* [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
@ 2016-04-20 13:43 ville.syrjala
2016-04-20 13:57 ` Chris Wilson
` (4 more replies)
0 siblings, 5 replies; 10+ messages in thread
From: ville.syrjala @ 2016-04-20 13:43 UTC (permalink / raw)
To: intel-gfx; +Cc: stable, Akash Goel, Chris Wilson
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
GPU hangs if the RPS EI/thresholds aren't suitably aligned.
It seems like scheduling/timer interupts stop working somehow
and things get stuck eg. in usleep_range().
I bisected the problem down to
commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
I observed that before all the values were at least multiples of 25,
but afterwards they are not. And rounding things up to the next multiple
of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
but that wasn't sufficient. Also I have no idea if we might need this sort of
thing on gen9+ as well.
These are the original EI/thresholds:
LOW_POWER
GEN6_RP_UP_EI 12500
GEN6_RP_UP_THRESHOLD 11800
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 21250
BETWEEN
GEN6_RP_UP_EI 10250
GEN6_RP_UP_THRESHOLD 9225
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 18750
HIGH_POWER
GEN6_RP_UP_EI 8000
GEN6_RP_UP_THRESHOLD 6800
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 15000
These are after 8a5864377b12:
LOW_POWER
GEN6_RP_UP_EI 12500
GEN6_RP_UP_THRESHOLD 11875
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 21250
BETWEEN
GEN6_RP_UP_EI 10156
GEN6_RP_UP_THRESHOLD 9140
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 18750
HIGH_POWER
GEN6_RP_UP_EI 7812
GEN6_RP_UP_THRESHOLD 6640
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 15000
And these are what we have after this patch:
LOW_POWER
GEN6_RP_UP_EI 12500
GEN6_RP_UP_THRESHOLD 11875
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 21250
BETWEEN
GEN6_RP_UP_EI 10175
GEN6_RP_UP_THRESHOLD 9150
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 18750
HIGH_POWER
GEN6_RP_UP_EI 7825
GEN6_RP_UP_THRESHOLD 6650
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 15000
Cc: stable@vger.kernel.org
Cc: Akash Goel <akash.goel@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B
Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
drivers/gpu/drm/i915/i915_reg.h | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c21b71c86a6b..08f01f4470cd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2948,7 +2948,14 @@ enum skl_disp_power_wells {
#define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
#define BXT_RP_STATE_CAP _MMIO(0x138170)
-#define INTERVAL_1_28_US(us) (((us) * 100) >> 7)
+/*
+ * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
+ * 8300) freezing up around GPU hangs. Looks as if even
+ * scheduling/timer interrupts start misbehaving if the RPS
+ * EI/thresholds are "bad", leading to a very sluggish or even
+ * frozen machine.
+ */
+#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25)
#define INTERVAL_1_33_US(us) (((us) * 3) >> 2)
#define INTERVAL_0_833_US(us) (((us) * 6) / 5)
#define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
--
2.7.4
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-20 13:43 [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB ville.syrjala
@ 2016-04-20 13:57 ` Chris Wilson
2016-04-20 15:09 ` Ville Syrjälä
` (3 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Chris Wilson @ 2016-04-20 13:57 UTC (permalink / raw)
To: ville.syrjala; +Cc: intel-gfx, stable, Akash Goel
On Wed, Apr 20, 2016 at 04:43:56PM +0300, ville.syrjala@linux.intel.com wrote:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
>
> Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
> GPU hangs if the RPS EI/thresholds aren't suitably aligned.
> It seems like scheduling/timer interupts stop working somehow
> and things get stuck eg. in usleep_range().
>
> I bisected the problem down to
> commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> I observed that before all the values were at least multiples of 25,
> but afterwards they are not. And rounding things up to the next multiple
> of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
> but that wasn't sufficient. Also I have no idea if we might need this sort of
> thing on gen9+ as well.
