13 files changed, 18809 insertions, 0 deletions

diff --git a/libdde-linux26/lib/src/kernel/capability.c b/libdde-linux26/lib/src/kernel/capability.c
new file mode 100644
index 00000000..c269aa7c
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/capability.c
@@ -0,0 +1,323 @@
+/*
+ * linux/kernel/capability.c
+ *
+ * Copyright (C) 1997  Andrew Main <zefram@fysh.org>
+ *
+ * Integrated into 2.1.97+,  Andrew G. Morgan <morgan@kernel.org>
+ * 30 May 2002:	Cleanup, Robert M. Love <rml@tech9.net>
+ */
+
+#include <linux/audit.h>
+#include <linux/capability.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/pid_namespace.h>
+#include <asm/uaccess.h>
+#include "cred-internals.h"
+
+#ifndef DDE_LINUX
+/*
+ * This lock protects task->cap_* for all tasks including current.
+ * Locking rule: acquire this prior to tasklist_lock.
+ */
+static DEFINE_SPINLOCK(task_capability_lock);
+
+/*
+ * Leveraged for setting/resetting capabilities
+ */
+
+const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET;
+const kernel_cap_t __cap_full_set = CAP_FULL_SET;
+const kernel_cap_t __cap_init_eff_set = CAP_INIT_EFF_SET;
+
+EXPORT_SYMBOL(__cap_empty_set);
+EXPORT_SYMBOL(__cap_full_set);
+EXPORT_SYMBOL(__cap_init_eff_set);
+
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+int file_caps_enabled = 1;
+
+static int __init file_caps_disable(char *str)
+{
+	file_caps_enabled = 0;
+	return 1;
+}
+__setup("no_file_caps", file_caps_disable);
+#endif
+
+/*
+ * More recent versions of libcap are available from:
+ *
+ *   http://www.kernel.org/pub/linux/libs/security/linux-privs/
+ */
+
+static void warn_legacy_capability_use(void)
+{
+	static int warned;
+	if (!warned) {
+		char name[sizeof(current->comm)];
+
+		printk(KERN_INFO "warning: `%s' uses 32-bit capabilities"
+		       " (legacy support in use)\n",
+		       get_task_comm(name, current));
+		warned = 1;
+	}
+}
+
+/*
+ * Version 2 capabilities worked fine, but the linux/capability.h file
+ * that accompanied their introduction encouraged their use without
+ * the necessary user-space source code changes. As such, we have
+ * created a version 3 with equivalent functionality to version 2, but
+ * with a header change to protect legacy source code from using
+ * version 2 when it wanted to use version 1. If your system has code
+ * that trips the following warning, it is using version 2 specific
+ * capabilities and may be doing so insecurely.
+ *
+ * The remedy is to either upgrade your version of libcap (to 2.10+,
+ * if the application is linked against it), or recompile your
+ * application with modern kernel headers and this warning will go
+ * away.
+ */
+
+static void warn_deprecated_v2(void)
+{
+	static int warned;
+
+	if (!warned) {
+		char name[sizeof(current->comm)];
+
+		printk(KERN_INFO "warning: `%s' uses deprecated v2"
+		       " capabilities in a way that may be insecure.\n",
+		       get_task_comm(name, current));
+		warned = 1;
+	}
+}
+
+/*
+ * Version check. Return the number of u32s in each capability flag
+ * array, or a negative value on error.
+ */
+static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
+{
+	__u32 version;
+
+	if (get_user(version, &header->version))
+		return -EFAULT;
+
+	switch (version) {
+	case _LINUX_CAPABILITY_VERSION_1:
+		warn_legacy_capability_use();
+		*tocopy = _LINUX_CAPABILITY_U32S_1;
+		break;
+	case _LINUX_CAPABILITY_VERSION_2:
+		warn_deprecated_v2();
+		/*
+		 * fall through - v3 is otherwise equivalent to v2.
+		 */
+	case _LINUX_CAPABILITY_VERSION_3:
+		*tocopy = _LINUX_CAPABILITY_U32S_3;
+		break;
+	default:
+		if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version))
+			return -EFAULT;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * The only thing that can change the capabilities of the current
+ * process is the current process. As such, we can't be in this code
+ * at the same time as we are in the process of setting capabilities
+ * in this process. The net result is that we can limit our use of
+ * locks to when we are reading the caps of another process.
+ */
+static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
+				     kernel_cap_t *pIp, kernel_cap_t *pPp)
+{
+	int ret;
+
+	if (pid && (pid != task_pid_vnr(current))) {
+		struct task_struct *target;
+
+		read_lock(&tasklist_lock);
+
+		target = find_task_by_vpid(pid);
+		if (!target)
+			ret = -ESRCH;
+		else
+			ret = security_capget(target, pEp, pIp, pPp);
+
+		read_unlock(&tasklist_lock);
+	} else
+		ret = security_capget(current, pEp, pIp, pPp);
+
+	return ret;
+}
+
+/**
+ * sys_capget - get the capabilities of a given process.
+ * @header: pointer to struct that contains capability version and
+ *	target pid data
+ * @dataptr: pointer to struct that contains the effective, permitted,
+ *	and inheritable capabilities that are returned
+ *
+ * Returns 0 on success and < 0 on error.
+ */
+SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
+{
+	int ret = 0;
+	pid_t pid;
+	unsigned tocopy;
+	kernel_cap_t pE, pI, pP;
+
+	ret = cap_validate_magic(header, &tocopy);
+	if (ret != 0)
+		return ret;
+
+	if (get_user(pid, &header->pid))
+		return -EFAULT;
+
+	if (pid < 0)
+		return -EINVAL;
+
+	ret = cap_get_target_pid(pid, &pE, &pI, &pP);
+	if (!ret) {
+		struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
+		unsigned i;
+
+		for (i = 0; i < tocopy; i++) {
+			kdata[i].effective = pE.cap[i];
+			kdata[i].permitted = pP.cap[i];
+			kdata[i].inheritable = pI.cap[i];
+		}
+
+		/*
+		 * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
+		 * we silently drop the upper capabilities here. This
+		 * has the effect of making older libcap
+		 * implementations implicitly drop upper capability
+		 * bits when they perform a: capget/modify/capset
+		 * sequence.
+		 *
+		 * This behavior is considered fail-safe
+		 * behavior. Upgrading the application to a newer
+		 * version of libcap will enable access to the newer
+		 * capabilities.
+		 *
+		 * An alternative would be to return an error here
+		 * (-ERANGE), but that causes legacy applications to
+		 * unexpectidly fail; the capget/modify/capset aborts
+		 * before modification is attempted and the application
+		 * fails.
+		 */
+		if (copy_to_user(dataptr, kdata, tocopy
+				 * sizeof(struct __user_cap_data_struct))) {
+			return -EFAULT;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sys_capset - set capabilities for a process or (*) a group of processes
+ * @header: pointer to struct that contains capability version and
+ *	target pid data
+ * @data: pointer to struct that contains the effective, permitted,
+ *	and inheritable capabilities
+ *
+ * Set capabilities for the current process only.  The ability to any other
+ * process(es) has been deprecated and removed.
+ *
+ * The restrictions on setting capabilities are specified as:
+ *
+ * I: any raised capabilities must be a subset of the old permitted
+ * P: any raised capabilities must be a subset of the old permitted
+ * E: must be set to a subset of new permitted
+ *
+ * Returns 0 on success and < 0 on error.
+ */
+SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
+{
+	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
+	unsigned i, tocopy;
+	kernel_cap_t inheritable, permitted, effective;
+	struct cred *new;
+	int ret;
+	pid_t pid;
+
+	ret = cap_validate_magic(header, &tocopy);
+	if (ret != 0)
+		return ret;
+
+	if (get_user(pid, &header->pid))
+		return -EFAULT;
+
+	/* may only affect current now */
+	if (pid != 0 && pid != task_pid_vnr(current))
+		return -EPERM;
+
+	if (copy_from_user(&kdata, data,
+			   tocopy * sizeof(struct __user_cap_data_struct)))
+		return -EFAULT;
+
+	for (i = 0; i < tocopy; i++) {
+		effective.cap[i] = kdata[i].effective;
+		permitted.cap[i] = kdata[i].permitted;
+		inheritable.cap[i] = kdata[i].inheritable;
+	}
+	while (i < _KERNEL_CAPABILITY_U32S) {
+		effective.cap[i] = 0;
+		permitted.cap[i] = 0;
+		inheritable.cap[i] = 0;
+		i++;
+	}
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = security_capset(new, current_cred(),
+			      &effective, &inheritable, &permitted);
+	if (ret < 0)
+		goto error;
+
+	audit_log_capset(pid, new, current_cred());
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return ret;
+}
+#endif /* !DDE_LINUX */
+
+/**
+ * capable - Determine if the current task has a superior capability in effect
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+int capable(int cap)
+{
+	if (unlikely(!cap_valid(cap))) {
+		printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
+		BUG();
+	}
+
+	if (security_capable(cap) == 0) {
+		current->flags |= PF_SUPERPRIV;
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(capable);
diff --git a/libdde-linux26/lib/src/kernel/cred-internals.h b/libdde-linux26/lib/src/kernel/cred-internals.h
new file mode 100644
index 00000000..2dc4fc2d
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/cred-internals.h
@@ -0,0 +1,21 @@
+/* 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/libdde-linux26/lib/src/kernel/exit.c b/libdde-linux26/lib/src/kernel/exit.c
new file mode 100644
index 00000000..703f9aab
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/exit.c
@@ -0,0 +1,1850 @@
+/*
+ *  linux/kernel/exit.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/personality.h>
+#include <linux/tty.h>
+#include <linux/mnt_namespace.h>
+#include <linux/iocontext.h>
+#include <linux/key.h>
+#include <linux/security.h>
+#include <linux/cpu.h>
+#include <linux/acct.h>
+#include <linux/tsacct_kern.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/binfmts.h>
+#include <linux/nsproxy.h>
+#include <linux/pid_namespace.h>
+#include <linux/ptrace.h>
+#include <linux/profile.h>
+#include <linux/mount.h>
+#include <linux/proc_fs.h>
+#include <linux/kthread.h>
+#include <linux/mempolicy.h>
+#include <linux/taskstats_kern.h>
+#include <linux/delayacct.h>
+#include <linux/freezer.h>
+#include <linux/cgroup.h>
+#include <linux/syscalls.h>
+#include <linux/signal.h>
+#include <linux/posix-timers.h>
+#include <linux/cn_proc.h>
+#include <linux/mutex.h>
+#include <linux/futex.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/audit.h> /* for audit_free() */
+#include <linux/resource.h>
+#include <linux/blkdev.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/tracehook.h>
+#include <linux/init_task.h>
+#include <trace/sched.h>
+
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/pgtable.h>
+#include <asm/mmu_context.h>
+#include "cred-internals.h"
+
+DEFINE_TRACE(sched_process_free);
+DEFINE_TRACE(sched_process_exit);
+DEFINE_TRACE(sched_process_wait);
+
+#ifndef DDE_LINUX
+static void exit_mm(struct task_struct * tsk);
+
+static inline int task_detached(struct task_struct *p)
+{
+	return p->exit_signal == -1;
+}
+
+static void __unhash_process(struct task_struct *p)
+{
+	nr_threads--;
+	detach_pid(p, PIDTYPE_PID);
+	if (thread_group_leader(p)) {
+		detach_pid(p, PIDTYPE_PGID);
+		detach_pid(p, PIDTYPE_SID);
+
+		list_del_rcu(&p->tasks);
+		__get_cpu_var(process_counts)--;
+	}
+	list_del_rcu(&p->thread_group);
+	list_del_init(&p->sibling);
+}
+
+/*
+ * This function expects the tasklist_lock write-locked.
+ */
+static void __exit_signal(struct task_struct *tsk)
+{
+	struct signal_struct *sig = tsk->signal;
+	struct sighand_struct *sighand;
+
+	BUG_ON(!sig);
+	BUG_ON(!atomic_read(&sig->count));
+
+	sighand = rcu_dereference(tsk->sighand);
+	spin_lock(&sighand->siglock);
+
+	posix_cpu_timers_exit(tsk);
+	if (atomic_dec_and_test(&sig->count))
+		posix_cpu_timers_exit_group(tsk);
+	else {
+		/*
+		 * If there is any task waiting for the group exit
+		 * then notify it:
+		 */
+		if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count)
+			wake_up_process(sig->group_exit_task);
+
+		if (tsk == sig->curr_target)
+			sig->curr_target = next_thread(tsk);
+		/*
+		 * Accumulate here the counters for all threads but the
+		 * group leader as they die, so they can be added into
+		 * the process-wide totals when those are taken.
+		 * The group leader stays around as a zombie as long
+		 * as there are other threads.  When it gets reaped,
+		 * the exit.c code will add its counts into these totals.
+		 * We won't ever get here for the group leader, since it
+		 * will have been the last reference on the signal_struct.
+		 */
+		sig->utime = cputime_add(sig->utime, task_utime(tsk));
+		sig->stime = cputime_add(sig->stime, task_stime(tsk));
+		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+		sig->min_flt += tsk->min_flt;
+		sig->maj_flt += tsk->maj_flt;
+		sig->nvcsw += tsk->nvcsw;
+		sig->nivcsw += tsk->nivcsw;
+		sig->inblock += task_io_get_inblock(tsk);
+		sig->oublock += task_io_get_oublock(tsk);
+		task_io_accounting_add(&sig->ioac, &tsk->ioac);
+		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
+		sig = NULL; /* Marker for below. */
+	}
+
+	__unhash_process(tsk);
+
+	/*
+	 * Do this under ->siglock, we can race with another thread
+	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
+	 */
+	flush_sigqueue(&tsk->pending);
+
+	tsk->signal = NULL;
+	tsk->sighand = NULL;
+	spin_unlock(&sighand->siglock);
+
+	__cleanup_sighand(sighand);
+	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
+	if (sig) {
+		flush_sigqueue(&sig->shared_pending);
+		taskstats_tgid_free(sig);
+		/*
+		 * Make sure ->signal can't go away under rq->lock,
+		 * see account_group_exec_runtime().
+		 */
+		task_rq_unlock_wait(tsk);
+		__cleanup_signal(sig);
+	}
+}
+
+static void delayed_put_task_struct(struct rcu_head *rhp)
+{
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+	trace_sched_process_free(tsk);
+	put_task_struct(tsk);
+}
+
+
+void release_task(struct task_struct * p)
+{
+	struct task_struct *leader;
+	int zap_leader;
+repeat:
+	tracehook_prepare_release_task(p);
+	/* don't need to get the RCU readlock here - the process is dead and
+	 * can't be modifying its own credentials */
+	atomic_dec(&__task_cred(p)->user->processes);
+
+	proc_flush_task(p);
+	write_lock_irq(&tasklist_lock);
+	tracehook_finish_release_task(p);
+	__exit_signal(p);
+
+	/*
+	 * If we are the last non-leader member of the thread
+	 * group, and the leader is zombie, then notify the
+	 * group leader's parent process. (if it wants notification.)
+	 */
+	zap_leader = 0;
+	leader = p->group_leader;
+	if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
+		BUG_ON(task_detached(leader));
+		do_notify_parent(leader, leader->exit_signal);
+		/*
+		 * If we were the last child thread and the leader has
+		 * exited already, and the leader's parent ignores SIGCHLD,
+		 * then we are the one who should release the leader.
+		 *
+		 * do_notify_parent() will have marked it self-reaping in
+		 * that case.
+		 */
+		zap_leader = task_detached(leader);
+
+		/*
+		 * This maintains the invariant that release_task()
+		 * only runs on a task in EXIT_DEAD, just for sanity.
+		 */
+		if (zap_leader)
+			leader->exit_state = EXIT_DEAD;
+	}
+
+	write_unlock_irq(&tasklist_lock);
+	release_thread(p);
+	call_rcu(&p->rcu, delayed_put_task_struct);
+
+	p = leader;
+	if (unlikely(zap_leader))
+		goto repeat;
+}
+
+/*
+ * This checks not only the pgrp, but falls back on the pid if no
+ * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
+ * without this...
+ *
+ * The caller must hold rcu lock or the tasklist lock.
+ */
+struct pid *session_of_pgrp(struct pid *pgrp)
+{
+	struct task_struct *p;
+	struct pid *sid = NULL;
+
+	p = pid_task(pgrp, PIDTYPE_PGID);
+	if (p == NULL)
+		p = pid_task(pgrp, PIDTYPE_PID);
+	if (p != NULL)
+		sid = task_session(p);
+
+	return sid;
+}
+
+/*
+ * Determine if a process group is "orphaned", according to the POSIX
+ * definition in 2.2.2.52.  Orphaned process groups are not to be affected
+ * by terminal-generated stop signals.  Newly orphaned process groups are
+ * to receive a SIGHUP and a SIGCONT.
+ *
+ * "I ask you, have you ever known what it is to be an orphan?"
+ */
+static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
+{
+	struct task_struct *p;
+
+	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+		if ((p == ignored_task) ||
+		    (p->exit_state && thread_group_empty(p)) ||
+		    is_global_init(p->real_parent))
+			continue;
+
+		if (task_pgrp(p->real_parent) != pgrp &&
+		    task_session(p->real_parent) == task_session(p))
+			return 0;
+	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+
+	return 1;
+}
+
+int is_current_pgrp_orphaned(void)
+{
+	int retval;
+
+	read_lock(&tasklist_lock);
+	retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
+	read_unlock(&tasklist_lock);
+
+	return retval;
+}
+
+static int has_stopped_jobs(struct pid *pgrp)
+{
+	int retval = 0;
+	struct task_struct *p;
+
+	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+		if (!task_is_stopped(p))
+			continue;
+		retval = 1;
+		break;
+	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+	return retval;
+}
+
+/*
+ * Check to see if any process groups have become orphaned as
+ * a result of our exiting, and if they have any stopped jobs,
+ * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
+ */
+static void
+kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
+{
+	struct pid *pgrp = task_pgrp(tsk);
+	struct task_struct *ignored_task = tsk;
+
+	if (!parent)
+		 /* exit: our father is in a different pgrp than
+		  * we are and we were the only connection outside.
+		  */
+		parent = tsk->real_parent;
+	else
+		/* reparent: our child is in a different pgrp than
+		 * we are, and it was the only connection outside.
+		 */
+		ignored_task = NULL;
+
+	if (task_pgrp(parent) != pgrp &&
+	    task_session(parent) == task_session(tsk) &&
+	    will_become_orphaned_pgrp(pgrp, ignored_task) &&
+	    has_stopped_jobs(pgrp)) {
+		__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
+		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
+	}
+}
+
+/**
+ * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
+ *
+ * If a kernel thread is launched as a result of a system call, or if
+ * it ever exits, it should generally reparent itself to kthreadd so it
+ * isn't in the way of other processes and is correctly cleaned up on exit.
+ *
+ * The various task state such as scheduling policy and priority may have
+ * been inherited from a user process, so we reset them to sane values here.
+ *
+ * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
+ */
+static void reparent_to_kthreadd(void)
+{
+	write_lock_irq(&tasklist_lock);
+
+	ptrace_unlink(current);
+	/* Reparent to init */
+	current->real_parent = current->parent = kthreadd_task;
+	list_move_tail(&current->sibling, &current->real_parent->children);
+
+	/* Set the exit signal to SIGCHLD so we signal init on exit */
+	current->exit_signal = SIGCHLD;
+
+	if (task_nice(current) < 0)
+		set_user_nice(current, 0);
+	/* cpus_allowed? */
+	/* rt_priority? */
+	/* signals? */
+	memcpy(current->signal->rlim, init_task.signal->rlim,
+	       sizeof(current->signal->rlim));
+
+#ifndef DDE_LINUX
+	atomic_inc(&init_cred.usage);
+	commit_creds(&init_cred);
+#endif
+	write_unlock_irq(&tasklist_lock);
+}
+
+void __set_special_pids(struct pid *pid)
+{
+	struct task_struct *curr = current->group_leader;
+	pid_t nr = pid_nr(pid);
+
+	if (task_session(curr) != pid) {
+		change_pid(curr, PIDTYPE_SID, pid);
+		set_task_session(curr, nr);
+	}
+	if (task_pgrp(curr) != pid) {
+		change_pid(curr, PIDTYPE_PGID, pid);
+		set_task_pgrp(curr, nr);
+	}
+}
+
+static void set_special_pids(struct pid *pid)
+{
+	write_lock_irq(&tasklist_lock);
+	__set_special_pids(pid);
+	write_unlock_irq(&tasklist_lock);
+}
+
+/*
+ * Let kernel threads use this to say that they
+ * allow a certain signal (since daemonize() will
+ * have disabled all of them by default).
+ */
+int allow_signal(int sig)
+{
+	if (!valid_signal(sig) || sig < 1)
+		return -EINVAL;
+
+	spin_lock_irq(&current->sighand->siglock);
+	sigdelset(&current->blocked, sig);
+	if (!current->mm) {
+		/* Kernel threads handle their own signals.
+		   Let the signal code know it'll be handled, so
+		   that they don't get converted to SIGKILL or
+		   just silently dropped */
+		current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
+	}
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+	return 0;
+}
+
+EXPORT_SYMBOL(allow_signal);
+
+int disallow_signal(int sig)
+{
+	if (!valid_signal(sig) || sig < 1)
+		return -EINVAL;
+
+	spin_lock_irq(&current->sighand->siglock);
+	current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+	return 0;
+}
+
+EXPORT_SYMBOL(disallow_signal);
+
+/*
+ *	Put all the gunge required to become a kernel thread without
+ *	attached user resources in one place where it belongs.
+ */
+
+void daemonize(const char *name, ...)
+{
+	va_list args;
+	struct fs_struct *fs;
+	sigset_t blocked;
+
+	va_start(args, name);
+	vsnprintf(current->comm, sizeof(current->comm), name, args);
+	va_end(args);
+
+	/*
+	 * If we were started as result of loading a module, close all of the
+	 * user space pages.  We don't need them, and if we didn't close them
+	 * they would be locked into memory.
+	 */
+	exit_mm(current);
+	/*
+	 * We don't want to have TIF_FREEZE set if the system-wide hibernation
+	 * or suspend transition begins right now.
+	 */
+	current->flags |= (PF_NOFREEZE | PF_KTHREAD);
+
+	if (current->nsproxy != &init_nsproxy) {
+		get_nsproxy(&init_nsproxy);
+		switch_task_namespaces(current, &init_nsproxy);
+	}
+	set_special_pids(&init_struct_pid);
+	proc_clear_tty(current);
+
+	/* Block and flush all signals */
+	sigfillset(&blocked);
+	sigprocmask(SIG_BLOCK, &blocked, NULL);
+	flush_signals(current);
+
+	/* Become as one with the init task */
+
+	exit_fs(current);	/* current->fs->count--; */
+	fs = init_task.fs;
+	current->fs = fs;
+	atomic_inc(&fs->count);
+
+	exit_files(current);
+	current->files = init_task.files;
+	atomic_inc(&current->files->count);
+
+	reparent_to_kthreadd();
+}
+
+EXPORT_SYMBOL(daemonize);
+
+static void close_files(struct files_struct * files)
+{
+	int i, j;
+	struct fdtable *fdt;
+
+	j = 0;
+
+	/*
+	 * It is safe to dereference the fd table without RCU or
+	 * ->file_lock because this is the last reference to the
+	 * files structure.
+	 */
+	fdt = files_fdtable(files);
+	for (;;) {
+		unsigned long set;
+		i = j * __NFDBITS;
+		if (i >= fdt->max_fds)
+			break;
+		set = fdt->open_fds->fds_bits[j++];
+		while (set) {
+			if (set & 1) {
+				struct file * file = xchg(&fdt->fd[i], NULL);
+				if (file) {
+					filp_close(file, files);
+					cond_resched();
+				}
+			}
+			i++;
+			set >>= 1;
+		}
+	}
+}
+
+struct files_struct *get_files_struct(struct task_struct *task)
+{
+	struct files_struct *files;
+
+	task_lock(task);
+	files = task->files;
+	if (files)
+		atomic_inc(&files->count);
+	task_unlock(task);
+
+	return files;
+}
+
+void put_files_struct(struct files_struct *files)
+{
+	struct fdtable *fdt;
+
+	if (atomic_dec_and_test(&files->count)) {
+		close_files(files);
+		/*
+		 * Free the fd and fdset arrays if we expanded them.
+		 * If the fdtable was embedded, pass files for freeing
+		 * at the end of the RCU grace period. Otherwise,
+		 * you can free files immediately.
+		 */
+		fdt = files_fdtable(files);
+		if (fdt != &files->fdtab)
+			kmem_cache_free(files_cachep, files);
+		free_fdtable(fdt);
+	}
+}
+
+void reset_files_struct(struct files_struct *files)
+{
+	struct task_struct *tsk = current;
+	struct files_struct *old;
+
+	old = tsk->files;
+	task_lock(tsk);
+	tsk->files = files;
+	task_unlock(tsk);
+	put_files_struct(old);
+}
+
+void exit_files(struct task_struct *tsk)
+{
+	struct files_struct * files = tsk->files;
+
+	if (files) {
+		task_lock(tsk);
+		tsk->files = NULL;
+		task_unlock(tsk);
+		put_files_struct(files);
+	}
+}
+
+void put_fs_struct(struct fs_struct *fs)
+{
+	/* No need to hold fs->lock if we are killing it */
+	if (atomic_dec_and_test(&fs->count)) {
+		path_put(&fs->root);
+		path_put(&fs->pwd);
+		kmem_cache_free(fs_cachep, fs);
+	}
+}
+
+void exit_fs(struct task_struct *tsk)
+{
+	struct fs_struct * fs = tsk->fs;
+
+	if (fs) {
+		task_lock(tsk);
+		tsk->fs = NULL;
+		task_unlock(tsk);
+		put_fs_struct(fs);
+	}
+}
+
+EXPORT_SYMBOL_GPL(exit_fs);
+
+#ifdef CONFIG_MM_OWNER
+/*
+ * Task p is exiting and it owned mm, lets find a new owner for it
+ */
+static inline int
+mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
+{
+	/*
+	 * If there are other users of the mm and the owner (us) is exiting
+	 * we need to find a new owner to take on the responsibility.
+	 */
+	if (atomic_read(&mm->mm_users) <= 1)
+		return 0;
+	if (mm->owner != p)
+		return 0;
+	return 1;
+}
+
+void mm_update_next_owner(struct mm_struct *mm)
+{
+	struct task_struct *c, *g, *p = current;
+
+retry:
+	if (!mm_need_new_owner(mm, p))
+		return;
+
+	read_lock(&tasklist_lock);
+	/*
+	 * Search in the children
+	 */
+	list_for_each_entry(c, &p->children, sibling) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	}
+
+	/*
+	 * Search in the siblings
+	 */
+	list_for_each_entry(c, &p->parent->children, sibling) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	}
+
+	/*
+	 * Search through everything else. We should not get
+	 * here often
+	 */
+	do_each_thread(g, c) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	} while_each_thread(g, c);
+
+	read_unlock(&tasklist_lock);
+	/*
+	 * We found no owner yet mm_users > 1: this implies that we are
+	 * most likely racing with swapoff (try_to_unuse()) or /proc or
+	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL.
+	 */
+	mm->owner = NULL;
+	return;
+
+assign_new_owner:
+	BUG_ON(c == p);
+	get_task_struct(c);
+	/*
+	 * The task_lock protects c->mm from changing.
+	 * We always want mm->owner->mm == mm
+	 */
+	task_lock(c);
+	/*
+	 * Delay read_unlock() till we have the task_lock()
+	 * to ensure that c does not slip away underneath us
+	 */
+	read_unlock(&tasklist_lock);
+	if (c->mm != mm) {
+		task_unlock(c);
+		put_task_struct(c);
+		goto retry;
+	}
+	mm->owner = c;
+	task_unlock(c);
+	put_task_struct(c);
+}
+#endif /* CONFIG_MM_OWNER */
+
+/*
+ * Turn us into a lazy TLB process if we
+ * aren't already..
+ */
+static void exit_mm(struct task_struct * tsk)
+{
+	struct mm_struct *mm = tsk->mm;
+	struct core_state *core_state;
+
+	mm_release(tsk, mm);
+	if (!mm)
+		return;
+	/*
+	 * Serialize with any possible pending coredump.
+	 * We must hold mmap_sem around checking core_state
+	 * and clearing tsk->mm.  The core-inducing thread
+	 * will increment ->nr_threads for each thread in the
+	 * group with ->mm != NULL.
+	 */
+	down_read(&mm->mmap_sem);
+	core_state = mm->core_state;
+	if (core_state) {
+		struct core_thread self;
+		up_read(&mm->mmap_sem);
+
+		self.task = tsk;
+		self.next = xchg(&core_state->dumper.next, &self);
+		/*
+		 * Implies mb(), the result of xchg() must be visible
+		 * to core_state->dumper.
+		 */
+		if (atomic_dec_and_test(&core_state->nr_threads))
+			complete(&core_state->startup);
+
+		for (;;) {
+			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+			if (!self.task) /* see coredump_finish() */
+				break;
+			schedule();
+		}
+		__set_task_state(tsk, TASK_RUNNING);
+		down_read(&mm->mmap_sem);
+	}
+	atomic_inc(&mm->mm_count);
+	BUG_ON(mm != tsk->active_mm);
+	/* more a memory barrier than a real lock */
+	task_lock(tsk);
+	tsk->mm = NULL;
+	up_read(&mm->mmap_sem);
+	enter_lazy_tlb(mm, current);
+	/* We don't want this task to be frozen prematurely */
+	clear_freeze_flag(tsk);
+	task_unlock(tsk);
+	mm_update_next_owner(mm);
+	mmput(mm);
+}
+
+/*
+ * Return nonzero if @parent's children should reap themselves.
+ *
+ * Called with write_lock_irq(&tasklist_lock) held.
+ */
+static int ignoring_children(struct task_struct *parent)
+{
+	int ret;
+	struct sighand_struct *psig = parent->sighand;
+	unsigned long flags;
+	spin_lock_irqsave(&psig->siglock, flags);
+	ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
+	       (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
+	spin_unlock_irqrestore(&psig->siglock, flags);
+	return ret;
+}
+
+/*
+ * Detach all tasks we were using ptrace on.
+ * Any that need to be release_task'd are put on the @dead list.
+ *
+ * Called with write_lock(&tasklist_lock) held.
+ */
+static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
+{
+	struct task_struct *p, *n;
+	int ign = -1;
+
+	list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
+		__ptrace_unlink(p);
+
+		if (p->exit_state != EXIT_ZOMBIE)
+			continue;
+
+		/*
+		 * If it's a zombie, our attachedness prevented normal
+		 * parent notification or self-reaping.  Do notification
+		 * now if it would have happened earlier.  If it should
+		 * reap itself, add it to the @dead list.  We can't call
+		 * release_task() here because we already hold tasklist_lock.
+		 *
+		 * If it's our own child, there is no notification to do.
+		 * But if our normal children self-reap, then this child
+		 * was prevented by ptrace and we must reap it now.
+		 */
+		if (!task_detached(p) && thread_group_empty(p)) {
+			if (!same_thread_group(p->real_parent, parent))
+				do_notify_parent(p, p->exit_signal);
+			else {
+				if (ign < 0)
+					ign = ignoring_children(parent);
+				if (ign)
+					p->exit_signal = -1;
+			}
+		}
+
+		if (task_detached(p)) {
+			/*
+			 * Mark it as in the process of being reaped.
+			 */
+			p->exit_state = EXIT_DEAD;
+			list_add(&p->ptrace_entry, dead);
+		}
+	}
+}
+
+/*
+ * Finish up exit-time ptrace cleanup.
+ *
+ * Called without locks.
+ */
+static void ptrace_exit_finish(struct task_struct *parent,
+			       struct list_head *dead)
+{
+	struct task_struct *p, *n;
+
+	BUG_ON(!list_empty(&parent->ptraced));
+
+	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
+}
+
+static void reparent_thread(struct task_struct *p, struct task_struct *father)
+{
+	if (p->pdeath_signal)
+		/* We already hold the tasklist_lock here.  */
+		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
+
+	list_move_tail(&p->sibling, &p->real_parent->children);
+
+	/* If this is a threaded reparent there is no need to
+	 * notify anyone anything has happened.
+	 */
+	if (same_thread_group(p->real_parent, father))
+		return;
+
+	/* We don't want people slaying init.  */
+	if (!task_detached(p))
+		p->exit_signal = SIGCHLD;
+
+	/* If we'd notified the old parent about this child's death,
+	 * also notify the new parent.
+	 */
+	if (!ptrace_reparented(p) &&
+	    p->exit_state == EXIT_ZOMBIE &&
+	    !task_detached(p) && thread_group_empty(p))
+		do_notify_parent(p, p->exit_signal);
+
+	kill_orphaned_pgrp(p, father);
+}
+
+/*
+ * When we die, we re-parent all our children.
+ * Try to give them to another thread in our thread
+ * group, and if no such member exists, give it to
+ * the child reaper process (ie "init") in our pid
+ * space.
+ */
+static struct task_struct *find_new_reaper(struct task_struct *father)
+{
+	struct pid_namespace *pid_ns = task_active_pid_ns(father);
+	struct task_struct *thread;
+
+	thread = father;
+	while_each_thread(father, thread) {
+		if (thread->flags & PF_EXITING)
+			continue;
+		if (unlikely(pid_ns->child_reaper == father))
+			pid_ns->child_reaper = thread;
+		return thread;
+	}
+
+	if (unlikely(pid_ns->child_reaper == father)) {
+		write_unlock_irq(&tasklist_lock);
+		if (unlikely(pid_ns == &init_pid_ns))
+			panic("Attempted to kill init!");
+
+		zap_pid_ns_processes(pid_ns);
+		write_lock_irq(&tasklist_lock);
+		/*
+		 * We can not clear ->child_reaper or leave it alone.
+		 * There may by stealth EXIT_DEAD tasks on ->children,
+		 * forget_original_parent() must move them somewhere.
+		 */
+		pid_ns->child_reaper = init_pid_ns.child_reaper;
+	}
+
+	return pid_ns->child_reaper;
+}
+
+static void forget_original_parent(struct task_struct *father)
+{
+	struct task_struct *p, *n, *reaper;
+	LIST_HEAD(ptrace_dead);
+
+	write_lock_irq(&tasklist_lock);
+	reaper = find_new_reaper(father);
+	/*
+	 * First clean up ptrace if we were using it.
+	 */
+	ptrace_exit(father, &ptrace_dead);
+
+	list_for_each_entry_safe(p, n, &father->children, sibling) {
+		p->real_parent = reaper;
+		if (p->parent == father) {
+			BUG_ON(p->ptrace);
+			p->parent = p->real_parent;
+		}
+		reparent_thread(p, father);
+	}
+
+	write_unlock_irq(&tasklist_lock);
+	BUG_ON(!list_empty(&father->children));
+
+	ptrace_exit_finish(father, &ptrace_dead);
+}
+
+/*
+ * Send signals to all our closest relatives so that they know
+ * to properly mourn us..
