X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Foom_kill.c;h=042e6436c3ee8db6548a687dc289a207f2c43fd6;hb=af57d238aa2107e1b45d8dacad6e50db938f0567;hp=949eba1d5ba3c23755ad2867797c18f4d78c6633;hpb=9827b781f20828e5ceb911b879f268f78fe90815;p=linux-2.6

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 949eba1d5b..042e6436c3 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -46,15 +46,25 @@
 unsigned long badness(struct task_struct *p, unsigned long uptime)
 {
 	unsigned long points, cpu_time, run_time, s;
-	struct list_head *tsk;
+	struct mm_struct *mm;
+	struct task_struct *child;
 
-	if (!p->mm)
+	task_lock(p);
+	mm = p->mm;
+	if (!mm) {
+		task_unlock(p);
 		return 0;
+	}
 
 	/*
 	 * The memory size of the process is the basis for the badness.
 	 */
-	points = p->mm->total_vm;
+	points = mm->total_vm;
+
+	/*
+	 * After this unlock we can no longer dereference local variable `mm'
+	 */
+	task_unlock(p);
 
 	/*
 	 * Processes which fork a lot of child processes are likely
@@ -64,11 +74,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * child is eating the vast majority of memory, adding only half
 	 * to the parents will make the child our kill candidate of choice.
 	 */
-	list_for_each(tsk, &p->children) {
-		struct task_struct *chld;
-		chld = list_entry(tsk, struct task_struct, sibling);
-		if (chld->mm != p->mm && chld->mm)
-			points += chld->mm->total_vm/2 + 1;
+	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);
 	}
 
 	/*
@@ -132,6 +142,36 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	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 = node_online_map;
+
+	for (z = zonelist->zones; *z; z++)
+		if (cpuset_zone_allowed(*z, gfp_mask))
+			node_clear((*z)->zone_pgdat->node_id,
+					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.
@@ -184,7 +224,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
  * CAP_SYS_RAW_IO set, send SIGTERM instead (but 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(task_t *p, const char *message)
 {
 	if (p->pid == 1) {
 		WARN_ON(1);
@@ -200,8 +240,8 @@ static void __oom_kill_task(task_t *p)
 		return;
 	}
 	task_unlock(p);
-	printk(KERN_ERR "Out of Memory: Killed process %d (%s).\n",
-							p->pid, p->comm);
+	printk(KERN_ERR "%s: Killed process %d (%s).\n",
+				message, p->pid, p->comm);
 
 	/*
 	 * We give our sacrificial lamb high priority and access to
@@ -214,35 +254,41 @@ static void __oom_kill_task(task_t *p)
 	force_sig(SIGKILL, p);
 }
 
-static struct mm_struct *oom_kill_task(task_t *p)
+static int oom_kill_task(task_t *p, const char *message)
 {
-	struct mm_struct *mm = get_task_mm(p);
+	struct mm_struct *mm;
 	task_t * g, * q;
 
-	if (!mm)
-		return NULL;
-	if (mm == &init_mm) {
-		mmput(mm);
-		return NULL;
-	}
+	mm = p->mm;
 
-	__oom_kill_task(p);
+	/* 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.
+	 */
+
+	if (mm == NULL || mm == &init_mm)
+		return 1;
+
+	__oom_kill_task(p, message);
 	/*
 	 * kill all processes that share the ->mm (i.e. all threads),
 	 * but are in a different thread group
 	 */
 	do_each_thread(g, q)
 		if (q->mm == mm && q->tgid != p->tgid)
-			__oom_kill_task(q);
+			__oom_kill_task(q, message);
 	while_each_thread(g, q);
 
-	return mm;
+	return 0;
 }
 
-static struct mm_struct *oom_kill_process(struct task_struct *p,
-					  unsigned long points)
+static int oom_kill_process(struct task_struct *p, unsigned long points,
+		const char *message)
 {
- 	struct mm_struct *mm;
 	struct task_struct *c;
 	struct list_head *tsk;
 
@@ -253,11 +299,10 @@ static struct mm_struct *oom_kill_process(struct task_struct *p,
 		c = list_entry(tsk, struct task_struct, sibling);
 		if (c->mm == p->mm)
 			continue;
-		mm = oom_kill_task(c);
-		if (mm)
-			return mm;
+		if (!oom_kill_task(c, message))
+			return 0;
 	}
-	return oom_kill_task(p);
+	return oom_kill_task(p, message);
 }
 
 /**
@@ -268,11 +313,10 @@ static struct mm_struct *oom_kill_process(struct task_struct *p,
  * 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(gfp_t gfp_mask, int order)
+void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 {
-	struct mm_struct *mm = NULL;
-	task_t * p;
-	unsigned long points;
+	task_t *p;
+	unsigned long points = 0;
 
 	if (printk_ratelimit()) {
 		printk("oom-killer: gfp_mask=0x%x, order=%d\n",
@@ -283,33 +327,54 @@ void out_of_memory(gfp_t gfp_mask, int order)
 
 	cpuset_lock();
 	read_lock(&tasklist_lock);
+
+	/*
+	 * Check if there were limitations on the allocation (only relevant for
+	 * NUMA) that may require different handling.
+	 */
+	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:
 retry:
-	p = select_bad_process(&points);
+		/*
+		 * 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;
+		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");
-	}
+		/* 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");
+		}
 
-	mm = oom_kill_process(p, points);
-	if (!mm)
-		goto retry;
+		if (oom_kill_process(p, points, "Out of memory"))
+			goto retry;
+
+		break;
+	}
 
- out:
+out:
 	read_unlock(&tasklist_lock);
 	cpuset_unlock();
-	if (mm)
-		mmput(mm);
 
 	/*
 	 * Give "p" a good chance of killing itself before we
 	 * retry to allocate memory unless "p" is current
 	 */
 	if (!test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_interruptible(1);
+		schedule_timeout_uninterruptible(1);
 }