Merge branch 'linus' into x86/x2apic

63 files changed, 11466 insertions, 1140 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 1c9938addb9..985ddb7da4d 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 +11,17 @@ 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
 
+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
+CFLAGS_REMOVE_sched.o = -mno-spe -pg
+endif
+
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
@@ -27,7 +38,8 @@ 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 +81,9 @@ 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 c77bc3a1c72..cfb1d43ab80 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);
 
@@ -277,6 +299,7 @@ int __ref cpu_down(unsigned int cpu)
 	cpu_maps_update_done();
 	return err;
 }
+EXPORT_SYMBOL(cpu_down);
 #endif /*CONFIG_HOTPLUG_CPU*/
 
 /* Requires cpu_add_remove_lock to be held */
@@ -403,3 +426,5 @@ 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..93d2711b938 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>
@@ -70,7 +71,7 @@ static void __unhash_process(struct task_struct *p)
 		__get_cpu_var(process_counts)--;
 	}
 	list_del_rcu(&p->thread_group);
-	remove_parent(p);
+	list_del_init(&p->sibling);
 }
 
 /*
@@ -151,6 +152,18 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 	put_task_struct(container_of(rhp, struct task_struct, rcu));
 }
 
+/*
+ * Do final ptrace-related cleanup of a zombie being reaped.
+ *
+ * Called with write_lock(&tasklist_lock) held.
+ */
+static void ptrace_release_task(struct task_struct *p)
+{
+	BUG_ON(!list_empty(&p->ptraced));
+	ptrace_unlink(p);
+	BUG_ON(!list_empty(&p->ptrace_entry));
+}
+
 void release_task(struct task_struct * p)
 {
 	struct task_struct *leader;
@@ -159,8 +172,7 @@ repeat:
 	atomic_dec(&p->user->processes);
 	proc_flush_task(p);
 	write_lock_irq(&tasklist_lock);
-	ptrace_unlink(p);
-	BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
+	ptrace_release_task(p);
 	__exit_signal(p);
 
 	/*
@@ -314,9 +326,8 @@ static void reparent_to_kthreadd(void)
 
 	ptrace_unlink(current);
 	/* Reparent to init */
-	remove_parent(current);
 	current->real_parent = current->parent = kthreadd_task;
-	add_parent(current);
+	list_move_tail(&current->sibling, &current->real_parent->children);
 
 	/* Set the exit signal to SIGCHLD so we signal init on exit */
 	current->exit_signal = SIGCHLD;
@@ -691,37 +702,97 @@ static void exit_mm(struct task_struct * tsk)
 	mmput(mm);
 }
 
-static void
-reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
+/*
+ * Return nonzero if @parent's children should reap themselves.
+ *
+ * Called with write_lock_irq(&tasklist_lock) held.
+ */
+static int ignoring_children(struct task_struct *parent)
 {
-	if (p->pdeath_signal)
-		/* We already hold the tasklist_lock here.  */
-		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
+	int ret;
+	struct sighand_struct *psig = parent->sighand;
+	unsigned long flags;
+	spin_lock_irqsave(&psig->siglock, flags);
+	ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
+	       (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
+	spin_unlock_irqrestore(&psig->siglock, flags);
+	return ret;
+}
 
-	/* Move the child from its dying parent to the new one.  */
-	if (unlikely(traced)) {
-		/* Preserve ptrace links if someone else is tracing this child.  */
-		list_del_init(&p->ptrace_list);
-		if (ptrace_reparented(p))
-			list_add(&p->ptrace_list, &p->real_parent->ptrace_children);
-	} else {
-		/* If this child is being traced, then we're the one tracing it
-		 * anyway, so let go of it.
+/*
+ * Detach all tasks we were using ptrace on.
+ * Any that need to be release_task'd are put on the @dead list.
+ *
+ * Called with write_lock(&tasklist_lock) held.
+ */
+static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
+{
+	struct task_struct *p, *n;
+	int ign = -1;
+
+	list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
+		__ptrace_unlink(p);
+
+		if (p->exit_state != EXIT_ZOMBIE)
+			continue;
+
+		/*
+		 * If it's a zombie, our attachedness prevented normal
+		 * parent notification or self-reaping.  Do notification
+		 * now if it would have happened earlier.  If it should
+		 * reap itself, add it to the @dead list.  We can't call
+		 * release_task() here because we already hold tasklist_lock.
+		 *
+		 * If it's our own child, there is no notification to do.
+		 * But if our normal children self-reap, then this child
+		 * was prevented by ptrace and we must reap it now.
 		 */
-		p->ptrace = 0;
-		remove_parent(p);
-		p->parent = p->real_parent;
-		add_parent(p);
+		if (!task_detached(p) && thread_group_empty(p)) {
+			if (!same_thread_group(p->real_parent, parent))
+				do_notify_parent(p, p->exit_signal);
+			else {
+				if (ign < 0)
+					ign = ignoring_children(parent);
+				if (ign)
+					p->exit_signal = -1;
+			}
+		}
 
-		if (task_is_traced(p)) {
+		if (task_detached(p)) {
 			/*
-			 * If it was at a trace stop, turn it into
-			 * a normal stop since it's no longer being
-			 * traced.
+			 * Mark it as in the process of being reaped.
 			 */
-			ptrace_untrace(p);
+			p->exit_state = EXIT_DEAD;
+			list_add(&p->ptrace_entry, dead);
 		}
 	}
+}
+
+/*
+ * Finish up exit-time ptrace cleanup.
+ *
+ * Called without locks.
+ */
+static void ptrace_exit_finish(struct task_struct *parent,
+			       struct list_head *dead)
+{
+	struct task_struct *p, *n;
+
+	BUG_ON(!list_empty(&parent->ptraced));
+
+	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
+}
+
+static void reparent_thread(struct task_struct *p, struct task_struct *father)
+{
+	if (p->pdeath_signal)
+		/* We already hold the tasklist_lock here.  */
+		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
+
+	list_move_tail(&p->sibling, &p->real_parent->children);
 
 	/* If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.
@@ -736,7 +807,8 @@ reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
 	/* If we'd notified the old parent about this child's death,
 	 * also notify the new parent.
 	 */
-	if (!traced && p->exit_state == EXIT_ZOMBIE &&
+	if (!ptrace_reparented(p) &&
+	    p->exit_state == EXIT_ZOMBIE &&
 	    !task_detached(p) && thread_group_empty(p))
 		do_notify_parent(p, p->exit_signal);
 
@@ -753,12 +825,15 @@ reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
 static void forget_original_parent(struct task_struct *father)
 {
 	struct task_struct *p, *n, *reaper = father;
-	struct list_head ptrace_dead;
-
-	INIT_LIST_HEAD(&ptrace_dead);
+	LIST_HEAD(ptrace_dead);
 
 	write_lock_irq(&tasklist_lock);
 
+	/*
+	 * First clean up ptrace if we were using it.
+	 */
+	ptrace_exit(father, &ptrace_dead);
+
 	do {
 		reaper = next_thread(reaper);
 		if (reaper == father) {
@@ -767,58 +842,19 @@ static void forget_original_parent(struct task_struct *father)
 		}
 	} while (reaper->flags & PF_EXITING);
 
-	/*
-	 * There are only two places where our children can be:
-	 *
-	 * - in our child list
-	 * - in our ptraced child list
-	 *
-	 * Search them and reparent children.
-	 */
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
-		int ptrace;
-
-		ptrace = p->ptrace;
-
-		/* if father isn't the real parent, then ptrace must be enabled */
-		BUG_ON(father != p->real_parent && !ptrace);
-
-		if (father == p->real_parent) {
-			/* reparent with a reaper, real father it's us */
-			p->real_parent = reaper;
-			reparent_thread(p, father, 0);
-		} else {
-			/* reparent ptraced task to its real parent */
-			__ptrace_unlink (p);
-			if (p->exit_state == EXIT_ZOMBIE && !task_detached(p) &&
-			    thread_group_empty(p))
-				do_notify_parent(p, p->exit_signal);
-		}
-
-		/*
-		 * if the ptraced child is a detached zombie we must collect
-		 * it before we exit, or it will remain zombie forever since
-		 * we prevented it from self-reap itself while it was being
-		 * traced by us, to be able to see it in wait4.
-		 */
-		if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && task_detached(p)))
-			list_add(&p->ptrace_list, &ptrace_dead);
-	}
-
-	list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) {
 		p->real_parent = reaper;
-		reparent_thread(p, father, 1);
+		if (p->parent == father) {
+			BUG_ON(p->ptrace);
+			p->parent = p->real_parent;
+		}
+		reparent_thread(p, father);
 	}
 
