s/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.a...@intel.com>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 559 -
1 file changed, 558 insertions(+), 1
ake -C gputop-data -f Makefile.xml SYSFS=0 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.a...@intel.com>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915_drv.h| 14
drivers/gpu/drm/i915/i
attempt to open a stream
will return an error.
v4:
s/DRM_IORW/DRM_IOW/ - Emil Velikov
v3:
update read() interface to avoid passing state struct - Chris Wilson
fix some rebase fallout, with i915-perf init/deinit
v2:
use i915_gem_context_get() - Chris Wilson
Signed-off-by: Robert Bragg
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before adding more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.a...@intel.com>
---
drivers/gpu/drm/i915/gv
running any Mesa based GL application
currently results in clearing OACONTROL when initializing which would
disable the capturing of metrics.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 38 ++
1 file chan
is disabled, but if we were to remove
OACONTROL from the parser's whitelist then the returned EINVAL would
break Mesa applications as they attempt an OACONTROL write.
This bumps the command parser version from 7 to 8, as the change is
visible to userspace.
Signed-off-by: Robert Bragg <rob...@sixbynine.
On Wed, Oct 12, 2016 at 12:41 PM, Joonas Lahtinen <
joonas.lahti...@linux.intel.com> wrote:
> On ti, 2016-10-11 at 12:03 -0700, Robert Bragg wrote:
> > > > + case DRM_I915_PERF_PROP_MAX:
> > > > + BUG();
> > >
>
On Fri, Oct 7, 2016 at 10:19 AM, Matthew Auld <
matthew.william.a...@gmail.com> wrote:
> On 14 September 2016 at 15:19, Robert Bragg <rob...@sixbynine.org> wrote:
>
> > diff --git a/drivers/gpu/drm/i915/i915_perf.c
> b/drivers/gpu/drm/i915/i915_perf.c
> &
On Fri, Oct 7, 2016 at 10:10 AM, Matthew Auld <
matthew.william.a...@gmail.com> wrote:
> On 14 September 2016 at 16:32, Robert Bragg <rob...@sixbynine.org> wrote:
>
> > +
> > +int i915_perf_open_ioctl_locked(struct drm_device *dev,
> > +
attempt to open a stream
will return an error.
v4:
s/DRM_IORW/DRM_IOR/ - Emil Velikov
v3:
update read() interface to avoid passing state struct - Chris Wilson
fix some rebase fallout, with i915-perf init/deinit
v2:
use i915_gem_context_get() - Chris Wilson
Signed-off-by: Robert Bragg
On Wed, Sep 14, 2016 at 3:42 PM, Emil Velikov <emil.l.veli...@gmail.com>
wrote:
> Hi Robert,
>
> I think I've spotted one interesting, yet trivial bit.
>
> On 14 September 2016 at 15:19, Robert Bragg <rob...@sixbynine.org> wrote:
> > Adds base i915 perf infrastru
is disabled, but if we were to remove
OACONTROL from the parser's whitelist then the returned EINVAL would
break Mesa applications as they attempt an OACONTROL write.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 2 +-
1 file changed, 1 insertion
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.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by:
s/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 559 -
1 file changed, 558 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915
and code generation scripts, ref:
https://github.com/rib/gputop
> gputop-data/guids.xml
> scripts/update-guids.py
> gputop-data/oa-*.xml
> scripts/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml SYSFS=1 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob..
Consistent with the kernel.perf_event_paranoid sysctl option that can
allow non-root users to access system wide cpu metrics, this can
optionally allow non-root users to access system wide OA counter metrics
from Gen graphics hardware.
Signed-off-by: Robert Bragg <rob...@sixbynine.
The minimal sampling period is now configurable via a
dev.i915.oa_min_timer_exponent sysctl parameter.
Following the precedent set by perf, the default is the minimum that
won't (on its own) exceed the default kernel.perf_event_max_sample_rate
default of 10 samples/s.
Signed-off-by: Robert
ake -C gputop-data -f Makefile.xml SYSFS=0 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915_drv.h| 14
drivers/gpu/drm/i915/i915_oa_hsw.c | 143 +
dri
In particular this tries to capture for posterity some of the early
challenges we had with using the core perf infrastructure in case we
ever want to revisit adapting perf for device metrics.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by: Robert Bragg <rob...@sixb
running any Mesa based GL application
currently results in clearing OACONTROL when initializing which would
disable the capturing of metrics.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 38 ++
1 file chan
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before adding more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++--
drivers/gpu/drm/i915/i915
for this series at the moment is just keeping up
with rebasing on nightlies.
Regards,
- Robert
Robert Bragg (11):
drm/i915: Add i915 perf infrastructure
drm/i915: rename OACONTROL GEN7_OACONTROL
drm/i915: return EACCES for check_cmd() failures
drm/i915: don't whitelist oacontrol in cmd parser
attempt to open a stream
will return an error.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile| 3 +
drivers/gpu/drm/i915/i915_drv.c | 4 +
drivers/gpu/drm/i915/i915_drv.h | 91
drivers/gpu/drm/i915/i915_perf.c
and code generation scripts, ref:
https://github.com/rib/gputop
> gputop-data/guids.xml
> scripts/update-guids.py
> gputop-data/oa-*.xml
> scripts/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml SYSFS=1 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob..
In particular this tries to capture for posterity some of the early
challenges we had with using the core perf infrastructure in case we
ever want to revisit adapting perf for device metrics.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by: Robert Bragg <rob...@sixb
Consistent with the kernel.perf_event_paranoid sysctl option that can
allow non-root users to access system wide cpu metrics, this can
optionally allow non-root users to access system wide OA counter metrics
from Gen graphics hardware.
Signed-off-by: Robert Bragg <rob...@sixbynine.
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.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by:
and code generation scripts, ref:
https://github.com/rib/gputop
> gputop-data/guids.xml
> scripts/update-guids.py
> gputop-data/oa-*.xml
> scripts/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml SYSFS=1 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob..
is disabled, but if we were to remove
OACONTROL from the parser's whitelist then the returned EINVAL would
break Mesa applications as they attempt an OACONTROL write.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 2 +-
1 file changed, 1 insertion
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before adding more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++--
drivers/gpu/drm/i915/i915
s/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 484 -
1 file changed, 483 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915
The minimal sampling period is now configurable via a
dev.i915.oa_min_timer_exponent sysctl parameter.
Following the precedent set by perf, the default is the minimum that
won't (on its own) exceed the default kernel.perf_event_max_sample_rate
default of 10 samples/s.
Signed-off-by: Robert
attempt to open a stream
will return an error.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile| 3 +
drivers/gpu/drm/i915/i915_drv.c | 4 +
drivers/gpu/drm/i915/i915_drv.h | 91
drivers/gpu/drm/i915/i915_perf.c
ake -C gputop-data -f Makefile.xml SYSFS=0 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915_drv.h| 14
drivers/gpu/drm/i915/i915_oa_hsw.c | 132 +
dri
d more fiddly error paths
in the ->read implementations.
The initialization code is now spit into an i915_perf_init() called in
i915_driver_init_early() and an i915_perf_register() called in
i915_driver_register() once we're visible to userspace, after sysfs has been
initialized.
- Robert
Robert
running any Mesa based GL application
currently results in clearing OACONTROL when initializing which would
disable the capturing of metrics.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 38 ++
1 file chan
On Mon, Aug 15, 2016 at 4:04 PM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Mon, Aug 15, 2016 at 03:41:20PM +0100, Robert Bragg wrote:
> > check_cmd() is checking whether a command adheres to certain
> > restrictions that ensure it's safe to execute within a privil
On Mon, Aug 15, 2016 at 3:57 PM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Mon, Aug 15, 2016 at 03:41:18PM +0100, Robert Bragg wrote:
> > Adds base i915 perf infrastructure for Gen performance metrics.
> >
> > This adds a DRM_IOCTL_I915_PERF_OPEN ioctl th
ake -C gputop-data -f Makefile.xml SYSFS=0 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915_drv.h| 14
drivers/gpu/drm/i915/i915_oa_hsw.c | 132 +
dri
Consistent with the kernel.perf_event_paranoid sysctl option that can
allow non-root users to access system wide cpu metrics, this can
optionally allow non-root users to access system wide OA counter metrics
from Gen graphics hardware.
Signed-off-by: Robert Bragg <rob...@sixbynine.
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.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by:
In particular this tries to capture for posterity some of the early
challenges we had with using the core perf infrastructure in case we
ever want to revisit adapting perf for device metrics.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by: Robert Bragg <rob...@sixb
s/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 484 -
1 file changed, 483 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915
running any Mesa based GL application
currently results in clearing OACONTROL when initializing which would
disable the capturing of metrics.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 38 ++
1 file chan
the
description + normalization equation. Having the web UI hosted on github
hopefully lowers the bar to trying it out since it avoids needing to set up
Emscripten first as a build dependency.
