Merge branch 'for-2.6.25' of master.kernel.org:/pub/scm/linux/kernel/git/arnd/cell-2.6 into merge

10 files changed, 270 insertions, 40 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 2eeea9a1424..10c4930c2bb 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -170,7 +170,9 @@ void audit_panic(const char *message)
 			printk(KERN_ERR "audit: %s\n", message);
 		break;
 	case AUDIT_FAIL_PANIC:
-		panic("audit: %s\n", message);
+		/* test audit_pid since printk is always losey, why bother? */
+		if (audit_pid)
+			panic("audit: %s\n", message);
 		break;
 	}
 }
@@ -352,6 +354,7 @@ static int kauditd_thread(void *dummy)
 				if (err < 0) {
 					BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */
 					printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
+					audit_log_lost("auditd dissapeared\n");
 					audit_pid = 0;
 				}
 			} else {
@@ -1350,17 +1353,19 @@ void audit_log_end(struct audit_buffer *ab)
 	if (!audit_rate_check()) {
 		audit_log_lost("rate limit exceeded");
 	} else {
+		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
 		if (audit_pid) {
-			struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
 			nlh->nlmsg_len = ab->skb->len - NLMSG_SPACE(0);
 			skb_queue_tail(&audit_skb_queue, ab->skb);
 			ab->skb = NULL;
 			wake_up_interruptible(&kauditd_wait);
-		} else if (printk_ratelimit()) {
-			struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
-			printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, ab->skb->data + NLMSG_SPACE(0));
-		} else {
-			audit_log_lost("printk limit exceeded\n");
+		} else if (nlh->nlmsg_type != AUDIT_EOE) {
+			if (printk_ratelimit()) {
+				printk(KERN_NOTICE "type=%d %s\n",
+					nlh->nlmsg_type,
+					ab->skb->data + NLMSG_SPACE(0));
+			} else
+				audit_log_lost("printk limit exceeded\n");
 		}
 	}
 	audit_buffer_free(ab);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 2087d6de67e..782262e4107 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1070,7 +1070,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 		 * so we can be sure nothing was lost.
 		 */
 		if ((i == 0) && (too_long))
-			audit_log_format(*ab, "a%d_len=%ld ", arg_num,
+			audit_log_format(*ab, "a%d_len=%zu ", arg_num,
 					 has_cntl ? 2*len : len);
 
 		/*
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 3574379f4d6..81a4e4a3f08 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -779,6 +779,10 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * parallel walking of the hash-list safe:
 	 */
 	list_add_tail_rcu(&class->hash_entry, hash_head);
+	/*
+	 * Add it to the global list of classes:
+	 */
+	list_add_tail_rcu(&class->lock_entry, &all_lock_classes);
 
 	if (verbose(class)) {
 		graph_unlock();
@@ -2282,10 +2286,6 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 		break;
 	case LOCK_USED:
-		/*
-		 * Add it to the global list of classes:
-		 */
-		list_add_tail_rcu(&this->class->lock_entry, &all_lock_classes);
 		debug_atomic_dec(&nr_unused_locks);
 		break;
 	default:
diff --git a/kernel/printk.c b/kernel/printk.c
index bee36100f11..9adc2a473e6 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -666,7 +666,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	}
 	/* Emit the output into the temporary buffer */
 	printed_len += vscnprintf(printk_buf + printed_len,
-				  sizeof(printk_buf), fmt, args);
+				  sizeof(printk_buf) - printed_len, fmt, args);
 
 	/*
 	 * Copy the output into log_buf.  If the caller didn't provide
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 987cfb7ade8..e9517014b57 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -23,6 +23,10 @@
  *		to Suparna Bhattacharya for pushing me completely away
  *		from atomic instructions on the read side.
  *
+ *  - Added handling of Dynamic Ticks
+ *      Copyright 2007 - Paul E. Mckenney <paulmck@us.ibm.com>
+ *                     - Steven Rostedt <srostedt@redhat.com>
+ *
  * Papers:  http://www.rdrop.com/users/paulmck/RCU
  *
  * Design Document: http://lwn.net/Articles/253651/
@@ -409,6 +413,212 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
 	}
 }
 
+#ifdef CONFIG_NO_HZ
+
+DEFINE_PER_CPU(long, dynticks_progress_counter) = 1;
+static DEFINE_PER_CPU(long, rcu_dyntick_snapshot);
+static DEFINE_PER_CPU(int, rcu_update_flag);
+
+/**
+ * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
+ *
+ * If the CPU was idle with dynamic ticks active, this updates the
+ * dynticks_progress_counter to let the RCU handling know that the
+ * CPU is active.
+ */
+void rcu_irq_enter(void)
+{
+	int cpu = smp_processor_id();
+
+	if (per_cpu(rcu_update_flag, cpu))
+		per_cpu(rcu_update_flag, cpu)++;
+
+	/*
+	 * Only update if we are coming from a stopped ticks mode
+	 * (dynticks_progress_counter is even).
+	 */
+	if (!in_interrupt() &&
+	    (per_cpu(dynticks_progress_counter, cpu) & 0x1) == 0) {
+		/*
+		 * The following might seem like we could have a race
+		 * with NMI/SMIs. But this really isn't a problem.
+		 * Here we do a read/modify/write, and the race happens
+		 * when an NMI/SMI comes in after the read and before
+		 * the write. But NMI/SMIs will increment this counter
+		 * twice before returning, so the zero bit will not
+		 * be corrupted by the NMI/SMI which is the most important
+		 * part.
+		 *
+		 * The only thing is that we would bring back the counter
+		 * to a postion that it was in during the NMI/SMI.
+		 * But the zero bit would be set, so the rest of the
+		 * counter would again be ignored.
+		 *
+		 * On return from the IRQ, the counter may have the zero
+		 * bit be 0 and the counter the same as the return from
+		 * the NMI/SMI. If the state machine was so unlucky to
+		 * see that, it still doesn't matter, since all
+		 * RCU read-side critical sections on this CPU would
+		 * have already completed.
+		 */
+		per_cpu(dynticks_progress_counter, cpu)++;
+		/*
+		 * The following memory barrier ensures that any
+		 * rcu_read_lock() primitives in the irq handler
+		 * are seen by other CPUs to follow the above
+		 * increment to dynticks_progress_counter. This is
+		 * required in order for other CPUs to correctly
+		 * determine when it is safe to advance the RCU
+		 * grace-period state machine.
+		 */
+		smp_mb(); /* see above block comment. */
+		/*
+		 * Since we can't determine the dynamic tick mode from
+		 * the dynticks_progress_counter after this routine,
+		 * we use a second flag to acknowledge that we came
+		 * from an idle state with ticks stopped.
+		 */
+		per_cpu(rcu_update_flag, cpu)++;
+		/*
+		 * If we take an NMI/SMI now, they will also increment
+		 * the rcu_update_flag, and will not update the
+		 * dynticks_progress_counter on exit. That is for
+		 * this IRQ to do.
+		 */
+	}
+}
+
+/**
+ * rcu_irq_exit - Called from exiting Hard irq context.
+ *
+ * If the CPU was idle with dynamic ticks active, update the
+ * dynticks_progress_counter to put let the RCU handling be
+ * aware that the CPU is going back to idle with no ticks.
+ */
+void rcu_irq_exit(void)
+{
+	int cpu = smp_processor_id();
+
+	/*
+	 * rcu_update_flag is set if we interrupted the CPU
+	 * when it was idle with ticks stopped.
+	 * Once this occurs, we keep track of interrupt nesting
+	 * because a NMI/SMI could also come in, and we still
+	 * only want the IRQ that started the increment of the
+	 * dynticks_progress_counter to be the one that modifies
+	 * it on exit.
+	 */
+	if (per_cpu(rcu_update_flag, cpu)) {
+		if (--per_cpu(rcu_update_flag, cpu))
+			return;
+
+		/* This must match the interrupt nesting */
+		WARN_ON(in_interrupt());
+
+		/*
+		 * If an NMI/SMI happens now we are still
+		 * protected by the dynticks_progress_counter being odd.
+		 */
+
+		/*
+		 * The following memory barrier ensures that any
+		 * rcu_read_unlock() primitives in the irq handler
+		 * are seen by other CPUs to preceed the following
+		 * increment to dynticks_progress_counter. This
+		 * is required in order for other CPUs to determine
+		 * when it is safe to advance the RCU grace-period
+		 * state machine.
+		 */
+		smp_mb(); /* see above block comment. */
+		per_cpu(dynticks_progress_counter, cpu)++;
+		WARN_ON(per_cpu(dynticks_progress_counter, cpu) & 0x1);
+	}
+}
+
+static void dyntick_save_progress_counter(int cpu)
+{
+	per_cpu(rcu_dyntick_snapshot, cpu) =
+		per_cpu(dynticks_progress_counter, cpu);
+}
+
+static inline int
+rcu_try_flip_waitack_needed(int cpu)
+{
+	long curr;
+	long snap;
+
+	curr = per_cpu(dynticks_progress_counter, cpu);
+	snap = per_cpu(rcu_dyntick_snapshot, cpu);
+	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+	/*
+	 * If the CPU remained in dynticks mode for the entire time
+	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
+	 * then it cannot be in the middle of an rcu_read_lock(), so
+	 * the next rcu_read_lock() it executes must use the new value
+	 * of the counter.  So we can safely pretend that this CPU
+	 * already acknowledged the counter.
+	 */
+
+	if ((curr == snap) && ((curr & 0x1) == 0))
+		return 0;
+
+	/*
+	 * If the CPU passed through or entered a dynticks idle phase with
+	 * no active irq handlers, then, as above, we can safely pretend
+	 * that this CPU already acknowledged the counter.
+	 */
+
+	if ((curr - snap) > 2 || (snap & 0x1) == 0)
+		return 0;
+
+	/* We need this CPU to explicitly acknowledge the counter flip. */
+
+	return 1;
+}
+
+static inline int
+rcu_try_flip_waitmb_needed(int cpu)
+{
+	long curr;
+	long snap;
+
+	curr = per_cpu(dynticks_progress_counter, cpu);
+	snap = per_cpu(rcu_dyntick_snapshot, cpu);
+	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+	/*
+	 * If the CPU remained in dynticks mode for the entire time
+	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
+	 * then it cannot have executed an RCU read-side critical section
+	 * during that time, so there is no need for it to execute a
+	 * memory barrier.
+	 */
+
+	if ((curr == snap) && ((curr & 0x1) == 0))
+		return 0;
+
+	/*
+	 * If the CPU either entered or exited an outermost interrupt,
+	 * SMI, NMI, or whatever handler, then we know that it executed
+	 * a memory barrier when doing so.  So we don't need another one.
+	 */
+	if (curr != snap)
+		return 0;
+
+	/* We need the CPU to execute a memory barrier. */
+
+	return 1;
+}
+
+#else /* !CONFIG_NO_HZ */
+
+# define dyntick_save_progress_counter(cpu)	do { } while (0)
+# define rcu_try_flip_waitack_needed(cpu)	(1)
+# define rcu_try_flip_waitmb_needed(cpu)	(1)
+
+#endif /* CONFIG_NO_HZ */
+
 /*
  * Get here when RCU is idle.  Decide whether we need to
  * move out of idle state, and return non-zero if so.
@@ -447,8 +657,10 @@ rcu_try_flip_idle(void)
 
 	/* Now ask each CPU for acknowledgement of the flip. */
 
-	for_each_cpu_mask(cpu, rcu_cpu_online_map)
+	for_each_cpu_mask(cpu, rcu_cpu_online_map) {
 		per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
+		dyntick_save_progress_counter(cpu);
+	}
 
 	return 1;
 }
@@ -464,7 +676,8 @@ rcu_try_flip_waitack(void)
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
 	for_each_cpu_mask(cpu, rcu_cpu_online_map)
-		if (per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
+		if (rcu_try_flip_waitack_needed(cpu) &&
+		    per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
 			RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
 			return 0;
 		}
@@ -509,8 +722,10 @@ rcu_try_flip_waitzero(void)
 	smp_mb();  /*  ^^^^^^^^^^^^ */
 
 	/* Call for a memory barrier from each CPU. */
-	for_each_cpu_mask(cpu, rcu_cpu_online_map)
+	for_each_cpu_mask(cpu, rcu_cpu_online_map) {
 		per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
+		dyntick_save_progress_counter(cpu);
+	}
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_z2);
 	return 1;
@@ -528,7 +743,8 @@ rcu_try_flip_waitmb(void)
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
 	for_each_cpu_mask(cpu, rcu_cpu_online_map)
-		if (per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
+		if (rcu_try_flip_waitmb_needed(cpu) &&
+		    per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
 			RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
 			return 0;
 		}
@@ -702,8 +918,9 @@ void rcu_offline_cpu(int cpu)
 	 * fix.
 	 */
 
