-1-chris@chris-wilson.co.uk
Gen12 uses a new indirect ctx offset.
Bspec: 11740
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190817093902.2171-28-lucas.demarchi@intel.com
Add a redzone to our context image and check the HW does not write into
after a context save, to verify that we have the correct context size.
(This does vary with feature bits, so test with a live setup that should
match how we run userspace.)
v2: Check the redzone on every context unpin
v3: Use a kernel context to prevent loading garbage for ringbuffer
submission
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190817073711.5897-1-chris@chris-wilson.co.uk
If we only call process_csb() from the tasklet, though we lose the
ability to bypass ksoftirqd interrupt processing on direct submission
paths, we can push it out of the irq-off spinlock.
The penalty is that we then allow schedule_out to be called concurrently
with schedule_in requiring us to handle the usage count (baked into the
pointer itself) atomically.
As we do kick the tasklets (via local_bh_enable()) after our submission,
there is a possibility there to see if we can pull the local softirq
processing back from the ksoftirqd.
v2: Store the 'switch_priority_hint' on submission, so that we can
safely check during process_csb().
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/20190816171608.11760-1-chris@chris-wilson.co.uk
Forgo the struct_mutex requirement for request retirement as we have
been transitioning over to only using the timeline->mutex for
controlling the lifetime of a request on that timeline.
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/20190815205709.24285-4-chris@chris-wilson.co.uk
Flush according to what gen11 expects when writing
breadcrumbs. As only the seqnowrite + flush differs
between engine and gens, enclose the footer to
helper.
v2: avoid problem of sane local naming by not using them
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/20190815094929.358-1-mika.kuoppala@linux.intel.com
Add tile cache flushing for gen11. To relive us from the
burden of previous obsolete workarounds, make a dedicated
flush/invalidate callback for gen11.
To fortify an independent single flush, do post
sync op as there are indications that without it
we don't flush everything. This should also make this
callback more readily usable in tgl (see l3 fabric flush).
v2: whitespacing
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
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/20190815083055.14132-1-mika.kuoppala@linux.intel.com
Since execlists and the guc have diverged in their port tracking, we
cannot simply reuse the execlists cancellation code as it leads to
unbalanced reference counting. Use a local, simpler routine for the guc.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190812203626.3948-1-chris@chris-wilson.co.uk
Move the timeline from being inside the intel_ring to intel_context
itself. This saves much pointer dancing and makes the relations of the
context to its timeline much clearer.
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/20190809182518.20486-4-chris@chris-wilson.co.uk
Refactor the backends to handle the deferred context allocation in a
consistent manner, and allow calling it as an explicit first step in
pinning a context for the first time. This should make it easier for
backends to keep track of partially constructed contexts from
initialisation.
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/20190809182518.20486-2-chris@chris-wilson.co.uk
It used to be handy that we only had a couple of headers, but over time
i915_drv.h has become unwieldy. Extract declarations to a separate
header file corresponding to the implementation module, clarifying the
modularity of the driver.
Ensure the new header is self-contained, and do so with minimal further
includes, using forward declarations as needed. Include the new header
only where needed, and sort the modified include directives while at it
and as needed.
No functional changes.
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/d7826e365695f691a3ac69a69ff6f2bbdb62700d.1565271681.git.jani.nikula@intel.com
As we need to acquire a mutex to serialise the final
intel_wakeref_put, we need to ensure that we are in process context at
that time. However, we want to allow operation on the intel_wakeref from
inside timer and other hardirq context, which means that need to defer
that final put to a workqueue.
Inside the final wakeref puts, we are safe to operate in any context, as
we are simply marking up the HW and state tracking for the potential
sleep. It's only the serialisation with the potential sleeping getting
that requires careful wait avoidance. This allows us to retain the
immediate processing as before (we only need to sleep over the same
races as the current mutex_lock).
v2: Add a selftest to ensure we exercise the code while lockdep watches.
v3: That test was extremely loud and complained about many things!
v4: Not a whale!
