[Intel-gfx] [PATCH 1/2] drm/i915: Try harder to reset the GPU

[Chris Wilson]

Repeat the reset a couple of times if at first we do not succeed.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170513083726.502-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_uncore.c | 44 +++++++++++++++++++++----------------
 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 71b9b387ad04..fc3da0a6fdbb 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1463,9 +1463,10 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	return ret;
 }
 
-static int i915_reset_complete(struct pci_dev *pdev)
+static bool i915_reset_complete(struct pci_dev *pdev)
 {
 	u8 gdrst;
+
 	pci_read_config_byte(pdev, I915_GDRST, &gdrst);
 	return (gdrst & GRDOM_RESET_STATUS) == 0;
 }
@@ -1476,15 +1477,16 @@ static int i915_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask
 
 	/* assert reset for at least 20 usec */
 	pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
-	udelay(20);
+	usleep_range(50, 200);
 	pci_write_config_byte(pdev, I915_GDRST, 0);
 
 	return wait_for(i915_reset_complete(pdev), 500);
 }
 
-static int g4x_reset_complete(struct pci_dev *pdev)
+static bool g4x_reset_complete(struct pci_dev *pdev)
 {
 	u8 gdrst;
+
 	pci_read_config_byte(pdev, I915_GDRST, &gdrst);
 	return (gdrst & GRDOM_RESET_ENABLE) == 0;
 }
@@ -1492,6 +1494,7 @@ static int g4x_reset_complete(struct pci_dev *pdev)
 static int g33_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 {
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+
 	pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
 	return wait_for(g4x_reset_complete(pdev), 500);
 }
@@ -1505,7 +1508,7 @@ static int g4x_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 			      GRDOM_RENDER | GRDOM_RESET_ENABLE);
 	ret =  wait_for(g4x_reset_complete(pdev), 500);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* WaVcpClkGateDisableForMediaReset:ctg,elk */
 	I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE);
@@ -1514,16 +1517,14 @@ static int g4x_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 	pci_write_config_byte(pdev, I915_GDRST,
 			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
 	ret =  wait_for(g4x_reset_complete(pdev), 500);
-	if (ret)
-		return ret;
 
 	/* WaVcpClkGateDisableForMediaReset:ctg,elk */
 	I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE);
 	POSTING_READ(VDECCLK_GATE_D);
 
+out:
 	pci_write_config_byte(pdev, I915_GDRST, 0);
-
-	return 0;
+	return ret;
 }
 
 static int ironlake_do_reset(struct drm_i915_private *dev_priv,
@@ -1531,25 +1532,21 @@ static int ironlake_do_reset(struct drm_i915_private *dev_priv,
 {
 	int ret;
 
-	I915_WRITE(ILK_GDSR,
-		   ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE);
+	I915_WRITE(ILK_GDSR, ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE);
 	ret = intel_wait_for_register(dev_priv,
 				      ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0,
 				      500);
 	if (ret)
-		return ret;
+		goto out;
 
-	I915_WRITE(ILK_GDSR,
-		   ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE);
+	I915_WRITE(ILK_GDSR, ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE);
 	ret = intel_wait_for_register(dev_priv,
 				      ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0,
 				      500);
-	if (ret)
-		return ret;
-
+out:
 	I915_WRITE(ILK_GDSR, 0);
-
-	return 0;
+	POSTING_READ(ILK_GDSR);
+	return ret;
 }
 
 /* Reset the hardware domains (GENX_GRDOM_*) specified by mask */
@@ -1758,8 +1755,11 @@ static reset_func intel_get_gpu_reset(struct drm_i915_private *dev_priv)
 int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 {
 	reset_func reset;
+	int retry;
 	int ret;
 
+	might_sleep();
+
 	reset = intel_get_gpu_reset(dev_priv);
 	if (reset == NULL)
 		return -ENODEV;
@@ -1768,7 +1768,13 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 	 * request may be dropped and never completes (causing -EIO).
 	 */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-	ret = reset(dev_priv, engine_mask);
+	for (retry = 0; retry < 3; retry++) {
+		ret = reset(dev_priv, engine_mask);
+		if (ret != -ETIMEDOUT)
+			break;
+
+		cond_resched();
+	}
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
 	return ret;
-- 
2.11.0