 	write_unlock_irq(&tasklist_lock);
 	BUG_ON(!list_empty(&father->children));
-	BUG_ON(!list_empty(&father->ptrace_children));
-
-	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_list) {
-		list_del_init(&p->ptrace_list);
-		release_task(p);
-	}
 
+	ptrace_exit_finish(father, &ptrace_dead);
 }
 
 /*
@@ -1179,13 +1215,6 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options,
 			return 0;
 	}
 
-	/*
-	 * Do not consider detached threads that are
-	 * not ptraced:
-	 */
-	if (task_detached(p) && !p->ptrace)
-		return 0;
-
 	/* Wait for all children (clone and not) if __WALL is set;
 	 * otherwise, wait for clone children *only* if __WCLONE is
 	 * set; otherwise, wait for non-clone children *only*.  (Note:
@@ -1196,14 +1225,10 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options,
 		return 0;
 
 	err = security_task_wait(p);
-	if (likely(!err))
-		return 1;
+	if (err)
+		return err;
 
-	if (type != PIDTYPE_PID)
-		return 0;
-	/* This child was explicitly requested, abort */
-	read_unlock(&tasklist_lock);
-	return err;
+	return 1;
 }
 
 static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
@@ -1237,7 +1262,7 @@ static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
  * the lock and this task is uninteresting.  If we return nonzero, we have
  * released the lock and the system call should return.
  */
-static int wait_task_zombie(struct task_struct *p, int noreap,
+static int wait_task_zombie(struct task_struct *p, int options,
 			    struct siginfo __user *infop,
 			    int __user *stat_addr, struct rusage __user *ru)
 {
@@ -1245,7 +1270,10 @@ static int wait_task_zombie(struct task_struct *p, int noreap,
 	int retval, status, traced;
 	pid_t pid = task_pid_vnr(p);
 
-	if (unlikely(noreap)) {
+	if (!likely(options & WEXITED))
+		return 0;
+
+	if (unlikely(options & WNOWAIT)) {
 		uid_t uid = p->uid;
 		int exit_code = p->exit_code;
 		int why, status;
@@ -1395,21 +1423,24 @@ static int wait_task_zombie(struct task_struct *p, int noreap,
  * the lock and this task is uninteresting.  If we return nonzero, we have
  * released the lock and the system call should return.
  */
-static int wait_task_stopped(struct task_struct *p,
-			     int noreap, struct siginfo __user *infop,
+static int wait_task_stopped(int ptrace, struct task_struct *p,
+			     int options, struct siginfo __user *infop,
 			     int __user *stat_addr, struct rusage __user *ru)
 {
 	int retval, exit_code, why;
 	uid_t uid = 0; /* unneeded, required by compiler */
 	pid_t pid;
 
+	if (!(options & WUNTRACED))
+		return 0;
+
 	exit_code = 0;
 	spin_lock_irq(&p->sighand->siglock);
 
 	if (unlikely(!task_is_stopped_or_traced(p)))
 		goto unlock_sig;
 
-	if (!(p->ptrace & PT_PTRACED) && p->signal->group_stop_count > 0)
+	if (!ptrace && p->signal->group_stop_count > 0)
 		/*
 		 * A group stop is in progress and this is the group leader.
 		 * We won't report until all threads have stopped.
@@ -1420,7 +1451,7 @@ static int wait_task_stopped(struct task_struct *p,
 	if (!exit_code)
 		goto unlock_sig;
 
-	if (!noreap)
+	if (!unlikely(options & WNOWAIT))
 		p->exit_code = 0;
 
 	uid = p->uid;
@@ -1438,10 +1469,10 @@ unlock_sig:
 	 */
 	get_task_struct(p);
 	pid = task_pid_vnr(p);
-	why