UAPI Changes:
- Weak parallel submission support for execlists
Minimal implementation of the parallel submission support for
execlists backend that was previously only implemented for GuC.
Support one sibling non-virtual engine.
Core Changes:
- Two backmerges of drm/drm-next for header file renames/changes and
i915_regs reorganization
Driver Changes:
- Add new DG2 subplatform: DG2-G12 (Matt R)
- Add new DG2 workarounds (Matt R, Ram, Bruce)
- Handle pre-programmed WOPCM registers for DG2+ (Daniele)
- Update guc shim control programming on XeHP SDV+ (Daniele)
- Add RPL-S C0/D0 stepping information (Anusha)
- Improve GuC ADS initialization to work on ARM64 on dGFX (Lucas)
- Fix KMD and GuC race on accessing PMU busyness (Umesh)
- Use PM timestamp instead of RING TIMESTAMP for reference in PMU with GuC (Umesh)
- Report error on invalid reset notification from GuC (John)
- Avoid WARN splat by holding RPM wakelock during PXP unbind (Juston)
- Fixes to parallel submission implementation (Matt B.)
- Improve GuC loading status check/error reports (John)
- Tweak TTM LRU priority hint selection (Matt A.)
- Align the plane_vma to min_page_size of stolen mem (Ram)
- Introduce vma resources and implement async unbinding (Thomas)
- Use struct vma_resource instead of struct vma_snapshot (Thomas)
- Return some TTM accel move errors instead of trying memcpy move (Thomas)
- Fix a race between vma / object destruction and unbinding (Thomas)
- Remove short-term pins from execbuf (Maarten)
- Update to GuC version 69.0.3 (John, Michal Wa.)
- Improvements to GT reset paths in GuC backend (Matt B.)
- Use shrinker_release_pages instead of writeback in shmem object hooks (Matt A., Tvrtko)
- Use trylock instead of blocking lock when freeing GEM objects (Maarten)
- Allocate intel_engine_coredump_alloc with ALLOW_FAIL (Matt B.)
- Fixes to object unmapping and purging (Matt A)
- Check for wedged device in GuC backend (John)
- Avoid lockdep splat by locking dpt_obj around set_cache_level (Maarten)
- Allow dead vm to unbind vma's without lock (Maarten)
- s/engine->i915/i915/ for DG2 engine workarounds (Matt R)
- Use to_gt() helper for GGTT accesses (Michal Wi.)
- Selftest improvements (Matt B., Thomas, Ram)
- Coding style and compiler warning fixes (Matt B., Jasmine, Andi, Colin, Gustavo, Dan)
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Yg4i2aCZvvee5Eai@jlahtine-mobl.ger.corp.intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Fixed conflicts while applying, using the fixups/drm-intel-gt-next.patch
from drm-rerere's 1f2b1742abdd ("2022y-02m-23d-16h-07m-57s UTC: drm-tip
rerere cache update")]
Add a cancel request selftest that results in an engine reset to cancel
the request as it is non-preemptable. Also insert a NOP request after
the cancelled request and confirm that it completes successfully.
v2:
(Tvrtko)
- Skip test if preemption timeout compiled out
- Skip test if engine reset isn't supported
- Update debug prints to be more descriptive
v3:
- Add comment explaining test
v4:
(John Harrison)
- Fix typos in comment explaining test
- goto out_rq is NOP creation fails
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/20220113181351.21296-2-matthew.brost@intel.com
GGTT is currently available both through i915->ggtt and gt->ggtt, and we
eventually want to get rid of the i915->ggtt one.
Use to_gt() for all i915->ggtt accesses to help with the future
refactoring.
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Sujaritha Sundaresan <sujaritha.sundaresan@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211219212500.61432-6-andi.shyti@linux.intel.com
Use to_gt() helper consistently throughout the codebase.
Pure mechanical s/i915->gt/to_gt(i915). No functional changes.
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211214193346.21231-8-andi.shyti@linux.intel.com
In igt_request_rewind(), mock_context(i915, "A") is assigned to ctx[0]
and used in i915_gem_context_get_engine(). There is a dereference
of ctx[0] in i915_gem_context_get_engine(), which could lead to a NULL
pointer dereference on failure of mock_context(i915, "A") .
So as mock_context(i915, "B").
Although this bug is not serious for it belongs to testing code, it is
better to be fixed to avoid unexpected failure in testing.
Fix this bugs by adding checks about ctx[0] and ctx[1].
This bug was found by a static analyzer. The analysis employs
differential checking to identify inconsistent security operations
(e.g., checks or kfrees) between two code paths and confirms that the
inconsistent operations are not recovered in the current function or
the callers, so they constitute bugs.
Note that, as a bug found by static analysis, it can be a false
positive or hard to trigger. Multiple researchers have cross-reviewed
the bug.
Builds with CONFIG_DRM_I915_SELFTEST=y show no new warnings,
and our static analyzer no longer warns about this code.
References: 591c0fb85d ("drm/i915: Exercise request cancellation using a mock selftest")
[tursulin: Replaced fixes with references to avoid.]
Signed-off-by: Zhou Qingyang <zhou1615@umn.edu>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211130141545.153899-1-zhou1615@umn.edu
perf_parallel_engines is micro benchmark to test i915 request
scheduling. The test creates a thread per physical engine and submits
NOP requests and waits the requests to complete in a loop. In execlists
mode this works perfectly fine as powerful CPU has enough cores to feed
each engine and process the CSBs. With GuC submission the uC gets
overwhelmed as all threads feed into a single CTB channel and the GuC
gets bombarded with CSBs as contexts are immediately switched in and out
on the engines due to the zero runtime of the requests. When the GuC is
overwhelmed scheduling of contexts is unfair due to the nature of the
GuC scheduling algorithm. This behavior is understood and deemed
acceptable as this micro benchmark isn't close to real world use case.
Increasing the timeout of wait period for requests to complete. This
makes the test understand that is ok for contexts to get starved in this
scenario.
A future patch / cleanup may just delete these micro benchmark tests as
they basically mean nothing. We care about real workloads not made up
ones.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211011175704.28509-1-matthew.brost@intel.com
UAPI Changes:
- Disable mmap ioctl for gen12+ (excl. TGL-LP)
- Start enabling HuC loading by default for upcoming Gen12+
platforms (excludes TGL and RKL)
Core Changes:
- Backmerge of drm-next
Driver Changes:
- Revert "i915: use io_mapping_map_user" (Eero, Matt A)
- Initialize the TTM device and memory managers (Thomas)
- Major rework to the GuC submission backend to prepare
for enabling on new platforms (Michal Wa., Daniele,
Matt B, Rodrigo)
- Fix i915_sg_page_sizes to record dma segments rather
than physical pages (Thomas)
- Locking rework to prep for TTM conversion (Thomas)
- Replace IS_GEN and friends with GRAPHICS_VER (Lucas)
- Use DEVICE_ATTR_RO macro (Yue)
- Static code checker fixes (Zhihao)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YMHeDxg9VLiFtyn3@jlahtine-mobl.ger.corp.intel.com
This was done by the following semantic patch:
@@ expression i915; @@
- INTEL_GEN(i915)
+ GRAPHICS_VER(i915)
@@ expression i915; expression E; @@
- INTEL_GEN(i915) >= E
+ GRAPHICS_VER(i915) >= E
@@ expression dev_priv; expression E; @@
- !IS_GEN(dev_priv, E)
+ GRAPHICS_VER(dev_priv) != E
@@ expression dev_priv; expression E; @@
- IS_GEN(dev_priv, E)
+ GRAPHICS_VER(dev_priv) == E
@@
expression dev_priv;
expression from, until;
@@
- IS_GEN_RANGE(dev_priv, from, until)
+ IS_GRAPHICS_VER(dev_priv, from, until)
@def@
expression E;
identifier id =~ "^gen$";
@@
- id = GRAPHICS_VER(E)
+ ver = GRAPHICS_VER(E)
@@
identifier def.id;
@@
- id
+ ver
It also takes care of renaming the variable we assign to GRAPHICS_VER()
so to use "ver" rather than "gen".
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210606045050.103862-2-lucas.demarchi@intel.com
In case of error, the function live_context() returns ERR_PTR() and never
returns NULL. The NULL test in the return value check should be replaced
with IS_ERR().
Fixes: 52c0fdb25c ("drm/i915: Replace global breadcrumbs with per-context interrupt tracking")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/33c46ef24cd547d0ad21dc106441491a@intel.com
[tursulin: Wrap commit text, fix Fixes: tag.]
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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
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
Pull the GT clock information [used to derive CS timestamps and PM
interval] under the GT so that is it local to the users. In doing so, we
consolidate the two references for the same information, of which the
runtime-info took note of a potential clock source override and scaling
factors.
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/20201223122359.22562-2-chris@chris-wilson.co.uk
If intel context create failed, the perf_request_latency() will return 0
rather than error, because we doesn't initialize the return value.
Fixes: 25c26f18ea ("drm/i915/selftests: Measure dispatch latency")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20201116143540.3648870-1-zhangxiaoxu5@huawei.com
If intel context create failed, the perf_series_engines() will return 0
rather than error, because we doesn't initialize the return value.
Fixes: cbfd3a0c5a ("drm/i915/selftests: Add request throughput measurement to perf")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20201116144112.3673011-1-zhangxiaoxu5@huawei.com
Just some prep work before we rework the lifetime handling, which
requires replacing all the drm_dev_put in selftests by something else.
v2: Don't go with a static inline, upsets the header tests and
separation.
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200918132505.2316382-2-daniel.vetter@ffwll.ch
Make sure vma_lock is not used as inner lock when kernel context is used,
and add ww handling where appropriate.
Ensure that execbuf selftests keep passing by using ww handling.
Changes since v2:
- Fix i915_gem_context finally.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-22-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
In function i915_active_acquire_preallocate_barrier(), not all
paths have the return value set correctly, and in case of memory
allocation failure, a negative error code should be returned.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.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/20200802115655.25568-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Since the engines belong to the GT, move the runtime-updated list of
available engines to the intel_gt struct. The original mask has been
renamed to indicate it contains the maximum engine list that can be
found on a matching device.
In preparation for other info being moved to the gt in follow up patches
(sseu), introduce an intel_gt_info structure to group all gt-related
runtime info.
v2: s/max_engine_mask/platform_engine_mask (tvrtko), fix selftest
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> #v1
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200708003952.21831-5-daniele.ceraolospurio@intel.com
Return the monotonic timestamp (ktime_get()) at the time of sampling the
busy-time. This is used in preference to taking ktime_get() separately
before or after the read seqlock as there can be some large variance in
reported timestamps. For selftests trying to ascertain that we are
reporting accurate to within a few microseconds, even a small delay
leads to the test failing.
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/20200617130916.15261-2-chris@chris-wilson.co.uk
A couple of very simple tests to ensure that the basic properties of
per-engine busyness accounting [0% and 100% busy] are faithful.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200617130916.15261-1-chris@chris-wilson.co.uk
A useful metric of the system's health is how fast we can tell the GPU
to do various actions, so measure our latency.
v2: Refactor all the instruction building into emitters.
v3: Mark the error handling if not perfect, at least consistent.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200519130802.4067-1-chris@chris-wilson.co.uk
Be consistent, and even when we know we had used a WC, flush the mapped
object after writing into it. The flush understands the mapping type and
will only clflush if !I915_MAP_WC, but will always insert a wmb [sfence]
so that we can be sure that all writes are visible.
v2: Add the unconditional wmb so we are know that we always flush the
writes to memory/HW at that point.
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/20200511141304.599-1-chris@chris-wilson.co.uk
Be consistent and ensure that we always emit the asynchronous waits
prior to issuing instructions that use the address. This ensures that if
we do emit GPU commands to do the await, they are before our use!
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200510102431.21959-1-chris@chris-wilson.co.uk
In the near future, we will utilize the busy-stats on each engine to
approximate the C0 cycles of each, and use that as an input to a manual
RPS mechanism. That entails having busy-stats always enabled and so we
can remove the enable/disable routines and simplify the pmu setup. As a
consequence of always having the stats enabled, we can also show the
current active time via sysfs/engine/xcs/active_time_ns.
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/20200429205446.3259-1-chris@chris-wilson.co.uk
Under ideal circumstances, the driver should be able to keep the GPU
fully saturated with work. Measure how close to ideal we get under the
harshest of conditions with no user payload.
v2: Also measure throughput using only one thread.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200422074203.9799-1-chris@chris-wilson.co.uk
We've migrated all the heavy users over to the intel_gt, and can finally
drop the last few users and with that the mirror in dev_priv->engine[].
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200325234803.6175-1-chris@chris-wilson.co.uk
Allocate only an internal intel_context for the kernel_context, forgoing
a global GEM context for internal use as we only require a separate
address space (for our own protection).
Now having weaned GT from requiring ce->gem_context, we can stop
referencing it entirely. This also means we no longer have to create random
and unnecessary GEM contexts for internal use.
GEM contexts are now entirely for tracking GEM clients, and intel_context
the execution environment on the GPU.
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/20191221160324.1073045-1-chris@chris-wilson.co.uk
As the engine->kernel_context is used within the engine-pm barrier, we
have to be careful when emitting requests outside of the barrier, as the
strict timeline locking rules do not apply. Instead, we must ensure the
engine_park() cannot be entered as we build the request, which is
simplest by taking an explicit engine-pm wakeref around the request
construction.
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/20191125105858.1718307-1-chris@chris-wilson.co.uk
Since drm provided us with a real struct file we can use for our
anonymous internal clients (mock_file), complete our transition to using
that as the primary interface (and not the mocked up struct drm_file we
previous were using).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191107213929.23286-1-chris@chris-wilson.co.uk
As drm now exports a method to create an anonymous struct file around a
drm_device for internal use, make use of it to avoid our horrible hacks.
