[Intel-gfx] [PATCH 3/3] drm/i915: Grab gpu state through debugfs

[Mika Kuoppala]

because it is handy to direct bug reporters to do things like:
'grep -i suspend /sys/kernel/debug/dri/0/i915_gpu_state'

Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c   | 42 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_drv.h       |  4 ++++
 drivers/gpu/drm/i915/i915_gpu_error.c | 22 ++++++++++++++----
 3 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e60d5c2..8d3266d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -976,6 +976,47 @@ static const struct file_operations i915_error_state_fops = {
 	.release = i915_error_state_release,
 };
 
+static int i915_gpu_state_open(struct inode *inode, struct file *file)
+{
+	struct drm_device *dev = inode->i_private;
+	struct i915_error_state_file_priv *gpu_priv;
+
+	gpu_priv = kzalloc(sizeof(*gpu_priv), GFP_KERNEL);
+	if (!gpu_priv)
+		return -ENOMEM;
+
+	gpu_priv->dev = dev;
+
+	gpu_priv->error = i915_capture_gpu_state(dev);
+	if (gpu_priv->error == NULL) {
+		kfree(gpu_priv);
+		return -ENOMEM;
+	}
+
+	file->private_data = gpu_priv;
+
+	return 0;
+}
+
+static int i915_gpu_state_release(struct inode *inode, struct file *file)
+{
+	struct i915_error_state_file_priv *gpu_priv = file->private_data;
+
+	kref_put(&gpu_priv->error->ref, i915_gpu_state_free);
+	kfree(gpu_priv);
+
+	return 0;
+}
+
+static const struct file_operations i915_gpu_state_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_gpu_state_open,
+	.read = i915_error_state_read,
+	.write = NULL,
+	.llseek = default_llseek,
+	.release = i915_gpu_state_release,
+};
+
 static int
 i915_next_seqno_get(void *data, u64 *val)
 {
@@ -4217,6 +4258,7 @@ static const struct i915_debugfs_files {
 	{"i915_ring_test_irq", &i915_ring_test_irq_fops},
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
 	{"i915_error_state", &i915_error_state_fops},
+	{"i915_gpu_state", &i915_gpu_state_fops},
 	{"i915_next_seqno", &i915_next_seqno_fops},
 	{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 23e7f20..cbefc64 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2756,6 +2756,10 @@ static inline void i915_error_state_buf_release(
 {
 	kfree(eb->buf);
 }
+
+struct drm_i915_error_state *i915_capture_gpu_state(struct drm_device *dev);
+void i915_gpu_state_free(struct kref *error_ref);
+
 void i915_capture_error_state(struct drm_device *dev, bool wedge,
 			      const char *error_msg);
 void i915_error_state_get(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index c11882a..76211b5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -538,7 +538,7 @@ static void i915_error_object_free(struct drm_i915_error_object *obj)
 	kfree(obj);
 }
 
-static void i915_error_state_free(struct kref *error_ref)
+void i915_gpu_state_free(struct kref *error_ref)
 {
 	struct drm_i915_error_state *error = container_of(error_ref,
 							  typeof(*error), ref);
@@ -1291,6 +1291,20 @@ __i915_capture_gpu_state(struct drm_device *dev)
 	return error;
 }
 
+struct drm_i915_error_state *i915_capture_gpu_state(struct drm_device *dev)
+{
+	struct drm_i915_error_state *gpu_state;
+
+	gpu_state = __i915_capture_gpu_state(dev);
+	if (gpu_state == NULL)
+		return NULL;
+
+	scnprintf(gpu_state->error_msg, sizeof(gpu_state->error_msg),
+		  "GPU state snapshot\n");
+
+	return gpu_state;
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -1323,7 +1337,7 @@ void i915_capture_error_state(struct drm_device *dev, bool wedged,
 	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 
 	if (error) {
-		i915_error_state_free(&error->ref);
+		i915_gpu_state_free(&error->ref);
 		return;
 	}
 
@@ -1353,7 +1367,7 @@ void i915_error_state_get(struct drm_device *dev,
 void i915_error_state_put(struct i915_error_state_file_priv *error_priv)
 {
 	if (error_priv->error)
-		kref_put(&error_priv->error->ref, i915_error_state_free);
+		kref_put(&error_priv->error->ref, i915_gpu_state_free);
 }
 
 void i915_destroy_error_state(struct drm_device *dev)
@@ -1367,7 +1381,7 @@ void i915_destroy_error_state(struct drm_device *dev)
 	spin_unlock_irq(&dev_priv->gpu_error.lock);
 
 	if (error)
-		kref_put(&error->ref, i915_error_state_free);
+		kref_put(&error->ref, i915_gpu_state_free);
 }
 
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
-- 
1.9.1