mm, memcg: fix the active list aging for lowmem requests when memcg is enabled

Nils Holland and Klaus Ethgen have reported unexpected OOM killer
invocations with 32b kernel starting with 4.8 kernels

	kworker/u4:5 invoked oom-killer: gfp_mask=0x2400840(GFP_NOFS|__GFP_NOFAIL), nodemask=0, order=0, oom_score_adj=0
	kworker/u4:5 cpuset=/ mems_allowed=0
	CPU: 1 PID: 2603 Comm: kworker/u4:5 Not tainted 4.9.0-gentoo #2
	[...]
	Mem-Info:
	active_anon:58685 inactive_anon:90 isolated_anon:0
	 active_file:274324 inactive_file:281962 isolated_file:0
	 unevictable:0 dirty:649 writeback:0 unstable:0
	 slab_reclaimable:40662 slab_unreclaimable:17754
	 mapped:7382 shmem:202 pagetables:351 bounce:0
	 free:206736 free_pcp:332 free_cma:0
	Node 0 active_anon:234740kB inactive_anon:360kB active_file:1097296kB inactive_file:1127848kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:29528kB dirty:2596kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 184320kB anon_thp: 808kB writeback_tmp:0kB unstable:0kB pages_scanned:0 all_unreclaimable? no
	DMA free:3952kB min:788kB low:984kB high:1180kB active_anon:0kB inactive_anon:0kB active_file:7316kB inactive_file:0kB unevictable:0kB writepending:96kB present:15992kB managed:15916kB mlocked:0kB slab_reclaimable:3200kB slab_unreclaimable:1408kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
	lowmem_reserve[]: 0 813 3474 3474
	Normal free:41332kB min:41368kB low:51708kB high:62048kB active_anon:0kB inactive_anon:0kB active_file:532748kB inactive_file:44kB unevictable:0kB writepending:24kB present:897016kB managed:836248kB mlocked:0kB slab_reclaimable:159448kB slab_unreclaimable:69608kB kernel_stack:1112kB pagetables:1404kB bounce:0kB free_pcp:528kB local_pcp:340kB free_cma:0kB
	lowmem_reserve[]: 0 0 21292 21292
	HighMem free:781660kB min:512kB low:34356kB high:68200kB active_anon:234740kB inactive_anon:360kB active_file:557232kB inactive_file:1127804kB unevictable:0kB writepending:2592kB present:2725384kB managed:2725384kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:800kB local_pcp:608kB free_cma:0kB

the oom killer is clearly pre-mature because there there is still a lot
of page cache in the zone Normal which should satisfy this lowmem
request.  Further debugging has shown that the reclaim cannot make any
forward progress because the page cache is hidden in the active list
which doesn't get rotated because inactive_list_is_low is not memcg
aware.

The code simply subtracts per-zone highmem counters from the respective
memcg's lru sizes which doesn't make any sense.  We can simply end up
always seeing the resulting active and inactive counts 0 and return
false.  This issue is not limited to 32b kernels but in practice the
effect on systems without CONFIG_HIGHMEM would be much harder to notice
because we do not invoke the OOM killer for allocations requests
targeting < ZONE_NORMAL.

Fix the issue by tracking per zone lru page counts in mem_cgroup_per_node
and subtract per-memcg highmem counts when memcg is enabled.  Introduce
helper lruvec_zone_lru_size which redirects to either zone counters or
mem_cgroup_get_zone_lru_size when appropriate.

We are losing empty LRU but non-zero lru size detection introduced by
ca707239e8a7 ("mm: update_lru_size warn and reset bad lru_size") because
of the inherent zone vs. node discrepancy.

Fixes: f8d1a31163fc ("mm: consider whether to decivate based on eligible zones inactive ratio")
Link: http://lkml.kernel.org/r/20170104100825.3729-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Nils Holland <nholland@tisys.org>
Tested-by: Nils Holland <nholland@tisys.org>
Reported-by: Klaus Ethgen <Klaus@Ethgen.de>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: <stable@vger.kernel.org>	[4.8+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 61d20c17f3b7e40ba706a49da463c2f9eabd7d93..254698856b8fc2723dae61e3dd20b6c8176129e7 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -120,7 +120,7 @@ struct mem_cgroup_reclaim_iter {
  */
 struct mem_cgroup_per_node {
        struct lruvec           lruvec;
-       unsigned long           lru_size[NR_LRU_LISTS];
+       unsigned long           lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
        struct mem_cgroup_reclaim_iter  iter[DEF_PRIORITY + 1];
 