+ */
+static void exit_notify(struct task_struct *tsk, int group_dead)
+{
+	int signal;
+	void *cookie;
+
+	/*
+	 * This does two things:
+	 *
+  	 * A.  Make init inherit all the child processes
+	 * B.  Check to see if any process groups have become orphaned
+	 *	as a result of our exiting, and if they have any stopped
+	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
+	 */
+	forget_original_parent(tsk);
+	exit_task_namespaces(tsk);
+
+	write_lock_irq(&tasklist_lock);
+	if (group_dead)
+		kill_orphaned_pgrp(tsk->group_leader, NULL);
+
+	/* Let father know we died
+	 *
+	 * Thread signals are configurable, but you aren't going to use
+	 * that to send signals to arbitary processes.
+	 * That stops right now.
+	 *
+	 * If the parent exec id doesn't match the exec id we saved
+	 * when we started then we know the parent has changed security
+	 * domain.
+	 *
+	 * If our self_exec id doesn't match our parent_exec_id then
+	 * we have changed execution domain as these two values started
+	 * the same after a fork.
+	 */
+	if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
+	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
+	     tsk->self_exec_id != tsk->parent_exec_id) &&
+	    !capable(CAP_KILL))
+		tsk->exit_signal = SIGCHLD;
+
+	signal = tracehook_notify_death(tsk, &cookie, group_dead);
+	if (signal >= 0)
+		signal = do_notify_parent(tsk, signal);
+
+	tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
+
+	/* mt-exec, de_thread() is waiting for us */
+	if (thread_group_leader(tsk) &&
+	    tsk->signal->group_exit_task &&
+	    tsk->signal->notify_count < 0)
+		wake_up_process(tsk->signal->group_exit_task);
+
+	write_unlock_irq(&tasklist_lock);
+
+	tracehook_report_death(tsk, signal, cookie, group_dead);
+
+	/* If the process is dead, release it - nobody will wait for it */
+	if (signal == DEATH_REAP)
+		release_task(tsk);
+}
+
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static void check_stack_usage(void)
+{
+	static DEFINE_SPINLOCK(low_water_lock);
+	static int lowest_to_date = THREAD_SIZE;
+	unsigned long *n = end_of_stack(current);
+	unsigned long free;
+
+	while (*n == 0)
+		n++;
+	free = (unsigned long)n - (unsigned long)end_of_stack(current);
+
+	if (free >= lowest_to_date)
+		return;
+
+	spin_lock(&low_water_lock);
+	if (free < lowest_to_date) {
+		printk(KERN_WARNING "%s used greatest stack depth: %lu bytes "
+				"left\n",
+				current->comm, free);
+		lowest_to_date = free;
+	}
+	spin_unlock(&low_water_lock);
+}
+#else
+static inline void check_stack_usage(void) {}
+#endif
+
+NORET_TYPE void do_exit(long code)
+{
+	struct task_struct *tsk = current;
+	int group_dead;
+
+	profile_task_exit(tsk);
+
+	WARN_ON(atomic_read(&tsk->fs_excl));
+
+	if (unlikely(in_interrupt()))
+		panic("Aiee, killing interrupt handler!");
+	if (unlikely(!tsk->pid))
+		panic("Attempted to kill the idle task!");
+
+	tracehook_report_exit(&code);
+
+	/*
+	 * We're taking recursive faults here in do_exit. Safest is to just
+	 * leave this task alone and wait for reboot.
+	 */
+	if (unlikely(tsk->flags & PF_EXITING)) {
+		printk(KERN_ALERT
+			"Fixing recursive fault but reboot is needed!\n");
+		/*
+		 * We can do this unlocked here. The futex code uses
+		 * this flag just to verify whether the pi state
+		 * cleanup has been done or not. In the worst case it
+		 * loops once more. We pretend that the cleanup was
+		 * done as there is no way to return. Either the
+		 * OWNER_DIED bit is set by now or we push the blocked
+		 * task into the wait for ever nirwana as well.
+		 */
+		tsk->flags |= PF_EXITPIDONE;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule();
+	}
+
+	exit_signals(tsk);  /* sets PF_EXITING */
+	/*
+	 * tsk->flags are checked in the futex code to protect against
+	 * an exiting task cleaning up the robust pi futexes.
+	 */
+	smp_mb();
+	spin_unlock_wait(&tsk->pi_lock);
+
+	if (unlikely(in_atomic()))
+		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
+				current->comm, task_pid_nr(current),
+				preempt_count());
+
+	acct_update_integrals(tsk);
+
+	group_dead = atomic_dec_and_test(&tsk->signal->live);
+	if (group_dead) {
+		hrtimer_cancel(&tsk->signal->real_timer);
+		exit_itimers(tsk->signal);
+	}
+	acct_collect(code, group_dead);
+	if (group_dead)
+		tty_audit_exit();
+	if (unlikely(tsk->audit_context))
+		audit_free(tsk);
+
+	tsk->exit_code = code;
+	taskstats_exit(tsk, group_dead);
+
+	exit_mm(tsk);
+
+	if (group_dead)
+		acct_process();
+	trace_sched_process_exit(tsk);
+
+	exit_sem(tsk);
+	exit_files(tsk);
+	exit_fs(tsk);
+	check_stack_usage();
+	exit_thread();
+	cgroup_exit(tsk, 1);
+
+	if (group_dead && tsk->signal->leader)
+		disassociate_ctty(1);
+
+	module_put(task_thread_info(tsk)->exec_domain->module);
+	if (tsk->binfmt)
+		module_put(tsk->binfmt->module);
+
+	proc_exit_connector(tsk);
+	exit_notify(tsk, group_dead);
+#ifdef CONFIG_NUMA
+	mpol_put(tsk->mempolicy);
+	tsk->mempolicy = NULL;
+#endif
+#ifdef CONFIG_FUTEX
+	/*
+	 * This must happen late, after the PID is not
+	 * hashed anymore:
+	 */
+	if (unlikely(!list_empty(&tsk->pi_state_list)))
+		exit_pi_state_list(tsk);
+	if (unlikely(current->pi_state_cache))
+		kfree(current->pi_state_cache);
+#endif
+	/*
+	 * Make sure we are holding no locks:
+	 */
+	debug_check_no_locks_held(tsk);
+	/*
+	 * We can do this unlocked here. The futex code uses this flag
+	 * just to verify whether the pi state cleanup has been done
+	 * or not. In the worst case it loops once more.
+	 */
+	tsk->flags |= PF_EXITPIDONE;
+
+	if (tsk->io_context)
+		exit_io_context();
+
+	if (tsk->splice_pipe)
+		__free_pipe_info(tsk->splice_pipe);
+
+	preempt_disable();
+	/* causes final put_task_struct in finish_task_switch(). */
+	tsk->state = TASK_DEAD;
+	schedule();
+	BUG();
+	/* Avoid "noreturn function does return".  */
+	for (;;)
+		cpu_relax();	/* For when BUG is null */
+}
+
+EXPORT_SYMBOL_GPL(do_exit);
+
+#endif /* !DDE_LINUX */
+
+NORET_TYPE void complete_and_exit(struct completion *comp, long code)
+{
+	if (comp)
+		complete(comp);
+
+	do_exit(code);
+}
+
+EXPORT_SYMBOL(complete_and_exit);
+
+#ifndef DDE_LINUX
+SYSCALL_DEFINE1(exit, int, error_code)
+{
+	do_exit((error_code&0xff)<<8);
+}
+
+/*
+ * Take down every thread in the group.  This is called by fatal signals
+ * as well as by sys_exit_group (below).
+ */
+NORET_TYPE void
+do_group_exit(int exit_code)
+{
+	struct signal_struct *sig = current->signal;
+
+	BUG_ON(exit_code & 0x80); /* core dumps don't get here */
+
+	if (signal_group_exit(sig))
+		exit_code = sig->group_exit_code;
+	else if (!thread_group_empty(current)) {
+		struct sighand_struct *const sighand = current->sighand;
+		spin_lock_irq(&sighand->siglock);
+		if (signal_group_exit(sig))
+			/* Another thread got here before we took the lock.  */
+			exit_code = sig->group_exit_code;
+		else {
+			sig->group_exit_code = exit_code;
+			sig->flags = SIGNAL_GROUP_EXIT;
+			zap_other_threads(current);
+		}
+		spin_unlock_irq(&sighand->siglock);
+	}
+
+	do_exit(exit_code);
+	/* NOTREACHED */
+}
+
+/*
+ * this kills every thread in the thread group. Note that any externally
+ * wait4()-ing process will get the correct exit code - even if this
+ * thread is not the thread group leader.
+ */
+SYSCALL_DEFINE1(exit_group, int, error_code)
+{
+	do_group_exit((error_code & 0xff) << 8);
+	/* NOTREACHED */
+	return 0;
+}
+
+static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+{
+	struct pid *pid = NULL;
+	if (type == PIDTYPE_PID)
+		pid = task->pids[type].pid;
+	else if (type < PIDTYPE_MAX)
+		pid = task->group_leader->pids[type].pid;
+	return pid;
+}
+
+static int eligible_child(enum pid_type type, struct pid *pid, int options,
+			  struct task_struct *p)
+{
+	int err;
+
+	if (type < PIDTYPE_MAX) {
+		if (task_pid_type(p, type) != pid)
+			return 0;
+	}
+
+	/* Wait for all children (clone and not) if __WALL is set;
+	 * otherwise, wait for clone children *only* if __WCLONE is
+	 * set; otherwise, wait for non-clone children *only*.  (Note:
+	 * A "clone" child here is one that reports to its parent
+	 * using a signal other than SIGCHLD.) */
+	if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
+	    && !(options & __WALL))
+		return 0;
+
+	err = security_task_wait(p);
+	if (err)
+		return err;
+
+	return 1;
+}
+
+static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
+			       int why, int status,
+			       struct siginfo __user *infop,
+			       struct rusage __user *rusagep)
+{
+	int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;
+
+	put_task_struct(p);
+	if (!retval)
+		retval = put_user(SIGCHLD, &infop->si_signo);
+	if (!retval)
+		retval = put_user(0, &infop->si_errno);
+	if (!retval)
+		retval = put_user((short)why, &infop->si_code);
+	if (!retval)
+		retval = put_user(pid, &infop->si_pid);
+	if (!retval)
+		retval = put_user(uid, &infop->si_uid);
+	if (!retval)
+		retval = put_user(status, &infop->si_status);
+	if (!retval)
+		retval = pid;
+	return retval;
+}
+
+/*
+ * Handle sys_wait4 work for one task in state EXIT_ZOMBIE.  We hold
+ * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
+ * the lock and this task is uninteresting.  If we return nonzero, we have
+ * released the lock and the system call should return.
+ */
+static int wait_task_zombie(struct task_struct *p, int options,
+			    struct siginfo __user *infop,
+			    int __user *stat_addr, struct rusage __user *ru)
+{
+	unsigned long state;
+	int retval, status, traced;
+	pid_t pid = task_pid_vnr(p);
+	uid_t uid = __task_cred(p)->uid;
+
+	if (!likely(options & WEXITED))
+		return 0;
+
+	if (unlikely(options & WNOWAIT)) {
+		int exit_code = p->exit_code;
+		int why, status;
+
+		get_task_struct(p);
+		read_unlock(&tasklist_lock);
+		if ((exit_code & 0x7f) == 0) {
+			why = CLD_EXITED;
+			status = exit_code >> 8;
+		} else {
+			why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
+			status = exit_code & 0x7f;
+		}
+		return wait_noreap_copyout(p, pid, uid, why,
+					   status, infop, ru);
+	}
+
+	/*
+	 * Try to move the task's state to DEAD
+	 * only one thread is allowed to do this:
+	 */
+	state = xchg(&p->exit_state, EXIT_DEAD);
+	if (state != EXIT_ZOMBIE) {
+		BUG_ON(state != EXIT_DEAD);
+		return 0;
+	}
+
+	traced = ptrace_reparented(p);
+
+	if (likely(!traced)) {
+		struct signal_struct *psig;
+		struct signal_struct *sig;
+		struct task_cputime cputime;
+
+		/*
+		 * The resource counters for the group leader are in its
+		 * own task_struct.  Those for dead threads in the group
+		 * are in its signal_struct, as are those for the child
+		 * processes it has previously reaped.  All these
+		 * accumulate in the parent's signal_struct c* fields.
+		 *
+		 * We don't bother to take a lock here to protect these
+		 * p->signal fields, because they are only touched by
+		 * __exit_signal, which runs with tasklist_lock
+		 * write-locked anyway, and so is excluded here.  We do
+		 * need to protect the access to p->parent->signal fields,
+		 * as other threads in the parent group can be right
+		 * here reaping other children at the same time.
+		 *
+		 * We use thread_group_cputime() to get times for the thread
+		 * group, which consolidates times for all threads in the
+		 * group including the group leader.
+		 */
+		thread_group_cputime(p, &cputime);
+		spin_lock_irq(&p->parent->sighand->siglock);
+		psig = p->parent->signal;
+		sig = p->signal;
+		psig->cutime =
+			cputime_add(psig->cutime,
+			cputime_add(cputime.utime,
+				    sig->cutime));
+		psig->cstime =
+			cputime_add(psig->cstime,
+			cputime_add(cputime.stime,
+				    sig->cstime));
+		psig->cgtime =
+			cputime_add(psig->cgtime,
+			cputime_add(p->gtime,
+			cputime_add(sig->gtime,
+				    sig->cgtime)));
+		psig->cmin_flt +=
+			p->min_flt + sig->min_flt + sig->cmin_flt;
+		psig->cmaj_flt +=
+			p->maj_flt + sig->maj_flt + sig->cmaj_flt;
+		psig->cnvcsw +=
+			p->nvcsw + sig->nvcsw + sig->cnvcsw;
+		psig->cnivcsw +=
+			p->nivcsw + sig->nivcsw + sig->cnivcsw;
+		psig->cinblock +=
+			task_io_get_inblock(p) +
+			sig->inblock + sig->cinblock;
+		psig->coublock +=
+			task_io_get_oublock(p) +
+			sig->oublock + sig->coublock;
+		task_io_accounting_add(&psig->ioac, &p->ioac);
+		task_io_accounting_add(&psig->ioac, &sig->ioac);
+		spin_unlock_irq(&p->parent->sighand->siglock);
+	}
+
+	/*
+	 * Now we are sure this task is interesting, and no other
+	 * thread can reap it because we set its state to EXIT_DEAD.
+	 */
+	read_unlock(&tasklist_lock);
+
+	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+	status = (p->signal->flags & SIGNAL_GROUP_EXIT)
+		? p->signal->group_exit_code : p->exit_code;
+	if (!retval && stat_addr)
+		retval = put_user(status, stat_addr);
+	if (!retval && infop)
+		retval = put_user(SIGCHLD, &infop->si_signo);
+	if (!retval && infop)
+		retval = put_user(0, &infop->si_errno);
+	if (!retval && infop) {
+		int why;
+
+		if ((status & 0x7f) == 0) {
+			why = CLD_EXITED;
+			status >>= 8;
+		} else {
+			why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED;
+			status &= 0x7f;
+		}
+		retval = put_user((short)why, &infop->si_code);
+		if (!retval)
+			retval = put_user(status, &infop->si_status);
+	}
+	if (!retval && infop)
+		retval = put_user(pid, &infop->si_pid);
+	if (!retval && infop)
+		retval = put_user(uid, &infop->si_uid);
+	if (!retval)
+		retval = pid;
+
+	if (traced) {
+		write_lock_irq(&tasklist_lock);
+		/* We dropped tasklist, ptracer could die and untrace */
+		ptrace_unlink(p);
+		/*
+		 * If this is not a detached task, notify the parent.
+		 * If it's still not detached after that, don't release
+		 * it now.
+		 */
+		if (!task_detached(p)) {
+			do_notify_parent(p, p->exit_signal);
+			if (!task_detached(p)) {
+				p->exit_state = EXIT_ZOMBIE;
+				p = NULL;
+			}
+		}
+		write_unlock_irq(&tasklist_lock);
+	}
+	if (p != NULL)
+		release_task(p);
+
+	return retval;
+}
+
+/*
+ * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
+ * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
+ * the lock and this task is uninteresting.  If we return nonzero, we have
+ * released the lock and the system call should return.
+ */
+static int wait_task_stopped(int ptrace, struct task_struct *p,
+			     int options, struct siginfo __user *infop,
+			     int __user *stat_addr, struct rusage __user *ru)
+{
+	int retval, exit_code, why;
+	uid_t uid = 0; /* unneeded, required by compiler */
+	pid_t pid;
+
+	if (!(options & WUNTRACED))
+		return 0;
+
+	exit_code = 0;
+	spin_lock_irq(&p->sighand->siglock);
+
+	if (unlikely(!task_is_stopped_or_traced(p)))
+		goto unlock_sig;
+
+	if (!ptrace && p->signal->group_stop_count > 0)
+		/*
+		 * A group stop is in progress and this is the group leader.
+		 * We won't report until all threads have stopped.
+		 */
+		goto unlock_sig;
+
+	exit_code = p->exit_code;
+	if (!exit_code)
+		goto unlock_sig;
+
+	if (!unlikely(options & WNOWAIT))
+		p->exit_code = 0;
+
+	/* don't need the RCU readlock here as we're holding a spinlock */
+	uid = __task_cred(p)->uid;
+unlock_sig:
+	spin_unlock_irq(&p->sighand->siglock);
+	if (!exit_code)
+		return 0;
+
+	/*
+	 * Now we are pretty sure this task is interesting.
+	 * Make sure it doesn't get reaped out from under us while we
+	 * give up the lock and then examine it below.  We don't want to
+	 * keep holding onto the tasklist_lock while we call getrusage and
+	 * possibly take page faults for user memory.
+	 */
+	get_task_struct(p);
+	pid = task_pid_vnr(p);
+	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
+	read_unlock(&tasklist_lock);
+
+	if (unlikely(options & WNOWAIT))
+		return wait_noreap_copyout(p, pid, uid,
+					   why, exit_code,
+					   infop, ru);
+
+	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+	if (!retval && stat_addr)
+		retval = put_user((exit_code << 8) | 0x7f, stat_addr);
+	if (!retval && infop)
+		retval = put_user(SIGCHLD, &infop->si_signo);
+	if (!retval && infop)
+		retval = put_user(0, &infop->si_errno);
+	if (!retval && infop)
+		retval = put_user((short)why, &infop->si_code);
+	if (!retval && infop)
+		retval = put_user(exit_code, &infop->si_status);
+	if (!retval && infop)
+		retval = put_user(pid, &infop->si_pid);
+	if (!retval && infop)
+		retval = put_user(uid, &infop->si_uid);
+	if (!retval)
+		retval = pid;
+	put_task_struct(p);
+
+	BUG_ON(!retval);
+	return retval;
+}
+
+/*
+ * Handle do_wait work for one task in a live, non-stopped state.
+ * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
+ * the lock and this task is uninteresting.  If we return nonzero, we have
+ * released the lock and the system call should return.
+ */
+static int wait_task_continued(struct task_struct *p, int options,
+			       struct siginfo __user *infop,
+			       int __user *stat_addr, struct rusage __user *ru)
+{
+	int retval;
+	pid_t pid;
+	uid_t uid;
+
+	if (!unlikely(options & WCONTINUED))
+		return 0;
+
+	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
+		return 0;
+
+	spin_lock_irq(&p->sighand->siglock);
+	/* Re-check with the lock held.  */
+	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) {
+		spin_unlock_irq(&p->sighand->siglock);
+		return 0;
+	}
+	if (!unlikely(options & WNOWAIT))
+		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
+	uid = __task_cred(p)->uid;
+	spin_unlock_irq(&p->sighand->siglock);
+
+	pid = task_pid_vnr(p);
+	get_task_struct(p);
+	read_unlock(&tasklist_lock);
+
+	if (!infop) {
+		retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+		put_task_struct(p);
+		if (!retval && stat_addr)
+			retval = put_user(0xffff, stat_addr);
+		if (!retval)
+			retval = pid;
+	} else {
+		retval = wait_noreap_copyout(p, pid, uid,
+					     CLD_CONTINUED, SIGCONT,
+					     infop, ru);
+		BUG_ON(retval == 0);
+	}
+
+	return retval;
+}
+
+/*
+ * Consider @p for a wait by @parent.
+ *
+ * -ECHILD should be in *@notask_error before the first call.
+ * Returns nonzero for a final return, when we have unlocked tasklist_lock.
+ * Returns zero if the search for a child should continue;
+ * then *@notask_error is 0 if @p is an eligible child,
+ * or another error from security_task_wait(), or still -ECHILD.
+ */
+static int wait_consider_task(struct task_struct *parent, int ptrace,
+			      struct task_struct *p, int *notask_error,
+			      enum pid_type type, struct pid *pid, int options,
+			      struct siginfo __user *infop,
+			      int __user *stat_addr, struct rusage __user *ru)
+{
+	int ret = eligible_child(type, pid, options, p);
+	if (!ret)
+		return ret;
+
+	if (unlikely(ret < 0)) {
+		/*
+		 * If we have not yet seen any eligible child,
+		 * then let this error code replace -ECHILD.
+		 * A permission error will give the user a clue
+		 * to look for security policy problems, rather
+		 * than for mysterious wait bugs.
+		 */
+		if (*notask_error)
+			*notask_error = ret;
+	}
+
+	if (likely(!ptrace) && unlikely(p->ptrace)) {
+		/*
+		 * This child is hidden by ptrace.
+		 * We aren't allowed to see it now, but eventually we will.
+		 */
+		*notask_error = 0;
+		return 0;
+	}
+
+	if (p->exit_state == EXIT_DEAD)
+		return 0;
+
+	/*
+	 * We don't reap group leaders with subthreads.
+	 */
+	if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
+		return wait_task_zombie(p, options, infop, stat_addr, ru);
+
+	/*
+	 * It's stopped or running now, so it might
+	 * later continue, exit, or stop again.
+	 */
+	*notask_error = 0;
+
+	if (task_is_stopped_or_traced(p))
+		return wait_task_stopped(ptrace, p, options,
+					 infop, stat_addr, ru);
+
+	return wait_task_continued(p, options, infop, stat_addr, ru);
+}
+
+/*
+ * Do the work of do_wait() for one thread in the group, @tsk.
+ *
+ * -ECHILD should be in *@notask_error before the first call.
+ * Returns nonzero for a final return, when we have unlocked tasklist_lock.
+ * Returns zero if the search for a child should continue; then
+ * *@notask_error is 0 if there were any eligible children,
+ * or another error from security_task_wait(), or still -ECHILD.
+ */
+static int do_wait_thread(struct task_struct *tsk, int *notask_error,
+			  enum pid_type type, struct pid *pid, int options,
+			  struct siginfo __user *infop, int __user *stat_addr,
+			  struct rusage __user *ru)
+{
+	struct task_struct *p;
+
+	list_for_each_entry(p, &tsk->children, sibling) {
+		/*
+		 * Do not consider detached threads.
+		 */
+		if (!task_detached(p)) {
+			int ret = wait_consider_task(tsk, 0, p, notask_error,
+						     type, pid, options,
+						     infop, stat_addr, ru);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
+			  enum pid_type type, struct pid *pid, int options,
+			  struct siginfo __user *infop, int __user *stat_addr,
+			  struct rusage __user *ru)
+{
+	struct task_struct *p;
+
+	/*
+	 * Traditionally we see ptrace'd stopped tasks regardless of options.
+	 */
+	options |= WUNTRACED;
+
+	list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
+		int ret = wait_consider_task(tsk, 1, p, notask_error,
+					     type, pid, options,
+					     infop, stat_addr, ru);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static long do_wait(enum pid_type type, struct pid *pid, int options,
+		    struct siginfo __user *infop, int __user *stat_addr,
+		    struct rusage __user *ru)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	struct task_struct *tsk;
+	int retval;
+
+	trace_sched_process_wait(pid);
+
+	add_wait_queue(&current->signal->wait_chldexit,&wait);
+repeat:
+	/*
+	 * If there is nothing that can match our critiera just get out.
+	 * We will clear @retval to zero if we see any child that might later
+	 * match our criteria, even if we are not able to reap it yet.
+	 */
+	retval = -ECHILD;
+	if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
+		goto end;
+
+	current->state = TASK_INTERRUPTIBLE;
+	read_lock(&tasklist_lock);
+	tsk = current;
+	do {
+		int tsk_result = do_wait_thread(tsk, &retval,
+						type, pid, options,
+						infop, stat_addr, ru);
+		if (!tsk_result)
+			tsk_result = ptrace_do_wait(tsk, &retval,
+						    type, pid, options,
+						    infop, stat_addr, ru);
+		if (tsk_result) {
+			/*
+			 * tasklist_lock is unlocked and we have a final result.
+			 */
+			retval = tsk_result;
+			goto end;
+		}
+
+		if (options & __WNOTHREAD)
+			break;
+		tsk = next_thread(tsk);
+		BUG_ON(tsk->signal != current->signal);
+	} while (tsk != current);
+	read_unlock(&tasklist_lock);
+
+	if (!retval && !(options & WNOHANG)) {
+		retval = -ERESTARTSYS;
+		if (!signal_pending(current)) {
+			schedule();
+			goto repeat;
+		}
+	}
+
+end:
+	current->state = TASK_RUNNING;
+	remove_wait_queue(&current->signal->wait_chldexit,&wait);
+	if (infop) {
+		if (retval > 0)
+			retval = 0;
+		else {
+			/*
+			 * For a WNOHANG return, clear out all the fields
+			 * we would set so the user can easily tell the
+			 * difference.
+			 */
+			if (!retval)
+				retval = put_user(0, &infop->si_signo);
+			if (!retval)
+				retval = put_user(0, &infop->si_errno);
+			if (!retval)
+				retval = put_user(0, &infop->si_code);
+			if (!retval)
+				retval = put_user(0, &infop->si_pid);
+			if (!retval)
+				retval = put_user(0, &infop->si_uid);
+			if (!retval)
+				retval = put_user(0, &infop->si_status);
+		}
+	}
+	return retval;
+}
+
+SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
+		infop, int, options, struct rusage __user *, ru)
+{
+	struct pid *pid = NULL;
+	enum pid_type type;
+	long ret;
+
+	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
+		return -EINVAL;
+	if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
+		return -EINVAL;
+
+	switch (which) {
+	case P_ALL:
+		type = PIDTYPE_MAX;
+		break;
+	case P_PID:
+		type = PIDTYPE_PID;
+		if (upid <= 0)
+			return -EINVAL;
+		break;
+	case P_PGID:
+		type = PIDTYPE_PGID;
+		if (upid <= 0)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (type < PIDTYPE_MAX)
+		pid = find_get_pid(upid);
+	ret = do_wait(type, pid, options, infop, NULL, ru);
+	put_pid(pid);
+
+	/* avoid REGPARM breakage on x86: */
+	asmlinkage_protect(5, ret, which, upid, infop, options, ru);
+	return ret;
+}
+
+SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
+		int, options, struct rusage __user *, ru)
+{
+	struct pid *pid = NULL;
+	enum pid_type type;
+	long ret;
+
+	if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
+			__WNOTHREAD|__WCLONE|__WALL))
+		return -EINVAL;
+
+	if (upid == -1)
+		type = PIDTYPE_MAX;
+	else if (upid < 0) {
+		type = PIDTYPE_PGID;
+		pid = find_get_pid(-upid);
+	} else if (upid == 0) {
+		type = PIDTYPE_PGID;
+		pid = get_pid(task_pgrp(current));
+	} else /* upid > 0 */ {
+		type = PIDTYPE_PID;
+		pid = find_get_pid(upid);
+	}
+
+	ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru);
+	put_pid(pid);
+
+	/* avoid REGPARM breakage on x86: */
+	asmlinkage_protect(4, ret, upid, stat_addr, options, ru);
+	return ret;
+}
+
+#ifdef __ARCH_WANT_SYS_WAITPID
+
+/*
+ * sys_waitpid() remains for compatibility. waitpid() should be
+ * implemented by calling sys_wait4() from libc.a.
+ */
+SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
+{
+	return sys_wait4(pid, stat_addr, options, NULL);
+}
+
+#endif
+#endif
diff --git a/libdde-linux26/lib/src/kernel/irq/handle.c b/libdde-linux26/lib/src/kernel/irq/handle.c
new file mode 100644
index 00000000..ac7b14f8
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/irq/handle.c
@@ -0,0 +1,23 @@
+/*
+ * linux/kernel/irq/handle.c
+ *
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the core interrupt handling code.
+ *
+ * Detailed information is available in Documentation/DocBook/genericirq
+ *
+ */
+
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/rculist.h>
+#include <linux/hash.h>
+
+int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL_GPL(nr_irqs);
+
diff --git a/libdde-linux26/lib/src/kernel/resource.c b/libdde-linux26/lib/src/kernel/resource.c
new file mode 100644
index 00000000..3dd07a35
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/resource.c
@@ -0,0 +1,936 @@
+/*
+ *	linux/kernel/resource.c
+ *
+ * Copyright (C) 1999	Linus Torvalds
+ * Copyright (C) 1999	Martin Mares <mj@ucw.cz>
+ *
+ * Arbitrary resource management.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/device.h>
+#include <linux/pfn.h>
+#include <asm/io.h>
+
+
+struct resource ioport_resource = {
+	.name	= "PCI IO",
+	.start	= 0,
+	.end	= IO_SPACE_LIMIT,
+	.flags	= IORESOURCE_IO,
+};
+EXPORT_SYMBOL(ioport_resource);
+
+struct resource iomem_resource = {
+	.name	= "PCI mem",
+	.start	= 0,
+	.end	= -1,
+	.flags	= IORESOURCE_MEM,
+};
+EXPORT_SYMBOL(iomem_resource);
+
+static DEFINE_RWLOCK(resource_lock);
+
+static void *r_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct resource *p = v;
+	(*pos)++;
+	if (p->child)
+		return p->child;
+	while (!p->sibling && p->parent)
+		p = p->parent;
+	return p->sibling;
+}
+
+#ifdef CONFIG_PROC_FS
+
+enum { MAX_IORES_LEVEL = 5 };
+
+static void *r_start(struct seq_file *m, loff_t *pos)
+	__acquires(resource_lock)
+{
+	struct resource *p = m->private;
+	loff_t l = 0;
+	read_lock(&resource_lock);
+	for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
+		;
+	return p;
+}
+
+static void r_stop(struct seq_file *m, void *v)
+	__releases(resource_lock)
+{
+	read_unlock(&resource_lock);
+}
+
+static int r_show(struct seq_file *m, void *v)
+{
+	struct resource *root = m->private;
+	struct resource *r = v, *p;
+	int width = root->end < 0x10000 ? 4 : 8;
+	int depth;
+
+	for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent)
+		if (p->parent == root)
+			break;
+	seq_printf(m, "%*s%0*llx-%0*llx : %s\n",
+			depth * 2, "",
+			width, (unsigned long long) r->start,
+			width, (unsigned long long) r->end,
+			r->name ? r->name : "<BAD>");
+	return 0;
+}
+
+static const struct seq_operations resource_op = {
+	.start	= r_start,
+	.next	= r_next,
+	.stop	= r_stop,
+	.show	= r_show,
+};
+
+static int ioports_open(struct inode *inode, struct file *file)
+{
+	int res = seq_open(file, &resource_op);
+	if (!res) {
+		struct seq_file *m = file->private_data;
+		m->private = &ioport_resource;
+	}
+	return res;
+}
+
+static int iomem_open(struct inode *inode, struct file *file)
+{
+	int res = seq_open(file, &resource_op);
+	if (!res) {
+		struct seq_file *m = file->private_data;
+		m->private = &iomem_resource;
+	}
+	return res;
+}
+
+static const struct file_operations proc_ioports_operations = {
+	.open		= ioports_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static const struct file_operations proc_iomem_operations = {
+	.open		= iomem_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init ioresources_init(void)
+{
+	proc_create("ioports", 0, NULL, &proc_ioports_operations);
+	proc_create("iomem", 0, NULL, &proc_iomem_operations);
+	return 0;
+}
+__initcall(ioresources_init);
+
+#endif /* CONFIG_PROC_FS */
+
+/* Return the conflict entry if you can't request it */
+static struct resource * __request_resource(struct resource *root, struct resource *new)
+{
+	resource_size_t start = new->start;
+	resource_size_t end = new->end;
+	struct resource *tmp, **p;
+
+	if (end < start)
+		return root;
+	if (start < root->start)
+		return root;
+	if (end > root->end)
+		return root;
+	p = &root->child;
+	for (;;) {
+		tmp = *p;
+		if (!tmp || tmp->start > end) {
+			new->sibling = tmp;
+			*p = new;
+			new->parent = root;
+			return NULL;
+		}
+		p = &tmp->sibling;
+		if (tmp->end < start)
+			continue;
+		return tmp;
+	}
+}
+
+static int __release_resource(struct resource *old)
+{
+	struct resource *tmp, **p;
+
+	p = &old->parent->child;
+	for (;;) {
+		tmp = *p;
+		if (!tmp)
+			break;
+		if (tmp == old) {
+			*p = tmp->sibling;
+			old->parent = NULL;
+			return 0;
+		}
+		p = &tmp->sibling;
+	}
+	return -EINVAL;
+}
+
+/**
+ * request_resource - request and reserve an I/O or memory resource
+ * @root: root resource descriptor
+ * @new: resource descriptor desired by caller
+ *
+ * Returns 0 for success, negative error code on error.
+ */
+int request_resource(struct resource *root, struct resource *new)
+{
+	struct resource *conflict;
+
+	write_lock(&resource_lock);
+	conflict = __request_resource(root, new);
+	write_unlock(&resource_lock);
+	return conflict ? -EBUSY : 0;
+}
+
+EXPORT_SYMBOL(request_resource);
+
+/**
+ * release_resource - release a previously reserved resource
+ * @old: resource pointer
+ */
+int release_resource(struct resource *old)
+{
+	int retval;
+
+	write_lock(&resource_lock);
+	retval = __release_resource(old);
+	write_unlock(&resource_lock);
+	return retval;
+}
+
+EXPORT_SYMBOL(release_resource);
+
+#if defined(CONFIG_MEMORY_HOTPLUG) && !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
+/*
+ * Finds the lowest memory reosurce exists within [res->start.res->end)
+ * the caller must specify res->start, res->end, res->flags.
+ * If found, returns 0, res is overwritten, if not found, returns -1.
