On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
> The number of scalers can depend on the pipe, so require at least 1
> scaler before running any subtests.
>
> Signed-off-by: Maarten Lankhorst
> ---
> tests/kms_plane_scaling.c | 20 ++--
> 1 file changed, 14 insertion
On 15/01/2018 18:23, Lionel Landwerlin wrote:
On 15/01/18 17:54, Tvrtko Ursulin wrote:
On 15/01/2018 14:41, Lionel Landwerlin wrote:
With the introduction of asymmetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell userspace what subslices
are available. Here we
== Series Details ==
Series: kms_plane_scaling tests.
URL : https://patchwork.freedesktop.org/series/36485/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
84a308022028a55903a1916fcee516aab768ed48 tests/kms_plane: Run test for all
supported pixel formats, v
== Series Details ==
Series: series starting with [01/10] drm/i915: Only attempt to scan the
requested number of shrinker slabs
URL : https://patchwork.freedesktop.org/series/36501/
State : success
== Summary ==
Test kms_frontbuffer_tracking:
Subgroup fbc-rgb565-draw-render:
On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
> The test only runs on gen9+, so we can safely replace all calls with
> COMMIT_ATOMIC.
>
> Also perform some cleanups by making fb an array, and cleaning up in
> prepare_crtc. This way failed subtests won't cause failures in other
> subt
On 15/01/2018 20:57, Chris Wilson wrote:
Tvrtko noticed that the comments describing the interaction of RCU and
the deferred worker for freeing drm_i915_gem_object were a little
confusing, so attempt to bring some sense to them.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Cc: Joonas Lahtin
On 15/01/2018 20:43, Chris Wilson wrote:
Check that we can successfully wait upon a dma_fence using the
i915_sw_fence, including the optional timeout mechanism.
v2: Account for the rounding up of the timeout to the next second.
Unfortunately, the minimum delay is then 1 second.
Signed-off-by:
On 15/01/2018 21:24, Chris Wilson wrote:
About the third resend of this series that tries to curtail the prolonged
reference lifetimes of fences via the signaler thread when the CPUs are
saturated by interrupts.
Happens on CI, regularly, occasionally? In the real-world it shouldnt
right? Tryi
On Mon, 2018-01-15 at 13:10 +0200, Tomi Sarvela wrote:
> On 15/01/18 12:28, Zhenyu Wang wrote:
> > On 2018.01.15 12:07:28 +0200, Joonas Lahtinen wrote:
> > > On Fri, 2018-01-12 at 14:08 +0800, Du, Changbin wrote:
> > > > On Fri, Jan 12, 2018 at 11:32:30AM +0530, Sagar Arun Kamble wrote:
> > > > > I
On Wed, 10 Jan 2018, Mustamin B Mustaffa wrote:
> Currently, BXT_PP is hardcoded with value '0'.
> It practically disabled eDP backlight on MRB (BXT) platform.
>
> This patch will tell which BXT_PP registers (there are two set of PP_CONTROL
> in the spec)
> to be used as defined in VBT (Video Bio
On 15/01/2018 21:24, Chris Wilson wrote:
When we finally decide the gpu is idle, that is a good time to shrink
our kmem_caches.
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/i915_gem.c | 22 ++
1 file changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/i915/i9
Quoting Tvrtko Ursulin (2018-01-16 09:52:10)
>
> On 15/01/2018 21:24, Chris Wilson wrote:
> > About the third resend of this series that tries to curtail the prolonged
> > reference lifetimes of fences via the signaler thread when the CPUs are
> > saturated by interrupts.
>
> Happens on CI, regul
The number of scalers can depend on the pipe, so require at least 1
scaler before running any subtests.
Changes since v1:
- More closely match kernel implementation. (Mika)
Signed-off-by: Maarten Lankhorst
---
tests/kms_plane_scaling.c | 22 --
1 file changed, 16 insertions(
Quoting Tvrtko Ursulin (2018-01-16 09:48:48)
>
> On 15/01/2018 20:43, Chris Wilson wrote:
> > +static struct dma_fence *alloc_dma_fence(void)
> > +{
> > + struct dma_fence *dma;
> > +
> > + dma = kmalloc(sizeof(*dma), GFP_KERNEL);
> > + if (dma)
> > + dma_fence_init(dma, &m
On 15/01/2018 21:24, Chris Wilson wrote:
If we fail to allocate a new request, make sure we recover the pages
that are in the process of being freed by inserting an RCU barrier.
