Merge branch 'master' into upstream

34 files changed, 511 insertions, 244 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 2a7c933..f4330ac 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -483,10 +483,14 @@ static void do_acct_process(struct file *file)
 	ac.ac_ppid = current->parent->tgid;
 #endif
 
-	read_lock(&tasklist_lock);	/* pin current->signal */
+	mutex_lock(&tty_mutex);
+	/* FIXME: Whoever is responsible for current->signal locking needs
+	   to use the same locking all over the kernel and document it */
+	read_lock(&tasklist_lock);
 	ac.ac_tty = current->signal->tty ?
 		old_encode_dev(tty_devnum(current->signal->tty)) : 0;
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&tty_mutex);
 
 	spin_lock_irq(&current->sighand->siglock);
 	ac.ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fb83c5c..1051476 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -817,6 +817,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		audit_log_format(ab, " success=%s exit=%ld", 
 				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
 				 context->return_code);
+
+	mutex_lock(&tty_mutex);
 	if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
 		tty = tsk->signal->tty->name;
 	else
@@ -838,6 +840,9 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		  context->gid,
 		  context->euid, context->suid, context->fsuid,
 		  context->egid, context->sgid, context->fsgid, tty);
+
+	mutex_unlock(&tty_mutex);
+
 	audit_log_task_info(ab, tsk);
 	if (context->filterkey) {
 		audit_log_format(ab, " key=");
diff --git a/kernel/capability.c b/kernel/capability.c
index c7685ad..edb845a 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -133,7 +133,7 @@ static inline int cap_set_all(kernel_cap_t *effective,
      int found = 0;
 
      do_each_thread(g, target) {
-             if (target == current || target->pid == 1)
+             if (target == current || is_init(target))
                      continue;
              found = 1;
 	     if (security_capset_check(target, effective, inheritable,
diff --git a/kernel/compat.c b/kernel/compat.c
index 126dee9..b4fbd83 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -22,9 +22,12 @@
 #include <linux/security.h>
 #include <linux/timex.h>
 #include <linux/migrate.h>
+#include <linux/posix-timers.h>
 
 #include <asm/uaccess.h>
 
+extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
@@ -601,6 +604,30 @@ long compat_sys_clock_getres(clockid_t which_clock,
 	return err;
 } 
 
+static long compat_clock_nanosleep_restart(struct restart_block *restart)
+{
+	long err;
+	mm_segment_t oldfs;
+	struct timespec tu;
+	struct compat_timespec *rmtp = (struct compat_timespec *)(restart->arg1);
+
+	restart->arg1 = (unsigned long) &tu;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	err = clock_nanosleep_restart(restart);
+	set_fs(oldfs);
+
+	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
+	    put_compat_timespec(&tu, rmtp))
+		return -EFAULT;
+
+	if (err == -ERESTART_RESTARTBLOCK) {
+		restart->fn = compat_clock_nanosleep_restart;
+		restart->arg1 = (unsigned long) rmtp;
+	}
+	return err;
+}
+
 long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 			    struct compat_timespec __user *rqtp,
 			    struct compat_timespec __user *rmtp)
@@ -608,6 +635,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 	long err;
 	mm_segment_t oldfs;
 	struct timespec in, out; 
+	struct restart_block *restart;
 
 	if (get_compat_timespec(&in, rqtp)) 
 		return -EFAULT;
@@ -618,9 +646,16 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 				  (struct timespec __user *) &in,
 				  (struct timespec __user *) &out);
 	set_fs(oldfs);
+
 	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
 	    put_compat_timespec(&out, rmtp))
 		return -EFAULT;
+
+	if (err == -ERESTART_RESTARTBLOCK) {
+		restart = &current_thread_info()->restart_block;
+		restart->fn = compat_clock_nanosleep_restart;
+		restart->arg1 = (unsigned long) rmtp;
+	}
 	return err;	
 } 
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1b32c2c..8c3c400 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -240,7 +240,7 @@ static struct super_block *cpuset_sb;
  * A cpuset can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cpusets is empty.  Since all
  * tasks in the system use _some_ cpuset, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cpuset
+ * least one task in the system (init), therefore, top_cpuset
  * always has either children cpusets and/or using tasks.  So we don't
  * need a special hack to ensure that top_cpuset cannot be deleted.
  *
@@ -912,6 +912,10 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	int fudge;
 	int retval;
 
+	/* top_cpuset.mems_allowed tracks node_online_map; it's read-only */
+	if (cs == &top_cpuset)
+		return -EACCES;
+
 	trialcs = *cs;
 	retval = nodelist_parse(buf, trialcs.mems_allowed);
 	if (retval < 0)
@@ -1221,7 +1225,12 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
 
 	task_lock(tsk);
 	oldcs = tsk->cpuset;
-	if (!oldcs) {
+	/*
+	 * After getting 'oldcs' cpuset ptr, be sure still not exiting.
+	 * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
+	 * then fail this attach_task(), to avoid breaking top_cpuset.count.
+	 */
+	if (tsk->flags & PF_EXITING) {
 		task_unlock(tsk);
 		mutex_unlock(&callback_mutex);
 		put_task_struct(tsk);
@@ -2036,33 +2045,104 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
 /*
- * The top_cpuset tracks what CPUs and Memory Nodes are online,
- * period.  This is necessary in order to make cpusets transparent
- * (of no affect) on systems that are actively using CPU hotplug
- * but making no active use of cpusets.
- *
- * This handles CPU hotplug (cpuhp) events.  If someday Memory
- * Nodes can be hotplugged (dynamically changing node_online_map)
- * then we should handle that too, perhaps in a similar way.
+ * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then the guarantee_online_cpus()
+ * or guarantee_online_mems() code will use that emptied cpusets
+ * parent online CPUs or nodes.  Cpusets that were already empty of
+ * CPUs or nodes are left empty.
+ *
+ * This routine is intentionally inefficient in a couple of regards.
+ * It will check all cpusets in a subtree even if the top cpuset of
+ * the subtree has no offline CPUs or nodes.  It checks both CPUs and
+ * nodes, even though the caller could have been coded to know that
+ * only one of CPUs or nodes needed to be checked on a given call.
+ * This was done to minimize text size rather than cpu cycles.
+ *
+ * Call with both manage_mutex and callback_mutex held.
+ *
+ * Recursive, on depth of cpuset subtree.
  */
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int cpuset_handle_cpuhp(struct notifier_block *nb,
-				unsigned long phase, void *cpu)
+static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
+{
+	struct cpuset *c;
+
+	/* Each of our child cpusets mems must be online */
+	list_for_each_entry(c, &cur->children, sibling) {
+		guarantee_online_cpus_mems_in_subtree(c);
+		if (!cpus_empty(c->cpus_allowed))
+			guarantee_online_cpus(c, &c->cpus_allowed);
+		if (!nodes_empty(c->mems_allowed))
+			guarantee_online_mems(c, &c->mems_allowed);
+	}
+}
+
+/*
+ * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
+ * cpu_online_map and node_online_map.  Force the top cpuset to track
+ * whats online after any CPU or memory node hotplug or unplug event.
+ *
+ * To ensure that we don't remove a CPU or node from the top cpuset
+ * that is currently in use by a child cpuset (which would violate
+ * the rule that cpusets must be subsets of their parent), we first
+ * call the recursive routine guarantee_online_cpus_mems_in_subtree().
+ *
+ * Since there are two callers of this routine, one for CPU hotplug
+ * events and one for memory node hotplug events, we could have coded
+ * two separate routines here.  We code it as a single common routine
+ * in order to minimize text size.
+ */
+
+static void common_cpu_mem_hotplug_unplug(void)
 {
 	mutex_lock(&manage_mutex);
 	mutex_lock(&callback_mutex);
 
