[0008/1094] drm/i915: Identify active VM for batchbuffer capture

Commit Message

Dheeraj Jamwal Oct. 21, 2014, 10:43 a.m. UTC

From: Ben Widawsky <[e-mail]>

Using the current state of the page directory registers, we can
determine which of our address spaces was active when the hang occurred.
This allows us to scan through all the address spaces to identify the
"active" one during error capture.

v2: Rebased for BDW error detection. BDW error detection is similar
except instead of PP_DIR_BASE, we can use the PDP registers.

Signed-off-by: Ben Widawsky <[e-mail]>
[danvet: Add FIXME about global gtt misuse.]
Signed-off-by: Daniel Vetter <[e-mail]>
(cherry picked from commit 685987c6915222730f45141a89f1cd87fb092e9a)

Signed-off-by: Dheeraj Jamwal <[e-mail]>
---
 drivers/gpu/drm/i915/i915_gpu_error.c |   33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

Patch

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 29956a0..956db2f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -658,6 +658,32 @@  static void i915_gem_record_fences(struct drm_device *dev,
 	}
 }
 
+/* This assumes all batchbuffers are executed from the PPGTT. It might have to
+ * change in the future. */
+static bool is_active_vm(struct i915_address_space *vm,
+			 struct intel_ring_buffer *ring)
+{
+	struct drm_device *dev = vm->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt;
+
+	if (INTEL_INFO(dev)->gen < 7)
+		return i915_is_ggtt(vm);
+
+	/* FIXME: This ignores that the global gtt vm is also on this list. */
+	ppgtt = container_of(vm, struct i915_hw_ppgtt, base);
+
+	if (INTEL_INFO(dev)->gen >= 8) {
+		u64 pdp0 = (u64)I915_READ(GEN8_RING_PDP_UDW(ring, 0)) << 32;
+		pdp0 |=  I915_READ(GEN8_RING_PDP_LDW(ring, 0));
+		return pdp0 == ppgtt->pd_dma_addr[0];
+	} else {
+		u32 pp_db;
+		pp_db = I915_READ(RING_PP_DIR_BASE(ring));
+		return (pp_db >> 10) == ppgtt->pd_offset;
+	}
+}
+
 static struct drm_i915_error_object *
 i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 			     struct intel_ring_buffer *ring)
@@ -665,6 +691,7 @@  i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	struct drm_i915_gem_object *obj;
+	bool found_active = false;
 	u32 seqno;
 
 	if (!ring->get_seqno)
@@ -685,6 +712,11 @@  i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 
 	seqno = ring->get_seqno(ring, false);
 	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
+		if (!is_active_vm(vm, ring))
+			continue;
+
+		found_active = true;
+
 		list_for_each_entry(vma, &vm->active_list, mm_list) {
 			obj = vma->obj;
 			if (obj->ring != ring)
@@ -703,6 +735,7 @@  i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 		}
 	}
 
+	WARN_ON(!found_active);
 	return NULL;
 }