If the driver was not fully loaded, we may still have globals lying
around. If we don't tear those down in i915_exit(), we'll leak a bunch
of memory slabs. This can happen two ways: use_kms = false and if we've
run mock selftests. In either case, we have an early exit from
i915_init which happens after i915_globals_init() and we need to clean
up those globals.
The mock selftests case is especially sticky. The load isn't entirely
a no-op. We actually do quite a bit inside those selftests including
allocating a bunch of mock objects and running tests on them. Once all
those tests are complete, we exit early from i915_init(). Perviously,
i915_init() would return a non-zero error code on failure and a zero
error code on success. In the success case, we would get to i915_exit()
and check i915_pci_driver.driver.owner to detect if i915_init exited early
and do nothing. In the failure case, we would fail i915_init() but
there would be no opportunity to clean up globals.
The most annoying part is that you don't actually notice the failure as
part of the self-tests since leaking a bit of memory, while bad, doesn't
result in anything observable from userspace. Instead, the next time we
load the driver (usually for next IGT test), i915_globals_init() gets
invoked again, we go to allocate a bunch of new memory slabs, those
implicitly create debugfs entries, and debugfs warns that we're trying
to create directories and files that already exist. Since this all
happens as part of the next driver load, it shows up in the dmesg-warn
of whatever IGT test ran after the mock selftests.
While the obvious thing to do here might be to call i915_globals_exit()
after selftests, that's not actually safe. The dma-buf selftests call
i915_gem_prime_export which creates a file. We call dma_buf_put() on
the resulting dmabuf which calls fput() on the file. However, fput()
isn't immediate and gets flushed right before syscall returns. This
means that all the fput()s from the selftests don't happen until right
before the module load syscall used to fire off the selftests returns
which is after i915_init(). If we call i915_globals_exit() in
i915_init() after selftests, we end up freeing slabs out from under
objects which won't get released until fput() is flushed at the end of
the module load syscall.
The solution here is to let i915_init() return success early and detect
the early success in i915_exit() and only tear down globals and nothing
else. This way the module loads successfully, regardless of the success
or failure of the tests. Because we've not enumerated any PCI devices,
no device nodes are created and it's entirely useless from userspace.
The only thing the module does at that point is hold on to a bit of
memory until we unload it and i915_exit() is called. Importantly, this
means that everything from our selftests has the ability to properly
flush out between i915_init() and i915_exit() because there is at least
one syscall boundary in between.
In order to handle all the delicate init/exit cases, we convert the
whole thing to a table of init/exit pairs and track the init status in
the new init_progress global. This allows us to ensure that i915_exit()
always tears down exactly the things that i915_init() successfully
initialized. We also allow early-exit of i915_init() without failure by
an init function returning > 0. This is useful for nomodeset, and
selftests. For the mock selftests, we convert them to always return 1
so we get the desired behavior of the driver always succeeding to load
the driver and then properly tearing down the partially loaded driver.
v2 (Tvrtko Ursulin):
- Guard init_funcs[i].exit with GEM_BUG_ON(i >= ARRAY_SIZE(init_funcs))
v2 (Daniel Vetter):
- Update the docstring for i915.mock_selftests
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210721152358.2893314-4-jason@jlekstrand.net
UAPI Changes:
- Deprecate I915_PMU_LAST and optimize state tracking (Tvrtko)
Avoid relying on last item ABI marker in i915_drm.h, add a
comment to mark as deprecated.
