Re: [Intel-gfx] [PATCH] drm/i915/gt: Sanitize RPS interrupts upon resume

Hi Chris, On Sat, May 02, 2020 at 06:35:12PM +0100, Chris Wilson wrote: > Currently we clear and disable the RPS pm interrupts on module load, and > presume that they remain disabled forevermore. However, the mask is > cleared on suspend and so after resume they may start showing up again > unexep

[Intel-gfx] ✗ Fi.CI.IGT: failure for drm/i915/gem: Implement legacy MI_STORE_DATA_IMM

== Series Details == Series: drm/i915/gem: Implement legacy MI_STORE_DATA_IMM URL : https://patchwork.freedesktop.org/series/76866/ State : failure == Summary == CI Bug Log - changes from CI_DRM_8412_full -> Patchwork_17555_full Summary ---

[Intel-gfx] ✓ Fi.CI.IGT: success for drm/i915/gt: Sanitize RPS interrupts upon resume

== Series Details == Series: drm/i915/gt: Sanitize RPS interrupts upon resume URL : https://patchwork.freedesktop.org/series/76863/ State : success == Summary == CI Bug Log - changes from CI_DRM_8411_full -> Patchwork_17554_full Summary ---

[Intel-gfx] ✗ Fi.CI.IGT: failure for perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev3)

== Series Details == Series: perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev3) URL : https://patchwork.freedesktop.org/series/76325/ State : failure == Summary == CI Bug Log - changes from CI_DRM_8411_full -> Patchwork_17553_full ===

[Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915/gem: Implement legacy MI_STORE_DATA_IMM

== Series Details == Series: drm/i915/gem: Implement legacy MI_STORE_DATA_IMM URL : https://patchwork.freedesktop.org/series/76866/ State : success == Summary == CI Bug Log - changes from CI_DRM_8412 -> Patchwork_17555 Summary --- **

[Intel-gfx] [PATCH] drm/i915/gem: Implement legacy MI_STORE_DATA_IMM

The older arches did not convert MI_STORE_DATA_IMM to using the GTT, but left them writing to a physical address. The notes suggest that the primary reason would be so that the writes were cache coherent, as the CPU cache uses physical tagging. As such we did not implement the legacy variant of MI_

[Intel-gfx] ✓ Fi.CI.IGT: success for drm/i915: Mark concurrent submissions with a weak-dependency (rev2)

== Series Details == Series: drm/i915: Mark concurrent submissions with a weak-dependency (rev2) URL : https://patchwork.freedesktop.org/series/76860/ State : success == Summary == CI Bug Log - changes from CI_DRM_8410_full -> Patchwork_17550_full ==

[Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915/gt: Sanitize RPS interrupts upon resume

== Series Details == Series: drm/i915/gt: Sanitize RPS interrupts upon resume URL : https://patchwork.freedesktop.org/series/76863/ State : success == Summary == CI Bug Log - changes from CI_DRM_8411 -> Patchwork_17554 Summary --- **

[Intel-gfx] ✓ Fi.CI.BAT: success for perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev3)

== Series Details == Series: perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev3) URL : https://patchwork.freedesktop.org/series/76325/ State : success == Summary == CI Bug Log - changes from CI_DRM_8411 -> Patchwork_17553 =

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev3)

== Series Details == Series: perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev3) URL : https://patchwork.freedesktop.org/series/76325/ State : warning == Summary == $ dim checkpatch origin/drm-tip 9cb5cee2dd0e perf/core: Only copy-to-user after completely unlocking a

[Intel-gfx] ✓ Fi.CI.BAT: success for perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev2)

== Series Details == Series: perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev2) URL : https://patchwork.freedesktop.org/series/76325/ State : success == Summary == CI Bug Log - changes from CI_DRM_8411 -> Patchwork_17552 =

[Intel-gfx] [PATCH] drm/i915/gt: Sanitize RPS interrupts upon resume

Currently we clear and disable the RPS pm interrupts on module load, and presume that they remain disabled forevermore. However, the mask is cleared on suspend and so after resume they may start showing up again unexepectedly. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1811 Fixes: 8

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev2)

== Series Details == Series: perf/core: Only copy-to-user after completely unlocking all locks, v3. (rev2) URL : https://patchwork.freedesktop.org/series/76325/ State : warning == Summary == $ dim checkpatch origin/drm-tip 435247c587f9 perf/core: Only copy-to-user after completely unlocking a

[Intel-gfx] [CI] perf/core: Only copy-to-user after completely unlocking all locks, v3.

From: Maarten Lankhorst We inadvertently create a dependency on mmap_sem with a whole chain. This breaks any user who wants to take a lock and call rcu_barrier(), while also taking that lock inside mmap_sem: <4> [604.892532] == <4> [604.892534

[Intel-gfx] ✗ Fi.CI.BUILD: failure for Introduce Rocket Lake (rev2)

== Series Details == Series: Introduce Rocket Lake (rev2) URL : https://patchwork.freedesktop.org/series/76826/ State : failure == Summary == Applying: drm/i915/rkl: Add RKL platform info and PCI ids Applying: x86/gpu: add RKL stolen memory support Applying: drm/i915/rkl: Re-use TGL GuC/HuC fi

[Intel-gfx] [CI] perf/core: Only copy-to-user after completely unlocking all locks, v3.

