When the engine idles waiting upon a semaphore, it loses its
pagetables and we must reload them before executing the batch.
v2: Restrict w/a to non-RCS rings (RCS works correctly apparently).
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Ville Syrjälä <ville.syrjala@xxxxxxxxxxxxxxx>
Reviewed-by: Ville Syrjälä <ville.syrjala@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/intel_ringbuffer.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 533ebbd384f6..70738a54ed0f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1481,6 +1481,7 @@ gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
{
struct intel_engine_cs *waiter = waiter_req->engine;
struct drm_i915_private *dev_priv = waiter->dev->dev_private;
+ struct i915_hw_ppgtt *ppgtt;
int ret;
ret = intel_ring_begin(waiter_req, 4);
@@ -1496,6 +1497,15 @@ gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
intel_ring_emit(waiter,
upper_32_bits(GEN8_WAIT_OFFSET(waiter, signaller->id)));
intel_ring_advance(waiter);
+
+ /* When the !RCS engines idle waiting upon a semaphore, they lose their
+ * pagetables and we must reload them before executing the batch.
+ * We do this on the i915_switch_context() following the wait and
+ * before the dispatch.
+ */
+ ppgtt = waiter_req->ctx->ppgtt;
+ if (ppgtt && waiter_req->engine->id != RCS)
+ ppgtt->pd_dirty_rings |= intel_engine_flag(waiter_req->engine);
return 0;
}
--
2.8.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
