kernel/watchdog.c: always return NOTIFY_OK during cpu up/down events

This patch addresses a couple of problems.  One was the case when the
hardlockup failed to start, it also failed to start the softlockup.  There
were valid cases when the hardlockup shouldn't start and that shouldn't
block the softlockup (no lapic, bios controls perf counters).

The second problem was when the hardlockup failed to start on boxes (from
a no lapic or bios controlled perf counter case), it reported failure to
the cpu notifier chain.  This blocked the notifier from continuing to
start other more critical pieces of cpu bring-up (in our case based on a
2.6.32 fork, it was the mce).  As a result, during soft cpu online/offline
testing, the system would panic when a cpu was offlined because the cpu
notifier would succeed in processing a watchdog disable cpu event and
would panic in the mce case as a result of un-initialized variables from a
never executed cpu up event.

I realized the hardlockup/softlockup cases are really just debugging aids
and should never impede the progress of a cpu up/down event.  Therefore I
modified the code to always return NOTIFY_OK and instead rely on printks
to inform the user of problems.

Signed-off-by: Don Zickus <dzickus@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: WANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 054a67cca9da37b07ebd1fad5f415d8bb7b711db..140dce750450edc8db5285817c26fd354ec0c56a 100644 (file)
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -418,19 +418,22 @@ static int watchdog_prepare_cpu(int cpu)
 static int watchdog_enable(int cpu)
 {
        struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
-       int err;
+       int err = 0;
 
        /* enable the perf event */
        err = watchdog_nmi_enable(cpu);
-       if (err)
-               return err;
+
+       /* Regardless of err above, fall through and start softlockup */
 
        /* create the watchdog thread */
        if (!p) {
                p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
                if (IS_ERR(p)) {
                        printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
-                       return PTR_ERR(p);
+                       if (!err)
+                               /* if hardlockup hasn't already set this */
+                               err = PTR_ERR(p);
+                       goto out;
                }
                kthread_bind(p, cpu);
                per_cpu(watchdog_touch_ts, cpu) = 0;
@@ -438,7 +441,8 @@ static int watchdog_enable(int cpu)
                wake_up_process(p);
        }
 
-       return 0;
+out:
+       return err;
 }
 
 static void watchdog_disable(int cpu)
@@ -550,7 +554,13 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
                break;
 #endif /* CONFIG_HOTPLUG_CPU */
        }
-       return notifier_from_errno(err);
+
+       /*
+        * hardlockup and softlockup are not important enough
+        * to block cpu bring up.  Just always succeed and
+        * rely on printk output to flag problems.
+        */
+       return NOTIFY_OK;
 }
 
 static struct notifier_block __cpuinitdata cpu_nfb = {