* for goading me into coding this file...
*
* The routines in this file are used to kill a process when
- * we're seriously out of memory. This gets called from kswapd()
- * in linux/mm/vmscan.c when we really run out of memory.
+ * we're seriously out of memory. This gets called from __alloc_pages()
+ * in mm/page_alloc.c when we really run out of memory.
*
* Since we won't call these routines often (on a well-configured
* machine) this file will double as a 'coding guide' and a signpost
* 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 */
/**
- * oom_badness - calculate a numeric value for how bad this task has been
+ * 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
* of least surprise ... (be careful when you change it)
*/
-static int badness(struct task_struct *p)
+unsigned long badness(struct task_struct *p, unsigned long uptime)
{
- int points, cpu_time, run_time, s;
+ unsigned long points, cpu_time, run_time, s;
+ struct mm_struct *mm;
+ struct task_struct *child;
- if (!p->mm)
+ task_lock(p);
+ mm = p->mm;
+ if (!mm) {
+ task_unlock(p);
return 0;
+ }
- if (p->flags & PF_MEMDIE)
- return 0;
/*
* The memory size of the process is the basis for the badness.
*/
- points = p->mm->total_vm;
- /* add vserver badness ;) */
+ points = mm->total_vm;
+
+ /*
+ * add points for context badness
+ */
+
+ points += vx_badness(p, mm);
+
+ /*
+ * After this unlock we can no longer dereference local variable `mm'
+ */
+ task_unlock(p);
+
+ /*
+ * swapoff can easily use up all memory, so kill those first.
+ */
+ if (p->flags & PF_SWAPOFF)
+ return ULONG_MAX;
/*
- * CPU time is in seconds and run time is in minutes. There is no
- * particular reason for this other than that it turned out to work
- * very well in practice.
+ * 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.
*/
- cpu_time = (p->utime + p->stime) >> (SHIFT_HZ + 3);
- run_time = (get_jiffies_64() - p->start_time) >> (SHIFT_HZ + 10);
+ 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);
+ }
+
+ /*
+ * 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.
+ */
+ cpu_time = (cputime_to_jiffies(p->utime) + cputime_to_jiffies(p->stime))
+ >> (SHIFT_HZ + 3);
+
+ if (uptime >= p->start_time.tv_sec)
+ run_time = (uptime - p->start_time.tv_sec) >> 10;
+ else
+ run_time = 0;
s = int_sqrt(cpu_time);
if (s)
*/
if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO))
points /= 4;
+
+ /*
+ * 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 (!cpuset_excl_nodes_overlap(p))
+ points /= 8;
+
+ /*
+ * Adjust the score by oomkilladj.
+ */
+ if (p->oomkilladj) {
+ if (p->oomkilladj > 0)
+ points <<= p->oomkilladj;
+ else
+ points >>= -(p->oomkilladj);
+ }
+
#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;
}
+/*
+ * 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)
+{
+#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);
+
+ for (z = zonelist->zones; *z; z++)
+ if (cpuset_zone_allowed_softwall(*z, gfp_mask))
+ node_clear(zone_to_nid(*z), nodes);
+ else
+ return CONSTRAINT_CPUSET;
+
+ if (!nodes_empty(nodes))
+ return CONSTRAINT_MEMORY_POLICY;
+#endif
+
+ return CONSTRAINT_NONE;
+}
+
/*
* Simple selection loop. We chose the process with the highest
* number of 'points'. We expect the caller will lock the tasklist.
*
* (not docbooked, we don't want this one cluttering up the manual)
*/
-static struct task_struct * select_bad_process(void)
+static struct task_struct *select_bad_process(unsigned long *ppoints)
{
- int maxpoints = 0;
struct task_struct *g, *p;
struct task_struct *chosen = NULL;
+ struct timespec uptime;
+ *ppoints = 0;
+
+ do_posix_clock_monotonic_gettime(&uptime);
+ do_each_thread(g, p) {
+ unsigned long points;
+
+ /*
+ * skip kernel threads and tasks which have already released
+ * their mm.
+ */
+ if (!p->mm)
+ continue;
+ /* 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.
+ *
+ * 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->oomkilladj == OOM_DISABLE)
+ continue;
- do_each_thread(g, p)
- if (p->pid) {
- int points = badness(p);
- if (points > maxpoints) {
- chosen = p;
- maxpoints = points;
- }
- if (p->flags & PF_SWAPOFF)
- return p;
+ points = badness(p, uptime.tv_sec);
+ if (points > *ppoints || !chosen) {
+ chosen = p;
+ *ppoints = points;
}
- while_each_thread(g, p);
+ } 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(task_t *p)
+static void __oom_kill_task(struct task_struct *p, int verbose)
{
- task_lock(p);
- if (!p->mm || p->mm == &init_mm) {
+ if (is_init(p)) {
+ WARN_ON(1);
+ printk(KERN_WARNING "tried to kill init!\n");
+ return;
+ }
+
+ if (!p->mm) {
WARN_ON(1);
printk(KERN_WARNING "tried to kill an mm-less task!\n");
- task_unlock(p);
return;
}
- task_unlock(p);
- printk(KERN_ERR "Out of Memory: Killed process %d (%s).\n", 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
* exit() and clear out its resources quickly...
