[Intel-gfx] [PATCH 1/3] drm/i915: close PM interrupt masking races in the irq handler

[Daniel Vetter]

Quoting Chris Wilson's more concise description:

"Ah I think I see the problem. As you point out we only mask the current
interrupt received, so that if we have a task pending (and so IMR != 0) we
actually unmask the pending interrupt and so could receive it again before the
tasklet is finally kicked off by the grumpy scheduler."

We need the hw to issue PM interrupts A, B, A while the scheduler is hating us
and refuses to run the rps work item. On receiving PM interrupt A we hit the
WARN because

dev_priv->pm_iir == PM_A | PM_B

Also add a posting read as suggested by Chris to ensure proper ordering of the
writes to PMIMR and PMIIR. Just in case somebody weakens write ordering.

Signed-off-by: Daniel Vetter <daniel.vetter at ffwll.ch>
Reviewed-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_irq.c |    6 ++++--
 1 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 9cbb0cd..2fdd9f9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -536,8 +536,9 @@ static irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS)
 		unsigned long flags;
 		spin_lock_irqsave(&dev_priv->rps_lock, flags);
 		WARN(dev_priv->pm_iir & pm_iir, "Missed a PM interrupt\n");
-		I915_WRITE(GEN6_PMIMR, pm_iir);
 		dev_priv->pm_iir |= pm_iir;
+		I915_WRITE(GEN6_PMIMR, dev_priv->pm_iir);
+		POSTING_READ(GEN6_PMIMR);
 		spin_unlock_irqrestore(&dev_priv->rps_lock, flags);
 		queue_work(dev_priv->wq, &dev_priv->rps_work);
 	}
@@ -649,8 +650,9 @@ static irqreturn_t ironlake_irq_handler(DRM_IRQ_ARGS)
 		unsigned long flags;
 		spin_lock_irqsave(&dev_priv->rps_lock, flags);
 		WARN(dev_priv->pm_iir & pm_iir, "Missed a PM interrupt\n");
-		I915_WRITE(GEN6_PMIMR, pm_iir);
 		dev_priv->pm_iir |= pm_iir;
+		I915_WRITE(GEN6_PMIMR, dev_priv->pm_iir);
+		POSTING_READ(GEN6_PMIMR);
 		spin_unlock_irqrestore(&dev_priv->rps_lock, flags);
 		queue_work(dev_priv->wq, &dev_priv->rps_work);
 	}
-- 
1.7.6