memcg, oom: provide more precise dump info while memcg oom happening

Currently when a memcg oom is happening the oom dump messages is still
global state and provides few useful info for users.  This patch prints
more pointed memcg page statistics for memcg-oom and take hierarchy into
consideration:

Based on Michal's advice, we take hierarchy into consideration: supppose
we trigger an OOM on A's limit

        root_memcg
            |
            A (use_hierachy=1)
           / \
          B   C
          |
          D
then the printed info will be:

  Memory cgroup stats for /A:...
  Memory cgroup stats for /A/B:...
  Memory cgroup stats for /A/C:...
  Memory cgroup stats for /A/B/D:...

Following are samples of oom output:

(1) Before change:

    mal-80 invoked oom-killer:gfp_mask=0xd0, order=0, oom_score_adj=0
    mal-80 cpuset=/ mems_allowed=0
    Pid: 2976, comm: mal-80 Not tainted 3.7.0+ #10
    Call Trace:
     [<ffffffff8167fbfb>] dump_header+0x83/0x1ca
     ..... (call trace)
     [<ffffffff8168a818>] page_fault+0x28/0x30
                             <<<<<<<<<<<<<<<<<<<<< memcg specific information
    Task in /A/B/D killed as a result of limit of /A
    memory: usage 101376kB, limit 101376kB, failcnt 57
    memory+swap: usage 101376kB, limit 101376kB, failcnt 0
    kmem: usage 0kB, limit 9007199254740991kB, failcnt 0
                             <<<<<<<<<<<<<<<<<<<<< print per cpu pageset stat
    Mem-Info:
    Node 0 DMA per-cpu:
    CPU    0: hi:    0, btch:   1 usd:   0
    ......
    CPU    3: hi:    0, btch:   1 usd:   0
    Node 0 DMA32 per-cpu:
    CPU    0: hi:  186, btch:  31 usd: 173
    ......
    CPU    3: hi:  186, btch:  31 usd: 130
                             <<<<<<<<<<<<<<<<<<<<< print global page state
    active_anon:92963 inactive_anon:40777 isolated_anon:0
     active_file:33027 inactive_file:51718 isolated_file:0
     unevictable:0 dirty:3 writeback:0 unstable:0
     free:729995 slab_reclaimable:6897 slab_unreclaimable:6263
     mapped:20278 shmem:35971 pagetables:5885 bounce:0
     free_cma:0
                             <<<<<<<<<<<<<<<<<<<<< print per zone page state
    Node 0 DMA free:15836kB ... all_unreclaimable? no
    lowmem_reserve[]: 0 3175 3899 3899
    Node 0 DMA32 free:2888564kB ... all_unrelaimable? no
    lowmem_reserve[]: 0 0 724 724
    lowmem_reserve[]: 0 0 0 0
    Node 0 DMA: 1*4kB (U) ... 3*4096kB (M) = 15836kB
    Node 0 DMA32: 41*4kB (UM) ... 702*4096kB (MR) = 2888316kB
    120710 total pagecache pages
    0 pages in swap cache
                             <<<<<<<<<<<<<<<<<<<<< print global swap cache stat
    Swap cache stats: add 0, delete 0, find 0/0
    Free swap  = 499708kB
    Total swap = 499708kB
    1040368 pages RAM
    58678 pages reserved
    169065 pages shared
    173632 pages non-shared
    [ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name
    [ 2693]     0  2693     6005     1324      17        0             0 god
    [ 2754]     0  2754     6003     1320      16        0             0 god
    [ 2811]     0  2811     5992     1304      18        0             0 god
    [ 2874]     0  2874     6005     1323      18        0             0 god
    [ 2935]     0  2935     8720     7742      21        0             0 mal-30
    [ 2976]     0  2976    21520    17577      42        0             0 mal-80
    Memory cgroup out of memory: Kill process 2976 (mal-80) score 665 or sacrifice child
    Killed process 2976 (mal-80) total-vm:86080kB, anon-rss:69964kB, file-rss:344kB

We can see that messages dumped by show_free_areas() are longsome and can
provide so limited info for memcg that just happen oom.

