d003f371b2
oom_kill.c assumes that PF_EXITING task should exit and free the memory soon. This is wrong in many ways and one important case is the coredump. A task can sleep in exit_mm() "forever" while the coredumping sub-thread can need more memory. Change the PF_EXITING checks to take SIGNAL_GROUP_COREDUMP into account, we add the new trivial helper for that. Note: this is only the first step, this patch doesn't try to solve other problems. The SIGNAL_GROUP_COREDUMP check is obviously racy, a task can participate in coredump after it was already observed in PF_EXITING state, so TIF_MEMDIE (which also blocks oom-killer) still can be wrongly set. fatal_signal_pending() can be true because of SIGNAL_GROUP_COREDUMP so out_of_memory() and mem_cgroup_out_of_memory() shouldn't blindly trust it. And even the name/usage of the new helper is confusing, an exiting thread can only free its ->mm if it is the only/last task in thread group. [akpm@linux-foundation.org: add comment] Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
110 lines
3 KiB
C
110 lines
3 KiB
C
#ifndef __INCLUDE_LINUX_OOM_H
|
|
#define __INCLUDE_LINUX_OOM_H
|
|
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/types.h>
|
|
#include <linux/nodemask.h>
|
|
#include <uapi/linux/oom.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,
|
|
};
|
|
|
|
enum oom_scan_t {
|
|
OOM_SCAN_OK, /* scan thread and find its badness */
|
|
OOM_SCAN_CONTINUE, /* do not consider thread for oom kill */
|
|
OOM_SCAN_ABORT, /* abort the iteration and return */
|
|
OOM_SCAN_SELECT, /* always select this thread first */
|
|
};
|
|
|
|
/* Thread is the potential origin of an oom condition; kill first on oom */
|
|
#define OOM_FLAG_ORIGIN ((__force oom_flags_t)0x1)
|
|
|
|
static inline void set_current_oom_origin(void)
|
|
{
|
|
current->signal->oom_flags |= OOM_FLAG_ORIGIN;
|
|
}
|
|
|
|
static inline void clear_current_oom_origin(void)
|
|
{
|
|
current->signal->oom_flags &= ~OOM_FLAG_ORIGIN;
|
|
}
|
|
|
|
static inline bool oom_task_origin(const struct task_struct *p)
|
|
{
|
|
return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
|
|
}
|
|
|
|
extern unsigned long oom_badness(struct task_struct *p,
|
|
struct mem_cgroup *memcg, const nodemask_t *nodemask,
|
|
unsigned long totalpages);
|
|
|
|
extern int oom_kills_count(void);
|
|
extern void note_oom_kill(void);
|
|
extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
|
|
unsigned int points, unsigned long totalpages,
|
|
struct mem_cgroup *memcg, nodemask_t *nodemask,
|
|
const char *message);
|
|
|
|
extern bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_flags);
|
|
extern void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_flags);
|
|
|
|
extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
|
|
int order, const nodemask_t *nodemask);
|
|
|
|
extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
|
|
unsigned long totalpages, const nodemask_t *nodemask,
|
|
bool force_kill);
|
|
|
|
extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
|
|
int order, nodemask_t *mask, bool force_kill);
|
|
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;
|
|
}
|
|
|
|
static inline bool oom_gfp_allowed(gfp_t gfp_mask)
|
|
{
|
|
return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY);
|
|
}
|
|
|
|
extern struct task_struct *find_lock_task_mm(struct task_struct *p);
|
|
|
|
static inline bool task_will_free_mem(struct task_struct *task)
|
|
{
|
|
/*
|
|
* A coredumping process may sleep for an extended period in exit_mm(),
|
|
* so the oom killer cannot assume that the process will promptly exit
|
|
* and release memory.
|
|
*/
|
|
return (task->flags & PF_EXITING) &&
|
|
!(task->signal->flags & SIGNAL_GROUP_COREDUMP);
|
|
}
|
|
|
|
/* sysctls */
|
|
extern int sysctl_oom_dump_tasks;
|
|
extern int sysctl_oom_kill_allocating_task;
|
|
extern int sysctl_panic_on_oom;
|
|
#endif /* _INCLUDE_LINUX_OOM_H */
|