return NULL;
}
+/* 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)
+{
+ if (is_global_init(p))
+ return true;
+ if (p->flags & PF_KTHREAD)
+ return true;
+
+ /* When mem_cgroup_out_of_memory() and p is not member of the group */
+ if (mem && !task_in_mem_cgroup(p, mem))
+ return true;
+
+ /* p may not have freeable memory in nodemask */
+ if (!has_intersects_mems_allowed(p, nodemask))
+ return true;
+
+ return false;
+}
+
/**
* badness - calculate a numeric value for how bad this task has been
* @p: task struct of which task we should calculate
* algorithm has been meticulously tuned to meet the principle
* of least surprise ... (be careful when you change it)
*/
-
-unsigned long badness(struct task_struct *p, unsigned long uptime)
+unsigned long badness(struct task_struct *p, struct mem_cgroup *mem,
+ const nodemask_t *nodemask, unsigned long uptime)
{
unsigned long points, cpu_time, run_time;
struct task_struct *child;
unsigned long utime;
unsigned long stime;
+ if (oom_unkillable_task(p, mem, nodemask))
+ return 0;
if (oom_adj == OOM_DISABLE)
return 0;
* (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, enum oom_constraint constraint,
- const nodemask_t *mask)
+ struct mem_cgroup *mem, const nodemask_t *nodemask)
{
struct task_struct *p;
struct task_struct *chosen = NULL;
for_each_process(p) {
unsigned long points;
- /* skip the init task and kthreads */
- if (is_global_init(p) || (p->flags & PF_KTHREAD))
- continue;
- if (mem && !task_in_mem_cgroup(p, mem))
- continue;
- if (!has_intersects_mems_allowed(p,
- constraint == CONSTRAINT_MEMORY_POLICY ? mask :
- NULL))
+ if (oom_unkillable_task(p, mem, nodemask))
continue;
/*
*ppoints = ULONG_MAX;
}
- if (p->signal->oom_adj == OOM_DISABLE)
- continue;
-
- points = badness(p, uptime.tv_sec);
+ points = badness(p, mem, nodemask, uptime.tv_sec);
if (points > *ppoints || !chosen) {
chosen = p;
*ppoints = points;
}
#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.
- */
-static void __oom_kill_task(struct task_struct *p, int verbose)
+static int oom_kill_task(struct task_struct *p)
{
- if (is_global_init(p)) {
- WARN_ON(1);
- printk(KERN_WARNING "tried to kill init!\n");
- return;
- }
-
p = find_lock_task_mm(p);
- if (!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, MM_ANONPAGES)),
- K(get_mm_counter(p->mm, MM_FILEPAGES)));
+ if (!p) {
+ task_unlock(p);
+ return 1;
+ }
+ 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);
- /*
- * 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...
- */
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);
-
return 0;
}
+#undef K
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)
+ nodemask_t *nodemask, const char *message)
{
struct task_struct *victim = p;
struct task_struct *child;
if (child->mm == p->mm)
continue;
- if (mem && !task_in_mem_cgroup(child, mem))
- continue;
/* badness() returns 0 if the thread is unkillable */
- child_points = badness(child, uptime.tv_sec);
+ child_points = badness(child, mem, nodemask,
+ uptime.tv_sec);
if (child_points > victim_points) {
victim = child;
victim_points = child_points;
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)
+{
+ 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;
+ }
+ read_lock(&tasklist_lock);
+ dump_header(NULL, gfp_mask, order, NULL);
+ 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)
{
unsigned long points = 0;
struct task_struct *p;
- if (sysctl_panic_on_oom == 2)
- panic("out of memory(memcg). panic_on_oom is selected.\n");
+ check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0);
read_lock(&tasklist_lock);
retry:
- p = select_bad_process(&points, mem, CONSTRAINT_NONE, NULL);
+ p = select_bad_process(&points, mem, NULL);
if (!p || PTR_ERR(p) == -1UL)
goto out;
- if (oom_kill_process(p, gfp_mask, 0, points, mem,
+ if (oom_kill_process(p, gfp_mask, 0, points, mem, NULL,
"Memory cgroup out of memory"))
goto retry;
out:
* 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;
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);
}
/*
- * Must be called with tasklist_lock held for read.
+ * Try to acquire the oom killer lock for all system zones. Returns zero if a
+ * parallel oom killing is taking place, otherwise locks all zones and returns
+ * non-zero.
