We only allow persistent requests to remain on the GPU past the closure
of their containing context (and process) so long as they are continuously
checked for hangs or allow other requests to preempt them, as we need to
ensure forward progress of the system. If we allow persistent contexts
to remain on the system after the the hangcheck mechanism is disabled,
the system may grind to a halt. On disabling the mechanism, we sent a
pulse along the engine to remove all executing contexts from the engine
which would check for hung contexts -- but we did not prevent those
contexts from being resubmitted if they survived the final hangcheck.
Fixes: 9a40bddd47 ("drm/i915/gt: Expose heartbeat interval via sysfs")
Testcase: igt/gem_ctx_persistence/heartbeat-stop
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.7+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-1-chris@chris-wilson.co.uk
(cherry picked from commit 7a991cd3e3)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
The reordering and rebasing of commit 2e4c6c1a9d ("drm/i915: Remove
i915_request.lock requirement for execution callbacks") caused it to
revert an earlier correction. Let us restore commit 99f0a640d464
("drm/i915: Remove requirement for holding i915_request.lock for
breadcrumbs")
Fixes: 2e4c6c1a9d ("drm/i915: Remove i915_request.lock requirement for execution callbacks")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200925101107.27869-1-chris@chris-wilson.co.uk
(cherry picked from commit 35faeb7de9)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
To implement preempt-to-busy (and so efficient timeslicing and best utilization
of the hardware submission ports) we let the GPU run asynchronously in respect
to the ELSP submission queue. This created challenges in keeping and accessing
the driver state mirroring the asynchronous GPU execution.
Previous fix 1d9221e9d3 ("drm/i915: Skip signaling a signaled request")
however did not correctly serialize request retirement with the execution
callbacks.
We were using the i915_request.lock to serialise adding an execution callback
with __i915_request_submit. However, if we use an atomic llist_add to serialise
multiple waiters and then check to see if the request is already executing, we
can remove the irq-spinlock and fix serialization between retirement and
execution callbacks in one go.
v2: Avoid using the irq_work when outside of the irq-spinlocks, where we
can execute the callbacks immediately.
v3: Pay close attention to the order of setting ACTIVE on retirement, we
need to ensure the request is signaled and breadcrumbs detached before
we finish removing the request from the engine.
v4: Expanded commit message.
Fixes: 1d9221e9d3 ("drm/i915: Skip signaling a signaled 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/20200716142207.13003-2-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
[Joonas: Added expanded commit message from Tvrtko and Chris]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
To implement preempt-to-busy (and so efficient timeslicing and best utilization
of the hardware submission ports) we let the GPU run asynchronously in respect
to the ELSP submission queue. This created challenges in keeping and accessing
the driver state mirroring the asynchronous GPU execution.
The latest occurence of this was spotted by KCSAN:
[ 1413.563200] BUG: KCSAN: data-race in __await_execution+0x217/0x370 [i915]
[ 1413.563221]
[ 1413.563236] race at unknown origin, with read to 0xffff88885bb6c478 of 8 bytes by task 9654 on cpu 1:
[ 1413.563548] __await_execution+0x217/0x370 [i915]
[ 1413.563891] i915_request_await_dma_fence+0x4eb/0x6a0 [i915]
[ 1413.564235] i915_request_await_object+0x421/0x490 [i915]
[ 1413.564577] i915_gem_do_execbuffer+0x29b7/0x3c40 [i915]
[ 1413.564967] i915_gem_execbuffer2_ioctl+0x22f/0x5c0 [i915]
[ 1413.564998] drm_ioctl_kernel+0x156/0x1b0
[ 1413.565022] drm_ioctl+0x2ff/0x480
[ 1413.565046] __x64_sys_ioctl+0x87/0xd0
[ 1413.565069] do_syscall_64+0x4d/0x80
[ 1413.565094] entry_SYSCALL_64_after_hwframe+0x44/0xa9
To complicate matters, we have to both avoid the read tearing of *active and
avoid any write tearing as perform the pending[] -> inflight[] promotion of the
execlists.
This is because we cannot rely on the memcpy doing u64 aligned copies on all
kernels/platforms and so we opt to open-code it with explicit WRITE_ONCE
annotations to satisfy KCSAN.
v2: When in doubt, write the same comment again.
v3: Expanded commit message.
Fixes: b55230e5e8 ("drm/i915: Check for awaits on still currently executing requests")
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/20200716142207.13003-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
[Joonas: Added expanded commit message from Tvrtko and Chris]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Currently we hold no actual reference to the request nor context while
they are attached to a breadcrumb. To avoid freeing the request/context
too early, we serialise with cancel-breadcrumbs by taking the irq
spinlock in i915_request_retire(). The alternative is to take a
reference for a new breadcrumb and release it upon signaling; removing
the more frequently hit contention point in i915_request_retire().