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295
References: https://bugs.freedesktop.org/show_bug.cgi?id=111245
References: https://bugs.freedesktop.org/show_bug.cgi?id=111256
Fixes: 18398904ca ("drm/i915: Only recover active engines")
Fixes: 51fbd8de87 ("drm/i915/pmu: Atomically acquire the gt_pm wakeref")
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/20190808202758.10453-1-chris@chris-wilson.co.uk
We only compute the lrc_descriptor() on pinning the context, i.e.
infrequently, so we do not benefit from storing the template as the
addressing mode is also fixed for the lifetime of the intel_context.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190730133035.1977-9-chris@chris-wilson.co.uk
Track the currently bound address space used by the HW context. Minor
conversions to use the local intel_context.vm are made, leaving behind
some more surgery required to make intel_context the primary through the
selftests.
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/20190730143209.4549-2-chris@chris-wilson.co.uk
We only use the init_context vfunc once while recording the default
context state, and we use the same sequence in each backend (eliding
steps that do not apply). Remove the vfunc for simplicity and
de-duplication.
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/20190729113720.24830-1-chris@chris-wilson.co.uk
Prior to freeing the struct, call the fini function to cleanup the
common members. Currently this only calls the debug functions to mark
the structs as destroyed, but may be extended to real work in future.
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/20190718070024.21781-2-chris@chris-wilson.co.uk
As we unwind the requests for a preemption event, we return a virtual
request back to its original virtual engine (so that it is available for
execution on any of its siblings). In the process, this means that its
breadcrumb should no longer be associated with the original physical
engine, and so we are forced to decouple it. Previously, as the request
could not complete without our awareness, we would move it to the next
real engine without any danger. However, preempt-to-busy allowed for
requests to continue on the HW and complete in the background as we
unwound, which meant that we could end up retiring the request before
fixing up the breadcrumb link.
[51679.517943] INFO: trying to register non-static key.
[51679.517956] the code is fine but needs lockdep annotation.
[51679.517960] turning off the locking correctness validator.
[51679.517966] CPU: 0 PID: 3270 Comm: kworker/u8:0 Tainted: G U 5.2.0+ #717
[51679.517971] Hardware name: Intel Corporation NUC7i5BNK/NUC7i5BNB, BIOS BNKBL357.86A.0052.2017.0918.1346 09/18/2017
[51679.518012] Workqueue: i915 retire_work_handler [i915]
[51679.518017] Call Trace:
[51679.518026] dump_stack+0x67/0x90
[51679.518031] register_lock_class+0x52c/0x540
[51679.518038] ? find_held_lock+0x2d/0x90
[51679.518042] __lock_acquire+0x68/0x1800
[51679.518047] ? find_held_lock+0x2d/0x90
[51679.518073] ? __i915_sw_fence_complete+0xff/0x1c0 [i915]
[51679.518079] lock_acquire+0x90/0x170
[51679.518105] ? i915_request_cancel_breadcrumb+0x29/0x160 [i915]
[51679.518112] _raw_spin_lock+0x27/0x40
[51679.518138] ? i915_request_cancel_breadcrumb+0x29/0x160 [i915]
[51679.518165] i915_request_cancel_breadcrumb+0x29/0x160 [i915]
[51679.518199] i915_request_retire+0x43f/0x530 [i915]
[51679.518232] retire_requests+0x4d/0x60 [i915]
[51679.518263] i915_retire_requests+0xdf/0x1f0 [i915]
[51679.518294] retire_work_handler+0x4c/0x60 [i915]
[51679.518301] process_one_work+0x22c/0x5c0
[51679.518307] worker_thread+0x37/0x390
[51679.518311] ? process_one_work+0x5c0/0x5c0
[51679.518316] kthread+0x116/0x130
[51679.518320] ? kthread_create_on_node+0x40/0x40
[51679.518325] ret_from_fork+0x24/0x30
[51679.520177] ------------[ cut here ]------------
[51679.520189] list_del corruption, ffff88883675e2f0->next is LIST_POISON1 (dead000000000100)
Fixes: 22b7a426bb ("drm/i915/execlists: Preempt-to-busy")
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/20190716124931.5870-4-chris@chris-wilson.co.uk
Push the engine stop into the back reset_prepare (where it already was!)
