drm/i915: Don't continually defer the hangcheck

With multiple rings, we may continue to render on the blitter whilst
executing an infinite shader on the render ring. As we currently, rearm
the timer with each execbuf, in this scenario the hangcheck will never
fire and we will never detect the lockup on the render ring. Instead,
only arm the timer once per hangcheck, so that hangcheck runs more
frequently.

v2: Rearrange code to avoid triggering a BUG_ON in add_timer from
softirq context.

Testcase: igt/gem_reset_stats/defer-hangcheck*
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=86225
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
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 5e5d3f709f0ff38cb8ba8e9fa7f11d85ef612c22..e298518c944e6de3457788020323202bb26d9200 100644 (file)
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -988,7 +988,6 @@ static void notify_ring(struct drm_device *dev,
        trace_i915_gem_request_complete(ring);
 
        wake_up_all(&ring->irq_queue);
-       i915_queue_hangcheck(dev);
 }
 
 static u32 vlv_c0_residency(struct drm_i915_private *dev_priv,
@@ -3041,11 +3040,15 @@ static void i915_hangcheck_elapsed(unsigned long data)
 void i915_queue_hangcheck(struct drm_device *dev)
 {
        struct drm_i915_private *dev_priv = dev->dev_private;
+       struct timer_list *timer = &dev_priv->gpu_error.hangcheck_timer;
+
        if (!i915.enable_hangcheck)
                return;
 
-       mod_timer(&dev_priv->gpu_error.hangcheck_timer,
-                 round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
+       /* Don't continually defer the hangcheck, but make sure it is active */
+       if (!timer_pending(timer))
+               timer->expires = round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES);
+       mod_timer(timer, timer->expires);
 }
 
 static void ibx_irq_reset(struct drm_device *dev)