* [PATCH 1/2] hrtimers: provide a hrtimers_late_resume() call
2013-06-20 19:13 [PATCHv5 0/4] xen: maintain an accurate persistent clock in more cases David Vrabel
@ 2013-06-20 19:13 ` David Vrabel
2013-06-20 19:13 ` [PATCH 2/2] time: add a notifier chain for when the system time is stepped David Vrabel
2013-06-20 19:18 ` [PATCHv5 0/4] xen: maintain an accurate persistent clock in more cases David Vrabel
2 siblings, 0 replies; 7+ messages in thread
From: David Vrabel @ 2013-06-20 19:13 UTC (permalink / raw)
To: xen-devel
Cc: David Vrabel, Konrad Rzeszutek Wilk, linux-kernel, John Stultz,
Thomas Gleixner
From: David Vrabel <david.vrabel@citrix.com>
Xen suspends (and resumes) without disabling non-boot CPUs as doing so
adds considerable delay to live migrations. A 4 VCPU guest had more
than 200 ms of additional downtime if disable_nonboot_cpus() was
called prior to suspending.
As a consequence, only high resolution timers on the current CPU are
retriggered when resuming. The Xen resume path worked around this
with a call to clock_was_set() to retrigger timers on all the CPUs.
A subsequent change will make clock_was_set() internal to hrtimers so
add an new call (hrtimers_late_resume()) to do the same job.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
drivers/xen/manage.c | 8 ++++++--
include/linux/hrtimer.h | 1 +
kernel/hrtimer.c | 9 +++++++++
3 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 412b96c..75bc2d5 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -166,8 +166,12 @@ out_resume:
dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
- /* Make sure timer events get retriggered on all CPUs */
- clock_was_set();
+ /*
+ * syscore_resume() ends up calling hrtimer_resume() but this
+ * only retriggers timer events on the current CPU. We need
+ * to retrigger the events on all the other CPUS.
+ */
+ hrtimers_late_resume();
out_thaw:
#ifdef CONFIG_PREEMPT
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index d19a5c2..13df0fa 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -323,6 +323,7 @@ extern void timerfd_clock_was_set(void);
static inline void timerfd_clock_was_set(void) { }
#endif
extern void hrtimers_resume(void);
+extern void hrtimers_late_resume(void);
extern ktime_t ktime_get(void);
extern ktime_t ktime_get_real(void);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index fd4b13b..34384b4 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -784,6 +784,15 @@ void hrtimers_resume(void)
timerfd_clock_was_set();
}
+/*
+ * If non-boot CPUs were online during resume, we need to retrigger
+ * the events for all the non-boot CPUs.
+ */
+void hrtimers_late_resume(void)
+{
+ clock_was_set();
+}
+
static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
--
1.7.2.5
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH 2/2] time: add a notifier chain for when the system time is stepped
2013-06-20 19:13 [PATCHv5 0/4] xen: maintain an accurate persistent clock in more cases David Vrabel
2013-06-20 19:13 ` [PATCH 1/2] hrtimers: provide a hrtimers_late_resume() call David Vrabel
@ 2013-06-20 19:13 ` David Vrabel
2013-06-20 19:18 ` [PATCHv5 0/4] xen: maintain an accurate persistent clock in more cases David Vrabel
2 siblings, 0 replies; 7+ messages in thread
From: David Vrabel @ 2013-06-20 19:13 UTC (permalink / raw)
To: xen-devel
Cc: David Vrabel, Konrad Rzeszutek Wilk, linux-kernel, John Stultz,
Thomas Gleixner
From: David Vrabel <david.vrabel@citrix.com>
The high resolution timer code gets notified of step changes to the
system time with clock_was_set() or clock_was_set_delayed() calls. If
other parts of the kernel require similar notification there is no
clear place to hook into.
Add a clock_was_set atomic notifier chain
(clock_was_set_notifier_list) and call this in place of
clock_was_set(). If the timekeeping locks are held, the calls are
deferred to a new tasklet.
The hrtimer code adds a notifier block to this chain and uses it to
call (the now internal) clock_was_set(). Since the timekeeping code
does not call the chain from the timer irq clock_was_set_delayed() and
associated code can be removed.
For the delayed case, clock_was_set() used to be called at the
beginning of the hrtimer softirq and now it is called from a tasklet.
The tasklet softirq will be called before the hrtimer one so this
should give the same behaviour.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/hrtimer.h | 7 -------
include/linux/time.h | 7 +++++++
kernel/hrtimer.c | 34 +++++++++++++---------------------
kernel/time/timekeeping.c | 39 ++++++++++++++++++++++++++++++---------
4 files changed, 50 insertions(+), 37 deletions(-)
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 13df0fa..45e30f6 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -166,7 +166,6 @@ enum hrtimer_base_type {
* @lock: lock protecting the base and associated clock bases
* and timers
* @active_bases: Bitfield to mark bases with active timers
- * @clock_was_set: Indicates that clock was set from irq context.