This allows us to avoid dangerously setting the RING registers to 0 for
logical contexts. If we clear the register on a live context, those
invalid register values are recorded in the logical context state and
replayed (with hilarious results).
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/20190716124931.5870-2-chris@chris-wilson.co.uk
By stopping the rings, we may trigger an arbitration point resulting in
a premature context-switch (i.e. a completion event before the request
is actually complete). This clears the active context before the reset,
but we must remember to rewind the incomplete context for replay upon
resume.
Fixes: 1863e3020a ("drm/i915/execlists: Always reset the context's RING registers")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190716124931.5870-3-chris@chris-wilson.co.uk
Avoid a global idle barrier by reconfiguring each context by rewriting
them with MI_STORE_DWORD from the kernel context.
v2: We only need to determine the desired register values once, they are
the same for all contexts.
v3: Don't remove the kernel context from the list of known GEM contexts;
the world is not ready for that yet.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190716213443.9874-1-chris@chris-wilson.co.uk
Preempt-to-busy uses a GPU semaphore to enforce an idle-barrier across
preemption, but mediated gvt does not fully support semaphores.
v2: Fiddle around with the flags and settle on using has-semaphores for
the core bits so that we retain the ability to preempt our own
semaphores.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Xiaolin Zhang <xiaolin.zhang@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190709091233.8573-1-chris@chris-wilson.co.uk
Having taken the first step in encapsulating the functionality by moving
the related files under gt/, the next step is to start encapsulating by
passing around the relevant structs rather than the global
drm_i915_private. In this step, we pass intel_gt to intel_reset.c
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@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/20190712192953.9187-1-chris@chris-wilson.co.uk
Put back the preemption counters lost in commit 22b7a426bb
("drm/i915/execlists: Preempt-to-busy") so that our selftests that
assert no preemption took place continue to function.
v2: But a timeslice is only a "soft" preemption!
Fixes: 22b7a426bb ("drm/i915/execlists: Preempt-to-busy")
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/20190710064454.682-1-chris@chris-wilson.co.uk
We want to set this flag in the next commit on requests containing
perf queries so that the result of the perf query can just be a delta
of global counters, rather than doing post processing of the OA
buffer.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
[ickle: add basic selftest for nopreempt]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190709164227.25859-1-chris@chris-wilson.co.uk
We have a bunch of offsets in the scratch buffer. As we're about to
add some more, let's group all of the offsets in a common location.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@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/20190709123351.5645-6-lionel.g.landwerlin@intel.com
We need to setup the workarounds on all engines, with the knowledge
about which platforms each workaround applies to kept together in the
workaround list. As such, we can pull the w/a initialisation into the
common setup and try to avoid duplicating knowledge about when to setup
the workarounds.
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/20190703135805.7310-2-chris@chris-wilson.co.uk
We can assume the caller is holding a blanket forcewake for the
register writes during resume, and so we can skip taking individual
locks around each write inside execlists resume.
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/20190703155225.9501-3-chris@chris-wilson.co.uk
The render state is used to initialise the default RCS context, and only
used during early setup from within the gt code. As such, it makes a
good candidate for placing within gt/, even if it is not yet entirely
clean of our GEM heritage.
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/20190704091925.7391-1-chris@chris-wilson.co.uk
Be a little more hesitant before injecting a timeslice, and try to take
into account any change in priority that is due for the running task
before switching to another task. This will allow us to arbitrarily
prevent switching away from a request if we deem it necessarily to
disable preemption, for instance.
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: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190703091726.11690-9-chris@chris-wilson.co.uk
Daniele pointed out that the CSB status information will change with
Tigerlake and suggested that we could rearrange our state machine to
hide the differences in generation. gcc also prefers the explicit state
machine, so make it so:
process_csb 1980 1967 -13
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.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/20190701100502.15639-4-chris@chris-wilson.co.uk
As this engine owns the lock around rq->sched.link (for those waiters
submitted to this engine), we can use that link as an element in a local
list. We can thus replace the recursive algorithm with an iterative walk
over the ordered list of waiters.
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/20190625130128.11009-1-chris@chris-wilson.co.uk
In the unlikely case (thank you CI!), we may find ourselves wanting to
issue a preemption but having no runnable requests left. In this case,
we set the semaphore before computing the preemption and so must unset
it before forgetting (or else we leave the machine busywaiting until the
next request comes along and so likely hang).
v2: Replace readback with only a wmb after asserting the semaphore
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/20190624092009.30189-1-chris@chris-wilson.co.uk
If we introduce a callback for i915_active that is only called the first
time we use the i915_active and is symmetrically paired with the
i915_active.retire callback, we can replace the open-coded and
non-atomic implementations -- which will be very fragile (i.e. broken)
upon removing the struct_mutex serialisation.
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/20190621183801.23252-4-chris@chris-wilson.co.uk
Remove the accumulated optimisations that we have for i915_vma_retire
and reduce it to the bare essential of tracking the active object
reference. This allows us to only use atomic operations, and so will be
able to avoid the struct_mutex requirement.
The principal loss here is the shrinker MRU bumping, so now if we have
to shrink, we will do so in much more random order and more likely to
try and shrink recently used objects. That is a nuisance, but shrinking
active objects is a second step we try to avoid and will always be a
system-wide performance issue.
The other loss is here is in the automatic pruning of the
reservation_object when idling. This is not as large an issue as upon
reservation_object introduction as now adding new fences into the object
replaces already signaled fences, keeping the array compact. But we do
lose the auto-expiration of stale fences and unused arrays. That may be
a noticeable problem for which we need to re-implement autopruning.
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/20190621183801.23252-3-chris@chris-wilson.co.uk
Scratch vma lives under gt but the API used to work on i915. Make this
consistent by renaming the function to intel_gt_scratch_offset and make
it take struct intel_gt.
v2:
* Move to intel_gt. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190621070811.7006-33-tvrtko.ursulin@linux.intel.com
Our timelines are stored inside intel_gt so we can convert the interface
to take exactly that and not i915.
At the same time re-order the params to our more typical layout and
replace the backpointer to the new containing structure.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190621070811.7006-31-tvrtko.ursulin@linux.intel.com
For gt related operations it makes more logical sense to stay in the realm
of gt instead of dereferencing via driver i915.
This patch handles a few of the easy ones with work requiring more
refactoring still outstanding.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190621070811.7006-30-tvrtko.ursulin@linux.intel.com
The call to kick_siblings() dereferences the rq->context, so we should
not drop our local reference until afterwards!
v2: Stick to setting ce.inflight=NULL before kicking as this is what the
other threads will check to see if the context is ready for takeover.
Fixes: 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>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190621080729.2652-1-chris@chris-wilson.co.uk
If we have multiple contexts of equal priority pending execution,
activate a timer to demote the currently executing context in favour of
the next in the queue when that timeslice expires. This enforces
fairness between contexts (so long as they allow preemption -- forced
preemption, in the future, will kick those who do not obey) and allows
us to avoid userspace blocking forward progress with e.g. unbounded
MI_SEMAPHORE_WAIT.
For the starting point here, we use the jiffie as our timeslice so that
we should be reasonably efficient wrt frequent CPU wakeups.