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/i915_gem_request.c | 3 +++
1 file changed, 3 insertions(+)
One important use of partial vma is to provide mappable access to the
object while it is being used elsewhere (pinned entirely into the
unmappable portion of the Global GTT, i.e. for use as a display scanout).
Signed-off-by: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/selftests/i9
On Tue, 16 Jan 2018 10:53:47 +0100, Joonas Lahtinen
wrote:
On Mon, 2018-01-15 at 13:10 +0200, Tomi Sarvela wrote:
On 15/01/18 12:28, Zhenyu Wang wrote:
> On 2018.01.15 12:07:28 +0200, Joonas Lahtinen wrote:
> > On Fri, 2018-01-12 at 14:08 +0800, Du, Changbin wrote:
> > > On Fri, Jan 12, 2018
On 15/01/2018 21:24, Chris Wilson wrote:
If we submit a request and see that the previous request on this
timeline was already signaled, we first do not need to add the
dependency tracker for that completed request and secondly we know that
we there is then a large backlog in retiring requests a
Quoting Tvrtko Ursulin (2018-01-16 10:00:16)
>
> On 15/01/2018 21:24, Chris Wilson wrote:
> > When we finally decide the gpu is idle, that is a good time to shrink
> > our kmem_caches.
> >
> > Signed-off-by: Chris Wilson
> > ---
> > drivers/gpu/drm/i915/i915_gem.c | 22 ++
>
== Series Details ==
Series: kms_plane_scaling tests. (rev2)
URL : https://patchwork.freedesktop.org/series/36485/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
84a308022028a55903a1916fcee516aab768ed48 tests/kms_plane: Run test for all
supported pixel for
Quoting Tvrtko Ursulin (2018-01-16 10:10:28)
>
> On 15/01/2018 21:24, Chris Wilson wrote:
> > If we fail to allocate a new request, make sure we recover the pages
> > that are in the process of being freed by inserting an RCU barrier.
> >
> > Signed-off-by: Chris Wilson
> > ---
> > drivers/gpu
Quoting Tvrtko Ursulin (2018-01-16 10:18:55)
>
> On 15/01/2018 21:24, Chris Wilson wrote:
> > If we submit a request and see that the previous request on this
> > timeline was already signaled, we first do not need to add the
> > dependency tracker for that completed request and secondly we know t
On Fri, 12 Jan 2018, Ville Syrjala wrote:
> From: Ville Syrjälä
>
> Allow encoders to customize their hotplug processing by moving the
> intel_hpd_irq_event() code into an encoder hotplug vfunc. Currently
> only SDVO needs this to re-enable hotplug signalling in the SDVO
> chip. We'll use this sa
On 16/01/18 08:42, Tvrtko Ursulin wrote:
On 15/01/2018 18:23, Lionel Landwerlin wrote:
On 15/01/18 17:54, Tvrtko Ursulin wrote:
On 15/01/2018 14:41, Lionel Landwerlin wrote:
With the introduction of asymmetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell users
== Series Details ==
Series: drm/i915/selftests: Extend partial vma coverage to check parallel
creation
URL : https://patchwork.freedesktop.org/series/36520/
State : success
== Summary ==
Series 36520v1 drm/i915/selftests: Extend partial vma coverage to check
parallel creation
https://patchw
Quoting Tvrtko Ursulin (2018-01-16 09:48:48)
>
> On 15/01/2018 20:43, Chris Wilson wrote:
> > Check that we can successfully wait upon a dma_fence using the
> > i915_sw_fence, including the optional timeout mechanism.
> >
> > v2: Account for the rounding up of the timeout to the next second.