+ */
+static int find_next_system_ram(struct resource *res)
+{
+	resource_size_t start, end;
+	struct resource *p;
+
+	BUG_ON(!res);
+
+	start = res->start;
+	end = res->end;
+	BUG_ON(start >= end);
+
+	read_lock(&resource_lock);
+	for (p = iomem_resource.child; p ; p = p->sibling) {
+		/* system ram is just marked as IORESOURCE_MEM */
+		if (p->flags != res->flags)
+			continue;
+		if (p->start > end) {
+			p = NULL;
+			break;
+		}
+		if ((p->end >= start) && (p->start < end))
+			break;
+	}
+	read_unlock(&resource_lock);
+	if (!p)
+		return -1;
+	/* copy data */
+	if (res->start < p->start)
+		res->start = p->start;
+	if (res->end > p->end)
+		res->end = p->end;
+	return 0;
+}
+int
+walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
+			int (*func)(unsigned long, unsigned long, void *))
+{
+	struct resource res;
+	unsigned long pfn, len;
+	u64 orig_end;
+	int ret = -1;
+	res.start = (u64) start_pfn << PAGE_SHIFT;
+	res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
+	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	orig_end = res.end;
+	while ((res.start < res.end) && (find_next_system_ram(&res) >= 0)) {
+		pfn = (unsigned long)(res.start >> PAGE_SHIFT);
+		len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT);
+		ret = (*func)(pfn, len, arg);
+		if (ret)
+			break;
+		res.start = res.end + 1;
+		res.end = orig_end;
+	}
+	return ret;
+}
+
+#endif
+
+/*
+ * Find empty slot in the resource tree given range and alignment.
+ */
+static int find_resource(struct resource *root, struct resource *new,
+			 resource_size_t size, resource_size_t min,
+			 resource_size_t max, resource_size_t align,
+			 void (*alignf)(void *, struct resource *,
+					resource_size_t, resource_size_t),
+			 void *alignf_data)
+{
+	struct resource *this = root->child;
+
+	new->start = root->start;
+	/*
+	 * Skip past an allocated resource that starts at 0, since the assignment
+	 * of this->start - 1 to new->end below would cause an underflow.
+	 */
+	if (this && this->start == 0) {
+		new->start = this->end + 1;
+		this = this->sibling;
+	}
+	for(;;) {
+		if (this)
+			new->end = this->start - 1;
+		else
+			new->end = root->end;
+		if (new->start < min)
+			new->start = min;
+		if (new->end > max)
+			new->end = max;
+		new->start = ALIGN(new->start, align);
+		if (alignf)
+			alignf(alignf_data, new, size, align);
+		if (new->start < new->end && new->end - new->start >= size - 1) {
+			new->end = new->start + size - 1;
+			return 0;
+		}
+		if (!this)
+			break;
+		new->start = this->end + 1;
+		this = this->sibling;
+	}
+	return -EBUSY;
+}
+
+/**
+ * allocate_resource - allocate empty slot in the resource tree given range & alignment
+ * @root: root resource descriptor
+ * @new: resource descriptor desired by caller
+ * @size: requested resource region size
+ * @min: minimum size to allocate
+ * @max: maximum size to allocate
+ * @align: alignment requested, in bytes
+ * @alignf: alignment function, optional, called if not NULL
+ * @alignf_data: arbitrary data to pass to the @alignf function
+ */
+int allocate_resource(struct resource *root, struct resource *new,
+		      resource_size_t size, resource_size_t min,
+		      resource_size_t max, resource_size_t align,
+		      void (*alignf)(void *, struct resource *,
+				     resource_size_t, resource_size_t),
+		      void *alignf_data)
+{
+	int err;
+
+	write_lock(&resource_lock);
+	err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
+	if (err >= 0 && __request_resource(root, new))
+		err = -EBUSY;
+	write_unlock(&resource_lock);
+	return err;
+}
+
+EXPORT_SYMBOL(allocate_resource);
+
+/*
+ * Insert a resource into the resource tree. If successful, return NULL,
+ * otherwise return the conflicting resource (compare to __request_resource())
+ */
+static struct resource * __insert_resource(struct resource *parent, struct resource *new)
+{
+	struct resource *first, *next;
+
+	for (;; parent = first) {
+		first = __request_resource(parent, new);
+		if (!first)
+			return first;
+
+		if (first == parent)
+			return first;
+
+		if ((first->start > new->start) || (first->end < new->end))
+			break;
+		if ((first->start == new->start) && (first->end == new->end))
+			break;
+	}
+
+	for (next = first; ; next = next->sibling) {
+		/* Partial overlap? Bad, and unfixable */
+		if (next->start < new->start || next->end > new->end)
+			return next;
+		if (!next->sibling)
+			break;
+		if (next->sibling->start > new->end)
+			break;
+	}
+
+	new->parent = parent;
+	new->sibling = next->sibling;
+	new->child = first;
+
+	next->sibling = NULL;
+	for (next = first; next; next = next->sibling)
+		next->parent = new;
+
+	if (parent->child == first) {
+		parent->child = new;
+	} else {
+		next = parent->child;
+		while (next->sibling != first)
+			next = next->sibling;
+		next->sibling = new;
+	}
+	return NULL;
+}
+
+/**
+ * insert_resource - Inserts a resource in the resource tree
+ * @parent: parent of the new resource
+ * @new: new resource to insert
+ *
+ * Returns 0 on success, -EBUSY if the resource can't be inserted.
+ *
+ * This function is equivalent to request_resource when no conflict
+ * happens. If a conflict happens, and the conflicting resources
+ * entirely fit within the range of the new resource, then the new
+ * resource is inserted and the conflicting resources become children of
+ * the new resource.
+ */
+int insert_resource(struct resource *parent, struct resource *new)
+{
+	struct resource *conflict;
+
+	write_lock(&resource_lock);
+	conflict = __insert_resource(parent, new);
+	write_unlock(&resource_lock);
+	return conflict ? -EBUSY : 0;
+}
+
+/**
+ * insert_resource_expand_to_fit - Insert a resource into the resource tree
+ * @root: root resource descriptor
+ * @new: new resource to insert
+ *
+ * Insert a resource into the resource tree, possibly expanding it in order
+ * to make it encompass any conflicting resources.
+ */
+void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
+{
+	if (new->parent)
+		return;
+
+	write_lock(&resource_lock);
+	for (;;) {
+		struct resource *conflict;
+
+		conflict = __insert_resource(root, new);
+		if (!conflict)
+			break;
+		if (conflict == root)
+			break;
+
+		/* Ok, expand resource to cover the conflict, then try again .. */
+		if (conflict->start < new->start)
+			new->start = conflict->start;
+		if (conflict->end > new->end)
+			new->end = conflict->end;
+
+		printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
+	}
+	write_unlock(&resource_lock);
+}
+
+/**
+ * adjust_resource - modify a resource's start and size
+ * @res: resource to modify
+ * @start: new start value
+ * @size: new size
+ *
+ * Given an existing resource, change its start and size to match the
+ * arguments.  Returns 0 on success, -EBUSY if it can't fit.
+ * Existing children of the resource are assumed to be immutable.
+ */
+int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size)
+{
+	struct resource *tmp, *parent = res->parent;
+	resource_size_t end = start + size - 1;
+	int result = -EBUSY;
+
+	write_lock(&resource_lock);
+
+	if ((start < parent->start) || (end > parent->end))
+		goto out;
+
+	for (tmp = res->child; tmp; tmp = tmp->sibling) {
+		if ((tmp->start < start) || (tmp->end > end))
+			goto out;
+	}
+
+	if (res->sibling && (res->sibling->start <= end))
+		goto out;
+
+	tmp = parent->child;
+	if (tmp != res) {
+		while (tmp->sibling != res)
+			tmp = tmp->sibling;
+		if (start <= tmp->end)
+			goto out;
+	}
+
+	res->start = start;
+	res->end = end;
+	result = 0;
+
+ out:
+	write_unlock(&resource_lock);
+	return result;
+}
+
+static void __init __reserve_region_with_split(struct resource *root,
+		resource_size_t start, resource_size_t end,
+		const char *name)
+{
+	struct resource *parent = root;
+	struct resource *conflict;
+	struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC);
+
+	if (!res)
+		return;
+
+	res->name = name;
+	res->start = start;
+	res->end = end;
+	res->flags = IORESOURCE_BUSY;
+
+	for (;;) {
+		conflict = __request_resource(parent, res);
+		if (!conflict)
+			break;
+		if (conflict != parent) {
+			parent = conflict;
+			if (!(conflict->flags & IORESOURCE_BUSY))
+				continue;
+		}
+
+		/* Uhhuh, that didn't work out.. */
+		kfree(res);
+		res = NULL;
+		break;
+	}
+
+	if (!res) {
+		/* failed, split and try again */
+
+		/* conflict covered whole area */
+		if (conflict->start <= start && conflict->end >= end)
+			return;
+
+		if (conflict->start > start)
+			__reserve_region_with_split(root, start, conflict->start-1, name);
+		if (!(conflict->flags & IORESOURCE_BUSY)) {
+			resource_size_t common_start, common_end;
+
+			common_start = max(conflict->start, start);
+			common_end = min(conflict->end, end);
+			if (common_start < common_end)
+				__reserve_region_with_split(root, common_start, common_end, name);
+		}
+		if (conflict->end < end)
+			__reserve_region_with_split(root, conflict->end+1, end, name);
+	}
+
+}
+
+void __init reserve_region_with_split(struct resource *root,
+		resource_size_t start, resource_size_t end,
+		const char *name)
+{
+	write_lock(&resource_lock);
+	__reserve_region_with_split(root, start, end, name);
+	write_unlock(&resource_lock);
+}
+
+EXPORT_SYMBOL(adjust_resource);
+
+/**
+ * resource_alignment - calculate resource's alignment
+ * @res: resource pointer
+ *
+ * Returns alignment on success, 0 (invalid alignment) on failure.
+ */
+resource_size_t resource_alignment(struct resource *res)
+{
+	switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) {
+	case IORESOURCE_SIZEALIGN:
+		return resource_size(res);
+	case IORESOURCE_STARTALIGN:
+		return res->start;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * This is compatibility stuff for IO resources.
+ *
+ * Note how this, unlike the above, knows about
+ * the IO flag meanings (busy etc).
+ *
+ * request_region creates a new busy region.
+ *
+ * check_region returns non-zero if the area is already busy.
+ *
+ * release_region releases a matching busy region.
+ */
+
+#ifndef DDE_LINUX
+/**
+ * __request_region - create a new busy resource region
+ * @parent: parent resource descriptor
+ * @start: resource start address
+ * @n: resource region size
+ * @name: reserving caller's ID string
+ * @flags: IO resource flags
+ */
+struct resource * __request_region(struct resource *parent,
+				   resource_size_t start, resource_size_t n,
+				   const char *name, int flags)
+{
+	struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
+
+	if (!res)
+		return NULL;
+
+	res->name = name;
+	res->start = start;
+	res->end = start + n - 1;
+	res->flags = IORESOURCE_BUSY;
+	res->flags |= flags;
+
+	write_lock(&resource_lock);
+
+	for (;;) {
+		struct resource *conflict;
+
+		conflict = __request_resource(parent, res);
+		if (!conflict)
+			break;
+		if (conflict != parent) {
+			parent = conflict;
+			if (!(conflict->flags & IORESOURCE_BUSY))
+				continue;
+		}
+
+		/* Uhhuh, that didn't work out.. */
+		kfree(res);
+		res = NULL;
+		break;
+	}
+	write_unlock(&resource_lock);
+	return res;
+}
+EXPORT_SYMBOL(__request_region);
+
+/**
+ * __check_region - check if a resource region is busy or free
+ * @parent: parent resource descriptor
+ * @start: resource start address
+ * @n: resource region size
+ *
+ * Returns 0 if the region is free at the moment it is checked,
+ * returns %-EBUSY if the region is busy.
+ *
+ * NOTE:
+ * This function is deprecated because its use is racy.
+ * Even if it returns 0, a subsequent call to request_region()
+ * may fail because another driver etc. just allocated the region.
+ * Do NOT use it.  It will be removed from the kernel.
+ */
+int __check_region(struct resource *parent, resource_size_t start,
+			resource_size_t n)
+{
+	struct resource * res;
+
+	res = __request_region(parent, start, n, "check-region", 0);
+	if (!res)
+		return -EBUSY;
+
+	release_resource(res);
+	kfree(res);
+	return 0;
+}
+EXPORT_SYMBOL(__check_region);
+
+/**
+ * __release_region - release a previously reserved resource region
+ * @parent: parent resource descriptor
+ * @start: resource start address
+ * @n: resource region size
+ *
+ * The described resource region must match a currently busy region.
+ */
+void __release_region(struct resource *parent, resource_size_t start,
+			resource_size_t n)
+{
+	struct resource **p;
+	resource_size_t end;
+
+	p = &parent->child;
+	end = start + n - 1;
+
+	write_lock(&resource_lock);
+
+	for (;;) {
+		struct resource *res = *p;
+
+		if (!res)
+			break;
+		if (res->start <= start && res->end >= end) {
+			if (!(res->flags & IORESOURCE_BUSY)) {
+				p = &res->child;
+				continue;
+			}
+			if (res->start != start || res->end != end)
+				break;
+			*p = res->sibling;
+			write_unlock(&resource_lock);
+			kfree(res);
+			return;
+		}
+		p = &res->sibling;
+	}
+
+	write_unlock(&resource_lock);
+
+	printk(KERN_WARNING "Trying to free nonexistent resource "
+		"<%016llx-%016llx>\n", (unsigned long long)start,
+		(unsigned long long)end);
+}
+EXPORT_SYMBOL(__release_region);
+#endif /* DDE_LINUX */
+
+/*
+ * Managed region resource
+ */
+struct region_devres {
+	struct resource *parent;
+	resource_size_t start;
+	resource_size_t n;
+};
+
+static void devm_region_release(struct device *dev, void *res)
+{
+	struct region_devres *this = res;
+
+	__release_region(this->parent, this->start, this->n);
+}
+
+static int devm_region_match(struct device *dev, void *res, void *match_data)
+{
+	struct region_devres *this = res, *match = match_data;
+
+	return this->parent == match->parent &&
+		this->start == match->start && this->n == match->n;
+}
+
+struct resource * __devm_request_region(struct device *dev,
+				struct resource *parent, resource_size_t start,
+				resource_size_t n, const char *name)
+{
+	struct region_devres *dr = NULL;
+	struct resource *res;
+
+	dr = devres_alloc(devm_region_release, sizeof(struct region_devres),
+			  GFP_KERNEL);
+	if (!dr)
+		return NULL;
+
+	dr->parent = parent;
+	dr->start = start;
+	dr->n = n;
+
+	res = __request_region(parent, start, n, name, 0);
+	if (res)
+		devres_add(dev, dr);
+	else
+		devres_free(dr);
+
+	return res;
+}
+EXPORT_SYMBOL(__devm_request_region);
+
+void __devm_release_region(struct device *dev, struct resource *parent,
+			   resource_size_t start, resource_size_t n)
+{
+	struct region_devres match_data = { parent, start, n };
+
+	__release_region(parent, start, n);
+	WARN_ON(devres_destroy(dev, devm_region_release, devm_region_match,
+			       &match_data));
+}
+EXPORT_SYMBOL(__devm_release_region);
+
+/*
+ * Called from init/main.c to reserve IO ports.
+ */
+#define MAXRESERVE 4
+static int __init reserve_setup(char *str)
+{
+	static int reserved;
+	static struct resource reserve[MAXRESERVE];
+
+	for (;;) {
+		int io_start, io_num;
+		int x = reserved;
+
+		if (get_option (&str, &io_start) != 2)
+			break;
+		if (get_option (&str, &io_num)   == 0)
+			break;
+		if (x < MAXRESERVE) {
+			struct resource *res = reserve + x;
+			res->name = "reserved";
+			res->start = io_start;
+			res->end = io_start + io_num - 1;
+			res->flags = IORESOURCE_BUSY;
+			res->child = NULL;
+			if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0)
+				reserved = x+1;
+		}
+	}
+	return 1;
+}
+
+__setup("reserve=", reserve_setup);
+
+/*
+ * Check if the requested addr and size spans more than any slot in the
+ * iomem resource tree.
+ */
+int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
+{
+	struct resource *p = &iomem_resource;
+	int err = 0;
+	loff_t l;
+
+	read_lock(&resource_lock);
+	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+		/*
+		 * We can probably skip the resources without
+		 * IORESOURCE_IO attribute?
+		 */
+		if (p->start >= addr + size)
+			continue;
+		if (p->end < addr)
+			continue;
+		if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
+		    PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
+			continue;
+		/*
+		 * if a resource is "BUSY", it's not a hardware resource
+		 * but a driver mapping of such a resource; we don't want
+		 * to warn for those; some drivers legitimately map only
+		 * partial hardware resources. (example: vesafb)
+		 */
+		if (p->flags & IORESOURCE_BUSY)
+			continue;
+
+		printk(KERN_WARNING "resource map sanity check conflict: "
+		       "0x%llx 0x%llx 0x%llx 0x%llx %s\n",
+		       (unsigned long long)addr,
+		       (unsigned long long)(addr + size - 1),
+		       (unsigned long long)p->start,
+		       (unsigned long long)p->end,
+		       p->name);
+		err = -1;
+		break;
+	}
+	read_unlock(&resource_lock);
+
+	return err;
+}
+
+#ifdef CONFIG_STRICT_DEVMEM
+static int strict_iomem_checks = 1;
+#else
+static int strict_iomem_checks;
+#endif
+
+/*
+ * check if an address is reserved in the iomem resource tree
+ * returns 1 if reserved, 0 if not reserved.
+ */
+int iomem_is_exclusive(u64 addr)
+{
+	struct resource *p = &iomem_resource;
+	int err = 0;
+	loff_t l;
+	int size = PAGE_SIZE;
+
+	if (!strict_iomem_checks)
+		return 0;
+
+	addr = addr & PAGE_MASK;
+
+	read_lock(&resource_lock);
+	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+		/*
+		 * We can probably skip the resources without
+		 * IORESOURCE_IO attribute?
+		 */
+		if (p->start >= addr + size)
+			break;
+		if (p->end < addr)
+			continue;
+		if (p->flags & IORESOURCE_BUSY &&
+		     p->flags & IORESOURCE_EXCLUSIVE) {
+			err = 1;
+			break;
+		}
+	}
+	read_unlock(&resource_lock);
+
+	return err;
+}
+
+static int __init strict_iomem(char *str)
+{
+	if (strstr(str, "relaxed"))
+		strict_iomem_checks = 0;
+	if (strstr(str, "strict"))
+		strict_iomem_checks = 1;
+	return 1;
+}
+
+__setup("iomem=", strict_iomem);
diff --git a/libdde-linux26/lib/src/kernel/sched.c b/libdde-linux26/lib/src/kernel/sched.c
new file mode 100644
index 00000000..5c51695e
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/sched.c
@@ -0,0 +1,9654 @@
+/*
+ *  kernel/sched.c
+ *
+ *  Kernel scheduler and related syscalls
+ *
+ *  Copyright (C) 1991-2002  Linus Torvalds
+ *
+ *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
+ *		make semaphores SMP safe
+ *  1998-11-19	Implemented schedule_timeout() and related stuff
+ *		by Andrea Arcangeli
+ *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
+ *		hybrid priority-list and round-robin design with
+ *		an array-switch method of distributing timeslices
+ *		and per-CPU runqueues.  Cleanups and useful suggestions
+ *		by Davide Libenzi, preemptible kernel bits by Robert Love.
+ *  2003-09-03	Interactivity tuning by Con Kolivas.
+ *  2004-04-02	Scheduler domains code by Nick Piggin
+ *  2007-04-15  Work begun on replacing all interactivity tuning with a
+ *              fair scheduling design by Con Kolivas.
+ *  2007-05-05  Load balancing (smp-nice) and other improvements
+ *              by Peter Williams
+ *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
+ *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
+ *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
+ *              Thomas Gleixner, Mike Kravetz
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <linux/uaccess.h>
+#include <linux/highmem.h>
+#include <linux/smp_lock.h>
+#include <asm/mmu_context.h>
+#include <linux/interrupt.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/kernel_stat.h>
+#include <linux/debug_locks.h>
+#include <linux/security.h>
+#include <linux/notifier.h>
+#include <linux/profile.h>
+#include <linux/freezer.h>
+#include <linux/vmalloc.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/pid_namespace.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/timer.h>
+#include <linux/rcupdate.h>
+#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/sysctl.h>
+#include <linux/syscalls.h>
+#include <linux/times.h>
+#include <linux/tsacct_kern.h>
+#include <linux/kprobes.h>
+#include <linux/delayacct.h>
+#include <linux/reciprocal_div.h>
+#include <linux/unistd.h>
+#include <linux/pagemap.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/bootmem.h>
+#include <linux/debugfs.h>
+#include <linux/ctype.h>
+#include <linux/ftrace.h>
+#include <trace/sched.h>
+
+#include <asm/tlb.h>
+#include <asm/irq_regs.h>
+
+#include "sched_cpupri.h"
+
+#ifdef DDE_LINUX
+/* DDE_LINUX implements this function externally */
+extern int try_to_wake_up(struct task_struct *p, unsigned int state, int sync);
+#endif
+
+/** DDE only uses small parts of this. */
+#ifndef DDE_LINUX
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
+#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
+#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+
+/*
+ * Helpers for converting nanosecond timing to jiffy resolution
+ */
+#define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
+
+#define NICE_0_LOAD		SCHED_LOAD_SCALE
+#define NICE_0_SHIFT		SCHED_LOAD_SHIFT
+
+/*
+ * These are the 'tuning knobs' of the scheduler:
+ *
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
+ * Timeslices get refilled after they expire.
+ */
+#define DEF_TIMESLICE		(100 * HZ / 1000)
+
+/*
+ * single value that denotes runtime == period, ie unlimited time.
+ */
+#define RUNTIME_INF	((u64)~0ULL)
+
+DEFINE_TRACE(sched_wait_task);
+DEFINE_TRACE(sched_wakeup);
+DEFINE_TRACE(sched_wakeup_new);
+DEFINE_TRACE(sched_switch);
+DEFINE_TRACE(sched_migrate_task);
+
+#ifdef CONFIG_SMP
+
+static void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
+/*
+ * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
+ * Since cpu_power is a 'constant', we can use a reciprocal divide.
+ */
+static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
+{
+	return reciprocal_divide(load, sg->reciprocal_cpu_power);
+}
+
+/*
+ * Each time a sched group cpu_power is changed,
+ * we must compute its reciprocal value
+ */
+static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
+{
+	sg->__cpu_power += val;
+	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
+}
+#endif
+
+static inline int rt_policy(int policy)
+{
+	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
+		return 1;
+	return 0;
+}
+
+static inline int task_has_rt_policy(struct task_struct *p)
+{
+	return rt_policy(p->policy);
+}
+
+/*
+ * This is the priority-queue data structure of the RT scheduling class:
+ */
+struct rt_prio_array {
+	DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
+	struct list_head queue[MAX_RT_PRIO];
+};
+
+struct rt_bandwidth {
+	/* nests inside the rq lock: */
+	spinlock_t		rt_runtime_lock;
+	ktime_t			rt_period;
+	u64			rt_runtime;
+	struct hrtimer		rt_period_timer;
+};
+
+static struct rt_bandwidth def_rt_bandwidth;
+
+static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
+
+static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
+{
+	struct rt_bandwidth *rt_b =
+		container_of(timer, struct rt_bandwidth, rt_period_timer);
+	ktime_t now;
+	int overrun;
+	int idle = 0;
+
+	for (;;) {
+		now = hrtimer_cb_get_time(timer);
+		overrun = hrtimer_forward(timer, now, rt_b->rt_period);
+
+		if (!overrun)
+			break;
+
+		idle = do_sched_rt_period_timer(rt_b, overrun);
+	}
+
+	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
+}
+
+static
+void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
+{
+	rt_b->rt_period = ns_to_ktime(period);
+	rt_b->rt_runtime = runtime;
+
+	spin_lock_init(&rt_b->rt_runtime_lock);
+
+	hrtimer_init(&rt_b->rt_period_timer,
+			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	rt_b->rt_period_timer.function = sched_rt_period_timer;
+}
+
+static inline int rt_bandwidth_enabled(void)
+{
+	return sysctl_sched_rt_runtime >= 0;
+}
+
+static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
+{
+	ktime_t now;
+
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
+		return;
+
+	if (hrtimer_active(&rt_b->rt_period_timer))
+		return;
+
+	spin_lock(&rt_b->rt_runtime_lock);
+	for (;;) {
+		if (hrtimer_active(&rt_b->rt_period_timer))
+			break;
+
+		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
+		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
+		hrtimer_start_expires(&rt_b->rt_period_timer,
+				HRTIMER_MODE_ABS);
+	}
+	spin_unlock(&rt_b->rt_runtime_lock);
+}
+
+#ifdef CONFIG_RT_GROUP_SCHED
+static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
+{
+	hrtimer_cancel(&rt_b->rt_period_timer);
+}
+#endif
+
+/*
+ * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * detach_destroy_domains and partition_sched_domains.
+ */
+static DEFINE_MUTEX(sched_domains_mutex);
+
+#ifdef CONFIG_GROUP_SCHED
+
+#include <linux/cgroup.h>
+
+struct cfs_rq;
+
+static LIST_HEAD(task_groups);
+
+/* task group related information */
+struct task_group {
+#ifdef CONFIG_CGROUP_SCHED
+	struct cgroup_subsys_state css;
+#endif
+
+#ifdef CONFIG_USER_SCHED
+	uid_t uid;
+#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/* schedulable entities of this group on each cpu */
+	struct sched_entity **se;
+	/* runqueue "owned" by this group on each cpu */
+	struct cfs_rq **cfs_rq;
+	unsigned long shares;
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct sched_rt_entity **rt_se;
+	struct rt_rq **rt_rq;
+
+	struct rt_bandwidth rt_bandwidth;
+#endif
+
+	struct rcu_head rcu;
+	struct list_head list;
+
+	struct task_group *parent;
+	struct list_head siblings;
+	struct list_head children;
+};
+
+#ifdef CONFIG_USER_SCHED
+
+/* Helper function to pass uid information to create_sched_user() */
+void set_tg_uid(struct user_struct *user)
+{
+	user->tg->uid = user->uid;
+}
+
+/*
+ * Root task group.
+ * 	Every UID task group (including init_task_group aka UID-0) will
+ * 	be a child to this group.
+ */
+struct task_group root_task_group;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* Default task group's sched entity on each cpu */
+static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
+/* Default task group's cfs_rq on each cpu */
+static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+#ifdef CONFIG_RT_GROUP_SCHED
+static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
+static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
+#endif /* CONFIG_RT_GROUP_SCHED */
+#else /* !CONFIG_USER_SCHED */
+#define root_task_group init_task_group
+#endif /* CONFIG_USER_SCHED */
+
+/* task_group_lock serializes add/remove of task groups and also changes to
+ * a task group's cpu shares.
+ */
+static DEFINE_SPINLOCK(task_group_lock);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_USER_SCHED
+# define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
+#else /* !CONFIG_USER_SCHED */
+# define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
+#endif /* CONFIG_USER_SCHED */
+
+/*
+ * A weight of 0 or 1 can cause arithmetics problems.
+ * A weight of a cfs_rq is the sum of weights of which entities
+ * are queued on this cfs_rq, so a weight of a entity should not be
+ * too large, so as the shares value of a task group.
+ * (The default weight is 1024 - so there's no practical
+ *  limitation from this.)
+ */
+#define MIN_SHARES	2
+#define MAX_SHARES	(1UL << 18)
+
+static int init_task_group_load = INIT_TASK_GROUP_LOAD;
+#endif
+
+/* Default task group.
+ *	Every task in system belong to this group at bootup.
+ */
+struct task_group init_task_group;
+
+/* return group to which a task belongs */
+static inline struct task_group *task_group(struct task_struct *p)
+{
+	struct task_group *tg;
+
+#ifdef CONFIG_USER_SCHED
+	rcu_read_lock();
+	tg = __task_cred(p)->user->tg;
+	rcu_read_unlock();
+#elif defined(CONFIG_CGROUP_SCHED)
+	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
+				struct task_group, css);
+#else
+	tg = &init_task_group;
+#endif
+	return tg;
+}
+
+/* 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)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
+	p->se.parent = task_group(p)->se[cpu];
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
+	p->rt.parent = task_group(p)->rt_se[cpu];
+#endif
+}
+
+#else
+
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
+static inline struct task_group *task_group(struct task_struct *p)
+{
+	return NULL;
+}
+
+#endif	/* CONFIG_GROUP_SCHED */
+
+/* CFS-related fields in a runqueue */
+struct cfs_rq {
+	struct load_weight load;
+	unsigned long nr_running;
+
+	u64 exec_clock;
+	u64 min_vruntime;
+
+	struct rb_root tasks_timeline;
+	struct rb_node *rb_leftmost;
+
+	struct list_head tasks;
+	struct list_head *balance_iterator;
+
+	/*
+	 * 'curr' points to currently running entity on this cfs_rq.
+	 * It is set to NULL otherwise (i.e when none are currently running).
+	 */
+	struct sched_entity *curr, *next, *last;
+
+	unsigned int nr_spread_over;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */
+
+	/*
+	 * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
+	 * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
+	 * (like users, containers etc.)
+	 *
+	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
+	 * list is used during load balance.
+	 */
+	struct list_head leaf_cfs_rq_list;
+	struct task_group *tg;	/* group that "owns" this runqueue */
+
+#ifdef CONFIG_SMP
+	/*
+	 * the part of load.weight contributed by tasks
+	 */
+	unsigned long task_weight;
+
+	/*
+	 *   h_load = weight * f(tg)
+	 *
+	 * Where f(tg) is the recursive weight fraction assigned to
+	 * this group.
+	 */
+	unsigned long h_load;
+
+	/*
+	 * this cpu's part of tg->shares
+	 */
+	unsigned long shares;
+
+	/*
+	 * load.weight at the time we set shares
+	 */
+	unsigned long rq_weight;
+#endif
+#endif
+};
+
+/* Real-Time classes' related field in a runqueue: */
+struct rt_rq {
+	struct rt_prio_array active;
+	unsigned long rt_nr_running;
+#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+	int highest_prio; /* highest queued rt task prio */
+#endif
+#ifdef CONFIG_SMP
+	unsigned long rt_nr_migratory;
+	int overloaded;
+#endif
+	int rt_throttled;
+	u64 rt_time;
+	u64 rt_runtime;
+	/* Nests inside the rq lock: */
+	spinlock_t rt_runtime_lock;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	unsigned long rt_nr_boosted;
+
+	struct rq *rq;
+	struct list_head leaf_rt_rq_list;
+	struct task_group *tg;
+	struct sched_rt_entity *rt_se;
+#endif
+};
+
+#ifdef CONFIG_SMP
+
+/*
+ * We add the notion of a root-domain which will be used to define per-domain
+ * variables. Each exclusive cpuset essentially defines an island domain by
+ * fully partitioning the member cpus from any other cpuset. Whenever a new
+ * exclusive cpuset is created, we also create and attach a new root-domain
+ * object.
+ *
+ */
+struct root_domain {
+	atomic_t refcount;
+	cpumask_var_t span;
+	cpumask_var_t online;
+
+	/*
+	 * The "RT overload" flag: it gets set if a CPU has more than
+	 * one runnable RT task.
+	 */
+	cpumask_var_t rto_mask;
+	atomic_t rto_count;
+#ifdef CONFIG_SMP
+	struct cpupri cpupri;
+#endif
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+	/*
+	 * Preferred wake up cpu nominated by sched_mc balance that will be
+	 * used when most cpus are idle in the system indicating overall very
+	 * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
+	 */
+	unsigned int sched_mc_preferred_wakeup_cpu;
+#endif
+};
+
+/*
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+static struct root_domain def_root_domain;
+
+#endif
+
+/*
+ * This is the main, per-CPU runqueue data structure.
+ *
+ * Locking rule: those places that want to lock multiple runqueues
+ * (such as the load balancing or the thread migration code), lock
+ * acquire operations must be ordered by ascending &runqueue.
+ */
+struct rq {
+	/* runqueue lock: */
+	spinlock_t lock;
+
+	/*
+	 * nr_running and cpu_load should be in the same cacheline because
+	 * remote CPUs use both these fields when doing load calculation.
+	 */
+	unsigned long nr_running;
+	#define CPU_LOAD_IDX_MAX 5
+	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
+	unsigned char idle_at_tick;
+#ifdef CONFIG_NO_HZ
+	unsigned long last_tick_seen;
+	unsigned char in_nohz_recently;
+#endif
+	/* capture load from *all* tasks on this cpu: */
+	struct load_weight load;
+	unsigned long nr_load_updates;
+	u64 nr_switches;
+
+	struct cfs_rq cfs;
+	struct rt_rq rt;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/* list of leaf cfs_rq on this cpu: */
+	struct list_head leaf_cfs_rq_list;
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct list_head leaf_rt_rq_list;
+#endif
+
+	/*
+	 * This is part of a global counter where only the total sum
+	 * over all CPUs matters. A task can increase this counter on
+	 * one CPU and if it got migrated afterwards it may decrease
+	 * it on another CPU. Always updated under the runqueue lock:
+	 */
+	unsigned long nr_uninterruptible;
+
+	struct task_struct *curr, *idle;
+	unsigned long next_balance;
+	struct mm_struct *prev_mm;
+
+	u64 clock;
+
+	atomic_t nr_iowait;
+
+#ifdef CONFIG_SMP
+	struct root_domain *rd;
+	struct sched_domain *sd;
+
+	/* For active balancing */
+	int active_balance;
+	int push_cpu;
+	/* cpu of this runqueue: */
+	int cpu;
+	int online;
+
+	unsigned long avg_load_per_task;
+
+	struct task_struct *migration_thread;
+	struct list_head migration_queue;
+#endif
+
+#ifdef CONFIG_SCHED_HRTICK
+#ifdef CONFIG_SMP
+	int hrtick_csd_pending;
+	struct call_single_data hrtick_csd;
+#endif
+	struct hrtimer hrtick_timer;
+#endif
+
+#ifdef CONFIG_SCHEDSTATS
+	/* latency stats */
+	struct sched_info rq_sched_info;
+	unsigned long long rq_cpu_time;
+	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
+
+	/* sys_sched_yield() stats */
+	unsigned int yld_exp_empty;
+	unsigned int yld_act_empty;
+	unsigned int yld_both_empty;
+	unsigned int yld_count;
+
+	/* schedule() stats */
+	unsigned int sched_switch;
+	unsigned int sched_count;
+	unsigned int sched_goidle;
+
+	/* try_to_wake_up() stats */
+	unsigned int ttwu_count;
+	unsigned int ttwu_local;
+
+	/* BKL stats */
+	unsigned int bkl_count;
+#endif
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+
+static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
+{
+	rq->curr->sched_class->check_preempt_curr(rq, p, sync);
+}
+
+static inline int cpu_of(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+	return rq->cpu;
+#else
+	return 0;
+#endif
+}
+
+/*
+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
+ * See detach_destroy_domains: synchronize_sched for details.
