[Intel-gfx] [RFC 4/4] drm/i915: Dispatch the shadow batch buffer

bradley.d.volkin at intel.com bradley.d.volkin at intel.com
Wed Jun 18 18:36:16 CEST 2014


From: Brad Volkin <bradley.d.volkin at intel.com>

This is useful for testing the batch pool code with aliasing PPGTT.
It doesn't work with full PPGTT though; the GPU hangs and the whole
UI is corrupted. We need fixes for the secure dispatch path to
enable this for real.

Signed-off-by: Brad Volkin <bradley.d.volkin at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 37 ++++++++++++++++--------------
 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0b263aa..981f66b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1321,31 +1321,34 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 
 		/*
-		 * XXX: Actually do this when enabling batch copy...
-		 *
 		 * Set the DISPATCH_SECURE bit to remove the NON_SECURE bit
 		 * from MI_BATCH_BUFFER_START commands issued in the
 		 * dispatch_execbuffer implementations. We specifically don't
 		 * want that set when the command parser is enabled.
 		 */
+		flags |= I915_DISPATCH_SECURE;
 	}
 
-	/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
-	 * batch" bit. Hence we need to pin secure batches into the global gtt.
-	 * hsw should have this fixed, but bdw mucks it up again. */
-	if (flags & I915_DISPATCH_SECURE &&
-	    !batch_obj->has_global_gtt_mapping) {
-		/* When we have multiple VMs, we'll need to make sure that we
-		 * allocate space first */
-		struct i915_vma *vma = i915_gem_obj_to_ggtt(batch_obj);
-		BUG_ON(!vma);
-		vma->bind_vma(vma, batch_obj->cache_level, GLOBAL_BIND);
-	}
+	if (!shadow_batch_obj) {
+		/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
+		 * batch" bit. Hence we need to pin secure batches into the global gtt.
+		 * hsw should have this fixed, but bdw mucks it up again. */
+		if (flags & I915_DISPATCH_SECURE &&
+		    !batch_obj->has_global_gtt_mapping) {
+			/* When we have multiple VMs, we'll need to make sure that we
+			 * allocate space first */
+			struct i915_vma *vma = i915_gem_obj_to_ggtt(batch_obj);
+			BUG_ON(!vma);
+			vma->bind_vma(vma, batch_obj->cache_level, GLOBAL_BIND);
+		}
 
-	if (flags & I915_DISPATCH_SECURE)
-		exec_start += i915_gem_obj_ggtt_offset(batch_obj);
-	else
-		exec_start += i915_gem_obj_offset(batch_obj, vm);
+		if (flags & I915_DISPATCH_SECURE)
+			exec_start += i915_gem_obj_ggtt_offset(batch_obj);
+		else
+			exec_start += i915_gem_obj_offset(batch_obj, vm);
+	} else {
+		exec_start += i915_gem_obj_ggtt_offset(shadow_batch_obj);
+	}
 
 	ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->vmas);
 	if (ret)
-- 
1.8.3.2




More information about the Intel-gfx mailing list