diff options
Diffstat (limited to 'mm/oom_kill.c')
| -rw-r--r-- | mm/oom_kill.c | 1331 |
1 files changed, 958 insertions, 373 deletions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 79e451a78c9e..5eb11fbba704 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -1,6 +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... @@ -22,7 +23,11 @@ #include <linux/err.h> #include <linux/gfp.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#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> @@ -35,31 +40,62 @@ #include <linux/freezer.h> #include <linux/ftrace.h> #include <linux/ratelimit.h> +#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" +#include "slab.h" #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 DEFINE_SPINLOCK(zone_scan_lock); +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 + * prevent from over eager oom killing (e.g. when the oom killer is invoked + * from different domains). + * + * oom_killer_disable() relies on this lock to stabilize oom_killer_disabled + * and mark_oom_victim + */ +DEFINE_MUTEX(oom_lock); +/* Serializes oom_score_adj and oom_score_adj_min updates */ +DEFINE_MUTEX(oom_adj_mutex); + +static inline bool is_memcg_oom(struct oom_control *oc) +{ + return oc->memcg != NULL; +} #ifdef CONFIG_NUMA /** - * has_intersects_mems_allowed() - check task eligiblity for kill - * @tsk: task struct of which task to consider - * @mask: nodemask passed to page allocator for mempolicy ooms + * oom_cpuset_eligible() - check task eligibility for kill + * @start: task struct of which task to consider + * @oc: pointer to struct oom_control * * Task eligibility is determined by whether or not a candidate task, @tsk, * shares the same mempolicy nodes as current if it is bound by such a policy * and whether or not it has the same set of allowed cpuset nodes. + * + * This function is assuming oom-killer context and 'current' has triggered + * the oom-killer. */ -static bool has_intersects_mems_allowed(struct task_struct *tsk, - const nodemask_t *mask) +static bool oom_cpuset_eligible(struct task_struct *start, + struct oom_control *oc) { - struct task_struct *start = tsk; + struct task_struct *tsk; + bool ret = false; + const nodemask_t *mask = oc->nodemask; - do { + rcu_read_lock(); + for_each_thread(start, tsk) { if (mask) { /* * If this is a mempolicy constrained oom, tsk's @@ -67,23 +103,23 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, * mempolicy intersects current, otherwise it may be * needlessly killed. */ - if (mempolicy_nodemask_intersects(tsk, mask)) - return true; + ret = mempolicy_in_oom_domain(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only * check the mems of tsk's cpuset. */ - if (cpuset_mems_allowed_intersects(current, tsk)) - return true; + ret = cpuset_mems_allowed_intersects(current, tsk); } - } while_each_thread(start, tsk); + if (ret) + break; + } + rcu_read_unlock(); - return false; + return ret; } #else -static bool has_intersects_mems_allowed(struct task_struct *tsk, - const nodemask_t *mask) +static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc) { return true; } @@ -91,42 +127,67 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, /* * The process p may have detached its own ->mm while exiting or through - * use_mm(), but one or more of its subthreads may still have a valid + * kthread_use_mm(), but one or more of its subthreads may still have a valid * pointer. Return p, or any of its subthreads with a valid ->mm, with * task_lock() held. */ struct task_struct *find_lock_task_mm(struct task_struct *p) { - struct task_struct *t = p; + struct task_struct *t; - do { + rcu_read_lock(); + + for_each_thread(p, t) { task_lock(t); if (likely(t->mm)) - return t; + goto found; task_unlock(t); - } while_each_thread(p, t); + } + t = NULL; +found: + rcu_read_unlock(); + + return t; +} - return NULL; +/* + * order == -1 means the oom kill is required by sysrq, otherwise only + * for display purposes. + */ +static inline bool is_sysrq_oom(struct oom_control *oc) +{ + return oc->order == -1; } /* return true if the task is not adequate as candidate victim task. */ -static bool oom_unkillable_task(struct task_struct *p, - const struct mem_cgroup *memcg, const nodemask_t *nodemask) +static bool oom_unkillable_task(struct task_struct *p) { if (is_global_init(p)) return true; if (p->flags & PF_KTHREAD) return true; + return false; +} - /* When mem_cgroup_out_of_memory() and p is not member of the group */ - if (memcg && !task_in_mem_cgroup(p, memcg)) - return true; +/* + * 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; - /* p may not have freeable memory in nodemask */ - if (!has_intersects_mems_allowed(p, nodemask)) - return true; + 