Parallel submission create composite fences (dma_fence_array) for excl /
shared slots in objects. The I915_GEM_BUSY IOCTL checks these slots to
determine the busyness of the object. Prior to patch it only check if
the fence in the slot was a i915_request. Update the check to understand
composite fences and correctly report the busyness.
v2:
(Tvrtko)
- Remove duplicate BUILD_BUG_ON
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-24-matthew.brost@intel.com
Allow multiple batch buffers to be submitted in a single execbuf IOCTL
after a context has been configured with the 'set_parallel' extension.
The number batches is implicit based on the contexts configuration.
This is implemented with a series of loops. First a loop is used to find
all the batches, a loop to pin all the HW contexts, a loop to create all
the requests, a loop to submit (emit BB start, etc...) all the requests,
a loop to tie the requests to the VMAs they touch, and finally a loop to
commit the requests to the backend.
A composite fence is also created for the generated requests to return
to the user and to stick in dma resv slots.
No behavior from the existing IOCTL should be changed aside from when
throttling because the ring for a context is full. In this situation,
i915 will now wait while holding the object locks. This change was done
because the code is much simpler to wait while holding the locks and we
believe there isn't a huge benefit of dropping these locks. If this
proves false we can restructure the code to drop the locks during the
wait.
IGT: https://patchwork.freedesktop.org/patch/447008/?series=93071&rev=1
media UMD: https://github.com/intel/media-driver/pull/1252
v2:
(Matthew Brost)
- Return proper error value if i915_request_create fails
v3:
(John Harrison)
- Add comment explaining create / add order loops + locking
- Update commit message explaining different in IOCTL behavior
- Line wrap some comments
- eb_add_request returns void
- Return -EINVAL rather triggering BUG_ON if cmd parser used
(Checkpatch)
- Check eb->batch_len[*current_batch]
v4:
(CI)
- Set batch len if passed if via execbuf args
- Call __i915_request_skip after __i915_request_commit
(Kernel test robot)
- Initialize rq to NULL in eb_pin_timeline
v5:
(John Harrison)
- Fix typo in comments near bb order loops
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-21-matthew.brost@intel.com
Implement multi-lrc submission via a single workqueue entry and single
H2G. The workqueue entry contains an updated tail value for each
request, of all the contexts in the multi-lrc submission, and updates
these values simultaneously. As such, the tasklet and bypass path have
been updated to coalesce requests into a single submission.
v2:
(John Harrison)
- s/wqe/wqi
- Use FIELD_PREP macros
- Add GEM_BUG_ONs ensures length fits within field
- Add comment / white space to intel_guc_write_barrier
(Kernel test robot)
- Make need_tasklet a static function
v3:
(Docs)
- A comment for submission_stall_reason
v4:
(Kernel test robot)
- Initialize return value in bypass tasklt submit function
(John Harrison)
- Add comment near work queue defs
- Add BUILD_BUG_ON to ensure WQ_SIZE is a power of 2
- Update write_barrier comment to talk about work queue
v5:
(John Harrison)
- Fix typo in work queue comment
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-13-matthew.brost@intel.com
Add GuC kernel doc for all structures added thus far for GuC submission
and update the main GuC submission section with the new interface
details.
v2:
- Drop guc_active.lock DOC
v3:
- Fixup a few kernel doc comments (Daniele)
v4 (Daniele):
- Implement doc suggestions from John
- Add kerneldoc for all members of the GuC structure and pull the file
in i915.rst
v5 (Daniele):
- Implement new doc suggestions from John
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210909164744.31249-24-matthew.brost@intel.com
A subsequent patch will flip the locking hierarchy from
ce->guc_state.lock -> sched_engine->lock to sched_engine->lock ->
ce->guc_state.lock. As such we need to release the submit fence for a
request from an IRQ to break a lock inversion - i.e. the fence must be
release went holding ce->guc_state.lock and the releasing of the can
acquire sched_engine->lock.
v2:
(Daniele)
- Delete request from list before calling irq_work_queue
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210909164744.31249-16-matthew.brost@intel.com
With the global kmem_cache shrink infrastructure gone there's nothing
special and we can convert them over.
