[Intel-gfx] [PATCH] drm/i915/skl: Tune IZ hashing when subslices are unbalanced

[Damien Lespiau]

When one EU is disabled in a particular subslice, we can tune how the
work is spread between subslices to improve EU utilization.

v2: - Use a bitfield to record which subslice(s) has(have) 7 EUs. That
      will also make the machinery work if several sublices have 7 EUs.
      (Jeff Mcgee)
    - Only apply the different hashing algorithm if the slice is
      effectively unbalanced by checking there's a single subslice with
      7 EUs. (Jeff Mcgee)

v3: Fix typo in comment (Jeff Mcgee)

Issue: VIZ-3845
Cc: Jeff Mcgee <jeff.mcgee at intel.com>
Reviewed-by: Jeff Mcgee <jeff.mcgee at intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau at intel.com>
---
 drivers/gpu/drm/i915/i915_dma.c         | 17 ++++++++++---
 drivers/gpu/drm/i915/i915_drv.h         |  2 ++
 drivers/gpu/drm/i915/i915_reg.h         |  2 ++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 45 ++++++++++++++++++++++++++++++++-
 4 files changed, 62 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 70acfe0..39164ff 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -649,13 +649,24 @@ static void intel_device_info_runtime_init(struct drm_device *dev)
 				continue;
 
 			for (ss = 0; ss < ss_max; ss++) {
+				u32 n_disabled;
+
 				if (ss_disable & (0x1 << ss))
 					/* skip disabled subslice */
 					continue;
 
-				info->eu_total += eu_max -
-						  hweight8(eu_disable[s] >>
-							   (ss * eu_max));
+				n_disabled = hweight8(eu_disable[s] >>
+						      (ss * eu_max));
+
+				/*
+				 * Record which subslice(s) has(have) 7 EUs. we
+				 * can tune the hash used to spread work among
+				 * subslices if they are unbalanced.
+				 */
+				if (eu_max - n_disabled == 7)
+					info->subslice_7eu[s] |= 1 << ss;
+
+				info->eu_total += eu_max - n_disabled;
 			}
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d910bac..5b4794b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -699,6 +699,8 @@ struct intel_device_info {
 	u8 subslice_per_slice;
 	u8 eu_total;
 	u8 eu_per_subslice;
+	/* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */
+	u8 subslice_7eu[3];
 	u8 has_slice_pg:1;
 	u8 has_subslice_pg:1;
 	u8 has_eu_pg:1;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 40f71bd..0aa6437 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1341,6 +1341,8 @@ enum skl_disp_power_wells {
 #define   GEN6_WIZ_HASHING_16x4				GEN6_WIZ_HASHING(1, 0)
 #define   GEN6_WIZ_HASHING_MASK				GEN6_WIZ_HASHING(1, 1)
 #define   GEN6_TD_FOUR_ROW_DISPATCH_DISABLE		(1 << 5)
+#define   GEN9_IZ_HASHING_MASK(slice)			(0x3 << (slice * 2))
+#define   GEN9_IZ_HASHING(slice, val)			((val) << (slice * 2))
 
 #define GFX_MODE	0x02520
 #define GFX_MODE_GEN7	0x0229c
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 443e19c..c24d856 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -937,6 +937,49 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	return 0;
 }
 
+static int skl_tune_iz_hashing(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u8 vals[3] = { 0, 0, 0 };
+	unsigned int i;
+
+	for (i = 0; i < 3; i++) {
+		u8 ss;
+
+		/*
+		 * Only consider slices where one, and only one, subslice has 7
+		 * EUs
+		 */
+		if (hweight8(dev_priv->info.subslice_7eu[i]) != 1)
+			continue;
+
+		/*
+		 * subslice_7eu[i] != 0 (because of the check above) and
+		 * ss_max == 4 (maximum number of subslices possible per slice)
+		 *
+		 * ->    0 <= ss <= 3;
+		 */
+		ss = ffs(dev_priv->info.subslice_7eu[i]) - 1;
+		vals[i] = 3 - ss;
+	}
+
+	if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0)
+		return 0;
+
+	/* Tune IZ hashing. See intel_device_info_runtime_init() */
+	WA_SET_FIELD_MASKED(GEN7_GT_MODE,
+			    GEN9_IZ_HASHING_MASK(2) |
+			    GEN9_IZ_HASHING_MASK(1) |
+			    GEN9_IZ_HASHING_MASK(0),
+			    GEN9_IZ_HASHING(2, vals[2]) |
+			    GEN9_IZ_HASHING(1, vals[1]) |
+			    GEN9_IZ_HASHING(0, vals[0]));
+
+	return 0;
+}
+
+
 static int skl_init_workarounds(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -956,7 +999,7 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 				  HDC_FENCE_DEST_SLM_DISABLE |
 				  HDC_BARRIER_PERFORMANCE_DISABLE);
 
-	return 0;
+	return skl_tune_iz_hashing(ring);
 }
 
 int init_workarounds_ring(struct intel_engine_cs *ring)
-- 
1.8.3.1