+	local_irq_save(flags);
 	rdp = RCU_DATA_ME();
-	spin_lock_irqsave(&rdp->lock, flags);
+	spin_lock(&rdp->lock);
 	*rdp->nexttail = list;
 	if (list)
 		rdp->nexttail = tail;
@@ -735,9 +952,11 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 {
 	unsigned long flags;
 	struct rcu_head *next, *list;
-	struct rcu_data *rdp = RCU_DATA_ME();
+	struct rcu_data *rdp;
 
-	spin_lock_irqsave(&rdp->lock, flags);
+	local_irq_save(flags);
+	rdp = RCU_DATA_ME();
+	spin_lock(&rdp->lock);
 	list = rdp->donelist;
 	if (list == NULL) {
 		spin_unlock_irqrestore(&rdp->lock, flags);
diff --git a/kernel/sched.c b/kernel/sched.c
index b387a8de26a..f06950c8a6c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -668,6 +668,8 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
  */
 unsigned int sysctl_sched_rt_period = 1000000;
 
+static __read_mostly int scheduler_running;
+
 /*
  * part of the period that we allow rt tasks to run in us.
  * default: 0.95s
@@ -689,14 +691,16 @@ unsigned long long cpu_clock(int cpu)
 	unsigned long flags;
 	struct rq *rq;
 
-	local_irq_save(flags);
-	rq = cpu_rq(cpu);
 	/*
 	 * Only call sched_clock() if the scheduler has already been
 	 * initialized (some code might call cpu_clock() very early):
 	 */
-	if (rq->idle)
-		update_rq_clock(rq);
+	if (unlikely(!scheduler_running))
+		return 0;
+
+	local_irq_save(flags);
+	rq = cpu_rq(cpu);
+	update_rq_clock(rq);
 	now = rq->clock;
 	local_irq_restore(flags);
 
@@ -3885,7 +3889,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 asmlinkage void __sched schedule(void)
 {
 	struct task_struct *prev, *next;
-	long *switch_count;
+	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
@@ -7284,6 +7288,8 @@ void __init sched_init(void)
 	 * During early bootup we pretend to be a normal task:
 	 */
 	current->sched_class = &fair_sched_class;
+
+	scheduler_running = 1;
 }
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6c091d6e159..c8e6492c592 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -202,17 +202,12 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 
 static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
-	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
-	struct sched_entity *se = NULL;
-	struct rb_node *parent;
+	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
 
-	while (*link) {
-		parent = *link;
-		se = rb_entry(parent, struct sched_entity, run_node);
-		link = &parent->rb_right;
-	}
+	if (!last)
+		return NULL;
 
-	return se;
+	return rb_entry(last, struct sched_entity, run_node);
 }
 
 /**************************************************************
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 5b3aea5f471..31e9f2a4792 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -313,6 +313,7 @@ void irq_exit(void)
 	/* Make sure that timer wheel updates are propagated */
 	if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
 		tick_nohz_stop_sched_tick();
+	rcu_irq_exit();
 #endif
 	preempt_enable_no_resched();
 }
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 7c2da88db4e..01b6522fd92 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -216,26 +216,27 @@ static int watchdog(void *__bind_cpu)
 	/* initialize timestamp */
 	touch_softlockup_watchdog();
 
+	set_current_state(TASK_INTERRUPTIBLE);
 	/*
 	 * Run briefly once per second to reset the softlockup timestamp.
 	 * If this gets delayed for more than 60 seconds then the
 	 * debug-printout triggers in softlockup_tick().
 	 */
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
 		touch_softlockup_watchdog();
 		schedule();
 
 		if (kthread_should_stop())
 			break;
 
-		if (this_cpu != check_cpu)
-			continue;
-
-		if (sysctl_hung_task_timeout_secs)
-			check_hung_uninterruptible_tasks(this_cpu);
+		if (this_cpu == check_cpu) {
+			if (sysctl_hung_task_timeout_secs)
+				check_hung_uninterruptible_tasks(this_cpu);
+		}
 
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
+	__set_current_state(TASK_RUNNING);
 
 	return 0;
 }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index fa9bb73dbdb..2968298f8f3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -282,6 +282,7 @@ void tick_nohz_stop_sched_tick(void)
 			ts->idle_tick = ts->sched_timer.expires;
 			ts->tick_stopped = 1;
 			ts->idle_jiffies = last_jiffies;
+			rcu_enter_nohz();
 		}
 
 		/*
@@ -375,6 +376,8 @@ void tick_nohz_restart_sched_tick(void)
 		return;
 	}
 
+	rcu_exit_nohz();
+
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
 	now = ktime_get();