drm/i915: Request full SSEU enablement on Gen9

On Gen9 the render power gating can leave slice/subslice/EU in
a partially enabled state. We must make an explicit request for
full SSEU enablement through the Render Power Clock State
register when resuming render work. This register is save/
restored in the logical ring context image for execlist
submission mode. Initialize its value in each LRC image to
request full enablement according to the device SSEU config.

Thanks to Sharma Ankitprasad and Akash Goel for highlighting the
issue and proposing the initial fix on which this patch is based.

v2: Adjusted the names of the power gating support flags to fit
    update of an earlier patch.
Signed-off-by: Jeff McGee <jeff.mcgee@intel.com>
Reviewed-by: "Akash Goel <akash.goel@intel.com>"
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -139,6 +139,19 @@
 #define GEN8_RING_PDP_UDW(ring, n)	((ring)->mmio_base+0x270 + ((n) * 8 + 4))
 #define GEN8_RING_PDP_LDW(ring, n)	((ring)->mmio_base+0x270 + (n) * 8)
 
+#define GEN8_R_PWR_CLK_STATE		0x20C8
+#define   GEN8_RPCS_ENABLE		(1 << 31)
+#define   GEN8_RPCS_S_CNT_ENABLE	(1 << 18)
+#define   GEN8_RPCS_S_CNT_SHIFT		15
+#define   GEN8_RPCS_S_CNT_MASK		(0x7 << GEN8_RPCS_S_CNT_SHIFT)
+#define   GEN8_RPCS_SS_CNT_ENABLE	(1 << 11)
+#define   GEN8_RPCS_SS_CNT_SHIFT	8
+#define   GEN8_RPCS_SS_CNT_MASK		(0x7 << GEN8_RPCS_SS_CNT_SHIFT)
+#define   GEN8_RPCS_EU_MAX_SHIFT	4
+#define   GEN8_RPCS_EU_MAX_MASK		(0xf << GEN8_RPCS_EU_MAX_SHIFT)
+#define   GEN8_RPCS_EU_MIN_SHIFT	0
+#define   GEN8_RPCS_EU_MIN_MASK		(0xf << GEN8_RPCS_EU_MIN_SHIFT)
+
 #define GAM_ECOCHK			0x4090
 #define   BDW_DISABLE_HDC_INVALIDATION	(1<<25)
 #define   ECOCHK_SNB_BIT		(1<<10)

drivers/gpu/drm/i915/intel_lrc.c

@@ -1636,6 +1636,49 @@ int intel_logical_rings_init(struct drm_device *dev)
 	return ret;
 }
 
+static u32
+make_rpcs(struct drm_device *dev)
+{
+	u32 rpcs = 0;
+
+	/*
+	 * No explicit RPCS request is needed to ensure full
+	 * slice/subslice/EU enablement prior to Gen9.
+	*/
+	if (INTEL_INFO(dev)->gen < 9)
+		return 0;
+
+	/*
+	 * Starting in Gen9, render power gating can leave
+	 * slice/subslice/EU in a partially enabled state. We
+	 * must make an explicit request through RPCS for full
+	 * enablement.
+	*/
+	if (INTEL_INFO(dev)->has_slice_pg) {
+		rpcs |= GEN8_RPCS_S_CNT_ENABLE;
+		rpcs |= INTEL_INFO(dev)->slice_total <<
+			GEN8_RPCS_S_CNT_SHIFT;
+		rpcs |= GEN8_RPCS_ENABLE;
+	}
+
+	if (INTEL_INFO(dev)->has_subslice_pg) {
+		rpcs |= GEN8_RPCS_SS_CNT_ENABLE;
+		rpcs |= INTEL_INFO(dev)->subslice_per_slice <<
+			GEN8_RPCS_SS_CNT_SHIFT;
+		rpcs |= GEN8_RPCS_ENABLE;
+	}
+
+	if (INTEL_INFO(dev)->has_eu_pg) {
+		rpcs |= INTEL_INFO(dev)->eu_per_subslice <<
+			GEN8_RPCS_EU_MIN_SHIFT;
+		rpcs |= INTEL_INFO(dev)->eu_per_subslice <<
+			GEN8_RPCS_EU_MAX_SHIFT;
+		rpcs |= GEN8_RPCS_ENABLE;
+	}
+
+	return rpcs;
+}
+
 static int
 populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_obj,
 		    struct intel_engine_cs *ring, struct intel_ringbuffer *ringbuf)
@@ -1739,8 +1782,8 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
 	reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[0]);
 	if (ring->id == RCS) {
 		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
-		reg_state[CTX_R_PWR_CLK_STATE] = 0x20c8;
-		reg_state[CTX_R_PWR_CLK_STATE+1] = 0;
+		reg_state[CTX_R_PWR_CLK_STATE] = GEN8_R_PWR_CLK_STATE;
+		reg_state[CTX_R_PWR_CLK_STATE+1] = make_rpcs(dev);
 	}
 
 	kunmap_atomic(reg_state);