@@ -2151,6 +2151,30 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj)
return 0;
}
+static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj)
+{
+ u32 old_write_domain, old_read_domains;
+
+ if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0)
+ return;
+
+ /* Act a barrier for all accesses through the GTT */
+ mb();
+
+ /* And force a pagefault following the invalidation */
+ i915_gem_release_mmap(obj);
+
+ old_read_domains = obj->base.read_domains;
+ old_write_domain = obj->base.write_domain;
+
+ obj->base.write_domain &= ~I915_GEM_DOMAIN_GTT;
+ obj->base.write_domain &= ~I915_GEM_DOMAIN_GTT;
+
+ trace_i915_gem_object_change_domain(obj,
+ old_read_domains,
+ old_write_domain);
+}
+
/**
* Unbinds an object from the GTT aperture.
*/
@@ -2168,7 +2192,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
}
/* blow away mappings if mapped through GTT */
- i915_gem_release_mmap(obj);
+ i915_gem_object_finish_gtt(obj);
/* Move the object to the CPU domain to ensure that
* any possible CPU writes while it's not in the GTT
Like its siblings finish_gpu(), this function clears the object from the GTT domain forcing it to be trigger a domain invalidation should we ever need to use via the GTT again. Note that the most important side-effect of finishing the GTT domain (aside from clearing the tracking read/write domains) is that is imposes an memory barrier so that all accesses are complete before it returns, which is important if you intend to be modifying translation tables shortly afterwards. The second most important side-effect is that it tears down the GTT mappings forcing a page-fault and invalidation on next user access to the object. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> --- drivers/gpu/drm/i915/i915_gem.c | 26 +++++++++++++++++++++++++- 1 files changed, 25 insertions(+), 1 deletions(-)