Gen graphics hardware can be set up to periodically write snapshots of
performance counters into a circular buffer via its Observation
Architecture and this patch exposes that capability to userspace via the
i915 perf interface.
v2:
Make sure to initialize ->specific_ctx_id when opening, without
relying on _pin_notify hook, in case ctx already pinned.
v3:
Revert back to pinning ctx upfront when opening stream, removing
need to hook in to pinning and to update OACONTROL on the fly.
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Sourab Gupta <sourab.gupta@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161107194957.3385-7-robert@sixbynine.org
Adds a static OA unit, MUX + B Counter configuration for basic render
metrics on Haswell. This is auto generated from an XML
description of metric sets, currently maintained in gputop, ref:
https://github.com/rib/gputop
> gputop-data/oa-*.xml
> scripts/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml SYSFS=0 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Sourab Gupta <sourab.gupta@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161107194957.3385-6-robert@sixbynine.org
Adds base i915 perf infrastructure for Gen performance metrics.
This adds a DRM_IOCTL_I915_PERF_OPEN ioctl that takes an array of uint64
properties to configure a stream of metrics and returns a new fd usable
with standard VFS system calls including read() to read typed and sized
records; ioctl() to enable or disable capture and poll() to wait for
data.
A stream is opened something like:
uint64_t properties[] = {
/* Single context sampling */
DRM_I915_PERF_PROP_CTX_HANDLE, ctx_handle,
/* Include OA reports in samples */
DRM_I915_PERF_PROP_SAMPLE_OA, true,
/* OA unit configuration */
DRM_I915_PERF_PROP_OA_METRICS_SET, metrics_set_id,
DRM_I915_PERF_PROP_OA_FORMAT, report_format,
DRM_I915_PERF_PROP_OA_EXPONENT, period_exponent,
};
struct drm_i915_perf_open_param parm = {
.flags = I915_PERF_FLAG_FD_CLOEXEC |
I915_PERF_FLAG_FD_NONBLOCK |
I915_PERF_FLAG_DISABLED,
.properties_ptr = (uint64_t)properties,
.num_properties = sizeof(properties) / 16,
};
int fd = drmIoctl(drm_fd, DRM_IOCTL_I915_PERF_OPEN, ¶m);
Records read all start with a common { type, size } header with
DRM_I915_PERF_RECORD_SAMPLE being of most interest. Sample records
contain an extensible number of fields and it's the
DRM_I915_PERF_PROP_SAMPLE_xyz properties given when opening that
determine what's included in every sample.
No specific streams are supported yet so any attempt to open a stream
will return an error.
v2:
use i915_gem_context_get() - Chris Wilson
v3:
update read() interface to avoid passing state struct - Chris Wilson
fix some rebase fallout, with i915-perf init/deinit
v4:
s/DRM_IORW/DRM_IOW/ - Emil Velikov
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Sourab Gupta <sourab.gupta@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161107194957.3385-2-robert@sixbynine.org
If we have a bad client submitting unfavourably across different
contexts, creating new ones, the per context scoring of badness
doesn't remove the root cause, the offending client.
To counter, keep track of per client context bans. Deny access if
client is responsible for more than 3 context bans in
it's lifetime.
v2: move ban check to context create ioctl (Chris)
v3: add commentary about hangs needed to reach client ban (Chris)
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Now when driver has per context scoring of 'hanging badness'
and also subsequent hangs during short windows are allowed,
if there is progress made in between, it does not make sense
to expose a ban timing window as a context parameter anymore.
Let the scoring be the sole indicator for ban policy and substitute
ban period context parameter as a boolean to get/set context
bannable property.
v2: allow non root to opt into being banned (Chris)
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
As hangcheck score was removed, the active decay of score
was removed also. This removed feature for hangcheck to detect
if the gpu client was accidentally or maliciously causing intermittent
hangs. Reinstate the scoring as a per context property, so that if
one context starts to act unfavourably, ban it.
v2: ban_period_secs as a gate to score check (Chris)
v3: decay in proper spot. scores as tunables (Chris)
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Hangcheck state accumulation has gained more steps
along the years, like head movement and more recently the
subunit inactivity check. As the subunit sampling is only
done if the previous state check showed inactivity, we
have added more stages (and time) to reach a hang verdict.
