drm/i915: Unconditionally flush any chipset buffers before execbuf

If userspace is asynchronously streaming into the batch or other
execobjects, we may not flush those writes along with a change in cache
domain (as there is no change). Therefore those writes may end up in
internal chipset buffers and not visible to the GPU upon execution. We
must issue a flush command or otherwise we encounter incoherency in the
batchbuffers and the GPU executing invalid commands (i.e. hanging) quite
regularly.

v2: Throw a paranoid wmb() into the general flush so that we remain
consistent with before.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90841
Fixes: 1816f9236303 ("drm/i915: Support creation of unbound wc user...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Tested-by: Matti Hämäläinen <ccr@tnsp.org>
Cc: stable@vger.kernel.org
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160818161718.27187-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 35caa9b..a08d259 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3420,6 +3420,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 /* belongs in i915_gem_gtt.h */
 static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv)
 {
+       wmb();
        if (INTEL_GEN(dev_priv) < 6)
                intel_gtt_chipset_flush();
 }

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 6993153..bce587a 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1015,8 +1015,6 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 {
        const unsigned int other_rings = eb_other_engines(req);
        struct i915_vma *vma;
-       uint32_t flush_domains = 0;
-       bool flush_chipset = false;
        int ret;
 
        list_for_each_entry(vma, vmas, exec_list) {
@@ -1029,16 +1027,11 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
                }
 
                if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-                       flush_chipset |= i915_gem_clflush_object(obj, false);
-
-               flush_domains |= obj->base.write_domain;
+                       i915_gem_clflush_object(obj, false);
        }
 
-       if (flush_chipset)
-               i915_gem_chipset_flush(req->engine->i915);
-
-       if (flush_domains & I915_GEM_DOMAIN_GTT)
-               wmb();
+       /* Unconditionally flush any chipset caches (for streaming writes). */
+       i915_gem_chipset_flush(req->engine->i915);
 
        /* Unconditionally invalidate GPU caches and TLBs. */
        return req->engine->emit_flush(req, EMIT_INVALIDATE);