Regards,
- Robert
Robert Bragg (11):
drm/i915: Add i915 perf infrastructure
drm/i915: rename
attempt to open a stream
will return an error.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile| 3 +
drivers/gpu/drm/i915/i915_drv.c | 6 +
drivers/gpu/drm/i915/i915_drv.h | 92 +
drivers/gpu/drm/i915/i915_perf.c
is disabled, but if we were to remove
OACONTROL from the parser's whitelist then the returned EINVAL would
break Mesa applications as they attempt an OACONTROL write.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 2 +-
1 file changed, 1 insertion
and code generation scripts, ref:
https://github.com/rib/gputop
> gputop-data/guids.xml
> scripts/update-guids.py
> gputop-data/oa-*.xml
> scripts/i915-perf-kernelgen.py
$ make -C gputop-data -f Makefile.xml SYSFS=1 WHITELIST=RenderBasic
Signed-off-by: Robert Bragg <rob..
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before adding more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++--
drivers/gpu/drm/i915/i915
The minimal sampling period is now configurable via a
dev.i915.oa_min_timer_exponent sysctl parameter.
Following the precedent set by perf, the default is the minimum that
won't (on its own) exceed the default kernel.perf_event_max_sample_rate
default of 10 samples/s.
Signed-off-by: Robert
On Thu, May 5, 2016 at 4:59 PM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Thu, May 05, 2016 at 04:06:02PM +0100, Robert Bragg wrote:
> > Fixed a rebase mistake where I dropped the use of the igt_ioctl wrapper
> in
> > do_ioctl().
> >
> > I'm not entir
>8 ---
In preparation for testing DRM_IOCTL_I915_PERF_OPEN which returns a file
descriptor this allows us to get the return value of ioctl called by the
do_ioctl() utility.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
lib/drmtest.h | 11 ---
1 file changed, 8 inse
In preparation for testing DRM_IOCTL_I915_PERF_OPEN which returns a file
descriptor this allows us to get the return value of ioctl called by the
do_ioctl() utility.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
lib/drmtest.h | 11 ---
1 file changed, 8 insertions
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
tests/Makefile.sources |1 +
tests/perf.c | 2053
2 files changed, 2054 insertions(+)
create mode 100644 tests/perf.c
diff --git a/tests/Makefile.sources b
On Wed, May 4, 2016 at 2:24 PM, Robert Bragg <rob...@sixbynine.org> wrote:
>
>
> On Wed, May 4, 2016 at 1:24 PM, Daniel Vetter <dan...@ffwll.ch> wrote:
>
>> On Wed, May 04, 2016 at 10:49:53AM +0100, Robert Bragg wrote:
>> > On Wed, May 4, 2016 a
On Wed, May 4, 2016 at 1:24 PM, Daniel Vetter <dan...@ffwll.ch> wrote:
> On Wed, May 04, 2016 at 10:49:53AM +0100, Robert Bragg wrote:
> > On Wed, May 4, 2016 at 10:09 AM, Martin Peres <
> martin.pe...@linux.intel.com>
> > wrote:
> >
> &g
On Wed, May 4, 2016 at 10:04 AM, Martin Peres <martin.pe...@linux.intel.com>
wrote:
> On 03/05/16 22:34, Robert Bragg wrote:
>
>> Sorry for the delay replying to this, I missed it.
>>
>
> No worries!
>
>
>> On Sat, Apr 23, 2016 at 11:34 AM, Martin Peres
On Wed, May 4, 2016 at 10:09 AM, Martin Peres <martin.pe...@linux.intel.com>
wrote:
> On 03/05/16 23:03, Robert Bragg wrote:
>
>>
>>
>> On Tue, May 3, 2016 at 8:34 PM, Robert Bragg <rob...@sixbynine.org
>> <mailto:rob...@sixbynine.org>> wrote:
&
On Fri, Apr 29, 2016 at 7:50 PM, Matthew Auld <
matthew.william.a...@gmail.com> wrote:
> > + bo = i915_gem_object_create(dev_priv->dev, OA_BUFFER_SIZE);
> > + if (bo == NULL) {
>
> IS_ERR()
>
Ah, yup, thanks.
___
Intel-gfx mailing list
Sorry for the delay replying to this, I missed it.
On Sat, Apr 23, 2016 at 11:34 AM, Martin Peres <martin.pe...@free.fr> wrote:
> On 20/04/16 17:23, Robert Bragg wrote:
>
>> Gen graphics hardware can be set up to periodically write snapshots of
>> performance counters in
This adds 'compute', 'compute extended', 'memory reads', 'memory writes'
and 'sampler balance' metric sets for Haswell.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 483 -
1 file changed, 482 insertions
The minimal sampling period is now configurable via a
dev.i915.oa_min_timer_exponent sysctl parameter.
