#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+int sysctl_panic_on_oom;
/* #define DEBUG */
/**
- * oom_badness - calculate a numeric value for how bad this task has been
+ * 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
*
unsigned long badness(struct task_struct *p, unsigned long uptime)
{
unsigned long points, cpu_time, run_time, s;
- struct list_head *tsk;
+ struct mm_struct *mm;
+ struct task_struct *child;
- if (!p->mm)
+ task_lock(p);
+ mm = p->mm;
+ if (!mm) {
+ task_unlock(p);
return 0;
+ }
+
+ /*
+ * swapoff can easily use up all memory, so kill those first.
+ */
+ if (p->flags & PF_SWAPOFF)
+ return ULONG_MAX;
/*
* The memory size of the process is the basis for the badness.
*/
- points = p->mm->total_vm;
+ points = mm->total_vm;
+
+ /*
+ * After this unlock we can no longer dereference local variable `mm'
+ */
+ task_unlock(p);
/*
* Processes which fork a lot of child processes are likely
* child is eating the vast majority of memory, adding only half
* to the parents will make the child our kill candidate of choice.
*/
- list_for_each(tsk, &p->children) {
- struct task_struct *chld;
- chld = list_entry(tsk, struct task_struct, sibling);
- if (chld->mm != p->mm && chld->mm)
- points += chld->mm->total_vm/2 + 1;
+ list_for_each_entry(child, &p->children, sibling) {
+ task_lock(child);
+ if (child->mm != mm && child->mm)
+ points += child->mm->total_vm/2 + 1;
+ task_unlock(child);
}
/*
if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO))
points /= 4;
+ /*
+ * If p's nodes don't overlap ours, it may still help to kill p
+ * because p may have allocated or otherwise mapped memory on
+ * this node before. However it will be less likely.
+ */
+ if (!cpuset_excl_nodes_overlap(p))
+ points /= 8;
+
/*
* Adjust the score by oomkilladj.
*/
for (z = zonelist->zones; *z; z++)
if (cpuset_zone_allowed(*z, gfp_mask))
- node_clear((*z)->zone_pgdat->node_id,
- nodes);
+ node_clear(zone_to_nid(*z), nodes);
else
return CONSTRAINT_CPUSET;
unsigned long points;
int releasing;
+ /* skip kernel threads */
+ if (!p->mm)
+ continue;
/* skip the init task with pid == 1 */
if (p->pid == 1)
continue;
- if (p->oomkilladj == OOM_DISABLE)
- continue;
- /* If p's nodes don't overlap ours, it won't help to kill p. */
- if (!cpuset_excl_nodes_overlap(p))
- continue;
/*
- * This is in the process of releasing memory so for wait it
+ * This is in the process of releasing memory so wait for it
* to finish before killing some other task by mistake.
+ *
+ * However, if p is the current task, we allow the 'kill' to
+ * go ahead if it is exiting: this will simply set TIF_MEMDIE,
+ * which will allow it to gain access to memory reserves in
+ * the process of exiting and releasing its resources.
+ * Otherwise we could get an OOM deadlock.
*/
releasing = test_tsk_thread_flag(p, TIF_MEMDIE) ||
p->flags & PF_EXITING;
- if (releasing && !(p->flags & PF_DEAD))
+ if (releasing) {
+ /* PF_DEAD tasks have already released their mm */
+ if (p->flags & PF_DEAD)
+ continue;
+ if (p->flags & PF_EXITING && p == current) {
+ chosen = p;
+ *ppoints = ULONG_MAX;
+ break;
+ }
return ERR_PTR(-1UL);
- if (p->flags & PF_SWAPOFF)
- return p;
+ }
+ if (p->oomkilladj == OOM_DISABLE)
+ continue;
points = badness(p, uptime.tv_sec);
if (points > *ppoints || !chosen) {
}
/**
- * We must be careful though to never send SIGKILL a process with
- * CAP_SYS_RAW_IO set, send SIGTERM instead (but it's unlikely that
- * we select a process with CAP_SYS_RAW_IO set).
