drm/i915: swizzling support for snb/ivb

We have to do this manually. Somebody had a Great Idea.

I've measured speed-ups just a few percent above the noise level
(below 5% for the best case), but no slowdows. Chris Wilson measured
quite a bit more (10-20% above the usual snb variance) on a more
recent and better tuned version of sna, but also recorded a few
slow-downs on benchmarks know for uglier amounts of snb-induced
variance.

v2: Incorporate Ben Widawsky's preliminary review comments and
elaborate a bit about the performance impact in the changelog.

v3: Add a comment as to why we don't need to check the 3rd memory
channel.

v4: Fixup whitespace.

Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 51a2b0c..86fffd2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3681,12 +3681,31 @@
 	return 0;
 }
 
+void i915_gem_init_swizzling(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	if (INTEL_INFO(dev)->gen < 6 ||
+	    dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
+		return;
+
+	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+				 DISP_TILE_SURFACE_SWIZZLING);
+
+	I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_SWZCTL);
+	if (IS_GEN6(dev))
+		I915_WRITE(ARB_MODE, ARB_MODE_ENABLE(ARB_MODE_SWIZZLE_SNB));
+	else
+		I915_WRITE(ARB_MODE, ARB_MODE_ENABLE(ARB_MODE_SWIZZLE_IVB));
+}
 int
-i915_gem_init_ringbuffer(struct drm_device *dev)
+i915_gem_init_hw(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	int ret;
 
+	i915_gem_init_swizzling(dev);
+
 	ret = intel_init_render_ring_buffer(dev);
 	if (ret)
 		return ret;
@@ -3742,7 +3761,7 @@
 	mutex_lock(&dev->struct_mutex);
 	dev_priv->mm.suspended = 0;
 
-	ret = i915_gem_init_ringbuffer(dev);
+	ret = i915_gem_init_hw(dev);
 	if (ret != 0) {
 		mutex_unlock(&dev->struct_mutex);
 		return ret;