Testcase: igt/gem_exec_scheduler/semaphore-resolve
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/20190620142052.19311-2-chris@chris-wilson.co.uk
When using a global seqno, we required a precise stop-the-workd event to
handle preemption and unwind the global seqno counter. To accomplish
this, we would preempt to a special out-of-band context and wait for the
machine to report that it was idle. Given an idle machine, we could very
precisely see which requests had completed and which we needed to feed
back into the run queue.
However, now that we have scrapped the global seqno, we no longer need
to precisely unwind the global counter and only track requests by their
per-context seqno. This allows us to loosely unwind inflight requests
while scheduling a preemption, with the enormous caveat that the
requests we put back on the run queue are still _inflight_ (until the
preemption request is complete). This makes request tracking much more
messy, as at any point then we can see a completed request that we
believe is not currently scheduled for execution. We also have to be
careful not to rewind RING_TAIL past RING_HEAD on preempting to the
running context, and for this we use a semaphore to prevent completion
of the request before continuing.
To accomplish this feat, we change how we track requests scheduled to
the HW. Instead of appending our requests onto a single list as we
submit, we track each submission to ELSP as its own block. Then upon
receiving the CS preemption event, we promote the pending block to the
inflight block (discarding what was previously being tracked). As normal
CS completion events arrive, we then remove stale entries from the
inflight tracker.
v2: Be a tinge paranoid and ensure we flush the write into the HWS page
for the GPU semaphore to pick in a timely fashion.
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/20190620142052.19311-1-chris@chris-wilson.co.uk
Remember to keep the rings pinned as well as the context image until the
GPU is no longer active.
v2: Introduce a ring->pin_count primarily to hide the
mock_ring that doesn't fit into the normal GGTT vma picture.
v3: Order is important in teardown, ringbuffer submission needs to drop
the pin count on the engine->kernel_context before it can gleefully free
its ring.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110946
Fixes: ce476c80b8 ("drm/i915: Keep contexts pinned until after the next kernel context switch")
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/20190619170135.15281-1-chris@chris-wilson.co.uk
The process_csb routine from execlists_submission is incompatible with
the GuC backend. Add a warning to detect if we accidentally end up in
the wrong spot.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190618110736.31155-1-chris@chris-wilson.co.uk
The idea behind keeping the saturation mask local to a context backfired
spectacularly. The premise with the local mask was that we would be more
proactive in attempting to use semaphores after each time the context
idled, and that all new contexts would attempt to use semaphores
ignoring the current state of the system. This turns out to be horribly
optimistic. If the system state is still oversaturated and the existing
workloads have all stopped using semaphores, the new workloads would
attempt to use semaphores and be deprioritised behind real work. The
new contexts would not switch off using semaphores until their initial
batch of low priority work had completed. Given sufficient backload load
of equal user priority, this would completely starve the new work of any
GPU time.
To compensate, remove the local tracking in favour of keeping it as
global state on the engine -- once the system is saturated and
semaphores are disabled, everyone stops attempting to use semaphores
until the system is idle again. One of the reason for preferring local
context tracking was that it worked with virtual engines, so for
switching to global state we could either do a complete check of all the
virtual siblings or simply disable semaphores for those requests. This
takes the simpler approach of disabling semaphores on virtual engines.
The downside is that the decision that the engine is saturated is a
local measure -- we are only checking whether or not this context was
scheduled in a timely fashion, it may be legitimately delayed due to user
priorities. We still have the same dilemma though, that we do not want
to employ the semaphore poll unless it will be used.
v2: Explain why we need to assume the worst wrt virtual engines.
Fixes: ca6e56f654 ("drm/i915: Disable semaphore busywaits on saturated systems")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Dmitry Ermilov <dmitry.ermilov@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190618074153.16055-8-chris@chris-wilson.co.uk
To continue the onslaught of removing the assumption of a global
execution ordering, another casualty is the engine->timeline. Without an
actual timeline to track, it is overkill and we can replace it with a
much less grand plain list. We still need a list of requests inflight,
for the simple purpose of finding inflight requests (for retiring,
resetting, preemption etc).