+ *
+ * The domain tree of any CPU may only be accessed from within
+ * preempt-disabled sections.
+ */
+#define for_each_domain(cpu, __sd) \
+	for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
+
+#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
+#define this_rq()		(&__get_cpu_var(runqueues))
+#define task_rq(p)		cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+
+static inline void update_rq_clock(struct rq *rq)
+{
+	rq->clock = sched_clock_cpu(cpu_of(rq));
+}
+
+/*
+ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
+ */
+#ifdef CONFIG_SCHED_DEBUG
+# define const_debug __read_mostly
+#else
+# define const_debug static const
+#endif
+
+/**
+ * runqueue_is_locked
+ *
+ * Returns true if the current cpu runqueue is locked.
+ * This interface allows printk to be called with the runqueue lock
+ * held and know whether or not it is OK to wake up the klogd.
+ */
+int runqueue_is_locked(void)
+{
+	int cpu = get_cpu();
+	struct rq *rq = cpu_rq(cpu);
+	int ret;
+
+	ret = spin_is_locked(&rq->lock);
+	put_cpu();
+	return ret;
+}
+
+/*
+ * Debugging: various feature bits
+ */
+
+#define SCHED_FEAT(name, enabled)	\
+	__SCHED_FEAT_##name ,
+
+enum {
+#include "sched_features.h"
+};
+
+#undef SCHED_FEAT
+
+#define SCHED_FEAT(name, enabled)	\
+	(1UL << __SCHED_FEAT_##name) * enabled |
+
+const_debug unsigned int sysctl_sched_features =
+#include "sched_features.h"
+	0;
+
+#undef SCHED_FEAT
+
+#ifdef CONFIG_SCHED_DEBUG
+#define SCHED_FEAT(name, enabled)	\
+	#name ,
+
+static __read_mostly char *sched_feat_names[] = {
+#include "sched_features.h"
+	NULL
+};
+
+#undef SCHED_FEAT
+
+static int sched_feat_show(struct seq_file *m, void *v)
+{
+	int i;
+
+	for (i = 0; sched_feat_names[i]; i++) {
+		if (!(sysctl_sched_features & (1UL << i)))
+			seq_puts(m, "NO_");
+		seq_printf(m, "%s ", sched_feat_names[i]);
+	}
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp = buf;
+	int neg = 0;
+	int i;
+
+	if (cnt > 63)
+		cnt = 63;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	if (strncmp(buf, "NO_", 3) == 0) {
+		neg = 1;
+		cmp += 3;
+	}
+
+	for (i = 0; sched_feat_names[i]; i++) {
+		int len = strlen(sched_feat_names[i]);
+
+		if (strncmp(cmp, sched_feat_names[i], len) == 0) {
+			if (neg)
+				sysctl_sched_features &= ~(1UL << i);
+			else
+				sysctl_sched_features |= (1UL << i);
+			break;
+		}
+	}
+
+	if (!sched_feat_names[i])
+		return -EINVAL;
+
+	filp->f_pos += cnt;
+
+	return cnt;
+}
+
+static int sched_feat_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_feat_show, NULL);
+}
+
+static struct file_operations sched_feat_fops = {
+	.open		= sched_feat_open,
+	.write		= sched_feat_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static __init int sched_init_debug(void)
+{
+	debugfs_create_file("sched_features", 0644, NULL, NULL,
+			&sched_feat_fops);
+
+	return 0;
+}
+late_initcall(sched_init_debug);
+
+#endif
+
+#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+
+/*
+ * Number of tasks to iterate in a single balance run.
+ * Limited because this is done with IRQs disabled.
+ */
+const_debug unsigned int sysctl_sched_nr_migrate = 32;
+
+/*
+ * ratelimit for updating the group shares.
+ * default: 0.25ms
+ */
+unsigned int sysctl_sched_shares_ratelimit = 250000;
+
+/*
+ * Inject some fuzzyness into changing the per-cpu group shares
+ * this avoids remote rq-locks at the expense of fairness.
+ * default: 4
+ */
+unsigned int sysctl_sched_shares_thresh = 4;
+
+/*
+ * period over which we measure -rt task cpu usage in us.
+ * default: 1s
+ */
+unsigned int sysctl_sched_rt_period = 1000000;
+
+static __read_mostly int scheduler_running;
+
+/*
+ * part of the period that we allow rt tasks to run in us.
+ * default: 0.95s
+ */
+int sysctl_sched_rt_runtime = 950000;
+
+static inline u64 global_rt_period(void)
+{
+	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
+}
+
+static inline u64 global_rt_runtime(void)
+{
+	if (sysctl_sched_rt_runtime < 0)
+		return RUNTIME_INF;
+
+	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
+}
+
+#ifndef prepare_arch_switch
+# define prepare_arch_switch(next)	do { } while (0)
+#endif
+#ifndef finish_arch_switch
+# define finish_arch_switch(prev)	do { } while (0)
+#endif
+
+static inline int task_current(struct rq *rq, struct task_struct *p)
+{
+	return rq->curr == p;
+}
+
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+static inline int task_running(struct rq *rq, struct task_struct *p)
+{
+	return task_current(rq, p);
+}
+
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+}
+
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/* this is a valid case when another task releases the spinlock */
+	rq->lock.owner = current;
+#endif
+	/*
+	 * If we are tracking spinlock dependencies then we have to
+	 * fix up the runqueue lock - which gets 'carried over' from
+	 * prev into current:
+	 */
+	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+
+	spin_unlock_irq(&rq->lock);
+}
+
+#else /* __ARCH_WANT_UNLOCKED_CTXSW */
+static inline int task_running(struct rq *rq, struct task_struct *p)
+{
+#ifdef CONFIG_SMP
+	return p->oncpu;
+#else
+	return task_current(rq, p);
+#endif
+}
+
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * We can optimise this out completely for !SMP, because the
+	 * SMP rebalancing from interrupt is the only thing that cares
+	 * here.
+	 */
+	next->oncpu = 1;
+#endif
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	spin_unlock_irq(&rq->lock);
+#else
+	spin_unlock(&rq->lock);
+#endif
+}
+
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * After ->oncpu is cleared, the task can be moved to a different CPU.
+	 * We must ensure this doesn't happen until the switch is completely
+	 * finished.
+	 */
+	smp_wmb();
+	prev->oncpu = 0;
+#endif
+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_enable();
+#endif
+}
+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
+
+/*
+ * __task_rq_lock - lock the runqueue a given task resides on.
+ * Must be called interrupts disabled.
+ */
+static inline struct rq *__task_rq_lock(struct task_struct *p)
+	__acquires(rq->lock)
+{
+	for (;;) {
+		struct rq *rq = task_rq(p);
+		spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p)))
+			return rq;
+		spin_unlock(&rq->lock);
+	}
+}
+
+/*
+ * task_rq_lock - lock the runqueue a given task resides on and disable
+ * interrupts. Note the ordering: we can safely lookup the task_rq without
+ * explicitly disabling preemption.
+ */
+static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	for (;;) {
+		local_irq_save(*flags);
+		rq = task_rq(p);
+		spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p)))
+			return rq;
+		spin_unlock_irqrestore(&rq->lock, *flags);
+	}
+}
+
+void task_rq_unlock_wait(struct task_struct *p)
+{
+	struct rq *rq = task_rq(p);
+
+	smp_mb(); /* spin-unlock-wait is not a full memory barrier */
+	spin_unlock_wait(&rq->lock);
+}
+
+static void __task_rq_unlock(struct rq *rq)
+	__releases(rq->lock)
+{
+	spin_unlock(&rq->lock);
+}
+
+static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
+	__releases(rq->lock)
+{
+	spin_unlock_irqrestore(&rq->lock, *flags);
+}
+
+/*
+ * this_rq_lock - lock this runqueue and disable interrupts.
+ */
+static struct rq *this_rq_lock(void)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	local_irq_disable();
+	rq = this_rq();
+	spin_lock(&rq->lock);
+
+	return rq;
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+/*
+ * Use HR-timers to deliver accurate preemption points.
+ *
+ * Its all a bit involved since we cannot program an hrt while holding the
+ * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
+ * reschedule event.
+ *
+ * When we get rescheduled we reprogram the hrtick_timer outside of the
+ * rq->lock.
+ */
+
+/*
+ * Use hrtick when:
+ *  - enabled by features
+ *  - hrtimer is actually high res
+ */
+static inline int hrtick_enabled(struct rq *rq)
+{
+	if (!sched_feat(HRTICK))
+		return 0;
+	if (!cpu_active(cpu_of(rq)))
+		return 0;
+	return hrtimer_is_hres_active(&rq->hrtick_timer);
+}
+
+static void hrtick_clear(struct rq *rq)
+{
+	if (hrtimer_active(&rq->hrtick_timer))
+		hrtimer_cancel(&rq->hrtick_timer);
+}
+
+/*
+ * High-resolution timer tick.
+ * Runs from hardirq context with interrupts disabled.
+ */
+static enum hrtimer_restart hrtick(struct hrtimer *timer)
+{
+	struct rq *rq = container_of(timer, struct rq, hrtick_timer);
+
+	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
+
+	spin_lock(&rq->lock);
+	update_rq_clock(rq);
+	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
+	spin_unlock(&rq->lock);
+
+	return HRTIMER_NORESTART;
+}
+
+#ifdef CONFIG_SMP
+/*
+ * called from hardirq (IPI) context
+ */
+static void __hrtick_start(void *arg)
+{
+	struct rq *rq = arg;
+
+	spin_lock(&rq->lock);
+	hrtimer_restart(&rq->hrtick_timer);
+	rq->hrtick_csd_pending = 0;
+	spin_unlock(&rq->lock);
+}
+
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay)
+{
+	struct hrtimer *timer = &rq->hrtick_timer;
+	ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
+
+	hrtimer_set_expires(timer, time);
+
+	if (rq == this_rq()) {
+		hrtimer_restart(timer);
+	} else if (!rq->hrtick_csd_pending) {
+		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+		rq->hrtick_csd_pending = 1;
+	}
+}
+
+static int
+hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	int cpu = (int)(long)hcpu;
+
+	switch (action) {
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		hrtick_clear(cpu_rq(cpu));
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static __init void init_hrtick(void)
+{
+	hotcpu_notifier(hotplug_hrtick, 0);
+}
+#else
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay)
+{
+	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+}
+
+static inline void init_hrtick(void)
+{
+}
+#endif /* CONFIG_SMP */
+
+static void init_rq_hrtick(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+	rq->hrtick_csd_pending = 0;
+
+	rq->hrtick_csd.flags = 0;
+	rq->hrtick_csd.func = __hrtick_start;
+	rq->hrtick_csd.info = rq;
+#endif
+
+	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	rq->hrtick_timer.function = hrtick;
+}
+#else	/* CONFIG_SCHED_HRTICK */
+static inline void hrtick_clear(struct rq *rq)
+{
+}
+
+static inline void init_rq_hrtick(struct rq *rq)
+{
+}
+
+static inline void init_hrtick(void)
+{
+}
+#endif	/* CONFIG_SCHED_HRTICK */
+
+/*
+ * resched_task - mark a task 'to be rescheduled now'.
+ *
+ * On UP this means the setting of the need_resched flag, on SMP it
+ * might also involve a cross-CPU call to trigger the scheduler on
+ * the target CPU.
+ */
+#ifdef CONFIG_SMP
+
+#ifndef tsk_is_polling
+#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
+#endif
+
+static void resched_task(struct task_struct *p)
+{
+	int cpu;
+
+	assert_spin_locked(&task_rq(p)->lock);
+
+	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+		return;
+
+	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+
+	cpu = task_cpu(p);
+	if (cpu == smp_processor_id())
+		return;
+
+	/* NEED_RESCHED must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(p))
+		smp_send_reschedule(cpu);
+}
+
+static void resched_cpu(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	if (!spin_trylock_irqsave(&rq->lock, flags))
+		return;
+	resched_task(cpu_curr(cpu));
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+#ifdef CONFIG_NO_HZ
+/*
+ * When add_timer_on() enqueues a timer into the timer wheel of an
+ * idle CPU then this timer might expire before the next timer event
+ * which is scheduled to wake up that CPU. In case of a completely
+ * idle system the next event might even be infinite time into the
+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
+ * leaves the inner idle loop so the newly added timer is taken into
+ * account when the CPU goes back to idle and evaluates the timer
+ * wheel for the next timer event.
+ */
+void wake_up_idle_cpu(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	if (cpu == smp_processor_id())
+		return;
+
+	/*
+	 * This is safe, as this function is called with the timer
+	 * wheel base lock of (cpu) held. When the CPU is on the way
+	 * to idle and has not yet set rq->curr to idle then it will
+	 * be serialized on the timer wheel base lock and take the new
+	 * timer into account automatically.
+	 */
+	if (rq->curr != rq->idle)
+		return;
+
+	/*
+	 * We can set TIF_RESCHED on the idle task of the other CPU
+	 * lockless. The worst case is that the other CPU runs the
+	 * idle task through an additional NOOP schedule()
+	 */
+	set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+
+	/* NEED_RESCHED must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(rq->idle))
+		smp_send_reschedule(cpu);
+}
+#endif /* CONFIG_NO_HZ */
+
+#else /* !CONFIG_SMP */
+static void resched_task(struct task_struct *p)
+{
+	assert_spin_locked(&task_rq(p)->lock);
+	set_tsk_need_resched(p);
+}
+#endif /* CONFIG_SMP */
+
+#if BITS_PER_LONG == 32
+# define WMULT_CONST	(~0UL)
+#else
+# define WMULT_CONST	(1UL << 32)
+#endif
+
+#define WMULT_SHIFT	32
+
+/*
+ * Shift right and round:
+ */
+#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+
+/*
+ * delta *= weight / lw
+ */
+static unsigned long
+calc_delta_mine(unsigned long delta_exec, unsigned long weight,
+		struct load_weight *lw)
+{
+	u64 tmp;
+
+	if (!lw->inv_weight) {
+		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
+			lw->inv_weight = 1;
+		else
+			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
+				/ (lw->weight+1);
+	}
+
+	tmp = (u64)delta_exec * weight;
+	/*
+	 * Check whether we'd overflow the 64-bit multiplication:
+	 */
+	if (unlikely(tmp > WMULT_CONST))
+		tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
+			WMULT_SHIFT/2);
+	else
+		tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
+
+	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
+}
+
+static inline void update_load_add(struct load_weight *lw, unsigned long inc)
+{
+	lw->weight += inc;
+	lw->inv_weight = 0;
+}
+
+static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
+{
+	lw->weight -= dec;
+	lw->inv_weight = 0;
+}
+
+/*
+ * To aid in avoiding the subversion of "niceness" due to uneven distribution
+ * of tasks with abnormal "nice" values across CPUs the contribution that
+ * each task makes to its run queue's load is weighted according to its
+ * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
+ * scaled version of the new time slice allocation that they receive on time
+ * slice expiry etc.
+ */
+
+#define WEIGHT_IDLEPRIO                3
+#define WMULT_IDLEPRIO         1431655765
+
+/*
+ * Nice levels are multiplicative, with a gentle 10% change for every
+ * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
+ * nice 1, it will get ~10% less CPU time than another CPU-bound task
+ * that remained on nice 0.
+ *
+ * The "10% effect" is relative and cumulative: from _any_ nice level,
+ * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
+ * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
+ * If a task goes up by ~10% and another task goes down by ~10% then
+ * the relative distance between them is ~25%.)
+ */
+static const int prio_to_weight[40] = {
+ /* -20 */     88761,     71755,     56483,     46273,     36291,
+ /* -15 */     29154,     23254,     18705,     14949,     11916,
+ /* -10 */      9548,      7620,      6100,      4904,      3906,
+ /*  -5 */      3121,      2501,      1991,      1586,      1277,
+ /*   0 */      1024,       820,       655,       526,       423,
+ /*   5 */       335,       272,       215,       172,       137,
+ /*  10 */       110,        87,        70,        56,        45,
+ /*  15 */        36,        29,        23,        18,        15,
+};
+
+/*
+ * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
+ *
+ * In cases where the weight does not change often, we can use the
+ * precalculated inverse to speed up arithmetics by turning divisions
+ * into multiplications:
+ */
+static const u32 prio_to_wmult[40] = {
+ /* -20 */     48388,     59856,     76040,     92818,    118348,
+ /* -15 */    147320,    184698,    229616,    287308,    360437,
+ /* -10 */    449829,    563644,    704093,    875809,   1099582,
+ /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
+ /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
+ /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
+ /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
+ /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
+};
+
+static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
+
+/*
+ * runqueue iterator, to support SMP load-balancing between different
+ * scheduling classes, without having to expose their internal data
+ * structures to the load-balancing proper:
+ */
+struct rq_iterator {
+	void *arg;
+	struct task_struct *(*start)(void *);
+	struct task_struct *(*next)(void *);
+};
+
+#ifdef CONFIG_SMP
+static unsigned long
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      unsigned long max_load_move, struct sched_domain *sd,
+	      enum cpu_idle_type idle, int *all_pinned,
+	      int *this_best_prio, struct rq_iterator *iterator);
+
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		   struct sched_domain *sd, enum cpu_idle_type idle,
+		   struct rq_iterator *iterator);
+#endif
+
+#ifdef CONFIG_CGROUP_CPUACCT
+static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+#else
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
+#endif
+
+static inline void inc_cpu_load(struct rq *rq, unsigned long load)
+{
+	update_load_add(&rq->load, load);
+}
+
+static inline void dec_cpu_load(struct rq *rq, unsigned long load)
+{
+	update_load_sub(&rq->load, load);
+}
+
+#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
+typedef int (*tg_visitor)(struct task_group *, void *);
+
+/*
+ * Iterate the full tree, calling @down when first entering a node and @up when
+ * leaving it for the final time.
+ */
+static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
+{
+	struct task_group *parent, *child;
+	int ret;
+
+	rcu_read_lock();
+	parent = &root_task_group;
+down:
+	ret = (*down)(parent, data);
+	if (ret)
+		goto out_unlock;
+	list_for_each_entry_rcu(child, &parent->children, siblings) {
+		parent = child;
+		goto down;
+
+up:
+		continue;
+	}
+	ret = (*up)(parent, data);
+	if (ret)
+		goto out_unlock;
+
+	child = parent;
+	parent = parent->parent;
+	if (parent)
+		goto up;
+out_unlock:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int tg_nop(struct task_group *tg, void *data)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+
+static unsigned long cpu_avg_load_per_task(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
+
+	if (nr_running)
+		rq->avg_load_per_task = rq->load.weight / nr_running;
+	else
+		rq->avg_load_per_task = 0;
+
+	return rq->avg_load_per_task;
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
+static void __set_se_shares(struct sched_entity *se, unsigned long shares);
+
+/*
+ * Calculate and set the cpu's group shares.
+ */
+static void
+update_group_shares_cpu(struct task_group *tg, int cpu,
+			unsigned long sd_shares, unsigned long sd_rq_weight)
+{
+	unsigned long shares;
+	unsigned long rq_weight;
+
+	if (!tg->se[cpu])
+		return;
+
+	rq_weight = tg->cfs_rq[cpu]->rq_weight;
+
+	/*
+	 *           \Sum shares * rq_weight
+	 * shares =  -----------------------
+	 *               \Sum rq_weight
+	 *
+	 */
+	shares = (sd_shares * rq_weight) / sd_rq_weight;
+	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
+
+	if (abs(shares - tg->se[cpu]->load.weight) >
+			sysctl_sched_shares_thresh) {
+		struct rq *rq = cpu_rq(cpu);
+		unsigned long flags;
+
+		spin_lock_irqsave(&rq->lock, flags);
+		tg->cfs_rq[cpu]->shares = shares;
+
+		__set_se_shares(tg->se[cpu], shares);
+		spin_unlock_irqrestore(&rq->lock, flags);
+	}
+}
+
+/*
+ * Re-compute the task group their per cpu shares over the given domain.
+ * This needs to be done in a bottom-up fashion because the rq weight of a
+ * parent group depends on the shares of its child groups.
+ */
+static int tg_shares_up(struct task_group *tg, void *data)
+{
+	unsigned long weight, rq_weight = 0;
+	unsigned long shares = 0;
+	struct sched_domain *sd = data;
+	int i;
+
+	for_each_cpu(i, sched_domain_span(sd)) {
+		/*
+		 * If there are currently no tasks on the cpu pretend there
+		 * is one of average load so that when a new task gets to
+		 * run here it will not get delayed by group starvation.
+		 */
+		weight = tg->cfs_rq[i]->load.weight;
+		if (!weight)
+			weight = NICE_0_LOAD;
+
+		tg->cfs_rq[i]->rq_weight = weight;
+		rq_weight += weight;
+		shares += tg->cfs_rq[i]->shares;
+	}
+
+	if ((!shares && rq_weight) || shares > tg->shares)
+		shares = tg->shares;
+
+	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
+		shares = tg->shares;
+
+	for_each_cpu(i, sched_domain_span(sd))
+		update_group_shares_cpu(tg, i, shares, rq_weight);
+
+	return 0;
+}
+
+/*
+ * Compute the cpu's hierarchical load factor for each task group.
+ * This needs to be done in a top-down fashion because the load of a child
+ * group is a fraction of its parents load.
+ */
+static int tg_load_down(struct task_group *tg, void *data)
+{
+	unsigned long load;
+	long cpu = (long)data;
+
+	if (!tg->parent) {
+		load = cpu_rq(cpu)->load.weight;
+	} else {
+		load = tg->parent->cfs_rq[cpu]->h_load;
+		load *= tg->cfs_rq[cpu]->shares;
+		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
+	}
+
+	tg->cfs_rq[cpu]->h_load = load;
+
+	return 0;
+}
+
+static void update_shares(struct sched_domain *sd)
+{
+	u64 now = cpu_clock(raw_smp_processor_id());
+	s64 elapsed = now - sd->last_update;
+
+	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
+		sd->last_update = now;
+		walk_tg_tree(tg_nop, tg_shares_up, sd);
+	}
+}
+
+static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
+{
+	spin_unlock(&rq->lock);
+	update_shares(sd);
+	spin_lock(&rq->lock);
+}
+
+static void update_h_load(long cpu)
+{
+	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
+}
+
+#else
+
+static inline void update_shares(struct sched_domain *sd)
+{
+}
+
+static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
+{
+}
+
+#endif
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+	__releases(this_rq->lock)
+	__acquires(busiest->lock)
+	__acquires(this_rq->lock)
+{
+	int ret = 0;
+
+	if (unlikely(!irqs_disabled())) {
+		/* printk() doesn't work good under rq->lock */
+		spin_unlock(&this_rq->lock);
+		BUG_ON(1);
+	}
+	if (unlikely(!spin_trylock(&busiest->lock))) {
+		if (busiest < this_rq) {
+			spin_unlock(&this_rq->lock);
+			spin_lock(&busiest->lock);
+			spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+			ret = 1;
+		} else
+			spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+	}
+	return ret;
+}
+
+static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+	__releases(busiest->lock)
+{
+	spin_unlock(&busiest->lock);
+	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
+#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
+{
+#ifdef CONFIG_SMP
+	cfs_rq->shares = shares;
+#endif
+}
+#endif
+
+#include "sched_stats.h"
+#include "sched_idletask.c"
+#include "sched_fair.c"
+#include "sched_rt.c"
+#ifdef CONFIG_SCHED_DEBUG
+# include "sched_debug.c"
+#endif
+
+#define sched_class_highest (&rt_sched_class)
+#define for_each_class(class) \
+   for (class = sched_class_highest; class; class = class->next)
+
+static void inc_nr_running(struct rq *rq)
+{
+	rq->nr_running++;
+}
+
+static void dec_nr_running(struct rq *rq)
+{
+	rq->nr_running--;
+}
+
+static void set_load_weight(struct task_struct *p)
+{
+	if (task_has_rt_policy(p)) {
+		p->se.load.weight = prio_to_weight[0] * 2;
+		p->se.load.inv_weight = prio_to_wmult[0] >> 1;
+		return;
+	}
+
+	/*
+	 * SCHED_IDLE tasks get minimal weight:
+	 */
+	if (p->policy == SCHED_IDLE) {
+		p->se.load.weight = WEIGHT_IDLEPRIO;
+		p->se.load.inv_weight = WMULT_IDLEPRIO;
+		return;
+	}
+
+	p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO];
+	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)
+{
+	sched_info_queued(p);
+	p->sched_class->enqueue_task(rq, p, wakeup);
+	p->se.on_rq = 1;
+}
+
+static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
+{
+	if (sleep && p->se.last_wakeup) {
+		update_avg(&p->se.avg_overlap,
+			   p->se.sum_exec_runtime - p->se.last_wakeup);
+		p->se.last_wakeup = 0;
+	}
+
+	sched_info_dequeued(p);
+	p->sched_class->dequeue_task(rq, p, sleep);
+	p->se.on_rq = 0;
+}
+
+/*
+ * __normal_prio - return the priority that is based on the static prio
+ */
+static inline int __normal_prio(struct task_struct *p)
+{
+	return p->static_prio;
+}
+
+/*
+ * Calculate the expected normal priority: i.e. priority
+ * without taking RT-inheritance into account. Might be
+ * boosted by interactivity modifiers. Changes upon fork,
+ * setprio syscalls, and whenever the interactivity
+ * estimator recalculates.
+ */
+static inline int normal_prio(struct task_struct *p)
+{
+	int prio;
+
+	if (task_has_rt_policy(p))
+		prio = MAX_RT_PRIO-1 - p->rt_priority;
+	else
+		prio = __normal_prio(p);
+	return prio;
+}
+
+/*
+ * Calculate the current priority, i.e. the priority
+ * taken into account by the scheduler. This value might
+ * be boosted by RT tasks, or might be boosted by
+ * interactivity modifiers. Will be RT if the task got
+ * RT-boosted. If not then it returns p->normal_prio.
+ */
+static int effective_prio(struct task_struct *p)
+{
+	p->normal_prio = normal_prio(p);
+	/*
+	 * If we are RT tasks or we were boosted to RT priority,
+	 * keep the priority unchanged. Otherwise, update priority
+	 * to the normal priority:
+	 */
+	if (!rt_prio(p->prio))
+		return p->normal_prio;
+	return p->prio;
+}
+
+/*
+ * activate_task - move a task to the runqueue.
+ */
+static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+{
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible--;
+
+	enqueue_task(rq, p, wakeup);
+	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)
+{
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible++;
+
+	dequeue_task(rq, p, sleep);
+	dec_nr_running(rq);
+}
+
+/**
+ * task_curr - is this task currently executing on a CPU?
+ * @p: the task in question.
+ */
+inline int task_curr(const struct task_struct *p)
+{
+	return cpu_curr(task_cpu(p)) == p;
+}
+
+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+	set_task_rq(p, cpu);
+#ifdef CONFIG_SMP
+	/*
+	 * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+	 * successfuly executed on another CPU. We must ensure that updates of
+	 * per-task data have been completed by this moment.
+	 */
+	smp_wmb();
+	task_thread_info(p)->cpu = cpu;
+#endif
+}
+
+static inline void check_class_changed(struct rq *rq, struct task_struct *p,
+				       const struct sched_class *prev_class,
+				       int oldprio, int running)
+{
+	if (prev_class != p->sched_class) {
+		if (prev_class->switched_from)
+			prev_class->switched_from(rq, p, running);
+		p->sched_class->switched_to(rq, p, running);
+	} else
+		p->sched_class->prio_changed(rq, p, oldprio, running);
+}
+
+#ifdef CONFIG_SMP
+
+/* Used instead of source_load when we know the type == 0 */
+static unsigned long weighted_cpuload(const int cpu)
+{
+	return cpu_rq(cpu)->load.weight;
+}
+
+/*
+ * Is this task likely cache-hot:
+ */
+static int
+task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
+{
+	s64 delta;
+
+	/*
+	 * Buddy candidates are cache hot:
+	 */
+	if (sched_feat(CACHE_HOT_BUDDY) &&
+			(&p->se == cfs_rq_of(&p->se)->next ||
+			 &p->se == cfs_rq_of(&p->se)->last))
+		return 1;
+
+	if (p->sched_class != &fair_sched_class)
+		return 0;
+
+	if (sysctl_sched_migration_cost == -1)
+		return 1;
+	if (sysctl_sched_migration_cost == 0)
+		return 0;
+
+	delta = now - p->se.exec_start;
+
+	return delta < (s64)sysctl_sched_migration_cost;
+}
+
+
+void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
+{
+	int old_cpu = task_cpu(p);
+	struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
+	struct cfs_rq *old_cfsrq = task_cfs_rq(p),
+		      *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
+	u64 clock_offset;
+
+	clock_offset = old_rq->clock - new_rq->clock;
+
+	trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+
+#ifdef CONFIG_SCHEDSTATS
+	if (p->se.wait_start)
+		p->se.wait_start -= clock_offset;
+	if (p->se.sleep_start)
+		p->se.sleep_start -= clock_offset;
+	if (p->se.block_start)
+		p->se.block_start -= clock_offset;
+	if (old_cpu != new_cpu) {
+		schedstat_inc(p, se.nr_migrations);
+		if (task_hot(p, old_rq->clock, NULL))
+			schedstat_inc(p, se.nr_forced2_migrations);
+	}
+#endif
+	p->se.vruntime -= old_cfsrq->min_vruntime -
+					 new_cfsrq->min_vruntime;
+
+	__set_task_cpu(p, new_cpu);
+}
+
+struct migration_req {
+	struct list_head list;
+
+	struct task_struct *task;
+	int dest_cpu;
+
+	struct completion done;
+};
+
+/*
+ * 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)
+{
+	struct rq *rq = task_rq(p);
+
+	/*
+	 * If the task is not on a runqueue (and not running), then
+	 * it is sufficient to simply update the task's cpu field.
+	 */
+	if (!p->se.on_rq && !task_running(rq, p)) {
+		set_task_cpu(p, dest_cpu);
+		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_inactive - wait for a thread to unschedule.
+ *
+ * If @match_state is nonzero, it's the @p->state value just checked and
+ * not expected to change.  If it changes, i.e. @p might have woken up,
+ * then return zero.  When we succeed in waiting for @p to be off its CPU,
+ * we return a positive number (its total switch count).  If a second call
+ * a short while later returns the same number, the caller can be sure that
+ * @p has remained unscheduled the whole time.
+ *
+ * The caller must ensure that the task *will* unschedule sometime soon,
+ * else this function might spin for a *long* time. This function can't
+ * be called with interrupts off, or it may introduce deadlock with
+ * smp_call_function() if an IPI is sent by the same process we are
+ * waiting to become inactive.
+ */
+unsigned long wait_task_inactive(struct task_struct *p, long match_state)
+{
+	unsigned long flags;
+	int running, on_rq;
+	unsigned long ncsw;
+	struct rq *rq;
+
+	for (;;) {
+		/*
+		 * We do the initial early heuristics without holding
+		 * any task-queue locks at all. We'll only try to get
+		 * the runqueue lock when things look like they will
+		 * work out!
+		 */
+		rq = task_rq(p);
+
+		/*
+		 * If the task is actively running on another CPU
+		 * still, just relax and busy-wait without holding
+		 * any locks.
+		 *
+		 * NOTE! Since we don't hold any locks, it's not
+		 * even sure that "rq" stays as the right runqueue!
+		 * But we don't care, since "task_running()" will
+		 * return false if the runqueue has changed and p
+		 * is actually now running somewhere else!
+		 */
+		while (task_running(rq, p)) {
+			if (match_state && unlikely(p->state != match_state))
+				return 0;
+			cpu_relax();
+		}
+
+		/*
+		 * Ok, time to look more closely! We need the rq
+		 * lock now, to be *sure*. If we're wrong, we'll
+		 * just go back and repeat.
+		 */
+		rq = task_rq_lock(p, &flags);
+		trace_sched_wait_task(rq, p);
+		running = task_running(rq, p);
+		on_rq = p->se.on_rq;
+		ncsw = 0;
+		if (!match_state || p->state == match_state)
+			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
+		task_rq_unlock(rq, &flags);
+
+		/*
+		 * If it changed from the expected state, bail out now.
+		 */
+		if (unlikely(!ncsw))
+			break;
+
+		/*
+		 * Was it really running after all now that we
+		 * checked with the proper locks actually held?
+		 *
+		 * Oops. Go back and try again..
+		 */
+		if (unlikely(running)) {
+			cpu_relax();
+			continue;
+		}
+
+		/*
+		 * It's not enough that it's not actively running,
+		 * it must be off the runqueue _entirely_, and not
+		 * preempted!
+		 *
+		 * So if it wa still runnable (but just not actively
+		 * running right now), it's preempted, and we should
+		 * yield - it could be a while.
+		 */
+		if (unlikely(on_rq)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
+
+		/*
+		 * Ahh, all good. It wasn't running, and it wasn't
+		 * runnable, which means that it will never become
+		 * running in the future either. We're all done!
+		 */
+		break;
+	}
+
+	return ncsw;
+}
+
+/***
+ * kick_process - kick a running thread to enter/exit the kernel
+ * @p: the to-be-kicked thread
+ *
+ * Cause a process which is running on another CPU to enter
+ * kernel-mode, without any delay. (to get signals handled.)
+ *
+ * NOTE: this function doesnt have to take the runqueue lock,
+ * because all it wants to ensure is that the remote task enters
+ * the kernel. If the IPI races and the task has been migrated
+ * to another CPU then no harm is done and the purpose has been
+ * achieved as well.
+ */
+void kick_process(struct task_struct *p)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if ((cpu != smp_processor_id()) && task_curr(p))
+		smp_send_reschedule(cpu);
+	preempt_enable();
+}
+
+/*
+ * Return a low guess at the load of a migration-source cpu weighted
+ * according to the scheduling class and "nice" value.
+ *
+ * We want to under-estimate the load of migration sources, to
+ * balance conservatively.
+ */
+static unsigned long source_load(int cpu, int type)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long total = weighted_cpuload(cpu);
+
+	if (type == 0 || !sched_feat(LB_BIAS))
+		return total;
+
+	return min(rq->cpu_load[type-1], total);
+}
+
+/*
+ * Return a high guess at the load of a migration-target cpu weighted
+ * according to the scheduling class and "nice" value.
+ */
+static unsigned long target_load(int cpu, int type)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long total = weighted_cpuload(cpu);
+
+	if (type == 0 || !sched_feat(LB_BIAS))
+		return total;
+
+	return max(rq->cpu_load[type-1], total);
+}
+
+/*
+ * find_idlest_group finds and returns the least busy CPU group within the
+ * domain.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+{
+	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+	unsigned long min_load = ULONG_MAX, this_load = 0;
+	int load_idx = sd->forkexec_idx;
+	int imbalance = 100 + (sd->imbalance_pct-100)/2;
+
+	do {
+		unsigned long load, avg_load;
+		int local_group;
+		int i;
+
+		/* Skip over this group if it has no CPUs allowed */
+		if (!cpumask_intersects(sched_group_cpus(group),
+					&p->cpus_allowed))
+			continue;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
+
+		/* Tally up the load of all CPUs in the group */
+		avg_load = 0;
+
+		for_each_cpu(i, sched_group_cpus(group)) {
+			/* Bias balancing toward cpus of our domain */
+			if (local_group)
+				load = source_load(i, load_idx);
+			else
+				load = target_load(i, load_idx);
+
+			avg_load += load;
+		}
+
+		/* Adjust by relative CPU power of the group */
+		avg_load = sg_div_cpu_power(group,
+				avg_load * SCHED_LOAD_SCALE);
+
+		if (local_group) {
+			this_load = avg_load;
+			this = group;
+		} else if (avg_load < min_load) {
+			min_load = avg_load;
+			idlest = group;
+		}
+	} while (group = group->next, group != sd->groups);
+
+	if (!idlest || 100*this_load < imbalance*min_load)
+		return NULL;
+	return idlest;
+}
+
+/*
+ * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ */
+static int
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+	unsigned long load, min_load = ULONG_MAX;
+	int idlest = -1;
+	int i;
+
+	/* Traverse only the allowed CPUs */
+	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+		load = weighted_cpuload(i);
+
+		if (load < min_load || (load == min_load && i == this_cpu)) {
+			min_load = load;
+			idlest = i;
+		}
+	}
+
+	return idlest;
+}
+
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int sched_balance_self(int cpu, int flag)
+{
+	struct task_struct *t = current;
+	struct sched_domain *tmp, *sd = NULL;
+
+	for_each_domain(cpu, tmp) {
+		/*
+		 * If power savings logic is enabled for a domain, stop there.
+		 */
+		if (tmp->flags & SD_POWERSAVINGS_BALANCE)
+			break;
+		if (tmp->flags & flag)
+			sd = tmp;
+	}
+
+	if (sd)
+		update_shares(sd);
+
+	while (sd) {
+		struct sched_group *group;
+		int new_cpu, weight;
+
+		if (!(sd->flags & flag)) {
+			sd = sd->child;
+			continue;
+		}
+
+		group = find_idlest_group(sd, t, cpu);
+		if (!group) {
+			sd = sd->child;
+			continue;
+		}
+
+		new_cpu = find_idlest_cpu(group, t, cpu);
+		if (new_cpu == -1 || new_cpu == cpu) {
+			/* Now try balancing at a lower domain level of cpu */
+			sd = sd->child;
+			continue;
+		}
+
+		/* Now try balancing at a lower domain level of new_cpu */
+		cpu = new_cpu;
+		weight = cpumask_weight(sched_domain_span(sd));
+		sd = NULL;
+		for_each_domain(cpu, tmp) {
+			if (weight <= cpumask_weight(sched_domain_span(tmp)))
+				break;
+			if (tmp->flags & flag)
+				sd = tmp;
+		}
+		/* while loop will break here if sd == NULL */
+	}
+
+	return cpu;
+}
+
+#endif /* CONFIG_SMP */
+
+/***
+ * try_to_wake_up - wake up a thread
+ * @p: the to-be-woken-up thread
+ * @state: the mask of task states that can be woken
+ * @sync: do a synchronous wakeup?
+ *
+ * Put it on the run-queue if it's not already there. The "current"
+ * thread is always on the run-queue (except when the actual
+ * re-schedule is in progress), and as such you're allowed to do
+ * the simpler "current->state = TASK_RUNNING" to mark yourself
+ * runnable without the overhead of this.
+ *
+ * returns failure only if the task is already active.
+ */
+static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
+{
+	int cpu, orig_cpu, this_cpu, success = 0;
+	unsigned long flags;
+	long old_state;
+	struct rq *rq;
+
+	if (!sched_feat(SYNC_WAKEUPS))
+		sync = 0;
+
+#ifdef CONFIG_SMP
+	if (sched_feat(LB_WAKEUP_UPDATE)) {
+		struct sched_domain *sd;
+
+		this_cpu = raw_smp_processor_id();
+		cpu = task_cpu(p);
+
+		for_each_domain(this_cpu, sd) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+				update_shares(sd);
+				break;
+			}
+		}
+	}
+#endif
+
+	smp_wmb();
+	rq = task_rq_lock(p, &flags);
+	update_rq_clock(rq);
+	old_state = p->state;
+	if (!(old_state & state))
+		goto out;
+
+	if (p->se.on_rq)
+		goto out_running;
+
+	cpu = task_cpu(p);
+	orig_cpu = cpu;
+	this_cpu = smp_processor_id();
+
+#ifdef CONFIG_SMP
+	if (unlikely(task_running(rq, p)))
+		goto out_activate;
+
+	cpu = p->sched_class->select_task_rq(p, sync);
+	if (cpu != orig_cpu) {
+		set_task_cpu(p, cpu);
+		task_rq_unlock(rq, &flags);
+		/* might preempt at this point */
+		rq = task_rq_lock(p, &flags);
+		old_state = p->state;
+		if (!(old_state & state))
+			goto out;
+		if (p->se.on_rq)
+			goto out_running;
+
+		this_cpu = smp_processor_id();
+		cpu = task_cpu(p);
+	}
+
+#ifdef CONFIG_SCHEDSTATS
+	schedstat_inc(rq, ttwu_count);
+	if (cpu == this_cpu)
+		schedstat_inc(rq, ttwu_local);
+	else {
+		struct sched_domain *sd;
+		for_each_domain(this_cpu, sd) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+				schedstat_inc(sd, ttwu_wake_remote);
+				break;
+			}
+		}
+	}
+#endif /* CONFIG_SCHEDSTATS */
+
+out_activate:
+#endif /* CONFIG_SMP */
+	schedstat_inc(p, se.nr_wakeups);
+	if (sync)
+		schedstat_inc(p, se.nr_wakeups_sync);
+	if (orig_cpu != cpu)
+		schedstat_inc(p, se.nr_wakeups_migrate);
+	if (cpu == this_cpu)
+		schedstat_inc(p, se.nr_wakeups_local);
+	else
+		schedstat_inc(p, se.nr_wakeups_remote);
+	activate_task(rq, p, 1);
+	success = 1;
+
+out_running:
+	trace_sched_wakeup(rq, p, success);
+	check_preempt_curr(rq, p, sync);
+
+	p->state = TASK_RUNNING;
+#ifdef CONFIG_SMP
+	if (p->sched_class->task_wake_up)
+		p->sched_class->task_wake_up(rq, p);
+#endif
+out:
+	current->se.last_wakeup = current->se.sum_exec_runtime;
+
+	task_rq_unlock(rq, &flags);
+
+	return success;
+}
+#endif /* !DDE_LINUX */
+
+int wake_up_process(struct task_struct *p)
+{
+	return try_to_wake_up(p, TASK_ALL, 0);
+}
+EXPORT_SYMBOL(wake_up_process);
+
+int wake_up_state(struct task_struct *p, unsigned int state)
+{
+	return try_to_wake_up(p, state, 0);
+}
+
+#ifndef DDE_LINUX
+/*
+ * Perform scheduler related setup for a newly forked process p.
+ * p is forked by current.
+ *
+ * __sched_fork() is basic setup used by init_idle() too:
+ */
+static void __sched_fork(struct task_struct *p)
+{
+	p->se.exec_start		= 0;
+	p->se.sum_exec_runtime		= 0;
+	p->se.prev_sum_exec_runtime	= 0;
+	p->se.last_wakeup		= 0;
+	p->se.avg_overlap		= 0;
+
+#ifdef CONFIG_SCHEDSTATS
+	p->se.wait_start		= 0;
+	p->se.sum_sleep_runtime		= 0;
+	p->se.sleep_start		= 0;
+	p->se.block_start		= 0;
+	p->se.sleep_max			= 0;
+	p->se.block_max			= 0;
+	p->se.exec_max			= 0;
+	p->se.slice_max			= 0;
+	p->se.wait_max			= 0;
+#endif
+
+	INIT_LIST_HEAD(&p->rt.run_list);
+	p->se.on_rq = 0;
+	INIT_LIST_HEAD(&p->se.group_node);
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	INIT_HLIST_HEAD(&p->preempt_notifiers);
+#endif
+
+	/*
+	 * We mark the process as running here, but have not actually
+	 * inserted it onto the runqueue yet. 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_RUNNING;
+}
+
+/*
+ * fork()/clone()-time setup:
+ */
+void sched_fork(struct task_struct *p, int clone_flags)
+{
+	int cpu = get_cpu();
+
+	__sched_fork(p);
+
+#ifdef CONFIG_SMP
+	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
+#endif
+	set_task_cpu(p, cpu);
+
+	/*
+	 * Make sure we do not leak PI boosting priority to the child:
+	 */
+	p->prio = current->normal_prio;
+	if (!rt_prio(p->prio))
+		p->sched_class = &fair_sched_class;
+
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+	if (likely(sched_info_on()))
+		memset(&p->sched_info, 0, sizeof(p->sched_info));
+#endif
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+	p->oncpu = 0;
+#endif
+#ifdef CONFIG_PREEMPT
+	/* Want to start with kernel preemption disabled. */
+	task_thread_info(p)->preempt_count = 1;
+#endif
+	put_cpu();
+}
+
+/*
+ * wake_up_new_task - wake up a newly created task for the first time.
+ *
+ * This function will do some initial scheduler statistics housekeeping
+ * that must be done for every newly created context, then puts the task
+ * on the runqueue and wakes it.
+ */
+void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
+{
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &flags);
+	BUG_ON(p->state != TASK_RUNNING);
+	update_rq_clock(rq);
+
+	p->prio = effective_prio(p);
+
+	if (!p->sched_class->task_new || !current->se.on_rq) {
+		activate_task(rq, p, 0);
+	} else {
+		/*
+		 * Let the scheduling class do new task startup
+		 * management (if any):
+		 */
+		p->sched_class->task_new(rq, p);
+		inc_nr_running(rq);
+	}
+	trace_sched_wakeup_new(rq, p, 1);
+	check_preempt_curr(rq, p, 0);
+#ifdef CONFIG_SMP
+	if (p->sched_class->task_wake_up)
+		p->sched_class->task_wake_up(rq, p);
+#endif
+	task_rq_unlock(rq, &flags);
+}
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+
+/**
+ * preempt_notifier_register - tell me when current is being being preempted & rescheduled
+ * @notifier: notifier struct to register
+ */
+void preempt_notifier_register(struct preempt_notifier *notifier)
+{
+	hlist_add_head(&notifier->link, &current->preempt_notifiers);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_register);
+
+/**
+ * preempt_notifier_unregister - no longer interested in preemption notifications
+ * @notifier: notifier struct to unregister
+ *
+ * This is safe to call from within a preemption notifier.
+ */
+void preempt_notifier_unregister(struct preempt_notifier *notifier)
+{
+	hlist_del(&notifier->link);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+	struct preempt_notifier *notifier;
+	struct hlist_node *node;
+
+	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+		notifier->ops->sched_in(notifier, raw_smp_processor_id());
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+	struct preempt_notifier *notifier;
+	struct hlist_node *node;
+
+	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+		notifier->ops->sched_out(notifier, next);
+}
+
+#else /* !CONFIG_PREEMPT_NOTIFIERS */
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+}
+
+#endif /* CONFIG_PREEMPT_NOTIFIERS */
+
+/**
+ * prepare_task_switch - prepare to switch tasks
+ * @rq: the runqueue preparing to switch
+ * @prev: the current task that is being switched out
+ * @next: the task we are going to switch to.
+ *
+ * This is called with the rq lock held and interrupts off. It must
+ * be paired with a subsequent finish_task_switch after the context
+ * switch.
+ *
+ * prepare_task_switch sets up locking and calls architecture specific
+ * hooks.
+ */
+static inline void
+prepare_task_switch(struct rq *rq, struct task_struct *prev,
+		    struct task_struct *next)
+{
+	fire_sched_out_preempt_notifiers(prev, next);
+	prepare_lock_switch(rq, next);
+	prepare_arch_switch(next);
+}
+
+/**
+ * finish_task_switch - clean up after a task-switch
+ * @rq: runqueue associated with task-switch
+ * @prev: the thread we just switched away from.
+ *
+ * finish_task_switch must be called after the context switch, paired
+ * with a prepare_task_switch call before the context switch.
+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
+ * and do any other architecture-specific cleanup actions.
+ *
+ * Note that we may have delayed dropping an mm in context_switch(). If
+ * so, we finish that here outside of the runqueue lock. (Doing it
+ * with the lock held can cause deadlocks; see schedule() for
+ * details.)
+ */
+static void finish_task_switch(struct rq *rq, struct task_struct *prev)
+	__releases(rq->lock)
+{
+	struct mm_struct *mm = rq->prev_mm;
+	long prev_state;
+
+	rq->prev_mm = NULL;
+
+	/*
+	 * A task struct has one reference for the use as "current".
+	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
+	 * schedule one last time. The schedule call will never return, and
+	 * the scheduled task must drop that reference.
+	 * The test for TASK_DEAD must occur while the runqueue locks are
+	 * still held, otherwise prev could be scheduled on another cpu, die
+	 * there before we look at prev->state, and then the reference would
+	 * be dropped twice.
+	 *		Manfred Spraul <manfred@colorfullife.com>
+	 */
+	prev_state = prev->state;
+	finish_arch_switch(prev);
+	finish_lock_switch(rq, prev);
+#ifdef CONFIG_SMP
+	if (current->sched_class->post_schedule)
+		current->sched_class->post_schedule(rq);
+#endif
+
+	fire_sched_in_preempt_notifiers(current);
+	if (mm)
+		mmdrop(mm);
+	if (unlikely(prev_state == TASK_DEAD)) {
+		/*
+		 * Remove function-return probe instances associated with this
+		 * task and put them back on the free list.
+		 */
+		kprobe_flush_task(prev);
+		put_task_struct(prev);
+	}
+}
+
+/**
+ * schedule_tail - first thing a freshly forked thread must call.
+ * @prev: the thread we just switched away from.
+ */
+asmlinkage void schedule_tail(struct task_struct *prev)
+	__releases(rq->lock)
+{
+	struct rq *rq = this_rq();
+
+	finish_task_switch(rq, prev);
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+	/* In this case, finish_task_switch does not reenable preemption */
+	preempt_enable();
+#endif
+	if (current->set_child_tid)
+		put_user(task_pid_vnr(current), current->set_child_tid);
+}
+
+/*
+ * context_switch - switch to the new MM and the new
+ * thread's register state.
+ */
+static inline void
+context_switch(struct rq *rq, struct task_struct *prev,
+	       struct task_struct *next)
+{
+	struct mm_struct *mm, *oldmm;
+
+	prepare_task_switch(rq, prev, next);
+	trace_sched_switch(rq, prev, next);
+	mm = next->mm;
+	oldmm = prev->active_mm;
+	/*
+	 * For paravirt, this is coupled with an exit in switch_to to
+	 * combine the page table reload and the switch backend into
+	 * one hypercall.
+	 */
+	arch_enter_lazy_cpu_mode();
+
+	if (unlikely(!mm)) {
+		next->active_mm = oldmm;
+		atomic_inc(&oldmm->mm_count);
+		enter_lazy_tlb(oldmm, next);
+	} else
+		switch_mm(oldmm, mm, next);
+
+	if (unlikely(!prev->mm)) {
+		prev->active_mm = NULL;
+		rq->prev_mm = oldmm;
+	}
+	/*
+	 * Since the runqueue lock will be released by the next
+	 * task (which is an invalid locking op but in the case
+	 * of the scheduler it's an obvious special-case), so we
+	 * do an early lockdep release here:
+	 */
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+#endif
+
+	/* Here we just switch the register state and the stack. */
+	switch_to(prev, next, prev);
+
+	barrier();
+	/*
+	 * this_rq must be evaluated again because prev may have moved
+	 * CPUs since it called schedule(), thus the 'rq' on its stack
+	 * frame will be invalid.
+	 */
+	finish_task_switch(this_rq(), prev);
+}
+
+/*
+ * nr_running, nr_uninterruptible and nr_context_switches:
+ *
+ * externally visible scheduler statistics: current number of runnable
+ * threads, current number of uninterruptible-sleeping threads, total
+ * number of context switches performed since bootup.
+ */
+unsigned long nr_running(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_online_cpu(i)
+		sum += cpu_rq(i)->nr_running;
+
+	return sum;
+}
+
+unsigned long nr_uninterruptible(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += cpu_rq(i)->nr_uninterruptible;
+
+	/*
+	 * Since we read the counters lockless, it might be slightly
+	 * inaccurate. Do not allow it to go below zero though:
+	 */
+	if (unlikely((long)sum < 0))
+		sum = 0;
+
+	return sum;
+}
+
+unsigned long long nr_context_switches(void)
+{
+	int i;
+	unsigned long long sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += cpu_rq(i)->nr_switches;
+
+	return sum;
+}
+
+unsigned long nr_iowait(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += atomic_read(&cpu_rq(i)->nr_iowait);
+
+	return sum;
+}
+
+unsigned long nr_active(void)
+{
+	unsigned long i, running = 0, uninterruptible = 0;
+
+	for_each_online_cpu(i) {
+		running += cpu_rq(i)->nr_running;
+		uninterruptible += cpu_rq(i)->nr_uninterruptible;
+	}
+
+	if (unlikely((long)uninterruptible < 0))
+		uninterruptible = 0;
+
+	return running + uninterruptible;
+}
+
+/*
+ * Update rq->cpu_load[] statistics. This function is usually called every
+ * scheduler tick (TICK_NSEC).
+ */
+static void update_cpu_load(struct rq *this_rq)
+{
+	unsigned long this_load = this_rq->load.weight;
+	int i, scale;
+
+	this_rq->nr_load_updates++;
+
+	/* Update our load: */
+	for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
+		unsigned long old_load, new_load;
+
+		/* scale is effectively 1 << i now, and >> i divides by scale */
+
+		old_load = this_rq->cpu_load[i];
+		new_load = this_load;
+		/*
+		 * Round up the averaging division if load is increasing. This
+		 * prevents us from getting stuck on 9 if the load is 10, for
+		 * example.
+		 */
+		if (new_load > old_load)
+			new_load += scale-1;
+		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
+	}
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	if (rq1 == rq2) {
+		spin_lock(&rq1->lock);
+		__acquire(rq2->lock);	/* Fake it out ;) */
+	} else {
+		if (rq1 < rq2) {
+			spin_lock(&rq1->lock);
+			spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+		} else {
+			spin_lock(&rq2->lock);
+			spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+		}
+	}
+	update_rq_clock(rq1);
+	update_rq_clock(rq2);
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	spin_unlock(&rq1->lock);
+	if (rq1 != rq2)
+		spin_unlock(&rq2->lock);
+	else
+		__release(rq2->lock);
+}
+
+/*
+ * If dest_cpu is allowed for this process, migrate the task to it.
+ * This is accomplished by forcing the cpu_allowed mask to only
+ * allow dest_cpu, which will force the cpu onto dest_cpu. Then
+ * the cpu_allowed mask is restored.
+ */
+static void sched_migrate_task(struct task_struct *p, int dest_cpu)
+{
+	struct migration_req req;
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &flags);
+	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
+	    || unlikely(!cpu_active(dest_cpu)))
+		goto out;
+
+	/* 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);
+
+		return;
+	}
+out:
+	task_rq_unlock(rq, &flags);
+}
+
+/*
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
+ */
+void sched_exec(void)
+{
+	int new_cpu, this_cpu = get_cpu();
+	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
+	put_cpu();
+	if (new_cpu != this_cpu)
+		sched_migrate_task(current, new_cpu);
+}
+
+/*
+ * pull_task - move a task from a remote runqueue to the local runqueue.
+ * Both runqueues must be locked.
+ */
+static void pull_task(struct rq *src_rq, struct task_struct *p,
+		      struct rq *this_rq, int this_cpu)
+{
+	deactivate_task(src_rq, p, 0);
+	set_task_cpu(p, this_cpu);
+	activate_task(this_rq, p, 0);
+	/*
+	 * Note that idle threads have a prio of MAX_PRIO, for this test
+	 * to be always true for them.
+	 */
+	check_preempt_curr(this_rq, p, 0);
+}
+
+/*
+ * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ */
+static
+int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
+		     struct sched_domain *sd, enum cpu_idle_type idle,
+		     int *all_pinned)
+{
+	/*
+	 * We do not migrate tasks that are:
+	 * 1) running (obviously), or
+	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
+	 * 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);
+		return 0;
+	}
+	*all_pinned = 0;
+
+	if (task_running(rq, p)) {
+		schedstat_inc(p, se.nr_failed_migrations_running);
+		return 0;
+	}
+
+	/*
+	 * Aggressive migration if:
+	 * 1) task is cache cold, or
+	 * 2) too many balance attempts have failed.
+	 */
+
+	if (!task_hot(p, rq->clock, sd) ||
+			sd->nr_balance_failed > sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+		if (task_hot(p, rq->clock, sd)) {
+			schedstat_inc(sd, lb_hot_gained[idle]);
+			schedstat_inc(p, se.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
+
+	if (task_hot(p, rq->clock, sd)) {
+		schedstat_inc(p, se.nr_failed_migrations_hot);
+		return 0;
+	}
+	return 1;
+}
+
+static unsigned long
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      unsigned long max_load_move, struct sched_domain *sd,
+	      enum cpu_idle_type idle, int *all_pinned,
+	      int *this_best_prio, struct rq_iterator *iterator)
+{
+	int loops = 0, pulled = 0, pinned = 0;
+	struct task_struct *p;
+	long rem_load_move = max_load_move;
+
+	if (max_load_move == 0)
+		goto out;
+
+	pinned = 1;
+
+	/*
+	 * Start the load-balancing iterator:
+	 */
+	p = iterator->start(iterator->arg);
+next:
+	if (!p || loops++ > sysctl_sched_nr_migrate)
+		goto out;
+
+	if ((p->se.load.weight >> 1) > rem_load_move ||
+	    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
+		p = iterator->next(iterator->arg);
+		goto next;
+	}
+
+	pull_task(busiest, p, this_rq, this_cpu);
+	pulled++;
+	rem_load_move -= p->se.load.weight;
+
+	/*
+	 * We only want to steal up to the prescribed amount of weighted load.
+	 */
+	if (rem_load_move > 0) {
+		if (p->prio < *this_best_prio)
+			*this_best_prio = p->prio;
+		p = iterator->next(iterator->arg);
+		goto next;
+	}
+out:
+	/*
+	 * Right now, this is one of only two places pull_task() is called,
+	 * so we can safely collect pull_task() stats here rather than
+	 * inside pull_task().
+	 */
+	schedstat_add(sd, lb_gained[idle], pulled);
+
+	if (all_pinned)
+		*all_pinned = pinned;
+
+	return max_load_move - rem_load_move;
+}
+
+/*
+ * move_tasks tries to move up to max_load_move weighted load from busiest to
+ * this_rq, as part of a balancing operation within domain "sd".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		      unsigned long max_load_move,
+		      struct sched_domain *sd, enum cpu_idle_type idle,
+		      int *all_pinned)
+{
+	const struct sched_class *class = sched_class_highest;
+	unsigned long total_load_moved = 0;
+	int this_best_prio = this_rq->curr->prio;
+
+	do {
+		total_load_moved +=
+			class->load_balance(this_rq, this_cpu, busiest,
+				max_load_move - total_load_moved,
+				sd, idle, all_pinned, &this_best_prio);
+		class = class->next;
+
+		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
+			break;
+
+	} while (class && max_load_move > total_load_moved);
+
+	return total_load_moved > 0;
+}
+
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		   struct sched_domain *sd, enum cpu_idle_type idle,
+		   struct rq_iterator *iterator)
+{
+	struct task_struct *p = iterator->start(iterator->arg);
+	int pinned = 0;
+
+	while (p) {
+		if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
+			pull_task(busiest, p, this_rq, this_cpu);
+			/*
+			 * Right now, this is only the second place pull_task()
+			 * is called, so we can safely collect pull_task()
+			 * stats here rather than inside pull_task().
+			 */
+			schedstat_inc(sd, lb_gained[idle]);
+
+			return 1;
+		}
+		p = iterator->next(iterator->arg);
+	}
+
+	return 0;
+}
+
+/*
+ * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * part of active balancing operations within "domain".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+			 struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	const struct sched_class *class;
+
+	for (class = sched_class_highest; class; class = class->next)
+		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
+			return 1;
+
+	return 0;
+}
+
+/*
+ * find_busiest_group finds and returns the busiest CPU group within the
+ * domain. It calculates and returns the amount of weighted load which
+ * should be moved to restore balance via the imbalance parameter.
+ */
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+		   unsigned long *imbalance, enum cpu_idle_type idle,
+		   int *sd_idle, const struct cpumask *cpus, int *balance)
+{
+	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
+	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
+	unsigned long max_pull;
+	unsigned long busiest_load_per_task, busiest_nr_running;
+	unsigned long this_load_per_task, this_nr_running;
+	int load_idx, group_imb = 0;
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+	int power_savings_balance = 1;
+	unsigned long leader_nr_running = 0, min_load_per_task = 0;
+	unsigned long min_nr_running = ULONG_MAX;
+	struct sched_group *group_min = NULL, *group_leader = NULL;
+#endif
+
+	max_load = this_load = total_load = total_pwr = 0;
+	busiest_load_per_task = busiest_nr_running = 0;
+	this_load_per_task = this_nr_running = 0;
+
+	if (idle == CPU_NOT_IDLE)
+		load_idx = sd->busy_idx;
+	else if (idle == CPU_NEWLY_IDLE)
+		load_idx = sd->newidle_idx;
+	else
+		load_idx = sd->idle_idx;
+
+	do {
+		unsigned long load, group_capacity, max_cpu_load, min_cpu_load;
+		int local_group;
+		int i;
+		int __group_imb = 0;
+		unsigned int balance_cpu = -1, first_idle_cpu = 0;
+		unsigned long sum_nr_running, sum_weighted_load;
+		unsigned long sum_avg_load_per_task;
+		unsigned long avg_load_per_task;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
+
+		if (local_group)
+			balance_cpu = cpumask_first(sched_group_cpus(group));
+
+		/* Tally up the load of all CPUs in the group */
+		sum_weighted_load = sum_nr_running = avg_load = 0;
+		sum_avg_load_per_task = avg_load_per_task = 0;
+
+		max_cpu_load = 0;
+		min_cpu_load = ~0UL;
+
+		for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+			struct rq *rq = cpu_rq(i);
+
+			if (*sd_idle && rq->nr_running)
+				*sd_idle = 0;
+
+			/* Bias balancing toward cpus of our domain */
+			if (local_group) {
+				if (idle_cpu(i) && !first_idle_cpu) {
+					first_idle_cpu = 1;
+					balance_cpu = i;
+				}
+
+				load = target_load(i, load_idx);
+			} else {
+				load = source_load(i, load_idx);
+				if (load > max_cpu_load)
+					max_cpu_load = load;
+				if (min_cpu_load > load)
+					min_cpu_load = load;
+			}
+
+			avg_load += load;
+			sum_nr_running += rq->nr_running;
+			sum_weighted_load += weighted_cpuload(i);
+
+			sum_avg_load_per_task += cpu_avg_load_per_task(i);
+		}
+
+		/*
+		 * First idle cpu or the first cpu(busiest) in this sched group
+		 * is eligible for doing load balancing at this and above
+		 * domains. In the newly idle case, we will allow all the cpu's
+		 * to do the newly idle load balance.
+		 */
+		if (idle != CPU_NEWLY_IDLE && local_group &&
+		    balance_cpu != this_cpu && balance) {
+			*balance = 0;
+			goto ret;
+		}
+
+		total_load += avg_load;
+		total_pwr += group->__cpu_power;
+
+		/* Adjust by relative CPU power of the group */
+		avg_load = sg_div_cpu_power(group,
+				avg_load * SCHED_LOAD_SCALE);
+
+
+		/*
+		 * Consider the group unbalanced when the imbalance is larger
+		 * than the average weight of two tasks.
+		 *
+		 * APZ: with cgroup the avg task weight can vary wildly and
+		 *      might not be a suitable number - should we keep a
+		 *      normalized nr_running number somewhere that negates
+		 *      the hierarchy?
+		 */
+		avg_load_per_task = sg_div_cpu_power(group,
+				sum_avg_load_per_task * SCHED_LOAD_SCALE);
+
+		if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+			__group_imb = 1;
+
+		group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+
+		if (local_group) {
+			this_load = avg_load;
+			this = group;
+			this_nr_running = sum_nr_running;
+			this_load_per_task = sum_weighted_load;
+		} else if (avg_load > max_load &&
+			   (sum_nr_running > group_capacity || __group_imb)) {
+			max_load = avg_load;
+			busiest = group;
+			busiest_nr_running = sum_nr_running;
+			busiest_load_per_task = sum_weighted_load;
+			group_imb = __group_imb;
+		}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+		/*
+		 * Busy processors will not participate in power savings
+		 * balance.
+		 */
+		if (idle == CPU_NOT_IDLE ||
+				!(sd->flags & SD_POWERSAVINGS_BALANCE))
+			goto group_next;
+
+		/*
+		 * If the local group is idle or completely loaded
+		 * no need to do power savings balance at this domain
+		 */
+		if (local_group && (this_nr_running >= group_capacity ||
+				    !this_nr_running))
+			power_savings_balance = 0;
+
+		/*
+		 * If a group is already running at full capacity or idle,
+		 * don't include that group in power savings calculations
+		 */
+		if (!power_savings_balance || sum_nr_running >= group_capacity
+		    || !sum_nr_running)
+			goto group_next;
+
+		/*
+		 * Calculate the group which has the least non-idle load.
+		 * This is the group from where we need to pick up the load
+		 * for saving power
+		 */
+		if ((sum_nr_running < min_nr_running) ||
+		    (sum_nr_running == min_nr_running &&
+		     cpumask_first(sched_group_cpus(group)) >
+		     cpumask_first(sched_group_cpus(group_min)))) {
+			group_min = group;
+			min_nr_running = sum_nr_running;
+			min_load_per_task = sum_weighted_load /
+						sum_nr_running;
+		}
+
+		/*
+		 * Calculate the group which is almost near its
+		 * capacity but still has some space to pick up some load
+		 * from other group and save more power
+		 */
+		if (sum_nr_running <= group_capacity - 1) {
+			if (sum_nr_running > leader_nr_running ||
+			    (sum_nr_running == leader_nr_running &&
+			     cpumask_first(sched_group_cpus(group)) <
+			     cpumask_first(sched_group_cpus(group_leader)))) {
+				group_leader = group;
+				leader_nr_running = sum_nr_running;
+			}
+		}
+group_next:
+#endif
+		group = group->next;
+	} while (group != sd->groups);
+
+	if (!busiest || this_load >= max_load || busiest_nr_running == 0)
+		goto out_balanced;
+
+	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
+
+	if (this_load >= avg_load ||
+			100*max_load <= sd->imbalance_pct*this_load)
+		goto out_balanced;
+
+	busiest_load_per_task /= busiest_nr_running;
+	if (group_imb)
+		busiest_load_per_task = min(busiest_load_per_task, avg_load);
+
+	/*
+	 * We're trying to get all the cpus to the average_load, so we don't
+	 * want to push ourselves above the average load, nor do we wish to
+	 * reduce the max loaded cpu below the average load, as either of these
+	 * actions would just result in more rebalancing later, and ping-pong
+	 * tasks around. Thus we look for the minimum possible imbalance.
+	 * Negative imbalances (*we* are more loaded than anyone else) will
+	 * be counted as no imbalance for these purposes -- we can't fix that
+	 * by pulling tasks to us. Be careful of negative numbers as they'll
+	 * appear as very large values with unsigned longs.
+	 */
+	if (max_load <= busiest_load_per_task)
+		goto out_balanced;
+
+	/*
+	 * In the presence of smp nice balancing, certain scenarios can have
+	 * max load less than avg load(as we skip the groups at or below
+	 * its cpu_power, while calculating max_load..)
+	 */
+	if (max_load < avg_load) {
+		*imbalance = 0;
+		goto small_imbalance;
+	}
+
+	/* Don't want to pull so many tasks that a group would go idle */
+	max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
+
+	/* How much load to actually move to equalise the imbalance */
+	*imbalance = min(max_pull * busiest->__cpu_power,
+				(avg_load - this_load) * this->__cpu_power)
+			/ SCHED_LOAD_SCALE;
+
+	/*
+	 * if *imbalance is less than the average load per runnable task
+	 * there is no gaurantee that any tasks will be moved so we'll have
+	 * a think about bumping its value to force at least one task to be
+	 * moved
+	 */
+	if (*imbalance < busiest_load_per_task) {
+		unsigned long tmp, pwr_now, pwr_move;
+		unsigned int imbn;
+
+small_imbalance:
+		pwr_move = pwr_now = 0;
+		imbn = 2;
+		if (this_nr_running) {
+			this_load_per_task /= this_nr_running;
+			if (busiest_load_per_task > this_load_per_task)
+				imbn = 1;
+		} else
+			this_load_per_task = cpu_avg_load_per_task(this_cpu);
+
+		if (max_load - this_load + busiest_load_per_task >=
+					busiest_load_per_task * imbn) {
+			*imbalance = busiest_load_per_task;
+			return busiest;
+		}
+
+		/*
+		 * OK, we don't have enough imbalance to justify moving tasks,
+		 * however we may be able to increase total CPU power used by
+		 * moving them.
