Merge branch 'linus' into cpus4096

Conflicts:

	arch/x86/xen/smp.c
	kernel/sched_rt.c
	net/iucv/iucv.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>

60 files changed, 11047 insertions, 867 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 1c9938addb9..0a7ed838984 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
-	    exit.o itimer.o time.o softirq.o resource.o \
+	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
@@ -11,6 +11,18 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o
 
+CFLAGS_REMOVE_sched.o = -mno-spe
+
+ifdef CONFIG_FTRACE
+# Do not trace debug files and internal ftrace files
+CFLAGS_REMOVE_lockdep.o = -pg
+CFLAGS_REMOVE_lockdep_proc.o = -pg
+CFLAGS_REMOVE_mutex-debug.o = -pg
+CFLAGS_REMOVE_rtmutex-debug.o = -pg
+CFLAGS_REMOVE_cgroup-debug.o = -pg
+CFLAGS_REMOVE_sched_clock.o = -pg
+endif
+
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
@@ -27,7 +39,8 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
-obj-$(CONFIG_SMP) += cpu.o spinlock.o
+obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o
+obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
@@ -69,6 +82,9 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_FTRACE) += trace/
+obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_SMP) += sched_cpupri.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c
index d1a7605c5b8..a5e026bc45c 100644
--- a/kernel/backtracetest.c
+++ b/kernel/backtracetest.c
@@ -10,30 +10,73 @@
  * of the License.
  */
 
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/delay.h>
+#include <linux/stacktrace.h>
+
+static void backtrace_test_normal(void)
+{
+	printk("Testing a backtrace from process context.\n");
+	printk("The following trace is a kernel self test and not a bug!\n");
 
-static struct timer_list backtrace_timer;
+	dump_stack();
+}
 
-static void backtrace_test_timer(unsigned long data)
+static DECLARE_COMPLETION(backtrace_work);
+
+static void backtrace_test_irq_callback(unsigned long data)
+{
+	dump_stack();
+	complete(&backtrace_work);
+}
+
+static DECLARE_TASKLET(backtrace_tasklet, &backtrace_test_irq_callback, 0);
+
+static void backtrace_test_irq(void)
 {
 	printk("Testing a backtrace from irq context.\n");
 	printk("The following trace is a kernel self test and not a bug!\n");
-	dump_stack();
+
+	init_completion(&backtrace_work);
+	tasklet_schedule(&backtrace_tasklet);
+	wait_for_completion(&backtrace_work);
+}
+
+#ifdef CONFIG_STACKTRACE
+static void backtrace_test_saved(void)
+{
+	struct stack_trace trace;
+	unsigned long entries[8];
+
+	printk("Testing a saved backtrace.\n");
+	printk("The following trace is a kernel self test and not a bug!\n");
+
+	trace.nr_entries = 0;
+	trace.max_entries = ARRAY_SIZE(entries);
+	trace.entries = entries;
+	trace.skip = 0;
+
+	save_stack_trace(&trace);
+	print_stack_trace(&trace, 0);
+}
+#else
+static void backtrace_test_saved(void)
+{
+	printk("Saved backtrace test skipped.\n");
 }
+#endif
+
 static int backtrace_regression_test(void)
 {
 	printk("====[ backtrace testing ]===========\n");
-	printk("Testing a backtrace from process context.\n");
-	printk("The following trace is a kernel self test and not a bug!\n");
-	dump_stack();
 
-	init_timer(&backtrace_timer);
-	backtrace_timer.function = backtrace_test_timer;
-	mod_timer(&backtrace_timer, jiffies + 10);
+	backtrace_test_normal();
+	backtrace_test_irq();
+	backtrace_test_saved();
 