*/
p->time_slice = HZ;
- p->flags |= PF_MEMALLOC | PF_MEMDIE;
+ set_tsk_thread_flag(p, TIF_MEMDIE);
- /* This process has hardware access, be more careful. */
- if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO)) {
- force_sig(SIGTERM, p);
- } else {
- force_sig(SIGKILL, p);
- }
+ force_sig(SIGKILL, p);
}
-static struct mm_struct *oom_kill_task(task_t *p)
+static int oom_kill_task(struct task_struct *p)
{
- struct mm_struct *mm = get_task_mm(p);
- if (!mm || mm == &init_mm)
- return NULL;
- __oom_kill_task(p);
- return mm;
-}
+ struct mm_struct *mm;
+ struct task_struct *g, *q;
+ mm = p->mm;
-/**
- * oom_kill - kill the "best" process when we run out of memory
- *
- * If we run out of memory, we have the choice between either
- * killing a random task (bad), letting the system crash (worse)
- * OR try to be smart about which process to kill. Note that we
- * don't have to be perfect here, we just have to be good.
- */
-static void oom_kill(void)
-{
- struct mm_struct *mm;
- struct task_struct *g, *p, *q;
-
- read_lock(&tasklist_lock);
-retry:
- p = select_bad_process();
+ /* 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.
+ */
- /* Found nothing?!?! Either we hang forever, or we panic. */
- if (!p) {
- show_free_areas();
- panic("Out of memory and no killable processes...\n");
- }
+ if (mm == NULL)
+ return 1;
+
+ /*
+ * 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);
- mm = oom_kill_task(p);
- if (!mm)
- goto retry;
/*
* 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);
- while_each_thread(g, q);
- if (!p->mm)
- printk(KERN_INFO "Fixed up OOM kill of mm-less task\n");
- read_unlock(&tasklist_lock);
- mmput(mm);
+ 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)
+{
+ struct task_struct *c;
+ struct list_head *tsk;
/*
- * Make kswapd go out of the way, so "p" has a good chance of
- * killing itself before someone else gets the chance to ask
- * for more memory.
+ * 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
*/
- yield();
- return;
+ if (p->flags & PF_EXITING) {
+ __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))
+ return 0;
+ }
+ return oom_kill_task(p);
+}
+
+static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
+
+int register_oom_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&oom_notify_list, nb);
}
+EXPORT_SYMBOL_GPL(register_oom_notifier);
+
+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 - is the system out of memory?
+ * out_of_memory - kill the "best" process when we run out of memory
+ *
+ * If we run out of memory, we have the choice between either
+ * killing a random task (bad), letting the system crash (worse)
+ * OR try to be smart about which process to kill. Note that we
+ * don't have to be perfect here, we just have to be good.
*/
-void out_of_memory(void)
+void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
{
- /*
- * oom_lock protects out_of_memory()'s static variables.
- * It's a global lock; this is not performance-critical.
- */
- static spinlock_t oom_lock = SPIN_LOCK_UNLOCKED;
- static unsigned long first, last, count, lastkill;
- unsigned long now, since;
+ struct task_struct *p;
+ unsigned long points = 0;
+ unsigned long freed = 0;
- /*
- * Enough swap space left? Not OOM.
- */
- if (nr_swap_pages > 0)
+ blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
+ if (freed > 0)
+ /* Got some memory back in the last second. */
return;
- 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.
- */
- last = now;
- if (since > 5*HZ)
- goto reset;
+ 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 we haven't tried for at least one second,
- * we're not really oom.
- */
- since = now - first;
- if (since < HZ)
- goto out_unlock;
+ cpuset_lock();
+ read_lock(&tasklist_lock);
/*
- * If we have gotten only a few failures,
- * we're not really oom.
+ * Check if there were limitations on the allocation (only relevant for
+ * NUMA) that may require different handling.
*/
- if (++count < 10)
- goto out_unlock;
+ switch (constrained_alloc(zonelist, gfp_mask)) {
+ case CONSTRAINT_MEMORY_POLICY:
+ oom_kill_process(current, 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");
+retry:
+ /*
+ * Rambo mode: Shoot down a process and hope it solves whatever
+ * issues we may have.
+ */
+ p = select_bad_process(&points);
+
+ if (PTR_ERR(p) == -1UL)
+ goto out;
+
+ /* 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 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;
+ if (oom_kill_process(p, points, "Out of memory"))
+ goto retry;
- /*
- * Ok, really out of memory. Kill something.
- */
- lastkill = now;
+ break;
+ }
- /* oom_kill() sleeps */
- spin_unlock(&oom_lock);
- oom_kill();
- spin_lock(&oom_lock);
+out:
+ read_unlock(&tasklist_lock);
+ cpuset_unlock();
-reset:
/*
- * We dropped the lock above, so check to be sure the variable
- * first only ever increases to prevent false OOM's.
+ * Give "p" a good chance of killing itself before we
+ * retry to allocate memory unless "p" is current
*/
- if (time_after(now, first))
- first = now;
- count = 0;
-
-out_unlock:
- spin_unlock(&oom_lock);
+ if (!test_thread_flag(TIF_MEMDIE))
+ schedule_timeout_uninterruptible(1);
}
git://git.onelab.eu / linux-2.6.git / blobdiff