linux_dsm_epyc7002/include/linux/oom.h
Johannes Weiner dc56401fc9 mm: oom_kill: simplify OOM killer locking
The zonelist locking and the oom_sem are two overlapping locks that are
used to serialize global OOM killing against different things.

The historical zonelist locking serializes OOM kills from allocations with
overlapping zonelists against each other to prevent killing more tasks
than necessary in the same memory domain.  Only when neither tasklists nor
zonelists from two concurrent OOM kills overlap (tasks in separate memcgs
bound to separate nodes) are OOM kills allowed to execute in parallel.

The younger oom_sem is a read-write lock to serialize OOM killing against
the PM code trying to disable the OOM killer altogether.

However, the OOM killer is a fairly cold error path, there is really no
reason to optimize for highly performant and concurrent OOM kills.  And
the oom_sem is just flat-out redundant.

Replace both locking schemes with a single global mutex serializing OOM
kills regardless of context.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 17:49:43 -07:00

103 lines
2.9 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)
extern struct mutex oom_lock;
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 void mark_oom_victim(struct task_struct *tsk);
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 void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
int order, const nodemask_t *nodemask,
struct mem_cgroup *memcg);
extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
unsigned long totalpages, const nodemask_t *nodemask,
bool force_kill);
extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *mask, bool force_kill);
extern void exit_oom_victim(void);
extern int register_oom_notifier(struct notifier_block *nb);
extern int unregister_oom_notifier(struct notifier_block *nb);
extern bool oom_killer_disabled;
extern bool oom_killer_disable(void);
extern void oom_killer_enable(void);
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 */