I'm doing this split up into each patch because there's quite a bit of
noise with removing the static global.slab_requests|execute_cbs to just a
slab_requests|execute_cbs.
v2: Make slab static (Jason, 0day)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-7-daniel.vetter@ffwll.ch
Implement a simple static mapping algorithm of the i915 priority levels
(int, -1k to 1k exposed to user) to the 4 GuC levels. Mapping is as
follows:
i915 level < 0 -> GuC low level (3)
i915 level == 0 -> GuC normal level (2)
i915 level < INT_MAX -> GuC high level (1)
i915 level == INT_MAX -> GuC highest level (0)
We believe this mapping should cover the UMD use cases (3 distinct user
levels + 1 kernel level).
In addition to static mapping, a simple counter system is attached to
each context tracking the number of requests inflight on the context at
each level. This is needed as the GuC levels are per context while in
the i915 levels are per request.
v2:
(Daniele)
- Add BUILD_BUG_ON to enforce ordering of priority levels
- Add missing lockdep to guc_prio_fini
- Check for return before setting context registered flag
- Map DISPLAY priority or higher to highest guc prio
- Update comment for guc_prio
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-33-matthew.brost@intel.com
In the case of a full GPU reset (e.g. because GuC has died or because
GuC's hang detection has been disabled), the driver can't rely on GuC
reporting the guilty context. Instead, the driver needs to scan all
active contexts and find one that is currently executing, as per the
execlist mode behaviour. In GuC mode, this scan is different to
execlist mode as the active request list is handled very differently.
Similarly, the request state dump in debugfs needs to be handled
differently when in GuC submission mode.
Also refactured some of the request scanning code to avoid duplication
across the multiple code paths that are now replicating it.
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-20-matthew.brost@intel.com
Move active request tracking to a backend vfunc rather than assuming all
backends want to do this in the manner. In the of case execlists /
ring submission the tracking is on the physical engine while with GuC
submission it is on the context.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-8-matthew.brost@intel.com
Sometimes during context pinning a context with the same guc_id is
registered with the GuC. In this a case deregister must be done before
the context can be registered. A fence is inserted on all requests while
the deregister is in flight. Once the G2H is received indicating the
deregistration is complete the context is registered and the fence is
released.
v2:
(John H)
- Fix commit message
Cc: John Harrison <john.c.harrison@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <john.c.harrison@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210721215101.139794-8-matthew.brost@intel.com
This was only ever used for FENCE_SUBMIT automatic engine selection
which was removed in the previous commit.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-12-jason@jlekstrand.net
Move active request tracking and its lock to i915_sched_engine. This
lock is also the submission lock so having it in the i915_sched_engine
is the correct place.
v3:
(Jason Ekstrand)
Add kernel doc
v6:
Rebase
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.comk>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210618010638.98941-5-matthew.brost@intel.com
Driver Changes:
- Prepare for local/device memory support on DG1 by starting
to use it for kernel internal allocations: context, ring
and engine scratch (Matt A, CQ, Abdiel, Imre)
- Sandybridge fix to avoid hard hang on ring resume (Chris)
- Limit imported dma-buf size to int32 (Matt A)
- Double check heartbeat timeout before resetting (Chris)
- Use new tasklet API for execution list (Emil)
- Fix SPDX checkpats warnings (Chris)
- Fixes for various checkpatch warnings (Chris)
- Selftest improvements (Chris)
- Move the defer_request waiter active assertion to correct spot (Chris)
- Make local-memory probing a GT operation (Matt, Tvrtko)
- Protect against request freeing during cancellation on wedging (Chris)
- Retire unexpected starting state error dumping (Chris)
- Distinction of memory regions in debugging (Zbigniew)
- Always flush the submission queue on checking for idle (Chris)
- Consolidate 2big error check to helper (Matt)
- Decrease number of subplatform bits (Tvrtko)
- Remove unused internal request priority levels (Chris)
- Document the unused internal header bits in buddy allocator (Matt)
- Cleanup the region class/instance encoding (Matt)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YGxksaZGXHnFxlwg@jlahtine-mobl.ger.corp.intel.com
Prepares the plumbing for setting request/fence expiration time. All code
is put in place but is never activated due yet missing ability to actually
configure the timer.