Following the precedent set by perf, the default is the minimum that
won't (on its own) exceed the default kernel.perf_event_max_sample_rate
default of 10 samples/s.
Signed-off-by: Robert
. The is a globally unique ID for a
specific OA unit configuration that can be reliably used as a key to
lookup corresponding counter meta data and normalization equations.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_drv.h| 2 ++
drivers/gpu/dr
Consistent with the kernel.perf_event_paranoid sysctl option that can
allow non-root users to access system wide cpu metrics, this can
optionally allow non-root users to access system wide OA counter metrics
from Gen graphics hardware.
Signed-off-by: Robert Bragg <rob...@sixbynine.
Adds a static OA unit, MUX + B Counter configuration for basic render
metrics on Haswell. This is autogenerated from an internal XML
description of metric sets.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915
is disabled, but if we were to remove
OACONTROL from the parser's whitelist then the returned EINVAL would
break Mesa applications as they attempt an OACONTROL write.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 2 +-
1 file changed, 1 insertion
attempt to open a stream
will return an error.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile| 3 +
drivers/gpu/drm/i915/i915_dma.c | 8 +
drivers/gpu/drm/i915/i915_drv.h | 92 +
drivers/gpu/drm/i915/i915_perf.c
running any Mesa based GL application
currently results in clearing OACONTROL when initializing which would
disable the capturing of metrics.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 33 ++---
1 file chan
Hopefully covers the last issues raised by Chris and addresses the open issue I
had with removing OACONTROL from the command parser whitelist.
- Robert
Robert Bragg (10):
drm/i915: Add i915 perf infrastructure
drm/i915: rename OACONTROL GEN7_OACONTROL
drm/i915: return EACCES for check_cmd
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.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by:
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before adding more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++--
drivers/gpu/drm/i915/i915
On Wed, Apr 20, 2016 at 11:46 PM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Wed, Apr 20, 2016 at 03:23:10PM +0100, Robert Bragg wrote:
> > +static void gen7_init_oa_buffer(struct drm_i915_private *dev_priv)
> > +{
> > + /* Pre-DevBDW: OABUFFER mu
On Thu, Apr 21, 2016 at 4:18 PM, Robert Bragg <rob...@sixbynine.org> wrote:
>
>
> On Thu, Apr 21, 2016 at 12:09 AM, Chris Wilson <ch...@chris-wilson.co.uk>
> wrote:
>
>> On Wed, Apr 20, 2016 at 03:23:10PM +0100, Robert Bragg wrote:
>> > +static void i91
On Wed, Apr 20, 2016 at 10:11 PM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Wed, Apr 20, 2016 at 03:23:10PM +0100, Robert Bragg wrote:
> > +static void gen7_update_oacontrol_locked(struct drm_i915_private
> *dev_priv)
> > +{
> > + assert_spi
On Wed, Apr 20, 2016 at 11:52 PM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Wed, Apr 20, 2016 at 03:23:10PM +0100, Robert Bragg wrote:
> > +static int i915_oa_read(struct i915_perf_stream *stream,
> > + struct i915_perf_read_state *read_state)
&g
On Thu, Apr 21, 2016 at 12:09 AM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Wed, Apr 20, 2016 at 03:23:10PM +0100, Robert Bragg wrote:
> > +static void i915_oa_stream_enable(struct i915_perf_stream *stream)
> > +{
> > + struct drm_i915_private *
On Thu, Apr 21, 2016 at 12:16 AM, Chris Wilson <ch...@chris-wilson.co.uk>
wrote:
> On Wed, Apr 20, 2016 at 03:23:10PM +0100, Robert Bragg wrote:
> > +static int hsw_enable_metric_set(struct drm_i915_private *dev_priv)
> > +{
> > + int ret = i915_oa_sel
zero which
disables the OA unit which may be in use via the i915 perf interface.
Regards,
- Robert
On Wed, Apr 20, 2016 at 3:23 PM, Robert Bragg <rob...@sixbynine.org> wrote:
> I've been working on some i-g-t tests for this new interface and while I
> still
> have some more tests to wri
The minimal sampling period is now configurable via a
dev.i915.oa_min_timer_exponent sysctl parameter.
Following the precedent set by perf, the default is the minimum that
won't (on its own) exceed the default kernel.perf_event_max_sample_rate
default of 10 samples/s.
