linux_dsm_epyc7002/include/linux/oom.h
Shakeel Butt ac311a14c6 oom: decouple mems_allowed from oom_unkillable_task
Commit ef08e3b498 ("[PATCH] cpusets: confine oom_killer to
mem_exclusive cpuset") introduces a heuristic where a potential
oom-killer victim is skipped if the intersection of the potential victim
and the current (the process triggered the oom) is empty based on the
reason that killing such victim most probably will not help the current
allocating process.

However the commit 7887a3da75 ("[PATCH] oom: cpuset hint") changed the
heuristic to just decrease the oom_badness scores of such potential
victim based on the reason that the cpuset of such processes might have
changed and previously they may have allocated memory on mems where the
current allocating process can allocate from.

Unintentionally 7887a3da75 ("[PATCH] oom: cpuset hint") introduced a
side effect as the oom_badness is also exposed to the user space through
/proc/[pid]/oom_score, so, readers with different cpusets can read
different oom_score of the same process.

Later, commit 6cf86ac6f3 ("oom: filter tasks not sharing the same
cpuset") fixed the side effect introduced by 7887a3da75 by moving the
cpuset intersection back to only oom-killer context and out of
oom_badness.  However the combination of ab290adbaf ("oom: make
oom_unkillable_task() helper function") and 26ebc98491 ("oom:
/proc/<pid>/oom_score treat kernel thread honestly") unintentionally
brought back the cpuset intersection check into the oom_badness
calculation function.

Other than doing cpuset/mempolicy intersection from oom_badness, the memcg
oom context is also doing cpuset/mempolicy intersection which is quite
wrong and is caught by syzcaller with the following report:

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 28426 Comm: syz-executor.5 Not tainted 5.2.0-rc3-next-20190607
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__read_once_size include/linux/compiler.h:194 [inline]
RIP: 0010:has_intersects_mems_allowed mm/oom_kill.c:84 [inline]
RIP: 0010:oom_unkillable_task mm/oom_kill.c:168 [inline]
RIP: 0010:oom_unkillable_task+0x180/0x400 mm/oom_kill.c:155
Code: c1 ea 03 80 3c 02 00 0f 85 80 02 00 00 4c 8b a3 10 07 00 00 48 b8 00
00 00 00 00 fc ff df 4d 8d 74 24 10 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f
85 67 02 00 00 49 8b 44 24 10 4c 8d a0 68 fa ff ff
RSP: 0018:ffff888000127490 EFLAGS: 00010a03
RAX: dffffc0000000000 RBX: ffff8880a4cd5438 RCX: ffffffff818dae9c
RDX: 100000000c3cc602 RSI: ffffffff818dac8d RDI: 0000000000000001
RBP: ffff8880001274d0 R08: ffff888000086180 R09: ffffed1015d26be0
R10: ffffed1015d26bdf R11: ffff8880ae935efb R12: 8000000061e63007
R13: 0000000000000000 R14: 8000000061e63017 R15: 1ffff11000024ea6
FS:  00005555561f5940(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000607304 CR3: 000000009237e000 CR4: 00000000001426f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
Call Trace:
  oom_evaluate_task+0x49/0x520 mm/oom_kill.c:321
  mem_cgroup_scan_tasks+0xcc/0x180 mm/memcontrol.c:1169
  select_bad_process mm/oom_kill.c:374 [inline]
  out_of_memory mm/oom_kill.c:1088 [inline]
  out_of_memory+0x6b2/0x1280 mm/oom_kill.c:1035
  mem_cgroup_out_of_memory+0x1ca/0x230 mm/memcontrol.c:1573
  mem_cgroup_oom mm/memcontrol.c:1905 [inline]
  try_charge+0xfbe/0x1480 mm/memcontrol.c:2468
  mem_cgroup_try_charge+0x24d/0x5e0 mm/memcontrol.c:6073
  mem_cgroup_try_charge_delay+0x1f/0xa0 mm/memcontrol.c:6088
  do_huge_pmd_wp_page_fallback+0x24f/0x1680 mm/huge_memory.c:1201
  do_huge_pmd_wp_page+0x7fc/0x2160 mm/huge_memory.c:1359
  wp_huge_pmd mm/memory.c:3793 [inline]
  __handle_mm_fault+0x164c/0x3eb0 mm/memory.c:4006
  handle_mm_fault+0x3b7/0xa90 mm/memory.c:4053
  do_user_addr_fault arch/x86/mm/fault.c:1455 [inline]
  __do_page_fault+0x5ef/0xda0 arch/x86/mm/fault.c:1521
  do_page_fault+0x71/0x57d arch/x86/mm/fault.c:1552
  page_fault+0x1e/0x30 arch/x86/entry/entry_64.S:1156
RIP: 0033:0x400590
Code: 06 e9 49 01 00 00 48 8b 44 24 10 48 0b 44 24 28 75 1f 48 8b 14 24 48
8b 7c 24 20 be 04 00 00 00 e8 f5 56 00 00 48 8b 74 24 08 <89> 06 e9 1e 01
00 00 48 8b 44 24 08 48 8b 14 24 be 04 00 00 00 8b
RSP: 002b:00007fff7bc49780 EFLAGS: 00010206
RAX: 0000000000000001 RBX: 0000000000760000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 000000002000cffc RDI: 0000000000000001
RBP: fffffffffffffffe R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000075 R11: 0000000000000246 R12: 0000000000760008
R13: 00000000004c55f2 R14: 0000000000000000 R15: 00007fff7bc499b0
Modules linked in:
---[ end trace a65689219582ffff ]---
RIP: 0010:__read_once_size include/linux/compiler.h:194 [inline]
RIP: 0010:has_intersects_mems_allowed mm/oom_kill.c:84 [inline]
RIP: 0010:oom_unkillable_task mm/oom_kill.c:168 [inline]
RIP: 0010:oom_unkillable_task+0x180/0x400 mm/oom_kill.c:155
Code: c1 ea 03 80 3c 02 00 0f 85 80 02 00 00 4c 8b a3 10 07 00 00 48 b8 00
00 00 00 00 fc ff df 4d 8d 74 24 10 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f
85 67 02 00 00 49 8b 44 24 10 4c 8d a0 68 fa ff ff
RSP: 0018:ffff888000127490 EFLAGS: 00010a03
RAX: dffffc0000000000 RBX: ffff8880a4cd5438 RCX: ffffffff818dae9c
RDX: 100000000c3cc602 RSI: ffffffff818dac8d RDI: 0000000000000001
RBP: ffff8880001274d0 R08: ffff888000086180 R09: ffffed1015d26be0
R10: ffffed1015d26bdf R11: ffff8880ae935efb R12: 8000000061e63007
R13: 0000000000000000 R14: 8000000061e63017 R15: 1ffff11000024ea6
FS:  00005555561f5940(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2f823000 CR3: 000000009237e000 CR4: 00000000001426f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600

The fix is to decouple the cpuset/mempolicy intersection check from
oom_unkillable_task() and make sure cpuset/mempolicy intersection check is
only done in the global oom context.

[shakeelb@google.com: change function name and update comment]
  Link: http://lkml.kernel.org/r/20190628152421.198994-3-shakeelb@google.com
Link: http://lkml.kernel.org/r/20190624212631.87212-3-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reported-by: syzbot+d0fc9d3c166bc5e4a94b@syzkaller.appspotmail.com
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Paul Jackson <pj@sgi.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:05:47 -07:00

130 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,
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 */