1 files changed, 37 insertions, 11 deletions

diff --git a/mm/page_counter.c b/mm/page_counter.c
index 0153f5bb3161..b249d15af9dd 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -13,6 +13,11 @@
 #include <linux/bug.h>
 #include <asm/page.h>
 
+static bool track_protection(struct page_counter *c)
+{
+	return c->protection_support;
+}
+
 static void propagate_protected_usage(struct page_counter *c,
 				      unsigned long usage)
 {
@@ -57,7 +62,8 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
 		new = 0;
 		atomic_long_set(&counter->usage, new);
 	}
-	propagate_protected_usage(counter, new);
+	if (track_protection(counter))
+		propagate_protected_usage(counter, new);
 }
 
 /**
@@ -70,18 +76,33 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
 void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
 {
 	struct page_counter *c;
+	bool protection = track_protection(counter);
 
 	for (c = counter; c; c = c->parent) {
 		long new;
 
 		new = atomic_long_add_return(nr_pages, &c->usage);
-		propagate_protected_usage(c, new);
+		if (protection)
+			propagate_protected_usage(c, new);
 		/*
 		 * This is indeed racy, but we can live with some
 		 * inaccuracy in the watermark.
+		 *
+		 * Notably, we have two watermarks to allow for both a globally
+		 * visible peak and one that can be reset at a smaller scope.
+		 *
+		 * Since we reset both watermarks when the global reset occurs,
+		 * we can guarantee that watermark >= local_watermark, so we
+		 * don't need to do both comparisons every time.
+		 *
+		 * On systems with branch predictors, the inner condition should
+		 * be almost free.
 		 */
-		if (new > READ_ONCE(c->watermark))
-			WRITE_ONCE(c->watermark, new);
+		if (new > READ_ONCE(c->local_watermark)) {
+			WRITE_ONCE(c->local_watermark, new);
+			if (new > READ_ONCE(c->watermark))
+				WRITE_ONCE(c->watermark, new);
+		}
 	}
 }
 
@@ -99,6 +120,7 @@ bool page_counter_try_charge(struct page_counter *counter,
 			     struct page_counter **fail)
 {
 	struct page_counter *c;
+	bool protection = track_protection(counter);
 
 	for (c = counter; c; c = c->parent) {
 		long new;
@@ -128,13 +150,15 @@ bool page_counter_try_charge(struct page_counter *counter,
 			*fail = c;
 			goto failed;
 		}
-		propagate_protected_usage(c, new);
-		/*
-		 * Just like with failcnt, we can live with some
-		 * inaccuracy in the watermark.
-		 */
-		if (new > READ_ONCE(c->watermark))
-			WRITE_ONCE(c->watermark, new);
+		if (protection)
+			propagate_protected_usage(c, new);
+
+		/* see comment on page_counter_charge */
+		if (new > READ_ONCE(c->local_watermark)) {
+			WRITE_ONCE(c->local_watermark, new);
+			if (new > READ_ONCE(c->watermark))
+				WRITE_ONCE(c->watermark, new);
+		}
 	}
 	return true;
 
@@ -264,6 +288,7 @@ int page_counter_memparse(const char *buf, const char *max,
 }
 
 
+#ifdef CONFIG_MEMCG
 /*
  * This function calculates an individual page counter's effective
  * protection which is derived from its own memory.min/low, its
@@ -435,3 +460,4 @@ void page_counter_calculate_protection(struct page_counter *root,
 			atomic_long_read(&parent->children_low_usage),
 			recursive_protection));
 }
+#endif /* CONFIG_MEMCG */