[Intel-gfx] [PATCH 2/3] drm/i915/perf: Whitelist OA counter and buffer registers

[Lionel Landwerlin]

On 17/07/2020 04:57, Umesh Nerlige Ramappa wrote:
> From: Piotr Maciejewski <piotr.maciejewski at intel.com>
>
> It is useful to have markers in the OA reports to identify triggered
> reports. Whitelist some OA counters that can be used as markers.
>
> A triggered report can be found faster if we can sample the HW tail and
> head registers when the report was triggered. Whitelist OA buffer
> specific registers.
>
> Signed-off-by: Piotr Maciejewski <piotr.maciejewski at intel.com>
> Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa at intel.com>
> ---
>   drivers/gpu/drm/i915/gt/intel_workarounds.c | 34 +++++++++++++++++++++
>   drivers/gpu/drm/i915/i915_reg.h             | 15 +++++++++
>   2 files changed, 49 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> index 582a2c8cd219..40a38023a05b 100644
> --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
> +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> @@ -1370,6 +1370,23 @@ static void gen9_whitelist_build_performance_counters(struct i915_wa_list *w)
>   	/* OA buffer trigger report 2/6 used by performance query */
>   	whitelist_reg(w, OAREPORTTRIG2);
>   	whitelist_reg(w, OAREPORTTRIG6);
> +
> +	/* Performance counters A18-20 used by tbs marker query */
> +	whitelist_reg_ext(w, OA_PERF_COUNTER_A18,
> +			  RING_FORCE_TO_NONPRIV_ACCESS_RW |
> +			  RING_FORCE_TO_NONPRIV_RANGE_4);
> +
> +	whitelist_reg(w, OA_PERF_COUNTER_A20);
> +	whitelist_reg(w, OA_PERF_COUNTER_A20_UPPER);
> +
> +	/* Read access to gpu ticks */
> +	whitelist_reg_ext(w, GEN8_GPU_TICKS,
> +			  RING_FORCE_TO_NONPRIV_ACCESS_RD);
> +
> +	/* Read access to: oa status, head, tail, buffer settings */
> +	whitelist_reg_ext(w, GEN8_OASTATUS,
> +			  RING_FORCE_TO_NONPRIV_ACCESS_RD |
> +			  RING_FORCE_TO_NONPRIV_RANGE_4);
>   }
>   
>   static void gen12_whitelist_build_performance_counters(struct i915_wa_list *w)
> @@ -1377,6 +1394,23 @@ static void gen12_whitelist_build_performance_counters(struct i915_wa_list *w)
>   	/* OA buffer trigger report 2/6 used by performance query */
>   	whitelist_reg(w, GEN12_OAG_OAREPORTTRIG2);
>   	whitelist_reg(w, GEN12_OAG_OAREPORTTRIG6);
> +
> +	/* Performance counters A18-20 used by tbs marker query */
> +	whitelist_reg_ext(w, GEN12_OAG_PERF_COUNTER_A18,
> +			  RING_FORCE_TO_NONPRIV_ACCESS_RW |
> +			  RING_FORCE_TO_NONPRIV_RANGE_4);
> +
> +	whitelist_reg(w, GEN12_OAG_PERF_COUNTER_A20);
> +	whitelist_reg(w, GEN12_OAG_PERF_COUNTER_A20_UPPER);
> +
> +	/* Read access to gpu ticks */
> +	whitelist_reg_ext(w, GEN12_OAG_GPU_TICKS,
> +			  RING_FORCE_TO_NONPRIV_ACCESS_RD);
> +
> +	/* Read access to: oa status, head, tail, buffer settings */
> +	whitelist_reg_ext(w, GEN12_OAG_OASTATUS,
> +			  RING_FORCE_TO_NONPRIV_ACCESS_RD |
> +			  RING_FORCE_TO_NONPRIV_RANGE_4);
>   }
>   
>   static void gen9_whitelist_build(struct i915_wa_list *w)
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index b9607ac3620d..33653aa0cfd3 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -675,6 +675,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
>   #define  GEN7_OASTATUS2_HEAD_MASK           0xffffffc0
>   #define  GEN7_OASTATUS2_MEM_SELECT_GGTT     (1 << 0) /* 0: PPGTT, 1: GGTT */
>   
> +#define GEN8_GPU_TICKS _MMIO(0x2910)
>   #define GEN8_OASTATUS _MMIO(0x2b08)
>   #define  GEN8_OASTATUS_OVERRUN_STATUS	    (1 << 3)
>   #define  GEN8_OASTATUS_COUNTER_OVERFLOW     (1 << 2)
> @@ -731,6 +732,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
>   #define  GEN12_OAG_OA_DEBUG_DISABLE_GO_1_0_REPORTS     (1 << 2)
>   #define  GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS (1 << 1)
>   
> +#define GEN12_OAG_GPU_TICKS _MMIO(0xda90)
>   #define GEN12_OAG_OASTATUS _MMIO(0xdafc)
>   #define  GEN12_OAG_OASTATUS_COUNTER_OVERFLOW (1 << 2)
>   #define  GEN12_OAG_OASTATUS_BUFFER_OVERFLOW  (1 << 1)
> @@ -972,6 +974,19 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
>   #define OAREPORTTRIG8_NOA_SELECT_6_SHIFT    24
>   #define OAREPORTTRIG8_NOA_SELECT_7_SHIFT    28
>   
> +/* Performance counters registers */
> +#define OA_PERF_COUNTER_A18       _MMIO(0x2890)
> +#define OA_PERF_COUNTER_A19       _MMIO(0x2898)
> +#define OA_PERF_COUNTER_A20       _MMIO(0x28A0)
> +#define OA_PERF_COUNTER_A20_UPPER _MMIO(0x28A4)

#define OA_PERF_COUNTER_A(idx) _MMIO(0x2800 + 8 * (idx))

> +
> +/* Gen12 Performance counters registers */
> +#define GEN12_OAG_PERF_COUNTER_A16       _MMIO(0xDA00)
> +#define GEN12_OAG_PERF_COUNTER_A18       _MMIO(0xDA10)
> +#define GEN12_OAG_PERF_COUNTER_A19       _MMIO(0xDA18)
> +#define GEN12_OAG_PERF_COUNTER_A20       _MMIO(0xDA20)
> +#define GEN12_OAG_PERF_COUNTER_A20_UPPER _MMIO(0xDA24)
#define GEN12_OA_PERF_COUNTER_A(idx) _MMIO(0xD980 + 8 * (idx)
> +
>   /* Same layout as OASTARTTRIGX */
>   #define GEN12_OAG_OASTARTTRIG1 _MMIO(0xd900)
>   #define GEN12_OAG_OASTARTTRIG2 _MMIO(0xd904)

I think this deserves its own i915-perf revision bump.


Thanks,


-Lionel