* @expires_next: absolute time of the next event which was scheduled
* via clock_set_next_event()
* @hres_active: State of high resolution mode
@@ -180,7 +179,6 @@ enum hrtimer_base_type {
struct hrtimer_cpu_base {
raw_spinlock_t lock;
unsigned int active_bases;
- unsigned int clock_was_set;
#ifdef CONFIG_HIGH_RES_TIMERS
ktime_t expires_next;
int hres_active;
@@ -289,8 +287,6 @@ extern void hrtimer_peek_ahead_timers(void);
# define MONOTONIC_RES_NSEC HIGH_RES_NSEC
# define KTIME_MONOTONIC_RES KTIME_HIGH_RES
-extern void clock_was_set_delayed(void);
-
#else
# define MONOTONIC_RES_NSEC LOW_RES_NSEC
@@ -312,11 +308,8 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
return 0;
}
-static inline void clock_was_set_delayed(void) { }
-
#endif
-extern void clock_was_set(void);
#ifdef CONFIG_TIMERFD
extern void timerfd_clock_was_set(void);
#else
diff --git a/include/linux/time.h b/include/linux/time.h
index d5d229b..a0c08a7 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -184,6 +184,13 @@ extern void timekeeping_clocktai(struct timespec *ts);
struct tms;
extern void do_sys_times(struct tms *);
+struct notifier_block;
+
+/*
+ * Notifier chain called when system time is stepped.
+ */
+extern int register_clock_was_set_notifier(struct notifier_block *nb);
+
/*
* Similar to the struct tm in userspace <time.h>, but it needs to be here so
* that the kernel source is self contained.
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 34384b4..a853f9b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -721,19 +721,6 @@ static int hrtimer_switch_to_hres(void)
return 1;
}
-/*
- * Called from timekeeping code to reprogramm the hrtimer interrupt
- * device. If called from the timer interrupt context we defer it to
- * softirq context.
- */
-void clock_was_set_delayed(void)
-{
- struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
- cpu_base->clock_was_set = 1;
- __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-}
-
#else
static inline int hrtimer_hres_active(void) { return 0; }
@@ -762,7 +749,7 @@ static inline void retrigger_next_event(void *arg) { }
* resolution timer interrupts. On UP we just disable interrupts and
* call the high resolution interrupt code.
*/
-void clock_was_set(void)
+static void clock_was_set(void)
{
#ifdef CONFIG_HIGH_RES_TIMERS
/* Retrigger the CPU local events everywhere */
@@ -1441,13 +1428,6 @@ void hrtimer_peek_ahead_timers(void)
static void run_hrtimer_softirq(struct softirq_action *h)
{
- struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
- if (cpu_base->clock_was_set) {
- cpu_base->clock_was_set = 0;
- clock_was_set();
- }
-
hrtimer_peek_ahead_timers();
}
@@ -1785,11 +1765,23 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
.notifier_call = hrtimer_cpu_notify,
};
+static int hrtimer_clock_was_set_notify(struct notifier_block *self,
+ unsigned long action, void *data)
+{
+ clock_was_set();
+ return NOTIFY_OK;
+}
+
+static struct notifier_block hrtimers_clock_was_set_nb = {
+ .notifier_call = hrtimer_clock_was_set_notify,
+};
+
void __init hrtimers_init(void)
{
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
+ register_clock_was_set_notifier(&hrtimers_clock_was_set_nb);
#ifdef CONFIG_HIGH_RES_TIMERS
open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
#endif
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index baeeb5c..96c5c8e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -198,6 +198,30 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
return nsec + get_arch_timeoffset();
}
+static ATOMIC_NOTIFIER_HEAD(clock_was_set_notifier_list);
+
+int register_clock_was_set_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_register(&clock_was_set_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_clock_was_set_notifier);
+
+static void timekeeping_clock_was_set(void)
+{
+ atomic_notifier_call_chain(&clock_was_set_notifier_list, 0, NULL);
+}
+
+static void timekeeping_clock_was_set_task(unsigned long d)
+{
+ timekeeping_clock_was_set();
+}
+DECLARE_TASKLET(clock_was_set_tasklet, timekeeping_clock_was_set_task, 0);
+
+static void timekeeping_clock_was_set_delayed(void)
+{
+ tasklet_schedule(&clock_was_set_tasklet);
+}
+
static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
static void update_pvclock_gtod(struct timekeeper *tk)
@@ -513,8 +537,7 @@ int do_settimeofday(const struct timespec *tv)
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
- /* signal hrtimers about time change */
- clock_was_set();
+ timekeeping_clock_was_set();
return 0;
}
@@ -557,8 +580,7 @@ error: /* even if we error out, we forwarded the time, so call update */
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
- /* signal hrtimers about time change */
- clock_was_set();
+ timekeeping_clock_was_set();
return ret;
}
@@ -607,7 +629,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
__timekeeping_set_tai_offset(tk, tai_offset);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
- clock_was_set();
+ timekeeping_clock_was_set();
}
/**
@@ -877,8 +899,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
- /* signal hrtimers about time change */
- clock_was_set();
+ timekeeping_clock_was_set();
}
/**
@@ -1260,7 +1281,7 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
- clock_was_set_delayed();
+ timekeeping_clock_was_set_delayed();
}
}
}
@@ -1677,7 +1698,7 @@ int do_adjtimex(struct timex *txc)
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tk, tai);
- clock_was_set_delayed();
+ timekeeping_clock_was_set_delayed();
}
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
--
1.7.2.5
^ permalink raw reply related [flat|nested] 7+ messages in thread