Outline of the basic operation:
A timer is started when request is ready for execution. If the request
completes (retires) before the timer fires, timer is cancelled and nothing
further happens.
If the timer fires request is added to a lockless list and worker queued.
Purpose of this is twofold: a) It allows request cancellation from a more
friendly context and b) coalesces multiple expirations into a single event
of consuming the list.
Worker locklessly consumes the list of expired requests and cancels them
all using previous added i915_request_cancel().
Associated timeout value is stored in rq->context.watchdog.timeout_us.
v2:
* Log expiration.
v3:
* Include more information about user timeline in the log message.
v4:
* Remove obsolete comment and fix formatting. (Matt)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-6-tvrtko.ursulin@linux.intel.com
Currently, we cancel outstanding requests within a context when the
context is closed. We may also want to cancel individual requests using
the same graceful preemption mechanism.
v2 (Tvrtko):
* Cancel waiters carefully considering no timeline lock and RCU.
* Fixed selftests.
v3 (Tvrtko):
* Remove error propagation to waiters for now.
v4 (Tvrtko):
* Rebase for extracted i915_request_active_engine. (Matt)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
[danvet: Resolve conflict because intel_engine_flush_scheduler is
still called intel_engine_flush_submission]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-3-tvrtko.ursulin@linux.intel.com
Move active engine lookup to exported i915_request_active_engine.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
[danvet: Slight rebase, engine->sched.lock is still called
engine->active.lock.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-2-tvrtko.ursulin@linux.intel.com
As soon as we mark a request as completed, it may be retired. So when
cancelling a request and marking it complete, make sure we first keep a
reference to the request.
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/20210201085715.27435-4-chris@chris-wilson.co.uk
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of sharing pages with breadcrumbs, give each timeline a
single page. This allows unrelated timelines not to share locks
any more during command submission.
As an additional benefit, seqno wraparound no longer requires
i915_vma_pin, which means we no longer need to worry about a
potential -EDEADLK at a point where we are ready to submit.
Changes since v1:
- Fix erroneous i915_vma_acquire that should be a i915_vma_release (ickle).
- Extra check for completion in intel_read_hwsp().
Changes since v2:
- Fix inconsistent indent in hwsp_alloc() (kbuild)
- memset entire cacheline to 0.
Changes since v3:
- Do same in intel_timeline_reset_seqno(), and clflush for good measure.
Changes since v4:
- Use refcounting on timeline, instead of relying on i915_active.
- Fix waiting on kernel requests.
Changes since v5:
- Bump amount of slots to maximum (256), for best wraparounds.
- Add hwsp_offset to i915_request to fix potential wraparound hang.
- Ensure timeline wrap test works with the changes.
- Assign hwsp in intel_timeline_read_hwsp() within the rcu lock to
fix a hang.
Changes since v6:
- Rename i915_request_active_offset to i915_request_active_seqno(),
and elaborate the function. (tvrtko)
Changes since v7:
- Move hunk to where it belongs. (jekstrand)
- Replace CACHELINE_BYTES with TIMELINE_SEQNO_BYTES. (jekstrand)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com> #v1
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210323155059.628690-2-maarten.lankhorst@linux.intel.com
When wedging the device, we cancel all outstanding requests and mark
them as EIO. Rather than duplicate the small function to do so between
each submission backend, export one.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210109163455.28466-3-chris@chris-wilson.co.uk
Rather than having special case code for opportunistically calling
process_csb() and performing a direct submit while holding the engine
spinlock for submitting the request, simply call the tasklet directly.
This allows us to retain the direct submission path, including the CS
draining to allow fast/immediate submissions, without requiring any
duplicated code paths, and most importantly greatly simplifying the
control flow by removing reentrancy. This will enable us to close a few
races in the virtual engines in the next few patches.