Signed-off-by: Robert
. The is a globally unique ID for a
specific OA unit configuration that can be reliably used as a key to
lookup corresponding counter meta data and normalization equations.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_drv.h| 2 ++
drivers/gpu/dr
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.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by:
This adds 'compute', 'compute extended', 'memory reads', 'memory writes'
and 'sampler balance' metric sets for Haswell.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 483 -
1 file changed, 482 insertions
Adds a static OA unit, MUX + B Counter configuration for basic render
metrics on Haswell. This is autogenerated from an internal XML
description of metric sets.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915
Consistent with the kernel.perf_event_paranoid sysctl option that can
allow non-root users to access system wide cpu metrics, this can
optionally allow non-root users to access system wide OA counter metrics
from Gen graphics hardware.
Signed-off-by: Robert Bragg <rob...@sixbynine.
seem to cause a problem based on v4.5 with the
same gnome-shell/mesa versions.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 33 ++---
1 file changed, 2 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/dr
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before add more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++--
drivers/gpu/drm/i915/i915
attempt to open a stream
will return an error.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile| 3 +
drivers/gpu/drm/i915/i915_dma.c | 8 +
drivers/gpu/drm/i915/i915_drv.h | 86
drivers/gpu/drm/i915/i915_perf.c
-gpu-tools
branch = wip/rib/i915-perf-tests
or browsed here:
https://github.com/rib/intel-gpu-tools/commits/wip/rib/i915-perf-tests
Also for reference these patches can be fetched from here:
https://github.com/rib/linux
branch = wip/rib/oa-2016-04-19-nightly
Regards,
- Robert
Robert Bragg (9
Hi Sourab,
As Sergio Martinez has started experimenting with this in gputop and
reported seeing lots of ENOSPC errors being reported when reading I had a
look into this and saw a few issues with how we check that there's data
available to read in command stream mode, and a I think there's a
On Thu, Feb 4, 2016 at 1:42 AM, Emil Velikov <emil.l.veli...@gmail.com>
wrote:
> On 3 February 2016 at 18:39, Robert Bragg <rob...@sixbynine.org> wrote:
>
> > index a5524cc..68ca26e 100644
> > --- a/include/uapi/drm/i915_drm.h
> > +++ b/include/uapi/drm/
On Thu, Feb 4, 2016 at 1:17 PM, Robert Bragg <rob...@sixbynine.org> wrote:
>
> On Thu, Feb 4, 2016 at 1:42 AM, Emil Velikov <emil.l.veli...@gmail.com>
> wrote:
>
>> On 3 February 2016 at 18:39, Robert Bragg <rob...@sixbynine.org> wrote:
&g
Adds a static OA unit, MUX + B Counter configuration for basic render
metrics on Haswell. This is autogenerated from an internal XML
description of metric sets.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile | 3 +-
drivers/gpu/drm/i915/i915
. The is a globally unique ID for a
specific OA unit configuration that can be reliably used as a key to
lookup corresponding counter meta data and normalization equations.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_drv.h| 2 ++
drivers/gpu/dr
Consistent with the kernel.perf_event_paranoid sysctl option that can
allow non-root users to access system wide cpu metrics, this can
optionally allow non-root users to access system wide OA counter metrics
from Gen graphics hardware.
Signed-off-by: Robert Bragg <rob...@sixbynine.
OACONTROL changes quite a bit for gen8, with some bits split out into a
per-context OACTXCONTROL register. Rename now before add more gen7 OA
registers
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++--
drivers/gpu/drm/i915/i915
The minimal sampling period is now configurable via a
dev.i915.oa_min_timer_exponent sysctl parameter.
Following the precedent set by perf, the default is the minimum that
won't (on its own) exceed the default kernel.perf_event_max_sample_rate
default of 10 samples/s.
Signed-off-by: Robert
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.
Cc: Chris Wilson <ch...@chris-wilson.co.uk>
Signed-off-by:
This adds 'compute', 'compute extended', 'memory reads', 'memory writes'
and 'sampler balance' metric sets for Haswell.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 513 +++--
1 file changed, 497 insertions(
a stream
will return an error.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/Makefile| 3 +
drivers/gpu/drm/i915/i915_dma.c | 7 +
drivers/gpu/drm/i915/i915_drv.h | 88
drivers/gpu/drm/i915/i915_perf.c
This adds 'compute', 'compute extended', 'memory reads', 'memory writes'
and 'sampler balance' metric sets for Haswell.
Signed-off-by: Robert Bragg <rob...@sixbynine.org>
---
drivers/gpu/drm/i915/i915_oa_hsw.c | 483 -
1 file changed, 482 insertions
201 - 300 of 363 matches
Mail list logo