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/20190614164606.15633-3-chris@chris-wilson.co.uk
We need to keep the context image pinned in memory until after the GPU
has finished writing into it. Since it continues to write as we signal
the final breadcrumb, we need to keep it pinned until the request after
it is complete. Currently we know the order in which requests execute on
each engine, and so to remove that presumption we need to identify a
request/context-switch we know must occur after our completion. Any
request queued after the signal must imply a context switch, for
simplicity we use a fresh request from the kernel context.
The sequence of operations for keeping the context pinned until saved is:
- On context activation, we preallocate a node for each physical engine
the context may operate on. This is to avoid allocations during
unpinning, which may be from inside FS_RECLAIM context (aka the
shrinker)
- On context deactivation on retirement of the last active request (which
is before we know the context has been saved), we add the
preallocated node onto a barrier list on each engine
- On engine idling, we emit a switch to kernel context. When this
switch completes, we know that all previous contexts must have been
saved, and so on retiring this request we can finally unpin all the
contexts that were marked as deactivated prior to the switch.
We can enhance this in future by flushing all the idle contexts on a
regular heartbeat pulse of a switch to kernel context, which will also
be used to check for hung engines.
v2: intel_context_active_acquire/_release
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/20190614164606.15633-1-chris@chris-wilson.co.uk
Rename the engine this HW context is currently active upon (that we are
flying upon) to disambiguate between the mixture of different active
terms (and prevent conflict in future patches).
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/20190528092956.14910-14-chris@chris-wilson.co.uk
Some users require that when a master batch is executed on one particular
engine, a companion batch is run simultaneously on a specific slave
engine. For this purpose, we introduce virtual engine bonding, allowing
maps of master:slaves to be constructed to constrain which physical
engines a virtual engine may select given a fence on a master engine.
For the moment, we continue to ignore the issue of preemption deferring
the master request for later. Ideally, we would like to then also remove
the slave and run something else rather than have it stall the pipeline.
With load balancing, we should be able to move workload around it, but
there is a similar stall on the master pipeline while it may wait for
the slave to be executed. At the cost of more latency for the bonded
request, it may be interesting to launch both on their engines in
lockstep. (Bubbles abound.)
Opens: Also what about bonding an engine as its own master? It doesn't
break anything internally, so allow the silliness.
v2: Emancipate the bonds
v3: Couple in delayed scheduling for the selftests
v4: Handle invalid mutually exclusive bonding
v5: Mention what the uapi does
v6: s/nbond/num_bonds/
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/20190521211134.16117-9-chris@chris-wilson.co.uk
Allow the user to direct which physical engines of the virtual engine
they wish to execute one, as sometimes it is necessary to override the
load balancing algorithm.
v2: Only kick the virtual engines on context-out if required
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/20190521211134.16117-7-chris@chris-wilson.co.uk
Having allowed the user to define a set of engines that they will want
to only use, we go one step further and allow them to bind those engines
into a single virtual instance. Submitting a batch to the virtual engine
will then forward it to any one of the set in a manner as best to
distribute load. The virtual engine has a single timeline across all
engines (it operates as a single queue), so it is not able to concurrently
run batches across multiple engines by itself; that is left up to the user
to submit multiple concurrent batches to multiple queues. Multiple users
will be load balanced across the system.
The mechanism used for load balancing in this patch is a late greedy
balancer. When a request is ready for execution, it is added to each
engine's queue, and when an engine is ready for its next request it
claims it from the virtual engine. The first engine to do so, wins, i.e.
the request is executed at the earliest opportunity (idle moment) in the
system.
As not all HW is created equal, the user is still able to skip the
virtual engine and execute the batch on a specific engine, all within the
same queue. It will then be executed in order on the correct engine,
with execution on other virtual engines being moved away due to the load
detection.
A couple of areas for potential improvement left!
- The virtual engine always take priority over equal-priority tasks.
