From ed5d4efb4df1014bd5bc1d479e157c7687d8c187 Mon Sep 17 00:00:00 2001 From: Nico Pache Date: Thu, 21 Apr 2022 16:36:01 -0700 Subject: [PATCH] oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup commit e4a38402c36e42df28eb1a5394be87e6571fb48a upstream. The pthread struct is allocated on PRIVATE|ANONYMOUS memory [1] which can be targeted by the oom reaper. This mapping is used to store the futex robust list head; the kernel does not keep a copy of the robust list and instead references a userspace address to maintain the robustness during a process death. A race can occur between exit_mm and the oom reaper that allows the oom reaper to free the memory of the futex robust list before the exit path has handled the futex death: CPU1 CPU2 -------------------------------------------------------------------- page_fault do_exit "signal" wake_oom_reaper oom_reaper oom_reap_task_mm (invalidates mm) exit_mm exit_mm_release futex_exit_release futex_cleanup exit_robust_list get_user (EFAULT- can't access memory) If the get_user EFAULT's, the kernel will be unable to recover the waiters on the robust_list, leaving userspace mutexes hung indefinitely. Delay the OOM reaper, allowing more time for the exit path to perform the futex cleanup. Reproducer: https://gitlab.com/jsavitz/oom_futex_reproducer Based on a patch by Michal Hocko. Link: https://elixir.bootlin.com/glibc/glibc-2.35/source/nptl/allocatestack.c#L370 [1] Link: https://lkml.kernel.org/r/20220414144042.677008-1-npache@redhat.com Fixes: 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently") Signed-off-by: Joel Savitz Signed-off-by: Nico Pache Co-developed-by: Joel Savitz Suggested-by: Thomas Gleixner Acked-by: Thomas Gleixner Acked-by: Michal Hocko Cc: Rafael Aquini Cc: Waiman Long Cc: Herton R. Krzesinski Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Steven Rostedt Cc: Ben Segall Cc: Mel Gorman Cc: Daniel Bristot de Oliveira Cc: David Rientjes Cc: Andrea Arcangeli Cc: Davidlohr Bueso Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Joel Savitz Cc: Darren Hart Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 1 + mm/oom_kill.c | 56 +++++++++++++++++++++++++++++++------------ 2 files changed, 42 insertions(+), 15 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index f996d1f343bb..4bca80c9931f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1325,6 +1325,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 419a814f467e..3d7c557fb70c 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -633,7 +633,7 @@ static void oom_reap_task(struct task_struct *tsk) */ set_bit(MMF_OOM_SKIP, &mm->flags); - /* Drop a reference taken by wake_oom_reaper */ + /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); } @@ -643,12 +643,12 @@ static int oom_reaper(void *unused) struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); - spin_lock(&oom_reaper_lock); + spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } - spin_unlock(&oom_reaper_lock); + spin_unlock_irq(&oom_reaper_lock); if (tsk) oom_reap_task(tsk); @@ -657,20 +657,46 @@ static int oom_reaper(void *unused) return 0; } -static void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct timer_list *timer) +{ + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; + + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); + return; + } + + spin_lock_irqsave(&oom_reaper_lock, flags); + tsk->oom_reaper_list = oom_reaper_list; + oom_reaper_list = tsk; + spin_unlock_irqrestore(&oom_reaper_lock, flags); + trace_wake_reaper(tsk->pid); + wake_up(&oom_reaper_wait); +} + +/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_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); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); } static int __init oom_init(void) @@ -680,7 +706,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ @@ -931,7 +957,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) rcu_read_unlock(); if (can_oom_reap) - wake_oom_reaper(victim); + queue_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); @@ -967,7 +993,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); - wake_oom_reaper(victim); + queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; @@ -1065,7 +1091,7 @@ bool out_of_memory(struct oom_control *oc) */ if (task_will_free_mem(current)) { mark_oom_victim(current); - wake_oom_reaper(current); + queue_oom_reaper(current); return true; }