drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf
Subsystems (2)
PATCH v2 1/1 drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)
drivers/gpu/drm/i915/i915_reg.h +1 -0
@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8C
drivers/gpu/drm/i915/intel_pm.c +4 -0
@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device *dev)if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER ))I915_WRITE (GEN9_CLKGATE_DIS_0 ,I915_READ (GEN9_CLKGATE_DIS_0 ) |PWM1_GATING_DIS |PWM2_GATING_DIS ); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) +I915_WRITE (GEN8_L3SQCREG1 ,BXT_WA_L3SQCREG1_DEFAULT ); }static void i915_pineview_get_mem_freq (struct drm_device *dev)
Signature · 6 lines
1.9.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 31 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)drivers/gpu/drm/i915/i915_reg.h +1
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8Cdrivers/gpu/drm/i915/intel_pm.c +0
-0
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev) · line 85
Quoted 10 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device *dev)if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER ))I915_WRITE (GEN9_CLKGATE_DIS_0 ,I915_READ (GEN9_CLKGATE_DIS_0 ) |PWM1_GATING_DIS |PWM2_GATING_DIS ); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) +I915_WRITE (GEN8_L3SQCREG1 ,BXT_WA_L3SQCREG1_DEFAULT ); }static void i915_pineview_get_mem_freq (struct drm_device *dev)
Isnt it better to add this to bxt_init_workarounds() instead of bxt_init_clock_gating()?
And It doesnt hurt to put what it is doing in the commit msg, i.e.:
"Increasing GP credits to 62 (from default 56), and reducing HP credits to 2 (from default 8)"
-Michel
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJ
Quoted 49 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 18 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 7 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8Cdrivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device
Quoted 5 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device*dev)
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device · line 77
Quoted 2 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER )) I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev)
Quoted 5 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0PWM1_GATING_DIS | PWM2_GATING_DIS); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);
Quoted 7 lines
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev) · line 85
Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0}static void i915_pineview_get_mem_freq (struct drm_device *dev)Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?
There is an equivalent Wa for bdw in bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume. bxt_init_workarounds only gets called after reset, not on resume as far as I know. I'll investigate further
Quoted 4 lines
And It doesnt hurt to put what it is doing in the commit msg, i.e.:
"Increasing GP credits to 62 (from default 56), and reducing HP credits to 2 (from default 8)"
Fair comment
Quoted 2 lines
-Michel
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 59 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 54 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 18 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 7 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8Cdrivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device
Quoted 5 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device*dev)
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device · line 77
Quoted 2 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER )) I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev)
Quoted 5 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0PWM1_GATING_DIS | PWM2_GATING_DIS); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0}static void i915_pineview_get_mem_freq (struct drm_device *dev)
Quoted 7 lines
Quoted 2 lines
Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?There is an equivalent Wa for bdw in
bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume.bxt_init_workaroundsonly gets called after reset, not on resume as far as I know. I'll investigate further
init_clock_gating() is called on init/reset/resume. Use it to set global registers. (Once upon a time it did only setup the clock gatings...)
init_workarounds() is the equivalent for per-context registers. -Chris
Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 63 lines · Chris Wilson
Quoted 62 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 56 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 18 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 7 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8Cdrivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device
Quoted 5 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device*dev)
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device · line 77
Quoted 2 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER )) I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev)
Quoted 5 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0PWM1_GATING_DIS | PWM2_GATING_DIS); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev) · line 85
Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0}static void i915_pineview_get_mem_freq (struct drm_device *dev)Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?
Quoted 7 lines
Quoted 4 lines
There is an equivalent Wa for bdw in
bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume.bxt_init_workaroundsonly gets called after reset, not on resume as far as I know. I'll investigate further
init_clock_gating()is called oninit/reset/resume. Use it to set global registers. (Once upon a time it did only setup the clock gatings...)
It's not called on reset. Or at least that was the case last time I looked. Which is a rather big problem. My old idea was that we'd move anything that gets clobbered by a GPU reset out from init_clock_gating into some more suitable place that does get called on reset.
Signature · 6 lines
Ville Syrjälä Intel OTC _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 69 lines · Ville Syrjälä
Quoted 68 lines · Chris Wilson
Quoted 66 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 49 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 18 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 7 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8Cdrivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device
Quoted 5 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device*dev)
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device · line 77
Quoted 2 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER )) I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev)
Quoted 5 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0PWM1_GATING_DIS | PWM2_GATING_DIS); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);Quoted 7 lines
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev) · line 85
Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0}static void i915_pineview_get_mem_freq (struct drm_device *dev)Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?There is an equivalent Wa for bdw in
bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume.bxt_init_workaroundsonly gets called after reset, not on resume as far as I know. I'll investigate further
Quoted 7 lines
Quoted 2 lines
init_clock_gating()is called oninit/reset/resume. Use it to set global registers. (Once upon a time it did only setup the clock gatings...)It's not called on reset. Or at least that was the case last time I looked. Which is a rather big problem. My old idea was that we'd move anything that gets clobbered by a GPU reset out from
init_clock_gatinginto some more suitable place that does get called on reset.