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/20200801160225.6814-2-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
On the virtual engines, we only use the intel_breadcrumbs for tracking
signaling of stale breadcrumbs from the irq_workers. They do not have
any associated interrupt handling, active requests are passed to a
physical engine and associated breadcrumb interrupt handler. This causes
issues for us as we need to ensure that we do not actually try and
enable interrupts and the powermanagement required for them on the
virtual engine, as they will never be disabled. Instead, let's
specify the physical engine used for interrupt handler on a particular
breadcrumb.
v2: Drop b->irq_armed = true mocking for no interrupt HW
Fixes: 4fe6abb8f5 ("drm/i915/gt: Ignore irq enabling on the virtual engines")
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/20200731154834.8378-4-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
After staring at the breadcrumb enabling/cancellation and coming to the
conclusion that the cause of the mysterious stale breadcrumbs must the
act of submitting a completed requests, we can then redirect those
completed requests onto a dedicated signaled_list at the time of
construction and so eliminate intel_engine_transfer_stale_breadcrumbs().
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/20200731154834.8378-2-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Since the breadcrumb enabling/cancelling itself is serialised by the
breadcrumbs.irq_lock, with a bit of care we can remove the outer
serialisation with i915_request.lock for concurrent
dma_fence_enable_signaling(). This has the important side-effect of
eliminating the nested i915_request.lock within request submission.
The challenge in serialisation is around the unsubmission where we take
an active request that wants a breadcrumb on the signaling engine and
put it to sleep. We do not want a concurrent
dma_fence_enable_signaling() to attach a breadcrumb as we unsubmit, so
we must mark the request as no longer active before serialising with the
concurrent enable-signaling.
On retire, we serialise with the concurrent enable-signaling, but
instead of clearing ACTIVE, we mark it as SIGNALED.
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/20200731154834.8378-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
I915_GEM_THROTTLE dates back to the time before contexts where there was
just a single engine, and therefore a single timeline and request list
globally. That request list was in execution/retirement order, and so
walking it to find a particular aged request made sense and could be
split per file.
That is no more. We now have many timelines with a file, as many as the
user wants to construct (essentially per-engine, per-context). Each of
those run independently and so make the single list futile. Remove the
disordered list, and iterate over all the timelines to find a request to
wait on in each to satisfy the criteria that the CPU is no more than 20ms
ahead of its oldest request.
It should go without saying that the I915_GEM_THROTTLE ioctl is no
longer used as the primary means of throttling, so it makes sense to push
the complication into the ioctl where it only impacts upon its few
irregular users, rather than the execbuf/retire where everybody has to
pay the cost. Fortunately, the few users do not create vast amount of
contexts, so the loops over contexts/engines should be concise.
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>
Link: https://patchwork.freedesktop.org/patch/msgid/20200728152010.30701-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
We include a tasklet flush before waiting on a request as a precaution
against the HW being lax in event signaling. We now have a precautionary
flush in the engine's heartbeat and so do not need to be quite so
zealous on every request wait. If we focus on the request, the only
tasklet flush that matters is if there is a delay in submitting this
request to HW, so if the request is not ready to be executed, no
advantage in reducing this wait can be gained by running the tasklet.
And there is little point in doing busy work for no result.
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/20200715115147.11866-10-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Currently, we use i915_request_completed() directly in
i915_request_wait() and follow up with a manual invocation of
dma_fence_signal(). This appears to cause a large number of contentions
on i915_request.lock as when the process is woken up after the fence is
signaled by an interrupt, we will then try and call dma_fence_signal()
ourselves while the signaler is still holding the lock.
dma_fence_is_signaled() has the benefit of checking the
DMA_FENCE_FLAG_SIGNALED_BIT prior to calling dma_fence_signal() and so
avoids most of that contention.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200716100754.5670-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
It's been a while since gen6_rps_boost() [that only worked on gen6+] was
replaced by intel_rps_boost() that understood itself when rps was
active. Since the intel_rps_boost() is gen-agnostic, just call it.
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/20200728152219.1387-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Preempt-to-busy introduces various fascinating complications in that the
requests may complete as we are unsubmitting them from HW. As they may
then signal after unsubmission, we may find ourselves having to cleanup
the signaling request from within the signaling callback. This causes us
to recurse onto the same i915_request.lock.
However, if the request is already signaled (as it will be before we
enter the signal callbacks), we know we can skip the signaling of that
request during submission, neatly evading the spinlock recursion.
unsubmit(ve.rq0) # timeslice expiration or other preemption
-> virtual_submit_request(ve.rq0)
dma_fence_signal(ve.rq0) # request completed before preemption ack
-> submit_notify(ve.rq1)
-> virtual_submit_request(ve.rq1) # sees that we have completed ve.rq0
-> __i915_request_submit(ve.rq0)
[ 264.210142] BUG: spinlock recursion on CPU#2, sample_multi_tr/2093
[ 264.210150] lock: 0xffff9efd6ac55080, .magic: dead4ead, .owner: sample_multi_tr/2093, .owner_cpu: 2
[ 264.210155] CPU: 2 PID: 2093 Comm: sample_multi_tr Tainted: G U
[ 264.210158] Hardware name: Intel Corporation CoffeeLake Client Platform/CoffeeLake S UDIMM RVP, BIOS CNLSFWR1.R00.X212.B01.1909060036 09/06/2019
[ 264.210160] Call Trace:
[ 264.210167] dump_stack+0x98/0xda
[ 264.210174] spin_dump.cold+0x24/0x3c
[ 264.210178] do_raw_spin_lock+0x9a/0xd0
[ 264.210184] _raw_spin_lock_nested+0x6a/0x70
[ 264.210314] __i915_request_submit+0x10a/0x3c0 [i915]
[ 264.210415] virtual_submit_request+0x9b/0x380 [i915]
[ 264.210516] submit_notify+0xaf/0x14c [i915]
[ 264.210602] __i915_sw_fence_complete+0x8a/0x230 [i915]
[ 264.210692] i915_sw_fence_complete+0x2d/0x40 [i915]
[ 264.210762] __dma_i915_sw_fence_wake+0x19/0x30 [i915]
[ 264.210767] dma_fence_signal_locked+0xb1/0x1c0
[ 264.210772] dma_fence_signal+0x29/0x50
[ 264.210871] i915_request_wait+0x5cb/0x830 [i915]
[ 264.210876] ? dma_resv_get_fences_rcu+0x294/0x5d0
[ 264.210974] i915_gem_object_wait_fence+0x2f/0x40 [i915]
[ 264.211084] i915_gem_object_wait+0xce/0x400 [i915]
[ 264.211178] i915_gem_wait_ioctl+0xff/0x290 [i915]
Fixes: 22b7a426bb ("drm/i915/execlists: Preempt-to-busy")
References: 6d06779e86 ("drm/i915: Load balancing across a virtual engine")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: "Nayana, Venkata Ramana" <venkata.ramana.nayana@intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200713141636.29326-1-chris@chris-wilson.co.uk
We infrequently use the direct i915 backpointer from the i915_request,
so do we really need to waste the space in the struct for it? 8 bytes
from the most frequently allocated struct vs an 3 bytes and pointer
chasing in using rq->engine->i915?
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200602220953.21178-1-chris@chris-wilson.co.uk
With the advent of preempt-to-busy, a request may still be on the GPU as
we unwind. And in the case of a unpreemptible [due to HW] request, that
request will remain indefinitely on the GPU even though we have
returned it back to our submission queue, and cleared the active bit.
We only run the execution callbacks on transferring the request from our
submission queue to the execution queue, but if this is a bonded request
that the HW is waiting for, we will not submit it (as we wait for a
fresh execution) even though it is still being executed.
As we know that there are always preemption points between requests, we
know that only the currently executing request may be still active even
though we have cleared the flag. However, we do not precisely know which
request is in ELSP[0] due to a delay in processing events, and
furthermore we only store the last request in a context in our state
tracker.
Fixes: 22b7a426bb ("drm/i915/execlists: Preempt-to-busy")
Testcase: igt/gem_exec_balancer/bonded-dual
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/20200529143926.3245-1-chris@chris-wilson.co.uk
When we push a virtual request onto the HW, we update the rq->engine to
point to the physical engine. A request that is then submitted by the
user that waits upon the virtual engine, but along the physical engine
in use, will then see that it is due to be submitted to the same engine
and take a shortcut (and be queued without waiting for the completion
fence). However, the virtual request may be preempted (either by higher
priority users, or by timeslicing) and removed from the physical engine
to be migrated over to one of its siblings. The dependent normal request
however is oblivious to the removal of the virtual request and remains
queued to execute on HW, believing that once it reaches the head of its
queue all of its predecessors will have completed executing!
v2: Beware restriction of signal->execution_mask prior to submission.