>
> These are the original EI/thresholds:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11800
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10250
> GEN6_RP_UP_THRESHOLD 9225
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 8000
> GEN6_RP_UP_THRESHOLD 6800
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> These are after 8a5864377b12:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11875
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10156
> GEN6_RP_UP_THRESHOLD 9140
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 7812
> GEN6_RP_UP_THRESHOLD 6640
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> And these are what we have after this patch:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11875
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10175
> GEN6_RP_UP_THRESHOLD 9150
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 7825
> GEN6_RP_UP_THRESHOLD 6650
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> Cc: stable@vger.kernel.org
> Cc: Akash Goel <akash.goel@intel.com>
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B
> Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Wow. The change is semantically sound, so
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-20 13:43 [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB ville.syrjala
2016-04-20 13:57 ` Chris Wilson
@ 2016-04-20 15:09 ` Ville Syrjälä
2016-04-21 6:54 ` ✓ Fi.CI.BAT: success for " Patchwork
` (2 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Ville Syrjälä @ 2016-04-20 15:09 UTC (permalink / raw)
To: intel-gfx; +Cc: Akash Goel, stable
On Wed, Apr 20, 2016 at 04:43:56PM +0300, ville.syrjala@linux.intel.com wrote:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
The patch subject should probably read
"drm/i915: Make RPS EI/thresholds multiple of 25 on SNB-BDW"
since it does change more than SNB. I'll fix that up when/if I push.
>
> Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
> GPU hangs if the RPS EI/thresholds aren't suitably aligned.
> It seems like scheduling/timer interupts stop working somehow
> and things get stuck eg. in usleep_range().
>
> I bisected the problem down to
> commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> I observed that before all the values were at least multiples of 25,
> but afterwards they are not. And rounding things up to the next multiple
> of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
> but that wasn't sufficient. Also I have no idea if we might need this sort of
> thing on gen9+ as well.
>
> These are the original EI/thresholds:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11800
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10250
> GEN6_RP_UP_THRESHOLD 9225
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 8000
> GEN6_RP_UP_THRESHOLD 6800
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> These are after 8a5864377b12:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11875
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10156
> GEN6_RP_UP_THRESHOLD 9140
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 7812
> GEN6_RP_UP_THRESHOLD 6640
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> And these are what we have after this patch:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11875
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10175
> GEN6_RP_UP_THRESHOLD 9150
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 7825
> GEN6_RP_UP_THRESHOLD 6650
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> Cc: stable@vger.kernel.org
> Cc: Akash Goel <akash.goel@intel.com>
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B
> Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 9 ++++++++-
> 1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index c21b71c86a6b..08f01f4470cd 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -2948,7 +2948,14 @@ enum skl_disp_power_wells {
> #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
> #define BXT_RP_STATE_CAP _MMIO(0x138170)
>
> -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7)
> +/*
> + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
> + * 8300) freezing up around GPU hangs. Looks as if even
> + * scheduling/timer interrupts start misbehaving if the RPS
> + * EI/thresholds are "bad", leading to a very sluggish or even
> + * frozen machine.