Mostly broken up by applying FQ_CODEL rules for prioritising new clients,
and hopefully the virtual and real engines are not then congested (i.e.
all work is via virtual engines, or all work is to the real engine).
- We require the breadcrumb irq around every virtual engine request. For
normal engines, we eliminate the need for the slow round trip via
interrupt by using the submit fence and queueing in order. For virtual
engines, we have to allow any job to transfer to a new ring, and cannot
coalesce the submissions, so require the completion fence instead,
forcing the persistent use of interrupts.
- We only drip feed single requests through each virtual engine and onto
the physical engines, even if there was enough work to fill all ELSP,
leaving small stalls with an idle CS event at the end of every request.
Could we be greedy and fill both slots? Being lazy is virtuous for load
distribution on less-than-full workloads though.
Other areas of improvement are more general, such as reducing lock
contention, reducing dispatch overhead, looking at direct submission
rather than bouncing around tasklets etc.
sseu: Lift the restriction to allow sseu to be reconfigured on virtual
engines composed of RENDER_CLASS (rcs).
v2: macroize check_user_mbz()
v3: Cancel virtual engines on wedging
v4: Commence commenting
v5: Replace 64b sibling_mask with a list of class:instance
v6: Drop the one-element array in the uabi
v7: Assert it is an virtual engine in to_virtual_engine()
v8: Skip over holes in [class][inst] so we can selftest with (vcs0, vcs2)
Link: https://github.com/intel/media-driver/pull/283
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/20190521211134.16117-6-chris@chris-wilson.co.uk
With the disappearance of NEWCLIENT, we no longer need to provide the
priority boost on preemption in order to prevent repeated gazumping,
and we can remove the dead code.
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/20190515130052.4475-5-chris@chris-wilson.co.uk
Commit 1413b2bc07 ("drm/i915: Trim NEWCLIENT boosting") had the
intended consequence of not allowing a sequence of work that merely
crossed into a new engine the privilege to be promoted to NEWCLIENT
status. It also had the unintended consequence of actually making
NEWCLIENT effective on heavily oversubscribed transcode machines and
impacting upon their throughput.
If we consider a client packet composed of (rcsA, rcsB, vcs) and 30 of
those clients, using the NEWCLIENT boost that will be scheduled as
rcsA x 30, (rcsB, vcs) x 30
where as before it would have been
(rcsA, rcsB, vcs) x 30
That is with NEWCLIENT only boosting the first request of each client,
we would execute all rcsA requests prior to running on the vcs engines;
acruing a lot of dead time as compared to the previous case where the
vcs engine would be started in parallel to processing the second client.
The previous patch has the effect of delaying submission until it is
required by a third party (either the user with an explicit wait, or by
another client/engine). We reduce the NEWCLIENT bump to a mere WAIT,
which has the effect of removing its preemptive grant and reducing it to
the same level as any other user interaction -- that it will not be
promoted above the interengine dependencies, and so preventing NEWCLIENTS
from starving other engines. This a large nerf to the rrul properties of
the current NEWCLIENT, but it still does give prioritised submission to
new requests from light workloads.
References: b16c765122 ("drm/i915: Priority boost for new clients")
Fixes: 1413b2bc07 ("drm/i915: Trim NEWCLIENT boosting") # customer impact
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Dmitry Ermilov <dmitry.ermilov@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190515130052.4475-4-chris@chris-wilson.co.uk
After realising we need to sample RING_START to detect context switches
from preemption events that do not allow for the seqno to advance, we
can also realise that the seqno itself is just a distance along the ring
and so can be replaced by sampling RING_HEAD.
v2: Bonus comment for the mystery separate CS_STALL before MI_USER_INTERRUPT
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/20190508080704.24223-1-chris@chris-wilson.co.uk
If we couple the scheduler more tightly with the execlists policy, we
can apply the preemption policy to the question of whether we need to
kick the tasklet at all for this priority bump.
v2: Rephrase it as a core i915 policy and not an execlists foible.
v3: Pull the kick together.