Fixes: 6d06779e86 ("drm/i915: Load balancing across a virtual engine")
Testcase: igt/gem_exec_balancer/sliced
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: <stable@vger.kernel.org> # v5.3+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200526090753.11329-2-chris@chris-wilson.co.uk
Reduce the irq_work llist for attaching the callbacks to the signal for
both smaller structs (two fewer pointers!) and simpler [debug] code:
Function old new delta
irq_execute_cb 35 34 -1
__igt_breadcrumbs_smoketest 1684 1682 -2
i915_request_retire 2003 1996 -7
__i915_request_create 1047 1040 -7
__notify_execute_cb 135 126 -9
__i915_request_ctor 188 178 -10
__await_execution.part.constprop 451 440 -11
igt_wait_request 924 714 -210
One minor artifact is that the order of cb exection is reversed. No
current use cases are affected by that change.
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/20200526112051.10229-1-chris@chris-wilson.co.uk
In order to be valid to dereference during the i915_fence_release, after
retiring the fence and releasing its refererences, we assume that
rq->engine can only be a real engine (that stay intact until the device
is shutdown after all fences have been flushed). However, due to a quirk
of preempt-to-busy, we may retire a request that still belongs to a
virtual engine and so eventually free it with rq->engine being invalid.
To avoid dereferencing that invalid engine, we look at the
execution_mask which if it indicates it may be executed on more than one
engine, we know it originated on a virtual engine and may still be on
one.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1906
Fixes: 43acd6516c ("drm/i915: Keep a per-engine request pool")
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/20200521140617.30015-2-chris@chris-wilson.co.uk
Now that we have fast timeslicing on semaphores, we no longer need to
prioritise none-semaphore work as we will yield any work blocked on a
semaphore to the next in the queue. Previously with no timeslicing,
blocking on the semaphore caused extremely bad scheduling with multiple
clients utilising multiple rings. Now, there is no impact and we can
remove the complication.
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/20200513173504.28322-1-chris@chris-wilson.co.uk
The initial-breadcrumb is used to mark the end of the awaiting and the
beginning of the user payload. We verify that we do not start the user
payload before all signaler are completed, checking our semaphore setup
by looking for the initial breadcrumb being written too early. We also
want to ensure that we do not add semaphore waits after we have already
closed the semaphore section, an issue for later deferred waits.
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/20200513165937.9508-2-chris@chris-wilson.co.uk
Expose the hardcoded timeout for unsignaled foreign fences as a Kconfig
option, primarily to allow brave systems to disable the timeout and
solely rely on correct signaling.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200509105021.12542-1-chris@chris-wilson.co.uk
The downside of using semaphores is that we lose metadata passing
along the signaling chain. This is particularly nasty when we
need to pass along a fatal error such as EFAULT or EDEADLK. For
fatal errors we want to scrub the request before it is executed,
which means that we cannot preload the request onto HW and have
it wait upon a semaphore.
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/20200508092933.738-3-chris@chris-wilson.co.uk
To allow faster engine to engine synchronization, peel the layer of
dma-fence-chain to expose potential i915 fences so that the
i915_request code can emit HW semaphore wait/signal operations in the
ring which is faster than waking up the host to submit unblocked
workloads after interrupt notification.
This is similar to the peeling we do for e.g. dma_fence_array.
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/20200508185448.29709-1-chris@chris-wilson.co.uk
As a means for a small code consolidation, but primarily to start
thinking more carefully about internal-vs-external linkage, pull the
pair of i915_sw_fence_await_dma_fence() calls into a common routine.
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/20200508092933.738-2-chris@chris-wilson.co.uk
While we ordinarily do not skip submit-fences due to the accompanying
hook that we want to callback on execution, a submit-fence on the same
timeline is meaningless.
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/20200508092933.738-1-chris@chris-wilson.co.uk
Upon waiting a request (when asked), we gave that request a small
priority boost, not enough for it to cause preemption, but enough for it
to be scheduled next before all equals. We also used that bit to give
new clients a small priority boost, similar to FQ_CODEL, such that we
favoured short interactive tasks ahead of long running streams.
However, this is causing lots of complications with timeslicing where we
both want to honour the boost and yet ignore it. Those complications
cause unexpected user behaviour (tasks not being timesliced and run
concurrently as epxected), and the easiest way to resolve that is to
remove the boost. Hopefully, we can find a compromise again if we need
to, but in theory timeslicing itself and future more advanced schedulers
should give us the interactivity boost we seek.
Testcase: igt/gem_exec_schedule/lateslice
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/20200507152338.7452-3-chris@chris-wilson.co.uk
We recorded the dependencies for WAIT_FOR_SUBMIT in order that we could
correctly perform priority inheritance from the parallel branches to the
common trunk. However, for the purpose of timeslicing and reset
handling, the dependency is weak -- as we the pair of requests are
allowed to run in parallel and not in strict succession.