*/
-static void __out_of_memory(gfp_t gfp_mask, int order,
- enum oom_constraint constraint, const nodemask_t *mask)
+static int try_set_system_oom(void)
{
- 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, constraint, mask);
-
- 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");
- }
+ struct zone *zone;
+ int ret = 1;
- if (oom_kill_process(p, gfp_mask, order, points, NULL,
- "Out of memory"))
- goto retry;
+ spin_lock(&zone_scan_lock);
+ for_each_populated_zone(zone)
+ if (zone_is_oom_locked(zone)) {
+ ret = 0;
+ goto out;
+ }
+ for_each_populated_zone(zone)
+ zone_set_flag(zone, ZONE_OOM_LOCKED);
+out:
+ spin_unlock(&zone_scan_lock);
+ return ret;
}
/*
- * pagefault handler calls into here because it is out of memory but
- * doesn't know exactly how or why.
+ * Clears ZONE_OOM_LOCKED for all system zones so that failed allocation
+ * attempts or page faults may now recall the oom killer, if necessary.
*/
-void pagefault_out_of_memory(void)
+static void clear_system_oom(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 (sysctl_panic_on_oom)
- panic("out of memory from page fault. panic_on_oom is selected.\n");
-
- read_lock(&tasklist_lock);
- /* unknown gfp_mask and order */
- __out_of_memory(0, 0, CONSTRAINT_NONE, NULL);
- read_unlock(&tasklist_lock);
+ struct zone *zone;
- /*
- * Give "p" a good chance of killing itself before we
- * retry to allocate memory.
- */
- if (!test_thread_flag(TIF_MEMDIE))
- schedule_timeout_uninterruptible(1);
+ spin_lock(&zone_scan_lock);
+ for_each_populated_zone(zone)
+ zone_clear_flag(zone, ZONE_OOM_LOCKED);
+ spin_unlock(&zone_scan_lock);
}
/**
void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *nodemask)
{
+ struct task_struct *p;
unsigned long freed = 0;
- enum oom_constraint constraint;
+ unsigned long points;
+ enum oom_constraint constraint = CONSTRAINT_NONE;
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
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");
- }
-
/*
* Check if there were limitations on the allocation (only relevant for
* NUMA) that may require different handling.
*/
- constraint = constrained_alloc(zonelist, gfp_mask, nodemask);
+ if (zonelist)
+ constraint = constrained_alloc(zonelist, gfp_mask, nodemask);
+ check_panic_on_oom(constraint, gfp_mask, order);
+
read_lock(&tasklist_lock);
- if (unlikely(sysctl_panic_on_oom)) {
+ if (sysctl_oom_kill_allocating_task &&
+ !oom_unkillable_task(current, NULL, nodemask) &&
+ (current->signal->oom_adj != OOM_DISABLE)) {
/*
- * panic_on_oom only affects CONSTRAINT_NONE, the kernel
- * should not panic for cpuset or mempolicy induced memory
- * failures.
+ * oom_kill_process() needs tasklist_lock held. If it returns
+ * non-zero, current could not be killed so we must fallback to
+ * the tasklist scan.
*/
- if (constraint == CONSTRAINT_NONE) {
- dump_header(NULL, gfp_mask, order, NULL);
- read_unlock(&tasklist_lock);
- panic("Out of memory: panic_on_oom is enabled\n");
- }
+ if (!oom_kill_process(current, gfp_mask, order, 0, NULL,
+ nodemask,
+ "Out of memory (oom_kill_allocating_task)"))
+ return;
+ }
+
+retry:
+ p = select_bad_process(&points, NULL,
+ constraint == CONSTRAINT_MEMORY_POLICY ? nodemask :
+ NULL);
+ if (PTR_ERR(p) == -1UL)
+ return;
+
+ /* Found nothing?!?! Either we hang forever, or we panic. */
+ if (!p) {
+ dump_header(NULL, gfp_mask, order, NULL);
+ read_unlock(&tasklist_lock);
+ panic("Out of memory and no killable processes...\n");
}
- __out_of_memory(gfp_mask, order, constraint, nodemask);
+
+ if (oom_kill_process(p, gfp_mask, order, points, NULL, nodemask,
+ "Out of memory"))
+ goto retry;
read_unlock(&tasklist_lock);
/*
if (!test_thread_flag(TIF_MEMDIE))
schedule_timeout_uninterruptible(1);
}
+
+/*
+ * The pagefault handler calls here because it is out of memory, so kill a
+ * memory-hogging task. If a populated zone has ZONE_OOM_LOCKED set, a parallel
+ * oom killing is already in progress so do nothing. If a task is found with
+ * TIF_MEMDIE set, it has been killed so do nothing and allow it to exit.
+ */
+void pagefault_out_of_memory(void)
+{
+ if (try_set_system_oom()) {
+ out_of_memory(NULL, 0, 0, NULL);
+ clear_system_oom();
+ }
+ if (!test_thread_flag(TIF_MEMDIE))
+ schedule_timeout_uninterruptible(1);
+}