Oh, I call upon Daniel!
-Chris
Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJ
Quoted 92 lines
-----Original Message-----
From: Chris Wilson [mailto:[email protected]]
Sent: Wednesday, April 20, 2016 7:48 PM
To: Ville Syrjälä
Cc: Gore, Tim; Daniel Vetter; Thierry, Michel; [email protected]
Subject: Re: [Intel-gfx] [PATCH v2] drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerfQuoted 29 lines · Ville Syrjälä
Quoted 28 lines · Chris Wilson
Quoted 27 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 21 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 13 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6075
Quoted 8 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h +0
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells {
Quoted 4 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 1 line
drivers/gpu/drm/i915/i915_reg.h +0
-0#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8CQuoted 7 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct
drm_device*dev)
Quoted 1 line
if (IS_BXT_REVID(dev_priv,
BXT_REVID_B0,
REVID_FOREVER))Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 1 line
I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|Quoted 1 line
PWM1_GATING_DIS|
PWM2_GATING_DIS);Quoted 24 lines
Quoted 23 lines
Quoted 11 lines
Quoted 11 lines
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev)
Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0+ +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);Quoted 5 lines
}static void i915_pineview_get_mem_freq(struct
drm_device
*dev)Quoted 8 lines
Quoted 2 lines
Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?There is an equivalent Wa for bdw in
bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume.bxt_init_workaroundsonly gets called after reset, not on resume as far as I know. I'll investigate further
init_clock_gating()is called oninit/reset/resume. Use it to set global registers. (Once upon a time it did only setup the clock gatings...)
Quoted 8 lines
Quoted 4 lines
It's not called on reset. Or at least that was the case last time I looked. Which is a rather big problem. My old idea was that we'd move anything that gets clobbered by a GPU reset out from
init_clock_gatinginto some more suitable place that does get called on reset.Oh, I call upon Daniel!
-Chris
Looks to me that init_clock_gating is called on reset thus:
I915_handle_error
-> i915_reset_and_wakeup
-> intel_finish_reset
-> intel_modeset_init_hw
-> intel_init_clock_gating
-> display.init_clock_gatingOr perhaps we should put WaProgramL3SqcReg1DefaultForPerf in the new gtt_write_workarounds function in i915_gem_gtt.c. I believe this is called on Init, reset and resume. ?
Tim
Quoted 1 line
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 114 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 92 lines
-----Original Message-----
From: Chris Wilson [mailto:[email protected]]
Sent: Wednesday, April 20, 2016 7:48 PM
To: Ville Syrjälä
Cc: Gore, Tim; Daniel Vetter; Thierry, Michel; [email protected]
Subject: Re: [Intel-gfx] [PATCH v2] drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerfQuoted 29 lines · Ville Syrjälä
Quoted 28 lines · Chris Wilson
Quoted 27 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 21 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 13 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6075
Quoted 8 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h +0
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6079
Quoted 4 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 1 line
drivers/gpu/drm/i915/i915_reg.h +0
-0#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8CQuoted 7 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct
drm_device*dev)
Quoted 1 line
if (IS_BXT_REVID(dev_priv,
BXT_REVID_B0,
REVID_FOREVER))Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 1 line
I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|Quoted 1 line
PWM1_GATING_DIS|
PWM2_GATING_DIS);Quoted 24 lines
Quoted 23 lines
Quoted 11 lines
Quoted 11 lines
drivers/gpu/drm/i915/intel_pm.c
Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0+ +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);Quoted 5 lines
}static void i915_pineview_get_mem_freq(struct
drm_device
*dev)Quoted 8 lines
Quoted 2 lines
Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?There is an equivalent Wa for bdw in
bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume.bxt_init_workaroundsonly gets called after reset, not on resume as far as I know. I'll investigate further
init_clock_gating()is called oninit/reset/resume. Use it to set global registers. (Once upon a time it did only setup the clock gatings...)Quoted 8 lines
Quoted 4 lines
It's not called on reset. Or at least that was the case last time I looked. Which is a rather big problem. My old idea was that we'd move anything that gets clobbered by a GPU reset out from
init_clock_gatinginto some more suitable place that does get called on reset.Oh, I call upon Daniel!
-ChrisLooks to me that
init_clock_gatingis called on reset thus:I915_handle_error -> i915_reset_and_wakeup -> intel_finish_reset -> intel_modeset_init_hw -> intel_init_clock_gating -> display.init_clock_gating
Quoted 3 lines
Or perhaps we should put WaProgramL3SqcReg1DefaultForPerf in the new
gtt_write_workaroundsfunction ini915_gem_gtt.c. I believe this is called on Init, reset and resume. ?
intel_modeset_init_hw should only be called on old crap where a gpu reset kills the entire chip, including the display block. That's not the case on modern stuff, much less once we have TDR.
