From edef7e685da05c13cce50c0126189c80fe2c8f71 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 14 Sep 2012 11:57:47 +0100 Subject: [PATCH] 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 Signed-off-by: Daniel Vetter --- drivers/char/agp/intel-gtt.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index 7fa655a..e01f5ea 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/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; -- 2.7.4