memcontrol: move oom task exclusion to tasklist scan

[linux-2.6-omap-h63xx.git] / mm / oom_kill.c

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 96473b482099793384af969b8158e1306e2d4f58..ef5084dbc793ab49d5ba1eae09b9df89d88509d6 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;
@@ -125,8 +127,7 @@ 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 +136,7 @@ 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 +195,8 @@ 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;
@@ -214,6 +216,8 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
                /* skip the init task */
                if (is_global_init(p))
                        continue;
+               if (mem && !task_in_mem_cgroup(p, mem))
+                       continue;
 
                /*
                 * This task already has access to memory reserves and is
@@ -248,7 +252,7 @@ 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;
@@ -369,6 +373,31 @@ 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)
@@ -485,7 +514,7 @@ 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;