-	msleep(10);
 	printk("====[ end of backtrace testing ]====\n");
 	return 0;
 }
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 50ae922c602..b21ba7e9036 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -15,6 +15,28 @@
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 
+/*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+cpumask_t cpu_present_map __read_mostly;
+EXPORT_SYMBOL(cpu_present_map);
+
+#ifndef CONFIG_SMP
+
+/*
+ * Represents all cpu's that are currently online.
+ */
+cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_online_map);
+
+cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_possible_map);
+
+#else /* CONFIG_SMP */
+
 /* Serializes the updates to cpu_online_map, cpu_present_map */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
@@ -403,3 +425,5 @@ out:
 	cpu_maps_update_done();
 }
 #endif /* CONFIG_PM_SLEEP_SMP */
+
+#endif /* CONFIG_SMP */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9fceb97e989..459d601947a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1194,6 +1194,15 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 
 	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
+	if (tsk->flags & PF_THREAD_BOUND) {
+		cpumask_t mask;
+
+		mutex_lock(&callback_mutex);
+		mask = cs->cpus_allowed;
+		mutex_unlock(&callback_mutex);
+		if (!cpus_equal(tsk->cpus_allowed, mask))
+			return -EINVAL;
+	}
 
 	return security_task_setscheduler(tsk, 0, NULL);
 }
@@ -1207,11 +1216,14 @@ static void cpuset_attach(struct cgroup_subsys *ss,
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
+	int err;
 
 	mutex_lock(&callback_mutex);
 	guarantee_online_cpus(cs, &cpus);
-	set_cpus_allowed_ptr(tsk, &cpus);
+	err = set_cpus_allowed_ptr(tsk, &cpus);
 	mutex_unlock(&callback_mutex);
+	if (err)
+		return;
 
 	from = oldcs->mems_allowed;
 	to = cs->mems_allowed;
@@ -1882,7 +1894,7 @@ static void scan_for_empty_cpusets(const struct cpuset *root)
  * in order to minimize text size.
  */
 
-static void common_cpu_mem_hotplug_unplug(void)
+static void common_cpu_mem_hotplug_unplug(int rebuild_sd)
 {
 	cgroup_lock();
 
@@ -1894,7 +1906,8 @@ static void common_cpu_mem_hotplug_unplug(void)
 	 * Scheduler destroys domains on hotplug events.
 	 * Rebuild them based on the current settings.
 	 */
-	rebuild_sched_domains();
+	if (rebuild_sd)
+		rebuild_sched_domains();
 
 	cgroup_unlock();
 }
@@ -1912,11 +1925,22 @@ static void common_cpu_mem_hotplug_unplug(void)
 static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
 				unsigned long phase, void *unused_cpu)
 {
-	if (phase == CPU_DYING || phase == CPU_DYING_FROZEN)
+	switch (phase) {
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		common_cpu_mem_hotplug_unplug(1);
+		break;
+	default:
 		return NOTIFY_DONE;
+	}
 
-	common_cpu_mem_hotplug_unplug();
-	return 0;
+	return NOTIFY_OK;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -1929,7 +1953,7 @@ static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
 
 void cpuset_track_online_nodes(void)
 {
-	common_cpu_mem_hotplug_unplug();
+	common_cpu_mem_hotplug_unplug(0);
 }
 #endif
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 8f6185e69b6..ceb25878283 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -13,6 +13,7 @@
 #include <linux/personality.h>
 #include <linux/tty.h>
 #include <linux/mnt_namespace.h>
+#include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/security.h>
 #include <linux/cpu.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 19908b26cf8..4bd2f516401 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -23,6 +23,7 @@
 #include <linux/sem.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>
@@ -909,7 +910,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	rt_mutex_init_task(p);
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_PROVE_LOCKING
 	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ab80515008f..b8e4dce80a7 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -300,11 +300,10 @@ EXPORT_SYMBOL_GPL(ktime_sub_ns);
  */
 u64 ktime_divns(const ktime_t kt, s64 div)
 {
-	u64 dclc, inc, dns;
+	u64 dclc;
 	int sft = 0;
 
-	dclc = dns = ktime_to_ns(kt);
-	inc = div;
+	dclc = ktime_to_ns(kt);
 	/* Make sure the divisor is less than 2^32: */
 	while (div >> 32) {
 		sft++;
@@ -623,7 +622,7 @@ static void retrigger_next_event(void *arg)
 void clock_was_set(void)
 {
 	/* Retrigger the CPU local events everywhere */
-	on_each_cpu(retrigger_next_event, NULL, 0, 1);
+	on_each_cpu(retrigger_next_event, NULL, 1);
 }
 
