aboutsummaryrefslogtreecommitdiff
path: root/mm/oom_kill.c
diff options
context:
space:
mode:
authorOleg Nesterov <oleg@redhat.com>2010-08-09 17:18:45 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-08-09 20:44:55 -0700
commitdd8e8f405ca386c7ce7cbb996ccd985d283b0e03 (patch)
tree7863585871d44c0272eb0b93ee909392ee85eb99 /mm/oom_kill.c
parentb52279406e77be711c068f9a8e970ea6471e089c (diff)
oom: introduce find_lock_task_mm() to fix !mm false positives
Almost all ->mm == NULL checks in oom_kill.c are wrong. The current code assumes that the task without ->mm has already released its memory and ignores the process. However this is not necessarily true when this process is multithreaded, other live sub-threads can use this ->mm. - Remove the "if (!p->mm)" check in select_bad_process(), it is just wrong. - Add the new helper, find_lock_task_mm(), which finds the live thread which uses the memory and takes task_lock() to pin ->mm - change oom_badness() to use this helper instead of just checking ->mm != NULL. - As David pointed out, select_bad_process() must never choose the task without ->mm, but no matter what oom_badness() returns the task can be chosen if nothing else has been found yet. Change oom_badness() to return int, change it to return -1 if find_lock_task_mm() fails, and change select_bad_process() to check points >= 0. Note! This patch is not enough, we need more changes. - oom_badness() was fixed, but oom_kill_task() still ignores the task without ->mm - oom_forkbomb_penalty() should use find_lock_task_mm() too, and it also needs other changes to actually find the first first-descendant children This will be addressed later. [kosaki.motohiro@jp.fujitsu.com: use in badness(), __oom_kill_task()] Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/oom_kill.c')
-rw-r--r--mm/oom_kill.c74
1 files changed, 43 insertions, 31 deletions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0a6e466155d..9a686aa35a4 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -52,6 +52,20 @@ static int has_intersects_mems_allowed(struct task_struct *tsk)
return 0;
}
+static struct task_struct *find_lock_task_mm(struct task_struct *p)
+{
+ struct task_struct *t = p;
+
+ do {
+ task_lock(t);
+ if (likely(t->mm))
+ return t;
+ task_unlock(t);
+ } while_each_thread(p, t);
+
+ return NULL;
+}
+
/**
* badness - calculate a numeric value for how bad this task has been
* @p: task struct of which task we should calculate
@@ -74,8 +88,8 @@ static int has_intersects_mems_allowed(struct task_struct *tsk)
unsigned long badness(struct task_struct *p, unsigned long uptime)
{
unsigned long points, cpu_time, run_time;
- struct mm_struct *mm;
struct task_struct *child;
+ struct task_struct *c, *t;
int oom_adj = p->signal->oom_adj;
struct task_cputime task_time;
unsigned long utime;
@@ -84,17 +98,14 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
if (oom_adj == OOM_DISABLE)
return 0;
- task_lock(p);
- mm = p->mm;
- if (!mm) {
- task_unlock(p);
+ p = find_lock_task_mm(p);
+ if (!p)
return 0;
- }
/*
* The memory size of the process is the basis for the badness.
*/
- points = mm->total_vm;
+ points = p->mm->total_vm;
/*
* After this unlock we can no longer dereference local variable `mm'
@@ -115,12 +126,17 @@ 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(child, &p->children, sibling) {
- task_lock(child);
- if (child->mm != mm && child->mm)
- points += child->mm->total_vm/2 + 1;
- task_unlock(child);
- }
+ t = p;
+ 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
@@ -256,9 +272,6 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
for_each_process(p) {
unsigned long points;
- /* skip tasks that have already released their mm */
- if (!p->mm)
- continue;
/* skip the init task and kthreads */
if (is_global_init(p) || (p->flags & PF_KTHREAD))
continue;
@@ -385,14 +398,9 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
return;
}
- task_lock(p);
- if (!p->mm) {
- WARN_ON(1);
- printk(KERN_WARNING "tried to kill an mm-less task %d (%s)!\n",
- task_pid_nr(p), p->comm);
- task_unlock(p);
+ p = find_lock_task_mm(p);
+ if (!p)
return;
- }
if (verbose)
printk(KERN_ERR "Killed process %d (%s) "
@@ -437,6 +445,7 @@ 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);
@@ -454,14 +463,17 @@ 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;
- if (mem && !task_in_mem_cgroup(c, mem))
- continue;
- if (!oom_kill_task(c))
- return 0;
- }
+ do {
+ list_for_each_entry(c, &t->children, sibling) {
+ if (c->mm == p->mm)
+ continue;
+ if (mem && !task_in_mem_cgroup(c, mem))
+ continue;
+ if (!oom_kill_task(c))
+ return 0;
+ }
+ } while_each_thread(p, t);
+
return oom_kill_task(p);
}