drm/i915: Cache last obj->pages location for i915_gem_object_get_page()

The biggest user of i915_gem_object_get_page() is the relocation
processing during execbuffer. Typically userspace passes in a set of
relocations in sorted order. Sadly, we alternate between relocations
increasing from the start of the buffers, and relocations decreasing
from the end. However the majority of consecutive lookups will still be
in the same page. We could cache the start of the last sg chain, however
for most callers, the entire sgl is inside a single chain and so we see
no improve from the extra layer of caching.

v2: Avoid the double increment inside unlikely()

References: https://bugs.freedesktop.org/show_bug.cgi?id=88308
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d5b21153f200c6cdaab08c8c9e45d4e3759cd9da..924676fdb26f1eb3ee8beb32f785a9c2e8d4cfd9 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1986,6 +1986,10 @@ struct drm_i915_gem_object {
 
        struct sg_table *pages;
        int pages_pin_count;
+       struct get_page {
+               struct scatterlist *sg;
+               int last;
+       } get_page;
 
        /* prime dma-buf support */
        void *dma_buf_vmapping;
@@ -2656,15 +2660,32 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
                                    int *needs_clflush);
 
 int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
-static inline struct page *i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
+
+static inline int __sg_page_count(struct scatterlist *sg)
+{
+       return sg->length >> PAGE_SHIFT;
+}
+
+static inline struct page *
+i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
 {
-       struct sg_page_iter sg_iter;
+       if (WARN_ON(n >= obj->base.size >> PAGE_SHIFT))
+               return NULL;
 
-       for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, n)
-               return sg_page_iter_page(&sg_iter);
+       if (n < obj->get_page.last) {
+               obj->get_page.sg = obj->pages->sgl;
+               obj->get_page.last = 0;
+       }
+
+       while (obj->get_page.last + __sg_page_count(obj->get_page.sg) <= n) {
+               obj->get_page.last += __sg_page_count(obj->get_page.sg++);
+               if (unlikely(sg_is_chain(obj->get_page.sg)))
+                       obj->get_page.sg = sg_chain_ptr(obj->get_page.sg);
+       }
 
-       return NULL;
+       return nth_page(sg_page(obj->get_page.sg), n - obj->get_page.last);
 }
+
 static inline void i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
 {
        BUG_ON(obj->pages == NULL);

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 267fdf0f46ae7b7b5808c2a7a8dd9d910f63b37b..976d27a191925d2191adb9de29a8ed90938602c9 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2178,6 +2178,10 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
                return ret;
 
        list_add_tail(&obj->global_list, &dev_priv->mm.unbound_list);
+
+       obj->get_page.sg = obj->pages->sgl;
+       obj->get_page.last = 0;
+
        return 0;
 }