+ * 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(task_t *p, const char *message)
+static void __oom_kill_task(struct task_struct *p, const char *message)
{
if (p->pid == 1) {
WARN_ON(1);
return;
}
task_unlock(p);
- printk(KERN_ERR "%s: Killed process %d (%s).\n",
+
+ if (message) {
+ printk(KERN_ERR "%s: Killed process %d (%s).\n",
message, p->pid, p->comm);
+ }
/*
* We give our sacrificial lamb high priority and access to
force_sig(SIGKILL, p);
}
-static struct mm_struct *oom_kill_task(task_t *p, const char *message)
+static int oom_kill_task(struct task_struct *p, const char *message)
{
- struct mm_struct *mm = get_task_mm(p);
- task_t * g, * q;
-
- if (!mm)
- return NULL;
- if (mm == &init_mm) {
- mmput(mm);
- return NULL;
- }
+ struct mm_struct *mm;
+ struct task_struct *g, *q;
+
+ mm = p->mm;
+
+ /* WARNING: mm may not be dereferenced since we did not obtain its
+ * value from get_task_mm(p). This is OK since all we need to do is
+ * compare mm to q->mm below.
+ *
+ * Furthermore, even if mm contains a non-NULL value, p->mm may
+ * change to NULL at any time since we do not hold task_lock(p).
+ * However, this is of no concern to us.
+ */
+
+ if (mm == NULL || mm == &init_mm)
+ return 1;
__oom_kill_task(p, message);
/*
__oom_kill_task(q, message);
while_each_thread(g, q);
- return mm;
+ return 0;
}
-static struct mm_struct *oom_kill_process(struct task_struct *p,
- unsigned long points, const char *message)
+static int oom_kill_process(struct task_struct *p, unsigned long points,
+ const char *message)
{
- struct mm_struct *mm;
struct task_struct *c;
struct list_head *tsk;
- printk(KERN_ERR "Out of Memory: Kill process %d (%s) score %li and "
- "children.\n", p->pid, p->comm, points);
+ /*
+ * If the task is already exiting, don't alarm the sysadmin or kill
+ * its children or threads, just set TIF_MEMDIE so it can die quickly
+ */
+ if (p->flags & PF_EXITING) {
+ __oom_kill_task(p, NULL);
+ return 0;
+ }
+
+ printk(KERN_ERR "Out of Memory: Kill process %d (%s) score %li"
+ " and children.\n", p->pid, p->comm, points);
/* Try to kill a child first */
list_for_each(tsk, &p->children) {
c = list_entry(tsk, struct task_struct, sibling);
if (c->mm == p->mm)
continue;
- mm = oom_kill_task(c, message);
- if (mm)
- return mm;
+ if (!oom_kill_task(c, message))
+ return 0;
}
return oom_kill_task(p, message);
}
+static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
+
+int register_oom_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_oom_notifier);
+
+int unregister_oom_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_oom_notifier);
+
/**
- * oom_kill - kill the "best" process when we run out of memory
+ * out_of_memory - kill the "best" process when we run out of memory
*
* If we run out of memory, we have the choice between either
* killing a random task (bad), letting the system crash (worse)
*/
void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
{
- struct mm_struct *mm = NULL;
- task_t *p;
+ struct task_struct *p;
unsigned long points = 0;
+ unsigned long freed = 0;
+
+ blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
+ if (freed > 0)
+ /* Got some memory back in the last second. */
+ return;
if (printk_ratelimit()) {
- printk("oom-killer: gfp_mask=0x%x, order=%d\n",
- gfp_mask, order);
+ printk(KERN_WARNING "%s invoked oom-killer: "
+ "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
+ current->comm, gfp_mask, order, current->oomkilladj);
dump_stack();
show_mem();
}
*/
switch (constrained_alloc(zonelist, gfp_mask)) {
case CONSTRAINT_MEMORY_POLICY:
- mm = oom_kill_process(current, points,
+ oom_kill_process(current, points,
"No available memory (MPOL_BIND)");
break;
case CONSTRAINT_CPUSET:
- mm = oom_kill_process(current, points,
+ oom_kill_process(current, points,
"No available memory in cpuset");
break;
case CONSTRAINT_NONE:
+ if (sysctl_panic_on_oom)
+ panic("out of memory. panic_on_oom is selected\n");
retry:
/*
* Rambo mode: Shoot down a process and hope it solves whatever
panic("Out of memory and no killable processes...\n");
}
- mm = oom_kill_process(p, points, "Out of memory");
- if (!mm)
+ if (oom_kill_process(p, points, "Out of memory"))
goto retry;
break;
out:
read_unlock(&tasklist_lock);
cpuset_unlock();
- if (mm)
- mmput(mm);
/*
* Give "p" a good chance of killing itself before we