2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 05:04:00 +08:00
linux-next/mm/oom_kill.c
Tetsuo Handa d342a0b386 mm,oom: don't kill global init via memory.oom.group
Since setting global init process to some memory cgroup is technically
possible, oom_kill_memcg_member() must check it.

  Tasks in /test1 are going to be killed due to memory.oom.group set
  Memory cgroup out of memory: Killed process 1 (systemd) total-vm:43400kB, anon-rss:1228kB, file-rss:3992kB, shmem-rss:0kB
  oom_reaper: reaped process 1 (systemd), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
  Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000008b

#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>

int main(int argc, char *argv[])
{
	static char buffer[10485760];
	static int pipe_fd[2] = { EOF, EOF };
	unsigned int i;
	int fd;
	char buf[64] = { };
	if (pipe(pipe_fd))
		return 1;
	if (chdir("/sys/fs/cgroup/"))
		return 1;
	fd = open("cgroup.subtree_control", O_WRONLY);
	write(fd, "+memory", 7);
	close(fd);
	mkdir("test1", 0755);
	fd = open("test1/memory.oom.group", O_WRONLY);
	write(fd, "1", 1);
	close(fd);
	fd = open("test1/cgroup.procs", O_WRONLY);
	write(fd, "1", 1);
	snprintf(buf, sizeof(buf) - 1, "%d", getpid());
	write(fd, buf, strlen(buf));
	close(fd);
	snprintf(buf, sizeof(buf) - 1, "%lu", sizeof(buffer) * 5);
	fd = open("test1/memory.max", O_WRONLY);
	write(fd, buf, strlen(buf));
	close(fd);
	for (i = 0; i < 10; i++)
		if (fork() == 0) {
			char c;
			close(pipe_fd[1]);
			read(pipe_fd[0], &c, 1);
			memset(buffer, 0, sizeof(buffer));
			sleep(3);
			_exit(0);
		}
	close(pipe_fd[0]);
	close(pipe_fd[1]);
	sleep(3);
	return 0;
}

[   37.052923][ T9185] a.out invoked oom-killer: gfp_mask=0xcc0(GFP_KERNEL), order=0, oom_score_adj=0
[   37.056169][ T9185] CPU: 4 PID: 9185 Comm: a.out Kdump: loaded Not tainted 5.0.0-rc4-next-20190131 #280
[   37.059205][ T9185] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018
[   37.062954][ T9185] Call Trace:
[   37.063976][ T9185]  dump_stack+0x67/0x95
[   37.065263][ T9185]  dump_header+0x51/0x570
[   37.066619][ T9185]  ? trace_hardirqs_on+0x3f/0x110
[   37.068171][ T9185]  ? _raw_spin_unlock_irqrestore+0x3d/0x70
[   37.069967][ T9185]  oom_kill_process+0x18d/0x210
[   37.071515][ T9185]  out_of_memory+0x11b/0x380
[   37.072936][ T9185]  mem_cgroup_out_of_memory+0xb6/0xd0
[   37.074601][ T9185]  try_charge+0x790/0x820
[   37.076021][ T9185]  mem_cgroup_try_charge+0x42/0x1d0
[   37.077629][ T9185]  mem_cgroup_try_charge_delay+0x11/0x30
[   37.079370][ T9185]  do_anonymous_page+0x105/0x5e0
[   37.080939][ T9185]  __handle_mm_fault+0x9cb/0x1070
[   37.082485][ T9185]  handle_mm_fault+0x1b2/0x3a0
[   37.083819][ T9185]  ? handle_mm_fault+0x47/0x3a0
[   37.085181][ T9185]  __do_page_fault+0x255/0x4c0
[   37.086529][ T9185]  do_page_fault+0x28/0x260
[   37.087788][ T9185]  ? page_fault+0x8/0x30
[   37.088978][ T9185]  page_fault+0x1e/0x30
[   37.090142][ T9185] RIP: 0033:0x7f8b183aefe0
[   37.091433][ T9185] Code: 20 f3 44 0f 7f 44 17 d0 f3 44 0f 7f 47 30 f3 44 0f 7f 44 17 c0 48 01 fa 48 83 e2 c0 48 39 d1 74 a3 66 0f 1f 84 00 00 00 00 00 <66> 44 0f 7f 01 66 44 0f 7f 41 10 66 44 0f 7f 41 20 66 44 0f 7f 41
[   37.096917][ T9185] RSP: 002b:00007fffc5d329e8 EFLAGS: 00010206
[   37.098615][ T9185] RAX: 00000000006010e0 RBX: 0000000000000008 RCX: 0000000000c30000
[   37.100905][ T9185] RDX: 00000000010010c0 RSI: 0000000000000000 RDI: 00000000006010e0
[   37.103349][ T9185] RBP: 0000000000000000 R08: 00007f8b188f4740 R09: 0000000000000000
[   37.105797][ T9185] R10: 00007fffc5d32420 R11: 00007f8b183aef40 R12: 0000000000000005
[   37.108228][ T9185] R13: 0000000000000000 R14: ffffffffffffffff R15: 0000000000000000
[   37.110840][ T9185] memory: usage 51200kB, limit 51200kB, failcnt 125
[   37.113045][ T9185] memory+swap: usage 0kB, limit 9007199254740988kB, failcnt 0
[   37.115808][ T9185] kmem: usage 0kB, limit 9007199254740988kB, failcnt 0
[   37.117660][ T9185] Memory cgroup stats for /test1: cache:0KB rss:49484KB rss_huge:30720KB shmem:0KB mapped_file:0KB dirty:0KB writeback:0KB inactive_anon:0KB active_anon:49700KB inactive_file:0KB active_file:0KB unevictable:0KB
[   37.123371][ T9185] oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0,oom_memcg=/test1,task_memcg=/test1,task=a.out,pid=9188,uid=0
[   37.128158][ T9185] Memory cgroup out of memory: Killed process 9188 (a.out) total-vm:14456kB, anon-rss:10324kB, file-rss:504kB, shmem-rss:0kB
[   37.132710][ T9185] Tasks in /test1 are going to be killed due to memory.oom.group set
[   37.132833][   T54] oom_reaper: reaped process 9188 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.135498][ T9185] Memory cgroup out of memory: Killed process 1 (systemd) total-vm:43400kB, anon-rss:1228kB, file-rss:3992kB, shmem-rss:0kB
[   37.143434][ T9185] Memory cgroup out of memory: Killed process 9182 (a.out) total-vm:14456kB, anon-rss:76kB, file-rss:588kB, shmem-rss:0kB
[   37.144328][   T54] oom_reaper: reaped process 1 (systemd), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.147585][ T9185] Memory cgroup out of memory: Killed process 9183 (a.out) total-vm:14456kB, anon-rss:6228kB, file-rss:512kB, shmem-rss:0kB
[   37.157222][ T9185] Memory cgroup out of memory: Killed process 9184 (a.out) total-vm:14456kB, anon-rss:6228kB, file-rss:508kB, shmem-rss:0kB
[   37.157259][ T9185] Memory cgroup out of memory: Killed process 9185 (a.out) total-vm:14456kB, anon-rss:6228kB, file-rss:512kB, shmem-rss:0kB
[   37.157291][ T9185] Memory cgroup out of memory: Killed process 9186 (a.out) total-vm:14456kB, anon-rss:4180kB, file-rss:508kB, shmem-rss:0kB
[   37.157306][   T54] oom_reaper: reaped process 9183 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.157328][ T9185] Memory cgroup out of memory: Killed process 9187 (a.out) total-vm:14456kB, anon-rss:4180kB, file-rss:512kB, shmem-rss:0kB
[   37.157452][ T9185] Memory cgroup out of memory: Killed process 9189 (a.out) total-vm:14456kB, anon-rss:6228kB, file-rss:512kB, shmem-rss:0kB
[   37.158733][ T9185] Memory cgroup out of memory: Killed process 9190 (a.out) total-vm:14456kB, anon-rss:552kB, file-rss:512kB, shmem-rss:0kB
[   37.160083][   T54] oom_reaper: reaped process 9186 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.160187][   T54] oom_reaper: reaped process 9189 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.206941][   T54] oom_reaper: reaped process 9185 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.212300][ T9185] Memory cgroup out of memory: Killed process 9191 (a.out) total-vm:14456kB, anon-rss:4180kB, file-rss:512kB, shmem-rss:0kB
[   37.212317][   T54] oom_reaper: reaped process 9190 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.218860][ T9185] Memory cgroup out of memory: Killed process 9192 (a.out) total-vm:14456kB, anon-rss:1080kB, file-rss:512kB, shmem-rss:0kB
[   37.227667][   T54] oom_reaper: reaped process 9192 (a.out), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
[   37.292323][ T9193] abrt-hook-ccpp (9193) used greatest stack depth: 10480 bytes left
[   37.351843][    T1] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000008b
[   37.354833][    T1] CPU: 7 PID: 1 Comm: systemd Kdump: loaded Not tainted 5.0.0-rc4-next-20190131 #280
[   37.357876][    T1] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018
[   37.361685][    T1] Call Trace:
[   37.363239][    T1]  dump_stack+0x67/0x95
[   37.365010][    T1]  panic+0xfc/0x2b0
[   37.366853][    T1]  do_exit+0xd55/0xd60
[   37.368595][    T1]  do_group_exit+0x47/0xc0
[   37.370415][    T1]  get_signal+0x32a/0x920
[   37.372449][    T1]  ? _raw_spin_unlock_irqrestore+0x3d/0x70
[   37.374596][    T1]  do_signal+0x32/0x6e0
[   37.376430][    T1]  ? exit_to_usermode_loop+0x26/0x9b
[   37.378418][    T1]  ? prepare_exit_to_usermode+0xa8/0xd0
[   37.380571][    T1]  exit_to_usermode_loop+0x3e/0x9b
[   37.382588][    T1]  prepare_exit_to_usermode+0xa8/0xd0
[   37.384594][    T1]  ? page_fault+0x8/0x30
[   37.386453][    T1]  retint_user+0x8/0x18
[   37.388160][    T1] RIP: 0033:0x7f42c06974a8
[   37.389922][    T1] Code: Bad RIP value.
[   37.391788][    T1] RSP: 002b:00007ffc3effd388 EFLAGS: 00010213
[   37.394075][    T1] RAX: 000000000000000e RBX: 00007ffc3effd390 RCX: 0000000000000000
[   37.396963][    T1] RDX: 000000000000002a RSI: 00007ffc3effd390 RDI: 0000000000000004
[   37.399550][    T1] RBP: 00007ffc3effd680 R08: 0000000000000000 R09: 0000000000000000
[   37.402334][    T1] R10: 00000000ffffffff R11: 0000000000000246 R12: 0000000000000001
[   37.404890][    T1] R13: ffffffffffffffff R14: 0000000000000884 R15: 000056460b1ac3b0

Link: http://lkml.kernel.org/r/201902010336.x113a4EO027170@www262.sakura.ne.jp
Fixes: 3d8b38eb81 ("mm, oom: introduce memory.oom.group")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-05 21:07:19 -08:00

1128 lines
30 KiB
C

/*
* linux/mm/oom_kill.c
*
* Copyright (C) 1998,2000 Rik van Riel
* Thanks go out to Claus Fischer for some serious inspiration and
* for goading me into coding this file...
* Copyright (C) 2010 Google, Inc.
* Rewritten by David Rientjes
*
* The routines in this file are used to kill a process when
* we're seriously out of memory. This gets called from __alloc_pages()
* in mm/page_alloc.c when we really run out of memory.
*
* Since we won't call these routines often (on a well-configured
* machine) this file will double as a 'coding guide' and a signpost
* for newbie kernel hackers. It features several pointers to major
* kernel subsystems and hints as to where to find out what things do.
*/
#include <linux/oom.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
#include <linux/export.h>
#include <linux/notifier.h>
#include <linux/memcontrol.h>
#include <linux/mempolicy.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/freezer.h>
#include <linux/ftrace.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/init.h>
#include <linux/mmu_notifier.h>
#include <asm/tlb.h>
#include "internal.h"
#include "slab.h"
#define CREATE_TRACE_POINTS
#include <trace/events/oom.h>
int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks = 1;
/*
* Serializes oom killer invocations (out_of_memory()) from all contexts to
* prevent from over eager oom killing (e.g. when the oom killer is invoked
* from different domains).
*
* oom_killer_disable() relies on this lock to stabilize oom_killer_disabled
* and mark_oom_victim
*/
DEFINE_MUTEX(oom_lock);
#ifdef CONFIG_NUMA
/**
* has_intersects_mems_allowed() - check task eligiblity for kill
* @start: task struct of which task to consider
* @mask: nodemask passed to page allocator for mempolicy ooms
*
* Task eligibility is determined by whether or not a candidate task, @tsk,
* shares the same mempolicy nodes as current if it is bound by such a policy
* and whether or not it has the same set of allowed cpuset nodes.
*/
static bool has_intersects_mems_allowed(struct task_struct *start,
const nodemask_t *mask)
{
struct task_struct *tsk;
bool ret = false;
rcu_read_lock();
for_each_thread(start, tsk) {
if (mask) {
/*
* If this is a mempolicy constrained oom, tsk's
* cpuset is irrelevant. Only return true if its
* mempolicy intersects current, otherwise it may be
* needlessly killed.
*/
ret = mempolicy_nodemask_intersects(tsk, mask);
} else {
/*
* This is not a mempolicy constrained oom, so only
* check the mems of tsk's cpuset.
*/
ret = cpuset_mems_allowed_intersects(current, tsk);
}
if (ret)
break;
}
rcu_read_unlock();
return ret;
}
#else
static bool has_intersects_mems_allowed(struct task_struct *tsk,
const nodemask_t *mask)
{
return true;
}
#endif /* CONFIG_NUMA */
/*
* The process p may have detached its own ->mm while exiting or through
* use_mm(), but one or more of its subthreads may still have a valid
* pointer. Return p, or any of its subthreads with a valid ->mm, with
* task_lock() held.
*/
struct task_struct *find_lock_task_mm(struct task_struct *p)
{
struct task_struct *t;
rcu_read_lock();
for_each_thread(p, t) {
task_lock(t);
if (likely(t->mm))
goto found;
task_unlock(t);
}
t = NULL;
found:
rcu_read_unlock();
return t;
}
/*
* order == -1 means the oom kill is required by sysrq, otherwise only
* for display purposes.
