Merge branch 'linus' into cpus4096

23 files changed, 617 insertions, 283 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 66ec9fd21e0c..657f8f8d93a5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -45,6 +45,7 @@
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
+#include <linux/namei.h>
 
 #include <asm/atomic.h>
 
@@ -1529,7 +1530,7 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
 	return cft->read_seq_string(state->cgroup, cft, m);
 }
 
-int cgroup_seqfile_release(struct inode *inode, struct file *file)
+static int cgroup_seqfile_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *seq = file->private_data;
 	kfree(seq->private);
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index c1ef192aa655..0d407e886735 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -168,7 +168,6 @@ __set_personality(u_long personality)
 	current->personality = personality;
 	oep = current_thread_info()->exec_domain;
 	current_thread_info()->exec_domain = ep;
-	set_fs_altroot();
 
 	module_put(oep->module);
 	return 0;
diff --git a/kernel/exit.c b/kernel/exit.c
index ad933bb29ec7..eb4d6470d1d0 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,6 +46,7 @@
 #include <linux/resource.h>
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/tracehook.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -120,18 +121,7 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->nivcsw += tsk->nivcsw;
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
-#ifdef CONFIG_TASK_XACCT
-		sig->rchar += tsk->rchar;
-		sig->wchar += tsk->wchar;
-		sig->syscr += tsk->syscr;
-		sig->syscw += tsk->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
-		sig->ioac.read_bytes += tsk->ioac.read_bytes;
-		sig->ioac.write_bytes += tsk->ioac.write_bytes;
-		sig->ioac.cancelled_write_bytes +=
-					tsk->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+		task_io_accounting_add(&sig->ioac, &tsk->ioac);
 		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
@@ -162,27 +152,17 @@ 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;
 	int zap_leader;
 repeat:
+	tracehook_prepare_release_task(p);
 	atomic_dec(&p->user->processes);
 	proc_flush_task(p);
 	write_lock_irq(&tasklist_lock);
-	ptrace_release_task(p);
+	tracehook_finish_release_task(p);
 	__exit_signal(p);
 
 	/*
@@ -204,6 +184,13 @@ repeat:
 		 * that case.
 		 */
 		zap_leader = task_detached(leader);
+
+		/*
+		 * This maintains the invariant that release_task()
+		 * only runs on a task in EXIT_DEAD, just for sanity.
+		 */
+		if (zap_leader)
+			leader->exit_state = EXIT_DEAD;
 	}
 
 	write_unlock_irq(&tasklist_lock);
@@ -567,8 +554,6 @@ void put_fs_struct(struct fs_struct *fs)
 	if (atomic_dec_and_test(&fs->count)) {
 		path_put(&fs->root);
 		path_put(&fs->pwd);
-		if (fs->altroot.dentry)
-			path_put(&fs->altroot);
 		kmem_cache_free(fs_cachep, fs);
 	}
 }
@@ -887,7 +872,8 @@ static void forget_original_parent(struct task_struct *father)
  */
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
-	int state;
+	int signal;
+	void *cookie;
 
 	/*
 	 * This does two things:
@@ -924,22 +910,11 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	    !capable(CAP_KILL))
 		tsk->exit_signal = SIGCHLD;
 
-	/* If something other than our normal parent is ptracing us, then
-	 * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
-	 * only has special meaning to our real parent.
-	 */
-	if (!task_detached(tsk) && thread_group_empty(tsk)) {
-		int signal = ptrace_reparented(tsk) ?
-				SIGCHLD : tsk->exit_signal;
-		do_notify_parent(tsk, signal);
-	} else if (tsk->ptrace) {
-		do_notify_parent(tsk, SIGCHLD);
-	}
+	signal = tracehook_notify_death(tsk, &cookie, group_dead);
+	if (signal > 0)
+		signal = do_notify_parent(tsk, signal);
 
-	state = EXIT_ZOMBIE;
-	if (task_detached(tsk) && likely(!tsk->ptrace))
-		state = EXIT_DEAD;
-	tsk->exit_state = state;
+	tsk->exit_state = signal < 0 ? EXIT_DEAD : EXIT_ZOMBIE;
 
 	/* mt-exec, de_thread() is waiting for us */
 	if (thread_group_leader(tsk) &&
@@ -949,8 +924,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 
 	write_unlock_irq(&tasklist_lock);
 
+	tracehook_report_death(tsk, signal, cookie, group_dead);
+
 	/* If the process is dead, release it - nobody will wait for it */
-	if (state == EXIT_DEAD)
+	if (signal < 0)
 		release_task(tsk);
 }
 
@@ -1029,10 +1006,7 @@ NORET_TYPE void do_exit(long code)
 	if (unlikely(!tsk->pid))
 		panic("Attempted to kill the idle task!");
 
-	if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
-		current->ptrace_message = code;
-		ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
-	}
+	tracehook_report_exit(&code);
 
 	/*
 	 * We're taking recursive faults here in do_exit. Safest is to just
@@ -1378,21 +1352,8 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		psig->coublock +=
 			task_io_get_oublock(p) +
 			sig->oublock + sig->coublock;
-#ifdef CONFIG_TASK_XACCT
-		psig->rchar += p->rchar + sig->rchar;
-		psig->wchar += p->wchar + sig->wchar;
-		psig->syscr += p->syscr + sig->syscr;
-		psig->syscw += p->syscw + sig->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
-		psig->ioac.read_bytes +=
-			p->ioac.read_bytes + sig->ioac.read_bytes;
-		psig->ioac.write_bytes +=
-			p->ioac.write_bytes + sig->ioac.write_bytes;
-		psig->ioac.cancelled_write_bytes +=
-				p->ioac.cancelled_write_bytes +
-				sig->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+		task_io_accounting_add(&psig->ioac, &p->ioac);
+		task_io_accounting_add(&psig->ioac, &sig->ioac);
 		spin_unlock_irq(&p->parent->sighand->siglock);
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index b99d73e971a4..8214ba7c8bb1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -37,6 +37,7 @@
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
+#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
@@ -656,13 +657,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
 		path_get(&old->root);
 		fs->pwd = old->pwd;
 		path_get(&old->pwd);
-		if (old->altroot.dentry) {
-			fs->altroot = old->altroot;
-			path_get(&old->altroot);
-		} else {
-			fs->altroot.mnt = NULL;
-			fs->altroot.dentry = NULL;
-		}
 		read_unlock(&old->lock);
 	}
 	return fs;
@@ -812,12 +806,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
-#ifdef CONFIG_TASK_XACCT
-	sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0;
-#endif
-#ifdef CONFIG_TASK_IO_ACCOUNTING
-	memset(&sig->ioac, 0, sizeof(sig->ioac));
-#endif
+	task_io_accounting_init(&sig->ioac);
 	sig->sum_sched_runtime = 0;
 	INIT_LIST_HEAD(&sig->cpu_timers[0]);
 	INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -865,8 +854,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
 	new_flags &= ~PF_SUPERPRIV;
 	new_flags |= PF_FORKNOEXEC;
-	if (!(clone_flags & CLONE_PTRACE))
-		p->ptrace = 0;
+	new_flags |= PF_STARTING;
 	p->flags = new_flags;
 	clear_freeze_flag(p);
 }
@@ -907,7 +895,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					struct pt_regs *regs,
 					unsigned long stack_size,
 					int __user *child_tidptr,
-					struct pid *pid)
+					struct pid *pid,
+					int trace)
 {
 	int retval;
 	struct task_struct *p;
@@ -1000,13 +989,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->last_switch_timestamp = 0;
 #endif
 
