3 files changed, 39 insertions, 5 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index a0ccc5b60260..17346da636e7 100644
--- a/Documentation/sysctl/vm.txt
+++ b/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
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c676b5ec88f5..5e63de0f9ee2 100644
--- a/kernel/sysctl.c
+++ b/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;
@@ -781,6 +782,14 @@ static ctl_table vm_table[] = {
                 .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",
                 .data           = &sysctl_overcommit_ratio,
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6e999c88c503..00d0bd7d6a2b 100644
--- a/mm/oom_kill.c
+++ b/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