From b90b91d87038f6b257b40a02b42ed4f9705e06f0 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 10 Jun 2014 12:14:40 +0100 Subject: [PATCH] drm/i915: Prefault the entire object on first page fault Inserting additional PTEs has no side-effect for us as the pfn are fixed for the entire time the object is resident in the global GTT. The downside is that we pay the entire cost of faulting the object upon the first hit, for which we in return receive the benefit of removing the per-page faulting overhead. On an Ivybridge i7-3720qm with 1600MHz DDR3, with 32 fences, Upload rate for 2 linear surfaces: 8127MiB/s -> 8134MiB/s Upload rate for 2 tiled surfaces: 8607MiB/s -> 8625MiB/s Upload rate for 4 linear surfaces: 8127MiB/s -> 8127MiB/s Upload rate for 4 tiled surfaces: 8611MiB/s -> 8602MiB/s Upload rate for 8 linear surfaces: 8114MiB/s -> 8124MiB/s Upload rate for 8 tiled surfaces: 8601MiB/s -> 8603MiB/s Upload rate for 16 linear surfaces: 8110MiB/s -> 8123MiB/s Upload rate for 16 tiled surfaces: 8595MiB/s -> 8606MiB/s Upload rate for 32 linear surfaces: 8104MiB/s -> 8121MiB/s Upload rate for 32 tiled surfaces: 8589MiB/s -> 8605MiB/s Upload rate for 64 linear surfaces: 8107MiB/s -> 8121MiB/s Upload rate for 64 tiled surfaces: 2013MiB/s -> 3017MiB/s Signed-off-by: Chris Wilson Cc: "Goel, Akash" Testcasee: igt/gem_fence_upload/performance Reviewed-by: Brad Volkin Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3768199f5311..c313cb2b641b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1561,14 +1561,26 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto unpin; - obj->fault_mappable = true; - + /* Finally, remap it using the new GTT offset */ pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj); pfn >>= PAGE_SHIFT; - pfn += page_offset; - /* Finally, remap it using the new GTT offset */ - ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn); + if (!obj->fault_mappable) { + int i; + + for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) { + ret = vm_insert_pfn(vma, + (unsigned long)vma->vm_start + i * PAGE_SIZE, + pfn + i); + if (ret) + break; + } + + obj->fault_mappable = true; + } else + ret = vm_insert_pfn(vma, + (unsigned long)vmf->virtual_address, + pfn + page_offset); unpin: i915_gem_object_ggtt_unpin(obj); unlock: -- 2.34.1