#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;
+ }
/*
* 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);
}
/*
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.
*/
releasing = test_tsk_thread_flag(p, TIF_MEMDIE) ||
* CAP_SYS_RAW_IO set, send SIGTERM instead (but 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);
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;
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",
*/
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
* retry to allocate memory unless "p" is current
*/
if (!test_thread_flag(TIF_MEMDIE))
- schedule_timeout_interruptible(1);
+ schedule_timeout_uninterruptible(1);
}
git.openpandora.org / pandora-kernel.git / blobdiff