diff options
Diffstat (limited to 'mm/oom_kill.c')
| -rw-r--r-- | mm/oom_kill.c | 868 |
1 files changed, 443 insertions, 425 deletions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f52481b1c1e..3291e82d435 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -4,6 +4,8 @@ * 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... + * Copyright (C) 2010 Google, Inc. + * Rewritten by David Rientjes * * The routines in this file are used to kill a process when * we're seriously out of memory. This gets called from __alloc_pages() @@ -18,179 +20,175 @@ #include <linux/oom.h> #include <linux/mm.h> #include <linux/err.h> +#include <linux/gfp.h> #include <linux/sched.h> #include <linux/swap.h> #include <linux/timex.h> #include <linux/jiffies.h> #include <linux/cpuset.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/notifier.h> #include <linux/memcontrol.h> +#include <linux/mempolicy.h> #include <linux/security.h> +#include <linux/ptrace.h> +#include <linux/freezer.h> +#include <linux/ftrace.h> +#include <linux/ratelimit.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; +int sysctl_oom_dump_tasks = 1; static DEFINE_SPINLOCK(zone_scan_lock); -/* #define DEBUG */ -/* - * Is all threads of the target process nodes overlap ours? +#ifdef CONFIG_NUMA +/** + * has_intersects_mems_allowed() - check task eligiblity for kill + * @start: task struct of which task to consider + * @mask: nodemask passed to page allocator for mempolicy ooms + * + * 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. */ -static int has_intersects_mems_allowed(struct task_struct *tsk) +static bool has_intersects_mems_allowed(struct task_struct *start, + const nodemask_t *mask) { - struct task_struct *t; + struct task_struct *tsk; + bool ret = false; - t = tsk; - do { - if (cpuset_mems_allowed_intersects(current, t)) - return 1; - t = next_thread(t); - } while (t != tsk); + rcu_read_lock(); + for_each_thread(start, tsk) { + if (mask) { + /* + * If this is a mempolicy constrained oom, tsk's + * cpuset is irrelevant. Only return true if its + * mempolicy intersects current, otherwise it may be + * needlessly killed. + */ + ret = mempolicy_nodemask_intersects(tsk, mask); + } else { + /* + * This is not a mempolicy constrained oom, so only + * check the mems of tsk's cpuset. + */ + ret = cpuset_mems_allowed_intersects(current, tsk); + } + if (ret) + break; + } + rcu_read_unlock(); - return 0; + return ret; +} +#else +static bool has_intersects_mems_allowed(struct task_struct *tsk, + const nodemask_t *mask) +{ + return true; } +#endif /* CONFIG_NUMA */ -/** - * badness - calculate a numeric value for how bad this task has been - * @p: task struct of which task we should calculate - * @uptime: current uptime in seconds - * - * The formula used is relatively simple and documented inline in the - * function. The main rationale is that we want to select a good task - * to kill when we run out of memory. - * - * Good in this context means that: - * 1) we lose the minimum amount of work done - * 2) we recover a large amount of memory - * 3) we don't kill anything innocent of eating tons of memory - * 4) we want to kill the minimum amount of processes (one) - * 5) we try to kill the process the user expects us to kill, this - * algorithm has been meticulously tuned to meet the principle - * of least surprise ... (be careful when you change it) +/* + * 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 + * pointer. Return p, or any of its subthreads with a valid ->mm, with + * task_lock() held. */ - -unsigned long badness(struct task_struct *p, unsigned long uptime) +struct task_struct *find_lock_task_mm(struct task_struct *p) { - unsigned long points, cpu_time, run_time; - struct mm_struct *mm; - struct task_struct *child; - int oom_adj = p->signal->oom_adj; - struct task_cputime task_time; - unsigned long utime; - unsigned long stime; + struct task_struct *t; - if (oom_adj == OOM_DISABLE) - return 0; + rcu_read_lock(); - task_lock(p); - mm = p->mm; - if (!mm) { - task_unlock(p); - return 0; + for_each_thread(p, t) { + task_lock(t); + if (likely(t->mm)) + goto found; + task_unlock(t); } + t = NULL; +found: + rcu_read_unlock(); - /* - * The memory size of the process is the basis for the badness. - */ - points = mm->total_vm; + return t; +} - /* - * After this unlock we can no longer dereference local variable `mm' - */ - task_unlock(p); +/* 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) +{ + if (is_global_init(p)) + return true; + if (p->flags & PF_KTHREAD) + return true; - /* - * swapoff can easily use up all memory, so kill those first. - */ - if (p->flags & PF_OOM_ORIGIN) - return ULONG_MAX; + /* When mem_cgroup_out_of_memory() and p is not member of the group */ + if (memcg && !task_in_mem_cgroup(p, memcg)) + return true; - /* - * Processes which fork a lot of child processes are likely - * a good choice. We add half the vmsize of the children if they - * have an own mm. This prevents forking servers to flood the - * machine with an endless amount of children. In case a single - * child is eating the vast majority of memory, adding only half - * to the parents will make the child our kill candidate of choice. - */ - list_for_each_entry(child, &p->children, sibling) { - task_lock(child); - if (child->mm != mm && child->mm) - points += child->mm->total_vm/2 + 1; - task_unlock(child); - } + /* p may not have freeable memory in nodemask */ + if (!has_intersects_mems_allowed(p, nodemask)) + return true; - /* - * CPU time is in tens of seconds and run time is in thousands - * of seconds. There is no particular reason for this other than - * that it turned out to work very well in practice. - */ - thread_group_cputime(p, &task_time); - utime = cputime_to_jiffies(task_time.utime); - stime = cputime_to_jiffies(task_time.stime); - cpu_time = (utime + stime) >> (SHIFT_HZ + 3); + return false; +} +/** + * oom_badness - heuristic function to determine which candidate task to kill + * @p: task struct of which task we should calculate + * @totalpages: total present RAM allowed for page allocation + * + * The heuristic for determining which task to kill is made to be as simple and + * 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 points; + long adj; - if (uptime >= p->start_time.tv_sec) - run_time = (uptime - p->start_time.tv_sec) >> 10; - else - run_time = 0; + if (oom_unkillable_task(p, memcg, nodemask)) + return 0; - if (cpu_time) - points /= int_sqrt(cpu_time); - if (run_time) - points /= int_sqrt(int_sqrt(run_time)); + p = find_lock_task_mm(p); + if (!p) + return 0; - /* - * Niced processes are most likely less important, so double - * their badness points. - */ - if (task_nice(p) > 0) - points *= 2; + adj = (long)p->signal->oom_score_adj; + if (adj == OOM_SCORE_ADJ_MIN) { + task_unlock(p); + return 0; + } /* - * Superuser processes are usually more important, so we make it - * less likely that we kill those. + * The baseline for the badness score is the proportion of RAM that each + * task's rss, pagetable and swap space use. */ - if (has_capability_noaudit(p, CAP_SYS_ADMIN) || - has_capability_noaudit(p, CAP_SYS_RESOURCE)) - points /= 4; + points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + + get_mm_counter(p->mm, MM_SWAPENTS); + task_unlock(p); /* - * We don't want to kill a process with direct hardware access. - * Not only could that mess up the hardware, but usually users - * tend to only have this flag set on applications they think - * of as important. + * Root processes get 3% bonus, just like the __vm_enough_memory() + * implementation used by LSMs. */ - if (has_capability_noaudit(p, CAP_SYS_RAWIO)) - points /= 4; + if (has_capability_noaudit(p, CAP_SYS_ADMIN)) + points -= (points * 3) / 100; - /* - * If p's nodes don't overlap ours, it may still help to kill p - * because p may have allocated or otherwise mapped memory on - * this node before. However it will be less likely. - */ - if (!has_intersects_mems_allowed(p)) - points /= 8; + /* Normalize to oom_score_adj units */ + adj *= totalpages / 1000; + points += adj; /* - * Adjust the score by oom_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). */ - if (oom_adj) { - if (oom_adj > 0) { - if (!points) - points = 1; - points <<= oom_adj; - } else - points >>= -(oom_adj); - } - -#ifdef DEBUG - printk(KERN_DEBUG "OOMkill: task %d (%s) got %lu points\n", - p->pid, p->comm, points); -#endif - return points; + return points > 0 ? points : 1; } /* @@ -198,12 +196,20 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) */ #ifdef CONFIG_NUMA static enum oom_constraint constrained_alloc(struct zonelist *zonelist, - gfp_t gfp_mask, nodemask_t *nodemask) + gfp_t gfp_mask, nodemask_t *nodemask, + unsigned long *totalpages) { struct zone *zone; struct zoneref *z; enum zone_type high_zoneidx = gfp_zone(gfp_mask); + bool cpuset_limited = false; + int nid; + + /* Default to all available memory */ + *totalpages = totalram_pages + total_swap_pages; + if (!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. @@ -213,280 +219,326 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, return CONSTRAINT_NONE; /* - * The nodemask here is a nodemask passed to alloc_pages(). Now, - * cpuset doesn't use this nodemask for its hardwall/softwall/hierarchy - * feature. mempolicy is an only user of nodemask here. - * check mempolicy's nodemask contains all N_HIGH_MEMORY + * This is not a __GFP_THISNODE allocation, so a truncated nodemask in + * 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_HIGH_MEMORY], *nodemask)) + if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) { + *totalpages = total_swap_pages; + for_each_node_mask(nid, *nodemask) + *totalpages += node_spanned_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)) - return CONSTRAINT_CPUSET; + cpuset_limited = true; + if (cpuset_limited) { + *totalpages = total_swap_pages; + for_each_node_mask(nid, cpuset_current_mems_allowed) + *totalpages += node_spanned_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) + 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) +{ + if (task->exit_state) + return OOM_SCAN_CONTINUE; + if (oom_unkillable_task(task, NULL, nodemask)) + return OOM_SCAN_CONTINUE; + + /* + * This task already has access to memory reserves and is being killed. + * Don't allow any other task to have access to the reserves. + */ + if (test_tsk_thread_flag(task, TIF_MEMDIE)) { + if (unlikely(frozen(task))) + __thaw_task(task); + if (!force_kill) + return OOM_SCAN_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; + } + return OOM_SCAN_OK; +} + /* * Simple selection loop. We chose the process with the highest - * number of 'points'. We expect the caller will lock the tasklist. + * number of 'points'. Returns -1 on scan abort. * * (not docbooked, we don't want this one cluttering up the manual) */ -static struct task_struct *select_bad_process(unsigned long *ppoints, - struct mem_cgroup *mem) +static struct task_struct *select_bad_process(unsigned int *ppoints, + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) { - struct task_struct *p; + struct task_struct *g, *p; struct task_struct *chosen = NULL; - struct timespec uptime; - *ppoints = 0; + unsigned long chosen_points = 0; - do_posix_clock_monotonic_gettime(&uptime); - for_each_process(p) { - unsigned long points; + rcu_read_lock(); + for_each_process_thread(g, p) { + unsigned int points; - /* - * skip kernel threads and tasks which have already released - * their mm. - */ - if (!p->mm) - continue; - /* skip the init task */ - if (is_global_init(p)) + 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; - if (mem && !task_in_mem_cgroup(p, mem)) + case OOM_SCAN_ABORT: + rcu_read_unlock(); + return (struct task_struct *)(-1UL); + case OOM_SCAN_OK: + break; + }; + points = oom_badness(p, NULL, nodemask, totalpages); + if (!points || points < chosen_points) continue; - - /* - * This task already has access to memory reserves and is - * being killed. Don't allow any other task access to the - * memory reserve. - * - * Note: this may have a chance of deadlock if it gets - * blocked waiting for another task which itself is waiting - * for memory. Is there a better alternative? - */ - if (test_tsk_thread_flag(p, TIF_MEMDIE)) - return ERR_PTR(-1UL); - - /* - * This is in the process of releasing memory so wait for it - * to finish before killing some other task by mistake. - * - * However, if p is the current task, we allow the 'kill' to - * go ahead if it is exiting: this will simply set TIF_MEMDIE, - * which will allow it to gain access to memory reserves in - * the process of exiting and releasing its resources. - * Otherwise we could get an easy OOM deadlock. - */ - if (p->flags & PF_EXITING) { - if (p != current) - return ERR_PTR(-1UL); - - chosen = p; - *ppoints = ULONG_MAX; - } - - if (p->signal->oom_adj == OOM_DISABLE) + /* Prefer thread group leaders for display purposes */ + if (points == chosen_points && thread_group_leader(chosen)) continue; - points = badness(p, uptime.tv_sec); - if (points > *ppoints || !chosen) { - chosen = p; - *ppoints = points; - } + chosen = p; + chosen_points = points; } + if (chosen) + get_task_struct(chosen); + rcu_read_unlock(); + *ppoints = chosen_points * 1000 / totalpages; return chosen; } /** * dump_tasks - dump current memory state of all system tasks - * @mem: target memory controller - * - * Dumps the current memory state of all system tasks, excluding kernel threads. - * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj - * score, and name. - * - * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are - * shown. + * @memcg: current's memory controller, if constrained + * @nodemask: nodemask passed to page allocator for mempolicy ooms * - * Call with tasklist_lock read-locked. + * 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. */ -static void dump_tasks(const struct mem_cgroup *mem) +static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask) { - struct task_struct *g, *p; - - printk(KERN_INFO "[ pid ] uid tgid total_vm rss cpu oom_adj " - "name\n"); - do_each_thread(g, p) { - struct mm_struct *mm; + struct task_struct *p; + struct task_struct *task; - if (mem && !task_in_mem_cgroup(p, mem)) - continue; - if (!thread_group_leader(p)) + 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; - task_lock(p); - mm = p->mm; - if (!mm) { + task = find_lock_task_mm(p); + if (!task) { /* - * total_vm and rss sizes do not exist for tasks with no - * mm so there's no need to report them; they can't be - * oom killed anyway. + * 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. */ - task_unlock(p); continue; } - printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", - p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, - get_mm_rss(mm), (int)task_cpu(p), p->signal->oom_adj, - p->comm); - task_unlock(p); - } while_each_thread(g, p); + + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %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), + get_mm_counter(task->mm, MM_SWAPENTS), + task->signal->oom_score_adj, task->comm); + task_unlock(task); + } + rcu_read_unlock(); } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, - struct mem_cgroup *mem) + struct mem_cgroup *memcg, const nodemask_t *nodemask) { - pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, " - "oom_adj=%d\n", - current->comm, gfp_mask, order, current->signal->oom_adj); 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(); - mem_cgroup_print_oom_info(mem, p); - show_mem(); + if (memcg) + mem_cgroup_print_oom_info(memcg, p); + else + show_mem(SHOW_MEM_FILTER_NODES); if (sysctl_oom_dump_tasks) - dump_tasks(mem); + dump_tasks(memcg, nodemask); } #define K(x) ((x) << (PAGE_SHIFT-10)) - /* - * Send SIGKILL to the selected process irrespective of CAP_SYS_RAW_IO - * flag though it's unlikely that we select a process with CAP_SYS_RAW_IO - * set. + * Must be called while holding a reference to p, which will be released upon + * returning. */ -static void __oom_kill_task(struct task_struct *p, int verbose) +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) { - if (is_global_init(p)) { - WARN_ON(1); - printk(KERN_WARNING "tried to kill init!\n"); - return; - } + struct task_struct *victim = p; + struct task_struct *child; + struct task_struct *t; + struct mm_struct *mm; + unsigned int victim_points = 0; + static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); - task_lock(p); - if (!p->mm) { - WARN_ON(1); - printk(KERN_WARNING "tried to kill an mm-less task %d (%s)!\n", - task_pid_nr(p), p->comm); - task_unlock(p); + /* + * 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 + */ + if (p->flags & PF_EXITING) { + set_tsk_thread_flag(p, TIF_MEMDIE); + put_task_struct(p); return; } - if (verbose) - printk(KERN_ERR "Killed process %d (%s) " - "vsz:%lukB, anon-rss:%lukB, file-rss:%lukB\n", - task_pid_nr(p), p->comm, - K(p->mm->total_vm), - K(get_mm_counter(p->mm, anon_rss)), - K(get_mm_counter(p->mm, file_rss))); + if (__ratelimit(&oom_rs)) + dump_header(p, gfp_mask, order, memcg, nodemask); + + 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); /* - * We give our sacrificial lamb high priority and access to - * all the memory it needs. That way it should be able to - * exit() and clear out its resources quickly... + * 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. */ - p->rt.time_slice = HZ; - set_tsk_thread_flag(p, TIF_MEMDIE); - - force_sig(SIGKILL, p); -} - -static int oom_kill_task(struct task_struct *p) -{ - /* WARNING: mm may not be dereferenced since we did not obtain its - * value from get_task_mm(p). This is OK since all we need to do is - * compare mm to q->mm below. - * - * Furthermore, even if mm contains a non-NULL value, p->mm may - * change to NULL at any time since we do not hold task_lock(p). - * However, this is of no concern to us. - */ - if (!p->mm || p->signal->oom_adj == OOM_DISABLE) - return 1; - - __oom_kill_task(p, 1); + read_lock(&tasklist_lock); + for_each_thread(p, t) { + list_for_each_entry(child, &t->children, sibling) { + unsigned int child_points; - return 0; -} + 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); + } + } + } + read_unlock(&tasklist_lock); -static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned long points, struct mem_cgroup *mem, - const char *message) -{ - struct task_struct *c; + p = find_lock_task_mm(victim); + if (!p) { + put_task_struct(victim); + return; + } else if (victim != p) { + get_task_struct(p); + put_task_struct(victim); + victim = p; + } - if (printk_ratelimit()) - dump_header(p, gfp_mask, order, mem); + /* mm cannot safely be dereferenced 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))); + task_unlock(victim); /* - * 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 + * 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 + * 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. */ - if (p->flags & PF_EXITING) { - __oom_kill_task(p, 0); - return 0; - } - - printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n", - message, task_pid_nr(p), p->comm, points); + rcu_read_lock(); + 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_unlock(); - /* Try to kill a child first */ - list_for_each_entry(c, &p->children, sibling) { - if (c->mm == p->mm) - continue; - if (!oom_kill_task(c)) - return 0; - } - return oom_kill_task(p); + set_tsk_thread_flag(victim, TIF_MEMDIE); + do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); + put_task_struct(victim); } +#undef K -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) +/* + * 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) { - unsigned long points = 0; - struct task_struct *p; - - read_lock(&tasklist_lock); -retry: - p = select_bad_process(&points, mem); - if (PTR_ERR(p) == -1UL) - goto out; - - if (!p) - p = current; - - if (oom_kill_process(p, gfp_mask, 0, points, mem, - "Memory cgroup out of memory")) - goto retry; -out: - read_unlock(&tasklist_lock); + if (likely(!sysctl_panic_on_oom)) + return; + if (sysctl_panic_on_oom != 2) { + /* + * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel + * does not panic for cpuset, mempolicy, or memcg allocation + * failures. + */ + if (constraint != CONSTRAINT_NONE) + return; + } + dump_header(NULL, gfp_mask, order, NULL, nodemask); + panic("Out of memory: %s panic_on_oom is enabled\n", + sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } -#endif static BLOCKING_NOTIFIER_HEAD(oom_notify_list); @@ -507,7 +559,7 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier); * 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_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask) +int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask) { struct zoneref *z; struct zone *zone; @@ -524,7 +576,7 @@ int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask) 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_zone_oom() doesn't succeed + * parallel invocation of try_set_zonelist_oom() doesn't succeed * when it shouldn't. */ zone_set_flag(zone, ZONE_OOM_LOCKED); @@ -552,81 +604,13 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask) spin_unlock(&zone_scan_lock); } -/* - * Must be called with tasklist_lock held for read. - */ -static void __out_of_memory(gfp_t gfp_mask, int order) -{ - struct task_struct *p; - unsigned long points; - - if (sysctl_oom_kill_allocating_task) - if (!oom_kill_process(current, gfp_mask, order, 0, NULL, - "Out of memory (oom_kill_allocating_task)")) - return; -retry: - /* - * Rambo mode: Shoot down a process and hope it solves whatever - * issues we may have. - */ - p = select_bad_process(&points, NULL); - - if (PTR_ERR(p) == -1UL) - return; - - /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!p) { - read_unlock(&tasklist_lock); - dump_header(NULL, gfp_mask, order, NULL); - panic("Out of memory and no killable processes...\n"); - } - - if (oom_kill_process(p, gfp_mask, order, points, NULL, - "Out of memory")) - goto retry; -} - -/* - * pagefault handler calls into here because it is out of memory but - * doesn't know exactly how or why. - */ -void pagefault_out_of_memory(void) -{ - unsigned long freed = 0; - - blocking_notifier_call_chain(&oom_notify_list, 0, &freed); - if (freed > 0) - /* Got some memory back in the last second. */ - return; - - /* - * If this is from memcg, oom-killer is already invoked. - * and not worth to go system-wide-oom. - */ - if (mem_cgroup_oom_called(current)) - goto rest_and_return; - - if (sysctl_panic_on_oom) - panic("out of memory from page fault. panic_on_oom is selected.\n"); - - read_lock(&tasklist_lock); - __out_of_memory(0, 0); /* unknown gfp_mask and order */ - read_unlock(&tasklist_lock); - - /* - * Give "p" a good chance of killing itself before we - * retry to allocate memory. - */ -rest_and_return: - if (!test_thread_flag(TIF_MEMDIE)) - schedule_timeout_uninterruptible(1); -} - /** * 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 * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) @@ -634,51 +618,85 @@ rest_and_return: * 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) + int order, nodemask_t *nodemask, bool force_kill) { + const nodemask_t *mpol_mask; + struct task_struct *p; + unsigned long totalpages; unsigned long freed = 0; - enum oom_constraint constraint; + 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 (sysctl_panic_on_oom == 2) { - dump_header(NULL, gfp_mask, order, NULL); - panic("out of memory. Compulsory panic_on_oom is selected.\n"); + /* + * 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; } /* * Check if there were limitations on the allocation (only relevant for * NUMA) that may require different handling. */ - constraint = constrained_alloc(zonelist, gfp_mask, nodemask); - read_lock(&tasklist_lock); - - switch (constraint) { - case CONSTRAINT_MEMORY_POLICY: - oom_kill_process(current, gfp_mask, order, 0, NULL, - "No available memory (MPOL_BIND)"); - break; - - case CONSTRAINT_NONE: - if (sysctl_panic_on_oom) { - dump_header(NULL, gfp_mask, order, NULL); - panic("out of memory. panic_on_oom is selected\n"); - } - /* Fall-through */ - case CONSTRAINT_CPUSET: - __out_of_memory(gfp_mask, order); - break; + 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 (sysctl_oom_kill_allocating_task && current->mm && + !oom_unkillable_task(current, NULL, nodemask) && + 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; } - read_unlock(&tasklist_lock); - + 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 (p != (void *)-1UL) { + oom_kill_process(p, gfp_mask, order, points, totalpages, NULL, + nodemask, "Out of memory"); + killed = 1; + } +out: /* - * Give "p" a good chance of killing itself before we - * retry to allocate memory unless "p" is current + * Give the killed threads a good chance of exiting before trying to + * allocate memory again. */ - if (!test_thread_flag(TIF_MEMDIE)) - schedule_timeout_uninterruptible(1); + if (killed) + schedule_timeout_killable(1); +} + +/* + * 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. + */ +void pagefault_out_of_memory(void) +{ + struct zonelist *zonelist; + + if (mem_cgroup_oom_synchronize(true)) + return; + + zonelist = node_zonelist(first_online_node, GFP_KERNEL); + if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) { + out_of_memory(NULL, 0, 0, NULL, false); + clear_zonelist_oom(zonelist, GFP_KERNEL); + } } |