Cross-subsystem Changes:
Core Changes:
Driver Changes:
- Restore clear residuals security mitigations for Ivybridge and
Baytrail (Chris)
- Close#1858: Allow sysadmin to choose applied GPU security mitigations
through i915.mitigations=... similar to CPU (Chris)
- Fix for #2024: GPU hangs on HSW GT1 (Chris)
- Fix for #2707: Driver hang when editing UVs in Blender (Chris, Ville)
- Fix for #2797: False positive GuC loading error message (Chris)
- Fix for #2859: Missing GuC firmware for older Cometlakes (Chris)
- Lessen probability of GPU hang due to DMAR faults [reason 7,
next page table ptr is invalid] on Tigerlake (Chris)
- Fix REVID macros for TGL to fetch correct stepping (Aditya)
- Limit frequency drop to RPe on parking (Chris, Edward)
- Limit W/A 1406941453 to TGL, RKL and DG1 (Swathi)
- Make W/A 22010271021 permanent on DG1 (Lucas)
- Implement W/A 16011163337 to prevent a HS/DS hang on DG1 (Swathi)
- Only disable preemption on gen8 render engines (Chris)
- Disable arbitration around Braswell's PDP updates (Chris)
- Disable arbitration on no-preempt requests (Chris)
- Check for arbitration after writing start seqno before busywaiting (Chris)
- Retain default context state across shrinking (Venkata, CQ)
- Fix mismatch between misplaced vma check and vma insert for 32-bit
addressing userspaces (Chris, CQ)
- Propagate error for vmap() failure instead kernel NULL deref (Chris)
- Propagate error from cancelled submit due to context closure
immediately (Chris)
- Fix RCU race on HWSP tracking per request (Chris)
- Clear CMD parser shadow and GPU reloc batches (Matt A)
- Populate logical context during first pin (Maarten)
- Optimistically prune dma-resv from the shrinker (Chris)
- Fix for virtual engine ownership race (Chris)
- Remove timeslice suppression to restore fairness for virtual engines (Chris)
- Rearrange IVB/HSW workarounds properly between GT and engine (Chris)
- Taint the reset mutex with the shrinker (Chris)
- Replace direct submit with direct call to tasklet (Chris)
- Multiple corrections to virtual engine dequeue and breadcrumbs code (Chris)
- Avoid wakeref from potentially hard IRQ context in PMU (Tvrtko)
- Use raw clock for RC6 time estimation in PMU (Tvrtko)
- Differentiate OOM failures from invalid map types (Chris)
- Fix Gen9 to have 64 MOCS entries similar to Gen11 (Chris)
- Ignore repeated attempts to suspend request flow across reset (Chris)
- Remove livelock from "do_idle_maps" VT-d W/A (Chris)
- Cancel the preemption timeout early in case engine reset fails (Chris)
- Code flow optimization in the scheduling code (Chris)
- Clear the execlists timers upon reset (Chris)
- Drain the breadcrumbs just once (Chris, Matt A)
- Track the overall GT awake/busy time (Chris)
- Tweak submission tasklet flushing to avoid starvation (Chris)
- Track timelines created using the HWSP to restore on resume (Chris)
- Use cmpxchg64 for 32b compatilibity for active tracking (Chris)
- Prefer recycling an idle GGTT fence to avoid GPU wait (Chris)
- Restructure GT code organization for clearer split between GuC
and execlists (Chris, Daniele, John, Matt A)
- Remove GuC code that will remain unused by new interfaces (Matt B)
- Restructure the CS timestamp clocks code to local to GT (Chris)
- Fix error return paths in perf code (Zhang)
- Replace idr_init() by idr_init_base() in perf (Deepak)
- Fix shmem_pin_map error path (Colin)
- Drop redundant free_work worker for GEM contexts (Chris, Mika)
- Increase readability and understandability of intel_workarounds.c (Lucas)
- Defer enabling the breadcrumb interrupt to after submission (Chris)
- Deal with buddy alloc block sizes beyond 4G (Venkata, Chris)
- Encode fence specific waitqueue behaviour into the wait.flags (Chris)
- Don't cancel the breadcrumb interrupt shadow too early (Chris)
- Cancel submitted requests upon context reset (Chris)
- Use correct locks in GuC code (Tvrtko)
- Prevent use of engine->wa_ctx after error (Chris, Matt R)
- Fix build warning on 32-bit (Arnd)
- Avoid memory leak if platform would have more than 16 W/A (Tvrtko)
- Avoid unnecessary #if CONFIG_PM in PMU code (Chris, Tvrtko)
- Improve debugging output (Chris, Tvrtko, Matt R)
- Make file local variables static (Jani)
- Avoid uint*_t types in i915 (Jani)
- Selftest improvements (Chris, Matt A, Dan)
- Documentation fixes (Chris, Jose)
Signed-off-by: Dave Airlie <airlied@redhat.com>
# Conflicts:
# drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
# drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
# drivers/gpu/drm/i915/gt/intel_lrc.c
# drivers/gpu/drm/i915/gvt/mmio_context.h
# drivers/gpu/drm/i915/i915_drv.h
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210114152232.GA21588@jlahtine-mobl.ger.corp.intel.com
accesses, inefficient and disfunctional code. The goal is to remove the
export of irq_to_desc() to prevent these things from creeping up again.
