[Intel-gfx] [PATCH v16 03/17] drm/i915: Record both min/max eu_per_subslice in sseu_dev_info
Lionel Landwerlin
lionel.g.landwerlin at intel.com
Mon Jun 5 14:48:44 UTC 2017
From: Chris Wilson <chris at chris-wilson.co.uk>
When we query the available eu on each subslice, we currently only
report the max. It would also be useful to report the minimum found as
well.
When we set RPCS (power gating over the EU), we can also specify both
the min and max number of eu to configure on each slice; currently we
just set it to a single value, but the flexibility may be beneficial in
future.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
drivers/gpu/drm/i915/i915_debugfs.c | 36 +++++++++++++++++++++++---------
drivers/gpu/drm/i915/i915_drv.h | 3 ++-
drivers/gpu/drm/i915/intel_device_info.c | 32 +++++++++++++++++-----------
drivers/gpu/drm/i915/intel_lrc.c | 4 ++--
4 files changed, 50 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3b088685a553..9bdf2bd59fbb 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4497,6 +4497,7 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_cache_sharing_fops,
static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
struct sseu_dev_info *sseu)
{
+ unsigned int min_eu_per_subslice, max_eu_per_subslice;
int ss_max = 2;
int ss;
u32 sig1[ss_max], sig2[ss_max];
@@ -4506,6 +4507,9 @@ static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
sig2[0] = I915_READ(CHV_POWER_SS0_SIG2);
sig2[1] = I915_READ(CHV_POWER_SS1_SIG2);
+ min_eu_per_subslice = ~0u;
+ max_eu_per_subslice = 0;
+
for (ss = 0; ss < ss_max; ss++) {
unsigned int eu_cnt;
@@ -4520,14 +4524,18 @@ static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
((sig1[ss] & CHV_EU210_PG_ENABLE) ? 0 : 2) +
((sig2[ss] & CHV_EU311_PG_ENABLE) ? 0 : 2);
sseu->eu_total += eu_cnt;
- sseu->eu_per_subslice = max_t(unsigned int,
- sseu->eu_per_subslice, eu_cnt);
+ min_eu_per_subslice = min(min_eu_per_subslice, eu_cnt);
+ max_eu_per_subslice = max(max_eu_per_subslice, eu_cnt);
}
+
+ sseu->min_eu_per_subslice = min_eu_per_subslice;
+ sseu->max_eu_per_subslice = max_eu_per_subslice;
}
static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
struct sseu_dev_info *sseu)
{
+ unsigned int min_eu_per_subslice, max_eu_per_subslice;
int s_max = 3, ss_max = 4;
int s, ss;
u32 s_reg[s_max], eu_reg[2*s_max], eu_mask[2];
@@ -4553,6 +4561,9 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
GEN9_PGCTL_SSB_EU210_ACK |
GEN9_PGCTL_SSB_EU311_ACK;
+ min_eu_per_subslice = ~0u;
+ max_eu_per_subslice = 0;
+
for (s = 0; s < s_max; s++) {
if ((s_reg[s] & GEN9_PGCTL_SLICE_ACK) == 0)
/* skip disabled slice */
@@ -4578,11 +4589,14 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
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);
+
+ min_eu_per_subslice = min(min_eu_per_subslice, eu_cnt);
+ max_eu_per_subslice = max(max_eu_per_subslice, eu_cnt);
}
}
+
+ sseu->min_eu_per_subslice = min_eu_per_subslice;
+ sseu->max_eu_per_subslice = max_eu_per_subslice;
}
static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
@@ -4595,9 +4609,11 @@ static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
if (sseu->slice_mask) {
sseu->subslice_mask = INTEL_INFO(dev_priv)->sseu.subslice_mask;
- sseu->eu_per_subslice =
- INTEL_INFO(dev_priv)->sseu.eu_per_subslice;
- sseu->eu_total = sseu->eu_per_subslice *
+ sseu->min_eu_per_subslice =
+ INTEL_INFO(dev_priv)->sseu.min_eu_per_subslice;
+ sseu->max_eu_per_subslice =
+ INTEL_INFO(dev_priv)->sseu.max_eu_per_subslice;
+ sseu->eu_total = sseu->max_eu_per_subslice *
sseu_subslice_total(sseu);
/* subtract fused off EU(s) from enabled slice(s) */
@@ -4628,8 +4644,8 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
hweight8(sseu->subslice_mask));
seq_printf(m, " %s EU Total: %u\n", type,
sseu->eu_total);
- seq_printf(m, " %s EU Per Subslice: %u\n", type,
- sseu->eu_per_subslice);
+ seq_printf(m, " %s EU Per Subslice: [%u, %u]\n", type,
+ sseu->min_eu_per_subslice, sseu->max_eu_per_subslice);
if (!is_available_info)
return;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c31c0cfe5c20..753c5698885a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -784,7 +784,8 @@ struct sseu_dev_info {
u8 slice_mask;
u8 subslice_mask;
u8 eu_total;
- u8 eu_per_subslice;
+ u8 min_eu_per_subslice;
+ u8 max_eu_per_subslice;
u8 min_eu_in_pool;
/* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */
u8 subslice_7eu[3];
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 3718341662c2..f21f597c5cb9 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -83,6 +83,7 @@ void intel_device_info_dump(struct drm_i915_private *dev_priv)
static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
{
struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
+ unsigned int eu_per_subslice;
u32 fuse, eu_dis;
fuse = I915_READ(CHV_FUSE_GT);
@@ -107,9 +108,10 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
* CHV expected to always have a uniform distribution of EU
* across subslices.