The trickiest part here is to ensure that paired operations (such as
schedule_in/schedule_out) remain under consistent locking domains,
e.g. when pulled outside of the engine->active.lock
v2: Use bh kicking, see commit 3c53776e29 ("Mark HI and TASKLET
softirq synchronous").
v3: Update engine-reset to be tasklet aware
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/20201224135544.1713-1-chris@chris-wilson.co.uk
Since we allow removing the timeline map at runtime, there is a risk
that rq->hwsp points into a stale page. To control that risk, we hold
the RCU read lock while reading *rq->hwsp, but we missed a couple of
important barriers. First, the unpinning / removal of the timeline map
must be after all RCU readers into that map are complete, i.e. after an
rcu barrier (in this case courtesy of call_rcu()). Secondly, we must
make sure that the rq->hwsp we are about to dereference under the RCU
lock is valid. In this case, we make the rq->hwsp pointer safe during
i915_request_retire() and so we know that rq->hwsp may become invalid
only after the request has been signaled. Therefore is the request is
not yet signaled when we acquire rq->hwsp under the RCU, we know that
rq->hwsp will remain valid for the duration of the RCU read lock.
This is a very small window that may lead to either considering the
request not completed (causing a delay until the request is checked
again, any wait for the request is not affected) or dereferencing an
invalid pointer.
Fixes: 3adac4689f ("drm/i915: Introduce concept of per-timeline (context) HWSP")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: <stable@vger.kernel.org> # v5.1+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201218122421.18344-1-chris@chris-wilson.co.uk
We plan to expand upon the number of available statuses for when we
pretty-print the requests along the timelines, and so need a new set of
flags. We have settled upon:
Unready [U]
- initial status after being submitted, the request is not
ready for execution as it is waiting for external fences
Ready [R]
- all fences the request was waiting on have been signaled,
and the request is now ready for execution and will be
in a backend queue
- a ready request may still need to wait on semaphores
[internal fences]
Ready/virtual [V]
- same as ready, but queued over multiple backends
Executing [E]
- the request has been transferred from the backend queue and
submitted for execution on HW
- a completed request may still be regarded as executing, its
status may not be updated until it is retired and removed
from the lists
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/20201119165616.10834-3-chris@chris-wilson.co.uk
Extract i915_request_show for reuse in other request chain pretty
printers.
For a bonus point, quietly change the seqno format from %llx to %lld to
match everywhere else.
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/20201119165616.10834-2-chris@chris-wilson.co.uk
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>
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>
Since these inline routines only return the desired pointer from the
i915_request(after checking the preconditions for acquiring said
pointer), they can be const.
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/20200616183139.4061-1-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
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
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
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
During i915_request_retire() we decouple the i915_request.hwsp_seqno
from the intel_timeline so that it may be freed before the request is
released. However, we need to warn the compiler that the pointer may
update under its nose.
[ 171.438899] BUG: KCSAN: data-race in i915_request_await_dma_fence [i915] / i915_request_retire [i915]
[ 171.438920]
[ 171.438932] write to 0xffff8881e7e28ce0 of 8 bytes by task 148 on cpu 2:
[ 171.439174] i915_request_retire+0x1ea/0x660 [i915]
[ 171.439408] retire_requests+0x7a/0xd0 [i915]
[ 171.439640] engine_retire+0xa1/0xe0 [i915]
[ 171.439657] process_one_work+0x3b1/0x690
[ 171.439671] worker_thread+0x80/0x670
[ 171.439685] kthread+0x19a/0x1e0
[ 171.439701] ret_from_fork+0x1f/0x30
[ 171.439721]
[ 171.439739] read to 0xffff8881e7e28ce0 of 8 bytes by task 696 on cpu 1:
[ 171.439990] i915_request_await_dma_fence+0x162/0x520 [i915]
[ 171.440230] i915_request_await_object+0x2fe/0x470 [i915]
[ 171.440467] i915_gem_do_execbuffer+0x45dc/0x4c20 [i915]
[ 171.440704] i915_gem_execbuffer2_ioctl+0x2c3/0x580 [i915]
[ 171.440722] drm_ioctl_kernel+0xe4/0x120
[ 171.440736] drm_ioctl+0x297/0x4c7
[ 171.440750] ksys_ioctl+0x89/0xb0
[ 171.440766] __x64_sys_ioctl+0x42/0x60
[ 171.440788] do_syscall_64+0x6e/0x2c0
[ 171.440802] entry_SYSCALL_64_after_hwframe+0x44/0xa9
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/20200309110934.868-1-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
A forgetful copy'n'paste left the name of the old function intact, and
did not introduce the new function 'i915_request_is_ready'
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200117101639.2908469-1-chris@chris-wilson.co.uk
In order to support out-of-line error capture, we need to remove the
active request from HW and put it to one side while a worker compresses
and stores all the details associated with that request. (As that
compression may take an arbitrary user-controlled amount of time, we
want to let the engine continue running on other workloads while the
hanging request is dumped.) Not only do we need to remove the active
request, but we also have to remove its context and all requests that
were dependent on it (both in flight, queued and future submission).
Finally once the capture is complete, we need to be able to resubmit the
request and its dependents and allow them to execute.
v2: Replace stack recursion with a simple list.
v3: Check all the parents, not just the first, when searching for a
stuck ancestor!
References: https://gitlab.freedesktop.org/drm/intel/issues/738
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-2-chris@chris-wilson.co.uk
If we keep track of when the i915_request.sched.link is on the HW
runlist, or in the priority queue we can simplify our interactions with
the request (such as during rescheduling). This also simplifies the next
patch where we introduce a new in-between list, for requests that are
ready but neither on the run list or in the queue.
v2: Update i915_sched_node.link explanation for current usage where it
is a link on both the queue and on the runlists.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116184754.2860848-1-chris@chris-wilson.co.uk
Add a space between the prefixed format and the users format so that the
join are not mistakenly combined into one long word.
Fixes: 639f2f2489 ("drm/i915: Introduce new macros for tracing")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191223204411.2355304-1-chris@chris-wilson.co.uk
The only protection for intel_context.gem_cotext is granted by RCU, so
annotate it as a rcu protected pointer and carefully dereference it in
the few occasions we need to use it.
Fixes: 9f3ccd40ac ("drm/i915: Drop GEM context as a direct link from i915_request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Acked-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191222233558.2201901-1-chris@chris-wilson.co.uk
Keep the intel_context as being the primary state for i915_request, with
the GEM context a backpointer from the low level state for the rarer
cases we need client information. Our goal is to remove such references
to clients from the backend, and leave the HW submission agnostic to
client interfaces and self-contained.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-1-chris@chris-wilson.co.uk
Knowing the round trip time of an engine is useful for tracking the
health of the system as well as providing a metric for the baseline
responsiveness of the engine. We can use the latter metric for
automatically tuning our waits in selftests and when idling so we don't
confuse a slower system with a dead one.
Upon idling the engine, we send one last pulse to switch the context
away from precious user state to the volatile kernel context. We know
the engine is idle at this point, and the pulse is non-preemptible, so
this provides us with a good measurement of the round trip time. It also
provides us with faster engine parking for ringbuffer submission, which
is a welcome bonus (e.g. softer-rc6).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191219105043.4169050-1-chris@chris-wilson.co.uk
Link: https://patchwork.freedesktop.org/patch/msgid/20191219124353.8607-2-chris@chris-wilson.co.uk
As we stash a pointer to the HWSP cacheline on the request, when reading
it we only need confirm that the cacheline is still valid by checking
that the request and timeline are still intact.
v2: Protect hwsp_cachline with RCU
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/20191217011659.3092130-1-chris@chris-wilson.co.uk
New macros ENGINE_TRACE(), CE_TRACE(), RQ_TRACE() and
GT_TRACE() are introduce to tag device name and engine
name with contexts and requests tracing in i915.
Cc: Sudeep Dutt <sudeep.dutt@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@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/20191213155152.69182-2-venkata.s.dhanalakota@intel.com
Sometimes we want to emit a terminator request, a request that flushes
the pipeline and allows no request to come after it. This can be used
for a "preempt-to-idle" to ensure that upon processing the
context-switch to that request, all other active contexts have been
flushed.
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/20191012070136.32058-1-chris@chris-wilson.co.uk
wait_for_timelines is essentially the same loop as retiring requests
(with an extra timeout), so merge the two into one routine.
v2: i915_retire_requests_timeout and keep VT'd w/a as !interruptible
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/20191004134015.13204-10-chris@chris-wilson.co.uk
Maarten Lankhorst