kernel_optimize_test/include/linux/oom.h
yuzhoujian ef8444ea01 mm, oom: reorganize the oom report in dump_header
OOM report contains several sections.  The first one is the allocation
context that has triggered the OOM.  Then we have cpuset context followed
by the stack trace of the OOM path.  The tird one is the OOM memory
information.  Followed by the current memory state of all system tasks.
At last, we will show oom eligible tasks and the information about the
chosen oom victim.

One thing that makes parsing more awkward than necessary is that we do not
have a single and easily parsable line about the oom context.  This patch
is reorganizing the oom report to

1) who invoked oom and what was the allocation request

[  515.902945] tuned invoked oom-killer: gfp_mask=0x6200ca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=0

2) OOM stack trace

[  515.904273] CPU: 24 PID: 1809 Comm: tuned Not tainted 4.20.0-rc3+ #3
[  515.905518] Hardware name: Inspur SA5212M4/YZMB-00370-107, BIOS 4.1.10 11/14/2016
[  515.906821] Call Trace:
[  515.908062]  dump_stack+0x5a/0x73
[  515.909311]  dump_header+0x55/0x28c
[  515.914260]  oom_kill_process+0x2d8/0x300
[  515.916708]  out_of_memory+0x145/0x4a0
[  515.917932]  __alloc_pages_slowpath+0x7d2/0xa16
[  515.919157]  __alloc_pages_nodemask+0x277/0x290
[  515.920367]  filemap_fault+0x3d0/0x6c0
[  515.921529]  ? filemap_map_pages+0x2b8/0x420
[  515.922709]  ext4_filemap_fault+0x2c/0x40 [ext4]
[  515.923884]  __do_fault+0x20/0x80
[  515.925032]  __handle_mm_fault+0xbc0/0xe80
[  515.926195]  handle_mm_fault+0xfa/0x210
[  515.927357]  __do_page_fault+0x233/0x4c0
[  515.928506]  do_page_fault+0x32/0x140
[  515.929646]  ? page_fault+0x8/0x30
[  515.930770]  page_fault+0x1e/0x30

3) OOM memory information

[  515.958093] Mem-Info:
[  515.959647] active_anon:26501758 inactive_anon:1179809 isolated_anon:0
 active_file:4402672 inactive_file:483963 isolated_file:1344
 unevictable:0 dirty:4886753 writeback:0 unstable:0
 slab_reclaimable:148442 slab_unreclaimable:18741
 mapped:1347 shmem:1347 pagetables:58669 bounce:0
 free:88663 free_pcp:0 free_cma:0
...

4) current memory state of all system tasks

[  516.079544] [    744]     0   744     9211     1345   114688       82             0 systemd-journal
[  516.082034] [    787]     0   787    31764        0   143360       92             0 lvmetad
[  516.084465] [    792]     0   792    10930        1   110592      208         -1000 systemd-udevd
[  516.086865] [   1199]     0  1199    13866        0   131072      112         -1000 auditd
[  516.089190] [   1222]     0  1222    31990        1   110592      157             0 smartd
[  516.091477] [   1225]     0  1225     4864       85    81920       43             0 irqbalance
[  516.093712] [   1226]     0  1226    52612        0   258048      426             0 abrtd
[  516.112128] [   1280]     0  1280   109774       55   299008      400             0 NetworkManager
[  516.113998] [   1295]     0  1295    28817       37    69632       24             0 ksmtuned
[  516.144596] [  10718]     0 10718  2622484  1721372 15998976   267219             0 panic
[  516.145792] [  10719]     0 10719  2622484  1164767  9818112    53576             0 panic
[  516.146977] [  10720]     0 10720  2622484  1174361  9904128    53709             0 panic
[  516.148163] [  10721]     0 10721  2622484  1209070 10194944    54824             0 panic
[  516.149329] [  10722]     0 10722  2622484  1745799 14774272    91138             0 panic

5) oom context (contrains and the chosen victim).

oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0-1,task=panic,pid=10737,uid=0

An admin can easily get the full oom context at a single line which
makes parsing much easier.

Link: http://lkml.kernel.org/r/1542799799-36184-1-git-send-email-ufo19890607@gmail.com
Signed-off-by: yuzhoujian <yuzhoujian@didichuxing.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <yang.s@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 12:11:48 -08:00

131 lines
3.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __INCLUDE_LINUX_OOM_H
#define __INCLUDE_LINUX_OOM_H
#include <linux/sched/signal.h>
#include <linux/types.h>
#include <linux/nodemask.h>
#include <uapi/linux/oom.h>
#include <linux/sched/coredump.h> /* MMF_* */
#include <linux/mm.h> /* VM_FAULT* */
struct zonelist;
struct notifier_block;
struct mem_cgroup;
struct task_struct;
enum oom_constraint {
CONSTRAINT_NONE,
CONSTRAINT_CPUSET,
CONSTRAINT_MEMORY_POLICY,
CONSTRAINT_MEMCG,
};
/*
* Details of the page allocation that triggered the oom killer that are used to
* determine what should be killed.
*/
struct oom_control {
/* Used to determine cpuset */
struct zonelist *zonelist;
/* Used to determine mempolicy */
nodemask_t *nodemask;
/* Memory cgroup in which oom is invoked, or NULL for global oom */
struct mem_cgroup *memcg;
/* Used to determine cpuset and node locality requirement */
const gfp_t gfp_mask;
/*
* order == -1 means the oom kill is required by sysrq, otherwise only
* for display purposes.
*/
const int order;
/* Used by oom implementation, do not set */
unsigned long totalpages;
struct task_struct *chosen;
unsigned long chosen_points;
/* Used to print the constraint info. */
enum oom_constraint constraint;
};
extern struct mutex oom_lock;
static inline void set_current_oom_origin(void)
{
current->signal->oom_flag_origin = true;
}
static inline void clear_current_oom_origin(void)
{
current->signal->oom_flag_origin = false;
}
static inline bool oom_task_origin(const struct task_struct *p)
{
return p->signal->oom_flag_origin;
}
static inline bool tsk_is_oom_victim(struct task_struct * tsk)
{
return tsk->signal->oom_mm;
}
/*
* Use this helper if tsk->mm != mm and the victim mm needs a special
* handling. This is guaranteed to stay true after once set.
*/
static inline bool mm_is_oom_victim(struct mm_struct *mm)
{
return test_bit(MMF_OOM_VICTIM, &mm->flags);
}
/*
* Checks whether a page fault on the given mm is still reliable.
* This is no longer true if the oom reaper started to reap the
* address space which is reflected by MMF_UNSTABLE flag set in
* the mm. At that moment any !shared mapping would lose the content
* and could cause a memory corruption (zero pages instead of the
* original content).
*
* User should call this before establishing a page table entry for
* a !shared mapping and under the proper page table lock.
*
* Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise.
*/
static inline vm_fault_t check_stable_address_space(struct mm_struct *mm)
{
if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags)))
return VM_FAULT_SIGBUS;
return 0;
}
bool __oom_reap_task_mm(struct mm_struct *mm);
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
extern bool out_of_memory(struct oom_control *oc);
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_disable(signed long timeout);
extern void oom_killer_enable(void);
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 /* _INCLUDE_LINUX_OOM_H */