+		 */
+
+		pwr_now += busiest->__cpu_power *
+				min(busiest_load_per_task, max_load);
+		pwr_now += this->__cpu_power *
+				min(this_load_per_task, this_load);
+		pwr_now /= SCHED_LOAD_SCALE;
+
+		/* Amount of load we'd subtract */
+		tmp = sg_div_cpu_power(busiest,
+				busiest_load_per_task * SCHED_LOAD_SCALE);
+		if (max_load > tmp)
+			pwr_move += busiest->__cpu_power *
+				min(busiest_load_per_task, max_load - tmp);
+
+		/* Amount of load we'd add */
+		if (max_load * busiest->__cpu_power <
+				busiest_load_per_task * SCHED_LOAD_SCALE)
+			tmp = sg_div_cpu_power(this,
+					max_load * busiest->__cpu_power);
+		else
+			tmp = sg_div_cpu_power(this,
+				busiest_load_per_task * SCHED_LOAD_SCALE);
+		pwr_move += this->__cpu_power *
+				min(this_load_per_task, this_load + tmp);
+		pwr_move /= SCHED_LOAD_SCALE;
+
+		/* Move if we gain throughput */
+		if (pwr_move > pwr_now)
+			*imbalance = busiest_load_per_task;
+	}
+
+	return busiest;
+
+out_balanced:
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+		goto ret;
+
+	if (this == group_leader && group_leader != group_min) {
+		*imbalance = min_load_per_task;
+		if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+			cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+				cpumask_first(sched_group_cpus(group_leader));
+		}
+		return group_min;
+	}
+#endif
+ret:
+	*imbalance = 0;
+	return NULL;
+}
+
+/*
+ * find_busiest_queue - find the busiest runqueue among the cpus in group.
+ */
+static struct rq *
+find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
+		   unsigned long imbalance, const struct cpumask *cpus)
+{
+	struct rq *busiest = NULL, *rq;
+	unsigned long max_load = 0;
+	int i;
+
+	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long wl;
+
+		if (!cpumask_test_cpu(i, cpus))
+			continue;
+
+		rq = cpu_rq(i);
+		wl = weighted_cpuload(i);
+
+		if (rq->nr_running == 1 && wl > imbalance)
+			continue;
+
+		if (wl > max_load) {
+			max_load = wl;
+			busiest = rq;
+		}
+	}
+
+	return busiest;
+}
+
+/*
+ * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
+ * so long as it is large enough.
+ */
+#define MAX_PINNED_INTERVAL	512
+
+/*
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ */
+static int load_balance(int this_cpu, struct rq *this_rq,
+			struct sched_domain *sd, enum cpu_idle_type idle,
+			int *balance, struct cpumask *cpus)
+{
+	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+	struct sched_group *group;
+	unsigned long imbalance;
+	struct rq *busiest;
+	unsigned long flags;
+
+	cpumask_setall(cpus);
+
+	/*
+	 * When power savings policy is enabled for the parent domain, idle
+	 * sibling can pick up load irrespective of busy siblings. In this case,
+	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
+	 * portraying it as CPU_NOT_IDLE.
+	 */
+	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_count[idle]);
+
+redo:
+	update_shares(sd);
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+				   cpus, balance);
+
+	if (*balance == 0)
+		goto out_balanced;
+
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[idle]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, idle, imbalance, cpus);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[idle]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[idle], imbalance);
+
+	ld_moved = 0;
+	if (busiest->nr_running > 1) {
+		/*
+		 * Attempt to move tasks. If find_busiest_group has found
+		 * an imbalance but busiest->nr_running <= 1, the group is
+		 * still unbalanced. ld_moved simply stays zero, so it is
+		 * correctly treated as an imbalance.
+		 */
+		local_irq_save(flags);
+		double_rq_lock(this_rq, busiest);
+		ld_moved = move_tasks(this_rq, this_cpu, busiest,
+				      imbalance, sd, idle, &all_pinned);
+		double_rq_unlock(this_rq, busiest);
+		local_irq_restore(flags);
+
+		/*
+		 * some other cpu did the load balance for us.
+		 */
+		if (ld_moved && this_cpu != smp_processor_id())
+			resched_cpu(this_cpu);
+
+		/* All tasks on this runqueue were pinned by CPU affinity */
+		if (unlikely(all_pinned)) {
+			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			if (!cpumask_empty(cpus))
+				goto redo;
+			goto out_balanced;
+		}
+	}
+
+	if (!ld_moved) {
+		schedstat_inc(sd, lb_failed[idle]);
+		sd->nr_balance_failed++;
+
+		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
+
+			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
+			 */
+			if (!cpumask_test_cpu(this_cpu,
+					      &busiest->curr->cpus_allowed)) {
+				spin_unlock_irqrestore(&busiest->lock, flags);
+				all_pinned = 1;
+				goto out_one_pinned;
+			}
+
+			if (!busiest->active_balance) {
+				busiest->active_balance = 1;
+				busiest->push_cpu = this_cpu;
+				active_balance = 1;
+			}
+			spin_unlock_irqrestore(&busiest->lock, flags);
+			if (active_balance)
+				wake_up_process(busiest->migration_thread);
+
+			/*
+			 * We've kicked active balancing, reset the failure
+			 * counter.
+			 */
+			sd->nr_balance_failed = sd->cache_nice_tries+1;
+		}
+	} else
+		sd->nr_balance_failed = 0;
+
+	if (likely(!active_balance)) {
+		/* We were unbalanced, so reset the balancing interval */
+		sd->balance_interval = sd->min_interval;
+	} else {
+		/*
+		 * If we've begun active balancing, start to back off. This
+		 * case may not be covered by the all_pinned logic if there
+		 * is only 1 task on the busy runqueue (because we don't call
+		 * move_tasks).
+		 */
+		if (sd->balance_interval < sd->max_interval)
+			sd->balance_interval *= 2;
+	}
+
+	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		ld_moved = -1;
+
+	goto out;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[idle]);
+
+	sd->nr_balance_failed = 0;
+
+out_one_pinned:
+	/* tune up the balancing interval */
+	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
+			(sd->balance_interval < sd->max_interval))
+		sd->balance_interval *= 2;
+
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		ld_moved = -1;
+	else
+		ld_moved = 0;
+out:
+	if (ld_moved)
+		update_shares(sd);
+	return ld_moved;
+}
+
+/*
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ *
+ * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
+ * this_rq is locked.
+ */
+static int
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
+			struct cpumask *cpus)
+{
+	struct sched_group *group;
+	struct rq *busiest = NULL;
+	unsigned long imbalance;
+	int ld_moved = 0;
+	int sd_idle = 0;
+	int all_pinned = 0;
+
+	cpumask_setall(cpus);
+
+	/*
+	 * When power savings policy is enabled for the parent domain, idle
+	 * sibling can pick up load irrespective of busy siblings. In this case,
+	 * let the state of idle sibling percolate up as IDLE, instead of
+	 * portraying it as CPU_NOT_IDLE.
+	 */
+	if (sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
+redo:
+	update_shares_locked(this_rq, sd);
+	group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
+				   &sd_idle, cpus, NULL);
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
+
+	ld_moved = 0;
+	if (busiest->nr_running > 1) {
+		/* Attempt to move tasks */
+		double_lock_balance(this_rq, busiest);
+		/* this_rq->clock is already updated */
+		update_rq_clock(busiest);
+		ld_moved = move_tasks(this_rq, this_cpu, busiest,
+					imbalance, sd, CPU_NEWLY_IDLE,
+					&all_pinned);
+		double_unlock_balance(this_rq, busiest);
+
+		if (unlikely(all_pinned)) {
+			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			if (!cpumask_empty(cpus))
+				goto redo;
+		}
+	}
+
+	if (!ld_moved) {
+		int active_balance = 0;
+
+		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
+		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+			return -1;
+
+		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+			return -1;
+
+		if (sd->nr_balance_failed++ < 2)
+			return -1;
+
+		/*
+		 * The only task running in a non-idle cpu can be moved to this
+		 * cpu in an attempt to completely freeup the other CPU
+		 * package. The same method used to move task in load_balance()
+		 * have been extended for load_balance_newidle() to speedup
+		 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
+		 *
+		 * The package power saving logic comes from
+		 * find_busiest_group().  If there are no imbalance, then
+		 * f_b_g() will return NULL.  However when sched_mc={1,2} then
+		 * f_b_g() will select a group from which a running task may be
+		 * pulled to this cpu in order to make the other package idle.
+		 * If there is no opportunity to make a package idle and if
+		 * there are no imbalance, then f_b_g() will return NULL and no
+		 * action will be taken in load_balance_newidle().
+		 *
+		 * Under normal task pull operation due to imbalance, there
+		 * will be more than one task in the source run queue and
+		 * move_tasks() will succeed.  ld_moved will be true and this
+		 * active balance code will not be triggered.
+		 */
+
+		/* Lock busiest in correct order while this_rq is held */
+		double_lock_balance(this_rq, busiest);
+
+		/*
+		 * don't kick the migration_thread, if the curr
+		 * task on busiest cpu can't be moved to this_cpu
+		 */
+		if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+			double_unlock_balance(this_rq, busiest);
+			all_pinned = 1;
+			return ld_moved;
+		}
+
+		if (!busiest->active_balance) {
+			busiest->active_balance = 1;
+			busiest->push_cpu = this_cpu;
+			active_balance = 1;
+		}
+
+		double_unlock_balance(this_rq, busiest);
+		/*
+		 * Should not call ttwu while holding a rq->lock
+		 */
+		spin_unlock(&this_rq->lock);
+		if (active_balance)
+			wake_up_process(busiest->migration_thread);
+		spin_lock(&this_rq->lock);
+
+	} else
+		sd->nr_balance_failed = 0;
+
+	update_shares_locked(this_rq, sd);
+	return ld_moved;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		return -1;
+	sd->nr_balance_failed = 0;
+
+	return 0;
+}
+
+/*
+ * idle_balance is called by schedule() if this_cpu is about to become
+ * idle. Attempts to pull tasks from other CPUs.
+ */
+static void idle_balance(int this_cpu, struct rq *this_rq)
+{
+	struct sched_domain *sd;
+	int pulled_task = 0;
+	unsigned long next_balance = jiffies + HZ;
+	cpumask_var_t tmpmask;
+
+	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
+		return;
+
+	for_each_domain(this_cpu, sd) {
+		unsigned long interval;
+
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		if (sd->flags & SD_BALANCE_NEWIDLE)
+			/* If we've pulled tasks over stop searching: */
+			pulled_task = load_balance_newidle(this_cpu, this_rq,
+							   sd, tmpmask);
+
+		interval = msecs_to_jiffies(sd->balance_interval);
+		if (time_after(next_balance, sd->last_balance + interval))
+			next_balance = sd->last_balance + interval;
+		if (pulled_task)
+			break;
+	}
+	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
+		/*
+		 * We are going idle. next_balance may be set based on
+		 * a busy processor. So reset next_balance.
+		 */
+		this_rq->next_balance = next_balance;
+	}
+	free_cpumask_var(tmpmask);
+}
+
+/*
+ * 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.
+ */
+static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+{
+	int target_cpu = busiest_rq->push_cpu;
+	struct sched_domain *sd;
+	struct rq *target_rq;
+
+	/* Is there any task to move? */
+	if (busiest_rq->nr_running <= 1)
+		return;
+
+	target_rq = cpu_rq(target_cpu);
+
+	/*
+	 * This condition is "impossible", if it occurs
+	 * we need to fix it. Originally reported by
+	 * Bjorn Helgaas on a 128-cpu setup.
+	 */
+	BUG_ON(busiest_rq == target_rq);
+
+	/* 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) {
+		if ((sd->flags & SD_LOAD_BALANCE) &&
+		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+				break;
+	}
+
+	if (likely(sd)) {
+		schedstat_inc(sd, alb_count);
+
+		if (move_one_task(target_rq, target_cpu, busiest_rq,
+				  sd, CPU_IDLE))
+			schedstat_inc(sd, alb_pushed);
+		else
+			schedstat_inc(sd, alb_failed);
+	}
+	double_unlock_balance(busiest_rq, target_rq);
+}
+
+#ifdef CONFIG_NO_HZ
+static struct {
+	atomic_t load_balancer;
+	cpumask_var_t cpu_mask;
+} nohz ____cacheline_aligned = {
+	.load_balancer = ATOMIC_INIT(-1),
+};
+
+/*
+ * This routine will try to nominate the ilb (idle load balancing)
+ * owner among the cpus whose ticks are stopped. ilb owner will do the idle
+ * load balancing on behalf of all those cpus. If all the cpus in the system
+ * go into this tickless mode, then there will be no ilb owner (as there is
+ * no need for one) and all the cpus will sleep till the next wakeup event
+ * arrives...
+ *
+ * For the ilb owner, tick is not stopped. And this tick will be used
+ * for idle load balancing. ilb owner will still be part of
+ * nohz.cpu_mask..
+ *
+ * While stopping the tick, this cpu will become the ilb owner if there
+ * is no other owner. And will be the owner till that cpu becomes busy
+ * or if all cpus in the system stop their ticks at which point
+ * there is no need for ilb owner.
+ *
+ * When the ilb owner becomes busy, it nominates another owner, during the
+ * next busy scheduler_tick()
+ */
+int select_nohz_load_balancer(int stop_tick)
+{
+	int cpu = smp_processor_id();
+
+	if (stop_tick) {
+		cpu_rq(cpu)->in_nohz_recently = 1;
+
+		if (!cpu_active(cpu)) {
+			if (atomic_read(&nohz.load_balancer) != cpu)
+				return 0;
+
+			/*
+			 * If we are going offline and still the leader,
+			 * give up!
+			 */
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+
+			return 0;
+		}
+
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
+
+		/* time for ilb owner also to sleep */
+		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+			if (atomic_read(&nohz.load_balancer) == cpu)
+				atomic_set(&nohz.load_balancer, -1);
+			return 0;
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			/* make me the ilb owner */
+			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
+				return 1;
+		} else if (atomic_read(&nohz.load_balancer) == cpu)
+			return 1;
+	} else {
+		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
+			return 0;
+
+		cpumask_clear_cpu(cpu, nohz.cpu_mask);
+
+		if (atomic_read(&nohz.load_balancer) == cpu)
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+	}
+	return 0;
+}
+#endif
+
+static DEFINE_SPINLOCK(balancing);
+
+/*
+ * It checks each scheduling domain to see if it is due to be balanced,
+ * and initiates a balancing operation if so.
+ *
+ * Balancing parameters are set up in arch_init_sched_domains.
+ */
+static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+{
+	int balance = 1;
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long interval;
+	struct sched_domain *sd;
+	/* Earliest time when we have to do rebalance again */
+	unsigned long next_balance = jiffies + 60*HZ;
+	int update_next_balance = 0;
+	int need_serialize;
+	cpumask_var_t tmp;
+
+	/* Fails alloc?  Rebalancing probably not a priority right now. */
+	if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
+		return;
+
+	for_each_domain(cpu, sd) {
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		interval = sd->balance_interval;
+		if (idle != CPU_IDLE)
+			interval *= sd->busy_factor;
+
+		/* scale ms to jiffies */
+		interval = msecs_to_jiffies(interval);
+		if (unlikely(!interval))
+			interval = 1;
+		if (interval > HZ*NR_CPUS/10)
+			interval = HZ*NR_CPUS/10;
+
+		need_serialize = sd->flags & SD_SERIALIZE;
+
+		if (need_serialize) {
+			if (!spin_trylock(&balancing))
+				goto out;
+		}
+
+		if (time_after_eq(jiffies, sd->last_balance + interval)) {
+			if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+				/*
+				 * We've pulled tasks over so either we're no
+				 * longer idle, or one of our SMT siblings is
+				 * not idle.
+				 */
+				idle = CPU_NOT_IDLE;
+			}
+			sd->last_balance = jiffies;
+		}
+		if (need_serialize)
+			spin_unlock(&balancing);
+out:
+		if (time_after(next_balance, sd->last_balance + interval)) {
+			next_balance = sd->last_balance + interval;
+			update_next_balance = 1;
+		}
+
+		/*
+		 * Stop the load balance at this level. There is another
+		 * CPU in our sched group which is doing load balancing more
+		 * actively.
+		 */
+		if (!balance)
+			break;
+	}
+
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the cpu is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		rq->next_balance = next_balance;
+
+	free_cpumask_var(tmp);
+}
+
+/*
+ * run_rebalance_domains is triggered when needed from the scheduler tick.
+ * In CONFIG_NO_HZ case, the idle load balance owner will do the
+ * rebalancing for all the cpus for whom scheduler ticks are stopped.
+ */
+static void run_rebalance_domains(struct softirq_action *h)
+{
+	int this_cpu = smp_processor_id();
+	struct rq *this_rq = cpu_rq(this_cpu);
+	enum cpu_idle_type idle = this_rq->idle_at_tick ?
+						CPU_IDLE : CPU_NOT_IDLE;
+
+	rebalance_domains(this_cpu, idle);
+
+#ifdef CONFIG_NO_HZ
+	/*
+	 * If this cpu is the owner for idle load balancing, then do the
+	 * balancing on behalf of the other idle cpus whose ticks are
+	 * stopped.
+	 */
+	if (this_rq->idle_at_tick &&
+	    atomic_read(&nohz.load_balancer) == this_cpu) {
+		struct rq *rq;
+		int balance_cpu;
+
+		for_each_cpu(balance_cpu, nohz.cpu_mask) {
+			if (balance_cpu == this_cpu)
+				continue;
+
+			/*
+			 * If this cpu gets work to do, stop the load balancing
+			 * work being done for other cpus. Next load
+			 * balancing owner will pick it up.
+			 */
+			if (need_resched())
+				break;
+
+			rebalance_domains(balance_cpu, CPU_IDLE);
+
+			rq = cpu_rq(balance_cpu);
+			if (time_after(this_rq->next_balance, rq->next_balance))
+				this_rq->next_balance = rq->next_balance;
+		}
+	}
+#endif
+}
+
+/*
+ * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
+ *
+ * In case of CONFIG_NO_HZ, this is the place where we nominate a new
+ * idle load balancing owner or decide to stop the periodic load balancing,
+ * if the whole system is idle.
+ */
+static inline void trigger_load_balance(struct rq *rq, int cpu)
+{
+#ifdef CONFIG_NO_HZ
+	/*
+	 * If we were in the nohz mode recently and busy at the current
+	 * scheduler tick, then check if we need to nominate new idle
+	 * load balancer.
+	 */
+	if (rq->in_nohz_recently && !rq->idle_at_tick) {
+		rq->in_nohz_recently = 0;
+
+		if (atomic_read(&nohz.load_balancer) == cpu) {
+			cpumask_clear_cpu(cpu, nohz.cpu_mask);
+			atomic_set(&nohz.load_balancer, -1);
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			/*
+			 * simple selection for now: Nominate the
+			 * first cpu in the nohz list to be the next
+			 * ilb owner.
+			 *
+			 * TBD: Traverse the sched domains and nominate
+			 * the nearest cpu in the nohz.cpu_mask.
+			 */
+			int ilb = cpumask_first(nohz.cpu_mask);
+
+			if (ilb < nr_cpu_ids)
+				resched_cpu(ilb);
+		}
+	}
+
+	/*
+	 * If this cpu is idle and doing idle load balancing for all the
+	 * cpus with ticks stopped, is it time for that to stop?
+	 */
+	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
+	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+		resched_cpu(cpu);
+		return;
+	}
+
+	/*
+	 * If this cpu is idle and the idle load balancing is done by
+	 * someone else, then no need raise the SCHED_SOFTIRQ
+	 */
+	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
+	    cpumask_test_cpu(cpu, nohz.cpu_mask))
+		return;
+#endif
+	if (time_after_eq(jiffies, rq->next_balance))
+		raise_softirq(SCHED_SOFTIRQ);
+}
+
+#else	/* CONFIG_SMP */
+
+/*
+ * on UP we do not need to balance between CPUs:
+ */
+static inline void idle_balance(int cpu, struct rq *rq)
+{
+}
+
+#endif
+
+DEFINE_PER_CPU(struct kernel_stat, kstat);
+
+EXPORT_PER_CPU_SYMBOL(kstat);
+
+/*
+ * Return any ns on the sched_clock that have not yet been banked in
+ * @p in case that task is currently running.
+ */
+unsigned long long task_delta_exec(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns = 0;
+
+	rq = task_rq_lock(p, &flags);
+
+	if (task_current(rq, p)) {
+		u64 delta_exec;
+
+		update_rq_clock(rq);
+		delta_exec = rq->clock - p->se.exec_start;
+		if ((s64)delta_exec > 0)
+			ns = delta_exec;
+	}
+
+	task_rq_unlock(rq, &flags);
+
+	return ns;
+}
+
+/*
+ * Account user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_user_time(struct task_struct *p, cputime_t cputime,
+		       cputime_t cputime_scaled)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t tmp;
+
+	/* Add user time to process. */
+	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
+	account_group_user_time(p, cputime);
+
+	/* Add user time to cpustat. */
+	tmp = cputime_to_cputime64(cputime);
+	if (TASK_NICE(p) > 0)
+		cpustat->nice = cputime64_add(cpustat->nice, tmp);
+	else
+		cpustat->user = cputime64_add(cpustat->user, tmp);
+	/* Account for user time used */
+	acct_update_integrals(p);
+}
+
+/*
+ * Account guest cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+			       cputime_t cputime_scaled)
+{
+	cputime64_t tmp;
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+	tmp = cputime_to_cputime64(cputime);
+
+	/* Add guest time to process. */
+	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
+	account_group_user_time(p, cputime);
+	p->gtime = cputime_add(p->gtime, cputime);
+
+	/* Add guest time to cpustat. */
+	cpustat->user = cputime64_add(cpustat->user, tmp);
+	cpustat->guest = cputime64_add(cpustat->guest, tmp);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+			 cputime_t cputime, cputime_t cputime_scaled)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t tmp;
+
+	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
+		account_guest_time(p, cputime, cputime_scaled);
+		return;
+	}
+
+	/* Add system time to process. */
+	p->stime = cputime_add(p->stime, cputime);
+	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+	account_group_system_time(p, cputime);
+
+	/* Add system time to cpustat. */
+	tmp = cputime_to_cputime64(cputime);
+	if (hardirq_count() - hardirq_offset)
+		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+	else if (softirq_count())
+		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+	else
+		cpustat->system = cputime64_add(cpustat->system, tmp);
+
+	/* Account for system time used */
+	acct_update_integrals(p);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
+ */
+void account_steal_time(cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+	cpustat->steal = cputime64_add(cpustat->steal, cputime64);
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+void account_idle_time(cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
+	struct rq *rq = this_rq();
+
+	if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+	else
+		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+	cputime_t one_jiffy = jiffies_to_cputime(1);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	struct rq *rq = this_rq();
+
+	if (user_tick)
+		account_user_time(p, one_jiffy, one_jiffy_scaled);
+	else if (p != rq->idle)
+		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+				    one_jiffy_scaled);
+	else
+		account_idle_time(one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+	account_idle_time(jiffies_to_cputime(ticks));
+}
+
+#endif
+
+/*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+cputime_t task_utime(struct task_struct *p)
+{
+	return p->utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+	return p->stime;
+}
+#else
+cputime_t task_utime(struct task_struct *p)
+{
+	clock_t utime = cputime_to_clock_t(p->utime),
+		total = utime + cputime_to_clock_t(p->stime);
+	u64 temp;
+
+	/*
+	 * Use CFS's precise accounting:
+	 */
+	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+
+	if (total) {
+		temp *= utime;
+		do_div(temp, total);
+	}
+	utime = (clock_t)temp;
+
+	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
+	return p->prev_utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+	clock_t stime;
+
+	/*
+	 * Use CFS's precise accounting. (we subtract utime from
+	 * the total, to make sure the total observed by userspace
+	 * grows monotonically - apps rely on that):
+	 */
+	stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
+			cputime_to_clock_t(task_utime(p));
+
+	if (stime >= 0)
+		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+
+	return p->prev_stime;
+}
+#endif
+
+inline cputime_t task_gtime(struct task_struct *p)
+{
+	return p->gtime;
+}
+
+/*
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled.
+ *
+ * It also gets called by the fork code, when changing the parent's
+ * timeslices.
+ */
+void scheduler_tick(void)
+{
+	int cpu = smp_processor_id();
+	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *curr = rq->curr;
+
+	sched_clock_tick();
+
+	spin_lock(&rq->lock);
+	update_rq_clock(rq);
+	update_cpu_load(rq);
+	curr->sched_class->task_tick(rq, curr, 0);
+	spin_unlock(&rq->lock);
+
+#ifdef CONFIG_SMP
+	rq->idle_at_tick = idle_cpu(cpu);
+	trigger_load_balance(rq, cpu);
+#endif
+}
+
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+
+static inline unsigned long get_parent_ip(unsigned long addr)
+{
+	if (in_lock_functions(addr)) {
+		addr = CALLER_ADDR2;
+		if (in_lock_functions(addr))
+			addr = CALLER_ADDR3;
+	}
+	return addr;
+}
+
+void __kprobes add_preempt_count(int val)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Underflow?
+	 */
+	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
+		return;
+#endif
+	preempt_count() += val;
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Spinlock count overflowing soon?
+	 */
+	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
+				PREEMPT_MASK - 10);
+#endif
+	if (preempt_count() == val)
+		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+}
+EXPORT_SYMBOL(add_preempt_count);
+
+void __kprobes sub_preempt_count(int val)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Underflow?
+	 */
+	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+		return;
+	/*
+	 * Is the spinlock portion underflowing?
+	 */
+	if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
+			!(preempt_count() & PREEMPT_MASK)))
+		return;
+#endif
+
+	if (preempt_count() == val)
+		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+	preempt_count() -= val;
+}
+EXPORT_SYMBOL(sub_preempt_count);
+
+#endif
+
+/*
+ * Print scheduling while atomic bug:
+ */
+static noinline void __schedule_bug(struct task_struct *prev)
+{
+	struct pt_regs *regs = get_irq_regs();
+
+	printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
+		prev->comm, prev->pid, preempt_count());
+
+	debug_show_held_locks(prev);
+	print_modules();
+	if (irqs_disabled())
+		print_irqtrace_events(prev);
+
+	if (regs)
+		show_regs(regs);
+	else
+		dump_stack();
+}
+
+/*
+ * Various schedule()-time debugging checks and statistics:
+ */
+static inline void schedule_debug(struct task_struct *prev)
+{
+	/*
+	 * Test if we are atomic. Since do_exit() needs to call into
+	 * schedule() atomically, we ignore that path for now.
+	 * Otherwise, whine if we are scheduling when we should not be.
+	 */
+	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+		__schedule_bug(prev);
+
+	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
+
+	schedstat_inc(this_rq(), sched_count);
+#ifdef CONFIG_SCHEDSTATS
+	if (unlikely(prev->lock_depth >= 0)) {
+		schedstat_inc(this_rq(), bkl_count);
+		schedstat_inc(prev, sched_info.bkl_count);
+	}
+#endif
+}
+
+/*
+ * Pick up the highest-prio task:
+ */
+static inline struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev)
+{
+	const struct sched_class *class;
+	struct task_struct *p;
+
+	/*
+	 * Optimization: we know that if all tasks are in
+	 * the fair class we can call that function directly:
+	 */
+	if (likely(rq->nr_running == rq->cfs.nr_running)) {
+		p = fair_sched_class.pick_next_task(rq);
+		if (likely(p))
+			return p;
+	}
+
+	class = sched_class_highest;
+	for ( ; ; ) {
+		p = class->pick_next_task(rq);
+		if (p)
+			return p;
+		/*
+		 * Will never be NULL as the idle class always
+		 * returns a non-NULL p:
+		 */
+		class = class->next;
+	}
+}
+
+/*
+ * schedule() is the main scheduler function.
+ */
+asmlinkage void __sched schedule(void)
+{
+	struct task_struct *prev, *next;
+	unsigned long *switch_count;
+	struct rq *rq;
+	int cpu;
+
+need_resched:
+	preempt_disable();
+	cpu = smp_processor_id();
+	rq = cpu_rq(cpu);
+	rcu_qsctr_inc(cpu);
+	prev = rq->curr;
+	switch_count = &prev->nivcsw;
+
+	release_kernel_lock(prev);
+need_resched_nonpreemptible:
+
+	schedule_debug(prev);
+
+	if (sched_feat(HRTICK))
+		hrtick_clear(rq);
+
+	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);
+		switch_count = &prev->nvcsw;
+	}
+
+#ifdef CONFIG_SMP
+	if (prev->sched_class->pre_schedule)
+		prev->sched_class->pre_schedule(rq, prev);
+#endif
+
+	if (unlikely(!rq->nr_running))
+		idle_balance(cpu, rq);
+
+	prev->sched_class->put_prev_task(rq, prev);
+	next = pick_next_task(rq, prev);
+
+	if (likely(prev != next)) {
+		sched_info_switch(prev, next);
+
+		rq->nr_switches++;
+		rq->curr = next;
+		++*switch_count;
+
+		context_switch(rq, prev, next); /* unlocks the rq */
+		/*
+		 * the context switch might have flipped the stack from under
+		 * us, hence refresh the local variables.
+		 */
+		cpu = smp_processor_id();
+		rq = cpu_rq(cpu);
+	} else
+		spin_unlock_irq(&rq->lock);
+
+	if (unlikely(reacquire_kernel_lock(current) < 0))
+		goto need_resched_nonpreemptible;
+
+	preempt_enable_no_resched();
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+		goto need_resched;
+}
+EXPORT_SYMBOL(schedule);
+
+#ifdef CONFIG_PREEMPT
+/*
+ * this is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable. Kernel preemptions off return from interrupt
+ * occur there and call schedule directly.
+ */
+asmlinkage void __sched preempt_schedule(void)
+{
+	struct thread_info *ti = current_thread_info();
+
+	/*
+	 * If there is a non-zero preempt_count or interrupts are disabled,
+	 * we do not want to preempt the current task. Just return..
+	 */
+	if (likely(ti->preempt_count || irqs_disabled()))
+		return;
+
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		schedule();
+		sub_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+}
+EXPORT_SYMBOL(preempt_schedule);
+
+/*
+ * this is the entry point to schedule() from kernel preemption
+ * off of irq context.
+ * Note, that this is called and return with irqs disabled. This will
+ * protect us against recursive calling from irq.
+ */
+asmlinkage void __sched preempt_schedule_irq(void)
+{
+	struct thread_info *ti = current_thread_info();
+
+	/* Catch callers which need to be fixed */
+	BUG_ON(ti->preempt_count || !irqs_disabled());
+
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		local_irq_enable();
+		schedule();
+		local_irq_disable();
+		sub_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+}
+
+#endif /* CONFIG_PREEMPT */
+#endif /* !DDE_LINUX */
+
+int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
+			  void *key)
+{
+	return try_to_wake_up(curr->private, mode, sync);
+}
+EXPORT_SYMBOL(default_wake_function);
+
+/*
+ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int sync, void *key)
+{
+	wait_queue_t *curr, *next;
+
+	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
+		unsigned flags = curr->flags;
+
+		if (curr->func(curr, mode, sync, key) &&
+				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+			break;
+	}
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ */
+void __wake_up(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+{
+	__wake_up_common(q, mode, 1, 0, NULL);
+}
+
+/**
+ * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ */
+void
+__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	unsigned long flags;
+	int sync = 1;
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(!nr_exclusive))
+		sync = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
+
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ */
+void complete(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done++;
+	__wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ */
+void complete_all(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done += UINT_MAX/2;
+	__wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+static inline long __sched
+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);
+		do {
+			if (signal_pending_state(state, current)) {
+				timeout = -ERESTARTSYS;
+				break;
+			}
+			__set_current_state(state);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = schedule_timeout(timeout);
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done && timeout);
+		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
+	}
+	x->done--;
+	return timeout ?: 1;
+}
+
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	timeout = do_wait_for_common(x, timeout, state);
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
+void __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ */
+unsigned long __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ */
+int __sched wait_for_completion_interruptible(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ */
+unsigned long __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ */
+int __sched wait_for_completion_killable(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
+/**
+ *	try_wait_for_completion - try to decrement a completion without blocking
+ *	@x:	completion structure
+ *
+ *	Returns: 0 if a decrement cannot be done without blocking
+ *		 1 if a decrement succeeded.
+ *
+ *	If a completion is being used as a counting completion,
+ *	attempt to decrement the counter without blocking. This
+ *	enables us to avoid waiting if the resource the completion
+ *	is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+	int ret = 1;
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done)
+		ret = 0;
+	else
+		x->done--;
+	spin_unlock_irq(&x->wait.lock);
+	return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *	completion_done - Test to see if a completion has any waiters
+ *	@x:	completion structure
+ *
+ *	Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *		 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+	int ret = 1;
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done)
+		ret = 0;
+	spin_unlock_irq(&x->wait.lock);
+	return ret;
+}
+EXPORT_SYMBOL(completion_done);
+
+static long __sched
+sleep_on_common(wait_queue_head_t *q, int state, long timeout)
+{
+	unsigned long flags;
+	wait_queue_t wait;
+
+	init_waitqueue_entry(&wait, current);
+
+	__set_current_state(state);
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, &wait);
+	spin_unlock(&q->lock);
+	timeout = schedule_timeout(timeout);
+	spin_lock_irq(&q->lock);
+	__remove_wait_queue(q, &wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return timeout;
+}
+
+#ifndef DDE_LINUX
+void __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(interruptible_sleep_on);
+
+long __sched
+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
+}
+EXPORT_SYMBOL(interruptible_sleep_on_timeout);
+
+void __sched sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(sleep_on);
+
+long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
+}
+EXPORT_SYMBOL(sleep_on_timeout);
+
+#ifdef CONFIG_RT_MUTEXES
+
+/*
+ * rt_mutex_setprio - set the current priority of a task
+ * @p: task
+ * @prio: prio value (kernel-internal form)
+ *
+ * This function changes the 'effective' priority of a task. It does
+ * not touch ->normal_prio like __setscheduler().
+ *
+ * Used by the rt_mutex code to implement priority inheritance logic.
+ */
+void rt_mutex_setprio(struct task_struct *p, int prio)
+{
+	unsigned long flags;
+	int oldprio, on_rq, running;
+	struct rq *rq;
+	const struct sched_class *prev_class = p->sched_class;
+
+	BUG_ON(prio < 0 || prio > MAX_PRIO);
+
+	rq = task_rq_lock(p, &flags);
+	update_rq_clock(rq);
+
+	oldprio = p->prio;
+	on_rq = p->se.on_rq;
+	running = task_current(rq, p);
+	if (on_rq)
+		dequeue_task(rq, p, 0);
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
+
+	if (rt_prio(prio))
+		p->sched_class = &rt_sched_class;
+	else
+		p->sched_class = &fair_sched_class;
+
+	p->prio = prio;
+
+	if (running)
+		p->sched_class->set_curr_task(rq);
+	if (on_rq) {
+		enqueue_task(rq, p, 0);
+
+		check_class_changed(rq, p, prev_class, oldprio, running);
+	}
+	task_rq_unlock(rq, &flags);
+}
+
+#endif
+
+void set_user_nice(struct task_struct *p, long nice)
+{
+	int old_prio, delta, on_rq;
+	unsigned long flags;
+	struct rq *rq;
+
+	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+		return;
+	/*
+	 * We have to be careful, if called from sys_setpriority(),
+	 * 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
+	 * it wont have any effect on scheduling until the task is
+	 * SCHED_FIFO/SCHED_RR:
+	 */
+	if (task_has_rt_policy(p)) {
+		p->static_prio = NICE_TO_PRIO(nice);
+		goto out_unlock;
+	}
+	on_rq = p->se.on_rq;
+	if (on_rq)
+		dequeue_task(rq, p, 0);
+
+	p->static_prio = NICE_TO_PRIO(nice);
+	set_load_weight(p);
+	old_prio = p->prio;
+	p->prio = effective_prio(p);
+	delta = p->prio - old_prio;
+
+	if (on_rq) {
+		enqueue_task(rq, p, 0);
+		/*
+		 * If the task increased its priority or is running and
+		 * lowered its priority, then reschedule its CPU:
+		 */
+		if (delta < 0 || (delta > 0 && task_running(rq, p)))
+			resched_task(rq->curr);
+	}
+out_unlock:
+	task_rq_unlock(rq, &flags);
+}
+EXPORT_SYMBOL(set_user_nice);
+
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const struct task_struct *p, const int nice)
+{
+	/* convert nice value [19,-20] to rlimit style value [1,40] */
+	int nice_rlim = 20 - nice;
+
+	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+		capable(CAP_SYS_NICE));
+}
+
+#ifdef __ARCH_WANT_SYS_NICE
+
+/*
+ * sys_nice - change the priority of the current process.