Asymmetric engine states led to different actual weight of
'one hangcheck unit' and it was demonstrated in some
hangs that due to difference in stages, simpler engines
were accused falsely of a hang as their scoring was much
more quicker to accumulate above the hang treshold.
To completely decouple the hangcheck guilty score
from the hangcheck period, convert hangcheck score to a
rough period of inactivity measurement. As these are
tracked as jiffies, they are meaningful also across
reset boundaries. This makes finding a guilty engine
more accurate across multi engine activity scenarios,
especially across asymmetric engines.
We lose the ability to detect cross batch malicious attempts
to hinder the progress. Plan is to move this functionality
to be part of context banning which is more natural fit,
later in the series.
v2: use time_before macros (Chris)
reinstate the pardoning of moving engine after hc (Chris)
v3: avoid global state for per engine stall detection (Chris)
v4: take timeline last retirement into account (Chris)
v5: do debug print on pardoning, split out retirement timestamp (Chris)
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
And a little bit of function prototype changes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
And a little bit of cascaded function prototype changes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
And a little bit of cascaded function prototype changes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Plus a small cascade of function prototype changes.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tvrtko needs
commit b3c11ac267
Author: Eric Engestrom <eric@engestrom.ch>
Date: Sat Nov 12 01:12:56 2016 +0000
drm: move allocation out of drm_get_format_name()
to be able to apply his patches without conflicts.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Decoupled MMIO is an alternative way to access forcewake domain
registers, which requires less cycles for a single read/write and
avoids frequent software forcewake.
This certainly gives advantage over the forcewake as this new
mechanism “decouples” CPU cycles and allow them to complete even
when GT is in a CPD (frequency change) or C6 state.
This can co-exist with forcewake and we will continue to use forcewake
as appropriate. E.g. 64-bit register writes to avoid writing 2 dwords
separately and land into funny situations.
v2:
- Moved platform check out of the function and got rid of duplicate
functions to find out decoupled power domain (Chris)
- Added a check for forcewake already held and skipped decoupled
access (Chris)
- Skipped writing 64 bit registers through decoupled MMIO (Chris)
v3:
- Improved commit message with more info on decoupled mmio (Tvrtko)
- Changed decoupled operation to enum and used u32 instead of
uint_32 data type for register offset (Tvrtko)
- Moved HAS_DECOUPLED_MMIO to device info (Tvrtko)
- Added lookup table for converting fw_engine to pd_engine (Tvrtko)
- Improved __gen9_decoupled_read and __gen9_decoupled_write
routines (Tvrtko)
v4:
- Fixed alignment and variable names (Chris)
- Write GEN9_DECOUPLED_REG0_DW1 register in just one go (Zhe Wang)
v5:
- Changed HAS_DECOUPLED_MMIO() argument name to dev_priv (Tvrtko)
- Sanitize info->had_decoupled_mmio at init (Chris)
Signed-off-by: Zhe Wang <zhe1.wang@intel.com>
Signed-off-by: Praveen Paneri <praveen.paneri@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1479230360-22395-1-git-send-email-praveen.paneri@intel.com
The watermark updates for SKL style watermarks are no longer done
in the plane callbacks, but are now called in a separate watermark
update function that's called during the same vblank evasion,
before the plane updates.
This also gets rid of the global skl_results, which was required for
keeping track of the current atomic commit.
Changes since v1:
- Move line unwrap to correct patch. (Lyude)
- Make sure we don't regress ILK watermarks. (Matt)
- Rephrase commit message. (Matt)
Changes since v2:
- Fix disable watermark check to use the correct way to determine single
step watermark support.
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Lyude <cpaul@redhat.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1478609742-13603-3-git-send-email-maarten.lankhorst@linux.intel.com
[mlankhorst: Small whitespace fix in skl_initial_wm]
Allow the driver to write watermarks during atomic evasion.