The real significance though is that this allows us to rearrange
groups of WAIT_FOR_SUBMIT linked requests along the single engine, and
so can resolve user level inter-batch scheduling dependencies from user
semaphores.
Fixes: c81471f5e9 ("drm/i915: Copy across scheduler behaviour flags across submit fences")
Testcase: igt/gem_exec_fence/submit
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: <stable@vger.kernel.org> # v5.6+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200507155109.8892-1-chris@chris-wilson.co.uk
We need to preserve fatal errors from fences that are being terminated
as we hook them up.
Fixes: ef46884975 ("drm/i915: Propagate fence errors")
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: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200506162136.3325-1-chris@chris-wilson.co.uk
Add a tiny per-engine request mempool so that we should always have a
request available for powermanagement allocations from tricky
contexts. This reserve is expected to be only used for kernel
contexts when barriers must be emitted [almost] without fail.
The main consumer for this reserved request is expected to be engine-pm,
for which we know that there will always be at least the previous pm
request that we can reuse under mempressure (so there should always be
a spare request for engine_park()).
This is an alternative to using a comparatively bulky mempool, which
requires custom handling for both our reserved allocation requirement
and to protect our TYPESAFE_BY_RCU slab cache. The advantage of mempool
would be that it would allow us to keep a larger per-engine request
pool. However, converting over to mempool is straightforward should the
need arise.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-and-tested-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200402184037.21630-1-chris@chris-wilson.co.uk
Drop the pretense of kicking the tasklet (used only for the defunct guc
submission backend, it should just take ownership of the submit!) and so
remove the bh-kicking from around submission.
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/20200323092841.22240-5-chris@chris-wilson.co.uk
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
Always wait on the start of the signaler request to reduce the problem
of dequeueing the bonded pair too early -- we want both payloads to
start at the same time, with no latency, and yet still allow others to
make full use of the slack in the system. This reduce the amount of time
we spend waiting on the semaphore used to synchronise the start of the
bonded payload.
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/20200306133852.3420322-3-chris@chris-wilson.co.uk
Requests within a timeline are ordered by that timeline, so awaiting for
the start of a request within the timeline is a no-op. This used to work
by falling out of the mutex_trylock() as the signaler and waiter had the
same timeline and not returning an error.
Fixes: 6a79d84840 ("drm/i915: Lock signaler timeline while navigating")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.5+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200305134822.2750496-1-chris@chris-wilson.co.uk
Fix the inverted test to emit the wait on the end of the previous
request if we /haven't/ already.
Fixes: 6a79d84840 ("drm/i915: Lock signaler timeline while navigating")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.5+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200305104210.2619967-1-chris@chris-wilson.co.uk
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
As setup takes a long time, the user may close the context during the
construction of the execbuf. In order to make sure we correctly track
all outstanding work with non-persistent contexts, we need to serialise
the submission with the context closure and mop up any leaks.
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/20200303080546.1140508-3-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
We need to be extremely careful inside i915_request_await_start() as it
needs to walk the list of requests in the foreign timeline with very
little protection. As we hold our own timeline mutex, we can not nest
inside the signaler's timeline mutex, so all that remains is our RCU
protection. However, to be safe we need to tell the compiler that we may
be traversing the list only under RCU protection, and furthermore we
need to start declaring requests as elements of the timeline from their
construction.
Fixes: 9ddc8ec027 ("drm/i915: Eliminate the trylock for awaiting an earlier request")
Fixes: 6a79d84840 ("drm/i915: Lock signaler timeline while navigating")
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/20200227085723.1961649-11-chris@chris-wilson.co.uk
On retiring the request, we should not re-use these elements in the ring
(at least not until we fill the ringbuffer and knowingly reuse the space).
Leave behind some poison to (hopefully) trap ourselves if we make a
mistake.
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>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200211205615.1190127-1-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
Rather than flushing the submission tasklets just before we sleep, flush
before we check the request status. Ideally this gives us a moment to
process the tasklets after sleeping just before we timeout.
v2: Compromise by pushing the flush prior to the timeout, but after the
check on completion so that we do not further delay the ready client.
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/20200205095441.1769599-1-chris@chris-wilson.co.uk
Inside the intel_timeline_get_seqno(), we currently track the retirement
of the old cachelines by listening to the new request. This requires
that the new request is ready to be used and so requires a minimum bit
of initialisation prior to getting the new seqno.
Fixes: b1e3177bd1 ("drm/i915: Coordinate i915_active with its own mutex")
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/20200203094152.4150550-2-chris@chris-wilson.co.uk
Chris Wilson