Merge branch 'master' into for-2.6.35

Conflicts: fs/ext3/fsync.c Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
author: Jens Axboe <jens.axboe@oracle.com> 2010-05-21 21:27:26 +0200
committer: Jens Axboe <jens.axboe@oracle.com> 2010-05-21 21:27:26 +0200
commit: ee9a3607fb03e804ddf624544105f4e34260c380 (patch)
tree: ce41b6e0fa10982a306f6c142a92dbf3c9961284 /kernel
parent: b492e95be0ae672922f4734acf3f5d35c30be948 (diff)
parent: d515e86e639890b33a09390d062b0831664f04a2 (diff)
102 files changed, 12638 insertions, 5064 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index a987aa1676b..057472fbc27 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -68,14 +68,14 @@ obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
-obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
+obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
 obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
-obj-$(CONFIG_KGDB) += kgdb.o
+obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
diff --git a/kernel/acct.c b/kernel/acct.c
index 24f8c81fc48..385b88461c2 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -216,7 +216,6 @@ static int acct_on(char *name)
 {
 	struct file *file;
 	struct vfsmount *mnt;
-	int error;
 	struct pid_namespace *ns;
 	struct bsd_acct_struct *acct = NULL;
 
@@ -244,13 +243,6 @@ static int acct_on(char *name)
 		}
 	}
 
-	error = security_acct(file);
-	if (error) {
-		kfree(acct);
-		filp_close(file, NULL);
-		return error;
-	}
-
 	spin_lock(&acct_lock);
 	if (ns->bacct == NULL) {
 		ns->bacct = acct;
@@ -281,7 +273,7 @@ static int acct_on(char *name)
  */
 SYSCALL_DEFINE1(acct, const char __user *, name)
 {
-	int error;
+	int error = 0;
 
 	if (!capable(CAP_SYS_PACCT))
 		return -EPERM;
@@ -299,13 +291,11 @@ SYSCALL_DEFINE1(acct, const char __user *, name)
 		if (acct == NULL)
 			return 0;
 
-		error = security_acct(NULL);
-		if (!error) {
-			spin_lock(&acct_lock);
-			acct_file_reopen(acct, NULL, NULL);
-			spin_unlock(&acct_lock);
-		}
+		spin_lock(&acct_lock);
+		acct_file_reopen(acct, NULL, NULL);
+		spin_unlock(&acct_lock);
 	}
+
 	return error;
 }
 
@@ -353,17 +343,18 @@ restart:
 
 void acct_exit_ns(struct pid_namespace *ns)
 {
-	struct bsd_acct_struct *acct;
+	struct bsd_acct_struct *acct = ns->bacct;
 
-	spin_lock(&acct_lock);
-	acct = ns->bacct;
-	if (acct != NULL) {
-		if (acct->file != NULL)
-			acct_file_reopen(acct, NULL, NULL);
+	if (acct == NULL)
+		return;
 
-		kfree(acct);
-	}
+	del_timer_sync(&acct->timer);
+	spin_lock(&acct_lock);
+	if (acct->file != NULL)
+		acct_file_reopen(acct, NULL, NULL);
 	spin_unlock(&acct_lock);
+
+	kfree(acct);
 }
 
 /*
diff --git a/kernel/capability.c b/kernel/capability.c
index 9e4697e9b27..2f05303715a 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -15,7 +15,6 @@
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
 #include <asm/uaccess.h>
-#include "cred-internals.h"
 
 /*
  * Leveraged for setting/resetting capabilities
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2769e13980..291775021b2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1646,7 +1646,9 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
 	char *start;
-	struct dentry *dentry = rcu_dereference(cgrp->dentry);
+	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+						      rcu_read_lock_held() ||
+						      cgroup_lock_is_held());
 
 	if (!dentry || cgrp == dummytop) {
 		/*
@@ -1662,13 +1664,17 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 	*--start = '\0';
 	for (;;) {
 		int len = dentry->d_name.len;
+
 		if ((start -= len) < buf)
 			return -ENAMETOOLONG;
-		memcpy(start, cgrp->dentry->d_name.name, len);
+		memcpy(start, dentry->d_name.name, len);
 		cgrp = cgrp->parent;
 		if (!cgrp)
 			break;
-		dentry = rcu_dereference(cgrp->dentry);
+
+		dentry = rcu_dereference_check(cgrp->dentry,
+					       rcu_read_lock_held() ||
+					       cgroup_lock_is_held());
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -3010,7 +3016,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
 	unsigned long flags = (unsigned long)key;
 
 	if (flags & POLLHUP) {
-		remove_wait_queue_locked(event->wqh, &event->wait);
+		__remove_wait_queue(event->wqh, &event->wait);
 		spin_lock(&cgrp->event_list_lock);
 		list_del(&event->list);
 		spin_unlock(&cgrp->event_list_lock);
@@ -3609,7 +3615,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
  * @ss: the subsystem to load
  *
  * This function should be called in a modular subsystem's initcall. If the
- * subsytem is built as a module, it will be assigned a new subsys_id and set
+ * subsystem is built as a module, it will be assigned a new subsys_id and set
  * up for use. If the subsystem is built-in anyway, work is delegated to the
  * simpler cgroup_init_subsys.
  */
@@ -4429,7 +4435,15 @@ __setup("cgroup_disable=", cgroup_disable);
  */
 unsigned short css_id(struct cgroup_subsys_state *css)
 {
-	struct css_id *cssid = rcu_dereference(css->id);
+	struct css_id *cssid;
+
+	/*
+	 * This css_id() can return correct value when somone has refcnt
+	 * on this or this is under rcu_read_lock(). Once css->id is allocated,
+	 * it's unchanged until freed.
+	 */
+	cssid = rcu_dereference_check(css->id,
+			rcu_read_lock_held() || atomic_read(&css->refcnt));
 
 	if (cssid)
 		return cssid->id;
@@ -4439,7 +4453,10 @@ EXPORT_SYMBOL_GPL(css_id);
 
 unsigned short css_depth(struct cgroup_subsys_state *css)
 {
-	struct css_id *cssid = rcu_dereference(css->id);
+	struct css_id *cssid;
+
+	cssid = rcu_dereference_check(css->id,
+			rcu_read_lock_held() || atomic_read(&css->refcnt));
 
 	if (cssid)
 		return cssid->depth;
@@ -4447,15 +4464,36 @@ unsigned short css_depth(struct cgroup_subsys_state *css)
 }
 EXPORT_SYMBOL_GPL(css_depth);
 
+/**
+ *  css_is_ancestor - test "root" css is an ancestor of "child"
+ * @child: the css to be tested.
+ * @root: the css supporsed to be an ancestor of the child.
+ *
+ * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
+ * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
+ * But, considering usual usage, the csses should be valid objects after test.
+ * Assuming that the caller will do some action to the child if this returns
+ * returns true, the caller must take "child";s reference count.
+ * If "child" is valid object and this returns true, "root" is valid, too.
+ */
+
 bool css_is_ancestor(struct cgroup_subsys_state *child,
 		    const struct cgroup_subsys_state *root)
 {
-	struct css_id *child_id = rcu_dereference(child->id);
-	struct css_id *root_id = rcu_dereference(root->id);
+	struct css_id *child_id;
+	struct css_id *root_id;
+	bool ret = true;
 
-	if (!child_id || !root_id || (child_id->depth < root_id->depth))
-		return false;
-	return child_id->stack[root_id->depth] == root_id->id;
+	rcu_read_lock();
+	child_id  = rcu_dereference(child->id);
+	root_id = rcu_dereference(root->id);
+	if (!child_id
+	    || !root_id
+	    || (child_id->depth < root_id->depth)
+	    || (child_id->stack[root_id->depth] != root_id->id))
+		ret = false;
+	rcu_read_unlock();
+	return ret;
 }
 
 static void __free_css_id_cb(struct rcu_head *head)
@@ -4555,13 +4593,13 @@ static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
 {
 	int subsys_id, i, depth = 0;
 	struct cgroup_subsys_state *parent_css, *child_css;
-	struct css_id *child_id, *parent_id = NULL;
+	struct css_id *child_id, *parent_id;
 
 	subsys_id = ss->subsys_id;
 	parent_css = parent->subsys[subsys_id];
 	child_css = child->subsys[subsys_id];
-	depth = css_depth(parent_css) + 1;
 	parent_id = parent_css->id;
+	depth = parent_id->depth;
 
 	child_id = get_new_cssid(ss, depth);
 	if (IS_ERR(child_id))
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index da5e1397553..ce71ed53e88 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -89,10 +89,10 @@ struct cgroup_subsys freezer_subsys;
 
 /* Locks taken and their ordering
  * ------------------------------
- * css_set_lock
  * cgroup_mutex (AKA cgroup_lock)
- * task->alloc_lock (AKA task_lock)
  * freezer->lock
+ * css_set_lock
+ * task->alloc_lock (AKA task_lock)
  * task->sighand->siglock
  *
  * cgroup code forces css_set_lock to be taken before task->alloc_lock
@@ -100,33 +100,38 @@ struct cgroup_subsys freezer_subsys;
  * freezer_create(), freezer_destroy():
  * cgroup_mutex [ by cgroup core ]
  *
- * can_attach():
- * cgroup_mutex
+ * freezer_can_attach():
+ * cgroup_mutex (held by caller of can_attach)
  *
- * cgroup_frozen():
+ * cgroup_freezing_or_frozen():
  * task->alloc_lock (to get task's cgroup)
  *
  * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
- * task->alloc_lock (to get task's cgroup)
  * freezer->lock
  *  sighand->siglock (if the cgroup is freezing)
  *
  * freezer_read():
  * cgroup_mutex
  *  freezer->lock
+ *   write_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
  *
  * freezer_write() (freeze):
  * cgroup_mutex
  *  freezer->lock
+ *   write_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
- *    sighand->siglock
+ *    sighand->siglock (fake signal delivery inside freeze_task())
  *
  * freezer_write() (unfreeze):
  * cgroup_mutex
  *  freezer->lock
+ *   write_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock (to prevent races with freeze_task())
+ *    task->alloc_lock (inside thaw_process(), prevents race with refrigerator())
  *     sighand->siglock
  */
 static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
@@ -205,9 +210,12 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 	 * No lock is needed, since the task isn't on tasklist yet,
 	 * so it can't be moved to another cgroup, which means the
 	 * freezer won't be removed and will be valid during this
-	 * function call.
+	 * function call.  Nevertheless, apply RCU read-side critical
+	 * section to suppress RCU lockdep false positives.
 	 */
+	rcu_read_lock();
 	freezer = task_freezer(task);
+	rcu_read_unlock();
 
 	/*
 	 * The root cgroup is non-freezable, so we can skip the
diff --git a/kernel/compat.c b/kernel/compat.c
index 7f40e9275fd..5adab05a317 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -495,29 +495,26 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
 {
 	int ret;
 	cpumask_var_t mask;
-	unsigned long *k;
-	unsigned int min_length = cpumask_size();
-
-	if (nr_cpu_ids <= BITS_PER_COMPAT_LONG)
-		min_length = sizeof(compat_ulong_t);
 
-	if (len < min_length)
+	if ((len * BITS_PER_BYTE) < nr_cpu_ids)
+		return -EINVAL;
+	if (len & (sizeof(compat_ulong_t)-1))
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
 
 	ret = sched_getaffinity(pid, mask);
-	if (ret < 0)
-		goto out;
+	if (ret == 0) {
+		size_t retlen = min_t(size_t, len, cpumask_size());
 
-	k = cpumask_bits(mask);
-	ret = compat_put_bitmap(user_mask_ptr, k, min_length * 8);
-	if (ret == 0)
-		ret = min_length;
-
-out:
+		if (compat_put_bitmap(user_mask_ptr, cpumask_bits(mask), retlen * 8))
+			ret = -EFAULT;
+		else
+			ret = retlen;
+	}
 	free_cpumask_var(mask);
+
 	return ret;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 25bba73b1be..54577757477 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -164,6 +164,7 @@ static inline void check_for_tasks(int cpu)
 }
 
 struct take_cpu_down_param {
+	struct task_struct *caller;
 	unsigned long mod;
 	void *hcpu;
 };
@@ -172,6 +173,7 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
+	unsigned int cpu = (unsigned long)param->hcpu;
 	int err;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
@@ -182,6 +184,8 @@ static int __ref take_cpu_down(void *_param)
 	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
 				param->hcpu);
 
+	if (task_cpu(param->caller) == cpu)
+		move_task_off_dead_cpu(cpu, param->caller);
 	/* Force idle task to run as soon as we yield: it should
 	   immediately notice cpu is offline and die quickly. */
 	sched_idle_next();
@@ -192,10 +196,10 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
 	int err, nr_calls = 0;
-	cpumask_var_t old_allowed;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
+		.caller = current,
 		.mod = mod,
 		.hcpu = hcpu,
 	};
@@ -206,9 +210,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	if (!cpu_online(cpu))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
-		return -ENOMEM;
-
 	cpu_hotplug_begin();
 	set_cpu_active(cpu, false);
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
@@ -225,10 +226,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		goto out_release;
 	}
 
-	/* Ensure that we are not runnable on dying cpu */
-	cpumask_copy(old_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpu_active_mask);
-
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		set_cpu_active(cpu, true);
@@ -237,7 +234,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 
-		goto out_allowed;
+		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
 
@@ -255,8 +252,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	check_for_tasks(cpu);
 
-out_allowed:
-	set_cpus_allowed_ptr(current, old_allowed);
 out_release:
 	cpu_hotplug_done();
 	if (!err) {
@@ -264,7 +259,6 @@ out_release:
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 	}
-	free_cpumask_var(old_allowed);
 	return err;
 }
 
@@ -272,9 +266,6 @@ int __ref cpu_down(unsigned int cpu)
 {
 	int err;
 
-	err = stop_machine_create();
-	if (err)
-		return err;
 	cpu_maps_update_begin();
 
 	if (cpu_hotplug_disabled) {
@@ -286,7 +277,6 @@ int __ref cpu_down(unsigned int cpu)
 
 out:
 	cpu_maps_update_done();
-	stop_machine_destroy();
 	return err;
 }
 EXPORT_SYMBOL(cpu_down);
@@ -367,9 +357,6 @@ int disable_nonboot_cpus(void)
 {
 	int cpu, first_cpu, error;
 
-	error = stop_machine_create();
-	if (error)
-		return error;
 	cpu_maps_update_begin();
 	first_cpu = cpumask_first(cpu_online_mask);
 	/*
@@ -400,7 +387,6 @@ int disable_nonboot_cpus(void)
 		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
 	}
 	cpu_maps_update_done();
-	stop_machine_destroy();
 	return error;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d10946748ec..9a50c5f6e72 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2182,19 +2182,52 @@ void __init cpuset_init_smp(void)
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	mutex_lock(&callback_mutex);
-	cpuset_cpus_allowed_locked(tsk, pmask);
+	task_lock(tsk);
+	guarantee_online_cpus(task_cs(tsk), pmask);
+	task_unlock(tsk);
 	mutex_unlock(&callback_mutex);
 }
 
-/**
- * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
- * Must be called with callback_mutex held.
- **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
-	task_lock(tsk);
-	guarantee_online_cpus(task_cs(tsk), pmask);
-	task_unlock(tsk);
+	const struct cpuset *cs;
+	int cpu;
+
+	rcu_read_lock();
+	cs = task_cs(tsk);
+	if (cs)
+		cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+	rcu_read_unlock();
+
+	/*
+	 * We own tsk->cpus_allowed, nobody can change it under us.
+	 *
+	 * But we used cs && cs->cpus_allowed lockless and thus can
+	 * race with cgroup_attach_task() or update_cpumask() and get
+	 * the wrong tsk->cpus_allowed. However, both cases imply the
+	 * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr()
+	 * which takes task_rq_lock().
+	 *
+	 * If we are called after it dropped the lock we must see all
+	 * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
+	 * set any mask even if it is not right from task_cs() pov,
+	 * the pending set_cpus_allowed_ptr() will fix things.
+	 */
+
+	cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
+	if (cpu >= nr_cpu_ids) {
+		/*
+		 * Either tsk->cpus_allowed is wrong (see above) or it
+		 * is actually empty. The latter case is only possible
+		 * if we are racing with remove_tasks_in_empty_cpuset().
+		 * Like above we can temporary set any mask and rely on
+		 * set_cpus_allowed_ptr() as synchronization point.
+		 */
+		cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+		cpu = cpumask_any(cpu_active_mask);
+	}
+
+	return cpu;
 }
 
 void cpuset_init_current_mems_allowed(void)
@@ -2383,22 +2416,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 }
 
 /**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset.  Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list.  The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
-	mutex_lock(&callback_mutex);
-}
-
-/**
  * cpuset_unlock - release lock on cpuset changes
  *
  * Undo the lock taken in a previous cpuset_lock() call.
diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h
deleted file mode 100644
index 2dc4fc2d0bf..00000000000
--- a/kernel/cred-internals.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* Internal credentials stuff
- *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-/*
- * user.c
- */
-static inline void sched_switch_user(struct task_struct *p)
-{
-#ifdef CONFIG_USER_SCHED
-	sched_move_task(p);
-#endif	/* CONFIG_USER_SCHED */
-}
-
diff --git a/kernel/cred.c b/kernel/cred.c
index 62af1816c23..2c24870c55d 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -17,7 +17,6 @@
 #include <linux/init_task.h>
 #include <linux/security.h>
 #include <linux/cn_proc.h>
-#include "cred-internals.h"
 
 #if 0
 #define kdebug(FMT, ...) \
@@ -523,8 +522,6 @@ int commit_creds(struct cred *new)
 #endif
 	BUG_ON(atomic_read(&new->usage) < 1);
 
-	security_commit_creds(new, old);
-
 	get_cred(new); /* we will require a ref for the subj creds too */
 
 	/* dumpability changes */
@@ -560,8 +557,6 @@ int commit_creds(struct cred *new)
 		atomic_dec(&old->user->processes);
 	alter_cred_subscribers(old, -2);
 
