drm/i915: check ACTHD of all rings

commit 097354eb14fa94d31a09c64d640643f58e4a5a9a upstream.

Otherwise hangcheck spuriously fires when running blitter/bsd-only
workloads.

Contrary to a similar patch by Ben Widawsky this does not check
INSTDONE of the other rings. Chris Wilson implied that in a failure to
detect a hang, most likely because INSTDONE was fluctuating. Thus only
check ACTHD, which as far as I know is rather reliable. Also, blitter
and bsd rings can't launch complex tasks from a single instruction
(like 3D_PRIM on the render with complex or even infinite shaders).

This fixes spurious gpu hang detection when running
tests/gem_hangcheck_forcewake on snb/ivb.

Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 554bef7a3b9c8db39c5963fcc72ba1d411f31125..505af3f64a079f4789986680830af3605b42b869 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -337,6 +337,8 @@ typedef struct drm_i915_private {
        struct timer_list hangcheck_timer;
        int hangcheck_count;
        uint32_t last_acthd;
+       uint32_t last_acthd_bsd;
+       uint32_t last_acthd_blt;
        uint32_t last_instdone;
        uint32_t last_instdone1;
 

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b40004b559771dc0244814335d44fb1537625087..d47a53b1db843d400981cd13640e45ab67a2eab0 100644 (file)
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1669,7 +1669,7 @@ void i915_hangcheck_elapsed(unsigned long data)
 {
        struct drm_device *dev = (struct drm_device *)data;
        drm_i915_private_t *dev_priv = dev->dev_private;
-       uint32_t acthd, instdone, instdone1;
+       uint32_t acthd, instdone, instdone1, acthd_bsd, acthd_blt;
        bool err = false;
 
        if (!i915_enable_hangcheck)
@@ -1686,16 +1686,21 @@ void i915_hangcheck_elapsed(unsigned long data)
        }
 
        if (INTEL_INFO(dev)->gen < 4) {
-               acthd = I915_READ(ACTHD);
                instdone = I915_READ(INSTDONE);
                instdone1 = 0;
        } else {
-               acthd = I915_READ(ACTHD_I965);
                instdone = I915_READ(INSTDONE_I965);
                instdone1 = I915_READ(INSTDONE1);
        }
+       acthd = intel_ring_get_active_head(&dev_priv->ring[RCS]);
+       acthd_bsd = HAS_BSD(dev) ?
+               intel_ring_get_active_head(&dev_priv->ring[VCS]) : 0;
+       acthd_blt = HAS_BLT(dev) ?
+               intel_ring_get_active_head(&dev_priv->ring[BCS]) : 0;
 
        if (dev_priv->last_acthd == acthd &&
+           dev_priv->last_acthd_bsd == acthd_bsd &&
+           dev_priv->last_acthd_blt == acthd_blt &&
            dev_priv->last_instdone == instdone &&
            dev_priv->last_instdone1 == instdone1) {
                if (dev_priv->hangcheck_count++ > 1) {
@@ -1727,6 +1732,8 @@ void i915_hangcheck_elapsed(unsigned long data)
                dev_priv->hangcheck_count = 0;
 
                dev_priv->last_acthd = acthd;
+               dev_priv->last_acthd_bsd = acthd_bsd;
+               dev_priv->last_acthd_blt = acthd_blt;
                dev_priv->last_instdone = instdone;
                dev_priv->last_instdone1 = instdone1;
        }