[Intel-gfx] [PATCH] drm/i915/ppgtt: Limit guilty hunt inside of relevant vm

[Mika Kuoppala]

With full ppgtt, ACTHD is only relevant inside one context
(address space). Trying to find guilty batch only relying
on ACTHD, the result is false positives as ACTHD points
inside batches on different address spaces.

Filter out nonrelated contexts by checking on which vm
the ring was running on when the hang happened. Only after
finding the relevant vm, use acthd to find the guilty
batch inside it.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=73652
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c |   25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5fcdb14..a7cc060 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2282,9 +2282,34 @@ request_to_vm(struct drm_i915_gem_request *request)
 	return vm;
 }
 
+static bool
+request_vm_active(struct drm_i915_gem_request *request)
+{
+	struct intel_ring_buffer *ring = request->ring;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt;
+	u32 pd_off;
+
+	if (USES_FULL_PPGTT(dev) == false)
+		return true;
+
+	if (WARN_ON(!request->ctx))
+		return false;
+
+	ppgtt = ctx_to_ppgtt(request->ctx);
+
+	pd_off = (I915_READ(RING_PP_DIR_BASE(ring)) >> 16) * 64;
+
+	return pd_off == ppgtt->pd_offset;
+}
+
 static bool i915_request_guilty(struct drm_i915_gem_request *request,
 				const u32 acthd, bool *inside)
 {
+	if (!request_vm_active(request))
+		return false;
+
 	/* There is a possibility that unmasked head address
 	 * pointing inside the ring, matches the batch_obj address range.
 	 * However this is extremely unlikely.
-- 
1.7.9.5