> + */
> +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25)
> #define INTERVAL_1_33_US(us) (((us) * 3) >> 2)
> #define INTERVAL_0_833_US(us) (((us) * 6) / 5)
> #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
> --
> 2.7.4
--
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread
* ✓ Fi.CI.BAT: success for drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-20 13:43 [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB ville.syrjala
2016-04-20 13:57 ` Chris Wilson
2016-04-20 15:09 ` Ville Syrjälä
@ 2016-04-21 6:54 ` Patchwork
2016-04-21 12:20 ` [Intel-gfx] [PATCH] " Patrik Jakobsson
2016-04-21 12:40 ` ✗ Fi.CI.BAT: warning for " Patchwork
4 siblings, 0 replies; 10+ messages in thread
From: Patchwork @ 2016-04-21 6:54 UTC (permalink / raw)
To: ville.syrjala; +Cc: intel-gfx
== Series Details ==
Series: drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
URL : https://patchwork.freedesktop.org/series/5987/
State : success
== Summary ==
Series 5987v1 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
http://patchwork.freedesktop.org/api/1.0/series/5987/revisions/1/mbox/
bdw-nuci7 total:194 pass:182 dwarn:0 dfail:0 fail:0 skip:12
bdw-ultra total:194 pass:170 dwarn:0 dfail:0 fail:1 skip:23
bsw-nuc-2 total:193 pass:153 dwarn:0 dfail:0 fail:0 skip:40
byt-nuc total:193 pass:155 dwarn:0 dfail:0 fail:0 skip:38
hsw-brixbox total:194 pass:170 dwarn:0 dfail:0 fail:0 skip:24
ilk-hp8440p total:194 pass:137 dwarn:0 dfail:0 fail:0 skip:57
ivb-t430s total:194 pass:166 dwarn:0 dfail:0 fail:0 skip:28
skl-i7k-2 total:194 pass:168 dwarn:0 dfail:0 fail:1 skip:25
skl-nuci5 total:194 pass:183 dwarn:0 dfail:0 fail:0 skip:11
snb-dellxps failed to connect after reboot
snb-x220t failed to connect after reboot
Results at /archive/results/CI_IGT_test/Patchwork_1960/
eb848ab2b19d25a08ca3b2b5e4b2f74c7f7c962c drm-intel-nightly: 2016y-04m-20d-18h-48m-11s UTC integration manifest
ca6a213 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Intel-gfx] [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-20 13:43 [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB ville.syrjala
` (2 preceding siblings ...)
2016-04-21 6:54 ` ✓ Fi.CI.BAT: success for " Patchwork
@ 2016-04-21 12:20 ` Patrik Jakobsson
2016-04-22 14:26 ` Ville Syrjälä
2016-04-22 17:35 ` Ville Syrjälä
2016-04-21 12:40 ` ✗ Fi.CI.BAT: warning for " Patchwork
4 siblings, 2 replies; 10+ messages in thread
From: Patrik Jakobsson @ 2016-04-21 12:20 UTC (permalink / raw)
To: ville.syrjala; +Cc: intel-gfx, Akash Goel, stable
On Wed, Apr 20, 2016 at 04:43:56PM +0300, ville.syrjala@linux.intel.com wrote:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
>
> Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
> GPU hangs if the RPS EI/thresholds aren't suitably aligned.
> It seems like scheduling/timer interupts stop working somehow
> and things get stuck eg. in usleep_range().
>
> I bisected the problem down to
> commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> I observed that before all the values were at least multiples of 25,
> but afterwards they are not. And rounding things up to the next multiple
> of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
> but that wasn't sufficient. Also I have no idea if we might need this sort of
> thing on gen9+ as well.
Do we need to test for performance regressions on stuff like this? And if so,
who do we ping about this?
OTOH impact should be really small and since this fixes a real problem:
Reviewed-by: Patrik Jakobsson <patrik.jakobsson@linux.intel.com>
>
> These are the original EI/thresholds:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11800
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10250
> GEN6_RP_UP_THRESHOLD 9225
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 8000
> GEN6_RP_UP_THRESHOLD 6800
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> These are after 8a5864377b12:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11875
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10156
> GEN6_RP_UP_THRESHOLD 9140
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 7812
> GEN6_RP_UP_THRESHOLD 6640
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> And these are what we have after this patch:
> LOW_POWER
> GEN6_RP_UP_EI 12500
> GEN6_RP_UP_THRESHOLD 11875
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 21250
> BETWEEN
> GEN6_RP_UP_EI 10175
> GEN6_RP_UP_THRESHOLD 9150
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 18750
> HIGH_POWER
> GEN6_RP_UP_EI 7825
> GEN6_RP_UP_THRESHOLD 6650
> GEN6_RP_DOWN_EI 25000
> GEN6_RP_DOWN_THRESHOLD 15000
>
> Cc: stable@vger.kernel.org
> Cc: Akash Goel <akash.goel@intel.com>
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B
> Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 9 ++++++++-
> 1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index c21b71c86a6b..08f01f4470cd 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -2948,7 +2948,14 @@ enum skl_disp_power_wells {
> #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
> #define BXT_RP_STATE_CAP _MMIO(0x138170)
>
> -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7)
> +/*
> + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
> + * 8300) freezing up around GPU hangs. Looks as if even
> + * scheduling/timer interrupts start misbehaving if the RPS
> + * EI/thresholds are "bad", leading to a very sluggish or even
> + * frozen machine.