(2) After change
    mal-80 invoked oom-killer: gfp_mask=0xd0, order=0, oom_score_adj=0
    mal-80 cpuset=/ mems_allowed=0
    Pid: 2704, comm: mal-80 Not tainted 3.7.0+ #10
    Call Trace:
     [<ffffffff8167fd0b>] dump_header+0x83/0x1d1
     .......(call trace)
     [<ffffffff8168a918>] page_fault+0x28/0x30
    Task in /A/B/D killed as a result of limit of /A
                             <<<<<<<<<<<<<<<<<<<<< memcg specific information
    memory: usage 102400kB, limit 102400kB, failcnt 140
    memory+swap: usage 102400kB, limit 102400kB, failcnt 0
    kmem: usage 0kB, limit 9007199254740991kB, failcnt 0
    Memory cgroup stats for /A: cache:32KB rss:30984KB mapped_file:0KB swap:0KB inactive_anon:6912KB active_anon:24072KB inactive_file:32KB active_file:0KB unevictable:0KB
    Memory cgroup stats for /A/B: cache:0KB rss:0KB mapped_file:0KB swap:0KB inactive_anon:0KB active_anon:0KB inactive_file:0KB active_file:0KB unevictable:0KB
    Memory cgroup stats for /A/C: cache:0KB rss:0KB mapped_file:0KB swap:0KB inactive_anon:0KB active_anon:0KB inactive_file:0KB active_file:0KB unevictable:0KB
    Memory cgroup stats for /A/B/D: cache:32KB rss:71352KB mapped_file:0KB swap:0KB inactive_anon:6656KB active_anon:64696KB inactive_file:16KB active_file:16KB unevictable:0KB
    [ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name
    [ 2260]     0  2260     6006     1325      18        0             0 god
    [ 2383]     0  2383     6003     1319      17        0             0 god
    [ 2503]     0  2503     6004     1321      18        0             0 god
    [ 2622]     0  2622     6004     1321      16        0             0 god
    [ 2695]     0  2695     8720     7741      22        0             0 mal-30
    [ 2704]     0  2704    21520    17839      43        0             0 mal-80
    Memory cgroup out of memory: Kill process 2704 (mal-80) score 669 or sacrifice child
    Killed process 2704 (mal-80) total-vm:86080kB, anon-rss:71016kB, file-rss:340kB

This version provides more pointed info for memcg in "Memory cgroup stats
for XXX" section.
Signed-off-by: Sha Zhengju <handai.szj@taobao.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/memcontrol.c

@@ -120,6 +120,14 @@ static const char * const mem_cgroup_events_names[] = {
 	"pgmajfault",
 };
 
+static const char * const mem_cgroup_lru_names[] = {
+	"inactive_anon",
+	"active_anon",
+	"inactive_file",
+	"active_file",
+	"unevictable",
+};
+
 /*
  * Per memcg event counter is incremented at every pagein/pageout. With THP,
  * it will be incremated by the number of pages. This counter is used for
@@ -1524,8 +1532,9 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
 	spin_unlock_irqrestore(&memcg->move_lock, *flags);
 }
 
+#define K(x) ((x) << (PAGE_SHIFT-10))
 /**
- * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
+ * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
  * @memcg: The memory cgroup that went over limit
  * @p: Task that is going to be killed
  *
@@ -1543,8 +1552,10 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	 */
 	static char memcg_name[PATH_MAX];
 	int ret;
+	struct mem_cgroup *iter;
+	unsigned int i;
 
-	if (!memcg || !p)
+	if (!p)
 		return;
 
 	rcu_read_lock();
@@ -1592,6 +1603,30 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
+
+	for_each_mem_cgroup_tree(iter, memcg) {
+		pr_info("Memory cgroup stats");
+
+		rcu_read_lock();
+		ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX);
+		if (!ret)
+			pr_cont(" for %s", memcg_name);
+		rcu_read_unlock();
+		pr_cont(":");
+
+		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
+			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+				continue;
+			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+				K(mem_cgroup_read_stat(iter, i)));
+		}
+
+		for (i = 0; i < NR_LRU_LISTS; i++)
+			pr_cont(" %s:%luKB", mem_cgroup_lru_names[i],
+				K(mem_cgroup_nr_lru_pages(iter, BIT(i))));
+
+		pr_cont("\n");
+	}
 }
 
 /*
@@ -5214,14 +5249,6 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 }
 #endif /* CONFIG_NUMA */
 
-static const char * const mem_cgroup_lru_names[] = {
-	"inactive_anon",
-	"active_anon",
-	"inactive_file",
-	"active_file",
-	"unevictable",
-};
-
 static inline void mem_cgroup_lru_names_not_uptodate(void)
 {
 	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);

mm/oom_kill.c

@@ -386,8 +386,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 	cpuset_print_task_mems_allowed(current);
 	task_unlock(current);
 	dump_stack();
-	mem_cgroup_print_oom_info(memcg, p);
-	show_mem(SHOW_MEM_FILTER_NODES);
+	if (memcg)
+		mem_cgroup_print_oom_info(memcg, p);
+	else
+		show_mem(SHOW_MEM_FILTER_NODES);
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(memcg, nodemask);
 }