Gitweb:     
http://git.kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=d3ed782458f315c30ea679b919a2cc59f2b82565
Commit:     d3ed782458f315c30ea679b919a2cc59f2b82565
Parent:     d5d3b736e3264934ec832a657a9a434b65f3d51f
Author:     Thomas Gleixner <[EMAIL PROTECTED]>
AuthorDate: Tue May 8 00:30:03 2007 -0700
Committer:  Linus Torvalds <[EMAIL PROTECTED]>
CommitDate: Tue May 8 11:15:10 2007 -0700

    highres/dyntick: prevent xtime lock contention
    
    While the !highres/!dyntick code assigns the duty of the do_timer() call to
    one specific CPU, this was dropped in the highres/dyntick part during
    development.
    
    Steven Rostedt discovered the xtime lock contention on highres/dyntick due
    to several CPUs trying to update jiffies.
    
    Add the single CPU assignement back.  In the dyntick case this needs to be
    handled carefully, as the CPU which has the do_timer() duty must drop the
    assignement and let it be grabbed by another CPU, which is active.
    Otherwise the do_timer() calls would not happen during the long sleep.
    
    Signed-off-by: Thomas Gleixner <[EMAIL PROTECTED]>
    Acked-by: Ingo Molnar <[EMAIL PROTECTED]>
    Cc: Steven Rostedt <[EMAIL PROTECTED]>
    Acked-by: Mark Lord <[EMAIL PROTECTED]>
    Cc: <[EMAIL PROTECTED]>
    Signed-off-by: Andrew Morton <[EMAIL PROTECTED]>
    Signed-off-by: Linus Torvalds <[EMAIL PROTECTED]>
---
 kernel/time/tick-common.c   |    8 +++++++-
 kernel/time/tick-internal.h |    1 +
 kernel/time/tick-sched.c    |   42 ++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index bfda3f7..a96ec9a 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -31,7 +31,7 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
  */
 ktime_t tick_next_period;
 ktime_t tick_period;
-static int tick_do_timer_cpu = -1;
+int tick_do_timer_cpu __read_mostly = -1;
 DEFINE_SPINLOCK(tick_device_lock);
 
 /*
@@ -295,6 +295,12 @@ static void tick_shutdown(unsigned int *cpup)
                clockevents_exchange_device(dev, NULL);
                td->evtdev = NULL;
        }
+       /* Transfer the do_timer job away from this cpu */
+       if (*cpup == tick_do_timer_cpu) {
+               int cpu = first_cpu(cpu_online_map);
+
+               tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : -1;
+       }
        spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index c9d203b..bb13f27 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -5,6 +5,7 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 extern spinlock_t tick_device_lock;
 extern ktime_t tick_next_period;
 extern ktime_t tick_period;
+extern int tick_do_timer_cpu __read_mostly;
 
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 51556b9..f4fc867 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -221,6 +221,18 @@ void tick_nohz_stop_sched_tick(void)
                        ts->tick_stopped = 1;
                        ts->idle_jiffies = last_jiffies;
                }
+
+               /*
+                * If this cpu is the one which updates jiffies, then
+                * give up the assignment and let it be taken by the
+                * cpu which runs the tick timer next, which might be
+                * this cpu as well. If we don't drop this here the
+                * jiffies might be stale and do_timer() never
+                * invoked.
+                */
+               if (cpu == tick_do_timer_cpu)
+                       tick_do_timer_cpu = -1;
+
                /*
                 * calculate the expiry time for the next timer wheel
                 * timer
@@ -338,12 +350,24 @@ static void tick_nohz_handler(struct clock_event_device 
*dev)
 {
        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
        struct pt_regs *regs = get_irq_regs();
+       int cpu = smp_processor_id();
        ktime_t now = ktime_get();
 
        dev->next_event.tv64 = KTIME_MAX;
 
+       /*
+        * Check if the do_timer duty was dropped. We don't care about
+        * concurrency: This happens only when the cpu in charge went
+        * into a long sleep. If two cpus happen to assign themself to
+        * this duty, then the jiffies update is still serialized by
+        * xtime_lock.
+        */
+       if (unlikely(tick_do_timer_cpu == -1))
+               tick_do_timer_cpu = cpu;
+
        /* Check, if the jiffies need an update */
-       tick_do_update_jiffies64(now);
+       if (tick_do_timer_cpu == cpu)
+               tick_do_update_jiffies64(now);
 
        /*
         * When we are idle and the tick is stopped, we have to touch
@@ -431,9 +455,23 @@ static enum hrtimer_restart tick_sched_timer(struct 
hrtimer *timer)
        struct hrtimer_cpu_base *base = timer->base->cpu_base;
        struct pt_regs *regs = get_irq_regs();
        ktime_t now = ktime_get();
+       int cpu = smp_processor_id();
+
+#ifdef CONFIG_NO_HZ
+       /*
+        * Check if the do_timer duty was dropped. We don't care about
+        * concurrency: This happens only when the cpu in charge went
+        * into a long sleep. If two cpus happen to assign themself to
+        * this duty, then the jiffies update is still serialized by
+        * xtime_lock.
+        */
+       if (unlikely(tick_do_timer_cpu == -1))
+               tick_do_timer_cpu = cpu;
+#endif
 
        /* Check, if the jiffies need an update */
-       tick_do_update_jiffies64(now);
+       if (tick_do_timer_cpu == cpu)
+               tick_do_update_jiffies64(now);
 
        /*
         * Do not call, when we are not in irq context and have
-
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

Reply via email to