> + */
> +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25)
> #define INTERVAL_1_33_US(us) (((us) * 3) >> 2)
> #define INTERVAL_0_833_US(us) (((us) * 6) / 5)
> #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
> --
> 2.7.4
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Intel Sweden AB Registered Office: Knarrarnasgatan 15, 164 40 Kista, Stockholm, Sweden Registration Number: 556189-6027
^ permalink raw reply [flat|nested] 10+ messages in thread
* ✗ Fi.CI.BAT: warning for drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-20 13:43 [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB ville.syrjala
` (3 preceding siblings ...)
2016-04-21 12:20 ` [Intel-gfx] [PATCH] " Patrik Jakobsson
@ 2016-04-21 12:40 ` Patchwork
2016-04-22 17:18 ` Ville Syrjälä
4 siblings, 1 reply; 10+ messages in thread
From: Patchwork @ 2016-04-21 12:40 UTC (permalink / raw)
To: ville.syrjala; +Cc: intel-gfx
== Series Details ==
Series: drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
URL : https://patchwork.freedesktop.org/series/5987/
State : warning
== Summary ==
Series 5987v1 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
http://patchwork.freedesktop.org/api/1.0/series/5987/revisions/1/mbox/
Test gem_busy:
Subgroup basic-blt:
pass -> SKIP (bsw-nuc-2)
Test kms_flip:
Subgroup basic-flip-vs-wf_vblank:
fail -> PASS (bsw-nuc-2)
bdw-nuci7 total:194 pass:182 dwarn:0 dfail:0 fail:0 skip:12
bdw-ultra total:194 pass:170 dwarn:0 dfail:0 fail:1 skip:23
bsw-nuc-2 total:193 pass:153 dwarn:0 dfail:0 fail:0 skip:40
byt-nuc total:193 pass:155 dwarn:0 dfail:0 fail:0 skip:38
hsw-brixbox total:194 pass:170 dwarn:0 dfail:0 fail:0 skip:24
ilk-hp8440p total:194 pass:137 dwarn:0 dfail:0 fail:0 skip:57
ivb-t430s total:194 pass:166 dwarn:0 dfail:0 fail:0 skip:28
skl-i7k-2 total:194 pass:168 dwarn:0 dfail:0 fail:1 skip:25
skl-nuci5 total:194 pass:183 dwarn:0 dfail:0 fail:0 skip:11
snb-dellxps failed to connect after reboot
snb-x220t failed to connect after reboot
Results at /archive/results/CI_IGT_test/Patchwork_1960/
eb848ab2b19d25a08ca3b2b5e4b2f74c7f7c962c drm-intel-nightly: 2016y-04m-20d-18h-48m-11s UTC integration manifest
ca6a213 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Intel-gfx] [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-21 12:20 ` [Intel-gfx] [PATCH] " Patrik Jakobsson
@ 2016-04-22 14:26 ` Ville Syrjälä
2016-04-22 17:35 ` Ville Syrjälä
1 sibling, 0 replies; 10+ messages in thread
From: Ville Syrjälä @ 2016-04-22 14:26 UTC (permalink / raw)
To: intel-gfx, Akash Goel, stable
On Thu, Apr 21, 2016 at 02:20:35PM +0200, Patrik Jakobsson wrote:
> On Wed, Apr 20, 2016 at 04:43:56PM +0300, ville.syrjala@linux.intel.com wrote:
> > From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> >
> > Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
> > GPU hangs if the RPS EI/thresholds aren't suitably aligned.
> > It seems like scheduling/timer interupts stop working somehow
> > and things get stuck eg. in usleep_range().
> >
> > I bisected the problem down to
> > commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> > I observed that before all the values were at least multiples of 25,
> > but afterwards they are not. And rounding things up to the next multiple
> > of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
> > but that wasn't sufficient. Also I have no idea if we might need this sort of
> > thing on gen9+ as well.