-#ifdef CONFIG_TASK_XACCT
-	p->rchar = 0;		/* I/O counter: bytes read */
-	p->wchar = 0;		/* I/O counter: bytes written */
-	p->syscr = 0;		/* I/O counter: read syscalls */
-	p->syscw = 0;		/* I/O counter: write syscalls */
-#endif
-	task_io_accounting_init(p);
+	task_io_accounting_init(&p->ioac);
 	acct_clear_integrals(p);
 
 	p->it_virt_expires = cputime_zero;
@@ -1163,8 +1146,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 */
 	p->group_leader = p;
 	INIT_LIST_HEAD(&p->thread_group);
-	INIT_LIST_HEAD(&p->ptrace_entry);
-	INIT_LIST_HEAD(&p->ptraced);
 
 	/* Now that the task is set up, run cgroup callbacks if
 	 * necessary. We need to run them before the task is visible
@@ -1195,7 +1176,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->real_parent = current->real_parent;
 	else
 		p->real_parent = current;
-	p->parent = p->real_parent;
 
 	spin_lock(&current->sighand->siglock);
 
@@ -1237,8 +1217,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	if (likely(p->pid)) {
 		list_add_tail(&p->sibling, &p->real_parent->children);
-		if (unlikely(p->ptrace & PT_PTRACED))
-			__ptrace_link(p, current->parent);
+		tracehook_finish_clone(p, clone_flags, trace);
 
 		if (thread_group_leader(p)) {
 			if (clone_flags & CLONE_NEWPID)
@@ -1323,29 +1302,13 @@ struct task_struct * __cpuinit fork_idle(int cpu)
 	struct pt_regs regs;
 
 	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
-				&init_struct_pid);
+			    &init_struct_pid, 0);
 	if (!IS_ERR(task))
 		init_idle(task, cpu);
 
 	return task;
 }
 
-static int fork_traceflag(unsigned clone_flags)
-{
-	if (clone_flags & CLONE_UNTRACED)
-		return 0;
-	else if (clone_flags & CLONE_VFORK) {
-		if (current->ptrace & PT_TRACE_VFORK)
-			return PTRACE_EVENT_VFORK;
-	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-		if (current->ptrace & PT_TRACE_CLONE)
-			return PTRACE_EVENT_CLONE;
-	} else if (current->ptrace & PT_TRACE_FORK)
-		return PTRACE_EVENT_FORK;
-
-	return 0;
-}
-
 /*
  *  Ok, this is the main fork-routine.
  *
@@ -1380,14 +1343,14 @@ long do_fork(unsigned long clone_flags,
 		}
 	}
 
-	if (unlikely(current->ptrace)) {
-		trace = fork_traceflag (clone_flags);
-		if (trace)
-			clone_flags |= CLONE_PTRACE;
-	}
+	/*
+	 * When called from kernel_thread, don't do user tracing stuff.
+	 */
+	if (likely(user_mode(regs)))
+		trace = tracehook_prepare_clone(clone_flags);
 
 	p = copy_process(clone_flags, stack_start, regs, stack_size,
-			child_tidptr, NULL);
+			 child_tidptr, NULL, trace);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
@@ -1405,32 +1368,35 @@ long do_fork(unsigned long clone_flags,
 			init_completion(&vfork);
 		}
 
-		if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
+		tracehook_report_clone(trace, regs, clone_flags, nr, p);
+
+		/*
+		 * We set PF_STARTING at creation in case tracing wants to
+		 * use this to distinguish a fully live task from one that
+		 * hasn't gotten to tracehook_report_clone() yet.  Now we
+		 * clear it and set the child going.
+		 */
+		p->flags &= ~PF_STARTING;
+
+		if (unlikely(clone_flags & CLONE_STOPPED)) {
 			/*
 			 * We'll start up with an immediate SIGSTOP.
 			 */
 			sigaddset(&p->pending.signal, SIGSTOP);
 			set_tsk_thread_flag(p, TIF_SIGPENDING);
-		}
-
-		if (!(clone_flags & CLONE_STOPPED))
-			wake_up_new_task(p, clone_flags);
-		else
 			__set_task_state(p, TASK_STOPPED);
-
-		if (unlikely (trace)) {
-			current->ptrace_message = nr;
-			ptrace_notify ((trace << 8) | SIGTRAP);
+		} else {
+			wake_up_new_task(p, clone_flags);
 		}
 
+		tracehook_report_clone_complete(trace, regs,
+						clone_flags, nr, p);
+
 		if (clone_flags & CLONE_VFORK) {
 			freezer_do_not_count();
 			wait_for_completion(&vfork);
 			freezer_count();
-			if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
-				current->ptrace_message = nr;
-				ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
-			}
+			tracehook_report_vfork_done(p, nr);
 		}
 	} else {
 		nr = PTR_ERR(p);
@@ -1442,7 +1408,7 @@ long do_fork(unsigned long clone_flags,
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
 
-static void sighand_ctor(struct kmem_cache *cachep, void *data)
+static void sighand_ctor(void *data)
 {
 	struct sighand_struct *sighand = data;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 964964baefa2..3cd441ebf5d2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -28,8 +28,7 @@ void dynamic_irq_init(unsigned int irq)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS) {
-		printk(KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
 	}
 
@@ -62,8 +61,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS) {
-		printk(KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
 		return;
 	}
 
@@ -71,9 +69,8 @@ void dynamic_irq_cleanup(unsigned int irq)
 	spin_lock_irqsave(&desc->lock, flags);
 	if (desc->action) {
 		spin_unlock_irqrestore(&desc->lock, flags);
-		printk(KERN_ERR "Destroying IRQ%d without calling free_irq\n",
+		WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
 			irq);
-		WARN_ON(1);
 		return;
 	}
 	desc->msi_desc = NULL;
@@ -96,8 +93,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS) {
-		printk(KERN_ERR "Trying to install chip for IRQ%d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
 		return -EINVAL;
 	}
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f8914b92b664..152abfd3589f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -177,8 +177,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
 {
 	switch (desc->depth) {
 	case 0:
-		printk(KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
 		unsigned int status = desc->status & ~IRQ_DISABLED;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 1c5fcacbcf33..c8a4370e2a34 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -24,6 +24,12 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -242,6 +248,12 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
 		goto out;
 	}
 
