diff options
Diffstat (limited to 'mm/oom_kill.c')
| -rw-r--r-- | mm/oom_kill.c | 109 |
1 files changed, 60 insertions, 49 deletions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1276e49b31b0..5eb11fbba704 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * 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... @@ -24,7 +24,6 @@ #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/sched/debug.h> #include <linux/swap.h> @@ -44,6 +43,8 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/cred.h> +#include <linux/nmi.h> #include <asm/tlb.h> #include "internal.h" @@ -217,7 +218,7 @@ long oom_badness(struct task_struct *p, unsigned long totalpages) */ adj = (long)p->signal->oom_score_adj; if (adj == OOM_SCORE_ADJ_MIN || - test_bit(MMF_OOM_SKIP, &p->mm->flags) || + mm_flags_test(MMF_OOM_SKIP, p->mm) || in_vfork(p)) { task_unlock(p); return LONG_MIN; @@ -324,7 +325,7 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) * 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)) + if (mm_flags_test(MMF_OOM_SKIP, task->signal->oom_mm)) goto next; goto abort; } @@ -399,10 +400,11 @@ static int dump_task(struct task_struct *p, void *arg) 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); @@ -423,21 +425,26 @@ 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); else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } -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", @@ -449,7 +456,7 @@ 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, @@ -465,10 +472,9 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) if (should_dump_unreclaim_slab()) dump_unreclaimable_slab(); } + mem_cgroup_show_protected_memory(oc->memcg); if (sysctl_oom_dump_tasks) dump_tasks(oc); - if (p) - dump_oom_summary(oc, p); } /* @@ -479,20 +485,18 @@ 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) +bool process_shares_mm(const struct task_struct *p, const struct mm_struct *mm) { - struct task_struct *t; + const struct task_struct *t; for_each_thread(p, t) { - struct mm_struct *t_mm = READ_ONCE(t->mm); + const struct mm_struct *t_mm = READ_ONCE(t->mm); if (t_mm) return t_mm == mm; } @@ -513,7 +517,7 @@ static bool __oom_reap_task_mm(struct mm_struct *mm) { struct vm_area_struct *vma; bool ret = true; - VMA_ITERATOR(vmi, mm, 0); + MA_STATE(mas, &mm->mm_mt, ULONG_MAX, ULONG_MAX); /* * Tell all users of get_user/copy_from_user etc... that the content @@ -521,9 +525,15 @@ static bool __oom_reap_task_mm(struct mm_struct *mm) * 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); + mm_flags_set(MMF_UNSTABLE, mm); - for_each_vma(vmi, vma) { + /* + * It might start racing with the dying task and compete for shared + * resources - e.g. page table lock contention has been observed. + * Reduce those races by reaping the oom victim from the other end + * of the address space. + */ + mas_for_each_rev(&mas, vma, 0) { if (vma->vm_flags & (VM_HUGETLB|VM_PFNMAP)) continue; @@ -542,7 +552,7 @@ static 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); if (mmu_notifier_invalidate_range_start_nonblock(&range)) { @@ -560,7 +570,7 @@ static bool __oom_reap_task_mm(struct mm_struct *mm) } /* - * Reaps the address space of the give task. + * Reaps the address space of the given task. * * Returns true on success and false if none or part of the address space * has been reclaimed and the caller should retry later. @@ -580,7 +590,7 @@ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) * under mmap_lock for reading because it serializes against the * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap(). */ - if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + if (mm_flags_test(MMF_OOM_SKIP, mm)) { trace_skip_task_reaping(tsk->pid); goto out_unlock; } @@ -616,7 +626,7 @@ static void oom_reap_task(struct task_struct *tsk) schedule_timeout_idle(HZ/10); if (attempts <= MAX_OOM_REAP_RETRIES || - test_bit(MMF_OOM_SKIP, &mm->flags)) + mm_flags_test(MMF_OOM_SKIP, mm)) goto done; pr_info("oom_reaper: unable to reap pid:%d (%s)\n", @@ -631,7 +641,7 @@ done: * Hide this mm from OOM killer because it has been either reaped or * somebody can't call mmap_write_unlock(mm). */ - set_bit(MMF_OOM_SKIP, &mm->flags); + mm_flags_set(MMF_OOM_SKIP, mm); /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); @@ -667,7 +677,7 @@ static void wake_oom_reaper(struct timer_list *timer) unsigned long flags; /* The victim managed to terminate on its own - see exit_mmap */ - if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + if (mm_flags_test(MMF_OOM_SKIP, mm)) { put_task_struct(tsk); return; } @@ -692,7 +702,7 @@ static void wake_oom_reaper(struct timer_list *timer) 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)) + if (mm_flags_test_and_set(MMF_OOM_REAP_QUEUED, tsk->signal->oom_mm)) return; get_task_struct(tsk); @@ -702,7 +712,7 @@ static void queue_oom_reaper(struct task_struct *tsk) } #ifdef CONFIG_SYSCTL -static struct ctl_table vm_oom_kill_table[] = { +static const struct ctl_table vm_oom_kill_table[] = { { .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, @@ -726,7 +736,6 @@ static struct ctl_table vm_oom_kill_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - {} }; #endif @@ -757,6 +766,7 @@ static inline void queue_oom_reaper(struct task_struct *tsk) */ static void mark_oom_victim(struct task_struct *tsk) { + const struct cred *cred; struct mm_struct *mm = tsk->mm; WARN_ON(oom_killer_disabled); @@ -769,14 +779,16 @@ static void mark_oom_victim(struct task_struct *tsk) mmgrab(tsk->signal->oom_mm); /* - * 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. + * Make sure that the process is woken up from uninterruptible sleep + * if it is frozen because OOM killer wouldn't be able to free any + * memory and livelock. The freezer will thaw the tasks that are OOM + * victims regardless of the PM freezing and cgroup freezing states. */ - __thaw_task(tsk); + thaw_process(tsk); atomic_inc(&oom_victims); - trace_mark_victim(tsk->pid); + cred = get_task_cred(tsk); + trace_mark_victim(tsk, cred->uid.val); + put_cred(cred); } /** @@ -887,7 +899,7 @@ static bool task_will_free_mem(struct task_struct *task) * 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)) + if (mm_flags_test(MMF_OOM_SKIP, mm)) return false; if (atomic_read(&mm->mm_users) <= 1) @@ -972,7 +984,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) continue; if (is_global_init(p)) { can_oom_reap = false; - set_bit(MMF_OOM_SKIP, &mm->flags); + mm_flags_set(MMF_OOM_SKIP, mm); 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); @@ -994,7 +1006,6 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) mmdrop(mm); put_task_struct(victim); } -#undef K /* * Kill provided task unless it's secured by setting @@ -1032,8 +1043,10 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } 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? @@ -1075,7 +1088,7 @@ 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"); } @@ -1130,12 +1143,10 @@ bool out_of_memory(struct oom_control *oc) /* * 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; /* @@ -1160,7 +1171,7 @@ 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 @@ -1231,7 +1242,7 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) reap = true; else { /* Error only if the work has not been done already */ - if (!test_bit(MMF_OOM_SKIP, &mm->flags)) + if (!mm_flags_test(MMF_OOM_SKIP, mm)) ret = -EINVAL; } task_unlock(p); @@ -1247,7 +1258,7 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) * 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)) + if (!mm_flags_test(MMF_OOM_SKIP, mm) && !__oom_reap_task_mm(mm)) ret = -EAGAIN; mmap_read_unlock(mm); |