This will make it possible to write the watermarks in a cleaner
way on gen9+.
intel_atomic_state is not used here yet, but will be used when
we program all watermarks as a separate step during evasion.
This also writes linetime all the time, while before it was only
done during plane updates. This looks like this could be a bugfix,
but I'm not sure what it affects.
Changes since v1:
- Add comment about atomic evasion to commit message.
- Unwrap I915_WRITE call. (Lyude)
Changes since v2:
- Rename atomic_evade_watermarks to atomic_update_watermarks. (Ville)
- Add line wraps where appropriate, fix grammar in commit message. (Matt)
Changes since v3:
- Actually fix commit message. (Matt)
- Line wrap calls to watermark update functions. (Matt)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1478609742-13603-2-git-send-email-maarten.lankhorst@linux.intel.com
Boost the priority of any rendering required to show the next pageflip
as we want to avoid missing the vblank by being delayed by invisible
workload. We prioritise avoiding jank and jitter in the GUI over
starving background tasks.
v2: Descend dma_fence_array when boosting priorities.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161114204105.29171-10-chris@chris-wilson.co.uk
In order to support userspace defining different levels of importance to
different contexts, and in particular the preferred order of execution,
store a priority value on each context. By default, the kernel's
context, which is used for idling and other background tasks, is given
minimum priority (i.e. all user contexts will execute before the kernel).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161114204105.29171-9-chris@chris-wilson.co.uk
The scheduler needs to know the dependencies of each request for the
lifetime of the request, as it may choose to reschedule the requests at
any time and must ensure the dependency tree is not broken. This is in
additional to using the fence to only allow execution after all
dependencies have been completed.
One option was to extend the fence to support the bidirectional
dependency tracking required by the scheduler. However the mismatch in
lifetimes between the submit fence and the request essentially meant
that we had to build a completely separate struct (and we could not
simply reuse the existing waitqueue in the fence for one half of the
dependency tracking). The extra dependency tracking simply did not mesh
well with the fence, and keeping it separate both keeps the fence
implementation simpler and allows us to extend the dependency tracking
into a priority tree (whilst maintaining support for reordering the
tree).
To avoid the additional allocations and list manipulations, the use of
the priotree is disabled when there are no schedulers to use it.
v2: Create a dedicated slab for i915_dependency.
Rename the lists.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161114204105.29171-7-chris@chris-wilson.co.uk
The term "preliminary hardware support" has always caused confusion both
among users and developers. It has always been about preliminary driver
support for new hardware, and not so much about preliminary hardware. Of
course, initially both the software and hardware are in early stages,
but the distinction becomes more clear when the user picks up production
hardware and an older kernel to go with it, with just the early support
we had for the hardware at the time the kernel was released. The user
has to specifically enable the alpha quality *driver* support for the
hardware in that specific kernel version.
Rename preliminary_hw_support to alpha_support to emphasize that the
module parameter, config option, and flag are about software, not about
hardware. Improve the language in help texts and debug logging as well.
This appears to be a good time to do the change, as there are currently
no platforms with preliminary^W alpha support.
Cc: Rob Clark <robdclark@gmail.com>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1477909108-18696-1-git-send-email-jani.nikula@intel.com
A small selection of macros which can only accept dev_priv from
now on and a resulting trickle of fixups.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
A small selection of macros which can only accept dev_priv from
now on and a resulting trickle of fixups.
v2: Keep original order. (Ville Syrjala)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
A small selection of macros which can only accept dev_priv from
now on and a resulting trickle of fixups.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
As a side product, had to split two other files;
- i915_gem_fence_reg.h
- i915_gem_object.h (only parts that needed immediate untanglement)
I tried to move code in as big chunks as possible, to make review
easier. i915_vma_compare was moved to a header temporarily.
v2:
- Use i915_gem_fence_reg.{c,h}
v3:
- Rebased
v4:
- Fix building when DEBUG_GEM is enabled by reordering a bit.
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1478861034-30643-1-git-send-email-joonas.lahtinen@linux.intel.com
- better atomic state debugging from Rob
- fence prep from gustavo
- sumits flushed out his backlog of pending dma-buf/fence patches from
various people
- drm_mm leak debugging plus trying to appease Kconfig (Chris)
- a few misc things all over
* tag 'topic/drm-misc-2016-11-10' of git://anongit.freedesktop.org/drm-intel: (35 commits)
drm: Make DRM_DEBUG_MM depend on STACKTRACE_SUPPORT
drm/i915: Restrict DRM_DEBUG_MM automatic selection
drm: Restrict stackdepot usage to builtin drm.ko
drm/msm: module param to dump state on error irq
drm/msm/mdp5: add atomic_print_state support
drm/atomic: add debugfs file to dump out atomic state
drm/atomic: add new drm_debug bit to dump atomic state
drm: add helpers to go from plane state to drm_rect
drm: add helper for printing to log or seq_file
drm: helper macros to print composite types
reservation: revert "wait only with non-zero timeout specified (v3)" v2
drm/ttm: fix ttm_bo_wait
dma-buf/fence: revert "don't wait when specified timeout is zero" (v2)
dma-buf/fence: make timeout handling in fence_default_wait consistent (v2)
drm/amdgpu: add the interface of waiting multiple fences (v4)
dma-buf: return index of the first signaled fence (v2)
MAINTAINERS: update Sync File Framework files
dma-buf/sw_sync: put fence reference from the fence creation
dma-buf/sw_sync: mark sync_timeline_create() static
drm: Add stackdepot include for DRM_DEBUG_MM
...
We always flush the chipset prior to executing with the GPU, so we can
skip the flush during ordinary domain management.
This should help mitigate some of the potential performance regressions,
but likely trivial, from doing the flush unconditionally before execbuf
introduced in commit dcd79934b0 ("drm/i915: Unconditionally flush any
chipset buffers before execbuf")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20161106130001.9509-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Move has_64bit_reloc into dev_priv->info. This will make it visible
in the feature listing debug output.
v2:
- Keep the struct member to keep GCC fragile but happy (Chris)
v3:
- More detailed commit message (Chris)
- Include forgotten CHV and BXT (Chris)
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1478162386-5018-1-git-send-email-joonas.lahtinen@linux.intel.com
Create new file for hangcheck specific code, intel_hangcheck.c,
and move all related code in it.
v2: s/intel_engine_hangcheck/intel_engine (Chris)
No functional changes.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1478018583-5816-1-git-send-email-mika.kuoppala@intel.com
Commit 1bec9b0bda ("drm/i915/shrinker: Only shmemfs objects
are backed by swap") stopped considering the userptr objects
in shrinker callbacks.
Restore that so idle userptr objects can be discarded in order
to free up memory.
One change further to what was introduced in 1bec9b0bda is
to start considering userptr objects in oom but that should
also be a correct thing to do.
v2: Introduce I915_GEM_OBJECT_IS_SHRINKABLE. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 1bec9b0bda ("drm/i915/shrinker: Only shmemfs objects are backed by swap")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: <stable@vger.kernel.org>
Link: http://patchwork.freedesktop.org/patch/msgid/1478011450-6634-1-git-send-email-tvrtko.ursulin@linux.intel.com
For legacy contexts we employ an optimisation to only flush the context
when binding into the global GTT. This avoids stalling on the GPU when
reloading an active context. Wrap this detail up into a helper and
export it for a potential third user. (Longer term, context pinning
needs to be reworked as the current handling of switch context pins too
late and so risks eviction and corrupting the request. Plans, plans,
plans.)
v2: Expand the comment explaining the optimisation for avoiding the
stall on active contexts.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20161030132820.32163-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
The shrinker may appear to recurse into obj->mm.lock as the shrinker may
be called from a direct reclaim path whilst handling get_pages. We
filter out recursing on the same obj->mm.lock by inspecting
obj->mm.pages, but we do want to take the lock on a second object in
order to reap their pages. lockdep spots the recursion on the same
lockclass and needs annotation to avoid a false positive. To keep the
two paths distinct, create an enum to indicate which subclass of
obj->mm.lock we are using. This removes the false positive and avoids
masking real bugs.
Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161101121134.27504-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
