drm/i915: Separate workaround list init from context initwa_init

We build the workarounds when we setup the rings.
We apply the workarounds when we initialize the ring context.

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>

3 files changed, 110 insertions, 109 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 564ae1f08291..d81476d522b6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2649,25 +2649,25 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-
+	u32 count;
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
 
 	intel_runtime_pm_get(dev_priv);
 
-	seq_printf(m, "Workarounds applied: %d\n", dev_priv->num_wa_regs);
-	for (i = 0; i < dev_priv->num_wa_regs; ++i) {
-		u32 addr, mask;
-
-		addr = dev_priv->intel_wa_regs[i].addr;
-		mask = dev_priv->intel_wa_regs[i].mask;
-		dev_priv->intel_wa_regs[i].value = I915_READ(addr) | mask;
-		if (dev_priv->intel_wa_regs[i].addr)
-			seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X\n",
-				   dev_priv->intel_wa_regs[i].addr,
-				   dev_priv->intel_wa_regs[i].value,
-				   dev_priv->intel_wa_regs[i].mask);
+	count = dev_priv->workarounds.count;
+
+	seq_printf(m, "Workarounds applied: %d\n", count);
+
+	for (i = 0; i < count; ++i) {
+		u32 addr, mask, value;
+
+		addr = dev_priv->workarounds.reg[i].addr;
+		mask = dev_priv->workarounds.reg[i].mask;
+		value = dev_priv->workarounds.reg[i].value;
+		seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X\n",
+			   addr, value, mask);
 	}
 
 	intel_runtime_pm_put(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d92f38507cd4..6796713e9e71 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1445,6 +1445,20 @@ struct i915_frontbuffer_tracking {
 	unsigned flip_bits;
 };
 
+struct i915_wa_reg {
+	u32 addr;
+	u32 value;
+	/* bitmask representing WA bits */
+	u32 mask;
+};
+
+#define I915_MAX_WA_REGS 16
+
+struct i915_workarounds {
+	struct i915_wa_reg reg[I915_MAX_WA_REGS];
+	u32 count;
+};
+
 struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -1587,19 +1601,7 @@ struct drm_i915_private {
 	struct intel_shared_dpll shared_dplls[I915_NUM_PLLS];
 	int dpio_phy_iosf_port[I915_NUM_PHYS_VLV];
 
-	/*
-	 * workarounds are currently applied at different places and
-	 * changes are being done to consolidate them so exact count is
-	 * not clear at this point, use a max value for now.
-	 */
-#define I915_MAX_WA_REGS  16
-	struct {
-		u32 addr;
-		u32 value;
-		/* bitmask representing WA bits */
-		u32 mask;
-	} intel_wa_regs[I915_MAX_WA_REGS];
-	u32 num_wa_regs;
+	struct i915_workarounds workarounds;
 
 	/* Reclocking support */
 	bool render_reclock_avail;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 25795f2efdcb..2f630c39f21f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -665,87 +665,90 @@ err:
 	return ret;
 }
 
-static inline void intel_ring_emit_wa(struct intel_engine_cs *ring,
-				       u32 addr, u32 value)
+static int wa_add(struct drm_i915_private *dev_priv,
+		  const u32 addr, const u32 val, const u32 mask)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	const u32 idx = dev_priv->workarounds.count;
 
-	if (WARN_ON(dev_priv->num_wa_regs >= I915_MAX_WA_REGS))
-		return;
+	if (WARN_ON(idx >= I915_MAX_WA_REGS))
+		return -ENOSPC;
 
-	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, addr);
-	intel_ring_emit(ring, value);
+	dev_priv->workarounds.reg[idx].addr = addr;
+	dev_priv->workarounds.reg[idx].value = val;
+	dev_priv->workarounds.reg[idx].mask = mask;
 
-	dev_priv->intel_wa_regs[dev_priv->num_wa_regs].addr = addr;
-	dev_priv->intel_wa_regs[dev_priv->num_wa_regs].mask = value & 0xFFFF;
-	/* value is updated with the status of remaining bits of this
-	 * register when it is read from debugfs file
-	 */
-	dev_priv->intel_wa_regs[dev_priv->num_wa_regs].value = value;
-	dev_priv->num_wa_regs++;
+	dev_priv->workarounds.count++;
 
-	return;
+	return 0;
 }
 
-static int bdw_init_workarounds(struct intel_engine_cs *ring)
+#define WA_REG_ME(addr, val) { \
+		const int r = wa_add(dev_priv, (addr), \
+				     _MASKED_BIT_ENABLE(val), (val) & 0xffff); \
+		if (r) return r; }
+
+static int intel_ring_workarounds_emit(struct intel_engine_cs *ring)
 {
-	int ret;
+	int ret, i;
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_workarounds *w = &dev_priv->workarounds;
 
-	/*
-	 * workarounds applied in this fn are part of register state context,
-	 * they need to be re-initialized followed by gpu reset, suspend/resume,
-	 * module reload.
-	 */
-	dev_priv->num_wa_regs = 0;
-	memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
-
-	/*
-	 * update the number of dwords required based on the
-	 * actual number of workarounds applied
-	 */
-	ret = intel_ring_begin(ring, 24);
+	ret = intel_ring_begin(ring, w->count * 3);
 	if (ret)
 		return ret;
 