If it's getting called unconditionally that's a bug. -Daniel
Signature · 7 lines
Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 73 lines · Chris Wilson
Quoted 72 lines · Ville Syrjälä
Quoted 70 lines · Chris Wilson
Quoted 59 lines · Tim
Tim Gore
Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJQuoted 54 lines
-----Original Message-----
From: Thierry, Michel
Sent: Wednesday, April 20, 2016 4:00 PM
To: Gore, Tim; [email protected]
Subject: Re: [PATCH v2] drm/i915:bxt: implement
WaProgramL3SqcReg1DefaultForPerfQuoted 18 lines · On 4/20/2016 3:23 PM, [email protected] wrote:
From: Tim Gore <[email protected]>
This patch applies a performance enhancement workaround based on analysis of DX and OCL S-Curve workloads.
v2: Only apply to B0 onwards
Signed-off-by Tim Gore <[email protected]>--- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 2 files changed, 5 insertions(+)(quoted diff) +0
-0
b/drivers/gpu/drm/i915/i915_reg.hindex f0a6d85..13e154a 100644drivers/gpu/drm/i915/i915_reg.h enum skl_disp_power_wells { · line 6080
Quoted 7 lines
drivers/gpu/drm/i915/i915_reg.h +1
-0@@ -6074,6 +6074,7 @@ enum skl_disp_power_wells {#define GEN8_L3SQCREG1 _MMIO(0xB100)#define BDW_WA_L3SQCREG1_DEFAULT 0x784000 +#define BXT_WA_L3SQCREG1_DEFAULT 0xF84000#define GEN7_L3CNTLREG1 _MMIO(0xB01C)#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8Cdrivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device
Quoted 5 lines
(quoted diff) +0
-0
b/drivers/gpu/drm/i915/intel_pm.cindex b7c2186..eecdc3a6 100644drivers/gpu/drm/i915/intel_pm.c +0
-0@@ -76,6 +76,10 @@ static void bxt_init_clock_gating(struct drm_device*dev)
drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device · line 77
Quoted 2 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0if (IS_BXT_REVID (dev_priv,BXT_REVID_B0 ,REVID_FOREVER )) I915_WRITE(GEN9_CLKGATE_DIS_0,
I915_READ(GEN9_CLKGATE_DIS_0)|drivers/gpu/drm/i915/intel_pm.c static void bxt_init_clock_gating(struct drm_device *dev)
Quoted 5 lines
drivers/gpu/drm/i915/intel_pm.c +4
-0PWM1_GATING_DIS | PWM2_GATING_DIS); + +/* WaProgramL3SqcReg1DefaultForPerf:bxt */ +if (IS_BXT_REVID (dev,BXT_REVID_B0 ,REVID_FOREVER )) + I915_WRITE(GEN8_L3SQCREG1,
BXT_WA_L3SQCREG1_DEFAULT);Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +0
-0}static void i915_pineview_get_mem_freq (struct drm_device *dev)Quoted 7 lines
Quoted 2 lines
Isnt it better to add this to
bxt_init_workarounds()instead ofbxt_init_clock_gating()?There is an equivalent Wa for bdw in
bdw_init_clock_gating, so I just tried to stay consistent with that. I'm not sure if this W/a will persist across suspend/resume.bxt_init_workaroundsonly gets called after reset, not on resume as far as I know. I'll investigate further
init_clock_gating()is called oninit/reset/resume. Use it to set global registers. (Once upon a time it did only setup the clock gatings...)
Quoted 6 lines
Quoted 4 lines
It's not called on reset. Or at least that was the case last time I looked. Which is a rather big problem. My old idea was that we'd move anything that gets clobbered by a GPU reset out from
init_clock_gatinginto some more suitable place that does get called on reset.Oh, I call upon Daniel!
We have that place already since ages. Either
- wa batch if it's in the context
- per-engine init function (most of those are for rcs)
init_clock_gating is for display/uncore wa only. I thought this is known by now?
-Daniel
Signature · 7 lines
Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI✗ Fi.CI.BAT: failure for drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf (rev2)
In reply to [email protected]== Series Details ==
== Series Details ==
Series: drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf (rev2)
URL : https://patchwork.freedesktop.org/series/5990/
State : failure
== Summary ==
Series 5990v2 drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf
http://patchwork.freedesktop.org/api/1.0/series/5990/revisions/2/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)
Test kms_force_connector_basic:
Subgroup force-load-detect:
pass -> SKIP (ivb-t430s)
Test kms_pipe_crc_basic:
Subgroup nonblocking-crc-pipe-a:
pass -> FAIL (ivb-t430s)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:164 dwarn:0 dfail:0 fail:1 skip:29 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
Results at /archive/results/CI_IGT_test/Patchwork_1961/
eb848ab2b19d25a08ca3b2b5e4b2f74c7f7c962c drm-intel-nightly: 2016y-04m-20d-18h-48m-11s UTC integration manifest d726e637 drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx