[git pull] scheduler fixes for -rc3

From: Ingo Molnar
Date: Mon Aug 11 2008 - 18:25:19 EST

Linus,

Please pull the latest sched-fixes-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus

Thanks,

Ingo

------------------>
Dmitry Adamushko (1):
sched, cpu hotplug: fix set_cpus_allowed() use in hotplug callbacks

Hugh Dickins (1):
sched: move sched_clock before first use

Ingo Molnar (5):
sched clock: revert various sched_clock() changes
sched clock: clean up sched_clock_cpu()
sched: eliminate scd->prev_raw
sched clock: simplify __update_sched_clock()
sched clock: couple local and remote clocks

Mike Galbraith (1):
sched: fix mysql+oltp regression

OGAWA Hirofumi (1):
sched: fix SCHED_HRTICK dependency

Peter Zijlstra (2):
sched: fix warning in hrtick_start_fair()
sched_clock: delay using sched_clock()

roel kluin (1):
sched: test runtime rather than period in global_rt_runtime()


include/linux/sched.h | 31 +-------
kernel/Kconfig.hz | 2 +-
kernel/cpu.c | 5 +-
kernel/sched.c | 2 +-
kernel/sched_clock.c | 178 ++++++++++++++-------------------------------
kernel/sched_fair.c | 21 ++++--
kernel/time/tick-sched.c | 2 -
7 files changed, 77 insertions(+), 164 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5270d44..5850bfb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1551,16 +1551,10 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)

extern unsigned long long sched_clock(void);

-#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline void sched_clock_init(void)
-{
-}
-
-static inline u64 sched_clock_cpu(int cpu)
-{
- return sched_clock();
-}
+extern void sched_clock_init(void);
+extern u64 sched_clock_cpu(int cpu);

+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
static inline void sched_clock_tick(void)
{
}
@@ -1572,28 +1566,11 @@ static inline void sched_clock_idle_sleep_event(void)
static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
{
}
-
-#ifdef CONFIG_NO_HZ
-static inline void sched_clock_tick_stop(int cpu)
-{
-}
-
-static inline void sched_clock_tick_start(int cpu)
-{
-}
-#endif
-
-#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-extern void sched_clock_init(void);
-extern u64 sched_clock_cpu(int cpu);
+#else
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
-#ifdef CONFIG_NO_HZ
-extern void sched_clock_tick_stop(int cpu);
-extern void sched_clock_tick_start(int cpu);
#endif
-#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */

/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
index 382dd5a..94fabd5 100644
--- a/kernel/Kconfig.hz
+++ b/kernel/Kconfig.hz
@@ -55,4 +55,4 @@ config HZ
default 1000 if HZ_1000

config SCHED_HRTICK
- def_bool HIGH_RES_TIMERS && USE_GENERIC_SMP_HELPERS
+ def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e202a68..c977c33 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -349,6 +349,8 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
goto out_notify;
BUG_ON(!cpu_online(cpu));

+ cpu_set(cpu, cpu_active_map);
+
/* Now call notifier in preparation. */
raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);

@@ -383,9 +385,6 @@ int __cpuinit cpu_up(unsigned int cpu)

err = _cpu_up(cpu, 0);

- if (cpu_online(cpu))
- cpu_set(cpu, cpu_active_map);
-
out:
cpu_maps_update_done();
return err;
diff --git a/kernel/sched.c b/kernel/sched.c
index 04160d2..f014194 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -834,7 +834,7 @@ static inline u64 global_rt_period(void)

static inline u64 global_rt_runtime(void)
{
- if (sysctl_sched_rt_period < 0)
+ if (sysctl_sched_rt_runtime < 0)
return RUNTIME_INF;

return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 22ed55d..204991a 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -32,13 +32,19 @@
#include <linux/ktime.h>
#include <linux/module.h>

+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+ return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}

-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static __read_mostly int sched_clock_running;

-#define MULTI_SHIFT 15
-/* Max is double, Min is 1/2 */
-#define MAX_MULTI (2LL << MULTI_SHIFT)
-#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK

struct sched_clock_data {
/*
@@ -49,14 +55,9 @@ struct sched_clock_data {
raw_spinlock_t lock;

unsigned long tick_jiffies;
- u64 prev_raw;
u64 tick_raw;
u64 tick_gtod;
u64 clock;
- s64 multi;
-#ifdef CONFIG_NO_HZ
- int check_max;
-#endif
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -71,8 +72,6 @@ static inline struct sched_clock_data *cpu_sdc(int cpu)
return &per_cpu(sched_clock_data, cpu);
}