-	sched_switch_user(task);
-
 	/* send notifications */
 	if (new->uid   != old->uid  ||
 	    new->euid  != old->euid ||
diff --git a/kernel/debug/Makefile b/kernel/debug/Makefile
new file mode 100644
index 00000000000..a85edc33998
--- /dev/null
+++ b/kernel/debug/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for the linux kernel debugger
+#
+
+obj-$(CONFIG_KGDB) += debug_core.o gdbstub.o
+obj-$(CONFIG_KGDB_KDB) += kdb/
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
new file mode 100644
index 00000000000..5cb7cd1de10
--- /dev/null
+++ b/kernel/debug/debug_core.c
@@ -0,0 +1,983 @@
+/*
+ * Kernel Debug Core
+ *
+ * Maintainer: Jason Wessel <jason.wessel@windriver.com>
+ *
+ * Copyright (C) 2000-2001 VERITAS Software Corporation.
+ * Copyright (C) 2002-2004 Timesys Corporation
+ * Copyright (C) 2003-2004 Amit S. Kale <amitkale@linsyssoft.com>
+ * Copyright (C) 2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2004-2006 Tom Rini <trini@kernel.crashing.org>
+ * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd.
+ * Copyright (C) 2005-2009 Wind River Systems, Inc.
+ * Copyright (C) 2007 MontaVista Software, Inc.
+ * Copyright (C) 2008 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * Contributors at various stages not listed above:
+ *  Jason Wessel ( jason.wessel@windriver.com )
+ *  George Anzinger <george@mvista.com>
+ *  Anurekh Saxena (anurekh.saxena@timesys.com)
+ *  Lake Stevens Instrument Division (Glenn Engel)
+ *  Jim Kingdon, Cygnus Support.
+ *
+ * Original KGDB stub: David Grothe <dave@gcom.com>,
+ * Tigran Aivazian <tigran@sco.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+#include <linux/pid_namespace.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/console.h>
+#include <linux/threads.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/sysrq.h>
+#include <linux/init.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/pid.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
+
+#include <asm/cacheflush.h>
+#include <asm/byteorder.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+
+#include "debug_core.h"
+
+static int kgdb_break_asap;
+
+struct debuggerinfo_struct kgdb_info[NR_CPUS];
+
+/**
+ * kgdb_connected - Is a host GDB connected to us?
+ */
+int				kgdb_connected;
+EXPORT_SYMBOL_GPL(kgdb_connected);
+
+/* All the KGDB handlers are installed */
+int			kgdb_io_module_registered;
+
+/* Guard for recursive entry */
+static int			exception_level;
+
+struct kgdb_io		*dbg_io_ops;
+static DEFINE_SPINLOCK(kgdb_registration_lock);
+
+/* kgdb console driver is loaded */
+static int kgdb_con_registered;
+/* determine if kgdb console output should be used */
+static int kgdb_use_con;
+/* Flag for alternate operations for early debugging */
+bool dbg_is_early = true;
+/* Next cpu to become the master debug core */
+int dbg_switch_cpu;
+
+/* Use kdb or gdbserver mode */
+int dbg_kdb_mode = 1;
+
+static int __init opt_kgdb_con(char *str)
+{
+	kgdb_use_con = 1;
+	return 0;
+}
+
+early_param("kgdbcon", opt_kgdb_con);
+
+module_param(kgdb_use_con, int, 0644);
+
+/*
+ * Holds information about breakpoints in a kernel. These breakpoints are
+ * added and removed by gdb.
+ */
+static struct kgdb_bkpt		kgdb_break[KGDB_MAX_BREAKPOINTS] = {
+	[0 ... KGDB_MAX_BREAKPOINTS-1] = { .state = BP_UNDEFINED }
+};
+
+/*
+ * The CPU# of the active CPU, or -1 if none:
+ */
+atomic_t			kgdb_active = ATOMIC_INIT(-1);
+EXPORT_SYMBOL_GPL(kgdb_active);
+
+/*
+ * We use NR_CPUs not PERCPU, in case kgdb is used to debug early
+ * bootup code (which might not have percpu set up yet):
+ */
+static atomic_t			passive_cpu_wait[NR_CPUS];
+static atomic_t			cpu_in_kgdb[NR_CPUS];
+static atomic_t			kgdb_break_tasklet_var;
+atomic_t			kgdb_setting_breakpoint;
+
+struct task_struct		*kgdb_usethread;
+struct task_struct		*kgdb_contthread;
+
+int				kgdb_single_step;
+static pid_t			kgdb_sstep_pid;
+
+/* to keep track of the CPU which is doing the single stepping*/
+atomic_t			kgdb_cpu_doing_single_step = ATOMIC_INIT(-1);
+
+/*
+ * If you are debugging a problem where roundup (the collection of
+ * all other CPUs) is a problem [this should be extremely rare],
+ * then use the nokgdbroundup option to avoid roundup. In that case
+ * the other CPUs might interfere with your debugging context, so
+ * use this with care:
+ */
+static int kgdb_do_roundup = 1;
+
+static int __init opt_nokgdbroundup(char *str)
+{
+	kgdb_do_roundup = 0;
+
+	return 0;
+}
+
+early_param("nokgdbroundup", opt_nokgdbroundup);
+
+/*
+ * Finally, some KGDB code :-)
+ */
+
+/*
+ * Weak aliases for breakpoint management,
+ * can be overriden by architectures when needed:
+ */
+int __weak kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr)
+{
+	int err;
+
+	err = probe_kernel_read(saved_instr, (char *)addr, BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+
+	return probe_kernel_write((char *)addr, arch_kgdb_ops.gdb_bpt_instr,
+				  BREAK_INSTR_SIZE);
+}
+
+int __weak kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle)
+{
+	return probe_kernel_write((char *)addr,
+				  (char *)bundle, BREAK_INSTR_SIZE);
+}
+
+int __weak kgdb_validate_break_address(unsigned long addr)
+{
+	char tmp_variable[BREAK_INSTR_SIZE];
+	int err;
+	/* Validate setting the breakpoint and then removing it.  In the
+	 * remove fails, the kernel needs to emit a bad message because we
+	 * are deep trouble not being able to put things back the way we
+	 * found them.
+	 */
+	err = kgdb_arch_set_breakpoint(addr, tmp_variable);
+	if (err)
+		return err;
+	err = kgdb_arch_remove_breakpoint(addr, tmp_variable);
+	if (err)
+		printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
+		   "memory destroyed at: %lx", addr);
+	return err;
+}
+
+unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+int __weak kgdb_arch_init(void)
+{
+	return 0;
+}
+
+int __weak kgdb_skipexception(int exception, struct pt_regs *regs)
+{
+	return 0;
+}
+
+/**
+ *	kgdb_disable_hw_debug - Disable hardware debugging while we in kgdb.
+ *	@regs: Current &struct pt_regs.
+ *
+ *	This function will be called if the particular architecture must
+ *	disable hardware debugging while it is processing gdb packets or
+ *	handling exception.
+ */
+void __weak kgdb_disable_hw_debug(struct pt_regs *regs)
+{
+}
+
+/*
+ * Some architectures need cache flushes when we set/clear a
+ * breakpoint:
+ */
+static void kgdb_flush_swbreak_addr(unsigned long addr)
+{
+	if (!CACHE_FLUSH_IS_SAFE)
+		return;
+
+	if (current->mm && current->mm->mmap_cache) {
+		flush_cache_range(current->mm->mmap_cache,
+				  addr, addr + BREAK_INSTR_SIZE);
+	}
+	/* Force flush instruction cache if it was outside the mm */
+	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
+}
+
+/*
+ * SW breakpoint management:
+ */
+int dbg_activate_sw_breakpoints(void)
+{
+	unsigned long addr;
+	int error;
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if (kgdb_break[i].state != BP_SET)
+			continue;
+
+		addr = kgdb_break[i].bpt_addr;
+		error = kgdb_arch_set_breakpoint(addr,
+				kgdb_break[i].saved_instr);
+		if (error) {
+			ret = error;
+			printk(KERN_INFO "KGDB: BP install failed: %lx", addr);
+			continue;
+		}
+
+		kgdb_flush_swbreak_addr(addr);
+		kgdb_break[i].state = BP_ACTIVE;
+	}
+	return ret;
+}
+
+int dbg_set_sw_break(unsigned long addr)
+{
+	int err = kgdb_validate_break_address(addr);
+	int breakno = -1;
+	int i;
+
+	if (err)
+		return err;
+
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if ((kgdb_break[i].state == BP_SET) &&
+					(kgdb_break[i].bpt_addr == addr))
+			return -EEXIST;
+	}
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if (kgdb_break[i].state == BP_REMOVED &&
+					kgdb_break[i].bpt_addr == addr) {
+			breakno = i;
+			break;
+		}
+	}
+
+	if (breakno == -1) {
+		for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+			if (kgdb_break[i].state == BP_UNDEFINED) {
+				breakno = i;
+				break;
+			}
+		}
+	}
+
+	if (breakno == -1)
+		return -E2BIG;
+
+	kgdb_break[breakno].state = BP_SET;
+	kgdb_break[breakno].type = BP_BREAKPOINT;
+	kgdb_break[breakno].bpt_addr = addr;
+
+	return 0;
+}
+
+int dbg_deactivate_sw_breakpoints(void)
+{
+	unsigned long addr;
+	int error;
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if (kgdb_break[i].state != BP_ACTIVE)
+			continue;
+		addr = kgdb_break[i].bpt_addr;
+		error = kgdb_arch_remove_breakpoint(addr,
+					kgdb_break[i].saved_instr);
+		if (error) {
+			printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr);
+			ret = error;
+		}
+
+		kgdb_flush_swbreak_addr(addr);
+		kgdb_break[i].state = BP_SET;
+	}
+	return ret;
+}
+
+int dbg_remove_sw_break(unsigned long addr)
+{
+	int i;
+
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if ((kgdb_break[i].state == BP_SET) &&
+				(kgdb_break[i].bpt_addr == addr)) {
+			kgdb_break[i].state = BP_REMOVED;
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
+int kgdb_isremovedbreak(unsigned long addr)
+{
+	int i;
+
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if ((kgdb_break[i].state == BP_REMOVED) &&
+					(kgdb_break[i].bpt_addr == addr))
+			return 1;
+	}
+	return 0;
+}
+
+int dbg_remove_all_break(void)
+{
+	unsigned long addr;
+	int error;
+	int i;
+
+	/* Clear memory breakpoints. */
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if (kgdb_break[i].state != BP_ACTIVE)
+			goto setundefined;
+		addr = kgdb_break[i].bpt_addr;
+		error = kgdb_arch_remove_breakpoint(addr,
+				kgdb_break[i].saved_instr);
+		if (error)
+			printk(KERN_ERR "KGDB: breakpoint remove failed: %lx\n",
+			   addr);
+setundefined:
+		kgdb_break[i].state = BP_UNDEFINED;
+	}
+
+	/* Clear hardware breakpoints. */
+	if (arch_kgdb_ops.remove_all_hw_break)
+		arch_kgdb_ops.remove_all_hw_break();
+
+	return 0;
+}
+
+/*
+ * Return true if there is a valid kgdb I/O module.  Also if no
+ * debugger is attached a message can be printed to the console about
+ * waiting for the debugger to attach.
+ *
+ * The print_wait argument is only to be true when called from inside
+ * the core kgdb_handle_exception, because it will wait for the
+ * debugger to attach.
+ */
+static int kgdb_io_ready(int print_wait)
+{
+	if (!dbg_io_ops)
+		return 0;
+	if (kgdb_connected)
+		return 1;
+	if (atomic_read(&kgdb_setting_breakpoint))
+		return 1;
+	if (print_wait) {
+#ifdef CONFIG_KGDB_KDB
+		if (!dbg_kdb_mode)
+			printk(KERN_CRIT "KGDB: waiting... or $3#33 for KDB\n");
+#else
+		printk(KERN_CRIT "KGDB: Waiting for remote debugger\n");
+#endif
+	}
+	return 1;
+}
+
+static int kgdb_reenter_check(struct kgdb_state *ks)
+{
+	unsigned long addr;
+
+	if (atomic_read(&kgdb_active) != raw_smp_processor_id())
+		return 0;
+
+	/* Panic on recursive debugger calls: */
+	exception_level++;
+	addr = kgdb_arch_pc(ks->ex_vector, ks->linux_regs);
+	dbg_deactivate_sw_breakpoints();
+
+	/*
+	 * If the break point removed ok at the place exception
+	 * occurred, try to recover and print a warning to the end
+	 * user because the user planted a breakpoint in a place that
+	 * KGDB needs in order to function.
+	 */
+	if (dbg_remove_sw_break(addr) == 0) {
+		exception_level = 0;
+		kgdb_skipexception(ks->ex_vector, ks->linux_regs);
+		dbg_activate_sw_breakpoints();
+		printk(KERN_CRIT "KGDB: re-enter error: breakpoint removed %lx\n",
+			addr);
+		WARN_ON_ONCE(1);
+
+		return 1;
+	}
+	dbg_remove_all_break();
+	kgdb_skipexception(ks->ex_vector, ks->linux_regs);
+
+	if (exception_level > 1) {
+		dump_stack();
+		panic("Recursive entry to debugger");
+	}
+
+	printk(KERN_CRIT "KGDB: re-enter exception: ALL breakpoints killed\n");
+#ifdef CONFIG_KGDB_KDB
+	/* Allow kdb to debug itself one level */
+	return 0;
+#endif
+	dump_stack();
+	panic("Recursive entry to debugger");
+
+	return 1;
+}
+
+static void dbg_cpu_switch(int cpu, int next_cpu)
+{
+	/* Mark the cpu we are switching away from as a slave when it
+	 * holds the kgdb_active token.  This must be done so that the
+	 * that all the cpus wait in for the debug core will not enter
+	 * again as the master. */
+	if (cpu == atomic_read(&kgdb_active)) {
+		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
+		kgdb_info[cpu].exception_state &= ~DCPU_WANT_MASTER;
+	}
+	kgdb_info[next_cpu].exception_state |= DCPU_NEXT_MASTER;
+}
+
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
+{
+	unsigned long flags;
+	int sstep_tries = 100;
+	int error;
+	int i, cpu;
+	int trace_on = 0;
+acquirelock:
+	/*
+	 * Interrupts will be restored by the 'trap return' code, except when
+	 * single stepping.
+	 */
+	local_irq_save(flags);
+
+	cpu = ks->cpu;
+	kgdb_info[cpu].debuggerinfo = regs;
+	kgdb_info[cpu].task = current;
+	kgdb_info[cpu].ret_state = 0;
+	kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT;
+	/*
+	 * Make sure the above info reaches the primary CPU before
+	 * our cpu_in_kgdb[] flag setting does:
+	 */
+	atomic_inc(&cpu_in_kgdb[cpu]);
+
+	if (exception_level == 1)
+		goto cpu_master_loop;
+
+	/*
+	 * CPU will loop if it is a slave or request to become a kgdb
+	 * master cpu and acquire the kgdb_active lock:
+	 */
+	while (1) {
+cpu_loop:
+		if (kgdb_info[cpu].exception_state & DCPU_NEXT_MASTER) {
+			kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER;
+			goto cpu_master_loop;
+		} else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
+			if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+				break;
+		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
+			if (!atomic_read(&passive_cpu_wait[cpu]))
+				goto return_normal;
+		} else {
+return_normal:
+			/* Return to normal operation by executing any
+			 * hw breakpoint fixup.
+			 */
+			if (arch_kgdb_ops.correct_hw_break)
+				arch_kgdb_ops.correct_hw_break();
+			if (trace_on)
+				tracing_on();
+			atomic_dec(&cpu_in_kgdb[cpu]);
+			touch_softlockup_watchdog_sync();
+			clocksource_touch_watchdog();
+			local_irq_restore(flags);
+			return 0;
+		}
+		cpu_relax();
+	}
+
+	/*
+	 * For single stepping, try to only enter on the processor
+	 * that was single stepping.  To gaurd against a deadlock, the
+	 * kernel will only try for the value of sstep_tries before
+	 * giving up and continuing on.
+	 */
+	if (atomic_read(&kgdb_cpu_doing_single_step) != -1 &&
+	    (kgdb_info[cpu].task &&
+	     kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
+		atomic_set(&kgdb_active, -1);
+		touch_softlockup_watchdog_sync();
+		clocksource_touch_watchdog();
+		local_irq_restore(flags);
+
+		goto acquirelock;
+	}
+
+	if (!kgdb_io_ready(1)) {
+		kgdb_info[cpu].ret_state = 1;
+		goto kgdb_restore; /* No I/O connection, resume the system */
+	}
+
+	/*
+	 * Don't enter if we have hit a removed breakpoint.
+	 */
+	if (kgdb_skipexception(ks->ex_vector, ks->linux_regs))
+		goto kgdb_restore;
+
+	/* Call the I/O driver's pre_exception routine */
+	if (dbg_io_ops->pre_exception)
+		dbg_io_ops->pre_exception();
+
+	kgdb_disable_hw_debug(ks->linux_regs);
+
+	/*
+	 * Get the passive CPU lock which will hold all the non-primary
+	 * CPU in a spin state while the debugger is active
+	 */
+	if (!kgdb_single_step) {
+		for (i = 0; i < NR_CPUS; i++)
+			atomic_inc(&passive_cpu_wait[i]);
+	}
+
+#ifdef CONFIG_SMP
+	/* Signal the other CPUs to enter kgdb_wait() */
+	if ((!kgdb_single_step) && kgdb_do_roundup)
+		kgdb_roundup_cpus(flags);
+#endif
+
+	/*
+	 * Wait for the other CPUs to be notified and be waiting for us:
+	 */
+	for_each_online_cpu(i) {
+		while (kgdb_do_roundup && !atomic_read(&cpu_in_kgdb[i]))
+			cpu_relax();
+	}
+
+	/*
+	 * At this point the primary processor is completely
+	 * in the debugger and all secondary CPUs are quiescent
+	 */
+	dbg_deactivate_sw_breakpoints();
+	kgdb_single_step = 0;
+	kgdb_contthread = current;
+	exception_level = 0;
+	trace_on = tracing_is_on();
+	if (trace_on)
+		tracing_off();
+
+	while (1) {
+cpu_master_loop:
+		if (dbg_kdb_mode) {
+			kgdb_connected = 1;
+			error = kdb_stub(ks);
+		} else {
+			error = gdb_serial_stub(ks);
+		}
+
+		if (error == DBG_PASS_EVENT) {
+			dbg_kdb_mode = !dbg_kdb_mode;
+			kgdb_connected = 0;
+		} else if (error == DBG_SWITCH_CPU_EVENT) {
+			dbg_cpu_switch(cpu, dbg_switch_cpu);
+			goto cpu_loop;
+		} else {
+			kgdb_info[cpu].ret_state = error;
+			break;
+		}
+	}
+
+	/* Call the I/O driver's post_exception routine */
+	if (dbg_io_ops->post_exception)
+		dbg_io_ops->post_exception();
+
+	atomic_dec(&cpu_in_kgdb[ks->cpu]);
+
+	if (!kgdb_single_step) {
+		for (i = NR_CPUS-1; i >= 0; i--)
+			atomic_dec(&passive_cpu_wait[i]);
+		/*
+		 * Wait till all the CPUs have quit from the debugger,
+		 * but allow a CPU that hit an exception and is
+		 * waiting to become the master to remain in the debug
+		 * core.
+		 */
+		for_each_online_cpu(i) {
+			while (kgdb_do_roundup &&
+			       atomic_read(&cpu_in_kgdb[i]) &&
+			       !(kgdb_info[i].exception_state &
+				 DCPU_WANT_MASTER))
+				cpu_relax();
+		}
+	}
+
+kgdb_restore:
+	if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
+		int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step);
+		if (kgdb_info[sstep_cpu].task)
+			kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid;
+		else
+			kgdb_sstep_pid = 0;
+	}
+	if (trace_on)
+		tracing_on();
+	/* Free kgdb_active */
+	atomic_set(&kgdb_active, -1);
+	touch_softlockup_watchdog_sync();
+	clocksource_touch_watchdog();
+	local_irq_restore(flags);
+
+	return kgdb_info[cpu].ret_state;
+}
+
+/*
+ * kgdb_handle_exception() - main entry point from a kernel exception
+ *
+ * Locking hierarchy:
+ *	interface locks, if any (begin_session)
+ *	kgdb lock (kgdb_active)
+ */
+int
+kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+{
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+	int ret;
+
+	ks->cpu			= raw_smp_processor_id();
+	ks->ex_vector		= evector;
+	ks->signo		= signo;
+	ks->err_code		= ecode;
+	ks->kgdb_usethreadid	= 0;
+	ks->linux_regs		= regs;
+
+	if (kgdb_reenter_check(ks))
+		return 0; /* Ouch, double exception ! */
+	kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
+	ret = kgdb_cpu_enter(ks, regs);
+	kgdb_info[ks->cpu].exception_state &= ~(DCPU_WANT_MASTER |
+						DCPU_IS_SLAVE);
+	return ret;
+}
+
+int kgdb_nmicallback(int cpu, void *regs)
+{
+#ifdef CONFIG_SMP
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+
+	memset(ks, 0, sizeof(struct kgdb_state));
+	ks->cpu			= cpu;
+	ks->linux_regs		= regs;
+
+	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
+	    atomic_read(&kgdb_active) != -1 &&
+	    atomic_read(&kgdb_active) != cpu) {
+		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
+		kgdb_cpu_enter(ks, regs);
+		kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
+		return 0;
+	}
+#endif
+	return 1;
+}
+
+static void kgdb_console_write(struct console *co, const char *s,
+   unsigned count)
+{
+	unsigned long flags;
+
+	/* If we're debugging, or KGDB has not connected, don't try
+	 * and print. */
+	if (!kgdb_connected || atomic_read(&kgdb_active) != -1 || dbg_kdb_mode)
+		return;
+
+	local_irq_save(flags);
+	gdbstub_msg_write(s, count);
+	local_irq_restore(flags);
+}
+
+static struct console kgdbcons = {
+	.name		= "kgdb",
+	.write		= kgdb_console_write,
+	.flags		= CON_PRINTBUFFER | CON_ENABLED,
+	.index		= -1,
+};
+
+#ifdef CONFIG_MAGIC_SYSRQ
+static void sysrq_handle_dbg(int key, struct tty_struct *tty)
+{
+	if (!dbg_io_ops) {
+		printk(KERN_CRIT "ERROR: No KGDB I/O module available\n");
+		return;
+	}
+	if (!kgdb_connected) {
+#ifdef CONFIG_KGDB_KDB
+		if (!dbg_kdb_mode)
+			printk(KERN_CRIT "KGDB or $3#33 for KDB\n");
+#else
+		printk(KERN_CRIT "Entering KGDB\n");
+#endif
+	}
+
+	kgdb_breakpoint();
+}
+
+static struct sysrq_key_op sysrq_dbg_op = {
+	.handler	= sysrq_handle_dbg,
+	.help_msg	= "debug(G)",
+	.action_msg	= "DEBUG",
+};
+#endif
+
+static int kgdb_panic_event(struct notifier_block *self,
+			    unsigned long val,
+			    void *data)
+{
+	if (dbg_kdb_mode)
+		kdb_printf("PANIC: %s\n", (char *)data);
+	kgdb_breakpoint();
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block kgdb_panic_event_nb = {
+       .notifier_call	= kgdb_panic_event,
+       .priority	= INT_MAX,
+};
+
+void __weak kgdb_arch_late(void)
+{
+}
+
+void __init dbg_late_init(void)
+{
+	dbg_is_early = false;
+	if (kgdb_io_module_registered)
+		kgdb_arch_late();
+	kdb_init(KDB_INIT_FULL);
+}
+
+static void kgdb_register_callbacks(void)
+{
+	if (!kgdb_io_module_registered) {
+		kgdb_io_module_registered = 1;
+		kgdb_arch_init();
+		if (!dbg_is_early)
+			kgdb_arch_late();
+		atomic_notifier_chain_register(&panic_notifier_list,
+					       &kgdb_panic_event_nb);
+#ifdef CONFIG_MAGIC_SYSRQ
+		register_sysrq_key('g', &sysrq_dbg_op);
+#endif
+		if (kgdb_use_con && !kgdb_con_registered) {
+			register_console(&kgdbcons);
+			kgdb_con_registered = 1;
+		}
+	}
+}
+
+static void kgdb_unregister_callbacks(void)
+{
+	/*
+	 * When this routine is called KGDB should unregister from the
+	 * panic handler and clean up, making sure it is not handling any
+	 * break exceptions at the time.
+	 */
+	if (kgdb_io_module_registered) {
+		kgdb_io_module_registered = 0;
+		atomic_notifier_chain_unregister(&panic_notifier_list,
+					       &kgdb_panic_event_nb);
+		kgdb_arch_exit();
+#ifdef CONFIG_MAGIC_SYSRQ
+		unregister_sysrq_key('g', &sysrq_dbg_op);
+#endif
+		if (kgdb_con_registered) {
+			unregister_console(&kgdbcons);
+			kgdb_con_registered = 0;
+		}
+	}
+}
+
+/*
+ * There are times a tasklet needs to be used vs a compiled in
+ * break point so as to cause an exception outside a kgdb I/O module,
+ * such as is the case with kgdboe, where calling a breakpoint in the
+ * I/O driver itself would be fatal.
+ */
+static void kgdb_tasklet_bpt(unsigned long ing)
+{
+	kgdb_breakpoint();
+	atomic_set(&kgdb_break_tasklet_var, 0);
+}
+
+static DECLARE_TASKLET(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt, 0);
+
+void kgdb_schedule_breakpoint(void)
+{
+	if (atomic_read(&kgdb_break_tasklet_var) ||
+		atomic_read(&kgdb_active) != -1 ||
+		atomic_read(&kgdb_setting_breakpoint))
+		return;
+	atomic_inc(&kgdb_break_tasklet_var);
+	tasklet_schedule(&kgdb_tasklet_breakpoint);
+}
+EXPORT_SYMBOL_GPL(kgdb_schedule_breakpoint);
+
+static void kgdb_initial_breakpoint(void)
+{
+	kgdb_break_asap = 0;
+
+	printk(KERN_CRIT "kgdb: Waiting for connection from remote gdb...\n");
+	kgdb_breakpoint();
+}
+
+/**
+ *	kgdb_register_io_module - register KGDB IO module
+ *	@new_dbg_io_ops: the io ops vector
+ *
+ *	Register it with the KGDB core.
+ */
+int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
+{
+	int err;
+
+	spin_lock(&kgdb_registration_lock);
+
+	if (dbg_io_ops) {
+		spin_unlock(&kgdb_registration_lock);
+
+		printk(KERN_ERR "kgdb: Another I/O driver is already "
+				"registered with KGDB.\n");
+		return -EBUSY;
+	}
+
+	if (new_dbg_io_ops->init) {
+		err = new_dbg_io_ops->init();
+		if (err) {
+			spin_unlock(&kgdb_registration_lock);
+			return err;
+		}
+	}
+
+	dbg_io_ops = new_dbg_io_ops;
+
+	spin_unlock(&kgdb_registration_lock);
+
+	printk(KERN_INFO "kgdb: Registered I/O driver %s.\n",
+	       new_dbg_io_ops->name);
+
+	/* Arm KGDB now. */
+	kgdb_register_callbacks();
+
+	if (kgdb_break_asap)
+		kgdb_initial_breakpoint();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kgdb_register_io_module);
+
+/**
+ *	kkgdb_unregister_io_module - unregister KGDB IO module
+ *	@old_dbg_io_ops: the io ops vector
+ *
+ *	Unregister it with the KGDB core.
+ */
+void kgdb_unregister_io_module(struct kgdb_io *old_dbg_io_ops)
+{
+	BUG_ON(kgdb_connected);
+
+	/*
+	 * KGDB is no longer able to communicate out, so
+	 * unregister our callbacks and reset state.
+	 */
+	kgdb_unregister_callbacks();
+
+	spin_lock(&kgdb_registration_lock);
+
+	WARN_ON_ONCE(dbg_io_ops != old_dbg_io_ops);
+	dbg_io_ops = NULL;
+
+	spin_unlock(&kgdb_registration_lock);
+
+	printk(KERN_INFO
+		"kgdb: Unregistered I/O driver %s, debugger disabled.\n",
+		old_dbg_io_ops->name);
+}
+EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
+
+int dbg_io_get_char(void)
+{
+	int ret = dbg_io_ops->read_char();
+	if (ret == NO_POLL_CHAR)
+		return -1;
+	if (!dbg_kdb_mode)
+		return ret;
+	if (ret == 127)
+		return 8;
+	return ret;
+}
+
+/**
+ * kgdb_breakpoint - generate breakpoint exception
+ *
+ * This function will generate a breakpoint exception.  It is used at the
+ * beginning of a program to sync up with a debugger and can be used
+ * otherwise as a quick means to stop program execution and "break" into
+ * the debugger.
+ */
+void kgdb_breakpoint(void)
+{
+	atomic_inc(&kgdb_setting_breakpoint);
+	wmb(); /* Sync point before breakpoint */
+	arch_kgdb_breakpoint();
+	wmb(); /* Sync point after breakpoint */
+	atomic_dec(&kgdb_setting_breakpoint);
+}
+EXPORT_SYMBOL_GPL(kgdb_breakpoint);
+
+static int __init opt_kgdb_wait(char *str)
+{
+	kgdb_break_asap = 1;
+
+	kdb_init(KDB_INIT_EARLY);
+	if (kgdb_io_module_registered)
+		kgdb_initial_breakpoint();
+
+	return 0;
+}
+
+early_param("kgdbwait", opt_kgdb_wait);
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
new file mode 100644
index 00000000000..c5d753d80f6
--- /dev/null
+++ b/kernel/debug/debug_core.h
@@ -0,0 +1,81 @@
+/*
+ * Created by: Jason Wessel <jason.wessel@windriver.com>
+ *
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef _DEBUG_CORE_H_
+#define _DEBUG_CORE_H_
+/*
+ * These are the private implementation headers between the kernel
+ * debugger core and the debugger front end code.
+ */
+
+/* kernel debug core data structures */
+struct kgdb_state {
+	int			ex_vector;
+	int			signo;
+	int			err_code;
+	int			cpu;
+	int			pass_exception;
+	unsigned long		thr_query;
+	unsigned long		threadid;
+	long			kgdb_usethreadid;
+	struct pt_regs		*linux_regs;
+};
+
+/* Exception state values */
+#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
+#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
+#define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
+#define DCPU_SSTEP       0x8 /* CPU is single stepping */
+
+struct debuggerinfo_struct {
+	void			*debuggerinfo;
+	struct task_struct	*task;
+	int			exception_state;
+	int			ret_state;
+	int			irq_depth;
+};
+
+extern struct debuggerinfo_struct kgdb_info[];
+
+/* kernel debug core break point routines */
+extern int dbg_remove_all_break(void);
+extern int dbg_set_sw_break(unsigned long addr);
+extern int dbg_remove_sw_break(unsigned long addr);
+extern int dbg_activate_sw_breakpoints(void);
+extern int dbg_deactivate_sw_breakpoints(void);
+
+/* polled character access to i/o module */
+extern int dbg_io_get_char(void);
+
+/* stub return value for switching between the gdbstub and kdb */
+#define DBG_PASS_EVENT -12345
+/* Switch from one cpu to another */
+#define DBG_SWITCH_CPU_EVENT -123456
+extern int dbg_switch_cpu;
+
+/* gdbstub interface functions */
+extern int gdb_serial_stub(struct kgdb_state *ks);
+extern void gdbstub_msg_write(const char *s, int len);
+
+/* gdbstub functions used for kdb <-> gdbstub transition */
+extern int gdbstub_state(struct kgdb_state *ks, char *cmd);
+extern int dbg_kdb_mode;
+
+#ifdef CONFIG_KGDB_KDB
+extern int kdb_stub(struct kgdb_state *ks);
+extern int kdb_parse(const char *cmdstr);
+#else /* ! CONFIG_KGDB_KDB */
+static inline int kdb_stub(struct kgdb_state *ks)
+{
+	return DBG_PASS_EVENT;
+}
+#endif /* CONFIG_KGDB_KDB */
+
+#endif /* _DEBUG_CORE_H_ */
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
new file mode 100644
index 00000000000..4b17b326952
--- /dev/null
+++ b/kernel/debug/gdbstub.c
@@ -0,0 +1,1017 @@
+/*
+ * Kernel Debug Core
+ *
+ * Maintainer: Jason Wessel <jason.wessel@windriver.com>
+ *
+ * Copyright (C) 2000-2001 VERITAS Software Corporation.
+ * Copyright (C) 2002-2004 Timesys Corporation
+ * Copyright (C) 2003-2004 Amit S. Kale <amitkale@linsyssoft.com>
+ * Copyright (C) 2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2004-2006 Tom Rini <trini@kernel.crashing.org>
+ * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd.
+ * Copyright (C) 2005-2009 Wind River Systems, Inc.
+ * Copyright (C) 2007 MontaVista Software, Inc.
+ * Copyright (C) 2008 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * Contributors at various stages not listed above:
+ *  Jason Wessel ( jason.wessel@windriver.com )
+ *  George Anzinger <george@mvista.com>
+ *  Anurekh Saxena (anurekh.saxena@timesys.com)
+ *  Lake Stevens Instrument Division (Glenn Engel)
+ *  Jim Kingdon, Cygnus Support.
+ *
+ * Original KGDB stub: David Grothe <dave@gcom.com>,
+ * Tigran Aivazian <tigran@sco.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/reboot.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/unaligned.h>
+#include "debug_core.h"
+
+#define KGDB_MAX_THREAD_QUERY 17
+
+/* Our I/O buffers. */
+static char			remcom_in_buffer[BUFMAX];
+static char			remcom_out_buffer[BUFMAX];
+
+/* Storage for the registers, in GDB format. */
+static unsigned long		gdb_regs[(NUMREGBYTES +
+					sizeof(unsigned long) - 1) /
+					sizeof(unsigned long)];
+
+/*
+ * GDB remote protocol parser:
+ */
+
+static int hex(char ch)
+{
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	if ((ch >= 'A') && (ch <= 'F'))
+		return ch - 'A' + 10;
+	return -1;
+}
+
+#ifdef CONFIG_KGDB_KDB
+static int gdbstub_read_wait(void)
+{
+	int ret = -1;
+	int i;
+
+	/* poll any additional I/O interfaces that are defined */
+	while (ret < 0)
+		for (i = 0; kdb_poll_funcs[i] != NULL; i++) {
+			ret = kdb_poll_funcs[i]();
+			if (ret > 0)
+				break;
+		}
+	return ret;
+}
+#else
+static int gdbstub_read_wait(void)
+{
+	int ret = dbg_io_ops->read_char();
+	while (ret == NO_POLL_CHAR)
+		ret = dbg_io_ops->read_char();
+	return ret;
+}
+#endif
+/* scan for the sequence $<data>#<checksum> */
+static void get_packet(char *buffer)
+{
+	unsigned char checksum;
+	unsigned char xmitcsum;
+	int count;
+	char ch;
+
+	do {
+		/*
+		 * Spin and wait around for the start character, ignore all
+		 * other characters:
+		 */
+		while ((ch = (gdbstub_read_wait())) != '$')
+			/* nothing */;
+
+		kgdb_connected = 1;
+		checksum = 0;
+		xmitcsum = -1;
+
+		count = 0;
+
+		/*
+		 * now, read until a # or end of buffer is found:
+		 */
+		while (count < (BUFMAX - 1)) {
+			ch = gdbstub_read_wait();
+			if (ch == '#')
+				break;
+			checksum = checksum + ch;
+			buffer[count] = ch;
+			count = count + 1;
+		}
+		buffer[count] = 0;
+
+		if (ch == '#') {
+			xmitcsum = hex(gdbstub_read_wait()) << 4;
+			xmitcsum += hex(gdbstub_read_wait());
+
+			if (checksum != xmitcsum)
+				/* failed checksum */
+				dbg_io_ops->write_char('-');
+			else
+				/* successful transfer */
+				dbg_io_ops->write_char('+');
+			if (dbg_io_ops->flush)
+				dbg_io_ops->flush();
+		}
+	} while (checksum != xmitcsum);
+}
+
+/*
+ * Send the packet in buffer.
+ * Check for gdb connection if asked for.
+ */
+static void put_packet(char *buffer)
+{
+	unsigned char checksum;
+	int count;
+	char ch;
+
+	/*
+	 * $<packet info>#<checksum>.
+	 */
+	while (1) {
+		dbg_io_ops->write_char('$');
+		checksum = 0;
+		count = 0;
+
+		while ((ch = buffer[count])) {
+			dbg_io_ops->write_char(ch);
+			checksum += ch;
+			count++;
+		}
+
+		dbg_io_ops->write_char('#');
+		dbg_io_ops->write_char(hex_asc_hi(checksum));
+		dbg_io_ops->write_char(hex_asc_lo(checksum));
+		if (dbg_io_ops->flush)
+			dbg_io_ops->flush();
+
+		/* Now see what we get in reply. */
+		ch = gdbstub_read_wait();
+
+		if (ch == 3)
+			ch = gdbstub_read_wait();
+
+		/* If we get an ACK, we are done. */
+		if (ch == '+')
+			return;
+
+		/*
+		 * If we get the start of another packet, this means
+		 * that GDB is attempting to reconnect.  We will NAK
+		 * the packet being sent, and stop trying to send this
+		 * packet.
+		 */
+		if (ch == '$') {
+			dbg_io_ops->write_char('-');
+			if (dbg_io_ops->flush)
+				dbg_io_ops->flush();
+			return;
+		}
+	}
+}
+
+static char gdbmsgbuf[BUFMAX + 1];
+
+void gdbstub_msg_write(const char *s, int len)
+{
+	char *bufptr;
+	int wcount;
+	int i;
+
+	if (len == 0)
+		len = strlen(s);
+
+	/* 'O'utput */
+	gdbmsgbuf[0] = 'O';
+
+	/* Fill and send buffers... */
+	while (len > 0) {
+		bufptr = gdbmsgbuf + 1;
+
+		/* Calculate how many this time */
+		if ((len << 1) > (BUFMAX - 2))
+			wcount = (BUFMAX - 2) >> 1;
+		else
+			wcount = len;
+
+		/* Pack in hex chars */
+		for (i = 0; i < wcount; i++)
+			bufptr = pack_hex_byte(bufptr, s[i]);
+		*bufptr = '\0';
+
+		/* Move up */
+		s += wcount;
+		len -= wcount;
+
+		/* Write packet */
+		put_packet(gdbmsgbuf);
+	}
+}
+
+/*
+ * Convert the memory pointed to by mem into hex, placing result in
+ * buf.  Return a pointer to the last char put in buf (null). May
+ * return an error.
+ */
+int kgdb_mem2hex(char *mem, char *buf, int count)
+{
+	char *tmp;
+	int err;
+
+	/*
+	 * We use the upper half of buf as an intermediate buffer for the
+	 * raw memory copy.  Hex conversion will work against this one.
+	 */
+	tmp = buf + count;
+
+	err = probe_kernel_read(tmp, mem, count);
+	if (!err) {
+		while (count > 0) {
+			buf = pack_hex_byte(buf, *tmp);
+			tmp++;
+			count--;
+		}
+
+		*buf = 0;
+	}
+
+	return err;
+}
+
+/*
+ * Convert the hex array pointed to by buf into binary to be placed in
+ * mem.  Return a pointer to the character AFTER the last byte
+ * written.  May return an error.
+ */
+int kgdb_hex2mem(char *buf, char *mem, int count)
+{
+	char *tmp_raw;
+	char *tmp_hex;
+
+	/*
+	 * We use the upper half of buf as an intermediate buffer for the
+	 * raw memory that is converted from hex.
+	 */
+	tmp_raw = buf + count * 2;
+
+	tmp_hex = tmp_raw - 1;
+	while (tmp_hex >= buf) {
+		tmp_raw--;
+		*tmp_raw = hex(*tmp_hex--);
+		*tmp_raw |= hex(*tmp_hex--) << 4;
+	}
+
+	return probe_kernel_write(mem, tmp_raw, count);
+}
+
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int kgdb_hex2long(char **ptr, unsigned long *long_val)
+{
+	int hex_val;
+	int num = 0;
+	int negate = 0;
+
+	*long_val = 0;
+
+	if (**ptr == '-') {
+		negate = 1;
+		(*ptr)++;
+	}
+	while (**ptr) {
+		hex_val = hex(**ptr);
+		if (hex_val < 0)
+			break;
+
+		*long_val = (*long_val << 4) | hex_val;
+		num++;
+		(*ptr)++;
+	}
+
+	if (negate)
+		*long_val = -*long_val;
+
+	return num;
+}
+
+/*
+ * Copy the binary array pointed to by buf into mem.  Fix $, #, and
+ * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success.
+ * The input buf is overwitten with the result to write to mem.
+ */
+static int kgdb_ebin2mem(char *buf, char *mem, int count)
+{
+	int size = 0;
+	char *c = buf;
+
+	while (count-- > 0) {
+		c[size] = *buf++;
+		if (c[size] == 0x7d)
+			c[size] = *buf++ ^ 0x20;
+		size++;
+	}
+
+	return probe_kernel_write(mem, c, size);
+}
+
+/* Write memory due to an 'M' or 'X' packet. */
+static int write_mem_msg(int binary)
+{
+	char *ptr = &remcom_in_buffer[1];
+	unsigned long addr;
+	unsigned long length;
+	int err;
+
+	if (kgdb_hex2long(&ptr, &addr) > 0 && *(ptr++) == ',' &&
+	    kgdb_hex2long(&ptr, &length) > 0 && *(ptr++) == ':') {
+		if (binary)
+			err = kgdb_ebin2mem(ptr, (char *)addr, length);
+		else
+			err = kgdb_hex2mem(ptr, (char *)addr, length);
+		if (err)
+			return err;
+		if (CACHE_FLUSH_IS_SAFE)
+			flush_icache_range(addr, addr + length);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void error_packet(char *pkt, int error)
+{
+	error = -error;
+	pkt[0] = 'E';
+	pkt[1] = hex_asc[(error / 10)];
+	pkt[2] = hex_asc[(error % 10)];
+	pkt[3] = '\0';
+}
+
+/*
+ * Thread ID accessors. We represent a flat TID space to GDB, where
+ * the per CPU idle threads (which under Linux all have PID 0) are
+ * remapped to negative TIDs.
+ */
+
+#define BUF_THREAD_ID_SIZE	16
+
+static char *pack_threadid(char *pkt, unsigned char *id)
+{
+	char *limit;
+
+	limit = pkt + BUF_THREAD_ID_SIZE;
+	while (pkt < limit)
+		pkt = pack_hex_byte(pkt, *id++);
+
+	return pkt;
+}
+
+static void int_to_threadref(unsigned char *id, int value)
+{
+	unsigned char *scan;
+	int i = 4;
+
+	scan = (unsigned char *)id;
+	while (i--)
+		*scan++ = 0;
+	put_unaligned_be32(value, scan);
+}
+
+static struct task_struct *getthread(struct pt_regs *regs, int tid)
+{
+	/*
+	 * Non-positive TIDs are remapped to the cpu shadow information
+	 */
+	if (tid == 0 || tid == -1)
+		tid = -atomic_read(&kgdb_active) - 2;
+	if (tid < -1 && tid > -NR_CPUS - 2) {
+		if (kgdb_info[-tid - 2].task)
+			return kgdb_info[-tid - 2].task;
+		else
+			return idle_task(-tid - 2);
+	}
+	if (tid <= 0) {
+		printk(KERN_ERR "KGDB: Internal thread select error\n");
+		dump_stack();
+		return NULL;
+	}
+
+	/*
+	 * find_task_by_pid_ns() does not take the tasklist lock anymore
+	 * but is nicely RCU locked - hence is a pretty resilient
+	 * thing to use:
+	 */
+	return find_task_by_pid_ns(tid, &init_pid_ns);
+}
+
+
+/*
+ * Remap normal tasks to their real PID,
+ * CPU shadow threads are mapped to -CPU - 2
+ */
+static inline int shadow_pid(int realpid)
+{
+	if (realpid)
+		return realpid;
+
+	return -raw_smp_processor_id() - 2;
+}
+
+/*
+ * All the functions that start with gdb_cmd are the various
+ * operations to implement the handlers for the gdbserial protocol
+ * where KGDB is communicating with an external debugger
+ */
+
+/* Handle the '?' status packets */
+static void gdb_cmd_status(struct kgdb_state *ks)
+{
+	/*
+	 * We know that this packet is only sent
+	 * during initial connect.  So to be safe,
+	 * we clear out our breakpoints now in case
+	 * GDB is reconnecting.
+	 */
+	dbg_remove_all_break();
+
+	remcom_out_buffer[0] = 'S';
+	pack_hex_byte(&remcom_out_buffer[1], ks->signo);
+}
+
+/* Handle the 'g' get registers request */
+static void gdb_cmd_getregs(struct kgdb_state *ks)
+{
+	struct task_struct *thread;
+	void *local_debuggerinfo;
+	int i;
+
+	thread = kgdb_usethread;
+	if (!thread) {
+		thread = kgdb_info[ks->cpu].task;
+		local_debuggerinfo = kgdb_info[ks->cpu].debuggerinfo;
+	} else {
+		local_debuggerinfo = NULL;
+		for_each_online_cpu(i) {
+			/*
+			 * Try to find the task on some other
+			 * or possibly this node if we do not
+			 * find the matching task then we try
+			 * to approximate the results.
+			 */
+			if (thread == kgdb_info[i].task)
+				local_debuggerinfo = kgdb_info[i].debuggerinfo;
+		}
+	}
+
+	/*
+	 * All threads that don't have debuggerinfo should be
+	 * in schedule() sleeping, since all other CPUs
+	 * are in kgdb_wait, and thus have debuggerinfo.
+	 */
+	if (local_debuggerinfo) {
+		pt_regs_to_gdb_regs(gdb_regs, local_debuggerinfo);
+	} else {
+		/*
+		 * Pull stuff saved during switch_to; nothing
+		 * else is accessible (or even particularly
+		 * relevant).
+		 *
+		 * This should be enough for a stack trace.
+		 */
+		sleeping_thread_to_gdb_regs(gdb_regs, thread);
+	}
+	kgdb_mem2hex((char *)gdb_regs, remcom_out_buffer, NUMREGBYTES);
+}
+
+/* Handle the 'G' set registers request */
+static void gdb_cmd_setregs(struct kgdb_state *ks)
+{
+	kgdb_hex2mem(&remcom_in_buffer[1], (char *)gdb_regs, NUMREGBYTES);
+
+	if (kgdb_usethread && kgdb_usethread != current) {
+		error_packet(remcom_out_buffer, -EINVAL);
+	} else {
+		gdb_regs_to_pt_regs(gdb_regs, ks->linux_regs);
+		strcpy(remcom_out_buffer, "OK");
+	}
+}
+
+/* Handle the 'm' memory read bytes */
+static void gdb_cmd_memread(struct kgdb_state *ks)
+{
+	char *ptr = &remcom_in_buffer[1];
+	unsigned long length;
+	unsigned long addr;
+	int err;
+
+	if (kgdb_hex2long(&ptr, &addr) > 0 && *ptr++ == ',' &&
+					kgdb_hex2long(&ptr, &length) > 0) {
+		err = kgdb_mem2hex((char *)addr, remcom_out_buffer, length);
+		if (err)
+			error_packet(remcom_out_buffer, err);
+	} else {
+		error_packet(remcom_out_buffer, -EINVAL);
+	}
+}
+
+/* Handle the 'M' memory write bytes */
+static void gdb_cmd_memwrite(struct kgdb_state *ks)
+{
+	int err = write_mem_msg(0);
+
+	if (err)
+		error_packet(remcom_out_buffer, err);
+	else
+		strcpy(remcom_out_buffer, "OK");
+}
+
+/* Handle the 'X' memory binary write bytes */
+static void gdb_cmd_binwrite(struct kgdb_state *ks)
+{
+	int err = write_mem_msg(1);
+
+	if (err)
+		error_packet(remcom_out_buffer, err);
+	else
+		strcpy(remcom_out_buffer, "OK");
+}
+
+/* Handle the 'D' or 'k', detach or kill packets */
+static void gdb_cmd_detachkill(struct kgdb_state *ks)
+{
+	int error;
+
+	/* The detach case */
+	if (remcom_in_buffer[0] == 'D') {
+		error = dbg_remove_all_break();
+		if (error < 0) {
+			error_packet(remcom_out_buffer, error);
+		} else {
+			strcpy(remcom_out_buffer, "OK");
+			kgdb_connected = 0;
+		}
+		put_packet(remcom_out_buffer);
+	} else {
+		/*
+		 * Assume the kill case, with no exit code checking,
+		 * trying to force detach the debugger:
+		 */
+		dbg_remove_all_break();
+		kgdb_connected = 0;
+	}
+}
+
+/* Handle the 'R' reboot packets */
+static int gdb_cmd_reboot(struct kgdb_state *ks)
+{
+	/* For now, only honor R0 */
+	if (strcmp(remcom_in_buffer, "R0") == 0) {
+		printk(KERN_CRIT "Executing emergency reboot\n");
+		strcpy(remcom_out_buffer, "OK");
+		put_packet(remcom_out_buffer);
+
+		/*
+		 * Execution should not return from
+		 * machine_emergency_restart()
+		 */
+		machine_emergency_restart();
+		kgdb_connected = 0;
+
+		return 1;
+	}
+	return 0;
+}
+
+/* Handle the 'q' query packets */
+static void gdb_cmd_query(struct kgdb_state *ks)
+{
+	struct task_struct *g;
+	struct task_struct *p;
+	unsigned char thref[8];
+	char *ptr;
+	int i;
+	int cpu;
+	int finished = 0;
+
+	switch (remcom_in_buffer[1]) {
+	case 's':
+	case 'f':
+		if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10)) {
+			error_packet(remcom_out_buffer, -EINVAL);
+			break;
+		}
+
+		i = 0;
+		remcom_out_buffer[0] = 'm';
+		ptr = remcom_out_buffer + 1;
+		if (remcom_in_buffer[1] == 'f') {
+			/* Each cpu is a shadow thread */
+			for_each_online_cpu(cpu) {
+				ks->thr_query = 0;
+				int_to_threadref(thref, -cpu - 2);
+				pack_threadid(ptr, thref);
+				ptr += BUF_THREAD_ID_SIZE;
+				*(ptr++) = ',';
+				i++;
+			}
+		}
+
+		do_each_thread(g, p) {
+			if (i >= ks->thr_query && !finished) {
+				int_to_threadref(thref, p->pid);
+				pack_threadid(ptr, thref);
+				ptr += BUF_THREAD_ID_SIZE;
+				*(ptr++) = ',';
+				ks->thr_query++;
+				if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0)
+					finished = 1;
+			}
+			i++;
+		} while_each_thread(g, p);
+
+		*(--ptr) = '\0';
+		break;
+
+	case 'C':
+		/* Current thread id */
+		strcpy(remcom_out_buffer, "QC");
+		ks->threadid = shadow_pid(current->pid);
+		int_to_threadref(thref, ks->threadid);
+		pack_threadid(remcom_out_buffer + 2, thref);
+		break;
+	case 'T':
+		if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16)) {
+			error_packet(remcom_out_buffer, -EINVAL);
+			break;
+		}
+		ks->threadid = 0;
+		ptr = remcom_in_buffer + 17;
+		kgdb_hex2long(&ptr, &ks->threadid);
+		if (!getthread(ks->linux_regs, ks->threadid)) {
+			error_packet(remcom_out_buffer, -EINVAL);
+			break;
+		}
+		if ((int)ks->threadid > 0) {
+			kgdb_mem2hex(getthread(ks->linux_regs,
+					ks->threadid)->comm,
+					remcom_out_buffer, 16);
+		} else {
+			static char tmpstr[23 + BUF_THREAD_ID_SIZE];
+
+			sprintf(tmpstr, "shadowCPU%d",
+					(int)(-ks->threadid - 2));
+			kgdb_mem2hex(tmpstr, remcom_out_buffer, strlen(tmpstr));
+		}
+		break;
+#ifdef CONFIG_KGDB_KDB
+	case 'R':
+		if (strncmp(remcom_in_buffer, "qRcmd,", 6) == 0) {
+			int len = strlen(remcom_in_buffer + 6);
+
+			if ((len % 2) != 0) {
+				strcpy(remcom_out_buffer, "E01");
+				break;
+			}
+			kgdb_hex2mem(remcom_in_buffer + 6,
+				     remcom_out_buffer, len);
+			len = len / 2;
+			remcom_out_buffer[len++] = 0;
+
+			kdb_parse(remcom_out_buffer);
+			strcpy(remcom_out_buffer, "OK");
+		}
+		break;
+#endif
+	}
+}
+
+/* Handle the 'H' task query packets */
+static void gdb_cmd_task(struct kgdb_state *ks)
+{
+	struct task_struct *thread;
+	char *ptr;
+
+	switch (remcom_in_buffer[1]) {
+	case 'g':
+		ptr = &remcom_in_buffer[2];
+		kgdb_hex2long(&ptr, &ks->threadid);
+		thread = getthread(ks->linux_regs, ks->threadid);
+		if (!thread && ks->threadid > 0) {
+			error_packet(remcom_out_buffer, -EINVAL);
+			break;
+		}
+		kgdb_usethread = thread;
+		ks->kgdb_usethreadid = ks->threadid;
+		strcpy(remcom_out_buffer, "OK");
+		break;
+	case 'c':
+		ptr = &remcom_in_buffer[2];
+		kgdb_hex2long(&ptr, &ks->threadid);
+		if (!ks->threadid) {
+			kgdb_contthread = NULL;
+		} else {
+			thread = getthread(ks->linux_regs, ks->threadid);
+			if (!thread && ks->threadid > 0) {
+				error_packet(remcom_out_buffer, -EINVAL);
+				break;
+			}
+			kgdb_contthread = thread;
+		}
+		strcpy(remcom_out_buffer, "OK");
+		break;
+	}
+}
+
+/* Handle the 'T' thread query packets */
+static void gdb_cmd_thread(struct kgdb_state *ks)
+{
+	char *ptr = &remcom_in_buffer[1];
+	struct task_struct *thread;
+
+	kgdb_hex2long(&ptr, &ks->threadid);
+	thread = getthread(ks->linux_regs, ks->threadid);
+	if (thread)
+		strcpy(remcom_out_buffer, "OK");
+	else
+		error_packet(remcom_out_buffer, -EINVAL);
+}
+
+/* Handle the 'z' or 'Z' breakpoint remove or set packets */
+static void gdb_cmd_break(struct kgdb_state *ks)
+{
+	/*
+	 * Since GDB-5.3, it's been drafted that '0' is a software
+	 * breakpoint, '1' is a hardware breakpoint, so let's do that.
+	 */
+	char *bpt_type = &remcom_in_buffer[1];
+	char *ptr = &remcom_in_buffer[2];
+	unsigned long addr;
+	unsigned long length;
+	int error = 0;
+
+	if (arch_kgdb_ops.set_hw_breakpoint && *bpt_type >= '1') {
+		/* Unsupported */
+		if (*bpt_type > '4')
+			return;
+	} else {
+		if (*bpt_type != '0' && *bpt_type != '1')
+			/* Unsupported. */
+			return;
+	}
+
+	/*
+	 * Test if this is a hardware breakpoint, and
+	 * if we support it:
+	 */
+	if (*bpt_type == '1' && !(arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT))
+		/* Unsupported. */
+		return;
+
+	if (*(ptr++) != ',') {
+		error_packet(remcom_out_buffer, -EINVAL);
+		return;
+	}
+	if (!kgdb_hex2long(&ptr, &addr)) {
+		error_packet(remcom_out_buffer, -EINVAL);
+		return;
+	}
+	if (*(ptr++) != ',' ||
+		!kgdb_hex2long(&ptr, &length)) {
+		error_packet(remcom_out_buffer, -EINVAL);
+		return;
+	}
+
+	if (remcom_in_buffer[0] == 'Z' && *bpt_type == '0')
+		error = dbg_set_sw_break(addr);
+	else if (remcom_in_buffer[0] == 'z' && *bpt_type == '0')
+		error = dbg_remove_sw_break(addr);
+	else if (remcom_in_buffer[0] == 'Z')
+		error = arch_kgdb_ops.set_hw_breakpoint(addr,
+			(int)length, *bpt_type - '0');
+	else if (remcom_in_buffer[0] == 'z')
+		error = arch_kgdb_ops.remove_hw_breakpoint(addr,
+			(int) length, *bpt_type - '0');
+
+	if (error == 0)
+		strcpy(remcom_out_buffer, "OK");
+	else
+		error_packet(remcom_out_buffer, error);
+}
+
+/* Handle the 'C' signal / exception passing packets */
+static int gdb_cmd_exception_pass(struct kgdb_state *ks)
+{
+	/* C09 == pass exception
+	 * C15 == detach kgdb, pass exception
+	 */
+	if (remcom_in_buffer[1] == '0' && remcom_in_buffer[2] == '9') {
+
+		ks->pass_exception = 1;
+		remcom_in_buffer[0] = 'c';
+
+	} else if (remcom_in_buffer[1] == '1' && remcom_in_buffer[2] == '5') {
+
+		ks->pass_exception = 1;
+		remcom_in_buffer[0] = 'D';
+		dbg_remove_all_break();
+		kgdb_connected = 0;
+		return 1;
+
+	} else {
+		gdbstub_msg_write("KGDB only knows signal 9 (pass)"
+			" and 15 (pass and disconnect)\n"
+			"Executing a continue without signal passing\n", 0);
+		remcom_in_buffer[0] = 'c';
+	}
+
+	/* Indicate fall through */
+	return -1;
+}
+
+/*
+ * This function performs all gdbserial command procesing
+ */
+int gdb_serial_stub(struct kgdb_state *ks)
+{
+	int error = 0;
+	int tmp;
+
+	/* Clear the out buffer. */
+	memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer));
+
+	if (kgdb_connected) {
+		unsigned char thref[8];
+		char *ptr;
+
+		/* Reply to host that an exception has occurred */
+		ptr = remcom_out_buffer;
+		*ptr++ = 'T';
+		ptr = pack_hex_byte(ptr, ks->signo);
+		ptr += strlen(strcpy(ptr, "thread:"));
+		int_to_threadref(thref, shadow_pid(current->pid));
+		ptr = pack_threadid(ptr, thref);
+		*ptr++ = ';';
+		put_packet(remcom_out_buffer);
+	}
+
+	kgdb_usethread = kgdb_info[ks->cpu].task;
+	ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid);
+	ks->pass_exception = 0;
+
+	while (1) {
+		error = 0;
+
+		/* Clear the out buffer. */
+		memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer));
+
+		get_packet(remcom_in_buffer);
+
+		switch (remcom_in_buffer[0]) {
+		case '?': /* gdbserial status */
+			gdb_cmd_status(ks);
+			break;
+		case 'g': /* return the value of the CPU registers */
+			gdb_cmd_getregs(ks);
+			break;
+		case 'G': /* set the value of the CPU registers - return OK */
+			gdb_cmd_setregs(ks);
+			break;
+		case 'm': /* mAA..AA,LLLL  Read LLLL bytes at address AA..AA */
+			gdb_cmd_memread(ks);
+			break;
+		case 'M': /* MAA..AA,LLLL: Write LLLL bytes at address AA..AA */
+			gdb_cmd_memwrite(ks);
+			break;
+		case 'X': /* XAA..AA,LLLL: Write LLLL bytes at address AA..AA */
+			gdb_cmd_binwrite(ks);
+			break;
+			/* kill or detach. KGDB should treat this like a
+			 * continue.
+			 */
+		case 'D': /* Debugger detach */
+		case 'k': /* Debugger detach via kill */
+			gdb_cmd_detachkill(ks);
+			goto default_handle;
+		case 'R': /* Reboot */
+			if (gdb_cmd_reboot(ks))
+				goto default_handle;
+			break;
+		case 'q': /* query command */
+			gdb_cmd_query(ks);
+			break;
+		case 'H': /* task related */
+			gdb_cmd_task(ks);
+			break;
+		case 'T': /* Query thread status */
+			gdb_cmd_thread(ks);
+			break;
+		case 'z': /* Break point remove */
+		case 'Z': /* Break point set */
+			gdb_cmd_break(ks);
+			break;
+#ifdef CONFIG_KGDB_KDB
+		case '3': /* Escape into back into kdb */
+			if (remcom_in_buffer[1] == '\0') {
+				gdb_cmd_detachkill(ks);
+				return DBG_PASS_EVENT;
+			}
+#endif
+		case 'C': /* Exception passing */
+			tmp = gdb_cmd_exception_pass(ks);
+			if (tmp > 0)
+				goto default_handle;
+			if (tmp == 0)
+				break;
+			/* Fall through on tmp < 0 */
+		case 'c': /* Continue packet */
+		case 's': /* Single step packet */
+			if (kgdb_contthread && kgdb_contthread != current) {
+				/* Can't switch threads in kgdb */
+				error_packet(remcom_out_buffer, -EINVAL);
+				break;
+			}
+			dbg_activate_sw_breakpoints();
+			/* Fall through to default processing */
+		default:
+default_handle:
+			error = kgdb_arch_handle_exception(ks->ex_vector,
+						ks->signo,
+						ks->err_code,
+						remcom_in_buffer,
+						remcom_out_buffer,
+						ks->linux_regs);
+			/*
+			 * Leave cmd processing on error, detach,
+			 * kill, continue, or single step.
+			 */
+			if (error >= 0 || remcom_in_buffer[0] == 'D' ||
+			    remcom_in_buffer[0] == 'k') {
+				error = 0;
+				goto kgdb_exit;
+			}
+
+		}
+
+		/* reply to the request */
+		put_packet(remcom_out_buffer);
+	}
+
+kgdb_exit:
+	if (ks->pass_exception)
+		error = 1;
+	return error;
+}
+
+int gdbstub_state(struct kgdb_state *ks, char *cmd)
+{
+	int error;
+
+	switch (cmd[0]) {
+	case 'e':
+		error = kgdb_arch_handle_exception(ks->ex_vector,
+						   ks->signo,
+						   ks->err_code,
+						   remcom_in_buffer,
+						   remcom_out_buffer,
+						   ks->linux_regs);
+		return error;
+	case 's':
+	case 'c':
+		strcpy(remcom_in_buffer, cmd);
+		return 0;
+	case '?':
+		gdb_cmd_status(ks);
+		break;
+	case '\0':
+		strcpy(remcom_out_buffer, "");
+		break;
+	}
+	dbg_io_ops->write_char('+');
+	put_packet(remcom_out_buffer);
+	return 0;
+}
diff --git a/kernel/debug/kdb/.gitignore b/kernel/debug/kdb/.gitignore
new file mode 100644
index 00000000000..396d12eda9e
--- /dev/null
+++ b/kernel/debug/kdb/.gitignore
@@ -0,0 +1 @@
+gen-kdb_cmds.c
diff --git a/kernel/debug/kdb/Makefile b/kernel/debug/kdb/Makefile
new file mode 100644
index 00000000000..d4fc58f4b88
--- /dev/null
+++ b/kernel/debug/kdb/Makefile
@@ -0,0 +1,25 @@
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (c) 1999-2004 Silicon Graphics, Inc.  All Rights Reserved.
+# Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved.
+#
+
+CCVERSION	:= $(shell $(CC) -v 2>&1 | sed -ne '$$p')
+obj-y := kdb_io.o kdb_main.o kdb_support.o kdb_bt.o gen-kdb_cmds.o kdb_bp.o kdb_debugger.o
+obj-$(CONFIG_KDB_KEYBOARD)    += kdb_keyboard.o
+
+clean-files := gen-kdb_cmds.c
+
+quiet_cmd_gen-kdb = GENKDB  $@
+      cmd_gen-kdb = $(AWK) 'BEGIN {print "\#include <linux/stddef.h>"; print "\#include <linux/init.h>"} \
+		/^\#/{next} \
+		/^[ \t]*$$/{next} \
+		{gsub(/"/, "\\\"", $$0); \
+		  print "static __initdata char kdb_cmd" cmds++ "[] = \"" $$0 "\\n\";"} \
+		END {print "extern char *kdb_cmds[]; char __initdata *kdb_cmds[] = {"; for (i = 0; i < cmds; ++i) {print "  kdb_cmd" i ","}; print("  NULL\n};");}' \
+		$(filter-out %/Makefile,$^) > $@#
+
+$(obj)/gen-kdb_cmds.c:	$(src)/kdb_cmds $(src)/Makefile
+	$(call cmd,gen-kdb)
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
new file mode 100644
index 00000000000..75bd9b3ebbb
--- /dev/null
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -0,0 +1,564 @@
+/*
+ * Kernel Debugger Architecture Independent Breakpoint Handler
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1999-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ */
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/kdb.h>
+#include <linux/kgdb.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include "kdb_private.h"
+
+/*
+ * Table of kdb_breakpoints
+ */
+kdb_bp_t kdb_breakpoints[KDB_MAXBPT];
+
+static void kdb_setsinglestep(struct pt_regs *regs)
+{
+	KDB_STATE_SET(DOING_SS);
+}
+
+static char *kdb_rwtypes[] = {
+	"Instruction(i)",
+	"Instruction(Register)",
+	"Data Write",
+	"I/O",
+	"Data Access"
+};
+
+static char *kdb_bptype(kdb_bp_t *bp)
+{
+	if (bp->bp_type < 0 || bp->bp_type > 4)
+		return "";
+
+	return kdb_rwtypes[bp->bp_type];
+}
+
+static int kdb_parsebp(int argc, const char **argv, int *nextargp, kdb_bp_t *bp)
+{
+	int nextarg = *nextargp;
+	int diag;
+
+	bp->bph_length = 1;
+	if ((argc + 1) != nextarg) {
+		if (strnicmp(argv[nextarg], "datar", sizeof("datar")) == 0)
+			bp->bp_type = BP_ACCESS_WATCHPOINT;
+		else if (strnicmp(argv[nextarg], "dataw", sizeof("dataw")) == 0)
+			bp->bp_type = BP_WRITE_WATCHPOINT;
+		else if (strnicmp(argv[nextarg], "inst", sizeof("inst")) == 0)
+			bp->bp_type = BP_HARDWARE_BREAKPOINT;
+		else
+			return KDB_ARGCOUNT;
+
+		bp->bph_length = 1;
+
+		nextarg++;
+
+		if ((argc + 1) != nextarg) {
+			unsigned long len;
+
+			diag = kdbgetularg((char *)argv[nextarg],
+					   &len);
+			if (diag)
+				return diag;
+
+
+			if (len > 8)
+				return KDB_BADLENGTH;
+
+			bp->bph_length = len;
+			nextarg++;
+		}
+
+		if ((argc + 1) != nextarg)
+			return KDB_ARGCOUNT;
+	}
+
+	*nextargp = nextarg;
+	return 0;
+}
+
+static int _kdb_bp_remove(kdb_bp_t *bp)
+{
+	int ret = 1;
+	if (!bp->bp_installed)
+		return ret;
+	if (!bp->bp_type)
+		ret = dbg_remove_sw_break(bp->bp_addr);
+	else
+		ret = arch_kgdb_ops.remove_hw_breakpoint(bp->bp_addr,
+			 bp->bph_length,
+			 bp->bp_type);
+	if (ret == 0)
+		bp->bp_installed = 0;
+	return ret;
+}
+
+static void kdb_handle_bp(struct pt_regs *regs, kdb_bp_t *bp)
+{
+	if (KDB_DEBUG(BP))
+		kdb_printf("regs->ip = 0x%lx\n", instruction_pointer(regs));
+
+	/*
+	 * Setup single step
+	 */
+	kdb_setsinglestep(regs);
+
+	/*
+	 * Reset delay attribute
+	 */
+	bp->bp_delay = 0;
+	bp->bp_delayed = 1;
+}
+
+static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp)
+{
+	int ret;
+	/*
+	 * Install the breakpoint, if it is not already installed.
+	 */
+
+	if (KDB_DEBUG(BP))
+		kdb_printf("%s: bp_installed %d\n",
+			   __func__, bp->bp_installed);
+	if (!KDB_STATE(SSBPT))
+		bp->bp_delay = 0;
+	if (bp->bp_installed)
+		return 1;
+	if (bp->bp_delay || (bp->bp_delayed && KDB_STATE(DOING_SS))) {
+		if (KDB_DEBUG(BP))
+			kdb_printf("%s: delayed bp\n", __func__);
+		kdb_handle_bp(regs, bp);
+		return 0;
+	}
+	if (!bp->bp_type)
+		ret = dbg_set_sw_break(bp->bp_addr);
+	else
+		ret = arch_kgdb_ops.set_hw_breakpoint(bp->bp_addr,
+			 bp->bph_length,
+			 bp->bp_type);
+	if (ret == 0) {
+		bp->bp_installed = 1;
+	} else {
+		kdb_printf("%s: failed to set breakpoint at 0x%lx\n",
+			   __func__, bp->bp_addr);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * kdb_bp_install
+ *
+ *	Install kdb_breakpoints prior to returning from the
+ *	kernel debugger.  This allows the kdb_breakpoints to be set
+ *	upon functions that are used internally by kdb, such as
+ *	printk().  This function is only called once per kdb session.
+ */
+void kdb_bp_install(struct pt_regs *regs)
+{
+	int i;
+
+	for (i = 0; i < KDB_MAXBPT; i++) {
+		kdb_bp_t *bp = &kdb_breakpoints[i];
+
+		if (KDB_DEBUG(BP)) {
+			kdb_printf("%s: bp %d bp_enabled %d\n",
+				   __func__, i, bp->bp_enabled);
+		}
+		if (bp->bp_enabled)
+			_kdb_bp_install(regs, bp);
+	}
+}
+
+/*
+ * kdb_bp_remove
+ *
+ *	Remove kdb_breakpoints upon entry to the kernel debugger.
+ *
+ * Parameters:
+ *	None.
+ * Outputs:
+ *	None.
+ * Returns:
+ *	None.
+ * Locking:
+ *	None.
+ * Remarks:
+ */
+void kdb_bp_remove(void)
+{
+	int i;
+
+	for (i = KDB_MAXBPT - 1; i >= 0; i--) {
+		kdb_bp_t *bp = &kdb_breakpoints[i];
+
+		if (KDB_DEBUG(BP)) {
+			kdb_printf("%s: bp %d bp_enabled %d\n",
+				   __func__, i, bp->bp_enabled);
+		}
+		if (bp->bp_enabled)
+			_kdb_bp_remove(bp);
+	}
+}
+
+
+/*
+ * kdb_printbp
+ *
+ *	Internal function to format and print a breakpoint entry.
+ *
+ * Parameters:
+ *	None.
+ * Outputs:
+ *	None.
+ * Returns:
+ *	None.
+ * Locking:
+ *	None.
+ * Remarks:
+ */
+
+static void kdb_printbp(kdb_bp_t *bp, int i)
+{
+	kdb_printf("%s ", kdb_bptype(bp));
+	kdb_printf("BP #%d at ", i);
+	kdb_symbol_print(bp->bp_addr, NULL, KDB_SP_DEFAULT);
+
+	if (bp->bp_enabled)
+		kdb_printf("\n    is enabled");
+	else
+		kdb_printf("\n    is disabled");
+
+	kdb_printf("\taddr at %016lx, hardtype=%d installed=%d\n",
+		   bp->bp_addr, bp->bp_type, bp->bp_installed);
+
+	kdb_printf("\n");
+}
+
+/*
+ * kdb_bp
+ *
+ *	Handle the bp commands.
+ *
+ *	[bp|bph] <addr-expression> [DATAR|DATAW]
+ *
+ * Parameters:
+ *	argc	Count of arguments in argv
+ *	argv	Space delimited command line arguments
+ * Outputs:
+ *	None.
+ * Returns:
+ *	Zero for success, a kdb diagnostic if failure.
+ * Locking:
+ *	None.
+ * Remarks:
+ *
+ *	bp	Set breakpoint on all cpus.  Only use hardware assist if need.
+ *	bph	Set breakpoint on all cpus.  Force hardware register
+ */
+
+static int kdb_bp(int argc, const char **argv)
+{
+	int i, bpno;
+	kdb_bp_t *bp, *bp_check;
+	int diag;
+	int free;
+	char *symname = NULL;
+	long offset = 0ul;
+	int nextarg;
+	kdb_bp_t template = {0};
+
+	if (argc == 0) {
+		/*
+		 * Display breakpoint table
+		 */
+		for (bpno = 0, bp = kdb_breakpoints; bpno < KDB_MAXBPT;
+		     bpno++, bp++) {
+			if (bp->bp_free)
+				continue;
+			kdb_printbp(bp, bpno);
+		}
+
+		return 0;
+	}
+
+	nextarg = 1;
+	diag = kdbgetaddrarg(argc, argv, &nextarg, &template.bp_addr,
+			     &offset, &symname);
+	if (diag)
+		return diag;
+	if (!template.bp_addr)
+		return KDB_BADINT;
+
+	/*
+	 * Find an empty bp structure to allocate
+	 */
+	free = KDB_MAXBPT;
+	for (bpno = 0, bp = kdb_breakpoints; bpno < KDB_MAXBPT; bpno++, bp++) {
+		if (bp->bp_free)
+			break;
+	}
+
+	if (bpno == KDB_MAXBPT)
+		return KDB_TOOMANYBPT;
+
+	if (strcmp(argv[0], "bph") == 0) {
+		template.bp_type = BP_HARDWARE_BREAKPOINT;
+		diag = kdb_parsebp(argc, argv, &nextarg, &template);
+		if (diag)
+			return diag;
+	} else {
+		template.bp_type = BP_BREAKPOINT;
+	}
+
+	/*
+	 * Check for clashing breakpoints.
+	 *
+	 * Note, in this design we can't have hardware breakpoints
+	 * enabled for both read and write on the same address.
+	 */
+	for (i = 0, bp_check = kdb_breakpoints; i < KDB_MAXBPT;
+	     i++, bp_check++) {
+		if (!bp_check->bp_free &&
+		    bp_check->bp_addr == template.bp_addr) {
+			kdb_printf("You already have a breakpoint at "
+				   kdb_bfd_vma_fmt0 "\n", template.bp_addr);
+			return KDB_DUPBPT;
+		}
+	}
+
+	template.bp_enabled = 1;
+
+	/*
+	 * Actually allocate the breakpoint found earlier
+	 */
+	*bp = template;
+	bp->bp_free = 0;
+
+	kdb_printbp(bp, bpno);
+
+	return 0;
+}
+
+/*
+ * kdb_bc
+ *
+ *	Handles the 'bc', 'be', and 'bd' commands
+ *
+ *	[bd|bc|be] <breakpoint-number>
+ *	[bd|bc|be] *
+ *
+ * Parameters:
+ *	argc	Count of arguments in argv
+ *	argv	Space delimited command line arguments
+ * Outputs:
+ *	None.
+ * Returns:
+ *	Zero for success, a kdb diagnostic for failure
+ * Locking:
+ *	None.
+ * Remarks:
+ */
+static int kdb_bc(int argc, const char **argv)
+{
+	unsigned long addr;
+	kdb_bp_t *bp = NULL;
+	int lowbp = KDB_MAXBPT;
+	int highbp = 0;
+	int done = 0;
+	int i;
+	int diag = 0;
+
+	int cmd;			/* KDBCMD_B? */
+#define KDBCMD_BC	0
+#define KDBCMD_BE	1
+#define KDBCMD_BD	2
+
+	if (strcmp(argv[0], "be") == 0)
+		cmd = KDBCMD_BE;
+	else if (strcmp(argv[0], "bd") == 0)
+		cmd = KDBCMD_BD;
+	else
+		cmd = KDBCMD_BC;
+
+	if (argc != 1)
+		return KDB_ARGCOUNT;
+
+	if (strcmp(argv[1], "*") == 0) {
+		lowbp = 0;
+		highbp = KDB_MAXBPT;
+	} else {
+		diag = kdbgetularg(argv[1], &addr);
+		if (diag)
+			return diag;
+
+		/*
+		 * For addresses less than the maximum breakpoint number,
+		 * assume that the breakpoint number is desired.
+		 */
+		if (addr < KDB_MAXBPT) {
+			bp = &kdb_breakpoints[addr];
+			lowbp = highbp = addr;
+			highbp++;
+		} else {
+			for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT;
+			    i++, bp++) {
+				if (bp->bp_addr == addr) {
+					lowbp = highbp = i;
+					highbp++;
+					break;
+				}
+			}
+		}
+	}
+
+	/*
+	 * Now operate on the set of breakpoints matching the input
+	 * criteria (either '*' for all, or an individual breakpoint).
+	 */
+	for (bp = &kdb_breakpoints[lowbp], i = lowbp;
+	    i < highbp;
+	    i++, bp++) {
+		if (bp->bp_free)
+			continue;
+
+		done++;
+
+		switch (cmd) {
+		case KDBCMD_BC:
+			bp->bp_enabled = 0;
+
+			kdb_printf("Breakpoint %d at "
+				   kdb_bfd_vma_fmt " cleared\n",
+				   i, bp->bp_addr);
+
+			bp->bp_addr = 0;
+			bp->bp_free = 1;
+
+			break;
+		case KDBCMD_BE:
+			bp->bp_enabled = 1;
+
+			kdb_printf("Breakpoint %d at "
+				   kdb_bfd_vma_fmt " enabled",
+				   i, bp->bp_addr);
+
+			kdb_printf("\n");
+			break;
+		case KDBCMD_BD:
+			if (!bp->bp_enabled)
+				break;
+
+			bp->bp_enabled = 0;
+
+			kdb_printf("Breakpoint %d at "
+				   kdb_bfd_vma_fmt " disabled\n",
+				   i, bp->bp_addr);
+
+			break;
+		}
+		if (bp->bp_delay && (cmd == KDBCMD_BC || cmd == KDBCMD_BD)) {
+			bp->bp_delay = 0;
+			KDB_STATE_CLEAR(SSBPT);
+		}
+	}
+
+	return (!done) ? KDB_BPTNOTFOUND : 0;
+}
+
+/*
+ * kdb_ss
+ *
+ *	Process the 'ss' (Single Step) and 'ssb' (Single Step to Branch)
+ *	commands.
+ *
+ *	ss
+ *	ssb
+ *
+ * Parameters:
+ *	argc	Argument count
+ *	argv	Argument vector
+ * Outputs:
+ *	None.
+ * Returns:
+ *	KDB_CMD_SS[B] for success, a kdb error if failure.
+ * Locking:
+ *	None.
+ * Remarks:
+ *
+ *	Set the arch specific option to trigger a debug trap after the next
+ *	instruction.
+ *
+ *	For 'ssb', set the trace flag in the debug trap handler
+ *	after printing the current insn and return directly without
+ *	invoking the kdb command processor, until a branch instruction
+ *	is encountered.
+ */
+
+static int kdb_ss(int argc, const char **argv)
+{
+	int ssb = 0;
+
+	ssb = (strcmp(argv[0], "ssb") == 0);
+	if (argc != 0)
+		return KDB_ARGCOUNT;
+	/*
+	 * Set trace flag and go.
+	 */
+	KDB_STATE_SET(DOING_SS);
+	if (ssb) {
+		KDB_STATE_SET(DOING_SSB);
+		return KDB_CMD_SSB;
+	}
+	return KDB_CMD_SS;
+}
+
+/* Initialize the breakpoint table and register	breakpoint commands. */
+
+void __init kdb_initbptab(void)
+{
+	int i;
+	kdb_bp_t *bp;
+
+	/*
+	 * First time initialization.
+	 */
+	memset(&kdb_breakpoints, '\0', sizeof(kdb_breakpoints));
+
+	for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++)
+		bp->bp_free = 1;
+
+	kdb_register_repeat("bp", kdb_bp, "[<vaddr>]",
+		"Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("bl", kdb_bp, "[<vaddr>]",
+		"Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
+	if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT)
+		kdb_register_repeat("bph", kdb_bp, "[<vaddr>]",
+		"[datar [length]|dataw [length]]   Set hw brk", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("bc", kdb_bc, "<bpnum>",
+		"Clear Breakpoint", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("be", kdb_bc, "<bpnum>",
+		"Enable Breakpoint", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("bd", kdb_bc, "<bpnum>",
+		"Disable Breakpoint", 0, KDB_REPEAT_NONE);
+
+	kdb_register_repeat("ss", kdb_ss, "",
+		"Single Step", 1, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("ssb", kdb_ss, "",
+		"Single step to branch/call", 0, KDB_REPEAT_NO_ARGS);
+	/*
+	 * Architecture dependent initialization.
+	 */
+}
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
new file mode 100644
index 00000000000..2f62fe85f16
--- /dev/null
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -0,0 +1,210 @@
+/*
+ * Kernel Debugger Architecture Independent Stack Traceback
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1999-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ */
+
+#include <linux/ctype.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/kdb.h>
+#include <linux/nmi.h>
+#include <asm/system.h>
+#include "kdb_private.h"
+
+
+static void kdb_show_stack(struct task_struct *p, void *addr)
+{
+	int old_lvl = console_loglevel;
+	console_loglevel = 15;
+	kdb_trap_printk++;
+	kdb_set_current_task(p);
+	if (addr) {
+		show_stack((struct task_struct *)p, addr);
+	} else if (kdb_current_regs) {
+#ifdef CONFIG_X86
+		show_stack(p, &kdb_current_regs->sp);
+#else
+		show_stack(p, NULL);
+#endif
+	} else {
+		show_stack(p, NULL);
+	}
+	console_loglevel = old_lvl;
+	kdb_trap_printk--;
+}
+
+/*
+ * kdb_bt
+ *
+ *	This function implements the 'bt' command.  Print a stack
+ *	traceback.
+ *
+ *	bt [<address-expression>]	(addr-exp is for alternate stacks)
+ *	btp <pid>			Kernel stack for <pid>
+ *	btt <address-expression>	Kernel stack for task structure at
+ *					<address-expression>
+ *	bta [DRSTCZEUIMA]		All useful processes, optionally
+ *					filtered by state
+ *	btc [<cpu>]			The current process on one cpu,
+ *					default is all cpus
+ *
+ *	bt <address-expression> refers to a address on the stack, that location
+ *	is assumed to contain a return address.
+ *
+ *	btt <address-expression> refers to the address of a struct task.
+ *
+ * Inputs:
+ *	argc	argument count
+ *	argv	argument vector
+ * Outputs:
+ *	None.
+ * Returns:
+ *	zero for success, a kdb diagnostic if error
+ * Locking:
+ *	none.
+ * Remarks:
+ *	Backtrack works best when the code uses frame pointers.  But even
+ *	without frame pointers we should get a reasonable trace.
+ *
+ *	mds comes in handy when examining the stack to do a manual traceback or
+ *	to get a starting point for bt <address-expression>.
+ */
+
+static int
+kdb_bt1(struct task_struct *p, unsigned long mask,
+	int argcount, int btaprompt)
+{
+	char buffer[2];
+	if (kdb_getarea(buffer[0], (unsigned long)p) ||
+	    kdb_getarea(buffer[0], (unsigned long)(p+1)-1))
+		return KDB_BADADDR;
+	if (!kdb_task_state(p, mask))
+		return 0;
+	kdb_printf("Stack traceback for pid %d\n", p->pid);
+	kdb_ps1(p);
+	kdb_show_stack(p, NULL);
+	if (btaprompt) {
+		kdb_getstr(buffer, sizeof(buffer),
+			   "Enter <q> to end, <cr> to continue:");
+		if (buffer[0] == 'q') {
+			kdb_printf("\n");
+			return 1;
+		}
+	}
+	touch_nmi_watchdog();
+	return 0;
+}
+
+int
+kdb_bt(int argc, const char **argv)
+{
+	int diag;
+	int argcount = 5;
+	int btaprompt = 1;
+	int nextarg;
+	unsigned long addr;
+	long offset;
+
+	kdbgetintenv("BTARGS", &argcount);	/* Arguments to print */
+	kdbgetintenv("BTAPROMPT", &btaprompt);	/* Prompt after each
+						 * proc in bta */
+
+	if (strcmp(argv[0], "bta") == 0) {
+		struct task_struct *g, *p;
+		unsigned long cpu;
+		unsigned long mask = kdb_task_state_string(argc ? argv[1] :
+							   NULL);
+		if (argc == 0)
+			kdb_ps_suppressed();
+		/* Run the active tasks first */
+		for_each_online_cpu(cpu) {
+			p = kdb_curr_task(cpu);
+			if (kdb_bt1(p, mask, argcount, btaprompt))
+				return 0;
+		}
+		/* Now the inactive tasks */
+		kdb_do_each_thread(g, p) {
+			if (task_curr(p))
+				continue;
+			if (kdb_bt1(p, mask, argcount, btaprompt))
+				return 0;
+		} kdb_while_each_thread(g, p);
+	} else if (strcmp(argv[0], "btp") == 0) {
+		struct task_struct *p;
+		unsigned long pid;
+		if (argc != 1)
+			return KDB_ARGCOUNT;
+		diag = kdbgetularg((char *)argv[1], &pid);
+		if (diag)
+			return diag;
+		p = find_task_by_pid_ns(pid, &init_pid_ns);
+		if (p) {
+			kdb_set_current_task(p);
+			return kdb_bt1(p, ~0UL, argcount, 0);
+		}
+		kdb_printf("No process with pid == %ld found\n", pid);
+		return 0;
+	} else if (strcmp(argv[0], "btt") == 0) {
+		if (argc != 1)
+			return KDB_ARGCOUNT;
+		diag = kdbgetularg((char *)argv[1], &addr);
+		if (diag)
+			return diag;
+		kdb_set_current_task((struct task_struct *)addr);
+		return kdb_bt1((struct task_struct *)addr, ~0UL, argcount, 0);
+	} else if (strcmp(argv[0], "btc") == 0) {
+		unsigned long cpu = ~0;
+		struct task_struct *save_current_task = kdb_current_task;
+		char buf[80];
+		if (argc > 1)
+			return KDB_ARGCOUNT;
+		if (argc == 1) {
+			diag = kdbgetularg((char *)argv[1], &cpu);
+			if (diag)
+				return diag;
+		}
+		/* Recursive use of kdb_parse, do not use argv after
+		 * this point */
+		argv = NULL;
+		if (cpu != ~0) {
+			if (cpu >= num_possible_cpus() || !cpu_online(cpu)) {
+				kdb_printf("no process for cpu %ld\n", cpu);
+				return 0;
+			}
+			sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+			kdb_parse(buf);
+			return 0;
+		}
+		kdb_printf("btc: cpu status: ");
+		kdb_parse("cpu\n");
+		for_each_online_cpu(cpu) {
+			sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+			kdb_parse(buf);
+			touch_nmi_watchdog();
+		}
+		kdb_set_current_task(save_current_task);
+		return 0;
+	} else {
+		if (argc) {
+			nextarg = 1;
+			diag = kdbgetaddrarg(argc, argv, &nextarg, &addr,
+					     &offset, NULL);
+			if (diag)
+				return diag;
+			kdb_show_stack(kdb_current_task, (void *)addr);
+			return 0;
+		} else {
+			return kdb_bt1(kdb_current_task, ~0UL, argcount, 0);
+		}
+	}
+
+	/* NOTREACHED */
+	return 0;
+}
diff --git a/kernel/debug/kdb/kdb_cmds b/kernel/debug/kdb/kdb_cmds
new file mode 100644
index 00000000000..56c88e4db30
--- /dev/null
+++ b/kernel/debug/kdb/kdb_cmds
@@ -0,0 +1,35 @@
+# Initial commands for kdb, alter to suit your needs.
+# These commands are executed in kdb_init() context, no SMP, no
+# processes.  Commands that require process data (including stack or
+# registers) are not reliable this early.  set and bp commands should
+# be safe.  Global breakpoint commands affect each cpu as it is booted.
+
+# Standard debugging information for first level support, just type archkdb
+# or archkdbcpu or archkdbshort at the kdb prompt.
+
+defcmd dumpcommon "" "Common kdb debugging"
+  set BTAPROMPT 0
+  set LINES 10000
+  -summary
+  -cpu
+  -ps
+  -dmesg 600
+  -bt
+endefcmd
+
+defcmd dumpall "" "First line debugging"
+  set BTSYMARG 1
+  set BTARGS 9
+  pid R
+  -dumpcommon
+  -bta
+endefcmd
+
+defcmd dumpcpu "" "Same as dumpall but only tasks on cpus"
+  set BTSYMARG 1
+  set BTARGS 9
+  pid R
+  -dumpcommon
+  -btc
+endefcmd
+
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
new file mode 100644
index 00000000000..bf6e8270e95
--- /dev/null
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -0,0 +1,169 @@
+/*
+ * Created by: Jason Wessel <jason.wessel@windriver.com>
+ *
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/kdebug.h>
+#include "kdb_private.h"
+#include "../debug_core.h"
+
+/*
+ * KDB interface to KGDB internals
+ */
+get_char_func kdb_poll_funcs[] = {
+	dbg_io_get_char,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+};
+EXPORT_SYMBOL_GPL(kdb_poll_funcs);
+
+int kdb_poll_idx = 1;
+EXPORT_SYMBOL_GPL(kdb_poll_idx);
+
+int kdb_stub(struct kgdb_state *ks)
+{
+	int error = 0;
+	kdb_bp_t *bp;
+	unsigned long addr = kgdb_arch_pc(ks->ex_vector, ks->linux_regs);
+	kdb_reason_t reason = KDB_REASON_OOPS;
+	kdb_dbtrap_t db_result = KDB_DB_NOBPT;
+	int i;
+
+	if (KDB_STATE(REENTRY)) {
+		reason = KDB_REASON_SWITCH;
+		KDB_STATE_CLEAR(REENTRY);
+		addr = instruction_pointer(ks->linux_regs);
+	}
+	ks->pass_exception = 0;
+	if (atomic_read(&kgdb_setting_breakpoint))
+		reason = KDB_REASON_KEYBOARD;
+
+	for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) {
+		if ((bp->bp_enabled) && (bp->bp_addr == addr)) {
+			reason = KDB_REASON_BREAK;
+			db_result = KDB_DB_BPT;
+			if (addr != instruction_pointer(ks->linux_regs))
+				kgdb_arch_set_pc(ks->linux_regs, addr);
+			break;
+		}
+	}
+	if (reason == KDB_REASON_BREAK || reason == KDB_REASON_SWITCH) {
+		for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) {
+			if (bp->bp_free)
+				continue;
+			if (bp->bp_addr == addr) {
+				bp->bp_delay = 1;
+				bp->bp_delayed = 1;
+	/*
+	 * SSBPT is set when the kernel debugger must single step a
+	 * task in order to re-establish an instruction breakpoint
+	 * which uses the instruction replacement mechanism.  It is
+	 * cleared by any action that removes the need to single-step
+	 * the breakpoint.
+	 */
+				reason = KDB_REASON_BREAK;
+				db_result = KDB_DB_BPT;
+				KDB_STATE_SET(SSBPT);
+				break;
+			}
+		}
+	}
+
+	if (reason != KDB_REASON_BREAK && ks->ex_vector == 0 &&
+		ks->signo == SIGTRAP) {
+		reason = KDB_REASON_SSTEP;
+		db_result = KDB_DB_BPT;
+	}
+	/* Set initial kdb state variables */
+	KDB_STATE_CLEAR(KGDB_TRANS);
+	kdb_initial_cpu = ks->cpu;
+	kdb_current_task = kgdb_info[ks->cpu].task;
+	kdb_current_regs = kgdb_info[ks->cpu].debuggerinfo;
+	/* Remove any breakpoints as needed by kdb and clear single step */
+	kdb_bp_remove();
+	KDB_STATE_CLEAR(DOING_SS);
+	KDB_STATE_CLEAR(DOING_SSB);
+	KDB_STATE_SET(PAGER);
+	/* zero out any offline cpu data */
+	for_each_present_cpu(i) {
+		if (!cpu_online(i)) {
+			kgdb_info[i].debuggerinfo = NULL;
+			kgdb_info[i].task = NULL;
+		}
+	}
+	if (ks->err_code == DIE_OOPS || reason == KDB_REASON_OOPS) {
+		ks->pass_exception = 1;
+		KDB_FLAG_SET(CATASTROPHIC);
+	}
+	kdb_initial_cpu = ks->cpu;
+	if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
+		KDB_STATE_CLEAR(SSBPT);
+		KDB_STATE_CLEAR(DOING_SS);
+	} else {
+		/* Start kdb main loop */
+		error = kdb_main_loop(KDB_REASON_ENTER, reason,
+				      ks->err_code, db_result, ks->linux_regs);
+	}
+	/*
+	 * Upon exit from the kdb main loop setup break points and restart
+	 * the system based on the requested continue state
+	 */
+	kdb_initial_cpu = -1;
+	kdb_current_task = NULL;
+	kdb_current_regs = NULL;
+	KDB_STATE_CLEAR(PAGER);
+	kdbnearsym_cleanup();
+	if (error == KDB_CMD_KGDB) {
+		if (KDB_STATE(DOING_KGDB) || KDB_STATE(DOING_KGDB2)) {
+	/*
+	 * This inteface glue which allows kdb to transition in into
+	 * the gdb stub.  In order to do this the '?' or '' gdb serial
+	 * packet response is processed here.  And then control is
+	 * passed to the gdbstub.
+	 */
+			if (KDB_STATE(DOING_KGDB))
+				gdbstub_state(ks, "?");
+			else
+				gdbstub_state(ks, "");
+			KDB_STATE_CLEAR(DOING_KGDB);
+			KDB_STATE_CLEAR(DOING_KGDB2);
+		}
+		return DBG_PASS_EVENT;
+	}
+	kdb_bp_install(ks->linux_regs);
+	dbg_activate_sw_breakpoints();
+	/* Set the exit state to a single step or a continue */
+	if (KDB_STATE(DOING_SS))
+		gdbstub_state(ks, "s");
+	else
+		gdbstub_state(ks, "c");
+
+	KDB_FLAG_CLEAR(CATASTROPHIC);
+
+	/* Invoke arch specific exception handling prior to system resume */
+	kgdb_info[ks->cpu].ret_state = gdbstub_state(ks, "e");
+	if (ks->pass_exception)
+		kgdb_info[ks->cpu].ret_state = 1;
+	if (error == KDB_CMD_CPU) {
+		KDB_STATE_SET(REENTRY);
+		/*
+		 * Force clear the single step bit because kdb emulates this
+		 * differently vs the gdbstub
+		 */
+		kgdb_single_step = 0;
+		dbg_deactivate_sw_breakpoints();
+		return DBG_SWITCH_CPU_EVENT;
+	}
+	return kgdb_info[ks->cpu].ret_state;
+}
+
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
new file mode 100644
index 00000000000..c9b7f4f90bb
--- /dev/null
+++ b/kernel/debug/kdb/kdb_io.c
@@ -0,0 +1,826 @@
+/*
+ * Kernel Debugger Architecture Independent Console I/O handler
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1999-2006 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/kdev_t.h>
+#include <linux/console.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/nmi.h>
+#include <linux/delay.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/kallsyms.h>
+#include "kdb_private.h"
+
+#define CMD_BUFLEN 256
+char kdb_prompt_str[CMD_BUFLEN];
+
+int kdb_trap_printk;
+
+static void kgdb_transition_check(char *buffer)
+{
+	int slen = strlen(buffer);
+	if (strncmp(buffer, "$?#3f", slen) != 0 &&
+	    strncmp(buffer, "$qSupported#37", slen) != 0 &&
+	    strncmp(buffer, "+$qSupported#37", slen) != 0) {
+		KDB_STATE_SET(KGDB_TRANS);
+		kdb_printf("%s", buffer);
+	}
+}
+
+static int kdb_read_get_key(char *buffer, size_t bufsize)
+{
+#define ESCAPE_UDELAY 1000
+#define ESCAPE_DELAY (2*1000000/ESCAPE_UDELAY) /* 2 seconds worth of udelays */
+	char escape_data[5];	/* longest vt100 escape sequence is 4 bytes */
+	char *ped = escape_data;
+	int escape_delay = 0;
+	get_char_func *f, *f_escape = NULL;
+	int key;
+
+	for (f = &kdb_poll_funcs[0]; ; ++f) {
+		if (*f == NULL) {
+			/* Reset NMI watchdog once per poll loop */
+			touch_nmi_watchdog();
+			f = &kdb_poll_funcs[0];
+		}
+		if (escape_delay == 2) {
+			*ped = '\0';
+			ped = escape_data;
+			--escape_delay;
+		}
+		if (escape_delay == 1) {
+			key = *ped++;
+			if (!*ped)
+				--escape_delay;
+			break;
+		}
+		key = (*f)();
+		if (key == -1) {
+			if (escape_delay) {
+				udelay(ESCAPE_UDELAY);
+				--escape_delay;
+			}
+			continue;
+		}
+		if (bufsize <= 2) {
+			if (key == '\r')
+				key = '\n';
+			*buffer++ = key;
+			*buffer = '\0';
+			return -1;
+		}
+		if (escape_delay == 0 && key == '\e') {
+			escape_delay = ESCAPE_DELAY;
+			ped = escape_data;
+			f_escape = f;
+		}
+		if (escape_delay) {
+			*ped++ = key;
+			if (f_escape != f) {
+				escape_delay = 2;
+				continue;
+			}
+			if (ped - escape_data == 1) {
+				/* \e */
+				continue;
+			} else if (ped - escape_data == 2) {
+				/* \e<something> */
+				if (key != '[')
+					escape_delay = 2;
+				continue;
+			} else if (ped - escape_data == 3) {
+				/* \e[<something> */
+				int mapkey = 0;
+				switch (key) {
+				case 'A': /* \e[A, up arrow */
+					mapkey = 16;
+					break;
+				case 'B': /* \e[B, down arrow */
+					mapkey = 14;
+					break;
+				case 'C': /* \e[C, right arrow */
+					mapkey = 6;
+					break;
+				case 'D': /* \e[D, left arrow */
+					mapkey = 2;
+					break;
+				case '1': /* dropthrough */
+				case '3': /* dropthrough */
+				/* \e[<1,3,4>], may be home, del, end */
+				case '4':
+					mapkey = -1;
+					break;
+				}
+				if (mapkey != -1) {
+					if (mapkey > 0) {
+						escape_data[0] = mapkey;
+						escape_data[1] = '\0';
+					}
+					escape_delay = 2;
+				}
+				continue;
+			} else if (ped - escape_data == 4) {
+				/* \e[<1,3,4><something> */
+				int mapkey = 0;
+				if (key == '~') {
+					switch (escape_data[2]) {
+					case '1': /* \e[1~, home */
+						mapkey = 1;
+						break;
+					case '3': /* \e[3~, del */
+						mapkey = 4;
+						break;
+					case '4': /* \e[4~, end */
+						mapkey = 5;
+						break;
+					}
+				}
+				if (mapkey > 0) {
+					escape_data[0] = mapkey;
+					escape_data[1] = '\0';
+				}
+				escape_delay = 2;
+				continue;
+			}
+		}
+		break;	/* A key to process */
+	}
+	return key;
+}
+
+/*
+ * kdb_read
+ *
+ *	This function reads a string of characters, terminated by
+ *	a newline, or by reaching the end of the supplied buffer,
+ *	from the current kernel debugger console device.
+ * Parameters:
+ *	buffer	- Address of character buffer to receive input characters.
+ *	bufsize - size, in bytes, of the character buffer
+ * Returns:
+ *	Returns a pointer to the buffer containing the received
+ *	character string.  This string will be terminated by a
+ *	newline character.
+ * Locking:
+ *	No locks are required to be held upon entry to this
+ *	function.  It is not reentrant - it relies on the fact
+ *	that while kdb is running on only one "master debug" cpu.
+ * Remarks:
+ *
+ * The buffer size must be >= 2.  A buffer size of 2 means that the caller only
+ * wants a single key.
+ *
+ * An escape key could be the start of a vt100 control sequence such as \e[D
+ * (left arrow) or it could be a character in its own right.  The standard
+ * method for detecting the difference is to wait for 2 seconds to see if there
+ * are any other characters.  kdb is complicated by the lack of a timer service
+ * (interrupts are off), by multiple input sources and by the need to sometimes
+ * return after just one key.  Escape sequence processing has to be done as
+ * states in the polling loop.
+ */
+
+static char *kdb_read(char *buffer, size_t bufsize)
+{
+	char *cp = buffer;
+	char *bufend = buffer+bufsize-2;	/* Reserve space for newline
+						 * and null byte */
+	char *lastchar;
+	char *p_tmp;
+	char tmp;
+	static char tmpbuffer[CMD_BUFLEN];
+	int len = strlen(buffer);
+	int len_tmp;
+	int tab = 0;
+	int count;
+	int i;
+	int diag, dtab_count;
+	int key;
+
+
+	diag = kdbgetintenv("DTABCOUNT", &dtab_count);
+	if (diag)
+		dtab_count = 30;
+
+	if (len > 0) {
+		cp += len;
+		if (*(buffer+len-1) == '\n')
+			cp--;
+	}
+
+	lastchar = cp;
+	*cp = '\0';
+	kdb_printf("%s", buffer);
+poll_again:
+	key = kdb_read_get_key(buffer, bufsize);
+	if (key == -1)
+		return buffer;
+	if (key != 9)
+		tab = 0;
+	switch (key) {
+	case 8: /* backspace */
+		if (cp > buffer) {
+			if (cp < lastchar) {
+				memcpy(tmpbuffer, cp, lastchar - cp);
+				memcpy(cp-1, tmpbuffer, lastchar - cp);
+			}
+			*(--lastchar) = '\0';
+			--cp;
+			kdb_printf("\b%s \r", cp);
+			tmp = *cp;
+			*cp = '\0';
+			kdb_printf(kdb_prompt_str);
+			kdb_printf("%s", buffer);
+			*cp = tmp;
+		}
+		break;
+	case 13: /* enter */
+		*lastchar++ = '\n';
+		*lastchar++ = '\0';
+		kdb_printf("\n");
+		return buffer;
+	case 4: /* Del */
+		if (cp < lastchar) {
+			memcpy(tmpbuffer, cp+1, lastchar - cp - 1);
+			memcpy(cp, tmpbuffer, lastchar - cp - 1);
+			*(--lastchar) = '\0';
+			kdb_printf("%s \r", cp);
+			tmp = *cp;
+			*cp = '\0';
+			kdb_printf(kdb_prompt_str);
+			kdb_printf("%s", buffer);
+			*cp = tmp;
+		}
+		break;
+	case 1: /* Home */
+		if (cp > buffer) {
+			kdb_printf("\r");
+			kdb_printf(kdb_prompt_str);
+			cp = buffer;
+		}
+		break;
+	case 5: /* End */
+		if (cp < lastchar) {
+			kdb_printf("%s", cp);
+			cp = lastchar;
+		}
+		break;
+	case 2: /* Left */
+		if (cp > buffer) {
+			kdb_printf("\b");
+			--cp;
+		}
+		break;
+	case 14: /* Down */
+		memset(tmpbuffer, ' ',
+		       strlen(kdb_prompt_str) + (lastchar-buffer));
+		*(tmpbuffer+strlen(kdb_prompt_str) +
+		  (lastchar-buffer)) = '\0';
+		kdb_printf("\r%s\r", tmpbuffer);
+		*lastchar = (char)key;
+		*(lastchar+1) = '\0';
+		return lastchar;
+	case 6: /* Right */
+		if (cp < lastchar) {
+			kdb_printf("%c", *cp);
+			++cp;
+		}
+		break;
+	case 16: /* Up */
+		memset(tmpbuffer, ' ',
+		       strlen(kdb_prompt_str) + (lastchar-buffer));
+		*(tmpbuffer+strlen(kdb_prompt_str) +
+		  (lastchar-buffer)) = '\0';
+		kdb_printf("\r%s\r", tmpbuffer);
+		*lastchar = (char)key;
+		*(lastchar+1) = '\0';
+		return lastchar;
+	case 9: /* Tab */
+		if (tab < 2)
+			++tab;
+		p_tmp = buffer;
+		while (*p_tmp == ' ')
+			p_tmp++;
+		if (p_tmp > cp)
+			break;
+		memcpy(tmpbuffer, p_tmp, cp-p_tmp);
+		*(tmpbuffer + (cp-p_tmp)) = '\0';
+		p_tmp = strrchr(tmpbuffer, ' ');
+		if (p_tmp)
+			++p_tmp;
+		else
+			p_tmp = tmpbuffer;
+		len = strlen(p_tmp);
+		count = kallsyms_symbol_complete(p_tmp,
+						 sizeof(tmpbuffer) -
+						 (p_tmp - tmpbuffer));
+		if (tab == 2 && count > 0) {
+			kdb_printf("\n%d symbols are found.", count);
+			if (count > dtab_count) {
+				count = dtab_count;
+				kdb_printf(" But only first %d symbols will"
+					   " be printed.\nYou can change the"
+					   " environment variable DTABCOUNT.",
+					   count);
+			}
+			kdb_printf("\n");
+			for (i = 0; i < count; i++) {
+				if (kallsyms_symbol_next(p_tmp, i) < 0)
+					break;
+				kdb_printf("%s ", p_tmp);
+				*(p_tmp + len) = '\0';
+			}
+			if (i >= dtab_count)
+				kdb_printf("...");
+			kdb_printf("\n");
+			kdb_printf(kdb_prompt_str);
+			kdb_printf("%s", buffer);
+		} else if (tab != 2 && count > 0) {
+			len_tmp = strlen(p_tmp);
+			strncpy(p_tmp+len_tmp, cp, lastchar-cp+1);
+			len_tmp = strlen(p_tmp);
+			strncpy(cp, p_tmp+len, len_tmp-len + 1);
+			len = len_tmp - len;
+			kdb_printf("%s", cp);
+			cp += len;
+			lastchar += len;
+		}
+		kdb_nextline = 1; /* reset output line number */
+		break;
+	default:
+		if (key >= 32 && lastchar < bufend) {
+			if (cp < lastchar) {
+				memcpy(tmpbuffer, cp, lastchar - cp);
+				memcpy(cp+1, tmpbuffer, lastchar - cp);
+				*++lastchar = '\0';
+				*cp = key;
+				kdb_printf("%s\r", cp);
+				++cp;
+				tmp = *cp;
+				*cp = '\0';
+				kdb_printf(kdb_prompt_str);
+				kdb_printf("%s", buffer);
+				*cp = tmp;
+			} else {
+				*++lastchar = '\0';
+				*cp++ = key;
+				/* The kgdb transition check will hide
+				 * printed characters if we think that
+				 * kgdb is connecting, until the check
+				 * fails */
+				if (!KDB_STATE(KGDB_TRANS))
+					kgdb_transition_check(buffer);
+				else
+					kdb_printf("%c", key);
+			}
+			/* Special escape to kgdb */
+			if (lastchar - buffer >= 5 &&
+			    strcmp(lastchar - 5, "$?#3f") == 0) {
+				strcpy(buffer, "kgdb");
+				KDB_STATE_SET(DOING_KGDB);
+				return buffer;
+			}
+			if (lastchar - buffer >= 14 &&
+			    strcmp(lastchar - 14, "$qSupported#37") == 0) {
+				strcpy(buffer, "kgdb");
+				KDB_STATE_SET(DOING_KGDB2);
+				return buffer;
+			}
+		}
+		break;
+	}
+	goto poll_again;
+}
+
+/*
+ * kdb_getstr
+ *
+ *	Print the prompt string and read a command from the
+ *	input device.
+ *
+ * Parameters:
+ *	buffer	Address of buffer to receive command
+ *	bufsize Size of buffer in bytes
+ *	prompt	Pointer to string to use as prompt string
+ * Returns:
+ *	Pointer to command buffer.
+ * Locking:
+ *	None.
+ * Remarks:
+ *	For SMP kernels, the processor number will be
+ *	substituted for %d, %x or %o in the prompt.
+ */
+
+char *kdb_getstr(char *buffer, size_t bufsize, char *prompt)
+{
+	if (prompt && kdb_prompt_str != prompt)
+		strncpy(kdb_prompt_str, prompt, CMD_BUFLEN);
+	kdb_printf(kdb_prompt_str);
+	kdb_nextline = 1;	/* Prompt and input resets line number */
+	return kdb_read(buffer, bufsize);
+}
+
+/*
+ * kdb_input_flush
+ *
+ *	Get rid of any buffered console input.
+ *
+ * Parameters:
+ *	none
+ * Returns:
+ *	nothing
+ * Locking:
+ *	none
+ * Remarks:
+ *	Call this function whenever you want to flush input.  If there is any
+ *	outstanding input, it ignores all characters until there has been no
+ *	data for approximately 1ms.
+ */
+
+static void kdb_input_flush(void)
+{
+	get_char_func *f;
+	int res;
+	int flush_delay = 1;
+	while (flush_delay) {
+		flush_delay--;
+empty:
+		touch_nmi_watchdog();
+		for (f = &kdb_poll_funcs[0]; *f; ++f) {
+			res = (*f)();
+			if (res != -1) {
+				flush_delay = 1;
+				goto empty;
+			}
+		}
+		if (flush_delay)
+			mdelay(1);
+	}
+}
+
+/*
+ * kdb_printf
+ *
+ *	Print a string to the output device(s).
+ *
+ * Parameters:
+ *	printf-like format and optional args.
+ * Returns:
+ *	0
+ * Locking:
+ *	None.
+ * Remarks:
+ *	use 'kdbcons->write()' to avoid polluting 'log_buf' with
+ *	kdb output.
+ *
+ *  If the user is doing a cmd args | grep srch
+ *  then kdb_grepping_flag is set.
+ *  In that case we need to accumulate full lines (ending in \n) before
+ *  searching for the pattern.
+ */
+
+static char kdb_buffer[256];	/* A bit too big to go on stack */
+static char *next_avail = kdb_buffer;
+static int  size_avail;
+static int  suspend_grep;
+
+/*
+ * search arg1 to see if it contains arg2
+ * (kdmain.c provides flags for ^pat and pat$)
+ *
+ * return 1 for found, 0 for not found
+ */
+static int kdb_search_string(char *searched, char *searchfor)
+{
+	char firstchar, *cp;
+	int len1, len2;
+
+	/* not counting the newline at the end of "searched" */
+	len1 = strlen(searched)-1;
+	len2 = strlen(searchfor);
+	if (len1 < len2)
+		return 0;
+	if (kdb_grep_leading && kdb_grep_trailing && len1 != len2)
+		return 0;
+	if (kdb_grep_leading) {
+		if (!strncmp(searched, searchfor, len2))
+			return 1;
+	} else if (kdb_grep_trailing) {
+		if (!strncmp(searched+len1-len2, searchfor, len2))
+			return 1;
+	} else {
+		firstchar = *searchfor;
+		cp = searched;
+		while ((cp = strchr(cp, firstchar))) {
+			if (!strncmp(cp, searchfor, len2))
+				return 1;
+			cp++;
+		}
+	}
+	return 0;
+}
+
+int vkdb_printf(const char *fmt, va_list ap)
+{
+	int diag;
+	int linecount;
+	int logging, saved_loglevel = 0;
+	int saved_trap_printk;
+	int got_printf_lock = 0;
+	int retlen = 0;
+	int fnd, len;
+	char *cp, *cp2, *cphold = NULL, replaced_byte = ' ';
+	char *moreprompt = "more> ";
+	struct console *c = console_drivers;
+	static DEFINE_SPINLOCK(kdb_printf_lock);
+	unsigned long uninitialized_var(flags);
+
+	preempt_disable();
+	saved_trap_printk = kdb_trap_printk;
+	kdb_trap_printk = 0;
+
+	/* Serialize kdb_printf if multiple cpus try to write at once.
+	 * But if any cpu goes recursive in kdb, just print the output,
+	 * even if it is interleaved with any other text.
+	 */
+	if (!KDB_STATE(PRINTF_LOCK)) {
+		KDB_STATE_SET(PRINTF_LOCK);
+		spin_lock_irqsave(&kdb_printf_lock, flags);
+		got_printf_lock = 1;
+		atomic_inc(&kdb_event);
+	} else {
+		__acquire(kdb_printf_lock);
+	}
+
+	diag = kdbgetintenv("LINES", &linecount);
+	if (diag || linecount <= 1)
+		linecount = 24;
+
+	diag = kdbgetintenv("LOGGING", &logging);
+	if (diag)
+		logging = 0;
+
+	if (!kdb_grepping_flag || suspend_grep) {
+		/* normally, every vsnprintf starts a new buffer */
+		next_avail = kdb_buffer;
+		size_avail = sizeof(kdb_buffer);
+	}
+	vsnprintf(next_avail, size_avail, fmt, ap);
+
+	/*
+	 * If kdb_parse() found that the command was cmd xxx | grep yyy
+	 * then kdb_grepping_flag is set, and kdb_grep_string contains yyy
+	 *
+	 * Accumulate the print data up to a newline before searching it.
+	 * (vsnprintf does null-terminate the string that it generates)
+	 */
+
+	/* skip the search if prints are temporarily unconditional */
+	if (!suspend_grep && kdb_grepping_flag) {
+		cp = strchr(kdb_buffer, '\n');
+		if (!cp) {
+			/*
+			 * Special cases that don't end with newlines
+			 * but should be written without one:
+			 *   The "[nn]kdb> " prompt should
+			 *   appear at the front of the buffer.
+			 *
+			 *   The "[nn]more " prompt should also be
+			 *     (MOREPROMPT -> moreprompt)
+			 *   written *   but we print that ourselves,
+			 *   we set the suspend_grep flag to make
+			 *   it unconditional.
+			 *
+			 */
+			if (next_avail == kdb_buffer) {
+				/*
+				 * these should occur after a newline,
+				 * so they will be at the front of the
+				 * buffer
+				 */
+				cp2 = kdb_buffer;
+				len = strlen(kdb_prompt_str);
+				if (!strncmp(cp2, kdb_prompt_str, len)) {
+					/*
+					 * We're about to start a new
+					 * command, so we can go back
+					 * to normal mode.
+					 */
+					kdb_grepping_flag = 0;
+					goto kdb_printit;
+				}
+			}
+			/* no newline; don't search/write the buffer
+			   until one is there */
+			len = strlen(kdb_buffer);
+			next_avail = kdb_buffer + len;
+			size_avail = sizeof(kdb_buffer) - len;
+			goto kdb_print_out;
+		}
+
+		/*
+		 * The newline is present; print through it or discard
+		 * it, depending on the results of the search.
+		 */
+		cp++;	 	     /* to byte after the newline */
+		replaced_byte = *cp; /* remember what/where it was */
+		cphold = cp;
+		*cp = '\0';	     /* end the string for our search */
+
+		/*
+		 * We now have a newline at the end of the string
+		 * Only continue with this output if it contains the
+		 * search string.
+		 */
+		fnd = kdb_search_string(kdb_buffer, kdb_grep_string);
+		if (!fnd) {
+			/*
+			 * At this point the complete line at the start
+			 * of kdb_buffer can be discarded, as it does
+			 * not contain what the user is looking for.
+			 * Shift the buffer left.
+			 */
+			*cphold = replaced_byte;
+			strcpy(kdb_buffer, cphold);
+			len = strlen(kdb_buffer);
+			next_avail = kdb_buffer + len;
+			size_avail = sizeof(kdb_buffer) - len;
+			goto kdb_print_out;
+		}
+		/*
+		 * at this point the string is a full line and
+		 * should be printed, up to the null.
+		 */
+	}
+kdb_printit:
+
+	/*
+	 * Write to all consoles.
+	 */
+	retlen = strlen(kdb_buffer);
+	if (!dbg_kdb_mode && kgdb_connected) {
+		gdbstub_msg_write(kdb_buffer, retlen);
+	} else {
+		if (!dbg_io_ops->is_console) {
+			len = strlen(kdb_buffer);
+			cp = kdb_buffer;
+			while (len--) {
+				dbg_io_ops->write_char(*cp);
+				cp++;
+			}
+		}
+		while (c) {
+			c->write(c, kdb_buffer, retlen);
+			touch_nmi_watchdog();
+			c = c->next;
+		}
+	}
+	if (logging) {
+		saved_loglevel = console_loglevel;
+		console_loglevel = 0;
+		printk(KERN_INFO "%s", kdb_buffer);
+	}
+
+	if (KDB_STATE(PAGER) && strchr(kdb_buffer, '\n'))
+		kdb_nextline++;
+
+	/* check for having reached the LINES number of printed lines */
+	if (kdb_nextline == linecount) {
+		char buf1[16] = "";
+#if defined(CONFIG_SMP)
+		char buf2[32];
+#endif
+
+		/* Watch out for recursion here.  Any routine that calls
+		 * kdb_printf will come back through here.  And kdb_read
+		 * uses kdb_printf to echo on serial consoles ...
+		 */
+		kdb_nextline = 1;	/* In case of recursion */
+
+		/*
+		 * Pause until cr.
+		 */
+		moreprompt = kdbgetenv("MOREPROMPT");
+		if (moreprompt == NULL)
+			moreprompt = "more> ";
+
+#if defined(CONFIG_SMP)
+		if (strchr(moreprompt, '%')) {
+			sprintf(buf2, moreprompt, get_cpu());
+			put_cpu();
+			moreprompt = buf2;
+		}
+#endif
+
+		kdb_input_flush();
+		c = console_drivers;
+
+		if (!dbg_io_ops->is_console) {
+			len = strlen(moreprompt);
+			cp = moreprompt;
+			while (len--) {
+				dbg_io_ops->write_char(*cp);
+				cp++;
+			}
+		}
+		while (c) {
+			c->write(c, moreprompt, strlen(moreprompt));
+			touch_nmi_watchdog();
+			c = c->next;
+		}
+
+		if (logging)
+			printk("%s", moreprompt);
+
+		kdb_read(buf1, 2); /* '2' indicates to return
+				    * immediately after getting one key. */
+		kdb_nextline = 1;	/* Really set output line 1 */
+
+		/* empty and reset the buffer: */
+		kdb_buffer[0] = '\0';
+		next_avail = kdb_buffer;
+		size_avail = sizeof(kdb_buffer);
+		if ((buf1[0] == 'q') || (buf1[0] == 'Q')) {
+			/* user hit q or Q */
+			KDB_FLAG_SET(CMD_INTERRUPT); /* command interrupted */
+			KDB_STATE_CLEAR(PAGER);
+			/* end of command output; back to normal mode */
+			kdb_grepping_flag = 0;
+			kdb_printf("\n");
+		} else if (buf1[0] == ' ') {
+			kdb_printf("\n");
+			suspend_grep = 1; /* for this recursion */
+		} else if (buf1[0] == '\n') {
+			kdb_nextline = linecount - 1;
+			kdb_printf("\r");
+			suspend_grep = 1; /* for this recursion */
+		} else if (buf1[0] && buf1[0] != '\n') {
+			/* user hit something other than enter */
+			suspend_grep = 1; /* for this recursion */
+			kdb_printf("\nOnly 'q' or 'Q' are processed at more "
+				   "prompt, input ignored\n");
+		} else if (kdb_grepping_flag) {
+			/* user hit enter */
+			suspend_grep = 1; /* for this recursion */
+			kdb_printf("\n");
+		}
+		kdb_input_flush();
+	}
+
+	/*
+	 * For grep searches, shift the printed string left.
+	 *  replaced_byte contains the character that was overwritten with
+	 *  the terminating null, and cphold points to the null.
+	 * Then adjust the notion of available space in the buffer.
+	 */
+	if (kdb_grepping_flag && !suspend_grep) {
+		*cphold = replaced_byte;
+		strcpy(kdb_buffer, cphold);
+		len = strlen(kdb_buffer);
+		next_avail = kdb_buffer + len;
+		size_avail = sizeof(kdb_buffer) - len;
+	}
+
+kdb_print_out:
+	suspend_grep = 0; /* end of what may have been a recursive call */
+	if (logging)
+		console_loglevel = saved_loglevel;
+	if (KDB_STATE(PRINTF_LOCK) && got_printf_lock) {
+		got_printf_lock = 0;
+		spin_unlock_irqrestore(&kdb_printf_lock, flags);
+		KDB_STATE_CLEAR(PRINTF_LOCK);
+		atomic_dec(&kdb_event);
+	} else {
+		__release(kdb_printf_lock);
+	}
+	kdb_trap_printk = saved_trap_printk;
+	preempt_enable();
+	return retlen;
+}
+
+int kdb_printf(const char *fmt, ...)
+{
+	va_list ap;
+	int r;
+
+	va_start(ap, fmt);
+	r = vkdb_printf(fmt, ap);
+	va_end(ap);
+
+	return r;
+}
+
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
new file mode 100644
index 00000000000..4bca634975c
--- /dev/null
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -0,0 +1,212 @@
+/*
+ * Kernel Debugger Architecture Dependent Console I/O handler
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.
+ *
+ * Copyright (c) 1999-2006 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ */
+
+#include <linux/kdb.h>
+#include <linux/keyboard.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/io.h>
+
+/* Keyboard Controller Registers on normal PCs. */
+
+#define KBD_STATUS_REG		0x64	/* Status register (R) */
+#define KBD_DATA_REG		0x60	/* Keyboard data register (R/W) */
+
+/* Status Register Bits */
+
+#define KBD_STAT_OBF 		0x01	/* Keyboard output buffer full */
+#define KBD_STAT_MOUSE_OBF	0x20	/* Mouse output buffer full */
+
+static int kbd_exists;
+
+/*
+ * Check if the keyboard controller has a keypress for us.
+ * Some parts (Enter Release, LED change) are still blocking polled here,
+ * but hopefully they are all short.
+ */
+int kdb_get_kbd_char(void)
+{
+	int scancode, scanstatus;
+	static int shift_lock;	/* CAPS LOCK state (0-off, 1-on) */
+	static int shift_key;	/* Shift next keypress */
+	static int ctrl_key;
+	u_short keychar;
+
+	if (KDB_FLAG(NO_I8042) || KDB_FLAG(NO_VT_CONSOLE) ||
+	    (inb(KBD_STATUS_REG) == 0xff && inb(KBD_DATA_REG) == 0xff)) {
+		kbd_exists = 0;
+		return -1;
+	}
+	kbd_exists = 1;
+
+	if ((inb(KBD_STATUS_REG) & KBD_STAT_OBF) == 0)
+		return -1;
+
+	/*
+	 * Fetch the scancode
+	 */
+	scancode = inb(KBD_DATA_REG);
+	scanstatus = inb(KBD_STATUS_REG);
+
+	/*
+	 * Ignore mouse events.
+	 */
+	if (scanstatus & KBD_STAT_MOUSE_OBF)
+		return -1;
+
+	/*
+	 * Ignore release, trigger on make
+	 * (except for shift keys, where we want to
+	 *  keep the shift state so long as the key is
+	 *  held down).
+	 */
+
+	if (((scancode&0x7f) == 0x2a) || ((scancode&0x7f) == 0x36)) {
+		/*
+		 * Next key may use shift table
+		 */
+		if ((scancode & 0x80) == 0)
+			shift_key = 1;
+		else
+			shift_key = 0;
+		return -1;
+	}
+
+	if ((scancode&0x7f) == 0x1d) {
+		/*
+		 * Left ctrl key
+		 */
+		if ((scancode & 0x80) == 0)
+			ctrl_key = 1;
+		else
+			ctrl_key = 0;
+		return -1;
+	}
+
+	if ((scancode & 0x80) != 0)
+		return -1;
+
+	scancode &= 0x7f;
+
+	/*
+	 * Translate scancode
+	 */
+
+	if (scancode == 0x3a) {
+		/*
+		 * Toggle caps lock
+		 */
+		shift_lock ^= 1;
+
+#ifdef	KDB_BLINK_LED
+		kdb_toggleled(0x4);
+#endif
+		return -1;
+	}
+
+	if (scancode == 0x0e) {
+		/*
+		 * Backspace
+		 */
+		return 8;
+	}
+
+	/* Special Key */
+	switch (scancode) {
+	case 0xF: /* Tab */
+		return 9;
+	case 0x53: /* Del */
+		return 4;
+	case 0x47: /* Home */
+		return 1;
+	case 0x4F: /* End */
+		return 5;
+	case 0x4B: /* Left */
+		return 2;
+	case 0x48: /* Up */
+		return 16;
+	case 0x50: /* Down */
+		return 14;
+	case 0x4D: /* Right */
+		return 6;
+	}
+
+	if (scancode == 0xe0)
+		return -1;
+
+	/*
+	 * For Japanese 86/106 keyboards
+	 * 	See comment in drivers/char/pc_keyb.c.
+	 * 	- Masahiro Adegawa
+	 */
+	if (scancode == 0x73)
+		scancode = 0x59;
+	else if (scancode == 0x7d)
+		scancode = 0x7c;
+
+	if (!shift_lock && !shift_key && !ctrl_key) {
+		keychar = plain_map[scancode];
+	} else if ((shift_lock || shift_key) && key_maps[1]) {
+		keychar = key_maps[1][scancode];
+	} else if (ctrl_key && key_maps[4]) {
+		keychar = key_maps[4][scancode];
+	} else {
+		keychar = 0x0020;
+		kdb_printf("Unknown state/scancode (%d)\n", scancode);
+	}
+	keychar &= 0x0fff;
+	if (keychar == '\t')
+		keychar = ' ';
+	switch (KTYP(keychar)) {
+	case KT_LETTER:
+	case KT_LATIN:
+		if (isprint(keychar))
+			break;		/* printable characters */
+		/* drop through */
+	case KT_SPEC:
+		if (keychar == K_ENTER)
+			break;
+		/* drop through */
+	default:
+		return -1;	/* ignore unprintables */
+	}
+
+	if ((scancode & 0x7f) == 0x1c) {
+		/*
+		 * enter key.  All done.  Absorb the release scancode.
+		 */
+		while ((inb(KBD_STATUS_REG) & KBD_STAT_OBF) == 0)
+			;
+
+		/*
+		 * Fetch the scancode
+		 */
+		scancode = inb(KBD_DATA_REG);
+		scanstatus = inb(KBD_STATUS_REG);
+
+		while (scanstatus & KBD_STAT_MOUSE_OBF) {
+			scancode = inb(KBD_DATA_REG);
+			scanstatus = inb(KBD_STATUS_REG);
+		}
+
+		if (scancode != 0x9c) {
+			/*
+			 * Wasn't an enter-release,  why not?
+			 */
+			kdb_printf("kdb: expected enter got 0x%x status 0x%x\n",
+			       scancode, scanstatus);
+		}
+
+		return 13;
+	}
+
+	return keychar & 0xff;
+}
+EXPORT_SYMBOL_GPL(kdb_get_kbd_char);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
new file mode 100644
index 00000000000..b724c791b6d
--- /dev/null
+++ b/kernel/debug/kdb/kdb_main.c
@@ -0,0 +1,2849 @@
+/*
+ * Kernel Debugger Architecture Independent Main Code
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (C) 2000 Stephane Eranian <eranian@hpl.hp.com>
+ * Xscale (R) modifications copyright (C) 2003 Intel Corporation.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ */
+
+#include <linux/ctype.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/sysrq.h>
+#include <linux/smp.h>
+#include <linux/utsname.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/kallsyms.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/notifier.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/nmi.h>
+#include <linux/time.h>
+#include <linux/ptrace.h>
+#include <linux/sysctl.h>
+#include <linux/cpu.h>
+#include <linux/kdebug.h>
+#include <linux/proc_fs.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include "kdb_private.h"
+
+#define GREP_LEN 256
+char kdb_grep_string[GREP_LEN];
+int kdb_grepping_flag;
+EXPORT_SYMBOL(kdb_grepping_flag);
+int kdb_grep_leading;
+int kdb_grep_trailing;
+
+/*
+ * Kernel debugger state flags
+ */
+int kdb_flags;
+atomic_t kdb_event;
+
+/*
+ * kdb_lock protects updates to kdb_initial_cpu.  Used to
+ * single thread processors through the kernel debugger.
+ */
+int kdb_initial_cpu = -1;	/* cpu number that owns kdb */
+int kdb_nextline = 1;
+int kdb_state;			/* General KDB state */
+
+struct task_struct *kdb_current_task;
+EXPORT_SYMBOL(kdb_current_task);
+struct pt_regs *kdb_current_regs;
+
+const char *kdb_diemsg;
+static int kdb_go_count;
+#ifdef CONFIG_KDB_CONTINUE_CATASTROPHIC
+static unsigned int kdb_continue_catastrophic =
+	CONFIG_KDB_CONTINUE_CATASTROPHIC;
+#else
+static unsigned int kdb_continue_catastrophic;
+#endif
+
+/* kdb_commands describes the available commands. */
+static kdbtab_t *kdb_commands;
+#define KDB_BASE_CMD_MAX 50
+static int kdb_max_commands = KDB_BASE_CMD_MAX;
+static kdbtab_t kdb_base_commands[50];
+#define for_each_kdbcmd(cmd, num)					\
+	for ((cmd) = kdb_base_commands, (num) = 0;			\
+	     num < kdb_max_commands;					\
+	     num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++, num++)
+
+typedef struct _kdbmsg {
+	int	km_diag;	/* kdb diagnostic */
+	char	*km_msg;	/* Corresponding message text */
+} kdbmsg_t;
+
+#define KDBMSG(msgnum, text) \
+	{ KDB_##msgnum, text }
+
+static kdbmsg_t kdbmsgs[] = {
+	KDBMSG(NOTFOUND, "Command Not Found"),
+	KDBMSG(ARGCOUNT, "Improper argument count, see usage."),
+	KDBMSG(BADWIDTH, "Illegal value for BYTESPERWORD use 1, 2, 4 or 8, "
+	       "8 is only allowed on 64 bit systems"),
+	KDBMSG(BADRADIX, "Illegal value for RADIX use 8, 10 or 16"),
+	KDBMSG(NOTENV, "Cannot find environment variable"),
+	KDBMSG(NOENVVALUE, "Environment variable should have value"),
+	KDBMSG(NOTIMP, "Command not implemented"),
+	KDBMSG(ENVFULL, "Environment full"),
+	KDBMSG(ENVBUFFULL, "Environment buffer full"),
+	KDBMSG(TOOMANYBPT, "Too many breakpoints defined"),
+#ifdef CONFIG_CPU_XSCALE
+	KDBMSG(TOOMANYDBREGS, "More breakpoints than ibcr registers defined"),
+#else
+	KDBMSG(TOOMANYDBREGS, "More breakpoints than db registers defined"),
+#endif
+	KDBMSG(DUPBPT, "Duplicate breakpoint address"),
+	KDBMSG(BPTNOTFOUND, "Breakpoint not found"),
+	KDBMSG(BADMODE, "Invalid IDMODE"),
+	KDBMSG(BADINT, "Illegal numeric value"),
+	KDBMSG(INVADDRFMT, "Invalid symbolic address format"),
+	KDBMSG(BADREG, "Invalid register name"),
+	KDBMSG(BADCPUNUM, "Invalid cpu number"),
+	KDBMSG(BADLENGTH, "Invalid length field"),
+	KDBMSG(NOBP, "No Breakpoint exists"),
+	KDBMSG(BADADDR, "Invalid address"),
+};
+#undef KDBMSG
+
+static const int __nkdb_err = sizeof(kdbmsgs) / sizeof(kdbmsg_t);
+
+
+/*
+ * Initial environment.   This is all kept static and local to
+ * this file.   We don't want to rely on the memory allocation
+ * mechanisms in the kernel, so we use a very limited allocate-only
+ * heap for new and altered environment variables.  The entire
+ * environment is limited to a fixed number of entries (add more
+ * to __env[] if required) and a fixed amount of heap (add more to
