[Intel-gfx] [PATCH] drm/i915/cnl: Fix SSEU Device Status.

[Oscar Mateo]

On 09/22/2017 06:15 AM, Rodrigo Vivi wrote:
> CNL adds an extra register for slice/subslice information.
> Although no SKU is planed with an extra slice let's already
> handle this extra piece of information so we don't have the
> risk in future of getting a part that might have chosen this
> part of the die instead of other slices or anything like that.
>
> Also if subslice is disabled the information of eu ack for that
> is garbage, so let's skip checks for eu if subslice is disabled
> as we skip the subslice if slice is disabled.
>
> The rest is pretty much like gen9.
>
> v2: Remove IS_CANNONLAKE from gen9 status function.
>
> v3: Consider s_max = 6 and ss_max=4 to run over all possible
>      slices and subslices possible by spec. Although no real
>      hardware will have that many slices/subslices.
>      To match with sseu info init.
> v4: Fix offset calculation for slices 4 and 5.
>      Removed Oscar's rv-b since this change also needs review.
>
> Cc: Oscar Mateo <oscar.mateo at intel.com>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>   drivers/gpu/drm/i915/i915_debugfs.c | 54 +++++++++++++++++++++++++++++++++++--
>   drivers/gpu/drm/i915/i915_reg.h     |  6 +++++
>   2 files changed, 58 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index ca6fa6d122c6..e197e5d99277 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -4575,6 +4575,54 @@ static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
>   	}
>   }
>   
> +static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
> +				     struct sseu_dev_info *sseu)
> +{
> +	const struct intel_device_info *info = INTEL_INFO(dev_priv);
> +	int s_max = 6, ss_max = 4;
> +	int s, ss;
> +	u32 s_reg[s_max], eu_reg[2 * s_max], eu_mask[2];
> +
> +	for (s = 0; s < s_max; s++) {
> +		s_reg[s] = I915_READ(GEN10_SLICE_PGCTL_ACK(s));
> +		eu_reg[2 * s] = I915_READ(GEN10_SS01_EU_PGCTL_ACK(s));
> +		eu_reg[2 * s + 1] = I915_READ(GEN10_SS23_EU_PGCTL_ACK(s));
> +	}
> +
> +	eu_mask[0] = GEN9_PGCTL_SSA_EU08_ACK |
> +		     GEN9_PGCTL_SSA_EU19_ACK |
> +		     GEN9_PGCTL_SSA_EU210_ACK |
> +		     GEN9_PGCTL_SSA_EU311_ACK;
> +	eu_mask[1] = GEN9_PGCTL_SSB_EU08_ACK |
> +		     GEN9_PGCTL_SSB_EU19_ACK |
> +		     GEN9_PGCTL_SSB_EU210_ACK |
> +		     GEN9_PGCTL_SSB_EU311_ACK;
> +
> +	for (s = 0; s < s_max; s++) {
> +		if ((s_reg[s] & GEN9_PGCTL_SLICE_ACK) == 0)
> +			/* skip disabled slice */
> +			continue;
> +
> +		sseu->slice_mask |= BIT(s);
> +		sseu->subslice_mask = info->sseu.subslice_mask;
> +
> +		for (ss = 0; ss < ss_max; ss++) {
> +			unsigned int eu_cnt;
> +
> +			if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
> +				/* skip disabled subslice */
> +				continue;

You are going to hate me, but I found something else:

SLICE0_PGCTL_ACK has powergate acknowledge bits for subslices 0, 1 & 2, 
but not for subslice 3
SLICEn_PGCTL_ACK (where n = 1-5) has powergate acknowledge bits for 
subslices 0 & 1, but not for subslices 2 & 3

I have no idea where the missing bits went (maybe the BSpec is wrong?).

> +
> +			eu_cnt = 2 * hweight32(eu_reg[2 * s + ss / 2] &
> +					       eu_mask[ss % 2]);
> +			sseu->eu_total += eu_cnt;
> +			sseu->eu_per_subslice = max_t(unsigned int,
> +						      sseu->eu_per_subslice,
> +						      eu_cnt);
> +		}
> +	}
> +}
> +
>   static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
>   				    struct sseu_dev_info *sseu)
>   {
> @@ -4610,7 +4658,7 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
>   
>   		sseu->slice_mask |= BIT(s);
>   
> -		if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv))
> +		if (IS_GEN9_BC(dev_priv))
>   			sseu->subslice_mask =
>   				INTEL_INFO(dev_priv)->sseu.subslice_mask;
>   
> @@ -4716,8 +4764,10 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
>   		cherryview_sseu_device_status(dev_priv, &sseu);
>   	} else if (IS_BROADWELL(dev_priv)) {
>   		broadwell_sseu_device_status(dev_priv, &sseu);
> -	} else if (INTEL_GEN(dev_priv) >= 9) {
> +	} else if (IS_GEN9(dev_priv)) {
>   		gen9_sseu_device_status(dev_priv, &sseu);
> +	} else if (INTEL_GEN(dev_priv) >= 10) {
> +		gen10_sseu_device_status(dev_priv, &sseu);
>   	}
>   
>   	intel_runtime_pm_put(dev_priv);
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index 1c257797c583..9729145e6c03 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -8020,11 +8020,17 @@ enum {
>   #define   CHV_EU311_PG_ENABLE		(1<<1)
>   
>   #define GEN9_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + (slice)*0x4)
> +#define GEN10_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + ((slice) / 3) * 0x34 + \
> +					      ((slice) % 3) * 0x4)
>   #define   GEN9_PGCTL_SLICE_ACK		(1 << 0)
>   #define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice)*2))
>   
>   #define GEN9_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + (slice)*0x8)
> +#define GEN10_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + ((slice) / 3) * 0x30 + \
> +					      ((slice) % 3) * 0x8)
>   #define GEN9_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + (slice)*0x8)
> +#define GEN10_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + ((slice) / 3) * 0x30 + \
> +					      ((slice) % 3) * 0x8)
>   #define   GEN9_PGCTL_SSA_EU08_ACK	(1 << 0)
>   #define   GEN9_PGCTL_SSA_EU19_ACK	(1 << 2)
>   #define   GEN9_PGCTL_SSA_EU210_ACK	(1 << 4)