*/
static inline bool is_sysrq_oom(struct oom_control *oc)
{
return oc->order == -1;
}
static inline bool is_memcg_oom(struct oom_control *oc)
{
return oc->memcg != NULL;
}
/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
if (is_global_init(p))
return true;
if (p->flags & PF_KTHREAD)
return true;
/* When mem_cgroup_out_of_memory() and p is not member of the group */
if (memcg && !task_in_mem_cgroup(p, memcg))
return true;
/* p may not have freeable memory in nodemask */
if (!has_intersects_mems_allowed(p, nodemask))
return true;
return false;
}
/*
* Print out unreclaimble slabs info when unreclaimable slabs amount is greater
* than all user memory (LRU pages)
*/
static bool is_dump_unreclaim_slabs(void)
{
unsigned long nr_lru;
nr_lru = global_node_page_state(NR_ACTIVE_ANON) +
global_node_page_state(NR_INACTIVE_ANON) +
global_node_page_state(NR_ACTIVE_FILE) +
global_node_page_state(NR_INACTIVE_FILE) +
global_node_page_state(NR_ISOLATED_ANON) +
global_node_page_state(NR_ISOLATED_FILE) +
global_node_page_state(NR_UNEVICTABLE);
return (global_node_page_state(NR_SLAB_UNRECLAIMABLE) > nr_lru);
}
/**
* oom_badness - heuristic function to determine which candidate task to kill
* @p: task struct of which task we should calculate
* @totalpages: total present RAM allowed for page allocation
* @memcg: task's memory controller, if constrained
* @nodemask: nodemask passed to page allocator for mempolicy ooms
*
* The heuristic for determining which task to kill is made to be as simple and
* predictable as possible. The goal is to return the highest value for the
* task consuming the most memory to avoid subsequent oom failures.
*/
unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
long points;
long adj;
if (oom_unkillable_task(p, memcg, nodemask))
return 0;
p = find_lock_task_mm(p);
if (!p)
return 0;
/*
* Do not even consider tasks which are explicitly marked oom
* unkillable or have been already oom reaped or the are in
* the middle of vfork
*/
adj = (long)p->signal->oom_score_adj;
if (adj == OOM_SCORE_ADJ_MIN ||
test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
in_vfork(p)) {
task_unlock(p);
return 0;
}
/*
* The baseline for the badness score is the proportion of RAM that each
* task's rss, pagetable and swap space use.
*/
points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
mm_pgtables_bytes(p->mm) / PAGE_SIZE;
task_unlock(p);
/* Normalize to oom_score_adj units */
adj *= totalpages / 1000;
points += adj;
/*
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
return points > 0 ? points : 1;
}
static const char * const oom_constraint_text[] = {
[CONSTRAINT_NONE] = "CONSTRAINT_NONE",
[CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET",
[CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY",
[CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG",
};
/*
* Determine the type of allocation constraint.
*/
static enum oom_constraint constrained_alloc(struct oom_control *oc)
{
struct zone *zone;
struct zoneref *z;
enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask);
bool cpuset_limited = false;
int nid;
if (is_memcg_oom(oc)) {
oc->totalpages = mem_cgroup_get_max(oc->memcg) ?: 1;
return CONSTRAINT_MEMCG;
}
/* Default to all available memory */
oc->totalpages = totalram_pages() + total_swap_pages;
if (!IS_ENABLED(CONFIG_NUMA))
return CONSTRAINT_NONE;
if (!oc->zonelist)
return CONSTRAINT_NONE;
/*
* Reach here only when __GFP_NOFAIL is used. So, we should avoid
* to kill current.We have to random task kill in this case.
* Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
*/
if (oc->gfp_mask & __GFP_THISNODE)
return CONSTRAINT_NONE;
/*
* This is not a __GFP_THISNODE allocation, so a truncated nodemask in
* the page allocator means a mempolicy is in effect. Cpuset policy
* is enforced in get_page_from_freelist().
*/
if (oc->nodemask &&
!nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
oc->totalpages = total_swap_pages;
for_each_node_mask(nid, *oc->nodemask)
oc->totalpages += node_spanned_pages(nid);
return CONSTRAINT_MEMORY_POLICY;
}
/* Check this allocation failure is caused by cpuset's wall function */
for_each_zone_zonelist_nodemask(zone, z, oc->zonelist,
high_zoneidx, oc->nodemask)
if (!cpuset_zone_allowed(zone, oc->gfp_mask))
cpuset_limited = true;
if (cpuset_limited) {
oc->totalpages = total_swap_pages;
for_each_node_mask(nid, cpuset_current_mems_allowed)
oc->totalpages += node_spanned_pages(nid);
return CONSTRAINT_CPUSET;
}
return CONSTRAINT_NONE;
}
static int oom_evaluate_task(struct task_struct *task, void *arg)
{
struct oom_control *oc = arg;
unsigned long points;
if (oom_unkillable_task(task, NULL, oc->nodemask))
goto next;
/*
* This task already has access to memory reserves and is being killed.
* Don't allow any other task to have access to the reserves unless
* the task has MMF_OOM_SKIP because chances that it would release
* any memory is quite low.
*/
if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) {
if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags))
goto next;
goto abort;
}
/*
* If task is allocating a lot of memory and has been marked to be
* killed first if it triggers an oom, then select it.
*/
if (oom_task_origin(task)) {
points = ULONG_MAX;
goto select;
}
points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
if (!points || points < oc->chosen_points)
goto next;
/* Prefer thread group leaders for display purposes */
if (points == oc->chosen_points && thread_group_leader(oc->chosen))
goto next;
select:
if (oc->chosen)
put_task_struct(oc->chosen);
get_task_struct(task);
oc->chosen = task;
oc->chosen_points = points;
next:
return 0;
abort:
if (oc->chosen)
put_task_struct(oc->chosen);
oc->chosen = (void *)-1UL;
return 1;
}
/*
* Simple selection loop. We choose the process with the highest number of
* 'points'. In case scan was aborted, oc->chosen is set to -1.
*/
static void select_bad_process(struct oom_control *oc)
{
if (is_memcg_oom(oc))
mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
else {
struct task_struct *p;
rcu_read_lock();
for_each_process(p)
if (oom_evaluate_task(p, oc))
break;
rcu_read_unlock();
}
oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
}
/**
* dump_tasks - dump current memory state of all system tasks
* @memcg: current's memory controller, if constrained
* @nodemask: nodemask passed to page allocator for mempolicy ooms
*
* Dumps the current memory state of all eligible tasks. Tasks not in the same
* memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
* are not shown.
* State information includes task's pid, uid, tgid, vm size, rss,
* pgtables_bytes, swapents, oom_score_adj value, and name.
*/
static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
struct task_struct *p;
struct task_struct *task;
pr_info("Tasks state (memory values in pages):\n");
pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n");
rcu_read_lock();
for_each_process(p) {
if (oom_unkillable_task(p, memcg, nodemask))
continue;
task = find_lock_task_mm(p);
if (!task) {
/*
* This is a kthread or all of p's threads have already
* detached their mm's. There's no need to report
* them; they can't be oom killed anyway.
*/
continue;
}
pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
task->pid, from_kuid(&init_user_ns, task_uid(task)),
task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
mm_pgtables_bytes(task->mm),
get_mm_counter(task->mm, MM_SWAPENTS),
task->signal->oom_score_adj, task->comm);
task_unlock(task);
}
rcu_read_unlock();
}
static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
{
/* one line summary of the oom killer context. */
pr_info("oom-kill:constraint=%s,nodemask=%*pbl",
oom_constraint_text[oc->constraint],
nodemask_pr_args(oc->nodemask));
cpuset_print_current_mems_allowed();
mem_cgroup_print_oom_context(oc->memcg, victim);
pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid,
from_kuid(&init_user_ns, task_uid(victim)));
}
static void dump_header(struct oom_control *oc, struct task_struct *p)
{
pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n",
current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order,
current->signal->oom_score_adj);
if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
pr_warn("COMPACTION is disabled!!!\n");
dump_stack();
if (is_memcg_oom(oc))
mem_cgroup_print_oom_meminfo(oc->memcg);
else {
show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
if (is_dump_unreclaim_slabs())
dump_unreclaimable_slab();
}
if (sysctl_oom_dump_tasks)
dump_tasks(oc->memcg, oc->nodemask);
if (p)
dump_oom_summary(oc, p);
}
/*
* Number of OOM victims in flight
*/
static atomic_t oom_victims = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
static bool oom_killer_disabled __read_mostly;
#define K(x) ((x) << (PAGE_SHIFT-10))
/*
* task->mm can be NULL if the task is the exited group leader. So to
* determine whether the task is using a particular mm, we examine all the
* task's threads: if one of those is using this mm then this task was also
* using it.
*/
bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
{
struct task_struct *t;
for_each_thread(p, t) {
struct mm_struct *t_mm = READ_ONCE(t->mm);
if (t_mm)
return t_mm == mm;
}
return false;
}
#ifdef CONFIG_MMU
/*
* OOM Reaper kernel thread which tries to reap the memory used by the OOM
* victim (if that is possible) to help the OOM killer to move on.
*/
static struct task_struct *oom_reaper_th;
static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);
bool __oom_reap_task_mm(struct mm_struct *mm)
{
struct vm_area_struct *vma;
bool ret = true;
/*
* Tell all users of get_user/copy_from_user etc... that the content
* is no longer stable. No barriers really needed because unmapping
* should imply barriers already and the reader would hit a page fault
* if it stumbled over a reaped memory.
*/
set_bit(MMF_UNSTABLE, &mm->flags);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
/*
* Only anonymous pages have a good chance to be dropped
* without additional steps which we cannot afford as we
* are OOM already.
*
* We do not even care about fs backed pages because all
* which are reclaimable have already been reclaimed and
* we do not want to block exit_mmap by keeping mm ref
* count elevated without a good reason.
*/
if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
struct mmu_notifier_range range;
struct mmu_gather tlb;
mmu_notifier_range_init(&range, mm, vma->vm_start,
vma->vm_end);
tlb_gather_mmu(&tlb, mm, range.start, range.end);
if (mmu_notifier_invalidate_range_start_nonblock(&range)) {
tlb_finish_mmu(&tlb, range.start, range.end);
ret = false;
continue;
}
unmap_page_range(&tlb, vma, range.start, range.end, NULL);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb, range.start, range.end);
}
}
return ret;
}
/*
* Reaps the address space of the give task.
*
* Returns true on success and false if none or part of the address space
* has been reclaimed and the caller should retry later.
*/
static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
{
bool ret = true;
if (!down_read_trylock(&mm->mmap_sem)) {
trace_skip_task_reaping(tsk->pid);
return false;
}
/*
* MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
* work on the mm anymore. The check for MMF_OOM_SKIP must run
* under mmap_sem for reading because it serializes against the
* down_write();up_write() cycle in exit_mmap().
*/
if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
trace_skip_task_reaping(tsk->pid);
goto out_unlock;
}
trace_start_task_reaping(tsk->pid);
/* failed to reap part of the address space. Try again later */
ret = __oom_reap_task_mm(mm);
if (!ret)
goto out_finish;
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
K(get_mm_counter(mm, MM_FILEPAGES)),
K(get_mm_counter(mm, MM_SHMEMPAGES)));
out_finish:
trace_finish_task_reaping(tsk->pid);
out_unlock:
up_read(&mm->mmap_sem);
return ret;
}
#define MAX_OOM_REAP_RETRIES 10
static void oom_reap_task(struct task_struct *tsk)
{
int attempts = 0;
struct mm_struct *mm = tsk->signal->oom_mm;
/* Retry the down_read_trylock(mmap_sem) a few times */
while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
if (attempts <= MAX_OOM_REAP_RETRIES ||
test_bit(MMF_OOM_SKIP, &mm->flags))
goto done;
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
debug_show_all_locks();
done:
tsk->oom_reaper_list = NULL;
/*
* Hide this mm from OOM killer because it has been either reaped or
* somebody can't call up_write(mmap_sem).
*/
set_bit(MMF_OOM_SKIP, &mm->flags);
/* Drop a reference taken by wake_oom_reaper */
put_task_struct(tsk);
}
static int oom_reaper(void *unused)
{
while (true) {
struct task_struct *tsk = NULL;
wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
spin_lock(&oom_reaper_lock);
if (oom_reaper_list != NULL) {
tsk = oom_reaper_list;
oom_reaper_list = tsk->oom_reaper_list;
}
spin_unlock(&oom_reaper_lock);
if (tsk)
oom_reap_task(tsk);
}
return 0;
}
static void wake_oom_reaper(struct task_struct *tsk)
{
/* mm is already queued? */
if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
return;
get_task_struct(tsk);
spin_lock(&oom_reaper_lock);
tsk->oom_reaper_list = oom_reaper_list;
oom_reaper_list = tsk;
spin_unlock(&oom_reaper_lock);
trace_wake_reaper(tsk->pid);
wake_up(&oom_reaper_wait);
}
static int __init oom_init(void)
{
oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
return 0;
}
subsys_initcall(oom_init)
#else
static inline void wake_oom_reaper(struct task_struct *tsk)
{
}
#endif /* CONFIG_MMU */
/**
* mark_oom_victim - mark the given task as OOM victim
* @tsk: task to mark
*
* Has to be called with oom_lock held and never after
* oom has been disabled already.
*
* tsk->mm has to be non NULL and caller has to guarantee it is stable (either
* under task_lock or operate on the current).
*/
static void mark_oom_victim(struct task_struct *tsk)
{
struct mm_struct *mm = tsk->mm;
WARN_ON(oom_killer_disabled);
/* OOM killer might race with memcg OOM */
if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
return;
/* oom_mm is bound to the signal struct life time. */
if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
mmgrab(tsk->signal->oom_mm);
set_bit(MMF_OOM_VICTIM, &mm->flags);
}
/*
* Make sure that the task is woken up from uninterruptible sleep
* if it is frozen because OOM killer wouldn't be able to free
* any memory and livelock. freezing_slow_path will tell the freezer
* that TIF_MEMDIE tasks should be ignored.
*/
__thaw_task(tsk);
atomic_inc(&oom_victims);
trace_mark_victim(tsk->pid);
}
/**
* exit_oom_victim - note the exit of an OOM victim
*/
void exit_oom_victim(void)
{
clear_thread_flag(TIF_MEMDIE);
if (!atomic_dec_return(&oom_victims))
wake_up_all(&oom_victims_wait);
}
/**
* oom_killer_enable - enable OOM killer
*/
void oom_killer_enable(void)
{
oom_killer_disabled = false;
pr_info("OOM killer enabled.\n");
}
/**
* oom_killer_disable - disable OOM killer
* @timeout: maximum timeout to wait for oom victims in jiffies
*
* Forces all page allocations to fail rather than trigger OOM killer.
