Memory controller: OOM handling

[safe/jmp/linux-2.6] / mm / oom_kill.c

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index a64decb..64751dc 100644 (file)
--- 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.
         */
@@ -125,8 +134,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
         * Superuser processes are usually more important, so we make it
         * less likely that we kill those.
         */
-       if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_ADMIN) ||
-                               p->uid == 0 || p->euid == 0)
+       if (__capable(p, CAP_SYS_ADMIN) || __capable(p, CAP_SYS_RESOURCE))
                points /= 4;
 
        /*
@@ -135,7 +143,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
         * tend to only have this flag set on applications they think
         * of as important.
         */
-       if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO))
+       if (__capable(p, CAP_SYS_RAWIO))
                points /= 4;
 
        /*
@@ -194,7 +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;
@@ -212,7 +221,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
                if (!p->mm)
                        continue;
                /* skip the init task */
-               if (is_init(p))
+               if (is_global_init(p))
                        continue;
 
                /*
@@ -248,7 +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;
@@ -265,7 +274,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
  */
 static void __oom_kill_task(struct task_struct *p, int verbose)
 {
-       if (is_init(p)) {
+       if (is_global_init(p)) {
                WARN_ON(1);
                printk(KERN_WARNING "tried to kill init!\n");
                return;
@@ -278,14 +287,15 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
        }
 
        if (verbose)
-               printk(KERN_ERR "Killed process %d (%s)\n", p->pid, p->comm);
+               printk(KERN_ERR "Killed process %d (%s)\n",
+                               task_pid_nr(p), p->comm);
 
        /*
         * We give our sacrificial lamb high priority and access to
         * all the memory it needs. That way it should be able to
         * exit() and clear out its resources quickly...
         */
-       p->time_slice = HZ;
+       p->rt.time_slice = HZ;
        set_tsk_thread_flag(p, TIF_MEMDIE);
 
        force_sig(SIGKILL, p);
@@ -326,7 +336,7 @@ static int oom_kill_task(struct task_struct *p)
         * to memory reserves though, otherwise we might deplete all memory.
         */
        do_each_thread(g, q) {
-               if (q->mm == mm && q->tgid != p->tgid)
+               if (q->mm == mm && !same_thread_group(q, p))
                        force_sig(SIGKILL, q);
        } while_each_thread(g, q);
 
@@ -337,7 +347,6 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
                            unsigned long points, const char *message)
 {
        struct task_struct *c;
-       struct list_head *tsk;
 
        if (printk_ratelimit()) {
                printk(KERN_WARNING "%s invoked oom-killer: "
@@ -357,11 +366,10 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
        }
 
        printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n",
-                                       message, p->pid, p->comm, points);
+                                       message, task_pid_nr(p), p->comm, points);
 
        /* Try to kill a child first */
-       list_for_each(tsk, &p->children) {
-               c = list_entry(tsk, struct task_struct, sibling);
+       list_for_each_entry(c, &p->children, sibling) {
                if (c->mm == p->mm)
                        continue;
                if (!oom_kill_task(c))
@@ -370,6 +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)
@@ -486,7 +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;
@@ -497,7 +530,7 @@ retry:
                        panic("Out of memory and no killable processes...\n");
                }
 
-               if (oom_kill_process(p, points, gfp_mask, order,
+               if (oom_kill_process(p, gfp_mask, order, points,
                                     "Out of memory"))
                        goto retry;