* 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>
return 0;
}
- /*
- * swapoff can easily use up all memory, so kill those first.
- */
- if (p->flags & PF_SWAPOFF)
- return ULONG_MAX;
-
/*
* The memory size of the process is the basis for the badness.
*/
*/
task_unlock(p);
+ /*
+ * 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
* a good choice. We add half the vmsize of the children if they
* Adjust the score by oomkilladj.
*/
if (p->oomkilladj) {
- if (p->oomkilladj > 0)
+ if (p->oomkilladj > 0) {
+ if (!points)
+ points = 1;
points <<= p->oomkilladj;
- else
+ } else
points >>= -(p->oomkilladj);
}
{
#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))
+ if (cpuset_zone_allowed_softwall(*z, gfp_mask))
node_clear(zone_to_nid(*z), nodes);
else
return CONSTRAINT_CPUSET;
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.
*/
- if ((p->flags & PF_EXITING) && p == current) {
+ if (p->flags & PF_EXITING) {
+ if (p != current)
+ return ERR_PTR(-1UL);
+
chosen = p;
*ppoints = ULONG_MAX;
- break;
}
- if ((p->flags & PF_EXITING) ||
- test_tsk_thread_flag(p, TIF_MEMDIE))
- return ERR_PTR(-1UL);
if (p->oomkilladj == OOM_DISABLE)
continue;
* 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 (is_init(p)) {
WARN_ON(1);
return;
}
- if (message) {
- printk(KERN_ERR "%s: Killed process %d (%s).\n",
- message, p->pid, p->comm);
- }
+ if (verbose)
+ printk(KERN_ERR "Killed process %d (%s)\n", p->pid, 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;
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 "Out of Memory: Kill process %d (%s) score %li"
- " and children.\n", p->pid, p->comm, points);
+ printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n",
+ message, p->pid, 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);
}
static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
struct task_struct *p;
unsigned long points = 0;
unsigned long freed = 0;
+ int constraint;
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
show_mem();
}
- cpuset_lock();
- read_lock(&tasklist_lock);
+ if (sysctl_panic_on_oom == 2)
+ 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.
*/
- switch (constrained_alloc(zonelist, gfp_mask)) {
+ constraint = constrained_alloc(zonelist, gfp_mask);
+ cpuset_lock();
+ read_lock(&tasklist_lock);
+
+ switch (constraint) {
case CONSTRAINT_MEMORY_POLICY:
oom_kill_process(current, points,
"No available memory (MPOL_BIND)");