Merge commit 'v2.6.29' into x86/setup-lzma

71 files changed, 1272 insertions, 631 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 2921d90ce32f..e4791b3ba55d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -41,6 +41,9 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o
+ifneq ($(CONFIG_SMP),y)
+obj-y += up.o
+endif
 obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
@@ -48,6 +51,7 @@ obj-$(CONFIG_UID16) += uid16.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_PM) += power/
+obj-$(CONFIG_FREEZER) += power/
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
diff --git a/kernel/acct.c b/kernel/acct.c
index d57b7cbb98b6..7afa31564162 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -277,7 +277,7 @@ static int acct_on(char *name)
  * should be written. If the filename is NULL, accounting will be
  * shutdown.
  */
-asmlinkage long sys_acct(const char __user *name)
+SYSCALL_DEFINE1(acct, const char __user *, name)
 {
 	int error;
 
diff --git a/kernel/async.c b/kernel/async.c
index f286e9f2b736..f565891f2c9b 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -54,6 +54,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/kthread.h>
+#include <linux/delay.h>
 #include <asm/atomic.h>
 
 static async_cookie_t next_cookie = 1;
@@ -90,12 +91,12 @@ extern int initcall_debug;
 static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
-	if (!list_empty(&async_pending)) {
-		entry = list_first_entry(&async_pending,
+	if (!list_empty(running)) {
+		entry = list_first_entry(running,
 			struct async_entry, list);
 		return entry->cookie;
-	} else if (!list_empty(running)) {
-		entry = list_first_entry(running,
+	} else if (!list_empty(&async_pending)) {
+		entry = list_first_entry(&async_pending,
 			struct async_entry, list);
 		return entry->cookie;
 	} else {
@@ -104,6 +105,17 @@ static async_cookie_t  __lowest_in_progress(struct list_head *running)
 	}
 
 }
+
+static async_cookie_t  lowest_in_progress(struct list_head *running)
+{
+	unsigned long flags;
+	async_cookie_t ret;
+
+	spin_lock_irqsave(&async_lock, flags);
+	ret = __lowest_in_progress(running);
+	spin_unlock_irqrestore(&async_lock, flags);
+	return ret;
+}
 /*
  * pick the first pending entry and run it
  */
@@ -121,21 +133,23 @@ static void run_one_entry(void)
 	entry = list_first_entry(&async_pending, struct async_entry, list);
 
 	/* 2) move it to the running queue */
-	list_del(&entry->list);
-	list_add_tail(&entry->list, &async_running);
+	list_move_tail(&entry->list, entry->running);
 	spin_unlock_irqrestore(&async_lock, flags);
 
 	/* 3) run it (and print duration)*/
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
-		printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+		printk("calling  %lli_%pF @ %i\n", (long long)entry->cookie,
+			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
 	}
 	entry->func(entry->data, entry->cookie);
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
-		printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
-			entry->func, ktime_to_ns(delta) >> 10);
+		printk("initcall %lli_%pF returned 0 after %lld usecs\n",
+			(long long)entry->cookie,
+			entry->func,
+			(long long)ktime_to_ns(delta) >> 10);
 	}
 
 	/* 4) remove it from the running queue */
@@ -194,18 +208,44 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l
 	return newcookie;
 }
 
+/**
+ * async_schedule - schedule a function for asynchronous execution
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
 async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
 {
-	return __async_schedule(ptr, data, &async_pending);
+	return __async_schedule(ptr, data, &async_running);
 }
 EXPORT_SYMBOL_GPL(async_schedule);
 
-async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+/**
+ * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ * @running: running list for the domain
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * @running may be used in the async_synchronize_*_domain() functions
+ * to wait within a certain synchronization domain rather than globally.
+ * A synchronization domain is specified via the running queue @running to use.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
+async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
+				     struct list_head *running)
 {
 	return __async_schedule(ptr, data, running);
 }
-EXPORT_SYMBOL_GPL(async_schedule_special);
+EXPORT_SYMBOL_GPL(async_schedule_domain);
 
+/**
+ * async_synchronize_full - synchronize all asynchronous function calls
+ *
+ * This function waits until all asynchronous function calls have been done.
+ */
 void async_synchronize_full(void)
 {
 	do {
@@ -214,13 +254,30 @@ void async_synchronize_full(void)
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
-void async_synchronize_full_special(struct list_head *list)
+/**
+ * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
+ * @list: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list have been done.
+ */
+void async_synchronize_full_domain(struct list_head *list)
 {
-	async_synchronize_cookie_special(next_cookie, list);
+	async_synchronize_cookie_domain(next_cookie, list);
 }
-EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
 
-void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+/**
+ * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ * @running: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list submitted
+ * prior to @cookie have been done.
+ */
+void async_synchronize_cookie_domain(async_cookie_t cookie,
+				     struct list_head *running)
 {
 	ktime_t starttime, delta, endtime;
 
@@ -229,21 +286,29 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r
 		starttime = ktime_get();
 	}
 
-	wait_event(async_done, __lowest_in_progress(running) >= cookie);
+	wait_event(async_done, lowest_in_progress(running) >= cookie);
 
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		endtime = ktime_get();
 		delta = ktime_sub(endtime, starttime);
 
 		printk("async_continuing @ %i after %lli usec\n",
-			task_pid_nr(current), ktime_to_ns(delta) >> 10);
+			task_pid_nr(current),
+			(long long)ktime_to_ns(delta) >> 10);
 	}
 }
-EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain);
 
+/**
+ * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ *
+ * This function waits until all asynchronous function calls prior to @cookie
+ * have been done.
+ */
 void async_synchronize_cookie(async_cookie_t cookie)
 {
-	async_synchronize_cookie_special(cookie, &async_running);
+	async_synchronize_cookie_domain(cookie, &async_running);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_cookie);
 
@@ -304,7 +369,11 @@ static int async_manager_thread(void *unused)
 		ec = atomic_read(&entry_count);
 
 		while (tc < ec && tc < MAX_THREADS) {
-			kthread_run(async_thread, NULL, "async/%i", tc);
+			if (IS_ERR(kthread_run(async_thread, NULL, "async/%i",
+					       tc))) {
+				msleep(100);
+				continue;
+			}
 			atomic_inc(&thread_count);
 			tc++;
 		}
@@ -319,7 +388,9 @@ static int async_manager_thread(void *unused)
 static int __init async_init(void)
 {
 	if (async_enabled)
-		kthread_run(async_manager_thread, NULL, "async/mgr");
+		if (IS_ERR(kthread_run(async_manager_thread, NULL,
+				       "async/mgr")))
+			async_enabled = 0;
 	return 0;
 }
 
diff --git a/kernel/capability.c b/kernel/capability.c
index 688926e496be..4e17041963f5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -161,7 +161,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
  *
  * Returns 0 on success and < 0 on error.
  */
-asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
+SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 {
 	int ret = 0;
 	pid_t pid;
@@ -235,7 +235,7 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
  *
  * Returns 0 on success and < 0 on error.
  */
-asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
+SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 {
 	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 	unsigned i, tocopy;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c29831076e7a..9edb5c4b79b4 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1115,13 +1115,15 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	}
 	write_unlock(&css_set_lock);
 
-	list_del(&root->root_list);
-	root_count--;
+	if (!list_empty(&root->root_list)) {
+		list_del(&root->root_list);
+		root_count--;
+	}
 
 	mutex_unlock(&cgroup_mutex);
 
-	kfree(root);
 	kill_litter_super(sb);
+	kfree(root);
 }
 
 static struct file_system_type cgroup_fs_type = {
@@ -2349,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
 		if (ss->root == root)
-			mutex_lock_nested(&ss->hierarchy_mutex, i);
+			mutex_lock(&ss->hierarchy_mutex);
 	}
 }
 
@@ -2434,7 +2436,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
  err_remove:
 
+	cgroup_lock_hierarchy(root);
 	list_del(&cgrp->sibling);
+	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups--;
 
  err_destroy:
@@ -2507,7 +2511,7 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
 		int refcnt;
-		do {
+		while (1) {
 			/* We can only remove a CSS with a refcnt==1 */
 			refcnt = atomic_read(&css->refcnt);
 			if (refcnt > 1) {
@@ -2521,7 +2525,10 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 			 * css_tryget() to spin until we set the
 			 * CSS_REMOVED bits or abort
 			 */
-		} while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+			if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
+				break;
+			cpu_relax();
+		}
 	}
  done:
 	for_each_subsys(cgrp->root, ss) {
@@ -2630,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(!list_empty(&init_task.tasks));
 
 	mutex_init(&ss->hierarchy_mutex);
+	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
 	ss->active = 1;
 }
 
@@ -2991,20 +2999,21 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
-	task_lock(tsk);
-	cg = tsk->cgroups;
-	parent = task_cgroup(tsk, subsys->subsys_id);
 
 	/* Pin the hierarchy */
-	if (!atomic_inc_not_zero(&parent->root->sb->s_active)) {
+	if (!atomic_inc_not_zero(&root->sb->s_active)) {
 		/* We race with the final deactivate_super() */
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
 
 	/* Keep the cgroup alive */
+	task_lock(tsk);
+	parent = task_cgroup(tsk, subsys->subsys_id);
+	cg = tsk->cgroups;
 	get_css_set(cg);
 	task_unlock(tsk);
+
 	mutex_unlock(&cgroup_mutex);
 
 	/* Now do the VFS work to create a cgroup */
@@ -3043,7 +3052,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&inode->i_mutex);
 		put_css_set(cg);
 
-		deactivate_super(parent->root->sb);
+		deactivate_super(root->sb);
 		/* The cgroup is still accessible in the VFS, but
 		 * we're not going to try to rmdir() it at this
 		 * point. */
@@ -3069,7 +3078,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 	mutex_lock(&cgroup_mutex);
 	put_css_set(cg);
 	mutex_unlock(&cgroup_mutex);
-	deactivate_super(parent->root->sb);
+	deactivate_super(root->sb);
 	return ret;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 647c77a88fcb..f76db9dcaa05 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -61,6 +61,14 @@
 #include <linux/cgroup.h>
 
 /*
+ * Workqueue for cpuset related tasks.
+ *
+ * Using kevent workqueue may cause deadlock when memory_migrate
+ * is set. So we create a separate workqueue thread for cpuset.
+ */
+static struct workqueue_struct *cpuset_wq;
+
+/*
  * Tracks how many cpusets are currently defined in system.
  * When there is only one cpuset (the root cpuset) we can
  * short circuit some hooks.
@@ -568,7 +576,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  * load balancing domains (sched domains) as specified by that partial
  * partition.
  *
- * See "What is sched_load_balance" in Documentation/cpusets.txt
+ * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt
  * for a background explanation of this.
  *
  * Does not return errors, on the theory that the callers of this
@@ -831,7 +839,7 @@ static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
  */
 static void async_rebuild_sched_domains(void)
 {
-	schedule_work(&rebuild_sched_domains_work);
+	queue_work(cpuset_wq, &rebuild_sched_domains_work);
 }
 
 /*
@@ -2111,6 +2119,9 @@ void __init cpuset_init_smp(void)
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
+
+	cpuset_wq = create_singlethread_workqueue("cpuset");
+	BUG_ON(!cpuset_wq);
 }
 
 /**
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index 038707404b76..962a3b574f21 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
  * @size:	size of requested memory area
  * @dma_handle:	This will be filled with the correct dma handle
  * @ret:	This pointer will be filled with the virtual address
- * 		to allocated area.
+ *		to allocated area.
  *
  * This function should be only called from per-arch dma_alloc_coherent()
  * to support allocation from per-device coherent memory pools.
@@ -118,31 +118,32 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 	mem = dev->dma_mem;
 	if (!mem)
 		return 0;
-	if (unlikely(size > mem->size))
- 		return 0;
+
+	*ret = NULL;
+
+	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+		goto err;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
-	if (pageno >= 0) {
-		/*
-		 * Memory was found in the per-device arena.
-		 */
-		*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
-		*ret = mem->virt_base + (pageno << PAGE_SHIFT);
-		memset(*ret, 0, size);
-	} else if (mem->flags & DMA_MEMORY_EXCLUSIVE) {
-		/*
-		 * The per-device arena is exhausted and we are not
-		 * permitted to fall back to generic memory.
-		 */
-		*ret = NULL;
-	} else {
-		/*
-		 * The per-device arena is exhausted and we are
-		 * permitted to fall back to generic memory.
-		 */
-		 return 0;
-	}
+	if (unlikely(pageno < 0))
+		goto err;
+
+	/*
+	 * Memory was found in the per-device area.
+	 */
+	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	memset(*ret, 0, size);
+
 	return 1;
+
+err:
+	/*
+	 * In the case where the allocation can not be satisfied from the
+	 * per-device area, try to fall back to generic memory if the
+	 * constraints allow it.
+	 */
+	return mem->flags & DMA_MEMORY_EXCLUSIVE;
 }
 EXPORT_SYMBOL(dma_alloc_from_coherent);
 
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 0511716e9424..667c841c2952 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -209,8 +209,7 @@ static int __init proc_execdomains_init(void)
 module_init(proc_execdomains_init);
 #endif
 
-asmlinkage long
-sys_personality(u_long personality)
+SYSCALL_DEFINE1(personality, u_long, personality)
 {
 	u_long old = current->personality;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c7740fa3252c..efd30ccf3858 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
+		sig->utime = cputime_add(sig->utime, task_utime(tsk));
+		sig->stime = cputime_add(sig->stime, task_stime(tsk));
 		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
@@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
 		task_io_accounting_add(&sig->ioac, &tsk->ioac);
+		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
 
@@ -1141,7 +1144,7 @@ NORET_TYPE void complete_and_exit(struct completion *comp, long code)
 
 EXPORT_SYMBOL(complete_and_exit);
 
-asmlinkage long sys_exit(int error_code)
+SYSCALL_DEFINE1(exit, int, error_code)
 {
 	do_exit((error_code&0xff)<<8);
 }
@@ -1182,9 +1185,11 @@ do_group_exit(int exit_code)
  * wait4()-ing process will get the correct exit code - even if this
  * thread is not the thread group leader.
  */
-asmlinkage void sys_exit_group(int error_code)
+SYSCALL_DEFINE1(exit_group, int, error_code)
 {
 	do_group_exit((error_code & 0xff) << 8);
+	/* NOTREACHED */
+	return 0;
 }
 
 static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
@@ -1752,9 +1757,8 @@ end:
 	return retval;
 }
 
-asmlinkage long sys_waitid(int which, pid_t upid,
-			   struct siginfo __user *infop, int options,
-			   struct rusage __user *ru)
+SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
+		infop, int, options, struct rusage __user *, ru)
 {
 	struct pid *pid = NULL;
 	enum pid_type type;
@@ -1793,8 +1797,8 @@ asmlinkage long sys_waitid(int which, pid_t upid,
 	return ret;
 }
 
-asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr,
-			  int options, struct rusage __user *ru)
+SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
+		int, options, struct rusage __user *, ru)
 {
 	struct pid *pid = NULL;
 	enum pid_type type;
@@ -1831,7 +1835,7 @@ asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr,
  * sys_waitpid() remains for compatibility. waitpid() should be
  * implemented by calling sys_wait4() from libc.a.
  */
-asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options)
+SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
 {
 	return sys_wait4(pid, stat_addr, options, NULL);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 1d68f1255dd8..4854c2c4a82e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -817,17 +817,17 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
-	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
-		ret = thread_group_cputime_clone_thread(current);
-		if (likely(!ret)) {
-			atomic_inc(&current->signal->count);
-			atomic_inc(&current->signal->live);
-		}
-		return ret;
+		atomic_inc(&current->signal->count);
+		atomic_inc(&current->signal->live);
+		return 0;
 	}
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+
+	if (sig)
+		posix_cpu_timers_init_group(sig);
+
 	tsk->signal = sig;
 	if (!sig)
 		return -ENOMEM;
@@ -851,21 +851,20 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->tty_old_pgrp = NULL;
 	sig->tty = NULL;
 
-	sig->cutime = sig->cstime = cputime_zero;
+	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
 	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;
 	task_io_accounting_init(&sig->ioac);
+	sig->sum_sched_runtime = 0;
 	taskstats_tgid_init(sig);
 
 	task_lock(current->group_leader);
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
-	posix_cpu_timers_init_group(sig);
-
 	acct_init_pacct(&sig->pacct);
 
 	tty_audit_fork(sig);
@@ -901,7 +900,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 	clear_freeze_flag(p);
 }
 
-asmlinkage long sys_set_tid_address(int __user *tidptr)
+SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 {
 	current->clear_child_tid = tidptr;
 
@@ -1007,6 +1006,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * triggers too late. This doesn't hurt, the check is only there
 	 * to stop root fork bombs.
 	 */
+	retval = -EAGAIN;
 	if (nr_threads >= max_threads)
 		goto bad_fork_cleanup_count;
 
@@ -1095,7 +1095,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-	if (unlikely(ptrace_reparented(current)))
+	if (unlikely(current->ptrace))
 		ptrace_fork(p, clone_flags);
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
@@ -1179,10 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 	clear_all_latency_tracing(p);
 
-	/* 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.. */
 	p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
 	p->pdeath_signal = 0;
@@ -1220,10 +1216,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		set_task_cpu(p, smp_processor_id());
 
 	/* CLONE_PARENT re-uses the old parent */
-	if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
+	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
-	else
+		p->parent_exec_id = current->parent_exec_id;
+	} else {
 		p->real_parent = current;
+		p->parent_exec_id = current->self_exec_id;
+	}
 
 	spin_lock(&current->sighand->siglock);
 
@@ -1603,7 +1602,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
  * constructed. Here we are modifying the current, active,
  * task_struct.
  */
-asmlinkage long sys_unshare(unsigned long unshare_flags)
+SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
 	int err = 0;
 	struct fs_struct *fs, *new_fs = NULL;
diff --git a/kernel/futex.c b/kernel/futex.c
index 002aa189eb09..438701adce23 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1165,6 +1165,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
 	struct task_struct *curr = current;
+	struct restart_block *restart;
 	DECLARE_WAITQUEUE(wait, curr);
 	struct futex_hash_bucket *hb;
 	struct futex_q q;
@@ -1216,11 +1217,13 @@ retry:
 
 		if (!ret)
 			goto retry;
-		return ret;
+		goto out;
 	}
 	ret = -EWOULDBLOCK;
-	if (uval != val)
-		goto out_unlock_put_key;
+	if (unlikely(uval != val)) {
+		queue_unlock(&q, hb);
+		goto out_put_key;
+	}
 
 	/* Only actually queue if *uaddr contained val.  */
 	queue_me(&q, hb);
@@ -1284,38 +1287,38 @@ retry:
 	 */
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
+	ret = 0;
 	if (!unqueue_me(&q))
-		return 0;
+		goto out_put_key;
+	ret = -ETIMEDOUT;
 	if (rem)
-		return -ETIMEDOUT;
+		goto out_put_key;
 
 	/*
 	 * We expect signal_pending(current), but another thread may
 	 * have handled it for us already.
 	 */
+	ret = -ERESTARTSYS;
 	if (!abs_time)
-		return -ERESTARTSYS;
-	else {
-		struct restart_block *restart;
-		restart = &current_thread_info()->restart_block;
-		restart->fn = futex_wait_restart;
-		restart->futex.uaddr = (u32 *)uaddr;
-		restart->futex.val = val;
-		restart->futex.time = abs_time->tv64;
-		restart->futex.bitset = bitset;
-		restart->futex.flags = 0;
-
-		if (fshared)
-			restart->futex.flags |= FLAGS_SHARED;
-		if (clockrt)
-			restart->futex.flags |= FLAGS_CLOCKRT;
-		return -ERESTART_RESTARTBLOCK;
-	}
+		goto out_put_key;
 
-out_unlock_put_key:
-	queue_unlock(&q, hb);
-	put_futex_key(fshared, &q.key);
+	restart = &current_thread_info()->restart_block;
+	restart->fn = futex_wait_restart;
+	restart->futex.uaddr = (u32 *)uaddr;
+	restart->futex.val = val;
+	restart->futex.time = abs_time->tv64;
+	restart->futex.bitset = bitset;
+	restart->futex.flags = 0;
+
+	if (fshared)
+		restart->futex.flags |= FLAGS_SHARED;
+	if (clockrt)
+		restart->futex.flags |= FLAGS_CLOCKRT;
 
+	ret = -ERESTART_RESTARTBLOCK;
+
+out_put_key:
+	put_futex_key(fshared, &q.key);
 out:
 	return ret;
 }
@@ -1733,9 +1736,8 @@ pi_faulted:
  * @head: pointer to the list-head
  * @len: length of the list-head, as userspace expects
  */
-asmlinkage long
-sys_set_robust_list(struct robust_list_head __user *head,
-		    size_t len)
+SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
+		size_t, len)
 {
 	if (!futex_cmpxchg_enabled)
 		return -ENOSYS;
@@ -1756,9 +1758,9 @@ sys_set_robust_list(struct robust_list_head __user *head,
  * @head_ptr: pointer to a list-head pointer, the kernel fills it in
  * @len_ptr: pointer to a length field, the kernel fills in the header size
  */
-asmlinkage long
-sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
-		    size_t __user *len_ptr)
+SYSCALL_DEFINE3(get_robust_list, int, pid,
+		struct robust_list_head __user * __user *, head_ptr,
+		size_t __user *, len_ptr)
 {
 	struct robust_list_head __user *head;
 	unsigned long ret;
@@ -1978,9 +1980,9 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 }
 
 
-asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
-			  struct timespec __user *utime, u32 __user *uaddr2,
-			  u32 val3)
+SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
+		struct timespec __user *, utime, u32 __user *, uaddr2,
+		u32, val3)
 {
 	struct timespec ts;
 	ktime_t t, *tp = NULL;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 1455b7651b6b..f394d2a42ca3 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -501,6 +501,13 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
 			continue;
 		timer = rb_entry(base->first, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+		/*
+		 * clock_was_set() has changed base->offset so the
+		 * result might be negative. Fix it up to prevent a
+		 * false positive in clockevents_program_event()
+		 */
+		if (expires.tv64 < 0)
+			expires.tv64 = 0;
 		if (expires.tv64 < cpu_base->expires_next.tv64)
 			cpu_base->expires_next = expires;
 	}
@@ -614,7 +621,9 @@ void clock_was_set(void)
  */
 void hres_timers_resume(void)
 {
-	/* Retrigger the CPU local events: */
+	WARN_ONCE(!irqs_disabled(),
+		  KERN_INFO "hres_timers_resume() called with IRQs enabled!");
+
 	retrigger_next_event(NULL);
 }
 
@@ -1156,6 +1165,29 @@ static void __run_hrtimer(struct hrtimer *timer)
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
+static int force_clock_reprogram;
+
+/*
+ * After 5 iteration's attempts, we consider that hrtimer_interrupt()
+ * is hanging, which could happen with something that slows the interrupt
+ * such as the tracing. Then we force the clock reprogramming for each future
+ * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
+ * threshold that we will overwrite.
+ * The next tick event will be scheduled to 3 times we currently spend on
+ * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
+ * 1/4 of their time to process the hrtimer interrupts. This is enough to
+ * let it running without serious starvation.
+ */
+
+static inline void
+hrtimer_interrupt_hanging(struct clock_event_device *dev,
+			ktime_t try_time)
+{
+	force_clock_reprogram = 1;
+	dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
+	printk(KERN_WARNING "hrtimer: interrupt too slow, "
+		"forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+}
 /*
  * High resolution timer interrupt
  * Called with interrupts disabled
@@ -1165,6 +1197,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	ktime_t expires_next, now;
+	int nr_retries = 0;
 	int i;
 
 	BUG_ON(!cpu_base->hres_active);
@@ -1172,6 +1205,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	dev->next_event.tv64 = KTIME_MAX;
 
  retry:
+	/* 5 retries is enough to notice a hang */
+	if (!(++nr_retries % 5))
+		hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
+
 	now = ktime_get();
 
 	expires_next.tv64 = KTIME_MAX;
@@ -1224,7 +1261,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 	/* Reprogramming necessary ? */
 	if (expires_next.tv64 != KTIME_MAX) {
-		if (tick_program_event(expires_next, 0))
+		if (tick_program_event(expires_next, force_clock_reprogram))
 			goto retry;
 	}
 }
@@ -1467,8 +1504,8 @@ out:
 	return ret;
 }
 
-asmlinkage long
-sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
+SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
+		struct timespec __user *, rmtp)
 {
 	struct timespec tu;
 
@@ -1578,6 +1615,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
+		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 	{
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f63c706d25e1..7de11bd64dfe 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -383,6 +383,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 out_unlock:
 	spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_level_irq);
 
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
@@ -593,6 +594,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	}
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__set_irq_handler);
 
 void
 set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index c20db0be9173..3aba8d12f328 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -39,6 +39,18 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 	ack_bad_irq(irq);
 }
 
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+static void __init init_irq_default_affinity(void)
+{
+	alloc_bootmem_cpumask_var(&irq_default_affinity);
+	cpumask_setall(irq_default_affinity);
+}
+#else
+static void __init init_irq_default_affinity(void)
+{
+}
+#endif
+
 /*
  * Linux has a controller-independent interrupt architecture.
  * Every controller has a 'controller-template', that is used
@@ -134,6 +146,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	init_irq_default_affinity();
+
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
@@ -219,6 +233,8 @@ int __init early_irq_init(void)
 	int count;
 	int i;
 
+	init_irq_default_affinity();
+
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index cd0cd8dcb345..291f03664552 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -15,17 +15,9 @@
 
 #include "internals.h"
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 cpumask_var_t irq_default_affinity;
 
-static int init_irq_default_affinity(void)
-{
-	alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL);
-	cpumask_setall(irq_default_affinity);
-	return 0;
-}
-core_initcall(init_irq_default_affinity);
-
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index ecf765c6a77a..acd88356ac76 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -71,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	desc = irq_desc_ptrs[irq];
 
 	if (desc && old_desc != desc)
-			goto out_unlock;
+		goto out_unlock;
 
 	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
@@ -84,10 +84,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
+	spin_unlock_irqrestore(&sparse_irq_lock, flags);
 
 	/* free the old one */
 	free_one_irq_desc(old_desc, desc);
+	spin_unlock(&old_desc->lock);
 	kfree(old_desc);
+	spin_lock(&desc->lock);
+
+	return desc;
 
 out_unlock:
 	spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/itimer.c b/kernel/itimer.c
index db7c358b9a02..58762f7077ec 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value)
 			struct task_cputime cputime;
 			cputime_t utime;
 
-			thread_group_cputime(tsk, &cputime);
+			thread_group_cputimer(tsk, &cputime);
 			utime = cputime.utime;
 			if (cputime_le(cval, utime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
@@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value)
 			struct task_cputime times;
 			cputime_t ptime;
 
-			thread_group_cputime(tsk, &times);
+			thread_group_cputimer(tsk, &times);
 			ptime = cputime_add(times.utime, times.stime);
 			if (cputime_le(cval, ptime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
@@ -100,7 +100,7 @@ int do_getitimer(int which, struct itimerval *value)
 	return 0;
 }
 
-asmlinkage long sys_getitimer(int which, struct itimerval __user *value)
+SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value)
 {
 	int error = -EFAULT;
 	struct itimerval get_buffer;
@@ -260,9 +260,8 @@ unsigned int alarm_setitimer(unsigned int seconds)
 	return it_old.it_value.tv_sec;
 }
 
-asmlinkage long sys_setitimer(int which,
-			      struct itimerval __user *value,
-			      struct itimerval __user *ovalue)
+SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value,
+		struct itimerval __user *, ovalue)
 {
 	struct itimerval set_buffer, get_buffer;
 	int error;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index e694afa0eb8c..7b8b0f21a5b1 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,19 +30,20 @@
 #define all_var 0
 #endif
 
-extern const unsigned long kallsyms_addresses[];
-extern const u8 kallsyms_names[];
+/* These will be re-linked against their real values during the second link stage */
+extern const unsigned long kallsyms_addresses[] __attribute__((weak));
+extern const u8 kallsyms_names[] __attribute__((weak));
 
 /* tell the compiler that the count isn't in the small data section if the arch
  * has one (eg: FRV)
  */
 extern const unsigned long kallsyms_num_syms
-	__attribute__((__section__(".rodata")));
+__attribute__((weak, section(".rodata")));
 
-extern const u8 kallsyms_token_table[];
-extern const u16 kallsyms_token_index[];
+extern const u8 kallsyms_token_table[] __attribute__((weak));
+extern const u16 kallsyms_token_index[] __attribute__((weak));
 
-extern const unsigned long kallsyms_markers[];
+extern const unsigned long kallsyms_markers[] __attribute__((weak));
 
 static inline int is_kernel_inittext(unsigned long addr)
 {
@@ -167,6 +168,9 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	unsigned long symbol_start = 0, symbol_end = 0;
 	unsigned long i, low, high, mid;
 
+	/* This kernel should never had been booted. */
+	BUG_ON(!kallsyms_addresses);
+
 	/* do a binary search on the sorted kallsyms_addresses array */
 	low = 0;
 	high = kallsyms_num_syms;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 3fb855ad6aa0..483899578259 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -934,9 +934,8 @@ struct kimage *kexec_crash_image;
 
 static DEFINE_MUTEX(kexec_mutex);
 
-asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
-				struct kexec_segment __user *segments,
-				unsigned long flags)
+SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
+		struct kexec_segment __user *, segments, unsigned long, flags)
 {
 	struct kimage **dest_image, *image;
 	int result;
@@ -1466,6 +1465,11 @@ int kernel_kexec(void)
 		error = device_power_down(PMSG_FREEZE);
 		if (error)
 			goto Enable_irqs;
+
+		/* Suspend system devices */
+		error = sysdev_suspend(PMSG_FREEZE);
+		if (error)
+			goto Power_up_devices;
 	} else
 #endif
 	{
@@ -1478,6 +1482,8 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
+		sysdev_resume();
+ Power_up_devices:
 		device_power_up(PMSG_RESTORE);
  Enable_irqs:
 		local_irq_enable();
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1b9cbdc0127a..7ba8cd9845cb 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -123,7 +123,7 @@ static int collect_garbage_slots(void);
 static int __kprobes check_safety(void)
 {
 	int ret = 0;
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_PM)
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_FREEZER)
 	ret = freeze_processes();
 	if (ret == 0) {
 		struct task_struct *p, *q;
diff --git a/kernel/module.c b/kernel/module.c
index c9332c90d5a0..1196f5d11700 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
-	unsigned int i;
+	int cpu;
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
-	for (i = 0; i < NR_CPUS; i++)
-		local_set(&mod->ref[i].count, 0);
+	for_each_possible_cpu(cpu)
+		local_set(__module_ref_addr(mod, cpu), 0);
 	/* Hold reference count during initialization. */
-	local_set(&mod->ref[raw_smp_processor_id()].count, 1);
+	local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -717,10 +717,11 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-	unsigned int i, total = 0;
+	unsigned int total = 0;
+	int cpu;
 
-	for (i = 0; i < NR_CPUS; i++)
-		total += local_read(&mod->ref[i].count);
+	for_each_possible_cpu(cpu)
+		total += local_read(__module_ref_addr(mod, cpu));
 	return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -743,8 +744,8 @@ static void wait_for_zero_refcount(struct module *mod)
 	mutex_lock(&module_mutex);
 }
 
-asmlinkage long
-sys_delete_module(const char __user *name_user, unsigned int flags)
+SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
+		unsigned int, flags)
 {
 	struct module *mod;
 	char name[MODULE_NAME_LEN];
@@ -894,7 +895,7 @@ void module_put(struct module *module)
 {
 	if (module) {
 		unsigned int cpu = get_cpu();
-		local_dec(&module->ref[cpu].count);
+		local_dec(__module_ref_addr(module, cpu));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1464,7 +1465,10 @@ static void free_module(struct module *mod)
 	kfree(mod->args);
 	if (mod->percpu)
 		percpu_modfree(mod->percpu);
-
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	if (mod->refptr)
+		percpu_modfree(mod->refptr);
+#endif
 	/* Free lock-classes: */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
@@ -2070,6 +2074,14 @@ static noinline struct module *load_module(void __user *umod,
 	/* Module has been moved. */
 	mod = (void *)sechdrs[modindex].sh_addr;
 
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+				      mod->name);
+	if (!mod->refptr) {
+		err = -ENOMEM;
+		goto free_init;
+	}
+#endif
 	/* Now we've moved module, initialize linked lists, etc. */
 	module_unload_init(mod);
 
@@ -2276,9 +2288,14 @@ static noinline struct module *load_module(void __user *umod,
 	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
+ free_init:
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	percpu_modfree(mod->refptr);
+#endif
 	module_free(mod, mod->module_init);
  free_core:
 	module_free(mod, mod->module_core);
+	/* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
 	if (percpu)
 		percpu_modfree(percpu);
@@ -2296,10 +2313,8 @@ static noinline struct module *load_module(void __user *umod,
 }
 
 /* This is where the real work happens */
-asmlinkage long
-sys_init_module(void __user *umod,
-		unsigned long len,
-		const char __user *uargs)
+SYSCALL_DEFINE3(init_module, void __user *, umod,
+		unsigned long, len, const char __user *, uargs)
 {
 	struct module *mod;
 	int ret = 0;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 157de3a47832..e976e505648d 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -10,76 +10,6 @@
 #include <linux/kernel_stat.h>
 
 /*
- * Allocate the thread_group_cputime structure appropriately and fill in the
- * current values of the fields.  Called from copy_signal() via
- * thread_group_cputime_clone_thread() when adding a second or subsequent
- * thread to a thread group.  Assumes interrupts are enabled when called.
- */
-int thread_group_cputime_alloc(struct task_struct *tsk)
-{
-	struct signal_struct *sig = tsk->signal;
-	struct task_cputime *cputime;
-
-	/*
-	 * If we have multiple threads and we don't already have a
-	 * per-CPU task_cputime struct (checked in the caller), allocate
-	 * one and fill it in with the times accumulated so far.  We may
-	 * race with another thread so recheck after we pick up the sighand
-	 * lock.
-	 */
-	cputime = alloc_percpu(struct task_cputime);
-	if (cputime == NULL)
-		return -ENOMEM;
-	spin_lock_irq(&tsk->sighand->siglock);
-	if (sig->cputime.totals) {
-		spin_unlock_irq(&tsk->sighand->siglock);
-		free_percpu(cputime);
-		return 0;
-	}
-	sig->cputime.totals = cputime;
-	cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id());
-	cputime->utime = tsk->utime;
-	cputime->stime = tsk->stime;
-	cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
-	spin_unlock_irq(&tsk->sighand->siglock);
-	return 0;
-}
-
-/**
- * thread_group_cputime - Sum the thread group time fields across all CPUs.
- *
- * @tsk:	The task we use to identify the thread group.
- * @times:	task_cputime structure in which we return the summed fields.
- *
- * Walk the list of CPUs to sum the per-CPU time fields in the thread group
- * time structure.
- */
-void thread_group_cputime(
-	struct task_struct *tsk,
-	struct task_cputime *times)
-{
-	struct task_cputime *totals, *tot;
-	int i;
-
-	totals = tsk->signal->cputime.totals;
-	if (!totals) {
-		times->utime = tsk->utime;
-		times->stime = tsk->stime;
-		times->sum_exec_runtime = tsk->se.sum_exec_runtime;
-		return;
-	}
-
-	times->stime = times->utime = cputime_zero;
-	times->sum_exec_runtime = 0;
-	for_each_possible_cpu(i) {
-		tot = per_cpu_ptr(totals, i);
-		times->utime = cputime_add(times->utime, tot->utime);
-		times->stime = cputime_add(times->stime, tot->stime);
-		times->sum_exec_runtime += tot->sum_exec_runtime;
-	}
-}
-
-/*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
 void update_rlimit_cpu(unsigned long rlim_new)
@@ -300,6 +230,71 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 	return 0;
 }
 
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct sighand_struct *sighand;
+	struct signal_struct *sig;
+	struct task_struct *t;
+
+	*times = INIT_CPUTIME;
+
+	rcu_read_lock();
+	sighand = rcu_dereference(tsk->sighand);
+	if (!sighand)
+		goto out;
+
+	sig = tsk->signal;
+
+	t = tsk;
+	do {
+		times->utime = cputime_add(times->utime, t->utime);
+		times->stime = cputime_add(times->stime, t->stime);
+		times->sum_exec_runtime += t->se.sum_exec_runtime;
+
+		t = next_thread(t);
+	} while (t != tsk);
+
+	times->utime = cputime_add(times->utime, sig->utime);
+	times->stime = cputime_add(times->stime, sig->stime);
+	times->sum_exec_runtime += sig->sum_sched_runtime;
+out:
+	rcu_read_unlock();
+}
+
+static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+{
+	if (cputime_gt(b->utime, a->utime))
+		a->utime = b->utime;
+
+	if (cputime_gt(b->stime, a->stime))
+		a->stime = b->stime;
+
+	if (b->sum_exec_runtime > a->sum_exec_runtime)
+		a->sum_exec_runtime = b->sum_exec_runtime;
+}
+
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct task_cputime sum;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cputimer->lock, flags);
+	if (!cputimer->running) {
+		cputimer->running = 1;
+		/*
+		 * The POSIX timer interface allows for absolute time expiry
+		 * values through the TIMER_ABSTIME flag, therefore we have
+		 * to synchronize the timer to the clock every time we start
+		 * it.
+		 */
+		thread_group_cputime(tsk, &sum);
+		update_gt_cputime(&cputimer->cputime, &sum);
+	}
+	*times = cputimer->cputime;
+	spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.
@@ -527,7 +522,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
 	struct task_cputime cputime;
 
-	thread_group_cputime(tsk, &cputime);
+	thread_group_cputimer(tsk, &cputime);
 	cleanup_timers(tsk->signal->cpu_timers,
 		       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
 }
@@ -686,6 +681,33 @@ static void cpu_timer_fire(struct k_itimer *timer)
 }
 
 /*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with tasklist_lock held for reading.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  union cpu_time_count *cpu)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputimer(p, &cputime);
+	switch (CPUCLOCK_WHICH(which_clock)) {
+	default:
+		return -EINVAL;
+	case CPUCLOCK_PROF:
+		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+		break;
+	case CPUCLOCK_VIRT:
+		cpu->cpu = cputime.utime;
+		break;
+	case CPUCLOCK_SCHED:
+		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+		break;
+	}
+	return 0;
+}
+
+/*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
@@ -746,7 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &val);
 	} else {
-		cpu_clock_sample_group(timer->it_clock, p, &val);
+		cpu_timer_sample_group(timer->it_clock, p, &val);
 	}
 
 	if (old) {
@@ -894,7 +916,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			read_unlock(&tasklist_lock);
 			goto dead;
 		} else {
-			cpu_clock_sample_group(timer->it_clock, p, &now);
+			cpu_timer_sample_group(timer->it_clock, p, &now);
 			clear_dead = (unlikely(p->exit_state) &&
 				      thread_group_empty(p));
 		}
@@ -1034,6 +1056,19 @@ static void check_thread_timers(struct task_struct *tsk,
 	}
 }
 
+static void stop_process_timers(struct task_struct *tsk)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	unsigned long flags;
+
+	if (!cputimer->running)
+		return;
+
+	spin_lock_irqsave(&cputimer->lock, flags);
+	cputimer->running = 0;
+	spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them
  * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -1057,13 +1092,15 @@ static void check_process_timers(struct task_struct *tsk,
 	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
 	    list_empty(&timers[CPUCLOCK_VIRT]) &&
 	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
-	    list_empty(&timers[CPUCLOCK_SCHED]))
+	    list_empty(&timers[CPUCLOCK_SCHED])) {
+		stop_process_timers(tsk);
 		return;
+	}
 
 	/*
 	 * Collect the current process totals.
 	 */
-	thread_group_cputime(tsk, &cputime);
+	thread_group_cputimer(tsk, &cputime);
 	utime = cputime.utime;
 	ptime = cputime_add(utime, cputime.stime);
 	sum_sched_runtime = cputime.sum_exec_runtime;
@@ -1234,7 +1271,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			clear_dead_task(timer, now);
 			goto out_unlock;
 		}
-		cpu_clock_sample_group(timer->it_clock, p, &now);
+		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
 		/* Leave the tasklist_lock locked for the call below.  */
 	}
@@ -1329,7 +1366,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	if (!task_cputime_zero(&sig->cputime_expires)) {
 		struct task_cputime group_sample;
 
-		thread_group_cputime(tsk, &group_sample);
+		thread_group_cputimer(tsk, &group_sample);
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
 	}
@@ -1411,7 +1448,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
-	cpu_clock_sample_group(clock_idx, tsk, &now);
+	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
 		if (!cputime_eq(*oldval, cputime_zero)) {
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 887c63787de6..052ec4d195c7 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -477,10 +477,9 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 
 /* Create a POSIX.1b interval timer. */
 
-asmlinkage long
-sys_timer_create(const clockid_t which_clock,
-		 struct sigevent __user *timer_event_spec,
-		 timer_t __user * created_timer_id)
+SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
+		struct sigevent __user *, timer_event_spec,
+		timer_t __user *, created_timer_id)
 {
 	struct k_itimer *new_timer;
 	int error, new_timer_id;
@@ -661,8 +660,8 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 }
 
 /* Get the time remaining on a POSIX.1b interval timer. */
-asmlinkage long
-sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting)
+SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
+		struct itimerspec __user *, setting)
 {
 	struct k_itimer *timr;
 	struct itimerspec cur_setting;
@@ -691,8 +690,7 @@ sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting)
  * the call back to do_schedule_next_timer().  So all we need to do is
  * to pick up the frozen overrun.
  */
-asmlinkage long
-sys_timer_getoverrun(timer_t timer_id)
+SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 {
 	struct k_itimer *timr;
 	int overrun;
@@ -760,10 +758,9 @@ common_timer_set(struct k_itimer *timr, int flags,
 }
 
 /* Set a POSIX.1b interval timer */
-asmlinkage long
-sys_timer_settime(timer_t timer_id, int flags,
-		  const struct itimerspec __user *new_setting,
-		  struct itimerspec __user *old_setting)
+SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
+		const struct itimerspec __user *, new_setting,
+		struct itimerspec __user *, old_setting)
 {
 	struct k_itimer *timr;
 	struct itimerspec new_spec, old_spec;
@@ -816,8 +813,7 @@ static inline int timer_delete_hook(struct k_itimer *timer)
 }
 
 /* Delete a POSIX.1b interval timer. */
-asmlinkage long
-sys_timer_delete(timer_t timer_id)
+SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
 {
 	struct k_itimer *timer;
 	unsigned long flags;
@@ -903,8 +899,8 @@ int do_posix_clock_nonanosleep(const clockid_t clock, int flags,
 }
 EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep);
 
-asmlinkage long sys_clock_settime(const clockid_t which_clock,
-				  const struct timespec __user *tp)
+SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
+		const struct timespec __user *, tp)
 {
 	struct timespec new_tp;
 
@@ -916,8 +912,8 @@ asmlinkage long sys_clock_settime(const clockid_t which_clock,
 	return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp));
 }
 
-asmlinkage long
-sys_clock_gettime(const clockid_t which_clock, struct timespec __user *tp)
+SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
+		struct timespec __user *,tp)
 {
 	struct timespec kernel_tp;
 	int error;
@@ -933,8 +929,8 @@ sys_clock_gettime(const clockid_t which_clock, struct timespec __user *tp)
 
 }
 
-asmlinkage long
-sys_clock_getres(const clockid_t which_clock, struct timespec __user *tp)
+SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
+		struct timespec __user *, tp)
 {
 	struct timespec rtn_tp;
 	int error;
@@ -963,10 +959,9 @@ static int common_nsleep(const clockid_t which_clock, int flags,
 				 which_clock);
 }
 
-asmlinkage long
-sys_clock_nanosleep(const clockid_t which_clock, int flags,
-		    const struct timespec __user *rqtp,
-		    struct timespec __user *rmtp)
+SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
+		const struct timespec __user *, rqtp,
+		struct timespec __user *, rmtp)
 {
 	struct timespec t;
 
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 597823b5b700..720ea4f781bd 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -3,8 +3,9 @@ ifeq ($(CONFIG_PM_DEBUG),y)
 EXTRA_CFLAGS	+=	-DDEBUG
 endif
 
-obj-y				:= main.o
-obj-$(CONFIG_PM_SLEEP)		+= process.o console.o
+obj-$(CONFIG_PM)		+= main.o
+obj-$(CONFIG_PM_SLEEP)		+= console.o
+obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index b8628be2a465..a3961b205de7 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -78,6 +78,12 @@ void pm_restore_console(void)
 	}
 	set_console(orig_fgconsole);
 	release_console_sem();
+
+	if (vt_waitactive(orig_fgconsole)) {
+		pr_debug("Resume: Can't switch VCs.");
+		return;
+	}
+
 	kmsg_redirect = orig_kmsg;
 }
 #endif
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 45e8541ab7e3..4a4a206b1979 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -71,6 +71,14 @@ void hibernation_set_ops(struct platform_hibernation_ops *ops)
 	mutex_unlock(&pm_mutex);
 }
 
+static bool entering_platform_hibernation;
+
+bool system_entering_hibernation(void)
+{
+	return entering_platform_hibernation;
+}
+EXPORT_SYMBOL(system_entering_hibernation);
+
 #ifdef CONFIG_PM_DEBUG
 static void hibernation_debug_sleep(void)
 {
@@ -219,6 +227,12 @@ static int create_image(int platform_mode)
 			"aborting hibernation\n");
 		goto Enable_irqs;
 	}
+	sysdev_suspend(PMSG_FREEZE);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to power down, "
+			"aborting hibernation\n");
+		goto Power_up_devices;
+	}
 
 	if (hibernation_test(TEST_CORE))
 		goto Power_up;
@@ -234,9 +248,11 @@ static int create_image(int platform_mode)
 	if (!in_suspend)
 		platform_leave(platform_mode);
  Power_up:
+	sysdev_resume();
 	/* NOTE:  device_power_up() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
+ Power_up_devices:
 	device_power_up(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Enable_irqs:
@@ -327,6 +343,7 @@ static int resume_target_kernel(void)
 			"aborting resume\n");
 		goto Enable_irqs;
 	}
+	sysdev_suspend(PMSG_QUIESCE);
 	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
@@ -349,6 +366,7 @@ static int resume_target_kernel(void)
 	swsusp_free();
 	restore_processor_state();
 	touch_softlockup_watchdog();
+	sysdev_resume();
 	device_power_up(PMSG_RECOVER);
  Enable_irqs:
 	local_irq_enable();
@@ -411,6 +429,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Close;
 
+	entering_platform_hibernation = true;
 	suspend_console();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
@@ -431,6 +450,7 @@ int hibernation_platform_enter(void)
 	local_irq_disable();
 	error = device_power_down(PMSG_HIBERNATE);
 	if (!error) {
+		sysdev_suspend(PMSG_HIBERNATE);
 		hibernation_ops->enter();
 		/* We should never get here */
 		while (1);
@@ -445,6 +465,7 @@ int hibernation_platform_enter(void)
  Finish:
 	hibernation_ops->finish();
  Resume_devices:
+	entering_platform_hibernation = false;
 	device_resume(PMSG_RESTORE);
 	resume_console();
  Close:
@@ -585,6 +606,12 @@ static int software_resume(void)
 	unsigned int flags;
 
 	/*
+	 * If the user said "noresume".. bail out early.
+	 */
+	if (noresume)
+		return 0;
+
+	/*
 	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
 	 * is configured into the kernel. Since the regular hibernate
 	 * trigger path is via sysfs which takes a buffer mutex before
@@ -600,6 +627,11 @@ static int software_resume(void)
 			mutex_unlock(&pm_mutex);
 			return -ENOENT;
 		}
+		/*
+		 * Some device discovery might still be in progress; we need
+		 * to wait for this to finish.
+		 */
+		wait_for_device_probe();
 		swsusp_resume_device = name_to_dev_t(resume_file);
 		pr_debug("PM: Resume from partition %s\n", resume_file);
 	} else {
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 239988873971..c9632f841f64 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -57,16 +57,6 @@ int pm_notifier_call_chain(unsigned long val)
 #ifdef CONFIG_PM_DEBUG
 int pm_test_level = TEST_NONE;
 
-static int suspend_test(int level)
-{
-	if (pm_test_level == level) {
-		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
-		mdelay(5000);
-		return 1;
-	}
-	return 0;
-}
-
 static const char * const pm_tests[__TEST_AFTER_LAST] = {
 	[TEST_NONE] = "none",
 	[TEST_CORE] = "core",
@@ -125,14 +115,24 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 }
 
 power_attr(pm_test);
-#else /* !CONFIG_PM_DEBUG */
-static inline int suspend_test(int level) { return 0; }
-#endif /* !CONFIG_PM_DEBUG */
+#endif /* CONFIG_PM_DEBUG */
 
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_SUSPEND
 
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+	if (pm_test_level == level) {
+		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+		mdelay(5000);
+		return 1;
+	}
+#endif /* !CONFIG_PM_DEBUG */
+	return 0;
+}
+
 #ifdef CONFIG_PM_TEST_SUSPEND
 
 /*
@@ -298,8 +298,12 @@ static int suspend_enter(suspend_state_t state)
 		goto Done;
 	}
 
-	if (!suspend_test(TEST_CORE))
-		error = suspend_ops->enter(state);
+	error = sysdev_suspend(PMSG_SUSPEND);
+	if (!error) {
+		if (!suspend_test(TEST_CORE))
+			error = suspend_ops->enter(state);
+		sysdev_resume();
+	}
 
 	device_power_up(PMSG_RESUME);
  Done:
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 6da14358537c..505f319e489c 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -60,6 +60,7 @@ static struct block_device *resume_bdev;
 static int submit(int rw, pgoff_t page_off, struct page *page,
 			struct bio **bio_chain)
 {
+	const int bio_rw = rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
 	struct bio *bio;
 
 	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
@@ -80,7 +81,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 	bio_get(bio);
 
 	if (bio_chain == NULL) {
-		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		submit_bio(bio_rw, bio);
 		wait_on_page_locked(page);
 		if (rw == READ)
 			bio_set_pages_dirty(bio);
@@ -90,7 +91,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 			get_page(page);	/* These pages are freed later */
 		bio->bi_private = *bio_chain;
 		*bio_chain = bio;
-		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		submit_bio(bio_rw, bio);
 	}
 	return 0;
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 005b93d839ba..6c85359364f2 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -95,15 +95,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		data->swap = swsusp_resume_device ?
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
-		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
 		if (error)
-			pm_notifier_call_chain(PM_POST_RESTORE);
+			pm_notifier_call_chain(PM_POST_HIBERNATION);
 	} else {
 		data->swap = -1;
 		data->mode = O_WRONLY;
-		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
 		if (error)
-			pm_notifier_call_chain(PM_POST_HIBERNATION);
+			pm_notifier_call_chain(PM_POST_RESTORE);
 	}
 	if (error)
 		atomic_inc(&snapshot_device_available);
diff --git a/kernel/printk.c b/kernel/printk.c
index 7015733793e8..e3602d0755b0 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -73,7 +73,6 @@ EXPORT_SYMBOL(oops_in_progress);
  * driver system.
  */
 static DECLARE_MUTEX(console_sem);
-static DECLARE_MUTEX(secondary_console_sem);
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
@@ -382,7 +381,7 @@ out:
 	return error;
 }
 
-asmlinkage long sys_syslog(int type, char __user *buf, int len)
+SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
 {
 	return do_syslog(type, buf, len);
 }
@@ -742,11 +741,6 @@ EXPORT_SYMBOL(vprintk);
 
 #else
 
-asmlinkage long sys_syslog(int type, char __user *buf, int len)
-{
-	return -ENOSYS;
-}
-
 static void call_console_drivers(unsigned start, unsigned end)
 {
 }
@@ -896,12 +890,14 @@ void suspend_console(void)
 	printk("Suspending console(s) (use no_console_suspend to debug)\n");
 	acquire_console_sem();
 	console_suspended = 1;
+	up(&console_sem);
 }
 
 void resume_console(void)
 {
 	if (!console_suspend_enabled)
 		return;
+	down(&console_sem);
 	console_suspended = 0;
 	release_console_sem();
 }
@@ -917,11 +913,9 @@ void resume_console(void)
 void acquire_console_sem(void)
 {
 	BUG_ON(in_interrupt());
-	if (console_suspended) {
-		down(&secondary_console_sem);
-		return;
-	}
 	down(&console_sem);
+	if (console_suspended)
+		return;
 	console_locked = 1;
 	console_may_schedule = 1;
 }
@@ -931,6 +925,10 @@ int try_acquire_console_sem(void)
 {
 	if (down_trylock(&console_sem))
 		return -1;
+	if (console_suspended) {
+		up(&console_sem);
+		return -1;
+	}
 	console_locked = 1;
 	console_may_schedule = 0;
 	return 0;
@@ -984,7 +982,7 @@ void release_console_sem(void)
 	unsigned wake_klogd = 0;
 
 	if (console_suspended) {
-		up(&secondary_console_sem);
+		up(&console_sem);
 		return;
 	}
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 784933acf5b8..7724e0409bae 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -114,12 +114,15 @@ int __ref profile_init(void)
 	if (!slab_is_available()) {
 		prof_buffer = alloc_bootmem(buffer_bytes);
 		alloc_bootmem_cpumask_var(&prof_cpu_mask);
+		cpumask_copy(prof_cpu_mask, cpu_possible_mask);
 		return 0;
 	}
 
 	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
+	cpumask_copy(prof_cpu_mask, cpu_possible_mask);
+
 	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
 	if (prof_buffer)
 		return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 29dc700e198c..c9cf48b21f05 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -574,7 +574,7 @@ struct task_struct *ptrace_get_task_struct(pid_t pid)
 #define arch_ptrace_attach(child)	do { } while (0)
 #endif
 
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 {
 	struct task_struct *child;
 	long ret;
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 490934fc7ac3..654c640a6b9c 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
@@ -716,7 +716,7 @@ void rcu_check_callbacks(int cpu, int user)
 	raise_rcu_softirq();
 }
 
-static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
+static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 						struct rcu_data *rdp)
 {
 	unsigned long flags;
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index d92a76a881aa..cae8a059cf47 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,6 +44,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kernel_stat.h>
 
 enum rcu_barrier {
 	RCU_BARRIER_STD,
@@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
+int rcu_scheduler_active __read_mostly;
 
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
@@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head  *head)
 void synchronize_rcu(void)
 {
 	struct rcu_synchronize rcu;
+
+	if (rcu_blocking_is_gp())
+		return;
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
@@ -175,3 +181,9 @@ void __init rcu_init(void)
 	__rcu_init();
 }
 
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 33cfc50781f9..5d59e850fb71 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1181,6 +1181,9 @@ void __synchronize_sched(void)
 {
 	struct rcu_synchronize rcu;
 
+	if (num_online_cpus() == 1)
+		return;  /* blocking is gp if only one CPU! */
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 1cff28db56b6..7c4142a79f0a 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -136,29 +136,47 @@ static int stutter_pause_test = 0;
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 
-#define FULLSTOP_SHUTDOWN 1	/* Bail due to system shutdown/panic. */
-#define FULLSTOP_CLEANUP  2	/* Orderly shutdown. */
-static int fullstop;		/* stop generating callbacks at test end. */
-DEFINE_MUTEX(fullstop_mutex);	/* protect fullstop transitions and */
-				/*  spawning of kthreads. */
+/* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
+
+#define FULLSTOP_DONTSTOP 0	/* Normal operation. */
+#define FULLSTOP_SHUTDOWN 1	/* System shutdown with rcutorture running. */
+#define FULLSTOP_RMMOD    2	/* Normal rmmod of rcutorture. */
+static int fullstop = FULLSTOP_RMMOD;
+DEFINE_MUTEX(fullstop_mutex);	/* Protect fullstop transitions and spawning */
+				/*  of kthreads. */
 
 /*
- * Detect and respond to a signal-based shutdown.
+ * Detect and respond to a system shutdown.
  */
 static int
 rcutorture_shutdown_notify(struct notifier_block *unused1,
 			   unsigned long unused2, void *unused3)
 {
-	if (fullstop)
-		return NOTIFY_DONE;
 	mutex_lock(&fullstop_mutex);
-	if (!fullstop)
+	if (fullstop == FULLSTOP_DONTSTOP)
 		fullstop = FULLSTOP_SHUTDOWN;
+	else
+		printk(KERN_WARNING /* but going down anyway, so... */
+		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
 	mutex_unlock(&fullstop_mutex);
 	return NOTIFY_DONE;
 }
 
 /*
+ * Absorb kthreads into a kernel function that won't return, so that
+ * they won't ever access module text or data again.
+ */
+static void rcutorture_shutdown_absorb(char *title)
+{
+	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+		printk(KERN_NOTICE
+		       "rcutorture thread %s parking due to system shutdown\n",
+		       title);
+		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
+	}
+}
+
+/*
  * Allocate an element from the rcu_tortures pool.
  */
 static struct rcu_torture *
@@ -219,13 +237,14 @@ rcu_random(struct rcu_random_state *rrsp)
 }
 
 static void
-rcu_stutter_wait(void)
+rcu_stutter_wait(char *title)
 {
-	while ((stutter_pause_test || !rcutorture_runnable) && !fullstop) {
+	while (stutter_pause_test || !rcutorture_runnable) {
 		if (rcutorture_runnable)
 			schedule_timeout_interruptible(1);
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
+		rcutorture_shutdown_absorb(title);
 	}
 }
 
@@ -287,7 +306,7 @@ rcu_torture_cb(struct rcu_head *p)
 	int i;
 	struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
 
-	if (fullstop) {
+	if (fullstop != FULLSTOP_DONTSTOP) {
 		/* Test is ending, just drop callbacks on the floor. */
 		/* The next initialization will pick up the pieces. */
 		return;
@@ -619,10 +638,11 @@ rcu_torture_writer(void *arg)
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
-		rcu_stutter_wait();
-	} while (!kthread_should_stop() && !fullstop);
+		rcu_stutter_wait("rcu_torture_writer");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
-	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
+	rcutorture_shutdown_absorb("rcu_torture_writer");
+	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -643,11 +663,12 @@ rcu_torture_fakewriter(void *arg)
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		cur_ops->sync();
-		rcu_stutter_wait();
-	} while (!kthread_should_stop() && !fullstop);
+		rcu_stutter_wait("rcu_torture_fakewriter");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
-	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
+	rcutorture_shutdown_absorb("rcu_torture_fakewriter");
+	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -752,12 +773,13 @@ rcu_torture_reader(void *arg)
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
-		rcu_stutter_wait();
-	} while (!kthread_should_stop() && !fullstop);
+		rcu_stutter_wait("rcu_torture_reader");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
+	rcutorture_shutdown_absorb("rcu_torture_reader");
 	if (irqreader && cur_ops->irqcapable)
 		del_timer_sync(&t);
-	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
+	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -854,7 +876,8 @@ rcu_torture_stats(void *arg)
 	do {
 		schedule_timeout_interruptible(stat_interval * HZ);
 		rcu_torture_stats_print();
-	} while (!kthread_should_stop() && !fullstop);
+		rcutorture_shutdown_absorb("rcu_torture_stats");
+	} while (!kthread_should_stop());
 	VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
 	return 0;
 }
@@ -866,52 +889,49 @@ static int rcu_idle_cpu;	/* Force all torture tasks off this CPU */
  */
 static void rcu_torture_shuffle_tasks(void)
 {
-	cpumask_var_t tmp_mask;
+	cpumask_t tmp_mask;
 	int i;
 
-	if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL))
-		BUG();
-
-	cpumask_setall(tmp_mask);
+	cpus_setall(tmp_mask);
 	get_online_cpus();
 
 	/* No point in shuffling if there is only one online CPU (ex: UP) */
-	if (num_online_cpus() == 1)
-		goto out;
+	if (num_online_cpus() == 1) {
+		put_online_cpus();
+		return;
+	}
 
 	if (rcu_idle_cpu != -1)
-		cpumask_clear_cpu(rcu_idle_cpu, tmp_mask);
+		cpu_clear(rcu_idle_cpu, tmp_mask);
 
-	set_cpus_allowed_ptr(current, tmp_mask);
+	set_cpus_allowed_ptr(current, &tmp_mask);
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
 			if (reader_tasks[i])
 				set_cpus_allowed_ptr(reader_tasks[i],
-						     tmp_mask);
+						     &tmp_mask);
 	}
 
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++)
 			if (fakewriter_tasks[i])
 				set_cpus_allowed_ptr(fakewriter_tasks[i],
-						     tmp_mask);
+						     &tmp_mask);
 	}
 
 	if (writer_task)
-		set_cpus_allowed_ptr(writer_task, tmp_mask);
+		set_cpus_allowed_ptr(writer_task, &tmp_mask);
 
 	if (stats_task)
-		set_cpus_allowed_ptr(stats_task, tmp_mask);
+		set_cpus_allowed_ptr(stats_task, &tmp_mask);
 
 	if (rcu_idle_cpu == -1)
 		rcu_idle_cpu = num_online_cpus() - 1;
 	else
 		rcu_idle_cpu--;
 
-out:
 	put_online_cpus();
-	free_cpumask_var(tmp_mask);
 }
 
 /* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
@@ -925,7 +945,8 @@ rcu_torture_shuffle(void *arg)
 	do {
 		schedule_timeout_interruptible(shuffle_interval * HZ);
 		rcu_torture_shuffle_tasks();
-	} while (!kthread_should_stop() && !fullstop);
+		rcutorture_shutdown_absorb("rcu_torture_shuffle");
+	} while (!kthread_should_stop());
 	VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
 	return 0;
 }
@@ -940,10 +961,11 @@ rcu_torture_stutter(void *arg)
 	do {
 		schedule_timeout_interruptible(stutter * HZ);
 		stutter_pause_test = 1;
-		if (!kthread_should_stop() && !fullstop)
+		if (!kthread_should_stop())
 			schedule_timeout_interruptible(stutter * HZ);
 		stutter_pause_test = 0;
-	} while (!kthread_should_stop() && !fullstop);
+		rcutorture_shutdown_absorb("rcu_torture_stutter");
+	} while (!kthread_should_stop());
 	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
 	return 0;
 }
@@ -970,15 +992,16 @@ rcu_torture_cleanup(void)
 	int i;
 
 	mutex_lock(&fullstop_mutex);
-	if (!fullstop) {
-		/* If being signaled, let it happen, then exit. */
+	if (fullstop == FULLSTOP_SHUTDOWN) {
+		printk(KERN_WARNING /* but going down anyway, so... */
+		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
 		mutex_unlock(&fullstop_mutex);
-		schedule_timeout_interruptible(10 * HZ);
+		schedule_timeout_uninterruptible(10);
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
 		return;
 	}
-	fullstop = FULLSTOP_CLEANUP;
+	fullstop = FULLSTOP_RMMOD;
 	mutex_unlock(&fullstop_mutex);
 	unregister_reboot_notifier(&rcutorture_nb);
 	if (stutter_task) {
@@ -1078,7 +1101,7 @@ rcu_torture_init(void)
 	else
 		nrealreaders = 2 * num_online_cpus();
 	rcu_torture_print_module_parms("Start of test");
-	fullstop = 0;
+	fullstop = FULLSTOP_DONTSTOP;
 
 	/* Set up the freelist. */
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f2d8638e6c60..97ce31579ec0 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
@@ -1314,7 +1314,7 @@ int rcu_needs_cpu(int cpu)
  * access due to the fact that this CPU cannot possibly have any RCU
  * callbacks in flight yet.
  */
-static void
+static void __cpuinit
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
diff --git a/kernel/relay.c b/kernel/relay.c
index 09ac2008f77b..9d79b7854fa6 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -663,8 +663,10 @@ int relay_late_setup_files(struct rchan *chan,
 
 	mutex_lock(&relay_channels_mutex);
 	/* Is chan already set up? */
-	if (unlikely(chan->has_base_filename))
+	if (unlikely(chan->has_base_filename)) {
+		mutex_unlock(&relay_channels_mutex);
 		return -EEXIST;
+	}
 	chan->has_base_filename = 1;
 	chan->parent = parent;
 	curr_cpu = get_cpu();
diff --git a/kernel/resource.c b/kernel/resource.c
index ca6a1536b205..fd5d7d574bb9 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -620,6 +620,7 @@ resource_size_t resource_alignment(struct resource *res)
  * @start: resource start address
  * @n: resource region size
  * @name: reserving caller's ID string
+ * @flags: IO resource flags
  */
 struct resource * __request_region(struct resource *parent,
 				   resource_size_t start, resource_size_t n,
diff --git a/kernel/sched.c b/kernel/sched.c
index deb5ac8c12f3..8e2558c2ba67 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -125,6 +125,9 @@ DEFINE_TRACE(sched_switch);
 DEFINE_TRACE(sched_migrate_task);
 
 #ifdef CONFIG_SMP
+
+static void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
  * Since cpu_power is a 'constant', we can use a reciprocal divide.
@@ -220,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	ktime_t now;
 
-	if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
 	if (hrtimer_active(&rt_b->rt_period_timer))
@@ -1320,8 +1323,8 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
  * slice expiry etc.
  */
 
-#define WEIGHT_IDLEPRIO		2
-#define WMULT_IDLEPRIO		(1 << 31)
+#define WEIGHT_IDLEPRIO                3
+#define WMULT_IDLEPRIO         1431655765
 
 /*
  * Nice levels are multiplicative, with a gentle 10% change for every
@@ -3877,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick)
 	int cpu = smp_processor_id();
 
 	if (stop_tick) {
-		cpumask_set_cpu(cpu, nohz.cpu_mask);
 		cpu_rq(cpu)->in_nohz_recently = 1;
 
-		/*
-		 * If we are going offline and still the leader, give up!
-		 */
-		if (!cpu_active(cpu) &&
-		    atomic_read(&nohz.load_balancer) == cpu) {
+		if (!cpu_active(cpu)) {
+			if (atomic_read(&nohz.load_balancer) != cpu)
+				return 0;
+
+			/*
+			 * If we are going offline and still the leader,
+			 * give up!
+			 */
 			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
 				BUG();
+
 			return 0;
 		}
 
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
+
 		/* time for ilb owner also to sleep */
 		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
 			if (atomic_read(&nohz.load_balancer) == cpu)
@@ -4437,7 +4445,7 @@ void __kprobes sub_preempt_count(int val)
 	/*
 	 * Underflow?
 	 */
-       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
+	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
 		return;
 	/*
 	 * Is the spinlock portion underflowing?
@@ -4684,8 +4692,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			     int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int sync, void *key)
 {
 	wait_queue_t *curr, *next;
 
@@ -5123,7 +5131,7 @@ int can_nice(const struct task_struct *p, const int nice)
  * sys_setpriority is a more generic, but much slower function that
  * does similar things.
  */
-asmlinkage long sys_nice(int increment)
+SYSCALL_DEFINE1(nice, int, increment)
 {
 	long nice, retval;
 
@@ -5430,8 +5438,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long
-sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
+		struct sched_param __user *, param)
 {
 	/* negative values for policy are not valid */
 	if (policy < 0)
@@ -5445,7 +5453,7 @@ sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @pid: the pid in question.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 {
 	return do_sched_setscheduler(pid, -1, param);
 }
@@ -5454,7 +5462,7 @@ asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
  */
-asmlinkage long sys_sched_getscheduler(pid_t pid)
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 {
 	struct task_struct *p;
 	int retval;
@@ -5479,7 +5487,7 @@ asmlinkage long sys_sched_getscheduler(pid_t pid)
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
-asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
 	struct sched_param lp;
 	struct task_struct *p;
@@ -5597,8 +5605,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to the new cpu mask
  */
-asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
-				      unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
 {
 	cpumask_var_t new_mask;
 	int retval;
@@ -5645,8 +5653,8 @@ out_unlock:
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
  */
-asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
-				      unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
 {
 	int ret;
 	cpumask_var_t mask;
@@ -5675,7 +5683,7 @@ asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
  * This function yields the current CPU to other tasks. If there are no
  * other threads running on this CPU then this function will return.
  */
-asmlinkage long sys_sched_yield(void)
+SYSCALL_DEFINE0(sched_yield)
 {
 	struct rq *rq = this_rq_lock();
 
@@ -5816,7 +5824,7 @@ long __sched io_schedule_timeout(long timeout)
  * this syscall returns the maximum rt_priority that can be used
  * by a given scheduling class.
  */
-asmlinkage long sys_sched_get_priority_max(int policy)
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 {
 	int ret = -EINVAL;
 
@@ -5841,7 +5849,7 @@ asmlinkage long sys_sched_get_priority_max(int policy)
  * this syscall returns the minimum rt_priority that can be used
  * by a given scheduling class.
  */
-asmlinkage long sys_sched_get_priority_min(int policy)
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 {
 	int ret = -EINVAL;
 
@@ -5866,8 +5874,8 @@ asmlinkage long sys_sched_get_priority_min(int policy)
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
  */
-asmlinkage
-long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+		struct timespec __user *, interval)
 {
 	struct task_struct *p;
 	unsigned int time_slice;
@@ -6936,20 +6944,26 @@ static void free_rootdomain(struct root_domain *rd)
 
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
+	struct root_domain *old_rd = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&rq->lock, flags);
 
 	if (rq->rd) {
-		struct root_domain *old_rd = rq->rd;
+		old_rd = rq->rd;
 
 		if (cpumask_test_cpu(rq->cpu, old_rd->online))
 			set_rq_offline(rq);
 
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
-		if (atomic_dec_and_test(&old_rd->refcount))
-			free_rootdomain(old_rd);
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
 	}
 
 	atomic_inc(&rd->refcount);
@@ -6960,6 +6974,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
+
+	if (old_rd)
+		free_rootdomain(old_rd);
 }
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
@@ -7282,10 +7299,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
  * groups, so roll our own. Now each node has its own list of groups which
  * gets dynamically allocated.
  */
-static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
 static struct sched_group ***sched_group_nodes_bycpu;
 
-static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
 
 static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
@@ -7560,7 +7577,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 #ifdef CONFIG_NUMA
 		if (cpumask_weight(cpu_map) >
 				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
-			sd = &per_cpu(allnodes_domains, i);
+			sd = &per_cpu(allnodes_domains, i).sd;
 			SD_INIT(sd, ALLNODES);
 			set_domain_attribute(sd, attr);
 			cpumask_copy(sched_domain_span(sd), cpu_map);
@@ -7570,7 +7587,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		} else
 			p = NULL;
 
-		sd = &per_cpu(node_domains, i);
+		sd = &per_cpu(node_domains, i).sd;
 		SD_INIT(sd, NODE);
 		set_domain_attribute(sd, attr);
 		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
@@ -7688,7 +7705,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		for_each_cpu(j, nodemask) {
 			struct sched_domain *sd;
 
-			sd = &per_cpu(node_domains, j);
+			sd = &per_cpu(node_domains, j).sd;
 			sd->groups = sg;
 		}
 		sg->__cpu_power = 0;
@@ -9047,6 +9064,13 @@ static int tg_schedulable(struct task_group *tg, void *data)
 		runtime = d->rt_runtime;
 	}
 
+#ifdef CONFIG_USER_SCHED
+	if (tg == &root_task_group) {
+		period = global_rt_period();
+		runtime = global_rt_runtime();
+	}
+#endif
+
 	/*
 	 * Cannot have more runtime than the period.
 	 */
@@ -9200,6 +9224,16 @@ static int sched_rt_global_constraints(void)
 
 	return ret;
 }
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
 #else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
@@ -9293,8 +9327,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		      struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
 		return -EINVAL;
 #else
 	/* We don't support RT-tasks being in separate groups */
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 4293cfa9681d..16eeba4e4169 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -145,6 +145,19 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_unlock_irqrestore(&tasklist_lock, flags);
 }
 
+#if defined(CONFIG_CGROUP_SCHED) && \
+	(defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED))
+static void task_group_path(struct task_group *tg, char *buf, int buflen)
+{
+	/* may be NULL if the underlying cgroup isn't fully-created yet */
+	if (!tg->css.cgroup) {
+		buf[0] = '\0';
+		return;
+	}
+	cgroup_path(tg->css.cgroup, buf, buflen);
+}
+#endif
+
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
@@ -154,10 +167,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	unsigned long flags;
 
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-	char path[128] = "";
+	char path[128];
 	struct task_group *tg = cfs_rq->tg;
 
-	cgroup_path(tg->css.cgroup, path, sizeof(path));
+	task_group_path(tg, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
 #elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
@@ -208,10 +221,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 {
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
-	char path[128] = "";
+	char path[128];
 	struct task_group *tg = rt_rq->tg;
 
-	cgroup_path(tg->css.cgroup, path, sizeof(path));
+	task_group_path(tg, path, sizeof(path));
 
 	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
 #else
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8e1352c75557..0566f2a03c42 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -283,7 +283,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 						   struct sched_entity,
 						   run_node);
 
-		if (vruntime == cfs_rq->min_vruntime)
+		if (!cfs_rq->curr)
 			vruntime = se->vruntime;
 		else
 			vruntime = min_vruntime(vruntime, se->vruntime);
@@ -429,7 +429,10 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
 
 	for_each_sched_entity(se) {
-		struct load_weight *load = &cfs_rq->load;
+		struct load_weight *load;
+
+		cfs_rq = cfs_rq_of(se);
+		load = &cfs_rq->load;
 
 		if (unlikely(!se->on_rq)) {
 			struct load_weight lw = cfs_rq->load;
@@ -677,9 +680,13 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 			unsigned long thresh = sysctl_sched_latency;
 
 			/*
-			 * convert the sleeper threshold into virtual time
+			 * Convert the sleeper threshold into virtual time.
+			 * SCHED_IDLE is a special sub-class.  We care about
+			 * fairness only relative to other SCHED_IDLE tasks,
+			 * all of which have the same weight.
 			 */
-			if (sched_feat(NORMALIZED_SLEEPER))
+			if (sched_feat(NORMALIZED_SLEEPER) &&
+					task_of(se)->policy != SCHED_IDLE)
 				thresh = calc_delta_fair(thresh, se);
 
 			vruntime -= thresh;
@@ -712,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 		__enqueue_entity(cfs_rq, se);
 }
 
-static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->last == se)
 		cfs_rq->last = NULL;
@@ -721,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		cfs_rq->next = NULL;
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	for_each_sched_entity(se)
+		__clear_buddies(cfs_rq_of(se), se);
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -761,8 +774,14 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 
 	ideal_runtime = sched_slice(cfs_rq, curr);
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	if (delta_exec > ideal_runtime)
+	if (delta_exec > ideal_runtime) {
 		resched_task(rq_of(cfs_rq)->curr);
+		/*
+		 * The current task ran long enough, ensure it doesn't get
+		 * re-elected due to buddy favours.
+		 */
+		clear_buddies(cfs_rq, curr);
+	}
 }
 
 static void
@@ -1340,14 +1359,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		cfs_rq_of(se)->last = se;
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->last = se;
+	}
 }
 
 static void set_next_buddy(struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		cfs_rq_of(se)->next = se;
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->next = se;
+	}
 }
 
 /*
@@ -1393,11 +1416,17 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 		return;
 
 	/*
-	 * Batch tasks do not preempt (their preemption is driven by
+	 * Batch and idle tasks do not preempt (their preemption is driven by
 	 * the tick):
 	 */
-	if (unlikely(p->policy == SCHED_BATCH))
+	if (unlikely(p->policy != SCHED_NORMAL))
+		return;
+
+	/* Idle tasks are by definition preempted by everybody. */
+	if (unlikely(curr->policy == SCHED_IDLE)) {
+		resched_task(curr);
 		return;
+	}
 
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
@@ -1435,6 +1464,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
+		/*
+		 * If se was a buddy, clear it so that it will have to earn
+		 * the favour again.
+		 */
+		__clear_buddies(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 954e1a81b796..bac1061cea2f 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -968,8 +968,8 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
 		return this_cpu;
 
-	first = first_cpu(*mask);
-	if (first != NR_CPUS)
+	first = cpumask_first(mask);
+	if (first < nr_cpu_ids)
 		return first;
 
 	return -1;
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index f2773b5d1226..a8f93dd374e1 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -296,20 +296,21 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 static inline void account_group_user_time(struct task_struct *tsk,
 					   cputime_t cputime)
 {
-	struct signal_struct *sig;
+	struct thread_group_cputimer *cputimer;
 
 	/* tsk == current, ensure it is safe to use ->signal */
 	if (unlikely(tsk->exit_state))
 		return;
 
-	sig = tsk->signal;
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	cputimer = &tsk->signal->cputimer;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->utime = cputime_add(times->utime, cputime);
-		put_cpu_no_resched();
-	}
+	if (!cputimer->running)
+		return;
+
+	spin_lock(&cputimer->lock);
+	cputimer->cputime.utime =
+		cputime_add(cputimer->cputime.utime, cputime);
+	spin_unlock(&cputimer->lock);
 }
 
 /**
@@ -325,20 +326,21 @@ static inline void account_group_user_time(struct task_struct *tsk,
 static inline void account_group_system_time(struct task_struct *tsk,
 					     cputime_t cputime)
 {
-	struct signal_struct *sig;
+	struct thread_group_cputimer *cputimer;
 
 	/* tsk == current, ensure it is safe to use ->signal */
 	if (unlikely(tsk->exit_state))
 		return;
 
-	sig = tsk->signal;
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	cputimer = &tsk->signal->cputimer;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->stime = cputime_add(times->stime, cputime);
-		put_cpu_no_resched();
-	}
+	if (!cputimer->running)
+		return;
+
+	spin_lock(&cputimer->lock);
+	cputimer->cputime.stime =
+		cputime_add(cputimer->cputime.stime, cputime);
+	spin_unlock(&cputimer->lock);
 }
 
 /**
@@ -354,6 +356,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
 static inline void account_group_exec_runtime(struct task_struct *tsk,
 					      unsigned long long ns)
 {
+	struct thread_group_cputimer *cputimer;
 	struct signal_struct *sig;
 
 	sig = tsk->signal;
@@ -362,11 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
 	if (unlikely(!sig))
 		return;
 
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	cputimer = &sig->cputimer;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->sum_exec_runtime += ns;
-		put_cpu_no_resched();
-	}
+	if (!cputimer->running)
+		return;
+
+	spin_lock(&cputimer->lock);
+	cputimer->cputime.sum_exec_runtime += ns;
+	spin_unlock(&cputimer->lock);
 }
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ad64fcb731f2..57d4b13b631d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -8,6 +8,7 @@
 
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
 
 /* #define SECCOMP_DEBUG 1 */
 #define NR_SECCOMP_MODES 1
@@ -22,7 +23,7 @@ static int mode1_syscalls[] = {
 	0, /* null terminated */
 };
 
-#ifdef TIF_32BIT
+#ifdef CONFIG_COMPAT
 static int mode1_syscalls_32[] = {
 	__NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
 	0, /* null terminated */
@@ -37,8 +38,8 @@ void __secure_computing(int this_syscall)
 	switch (mode) {
 	case 1:
 		syscall = mode1_syscalls;
-#ifdef TIF_32BIT
-		if (test_thread_flag(TIF_32BIT))
+#ifdef CONFIG_COMPAT
+		if (is_compat_task())
 			syscall = mode1_syscalls_32;
 #endif
 		do {
diff --git a/kernel/signal.c b/kernel/signal.c
index 3152ac3b62e2..1c8814481a11 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -909,7 +909,9 @@ static void print_fatal_signal(struct pt_regs *regs, int signr)
 	}
 #endif
 	printk("\n");
+	preempt_disable();
 	show_regs(regs);
+	preempt_enable();
 }
 
 static int __init setup_print_fatal_signals(char *str)
@@ -1365,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 	struct siginfo info;
 	unsigned long flags;
 	struct sighand_struct *psig;
-	struct task_cputime cputime;
 	int ret = sig;
 
 	BUG_ON(sig == -1);
@@ -1395,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 	info.si_uid = __task_cred(tsk)->uid;
 	rcu_read_unlock();
 
-	thread_group_cputime(tsk, &cputime);
-	info.si_utime = cputime_to_jiffies(cputime.utime);
-	info.si_stime = cputime_to_jiffies(cputime.stime);
+	info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
+				tsk->signal->utime));
+	info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
+				tsk->signal->stime));
 
 	info.si_status = tsk->exit_code & 0x7f;
 	if (tsk->exit_code & 0x80)
@@ -1573,7 +1575,15 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
 	read_lock(&tasklist_lock);
 	if (may_ptrace_stop()) {
 		do_notify_parent_cldstop(current, CLD_TRAPPED);
+		/*
+		 * Don't want to allow preemption here, because
+		 * sys_ptrace() needs this task to be inactive.
+		 *
+		 * XXX: implement read_unlock_no_resched().
+		 */
+		preempt_disable();
 		read_unlock(&tasklist_lock);
+		preempt_enable_no_resched();
 		schedule();
 	} else {
 		/*
@@ -1961,7 +1971,7 @@ EXPORT_SYMBOL(unblock_all_signals);
  * System call entry points.
  */
 
-asmlinkage long sys_restart_syscall(void)
+SYSCALL_DEFINE0(restart_syscall)
 {
 	struct restart_block *restart = &current_thread_info()->restart_block;
 	return restart->fn(restart);
@@ -2014,8 +2024,8 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset)
 	return error;
 }
 
-asmlinkage long
-sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize)
+SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, set,
+		sigset_t __user *, oset, size_t, sigsetsize)
 {
 	int error = -EINVAL;
 	sigset_t old_set, new_set;
@@ -2074,8 +2084,7 @@ out:
 	return error;
 }	
 
-asmlinkage long
-sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize)
+SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, set, size_t, sigsetsize)
 {
 	return do_sigpending(set, sigsetsize);
 }
@@ -2146,11 +2155,9 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
 
 #endif
 
-asmlinkage long
-sys_rt_sigtimedwait(const sigset_t __user *uthese,
-		    siginfo_t __user *uinfo,
-		    const struct timespec __user *uts,
-		    size_t sigsetsize)
+SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese,
+		siginfo_t __user *, uinfo, const struct timespec __user *, uts,
+		size_t, sigsetsize)
 {
 	int ret, sig;
 	sigset_t these;
@@ -2223,8 +2230,7 @@ sys_rt_sigtimedwait(const sigset_t __user *uthese,
 	return ret;
 }
 
-asmlinkage long
-sys_kill(pid_t pid, int sig)
+SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 {
 	struct siginfo info;
 
@@ -2283,7 +2289,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
  *  exists but it's not belonging to the target process anymore. This
  *  method solves the problem of threads exiting and PIDs getting reused.
  */
-asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig)
+SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig)
 {
 	/* This is only valid for single tasks */
 	if (pid <= 0 || tgid <= 0)
@@ -2295,8 +2301,7 @@ asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig)
 /*
  *  Send a signal to only one task, even if it's a CLONE_THREAD task.
  */
-asmlinkage long
-sys_tkill(pid_t pid, int sig)
+SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig)
 {
 	/* This is only valid for single tasks */
 	if (pid <= 0)
@@ -2305,8 +2310,8 @@ sys_tkill(pid_t pid, int sig)
 	return do_tkill(0, pid, sig);
 }
 
-asmlinkage long
-sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo)
+SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig,
+		siginfo_t __user *, uinfo)
 {
 	siginfo_t info;
 
@@ -2434,8 +2439,7 @@ out:
 
 #ifdef __ARCH_WANT_SYS_SIGPENDING
 
-asmlinkage long
-sys_sigpending(old_sigset_t __user *set)
+SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
 {
 	return do_sigpending(set, sizeof(*set));
 }
@@ -2446,8 +2450,8 @@ sys_sigpending(old_sigset_t __user *set)
 /* Some platforms have their own version with special arguments others
    support only sys_rt_sigprocmask.  */
 
-asmlinkage long
-sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset)
+SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, set,
+		old_sigset_t __user *, oset)
 {
 	int error;
 	old_sigset_t old_set, new_set;
@@ -2497,11 +2501,10 @@ out:
 #endif /* __ARCH_WANT_SYS_SIGPROCMASK */
 
 #ifdef __ARCH_WANT_SYS_RT_SIGACTION
-asmlinkage long
-sys_rt_sigaction(int sig,
-		 const struct sigaction __user *act,
-		 struct sigaction __user *oact,
-		 size_t sigsetsize)
+SYSCALL_DEFINE4(rt_sigaction, int, sig,
+		const struct sigaction __user *, act,
+		struct sigaction __user *, oact,
+		size_t, sigsetsize)
 {
 	struct k_sigaction new_sa, old_sa;
 	int ret = -EINVAL;
@@ -2531,15 +2534,13 @@ out:
 /*
  * For backwards compatibility.  Functionality superseded by sigprocmask.
  */
-asmlinkage long
-sys_sgetmask(void)
+SYSCALL_DEFINE0(sgetmask)
 {
 	/* SMP safe */
 	return current->blocked.sig[0];
 }
 
-asmlinkage long
-sys_ssetmask(int newmask)
+SYSCALL_DEFINE1(ssetmask, int, newmask)
 {
 	int old;
 
@@ -2559,8 +2560,7 @@ sys_ssetmask(int newmask)
 /*
  * For backwards compatibility.  Functionality superseded by sigaction.
  */
-asmlinkage unsigned long
-sys_signal(int sig, __sighandler_t handler)
+SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler)
 {
 	struct k_sigaction new_sa, old_sa;
 	int ret;
@@ -2577,8 +2577,7 @@ sys_signal(int sig, __sighandler_t handler)
 
 #ifdef __ARCH_WANT_SYS_PAUSE
 
-asmlinkage long
-sys_pause(void)
+SYSCALL_DEFINE0(pause)
 {
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -2588,7 +2587,7 @@ sys_pause(void)
 #endif
 
 #ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND
-asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize)
+SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize)
 {
 	sigset_t newset;
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 5cfa0e5e3e88..bbedbb7efe32 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -18,6 +18,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
 enum {
 	CSD_FLAG_WAIT		= 0x01,
 	CSD_FLAG_ALLOC		= 0x02,
+	CSD_FLAG_LOCK		= 0x04,
 };
 
 struct call_function_data {
@@ -186,6 +187,9 @@ void generic_smp_call_function_single_interrupt(void)
 			if (data_flags & CSD_FLAG_WAIT) {
 				smp_wmb();
 				data->flags &= ~CSD_FLAG_WAIT;
+			} else if (data_flags & CSD_FLAG_LOCK) {
+				smp_wmb();
+				data->flags &= ~CSD_FLAG_LOCK;
 			} else if (data_flags & CSD_FLAG_ALLOC)
 				kfree(data);
 		}
@@ -196,6 +200,8 @@ void generic_smp_call_function_single_interrupt(void)
 	}
 }
 
+static DEFINE_PER_CPU(struct call_single_data, csd_data);
+
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -224,14 +230,38 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 		func(info);
 		local_irq_restore(flags);
 	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-		struct call_single_data *data = NULL;
+		struct call_single_data *data;
 
 		if (!wait) {
+			/*
+			 * We are calling a function on a single CPU
+			 * and we are not going to wait for it to finish.
+			 * We first try to allocate the data, but if we
+			 * fail, we fall back to use a per cpu data to pass
+			 * the information to that CPU. Since all callers
+			 * of this code will use the same data, we must
+			 * synchronize the callers to prevent a new caller
+			 * from corrupting the data before the callee
+			 * can access it.
+			 *
+			 * The CSD_FLAG_LOCK is used to let us know when
+			 * the IPI handler is done with the data.
+			 * The first caller will set it, and the callee
+			 * will clear it. The next caller must wait for
+			 * it to clear before we set it again. This
+			 * will make sure the callee is done with the
+			 * data before a new caller will use it.
+			 */
 			data = kmalloc(sizeof(*data), GFP_ATOMIC);
 			if (data)
 				data->flags = CSD_FLAG_ALLOC;
-		}
-		if (!data) {
+			else {
+				data = &per_cpu(csd_data, me);
+				while (data->flags & CSD_FLAG_LOCK)
+					cpu_relax();
+				data->flags = CSD_FLAG_LOCK;
+			}
+		} else {
 			data = &d;
 			data->flags = CSD_FLAG_WAIT;
 		}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8d..9041ea7948fe 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
+			rcu_qsctr_inc((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index d9188c66278a..85d5a2455103 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -16,6 +16,7 @@
 #include <linux/lockdep.h>
 #include <linux/notifier.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 
 #include <asm/irq_regs.h>
 
@@ -88,6 +89,14 @@ void touch_all_softlockup_watchdogs(void)
 }
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
+int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
+			     struct file *filp, void __user *buffer,
+			     size_t *lenp, loff_t *ppos)
+{
+	touch_all_softlockup_watchdogs();
+	return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+}
+
 /*
  * This callback runs from the timer interrupt, and checks
  * whether the watchdog thread has hung or not:
diff --git a/kernel/sys.c b/kernel/sys.c
index 763c3c17ded3..37f458e6882a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -143,7 +143,7 @@ out:
 	return error;
 }
 
-asmlinkage long sys_setpriority(int which, int who, int niceval)
+SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 {
 	struct task_struct *g, *p;
 	struct user_struct *user;
@@ -208,7 +208,7 @@ out:
  * has been offset by 20 (ie it returns 40..1 instead of -20..19)
  * to stay compatible.
  */
-asmlinkage long sys_getpriority(int which, int who)
+SYSCALL_DEFINE2(getpriority, int, which, int, who)
 {
 	struct task_struct *g, *p;
 	struct user_struct *user;
@@ -355,7 +355,8 @@ EXPORT_SYMBOL_GPL(kernel_power_off);
  *
  * reboot doesn't sync: do that yourself before calling this.
  */
-asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user * arg)
+SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
+		void __user *, arg)
 {
 	char buffer[256];
 
@@ -478,7 +479,7 @@ void ctrl_alt_del(void)
  * SMP: There are not races, the GIDs are checked only by filesystem
  *      operations (as far as semantic preservation is concerned).
  */
-asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
+SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -529,7 +530,7 @@ error:
  *
  * SMP: Same implicit races as above.
  */
-asmlinkage long sys_setgid(gid_t gid)
+SYSCALL_DEFINE1(setgid, gid_t, gid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -558,7 +559,7 @@ error:
 	abort_creds(new);
 	return retval;
 }
-  
+
 /*
  * change the user struct in a credentials set to match the new UID
  */
@@ -570,6 +571,11 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
+	if (!task_can_switch_user(new_user, current)) {
+		free_uid(new_user);
+		return -EINVAL;
+	}
+
 	if (atomic_read(&new_user->processes) >=
 				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
 			new_user != INIT_USER) {
@@ -597,7 +603,7 @@ static int set_user(struct cred *new)
  * 100% compatible with BSD.  A program which uses just setuid() will be
  * 100% compatible with POSIX with saved IDs. 
  */
-asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
+SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -630,10 +636,11 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
 			goto error;
 	}
 
-	retval = -EAGAIN;
-	if (new->uid != old->uid && set_user(new) < 0)
-		goto error;
-
+	if (new->uid != old->uid) {
+		retval = set_user(new);
+		if (retval < 0)
+			goto error;
+	}
 	if (ruid != (uid_t) -1 ||
 	    (euid != (uid_t) -1 && euid != old->uid))
 		new->suid = new->euid;
@@ -661,7 +668,7 @@ error:
  * will allow a root program to temporarily drop privileges and be able to
  * regain them by swapping the real and effective uid.  
  */
-asmlinkage long sys_setuid(uid_t uid)
+SYSCALL_DEFINE1(setuid, uid_t, uid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -679,9 +686,10 @@ asmlinkage long sys_setuid(uid_t uid)
 	retval = -EPERM;
 	if (capable(CAP_SETUID)) {
 		new->suid = new->uid = uid;
-		if (uid != old->uid && set_user(new) < 0) {
-			retval = -EAGAIN;
-			goto error;
+		if (uid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
 		}
 	} else if (uid != old->uid && uid != new->suid) {
 		goto error;
@@ -705,7 +713,7 @@ error:
  * This function implements a generic ability to update ruid, euid,
  * and suid.  This allows you to implement the 4.4 compatible seteuid().
  */
-asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
+SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -733,11 +741,13 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 			goto error;
 	}
 
-	retval = -EAGAIN;
 	if (ruid != (uid_t) -1) {
 		new->uid = ruid;
-		if (ruid != old->uid && set_user(new) < 0)
-			goto error;
+		if (ruid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
+		}
 	}
 	if (euid != (uid_t) -1)
 		new->euid = euid;
@@ -756,7 +766,7 @@ error:
 	return retval;
 }
 
-asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
+SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -771,7 +781,7 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us
 /*
  * Same as above, but for rgid, egid, sgid.
  */
-asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
+SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -814,7 +824,7 @@ error:
 	return retval;
 }
 
-asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
+SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -833,7 +843,7 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us
  * whatever uid it wants to). It normally shadows "euid", except when
  * explicitly set by setfsuid() or for access..
  */
-asmlinkage long sys_setfsuid(uid_t uid)
+SYSCALL_DEFINE1(setfsuid, uid_t, uid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -870,7 +880,7 @@ change_okay:
 /*
  * Samma på svenska..
  */
-asmlinkage long sys_setfsgid(gid_t gid)
+SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -919,7 +929,7 @@ void do_sys_times(struct tms *tms)
 	tms->tms_cstime = cputime_to_clock_t(cstime);
 }
 
-asmlinkage long sys_times(struct tms __user * tbuf)
+SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
 {
 	if (tbuf) {
 		struct tms tmp;
@@ -944,7 +954,7 @@ asmlinkage long sys_times(struct tms __user * tbuf)
  * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
  * LBT 04.03.94
  */
-asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
+SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 {
 	struct task_struct *p;
 	struct task_struct *group_leader = current->group_leader;
@@ -1015,7 +1025,7 @@ out:
 	return err;
 }
 
-asmlinkage long sys_getpgid(pid_t pid)
+SYSCALL_DEFINE1(getpgid, pid_t, pid)
 {
 	struct task_struct *p;
 	struct pid *grp;
@@ -1045,14 +1055,14 @@ out:
 
 #ifdef __ARCH_WANT_SYS_GETPGRP
 
-asmlinkage long sys_getpgrp(void)
+SYSCALL_DEFINE0(getpgrp)
 {
 	return sys_getpgid(0);
 }
 
 #endif
 
-asmlinkage long sys_getsid(pid_t pid)
+SYSCALL_DEFINE1(getsid, pid_t, pid)
 {
 	struct task_struct *p;
 	struct pid *sid;
@@ -1080,7 +1090,7 @@ out:
 	return retval;
 }
 
-asmlinkage long sys_setsid(void)
+SYSCALL_DEFINE0(setsid)
 {
 	struct task_struct *group_leader = current->group_leader;
 	struct pid *sid = task_pid(group_leader);
@@ -1311,7 +1321,7 @@ int set_current_groups(struct group_info *group_info)
 
 EXPORT_SYMBOL(set_current_groups);
 
-asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
+SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
 {
 	const struct cred *cred = current_cred();
 	int i;
@@ -1340,7 +1350,7 @@ out:
  *	without another task interfering.
  */
  
-asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
+SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 {
 	struct group_info *group_info;
 	int retval;
@@ -1394,7 +1404,7 @@ EXPORT_SYMBOL(in_egroup_p);
 
 DECLARE_RWSEM(uts_sem);
 
-asmlinkage long sys_newuname(struct new_utsname __user * name)
+SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 {
 	int errno = 0;
 
@@ -1405,7 +1415,7 @@ asmlinkage long sys_newuname(struct new_utsname __user * name)
 	return errno;
 }
 
-asmlinkage long sys_sethostname(char __user *name, int len)
+SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
 {
 	int errno;
 	char tmp[__NEW_UTS_LEN];
@@ -1429,7 +1439,7 @@ asmlinkage long sys_sethostname(char __user *name, int len)
 
 #ifdef __ARCH_WANT_SYS_GETHOSTNAME
 
-asmlinkage long sys_gethostname(char __user *name, int len)
+SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
 {
 	int i, errno;
 	struct new_utsname *u;
@@ -1454,7 +1464,7 @@ asmlinkage long sys_gethostname(char __user *name, int len)
  * Only setdomainname; getdomainname can be implemented by calling
  * uname()
  */
-asmlinkage long sys_setdomainname(char __user *name, int len)
+SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
 {
 	int errno;
 	char tmp[__NEW_UTS_LEN];
@@ -1477,7 +1487,7 @@ asmlinkage long sys_setdomainname(char __user *name, int len)
 	return errno;
 }
 
-asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 {
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
@@ -1496,7 +1506,8 @@ asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
  *	Back compatibility for getrlimit. Needed for some apps.
  */
  
-asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+		struct rlimit __user *, rlim)
 {
 	struct rlimit x;
 	if (resource >= RLIM_NLIMITS)
@@ -1514,7 +1525,7 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
 
 #endif
 
-asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 {
 	struct rlimit new_rlim, *old_rlim;
 	int retval;
@@ -1523,22 +1534,14 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 		return -EINVAL;
 	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
 		return -EFAULT;
+	if (new_rlim.rlim_cur > new_rlim.rlim_max)
+		return -EINVAL;
 	old_rlim = current->signal->rlim + resource;
 	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
 	    !capable(CAP_SYS_RESOURCE))
 		return -EPERM;
-
-	if (resource == RLIMIT_NOFILE) {
-		if (new_rlim.rlim_max == RLIM_INFINITY)
-			new_rlim.rlim_max = sysctl_nr_open;
-		if (new_rlim.rlim_cur == RLIM_INFINITY)
-			new_rlim.rlim_cur = sysctl_nr_open;
-		if (new_rlim.rlim_max > sysctl_nr_open)
-			return -EPERM;
-	}
-
-	if (new_rlim.rlim_cur > new_rlim.rlim_max)
-		return -EINVAL;
+	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+		return -EPERM;
 
 	retval = security_task_setrlimit(resource, &new_rlim);
 	if (retval)
@@ -1687,7 +1690,7 @@ int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
 	return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
 }
 
-asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
+SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
 {
 	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
 	    who != RUSAGE_THREAD)
@@ -1695,14 +1698,14 @@ asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
 	return getrusage(current, who, ru);
 }
 
-asmlinkage long sys_umask(int mask)
+SYSCALL_DEFINE1(umask, int, mask)
 {
 	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
 	return mask;
 }
 
-asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
-			  unsigned long arg4, unsigned long arg5)
+SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
+		unsigned long, arg4, unsigned long, arg5)
 {
 	struct task_struct *me = current;
 	unsigned char comm[sizeof(me->comm)];
@@ -1815,8 +1818,8 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 	return error;
 }
 
-asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
-			   struct getcpu_cache __user *unused)
+SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
+		struct getcpu_cache __user *, unused)
 {
 	int err = 0;
 	int cpu = raw_smp_processor_id();
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e14a23281707..27dad2967387 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -131,6 +131,7 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(sys_syslog);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 89d74436318c..c5ef44ff850f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -101,6 +101,7 @@ static int two = 2;
 
 static int zero;
 static int one = 1;
+static unsigned long one_ul = 1;
 static int one_hundred = 100;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -144,6 +145,7 @@ extern int acct_parm[];
 
 #ifdef CONFIG_IA64
 extern int no_unaligned_warning;
+extern int unaligned_dump_stack;
 #endif
 
 #ifdef CONFIG_RT_MUTEXES
@@ -781,6 +783,14 @@ static struct ctl_table kern_table[] = {
 	 	.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "unaligned-dump-stack",
+		.data		= &unaligned_dump_stack,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #endif
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 	{
@@ -800,7 +810,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &softlockup_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
+		.proc_handler	= &proc_dosoftlockup_thresh,
 		.strategy	= &sysctl_intvec,
 		.extra1		= &neg_one,
 		.extra2		= &sixty,
@@ -965,7 +975,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &dirty_background_bytes_handler,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &one,
+		.extra1		= &one_ul,
 	},
 	{
 		.ctl_name	= VM_DIRTY_RATIO,
@@ -986,7 +996,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &dirty_bytes_handler,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &one,
+		.extra1		= &one_ul,
 	},
 	{
 		.procname	= "dirty_writeback_centisecs",
@@ -1688,7 +1698,7 @@ int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *ol
 	return error;
 }
 
-asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
 {
 	struct __sysctl_args tmp;
 	int error;
@@ -2989,7 +2999,7 @@ int sysctl_ms_jiffies(struct ctl_table *table,
 #else /* CONFIG_SYSCTL_SYSCALL */
 
 
-asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
 {
 	struct __sysctl_args tmp;
 	int error;
diff --git a/kernel/time.c b/kernel/time.c
index 4886e3ce83a4..29511943871a 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -60,7 +60,7 @@ EXPORT_SYMBOL(sys_tz);
  * why not move it into the appropriate arch directory (for those
  * architectures that need it).
  */
-asmlinkage long sys_time(time_t __user * tloc)
+SYSCALL_DEFINE1(time, time_t __user *, tloc)
 {
 	time_t i = get_seconds();
 
@@ -79,7 +79,7 @@ asmlinkage long sys_time(time_t __user * tloc)
  * architectures that need it).
  */
 
-asmlinkage long sys_stime(time_t __user *tptr)
+SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 {
 	struct timespec tv;
 	int err;
@@ -99,8 +99,8 @@ asmlinkage long sys_stime(time_t __user *tptr)
 
 #endif /* __ARCH_WANT_SYS_TIME */
 
-asmlinkage long sys_gettimeofday(struct timeval __user *tv,
-				 struct timezone __user *tz)
+SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
+		struct timezone __user *, tz)
 {
 	if (likely(tv != NULL)) {
 		struct timeval ktv;
@@ -184,8 +184,8 @@ int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
 	return 0;
 }
 
-asmlinkage long sys_settimeofday(struct timeval __user *tv,
-				struct timezone __user *tz)
+SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
+		struct timezone __user *, tz)
 {
 	struct timeval user_tv;
 	struct timespec	new_ts;
@@ -205,7 +205,7 @@ asmlinkage long sys_settimeofday(struct timeval __user *tv,
 	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
-asmlinkage long sys_adjtimex(struct timex __user *txc_p)
+SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
 {
 	struct timex txc;		/* Local copy of parameter */
 	int ret;
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 63e05d423a09..21a5ca849514 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -274,6 +274,21 @@ out_bc:
 }
 
 /*
+ * Transfer the do_timer job away from a dying cpu.
+ *
+ * Called with interrupts disabled.
+ */
+static void tick_handover_do_timer(int *cpup)
+{
+	if (*cpup == tick_do_timer_cpu) {
+		int cpu = cpumask_first(cpu_online_mask);
+
+		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
+			TICK_DO_TIMER_NONE;
+	}
+}
+
+/*
  * Shutdown an event device on a given cpu:
  *
  * This is called on a life CPU, when a CPU is dead. So we cannot
@@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup)
 		clockevents_exchange_device(dev, NULL);
 		td->evtdev = NULL;
 	}
-	/* Transfer the do_timer job away from this cpu */
-	if (*cpup == tick_do_timer_cpu) {
-		int cpu = cpumask_first(cpu_online_mask);
-
-		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
-			TICK_DO_TIMER_NONE;
-	}
 	spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
@@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
 		tick_broadcast_oneshot_control(reason);
 		break;
 
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(dev);
+		break;
+
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
 		tick_shutdown_broadcast_oneshot(dev);
 		tick_shutdown_broadcast(dev);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1b6c05bd0d0a..d3f1ef4d5cbe 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,7 +134,7 @@ __setup("nohz=", setup_tick_nohz);
  * value. We do this unconditionally on any cpu, as we don't know whether the
  * cpu, which has the update task assigned is in a long sleep.
  */
-void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
diff --git a/kernel/timer.c b/kernel/timer.c
index dee3f641a7a7..13dd64fe143d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1129,7 +1129,7 @@ void do_timer(unsigned long ticks)
  * For backwards compatibility?  This can be done in libc so Alpha
  * and all newer ports shouldn't need it.
  */
-asmlinkage unsigned long sys_alarm(unsigned int seconds)
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
 {
 	return alarm_setitimer(seconds);
 }
@@ -1152,7 +1152,7 @@ asmlinkage unsigned long sys_alarm(unsigned int seconds)
  *
  * This is SMP safe as current->tgid does not change.
  */
-asmlinkage long sys_getpid(void)
+SYSCALL_DEFINE0(getpid)
 {
 	return task_tgid_vnr(current);
 }
@@ -1163,7 +1163,7 @@ asmlinkage long sys_getpid(void)
  * value of ->real_parent under rcu_read_lock(), see
  * release_task()->call_rcu(delayed_put_task_struct).
  */
-asmlinkage long sys_getppid(void)
+SYSCALL_DEFINE0(getppid)
 {
 	int pid;
 
@@ -1174,25 +1174,25 @@ asmlinkage long sys_getppid(void)
 	return pid;
 }
 
-asmlinkage long sys_getuid(void)
+SYSCALL_DEFINE0(getuid)
 {
 	/* Only we change this so SMP safe */
 	return current_uid();
 }
 
-asmlinkage long sys_geteuid(void)
+SYSCALL_DEFINE0(geteuid)
 {
 	/* Only we change this so SMP safe */
 	return current_euid();
 }
 
-asmlinkage long sys_getgid(void)
+SYSCALL_DEFINE0(getgid)
 {
 	/* Only we change this so SMP safe */
 	return current_gid();
 }
 
-asmlinkage long sys_getegid(void)
+SYSCALL_DEFINE0(getegid)
 {
 	/* Only we change this so SMP safe */
 	return  current_egid();
@@ -1308,7 +1308,7 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
 /* Thread ID - the internal kernel "pid" */
-asmlinkage long sys_gettid(void)
+SYSCALL_DEFINE0(gettid)
 {
 	return task_pid_vnr(current);
 }
@@ -1400,7 +1400,7 @@ out:
 	return 0;
 }
 
-asmlinkage long sys_sysinfo(struct sysinfo __user *info)
+SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
 {
 	struct sysinfo val;
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e2a4ff6fc3a6..34e707e5ab87 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -52,6 +52,7 @@ config FUNCTION_TRACER
 	depends on HAVE_FUNCTION_TRACER
 	depends on DEBUG_KERNEL
 	select FRAME_POINTER
+	select KALLSYMS
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	help
@@ -238,6 +239,7 @@ config STACK_TRACER
 	depends on DEBUG_KERNEL
 	select FUNCTION_TRACER
 	select STACKTRACE
+	select KALLSYMS
 	help
 	  This special tracer records the maximum stack footprint of the
 	  kernel and displays it in debugfs/tracing/stack_trace.
@@ -302,4 +304,27 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config MMIOTRACE
+	bool "Memory mapped IO tracing"
+	depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+	select TRACING
+	help
+	  Mmiotrace traces Memory Mapped I/O access and is meant for
+	  debugging and reverse engineering. It is called from the ioremap
+	  implementation and works via page faults. Tracing is disabled by
+	  default and can be enabled at run-time.
+
+	  See Documentation/tracers/mmiotrace.txt.
+	  If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+	tristate "Test module for mmiotrace"
+	depends on MMIOTRACE && m
+	help
+	  This is a dumb module for testing mmiotrace. It is very dangerous
+	  as it will write garbage to IO memory starting at a given address.
+	  However, it should be safe to use on e.g. unused portion of VRAM.
+
+	  Say N, unless you absolutely know what you are doing.
+
 endmenu
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2f32969c09df..fdf913dfc7e8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/suspend.h>
 #include <linux/debugfs.h>
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
@@ -1736,9 +1737,12 @@ static void clear_ftrace_pid(struct pid *pid)
 {
 	struct task_struct *p;
 
+	rcu_read_lock();
 	do_each_pid_task(pid, PIDTYPE_PID, p) {
 		clear_tsk_trace_trace(p);
 	} while_each_pid_task(pid, PIDTYPE_PID, p);
+	rcu_read_unlock();
+
 	put_pid(pid);
 }
 
@@ -1746,9 +1750,11 @@ static void set_ftrace_pid(struct pid *pid)
 {
 	struct task_struct *p;
 
+	rcu_read_lock();
 	do_each_pid_task(pid, PIDTYPE_PID, p) {
 		set_tsk_trace_trace(p);
 	} while_each_pid_task(pid, PIDTYPE_PID, p);
+	rcu_read_unlock();
 }
 
 static void clear_ftrace_pid_task(struct pid **pid)
@@ -1965,6 +1971,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 static atomic_t ftrace_graph_active;
+static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
@@ -2026,7 +2033,7 @@ free:
 static int start_graph_tracing(void)
 {
 	struct ftrace_ret_stack **ret_stack_list;
-	int ret;
+	int ret, cpu;
 
 	ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
 				sizeof(struct ftrace_ret_stack *),
@@ -2035,6 +2042,10 @@ static int start_graph_tracing(void)
 	if (!ret_stack_list)
 		return -ENOMEM;
 
+	/* The cpu_boot init_task->ret_stack will never be freed */
+	for_each_online_cpu(cpu)
+		ftrace_graph_init_task(idle_task(cpu));
+
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
@@ -2043,6 +2054,27 @@ static int start_graph_tracing(void)
 	return ret;
 }
 
+/*
+ * Hibernation protection.
+ * The state of the current task is too much unstable during
+ * suspend/restore to disk. We want to protect against that.
+ */
+static int
+ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
+							void *unused)
+{
+	switch (state) {
+	case PM_HIBERNATION_PREPARE:
+		pause_graph_tracing();
+		break;
+
+	case PM_POST_HIBERNATION:
+		unpause_graph_tracing();
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -2050,6 +2082,9 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
 	mutex_lock(&ftrace_sysctl_lock);
 
+	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
+	register_pm_notifier(&ftrace_suspend_notifier);
+
 	atomic_inc(&ftrace_graph_active);
 	ret = start_graph_tracing();
 	if (ret) {
@@ -2075,6 +2110,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+	unregister_pm_notifier(&ftrace_suspend_notifier);
 
 	mutex_unlock(&ftrace_sysctl_lock);
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8b0daf0662ef..bd38c5cfd8ad 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -246,7 +246,7 @@ static inline int test_time_stamp(u64 delta)
 	return 0;
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page))
+#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
 
 /*
  * head_page == tail_page && head == tail then buffer is empty.
@@ -1025,12 +1025,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		}
 
 		if (next_page == head_page) {
-			if (!(buffer->flags & RB_FL_OVERWRITE)) {
-				/* reset write */
-				if (tail <= BUF_PAGE_SIZE)
-					local_set(&tail_page->write, tail);
+			if (!(buffer->flags & RB_FL_OVERWRITE))
 				goto out_unlock;
-			}
 
 			/* tail_page has not moved yet? */
 			if (tail_page == cpu_buffer->tail_page) {
@@ -1105,6 +1101,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 
  out_unlock:
+	/* reset write */
+	if (tail <= BUF_PAGE_SIZE)
+		local_set(&tail_page->write, tail);
+
 	__raw_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 	return NULL;
@@ -2174,6 +2174,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 
 	cpu_buffer->overrun = 0;
 	cpu_buffer->entries = 0;
+
+	cpu_buffer->write_stamp = 0;
+	cpu_buffer->read_stamp = 0;
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c580233add95..17bb88d86ac2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -40,7 +40,7 @@
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
-unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
+unsigned long __read_mostly	tracing_max_latency;
 unsigned long __read_mostly	tracing_thresh;
 
 /*
@@ -3736,7 +3736,7 @@ static struct notifier_block trace_die_notifier = {
  * it if we decide to change what log level the ftrace dump
  * should be at.
  */
-#define KERN_TRACE		KERN_INFO
+#define KERN_TRACE		KERN_EMERG
 
 static void
 trace_printk_seq(struct trace_seq *s)
@@ -3770,6 +3770,7 @@ void ftrace_dump(void)
 	dump_ran = 1;
 
 	/* No turning back! */
+	tracing_off();
 	ftrace_kill();
 
 	for_each_tracing_cpu(cpu) {
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 7c2e326bbc8b..62a78d943534 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -380,6 +380,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
+	tracing_max_latency = 0;
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index fffcb069f1dc..80e503ef6136 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <asm/atomic.h>
 
 #include "trace.h"
 
@@ -19,6 +20,7 @@ struct header_iter {
 static struct trace_array *mmio_trace_array;
 static bool overrun_detected;
 static unsigned long prev_overruns;
+static atomic_t dropped_count;
 
 static void mmio_reset_data(struct trace_array *tr)
 {
@@ -121,11 +123,11 @@ static void mmio_close(struct trace_iterator *iter)
 
 static unsigned long count_overruns(struct trace_iterator *iter)
 {
-	unsigned long cnt = 0;
+	unsigned long cnt = atomic_xchg(&dropped_count, 0);
 	unsigned long over = ring_buffer_overruns(iter->tr->buffer);
 
 	if (over > prev_overruns)
-		cnt = over - prev_overruns;
+		cnt += over - prev_overruns;
 	prev_overruns = over;
 	return cnt;
 }
@@ -310,8 +312,10 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 
 	event	= ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					   &irq_flags);
-	if (!event)
+	if (!event) {
+		atomic_inc(&dropped_count);
 		return;
+	}
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, preempt_count());
 	entry->ent.type			= TRACE_MMIO_RW;
@@ -338,8 +342,10 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 
 	event	= ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					   &irq_flags);
-	if (!event)
+	if (!event) {
+		atomic_inc(&dropped_count);
 		return;
+	}
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, preempt_count());
 	entry->ent.type			= TRACE_MMIO_MAP;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 43586b689e31..42ae1e77b6b3 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -333,6 +333,7 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	tracing_max_latency = 0;
 	wakeup_trace = tr;
 	start_wakeup_tracer(tr);
 	return 0;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 88c8eb70f54a..bc8e80a86bca 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -23,10 +23,20 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 {
 	struct ring_buffer_event *event;
 	struct trace_entry *entry;
+	unsigned int loops = 0;
 
 	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
 		entry = ring_buffer_event_data(event);
 
+		/*
+		 * The ring buffer is a size of trace_buf_size, if
+		 * we loop more than the size, there's something wrong
+		 * with the ring buffer.
+		 */
+		if (loops++ > trace_buf_size) {
+			printk(KERN_CONT ".. bad ring buffer ");
+			goto failed;
+		}
 		if (!trace_valid_entry(entry)) {
 			printk(KERN_CONT ".. invalid entry %d ",
 				entry->type);
@@ -57,11 +67,20 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 
 	cnt = ring_buffer_entries(tr->buffer);
 
+	/*
+	 * The trace_test_buffer_cpu runs a while loop to consume all data.
+	 * If the calling tracer is broken, and is constantly filling
+	 * the buffer, this will run forever, and hard lock the box.
+	 * We disable the ring buffer while we do this test to prevent
+	 * a hard lock up.
+	 */
+	tracing_off();
 	for_each_possible_cpu(cpu) {
 		ret = trace_test_buffer_cpu(tr, cpu);
 		if (ret)
 			break;
 	}
+	tracing_on();
 	__raw_spin_unlock(&ftrace_max_lock);
 	local_irq_restore(flags);
 
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 43f891b05a4b..00d59d048edf 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -122,8 +122,10 @@ void acct_update_integrals(struct task_struct *tsk)
 	if (likely(tsk->mm)) {
 		cputime_t time, dtime;
 		struct timeval value;
+		unsigned long flags;
 		u64 delta;
 
+		local_irq_save(flags);
 		time = tsk->stime + tsk->utime;
 		dtime = cputime_sub(time, tsk->acct_timexpd);
 		jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
@@ -131,10 +133,12 @@ void acct_update_integrals(struct task_struct *tsk)
 		delta = delta * USEC_PER_SEC + value.tv_usec;
 
 		if (delta == 0)
-			return;
+			goto out;
 		tsk->acct_timexpd = time;
 		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
 		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
+	out:
+		local_irq_restore(flags);
 	}
 }
 
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 2460c3199b5a..0314501688b9 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -17,7 +17,7 @@
 
 #include <asm/uaccess.h>
 
-asmlinkage long sys_chown16(const char __user * filename, old_uid_t user, old_gid_t group)
+SYSCALL_DEFINE3(chown16, const char __user *, filename, old_uid_t, user, old_gid_t, group)
 {
 	long ret = sys_chown(filename, low2highuid(user), low2highgid(group));
 	/* avoid REGPARM breakage on x86: */
@@ -25,7 +25,7 @@ asmlinkage long sys_chown16(const char __user * filename, old_uid_t user, old_gi
 	return ret;
 }
 
-asmlinkage long sys_lchown16(const char __user * filename, old_uid_t user, old_gid_t group)
+SYSCALL_DEFINE3(lchown16, const char __user *, filename, old_uid_t, user, old_gid_t, group)
 {
 	long ret = sys_lchown(filename, low2highuid(user), low2highgid(group));
 	/* avoid REGPARM breakage on x86: */
@@ -33,7 +33,7 @@ asmlinkage long sys_lchown16(const char __user * filename, old_uid_t user, old_g
 	return ret;
 }
 
-asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group)
+SYSCALL_DEFINE3(fchown16, unsigned int, fd, old_uid_t, user, old_gid_t, group)
 {
 	long ret = sys_fchown(fd, low2highuid(user), low2highgid(group));
 	/* avoid REGPARM breakage on x86: */
@@ -41,7 +41,7 @@ asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group)
 	return ret;
 }
 
-asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid)
+SYSCALL_DEFINE2(setregid16, old_gid_t, rgid, old_gid_t, egid)
 {
 	long ret = sys_setregid(low2highgid(rgid), low2highgid(egid));
 	/* avoid REGPARM breakage on x86: */
@@ -49,7 +49,7 @@ asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid)
 	return ret;
 }
 
-asmlinkage long sys_setgid16(old_gid_t gid)
+SYSCALL_DEFINE1(setgid16, old_gid_t, gid)
 {
 	long ret = sys_setgid(low2highgid(gid));
 	/* avoid REGPARM breakage on x86: */
@@ -57,7 +57,7 @@ asmlinkage long sys_setgid16(old_gid_t gid)
 	return ret;
 }
 
-asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid)
+SYSCALL_DEFINE2(setreuid16, old_uid_t, ruid, old_uid_t, euid)
 {
 	long ret = sys_setreuid(low2highuid(ruid), low2highuid(euid));
 	/* avoid REGPARM breakage on x86: */
@@ -65,7 +65,7 @@ asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid)
 	return ret;
 }
 
-asmlinkage long sys_setuid16(old_uid_t uid)
+SYSCALL_DEFINE1(setuid16, old_uid_t, uid)
 {
 	long ret = sys_setuid(low2highuid(uid));
 	/* avoid REGPARM breakage on x86: */
@@ -73,7 +73,7 @@ asmlinkage long sys_setuid16(old_uid_t uid)
 	return ret;
 }
 
-asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
+SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid)
 {
 	long ret = sys_setresuid(low2highuid(ruid), low2highuid(euid),
 				 low2highuid(suid));
@@ -82,7 +82,7 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
 	return ret;
 }
 
-asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid, old_uid_t __user *suid)
+SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruid, old_uid_t __user *, euid, old_uid_t __user *, suid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -94,7 +94,7 @@ asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid,
 	return retval;
 }
 
-asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
+SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid)
 {
 	long ret = sys_setresgid(low2highgid(rgid), low2highgid(egid),
 				 low2highgid(sgid));
@@ -103,7 +103,8 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
 	return ret;
 }
 
-asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid, old_gid_t __user *sgid)
+
+SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgid, old_gid_t __user *, egid, old_gid_t __user *, sgid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -115,7 +116,7 @@ asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid,
 	return retval;
 }
 
-asmlinkage long sys_setfsuid16(old_uid_t uid)
+SYSCALL_DEFINE1(setfsuid16, old_uid_t, uid)
 {
 	long ret = sys_setfsuid(low2highuid(uid));
 	/* avoid REGPARM breakage on x86: */
@@ -123,7 +124,7 @@ asmlinkage long sys_setfsuid16(old_uid_t uid)
 	return ret;
 }
 
-asmlinkage long sys_setfsgid16(old_gid_t gid)
+SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid)
 {
 	long ret = sys_setfsgid(low2highgid(gid));
 	/* avoid REGPARM breakage on x86: */
@@ -161,7 +162,7 @@ static int groups16_from_user(struct group_info *group_info,
 	return 0;
 }
 
-asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist)
+SYSCALL_DEFINE2(getgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 {
 	const struct cred *cred = current_cred();
 	int i;
@@ -184,7 +185,7 @@ out:
 	return i;
 }
 
-asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
+SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 {
 	struct group_info *group_info;
 	int retval;
@@ -209,22 +210,22 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
 	return retval;
 }
 
-asmlinkage long sys_getuid16(void)
+SYSCALL_DEFINE0(getuid16)
 {
 	return high2lowuid(current_uid());
 }
 
-asmlinkage long sys_geteuid16(void)
+SYSCALL_DEFINE0(geteuid16)
 {
 	return high2lowuid(current_euid());
 }
 
-asmlinkage long sys_getgid16(void)
+SYSCALL_DEFINE0(getgid16)
 {
 	return high2lowgid(current_gid());
 }
 
-asmlinkage long sys_getegid16(void)
+SYSCALL_DEFINE0(getegid16)
 {
 	return high2lowgid(current_egid());
 }
diff --git a/kernel/up.c b/kernel/up.c
new file mode 100644
index 000000000000..1ff27a28bb7d
--- /dev/null
+++ b/kernel/up.c
@@ -0,0 +1,21 @@
+/*
+ * Uniprocessor-only support functions.  The counterpart to kernel/smp.c
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+
+int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+				int wait)
+{
+	WARN_ON(cpu != 0);
+
+	local_irq_disable();
+	(func)(info);
+	local_irq_enable();
+
+	return 0;
+}
+EXPORT_SYMBOL(smp_call_function_single);
diff --git a/kernel/user.c b/kernel/user.c
index 477b6660f447..fbb300e6191f 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -72,6 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 static void uid_hash_remove(struct user_struct *up)
 {
 	hlist_del_init(&up->uidhash_node);
+	put_user_ns(up->user_ns);
 }
 
 static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
@@ -285,14 +286,12 @@ int __init uids_sysfs_init(void)
 /* work function to remove sysfs directory for a user and free up
  * corresponding structures.
  */
-static void remove_user_sysfs_dir(struct work_struct *w)
+static void cleanup_user_struct(struct work_struct *w)
 {
 	struct user_struct *up = container_of(w, struct user_struct, work);
 	unsigned long flags;
 	int remove_user = 0;
 
-	if (up->user_ns != &init_user_ns)
-		return;
 	/* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
 	 * atomic.
 	 */
@@ -311,9 +310,11 @@ static void remove_user_sysfs_dir(struct work_struct *w)
 	if (!remove_user)
 		goto done;
 
-	kobject_uevent(&up->kobj, KOBJ_REMOVE);
-	kobject_del(&up->kobj);
-	kobject_put(&up->kobj);
+	if (up->user_ns == &init_user_ns) {
+		kobject_uevent(&up->kobj, KOBJ_REMOVE);
+		kobject_del(&up->kobj);
+		kobject_put(&up->kobj);
+	}
 
 	sched_destroy_user(up);
 	key_put(up->uid_keyring);
@@ -334,8 +335,7 @@ static void free_user(struct user_struct *up, unsigned long flags)
 	atomic_inc(&up->__count);
 	spin_unlock_irqrestore(&uidhash_lock, flags);
 
-	put_user_ns(up->user_ns);
-	INIT_WORK(&up->work, remove_user_sysfs_dir);
+	INIT_WORK(&up->work, cleanup_user_struct);
 	schedule_work(&up->work);
 }
 
@@ -357,12 +357,29 @@ static void free_user(struct user_struct *up, unsigned long flags)
 	sched_destroy_user(up);
 	key_put(up->uid_keyring);
 	key_put(up->session_keyring);
-	put_user_ns(up->user_ns);
 	kmem_cache_free(uid_cachep, up);
 }
 
 #endif
 
+#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
+/*
+ * We need to check if a setuid can take place. This function should be called
+ * before successfully completing the setuid.
+ */
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+
+	return sched_rt_can_attach(up->tg, tsk);
+
+}
+#else
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+	return 1;
+}
+#endif
+
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 79084311ee57..076c7c8215b0 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -60,12 +60,25 @@ int create_user_ns(struct cred *new)
 	return 0;
 }
 
-void free_user_ns(struct kref *kref)
+/*
+ * Deferred destructor for a user namespace.  This is required because
+ * free_user_ns() may be called with uidhash_lock held, but we need to call
+ * back to free_uid() which will want to take the lock again.
+ */
+static void free_user_ns_work(struct work_struct *work)
 {
-	struct user_namespace *ns;
-
-	ns = container_of(kref, struct user_namespace, kref);
+	struct user_namespace *ns =
+		container_of(work, struct user_namespace, destroyer);
 	free_uid(ns->creator);
 	kfree(ns);
 }
+
+void free_user_ns(struct kref *kref)
+{
+	struct user_namespace *ns =
+		container_of(kref, struct user_namespace, kref);
+
+	INIT_WORK(&ns->destroyer, free_user_ns_work);
+	schedule_work(&ns->destroyer);
+}
 EXPORT_SYMBOL(free_user_ns);
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131f2fc2..42a2dbc181c8 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 {
 	unsigned long flags;
@@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(finish_wait);
 
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	spin_lock_irqsave(&q->lock, flags);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+	else if (waitqueue_active(q))
+		__wake_up_common(q, mode, 1, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
 	int ret = default_wake_function(wait, mode, sync, key);
@@ -177,17 +219,20 @@ int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 			int (*action)(void *), unsigned mode)
 {
-	int ret = 0;
-
 	do {
+		int ret;
+
 		prepare_to_wait_exclusive(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags)) {
-			if ((ret = (*action)(q->key.flags)))
-				break;
-		}
+		if (!test_bit(q->key.bit_nr, q->key.flags))
+			continue;
+		ret = action(q->key.flags);
+		if (!ret)
+			continue;
+		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+		return ret;
 	} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
 	finish_wait(wq, &q->wait);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(__wait_on_bit_lock);
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2f445833ae37..1f0c509b40d3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -971,6 +971,8 @@ undo:
 }
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *work_on_cpu_wq __read_mostly;
+
 struct work_for_cpu {
 	struct work_struct work;
 	long (*fn)(void *);
@@ -991,8 +993,8 @@ static void do_work_for_cpu(struct work_struct *w)
  * @fn: the function to run
  * @arg: the function arg
  *
- * This will return -EINVAL in the cpu is not online, or the return value
- * of @fn otherwise.
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
@@ -1001,14 +1003,8 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 	INIT_WORK(&wfc.work, do_work_for_cpu);
 	wfc.fn = fn;
 	wfc.arg = arg;
-	get_online_cpus();
-	if (unlikely(!cpu_online(cpu)))
-		wfc.ret = -EINVAL;
-	else {
-		schedule_work_on(cpu, &wfc.work);
-		flush_work(&wfc.work);
-	}
-	put_online_cpus();
+	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
+	flush_work(&wfc.work);
 
 	return wfc.ret;
 }
@@ -1025,4 +1021,8 @@ void __init init_workqueues(void)
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
+#ifdef CONFIG_SMP
+	work_on_cpu_wq = create_workqueue("work_on_cpu");
+	BUG_ON(!work_on_cpu_wq);
+#endif
 }