memcg: fix hotplugged memory zone oops

When MEMCG is configured on (even when it's disabled by boot option),
when adding or removing a page to/from its lru list, the zone pointer
used for stats updates is nowadays taken from the struct lruvec.  (On
many configurations, calculating zone from page is slower.)

But we have no code to update all the lruvecs (per zone, per memcg) when
a memory node is hotadded.  Here's an extract from the oops which
results when running numactl to bind a program to a newly onlined node:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000f60
  IP:  __mod_zone_page_state+0x9/0x60
  Pid: 1219, comm: numactl Not tainted 3.6.0-rc5+ #180 Bochs Bochs
  Process numactl (pid: 1219, threadinfo ffff880039abc000, task ffff8800383c4ce0)
  Call Trace:
    __pagevec_lru_add_fn+0xdf/0x140
    pagevec_lru_move_fn+0xb1/0x100
    __pagevec_lru_add+0x1c/0x30
    lru_add_drain_cpu+0xa3/0x130
    lru_add_drain+0x2f/0x40
   ...

The natural solution might be to use a memcg callback whenever memory is
hotadded; but that solution has not been scoped out, and it happens that
we do have an easy location at which to update lruvec->zone.  The lruvec
pointer is discovered either by mem_cgroup_zone_lruvec() or by
mem_cgroup_page_lruvec(), and both of those do know the right zone.

So check and set lruvec->zone in those; and remove the inadequate
attempt to set lruvec->zone from lruvec_init(), which is called before
NODE_DATA(node) has been allocated in such cases.

Ah, there was one exceptionr.  For no particularly good reason,
mem_cgroup_force_empty_list() has its own code for deciding lruvec.
Change it to use the standard mem_cgroup_zone_lruvec() and
mem_cgroup_get_lru_size() too.  In fact it was already safe against such
an oops (the lru lists in danger could only be empty), but we're better
proofed against future changes this way.

I've marked this for stable (3.6) since we introduced the problem in 3.5
(now closed to stable); but I have no idea if this is the only fix
needed to get memory hotadd working with memcg in 3.6, and received no
answer when I enquired twice before.

Reported-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 50aaca81f63d6db3914b7858f0209fed036a5971..a23923ba8263b18dac16ec73971d19bed719d015 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -752,7 +752,7 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
                                     unsigned long size,
                                     enum memmap_context context);
 
-extern void lruvec_init(struct lruvec *lruvec, struct zone *zone);
+extern void lruvec_init(struct lruvec *lruvec);
 
 static inline struct zone *lruvec_zone(struct lruvec *lruvec)
 {

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 93a7e36ded89f264194c77c7f8cd27c5f02410fa..dd39ba000b31f98730c6fd6d22bdf695ced3bedf 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1055,12 +1055,24 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
                                      struct mem_cgroup *memcg)
 {
        struct mem_cgroup_per_zone *mz;
+       struct lruvec *lruvec;
 
-       if (mem_cgroup_disabled())
-               return &zone->lruvec;
+       if (mem_cgroup_disabled()) {
+               lruvec = &zone->lruvec;
+               goto out;
+       }
 
        mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone));
-       return &mz->lruvec;
+       lruvec = &mz->lruvec;
+out:
+       /*
+        * Since a node can be onlined after the mem_cgroup was created,
+        * we have to be prepared to initialize lruvec->zone here;
+        * and if offlined then reonlined, we need to reinitialize it.
+        */
+       if (unlikely(lruvec->zone != zone))
+               lruvec->zone = zone;
+       return lruvec;
 }
 
 /*
@@ -1087,9 +1099,12 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
        struct mem_cgroup_per_zone *mz;
        struct mem_cgroup *memcg;
        struct page_cgroup *pc;
+       struct lruvec *lruvec;
 
-       if (mem_cgroup_disabled())
-               return &zone->lruvec;
+       if (mem_cgroup_disabled()) {
+               lruvec = &zone->lruvec;
+               goto out;
+       }
 
        pc = lookup_page_cgroup(page);
        memcg = pc->mem_cgroup;
@@ -1107,7 +1122,16 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
                pc->mem_cgroup = memcg = root_mem_cgroup;
 
        mz = page_cgroup_zoneinfo(memcg, page);
-       return &mz->lruvec;
+       lruvec = &mz->lruvec;
+out:
+       /*
+        * Since a node can be onlined after the mem_cgroup was created,
+        * we have to be prepared to initialize lruvec->zone here;
+        * and if offlined then reonlined, we need to reinitialize it.
+        */
+       if (unlikely(lruvec->zone != zone))
+               lruvec->zone = zone;
+       return lruvec;
 }
 
 /**
@@ -3697,17 +3721,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
                                int node, int zid, enum lru_list lru)
 {
-       struct mem_cgroup_per_zone *mz;
+       struct lruvec *lruvec;
        unsigned long flags, loop;
        struct list_head *list;
        struct page *busy;
        struct zone *zone;
 
        zone = &NODE_DATA(node)->node_zones[zid];
-       mz = mem_cgroup_zoneinfo(memcg, node, zid);
-       list = &mz->lruvec.lists[lru];
+       lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+       list = &lruvec->lists[lru];
 
-       loop = mz->lru_size[lru];
+       loop = mem_cgroup_get_lru_size(lruvec, lru);
        /* give some margin against EBUSY etc...*/
        loop += 256;
        busy = NULL;
@@ -4745,7 +4769,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 
        for (zone = 0; zone < MAX_NR_ZONES; zone++) {
                mz = &pn->zoneinfo[zone];
-               lruvec_init(&mz->lruvec, &NODE_DATA(node)->node_zones[zone]);
+               lruvec_init(&mz->lruvec);
                mz->usage_in_excess = 0;
                mz->on_tree = false;
                mz->memcg = memcg;

diff --git a/mm/mmzone.c b/mm/mmzone.c
index 3cef80f6ac79ff2e8b5fef7bcd373679e91df2c1..4596d81b89b16280b4768e83df3290d674aaf005 100644 (file)
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -87,7 +87,7 @@ int memmap_valid_within(unsigned long pfn,
 }
 #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
 
-void lruvec_init(struct lruvec *lruvec, struct zone *zone)
+void lruvec_init(struct lruvec *lruvec)
 {
        enum lru_list lru;
 
@@ -95,8 +95,4 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone)
 
        for_each_lru(lru)
                INIT_LIST_HEAD(&lruvec->lists[lru]);
-
-#ifdef CONFIG_MEMCG
-       lruvec->zone = zone;
-#endif
 }

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5b74de6702e06587e0d4f36060f810526ff8fbe3..c91598b1b4c0adb24e5268c23d19db8fbe9e21cf 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4505,7 +4505,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
                zone->zone_pgdat = pgdat;
 
                zone_pcp_init(zone);
-               lruvec_init(&zone->lruvec, zone);
+               lruvec_init(&zone->lruvec);
                if (!size)
                        continue;