[PATCH] cpusets: confine oom_killer to mem_exclusive cpuset

Now the real motivation for this cpuset mem_exclusive patch series seems
trivial.

This patch keeps a task in or under one mem_exclusive cpuset from provoking an
oom kill of a task under a non-overlapping mem_exclusive cpuset. Since only
interrupt and GFP_ATOMIC allocations are allowed to escape mem_exclusive
containment, there is little to gain from oom killing a task under a
non-overlapping mem_exclusive cpuset, as almost all kernel and user memory
allocation must come from disjoint memory nodes.

This patch enables configuring a system so that a runaway job under one
mem_exclusive cpuset cannot cause the killing of a job in another such cpuset
that might be using very high compute and memory resources for a prolonged
time.

Signed-off-by: Paul Jackson <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/cpuset.h

···
 void cpuset_restrict_to_mems_allowed(unsigned long *nodes);
 int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl);
 extern int cpuset_zone_allowed(struct zone *z, unsigned int __nocast gfp_mask);
+extern int cpuset_excl_nodes_overlap(const struct task_struct *p);
 extern struct file_operations proc_cpuset_operations;
 extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer);
 
···
 
 static inline int cpuset_zone_allowed(struct zone *z,
 					unsigned int __nocast gfp_mask)
+{
+	return 1;
+}
+
+static inline int cpuset_excl_nodes_overlap(const struct task_struct *p)
 {
 	return 1;
 }

kernel/cpuset.c

···
 	return allowed;
 }
 
+/**
+ * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors?
+ * @p: pointer to task_struct of some other task.
+ *
+ * Description: Return true if the nearest mem_exclusive ancestor
+ * cpusets of tasks @p and current overlap.  Used by oom killer to
+ * determine if task @p's memory usage might impact the memory
+ * available to the current task.
+ *
+ * Acquires cpuset_sem - not suitable for calling from a fast path.
+ **/
+
+int cpuset_excl_nodes_overlap(const struct task_struct *p)
+{
+	const struct cpuset *cs1, *cs2;	/* my and p's cpuset ancestors */
+	int overlap = 0;		/* do cpusets overlap? */
+
+	down(&cpuset_sem);
+	cs1 = current->cpuset;
+	if (!cs1)
+		goto done;		/* current task exiting */
+	cs2 = p->cpuset;
+	if (!cs2)
+		goto done;		/* task p is exiting */
+	cs1 = nearest_exclusive_ancestor(cs1);
+	cs2 = nearest_exclusive_ancestor(cs2);
+	overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
+done:
+	up(&cpuset_sem);
+
+	return overlap;
+}
+
 /*
  * proc_cpuset_show()
  *  - Print tasks cpuset path into seq_file.

mm/oom_kill.c

···
 #include <linux/swap.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
+#include <linux/cpuset.h>
 
 /* #define DEBUG */
 
···
 			continue;
 		if (p->oomkilladj == OOM_DISABLE)
 			continue;
+		/* If p's nodes don't overlap ours, it won't help to kill p. */
+		if (!cpuset_excl_nodes_overlap(p))
+			continue;
+
 		/*
 		 * This is in the process of releasing memory so for wait it
 		 * to finish before killing some other task by mistake.