> >
== Series Details ==
Series: kms_plane_scaling tests. (rev2)
URL : https://patchwork.freedesktop.org/series/36485/
State : failure
== Summary ==
Test kms_cursor_crc:
Subgroup cursor-128x128-suspend:
skip -> PASS (shard-snb) fdo#103880
Test gem_softpin:
Signed-off-by: Petri Latvala
---
tools/meson.build | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/meson.build b/tools/meson.build
index 7fc5390a..4258853e 100644
--- a/tools/meson.build
+++ b/tools/meson.build
@@ -1,4 +1,5 @@
tools_progs_noisnt = [
+ 'cnl_compute_wrpll',
If the directories contain spaces, run-test.sh fails.
Signed-off-by: Petri Latvala
---
assembler/test/run-test.sh | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/assembler/test/run-test.sh b/assembler/test/run-test.sh
index b06e1044..f5e1a8fb 100644
--- a/assembl
If the directories contain spaces, rst2man.sh fails.
Signed-off-by: Petri Latvala
---
man/rst2man.sh | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/man/rst2man.sh b/man/rst2man.sh
index fc2b5ed8..8106ca4b 100755
--- a/man/rst2man.sh
+++ b/man/rst2man.sh
@@ -3,14
Eventually we're switching the official name to "IGT GPU Tools", but
right now there's still a lot of hardcoding to intel-gpu-tools that is
to be fixed in the near future.
Rename the project in toplevel meson.build to intel-gpu-tools to get
meson to generate tarballs roughly the same as autotools
On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
> From: Jyoti Yadav
>
> This patch adds subtest to test scaler clipping and clamping
> scenario.
>
> Changes since v1:
> - Modify test to work with the changes to kms_plane_scaling.
> (Maarten)
> Changes since v2:
> - Use get_num_scaler
As described in the WA on GLK and CNL planes on the right edge of the
screen that have less than 4 pixels visible from the beginning of the
plane to the edge of the screen can cause FIFO underflow and display
corruption.
On GLK/CNL I could trigger the problem only if the plane was at the same
time
While running the kms_plane clipping test I noticed a similar problem to
the one described in Display WA #1175. In this case, similarly for
planes other than the cursor, with 1 or 3 pixels visible from the left
edge of the screen to the end of the plane and an odd plane X offset
used for clipping c
On Tue, 2018-01-16 at 11:03 +0100, Maarten Lankhorst wrote:
> The number of scalers can depend on the pipe, so require at least 1
> scaler before running any subtests.
>
> Changes since v1:
> - More closely match kernel implementation. (Mika)
>
Reviewed-by: Mika Kahola
> Signed-off-by: Maarten
== Series Details ==
Series: drm/i915/selftests: Extend partial vma coverage to check parallel
creation
URL : https://patchwork.freedesktop.org/series/36520/
State : success
== Summary ==
Warning: bzip Patchwork_7679/shard-snb7/results4.json.bz2 wasn't in correct
JSON format
Test kms_frontbu
== Series Details ==
Series: series starting with [v2,1/2] drm/i915: Add display WA #1175 for planes
ending close to right screen edge
URL : https://patchwork.freedesktop.org/series/36526/
State : success
== Summary ==
Series 36526v1 series starting with [v2,1/2] drm/i915: Add display WA #117
On Tue, Jan 16, 2018 at 01:13:03PM +0200, Petri Latvala wrote:
> Signed-off-by: Petri Latvala
Reviewed-by: Arkadiusz Hiler
one the whole series
--
Cheers,
Arek
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/
On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
> From: Jyoti Yadav
>
> This patch adds subtest for testing scaling in combination with
> rotation
> and pixel formats.
>
> Changes since v1:
> - Rework test to work with the other changes to kms_plane_scaling.
> (Maarten)
> - Remove ha
== Series Details ==
Series: series starting with [1/4] meson: Build cnl_compute_wrpll
URL : https://patchwork.freedesktop.org/series/36525/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
84a308022028a55903a1916fcee516aab768ed48 tests/kms_plane: Run test fo
When we finally decide the gpu is idle, that is a good time to shrink
our kmem_caches.
v2: Comment upon the random sprinkling of rcu_barrier() inside the idle
worker.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem.c | 30 ++
1 file
Quoting Tvrtko Ursulin (2018-01-16 09:52:10)
>
> On 15/01/2018 21:24, Chris Wilson wrote:
> > About the third resend of this series that tries to curtail the prolonged
> > reference lifetimes of fences via the signaler thread when the CPUs are
> > saturated by interrupts.
