Ignore stolen time in the softlockup watchdog

[Linux Kernel Mailing List]

Gitweb:     
http://git.kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=966812dc98e6a7fcdf759cbfa0efab77500a8868
Commit:     966812dc98e6a7fcdf759cbfa0efab77500a8868
Parent:     8524070b7982d76258942275908b7434cfcab4b4
Author:     Jeremy Fitzhardinge <[EMAIL PROTECTED]>
AuthorDate: Tue May 8 00:28:02 2007 -0700
Committer:  Linus Torvalds <[EMAIL PROTECTED]>
CommitDate: Tue May 8 11:15:06 2007 -0700

    Ignore stolen time in the softlockup watchdog
    
    The softlockup watchdog is currently a nuisance in a virtual machine, since
    the whole system could have the CPU stolen from it for a long period of
    time.  While it would be unlikely for a guest domain to be denied timer
    interrupts for over 10s, it could happen and any softlockup message would
    be completely spurious.
    
    Earlier I proposed that sched_clock() return time in unstolen nanoseconds,
    which is how Xen and VMI currently implement it.  If the softlockup
    watchdog uses sched_clock() to measure time, it would automatically ignore
    stolen time, and therefore only report when the guest itself locked up.
    When running native, sched_clock() returns real-time nanoseconds, so the
    behaviour would be unchanged.
    
    Note that sched_clock() used this way is inherently per-cpu, so this patch
    makes sure that the per-processor watchdog thread initialized its own
    timestamp.
    
    Signed-off-by: Jeremy Fitzhardinge <[EMAIL PROTECTED]>
    Cc: Ingo Molnar <[EMAIL PROTECTED]>
    Cc: Thomas Gleixner <[EMAIL PROTECTED]>
    Cc: john stultz <[EMAIL PROTECTED]>
    Cc: Zachary Amsden <[EMAIL PROTECTED]>
    Cc: James Morris <[EMAIL PROTECTED]>
    Cc: Dan Hecht <[EMAIL PROTECTED]>
    Cc: Paul Mackerras <[EMAIL PROTECTED]>
    Cc: Martin Schwidefsky <[EMAIL PROTECTED]>
    Cc: Prarit Bhargava <[EMAIL PROTECTED]>
    Cc: Chris Lalancette <[EMAIL PROTECTED]>
    Cc: Rick Lindsley <[EMAIL PROTECTED]>
    Cc: Eric Dumazet <[EMAIL PROTECTED]>
    Signed-off-by: Andrew Morton <[EMAIL PROTECTED]>
    Signed-off-by: Linus Torvalds <[EMAIL PROTECTED]>
---
 kernel/softlockup.c |   35 +++++++++++++++++++++++++++++------
 1 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 81d43ca..5ea6317 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -34,9 +34,19 @@ static struct notifier_block panic_block = {
        .notifier_call = softlock_panic,
 };
 
+/*
+ * Returns seconds, approximately.  We don't need nanosecond
+ * resolution, and we don't need to waste time with a big divide when
+ * 2^30ns == 1.074s.
+ */
+static unsigned long get_timestamp(void)
+{
+       return sched_clock() >> 30;  /* 2^30 ~= 10^9 */
+}
+
 void touch_softlockup_watchdog(void)
 {
-       __raw_get_cpu_var(touch_timestamp) = jiffies;
+       __raw_get_cpu_var(touch_timestamp) = get_timestamp();
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
@@ -48,9 +58,17 @@ void softlockup_tick(void)
 {
        int this_cpu = smp_processor_id();
        unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+       unsigned long print_timestamp;
+       unsigned long now;
 
-       /* prevent double reports: */
-       if (per_cpu(print_timestamp, this_cpu) == touch_timestamp ||
+       /* watchdog task hasn't updated timestamp yet */
+       if (touch_timestamp == 0)
+               return;
+
+       print_timestamp = per_cpu(print_timestamp, this_cpu);
+
+       /* report at most once a second */
+       if (print_timestamp < (touch_timestamp + 1) ||
                did_panic ||
                        !per_cpu(watchdog_task, this_cpu))
                return;
@@ -61,12 +79,14 @@ void softlockup_tick(void)
                return;
        }
 
+       now = get_timestamp();
+
        /* Wake up the high-prio watchdog task every second: */
-       if (time_after(jiffies, touch_timestamp + HZ))
+       if (now > (touch_timestamp + 1))
                wake_up_process(per_cpu(watchdog_task, this_cpu));
 
        /* Warn about unreasonable 10+ seconds delays: */
-       if (time_after(jiffies, touch_timestamp + 10*HZ)) {
+       if (now > (touch_timestamp + 10)) {
                per_cpu(print_timestamp, this_cpu) = touch_timestamp;
 
                spin_lock(&print_lock);
@@ -87,6 +107,9 @@ static int watchdog(void * __bind_cpu)
        sched_setscheduler(current, SCHED_FIFO, &param);
        current->flags |= PF_NOFREEZE;
 
+       /* initialize timestamp */
+       touch_softlockup_watchdog();
+
        /*
         * Run briefly once per second to reset the softlockup timestamp.
         * If this gets delayed for more than 10 seconds then the
@@ -118,7 +141,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long 
action, void *hcpu)
                        printk("watchdog for %i failed\n", hotcpu);
                        return NOTIFY_BAD;
                }
-               per_cpu(touch_timestamp, hotcpu) = jiffies;
+               per_cpu(touch_timestamp, hotcpu) = 0;
                per_cpu(watchdog_task, hotcpu) = p;
                kthread_bind(p, hotcpu);
                break;
-
To unsubscribe from this list: send the line "unsubscribe git-commits-head" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html