* Will block and wait until all OOM victims are killed or the given
* timeout expires.
*
* The function cannot be called when there are runnable user tasks because
* the userspace would see unexpected allocation failures as a result. Any
* new usage of this function should be consulted with MM people.
*
* Returns true if successful and false if the OOM killer cannot be
* disabled.
*/
bool oom_killer_disable(signed long timeout)
{
signed long ret;
/*
* Make sure to not race with an ongoing OOM killer. Check that the
* current is not killed (possibly due to sharing the victim's memory).
*/
if (mutex_lock_killable(&oom_lock))
return false;
oom_killer_disabled = true;
mutex_unlock(&oom_lock);
ret = wait_event_interruptible_timeout(oom_victims_wait,
!atomic_read(&oom_victims), timeout);
if (ret <= 0) {
oom_killer_enable();
return false;
}
pr_info("OOM killer disabled.\n");
return true;
}
static inline bool __task_will_free_mem(struct task_struct *task)
{
struct signal_struct *sig = task->signal;
/*
* 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.
*/
if (sig->flags & SIGNAL_GROUP_COREDUMP)
return false;
if (sig->flags & SIGNAL_GROUP_EXIT)
return true;
if (thread_group_empty(task) && (task->flags & PF_EXITING))
return true;
return false;
}
/*
* Checks whether the given task is dying or exiting and likely to
* release its address space. This means that all threads and processes
* sharing the same mm have to be killed or exiting.
* Caller has to make sure that task->mm is stable (hold task_lock or
* it operates on the current).
*/
static bool task_will_free_mem(struct task_struct *task)
{
struct mm_struct *mm = task->mm;
struct task_struct *p;
bool ret = true;
/*
* Skip tasks without mm because it might have passed its exit_mm and
* exit_oom_victim. oom_reaper could have rescued that but do not rely
* on that for now. We can consider find_lock_task_mm in future.
*/
if (!mm)
return false;
if (!__task_will_free_mem(task))
return false;
/*
* This task has already been drained by the oom reaper so there are
* only small chances it will free some more
*/
if (test_bit(MMF_OOM_SKIP, &mm->flags))
return false;
if (atomic_read(&mm->mm_users) <= 1)
return true;
/*
* Make sure that all tasks which share the mm with the given tasks
* are dying as well to make sure that a) nobody pins its mm and
* b) the task is also reapable by the oom reaper.
*/
rcu_read_lock();
for_each_process(p) {
if (!process_shares_mm(p, mm))
continue;
if (same_thread_group(task, p))
continue;
ret = __task_will_free_mem(p);
if (!ret)
break;
}
rcu_read_unlock();
return ret;
}
static void __oom_kill_process(struct task_struct *victim, const char *message)
{
struct task_struct *p;
struct mm_struct *mm;
bool can_oom_reap = true;
p = find_lock_task_mm(victim);
if (!p) {
put_task_struct(victim);
return;
} else if (victim != p) {
get_task_struct(p);
put_task_struct(victim);
victim = p;
}
/* Get a reference to safely compare mm after task_unlock(victim) */
mm = victim->mm;
mmgrab(mm);
/* Raise event before sending signal: task reaper must see this */
count_vm_event(OOM_KILL);
memcg_memory_event_mm(mm, MEMCG_OOM_KILL);
/*
* We should send SIGKILL before granting access to memory reserves
* in order to prevent the OOM victim from depleting the memory
* reserves from the user space under its control.
*/
do_send_sig_info(SIGKILL, SEND_SIG_PRIV, victim, PIDTYPE_TGID);
mark_oom_victim(victim);
pr_err("%s: Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
message, task_pid_nr(victim), victim->comm,
K(victim->mm->total_vm),
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
K(get_mm_counter(victim->mm, MM_FILEPAGES)),
K(get_mm_counter(victim->mm, MM_SHMEMPAGES)));
task_unlock(victim);
/*
* Kill all user processes sharing victim->mm in other thread groups, if
* any. They don't get access to memory reserves, though, to avoid
* depletion of all memory. This prevents mm->mmap_sem livelock when an
* oom killed thread cannot exit because it requires the semaphore and
* its contended by another thread trying to allocate memory itself.
* That thread will now get access to memory reserves since it has a
* pending fatal signal.
*/
rcu_read_lock();
for_each_process(p) {
if (!process_shares_mm(p, mm))
continue;
if (same_thread_group(p, victim))
continue;
if (is_global_init(p)) {
can_oom_reap = false;
set_bit(MMF_OOM_SKIP, &mm->flags);
pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n",
task_pid_nr(victim), victim->comm,
task_pid_nr(p), p->comm);
continue;
}
/*
* No use_mm() user needs to read from the userspace so we are
* ok to reap it.
*/
if (unlikely(p->flags & PF_KTHREAD))
continue;
do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID);
}
rcu_read_unlock();
if (can_oom_reap)
wake_oom_reaper(victim);
mmdrop(mm);
put_task_struct(victim);
}
#undef K
/*
* Kill provided task unless it's secured by setting
* oom_score_adj to OOM_SCORE_ADJ_MIN.