Danial suggested that the mock_file_put() wrapper was suitable for
drm-core, along with the mock_drm_getfile() [and that the vestigal
mock_drm_file() in this patch should perhaps be the drm interface
itself]. However, the eventual goal is to remove the mock_drm_file() and
use the struct file and fput() directly, in this patch we take a simple
transition in that direction.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20191107180601.30815-3-chris@chris-wilson.co.uk
Vanshidhar Konda asked for the simplest test "to verify that the kernel
can submit and hardware can execute batch buffers on all the command
streamers in parallel." We have a number of tests in userspace that
submit load to each engine and verify that it is present, but strictly
we have no selftest to prove that the kernel can _simultaneously_
execute on all known engines. (We have tests to demonstrate that we can
submit to HW in parallel, but we don't insist that they execute in
parallel.)
v2: Improve the igt_spinner support for older gen.
Suggested-by: Vanshidhar Konda <vanshidhar.r.konda@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Vanshidhar Konda <vanshidhar.r.konda@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Vanshidhar Konda <vanshidhar.r.konda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191101101528.10553-1-chris@chris-wilson.co.uk
An interesting observation made with our parallel selftests was that on
our small/single cpu systems we would call kthread_stop() before the
kthreads were spawned. If this happens, the kthread is never run at all;
completely bypassing the test.
A simple yield() from the parent will ensure that all children have the
opportunity to start before we reap them.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191101084940.31838-1-chris@chris-wilson.co.uk
The request selftests straddle the boundary between checking the driver
and the hardware. They are subject to the quirks of the underlying HW,
but operate on top of the backend abstractions. The tests focus on the
scheduler elements and so should check for interactions of the scheduler
across all exposed 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/20191016125236.17960-1-chris@chris-wilson.co.uk
Keep track of the GEM contexts underneath i915->gem.contexts and assign
them their own lock for the purposes of list management.
v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex
v3: Correct split with removal of logical HW ID
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/20191004134015.13204-15-chris@chris-wilson.co.uk
We don't need to hold struct_mutex now for retiring requests, so drop it
from i915_retire_requests() and i915_gem_wait_for_idle(), finally
removing I915_WAIT_LOCKED for good.
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/20191004134015.13204-8-chris@chris-wilson.co.uk
Replace the struct_mutex requirement for pinning the i915_vma with the
local vm->mutex instead. Note that the vm->mutex is tainted by the
shrinker (we require unbinding from inside fs-reclaim) and so we cannot
allocate while holding that mutex. Instead we have to preallocate
workers to do allocate and apply the PTE updates after we have we
reserved their slot in the drm_mm (using fences to order the PTE writes
with the GPU work and with later unbind).
In adding the asynchronous vma binding, one subtle requirement is to
avoid coupling the binding fence into the backing object->resv. That is
the asynchronous binding only applies to the vma timeline itself and not
to the pages as that is a more global timeline (the binding of one vma
does not need to be ordered with another vma, nor does the implicit GEM
fencing depend on a vma, only on writes to the backing store). Keeping
the vma binding distinct from the backing store timelines is verified by
a number of async gem_exec_fence and gem_exec_schedule tests. The way we
do this is quite simple, we keep the fence for the vma binding separate
and only wait on it as required, and never add it to the obj->resv
itself.
Another consequence in reducing the locking around the vma is the
destruction of the vma is no longer globally serialised by struct_mutex.
A natural solution would be to add a kref to i915_vma, but that requires
decoupling the reference cycles, possibly by introducing a new
i915_mm_pages object that is own by both obj->mm and vma->pages.
However, we have not taken that route due to the overshadowing lmem/ttm
discussions, and instead play a series of complicated games with
trylocks to (hopefully) ensure that only one destruction path is called!
v2: Add some commentary, and some helpers to reduce patch churn.
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/20191004134015.13204-4-chris@chris-wilson.co.uk
In commit 70d6894d14 ("drm/i915: Serialize against vma moves")
I managed to miss a couple of i915_vma_move_to_active() that had not
serialised against an async vma pinning. Add the missing
i915_request_await.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821193851.18232-1-chris@chris-wilson.co.uk
Make sure that when submitting requests, we always serialize against
potential vma moves and clflushes.
Time for a i915_request_await_vma() interface!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190819112033.30638-1-chris@chris-wilson.co.uk
Grr, missed one*. For using the legacy engine map, we should use
engine->legacy_idx. Ideally, we should know the intel_context in the
selftest and avoid all the fiddling around with unwanted GEM contexts.
* In my defence, the conflict was added in another patch after it was
tested by CI.
v2: mock engines needs legacy love as well
Fixes: f1c4d157ab ("drm/i915: Fix up the inverse mapping for default ctx->engines[]")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190808194525.9410-2-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
