agp/intel: Use a write-combining map for updating PTEs

Rewriting the PTE entries using an WC mapping is roughly an order of
magnitude faster than through the uncached mapping. This makes an
observable difference on workloads that cycle through large numbers of
buffers, for example Chromium using ShmPixmaps where virtually all the
CPU time is currently spent rebinding the userptr.

v2: Limit the WC mapping to older generations as we have observed that
the TLB invalidation on SandyBridge+ is unreliable with WC updates.
See i-g-t/tests/gem_gtt_cpu_tlb
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/char/agp/intel-gtt.c

@@ -666,9 +666,14 @@ static int intel_gtt_init(void)
 
 	gtt_map_size = intel_private.base.gtt_total_entries * 4;
 
-	intel_private.gtt = ioremap(intel_private.gtt_bus_addr,
-				    gtt_map_size);
-	if (!intel_private.gtt) {
+	intel_private.gtt = NULL;
+	if (INTEL_GTT_GEN < 6)
+		intel_private.gtt = ioremap_wc(intel_private.gtt_bus_addr,
+					       gtt_map_size);
+	if (intel_private.gtt == NULL)
+		intel_private.gtt = ioremap(intel_private.gtt_bus_addr,
+					    gtt_map_size);
+	if (intel_private.gtt == NULL) {
 		intel_private.driver->cleanup();
 		iounmap(intel_private.registers);
 		return -ENOMEM;