From: Maarten Lankhorst We inadvertently create a dependency on mmap_sem with a whole chain. This breaks any user who wants to take a lock and call rcu_barrier(), while also taking that lock inside mmap_sem: <4> [604.892532] == <4> [604.892534

Re: [Intel-gfx] [PATCH 11/23] drm/i915/rkl: Add cdclk support

Hi Matt, The follow cdclk doesn't looked right, isn’t it should be 96000 and 54 according to their respective divider and ratio? + { .refclk = 19200, .cdclk = 192000, .divider = 3, .ratio = 15 }, + { .refclk = 24000, .cdclk = 552000, .divider = 2, .ratio = 45 }, Reg

[Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915: Mark concurrent submissions with a weak-dependency (rev2)

== Series Details == Series: drm/i915: Mark concurrent submissions with a weak-dependency (rev2) URL : https://patchwork.freedesktop.org/series/76860/ State : success == Summary == CI Bug Log - changes from CI_DRM_8410 -> Patchwork_17550 Su

[Intel-gfx] [PATCH] drm/i915: Mark concurrent submissions with a weak-dependency

We recorded the dependencies for WAIT_FOR_SUBMIT in order that we could correctly perform priority inheritance from the parallel branches to the common trunk. However, for the purpose of timeslicing and reset handling, the dependency is weak -- as we the pair of requests are allowed to run in paral

[Intel-gfx] [PATCH] drm/i915: Mark concurrent submissions with a weak-dependency

We recorded the dependencies for WAIT_FOR_SUBMIT in order that we could correctly perform priority inheritance from the parallel branches to the common trunk. However, for the purpose of timeslicing and reset handling, the dependency is weak -- as we the pair of requests are allowed to run in paral

[Intel-gfx] [PATCH i-g-t 3/3] i915/gem_exec_fence: Teach invalid-wait about invalid future fences

When we allow a wait on a future future fence, it must autoexpire if the fence is never signaled by userspace. Signed-off-by: Chris Wilson --- tests/i915/gem_exec_fence.c | 243 +++- 1 file changed, 240 insertions(+), 3 deletions(-) diff --git a/tests/i915/gem_ex

[Intel-gfx] [PATCH i-g-t 1/3] intel-ci: Only skip the hanging gem_exec_fence tests

gem_exec_fence includes a bunch of functional syncobj tests that are currently being skipped due to an eagerness to avoid the intentionally very slow hang tests. Signed-off-by: Chris Wilson --- tests/intel-ci/blacklist.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests

[Intel-gfx] [PATCH i-g-t 2/3] lib/i915: Report scheduler caps for timeslicing

Signed-off-by: Chris Wilson --- include/drm-uapi/i915_drm.h | 8 +--- lib/i915/gem_scheduler.c| 15 +++ lib/i915/gem_scheduler.h| 1 + 3 files changed, 21 insertions(+), 3 deletions(-) diff --git a/include/drm-uapi/i915_drm.h b/include/drm-uapi/i915_drm.h index 2b55af13

[Intel-gfx] ✗ Fi.CI.IGT: failure for drm/i915/selftests: Repeat the rps clock frequency measurement

== Series Details == Series: drm/i915/selftests: Repeat the rps clock frequency measurement URL : https://patchwork.freedesktop.org/series/76846/ State : failure == Summary == CI Bug Log - changes from CI_DRM_8409_full -> Patchwork_17549_full ===

[Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915/selftests: Repeat the rps clock frequency measurement

== Series Details == Series: drm/i915/selftests: Repeat the rps clock frequency measurement URL : https://patchwork.freedesktop.org/series/76846/ State : success == Summary == CI Bug Log - changes from CI_DRM_8409 -> Patchwork_17549 Summary

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/i915/selftests: Repeat the rps clock frequency measurement

== Series Details == Series: drm/i915/selftests: Repeat the rps clock frequency measurement URL : https://patchwork.freedesktop.org/series/76846/ State : warning == Summary == $ dim checkpatch origin/drm-tip 78830699b88e drm/i915/selftests: Repeat the rps clock frequency measurement -:67: CHEC

[Intel-gfx] [PATCH] drm/i915/selftests: Repeat the rps clock frequency measurement

Repeat the measurement of the clock frequency a few times and use the median to try and reduce the systematic measurement error. Signed-off-by: Chris Wilson --- drivers/gpu/drm/i915/gt/selftest_rps.c | 53 +++--- 1 file changed, 39 insertions(+), 14 deletions(-) diff --git a

Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Setup multicast register steering for all gen >= 10

Quoting Matt Roper (2020-05-02 05:57:42) > @@ -961,6 +955,9 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, > struct i915_wa_list *wal) > static void > gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal) > { > + if (INTEL_GEN(i915) >= 10) > +