>
> Do we need to test for performance regressions on stuff like this? And if so,
> who do we ping about this?
I think Chris or the perf team might complain if things go downhill too
much.
>
> OTOH impact should be really small and since this fixes a real problem:
>
> Reviewed-by: Patrik Jakobsson <patrik.jakobsson@linux.intel.com>
>
> >
> > These are the original EI/thresholds:
> > LOW_POWER
> > GEN6_RP_UP_EI 12500
> > GEN6_RP_UP_THRESHOLD 11800
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 21250
> > BETWEEN
> > GEN6_RP_UP_EI 10250
> > GEN6_RP_UP_THRESHOLD 9225
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 18750
> > HIGH_POWER
> > GEN6_RP_UP_EI 8000
> > GEN6_RP_UP_THRESHOLD 6800
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 15000
> >
> > These are after 8a5864377b12:
> > LOW_POWER
> > GEN6_RP_UP_EI 12500
> > GEN6_RP_UP_THRESHOLD 11875
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 21250
> > BETWEEN
> > GEN6_RP_UP_EI 10156
> > GEN6_RP_UP_THRESHOLD 9140
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 18750
> > HIGH_POWER
> > GEN6_RP_UP_EI 7812
> > GEN6_RP_UP_THRESHOLD 6640
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 15000
> >
> > And these are what we have after this patch:
> > LOW_POWER
> > GEN6_RP_UP_EI 12500
> > GEN6_RP_UP_THRESHOLD 11875
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 21250
> > BETWEEN
> > GEN6_RP_UP_EI 10175
> > GEN6_RP_UP_THRESHOLD 9150
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 18750
> > HIGH_POWER
> > GEN6_RP_UP_EI 7825
> > GEN6_RP_UP_THRESHOLD 6650
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 15000
> >
> > Cc: stable@vger.kernel.org
> > Cc: Akash Goel <akash.goel@intel.com>
> > Cc: Chris Wilson <chris@chris-wilson.co.uk>
> > Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B
> > Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> > Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > ---
> > drivers/gpu/drm/i915/i915_reg.h | 9 ++++++++-
> > 1 file changed, 8 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> > index c21b71c86a6b..08f01f4470cd 100644
> > --- a/drivers/gpu/drm/i915/i915_reg.h
> > +++ b/drivers/gpu/drm/i915/i915_reg.h
> > @@ -2948,7 +2948,14 @@ enum skl_disp_power_wells {
> > #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
> > #define BXT_RP_STATE_CAP _MMIO(0x138170)
> >
> > -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7)
> > +/*
> > + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
> > + * 8300) freezing up around GPU hangs. Looks as if even
> > + * scheduling/timer interrupts start misbehaving if the RPS
> > + * EI/thresholds are "bad", leading to a very sluggish or even
> > + * frozen machine.
> > + */
> > +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25)
> > #define INTERVAL_1_33_US(us) (((us) * 3) >> 2)
> > #define INTERVAL_0_833_US(us) (((us) * 6) / 5)
> > #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
> > --
> > 2.7.4
> >
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
>
> --
> Intel Sweden AB Registered Office: Knarrarnasgatan 15, 164 40 Kista, Stockholm, Sweden Registration Number: 556189-6027
--
Ville Syrjälä
Intel OTC
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: ✗ Fi.CI.BAT: warning for drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-21 12:40 ` ✗ Fi.CI.BAT: warning for " Patchwork
@ 2016-04-22 17:18 ` Ville Syrjälä
2016-04-22 17:38 ` Chris Wilson
0 siblings, 1 reply; 10+ messages in thread
From: Ville Syrjälä @ 2016-04-22 17:18 UTC (permalink / raw)
To: intel-gfx
On Thu, Apr 21, 2016 at 12:40:24PM -0000, Patchwork wrote:
> == Series Details ==
>
> Series: drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
> URL : https://patchwork.freedesktop.org/series/5987/
> State : warning
>
> == Summary ==
>
> Series 5987v1 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
> http://patchwork.freedesktop.org/api/1.0/series/5987/revisions/1/mbox/
>
> Test gem_busy:
> Subgroup basic-blt:
> pass -> SKIP (bsw-nuc-2)
Someone really should to fix this test to be stable...
