* kernel subsystems and hints as to where to find out what things do.
*/
+#include <linux/oom.h>
#include <linux/mm.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/notifier.h>
+#include <linux/vs_memory.h>
int sysctl_panic_on_oom;
/* #define DEBUG */
}
/*
- * swapoff can easily use up all memory, so kill those first.
+ * The memory size of the process is the basis for the badness.
*/
- if (p->flags & PF_SWAPOFF)
- return ULONG_MAX;
+ points = mm->total_vm;
/*
- * The memory size of the process is the basis for the badness.
+ * add points for context badness
*/
- points = mm->total_vm;
+
+ points += vx_badness(p, mm);
/*
* After this unlock we can no longer dereference local variable `mm'
*/
task_unlock(p);
- /* FIXME: add vserver badness ;) */
+ /*
+ * swapoff can easily use up all memory, so kill those first.
+ */
+ if (p->flags & PF_SWAPOFF)
+ return ULONG_MAX;
/*
* Processes which fork a lot of child processes are likely
}
#ifdef DEBUG
- printk(KERN_DEBUG "OOMkill: task %d (%s) got %d points\n",
- p->pid, p->comm, points);
+ printk(KERN_DEBUG "OOMkill: task %d:#%u (%s) got %d points\n",
+ p->pid, p->xid, p->comm, points);
#endif
return points;
}
{
#ifdef CONFIG_NUMA
struct zone **z;
- nodemask_t nodes = node_online_map;
+ 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);
for (z = zonelist->zones; *z; z++)
- if (cpuset_zone_allowed(*z, gfp_mask))
- node_clear((*z)->zone_pgdat->node_id,
- nodes);
+ if (cpuset_zone_allowed_softwall(*z, gfp_mask))
+ node_clear(zone_to_nid(*z), nodes);
else
return CONSTRAINT_CPUSET;
do_posix_clock_monotonic_gettime(&uptime);
do_each_thread(g, p) {
unsigned long points;
- int releasing;
- /* skip kernel threads */
+ /*
+ * skip kernel threads and tasks which have already released
+ * their mm.
+ */
if (!p->mm)
continue;
-
- /* skip the init task with pid == 1 */
- if (p->pid == 1)
+ /* skip the init task */
+ if (is_init(p))
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.
* 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 OOM deadlock.
+ * Otherwise we could get an easy OOM deadlock.
*/
- releasing = test_tsk_thread_flag(p, TIF_MEMDIE) ||
- p->flags & PF_EXITING;
- if (releasing) {
- /* PF_DEAD tasks have already released their mm */
- if (p->flags & PF_DEAD)
- continue;
- if (p->flags & PF_EXITING && p == current) {
- chosen = p;
- *ppoints = ULONG_MAX;
- break;
- }
- return ERR_PTR(-1UL);
+ if (p->flags & PF_EXITING) {
+ if (p != current)
+ return ERR_PTR(-1UL);
+
+ chosen = p;
+ *ppoints = ULONG_MAX;
}
+
if (p->oomkilladj == OOM_DISABLE)
continue;
*ppoints = points;
}
} while_each_thread(g, p);
+
return chosen;
}
/**
- * We must be careful though to never send SIGKILL a process with
- * CAP_SYS_RAW_IO set, send SIGTERM instead (but it's unlikely that
- * we select a process with CAP_SYS_RAW_IO set).
+ * 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, const char *message)
+static void __oom_kill_task(struct task_struct *p, int verbose)
{
- if (p->pid == 1) {
+ if (is_init(p)) {
WARN_ON(1);
printk(KERN_WARNING "tried to kill init!\n");
return;
}
- task_lock(p);
- if (!p->mm || p->mm == &init_mm) {
+ if (!p->mm) {
WARN_ON(1);
printk(KERN_WARNING "tried to kill an mm-less task!\n");
- task_unlock(p);
return;
}
- task_unlock(p);
- if (message)
- printk(KERN_ERR "%s: Killed process %d (%s).\n",
- message, p->pid, p->comm);
+
+ if (verbose)
+ printk(KERN_ERR "Killed process %d:#%u (%s)\n",
+ p->pid, p->xid, p->comm);
/*
* We give our sacrificial lamb high priority and access to
force_sig(SIGKILL, p);
}
-static int oom_kill_task(struct task_struct *p, const char *message)
+static int oom_kill_task(struct task_struct *p)
{
struct mm_struct *mm;
struct task_struct *g, *q;
* However, this is of no concern to us.