+	image->swap_page = kimage_alloc_control_pages(image, 0);
+	if (!image->swap_page) {
+		printk(KERN_ERR "Could not allocate swap buffer\n");
+		goto out;
+	}
+
 	result = 0;
  out:
 	if (result == 0)
@@ -589,14 +601,12 @@ static void kimage_free_extra_pages(struct kimage *image)
 	kimage_free_page_list(&image->unuseable_pages);
 
 }
-static int kimage_terminate(struct kimage *image)
+static void kimage_terminate(struct kimage *image)
 {
 	if (*image->entry != 0)
 		image->entry++;
 
 	*image->entry = IND_DONE;
-
-	return 0;
 }
 
 #define for_each_kimage_entry(image, ptr, entry) \
@@ -988,6 +998,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 		if (result)
 			goto out;
 
+		if (flags & KEXEC_PRESERVE_CONTEXT)
+			image->preserve_context = 1;
 		result = machine_kexec_prepare(image);
 		if (result)
 			goto out;
@@ -997,9 +1009,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 			if (result)
 				goto out;
 		}
-		result = kimage_terminate(image);
-		if (result)
-			goto out;
+		kimage_terminate(image);
 	}
 	/* Install the new kernel, and  Uninstall the old */
 	image = xchg(dest_image, image);
@@ -1415,3 +1425,85 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+/**
+ *	kernel_kexec - reboot the system
+ *
+ *	Move into place and start executing a preloaded standalone
+ *	executable.  If nothing was preloaded return an error.
+ */
+int kernel_kexec(void)
+{
+	int error = 0;
+
+	if (xchg(&kexec_lock, 1))
+		return -EBUSY;
+	if (!kexec_image) {
+		error = -EINVAL;
+		goto Unlock;
+	}
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		mutex_lock(&pm_mutex);
+		pm_prepare_console();
+		error = freeze_processes();
+		if (error) {
+			error = -EBUSY;
+			goto Restore_console;
+		}
+		suspend_console();
+		error = device_suspend(PMSG_FREEZE);
+		if (error)
+			goto Resume_console;
+		error = disable_nonboot_cpus();
+		if (error)
+			goto Resume_devices;
+		local_irq_disable();
+		/* At this point, device_suspend() has been called,
+		 * but *not* device_power_down(). We *must*
+		 * device_power_down() now.  Otherwise, drivers for
+		 * some devices (e.g. interrupt controllers) become
+		 * desynchronized with the actual state of the
+		 * hardware at resume time, and evil weirdness ensues.
+		 */
+		error = device_power_down(PMSG_FREEZE);
+		if (error)
+			goto Enable_irqs;
+		save_processor_state();
+#endif
+	} else {
+		blocking_notifier_call_chain(&reboot_notifier_list,
+					     SYS_RESTART, NULL);
+		system_state = SYSTEM_RESTART;
+		device_shutdown();
+		sysdev_shutdown();
+		printk(KERN_EMERG "Starting new kernel\n");
+		machine_shutdown();
+	}
+
+	machine_kexec(kexec_image);
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		restore_processor_state();
+		device_power_up(PMSG_RESTORE);
+ Enable_irqs:
+		local_irq_enable();
+		enable_nonboot_cpus();
+ Resume_devices:
+		device_resume(PMSG_RESTORE);
+ Resume_console:
+		resume_console();
+		thaw_processes();
+ Restore_console:
+		pm_restore_console();
+		mutex_unlock(&pm_mutex);
+#endif
+	}
+
+ Unlock:
+	xchg(&kexec_lock, 0);
+
+	return error;
+}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 6111c27491b1..96cff2f8710b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -176,7 +176,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
 		return;
 	}
 	/* Must have done schedule() in kthread() before we set_task_cpu */
-	wait_task_inactive(k);
+	wait_task_inactive(k, 0);
 	set_task_cpu(k, cpu);
 	k->cpus_allowed = cpumask_of_cpu(cpu);
 	k->rt.nr_cpus_allowed = 1;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 95bff23ecdaa..0b7476f5d2a6 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -635,6 +635,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	}
 	if (status < 0)
 		printk(err_suspend, status);
+
+	/* Some platforms can't detect that the alarm triggered the
+	 * wakeup, or (accordingly) disable it after it afterwards.
+	 * It's supposed to give oneshot behavior; cope.
+	 */
+	alm.enabled = false;
+	rtc_set_alarm(rtc, &alm);
 }
 
 static int __init has_wakealarm(struct device *dev, void *name_ptr)
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 700f44ec8406..acc0c101dbd5 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void);
 
 extern int pfn_is_nosave(unsigned long);
 
-extern struct mutex pm_mutex;
-
 #define power_attr(_name) \
 static struct kobj_attribute _name##_attr = {	\
 	.attr	= {				\
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 8392a9da6450..082b3fcb32a0 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -107,7 +107,7 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 	read_unlock(&tasklist_lock);
 
 	if (!ret && !kill)
-		wait_task_inactive(child);
+		ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
 
 	/* All systems go.. */
 	return ret;
diff --git a/kernel/relay.c b/kernel/relay.c
index 7de644cdec43..04006ef970b8 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -407,6 +407,35 @@ void relay_reset(struct rchan *chan)
 }
 EXPORT_SYMBOL_GPL(relay_reset);
 
+static inline void relay_set_buf_dentry(struct rchan_buf *buf,
+					struct dentry *dentry)
+{
+	buf->dentry = dentry;
+	buf->dentry->d_inode->i_size = buf->early_bytes;
+}
+
+static struct dentry *relay_create_buf_file(struct rchan *chan,
+					    struct rchan_buf *buf,
+					    unsigned int cpu)
+{
+	struct dentry *dentry;
+	char *tmpname;
+
+	tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
+	if (!tmpname)
+		return NULL;
+	snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
+
+	/* Create file in fs */
+	dentry = chan->cb->create_buf_file(tmpname, chan->parent,
+					   S_IRUSR, buf,
+					   &chan->is_global);
+
+	kfree(tmpname);
+
+	return dentry;
+}
+
 /*
  *	relay_open_buf - create a new relay channel buffer
  *
@@ -416,45 +445,34 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 {
  	struct rchan_buf *buf = NULL;
 	struct dentry *dentry;
- 	char *tmpname;
 
  	if (chan->is_global)
 		return chan->buf[0];
 
