Merge ../linux-2.6

5 files changed, 134 insertions, 21 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 5ae51f1bc7c8..14bc9cfa6399 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -505,6 +505,41 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 	return rem;
 }
 
+#ifdef CONFIG_NO_IDLE_HZ
+/**
+ * hrtimer_get_next_event - get the time until next expiry event
+ *
+ * Returns the delta to the next expiry event or KTIME_MAX if no timer
+ * is pending.
+ */
+ktime_t hrtimer_get_next_event(void)
+{
+	struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
+		struct hrtimer *timer;
+
+		spin_lock_irqsave(&base->lock, flags);
+		if (!base->first) {
+			spin_unlock_irqrestore(&base->lock, flags);
+			continue;
+		}
+		timer = rb_entry(base->first, struct hrtimer, node);
+		delta.tv64 = timer->expires.tv64;
+		spin_unlock_irqrestore(&base->lock, flags);
+		delta = ktime_sub(delta, base->get_time());
+		if (delta.tv64 < mindelta.tv64)
+			mindelta.tv64 = delta.tv64;
+	}
+	if (mindelta.tv64 < 0)
+		mindelta.tv64 = 0;
+	return mindelta;
+}
+#endif
+
 /**
  * hrtimer_init - initialize a timer to the given clock
  *
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 0cf8146bd585..8cf15a569fcd 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -67,7 +67,43 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 
 /* Fake initialization required by compiler */
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
-static int maxbatch = 10000;
+static int blimit = 10;
+static int qhimark = 10000;
+static int qlowmark = 100;
+#ifdef CONFIG_SMP
+static int rsinterval = 1000;
+#endif
+
+static atomic_t rcu_barrier_cpu_count;
+static struct semaphore rcu_barrier_sema;
+static struct completion rcu_barrier_completion;
+
+#ifdef CONFIG_SMP
+static void force_quiescent_state(struct rcu_data *rdp,
+			struct rcu_ctrlblk *rcp)
+{
+	int cpu;
+	cpumask_t cpumask;
+	set_need_resched();
+	if (unlikely(rdp->qlen - rdp->last_rs_qlen > rsinterval)) {
+		rdp->last_rs_qlen = rdp->qlen;
+		/*
+		 * Don't send IPI to itself. With irqs disabled,
+		 * rdp->cpu is the current cpu.
+		 */
+		cpumask = rcp->cpumask;
+		cpu_clear(rdp->cpu, cpumask);
+		for_each_cpu_mask(cpu, cpumask)
+			smp_send_reschedule(cpu);
+	}
+}
+#else
+static inline void force_quiescent_state(struct rcu_data *rdp,
+			struct rcu_ctrlblk *rcp)
+{
+	set_need_resched();
+}
+#endif
 
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
@@ -92,17 +128,13 @@ void fastcall call_rcu(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
-
-	if (unlikely(++rdp->count > 10000))
-		set_need_resched();
-
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = INT_MAX;
+		force_quiescent_state(rdp, &rcu_ctrlblk);
+	}
 	local_irq_restore(flags);
 }
 
-static atomic_t rcu_barrier_cpu_count;
-static struct semaphore rcu_barrier_sema;
-static struct completion rcu_barrier_completion;
-
 /**
  * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -131,12 +163,12 @@ void fastcall call_rcu_bh(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_bh_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
-	rdp->count++;
-/*
- *  Should we directly call rcu_do_batch() here ?
- *  if (unlikely(rdp->count > 10000))
- *      rcu_do_batch(rdp);
- */
+
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = INT_MAX;
+		force_quiescent_state(rdp, &rcu_bh_ctrlblk);
+	}
+
 	local_irq_restore(flags);
 }
 
@@ -199,10 +231,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		next = rdp->donelist = list->next;
 		list->func(list);
 		list = next;
-		rdp->count--;
-		if (++count >= maxbatch)
+		rdp->qlen--;
+		if (++count >= rdp->blimit)
 			break;
 	}
+	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
+		rdp->blimit = blimit;
 	if (!rdp->donelist)
 		rdp->donetail = &rdp->donelist;
 	else
@@ -473,6 +507,7 @@ static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 	rdp->quiescbatch = rcp->completed;
 	rdp->qs_pending = 0;
 	rdp->cpu = cpu;
+	rdp->blimit = blimit;
 }
 
 static void __devinit rcu_online_cpu(int cpu)
@@ -567,7 +602,12 @@ void synchronize_kernel(void)
 	synchronize_rcu();
 }
 
