[PATCH v2] mm/vmscan: fix data races at kswapd_classzone_idx

[Qian Cai]

pgdat->kswapd_classzone_idx could be accessed concurrently in
wakeup_kswapd(). Plain writes and reads without any lock protection
result in data races. Fix them by adding a pair of READ|WRITE_ONCE() as
well as saving a branch (compilers might well optimize the original code
in an unintentional way anyway). While at it, also take care of
pgdat->kswapd_order and non-kswapd threads in allow_direct_reclaim().
The data races were reported by KCSAN,

 BUG: KCSAN: data-race in wakeup_kswapd / wakeup_kswapd

 write to 0xffff9f427ffff2dc of 4 bytes by task 7454 on cpu 13:
  wakeup_kswapd+0xf1/0x400
  wakeup_kswapd at mm/vmscan.c:3967
  wake_all_kswapds+0x59/0xc0
  wake_all_kswapds at mm/page_alloc.c:4241
  __alloc_pages_slowpath+0xdcc/0x1290
  __alloc_pages_slowpath at mm/page_alloc.c:4512
  __alloc_pages_nodemask+0x3bb/0x450
  alloc_pages_vma+0x8a/0x2c0
  do_anonymous_page+0x16e/0x6f0
  __handle_mm_fault+0xcd5/0xd40
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 1 lock held by mtest01/7454:
  #0: ffff9f425afe8808 (&mm->mmap_sem#2){++++}, at:
 do_page_fault+0x143/0x6f9
 do_user_addr_fault at arch/x86/mm/fault.c:1405
 (inlined by) do_page_fault at arch/x86/mm/fault.c:1539
 irq event stamp: 6944085
 count_memcg_event_mm+0x1a6/0x270
 count_memcg_event_mm+0x119/0x270
 __do_softirq+0x34c/0x57c
 irq_exit+0xa2/0xc0

 read to 0xffff9f427ffff2dc of 4 bytes by task 7472 on cpu 38:
  wakeup_kswapd+0xc8/0x400
  wake_all_kswapds+0x59/0xc0
  __alloc_pages_slowpath+0xdcc/0x1290
  __alloc_pages_nodemask+0x3bb/0x450
  alloc_pages_vma+0x8a/0x2c0
  do_anonymous_page+0x16e/0x6f0
  __handle_mm_fault+0xcd5/0xd40
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 1 lock held by mtest01/7472:
  #0: ffff9f425a9ac148 (&mm->mmap_sem#2){++++}, at:
 do_page_fault+0x143/0x6f9
 irq event stamp: 6793561
 count_memcg_event_mm+0x1a6/0x270
 count_memcg_event_mm+0x119/0x270
 __do_softirq+0x34c/0x57c
 irq_exit+0xa2/0xc0

Signed-off-by: Qian Cai <cai@xxxxxx>
---

v2: use a temp variable and take care of kswapd_order per Matthew.
     take care of allow_direct_reclaim() as well.

 mm/vmscan.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 876370565455..e61cc71b8915 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3136,8 +3136,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
-						(enum zone_type)ZONE_NORMAL);
+		if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
+			WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
 
@@ -3953,20 +3954,23 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 		   enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	enum zone_type curr_idx;
 
 	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
+
 	pgdat = zone->zone_pgdat;
+	curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+
+	if (READ_ONCE(pgdat->kswapd_order) < order)
+		WRITE_ONCE(pgdat->kswapd_order, order);
 
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		pgdat->kswapd_classzone_idx = classzone_idx;
-	else
-		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
-						  classzone_idx);
-	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 
-- 
2.21.0 (Apple Git-122.2)