kernel-ark/include/linux/oom.h
David Rientjes 43362a4977 oom: fix race while temporarily setting current's oom_score_adj
test_set_oom_score_adj() was introduced in 72788c3856 ("oom: replace
PF_OOM_ORIGIN with toggling oom_score_adj") to temporarily elevate
current's oom_score_adj for ksm and swapoff without requiring an
additional per-process flag.

Using that function to both set oom_score_adj to OOM_SCORE_ADJ_MAX and
then reinstate the previous value is racy since it's possible that
userspace can set the value to something else itself before the old value
is reinstated.  That results in userspace setting current's oom_score_adj
to a different value and then the kernel immediately setting it back to
its previous value without notification.

To fix this, a new compare_swap_oom_score_adj() function is introduced
with the same semantics as the compare and swap CAS instruction, or
CMPXCHG on x86.  It is used to reinstate the previous value of
oom_score_adj if and only if the present value is the same as the old
value.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Ying Han <yinghan@google.com>
Cc: 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>
2011-10-31 17:30:45 -07:00

76 lines
1.9 KiB
C

#ifndef __INCLUDE_LINUX_OOM_H
#define __INCLUDE_LINUX_OOM_H
/*
* /proc/<pid>/oom_adj is deprecated, see
* Documentation/feature-removal-schedule.txt.
*
* /proc/<pid>/oom_adj set to -17 protects from the oom-killer
*/
#define OOM_DISABLE (-17)
/* inclusive */
#define OOM_ADJUST_MIN (-16)
#define OOM_ADJUST_MAX 15
/*
* /proc/<pid>/oom_score_adj set to OOM_SCORE_ADJ_MIN disables oom killing for
* pid.
*/
#define OOM_SCORE_ADJ_MIN (-1000)
#define OOM_SCORE_ADJ_MAX 1000
#ifdef __KERNEL__
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/nodemask.h>
struct zonelist;
struct notifier_block;
struct mem_cgroup;
struct task_struct;
/*
* Types of limitations to the nodes from which allocations may occur
*/
enum oom_constraint {
CONSTRAINT_NONE,
CONSTRAINT_CPUSET,
CONSTRAINT_MEMORY_POLICY,
CONSTRAINT_MEMCG,
};
extern void compare_swap_oom_score_adj(int old_val, int new_val);
extern int test_set_oom_score_adj(int new_val);
extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
const nodemask_t *nodemask, unsigned long totalpages);
extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *mask);
extern int register_oom_notifier(struct notifier_block *nb);
extern int unregister_oom_notifier(struct notifier_block *nb);
extern bool oom_killer_disabled;
static inline void oom_killer_disable(void)
{
oom_killer_disabled = true;
}
static inline void oom_killer_enable(void)
{
oom_killer_disabled = false;
}
extern struct task_struct *find_lock_task_mm(struct task_struct *p);
/* sysctls */
extern int sysctl_oom_dump_tasks;
extern int sysctl_oom_kill_allocating_task;
extern int sysctl_panic_on_oom;
#endif /* __KERNEL__*/
#endif /* _INCLUDE_LINUX_OOM_H */