[Intel-gfx] [PATCH] drm/i915: Disable irqs across GPU reset

[Chris Wilson]

Whilst we reset the GPU, we want to prevent execlists from submitting
new work (which it does via an interrupt handler). To achieve this we
disable the irq (and drain the irq tasklet) around the reset. When we
enable it again afters, the interrupt queue should be empty and we can
reinitialise from a known state without fear of the tasklet running
concurrently.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 19 +++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem.c |  2 --
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 31b2b6300d8d..7ce498898217 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1728,6 +1728,21 @@ int i915_resume_switcheroo(struct drm_device *dev)
 	return i915_drm_resume(dev);
 }
 
+static void disable_engines_irq(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+
+	/* Ensure irq handler finishes, and not run again. */
+	disable_irq(dev_priv->drm.irq);
+	for_each_engine(engine, dev_priv)
+		tasklet_kill(&engine->irq_tasklet);
+}
+
+static void enable_engines_irq(struct drm_i915_private *dev_priv)
+{
+	enable_irq(dev_priv->drm.irq);
+}
+
 /**
  * i915_reset - reset chip after a hang
  * @dev: drm device to reset
@@ -1761,7 +1776,11 @@ void i915_reset(struct drm_i915_private *dev_priv)
 	error->reset_count++;
 
 	pr_notice("drm/i915: Resetting chip after gpu hang\n");
+
+	disable_engines_irq(dev_priv);
 	ret = intel_gpu_reset(dev_priv, ALL_ENGINES);
+	enable_engines_irq(dev_priv);
+
 	if (ret) {
 		if (ret != -ENODEV)
 			DRM_ERROR("Failed to reset chip: %i\n", ret);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1418c1c522cb..0cae8acdf906 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2581,8 +2581,6 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine)
 	struct i915_gem_context *incomplete_ctx;
 	bool ring_hung;
 
-	/* Ensure irq handler finishes, and not run again. */
-	tasklet_kill(&engine->irq_tasklet);
 	if (engine->irq_seqno_barrier)
 		engine->irq_seqno_barrier(engine);
 
-- 
2.9.3