+	for (i = 0; i < w->count; i++) {
+		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit(ring, w->reg[i].addr);
+		intel_ring_emit(ring, w->reg[i].value);
+	}
+
+	intel_ring_advance(ring);
+
+	DRM_DEBUG_DRIVER("Number of Workarounds applied: %d\n", w->count);
+
+	return 0;
+}
+
+static int bdw_init_workarounds(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
 	/* WaDisablePartialInstShootdown:bdw */
 	/* WaDisableThreadStallDopClockGating:bdw */
-	/* FIXME: Unclear whether we really need this on production bdw. */
-	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
-			   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE
-					     | STALL_DOP_GATING_DISABLE));
+	WA_REG_ME(GEN8_ROW_CHICKEN,
+		  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
+		  STALL_DOP_GATING_DISABLE);
 
 	/* WaDisableDopClockGating:bdw May not be needed for production */
-	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
-			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+	WA_REG_ME(GEN7_ROW_CHICKEN2,
+		  DOP_CLOCK_GATING_DISABLE);
 
 	/*
 	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
 	 * pre-production hardware
 	 */
-	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
-			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
-					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
+	WA_REG_ME(HALF_SLICE_CHICKEN3,
+		  GEN8_CENTROID_PIXEL_OPT_DIS | GEN8_SAMPLER_POWER_BYPASS_DIS);
 
-	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
+	WA_REG_ME(GEN7_HALF_SLICE_CHICKEN1,
+		  GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE);
 
-	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
-			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
+	WA_REG_ME(COMMON_SLICE_CHICKEN2,
+		  GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE);
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for for a possible hang in the unlikely event a TLB
 	 * invalidation occurs during a PSD flush.
 	 */
-	intel_ring_emit_wa(ring, HDC_CHICKEN0,
-			   _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
+	WA_REG_ME(HDC_CHICKEN0,
+		  HDC_FORCE_NON_COHERENT);
 
 	/* Wa4x4STCOptimizationDisable:bdw */
-	intel_ring_emit_wa(ring, CACHE_MODE_1,
-			   _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+	WA_REG_ME(CACHE_MODE_1,
+		  GEN8_4x4_STC_OPTIMIZATION_DISABLE);
 
 	/*
 	 * BSpec recommends 8x4 when MSAA is used,
@@ -755,52 +758,50 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 * disable bit, which we don't touch here, but it's good
 	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
 	 */
-	intel_ring_emit_wa(ring, GEN7_GT_MODE,
-			   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
-
-	intel_ring_advance(ring);
-
-	DRM_DEBUG_DRIVER("Number of Workarounds applied: %d\n",
-			 dev_priv->num_wa_regs);
+	WA_REG_ME(GEN7_GT_MODE,
+		  GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
 
 	return 0;
 }
 
 static int chv_init_workarounds(struct intel_engine_cs *ring)
 {
-	int ret;
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	/*
-	 * workarounds applied in this fn are part of register state context,
-	 * they need to be re-initialized followed by gpu reset, suspend/resume,
-	 * module reload.
-	 */
-	dev_priv->num_wa_regs = 0;
-	memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
-
-	ret = intel_ring_begin(ring, 12);
-	if (ret)
-		return ret;
-
 	/* WaDisablePartialInstShootdown:chv */
-	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
-			   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
+	WA_REG_ME(GEN8_ROW_CHICKEN,
+		  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
 
 	/* WaDisableThreadStallDopClockGating:chv */
-	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
-			   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+	WA_REG_ME(GEN8_ROW_CHICKEN,
+		  STALL_DOP_GATING_DISABLE);
 
 	/* WaDisableDopClockGating:chv (pre-production hw) */
-	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
-			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+	WA_REG_ME(GEN7_ROW_CHICKEN2,
+		  DOP_CLOCK_GATING_DISABLE);
 
 	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
-	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
-			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+	WA_REG_ME(HALF_SLICE_CHICKEN3,
+		  GEN8_SAMPLER_POWER_BYPASS_DIS);
 
-	intel_ring_advance(ring);
+	return 0;
+}
+
+static int init_ring_workarounds(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	WARN_ON(ring->id != RCS);
+
+	dev_priv->workarounds.count = 0;
+
+	if (IS_BROADWELL(dev))
+		return bdw_init_workarounds(ring);
+
+	if (IS_CHERRYVIEW(dev))
+		return chv_init_workarounds(ring);
 
 	return 0;
 }
@@ -860,7 +861,7 @@ static int init_render_ring(struct intel_engine_cs *ring)
 	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
-	return ret;
+	return init_ring_workarounds(ring);
 }
 
 static void render_ring_cleanup(struct intel_engine_cs *ring)
@@ -2304,10 +2305,8 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 					dev_priv->semaphore_obj = obj;
 			}
 		}
-		if (IS_CHERRYVIEW(dev))
-			ring->init_context = chv_init_workarounds;
-		else
-			ring->init_context = bdw_init_workarounds;
+
+		ring->init_context = intel_ring_workarounds_emit;
 		ring->add_request = gen6_add_request;
 		ring->flush = gen8_render_ring_flush;
 		ring->irq_get = gen8_ring_get_irq;