drm/i915: Add reason for capture in error state
We capture error state not only when the GPU hangs but also on
other situations as in interrupt errors and in situations where
we can kick things forward without GPU reset. There will be log
entry on most of these cases. But as error state capture might be
only thing we have, if dmesg was not captured. Or as in GEN4 case,
interrupt error can trigger error state capture without log entry,
the exact reason why capture was made is hard to decipher.
v2: Split out the the error code stuff to separate patch (Ben)
References: https://bugs.freedesktop.org/show_bug.cgi?id=74193
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 484415b..3e8359e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1297,8 +1297,8 @@
if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
GT_BSD_CS_ERROR_INTERRUPT |
GT_RENDER_CS_MASTER_ERROR_INTERRUPT)) {
- DRM_ERROR("GT error interrupt 0x%08x\n", gt_iir);
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false, "GT error interrupt 0x%08x",
+ gt_iir);
}
if (gt_iir & GT_PARITY_ERROR(dev))
@@ -1545,8 +1545,9 @@
notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) {
- DRM_ERROR("VEBOX CS error interrupt 0x%08x\n", pm_iir);
- i915_handle_error(dev_priv->dev, false);
+ i915_handle_error(dev_priv->dev, false,
+ "VEBOX CS error interrupt 0x%08x",
+ pm_iir);
}
}
}
@@ -2278,11 +2279,18 @@
* so userspace knows something bad happened (should trigger collection
* of a ring dump etc.).
*/
-void i915_handle_error(struct drm_device *dev, bool wedged)
+void i915_handle_error(struct drm_device *dev, bool wedged,
+ const char *fmt, ...)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ va_list args;
+ char error_msg[80];
- i915_capture_error_state(dev);
+ va_start(args, fmt);
+ vscnprintf(error_msg, sizeof(error_msg), fmt, args);
+ va_end(args);
+
+ i915_capture_error_state(dev, wedged, error_msg);
i915_report_and_clear_eir(dev);
if (wedged) {
@@ -2585,9 +2593,9 @@
*/
tmp = I915_READ_CTL(ring);
if (tmp & RING_WAIT) {
- DRM_ERROR("Kicking stuck wait on %s\n",
- ring->name);
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Kicking stuck wait on %s",
+ ring->name);
I915_WRITE_CTL(ring, tmp);
return HANGCHECK_KICK;
}
@@ -2597,9 +2605,9 @@
default:
return HANGCHECK_HUNG;
case 1:
- DRM_ERROR("Kicking stuck semaphore on %s\n",
- ring->name);
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Kicking stuck semaphore on %s",
+ ring->name);
I915_WRITE_CTL(ring, tmp);
return HANGCHECK_KICK;
case 0:
@@ -2721,7 +2729,7 @@
}
if (rings_hung)
- return i915_handle_error(dev, true);
+ return i915_handle_error(dev, true, "Ring hung");
if (busy_count)
/* Reset timer case chip hangs without another request
@@ -3338,7 +3346,9 @@
*/
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Command parser error, iir 0x%08x",
+ iir);
for_each_pipe(pipe) {
int reg = PIPESTAT(pipe);
@@ -3520,7 +3530,9 @@
*/
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Command parser error, iir 0x%08x",
+ iir);
for_each_pipe(pipe) {
int reg = PIPESTAT(pipe);
@@ -3757,7 +3769,9 @@
*/
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Command parser error, iir 0x%08x",
+ iir);
for_each_pipe(pipe) {
int reg = PIPESTAT(pipe);