+ * KDB_ENVBUFSIZE if required).
+ */
+
+static char *__env[] = {
+#if defined(CONFIG_SMP)
+ "PROMPT=[%d]kdb> ",
+ "MOREPROMPT=[%d]more> ",
+#else
+ "PROMPT=kdb> ",
+ "MOREPROMPT=more> ",
+#endif
+ "RADIX=16",
+ "MDCOUNT=8",			/* lines of md output */
+ "BTARGS=9",			/* 9 possible args in bt */
+ KDB_PLATFORM_ENV,
+ "DTABCOUNT=30",
+ "NOSECT=1",
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+ (char *)0,
+};
+
+static const int __nenv = (sizeof(__env) / sizeof(char *));
+
+struct task_struct *kdb_curr_task(int cpu)
+{
+	struct task_struct *p = curr_task(cpu);
+#ifdef	_TIF_MCA_INIT
+	if ((task_thread_info(p)->flags & _TIF_MCA_INIT) && KDB_TSK(cpu))
+		p = krp->p;
+#endif
+	return p;
+}
+
+/*
+ * kdbgetenv - This function will return the character string value of
+ *	an environment variable.
+ * Parameters:
+ *	match	A character string representing an environment variable.
+ * Returns:
+ *	NULL	No environment variable matches 'match'
+ *	char*	Pointer to string value of environment variable.
+ */
+char *kdbgetenv(const char *match)
+{
+	char **ep = __env;
+	int matchlen = strlen(match);
+	int i;
+
+	for (i = 0; i < __nenv; i++) {
+		char *e = *ep++;
+
+		if (!e)
+			continue;
+
+		if ((strncmp(match, e, matchlen) == 0)
+		 && ((e[matchlen] == '\0')
+		   || (e[matchlen] == '='))) {
+			char *cp = strchr(e, '=');
+			return cp ? ++cp : "";
+		}
+	}
+	return NULL;
+}
+
+/*
+ * kdballocenv - This function is used to allocate bytes for
+ *	environment entries.
+ * Parameters:
+ *	match	A character string representing a numeric value
+ * Outputs:
+ *	*value  the unsigned long representation of the env variable 'match'
+ * Returns:
+ *	Zero on success, a kdb diagnostic on failure.
+ * Remarks:
+ *	We use a static environment buffer (envbuffer) to hold the values
+ *	of dynamically generated environment variables (see kdb_set).  Buffer
+ *	space once allocated is never free'd, so over time, the amount of space
+ *	(currently 512 bytes) will be exhausted if env variables are changed
+ *	frequently.
+ */
+static char *kdballocenv(size_t bytes)
+{
+#define	KDB_ENVBUFSIZE	512
+	static char envbuffer[KDB_ENVBUFSIZE];
+	static int envbufsize;
+	char *ep = NULL;
+
+	if ((KDB_ENVBUFSIZE - envbufsize) >= bytes) {
+		ep = &envbuffer[envbufsize];
+		envbufsize += bytes;
+	}
+	return ep;
+}
+
+/*
+ * kdbgetulenv - This function will return the value of an unsigned
+ *	long-valued environment variable.
+ * Parameters:
+ *	match	A character string representing a numeric value
+ * Outputs:
+ *	*value  the unsigned long represntation of the env variable 'match'
+ * Returns:
+ *	Zero on success, a kdb diagnostic on failure.
+ */
+static int kdbgetulenv(const char *match, unsigned long *value)
+{
+	char *ep;
+
+	ep = kdbgetenv(match);
+	if (!ep)
+		return KDB_NOTENV;
+	if (strlen(ep) == 0)
+		return KDB_NOENVVALUE;
+
+	*value = simple_strtoul(ep, NULL, 0);
+
+	return 0;
+}
+
+/*
+ * kdbgetintenv - This function will return the value of an
+ *	integer-valued environment variable.
+ * Parameters:
+ *	match	A character string representing an integer-valued env variable
+ * Outputs:
+ *	*value  the integer representation of the environment variable 'match'
+ * Returns:
+ *	Zero on success, a kdb diagnostic on failure.
+ */
+int kdbgetintenv(const char *match, int *value)
+{
+	unsigned long val;
+	int diag;
+
+	diag = kdbgetulenv(match, &val);
+	if (!diag)
+		*value = (int) val;
+	return diag;
+}
+
+/*
+ * kdbgetularg - This function will convert a numeric string into an
+ *	unsigned long value.
+ * Parameters:
+ *	arg	A character string representing a numeric value
+ * Outputs:
+ *	*value  the unsigned long represntation of arg.
+ * Returns:
+ *	Zero on success, a kdb diagnostic on failure.
+ */
+int kdbgetularg(const char *arg, unsigned long *value)
+{
+	char *endp;
+	unsigned long val;
+
+	val = simple_strtoul(arg, &endp, 0);
+
+	if (endp == arg) {
+		/*
+		 * Try base 16, for us folks too lazy to type the
+		 * leading 0x...
+		 */
+		val = simple_strtoul(arg, &endp, 16);
+		if (endp == arg)
+			return KDB_BADINT;
+	}
+
+	*value = val;
+
+	return 0;
+}
+
+/*
+ * kdb_set - This function implements the 'set' command.  Alter an
+ *	existing environment variable or create a new one.
+ */
+int kdb_set(int argc, const char **argv)
+{
+	int i;
+	char *ep;
+	size_t varlen, vallen;
+
+	/*
+	 * we can be invoked two ways:
+	 *   set var=value    argv[1]="var", argv[2]="value"
+	 *   set var = value  argv[1]="var", argv[2]="=", argv[3]="value"
+	 * - if the latter, shift 'em down.
+	 */
+	if (argc == 3) {
+		argv[2] = argv[3];
+		argc--;
+	}
+
+	if (argc != 2)
+		return KDB_ARGCOUNT;
+
+	/*
+	 * Check for internal variables
+	 */
+	if (strcmp(argv[1], "KDBDEBUG") == 0) {
+		unsigned int debugflags;
+		char *cp;
+
+		debugflags = simple_strtoul(argv[2], &cp, 0);
+		if (cp == argv[2] || debugflags & ~KDB_DEBUG_FLAG_MASK) {
+			kdb_printf("kdb: illegal debug flags '%s'\n",
+				    argv[2]);
+			return 0;
+		}
+		kdb_flags = (kdb_flags &
+			     ~(KDB_DEBUG_FLAG_MASK << KDB_DEBUG_FLAG_SHIFT))
+			| (debugflags << KDB_DEBUG_FLAG_SHIFT);
+
+		return 0;
+	}
+
+	/*
+	 * Tokenizer squashed the '=' sign.  argv[1] is variable
+	 * name, argv[2] = value.
+	 */
+	varlen = strlen(argv[1]);
+	vallen = strlen(argv[2]);
+	ep = kdballocenv(varlen + vallen + 2);
+	if (ep == (char *)0)
+		return KDB_ENVBUFFULL;
+
+	sprintf(ep, "%s=%s", argv[1], argv[2]);
+
+	ep[varlen+vallen+1] = '\0';
+
+	for (i = 0; i < __nenv; i++) {
+		if (__env[i]
+		 && ((strncmp(__env[i], argv[1], varlen) == 0)
+		   && ((__env[i][varlen] == '\0')
+		    || (__env[i][varlen] == '=')))) {
+			__env[i] = ep;
+			return 0;
+		}
+	}
+
+	/*
+	 * Wasn't existing variable.  Fit into slot.
+	 */
+	for (i = 0; i < __nenv-1; i++) {
+		if (__env[i] == (char *)0) {
+			__env[i] = ep;
+			return 0;
+		}
+	}
+
+	return KDB_ENVFULL;
+}
+
+static int kdb_check_regs(void)
+{
+	if (!kdb_current_regs) {
+		kdb_printf("No current kdb registers."
+			   "  You may need to select another task\n");
+		return KDB_BADREG;
+	}
+	return 0;
+}
+
+/*
+ * kdbgetaddrarg - This function is responsible for parsing an
+ *	address-expression and returning the value of the expression,
+ *	symbol name, and offset to the caller.
+ *
+ *	The argument may consist of a numeric value (decimal or
+ *	hexidecimal), a symbol name, a register name (preceeded by the
+ *	percent sign), an environment variable with a numeric value
+ *	(preceeded by a dollar sign) or a simple arithmetic expression
+ *	consisting of a symbol name, +/-, and a numeric constant value
+ *	(offset).
+ * Parameters:
+ *	argc	- count of arguments in argv
+ *	argv	- argument vector
+ *	*nextarg - index to next unparsed argument in argv[]
+ *	regs	- Register state at time of KDB entry
+ * Outputs:
+ *	*value	- receives the value of the address-expression
+ *	*offset - receives the offset specified, if any
+ *	*name   - receives the symbol name, if any
+ *	*nextarg - index to next unparsed argument in argv[]
+ * Returns:
+ *	zero is returned on success, a kdb diagnostic code is
+ *      returned on error.
+ */
+int kdbgetaddrarg(int argc, const char **argv, int *nextarg,
+		  unsigned long *value,  long *offset,
+		  char **name)
+{
+	unsigned long addr;
+	unsigned long off = 0;
+	int positive;
+	int diag;
+	int found = 0;
+	char *symname;
+	char symbol = '\0';
+	char *cp;
+	kdb_symtab_t symtab;
+
+	/*
+	 * Process arguments which follow the following syntax:
+	 *
+	 *  symbol | numeric-address [+/- numeric-offset]
+	 *  %register
+	 *  $environment-variable
+	 */
+
+	if (*nextarg > argc)
+		return KDB_ARGCOUNT;
+
+	symname = (char *)argv[*nextarg];
+
+	/*
+	 * If there is no whitespace between the symbol
+	 * or address and the '+' or '-' symbols, we
+	 * remember the character and replace it with a
+	 * null so the symbol/value can be properly parsed
+	 */
+	cp = strpbrk(symname, "+-");
+	if (cp != NULL) {
+		symbol = *cp;
+		*cp++ = '\0';
+	}
+
+	if (symname[0] == '$') {
+		diag = kdbgetulenv(&symname[1], &addr);
+		if (diag)
+			return diag;
+	} else if (symname[0] == '%') {
+		diag = kdb_check_regs();
+		if (diag)
+			return diag;
+		/* Implement register values with % at a later time as it is
+		 * arch optional.
+		 */
+		return KDB_NOTIMP;
+	} else {
+		found = kdbgetsymval(symname, &symtab);
+		if (found) {
+			addr = symtab.sym_start;
+		} else {
+			diag = kdbgetularg(argv[*nextarg], &addr);
+			if (diag)
+				return diag;
+		}
+	}
+
+	if (!found)
+		found = kdbnearsym(addr, &symtab);
+
+	(*nextarg)++;
+
+	if (name)
+		*name = symname;
+	if (value)
+		*value = addr;
+	if (offset && name && *name)
+		*offset = addr - symtab.sym_start;
+
+	if ((*nextarg > argc)
+	 && (symbol == '\0'))
+		return 0;
+
+	/*
+	 * check for +/- and offset
+	 */
+
+	if (symbol == '\0') {
+		if ((argv[*nextarg][0] != '+')
+		 && (argv[*nextarg][0] != '-')) {
+			/*
+			 * Not our argument.  Return.
+			 */
+			return 0;
+		} else {
+			positive = (argv[*nextarg][0] == '+');
+			(*nextarg)++;
+		}
+	} else
+		positive = (symbol == '+');
+
+	/*
+	 * Now there must be an offset!
+	 */
+	if ((*nextarg > argc)
+	 && (symbol == '\0')) {
+		return KDB_INVADDRFMT;
+	}
+
+	if (!symbol) {
+		cp = (char *)argv[*nextarg];
+		(*nextarg)++;
+	}
+
+	diag = kdbgetularg(cp, &off);
+	if (diag)
+		return diag;
+
+	if (!positive)
+		off = -off;
+
+	if (offset)
+		*offset += off;
+
+	if (value)
+		*value += off;
+
+	return 0;
+}
+
+static void kdb_cmderror(int diag)
+{
+	int i;
+
+	if (diag >= 0) {
+		kdb_printf("no error detected (diagnostic is %d)\n", diag);
+		return;
+	}
+
+	for (i = 0; i < __nkdb_err; i++) {
+		if (kdbmsgs[i].km_diag == diag) {
+			kdb_printf("diag: %d: %s\n", diag, kdbmsgs[i].km_msg);
+			return;
+		}
+	}
+
+	kdb_printf("Unknown diag %d\n", -diag);
+}
+
+/*
+ * kdb_defcmd, kdb_defcmd2 - This function implements the 'defcmd'
+ *	command which defines one command as a set of other commands,
+ *	terminated by endefcmd.  kdb_defcmd processes the initial
+ *	'defcmd' command, kdb_defcmd2 is invoked from kdb_parse for
+ *	the following commands until 'endefcmd'.
+ * Inputs:
+ *	argc	argument count
+ *	argv	argument vector
+ * Returns:
+ *	zero for success, a kdb diagnostic if error
+ */
+struct defcmd_set {
+	int count;
+	int usable;
+	char *name;
+	char *usage;
+	char *help;
+	char **command;
+};
+static struct defcmd_set *defcmd_set;
+static int defcmd_set_count;
+static int defcmd_in_progress;
+
+/* Forward references */
+static int kdb_exec_defcmd(int argc, const char **argv);
+
+static int kdb_defcmd2(const char *cmdstr, const char *argv0)
+{
+	struct defcmd_set *s = defcmd_set + defcmd_set_count - 1;
+	char **save_command = s->command;
+	if (strcmp(argv0, "endefcmd") == 0) {
+		defcmd_in_progress = 0;
+		if (!s->count)
+			s->usable = 0;
+		if (s->usable)
+			kdb_register(s->name, kdb_exec_defcmd,
+				     s->usage, s->help, 0);
+		return 0;
+	}
+	if (!s->usable)
+		return KDB_NOTIMP;
+	s->command = kmalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
+	if (!s->command) {
+		kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
+			   cmdstr);
+		s->usable = 0;
+		return KDB_NOTIMP;
+	}
+	memcpy(s->command, save_command, s->count * sizeof(*(s->command)));
+	s->command[s->count++] = kdb_strdup(cmdstr, GFP_KDB);
+	kfree(save_command);
+	return 0;
+}
+
+static int kdb_defcmd(int argc, const char **argv)
+{
+	struct defcmd_set *save_defcmd_set = defcmd_set, *s;
+	if (defcmd_in_progress) {
+		kdb_printf("kdb: nested defcmd detected, assuming missing "
+			   "endefcmd\n");
+		kdb_defcmd2("endefcmd", "endefcmd");
+	}
+	if (argc == 0) {
+		int i;
+		for (s = defcmd_set; s < defcmd_set + defcmd_set_count; ++s) {
+			kdb_printf("defcmd %s \"%s\" \"%s\"\n", s->name,
+				   s->usage, s->help);
+			for (i = 0; i < s->count; ++i)
+				kdb_printf("%s", s->command[i]);
+			kdb_printf("endefcmd\n");
+		}
+		return 0;
+	}
+	if (argc != 3)
+		return KDB_ARGCOUNT;
+	defcmd_set = kmalloc((defcmd_set_count + 1) * sizeof(*defcmd_set),
+			     GFP_KDB);
+	if (!defcmd_set) {
+		kdb_printf("Could not allocate new defcmd_set entry for %s\n",
+			   argv[1]);
+		defcmd_set = save_defcmd_set;
+		return KDB_NOTIMP;
+	}
+	memcpy(defcmd_set, save_defcmd_set,
+	       defcmd_set_count * sizeof(*defcmd_set));
+	kfree(save_defcmd_set);
+	s = defcmd_set + defcmd_set_count;
+	memset(s, 0, sizeof(*s));
+	s->usable = 1;
+	s->name = kdb_strdup(argv[1], GFP_KDB);
+	s->usage = kdb_strdup(argv[2], GFP_KDB);
+	s->help = kdb_strdup(argv[3], GFP_KDB);
+	if (s->usage[0] == '"') {
+		strcpy(s->usage, s->usage+1);
+		s->usage[strlen(s->usage)-1] = '\0';
+	}
+	if (s->help[0] == '"') {
+		strcpy(s->help, s->help+1);
+		s->help[strlen(s->help)-1] = '\0';
+	}
+	++defcmd_set_count;
+	defcmd_in_progress = 1;
+	return 0;
+}
+
+/*
+ * kdb_exec_defcmd - Execute the set of commands associated with this
+ *	defcmd name.
+ * Inputs:
+ *	argc	argument count
+ *	argv	argument vector
+ * Returns:
+ *	zero for success, a kdb diagnostic if error
+ */
+static int kdb_exec_defcmd(int argc, const char **argv)
+{
+	int i, ret;
+	struct defcmd_set *s;
+	if (argc != 0)
+		return KDB_ARGCOUNT;
+	for (s = defcmd_set, i = 0; i < defcmd_set_count; ++i, ++s) {
+		if (strcmp(s->name, argv[0]) == 0)
+			break;
+	}
+	if (i == defcmd_set_count) {
+		kdb_printf("kdb_exec_defcmd: could not find commands for %s\n",
+			   argv[0]);
+		return KDB_NOTIMP;
+	}
+	for (i = 0; i < s->count; ++i) {
+		/* Recursive use of kdb_parse, do not use argv after
+		 * this point */
+		argv = NULL;
+		kdb_printf("[%s]kdb> %s\n", s->name, s->command[i]);
+		ret = kdb_parse(s->command[i]);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/* Command history */
+#define KDB_CMD_HISTORY_COUNT	32
+#define CMD_BUFLEN		200	/* kdb_printf: max printline
+					 * size == 256 */
+static unsigned int cmd_head, cmd_tail;
+static unsigned int cmdptr;
+static char cmd_hist[KDB_CMD_HISTORY_COUNT][CMD_BUFLEN];
+static char cmd_cur[CMD_BUFLEN];
+
+/*
+ * The "str" argument may point to something like  | grep xyz
+ */
+static void parse_grep(const char *str)
+{
+	int	len;
+	char	*cp = (char *)str, *cp2;
+
+	/* sanity check: we should have been called with the \ first */
+	if (*cp != '|')
+		return;
+	cp++;
+	while (isspace(*cp))
+		cp++;
+	if (strncmp(cp, "grep ", 5)) {
+		kdb_printf("invalid 'pipe', see grephelp\n");
+		return;
+	}
+	cp += 5;
+	while (isspace(*cp))
+		cp++;
+	cp2 = strchr(cp, '\n');
+	if (cp2)
+		*cp2 = '\0'; /* remove the trailing newline */
+	len = strlen(cp);
+	if (len == 0) {
+		kdb_printf("invalid 'pipe', see grephelp\n");
+		return;
+	}
+	/* now cp points to a nonzero length search string */
+	if (*cp == '"') {
+		/* allow it be "x y z" by removing the "'s - there must
+		   be two of them */
+		cp++;
+		cp2 = strchr(cp, '"');
+		if (!cp2) {
+			kdb_printf("invalid quoted string, see grephelp\n");
+			return;
+		}
+		*cp2 = '\0'; /* end the string where the 2nd " was */
+	}
+	kdb_grep_leading = 0;
+	if (*cp == '^') {
+		kdb_grep_leading = 1;
+		cp++;
+	}
+	len = strlen(cp);
+	kdb_grep_trailing = 0;
+	if (*(cp+len-1) == '$') {
+		kdb_grep_trailing = 1;
+		*(cp+len-1) = '\0';
+	}
+	len = strlen(cp);
+	if (!len)
+		return;
+	if (len >= GREP_LEN) {
+		kdb_printf("search string too long\n");
+		return;
+	}
+	strcpy(kdb_grep_string, cp);
+	kdb_grepping_flag++;
+	return;
+}
+
+/*
+ * kdb_parse - Parse the command line, search the command table for a
+ *	matching command and invoke the command function.  This
+ *	function may be called recursively, if it is, the second call
+ *	will overwrite argv and cbuf.  It is the caller's
+ *	responsibility to save their argv if they recursively call
+ *	kdb_parse().
+ * Parameters:
+ *      cmdstr	The input command line to be parsed.
+ *	regs	The registers at the time kdb was entered.
+ * Returns:
+ *	Zero for success, a kdb diagnostic if failure.
+ * Remarks:
+ *	Limited to 20 tokens.
+ *
+ *	Real rudimentary tokenization. Basically only whitespace
+ *	is considered a token delimeter (but special consideration
+ *	is taken of the '=' sign as used by the 'set' command).
+ *
+ *	The algorithm used to tokenize the input string relies on
+ *	there being at least one whitespace (or otherwise useless)
+ *	character between tokens as the character immediately following
+ *	the token is altered in-place to a null-byte to terminate the
+ *	token string.
+ */
+
+#define MAXARGC	20
+
+int kdb_parse(const char *cmdstr)
+{
+	static char *argv[MAXARGC];
+	static int argc;
+	static char cbuf[CMD_BUFLEN+2];
+	char *cp;
+	char *cpp, quoted;
+	kdbtab_t *tp;
+	int i, escaped, ignore_errors = 0, check_grep;
+
+	/*
+	 * First tokenize the command string.
+	 */
+	cp = (char *)cmdstr;
+	kdb_grepping_flag = check_grep = 0;
+
+	if (KDB_FLAG(CMD_INTERRUPT)) {
+		/* Previous command was interrupted, newline must not
+		 * repeat the command */
+		KDB_FLAG_CLEAR(CMD_INTERRUPT);
+		KDB_STATE_SET(PAGER);
+		argc = 0;	/* no repeat */
+	}
+
+	if (*cp != '\n' && *cp != '\0') {
+		argc = 0;
+		cpp = cbuf;
+		while (*cp) {
+			/* skip whitespace */
+			while (isspace(*cp))
+				cp++;
+			if ((*cp == '\0') || (*cp == '\n') ||
+			    (*cp == '#' && !defcmd_in_progress))
+				break;
+			/* special case: check for | grep pattern */
+			if (*cp == '|') {
+				check_grep++;
+				break;
+			}
+			if (cpp >= cbuf + CMD_BUFLEN) {
+				kdb_printf("kdb_parse: command buffer "
+					   "overflow, command ignored\n%s\n",
+					   cmdstr);
+				return KDB_NOTFOUND;
+			}
+			if (argc >= MAXARGC - 1) {
+				kdb_printf("kdb_parse: too many arguments, "
+					   "command ignored\n%s\n", cmdstr);
+				return KDB_NOTFOUND;
+			}
+			argv[argc++] = cpp;
+			escaped = 0;
+			quoted = '\0';
+			/* Copy to next unquoted and unescaped
+			 * whitespace or '=' */
+			while (*cp && *cp != '\n' &&
+			       (escaped || quoted || !isspace(*cp))) {
+				if (cpp >= cbuf + CMD_BUFLEN)
+					break;
+				if (escaped) {
+					escaped = 0;
+					*cpp++ = *cp++;
+					continue;
+				}
+				if (*cp == '\\') {
+					escaped = 1;
+					++cp;
+					continue;
+				}
+				if (*cp == quoted)
+					quoted = '\0';
+				else if (*cp == '\'' || *cp == '"')
+					quoted = *cp;
+				*cpp = *cp++;
+				if (*cpp == '=' && !quoted)
+					break;
+				++cpp;
+			}
+			*cpp++ = '\0';	/* Squash a ws or '=' character */
+		}
+	}
+	if (!argc)
+		return 0;
+	if (check_grep)
+		parse_grep(cp);
+	if (defcmd_in_progress) {
+		int result = kdb_defcmd2(cmdstr, argv[0]);
+		if (!defcmd_in_progress) {
+			argc = 0;	/* avoid repeat on endefcmd */
+			*(argv[0]) = '\0';
+		}
+		return result;
+	}
+	if (argv[0][0] == '-' && argv[0][1] &&
+	    (argv[0][1] < '0' || argv[0][1] > '9')) {
+		ignore_errors = 1;
+		++argv[0];
+	}
+
+	for_each_kdbcmd(tp, i) {
+		if (tp->cmd_name) {
+			/*
+			 * If this command is allowed to be abbreviated,
+			 * check to see if this is it.
+			 */
+
+			if (tp->cmd_minlen
+			 && (strlen(argv[0]) <= tp->cmd_minlen)) {
+				if (strncmp(argv[0],
+					    tp->cmd_name,
+					    tp->cmd_minlen) == 0) {
+					break;
+				}
+			}
+
+			if (strcmp(argv[0], tp->cmd_name) == 0)
+				break;
+		}
+	}
+
+	/*
+	 * If we don't find a command by this name, see if the first
+	 * few characters of this match any of the known commands.
+	 * e.g., md1c20 should match md.
+	 */
+	if (i == kdb_max_commands) {
+		for_each_kdbcmd(tp, i) {
+			if (tp->cmd_name) {
+				if (strncmp(argv[0],
+					    tp->cmd_name,
+					    strlen(tp->cmd_name)) == 0) {
+					break;
+				}
+			}
+		}
+	}
+
+	if (i < kdb_max_commands) {
+		int result;
+		KDB_STATE_SET(CMD);
+		result = (*tp->cmd_func)(argc-1, (const char **)argv);
+		if (result && ignore_errors && result > KDB_CMD_GO)
+			result = 0;
+		KDB_STATE_CLEAR(CMD);
+		switch (tp->cmd_repeat) {
+		case KDB_REPEAT_NONE:
+			argc = 0;
+			if (argv[0])
+				*(argv[0]) = '\0';
+			break;
+		case KDB_REPEAT_NO_ARGS:
+			argc = 1;
+			if (argv[1])
+				*(argv[1]) = '\0';
+			break;
+		case KDB_REPEAT_WITH_ARGS:
+			break;
+		}
+		return result;
+	}
+
+	/*
+	 * If the input with which we were presented does not
+	 * map to an existing command, attempt to parse it as an
+	 * address argument and display the result.   Useful for
+	 * obtaining the address of a variable, or the nearest symbol
+	 * to an address contained in a register.
+	 */
+	{
+		unsigned long value;
+		char *name = NULL;
+		long offset;
+		int nextarg = 0;
+
+		if (kdbgetaddrarg(0, (const char **)argv, &nextarg,
+				  &value, &offset, &name)) {
+			return KDB_NOTFOUND;
+		}
+
+		kdb_printf("%s = ", argv[0]);
+		kdb_symbol_print(value, NULL, KDB_SP_DEFAULT);
+		kdb_printf("\n");
+		return 0;
+	}
+}
+
+
+static int handle_ctrl_cmd(char *cmd)
+{
+#define CTRL_P	16
+#define CTRL_N	14
+
+	/* initial situation */
+	if (cmd_head == cmd_tail)
+		return 0;
+	switch (*cmd) {
+	case CTRL_P:
+		if (cmdptr != cmd_tail)
+			cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT;
+		strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
+		return 1;
+	case CTRL_N:
+		if (cmdptr != cmd_head)
+			cmdptr = (cmdptr+1) % KDB_CMD_HISTORY_COUNT;
+		strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * kdb_reboot - This function implements the 'reboot' command.  Reboot
+ *	the system immediately, or loop for ever on failure.
+ */
+static int kdb_reboot(int argc, const char **argv)
+{
+	emergency_restart();
+	kdb_printf("Hmm, kdb_reboot did not reboot, spinning here\n");
+	while (1)
+		cpu_relax();
+	/* NOTREACHED */
+	return 0;
+}
+
+static void kdb_dumpregs(struct pt_regs *regs)
+{
+	int old_lvl = console_loglevel;
+	console_loglevel = 15;
+	kdb_trap_printk++;
+	show_regs(regs);
+	kdb_trap_printk--;
+	kdb_printf("\n");
+	console_loglevel = old_lvl;
+}
+
+void kdb_set_current_task(struct task_struct *p)
+{
+	kdb_current_task = p;
+
+	if (kdb_task_has_cpu(p)) {
+		kdb_current_regs = KDB_TSKREGS(kdb_process_cpu(p));
+		return;
+	}
+	kdb_current_regs = NULL;
+}
+
+/*
+ * kdb_local - The main code for kdb.  This routine is invoked on a
+ *	specific processor, it is not global.  The main kdb() routine
+ *	ensures that only one processor at a time is in this routine.
+ *	This code is called with the real reason code on the first
+ *	entry to a kdb session, thereafter it is called with reason
+ *	SWITCH, even if the user goes back to the original cpu.
+ * Inputs:
+ *	reason		The reason KDB was invoked
+ *	error		The hardware-defined error code
+ *	regs		The exception frame at time of fault/breakpoint.
+ *	db_result	Result code from the break or debug point.
+ * Returns:
+ *	0	KDB was invoked for an event which it wasn't responsible
+ *	1	KDB handled the event for which it was invoked.
+ *	KDB_CMD_GO	User typed 'go'.
+ *	KDB_CMD_CPU	User switched to another cpu.
+ *	KDB_CMD_SS	Single step.
+ *	KDB_CMD_SSB	Single step until branch.
+ */
+static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
+		     kdb_dbtrap_t db_result)
+{
+	char *cmdbuf;
+	int diag;
+	struct task_struct *kdb_current =
+		kdb_curr_task(raw_smp_processor_id());
+
+	KDB_DEBUG_STATE("kdb_local 1", reason);
+	kdb_go_count = 0;
+	if (reason == KDB_REASON_DEBUG) {
+		/* special case below */
+	} else {
+		kdb_printf("\nEntering kdb (current=0x%p, pid %d) ",
+			   kdb_current, kdb_current->pid);
+#if defined(CONFIG_SMP)
+		kdb_printf("on processor %d ", raw_smp_processor_id());
+#endif
+	}
+
+	switch (reason) {
+	case KDB_REASON_DEBUG:
+	{
+		/*
+		 * If re-entering kdb after a single step
+		 * command, don't print the message.
+		 */
+		switch (db_result) {
+		case KDB_DB_BPT:
+			kdb_printf("\nEntering kdb (0x%p, pid %d) ",
+				   kdb_current, kdb_current->pid);
+#if defined(CONFIG_SMP)
+			kdb_printf("on processor %d ", raw_smp_processor_id());
+#endif
+			kdb_printf("due to Debug @ " kdb_machreg_fmt "\n",
+				   instruction_pointer(regs));
+			break;
+		case KDB_DB_SSB:
+			/*
+			 * In the midst of ssb command. Just return.
+			 */
+			KDB_DEBUG_STATE("kdb_local 3", reason);
+			return KDB_CMD_SSB;	/* Continue with SSB command */
+
+			break;
+		case KDB_DB_SS:
+			break;
+		case KDB_DB_SSBPT:
+			KDB_DEBUG_STATE("kdb_local 4", reason);
+			return 1;	/* kdba_db_trap did the work */
+		default:
+			kdb_printf("kdb: Bad result from kdba_db_trap: %d\n",
+				   db_result);
+			break;
+		}
+
+	}
+		break;
+	case KDB_REASON_ENTER:
+		if (KDB_STATE(KEYBOARD))
+			kdb_printf("due to Keyboard Entry\n");
+		else
+			kdb_printf("due to KDB_ENTER()\n");
+		break;
+	case KDB_REASON_KEYBOARD:
+		KDB_STATE_SET(KEYBOARD);
+		kdb_printf("due to Keyboard Entry\n");
+		break;
+	case KDB_REASON_ENTER_SLAVE:
+		/* drop through, slaves only get released via cpu switch */
+	case KDB_REASON_SWITCH:
+		kdb_printf("due to cpu switch\n");
+		break;
+	case KDB_REASON_OOPS:
+		kdb_printf("Oops: %s\n", kdb_diemsg);
+		kdb_printf("due to oops @ " kdb_machreg_fmt "\n",
+			   instruction_pointer(regs));
+		kdb_dumpregs(regs);
+		break;
+	case KDB_REASON_NMI:
+		kdb_printf("due to NonMaskable Interrupt @ "
+			   kdb_machreg_fmt "\n",
+			   instruction_pointer(regs));
+		kdb_dumpregs(regs);
+		break;
+	case KDB_REASON_SSTEP:
+	case KDB_REASON_BREAK:
+		kdb_printf("due to %s @ " kdb_machreg_fmt "\n",
+			   reason == KDB_REASON_BREAK ?
+			   "Breakpoint" : "SS trap", instruction_pointer(regs));
+		/*
+		 * Determine if this breakpoint is one that we
+		 * are interested in.
+		 */
+		if (db_result != KDB_DB_BPT) {
+			kdb_printf("kdb: error return from kdba_bp_trap: %d\n",
+				   db_result);
+			KDB_DEBUG_STATE("kdb_local 6", reason);
+			return 0;	/* Not for us, dismiss it */
+		}
+		break;
+	case KDB_REASON_RECURSE:
+		kdb_printf("due to Recursion @ " kdb_machreg_fmt "\n",
+			   instruction_pointer(regs));
+		break;
+	default:
+		kdb_printf("kdb: unexpected reason code: %d\n", reason);
+		KDB_DEBUG_STATE("kdb_local 8", reason);
+		return 0;	/* Not for us, dismiss it */
+	}
+
+	while (1) {
+		/*
+		 * Initialize pager context.
+		 */
+		kdb_nextline = 1;
+		KDB_STATE_CLEAR(SUPPRESS);
+
+		cmdbuf = cmd_cur;
+		*cmdbuf = '\0';
+		*(cmd_hist[cmd_head]) = '\0';
+
+		if (KDB_FLAG(ONLY_DO_DUMP)) {
+			/* kdb is off but a catastrophic error requires a dump.
+			 * Take the dump and reboot.
+			 * Turn on logging so the kdb output appears in the log
+			 * buffer in the dump.
+			 */
+			const char *setargs[] = { "set", "LOGGING", "1" };
+			kdb_set(2, setargs);
+			kdb_reboot(0, NULL);
+			/*NOTREACHED*/
+		}
+
+do_full_getstr:
+#if defined(CONFIG_SMP)
+		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"),
+			 raw_smp_processor_id());
+#else
+		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"));
+#endif
+		if (defcmd_in_progress)
+			strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN);
+
+		/*
+		 * Fetch command from keyboard
+		 */
+		cmdbuf = kdb_getstr(cmdbuf, CMD_BUFLEN, kdb_prompt_str);
+		if (*cmdbuf != '\n') {
+			if (*cmdbuf < 32) {
+				if (cmdptr == cmd_head) {
+					strncpy(cmd_hist[cmd_head], cmd_cur,
+						CMD_BUFLEN);
+					*(cmd_hist[cmd_head] +
+					  strlen(cmd_hist[cmd_head])-1) = '\0';
+				}
+				if (!handle_ctrl_cmd(cmdbuf))
+					*(cmd_cur+strlen(cmd_cur)-1) = '\0';
+				cmdbuf = cmd_cur;
+				goto do_full_getstr;
+			} else {
+				strncpy(cmd_hist[cmd_head], cmd_cur,
+					CMD_BUFLEN);
+			}
+
+			cmd_head = (cmd_head+1) % KDB_CMD_HISTORY_COUNT;
+			if (cmd_head == cmd_tail)
+				cmd_tail = (cmd_tail+1) % KDB_CMD_HISTORY_COUNT;
+		}
+
+		cmdptr = cmd_head;
+		diag = kdb_parse(cmdbuf);
+		if (diag == KDB_NOTFOUND) {
+			kdb_printf("Unknown kdb command: '%s'\n", cmdbuf);
+			diag = 0;
+		}
+		if (diag == KDB_CMD_GO
+		 || diag == KDB_CMD_CPU
+		 || diag == KDB_CMD_SS
+		 || diag == KDB_CMD_SSB
+		 || diag == KDB_CMD_KGDB)
+			break;
+
+		if (diag)
+			kdb_cmderror(diag);
+	}
+	KDB_DEBUG_STATE("kdb_local 9", diag);
+	return diag;
+}
+
+
+/*
+ * kdb_print_state - Print the state data for the current processor
+ *	for debugging.
+ * Inputs:
+ *	text		Identifies the debug point
+ *	value		Any integer value to be printed, e.g. reason code.
+ */
+void kdb_print_state(const char *text, int value)
+{
+	kdb_printf("state: %s cpu %d value %d initial %d state %x\n",
+		   text, raw_smp_processor_id(), value, kdb_initial_cpu,
+		   kdb_state);
+}
+
+/*
+ * kdb_main_loop - After initial setup and assignment of the
+ *	controlling cpu, all cpus are in this loop.  One cpu is in
+ *	control and will issue the kdb prompt, the others will spin
+ *	until 'go' or cpu switch.
+ *
+ *	To get a consistent view of the kernel stacks for all
+ *	processes, this routine is invoked from the main kdb code via
+ *	an architecture specific routine.  kdba_main_loop is
+ *	responsible for making the kernel stacks consistent for all
+ *	processes, there should be no difference between a blocked
+ *	process and a running process as far as kdb is concerned.
+ * Inputs:
+ *	reason		The reason KDB was invoked
+ *	error		The hardware-defined error code
+ *	reason2		kdb's current reason code.
+ *			Initially error but can change
+ *			acording to kdb state.
+ *	db_result	Result code from break or debug point.
+ *	regs		The exception frame at time of fault/breakpoint.
+ *			should always be valid.
+ * Returns:
+ *	0	KDB was invoked for an event which it wasn't responsible
+ *	1	KDB handled the event for which it was invoked.
+ */
+int kdb_main_loop(kdb_reason_t reason, kdb_reason_t reason2, int error,
+	      kdb_dbtrap_t db_result, struct pt_regs *regs)
+{
+	int result = 1;
+	/* Stay in kdb() until 'go', 'ss[b]' or an error */
+	while (1) {
+		/*
+		 * All processors except the one that is in control
+		 * will spin here.
+		 */
+		KDB_DEBUG_STATE("kdb_main_loop 1", reason);
+		while (KDB_STATE(HOLD_CPU)) {
+			/* state KDB is turned off by kdb_cpu to see if the
+			 * other cpus are still live, each cpu in this loop
+			 * turns it back on.
+			 */
+			if (!KDB_STATE(KDB))
+				KDB_STATE_SET(KDB);
+		}
+
+		KDB_STATE_CLEAR(SUPPRESS);
+		KDB_DEBUG_STATE("kdb_main_loop 2", reason);
+		if (KDB_STATE(LEAVING))
+			break;	/* Another cpu said 'go' */
+		/* Still using kdb, this processor is in control */
+		result = kdb_local(reason2, error, regs, db_result);
+		KDB_DEBUG_STATE("kdb_main_loop 3", result);
+
+		if (result == KDB_CMD_CPU)
+			break;
+
+		if (result == KDB_CMD_SS) {
+			KDB_STATE_SET(DOING_SS);
+			break;
+		}
+
+		if (result == KDB_CMD_SSB) {
+			KDB_STATE_SET(DOING_SS);
+			KDB_STATE_SET(DOING_SSB);
+			break;
+		}
+
+		if (result == KDB_CMD_KGDB) {
+			if (!(KDB_STATE(DOING_KGDB) || KDB_STATE(DOING_KGDB2)))
+				kdb_printf("Entering please attach debugger "
+					   "or use $D#44+ or $3#33\n");
+			break;
+		}
+		if (result && result != 1 && result != KDB_CMD_GO)
+			kdb_printf("\nUnexpected kdb_local return code %d\n",
+				   result);
+		KDB_DEBUG_STATE("kdb_main_loop 4", reason);
+		break;
+	}
+	if (KDB_STATE(DOING_SS))
+		KDB_STATE_CLEAR(SSBPT);
+
+	return result;
+}
+
+/*
+ * kdb_mdr - This function implements the guts of the 'mdr', memory
+ * read command.
+ *	mdr  <addr arg>,<byte count>
+ * Inputs:
+ *	addr	Start address
+ *	count	Number of bytes
+ * Returns:
+ *	Always 0.  Any errors are detected and printed by kdb_getarea.
+ */
+static int kdb_mdr(unsigned long addr, unsigned int count)
+{
+	unsigned char c;
+	while (count--) {
+		if (kdb_getarea(c, addr))
+			return 0;
+		kdb_printf("%02x", c);
+		addr++;
+	}
+	kdb_printf("\n");
+	return 0;
+}
+
+/*
+ * kdb_md - This function implements the 'md', 'md1', 'md2', 'md4',
+ *	'md8' 'mdr' and 'mds' commands.
+ *
+ *	md|mds  [<addr arg> [<line count> [<radix>]]]
+ *	mdWcN	[<addr arg> [<line count> [<radix>]]]
+ *		where W = is the width (1, 2, 4 or 8) and N is the count.
+ *		for eg., md1c20 reads 20 bytes, 1 at a time.
+ *	mdr  <addr arg>,<byte count>
+ */
+static void kdb_md_line(const char *fmtstr, unsigned long addr,
+			int symbolic, int nosect, int bytesperword,
+			int num, int repeat, int phys)
+{
+	/* print just one line of data */
+	kdb_symtab_t symtab;
+	char cbuf[32];
+	char *c = cbuf;
+	int i;
+	unsigned long word;
+
+	memset(cbuf, '\0', sizeof(cbuf));
+	if (phys)
+		kdb_printf("phys " kdb_machreg_fmt0 " ", addr);
+	else
+		kdb_printf(kdb_machreg_fmt0 " ", addr);
+
+	for (i = 0; i < num && repeat--; i++) {
+		if (phys) {
+			if (kdb_getphysword(&word, addr, bytesperword))
+				break;
+		} else if (kdb_getword(&word, addr, bytesperword))
+			break;
+		kdb_printf(fmtstr, word);
+		if (symbolic)
+			kdbnearsym(word, &symtab);
+		else
+			memset(&symtab, 0, sizeof(symtab));
+		if (symtab.sym_name) {
+			kdb_symbol_print(word, &symtab, 0);
+			if (!nosect) {
+				kdb_printf("\n");
+				kdb_printf("                       %s %s "
+					   kdb_machreg_fmt " "
+					   kdb_machreg_fmt " "
+					   kdb_machreg_fmt, symtab.mod_name,
+					   symtab.sec_name, symtab.sec_start,
+					   symtab.sym_start, symtab.sym_end);
+			}
+			addr += bytesperword;
+		} else {
+			union {
+				u64 word;
+				unsigned char c[8];
+			} wc;
+			unsigned char *cp;
+#ifdef	__BIG_ENDIAN
+			cp = wc.c + 8 - bytesperword;
+#else
+			cp = wc.c;
+#endif
+			wc.word = word;
+#define printable_char(c) \
+	({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; })
+			switch (bytesperword) {
+			case 8:
+				*c++ = printable_char(*cp++);
+				*c++ = printable_char(*cp++);
+				*c++ = printable_char(*cp++);
+				*c++ = printable_char(*cp++);
+				addr += 4;
+			case 4:
+				*c++ = printable_char(*cp++);
+				*c++ = printable_char(*cp++);
+				addr += 2;
+			case 2:
+				*c++ = printable_char(*cp++);
+				addr++;
+			case 1:
+				*c++ = printable_char(*cp++);
+				addr++;
+				break;
+			}
+#undef printable_char
+		}
+	}
+	kdb_printf("%*s %s\n", (int)((num-i)*(2*bytesperword + 1)+1),
+		   " ", cbuf);
+}
+
+static int kdb_md(int argc, const char **argv)
+{
+	static unsigned long last_addr;
+	static int last_radix, last_bytesperword, last_repeat;
+	int radix = 16, mdcount = 8, bytesperword = KDB_WORD_SIZE, repeat;
+	int nosect = 0;
+	char fmtchar, fmtstr[64];
+	unsigned long addr;
+	unsigned long word;
+	long offset = 0;
+	int symbolic = 0;
+	int valid = 0;
+	int phys = 0;
+
+	kdbgetintenv("MDCOUNT", &mdcount);
+	kdbgetintenv("RADIX", &radix);
+	kdbgetintenv("BYTESPERWORD", &bytesperword);
+
+	/* Assume 'md <addr>' and start with environment values */
+	repeat = mdcount * 16 / bytesperword;
+
+	if (strcmp(argv[0], "mdr") == 0) {
+		if (argc != 2)
+			return KDB_ARGCOUNT;
+		valid = 1;
+	} else if (isdigit(argv[0][2])) {
+		bytesperword = (int)(argv[0][2] - '0');
+		if (bytesperword == 0) {
+			bytesperword = last_bytesperword;
+			if (bytesperword == 0)
+				bytesperword = 4;
+		}
+		last_bytesperword = bytesperword;
+		repeat = mdcount * 16 / bytesperword;
+		if (!argv[0][3])
+			valid = 1;
+		else if (argv[0][3] == 'c' && argv[0][4]) {
+			char *p;
+			repeat = simple_strtoul(argv[0] + 4, &p, 10);
+			mdcount = ((repeat * bytesperword) + 15) / 16;
+			valid = !*p;
+		}
+		last_repeat = repeat;
+	} else if (strcmp(argv[0], "md") == 0)
+		valid = 1;
+	else if (strcmp(argv[0], "mds") == 0)
+		valid = 1;
+	else if (strcmp(argv[0], "mdp") == 0) {
+		phys = valid = 1;
+	}
+	if (!valid)
+		return KDB_NOTFOUND;
+
+	if (argc == 0) {
+		if (last_addr == 0)
+			return KDB_ARGCOUNT;
+		addr = last_addr;
+		radix = last_radix;
+		bytesperword = last_bytesperword;
+		repeat = last_repeat;
+		mdcount = ((repeat * bytesperword) + 15) / 16;
+	}
+
+	if (argc) {
+		unsigned long val;
+		int diag, nextarg = 1;
+		diag = kdbgetaddrarg(argc, argv, &nextarg, &addr,
+				     &offset, NULL);
+		if (diag)
+			return diag;
+		if (argc > nextarg+2)
+			return KDB_ARGCOUNT;
+
+		if (argc >= nextarg) {
+			diag = kdbgetularg(argv[nextarg], &val);
+			if (!diag) {
+				mdcount = (int) val;
+				repeat = mdcount * 16 / bytesperword;
+			}
+		}
+		if (argc >= nextarg+1) {
+			diag = kdbgetularg(argv[nextarg+1], &val);
+			if (!diag)
+				radix = (int) val;
+		}
+	}
+
+	if (strcmp(argv[0], "mdr") == 0)
+		return kdb_mdr(addr, mdcount);
+
+	switch (radix) {
+	case 10:
+		fmtchar = 'd';
+		break;
+	case 16:
+		fmtchar = 'x';
+		break;
+	case 8:
+		fmtchar = 'o';
+		break;
+	default:
+		return KDB_BADRADIX;
+	}
+
+	last_radix = radix;
+
+	if (bytesperword > KDB_WORD_SIZE)
+		return KDB_BADWIDTH;
+
+	switch (bytesperword) {
+	case 8:
+		sprintf(fmtstr, "%%16.16l%c ", fmtchar);
+		break;
+	case 4:
+		sprintf(fmtstr, "%%8.8l%c ", fmtchar);
+		break;
+	case 2:
+		sprintf(fmtstr, "%%4.4l%c ", fmtchar);
+		break;
+	case 1:
+		sprintf(fmtstr, "%%2.2l%c ", fmtchar);
+		break;
+	default:
+		return KDB_BADWIDTH;
+	}
+
+	last_repeat = repeat;
+	last_bytesperword = bytesperword;
+
+	if (strcmp(argv[0], "mds") == 0) {
+		symbolic = 1;
+		/* Do not save these changes as last_*, they are temporary mds
+		 * overrides.
+		 */
+		bytesperword = KDB_WORD_SIZE;
+		repeat = mdcount;
+		kdbgetintenv("NOSECT", &nosect);
+	}
+
+	/* Round address down modulo BYTESPERWORD */
+
+	addr &= ~(bytesperword-1);
+
+	while (repeat > 0) {
+		unsigned long a;
+		int n, z, num = (symbolic ? 1 : (16 / bytesperword));
+
+		if (KDB_FLAG(CMD_INTERRUPT))
+			return 0;
+		for (a = addr, z = 0; z < repeat; a += bytesperword, ++z) {
+			if (phys) {
+				if (kdb_getphysword(&word, a, bytesperword)
+						|| word)
+					break;
+			} else if (kdb_getword(&word, a, bytesperword) || word)
+				break;
+		}
+		n = min(num, repeat);
+		kdb_md_line(fmtstr, addr, symbolic, nosect, bytesperword,
+			    num, repeat, phys);
+		addr += bytesperword * n;
+		repeat -= n;
+		z = (z + num - 1) / num;
+		if (z > 2) {
+			int s = num * (z-2);
+			kdb_printf(kdb_machreg_fmt0 "-" kdb_machreg_fmt0
+				   " zero suppressed\n",
+				addr, addr + bytesperword * s - 1);
+			addr += bytesperword * s;
+			repeat -= s;
+		}
+	}
+	last_addr = addr;
+
+	return 0;
+}
+
+/*
+ * kdb_mm - This function implements the 'mm' command.
+ *	mm address-expression new-value
+ * Remarks:
+ *	mm works on machine words, mmW works on bytes.
+ */
+static int kdb_mm(int argc, const char **argv)
+{
+	int diag;
+	unsigned long addr;
+	long offset = 0;
+	unsigned long contents;
+	int nextarg;
+	int width;
+
+	if (argv[0][2] && !isdigit(argv[0][2]))
+		return KDB_NOTFOUND;
+
+	if (argc < 2)
+		return KDB_ARGCOUNT;
+
+	nextarg = 1;
+	diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, &offset, NULL);
+	if (diag)
+		return diag;
+
+	if (nextarg > argc)
+		return KDB_ARGCOUNT;
+	diag = kdbgetaddrarg(argc, argv, &nextarg, &contents, NULL, NULL);
+	if (diag)
+		return diag;
+
+	if (nextarg != argc + 1)
+		return KDB_ARGCOUNT;
+
+	width = argv[0][2] ? (argv[0][2] - '0') : (KDB_WORD_SIZE);
+	diag = kdb_putword(addr, contents, width);
+	if (diag)
+		return diag;
+
+	kdb_printf(kdb_machreg_fmt " = " kdb_machreg_fmt "\n", addr, contents);
+
+	return 0;
+}
+
+/*
+ * kdb_go - This function implements the 'go' command.
+ *	go [address-expression]
+ */
+static int kdb_go(int argc, const char **argv)
+{
+	unsigned long addr;
+	int diag;
+	int nextarg;
+	long offset;
+
+	if (argc == 1) {
+		if (raw_smp_processor_id() != kdb_initial_cpu) {
+			kdb_printf("go <address> must be issued from the "
+				   "initial cpu, do cpu %d first\n",
+				   kdb_initial_cpu);
+			return KDB_ARGCOUNT;
+		}
+		nextarg = 1;
+		diag = kdbgetaddrarg(argc, argv, &nextarg,
+				     &addr, &offset, NULL);
+		if (diag)
+			return diag;
+	} else if (argc) {
+		return KDB_ARGCOUNT;
+	}
+
+	diag = KDB_CMD_GO;
+	if (KDB_FLAG(CATASTROPHIC)) {
+		kdb_printf("Catastrophic error detected\n");
+		kdb_printf("kdb_continue_catastrophic=%d, ",
+			kdb_continue_catastrophic);
+		if (kdb_continue_catastrophic == 0 && kdb_go_count++ == 0) {
+			kdb_printf("type go a second time if you really want "
+				   "to continue\n");
+			return 0;
+		}
+		if (kdb_continue_catastrophic == 2) {
+			kdb_printf("forcing reboot\n");
+			kdb_reboot(0, NULL);
+		}
+		kdb_printf("attempting to continue\n");
+	}
+	return diag;
+}
+
+/*
+ * kdb_rd - This function implements the 'rd' command.
+ */
+static int kdb_rd(int argc, const char **argv)
+{
+	int diag = kdb_check_regs();
+	if (diag)
+		return diag;
+
+	kdb_dumpregs(kdb_current_regs);
+	return 0;
+}
+
+/*
+ * kdb_rm - This function implements the 'rm' (register modify)  command.
+ *	rm register-name new-contents
+ * Remarks:
+ *	Currently doesn't allow modification of control or
+ *	debug registers.
+ */
+static int kdb_rm(int argc, const char **argv)
+{
+	int diag;
+	int ind = 0;
+	unsigned long contents;
+
+	if (argc != 2)
+		return KDB_ARGCOUNT;
+	/*
+	 * Allow presence or absence of leading '%' symbol.
+	 */
+	if (argv[1][0] == '%')
+		ind = 1;
+
+	diag = kdbgetularg(argv[2], &contents);
+	if (diag)
+		return diag;
+
+	diag = kdb_check_regs();
+	if (diag)
+		return diag;
+	kdb_printf("ERROR: Register set currently not implemented\n");
+	return 0;
+}
+
+#if defined(CONFIG_MAGIC_SYSRQ)
+/*
+ * kdb_sr - This function implements the 'sr' (SYSRQ key) command
+ *	which interfaces to the soi-disant MAGIC SYSRQ functionality.
+ *		sr <magic-sysrq-code>
+ */
+static int kdb_sr(int argc, const char **argv)
+{
+	if (argc != 1)
+		return KDB_ARGCOUNT;
+	sysrq_toggle_support(1);
+	kdb_trap_printk++;
+	handle_sysrq(*argv[1], NULL);
+	kdb_trap_printk--;
+
+	return 0;
+}
+#endif	/* CONFIG_MAGIC_SYSRQ */
+
+/*
+ * kdb_ef - This function implements the 'regs' (display exception
+ *	frame) command.  This command takes an address and expects to
+ *	find an exception frame at that address, formats and prints
+ *	it.
+ *		regs address-expression
+ * Remarks:
+ *	Not done yet.
+ */
+static int kdb_ef(int argc, const char **argv)
+{
+	int diag;
+	unsigned long addr;
+	long offset;
+	int nextarg;
+
+	if (argc != 1)
+		return KDB_ARGCOUNT;
+
+	nextarg = 1;
+	diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, &offset, NULL);
+	if (diag)
+		return diag;
+	show_regs((struct pt_regs *)addr);
+	return 0;
+}
+
+#if defined(CONFIG_MODULES)
+/* modules using other modules */
+struct module_use {
+	struct list_head list;
+	struct module *module_which_uses;
+};
+
+/*
+ * kdb_lsmod - This function implements the 'lsmod' command.  Lists
+ *	currently loaded kernel modules.
+ *	Mostly taken from userland lsmod.
+ */
+static int kdb_lsmod(int argc, const char **argv)
+{
+	struct module *mod;
+
+	if (argc != 0)
+		return KDB_ARGCOUNT;
+
+	kdb_printf("Module                  Size  modstruct     Used by\n");
+	list_for_each_entry(mod, kdb_modules, list) {
+
+		kdb_printf("%-20s%8u  0x%p ", mod->name,
+			   mod->core_size, (void *)mod);
+#ifdef CONFIG_MODULE_UNLOAD
+		kdb_printf("%4d ", module_refcount(mod));
+#endif
+		if (mod->state == MODULE_STATE_GOING)
+			kdb_printf(" (Unloading)");
+		else if (mod->state == MODULE_STATE_COMING)
+			kdb_printf(" (Loading)");
+		else
+			kdb_printf(" (Live)");
+
+#ifdef CONFIG_MODULE_UNLOAD
+		{
+			struct module_use *use;
+			kdb_printf(" [ ");
+			list_for_each_entry(use, &mod->modules_which_use_me,
+					    list)
+				kdb_printf("%s ", use->module_which_uses->name);
+			kdb_printf("]\n");
+		}
+#endif
+	}
+
+	return 0;
+}
+
+#endif	/* CONFIG_MODULES */
+
+/*
+ * kdb_env - This function implements the 'env' command.  Display the
+ *	current environment variables.
+ */
+
+static int kdb_env(int argc, const char **argv)
+{
+	int i;
+
+	for (i = 0; i < __nenv; i++) {
+		if (__env[i])
+			kdb_printf("%s\n", __env[i]);
+	}
+
+	if (KDB_DEBUG(MASK))
+		kdb_printf("KDBFLAGS=0x%x\n", kdb_flags);
+
+	return 0;
+}
+
+#ifdef CONFIG_PRINTK
+/*
+ * kdb_dmesg - This function implements the 'dmesg' command to display
+ *	the contents of the syslog buffer.
+ *		dmesg [lines] [adjust]
+ */
+static int kdb_dmesg(int argc, const char **argv)
+{
+	char *syslog_data[4], *start, *end, c = '\0', *p;
+	int diag, logging, logsize, lines = 0, adjust = 0, n;
+
+	if (argc > 2)
+		return KDB_ARGCOUNT;
+	if (argc) {
+		char *cp;
+		lines = simple_strtol(argv[1], &cp, 0);
+		if (*cp)
+			lines = 0;
+		if (argc > 1) {
+			adjust = simple_strtoul(argv[2], &cp, 0);
+			if (*cp || adjust < 0)
+				adjust = 0;
+		}
+	}
+
+	/* disable LOGGING if set */
+	diag = kdbgetintenv("LOGGING", &logging);
+	if (!diag && logging) {
+		const char *setargs[] = { "set", "LOGGING", "0" };
+		kdb_set(2, setargs);
+	}
+
+	/* syslog_data[0,1] physical start, end+1.  syslog_data[2,3]
+	 * logical start, end+1. */
+	kdb_syslog_data(syslog_data);
+	if (syslog_data[2] == syslog_data[3])
+		return 0;
+	logsize = syslog_data[1] - syslog_data[0];
+	start = syslog_data[2];
+	end = syslog_data[3];
+#define KDB_WRAP(p) (((p - syslog_data[0]) % logsize) + syslog_data[0])
+	for (n = 0, p = start; p < end; ++p) {
+		c = *KDB_WRAP(p);
+		if (c == '\n')
+			++n;
+	}
+	if (c != '\n')
+		++n;
+	if (lines < 0) {
+		if (adjust >= n)
+			kdb_printf("buffer only contains %d lines, nothing "
+				   "printed\n", n);
+		else if (adjust - lines >= n)
+			kdb_printf("buffer only contains %d lines, last %d "
+				   "lines printed\n", n, n - adjust);
+		if (adjust) {
+			for (; start < end && adjust; ++start) {
+				if (*KDB_WRAP(start) == '\n')
+					--adjust;
+			}
+			if (start < end)
+				++start;
+		}
+		for (p = start; p < end && lines; ++p) {
+			if (*KDB_WRAP(p) == '\n')
+				++lines;
+		}
+		end = p;
+	} else if (lines > 0) {
+		int skip = n - (adjust + lines);
+		if (adjust >= n) {
+			kdb_printf("buffer only contains %d lines, "
+				   "nothing printed\n", n);
+			skip = n;
+		} else if (skip < 0) {
+			lines += skip;
+			skip = 0;
+			kdb_printf("buffer only contains %d lines, first "
+				   "%d lines printed\n", n, lines);
+		}
+		for (; start < end && skip; ++start) {
+			if (*KDB_WRAP(start) == '\n')
+				--skip;
+		}
+		for (p = start; p < end && lines; ++p) {
+			if (*KDB_WRAP(p) == '\n')
+				--lines;
+		}
+		end = p;
+	}
+	/* Do a line at a time (max 200 chars) to reduce protocol overhead */
+	c = '\n';
+	while (start != end) {
+		char buf[201];
+		p = buf;
+		if (KDB_FLAG(CMD_INTERRUPT))
+			return 0;
+		while (start < end && (c = *KDB_WRAP(start)) &&
+		       (p - buf) < sizeof(buf)-1) {
+			++start;
+			*p++ = c;
+			if (c == '\n')
+				break;
+		}
+		*p = '\0';
+		kdb_printf("%s", buf);
+	}
+	if (c != '\n')
+		kdb_printf("\n");
+
+	return 0;
+}
+#endif /* CONFIG_PRINTK */
+/*
+ * kdb_cpu - This function implements the 'cpu' command.
+ *	cpu	[<cpunum>]
+ * Returns:
+ *	KDB_CMD_CPU for success, a kdb diagnostic if error
+ */
+static void kdb_cpu_status(void)
+{
+	int i, start_cpu, first_print = 1;
+	char state, prev_state = '?';
+
+	kdb_printf("Currently on cpu %d\n", raw_smp_processor_id());
+	kdb_printf("Available cpus: ");
+	for (start_cpu = -1, i = 0; i < NR_CPUS; i++) {
+		if (!cpu_online(i)) {
+			state = 'F';	/* cpu is offline */
+		} else {
+			state = ' ';	/* cpu is responding to kdb */
+			if (kdb_task_state_char(KDB_TSK(i)) == 'I')
+				state = 'I';	/* idle task */
+		}
+		if (state != prev_state) {
+			if (prev_state != '?') {
+				if (!first_print)
+					kdb_printf(", ");
+				first_print = 0;
+				kdb_printf("%d", start_cpu);
+				if (start_cpu < i-1)
+					kdb_printf("-%d", i-1);
+				if (prev_state != ' ')
+					kdb_printf("(%c)", prev_state);
+			}
+			prev_state = state;
+			start_cpu = i;
+		}
+	}
+	/* print the trailing cpus, ignoring them if they are all offline */
+	if (prev_state != 'F') {
+		if (!first_print)
+			kdb_printf(", ");
+		kdb_printf("%d", start_cpu);
+		if (start_cpu < i-1)
+			kdb_printf("-%d", i-1);
+		if (prev_state != ' ')
+			kdb_printf("(%c)", prev_state);
+	}
+	kdb_printf("\n");
+}
+
+static int kdb_cpu(int argc, const char **argv)
+{
+	unsigned long cpunum;
+	int diag;
+
+	if (argc == 0) {
+		kdb_cpu_status();
+		return 0;
+	}
+
+	if (argc != 1)
+		return KDB_ARGCOUNT;
+
+	diag = kdbgetularg(argv[1], &cpunum);
+	if (diag)
+		return diag;
+
+	/*
+	 * Validate cpunum
+	 */
+	if ((cpunum > NR_CPUS) || !cpu_online(cpunum))
+		return KDB_BADCPUNUM;
+
+	dbg_switch_cpu = cpunum;
+
+	/*
+	 * Switch to other cpu
+	 */
+	return KDB_CMD_CPU;
+}
+
+/* The user may not realize that ps/bta with no parameters does not print idle
+ * or sleeping system daemon processes, so tell them how many were suppressed.
+ */
+void kdb_ps_suppressed(void)
+{
+	int idle = 0, daemon = 0;
+	unsigned long mask_I = kdb_task_state_string("I"),
+		      mask_M = kdb_task_state_string("M");
+	unsigned long cpu;
+	const struct task_struct *p, *g;
+	for_each_online_cpu(cpu) {
+		p = kdb_curr_task(cpu);
+		if (kdb_task_state(p, mask_I))
+			++idle;
+	}
+	kdb_do_each_thread(g, p) {
+		if (kdb_task_state(p, mask_M))
+			++daemon;
+	} kdb_while_each_thread(g, p);
+	if (idle || daemon) {
+		if (idle)
+			kdb_printf("%d idle process%s (state I)%s\n",
+				   idle, idle == 1 ? "" : "es",
+				   daemon ? " and " : "");
+		if (daemon)
+			kdb_printf("%d sleeping system daemon (state M) "
+				   "process%s", daemon,
+				   daemon == 1 ? "" : "es");
+		kdb_printf(" suppressed,\nuse 'ps A' to see all.\n");
+	}
+}
+
+/*
+ * kdb_ps - This function implements the 'ps' command which shows a
+ *	list of the active processes.
+ *		ps [DRSTCZEUIMA]   All processes, optionally filtered by state
+ */
+void kdb_ps1(const struct task_struct *p)
+{
+	int cpu;
+	unsigned long tmp;
+
+	if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+		return;
+
+	cpu = kdb_process_cpu(p);
+	kdb_printf("0x%p %8d %8d  %d %4d   %c  0x%p %c%s\n",
+		   (void *)p, p->pid, p->parent->pid,
+		   kdb_task_has_cpu(p), kdb_process_cpu(p),
+		   kdb_task_state_char(p),
+		   (void *)(&p->thread),
+		   p == kdb_curr_task(raw_smp_processor_id()) ? '*' : ' ',
+		   p->comm);
+	if (kdb_task_has_cpu(p)) {
+		if (!KDB_TSK(cpu)) {
+			kdb_printf("  Error: no saved data for this cpu\n");
+		} else {
+			if (KDB_TSK(cpu) != p)
+				kdb_printf("  Error: does not match running "
+				   "process table (0x%p)\n", KDB_TSK(cpu));
+		}
+	}
+}
+
+static int kdb_ps(int argc, const char **argv)
+{
+	struct task_struct *g, *p;
+	unsigned long mask, cpu;
+
+	if (argc == 0)
+		kdb_ps_suppressed();
+	kdb_printf("%-*s      Pid   Parent [*] cpu State %-*s Command\n",
+		(int)(2*sizeof(void *))+2, "Task Addr",
+		(int)(2*sizeof(void *))+2, "Thread");
+	mask = kdb_task_state_string(argc ? argv[1] : NULL);
+	/* Run the active tasks first */
+	for_each_online_cpu(cpu) {
+		if (KDB_FLAG(CMD_INTERRUPT))
+			return 0;
+		p = kdb_curr_task(cpu);
+		if (kdb_task_state(p, mask))
+			kdb_ps1(p);
+	}
+	kdb_printf("\n");
+	/* Now the real tasks */
+	kdb_do_each_thread(g, p) {
+		if (KDB_FLAG(CMD_INTERRUPT))
+			return 0;
+		if (kdb_task_state(p, mask))
+			kdb_ps1(p);
+	} kdb_while_each_thread(g, p);
+
+	return 0;
+}
+
+/*
+ * kdb_pid - This function implements the 'pid' command which switches
+ *	the currently active process.
+ *		pid [<pid> | R]
+ */
+static int kdb_pid(int argc, const char **argv)
+{
+	struct task_struct *p;
+	unsigned long val;
+	int diag;
+
+	if (argc > 1)
+		return KDB_ARGCOUNT;
+
+	if (argc) {
+		if (strcmp(argv[1], "R") == 0) {
+			p = KDB_TSK(kdb_initial_cpu);
+		} else {
+			diag = kdbgetularg(argv[1], &val);
+			if (diag)
+				return KDB_BADINT;
+
+			p = find_task_by_pid_ns((pid_t)val,	&init_pid_ns);
+			if (!p) {
+				kdb_printf("No task with pid=%d\n", (pid_t)val);
+				return 0;
+			}
+		}
+		kdb_set_current_task(p);
+	}
+	kdb_printf("KDB current process is %s(pid=%d)\n",
+		   kdb_current_task->comm,
+		   kdb_current_task->pid);
+
+	return 0;
+}
+
+/*
+ * kdb_ll - This function implements the 'll' command which follows a
+ *	linked list and executes an arbitrary command for each
+ *	element.
+ */
+static int kdb_ll(int argc, const char **argv)
+{
+	int diag;
+	unsigned long addr;
+	long offset = 0;
+	unsigned long va;
+	unsigned long linkoffset;
+	int nextarg;
+	const char *command;
+
+	if (argc != 3)
+		return KDB_ARGCOUNT;
+
+	nextarg = 1;
+	diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, &offset, NULL);
+	if (diag)
+		return diag;
+
+	diag = kdbgetularg(argv[2], &linkoffset);
+	if (diag)
+		return diag;
+
+	/*
+	 * Using the starting address as
+	 * the first element in the list, and assuming that
+	 * the list ends with a null pointer.
+	 */
+
+	va = addr;
+	command = kdb_strdup(argv[3], GFP_KDB);
+	if (!command) {
+		kdb_printf("%s: cannot duplicate command\n", __func__);
+		return 0;
+	}
+	/* Recursive use of kdb_parse, do not use argv after this point */
+	argv = NULL;
+
+	while (va) {
+		char buf[80];
+
+		sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
+		diag = kdb_parse(buf);
+		if (diag)
+			return diag;
+
+		addr = va + linkoffset;
+		if (kdb_getword(&va, addr, sizeof(va)))
+			return 0;
+	}
+	kfree(command);
+
+	return 0;
+}
+
+static int kdb_kgdb(int argc, const char **argv)
+{
+	return KDB_CMD_KGDB;
+}
+
+/*
+ * kdb_help - This function implements the 'help' and '?' commands.
+ */
+static int kdb_help(int argc, const char **argv)
+{
+	kdbtab_t *kt;
+	int i;
+
+	kdb_printf("%-15.15s %-20.20s %s\n", "Command", "Usage", "Description");
+	kdb_printf("-----------------------------"
+		   "-----------------------------\n");
+	for_each_kdbcmd(kt, i) {
+		if (kt->cmd_name)
+			kdb_printf("%-15.15s %-20.20s %s\n", kt->cmd_name,
+				   kt->cmd_usage, kt->cmd_help);
+		if (KDB_FLAG(CMD_INTERRUPT))
+			return 0;
+	}
+	return 0;
+}
+
+/*
+ * kdb_kill - This function implements the 'kill' commands.
+ */
+static int kdb_kill(int argc, const char **argv)
+{
+	long sig, pid;
+	char *endp;
+	struct task_struct *p;
+	struct siginfo info;
+
+	if (argc != 2)
+		return KDB_ARGCOUNT;
+
+	sig = simple_strtol(argv[1], &endp, 0);
+	if (*endp)
+		return KDB_BADINT;
+	if (sig >= 0) {
+		kdb_printf("Invalid signal parameter.<-signal>\n");
+		return 0;
+	}
+	sig = -sig;
+
+	pid = simple_strtol(argv[2], &endp, 0);
+	if (*endp)
+		return KDB_BADINT;
+	if (pid <= 0) {
+		kdb_printf("Process ID must be large than 0.\n");
+		return 0;
+	}
+
+	/* Find the process. */
+	p = find_task_by_pid_ns(pid, &init_pid_ns);
+	if (!p) {
+		kdb_printf("The specified process isn't found.\n");
+		return 0;
+	}
+	p = p->group_leader;
+	info.si_signo = sig;
+	info.si_errno = 0;
+	info.si_code = SI_USER;
+	info.si_pid = pid;  /* same capabilities as process being signalled */
+	info.si_uid = 0;    /* kdb has root authority */
+	kdb_send_sig_info(p, &info);
+	return 0;
+}
+
+struct kdb_tm {
+	int tm_sec;	/* seconds */
+	int tm_min;	/* minutes */
+	int tm_hour;	/* hours */
+	int tm_mday;	/* day of the month */
+	int tm_mon;	/* month */
+	int tm_year;	/* year */
+};
+
+static void kdb_gmtime(struct timespec *tv, struct kdb_tm *tm)
+{
+	/* This will work from 1970-2099, 2100 is not a leap year */
+	static int mon_day[] = { 31, 29, 31, 30, 31, 30, 31,
+				 31, 30, 31, 30, 31 };
+	memset(tm, 0, sizeof(*tm));
+	tm->tm_sec  = tv->tv_sec % (24 * 60 * 60);
+	tm->tm_mday = tv->tv_sec / (24 * 60 * 60) +
+		(2 * 365 + 1); /* shift base from 1970 to 1968 */
+	tm->tm_min =  tm->tm_sec / 60 % 60;
+	tm->tm_hour = tm->tm_sec / 60 / 60;
+	tm->tm_sec =  tm->tm_sec % 60;
+	tm->tm_year = 68 + 4*(tm->tm_mday / (4*365+1));
+	tm->tm_mday %= (4*365+1);
+	mon_day[1] = 29;
+	while (tm->tm_mday >= mon_day[tm->tm_mon]) {
+		tm->tm_mday -= mon_day[tm->tm_mon];
+		if (++tm->tm_mon == 12) {
+			tm->tm_mon = 0;
+			++tm->tm_year;
+			mon_day[1] = 28;
+		}
+	}
+	++tm->tm_mday;
+}
+
+/*
+ * Most of this code has been lifted from kernel/timer.c::sys_sysinfo().
+ * I cannot call that code directly from kdb, it has an unconditional
+ * cli()/sti() and calls routines that take locks which can stop the debugger.
+ */
+static void kdb_sysinfo(struct sysinfo *val)
+{
+	struct timespec uptime;
+	do_posix_clock_monotonic_gettime(&uptime);
+	memset(val, 0, sizeof(*val));
+	val->uptime = uptime.tv_sec;
+	val->loads[0] = avenrun[0];
+	val->loads[1] = avenrun[1];
+	val->loads[2] = avenrun[2];
+	val->procs = nr_threads-1;
+	si_meminfo(val);
+
+	return;
+}
+
+/*
+ * kdb_summary - This function implements the 'summary' command.
+ */
+static int kdb_summary(int argc, const char **argv)
+{
+	struct kdb_tm tm;
+	struct sysinfo val;
+
+	if (argc)
+		return KDB_ARGCOUNT;
+
+	kdb_printf("sysname    %s\n", init_uts_ns.name.sysname);
+	kdb_printf("release    %s\n", init_uts_ns.name.release);
+	kdb_printf("version    %s\n", init_uts_ns.name.version);
+	kdb_printf("machine    %s\n", init_uts_ns.name.machine);
+	kdb_printf("nodename   %s\n", init_uts_ns.name.nodename);
+	kdb_printf("domainname %s\n", init_uts_ns.name.domainname);
+	kdb_printf("ccversion  %s\n", __stringify(CCVERSION));
+
+	kdb_gmtime(&xtime, &tm);
+	kdb_printf("date       %04d-%02d-%02d %02d:%02d:%02d "
+		   "tz_minuteswest %d\n",
+		1900+tm.tm_year, tm.tm_mon+1, tm.tm_mday,
+		tm.tm_hour, tm.tm_min, tm.tm_sec,
+		sys_tz.tz_minuteswest);
+
+	kdb_sysinfo(&val);
+	kdb_printf("uptime     ");
+	if (val.uptime > (24*60*60)) {
+		int days = val.uptime / (24*60*60);
+		val.uptime %= (24*60*60);
+		kdb_printf("%d day%s ", days, days == 1 ? "" : "s");
+	}
+	kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60);
+
+	/* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+	kdb_printf("load avg   %ld.%02ld %ld.%02ld %ld.%02ld\n",
+		LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]),
+		LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]),
+		LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2]));
+#undef LOAD_INT
+#undef LOAD_FRAC
+	/* Display in kilobytes */
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+	kdb_printf("\nMemTotal:       %8lu kB\nMemFree:        %8lu kB\n"
+		   "Buffers:        %8lu kB\n",
+		   val.totalram, val.freeram, val.bufferram);
+	return 0;
+}
+
+/*
+ * kdb_per_cpu - This function implements the 'per_cpu' command.
+ */
+static int kdb_per_cpu(int argc, const char **argv)
+{
+	char buf[256], fmtstr[64];
+	kdb_symtab_t symtab;
+	cpumask_t suppress = CPU_MASK_NONE;
+	int cpu, diag;
+	unsigned long addr, val, bytesperword = 0, whichcpu = ~0UL;
+
+	if (argc < 1 || argc > 3)
+		return KDB_ARGCOUNT;
+
+	snprintf(buf, sizeof(buf), "per_cpu__%s", argv[1]);
+	if (!kdbgetsymval(buf, &symtab)) {
+		kdb_printf("%s is not a per_cpu variable\n", argv[1]);
+		return KDB_BADADDR;
+	}
+	if (argc >= 2) {
+		diag = kdbgetularg(argv[2], &bytesperword);
+		if (diag)
+			return diag;
+	}
+	if (!bytesperword)
+		bytesperword = KDB_WORD_SIZE;
+	else if (bytesperword > KDB_WORD_SIZE)
+		return KDB_BADWIDTH;
+	sprintf(fmtstr, "%%0%dlx ", (int)(2*bytesperword));
+	if (argc >= 3) {
+		diag = kdbgetularg(argv[3], &whichcpu);
+		if (diag)
+			return diag;
+		if (!cpu_online(whichcpu)) {
+			kdb_printf("cpu %ld is not online\n", whichcpu);
+			return KDB_BADCPUNUM;
+		}
+	}
+
+	/* Most architectures use __per_cpu_offset[cpu], some use
+	 * __per_cpu_offset(cpu), smp has no __per_cpu_offset.
+	 */
+#ifdef	__per_cpu_offset
+#define KDB_PCU(cpu) __per_cpu_offset(cpu)
+#else
+#ifdef	CONFIG_SMP
+#define KDB_PCU(cpu) __per_cpu_offset[cpu]
+#else
+#define KDB_PCU(cpu) 0
+#endif
+#endif
+
+	for_each_online_cpu(cpu) {
+		if (whichcpu != ~0UL && whichcpu != cpu)
+			continue;
+		addr = symtab.sym_start + KDB_PCU(cpu);
+		diag = kdb_getword(&val, addr, bytesperword);
+		if (diag) {
+			kdb_printf("%5d " kdb_bfd_vma_fmt0 " - unable to "
+				   "read, diag=%d\n", cpu, addr, diag);
+			continue;
+		}
+#ifdef	CONFIG_SMP
+		if (!val) {
+			cpu_set(cpu, suppress);
+			continue;
+		}
+#endif	/* CONFIG_SMP */
+		kdb_printf("%5d ", cpu);
+		kdb_md_line(fmtstr, addr,
+			bytesperword == KDB_WORD_SIZE,
+			1, bytesperword, 1, 1, 0);
+	}
+	if (cpus_weight(suppress) == 0)
+		return 0;
+	kdb_printf("Zero suppressed cpu(s):");
+	for (cpu = first_cpu(suppress); cpu < num_possible_cpus();
+	     cpu = next_cpu(cpu, suppress)) {
+		kdb_printf(" %d", cpu);
+		if (cpu == num_possible_cpus() - 1 ||
+		    next_cpu(cpu, suppress) != cpu + 1)
+			continue;
+		while (cpu < num_possible_cpus() &&
+		       next_cpu(cpu, suppress) == cpu + 1)
+			++cpu;
+		kdb_printf("-%d", cpu);
+	}
+	kdb_printf("\n");
+
+#undef KDB_PCU
+
+	return 0;
+}
+
+/*
+ * display help for the use of cmd | grep pattern
+ */
+static int kdb_grep_help(int argc, const char **argv)
+{
+	kdb_printf("Usage of  cmd args | grep pattern:\n");
+	kdb_printf("  Any command's output may be filtered through an ");
+	kdb_printf("emulated 'pipe'.\n");
+	kdb_printf("  'grep' is just a key word.\n");
+	kdb_printf("  The pattern may include a very limited set of "
+		   "metacharacters:\n");
+	kdb_printf("   pattern or ^pattern or pattern$ or ^pattern$\n");
+	kdb_printf("  And if there are spaces in the pattern, you may "
+		   "quote it:\n");
+	kdb_printf("   \"pat tern\" or \"^pat tern\" or \"pat tern$\""
+		   " or \"^pat tern$\"\n");
+	return 0;
+}
+
+/*
+ * kdb_register_repeat - This function is used to register a kernel
+ * 	debugger command.
+ * Inputs:
+ *	cmd	Command name
+ *	func	Function to execute the command
+ *	usage	A simple usage string showing arguments
+ *	help	A simple help string describing command
+ *	repeat	Does the command auto repeat on enter?
+ * Returns:
+ *	zero for success, one if a duplicate command.
+ */
+#define kdb_command_extend 50	/* arbitrary */
+int kdb_register_repeat(char *cmd,
+			kdb_func_t func,
+			char *usage,
+			char *help,
+			short minlen,
+			kdb_repeat_t repeat)
+{
+	int i;
+	kdbtab_t *kp;
+
+	/*
+	 *  Brute force method to determine duplicates
+	 */
+	for_each_kdbcmd(kp, i) {
+		if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
+			kdb_printf("Duplicate kdb command registered: "
+				"%s, func %p help %s\n", cmd, func, help);
+			return 1;
+		}
+	}
+
+	/*
+	 * Insert command into first available location in table
+	 */
+	for_each_kdbcmd(kp, i) {
+		if (kp->cmd_name == NULL)
+			break;
+	}
+
+	if (i >= kdb_max_commands) {
+		kdbtab_t *new = kmalloc((kdb_max_commands - KDB_BASE_CMD_MAX +
+			 kdb_command_extend) * sizeof(*new), GFP_KDB);
+		if (!new) {
+			kdb_printf("Could not allocate new kdb_command "
+				   "table\n");
+			return 1;
+		}
+		if (kdb_commands) {
+			memcpy(new, kdb_commands,
+			       kdb_max_commands * sizeof(*new));
+			kfree(kdb_commands);
+		}
+		memset(new + kdb_max_commands, 0,
+		       kdb_command_extend * sizeof(*new));
+		kdb_commands = new;
+		kp = kdb_commands + kdb_max_commands;
+		kdb_max_commands += kdb_command_extend;
+	}
+
+	kp->cmd_name   = cmd;
+	kp->cmd_func   = func;
+	kp->cmd_usage  = usage;
+	kp->cmd_help   = help;
+	kp->cmd_flags  = 0;
+	kp->cmd_minlen = minlen;
+	kp->cmd_repeat = repeat;
+
+	return 0;
+}
+
+/*
+ * kdb_register - Compatibility register function for commands that do
+ *	not need to specify a repeat state.  Equivalent to
+ *	kdb_register_repeat with KDB_REPEAT_NONE.
+ * Inputs:
+ *	cmd	Command name
+ *	func	Function to execute the command
+ *	usage	A simple usage string showing arguments
+ *	help	A simple help string describing command
+ * Returns:
+ *	zero for success, one if a duplicate command.
+ */
+int kdb_register(char *cmd,
+	     kdb_func_t func,
+	     char *usage,
+	     char *help,
+	     short minlen)
+{
+	return kdb_register_repeat(cmd, func, usage, help, minlen,
+				   KDB_REPEAT_NONE);
+}
+
+/*
+ * kdb_unregister - This function is used to unregister a kernel
+ *	debugger command.  It is generally called when a module which
+ *	implements kdb commands is unloaded.
+ * Inputs:
+ *	cmd	Command name
+ * Returns:
+ *	zero for success, one command not registered.
+ */
+int kdb_unregister(char *cmd)
+{
+	int i;
+	kdbtab_t *kp;
+
+	/*
+	 *  find the command.
+	 */
+	for (i = 0, kp = kdb_commands; i < kdb_max_commands; i++, kp++) {
+		if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
+			kp->cmd_name = NULL;
+			return 0;
+		}
+	}
+
+	/* Couldn't find it.  */
+	return 1;
+}
+
+/* Initialize the kdb command table. */
+static void __init kdb_inittab(void)
+{
+	int i;
+	kdbtab_t *kp;
+
+	for_each_kdbcmd(kp, i)
+		kp->cmd_name = NULL;
+
+	kdb_register_repeat("md", kdb_md, "<vaddr>",
+	  "Display Memory Contents, also mdWcN, e.g. md8c1", 1,
+			    KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("mdr", kdb_md, "<vaddr> <bytes>",
+	  "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("mdp", kdb_md, "<paddr> <bytes>",
+	  "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("mds", kdb_md, "<vaddr>",
+	  "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("mm", kdb_mm, "<vaddr> <contents>",
+	  "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_repeat("go", kdb_go, "[<vaddr>]",
+	  "Continue Execution", 1, KDB_REPEAT_NONE);
+	kdb_register_repeat("rd", kdb_rd, "",
+	  "Display Registers", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("rm", kdb_rm, "<reg> <contents>",
+	  "Modify Registers", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("ef", kdb_ef, "<vaddr>",
+	  "Display exception frame", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("bt", kdb_bt, "[<vaddr>]",
+	  "Stack traceback", 1, KDB_REPEAT_NONE);
+	kdb_register_repeat("btp", kdb_bt, "<pid>",
+	  "Display stack for process <pid>", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("bta", kdb_bt, "[DRSTCZEUIMA]",
+	  "Display stack all processes", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("btc", kdb_bt, "",
+	  "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("btt", kdb_bt, "<vaddr>",
+	  "Backtrace process given its struct task address", 0,
+			    KDB_REPEAT_NONE);
+	kdb_register_repeat("ll", kdb_ll, "<first-element> <linkoffset> <cmd>",
+	  "Execute cmd for each element in linked list", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("env", kdb_env, "",
+	  "Show environment variables", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("set", kdb_set, "",
+	  "Set environment variables", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("help", kdb_help, "",
+	  "Display Help Message", 1, KDB_REPEAT_NONE);
+	kdb_register_repeat("?", kdb_help, "",
+	  "Display Help Message", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("cpu", kdb_cpu, "<cpunum>",
+	  "Switch to new cpu", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("kgdb", kdb_kgdb, "",
+	  "Enter kgdb mode", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("ps", kdb_ps, "[<flags>|A]",
+	  "Display active task list", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("pid", kdb_pid, "<pidnum>",
+	  "Switch to another task", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("reboot", kdb_reboot, "",
+	  "Reboot the machine immediately", 0, KDB_REPEAT_NONE);
+#if defined(CONFIG_MODULES)
+	kdb_register_repeat("lsmod", kdb_lsmod, "",
+	  "List loaded kernel modules", 0, KDB_REPEAT_NONE);
+#endif
+#if defined(CONFIG_MAGIC_SYSRQ)
+	kdb_register_repeat("sr", kdb_sr, "<key>",
+	  "Magic SysRq key", 0, KDB_REPEAT_NONE);
+#endif
+#if defined(CONFIG_PRINTK)
+	kdb_register_repeat("dmesg", kdb_dmesg, "[lines]",
+	  "Display syslog buffer", 0, KDB_REPEAT_NONE);
+#endif
+	kdb_register_repeat("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
+	  "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("kill", kdb_kill, "<-signal> <pid>",
+	  "Send a signal to a process", 0, KDB_REPEAT_NONE);
+	kdb_register_repeat("summary", kdb_summary, "",
+	  "Summarize the system", 4, KDB_REPEAT_NONE);
+	kdb_register_repeat("per_cpu", kdb_per_cpu, "",
+	  "Display per_cpu variables", 3, KDB_REPEAT_NONE);
+	kdb_register_repeat("grephelp", kdb_grep_help, "",
+	  "Display help on | grep", 0, KDB_REPEAT_NONE);
+}
+
+/* Execute any commands defined in kdb_cmds.  */
+static void __init kdb_cmd_init(void)
+{
+	int i, diag;
+	for (i = 0; kdb_cmds[i]; ++i) {
+		diag = kdb_parse(kdb_cmds[i]);
+		if (diag)
+			kdb_printf("kdb command %s failed, kdb diag %d\n",
+				kdb_cmds[i], diag);
+	}
+	if (defcmd_in_progress) {
+		kdb_printf("Incomplete 'defcmd' set, forcing endefcmd\n");
+		kdb_parse("endefcmd");
+	}
+}
+
+/* Intialize kdb_printf, breakpoint tables and kdb state */
+void __init kdb_init(int lvl)
+{
+	static int kdb_init_lvl = KDB_NOT_INITIALIZED;
+	int i;
+
+	if (kdb_init_lvl == KDB_INIT_FULL || lvl <= kdb_init_lvl)
+		return;
+	for (i = kdb_init_lvl; i < lvl; i++) {
+		switch (i) {
+		case KDB_NOT_INITIALIZED:
+			kdb_inittab();		/* Initialize Command Table */
+			kdb_initbptab();	/* Initialize Breakpoints */
+			break;
+		case KDB_INIT_EARLY:
+			kdb_cmd_init();		/* Build kdb_cmds tables */
+			break;
+		}
+	}
+	kdb_init_lvl = lvl;
+}
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
new file mode 100644
index 00000000000..97d3ba69775
--- /dev/null
+++ b/kernel/debug/kdb/kdb_private.h
@@ -0,0 +1,300 @@
+#ifndef _KDBPRIVATE_H
+#define _KDBPRIVATE_H
+
+/*
+ * Kernel Debugger Architecture Independent Private Headers
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 2000-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ */
+
+#include <linux/kgdb.h>
+#include "../debug_core.h"
+
+/* Kernel Debugger Error codes.  Must not overlap with command codes. */
+#define KDB_NOTFOUND	(-1)
+#define KDB_ARGCOUNT	(-2)
+#define KDB_BADWIDTH	(-3)
+#define KDB_BADRADIX	(-4)
+#define KDB_NOTENV	(-5)
+#define KDB_NOENVVALUE	(-6)
+#define KDB_NOTIMP	(-7)
+#define KDB_ENVFULL	(-8)
+#define KDB_ENVBUFFULL	(-9)
+#define KDB_TOOMANYBPT	(-10)
+#define KDB_TOOMANYDBREGS (-11)
+#define KDB_DUPBPT	(-12)
+#define KDB_BPTNOTFOUND	(-13)
+#define KDB_BADMODE	(-14)
+#define KDB_BADINT	(-15)
+#define KDB_INVADDRFMT  (-16)
+#define KDB_BADREG      (-17)
+#define KDB_BADCPUNUM   (-18)
+#define KDB_BADLENGTH	(-19)
+#define KDB_NOBP	(-20)
+#define KDB_BADADDR	(-21)
+
+/* Kernel Debugger Command codes.  Must not overlap with error codes. */
+#define KDB_CMD_GO	(-1001)
+#define KDB_CMD_CPU	(-1002)
+#define KDB_CMD_SS	(-1003)
+#define KDB_CMD_SSB	(-1004)
+#define KDB_CMD_KGDB (-1005)
+#define KDB_CMD_KGDB2 (-1006)
+
+/* Internal debug flags */
+#define KDB_DEBUG_FLAG_BP	0x0002	/* Breakpoint subsystem debug */
+#define KDB_DEBUG_FLAG_BB_SUMM	0x0004	/* Basic block analysis, summary only */
+#define KDB_DEBUG_FLAG_AR	0x0008	/* Activation record, generic */
+#define KDB_DEBUG_FLAG_ARA	0x0010	/* Activation record, arch specific */
+#define KDB_DEBUG_FLAG_BB	0x0020	/* All basic block analysis */
+#define KDB_DEBUG_FLAG_STATE	0x0040	/* State flags */
+#define KDB_DEBUG_FLAG_MASK	0xffff	/* All debug flags */
+#define KDB_DEBUG_FLAG_SHIFT	16	/* Shift factor for dbflags */
+
+#define KDB_DEBUG(flag)	(kdb_flags & \
+	(KDB_DEBUG_FLAG_##flag << KDB_DEBUG_FLAG_SHIFT))
+#define KDB_DEBUG_STATE(text, value) if (KDB_DEBUG(STATE)) \
+		kdb_print_state(text, value)
+
+#if BITS_PER_LONG == 32
+
+#define KDB_PLATFORM_ENV	"BYTESPERWORD=4"
+
+#define kdb_machreg_fmt		"0x%lx"
+#define kdb_machreg_fmt0	"0x%08lx"
+#define kdb_bfd_vma_fmt		"0x%lx"
+#define kdb_bfd_vma_fmt0	"0x%08lx"
+#define kdb_elfw_addr_fmt	"0x%x"
+#define kdb_elfw_addr_fmt0	"0x%08x"
+#define kdb_f_count_fmt		"%d"
+
+#elif BITS_PER_LONG == 64
+
+#define KDB_PLATFORM_ENV	"BYTESPERWORD=8"
+
+#define kdb_machreg_fmt		"0x%lx"
+#define kdb_machreg_fmt0	"0x%016lx"
+#define kdb_bfd_vma_fmt		"0x%lx"
+#define kdb_bfd_vma_fmt0	"0x%016lx"
+#define kdb_elfw_addr_fmt	"0x%x"
+#define kdb_elfw_addr_fmt0	"0x%016x"
+#define kdb_f_count_fmt		"%ld"
+
+#endif
+
+/*
+ * KDB_MAXBPT describes the total number of breakpoints
+ * supported by this architecure.
+ */
+#define KDB_MAXBPT	16
+
+/* Maximum number of arguments to a function  */
+#define KDB_MAXARGS    16
+
+typedef enum {
+	KDB_REPEAT_NONE = 0,	/* Do not repeat this command */
+	KDB_REPEAT_NO_ARGS,	/* Repeat the command without arguments */
+	KDB_REPEAT_WITH_ARGS,	/* Repeat the command including its arguments */
+} kdb_repeat_t;
+
+typedef int (*kdb_func_t)(int, const char **);
+
+/* Symbol table format returned by kallsyms. */
+typedef struct __ksymtab {
+		unsigned long value;	/* Address of symbol */
+		const char *mod_name;	/* Module containing symbol or
+					 * "kernel" */
+		unsigned long mod_start;
+		unsigned long mod_end;
+		const char *sec_name;	/* Section containing symbol */
+		unsigned long sec_start;
+		unsigned long sec_end;
+		const char *sym_name;	/* Full symbol name, including
+					 * any version */
+		unsigned long sym_start;
+		unsigned long sym_end;
+		} kdb_symtab_t;
+extern int kallsyms_symbol_next(char *prefix_name, int flag);
+extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
+
+/* Exported Symbols for kernel loadable modules to use. */
+extern int kdb_register(char *, kdb_func_t, char *, char *, short);
+extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
+			       short, kdb_repeat_t);
+extern int kdb_unregister(char *);
+
+extern int kdb_getarea_size(void *, unsigned long, size_t);
+extern int kdb_putarea_size(unsigned long, void *, size_t);
+
+/*
+ * Like get_user and put_user, kdb_getarea and kdb_putarea take variable
+ * names, not pointers.  The underlying *_size functions take pointers.
+ */
+#define kdb_getarea(x, addr) kdb_getarea_size(&(x), addr, sizeof((x)))
+#define kdb_putarea(addr, x) kdb_putarea_size(addr, &(x), sizeof((x)))
+
+extern int kdb_getphysword(unsigned long *word,
+			unsigned long addr, size_t size);
+extern int kdb_getword(unsigned long *, unsigned long, size_t);
+extern int kdb_putword(unsigned long, unsigned long, size_t);
+
+extern int kdbgetularg(const char *, unsigned long *);
+extern int kdb_set(int, const char **);
+extern char *kdbgetenv(const char *);
+extern int kdbgetintenv(const char *, int *);
+extern int kdbgetaddrarg(int, const char **, int*, unsigned long *,
+			 long *, char **);
+extern int kdbgetsymval(const char *, kdb_symtab_t *);
+extern int kdbnearsym(unsigned long, kdb_symtab_t *);
+extern void kdbnearsym_cleanup(void);
+extern char *kdb_strdup(const char *str, gfp_t type);
+extern void kdb_symbol_print(unsigned long, const kdb_symtab_t *, unsigned int);
+
+/* Routine for debugging the debugger state. */
+extern void kdb_print_state(const char *, int);
+
+extern int kdb_state;
+#define KDB_STATE_KDB		0x00000001	/* Cpu is inside kdb */
+#define KDB_STATE_LEAVING	0x00000002	/* Cpu is leaving kdb */
+#define KDB_STATE_CMD		0x00000004	/* Running a kdb command */
+#define KDB_STATE_KDB_CONTROL	0x00000008	/* This cpu is under
+						 * kdb control */
+#define KDB_STATE_HOLD_CPU	0x00000010	/* Hold this cpu inside kdb */
+#define KDB_STATE_DOING_SS	0x00000020	/* Doing ss command */
+#define KDB_STATE_DOING_SSB	0x00000040	/* Doing ssb command,
+						 * DOING_SS is also set */
+#define KDB_STATE_SSBPT		0x00000080	/* Install breakpoint
+						 * after one ss, independent of
+						 * DOING_SS */
+#define KDB_STATE_REENTRY	0x00000100	/* Valid re-entry into kdb */
+#define KDB_STATE_SUPPRESS	0x00000200	/* Suppress error messages */
+#define KDB_STATE_PAGER		0x00000400	/* pager is available */
+#define KDB_STATE_GO_SWITCH	0x00000800	/* go is switching
+						 * back to initial cpu */
+#define KDB_STATE_PRINTF_LOCK	0x00001000	/* Holds kdb_printf lock */
+#define KDB_STATE_WAIT_IPI	0x00002000	/* Waiting for kdb_ipi() NMI */
+#define KDB_STATE_RECURSE	0x00004000	/* Recursive entry to kdb */
+#define KDB_STATE_IP_ADJUSTED	0x00008000	/* Restart IP has been
+						 * adjusted */
+#define KDB_STATE_GO1		0x00010000	/* go only releases one cpu */
+#define KDB_STATE_KEYBOARD	0x00020000	/* kdb entered via
+						 * keyboard on this cpu */
+#define KDB_STATE_KEXEC		0x00040000	/* kexec issued */
+#define KDB_STATE_DOING_KGDB	0x00080000	/* kgdb enter now issued */
+#define KDB_STATE_DOING_KGDB2	0x00100000	/* kgdb enter now issued */
+#define KDB_STATE_KGDB_TRANS	0x00200000	/* Transition to kgdb */
+#define KDB_STATE_ARCH		0xff000000	/* Reserved for arch
+						 * specific use */
+
+#define KDB_STATE(flag) (kdb_state & KDB_STATE_##flag)
+#define KDB_STATE_SET(flag) ((void)(kdb_state |= KDB_STATE_##flag))
+#define KDB_STATE_CLEAR(flag) ((void)(kdb_state &= ~KDB_STATE_##flag))
+
+extern int kdb_nextline; /* Current number of lines displayed */
+
+typedef struct _kdb_bp {
+	unsigned long	bp_addr;	/* Address breakpoint is present at */
+	unsigned int	bp_free:1;	/* This entry is available */
+	unsigned int	bp_enabled:1;	/* Breakpoint is active in register */
+	unsigned int	bp_type:4;	/* Uses hardware register */
+	unsigned int	bp_installed:1;	/* Breakpoint is installed */
+	unsigned int	bp_delay:1;	/* Do delayed bp handling */
+	unsigned int	bp_delayed:1;	/* Delayed breakpoint */
+	unsigned int	bph_length;	/* HW break length */
+} kdb_bp_t;
+
+#ifdef CONFIG_KGDB_KDB
+extern kdb_bp_t kdb_breakpoints[/* KDB_MAXBPT */];
+
+/* The KDB shell command table */
+typedef struct _kdbtab {
+	char    *cmd_name;		/* Command name */
+	kdb_func_t cmd_func;		/* Function to execute command */
+	char    *cmd_usage;		/* Usage String for this command */
+	char    *cmd_help;		/* Help message for this command */
+	short    cmd_flags;		/* Parsing flags */
+	short    cmd_minlen;		/* Minimum legal # command
+					 * chars required */
+	kdb_repeat_t cmd_repeat;	/* Does command auto repeat on enter? */
+} kdbtab_t;
+
+extern int kdb_bt(int, const char **);	/* KDB display back trace */
+
+/* KDB breakpoint management functions */
+extern void kdb_initbptab(void);
+extern void kdb_bp_install(struct pt_regs *);
+extern void kdb_bp_remove(void);
+
+typedef enum {
+	KDB_DB_BPT,	/* Breakpoint */
+	KDB_DB_SS,	/* Single-step trap */
+	KDB_DB_SSB,	/* Single step to branch */
+	KDB_DB_SSBPT,	/* Single step over breakpoint */
+	KDB_DB_NOBPT	/* Spurious breakpoint */
+} kdb_dbtrap_t;
+
+extern int kdb_main_loop(kdb_reason_t, kdb_reason_t,
+			 int, kdb_dbtrap_t, struct pt_regs *);
+
+/* Miscellaneous functions and data areas */
+extern int kdb_grepping_flag;
+extern char kdb_grep_string[];
+extern int kdb_grep_leading;
+extern int kdb_grep_trailing;
+extern char *kdb_cmds[];
+extern void kdb_syslog_data(char *syslog_data[]);
+extern unsigned long kdb_task_state_string(const char *);
+extern char kdb_task_state_char (const struct task_struct *);
+extern unsigned long kdb_task_state(const struct task_struct *p,
+				    unsigned long mask);
+extern void kdb_ps_suppressed(void);
+extern void kdb_ps1(const struct task_struct *p);
+extern void kdb_print_nameval(const char *name, unsigned long val);
+extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
+extern void kdb_meminfo_proc_show(void);
+extern const char *kdb_walk_kallsyms(loff_t *pos);
+extern char *kdb_getstr(char *, size_t, char *);
+
+/* Defines for kdb_symbol_print */
+#define KDB_SP_SPACEB	0x0001		/* Space before string */
+#define KDB_SP_SPACEA	0x0002		/* Space after string */
+#define KDB_SP_PAREN	0x0004		/* Parenthesis around string */
+#define KDB_SP_VALUE	0x0008		/* Print the value of the address */
+#define KDB_SP_SYMSIZE	0x0010		/* Print the size of the symbol */
+#define KDB_SP_NEWLINE	0x0020		/* Newline after string */
+#define KDB_SP_DEFAULT (KDB_SP_VALUE|KDB_SP_PAREN)
+
+#define KDB_TSK(cpu) kgdb_info[cpu].task
+#define KDB_TSKREGS(cpu) kgdb_info[cpu].debuggerinfo
+
+extern struct task_struct *kdb_curr_task(int);
+
+#define kdb_task_has_cpu(p) (task_curr(p))
+
+/* Simplify coexistence with NPTL */
+#define	kdb_do_each_thread(g, p) do_each_thread(g, p)
+#define	kdb_while_each_thread(g, p) while_each_thread(g, p)
+
+#define GFP_KDB (in_interrupt() ? GFP_ATOMIC : GFP_KERNEL)
+
+extern void *debug_kmalloc(size_t size, gfp_t flags);
+extern void debug_kfree(void *);
+extern void debug_kusage(void);
+
+extern void kdb_set_current_task(struct task_struct *);
+extern struct task_struct *kdb_current_task;
+#ifdef CONFIG_MODULES
+extern struct list_head *kdb_modules;
+#endif /* CONFIG_MODULES */
+
+extern char kdb_prompt_str[];
+
+#define	KDB_WORD_SIZE	((int)sizeof(unsigned long))
+
+#endif /* CONFIG_KGDB_KDB */
+#endif	/* !_KDBPRIVATE_H */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
new file mode 100644
index 00000000000..45344d5c53d
--- /dev/null
+++ b/kernel/debug/kdb/kdb_support.c
@@ -0,0 +1,927 @@
+/*
+ * Kernel Debugger Architecture Independent Support Functions
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1999-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
+ * 03/02/13    added new 2.5 kallsyms <xavier.bru@bull.net>
+ */
+
+#include <stdarg.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/kallsyms.h>
+#include <linux/stddef.h>
+#include <linux/vmalloc.h>
+#include <linux/ptrace.h>
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <linux/hardirq.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+#include <linux/kdb.h>
+#include <linux/slab.h>
+#include "kdb_private.h"
+
+/*
+ * kdbgetsymval - Return the address of the given symbol.
+ *
+ * Parameters:
+ *	symname	Character string containing symbol name
+ *      symtab  Structure to receive results
+ * Returns:
+ *	0	Symbol not found, symtab zero filled
+ *	1	Symbol mapped to module/symbol/section, data in symtab
+ */
+int kdbgetsymval(const char *symname, kdb_symtab_t *symtab)
+{
+	if (KDB_DEBUG(AR))
+		kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname,
+			   symtab);
+	memset(symtab, 0, sizeof(*symtab));
+	symtab->sym_start = kallsyms_lookup_name(symname);
+	if (symtab->sym_start) {
+		if (KDB_DEBUG(AR))
+			kdb_printf("kdbgetsymval: returns 1, "
+				   "symtab->sym_start=0x%lx\n",
+				   symtab->sym_start);
+		return 1;
+	}
+	if (KDB_DEBUG(AR))
+		kdb_printf("kdbgetsymval: returns 0\n");
+	return 0;
+}
+EXPORT_SYMBOL(kdbgetsymval);
+
+static char *kdb_name_table[100];	/* arbitrary size */
+
+/*
+ * kdbnearsym -	Return the name of the symbol with the nearest address
+ *	less than 'addr'.
+ *
+ * Parameters:
+ *	addr	Address to check for symbol near
+ *	symtab  Structure to receive results
+ * Returns:
+ *	0	No sections contain this address, symtab zero filled
+ *	1	Address mapped to module/symbol/section, data in symtab
+ * Remarks:
+ *	2.6 kallsyms has a "feature" where it unpacks the name into a
+ *	string.  If that string is reused before the caller expects it
+ *	then the caller sees its string change without warning.  To
+ *	avoid cluttering up the main kdb code with lots of kdb_strdup,
+ *	tests and kfree calls, kdbnearsym maintains an LRU list of the
+ *	last few unique strings.  The list is sized large enough to
+ *	hold active strings, no kdb caller of kdbnearsym makes more
+ *	than ~20 later calls before using a saved value.
+ */
+int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
+{
+	int ret = 0;
+	unsigned long symbolsize;
+	unsigned long offset;
+#define knt1_size 128		/* must be >= kallsyms table size */
+	char *knt1 = NULL;
+
+	if (KDB_DEBUG(AR))
+		kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab);
+	memset(symtab, 0, sizeof(*symtab));
+
+	if (addr < 4096)
+		goto out;
+	knt1 = debug_kmalloc(knt1_size, GFP_ATOMIC);
+	if (!knt1) {
+		kdb_printf("kdbnearsym: addr=0x%lx cannot kmalloc knt1\n",
+			   addr);
+		goto out;
+	}
+	symtab->sym_name = kallsyms_lookup(addr, &symbolsize , &offset,
+				(char **)(&symtab->mod_name), knt1);
+	if (offset > 8*1024*1024) {
+		symtab->sym_name = NULL;
+		addr = offset = symbolsize = 0;
+	}
+	symtab->sym_start = addr - offset;
+	symtab->sym_end = symtab->sym_start + symbolsize;
+	ret = symtab->sym_name != NULL && *(symtab->sym_name) != '\0';
+
+	if (ret) {
+		int i;
+		/* Another 2.6 kallsyms "feature".  Sometimes the sym_name is
+		 * set but the buffer passed into kallsyms_lookup is not used,
+		 * so it contains garbage.  The caller has to work out which
+		 * buffer needs to be saved.
+		 *
+		 * What was Rusty smoking when he wrote that code?
+		 */
+		if (symtab->sym_name != knt1) {
+			strncpy(knt1, symtab->sym_name, knt1_size);
+			knt1[knt1_size-1] = '\0';
+		}
+		for (i = 0; i < ARRAY_SIZE(kdb_name_table); ++i) {
+			if (kdb_name_table[i] &&
+			    strcmp(kdb_name_table[i], knt1) == 0)
+				break;
+		}
+		if (i >= ARRAY_SIZE(kdb_name_table)) {
+			debug_kfree(kdb_name_table[0]);
+			memcpy(kdb_name_table, kdb_name_table+1,
+			       sizeof(kdb_name_table[0]) *
+			       (ARRAY_SIZE(kdb_name_table)-1));
+		} else {
+			debug_kfree(knt1);
+			knt1 = kdb_name_table[i];
+			memcpy(kdb_name_table+i, kdb_name_table+i+1,
+			       sizeof(kdb_name_table[0]) *
+			       (ARRAY_SIZE(kdb_name_table)-i-1));
+		}
+		i = ARRAY_SIZE(kdb_name_table) - 1;
+		kdb_name_table[i] = knt1;
+		symtab->sym_name = kdb_name_table[i];
+		knt1 = NULL;
+	}
+
+	if (symtab->mod_name == NULL)
+		symtab->mod_name = "kernel";
+	if (KDB_DEBUG(AR))
+		kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, "
+		   "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret,
+		   symtab->sym_start, symtab->mod_name, symtab->sym_name,
+		   symtab->sym_name);
+
+out:
+	debug_kfree(knt1);
+	return ret;
+}
+
+void kdbnearsym_cleanup(void)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(kdb_name_table); ++i) {
+		if (kdb_name_table[i]) {
+			debug_kfree(kdb_name_table[i]);
+			kdb_name_table[i] = NULL;
+		}
+	}
+}
+
+static char ks_namebuf[KSYM_NAME_LEN+1], ks_namebuf_prev[KSYM_NAME_LEN+1];
+
+/*
+ * kallsyms_symbol_complete
+ *
+ * Parameters:
+ *	prefix_name	prefix of a symbol name to lookup
+ *	max_len		maximum length that can be returned
+ * Returns:
+ *	Number of symbols which match the given prefix.
+ * Notes:
+ *	prefix_name is changed to contain the longest unique prefix that
+ *	starts with this prefix (tab completion).
+ */
+int kallsyms_symbol_complete(char *prefix_name, int max_len)
+{
+	loff_t pos = 0;
+	int prefix_len = strlen(prefix_name), prev_len = 0;
+	int i, number = 0;
+	const char *name;
+
+	while ((name = kdb_walk_kallsyms(&pos))) {
+		if (strncmp(name, prefix_name, prefix_len) == 0) {
+			strcpy(ks_namebuf, name);
+			/* Work out the longest name that matches the prefix */
+			if (++number == 1) {
+				prev_len = min_t(int, max_len-1,
+						 strlen(ks_namebuf));
+				memcpy(ks_namebuf_prev, ks_namebuf, prev_len);
+				ks_namebuf_prev[prev_len] = '\0';
+				continue;
+			}
+			for (i = 0; i < prev_len; i++) {
+				if (ks_namebuf[i] != ks_namebuf_prev[i]) {
+					prev_len = i;
+					ks_namebuf_prev[i] = '\0';
+					break;
+				}
+			}
+		}
+	}
+	if (prev_len > prefix_len)
+		memcpy(prefix_name, ks_namebuf_prev, prev_len+1);
+	return number;
+}
+
+/*
+ * kallsyms_symbol_next
+ *
+ * Parameters:
+ *	prefix_name	prefix of a symbol name to lookup
+ *	flag	0 means search from the head, 1 means continue search.
+ * Returns:
+ *	1 if a symbol matches the given prefix.
+ *	0 if no string found
+ */
+int kallsyms_symbol_next(char *prefix_name, int flag)
+{
+	int prefix_len = strlen(prefix_name);
+	static loff_t pos;
+	const char *name;
+
+	if (!flag)
+		pos = 0;
+
+	while ((name = kdb_walk_kallsyms(&pos))) {
+		if (strncmp(name, prefix_name, prefix_len) == 0) {
+			strncpy(prefix_name, name, strlen(name)+1);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * kdb_symbol_print - Standard method for printing a symbol name and offset.
+ * Inputs:
+ *	addr	Address to be printed.
+ *	symtab	Address of symbol data, if NULL this routine does its
+ *		own lookup.
+ *	punc	Punctuation for string, bit field.
+ * Remarks:
+ *	The string and its punctuation is only printed if the address
+ *	is inside the kernel, except that the value is always printed
+ *	when requested.
+ */
+void kdb_symbol_print(unsigned long addr, const kdb_symtab_t *symtab_p,
+		      unsigned int punc)
+{
+	kdb_symtab_t symtab, *symtab_p2;
+	if (symtab_p) {
+		symtab_p2 = (kdb_symtab_t *)symtab_p;
+	} else {
+		symtab_p2 = &symtab;
+		kdbnearsym(addr, symtab_p2);
+	}
+	if (!(symtab_p2->sym_name || (punc & KDB_SP_VALUE)))
+		return;
+	if (punc & KDB_SP_SPACEB)
+		kdb_printf(" ");
+	if (punc & KDB_SP_VALUE)
+		kdb_printf(kdb_machreg_fmt0, addr);
+	if (symtab_p2->sym_name) {
+		if (punc & KDB_SP_VALUE)
+			kdb_printf(" ");
+		if (punc & KDB_SP_PAREN)
+			kdb_printf("(");
+		if (strcmp(symtab_p2->mod_name, "kernel"))
+			kdb_printf("[%s]", symtab_p2->mod_name);
+		kdb_printf("%s", symtab_p2->sym_name);
+		if (addr != symtab_p2->sym_start)
+			kdb_printf("+0x%lx", addr - symtab_p2->sym_start);
+		if (punc & KDB_SP_SYMSIZE)
+			kdb_printf("/0x%lx",
+				   symtab_p2->sym_end - symtab_p2->sym_start);
+		if (punc & KDB_SP_PAREN)
+			kdb_printf(")");
+	}
+	if (punc & KDB_SP_SPACEA)
+		kdb_printf(" ");
+	if (punc & KDB_SP_NEWLINE)
+		kdb_printf("\n");
+}
+
+/*
+ * kdb_strdup - kdb equivalent of strdup, for disasm code.
+ * Inputs:
+ *	str	The string to duplicate.
+ *	type	Flags to kmalloc for the new string.
+ * Returns:
+ *	Address of the new string, NULL if storage could not be allocated.
+ * Remarks:
+ *	This is not in lib/string.c because it uses kmalloc which is not
+ *	available when string.o is used in boot loaders.
+ */
+char *kdb_strdup(const char *str, gfp_t type)
+{
+	int n = strlen(str)+1;
+	char *s = kmalloc(n, type);
+	if (!s)
+		return NULL;
+	return strcpy(s, str);
+}
+
+/*
+ * kdb_getarea_size - Read an area of data.  The kdb equivalent of
+ *	copy_from_user, with kdb messages for invalid addresses.
+ * Inputs:
+ *	res	Pointer to the area to receive the result.
+ *	addr	Address of the area to copy.
+ *	size	Size of the area.
+ * Returns:
+ *	0 for success, < 0 for error.
+ */
+int kdb_getarea_size(void *res, unsigned long addr, size_t size)
+{
+	int ret = probe_kernel_read((char *)res, (char *)addr, size);
+	if (ret) {
+		if (!KDB_STATE(SUPPRESS)) {
+			kdb_printf("kdb_getarea: Bad address 0x%lx\n", addr);
+			KDB_STATE_SET(SUPPRESS);
+		}
+		ret = KDB_BADADDR;
+	} else {
+		KDB_STATE_CLEAR(SUPPRESS);
+	}
+	return ret;
+}
+
+/*
+ * kdb_putarea_size - Write an area of data.  The kdb equivalent of
+ *	copy_to_user, with kdb messages for invalid addresses.
+ * Inputs:
+ *	addr	Address of the area to write to.
+ *	res	Pointer to the area holding the data.
+ *	size	Size of the area.
+ * Returns:
+ *	0 for success, < 0 for error.
+ */
+int kdb_putarea_size(unsigned long addr, void *res, size_t size)
+{
+	int ret = probe_kernel_read((char *)addr, (char *)res, size);
+	if (ret) {
+		if (!KDB_STATE(SUPPRESS)) {
+			kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr);
+			KDB_STATE_SET(SUPPRESS);
+		}
+		ret = KDB_BADADDR;
+	} else {
+		KDB_STATE_CLEAR(SUPPRESS);
+	}
+	return ret;
+}
+
+/*
+ * kdb_getphys - Read data from a physical address. Validate the
+ * 	address is in range, use kmap_atomic() to get data
+ * 	similar to kdb_getarea() - but for phys addresses
+ * Inputs:
+ * 	res	Pointer to the word to receive the result
+ * 	addr	Physical address of the area to copy
+ * 	size	Size of the area
+ * Returns:
+ *	0 for success, < 0 for error.
+ */
+static int kdb_getphys(void *res, unsigned long addr, size_t size)
+{
+	unsigned long pfn;
+	void *vaddr;
+	struct page *page;
+
+	pfn = (addr >> PAGE_SHIFT);
+	if (!pfn_valid(pfn))
+		return 1;
+	page = pfn_to_page(pfn);
+	vaddr = kmap_atomic(page, KM_KDB);
+	memcpy(res, vaddr + (addr & (PAGE_SIZE - 1)), size);
+	kunmap_atomic(vaddr, KM_KDB);
+
+	return 0;
+}
+
+/*
+ * kdb_getphysword
+ * Inputs:
+ *	word	Pointer to the word to receive the result.
+ *	addr	Address of the area to copy.
+ *	size	Size of the area.
+ * Returns:
+ *	0 for success, < 0 for error.
+ */
+int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size)
+{
+	int diag;
+	__u8  w1;
+	__u16 w2;
+	__u32 w4;
+	__u64 w8;
+	*word = 0;	/* Default value if addr or size is invalid */
+
+	switch (size) {
+	case 1:
+		diag = kdb_getphys(&w1, addr, sizeof(w1));
+		if (!diag)
+			*word = w1;
+		break;
+	case 2:
+		diag = kdb_getphys(&w2, addr, sizeof(w2));
+		if (!diag)
+			*word = w2;
+		break;
+	case 4:
+		diag = kdb_getphys(&w4, addr, sizeof(w4));
+		if (!diag)
+			*word = w4;
+		break;
+	case 8:
+		if (size <= sizeof(*word)) {
+			diag = kdb_getphys(&w8, addr, sizeof(w8));
+			if (!diag)
+				*word = w8;
+			break;
+		}
+		/* drop through */
+	default:
+		diag = KDB_BADWIDTH;
+		kdb_printf("kdb_getphysword: bad width %ld\n", (long) size);
+	}
+	return diag;
+}
+
+/*
+ * kdb_getword - Read a binary value.  Unlike kdb_getarea, this treats
+ *	data as numbers.
+ * Inputs:
+ *	word	Pointer to the word to receive the result.
+ *	addr	Address of the area to copy.
+ *	size	Size of the area.
+ * Returns:
+ *	0 for success, < 0 for error.
+ */
+int kdb_getword(unsigned long *word, unsigned long addr, size_t size)
+{
+	int diag;
+	__u8  w1;
+	__u16 w2;
+	__u32 w4;
+	__u64 w8;
+	*word = 0;	/* Default value if addr or size is invalid */
+	switch (size) {
+	case 1:
+		diag = kdb_getarea(w1, addr);
+		if (!diag)
+			*word = w1;
+		break;
+	case 2:
+		diag = kdb_getarea(w2, addr);
+		if (!diag)
+			*word = w2;
+		break;
+	case 4:
+		diag = kdb_getarea(w4, addr);
+		if (!diag)
+			*word = w4;
+		break;
+	case 8:
+		if (size <= sizeof(*word)) {
+			diag = kdb_getarea(w8, addr);
+			if (!diag)
+				*word = w8;
+			break;
+		}
+		/* drop through */
+	default:
+		diag = KDB_BADWIDTH;
+		kdb_printf("kdb_getword: bad width %ld\n", (long) size);
+	}
+	return diag;
+}
+
+/*
+ * kdb_putword - Write a binary value.  Unlike kdb_putarea, this
+ *	treats data as numbers.
+ * Inputs:
+ *	addr	Address of the area to write to..
+ *	word	The value to set.
+ *	size	Size of the area.
+ * Returns:
+ *	0 for success, < 0 for error.
+ */
+int kdb_putword(unsigned long addr, unsigned long word, size_t size)
+{
+	int diag;
+	__u8  w1;
+	__u16 w2;
+	__u32 w4;
+	__u64 w8;
+	switch (size) {
+	case 1:
+		w1 = word;
+		diag = kdb_putarea(addr, w1);
+		break;
+	case 2:
+		w2 = word;
+		diag = kdb_putarea(addr, w2);
+		break;
+	case 4:
+		w4 = word;
+		diag = kdb_putarea(addr, w4);
+		break;
+	case 8:
+		if (size <= sizeof(word)) {
+			w8 = word;
+			diag = kdb_putarea(addr, w8);
+			break;
+		}
+		/* drop through */
+	default:
+		diag = KDB_BADWIDTH;
+		kdb_printf("kdb_putword: bad width %ld\n", (long) size);
+	}
+	return diag;
+}
+
+/*
+ * kdb_task_state_string - Convert a string containing any of the
+ *	letters DRSTCZEUIMA to a mask for the process state field and
+ *	return the value.  If no argument is supplied, return the mask
+ *	that corresponds to environment variable PS, DRSTCZEU by
+ *	default.
+ * Inputs:
+ *	s	String to convert
+ * Returns:
+ *	Mask for process state.
+ * Notes:
+ *	The mask folds data from several sources into a single long value, so
+ *	be carefull not to overlap the bits.  TASK_* bits are in the LSB,
+ *	special cases like UNRUNNABLE are in the MSB.  As of 2.6.10-rc1 there
+ *	is no overlap between TASK_* and EXIT_* but that may not always be
+ *	true, so EXIT_* bits are shifted left 16 bits before being stored in
+ *	the mask.
+ */
+
+/* unrunnable is < 0 */
+#define UNRUNNABLE	(1UL << (8*sizeof(unsigned long) - 1))
+#define RUNNING		(1UL << (8*sizeof(unsigned long) - 2))
+#define IDLE		(1UL << (8*sizeof(unsigned long) - 3))
+#define DAEMON		(1UL << (8*sizeof(unsigned long) - 4))
+
+unsigned long kdb_task_state_string(const char *s)
+{
+	long res = 0;
+	if (!s) {
+		s = kdbgetenv("PS");
+		if (!s)
+			s = "DRSTCZEU";	/* default value for ps */
+	}
+	while (*s) {
+		switch (*s) {
+		case 'D':
+			res |= TASK_UNINTERRUPTIBLE;
+			break;
+		case 'R':
+			res |= RUNNING;
+			break;
+		case 'S':
+			res |= TASK_INTERRUPTIBLE;
+			break;
+		case 'T':
+			res |= TASK_STOPPED;
+			break;
+		case 'C':
+			res |= TASK_TRACED;
+			break;
+		case 'Z':
+			res |= EXIT_ZOMBIE << 16;
+			break;
+		case 'E':
+			res |= EXIT_DEAD << 16;
+			break;
+		case 'U':
+			res |= UNRUNNABLE;
+			break;
+		case 'I':
+			res |= IDLE;
+			break;
+		case 'M':
+			res |= DAEMON;
+			break;
+		case 'A':
+			res = ~0UL;
+			break;
+		default:
+			  kdb_printf("%s: unknown flag '%c' ignored\n",
+				     __func__, *s);
+			  break;
+		}
+		++s;
+	}
+	return res;
+}
+
+/*
+ * kdb_task_state_char - Return the character that represents the task state.
+ * Inputs:
+ *	p	struct task for the process
+ * Returns:
+ *	One character to represent the task state.
+ */
+char kdb_task_state_char (const struct task_struct *p)
+{
+	int cpu;
+	char state;
+	unsigned long tmp;
+
+	if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+		return 'E';
+
+	cpu = kdb_process_cpu(p);
+	state = (p->state == 0) ? 'R' :
+		(p->state < 0) ? 'U' :
+		(p->state & TASK_UNINTERRUPTIBLE) ? 'D' :
+		(p->state & TASK_STOPPED) ? 'T' :
+		(p->state & TASK_TRACED) ? 'C' :
+		(p->exit_state & EXIT_ZOMBIE) ? 'Z' :
+		(p->exit_state & EXIT_DEAD) ? 'E' :
+		(p->state & TASK_INTERRUPTIBLE) ? 'S' : '?';
+	if (p->pid == 0) {
+		/* Idle task.  Is it really idle, apart from the kdb
+		 * interrupt? */
+		if (!kdb_task_has_cpu(p) || kgdb_info[cpu].irq_depth == 1) {
+			if (cpu != kdb_initial_cpu)
+				state = 'I';	/* idle task */
+		}
+	} else if (!p->mm && state == 'S') {
+		state = 'M';	/* sleeping system daemon */
+	}
+	return state;
+}
+
+/*
+ * kdb_task_state - Return true if a process has the desired state
+ *	given by the mask.
+ * Inputs:
+ *	p	struct task for the process
+ *	mask	mask from kdb_task_state_string to select processes
+ * Returns:
+ *	True if the process matches at least one criteria defined by the mask.
+ */
+unsigned long kdb_task_state(const struct task_struct *p, unsigned long mask)
+{
+	char state[] = { kdb_task_state_char(p), '\0' };
+	return (mask & kdb_task_state_string(state)) != 0;
+}
+
+/*
+ * kdb_print_nameval - Print a name and its value, converting the
+ *	value to a symbol lookup if possible.
+ * Inputs:
+ *	name	field name to print
+ *	val	value of field
+ */
+void kdb_print_nameval(const char *name, unsigned long val)
+{
+	kdb_symtab_t symtab;
+	kdb_printf("  %-11.11s ", name);
+	if (kdbnearsym(val, &symtab))
+		kdb_symbol_print(val, &symtab,
+				 KDB_SP_VALUE|KDB_SP_SYMSIZE|KDB_SP_NEWLINE);
+	else
+		kdb_printf("0x%lx\n", val);
+}
+
+/* Last ditch allocator for debugging, so we can still debug even when
+ * the GFP_ATOMIC pool has been exhausted.  The algorithms are tuned
+ * for space usage, not for speed.  One smallish memory pool, the free
+ * chain is always in ascending address order to allow coalescing,
+ * allocations are done in brute force best fit.
+ */
+
+struct debug_alloc_header {
+	u32 next;	/* offset of next header from start of pool */
+	u32 size;
+	void *caller;
+};
+
+/* The memory returned by this allocator must be aligned, which means
+ * so must the header size.  Do not assume that sizeof(struct
+ * debug_alloc_header) is a multiple of the alignment, explicitly
+ * calculate the overhead of this header, including the alignment.
+ * The rest of this code must not use sizeof() on any header or
+ * pointer to a header.
+ */
+#define dah_align 8
+#define dah_overhead ALIGN(sizeof(struct debug_alloc_header), dah_align)
+
+static u64 debug_alloc_pool_aligned[256*1024/dah_align];	/* 256K pool */
+static char *debug_alloc_pool = (char *)debug_alloc_pool_aligned;
+static u32 dah_first, dah_first_call = 1, dah_used, dah_used_max;
+
+/* Locking is awkward.  The debug code is called from all contexts,
+ * including non maskable interrupts.  A normal spinlock is not safe
+ * in NMI context.  Try to get the debug allocator lock, if it cannot
+ * be obtained after a second then give up.  If the lock could not be
+ * previously obtained on this cpu then only try once.
+ *
+ * sparse has no annotation for "this function _sometimes_ acquires a
+ * lock", so fudge the acquire/release notation.
+ */
+static DEFINE_SPINLOCK(dap_lock);
+static int get_dap_lock(void)
+	__acquires(dap_lock)
+{
+	static int dap_locked = -1;
+	int count;
+	if (dap_locked == smp_processor_id())
+		count = 1;
+	else
+		count = 1000;
+	while (1) {
+		if (spin_trylock(&dap_lock)) {
+			dap_locked = -1;
+			return 1;
+		}
+		if (!count--)
+			break;
+		udelay(1000);
+	}
+	dap_locked = smp_processor_id();
+	__acquire(dap_lock);
+	return 0;
+}
+
+void *debug_kmalloc(size_t size, gfp_t flags)
+{
+	unsigned int rem, h_offset;
+	struct debug_alloc_header *best, *bestprev, *prev, *h;
+	void *p = NULL;
+	if (!get_dap_lock()) {
+		__release(dap_lock);	/* we never actually got it */
+		return NULL;
+	}
+	h = (struct debug_alloc_header *)(debug_alloc_pool + dah_first);
+	if (dah_first_call) {
+		h->size = sizeof(debug_alloc_pool_aligned) - dah_overhead;
+		dah_first_call = 0;
+	}
+	size = ALIGN(size, dah_align);
+	prev = best = bestprev = NULL;
+	while (1) {
+		if (h->size >= size && (!best || h->size < best->size)) {
+			best = h;
+			bestprev = prev;
+			if (h->size == size)
+				break;
+		}
+		if (!h->next)
+			break;
+		prev = h;
+		h = (struct debug_alloc_header *)(debug_alloc_pool + h->next);
+	}
+	if (!best)
+		goto out;
+	rem = best->size - size;
+	/* The pool must always contain at least one header */
+	if (best->next == 0 && bestprev == NULL && rem < dah_overhead)
+		goto out;
+	if (rem >= dah_overhead) {
+		best->size = size;
+		h_offset = ((char *)best - debug_alloc_pool) +
+			   dah_overhead + best->size;
+		h = (struct debug_alloc_header *)(debug_alloc_pool + h_offset);
+		h->size = rem - dah_overhead;
+		h->next = best->next;
+	} else
+		h_offset = best->next;
+	best->caller = __builtin_return_address(0);
+	dah_used += best->size;
+	dah_used_max = max(dah_used, dah_used_max);
+	if (bestprev)
+		bestprev->next = h_offset;
+	else
+		dah_first = h_offset;
+	p = (char *)best + dah_overhead;
+	memset(p, POISON_INUSE, best->size - 1);
+	*((char *)p + best->size - 1) = POISON_END;
+out:
+	spin_unlock(&dap_lock);
+	return p;
+}
+
+void debug_kfree(void *p)
+{
+	struct debug_alloc_header *h;
+	unsigned int h_offset;
+	if (!p)
+		return;
+	if ((char *)p < debug_alloc_pool ||
+	    (char *)p >= debug_alloc_pool + sizeof(debug_alloc_pool_aligned)) {
+		kfree(p);
+		return;
+	}
+	if (!get_dap_lock()) {
+		__release(dap_lock);	/* we never actually got it */
+		return;		/* memory leak, cannot be helped */
+	}
+	h = (struct debug_alloc_header *)((char *)p - dah_overhead);
+	memset(p, POISON_FREE, h->size - 1);
+	*((char *)p + h->size - 1) = POISON_END;
+	h->caller = NULL;
+	dah_used -= h->size;
+	h_offset = (char *)h - debug_alloc_pool;
+	if (h_offset < dah_first) {
+		h->next = dah_first;
+		dah_first = h_offset;
+	} else {
+		struct debug_alloc_header *prev;
+		unsigned int prev_offset;
+		prev = (struct debug_alloc_header *)(debug_alloc_pool +
+						     dah_first);
+		while (1) {
+			if (!prev->next || prev->next > h_offset)
+				break;
+			prev = (struct debug_alloc_header *)
+				(debug_alloc_pool + prev->next);
+		}
+		prev_offset = (char *)prev - debug_alloc_pool;
+		if (prev_offset + dah_overhead + prev->size == h_offset) {
+			prev->size += dah_overhead + h->size;
+			memset(h, POISON_FREE, dah_overhead - 1);
+			*((char *)h + dah_overhead - 1) = POISON_END;
+			h = prev;
+			h_offset = prev_offset;
+		} else {
+			h->next = prev->next;
+			prev->next = h_offset;
+		}
+	}
+	if (h_offset + dah_overhead + h->size == h->next) {
+		struct debug_alloc_header *next;
+		next = (struct debug_alloc_header *)
+			(debug_alloc_pool + h->next);
+		h->size += dah_overhead + next->size;
+		h->next = next->next;
+		memset(next, POISON_FREE, dah_overhead - 1);
+		*((char *)next + dah_overhead - 1) = POISON_END;
+	}
+	spin_unlock(&dap_lock);
+}
+
+void debug_kusage(void)
+{
+	struct debug_alloc_header *h_free, *h_used;
+#ifdef	CONFIG_IA64
+	/* FIXME: using dah for ia64 unwind always results in a memory leak.
+	 * Fix that memory leak first, then set debug_kusage_one_time = 1 for
+	 * all architectures.
+	 */
+	static int debug_kusage_one_time;
+#else
+	static int debug_kusage_one_time = 1;
+#endif
+	if (!get_dap_lock()) {
+		__release(dap_lock);	/* we never actually got it */
+		return;
+	}
+	h_free = (struct debug_alloc_header *)(debug_alloc_pool + dah_first);
+	if (dah_first == 0 &&
+	    (h_free->size == sizeof(debug_alloc_pool_aligned) - dah_overhead ||
+	     dah_first_call))
+		goto out;
+	if (!debug_kusage_one_time)
+		goto out;
+	debug_kusage_one_time = 0;
+	kdb_printf("%s: debug_kmalloc memory leak dah_first %d\n",
+		   __func__, dah_first);
+	if (dah_first) {
+		h_used = (struct debug_alloc_header *)debug_alloc_pool;
+		kdb_printf("%s: h_used %p size %d\n", __func__, h_used,
+			   h_used->size);
+	}
+	do {
+		h_used = (struct debug_alloc_header *)
+			  ((char *)h_free + dah_overhead + h_free->size);
+		kdb_printf("%s: h_used %p size %d caller %p\n",
+			   __func__, h_used, h_used->size, h_used->caller);
+		h_free = (struct debug_alloc_header *)
+			  (debug_alloc_pool + h_free->next);
+	} while (h_free->next);
+	h_used = (struct debug_alloc_header *)
+		  ((char *)h_free + dah_overhead + h_free->size);
+	if ((char *)h_used - debug_alloc_pool !=
+	    sizeof(debug_alloc_pool_aligned))
+		kdb_printf("%s: h_used %p size %d caller %p\n",
+			   __func__, h_used, h_used->size, h_used->caller);
+out:
+	spin_unlock(&dap_lock);
+}
+
+/* Maintain a small stack of kdb_flags to allow recursion without disturbing
+ * the global kdb state.
+ */
+
+static int kdb_flags_stack[4], kdb_flags_index;
+
+void kdb_save_flags(void)
+{
+	BUG_ON(kdb_flags_index >= ARRAY_SIZE(kdb_flags_stack));
+	kdb_flags_stack[kdb_flags_index++] = kdb_flags;
+}
+
+void kdb_restore_flags(void)
+{
+	BUG_ON(kdb_flags_index <= 0);
+	kdb_flags = kdb_flags_stack[--kdb_flags_index];
+}
diff --git a/kernel/exit.c b/kernel/exit.c
index 7f2683a10ac..eabca5a73a8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,7 +55,6 @@
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include "cred-internals.h"
 