-----BEGIN PGP SIGNATURE-----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=BXv+
-----END PGP SIGNATURE-----
Merge tag 'irq-core-2020-12-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq updates from Thomas Gleixner:
"This is the second attempt after the first one failed miserably and
got zapped to unblock the rest of the interrupt related patches.
A treewide cleanup of interrupt descriptor (ab)use with all sorts of
racy accesses, inefficient and disfunctional code. The goal is to
remove the export of irq_to_desc() to prevent these things from
creeping up again"
* tag 'irq-core-2020-12-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
genirq: Restrict export of irq_to_desc()
xen/events: Implement irq distribution
xen/events: Reduce irq_info:: Spurious_cnt storage size
xen/events: Only force affinity mask for percpu interrupts
xen/events: Use immediate affinity setting
xen/events: Remove disfunct affinity spreading
xen/events: Remove unused bind_evtchn_to_irq_lateeoi()
net/mlx5: Use effective interrupt affinity
net/mlx5: Replace irq_to_desc() abuse
net/mlx4: Use effective interrupt affinity
net/mlx4: Replace irq_to_desc() abuse
PCI: mobiveil: Use irq_data_get_irq_chip_data()
PCI: xilinx-nwl: Use irq_data_get_irq_chip_data()
NTB/msi: Use irq_has_action()
mfd: ab8500-debugfs: Remove the racy fiddling with irq_desc
pinctrl: nomadik: Use irq_has_action()
drm/i915/pmu: Replace open coded kstat_irqs() copy
drm/i915/lpe_audio: Remove pointless irq_to_desc() usage
s390/irq: Use irq_desc_kstat_cpu() in show_msi_interrupt()
parisc/irq: Use irq_desc_kstat_cpu() in show_interrupts()
...
Driver code has no business with the internals of the irq descriptor.
Aside of that the count is per interrupt line and therefore takes
interrupts from other devices into account which share the interrupt line
and are not handled by the graphics driver.
Replace it with a pmu private count which only counts interrupts which
originate from the graphics card.
To avoid atomics or heuristics of some sort make the counter field
'unsigned long'. That limits the count to 4e9 on 32bit which is a lot and
postprocessing can easily deal with the occasional wraparound.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: https://lore.kernel.org/r/20201210194043.957046529@linutronix.de
Adding any kinds of "last" abi markers is usually a mistake which I
repeated when implementing the PMU because it felt convenient at the time.
This patch marks I915_PMU_LAST as deprecated and stops the internal
implementation using it for sizing the event status bitmask and array.
New way of sizing the fields is a bit less elegant, but it omits reserving
slots for tracking events we are not interested in, and as such saves some
runtime space. Adding sampling events is likely to be a special event and
the new plumbing needed will be easily detected in testing. Existing
asserts against the bitfield and array sizes are keeping the code safe.
First event which gets the new treatment in this new scheme are the
interrupts - which neither needs any tracking in i915 pmu nor needs
waking up the GPU to read it.
v2:
* Streamline helper names. (Chris)
v3:
* Comment which events need tracking. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20201201131757.206367-1-tvrtko.ursulin@linux.intel.com
Since we keep a driver global mask of online CPUs and base the decision
whether PMU needs to be migrated upon it, we need to make sure the
migration is done for all registered PMUs (so GPUs).
To do this we need to track the current CPU for each PMU and base the
decision on whether to migrate on a comparison between global and local
state.
At the same time, since dynamic CPU hotplug notification slots are a
scarce resource and given how we already register the multi instance type
state, we can and should add multiple instance of the i915 PMU to this
same state and not allocate a new one for every GPU.
v2:
* Use pr_notice. (Chris)
v3:
* Handle a nasty interaction where unregistration which triggers a false
CPU offline event. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Daniel Vetter <daniel.vetter@intel.com> # dynamic slot optimisation
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20201020161144.678668-1-tvrtko.ursulin@linux.intel.com
Mark the device as closed and keep references to driver data alive to
allow for safe driver unbind with active PMU clients. Perf core does not
otherwise handle this case so we have to do it manually like this.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20201020100822.543332-1-tvrtko.ursulin@linux.intel.com
The #include has been splattered all over the place, but there are
precious few places, all .c files, that actually need it.
v2: remove leftover double newlines
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200225133131.3301-1-jani.nikula@intel.com
Attempting to bind / unbind module from devices where we have both
integrated and discreete GPU handled by i915, will cause us to try and
double free the global state, hitting null ptr deref in free_event_attributes.
Let's move it to i915_pmu.
Fixes: 05488673a4 ("drm/i915/pmu: Support multiple GPUs")
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200219161822.24592-2-michal.winiarski@intel.com
Attempting to bind / unbind module from devices where we have both
integrated and discreete GPU handled by i915 can lead to leaks and
warnings from cpuhp:
Error: Removing state XXX which has instances left.
Let's move the state to i915_pmu.
Fixes: 05488673a4 ("drm/i915/pmu: Support multiple GPUs")
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200219161822.24592-1-michal.winiarski@intel.com
Avoid rc6 counter going backward in close to 0% RC6 scenarios like:
15.005477996 114,246,613 ns i915/rc6-residency/
16.005876662 667,657 ns i915/rc6-residency/
17.006131417 7,286 ns i915/rc6-residency/
18.006615031 18,446,744,073,708,914,688 ns i915/rc6-residency/
19.007158361 18,446,744,073,709,447,168 ns i915/rc6-residency/
20.007806498 0 ns i915/rc6-residency/
21.008227495 1,440,403 ns i915/rc6-residency/
There are two aspects to this fix.
First is not assuming rc6 value zero means GT is asleep since that can
also mean GPU is fully busy and we do not want to enter the estimation
path in that case.
Second is ensuring monotonicity on the estimation path itself. I suspect
what is happening is with extremely rapid park/unpark cycles we get no
updates on the real rc6 and therefore have to careful not to
unconditionally trust use last known real rc6 when creating a new
estimation.
v2:
* Simplify logic by not tracking the estimate but last reported value.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 16ffe73c18 ("drm/i915/pmu: Use GT parked for estimating RC6 while asleep")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v1
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191217142057.1000-1-tvrtko.ursulin@linux.intel.com
With discrete graphics system can have both integrated and discrete GPU
handled by i915.
Currently we use a fixed name ("i915") when registering as the uncore PMU
provider which stops working in this case.
To fix this we add the PCI device name string to non-integrated devices
handled by us. Integrated devices keep the legacy name preserving
backward compatibility.
v2:
* Detect IGP and keep legacy name. (Michal)
* Use PCI device name as suffix. (Michal, Chris)
v3:
* Constify the name. (Chris)
* Use pci_domain_nr. (Chris)
v4:
* Fix kfree_const usage. (Chris)
v5:
* kfree_const does not work for modules. (Chris)
* Changed is_igp helper to take i915.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016093802.12483-1-tvrtko.ursulin@linux.intel.com
As we track when we put the GT device to sleep upon idling, we can use
that callback to sample the current rc6 counters and record the
timestamp for estimating samples after that point while asleep.
v2: Stick to using ktime_t
v3: Track user_wakerefs that interfere with the new
intel_gt_pm_wait_for_idle
v4: No need for parked/unparked estimation if !CONFIG_PM
v5: Keep timer park/unpark logic as was
v6: Refactor duplicated estimate/update rc6 logic
v7: Pull intel_get_pm_get_if_awake() out from the pmu->lock.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105010
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/20190912124813.19225-1-chris@chris-wilson.co.uk
Enable count array is supposed to have one counter for each possible
engine sampler. As such, array sizing and bounds checking is not correct
and would blow up the asserts if more samplers were added.
No ill-effect in the current code base but lets fix it for correctness.
At the same time tidy the assert for readability and robustness.
v2:
* One check per assert. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: b46a33e271 ("drm/i915/pmu: Expose a PMU interface for perf queries")
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190205130353.21105-1-tvrtko.ursulin@linux.intel.com
(cherry picked from commit 26a11deea6)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Use the new PM-runtime interface to get the accounted suspended time:
pm_runtime_suspended_time().
