mm, page_owner: make init_pages_in_zone() faster

In init_pages_in_zone() we currently use the generic set_page_owner()
function to initialize page_owner info for early allocated pages.  This
means we needlessly do lookup_page_ext() twice for each page, and more
importantly save_stack(), which has to unwind the stack and find the
corresponding stack depot handle.  Because the stack is always the same
for the initialization, unwind it once in init_pages_in_zone() and reuse
the handle.  Also avoid the repeated lookup_page_ext().

This can significantly reduce boot times with page_owner=on on large
machines, especially for kernels built without frame pointer, where the
stack unwinding is noticeably slower.

[vbabka@suse.cz: don't duplicate code of __set_page_owner(), per Michal Hocko]
[akpm@linux-foundation.org: coding-style fixes]
[vbabka@suse.cz: create statically allocated fake stack trace for early allocated pages, per Michal]
  Link: http://lkml.kernel.org/r/45813564-2342-fc8d-d31a-f4b68a724325@suse.cz
Link: http://lkml.kernel.org/r/20170720134029.25268-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Yang Shi <yang.shi@linaro.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Cc: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 0fd9dcf..33634f7 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -30,6 +30,7 @@
 
 static depot_stack_handle_t dummy_handle;
 static depot_stack_handle_t failure_handle;
+static depot_stack_handle_t early_handle;
 
 static void init_early_allocated_pages(void);
 
@@ -53,7 +54,7 @@
 	return true;
 }
 
-static noinline void register_dummy_stack(void)
+static __always_inline depot_stack_handle_t create_dummy_stack(void)
 {
 	unsigned long entries[4];
 	struct stack_trace dummy;
@@ -64,21 +65,22 @@
 	dummy.skip = 0;
 
 	save_stack_trace(&dummy);
-	dummy_handle = depot_save_stack(&dummy, GFP_KERNEL);
+	return depot_save_stack(&dummy, GFP_KERNEL);
+}
+
+static noinline void register_dummy_stack(void)
+{
+	dummy_handle = create_dummy_stack();
 }
 
 static noinline void register_failure_stack(void)
 {
-	unsigned long entries[4];
-	struct stack_trace failure;
+	failure_handle = create_dummy_stack();
+}
 
-	failure.nr_entries = 0;
-	failure.max_entries = ARRAY_SIZE(entries);
-	failure.entries = &entries[0];
-	failure.skip = 0;
-
-	save_stack_trace(&failure);
-	failure_handle = depot_save_stack(&failure, GFP_KERNEL);
+static noinline void register_early_stack(void)
+{
+	early_handle = create_dummy_stack();
 }
 
 static void init_page_owner(void)
@@ -88,6 +90,7 @@
 
 	register_dummy_stack();
 	register_failure_stack();
+	register_early_stack();
 	static_branch_enable(&page_owner_inited);
 	init_early_allocated_pages();
 }
@@ -165,17 +168,13 @@
 	return handle;
 }
 
-noinline void __set_page_owner(struct page *page, unsigned int order,
-					gfp_t gfp_mask)
+static inline void __set_page_owner_handle(struct page_ext *page_ext,
+	depot_stack_handle_t handle, unsigned int order, gfp_t gfp_mask)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
 	struct page_owner *page_owner;
 
-	if (unlikely(!page_ext))
-		return;
-
 	page_owner = get_page_owner(page_ext);
-	page_owner->handle = save_stack(gfp_mask);
+	page_owner->handle = handle;
 	page_owner->order = order;
 	page_owner->gfp_mask = gfp_mask;
 	page_owner->last_migrate_reason = -1;
@@ -183,6 +182,19 @@
 	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
 }
 
+noinline void __set_page_owner(struct page *page, unsigned int order,
+					gfp_t gfp_mask)
+{
+	struct page_ext *page_ext = lookup_page_ext(page);
+	depot_stack_handle_t handle;
+
+	if (unlikely(!page_ext))
+		return;
+
+	handle = save_stack(gfp_mask);
+	__set_page_owner_handle(page_ext, handle, order, gfp_mask);
+}
+
 void __set_page_owner_migrate_reason(struct page *page, int reason)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
@@ -565,12 +577,12 @@
 			if (unlikely(!page_ext))
 				continue;
 
-			/* Maybe overraping zone */
+			/* Maybe overlapping zone */
 			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
 				continue;
 
 			/* Found early allocated page */
-			set_page_owner(page, 0, 0);
+			__set_page_owner_handle(page_ext, early_handle, 0, 0);
 			count++;
 		}
 	}