 static void exit_mm(struct task_struct * tsk);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 44b0791b0a2..4d57d9e3a6e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1112,10 +1112,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->memcg_batch.memcg = NULL;
 #endif
 
-	p->bts = NULL;
-
-	p->stack_start = stack_start;
-
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 
diff --git a/kernel/groups.c b/kernel/groups.c
index 2b45b2ee396..53b1916c949 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -164,12 +164,6 @@ int groups_search(const struct group_info *group_info, gid_t grp)
  */
 int set_groups(struct cred *new, struct group_info *group_info)
 {
-	int retval;
-
-	retval = security_task_setgroups(group_info);
-	if (retval)
-		return retval;
-
 	put_group_info(new->group_info);
 	groups_sort(group_info);
 	get_group_info(group_info);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0086628b6e9..b9b134b3508 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1749,35 +1749,15 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout_range - sleep until timeout
+ * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:	timeout value (ktime_t)
  * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
- *
- * Make the current task sleep until the given expiry time has
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
- *
- * The @delta argument gives the kernel the freedom to schedule the
- * actual wakeup to a time that is both power and performance friendly.
- * The kernel give the normal best effort behavior for "@expires+@delta",
- * but may decide to fire the timer earlier, but no earlier than @expires.
- *
- * You can set the task state as follows -
- *
- * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
- * pass before the routine returns.
- *
- * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
- * delivered to the current task.
- *
- * The current task state is guaranteed to be TASK_RUNNING when this
- * routine returns.
- *
- * Returns 0 when the timer has expired otherwise -EINTR
+ * @clock:	timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
  */
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
-			       const enum hrtimer_mode mode)
+int __sched
+schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+			       const enum hrtimer_mode mode, int clock)
 {
 	struct hrtimer_sleeper t;
 
@@ -1799,7 +1779,7 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 		return -EINTR;
 	}
 
-	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_init_on_stack(&t.timer, clock, mode);
 	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
 	hrtimer_init_sleeper(&t, current);
@@ -1818,6 +1798,41 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 
 	return !t.task ? 0 : -EINTR;
 }
+
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
+ * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+				     const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range_clock(expires, delta, mode,
+					      CLOCK_MONOTONIC);
+}
 EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
 
 /**
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 03808ed342a..7a56b22e060 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -40,23 +40,29 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
 
 #include <linux/hw_breakpoint.h>
 
+
 /*
  * Constraints data
  */
 
 /* Number of pinned cpu breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned[TYPE_MAX]);
 
 /* Number of pinned task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]);
+static DEFINE_PER_CPU(unsigned int *, nr_task_bp_pinned[TYPE_MAX]);
 
 /* Number of non-pinned cpu/task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
+
+static int nr_slots[TYPE_MAX];
+
+static int constraints_initialized;
 
 /* Gather the number of total pinned and un-pinned bp in a cpuset */
 struct bp_busy_slots {
@@ -67,16 +73,29 @@ struct bp_busy_slots {
 /* Serialize accesses to the above constraints */
 static DEFINE_MUTEX(nr_bp_mutex);
 
+__weak int hw_breakpoint_weight(struct perf_event *bp)
+{
+	return 1;
+}
+
+static inline enum bp_type_idx find_slot_idx(struct perf_event *bp)
+{
+	if (bp->attr.bp_type & HW_BREAKPOINT_RW)
+		return TYPE_DATA;
+
+	return TYPE_INST;
+}
+
 /*
  * Report the maximum number of pinned breakpoints a task
  * have in this cpu
  */
-static unsigned int max_task_bp_pinned(int cpu)
+static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
 {
 	int i;
-	unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+	unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 
-	for (i = HBP_NUM -1; i >= 0; i--) {
+	for (i = nr_slots[type] - 1; i >= 0; i--) {
 		if (tsk_pinned[i] > 0)
 			return i + 1;
 	}
@@ -84,7 +103,7 @@ static unsigned int max_task_bp_pinned(int cpu)
 	return 0;
 }
 
-static int task_bp_pinned(struct task_struct *tsk)
+static int task_bp_pinned(struct task_struct *tsk, enum bp_type_idx type)
 {
 	struct perf_event_context *ctx = tsk->perf_event_ctxp;
 	struct list_head *list;
@@ -105,7 +124,8 @@ static int task_bp_pinned(struct task_struct *tsk)
 	 */
 	list_for_each_entry(bp, list, event_entry) {
 		if (bp->attr.type == PERF_TYPE_BREAKPOINT)
-			count++;
+			if (find_slot_idx(bp) == type)
+				count += hw_breakpoint_weight(bp);
 	}
 
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
@@ -118,18 +138,19 @@ static int task_bp_pinned(struct task_struct *tsk)
  * a given cpu (cpu > -1) or in all of them (cpu = -1).
  */
 static void
-fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
+fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
+		    enum bp_type_idx type)
 {
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
 
 	if (cpu >= 0) {
-		slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+		slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
 		if (!tsk)
-			slots->pinned += max_task_bp_pinned(cpu);
+			slots->pinned += max_task_bp_pinned(cpu, type);
 		else
-			slots->pinned += task_bp_pinned(tsk);
-		slots->flexible = per_cpu(nr_bp_flexible, cpu);
+			slots->pinned += task_bp_pinned(tsk, type);
+		slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
 
 		return;
 	}
@@ -137,16 +158,16 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
 	for_each_online_cpu(cpu) {
 		unsigned int nr;
 
-		nr = per_cpu(nr_cpu_bp_pinned, cpu);
+		nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
 		if (!tsk)
-			nr += max_task_bp_pinned(cpu);
+			nr += max_task_bp_pinned(cpu, type);
 		else
-			nr += task_bp_pinned(tsk);
+			nr += task_bp_pinned(tsk, type);
 
 		if (nr > slots->pinned)
 			slots->pinned = nr;
 
-		nr = per_cpu(nr_bp_flexible, cpu);
+		nr = per_cpu(nr_bp_flexible[type], cpu);
 
 		if (nr > slots->flexible)
 			slots->flexible = nr;
@@ -154,31 +175,49 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
 }
 
 /*
+ * For now, continue to consider flexible as pinned, until we can
+ * ensure no flexible event can ever be scheduled before a pinned event
+ * in a same cpu.
+ */
+static void
+fetch_this_slot(struct bp_busy_slots *slots, int weight)
+{
+	slots->pinned += weight;
+}
+
+/*
  * Add a pinned breakpoint for the given task in our constraint table
  */
-static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
+static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable,
+				enum bp_type_idx type, int weight)
 {
 	unsigned int *tsk_pinned;
-	int count = 0;
+	int old_count = 0;
+	int old_idx = 0;
+	int idx = 0;
 
-	count = task_bp_pinned(tsk);
+	old_count = task_bp_pinned(tsk, type);
+	old_idx = old_count - 1;
+	idx = old_idx + weight;
 
-	tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+	tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 	if (enable) {
-		tsk_pinned[count]++;
-		if (count > 0)
-			tsk_pinned[count-1]--;
+		tsk_pinned[idx]++;
+		if (old_count > 0)
+			tsk_pinned[old_idx]--;
 	} else {
-		tsk_pinned[count]--;
-		if (count > 0)
-			tsk_pinned[count-1]++;
+		tsk_pinned[idx]--;
+		if (old_count > 0)
+			tsk_pinned[old_idx]++;
 	}
 }
 
 /*
  * Add/remove the given breakpoint in our constraint table
  */
-static void toggle_bp_slot(struct perf_event *bp, bool enable)
+static void
+toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
+	       int weight)
 {
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
@@ -186,20 +225,20 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
 	/* Pinned counter task profiling */
 	if (tsk) {
 		if (cpu >= 0) {
-			toggle_bp_task_slot(tsk, cpu, enable);
+			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
 			return;
 		}
 
 		for_each_online_cpu(cpu)
-			toggle_bp_task_slot(tsk, cpu, enable);
+			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
 		return;
 	}
 
 	/* Pinned counter cpu profiling */
 	if (enable)
-		per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
+		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
 	else
-		per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
+		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight;
 }
 
 /*
@@ -246,14 +285,29 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
 static int __reserve_bp_slot(struct perf_event *bp)
 {
 	struct bp_busy_slots slots = {0};
+	enum bp_type_idx type;
+	int weight;
 
-	fetch_bp_busy_slots(&slots, bp);
+	/* We couldn't initialize breakpoint constraints on boot */
+	if (!constraints_initialized)
+		return -ENOMEM;
+
+	/* Basic checks */
+	if (bp->attr.bp_type == HW_BREAKPOINT_EMPTY ||
+	    bp->attr.bp_type == HW_BREAKPOINT_INVALID)
+		return -EINVAL;
+
+	type = find_slot_idx(bp);
+	weight = hw_breakpoint_weight(bp);
+
+	fetch_bp_busy_slots(&slots, bp, type);
+	fetch_this_slot(&slots, weight);
 
 	/* Flexible counters need to keep at least one slot */
-	if (slots.pinned + (!!slots.flexible) == HBP_NUM)
+	if (slots.pinned + (!!slots.flexible) > nr_slots[type])
 		return -ENOSPC;
 
-	toggle_bp_slot(bp, true);
+	toggle_bp_slot(bp, true, type, weight);
 
 	return 0;
 }
@@ -273,7 +327,12 @@ int reserve_bp_slot(struct perf_event *bp)
 
 static void __release_bp_slot(struct perf_event *bp)
 {
-	toggle_bp_slot(bp, false);
+	enum bp_type_idx type;
+	int weight;
+
+	type = find_slot_idx(bp);
+	weight = hw_breakpoint_weight(bp);
+	toggle_bp_slot(bp, false, type, weight);
 }
 
 void release_bp_slot(struct perf_event *bp)
@@ -308,6 +367,28 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
+static int validate_hw_breakpoint(struct perf_event *bp)
+{
+	int ret;
+
+	ret = arch_validate_hwbkpt_settings(bp);
+	if (ret)
+		return ret;
+
+	if (arch_check_bp_in_kernelspace(bp)) {
+		if (bp->attr.exclude_kernel)
+			return -EINVAL;
+		/*
+		 * Don't let unprivileged users set a breakpoint in the trap
+		 * path to avoid trap recursion attacks.
+		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	}
+
+	return 0;
+}
+
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
 	int ret;
@@ -316,17 +397,7 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
 	if (ret)
 		return ret;
 
-	/*
-	 * Ptrace breakpoints can be temporary perf events only
-	 * meant to reserve a slot. In this case, it is created disabled and
-	 * we don't want to check the params right now (as we put a null addr)
-	 * But perf tools create events as disabled and we want to check
-	 * the params for them.
-	 * This is a quick hack that will be removed soon, once we remove
-	 * the tmp breakpoints from ptrace
-	 */
-	if (!bp->attr.disabled || !bp->overflow_handler)
-		ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+	ret = validate_hw_breakpoint(bp);
 
 	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
 	if (ret)
@@ -373,7 +444,7 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	if (attr->disabled)
 		goto end;
 
-	err = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+	err = validate_hw_breakpoint(bp);
 	if (!err)
 		perf_event_enable(bp);
 
@@ -480,7 +551,36 @@ static struct notifier_block hw_breakpoint_exceptions_nb = {
 
 static int __init init_hw_breakpoint(void)
 {
+	unsigned int **task_bp_pinned;
+	int cpu, err_cpu;
+	int i;
+
+	for (i = 0; i < TYPE_MAX; i++)
+		nr_slots[i] = hw_breakpoint_slots(i);
+
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < TYPE_MAX; i++) {
+			task_bp_pinned = &per_cpu(nr_task_bp_pinned[i], cpu);
+			*task_bp_pinned = kzalloc(sizeof(int) * nr_slots[i],
+						  GFP_KERNEL);
+			if (!*task_bp_pinned)
+				goto err_alloc;
+		}
+	}
+
+	constraints_initialized = 1;
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
+
+ err_alloc:
+	for_each_possible_cpu(err_cpu) {
+		if (err_cpu == cpu)
+			break;
+		for (i = 0; i < TYPE_MAX; i++)
+			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+	}
+
+	return -ENOMEM;
 }
 core_initcall(init_hw_breakpoint);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 76d5a671bfe..27e5c691122 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -370,9 +370,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 	irqreturn_t ret, retval = IRQ_NONE;
 	unsigned int status = 0;
 
-	if (!(action->flags & IRQF_DISABLED))
-		local_irq_enable_in_hardirq();
-
 	do {
 		trace_irq_handler_entry(irq, action);
 		ret = action->handler(irq, action->dev_id);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 704e488730a..3164ba7ce15 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -138,6 +138,22 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	return 0;
 }
 
+int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	unsigned long flags;
+
+	if (!desc)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	desc->affinity_hint = m;
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+
 #ifndef CONFIG_AUTO_IRQ_AFFINITY
 /*
  * Generic version of the affinity autoselector.
@@ -757,16 +773,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		if (new->flags & IRQF_ONESHOT)
 			desc->status |= IRQ_ONESHOT;
 
-		/*
-		 * Force MSI interrupts to run with interrupts
-		 * disabled. The multi vector cards can cause stack
-		 * overflows due to nested interrupts when enough of
-		 * them are directed to a core and fire at the same
-		 * time.
-		 */
-		if (desc->msi_desc)
-			new->flags |= IRQF_DISABLED;
-
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
@@ -916,6 +922,12 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 			desc->chip->disable(irq);
 	}
 
+#ifdef CONFIG_SMP
+	/* make sure affinity_hint is cleaned up */
+	if (WARN_ON_ONCE(desc->affinity_hint))
+		desc->affinity_hint = NULL;
+#endif
+
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	unregister_handler_proc(irq, action);
@@ -1027,7 +1039,6 @@ EXPORT_SYMBOL(free_irq);
  *	Flags:
  *
  *	IRQF_SHARED		Interrupt is shared
- *	IRQF_DISABLED	Disable local interrupts while processing
  *	IRQF_SAMPLE_RANDOM	The interrupt can be used for entropy
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
  *
@@ -1041,25 +1052,6 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	int retval;
 
 	/*
-	 * handle_IRQ_event() always ignores IRQF_DISABLED except for
-	 * the _first_ irqaction (sigh).  That can cause oopsing, but
-	 * the behavior is classified as "will not fix" so we need to
-	 * start nudging drivers away from using that idiom.
-	 */
-	if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) ==
-					(IRQF_SHARED|IRQF_DISABLED)) {
-		pr_warning(
-		  "IRQ %d/%s: IRQF_DISABLED is not guaranteed on shared IRQs\n",
-			irq, devname);
-	}
-
-#ifdef CONFIG_LOCKDEP
-	/*
-	 * Lockdep wants atomic interrupt handlers:
-	 */
-	irqflags |= IRQF_DISABLED;
-#endif
-	/*
 	 * Sanity-check: shared interrupts must pass in a real dev-ID,
 	 * otherwise we'll have trouble later trying to figure out
 	 * which interrupt is which (messes up the interrupt freeing
@@ -1120,3 +1112,40 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	return retval;
 }
 EXPORT_SYMBOL(request_threaded_irq);
+
+/**
+ *	request_any_context_irq - allocate an interrupt line
+ *	@irq: Interrupt line to allocate
+ *	@handler: Function to be called when the IRQ occurs.
+ *		  Threaded handler for threaded interrupts.
+ *	@flags: Interrupt type flags
+ *	@name: An ascii name for the claiming device
+ *	@dev_id: A cookie passed back to the handler function
+ *
+ *	This call allocates interrupt resources and enables the
+ *	interrupt line and IRQ handling. It selects either a
+ *	hardirq or threaded handling method depending on the
+ *	context.
+ *
+ *	On failure, it returns a negative value. On success,
+ *	it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
+ */
+int request_any_context_irq(unsigned int irq, irq_handler_t handler,
+			    unsigned long flags, const char *name, void *dev_id)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	int ret;
+
+	if (!desc)
+		return -EINVAL;
+
+	if (desc->status & IRQ_NESTED_THREAD) {
+		ret = request_threaded_irq(irq, NULL, handler,
+					   flags, name, dev_id);
+		return !ret ? IRQC_IS_NESTED : ret;
+	}
+
+	ret = request_irq(irq, handler, flags, name, dev_id);
+	return !ret ? IRQC_IS_HARDIRQ : ret;
+}
+EXPORT_SYMBOL_GPL(request_any_context_irq);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 7a6eb04ef6b..09a2ee540bd 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -32,6 +32,27 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int irq_affinity_hint_proc_show(struct seq_file *m, void *v)
+{
+	struct irq_desc *desc = irq_to_desc((long)m->private);
+	unsigned long flags;
+	cpumask_var_t mask;
+
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	if (desc->affinity_hint)
+		cpumask_copy(mask, desc->affinity_hint);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	seq_cpumask(m, mask);
+	seq_putc(m, '\n');
+	free_cpumask_var(mask);
+
+	return 0;
+}
+
 #ifndef is_affinity_mask_valid
 #define is_affinity_mask_valid(val) 1
 #endif
@@ -84,6 +105,11 @@ static int irq_affinity_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, irq_affinity_proc_show, PDE(inode)->data);
 }
 
+static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, irq_affinity_hint_proc_show, PDE(inode)->data);
+}
+
 static const struct file_operations irq_affinity_proc_fops = {
 	.open		= irq_affinity_proc_open,
 	.read		= seq_read,
@@ -92,6 +118,13 @@ static const struct file_operations irq_affinity_proc_fops = {
 	.write		= irq_affinity_proc_write,
 };
 
+static const struct file_operations irq_affinity_hint_proc_fops = {
+	.open		= irq_affinity_hint_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static int default_affinity_show(struct seq_file *m, void *v)
 {
 	seq_cpumask(m, irq_default_affinity);
@@ -147,6 +180,26 @@ static const struct file_operations default_affinity_proc_fops = {
 	.release	= single_release,
 	.write		= default_affinity_write,
 };
+
+static int irq_node_proc_show(struct seq_file *m, void *v)
+{
+	struct irq_desc *desc = irq_to_desc((long) m->private);
+
+	seq_printf(m, "%d\n", desc->node);
+	return 0;
+}
+
+static int irq_node_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, irq_node_proc_show, PDE(inode)->data);
+}
+
+static const struct file_operations irq_node_proc_fops = {
+	.open		= irq_node_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 #endif
 
 static int irq_spurious_proc_show(struct seq_file *m, void *v)
@@ -231,6 +284,13 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 	/* create /proc/irq/<irq>/smp_affinity */
 	proc_create_data("smp_affinity", 0600, desc->dir,
 			 &irq_affinity_proc_fops, (void *)(long)irq);
+
+	/* create /proc/irq/<irq>/affinity_hint */
+	proc_create_data("affinity_hint", 0400, desc->dir,
+			 &irq_affinity_hint_proc_fops, (void *)(long)irq);
+
+	proc_create_data("node", 0444, desc->dir,
+			 &irq_node_proc_fops, (void *)(long)irq);
 #endif
 
 	proc_create_data("spurious", 0444, desc->dir,
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 13aff293f4d..6f6d091b575 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/fs.h>
+#include <linux/kdb.h>
 #include <linux/err.h>
 #include <linux/proc_fs.h>
 #include <linux/sched.h>	/* for cond_resched */
@@ -516,6 +517,26 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+#ifdef	CONFIG_KGDB_KDB
+const char *kdb_walk_kallsyms(loff_t *pos)
+{
+	static struct kallsym_iter kdb_walk_kallsyms_iter;
+	if (*pos == 0) {
+		memset(&kdb_walk_kallsyms_iter, 0,
+		       sizeof(kdb_walk_kallsyms_iter));
+		reset_iter(&kdb_walk_kallsyms_iter, 0);
+	}
+	while (1) {
+		if (!update_iter(&kdb_walk_kallsyms_iter, *pos))
+			return NULL;
+		++*pos;
+		/* Some debugging symbols have no name.  Ignore them. */
+		if (kdb_walk_kallsyms_iter.name[0])
+			return kdb_walk_kallsyms_iter.name;
+	}
+}
+#endif	/* CONFIG_KGDB_KDB */
+
 static const struct file_operations kallsyms_operations = {
 	.open = kallsyms_open,
 	.read = seq_read,
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 87ebe8adc47..474a84715ea 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1134,11 +1134,9 @@ int crash_shrink_memory(unsigned long new_size)
 
 	free_reserved_phys_range(end, crashk_res.end);
 
-	if (start == end) {
-		crashk_res.end = end;
+	if (start == end)
 		release_resource(&crashk_res);
-	} else
-		crashk_res.end = end - 1;
+	crashk_res.end = end - 1;
 
 unlock:
 	mutex_unlock(&kexec_mutex);
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
deleted file mode 100644
index 11f3515ca83..00000000000
--- a/kernel/kgdb.c
+++ /dev/null
@@ -1,1764 +0,0 @@
-/*
- * KGDB stub.
- *
- * Maintainer: Jason Wessel <jason.wessel@windriver.com>
- *
- * Copyright (C) 2000-2001 VERITAS Software Corporation.
- * Copyright (C) 2002-2004 Timesys Corporation
- * Copyright (C) 2003-2004 Amit S. Kale <amitkale@linsyssoft.com>
- * Copyright (C) 2004 Pavel Machek <pavel@suse.cz>
- * Copyright (C) 2004-2006 Tom Rini <trini@kernel.crashing.org>
- * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd.
- * Copyright (C) 2005-2008 Wind River Systems, Inc.
- * Copyright (C) 2007 MontaVista Software, Inc.
- * Copyright (C) 2008 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *
- * Contributors at various stages not listed above:
- *  Jason Wessel ( jason.wessel@windriver.com )
- *  George Anzinger <george@mvista.com>
- *  Anurekh Saxena (anurekh.saxena@timesys.com)
- *  Lake Stevens Instrument Division (Glenn Engel)
- *  Jim Kingdon, Cygnus Support.
- *
- * Original KGDB stub: David Grothe <dave@gcom.com>,
- * Tigran Aivazian <tigran@sco.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-#include <linux/pid_namespace.h>
-#include <linux/clocksource.h>
-#include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/console.h>
-#include <linux/threads.h>
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/ptrace.h>
-#include <linux/reboot.h>
-#include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/sysrq.h>
-#include <linux/init.h>
-#include <linux/kgdb.h>
-#include <linux/pid.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
-
-#include <asm/cacheflush.h>
-#include <asm/byteorder.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/unaligned.h>
-
-static int kgdb_break_asap;
-
-#define KGDB_MAX_THREAD_QUERY 17
-struct kgdb_state {
-	int			ex_vector;
-	int			signo;
-	int			err_code;
-	int			cpu;
-	int			pass_exception;
-	unsigned long		thr_query;
-	unsigned long		threadid;
-	long			kgdb_usethreadid;
-	struct pt_regs		*linux_regs;
-};
-
-/* Exception state values */
-#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
-#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
-#define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
-#define DCPU_SSTEP       0x8 /* CPU is single stepping */
-
-static struct debuggerinfo_struct {
-	void			*debuggerinfo;
-	struct task_struct	*task;
-	int 			exception_state;
-} kgdb_info[NR_CPUS];
-
-/**
- * kgdb_connected - Is a host GDB connected to us?
- */
-int				kgdb_connected;
-EXPORT_SYMBOL_GPL(kgdb_connected);
-
-/* All the KGDB handlers are installed */
-static int			kgdb_io_module_registered;
-
-/* Guard for recursive entry */
-static int			exception_level;
-
-static struct kgdb_io		*kgdb_io_ops;
-static DEFINE_SPINLOCK(kgdb_registration_lock);
-
-/* kgdb console driver is loaded */
-static int kgdb_con_registered;
-/* determine if kgdb console output should be used */
-static int kgdb_use_con;
-
-static int __init opt_kgdb_con(char *str)
-{
-	kgdb_use_con = 1;
-	return 0;
-}
-
-early_param("kgdbcon", opt_kgdb_con);
-
-module_param(kgdb_use_con, int, 0644);
-
-/*
- * Holds information about breakpoints in a kernel. These breakpoints are
- * added and removed by gdb.
- */
-static struct kgdb_bkpt		kgdb_break[KGDB_MAX_BREAKPOINTS] = {
-	[0 ... KGDB_MAX_BREAKPOINTS-1] = { .state = BP_UNDEFINED }
-};
-
-/*
- * The CPU# of the active CPU, or -1 if none:
- */
-atomic_t			kgdb_active = ATOMIC_INIT(-1);
-
-/*
- * We use NR_CPUs not PERCPU, in case kgdb is used to debug early
- * bootup code (which might not have percpu set up yet):
- */
-static atomic_t			passive_cpu_wait[NR_CPUS];
-static atomic_t			cpu_in_kgdb[NR_CPUS];
-atomic_t			kgdb_setting_breakpoint;
-
-struct task_struct		*kgdb_usethread;
-struct task_struct		*kgdb_contthread;
-
-int				kgdb_single_step;
-pid_t				kgdb_sstep_pid;
-
-/* Our I/O buffers. */
-static char			remcom_in_buffer[BUFMAX];
-static char			remcom_out_buffer[BUFMAX];
-
-/* Storage for the registers, in GDB format. */
-static unsigned long		gdb_regs[(NUMREGBYTES +
-					sizeof(unsigned long) - 1) /
-					sizeof(unsigned long)];
-
-/* to keep track of the CPU which is doing the single stepping*/
-atomic_t			kgdb_cpu_doing_single_step = ATOMIC_INIT(-1);
-
-/*
- * If you are debugging a problem where roundup (the collection of
- * all other CPUs) is a problem [this should be extremely rare],
- * then use the nokgdbroundup option to avoid roundup. In that case
- * the other CPUs might interfere with your debugging context, so
- * use this with care:
- */
-static int kgdb_do_roundup = 1;
-
-static int __init opt_nokgdbroundup(char *str)
-{
-	kgdb_do_roundup = 0;
-
-	return 0;
-}
-
-early_param("nokgdbroundup", opt_nokgdbroundup);
-
-/*
- * Finally, some KGDB code :-)
- */
-
-/*
- * Weak aliases for breakpoint management,
- * can be overriden by architectures when needed:
- */
-int __weak kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr)
-{
-	int err;
-
-	err = probe_kernel_read(saved_instr, (char *)addr, BREAK_INSTR_SIZE);
-	if (err)
-		return err;
-
-	return probe_kernel_write((char *)addr, arch_kgdb_ops.gdb_bpt_instr,
-				  BREAK_INSTR_SIZE);
-}
-
-int __weak kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle)
-{
-	return probe_kernel_write((char *)addr,
-				  (char *)bundle, BREAK_INSTR_SIZE);
-}
-
-int __weak kgdb_validate_break_address(unsigned long addr)
-{
-	char tmp_variable[BREAK_INSTR_SIZE];
-	int err;
-	/* Validate setting the breakpoint and then removing it.  In the
-	 * remove fails, the kernel needs to emit a bad message because we
-	 * are deep trouble not being able to put things back the way we
-	 * found them.
-	 */
-	err = kgdb_arch_set_breakpoint(addr, tmp_variable);
-	if (err)
-		return err;
-	err = kgdb_arch_remove_breakpoint(addr, tmp_variable);
-	if (err)
-		printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
-		   "memory destroyed at: %lx", addr);
-	return err;
-}
-
-unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs)
-{
-	return instruction_pointer(regs);
-}
-
-int __weak kgdb_arch_init(void)
-{
-	return 0;
-}
-
-int __weak kgdb_skipexception(int exception, struct pt_regs *regs)
-{
-	return 0;
-}
-
-void __weak
-kgdb_post_primary_code(struct pt_regs *regs, int e_vector, int err_code)
-{
-	return;
-}
-
-/**
- *	kgdb_disable_hw_debug - Disable hardware debugging while we in kgdb.
- *	@regs: Current &struct pt_regs.
- *
- *	This function will be called if the particular architecture must
- *	disable hardware debugging while it is processing gdb packets or
- *	handling exception.
- */
-void __weak kgdb_disable_hw_debug(struct pt_regs *regs)
-{
-}
-
-/*
- * GDB remote protocol parser:
- */
-
-static int hex(char ch)
-{
-	if ((ch >= 'a') && (ch <= 'f'))
-		return ch - 'a' + 10;
-	if ((ch >= '0') && (ch <= '9'))
-		return ch - '0';
-	if ((ch >= 'A') && (ch <= 'F'))
-		return ch - 'A' + 10;
-	return -1;
-}
-
-/* scan for the sequence $<data>#<checksum> */
-static void get_packet(char *buffer)
-{
-	unsigned char checksum;
-	unsigned char xmitcsum;
-	int count;
-	char ch;
-
-	do {
-		/*
-		 * Spin and wait around for the start character, ignore all
-		 * other characters:
-		 */
-		while ((ch = (kgdb_io_ops->read_char())) != '$')
-			/* nothing */;
-
-		kgdb_connected = 1;
-		checksum = 0;
-		xmitcsum = -1;
-
-		count = 0;
-
-		/*
-		 * now, read until a # or end of buffer is found:
-		 */
-		while (count < (BUFMAX - 1)) {
-			ch = kgdb_io_ops->read_char();
-			if (ch == '#')
-				break;
-			checksum = checksum + ch;
-			buffer[count] = ch;
-			count = count + 1;
-		}
-		buffer[count] = 0;
-
-		if (ch == '#') {
-			xmitcsum = hex(kgdb_io_ops->read_char()) << 4;
-			xmitcsum += hex(kgdb_io_ops->read_char());
-
-			if (checksum != xmitcsum)
-				/* failed checksum */
-				kgdb_io_ops->write_char('-');
-			else
-				/* successful transfer */
-				kgdb_io_ops->write_char('+');
-			if (kgdb_io_ops->flush)
-				kgdb_io_ops->flush();
-		}
-	} while (checksum != xmitcsum);
-}
-
-/*
- * Send the packet in buffer.
- * Check for gdb connection if asked for.
- */
-static void put_packet(char *buffer)
-{
-	unsigned char checksum;
-	int count;
-	char ch;
-
-	/*
-	 * $<packet info>#<checksum>.
-	 */
-	while (1) {
-		kgdb_io_ops->write_char('$');
-		checksum = 0;
-		count = 0;
-
-		while ((ch = buffer[count])) {
-			kgdb_io_ops->write_char(ch);
-			checksum += ch;
-			count++;
-		}
-
-		kgdb_io_ops->write_char('#');
-		kgdb_io_ops->write_char(hex_asc_hi(checksum));
-		kgdb_io_ops->write_char(hex_asc_lo(checksum));
-		if (kgdb_io_ops->flush)
-			kgdb_io_ops->flush();
-
-		/* Now see what we get in reply. */
-		ch = kgdb_io_ops->read_char();
-
-		if (ch == 3)
-			ch = kgdb_io_ops->read_char();
-
-		/* If we get an ACK, we are done. */
-		if (ch == '+')
-			return;
-
-		/*
-		 * If we get the start of another packet, this means
-		 * that GDB is attempting to reconnect.  We will NAK
-		 * the packet being sent, and stop trying to send this
-		 * packet.
-		 */
-		if (ch == '$') {
-			kgdb_io_ops->write_char('-');
-			if (kgdb_io_ops->flush)
-				kgdb_io_ops->flush();
-			return;
-		}
-	}
-}
-
-/*
- * Convert the memory pointed to by mem into hex, placing result in buf.
- * Return a pointer to the last char put in buf (null). May return an error.
- */
-int kgdb_mem2hex(char *mem, char *buf, int count)
-{
-	char *tmp;
-	int err;
-
-	/*
-	 * We use the upper half of buf as an intermediate buffer for the
-	 * raw memory copy.  Hex conversion will work against this one.
-	 */
-	tmp = buf + count;
-
-	err = probe_kernel_read(tmp, mem, count);
-	if (!err) {
-		while (count > 0) {
-			buf = pack_hex_byte(buf, *tmp);
-			tmp++;
-			count--;
-		}
-
-		*buf = 0;
-	}
-
-	return err;
-}
-
-/*
- * Copy the binary array pointed to by buf into mem.  Fix $, #, and
- * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success.
- * The input buf is overwitten with the result to write to mem.
- */
-static int kgdb_ebin2mem(char *buf, char *mem, int count)
-{
-	int size = 0;
-	char *c = buf;
-
-	while (count-- > 0) {
-		c[size] = *buf++;
-		if (c[size] == 0x7d)
-			c[size] = *buf++ ^ 0x20;
-		size++;
-	}
-
-	return probe_kernel_write(mem, c, size);
-}
-
-/*
- * Convert the hex array pointed to by buf into binary to be placed in mem.
- * Return a pointer to the character AFTER the last byte written.
- * May return an error.
- */
-int kgdb_hex2mem(char *buf, char *mem, int count)
-{
-	char *tmp_raw;
-	char *tmp_hex;
-
-	/*
-	 * We use the upper half of buf as an intermediate buffer for the
-	 * raw memory that is converted from hex.
-	 */
-	tmp_raw = buf + count * 2;
-
-	tmp_hex = tmp_raw - 1;
-	while (tmp_hex >= buf) {
-		tmp_raw--;
-		*tmp_raw = hex(*tmp_hex--);
-		*tmp_raw |= hex(*tmp_hex--) << 4;
-	}
-
-	return probe_kernel_write(mem, tmp_raw, count);
-}
-
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int kgdb_hex2long(char **ptr, unsigned long *long_val)
-{
-	int hex_val;
-	int num = 0;
-	int negate = 0;
-
-	*long_val = 0;
-
-	if (**ptr == '-') {
-		negate = 1;
-		(*ptr)++;
-	}
-	while (**ptr) {
-		hex_val = hex(**ptr);
-		if (hex_val < 0)
-			break;
-
-		*long_val = (*long_val << 4) | hex_val;
-		num++;
-		(*ptr)++;
-	}
-
-	if (negate)
-		*long_val = -*long_val;
-
-	return num;
-}
-
-/* Write memory due to an 'M' or 'X' packet. */
-static int write_mem_msg(int binary)
-{
-	char *ptr = &remcom_in_buffer[1];
-	unsigned long addr;
-	unsigned long length;
-	int err;
-
-	if (kgdb_hex2long(&ptr, &addr) > 0 && *(ptr++) == ',' &&
-	    kgdb_hex2long(&ptr, &length) > 0 && *(ptr++) == ':') {
-		if (binary)
-			err = kgdb_ebin2mem(ptr, (char *)addr, length);
-		else
-			err = kgdb_hex2mem(ptr, (char *)addr, length);
-		if (err)
-			return err;
-		if (CACHE_FLUSH_IS_SAFE)
-			flush_icache_range(addr, addr + length);
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-static void error_packet(char *pkt, int error)
-{
-	error = -error;
-	pkt[0] = 'E';
-	pkt[1] = hex_asc[(error / 10)];
-	pkt[2] = hex_asc[(error % 10)];
-	pkt[3] = '\0';
-}
-
-/*
- * Thread ID accessors. We represent a flat TID space to GDB, where
- * the per CPU idle threads (which under Linux all have PID 0) are
- * remapped to negative TIDs.
- */
-
-#define BUF_THREAD_ID_SIZE	16
-
-static char *pack_threadid(char *pkt, unsigned char *id)
-{
-	char *limit;
-
-	limit = pkt + BUF_THREAD_ID_SIZE;
-	while (pkt < limit)
-		pkt = pack_hex_byte(pkt, *id++);
-
-	return pkt;
-}
-
-static void int_to_threadref(unsigned char *id, int value)
-{
-	unsigned char *scan;
-	int i = 4;
-
-	scan = (unsigned char *)id;
-	while (i--)
-		*scan++ = 0;
-	put_unaligned_be32(value, scan);
-}
-
-static struct task_struct *getthread(struct pt_regs *regs, int tid)
-{
-	/*
-	 * Non-positive TIDs are remapped to the cpu shadow information
-	 */
-	if (tid == 0 || tid == -1)
-		tid = -atomic_read(&kgdb_active) - 2;
-	if (tid < -1 && tid > -NR_CPUS - 2) {
-		if (kgdb_info[-tid - 2].task)
-			return kgdb_info[-tid - 2].task;
-		else
-			return idle_task(-tid - 2);
-	}
-	if (tid <= 0) {
-		printk(KERN_ERR "KGDB: Internal thread select error\n");
-		dump_stack();
-		return NULL;
-	}
-
-	/*
-	 * find_task_by_pid_ns() does not take the tasklist lock anymore
-	 * but is nicely RCU locked - hence is a pretty resilient
-	 * thing to use:
-	 */
-	return find_task_by_pid_ns(tid, &init_pid_ns);
-}
-
-/*
- * Some architectures need cache flushes when we set/clear a
- * breakpoint:
- */
-static void kgdb_flush_swbreak_addr(unsigned long addr)
-{
-	if (!CACHE_FLUSH_IS_SAFE)
-		return;
-
-	if (current->mm && current->mm->mmap_cache) {
-		flush_cache_range(current->mm->mmap_cache,
-				  addr, addr + BREAK_INSTR_SIZE);
-	}
-	/* Force flush instruction cache if it was outside the mm */
-	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
-}
-
-/*
- * SW breakpoint management:
- */
-static int kgdb_activate_sw_breakpoints(void)
-{
-	unsigned long addr;
-	int error;
-	int ret = 0;
-	int i;
-
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if (kgdb_break[i].state != BP_SET)
-			continue;
-
-		addr = kgdb_break[i].bpt_addr;
-		error = kgdb_arch_set_breakpoint(addr,
-				kgdb_break[i].saved_instr);
-		if (error) {
-			ret = error;
-			printk(KERN_INFO "KGDB: BP install failed: %lx", addr);
-			continue;
-		}
-
-		kgdb_flush_swbreak_addr(addr);
-		kgdb_break[i].state = BP_ACTIVE;
-	}
-	return ret;
-}
-
-static int kgdb_set_sw_break(unsigned long addr)
-{
-	int err = kgdb_validate_break_address(addr);
-	int breakno = -1;
-	int i;
-
-	if (err)
-		return err;
-
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if ((kgdb_break[i].state == BP_SET) &&
-					(kgdb_break[i].bpt_addr == addr))
-			return -EEXIST;
-	}
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if (kgdb_break[i].state == BP_REMOVED &&
-					kgdb_break[i].bpt_addr == addr) {
-			breakno = i;
-			break;
-		}
-	}
-
-	if (breakno == -1) {
-		for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-			if (kgdb_break[i].state == BP_UNDEFINED) {
-				breakno = i;
-				break;
-			}
-		}
-	}
-
-	if (breakno == -1)
-		return -E2BIG;
-
-	kgdb_break[breakno].state = BP_SET;
-	kgdb_break[breakno].type = BP_BREAKPOINT;
-	kgdb_break[breakno].bpt_addr = addr;
-
-	return 0;
-}
-
-static int kgdb_deactivate_sw_breakpoints(void)
-{
-	unsigned long addr;
-	int error;
-	int ret = 0;
-	int i;
-
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if (kgdb_break[i].state != BP_ACTIVE)
-			continue;
-		addr = kgdb_break[i].bpt_addr;
-		error = kgdb_arch_remove_breakpoint(addr,
-					kgdb_break[i].saved_instr);
-		if (error) {
-			printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr);
-			ret = error;
-		}
-
-		kgdb_flush_swbreak_addr(addr);
-		kgdb_break[i].state = BP_SET;
-	}
-	return ret;
-}
-
-static int kgdb_remove_sw_break(unsigned long addr)
-{
-	int i;
-
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if ((kgdb_break[i].state == BP_SET) &&
-				(kgdb_break[i].bpt_addr == addr)) {
-			kgdb_break[i].state = BP_REMOVED;
-			return 0;
-		}
-	}
-	return -ENOENT;
-}
-
-int kgdb_isremovedbreak(unsigned long addr)
-{
-	int i;
-
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if ((kgdb_break[i].state == BP_REMOVED) &&
-					(kgdb_break[i].bpt_addr == addr))
-			return 1;
-	}
-	return 0;
-}
-
-static int remove_all_break(void)
-{
-	unsigned long addr;
-	int error;
-	int i;
-
-	/* Clear memory breakpoints. */
-	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
-		if (kgdb_break[i].state != BP_ACTIVE)
-			goto setundefined;
-		addr = kgdb_break[i].bpt_addr;
-		error = kgdb_arch_remove_breakpoint(addr,
-				kgdb_break[i].saved_instr);
-		if (error)
-			printk(KERN_ERR "KGDB: breakpoint remove failed: %lx\n",
-			   addr);
-setundefined:
-		kgdb_break[i].state = BP_UNDEFINED;
-	}
-
-	/* Clear hardware breakpoints. */
-	if (arch_kgdb_ops.remove_all_hw_break)
-		arch_kgdb_ops.remove_all_hw_break();
-
-	return 0;
-}
-
-/*
- * Remap normal tasks to their real PID,
- * CPU shadow threads are mapped to -CPU - 2
- */
-static inline int shadow_pid(int realpid)
-{
-	if (realpid)
-		return realpid;
-
-	return -raw_smp_processor_id() - 2;
-}
-
-static char gdbmsgbuf[BUFMAX + 1];
-
-static void kgdb_msg_write(const char *s, int len)
-{
-	char *bufptr;
-	int wcount;
-	int i;
-
-	/* 'O'utput */
-	gdbmsgbuf[0] = 'O';
-
-	/* Fill and send buffers... */
-	while (len > 0) {
-		bufptr = gdbmsgbuf + 1;
-
-		/* Calculate how many this time */
-		if ((len << 1) > (BUFMAX - 2))
-			wcount = (BUFMAX - 2) >> 1;
-		else
-			wcount = len;
-
-		/* Pack in hex chars */
-		for (i = 0; i < wcount; i++)
-			bufptr = pack_hex_byte(bufptr, s[i]);
-		*bufptr = '\0';
-
-		/* Move up */
-		s += wcount;
-		len -= wcount;
-
-		/* Write packet */
-		put_packet(gdbmsgbuf);
-	}
-}
-
-/*
- * Return true if there is a valid kgdb I/O module.  Also if no
- * debugger is attached a message can be printed to the console about
- * waiting for the debugger to attach.
- *
- * The print_wait argument is only to be true when called from inside
- * the core kgdb_handle_exception, because it will wait for the
- * debugger to attach.
- */
-static int kgdb_io_ready(int print_wait)
-{
-	if (!kgdb_io_ops)
-		return 0;
-	if (kgdb_connected)
-		return 1;
-	if (atomic_read(&kgdb_setting_breakpoint))
-		return 1;
-	if (print_wait)
-		printk(KERN_CRIT "KGDB: Waiting for remote debugger\n");
-	return 1;
-}
-
-/*
- * All the functions that start with gdb_cmd are the various
- * operations to implement the handlers for the gdbserial protocol
- * where KGDB is communicating with an external debugger
- */
-
-/* Handle the '?' status packets */
-static void gdb_cmd_status(struct kgdb_state *ks)
-{
-	/*
-	 * We know that this packet is only sent
-	 * during initial connect.  So to be safe,
-	 * we clear out our breakpoints now in case
-	 * GDB is reconnecting.
-	 */
-	remove_all_break();
-
-	remcom_out_buffer[0] = 'S';
-	pack_hex_byte(&remcom_out_buffer[1], ks->signo);
-}
-
-/* Handle the 'g' get registers request */
-static void gdb_cmd_getregs(struct kgdb_state *ks)
-{
-	struct task_struct *thread;
-	void *local_debuggerinfo;
-	int i;
-
-	thread = kgdb_usethread;
-	if (!thread) {
-		thread = kgdb_info[ks->cpu].task;
-		local_debuggerinfo = kgdb_info[ks->cpu].debuggerinfo;
-	} else {
-		local_debuggerinfo = NULL;
-		for_each_online_cpu(i) {
-			/*
-			 * Try to find the task on some other
-			 * or possibly this node if we do not
-			 * find the matching task then we try
-			 * to approximate the results.
-			 */
-			if (thread == kgdb_info[i].task)
-				local_debuggerinfo = kgdb_info[i].debuggerinfo;
-		}
-	}
-
-	/*
-	 * All threads that don't have debuggerinfo should be
-	 * in schedule() sleeping, since all other CPUs
-	 * are in kgdb_wait, and thus have debuggerinfo.
-	 */
-	if (local_debuggerinfo) {
-		pt_regs_to_gdb_regs(gdb_regs, local_debuggerinfo);
-	} else {
-		/*
-		 * Pull stuff saved during switch_to; nothing
-		 * else is accessible (or even particularly
-		 * relevant).
-		 *
-		 * This should be enough for a stack trace.
-		 */
-		sleeping_thread_to_gdb_regs(gdb_regs, thread);
-	}
-	kgdb_mem2hex((char *)gdb_regs, remcom_out_buffer, NUMREGBYTES);
-}
-
-/* Handle the 'G' set registers request */
-static void gdb_cmd_setregs(struct kgdb_state *ks)
-{
-	kgdb_hex2mem(&remcom_in_buffer[1], (char *)gdb_regs, NUMREGBYTES);
-
-	if (kgdb_usethread && kgdb_usethread != current) {
-		error_packet(remcom_out_buffer, -EINVAL);
-	} else {
-		gdb_regs_to_pt_regs(gdb_regs, ks->linux_regs);
-		strcpy(remcom_out_buffer, "OK");
-	}
-}
-
-/* Handle the 'm' memory read bytes */
-static void gdb_cmd_memread(struct kgdb_state *ks)
-{
-	char *ptr = &remcom_in_buffer[1];
-	unsigned long length;
-	unsigned long addr;
-	int err;
-
-	if (kgdb_hex2long(&ptr, &addr) > 0 && *ptr++ == ',' &&
-					kgdb_hex2long(&ptr, &length) > 0) {
-		err = kgdb_mem2hex((char *)addr, remcom_out_buffer, length);
-		if (err)
-			error_packet(remcom_out_buffer, err);
-	} else {
-		error_packet(remcom_out_buffer, -EINVAL);
-	}
-}
-
-/* Handle the 'M' memory write bytes */
-static void gdb_cmd_memwrite(struct kgdb_state *ks)
-{
-	int err = write_mem_msg(0);
-
-	if (err)
-		error_packet(remcom_out_buffer, err);
-	else
-		strcpy(remcom_out_buffer, "OK");
-}
-
-/* Handle the 'X' memory binary write bytes */
-static void gdb_cmd_binwrite(struct kgdb_state *ks)
-{
-	int err = write_mem_msg(1);
-
-	if (err)
-		error_packet(remcom_out_buffer, err);
-	else
-		strcpy(remcom_out_buffer, "OK");
-}
-
-/* Handle the 'D' or 'k', detach or kill packets */
-static void gdb_cmd_detachkill(struct kgdb_state *ks)
-{
-	int error;
-
-	/* The detach case */
-	if (remcom_in_buffer[0] == 'D') {
-		error = remove_all_break();
-		if (error < 0) {
-			error_packet(remcom_out_buffer, error);
-		} else {
-			strcpy(remcom_out_buffer, "OK");
-			kgdb_connected = 0;
-		}
-		put_packet(remcom_out_buffer);
-	} else {
-		/*
-		 * Assume the kill case, with no exit code checking,
-		 * trying to force detach the debugger:
-		 */
-		remove_all_break();
-		kgdb_connected = 0;
-	}
-}
-
-/* Handle the 'R' reboot packets */
-static int gdb_cmd_reboot(struct kgdb_state *ks)
-{
-	/* For now, only honor R0 */
-	if (strcmp(remcom_in_buffer, "R0") == 0) {
-		printk(KERN_CRIT "Executing emergency reboot\n");
-		strcpy(remcom_out_buffer, "OK");
-		put_packet(remcom_out_buffer);
-
-		/*
-		 * Execution should not return from
-		 * machine_emergency_restart()
-		 */
-		machine_emergency_restart();
-		kgdb_connected = 0;
-
-		return 1;
-	}
-	return 0;
-}
-
-/* Handle the 'q' query packets */
-static void gdb_cmd_query(struct kgdb_state *ks)
-{
-	struct task_struct *g;
-	struct task_struct *p;
-	unsigned char thref[8];
-	char *ptr;
-	int i;
-	int cpu;
-	int finished = 0;
-
-	switch (remcom_in_buffer[1]) {
-	case 's':
-	case 'f':
-		if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10)) {
-			error_packet(remcom_out_buffer, -EINVAL);
-			break;
-		}
-
-		i = 0;
-		remcom_out_buffer[0] = 'm';
-		ptr = remcom_out_buffer + 1;
-		if (remcom_in_buffer[1] == 'f') {
-			/* Each cpu is a shadow thread */
-			for_each_online_cpu(cpu) {
-				ks->thr_query = 0;
-				int_to_threadref(thref, -cpu - 2);
-				pack_threadid(ptr, thref);
-				ptr += BUF_THREAD_ID_SIZE;
-				*(ptr++) = ',';
-				i++;
-			}
-		}
-
-		do_each_thread(g, p) {
-			if (i >= ks->thr_query && !finished) {
-				int_to_threadref(thref, p->pid);
-				pack_threadid(ptr, thref);
-				ptr += BUF_THREAD_ID_SIZE;
-				*(ptr++) = ',';
-				ks->thr_query++;
-				if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0)
-					finished = 1;
-			}
-			i++;
-		} while_each_thread(g, p);
-
-		*(--ptr) = '\0';
-		break;
-
-	case 'C':
-		/* Current thread id */
-		strcpy(remcom_out_buffer, "QC");
-		ks->threadid = shadow_pid(current->pid);
-		int_to_threadref(thref, ks->threadid);
-		pack_threadid(remcom_out_buffer + 2, thref);
-		break;
-	case 'T':
-		if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16)) {
-			error_packet(remcom_out_buffer, -EINVAL);
-			break;
-		}
-		ks->threadid = 0;
-		ptr = remcom_in_buffer + 17;
-		kgdb_hex2long(&ptr, &ks->threadid);
-		if (!getthread(ks->linux_regs, ks->threadid)) {
-			error_packet(remcom_out_buffer, -EINVAL);
-			break;
-		}
-		if ((int)ks->threadid > 0) {
-			kgdb_mem2hex(getthread(ks->linux_regs,
-					ks->threadid)->comm,
-					remcom_out_buffer, 16);
-		} else {
-			static char tmpstr[23 + BUF_THREAD_ID_SIZE];
-
-			sprintf(tmpstr, "shadowCPU%d",
-					(int)(-ks->threadid - 2));
-			kgdb_mem2hex(tmpstr, remcom_out_buffer, strlen(tmpstr));
-		}
-		break;
-	}
-}
-
-/* Handle the 'H' task query packets */
-static void gdb_cmd_task(struct kgdb_state *ks)
-{
-	struct task_struct *thread;
-	char *ptr;
-
-	switch (remcom_in_buffer[1]) {
-	case 'g':
-		ptr = &remcom_in_buffer[2];
-		kgdb_hex2long(&ptr, &ks->threadid);
-		thread = getthread(ks->linux_regs, ks->threadid);
-		if (!thread && ks->threadid > 0) {
-			error_packet(remcom_out_buffer, -EINVAL);
-			break;
-		}
-		kgdb_usethread = thread;
-		ks->kgdb_usethreadid = ks->threadid;
-		strcpy(remcom_out_buffer, "OK");
-		break;
-	case 'c':
-		ptr = &remcom_in_buffer[2];
-		kgdb_hex2long(&ptr, &ks->threadid);
-		if (!ks->threadid) {
-			kgdb_contthread = NULL;
-		} else {
-			thread = getthread(ks->linux_regs, ks->threadid);
-			if (!thread && ks->threadid > 0) {
-				error_packet(remcom_out_buffer, -EINVAL);
-				break;
-			}
-			kgdb_contthread = thread;
-		}
-		strcpy(remcom_out_buffer, "OK");
-		break;
-	}
-}
-
-/* Handle the 'T' thread query packets */
-static void gdb_cmd_thread(struct kgdb_state *ks)
-{
-	char *ptr = &remcom_in_buffer[1];
-	struct task_struct *thread;
-
-	kgdb_hex2long(&ptr, &ks->threadid);
-	thread = getthread(ks->linux_regs, ks->threadid);
-	if (thread)
-		strcpy(remcom_out_buffer, "OK");
-	else
-		error_packet(remcom_out_buffer, -EINVAL);
-}
-
-/* Handle the 'z' or 'Z' breakpoint remove or set packets */
-static void gdb_cmd_break(struct kgdb_state *ks)
-{
-	/*
-	 * Since GDB-5.3, it's been drafted that '0' is a software
-	 * breakpoint, '1' is a hardware breakpoint, so let's do that.
-	 */
-	char *bpt_type = &remcom_in_buffer[1];
-	char *ptr = &remcom_in_buffer[2];
-	unsigned long addr;
-	unsigned long length;
-	int error = 0;
-
-	if (arch_kgdb_ops.set_hw_breakpoint && *bpt_type >= '1') {
-		/* Unsupported */
-		if (*bpt_type > '4')
-			return;
-	} else {
-		if (*bpt_type != '0' && *bpt_type != '1')
-			/* Unsupported. */
-			return;
-	}
-
-	/*
-	 * Test if this is a hardware breakpoint, and
-	 * if we support it:
-	 */
-	if (*bpt_type == '1' && !(arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT))
-		/* Unsupported. */
-		return;
-
-	if (*(ptr++) != ',') {
-		error_packet(remcom_out_buffer, -EINVAL);
-		return;
-	}
-	if (!kgdb_hex2long(&ptr, &addr)) {
-		error_packet(remcom_out_buffer, -EINVAL);
-		return;
-	}
-	if (*(ptr++) != ',' ||
-		!kgdb_hex2long(&ptr, &length)) {
-		error_packet(remcom_out_buffer, -EINVAL);
-		return;
-	}
-
-	if (remcom_in_buffer[0] == 'Z' && *bpt_type == '0')
-		error = kgdb_set_sw_break(addr);
-	else if (remcom_in_buffer[0] == 'z' && *bpt_type == '0')
-		error = kgdb_remove_sw_break(addr);
-	else if (remcom_in_buffer[0] == 'Z')
-		error = arch_kgdb_ops.set_hw_breakpoint(addr,
-			(int)length, *bpt_type - '0');
-	else if (remcom_in_buffer[0] == 'z')
-		error = arch_kgdb_ops.remove_hw_breakpoint(addr,
-			(int) length, *bpt_type - '0');
-
-	if (error == 0)
-		strcpy(remcom_out_buffer, "OK");
-	else
-		error_packet(remcom_out_buffer, error);
-}
-
-/* Handle the 'C' signal / exception passing packets */
-static int gdb_cmd_exception_pass(struct kgdb_state *ks)
-{
-	/* C09 == pass exception
-	 * C15 == detach kgdb, pass exception
-	 */
-	if (remcom_in_buffer[1] == '0' && remcom_in_buffer[2] == '9') {
-
-		ks->pass_exception = 1;
-		remcom_in_buffer[0] = 'c';
-
-	} else if (remcom_in_buffer[1] == '1' && remcom_in_buffer[2] == '5') {
-
-		ks->pass_exception = 1;
-		remcom_in_buffer[0] = 'D';
-		remove_all_break();
-		kgdb_connected = 0;
-		return 1;
-
-	} else {
-		kgdb_msg_write("KGDB only knows signal 9 (pass)"
-			" and 15 (pass and disconnect)\n"
-			"Executing a continue without signal passing\n", 0);
-		remcom_in_buffer[0] = 'c';
-	}
-
-	/* Indicate fall through */
-	return -1;
-}
-
-/*
- * This function performs all gdbserial command procesing
- */
-static int gdb_serial_stub(struct kgdb_state *ks)
-{
-	int error = 0;
-	int tmp;
-
-	/* Clear the out buffer. */
-	memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer));
-
-	if (kgdb_connected) {
-		unsigned char thref[8];
-		char *ptr;
-
-		/* Reply to host that an exception has occurred */
-		ptr = remcom_out_buffer;
-		*ptr++ = 'T';
-		ptr = pack_hex_byte(ptr, ks->signo);
-		ptr += strlen(strcpy(ptr, "thread:"));
-		int_to_threadref(thref, shadow_pid(current->pid));
-		ptr = pack_threadid(ptr, thref);
-		*ptr++ = ';';
-		put_packet(remcom_out_buffer);
-	}
-
-	kgdb_usethread = kgdb_info[ks->cpu].task;
-	ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid);
-	ks->pass_exception = 0;
-
-	while (1) {
-		error = 0;
-
-		/* Clear the out buffer. */
-		memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer));
-
-		get_packet(remcom_in_buffer);
-
-		switch (remcom_in_buffer[0]) {
-		case '?': /* gdbserial status */
-			gdb_cmd_status(ks);
-			break;
-		case 'g': /* return the value of the CPU registers */
-			gdb_cmd_getregs(ks);
-			break;
-		case 'G': /* set the value of the CPU registers - return OK */
-			gdb_cmd_setregs(ks);
-			break;
-		case 'm': /* mAA..AA,LLLL  Read LLLL bytes at address AA..AA */
-			gdb_cmd_memread(ks);
-			break;
-		case 'M': /* MAA..AA,LLLL: Write LLLL bytes at address AA..AA */
-			gdb_cmd_memwrite(ks);
-			break;
-		case 'X': /* XAA..AA,LLLL: Write LLLL bytes at address AA..AA */
-			gdb_cmd_binwrite(ks);
-			break;
-			/* kill or detach. KGDB should treat this like a
-			 * continue.
-			 */
-		case 'D': /* Debugger detach */
-		case 'k': /* Debugger detach via kill */
-			gdb_cmd_detachkill(ks);
-			goto default_handle;
-		case 'R': /* Reboot */
-			if (gdb_cmd_reboot(ks))
-				goto default_handle;
-			break;
-		case 'q': /* query command */
-			gdb_cmd_query(ks);
-			break;
-		case 'H': /* task related */
-			gdb_cmd_task(ks);
-			break;
-		case 'T': /* Query thread status */
-			gdb_cmd_thread(ks);
-			break;
-		case 'z': /* Break point remove */
-		case 'Z': /* Break point set */
-			gdb_cmd_break(ks);
-			break;
-		case 'C': /* Exception passing */
-			tmp = gdb_cmd_exception_pass(ks);
-			if (tmp > 0)
-				goto default_handle;
-			if (tmp == 0)
-				break;
-			/* Fall through on tmp < 0 */
-		case 'c': /* Continue packet */
-		case 's': /* Single step packet */
-			if (kgdb_contthread && kgdb_contthread != current) {
-				/* Can't switch threads in kgdb */
-				error_packet(remcom_out_buffer, -EINVAL);
-				break;
-			}
-			kgdb_activate_sw_breakpoints();
-			/* Fall through to default processing */
-		default:
-default_handle:
-			error = kgdb_arch_handle_exception(ks->ex_vector,
-						ks->signo,
-						ks->err_code,
-						remcom_in_buffer,
-						remcom_out_buffer,
-						ks->linux_regs);
-			/*
-			 * Leave cmd processing on error, detach,
-			 * kill, continue, or single step.
-			 */
-			if (error >= 0 || remcom_in_buffer[0] == 'D' ||
-			    remcom_in_buffer[0] == 'k') {
-				error = 0;
-				goto kgdb_exit;
-			}
-
-		}
-
-		/* reply to the request */
-		put_packet(remcom_out_buffer);
-	}
-
-kgdb_exit:
-	if (ks->pass_exception)
-		error = 1;
-	return error;
-}
-
-static int kgdb_reenter_check(struct kgdb_state *ks)
-{
-	unsigned long addr;
-
-	if (atomic_read(&kgdb_active) != raw_smp_processor_id())
-		return 0;
-
-	/* Panic on recursive debugger calls: */
-	exception_level++;
-	addr = kgdb_arch_pc(ks->ex_vector, ks->linux_regs);
-	kgdb_deactivate_sw_breakpoints();
-
-	/*
-	 * If the break point removed ok at the place exception
-	 * occurred, try to recover and print a warning to the end
-	 * user because the user planted a breakpoint in a place that
-	 * KGDB needs in order to function.
-	 */
-	if (kgdb_remove_sw_break(addr) == 0) {
-		exception_level = 0;
-		kgdb_skipexception(ks->ex_vector, ks->linux_regs);
-		kgdb_activate_sw_breakpoints();
-		printk(KERN_CRIT "KGDB: re-enter error: breakpoint removed %lx\n",
-			addr);
-		WARN_ON_ONCE(1);
-
-		return 1;
-	}
-	remove_all_break();
-	kgdb_skipexception(ks->ex_vector, ks->linux_regs);
-
-	if (exception_level > 1) {
-		dump_stack();
-		panic("Recursive entry to debugger");
-	}
-
-	printk(KERN_CRIT "KGDB: re-enter exception: ALL breakpoints killed\n");
-	dump_stack();
-	panic("Recursive entry to debugger");
-
-	return 1;
-}
-
-static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
-{
-	unsigned long flags;
-	int sstep_tries = 100;
-	int error = 0;
-	int i, cpu;
-	int trace_on = 0;
-acquirelock:
-	/*
-	 * Interrupts will be restored by the 'trap return' code, except when
-	 * single stepping.
-	 */
-	local_irq_save(flags);
-
-	cpu = ks->cpu;
-	kgdb_info[cpu].debuggerinfo = regs;
-	kgdb_info[cpu].task = current;
-	/*
-	 * Make sure the above info reaches the primary CPU before
-	 * our cpu_in_kgdb[] flag setting does:
-	 */
-	atomic_inc(&cpu_in_kgdb[cpu]);
-
-	/*
-	 * CPU will loop if it is a slave or request to become a kgdb
-	 * master cpu and acquire the kgdb_active lock:
-	 */
-	while (1) {
-		if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
-			if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
-				break;
-		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
-			if (!atomic_read(&passive_cpu_wait[cpu]))
-				goto return_normal;
-		} else {
-return_normal:
-			/* Return to normal operation by executing any
-			 * hw breakpoint fixup.
-			 */
-			if (arch_kgdb_ops.correct_hw_break)
-				arch_kgdb_ops.correct_hw_break();
-			if (trace_on)
-				tracing_on();
-			atomic_dec(&cpu_in_kgdb[cpu]);
-			touch_softlockup_watchdog_sync();
-			clocksource_touch_watchdog();
-			local_irq_restore(flags);
-			return 0;
-		}
-		cpu_relax();
-	}
-
-	/*
-	 * For single stepping, try to only enter on the processor
-	 * that was single stepping.  To gaurd against a deadlock, the
-	 * kernel will only try for the value of sstep_tries before
-	 * giving up and continuing on.
-	 */
-	if (atomic_read(&kgdb_cpu_doing_single_step) != -1 &&
-	    (kgdb_info[cpu].task &&
-	     kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
-		atomic_set(&kgdb_active, -1);
-		touch_softlockup_watchdog_sync();
-		clocksource_touch_watchdog();
-		local_irq_restore(flags);
-
-		goto acquirelock;
-	}
-
-	if (!kgdb_io_ready(1)) {
-		error = 1;
-		goto kgdb_restore; /* No I/O connection, so resume the system */
-	}
-
-	/*
-	 * Don't enter if we have hit a removed breakpoint.
-	 */
-	if (kgdb_skipexception(ks->ex_vector, ks->linux_regs))
-		goto kgdb_restore;
-
-	/* Call the I/O driver's pre_exception routine */
-	if (kgdb_io_ops->pre_exception)
-		kgdb_io_ops->pre_exception();
-
-	kgdb_disable_hw_debug(ks->linux_regs);
-
-	/*
-	 * Get the passive CPU lock which will hold all the non-primary
-	 * CPU in a spin state while the debugger is active
-	 */
-	if (!kgdb_single_step) {
-		for (i = 0; i < NR_CPUS; i++)
-			atomic_inc(&passive_cpu_wait[i]);
-	}
-
-#ifdef CONFIG_SMP
-	/* Signal the other CPUs to enter kgdb_wait() */
-	if ((!kgdb_single_step) && kgdb_do_roundup)
-		kgdb_roundup_cpus(flags);
-#endif
-
-	/*
-	 * Wait for the other CPUs to be notified and be waiting for us:
-	 */
-	for_each_online_cpu(i) {
-		while (!atomic_read(&cpu_in_kgdb[i]))
-			cpu_relax();
-	}
-
-	/*
-	 * At this point the primary processor is completely
-	 * in the debugger and all secondary CPUs are quiescent
-	 */
-	kgdb_post_primary_code(ks->linux_regs, ks->ex_vector, ks->err_code);
-	kgdb_deactivate_sw_breakpoints();
-	kgdb_single_step = 0;
-	kgdb_contthread = current;
-	exception_level = 0;
-	trace_on = tracing_is_on();
-	if (trace_on)
-		tracing_off();
-
-	/* Talk to debugger with gdbserial protocol */
-	error = gdb_serial_stub(ks);
-
-	/* Call the I/O driver's post_exception routine */
-	if (kgdb_io_ops->post_exception)
-		kgdb_io_ops->post_exception();
-
-	atomic_dec(&cpu_in_kgdb[ks->cpu]);
-
-	if (!kgdb_single_step) {
-		for (i = NR_CPUS-1; i >= 0; i--)
-			atomic_dec(&passive_cpu_wait[i]);
-		/*
-		 * Wait till all the CPUs have quit
-		 * from the debugger.
-		 */
-		for_each_online_cpu(i) {
-			while (atomic_read(&cpu_in_kgdb[i]))
-				cpu_relax();
-		}
-	}
-
-kgdb_restore:
-	if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
-		int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step);
-		if (kgdb_info[sstep_cpu].task)
-			kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid;
-		else
-			kgdb_sstep_pid = 0;
-	}
-	if (trace_on)
-		tracing_on();
-	/* Free kgdb_active */
-	atomic_set(&kgdb_active, -1);
-	touch_softlockup_watchdog_sync();
-	clocksource_touch_watchdog();
-	local_irq_restore(flags);
-
-	return error;
-}
-
-/*
- * kgdb_handle_exception() - main entry point from a kernel exception
- *
- * Locking hierarchy:
- *	interface locks, if any (begin_session)
- *	kgdb lock (kgdb_active)
- */
-int
-kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
-{
-	struct kgdb_state kgdb_var;
-	struct kgdb_state *ks = &kgdb_var;
-	int ret;
-
-	ks->cpu			= raw_smp_processor_id();
-	ks->ex_vector		= evector;
-	ks->signo		= signo;
-	ks->ex_vector		= evector;
-	ks->err_code		= ecode;
-	ks->kgdb_usethreadid	= 0;
-	ks->linux_regs		= regs;
-
-	if (kgdb_reenter_check(ks))
-		return 0; /* Ouch, double exception ! */
-	kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
-	ret = kgdb_cpu_enter(ks, regs);
-	kgdb_info[ks->cpu].exception_state &= ~DCPU_WANT_MASTER;
-	return ret;
-}
-
-int kgdb_nmicallback(int cpu, void *regs)
-{
-#ifdef CONFIG_SMP
-	struct kgdb_state kgdb_var;
-	struct kgdb_state *ks = &kgdb_var;
-
-	memset(ks, 0, sizeof(struct kgdb_state));
-	ks->cpu			= cpu;
-	ks->linux_regs		= regs;
-
-	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-	    atomic_read(&kgdb_active) != -1 &&
-	    atomic_read(&kgdb_active) != cpu) {
-		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
-		kgdb_cpu_enter(ks, regs);
-		kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
-		return 0;
-	}
-#endif
-	return 1;
-}
-
-static void kgdb_console_write(struct console *co, const char *s,
-   unsigned count)
-{
-	unsigned long flags;
-
-	/* If we're debugging, or KGDB has not connected, don't try
-	 * and print. */
-	if (!kgdb_connected || atomic_read(&kgdb_active) != -1)
-		return;
-
-	local_irq_save(flags);
-	kgdb_msg_write(s, count);
-	local_irq_restore(flags);
-}
-
-static struct console kgdbcons = {
-	.name		= "kgdb",
-	.write		= kgdb_console_write,
-	.flags		= CON_PRINTBUFFER | CON_ENABLED,
-	.index		= -1,
-};
-
-#ifdef CONFIG_MAGIC_SYSRQ
-static void sysrq_handle_gdb(int key, struct tty_struct *tty)
-{
-	if (!kgdb_io_ops) {
-		printk(KERN_CRIT "ERROR: No KGDB I/O module available\n");
-		return;
-	}
-	if (!kgdb_connected)
-		printk(KERN_CRIT "Entering KGDB\n");
-
-	kgdb_breakpoint();
-}
-
-static struct sysrq_key_op sysrq_gdb_op = {
-	.handler	= sysrq_handle_gdb,
-	.help_msg	= "debug(G)",
-	.action_msg	= "DEBUG",
-};
-#endif
-
-static void kgdb_register_callbacks(void)
-{
-	if (!kgdb_io_module_registered) {
-		kgdb_io_module_registered = 1;
-		kgdb_arch_init();
-#ifdef CONFIG_MAGIC_SYSRQ
-		register_sysrq_key('g', &sysrq_gdb_op);
-#endif
-		if (kgdb_use_con && !kgdb_con_registered) {
-			register_console(&kgdbcons);
-			kgdb_con_registered = 1;
-		}
-	}
-}
-
-static void kgdb_unregister_callbacks(void)
-{
-	/*
-	 * When this routine is called KGDB should unregister from the
-	 * panic handler and clean up, making sure it is not handling any
-	 * break exceptions at the time.
-	 */
-	if (kgdb_io_module_registered) {
-		kgdb_io_module_registered = 0;
-		kgdb_arch_exit();
-#ifdef CONFIG_MAGIC_SYSRQ
-		unregister_sysrq_key('g', &sysrq_gdb_op);
-#endif
-		if (kgdb_con_registered) {
-			unregister_console(&kgdbcons);
-			kgdb_con_registered = 0;
-		}
-	}
-}
-
-static void kgdb_initial_breakpoint(void)
-{
-	kgdb_break_asap = 0;
-
-	printk(KERN_CRIT "kgdb: Waiting for connection from remote gdb...\n");
-	kgdb_breakpoint();
-}
-
-/**
- *	kgdb_register_io_module - register KGDB IO module
- *	@new_kgdb_io_ops: the io ops vector
- *
- *	Register it with the KGDB core.
- */
-int kgdb_register_io_module(struct kgdb_io *new_kgdb_io_ops)
-{
-	int err;
-
-	spin_lock(&kgdb_registration_lock);
-
-	if (kgdb_io_ops) {
-		spin_unlock(&kgdb_registration_lock);
-
-		printk(KERN_ERR "kgdb: Another I/O driver is already "
-				"registered with KGDB.\n");
-		return -EBUSY;
-	}
-
-	if (new_kgdb_io_ops->init) {
-		err = new_kgdb_io_ops->init();
-		if (err) {
-			spin_unlock(&kgdb_registration_lock);
-			return err;
-		}
-	}
-
-	kgdb_io_ops = new_kgdb_io_ops;
-
-	spin_unlock(&kgdb_registration_lock);
-
-	printk(KERN_INFO "kgdb: Registered I/O driver %s.\n",
-	       new_kgdb_io_ops->name);
-
-	/* Arm KGDB now. */
-	kgdb_register_callbacks();
-
-	if (kgdb_break_asap)
-		kgdb_initial_breakpoint();
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(kgdb_register_io_module);
-
-/**
- *	kkgdb_unregister_io_module - unregister KGDB IO module
- *	@old_kgdb_io_ops: the io ops vector
- *
- *	Unregister it with the KGDB core.
- */
-void kgdb_unregister_io_module(struct kgdb_io *old_kgdb_io_ops)
-{
-	BUG_ON(kgdb_connected);
-
-	/*
-	 * KGDB is no longer able to communicate out, so
-	 * unregister our callbacks and reset state.
-	 */
-	kgdb_unregister_callbacks();
-
-	spin_lock(&kgdb_registration_lock);
-
-	WARN_ON_ONCE(kgdb_io_ops != old_kgdb_io_ops);
-	kgdb_io_ops = NULL;
-
-	spin_unlock(&kgdb_registration_lock);
-
-	printk(KERN_INFO
-		"kgdb: Unregistered I/O driver %s, debugger disabled.\n",
-		old_kgdb_io_ops->name);
-}
-EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
-
-/**
- * kgdb_breakpoint - generate breakpoint exception
- *
- * This function will generate a breakpoint exception.  It is used at the
- * beginning of a program to sync up with a debugger and can be used
- * otherwise as a quick means to stop program execution and "break" into
- * the debugger.
- */
-void kgdb_breakpoint(void)
-{
-	atomic_inc(&kgdb_setting_breakpoint);
-	wmb(); /* Sync point before breakpoint */
-	arch_kgdb_breakpoint();
-	wmb(); /* Sync point after breakpoint */
-	atomic_dec(&kgdb_setting_breakpoint);
-}
-EXPORT_SYMBOL_GPL(kgdb_breakpoint);
-
-static int __init opt_kgdb_wait(char *str)
-{
-	kgdb_break_asap = 1;
-
-	if (kgdb_io_module_registered)
-		kgdb_initial_breakpoint();
-
-	return 0;
-}
-
-early_param("kgdbwait", opt_kgdb_wait);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 0ed46f3e51e..282035f3ae9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1588,6 +1588,72 @@ static void __kprobes kill_kprobe(struct kprobe *p)
 	arch_remove_kprobe(p);
 }
 
+/* Disable one kprobe */
+int __kprobes disable_kprobe(struct kprobe *kp)
+{
+	int ret = 0;
+	struct kprobe *p;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Check whether specified probe is valid. */
+	p = __get_valid_kprobe(kp);
+	if (unlikely(p == NULL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* If the probe is already disabled (or gone), just return */
+	if (kprobe_disabled(kp))
+		goto out;
+
+	kp->flags |= KPROBE_FLAG_DISABLED;
+	if (p != kp)
+		/* When kp != p, p is always enabled. */
+		try_to_disable_aggr_kprobe(p);
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p))
+		disarm_kprobe(p);
+out:
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(disable_kprobe);
+
+/* Enable one kprobe */
+int __kprobes enable_kprobe(struct kprobe *kp)
+{
+	int ret = 0;
+	struct kprobe *p;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Check whether specified probe is valid. */
+	p = __get_valid_kprobe(kp);
+	if (unlikely(p == NULL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (kprobe_gone(kp)) {
+		/* This kprobe has gone, we couldn't enable it. */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (p != kp)
+		kp->flags &= ~KPROBE_FLAG_DISABLED;
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
+		p->flags &= ~KPROBE_FLAG_DISABLED;
+		arm_kprobe(p);
+	}
+out:
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(enable_kprobe);
+
 void __kprobes dump_kprobe(struct kprobe *kp)
 {
 	printk(KERN_WARNING "Dumping kprobe:\n");
@@ -1805,72 +1871,6 @@ static const struct file_operations debugfs_kprobes_operations = {
 	.release        = seq_release,
 };
 
-/* Disable one kprobe */
-int __kprobes disable_kprobe(struct kprobe *kp)
-{
-	int ret = 0;
-	struct kprobe *p;
-
-	mutex_lock(&kprobe_mutex);
-
-	/* Check whether specified probe is valid. */
-	p = __get_valid_kprobe(kp);
-	if (unlikely(p == NULL)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* If the probe is already disabled (or gone), just return */
-	if (kprobe_disabled(kp))
-		goto out;
-
-	kp->flags |= KPROBE_FLAG_DISABLED;
-	if (p != kp)
-		/* When kp != p, p is always enabled. */
-		try_to_disable_aggr_kprobe(p);
-
-	if (!kprobes_all_disarmed && kprobe_disabled(p))
-		disarm_kprobe(p);
-out:
-	mutex_unlock(&kprobe_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(disable_kprobe);
-
-/* Enable one kprobe */
-int __kprobes enable_kprobe(struct kprobe *kp)
-{
-	int ret = 0;
-	struct kprobe *p;
-
-	mutex_lock(&kprobe_mutex);
-
-	/* Check whether specified probe is valid. */
-	p = __get_valid_kprobe(kp);
-	if (unlikely(p == NULL)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (kprobe_gone(kp)) {
-		/* This kprobe has gone, we couldn't enable it. */
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (p != kp)
-		kp->flags &= ~KPROBE_FLAG_DISABLED;
-
-	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
-		p->flags &= ~KPROBE_FLAG_DISABLED;
-		arm_kprobe(p);
-	}
-out:
-	mutex_unlock(&kprobe_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(enable_kprobe);
-
 static void __kprobes arm_all_kprobes(void)
 {
 	struct hlist_head *head;
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 21fe3c42694..0b624e79180 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -138,7 +138,8 @@ extern const void __start_notes __attribute__((weak));
 extern const void __stop_notes __attribute__((weak));
 #define	notes_size (&__stop_notes - &__start_notes)
 
-static ssize_t notes_read(struct kobject *kobj, struct bin_attribute *bin_attr,
+static ssize_t notes_read(struct file *filp, struct kobject *kobj,
+			  struct bin_attribute *bin_attr,
 			  char *buf, loff_t off, size_t count)
 {
 	memcpy(buf, &__start_notes + off, count);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 2594e1ce41c..54286798c37 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -431,20 +431,7 @@ static struct stack_trace lockdep_init_trace = {
 /*
  * Various lockdep statistics:
  */
-atomic_t chain_lookup_hits;
-atomic_t chain_lookup_misses;
-atomic_t hardirqs_on_events;
-atomic_t hardirqs_off_events;
-atomic_t redundant_hardirqs_on;
-atomic_t redundant_hardirqs_off;
-atomic_t softirqs_on_events;
-atomic_t softirqs_off_events;
-atomic_t redundant_softirqs_on;
-atomic_t redundant_softirqs_off;
-atomic_t nr_unused_locks;
-atomic_t nr_cyclic_checks;
-atomic_t nr_find_usage_forwards_checks;
-atomic_t nr_find_usage_backwards_checks;
+DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
 #endif
 
 /*
@@ -748,7 +735,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		return NULL;
 	}
 	class = lock_classes + nr_lock_classes++;
-	debug_atomic_inc(&nr_unused_locks);
+	debug_atomic_inc(nr_unused_locks);
 	class->key = key;
 	class->name = lock->name;
 	class->subclass = subclass;
@@ -818,7 +805,8 @@ static struct lock_list *alloc_list_entry(void)
  * Add a new dependency to the head of the list:
  */
 static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
-			    struct list_head *head, unsigned long ip, int distance)
+			    struct list_head *head, unsigned long ip,
+			    int distance, struct stack_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -829,11 +817,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
 	if (!entry)
 		return 0;
 
-	if (!save_trace(&entry->trace))
-		return 0;
-
 	entry->class = this;
 	entry->distance = distance;
+	entry->trace = *trace;
 	/*
 	 * Since we never remove from the dependency list, the list can
 	 * be walked lockless by other CPUs, it's only allocation
@@ -1205,7 +1191,7 @@ check_noncircular(struct lock_list *root, struct lock_class *target,
 {
 	int result;
 
-	debug_atomic_inc(&nr_cyclic_checks);
+	debug_atomic_inc(nr_cyclic_checks);
 
 	result = __bfs_forwards(root, target, class_equal, target_entry);
 
@@ -1242,7 +1228,7 @@ find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
 {
 	int result;
 
-	debug_atomic_inc(&nr_find_usage_forwards_checks);
+	debug_atomic_inc(nr_find_usage_forwards_checks);
 
 	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
 
@@ -1265,7 +1251,7 @@ find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
 {
 	int result;
 
-	debug_atomic_inc(&nr_find_usage_backwards_checks);
+	debug_atomic_inc(nr_find_usage_backwards_checks);
 
 	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
 
@@ -1635,12 +1621,20 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance)
+	       struct held_lock *next, int distance, int trylock_loop)
 {
 	struct lock_list *entry;
 	int ret;
 	struct lock_list this;
 	struct lock_list *uninitialized_var(target_entry);
+	/*
+	 * Static variable, serialized by the graph_lock().
+	 *
+	 * We use this static variable to save the stack trace in case
+	 * we call into this function multiple times due to encountering
+	 * trylocks in the held lock stack.
+	 */
+	static struct stack_trace trace;
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1688,20 +1682,23 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		}
 	}
 
+	if (!trylock_loop && !save_trace(&trace))
+		return 0;
+
 	/*
 	 * Ok, all validations passed, add the new lock
 	 * to the previous lock's dependency list:
 	 */
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
 			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance);
+			       next->acquire_ip, distance, &trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
 			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance);
+			       next->acquire_ip, distance, &trace);
 	if (!ret)
 		return 0;
 
@@ -1731,6 +1728,7 @@ static int
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
+	int trylock_loop = 0;
 	struct held_lock *hlock;
 
 	/*
@@ -1756,7 +1754,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		 * added:
 		 */
 		if (hlock->read != 2) {
-			if (!check_prev_add(curr, hlock, next, distance))
+			if (!check_prev_add(curr, hlock, next,
+						distance, trylock_loop))
 				return 0;
 			/*
 			 * Stop after the first non-trylock entry,
@@ -1779,6 +1778,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		if (curr->held_locks[depth].irq_context !=
 				curr->held_locks[depth-1].irq_context)
 			break;
+		trylock_loop = 1;
 	}
 	return 1;
 out_bug:
@@ -1825,7 +1825,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	list_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
-			debug_atomic_inc(&chain_lookup_hits);
+			debug_atomic_inc(chain_lookup_hits);
 			if (very_verbose(class))
 				printk("\nhash chain already cached, key: "
 					"%016Lx tail class: [%p] %s\n",
@@ -1890,7 +1890,7 @@ cache_hit:
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
 	list_add_tail_rcu(&chain->entry, hash_head);
-	debug_atomic_inc(&chain_lookup_misses);
+	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
 	return 1;
@@ -2311,7 +2311,12 @@ void trace_hardirqs_on_caller(unsigned long ip)
 		return;
 
 	if (unlikely(curr->hardirqs_enabled)) {
-		debug_atomic_inc(&redundant_hardirqs_on);
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but loosing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
 		return;
 	}
 	/* we'll do an OFF -> ON transition: */
@@ -2338,7 +2343,7 @@ void trace_hardirqs_on_caller(unsigned long ip)
 
 	curr->hardirq_enable_ip = ip;
 	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(&hardirqs_on_events);
+	debug_atomic_inc(hardirqs_on_events);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
@@ -2370,9 +2375,9 @@ void trace_hardirqs_off_caller(unsigned long ip)
 		curr->hardirqs_enabled = 0;
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
-		debug_atomic_inc(&hardirqs_off_events);
+		debug_atomic_inc(hardirqs_off_events);
 	} else
-		debug_atomic_inc(&redundant_hardirqs_off);
+		debug_atomic_inc(redundant_hardirqs_off);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 
@@ -2396,7 +2401,7 @@ void trace_softirqs_on(unsigned long ip)
 		return;
 
 	if (curr->softirqs_enabled) {
-		debug_atomic_inc(&redundant_softirqs_on);
+		debug_atomic_inc(redundant_softirqs_on);
 		return;
 	}
 
@@ -2406,7 +2411,7 @@ void trace_softirqs_on(unsigned long ip)
 	curr->softirqs_enabled = 1;
 	curr->softirq_enable_ip = ip;
 	curr->softirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(&softirqs_on_events);
+	debug_atomic_inc(softirqs_on_events);
 	/*
 	 * We are going to turn softirqs on, so set the
 	 * usage bit for all held locks, if hardirqs are
@@ -2436,10 +2441,10 @@ void trace_softirqs_off(unsigned long ip)
 		curr->softirqs_enabled = 0;
 		curr->softirq_disable_ip = ip;
 		curr->softirq_disable_event = ++curr->irq_events;
-		debug_atomic_inc(&softirqs_off_events);
+		debug_atomic_inc(softirqs_off_events);
 		DEBUG_LOCKS_WARN_ON(!softirq_count());
 	} else
-		debug_atomic_inc(&redundant_softirqs_off);
+		debug_atomic_inc(redundant_softirqs_off);
 }
 
 static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
@@ -2644,7 +2649,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 		break;
 	case LOCK_USED:
-		debug_atomic_dec(&nr_unused_locks);
+		debug_atomic_dec(nr_unused_locks);
 		break;
 	default:
 		if (!debug_locks_off_graph_unlock())
@@ -2706,6 +2711,8 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 }
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
+struct lock_class_key __lockdep_no_validate__;
+
 /*
  * This gets called for every mutex_lock*()/spin_lock*() operation.
  * We maintain the dependency maps and validate the locking attempt:
@@ -2740,6 +2747,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		return 0;
 	}
 
+	if (lock->key == &__lockdep_no_validate__)
+		check = 1;
+
 	if (!subclass)
 		class = lock->class_cache;
 	/*
@@ -2750,7 +2760,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		if (!class)
 			return 0;
 	}
-	debug_atomic_inc((atomic_t *)&class->ops);
+	atomic_inc((atomic_t *)&class->ops);
 	if (very_verbose(class)) {
 		printk("\nacquire class [%p] %s", class->key, class->name);
 		if (class->name_version > 1)
@@ -3227,7 +3237,7 @@ void lock_release(struct lockdep_map *lock, int nested,
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
-	trace_lock_release(lock, nested, ip);
+	trace_lock_release(lock, ip);
 	__lock_release(lock, nested, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -3380,7 +3390,7 @@ found_it:
 		hlock->holdtime_stamp = now;
 	}
 
-	trace_lock_acquired(lock, ip, waittime);
+	trace_lock_acquired(lock, ip);
 
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
@@ -3801,8 +3811,11 @@ void lockdep_rcu_dereference(const char *file, const int line)
 {
 	struct task_struct *curr = current;
 
+#ifndef CONFIG_PROVE_RCU_REPEATEDLY
 	if (!debug_locks_off())
 		return;
+#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
+	/* Note: the following can be executed concurrently, so be careful. */
 	printk("\n===================================================\n");
 	printk(  "[ INFO: suspicious rcu_dereference_check() usage. ]\n");
 	printk(  "---------------------------------------------------\n");
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index a2ee95ad131..4f560cfedc8 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -110,30 +110,60 @@ lockdep_count_backward_deps(struct lock_class *class)
 #endif
 
 #ifdef CONFIG_DEBUG_LOCKDEP
+
+#include <asm/local.h>
 /*
- * Various lockdep statistics:
+ * Various lockdep statistics.
+ * We want them per cpu as they are often accessed in fast path
+ * and we want to avoid too much cache bouncing.
  */
-extern atomic_t chain_lookup_hits;
-extern atomic_t chain_lookup_misses;
-extern atomic_t hardirqs_on_events;
-extern atomic_t hardirqs_off_events;
-extern atomic_t redundant_hardirqs_on;
-extern atomic_t redundant_hardirqs_off;
-extern atomic_t softirqs_on_events;
-extern atomic_t softirqs_off_events;
-extern atomic_t redundant_softirqs_on;
-extern atomic_t redundant_softirqs_off;
-extern atomic_t nr_unused_locks;
-extern atomic_t nr_cyclic_checks;
-extern atomic_t nr_cyclic_check_recursions;
-extern atomic_t nr_find_usage_forwards_checks;
-extern atomic_t nr_find_usage_forwards_recursions;
-extern atomic_t nr_find_usage_backwards_checks;
-extern atomic_t nr_find_usage_backwards_recursions;
-# define debug_atomic_inc(ptr)		atomic_inc(ptr)
-# define debug_atomic_dec(ptr)		atomic_dec(ptr)
-# define debug_atomic_read(ptr)		atomic_read(ptr)
+struct lockdep_stats {
+	int	chain_lookup_hits;
+	int	chain_lookup_misses;
+	int	hardirqs_on_events;
+	int	hardirqs_off_events;
+	int	redundant_hardirqs_on;
+	int	redundant_hardirqs_off;
+	int	softirqs_on_events;
+	int	softirqs_off_events;
+	int	redundant_softirqs_on;
+	int	redundant_softirqs_off;
+	int	nr_unused_locks;
+	int	nr_cyclic_checks;
+	int	nr_cyclic_check_recursions;
+	int	nr_find_usage_forwards_checks;
+	int	nr_find_usage_forwards_recursions;
+	int	nr_find_usage_backwards_checks;
+	int	nr_find_usage_backwards_recursions;
+};
+
+DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
+
+#define __debug_atomic_inc(ptr)					\
+	this_cpu_inc(lockdep_stats.ptr);
+
+#define debug_atomic_inc(ptr)			{		\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__this_cpu_inc(lockdep_stats.ptr);			\
+}
+
+#define debug_atomic_dec(ptr)			{		\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__this_cpu_dec(lockdep_stats.ptr);			\
+}
+
+#define debug_atomic_read(ptr)		({				\
+	struct lockdep_stats *__cpu_lockdep_stats;			\
+	unsigned long long __total = 0;					\
+	int __cpu;							\
+	for_each_possible_cpu(__cpu) {					\
+		__cpu_lockdep_stats = &per_cpu(lockdep_stats, __cpu);	\
+		__total += __cpu_lockdep_stats->ptr;			\
+	}								\
+	__total;							\
+})
 #else
+# define __debug_atomic_inc(ptr)	do { } while (0)
 # define debug_atomic_inc(ptr)		do { } while (0)
 # define debug_atomic_dec(ptr)		do { } while (0)
 # define debug_atomic_read(ptr)		0
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d4aba4f3584..59b76c8ce9d 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -184,34 +184,34 @@ static const struct file_operations proc_lockdep_chains_operations = {
 static void lockdep_stats_debug_show(struct seq_file *m)
 {
 #ifdef CONFIG_DEBUG_LOCKDEP
-	unsigned int hi1 = debug_atomic_read(&hardirqs_on_events),
-		     hi2 = debug_atomic_read(&hardirqs_off_events),
-		     hr1 = debug_atomic_read(&redundant_hardirqs_on),
-		     hr2 = debug_atomic_read(&redundant_hardirqs_off),
-		     si1 = debug_atomic_read(&softirqs_on_events),
-		     si2 = debug_atomic_read(&softirqs_off_events),
-		     sr1 = debug_atomic_read(&redundant_softirqs_on),
-		     sr2 = debug_atomic_read(&redundant_softirqs_off);
-
-	seq_printf(m, " chain lookup misses:           %11u\n",
-		debug_atomic_read(&chain_lookup_misses));
-	seq_printf(m, " chain lookup hits:             %11u\n",
-		debug_atomic_read(&chain_lookup_hits));
-	seq_printf(m, " cyclic checks:                 %11u\n",
-		debug_atomic_read(&nr_cyclic_checks));
-	seq_printf(m, " find-mask forwards checks:     %11u\n",
-		debug_atomic_read(&nr_find_usage_forwards_checks));
-	seq_printf(m, " find-mask backwards checks:    %11u\n",
-		debug_atomic_read(&nr_find_usage_backwards_checks));
-
-	seq_printf(m, " hardirq on events:             %11u\n", hi1);
-	seq_printf(m, " hardirq off events:            %11u\n", hi2);
-	seq_printf(m, " redundant hardirq ons:         %11u\n", hr1);
-	seq_printf(m, " redundant hardirq offs:        %11u\n", hr2);
-	seq_printf(m, " softirq on events:             %11u\n", si1);
-	seq_printf(m, " softirq off events:            %11u\n", si2);
-	seq_printf(m, " redundant softirq ons:         %11u\n", sr1);
-	seq_printf(m, " redundant softirq offs:        %11u\n", sr2);
+	unsigned long long hi1 = debug_atomic_read(hardirqs_on_events),
+			   hi2 = debug_atomic_read(hardirqs_off_events),
+			   hr1 = debug_atomic_read(redundant_hardirqs_on),
+			   hr2 = debug_atomic_read(redundant_hardirqs_off),
+			   si1 = debug_atomic_read(softirqs_on_events),
+			   si2 = debug_atomic_read(softirqs_off_events),
+			   sr1 = debug_atomic_read(redundant_softirqs_on),
+			   sr2 = debug_atomic_read(redundant_softirqs_off);
+
+	seq_printf(m, " chain lookup misses:           %11llu\n",
+		debug_atomic_read(chain_lookup_misses));
+	seq_printf(m, " chain lookup hits:             %11llu\n",
+		debug_atomic_read(chain_lookup_hits));
+	seq_printf(m, " cyclic checks:                 %11llu\n",
+		debug_atomic_read(nr_cyclic_checks));
+	seq_printf(m, " find-mask forwards checks:     %11llu\n",
+		debug_atomic_read(nr_find_usage_forwards_checks));
+	seq_printf(m, " find-mask backwards checks:    %11llu\n",
+		debug_atomic_read(nr_find_usage_backwards_checks));
+
+	seq_printf(m, " hardirq on events:             %11llu\n", hi1);
+	seq_printf(m, " hardirq off events:            %11llu\n", hi2);
+	seq_printf(m, " redundant hardirq ons:         %11llu\n", hr1);
+	seq_printf(m, " redundant hardirq offs:        %11llu\n", hr2);
+	seq_printf(m, " softirq on events:             %11llu\n", si1);
+	seq_printf(m, " softirq off events:            %11llu\n", si2);
+	seq_printf(m, " redundant softirq ons:         %11llu\n", sr1);
+	seq_printf(m, " redundant softirq offs:        %11llu\n", sr2);
 #endif
 }
 
@@ -263,7 +263,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 #endif
 	}
 #ifdef CONFIG_DEBUG_LOCKDEP
-	DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
+	DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
 #endif
 	seq_printf(m, " lock-classes:                  %11lu [max: %lu]\n",
 			nr_lock_classes, MAX_LOCKDEP_KEYS);
diff --git a/kernel/module.c b/kernel/module.c
index 1016b75b026..3c4fc4bb4b8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -59,8 +59,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
 
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
 #if 0
 #define DEBUGP printk
 #else
@@ -79,6 +77,10 @@ EXPORT_TRACEPOINT_SYMBOL(module_get);
 DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
+#ifdef CONFIG_KGDB_KDB
+struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
+#endif /* CONFIG_KGDB_KDB */
+
 
 /* Block module loading/unloading? */
 int modules_disabled = 0;
@@ -515,6 +517,9 @@ MODINFO_ATTR(srcversion);
 static char last_unloaded_module[MODULE_NAME_LEN+1];
 
 #ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
@@ -723,16 +728,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	/* Create stop_machine threads since free_module relies on
-	 * a non-failing stop_machine call. */
-	ret = stop_machine_create();
-	if (ret)
-		return ret;
-
-	if (mutex_lock_interruptible(&module_mutex) != 0) {
-		ret = -EINTR;
-		goto out_stop;
-	}
+	if (mutex_lock_interruptible(&module_mutex) != 0)
+		return -EINTR;
 
 	mod = find_module(name);
 	if (!mod) {
@@ -792,8 +789,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 
  out:
 	mutex_unlock(&module_mutex);
-out_stop:
-	stop_machine_destroy();
 	return ret;
 }
 
@@ -867,8 +862,7 @@ void module_put(struct module *module)
 		smp_wmb(); /* see comment in module_refcount */
 		__this_cpu_inc(module->refptr->decs);
 
-		trace_module_put(module, _RET_IP_,
-				 __this_cpu_read(module->refptr->decs));
+		trace_module_put(module, _RET_IP_);
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1192,7 +1186,7 @@ struct module_notes_attrs {
 	struct bin_attribute attrs[0];
 };
 
-static ssize_t module_notes_read(struct kobject *kobj,
+static ssize_t module_notes_read(struct file *filp, struct kobject *kobj,
 				 struct bin_attribute *bin_attr,
 				 char *buf, loff_t pos, size_t count)
 {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 2f3fbf84215..a4fa381db3c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -16,6 +16,7 @@
 #include <linux/file.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
+#include <linux/hash.h>
 #include <linux/sysfs.h>
 #include <linux/dcache.h>
 #include <linux/percpu.h>
@@ -82,14 +83,6 @@ extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
 void __weak hw_perf_disable(void)		{ barrier(); }
 void __weak hw_perf_enable(void)		{ barrier(); }
 
-int __weak
-hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx)
-{
-	return 0;
-}
-
 void __weak perf_event_print_debug(void)	{ }
 
 static DEFINE_PER_CPU(int, perf_disable_count);
@@ -262,6 +255,18 @@ static void update_event_times(struct perf_event *event)
 	event->total_time_running = run_end - event->tstamp_running;
 }
 
+/*
+ * Update total_time_enabled and total_time_running for all events in a group.
+ */
+static void update_group_times(struct perf_event *leader)
+{
+	struct perf_event *event;
+
+	update_event_times(leader);
+	list_for_each_entry(event, &leader->sibling_list, group_entry)
+		update_event_times(event);
+}
+
 static struct list_head *
 ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 {
@@ -315,8 +320,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-	struct perf_event *sibling, *tmp;
-
 	if (list_empty(&event->group_entry))
 		return;
 	ctx->nr_events--;
@@ -329,7 +332,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (event->group_leader != event)
 		event->group_leader->nr_siblings--;
 
-	update_event_times(event);
+	update_group_times(event);
 
 	/*
 	 * If event was in error state, then keep it
@@ -340,6 +343,12 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	 */
 	if (event->state > PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_OFF;
+}
+
+static void
+perf_destroy_group(struct perf_event *event, struct perf_event_context *ctx)
+{
+	struct perf_event *sibling, *tmp;
 
 	/*
 	 * If this was a group event with sibling events then
@@ -505,18 +514,6 @@ retry:
 }
 
 /*
- * Update total_time_enabled and total_time_running for all events in a group.
- */
-static void update_group_times(struct perf_event *leader)
-{
-	struct perf_event *event;
-
-	update_event_times(leader);
-	list_for_each_entry(event, &leader->sibling_list, group_entry)
-		update_event_times(event);
-}
-
-/*
  * Cross CPU call to disable a performance event
  */
 static void __perf_event_disable(void *info)
@@ -640,15 +637,20 @@ group_sched_in(struct perf_event *group_event,
 	       struct perf_cpu_context *cpuctx,
 	       struct perf_event_context *ctx)
 {
-	struct perf_event *event, *partial_group;
+	struct perf_event *event, *partial_group = NULL;
+	const struct pmu *pmu = group_event->pmu;
+	bool txn = false;
 	int ret;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	ret = hw_perf_group_sched_in(group_event, cpuctx, ctx);
-	if (ret)
-		return ret < 0 ? ret : 0;
+	/* Check if group transaction availabe */
+	if (pmu->start_txn)
+		txn = true;
+
+	if (txn)
+		pmu->start_txn(pmu);
 
 	if (event_sched_in(group_event, cpuctx, ctx))
 		return -EAGAIN;
@@ -663,9 +665,19 @@ group_sched_in(struct perf_event *group_event,
 		}
 	}
 
-	return 0;
+	if (!txn)
+		return 0;
+
+	ret = pmu->commit_txn(pmu);
+	if (!ret) {
+		pmu->cancel_txn(pmu);
+		return 0;
+	}
 
 group_error:
+	if (txn)
+		pmu->cancel_txn(pmu);
+
 	/*
 	 * Groups can be scheduled in as one unit only, so undo any
 	 * partial group before returning:
@@ -1367,6 +1379,8 @@ void perf_event_task_sched_in(struct task_struct *task)
 	if (cpuctx->task_ctx == ctx)
 		return;
 
+	perf_disable();
+
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -1379,6 +1393,8 @@ void perf_event_task_sched_in(struct task_struct *task)
 	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 
 	cpuctx->task_ctx = ctx;
+
+	perf_enable();
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -1856,9 +1872,30 @@ int perf_event_release_kernel(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 
+	/*
+	 * Remove from the PMU, can't get re-enabled since we got
+	 * here because the last ref went.
+	 */
+	perf_event_disable(event);
+
 	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
-	perf_event_remove_from_context(event);
+	/*
+	 * There are two ways this annotation is useful:
+	 *
+	 *  1) there is a lock recursion from perf_event_exit_task
+	 *     see the comment there.
+	 *
+	 *  2) there is a lock-inversion with mmap_sem through
+	 *     perf_event_read_group(), which takes faults while
+	 *     holding ctx->mutex, however this is called after
+	 *     the last filedesc died, so there is no possibility
+	 *     to trigger the AB-BA case.
+	 */
+	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+	raw_spin_lock_irq(&ctx->lock);
+	list_del_event(event, ctx);
+	perf_destroy_group(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
 	mutex_lock(&event->owner->perf_event_mutex);
@@ -2642,6 +2679,7 @@ static int perf_fasync(int fd, struct file *filp, int on)
 }
 
 static const struct file_operations perf_fops = {
+	.llseek			= no_llseek,
 	.release		= perf_release,
 	.read			= perf_read,
 	.poll			= perf_poll,
@@ -2792,6 +2830,27 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
 
 
 /*
+ * We assume there is only KVM supporting the callbacks.
+ * Later on, we might change it to a list if there is
+ * another virtualization implementation supporting the callbacks.
+ */
+struct perf_guest_info_callbacks *perf_guest_cbs;
+
+int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
+{
+	perf_guest_cbs = cbs;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
+
+int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
+{
+	perf_guest_cbs = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
+
+/*
  * Output
  */
 static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
@@ -3743,7 +3802,7 @@ void __perf_event_mmap(struct vm_area_struct *vma)
 		.event_id  = {
 			.header = {
 				.type = PERF_RECORD_MMAP,
-				.misc = 0,
+				.misc = PERF_RECORD_MISC_USER,
 				/* .size */
 			},
 			/* .pid */
@@ -3961,36 +4020,6 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 	perf_swevent_overflow(event, 0, nmi, data, regs);
 }
 
-static int perf_swevent_is_counting(struct perf_event *event)
-{
-	/*
-	 * The event is active, we're good!
-	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		return 1;
-
-	/*
-	 * The event is off/error, not counting.
-	 */
-	if (event->state != PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	/*
-	 * The event is inactive, if the context is active
-	 * we're part of a group that didn't make it on the 'pmu',
-	 * not counting.
-	 */
-	if (event->ctx->is_active)
-		return 0;
-
-	/*
-	 * We're inactive and the context is too, this means the
-	 * task is scheduled out, we're counting events that happen
-	 * to us, like migration events.
-	 */
-	return 1;
-}
-
 static int perf_tp_event_match(struct perf_event *event,
 				struct perf_sample_data *data);
 
@@ -4014,12 +4043,6 @@ static int perf_swevent_match(struct perf_event *event,
 				struct perf_sample_data *data,
 				struct pt_regs *regs)
 {
-	if (event->cpu != -1 && event->cpu != smp_processor_id())
-		return 0;
-
-	if (!perf_swevent_is_counting(event))
-		return 0;
-
 	if (event->attr.type != type)
 		return 0;
 
@@ -4036,18 +4059,53 @@ static int perf_swevent_match(struct perf_event *event,
 	return 1;
 }
 
-static void perf_swevent_ctx_event(struct perf_event_context *ctx,
-				     enum perf_type_id type,
-				     u32 event_id, u64 nr, int nmi,
-				     struct perf_sample_data *data,
-				     struct pt_regs *regs)
+static inline u64 swevent_hash(u64 type, u32 event_id)
+{
+	u64 val = event_id | (type << 32);
+
+	return hash_64(val, SWEVENT_HLIST_BITS);
+}
+
+static struct hlist_head *
+find_swevent_head(struct perf_cpu_context *ctx, u64 type, u32 event_id)
+{
+	u64 hash;
+	struct swevent_hlist *hlist;
+
+	hash = swevent_hash(type, event_id);
+
+	hlist = rcu_dereference(ctx->swevent_hlist);
+	if (!hlist)
+		return NULL;
+
+	return &hlist->heads[hash];
+}
+
+static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
+				    u64 nr, int nmi,
+				    struct perf_sample_data *data,
+				    struct pt_regs *regs)
 {
+	struct perf_cpu_context *cpuctx;
 	struct perf_event *event;
+	struct hlist_node *node;
+	struct hlist_head *head;
 
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+	cpuctx = &__get_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+
+	head = find_swevent_head(cpuctx, type, event_id);
+
+	if (!head)
+		goto end;
+
+	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_swevent_match(event, type, event_id, data, regs))
 			perf_swevent_add(event, nr, nmi, data, regs);
 	}
+end:
+	rcu_read_unlock();
 }
 
 int perf_swevent_get_recursion_context(void)
@@ -4085,27 +4143,6 @@ void perf_swevent_put_recursion_context(int rctx)
 }
 EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
 
-static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
-				    u64 nr, int nmi,
-				    struct perf_sample_data *data,
-				    struct pt_regs *regs)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-	rcu_read_lock();
-	perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
-				 nr, nmi, data, regs);
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
-	rcu_read_unlock();
-}
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 			    struct pt_regs *regs, u64 addr)
@@ -4131,16 +4168,28 @@ static void perf_swevent_read(struct perf_event *event)
 static int perf_swevent_enable(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct perf_cpu_context *cpuctx;
+	struct hlist_head *head;
+
+	cpuctx = &__get_cpu_var(perf_cpu_context);
 
 	if (hwc->sample_period) {
 		hwc->last_period = hwc->sample_period;
 		perf_swevent_set_period(event);
 	}
+
+	head = find_swevent_head(cpuctx, event->attr.type, event->attr.config);
+	if (WARN_ON_ONCE(!head))
+		return -EINVAL;
+
+	hlist_add_head_rcu(&event->hlist_entry, head);
+
 	return 0;
 }
 
 static void perf_swevent_disable(struct perf_event *event)
 {
+	hlist_del_rcu(&event->hlist_entry);
 }
 
 static const struct pmu perf_ops_generic = {
@@ -4168,15 +4217,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	perf_sample_data_init(&data, 0);
 	data.period = event->hw.last_period;
 	regs = get_irq_regs();
-	/*
-	 * In case we exclude kernel IPs or are somehow not in interrupt
-	 * context, provide the next best thing, the user IP.
-	 */
-	if ((event->attr.exclude_kernel || !regs) &&
-			!event->attr.exclude_user)
-		regs = task_pt_regs(current);
 
-	if (regs) {
+	if (regs && !perf_exclude_event(event, regs)) {
 		if (!(event->attr.exclude_idle && current->pid == 0))
 			if (perf_event_overflow(event, 0, &data, regs))
 				ret = HRTIMER_NORESTART;
@@ -4324,6 +4366,105 @@ static const struct pmu perf_ops_task_clock = {
 	.read		= task_clock_perf_event_read,
 };
 
+static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
+{
+	struct swevent_hlist *hlist;
+
+	hlist = container_of(rcu_head, struct swevent_hlist, rcu_head);
+	kfree(hlist);
+}
+
+static void swevent_hlist_release(struct perf_cpu_context *cpuctx)
+{
+	struct swevent_hlist *hlist;
+
+	if (!cpuctx->swevent_hlist)
+		return;
+
+	hlist = cpuctx->swevent_hlist;
+	rcu_assign_pointer(cpuctx->swevent_hlist, NULL);
+	call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu);
+}
+
+static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+
+	mutex_lock(&cpuctx->hlist_mutex);
+
+	if (!--cpuctx->hlist_refcount)
+		swevent_hlist_release(cpuctx);
+
+	mutex_unlock(&cpuctx->hlist_mutex);
+}
+
+static void swevent_hlist_put(struct perf_event *event)
+{
+	int cpu;
+
+	if (event->cpu != -1) {
+		swevent_hlist_put_cpu(event, event->cpu);
+		return;
+	}
+
+	for_each_possible_cpu(cpu)
+		swevent_hlist_put_cpu(event, cpu);
+}
+
+static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	int err = 0;
+
+	mutex_lock(&cpuctx->hlist_mutex);
+
+	if (!cpuctx->swevent_hlist && cpu_online(cpu)) {
+		struct swevent_hlist *hlist;
+
+		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
+		if (!hlist) {
+			err = -ENOMEM;
+			goto exit;
+		}
+		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+	}
+	cpuctx->hlist_refcount++;
+ exit:
+	mutex_unlock(&cpuctx->hlist_mutex);
+
+	return err;
+}
+
+static int swevent_hlist_get(struct perf_event *event)
+{
+	int err;
+	int cpu, failed_cpu;
+
+	if (event->cpu != -1)
+		return swevent_hlist_get_cpu(event, event->cpu);
+
+	get_online_cpus();
+	for_each_possible_cpu(cpu) {
+		err = swevent_hlist_get_cpu(event, cpu);
+		if (err) {
+			failed_cpu = cpu;
+			goto fail;
+		}
+	}
+	put_online_cpus();
+
+	return 0;
+ fail:
+	for_each_possible_cpu(cpu) {
+		if (cpu == failed_cpu)
+			break;
+		swevent_hlist_put_cpu(event, cpu);
+	}
+
+	put_online_cpus();
+	return err;
+}
+
 #ifdef CONFIG_EVENT_TRACING
 
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
@@ -4357,10 +4498,13 @@ static int perf_tp_event_match(struct perf_event *event,
 static void tp_perf_event_destroy(struct perf_event *event)
 {
 	perf_trace_disable(event->attr.config);
+	swevent_hlist_put(event);
 }
 
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
 {
+	int err;
+
 	/*
 	 * Raw tracepoint data is a severe data leak, only allow root to
 	 * have these.
@@ -4374,6 +4518,11 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
 		return NULL;
 
 	event->destroy = tp_perf_event_destroy;
+	err = swevent_hlist_get(event);
+	if (err) {
+		perf_trace_disable(event->attr.config);
+		return ERR_PTR(err);
+	}
 
 	return &perf_ops_generic;
 }
@@ -4474,6 +4623,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 	WARN_ON(event->parent);
 
 	atomic_dec(&perf_swevent_enabled[event_id]);
+	swevent_hlist_put(event);
 }
 
 static const struct pmu *sw_perf_event_init(struct perf_event *event)
@@ -4512,6 +4662,12 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event)
 	case PERF_COUNT_SW_ALIGNMENT_FAULTS:
 	case PERF_COUNT_SW_EMULATION_FAULTS:
 		if (!event->parent) {
+			int err;
+
+			err = swevent_hlist_get(event);
+			if (err)
+				return ERR_PTR(err);
+
 			atomic_inc(&perf_swevent_enabled[event_id]);
 			event->destroy = sw_perf_event_destroy;
 		}
@@ -4897,7 +5053,7 @@ err_fput_free_put_context:
 
 err_free_put_context:
 	if (err < 0)
-		kfree(event);
+		free_event(event);
 
 err_put_context:
 	if (err < 0)
@@ -5176,7 +5332,7 @@ void perf_event_exit_task(struct task_struct *child)
 	 *
 	 * But since its the parent context it won't be the same instance.
 	 */
-	mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);
+	mutex_lock(&child_ctx->mutex);
 
 again:
 	list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
@@ -5384,6 +5540,7 @@ static void __init perf_event_init_all_cpus(void)
 
 	for_each_possible_cpu(cpu) {
 		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		mutex_init(&cpuctx->hlist_mutex);
 		__perf_event_init_context(&cpuctx->ctx, NULL);
 	}
 }
@@ -5397,6 +5554,16 @@ static void __cpuinit perf_event_init_cpu(int cpu)
 	spin_lock(&perf_resource_lock);
 	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
 	spin_unlock(&perf_resource_lock);
+
+	mutex_lock(&cpuctx->hlist_mutex);
+	if (cpuctx->hlist_refcount > 0) {
+		struct swevent_hlist *hlist;
+
+		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
+		WARN_ON_ONCE(!hlist);
+		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+	}
+	mutex_unlock(&cpuctx->hlist_mutex);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -5416,6 +5583,10 @@ static void perf_event_exit_cpu(int cpu)
 	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
+	mutex_lock(&cpuctx->hlist_mutex);
+	swevent_hlist_release(cpuctx);
+	mutex_unlock(&cpuctx->hlist_mutex);
+
 	mutex_lock(&ctx->mutex);
 	smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1);
 	mutex_unlock(&ctx->mutex);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 3db49b9ca37..f42d3f737a3 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -2,7 +2,7 @@
  * This module exposes the interface to kernel space for specifying
  * QoS dependencies.  It provides infrastructure for registration of:
  *
- * Dependents on a QoS value : register requirements
+ * Dependents on a QoS value : register requests
  * Watchers of QoS value : get notified when target QoS value changes
  *
  * This QoS design is best effort based.  Dependents register their QoS needs.
@@ -14,19 +14,21 @@
  * timeout: usec <-- currently not used.
  * throughput: kbs (kilo byte / sec)
  *
- * There are lists of pm_qos_objects each one wrapping requirements, notifiers
+ * There are lists of pm_qos_objects each one wrapping requests, notifiers
  *
- * User mode requirements on a QOS parameter register themselves to the
+ * User mode requests on a QOS parameter register themselves to the
  * subsystem by opening the device node /dev/... and writing there request to
  * the node.  As long as the process holds a file handle open to the node the
  * client continues to be accounted for.  Upon file release the usermode
- * requirement is removed and a new qos target is computed.  This way when the
- * requirement that the application has is cleaned up when closes the file
+ * request is removed and a new qos target is computed.  This way when the
+ * request that the application has is cleaned up when closes the file
  * pointer or exits the pm_qos_object will get an opportunity to clean up.
  *
  * Mark Gross <mgross@linux.intel.com>
  */
 
+/*#define DEBUG*/
+
 #include <linux/pm_qos_params.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
@@ -42,25 +44,25 @@
 #include <linux/uaccess.h>
 
 /*
- * locking rule: all changes to requirements or notifiers lists
+ * locking rule: all changes to requests or notifiers lists
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
-struct requirement_list {
+struct pm_qos_request_list {
 	struct list_head list;
 	union {
 		s32 value;
 		s32 usec;
 		s32 kbps;
 	};
-	char *name;
+	int pm_qos_class;
 };
 
 static s32 max_compare(s32 v1, s32 v2);
 static s32 min_compare(s32 v1, s32 v2);
 
 struct pm_qos_object {
-	struct requirement_list requirements;
+	struct pm_qos_request_list requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
@@ -72,7 +74,7 @@ struct pm_qos_object {
 static struct pm_qos_object null_pm_qos;
 static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
 static struct pm_qos_object cpu_dma_pm_qos = {
-	.requirements = {LIST_HEAD_INIT(cpu_dma_pm_qos.requirements.list)},
+	.requests = {LIST_HEAD_INIT(cpu_dma_pm_qos.requests.list)},
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
 	.default_value = 2000 * USEC_PER_SEC,
@@ -82,7 +84,7 @@ static struct pm_qos_object cpu_dma_pm_qos = {
 
 static BLOCKING_NOTIFIER_HEAD(network_lat_notifier);
 static struct pm_qos_object network_lat_pm_qos = {
-	.requirements = {LIST_HEAD_INIT(network_lat_pm_qos.requirements.list)},
+	.requests = {LIST_HEAD_INIT(network_lat_pm_qos.requests.list)},
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
 	.default_value = 2000 * USEC_PER_SEC,
@@ -93,8 +95,7 @@ static struct pm_qos_object network_lat_pm_qos = {
 
 static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier);
 static struct pm_qos_object network_throughput_pm_qos = {
-	.requirements =
-		{LIST_HEAD_INIT(network_throughput_pm_qos.requirements.list)},
+	.requests = {LIST_HEAD_INIT(network_throughput_pm_qos.requests.list)},
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
 	.default_value = 0,
@@ -135,31 +136,34 @@ static s32 min_compare(s32 v1, s32 v2)
 }
 
 
-static void update_target(int target)
+static void update_target(int pm_qos_class)
 {
 	s32 extreme_value;
-	struct requirement_list *node;
+	struct pm_qos_request_list *node;
 	unsigned long flags;
 	int call_notifier = 0;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	extreme_value = pm_qos_array[target]->default_value;
+	extreme_value = pm_qos_array[pm_qos_class]->default_value;
 	list_for_each_entry(node,
-			&pm_qos_array[target]->requirements.list, list) {
-		extreme_value = pm_qos_array[target]->comparitor(
+			&pm_qos_array[pm_qos_class]->requests.list, list) {
+		extreme_value = pm_qos_array[pm_qos_class]->comparitor(
 				extreme_value, node->value);
 	}
-	if (atomic_read(&pm_qos_array[target]->target_value) != extreme_value) {
+	if (atomic_read(&pm_qos_array[pm_qos_class]->target_value) !=
+			extreme_value) {
 		call_notifier = 1;
-		atomic_set(&pm_qos_array[target]->target_value, extreme_value);
-		pr_debug(KERN_ERR "new target for qos %d is %d\n", target,
-			atomic_read(&pm_qos_array[target]->target_value));
+		atomic_set(&pm_qos_array[pm_qos_class]->target_value,
+				extreme_value);
+		pr_debug(KERN_ERR "new target for qos %d is %d\n", pm_qos_class,
+			atomic_read(&pm_qos_array[pm_qos_class]->target_value));
 	}
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	if (call_notifier)
-		blocking_notifier_call_chain(pm_qos_array[target]->notifiers,
-			(unsigned long) extreme_value, NULL);
+		blocking_notifier_call_chain(
+				pm_qos_array[pm_qos_class]->notifiers,
+					(unsigned long) extreme_value, NULL);
 }
 
 static int register_pm_qos_misc(struct pm_qos_object *qos)
@@ -185,125 +189,112 @@ static int find_pm_qos_object_by_minor(int minor)
 }
 
 /**
- * pm_qos_requirement - returns current system wide qos expectation
+ * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
  * This function returns the current target value in an atomic manner.
  */
-int pm_qos_requirement(int pm_qos_class)
+int pm_qos_request(int pm_qos_class)
 {
 	return atomic_read(&pm_qos_array[pm_qos_class]->target_value);
 }
-EXPORT_SYMBOL_GPL(pm_qos_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_request);
 
 /**
- * pm_qos_add_requirement - inserts new qos request into the list
+ * pm_qos_add_request - inserts new qos request into the list
  * @pm_qos_class: identifies which list of qos request to us
- * @name: identifies the request
  * @value: defines the qos request
  *
  * This function inserts a new entry in the pm_qos_class list of requested qos
  * performance characteristics.  It recomputes the aggregate QoS expectations
- * for the pm_qos_class of parameters.
+ * for the pm_qos_class of parameters, and returns the pm_qos_request list
+ * element as a handle for use in updating and removal.  Call needs to save
+ * this handle for later use.
  */
-int pm_qos_add_requirement(int pm_qos_class, char *name, s32 value)
+struct pm_qos_request_list *pm_qos_add_request(int pm_qos_class, s32 value)
 {
-	struct requirement_list *dep;
+	struct pm_qos_request_list *dep;
 	unsigned long flags;
 
-	dep = kzalloc(sizeof(struct requirement_list), GFP_KERNEL);
+	dep = kzalloc(sizeof(struct pm_qos_request_list), GFP_KERNEL);
 	if (dep) {
 		if (value == PM_QOS_DEFAULT_VALUE)
 			dep->value = pm_qos_array[pm_qos_class]->default_value;
 		else
 			dep->value = value;
-		dep->name = kstrdup(name, GFP_KERNEL);
-		if (!dep->name)
-			goto cleanup;
+		dep->pm_qos_class = pm_qos_class;
 
 		spin_lock_irqsave(&pm_qos_lock, flags);
 		list_add(&dep->list,
-			&pm_qos_array[pm_qos_class]->requirements.list);
+			&pm_qos_array[pm_qos_class]->requests.list);
 		spin_unlock_irqrestore(&pm_qos_lock, flags);
 		update_target(pm_qos_class);
-
-		return 0;
 	}
 
-cleanup:
-	kfree(dep);
-	return -ENOMEM;
+	return dep;
 }
-EXPORT_SYMBOL_GPL(pm_qos_add_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_add_request);
 
 /**
- * pm_qos_update_requirement - modifies an existing qos request
- * @pm_qos_class: identifies which list of qos request to us
- * @name: identifies the request
+ * pm_qos_update_request - modifies an existing qos request
+ * @pm_qos_req : handle to list element holding a pm_qos request to use
  * @value: defines the qos request
  *
- * Updates an existing qos requirement for the pm_qos_class of parameters along
+ * Updates an existing qos request for the pm_qos_class of parameters along
  * with updating the target pm_qos_class value.
  *
- * If the named request isn't in the list then no change is made.
+ * Attempts are made to make this code callable on hot code paths.
  */
-int pm_qos_update_requirement(int pm_qos_class, char *name, s32 new_value)
+void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req,
+		s32 new_value)
 {
 	unsigned long flags;
-	struct requirement_list *node;
 	int pending_update = 0;
+	s32 temp;
 
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	list_for_each_entry(node,
-		&pm_qos_array[pm_qos_class]->requirements.list, list) {
-		if (strcmp(node->name, name) == 0) {
-			if (new_value == PM_QOS_DEFAULT_VALUE)
-				node->value =
-				pm_qos_array[pm_qos_class]->default_value;
-			else
-				node->value = new_value;
+	if (pm_qos_req) { /*guard against callers passing in null */
+		spin_lock_irqsave(&pm_qos_lock, flags);
+		if (new_value == PM_QOS_DEFAULT_VALUE)
+			temp = pm_qos_array[pm_qos_req->pm_qos_class]->default_value;
+		else
+			temp = new_value;
+
+		if (temp != pm_qos_req->value) {
 			pending_update = 1;
-			break;
+			pm_qos_req->value = temp;
 		}
+		spin_unlock_irqrestore(&pm_qos_lock, flags);
+		if (pending_update)
+			update_target(pm_qos_req->pm_qos_class);
 	}
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	if (pending_update)
-		update_target(pm_qos_class);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(pm_qos_update_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
 /**
- * pm_qos_remove_requirement - modifies an existing qos request
- * @pm_qos_class: identifies which list of qos request to us
- * @name: identifies the request
+ * pm_qos_remove_request - modifies an existing qos request
+ * @pm_qos_req: handle to request list element
  *
- * Will remove named qos request from pm_qos_class list of parameters and
- * recompute the current target value for the pm_qos_class.
+ * Will remove pm qos request from the list of requests and
+ * recompute the current target value for the pm_qos_class.  Call this
+ * on slow code paths.
  */
-void pm_qos_remove_requirement(int pm_qos_class, char *name)
+void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req)
 {
 	unsigned long flags;
-	struct requirement_list *node;
-	int pending_update = 0;
+	int qos_class;
 
+	if (pm_qos_req == NULL)
+		return;
+		/* silent return to keep pcm code cleaner */
+
+	qos_class = pm_qos_req->pm_qos_class;
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	list_for_each_entry(node,
-		&pm_qos_array[pm_qos_class]->requirements.list, list) {
-		if (strcmp(node->name, name) == 0) {
-			kfree(node->name);
-			list_del(&node->list);
-			kfree(node);
-			pending_update = 1;
-			break;
-		}
-	}
+	list_del(&pm_qos_req->list);
+	kfree(pm_qos_req);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	if (pending_update)
-		update_target(pm_qos_class);
+	update_target(qos_class);
 }
-EXPORT_SYMBOL_GPL(pm_qos_remove_requirement);
+EXPORT_SYMBOL_GPL(pm_qos_remove_request);
 
 /**
  * pm_qos_add_notifier - sets notification entry for changes to target value
@@ -313,7 +304,7 @@ EXPORT_SYMBOL_GPL(pm_qos_remove_requirement);
  * will register the notifier into a notification chain that gets called
  * upon changes to the pm_qos_class target value.
  */
- int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
+int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
 {
 	int retval;
 
@@ -343,21 +334,16 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
 }
 EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
 
-#define PID_NAME_LEN 32
-
 static int pm_qos_power_open(struct inode *inode, struct file *filp)
 {
-	int ret;
 	long pm_qos_class;
-	char name[PID_NAME_LEN];
 
 	pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
 	if (pm_qos_class >= 0) {
-		filp->private_data = (void *)pm_qos_class;
-		snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
-		ret = pm_qos_add_requirement(pm_qos_class, name,
-					PM_QOS_DEFAULT_VALUE);
-		if (ret >= 0)
+		filp->private_data = (void *) pm_qos_add_request(pm_qos_class,
+				PM_QOS_DEFAULT_VALUE);
+
+		if (filp->private_data)
 			return 0;
 	}
 	return -EPERM;
@@ -365,32 +351,40 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp)
 
 static int pm_qos_power_release(struct inode *inode, struct file *filp)
 {
-	int pm_qos_class;
-	char name[PID_NAME_LEN];
+	struct pm_qos_request_list *req;
 
-	pm_qos_class = (long)filp->private_data;
-	snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
-	pm_qos_remove_requirement(pm_qos_class, name);
+	req = (struct pm_qos_request_list *)filp->private_data;
+	pm_qos_remove_request(req);
 
 	return 0;
 }
 
+
 static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos)
 {
 	s32 value;
-	int pm_qos_class;
-	char name[PID_NAME_LEN];
-
-	pm_qos_class = (long)filp->private_data;
-	if (count != sizeof(s32))
+	int x;
+	char ascii_value[11];
+	struct pm_qos_request_list *pm_qos_req;
+
+	if (count == sizeof(s32)) {
+		if (copy_from_user(&value, buf, sizeof(s32)))
+			return -EFAULT;
+	} else if (count == 11) { /* len('0x12345678/0') */
+		if (copy_from_user(ascii_value, buf, 11))
+			return -EFAULT;
+		x = sscanf(ascii_value, "%x", &value);
+		if (x != 1)
+			return -EINVAL;
+		pr_debug(KERN_ERR "%s, %d, 0x%x\n", ascii_value, x, value);
+	} else
 		return -EINVAL;
-	if (copy_from_user(&value, buf, sizeof(s32)))
-		return -EFAULT;
-	snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
-	pm_qos_update_requirement(pm_qos_class, name, value);
 
-	return  sizeof(s32);
+	pm_qos_req = (struct pm_qos_request_list *)filp->private_data;
+	pm_qos_update_request(pm_qos_req, value);
+
+	return count;
 }
 
 
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index bc7704b3a44..00bb252f29a 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -11,19 +11,18 @@
 #include <trace/events/timer.h>
 
 /*
- * Called after updating RLIMIT_CPU to set timer expiration if necessary.
+ * Called after updating RLIMIT_CPU to run cpu timer and update
+ * tsk->signal->cputime_expires expiration cache if necessary. Needs
+ * siglock protection since other code may update expiration cache as
+ * well.
  */
 void update_rlimit_cpu(unsigned long rlim_new)
 {
 	cputime_t cputime = secs_to_cputime(rlim_new);
-	struct signal_struct *const sig = current->signal;
 
-	if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
-	    cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
-		spin_lock_irq(&current->sighand->siglock);
-		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
-		spin_unlock_irq(&current->sighand->siglock);
-	}
+	spin_lock_irq(&current->sighand->siglock);
+	set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
+	spin_unlock_irq(&current->sighand->siglock);
 }
 
 static int check_clock(const clockid_t which_clock)
@@ -548,111 +547,62 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 	       cputime_gt(expires, new_exp);
 }
 
-static inline int expires_le(cputime_t expires, cputime_t new_exp)
-{
-	return !cputime_eq(expires, cputime_zero) &&
-	       cputime_le(expires, new_exp);
-}
 /*
  * Insert the timer on the appropriate list before any timers that
  * expire later.  This must be called with the tasklist_lock held
- * for reading, and interrupts disabled.
+ * for reading, interrupts disabled and p->sighand->siglock taken.
  */
-static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
+static void arm_timer(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	struct list_head *head, *listpos;
+	struct task_cputime *cputime_expires;
 	struct cpu_timer_list *const nt = &timer->it.cpu;
 	struct cpu_timer_list *next;
-	unsigned long i;
 
-	head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
-		p->cpu_timers : p->signal->cpu_timers);
+	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+		head = p->cpu_timers;
+		cputime_expires = &p->cputime_expires;
+	} else {
+		head = p->signal->cpu_timers;
+		cputime_expires = &p->signal->cputime_expires;
+	}
 	head += CPUCLOCK_WHICH(timer->it_clock);
 
-	BUG_ON(!irqs_disabled());
-	spin_lock(&p->sighand->siglock);
-
 	listpos = head;
-	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
-		list_for_each_entry(next, head, entry) {
-			if (next->expires.sched > nt->expires.sched)
-				break;
-			listpos = &next->entry;
-		}
-	} else {
-		list_for_each_entry(next, head, entry) {
-			if (cputime_gt(next->expires.cpu, nt->expires.cpu))
-				break;
-			listpos = &next->entry;
-		}
+	list_for_each_entry(next, head, entry) {
+		if (cpu_time_before(timer->it_clock, nt->expires, next->expires))
+			break;
+		listpos = &next->entry;
 	}
 	list_add(&nt->entry, listpos);
 
 	if (listpos == head) {
+		union cpu_time_count *exp = &nt->expires;
+
 		/*
-		 * We are the new earliest-expiring timer.
-		 * If we are a thread timer, there can always
-		 * be a process timer telling us to stop earlier.
+		 * We are the new earliest-expiring POSIX 1.b timer, hence
+		 * need to update expiration cache. Take into account that
+		 * for process timers we share expiration cache with itimers
+		 * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME.
 		 */
 
-		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
-			union cpu_time_count *exp = &nt->expires;
-
-			switch (CPUCLOCK_WHICH(timer->it_clock)) {
-			default:
-				BUG();
-			case CPUCLOCK_PROF:
-				if (expires_gt(p->cputime_expires.prof_exp,
-					       exp->cpu))
-					p->cputime_expires.prof_exp = exp->cpu;
-				break;
-			case CPUCLOCK_VIRT:
-				if (expires_gt(p->cputime_expires.virt_exp,
-					       exp->cpu))
-					p->cputime_expires.virt_exp = exp->cpu;
-				break;
-			case CPUCLOCK_SCHED:
-				if (p->cputime_expires.sched_exp == 0 ||
-				    p->cputime_expires.sched_exp > exp->sched)
-					p->cputime_expires.sched_exp =
-								exp->sched;
-				break;
-			}
-		} else {
-			struct signal_struct *const sig = p->signal;
-			union cpu_time_count *exp = &timer->it.cpu.expires;
-
-			/*
-			 * For a process timer, set the cached expiration time.
-			 */
-			switch (CPUCLOCK_WHICH(timer->it_clock)) {
-			default:
-				BUG();
-			case CPUCLOCK_VIRT:
-				if (expires_le(sig->it[CPUCLOCK_VIRT].expires,
-					       exp->cpu))
-					break;
-				sig->cputime_expires.virt_exp = exp->cpu;
-				break;
-			case CPUCLOCK_PROF:
-				if (expires_le(sig->it[CPUCLOCK_PROF].expires,
-					       exp->cpu))
-					break;
-				i = sig->rlim[RLIMIT_CPU].rlim_cur;
-				if (i != RLIM_INFINITY &&
-				    i <= cputime_to_secs(exp->cpu))
-					break;
-				sig->cputime_expires.prof_exp = exp->cpu;
-				break;
-			case CPUCLOCK_SCHED:
-				sig->cputime_expires.sched_exp = exp->sched;
-				break;
-			}
+		switch (CPUCLOCK_WHICH(timer->it_clock)) {
+		case CPUCLOCK_PROF:
+			if (expires_gt(cputime_expires->prof_exp, exp->cpu))
+				cputime_expires->prof_exp = exp->cpu;
+			break;
+		case CPUCLOCK_VIRT:
+			if (expires_gt(cputime_expires->virt_exp, exp->cpu))
+				cputime_expires->virt_exp = exp->cpu;
+			break;
+		case CPUCLOCK_SCHED:
+			if (cputime_expires->sched_exp == 0 ||
+			    cputime_expires->sched_exp > exp->sched)
+				cputime_expires->sched_exp = exp->sched;
+			break;
 		}
 	}
-
-	spin_unlock(&p->sighand->siglock);
 }
 
 /*
@@ -660,7 +610,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
  */
 static void cpu_timer_fire(struct k_itimer *timer)
 {
-	if (unlikely(timer->sigq == NULL)) {
+	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
+		/*
+		 * User don't want any signal.
+		 */
+		timer->it.cpu.expires.sched = 0;
+	} else if (unlikely(timer->sigq == NULL)) {
 		/*
 		 * This a special case for clock_nanosleep,
 		 * not a normal timer from sys_timer_create.
@@ -721,7 +676,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 			struct itimerspec *new, struct itimerspec *old)
 {
 	struct task_struct *p = timer->it.cpu.task;
-	union cpu_time_count old_expires, new_expires, val;
+	union cpu_time_count old_expires, new_expires, old_incr, val;
 	int ret;
 
 	if (unlikely(p == NULL)) {
@@ -752,6 +707,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	BUG_ON(!irqs_disabled());
 
 	ret = 0;
+	old_incr = timer->it.cpu.incr;
 	spin_lock(&p->sighand->siglock);
 	old_expires = timer->it.cpu.expires;
 	if (unlikely(timer->it.cpu.firing)) {
@@ -759,7 +715,6 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		ret = TIMER_RETRY;
 	} else
 		list_del_init(&timer->it.cpu.entry);
-	spin_unlock(&p->sighand->siglock);
 
 	/*
 	 * We need to sample the current value to convert the new
@@ -813,6 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		 * disable this firing since we are already reporting
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
+		spin_unlock(&p->sighand->siglock);
 		read_unlock(&tasklist_lock);
 		goto out;
 	}
@@ -828,11 +784,11 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	 */
 	timer->it.cpu.expires = new_expires;
 	if (new_expires.sched != 0 &&
-	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
 	    cpu_time_before(timer->it_clock, val, new_expires)) {
-		arm_timer(timer, val);
+		arm_timer(timer);
 	}
 
+	spin_unlock(&p->sighand->siglock);
 	read_unlock(&tasklist_lock);
 
 	/*
@@ -853,7 +809,6 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	timer->it_overrun = -1;
 
 	if (new_expires.sched != 0 &&
-	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
 	    !cpu_time_before(timer->it_clock, val, new_expires)) {
 		/*
 		 * The designated time already passed, so we notify
@@ -867,7 +822,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
  out:
 	if (old) {
 		sample_to_timespec(timer->it_clock,
-				   timer->it.cpu.incr, &old->it_interval);
+				   old_incr, &old->it_interval);
 	}
 	return ret;
 }
@@ -927,25 +882,6 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 		read_unlock(&tasklist_lock);
 	}
 
-	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
-		if (timer->it.cpu.incr.sched == 0 &&
-		    cpu_time_before(timer->it_clock,
-				    timer->it.cpu.expires, now)) {
-			/*
-			 * Do-nothing timer expired and has no reload,
-			 * so it's as if it was never set.
-			 */
-			timer->it.cpu.expires.sched = 0;
-			itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
-			return;
-		}
-		/*
-		 * Account for any expirations and reloads that should
-		 * have happened.
-		 */
-		bump_cpu_timer(timer, now);
-	}
-
 	if (unlikely(clear_dead)) {
 		/*
 		 * We've noticed that the thread is dead, but
@@ -1066,16 +1002,9 @@ static void stop_process_timers(struct signal_struct *sig)
 	struct thread_group_cputimer *cputimer = &sig->cputimer;
 	unsigned long flags;
 
-	if (!cputimer->running)
-		return;
-
 	spin_lock_irqsave(&cputimer->lock, flags);
 	cputimer->running = 0;
 	spin_unlock_irqrestore(&cputimer->lock, flags);
-
-	sig->cputime_expires.prof_exp = cputime_zero;
-	sig->cputime_expires.virt_exp = cputime_zero;
-	sig->cputime_expires.sched_exp = 0;
 }
 
 static u32 onecputick;
@@ -1112,6 +1041,23 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 	}
 }
 
+/**
+ * task_cputime_zero - Check a task_cputime struct for all zero fields.
+ *
+ * @cputime:	The struct to compare.
+ *
+ * Checks @cputime to see if all fields are zero.  Returns true if all fields
+ * are zero, false if any field is nonzero.
+ */
+static inline int task_cputime_zero(const struct task_cputime *cputime)
+{
+	if (cputime_eq(cputime->utime, cputime_zero) &&
+	    cputime_eq(cputime->stime, cputime_zero) &&
+	    cputime->sum_exec_runtime == 0)
+		return 1;
+	return 0;
+}
+
 /*
  * 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
@@ -1129,19 +1075,6 @@ static void check_process_timers(struct task_struct *tsk,
 	unsigned long soft;
 
 	/*
-	 * Don't sample the current process CPU clocks if there are no timers.
-	 */
-	if (list_empty(&timers[CPUCLOCK_PROF]) &&
-	    cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
-	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
-	    list_empty(&timers[CPUCLOCK_VIRT]) &&
-	    cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
-	    list_empty(&timers[CPUCLOCK_SCHED])) {
-		stop_process_timers(sig);
-		return;
-	}
-
-	/*
 	 * Collect the current process totals.
 	 */
 	thread_group_cputimer(tsk, &cputime);
@@ -1230,18 +1163,11 @@ static void check_process_timers(struct task_struct *tsk,
 		}
 	}
 
-	if (!cputime_eq(prof_expires, cputime_zero) &&
-	    (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) ||
-	     cputime_gt(sig->cputime_expires.prof_exp, prof_expires)))
-		sig->cputime_expires.prof_exp = prof_expires;
-	if (!cputime_eq(virt_expires, cputime_zero) &&
-	    (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) ||
-	     cputime_gt(sig->cputime_expires.virt_exp, virt_expires)))
-		sig->cputime_expires.virt_exp = virt_expires;
-	if (sched_expires != 0 &&
-	    (sig->cputime_expires.sched_exp == 0 ||
-	     sig->cputime_expires.sched_exp > sched_expires))
-		sig->cputime_expires.sched_exp = sched_expires;
+	sig->cputime_expires.prof_exp = prof_expires;
+	sig->cputime_expires.virt_exp = virt_expires;
+	sig->cputime_expires.sched_exp = sched_expires;
+	if (task_cputime_zero(&sig->cputime_expires))
+		stop_process_timers(sig);
 }
 
 /*
@@ -1270,6 +1196,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			goto out;
 		}
 		read_lock(&tasklist_lock); /* arm_timer needs it.  */
+		spin_lock(&p->sighand->siglock);
 	} else {
 		read_lock(&tasklist_lock);
 		if (unlikely(p->signal == NULL)) {
@@ -1290,6 +1217,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			clear_dead_task(timer, now);
 			goto out_unlock;
 		}
+		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
 		/* Leave the tasklist_lock locked for the call below.  */
@@ -1298,7 +1226,9 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	arm_timer(timer, now);
+	BUG_ON(!irqs_disabled());
+	arm_timer(timer);
+	spin_unlock(&p->sighand->siglock);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
@@ -1310,23 +1240,6 @@ out:
 }
 
 /**
- * task_cputime_zero - Check a task_cputime struct for all zero fields.
- *
- * @cputime:	The struct to compare.
- *
- * Checks @cputime to see if all fields are zero.  Returns true if all fields
- * are zero, false if any field is nonzero.
- */
-static inline int task_cputime_zero(const struct task_cputime *cputime)
-{
-	if (cputime_eq(cputime->utime, cputime_zero) &&
-	    cputime_eq(cputime->stime, cputime_zero) &&
-	    cputime->sum_exec_runtime == 0)
-		return 1;
-	return 0;
-}
-
-/**
  * task_cputime_expired - Compare two task_cputime entities.
  *
  * @sample:	The task_cputime structure to be checked for expiration.
@@ -1382,7 +1295,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	}
 
 	sig = tsk->signal;
-	if (!task_cputime_zero(&sig->cputime_expires)) {
+	if (sig->cputimer.running) {
 		struct task_cputime group_sample;
 
 		thread_group_cputimer(tsk, &group_sample);
@@ -1390,7 +1303,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 			return 1;
 	}
 
-	return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
+	return 0;
 }
 
 /*
@@ -1419,7 +1332,12 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * put them on the firing list.
 	 */
 	check_thread_timers(tsk, &firing);
-	check_process_timers(tsk, &firing);
+	/*
+	 * If there are any active process wide timers (POSIX 1.b, itimers,
+	 * RLIMIT_CPU) cputimer must be running.
+	 */
+	if (tsk->signal->cputimer.running)
+		check_process_timers(tsk, &firing);
 
 	/*
 	 * We must release these locks before taking any timer's lock.
@@ -1456,21 +1374,23 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 }
 
 /*
- * Set one of the process-wide special case CPU timers.
+ * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.
- * The *newval argument is relative and we update it to be absolute, *oldval
- * is absolute and we update it to be relative.
  */
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval)
 {
 	union cpu_time_count now;
-	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
+		/*
+		 * We are setting itimer. The *oldval is absolute and we update
+		 * it to be relative, *newval argument is relative and we update
+		 * it to be absolute.
+		 */
 		if (!cputime_eq(*oldval, cputime_zero)) {
 			if (cputime_le(*oldval, now.cpu)) {
 				/* Just about to fire. */
@@ -1483,33 +1403,21 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		if (cputime_eq(*newval, cputime_zero))
 			return;
 		*newval = cputime_add(*newval, now.cpu);
-
-		/*
-		 * If the RLIMIT_CPU timer will expire before the
-		 * ITIMER_PROF timer, we have nothing else to do.
-		 */
-		if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur
-		    < cputime_to_secs(*newval))
-			return;
 	}
 
 	/*
-	 * Check whether there are any process timers already set to fire
-	 * before this one.  If so, we don't have anything more to do.
+	 * Update expiration cache if we are the earliest timer, or eventually
+	 * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
 	 */
-	head = &tsk->signal->cpu_timers[clock_idx];
-	if (list_empty(head) ||
-	    cputime_ge(list_first_entry(head,
-				  struct cpu_timer_list, entry)->expires.cpu,
-		       *newval)) {
-		switch (clock_idx) {
-		case CPUCLOCK_PROF:
+	switch (clock_idx) {
+	case CPUCLOCK_PROF:
+		if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
 			tsk->signal->cputime_expires.prof_exp = *newval;
-			break;
-		case CPUCLOCK_VIRT:
+		break;
+	case CPUCLOCK_VIRT:
+		if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
 			tsk->signal->cputime_expires.virt_exp = *newval;
-			break;
-		}
+		break;
 	}
 }
 
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 43191815f87..524e058dcf0 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -8,7 +8,8 @@ obj-$(CONFIG_PM_SLEEP)		+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
+				   block_io.o
 obj-$(CONFIG_HIBERNATION_NVS)	+= hibernate_nvs.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/block_io.c b/kernel/power/block_io.c
new file mode 100644
index 00000000000..97024fd40cd
--- /dev/null
+++ b/kernel/power/block_io.c
@@ -0,0 +1,103 @@
+/*
+ * This file provides functions for block I/O operations on swap/file.
+ *
+ * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/bio.h>
+#include <linux/kernel.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+#include "power.h"
+
+/**
+ *	submit - submit BIO request.
+ *	@rw:	READ or WRITE.
+ *	@off	physical offset of page.
+ *	@page:	page we're reading or writing.
+ *	@bio_chain: list of pending biod (for async reading)
+ *
+ *	Straight from the textbook - allocate and initialize the bio.
+ *	If we're reading, make sure the page is marked as dirty.
+ *	Then submit it and, if @bio_chain == NULL, wait.
+ */
+static int submit(int rw, struct block_device *bdev, sector_t sector,
+		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);
+	bio->bi_sector = sector;
+	bio->bi_bdev = bdev;
+	bio->bi_end_io = end_swap_bio_read;
+
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
+			(unsigned long long)sector);
+		bio_put(bio);
+		return -EFAULT;
+	}
+
+	lock_page(page);
+	bio_get(bio);
+
+	if (bio_chain == NULL) {
+		submit_bio(bio_rw, bio);
+		wait_on_page_locked(page);
+		if (rw == READ)
+			bio_set_pages_dirty(bio);
+		bio_put(bio);
+	} else {
+		if (rw == READ)
+			get_page(page);	/* These pages are freed later */
+		bio->bi_private = *bio_chain;
+		*bio_chain = bio;
+		submit_bio(bio_rw, bio);
+	}
+	return 0;
+}
+
+int hib_bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
+{
+	return submit(READ, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
+			virt_to_page(addr), bio_chain);
+}
+
+int hib_bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
+{
+	return submit(WRITE, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
+			virt_to_page(addr), bio_chain);
+}
+
+int hib_wait_on_bio_chain(struct bio **bio_chain)
+{
+	struct bio *bio;
+	struct bio *next_bio;
+	int ret = 0;
+
+	if (bio_chain == NULL)
+		return 0;
+
+	bio = *bio_chain;
+	if (bio == NULL)
+		return 0;
+	while (bio) {
+		struct page *page;
+
+		next_bio = bio->bi_private;
+		page = bio->bi_io_vec[0].bv_page;
+		wait_on_page_locked(page);
+		if (!PageUptodate(page) || PageError(page))
+			ret = -EIO;
+		put_page(page);
+		bio_put(bio);
+		bio = next_bio;
+	}
+	*bio_chain = NULL;
+	return ret;
+}
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 46c5a26630a..006270fe382 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -97,24 +97,12 @@ extern int hibernate_preallocate_memory(void);
  */
 
 struct snapshot_handle {
-	loff_t		offset;	/* number of the last byte ready for reading
-				 * or writing in the sequence
-				 */
 	unsigned int	cur;	/* number of the block of PAGE_SIZE bytes the
 				 * next operation will refer to (ie. current)
 				 */
-	unsigned int	cur_offset;	/* offset with respect to the current
-					 * block (for the next operation)
-					 */
-	unsigned int	prev;	/* number of the block of PAGE_SIZE bytes that
-				 * was the current one previously
-				 */
 	void		*buffer;	/* address of the block to read from
 					 * or write to
 					 */
-	unsigned int	buf_offset;	/* location to read from or write to,
-					 * given as a displacement from 'buffer'
-					 */
 	int		sync_read;	/* Set to one to notify the caller of
 					 * snapshot_write_next() that it may
 					 * need to call wait_on_bio_chain()
@@ -125,12 +113,12 @@ struct snapshot_handle {
  * snapshot_read_next()/snapshot_write_next() is allowed to
  * read/write data after the function returns
  */
-#define data_of(handle)	((handle).buffer + (handle).buf_offset)
+#define data_of(handle)	((handle).buffer)
 
 extern unsigned int snapshot_additional_pages(struct zone *zone);
 extern unsigned long snapshot_get_image_size(void);
-extern int snapshot_read_next(struct snapshot_handle *handle, size_t count);
-extern int snapshot_write_next(struct snapshot_handle *handle, size_t count);
+extern int snapshot_read_next(struct snapshot_handle *handle);
+extern int snapshot_write_next(struct snapshot_handle *handle);
 extern void snapshot_write_finalize(struct snapshot_handle *handle);
 extern int snapshot_image_loaded(struct snapshot_handle *handle);
 
@@ -154,6 +142,15 @@ extern int swsusp_read(unsigned int *flags_p);
 extern int swsusp_write(unsigned int flags);
 extern void swsusp_close(fmode_t);
 
+/* kernel/power/block_io.c */
+extern struct block_device *hib_resume_bdev;
+
+extern int hib_bio_read_page(pgoff_t page_off, void *addr,
+		struct bio **bio_chain);
+extern int hib_bio_write_page(pgoff_t page_off, void *addr,
+		struct bio **bio_chain);
+extern int hib_wait_on_bio_chain(struct bio **bio_chain);
+
 struct timeval;
 /* kernel/power/swsusp.c */
 extern void swsusp_show_speed(struct timeval *, struct timeval *,
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index be861c26dda..25ce010e9f8 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1604,14 +1604,9 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
  *	snapshot_handle structure.  The structure gets updated and a pointer
  *	to it should be passed to this function every next time.
  *
- *	The @count parameter should contain the number of bytes the caller
- *	wants to read from the snapshot.  It must not be zero.
- *
  *	On success the function returns a positive number.  Then, the caller
  *	is allowed to read up to the returned number of bytes from the memory
- *	location computed by the data_of() macro.  The number returned
- *	may be smaller than @count, but this only happens if the read would
- *	cross a page boundary otherwise.
+ *	location computed by the data_of() macro.
  *
  *	The function returns 0 to indicate the end of data stream condition,
  *	and a negative number is returned on error.  In such cases the
@@ -1619,7 +1614,7 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
  *	any more.
  */
 
-int snapshot_read_next(struct snapshot_handle *handle, size_t count)
+int snapshot_read_next(struct snapshot_handle *handle)
 {
 	if (handle->cur > nr_meta_pages + nr_copy_pages)
 		return 0;
@@ -1630,7 +1625,7 @@ int snapshot_read_next(struct snapshot_handle *handle, size_t count)
 		if (!buffer)
 			return -ENOMEM;
 	}
-	if (!handle->offset) {
+	if (!handle->cur) {
 		int error;
 
 		error = init_header((struct swsusp_info *)buffer);
@@ -1639,42 +1634,30 @@ int snapshot_read_next(struct snapshot_handle *handle, size_t count)
 		handle->buffer = buffer;
 		memory_bm_position_reset(&orig_bm);
 		memory_bm_position_reset(&copy_bm);
-	}
-	if (handle->prev < handle->cur) {
-		if (handle->cur <= nr_meta_pages) {
-			memset(buffer, 0, PAGE_SIZE);
-			pack_pfns(buffer, &orig_bm);
-		} else {
-			struct page *page;
+	} else if (handle->cur <= nr_meta_pages) {
+		memset(buffer, 0, PAGE_SIZE);
+		pack_pfns(buffer, &orig_bm);
+	} else {
+		struct page *page;
 
-			page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
-			if (PageHighMem(page)) {
-				/* Highmem pages are copied to the buffer,
-				 * because we can't return with a kmapped
-				 * highmem page (we may not be called again).
-				 */
-				void *kaddr;
+		page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
+		if (PageHighMem(page)) {
+			/* Highmem pages are copied to the buffer,
+			 * because we can't return with a kmapped
+			 * highmem page (we may not be called again).
+			 */
+			void *kaddr;
 
-				kaddr = kmap_atomic(page, KM_USER0);
-				memcpy(buffer, kaddr, PAGE_SIZE);
-				kunmap_atomic(kaddr, KM_USER0);
-				handle->buffer = buffer;
-			} else {
-				handle->buffer = page_address(page);
-			}
+			kaddr = kmap_atomic(page, KM_USER0);
+			memcpy(buffer, kaddr, PAGE_SIZE);
+			kunmap_atomic(kaddr, KM_USER0);
+			handle->buffer = buffer;
+		} else {
+			handle->buffer = page_address(page);
 		}
-		handle->prev = handle->cur;
-	}
-	handle->buf_offset = handle->cur_offset;
-	if (handle->cur_offset + count >= PAGE_SIZE) {
-		count = PAGE_SIZE - handle->cur_offset;
-		handle->cur_offset = 0;
-		handle->cur++;
-	} else {
-		handle->cur_offset += count;
 	}
-	handle->offset += count;
-	return count;
+	handle->cur++;
+	return PAGE_SIZE;
 }
 
 /**
@@ -2133,14 +2116,9 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
  *	snapshot_handle structure.  The structure gets updated and a pointer
  *	to it should be passed to this function every next time.
  *
- *	The @count parameter should contain the number of bytes the caller
- *	wants to write to the image.  It must not be zero.
- *
  *	On success the function returns a positive number.  Then, the caller
  *	is allowed to write up to the returned number of bytes to the memory
- *	location computed by the data_of() macro.  The number returned
- *	may be smaller than @count, but this only happens if the write would
- *	cross a page boundary otherwise.
+ *	location computed by the data_of() macro.
  *
  *	The function returns 0 to indicate the "end of file" condition,
  *	and a negative number is returned on error.  In such cases the
@@ -2148,16 +2126,18 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
  *	any more.
  */
 
-int snapshot_write_next(struct snapshot_handle *handle, size_t count)
+int snapshot_write_next(struct snapshot_handle *handle)
 {
 	static struct chain_allocator ca;
 	int error = 0;
 
 	/* Check if we have already loaded the entire image */
-	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages)
+	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages)
 		return 0;
 
-	if (handle->offset == 0) {
+	handle->sync_read = 1;
+
+	if (!handle->cur) {
 		if (!buffer)
 			/* This makes the buffer be freed by swsusp_free() */
 			buffer = get_image_page(GFP_ATOMIC, PG_ANY);
@@ -2166,56 +2146,43 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 			return -ENOMEM;
 
 		handle->buffer = buffer;
-	}
-	handle->sync_read = 1;
-	if (handle->prev < handle->cur) {
-		if (handle->prev == 0) {
-			error = load_header(buffer);
-			if (error)
-				return error;
+	} else if (handle->cur == 1) {
+		error = load_header(buffer);
+		if (error)
+			return error;
 
-			error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
-			if (error)
-				return error;
+		error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
+		if (error)
+			return error;
+
+	} else if (handle->cur <= nr_meta_pages + 1) {
+		error = unpack_orig_pfns(buffer, &copy_bm);
+		if (error)
+			return error;
 
-		} else if (handle->prev <= nr_meta_pages) {
-			error = unpack_orig_pfns(buffer, &copy_bm);
+		if (handle->cur == nr_meta_pages + 1) {
+			error = prepare_image(&orig_bm, &copy_bm);
 			if (error)
 				return error;
 
-			if (handle->prev == nr_meta_pages) {
-				error = prepare_image(&orig_bm, &copy_bm);
-				if (error)
-					return error;
-
-				chain_init(&ca, GFP_ATOMIC, PG_SAFE);
-				memory_bm_position_reset(&orig_bm);
-				restore_pblist = NULL;
-				handle->buffer = get_buffer(&orig_bm, &ca);
-				handle->sync_read = 0;
-				if (IS_ERR(handle->buffer))
-					return PTR_ERR(handle->buffer);
-			}
-		} else {
-			copy_last_highmem_page();
+			chain_init(&ca, GFP_ATOMIC, PG_SAFE);
+			memory_bm_position_reset(&orig_bm);
+			restore_pblist = NULL;
 			handle->buffer = get_buffer(&orig_bm, &ca);
+			handle->sync_read = 0;
 			if (IS_ERR(handle->buffer))
 				return PTR_ERR(handle->buffer);
-			if (handle->buffer != buffer)
-				handle->sync_read = 0;
 		}
-		handle->prev = handle->cur;
-	}
-	handle->buf_offset = handle->cur_offset;
-	if (handle->cur_offset + count >= PAGE_SIZE) {
-		count = PAGE_SIZE - handle->cur_offset;
-		handle->cur_offset = 0;
-		handle->cur++;
 	} else {
-		handle->cur_offset += count;
+		copy_last_highmem_page();
+		handle->buffer = get_buffer(&orig_bm, &ca);
+		if (IS_ERR(handle->buffer))
+			return PTR_ERR(handle->buffer);
+		if (handle->buffer != buffer)
+			handle->sync_read = 0;
 	}
-	handle->offset += count;
-	return count;
+	handle->cur++;
+	return PAGE_SIZE;
 }
 
 /**
@@ -2230,7 +2197,7 @@ void snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	copy_last_highmem_page();
 	/* Free only if we have loaded the image entirely */
-	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages) {
+	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
 		memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
 		free_highmem_data();
 	}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 66824d71983..b0bb2177839 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -29,6 +29,40 @@
 
 #define SWSUSP_SIG	"S1SUSPEND"
 
+/*
+ *	The swap map is a data structure used for keeping track of each page
+ *	written to a swap partition.  It consists of many swap_map_page
+ *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
+ *	These structures are stored on the swap and linked together with the
+ *	help of the .next_swap member.
+ *
+ *	The swap map is created during suspend.  The swap map pages are
+ *	allocated and populated one at a time, so we only need one memory
+ *	page to set up the entire structure.
+ *
+ *	During resume we also only need to use one swap_map_page structure
+ *	at a time.
+ */
+
+#define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
+
+struct swap_map_page {
+	sector_t entries[MAP_PAGE_ENTRIES];
+	sector_t next_swap;
+};
+
+/**
+ *	The swap_map_handle structure is used for handling swap in
+ *	a file-alike way
+ */
+
+struct swap_map_handle {
+	struct swap_map_page *cur;
+	sector_t cur_swap;
+	sector_t first_sector;
+	unsigned int k;
+};
+
 struct swsusp_header {
 	char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int)];
 	sector_t image;
@@ -145,110 +179,24 @@ int swsusp_swap_in_use(void)
  */
 
 static unsigned short root_swap = 0xffff;
-static struct block_device *resume_bdev;
-
-/**
- *	submit - submit BIO request.
- *	@rw:	READ or WRITE.
- *	@off	physical offset of page.
- *	@page:	page we're reading or writing.
- *	@bio_chain: list of pending biod (for async reading)
- *
- *	Straight from the textbook - allocate and initialize the bio.
- *	If we're reading, make sure the page is marked as dirty.
- *	Then submit it and, if @bio_chain == NULL, wait.
- */
-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);
-	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
-	bio->bi_bdev = resume_bdev;
-	bio->bi_end_io = end_swap_bio_read;
-
-	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
-		printk(KERN_ERR "PM: Adding page to bio failed at %ld\n",
-			page_off);
-		bio_put(bio);
-		return -EFAULT;
-	}
-
-	lock_page(page);
-	bio_get(bio);
-
-	if (bio_chain == NULL) {
-		submit_bio(bio_rw, bio);
-		wait_on_page_locked(page);
-		if (rw == READ)
-			bio_set_pages_dirty(bio);
-		bio_put(bio);
-	} else {
-		if (rw == READ)
-			get_page(page);	/* These pages are freed later */
-		bio->bi_private = *bio_chain;
-		*bio_chain = bio;
-		submit_bio(bio_rw, bio);
-	}
-	return 0;
-}
-
-static int bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(READ, page_off, virt_to_page(addr), bio_chain);
-}
-
-static int bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(WRITE, page_off, virt_to_page(addr), bio_chain);
-}
-
-static int wait_on_bio_chain(struct bio **bio_chain)
-{
-	struct bio *bio;
-	struct bio *next_bio;
-	int ret = 0;
-
-	if (bio_chain == NULL)
-		return 0;
-
-	bio = *bio_chain;
-	if (bio == NULL)
-		return 0;
-	while (bio) {
-		struct page *page;
-
-		next_bio = bio->bi_private;
-		page = bio->bi_io_vec[0].bv_page;
-		wait_on_page_locked(page);
-		if (!PageUptodate(page) || PageError(page))
-			ret = -EIO;
-		put_page(page);
-		bio_put(bio);
-		bio = next_bio;
-	}
-	*bio_chain = NULL;
-	return ret;
-}
+struct block_device *hib_resume_bdev;
 
 /*
  * Saving part
  */
 
-static int mark_swapfiles(sector_t start, unsigned int flags)
+static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
 		memcpy(swsusp_header->sig,SWSUSP_SIG, 10);
-		swsusp_header->image = start;
+		swsusp_header->image = handle->first_sector;
 		swsusp_header->flags = flags;
-		error = bio_write_page(swsusp_resume_block,
+		error = hib_bio_write_page(swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Swap header not found!\n");
@@ -260,25 +208,26 @@ static int mark_swapfiles(sector_t start, unsigned int flags)
 /**
  *	swsusp_swap_check - check if the resume device is a swap device
  *	and get its index (if so)
+ *
+ *	This is called before saving image
  */
-
-static int swsusp_swap_check(void) /* This is called before saving image */
+static int swsusp_swap_check(void)
 {
 	int res;
 
 	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
-			&resume_bdev);
+			&hib_resume_bdev);
 	if (res < 0)
 		return res;
 
 	root_swap = res;
-	res = blkdev_get(resume_bdev, FMODE_WRITE);
+	res = blkdev_get(hib_resume_bdev, FMODE_WRITE);
 	if (res)
 		return res;
 
-	res = set_blocksize(resume_bdev, PAGE_SIZE);
+	res = set_blocksize(hib_resume_bdev, PAGE_SIZE);
 	if (res < 0)
-		blkdev_put(resume_bdev, FMODE_WRITE);
+		blkdev_put(hib_resume_bdev, FMODE_WRITE);
 
 	return res;
 }
@@ -309,42 +258,9 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 	} else {
 		src = buf;
 	}
-	return bio_write_page(offset, src, bio_chain);
+	return hib_bio_write_page(offset, src, bio_chain);
 }
 
-/*
- *	The swap map is a data structure used for keeping track of each page
- *	written to a swap partition.  It consists of many swap_map_page
- *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
- *	These structures are stored on the swap and linked together with the
- *	help of the .next_swap member.
- *
- *	The swap map is created during suspend.  The swap map pages are
- *	allocated and populated one at a time, so we only need one memory
- *	page to set up the entire structure.
- *
- *	During resume we also only need to use one swap_map_page structure
- *	at a time.
- */
-
-#define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
-
-struct swap_map_page {
-	sector_t entries[MAP_PAGE_ENTRIES];
-	sector_t next_swap;
-};
-
-/**
- *	The swap_map_handle structure is used for handling swap in
- *	a file-alike way
- */
-
-struct swap_map_handle {
-	struct swap_map_page *cur;
-	sector_t cur_swap;
-	unsigned int k;
-};
-
 static void release_swap_writer(struct swap_map_handle *handle)
 {
 	if (handle->cur)
@@ -354,16 +270,33 @@ static void release_swap_writer(struct swap_map_handle *handle)
 
 static int get_swap_writer(struct swap_map_handle *handle)
 {
+	int ret;
+
+	ret = swsusp_swap_check();
+	if (ret) {
+		if (ret != -ENOSPC)
+			printk(KERN_ERR "PM: Cannot find swap device, try "
+					"swapon -a.\n");
+		return ret;
+	}
 	handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL);
-	if (!handle->cur)
-		return -ENOMEM;
+	if (!handle->cur) {
+		ret = -ENOMEM;
+		goto err_close;
+	}
 	handle->cur_swap = alloc_swapdev_block(root_swap);
 	if (!handle->cur_swap) {
-		release_swap_writer(handle);
-		return -ENOSPC;
+		ret = -ENOSPC;
+		goto err_rel;
 	}
 	handle->k = 0;
+	handle->first_sector = handle->cur_swap;
 	return 0;
+err_rel:
+	release_swap_writer(handle);
+err_close:
+	swsusp_close(FMODE_WRITE);
+	return ret;
 }
 
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
@@ -380,7 +313,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		return error;
 	handle->cur->entries[handle->k++] = offset;
 	if (handle->k >= MAP_PAGE_ENTRIES) {
-		error = wait_on_bio_chain(bio_chain);
+		error = hib_wait_on_bio_chain(bio_chain);
 		if (error)
 			goto out;
 		offset = alloc_swapdev_block(root_swap);
@@ -406,6 +339,24 @@ static int flush_swap_writer(struct swap_map_handle *handle)
 		return -EINVAL;
 }
 
+static int swap_writer_finish(struct swap_map_handle *handle,
+		unsigned int flags, int error)
+{
+	if (!error) {
+		flush_swap_writer(handle);
+		printk(KERN_INFO "PM: S");
+		error = mark_swapfiles(handle, flags);
+		printk("|\n");
+	}
+
+	if (error)
+		free_all_swap_pages(root_swap);
+	release_swap_writer(handle);
+	swsusp_close(FMODE_WRITE);
+
+	return error;
+}
+
 /**
  *	save_image - save the suspend image data
  */
@@ -431,7 +382,7 @@ static int save_image(struct swap_map_handle *handle,
 	bio = NULL;
 	do_gettimeofday(&start);
 	while (1) {
-		ret = snapshot_read_next(snapshot, PAGE_SIZE);
+		ret = snapshot_read_next(snapshot);
 		if (ret <= 0)
 			break;
 		ret = swap_write_page(handle, data_of(*snapshot), &bio);
@@ -441,7 +392,7 @@ static int save_image(struct swap_map_handle *handle,
 			printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m);
 		nr_pages++;
 	}
-	err2 = wait_on_bio_chain(&bio);
+	err2 = hib_wait_on_bio_chain(&bio);
 	do_gettimeofday(&stop);
 	if (!ret)
 		ret = err2;
@@ -483,50 +434,34 @@ int swsusp_write(unsigned int flags)
 	struct swap_map_handle handle;
 	struct snapshot_handle snapshot;
 	struct swsusp_info *header;
+	unsigned long pages;
 	int error;
 
-	error = swsusp_swap_check();
+	pages = snapshot_get_image_size();
+	error = get_swap_writer(&handle);
 	if (error) {
-		printk(KERN_ERR "PM: Cannot find swap device, try "
-				"swapon -a.\n");
+		printk(KERN_ERR "PM: Cannot get swap writer\n");
 		return error;
 	}
+	if (!enough_swap(pages)) {
+		printk(KERN_ERR "PM: Not enough free swap\n");
+		error = -ENOSPC;
+		goto out_finish;
+	}
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
-	error = snapshot_read_next(&snapshot, PAGE_SIZE);
+	error = snapshot_read_next(&snapshot);
 	if (error < PAGE_SIZE) {
 		if (error >= 0)
 			error = -EFAULT;
 
-		goto out;
+		goto out_finish;
 	}
 	header = (struct swsusp_info *)data_of(snapshot);
-	if (!enough_swap(header->pages)) {
-		printk(KERN_ERR "PM: Not enough free swap\n");
-		error = -ENOSPC;
-		goto out;
-	}
-	error = get_swap_writer(&handle);
-	if (!error) {
-		sector_t start = handle.cur_swap;
-
-		error = swap_write_page(&handle, header, NULL);
-		if (!error)
-			error = save_image(&handle, &snapshot,
-					header->pages - 1);
-
-		if (!error) {
-			flush_swap_writer(&handle);
-			printk(KERN_INFO "PM: S");
-			error = mark_swapfiles(start, flags);
-			printk("|\n");
-		}
-	}
-	if (error)
-		free_all_swap_pages(root_swap);
-
-	release_swap_writer(&handle);
- out:
-	swsusp_close(FMODE_WRITE);
+	error = swap_write_page(&handle, header, NULL);
+	if (!error)
+		error = save_image(&handle, &snapshot, pages - 1);
+out_finish:
+	error = swap_writer_finish(&handle, flags, error);
 	return error;
 }
 
@@ -542,18 +477,21 @@ static void release_swap_reader(struct swap_map_handle *handle)
 	handle->cur = NULL;
 }
 
-static int get_swap_reader(struct swap_map_handle *handle, sector_t start)
+static int get_swap_reader(struct swap_map_handle *handle,
+		unsigned int *flags_p)
 {
 	int error;
 
-	if (!start)
+	*flags_p = swsusp_header->flags;
+
+	if (!swsusp_header->image) /* how can this happen? */
 		return -EINVAL;
 
 	handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH);
 	if (!handle->cur)
 		return -ENOMEM;
 
-	error = bio_read_page(start, handle->cur, NULL);
+	error = hib_bio_read_page(swsusp_header->image, handle->cur, NULL);
 	if (error) {
 		release_swap_reader(handle);
 		return error;
@@ -573,21 +511,28 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = bio_read_page(offset, buf, bio_chain);
+	error = hib_bio_read_page(offset, buf, bio_chain);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
-		error = wait_on_bio_chain(bio_chain);
+		error = hib_wait_on_bio_chain(bio_chain);
 		handle->k = 0;
 		offset = handle->cur->next_swap;
 		if (!offset)
 			release_swap_reader(handle);
 		else if (!error)
-			error = bio_read_page(offset, handle->cur, NULL);
+			error = hib_bio_read_page(offset, handle->cur, NULL);
 	}
 	return error;
 }
 
+static int swap_reader_finish(struct swap_map_handle *handle)
+{
+	release_swap_reader(handle);
+
+	return 0;
+}
+
 /**
  *	load_image - load the image using the swap map handle
  *	@handle and the snapshot handle @snapshot
@@ -615,21 +560,21 @@ static int load_image(struct swap_map_handle *handle,
 	bio = NULL;
 	do_gettimeofday(&start);
 	for ( ; ; ) {
-		error = snapshot_write_next(snapshot, PAGE_SIZE);
+		error = snapshot_write_next(snapshot);
 		if (error <= 0)
 			break;
 		error = swap_read_page(handle, data_of(*snapshot), &bio);
 		if (error)
 			break;
 		if (snapshot->sync_read)
-			error = wait_on_bio_chain(&bio);
+			error = hib_wait_on_bio_chain(&bio);
 		if (error)
 			break;
 		if (!(nr_pages % m))
 			printk("\b\b\b\b%3d%%", nr_pages / m);
 		nr_pages++;
 	}
-	err2 = wait_on_bio_chain(&bio);
+	err2 = hib_wait_on_bio_chain(&bio);
 	do_gettimeofday(&stop);
 	if (!error)
 		error = err2;
@@ -657,20 +602,20 @@ int swsusp_read(unsigned int *flags_p)
 	struct snapshot_handle snapshot;
 	struct swsusp_info *header;
 
-	*flags_p = swsusp_header->flags;
-
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
-	error = snapshot_write_next(&snapshot, PAGE_SIZE);
+	error = snapshot_write_next(&snapshot);
 	if (error < PAGE_SIZE)
 		return error < 0 ? error : -EFAULT;
 	header = (struct swsusp_info *)data_of(snapshot);
-	error = get_swap_reader(&handle, swsusp_header->image);
+	error = get_swap_reader(&handle, flags_p);
+	if (error)
+		goto end;
 	if (!error)
 		error = swap_read_page(&handle, header, NULL);
 	if (!error)
 		error = load_image(&handle, &snapshot, header->pages - 1);
-	release_swap_reader(&handle);
-
+	swap_reader_finish(&handle);
+end:
 	if (!error)
 		pr_debug("PM: Image successfully loaded\n");
 	else
@@ -686,11 +631,11 @@ int swsusp_check(void)
 {
 	int error;
 
-	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
-	if (!IS_ERR(resume_bdev)) {
-		set_blocksize(resume_bdev, PAGE_SIZE);
+	hib_resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
+	if (!IS_ERR(hib_resume_bdev)) {
+		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		memset(swsusp_header, 0, PAGE_SIZE);
-		error = bio_read_page(swsusp_resume_block,
+		error = hib_bio_read_page(swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
@@ -698,7 +643,7 @@ int swsusp_check(void)
 		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = bio_write_page(swsusp_resume_block,
+			error = hib_bio_write_page(swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
 			error = -EINVAL;
@@ -706,11 +651,11 @@ int swsusp_check(void)
 
 put:
 		if (error)
-			blkdev_put(resume_bdev, FMODE_READ);
+			blkdev_put(hib_resume_bdev, FMODE_READ);
 		else
 			pr_debug("PM: Signature found, resuming\n");
 	} else {
-		error = PTR_ERR(resume_bdev);
+		error = PTR_ERR(hib_resume_bdev);
 	}
 
 	if (error)
@@ -725,12 +670,12 @@ put:
 
 void swsusp_close(fmode_t mode)
 {
-	if (IS_ERR(resume_bdev)) {
+	if (IS_ERR(hib_resume_bdev)) {
 		pr_debug("PM: Image device not initialised\n");
 		return;
 	}
 
-	blkdev_put(resume_bdev, mode);
+	blkdev_put(hib_resume_bdev, mode);
 }
 
 static int swsusp_header_init(void)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index a8c96212bc1..e819e17877c 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -151,6 +151,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 {
 	struct snapshot_data *data;
 	ssize_t res;
+	loff_t pg_offp = *offp & ~PAGE_MASK;
 
 	mutex_lock(&pm_mutex);
 
@@ -159,14 +160,19 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 		res = -ENODATA;
 		goto Unlock;
 	}
-	res = snapshot_read_next(&data->handle, count);
-	if (res > 0) {
-		if (copy_to_user(buf, data_of(data->handle), res))
-			res = -EFAULT;
-		else
-			*offp = data->handle.offset;
+	if (!pg_offp) { /* on page boundary? */
+		res = snapshot_read_next(&data->handle);
+		if (res <= 0)
+			goto Unlock;
+	} else {
+		res = PAGE_SIZE - pg_offp;
 	}
 
+	res = simple_read_from_buffer(buf, count, &pg_offp,
+			data_of(data->handle), res);
+	if (res > 0)
+		*offp += res;
+
  Unlock:
 	mutex_unlock(&pm_mutex);
 
@@ -178,18 +184,25 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 {
 	struct snapshot_data *data;
 	ssize_t res;
+	loff_t pg_offp = *offp & ~PAGE_MASK;
 
 	mutex_lock(&pm_mutex);
 
 	data = filp->private_data;
-	res = snapshot_write_next(&data->handle, count);
-	if (res > 0) {
-		if (copy_from_user(data_of(data->handle), buf, res))
-			res = -EFAULT;
-		else
-			*offp = data->handle.offset;
+
+	if (!pg_offp) {
+		res = snapshot_write_next(&data->handle);
+		if (res <= 0)
+			goto unlock;
+	} else {
+		res = PAGE_SIZE - pg_offp;
 	}
 
+	res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
+			buf, count);
+	if (res > 0)
+		*offp += res;
+unlock:
 	mutex_unlock(&pm_mutex);
 
 	return res;
diff --git a/kernel/printk.c b/kernel/printk.c
index 75077ad0b53..444b770c959 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -33,6 +33,7 @@
 #include <linux/bootmem.h>
 #include <linux/syscalls.h>
 #include <linux/kexec.h>
+#include <linux/kdb.h>
 #include <linux/ratelimit.h>
 #include <linux/kmsg_dump.h>
 #include <linux/syslog.h>
@@ -413,6 +414,22 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
 	return do_syslog(type, buf, len, SYSLOG_FROM_CALL);
 }
 
+#ifdef	CONFIG_KGDB_KDB
+/* kdb dmesg command needs access to the syslog buffer.  do_syslog()
+ * uses locks so it cannot be used during debugging.  Just tell kdb
+ * where the start and end of the physical and logical logs are.  This
+ * is equivalent to do_syslog(3).
+ */
+void kdb_syslog_data(char *syslog_data[4])
+{
+	syslog_data[0] = log_buf;
+	syslog_data[1] = log_buf + log_buf_len;
+	syslog_data[2] = log_buf + log_end -
+		(logged_chars < log_buf_len ? logged_chars : log_buf_len);
+	syslog_data[3] = log_buf + log_end;
+}
+#endif	/* CONFIG_KGDB_KDB */
+
 /*
  * Call the console drivers on a range of log_buf
  */
@@ -586,6 +603,14 @@ asmlinkage int printk(const char *fmt, ...)
 	va_list args;
 	int r;
 
+#ifdef CONFIG_KGDB_KDB
+	if (unlikely(kdb_trap_printk)) {
+		va_start(args, fmt);
+		r = vkdb_printf(fmt, args);
+		va_end(args);
+		return r;
+	}
+#endif
 	va_start(args, fmt);
 	r = vprintk(fmt, args);
 	va_end(args);
diff --git a/kernel/profile.c b/kernel/profile.c
index a55d3a367ae..dfadc5b729f 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -127,8 +127,10 @@ int __ref profile_init(void)
 		return 0;
 
 	prof_buffer = vmalloc(buffer_bytes);
-	if (prof_buffer)
+	if (prof_buffer) {
+		memset(prof_buffer, 0, buffer_bytes);
 		return 0;
+	}
 
 	free_cpumask_var(prof_cpu_mask);
 	return -ENOMEM;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 42ad8ae729a..6af9cdd558b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -14,7 +14,6 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/signal.h>
@@ -76,7 +75,6 @@ void __ptrace_unlink(struct task_struct *child)
 	child->parent = child->real_parent;
 	list_del_init(&child->ptrace_entry);
 
-	arch_ptrace_untrace(child);
 	if (task_is_traced(child))
 		ptrace_untrace(child);
 }
@@ -666,10 +664,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 	struct task_struct *child;
 	long ret;
 
-	/*
-	 * This lock_kernel fixes a subtle race with suid exec
-	 */
-	lock_kernel();
 	if (request == PTRACE_TRACEME) {
 		ret = ptrace_traceme();
 		if (!ret)
@@ -703,7 +697,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
  out_put_task_struct:
 	put_task_struct(child);
  out:
-	unlock_kernel();
 	return ret;
 }
 
@@ -813,10 +806,6 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	struct task_struct *child;
 	long ret;
 
-	/*
-	 * This lock_kernel fixes a subtle race with suid exec
-	 */
-	lock_kernel();
 	if (request == PTRACE_TRACEME) {
 		ret = ptrace_traceme();
 		goto out;
@@ -846,7 +835,6 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
  out_put_task_struct:
 	put_task_struct(child);
  out:
-	unlock_kernel();
 	return ret;
 }
 #endif	/* CONFIG_COMPAT */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 03a7ea1579f..72a8dc9567f 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,7 +44,6 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <linux/kernel_stat.h>
 #include <linux/hardirq.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -64,9 +63,6 @@ struct lockdep_map rcu_sched_lock_map =
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 #endif
 
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 int debug_lockdep_rcu_enabled(void)
@@ -97,21 +93,6 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * This function is invoked towards the end of the scheduler's initialization
- * process.  Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system).  After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections.
- */
-void rcu_scheduler_starting(void)
-{
-	WARN_ON(num_online_cpus() != 1);
-	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
-}
-
-/*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
  */
@@ -122,3 +103,14 @@ void wakeme_after_rcu(struct rcu_head  *head)
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
+
+#ifdef CONFIG_PROVE_RCU
+/*
+ * wrapper function to avoid #include problems.
+ */
+int rcu_my_thread_group_empty(void)
+{
+	return thread_group_empty(current);
+}
+EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
+#endif /* #ifdef CONFIG_PROVE_RCU */
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9f6d9ff2572..38729d3cd23 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -44,9 +44,9 @@ struct rcu_ctrlblk {
 };
 
 /* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_ctrlblk = {
-	.donetail	= &rcu_ctrlblk.rcucblist,
-	.curtail	= &rcu_ctrlblk.rcucblist,
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+	.donetail	= &rcu_sched_ctrlblk.rcucblist,
+	.curtail	= &rcu_sched_ctrlblk.rcucblist,
 };
 
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
@@ -54,6 +54,11 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.curtail	= &rcu_bh_ctrlblk.rcucblist,
 };
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 #ifdef CONFIG_NO_HZ
 
 static long rcu_dynticks_nesting = 1;
@@ -108,7 +113,8 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
  */
 void rcu_sched_qs(int cpu)
 {
-	if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
+	    rcu_qsctr_help(&rcu_bh_ctrlblk))
 		raise_softirq(RCU_SOFTIRQ);
 }
 
@@ -173,7 +179,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
  */
 static void rcu_process_callbacks(struct softirq_action *unused)
 {
-	__rcu_process_callbacks(&rcu_ctrlblk);
+	__rcu_process_callbacks(&rcu_sched_ctrlblk);
 	__rcu_process_callbacks(&rcu_bh_ctrlblk);
 }
 
@@ -187,7 +193,8 @@ static void rcu_process_callbacks(struct softirq_action *unused)
  *
  * Cool, huh?  (Due to Josh Triplett.)
  *
- * But we want to make this a static inline later.
+ * But we want to make this a static inline later.  The cond_resched()
+ * currently makes this problematic.
  */
 void synchronize_sched(void)
 {
@@ -195,12 +202,6 @@ void synchronize_sched(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
-void synchronize_rcu_bh(void)
-{
-	synchronize_sched();
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
 /*
  * Helper function for call_rcu() and call_rcu_bh().
  */
@@ -226,7 +227,7 @@ static void __call_rcu(struct rcu_head *head,
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_ctrlblk);
+	__call_rcu(head, func, &rcu_sched_ctrlblk);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -244,11 +245,13 @@ void rcu_barrier(void)
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
@@ -256,11 +259,13 @@ void rcu_barrier_bh(void)
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_bh(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_bh);
 
@@ -268,11 +273,13 @@ void rcu_barrier_sched(void)
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
@@ -280,3 +287,5 @@ void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
+
+#include "rcutiny_plugin.h"
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
new file mode 100644
index 00000000000..d223a92bc74
--- /dev/null
+++ b/kernel/rcutiny_plugin.h
@@ -0,0 +1,39 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions that provide either classic
+ * or preemptable semantics.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2009
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+#include <linux/kernel_stat.h>
+
+/*
+ * During boot, we forgive RCU lockdep issues.  After this function is
+ * invoked, we start taking RCU lockdep issues seriously.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 58df55bf83e..6535ac8bc6a 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -464,9 +464,11 @@ static void rcu_bh_torture_synchronize(void)
 {
 	struct rcu_bh_torture_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	call_rcu_bh(&rcu.head, rcu_bh_torture_wakeme_after_cb);
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
@@ -669,7 +671,7 @@ static struct rcu_torture_ops sched_expedited_ops = {
 	.sync		= synchronize_sched_expedited,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= rcu_expedited_torture_stats,
+	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "sched_expedited"
 };
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 3ec8160fc75..d4437345706 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,6 +46,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/time.h>
+#include <linux/kernel_stat.h>
 
 #include "rcutree.h"
 
@@ -53,8 +54,8 @@
 
 static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 
-#define RCU_STATE_INITIALIZER(name) { \
-	.level = { &name.node[0] }, \
+#define RCU_STATE_INITIALIZER(structname) { \
+	.level = { &structname.node[0] }, \
 	.levelcnt = { \
 		NUM_RCU_LVL_0,  /* root of hierarchy. */ \
 		NUM_RCU_LVL_1, \
@@ -65,13 +66,14 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
-	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&name.onofflock), \
+	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
 	.orphan_cbs_list = NULL, \
-	.orphan_cbs_tail = &name.orphan_cbs_list, \
+	.orphan_cbs_tail = &structname.orphan_cbs_list, \
 	.orphan_qlen = 0, \
-	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&name.fqslock), \
+	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
 	.n_force_qs = 0, \
 	.n_force_qs_ngp = 0, \
+	.name = #structname, \
 }
 
 struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
@@ -80,6 +82,9 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+
 /*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
@@ -97,25 +102,32 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  */
 void rcu_sched_qs(int cpu)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
 
-	rdp = &per_cpu(rcu_sched_data, cpu);
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
-	rcu_preempt_note_context_switch(cpu);
 }
 
 void rcu_bh_qs(int cpu)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
 
-	rdp = &per_cpu(rcu_bh_data, cpu);
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
 }
 
+/*
+ * Note a context switch.  This is a quiescent state for RCU-sched,
+ * and requires special handling for preemptible RCU.
+ */
+void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch(cpu);
+}
+
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
@@ -438,6 +450,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
+int rcu_cpu_stall_panicking __read_mostly;
+
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
@@ -470,7 +484,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 
 	/* OK, time to rat on our buddy... */
 
-	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
+	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {",
+	       rsp->name);
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rcu_print_task_stall(rnp);
@@ -481,7 +496,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 			if (rnp->qsmask & (1UL << cpu))
 				printk(" %d", rnp->grplo + cpu);
 	}
-	printk(" (detected by %d, t=%ld jiffies)\n",
+	printk("} (detected by %d, t=%ld jiffies)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
 	trigger_all_cpu_backtrace();
 
@@ -497,8 +512,8 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
-			smp_processor_id(), jiffies - rsp->gp_start);
+	printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
+	       rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
 	trigger_all_cpu_backtrace();
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -515,6 +530,8 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	long delta;
 	struct rcu_node *rnp;
 
+	if (rcu_cpu_stall_panicking)
+		return;
 	delta = jiffies - rsp->jiffies_stall;
 	rnp = rdp->mynode;
 	if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
@@ -529,6 +546,21 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 }
 
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+	rcu_cpu_stall_panicking = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+	.notifier_call = rcu_panic,
+};
+
+static void __init check_cpu_stall_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+}
+
 #else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -539,6 +571,10 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 }
 
+static void __init check_cpu_stall_init(void)
+{
+}
+
 #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -1125,8 +1161,6 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 void rcu_check_callbacks(int cpu, int user)
 {
-	if (!rcu_pending(cpu))
-		return; /* if nothing for RCU to do. */
 	if (user ||
 	    (idle_cpu(cpu) && rcu_scheduler_active &&
 	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
@@ -1158,7 +1192,8 @@ void rcu_check_callbacks(int cpu, int user)
 		rcu_bh_qs(cpu);
 	}
 	rcu_preempt_check_callbacks(cpu);
-	raise_softirq(RCU_SOFTIRQ);
+	if (rcu_pending(cpu))
+		raise_softirq(RCU_SOFTIRQ);
 }
 
 #ifdef CONFIG_SMP
@@ -1236,11 +1271,11 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		break; /* grace period idle or initializing, ignore. */
 
 	case RCU_SAVE_DYNTICK:
-
-		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
 		if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK)
 			break; /* So gcc recognizes the dead code. */
 
+		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
+
 		/* Record dyntick-idle state. */
 		force_qs_rnp(rsp, dyntick_save_progress_counter);
 		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
@@ -1449,11 +1484,13 @@ void synchronize_sched(void)
 	if (rcu_blocking_is_gp())
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
@@ -1473,11 +1510,13 @@ void synchronize_rcu_bh(void)
 	if (rcu_blocking_is_gp())
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_bh(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
@@ -1498,8 +1537,20 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	check_cpu_stall(rsp, rdp);
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->qs_pending) {
+	if (rdp->qs_pending && !rdp->passed_quiesc) {
+
+		/*
+		 * If force_quiescent_state() coming soon and this CPU
+		 * needs a quiescent state, and this is either RCU-sched
+		 * or RCU-bh, force a local reschedule.
+		 */
 		rdp->n_rp_qs_pending++;
+		if (!rdp->preemptable &&
+		    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
+				 jiffies))
+			set_need_resched();
+	} else if (rdp->qs_pending && rdp->passed_quiesc) {
+		rdp->n_rp_report_qs++;
 		return 1;
 	}
 
@@ -1767,6 +1818,21 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 }
 
 /*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process.  Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system).  After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections.  This function also enables RCU lockdep checking.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
+/*
  * Compute the per-level fanout, either using the exact fanout specified
  * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
  */
@@ -1849,6 +1915,14 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
 		}
 	}
+
+	rnp = rsp->level[NUM_RCU_LVLS - 1];
+	for_each_possible_cpu(i) {
+		while (i > rnp->grphi)
+			rnp++;
+		rsp->rda[i]->mynode = rnp;
+		rcu_boot_init_percpu_data(i, rsp);
+	}
 }
 
 /*
@@ -1859,19 +1933,11 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 #define RCU_INIT_FLAVOR(rsp, rcu_data) \
 do { \
 	int i; \
-	int j; \
-	struct rcu_node *rnp; \
 	\
-	rcu_init_one(rsp); \
-	rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
-	j = 0; \
 	for_each_possible_cpu(i) { \
-		if (i > rnp[j].grphi) \
-			j++; \
-		per_cpu(rcu_data, i).mynode = &rnp[j]; \
 		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
-		rcu_boot_init_percpu_data(i, rsp); \
 	} \
+	rcu_init_one(rsp); \
 } while (0)
 
 void __init rcu_init(void)
@@ -1879,12 +1945,6 @@ void __init rcu_init(void)
 	int cpu;
 
 	rcu_bootup_announce();
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#if NUM_RCU_LVL_4 != 0
-	printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
-#endif /* #if NUM_RCU_LVL_4 != 0 */
 	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
 	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
 	__rcu_init_preempt();
@@ -1898,6 +1958,7 @@ void __init rcu_init(void)
 	cpu_notifier(rcu_cpu_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+	check_cpu_stall_init();
 }
 
 #include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 4a525a30e08..14c040b18ed 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -223,6 +223,7 @@ struct rcu_data {
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
 	unsigned long n_rp_qs_pending;
+	unsigned long n_rp_report_qs;
 	unsigned long n_rp_cb_ready;
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
@@ -326,6 +327,7 @@ struct rcu_state {
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	char *name;				/* Name of structure. */
 };
 
 /* Return values for rcu_preempt_offline_tasks(). */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 79b53bda894..0e4f420245d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -26,6 +26,45 @@
 
 #include <linux/delay.h>
 
+/*
+ * Check the RCU kernel configuration parameters and print informative
+ * messages about anything out of the ordinary.  If you like #ifdef, you
+ * will love this function.
+ */
+static void __init rcu_bootup_announce_oddness(void)
+{
+#ifdef CONFIG_RCU_TRACE
+	printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");
+#endif
+#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
+	printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+	       CONFIG_RCU_FANOUT);
+#endif
+#ifdef CONFIG_RCU_FANOUT_EXACT
+	printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");
+#endif
+#ifdef CONFIG_RCU_FAST_NO_HZ
+	printk(KERN_INFO
+	       "\tRCU dyntick-idle grace-period acceleration is enabled.\n");
+#endif
+#ifdef CONFIG_PROVE_RCU
+	printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
+#endif
+#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
+	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
+	printk(KERN_INFO
+	       "\tRCU-based detection of stalled CPUs is disabled.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+	printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
+#endif
+#if NUM_RCU_LVL_4 != 0
+	printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n");
+#endif
+}
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
@@ -38,8 +77,8 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp);
  */
 static void __init rcu_bootup_announce(void)
 {
-	printk(KERN_INFO
-	       "Experimental preemptable hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+	rcu_bootup_announce_oddness();
 }
 
 /*
@@ -75,13 +114,19 @@ EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
  */
 static void rcu_preempt_qs(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
+	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 }
 
 /*
@@ -144,9 +189,8 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * grace period, then the fact that the task has been enqueued
 	 * means that we continue to block the current grace period.
 	 */
-	rcu_preempt_qs(cpu);
 	local_irq_save(flags);
-	t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+	rcu_preempt_qs(cpu);
 	local_irq_restore(flags);
 }
 
@@ -236,7 +280,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	 */
 	special = t->rcu_read_unlock_special;
 	if (special & RCU_READ_UNLOCK_NEED_QS) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 		rcu_preempt_qs(smp_processor_id());
 	}
 
@@ -473,7 +516,6 @@ static void rcu_preempt_check_callbacks(int cpu)
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 		rcu_preempt_qs(cpu);
 		return;
 	}
@@ -515,11 +557,13 @@ void synchronize_rcu(void)
 	if (!rcu_scheduler_active)
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
@@ -754,6 +798,7 @@ void exit_rcu(void)
 static void __init rcu_bootup_announce(void)
 {
 	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+	rcu_bootup_announce_oddness();
 }
 
 /*
@@ -1008,6 +1053,8 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
 int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
+	int snap;
+	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1015,12 +1062,18 @@ int rcu_needs_cpu(int cpu)
 		return rcu_needs_cpu_quick_check(cpu);
 
 	/* Don't bother unless we are the last non-dyntick-idle CPU. */
-	for_each_cpu_not(thatcpu, nohz_cpu_mask)
-		if (thatcpu != cpu) {
+	for_each_online_cpu(thatcpu) {
+		if (thatcpu == cpu)
+			continue;
+		snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
+		snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+		smp_mb(); /* Order sampling of snap with end of grace period. */
+		if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu_needs_cpu_quick_check(cpu);
 		}
+	}
 
 	/* Check and update the rcu_dyntick_drain sequencing. */
 	if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d45db2e35d2..36c95b45738 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -241,11 +241,13 @@ static const struct file_operations rcugp_fops = {
 static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 {
 	seq_printf(m, "%3d%cnp=%ld "
-		   "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+		   "qsp=%ld rpq=%ld cbr=%ld cng=%ld "
+		   "gpc=%ld gps=%ld nf=%ld nn=%ld\n",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->n_rcu_pending,
 		   rdp->n_rp_qs_pending,
+		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp,
 		   rdp->n_rp_gp_completed,
diff --git a/kernel/sched.c b/kernel/sched.c
index 6af210a7de7..054a6012de9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,9 +55,9 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
-#include <linux/kthread.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/stop_machine.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
 #include <linux/times.h>
@@ -323,6 +323,15 @@ static inline struct task_group *task_group(struct task_struct *p)
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 {
+	/*
+	 * Strictly speaking this rcu_read_lock() is not needed since the
+	 * task_group is tied to the cgroup, which in turn can never go away
+	 * as long as there are tasks attached to it.
+	 *
+	 * However since task_group() uses task_subsys_state() which is an
+	 * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
+	 */
+	rcu_read_lock();
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
 	p->se.parent = task_group(p)->se[cpu];
@@ -332,6 +341,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
 	p->rt.parent = task_group(p)->rt_se[cpu];
 #endif
+	rcu_read_unlock();
 }
 
 #else
@@ -493,8 +503,11 @@ struct rq {
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ
+	u64 nohz_stamp;
 	unsigned char in_nohz_recently;
 #endif
+	unsigned int skip_clock_update;
+
 	/* capture load from *all* tasks on this cpu: */
 	struct load_weight load;
 	unsigned long nr_load_updates;
@@ -536,15 +549,13 @@ struct rq {
 	int post_schedule;
 	int active_balance;
 	int push_cpu;
+	struct cpu_stop_work active_balance_work;
 	/* cpu of this runqueue: */
 	int cpu;
 	int online;
 
 	unsigned long avg_load_per_task;
 
-	struct task_struct *migration_thread;
-	struct list_head migration_queue;
-
 	u64 rt_avg;
 	u64 age_stamp;
 	u64 idle_stamp;
@@ -592,6 +603,13 @@ static inline
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
 	rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+
+	/*
+	 * A queue event has occurred, and we're going to schedule.  In
+	 * this case, we can save a useless back to back clock update.
+	 */
+	if (test_tsk_need_resched(p))
+		rq->skip_clock_update = 1;
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -626,7 +644,8 @@ static inline int cpu_of(struct rq *rq)
 
 inline void update_rq_clock(struct rq *rq)
 {
-	rq->clock = sched_clock_cpu(cpu_of(rq));
+	if (!rq->skip_clock_update)
+		rq->clock = sched_clock_cpu(cpu_of(rq));
 }
 
 /*
@@ -904,16 +923,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize against
- * ttwu() so that task_cpu() reports a stable number.
- *
- * We need to make an exception for PF_STARTING tasks because the fork
- * path might require task_rq_lock() to work, eg. it can call
- * set_cpus_allowed_ptr() from the cpuset clone_ns code.
+ * Check whether the task is waking, we use this to synchronize ->cpus_allowed
+ * against ttwu().
  */
 static inline int task_is_waking(struct task_struct *p)
 {
-	return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING));
+	return unlikely(p->state == TASK_WAKING);
 }
 
 /*
@@ -926,11 +941,9 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
 	struct rq *rq;
 
 	for (;;) {
-		while (task_is_waking(p))
-			cpu_relax();
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_is_waking(p)))
+		if (likely(rq == task_rq(p)))
 			return rq;
 		raw_spin_unlock(&rq->lock);
 	}
@@ -947,12 +960,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 	struct rq *rq;
 
 	for (;;) {
-		while (task_is_waking(p))
-			cpu_relax();
 		local_irq_save(*flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_is_waking(p)))
+		if (likely(rq == task_rq(p)))
 			return rq;
 		raw_spin_unlock_irqrestore(&rq->lock, *flags);
 	}
@@ -1229,6 +1240,17 @@ void wake_up_idle_cpu(int cpu)
 	if (!tsk_is_polling(rq->idle))
 		smp_send_reschedule(cpu);
 }
+
+int nohz_ratelimit(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 diff = rq->clock - rq->nohz_stamp;
+
+	rq->nohz_stamp = rq->clock;
+
+	return diff < (NSEC_PER_SEC / HZ) >> 1;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -1771,8 +1793,6 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
 			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
 		}
 	}
-	update_rq_clock(rq1);
-	update_rq_clock(rq2);
 }
 
 /*
@@ -1803,7 +1823,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 }
 #endif
 
-static void calc_load_account_active(struct rq *this_rq);
+static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
 
@@ -1860,62 +1880,43 @@ static void set_load_weight(struct task_struct *p)
 	p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
 }
 
-static void update_avg(u64 *avg, u64 sample)
-{
-	s64 diff = sample - *avg;
-	*avg += diff >> 3;
-}
-
-static void
-enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (wakeup)
-		p->se.start_runtime = p->se.sum_exec_runtime;
-
+	update_rq_clock(rq);
 	sched_info_queued(p);
-	p->sched_class->enqueue_task(rq, p, wakeup, head);
+	p->sched_class->enqueue_task(rq, p, flags);
 	p->se.on_rq = 1;
 }
 
-static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (sleep) {
-		if (p->se.last_wakeup) {
-			update_avg(&p->se.avg_overlap,
-				p->se.sum_exec_runtime - p->se.last_wakeup);
-			p->se.last_wakeup = 0;
-		} else {
-			update_avg(&p->se.avg_wakeup,
-				sysctl_sched_wakeup_granularity);
-		}
-	}
-
+	update_rq_clock(rq);
 	sched_info_dequeued(p);
-	p->sched_class->dequeue_task(rq, p, sleep);
+	p->sched_class->dequeue_task(rq, p, flags);
 	p->se.on_rq = 0;
 }
 
 /*
  * activate_task - move a task to the runqueue.
  */
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible--;
 
-	enqueue_task(rq, p, wakeup, false);
+	enqueue_task(rq, p, flags);
 	inc_nr_running(rq);
 }
 
 /*
  * deactivate_task - remove a task from the runqueue.
  */
-static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
+static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
-	dequeue_task(rq, p, sleep);
+	dequeue_task(rq, p, flags);
 	dec_nr_running(rq);
 }
 
@@ -2044,21 +2045,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
-struct migration_req {
-	struct list_head list;
-
+struct migration_arg {
 	struct task_struct *task;
 	int dest_cpu;
-
-	struct completion done;
 };
 
+static int migration_cpu_stop(void *data);
+
 /*
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static int
-migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
+static bool migrate_task(struct task_struct *p, int dest_cpu)
 {
 	struct rq *rq = task_rq(p);
 
@@ -2066,58 +2064,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
 	 */
-	if (!p->se.on_rq && !task_running(rq, p))
-		return 0;
-
-	init_completion(&req->done);
-	req->task = p;
-	req->dest_cpu = dest_cpu;
-	list_add(&req->list, &rq->migration_queue);
-
-	return 1;
-}
-
-/*
- * wait_task_context_switch -	wait for a thread to complete at least one
- *				context switch.
- *
- * @p must not be current.
- */
-void wait_task_context_switch(struct task_struct *p)
-{
-	unsigned long nvcsw, nivcsw, flags;
-	int running;
-	struct rq *rq;
-
-	nvcsw	= p->nvcsw;
-	nivcsw	= p->nivcsw;
-	for (;;) {
-		/*
-		 * The runqueue is assigned before the actual context
-		 * switch. We need to take the runqueue lock.
-		 *
-		 * We could check initially without the lock but it is
-		 * very likely that we need to take the lock in every
-		 * iteration.
-		 */
-		rq = task_rq_lock(p, &flags);
-		running = task_running(rq, p);
-		task_rq_unlock(rq, &flags);
-
-		if (likely(!running))
-			break;
-		/*
-		 * The switch count is incremented before the actual
-		 * context switch. We thus wait for two switches to be
-		 * sure at least one completed.
-		 */
-		if ((p->nvcsw - nvcsw) > 1)
-			break;
-		if ((p->nivcsw - nivcsw) > 1)
-			break;
-
-		cpu_relax();
-	}
+	return p->se.on_rq || task_running(rq, p);
 }
 
 /*
@@ -2175,7 +2122,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &flags);
-		trace_sched_wait_task(rq, p);
+		trace_sched_wait_task(p);
 		running = task_running(rq, p);
 		on_rq = p->se.on_rq;
 		ncsw = 0;
@@ -2273,6 +2220,9 @@ void task_oncpu_function_call(struct task_struct *p,
 }
 
 #ifdef CONFIG_SMP
+/*
+ * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
 	int dest_cpu;
@@ -2289,12 +2239,8 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		return dest_cpu;
 
 	/* No more Mr. Nice Guy. */
-	if (dest_cpu >= nr_cpu_ids) {
-		rcu_read_lock();
-		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
-		rcu_read_unlock();
-		dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
-
+	if (unlikely(dest_cpu >= nr_cpu_ids)) {
+		dest_cpu = cpuset_cpus_allowed_fallback(p);
 		/*
 		 * Don't tell them about moving exiting tasks or
 		 * kernel threads (both mm NULL), since they never
@@ -2311,17 +2257,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * Gets called from 3 sites (exec, fork, wakeup), since it is called without
- * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
- * by:
- *
- *  exec:           is unstable, retry loop
- *  fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
+ * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+	int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -2339,6 +2280,12 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 
 	return cpu;
 }
+
+static void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff >> 3;
+}
 #endif
 
 /***
@@ -2360,16 +2307,13 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
 	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
+	unsigned long en_flags = ENQUEUE_WAKEUP;
 	struct rq *rq;
 
-	if (!sched_feat(SYNC_WAKEUPS))
-		wake_flags &= ~WF_SYNC;
-
 	this_cpu = get_cpu();
 
 	smp_wmb();
 	rq = task_rq_lock(p, &flags);
-	update_rq_clock(rq);
 	if (!(p->state & state))
 		goto out;
 
@@ -2389,28 +2333,26 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	 *
 	 * First fix up the nr_uninterruptible count:
 	 */
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
+	if (task_contributes_to_load(p)) {
+		if (likely(cpu_online(orig_cpu)))
+			rq->nr_uninterruptible--;
+		else
+			this_rq()->nr_uninterruptible--;
+	}
 	p->state = TASK_WAKING;
 
-	if (p->sched_class->task_waking)
+	if (p->sched_class->task_waking) {
 		p->sched_class->task_waking(rq, p);
+		en_flags |= ENQUEUE_WAKING;
+	}
 
-	__task_rq_unlock(rq);
-
-	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu) {
-		/*
-		 * Since we migrate the task without holding any rq->lock,
-		 * we need to be careful with task_rq_lock(), since that
-		 * might end up locking an invalid rq.
-		 */
+	cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
+	if (cpu != orig_cpu)
 		set_task_cpu(p, cpu);
-	}
+	__task_rq_unlock(rq);
 
 	rq = cpu_rq(cpu);
 	raw_spin_lock(&rq->lock);
-	update_rq_clock(rq);
 
 	/*
 	 * We migrated the task without holding either rq->lock, however
@@ -2438,36 +2380,20 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 out_activate:
 #endif /* CONFIG_SMP */
-	schedstat_inc(p, se.nr_wakeups);
+	schedstat_inc(p, se.statistics.nr_wakeups);
 	if (wake_flags & WF_SYNC)
-		schedstat_inc(p, se.nr_wakeups_sync);
+		schedstat_inc(p, se.statistics.nr_wakeups_sync);
 	if (orig_cpu != cpu)
-		schedstat_inc(p, se.nr_wakeups_migrate);
+		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
 	if (cpu == this_cpu)
-		schedstat_inc(p, se.nr_wakeups_local);
+		schedstat_inc(p, se.statistics.nr_wakeups_local);
 	else
-		schedstat_inc(p, se.nr_wakeups_remote);
-	activate_task(rq, p, 1);
+		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+	activate_task(rq, p, en_flags);
 	success = 1;
 
-	/*
-	 * Only attribute actual wakeups done by this task.
-	 */
-	if (!in_interrupt()) {
-		struct sched_entity *se = &current->se;
-		u64 sample = se->sum_exec_runtime;
-
-		if (se->last_wakeup)
-			sample -= se->last_wakeup;
-		else
-			sample -= se->start_runtime;
-		update_avg(&se->avg_wakeup, sample);
-
-		se->last_wakeup = se->sum_exec_runtime;
-	}
-
 out_running:
-	trace_sched_wakeup(rq, p, success);
+	trace_sched_wakeup(p, success);
 	check_preempt_curr(rq, p, wake_flags);
 
 	p->state = TASK_RUNNING;
@@ -2527,42 +2453,9 @@ static void __sched_fork(struct task_struct *p)
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
-	p->se.last_wakeup		= 0;
-	p->se.avg_overlap		= 0;
-	p->se.start_runtime		= 0;
-	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_start			= 0;
-	p->se.wait_max				= 0;
-	p->se.wait_count			= 0;
-	p->se.wait_sum				= 0;
-
-	p->se.sleep_start			= 0;
-	p->se.sleep_max				= 0;
-	p->se.sum_sleep_runtime			= 0;
-
-	p->se.block_start			= 0;
-	p->se.block_max				= 0;
-	p->se.exec_max				= 0;
-	p->se.slice_max				= 0;
-
-	p->se.nr_migrations_cold		= 0;
-	p->se.nr_failed_migrations_affine	= 0;
-	p->se.nr_failed_migrations_running	= 0;
-	p->se.nr_failed_migrations_hot		= 0;
-	p->se.nr_forced_migrations		= 0;
-
-	p->se.nr_wakeups			= 0;
-	p->se.nr_wakeups_sync			= 0;
-	p->se.nr_wakeups_migrate		= 0;
-	p->se.nr_wakeups_local			= 0;
-	p->se.nr_wakeups_remote			= 0;
-	p->se.nr_wakeups_affine			= 0;
-	p->se.nr_wakeups_affine_attempts	= 0;
-	p->se.nr_wakeups_passive		= 0;
-	p->se.nr_wakeups_idle			= 0;
-
+	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2583,11 +2476,11 @@ void sched_fork(struct task_struct *p, int clone_flags)
 
 	__sched_fork(p);
 	/*
-	 * We mark the process as waking here. This guarantees that
+	 * We mark the process as running here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
 	 * event cannot wake it up and insert it on the runqueue either.
 	 */
-	p->state = TASK_WAKING;
+	p->state = TASK_RUNNING;
 
 	/*
 	 * Revert to default priority/policy on fork if requested.
@@ -2654,31 +2547,27 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 	int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
+	rq = task_rq_lock(p, &flags);
+	p->state = TASK_WAKING;
+
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
 	 *
-	 * We still have TASK_WAKING but PF_STARTING is gone now, meaning
-	 * ->cpus_allowed is stable, we have preemption disabled, meaning
-	 * cpu_online_mask is stable.
+	 * We set TASK_WAKING so that select_task_rq() can drop rq->lock
+	 * without people poking at ->cpus_allowed.
 	 */
-	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+	cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
 	set_task_cpu(p, cpu);
-#endif
 
-	/*
-	 * Since the task is not on the rq and we still have TASK_WAKING set
-	 * nobody else will migrate this task.
-	 */
-	rq = cpu_rq(cpu);
-	raw_spin_lock_irqsave(&rq->lock, flags);
-
-	BUG_ON(p->state != TASK_WAKING);
 	p->state = TASK_RUNNING;
-	update_rq_clock(rq);
+	task_rq_unlock(rq, &flags);
+#endif
+
+	rq = task_rq_lock(p, &flags);
 	activate_task(rq, p, 0);
-	trace_sched_wakeup_new(rq, p, 1);
+	trace_sched_wakeup_new(p, 1);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
@@ -2898,7 +2787,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_sched_switch(rq, prev, next);
+	trace_sched_switch(prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -3015,6 +2904,61 @@ static unsigned long calc_load_update;
 unsigned long avenrun[3];
 EXPORT_SYMBOL(avenrun);
 
+static long calc_load_fold_active(struct rq *this_rq)
+{
+	long nr_active, delta = 0;
+
+	nr_active = this_rq->nr_running;
+	nr_active += (long) this_rq->nr_uninterruptible;
+
+	if (nr_active != this_rq->calc_load_active) {
+		delta = nr_active - this_rq->calc_load_active;
+		this_rq->calc_load_active = nr_active;
+	}
+
+	return delta;
+}
+
+#ifdef CONFIG_NO_HZ
+/*
+ * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
+ *
+ * When making the ILB scale, we should try to pull this in as well.
+ */
+static atomic_long_t calc_load_tasks_idle;
+
+static void calc_load_account_idle(struct rq *this_rq)
+{
+	long delta;
+
+	delta = calc_load_fold_active(this_rq);
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks_idle);
+}
+
+static long calc_load_fold_idle(void)
+{
+	long delta = 0;
+
+	/*
+	 * Its got a race, we don't care...
+	 */
+	if (atomic_long_read(&calc_load_tasks_idle))
+		delta = atomic_long_xchg(&calc_load_tasks_idle, 0);
+
+	return delta;
+}
+#else
+static void calc_load_account_idle(struct rq *this_rq)
+{
+}
+
+static inline long calc_load_fold_idle(void)
+{
+	return 0;
+}
+#endif
+
 /**
  * get_avenrun - get the load average array
  * @loads:	pointer to dest load array
@@ -3061,20 +3005,22 @@ void calc_global_load(void)
 }
 
 /*
- * Either called from update_cpu_load() or from a cpu going idle
+ * Called from update_cpu_load() to periodically update this CPU's
+ * active count.
  */
 static void calc_load_account_active(struct rq *this_rq)
 {
-	long nr_active, delta;
+	long delta;
 
-	nr_active = this_rq->nr_running;
-	nr_active += (long) this_rq->nr_uninterruptible;
+	if (time_before(jiffies, this_rq->calc_load_update))
+		return;
 
-	if (nr_active != this_rq->calc_load_active) {
-		delta = nr_active - this_rq->calc_load_active;
-		this_rq->calc_load_active = nr_active;
+	delta  = calc_load_fold_active(this_rq);
+	delta += calc_load_fold_idle();
+	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
-	}
+
+	this_rq->calc_load_update += LOAD_FREQ;
 }
 
 /*
@@ -3106,10 +3052,7 @@ static void update_cpu_load(struct rq *this_rq)
 		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
 	}
 
-	if (time_after_eq(jiffies, this_rq->calc_load_update)) {
-		this_rq->calc_load_update += LOAD_FREQ;
-		calc_load_account_active(this_rq);
-	}
+	calc_load_account_active(this_rq);
 }
 
 #ifdef CONFIG_SMP
@@ -3121,44 +3064,27 @@ static void update_cpu_load(struct rq *this_rq)
 void sched_exec(void)
 {
 	struct task_struct *p = current;
-	struct migration_req req;
-	int dest_cpu, this_cpu;
 	unsigned long flags;
 	struct rq *rq;
-
-again:
-	this_cpu = get_cpu();
-	dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
-	if (dest_cpu == this_cpu) {
-		put_cpu();
-		return;
-	}
+	int dest_cpu;
 
 	rq = task_rq_lock(p, &flags);
-	put_cpu();
+	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	if (dest_cpu == smp_processor_id())
+		goto unlock;
 
 	/*
 	 * select_task_rq() can race against ->cpus_allowed
 	 */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
-	    || unlikely(!cpu_active(dest_cpu))) {
-		task_rq_unlock(rq, &flags);
-		goto again;
-	}
+	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
+	    likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+		struct migration_arg arg = { p, dest_cpu };
 
-	/* force the process onto the specified CPU */
-	if (migrate_task(p, dest_cpu, &req)) {
-		/* Need to wait for migration thread (might exit: take ref). */
-		struct task_struct *mt = rq->migration_thread;
-
-		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
-		wake_up_process(mt);
-		put_task_struct(mt);
-		wait_for_completion(&req.done);
-
+		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		return;
 	}
+unlock:
 	task_rq_unlock(rq, &flags);
 }
 
@@ -3630,23 +3556,9 @@ static inline void schedule_debug(struct task_struct *prev)
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-	if (prev->state == TASK_RUNNING) {
-		u64 runtime = prev->se.sum_exec_runtime;
-
-		runtime -= prev->se.prev_sum_exec_runtime;
-		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
-
-		/*
-		 * In order to avoid avg_overlap growing stale when we are
-		 * indeed overlapping and hence not getting put to sleep, grow
-		 * the avg_overlap on preemption.
-		 *
-		 * We use the average preemption runtime because that
-		 * correlates to the amount of cache footprint a task can
-		 * build up.
-		 */
-		update_avg(&prev->se.avg_overlap, runtime);
-	}
+	if (prev->se.on_rq)
+		update_rq_clock(rq);
+	rq->skip_clock_update = 0;
 	prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3696,7 +3608,7 @@ need_resched:
 	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_sched_qs(cpu);
+	rcu_note_context_switch(cpu);
 	prev = rq->curr;
 	switch_count = &prev->nivcsw;
 
@@ -3709,14 +3621,13 @@ need_resched_nonpreemptible:
 		hrtick_clear(rq);
 
 	raw_spin_lock_irq(&rq->lock);
-	update_rq_clock(rq);
 	clear_tsk_need_resched(prev);
 
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
 		if (unlikely(signal_pending_state(prev->state, prev)))
 			prev->state = TASK_RUNNING;
 		else
-			deactivate_task(rq, prev, 1);
+			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 		switch_count = &prev->nvcsw;
 	}
 
@@ -3780,7 +3691,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 	 * the mutex owner just released it and exited.
 	 */
 	if (probe_kernel_address(&owner->cpu, cpu))
-		goto out;
+		return 0;
 #else
 	cpu = owner->cpu;
 #endif
@@ -3790,14 +3701,14 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 	 * the cpu field may no longer be valid.
 	 */
 	if (cpu >= nr_cpumask_bits)
-		goto out;
+		return 0;
 
 	/*
 	 * We need to validate that we can do a
 	 * get_cpu() and that we have the percpu area.
 	 */
 	if (!cpu_online(cpu))
-		goto out;
+		return 0;
 
 	rq = cpu_rq(cpu);
 
@@ -3816,7 +3727,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 
 		cpu_relax();
 	}
-out:
+
 	return 1;
 }
 #endif
@@ -3940,6 +3851,7 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
 {
 	__wake_up_common(q, mode, 1, 0, NULL);
 }
+EXPORT_SYMBOL_GPL(__wake_up_locked);
 
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
@@ -4039,8 +3951,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
 	if (!x->done) {
 		DECLARE_WAITQUEUE(wait, current);
 
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
+		__add_wait_queue_tail_exclusive(&x->wait, &wait);
 		do {
 			if (signal_pending_state(state, current)) {
 				timeout = -ERESTARTSYS;
@@ -4266,7 +4177,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
 	rq = task_rq_lock(p, &flags);
-	update_rq_clock(rq);
 
 	oldprio = p->prio;
 	prev_class = p->sched_class;
@@ -4287,7 +4197,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		enqueue_task(rq, p, 0, oldprio < prio);
+		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
 	}
@@ -4309,7 +4219,6 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * the task might be in the middle of scheduling on another CPU.
 	 */
 	rq = task_rq_lock(p, &flags);
-	update_rq_clock(rq);
 	/*
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
@@ -4331,7 +4240,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	delta = p->prio - old_prio;
 
 	if (on_rq) {
-		enqueue_task(rq, p, 0, false);
+		enqueue_task(rq, p, 0);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -4592,7 +4501,6 @@ recheck:
 		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 		goto recheck;
 	}
-	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -5329,17 +5237,15 @@ static inline void sched_init_granularity(void)
 /*
  * This is how migration works:
  *
- * 1) we queue a struct migration_req structure in the source CPU's
- *    runqueue and wake up that CPU's migration thread.
- * 2) we down() the locked semaphore => thread blocks.
- * 3) migration thread wakes up (implicitly it forces the migrated
- *    thread off the CPU)
- * 4) it gets the migration request and checks whether the migrated
- *    task is still in the wrong runqueue.
- * 5) if it's in the wrong runqueue then the migration thread removes
+ * 1) we invoke migration_cpu_stop() on the target CPU using
+ *    stop_one_cpu().
+ * 2) stopper starts to run (implicitly forcing the migrated thread
+ *    off the CPU)
+ * 3) it checks whether the migrated task is still in the wrong runqueue.
+ * 4) if it's in the wrong runqueue then the migration thread removes
  *    it and puts it into the right queue.
- * 6) migration thread up()s the semaphore.
- * 7) we wake up and the migration is done.
+ * 5) stopper completes and stop_one_cpu() returns and the migration
+ *    is done.
  */
 
 /*
@@ -5353,12 +5259,23 @@ static inline void sched_init_granularity(void)
  */
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
-	struct migration_req req;
 	unsigned long flags;
 	struct rq *rq;
+	unsigned int dest_cpu;
 	int ret = 0;
 
+	/*
+	 * Serialize against TASK_WAKING so that ttwu() and wunt() can
+	 * drop the rq->lock and still rely on ->cpus_allowed.
+	 */
+again:
+	while (task_is_waking(p))
+		cpu_relax();
 	rq = task_rq_lock(p, &flags);
+	if (task_is_waking(p)) {
+		task_rq_unlock(rq, &flags);
+		goto again;
+	}
 
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;
@@ -5382,15 +5299,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
+	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
+	if (migrate_task(p, dest_cpu)) {
+		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
-		struct task_struct *mt = rq->migration_thread;
-
-		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
-		wake_up_process(mt);
-		put_task_struct(mt);
-		wait_for_completion(&req.done);
+		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
 	}
@@ -5448,98 +5362,49 @@ fail:
 	return ret;
 }
 
-#define RCU_MIGRATION_IDLE	0
-#define RCU_MIGRATION_NEED_QS	1
-#define RCU_MIGRATION_GOT_QS	2
-#define RCU_MIGRATION_MUST_SYNC	3
-
 /*
- * migration_thread - this is a highprio system thread that performs
- * thread migration by bumping thread off CPU then 'pushing' onto
- * another runqueue.
+ * migration_cpu_stop - this will be executed by a highprio stopper thread
+ * and performs thread migration by bumping thread off CPU then
+ * 'pushing' onto another runqueue.
  */
-static int migration_thread(void *data)
-{
-	int badcpu;
-	int cpu = (long)data;
-	struct rq *rq;
-
-	rq = cpu_rq(cpu);
-	BUG_ON(rq->migration_thread != current);
-
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop()) {
-		struct migration_req *req;
-		struct list_head *head;
-
-		raw_spin_lock_irq(&rq->lock);
-
-		if (cpu_is_offline(cpu)) {
-			raw_spin_unlock_irq(&rq->lock);
-			break;
-		}
-
-		if (rq->active_balance) {
-			active_load_balance(rq, cpu);
-			rq->active_balance = 0;
-		}
-
-		head = &rq->migration_queue;
-
-		if (list_empty(head)) {
-			raw_spin_unlock_irq(&rq->lock);
-			schedule();
-			set_current_state(TASK_INTERRUPTIBLE);
-			continue;
-		}
-		req = list_entry(head->next, struct migration_req, list);
-		list_del_init(head->next);
-
-		if (req->task != NULL) {
-			raw_spin_unlock(&rq->lock);
-			__migrate_task(req->task, cpu, req->dest_cpu);
-		} else if (likely(cpu == (badcpu = smp_processor_id()))) {
-			req->dest_cpu = RCU_MIGRATION_GOT_QS;
-			raw_spin_unlock(&rq->lock);
-		} else {
-			req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
-			raw_spin_unlock(&rq->lock);
-			WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
-		}
-		local_irq_enable();
-
-		complete(&req->done);
-	}
-	__set_current_state(TASK_RUNNING);
-
-	return 0;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
+static int migration_cpu_stop(void *data)
 {
-	int ret;
+	struct migration_arg *arg = data;
 
+	/*
+	 * The original target cpu might have gone down and we might
+	 * be on another cpu but it doesn't matter.
+	 */
 	local_irq_disable();
-	ret = __migrate_task(p, src_cpu, dest_cpu);
+	__migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
 	local_irq_enable();
-	return ret;
+	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Figure out where task on dead CPU should go, use force if necessary.
  */
-static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
-	int dest_cpu;
+	struct rq *rq = cpu_rq(dead_cpu);
+	int needs_cpu, uninitialized_var(dest_cpu);
+	unsigned long flags;
 
-again:
-	dest_cpu = select_fallback_rq(dead_cpu, p);
+	local_irq_save(flags);
 
-	/* It can have affinity changed while we were choosing. */
-	if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
-		goto again;
+	raw_spin_lock(&rq->lock);
+	needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
+	if (needs_cpu)
+		dest_cpu = select_fallback_rq(dead_cpu, p);
+	raw_spin_unlock(&rq->lock);
+	/*
+	 * It can only fail if we race with set_cpus_allowed(),
+	 * in the racer should migrate the task anyway.
+	 */
+	if (needs_cpu)
+		__migrate_task(p, dead_cpu, dest_cpu);
+	local_irq_restore(flags);
 }
 
 /*
@@ -5603,7 +5468,6 @@ void sched_idle_next(void)
 
 	__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 
-	update_rq_clock(rq);
 	activate_task(rq, p, 0);
 
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -5658,7 +5522,6 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 	for ( ; ; ) {
 		if (!rq->nr_running)
 			break;
-		update_rq_clock(rq);
 		next = pick_next_task(rq);
 		if (!next)
 			break;
@@ -5881,35 +5744,20 @@ static void set_rq_offline(struct rq *rq)
 static int __cpuinit
 migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
-	struct task_struct *p;
 	int cpu = (long)hcpu;
 	unsigned long flags;
-	struct rq *rq;
+	struct rq *rq = cpu_rq(cpu);
 
 	switch (action) {
 
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		p = kthread_create(migration_thread, hcpu, "migration/%d", cpu);
-		if (IS_ERR(p))
-			return NOTIFY_BAD;
-		kthread_bind(p, cpu);
-		/* Must be high prio: stop_machine expects to yield to it. */
-		rq = task_rq_lock(p, &flags);
-		__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-		task_rq_unlock(rq, &flags);
-		get_task_struct(p);
-		cpu_rq(cpu)->migration_thread = p;
 		rq->calc_load_update = calc_load_update;
 		break;
 
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		/* Strictly unnecessary, as first user will wake it. */
-		wake_up_process(cpu_rq(cpu)->migration_thread);
-
 		/* Update our root-domain */
-		rq = cpu_rq(cpu);
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -5920,61 +5768,24 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		if (!cpu_rq(cpu)->migration_thread)
-			break;
-		/* Unbind it from offline cpu so it can run. Fall thru. */
-		kthread_bind(cpu_rq(cpu)->migration_thread,
-			     cpumask_any(cpu_online_mask));
-		kthread_stop(cpu_rq(cpu)->migration_thread);
-		put_task_struct(cpu_rq(cpu)->migration_thread);
-		cpu_rq(cpu)->migration_thread = NULL;
-		break;
-
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
 		migrate_live_tasks(cpu);
-		rq = cpu_rq(cpu);
-		kthread_stop(rq->migration_thread);
-		put_task_struct(rq->migration_thread);
-		rq->migration_thread = NULL;
 		/* Idle task back to normal (off runqueue, low prio) */
 		raw_spin_lock_irq(&rq->lock);
-		update_rq_clock(rq);
 		deactivate_task(rq, rq->idle, 0);
 		__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
 		rq->idle->sched_class = &idle_sched_class;
 		migrate_dead_tasks(cpu);
 		raw_spin_unlock_irq(&rq->lock);
-		cpuset_unlock();
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
 		calc_global_load_remove(rq);
-		/*
-		 * No need to migrate the tasks: it was best-effort if
-		 * they didn't take sched_hotcpu_mutex. Just wake up
-		 * the requestors.
-		 */
-		raw_spin_lock_irq(&rq->lock);
-		while (!list_empty(&rq->migration_queue)) {
-			struct migration_req *req;
-
-			req = list_entry(rq->migration_queue.next,
-					 struct migration_req, list);
-			list_del_init(&req->list);
-			raw_spin_unlock_irq(&rq->lock);
-			complete(&req->done);
-			raw_spin_lock_irq(&rq->lock);
-		}
-		raw_spin_unlock_irq(&rq->lock);
 		break;
 
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:
 		/* Update our root-domain */
-		rq = cpu_rq(cpu);
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -6305,6 +6116,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
 
+	for (tmp = sd; tmp; tmp = tmp->parent)
+		tmp->span_weight = cpumask_weight(sched_domain_span(tmp));
+
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
 		struct sched_domain *parent = tmp->parent;
@@ -7788,10 +7602,8 @@ void __init sched_init(void)
 		rq->push_cpu = 0;
 		rq->cpu = i;
 		rq->online = 0;
-		rq->migration_thread = NULL;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
-		INIT_LIST_HEAD(&rq->migration_queue);
 		rq_attach_root(rq, &def_root_domain);
 #endif
 		init_rq_hrtick(rq);
@@ -7892,7 +7704,6 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 {
 	int on_rq;
 
-	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	if (on_rq)
 		deactivate_task(rq, p, 0);
@@ -7919,9 +7730,9 @@ void normalize_rt_tasks(void)
 
 		p->se.exec_start		= 0;
 #ifdef CONFIG_SCHEDSTATS
-		p->se.wait_start		= 0;
-		p->se.sleep_start		= 0;
-		p->se.block_start		= 0;
+		p->se.statistics.wait_start	= 0;
+		p->se.statistics.sleep_start	= 0;
+		p->se.statistics.block_start	= 0;
 #endif
 
 		if (!rt_task(p)) {
@@ -7948,9 +7759,9 @@ void normalize_rt_tasks(void)
 
 #endif /* CONFIG_MAGIC_SYSRQ */
 
-#ifdef CONFIG_IA64
+#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
 /*
- * These functions are only useful for the IA64 MCA handling.
+ * These functions are only useful for the IA64 MCA handling, or kdb.
  *
  * They can only be called when the whole system has been
  * stopped - every CPU needs to be quiescent, and no scheduling
@@ -7970,6 +7781,9 @@ struct task_struct *curr_task(int cpu)
 	return cpu_curr(cpu);
 }
 
+#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
+
+#ifdef CONFIG_IA64
 /**
  * set_curr_task - set the current task for a given cpu.
  * @cpu: the processor in question.
@@ -8254,8 +8068,6 @@ void sched_move_task(struct task_struct *tsk)
 
 	rq = task_rq_lock(tsk, &flags);
 
-	update_rq_clock(rq);
-
 	running = task_current(rq, tsk);
 	on_rq = tsk->se.on_rq;
 
@@ -8274,7 +8086,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, tsk, 0, false);
+		enqueue_task(rq, tsk, 0);
 
 	task_rq_unlock(rq, &flags);
 }
@@ -9088,43 +8900,32 @@ struct cgroup_subsys cpuacct_subsys = {
 
 #ifndef CONFIG_SMP
 
-int rcu_expedited_torture_stats(char *page)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
 void synchronize_sched_expedited(void)
 {
+	barrier();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
 #else /* #ifndef CONFIG_SMP */
 
-static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
-static DEFINE_MUTEX(rcu_sched_expedited_mutex);
-
-#define RCU_EXPEDITED_STATE_POST -2
-#define RCU_EXPEDITED_STATE_IDLE -1
+static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
 
-static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
-
-int rcu_expedited_torture_stats(char *page)
+static int synchronize_sched_expedited_cpu_stop(void *data)
 {
-	int cnt = 0;
-	int cpu;
-
-	cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
-	for_each_online_cpu(cpu) {
-		 cnt += sprintf(&page[cnt], " %d:%d",
-				cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
-	}
-	cnt += sprintf(&page[cnt], "\n");
-	return cnt;
+	/*
+	 * There must be a full memory barrier on each affected CPU
+	 * between the time that try_stop_cpus() is called and the
+	 * time that it returns.
+	 *
+	 * In the current initial implementation of cpu_stop, the
+	 * above condition is already met when the control reaches
+	 * this point and the following smp_mb() is not strictly
+	 * necessary.  Do smp_mb() anyway for documentation and
+	 * robustness against future implementation changes.
+	 */
+	smp_mb(); /* See above comment block. */
+	return 0;
 }
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
-static long synchronize_sched_expedited_count;
 
 /*
  * Wait for an rcu-sched grace period to elapse, but use "big hammer"
@@ -9138,18 +8939,14 @@ static long synchronize_sched_expedited_count;
  */
 void synchronize_sched_expedited(void)
 {
-	int cpu;
-	unsigned long flags;
-	bool need_full_sync = 0;
-	struct rq *rq;
-	struct migration_req *req;
-	long snap;
-	int trycount = 0;
+	int snap, trycount = 0;
 
 	smp_mb();  /* ensure prior mod happens before capturing snap. */
-	snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+	snap = atomic_read(&synchronize_sched_expedited_count) + 1;
 	get_online_cpus();
-	while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+	while (try_stop_cpus(cpu_online_mask,
+			     synchronize_sched_expedited_cpu_stop,
+			     NULL) == -EAGAIN) {
 		put_online_cpus();
 		if (trycount++ < 10)
 			udelay(trycount * num_online_cpus());
@@ -9157,41 +8954,15 @@ void synchronize_sched_expedited(void)
 			synchronize_sched();
 			return;
 		}
-		if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+		if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
 			smp_mb(); /* ensure test happens before caller kfree */
 			return;
 		}
 		get_online_cpus();
 	}
-	rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
-	for_each_online_cpu(cpu) {
-		rq = cpu_rq(cpu);
-		req = &per_cpu(rcu_migration_req, cpu);
-		init_completion(&req->done);
-		req->task = NULL;
-		req->dest_cpu = RCU_MIGRATION_NEED_QS;
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		list_add(&req->list, &rq->migration_queue);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-		wake_up_process(rq->migration_thread);
-	}
-	for_each_online_cpu(cpu) {
-		rcu_expedited_state = cpu;
-		req = &per_cpu(rcu_migration_req, cpu);
-		rq = cpu_rq(cpu);
-		wait_for_completion(&req->done);
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
-			need_full_sync = 1;
-		req->dest_cpu = RCU_MIGRATION_IDLE;
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-	}
-	rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
-	synchronize_sched_expedited_count++;
-	mutex_unlock(&rcu_sched_expedited_mutex);
+	atomic_inc(&synchronize_sched_expedited_count);
+	smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
 	put_online_cpus();
-	if (need_full_sync)
-		synchronize_sched();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9b49db14403..87a330a7185 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -70,16 +70,16 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu,
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-	PN(se->wait_start);
-	PN(se->sleep_start);
-	PN(se->block_start);
-	PN(se->sleep_max);
-	PN(se->block_max);
-	PN(se->exec_max);
-	PN(se->slice_max);
-	PN(se->wait_max);
-	PN(se->wait_sum);
-	P(se->wait_count);
+	PN(se->statistics.wait_start);
+	PN(se->statistics.sleep_start);
+	PN(se->statistics.block_start);
+	PN(se->statistics.sleep_max);
+	PN(se->statistics.block_max);
+	PN(se->statistics.exec_max);
+	PN(se->statistics.slice_max);
+	PN(se->statistics.wait_max);
+	PN(se->statistics.wait_sum);
+	P(se->statistics.wait_count);
 #endif
 	P(se->load.weight);
 #undef PN
@@ -104,7 +104,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
 		SPLIT_NS(p->se.vruntime),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(p->se.sum_sleep_runtime));
+		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
 #else
 	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
@@ -114,7 +114,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	{
 		char path[64];
 
+		rcu_read_lock();
 		cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
+		rcu_read_unlock();
 		SEQ_printf(m, " %s", path);
 	}
 #endif
@@ -173,11 +175,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	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)
-	{
-		uid_t uid = cfs_rq->tg->uid;
-		SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
-	}
 #else
 	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
@@ -407,40 +404,38 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.exec_start);
 	PN(se.vruntime);
 	PN(se.sum_exec_runtime);
-	PN(se.avg_overlap);
-	PN(se.avg_wakeup);
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
-	PN(se.wait_start);
-	PN(se.sleep_start);
-	PN(se.block_start);
-	PN(se.sleep_max);
-	PN(se.block_max);
-	PN(se.exec_max);
-	PN(se.slice_max);
-	PN(se.wait_max);
-	PN(se.wait_sum);
-	P(se.wait_count);
-	PN(se.iowait_sum);
-	P(se.iowait_count);
+	PN(se.statistics.wait_start);
+	PN(se.statistics.sleep_start);
+	PN(se.statistics.block_start);
+	PN(se.statistics.sleep_max);
+	PN(se.statistics.block_max);
+	PN(se.statistics.exec_max);
+	PN(se.statistics.slice_max);
+	PN(se.statistics.wait_max);
+	PN(se.statistics.wait_sum);
+	P(se.statistics.wait_count);
+	PN(se.statistics.iowait_sum);
+	P(se.statistics.iowait_count);
 	P(sched_info.bkl_count);
 	P(se.nr_migrations);
-	P(se.nr_migrations_cold);
-	P(se.nr_failed_migrations_affine);
-	P(se.nr_failed_migrations_running);
-	P(se.nr_failed_migrations_hot);
-	P(se.nr_forced_migrations);
-	P(se.nr_wakeups);
-	P(se.nr_wakeups_sync);
-	P(se.nr_wakeups_migrate);
-	P(se.nr_wakeups_local);
-	P(se.nr_wakeups_remote);
-	P(se.nr_wakeups_affine);
-	P(se.nr_wakeups_affine_attempts);
-	P(se.nr_wakeups_passive);
-	P(se.nr_wakeups_idle);
+	P(se.statistics.nr_migrations_cold);
+	P(se.statistics.nr_failed_migrations_affine);
+	P(se.statistics.nr_failed_migrations_running);
+	P(se.statistics.nr_failed_migrations_hot);
+	P(se.statistics.nr_forced_migrations);
+	P(se.statistics.nr_wakeups);
+	P(se.statistics.nr_wakeups_sync);
+	P(se.statistics.nr_wakeups_migrate);
+	P(se.statistics.nr_wakeups_local);
+	P(se.statistics.nr_wakeups_remote);
+	P(se.statistics.nr_wakeups_affine);
+	P(se.statistics.nr_wakeups_affine_attempts);
+	P(se.statistics.nr_wakeups_passive);
+	P(se.statistics.nr_wakeups_idle);
 
 	{
 		u64 avg_atom, avg_per_cpu;
@@ -491,31 +486,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_max				= 0;
-	p->se.wait_sum				= 0;
-	p->se.wait_count			= 0;
-	p->se.iowait_sum			= 0;
-	p->se.iowait_count			= 0;
-	p->se.sleep_max				= 0;
-	p->se.sum_sleep_runtime			= 0;
-	p->se.block_max				= 0;
-	p->se.exec_max				= 0;
-	p->se.slice_max				= 0;
-	p->se.nr_migrations			= 0;
-	p->se.nr_migrations_cold		= 0;
-	p->se.nr_failed_migrations_affine	= 0;
-	p->se.nr_failed_migrations_running	= 0;
-	p->se.nr_failed_migrations_hot		= 0;
-	p->se.nr_forced_migrations		= 0;
-	p->se.nr_wakeups			= 0;
-	p->se.nr_wakeups_sync			= 0;
-	p->se.nr_wakeups_migrate		= 0;
-	p->se.nr_wakeups_local			= 0;
-	p->se.nr_wakeups_remote			= 0;
-	p->se.nr_wakeups_affine			= 0;
-	p->se.nr_wakeups_affine_attempts	= 0;
-	p->se.nr_wakeups_passive		= 0;
-	p->se.nr_wakeups_idle			= 0;
-	p->sched_info.bkl_count			= 0;
+	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5a5ea2cd924..217e4a9393e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -35,8 +35,8 @@
  * (to see the precise effective timeslice length of your workload,
  *  run vmstat and monitor the context-switches (cs) field)
  */
-unsigned int sysctl_sched_latency = 5000000ULL;
-unsigned int normalized_sysctl_sched_latency = 5000000ULL;
+unsigned int sysctl_sched_latency = 6000000ULL;
+unsigned int normalized_sysctl_sched_latency = 6000000ULL;
 
 /*
  * The initial- and re-scaling of tunables is configurable
@@ -52,15 +52,15 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 1000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
+unsigned int sysctl_sched_min_granularity = 2000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-static unsigned int sched_nr_latency = 5;
+static unsigned int sched_nr_latency = 3;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -505,7 +505,8 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 {
 	unsigned long delta_exec_weighted;
 
-	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
+	schedstat_set(curr->statistics.exec_max,
+		      max((u64)delta_exec, curr->statistics.exec_max));
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
@@ -548,7 +549,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
+	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
 }
 
 /*
@@ -567,18 +568,18 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->wait_max, max(se->wait_max,
-			rq_of(cfs_rq)->clock - se->wait_start));
-	schedstat_set(se->wait_count, se->wait_count + 1);
-	schedstat_set(se->wait_sum, se->wait_sum +
-			rq_of(cfs_rq)->clock - se->wait_start);
+	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
+			rq_of(cfs_rq)->clock - se->statistics.wait_start));
+	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
+	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
+			rq_of(cfs_rq)->clock - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
 	if (entity_is_task(se)) {
 		trace_sched_stat_wait(task_of(se),
-			rq_of(cfs_rq)->clock - se->wait_start);
+			rq_of(cfs_rq)->clock - se->statistics.wait_start);
 	}
 #endif
-	schedstat_set(se->wait_start, 0);
+	schedstat_set(se->statistics.wait_start, 0);
 }
 
 static inline void
@@ -657,39 +658,39 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (entity_is_task(se))
 		tsk = task_of(se);
 
-	if (se->sleep_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
+	if (se->statistics.sleep_start) {
+		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
 
-		if (unlikely(delta > se->sleep_max))
-			se->sleep_max = delta;
+		if (unlikely(delta > se->statistics.sleep_max))
+			se->statistics.sleep_max = delta;
 
-		se->sleep_start = 0;
-		se->sum_sleep_runtime += delta;
+		se->statistics.sleep_start = 0;
+		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {
 			account_scheduler_latency(tsk, delta >> 10, 1);
 			trace_sched_stat_sleep(tsk, delta);
 		}
 	}
-	if (se->block_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
+	if (se->statistics.block_start) {
+		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
 
-		if (unlikely(delta > se->block_max))
-			se->block_max = delta;
+		if (unlikely(delta > se->statistics.block_max))
+			se->statistics.block_max = delta;
 
-		se->block_start = 0;
-		se->sum_sleep_runtime += delta;
+		se->statistics.block_start = 0;
+		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {
 			if (tsk->in_iowait) {
-				se->iowait_sum += delta;
-				se->iowait_count++;
+				se->statistics.iowait_sum += delta;
+				se->statistics.iowait_count++;
 				trace_sched_stat_iowait(tsk, delta);
 			}
 
@@ -737,20 +738,10 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		vruntime += sched_vslice(cfs_rq, se);
 
 	/* sleeps up to a single latency don't count. */
-	if (!initial && sched_feat(FAIR_SLEEPERS)) {
+	if (!initial) {
 		unsigned long thresh = sysctl_sched_latency;
 
 		/*
-		 * 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) && (!entity_is_task(se) ||
-				 task_of(se)->policy != SCHED_IDLE))
-			thresh = calc_delta_fair(thresh, se);
-
-		/*
 		 * Halve their sleep time's effect, to allow
 		 * for a gentler effect of sleepers:
 		 */
@@ -766,9 +757,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	se->vruntime = vruntime;
 }
 
-#define ENQUEUE_WAKEUP	1
-#define ENQUEUE_MIGRATE 2
-
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -776,7 +764,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update the normalized vruntime before updating min_vruntime
 	 * through callig update_curr().
 	 */
-	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATE))
+	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
 		se->vruntime += cfs_rq->min_vruntime;
 
 	/*
@@ -812,7 +800,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static void
-dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
+dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Update run-time statistics of the 'current'.
@@ -820,15 +808,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	update_curr(cfs_rq);
 
 	update_stats_dequeue(cfs_rq, se);
-	if (sleep) {
+	if (flags & DEQUEUE_SLEEP) {
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
 
 			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->sleep_start = rq_of(cfs_rq)->clock;
+				se->statistics.sleep_start = rq_of(cfs_rq)->clock;
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->block_start = rq_of(cfs_rq)->clock;
+				se->statistics.block_start = rq_of(cfs_rq)->clock;
 		}
 #endif
 	}
@@ -845,7 +833,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	 * update can refer to the ->curr item and we need to reflect this
 	 * movement in our normalized position.
 	 */
-	if (!sleep)
+	if (!(flags & DEQUEUE_SLEEP))
 		se->vruntime -= cfs_rq->min_vruntime;
 }
 
@@ -912,7 +900,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * when there are only lesser-weight tasks around):
 	 */
 	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
-		se->slice_max = max(se->slice_max,
+		se->statistics.slice_max = max(se->statistics.slice_max,
 			se->sum_exec_runtime - se->prev_sum_exec_runtime);
 	}
 #endif
@@ -1054,16 +1042,10 @@ static inline void hrtick_update(struct rq *rq)
  * then put the task into the rbtree:
  */
 static void
-enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
-	int flags = 0;
-
-	if (wakeup)
-		flags |= ENQUEUE_WAKEUP;
-	if (p->state == TASK_WAKING)
-		flags |= ENQUEUE_MIGRATE;
 
 	for_each_sched_entity(se) {
 		if (se->on_rq)
@@ -1081,18 +1063,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
  * decreased. We remove the task from the rbtree and
  * update the fair scheduling stats:
  */
-static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		dequeue_entity(cfs_rq, se, sleep);
+		dequeue_entity(cfs_rq, se, flags);
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight)
 			break;
-		sleep = 1;
+		flags |= DEQUEUE_SLEEP;
 	}
 
 	hrtick_update(rq);
@@ -1240,7 +1222,6 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-	struct task_struct *curr = current;
 	unsigned long this_load, load;
 	int idx, this_cpu, prev_cpu;
 	unsigned long tl_per_task;
@@ -1255,18 +1236,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	load	  = source_load(prev_cpu, idx);
 	this_load = target_load(this_cpu, idx);
 
-	if (sync) {
-	       if (sched_feat(SYNC_LESS) &&
-		   (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-		    p->se.avg_overlap > sysctl_sched_migration_cost))
-		       sync = 0;
-	} else {
-		if (sched_feat(SYNC_MORE) &&
-		    (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-		     p->se.avg_overlap < sysctl_sched_migration_cost))
-			sync = 1;
-	}
-
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
 	 * effect of the currently running task from the load
@@ -1306,7 +1275,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	if (sync && balanced)
 		return 1;
 
-	schedstat_inc(p, se.nr_wakeups_affine_attempts);
+	schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);
 	tl_per_task = cpu_avg_load_per_task(this_cpu);
 
 	if (balanced ||
@@ -1318,7 +1287,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 		 * there is no bad imbalance.
 		 */
 		schedstat_inc(sd, ttwu_move_affine);
-		schedstat_inc(p, se.nr_wakeups_affine);
+		schedstat_inc(p, se.statistics.nr_wakeups_affine);
 
 		return 1;
 	}
@@ -1406,29 +1375,48 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 /*
  * Try and locate an idle CPU in the sched_domain.
  */
-static int
-select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_sibling(struct task_struct *p, int target)
 {
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
+	struct sched_domain *sd;
 	int i;
 
 	/*
-	 * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
-	 * test in select_task_rq_fair) and the prev_cpu is idle then that's
-	 * always a better target than the current cpu.
+	 * If the task is going to be woken-up on this cpu and if it is
+	 * already idle, then it is the right target.
 	 */
-	if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+	if (target == cpu && idle_cpu(cpu))
+		return cpu;
+
+	/*
+	 * If the task is going to be woken-up on the cpu where it previously
+	 * ran and if it is currently idle, then it the right target.
+	 */
+	if (target == prev_cpu && idle_cpu(prev_cpu))
 		return prev_cpu;
 
 	/*
-	 * Otherwise, iterate the domain and find an elegible idle cpu.
+	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
-	for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
-		if (!cpu_rq(i)->cfs.nr_running) {
-			target = i;
+	for_each_domain(target, sd) {
+		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
 			break;
+
+		for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+			if (idle_cpu(i)) {
+				target = i;
+				break;
+			}
 		}
+
+		/*
+		 * Lets stop looking for an idle sibling when we reached
+		 * the domain that spans the current cpu and prev_cpu.
+		 */
+		if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
+		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+			break;
 	}
 
 	return target;
@@ -1445,7 +1433,8 @@ select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
  *
  * preempt must be disabled.
  */
-static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+static int
+select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
@@ -1456,8 +1445,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 	int sync = wake_flags & WF_SYNC;
 
 	if (sd_flag & SD_BALANCE_WAKE) {
-		if (sched_feat(AFFINE_WAKEUPS) &&
-		    cpumask_test_cpu(cpu, &p->cpus_allowed))
+		if (cpumask_test_cpu(cpu, &p->cpus_allowed))
 			want_affine = 1;
 		new_cpu = prev_cpu;
 	}
@@ -1491,34 +1479,13 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 		}
 
 		/*
-		 * While iterating the domains looking for a spanning
-		 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
-		 * in cache sharing domains along the way.
+		 * If both cpu and prev_cpu are part of this domain,
+		 * cpu is a valid SD_WAKE_AFFINE target.
 		 */
-		if (want_affine) {
-			int target = -1;
-
-			/*
-			 * If both cpu and prev_cpu are part of this domain,
-			 * cpu is a valid SD_WAKE_AFFINE target.
-			 */
-			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
-				target = cpu;
-
-			/*
-			 * If there's an idle sibling in this domain, make that
-			 * the wake_affine target instead of the current cpu.
-			 */
-			if (tmp->flags & SD_SHARE_PKG_RESOURCES)
-				target = select_idle_sibling(p, tmp, target);
-
-			if (target >= 0) {
-				if (tmp->flags & SD_WAKE_AFFINE) {
-					affine_sd = tmp;
-					want_affine = 0;
-				}
-				cpu = target;
-			}
+		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+			affine_sd = tmp;
+			want_affine = 0;
 		}
 
 		if (!want_sd && !want_affine)
@@ -1531,22 +1498,29 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 			sd = tmp;
 	}
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	if (sched_feat(LB_SHARES_UPDATE)) {
 		/*
 		 * Pick the largest domain to update shares over
 		 */
 		tmp = sd;
-		if (affine_sd && (!tmp ||
-				  cpumask_weight(sched_domain_span(affine_sd)) >
-				  cpumask_weight(sched_domain_span(sd))))
+		if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight))
 			tmp = affine_sd;
 
-		if (tmp)
+		if (tmp) {
+			raw_spin_unlock(&rq->lock);
 			update_shares(tmp);
+			raw_spin_lock(&rq->lock);
+		}
 	}
+#endif
 
-	if (affine_sd && wake_affine(affine_sd, p, sync))
-		return cpu;
+	if (affine_sd) {
+		if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+			return select_idle_sibling(p, cpu);
+		else
+			return select_idle_sibling(p, prev_cpu);
+	}
 
 	while (sd) {
 		int load_idx = sd->forkexec_idx;
@@ -1576,10 +1550,10 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 
 		/* Now try balancing at a lower domain level of new_cpu */
 		cpu = new_cpu;
-		weight = cpumask_weight(sched_domain_span(sd));
+		weight = sd->span_weight;
 		sd = NULL;
 		for_each_domain(cpu, tmp) {
-			if (weight <= cpumask_weight(sched_domain_span(tmp)))
+			if (weight <= tmp->span_weight)
 				break;
 			if (tmp->flags & sd_flag)
 				sd = tmp;
@@ -1591,63 +1565,26 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 }
 #endif /* CONFIG_SMP */
 
-/*
- * Adaptive granularity
- *
- * se->avg_wakeup gives the average time a task runs until it does a wakeup,
- * with the limit of wakeup_gran -- when it never does a wakeup.
- *
- * So the smaller avg_wakeup is the faster we want this task to preempt,
- * but we don't want to treat the preemptee unfairly and therefore allow it
- * to run for at least the amount of time we'd like to run.
- *
- * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
- *
- * NOTE: we use *nr_running to scale with load, this nicely matches the
- *       degrading latency on load.
- */
-static unsigned long
-adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
-{
-	u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
-	u64 gran = 0;
-
-	if (this_run < expected_wakeup)
-		gran = expected_wakeup - this_run;
-
-	return min_t(s64, gran, sysctl_sched_wakeup_granularity);
-}
-
 static unsigned long
 wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 {
 	unsigned long gran = sysctl_sched_wakeup_granularity;
 
-	if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
-		gran = adaptive_gran(curr, se);
-
 	/*
 	 * Since its curr running now, convert the gran from real-time
 	 * to virtual-time in his units.
+	 *
+	 * By using 'se' instead of 'curr' we penalize light tasks, so
+	 * they get preempted easier. That is, if 'se' < 'curr' then
+	 * the resulting gran will be larger, therefore penalizing the
+	 * lighter, if otoh 'se' > 'curr' then the resulting gran will
+	 * be smaller, again penalizing the lighter task.
+	 *
+	 * This is especially important for buddies when the leftmost
+	 * task is higher priority than the buddy.
 	 */
-	if (sched_feat(ASYM_GRAN)) {
-		/*
-		 * By using 'se' instead of 'curr' we penalize light tasks, so
-		 * they get preempted easier. That is, if 'se' < 'curr' then
-		 * the resulting gran will be larger, therefore penalizing the
-		 * lighter, if otoh 'se' > 'curr' then the resulting gran will
-		 * be smaller, again penalizing the lighter task.
-		 *
-		 * This is especially important for buddies when the leftmost
-		 * task is higher priority than the buddy.
-		 */
-		if (unlikely(se->load.weight != NICE_0_LOAD))
-			gran = calc_delta_fair(gran, se);
-	} else {
-		if (unlikely(curr->load.weight != NICE_0_LOAD))
-			gran = calc_delta_fair(gran, curr);
-	}
+	if (unlikely(se->load.weight != NICE_0_LOAD))
+		gran = calc_delta_fair(gran, se);
 
 	return gran;
 }
@@ -1705,7 +1642,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	int sync = wake_flags & WF_SYNC;
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
 	if (unlikely(rt_prio(p->prio)))
@@ -1738,14 +1674,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(curr->policy == SCHED_IDLE))
 		goto preempt;
 
-	if (sched_feat(WAKEUP_SYNC) && sync)
-		goto preempt;
-
-	if (sched_feat(WAKEUP_OVERLAP) &&
-			se->avg_overlap < sysctl_sched_migration_cost &&
-			pse->avg_overlap < sysctl_sched_migration_cost)
-		goto preempt;
-
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
@@ -1844,13 +1772,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 3) are cache-hot on their current CPU.
 	 */
 	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
-		schedstat_inc(p, se.nr_failed_migrations_affine);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 		return 0;
 	}
 	*all_pinned = 0;
 
 	if (task_running(rq, p)) {
-		schedstat_inc(p, se.nr_failed_migrations_running);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
 		return 0;
 	}
 
@@ -1866,14 +1794,14 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 #ifdef CONFIG_SCHEDSTATS
 		if (tsk_cache_hot) {
 			schedstat_inc(sd, lb_hot_gained[idle]);
-			schedstat_inc(p, se.nr_forced_migrations);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
 #endif
 		return 1;
 	}
 
 	if (tsk_cache_hot) {
-		schedstat_inc(p, se.nr_failed_migrations_hot);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
 		return 0;
 	}
 	return 1;
@@ -2311,7 +2239,7 @@ unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
 
 unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
 {
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long weight = sd->span_weight;
 	unsigned long smt_gain = sd->smt_gain;
 
 	smt_gain /= weight;
@@ -2344,7 +2272,7 @@ unsigned long scale_rt_power(int cpu)
 
 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long weight = sd->span_weight;
 	unsigned long power = SCHED_LOAD_SCALE;
 	struct sched_group *sdg = sd->groups;
 
@@ -2870,6 +2798,8 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle)
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
+static int active_load_balance_cpu_stop(void *data);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
@@ -2959,8 +2889,9 @@ redo:
 		if (need_active_balance(sd, sd_idle, idle)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
-			/* don't kick the migration_thread, if the curr
-			 * task on busiest cpu can't be moved to this_cpu
+			/* don't kick the active_load_balance_cpu_stop,
+			 * if the curr task on busiest cpu can't be
+			 * moved to this_cpu
 			 */
 			if (!cpumask_test_cpu(this_cpu,
 					      &busiest->curr->cpus_allowed)) {
@@ -2970,14 +2901,22 @@ redo:
 				goto out_one_pinned;
 			}
 
+			/*
+			 * ->active_balance synchronizes accesses to
+			 * ->active_balance_work.  Once set, it's cleared
+			 * only after active load balance is finished.
+			 */
 			if (!busiest->active_balance) {
 				busiest->active_balance = 1;
 				busiest->push_cpu = this_cpu;
 				active_balance = 1;
 			}
 			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+
 			if (active_balance)
-				wake_up_process(busiest->migration_thread);
+				stop_one_cpu_nowait(cpu_of(busiest),
+					active_load_balance_cpu_stop, busiest,
+					&busiest->active_balance_work);
 
 			/*
 			 * We've kicked active balancing, reset the failure
@@ -3084,24 +3023,29 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 }
 
 /*
- * active_load_balance is run by migration threads. It pushes running tasks
- * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
- * running on each physical CPU where possible, and avoids physical /
- * logical imbalances.
- *
- * Called with busiest_rq locked.
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
  */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+static int active_load_balance_cpu_stop(void *data)
 {
+	struct rq *busiest_rq = data;
+	int busiest_cpu = cpu_of(busiest_rq);
 	int target_cpu = busiest_rq->push_cpu;
+	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
-	struct rq *target_rq;
+
+	raw_spin_lock_irq(&busiest_rq->lock);
+
+	/* make sure the requested cpu hasn't gone down in the meantime */
+	if (unlikely(busiest_cpu != smp_processor_id() ||
+		     !busiest_rq->active_balance))
+		goto out_unlock;
 
 	/* Is there any task to move? */
 	if (busiest_rq->nr_running <= 1)
-		return;
-
-	target_rq = cpu_rq(target_cpu);
+		goto out_unlock;
 
 	/*
 	 * This condition is "impossible", if it occurs
@@ -3112,8 +3056,6 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 
 	/* move a task from busiest_rq to target_rq */
 	double_lock_balance(busiest_rq, target_rq);
-	update_rq_clock(busiest_rq);
-	update_rq_clock(target_rq);
 
 	/* Search for an sd spanning us and the target CPU. */
 	for_each_domain(target_cpu, sd) {
@@ -3132,6 +3074,10 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 			schedstat_inc(sd, alb_failed);
 	}
 	double_unlock_balance(busiest_rq, target_rq);
+out_unlock:
+	busiest_rq->active_balance = 0;
+	raw_spin_unlock_irq(&busiest_rq->lock);
+	return 0;
 }
 
 #ifdef CONFIG_NO_HZ
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index d5059fd761d..83c66e8ad3e 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,11 +1,4 @@
 /*
- * Disregards a certain amount of sleep time (sched_latency_ns) and
- * considers the task to be running during that period. This gives it
- * a service deficit on wakeup, allowing it to run sooner.
- */
-SCHED_FEAT(FAIR_SLEEPERS, 1)
-
-/*
  * Only give sleepers 50% of their service deficit. This allows
  * them to run sooner, but does not allow tons of sleepers to
  * rip the spread apart.
@@ -13,13 +6,6 @@ SCHED_FEAT(FAIR_SLEEPERS, 1)
 SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1)
 
 /*
- * By not normalizing the sleep time, heavy tasks get an effective
- * longer period, and lighter task an effective shorter period they
- * are considered running.
- */
-SCHED_FEAT(NORMALIZED_SLEEPER, 0)
-
-/*
  * Place new tasks ahead so that they do not starve already running
  * tasks
  */
@@ -31,37 +17,6 @@ SCHED_FEAT(START_DEBIT, 1)
 SCHED_FEAT(WAKEUP_PREEMPT, 1)
 
 /*
- * Compute wakeup_gran based on task behaviour, clipped to
- *  [0, sched_wakeup_gran_ns]
- */
-SCHED_FEAT(ADAPTIVE_GRAN, 1)
-
-/*
- * When converting the wakeup granularity to virtual time, do it such
- * that heavier tasks preempting a lighter task have an edge.
- */
-SCHED_FEAT(ASYM_GRAN, 1)
-
-/*
- * Always wakeup-preempt SYNC wakeups, see SYNC_WAKEUPS.
- */
-SCHED_FEAT(WAKEUP_SYNC, 0)
-
-/*
- * Wakeup preempt based on task behaviour. Tasks that do not overlap
- * don't get preempted.
- */
-SCHED_FEAT(WAKEUP_OVERLAP, 0)
-
-/*
- * Use the SYNC wakeup hint, pipes and the likes use this to indicate
- * the remote end is likely to consume the data we just wrote, and
- * therefore has cache benefit from being placed on the same cpu, see
- * also AFFINE_WAKEUPS.
- */
-SCHED_FEAT(SYNC_WAKEUPS, 1)
-
-/*
  * Based on load and program behaviour, see if it makes sense to place
  * a newly woken task on the same cpu as the task that woke it --
  * improve cache locality. Typically used with SYNC wakeups as
@@ -70,16 +25,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1)
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
 
 /*
- * Weaken SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_LESS, 1)
-
-/*
- * Add SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_MORE, 0)
-
-/*
  * Prefer to schedule the task we woke last (assuming it failed
  * wakeup-preemption), since its likely going to consume data we
  * touched, increases cache locality.
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index a8a6d8a5094..9fa0f402c87 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -6,7 +6,8 @@
  */
 
 #ifdef CONFIG_SMP
-static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -22,8 +23,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
-	/* adjust the active tasks as we might go into a long sleep */
-	calc_load_account_active(rq);
+	calc_load_account_idle(rq);
 	return rq->idle;
 }
 
@@ -32,7 +32,7 @@ static struct task_struct *pick_next_task_idle(struct rq *rq)
  * message if some code attempts to do it:
  */
 static void
-dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep)
+dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	raw_spin_unlock_irq(&rq->lock);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index b5b920ae2ea..8afb953e31c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -613,7 +613,7 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
-	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
+	schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
@@ -888,20 +888,20 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Adding/removing a task to/from a priority array:
  */
 static void
-enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
-	if (wakeup)
+	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se, head);
+	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
@@ -948,10 +948,9 @@ static void yield_task_rt(struct rq *rq)
 #ifdef CONFIG_SMP
 static int find_lowest_rq(struct task_struct *task);
 
-static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
-	struct rq *rq = task_rq(p);
-
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();
 
diff --git a/kernel/signal.c b/kernel/signal.c
index dbd7fe073c5..825a3f24ad7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2735,3 +2735,43 @@ void __init signals_init(void)
 {
 	sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC);
 }
+
+#ifdef CONFIG_KGDB_KDB
+#include <linux/kdb.h>
+/*
+ * kdb_send_sig_info - Allows kdb to send signals without exposing
+ * signal internals.  This function checks if the required locks are
+ * available before calling the main signal code, to avoid kdb
+ * deadlocks.
+ */
+void
+kdb_send_sig_info(struct task_struct *t, struct siginfo *info)
+{
+	static struct task_struct *kdb_prev_t;
+	int sig, new_t;
+	if (!spin_trylock(&t->sighand->siglock)) {
+		kdb_printf("Can't do kill command now.\n"
+			   "The sigmask lock is held somewhere else in "
+			   "kernel, try again later\n");
+		return;
+	}
+	spin_unlock(&t->sighand->siglock);
+	new_t = kdb_prev_t != t;
+	kdb_prev_t = t;
+	if (t->state != TASK_RUNNING && new_t) {
+		kdb_printf("Process is not RUNNING, sending a signal from "
+			   "kdb risks deadlock\n"
+			   "on the run queue locks. "
+			   "The signal has _not_ been sent.\n"
+			   "Reissue the kill command if you want to risk "
+			   "the deadlock.\n");
+		return;
+	}
+	sig = info->si_signo;
+	if (send_sig_info(sig, info, t))
+		kdb_printf("Fail to deliver Signal %d to process %d.\n",
+			   sig, t->pid);
+	else
+		kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid);
+}
+#endif	/* CONFIG_KGDB_KDB */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 7c1a67ef027..0db913a5c60 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -716,7 +716,7 @@ static int run_ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
-			rcu_sched_qs((long)__bind_cpu);
+			rcu_note_context_switch((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 9bb9fb1bd79..b4e7431e7c7 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,17 +1,384 @@
-/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
- * GPL v2 and any later version.
+/*
+ * kernel/stop_machine.c
+ *
+ * Copyright (C) 2008, 2005	IBM Corporation.
+ * Copyright (C) 2008, 2005	Rusty Russell rusty@rustcorp.com.au
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2 and any later version.
  */
+#include <linux/completion.h>
 #include <linux/cpu.h>
-#include <linux/err.h>
+#include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
+#include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/stop_machine.h>
-#include <linux/syscalls.h>
 #include <linux/interrupt.h>
+#include <linux/kallsyms.h>
 
 #include <asm/atomic.h>
-#include <asm/uaccess.h>
+
+/*
+ * Structure to determine completion condition and record errors.  May
+ * be shared by works on different cpus.
+ */
+struct cpu_stop_done {
+	atomic_t		nr_todo;	/* nr left to execute */
+	bool			executed;	/* actually executed? */
+	int			ret;		/* collected return value */
+	struct completion	completion;	/* fired if nr_todo reaches 0 */
+};
+
+/* the actual stopper, one per every possible cpu, enabled on online cpus */
+struct cpu_stopper {
+	spinlock_t		lock;
+	struct list_head	works;		/* list of pending works */
+	struct task_struct	*thread;	/* stopper thread */
+	bool			enabled;	/* is this stopper enabled? */
+};
+
+static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
+
+static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
+{
+	memset(done, 0, sizeof(*done));
+	atomic_set(&done->nr_todo, nr_todo);
+	init_completion(&done->completion);
+}
+
+/* signal completion unless @done is NULL */
+static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
+{
+	if (done) {
+		if (executed)
+			done->executed = true;
+		if (atomic_dec_and_test(&done->nr_todo))
+			complete(&done->completion);
+	}
+}
+
+/* queue @work to @stopper.  if offline, @work is completed immediately */
+static void cpu_stop_queue_work(struct cpu_stopper *stopper,
+				struct cpu_stop_work *work)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&stopper->lock, flags);
+
+	if (stopper->enabled) {
+		list_add_tail(&work->list, &stopper->works);
+		wake_up_process(stopper->thread);
+	} else
+		cpu_stop_signal_done(work->done, false);
+
+	spin_unlock_irqrestore(&stopper->lock, flags);
+}
+
+/**
+ * stop_one_cpu - stop a cpu
+ * @cpu: cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Execute @fn(@arg) on @cpu.  @fn is run in a process context with
+ * the highest priority preempting any task on the cpu and
+ * monopolizing it.  This function returns after the execution is
+ * complete.
+ *
+ * This function doesn't guarantee @cpu stays online till @fn
+ * completes.  If @cpu goes down in the middle, execution may happen
+ * partially or fully on different cpus.  @fn should either be ready
+ * for that or the caller should ensure that @cpu stays online until
+ * this function completes.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -ENOENT if @fn(@arg) was not executed because @cpu was offline;
+ * otherwise, the return value of @fn.
+ */
+int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_done done;
+	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+
+	cpu_stop_init_done(&done, 1);
+	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work);
+	wait_for_completion(&done.completion);
+	return done.executed ? done.ret : -ENOENT;
+}
+
+/**
+ * stop_one_cpu_nowait - stop a cpu but don't wait for completion
+ * @cpu: cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Similar to stop_one_cpu() but doesn't wait for completion.  The
+ * caller is responsible for ensuring @work_buf is currently unused
+ * and will remain untouched until stopper starts executing @fn.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+			struct cpu_stop_work *work_buf)
+{
+	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
+	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf);
+}
+
+/* static data for stop_cpus */
+static DEFINE_MUTEX(stop_cpus_mutex);
+static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
+
+int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_work *work;
+	struct cpu_stop_done done;
+	unsigned int cpu;
+
+	/* initialize works and done */
+	for_each_cpu(cpu, cpumask) {
+		work = &per_cpu(stop_cpus_work, cpu);
+		work->fn = fn;
+		work->arg = arg;
+		work->done = &done;
+	}
+	cpu_stop_init_done(&done, cpumask_weight(cpumask));
+
+	/*
+	 * Disable preemption while queueing to avoid getting
+	 * preempted by a stopper which might wait for other stoppers
+	 * to enter @fn which can lead to deadlock.
+	 */
+	preempt_disable();
+	for_each_cpu(cpu, cpumask)
+		cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
+				    &per_cpu(stop_cpus_work, cpu));
+	preempt_enable();
+
+	wait_for_completion(&done.completion);
+	return done.executed ? done.ret : -ENOENT;
+}
+
+/**
+ * stop_cpus - stop multiple cpus
+ * @cpumask: cpus to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Execute @fn(@arg) on online cpus in @cpumask.  On each target cpu,
+ * @fn is run in a process context with the highest priority
+ * preempting any task on the cpu and monopolizing it.  This function
+ * returns after all executions are complete.
+ *
+ * This function doesn't guarantee the cpus in @cpumask stay online
+ * till @fn completes.  If some cpus go down in the middle, execution
+ * on the cpu may happen partially or fully on different cpus.  @fn
+ * should either be ready for that or the caller should ensure that
+ * the cpus stay online until this function completes.
+ *
+ * All stop_cpus() calls are serialized making it safe for @fn to wait
+ * for all cpus to start executing it.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -ENOENT if @fn(@arg) was not executed at all because all cpus in
+ * @cpumask were offline; otherwise, 0 if all executions of @fn
+ * returned 0, any non zero return value if any returned non zero.
+ */
+int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+	int ret;
+
+	/* static works are used, process one request at a time */
+	mutex_lock(&stop_cpus_mutex);
+	ret = __stop_cpus(cpumask, fn, arg);
+	mutex_unlock(&stop_cpus_mutex);
+	return ret;
+}
+
+/**
+ * try_stop_cpus - try to stop multiple cpus
+ * @cpumask: cpus to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Identical to stop_cpus() except that it fails with -EAGAIN if
+ * someone else is already using the facility.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -EAGAIN if someone else is already stopping cpus, -ENOENT if
+ * @fn(@arg) was not executed at all because all cpus in @cpumask were
+ * offline; otherwise, 0 if all executions of @fn returned 0, any non
+ * zero return value if any returned non zero.
+ */
+int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+	int ret;
+
+	/* static works are used, process one request at a time */
+	if (!mutex_trylock(&stop_cpus_mutex))
+		return -EAGAIN;
+	ret = __stop_cpus(cpumask, fn, arg);
+	mutex_unlock(&stop_cpus_mutex);
+	return ret;
+}
+
+static int cpu_stopper_thread(void *data)
+{
+	struct cpu_stopper *stopper = data;
+	struct cpu_stop_work *work;
+	int ret;
+
+repeat:
+	set_current_state(TASK_INTERRUPTIBLE);	/* mb paired w/ kthread_stop */
+
+	if (kthread_should_stop()) {
+		__set_current_state(TASK_RUNNING);
+		return 0;
+	}
+
+	work = NULL;
+	spin_lock_irq(&stopper->lock);
+	if (!list_empty(&stopper->works)) {
+		work = list_first_entry(&stopper->works,
+					struct cpu_stop_work, list);
+		list_del_init(&work->list);
+	}
+	spin_unlock_irq(&stopper->lock);
+
+	if (work) {
+		cpu_stop_fn_t fn = work->fn;
+		void *arg = work->arg;
+		struct cpu_stop_done *done = work->done;
+		char ksym_buf[KSYM_NAME_LEN];
+
+		__set_current_state(TASK_RUNNING);
+
+		/* cpu stop callbacks are not allowed to sleep */
+		preempt_disable();
+
+		ret = fn(arg);
+		if (ret)
+			done->ret = ret;
+
+		/* restore preemption and check it's still balanced */
+		preempt_enable();
+		WARN_ONCE(preempt_count(),
+			  "cpu_stop: %s(%p) leaked preempt count\n",
+			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
+					  ksym_buf), arg);
+
+		cpu_stop_signal_done(done, true);
+	} else
+		schedule();
+
+	goto repeat;
+}
+
+/* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
+static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
+					   unsigned long action, void *hcpu)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	unsigned int cpu = (unsigned long)hcpu;
+	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+	struct task_struct *p;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		BUG_ON(stopper->thread || stopper->enabled ||
+		       !list_empty(&stopper->works));
+		p = kthread_create(cpu_stopper_thread, stopper, "migration/%d",
+				   cpu);
+		if (IS_ERR(p))
+			return NOTIFY_BAD;
+		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
+		get_task_struct(p);
+		stopper->thread = p;
+		break;
+
+	case CPU_ONLINE:
+		kthread_bind(stopper->thread, cpu);
+		/* strictly unnecessary, as first user will wake it */
+		wake_up_process(stopper->thread);
+		/* mark enabled */
+		spin_lock_irq(&stopper->lock);
+		stopper->enabled = true;
+		spin_unlock_irq(&stopper->lock);
+		break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+	{
+		struct cpu_stop_work *work;
+
+		/* kill the stopper */
+		kthread_stop(stopper->thread);
+		/* drain remaining works */
+		spin_lock_irq(&stopper->lock);
+		list_for_each_entry(work, &stopper->works, list)
+			cpu_stop_signal_done(work->done, false);
+		stopper->enabled = false;
+		spin_unlock_irq(&stopper->lock);
+		/* release the stopper */
+		put_task_struct(stopper->thread);
+		stopper->thread = NULL;
+		break;
+	}
+#endif
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * Give it a higher priority so that cpu stopper is available to other
+ * cpu notifiers.  It currently shares the same priority as sched
+ * migration_notifier.
+ */
+static struct notifier_block __cpuinitdata cpu_stop_cpu_notifier = {
+	.notifier_call	= cpu_stop_cpu_callback,
+	.priority	= 10,
+};
+
+static int __init cpu_stop_init(void)
+{
+	void *bcpu = (void *)(long)smp_processor_id();
+	unsigned int cpu;
+	int err;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+
+		spin_lock_init(&stopper->lock);
+		INIT_LIST_HEAD(&stopper->works);
+	}
+
+	/* start one for the boot cpu */
+	err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE,
+				    bcpu);
+	BUG_ON(err == NOTIFY_BAD);
+	cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu);
+	register_cpu_notifier(&cpu_stop_cpu_notifier);
+
+	return 0;
+}
+early_initcall(cpu_stop_init);
+
+#ifdef CONFIG_STOP_MACHINE
 
 /* This controls the threads on each CPU. */
 enum stopmachine_state {
@@ -26,174 +393,94 @@ enum stopmachine_state {
 	/* Exit */
 	STOPMACHINE_EXIT,
 };
-static enum stopmachine_state state;
 
 struct stop_machine_data {
-	int (*fn)(void *);
-	void *data;
-	int fnret;
+	int			(*fn)(void *);
+	void			*data;
+	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+	unsigned int		num_threads;
+	const struct cpumask	*active_cpus;
+
+	enum stopmachine_state	state;
+	atomic_t		thread_ack;
 };
 
-/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-static unsigned int num_threads;
-static atomic_t thread_ack;
-static DEFINE_MUTEX(lock);
-/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
-static DEFINE_MUTEX(setup_lock);
-/* Users of stop_machine. */
-static int refcount;
-static struct workqueue_struct *stop_machine_wq;
-static struct stop_machine_data active, idle;
-static const struct cpumask *active_cpus;
-static void __percpu *stop_machine_work;
-
-static void set_state(enum stopmachine_state newstate)
+static void set_state(struct stop_machine_data *smdata,
+		      enum stopmachine_state newstate)
 {
 	/* Reset ack counter. */
-	atomic_set(&thread_ack, num_threads);
+	atomic_set(&smdata->thread_ack, smdata->num_threads);
 	smp_wmb();
-	state = newstate;
+	smdata->state = newstate;
 }
 
 /* Last one to ack a state moves to the next state. */
-static void ack_state(void)
+static void ack_state(struct stop_machine_data *smdata)
 {
-	if (atomic_dec_and_test(&thread_ack))
-		set_state(state + 1);
+	if (atomic_dec_and_test(&smdata->thread_ack))
+		set_state(smdata, smdata->state + 1);
 }
 
-/* This is the actual function which stops the CPU. It runs
- * in the context of a dedicated stopmachine workqueue. */
-static void stop_cpu(struct work_struct *unused)
+/* This is the cpu_stop function which stops the CPU. */
+static int stop_machine_cpu_stop(void *data)
 {
+	struct stop_machine_data *smdata = data;
 	enum stopmachine_state curstate = STOPMACHINE_NONE;
-	struct stop_machine_data *smdata = &idle;
-	int cpu = smp_processor_id();
-	int err;
+	int cpu = smp_processor_id(), err = 0;
+	bool is_active;
+
+	if (!smdata->active_cpus)
+		is_active = cpu == cpumask_first(cpu_online_mask);
+	else
+		is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
 
-	if (!active_cpus) {
-		if (cpu == cpumask_first(cpu_online_mask))
-			smdata = &active;
-	} else {
-		if (cpumask_test_cpu(cpu, active_cpus))
-			smdata = &active;
-	}
 	/* Simple state machine */
 	do {
 		/* Chill out and ensure we re-read stopmachine_state. */
 		cpu_relax();
-		if (state != curstate) {
-			curstate = state;
+		if (smdata->state != curstate) {
+			curstate = smdata->state;
 			switch (curstate) {
 			case STOPMACHINE_DISABLE_IRQ:
 				local_irq_disable();
 				hard_irq_disable();
 				break;
 			case STOPMACHINE_RUN:
-				/* On multiple CPUs only a single error code
-				 * is needed to tell that something failed. */
-				err = smdata->fn(smdata->data);
-				if (err)
-					smdata->fnret = err;
+				if (is_active)
+					err = smdata->fn(smdata->data);
 				break;
 			default:
 				break;
 			}
-			ack_state();
+			ack_state(smdata);
 		}
 	} while (curstate != STOPMACHINE_EXIT);
 
 	local_irq_enable();
+	return err;
 }
 
-/* Callback for CPUs which aren't supposed to do anything. */
-static int chill(void *unused)
-{
-	return 0;
-}
-
-int stop_machine_create(void)
-{
-	mutex_lock(&setup_lock);
-	if (refcount)
-		goto done;
-	stop_machine_wq = create_rt_workqueue("kstop");
-	if (!stop_machine_wq)
-		goto err_out;
-	stop_machine_work = alloc_percpu(struct work_struct);
-	if (!stop_machine_work)
-		goto err_out;
-done:
-	refcount++;
-	mutex_unlock(&setup_lock);
-	return 0;
-
-err_out:
-	if (stop_machine_wq)
-		destroy_workqueue(stop_machine_wq);
-	mutex_unlock(&setup_lock);
-	return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(stop_machine_create);
-
-void stop_machine_destroy(void)
-{
-	mutex_lock(&setup_lock);
-	refcount--;
-	if (refcount)
-		goto done;
-	destroy_workqueue(stop_machine_wq);
-	free_percpu(stop_machine_work);
-done:
-	mutex_unlock(&setup_lock);
-}
-EXPORT_SYMBOL_GPL(stop_machine_destroy);
-
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
-	struct work_struct *sm_work;
-	int i, ret;
-
-	/* Set up initial state. */
-	mutex_lock(&lock);
-	num_threads = num_online_cpus();
-	active_cpus = cpus;
-	active.fn = fn;
-	active.data = data;
-	active.fnret = 0;
-	idle.fn = chill;
-	idle.data = NULL;
-
-	set_state(STOPMACHINE_PREPARE);
-
-	/* Schedule the stop_cpu work on all cpus: hold this CPU so one
-	 * doesn't hit this CPU until we're ready. */
-	get_cpu();
-	for_each_online_cpu(i) {
-		sm_work = per_cpu_ptr(stop_machine_work, i);
-		INIT_WORK(sm_work, stop_cpu);
-		queue_work_on(i, stop_machine_wq, sm_work);
-	}
-	/* This will release the thread on our CPU. */
-	put_cpu();
-	flush_workqueue(stop_machine_wq);
-	ret = active.fnret;
-	mutex_unlock(&lock);
-	return ret;
+	struct stop_machine_data smdata = { .fn = fn, .data = data,
+					    .num_threads = num_online_cpus(),
+					    .active_cpus = cpus };
+
+	/* Set the initial state and stop all online cpus. */
+	set_state(&smdata, STOPMACHINE_PREPARE);
+	return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
 }
 
 int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
 	int ret;
 
-	ret = stop_machine_create();
-	if (ret)
-		return ret;
 	/* No CPUs can come up or down during this. */
 	get_online_cpus();
 	ret = __stop_machine(fn, data, cpus);
 	put_online_cpus();
-	stop_machine_destroy();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
+
+#endif	/* CONFIG_STOP_MACHINE */
diff --git a/kernel/sys.c b/kernel/sys.c
index 7cb426a5896..0d36d889c74 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -492,10 +492,6 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 		return -ENOMEM;
 	old = current_cred();
 
-	retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
-	if (retval)
-		goto error;
-
 	retval = -EPERM;
 	if (rgid != (gid_t) -1) {
 		if (old->gid == rgid ||
@@ -543,10 +539,6 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
 		return -ENOMEM;
 	old = current_cred();
 
-	retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
-	if (retval)
-		goto error;
-
 	retval = -EPERM;
 	if (capable(CAP_SETGID))
 		new->gid = new->egid = new->sgid = new->fsgid = gid;
@@ -610,10 +602,6 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 		return -ENOMEM;
 	old = current_cred();
 
-	retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
-	if (retval)
-		goto error;
-
 	retval = -EPERM;
 	if (ruid != (uid_t) -1) {
 		new->uid = ruid;
@@ -675,10 +663,6 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
 		return -ENOMEM;
 	old = current_cred();
 
-	retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
-	if (retval)
-		goto error;
-
 	retval = -EPERM;
 	if (capable(CAP_SETUID)) {
 		new->suid = new->uid = uid;
@@ -719,9 +703,6 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 	if (!new)
 		return -ENOMEM;
 
-	retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
-	if (retval)
-		goto error;
 	old = current_cred();
 
 	retval = -EPERM;
@@ -788,10 +769,6 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
 		return -ENOMEM;
 	old = current_cred();
 
-	retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
-	if (retval)
-		goto error;
-
 	retval = -EPERM;
 	if (!capable(CAP_SETGID)) {
 		if (rgid != (gid_t) -1 && rgid != old->gid &&
@@ -851,9 +828,6 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
 	old = current_cred();
 	old_fsuid = old->fsuid;
 
-	if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0)
-		goto error;
-
 	if (uid == old->uid  || uid == old->euid  ||
 	    uid == old->suid || uid == old->fsuid ||
 	    capable(CAP_SETUID)) {
@@ -864,7 +838,6 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
 		}
 	}
 
-error:
 	abort_creds(new);
 	return old_fsuid;
 
@@ -888,9 +861,6 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 	old = current_cred();
 	old_fsgid = old->fsgid;
 
-	if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
-		goto error;
-
 	if (gid == old->gid  || gid == old->egid  ||
 	    gid == old->sgid || gid == old->fsgid ||
 	    capable(CAP_SETGID)) {
@@ -900,7 +870,6 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 		}
 	}
 
-error:
 	abort_creds(new);
 	return old_fsgid;
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c649d1c5fe0..18821e77b2a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -164,6 +164,27 @@ static int proc_taint(struct ctl_table *table, int write,
 			       void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
+#ifdef CONFIG_MAGIC_SYSRQ
+static int __sysrq_enabled; /* Note: sysrq code ises it's own private copy */
+
+static int sysrq_sysctl_handler(ctl_table *table, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	int error;
+
+	error = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (error)
+		return error;
+
+	if (write)
+		sysrq_toggle_support(__sysrq_enabled);
+
+	return 0;
+}
+
+#endif
+
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
@@ -568,7 +589,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &__sysrq_enabled,
 		.maxlen		= sizeof (int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sysrq_sysctl_handler,
 	},
 #endif
 #ifdef CONFIG_PROC_SYSCTL
@@ -622,7 +643,7 @@ static struct ctl_table kern_table[] = {
 #endif
 	{
 		.procname	= "userprocess_debug",
-		.data		= &sysctl_userprocess_debug,
+		.data		= &show_unhandled_signals,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
@@ -1440,7 +1461,8 @@ static struct ctl_table fs_table[] = {
 };
 
 static struct ctl_table debug_table[] = {
-#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC)
+#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || \
+    defined(CONFIG_S390)
 	{
 		.procname	= "exception-trace",
 		.data		= &show_unhandled_signals,
@@ -2049,8 +2071,132 @@ int proc_dostring(struct ctl_table *table, int write,
 			       buffer, lenp, ppos);
 }
 
+static size_t proc_skip_spaces(char **buf)
+{
+	size_t ret;
+	char *tmp = skip_spaces(*buf);
+	ret = tmp - *buf;
+	*buf = tmp;
+	return ret;
+}
+
+static void proc_skip_char(char **buf, size_t *size, const char v)
+{
+	while (*size) {
+		if (**buf != v)
+			break;
+		(*size)--;
+		(*buf)++;
+	}
+}
+
+#define TMPBUFLEN 22
+/**
+ * proc_get_long - reads an ASCII formated integer from a user buffer
+ *
+ * @buf - a kernel buffer
+ * @size - size of the kernel buffer
+ * @val - this is where the number will be stored
+ * @neg - set to %TRUE if number is negative
+ * @perm_tr - a vector which contains the allowed trailers
+ * @perm_tr_len - size of the perm_tr vector
+ * @tr - pointer to store the trailer character
+ *
+ * In case of success 0 is returned and buf and size are updated with
+ * the amount of bytes read. If tr is non NULL and a trailing
+ * character exist (size is non zero after returning from this
+ * function) tr is updated with the trailing character.
+ */
+static int proc_get_long(char **buf, size_t *size,
+			  unsigned long *val, bool *neg,
+			  const char *perm_tr, unsigned perm_tr_len, char *tr)
+{
+	int len;
+	char *p, tmp[TMPBUFLEN];
+
+	if (!*size)
+		return -EINVAL;
+
+	len = *size;
+	if (len > TMPBUFLEN - 1)
+		len = TMPBUFLEN - 1;
+
+	memcpy(tmp, *buf, len);
+
+	tmp[len] = 0;
+	p = tmp;
+	if (*p == '-' && *size > 1) {
+		*neg = true;
+		p++;
+	} else
+		*neg = false;
+	if (!isdigit(*p))
+		return -EINVAL;
+
+	*val = simple_strtoul(p, &p, 0);
+
+	len = p - tmp;
+
+	/* We don't know if the next char is whitespace thus we may accept
+	 * invalid integers (e.g. 1234...a) or two integers instead of one
+	 * (e.g. 123...1). So lets not allow such large numbers. */
+	if (len == TMPBUFLEN - 1)
+		return -EINVAL;
+
+	if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len))
+		return -EINVAL;
+
+	if (tr && (len < *size))
+		*tr = *p;
+
+	*buf += len;
+	*size -= len;
+
+	return 0;
+}
+
+/**
+ * proc_put_long - coverts an integer to a decimal ASCII formated string
+ *
+ * @buf - the user buffer
+ * @size - the size of the user buffer
+ * @val - the integer to be converted
+ * @neg - sign of the number, %TRUE for negative
+ *
+ * In case of success 0 is returned and buf and size are updated with
+ * the amount of bytes read.
+ */
+static int proc_put_long(void __user **buf, size_t *size, unsigned long val,
+			  bool neg)
+{
+	int len;
+	char tmp[TMPBUFLEN], *p = tmp;
+
+	sprintf(p, "%s%lu", neg ? "-" : "", val);
+	len = strlen(tmp);
+	if (len > *size)
+		len = *size;
+	if (copy_to_user(*buf, tmp, len))
+		return -EFAULT;
+	*size -= len;
+	*buf += len;
+	return 0;
+}
+#undef TMPBUFLEN
 
-static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
+static int proc_put_char(void __user **buf, size_t *size, char c)
+{
+	if (*size) {
+		char __user **buffer = (char __user **)buf;
+		if (put_user(c, *buffer))
+			return -EFAULT;
+		(*size)--, (*buffer)++;
+		*buf = *buffer;
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 				 int *valp,
 				 int write, void *data)
 {
@@ -2059,33 +2205,31 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
 	} else {
 		int val = *valp;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			*lvalp = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			*lvalp = (unsigned long)val;
 		}
 	}
 	return 0;
 }
 
+static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
+
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 		  int write, void __user *buffer,
 		  size_t *lenp, loff_t *ppos,
-		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
 		  void *data)
 {
-#define TMPBUFLEN 21
-	int *i, vleft, first = 1, neg;
-	unsigned long lval;
-	size_t left, len;
+	int *i, vleft, first = 1, err = 0;
+	unsigned long page = 0;
+	size_t left;
+	char *kbuf;
 	
-	char buf[TMPBUFLEN], *p;
-	char __user *s = buffer;
-	
-	if (!tbl_data || !table->maxlen || !*lenp ||
-	    (*ppos && !write)) {
+	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}
@@ -2097,89 +2241,69 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 	if (!conv)
 		conv = do_proc_dointvec_conv;
 
+	if (write) {
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+		page = __get_free_page(GFP_TEMPORARY);
+		kbuf = (char *) page;
+		if (!kbuf)
+			return -ENOMEM;
+		if (copy_from_user(kbuf, buffer, left)) {
+			err = -EFAULT;
+			goto free;
+		}
+		kbuf[left] = 0;
+	}
+
 	for (; left && vleft--; i++, first=0) {
-		if (write) {
-			while (left) {
-				char c;
-				if (get_user(c, s))
-					return -EFAULT;
-				if (!isspace(c))
-					break;
-				left--;
-				s++;
-			}
-			if (!left)
-				break;
-			neg = 0;
-			len = left;
-			if (len > sizeof(buf) - 1)
-				len = sizeof(buf) - 1;
-			if (copy_from_user(buf, s, len))
-				return -EFAULT;
-			buf[len] = 0;
-			p = buf;
-			if (*p == '-' && left > 1) {
-				neg = 1;
-				p++;
-			}
-			if (*p < '0' || *p > '9')
-				break;
+		unsigned long lval;
+		bool neg;
 
-			lval = simple_strtoul(p, &p, 0);
+		if (write) {
+			left -= proc_skip_spaces(&kbuf);
 
-			len = p-buf;
-			if ((len < left) && *p && !isspace(*p))
+			err = proc_get_long(&kbuf, &left, &lval, &neg,
+					     proc_wspace_sep,
+					     sizeof(proc_wspace_sep), NULL);
+			if (err)
 				break;
-			s += len;
-			left -= len;
-
-			if (conv(&neg, &lval, i, 1, data))
+			if (conv(&neg, &lval, i, 1, data)) {
+				err = -EINVAL;
 				break;
+			}
 		} else {
-			p = buf;
+			if (conv(&neg, &lval, i, 0, data)) {
+				err = -EINVAL;
+				break;
+			}
 			if (!first)
-				*p++ = '\t';
-	
-			if (conv(&neg, &lval, i, 0, data))
+				err = proc_put_char(&buffer, &left, '\t');
+			if (err)
+				break;
+			err = proc_put_long(&buffer, &left, lval, neg);
+			if (err)
 				break;
-
-			sprintf(p, "%s%lu", neg ? "-" : "", lval);
-			len = strlen(buf);
-			if (len > left)
-				len = left;
-			if(copy_to_user(s, buf, len))
-				return -EFAULT;
-			left -= len;
-			s += len;
 		}
 	}
 
-	if (!write && !first && left) {
-		if(put_user('\n', s))
-			return -EFAULT;
-		left--, s++;
-	}
+	if (!write && !first && left && !err)
+		err = proc_put_char(&buffer, &left, '\n');
+	if (write && !err)
+		left -= proc_skip_spaces(&kbuf);
+free:
 	if (write) {
-		while (left) {
-			char c;
-			if (get_user(c, s++))
-				return -EFAULT;
-			if (!isspace(c))
-				break;
-			left--;
-		}
+		free_page(page);
+		if (first)
+			return err ? : -EINVAL;
 	}
-	if (write && first)
-		return -EINVAL;
 	*lenp -= left;
 	*ppos += *lenp;
-	return 0;
-#undef TMPBUFLEN
+	return err;
 }
 
 static int do_proc_dointvec(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos,
-		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
 		  void *data)
 {
@@ -2247,8 +2371,8 @@ struct do_proc_dointvec_minmax_conv_param {
 	int *max;
 };
 
-static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, 
-					int *valp, 
+static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
+					int *valp,
 					int write, void *data)
 {
 	struct do_proc_dointvec_minmax_conv_param *param = data;
@@ -2261,10 +2385,10 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
 	} else {
 		int val = *valp;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			*lvalp = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			*lvalp = (unsigned long)val;
 		}
 	}
@@ -2304,102 +2428,78 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 				     unsigned long convmul,
 				     unsigned long convdiv)
 {
-#define TMPBUFLEN 21
-	unsigned long *i, *min, *max, val;
-	int vleft, first=1, neg;
-	size_t len, left;
-	char buf[TMPBUFLEN], *p;
-	char __user *s = buffer;
-	
-	if (!data || !table->maxlen || !*lenp ||
-	    (*ppos && !write)) {
+	unsigned long *i, *min, *max;
+	int vleft, first = 1, err = 0;
+	unsigned long page = 0;
+	size_t left;
+	char *kbuf;
+
+	if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}
-	
+
 	i = (unsigned long *) data;
 	min = (unsigned long *) table->extra1;
 	max = (unsigned long *) table->extra2;
 	vleft = table->maxlen / sizeof(unsigned long);
 	left = *lenp;
-	
+
+	if (write) {
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+		page = __get_free_page(GFP_TEMPORARY);
+		kbuf = (char *) page;
+		if (!kbuf)
+			return -ENOMEM;
+		if (copy_from_user(kbuf, buffer, left)) {
+			err = -EFAULT;
+			goto free;
+		}
+		kbuf[left] = 0;
+	}
+
 	for (; left && vleft--; i++, min++, max++, first=0) {
+		unsigned long val;
+
 		if (write) {
-			while (left) {
-				char c;
-				if (get_user(c, s))
-					return -EFAULT;
-				if (!isspace(c))
-					break;
-				left--;
-				s++;
-			}
-			if (!left)
-				break;
-			neg = 0;
-			len = left;
-			if (len > TMPBUFLEN-1)
-				len = TMPBUFLEN-1;
-			if (copy_from_user(buf, s, len))
-				return -EFAULT;
-			buf[len] = 0;
-			p = buf;
-			if (*p == '-' && left > 1) {
-				neg = 1;
-				p++;
-			}
-			if (*p < '0' || *p > '9')
-				break;
-			val = simple_strtoul(p, &p, 0) * convmul / convdiv ;
-			len = p-buf;
-			if ((len < left) && *p && !isspace(*p))
+			bool neg;
+
+			left -= proc_skip_spaces(&kbuf);
+
+			err = proc_get_long(&kbuf, &left, &val, &neg,
+					     proc_wspace_sep,
+					     sizeof(proc_wspace_sep), NULL);
+			if (err)
 				break;
 			if (neg)
-				val = -val;
-			s += len;
-			left -= len;
-
-			if(neg)
 				continue;
 			if ((min && val < *min) || (max && val > *max))
 				continue;
 			*i = val;
 		} else {
-			p = buf;
+			val = convdiv * (*i) / convmul;
 			if (!first)
-				*p++ = '\t';
-			sprintf(p, "%lu", convdiv * (*i) / convmul);
-			len = strlen(buf);
-			if (len > left)
-				len = left;
-			if(copy_to_user(s, buf, len))
-				return -EFAULT;
-			left -= len;
-			s += len;
+				err = proc_put_char(&buffer, &left, '\t');
+			err = proc_put_long(&buffer, &left, val, false);
+			if (err)
+				break;
 		}
 	}
 
-	if (!write && !first && left) {
-		if(put_user('\n', s))
-			return -EFAULT;
-		left--, s++;
-	}
+	if (!write && !first && left && !err)
+		err = proc_put_char(&buffer, &left, '\n');
+	if (write && !err)
+		left -= proc_skip_spaces(&kbuf);
+free:
 	if (write) {
-		while (left) {
-			char c;
-			if (get_user(c, s++))
-				return -EFAULT;
-			if (!isspace(c))
-				break;
-			left--;
-		}
+		free_page(page);
+		if (first)
+			return err ? : -EINVAL;
 	}
-	if (write && first)
-		return -EINVAL;
 	*lenp -= left;
 	*ppos += *lenp;
-	return 0;
-#undef TMPBUFLEN
+	return err;
 }
 
 static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
@@ -2460,7 +2560,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
 }
 
 
-static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
 					 int *valp,
 					 int write, void *data)
 {
@@ -2472,10 +2572,10 @@ static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			lval = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			lval = (unsigned long)val;
 		}
 		*lvalp = lval / HZ;
@@ -2483,7 +2583,7 @@ static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
 	return 0;
 }
 
-static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
 						int *valp,
 						int write, void *data)
 {
@@ -2495,10 +2595,10 @@ static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			lval = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			lval = (unsigned long)val;
 		}
 		*lvalp = jiffies_to_clock_t(lval);
@@ -2506,7 +2606,7 @@ static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
 	return 0;
 }
 
-static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
 					    int *valp,
 					    int write, void *data)
 {
@@ -2516,10 +2616,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			lval = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			lval = (unsigned long)val;
 		}
 		*lvalp = jiffies_to_msecs(lval);
@@ -2616,6 +2716,157 @@ static int proc_do_cad_pid(struct ctl_table *table, int write,
 	return 0;
 }
 
+/**
+ * proc_do_large_bitmap - read/write from/to a large bitmap
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * The bitmap is stored at table->data and the bitmap length (in bits)
+ * in table->maxlen.
+ *
+ * We use a range comma separated format (e.g. 1,3-4,10-10) so that
+ * large bitmaps may be represented in a compact manner. Writing into
+ * the file will clear the bitmap then update it with the given input.
+ *
+ * Returns 0 on success.
+ */
+int proc_do_large_bitmap(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err = 0;
+	bool first = 1;
+	size_t left = *lenp;
+	unsigned long bitmap_len = table->maxlen;
+	unsigned long *bitmap = (unsigned long *) table->data;
+	unsigned long *tmp_bitmap = NULL;
+	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
+
+	if (!bitmap_len || !left || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (write) {
+		unsigned long page = 0;
+		char *kbuf;
+
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+
+		page = __get_free_page(GFP_TEMPORARY);
+		kbuf = (char *) page;
+		if (!kbuf)
+			return -ENOMEM;
+		if (copy_from_user(kbuf, buffer, left)) {
+			free_page(page);
+			return -EFAULT;
+                }
+		kbuf[left] = 0;
+
+		tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long),
+				     GFP_KERNEL);
+		if (!tmp_bitmap) {
+			free_page(page);
+			return -ENOMEM;
+		}
+		proc_skip_char(&kbuf, &left, '\n');
+		while (!err && left) {
+			unsigned long val_a, val_b;
+			bool neg;
+
+			err = proc_get_long(&kbuf, &left, &val_a, &neg, tr_a,
+					     sizeof(tr_a), &c);
+			if (err)
+				break;
+			if (val_a >= bitmap_len || neg) {
+				err = -EINVAL;
+				break;
+			}
+
+			val_b = val_a;
+			if (left) {
+				kbuf++;
+				left--;
+			}
+
+			if (c == '-') {
+				err = proc_get_long(&kbuf, &left, &val_b,
+						     &neg, tr_b, sizeof(tr_b),
+						     &c);
+				if (err)
+					break;
+				if (val_b >= bitmap_len || neg ||
+				    val_a > val_b) {
+					err = -EINVAL;
+					break;
+				}
+				if (left) {
+					kbuf++;
+					left--;
+				}
+			}
+
+			while (val_a <= val_b)
+				set_bit(val_a++, tmp_bitmap);
+
+			first = 0;
+			proc_skip_char(&kbuf, &left, '\n');
+		}
+		free_page(page);
+	} else {
+		unsigned long bit_a, bit_b = 0;
+
+		while (left) {
+			bit_a = find_next_bit(bitmap, bitmap_len, bit_b);
+			if (bit_a >= bitmap_len)
+				break;
+			bit_b = find_next_zero_bit(bitmap, bitmap_len,
+						   bit_a + 1) - 1;
+
+			if (!first) {
+				err = proc_put_char(&buffer, &left, ',');
+				if (err)
+					break;
+			}
+			err = proc_put_long(&buffer, &left, bit_a, false);
+			if (err)
+				break;
+			if (bit_a != bit_b) {
+				err = proc_put_char(&buffer, &left, '-');
+				if (err)
+					break;
+				err = proc_put_long(&buffer, &left, bit_b, false);
+				if (err)
+					break;
+			}
+
+			first = 0; bit_b++;
+		}
+		if (!err)
+			err = proc_put_char(&buffer, &left, '\n');
+	}
+
+	if (!err) {
+		if (write) {
+			if (*ppos)
+				bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
+			else
+				memcpy(bitmap, tmp_bitmap,
+					BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long));
+		}
+		kfree(tmp_bitmap);
+		*lenp -= left;
+		*ppos += *lenp;
+		return 0;
+	} else {
+		kfree(tmp_bitmap);
+		return err;
+	}
+}
+
 #else /* CONFIG_PROC_FS */
 
 int proc_dostring(struct ctl_table *table, int write,
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 59030570f5c..937d31dc856 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -224,7 +224,6 @@ static const struct bin_table bin_net_ipv4_route_table[] = {
 	{ CTL_INT,	NET_IPV4_ROUTE_MTU_EXPIRES,		"mtu_expires" },
 	{ CTL_INT,	NET_IPV4_ROUTE_MIN_PMTU,		"min_pmtu" },
 	{ CTL_INT,	NET_IPV4_ROUTE_MIN_ADVMSS,		"min_adv_mss" },
-	{ CTL_INT,	NET_IPV4_ROUTE_SECRET_INTERVAL,		"secret_interval" },
 	{}
 };
 
diff --git a/kernel/time.c b/kernel/time.c
index 656dccfe1cb..50612faa9ba 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -132,12 +132,11 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
  */
 static inline void warp_clock(void)
 {
-	write_seqlock_irq(&xtime_lock);
-	wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
-	xtime.tv_sec += sys_tz.tz_minuteswest * 60;
-	update_xtime_cache(0);
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
+	struct timespec delta, adjust;
+	delta.tv_sec = sys_tz.tz_minuteswest * 60;
+	delta.tv_nsec = 0;
+	adjust = timespec_add_safe(current_kernel_time(), delta);
+	do_settimeofday(&adjust);
 }
 
 /*
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1f5dde63745..f08e99c1d56 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -625,6 +625,54 @@ static void clocksource_enqueue(struct clocksource *cs)
 	list_add(&cs->list, entry);
 }
 
+
+/*
+ * Maximum time we expect to go between ticks. This includes idle
+ * tickless time. It provides the trade off between selecting a
+ * mult/shift pair that is very precise but can only handle a short
+ * period of time, vs. a mult/shift pair that can handle long periods
+ * of time but isn't as precise.
+ *
+ * This is a subsystem constant, and actual hardware limitations
+ * may override it (ie: clocksources that wrap every 3 seconds).
+ */
+#define MAX_UPDATE_LENGTH 5 /* Seconds */
+
+/**
+ * __clocksource_register_scale - Used to install new clocksources
+ * @t:		clocksource to be registered
+ * @scale:	Scale factor multiplied against freq to get clocksource hz
+ * @freq:	clocksource frequency (cycles per second) divided by scale
+ *
+ * Returns -EBUSY if registration fails, zero otherwise.
+ *
+ * This *SHOULD NOT* be called directly! Please use the
+ * clocksource_register_hz() or clocksource_register_khz helper functions.
+ */
+int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
+{
+
+	/*
+	 * Ideally we want to use  some of the limits used in
+	 * clocksource_max_deferment, to provide a more informed
+	 * MAX_UPDATE_LENGTH. But for now this just gets the
+	 * register interface working properly.
+	 */
+	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
+				      NSEC_PER_SEC/scale,
+				      MAX_UPDATE_LENGTH*scale);
+	cs->max_idle_ns = clocksource_max_deferment(cs);
+
+	mutex_lock(&clocksource_mutex);
+	clocksource_enqueue(cs);
+	clocksource_select();
+	clocksource_enqueue_watchdog(cs);
+	mutex_unlock(&clocksource_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__clocksource_register_scale);
+
+
 /**
  * clocksource_register - Used to install new clocksources
  * @t:		clocksource to be registered
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7c0f180d6e9..c63116863a8 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -69,7 +69,7 @@ static s64			time_freq;
 /* time at last adjustment (secs):					*/
 static long			time_reftime;
 
-long				time_adjust;
+static long			time_adjust;
 
 /* constant (boot-param configurable) NTP tick adjustment (upscaled)	*/
 static s64			ntp_tick_adj;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f992762d7f5..1d7b9bc1c03 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,14 +150,32 @@ static void tick_nohz_update_jiffies(ktime_t now)
 	touch_softlockup_watchdog();
 }
 
+/*
+ * Updates the per cpu time idle statistics counters
+ */
+static void
+update_ts_time_stats(struct tick_sched *ts, ktime_t now, u64 *last_update_time)
+{
+	ktime_t delta;
+
+	if (ts->idle_active) {
+		delta = ktime_sub(now, ts->idle_entrytime);
+		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+		if (nr_iowait_cpu() > 0)
+			ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+		ts->idle_entrytime = now;
+	}
+
+	if (last_update_time)
+		*last_update_time = ktime_to_us(now);
+
+}
+
 static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-	ktime_t delta;
 
-	delta = ktime_sub(now, ts->idle_entrytime);
-	ts->idle_lastupdate = now;
-	ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	update_ts_time_stats(ts, now, NULL);
 	ts->idle_active = 0;
 
 	sched_clock_idle_wakeup_event(0);
@@ -165,20 +183,32 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now)
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
-	ktime_t now, delta;
+	ktime_t now;
 
 	now = ktime_get();
-	if (ts->idle_active) {
-		delta = ktime_sub(now, ts->idle_entrytime);
-		ts->idle_lastupdate = now;
-		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-	}
+
+	update_ts_time_stats(ts, now, NULL);
+
 	ts->idle_entrytime = now;
 	ts->idle_active = 1;
 	sched_clock_idle_sleep_event();
 	return now;
 }
 
+/**
+ * get_cpu_idle_time_us - get the total idle time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds. The idle time returned includes
+ * the iowait time (unlike what "top" and co report).
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -186,15 +216,38 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 	if (!tick_nohz_enabled)
 		return -1;
 
-	if (ts->idle_active)
-		*last_update_time = ktime_to_us(ts->idle_lastupdate);
-	else
-		*last_update_time = ktime_to_us(ktime_get());
+	update_ts_time_stats(ts, ktime_get(), last_update_time);
 
 	return ktime_to_us(ts->idle_sleeptime);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
+/*
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (!tick_nohz_enabled)
+		return -1;
+
+	update_ts_time_stats(ts, ktime_get(), last_update_time);
+
+	return ktime_to_us(ts->iowait_sleeptime);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
 /**
  * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
  *
@@ -262,6 +315,9 @@ void tick_nohz_stop_sched_tick(int inidle)
 		goto end;
 	}
 
+	if (nohz_ratelimit(cpu))
+		goto end;
+
 	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 39f6177fafa..caf8d4d4f5c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -165,13 +165,6 @@ struct timespec raw_time;
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
-	xtime_cache = xtime;
-	timespec_add_ns(&xtime_cache, nsec);
-}
-
 /* must hold xtime_lock */
 void timekeeping_leap_insert(int leapsecond)
 {
@@ -332,8 +325,6 @@ int do_settimeofday(struct timespec *tv)
 
 	xtime = *tv;
 
-	update_xtime_cache(0);
-
 	timekeeper.ntp_error = 0;
 	ntp_clear();
 
@@ -559,7 +550,6 @@ void __init timekeeping_init(void)
 	}
 	set_normalized_timespec(&wall_to_monotonic,
 				-boot.tv_sec, -boot.tv_nsec);
-	update_xtime_cache(0);
 	total_sleep_time.tv_sec = 0;
 	total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -593,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev)
 		wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
 		total_sleep_time = timespec_add_safe(total_sleep_time, ts);
 	}
-	update_xtime_cache(0);
 	/* re-base the last cycle value */
 	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
 	timekeeper.ntp_error = 0;
@@ -788,7 +777,6 @@ void update_wall_time(void)
 {
 	struct clocksource *clock;
 	cycle_t offset;
-	u64 nsecs;
 	int shift = 0, maxshift;
 
 	/* Make sure we're fully resumed: */
@@ -847,7 +835,9 @@ void update_wall_time(void)
 		timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
 	}
 
-	/* store full nanoseconds into xtime after rounding it up and
+
+	/*
+	 * Store full nanoseconds into xtime after rounding it up and
 	 * add the remainder to the error difference.
 	 */
 	xtime.tv_nsec =	((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
@@ -855,8 +845,15 @@ void update_wall_time(void)
 	timekeeper.ntp_error +=	timekeeper.xtime_nsec <<
 				timekeeper.ntp_error_shift;
 
-	nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
-	update_xtime_cache(nsecs);
+	/*
+	 * Finally, make sure that after the rounding
+	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+	 */
+	if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
+		xtime.tv_nsec -= NSEC_PER_SEC;
+		xtime.tv_sec++;
+		second_overflow();
+	}
 
 	/* check to see if there is a new clocksource to use */
 	update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
@@ -896,13 +893,13 @@ EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
 
 unsigned long get_seconds(void)
 {
-	return xtime_cache.tv_sec;
+	return xtime.tv_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-	return xtime_cache;
+	return xtime;
 }
 
 struct timespec current_kernel_time(void)
@@ -913,7 +910,7 @@ struct timespec current_kernel_time(void)
 	do {
 		seq = read_seqbegin(&xtime_lock);
 
-		now = xtime_cache;
+		now = xtime;
 	} while (read_seqretry(&xtime_lock, seq));
 
 	return now;
@@ -928,7 +925,7 @@ struct timespec get_monotonic_coarse(void)
 	do {
 		seq = read_seqbegin(&xtime_lock);
 
-		now = xtime_cache;
+		now = xtime;
 		mono = wall_to_monotonic;
 	} while (read_seqretry(&xtime_lock, seq));
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1a4a7dd7877..ab8f5e33fa9 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -176,6 +176,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 		P_ns(idle_waketime);
 		P_ns(idle_exittime);
 		P_ns(idle_sleeptime);
+		P_ns(iowait_sleeptime);
 		P(last_jiffies);
 		P(next_jiffies);
 		P_ns(idle_expires);
diff --git a/kernel/timer.c b/kernel/timer.c
index aeb6a54f277..9199f3c5221 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -319,6 +319,24 @@ unsigned long round_jiffies_up_relative(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
 
+/**
+ * set_timer_slack - set the allowed slack for a timer
+ * @slack_hz: the amount of time (in jiffies) allowed for rounding
+ *
+ * Set the amount of time, in jiffies, that a certain timer has
+ * in terms of slack. By setting this value, the timer subsystem
+ * will schedule the actual timer somewhere between
+ * the time mod_timer() asks for, and that time plus the slack.
+ *
+ * By setting the slack to -1, a percentage of the delay is used
+ * instead.
+ */
+void set_timer_slack(struct timer_list *timer, int slack_hz)
+{
+	timer->slack = slack_hz;
+}
+EXPORT_SYMBOL_GPL(set_timer_slack);
+
 
 static inline void set_running_timer(struct tvec_base *base,
 					struct timer_list *timer)
@@ -550,6 +568,7 @@ static void __init_timer(struct timer_list *timer,
 {
 	timer->entry.next = NULL;
 	timer->base = __raw_get_cpu_var(tvec_bases);
+	timer->slack = -1;
 #ifdef CONFIG_TIMER_STATS
 	timer->start_site = NULL;
 	timer->start_pid = -1;
@@ -715,6 +734,41 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 }
 EXPORT_SYMBOL(mod_timer_pending);
 
+/*
+ * Decide where to put the timer while taking the slack into account
+ *
+ * Algorithm:
+ *   1) calculate the maximum (absolute) time
+ *   2) calculate the highest bit where the expires and new max are different
+ *   3) use this bit to make a mask
+ *   4) use the bitmask to round down the maximum time, so that all last
+ *      bits are zeros
+ */
+static inline
+unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
+{
+	unsigned long expires_limit, mask;
+	int bit;
+
+	expires_limit = expires + timer->slack;
+
+	if (timer->slack < 0) /* auto slack: use 0.4% */
+		expires_limit = expires + (expires - jiffies)/256;
+
+	mask = expires ^ expires_limit;
+
+	if (mask == 0)
+		return expires;
+
+	bit = find_last_bit(&mask, BITS_PER_LONG);
+
+	mask = (1 << bit) - 1;
+
+	expires_limit = expires_limit & ~(mask);
+
+	return expires_limit;
+}
+
 /**
  * mod_timer - modify a timer's timeout
  * @timer: the timer to be modified
@@ -745,6 +799,8 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer_pending(timer) && timer->expires == expires)
 		return 1;
 
+	expires = apply_slack(timer, expires);
+
 	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);
@@ -955,6 +1011,47 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 	return index;
 }
 
+static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
+			  unsigned long data)
+{
+	int preempt_count = preempt_count();
+
+#ifdef CONFIG_LOCKDEP
+	/*
+	 * It is permissible to free the timer from inside the
+	 * function that is called from it, this we need to take into
+	 * account for lockdep too. To avoid bogus "held lock freed"
+	 * warnings as well as problems when looking into
+	 * timer->lockdep_map, make a copy and use that here.
+	 */
+	struct lockdep_map lockdep_map = timer->lockdep_map;
+#endif
+	/*
+	 * Couple the lock chain with the lock chain at
+	 * del_timer_sync() by acquiring the lock_map around the fn()
+	 * call here and in del_timer_sync().
+	 */
+	lock_map_acquire(&lockdep_map);
+
+	trace_timer_expire_entry(timer);
+	fn(data);
+	trace_timer_expire_exit(timer);
+
+	lock_map_release(&lockdep_map);
+
+	if (preempt_count != preempt_count()) {
+		WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
+			  fn, preempt_count, preempt_count());
+		/*
+		 * Restore the preempt count. That gives us a decent
+		 * chance to survive and extract information. If the
+		 * callback kept a lock held, bad luck, but not worse
+		 * than the BUG() we had.
+		 */
+		preempt_count() = preempt_count;
+	}
+}
+
 #define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
 
 /**
@@ -998,45 +1095,7 @@ static inline void __run_timers(struct tvec_base *base)
 			detach_timer(timer, 1);
 
 			spin_unlock_irq(&base->lock);
-			{
-				int preempt_count = preempt_count();
-
-#ifdef CONFIG_LOCKDEP
-				/*
-				 * It is permissible to free the timer from
-				 * inside the function that is called from
-				 * it, this we need to take into account for
-				 * lockdep too. To avoid bogus "held lock
-				 * freed" warnings as well as problems when
-				 * looking into timer->lockdep_map, make a
-				 * copy and use that here.
-				 */
-				struct lockdep_map lockdep_map =
-					timer->lockdep_map;
-#endif
-				/*
-				 * Couple the lock chain with the lock chain at
-				 * del_timer_sync() by acquiring the lock_map
-				 * around the fn() call here and in
-				 * del_timer_sync().
-				 */
-				lock_map_acquire(&lockdep_map);
-
-				trace_timer_expire_entry(timer);
-				fn(data);
-				trace_timer_expire_exit(timer);
-
-				lock_map_release(&lockdep_map);
-
-				if (preempt_count != preempt_count()) {
-					printk(KERN_ERR "huh, entered %p "
-					       "with preempt_count %08x, exited"
-					       " with %08x?\n",
-					       fn, preempt_count,
-					       preempt_count());
-					BUG();
-				}
-			}
+			call_timer_fn(timer, fn, data);
 			spin_lock_irq(&base->lock);
 		}
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 13e13d428cd..8b1797c4545 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -44,9 +44,6 @@ config HAVE_FTRACE_MCOUNT_RECORD
 	help
 	  See Documentation/trace/ftrace-design.txt
 
-config HAVE_HW_BRANCH_TRACER
-	bool
-
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
 	help
@@ -374,14 +371,6 @@ config STACK_TRACER
 
 	  Say N if unsure.
 