*/
static int oom_kill_memcg_member(struct task_struct *task, void *message)
{
if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN &&
!is_global_init(task)) {
get_task_struct(task);
__oom_kill_process(task, message);
}
return 0;
}
static void oom_kill_process(struct oom_control *oc, const char *message)
{
struct task_struct *victim = oc->chosen;
struct mem_cgroup *oom_group;
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
/*
* If the task is already exiting, don't alarm the sysadmin or kill
* its children or threads, just give it access to memory reserves
* so it can die quickly
*/
task_lock(victim);
if (task_will_free_mem(victim)) {
mark_oom_victim(victim);
wake_oom_reaper(victim);
task_unlock(victim);
put_task_struct(victim);
return;
}
task_unlock(victim);
if (__ratelimit(&oom_rs))
dump_header(oc, victim);
/*
* Do we need to kill the entire memory cgroup?
* Or even one of the ancestor memory cgroups?
* Check this out before killing the victim task.
*/
oom_group = mem_cgroup_get_oom_group(victim, oc->memcg);
__oom_kill_process(victim, message);
/*
* If necessary, kill all tasks in the selected memory cgroup.
*/
if (oom_group) {
mem_cgroup_print_oom_group(oom_group);
mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member,
(void*)message);
mem_cgroup_put(oom_group);
}
}
/*
* Determines whether the kernel must panic because of the panic_on_oom sysctl.
*/
static void check_panic_on_oom(struct oom_control *oc,
enum oom_constraint constraint)
{
if (likely(!sysctl_panic_on_oom))
return;
if (sysctl_panic_on_oom != 2) {
/*
* panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel
* does not panic for cpuset, mempolicy, or memcg allocation
* failures.
*/
if (constraint != CONSTRAINT_NONE)
return;
}
/* Do not panic for oom kills triggered by sysrq */
if (is_sysrq_oom(oc))
return;
dump_header(oc, NULL);
panic("Out of memory: %s panic_on_oom is enabled\n",
sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
}
static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
int register_oom_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&oom_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_oom_notifier);
int unregister_oom_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&oom_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_oom_notifier);
/**
* out_of_memory - kill the "best" process when we run out of memory
* @oc: pointer to struct oom_control
*
* If we run out of memory, we have the choice between either
* killing a random task (bad), letting the system crash (worse)
* OR try to be smart about which process to kill. Note that we
* don't have to be perfect here, we just have to be good.
*/
bool out_of_memory(struct oom_control *oc)
{
unsigned long freed = 0;
enum oom_constraint constraint = CONSTRAINT_NONE;
if (oom_killer_disabled)
return false;
if (!is_memcg_oom(oc)) {
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
/* Got some memory back in the last second. */
return true;
}
/*
* If current has a pending SIGKILL or is exiting, then automatically
* select it. The goal is to allow it to allocate so that it may
* quickly exit and free its memory.
*/
if (task_will_free_mem(current)) {
mark_oom_victim(current);
wake_oom_reaper(current);
return true;
}
/*
* The OOM killer does not compensate for IO-less reclaim.
* pagefault_out_of_memory lost its gfp context so we have to
* make sure exclude 0 mask - all other users should have at least
* ___GFP_DIRECT_RECLAIM to get here.
*/
if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS))
return true;
/*
* Check if there were limitations on the allocation (only relevant for
* NUMA and memcg) that may require different handling.
*/
constraint = constrained_alloc(oc);
if (constraint != CONSTRAINT_MEMORY_POLICY)
oc->nodemask = NULL;
check_panic_on_oom(oc, constraint);
if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
get_task_struct(current);
oc->chosen = current;
oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
return true;
}
select_bad_process(oc);
/* Found nothing?!?! */
if (!oc->chosen) {
dump_header(oc, NULL);
pr_warn("Out of memory and no killable processes...\n");
/*
* If we got here due to an actual allocation at the
* system level, we cannot survive this and will enter
* an endless loop in the allocator. Bail out now.
*/
if (!is_sysrq_oom(oc) && !is_memcg_oom(oc))
panic("System is deadlocked on memory\n");
}
if (oc->chosen && oc->chosen != (void *)-1UL)
oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
"Memory cgroup out of memory");
return !!oc->chosen;
}
/*
* The pagefault handler calls here because it is out of memory, so kill a
* memory-hogging task. If oom_lock is held by somebody else, a parallel oom
* killing is already in progress so do nothing.
*/
void pagefault_out_of_memory(void)
{
struct oom_control oc = {
.zonelist = NULL,
.nodemask = NULL,
.memcg = NULL,
.gfp_mask = 0,
.order = 0,
};
if (mem_cgroup_oom_synchronize(true))
return;
if (!mutex_trylock(&oom_lock))
return;
out_of_memory(&oc);
mutex_unlock(&oom_lock);
}