#include <linux/notifier.h>
int sysctl_panic_on_oom;
+int sysctl_oom_kill_allocating_task;
+static DEFINE_SPINLOCK(zone_scan_mutex);
/* #define DEBUG */
/**
* because p may have allocated or otherwise mapped memory on
* this node before. However it will be less likely.
*/
- if (!cpuset_excl_nodes_overlap(p))
+ if (!cpuset_mems_allowed_intersects(current, p))
points /= 8;
/*
return points;
}
-/*
- * Types of limitations to the nodes from which allocations may occur
- */
-#define CONSTRAINT_NONE 1
-#define CONSTRAINT_MEMORY_POLICY 2
-#define CONSTRAINT_CPUSET 3
-
/*
* Determine the type of allocation constraint.
*/
-static inline int constrained_alloc(struct zonelist *zonelist, gfp_t gfp_mask)
+static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
+ gfp_t gfp_mask)
{
#ifdef CONFIG_NUMA
struct zone **z;
- nodemask_t nodes;
- int node;
-
- nodes_clear(nodes);
- /* node has memory ? */
- for_each_online_node(node)
- if (NODE_DATA(node)->node_present_pages)
- node_set(node, nodes);
+ nodemask_t nodes = node_states[N_HIGH_MEMORY];
for (z = zonelist->zones; *z; z++)
if (cpuset_zone_allowed_softwall(*z, gfp_mask))
if (!p->mm)
continue;
/* skip the init task */
- if (is_init(p))
+ if (is_global_init(p))
continue;
/*
*/
static void __oom_kill_task(struct task_struct *p, int verbose)
{
- if (is_init(p)) {
+ if (is_global_init(p)) {
WARN_ON(1);
printk(KERN_WARNING "tried to kill init!\n");
return;
}
if (verbose)
- printk(KERN_ERR "Killed process %d (%s)\n", p->pid, p->comm);
+ printk(KERN_ERR "Killed process %d (%s)\n",
+ task_pid_nr(p), p->comm);
/*
* 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->time_slice = HZ;
+ p->rt.time_slice = HZ;
set_tsk_thread_flag(p, TIF_MEMDIE);
force_sig(SIGKILL, p);
* to memory reserves though, otherwise we might deplete all memory.
*/
do_each_thread(g, q) {
- if (q->mm == mm && q->tgid != p->tgid)
+ if (q->mm == mm && !same_thread_group(q, p))
force_sig(SIGKILL, q);
} while_each_thread(g, q);
return 0;
}
-static int oom_kill_process(struct task_struct *p, unsigned long points,
- const char *message)
+static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+ unsigned long points, const char *message)
{
struct task_struct *c;
- struct list_head *tsk;
+
+ if (printk_ratelimit()) {
+ printk(KERN_WARNING "%s invoked oom-killer: "
+ "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
+ current->comm, gfp_mask, order, current->oomkilladj);
+ dump_stack();
+ show_mem();
+ }
/*
* If the task is already exiting, don't alarm the sysadmin or kill
}
printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n",
- message, p->pid, p->comm, points);
+ message, task_pid_nr(p), p->comm, points);
/* Try to kill a child first */
- list_for_each(tsk, &p->children) {
- c = list_entry(tsk, struct task_struct, sibling);
+ list_for_each_entry(c, &p->children, sibling) {
if (c->mm == p->mm)
continue;
if (!oom_kill_task(c))
}
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_zone_oom(struct zonelist *zonelist)
+{
+ struct zone **z;
+ int ret = 1;
+
+ z = zonelist->zones;
+
+ spin_lock(&zone_scan_mutex);
+ do {
+ if (zone_is_oom_locked(*z)) {
+ ret = 0;
+ goto out;
+ }
+ } while (*(++z) != NULL);
+
+ /*
+ * Lock each zone in the zonelist under zone_scan_mutex so a parallel
+ * invocation of try_set_zone_oom() doesn't succeed when it shouldn't.
+ */
+ z = zonelist->zones;
+ do {
+ zone_set_flag(*z, ZONE_OOM_LOCKED);
+ } while (*(++z) != NULL);
+out:
+ spin_unlock(&zone_scan_mutex);
+ 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)
+{
+ struct zone **z;
+
+ z = zonelist->zones;
+
+ spin_lock(&zone_scan_mutex);
+ do {
+ zone_clear_flag(*z, ZONE_OOM_LOCKED);
+ } while (*(++z) != NULL);
+ spin_unlock(&zone_scan_mutex);
+}
+
/**
* out_of_memory - kill the "best" process when we run out of memory
*
struct task_struct *p;
unsigned long points = 0;
unsigned long freed = 0;
- int constraint;
+ enum oom_constraint constraint;
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
/* Got some memory back in the last second. */
return;
- if (printk_ratelimit()) {
- printk(KERN_WARNING "%s invoked oom-killer: "
- "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
- current->comm, gfp_mask, order, current->oomkilladj);
- dump_stack();
- show_mem();
- }
-
if (sysctl_panic_on_oom == 2)
panic("out of memory. Compulsory panic_on_oom is selected.\n");
* NUMA) that may require different handling.
*/
constraint = constrained_alloc(zonelist, gfp_mask);
- cpuset_lock();
read_lock(&tasklist_lock);
switch (constraint) {
case CONSTRAINT_MEMORY_POLICY:
- oom_kill_process(current, points,
+ oom_kill_process(current, gfp_mask, order, points,
"No available memory (MPOL_BIND)");
break;
- case CONSTRAINT_CPUSET:
- oom_kill_process(current, points,
- "No available memory in cpuset");
- break;
-
case CONSTRAINT_NONE:
if (sysctl_panic_on_oom)
panic("out of memory. panic_on_oom is selected\n");
+ /* Fall-through */
+ case CONSTRAINT_CPUSET:
+ if (sysctl_oom_kill_allocating_task) {
+ oom_kill_process(current, gfp_mask, order, points,
+ "Out of memory (oom_kill_allocating_task)");
+ break;
+ }
retry:
/*
* Rambo mode: Shoot down a process and hope it solves whatever
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!p) {
read_unlock(&tasklist_lock);
- cpuset_unlock();
panic("Out of memory and no killable processes...\n");
}
- if (oom_kill_process(p, points, "Out of memory"))
+ if (oom_kill_process(p, gfp_mask, order, points,
+ "Out of memory"))
goto retry;
break;
out:
read_unlock(&tasklist_lock);
- cpuset_unlock();
/*
* Give "p" a good chance of killing itself before we