+	guarantee_online_cpus_mems_in_subtree(&top_cpuset);
 	top_cpuset.cpus_allowed = cpu_online_map;
+	top_cpuset.mems_allowed = node_online_map;
 
 	mutex_unlock(&callback_mutex);
 	mutex_unlock(&manage_mutex);
+}
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The top_cpuset tracks what CPUs and Memory Nodes are online,
+ * period.  This is necessary in order to make cpusets transparent
+ * (of no affect) on systems that are actively using CPU hotplug
+ * but making no active use of cpusets.
+ *
+ * This routine ensures that top_cpuset.cpus_allowed tracks
+ * cpu_online_map on each CPU hotplug (cpuhp) event.
+ */
 
+static int cpuset_handle_cpuhp(struct notifier_block *nb,
+				unsigned long phase, void *cpu)
+{
+	common_cpu_mem_hotplug_unplug();
 	return 0;
 }
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * Keep top_cpuset.mems_allowed tracking node_online_map.
+ * Call this routine anytime after you change node_online_map.
+ * See also the previous routine cpuset_handle_cpuhp().
+ */
+
+void cpuset_track_online_nodes()
+{
+	common_cpu_mem_hotplug_unplug();
+}
+#endif
+
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
diff --git a/kernel/exit.c b/kernel/exit.c
index d891883..c189de2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -38,6 +38,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/audit.h> /* for audit_free() */
 #include <linux/resource.h>
+#include <linux/blkdev.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -219,7 +220,7 @@ static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task)
 	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
 		if (p == ignored_task
 				|| p->exit_state
-				|| p->real_parent->pid == 1)
+				|| is_init(p->real_parent))
 			continue;
 		if (process_group(p->real_parent) != pgrp
 			    && p->real_parent->signal->session == p->signal->session) {
@@ -249,17 +250,6 @@ static int has_stopped_jobs(int pgrp)
 	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
 		if (p->state != TASK_STOPPED)
 			continue;
-
-		/* If p is stopped by a debugger on a signal that won't
-		   stop it, then don't count p as stopped.  This isn't
-		   perfect but it's a good approximation.  */
-		if (unlikely (p->ptrace)
-		    && p->exit_code != SIGSTOP
-		    && p->exit_code != SIGTSTP
-		    && p->exit_code != SIGTTOU
-		    && p->exit_code != SIGTTIN)
-			continue;
-
 		retval = 1;
 		break;
 	} while_each_task_pid(pgrp, PIDTYPE_PGID, p);
@@ -292,9 +282,7 @@ static void reparent_to_init(void)
 	/* Set the exit signal to SIGCHLD so we signal init on exit */
 	current->exit_signal = SIGCHLD;
 
-	if ((current->policy == SCHED_NORMAL ||
-			current->policy == SCHED_BATCH)
-				&& (task_nice(current) < 0))
+	if (!has_rt_policy(current) && (task_nice(current) < 0))
 		set_user_nice(current, 0);
 	/* cpus_allowed? */
 	/* rt_priority? */
@@ -487,6 +475,18 @@ void fastcall put_files_struct(struct files_struct *files)
 
 EXPORT_SYMBOL(put_files_struct);
 
+void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
+{
+	struct files_struct *old;
+
+	old = tsk->files;
+	task_lock(tsk);
+	tsk->files = files;
+	task_unlock(tsk);
+	put_files_struct(old);
+}
+EXPORT_SYMBOL(reset_files_struct);
+
 static inline void __exit_files(struct task_struct *tsk)
 {
 	struct files_struct * files = tsk->files;
@@ -954,15 +954,15 @@ fastcall NORET_TYPE void do_exit(long code)
 	if (tsk->splice_pipe)
 		__free_pipe_info(tsk->splice_pipe);
 
-	/* PF_DEAD causes final put_task_struct after we schedule. */
 	preempt_disable();
-	BUG_ON(tsk->flags & PF_DEAD);
-	tsk->flags |= PF_DEAD;
+	/* causes final put_task_struct in finish_task_switch(). */
+	tsk->state = TASK_DEAD;
 
 	schedule();
 	BUG();
 	/* Avoid "noreturn function does return".  */
-	for (;;) ;
+	for (;;)
+		cpu_relax();	/* For when BUG is null */
 }
 
 EXPORT_SYMBOL_GPL(do_exit);
@@ -971,7 +971,7 @@ NORET_TYPE void complete_and_exit(struct completion *comp, long code)
 {
 	if (comp)
 		complete(comp);
-	
+
 	do_exit(code);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a0dad84..1c999f3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -183,7 +183,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	/* One for us, one for whoever does the "release_task()" (usually parent) */
 	atomic_set(&tsk->usage,2);
 	atomic_set(&tsk->fs_excl, 0);
+#ifdef CONFIG_BLK_DEV_IO_TRACE
 	tsk->btrace_seq = 0;
+#endif
 	tsk->splice_pipe = NULL;
 	return tsk;
 }
@@ -1061,7 +1063,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	p->hardirqs_enabled = 1;
+#else
 	p->hardirqs_enabled = 0;
+#endif
 	p->hardirq_enable_ip = 0;
 	p->hardirq_enable_event = 0;
 	p->hardirq_disable_ip = _THIS_IP_;
@@ -1144,7 +1150,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	/* Our parent execution domain becomes current domain
 	   These must match for thread signalling to apply */
-	   
 	p->parent_exec_id = p->self_exec_id;
 
 	/* ok, now we should be set up.. */
@@ -1167,6 +1172,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
+	/* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
+	p->ioprio = current->ioprio;
+
 	/*
 	 * The task hasn't been attached yet, so its cpus_allowed mask will
 	 * not be changed, nor will its assigned CPU.
@@ -1226,11 +1234,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		}
 	}
 
-	/*
-	 * inherit ioprio
-	 */
-	p->ioprio = current->ioprio;
-
 	if (likely(p->pid)) {
 		add_parent(p);
 		if (unlikely(p->ptrace & PT_PTRACED))
diff --git a/kernel/futex.c b/kernel/futex.c
index 9d260e8..4b6770e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -389,7 +389,7 @@ static struct task_struct * futex_find_get_task(pid_t pid)
 {
 	struct task_struct *p;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	p = find_task_by_pid(pid);
 	if (!p)
 		goto out_unlock;
@@ -403,7 +403,7 @@ static struct task_struct * futex_find_get_task(pid_t pid)
 	}
 	get_task_struct(p);
 out_unlock:
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return p;
 }
@@ -1624,7 +1624,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
 		struct task_struct *p;
 
 		ret = -ESRCH;
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		p = find_task_by_pid(pid);
 		if (!p)
 			goto err_unlock;
@@ -1633,7 +1633,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
 				!capable(CAP_SYS_PTRACE))
 			goto err_unlock;
 		head = p->robust_list;
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 	}
 
 	if (put_user(sizeof(*head), len_ptr))
@@ -1641,7 +1641,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
 	return put_user(head, head_ptr);
 
 err_unlock:
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 21c38a7..d0ba190 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -693,7 +693,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	return t->task == NULL;
 }
 
-static long __sched nanosleep_restart(struct restart_block *restart)
+long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 {
 	struct hrtimer_sleeper t;
 	struct timespec __user *rmtp;
@@ -702,13 +702,13 @@ static long __sched nanosleep_restart(struct restart_block *restart)
 
 	restart->fn = do_no_restart_syscall;
 
