From: KOSAKI Motohiro on
Oleg pointed out that current oom child process iterating logic is wrong.

> list_for_each_entry(p->children) can only see the tasks forked
> by p, it can't see other children forked by its sub-threads.

This patch fixes it.

Reported-by: Oleg Nesterov <oleg(a)redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro(a)jp.fujitsu.com>
---
mm/oom_kill.c | 34 ++++++++++++++++++++--------------
1 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 70e1a85..1bdf27d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -88,6 +88,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
{
unsigned long points, cpu_time, run_time;
struct task_struct *c;
+ struct task_struct *t = p;
struct task_struct *child;
int oom_adj = p->signal->oom_adj;
struct task_cputime task_time;
@@ -125,14 +126,16 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
* 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_entry(c, &p->children, sibling) {
- child = find_lock_task_mm(c);
- if (child) {
- if (child->mm != p->mm)
- points += child->mm->total_vm/2 + 1;
- task_unlock(child);
+ do {
+ list_for_each_entry(c, &t->children, sibling) {
+ child = find_lock_task_mm(c);
+ if (child) {
+ if (child->mm != p->mm)
+ points += child->mm->total_vm/2 + 1;
+ task_unlock(child);
+ }
}
- }
+ } while_each_thread(p, t);

/*
* CPU time is in tens of seconds and run time is in thousands
@@ -432,6 +435,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
const char *message)
{
struct task_struct *c;
+ struct task_struct *t = p;

if (printk_ratelimit())
dump_header(p, gfp_mask, order, mem);
@@ -449,14 +453,16 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
message, task_pid_nr(p), p->comm, points);

/* Try to kill a child first */
- list_for_each_entry(c, &p->children, sibling) {
- if (c->mm == p->mm)
- continue;
+ do {
+ list_for_each_entry(c, &t->children, sibling) {
+ if (c->mm == p->mm)
+ continue;

- /* Ok, Kill the child */
- if (!__oom_kill_process(c, mem, 1))
- return 0;
- }
+ /* Ok, Kill the child */
+ if (!__oom_kill_process(c, mem, 1))
+ return 0;
+ }
+ } while_each_thread(p, t);

return __oom_kill_process(p, mem, 1);
}
--
1.6.5.2



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/