1 files changed, 62 insertions, 23 deletions

diff --git a/mm/swap.c b/mm/swap.c
index d16d65d9b4e0..47a47681c86b 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -348,7 +348,7 @@ static bool need_activate_page_drain(int cpu)
 	return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
 }
 
-void activate_page(struct page *page)
+static void activate_page(struct page *page)
 {
 	page = compound_head(page);
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
@@ -368,7 +368,7 @@ static inline void activate_page_drain(int cpu)
 {
 }
 
-void activate_page(struct page *page)
+static void activate_page(struct page *page)
 {
 	pg_data_t *pgdat = page_pgdat(page);
 
@@ -481,9 +481,7 @@ EXPORT_SYMBOL(lru_cache_add);
  * @vma:   vma in which page is mapped for determining reclaimability
  *
  * Place @page on the inactive or unevictable LRU list, depending on its
- * evictability.  Note that if the page is not evictable, it goes
- * directly back onto it's zone's unevictable list, it does NOT use a
- * per cpu pagevec.
+ * evictability.
  */
 void lru_cache_add_inactive_or_unevictable(struct page *page,
 					 struct vm_area_struct *vma)
@@ -494,14 +492,14 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
 
 	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
 	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
+		int nr_pages = thp_nr_pages(page);
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
 		 * lock is held(spinlock), which implies preemption disabled.
 		 */
-		__mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    thp_nr_pages(page));
-		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		__mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
+		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
 	}
 	lru_cache_add(page);
 }
@@ -763,10 +761,20 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
  */
 void lru_add_drain_all(void)
 {
-	static seqcount_t seqcount = SEQCNT_ZERO(seqcount);
-	static DEFINE_MUTEX(lock);
+	/*
+	 * lru_drain_gen - Global pages generation number
+	 *
+	 * (A) Definition: global lru_drain_gen = x implies that all generations
+	 *     0 < n <= x are already *scheduled* for draining.
+	 *
+	 * This is an optimization for the highly-contended use case where a
+	 * user space workload keeps constantly generating a flow of pages for
+	 * each CPU.
+	 */
+	static unsigned int lru_drain_gen;
 	static struct cpumask has_work;
-	int cpu, seq;
+	static DEFINE_MUTEX(lock);
+	unsigned cpu, this_gen;
 
 	/*
 	 * Make sure nobody triggers this path before mm_percpu_wq is fully
@@ -775,21 +783,54 @@ void lru_add_drain_all(void)
 	if (WARN_ON(!mm_percpu_wq))
 		return;
 
-	seq = raw_read_seqcount_latch(&seqcount);
+	/*
+	 * Guarantee pagevec counter stores visible by this CPU are visible to
+	 * other CPUs before loading the current drain generation.
+	 */
+	smp_mb();
+
+	/*
+	 * (B) Locally cache global LRU draining generation number
+	 *
+	 * The read barrier ensures that the counter is loaded before the mutex
+	 * is taken. It pairs with smp_mb() inside the mutex critical section
+	 * at (D).
+	 */
+	this_gen = smp_load_acquire(&lru_drain_gen);
 
 	mutex_lock(&lock);
 
 	/*
-	 * Piggyback on drain started and finished while we waited for lock:
-	 * all pages pended at the time of our enter were drained from vectors.
+	 * (C) Exit the draining operation if a newer generation, from another
+	 * lru_add_drain_all(), was already scheduled for draining. Check (A).
 	 */
-	if (__read_seqcount_retry(&seqcount, seq))
+	if (unlikely(this_gen != lru_drain_gen))
 		goto done;
 
-	raw_write_seqcount_latch(&seqcount);
+	/*
+	 * (D) Increment global generation number
+	 *
+	 * Pairs with smp_load_acquire() at (B), outside of the critical
+	 * section. Use a full memory barrier to guarantee that the new global
+	 * drain generation number is stored before loading pagevec counters.
+	 *
+	 * This pairing must be done here, before the for_each_online_cpu loop
+	 * below which drains the page vectors.
+	 *
+	 * Let x, y, and z represent some system CPU numbers, where x < y < z.
+	 * Assume CPU #z is is in the middle of the for_each_online_cpu loop
+	 * below and has already reached CPU #y's per-cpu data. CPU #x comes
+	 * along, adds some pages to its per-cpu vectors, then calls
+	 * lru_add_drain_all().
+	 *
+	 * If the paired barrier is done at any later step, e.g. after the
+	 * loop, CPU #x will just exit at (C) and miss flushing out all of its
+	 * added pages.
+	 */
+	WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1);
+	smp_mb();
 
 	cpumask_clear(&has_work);
-
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
@@ -801,7 +842,7 @@ void lru_add_drain_all(void)
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
-			cpumask_set_cpu(cpu, &has_work);
+			__cpumask_set_cpu(cpu, &has_work);
 		}
 	}
 
@@ -816,7 +857,7 @@ void lru_add_drain_all(void)
 {
 	lru_add_drain();
 }
-#endif
+#endif /* CONFIG_SMP */
 
 /**
  * release_pages - batched put_page()
@@ -848,6 +889,7 @@ void release_pages(struct page **pages, int nr)
 			locked_pgdat = NULL;
 		}
 
+		page = compound_head(page);
 		if (is_huge_zero_page(page))
 			continue;
 
@@ -859,7 +901,7 @@ void release_pages(struct page **pages, int nr)
 			}
 			/*
 			 * ZONE_DEVICE pages that return 'false' from
-			 * put_devmap_managed_page() do not require special
+			 * page_is_devmap_managed() do not require special
 			 * processing, and instead, expect a call to
 			 * put_page_testzero().
 			 */
@@ -869,7 +911,6 @@ void release_pages(struct page **pages, int nr)
 			}
 		}
 
-		page = compound_head(page);
 		if (!put_page_testzero(page))
 			continue;
 
@@ -900,8 +941,6 @@ void release_pages(struct page **pages, int nr)
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		}
 
-		/* Clear Active bit in case of parallel mark_page_accessed */
-		__ClearPageActive(page);
 		__ClearPageWaiters(page);
 
 		list_add(&page->lru, &pages_to_free);