 /*
@@ -632,8 +631,6 @@ void clock_was_set(void)
  */
 void hres_timers_resume(void)
 {
-	WARN_ON_ONCE(num_online_cpus() > 1);
-
 	/* Retrigger the CPU local events: */
 	retrigger_next_event(NULL);
 }
@@ -1086,7 +1083,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 
-#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
+#ifdef CONFIG_NO_HZ
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
@@ -1677,7 +1674,7 @@ void __init hrtimers_init(void)
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
 #ifdef CONFIG_HIGH_RES_TIMERS
-	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
+	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
 #endif
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 46d6611a33b..77a51be3601 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,8 @@
 
 #ifdef CONFIG_SMP
 
+cpumask_t irq_default_affinity = CPU_MASK_ALL;
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -95,6 +97,27 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 	return 0;
 }
 
+#ifndef CONFIG_AUTO_IRQ_AFFINITY
+/*
+ * Generic version of the affinity autoselector.
+ */
+int irq_select_affinity(unsigned int irq)
+{
+	cpumask_t mask;
+
+	if (!irq_can_set_affinity(irq))
+		return 0;
+
+	cpus_and(mask, cpu_online_map, irq_default_affinity);
+
+	irq_desc[irq].affinity = mask;
+	irq_desc[irq].chip->set_affinity(irq, mask);
+
+	set_balance_irq_affinity(irq, mask);
+	return 0;
+}
+#endif
+
 #endif
 
 /**
@@ -354,7 +377,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 
 		/* Setup the type (level, edge polarity) if configured: */
 		if (new->flags & IRQF_TRIGGER_MASK) {
-			if (desc->chip && desc->chip->set_type)
+			if (desc->chip->set_type)
 				desc->chip->set_type(irq,
 						new->flags & IRQF_TRIGGER_MASK);
 			else
@@ -364,8 +387,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 				 */
 				printk(KERN_WARNING "No IRQF_TRIGGER set_type "
 				       "function for IRQ %d (%s)\n", irq,
-				       desc->chip ? desc->chip->name :
-				       "unknown");
+				       desc->chip->name);
 		} else
 			compat_irq_chip_set_default_handler(desc);
 
@@ -382,6 +404,9 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 		} else
 			/* Undo nested disables: */
 			desc->depth = 1;
+
+		/* Set default affinity mask once everything is setup */
+		irq_select_affinity(irq);
 	}
 	/* Reset broken irq detection when installing new handler */
 	desc->irq_count = 0;
@@ -571,8 +596,6 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	action->next = NULL;
 	action->dev_id = dev_id;
 
-	select_smp_affinity(irq);
-
 #ifdef CONFIG_DEBUG_SHIRQ
 	if (irqflags & IRQF_SHARED) {
 		/*
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index c2f2ccb0549..6c6d35d68ee 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -44,7 +44,7 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
 				   unsigned long count, void *data)
 {
 	unsigned int irq = (int)(long)data, full_count = count, err;
-	cpumask_t new_value, tmp;
+	cpumask_t new_value;
 
 	if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
@@ -62,17 +62,51 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
 	 * way to make the system unusable accidentally :-) At least
 	 * one online CPU still has to be targeted.
 	 */
-	cpus_and(tmp, new_value, cpu_online_map);
-	if (cpus_empty(tmp))
+	if (!cpus_intersects(new_value, cpu_online_map))
 		/* Special case for empty set - allow the architecture
 		   code to set default SMP affinity. */
-		return select_smp_affinity(irq) ? -EINVAL : full_count;
+		return irq_select_affinity(irq) ? -EINVAL : full_count;
 
 	irq_set_affinity(irq, new_value);
 
 	return full_count;
 }
 
+static int default_affinity_read(char *page, char **start, off_t off,
+				  int count, int *eof, void *data)
+{
+	int len = cpumask_scnprintf(page, count, irq_default_affinity);
+	if (count - len < 2)
+		return -EINVAL;
+	len += sprintf(page + len, "\n");
+	return len;
+}
+
+static int default_affinity_write(struct file *file, const char __user *buffer,
+				   unsigned long count, void *data)
+{
+	unsigned int full_count = count, err;
+	cpumask_t new_value;
+
+	err = cpumask_parse_user(buffer, count, new_value);
+	if (err)
+		return err;
+
+	if (!is_affinity_mask_valid(new_value))
+		return -EINVAL;
+
+	/*
+	 * Do not allow disabling IRQs completely - it's a too easy
+	 * way to make the system unusable accidentally :-) At least
+	 * one online CPU still has to be targeted.
+	 */
+	if (!cpus_intersects(new_value, cpu_online_map))
+		return -EINVAL;
+
+	irq_default_affinity = new_value;
+
+	return full_count;
+}
 #endif
 