>
> Happens on CI, regul
If we fail to allocate a new request, make sure we recover the pages
that are in the process of being freed by inserting an RCU barrier.
v2: Comment before the shrink and barrier in the error path.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_request.c | 11
If we submit a request and see that the previous request on this
timeline was already signaled, we first do not need to add the
dependency tracker for that completed request and secondly we know that
we there is then a large backlog in retiring requests affecting this
timeline. Given that we just s
On 15/01/18 17:43, Tvrtko Ursulin wrote:
On 15/01/2018 14:41, Lionel Landwerlin wrote:
This might be useful information for developers looking at an error
state.
v2: Place topology towards the end of the error state (Chris)
v3: Reuse common printing code (Michal)
Signed-off-by: Lionel Landwe
There are a number of information that are readable from hardware
registers and that we would like to make accessible to userspace. One
particular example is the topology of the execution units (how are
execution units grouped in subslices and slices and also which ones
have been fused off for die
This might be useful information for developers looking at an error
state.
v2: Place topology towards the end of the error state (Chris)
v3: Reuse common printing code (Michal)
Signed-off-by: Lionel Landwerlin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gpu_error.c | 9 +
Up to now, subslice mask was assumed to be uniform across slices. But
starting with Cannonlake, slices can be asymmetric (for example slice0
has different number of subslices as slice1+). This change stores all
subslices masks for all slices rather than having a single mask that
applies to all slic
While the end goal is to make this information available to userspace
through a new ioctl, there is no reason we can't display it in a human
readable fashion through debugfs.
slice0: 3 subslice(s) (0x7):
subslice0: 8 EUs (0xff)
subslice1: 8 EUs (0xff)
subslice2: 8 EUs (0xff
With the introduction of asymmetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell userspace what subslices
are available. Here we introduce a more detailed way of querying the
Gen's GPU topology that doesn't aggregate numbers.
This is essential for monitoring parts o
Now that we have that information in topology fields, let's just reused it.
v2: Style tweaks (Tvrtko)
Signed-off-by: Lionel Landwerlin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_debugfs.c | 27 +++
1 file changed, 11 insertions(+), 16 deletions(-)
diff -
Hi all,
Hopefully this is the last iteration. A few more tweaks only on patch
6 for uapi define/struct naming and factored out code in the data
exchange between kernel & userspace.
Thanks,
Lionel Landwerlin (6):
drm/i915: store all subslice masks
drm/i915/debugfs: reuse max slice/subslices a
== Series Details ==
Series: series starting with [01/10] drm/i915: Only attempt to scan the
requested number of shrinker slabs (rev3)
URL : https://patchwork.freedesktop.org/series/36501/
State : success
== Summary ==
Series 36501v3 series starting with [01/10] drm/i915: Only attempt to scan
On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
> From: Jyoti Yadav
>
> Add a subtest to display primary and overlay planes on two
> connected pipes and runs scaling test on both pipes
>
> Changes since v1:
> - Commit first before trying any scaling. (Maarten)
> - Use the same logic
Op 16-01-18 om 14:46 schreef Mika Kahola:
> On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
>> From: Jyoti Yadav
>>
>> Add a subtest to display primary and overlay planes on two
>> connected pipes and runs scaling test on both pipes
>>
>> Changes since v1:
>> - Commit first before tryi
Since vendor may set bad defaults or user just generally may prefer her health
over
display life.
1. Allow overriding of PWM frequency otherwise people use solutions like
http://devbraindom.blogspot.ru/2013/03/eliminate-led-screen-flicker-with-intel.html
which are bad because
I. frequency converta
On Tue, 2018-01-16 at 14:47 +0100, Maarten Lankhorst wrote:
> Op 16-01-18 om 14:46 schreef Mika Kahola:
> >
> > On Mon, 2018-01-15 at 15:28 +0100, Maarten Lankhorst wrote:
> > >
> > > From: Jyoti Yadav
> > >
> > > Add a subtest to display primary and overlay planes on two
> > > connected pipes
Quoting Lionel Landwerlin (2018-01-16 13:40:08)
> This might be useful information for developers looking at an error
> state.
>
> v2: Place topology towards the end of the error state (Chris)
>
> v3: Reuse common printing code (Michal)
>
> Signed-off-by: Lionel Landwerlin
> Reviewed-by: Tvrtko
From: Jyoti Yadav
This patch adds subtest for testing scaling in combination with rotation
and pixel formats.
Changes since v1:
- Rework test to work with the other changes to kms_plane_scaling. (Maarten)
- Remove hardcodes for MIN/MAX_SRC_WIDTH, and use the value directly. (Maarten)
Changes sin
== Series Details ==
Series: series starting with [01/10] drm/i915: Only attempt to scan the
requested number of shrinker slabs (rev4)
URL : https://patchwork.freedesktop.org/series/36501/
State : success
== Summary ==
Series 36501v4 series starting with [01/10] drm/i915: Only attempt to scan
== Series Details ==
Series: series starting with [v2,1/2] drm/i915: Add display WA #1175 for planes
ending close to right screen edge
URL : https://patchwork.freedesktop.org/series/36526/
State : failure
== Summary ==
Test drv_selftest:
Subgroup mock_fence:
pass
Quoting Lionel Landwerlin (2018-01-16 13:40:09)
> +int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file
> *file)
> +{
> + struct drm_i915_query *args = data;
> + struct drm_i915_query_item __user *user_item_ptr =
> + u64_to_user_ptr(args->items_ptr);
>
== Series Details ==
Series: series starting with [1/4] meson: Build cnl_compute_wrpll
URL : https://patchwork.freedesktop.org/series/36525/
State : failure
== Summary ==
Test perf:
Subgroup polling:
fail -> PASS (shard-hsw) fdo#102252
Test kms_flip:
On 16/01/18 13:57, Chris Wilson wrote:
Quoting Lionel Landwerlin (2018-01-16 13:40:08)
This might be useful information for developers looking at an error
state.
v2: Place topology towards the end of the error state (Chris)
v3: Reuse common printing code (Michal)
Signed-off-by: Lionel Landwer
On Tue, 2018-01-16 at 15:00 +0100, Maarten Lankhorst wrote:
> From: Jyoti Yadav
>
> This patch adds subtest for testing scaling in combination with
> rotation
> and pixel formats.
>
> Changes since v1:
> - Rework test to work with the other changes to kms_plane_scaling.
> (Maarten)
> - Remove ha
Quoting Lionel Landwerlin (2018-01-16 13:40:10)
> With the introduction of asymmetric slices in CNL, we cannot rely on
> the previous SUBSLICE_MASK getparam to tell userspace what subslices
> are available. Here we introduce a more detailed way of querying the
> Gen's GPU topology that doesn't aggr
On 16/01/18 14:08, Chris Wilson wrote:
Quoting Lionel Landwerlin (2018-01-16 13:40:09)
+int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+ struct drm_i915_query *args = data;
+ struct drm_i915_query_item __user *user_item_ptr =
+ u64_to
== Series Details ==
Series: drm/i915: expose RCS topology to userspace
URL : https://patchwork.freedesktop.org/series/36539/
State : success
== Summary ==
Series 36539v1 drm/i915: expose RCS topology to userspace
https://patchwork.freedesktop.org/api/1.0/series/36539/revisions/1/mbox/
Test d
== Series Details ==
Series: drm/i915: Allow user to override PWM backlight frequency and duty cycle
URL : https://patchwork.freedesktop.org/series/36540/
State : failure
== Summary ==
Applying: drm/i915: Allow user to override PWM backlight frequency and duty
cycle
error: Failed to merge in
A new intel-gpu-tools quarterly release is available with the
following changes:
Library changes:
- Added helpers for using DRM syncobj. (Jason Ekstrand)
- Refactored several i915 helpers into library functions.
(Michał Winiarski)
- Improved the GPU quiescing code to more thoroughly flush ol
On 16/01/18 14:22, Chris Wilson wrote:
Quoting Lionel Landwerlin (2018-01-16 13:40:10)
With the introduction of asymmetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell userspace what subslices
are available. Here we introduce a more detailed way of querying the
Ge
== Series Details ==
Series: kms_plane_scaling tests. (rev3)
URL : https://patchwork.freedesktop.org/series/36485/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
7b685d5790c1770eeac43c17d6b207a6df602985 Update NEWS, bump version to 1.21.
with latest DRM-Ti
Execute the same batch on each engine and check that the composite fence
across all engines completes only after the batch is completed on every
engine.