> Test kms_flip:
> Subgroup basic-flip-vs-wf_vblank:
> fail -> PASS (bsw-nuc-2)
>
> bdw-nuci7 total:194 pass:182 dwarn:0 dfail:0 fail:0 skip:12
> bdw-ultra total:194 pass:170 dwarn:0 dfail:0 fail:1 skip:23
> bsw-nuc-2 total:193 pass:153 dwarn:0 dfail:0 fail:0 skip:40
> byt-nuc total:193 pass:155 dwarn:0 dfail:0 fail:0 skip:38
> hsw-brixbox total:194 pass:170 dwarn:0 dfail:0 fail:0 skip:24
> ilk-hp8440p total:194 pass:137 dwarn:0 dfail:0 fail:0 skip:57
> ivb-t430s total:194 pass:166 dwarn:0 dfail:0 fail:0 skip:28
> skl-i7k-2 total:194 pass:168 dwarn:0 dfail:0 fail:1 skip:25
> skl-nuci5 total:194 pass:183 dwarn:0 dfail:0 fail:0 skip:11
> snb-dellxps failed to connect after reboot
> snb-x220t failed to connect after reboot
>
> Results at /archive/results/CI_IGT_test/Patchwork_1960/
>
> eb848ab2b19d25a08ca3b2b5e4b2f74c7f7c962c drm-intel-nightly: 2016y-04m-20d-18h-48m-11s UTC integration manifest
> ca6a213 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
--
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-21 12:20 ` [Intel-gfx] [PATCH] " Patrik Jakobsson
2016-04-22 14:26 ` Ville Syrjälä
@ 2016-04-22 17:35 ` Ville Syrjälä
1 sibling, 0 replies; 10+ messages in thread
From: Ville Syrjälä @ 2016-04-22 17:35 UTC (permalink / raw)
To: intel-gfx, Akash Goel, stable
On Thu, Apr 21, 2016 at 02:20:35PM +0200, Patrik Jakobsson wrote:
> On Wed, Apr 20, 2016 at 04:43:56PM +0300, ville.syrjala@linux.intel.com wrote:
> > From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> >
> > Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
> > GPU hangs if the RPS EI/thresholds aren't suitably aligned.
> > It seems like scheduling/timer interupts stop working somehow
> > and things get stuck eg. in usleep_range().
> >
> > I bisected the problem down to
> > commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> > I observed that before all the values were at least multiples of 25,
> > but afterwards they are not. And rounding things up to the next multiple
> > of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
> > but that wasn't sufficient. Also I have no idea if we might need this sort of
> > thing on gen9+ as well.
>
> Do we need to test for performance regressions on stuff like this? And if so,
> who do we ping about this?
>
> OTOH impact should be really small and since this fixes a real problem:
>
> Reviewed-by: Patrik Jakobsson <patrik.jakobsson@linux.intel.com>
Pushed to dinq. Thanks for reviews/acks.
