diff options
Diffstat (limited to 'mm/oom_kill.c')
| -rw-r--r-- | mm/oom_kill.c | 100 |
1 files changed, 61 insertions, 39 deletions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9e8b4f030c1c..c86fbd1b590e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -40,9 +40,11 @@ #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> @@ -160,6 +162,25 @@ static bool oom_unkillable_task(struct task_struct *p, 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 @@ -200,7 +221,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * task's rss, pagetable and swap space use. */ points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + - atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm); + mm_pgtables_bytes(p->mm) / PAGE_SIZE; task_unlock(p); /* @@ -368,15 +389,15 @@ static void select_bad_process(struct oom_control *oc) * 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, nr_ptes, - * swapents, oom_score_adj value, and name. + * 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("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\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)) @@ -392,11 +413,10 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n", + pr_info("[%5d] %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), - atomic_long_read(&task->mm->nr_ptes), - mm_nr_pmds(task->mm), + mm_pgtables_bytes(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); @@ -406,23 +426,22 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) static void dump_header(struct oom_control *oc, struct task_struct *p) { - pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=", - current->comm, oc->gfp_mask, &oc->gfp_mask); - if (oc->nodemask) - pr_cont("%*pbl", nodemask_pr_args(oc->nodemask)); - else - pr_cont("(null)"); - pr_cont(", order=%d, oom_score_adj=%hd\n", - oc->order, current->signal->oom_score_adj); + pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n", + current->comm, oc->gfp_mask, &oc->gfp_mask, + nodemask_pr_args(oc->nodemask), oc->order, + current->signal->oom_score_adj); if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) pr_warn("COMPACTION is disabled!!!\n"); cpuset_print_current_mems_allowed(); dump_stack(); - if (oc->memcg) + if (is_memcg_oom(oc)) mem_cgroup_print_oom_info(oc->memcg, p); - else + 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); } @@ -495,11 +514,27 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) } /* - * increase mm_users only after we know we will reap something so - * that the mmput_async is called only when we have reaped something - * and delayed __mmput doesn't matter that much + * If the mm has notifiers then we would need to invalidate them around + * unmap_page_range and that is risky because notifiers can sleep and + * what they do is basically undeterministic. So let's have a short + * sleep to give the oom victim some more time. + * TODO: we really want to get rid of this ugly hack and make sure that + * notifiers cannot block for unbounded amount of time and add + * mmu_notifier_invalidate_range_{start,end} around unmap_page_range */ - if (!mmget_not_zero(mm)) { + if (mm_has_notifiers(mm)) { + up_read(&mm->mmap_sem); + schedule_timeout_idle(HZ); + goto unlock_oom; + } + + /* + * 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)) { up_read(&mm->mmap_sem); trace_skip_task_reaping(tsk->pid); goto unlock_oom; @@ -542,12 +577,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) K(get_mm_counter(mm, MM_SHMEMPAGES))); up_read(&mm->mmap_sem); - /* - * Drop our reference but make sure the mmput slow path is called from a - * different context because we shouldn't risk we get stuck there and - * put the oom_reaper out of the way. - */ - mmput_async(mm); trace_finish_task_reaping(tsk->pid); unlock_oom: mutex_unlock(&oom_lock); @@ -607,9 +636,6 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - if (!oom_reaper_th) - return; - /* tsk is already queued? */ if (tsk == oom_reaper_list || tsk->oom_reaper_list) return; @@ -627,11 +653,6 @@ static void wake_oom_reaper(struct task_struct *tsk) static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); - if (IS_ERR(oom_reaper_th)) { - pr_err("Unable to start OOM reaper %ld. Continuing regardless\n", - PTR_ERR(oom_reaper_th)); - oom_reaper_th = NULL; - } return 0; } subsys_initcall(oom_init) @@ -824,7 +845,8 @@ static void oom_kill_process(struct oom_control *oc, const char *message) /* * If the task is already exiting, don't alarm the sysadmin or kill - * its children or threads, just set TIF_MEMDIE so it can die quickly + * its children or threads, just give it access to memory reserves + * so it can die quickly */ task_lock(p); if (task_will_free_mem(p)) { @@ -889,9 +911,9 @@ static void oom_kill_process(struct oom_control *oc, const char *message) count_memcg_event_mm(mm, OOM_KILL); /* - * We should send SIGKILL before setting TIF_MEMDIE in order to prevent - * the OOM victim from depleting the memory reserves from the user - * space under its control. + * 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_FORCED, victim, true); mark_oom_victim(victim); |