int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks;
-static DEFINE_SPINLOCK(zone_scan_mutex);
+static DEFINE_SPINLOCK(zone_scan_lock);
/* #define DEBUG */
+/*
+ * Is all threads of the target process nodes overlap ours?
+ */
+static int has_intersects_mems_allowed(struct task_struct *tsk)
+{
+ struct task_struct *t;
+
+ t = tsk;
+ do {
+ if (cpuset_mems_allowed_intersects(current, t))
+ return 1;
+ t = next_thread(t);
+ } while (t != tsk);
+
+ return 0;
+}
+
/**
* badness - calculate a numeric value for how bad this task has been
* @p: task struct of which task we should calculate
unsigned long badness(struct task_struct *p, unsigned long uptime)
{
- unsigned long points, cpu_time, run_time, s;
+ unsigned long points, cpu_time, run_time;
struct mm_struct *mm;
struct task_struct *child;
+ int oom_adj = p->signal->oom_adj;
+ struct task_cputime task_time;
+ unsigned long utime;
+ unsigned long stime;
+
+ if (oom_adj == OOM_DISABLE)
+ return 0;
task_lock(p);
mm = p->mm;
/*
* swapoff can easily use up all memory, so kill those first.
*/
- if (p->flags & PF_SWAPOFF)
+ if (p->flags & PF_OOM_ORIGIN)
return ULONG_MAX;
/*
* 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);
+ thread_group_cputime(p, &task_time);
+ utime = cputime_to_jiffies(task_time.utime);
+ stime = cputime_to_jiffies(task_time.stime);
+ cpu_time = (utime + 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)
- points /= s;
- s = int_sqrt(int_sqrt(run_time));
- if (s)
- points /= s;
+ if (cpu_time)
+ points /= int_sqrt(cpu_time);
+ if (run_time)
+ points /= int_sqrt(int_sqrt(run_time));
/*
* Niced processes are most likely less important, so double
* because p may have allocated or otherwise mapped memory on
* this node before. However it will be less likely.
*/
- if (!cpuset_mems_allowed_intersects(current, p))
+ if (!has_intersects_mems_allowed(p))
points /= 8;
/*
- * Adjust the score by oomkilladj.
+ * Adjust the score by oom_adj.
*/
- if (p->oomkilladj) {
- if (p->oomkilladj > 0) {
+ if (oom_adj) {
+ if (oom_adj > 0) {
if (!points)
points = 1;
- points <<= p->oomkilladj;
+ points <<= oom_adj;
} else
- points >>= -(p->oomkilladj);
+ points >>= -(oom_adj);
}
#ifdef DEBUG
static struct task_struct *select_bad_process(unsigned long *ppoints,
struct mem_cgroup *mem)
{
- struct task_struct *g, *p;
+ struct task_struct *p;
struct task_struct *chosen = NULL;
struct timespec uptime;
*ppoints = 0;
do_posix_clock_monotonic_gettime(&uptime);
- do_each_thread(g, p) {
+ for_each_process(p) {
unsigned long points;
/*
*ppoints = ULONG_MAX;
}
- if (p->oomkilladj == OOM_DISABLE)
+ if (p->signal->oom_adj == OOM_DISABLE)
continue;
points = badness(p, uptime.tv_sec);
chosen = p;
*ppoints = points;
}
- } while_each_thread(g, p);
+ }
return chosen;
}
printk(KERN_INFO "[ pid ] uid tgid total_vm rss cpu oom_adj "
"name\n");
do_each_thread(g, p) {
- /*
- * total_vm and rss sizes do not exist for tasks with a
- * detached mm so there's no need to report them.
- */
- if (!p->mm)
- continue;
+ struct mm_struct *mm;
+
if (mem && !task_in_mem_cgroup(p, mem))
continue;
if (!thread_group_leader(p))
continue;
task_lock(p);
+ mm = p->mm;
+ if (!mm) {
+ /*
+ * total_vm and rss sizes do not exist for tasks with no
+ * mm so there's no need to report them; they can't be
+ * oom killed anyway.
+ */
+ task_unlock(p);
+ continue;
+ }
printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n",
- p->pid, __task_cred(p)->uid, p->tgid,
- p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p),
- p->oomkilladj, p->comm);
+ p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
+ get_mm_rss(mm), (int)task_cpu(p), p->signal->oom_adj,
+ p->comm);
task_unlock(p);
} while_each_thread(g, p);
}
+static void dump_header(gfp_t gfp_mask, int order, struct mem_cgroup *mem)
+{
+ pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
+ "oom_adj=%d\n",
+ current->comm, gfp_mask, order, current->signal->oom_adj);
+ task_lock(current);
+ cpuset_print_task_mems_allowed(current);
+ task_unlock(current);
+ dump_stack();
+ mem_cgroup_print_oom_info(mem, current);
+ show_mem();
+ if (sysctl_oom_dump_tasks)
+ dump_tasks(mem);
+}
+
/*
* 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
static int oom_kill_task(struct task_struct *p)
{
- struct mm_struct *mm;
- struct task_struct *g, *q;
-
- mm = p->mm;
-
/* 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.
* change to NULL at any time since we do not hold task_lock(p).
* However, this is of no concern to us.
*/
-
- if (mm == NULL)
+ if (!p->mm || p->signal->oom_adj == OOM_DISABLE)
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);
- /*
- * kill all processes that share the ->mm (i.e. all threads),
- * 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) {
- if (q->mm == mm && !same_thread_group(q, p))
- force_sig(SIGKILL, q);
- } while_each_thread(g, q);
-
return 0;
}
{
struct task_struct *c;
- 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_oom_dump_tasks)
- dump_tasks(mem);
- }
+ if (printk_ratelimit())
+ dump_header(gfp_mask, order, mem);
/*
* If the task is already exiting, don't alarm the sysadmin or kill
unsigned long points = 0;
struct task_struct *p;
- cgroup_lock();
read_lock(&tasklist_lock);
retry:
p = select_bad_process(&points, mem);
goto retry;
out:
read_unlock(&tasklist_lock);
- cgroup_unlock();
}
#endif
struct zone *zone;
int ret = 1;
- spin_lock(&zone_scan_mutex);
+ spin_lock(&zone_scan_lock);
for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
if (zone_is_oom_locked(zone)) {
ret = 0;
for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
/*
- * Lock each zone in the zonelist under zone_scan_mutex so a
+ * Lock each zone in the zonelist under zone_scan_lock so a
* parallel invocation of try_set_zone_oom() doesn't succeed
* when it shouldn't.
*/
}
out:
- spin_unlock(&zone_scan_mutex);
+ spin_unlock(&zone_scan_lock);
return ret;
}
struct zoneref *z;
struct zone *zone;
- spin_lock(&zone_scan_mutex);
+ spin_lock(&zone_scan_lock);
for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
zone_clear_flag(zone, ZONE_OOM_LOCKED);
}
- spin_unlock(&zone_scan_mutex);
+ spin_unlock(&zone_scan_lock);
}
/*
*/
static void __out_of_memory(gfp_t gfp_mask, int order)
{
- if (sysctl_oom_kill_allocating_task) {
- oom_kill_process(current, gfp_mask, order, 0, NULL,
- "Out of memory (oom_kill_allocating_task)");
-
- } else {
- unsigned long points;
- struct task_struct *p;
-
-retry:
- /*
- * Rambo mode: Shoot down a process and hope it solves whatever
- * issues we may have.
- */
- p = select_bad_process(&points, NULL);
+ struct task_struct *p;
+ unsigned long points;
- if (PTR_ERR(p) == -1UL)
+ 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);
- /* Found nothing?!?! Either we hang forever, or we panic. */
- if (!p) {
- read_unlock(&tasklist_lock);
- panic("Out of memory and no killable processes...\n");
- }
+ if (PTR_ERR(p) == -1UL)
+ return;
- if (oom_kill_process(p, gfp_mask, order, points, NULL,
- "Out of memory"))
- goto retry;
+ /* Found nothing?!?! Either we hang forever, or we panic. */
+ if (!p) {
+ read_unlock(&tasklist_lock);
+ dump_header(gfp_mask, order, NULL);
+ panic("Out of memory and no killable processes...\n");
}
+
+ if (oom_kill_process(p, gfp_mask, order, points, NULL,
+ "Out of memory"))
+ goto retry;
}
/*
/* Got some memory back in the last second. */
return;
+ /*
+ * If this is from memcg, oom-killer is already invoked.
+ * and not worth to go system-wide-oom.
+ */
+ if (mem_cgroup_oom_called(current))
+ goto rest_and_return;
+
if (sysctl_panic_on_oom)
panic("out of memory from page fault. panic_on_oom is selected.\n");
* Give "p" a good chance of killing itself before we
* retry to allocate memory.
*/
+rest_and_return:
if (!test_thread_flag(TIF_MEMDIE))
schedule_timeout_uninterruptible(1);
}
/* Got some memory back in the last second. */
return;
- if (sysctl_panic_on_oom == 2)
+ if (sysctl_panic_on_oom == 2) {
+ dump_header(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
break;
case CONSTRAINT_NONE:
- if (sysctl_panic_on_oom)
+ if (sysctl_panic_on_oom) {
+ dump_header(gfp_mask, order, NULL);
panic("out of memory. panic_on_oom is selected\n");
+ }
/* Fall-through */
case CONSTRAINT_CPUSET:
__out_of_memory(gfp_mask, order);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff