Memory controller: OOM handling

Out of memory handling for cgroups over their limit. A task from the
cgroup over limit is chosen using the existing OOM logic and killed.

TODO:
1. As discussed in the OLS BOF session, consider implementing a user
space policy for OOM handling.

[akpm@linux-foundation.org: fix build due to oom-killer changes]
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 41 insertions, 4 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9c3c1c97c197..9bbbf524ba8f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -39,6 +39,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
                                         int mode, struct zone *z,
                                         struct mem_cgroup *mem_cont,
                                         int active);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 
 static inline void mem_cgroup_uncharge_page(struct page *page)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d73692279ab1..5260658c90aa 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -329,6 +329,7 @@ retry:
                 }
 
                 css_put(&mem->css);
+                mem_cgroup_out_of_memory(mem, GFP_KERNEL);
                 goto free_pc;
         }
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c1850bf991cd..64751dc9d997 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -25,6 +25,7 @@
 #include <linux/cpuset.h>
 #include <linux/module.h>
 #include <linux/notifier.h>
+#include <linux/memcontrol.h>
 
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
@@ -50,7 +51,8 @@ static DEFINE_SPINLOCK(zone_scan_mutex);
  *    of least surprise ... (be careful when you change it)
  */
 
-unsigned long badness(struct task_struct *p, unsigned long uptime)
+unsigned long badness(struct task_struct *p, unsigned long uptime,
+                        struct mem_cgroup *mem)
 {
         unsigned long points, cpu_time, run_time, s;
         struct mm_struct *mm;
@@ -63,6 +65,13 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
                 return 0;
         }
 
+#ifdef CONFIG_CGROUP_MEM_CONT
+        if (mem != NULL && mm->mem_cgroup != mem) {
+                task_unlock(p);
+                return 0;
+        }
+#endif
+
         /*
          * The memory size of the process is the basis for the badness.
          */
@@ -193,7 +202,8 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
  *
  * (not docbooked, we don't want this one cluttering up the manual)
  */
-static struct task_struct *select_bad_process(unsigned long *ppoints)
+static struct task_struct *select_bad_process(unsigned long *ppoints,
+                                                struct mem_cgroup *mem)
 {
         struct task_struct *g, *p;
         struct task_struct *chosen = NULL;
@@ -247,7 +257,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
                 if (p->oomkilladj == OOM_DISABLE)
                         continue;
 
-                points = badness(p, uptime.tv_sec);
+                points = badness(p, uptime.tv_sec, mem);
                 if (points > *ppoints || !chosen) {
                         chosen = p;
                         *ppoints = points;
@@ -368,6 +378,31 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
         return oom_kill_task(p);
 }
 
+#ifdef CONFIG_CGROUP_MEM_CONT
+void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
+{
+        unsigned long points = 0;
+        struct task_struct *p;
+
+        cgroup_lock();
+        rcu_read_lock();
+retry:
+        p = select_bad_process(&points, mem);
+        if (PTR_ERR(p) == -1UL)
+                goto out;
+
+        if (!p)
+                p = current;
+
+        if (oom_kill_process(p, gfp_mask, 0, points,
+                                "Memory cgroup out of memory"))
+                goto retry;
+out:
+        rcu_read_unlock();
+        cgroup_unlock();
+}
+#endif
+
 static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
 
 int register_oom_notifier(struct notifier_block *nb)
@@ -484,7 +519,7 @@ retry:
                  * Rambo mode: Shoot down a process and hope it solves whatever
                  * issues we may have.
                  */
-                p = select_bad_process(&points);
+                p = select_bad_process(&points, NULL);
 
                 if (PTR_ERR(p) == -1UL)
                         goto out;