drm/i915: add interface to simulate gpu hangs

gpu reset is a very important piece of our infrastructure.
Unfortunately we only really it test by actually hanging the gpu,
which often has bad side-effects for the entire system. And the gpu
hang handling code is one of the rather complicated pieces of code we
have, consisting of
- hang detection
- error capture
- actual gpu reset
- reset of all the gem bookkeeping
- reinitialition of the entire gpu

This patch adds a debugfs to selectively stopping rings by ceasing to
update the hw tail pointer, which will result in the gpu no longer
updating it's head pointer and eventually to the hangcheck firing.
This way we can exercise the gpu hang code under controlled conditions
without a dying gpu taking down the entire systems.

Patch motivated by me forgetting to properly reinitialize ppgtt after
a gpu reset.

Usage:

echo $((1 << $ringnum)) > i915_ring_stop # stops one ring

echo 0xffffffff > i915_ring_stop # stops all, future-proof version

then run whatever testload is desired. i915_ring_stop automatically
resets after a gpu hang is detected to avoid hanging the gpu to fast
and declaring it wedged.

v2: Incorporate feedback from Chris Wilson.

v3: Add the missing cleanup.

v4: Fix up inconsistent size of ring_stop_read vs _write, noticed by
Eugeni Dodonov.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 65 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ae68ac1c488..192b27e9046 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1586,6 +1586,64 @@ static const struct file_operations i915_wedged_fops = {
 };
 
 static ssize_t
+i915_ring_stop_read(struct file *filp,
+		    char __user *ubuf,
+		    size_t max,
+		    loff_t *ppos)
+{
+	struct drm_device *dev = filp->private_data;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	char buf[20];
+	int len;
+
+	len = snprintf(buf, sizeof(buf),
+		       "0x%08x\n", dev_priv->stop_rings);
+
+	if (len > sizeof(buf))
+		len = sizeof(buf);
+
+	return simple_read_from_buffer(ubuf, max, ppos, buf, len);
+}
+
+static ssize_t
+i915_ring_stop_write(struct file *filp,
+		     const char __user *ubuf,
+		     size_t cnt,
+		     loff_t *ppos)
+{
+	struct drm_device *dev = filp->private_data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	char buf[20];
+	int val = 0;
+
+	if (cnt > 0) {
+		if (cnt > sizeof(buf) - 1)
+			return -EINVAL;
+
+		if (copy_from_user(buf, ubuf, cnt))
+			return -EFAULT;
+		buf[cnt] = 0;
+
+		val = simple_strtoul(buf, NULL, 0);
+	}
+
+	DRM_DEBUG_DRIVER("Stopping rings 0x%08x\n", val);
+
+	mutex_lock(&dev->struct_mutex);
+	dev_priv->stop_rings = val;
+	mutex_unlock(&dev->struct_mutex);
+
+	return cnt;
+}
+
+static const struct file_operations i915_ring_stop_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = i915_ring_stop_read,
+	.write = i915_ring_stop_write,
+	.llseek = default_llseek,
+};
+static ssize_t
 i915_max_freq_read(struct file *filp,
 		   char __user *ubuf,
 		   size_t max,
@@ -1885,6 +1943,11 @@ int i915_debugfs_init(struct drm_minor *minor)
 				  &i915_cache_sharing_fops);
 	if (ret)
 		return ret;
+	ret = i915_debugfs_create(minor->debugfs_root, minor,
+				  "i915_ring_stop",
+				  &i915_ring_stop_fops);
+	if (ret)
+		return ret;
 
 	return drm_debugfs_create_files(i915_debugfs_list,
 					I915_DEBUGFS_ENTRIES,
@@ -1903,6 +1966,8 @@ void i915_debugfs_cleanup(struct drm_minor *minor)
 				 1, minor);
 	drm_debugfs_remove_files((struct drm_info_list *) &i915_cache_sharing_fops,
 				 1, minor);
+	drm_debugfs_remove_files((struct drm_info_list *) &i915_ring_stop_fops,
+				 1, minor);
 }
 
 #endif /* CONFIG_DEBUG_FS */