-config HW_BRANCH_TRACER
-	depends on HAVE_HW_BRANCH_TRACER
-	bool "Trace hw branches"
-	select GENERIC_TRACER
-	help
-	  This tracer records all branches on the system in a circular
-	  buffer, giving access to the last N branches for each cpu.
-
 config KMEMTRACE
 	bool "Trace SLAB allocations"
 	select GENERIC_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 78edc649003..ffb1a5b0550 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -41,7 +41,6 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2404b59b309..32837e19e3b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -264,6 +264,7 @@ struct ftrace_profile {
 	unsigned long			counter;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	unsigned long long		time;
+	unsigned long long		time_squared;
 #endif
 };
 
@@ -366,9 +367,9 @@ static int function_stat_headers(struct seq_file *m)
 {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	seq_printf(m, "  Function                               "
-		   "Hit    Time            Avg\n"
+		   "Hit    Time            Avg             s^2\n"
 		      "  --------                               "
-		   "---    ----            ---\n");
+		   "---    ----            ---             ---\n");
 #else
 	seq_printf(m, "  Function                               Hit\n"
 		      "  --------                               ---\n");
@@ -384,6 +385,7 @@ static int function_stat_show(struct seq_file *m, void *v)
 	static DEFINE_MUTEX(mutex);
 	static struct trace_seq s;
 	unsigned long long avg;
+	unsigned long long stddev;
 #endif
 
 	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -394,11 +396,25 @@ static int function_stat_show(struct seq_file *m, void *v)
 	avg = rec->time;
 	do_div(avg, rec->counter);
 
+	/* Sample standard deviation (s^2) */
+	if (rec->counter <= 1)
+		stddev = 0;
+	else {
+		stddev = rec->time_squared - rec->counter * avg * avg;
+		/*
+		 * Divide only 1000 for ns^2 -> us^2 conversion.
+		 * trace_print_graph_duration will divide 1000 again.
+		 */
+		do_div(stddev, (rec->counter - 1) * 1000);
+	}
+
 	mutex_lock(&mutex);
 	trace_seq_init(&s);
 	trace_print_graph_duration(rec->time, &s);
 	trace_seq_puts(&s, "    ");
 	trace_print_graph_duration(avg, &s);
+	trace_seq_puts(&s, "    ");
+	trace_print_graph_duration(stddev, &s);
 	trace_print_seq(m, &s);
 	mutex_unlock(&mutex);
 #endif
@@ -650,6 +666,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
+	/* If the calltime was zero'd ignore it */
+	if (!trace->calltime)
+		goto out;
+
 	calltime = trace->rettime - trace->calltime;
 
 	if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
@@ -668,8 +688,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 	}
 
 	rec = ftrace_find_profiled_func(stat, trace->func);
-	if (rec)
+	if (rec) {
 		rec->time += calltime;
+		rec->time_squared += calltime * calltime;
+	}
 
  out:
 	local_irq_restore(flags);
@@ -3212,8 +3234,7 @@ free:
 }
 
 static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-				struct task_struct *next)
+ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next)
 {
 	unsigned long long timestamp;
 	int index;
@@ -3339,11 +3360,11 @@ void unregister_ftrace_graph(void)
 		goto out;
 
 	ftrace_graph_active--;
-	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 	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);
+	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 
  out:
 	mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41ca394feb2..7f6059c5aa9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -319,6 +319,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST	(~TS_MASK)
 
+/* Flag when events were overwritten */
+#define RB_MISSED_EVENTS	(1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED	(1 << 30)
+
 struct buffer_data_page {
 	u64		 time_stamp;	/* page time stamp */
 	local_t		 commit;	/* write committed index */
@@ -338,6 +343,7 @@ struct buffer_page {
 	local_t		 write;		/* index for next write */
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
+	unsigned long	 real_end;	/* real end of data */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -417,6 +423,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 			       (unsigned int)sizeof(field.commit),
 			       (unsigned int)is_signed_type(long));
 
+	ret = trace_seq_printf(s, "\tfield: int overwrite;\t"
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			       (unsigned int)offsetof(typeof(field), commit),
+			       1,
+			       (unsigned int)is_signed_type(long));
+
 	ret = trace_seq_printf(s, "\tfield: char data;\t"
 			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			       (unsigned int)offsetof(typeof(field), data),
@@ -440,6 +452,8 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
+	unsigned long			lost_events;
+	unsigned long			last_overrun;
 	local_t				commit_overrun;
 	local_t				overrun;
 	local_t				entries;
@@ -1762,6 +1776,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	kmemcheck_annotate_bitfield(event, bitfield);
 
 	/*
+	 * Save the original length to the meta data.
+	 * This will be used by the reader to add lost event
+	 * counter.
+	 */
+	tail_page->real_end = tail;
+
+	/*
 	 * If this event is bigger than the minimum size, then
 	 * we need to be careful that we don't subtract the
 	 * write counter enough to allow another writer to slip
@@ -1979,17 +2000,13 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		  u64 *ts, u64 *delta)
 {
 	struct ring_buffer_event *event;
-	static int once;
 	int ret;
 
-	if (unlikely(*delta > (1ULL << 59) && !once++)) {
-		printk(KERN_WARNING "Delta way too big! %llu"
-		       " ts=%llu write stamp = %llu\n",
-		       (unsigned long long)*delta,
-		       (unsigned long long)*ts,
-		       (unsigned long long)cpu_buffer->write_stamp);
-		WARN_ON(1);
-	}
+	WARN_ONCE(*delta > (1ULL << 59),
+		  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+		  (unsigned long long)*delta,
+		  (unsigned long long)*ts,
+		  (unsigned long long)cpu_buffer->write_stamp);
 
 	/*
 	 * The delta is too big, we to add a
@@ -2838,6 +2855,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
 	int ret;
@@ -2879,6 +2897,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->write, 0);
 	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
+	cpu_buffer->reader_page->real_end = 0;
 
  spin:
 	/*
@@ -2899,6 +2918,18 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
 	/*
+	 * We want to make sure we read the overruns after we set up our
+	 * pointers to the next object. The writer side does a
+	 * cmpxchg to cross pages which acts as the mb on the writer
+	 * side. Note, the reader will constantly fail the swap
+	 * while the writer is updating the pointers, so this
+	 * guarantees that the overwrite recorded here is the one we
+	 * want to compare with the last_overrun.
+	 */
+	smp_mb();
+	overwrite = local_read(&(cpu_buffer->overrun));
+
+	/*
 	 * Here's the tricky part.
 	 *
 	 * We need to move the pointer past the header page.
@@ -2929,6 +2960,11 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page = reader;
 	rb_reset_reader_page(cpu_buffer);
 
+	if (overwrite != cpu_buffer->last_overrun) {
+		cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
+		cpu_buffer->last_overrun = overwrite;
+	}
+
 	goto again;
 
  out:
@@ -3005,8 +3041,14 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 		rb_advance_iter(iter);
 }
 
+static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return cpu_buffer->lost_events;
+}
+
 static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+	       unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct buffer_page *reader;
@@ -3058,6 +3100,8 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
+		if (lost_events)
+			*lost_events = rb_lost_events(cpu_buffer);
 		return event;
 
 	default:
@@ -3168,12 +3212,14 @@ static inline int rb_ok_to_lock(void)
  * @buffer: The ring buffer to read
  * @cpu: The cpu to peak at
  * @ts: The timestamp counter of this event.
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * This will return the event that will be read next, but does
  * not consume the data.
  */
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -3188,7 +3234,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	local_irq_save(flags);
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
-	event = rb_buffer_peek(cpu_buffer, ts);
+	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		rb_advance_reader(cpu_buffer);
 	if (dolock)
@@ -3230,13 +3276,17 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 /**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
+ * @cpu: the cpu to read the buffer from
+ * @ts: a variable to store the timestamp (may be NULL)
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * Returns the next event in the ring buffer, and that event is consumed.
  * Meaning, that sequential reads will keep returning a different event,
  * and eventually empty the ring buffer if the producer is slower.
  */
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event = NULL;
@@ -3257,9 +3307,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
 
-	event = rb_buffer_peek(cpu_buffer, ts);
-	if (event)
+	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+	if (event) {
+		cpu_buffer->lost_events = 0;
 		rb_advance_reader(cpu_buffer);
+	}
 
 	if (dolock)
 		spin_unlock(&cpu_buffer->reader_lock);
@@ -3276,23 +3328,30 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
 
 /**
- * ring_buffer_read_start - start a non consuming read of the buffer
+ * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
  * @buffer: The ring buffer to read from
  * @cpu: The cpu buffer to iterate over
  *
- * This starts up an iteration through the buffer. It also disables
- * the recording to the buffer until the reading is finished.
- * This prevents the reading from being corrupted. This is not
- * a consuming read, so a producer is not expected.
+ * This performs the initial preparations necessary to iterate
+ * through the buffer.  Memory is allocated, buffer recording
+ * is disabled, and the iterator pointer is returned to the caller.
  *
- * Must be paired with ring_buffer_finish.
+ * Disabling buffer recordng prevents the reading from being
+ * corrupted. This is not a consuming read, so a producer is not
+ * expected.
+ *
+ * After a sequence of ring_buffer_read_prepare calls, the user is
+ * expected to make at least one call to ring_buffer_prepare_sync.
+ * Afterwards, ring_buffer_read_start is invoked to get things going
+ * for real.
+ *
+ * This overall must be paired with ring_buffer_finish.
  */
 struct ring_buffer_iter *
-ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_iter *iter;
-	unsigned long flags;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
@@ -3306,15 +3365,52 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 	iter->cpu_buffer = cpu_buffer;
 
 	atomic_inc(&cpu_buffer->record_disabled);
+
+	return iter;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
+
+/**
+ * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
+ *
+ * All previously invoked ring_buffer_read_prepare calls to prepare
+ * iterators will be synchronized.  Afterwards, read_buffer_read_start
+ * calls on those iterators are allowed.
+ */
+void
+ring_buffer_read_prepare_sync(void)
+{
 	synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @iter: The iterator returned by ring_buffer_read_prepare
+ *
+ * This finalizes the startup of an iteration through the buffer.
+ * The iterator comes from a call to ring_buffer_read_prepare and
+ * an intervening ring_buffer_read_prepare_sync must have been
+ * performed.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+void
+ring_buffer_read_start(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long flags;
+
+	if (!iter)
+		return;
+
+	cpu_buffer = iter->cpu_buffer;
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	arch_spin_lock(&cpu_buffer->lock);
 	rb_iter_reset(iter);
 	arch_spin_unlock(&cpu_buffer->lock);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-
-	return iter;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
@@ -3408,6 +3504,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
 
+	cpu_buffer->lost_events = 0;
+	cpu_buffer->last_overrun = 0;
+
 	rb_head_page_activate(cpu_buffer);
 }
 
@@ -3683,6 +3782,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
 	struct buffer_page *reader;
+	unsigned long missed_events;
 	unsigned long flags;
 	unsigned int commit;
 	unsigned int read;
@@ -3719,6 +3819,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	read = reader->read;
 	commit = rb_page_commit(reader);
 
+	/* Check if any events were dropped */
+	missed_events = cpu_buffer->lost_events;
+
 	/*
 	 * If this page has been partially read or
 	 * if len is not big enough to read the rest of the page or
@@ -3779,9 +3882,35 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		local_set(&reader->entries, 0);
 		reader->read = 0;
 		*data_page = bpage;
+
+		/*
+		 * Use the real_end for the data size,
+		 * This gives us a chance to store the lost events
+		 * on the page.
+		 */
+		if (reader->real_end)
+			local_set(&bpage->commit, reader->real_end);
 	}
 	ret = read;
 
+	cpu_buffer->lost_events = 0;
+	/*
+	 * Set a flag in the commit field if we lost events
+	 */
+	if (missed_events) {
+		commit = local_read(&bpage->commit);
+
+		/* If there is room at the end of the page to save the
+		 * missed events, then record it there.
+		 */
+		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+			memcpy(&bpage->data[commit], &missed_events,
+			       sizeof(missed_events));
+			local_add(RB_MISSED_STORED, &bpage->commit);
+		}
+		local_add(RB_MISSED_EVENTS, &bpage->commit);
+	}
+
  out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index df74c798225..302f8a61463 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -81,7 +81,7 @@ static enum event_status read_event(int cpu)
 	int *entry;
 	u64 ts;
 
-	event = ring_buffer_consume(buffer, cpu, &ts);
+	event = ring_buffer_consume(buffer, cpu, &ts, NULL);
 	if (!event)
 		return EVENT_DROPPED;
 
@@ -113,7 +113,8 @@ static enum event_status read_page(int cpu)
 	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
 	if (ret >= 0) {
 		rpage = bpage;
-		commit = local_read(&rpage->commit);
+		/* The commit may have missed event flags set, clear them */
+		commit = local_read(&rpage->commit) & 0xfffff;
 		for (i = 0; i < commit && !kill_test; i += inc) {
 
 			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7b155a0e6f3..8a76339a9e6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -117,9 +117,12 @@ static cpumask_var_t __read_mostly	tracing_buffer_mask;
  *
  * It is default off, but you can enable it with either specifying
  * "ftrace_dump_on_oops" in the kernel command line, or setting
- * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ * /proc/sys/kernel/ftrace_dump_on_oops
+ * Set 1 if you want to dump buffers of all CPUs
+ * Set 2 if you want to dump the buffer of the CPU that triggered oops
  */
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
 
 static int tracing_set_tracer(const char *buf);
 
@@ -139,8 +142,17 @@ __setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {
-	ftrace_dump_on_oops = 1;
-	return 1;
+	if (*str++ != '=' || !*str) {
+		ftrace_dump_on_oops = DUMP_ALL;
+		return 1;
+	}
+
+	if (!strcmp("orig_cpu", str)) {
+		ftrace_dump_on_oops = DUMP_ORIG;
+                return 1;
+        }
+
+        return 0;
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
@@ -1545,7 +1557,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+		unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1556,7 +1569,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+					 lost_events);
 
 	ftrace_enable_cpu();
 
@@ -1564,10 +1578,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+		  unsigned long *missing_events, u64 *ent_ts)
 {
 	struct ring_buffer *buffer = iter->tr->buffer;
 	struct trace_entry *ent, *next = NULL;
+	unsigned long lost_events = 0, next_lost = 0;
 	int cpu_file = iter->cpu_file;
 	u64 next_ts = 0, ts;
 	int next_cpu = -1;
@@ -1580,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (cpu_file > TRACE_PIPE_ALL_CPU) {
 		if (ring_buffer_empty_cpu(buffer, cpu_file))
 			return NULL;
-		ent = peek_next_entry(iter, cpu_file, ent_ts);
+		ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
 		if (ent_cpu)
 			*ent_cpu = cpu_file;
 
@@ -1592,7 +1608,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 		if (ring_buffer_empty_cpu(buffer, cpu))
 			continue;
 
-		ent = peek_next_entry(iter, cpu, &ts);
+		ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
 		/*
 		 * Pick the entry with the smallest timestamp:
@@ -1601,6 +1617,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 			next = ent;
 			next_cpu = cpu;
 			next_ts = ts;
+			next_lost = lost_events;
 		}
 	}
 
@@ -1610,6 +1627,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (ent_ts)
 		*ent_ts = next_ts;
 
+	if (missing_events)
+		*missing_events = next_lost;
+
 	return next;
 }
 
@@ -1617,13 +1637,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, ent_ts);
+	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-	iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+	iter->ent = __find_next_entry(iter, &iter->cpu,
+				      &iter->lost_events, &iter->ts);
 
 	if (iter->ent)
 		trace_iterator_increment(iter);
@@ -1635,7 +1656,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+			    &iter->lost_events);
 	ftrace_enable_cpu();
 }
 
@@ -1786,7 +1808,7 @@ static void print_func_help_header(struct seq_file *m)
 }
 
 
-static void
+void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
 	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1995,7 +2017,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 	return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
 }
 
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
 {
 	int cpu;
 
@@ -2030,6 +2052,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
+	if (iter->lost_events)
+		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events);
+
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
 		if (ret != TRACE_TYPE_UNHANDLED)
@@ -2058,6 +2084,23 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 	return print_trace_fmt(iter);
 }
 
+void trace_default_header(struct seq_file *m)
+{
+	struct trace_iterator *iter = m->private;
+
+	if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+		/* print nothing if the buffers are empty */
+		if (trace_empty(iter))
+			return;
+		print_trace_header(m, iter);
+		if (!(trace_flags & TRACE_ITER_VERBOSE))
+			print_lat_help_header(m);
+	} else {
+		if (!(trace_flags & TRACE_ITER_VERBOSE))
+			print_func_help_header(m);
+	}
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2070,17 +2113,9 @@ static int s_show(struct seq_file *m, void *v)
 		}
 		if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
-		else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
-			/* print nothing if the buffers are empty */
-			if (trace_empty(iter))
-				return 0;
-			print_trace_header(m, iter);
-			if (!(trace_flags & TRACE_ITER_VERBOSE))
-				print_lat_help_header(m);
-		} else {
-			if (!(trace_flags & TRACE_ITER_VERBOSE))
-				print_func_help_header(m);
-		}
+		else
+			trace_default_header(m);
+
 	} else if (iter->leftover) {
 		/*
 		 * If we filled the seq_file buffer earlier, we
@@ -2166,15 +2201,20 @@ __tracing_open(struct inode *inode, struct file *file)
 
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
-
 			iter->buffer_iter[cpu] =
-				ring_buffer_read_start(iter->tr->buffer, cpu);
+				ring_buffer_read_prepare(iter->tr->buffer, cpu);
+		}
+		ring_buffer_read_prepare_sync();
+		for_each_tracing_cpu(cpu) {
+			ring_buffer_read_start(iter->buffer_iter[cpu]);
 			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
-				ring_buffer_read_start(iter->tr->buffer, cpu);
+			ring_buffer_read_prepare(iter->tr->buffer, cpu);
+		ring_buffer_read_prepare_sync();
+		ring_buffer_read_start(iter->buffer_iter[cpu]);
 		tracing_iter_reset(iter, cpu);
 	}
 
@@ -4336,7 +4376,7 @@ static int trace_panic_handler(struct notifier_block *this,
 			       unsigned long event, void *unused)
 {
 	if (ftrace_dump_on_oops)
-		ftrace_dump();
+		ftrace_dump(ftrace_dump_on_oops);
 	return NOTIFY_OK;
 }
 
@@ -4353,7 +4393,7 @@ static int trace_die_handler(struct notifier_block *self,
 	switch (val) {
 	case DIE_OOPS:
 		if (ftrace_dump_on_oops)
-			ftrace_dump();
+			ftrace_dump(ftrace_dump_on_oops);
 		break;
 	default:
 		break;
@@ -4394,7 +4434,8 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_init(s);
 }
 
-static void __ftrace_dump(bool disable_tracing)
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 {
 	static arch_spinlock_t ftrace_dump_lock =
 		(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -4427,12 +4468,25 @@ static void __ftrace_dump(bool disable_tracing)
 	/* don't look at user memory in panic mode */
 	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-	printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
 	/* Simulate the iterator */
 	iter.tr = &global_trace;
 	iter.trace = current_trace;
-	iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+	switch (oops_dump_mode) {
+	case DUMP_ALL:
+		iter.cpu_file = TRACE_PIPE_ALL_CPU;
+		break;
+	case DUMP_ORIG:
+		iter.cpu_file = raw_smp_processor_id();
+		break;
+	case DUMP_NONE:
+		goto out_enable;
+	default:
+		printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+		iter.cpu_file = TRACE_PIPE_ALL_CPU;
+	}
+
+	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
 	/*
 	 * We need to stop all tracing on all CPUS to read the
@@ -4471,6 +4525,7 @@ static void __ftrace_dump(bool disable_tracing)
 	else
 		printk(KERN_TRACE "---------------------------------\n");
 
+ out_enable:
 	/* Re-enable tracing if requested */
 	if (!disable_tracing) {
 		trace_flags |= old_userobj;
@@ -4487,9 +4542,9 @@ static void __ftrace_dump(bool disable_tracing)
 }
 
 /* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-	__ftrace_dump(true);
+	__ftrace_dump(true, oops_dump_mode);
 }
 
 __init static int tracer_alloc_buffers(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2825ef2c0b1..d1ce0bec1b3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -34,7 +34,6 @@ enum trace_type {
 	TRACE_GRAPH_RET,
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
-	TRACE_HW_BRANCHES,
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
 	TRACE_BLK,
@@ -103,29 +102,17 @@ struct syscall_trace_exit {
 	long			ret;
 };
 
-struct kprobe_trace_entry {
+struct kprobe_trace_entry_head {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			nargs;
-	unsigned long		args[];
 };
 
-#define SIZEOF_KPROBE_TRACE_ENTRY(n)			\
-	(offsetof(struct kprobe_trace_entry, args) +	\
-	(sizeof(unsigned long) * (n)))
-
-struct kretprobe_trace_entry {
+struct kretprobe_trace_entry_head {
 	struct trace_entry	ent;
 	unsigned long		func;
 	unsigned long		ret_ip;
-	int			nargs;
-	unsigned long		args[];
 };
 
-#define SIZEOF_KRETPROBE_TRACE_ENTRY(n)			\
-	(offsetof(struct kretprobe_trace_entry, args) +	\
-	(sizeof(unsigned long) * (n)))
-
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -229,7 +216,6 @@ extern void __ftrace_bad_type(void);
 			  TRACE_GRAPH_ENT);		\
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
-		IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
 		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
@@ -378,6 +364,9 @@ void trace_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
 		    unsigned long flags, int pc);
+void trace_default_header(struct seq_file *m);
+void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
+int trace_empty(struct trace_iterator *iter);
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
@@ -467,8 +456,6 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
-extern int trace_selftest_startup_hw_branches(struct tracer *trace,
-					      struct trace_array *tr);
 extern int trace_selftest_startup_ksym(struct tracer *trace,
 					 struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
@@ -491,9 +478,29 @@ extern int trace_clock_id;
 
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+
+/* Flag options */
+#define TRACE_GRAPH_PRINT_OVERRUN       0x1
+#define TRACE_GRAPH_PRINT_CPU           0x2
+#define TRACE_GRAPH_PRINT_OVERHEAD      0x4
+#define TRACE_GRAPH_PRINT_PROC          0x8
+#define TRACE_GRAPH_PRINT_DURATION      0x10
+#define TRACE_GRAPH_PRINT_ABS_TIME      0x20
+
+extern enum print_line_t
+print_graph_function_flags(struct trace_iterator *iter, u32 flags);
+extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
 extern enum print_line_t
 trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
+extern void graph_trace_open(struct trace_iterator *iter);
+extern void graph_trace_close(struct trace_iterator *iter);
+extern int __trace_graph_entry(struct trace_array *tr,
+			       struct ftrace_graph_ent *trace,
+			       unsigned long flags, int pc);
+extern void __trace_graph_return(struct trace_array *tr,
+				 struct ftrace_graph_ret *trace,
+				 unsigned long flags, int pc);
+
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* TODO: make this variable */
@@ -524,7 +531,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #else /* CONFIG_FUNCTION_GRAPH_TRACER */
 static inline enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
 	return TRACE_TYPE_UNHANDLED;
 }
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c16a08f399d..dc008c1240d 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -318,18 +318,6 @@ FTRACE_ENTRY(branch, trace_branch,
 		 __entry->func, __entry->file, __entry->correct)
 );
 
-FTRACE_ENTRY(hw_branch, hw_branch_entry,
-
-	TRACE_HW_BRANCHES,
-
-	F_STRUCT(
-		__field(	u64,	from	)
-		__field(	u64,	to	)
-	),
-
-	F_printk("from: %llx to: %llx", __entry->from, __entry->to)
-);
-
 FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
 
 	TRACE_KMEM_ALLOC,
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 88c0b6dbd7f..58092d844a1 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1398,7 +1398,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	}
 
 	err = -EINVAL;
-	if (!call)
+	if (&call->list == &ftrace_events)
 		goto out_unlock;
 
 	err = -EEXIST;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9aed1a5cf55..dd11c830eb8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -40,7 +40,7 @@ struct fgraph_data {
 #define TRACE_GRAPH_PRINT_OVERHEAD	0x4
 #define TRACE_GRAPH_PRINT_PROC		0x8
 #define TRACE_GRAPH_PRINT_DURATION	0x10
-#define TRACE_GRAPH_PRINT_ABS_TIME	0X20
+#define TRACE_GRAPH_PRINT_ABS_TIME	0x20
 
 static struct tracer_opt trace_opts[] = {
 	/* Display overruns? (for self-debug purpose) */
@@ -179,7 +179,7 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	return ret;
 }
 
-static int __trace_graph_entry(struct trace_array *tr,
+int __trace_graph_entry(struct trace_array *tr,
 				struct ftrace_graph_ent *trace,
 				unsigned long flags,
 				int pc)
@@ -246,7 +246,7 @@ int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
 		return trace_graph_entry(trace);
 }
 
-static void __trace_graph_return(struct trace_array *tr,
+void __trace_graph_return(struct trace_array *tr,
 				struct ftrace_graph_ret *trace,
 				unsigned long flags,
 				int pc)
@@ -490,9 +490,10 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * We need to consume the current entry to see
 			 * the next one.
 			 */
-			ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+			ring_buffer_consume(iter->tr->buffer, iter->cpu,
+					    NULL, NULL);
 			event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-						 NULL);
+						 NULL, NULL);
 		}
 
 		if (!event)
@@ -526,17 +527,18 @@ get_return_for_leaf(struct trace_iterator *iter,
 
 /* Signal a overhead of time execution to the output */
 static int
-print_graph_overhead(unsigned long long duration, struct trace_seq *s)
+print_graph_overhead(unsigned long long duration, struct trace_seq *s,
+		     u32 flags)
 {
 	/* If duration disappear, we don't need anything */
-	if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION))
+	if (!(flags & TRACE_GRAPH_PRINT_DURATION))
 		return 1;
 
 	/* Non nested entry or return */
 	if (duration == -1)
 		return trace_seq_printf(s, "  ");
 
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+	if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
 		/* Duration exceeded 100 msecs */
 		if (duration > 100000ULL)
 			return trace_seq_printf(s, "! ");
@@ -562,7 +564,7 @@ static int print_graph_abs_time(u64 t, struct trace_seq *s)
 
 static enum print_line_t
 print_graph_irq(struct trace_iterator *iter, unsigned long addr,
-		enum trace_type type, int cpu, pid_t pid)
+		enum trace_type type, int cpu, pid_t pid, u32 flags)
 {
 	int ret;
 	struct trace_seq *s = &iter->seq;
@@ -572,21 +574,21 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		return TRACE_TYPE_UNHANDLED;
 
 	/* Absolute time */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+	if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
 		ret = print_graph_abs_time(iter->ts, s);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	/* Cpu */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+	if (flags & TRACE_GRAPH_PRINT_CPU) {
 		ret = print_graph_cpu(s, cpu);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	/* Proc */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+	if (flags & TRACE_GRAPH_PRINT_PROC) {
 		ret = print_graph_proc(s, pid);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -596,7 +598,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 	}
 
 	/* No overhead */
-	ret = print_graph_overhead(-1, s);
+	ret = print_graph_overhead(-1, s, flags);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -609,7 +611,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Don't close the duration column if haven't one */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		trace_seq_printf(s, " |");
 	ret = trace_seq_printf(s, "\n");
 
@@ -679,7 +681,8 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
 static enum print_line_t
 print_graph_entry_leaf(struct trace_iterator *iter,
 		struct ftrace_graph_ent_entry *entry,
-		struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
+		struct ftrace_graph_ret_entry *ret_entry,
+		struct trace_seq *s, u32 flags)
 {
 	struct fgraph_data *data = iter->private;
 	struct ftrace_graph_ret *graph_ret;
@@ -711,12 +714,12 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	}
 
 	/* Overhead */
-	ret = print_graph_overhead(duration, s);
+	ret = print_graph_overhead(duration, s, flags);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Duration */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+	if (flags & TRACE_GRAPH_PRINT_DURATION) {
 		ret = print_graph_duration(duration, s);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -739,7 +742,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 static enum print_line_t
 print_graph_entry_nested(struct trace_iterator *iter,
 			 struct ftrace_graph_ent_entry *entry,
-			 struct trace_seq *s, int cpu)
+			 struct trace_seq *s, int cpu, u32 flags)
 {
 	struct ftrace_graph_ent *call = &entry->graph_ent;
 	struct fgraph_data *data = iter->private;
@@ -759,12 +762,12 @@ print_graph_entry_nested(struct trace_iterator *iter,
 	}
 
 	/* No overhead */
-	ret = print_graph_overhead(-1, s);
+	ret = print_graph_overhead(-1, s, flags);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* No time */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+	if (flags & TRACE_GRAPH_PRINT_DURATION) {
 		ret = trace_seq_printf(s, "            |  ");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -790,7 +793,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 
 static enum print_line_t
 print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
-		     int type, unsigned long addr)
+		     int type, unsigned long addr, u32 flags)
 {
 	struct fgraph_data *data = iter->private;
 	struct trace_entry *ent = iter->ent;
@@ -803,27 +806,27 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 
 	if (type) {
 		/* Interrupt */
-		ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
+		ret = print_graph_irq(iter, addr, type, cpu, ent->pid, flags);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	/* Absolute time */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+	if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
 		ret = print_graph_abs_time(iter->ts, s);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	/* Cpu */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+	if (flags & TRACE_GRAPH_PRINT_CPU) {
 		ret = print_graph_cpu(s, cpu);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	/* Proc */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+	if (flags & TRACE_GRAPH_PRINT_PROC) {
 		ret = print_graph_proc(s, ent->pid);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -845,7 +848,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 
 static enum print_line_t
 print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
-			struct trace_iterator *iter)
+			struct trace_iterator *iter, u32 flags)
 {
 	struct fgraph_data *data = iter->private;
 	struct ftrace_graph_ent *call = &field->graph_ent;
@@ -853,14 +856,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 	static enum print_line_t ret;
 	int cpu = iter->cpu;
 
-	if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
+	if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	leaf_ret = get_return_for_leaf(iter, field);
 	if (leaf_ret)
-		ret = print_graph_entry_leaf(iter, field, leaf_ret, s);
+		ret = print_graph_entry_leaf(iter, field, leaf_ret, s, flags);
 	else
-		ret = print_graph_entry_nested(iter, field, s, cpu);
+		ret = print_graph_entry_nested(iter, field, s, cpu, flags);
 
 	if (data) {
 		/*
@@ -879,7 +882,8 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 
 static enum print_line_t
 print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
-		   struct trace_entry *ent, struct trace_iterator *iter)
+		   struct trace_entry *ent, struct trace_iterator *iter,
+		   u32 flags)
 {
 	unsigned long long duration = trace->rettime - trace->calltime;
 	struct fgraph_data *data = iter->private;
@@ -909,16 +913,16 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 		}
 	}
 
-	if (print_graph_prologue(iter, s, 0, 0))
+	if (print_graph_prologue(iter, s, 0, 0, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Overhead */
-	ret = print_graph_overhead(duration, s);
+	ret = print_graph_overhead(duration, s, flags);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Duration */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+	if (flags & TRACE_GRAPH_PRINT_DURATION) {
 		ret = print_graph_duration(duration, s);
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -948,14 +952,15 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	}
 
 	/* Overrun */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+	if (flags & TRACE_GRAPH_PRINT_OVERRUN) {
 		ret = trace_seq_printf(s, " (Overruns: %lu)\n",
 					trace->overrun);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid);
+	ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET,
+			      cpu, pid, flags);
 	if (ret == TRACE_TYPE_PARTIAL_LINE)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -963,8 +968,8 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 }
 
 static enum print_line_t
-print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
-		    struct trace_iterator *iter)
+print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
+		    struct trace_iterator *iter, u32 flags)
 {
 	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
 	struct fgraph_data *data = iter->private;
@@ -976,16 +981,16 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
 	if (data)
 		depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
 
-	if (print_graph_prologue(iter, s, 0, 0))
+	if (print_graph_prologue(iter, s, 0, 0, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* No overhead */
-	ret = print_graph_overhead(-1, s);
+	ret = print_graph_overhead(-1, s, flags);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* No time */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+	if (flags & TRACE_GRAPH_PRINT_DURATION) {
 		ret = trace_seq_printf(s, "            |  ");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -1040,7 +1045,7 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
 
 
 enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
 	struct ftrace_graph_ent_entry *field;
 	struct fgraph_data *data = iter->private;
@@ -1061,7 +1066,7 @@ print_graph_function(struct trace_iterator *iter)
 	if (data && data->failed) {
 		field = &data->ent;
 		iter->cpu = data->cpu;
-		ret = print_graph_entry(field, s, iter);
+		ret = print_graph_entry(field, s, iter, flags);
 		if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
 			per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
 			ret = TRACE_TYPE_NO_CONSUME;
@@ -1081,32 +1086,49 @@ print_graph_function(struct trace_iterator *iter)
 		struct ftrace_graph_ent_entry saved;
 		trace_assign_type(field, entry);
 		saved = *field;
-		return print_graph_entry(&saved, s, iter);
+		return print_graph_entry(&saved, s, iter, flags);
 	}
 	case TRACE_GRAPH_RET: {
 		struct ftrace_graph_ret_entry *field;
 		trace_assign_type(field, entry);
-		return print_graph_return(&field->ret, s, entry, iter);
+		return print_graph_return(&field->ret, s, entry, iter, flags);
 	}
+	case TRACE_STACK:
+	case TRACE_FN:
+		/* dont trace stack and functions as comments */
+		return TRACE_TYPE_UNHANDLED;
+
 	default:
-		return print_graph_comment(s, entry, iter);
+		return print_graph_comment(s, entry, iter, flags);
 	}
 
 	return TRACE_TYPE_HANDLED;
 }
 
-static void print_lat_header(struct seq_file *s)
+static enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+	return print_graph_function_flags(iter, tracer_flags.val);
+}
+
+static enum print_line_t
+print_graph_function_event(struct trace_iterator *iter, int flags)
+{
+	return print_graph_function(iter);
+}
+
+static void print_lat_header(struct seq_file *s, u32 flags)
 {
 	static const char spaces[] = "                "	/* 16 spaces */
 		"    "					/* 4 spaces */
 		"                 ";			/* 17 spaces */
 	int size = 0;
 
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+	if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
 		size += 16;
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+	if (flags & TRACE_GRAPH_PRINT_CPU)
 		size += 4;
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+	if (flags & TRACE_GRAPH_PRINT_PROC)
 		size += 17;
 
 	seq_printf(s, "#%.*s  _-----=> irqs-off        \n", size, spaces);
@@ -1117,43 +1139,48 @@ static void print_lat_header(struct seq_file *s)
 	seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
 }
 
-static void print_graph_headers(struct seq_file *s)
+void print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
 	int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
 
 	if (lat)
-		print_lat_header(s);
+		print_lat_header(s, flags);
 
 	/* 1st line */
 	seq_printf(s, "#");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+	if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
 		seq_printf(s, "     TIME       ");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+	if (flags & TRACE_GRAPH_PRINT_CPU)
 		seq_printf(s, " CPU");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+	if (flags & TRACE_GRAPH_PRINT_PROC)
 		seq_printf(s, "  TASK/PID       ");
 	if (lat)
 		seq_printf(s, "|||||");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		seq_printf(s, "  DURATION   ");
 	seq_printf(s, "               FUNCTION CALLS\n");
 
 	/* 2nd line */
 	seq_printf(s, "#");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+	if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
 		seq_printf(s, "      |         ");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+	if (flags & TRACE_GRAPH_PRINT_CPU)
 		seq_printf(s, " |  ");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+	if (flags & TRACE_GRAPH_PRINT_PROC)
 		seq_printf(s, "   |    |        ");
 	if (lat)
 		seq_printf(s, "|||||");
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		seq_printf(s, "   |   |      ");
 	seq_printf(s, "               |   |   |   |\n");
 }
 
-static void graph_trace_open(struct trace_iterator *iter)
+void print_graph_headers(struct seq_file *s)
+{
+	print_graph_headers_flags(s, tracer_flags.val);
+}
+
+void graph_trace_open(struct trace_iterator *iter)
 {
 	/* pid and depth on the last trace processed */
 	struct fgraph_data *data;
@@ -1188,7 +1215,7 @@ static void graph_trace_open(struct trace_iterator *iter)
 	pr_warning("function graph tracer: not enough memory\n");
 }
 
-static void graph_trace_close(struct trace_iterator *iter)
+void graph_trace_close(struct trace_iterator *iter)
 {
 	struct fgraph_data *data = iter->private;
 
@@ -1198,6 +1225,16 @@ static void graph_trace_close(struct trace_iterator *iter)
 	}
 }
 
+static struct trace_event graph_trace_entry_event = {
+	.type		= TRACE_GRAPH_ENT,
+	.trace		= print_graph_function_event,
+};
+
+static struct trace_event graph_trace_ret_event = {
+	.type		= TRACE_GRAPH_RET,
+	.trace		= print_graph_function_event,
+};
+
 static struct tracer graph_trace __read_mostly = {
 	.name		= "function_graph",
 	.open		= graph_trace_open,
@@ -1219,6 +1256,16 @@ static __init int init_graph_trace(void)
 {
 	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
 
+	if (!register_ftrace_event(&graph_trace_entry_event)) {
+		pr_warning("Warning: could not register graph trace events\n");
+		return 1;
+	}
+
+	if (!register_ftrace_event(&graph_trace_ret_event)) {
+		pr_warning("Warning: could not register graph trace events\n");
+		return 1;
+	}
+
 	return register_tracer(&graph_trace);
 }
 
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
deleted file mode 100644
index 7b97000745f..00000000000
--- a/kernel/trace/trace_hw_branches.c
+++ /dev/null
@@ -1,312 +0,0 @@
-/*
- * h/w branch tracer for x86 based on BTS
- *
- * Copyright (C) 2008-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
-
-#include <asm/ds.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-
-#define BTS_BUFFER_SIZE (1 << 13)
-
-static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
-
-#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
-
-static int trace_hw_branches_enabled __read_mostly;
-static int trace_hw_branches_suspended __read_mostly;
-static struct trace_array *hw_branch_trace __read_mostly;
-
-
-static void bts_trace_init_cpu(int cpu)
-{
-	per_cpu(hwb_tracer, cpu) =
-		ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
-				   BTS_BUFFER_SIZE, NULL, (size_t)-1,
-				   BTS_KERNEL);
-
-	if (IS_ERR(per_cpu(hwb_tracer, cpu)))
-		per_cpu(hwb_tracer, cpu) = NULL;
-}
-
-static int bts_trace_init(struct trace_array *tr)
-{
-	int cpu;
-
-	hw_branch_trace = tr;
-	trace_hw_branches_enabled = 0;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		bts_trace_init_cpu(cpu);
-
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			trace_hw_branches_enabled = 1;
-	}
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-
-	/* If we could not enable tracing on a single cpu, we fail. */
-	return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (likely(per_cpu(hwb_tracer, cpu))) {
-			ds_release_bts(per_cpu(hwb_tracer, cpu));
-			per_cpu(hwb_tracer, cpu) = NULL;
-		}
-	}
-	trace_hw_branches_enabled = 0;
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-}
-
-static void bts_trace_start(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_resume_bts(per_cpu(hwb_tracer, cpu));
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-}
-
-static void bts_trace_stop(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-	trace_hw_branches_suspended = 1;
-	put_online_cpus();
-}
-
-static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	int cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		/* The notification is sent with interrupts enabled. */
-		if (trace_hw_branches_enabled) {
-			bts_trace_init_cpu(cpu);
-
-			if (trace_hw_branches_suspended &&
-			    likely(per_cpu(hwb_tracer, cpu)))
-				ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-		}
-		break;
-
-	case CPU_DOWN_PREPARE:
-		/* The notification is sent with interrupts enabled. */
-		if (likely(per_cpu(hwb_tracer, cpu))) {
-			ds_release_bts(per_cpu(hwb_tracer, cpu));
-			per_cpu(hwb_tracer, cpu) = NULL;
-		}
-	}
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
-	.notifier_call = bts_hotcpu_handler
-};
-
-static void bts_trace_print_header(struct seq_file *m)
-{
-	seq_puts(m, "# CPU#        TO  <-  FROM\n");
-}
-
-static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
-{
-	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
-	struct trace_entry *entry = iter->ent;
-	struct trace_seq *seq = &iter->seq;
-	struct hw_branch_entry *it;
-
-	trace_assign_type(it, entry);
-
-	if (entry->type == TRACE_HW_BRANCHES) {
-		if (trace_seq_printf(seq, "%4d  ", iter->cpu) &&
-		    seq_print_ip_sym(seq, it->to, symflags) &&
-		    trace_seq_printf(seq, "\t  <-  ") &&
-		    seq_print_ip_sym(seq, it->from, symflags) &&
-		    trace_seq_printf(seq, "\n"))
-			return TRACE_TYPE_HANDLED;
-		return TRACE_TYPE_PARTIAL_LINE;
-	}
-	return TRACE_TYPE_UNHANDLED;
-}
-
-void trace_hw_branch(u64 from, u64 to)
-{
-	struct ftrace_event_call *call = &event_hw_branch;
-	struct trace_array *tr = hw_branch_trace;
-	struct ring_buffer_event *event;
-	struct ring_buffer *buf;
-	struct hw_branch_entry *entry;
-	unsigned long irq1;
-	int cpu;
-
-	if (unlikely(!tr))
-		return;
-
-	if (unlikely(!trace_hw_branches_enabled))
-		return;
-
-	local_irq_save(irq1);
-	cpu = raw_smp_processor_id();
-	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
-		goto out;
-
-	buf = tr->buffer;
-	event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	tracing_generic_entry_update(&entry->ent, 0, from);
-	entry->ent.type = TRACE_HW_BRANCHES;
-	entry->from = from;
-	entry->to   = to;
-	if (!filter_check_discard(call, entry, buf, event))
-		trace_buffer_unlock_commit(buf, event, 0, 0);
-
- out:
-	atomic_dec(&tr->data[cpu]->disabled);
-	local_irq_restore(irq1);
-}
-
-static void trace_bts_at(const struct bts_trace *trace, void *at)
-{
-	struct bts_struct bts;
-	int err = 0;
-
-	WARN_ON_ONCE(!trace->read);
-	if (!trace->read)
-		return;
-
-	err = trace->read(this_tracer, at, &bts);
-	if (err < 0)
-		return;
-
-	switch (bts.qualifier) {
-	case BTS_BRANCH:
-		trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to);
-		break;
-	}
-}
-
-/*
- * Collect the trace on the current cpu and write it into the ftrace buffer.
- *
- * pre: tracing must be suspended on the current cpu
- */
-static void trace_bts_cpu(void *arg)
-{
-	struct trace_array *tr = (struct trace_array *)arg;
-	const struct bts_trace *trace;
-	unsigned char *at;
-
-	if (unlikely(!tr))
-		return;
-
-	if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled)))
-		return;
-
-	if (unlikely(!this_tracer))
-		return;
-
-	trace = ds_read_bts(this_tracer);
-	if (!trace)
-		return;
-
-	for (at = trace->ds.top; (void *)at < trace->ds.end;
-	     at += trace->ds.size)
-		trace_bts_at(trace, at);
-
-	for (at = trace->ds.begin; (void *)at < trace->ds.top;
-	     at += trace->ds.size)
-		trace_bts_at(trace, at);
-}
-
-static void trace_bts_prepare(struct trace_iterator *iter)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-	/*
-	 * We need to collect the trace on the respective cpu since ftrace
-	 * implicitly adds the record for the current cpu.
-	 * Once that is more flexible, we could collect the data from any cpu.
-	 */
-	on_each_cpu(trace_bts_cpu, iter->tr, 1);
-
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_resume_bts(per_cpu(hwb_tracer, cpu));
-	put_online_cpus();
-}
-
-static void trace_bts_close(struct trace_iterator *iter)
-{
-	tracing_reset_online_cpus(iter->tr);
-}
-
-void trace_hw_branch_oops(void)
-{
-	if (this_tracer) {
-		ds_suspend_bts_noirq(this_tracer);
-		trace_bts_cpu(hw_branch_trace);
-		ds_resume_bts_noirq(this_tracer);
-	}
-}
-
-struct tracer bts_tracer __read_mostly =
-{
-	.name		= "hw-branch-tracer",
-	.init		= bts_trace_init,
-	.reset		= bts_trace_reset,
-	.print_header	= bts_trace_print_header,
-	.print_line	= bts_trace_print_line,
-	.start		= bts_trace_start,
-	.stop		= bts_trace_stop,
-	.open		= trace_bts_prepare,
-	.close		= trace_bts_close,
-#ifdef CONFIG_FTRACE_SELFTEST
-	.selftest	= trace_selftest_startup_hw_branches,
-#endif /* CONFIG_FTRACE_SELFTEST */
-};
-
-__init static int init_bts_trace(void)
-{
-	register_hotcpu_notifier(&bts_hotcpu_notifier);
-	return register_tracer(&bts_tracer);
-}
-device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2974bc7538c..6fd486e0cef 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -34,6 +34,9 @@ static int trace_type __read_mostly;
 
 static int save_lat_flag;
 
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
+static int start_irqsoff_tracer(struct trace_array *tr, int graph);
+
 #ifdef CONFIG_PREEMPT_TRACER
 static inline int
 preempt_trace(void)
@@ -55,6 +58,23 @@ irq_trace(void)
 # define irq_trace() (0)
 #endif
 
+#define TRACE_DISPLAY_GRAPH	1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* display latency trace as call graph */
+	{ TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+	{ } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+	.val  = 0,
+	.opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
 /*
  * Sequence count - we record it when starting a measurement and
  * skip the latency if the sequence has changed - some other section
@@ -108,6 +128,202 @@ static struct ftrace_ops trace_ops __read_mostly =
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+	int cpu;
+
+	if (!(bit & TRACE_DISPLAY_GRAPH))
+		return -EINVAL;
+
+	if (!(is_graph() ^ set))
+		return 0;
+
+	stop_irqsoff_tracer(irqsoff_trace, !set);
+
+	for_each_possible_cpu(cpu)
+		per_cpu(tracing_cpu, cpu) = 0;
+
+	tracing_max_latency = 0;
+	tracing_reset_online_cpus(irqsoff_trace);
+
+	return start_irqsoff_tracer(irqsoff_trace, set);
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int ret;
+	int cpu;
+	int pc;
+
+	cpu = raw_smp_processor_id();
+	if (likely(!per_cpu(tracing_cpu, cpu)))
+		return 0;
+
+	local_save_flags(flags);
+	/* slight chance to get a false positive on tracing_cpu */
+	if (!irqs_disabled_flags(flags))
+		return 0;
+
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		ret = __trace_graph_entry(tr, trace, flags, pc);
+	} else
+		ret = 0;
+
+	atomic_dec(&data->disabled);
+	return ret;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	cpu = raw_smp_processor_id();
+	if (likely(!per_cpu(tracing_cpu, cpu)))
+		return;
+
+	local_save_flags(flags);
+	/* slight chance to get a false positive on tracing_cpu */
+	if (!irqs_disabled_flags(flags))
+		return;
+
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		__trace_graph_return(tr, trace, flags, pc);
+	}
+
+	atomic_dec(&data->disabled);
+}
+
+static void irqsoff_trace_open(struct trace_iterator *iter)
+{
+	if (is_graph())
+		graph_trace_open(iter);
+
+}
+
+static void irqsoff_trace_close(struct trace_iterator *iter)
+{
+	if (iter->private)
+		graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
+			    TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+	u32 flags = GRAPH_TRACER_FLAGS;
+
+	if (trace_flags & TRACE_ITER_LATENCY_FMT)
+		flags |= TRACE_GRAPH_PRINT_DURATION;
+	else
+		flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+	/*
+	 * In graph mode call the graph tracer output function,
+	 * otherwise go with the TRACE_FN event handler
+	 */
+	if (is_graph())
+		return print_graph_function_flags(iter, flags);
+
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_print_header(struct seq_file *s)
+{
+	if (is_graph()) {
+		struct trace_iterator *iter = s->private;
+		u32 flags = GRAPH_TRACER_FLAGS;
+
+		if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+			/* print nothing if the buffers are empty */
+			if (trace_empty(iter))
+				return;
+
+			print_trace_header(s, iter);
+			flags |= TRACE_GRAPH_PRINT_DURATION;
+		} else
+			flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+		print_graph_headers_flags(s, flags);
+	} else
+		trace_default_header(s);
+}
+
+static void
+trace_graph_function(struct trace_array *tr,
+		 unsigned long ip, unsigned long flags, int pc)
+{
+	u64 time = trace_clock_local();
+	struct ftrace_graph_ent ent = {
+		.func  = ip,
+		.depth = 0,
+	};
+	struct ftrace_graph_ret ret = {
+		.func     = ip,
+		.depth    = 0,
+		.calltime = time,
+		.rettime  = time,
+	};
+
+	__trace_graph_entry(tr, &ent, flags, pc);
+	__trace_graph_return(tr, &ret, flags, pc);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+		 unsigned long ip, unsigned long parent_ip,
+		 unsigned long flags, int pc)
+{
+	if (!is_graph())
+		trace_function(tr, ip, parent_ip, flags, pc);
+	else {
+		trace_graph_function(tr, parent_ip, flags, pc);
+		trace_graph_function(tr, ip, flags, pc);
+	}
+}
+
+#else
+#define __trace_function trace_function
+
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+	return -EINVAL;
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+	return -1;
+}
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
+static void irqsoff_print_header(struct seq_file *s) { }
+static void irqsoff_trace_open(struct trace_iterator *iter) { }
+static void irqsoff_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /*
  * Should this new latency be reported/recorded?
  */
@@ -150,7 +366,7 @@ check_critical_timing(struct trace_array *tr,
 	if (!report_latency(delta))
 		goto out_unlock;
 
-	trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 	/* Skip 5 functions to get to the irq/preempt enable function */
 	__trace_stack(tr, flags, 5, pc);
 
@@ -172,7 +388,7 @@ out_unlock:
 out:
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
-	trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
 static inline void
@@ -204,7 +420,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 
 	local_save_flags(flags);
 
-	trace_function(tr, ip, parent_ip, flags, preempt_count());
+	__trace_function(tr, ip, parent_ip, flags, preempt_count());
 
 	per_cpu(tracing_cpu, cpu) = 1;
 
@@ -238,7 +454,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 	atomic_inc(&data->disabled);
 
 	local_save_flags(flags);
-	trace_function(tr, ip, parent_ip, flags, preempt_count());
+	__trace_function(tr, ip, parent_ip, flags, preempt_count());
 	check_critical_timing(tr, data, parent_ip ? : ip, cpu);
 	data->critical_start = 0;
 	atomic_dec(&data->disabled);
@@ -347,19 +563,32 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
-static void start_irqsoff_tracer(struct trace_array *tr)
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
 {
-	register_ftrace_function(&trace_ops);
-	if (tracing_is_enabled())
+	int ret = 0;
+
+	if (!graph)
+		ret = register_ftrace_function(&trace_ops);
+	else
+		ret = register_ftrace_graph(&irqsoff_graph_return,
+					    &irqsoff_graph_entry);
+
+	if (!ret && tracing_is_enabled())
 		tracer_enabled = 1;
 	else
 		tracer_enabled = 0;
+
+	return ret;
 }
 
-static void stop_irqsoff_tracer(struct trace_array *tr)
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 {
 	tracer_enabled = 0;
-	unregister_ftrace_function(&trace_ops);
+
+	if (!graph)
+		unregister_ftrace_function(&trace_ops);
+	else
+		unregister_ftrace_graph();
 }
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
@@ -372,12 +601,14 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	/* make sure that the tracer is visible */
 	smp_wmb();
 	tracing_reset_online_cpus(tr);
-	start_irqsoff_tracer(tr);
+
+	if (start_irqsoff_tracer(tr, is_graph()))
+		printk(KERN_ERR "failed to start irqsoff tracer\n");
 }
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
-	stop_irqsoff_tracer(tr);
+	stop_irqsoff_tracer(tr, is_graph());
 
 	if (!save_lat_flag)
 		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
@@ -409,9 +640,15 @@ static struct tracer irqsoff_tracer __read_mostly =
 	.start		= irqsoff_tracer_start,
 	.stop		= irqsoff_tracer_stop,
 	.print_max	= 1,
+	.print_header   = irqsoff_print_header,
+	.print_line     = irqsoff_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
 #endif
+	.open           = irqsoff_trace_open,
+	.close          = irqsoff_trace_close,
 };
 # define register_irqsoff(trace) register_tracer(&trace)
 #else
@@ -435,9 +672,15 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.start		= irqsoff_tracer_start,
 	.stop		= irqsoff_tracer_stop,
 	.print_max	= 1,
+	.print_header   = irqsoff_print_header,
+	.print_line     = irqsoff_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
 #endif
+	.open		= irqsoff_trace_open,
+	.close		= irqsoff_trace_close,
 };
 # define register_preemptoff(trace) register_tracer(&trace)
 #else
@@ -463,9 +706,15 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.start		= irqsoff_tracer_start,
 	.stop		= irqsoff_tracer_stop,
 	.print_max	= 1,
+	.print_header   = irqsoff_print_header,
+	.print_line     = irqsoff_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
+	.open		= irqsoff_trace_open,
+	.close		= irqsoff_trace_close,
 };
 
 # define register_preemptirqsoff(trace) register_tracer(&trace)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1251e367bae..a7514326052 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -29,6 +29,8 @@
 #include <linux/ctype.h>
 #include <linux/ptrace.h>
 #include <linux/perf_event.h>
+#include <linux/stringify.h>
+#include <asm/bitsperlong.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -40,7 +42,6 @@
 
 /* Reserved field names */
 #define FIELD_STRING_IP "__probe_ip"
-#define FIELD_STRING_NARGS "__probe_nargs"
 #define FIELD_STRING_RETIP "__probe_ret_ip"
 #define FIELD_STRING_FUNC "__probe_func"
 
@@ -52,56 +53,102 @@ const char *reserved_field_names[] = {
 	"common_tgid",
 	"common_lock_depth",
 	FIELD_STRING_IP,
-	FIELD_STRING_NARGS,
 	FIELD_STRING_RETIP,
 	FIELD_STRING_FUNC,
 };
 
-struct fetch_func {
-	unsigned long (*func)(struct pt_regs *, void *);
+/* Printing function type */
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *);
+#define PRINT_TYPE_FUNC_NAME(type)	print_type_##type
+#define PRINT_TYPE_FMT_NAME(type)	print_type_format_##type
+
+/* Printing  in basic type function template */
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast)			\
+static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,	\
+						const char *name, void *data)\
+{									\
+	return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+}									\
+static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
+
+/* Data fetch function type */
+typedef	void (*fetch_func_t)(struct pt_regs *, void *, void *);
+
+struct fetch_param {
+	fetch_func_t	fn;
 	void *data;
 };
 
-static __kprobes unsigned long call_fetch(struct fetch_func *f,
-					  struct pt_regs *regs)
+static __kprobes void call_fetch(struct fetch_param *fprm,
+				 struct pt_regs *regs, void *dest)
 {
-	return f->func(regs, f->data);
+	return fprm->fn(regs, fprm->data, dest);
 }
 
-/* fetch handlers */
-static __kprobes unsigned long fetch_register(struct pt_regs *regs,
-					      void *offset)
-{
-	return regs_get_register(regs, (unsigned int)((unsigned long)offset));
+#define FETCH_FUNC_NAME(kind, type)	fetch_##kind##_##type
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(kind)  \
+DEFINE_FETCH_##kind(u8)			\
+DEFINE_FETCH_##kind(u16)		\
+DEFINE_FETCH_##kind(u32)		\
+DEFINE_FETCH_##kind(u64)
+
+#define CHECK_BASIC_FETCH_FUNCS(kind, fn)	\
+	((FETCH_FUNC_NAME(kind, u8) == fn) ||	\
+	 (FETCH_FUNC_NAME(kind, u16) == fn) ||	\
+	 (FETCH_FUNC_NAME(kind, u32) == fn) ||	\
+	 (FETCH_FUNC_NAME(kind, u64) == fn))
+
+/* Data fetch function templates */
+#define DEFINE_FETCH_reg(type)						\
+static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,	\
+					  void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_get_register(regs,			\
+				(unsigned int)((unsigned long)offset));	\
 }
-
-static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
-					   void *num)
-{
-	return regs_get_kernel_stack_nth(regs,
-					 (unsigned int)((unsigned long)num));
+DEFINE_BASIC_FETCH_FUNCS(reg)
+
+#define DEFINE_FETCH_stack(type)					\
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+					  void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_get_kernel_stack_nth(regs,		\
+				(unsigned int)((unsigned long)offset));	\
 }
+DEFINE_BASIC_FETCH_FUNCS(stack)
 
-static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
-{
-	unsigned long retval;
-
-	if (probe_kernel_address(addr, retval))
-		return 0;
-	return retval;
+#define DEFINE_FETCH_retval(type)					\
+static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+					  void *dummy, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_return_value(regs);			\
 }
-
-static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
-					      void *dummy)
-{
-	return regs_return_value(regs);
-}
-
-static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
-						   void *dummy)
-{
-	return kernel_stack_pointer(regs);
+DEFINE_BASIC_FETCH_FUNCS(retval)
+
+#define DEFINE_FETCH_memory(type)					\
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+					  void *addr, void *dest)	\
+{									\
+	type retval;							\
+	if (probe_kernel_address(addr, retval))				\
+		*(type *)dest = 0;					\
+	else								\
+		*(type *)dest = retval;					\
 }
+DEFINE_BASIC_FETCH_FUNCS(memory)
 
 /* Memory fetching by symbol */
 struct symbol_cache {
@@ -145,51 +192,126 @@ static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
 	return sc;
 }
 
-static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
-{
-	struct symbol_cache *sc = data;
-
-	if (sc->addr)
-		return fetch_memory(regs, (void *)sc->addr);
-	else
-		return 0;
+#define DEFINE_FETCH_symbol(type)					\
+static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
+					  void *data, void *dest)	\
+{									\
+	struct symbol_cache *sc = data;					\
+	if (sc->addr)							\
+		fetch_memory_##type(regs, (void *)sc->addr, dest);	\
+	else								\
+		*(type *)dest = 0;					\
 }
+DEFINE_BASIC_FETCH_FUNCS(symbol)
 
-/* Special indirect memory access interface */
-struct indirect_fetch_data {
-	struct fetch_func orig;
+/* Dereference memory access function */
+struct deref_fetch_param {
+	struct fetch_param orig;
 	long offset;
 };
 
-static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
-{
-	struct indirect_fetch_data *ind = data;
-	unsigned long addr;
-
-	addr = call_fetch(&ind->orig, regs);
-	if (addr) {
-		addr += ind->offset;
-		return fetch_memory(regs, (void *)addr);
-	} else
-		return 0;
+#define DEFINE_FETCH_deref(type)					\
+static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+					    void *data, void *dest)	\
+{									\
+	struct deref_fetch_param *dprm = data;				\
+	unsigned long addr;						\
+	call_fetch(&dprm->orig, regs, &addr);				\
+	if (addr) {							\
+		addr += dprm->offset;					\
+		fetch_memory_##type(regs, (void *)addr, dest);		\
+	} else								\
+		*(type *)dest = 0;					\
 }
+DEFINE_BASIC_FETCH_FUNCS(deref)
 
-static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
-	if (data->orig.func == fetch_indirect)
-		free_indirect_fetch_data(data->orig.data);
-	else if (data->orig.func == fetch_symbol)
+	if (CHECK_BASIC_FETCH_FUNCS(deref, data->orig.fn))
+		free_deref_fetch_param(data->orig.data);
+	else if (CHECK_BASIC_FETCH_FUNCS(symbol, data->orig.fn))
 		free_symbol_cache(data->orig.data);
 	kfree(data);
 }
 
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(kind, type)	\
+	.kind = FETCH_FUNC_NAME(kind, type)
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)	\
+	{.name = #ptype,			\
+	 .size = sizeof(ftype),			\
+	 .is_signed = sign,			\
+	 .print = PRINT_TYPE_FUNC_NAME(ptype),	\
+	 .fmt = PRINT_TYPE_FMT_NAME(ptype),	\
+ASSIGN_FETCH_FUNC(reg, ftype),			\
+ASSIGN_FETCH_FUNC(stack, ftype),		\
+ASSIGN_FETCH_FUNC(retval, ftype),		\
+ASSIGN_FETCH_FUNC(memory, ftype),		\
+ASSIGN_FETCH_FUNC(symbol, ftype),		\
+ASSIGN_FETCH_FUNC(deref, ftype),		\
+	}
+
+/* Fetch type information table */
+static const struct fetch_type {
+	const char	*name;		/* Name of type */
+	size_t		size;		/* Byte size of type */
+	int		is_signed;	/* Signed flag */
+	print_type_func_t	print;	/* Print functions */
+	const char	*fmt;		/* Fromat string */
+	/* Fetch functions */
+	fetch_func_t	reg;
+	fetch_func_t	stack;
+	fetch_func_t	retval;
+	fetch_func_t	memory;
+	fetch_func_t	symbol;
+	fetch_func_t	deref;
+} fetch_type_table[] = {
+	ASSIGN_FETCH_TYPE(u8,  u8,  0),
+	ASSIGN_FETCH_TYPE(u16, u16, 0),
+	ASSIGN_FETCH_TYPE(u32, u32, 0),
+	ASSIGN_FETCH_TYPE(u64, u64, 0),
+	ASSIGN_FETCH_TYPE(s8,  u8,  1),
+	ASSIGN_FETCH_TYPE(s16, u16, 1),
+	ASSIGN_FETCH_TYPE(s32, u32, 1),
+	ASSIGN_FETCH_TYPE(s64, u64, 1),
+};
+
+static const struct fetch_type *find_fetch_type(const char *type)
+{
+	int i;
+
+	if (!type)
+		type = DEFAULT_FETCH_TYPE_STR;
+
+	for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
+		if (strcmp(type, fetch_type_table[i].name) == 0)
+			return &fetch_type_table[i];
+	return NULL;
+}
+
+/* Special function : only accept unsigned long */
+static __kprobes void fetch_stack_address(struct pt_regs *regs,
+					  void *dummy, void *dest)
+{
+	*(unsigned long *)dest = kernel_stack_pointer(regs);
+}
+
 /**
  * Kprobe event core functions
  */
 
 struct probe_arg {
-	struct fetch_func	fetch;
-	const char		*name;
+	struct fetch_param	fetch;
+	unsigned int		offset;	/* Offset from argument entry */
+	const char		*name;	/* Name of this argument */
+	const char		*comm;	/* Command of this argument */
+	const struct fetch_type	*type;	/* Type of this argument */
 };
 
 /* Flags for trace_probe */
@@ -204,6 +326,7 @@ struct trace_probe {
 	const char		*symbol;	/* symbol name */
 	struct ftrace_event_call	call;
 	struct trace_event		event;
+	ssize_t			size;		/* trace entry size */
 	unsigned int		nr_args;
 	struct probe_arg	args[];
 };
@@ -212,6 +335,7 @@ struct trace_probe {
 	(offsetof(struct trace_probe, args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
+
 static __kprobes int probe_is_return(struct trace_probe *tp)
 {
 	return tp->rp.handler != NULL;
@@ -222,49 +346,6 @@ static __kprobes const char *probe_symbol(struct trace_probe *tp)
 	return tp->symbol ? tp->symbol : "unknown";
 }
 
-static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
-{
-	int ret = -EINVAL;
-
-	if (ff->func == fetch_register) {
-		const char *name;
-		name = regs_query_register_name((unsigned int)((long)ff->data));
-		ret = snprintf(buf, n, "%%%s", name);
-	} else if (ff->func == fetch_stack)
-		ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
-	else if (ff->func == fetch_memory)
-		ret = snprintf(buf, n, "@0x%p", ff->data);
-	else if (ff->func == fetch_symbol) {
-		struct symbol_cache *sc = ff->data;
-		if (sc->offset)
-			ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
-					sc->offset);
-		else
-			ret = snprintf(buf, n, "@%s", sc->symbol);
-	} else if (ff->func == fetch_retvalue)
-		ret = snprintf(buf, n, "$retval");
-	else if (ff->func == fetch_stack_address)
-		ret = snprintf(buf, n, "$stack");
-	else if (ff->func == fetch_indirect) {
-		struct indirect_fetch_data *id = ff->data;
-		size_t l = 0;
-		ret = snprintf(buf, n, "%+ld(", id->offset);
-		if (ret >= n)
-			goto end;
-		l += ret;
-		ret = probe_arg_string(buf + l, n - l, &id->orig);
-		if (ret < 0)
-			goto end;
-		l += ret;
-		ret = snprintf(buf + l, n - l, ")");
-		ret += l;
-	}
-end:
-	if (ret >= n)
-		return -ENOSPC;
-	return ret;
-}
-
 static int register_probe_event(struct trace_probe *tp);
 static void unregister_probe_event(struct trace_probe *tp);
 
@@ -347,11 +428,12 @@ error:
 
 static void free_probe_arg(struct probe_arg *arg)
 {
-	if (arg->fetch.func == fetch_symbol)
+	if (CHECK_BASIC_FETCH_FUNCS(deref, arg->fetch.fn))
+		free_deref_fetch_param(arg->fetch.data);
+	else if (CHECK_BASIC_FETCH_FUNCS(symbol, arg->fetch.fn))
 		free_symbol_cache(arg->fetch.data);
-	else if (arg->fetch.func == fetch_indirect)
-		free_indirect_fetch_data(arg->fetch.data);
 	kfree(arg->name);
+	kfree(arg->comm);
 }
 
 static void free_trace_probe(struct trace_probe *tp)
@@ -457,28 +539,30 @@ static int split_symbol_offset(char *symbol, unsigned long *offset)
 #define PARAM_MAX_ARGS 16
 #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
 
-static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_vars(char *arg, const struct fetch_type *t,
+			    struct fetch_param *f, int is_return)
 {
 	int ret = 0;
 	unsigned long param;
 
 	if (strcmp(arg, "retval") == 0) {
-		if (is_return) {
-			ff->func = fetch_retvalue;
-			ff->data = NULL;
-		} else
+		if (is_return)
+			f->fn = t->retval;
+		else
 			ret = -EINVAL;
 	} else if (strncmp(arg, "stack", 5) == 0) {
 		if (arg[5] == '\0') {
-			ff->func = fetch_stack_address;
-			ff->data = NULL;
+			if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
+				f->fn = fetch_stack_address;
+			else
+				ret = -EINVAL;
 		} else if (isdigit(arg[5])) {
 			ret = strict_strtoul(arg + 5, 10, &param);
 			if (ret || param > PARAM_MAX_STACK)
 				ret = -EINVAL;
 			else {
-				ff->func = fetch_stack;
-				ff->data = (void *)param;
+				f->fn = t->stack;
+				f->data = (void *)param;
 			}
 		} else
 			ret = -EINVAL;
@@ -488,7 +572,8 @@ static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
 }
 
 /* Recursive argument parser */
-static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int __parse_probe_arg(char *arg, const struct fetch_type *t,
+			     struct fetch_param *f, int is_return)
 {
 	int ret = 0;
 	unsigned long param;
@@ -497,13 +582,13 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
 
 	switch (arg[0]) {
 	case '$':
-		ret = parse_probe_vars(arg + 1, ff, is_return);
+		ret = parse_probe_vars(arg + 1, t, f, is_return);
 		break;
 	case '%':	/* named register */
 		ret = regs_query_register_offset(arg + 1);
 		if (ret >= 0) {
-			ff->func = fetch_register;
-			ff->data = (void *)(unsigned long)ret;
+			f->fn = t->reg;
+			f->data = (void *)(unsigned long)ret;
 			ret = 0;
 		}
 		break;
@@ -512,26 +597,22 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
 			ret = strict_strtoul(arg + 1, 0, &param);
 			if (ret)
 				break;
-			ff->func = fetch_memory;
-			ff->data = (void *)param;
+			f->fn = t->memory;
+			f->data = (void *)param;
 		} else {
 			ret = split_symbol_offset(arg + 1, &offset);
 			if (ret)
 				break;
-			ff->data = alloc_symbol_cache(arg + 1, offset);
-			if (ff->data)
-				ff->func = fetch_symbol;
-			else
-				ret = -EINVAL;
+			f->data = alloc_symbol_cache(arg + 1, offset);
+			if (f->data)
+				f->fn = t->symbol;
 		}
 		break;
-	case '+':	/* indirect memory */
+	case '+':	/* deref memory */
 	case '-':
 		tmp = strchr(arg, '(');
-		if (!tmp) {
-			ret = -EINVAL;
+		if (!tmp)
 			break;
-		}
 		*tmp = '\0';
 		ret = strict_strtol(arg + 1, 0, &offset);
 		if (ret)
@@ -541,38 +622,58 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
 		arg = tmp + 1;
 		tmp = strrchr(arg, ')');
 		if (tmp) {
-			struct indirect_fetch_data *id;
+			struct deref_fetch_param *dprm;
+			const struct fetch_type *t2 = find_fetch_type(NULL);
 			*tmp = '\0';
-			id = kzalloc(sizeof(struct indirect_fetch_data),
-				     GFP_KERNEL);
-			if (!id)
+			dprm = kzalloc(sizeof(struct deref_fetch_param),
+				       GFP_KERNEL);
+			if (!dprm)
 				return -ENOMEM;
-			id->offset = offset;
-			ret = __parse_probe_arg(arg, &id->orig, is_return);
+			dprm->offset = offset;
+			ret = __parse_probe_arg(arg, t2, &dprm->orig,
+						is_return);
 			if (ret)
-				kfree(id);
+				kfree(dprm);
 			else {
-				ff->func = fetch_indirect;
-				ff->data = (void *)id;
+				f->fn = t->deref;
+				f->data = (void *)dprm;
 			}
-		} else
-			ret = -EINVAL;
+		}
 		break;
-	default:
-		/* TODO: support custom handler */
-		ret = -EINVAL;
 	}
+	if (!ret && !f->fn)
+		ret = -EINVAL;
 	return ret;
 }
 
 /* String length checking wrapper */
-static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_arg(char *arg, struct trace_probe *tp,
+			   struct probe_arg *parg, int is_return)
 {
+	const char *t;
+
 	if (strlen(arg) > MAX_ARGSTR_LEN) {
 		pr_info("Argument is too long.: %s\n",  arg);
 		return -ENOSPC;
 	}
-	return __parse_probe_arg(arg, ff, is_return);
+	parg->comm = kstrdup(arg, GFP_KERNEL);
+	if (!parg->comm) {
+		pr_info("Failed to allocate memory for command '%s'.\n", arg);
+		return -ENOMEM;
+	}
+	t = strchr(parg->comm, ':');
+	if (t) {
+		arg[t - parg->comm] = '\0';
+		t++;
+	}
+	parg->type = find_fetch_type(t);
+	if (!parg->type) {
+		pr_info("Unsupported type: %s\n", t);
+		return -EINVAL;
+	}
+	parg->offset = tp->size;
+	tp->size += parg->type->size;
+	return __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
 }
 
 /* Return 1 if name is reserved or already used by another argument */
@@ -602,15 +703,18 @@ static int create_trace_probe(int argc, char **argv)
 	 *  @ADDR	: fetch memory at ADDR (ADDR should be in kernel)
 	 *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
 	 *  %REG	: fetch register REG
-	 * Indirect memory fetch:
+	 * Dereferencing memory fetch:
 	 *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
 	 * Alias name of args:
 	 *  NAME=FETCHARG : set NAME as alias of FETCHARG.
+	 * Type of args:
+	 *  FETCHARG:TYPE : use TYPE instead of unsigned long.
 	 */
 	struct trace_probe *tp;
 	int i, ret = 0;
 	int is_return = 0, is_delete = 0;
-	char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+	char *symbol = NULL, *event = NULL, *group = NULL;
+	char *arg, *tmp;
 	unsigned long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
@@ -723,13 +827,6 @@ static int create_trace_probe(int argc, char **argv)
 		else
 			arg = argv[i];
 
-		if (conflict_field_name(argv[i], tp->args, i)) {
-			pr_info("Argument%d name '%s' conflicts with "
-				"another field.\n", i, argv[i]);
-			ret = -EINVAL;
-			goto error;
-		}
-
 		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
 		if (!tp->args[i].name) {
 			pr_info("Failed to allocate argument%d name '%s'.\n",
@@ -737,9 +834,19 @@ static int create_trace_probe(int argc, char **argv)
 			ret = -ENOMEM;
 			goto error;
 		}
+		tmp = strchr(tp->args[i].name, ':');
+		if (tmp)
+			*tmp = '_';	/* convert : to _ */
+
+		if (conflict_field_name(tp->args[i].name, tp->args, i)) {
+			pr_info("Argument%d name '%s' conflicts with "
+				"another field.\n", i, argv[i]);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		/* Parse fetch argument */
-		ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+		ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
 		if (ret) {
 			pr_info("Parse error at argument%d. (%d)\n", i, ret);
 			kfree(tp->args[i].name);
@@ -794,8 +901,7 @@ static void probes_seq_stop(struct seq_file *m, void *v)
 static int probes_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_probe *tp = v;
-	int i, ret;
-	char buf[MAX_ARGSTR_LEN + 1];
+	int i;
 
 	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
 	seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
@@ -807,15 +913,10 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	else
 		seq_printf(m, " %s", probe_symbol(tp));
 
-	for (i = 0; i < tp->nr_args; i++) {
-		ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
-		if (ret < 0) {
-			pr_warning("Argument%d decoding error(%d).\n", i, ret);
-			return ret;
-		}
-		seq_printf(m, " %s=%s", tp->args[i].name, buf);
-	}
+	for (i = 0; i < tp->nr_args; i++)
+		seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
 	seq_printf(m, "\n");
+
 	return 0;
 }
 
@@ -945,9 +1046,10 @@ static const struct file_operations kprobe_profile_ops = {
 static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
-	struct kprobe_trace_entry *entry;
+	struct kprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	u8 *data;
 	int size, i, pc;
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tp->call;
@@ -957,7 +1059,7 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+	size = sizeof(*entry) + tp->size;
 
 	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
 						  irq_flags, pc);
@@ -965,10 +1067,10 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->nargs = tp->nr_args;
 	entry->ip = (unsigned long)kp->addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
@@ -979,9 +1081,10 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 					  struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
-	struct kretprobe_trace_entry *entry;
+	struct kretprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	u8 *data;
 	int size, i, pc;
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tp->call;
@@ -989,7 +1092,7 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+	size = sizeof(*entry) + tp->size;
 
 	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
 						  irq_flags, pc);
@@ -997,11 +1100,11 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->nargs = tp->nr_args;
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
@@ -1011,13 +1114,14 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 enum print_line_t
 print_kprobe_event(struct trace_iterator *iter, int flags)
 {
-	struct kprobe_trace_entry *field;
+	struct kprobe_trace_entry_head *field;
 	struct trace_seq *s = &iter->seq;
 	struct trace_event *event;
 	struct trace_probe *tp;
+	u8 *data;
 	int i;
 
-	field = (struct kprobe_trace_entry *)iter->ent;
+	field = (struct kprobe_trace_entry_head *)iter->ent;
 	event = ftrace_find_event(field->ent.type);
 	tp = container_of(event, struct trace_probe, event);
 
@@ -1030,9 +1134,10 @@ print_kprobe_event(struct trace_iterator *iter, int flags)
 	if (!trace_seq_puts(s, ")"))
 		goto partial;
 
-	for (i = 0; i < field->nargs; i++)
-		if (!trace_seq_printf(s, " %s=%lx",
-				      tp->args[i].name, field->args[i]))
+	data = (u8 *)&field[1];
+	for (i = 0; i < tp->nr_args; i++)
+		if (!tp->args[i].type->print(s, tp->args[i].name,
+					     data + tp->args[i].offset))
 			goto partial;
 
 	if (!trace_seq_puts(s, "\n"))
@@ -1046,13 +1151,14 @@ partial:
 enum print_line_t
 print_kretprobe_event(struct trace_iterator *iter, int flags)
 {
-	struct kretprobe_trace_entry *field;
+	struct kretprobe_trace_entry_head *field;
 	struct trace_seq *s = &iter->seq;
 	struct trace_event *event;
 	struct trace_probe *tp;
+	u8 *data;
 	int i;
 
-	field = (struct kretprobe_trace_entry *)iter->ent;
+	field = (struct kretprobe_trace_entry_head *)iter->ent;
 	event = ftrace_find_event(field->ent.type);
 	tp = container_of(event, struct trace_probe, event);
 
@@ -1071,9 +1177,10 @@ print_kretprobe_event(struct trace_iterator *iter, int flags)
 	if (!trace_seq_puts(s, ")"))
 		goto partial;
 
-	for (i = 0; i < field->nargs; i++)
-		if (!trace_seq_printf(s, " %s=%lx",
-				      tp->args[i].name, field->args[i]))
+	data = (u8 *)&field[1];
+	for (i = 0; i < tp->nr_args; i++)
+		if (!tp->args[i].type->print(s, tp->args[i].name,
+					     data + tp->args[i].offset))
 			goto partial;
 
 	if (!trace_seq_puts(s, "\n"))
@@ -1129,29 +1236,43 @@ static int probe_event_raw_init(struct ftrace_event_call *event_call)
 static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
 	int ret, i;
-	struct kprobe_trace_entry field;
+	struct kprobe_trace_entry_head field;
 	struct trace_probe *tp = (struct trace_probe *)event_call->data;
 
 	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
-	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
 	/* Set argument names as fields */
-	for (i = 0; i < tp->nr_args; i++)
-		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+	for (i = 0; i < tp->nr_args; i++) {
+		ret = trace_define_field(event_call, tp->args[i].type->name,
+					 tp->args[i].name,
+					 sizeof(field) + tp->args[i].offset,
+					 tp->args[i].type->size,
+					 tp->args[i].type->is_signed,
+					 FILTER_OTHER);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 
 static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
 	int ret, i;
-	struct kretprobe_trace_entry field;
+	struct kretprobe_trace_entry_head field;
 	struct trace_probe *tp = (struct trace_probe *)event_call->data;
 
 	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
 	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
-	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
 	/* Set argument names as fields */
-	for (i = 0; i < tp->nr_args; i++)
-		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+	for (i = 0; i < tp->nr_args; i++) {
+		ret = trace_define_field(event_call, tp->args[i].type->name,
+					 tp->args[i].name,
+					 sizeof(field) + tp->args[i].offset,
+					 tp->args[i].type->size,
+					 tp->args[i].type->is_signed,
+					 FILTER_OTHER);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 
@@ -1176,8 +1297,8 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
 
 	for (i = 0; i < tp->nr_args; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx",
-				tp->args[i].name);
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+				tp->args[i].name, tp->args[i].type->fmt);
 	}
 
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
@@ -1219,12 +1340,13 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 {
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
 	struct ftrace_event_call *call = &tp->call;
-	struct kprobe_trace_entry *entry;
+	struct kprobe_trace_entry_head *entry;
+	u8 *data;
 	int size, __size, i;
 	unsigned long irq_flags;
 	int rctx;
 
-	__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+	__size = sizeof(*entry) + tp->size;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
@@ -1235,10 +1357,10 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	if (!entry)
 		return;
 
-	entry->nargs = tp->nr_args;
 	entry->ip = (unsigned long)kp->addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
 }
@@ -1249,12 +1371,13 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 {
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
 	struct ftrace_event_call *call = &tp->call;
-	struct kretprobe_trace_entry *entry;
+	struct kretprobe_trace_entry_head *entry;
+	u8 *data;
 	int size, __size, i;
 	unsigned long irq_flags;
 	int rctx;
 
-	__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+	__size = sizeof(*entry) + tp->size;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
@@ -1265,11 +1388,11 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	if (!entry)
 		return;
 
-	entry->nargs = tp->nr_args;
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
+	data = (u8 *)&entry[1];
 	for (i = 0; i < tp->nr_args; i++)
-		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
 			       irq_flags, regs);
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index d59cd687947..8eaf00749b6 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -34,12 +34,6 @@
 
 #include <asm/atomic.h>
 
-/*
- * For now, let us restrict the no. of symbols traced simultaneously to number
- * of available hardware breakpoint registers.
- */
-#define KSYM_TRACER_MAX HBP_NUM
-
 #define KSYM_TRACER_OP_LEN 3 /* rw- */
 
 struct trace_ksym {
@@ -53,7 +47,6 @@ struct trace_ksym {
 
 static struct trace_array *ksym_trace_array;
 
-static unsigned int ksym_filter_entry_count;
 static unsigned int ksym_tracing_enabled;
 
 static HLIST_HEAD(ksym_filter_head);
@@ -181,13 +174,6 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
 	struct trace_ksym *entry;
 	int ret = -ENOMEM;
 
-	if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
-		printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
-		" new requests for tracing can be accepted now.\n",
-			KSYM_TRACER_MAX);
-		return -ENOSPC;
-	}
-
 	entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
@@ -203,13 +189,17 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
 
 	if (IS_ERR(entry->ksym_hbp)) {
 		ret = PTR_ERR(entry->ksym_hbp);
-		printk(KERN_INFO "ksym_tracer request failed. Try again"
-					" later!!\n");
+		if (ret == -ENOSPC) {
+			printk(KERN_ERR "ksym_tracer: Maximum limit reached."
+			" No new requests for tracing can be accepted now.\n");
+		} else {
+			printk(KERN_INFO "ksym_tracer request failed. Try again"
+					 " later!!\n");
+		}
 		goto err;
 	}
 
 	hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
-	ksym_filter_entry_count++;
 
 	return 0;
 
@@ -265,7 +255,6 @@ static void __ksym_trace_reset(void)
 	hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
 								ksym_hlist) {
 		unregister_wide_hw_breakpoint(entry->ksym_hbp);
-		ksym_filter_entry_count--;
 		hlist_del_rcu(&(entry->ksym_hlist));
 		synchronize_rcu();
 		kfree(entry);
@@ -338,7 +327,6 @@ static ssize_t ksym_trace_filter_write(struct file *file,
 				goto out_unlock;
 		}
 		/* Error or "symbol:---" case: drop it */
-		ksym_filter_entry_count--;
 		hlist_del_rcu(&(entry->ksym_hlist));
 		synchronize_rcu();
 		kfree(entry);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 8e46b3323cd..ab13d700806 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -209,6 +209,7 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
 
 	return 1;
 }
+EXPORT_SYMBOL(trace_seq_putc);
 
 int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
 {
@@ -253,7 +254,7 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
 	void *ret;
 
 	if (s->full)
-		return 0;
+		return NULL;
 
 	if (len > ((PAGE_SIZE - 1) - s->len)) {
 		s->full = 1;
@@ -355,6 +356,21 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
+const char *
+ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
+{
+	int i;
+	const char *ret = p->buffer + p->len;
+
+	for (i = 0; i < buf_len; i++)
+		trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]);
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_hex_seq);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 5fca0f51fde..a55fccfede5 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -50,8 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-			struct task_struct *next)
+probe_sched_switch(struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
@@ -109,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
+probe_sched_wakeup(struct task_struct *wakee, int success)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0271742abb8..8052446ceea 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -107,8 +107,7 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
 }
 
 static void notrace
-probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
-	struct task_struct *next)
+probe_wakeup_sched_switch(struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
 	cycle_t T0, T1, delta;
@@ -200,7 +199,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(struct rq *rq, struct task_struct *p, int success)
+probe_wakeup(struct task_struct *p, int success)
 {
 	struct trace_array_cpu *data;
 	int cpu = smp_processor_id();
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 81003b4d617..250e7f9bd2f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,7 +17,6 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
-	case TRACE_HW_BRANCHES:
 	case TRACE_KSYM:
 		return 1;
 	}
@@ -30,7 +29,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 	struct trace_entry *entry;
 	unsigned int loops = 0;
 
-	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
 		entry = ring_buffer_event_data(event);
 
 		/*
@@ -256,7 +255,8 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 /* Maximum number of functions to trace before diagnosing a hang */
 #define GRAPH_MAX_FUNC_TEST	100000000
 
-static void __ftrace_dump(bool disable_tracing);
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
 static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
@@ -267,7 +267,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
 		ftrace_graph_stop();
 		printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
 		if (ftrace_dump_on_oops)
-			__ftrace_dump(false);
+			__ftrace_dump(false, DUMP_ALL);
 		return 0;
 	}
 
@@ -755,62 +755,6 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-int
-trace_selftest_startup_hw_branches(struct tracer *trace,
-				   struct trace_array *tr)
-{
-	struct trace_iterator *iter;
-	struct tracer tracer;
-	unsigned long count;
-	int ret;
-
-	if (!trace->open) {
-		printk(KERN_CONT "missing open function...");
-		return -1;
-	}
-
-	ret = tracer_init(trace, tr);
-	if (ret) {
-		warn_failed_init_tracer(trace, ret);
-		return ret;
-	}
-
-	/*
-	 * The hw-branch tracer needs to collect the trace from the various
-	 * cpu trace buffers - before tracing is stopped.
-	 */
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return -ENOMEM;
-
-	memcpy(&tracer, trace, sizeof(tracer));
-
-	iter->trace = &tracer;
-	iter->tr = tr;
-	iter->pos = -1;
-	mutex_init(&iter->mutex);
-
-	trace->open(iter);
-
-	mutex_destroy(&iter->mutex);
-	kfree(iter);
-
-	tracing_stop();
-
-	ret = trace_test_buffer(tr, &count);
-	trace->reset(tr);
-	tracing_start();
-
-	if (!ret && !count) {
-		printk(KERN_CONT "no entries found..");
-		ret = -1;
-	}
-
-	return ret;
-}
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_KSYM_TRACER
 static int ksym_selftest_dummy;
 
diff --git a/kernel/user.c b/kernel/user.c
index 766467b3bcb..7e72614b736 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/user_namespace.h>
-#include "cred-internals.h"
 
 struct user_namespace init_user_ns = {
 	.kref = {
@@ -137,9 +136,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 	struct hlist_head *hashent = uidhashentry(ns, uid);
 	struct user_struct *up, *new;
 
-	/* Make uid_hash_find() + uids_user_create() + uid_hash_insert()
-	 * atomic.
-	 */
 	spin_lock_irq(&uidhash_lock);
 	up = uid_hash_find(uid, hashent);
 	spin_unlock_irq(&uidhash_lock);
@@ -161,11 +157,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
-			/* This case is not possible when CONFIG_USER_SCHED
-			 * is defined, since we serialize alloc_uid() using
-			 * uids_mutex. Hence no need to call
-			 * sched_destroy_user() or remove_user_sysfs_dir().
-			 */
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);
@@ -178,8 +169,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 
 	return up;
 
-	put_user_ns(new->user_ns);
-	kmem_cache_free(uid_cachep, new);
 out_unlock:
 	return NULL;
 }
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 076c7c8215b..b2d70d38dff 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -54,8 +54,8 @@ int create_user_ns(struct cred *new)
 #endif
 	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
 
-	/* alloc_uid() incremented the userns refcount.  Just set it to 1 */
-	kref_set(&ns->kref, 1);
+	/* root_user holds a reference to ns, our reference can be dropped */
+	put_user_ns(ns);
 
 	return 0;
 }
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index dee48658805..77dabbf64b8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -229,6 +229,16 @@ static inline void set_wq_data(struct work_struct *work,
 	atomic_long_set(&work->data, new);
 }
 
+/*
+ * Clear WORK_STRUCT_PENDING and the workqueue on which it was queued.
+ */
+static inline void clear_wq_data(struct work_struct *work)
+{
+	unsigned long flags = *work_data_bits(work) &
+				(1UL << WORK_STRUCT_STATIC);
+	atomic_long_set(&work->data, flags);
+}
+
 static inline
 struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
 {
@@ -671,7 +681,7 @@ static int __cancel_work_timer(struct work_struct *work,
 		wait_on_work(work);
 	} while (unlikely(ret < 0));
 
-	work_clear_pending(work);
+	clear_wq_data(work);
 	return ret;
 }
 
@@ -774,7 +784,7 @@ void flush_delayed_work(struct delayed_work *dwork)
 {
 	if (del_timer_sync(&dwork->timer)) {
 		struct cpu_workqueue_struct *cwq;
-		cwq = wq_per_cpu(keventd_wq, get_cpu());
+		cwq = wq_per_cpu(get_wq_data(&dwork->work)->wq, get_cpu());
 		__queue_work(cwq, &dwork->work);
 		put_cpu();
 	}
@@ -845,6 +855,30 @@ int schedule_on_each_cpu(work_func_t func)
 	return 0;
 }
 
+/**
+ * flush_scheduled_work - ensure that any scheduled work has run to completion.
+ *
+ * Forces execution of the kernel-global workqueue and blocks until its
+ * completion.
+ *
+ * Think twice before calling this function!  It's very easy to get into
+ * trouble if you don't take great care.  Either of the following situations
+ * will lead to deadlock:
+ *
+ *	One of the work items currently on the workqueue needs to acquire
+ *	a lock held by your code or its caller.
+ *
+ *	Your code is running in the context of a work routine.
+ *
+ * They will be detected by lockdep when they occur, but the first might not
+ * occur very often.  It depends on what work items are on the workqueue and
+ * what locks they need, which you have no control over.
+ *
+ * In most situations flushing the entire workqueue is overkill; you merely
+ * need to know that a particular work item isn't queued and isn't running.
+ * In such cases you should use cancel_delayed_work_sync() or
+ * cancel_work_sync() instead.
+ */
 void flush_scheduled_work(void)
 {
 	flush_workqueue(keventd_wq);
author	Jens Axboe <jens.axboe@oracle.com>	2010-05-21 21:27:26 +0200
committer	Jens Axboe <jens.axboe@oracle.com>	2010-05-21 21:27:26 +0200
commit	ee9a3607fb03e804ddf624544105f4e34260c380 (patch)
tree	ce41b6e0fa10982a306f6c142a92dbf3c9961284 /kernel
parent	b492e95be0ae672922f4734acf3f5d35c30be948 (diff)
parent	d515e86e639890b33a09390d062b0831664f04a2 (diff)