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/20190507122544.12698-1-chris@chris-wilson.co.uk
Due to the asynchronous tasklet and recursive GT wakeref, it may happen
that we submit to the engine (underneath it's own wakeref) prior to the
central wakeref being marked as taken. Switch to checking the local wakeref
for greater consistency.
Fixes: 79ffac8599 ("drm/i915: Invert the GEM wakeref hierarchy")
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/20190503115225.30831-3-chris@chris-wilson.co.uk
Tidy up the cleanup sequence by always ensure that the tasklet is
flushed on parking (before we cleanup). The parking provides a
convenient point to ensure that the backend is truly idle.
v2: Do the full check for idleness before parking, to be sure we flush
any residual interrupt.
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/20190503080942.30151-1-chris@chris-wilson.co.uk
Make the engine responsible for cleaning itself up!
This removes the i915->gt.cleanup vfunc that has been annoying the
casual reader and myself for the last several years, and helps keep a
future patch to add more cleanup tidy.
v2: Assert that engine->destroy is set after the backend starts
allocating its own state.
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/20190501103204.18632-1-chris@chris-wilson.co.uk
In the next patch, we require the engine vfuncs setup prior to
initialising the pinned kernel contexts, so split the vfunc setup from
the engine initialisation and call it earlier.
v2: s/setup_xcs/setup_common/ for intel_ring_submission_setup()
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/20190426163336.15906-6-chris@chris-wilson.co.uk
In the current scheme, on submitting a request we take a single global
GEM wakeref, which trickles down to wake up all GT power domains. This
is undesirable as we would like to be able to localise our power
management to the available power domains and to remove the global GEM
operations from the heart of the driver. (The intent there is to push
global GEM decisions to the boundary as used by the GEM user interface.)
Now during request construction, each request is responsible via its
logical context to acquire a wakeref on each power domain it intends to
utilize. Currently, each request takes a wakeref on the engine(s) and
the engines themselves take a chipset wakeref. This gives us a
transition on each engine which we can extend if we want to insert more
powermangement control (such as soft rc6). The global GEM operations
that currently require a struct_mutex are reduced to listening to pm
events from the chipset GT wakeref. As we reduce the struct_mutex
requirement, these listeners should evaporate.
Perhaps the biggest immediate change is that this removes the
struct_mutex requirement around GT power management, allowing us greater
flexibility in request construction. Another important knock-on effect,
is that by tracking engine usage, we can insert a switch back to the
kernel context on that engine immediately, avoiding any extra delay or
inserting global synchronisation barriers. This makes tracking when an
engine and its associated contexts are idle much easier -- important for
when we forgo our assumed execution ordering and need idle barriers to
unpin used contexts. In the process, it means we remove a large chunk of
code whose only purpose was to switch back to the kernel context.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190424200717.1686-5-chris@chris-wilson.co.uk
We wish to start segregating the power management into different control
domains, both with respect to the hardware and the user interface. The
first step is that at the lowest level flow of requests, we want to
process a context event (and not a global GEM operation). In this patch,
we introduce the context callbacks that in future patches will be
redirected to per-engine interfaces leading to global operations as
required.
The intent is that this will be guarded by the timeline->mutex, except
that retiring has not quite finished transitioning over from being
guarded by struct_mutex. So at the moment it is protected by
struct_mutex with a reminded to switch.
v2: Rename default handlers to intel_context_enter_engine.
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/20190424200717.1686-3-chris@chris-wilson.co.uk
Start partitioning off the code that talks to the hardware (GT) from the
uapi layers and move the device facing code under gt/
One casualty is s/intel_ringbuffer.h/intel_engine.h/ with the plan to
subdivide that header and body further (and split out the submission
code from the ringbuffer and logical context handling). This patch aims
to be simple motion so git can fixup inflight patches with little mess.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190424174839.7141-1-chris@chris-wilson.co.uk