-static __read_mostly int sched_clock_running;
-
void sched_clock_init(void)
{
u64 ktime_now = ktime_to_ns(ktime_get());
@@ -84,90 +83,39 @@ void sched_clock_init(void)

scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
scd->tick_jiffies = now_jiffies;
- scd->prev_raw = 0;
scd->tick_raw = 0;
scd->tick_gtod = ktime_now;
scd->clock = ktime_now;
- scd->multi = 1 << MULTI_SHIFT;
-#ifdef CONFIG_NO_HZ
- scd->check_max = 1;
-#endif
}

sched_clock_running = 1;
}

-#ifdef CONFIG_NO_HZ
-/*
- * The dynamic ticks makes the delta jiffies inaccurate. This
- * prevents us from checking the maximum time update.
- * Disable the maximum check during stopped ticks.
- */
-void sched_clock_tick_stop(int cpu)
-{
- struct sched_clock_data *scd = cpu_sdc(cpu);
-
- scd->check_max = 0;
-}
-
-void sched_clock_tick_start(int cpu)
-{
- struct sched_clock_data *scd = cpu_sdc(cpu);
-
- scd->check_max = 1;
-}
-
-static int check_max(struct sched_clock_data *scd)
-{
- return scd->check_max;
-}
-#else
-static int check_max(struct sched_clock_data *scd)
-{
- return 1;
-}
-#endif /* CONFIG_NO_HZ */
-
/*
* update the percpu scd from the raw @now value
*
* - filter out backward motion
* - use jiffies to generate a min,max window to clip the raw values
*/
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
+static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
{
unsigned long now_jiffies = jiffies;
long delta_jiffies = now_jiffies - scd->tick_jiffies;
u64 clock = scd->clock;
u64 min_clock, max_clock;
- s64 delta = now - scd->prev_raw;
+ s64 delta = now - scd->tick_raw;

WARN_ON_ONCE(!irqs_disabled());
-
- /*
- * At schedule tick the clock can be just under the gtod. We don't
- * want to push it too prematurely.
- */
- min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
- if (min_clock > TICK_NSEC)
- min_clock -= TICK_NSEC / 2;
+ min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;

if (unlikely(delta < 0)) {
clock++;
goto out;
}

- /*
- * The clock must stay within a jiffie of the gtod.
- * But since we may be at the start of a jiffy or the end of one
- * we add another jiffy buffer.
- */
- max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
-
- delta *= scd->multi;
- delta >>= MULTI_SHIFT;
+ max_clock = min_clock + TICK_NSEC;

- if (unlikely(clock + delta > max_clock) && check_max(scd)) {
+ if (unlikely(clock + delta > max_clock)) {
if (clock < max_clock)
clock = max_clock;
else
@@ -180,12 +128,10 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim
if (unlikely(clock < min_clock))
clock = min_clock;

- if (time)
- *time = clock;
- else {
- scd->prev_raw = now;
- scd->clock = clock;
- }
+ scd->tick_jiffies = now_jiffies;
+ scd->clock = clock;
+
+ return clock;
}

static void lock_double_clock(struct sched_clock_data *data1,
@@ -203,7 +149,7 @@ static void lock_double_clock(struct sched_clock_data *data1,
u64 sched_clock_cpu(int cpu)
{
struct sched_clock_data *scd = cpu_sdc(cpu);
- u64 now, clock;
+ u64 now, clock, this_clock, remote_clock;

if (unlikely(!sched_clock_running))
return 0ull;
@@ -212,43 +158,44 @@ u64 sched_clock_cpu(int cpu)
now = sched_clock();

if (cpu != raw_smp_processor_id()) {
- /*
- * in order to update a remote cpu's clock based on our
- * unstable raw time rebase it against:
- * tick_raw (offset between raw counters)
- * tick_gotd (tick offset between cpus)
- */
struct sched_clock_data *my_scd = this_scd();

lock_double_clock(scd, my_scd);

- now -= my_scd->tick_raw;
- now += scd->tick_raw;
+ this_clock = __update_sched_clock(my_scd, now);
+ remote_clock = scd->clock;

- now += my_scd->tick_gtod;
- now -= scd->tick_gtod;
+ /*
+ * Use the opportunity that we have both locks
+ * taken to couple the two clocks: we take the
+ * larger time as the latest time for both
+ * runqueues. (this creates monotonic movement)
+ */
+ if (likely(remote_clock < this_clock)) {
+ clock = this_clock;
+ scd->clock = clock;
+ } else {
+ /*
+ * Should be rare, but possible:
+ */
+ clock = remote_clock;
+ my_scd->clock = remote_clock;
+ }

__raw_spin_unlock(&my_scd->lock);
-
- __update_sched_clock(scd, now, &clock);
-
- __raw_spin_unlock(&scd->lock);
-
} else {
__raw_spin_lock(&scd->lock);
- __update_sched_clock(scd, now, NULL);
- clock = scd->clock;
- __raw_spin_unlock(&scd->lock);
+ clock = __update_sched_clock(scd, now);
}

+ __raw_spin_unlock(&scd->lock);
+
return clock;
}

void sched_clock_tick(void)
{
struct sched_clock_data *scd = this_scd();
- unsigned long now_jiffies = jiffies;
- s64 mult, delta_gtod, delta_raw;
u64 now, now_gtod;

if (unlikely(!sched_clock_running))
@@ -260,29 +207,14 @@ void sched_clock_tick(void)
now = sched_clock();

__raw_spin_lock(&scd->lock);
- __update_sched_clock(scd, now, NULL);
+ __update_sched_clock(scd, now);
/*
* update tick_gtod after __update_sched_clock() because that will
* already observe 1 new jiffy; adding a new tick_gtod to that would
* increase the clock 2 jiffies.
*/
- delta_gtod = now_gtod - scd->tick_gtod;
- delta_raw = now - scd->tick_raw;
-
- if ((long)delta_raw > 0) {
- mult = delta_gtod << MULTI_SHIFT;
- do_div(mult, delta_raw);
- scd->multi = mult;
- if (scd->multi > MAX_MULTI)
- scd->multi = MAX_MULTI;
- else if (scd->multi < MIN_MULTI)
- scd->multi = MIN_MULTI;
- } else
- scd->multi = 1 << MULTI_SHIFT;
-
scd->tick_raw = now;
scd->tick_gtod = now_gtod;
- scd->tick_jiffies = now_jiffies;
__raw_spin_unlock(&scd->lock);
}

@@ -301,7 +233,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
void sched_clock_idle_wakeup_event(u64 delta_ns)
{
struct sched_clock_data *scd = this_scd();
- u64 now = sched_clock();

/*
* Override the previous timestamp and ignore all
@@ -310,27 +241,30 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
* rq clock:
*/
__raw_spin_lock(&scd->lock);
- scd->prev_raw = now;
scd->clock += delta_ns;
- scd->multi = 1 << MULTI_SHIFT;
__raw_spin_unlock(&scd->lock);

touch_softlockup_watchdog();
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);

-#endif
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */

-/*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
+void sched_clock_init(void)
{
- return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+ sched_clock_running = 1;
}

+u64 sched_clock_cpu(int cpu)
+{
+ if (unlikely(!sched_clock_running))
+ return 0;
+
+ return sched_clock();
+}
+
+#endif
+
unsigned long long cpu_clock(int cpu)
{
unsigned long long clock;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index cf2cd6c..fb8994c 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -899,7 +899,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
* doesn't make sense. Rely on vruntime for fairness.
*/
if (rq->curr != p)
- delta = max(10000LL, delta);
+ delta = max_t(s64, 10000LL, delta);

hrtick_start(rq, delta);
}
@@ -1442,18 +1442,23 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
struct task_struct *p = NULL;
struct sched_entity *se;

- while (next != &cfs_rq->tasks) {
+ if (next == &cfs_rq->tasks)
+ return NULL;
+
+ /* Skip over entities that are not tasks */
+ do {
se = list_entry(next, struct sched_entity, group_node);
next = next->next;
+ } while (next != &cfs_rq->tasks && !entity_is_task(se));

- /* Skip over entities that are not tasks */
- if (entity_is_task(se)) {
- p = task_of(se);
- break;
- }
- }
+ if (next == &cfs_rq->tasks)
+ return NULL;

cfs_rq->balance_iterator = next;
+
+ if (entity_is_task(se))
+ p = task_of(se);
+
return p;
}

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 825b4c0..f5da526 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -289,7 +289,6 @@ void tick_nohz_stop_sched_tick(int inidle)
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
rcu_enter_nohz();
- sched_clock_tick_stop(cpu);
}

/*
@@ -392,7 +391,6 @@ void tick_nohz_restart_sched_tick(void)
select_nohz_load_balancer(0);
now = ktime_get();
tick_do_update_jiffies64(now);
- sched_clock_tick_start(cpu);
cpu_clear(cpu, nohz_cpu_mask);

/*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/