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 false; + return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru); } /** @@ -138,76 +199,83 @@ static bool oom_unkillable_task(struct task_struct *p, * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ -unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages) +long oom_badness(struct task_struct *p, unsigned long totalpages) { long points; long adj; - if (oom_unkillable_task(p, memcg, nodemask)) - return 0; + if (oom_unkillable_task(p)) + return LONG_MIN; p = find_lock_task_mm(p); if (!p) - return 0; + return LONG_MIN; + /* + * Do not even consider tasks which are explicitly marked oom + * unkillable or have been already oom reaped or the are in + * the middle of vfork + */ adj = (long)p->signal->oom_score_adj; - if (adj == OOM_SCORE_ADJ_MIN) { + if (adj == OOM_SCORE_ADJ_MIN || + mm_flags_test(MMF_OOM_SKIP, p->mm) || + in_vfork(p)) { task_unlock(p); - return 0; + return LONG_MIN; } /* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + p->mm->nr_ptes + - get_mm_counter(p->mm, MM_SWAPENTS); + points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + + mm_pgtables_bytes(p->mm) / PAGE_SIZE; task_unlock(p); - /* - * Root processes get 3% bonus, just like the __vm_enough_memory() - * implementation used by LSMs. - */ - if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - adj -= 30; - /* Normalize to oom_score_adj units */ adj *= totalpages / 1000; points += adj; - /* - * Never return 0 for an eligible task regardless of the root bonus and - * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here). - */ - return points > 0 ? points : 1; + return points; } +static const char * const oom_constraint_text[] = { + [CONSTRAINT_NONE] = "CONSTRAINT_NONE", + [CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET", + [CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY", + [CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG", +}; + /* * Determine the type of allocation constraint. */ -#ifdef CONFIG_NUMA -static enum oom_constraint constrained_alloc(struct zonelist *zonelist, - gfp_t gfp_mask, nodemask_t *nodemask, - unsigned long *totalpages) +static enum oom_constraint constrained_alloc(struct oom_control *oc) { struct zone *zone; struct zoneref *z; - enum zone_type high_zoneidx = gfp_zone(gfp_mask); + enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask); bool cpuset_limited = false; int nid; + if (is_memcg_oom(oc)) { + oc->totalpages = mem_cgroup_get_max(oc->memcg) ?: 1; + return CONSTRAINT_MEMCG; + } + /* Default to all available memory */ - *totalpages = totalram_pages + total_swap_pages; + oc->totalpages = totalram_pages() + total_swap_pages; + + if (!IS_ENABLED(CONFIG_NUMA)) + return CONSTRAINT_NONE; - if (!zonelist) + if (!oc->zonelist) return CONSTRAINT_NONE; /* * Reach here only when __GFP_NOFAIL is used. So, we should avoid * to kill current.We have to random task kill in this case. * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now. */ - if (gfp_mask & __GFP_THISNODE) + if (oc->gfp_mask & __GFP_THISNODE) return CONSTRAINT_NONE; /* @@ -215,253 +283,658 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, * the page allocator means a mempolicy is in effect. Cpuset policy * is enforced in get_page_from_freelist(). */ - if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) { - *totalpages = total_swap_pages; - for_each_node_mask(nid, *nodemask) - *totalpages += node_spanned_pages(nid); + if (oc->nodemask && + !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) { + oc->totalpages = total_swap_pages; + for_each_node_mask(nid, *oc->nodemask) + oc->totalpages += node_present_pages(nid); return CONSTRAINT_MEMORY_POLICY; } /* Check this allocation failure is caused by cpuset's wall function */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, - high_zoneidx, nodemask) - if (!cpuset_zone_allowed_softwall(zone, gfp_mask)) + for_each_zone_zonelist_nodemask(zone, z, oc->zonelist, + highest_zoneidx, oc->nodemask) + if (!cpuset_zone_allowed(zone, oc->gfp_mask)) cpuset_limited = true; if (cpuset_limited) { - *totalpages = total_swap_pages; + oc->totalpages = total_swap_pages; for_each_node_mask(nid, cpuset_current_mems_allowed) - *totalpages += node_spanned_pages(nid); + oc->totalpages += node_present_pages(nid); return CONSTRAINT_CPUSET; } return CONSTRAINT_NONE; } -#else -static enum oom_constraint constrained_alloc(struct zonelist *zonelist, - gfp_t gfp_mask, nodemask_t *nodemask, - unsigned long *totalpages) -{ - *totalpages = totalram_pages + total_swap_pages; - return CONSTRAINT_NONE; -} -#endif -enum oom_scan_t oom_scan_process_thread(struct task_struct *task, - unsigned long totalpages, const nodemask_t *nodemask, - bool force_kill) +static int oom_evaluate_task(struct task_struct *task, void *arg) { - if (task->exit_state) - return OOM_SCAN_CONTINUE; - if (oom_unkillable_task(task, NULL, nodemask)) - return OOM_SCAN_CONTINUE; + struct oom_control *oc = arg; + long points; + + if (oom_unkillable_task(task)) + goto next; + + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc)) + goto next; /* * This task already has access to memory reserves and is being killed. - * Don't allow any other task to have access to the reserves. + * Don't allow any other task to have access to the reserves unless + * the task has MMF_OOM_SKIP because chances that it would release + * any memory is quite low. */ - if (test_tsk_thread_flag(task, TIF_MEMDIE)) { - if (unlikely(frozen(task))) - __thaw_task(task); - if (!force_kill) - return OOM_SCAN_ABORT; + if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) { + if (mm_flags_test(MMF_OOM_SKIP, task->signal->oom_mm)) + goto next; + goto abort; } - if (!task->mm) - return OOM_SCAN_CONTINUE; /* * If task is allocating a lot of memory and has been marked to be * killed first if it triggers an oom, then select it. */ - if (oom_task_origin(task)) - return OOM_SCAN_SELECT; - - if (task->flags & PF_EXITING && !force_kill) { - /* - * If this task is not being ptraced on exit, then wait for it - * to finish before killing some other task unnecessarily. - */ - if (!(task->group_leader->ptrace & PT_TRACE_EXIT)) - return OOM_SCAN_ABORT; + if (oom_task_origin(task)) { + points = LONG_MAX; + goto select; } - return OOM_SCAN_OK; + + points = oom_badness(task, oc->totalpages); + if (points == LONG_MIN || points < oc->chosen_points) + goto next; + +select: + if (oc->chosen) + put_task_struct(oc->chosen); + get_task_struct(task); + oc->chosen = task; + oc->chosen_points = points; +next: + return 0; +abort: + if (oc->chosen) + put_task_struct(oc->chosen); + oc->chosen = (void *)-1UL; + return 1; } /* - * Simple selection loop. We chose the process with the highest - * number of 'points'. - * - * (not docbooked, we don't want this one cluttering up the manual) + * Simple selection loop. We choose the process with the highest number of + * 'points'. In case scan was aborted, oc->chosen is set to -1. */ -static struct task_struct *select_bad_process(unsigned int *ppoints, - unsigned long totalpages, const nodemask_t *nodemask, - bool force_kill) +static void select_bad_process(struct oom_control *oc) { - struct task_struct *g, *p; - struct task_struct *chosen = NULL; - unsigned long chosen_points = 0; + oc->chosen_points = LONG_MIN; - rcu_read_lock(); - do_each_thread(g, p) { - unsigned int points; - - switch (oom_scan_process_thread(p, totalpages, nodemask, - force_kill)) { - case OOM_SCAN_SELECT: - chosen = p; - chosen_points = ULONG_MAX; - /* fall through */ - case OOM_SCAN_CONTINUE: - continue; - case OOM_SCAN_ABORT: - rcu_read_unlock(); - return ERR_PTR(-1UL); - case OOM_SCAN_OK: - break; - }; - points = oom_badness(p, NULL, nodemask, totalpages); - if (points > chosen_points) { - chosen = p; - chosen_points = points; - } - } while_each_thread(g, p); - if (chosen) - get_task_struct(chosen); - rcu_read_unlock(); + if (is_memcg_oom(oc)) + mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); + else { + struct task_struct *p; + + rcu_read_lock(); + for_each_process(p) + if (oom_evaluate_task(p, oc)) + break; + rcu_read_unlock(); + } +} + +static int dump_task(struct task_struct *p, void *arg) +{ + struct oom_control *oc = arg; + struct task_struct *task; + + if (oom_unkillable_task(p)) + return 0; + + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc)) + return 0; + + task = find_lock_task_mm(p); + if (!task) { + /* + * 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; + } - *ppoints = chosen_points * 1000 / totalpages; - return chosen; + 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), + 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); + + return 0; } /** * dump_tasks - dump current memory state of all system tasks - * @memcg: current's memory controller, if constrained - * @nodemask: nodemask passed to page allocator for mempolicy ooms + * @oc: pointer to struct oom_control * * 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(const struct mem_cgroup *memcg, const nodemask_t *nodemask) +static void dump_tasks(struct oom_control *oc) { - struct task_struct *p; - struct task_struct *task; + pr_info("Tasks state (memory values in pages):\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) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); + dump_task(p, oc); + } + rcu_read_unlock(); + } +} - pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); - rcu_read_lock(); - for_each_process(p) { - if (oom_unkillable_task(p, memcg, nodemask)) - continue; +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", + oom_constraint_text[oc->constraint], + nodemask_pr_args(oc->nodemask)); + cpuset_print_current_mems_allowed(); + mem_cgroup_print_oom_context(oc->memcg, victim); + pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid, + from_kuid(&init_user_ns, task_uid(victim))); +} - 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. - */ +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, + current->signal->oom_score_adj); + if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) + pr_warn("COMPACTION is disabled!!!\n"); + + dump_stack(); + if (is_memcg_oom(oc)) + mem_cgroup_print_oom_meminfo(oc->memcg); + else { + __show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask, gfp_zone(oc->gfp_mask)); + if (should_dump_unreclaim_slab()) + dump_unreclaimable_slab(); + } + mem_cgroup_show_protected_memory(oc->memcg); + if (sysctl_oom_dump_tasks) + dump_tasks(oc); +} + +/* + * Number of OOM victims in flight + */ +static atomic_t oom_victims = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); + +static bool oom_killer_disabled __read_mostly; + +/* + * 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(const struct task_struct *p, const struct mm_struct *mm) +{ + const struct task_struct *t; + + for_each_thread(p, t) { + const struct mm_struct *t_mm = READ_ONCE(t->mm); + if (t_mm) + return t_mm == mm; + } + return false; +} + +#ifdef CONFIG_MMU +/* + * OOM Reaper kernel thread which tries to reap the memory used by the OOM + * victim (if that is possible) to help the OOM killer to move on. + */ +static struct task_struct *oom_reaper_th; +static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); +static struct task_struct *oom_reaper_list; +static DEFINE_SPINLOCK(oom_reaper_lock); + +static bool __oom_reap_task_mm(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + bool ret = true; + MA_STATE(mas, &mm->mm_mt, ULONG_MAX, ULONG_MAX); + + /* + * Tell all users of get_user/copy_from_user etc... that the content + * is no longer stable. No barriers really needed because unmapping + * should imply barriers already and the reader would hit a page fault + * if it stumbled over a reaped memory. + */ + mm_flags_set(MMF_UNSTABLE, mm); + + /* + * 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; + + /* + * Only anonymous pages have a good chance to be dropped + * without additional steps which we cannot afford as we + * are OOM already. + * + * We do not even care about fs backed pages because all + * which are reclaimable have already been reclaimed and + * we do not want to block exit_mmap by keeping mm ref + * count elevated without a good reason. + */ + if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { + struct mmu_notifier_range range; + struct mmu_gather tlb; + + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, + mm, vma->vm_start, + vma->vm_end); + tlb_gather_mmu(&tlb, mm); + if (mmu_notifier_invalidate_range_start_nonblock(&range)) { + 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); } + } - pr_info("[%5d] %5d %5d %8lu %8lu %7lu %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), - task->mm->nr_ptes, - get_mm_counter(task->mm, MM_SWAPENTS), - task->signal->oom_score_adj, task->comm); - task_unlock(task); + return ret; +} + +/* + * 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. + */ +static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +{ + bool ret = true; + + if (!mmap_read_trylock(mm)) { + trace_skip_task_reaping(tsk->pid); + return false; } - rcu_read_unlock(); + + /* + * 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_lock for reading because it serializes against the + * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap(). + */ + if (mm_flags_test(MMF_OOM_SKIP, mm)) { + trace_skip_task_reaping(tsk->pid); + goto out_unlock; + } + + trace_start_task_reaping(tsk->pid); + + /* failed to reap part of the address space. Try again later */ + ret = __oom_reap_task_mm(mm); + if (!ret) + goto out_finish; + + pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", + task_pid_nr(tsk), tsk->comm, + K(get_mm_counter(mm, MM_ANONPAGES)), + K(get_mm_counter(mm, MM_FILEPAGES)), + K(get_mm_counter(mm, MM_SHMEMPAGES))); +out_finish: + trace_finish_task_reaping(tsk->pid); +out_unlock: + mmap_read_unlock(mm); + + return ret; } -static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, - struct mem_cgroup *memcg, const nodemask_t *nodemask) +#define MAX_OOM_REAP_RETRIES 10 +static void oom_reap_task(struct task_struct *tsk) { - task_lock(current); - pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, " - "oom_score_adj=%hd\n", - current->comm, gfp_mask, order, - current->signal->oom_score_adj); - cpuset_print_task_mems_allowed(current); - task_unlock(current); - dump_stack(); - if (memcg) - mem_cgroup_print_oom_info(memcg, p); - else - show_mem(SHOW_MEM_FILTER_NODES); - if (sysctl_oom_dump_tasks) - dump_tasks(memcg, nodemask); + int attempts = 0; + struct mm_struct *mm = tsk->signal->oom_mm; + + /* Retry the mmap_read_trylock(mm) a few times */ + while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm)) + schedule_timeout_idle(HZ/10); + + if (attempts <= MAX_OOM_REAP_RETRIES || + mm_flags_test(MMF_OOM_SKIP, mm)) + goto done; + + pr_info("oom_reaper: unable to reap pid:%d (%s)\n", + task_pid_nr(tsk), tsk->comm); + sched_show_task(tsk); + debug_show_all_locks(); + +done: + tsk->oom_reaper_list = NULL; + + /* + * Hide this mm from OOM killer because it has been either reaped or + * somebody can't call mmap_write_unlock(mm). + */ + mm_flags_set(MMF_OOM_SKIP, mm); + + /* 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_irq(&oom_reaper_lock); + if (oom_reaper_list != NULL) { + tsk = oom_reaper_list; + oom_reaper_list = tsk->oom_reaper_list; + } + spin_unlock_irq(&oom_reaper_lock); + + if (tsk) + oom_reap_task(tsk); + } + + return 0; +} + +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 (mm_flags_test(MMF_OOM_SKIP, mm)) { + 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); } -#define K(x) ((x) << (PAGE_SHIFT-10)) /* - * Must be called while holding a reference to p, which will be released upon - * returning. + * 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. */ -void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message) -{ - struct task_struct *victim = p; - struct task_struct *child; - struct task_struct *t = p; - struct mm_struct *mm; - unsigned int victim_points = 0; - static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (mm_flags_test_and_set(MMF_OOM_REAP_QUEUED, tsk->signal->oom_mm)) + 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 const 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 queue_oom_reaper(struct task_struct *tsk) +{ +} +#endif /* CONFIG_MMU */ + +/** + * mark_oom_victim - mark the given task as OOM victim + * @tsk: task to mark + * + * Has to be called with oom_lock held and never after + * oom has been disabled already. + * + * tsk->mm has to be non NULL and caller has to guarantee it is stable (either + * under task_lock or operate on the current). + */ +static void mark_oom_victim(struct task_struct *tsk) +{ + const struct cred *cred; + struct mm_struct *mm = tsk->mm; + + WARN_ON(oom_killer_disabled); + /* OOM killer might race with memcg OOM */ + if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) + return; + + /* oom_mm is bound to the signal struct life time. */ + if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) + mmgrab(tsk->signal->oom_mm); /* - * 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 + * 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. */ - if (p->flags & PF_EXITING) { - set_tsk_thread_flag(p, TIF_MEMDIE); - put_task_struct(p); - return; + thaw_process(tsk); + atomic_inc(&oom_victims); + cred = get_task_cred(tsk); + trace_mark_victim(tsk, cred->uid.val); + put_cred(cred); +} + +/** + * exit_oom_victim - note the exit of an OOM victim + */ +void exit_oom_victim(void) +{ + clear_thread_flag(TIF_MEMDIE); + + if (!atomic_dec_return(&oom_victims)) + wake_up_all(&oom_victims_wait); +} + +/** + * oom_killer_enable - enable OOM killer + */ +void oom_killer_enable(void) +{ + oom_killer_disabled = false; + pr_info("OOM killer enabled.\n"); +} + +/** + * oom_killer_disable - disable OOM killer + * @timeout: maximum timeout to wait for oom victims in jiffies + * + * Forces all page allocations to fail rather than trigger OOM killer. + * Will block and wait until all OOM victims are killed or the given + * timeout expires. + * + * The function cannot be called when there are runnable user tasks because + * the userspace would see unexpected allocation failures as a result. Any + * new usage of this function should be consulted with MM people. + * + * Returns true if successful and false if the OOM killer cannot be + * disabled. + */ +bool oom_killer_disable(signed long timeout) +{ + signed long ret; + + /* + * Make sure to not race with an ongoing OOM killer. Check that the + * current is not killed (possibly due to sharing the victim's memory). + */ + if (mutex_lock_killable(&oom_lock)) + return false; + oom_killer_disabled = true; + mutex_unlock(&oom_lock); + + ret = wait_event_interruptible_timeout(oom_victims_wait, + !atomic_read(&oom_victims), timeout); + if (ret <= 0) { + oom_killer_enable(); + return false; } + pr_info("OOM killer disabled.\n"); - if (__ratelimit(&oom_rs)) - dump_header(p, gfp_mask, order, memcg, nodemask); + return true; +} - task_lock(p); - pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n", - message, task_pid_nr(p), p->comm, points); - task_unlock(p); +static inline bool __task_will_free_mem(struct task_struct *task) +{ + struct signal_struct *sig = task->signal; /* - * If any of p's children has a different mm and is eligible for kill, - * the one with the highest oom_badness() score is sacrificed for its - * parent. This attempts to lose the minimal amount of work done while - * still freeing 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. */ - read_lock(&tasklist_lock); - do { - list_for_each_entry(child, &t->children, sibling) { - unsigned int child_points; + if (sig->core_state) + return false; - if (child->mm == p->mm) - continue; - /* - * oom_badness() returns 0 if the thread is unkillable - */ - child_points = oom_badness(child, memcg, nodemask, - totalpages); - if (child_points > victim_points) { - put_task_struct(victim); - victim = child; - victim_points = child_points; - get_task_struct(victim); - } - } - } while_each_thread(p, t); - read_unlock(&tasklist_lock); + if (sig->flags & SIGNAL_GROUP_EXIT) + return true; + + if (thread_group_empty(task) && (task->flags & PF_EXITING)) + return true; + + return false; +} +/* + * Checks whether the given task is dying or exiting and likely to + * release its address space. This means that all threads and processes + * sharing the same mm have to be killed or exiting. + * Caller has to make sure that task->mm is stable (hold task_lock or + * it operates on the current). + */ +static bool task_will_free_mem(struct task_struct *task) +{ + struct mm_struct *mm = task->mm; + struct task_struct *p; + bool ret = true; + + /* + * Skip tasks without mm because it might have passed its exit_mm and + * exit_oom_victim. oom_reaper could have rescued that but do not rely + * on that for now. We can consider find_lock_task_mm in future. + */ + if (!mm) + return false; + + if (!__task_will_free_mem(task)) + return false; + + /* + * This task has already been drained by the oom reaper so there are + * only small chances it will free some more + */ + if (mm_flags_test(MMF_OOM_SKIP, mm)) + return false; + + if (atomic_read(&mm->mm_users) <= 1) + return true; + + /* + * Make sure that all tasks which share the mm with the given tasks + * are dying as well to make sure that a) nobody pins its mm and + * b) the task is also reapable by the oom reaper. + */ rcu_read_lock(); + for_each_process(p) { + if (!process_shares_mm(p, mm)) + continue; + if (same_thread_group(task, p)) + continue; + ret = __task_will_free_mem(p); + if (!ret) + break; + } + rcu_read_unlock(); + + return ret; +} + +static void __oom_kill_process(struct task_struct *victim, const char *message) +{ + struct task_struct *p; + struct mm_struct *mm; + bool can_oom_reap = true; + p = find_lock_task_mm(victim); if (!p) { - rcu_read_unlock(); + pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n", + message, task_pid_nr(victim), victim->comm); put_task_struct(victim); return; } else if (victim != p) { @@ -470,48 +943,136 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, victim = p; } - /* mm cannot safely be dereferenced after task_unlock(victim) */ + /* Get a reference to safely compare mm after task_unlock(victim) */ mm = victim->mm; - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", - task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), - K(get_mm_counter(victim->mm, MM_ANONPAGES)), - K(get_mm_counter(victim->mm, MM_FILEPAGES))); + mmgrab(mm); + + /* Raise event before sending signal: task reaper must see this */ + count_vm_event(OOM_KILL); + memcg_memory_event_mm(mm, MEMCG_OOM_KILL); + + /* + * 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_PRIV, victim, PIDTYPE_TGID); + mark_oom_victim(victim); + pr_err("%s: Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB, UID:%u pgtables:%lukB oom_score_adj:%hd\n", + message, task_pid_nr(victim), victim->comm, K(mm->total_vm), + K(get_mm_counter(mm, MM_ANONPAGES)), + K(get_mm_counter(mm, MM_FILEPAGES)), + K(get_mm_counter(mm, MM_SHMEMPAGES)), + from_kuid(&init_user_ns, task_uid(victim)), + mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj); task_unlock(victim); /* * Kill all user processes sharing victim->mm in other thread groups, if * any. They don't get access to memory reserves, though, to avoid - * depletion of all memory. This prevents mm->mmap_sem livelock when an + * depletion of all memory. This prevents mm->mmap_lock livelock when an * oom killed thread cannot exit because it requires the semaphore and * its contended by another thread trying to allocate memory itself. * That thread will now get access to memory reserves since it has a * pending fatal signal. */ - for_each_process(p) - if (p->mm == mm && !same_thread_group(p, victim) && - !(p->flags & PF_KTHREAD)) { - if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - continue; - - task_lock(p); /* Protect ->comm from prctl() */ - pr_err("Kill process %d (%s) sharing same memory\n", - task_pid_nr(p), p->comm); - task_unlock(p); - do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); + rcu_read_lock(); + for_each_process(p) { + if (!process_shares_mm(p, mm)) + continue; + if (same_thread_group(p, victim)) + continue; + if (is_global_init(p)) { + can_oom_reap = false; + 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); + continue; } + /* + * No kthread_use_mm() user needs to read from the userspace so + * we are ok to reap it. + */ + if (unlikely(p->flags & PF_KTHREAD)) + continue; + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID); + } rcu_read_unlock(); - set_tsk_thread_flag(victim, TIF_MEMDIE); - do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); + if (can_oom_reap) + queue_oom_reaper(victim); + + mmdrop(mm); put_task_struct(victim); } -#undef K + +/* + * Kill provided task unless it's secured by setting + * oom_score_adj to OOM_SCORE_ADJ_MIN. + */ +static int oom_kill_memcg_member(struct task_struct *task, void *message) +{ + if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN && + !is_global_init(task)) { + get_task_struct(task); + __oom_kill_process(task, message); + } + return 0; +} + +static void oom_kill_process(struct oom_control *oc, const char *message) +{ + struct task_struct *victim = oc->chosen; + struct mem_cgroup *oom_group; + static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + /* + * If the task is already exiting, don't alarm the sysadmin or kill + * its children or threads, just give it access to memory reserves + * so it can die quickly + */ + task_lock(victim); + if (task_will_free_mem(victim)) { + mark_oom_victim(victim); + queue_oom_reaper(victim); + task_unlock(victim); + put_task_struct(victim); + return; + } + task_unlock(victim); + + if (__ratelimit(&oom_rs)) { + dump_header(oc); + dump_oom_victim(oc, victim); + } + + /* + * Do we need to kill the entire memory cgroup? + * Or even one of the ancestor memory cgroups? + * Check this out before killing the victim task. + */ + oom_group = mem_cgroup_get_oom_group(victim, oc->memcg); + + __oom_kill_process(victim, 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); + mem_cgroup_put(oom_group); + } +} /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask) +static void check_panic_on_oom(struct oom_control *oc) { if (likely(!sysctl_panic_on_oom)) return; @@ -521,10 +1082,13 @@ void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, * does not panic for cpuset, mempolicy, or memcg allocation * failures. */ - if (constraint != CONSTRAINT_NONE) + if (oc->constraint != CONSTRAINT_NONE) return; } - dump_header(NULL, gfp_mask, order, NULL, nodemask); + /* Do not panic for oom kills triggered by sysrq */ + if (is_sysrq_oom(oc)) + return; + dump_header(oc); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -543,146 +1107,167 @@ int unregister_oom_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_oom_notifier); -/* - * Try to acquire the OOM killer lock for the zones in zonelist. Returns zero - * if a parallel OOM killing is already taking place that includes a zone in - * the zonelist. Otherwise, locks all zones in the zonelist and returns 1. - */ -int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask) -{ - struct zoneref *z; - struct zone *zone; - int ret = 1; - - spin_lock(&zone_scan_lock); - for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) { - if (zone_is_oom_locked(zone)) { - ret = 0; - goto out; - } - } - - for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) { - /* - * Lock each zone in the zonelist under zone_scan_lock so a - * parallel invocation of try_set_zonelist_oom() doesn't succeed - * when it shouldn't. - */ - zone_set_flag(zone, ZONE_OOM_LOCKED); - } - -out: - spin_unlock(&zone_scan_lock); - return ret; -} - -/* - * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed - * allocation attempts with zonelists containing them may now recall the OOM - * killer, if necessary. - */ -void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask) -{ - struct zoneref *z; - struct zone *zone; - - spin_lock(&zone_scan_lock); - for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) { - zone_clear_flag(zone, ZONE_OOM_LOCKED); - } - spin_unlock(&zone_scan_lock); -} - /** * out_of_memory - kill the "best" process when we run out of memory - * @zonelist: zonelist pointer - * @gfp_mask: memory allocation flags - * @order: amount of memory being requested as a power of 2 - * @nodemask: nodemask passed to page allocator - * @force_kill: true if a task must be killed, even if others are exiting + * @oc: pointer to struct oom_control * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ -void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, - int order, nodemask_t *nodemask, bool force_kill) +bool out_of_memory(struct oom_control *oc) { - const nodemask_t *mpol_mask; - struct task_struct *p; - unsigned long totalpages; unsigned long freed = 0; - unsigned int uninitialized_var(points); - enum oom_constraint constraint = CONSTRAINT_NONE; - int killed = 0; - blocking_notifier_call_chain(&oom_notify_list, 0, &freed); - if (freed > 0) - /* Got some memory back in the last second. */ - return; + if (oom_killer_disabled) + return false; + + if (!is_memcg_oom(oc)) { + blocking_notifier_call_chain(&oom_notify_list, 0, &freed); + if (freed > 0 && !is_sysrq_oom(oc)) + /* Got some memory back in the last second. */ + return true; + } /* * If current has a pending SIGKILL or is exiting, then automatically * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ - if (fatal_signal_pending(current) || current->flags & PF_EXITING) { - set_thread_flag(TIF_MEMDIE); - return; + if (task_will_free_mem(current)) { + mark_oom_victim(current); + queue_oom_reaper(current); + return true; } /* - * Check if there were limitations on the allocation (only relevant for - * NUMA) that may require different handling. + * The OOM killer does not compensate for IO-less reclaim. + * But mem_cgroup_oom() has to invoke the OOM killer even + * if it is a GFP_NOFS allocation. */ - constraint = constrained_alloc(zonelist, gfp_mask, nodemask, - &totalpages); - mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; - check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); + if (!(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc)) + return true; - if (sysctl_oom_kill_allocating_task && current->mm && - !oom_unkillable_task(current, NULL, nodemask) && + /* + * Check if there were limitations on the allocation (only relevant for + * NUMA and memcg) that may require different handling. + */ + oc->constraint = constrained_alloc(oc); + if (oc->constraint != CONSTRAINT_MEMORY_POLICY) + oc->nodemask = NULL; + check_panic_on_oom(oc); + + if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && + current->mm && !oom_unkillable_task(current) && + oom_cpuset_eligible(current, oc) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); - oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL, - nodemask, - "Out of memory (oom_kill_allocating_task)"); - goto out; + oc->chosen = current; + oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)"); + return true; } - p = select_bad_process(&points, totalpages, mpol_mask, force_kill); - /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!p) { - dump_header(NULL, gfp_mask, order, NULL, mpol_mask); - panic("Out of memory and no killable processes...\n"); - } - if (PTR_ERR(p) != -1UL) { - oom_kill_process(p, gfp_mask, order, points, totalpages, NULL, - nodemask, "Out of memory"); - killed = 1; + select_bad_process(oc); + /* Found nothing?!?! */ + if (!oc->chosen) { + dump_header(oc); + pr_warn("Out of memory and no killable processes...\n"); + /* + * If we got here due to an actual allocation at the + * system level, we cannot survive this and will enter + * an endless loop in the allocator. Bail out now. + */ + if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) + panic("System is deadlocked on memory\n"); } -out: - /* - * Give the killed threads a good chance of exiting before trying to - * allocate memory again. - */ - if (killed) - schedule_timeout_killable(1); + if (oc->chosen && oc->chosen != (void *)-1UL) + oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : + "Memory cgroup out of memory"); + return !!oc->chosen; } /* - * The pagefault handler calls here because it is out of memory, so kill a - * memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, 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 zonelist *zonelist = node_zonelist(first_online_node, - GFP_KERNEL); + static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if (mem_cgroup_oom_synchronize(true)) + return; + + if (fatal_signal_pending(current)) + return; + + 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 (!mm_flags_test(MMF_OOM_SKIP, mm)) + ret = -EINVAL; + } + task_unlock(p); + + if (!reap) + goto drop_mm; - if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) { - out_of_memory(NULL, 0, 0, NULL, false); - clear_zonelist_oom(zonelist, GFP_KERNEL); + 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 (!mm_flags_test(MMF_OOM_SKIP, mm) && !__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 */ } |