mm: batch activate_page() to reduce lock contention

The zone->lru_lock is heavily contented in workload where activate_page()
is frequently used. We could do batch activate_page() to reduce the lock
contention. The batched pages will be added into zone list when the pool
is full or page reclaim is trying to drain them.

For example, in a 4 socket 64 CPU system, create a sparse file and 64
processes, processes shared map to the file. Each process read access the
whole file and then exit. The process exit will do unmap_vmas() and cause
a lot of activate_page() call. In such workload, we saw about 58% total
time reduction with below patch. Other workloads with a lot of
activate_page also benefits a lot too.

I tested some microbenchmarks:
case-anon-cow-rand-mt 0.58%
case-anon-cow-rand -3.30%
case-anon-cow-seq-mt -0.51%
case-anon-cow-seq -5.68%
case-anon-r-rand-mt 0.23%
case-anon-r-rand 0.81%
case-anon-r-seq-mt -0.71%
case-anon-r-seq -1.99%
case-anon-rx-rand-mt 2.11%
case-anon-rx-seq-mt 3.46%
case-anon-w-rand-mt -0.03%
case-anon-w-rand -0.50%
case-anon-w-seq-mt -1.08%
case-anon-w-seq -0.12%
case-anon-wx-rand-mt -5.02%
case-anon-wx-seq-mt -1.43%
case-fork 1.65%
case-fork-sleep -0.07%
case-fork-withmem 1.39%
case-hugetlb -0.59%
case-lru-file-mmap-read-mt -0.54%
case-lru-file-mmap-read 0.61%
case-lru-file-mmap-read-rand -2.24%
case-lru-file-readonce -0.64%
case-lru-file-readtwice -11.69%
case-lru-memcg -1.35%
case-mmap-pread-rand-mt 1.88%
case-mmap-pread-rand -15.26%
case-mmap-pread-seq-mt 0.89%
case-mmap-pread-seq -69.72%
case-mmap-xread-rand-mt 0.71%
case-mmap-xread-seq-mt 0.38%

The most significent are:
case-lru-file-readtwice -11.69%
case-mmap-pread-rand -15.26%
case-mmap-pread-seq -69.72%

which use activate_page a lot. others are basically variations because
each run has slightly difference.

[[e-mail]: coding-style fixes]
Signed-off-by: Shaohua Li <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Minchan Kim <[e-mail]>
Cc: KOSAKI Motohiro <[e-mail]>
Cc: Rik van Riel <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

mm/internal.h

···
 
 extern unsigned long highest_memmap_pfn;
 
+#ifdef CONFIG_SMP
+extern int putback_active_lru_page(struct zone *zone, struct page *page);
+#else
+static inline int putback_active_lru_page(struct zone *zone, struct page *page)
+{
+	return 0;
+}
+#endif
+
 /*
  * in mm/vmscan.c:
  */

mm/swap.c

···
 }
 
 /*
- * FIXME: speed this up?
+ * A page will go to active list either by activate_page or putback_lru_page.
+ * In the activate_page case, the page hasn't active bit set. The page might
+ * not in LRU list because it's isolated before it gets a chance to be moved to
+ * active list. The window is small because pagevec just stores several pages.
+ * For such case, we do nothing for such page.
+ * In the putback_lru_page case, the page isn't in lru list but has active
+ * bit set
  */
+static void __activate_page(struct page *page, void *arg)
+{
+	struct zone *zone = page_zone(page);
+	int file = page_is_file_cache(page);
+	int lru = page_lru_base_type(page);
+	bool putback = !PageLRU(page);
+
+	/* The page is isolated before it's moved to active list */
+	if (!PageLRU(page) && !PageActive(page))
+		return;
+	if ((PageLRU(page) && PageActive(page)) || PageUnevictable(page))
+		return;
+
+	if (!putback)
+		del_page_from_lru_list(zone, page, lru);
+	else
+		SetPageLRU(page);
+
+	SetPageActive(page);
+	lru += LRU_ACTIVE;
+	add_page_to_lru_list(zone, page, lru);
+
+	if (putback)
+		return;
+	__count_vm_event(PGACTIVATE);
+	update_page_reclaim_stat(zone, page, file, 1);
+}
+
+#ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
+
+static void activate_page_drain(int cpu)
+{
+	struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
+
+	if (pagevec_count(pvec))
+		pagevec_lru_move_fn(pvec, __activate_page, NULL);
+}
+
+void activate_page(struct page *page)
+{
+	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+
+		page_cache_get(page);
+		if (!pagevec_add(pvec, page))
+			pagevec_lru_move_fn(pvec, __activate_page, NULL);
+		put_cpu_var(activate_page_pvecs);
+	}
+}
+
+/* Caller should hold zone->lru_lock */
+int putback_active_lru_page(struct zone *zone, struct page *page)
+{
+	struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+
+	if (!pagevec_add(pvec, page)) {
+		spin_unlock_irq(&zone->lru_lock);
+		pagevec_lru_move_fn(pvec, __activate_page, NULL);
+		spin_lock_irq(&zone->lru_lock);
+	}
+	put_cpu_var(activate_page_pvecs);
+	return 1;
+}
+
+#else
+static inline void activate_page_drain(int cpu)
+{
+}
+
 void activate_page(struct page *page)
 {
 	struct zone *zone = page_zone(page);
 
 	spin_lock_irq(&zone->lru_lock);
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-		int file = page_is_file_cache(page);
-		int lru = page_lru_base_type(page);
-		del_page_from_lru_list(zone, page, lru);
-
-		SetPageActive(page);
-		lru += LRU_ACTIVE;
-		add_page_to_lru_list(zone, page, lru);
-		__count_vm_event(PGACTIVATE);
-
-		update_page_reclaim_stat(zone, page, file, 1);
-	}
+	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page))
+		__activate_page(page, NULL);
 	spin_unlock_irq(&zone->lru_lock);
 }
+#endif
 
 /*
  * Mark a page as having seen activity.
···
 		pagevec_move_tail(pvec);
 		local_irq_restore(flags);
 	}
+	activate_page_drain(cpu);
 }
 
 void lru_add_drain(void)

mm/vmscan.c

···
 			spin_lock_irq(&zone->lru_lock);
 			continue;
 		}
-		SetPageLRU(page);
 		lru = page_lru(page);
-		add_page_to_lru_list(zone, page, lru);
 		if (is_active_lru(lru)) {
 			int file = is_file_lru(lru);
 			int numpages = hpage_nr_pages(page);
 			reclaim_stat->recent_rotated[file] += numpages;
+			if (putback_active_lru_page(zone, page))
+				continue;
 		}
+		SetPageLRU(page);
+		add_page_to_lru_list(zone, page, lru);
 		if (!pagevec_add(&pvec, page)) {
 			spin_unlock_irq(&zone->lru_lock);
 			__pagevec_release(&pvec);