#include <linux/oom.h>
#include <linux/mm.h>
#include <linux/err.h>
+#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/swap.h>
#include <linux/timex.h>
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 points, cpu_time, run_time;
struct mm_struct *mm;
struct task_struct *child;
- int oom_adj;
+ 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;
task_unlock(p);
return 0;
}
- oom_adj = mm->oom_adj;
/*
* The memory size of the process is the basis for the badness.
/*
* 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;
* 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;
/*
/*
* Determine the type of allocation constraint.
*/
-static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
- gfp_t gfp_mask)
-{
#ifdef CONFIG_NUMA
+static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
+ gfp_t gfp_mask, nodemask_t *nodemask)
+{
struct zone *zone;
struct zoneref *z;
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
- nodemask_t nodes = node_states[N_HIGH_MEMORY];
- for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
- if (cpuset_zone_allowed_softwall(zone, gfp_mask))
- node_clear(zone_to_nid(zone), nodes);
- else
- return CONSTRAINT_CPUSET;
+ /*
+ * Reach here only when __GFP_NOFAIL is used. So, we should avoid
+ * to kill current.We have to random task kill in this case.
+ * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
+ */
+ if (gfp_mask & __GFP_THISNODE)
+ return CONSTRAINT_NONE;
- if (!nodes_empty(nodes))
+ /*
+ * The nodemask here is a nodemask passed to alloc_pages(). Now,
+ * cpuset doesn't use this nodemask for its hardwall/softwall/hierarchy
+ * feature. mempolicy is an only user of nodemask here.
+ * check mempolicy's nodemask contains all N_HIGH_MEMORY
+ */
+ if (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask))
return CONSTRAINT_MEMORY_POLICY;
-#endif
+ /* Check this allocation failure is caused by cpuset's wall function */
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ high_zoneidx, nodemask)
+ if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
+ return CONSTRAINT_CPUSET;
+
+ return CONSTRAINT_NONE;
+}
+#else
+static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
+ gfp_t gfp_mask, nodemask_t *nodemask)
+{
return CONSTRAINT_NONE;
}
+#endif
/*
* Simple selection loop. We chose the process with the highest
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;
}
- task_lock(p);
- if (p->mm && p->mm->oom_adj == OOM_DISABLE) {
- task_unlock(p);
+ if (p->signal->oom_adj == OOM_DISABLE)
continue;
- }
- task_unlock(p);
points = badness(p, uptime.tv_sec);
if (points > *ppoints || !chosen) {
chosen = p;
*ppoints = points;
}
- } while_each_thread(g, p);
+ }
return chosen;
}
}
printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n",
p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
- get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm);
+ 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(struct task_struct *p, 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, p);
+ show_mem();
+ if (sysctl_oom_dump_tasks)
+ dump_tasks(mem);
+}
+
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
/*
* 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
return;
}
+ task_lock(p);
if (!p->mm) {
WARN_ON(1);
- printk(KERN_WARNING "tried to kill an mm-less task!\n");
+ printk(KERN_WARNING "tried to kill an mm-less task %d (%s)!\n",
+ task_pid_nr(p), p->comm);
+ task_unlock(p);
return;
}
if (verbose)
- printk(KERN_ERR "Killed process %d (%s)\n",
- task_pid_nr(p), p->comm);
+ printk(KERN_ERR "Killed process %d (%s) "
+ "vsz:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
+ task_pid_nr(p), p->comm,
+ K(p->mm->total_vm),
+ K(get_mm_counter(p->mm, MM_ANONPAGES)),
+ K(get_mm_counter(p->mm, MM_FILEPAGES)));
+ task_unlock(p);
/*
* We give our sacrificial lamb high priority and access to
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) {
- task_lock(q);
- if (q->mm == mm && q->mm && q->mm->oom_adj == OOM_DISABLE) {
- task_unlock(q);
- return 1;
- }
- task_unlock(q);
- } 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()) {
- task_lock(current);
- printk(KERN_WARNING "%s invoked oom-killer: "
- "gfp_mask=0x%x, order=%d, oom_adj=%d\n",
- current->comm, gfp_mask, order,
- current->mm ? current->mm->oom_adj : OOM_DISABLE);
- 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);
- }
+ if (printk_ratelimit())
+ dump_header(p, gfp_mask, order, mem);
/*
* If the task is already exiting, don't alarm the sysadmin or kill
list_for_each_entry(c, &p->children, sibling) {
if (c->mm == p->mm)
continue;
+ if (mem && !task_in_mem_cgroup(c, mem))
+ continue;
if (!oom_kill_task(c))
return 0;
}
unsigned long points = 0;
struct task_struct *p;
+ if (sysctl_panic_on_oom == 2)
+ panic("out of memory(memcg). panic_on_oom is selected.\n");
read_lock(&tasklist_lock);
retry:
p = select_bad_process(&points, mem);
- if (PTR_ERR(p) == -1UL)
+ if (!p || PTR_ERR(p) == -1UL)
goto out;
- if (!p)
- p = current;
-
if (oom_kill_process(p, gfp_mask, 0, points, mem,
"Memory cgroup out of memory"))
goto retry;
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!p) {
read_unlock(&tasklist_lock);
+ dump_header(NULL, gfp_mask, order, NULL);
panic("Out of memory and no killable processes...\n");
}
/* 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);
}
* 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(struct zonelist *zonelist, gfp_t gfp_mask, int order)
+void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+ int order, nodemask_t *nodemask)
{
unsigned long freed = 0;
enum oom_constraint constraint;
/* Got some memory back in the last second. */
return;
- if (sysctl_panic_on_oom == 2)
+ if (sysctl_panic_on_oom == 2) {
+ dump_header(NULL, 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
* NUMA) that may require different handling.
*/
- constraint = constrained_alloc(zonelist, gfp_mask);
+ constraint = constrained_alloc(zonelist, gfp_mask, nodemask);
read_lock(&tasklist_lock);
switch (constraint) {
break;
case CONSTRAINT_NONE:
- if (sysctl_panic_on_oom)
+ if (sysctl_panic_on_oom) {
+ dump_header(NULL, 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);