diff options
Diffstat (limited to 'mm/oom_kill.c')
-rw-r--r-- | mm/oom_kill.c | 276 |
1 files changed, 196 insertions, 80 deletions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 8b84661a6410..91ccd82097c2 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -28,6 +28,7 @@ #include <linux/sched/task.h> #include <linux/sched/debug.h> #include <linux/swap.h> +#include <linux/syscalls.h> #include <linux/timex.h> #include <linux/jiffies.h> #include <linux/cpuset.h> @@ -51,9 +52,9 @@ #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; +static int sysctl_panic_on_oom; +static int sysctl_oom_kill_allocating_task; +static int sysctl_oom_dump_tasks = 1; /* * Serializes oom killer invocations (out_of_memory()) from all contexts to @@ -74,7 +75,7 @@ static inline bool is_memcg_oom(struct oom_control *oc) #ifdef CONFIG_NUMA /** - * oom_cpuset_eligible() - check task eligiblity for kill + * oom_cpuset_eligible() - check task eligibility for kill * @start: task struct of which task to consider * @oc: pointer to struct oom_control * @@ -92,9 +93,6 @@ static bool oom_cpuset_eligible(struct task_struct *start, bool ret = false; const nodemask_t *mask = oc->nodemask; - if (is_memcg_oom(oc)) - return true; - rcu_read_lock(); for_each_thread(start, tsk) { if (mask) { @@ -104,7 +102,7 @@ static bool oom_cpuset_eligible(struct task_struct *start, * mempolicy intersects current, otherwise it may be * needlessly killed. */ - ret = mempolicy_nodemask_intersects(tsk, mask); + ret = mempolicy_in_oom_domain(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only @@ -171,10 +169,12 @@ static bool oom_unkillable_task(struct task_struct *p) } /* - * Print out unreclaimble slabs info when unreclaimable slabs amount is greater - * than all user memory (LRU pages) - */ -static bool is_dump_unreclaim_slabs(void) + * Check whether unreclaimable slab amount is greater than + * all user memory(LRU pages). + * dump_unreclaimable_slab() could help in the case that + * oom due to too much unreclaimable slab used by kernel. +*/ +static bool should_dump_unreclaim_slab(void) { unsigned long nr_lru; @@ -393,17 +393,17 @@ static int dump_task(struct task_struct *p, void *arg) 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. + * 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. */ return 0; } - pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", + pr_info("[%7d] %5d %5d %8lu %8lu %8lu %8lu %9lu %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_ANONPAGES), get_mm_counter(task->mm, MM_FILEPAGES), + get_mm_counter(task->mm, MM_SHMEMPAGES), mm_pgtables_bytes(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); @@ -424,7 +424,7 @@ static int dump_task(struct task_struct *p, void *arg) static void dump_tasks(struct oom_control *oc) { 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"); + pr_info("[ pid ] uid tgid total_vm rss rss_anon rss_file rss_shmem pgtables_bytes swapents oom_score_adj name\n"); if (is_memcg_oom(oc)) mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); @@ -438,7 +438,7 @@ static void dump_tasks(struct oom_control *oc) } } -static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) +static void dump_oom_victim(struct oom_control *oc, struct task_struct *victim) { /* one line summary of the oom killer context. */ pr_info("oom-kill:constraint=%s,nodemask=%*pbl", @@ -450,7 +450,7 @@ static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) from_kuid(&init_user_ns, task_uid(victim))); } -static void dump_header(struct oom_control *oc, struct task_struct *p) +static void dump_header(struct oom_control *oc) { 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, @@ -462,14 +462,12 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) 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()) + __show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask, gfp_zone(oc->gfp_mask)); + if (should_dump_unreclaim_slab()) dump_unreclaimable_slab(); } if (sysctl_oom_dump_tasks) dump_tasks(oc); - if (p) - dump_oom_summary(oc, p); } /* @@ -480,8 +478,6 @@ 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 @@ -510,10 +506,11 @@ 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) +static bool __oom_reap_task_mm(struct mm_struct *mm) { struct vm_area_struct *vma; bool ret = true; + VMA_ITERATOR(vmi, mm, 0); /* * Tell all users of get_user/copy_from_user etc... that the content @@ -523,8 +520,8 @@ bool __oom_reap_task_mm(struct mm_struct *mm) */ set_bit(MMF_UNSTABLE, &mm->flags); - for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (!can_madv_lru_vma(vma)) + for_each_vma(vmi, vma) { + if (vma->vm_flags & (VM_HUGETLB|VM_PFNMAP)) continue; /* @@ -542,17 +539,17 @@ bool __oom_reap_task_mm(struct mm_struct *mm) struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, - vma, mm, vma->vm_start, + mm, vma->vm_start, vma->vm_end); - tlb_gather_mmu(&tlb, mm, range.start, range.end); + tlb_gather_mmu(&tlb, mm); if (mmu_notifier_invalidate_range_start_nonblock(&range)) { - tlb_finish_mmu(&tlb, range.start, range.end); + tlb_finish_mmu(&tlb); 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); + tlb_finish_mmu(&tlb); } } @@ -633,22 +630,24 @@ done: */ 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); } static int oom_reaper(void *unused) { + set_freezable(); + while (true) { 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); @@ -657,30 +656,88 @@ 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) { - /* mm is already queued? */ - if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) - return; + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; - get_task_struct(tsk); + /* 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(&oom_reaper_lock); + spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; - spin_unlock(&oom_reaper_lock); + 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); + 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); +} + +#ifdef CONFIG_SYSCTL +static struct ctl_table vm_oom_kill_table[] = { + { + .procname = "panic_on_oom", + .data = &sysctl_panic_on_oom, + .maxlen = sizeof(sysctl_panic_on_oom), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "oom_kill_allocating_task", + .data = &sysctl_oom_kill_allocating_task, + .maxlen = sizeof(sysctl_oom_kill_allocating_task), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "oom_dump_tasks", + .data = &sysctl_oom_dump_tasks, + .maxlen = sizeof(sysctl_oom_dump_tasks), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; +#endif + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); +#ifdef CONFIG_SYSCTL + register_sysctl_init("vm", vm_oom_kill_table); +#endif return 0; } 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 */ @@ -705,10 +762,8 @@ static void mark_oom_victim(struct task_struct *tsk) return; /* oom_mm is bound to the signal struct life time. */ - if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) { + 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 @@ -785,11 +840,11 @@ 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. + * A coredumping process may sleep for an extended period in + * coredump_task_exit(), so the oom killer cannot assume that + * the process will promptly exit and release memory. */ - if (sig->flags & SIGNAL_GROUP_COREDUMP) + if (sig->core_state) return false; if (sig->flags & SIGNAL_GROUP_EXIT) @@ -921,7 +976,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) continue; } /* - * No kthead_use_mm() user needs to read from the userspace so + * No kthread_use_mm() user needs to read from the userspace so * we are ok to reap it. */ if (unlikely(p->flags & PF_KTHREAD)) @@ -931,12 +986,11 @@ 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); } -#undef K /* * Kill provided task unless it's secured by setting @@ -967,15 +1021,17 @@ 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; } task_unlock(victim); - if (__ratelimit(&oom_rs)) - dump_header(oc, victim); + if (__ratelimit(&oom_rs)) { + dump_header(oc); + dump_oom_victim(oc, victim); + } /* * Do we need to kill the entire memory cgroup? @@ -990,9 +1046,10 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * If necessary, kill all tasks in the selected memory cgroup. */ if (oom_group) { + memcg_memory_event(oom_group, MEMCG_OOM_GROUP_KILL); mem_cgroup_print_oom_group(oom_group); mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, - (void*)message); + (void *)message); mem_cgroup_put(oom_group); } } @@ -1016,7 +1073,7 @@ static void check_panic_on_oom(struct oom_control *oc) /* Do not panic for oom kills triggered by sysrq */ if (is_sysrq_oom(oc)) return; - dump_header(oc, NULL); + dump_header(oc); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -1053,7 +1110,7 @@ bool out_of_memory(struct oom_control *oc) if (!is_memcg_oom(oc)) { blocking_notifier_call_chain(&oom_notify_list, 0, &freed); - if (freed > 0) + if (freed > 0 && !is_sysrq_oom(oc)) /* Got some memory back in the last second. */ return true; } @@ -1065,18 +1122,16 @@ 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; } /* * 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. But mem_cgroup_oom() has to - * invoke the OOM killer even if it is a GFP_NOFS allocation. + * But mem_cgroup_oom() has to invoke the OOM killer even + * if it is a GFP_NOFS allocation. */ - if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc)) + if (!(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc)) return true; /* @@ -1101,7 +1156,7 @@ bool out_of_memory(struct oom_control *oc) select_bad_process(oc); /* Found nothing?!?! */ if (!oc->chosen) { - dump_header(oc, NULL); + dump_header(oc); pr_warn("Out of memory and no killable processes...\n"); /* * If we got here due to an actual allocation at the @@ -1118,25 +1173,86 @@ bool out_of_memory(struct oom_control *oc) } /* - * 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. + * The pagefault handler calls here because some allocation has failed. We have + * to take care of the memcg OOM here because this is the only safe context without + * any locks held but let the oom killer triggered from the allocation context care + * about the global OOM. */ void pagefault_out_of_memory(void) { - struct oom_control oc = { - .zonelist = NULL, - .nodemask = NULL, - .memcg = NULL, - .gfp_mask = 0, - .order = 0, - }; + static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); if (mem_cgroup_oom_synchronize(true)) return; - if (!mutex_trylock(&oom_lock)) + if (fatal_signal_pending(current)) return; - out_of_memory(&oc); - mutex_unlock(&oom_lock); + + if (__ratelimit(&pfoom_rs)) + pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n"); +} + +SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) +{ +#ifdef CONFIG_MMU + struct mm_struct *mm = NULL; + struct task_struct *task; + struct task_struct *p; + unsigned int f_flags; + bool reap = false; + long ret = 0; + + if (flags) + return -EINVAL; + + task = pidfd_get_task(pidfd, &f_flags); + if (IS_ERR(task)) + return PTR_ERR(task); + + /* + * Make sure to choose a thread which still has a reference to mm + * during the group exit + */ + p = find_lock_task_mm(task); + if (!p) { + ret = -ESRCH; + goto put_task; + } + + mm = p->mm; + mmgrab(mm); + + if (task_will_free_mem(p)) + reap = true; + else { + /* Error only if the work has not been done already */ + if (!test_bit(MMF_OOM_SKIP, &mm->flags)) + ret = -EINVAL; + } + task_unlock(p); + + if (!reap) + goto drop_mm; + + if (mmap_read_lock_killable(mm)) { + ret = -EINTR; + goto drop_mm; + } + /* + * Check MMF_OOM_SKIP again under mmap_read_lock protection to ensure + * possible change in exit_mmap is seen + */ + if (!test_bit(MMF_OOM_SKIP, &mm->flags) && !__oom_reap_task_mm(mm)) + ret = -EAGAIN; + mmap_read_unlock(mm); + +drop_mm: + mmdrop(mm); +put_task: + put_task_struct(task); + return ret; +#else + return -ENOSYS; +#endif /* CONFIG_MMU */ } |