 static int irq_spurious_read(char *page, char **start, off_t off,
@@ -171,6 +205,21 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 		remove_proc_entry(action->dir->name, irq_desc[irq].dir);
 }
 
+void register_default_affinity_proc(void)
+{
+#ifdef CONFIG_SMP
+	struct proc_dir_entry *entry;
+
+	/* create /proc/irq/default_smp_affinity */
+	entry = create_proc_entry("default_smp_affinity", 0600, root_irq_dir);
+	if (entry) {
+		entry->data = NULL;
+		entry->read_proc  = default_affinity_read;
+		entry->write_proc = default_affinity_write;
+	}
+#endif
+}
+
 void init_irq_proc(void)
 {
 	int i;
@@ -180,6 +229,8 @@ void init_irq_proc(void)
 	if (!root_irq_dir)
 		return;
 
+	register_default_affinity_proc();
+
 	/*
 	 * Create entries for all existing IRQs.
 	 */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d4998f81e22..1485ca8d0e0 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -79,7 +79,7 @@ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
  *
  * For such cases, we now have a blacklist
  */
-struct kprobe_blackpoint kprobe_blacklist[] = {
+static struct kprobe_blackpoint kprobe_blacklist[] = {
 	{"preempt_schedule",},
 	{NULL}    /* Terminator */
 };
diff --git a/kernel/kthread.c b/kernel/kthread.c
index bd1b9ea024e..97747cdd37c 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -180,6 +180,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
 	set_task_cpu(k, cpu);
 	k->cpus_allowed = cpumask_of_cpu(cpu);
 	k->rt.nr_cpus_allowed = 1;
+	k->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 81a4e4a3f08..d38a6436297 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -39,6 +39,7 @@
 #include <linux/irqflags.h>
 #include <linux/utsname.h>
 #include <linux/hash.h>
+#include <linux/ftrace.h>
 
 #include <asm/sections.h>
 
@@ -81,6 +82,8 @@ static int graph_lock(void)
 		__raw_spin_unlock(&lockdep_lock);
 		return 0;
 	}
+	/* prevent any recursions within lockdep from causing deadlocks */
+	current->lockdep_recursion++;
 	return 1;
 }
 
@@ -89,6 +92,7 @@ static inline int graph_unlock(void)
 	if (debug_locks && !__raw_spin_is_locked(&lockdep_lock))
 		return DEBUG_LOCKS_WARN_ON(1);
 
+	current->lockdep_recursion--;
 	__raw_spin_unlock(&lockdep_lock);
 	return 0;
 }
@@ -982,7 +986,7 @@ check_noncircular(struct lock_class *source, unsigned int depth)
 	return 1;
 }
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 /*
  * Forwards and backwards subgraph searching, for the purposes of
  * proving that two subgraphs can be connected by a new dependency
@@ -1458,7 +1462,14 @@ out_bug:
 }
 
 unsigned long nr_lock_chains;
-static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
+struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
+int nr_chain_hlocks;
+static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
+
+struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i)
+{
+	return lock_classes + chain_hlocks[chain->base + i];
+}
 
 /*
  * Look up a dependency chain. If the key is not present yet then
@@ -1466,10 +1477,15 @@ static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
  * validated. If the key is already hashed, return 0.
  * (On return with 1 graph_lock is held.)
  */
-static inline int lookup_chain_cache(u64 chain_key, struct lock_class *class)
+static inline int lookup_chain_cache(struct task_struct *curr,
+				     struct held_lock *hlock,
+				     u64 chain_key)
 {
+	struct lock_class *class = hlock->class;
 	struct list_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
+	struct held_lock *hlock_curr, *hlock_next;
+	int i, j, n, cn;
 
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))