-module_param(maxbatch, int, 0);
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
+#ifdef CONFIG_SMP
+module_param(rsinterval, int, 0);
+#endif
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 EXPORT_SYMBOL(call_rcu);  /* WARNING: GPL-only in April 2006. */
 EXPORT_SYMBOL(call_rcu_bh);  /* WARNING: GPL-only in April 2006. */
diff --git a/kernel/sched.c b/kernel/sched.c
index 12d291bf3379..e82c99f1db64 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4028,6 +4028,8 @@ static inline void __cond_resched(void)
 	 */
 	if (unlikely(preempt_count()))
 		return;
+	if (unlikely(system_state != SYSTEM_RUNNING))
+		return;
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		schedule();
@@ -4333,6 +4335,7 @@ void __devinit init_idle(task_t *idle, int cpu)
 	runqueue_t *rq = cpu_rq(cpu);
 	unsigned long flags;
 
+	idle->timestamp = sched_clock();
 	idle->sleep_avg = 0;
 	idle->array = NULL;
 	idle->prio = MAX_PRIO;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c05a2b7125e1..32b48e8ee36e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -50,6 +50,9 @@
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 
+extern int proc_nr_files(ctl_table *table, int write, struct file *filp,
+                     void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
@@ -124,6 +127,10 @@ extern int sysctl_hz_timer;
 extern int acct_parm[];
 #endif
 
+#ifdef CONFIG_IA64
+extern int no_unaligned_warning;
+#endif
+
 static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t,
 		       ctl_table *, void **);
 static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
@@ -663,6 +670,16 @@ static ctl_table kern_table[] = {
 		.data		= &acpi_video_flags,
 		.maxlen		= sizeof (unsigned long),
 		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+	},
+#endif
+#ifdef CONFIG_IA64
+	{
+		.ctl_name	= KERN_IA64_UNALIGNED,
+		.procname	= "ignore-unaligned-usertrap",
+		.data		= &no_unaligned_warning,
+		.maxlen		= sizeof (int),
+	 	.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
@@ -929,7 +946,7 @@ static ctl_table fs_table[] = {
 		.data		= &files_stat,
 		.maxlen		= 3*sizeof(int),
 		.mode		= 0444,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_nr_files,
 	},
 	{
 		.ctl_name	= FS_MAXFILE,
diff --git a/kernel/timer.c b/kernel/timer.c
index fe3a9a9f8328..bf7c4193b936 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -489,9 +489,21 @@ unsigned long next_timer_interrupt(void)
 	struct list_head *list;
 	struct timer_list *nte;
 	unsigned long expires;
+	unsigned long hr_expires = MAX_JIFFY_OFFSET;
+	ktime_t hr_delta;
 	tvec_t *varray[4];
 	int i, j;
 
+	hr_delta = hrtimer_get_next_event();
+	if (hr_delta.tv64 != KTIME_MAX) {
+		struct timespec tsdelta;
+		tsdelta = ktime_to_timespec(hr_delta);
+		hr_expires = timespec_to_jiffies(&tsdelta);
+		if (hr_expires < 3)
+			return hr_expires + jiffies;
+	}
+	hr_expires += jiffies;
+
 	base = &__get_cpu_var(tvec_bases);
 	spin_lock(&base->t_base.lock);
 	expires = base->timer_jiffies + (LONG_MAX >> 1);
@@ -542,6 +554,10 @@ found:
 		}
 	}
 	spin_unlock(&base->t_base.lock);
+
+	if (time_before(hr_expires, expires))
+		return hr_expires;
+
 	return expires;
 }
 #endif
@@ -925,6 +941,8 @@ static inline void update_times(void)
 void do_timer(struct pt_regs *regs)
 {
 	jiffies_64++;
+	/* prevent loading jiffies before storing new jiffies_64 value. */
+	barrier();
 	update_times();
 	softlockup_tick(regs);
 }
@@ -1351,10 +1369,10 @@ static inline u64 time_interpolator_get_cycles(unsigned int src)
 			return x();
 
 		case TIME_SOURCE_MMIO64	:
-			return readq((void __iomem *) time_interpolator->addr);
+			return readq_relaxed((void __iomem *)time_interpolator->addr);
 
 		case TIME_SOURCE_MMIO32	:
-			return readl((void __iomem *) time_interpolator->addr);
+			return readl_relaxed((void __iomem *)time_interpolator->addr);
 
 		default: return get_cycles();
 	}