This new interface helps to simplify and cleanup the code that computes
__I915_SAMPLE_RC6_ESTIMATED and to remove direct access to internals of
PM-runtime.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
As Chris has discovered on his Ivybridge, and later automated test runs
have confirmed, on most of our platforms hrtimer faced with heavy GPU load
can occasionally become sufficiently imprecise to affect PMU sampling
calculations.
This means we cannot assume sampling frequency is what we asked for, but
we need to measure the interval ourselves.
This patch is similar to Chris' original proposal for per-engine counters,
but instead of introducing a new set to work around the problem with
frequency sampling, it swaps around the way internal frequency accounting
is done. Instead of accumulating current frequency and dividing by
sampling frequency on readout, it accumulates frequency scaled by each
period.
v2:
* Typo in commit message, comment on period calculation and USEC_PER_SEC.
(Chris Wilson)
Testcase: igt/perf_pmu/*busy* # snb, ivb, hsw
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605140253.3541-1-tvrtko.ursulin@linux.intel.com
Definitions in i915_pmu.h header depend on other types and
declarations that were not explicitly included. Fix that by
adding related headers and forward declarations.
While here, change license text to SPDX format.
v2: don't drop "intel_ringbuffer.h" (Tvrtko)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180308095037.18264-4-michal.wajdeczko@intel.com
We are not allowed to call intel_runtime_pm_get from the PMU counter read
callback since the former can sleep, and the latter is running under IRQ
context.
To workaround this, we record the last known RC6 and while runtime
suspended estimate its increase by querying the runtime PM core
timestamps.
Downside of this approach is that we can temporarily lose a chunk of RC6
time, from the last PMU read-out to runtime suspend entry, but that will
eventually catch up, once device comes back online and in the presence of
PMU queries.
Also, we have to be careful not to overshoot the RC6 estimate, so once
resumed after a period of approximation, we only update the counter once
it catches up. With the observation that RC6 is increasing while the
device is suspended, this should not pose a problem and can only cause
slight inaccuracies due clock base differences.
v2: Simplify by estimating on top of PM core counters. (Imre)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104943
Fixes: 6060b6aec0 ("drm/i915/pmu: Add RC6 residency metrics")
Testcase: igt/perf_pmu/rc6-runtime-pm
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: intel-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180206183311.17924-1-tvrtko.ursulin@linux.intel.com
Switch over to dynamically creating device attributes, which are in turn
used by the perf core to expose available counters in sysfs.
This way we do not expose counters which are not avaiable on the current
platform, and are so more consistent between what we reply to open
attempts via the perf_event_open(2), and what is discoverable in sysfs.
v2:
* Simplify attribute pointer freeing loop.
* Changed attr init from macro to function.
* More common error unwind. (Chris Wilson)
* Rename some locals. (Chris Wilson)
v3:
* Fixed double semi-colon. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180111083525.32394-1-tvrtko.ursulin@linux.intel.com
Averaging with the previous sample brings a small statistical improvement
to sampling counters, but can leek a little bit of state from a current
client to the next which mulls the border between past and present for
observing clients.
This is because on event enable clients record the current counter value
and use it as reference, but with rapid off-on event cycles, and due the
delayed nature of sampling timer self-disarm, previous sample value does
not get cleared under these circumstances.
Solution is to stop averaging with the previous sample. This has a small
downside of losing some precision with short and spiky signals, but the
alternatives look too complicated for the benefit.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171124094959.10725-1-tvrtko.ursulin@linux.intel.com
If only a subset of events is enabled we can afford to suspend
the sampling timer when the GPU is idle and so save some cycles
and power.
v2: Rebase and limit timer even more.
v3: Rebase.
v4: Rebase.
v5: Skip action if perf PMU failed to register.
v6: Checkpatch cleanup.
v7:
* Add a common helper to start the timer if needed. (Chris Wilson)
* Add comment explaining bitwise logic in pmu_needs_timer.
v8: Fix some comments styles. (Chris Wilson)
v9: Rebase.
v10: Move function declarations to i915_pmu.h.
v11: Rename functions to i915_pmu_gt_(un)parked. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-3-tvrtko.ursulin@linux.intel.com
From: Chris Wilson <chris@chris-wilson.co.uk>
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
The first goal is to be able to measure GPU (and invidual ring) busyness
without having to poll registers from userspace. (Which not only incurs
holding the forcewake lock indefinitely, perturbing the system, but also
runs the risk of hanging the machine.) As an alternative we can use the
perf event counter interface to sample the ring registers periodically
and send those results to userspace.
Functionality we are exporting to userspace is via the existing perf PMU
API and can be exercised via the existing tools. For example:
perf stat -a -e i915/rcs0-busy/ -I 1000
Will print the render engine busynnes once per second. All the performance
counters can be enumerated (perf list) and have their unit of measure
correctly reported in sysfs.
v1-v2 (Chris Wilson):
v2: Use a common timer for the ring sampling.
v3: (Tvrtko Ursulin)
* Decouple uAPI from i915 engine ids.
* Complete uAPI defines.
* Refactor some code to helpers for clarity.
* Skip sampling disabled engines.
* Expose counters in sysfs.
* Pass in fake regs to avoid null ptr deref in perf core.
* Convert to class/instance uAPI.
* Use shared driver code for rc6 residency, power and frequency.
v4: (Dmitry Rogozhkin)
* Register PMU with .task_ctx_nr=perf_invalid_context
* Expose cpumask for the PMU with the single CPU in the mask
* Properly support pmu->stop(): it should call pmu->read()
* Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE)
* Introduce refcounting of event subscriptions.
* Make pmu.busy_stats a refcounter to avoid busy stats going away
with some deleted event.
* Expose cpumask for i915 PMU to avoid multiple events creation of
the same type followed by counter aggregation by perf-stat.
* Track CPUs getting online/offline to migrate perf context. If (likely)
cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be
needed to see effect of CPU status tracking.
* End result is that only global events are supported and perf stat
works correctly.
* Deny perf driver level sampling - it is prohibited for uncore PMU.
v5: (Tvrtko Ursulin)
* Don't hardcode number of engine samplers.
* Rewrite event ref-counting for correctness and simplicity.
* Store initial counter value when starting already enabled events
to correctly report values to all listeners.
* Fix RC6 residency readout.
* Comments, GPL header.
v6:
* Add missing entry to v4 changelog.
* Fix accounting in CPU hotplug case by copying the approach from
arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin)
v7:
* Log failure message only on failure.
* Remove CPU hotplug notification state on unregister.
v8:
* Fix error unwind on failed registration.
* Checkpatch cleanup.
v9:
* Drop the energy metric, it is available via intel_rapl_perf.
(Ville Syrjälä)
* Use HAS_RC6(p). (Chris Wilson)
* Handle unsupported non-engine events. (Dmitry Rogozhkin)
* Rebase for intel_rc6_residency_ns needing caller managed
runtime pm.
* Drop HAS_RC6 checks from the read callback since creating those
events will be rejected at init time already.
* Add counter units to sysfs so perf stat output is nicer.
* Cleanup the attribute tables for brevity and readability.
v10:
* Fixed queued accounting.
v11:
* Move intel_engine_lookup_user to intel_engine_cs.c
* Commit update. (Joonas Lahtinen)
v12:
* More accurate sampling. (Chris Wilson)
* Store and report frequency in MHz for better usability from
perf stat.
* Removed metrics: queued, interrupts, rc6 counters.
* Sample engine busyness based on seqno difference only
for less MMIO (and forcewake) on all platforms. (Chris Wilson)
v13:
* Comment spelling, use mul_u32_u32 to work around potential GCC
issue and somne code alignment changes. (Chris Wilson)
v14:
* Rebase.
v15:
* Rebase for RPS refactoring.
v16:
* Use the dynamic slot in the CPU hotplug state machine so that we are
free to setup our state as multi-instance. Previously we were re-using
the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as
multi-instance, nor owned by our driver to start with.
* Register the CPU hotplug handlers after the PMU, otherwise the callback
will get called before the PMU is initialized which can end up in
perf_pmu_migrate_context with an un-initialized base.
* Added workaround for a probable bug in cpuhp core.
v17:
* Remove workaround for the cpuhp bug.
v18:
* Rebase for drm_i915_gem_engine_class getting upstream before us.
v19:
* Rebase. (trivial)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
Jason Ekstrand