*/
- sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
- sseu->eu_total / sseu_subslice_total(sseu) :
- 0;
+ eu_per_subslice = sseu_subslice_total(sseu) ?
+ sseu->eu_total / sseu_subslice_total(sseu) : 0;
+ sseu->min_eu_per_subslice = eu_per_subslice;
+ sseu->max_eu_per_subslice = eu_per_subslice;
/*
* CHV supports subslice power gating on devices with more than
* one subslice, and supports EU power gating on devices with
@@ -117,13 +119,14 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
*/
sseu->has_slice_pg = 0;
sseu->has_subslice_pg = sseu_subslice_total(sseu) > 1;
- sseu->has_eu_pg = (sseu->eu_per_subslice > 2);
+ sseu->has_eu_pg = eu_per_subslice > 2;
}
static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
{
struct intel_device_info *info = mkwrite_device_info(dev_priv);
struct sseu_dev_info *sseu = &info->sseu;
+ unsigned int eu_per_subslice;
int s_max = 3, ss_max = 4, eu_max = 8;
int s, ss;
u32 fuse2, eu_disable;
@@ -179,9 +182,10 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
* recovery. BXT is expected to be perfectly uniform in EU
* distribution.
*/
- sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
- DIV_ROUND_UP(sseu->eu_total,
- sseu_subslice_total(sseu)) : 0;
+ eu_per_subslice = sseu_subslice_total(sseu) ?
+ DIV_ROUND_UP(sseu->eu_total, sseu_subslice_total(sseu)) : 0;
+ sseu->min_eu_per_subslice = eu_per_subslice;
+ sseu->max_eu_per_subslice = eu_per_subslice;
/*
* SKL supports slice power gating on devices with more than
* one slice, and supports EU power gating on devices with
@@ -195,7 +199,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
hweight8(sseu->slice_mask) > 1;
sseu->has_subslice_pg =
IS_GEN9_LP(dev_priv) && sseu_subslice_total(sseu) > 1;
- sseu->has_eu_pg = sseu->eu_per_subslice > 2;
+ sseu->has_eu_pg = eu_per_subslice > 2;
if (IS_GEN9_LP(dev_priv)) {
#define IS_SS_DISABLED(ss) (!(sseu->subslice_mask & BIT(ss)))
@@ -228,6 +232,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
{
struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
const int s_max = 3, ss_max = 3, eu_max = 8;
+ unsigned int eu_per_subslice;
int s, ss;
u32 fuse2, eu_disable[3]; /* s_max */
@@ -282,9 +287,10 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
* subslices with the exception that any one EU in any one subslice may
* be fused off for die recovery.
*/
- sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
- DIV_ROUND_UP(sseu->eu_total,
- sseu_subslice_total(sseu)) : 0;
+ eu_per_subslice = sseu_subslice_total(sseu) ?
+ DIV_ROUND_UP(sseu->eu_total, sseu_subslice_total(sseu)) : 0;
+ sseu->min_eu_per_subslice = eu_per_subslice;
+ sseu->max_eu_per_subslice = eu_per_subslice;
/*
* BDW supports slice power gating on devices with more than
@@ -421,7 +427,9 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
DRM_DEBUG_DRIVER("subslice per slice: %u\n",
hweight8(info->sseu.subslice_mask));
DRM_DEBUG_DRIVER("EU total: %u\n", info->sseu.eu_total);
- DRM_DEBUG_DRIVER("EU per subslice: %u\n", info->sseu.eu_per_subslice);
+ DRM_DEBUG_DRIVER("EU per subslice: [%u, %u]\n",
+ info->sseu.min_eu_per_subslice,
+ info->sseu.max_eu_per_subslice);
DRM_DEBUG_DRIVER("has slice power gating: %s\n",
info->sseu.has_slice_pg ? "y" : "n");
DRM_DEBUG_DRIVER("has subslice power gating: %s\n",
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 014b30ace8a0..9a279a559a0f 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1843,9 +1843,9 @@ make_rpcs(struct drm_i915_private *dev_priv)
}
if (INTEL_INFO(dev_priv)->sseu.has_eu_pg) {
- rpcs |= INTEL_INFO(dev_priv)->sseu.eu_per_subslice <<
+ rpcs |= INTEL_INFO(dev_priv)->sseu.min_eu_per_subslice <<
GEN8_RPCS_EU_MIN_SHIFT;
- rpcs |= INTEL_INFO(dev_priv)->sseu.eu_per_subslice <<
+ rpcs |= INTEL_INFO(dev_priv)->sseu.max_eu_per_subslice <<
GEN8_RPCS_EU_MAX_SHIFT;
rpcs |= GEN8_RPCS_ENABLE;
}
--
2.11.0
More information about the Intel-gfx
mailing list