drm/i915: Trim the object sg table

tursulin · tursulin · commit 0c40ce130e38 · 2016-11-10T09:29:25.000Z
At the moment we allocate enough sg table entries assuming we will not be able to do any coalescing. But since in practice we most often can, and more so very effectively, this ends up wasting a lot of memory. A simple and effective way of trimming the over-allocated entries is to copy the table over to a new one allocated to the exact size. Experiments on my freshly logged and idle desktop (KDE) showed that by doing this we can save approximately 1 MiB of RAM, or when running a typical benchmark like gl_manhattan I have even seen a 6 MiB saving. More complicated techniques such as only copying the last used page and freeing the rest are left to the reader. v2: * Update commit message. * Use temporary sg_table on stack. (Chris Wilson) v3: * Commit message update. * Comment added. * Replace memcpy with copy assignment. (Chris Wilson) Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Link: http://patchwork.freedesktop.org/patch/msgid/1478704423-7447-1-git-send-email-tvrtko.ursulin@linux.intel.com
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
@@ -2232,6 +2232,30 @@ static unsigned int swiotlb_max_size(void)
 #endif
 }
 
+static void i915_sg_trim(struct sg_table *orig_st)
+{
+	struct sg_table new_st;
+	struct scatterlist *sg, *new_sg;
+	unsigned int i;
+
+	if (orig_st->nents == orig_st->orig_nents)
+		return;
+
+	if (sg_alloc_table(&new_st, orig_st->nents, GFP_KERNEL))
+		return;
+
+	new_sg = new_st.sgl;
+	for_each_sg(orig_st->sgl, sg, orig_st->nents, i) {
+		sg_set_page(new_sg, sg_page(sg), sg->length, 0);
+		/* called before being DMA mapped, no need to copy sg->dma_* */
+		new_sg = sg_next(new_sg);
+	}
+
+	sg_free_table(orig_st);
+
+	*orig_st = new_st;
+}
+
 static struct sg_table *
 i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 {
@@ -2317,6 +2341,9 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	if (sg) /* loop terminated early; short sg table */
 		sg_mark_end(sg);
 
+	/* Trim unused sg entries to avoid wasting memory. */
+	i915_sg_trim(st);
+
 	ret = i915_gem_gtt_prepare_pages(obj, st);
 	if (ret)
 		goto err_pages;
