oom: add oom_kill_allocating_task sysctl

Adds a new sysctl, 'oom_kill_allocating_task', which will automatically kill
the OOM-triggering task instead of scanning through the tasklist to find a
memory-hogging target.  This is helpful for systems with an insanely large
number of tasks where scanning the tasklist significantly degrades
performance.

Cc: Andrea Arcangeli <andrea@suse.de>
Acked-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Documentation/sysctl/vm.txt

@@ -31,6 +31,7 @@ Currently, these files are in /proc/sys/vm:
 - min_unmapped_ratio
 - min_slab_ratio
 - panic_on_oom
+- oom_kill_allocating_task
 - mmap_min_address
 - numa_zonelist_order
 
@@ -220,6 +221,27 @@ The default value is 0.
 1 and 2 are for failover of clustering. Please select either
 according to your policy of failover.
 
+=============================================================
+
+oom_kill_allocating_task
+
+This enables or disables killing the OOM-triggering task in
+out-of-memory situations.
+
+If this is set to zero, the OOM killer will scan through the entire
+tasklist and select a task based on heuristics to kill.  This normally
+selects a rogue memory-hogging task that frees up a large amount of
+memory when killed.
+
+If this is set to non-zero, the OOM killer simply kills the task that
+triggered the out-of-memory condition.  This avoids the expensive
+tasklist scan.
+
+If panic_on_oom is selected, it takes precedence over whatever value
+is used in oom_kill_allocating_task.
+
+The default value is 0.
+
 ==============================================================
 
 mmap_min_addr

kernel/sysctl.c

@@ -63,6 +63,7 @@ extern int print_fatal_signals;
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern int sysctl_panic_on_oom;
+extern int sysctl_oom_kill_allocating_task;
 extern int max_threads;
 extern int core_uses_pid;
 extern int suid_dumpable;
@@ -780,6 +781,14 @@ static ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "oom_kill_allocating_task",
+		.data		= &sysctl_oom_kill_allocating_task,
+		.maxlen		= sizeof(sysctl_oom_kill_allocating_task),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= VM_OVERCOMMIT_RATIO,
 		.procname	= "overcommit_ratio",

mm/oom_kill.c

@@ -27,6 +27,7 @@
 #include <linux/notifier.h>
 
 int sysctl_panic_on_oom;
+int sysctl_oom_kill_allocating_task;
 static DEFINE_MUTEX(zone_scan_mutex);
 /* #define DEBUG */
 
@@ -471,14 +472,16 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 				"No available memory (MPOL_BIND)");
 		break;
 
-	case CONSTRAINT_CPUSET:
-		oom_kill_process(current, points,
-				"No available memory in cpuset");
-		break;
-
 	case CONSTRAINT_NONE:
 		if (sysctl_panic_on_oom)
 			panic("out of memory. panic_on_oom is selected\n");
+		/* Fall-through */
+	case CONSTRAINT_CPUSET:
+		if (sysctl_oom_kill_allocating_task) {
+			oom_kill_process(current, points,
+					"Out of memory (oom_kill_allocating_task)");
+			break;
+		}
 retry:
 		/*
 		 * Rambo mode: Shoot down a process and hope it solves whatever