drm/i915: add multi-threaded forcewake support

On IVB C0+ with newer BIOSes, the forcewake handshake has changed.  There's
now a bitfield for different driver components to keep the GT powered
on.  On Linux, we centralize forcewake handling in one place, so we
still just need a single bit, but we need to use the new registers if MT
forcewake is enabled.

This needs testing on affected machines.  Please reply with your
tested-by if you had problems after a BIOS upgrade and this patch fixes
them.

v2: force MT mode. shift by 16
v3: set MT force wake bits then check ECOBUS

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=42923
Tested-by: Manoj Iyer <manoj.iyer@canonical.com>
Tested-by: Robert Hooker <robert.hooker@canonical.com>
Tested-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Keith Packard <keithp@keithp.com>

4 files changed, 66 insertions, 8 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 15bfa9145d2b..28836fe72211 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -328,7 +328,7 @@ void intel_detect_pch(struct drm_device *dev)
 	}
 }
 
-static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 {
 	int count;
 
@@ -344,6 +344,22 @@ static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 		udelay(10);
 }
 
+void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
+{
+	int count;
+
+	count = 0;
+	while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_MT_ACK) & 1))
+		udelay(10);
+
+	I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 1);
+	POSTING_READ(FORCEWAKE_MT);
+
+	count = 0;
+	while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_MT_ACK) & 1) == 0)
+		udelay(10);
+}
+
 /*
  * Generally this is called implicitly by the register read function. However,
  * if some sequence requires the GT to not power down then this function should
@@ -356,15 +372,21 @@ void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 
 	/* Forcewake is atomic in case we get in here without the lock */
 	if (atomic_add_return(1, &dev_priv->forcewake_count) == 1)
-		__gen6_gt_force_wake_get(dev_priv);
+		dev_priv->display.force_wake_get(dev_priv);
 }
 
-static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
 	POSTING_READ(FORCEWAKE);
 }
 
+void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 0);
+	POSTING_READ(FORCEWAKE_MT);
+}
+
 /*
  * see gen6_gt_force_wake_get()
  */
@@ -373,7 +395,7 @@ void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
 
 	if (atomic_dec_and_test(&dev_priv->forcewake_count))
-		__gen6_gt_force_wake_put(dev_priv);
+		dev_priv->display.force_wake_put(dev_priv);
 }
 
 void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
@@ -903,8 +925,9 @@ MODULE_LICENSE("GPL and additional rights");
 /* We give fast paths for the really cool registers */
 #define NEEDS_FORCE_WAKE(dev_priv, reg) \
 	(((dev_priv)->info->gen >= 6) && \
-	((reg) < 0x40000) && \
-	((reg) != FORCEWAKE))
+	 ((reg) < 0x40000) &&		 \
+	 ((reg) != FORCEWAKE) &&	 \
+	 ((reg) != ECOBUS))
 
 #define __i915_read(x, y) \
 u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a9c1b979804..8ba88cfc36de 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -107,6 +107,7 @@ struct opregion_header;
 struct opregion_acpi;
 struct opregion_swsci;
 struct opregion_asle;
+struct drm_i915_private;
 
 struct intel_opregion {
 	struct opregion_header *header;
@@ -221,6 +222,8 @@ struct drm_i915_display_funcs {
 			  struct drm_i915_gem_object *obj);
 	int (*update_plane)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 			    int x, int y);
+	void (*force_wake_get)(struct drm_i915_private *dev_priv);
+	void (*force_wake_put)(struct drm_i915_private *dev_priv);
 	/* clock updates for mode set */
 	/* cursor updates */
 	/* render clock increase/decrease */
@@ -1308,6 +1311,11 @@ extern void gen6_set_rps(struct drm_device *dev, u8 val);
 extern void intel_detect_pch(struct drm_device *dev);
 extern int intel_trans_dp_port_sel(struct drm_crtc *crtc);
 
+extern void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv);
+
 /* overlay */
 #ifdef CONFIG_DEBUG_FS
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
@@ -1352,8 +1360,9 @@ void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
 /* We give fast paths for the really cool registers */
 #define NEEDS_FORCE_WAKE(dev_priv, reg) \
 	(((dev_priv)->info->gen >= 6) && \
-	((reg) < 0x40000) && \
-	((reg) != FORCEWAKE))
+	 ((reg) < 0x40000) &&		 \
+	 ((reg) != FORCEWAKE) &&	 \
+	 ((reg) != ECOBUS))
 
 #define __i915_read(x, y) \
 	u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b080cc824001..8990057e384c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3449,6 +3449,10 @@
 
 #define  FORCEWAKE				0xA18C
 #define  FORCEWAKE_ACK				0x130090
+#define  FORCEWAKE_MT				0xa188 /* multi-threaded */
+#define  FORCEWAKE_MT_ACK			0x130040
+#define  ECOBUS					0xa180
+#define    FORCEWAKE_MT_ENABLE			(1<<5)
 
 #define  GT_FIFO_FREE_ENTRIES			0x120008
 #define    GT_FIFO_NUM_RESERVED_ENTRIES		20
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e77a863a3833..633c69365388 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8491,6 +8491,28 @@ static void intel_init_display(struct drm_device *dev)
 
 	/* For FIFO watermark updates */
 	if (HAS_PCH_SPLIT(dev)) {
+		dev_priv->display.force_wake_get = __gen6_gt_force_wake_get;
+		dev_priv->display.force_wake_put = __gen6_gt_force_wake_put;
+
+		/* IVB configs may use multi-threaded forcewake */
+		if (IS_IVYBRIDGE(dev)) {
+			u32	ecobus;
+
+			mutex_lock(&dev->struct_mutex);
+			__gen6_gt_force_wake_mt_get(dev_priv);
+			ecobus = I915_READ(ECOBUS);
+			__gen6_gt_force_wake_mt_put(dev_priv);
+			mutex_unlock(&dev->struct_mutex);
+
+			if (ecobus & FORCEWAKE_MT_ENABLE) {
+				DRM_DEBUG_KMS("Using MT version of forcewake\n");
+				dev_priv->display.force_wake_get =
+					__gen6_gt_force_wake_mt_get;
+				dev_priv->display.force_wake_put =
+					__gen6_gt_force_wake_mt_put;
+			}
+		}
+
 		if (HAS_PCH_IBX(dev))
 			dev_priv->display.init_pch_clock_gating = ibx_init_clock_gating;
 		else if (HAS_PCH_CPT(dev))