drm/i915: reference counted forcewake

Provide a reference count to track the forcewake state of the GPU and
give a safe mechanism for userspace to wake the GT. This also potentially
saves a UC read if the GT is known to be awake already.

The reference count is atomic, but the register access and hardware wake
sequence is protected by struct_mutex.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drivers/gpu/drm/i915/i915_debugfs.c

@@ -874,7 +874,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		int max_freq;
 
 		/* RPSTAT1 is in the GT power well */
-		__gen6_gt_force_wake_get(dev_priv);
+		gen6_gt_force_wake_get(dev_priv);
 
 		rpstat = I915_READ(GEN6_RPSTAT1);
 		rpupei = I915_READ(GEN6_RP_CUR_UP_EI);
@@ -919,7 +919,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
 			   max_freq * 50);
 
-		__gen6_gt_force_wake_put(dev_priv);
+		gen6_gt_force_wake_put(dev_priv);
 	} else {
 		seq_printf(m, "no P-state info available\n");
 	}

drivers/gpu/drm/i915/i915_drv.c

@@ -263,7 +263,7 @@ void intel_detect_pch (struct drm_device *dev)
 	}
 }
 
-void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 {
 	int count;
 
@@ -279,12 +279,38 @@ void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 		udelay(10);
 }
 
-void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+/*
+ * 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
+ * be called at the beginning of the sequence followed by a call to
+ * gen6_gt_force_wake_put() at the end of the sequence.
+ */
+void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+
+	/* 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);
+}
+
+static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
 	POSTING_READ(FORCEWAKE);
 }
 
+/*
+ * see gen6_gt_force_wake_get()
+ */
+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);
+}
+
 void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
 {
 	int loop = 500;

drivers/gpu/drm/i915/i915_drv.h

@@ -709,6 +709,8 @@ typedef struct drm_i915_private {
 	struct intel_fbdev *fbdev;
 
 	struct drm_property *broadcast_rgb_property;
+
+	atomic_t forcewake_count;
 } drm_i915_private_t;
 
 enum i915_cache_level {
@@ -1329,8 +1331,8 @@ extern void intel_display_print_error_state(struct seq_file *m,
  * must be set to prevent GT core from power down and stale values being
  * returned.
  */
-void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
-void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
 void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
 
 /* We give fast paths for the really cool registers */
@@ -1343,15 +1345,16 @@ void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
 static inline u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
 	u##x val = 0; \
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		__gen6_gt_force_wake_get(dev_priv); \
+		gen6_gt_force_wake_get(dev_priv); \
 		val = read##y(dev_priv->regs + reg); \
-		__gen6_gt_force_wake_put(dev_priv); \
+		gen6_gt_force_wake_put(dev_priv); \
 	} else { \
 		val = read##y(dev_priv->regs + reg); \
 	} \
 	trace_i915_reg_rw(false, reg, val, sizeof(val)); \
 	return val; \
 }
+
 __i915_read(8, b)
 __i915_read(16, w)
 __i915_read(32, l)

drivers/gpu/drm/i915/i915_irq.c

@@ -396,7 +396,6 @@ static void gen6_pm_irq_handler(struct drm_device *dev)
 			I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
 				   I915_READ(GEN6_RP_INTERRUPT_LIMITS) & ~0x3f0000);
 		}
-
 	}
 
 	gen6_set_rps(dev, new_delay);

drivers/gpu/drm/i915/intel_display.c

@@ -1540,7 +1540,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
 	u32 blt_ecoskpd;
 
 	/* Make sure blitter notifies FBC of writes */
-	__gen6_gt_force_wake_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv);
 	blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
 	blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
 		GEN6_BLITTER_LOCK_SHIFT;
@@ -1551,7 +1551,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
 			 GEN6_BLITTER_LOCK_SHIFT);
 	I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
 	POSTING_READ(GEN6_BLITTER_ECOSKPD);
-	__gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv);
 }
 
 static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
@@ -6973,7 +6973,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	 * userspace...
 	 */
 	I915_WRITE(GEN6_RC_STATE, 0);
-	__gen6_gt_force_wake_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv);
 
 	/* disable the counters and set deterministic thresholds */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -7074,7 +7074,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	/* enable all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);
 
-	__gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv);
 }
 
 void intel_enable_clock_gating(struct drm_device *dev)