-	hrtimer_init(&t.timer, restart->arg3, HRTIMER_ABS);
-	t.timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0;
+	hrtimer_init(&t.timer, restart->arg0, HRTIMER_ABS);
+	t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
 
 	if (do_nanosleep(&t, HRTIMER_ABS))
 		return 0;
 
-	rmtp = (struct timespec __user *) restart->arg2;
+	rmtp = (struct timespec __user *) restart->arg1;
 	if (rmtp) {
 		time = ktime_sub(t.timer.expires, t.timer.base->get_time());
 		if (time.tv64 <= 0)
@@ -718,7 +718,7 @@ static long __sched nanosleep_restart(struct restart_block *restart)
 			return -EFAULT;
 	}
 
-	restart->fn = nanosleep_restart;
+	restart->fn = hrtimer_nanosleep_restart;
 
 	/* The other values in restart are already filled in */
 	return -ERESTART_RESTARTBLOCK;
@@ -751,11 +751,11 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	}
 
 	restart = &current_thread_info()->restart_block;
-	restart->fn = nanosleep_restart;
-	restart->arg0 = t.timer.expires.tv64 & 0xFFFFFFFF;
-	restart->arg1 = t.timer.expires.tv64 >> 32;
-	restart->arg2 = (unsigned long) rmtp;
-	restart->arg3 = (unsigned long) t.timer.base->index;
+	restart->fn = hrtimer_nanosleep_restart;
+	restart->arg0 = (unsigned long) t.timer.base->index;
+	restart->arg1 = (unsigned long) rmtp;
+	restart->arg2 = t.timer.expires.tv64 & 0xFFFFFFFF;
+	restart->arg3 = t.timer.expires.tv64 >> 32;
 
 	return -ERESTART_RESTARTBLOCK;
 }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index ac1f850..736cb0b 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -40,10 +40,6 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
 	desc->chip = chip;
-	/*
-	 * For compatibility only:
-	 */
-	desc->chip = chip;
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
@@ -146,7 +142,7 @@ static void default_disable(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 
 	if (!(desc->status & IRQ_DELAYED_DISABLE))
-		irq_desc[irq].chip->mask(irq);
+		desc->chip->mask(irq);
 }
 
 /*
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 50087ec..fcdd5d2 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -40,7 +40,7 @@ struct resource crashk_res = {
 
 int kexec_should_crash(struct task_struct *p)
 {
-	if (in_interrupt() || !p->pid || p->pid == 1 || panic_on_oops)
+	if (in_interrupt() || !p->pid || is_init(p) || panic_on_oops)
 		return 1;
 	return 0;
 }
@@ -995,7 +995,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 	image = xchg(dest_image, image);
 
 out:
-	xchg(&kexec_lock, 0); /* Release the mutex */
+	locked = xchg(&kexec_lock, 0); /* Release the mutex */
+	BUG_ON(!locked);
 	kimage_free(image);
 
 	return result;
@@ -1061,7 +1062,8 @@ void crash_kexec(struct pt_regs *regs)
 			machine_crash_shutdown(&fixed_regs);
 			machine_kexec(kexec_crash_image);
 		}
-		xchg(&kexec_lock, 0);
+		locked = xchg(&kexec_lock, 0);
+		BUG_ON(!locked);
 	}
 }
 
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 64ab045..5d1d907 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -122,6 +122,13 @@ unsigned int __kfifo_put(struct kfifo *fifo,
 
 	len = min(len, fifo->size - fifo->in + fifo->out);
 
+	/*
+	 * Ensure that we sample the fifo->out index -before- we
+	 * start putting bytes into the kfifo.
+	 */
+
+	smp_mb();
+
 	/* first put the data starting from fifo->in to buffer end */
 	l = min(len, fifo->size - (fifo->in & (fifo->size - 1)));
 	memcpy(fifo->buffer + (fifo->in & (fifo->size - 1)), buffer, l);
@@ -129,6 +136,13 @@ unsigned int __kfifo_put(struct kfifo *fifo,
 	/* then put the rest (if any) at the beginning of the buffer */
 	memcpy(fifo->buffer, buffer + l, len - l);
 
+	/*
+	 * Ensure that we add the bytes to the kfifo -before-
+	 * we update the fifo->in index.
+	 */
+
+	smp_wmb();
+
 	fifo->in += len;
 
 	return len;
@@ -154,6 +168,13 @@ unsigned int __kfifo_get(struct kfifo *fifo,
 
 	len = min(len, fifo->in - fifo->out);
 
+	/*
+	 * Ensure that we sample the fifo->in index -before- we
+	 * start removing bytes from the kfifo.
+	 */
+
+	smp_rmb();
+
 	/* first get the data from fifo->out until the end of the buffer */
 	l = min(len, fifo->size - (fifo->out & (fifo->size - 1)));
 	memcpy(buffer, fifo->buffer + (fifo->out & (fifo->size - 1)), l);
@@ -161,6 +182,13 @@ unsigned int __kfifo_get(struct kfifo *fifo,
 	/* then get the rest (if any) from the beginning of the buffer */
 	memcpy(buffer + l, fifo->buffer, len - l);
 
+	/*
+	 * Ensure that we remove the bytes from the kfifo -before-
+	 * we update the fifo->out index.
+	 */
+
+	smp_mb();
+
 	fifo->out += len;
 
 	return len;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 5c470c5..842f801 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -176,6 +176,8 @@ static int wait_for_helper(void *data)
 	if (pid < 0) {
 		sub_info->retval = pid;
 	} else {
+		int ret;
+
 		/*
 		 * Normally it is bogus to call wait4() from in-kernel because
 		 * wait4() wants to write the exit code to a userspace address.
@@ -185,7 +187,15 @@ static int wait_for_helper(void *data)
 		 *
 		 * Thus the __user pointer cast is valid here.
 		 */
-		sys_wait4(pid, (int __user *) &sub_info->retval, 0, NULL);
+		sys_wait4(pid, (int __user *)&ret, 0, NULL);
+
+		/*
+		 * If ret is 0, either ____call_usermodehelper failed and the
+		 * real error code is already in sub_info->retval or
+		 * sub_info->retval is 0 anyway, so don't mess with it then.
+		 */
+		if (ret)
+			sub_info->retval = ret;
 	}
 
 	complete(sub_info->complete);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index c088e55..e596525 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -36,6 +36,7 @@
 #include <linux/stacktrace.h>
 #include <linux/debug_locks.h>
 #include <linux/irqflags.h>
+#include <linux/utsname.h>
 
 #include <asm/sections.h>
 
@@ -121,8 +122,8 @@ static struct list_head chainhash_table[CHAINHASH_SIZE];
  * unique.
  */
 #define iterate_chain_key(key1, key2) \
-	(((key1) << MAX_LOCKDEP_KEYS_BITS/2) ^ \
-	((key1) >> (64-MAX_LOCKDEP_KEYS_BITS/2)) ^ \
+	(((key1) << MAX_LOCKDEP_KEYS_BITS) ^ \
+	((key1) >> (64-MAX_LOCKDEP_KEYS_BITS)) ^ \
 	(key2))
 
 void lockdep_off(void)
@@ -515,6 +516,13 @@ print_circular_bug_entry(struct lock_list *target, unsigned int depth)
 	return 0;
 }
 
+static void print_kernel_version(void)
+{
+	printk("%s %.*s\n", system_utsname.release,
+		(int)strcspn(system_utsname.version, " "),
+		system_utsname.version);
+}
+
 /*
  * When a circular dependency is detected, print the
  * header first:
@@ -531,6 +539,7 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth)
 
 	printk("\n=======================================================\n");
 	printk(  "[ INFO: possible circular locking dependency detected ]\n");
+	print_kernel_version();
 	printk(  "-------------------------------------------------------\n");
 	printk("%s/%d is trying to acquire lock:\n",
 		curr->comm, curr->pid);
@@ -712,6 +721,7 @@ print_bad_irq_dependency(struct task_struct *curr,
 	printk("\n======================================================\n");
 	printk(  "[ INFO: %s-safe -> %s-unsafe lock order detected ]\n",
 		irqclass, irqclass);
+	print_kernel_version();
 	printk(  "------------------------------------------------------\n");
 	printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
 		curr->comm, curr->pid,
@@ -793,6 +803,7 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 
 	printk("\n=============================================\n");
 	printk(  "[ INFO: possible recursive locking detected ]\n");
+	print_kernel_version();
 	printk(  "---------------------------------------------\n");
 	printk("%s/%d is trying to acquire lock:\n",
 		curr->comm, curr->pid);
@@ -1375,6 +1386,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
 
 	printk("\n=========================================================\n");
 	printk(  "[ INFO: possible irq lock inversion dependency detected ]\n");
+	print_kernel_version();
 	printk(  "---------------------------------------------------------\n");
 	printk("%s/%d just changed the state of lock:\n",
 		curr->comm, curr->pid);
@@ -1469,6 +1481,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 
 	printk("\n=================================\n");
 	printk(  "[ INFO: inconsistent lock state ]\n");
+	print_kernel_version();
 	printk(  "---------------------------------\n");
 
 	printk("inconsistent {%s} -> {%s} usage.\n",
diff --git a/kernel/module.c b/kernel/module.c
index b7fe6e8..05625d5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -933,6 +933,15 @@ static ssize_t module_sect_show(struct module_attribute *mattr,
 	return sprintf(buf, "0x%lx\n", sattr->address);
 }
 
+static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
+{
+	int section;
+
+	for (section = 0; section < sect_attrs->nsections; section++)
+		kfree(sect_attrs->attrs[section].name);
+	kfree(sect_attrs);
+}
+
 static void add_sect_attrs(struct module *mod, unsigned int nsect,
 		char *secstrings, Elf_Shdr *sechdrs)
 {
@@ -949,21 +958,26 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 			+ nloaded * sizeof(sect_attrs->attrs[0]),
 			sizeof(sect_attrs->grp.attrs[0]));
 	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]);
-	if (! (sect_attrs = kmalloc(size[0] + size[1], GFP_KERNEL)))
+	sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL);
+	if (sect_attrs == NULL)
 		return;
 
 	/* Setup section attributes. */
 	sect_attrs->grp.name = "sections";
 	sect_attrs->grp.attrs = (void *)sect_attrs + size[0];
 
+	sect_attrs->nsections = 0;
 	sattr = &sect_attrs->attrs[0];
 	gattr = &sect_attrs->grp.attrs[0];
 	for (i = 0; i < nsect; i++) {
 		if (! (sechdrs[i].sh_flags & SHF_ALLOC))
 			continue;
 		sattr->address = sechdrs[i].sh_addr;
-		strlcpy(sattr->name, secstrings + sechdrs[i].sh_name,
-			MODULE_SECT_NAME_LEN);
+		sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
+					GFP_KERNEL);
+		if (sattr->name == NULL)
+			goto out;
+		sect_attrs->nsections++;
 		sattr->mattr.show = module_sect_show;
 		sattr->mattr.store = NULL;
 		sattr->mattr.attr.name = sattr->name;
@@ -979,7 +993,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 	mod->sect_attrs = sect_attrs;
 	return;
   out:
-	kfree(sect_attrs);
+	free_sect_attrs(sect_attrs);
 }
 
 static void remove_sect_attrs(struct module *mod)
@@ -989,13 +1003,13 @@ static void remove_sect_attrs(struct module *mod)
 				   &mod->sect_attrs->grp);
 		/* We are positive that no one is using any sect attrs
 		 * at this point.  Deallocate immediately. */
-		kfree(mod->sect_attrs);
+		free_sect_attrs(mod->sect_attrs);
 		mod->sect_attrs = NULL;
 	}
 }
 
-
 #else
+
 static inline void add_sect_attrs(struct module *mod, unsigned int nsect,
 		char *sectstrings, Elf_Shdr *sechdrs)
 {
diff --git a/kernel/panic.c b/kernel/panic.c
index 6ceb664..525e365 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -21,7 +21,6 @@
 #include <linux/debug_locks.h>
 
 int panic_on_oops;
-int panic_on_unrecovered_nmi;
 int tainted;
 static int pause_on_oops;
 static int pause_on_oops_flag;
diff --git a/kernel/params.c b/kernel/params.c
index 91aea7aa..f406655 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -547,6 +547,7 @@ static void __init kernel_param_sysfs_setup(const char *name,
 					    unsigned int name_skip)
 {
 	struct module_kobject *mk;
+	int ret;
 
 	mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
 	BUG_ON(!mk);
@@ -554,7 +555,8 @@ static void __init kernel_param_sysfs_setup(const char *name,
 	mk->mod = THIS_MODULE;
 	kobj_set_kset_s(mk, module_subsys);
 	kobject_set_name(&mk->kobj, name);
-	kobject_register(&mk->kobj);
+	ret = kobject_register(&mk->kobj);
+	BUG_ON(ret < 0);
 
 	/* no need to keep the kobject if no parameter is exported */
 	if (!param_sysfs_setup(mk, kparam, num_params, name_skip)) {
@@ -684,13 +686,20 @@ decl_subsys(module, &module_ktype, NULL);
  */
 static int __init param_sysfs_init(void)
 {
-	subsystem_register(&module_subsys);
+	int ret;
+
+	ret = subsystem_register(&module_subsys);
+	if (ret < 0) {
+		printk(KERN_WARNING "%s (%d): subsystem_register error: %d\n",
+			__FILE__, __LINE__, ret);
+		return ret;
+	}
 
 	param_sysfs_builtin();
 
 	return 0;
 }
-__initcall(param_sysfs_init);
+subsys_initcall(param_sysfs_init);
 
 EXPORT_SYMBOL(param_set_byte);
 EXPORT_SYMBOL(param_get_byte);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index d38d9ec..479b16b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1393,25 +1393,13 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	}
 }
 
-static long posix_cpu_clock_nanosleep_restart(struct restart_block *);
-
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp)
+static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
+			    struct timespec *rqtp, struct itimerspec *it)
 {
-	struct restart_block *restart_block =
-	    &current_thread_info()->restart_block;
 	struct k_itimer timer;
 	int error;
 
 	/*
-	 * Diagnose required errors first.
-	 */
-	if (CPUCLOCK_PERTHREAD(which_clock) &&
-	    (CPUCLOCK_PID(which_clock) == 0 ||
-	     CPUCLOCK_PID(which_clock) == current->pid))
-		return -EINVAL;
-
-	/*
 	 * Set up a temporary timer and then wait for it to go off.
 	 */
 	memset(&timer, 0, sizeof timer);
@@ -1422,11 +1410,12 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 	timer.it_process = current;
 	if (!error) {
 		static struct itimerspec zero_it;
-		struct itimerspec it = { .it_value = *rqtp,
-					 .it_interval = {} };
+
+		memset(it, 0, sizeof *it);
+		it->it_value = *rqtp;
 
 		spin_lock_irq(&timer.it_lock);
-		error = posix_cpu_timer_set(&timer, flags, &it, NULL);
+		error = posix_cpu_timer_set(&timer, flags, it, NULL);
 		if (error) {
 			spin_unlock_irq(&timer.it_lock);
 			return error;
@@ -1454,49 +1443,89 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 		 * We were interrupted by a signal.
 		 */
 		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
-		posix_cpu_timer_set(&timer, 0, &zero_it, &it);
+		posix_cpu_timer_set(&timer, 0, &zero_it, it);
 		spin_unlock_irq(&timer.it_lock);
 
-		if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) {
+		if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
 			/*
 			 * It actually did fire already.
 			 */
 			return 0;
 		}
 
+		error = -ERESTART_RESTARTBLOCK;
+	}
+
+	return error;
+}
+
+int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+		     struct timespec *rqtp, struct timespec __user *rmtp)
+{
+	struct restart_block *restart_block =
+	    &current_thread_info()->restart_block;
+	struct itimerspec it;
+	int error;
+
+	/*
+	 * Diagnose required errors first.
+	 */
+	if (CPUCLOCK_PERTHREAD(which_clock) &&
+	    (CPUCLOCK_PID(which_clock) == 0 ||
+	     CPUCLOCK_PID(which_clock) == current->pid))
+		return -EINVAL;
+
+	error = do_cpu_nanosleep(which_clock, flags, rqtp, &it);
+
+	if (error == -ERESTART_RESTARTBLOCK) {
+
+	       	if (flags & TIMER_ABSTIME)
+			return -ERESTARTNOHAND;
 		/*
-		 * Report back to the user the time still remaining.
-		 */
-		if (rmtp != NULL && !(flags & TIMER_ABSTIME) &&
-		    copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+	 	 * Report back to the user the time still remaining.
+	 	 */
+		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
-		restart_block->fn = posix_cpu_clock_nanosleep_restart;
-		/* Caller already set restart_block->arg1 */
+		restart_block->fn = posix_cpu_nsleep_restart;
 		restart_block->arg0 = which_clock;
 		restart_block->arg1 = (unsigned long) rmtp;
 		restart_block->arg2 = rqtp->tv_sec;
 		restart_block->arg3 = rqtp->tv_nsec;
-
-		error = -ERESTART_RESTARTBLOCK;
 	}
-
 	return error;
 }
 
-static long
-posix_cpu_clock_nanosleep_restart(struct restart_block *restart_block)
+long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 {
 	clockid_t which_clock = restart_block->arg0;
 	struct timespec __user *rmtp;
 	struct timespec t;
+	struct itimerspec it;
+	int error;
 
 	rmtp = (struct timespec __user *) restart_block->arg1;
 	t.tv_sec = restart_block->arg2;
 	t.tv_nsec = restart_block->arg3;
 
 	restart_block->fn = do_no_restart_syscall;
-	return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t, rmtp);
+	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
+
+	if (error == -ERESTART_RESTARTBLOCK) {
+		/*
+	 	 * Report back to the user the time still remaining.
+	 	 */
+		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+			return -EFAULT;
+
+		restart_block->fn = posix_cpu_nsleep_restart;
+		restart_block->arg0 = which_clock;
+		restart_block->arg1 = (unsigned long) rmtp;
+		restart_block->arg2 = t.tv_sec;
+		restart_block->arg3 = t.tv_nsec;
+	}
+	return error;
+
 }
 
 
@@ -1524,6 +1553,10 @@ static int process_cpu_nsleep(const clockid_t which_clock, int flags,
 {
 	return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
 }
+static long process_cpu_nsleep_restart(struct restart_block *restart_block)
+{
+	return -EINVAL;
+}
 static int thread_cpu_clock_getres(const clockid_t which_clock,
 				   struct timespec *tp)
 {
@@ -1544,6 +1577,10 @@ static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
 {
 	return -EINVAL;
 }
+static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
+{
+	return -EINVAL;
+}
 
 static __init int init_posix_cpu_timers(void)
 {
@@ -1553,6 +1590,7 @@ static __init int init_posix_cpu_timers(void)
 		.clock_set = do_posix_clock_nosettime,
 		.timer_create = process_cpu_timer_create,
 		.nsleep = process_cpu_nsleep,
+		.nsleep_restart = process_cpu_nsleep_restart,
 	};
 	struct k_clock thread = {
 		.clock_getres = thread_cpu_clock_getres,
@@ -1560,6 +1598,7 @@ static __init int init_posix_cpu_timers(void)
 		.clock_set = do_posix_clock_nosettime,
 		.timer_create = thread_cpu_timer_create,
 		.nsleep = thread_cpu_nsleep,
+		.nsleep_restart = thread_cpu_nsleep_restart,
 	};
 
 	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index ac6dc87..e5ebcc1 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -973,3 +973,24 @@ sys_clock_nanosleep(const clockid_t which_clock, int flags,
 	return CLOCK_DISPATCH(which_clock, nsleep,
 			      (which_clock, flags, &t, rmtp));
 }
+
+/*
+ * nanosleep_restart for monotonic and realtime clocks
+ */
+static int common_nsleep_restart(struct restart_block *restart_block)
+{
+	return hrtimer_nanosleep_restart(restart_block);
+}
+
+/*
+ * This will restart clock_nanosleep. This is required only by
+ * compat_clock_nanosleep_restart for now.
+ */
+long
+clock_nanosleep_restart(struct restart_block *restart_block)
+{
+	clockid_t which_clock = restart_block->arg0;
+
+	return CLOCK_DISPATCH(which_clock, nsleep_restart,
+			      (restart_block));
+}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 8aad033..4d50e06 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -440,6 +440,7 @@ struct task_struct *ptrace_get_task_struct(pid_t pid)
 	child = find_task_by_pid(pid);
 	if (child)
 		get_task_struct(child);
+
 	read_unlock(&tasklist_lock);
 	if (!child)
 		return ERR_PTR(-ESRCH);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 4d1c3d2..4f2c427 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -192,13 +192,13 @@ static struct rcu_torture_ops *cur_ops = NULL;
  * Definitions for rcu torture testing.
  */
 
-static int rcu_torture_read_lock(void)
+static int rcu_torture_read_lock(void) __acquires(RCU)
 {
 	rcu_read_lock();
 	return 0;
 }
 
-static void rcu_torture_read_unlock(int idx)
+static void rcu_torture_read_unlock(int idx) __releases(RCU)
 {
 	rcu_read_unlock();
 }
@@ -250,13 +250,13 @@ static struct rcu_torture_ops rcu_ops = {
  * Definitions for rcu_bh torture testing.
  */
 
-static int rcu_bh_torture_read_lock(void)
+static int rcu_bh_torture_read_lock(void) __acquires(RCU_BH)
 {
 	rcu_read_lock_bh();
 	return 0;
 }
 
-static void rcu_bh_torture_read_unlock(int idx)
+static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH)
 {
 	rcu_read_unlock_bh();
 }
diff --git a/kernel/relay.c b/kernel/relay.c
index 85786ff..1d63ecd 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -95,7 +95,7 @@ int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
  *	@buf: the buffer struct
  *	@size: total size of the buffer
  *
- *	Returns a pointer to the resulting buffer, NULL if unsuccessful. The
+ *	Returns a pointer to the resulting buffer, %NULL if unsuccessful. The
  *	passed in size will get page aligned, if it isn't already.
  */
 static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
@@ -132,10 +132,9 @@ depopulate:
 
 /**
  *	relay_create_buf - allocate and initialize a channel buffer
- *	@alloc_size: size of the buffer to allocate
- *	@n_subbufs: number of sub-buffers in the channel
+ *	@chan: the relay channel
  *
- *	Returns channel buffer if successful, NULL otherwise
+ *	Returns channel buffer if successful, %NULL otherwise.
  */
 struct rchan_buf *relay_create_buf(struct rchan *chan)
 {
@@ -163,6 +162,7 @@ free_buf:
 
 /**
  *	relay_destroy_channel - free the channel struct
+ *	@kref: target kernel reference that contains the relay channel
  *
  *	Should only be called from kref_put().
  */
@@ -194,6 +194,7 @@ void relay_destroy_buf(struct rchan_buf *buf)
 
 /**
  *	relay_remove_buf - remove a channel buffer
+ *	@kref: target kernel reference that contains the relay buffer
  *
  *	Removes the file from the fileystem, which also frees the
  *	rchan_buf_struct and the channel buffer.  Should only be called from
@@ -374,7 +375,7 @@ void relay_reset(struct rchan *chan)
 }
 EXPORT_SYMBOL_GPL(relay_reset);
 
-/**
+/*
  *	relay_open_buf - create a new relay channel buffer
  *
  *	Internal - used by relay_open().
@@ -448,12 +449,12 @@ static inline void setup_callbacks(struct rchan *chan,
 /**
  *	relay_open - create a new relay channel
  *	@base_filename: base name of files to create
- *	@parent: dentry of parent directory, NULL for root directory
+ *	@parent: dentry of parent directory, %NULL for root directory
  *	@subbuf_size: size of sub-buffers
  *	@n_subbufs: number of sub-buffers
  *	@cb: client callback functions
  *
- *	Returns channel pointer if successful, NULL otherwise.
+ *	Returns channel pointer if successful, %NULL otherwise.
  *
  *	Creates a channel buffer for each cpu using the sizes and
  *	attributes specified.  The created channel buffer files
@@ -585,7 +586,7 @@ EXPORT_SYMBOL_GPL(relay_switch_subbuf);
  *	subbufs_consumed should be the number of sub-buffers newly consumed,
  *	not the total consumed.
  *
- *	NOTE: kernel clients don't need to call this function if the channel
+ *	NOTE: Kernel clients don't need to call this function if the channel
  *	mode is 'overwrite'.
  */
 void relay_subbufs_consumed(struct rchan *chan,
@@ -641,7 +642,7 @@ EXPORT_SYMBOL_GPL(relay_close);
  *	relay_flush - close the channel
  *	@chan: the channel
  *
- *	Flushes all channel buffers i.e. forces buffer switch.
+ *	Flushes all channel buffers, i.e. forces buffer switch.
  */
 void relay_flush(struct rchan *chan)
 {
@@ -729,7 +730,7 @@ static int relay_file_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-/**
+/*
  *	relay_file_read_consume - update the consumed count for the buffer
  */
 static void relay_file_read_consume(struct rchan_buf *buf,
@@ -756,7 +757,7 @@ static void relay_file_read_consume(struct rchan_buf *buf,
 	}
 }
 
-/**
+/*
  *	relay_file_read_avail - boolean, are there unconsumed bytes available?
  */
 static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
@@ -793,6 +794,8 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
 
 /**
  *	relay_file_read_subbuf_avail - return bytes available in sub-buffer
+ *	@read_pos: file read position
+ *	@buf: relay channel buffer
  */
 static size_t relay_file_read_subbuf_avail(size_t read_pos,
 					   struct rchan_buf *buf)
@@ -818,6 +821,8 @@ static size_t relay_file_read_subbuf_avail(size_t read_pos,
 
 /**
  *	relay_file_read_start_pos - find the first available byte to read
+ *	@read_pos: file read position
+ *	@buf: relay channel buffer
  *
  *	If the read_pos is in the middle of padding, return the
  *	position of the first actually available byte, otherwise
@@ -844,6 +849,9 @@ static size_t relay_file_read_start_pos(size_t read_pos,
 
 /**
  *	relay_file_read_end_pos - return the new read position
+ *	@read_pos: file read position
+ *	@buf: relay channel buffer
+ *	@count: number of bytes to be read
  */
 static size_t relay_file_read_end_pos(struct rchan_buf *buf,
 				      size_t read_pos,
@@ -865,7 +873,7 @@ static size_t relay_file_read_end_pos(struct rchan_buf *buf,
 	return end_pos;
 }
 
-/**
+/*
  *	subbuf_read_actor - read up to one subbuf's worth of data
  */
 static int subbuf_read_actor(size_t read_start,
@@ -890,7 +898,7 @@ static int subbuf_read_actor(size_t read_start,
 	return ret;
 }
 
-/**
+/*
  *	subbuf_send_actor - send up to one subbuf's worth of data
  */
 static int subbuf_send_actor(size_t read_start,
@@ -933,7 +941,7 @@ typedef int (*subbuf_actor_t) (size_t read_start,
 			       read_descriptor_t *desc,
 			       read_actor_t actor);
 
-/**
+/*
  *	relay_file_read_subbufs - read count bytes, bridging subbuf boundaries
  */
 static inline ssize_t relay_file_read_subbufs(struct file *filp,
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 3e13a1e..4ab17da 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -251,6 +251,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* Grab the next task */
 	task = rt_mutex_owner(lock);
+	get_task_struct(task);
 	spin_lock_irqsave(&task->pi_lock, flags);
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
@@ -269,7 +270,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		__rt_mutex_adjust_prio(task);
 	}
 
-	get_task_struct(task);
 	spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	top_waiter = rt_mutex_top_waiter(lock);
@@ -409,7 +409,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
 	unsigned long flags;
-	int boost = 0, res;
+	int chain_walk = 0, res;
 
 	spin_lock_irqsave(&current->pi_lock, flags);
 	__rt_mutex_adjust_prio(current);
@@ -433,25 +433,23 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
 
 		__rt_mutex_adjust_prio(owner);
-		if (owner->pi_blocked_on) {
-			boost = 1;
-			/* gets dropped in rt_mutex_adjust_prio_chain()! */
-			get_task_struct(owner);
-		}
-		spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
-		spin_lock_irqsave(&owner->pi_lock, flags);
-		if (owner->pi_blocked_on) {
-			boost = 1;
-			/* gets dropped in rt_mutex_adjust_prio_chain()! */
-			get_task_struct(owner);
-		}
+		if (owner->pi_blocked_on)
+			chain_walk = 1;
 		spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
-	if (!boost)
+	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+		chain_walk = 1;
+
+	if (!chain_walk)
 		return 0;
 
+	/*
+	 * The owner can't disappear while holding a lock,
+	 * so the owner struct is protected by wait_lock.
+	 * Gets dropped in rt_mutex_adjust_prio_chain()!
+	 */
+	get_task_struct(owner);
+
 	spin_unlock(&lock->wait_lock);
 
 	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
@@ -532,7 +530,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
 	unsigned long flags;
-	int boost = 0;
+	int chain_walk = 0;
 
 	spin_lock_irqsave(&current->pi_lock, flags);
 	plist_del(&waiter->list_entry, &lock->wait_list);
@@ -554,19 +552,20 @@ static void remove_waiter(struct rt_mutex *lock,
 		}
 		__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on) {
-			boost = 1;
-			/* gets dropped in rt_mutex_adjust_prio_chain()! */
-			get_task_struct(owner);
-		}
+		if (owner->pi_blocked_on)
+			chain_walk = 1;
+
 		spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 
-	if (!boost)
+	if (!chain_walk)
 		return;
 
+	/* gets dropped in rt_mutex_adjust_prio_chain()! */
+	get_task_struct(owner);
+
 	spin_unlock(&lock->wait_lock);
 
 	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
@@ -592,10 +591,10 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		return;
 	}
 
-	/* gets dropped in rt_mutex_adjust_prio_chain()! */
-	get_task_struct(task);
 	spin_unlock_irqrestore(&task->pi_lock, flags);
 
+	/* gets dropped in rt_mutex_adjust_prio_chain()! */
+	get_task_struct(task);
 	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
 }
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 5c848fd..74f169a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1755,27 +1755,27 @@ static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	__releases(rq->lock)
 {
 	struct mm_struct *mm = rq->prev_mm;
-	unsigned long prev_task_flags;
+	long prev_state;
 
 	rq->prev_mm = NULL;
 
 	/*
 	 * A task struct has one reference for the use as "current".
-	 * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
-	 * calls schedule one last time. The schedule call will never return,
-	 * and the scheduled task must drop that reference.
-	 * The test for EXIT_ZOMBIE must occur while the runqueue locks are
+	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
+	 * schedule one last time. The schedule call will never return, and
+	 * the scheduled task must drop that reference.
+	 * The test for TASK_DEAD must occur while the runqueue locks are
 	 * still held, otherwise prev could be scheduled on another cpu, die
 	 * there before we look at prev->state, and then the reference would
 	 * be dropped twice.
 	 *		Manfred Spraul <manfred@colorfullife.com>
 	 */
-	prev_task_flags = prev->flags;
+	prev_state = prev->state;
 	finish_arch_switch(prev);
 	finish_lock_switch(rq, prev);
 	if (mm)
 		mmdrop(mm);
-	if (unlikely(prev_task_flags & PF_DEAD)) {
+	if (unlikely(prev_state == TASK_DEAD)) {
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
@@ -3348,9 +3348,6 @@ need_resched_nonpreemptible:
 
 	spin_lock_irq(&rq->lock);
 
-	if (unlikely(prev->flags & PF_DEAD))
-		prev->state = EXIT_DEAD;
-
 	switch_count = &prev->nivcsw;
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
 		switch_count = &prev->nvcsw;
@@ -4080,6 +4077,8 @@ static void __setscheduler(struct task_struct *p, int policy, int prio)
  * @p: the task in question.
  * @policy: new policy.
  * @param: structure containing the new RT priority.
+ *
+ * NOTE: the task may be already dead
  */
 int sched_setscheduler(struct task_struct *p, int policy,
 		       struct sched_param *param)
@@ -4107,28 +4106,32 @@ recheck:
 	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
 	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
-	if ((policy == SCHED_NORMAL || policy == SCHED_BATCH)
-					!= (param->sched_priority == 0))
+	if (is_rt_policy(policy) != (param->sched_priority != 0))
 		return -EINVAL;
 
 	/*
 	 * Allow unprivileged RT tasks to decrease priority:
 	 */
 	if (!capable(CAP_SYS_NICE)) {
-		/*
-		 * can't change policy, except between SCHED_NORMAL
-		 * and SCHED_BATCH:
-		 */
-		if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) &&
-			(policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) &&
-				!p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
-			return -EPERM;
-		/* can't increase priority */
-		if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) &&
-		    param->sched_priority > p->rt_priority &&
-		    param->sched_priority >
-				p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
-			return -EPERM;
+		if (is_rt_policy(policy)) {
+			unsigned long rlim_rtprio;
+			unsigned long flags;
+
+			if (!lock_task_sighand(p, &flags))
+				return -ESRCH;
+			rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+			unlock_task_sighand(p, &flags);
+
+			/* can't set/change the rt policy */
+			if (policy != p->policy && !rlim_rtprio)
+				return -EPERM;
+
+			/* can't increase priority */
+			if (param->sched_priority > p->rt_priority &&
+			    param->sched_priority > rlim_rtprio)
+				return -EPERM;
+		}
+
 		/* can't change other user's priorities */
 		if ((current->euid != p->euid) &&
 		    (current->euid != p->uid))
@@ -4193,14 +4196,13 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 		return -EINVAL;
 	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
 		return -EFAULT;
-	read_lock_irq(&tasklist_lock);
+
+	rcu_read_lock();
+	retval = -ESRCH;
 	p = find_process_by_pid(pid);
-	if (!p) {
-		read_unlock_irq(&tasklist_lock);
-		return -ESRCH;
-	}
-	retval = sched_setscheduler(p, policy, &lparam);
-	read_unlock_irq(&tasklist_lock);
+	if (p != NULL)
+		retval = sched_setscheduler(p, policy, &lparam);
+	rcu_read_unlock();
 
 	return retval;
 }
@@ -5151,7 +5153,7 @@ static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
 	BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD);
 
 	/* Cannot have done final schedule yet: would have vanished. */
-	BUG_ON(p->flags & PF_DEAD);
+	BUG_ON(p->state == TASK_DEAD);
 
 	get_task_struct(p);
 
@@ -5272,9 +5274,11 @@ static struct notifier_block __cpuinitdata migration_notifier = {
 int __init migration_init(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
+	int err;
 
 	/* Start one for the boot CPU: */
-	migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+	err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+	BUG_ON(err == NOTIFY_BAD);
 	migration_call(&migration_notifier, CPU_ONLINE, cpu);
 	register_cpu_notifier(&migration_notifier);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 05853a7..fb5da6d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -417,9 +417,8 @@ static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
 			siginfo_t *info)
 {
-	int sig = 0;
+	int sig = next_signal(pending, mask);
 
-	sig = next_signal(pending, mask);
 	if (sig) {
 		if (current->notifier) {
 			if (sigismember(current->notifier_mask, sig)) {
@@ -432,9 +431,7 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
 
 		if (!collect_signal(sig, pending, info))
 			sig = 0;
-				
 	}
-	recalc_sigpending();
 
 	return sig;
 }
@@ -451,6 +448,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 	if (!signr)
 		signr = __dequeue_signal(&tsk->signal->shared_pending,
 					 mask, info);
+	recalc_sigpending_tsk(tsk);
  	if (signr && unlikely(sig_kernel_stop(signr))) {
  		/*
  		 * Set a marker that we have dequeued a stop signal.  Our
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3789ca9..bf25015 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -612,7 +612,9 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
 __init int spawn_ksoftirqd(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
-	cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+
+	BUG_ON(err == NOTIFY_BAD);
 	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
 	register_cpu_notifier(&cpu_nfb);
 	return 0;
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 03e6a2b..50afeb8 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -149,8 +149,9 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
 __init void spawn_softlockup_task(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
+	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
 
-	cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+	BUG_ON(err == NOTIFY_BAD);
 	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
 	register_cpu_notifier(&cpu_nfb);
 
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 9644a41..d48143e 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -21,17 +21,6 @@
 #include <linux/debug_locks.h>
 #include <linux/module.h>
 