Signed-off-by: Chris Wilson
---
tests/gem_exec_fence.c | 127 +
1 file changed, 127 insertions(
EXEC_OBJECT_CAPTURE extends the type of buffers we may read during error
capture. Previously we knew that we would only see batch buffers (which
limited the objects to being from gem_create()), but now we need to
check that any buffer the user can create can be read. The first
alternate buffer type
Ensure that we always use every context at least once before we start
running the stress-test.
Signed-off-by: Chris Wilson
---
tests/gem_ctx_switch.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/tests/gem_ctx_switch.c b/tests/gem_ctx_switch.c
index fdd67202f..159554e52 100644
--- a
A new context assumes that all of its registers are in the default state
when it is created. What may happen is that a register written by one
context may leak into the second, causing mass confusion.
v2: Extend back to Sandybridge (etc)
v3: Check context preserves registers across suspend/hiberna
Just a small variant to apply a continuous context-switch load to all
engines.
---
tests/gem_ctx_switch.c | 76 ++
1 file changed, 76 insertions(+)
diff --git a/tests/gem_ctx_switch.c b/tests/gem_ctx_switch.c
index 159554e52..fe919f7d6 100644
--- a/
Signed-off-by: Chris Wilson
---
tests/kms_frontbuffer_tracking.c | 4
1 file changed, 4 insertions(+)
diff --git a/tests/kms_frontbuffer_tracking.c b/tests/kms_frontbuffer_tracking.c
index 1601cab45..8b440dadc 100644
--- a/tests/kms_frontbuffer_tracking.c
+++ b/tests/kms_frontbuffer_trackin
On 16/01/2018 13:05, Chris Wilson wrote:
When we finally decide the gpu is idle, that is a good time to shrink
our kmem_caches.
v2: Comment upon the random sprinkling of rcu_barrier() inside the idle
worker.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem.c
On 16/01/2018 15:12, Tvrtko Ursulin wrote:
On 16/01/2018 13:05, Chris Wilson wrote:
When we finally decide the gpu is idle, that is a good time to shrink
our kmem_caches.
v2: Comment upon the random sprinkling of rcu_barrier() inside the idle
worker.
Signed-off-by: Chris Wilson
Cc: Tvrtko U
On 16/01/2018 13:15, Chris Wilson wrote:
If we fail to allocate a new request, make sure we recover the pages
that are in the process of being freed by inserting an RCU barrier.
v2: Comment before the shrink and barrier in the error path.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
---
Quoting Tvrtko Ursulin (2018-01-16 15:12:43)
>
> On 16/01/2018 13:05, Chris Wilson wrote:
> > When we finally decide the gpu is idle, that is a good time to shrink
> > our kmem_caches.
> >
> > v2: Comment upon the random sprinkling of rcu_barrier() inside the idle
> > worker.
> >
> > Signed-off-
There is a suspicion that with aggressive upclocking, power rail
voltage fluctuations can disrupt c state transition, leading
to system hang.
When upclocking with 4 cpu Baytrails, bring up cpus to c1 and then
go through bins gradually towards target frequency to give leeway
for hw.
We go towards
Quoting Mika Kuoppala (2018-01-16 15:21:16)
> There is a suspicion that with aggressive upclocking, power rail
> voltage fluctuations can disrupt c state transition, leading
> to system hang.
>
> When upclocking with 4 cpu Baytrails, bring up cpus to c1 and then
> go through bins gradually towards
Chris Wilson writes:
> Quoting Mika Kuoppala (2018-01-15 12:04:40)
>> Chris Wilson writes:
>>
>> > While we talk to the punit over its sideband, we need to prevent the cpu
>> > from sleeping in order to prevent a potential machine hang.
>> >
>> > Note that by itself, it appears that pm_qos_upda
== Series Details ==
Series: series starting with [01/10] drm/i915: Only attempt to scan the
requested number of shrinker slabs (rev4)
URL : https://patchwork.freedesktop.org/series/36501/
State : success
== Summary ==
Test kms_flip:
Subgroup flip-vs-fences-interruptible:
What branch CI tests against?
