drm/i915: Batch copy_from_user for relocation processing

Originally the code tried to allocate a large enough array to perform
the copy using vmalloc, performance wasn't great and throughput was
improved by processing each individual relocation entry separately.
This too is not as efficient as one would desire. A compromise would be
to allocate a single page, or to allocate a few entries on the stack,
and process the copy in batches. The latter gives simpler code and more
consistent performance due to a lack of heuristic.

x11perf -copywinwin10:	n450/pnv	i3-330m		i5-2520m (cpu)
               before: 	  249000	 785000		 1280000 (80%)
                 page:	  264000	 896000		 1280000 (65%)
             on-stack:	  264000	 902000		 1280000 (67%)

v2: Use 512-bytes of stack for batching rather than allocate a page.
v3: Tidy the code slightly with more descriptive variable names
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -405,30 +405,46 @@ static int
 i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
 				    struct eb_objects *eb)
 {
+#define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
+	struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)];
 	struct drm_i915_gem_relocation_entry __user *user_relocs;
 	struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
-	int i, ret;
+	int remain, ret;
 
 	user_relocs = (void __user *)(uintptr_t)entry->relocs_ptr;
-	for (i = 0; i < entry->relocation_count; i++) {
-		struct drm_i915_gem_relocation_entry reloc;
 
-		if (__copy_from_user_inatomic(&reloc,
-					      user_relocs+i,
-					      sizeof(reloc)))
+	remain = entry->relocation_count;
+	while (remain) {
+		struct drm_i915_gem_relocation_entry *r = stack_reloc;
+		int count = remain;
+		if (count > ARRAY_SIZE(stack_reloc))
+			count = ARRAY_SIZE(stack_reloc);
+		remain -= count;
+
+		if (__copy_from_user_inatomic(r, user_relocs, count*sizeof(r[0])))
 			return -EFAULT;
 
-		ret = i915_gem_execbuffer_relocate_entry(obj, eb, &reloc);
+		do {
+			u64 offset = r->presumed_offset;
+
+			ret = i915_gem_execbuffer_relocate_entry(obj, eb, r);
 			if (ret)
 				return ret;
 
-		if (__copy_to_user_inatomic(&user_relocs[i].presumed_offset,
-					    &reloc.presumed_offset,
-					    sizeof(reloc.presumed_offset)))
+			if (r->presumed_offset != offset &&
+			    __copy_to_user_inatomic(&user_relocs->presumed_offset,
+						    &r->presumed_offset,
+						    sizeof(r->presumed_offset))) {
 				return -EFAULT;
 			}
 
+			user_relocs++;
+			r++;
+		} while (--count);
+	}
+
 	return 0;
+#undef N_RELOC
 }
 
 static int