-/*
- * Generic declaration of the raw read_trylock() function,
- * architectures are supposed to optimize this:
- */
-int __lockfunc generic__raw_read_trylock(raw_rwlock_t *lock)
-{
-	__raw_read_lock(lock);
-	return 1;
-}
-EXPORT_SYMBOL(generic__raw_read_trylock);
-
 int __lockfunc _spin_trylock(spinlock_t *lock)
 {
 	preempt_disable();
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 51cacd1..1245804 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,3 +1,6 @@
+/* Copyright 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
+ * GPL v2 and any later version.
+ */
 #include <linux/stop_machine.h>
 #include <linux/kthread.h>
 #include <linux/sched.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index 3f89477..b88806c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -612,7 +612,6 @@ void kernel_restart(char *cmd)
 	} else {
 		printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
 	}
-	printk(".\n");
 	machine_restart(cmd);
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
@@ -2084,12 +2083,12 @@ asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
 		 * padding
 		 */
 		unsigned long t0, t1;
-		get_user(t0, &cache->t0);
-		get_user(t1, &cache->t1);
+		get_user(t0, &cache->blob[0]);
+		get_user(t1, &cache->blob[1]);
 		t0++;
 		t1++;
-		put_user(t0, &cache->t0);
-		put_user(t1, &cache->t1);
+		put_user(t0, &cache->blob[0]);
+		put_user(t1, &cache->blob[1]);
 	}
 	return err ? -EFAULT : 0;
 }
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 6991bec..7a3b2e75 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -134,3 +134,8 @@ cond_syscall(sys_madvise);
 cond_syscall(sys_mremap);
 cond_syscall(sys_remap_file_pages);
 cond_syscall(compat_sys_move_pages);
+
+/* block-layer dependent */
+cond_syscall(sys_bdflush);
+cond_syscall(sys_ioprio_set);
+cond_syscall(sys_ioprio_get);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8bfa7d1..c57c453 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -52,6 +52,10 @@
 extern int proc_nr_files(ctl_table *table, int write, struct file *filp,
                      void __user *buffer, size_t *lenp, loff_t *ppos);
 
+#ifdef CONFIG_X86
+#include <asm/nmi.h>
+#endif
+
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
@@ -74,13 +78,6 @@ extern int sysctl_drop_caches;
 extern int percpu_pagelist_fraction;
 extern int compat_log;
 
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
-int unknown_nmi_panic;
-int nmi_watchdog_enabled;
-extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
-			void __user *, size_t *, loff_t *);
-#endif
-
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
@@ -1915,7 +1912,7 @@ int proc_dointvec_bset(ctl_table *table, int write, struct file *filp,
 		return -EPERM;
 	}
 
-	op = (current->pid == 1) ? OP_SET : OP_AND;
+	op = is_init(current) ? OP_SET : OP_AND;
 	return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
 				do_proc_dointvec_bset_conv,&op);
 }
diff --git a/kernel/timer.c b/kernel/timer.c
index 1d7dd62..4f55622 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -136,7 +136,7 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer)
 	list_add_tail(&timer->entry, vec);
 }
 
-/***
+/**
  * init_timer - initialize a timer.
  * @timer: the timer to be initialized
  *
@@ -175,6 +175,7 @@ static inline void detach_timer(struct timer_list *timer,
  */
 static tvec_base_t *lock_timer_base(struct timer_list *timer,
 					unsigned long *flags)
+	__acquires(timer->base->lock)
 {
 	tvec_base_t *base;
 
@@ -235,7 +236,7 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 
 EXPORT_SYMBOL(__mod_timer);
 
-/***
+/**
  * add_timer_on - start a timer on a particular CPU
  * @timer: the timer to be added
  * @cpu: the CPU to start it on
@@ -255,9 +256,10 @@ void add_timer_on(struct timer_list *timer, int cpu)
 }
 
 
-/***
+/**
  * mod_timer - modify a timer's timeout
  * @timer: the timer to be modified
+ * @expires: new timeout in jiffies
  *
  * mod_timer is a more efficient way to update the expire field of an
  * active timer (if the timer is inactive it will be activated)
@@ -291,7 +293,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 
 EXPORT_SYMBOL(mod_timer);
 
-/***
+/**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
  *
@@ -323,7 +325,10 @@ int del_timer(struct timer_list *timer)
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
-/*
+/**
+ * try_to_del_timer_sync - Try to deactivate a timer
+ * @timer: timer do del
+ *
  * This function tries to deactivate a timer. Upon successful (ret >= 0)
  * exit the timer is not queued and the handler is not running on any CPU.
  *
@@ -351,7 +356,7 @@ out:
 	return ret;
 }
 
-/***
+/**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
  *
@@ -401,15 +406,15 @@ static int cascade(tvec_base_t *base, tvec_t *tv, int index)
 	return index;
 }
 
-/***
+#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
+
+/**
  * __run_timers - run all expired timers (if any) on this CPU.
  * @base: the timer vector to be processed.
  *
  * This function cascades all vectors and executes all expired timer
  * vectors.
  */
-#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
-
 static inline void __run_timers(tvec_base_t *base)
 {
 	struct timer_list *timer;
@@ -970,7 +975,7 @@ void __init timekeeping_init(void)
 
 
 static int timekeeping_suspended;
-/*
+/**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
  * @dev:	unused
  *
@@ -1106,7 +1111,7 @@ static void clocksource_adjust(struct clocksource *clock, s64 offset)
 	clock->error -= (interval - offset) << (TICK_LENGTH_SHIFT - clock->shift);
 }
 
-/*
+/**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
  * Called from the timer interrupt, must hold a write on xtime_lock.
@@ -1217,10 +1222,8 @@ static inline void calc_load(unsigned long ticks)
 	unsigned long active_tasks; /* fixed-point */
 	static int count = LOAD_FREQ;
 
-	count -= ticks;
-	if (count < 0) {
-		count += LOAD_FREQ;
-		active_tasks = count_active_tasks();
+	active_tasks = count_active_tasks();
+	for (count -= ticks; count < 0; count += LOAD_FREQ) {
 		CALC_LOAD(avenrun[0], EXP_1, active_tasks);
 		CALC_LOAD(avenrun[1], EXP_5, active_tasks);
 		CALC_LOAD(avenrun[2], EXP_15, active_tasks);
@@ -1265,11 +1268,8 @@ void run_local_timers(void)
  * Called by the timer interrupt. xtime_lock must already be taken
  * by the timer IRQ!
  */
-static inline void update_times(void)
+static inline void update_times(unsigned long ticks)
 {
-	unsigned long ticks;
-
-	ticks = jiffies - wall_jiffies;
 	wall_jiffies += ticks;
 	update_wall_time();
 	calc_load(ticks);
@@ -1281,12 +1281,10 @@ static inline void update_times(void)
  * jiffies is defined in the linker script...
  */
 
-void do_timer(struct pt_regs *regs)
+void do_timer(unsigned long ticks)
 {
-	jiffies_64++;
-	/* prevent loading jiffies before storing new jiffies_64 value. */
-	barrier();
-	update_times();
+	jiffies_64 += ticks;
+	update_times(ticks);
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM
@@ -1470,8 +1468,9 @@ asmlinkage long sys_gettid(void)
 	return current->pid;
 }
 
-/*
+/**
  * sys_sysinfo - fill in sysinfo struct
+ * @info: pointer to buffer to fill
  */ 
 asmlinkage long sys_sysinfo(struct sysinfo __user *info)
 {
@@ -1688,8 +1687,10 @@ static struct notifier_block __cpuinitdata timers_nb = {
 
 void __init init_timers(void)
 {
-	timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
+	int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
 				(void *)(long)smp_processor_id());
+
+	BUG_ON(err == NOTIFY_BAD);
 	register_cpu_notifier(&timers_nb);
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
 }
diff --git a/kernel/unwind.c b/kernel/unwind.c
index 3430475..2e23686 100644
--- a/kernel/unwind.c
+++ b/kernel/unwind.c
@@ -102,7 +102,7 @@ static struct unwind_table {
 	unsigned long size;
 	struct unwind_table *link;
 	const char *name;
-} root_table, *last_table;
+} root_table;
 
 struct unwind_item {
 	enum item_location {
@@ -174,6 +174,8 @@ void __init unwind_init(void)
 
 #ifdef CONFIG_MODULES
 
+static struct unwind_table *last_table;
+
 /* Must be called with module_mutex held. */
 void *unwind_add_table(struct module *module,
                        const void *table_start,