memcg: show memcg information during OOM

Add RSS and swap to OOM output from memcg

Display memcg values like failcnt, usage and limit when an OOM occurs due
to memcg.

Thanks to Johannes Weiner, Li Zefan, David Rientjes, Kamezawa Hiroyuki,
Daisuke Nishimura and KOSAKI Motohiro for review.

Sample output
-------------

Task in /a/x killed as a result of limit of /a
memory: usage 1048576kB, limit 1048576kB, failcnt 4183
memory+swap: usage 1400964kB, limit 9007199254740991kB, failcnt 0

[akpm@linux-foundation.org: compilation fix]
[akpm@linux-foundation.org: fix kerneldoc and whitespace]
[akpm@linux-foundation.org: add printk facility level]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 77 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 326f45c86530..7aba9f264622 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -104,6 +104,8 @@ struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
                                                       struct zone *zone);
 struct zone_reclaim_stat*
 mem_cgroup_get_reclaim_stat_from_page(struct page *page);
+extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+                                        struct task_struct *p);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 extern int do_swap_account;
@@ -270,6 +272,11 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
         return NULL;
 }
 
+static inline void
+mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+{
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 025f8abfae2d..2bdb6149faeb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -721,6 +722,74 @@ static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
         (*val)++;
         return 0;
 }
+
+/**
+ * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode.
+ * @memcg: The memory cgroup that went over limit
+ * @p: Task that is going to be killed
+ *
+ * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
+ * enabled
+ */
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+{
+        struct cgroup *task_cgrp;
+        struct cgroup *mem_cgrp;
+        /*
+         * Need a buffer in BSS, can't rely on allocations. The code relies
+         * on the assumption that OOM is serialized for memory controller.
+         * If this assumption is broken, revisit this code.
+         */
+        static char memcg_name[PATH_MAX];
+        int ret;
+
+        if (!memcg)
+                return;
+
+
+        rcu_read_lock();
+
+        mem_cgrp = memcg->css.cgroup;
+        task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+
+        ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
+        if (ret < 0) {
+                /*
+                 * Unfortunately, we are unable to convert to a useful name
+                 * But we'll still print out the usage information
+                 */
+                rcu_read_unlock();
+                goto done;
+        }
+        rcu_read_unlock();
+
+        printk(KERN_INFO "Task in %s killed", memcg_name);
+
+        rcu_read_lock();
+        ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
+        if (ret < 0) {
+                rcu_read_unlock();
+                goto done;
+        }
+        rcu_read_unlock();
+
+        /*
+         * Continues from above, so we don't need an KERN_ level
+         */
+        printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
+done:
+
+        printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+                res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
+                res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
+                res_counter_read_u64(&memcg->res, RES_FAILCNT));
+        printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
+                "failcnt %llu\n",
+                res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
+                res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
+                res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
+}
+
 /*
  * This function returns the number of memcg under hierarchy tree. Returns
  * 1(self count) if no children.
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d3b9bac085b5..2f3166e308d9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -394,6 +394,7 @@ static int oom_kill_process(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(mem, current);
                 show_mem();
                 if (sysctl_oom_dump_tasks)
                         dump_tasks(mem);