From: Chris Wilson Date: Thu, 18 Aug 2016 16:16:48 +0000 (+0100) Subject: drm/i915: Before accessing an object via the cpu, flush GTT writes X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=a314d5cb4ac3722b9a673656e2499f4d92ee5e6f;p=linux-beck.git drm/i915: Before accessing an object via the cpu, flush GTT writes If we want to read the pages directly via the CPU, we have to be sure that we have to flush the writes via the GTT (as the CPU can not see the address aliasing). Signed-off-by: Chris Wilson Reviewed-by: Joonas Lahtinen Link: http://patchwork.freedesktop.org/patch/msgid/20160818161718.27187-9-chris@chris-wilson.co.uk --- diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index f27c340bb8ee..c3f1a981b544 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -622,6 +622,8 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, if (ret) return ret; + i915_gem_object_flush_gtt_write_domain(obj); + /* If we're not in the cpu read domain, set ourself into the gtt * read domain and manually flush cachelines (if required). This * optimizes for the case when the gpu will dirty the data @@ -662,6 +664,8 @@ int i915_gem_obj_prepare_shmem_write(struct drm_i915_gem_object *obj, if (ret) return ret; + i915_gem_object_flush_gtt_write_domain(obj); + /* If we're not in the cpu write domain, set ourself into the * gtt write domain and manually flush cachelines (as required). * This optimizes for the case when the gpu will use the data