-	tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
- 	if (!tmpname)
- 		goto end;
- 	snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
-
 	buf = relay_create_buf(chan);
 	if (!buf)
- 		goto free_name;
+		return NULL;
+
+	if (chan->has_base_filename) {
+		dentry = relay_create_buf_file(chan, buf, cpu);
+		if (!dentry)
+			goto free_buf;
+		relay_set_buf_dentry(buf, dentry);
+	}
 
  	buf->cpu = cpu;
  	__relay_reset(buf, 1);
 
-	/* Create file in fs */
- 	dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR,
- 					   buf, &chan->is_global);
- 	if (!dentry)
- 		goto free_buf;
-
-	buf->dentry = dentry;
-
  	if(chan->is_global) {
  		chan->buf[0] = buf;
  		buf->cpu = 0;
   	}
 
- 	goto free_name;
+	return buf;
 
 free_buf:
  	relay_destroy_buf(buf);
- 	buf = NULL;
-free_name:
- 	kfree(tmpname);
-end:
-	return buf;
+	return NULL;
 }
 
 /**
@@ -537,8 +555,8 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
 
 /**
  *	relay_open - create a new relay channel
- *	@base_filename: base name of files to create
- *	@parent: dentry of parent directory, %NULL for root directory
+ *	@base_filename: base name of files to create, %NULL for buffering only
+ *	@parent: dentry of parent directory, %NULL for root directory or buffer
  *	@subbuf_size: size of sub-buffers
  *	@n_subbufs: number of sub-buffers
  *	@cb: client callback functions
@@ -560,8 +578,6 @@ struct rchan *relay_open(const char *base_filename,
 {
 	unsigned int i;
 	struct rchan *chan;
-	if (!base_filename)
-		return NULL;
 
 	if (!(subbuf_size && n_subbufs))
 		return NULL;
@@ -576,7 +592,10 @@ struct rchan *relay_open(const char *base_filename,
 	chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs);
 	chan->parent = parent;
 	chan->private_data = private_data;
-	strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	if (base_filename) {
+		chan->has_base_filename = 1;
+		strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	}
 	setup_callbacks(chan, cb);
 	kref_init(&chan->kref);
 
@@ -604,6 +623,94 @@ free_bufs:
 }
 EXPORT_SYMBOL_GPL(relay_open);
 
+struct rchan_percpu_buf_dispatcher {
+	struct rchan_buf *buf;
+	struct dentry *dentry;
+};
+
+/* Called in atomic context. */
+static void __relay_set_buf_dentry(void *info)
+{
+	struct rchan_percpu_buf_dispatcher *p = info;
+
+	relay_set_buf_dentry(p->buf, p->dentry);
+}
+
+/**
+ *	relay_late_setup_files - triggers file creation
+ *	@chan: channel to operate on
+ *	@base_filename: base name of files to create
+ *	@parent: dentry of parent directory, %NULL for root directory
+ *
+ *	Returns 0 if successful, non-zero otherwise.
+ *
+ *	Use to setup files for a previously buffer-only channel.
+ *	Useful to do early tracing in kernel, before VFS is up, for example.
+ */
+int relay_late_setup_files(struct rchan *chan,
+			   const char *base_filename,
+			   struct dentry *parent)
+{
+	int err = 0;
+	unsigned int i, curr_cpu;
+	unsigned long flags;
+	struct dentry *dentry;
+	struct rchan_percpu_buf_dispatcher disp;
+
+	if (!chan || !base_filename)
+		return -EINVAL;
+
+	strlcpy(chan->base_filename, base_filename, NAME_MAX);
+
+	mutex_lock(&relay_channels_mutex);
+	/* Is chan already set up? */
+	if (unlikely(chan->has_base_filename))
+		return -EEXIST;
+	chan->has_base_filename = 1;
+	chan->parent = parent;
+	curr_cpu = get_cpu();
+	/*
+	 * The CPU hotplug notifier ran before us and created buffers with
+	 * no files associated. So it's safe to call relay_setup_buf_file()
+	 * on all currently online CPUs.
+	 */
+	for_each_online_cpu(i) {
+		if (unlikely(!chan->buf[i])) {
+			printk(KERN_ERR "relay_late_setup_files: CPU %u "
+					"has no buffer, it must have!\n", i);
+			BUG();
+			err = -EINVAL;
+			break;
+		}
+
+		dentry = relay_create_buf_file(chan, chan->buf[i], i);
+		if (unlikely(!dentry)) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (curr_cpu == i) {
+			local_irq_save(flags);
+			relay_set_buf_dentry(chan->buf[i], dentry);
+			local_irq_restore(flags);
+		} else {
+			disp.buf = chan->buf[i];
+			disp.dentry = dentry;
+			smp_mb();
+			/* relay_channels_mutex must be held, so wait. */
+			err = smp_call_function_single(i,
+						       __relay_set_buf_dentry,
+						       &disp, 1);
+		}
+		if (unlikely(err))
+			break;
+	}
+	put_cpu();
+	mutex_unlock(&relay_channels_mutex);
+
+	return err;
+}
+
 /**
  *	relay_switch_subbuf - switch to a new sub-buffer
  *	@buf: channel buffer
@@ -627,8 +734,13 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 		old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
 		buf->padding[old_subbuf] = buf->prev_padding;
 		buf->subbufs_produced++;
-		buf->dentry->d_inode->i_size += buf->chan->subbuf_size -
-			buf->padding[old_subbuf];
+		if (buf->dentry)
+			buf->dentry->d_inode->i_size +=
+				buf->chan->subbuf_size -
+				buf->padding[old_subbuf];
+		else
+			buf->early_bytes += buf->chan->subbuf_size -
+					    buf->padding[old_subbuf];
 		smp_mb();
 		if (waitqueue_active(&buf->read_wait))
 			/*
@@ -1237,4 +1349,4 @@ static __init int relay_init(void)
 	return 0;
 }
 
-module_init(relay_init);
+early_initcall(relay_init);
diff --git a/kernel/sched.c b/kernel/sched.c
index 0047bd9b96aa..0236958addcb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1867,16 +1867,24 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
+ * If @match_state is nonzero, it's the @p->state value just checked and
+ * not expected to change.  If it changes, i.e. @p might have woken up,
+ * then return zero.  When we succeed in waiting for @p to be off its CPU,
+ * we return a positive number (its total switch count).  If a second call
+ * a short while later returns the same number, the caller can be sure that
+ * @p has remained unscheduled the whole time.
+ *
  * The caller must ensure that the task *will* unschedule sometime soon,
  * else this function might spin for a *long* time. This function can't
  * be called with interrupts off, or it may introduce deadlock with
  * smp_call_function() if an IPI is sent by the same process we are
  * waiting to become inactive.
  */
-void wait_task_inactive(struct task_struct *p)
+unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
 	unsigned long flags;
 	int running, on_rq;
+	unsigned long ncsw;
 	struct rq *rq;
 
 	for (;;) {
@@ -1899,8 +1907,11 @@ void wait_task_inactive(struct task_struct *p)
 		 * return false if the runqueue has changed and p
 		 * is actually now running somewhere else!
 		 */
-		while (task_running(rq, p))
+		while (task_running(rq, p)) {
+			if (match_state && unlikely(p->state != match_state))
+				return 0;
 			cpu_relax();
+		}
 
 		/*
 		 * Ok, time to look more closely! We need the rq
@@ -1910,9 +1921,21 @@ void wait_task_inactive(struct task_struct *p)
 		rq = task_rq_lock(p, &flags);
 		running = task_running(rq, p);
 		on_rq = p->se.on_rq;
+		ncsw = 0;
+		if (!match_state || p->state == match_state) {
+			ncsw = p->nivcsw + p->nvcsw;
+			if (unlikely(!ncsw))
+				ncsw = 1;
+		}
 		task_rq_unlock(rq, &flags);
 
 		/*
+		 * If it changed from the expected state, bail out now.
+		 */
+		if (unlikely(!ncsw))
+			break;
+
+		/*
 		 * Was it really running after all now that we
 		 * checked with the proper locks actually held?
 		 *
@@ -1944,6 +1967,8 @@ void wait_task_inactive(struct task_struct *p)
 		 */
 		break;
 	}
+
+	return ncsw;
 }
 
 /***
@@ -6389,7 +6414,7 @@ static struct notifier_block __cpuinitdata migration_notifier = {
 	.priority = 10
 };
 
-void __init migration_init(void)
+static int __init migration_init(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
 	int err;
@@ -6399,7 +6424,10 @@ void __init migration_init(void)
 	BUG_ON(err == NOTIFY_BAD);
 	migration_call(&migration_notifier, CPU_ONLINE, cpu);
 	register_cpu_notifier(&migration_notifier);
+
+	return err;
 }
+early_initcall(migration_init);
 #endif
 
 #ifdef CONFIG_SMP
diff --git a/kernel/signal.c b/kernel/signal.c
index 82c3545596c5..954f77d7e3bc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,6 +22,7 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/signalfd.h>
+#include <linux/tracehook.h>
 #include <linux/capability.h>
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
@@ -39,24 +40,21 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
-static int __sig_ignored(struct task_struct *t, int sig)
+static void __user *sig_handler(struct task_struct *t, int sig)
 {
-	void __user *handler;
+	return t->sighand->action[sig - 1].sa.sa_handler;
+}
 
+static int sig_handler_ignored(void __user *handler, int sig)
+{
 	/* Is it explicitly or implicitly ignored? */
-
-	handler = t->sighand->action[sig - 1].sa.sa_handler;
 	return handler == SIG_IGN ||
 		(handler == SIG_DFL && sig_kernel_ignore(sig));
 }
 
 static int sig_ignored(struct task_struct *t, int sig)
 {
-	/*
-	 * Tracers always want to know about signals..
-	 */
-	if (t->ptrace & PT_PTRACED)
-		return 0;
+	void __user *handler;
 
 	/*
 	 * Blocked signals are never ignored, since the
@@ -66,7 +64,14 @@ static int sig_ignored(struct task_struct *t, int sig)
 	if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
 		return 0;
 
-	return __sig_ignored(t, sig);
+	handler = sig_handler(t, sig);
+	if (!sig_handler_ignored(handler, sig))
+		return 0;
+
+	/*
+	 * Tracers may want to know about even ignored signals.
+	 */
+	return !tracehook_consider_ignored_signal(t, sig, handler);
 }
 
 /*
@@ -129,7 +134,9 @@ void recalc_sigpending_and_wake(struct task_struct *t)
 
 void recalc_sigpending(void)
 {
-	if (!recalc_sigpending_tsk(current) && !freezing(current))
+	if (unlikely(tracehook_force_sigpending()))
+		set_thread_flag(TIF_SIGPENDING);
+	else if (!recalc_sigpending_tsk(current) && !freezing(current))
 		clear_thread_flag(TIF_SIGPENDING);
 
 }
@@ -295,12 +302,12 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 
 int unhandled_signal(struct task_struct *tsk, int sig)
 {
+	void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler;
 	if (is_global_init(tsk))
 		return 1;
-	if (tsk->ptrace & PT_PTRACED)
+	if (handler != SIG_IGN && handler != SIG_DFL)
 		return 0;
-	return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) ||
-		(tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL);
+	return !tracehook_consider_fatal_signal(tsk, sig, handler);
 }
 
 
@@ -591,9 +598,6 @@ static int check_kill_permission(int sig, struct siginfo *info,
 	return security_task_kill(t, info, sig, 0);
 }
 
-/* forward decl */
-static void do_notify_parent_cldstop(struct task_struct *tsk, int why);
-
 /*
  * Handle magic process-wide effects of stop/continue signals. Unlike
  * the signal actions, these happen immediately at signal-generation
@@ -756,7 +760,8 @@ static void complete_signal(int sig, struct task_struct *p, int group)
 	if (sig_fatal(p, sig) &&
 	    !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
 	    !sigismember(&t->real_blocked, sig) &&
-	    (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) {
+	    (sig == SIGKILL ||
+	     !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) {
 		/*
 		 * This signal will be fatal to the whole group.
 		 */
@@ -1323,9 +1328,11 @@ static inline void __wake_up_parent(struct task_struct *p,
 /*
  * Let a parent know about the death of a child.
  * For a stopped/continued status change, use do_notify_parent_cldstop instead.
+ *
+ * Returns -1 if our parent ignored us and so we've switched to
+ * self-reaping, or else @sig.
  */
-
-void do_notify_parent(struct task_struct *tsk, int sig)
+int do_notify_parent(struct task_struct *tsk, int sig)
 {
 	struct siginfo info;
 	unsigned long flags;
@@ -1396,12 +1403,14 @@ void do_notify_parent(struct task_struct *tsk, int sig)
 		 */
 		tsk->exit_signal = -1;
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
-			sig = 0;
+			sig = -1;
 	}
 	if (valid_signal(sig) && sig > 0)
 		__group_send_sig_info(sig, &info, tsk->parent);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
+
+	return sig;
 }
 
 static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
@@ -1599,7 +1608,7 @@ finish_stop(int stop_count)
 	 * a group stop in progress and we are the last to stop,
 	 * report to the parent.  When ptraced, every thread reports itself.
 	 */
-	if (stop_count == 0 || (current->ptrace & PT_PTRACED)) {
+	if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
 		read_lock(&tasklist_lock);
 		do_notify_parent_cldstop(current, CLD_STOPPED);
 		read_unlock(&tasklist_lock);
@@ -1735,6 +1744,9 @@ relock:
 		signal->flags &= ~SIGNAL_CLD_MASK;
 		spin_unlock_irq(&sighand->siglock);
 
+		if (unlikely(!tracehook_notify_jctl(1, why)))
+			goto relock;
+
 		read_lock(&tasklist_lock);
 		do_notify_parent_cldstop(current->group_leader, why);
 		read_unlock(&tasklist_lock);
@@ -1748,17 +1760,33 @@ relock:
 		    do_signal_stop(0))
 			goto relock;
 
-		signr = dequeue_signal(current, &current->blocked, info);
-		if (!signr)
-			break; /* will return 0 */
+		/*
+		 * Tracing can induce an artifical signal and choose sigaction.
+		 * The return value in @signr determines the default action,
+		 * but @info->si_signo is the signal number we will report.
+		 */
+		signr = tracehook_get_signal(current, regs, info, return_ka);
+		if (unlikely(signr < 0))
+			goto relock;
+		if (unlikely(signr != 0))
+			ka = return_ka;
+		else {
+			signr = dequeue_signal(current, &current->blocked,
+					       info);
 
-		if (signr != SIGKILL) {
-			signr = ptrace_signal(signr, info, regs, cookie);
 			if (!signr)
-				continue;
+				break; /* will return 0 */
+
+			if (signr != SIGKILL) {
+				signr = ptrace_signal(signr, info,
+						      regs, cookie);
+				if (!signr)
+					continue;
+			}
+
+			ka = &sighand->action[signr-1];
 		}
 
-		ka = &sighand->action[signr-1];
 		if (ka->sa.sa_handler == SIG_IGN) /* Do nothing.  */
 			continue;
 		if (ka->sa.sa_handler != SIG_DFL) {
@@ -1806,7 +1834,7 @@ relock:
 				spin_lock_irq(&sighand->siglock);
 			}
 
-			if (likely(do_signal_stop(signr))) {
+			if (likely(do_signal_stop(info->si_signo))) {
 				/* It released the siglock.  */
 				goto relock;
 			}
@@ -1827,7 +1855,7 @@ relock:
 
 		if (sig_kernel_coredump(signr)) {
 			if (print_fatal_signals)
-				print_fatal_signal(regs, signr);
+				print_fatal_signal(regs, info->si_signo);
 			/*
 			 * If it was able to dump core, this kills all
 			 * other threads in the group and synchronizes with
@@ -1836,13 +1864,13 @@ relock:
 			 * first and our do_group_exit call below will use
 			 * that value and ignore the one we pass it.
 			 */
-			do_coredump((long)signr, signr, regs);
+			do_coredump(info->si_signo, info->si_signo, regs);
 		}
 
 		/*
 		 * Death signals, no core dump.
 		 */
-		do_group_exit(signr);
+		do_group_exit(info->si_signo);
 		/* NOTREACHED */
 	}
 	spin_unlock_irq(&sighand->siglock);
@@ -1884,7 +1912,7 @@ void exit_signals(struct task_struct *tsk)
 out:
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (unlikely(group_stop)) {
+	if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
 		read_lock(&tasklist_lock);
 		do_notify_parent_cldstop(tsk, CLD_STOPPED);
 		read_unlock(&tasklist_lock);
@@ -1895,7 +1923,6 @@ EXPORT_SYMBOL(recalc_sigpending);
 EXPORT_SYMBOL_GPL(dequeue_signal);
 EXPORT_SYMBOL(flush_signals);
 EXPORT_SYMBOL(force_sig);
-EXPORT_SYMBOL(ptrace_notify);
 EXPORT_SYMBOL(send_sig);
 EXPORT_SYMBOL(send_sig_info);
 EXPORT_SYMBOL(sigprocmask);
@@ -2299,7 +2326,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 		 *   (for example, SIGCHLD), shall cause the pending signal to
 		 *   be discarded, whether or not it is blocked"
 		 */
-		if (__sig_ignored(t, sig)) {
+		if (sig_handler_ignored(sig_handler(t, sig), sig)) {
 			sigemptyset(&mask);
 			sigaddset(&mask, sig);
 			rm_from_queue_full(&mask, &t->signal->shared_pending);
diff --git a/kernel/smp.c b/kernel/smp.c
index 462c785ca1ee..96fc7c0edc59 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -33,7 +33,7 @@ struct call_single_queue {
 	spinlock_t lock;
 };
 
-void __cpuinit init_call_single_data(void)
+static int __cpuinit init_call_single_data(void)
 {
 	int i;
 
@@ -43,7 +43,9 @@ void __cpuinit init_call_single_data(void)
 		spin_lock_init(&q->lock);
 		INIT_LIST_HEAD(&q->list);
 	}
+	return 0;
 }
+early_initcall(init_call_single_data);
 
 static void csd_flag_wait(struct call_single_data *data)
 {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f6b03d56c2bf..c506f266a6b9 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -630,7 +630,7 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
 	.notifier_call = cpu_callback
 };
 
-__init int spawn_ksoftirqd(void)
+static __init int spawn_ksoftirqd(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
 	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
@@ -640,6 +640,7 @@ __init int spawn_ksoftirqd(void)
 	register_cpu_notifier(&cpu_nfb);
 	return 0;
 }
+early_initcall(spawn_ksoftirqd);
 
 #ifdef CONFIG_SMP
 /*
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 7bd8d1aadd5d..b75b492fbfcf 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -338,14 +338,33 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
 	.notifier_call = cpu_callback
 };
 
-__init void spawn_softlockup_task(void)
+static int __initdata nosoftlockup;
+
+static int __init nosoftlockup_setup(char *str)
+{
+	nosoftlockup = 1;
+	return 1;
+}
+__setup("nosoftlockup", nosoftlockup_setup);
+
+static int __init spawn_softlockup_task(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
-	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+	int err;
 
-	BUG_ON(err == NOTIFY_BAD);
+	if (nosoftlockup)
+		return 0;
+
+	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+	if (err == NOTIFY_BAD) {
+		BUG();
+		return 1;
+	}
 	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
 	register_cpu_notifier(&cpu_nfb);
 
 	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+	return 0;
 }
+early_initcall(spawn_softlockup_task);
diff --git a/kernel/sys.c b/kernel/sys.c
index 0c9d3fa1f5ff..c01858090a98 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -301,26 +301,6 @@ void kernel_restart(char *cmd)
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
 
-/**
- *	kernel_kexec - reboot the system
- *
- *	Move into place and start executing a preloaded standalone
- *	executable.  If nothing was preloaded return an error.
- */
-static void kernel_kexec(void)
-{
-#ifdef CONFIG_KEXEC
-	struct kimage *image;
-	image = xchg(&kexec_image, NULL);
-	if (!image)
-		return;
-	kernel_restart_prepare(NULL);
-	printk(KERN_EMERG "Starting new kernel\n");
-	machine_shutdown();
-	machine_kexec(image);
-#endif
-}
-
 static void kernel_shutdown_prepare(enum system_states state)
 {
 	blocking_notifier_call_chain(&reboot_notifier_list,
@@ -425,10 +405,15 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
 		kernel_restart(buffer);
 		break;
 
+#ifdef CONFIG_KEXEC
 	case LINUX_REBOOT_CMD_KEXEC:
-		kernel_kexec();
-		unlock_kernel();
-		return -EINVAL;
+		{
+			int ret;
+			ret = kernel_kexec();
+			unlock_kernel();
+			return ret;
+		}
+#endif
 
 #ifdef CONFIG_HIBERNATION
 	case LINUX_REBOOT_CMD_SW_SUSPEND:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 35a50db9b6ce..fe4713347275 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -160,12 +160,13 @@ static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
 	.ctl_table = root_table,
-	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.header_list),
+	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
 	.root = &sysctl_table_root,
+	.set = &sysctl_table_root.default_set,
 };
 static struct ctl_table_root sysctl_table_root = {
 	.root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
-	.header_list = LIST_HEAD_INIT(root_table_header.ctl_entry),
+	.default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry),
 };
 
 static struct ctl_table kern_table[];
@@ -1386,6 +1387,9 @@ static void start_unregistering(struct ctl_table_header *p)
 		spin_unlock(&sysctl_lock);
 		wait_for_completion(&wait);
 		spin_lock(&sysctl_lock);
+	} else {
+		/* anything non-NULL; we'll never dereference it */
+		p->unregistering = ERR_PTR(-EINVAL);
 	}
 	/*
 	 * do not remove from the list until nobody holds it; walking the
@@ -1394,6 +1398,32 @@ static void start_unregistering(struct ctl_table_header *p)
 	list_del_init(&p->ctl_entry);
 }
 
+void sysctl_head_get(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	head->count++;
+	spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	if (!--head->count)
+		kfree(head);
+	spin_unlock(&sysctl_lock);
+}
+
+struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+	if (!head)
+		BUG();
+	spin_lock(&sysctl_lock);
+	if (!use_table(head))
+		head = ERR_PTR(-ENOENT);
+	spin_unlock(&sysctl_lock);
+	return head;
+}
+
 void sysctl_head_finish(struct ctl_table_header *head)
 {
 	if (!head)
@@ -1403,14 +1433,20 @@ void sysctl_head_finish(struct ctl_table_header *head)
 	spin_unlock(&sysctl_lock);
 }
 
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+	struct ctl_table_set *set = &root->default_set;
+	if (root->lookup)
+		set = root->lookup(root, namespaces);
+	return set;
+}
+
 static struct list_head *
 lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
 {
-	struct list_head *header_list;
-	header_list = &root->header_list;
-	if (root->lookup)
-		header_list = root->lookup(root, namespaces);
-	return header_list;
+	struct ctl_table_set *set = lookup_header_set(root, namespaces);
+	return &set->list;
 }
 
 struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
@@ -1480,9 +1516,9 @@ static int do_sysctl_strategy(struct ctl_table_root *root,
 	int op = 0, rc;
 
 	if (oldval)
-		op |= 004;
+		op |= MAY_READ;
 	if (newval)
-		op |= 002;
+		op |= MAY_WRITE;
 	if (sysctl_perm(root, table, op))
 		return -EPERM;
 
@@ -1524,7 +1560,7 @@ repeat:
 		if (n == table->ctl_name) {
 			int error;
 			if (table->child) {
-				if (sysctl_perm(root, table, 001))
+				if (sysctl_perm(root, table, MAY_EXEC))
 					return -EPERM;
 				name++;
 				nlen--;
@@ -1599,7 +1635,7 @@ static int test_perm(int mode, int op)
 		mode >>= 6;
 	else if (in_egroup_p(0))
 		mode >>= 3;
-	if ((mode & op & 0007) == op)
+	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
 		return 0;
 	return -EACCES;
 }
@@ -1609,7 +1645,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
 	int error;
 	int mode;
 
-	error = security_sysctl(table, op);
+	error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
 	if (error)
 		return error;
 
@@ -1644,6 +1680,54 @@ static __init int sysctl_init(void)
 
 core_initcall(sysctl_init);
 
+static struct ctl_table *is_branch_in(struct ctl_table *branch,
+				      struct ctl_table *table)
+{
+	struct ctl_table *p;
+	const char *s = branch->procname;
+
+	/* branch should have named subdirectory as its first element */
+	if (!s || !branch->child)
+		return NULL;
+
+	/* ... and nothing else */
+	if (branch[1].procname || branch[1].ctl_name)
+		return NULL;
+
+	/* table should contain subdirectory with the same name */
+	for (p = table; p->procname || p->ctl_name; p++) {
+		if (!p->child)
+			continue;
+		if (p->procname && strcmp(p->procname, s) == 0)
+			return p;
+	}
+	return NULL;
+}
+
+/* see if attaching q to p would be an improvement */
+static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
+{
+	struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
+	struct ctl_table *next;
+	int is_better = 0;
+	int not_in_parent = !p->attached_by;
+
+	while ((next = is_branch_in(by, to)) != NULL) {
+		if (by == q->attached_by)
+			is_better = 1;
+		if (to == p->attached_by)
+			not_in_parent = 1;
+		by = by->child;
+		to = next->child;
+	}
+
+	if (is_better && not_in_parent) {
+		q->attached_by = by;
+		q->attached_to = to;
+		q->parent = p;
+	}
+}
+
 /**
  * __register_sysctl_paths - register a sysctl hierarchy
  * @root: List of sysctl headers to register on
@@ -1720,10 +1804,10 @@ struct ctl_table_header *__register_sysctl_paths(
 	struct nsproxy *namespaces,
 	const struct ctl_path *path, struct ctl_table *table)
 {
-	struct list_head *header_list;
 	struct ctl_table_header *header;
 	struct ctl_table *new, **prevp;
 	unsigned int n, npath;
+	struct ctl_table_set *set;
 
 	/* Count the path components */
 	for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath)
@@ -1765,6 +1849,7 @@ struct ctl_table_header *__register_sysctl_paths(
 	header->unregistering = NULL;
 	header->root = root;
 	sysctl_set_parent(NULL, header->ctl_table);
+	header->count = 1;
 #ifdef CONFIG_SYSCTL_SYSCALL_CHECK
 	if (sysctl_check_table(namespaces, header->ctl_table)) {
 		kfree(header);
@@ -1772,8 +1857,20 @@ struct ctl_table_header *__register_sysctl_paths(
 	}
 #endif
 	spin_lock(&sysctl_lock);
-	header_list = lookup_header_list(root, namespaces);
-	list_add_tail(&header->ctl_entry, header_list);
+	header->set = lookup_header_set(root, namespaces);
+	header->attached_by = header->ctl_table;
+	header->attached_to = root_table;
+	header->parent = &root_table_header;
+	for (set = header->set; set; set = set->parent) {
+		struct ctl_table_header *p;
+		list_for_each_entry(p, &set->list, ctl_entry) {
+			if (p->unregistering)
+				continue;
+			try_attach(p, header);
+		}
+	}
+	header->parent->count++;
+	list_add_tail(&header->ctl_entry, &header->set->list);
 	spin_unlock(&sysctl_lock);
 
 	return header;
@@ -1828,8 +1925,37 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 
 	spin_lock(&sysctl_lock);
 	start_unregistering(header);
+	if (!--header->parent->count) {
+		WARN_ON(1);
+		kfree(header->parent);
+	}
+	if (!--header->count)
+		kfree(header);
 	spin_unlock(&sysctl_lock);
-	kfree(header);
+}
+
+int sysctl_is_seen(struct ctl_table_header *p)
+{
+	struct ctl_table_set *set = p->set;
+	int res;
+	spin_lock(&sysctl_lock);
+	if (p->unregistering)
+		res = 0;
+	else if (!set->is_seen)
+		res = 1;
+	else
+		res = set->is_seen(set);
+	spin_unlock(&sysctl_lock);
+	return res;
+}
+
+void setup_sysctl_set(struct ctl_table_set *p,
+	struct ctl_table_set *parent,
+	int (*is_seen)(struct ctl_table_set *))
+{
+	INIT_LIST_HEAD(&p->list);
+	p->parent = parent ? parent : &sysctl_table_root.default_set;
+	p->is_seen = is_seen;
 }
 
 #else /* !CONFIG_SYSCTL */
@@ -1848,6 +1974,16 @@ void unregister_sysctl_table(struct ctl_table_header * table)
 {
 }
 
+void setup_sysctl_set(struct ctl_table_set *p,
+	struct ctl_table_set *parent,
+	int (*is_seen)(struct ctl_table_set *))
+{
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+}
+
 #endif /* CONFIG_SYSCTL */
 
 /*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 868e121c8e38..8f3fb3db61c3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1183,7 +1183,6 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct trace_iterator *iter = m->private;
-	void *last_ent = iter->ent;
 	int i = (int)*pos;
 	void *ent;
 
@@ -1203,9 +1202,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
 	iter->pos = *pos;
 
-	if (last_ent && !ent)
-		seq_puts(m, "\n\nvim:ft=help\n");
-
 	return ent;
 }
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 421d6fe3650e..ece6cfb649fa 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -253,12 +253,14 @@ void start_critical_timings(void)
 	if (preempt_trace() || irq_trace())
 		start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
+EXPORT_SYMBOL_GPL(start_critical_timings);
 
 void stop_critical_timings(void)
 {
 	if (preempt_trace() || irq_trace())
 		stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
+EXPORT_SYMBOL_GPL(stop_critical_timings);
 
 #ifdef CONFIG_IRQSOFF_TRACER
 #ifdef CONFIG_PROVE_LOCKING
@@ -337,12 +339,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller);
 #ifdef CONFIG_PREEMPT_TRACER
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-	stop_critical_timing(a0, a1);
+	if (preempt_trace())
+		stop_critical_timing(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-	start_critical_timing(a0, a1);
+	if (preempt_trace())
+		start_critical_timing(a0, a1);
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3c8d61df4474..e303ccb62cdf 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -26,7 +26,8 @@ static struct task_struct	*wakeup_task;
 static int			wakeup_cpu;
 static unsigned			wakeup_prio = -1;
 
-static DEFINE_SPINLOCK(wakeup_lock);
+static raw_spinlock_t wakeup_lock =
+	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 
 static void __wakeup_reset(struct trace_array *tr);
 
@@ -56,7 +57,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 	if (unlikely(disabled != 1))
 		goto out;
 
-	spin_lock_irqsave(&wakeup_lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&wakeup_lock);
 
 	if (unlikely(!wakeup_task))
 		goto unlock;
@@ -71,7 +73,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 	trace_function(tr, data, ip, parent_ip, flags);
 
  unlock:
-	spin_unlock_irqrestore(&wakeup_lock, flags);
+	__raw_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
 
  out:
 	atomic_dec(&data->disabled);
@@ -145,7 +148,8 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
 	if (likely(disabled != 1))
 		goto out;
 
-	spin_lock_irqsave(&wakeup_lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&wakeup_lock);
 
 	/* We could race with grabbing wakeup_lock */
 	if (unlikely(!tracer_enabled || next != wakeup_task))
@@ -174,7 +178,8 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
 
 out_unlock:
 	__wakeup_reset(tr);
-	spin_unlock_irqrestore(&wakeup_lock, flags);
+	__raw_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
 out:
 	atomic_dec(&tr->data[cpu]->disabled);
 }
@@ -209,8 +214,6 @@ static void __wakeup_reset(struct trace_array *tr)
 	struct trace_array_cpu *data;
 	int cpu;
 
-	assert_spin_locked(&wakeup_lock);
-
 	for_each_possible_cpu(cpu) {
 		data = tr->data[cpu];
 		tracing_reset(data);
@@ -229,9 +232,11 @@ static void wakeup_reset(struct trace_array *tr)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&wakeup_lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&wakeup_lock);
 	__wakeup_reset(tr);
-	spin_unlock_irqrestore(&wakeup_lock, flags);
+	__raw_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
 }
 
 static void
@@ -252,7 +257,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p,
 		goto out;
 
 	/* interrupts should be off from try_to_wake_up */
-	spin_lock(&wakeup_lock);
+	__raw_spin_lock(&wakeup_lock);
 
 	/* check for races. */
 	if (!tracer_enabled || p->prio >= wakeup_prio)
@@ -274,7 +279,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p,
 		       CALLER_ADDR1, CALLER_ADDR2, flags);
 
 out_locked:
-	spin_unlock(&wakeup_lock);
+	__raw_spin_unlock(&wakeup_lock);
 out:
 	atomic_dec(&tr->data[cpu]->disabled);
 }
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 3da47ccdc5e5..8ebcd8532dfb 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -94,10 +94,10 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 		stats->hiwater_vm    = mm->hiwater_vm * PAGE_SIZE / KB;
 		mmput(mm);
 	}
-	stats->read_char	= p->rchar;
-	stats->write_char	= p->wchar;
-	stats->read_syscalls	= p->syscr;
-	stats->write_syscalls	= p->syscw;
+	stats->read_char	= p->ioac.rchar;
+	stats->write_char	= p->ioac.wchar;
+	stats->read_syscalls	= p->ioac.syscr;
+	stats->write_syscalls	= p->ioac.syscw;
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	stats->read_bytes	= p->ioac.read_bytes;
 	stats->write_bytes	= p->ioac.write_bytes;