I've created the patch against current torvalds/linux
16.01.2018, 17:42, "Patchwork" :
> == Series Details ==
>
> Series: drm/i915: Allow user to override PWM backlight frequency and duty
> cycle
> URL : https://patchwork.freedesktop.org/series/36540/
> State : failu
intel_power_domains_init_hw() calls set_init_power, but when using
runtime power management this call is skipped. This prevents hw readout
from taking place.
Signed-off-by: Maarten Lankhorst
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104172
Cc: imre.d...@intel.com
---
drivers/gpu/drm
It's perfectly legal to create a fb with stride < 512, and one of
the kms_plane_scaling subtests creates a very small fb.
Downgrade the WARN_ON to a simple check check, and because this
function is potentially called on every atomic update/pageflip,
downgrade the other WARN_ON to a WARN_ON_ONCE, a
Now that we have that information in topology fields, let's just reused it.
v2: Style tweaks (Tvrtko)
Signed-off-by: Lionel Landwerlin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_debugfs.c | 27 +++
1 file changed, 11 insertions(+), 16 deletions(-)
diff -
With the introduction of asymmetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell userspace what subslices
are available. Here we introduce a more detailed way of querying the
Gen's GPU topology that doesn't aggregate numbers.
This is essential for monitoring parts o
Up to now, subslice mask was assumed to be uniform across slices. But
starting with Cannonlake, slices can be asymmetric (for example slice0
has different number of subslices as slice1+). This change stores all
subslices masks for all slices rather than having a single mask that
applies to all slic
There are a number of information that are readable from hardware
registers and that we would like to make accessible to userspace. One
particular example is the topology of the execution units (how are
execution units grouped in subslices and slices and also which ones
have been fused off for die
While the end goal is to make this information available to userspace
through a new ioctl, there is no reason we can't display it in a human
readable fashion through debugfs.
slice0: 3 subslice(s) (0x7):
subslice0: 8 EUs (0xff)
subslice1: 8 EUs (0xff)
subslice2: 8 EUs (0xff
This might be useful information for developers looking at an error
state.
v2: Place topology towards the end of the error state (Chris)
v3: Reuse common printing code (Michal)
v4: Make this a one-liner (Chris)
Signed-off-by: Lionel Landwerlin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/
Hi again,
A few more changes following Chris' comments.
Cheers,
Lionel Landwerlin (6):
drm/i915: store all subslice masks
drm/i915/debugfs: reuse max slice/subslices already stored in sseu
drm/i915/debugfs: add rcs topology entry
drm/i915: add rcs topology to error state
drm/i915: add
== Series Details ==
Series: drm/i915/vlv: Ramp up gpu freq gradually
URL : https://patchwork.freedesktop.org/series/36550/
State : warning
== Summary ==
Series 36550v1 drm/i915/vlv: Ramp up gpu freq gradually
https://patchwork.freedesktop.org/api/1.0/series/36550/revisions/1/mbox/
Test kms_b
Signed-off-by: Lionel Landwerlin
---
include/drm-uapi/i915_drm.h | 126
lib/igt_perf.h | 7 ---
2 files changed, 126 insertions(+), 7 deletions(-)
diff --git a/include/drm-uapi/i915_drm.h b/include/drm-uapi/i915_drm.h
index 7f28eea4..80
Signed-off-by: Lionel Landwerlin
---
tests/Makefile.sources | 1 +
tests/meson.build | 1 +
tests/query.c | 268 +
3 files changed, 270 insertions(+)
create mode 100644 tests/query.c
diff --git a/tests/Makefile.sources b/tests/Ma
Instead of returning a zero value for non root users, return an EPERM
error.
Signed-off-by: Antonio Argenziano
Cc: Chris Wilson
Cc: Michel Thierry
---
drivers/gpu/drm/i915/i915_drv.c | 2 +-
drivers/gpu/drm/i915/i915_gem_context.c | 9 -
2 files changed, 5 insertions(+), 6 dele
1 - 100 of 158 matches
Mail list logo
