drm/i915: optimise i915_gem_object_map() for small objects

We're using this function for ringbuffers and other "small" objects, so
it's worth avoiding an extra malloc()/free() cycle if the page array is
small enough to put on the stack. Here we've chosen an arbitrary cutoff
of 32 (4k) pages, which is big enough for a ringbuffer (4 pages) or a
context image (currently up to 22 pages).

v5:
    change name of local array [Chris Wilson]

Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1463741647-15666-3-git-send-email-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f504c3168da5e3cc5f8ac90721cd627f0ddfb095..fd3be2b385cb751a3057ea895f1fe3403d92ac5b 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2404,7 +2404,8 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
        unsigned long n_pages = obj->base.size >> PAGE_SHIFT;
        struct sg_table *sgt = obj->pages;
        struct sg_page_iter sg_iter;
-       struct page **pages;
+       struct page *stack_pages[32];
+       struct page **pages = stack_pages;
        unsigned long i = 0;
        void *addr;
 
@@ -2412,9 +2413,12 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
        if (n_pages == 1)
                return kmap(sg_page(sgt->sgl));
 
-       pages = drm_malloc_gfp(n_pages, sizeof(*pages), GFP_TEMPORARY);
-       if (!pages)
-               return NULL;
+       if (n_pages > ARRAY_SIZE(stack_pages)) {
+               /* Too big for stack -- allocate temporary array instead */
+               pages = drm_malloc_gfp(n_pages, sizeof(*pages), GFP_TEMPORARY);
+               if (!pages)
+                       return NULL;
+       }
 
        for_each_sg_page(sgt->sgl, &sg_iter, sgt->nents, 0)
                pages[i++] = sg_page_iter_page(&sg_iter);
@@ -2424,7 +2428,8 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
 
        addr = vmap(pages, n_pages, 0, PAGE_KERNEL);
 
-       drm_free_large(pages);
+       if (pages != stack_pages)
+               drm_free_large(pages);
 
        return addr;
 }