*/
- if (mm == NULL || mm == &init_mm)
+ if (mm == NULL)
return 1;
- __oom_kill_task(p, message);
+ /*
+ * Don't kill the process if any threads are set to OOM_DISABLE
+ */
+ do_each_thread(g, q) {
+ if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
+ return 1;
+ } while_each_thread(g, q);
+
+ __oom_kill_task(p, 1);
+
/*
* kill all processes that share the ->mm (i.e. all threads),
- * but are in a different thread group
+ * but are in a different thread group. Don't let them have access
+ * to memory reserves though, otherwise we might deplete all memory.
*/
- do_each_thread(g, q)
+ do_each_thread(g, q) {
if (q->mm == mm && q->tgid != p->tgid)
- __oom_kill_task(q, message);
- while_each_thread(g, q);
+ force_sig(SIGKILL, q);
+ } while_each_thread(g, q);
return 0;
}
* its children or threads, just set TIF_MEMDIE so it can die quickly
*/
if (p->flags & PF_EXITING) {
- __oom_kill_task(p, NULL);
+ __oom_kill_task(p, 0);
return 0;
}
+ printk(KERN_ERR "%s: kill process %d:#%u (%s) score %li or a child\n",
+ message, p->pid, p->xid, p->comm, points);
+
/* Try to kill a child first */
list_for_each(tsk, &p->children) {
c = list_entry(tsk, struct task_struct, sibling);
if (c->mm == p->mm)
continue;
- if (!oom_kill_task(c, message))
+ if (!oom_kill_task(c))
return 0;
}
- return oom_kill_task(p, message);
+ return oom_kill_task(p);
}
-int should_oom_kill(void)
-{
- static spinlock_t oom_lock = SPIN_LOCK_UNLOCKED;
- static unsigned long first, last, count, lastkill;
- unsigned long now, since;
- int ret = 0;
-
- spin_lock(&oom_lock);
- now = jiffies;
- since = now - last;
- last = now;
-
- /*
- * If it's been a long time since last failure,
- * we're not oom.
- */
- if (since > 5*HZ)
- goto reset;
-
- /*
- * If we haven't tried for at least one second,
- * we're not really oom.
- */
- since = now - first;
- if (since < HZ)
- goto out_unlock;
-
- /*
- * If we have gotten only a few failures,
- * we're not really oom.
- */
- if (++count < 10)
- goto out_unlock;
+static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
- /*
- * If we just killed a process, wait a while
- * to give that task a chance to exit. This
- * avoids killing multiple processes needlessly.
- */
- since = now - lastkill;
- if (since < HZ*5)
- goto out_unlock;
-
- /*
- * Ok, really out of memory. Kill something.
- */
- lastkill = now;
- ret = 1;
-
-reset:
-/*
- * We dropped the lock above, so check to be sure the variable
- * first only ever increases to prevent false OOM's.
- */
- if (time_after(now, first))
- first = now;
- count = 0;
+int register_oom_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_oom_notifier);
-out_unlock:
- spin_unlock(&oom_lock);
- return ret;
+int unregister_oom_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&oom_notify_list, nb);
}
+EXPORT_SYMBOL_GPL(unregister_oom_notifier);
/**
* 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;
+
+ 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);
+ "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
+ current->comm, gfp_mask, order, current->oomkilladj);
dump_stack();
show_mem();
}
- if (!should_oom_kill())
- return;
-
cpuset_lock();
read_lock(&tasklist_lock);
git://git.onelab.eu / linux-2.6.git / blobdiff