@@ -432,7 +432,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
-               int nr_pages);
+               int zid, int nr_pages);
 
 unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
                                           int nid, unsigned int lru_mask);
@@ -441,9 +441,23 @@ static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
        struct mem_cgroup_per_node *mz;
+       unsigned long nr_pages = 0;
+       int zid;
 
        mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-       return mz->lru_size[lru];
+       for (zid = 0; zid < MAX_NR_ZONES; zid++)
+               nr_pages += mz->lru_zone_size[zid][lru];
+       return nr_pages;
+}
+
+static inline
+unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
+               enum lru_list lru, int zone_idx)
+{
+       struct mem_cgroup_per_node *mz;
+
+       mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+       return mz->lru_zone_size[zone_idx][lru];
 }
 
 void mem_cgroup_handle_over_high(void);
@@ -671,6 +685,12 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
        return 0;
 }
+static inline
+unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
+               enum lru_list lru, int zone_idx)
+{
+       return 0;
+}
 
 static inline unsigned long
 mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 71613e8a720f99b6870f1e3f8957d2761a6ac1a0..41d376e7116dccae22d9881312cfb660cd9fd58e 100644 (file)
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -39,7 +39,7 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
 {
        __update_lru_size(lruvec, lru, zid, nr_pages);
 #ifdef CONFIG_MEMCG
-       mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
+       mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
 #endif
 }
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4048897e7b01a6e5e82333c0852629eded927ff3..a63a8f8326647b92bdc63810c8a93be96047f748 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -625,8 +625,8 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
                                           int nid, unsigned int lru_mask)
 {
+       struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
        unsigned long nr = 0;
-       struct mem_cgroup_per_node *mz;
        enum lru_list lru;
 
        VM_BUG_ON((unsigned)nid >= nr_node_ids);
@@ -634,8 +634,7 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
        for_each_lru(lru) {
                if (!(BIT(lru) & lru_mask))
                        continue;
-               mz = mem_cgroup_nodeinfo(memcg, nid);
-               nr += mz->lru_size[lru];
+               nr += mem_cgroup_get_lru_size(lruvec, lru);
        }
        return nr;
 }
@@ -1002,6 +1001,7 @@ out:
  * mem_cgroup_update_lru_size - account for adding or removing an lru page
  * @lruvec: mem_cgroup per zone lru vector
  * @lru: index of lru list the page is sitting on
+ * @zid: zone id of the accounted pages
  * @nr_pages: positive when adding or negative when removing
  *
  * This function must be called under lru_lock, just before a page is added
@@ -1009,27 +1009,25 @@ out:
  * so as to allow it to check that lru_size 0 is consistent with list_empty).
  */
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
-                               int nr_pages)
+                               int zid, int nr_pages)
 {
        struct mem_cgroup_per_node *mz;
        unsigned long *lru_size;
        long size;
-       bool empty;
 
        if (mem_cgroup_disabled())
                return;
 
        mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-       lru_size = mz->lru_size + lru;
-       empty = list_empty(lruvec->lists + lru);
+       lru_size = &mz->lru_zone_size[zid][lru];
 
        if (nr_pages < 0)
                *lru_size += nr_pages;
 
        size = *lru_size;
-       if (WARN_ONCE(size < 0 || empty != !size,
-               "%s(%p, %d, %d): lru_size %ld but %sempty\n",
-               __func__, lruvec, lru, nr_pages, size, empty ? "" : "not ")) {
+       if (WARN_ONCE(size < 0,
+               "%s(%p, %d, %d): lru_size %ld\n",
+               __func__, lruvec, lru, nr_pages, size)) {
                VM_BUG_ON(1);
                *lru_size = 0;
        }

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6aa5b01d3e757b9b462993f3421050fd8831ceea..532a2a750952daffed4e4242d36a449eb9ba8837 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -242,6 +242,16 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
        return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 }
 
+unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru,
+                                  int zone_idx)
+{
+       if (!mem_cgroup_disabled())
+               return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx);
+
+       return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx],
+                              NR_ZONE_LRU_BASE + lru);
+}
+
 /*
  * Add a shrinker callback to be called from the vm.
  */
@@ -1382,8 +1392,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
  * be complete before mem_cgroup_update_lru_size due to a santity check.
  */
 static __always_inline void update_lru_sizes(struct lruvec *lruvec,
-                       enum lru_list lru, unsigned long *nr_zone_taken,
-                       unsigned long nr_taken)
+                       enum lru_list lru, unsigned long *nr_zone_taken)
 {
        int zid;
 
@@ -1392,11 +1401,11 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
                        continue;
 
                __update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
-       }
-
 #ifdef CONFIG_MEMCG
-       mem_cgroup_update_lru_size(lruvec, lru, -nr_taken);
+               mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
 #endif
+       }
+
 }
 
 /*
@@ -1501,7 +1510,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
        *nr_scanned = scan;
        trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
                                    nr_taken, mode, is_file_lru(lru));
-       update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
+       update_lru_sizes(lruvec, lru, nr_zone_taken);
        return nr_taken;
 }
 
@@ -2047,10 +2056,8 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
                if (!managed_zone(zone))
                        continue;
 
-               inactive_zone = zone_page_state(zone,
-                               NR_ZONE_LRU_BASE + (file * LRU_FILE));
-               active_zone = zone_page_state(zone,
-                               NR_ZONE_LRU_BASE + (file * LRU_FILE) + LRU_ACTIVE);
+               inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid);
+               active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid);
 
                inactive -= min(inactive, inactive_zone);
                active -= min(active, active_zone);