Merge tag 'v3.12-rc3' into timers/core

Merge Linux 3.12-rc3 - refresh the tree with the latest fixes before merging new bits.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 126 insertions, 29 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d0..7b0e23a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			sleep_time = timeout_start + audit_backlog_wait_time -
 					jiffies;
-			if ((long)sleep_time > 0)
+			if ((long)sleep_time > 0) {
 				wait_for_auditd(sleep_time);
-			continue;
+				continue;
+			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
 			printk(KERN_WARNING
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 247091b..859c8df 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -51,6 +51,15 @@ void context_tracking_user_enter(void)
 	unsigned long flags;
 
 	/*
+	 * Repeat the user_enter() check here because some archs may be calling
+	 * this from asm and if no CPU needs context tracking, they shouldn't
+	 * go further. Repeat the check here until they support the static key
+	 * check.
+	 */
+	if (!static_key_false(&context_tracking_enabled))
+		return;
+
+	/*
 	 * Some contexts may involve an exception occuring in an irq,
 	 * leading to that nesting:
 	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
@@ -151,6 +160,9 @@ void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
+	if (!static_key_false(&context_tracking_enabled))
+		return;
+
 	if (in_interrupt())
 		return;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b6..cb4238e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
 	*running = ctx_time - event->tstamp_running;
 }
 
+static void perf_event_init_userpage(struct perf_event *event)
+{
+	struct perf_event_mmap_page *userpg;
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	if (!rb)
+		goto unlock;
+
+	userpg = rb->user_page;
+
+	/* Allow new userspace to detect that bit 0 is deprecated */
+	userpg->cap_bit0_is_deprecated = 1;
+	userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+	rcu_read_unlock();
+}
+
 void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
@@ -4044,6 +4064,7 @@ again:
 	ring_buffer_attach(event, rb);
 	rcu_assign_pointer(event->rb, rb);
 
+	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
 
 unlock:
diff --git a/kernel/params.c b/kernel/params.c
index 81c4e78..c00d5b5 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -254,11 +254,11 @@ int parse_args(const char *doing,
 
 
 STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
 STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
 STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
 STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 269ed93..f813b34 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid);
 #endif
 enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
 
-int reboot_default;
+/*
+ * This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+int reboot_default = 1;
 int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e076bdd..1965599 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -124,7 +124,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		SEQ_printf(m, " ");
 
 	SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
-		p->comm, p->pid,
+		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
@@ -289,7 +289,7 @@ do {									\
 	P(nr_load_updates);
 	P(nr_uninterruptible);
 	PN(next_balance);
-	P(curr->pid);
+	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
 	PN(clock);
 	P(cpu_load[0]);
 	P(cpu_load[1]);
@@ -492,7 +492,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 {
 	unsigned long nr_switches;
 
-	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid,
+	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
 						get_nr_threads(p));
 	SEQ_printf(m,
 		"---------------------------------------------------------"
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9b3fe1c..7c70201 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	}
 
 	if (!se) {
-		cfs_rq->h_load = rq->avg.load_avg_contrib;
+		cfs_rq->h_load = cfs_rq->runnable_load_avg;
 		cfs_rq->last_h_load_update = now;
 	}
 
@@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 		(busiest->load_per_task * SCHED_POWER_SCALE) /
 		busiest->group_power;
 
-	if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >=
-	    (scaled_busy_load_per_task * imbn)) {
+	if (busiest->avg_load + scaled_busy_load_per_task >=
+	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
 		env->imbalance = busiest->load_per_task;
 		return;
 	}
@@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * max load less than avg load(as we skip the groups at or below
 	 * its cpu_power, while calculating max_load..)
 	 */
-	if (busiest->avg_load < sds->avg_load) {
+	if (busiest->avg_load <= sds->avg_load ||
+	    local->avg_load >= sds->avg_load) {
 		env->imbalance = 0;
 		return fix_small_imbalance(env, sds);
 	}
@@ -5928,11 +5929,15 @@ static void task_fork_fair(struct task_struct *p)
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
 
-	if (unlikely(task_cpu(p) != this_cpu)) {
-		rcu_read_lock();
-		__set_task_cpu(p, this_cpu);
-		rcu_read_unlock();
-	}
+	/*
+	 * Not only the cpu but also the task_group of the parent might have
+	 * been changed after parent->se.parent,cfs_rq were copied to
+	 * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
+	 * of child point to valid ones.
+	 */
+	rcu_read_lock();
+	__set_task_cpu(p, this_cpu);
+	rcu_read_unlock();
 
 	update_curr(cfs_rq);
 
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 5aef494..c7edee7 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -104,8 +104,9 @@ static inline void sched_info_queued(struct task_struct *t)
 }
 
 /*
- * Called when a process ceases being the active-running process, either
- * voluntarily or involuntarily.  Now we can calculate how long we ran.
+ * Called when a process ceases being the active-running process involuntarily
+ * due, typically, to expiring its time slice (this may also be called when
+ * switching to the idle task).  Now we can calculate how long we ran.
  * Also, if the process is still in the TASK_RUNNING state, call
  * sched_info_queued() to mark that it has now again started waiting on
  * the runqueue.
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index ab1fa7c..af8d1d4 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -517,13 +517,13 @@ static void sync_cmos_clock(struct work_struct *work)
 	schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
 }
 
-static void notify_cmos_timer(void)
+void ntp_notify_cmos_timer(void)
 {
 	schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
-static inline void notify_cmos_timer(void) { }
+void ntp_notify_cmos_timer(void) { }
 #endif
 
 
@@ -688,8 +688,6 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
 	if (!(time_status & STA_NANO))
 		txc->time.tv_usec /= NSEC_PER_USEC;
 
-	notify_cmos_timer();
-
 	return result;
 }
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 48b9fff..947ba25 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1703,6 +1703,8 @@ int do_adjtimex(struct timex *txc)
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	ntp_notify_cmos_timer();
+
 	return ret;
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 51c4f34..4431610 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = {
 	.unpark			= watchdog_enable,
 };
 
-static int watchdog_enable_all_cpus(void)
+static void restart_watchdog_hrtimer(void *info)
+{
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	int ret;
+
+	/*
+	 * No need to cancel and restart hrtimer if it is currently executing
+	 * because it will reprogram itself with the new period now.
+	 * We should never see it unqueued here because we are running per-cpu
+	 * with interrupts disabled.
+	 */
+	ret = hrtimer_try_to_cancel(hrtimer);
+	if (ret == 1)
+		hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+				HRTIMER_MODE_REL_PINNED);
+}
+
+static void update_timers(int cpu)
+{
+	struct call_single_data data = {.func = restart_watchdog_hrtimer};
+	/*
+	 * Make sure that perf event counter will adopt to a new
+	 * sampling period. Updating the sampling period directly would
+	 * be much nicer but we do not have an API for that now so
+	 * let's use a big hammer.
+	 * Hrtimer will adopt the new period on the next tick but this
+	 * might be late already so we have to restart the timer as well.
+	 */
+	watchdog_nmi_disable(cpu);
+	__smp_call_function_single(cpu, &data, 1);
+	watchdog_nmi_enable(cpu);
+}
+
+static void update_timers_all_cpus(void)
+{
+	int cpu;
+
+	get_online_cpus();
+	preempt_disable();
+	for_each_online_cpu(cpu)
+		update_timers(cpu);
+	preempt_enable();
+	put_online_cpus();
+}
+
+static int watchdog_enable_all_cpus(bool sample_period_changed)
 {
 	int err = 0;
 
@@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void)
 			pr_err("Failed to create watchdog threads, disabled\n");
 		else
 			watchdog_running = 1;
+	} else if (sample_period_changed) {
+		update_timers_all_cpus();
 	}
 
 	return err;
@@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old_thresh, old_enabled;
+	static DEFINE_MUTEX(watchdog_proc_mutex);
 
+	mutex_lock(&watchdog_proc_mutex);
 	old_thresh = ACCESS_ONCE(watchdog_thresh);
 	old_enabled = ACCESS_ONCE(watchdog_user_enabled);
 
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (err || !write)
-		return err;
+		goto out;
 
 	set_sample_period();
 	/*
@@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 	 * watchdog_*_all_cpus() function takes care of this.
 	 */
 	if (watchdog_user_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
+		err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
 	else
 		watchdog_disable_all_cpus();
 
@@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		watchdog_thresh = old_thresh;
 		watchdog_user_enabled = old_enabled;
 	}
-
+out:
+	mutex_unlock(&watchdog_proc_mutex);
 	return err;
 }
 #endif /* CONFIG_SYSCTL */
@@ -554,5 +604,5 @@ void __init lockup_detector_init(void)
 	set_sample_period();
 
 	if (watchdog_user_enabled)
-		watchdog_enable_all_cpus();
+		watchdog_enable_all_cpus(false);
 }