mm: maintain randomization of page free lists

When freeing a page with an order >= shuffle_page_order randomly select
the front or back of the list for insertion.

While the mm tries to defragment physical pages into huge pages this can
tend to make the page allocator more predictable over time.  Inject the
front-back randomness to preserve the initial randomness established by
shuffle_free_memory() when the kernel was booted.

The overhead of this manipulation is constrained by only being applied
for MAX_ORDER sized pages by default.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/154899812788.3165233.9066631950746578517.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Robert Elliott <elliott@hpe.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 44 insertions, 2 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b674625762c4..3b13d3914176 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -43,6 +43,7 @@
 #include <linux/mempolicy.h>
 #include <linux/memremap.h>
 #include <linux/stop_machine.h>
+#include <linux/random.h>
 #include <linux/sort.h>
 #include <linux/pfn.h>
 #include <linux/backing-dev.h>
@@ -958,7 +959,8 @@ done_merging:
 	 * so it's less likely to be used soon and more likely to be merged
 	 * as a higher order page
 	 */
-	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
+	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
+			&& !is_shuffle_order(order)) {
 		struct page *higher_page, *higher_buddy;
 		combined_pfn = buddy_pfn & pfn;
 		higher_page = page + (combined_pfn - pfn);
@@ -972,7 +974,12 @@ done_merging:
 		}
 	}
 
-	add_to_free_area(page, &zone->free_area[order], migratetype);
+	if (is_shuffle_order(order))
+		add_to_free_area_random(page, &zone->free_area[order],
+				migratetype);
+	else
+		add_to_free_area(page, &zone->free_area[order], migratetype);
+
 }
 
 /*
diff --git a/mm/shuffle.c b/mm/shuffle.c
index bc0419a61fbe..3ce12481b1dc 100644
--- a/mm/shuffle.c
+++ b/mm/shuffle.c
@@ -182,3 +182,26 @@ void __meminit __shuffle_free_memory(pg_data_t *pgdat)
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		shuffle_zone(z);
 }
+
+void add_to_free_area_random(struct page *page, struct free_area *area,
+		int migratetype)
+{
+	static u64 rand;
+	static u8 rand_bits;
+
+	/*
+	 * The lack of locking is deliberate. If 2 threads race to
+	 * update the rand state it just adds to the entropy.
+	 */
+	if (rand_bits == 0) {
+		rand_bits = 64;
+		rand = get_random_u64();
+	}
+
+	if (rand & 1)
+		add_to_free_area(page, area, migratetype);
+	else
+		add_to_free_area_tail(page, area, migratetype);
+	rand_bits--;
+	rand >>= 1;
+}
diff --git a/mm/shuffle.h b/mm/shuffle.h
index 644c8ee97b9e..777a257a0d2f 100644
--- a/mm/shuffle.h
+++ b/mm/shuffle.h
@@ -36,6 +36,13 @@ static inline void shuffle_zone(struct zone *z)
 		return;
 	__shuffle_zone(z);
 }
+
+static inline bool is_shuffle_order(int order)
+{
+	if (!static_branch_unlikely(&page_alloc_shuffle_key))
+		return false;
+	return order >= SHUFFLE_ORDER;
+}
 #else
 static inline void shuffle_free_memory(pg_data_t *pgdat)
 {
@@ -48,5 +55,10 @@ static inline void shuffle_zone(struct zone *z)
 static inline void page_alloc_shuffle(enum mm_shuffle_ctl ctl)
 {
 }
+
+static inline bool is_shuffle_order(int order)
+{
+	return false;
+}
 #endif
 #endif /* _MM_SHUFFLE_H */