#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;
-static DEFINE_MUTEX(zone_scan_mutex);
+int sysctl_oom_dump_tasks;
+static DEFINE_SPINLOCK(zone_scan_mutex);
/* #define DEBUG */
/**
* badness - calculate a numeric value for how bad this task has been
* @p: task struct of which task we should calculate
* @uptime: current uptime in seconds
+ * @mem: target memory controller
*
* The formula used is relatively simple and documented inline in the
* function. The main rationale is that we want to select a good task
* 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;
* 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;
/*
* 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;
/*
*
* (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;
if (!p->mm)
continue;
/* skip the init task */
- if (is_init(p))
+ if (is_global_init(p))
+ continue;
+ if (mem && !task_in_mem_cgroup(p, mem))
continue;
/*
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;
}
/**
+ * dump_tasks - dump current memory state of all system tasks
+ * @mem: target memory controller
+ *
+ * Dumps the current memory state of all system tasks, excluding kernel threads.
+ * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
+ * score, and name.
+ *
+ * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are
+ * shown.
+ *
+ * Call with tasklist_lock read-locked.
+ */
+static void dump_tasks(const struct mem_cgroup *mem)
+{
+ struct task_struct *g, *p;
+
+ printk(KERN_INFO "[ pid ] uid tgid total_vm rss cpu oom_adj "
+ "name\n");
+ do_each_thread(g, p) {
+ /*
+ * total_vm and rss sizes do not exist for tasks with a
+ * detached mm so there's no need to report them.
+ */
+ if (!p->mm)
+ continue;
+ if (mem && !task_in_mem_cgroup(p, mem))
+ continue;
+
+ task_lock(p);
+ printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n",
+ p->pid, p->uid, p->tgid, p->mm->total_vm,
+ get_mm_rss(p->mm), (int)task_cpu(p), p->oomkilladj,
+ p->comm);
+ task_unlock(p);
+ } while_each_thread(g, p);
+}
+
+/*
* Send SIGKILL to the selected process irrespective of CAP_SYS_RAW_IO
* flag though it's unlikely that we select a process with CAP_SYS_RAW_IO
* set.
*/
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;
}
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);
* 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);
}
static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
- unsigned long points, const char *message)
+ unsigned long points, struct mem_cgroup *mem,
+ const char *message)
{
struct task_struct *c;
- struct list_head *tsk;
if (printk_ratelimit()) {
printk(KERN_WARNING "%s invoked oom-killer: "
current->comm, gfp_mask, order, current->oomkilladj);
dump_stack();
show_mem();
+ if (sysctl_oom_dump_tasks)
+ dump_tasks(mem);
}
/*
}
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))
return oom_kill_task(p);
}
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
+{
+ unsigned long points = 0;
+ struct task_struct *p;
+
+ cgroup_lock();
+ read_lock(&tasklist_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, mem,
+ "Memory cgroup out of memory"))
+ goto retry;
+out:
+ read_unlock(&tasklist_lock);
+ cgroup_unlock();
+}
+#endif
+
static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
int register_oom_notifier(struct notifier_block *nb)
z = zonelist->zones;
- mutex_lock(&zone_scan_mutex);
+ spin_lock(&zone_scan_mutex);
do {
if (zone_is_oom_locked(*z)) {
ret = 0;
zone_set_flag(*z, ZONE_OOM_LOCKED);
} while (*(++z) != NULL);
out:
- mutex_unlock(&zone_scan_mutex);
+ spin_unlock(&zone_scan_mutex);
return ret;
}
z = zonelist->zones;
- mutex_lock(&zone_scan_mutex);
+ spin_lock(&zone_scan_mutex);
do {
zone_clear_flag(*z, ZONE_OOM_LOCKED);
} while (*(++z) != NULL);
- mutex_unlock(&zone_scan_mutex);
+ spin_unlock(&zone_scan_mutex);
}
/**
* out_of_memory - kill the "best" process when we run out of memory
+ * @zonelist: zonelist pointer
+ * @gfp_mask: memory allocation flags
+ * @order: amount of memory being requested as a power of 2
*
* If we run out of memory, we have the choice between either
* killing a random task (bad), letting the system crash (worse)
switch (constraint) {
case CONSTRAINT_MEMORY_POLICY:
- oom_kill_process(current, gfp_mask, order, points,
+ oom_kill_process(current, gfp_mask, order, points, NULL,
"No available memory (MPOL_BIND)");
break;
/* Fall-through */
case CONSTRAINT_CPUSET:
if (sysctl_oom_kill_allocating_task) {
- oom_kill_process(current, gfp_mask, order, points,
+ oom_kill_process(current, gfp_mask, order, points, NULL,
"Out of memory (oom_kill_allocating_task)");
break;
}
* 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;
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, NULL,
"Out of memory"))
goto retry;