>
> >
> > These are the original EI/thresholds:
> > LOW_POWER
> > GEN6_RP_UP_EI 12500
> > GEN6_RP_UP_THRESHOLD 11800
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 21250
> > BETWEEN
> > GEN6_RP_UP_EI 10250
> > GEN6_RP_UP_THRESHOLD 9225
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 18750
> > HIGH_POWER
> > GEN6_RP_UP_EI 8000
> > GEN6_RP_UP_THRESHOLD 6800
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 15000
> >
> > These are after 8a5864377b12:
> > LOW_POWER
> > GEN6_RP_UP_EI 12500
> > GEN6_RP_UP_THRESHOLD 11875
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 21250
> > BETWEEN
> > GEN6_RP_UP_EI 10156
> > GEN6_RP_UP_THRESHOLD 9140
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 18750
> > HIGH_POWER
> > GEN6_RP_UP_EI 7812
> > GEN6_RP_UP_THRESHOLD 6640
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 15000
> >
> > And these are what we have after this patch:
> > LOW_POWER
> > GEN6_RP_UP_EI 12500
> > GEN6_RP_UP_THRESHOLD 11875
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 21250
> > BETWEEN
> > GEN6_RP_UP_EI 10175
> > GEN6_RP_UP_THRESHOLD 9150
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 18750
> > HIGH_POWER
> > GEN6_RP_UP_EI 7825
> > GEN6_RP_UP_THRESHOLD 6650
> > GEN6_RP_DOWN_EI 25000
> > GEN6_RP_DOWN_THRESHOLD 15000
> >
> > Cc: stable@vger.kernel.org
> > Cc: Akash Goel <akash.goel@intel.com>
> > Cc: Chris Wilson <chris@chris-wilson.co.uk>
> > Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B
> > Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
> > Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > ---
> > drivers/gpu/drm/i915/i915_reg.h | 9 ++++++++-
> > 1 file changed, 8 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> > index c21b71c86a6b..08f01f4470cd 100644
> > --- a/drivers/gpu/drm/i915/i915_reg.h
> > +++ b/drivers/gpu/drm/i915/i915_reg.h
> > @@ -2948,7 +2948,14 @@ enum skl_disp_power_wells {
> > #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
> > #define BXT_RP_STATE_CAP _MMIO(0x138170)
> >
> > -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7)
> > +/*
> > + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
> > + * 8300) freezing up around GPU hangs. Looks as if even
> > + * scheduling/timer interrupts start misbehaving if the RPS
> > + * EI/thresholds are "bad", leading to a very sluggish or even
> > + * frozen machine.
> > + */
> > +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25)
> > #define INTERVAL_1_33_US(us) (((us) * 3) >> 2)
> > #define INTERVAL_0_833_US(us) (((us) * 6) / 5)
> > #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
> > --
> > 2.7.4
> >
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
>
> --
> Intel Sweden AB Registered Office: Knarrarnasgatan 15, 164 40 Kista, Stockholm, Sweden Registration Number: 556189-6027
--
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: ✗ Fi.CI.BAT: warning for drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
2016-04-22 17:18 ` Ville Syrjälä
@ 2016-04-22 17:38 ` Chris Wilson
0 siblings, 0 replies; 10+ messages in thread
From: Chris Wilson @ 2016-04-22 17:38 UTC (permalink / raw)
To: Ville Syrjälä; +Cc: intel-gfx
On Fri, Apr 22, 2016 at 08:18:22PM +0300, Ville Syrjälä wrote:
> On Thu, Apr 21, 2016 at 12:40:24PM -0000, Patchwork wrote:
> > == Series Details ==
> >
> > Series: drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
> > URL : https://patchwork.freedesktop.org/series/5987/
> > State : warning
> >
> > == Summary ==
> >
> > Series 5987v1 drm/i915: Make RPS EI/thresholds multiple of 25 on SNB
> > http://patchwork.freedesktop.org/api/1.0/series/5987/revisions/1/mbox/
> >
> > Test gem_busy:
> > Subgroup basic-blt:
> > pass -> SKIP (bsw-nuc-2)
>
> Someone really should to fix this test to be stable...
It is on my list of intrigue.
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2016-04-22 17:38 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-04-20 13:43 [PATCH] drm/i915: Make RPS EI/thresholds multiple of 25 on SNB ville.syrjala
2016-04-20 13:57 ` Chris Wilson
2016-04-20 15:09 ` Ville Syrjälä
2016-04-21 6:54 ` ✓ Fi.CI.BAT: success for " Patchwork
2016-04-21 12:20 ` [Intel-gfx] [PATCH] " Patrik Jakobsson
2016-04-22 14:26 ` Ville Syrjälä
2016-04-22 17:35 ` Ville Syrjälä
2016-04-21 12:40 ` ✗ Fi.CI.BAT: warning for " Patchwork
2016-04-22 17:18 ` Ville Syrjälä
2016-04-22 17:38 ` Chris Wilson
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox