#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>
+
+#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);
+/*
+ * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj
+ * @old_val: old oom_score_adj for compare
+ * @new_val: new oom_score_adj for swap
+ *
+ * Sets the oom_score_adj value for current to @new_val iff its present value is
+ * @old_val. Usually used to reinstate a previous value to prevent racing with
+ * userspacing tuning the value in the interim.
+ */
+void compare_swap_oom_score_adj(int old_val, int new_val)
+{
+ struct sighand_struct *sighand = current->sighand;
+
+ spin_lock_irq(&sighand->siglock);
+ if (current->signal->oom_score_adj == old_val)
+ current->signal->oom_score_adj = new_val;
+ trace_oom_score_adj_update(current);
+ spin_unlock_irq(&sighand->siglock);
+}
+
+/**
+ * test_set_oom_score_adj() - set current's oom_score_adj and return old value
+ * @new_val: new oom_score_adj value
+ *
+ * Sets the oom_score_adj value for current to @new_val with proper
+ * synchronization and returns the old value. Usually used to temporarily
+ * set a value, save the old value in the caller, and then reinstate it later.
+ */
+int test_set_oom_score_adj(int new_val)
+{
+ struct sighand_struct *sighand = current->sighand;
+ int old_val;
+
+ spin_lock_irq(&sighand->siglock);
+ old_val = current->signal->oom_score_adj;
+ current->signal->oom_score_adj = new_val;
+ trace_oom_score_adj_update(current);
+ spin_unlock_irq(&sighand->siglock);
+
+ return old_val;
+}
+
#ifdef CONFIG_NUMA
/**
* has_intersects_mems_allowed() - check task eligiblity for kill
}
#endif /* CONFIG_NUMA */
-/*
- * If this is a system OOM (not a memcg OOM) and the task selected to be
- * killed is not already running at high (RT) priorities, speed up the
- * recovery by boosting the dying task to the lowest FIFO priority.
- * That helps with the recovery and avoids interfering with RT tasks.
- */
-static void boost_dying_task_prio(struct task_struct *p,
- struct mem_cgroup *mem)
-{
- struct sched_param param = { .sched_priority = 1 };
-
- if (mem)
- return;
-
- if (!rt_task(p))
- sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
-}
-
/*
* 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.
*/
-static struct task_struct *find_lock_task_mm(struct task_struct *p)
+struct task_struct *find_lock_task_mm(struct task_struct *p)
{
struct task_struct *t = p;
}
/* return true if the task is not adequate as candidate victim task. */
-static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *mem,
- const nodemask_t *nodemask)
+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;
return true;
/* When mem_cgroup_out_of_memory() and p is not member of the group */
- if (mem && !task_in_mem_cgroup(p, mem))
+ if (memcg && !task_in_mem_cgroup(p, memcg))
return true;
/* p may not have freeable memory in nodemask */
* predictable as possible. The goal is to return the highest value for the
* task consuming the most memory to avoid subsequent oom failures.
*/
-unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
+unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
- int points;
+ long points;
- if (oom_unkillable_task(p, mem, nodemask))
+ if (oom_unkillable_task(p, memcg, nodemask))
return 0;
p = find_lock_task_mm(p);
if (!p)
return 0;
- /*
- * Shortcut check for OOM_SCORE_ADJ_MIN so the entire heuristic doesn't
- * need to be executed for something that cannot be killed.
- */
if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
task_unlock(p);
return 0;
}
- /*
- * When the PF_OOM_ORIGIN bit is set, it indicates the task should have
- * priority for oom killing.
- */
- if (p->flags & PF_OOM_ORIGIN) {
- task_unlock(p);
- return 1000;
- }
-
/*
* The memory controller may have a limit of 0 bytes, so avoid a divide
* by zero, if necessary.
/*
* The baseline for the badness score is the proportion of RAM that each
- * task's rss and swap space use.
+ * task's rss, pagetable and swap space use.
*/
- points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 /
- totalpages;
+ points = get_mm_rss(p->mm) + p->mm->nr_ptes;
+ points += get_mm_counter(p->mm, MM_SWAPENTS);
+
+ points *= 1000;
+ points /= totalpages;
task_unlock(p);
/*
*/
points += p->signal->oom_score_adj;
- if (points < 0)
- return 0;
+ /*
+ * Never return 0 for an eligible task that may be killed since it's
+ * possible that no single user task uses more than 0.1% of memory and
+ * no single admin tasks uses more than 3.0%.
+ */
+ if (points <= 0)
+ return 1;
return (points < 1000) ? points : 1000;
}
* (not docbooked, we don't want this one cluttering up the manual)
*/
static struct task_struct *select_bad_process(unsigned int *ppoints,
- unsigned long totalpages, struct mem_cgroup *mem,
+ unsigned long totalpages, struct mem_cgroup *memcg,
const nodemask_t *nodemask)
{
- struct task_struct *p;
+ struct task_struct *g, *p;
struct task_struct *chosen = NULL;
*ppoints = 0;
- for_each_process(p) {
+ do_each_thread(g, p) {
unsigned int points;
- if (oom_unkillable_task(p, mem, nodemask))
+ if (p->exit_state)
+ continue;
+ if (oom_unkillable_task(p, memcg, nodemask))
continue;
/*
* blocked waiting for another task which itself is waiting
* for memory. Is there a better alternative?
*/
- if (test_tsk_thread_flag(p, TIF_MEMDIE))
+ if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
+ if (unlikely(frozen(p)))
+ __thaw_task(p);
return ERR_PTR(-1UL);
+ }
+ if (!p->mm)
+ continue;
- /*
- * 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 (thread_group_empty(p) && (p->flags & PF_EXITING) && p->mm) {
- if (p != current)
- return ERR_PTR(-1UL);
-
- chosen = p;
- *ppoints = 1000;
+ if (p->flags & PF_EXITING) {
+ /*
+ * If p is the current task and is in the process of
+ * releasing memory, we allow the "kill" to set
+ * TIF_MEMDIE, which will allow it to gain access to
+ * memory reserves. Otherwise, it may stall forever.
+ *
+ * The loop isn't broken here, however, in case other
+ * threads are found to have already been oom killed.
+ */
+ if (p == current) {
+ chosen = p;
+ *ppoints = 1000;
+ } else {
+ /*
+ * If this task is not being ptraced on exit,
+ * then wait for it to finish before killing
+ * some other task unnecessarily.
+ */
+ if (!(p->group_leader->ptrace & PT_TRACE_EXIT))
+ return ERR_PTR(-1UL);
+ }
}
- points = oom_badness(p, mem, nodemask, totalpages);
+ points = oom_badness(p, memcg, nodemask, totalpages);
if (points > *ppoints) {
chosen = p;
*ppoints = points;
}
- }
+ } while_each_thread(g, p);
return chosen;
}
/**
* dump_tasks - dump current memory state of all system tasks
* @mem: current's memory controller, if constrained
+ * @nodemask: nodemask passed to page allocator for mempolicy ooms
*
- * Dumps the current memory state of all system tasks, excluding kernel threads.
+ * 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, cpu, oom_adj
* value, oom_score_adj value, and name.
*
- * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are
- * shown.
- *
* Call with tasklist_lock read-locked.
*/
-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 *p;
struct task_struct *task;
pr_info("[ pid ] uid tgid total_vm rss cpu oom_adj oom_score_adj name\n");
for_each_process(p) {
- if (p->flags & PF_KTHREAD)
- continue;
- if (mem && !task_in_mem_cgroup(p, mem))
+ if (oom_unkillable_task(p, memcg, nodemask))
continue;
task = find_lock_task_mm(p);
}
pr_info("[%5d] %5d %5d %8lu %8lu %3u %3d %5d %s\n",
- task->pid, __task_cred(task)->uid, task->tgid,
+ task->pid, task_uid(task), task->tgid,
task->mm->total_vm, get_mm_rss(task->mm),
task_cpu(task), task->signal->oom_adj,
task->signal->oom_score_adj, task->comm);
}
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)
{
task_lock(current);
pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
cpuset_print_task_mems_allowed(current);
task_unlock(current);
dump_stack();
- mem_cgroup_print_oom_info(mem, p);
- show_mem();
+ mem_cgroup_print_oom_info(memcg, p);
+ 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))
-static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
+static int oom_kill_task(struct task_struct *p)
{
+ struct task_struct *q;
+ struct mm_struct *mm;
+
p = find_lock_task_mm(p);
- if (!p) {
- task_unlock(p);
+ if (!p)
return 1;
- }
+
+ /* mm cannot be safely dereferenced after task_unlock(p) */
+ mm = p->mm;
+
pr_err("Killed process %d (%s) total-vm:%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, MM_ANONPAGES)),
K(get_mm_counter(p->mm, MM_FILEPAGES)));
task_unlock(p);
+ /*
+ * Kill all user processes sharing p->mm in other thread groups, if any.
+ * They don't get access to memory reserves or a higher scheduler
+ * priority, though, to avoid depletion of all memory or task
+ * starvation. This prevents mm->mmap_sem livelock when an oom killed
+ * task 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(q)
+ if (q->mm == mm && !same_thread_group(q, p) &&
+ !(q->flags & PF_KTHREAD)) {
+ if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ continue;
+
+ task_lock(q); /* Protect ->comm from prctl() */
+ pr_err("Kill process %d (%s) sharing same memory\n",
+ task_pid_nr(q), q->comm);
+ task_unlock(q);
+ force_sig(SIGKILL, q);
+ }
set_tsk_thread_flag(p, TIF_MEMDIE);
force_sig(SIGKILL, 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...
- */
- boost_dying_task_prio(p, mem);
-
return 0;
}
#undef K
static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
unsigned int points, unsigned long totalpages,
- struct mem_cgroup *mem, nodemask_t *nodemask,
+ struct mem_cgroup *memcg, nodemask_t *nodemask,
const char *message)
{
struct task_struct *victim = p;
unsigned int victim_points = 0;
if (printk_ratelimit())
- dump_header(p, gfp_mask, order, mem);
+ dump_header(p, gfp_mask, order, memcg, nodemask);
/*
* If the task is already exiting, don't alarm the sysadmin or kill
*/
if (p->flags & PF_EXITING) {
set_tsk_thread_flag(p, TIF_MEMDIE);
- boost_dying_task_prio(p, mem);
return 0;
}
/*
* If any of p's children has a different mm and is eligible for kill,
- * the one with the highest badness() score is sacrificed for its
+ * 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.
*/
list_for_each_entry(child, &t->children, sibling) {
unsigned int child_points;
+ if (child->mm == p->mm)
+ continue;
/*
* oom_badness() returns 0 if the thread is unkillable
*/
- child_points = oom_badness(child, mem, nodemask,
+ child_points = oom_badness(child, memcg, nodemask,
totalpages);
if (child_points > victim_points) {
victim = child;
}
} while_each_thread(p, t);
- return oom_kill_task(victim, mem);
+ return oom_kill_task(victim);
}
/*
* Determines whether the kernel must panic because of the panic_on_oom sysctl.
*/
static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
- int order)
+ int order, const nodemask_t *nodemask)
{
if (likely(!sysctl_panic_on_oom))
return;
return;
}
read_lock(&tasklist_lock);
- dump_header(NULL, gfp_mask, order, NULL);
+ dump_header(NULL, gfp_mask, order, NULL, nodemask);
read_unlock(&tasklist_lock);
panic("Out of memory: %s panic_on_oom is enabled\n",
sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
}
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
+void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask)
{
unsigned long limit;
unsigned int points = 0;
struct task_struct *p;
- check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0);
- limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT;
+ /*
+ * If current has a pending SIGKILL, 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)) {
+ set_thread_flag(TIF_MEMDIE);
+ return;
+ }
+
+ check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL);
+ limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT;
read_lock(&tasklist_lock);
retry:
- p = select_bad_process(&points, limit, mem, NULL);
+ p = select_bad_process(&points, limit, memcg, NULL);
if (!p || PTR_ERR(p) == -1UL)
goto out;
- if (oom_kill_process(p, gfp_mask, 0, points, limit, mem, NULL,
+ if (oom_kill_process(p, gfp_mask, 0, points, limit, memcg, NULL,
"Memory cgroup out of memory"))
goto retry;
out:
void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *nodemask)
{
+ const nodemask_t *mpol_mask;
struct task_struct *p;
unsigned long totalpages;
unsigned long freed = 0;
unsigned int points;
enum oom_constraint constraint = CONSTRAINT_NONE;
+ int killed = 0;
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
*/
if (fatal_signal_pending(current)) {
set_thread_flag(TIF_MEMDIE);
- boost_dying_task_prio(current, NULL);
return;
}
*/
constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
&totalpages);
- check_panic_on_oom(constraint, gfp_mask, order);
+ mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
+ check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
read_lock(&tasklist_lock);
if (sysctl_oom_kill_allocating_task &&
!oom_unkillable_task(current, NULL, nodemask) &&
- (current->signal->oom_adj != OOM_DISABLE)) {
+ current->mm) {
/*
* oom_kill_process() needs tasklist_lock held. If it returns
* non-zero, current could not be killed so we must fallback to
if (!oom_kill_process(current, gfp_mask, order, 0, totalpages,
NULL, nodemask,
"Out of memory (oom_kill_allocating_task)"))
- return;
+ goto out;
}
retry:
- p = select_bad_process(&points, totalpages, NULL,
- constraint == CONSTRAINT_MEMORY_POLICY ? nodemask :
- NULL);
+ p = select_bad_process(&points, totalpages, NULL, mpol_mask);
if (PTR_ERR(p) == -1UL)
- return;
+ goto out;
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!p) {
- dump_header(NULL, gfp_mask, order, NULL);
+ dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
read_unlock(&tasklist_lock);
panic("Out of memory and no killable processes...\n");
}
if (oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
nodemask, "Out of memory"))
goto retry;
+ killed = 1;
+out:
read_unlock(&tasklist_lock);
/*
* Give "p" a good chance of killing itself before we
* retry to allocate memory unless "p" is current
*/
- if (!test_thread_flag(TIF_MEMDIE))
+ if (killed && !test_thread_flag(TIF_MEMDIE))
schedule_timeout_uninterruptible(1);
}