[PATCH] mm, memcg: do not set reclaim_state on soft limit reclaim

[Michal Hocko]

From: Michal Hocko <mhocko@xxxxxxxx>

Adric Blake has noticed[1] the following warning:
[38491.963105] WARNING: CPU: 7 PID: 175 at mm/vmscan.c:245 set_task_reclaim_state+0x1e/0x40
[...]
[38491.963239] Call Trace:
[38491.963246]  mem_cgroup_shrink_node+0x9b/0x1d0
[38491.963250]  mem_cgroup_soft_limit_reclaim+0x10c/0x3a0
[38491.963254]  balance_pgdat+0x276/0x540
[38491.963258]  kswapd+0x200/0x3f0
[38491.963261]  ? wait_woken+0x80/0x80
[38491.963265]  kthread+0xfd/0x130
[38491.963267]  ? balance_pgdat+0x540/0x540
[38491.963269]  ? kthread_park+0x80/0x80
[38491.963273]  ret_from_fork+0x35/0x40
[38491.963276] ---[ end trace 727343df67b2398a ]---

which tells us that soft limit reclaim is about to overwrite the
reclaim_state configured up in the call chain (kswapd in this case but
the direct reclaim is equally possible). This means that reclaim stats
would get misleading once the soft reclaim returns and another reclaim
is done.

Fix the warning by dropping set_task_reclaim_state from the soft reclaim
which is always called with reclaim_state set up.

Reported-by: Adric Blake <promarbler14@xxxxxxxxx>
Acked-by: Yafang Shao <laoar.shao@xxxxxxxxx>
Acked-by: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>

[1] http://lkml.kernel.org/r/CAE1jjeePxYPvw1mw2B3v803xHVR_BNnz0hQUY_JDMN8ny29M6w@xxxxxxxxxxxxxx
---
 mm/vmscan.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c77d1e3761a7..a6c5d0b28321 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3220,6 +3220,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 
 #ifdef CONFIG_MEMCG
 
+/* Only used by soft limit reclaim. Do not reuse for anything else. */
 unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,
@@ -3235,7 +3236,8 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 	};
 	unsigned long lru_pages;
 
-	set_task_reclaim_state(current, &sc.reclaim_state);
+	WARN_ON_ONCE(!current->reclaim_state);
+
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 
@@ -3253,7 +3255,6 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
-	set_task_reclaim_state(current, NULL);
 	*nr_scanned = sc.nr_scanned;
 
 	return sc.nr_reclaimed;
-- 
2.20.1