[PATCH] support for panic at OOM

This patch adds panic_on_oom sysctl under sys.vm.

When sysctl vm.panic_on_oom = 1, the kernel panics intead of killing rogue
processes.  And if vm.panic_on_oom is 0 the kernel will do oom_kill() in
the same way as it does today.  Of course, the default value is 0 and only
root can modifies it.

In general, oom_killer works well and kill rogue processes.  So the whole
system can survive.  But there are environments where panic is preferable
rather than kill some processes.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 26 insertions, 0 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index a46c10fcddfc..2dc246af4885 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -29,6 +29,7 @@ Currently, these files are in /proc/sys/vm:
 - drop-caches
 - zone_reclaim_mode
 - zone_reclaim_interval
+- panic_on_oom
 
 ==============================================================
 
@@ -178,3 +179,15 @@ Time is set in seconds and set by default to 30 seconds.
 Reduce the interval if undesired off node allocations occur. However, too
 frequent scans will have a negative impact onoff node allocation performance.
 
+=============================================================
+
+panic_on_oom
+
+This enables or disables panic on out-of-memory feature.  If this is set to 1,
+the kernel panics when out-of-memory happens.  If this is set to 0, the kernel
+will kill some rogue process, called oom_killer.  Usually, oom_killer can kill
+rogue processes and system will survive.  If you want to panic the system
+rather than killing rogue processes, set this to 1.
+
+The default value is 0.
+
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index cee944dbdcd4..c7132029af0f 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -186,6 +186,7 @@ enum
         VM_PERCPU_PAGELIST_FRACTION=30,/* int: fraction of pages in each percpu_pagelist */
         VM_ZONE_RECLAIM_MODE=31, /* reclaim local zone memory before going off node */
         VM_ZONE_RECLAIM_INTERVAL=32, /* time period to wait after reclaim failure */
+        VM_PANIC_ON_OOM=33,     /* panic at out-of-memory */
 };
 
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0d656e61621d..072ac446810a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -59,6 +59,7 @@ extern int proc_nr_files(ctl_table *table, int write, struct file *filp,
 extern int C_A_D;
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
+extern int sysctl_panic_on_oom;
 extern int max_threads;
 extern int sysrq_enabled;
 extern int core_uses_pid;
@@ -702,6 +703,14 @@ static ctl_table vm_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
         {
+                .ctl_name       = VM_PANIC_ON_OOM,
+                .procname       = "panic_on_oom",
+                .data           = &sysctl_panic_on_oom,
+                .maxlen         = sizeof(sysctl_panic_on_oom),
+                .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 042e6436c3ee..f9bb3cf32384 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -22,6 +22,7 @@
 #include <linux/jiffies.h>
 #include <linux/cpuset.h>
 
+int sysctl_panic_on_oom;
 /* #define DEBUG */
 
 /**
@@ -344,6 +345,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
                 break;
 
         case CONSTRAINT_NONE:
+                if (sysctl_panic_on_oom)
+                        panic("out of memory. panic_on_oom is selected\n");
 retry:
                 /*
                  * Rambo mode: Shoot down a process and hope it solves whatever