+ * @increment: priority increment
+ *
+ * sys_setpriority is a more generic, but much slower function that
+ * does similar things.
+ */
+SYSCALL_DEFINE1(nice, int, increment)
+{
+	long nice, retval;
+
+	/*
+	 * Setpriority might change our priority at the same moment.
+	 * We don't have to worry. Conceptually one call occurs first
+	 * and we have a single winner.
+	 */
+	if (increment < -40)
+		increment = -40;
+	if (increment > 40)
+		increment = 40;
+
+	nice = PRIO_TO_NICE(current->static_prio) + increment;
+	if (nice < -20)
+		nice = -20;
+	if (nice > 19)
+		nice = 19;
+
+	if (increment < 0 && !can_nice(current, nice))
+		return -EPERM;
+
+	retval = security_task_setnice(current, nice);
+	if (retval)
+		return retval;
+
+	set_user_nice(current, nice);
+	return 0;
+}
+
+#endif
+
+/**
+ * task_prio - return the priority value of a given task.
+ * @p: the task in question.
+ *
+ * This is the priority value as seen by users in /proc.
+ * RT tasks are offset by -200. Normal tasks are centered
+ * around 0, value goes from -16 to +15.
+ */
+int task_prio(const struct task_struct *p)
+{
+	return p->prio - MAX_RT_PRIO;
+}
+
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ */
+int task_nice(const struct task_struct *p)
+{
+	return TASK_NICE(p);
+}
+EXPORT_SYMBOL(task_nice);
+
+/**
+ * idle_cpu - is a given cpu idle currently?
+ * @cpu: the processor in question.
+ */
+int idle_cpu(int cpu)
+{
+	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
+}
+
+/**
+ * idle_task - return the idle task for a given cpu.
+ * @cpu: the processor in question.
+ */
+struct task_struct *idle_task(int cpu)
+{
+	return cpu_rq(cpu)->idle;
+}
+
+/**
+ * find_process_by_pid - find a process with a matching PID value.
+ * @pid: the pid in question.
+ */
+static struct task_struct *find_process_by_pid(pid_t pid)
+{
+	return pid ? find_task_by_vpid(pid) : current;
+}
+
+/* Actually do priority change: must hold rq lock. */
+static void
+__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+{
+	BUG_ON(p->se.on_rq);
+
+	p->policy = policy;
+	switch (p->policy) {
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_IDLE:
+		p->sched_class = &fair_sched_class;
+		break;
+	case SCHED_FIFO:
+	case SCHED_RR:
+		p->sched_class = &rt_sched_class;
+		break;
+	}
+
+	p->rt_priority = prio;
+	p->normal_prio = normal_prio(p);
+	/* we are holding p->pi_lock already */
+	p->prio = rt_mutex_getprio(p);
+	set_load_weight(p);
+}
+#endif
+
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+	const struct cred *cred = current_cred(), *pcred;
+	bool match;
+
+	rcu_read_lock();
+	pcred = __task_cred(p);
+	match = (cred->euid == pcred->euid ||
+		 cred->euid == pcred->uid);
+	rcu_read_unlock();
+	return match;
+}
+
+static int __sched_setscheduler(struct task_struct *p, int policy,
+				struct sched_param *param, bool user)
+{
+#ifndef DDE_LINUX
+	int retval, oldprio, oldpolicy = -1, on_rq, running;
+	unsigned long flags;
+	const struct sched_class *prev_class = p->sched_class;
+	struct rq *rq;
+
+	/* may grab non-irq protected spin_locks */
+	BUG_ON(in_interrupt());
+recheck:
+	/* double check policy once rq lock held */
+	if (policy < 0)
+		policy = oldpolicy = p->policy;
+	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
+			policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+			policy != SCHED_IDLE)
+		return -EINVAL;
+	/*
+	 * Valid priorities for SCHED_FIFO and SCHED_RR are
+	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
+	 * SCHED_BATCH and SCHED_IDLE is 0.
+	 */
+	if (param->sched_priority < 0 ||
+	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+		return -EINVAL;
+	if (rt_policy(policy) != (param->sched_priority != 0))
+		return -EINVAL;
+
+	/*
+	 * Allow unprivileged RT tasks to decrease priority:
+	 */
+	if (user && !capable(CAP_SYS_NICE)) {
+		if (rt_policy(policy)) {
+			unsigned long rlim_rtprio;
+
+			if (!lock_task_sighand(p, &flags))
+				return -ESRCH;
+			rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+			unlock_task_sighand(p, &flags);
+
+			/* can't set/change the rt policy */
+			if (policy != p->policy && !rlim_rtprio)
+				return -EPERM;
+
+			/* can't increase priority */
+			if (param->sched_priority > p->rt_priority &&
+			    param->sched_priority > rlim_rtprio)
+				return -EPERM;
+		}
+		/*
+		 * Like positive nice levels, dont allow tasks to
+		 * move out of SCHED_IDLE either:
+		 */
+		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
+			return -EPERM;
+
+		/* can't change other user's priorities */
+		if (!check_same_owner(p))
+			return -EPERM;
+	}
+
+	if (user) {
+#ifdef CONFIG_RT_GROUP_SCHED
+		/*
+		 * Do not allow realtime tasks into groups that have no runtime
+		 * assigned.
+		 */
+		if (rt_bandwidth_enabled() && rt_policy(policy) &&
+				task_group(p)->rt_bandwidth.rt_runtime == 0)
+			return -EPERM;
+#endif
+
+		retval = security_task_setscheduler(p, policy, param);
+		if (retval)
+			return retval;
+	}
+
+	/*
+	 * make sure no PI-waiters arrive (or leave) while we are
+	 * changing the priority of the task:
+	 */
+	spin_lock_irqsave(&p->pi_lock, flags);
+	/*
+	 * To be able to change p->policy safely, the apropriate
+	 * runqueue lock must be held.
+	 */
+	rq = __task_rq_lock(p);
+	/* recheck policy now with rq lock held */
+	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
+		policy = oldpolicy = -1;
+		__task_rq_unlock(rq);
+		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)
+		deactivate_task(rq, p, 0);
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
+
+	oldprio = p->prio;
+	__setscheduler(rq, p, policy, param->sched_priority);
+
+	if (running)
+		p->sched_class->set_curr_task(rq);
+	if (on_rq) {
+		activate_task(rq, p, 0);
+
+		check_class_changed(rq, p, prev_class, oldprio, running);
+	}
+	__task_rq_unlock(rq);
+	spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	rt_mutex_adjust_pi(p);
+
+	return 0;
+#else
+	//WARN_UNIMPL;
+	return 0;
+#endif
+}
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+		       struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, true);
+}
+EXPORT_SYMBOL_GPL(sched_setscheduler);
+
+#ifndef DDE_LINUX
+
+/**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission.  For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+			       struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, false);
+}
+
+static int
+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+{
+	struct sched_param lparam;
+	struct task_struct *p;
+	int retval;
+
+	if (!param || pid < 0)
+		return -EINVAL;
+	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
+		return -EFAULT;
+
+	rcu_read_lock();
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (p != NULL)
+		retval = sched_setscheduler(p, policy, &lparam);
+	rcu_read_unlock();
+
+	return retval;
+}
+
+/**
+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
+ * @pid: the pid in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
+		struct sched_param __user *, param)
+{
+	/* negative values for policy are not valid */
+	if (policy < 0)
+		return -EINVAL;
+
+	return do_sched_setscheduler(pid, policy, param);
+}
+
+/**
+ * sys_sched_setparam - set/change the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the new RT priority.
+ */
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
+{
+	return do_sched_setscheduler(pid, -1, param);
+}
+
+/**
+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
+ * @pid: the pid in question.
+ */
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
+{
+	struct task_struct *p;
+	int retval;
+
+	if (pid < 0)
+		return -EINVAL;
+
+	retval = -ESRCH;
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (p) {
+		retval = security_task_getscheduler(p);
+		if (!retval)
+			retval = p->policy;
+	}
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+/**
+ * sys_sched_getscheduler - get the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the RT priority.
+ */
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
+{
+	struct sched_param lp;
+	struct task_struct *p;
+	int retval;
+
+	if (!param || pid < 0)
+		return -EINVAL;
+
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	retval = -ESRCH;
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	lp.sched_priority = p->rt_priority;
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * This one might sleep, we cannot do it with a spinlock held ...
+	 */
+	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
+
+	return retval;
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+{
+	cpumask_var_t cpus_allowed, new_mask;
+	struct task_struct *p;
+	int retval;
+
+	get_online_cpus();
+	read_lock(&tasklist_lock);
+
+	p = find_process_by_pid(pid);
+	if (!p) {
+		read_unlock(&tasklist_lock);
+		put_online_cpus();
+		return -ESRCH;
+	}
+
+	/*
+	 * It is not safe to call set_cpus_allowed with the
+	 * tasklist_lock held. We will bump the task_struct's
+	 * usage count and then drop tasklist_lock.
+	 */
+	get_task_struct(p);
+	read_unlock(&tasklist_lock);
+
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_put_task;
+	}
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_free_cpus_allowed;
+	}
+	retval = -EPERM;
+	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
+		goto out_unlock;
+
+	retval = security_task_setscheduler(p, 0, NULL);
+	if (retval)
+		goto out_unlock;
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, in_mask, cpus_allowed);
+ again:
+	retval = set_cpus_allowed_ptr(p, new_mask);
+
+	if (!retval) {
+		cpuset_cpus_allowed(p, cpus_allowed);
+		if (!cpumask_subset(new_mask, cpus_allowed)) {
+			/*
+			 * We must have raced with a concurrent cpuset
+			 * update. Just reset the cpus_allowed to the
+			 * cpuset's cpus_allowed
+			 */
+			cpumask_copy(new_mask, cpus_allowed);
+			goto again;
+		}
+	}
+out_unlock:
+	free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+	free_cpumask_var(cpus_allowed);
+out_put_task:
+	put_task_struct(p);
+	put_online_cpus();
+	return retval;
+}
+
+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
+			     struct cpumask *new_mask)
+{
+	if (len < cpumask_size())
+		cpumask_clear(new_mask);
+	else if (len > cpumask_size())
+		len = cpumask_size();
+
+	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
+}
+
+/**
+ * sys_sched_setaffinity - set the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to the new cpu mask
+ */
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
+{
+	cpumask_var_t new_mask;
+	int retval;
+
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
+	if (retval == 0)
+		retval = sched_setaffinity(pid, new_mask);
+	free_cpumask_var(new_mask);
+	return retval;
+}
+
+long sched_getaffinity(pid_t pid, struct cpumask *mask)
+{
+	struct task_struct *p;
+	int retval;
+
+	get_online_cpus();
+	read_lock(&tasklist_lock);
+
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	put_online_cpus();
+
+	return retval;
+}
+
+/**
+ * sys_sched_getaffinity - get the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ */
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
+{
+	int ret;
+	cpumask_var_t mask;
+
+	if (len < cpumask_size())
+		return -EINVAL;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = sched_getaffinity(pid, mask);
+	if (ret == 0) {
+		if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+			ret = -EFAULT;
+		else
+			ret = cpumask_size();
+	}
+	free_cpumask_var(mask);
+
+	return ret;
+}
+
+/**
+ * sys_sched_yield - yield the current processor to other threads.
+ *
+ * This function yields the current CPU to other tasks. If there are no
+ * other threads running on this CPU then this function will return.
+ */
+SYSCALL_DEFINE0(sched_yield)
+{
+	struct rq *rq = this_rq_lock();
+
+	schedstat_inc(rq, yld_count);
+	current->sched_class->yield_task(rq);
+
+	/*
+	 * Since we are going to call schedule() anyway, there's
+	 * no need to preempt or enable interrupts:
+	 */
+	__release(rq->lock);
+	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+	_raw_spin_unlock(&rq->lock);
+	preempt_enable_no_resched();
+
+	schedule();
+
+	return 0;
+}
+#endif /* !DDE_LINUX */
+
+static void __cond_resched(void)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
+	__might_sleep(__FILE__, __LINE__);
+#endif
+	/*
+	 * The BKS might be reacquired before we have dropped
+	 * PREEMPT_ACTIVE, which could trigger a second
+	 * cond_resched() call.
+	 */
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		schedule();
+		sub_preempt_count(PREEMPT_ACTIVE);
+	} while (need_resched());
+}
+
+int __sched _cond_resched(void)
+{
+	if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
+					system_state == SYSTEM_RUNNING) {
+		__cond_resched();
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(_cond_resched);
+
+/*
+ * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * call schedule, and on return reacquire the lock.
+ *
+ * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
+ * operations here to prevent schedule() from being called twice (once via
+ * spin_unlock(), once by hand).
+ */
+int cond_resched_lock(spinlock_t *lock)
+{
+	int resched = need_resched() && system_state == SYSTEM_RUNNING;
+	int ret = 0;
+
+	if (spin_needbreak(lock) || resched) {
+		spin_unlock(lock);
+		if (resched && need_resched())
+			__cond_resched();
+		else
+			cpu_relax();
+		ret = 1;
+		spin_lock(lock);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(cond_resched_lock);
+
+int __sched cond_resched_softirq(void)
+{
+	BUG_ON(!in_softirq());
+
+	if (need_resched() && system_state == SYSTEM_RUNNING) {
+		local_bh_enable();
+		__cond_resched();
+		local_bh_disable();
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(cond_resched_softirq);
+
+#ifndef DDE_LINUX
+/**
+ * yield - yield the current processor to other threads.
+ *
+ * This is a shortcut for kernel-space yielding - it marks the
+ * thread runnable and calls sys_sched_yield().
+ */
+void __sched yield(void)
+{
+	set_current_state(TASK_RUNNING);
+	sys_sched_yield();
+}
+EXPORT_SYMBOL(yield);
+
+/*
+ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
+ * that process accounting knows that this is a task in IO wait state.
+ *
+ * But don't do that if it is a deliberate, throttling IO wait (this task
+ * has set its backing_dev_info: the queue against which it should throttle)
+ */
+void __sched io_schedule(void)
+{
+	struct rq *rq = &__raw_get_cpu_var(runqueues);
+
+	delayacct_blkio_start();
+	atomic_inc(&rq->nr_iowait);
+	schedule();
+	atomic_dec(&rq->nr_iowait);
+	delayacct_blkio_end();
+}
+EXPORT_SYMBOL(io_schedule);
+
+long __sched io_schedule_timeout(long timeout)
+{
+	struct rq *rq = &__raw_get_cpu_var(runqueues);
+	long ret;
+
+	delayacct_blkio_start();
+	atomic_inc(&rq->nr_iowait);
+	ret = schedule_timeout(timeout);
+	atomic_dec(&rq->nr_iowait);
+	delayacct_blkio_end();
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_max - return maximum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the maximum rt_priority that can be used
+ * by a given scheduling class.
+ */
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = MAX_USER_RT_PRIO-1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_IDLE:
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_min - return minimum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the minimum rt_priority that can be used
+ * by a given scheduling class.
+ */
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = 1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_IDLE:
+		ret = 0;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ */
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+		struct timespec __user *, interval)
+{
+	struct task_struct *p;
+	unsigned int time_slice;
+	int retval;
+	struct timespec t;
+
+	if (pid < 0)
+		return -EINVAL;
+
+	retval = -ESRCH;
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	/*
+	 * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER
+	 * tasks that are on an otherwise idle runqueue:
+	 */
+	time_slice = 0;
+	if (p->policy == SCHED_RR) {
+		time_slice = DEF_TIMESLICE;
+	} else if (p->policy != SCHED_FIFO) {
+		struct sched_entity *se = &p->se;
+		unsigned long flags;
+		struct rq *rq;
+
+		rq = task_rq_lock(p, &flags);
+		if (rq->cfs.load.weight)
+			time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
+		task_rq_unlock(rq, &flags);
+	}
+	read_unlock(&tasklist_lock);
+	jiffies_to_timespec(time_slice, &t);
+	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
+	return retval;
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
+
+void sched_show_task(struct task_struct *p)
+{
+	unsigned long free = 0;
+	unsigned state;
+
+	state = p->state ? __ffs(p->state) + 1 : 0;
+	printk(KERN_INFO "%-13.13s %c", p->comm,
+		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
+#if BITS_PER_LONG == 32
+	if (state == TASK_RUNNING)
+		printk(KERN_CONT " running  ");
+	else
+		printk(KERN_CONT " %08lx ", thread_saved_pc(p));
+#else
+	if (state == TASK_RUNNING)
+		printk(KERN_CONT "  running task    ");
+	else
+		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
+#endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+	{
+		unsigned long *n = end_of_stack(p);
+		while (!*n)
+			n++;
+		free = (unsigned long)n - (unsigned long)end_of_stack(p);
+	}
+#endif
+	printk(KERN_CONT "%5lu %5d %6d\n", free,
+		task_pid_nr(p), task_pid_nr(p->real_parent));
+
+	show_stack(p, NULL);
+}
+
+void show_state_filter(unsigned long state_filter)
+{
+	struct task_struct *g, *p;
+
+#if BITS_PER_LONG == 32
+	printk(KERN_INFO
+		"  task                PC stack   pid father\n");
+#else
+	printk(KERN_INFO
+		"  task                        PC stack   pid father\n");
+#endif
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		/*
+		 * reset the NMI-timeout, listing all files on a slow
+		 * console might take alot of time:
+		 */
+		touch_nmi_watchdog();
+		if (!state_filter || (p->state & state_filter))
+			sched_show_task(p);
+	} while_each_thread(g, p);
+
+	touch_all_softlockup_watchdogs();
+
+#ifdef CONFIG_SCHED_DEBUG
+	sysrq_sched_debug_show();
+#endif
+	read_unlock(&tasklist_lock);
+	/*
+	 * Only show locks if all tasks are dumped:
+	 */
+	if (state_filter == -1)
+		debug_show_all_locks();
+}
+
+void __cpuinit init_idle_bootup_task(struct task_struct *idle)
+{
+	idle->sched_class = &idle_sched_class;
+}
+
+/**
+ * init_idle - set up an idle thread for a given CPU
+ * @idle: task in question
+ * @cpu: cpu the idle task belongs to
+ *
+ * NOTE: this function does not set the idle thread's NEED_RESCHED
+ * flag, to make booting more robust.
+ */
+void __cpuinit init_idle(struct task_struct *idle, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+
+	__sched_fork(idle);
+	idle->se.exec_start = sched_clock();
+
+	idle->prio = idle->normal_prio = MAX_PRIO;
+	cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
+	__set_task_cpu(idle, cpu);
+
+	rq->curr = rq->idle = idle;
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+	idle->oncpu = 1;
+#endif
+	spin_unlock_irqrestore(&rq->lock, flags);
+
+	/* Set the preempt count _outside_ the spinlocks! */
+#if defined(CONFIG_PREEMPT)
+	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
+#else
+	task_thread_info(idle)->preempt_count = 0;
+#endif
+	/*
+	 * The idle tasks have their own, simple scheduling class:
+	 */
+	idle->sched_class = &idle_sched_class;
+	ftrace_graph_init_task(idle);
+}
+#endif /* DDE_LINUX */
+
+/*
+ * In a system that switches off the HZ timer nohz_cpu_mask
+ * indicates which cpus entered this state. This is used
+ * in the rcu update to wait only for active cpus. For system
+ * which do not switch off the HZ timer nohz_cpu_mask should
+ * always be CPU_BITS_NONE.
+ */
+cpumask_var_t nohz_cpu_mask;
+
+#ifndef DDE_LINUX
+/*
+ * Increase the granularity value when there are more CPUs,
+ * because with more CPUs the 'effective latency' as visible
+ * to users decreases. But the relationship is not linear,
+ * so pick a second-best guess by going with the log2 of the
+ * number of CPUs.
+ *
+ * This idea comes from the SD scheduler of Con Kolivas:
+ */
+static inline void sched_init_granularity(void)
+{
+	unsigned int factor = 1 + ilog2(num_online_cpus());
+	const unsigned long limit = 200000000;
+
+	sysctl_sched_min_granularity *= factor;
+	if (sysctl_sched_min_granularity > limit)
+		sysctl_sched_min_granularity = limit;
+
+	sysctl_sched_latency *= factor;
+	if (sysctl_sched_latency > limit)
+		sysctl_sched_latency = limit;
+
+	sysctl_sched_wakeup_granularity *= factor;
+
+	sysctl_sched_shares_ratelimit *= factor;
+}
+
+#ifdef CONFIG_SMP
+/*
+ * 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
+ *    it and puts it into the right queue.
+ * 6) migration thread up()s the semaphore.
+ * 7) we wake up and the migration is done.
+ */
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+{
+	struct migration_req req;
+	unsigned long flags;
+	struct rq *rq;
+	int ret = 0;
+
+	rq = task_rq_lock(p, &flags);
+	if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
+		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (p->sched_class->set_cpus_allowed)
+		p->sched_class->set_cpus_allowed(p, new_mask);
+	else {
+		cpumask_copy(&p->cpus_allowed, new_mask);
+		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	}
+
+	/* Can the task run on the task's current CPU? If so, we're done */
+	if (cpumask_test_cpu(task_cpu(p), new_mask))
+		goto out;
+
+	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
+		/* Need help from migration thread: drop lock and wait. */
+		task_rq_unlock(rq, &flags);
+		wake_up_process(rq->migration_thread);
+		wait_for_completion(&req.done);
+		tlb_migrate_finish(p->mm);
+		return 0;
+	}
+out:
+	task_rq_unlock(rq, &flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
+
+/*
+ * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * this because either it can't run here any more (set_cpus_allowed()
+ * away from this CPU, or CPU going down), or because we're
+ * attempting to rebalance this task on exec (sched_exec).
+ *
+ * So we race with normal scheduler movements, but that's OK, as long
+ * as the task is no longer on this CPU.
+ *
+ * Returns non-zero if task was successfully migrated.
+ */
+static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
+{
+	struct rq *rq_dest, *rq_src;
+	int ret = 0, on_rq;
+
+	if (unlikely(!cpu_active(dest_cpu)))
+		return ret;
+
+	rq_src = cpu_rq(src_cpu);
+	rq_dest = cpu_rq(dest_cpu);
+
+	double_rq_lock(rq_src, rq_dest);
+	/* Already moved. */
+	if (task_cpu(p) != src_cpu)
+		goto done;
+	/* Affinity changed (again). */
+	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+		goto fail;
+
+	on_rq = p->se.on_rq;
+	if (on_rq)
+		deactivate_task(rq_src, p, 0);
+
+	set_task_cpu(p, dest_cpu);
+	if (on_rq) {
+		activate_task(rq_dest, p, 0);
+		check_preempt_curr(rq_dest, p, 0);
+	}
+done:
+	ret = 1;
+fail:
+	double_rq_unlock(rq_src, rq_dest);
+	return ret;
+}
+
+/*
+ * migration_thread - this is a highprio system thread that performs
+ * thread migration by bumping thread off CPU then 'pushing' onto
+ * another runqueue.
+ */
+static int migration_thread(void *data)
+{
+	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;
+
+		spin_lock_irq(&rq->lock);
+
+		if (cpu_is_offline(cpu)) {
+			spin_unlock_irq(&rq->lock);
+			goto wait_to_die;
+		}
+
+		if (rq->active_balance) {
+			active_load_balance(rq, cpu);
+			rq->active_balance = 0;
+		}
+
+		head = &rq->migration_queue;
+
+		if (list_empty(head)) {
+			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);
+
+		spin_unlock(&rq->lock);
+		__migrate_task(req->task, cpu, req->dest_cpu);
+		local_irq_enable();
+
+		complete(&req->done);
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+
+wait_to_die:
+	/* Wait for kthread_stop */
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__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)
+{
+	int ret;
+
+	local_irq_disable();
+	ret = __migrate_task(p, src_cpu, dest_cpu);
+	local_irq_enable();
+	return ret;
+}
+
+/*
+ * 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)
+{
+	int dest_cpu;
+	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));
+
+again:
+	/* Look for allowed, online CPU in same node. */
+	for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
+		if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+			goto move;
+
+	/* Any allowed, online CPU? */
+	dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
+	if (dest_cpu < nr_cpu_ids)
+		goto move;
+
+	/* No more Mr. Nice Guy. */
+	if (dest_cpu >= nr_cpu_ids) {
+		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
+		dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
+
+		/*
+		 * Don't tell them about moving exiting tasks or
+		 * kernel threads (both mm NULL), since they never
+		 * leave kernel.
+		 */
+		if (p->mm && printk_ratelimit()) {
+			printk(KERN_INFO "process %d (%s) no "
+			       "longer affine to cpu%d\n",
+			       task_pid_nr(p), p->comm, dead_cpu);
+		}
+	}
+
+move:
+	/* It can have affinity changed while we were choosing. */
+	if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
+		goto again;
+}
+
+/*
+ * While a dead CPU has no uninterruptible tasks queued at this point,
+ * it might still have a nonzero ->nr_uninterruptible counter, because
+ * for performance reasons the counter is not stricly tracking tasks to
+ * their home CPUs. So we just add the counter to another CPU's counter,
+ * to keep the global sum constant after CPU-down:
+ */
+static void migrate_nr_uninterruptible(struct rq *rq_src)
+{
+	struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
+	unsigned long flags;
+
+	local_irq_save(flags);
+	double_rq_lock(rq_src, rq_dest);
+	rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
+	rq_src->nr_uninterruptible = 0;
+	double_rq_unlock(rq_src, rq_dest);
+	local_irq_restore(flags);
+}
+
+/* Run through task list and migrate tasks from the dead cpu. */
+static void migrate_live_tasks(int src_cpu)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+
+	do_each_thread(t, p) {
+		if (p == current)
+			continue;
+
+		if (task_cpu(p) == src_cpu)
+			move_task_off_dead_cpu(src_cpu, p);
+	} while_each_thread(t, p);
+
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Schedules idle task to be the next runnable task on current CPU.
+ * It does so by boosting its priority to highest possible.
+ * Used by CPU offline code.
+ */
+void sched_idle_next(void)
+{
+	int this_cpu = smp_processor_id();
+	struct rq *rq = cpu_rq(this_cpu);
+	struct task_struct *p = rq->idle;
+	unsigned long flags;
+
+	/* cpu has to be offline */
+	BUG_ON(cpu_online(this_cpu));
+
+	/*
+	 * Strictly not necessary since rest of the CPUs are stopped by now
+	 * and interrupts disabled on the current cpu.
+	 */
+	spin_lock_irqsave(&rq->lock, flags);
+
+	__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
+
+	update_rq_clock(rq);
+	activate_task(rq, p, 0);
+
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+/*
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+	struct mm_struct *mm = current->active_mm;
+
+	BUG_ON(cpu_online(smp_processor_id()));
+
+	if (mm != &init_mm)
+		switch_mm(mm, &init_mm, current);
+	mmdrop(mm);
+}
+
+/* called under rq->lock with disabled interrupts */
+static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
+{
+	struct rq *rq = cpu_rq(dead_cpu);
+
+	/* Must be exiting, otherwise would be on tasklist. */
+	BUG_ON(!p->exit_state);
+
+	/* Cannot have done final schedule yet: would have vanished. */
+	BUG_ON(p->state == TASK_DEAD);
+
+	get_task_struct(p);
+
+	/*
+	 * Drop lock around migration; if someone else moves it,
+	 * that's OK. No task can be added to this CPU, so iteration is
+	 * fine.
+	 */
+	spin_unlock_irq(&rq->lock);
+	move_task_off_dead_cpu(dead_cpu, p);
+	spin_lock_irq(&rq->lock);
+
+	put_task_struct(p);
+}
+
+/* release_task() removes task from tasklist, so we won't find dead tasks. */
+static void migrate_dead_tasks(unsigned int dead_cpu)
+{
+	struct rq *rq = cpu_rq(dead_cpu);
+	struct task_struct *next;
+
+	for ( ; ; ) {
+		if (!rq->nr_running)
+			break;
+		update_rq_clock(rq);
+		next = pick_next_task(rq, rq->curr);
+		if (!next)
+			break;
+		next->sched_class->put_prev_task(rq, next);
+		migrate_dead(dead_cpu, next);
+
+	}
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+
+static struct ctl_table sd_ctl_dir[] = {
+	{
+		.procname	= "sched_domain",
+		.mode		= 0555,
+	},
+	{0, },
+};
+
+static struct ctl_table sd_ctl_root[] = {
+	{
+		.ctl_name	= CTL_KERN,
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= sd_ctl_dir,
+	},
+	{0, },
+};
+
+static struct ctl_table *sd_alloc_ctl_entry(int n)
+{
+	struct ctl_table *entry =
+		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
+
+	return entry;
+}
+
+static void sd_free_ctl_entry(struct ctl_table **tablep)
+{
+	struct ctl_table *entry;
+
+	/*
+	 * In the intermediate directories, both the child directory and
+	 * procname are dynamically allocated and could fail but the mode
+	 * will always be set. In the lowest directory the names are
+	 * static strings and all have proc handlers.
+	 */
+	for (entry = *tablep; entry->mode; entry++) {
+		if (entry->child)
+			sd_free_ctl_entry(&entry->child);
+		if (entry->proc_handler == NULL)
+			kfree(entry->procname);
+	}
+
+	kfree(*tablep);
+	*tablep = NULL;
+}
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		mode_t mode, proc_handler *proc_handler)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(13);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[11], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring);
+	/* &table[12] is terminator */
+
+	return table;
+}
+
+static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+{
+	struct ctl_table *entry, *table;
+	struct sched_domain *sd;
+	int domain_num = 0, i;
+	char buf[32];
+
+	for_each_domain(cpu, sd)
+		domain_num++;
+	entry = table = sd_alloc_ctl_entry(domain_num + 1);
+	if (table == NULL)
+		return NULL;
+
+	i = 0;
+	for_each_domain(cpu, sd) {
+		snprintf(buf, 32, "domain%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_domain_table(sd);
+		entry++;
+		i++;
+	}
+	return table;
+}
+
+static struct ctl_table_header *sd_sysctl_header;
+static void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_online_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_online_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+static void unregister_sched_domain_sysctl(void)
+{
+	if (sd_sysctl_header)
+		unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#else
+static void register_sched_domain_sysctl(void)
+{
+}
+static void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
+static void set_rq_online(struct rq *rq)
+{
+	if (!rq->online) {
+		const struct sched_class *class;
+
+		cpumask_set_cpu(rq->cpu, rq->rd->online);
+		rq->online = 1;
+
+		for_each_class(class) {
+			if (class->rq_online)
+				class->rq_online(rq);
+		}
+	}
+}
+
+static void set_rq_offline(struct rq *rq)
+{
+	if (rq->online) {
+		const struct sched_class *class;
+
+		for_each_class(class) {
+			if (class->rq_offline)
+				class->rq_offline(rq);
+		}
+
+		cpumask_clear_cpu(rq->cpu, rq->rd->online);
+		rq->online = 0;
+	}
+}
+
+/*
+ * migration_call - callback that gets triggered when a CPU is added.
+ * Here we can start up the necessary migration thread for the new CPU.
+ */
+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;
+
+	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);
+		cpu_rq(cpu)->migration_thread = p;
+		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);
+		spin_lock_irqsave(&rq->lock, flags);
+		if (rq->rd) {
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+
+			set_rq_online(rq);
+		}
+		spin_unlock_irqrestore(&rq->lock, flags);
+		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);
+		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);
+		rq->migration_thread = NULL;
+		/* Idle task back to normal (off runqueue, low prio) */
+		spin_lock_irq(&rq->lock);
+		update_rq_clock(rq);
+		deactivate_task(rq, rq->idle, 0);
+		rq->idle->static_prio = MAX_PRIO;
+		__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
+		rq->idle->sched_class = &idle_sched_class;
+		migrate_dead_tasks(cpu);
+		spin_unlock_irq(&rq->lock);
+		cpuset_unlock();
+		migrate_nr_uninterruptible(rq);
+		BUG_ON(rq->nr_running != 0);
+
+		/*
+		 * No need to migrate the tasks: it was best-effort if
+		 * they didn't take sched_hotcpu_mutex. Just wake up
+		 * the requestors.
+		 */
+		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);
+			spin_unlock_irq(&rq->lock);
+			complete(&req->done);
+			spin_lock_irq(&rq->lock);
+		}
+		spin_unlock_irq(&rq->lock);
+		break;
+
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		/* Update our root-domain */
+		rq = cpu_rq(cpu);
+		spin_lock_irqsave(&rq->lock, flags);
+		if (rq->rd) {
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+			set_rq_offline(rq);
+		}
+		spin_unlock_irqrestore(&rq->lock, flags);
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+/* Register at highest priority so that task migration (migrate_all_tasks)
+ * happens before everything else.
+ */
+static struct notifier_block __cpuinitdata migration_notifier = {
+	.notifier_call = migration_call,
+	.priority = 10
+};
+
+static int __init migration_init(void)
+{
+	void *cpu = (void *)(long)smp_processor_id();
+	int err;
+
+	/* Start one for the boot CPU: */
+	err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+	BUG_ON(err == NOTIFY_BAD);
+	migration_call(&migration_notifier, CPU_ONLINE, cpu);
+	register_cpu_notifier(&migration_notifier);
+
+	return err;
+}
+early_initcall(migration_init);
+#endif
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
+				  struct cpumask *groupmask)
+{
+	struct sched_group *group = sd->groups;
+	char str[256];
+
+	cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
+	cpumask_clear(groupmask);
+
+	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+
+	if (!(sd->flags & SD_LOAD_BALANCE)) {
+		printk("does not load-balance\n");
+		if (sd->parent)
+			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+					" has parent");
+		return -1;
+	}
+
+	printk(KERN_CONT "span %s level %s\n", str, sd->name);
+
+	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+		printk(KERN_ERR "ERROR: domain->span does not contain "
+				"CPU%d\n", cpu);
+	}
+	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+		printk(KERN_ERR "ERROR: domain->groups does not contain"
+				" CPU%d\n", cpu);
+	}
+
+	printk(KERN_DEBUG "%*s groups:", level + 1, "");
+	do {
+		if (!group) {
+			printk("\n");
+			printk(KERN_ERR "ERROR: group is NULL\n");
+			break;
+		}
+
+		if (!group->__cpu_power) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: domain->cpu_power not "
+					"set\n");
+			break;
+		}
+
+		if (!cpumask_weight(sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: empty group\n");
+			break;
+		}
+
+		if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: repeated CPUs\n");
+			break;
+		}
+
+		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+
+		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
+		printk(KERN_CONT " %s", str);
+
+		group = group->next;
+	} while (group != sd->groups);
+	printk(KERN_CONT "\n");
+
+	if (!cpumask_equal(sched_domain_span(sd), groupmask))
+		printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+	if (sd->parent &&
+	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
+		printk(KERN_ERR "ERROR: parent span is not a superset "
+			"of domain->span\n");
+	return 0;
+}
+
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+	cpumask_var_t groupmask;
+	int level = 0;
+
+	if (!sd) {
+		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+		return;
+	}
+
+	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+	if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
+		printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
+		return;
+	}
+
+	for (;;) {
+		if (sched_domain_debug_one(sd, cpu, level, groupmask))
+			break;
+		level++;
+		sd = sd->parent;
+		if (!sd)
+			break;
+	}
+	free_cpumask_var(groupmask);
+}
+#else /* !CONFIG_SCHED_DEBUG */
+# define sched_domain_debug(sd, cpu) do { } while (0)
+#endif /* CONFIG_SCHED_DEBUG */
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+	if (cpumask_weight(sched_domain_span(sd)) == 1)
+		return 1;
+
+	/* Following flags need at least 2 groups */
+	if (sd->flags & (SD_LOAD_BALANCE |
+			 SD_BALANCE_NEWIDLE |
+			 SD_BALANCE_FORK |
+			 SD_BALANCE_EXEC |
+			 SD_SHARE_CPUPOWER |
+			 SD_SHARE_PKG_RESOURCES)) {
+		if (sd->groups != sd->groups->next)
+			return 0;
+	}
+
+	/* Following flags don't use groups */
+	if (sd->flags & (SD_WAKE_IDLE |
+			 SD_WAKE_AFFINE |
+			 SD_WAKE_BALANCE))
+		return 0;
+
+	return 1;
+}
+
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
+{
+	unsigned long cflags = sd->flags, pflags = parent->flags;
+
+	if (sd_degenerate(parent))
+		return 1;
+
+	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
+		return 0;
+
+	/* Does parent contain flags not in child? */
+	/* WAKE_BALANCE is a subset of WAKE_AFFINE */
+	if (cflags & SD_WAKE_AFFINE)
+		pflags &= ~SD_WAKE_BALANCE;
+	/* Flags needing groups don't count if only 1 group in parent */
+	if (parent->groups == parent->groups->next) {
+		pflags &= ~(SD_LOAD_BALANCE |
+				SD_BALANCE_NEWIDLE |
+				SD_BALANCE_FORK |
+				SD_BALANCE_EXEC |
+				SD_SHARE_CPUPOWER |
+				SD_SHARE_PKG_RESOURCES);
+		if (nr_node_ids == 1)
+			pflags &= ~SD_SERIALIZE;
+	}
+	if (~cflags & pflags)
+		return 0;
+
+	return 1;
+}
+
+static void free_rootdomain(struct root_domain *rd)
+{
+	cpupri_cleanup(&rd->cpupri);
+
+	free_cpumask_var(rd->rto_mask);
+	free_cpumask_var(rd->online);
+	free_cpumask_var(rd->span);
+	kfree(rd);
+}
+
+static void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+	struct root_domain *old_rd = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+
+	if (rq->rd) {
+		old_rd = rq->rd;
+
+		if (cpumask_test_cpu(rq->cpu, old_rd->online))
+			set_rq_offline(rq);
+
+		cpumask_clear_cpu(rq->cpu, old_rd->span);
+
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
+	}
+
+	atomic_inc(&rd->refcount);
+	rq->rd = rd;
+
+	cpumask_set_cpu(rq->cpu, rd->span);
+	if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+		set_rq_online(rq);
+
+	spin_unlock_irqrestore(&rq->lock, flags);
+
+	if (old_rd)
+		free_rootdomain(old_rd);
+}
+
+static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
+{
+	memset(rd, 0, sizeof(*rd));
+
+	if (bootmem) {
+		alloc_bootmem_cpumask_var(&def_root_domain.span);
+		alloc_bootmem_cpumask_var(&def_root_domain.online);
+		alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
+		cpupri_init(&rd->cpupri, true);
+		return 0;
+	}
+
+	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+		goto out;
+	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+		goto free_span;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_online;
+
+	if (cpupri_init(&rd->cpupri, false) != 0)
+		goto free_rto_mask;
+	return 0;
+
+free_rto_mask:
+	free_cpumask_var(rd->rto_mask);
+free_online:
+	free_cpumask_var(rd->online);
+free_span:
+	free_cpumask_var(rd->span);
+out:
+	return -ENOMEM;
+}
+
+static void init_defrootdomain(void)
+{
+	init_rootdomain(&def_root_domain, true);
+
+	atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+	struct root_domain *rd;
+
+	rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return NULL;
+
+	if (init_rootdomain(rd, false) != 0) {
+		kfree(rd);
+		return NULL;
+	}
+
+	return rd;
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
+ */
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct sched_domain *tmp;
+
+	/* Remove the sched domains which do not contribute to scheduling. */
+	for (tmp = sd; tmp; ) {
+		struct sched_domain *parent = tmp->parent;
+		if (!parent)
+			break;
+
+		if (sd_parent_degenerate(tmp, parent)) {
+			tmp->parent = parent->parent;
+			if (parent->parent)
+				parent->parent->child = tmp;
+		} else
+			tmp = tmp->parent;
+	}
+
+	if (sd && sd_degenerate(sd)) {
+		sd = sd->parent;
+		if (sd)
+			sd->child = NULL;
+	}
+
+	sched_domain_debug(sd, cpu);
+
+	rq_attach_root(rq, rd);
+	rcu_assign_pointer(rq->sd, sd);
+}
+
+/* cpus with isolated domains */
+static cpumask_var_t cpu_isolated_map;
+
+/* Setup the mask of cpus configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+	cpulist_parse(str, cpu_isolated_map);
+	return 1;
+}
+
+__setup("isolcpus=", isolated_cpu_setup);
+
+/*
+ * init_sched_build_groups takes the cpumask we wish to span, and a pointer
+ * to a function which identifies what group(along with sched group) a CPU
+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
+ * (due to the fact that we keep track of groups covered with a struct cpumask).
+ *
+ * init_sched_build_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
+ */
+static void
+init_sched_build_groups(const struct cpumask *span,
+			const struct cpumask *cpu_map,
+			int (*group_fn)(int cpu, const struct cpumask *cpu_map,
+					struct sched_group **sg,
+					struct cpumask *tmpmask),
+			struct cpumask *covered, struct cpumask *tmpmask)
+{
+	struct sched_group *first = NULL, *last = NULL;
+	int i;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct sched_group *sg;
+		int group = group_fn(i, cpu_map, &sg, tmpmask);
+		int j;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		cpumask_clear(sched_group_cpus(sg));
+		sg->__cpu_power = 0;
+
+		for_each_cpu(j, span) {
+			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
+				continue;
+
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
+		}
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+	}
+	last->next = first;
+}
+
+#define SD_NODES_PER_DOMAIN 16
+
+#ifdef CONFIG_NUMA
+
+/**
+ * find_next_best_node - find the next node to include in a sched_domain
+ * @node: node whose sched_domain we're building
+ * @used_nodes: nodes already in the sched_domain
+ *
+ * Find the next node to include in a given scheduling domain. Simply
+ * finds the closest node not already in the @used_nodes map.
+ *
+ * Should use nodemask_t.
+ */
+static int find_next_best_node(int node, nodemask_t *used_nodes)
+{
+	int i, n, val, min_val, best_node = 0;
+
+	min_val = INT_MAX;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		/* Start at @node */
+		n = (node + i) % nr_node_ids;
+
+		if (!nr_cpus_node(n))
+			continue;
+
+		/* Skip already used nodes */
+		if (node_isset(n, *used_nodes))
+			continue;
+
+		/* Simple min distance search */
+		val = node_distance(node, n);
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	node_set(best_node, *used_nodes);
+	return best_node;
+}
+
+/**
+ * sched_domain_node_span - get a cpumask for a node's sched_domain
+ * @node: node whose cpumask we're constructing
+ * @span: resulting cpumask
+ *
+ * Given a node, construct a good cpumask for its sched_domain to span. It
+ * should be one that prevents unnecessary balancing, but also spreads tasks
+ * out optimally.
+ */
+static void sched_domain_node_span(int node, struct cpumask *span)
+{
+	nodemask_t used_nodes;
+	int i;
+
+	cpumask_clear(span);
+	nodes_clear(used_nodes);
+
+	cpumask_or(span, span, cpumask_of_node(node));
+	node_set(node, used_nodes);
+
+	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
+		int next_node = find_next_best_node(node, &used_nodes);
+
+		cpumask_or(span, span, cpumask_of_node(next_node));
+	}
+}
+#endif /* CONFIG_NUMA */
+
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+
+/*
+ * The cpus mask in sched_group and sched_domain hangs off the end.
+ * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space
+ * for nr_cpu_ids < CONFIG_NR_CPUS.
+ */
+struct static_sched_group {
+	struct sched_group sg;
+	DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
+};
+
+struct static_sched_domain {
+	struct sched_domain sd;
+	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
+};
+
+/*
+ * SMT sched-domains:
+ */
+#ifdef CONFIG_SCHED_SMT
+static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+
+static int
+cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
+		 struct sched_group **sg, struct cpumask *unused)
+{
+	if (sg)
+		*sg = &per_cpu(sched_group_cpus, cpu).sg;
+	return cpu;
+}
+#endif /* CONFIG_SCHED_SMT */
+
+/*
+ * multi-core sched-domains:
+ */
+#ifdef CONFIG_SCHED_MC
+static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
+#endif /* CONFIG_SCHED_MC */
+
+#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
+static int
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
+{
+	int group;
+
+	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	group = cpumask_first(mask);
+	if (sg)
+		*sg = &per_cpu(sched_group_core, group).sg;
+	return group;
+}
+#elif defined(CONFIG_SCHED_MC)
+static int
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *unused)
+{
+	if (sg)
+		*sg = &per_cpu(sched_group_core, cpu).sg;
+	return cpu;
+}
+#endif
+
+static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
+
+static int
+cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
+{
+	int group;
+#ifdef CONFIG_SCHED_MC
+	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	group = cpumask_first(mask);
+#else
+	group = cpu;
+#endif
+	if (sg)
+		*sg = &per_cpu(sched_group_phys, group).sg;
+	return group;
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * The init_sched_build_groups can't handle what we want to do with node
+ * groups, so roll our own. Now each node has its own list of groups which
+ * gets dynamically allocated.
+ */
+static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
+static struct sched_group ***sched_group_nodes_bycpu;
+
+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
+
+static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
+				 struct sched_group **sg,
+				 struct cpumask *nodemask)
+{
+	int group;
+
+	cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
+	group = cpumask_first(nodemask);
+
+	if (sg)
+		*sg = &per_cpu(sched_group_allnodes, group).sg;
+	return group;
+}
+
+static void init_numa_sched_groups_power(struct sched_group *group_head)
+{
+	struct sched_group *sg = group_head;
+	int j;
+
+	if (!sg)
+		return;
+	do {
+		for_each_cpu(j, sched_group_cpus(sg)) {
+			struct sched_domain *sd;
+
+			sd = &per_cpu(phys_domains, j).sd;
+			if (j != cpumask_first(sched_group_cpus(sd->groups))) {
+				/*
+				 * Only add "power" once for each
+				 * physical package.
+				 */
+				continue;
+			}
+
+			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+		}
+		sg = sg->next;
+	} while (sg != group_head);
+}
+#endif /* CONFIG_NUMA */
+
+#ifdef CONFIG_NUMA
+/* Free memory allocated for various sched_group structures */
+static void free_sched_groups(const struct cpumask *cpu_map,
+			      struct cpumask *nodemask)
+{
+	int cpu, i;
+
+	for_each_cpu(cpu, cpu_map) {
+		struct sched_group **sched_group_nodes
+			= sched_group_nodes_bycpu[cpu];
+
+		if (!sched_group_nodes)
+			continue;
+
+		for (i = 0; i < nr_node_ids; i++) {
+			struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+			cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+			if (cpumask_empty(nodemask))
+				continue;
+
+			if (sg == NULL)
+				continue;
+			sg = sg->next;
+next_sg:
+			oldsg = sg;
+			sg = sg->next;
+			kfree(oldsg);
+			if (oldsg != sched_group_nodes[i])
+				goto next_sg;
+		}
+		kfree(sched_group_nodes);
+		sched_group_nodes_bycpu[cpu] = NULL;
+	}
+}
+#else /* !CONFIG_NUMA */
+static void free_sched_groups(const struct cpumask *cpu_map,
+			      struct cpumask *nodemask)
+{
+}
+#endif /* CONFIG_NUMA */
+
+/*
+ * Initialize sched groups cpu_power.
+ *
+ * cpu_power indicates the capacity of sched group, which is used while
+ * distributing the load between different sched groups in a sched domain.
+ * Typically cpu_power for all the groups in a sched domain will be same unless
+ * there are asymmetries in the topology. If there are asymmetries, group
+ * having more cpu_power will pickup more load compared to the group having
+ * less cpu_power.
+ *
+ * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
+ * the maximum number of tasks a group can handle in the presence of other idle
+ * or lightly loaded groups in the same sched domain.
+ */
+static void init_sched_groups_power(int cpu, struct sched_domain *sd)
+{
+	struct sched_domain *child;
+	struct sched_group *group;
+
+	WARN_ON(!sd || !sd->groups);
+
+	if (cpu != cpumask_first(sched_group_cpus(sd->groups)))
+		return;
+
+	child = sd->child;
+
+	sd->groups->__cpu_power = 0;
+
+	/*
+	 * For perf policy, if the groups in child domain share resources
+	 * (for example cores sharing some portions of the cache hierarchy
+	 * or SMT), then set this domain groups cpu_power such that each group
+	 * can handle only one task, when there are other idle groups in the
+	 * same sched domain.
+	 */
+	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
+		       (child->flags &
+			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
+		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+		return;
+	}
+
+	/*
+	 * add cpu_power of each child group to this groups cpu_power
+	 */
+	group = child->groups;
+	do {
+		sg_inc_cpu_power(sd->groups, group->__cpu_power);
+		group = group->next;
+	} while (group != child->groups);
+}
+
+/*
+ * Initializers for schedule domains
+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
+ */
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(sd, type)		sd->name = #type
+#else
+# define SD_INIT_NAME(sd, type)		do { } while (0)
+#endif
+
+#define	SD_INIT(sd, type)	sd_init_##type(sd)
+
+#define SD_INIT_FUNC(type)	\
+static noinline void sd_init_##type(struct sched_domain *sd)	\
+{								\
+	memset(sd, 0, sizeof(*sd));				\
+	*sd = SD_##type##_INIT;					\
+	sd->level = SD_LV_##type;				\
+	SD_INIT_NAME(sd, type);					\
+}
+
+SD_INIT_FUNC(CPU)
+#ifdef CONFIG_NUMA
+ SD_INIT_FUNC(ALLNODES)
+ SD_INIT_FUNC(NODE)
+#endif
+#ifdef CONFIG_SCHED_SMT
+ SD_INIT_FUNC(SIBLING)
+#endif
+#ifdef CONFIG_SCHED_MC
+ SD_INIT_FUNC(MC)
+#endif
+
+static int default_relax_domain_level = -1;
+
+static int __init setup_relax_domain_level(char *str)
+{
+	unsigned long val;
+
+	val = simple_strtoul(str, NULL, 0);
+	if (val < SD_LV_MAX)
+		default_relax_domain_level = val;
+
+	return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+				 struct sched_domain_attr *attr)
+{
+	int request;
+
+	if (!attr || attr->relax_domain_level < 0) {
+		if (default_relax_domain_level < 0)
+			return;
+		else
+			request = default_relax_domain_level;
+	} else
+		request = attr->relax_domain_level;
+	if (request < sd->level) {
+		/* turn off idle balance on this domain */
+		sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE);
+	} else {
+		/* turn on idle balance on this domain */
+		sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE);
+	}
+}
+
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int __build_sched_domains(const struct cpumask *cpu_map,
+				 struct sched_domain_attr *attr)
+{
+	int i, err = -ENOMEM;
+	struct root_domain *rd;
+	cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
+		tmpmask;
+#ifdef CONFIG_NUMA
+	cpumask_var_t domainspan, covered, notcovered;
+	struct sched_group **sched_group_nodes = NULL;
+	int sd_allnodes = 0;
+
+	if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
+		goto out;
+	if (!alloc_cpumask_var(&covered, GFP_KERNEL))
+		goto free_domainspan;
+	if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
+		goto free_covered;
+#endif
+
+	if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
+		goto free_notcovered;
+	if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
+		goto free_nodemask;
+	if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
+		goto free_this_sibling_map;
+	if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
+		goto free_this_core_map;
+	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		goto free_send_covered;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * Allocate the per-node list of sched groups
+	 */
+	sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
+				    GFP_KERNEL);
+	if (!sched_group_nodes) {
+		printk(KERN_WARNING "Can not alloc sched group node list\n");
+		goto free_tmpmask;
+	}
+#endif
+
+	rd = alloc_rootdomain();
+	if (!rd) {
+		printk(KERN_WARNING "Cannot alloc root domain\n");
+		goto free_sched_groups;
+	}
+
+#ifdef CONFIG_NUMA
+	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
+#endif
+
+	/*
+	 * Set up domains for cpus specified by the cpu_map.
+	 */
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = NULL, *p;
+
+		cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
+
+#ifdef CONFIG_NUMA
+		if (cpumask_weight(cpu_map) >
+				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
+			sd = &per_cpu(allnodes_domains, i).sd;
+			SD_INIT(sd, ALLNODES);
+			set_domain_attribute(sd, attr);
+			cpumask_copy(sched_domain_span(sd), cpu_map);
+			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
+			p = sd;
+			sd_allnodes = 1;
+		} else
+			p = NULL;
+
+		sd = &per_cpu(node_domains, i).sd;
+		SD_INIT(sd, NODE);
+		set_domain_attribute(sd, attr);
+		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
+		sd->parent = p;
+		if (p)
+			p->child = sd;
+		cpumask_and(sched_domain_span(sd),
+			    sched_domain_span(sd), cpu_map);
+#endif
+
+		p = sd;
+		sd = &per_cpu(phys_domains, i).sd;
+		SD_INIT(sd, CPU);
+		set_domain_attribute(sd, attr);
+		cpumask_copy(sched_domain_span(sd), nodemask);
+		sd->parent = p;
+		if (p)
+			p->child = sd;
+		cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
+
+#ifdef CONFIG_SCHED_MC
+		p = sd;
+		sd = &per_cpu(core_domains, i).sd;
+		SD_INIT(sd, MC);
+		set_domain_attribute(sd, attr);
+		cpumask_and(sched_domain_span(sd), cpu_map,
+						   cpu_coregroup_mask(i));
+		sd->parent = p;
+		p->child = sd;
+		cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+		p = sd;
+		sd = &per_cpu(cpu_domains, i).sd;
+		SD_INIT(sd, SIBLING);
+		set_domain_attribute(sd, attr);
+		cpumask_and(sched_domain_span(sd),
+			    &per_cpu(cpu_sibling_map, i), cpu_map);
+		sd->parent = p;
+		p->child = sd;
+		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
+#endif
+	}
+
+#ifdef CONFIG_SCHED_SMT
+	/* Set up CPU (sibling) groups */
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(this_sibling_map,
+			    &per_cpu(cpu_sibling_map, i), cpu_map);
+		if (i != cpumask_first(this_sibling_map))
+			continue;
+
+		init_sched_build_groups(this_sibling_map, cpu_map,
+					&cpu_to_cpu_group,
+					send_covered, tmpmask);
+	}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+	/* Set up multi-core groups */
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
+		if (i != cpumask_first(this_core_map))
+			continue;
+
+		init_sched_build_groups(this_core_map, cpu_map,
+					&cpu_to_core_group,
+					send_covered, tmpmask);
+	}
+#endif
+
+	/* Set up physical groups */
+	for (i = 0; i < nr_node_ids; i++) {
+		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+		if (cpumask_empty(nodemask))
+			continue;
+
+		init_sched_build_groups(nodemask, cpu_map,
+					&cpu_to_phys_group,
+					send_covered, tmpmask);
+	}
+
+#ifdef CONFIG_NUMA
+	/* Set up node groups */
+	if (sd_allnodes) {
+		init_sched_build_groups(cpu_map, cpu_map,
+					&cpu_to_allnodes_group,
+					send_covered, tmpmask);
+	}
+
+	for (i = 0; i < nr_node_ids; i++) {
+		/* Set up node groups */
+		struct sched_group *sg, *prev;
+		int j;
+
+		cpumask_clear(covered);
+		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+		if (cpumask_empty(nodemask)) {
+			sched_group_nodes[i] = NULL;
+			continue;
+		}
+
+		sched_domain_node_span(i, domainspan);
+		cpumask_and(domainspan, domainspan, cpu_map);
+
+		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				  GFP_KERNEL, i);
+		if (!sg) {
+			printk(KERN_WARNING "Can not alloc domain group for "
+				"node %d\n", i);
+			goto error;
+		}
+		sched_group_nodes[i] = sg;
+		for_each_cpu(j, nodemask) {
+			struct sched_domain *sd;
+
+			sd = &per_cpu(node_domains, j).sd;
+			sd->groups = sg;
+		}
+		sg->__cpu_power = 0;
+		cpumask_copy(sched_group_cpus(sg), nodemask);
+		sg->next = sg;
+		cpumask_or(covered, covered, nodemask);
+		prev = sg;
+
+		for (j = 0; j < nr_node_ids; j++) {
+			int n = (i + j) % nr_node_ids;
+
+			cpumask_complement(notcovered, covered);
+			cpumask_and(tmpmask, notcovered, cpu_map);
+			cpumask_and(tmpmask, tmpmask, domainspan);
+			if (cpumask_empty(tmpmask))
+				break;
+
+			cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
+			if (cpumask_empty(tmpmask))
+				continue;
+
+			sg = kmalloc_node(sizeof(struct sched_group) +
+					  cpumask_size(),
+					  GFP_KERNEL, i);
+			if (!sg) {
+				printk(KERN_WARNING
+				"Can not alloc domain group for node %d\n", j);
+				goto error;
+			}
+			sg->__cpu_power = 0;
+			cpumask_copy(sched_group_cpus(sg), tmpmask);
+			sg->next = prev->next;
+			cpumask_or(covered, covered, tmpmask);
+			prev->next = sg;
+			prev = sg;
+		}
+	}
+#endif
+
+	/* Calculate CPU power for physical packages and nodes */
+#ifdef CONFIG_SCHED_SMT
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
+
+		init_sched_groups_power(i, sd);
+	}
+#endif
+#ifdef CONFIG_SCHED_MC
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(core_domains, i).sd;
+
+		init_sched_groups_power(i, sd);
+	}
+#endif
+
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
+
+		init_sched_groups_power(i, sd);
+	}
+
+#ifdef CONFIG_NUMA
+	for (i = 0; i < nr_node_ids; i++)
+		init_numa_sched_groups_power(sched_group_nodes[i]);
+
+	if (sd_allnodes) {
+		struct sched_group *sg;
+
+		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
+								tmpmask);
+		init_numa_sched_groups_power(sg);
+	}
+#endif
+
+	/* Attach the domains */
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd;
+#ifdef CONFIG_SCHED_SMT
+		sd = &per_cpu(cpu_domains, i).sd;
+#elif defined(CONFIG_SCHED_MC)
+		sd = &per_cpu(core_domains, i).sd;
+#else
+		sd = &per_cpu(phys_domains, i).sd;
+#endif
+		cpu_attach_domain(sd, rd, i);
+	}
+
+	err = 0;
+
+free_tmpmask:
+	free_cpumask_var(tmpmask);
+free_send_covered:
+	free_cpumask_var(send_covered);
+free_this_core_map:
+	free_cpumask_var(this_core_map);
+free_this_sibling_map:
+	free_cpumask_var(this_sibling_map);
+free_nodemask:
+	free_cpumask_var(nodemask);
+free_notcovered:
+#ifdef CONFIG_NUMA
+	free_cpumask_var(notcovered);
+free_covered:
+	free_cpumask_var(covered);
+free_domainspan:
+	free_cpumask_var(domainspan);
+out:
+#endif
+	return err;
+
+free_sched_groups:
+#ifdef CONFIG_NUMA
+	kfree(sched_group_nodes);
+#endif
+	goto free_tmpmask;
+
+#ifdef CONFIG_NUMA
+error:
+	free_sched_groups(cpu_map, tmpmask);
+	free_rootdomain(rd);
+	goto free_tmpmask;
+#endif
+}
+
+static int build_sched_domains(const struct cpumask *cpu_map)
+{
+	return __build_sched_domains(cpu_map, NULL);
+}
+
+static struct cpumask *doms_cur;	/* current sched domains */
+static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;
+				/* attribues of custom domains in 'doms_cur' */
+
+/*
+ * Special case: If a kmalloc of a doms_cur partition (array of
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
+ */
+static cpumask_var_t fallback_doms;
+
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
+{
+	return 0;
+}
+
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * For now this just excludes isolated cpus, but could be used to
+ * exclude other special cases in the future.
+ */
+static int arch_init_sched_domains(const struct cpumask *cpu_map)
+{
+	int err;
+
+	arch_update_cpu_topology();
+	ndoms_cur = 1;
+	doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+	if (!doms_cur)
+		doms_cur = fallback_doms;
+	cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+	dattr_cur = NULL;
+	err = build_sched_domains(doms_cur);
+	register_sched_domain_sysctl();
+
+	return err;
+}
+
+static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
+				       struct cpumask *tmpmask)
+{
+	free_sched_groups(cpu_map, tmpmask);
+}
+
+/*
+ * Detach sched domains from a group of cpus specified in cpu_map
+ * These cpus will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const struct cpumask *cpu_map)
+{
+	/* Save because hotplug lock held. */
+	static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
+	int i;
+
+	for_each_cpu(i, cpu_map)
+		cpu_attach_domain(NULL, &def_root_domain, i);
+	synchronize_sched();
+	arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
+}
+
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+			struct sched_domain_attr *new, int idx_new)
+{
+	struct sched_domain_attr tmp;
+
+	/* fast path */
+	if (!new && !cur)
+		return 1;
+
+	tmp = SD_ATTR_INIT;
+	return !memcmp(cur ? (cur + idx_cur) : &tmp,
+			new ? (new + idx_new) : &tmp,
+			sizeof(struct sched_domain_attr));
+}
+
+/*
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks. This compares
+ * doms_new[] to the current sched domain partitioning, doms_cur[].
+ * It destroys each deleted domain and builds each new domain.
+ *
+ * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * The masks don't intersect (don't overlap.) We should setup one
+ * sched domain for each mask. CPUs not in any of the cpumasks will
+ * not be load balanced. If the same cpumask appears both in the
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be kmalloc'd. This routine takes
+ * ownership of it and will kfree it when done with it. If the caller
+ * failed the kmalloc call, then it can pass in doms_new == NULL &&
+ * ndoms_new == 1, and partition_sched_domains() will fallback to
+ * the single partition 'fallback_doms', it also forces the domains
+ * to be rebuilt.
+ *
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
+ *
+ * Call with hotplug lock held
+ */
+/* FIXME: Change to struct cpumask *doms_new[] */
+void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+			     struct sched_domain_attr *dattr_new)
+{
+	int i, j, n;
+	int new_topology;
+
+	mutex_lock(&sched_domains_mutex);
+
+	/* always unregister in case we don't destroy any domains */
+	unregister_sched_domain_sysctl();
+
+	/* Let architecture update cpu core mappings. */
+	new_topology = arch_update_cpu_topology();
+
+	n = doms_new ? ndoms_new : 0;
+
+	/* Destroy deleted domains */
+	for (i = 0; i < ndoms_cur; i++) {
+		for (j = 0; j < n && !new_topology; j++) {
+			if (cpumask_equal(&doms_cur[i], &doms_new[j])
+			    && dattrs_equal(dattr_cur, i, dattr_new, j))
+				goto match1;
+		}
+		/* no match - a current sched domain not in new doms_new[] */
+		detach_destroy_domains(doms_cur + i);
+match1:
+		;
+	}
+
+	if (doms_new == NULL) {
+		ndoms_cur = 0;
+		doms_new = fallback_doms;
+		cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+		WARN_ON_ONCE(dattr_new);
+	}
+
+	/* Build new domains */
+	for (i = 0; i < ndoms_new; i++) {
+		for (j = 0; j < ndoms_cur && !new_topology; j++) {
+			if (cpumask_equal(&doms_new[i], &doms_cur[j])
+			    && dattrs_equal(dattr_new, i, dattr_cur, j))
+				goto match2;
+		}
+		/* no match - add a new doms_new */
+		__build_sched_domains(doms_new + i,
+					dattr_new ? dattr_new + i : NULL);
+match2:
+		;
+	}
+
+	/* Remember the new sched domains */
+	if (doms_cur != fallback_doms)
+		kfree(doms_cur);
+	kfree(dattr_cur);	/* kfree(NULL) is safe */
+	doms_cur = doms_new;
+	dattr_cur = dattr_new;
+	ndoms_cur = ndoms_new;
+
+	register_sched_domain_sysctl();
+
+	mutex_unlock(&sched_domains_mutex);
+}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+static void arch_reinit_sched_domains(void)
+{
+	get_online_cpus();
+
+	/* Destroy domains first to force the rebuild */
+	partition_sched_domains(0, NULL, NULL);
+
+	rebuild_sched_domains();
+	put_online_cpus();
+}
+
+static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
+{
+	unsigned int level = 0;
+
+	if (sscanf(buf, "%u", &level) != 1)
+		return -EINVAL;
+
+	/*
+	 * level is always be positive so don't check for
+	 * level < POWERSAVINGS_BALANCE_NONE which is 0
+	 * What happens on 0 or 1 byte write,
+	 * need to check for count as well?
+	 */
+
+	if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
+		return -EINVAL;
+
+	if (smt)
+		sched_smt_power_savings = level;
+	else
+		sched_mc_power_savings = level;
+
+	arch_reinit_sched_domains();
+
+	return count;
+}
+
+#ifdef CONFIG_SCHED_MC
+static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
+					   char *page)
+{
+	return sprintf(page, "%u\n", sched_mc_power_savings);
+}
+static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
+					    const char *buf, size_t count)
+{
+	return sched_power_savings_store(buf, count, 0);
+}
+static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
+			 sched_mc_power_savings_show,
+			 sched_mc_power_savings_store);
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
+					    char *page)
+{
+	return sprintf(page, "%u\n", sched_smt_power_savings);
+}
+static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
+					     const char *buf, size_t count)
+{
+	return sched_power_savings_store(buf, count, 1);
+}
+static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
+		   sched_smt_power_savings_show,
+		   sched_smt_power_savings_store);
+#endif
+
+int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
+{
+	int err = 0;
+
+#ifdef CONFIG_SCHED_SMT
+	if (smt_capable())
+		err = sysfs_create_file(&cls->kset.kobj,
+					&attr_sched_smt_power_savings.attr);
+#endif
+#ifdef CONFIG_SCHED_MC
+	if (!err && mc_capable())
+		err = sysfs_create_file(&cls->kset.kobj,
+					&attr_sched_mc_power_savings.attr);
+#endif
+	return err;
+}
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+#ifndef CONFIG_CPUSETS
+/*
+ * Add online and remove offline CPUs from the scheduler domains.
+ * When cpusets are enabled they take over this function.
+ */
+static int update_sched_domains(struct notifier_block *nfb,
+				unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		partition_sched_domains(1, NULL, NULL);
+		return NOTIFY_OK;
+
+	default:
+		return NOTIFY_DONE;
+	}
+}
+#endif
+
+static int update_runtime(struct notifier_block *nfb,
+				unsigned long action, void *hcpu)
+{
+	int cpu = (int)(long)hcpu;
+
+	switch (action) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		disable_runtime(cpu_rq(cpu));
+		return NOTIFY_OK;
+
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		enable_runtime(cpu_rq(cpu));
+		return NOTIFY_OK;
+
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+void __init sched_init_smp(void)
+{
+	cpumask_var_t non_isolated_cpus;
+
+	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
+
+#if defined(CONFIG_NUMA)
+	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
+								GFP_KERNEL);
+	BUG_ON(sched_group_nodes_bycpu == NULL);
+#endif
+	get_online_cpus();
+	mutex_lock(&sched_domains_mutex);
+	arch_init_sched_domains(cpu_online_mask);
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+	if (cpumask_empty(non_isolated_cpus))
+		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
+	mutex_unlock(&sched_domains_mutex);
+	put_online_cpus();
+
+#ifndef CONFIG_CPUSETS
+	/* XXX: Theoretical race here - CPU may be hotplugged now */
+	hotcpu_notifier(update_sched_domains, 0);
+#endif
+
+	/* RT runtime code needs to handle some hotplug events */
+	hotcpu_notifier(update_runtime, 0);
+
+	init_hrtick();
+
+	/* Move init over to a non-isolated CPU */
+	if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
+		BUG();
+	sched_init_granularity();
+	free_cpumask_var(non_isolated_cpus);
+
+	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+	init_sched_rt_class();
+}
+#else
+void __init sched_init_smp(void)
+{
+	sched_init_granularity();
+}
+#endif /* CONFIG_SMP */
+
+int in_sched_functions(unsigned long addr)
+{
+	return in_lock_functions(addr) ||
+		(addr >= (unsigned long)__sched_text_start
+		&& addr < (unsigned long)__sched_text_end);
+}
+
+static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
+{
+	cfs_rq->tasks_timeline = RB_ROOT;
+	INIT_LIST_HEAD(&cfs_rq->tasks);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	cfs_rq->rq = rq;
+#endif
+	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
+}
+
+static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
+{
+	struct rt_prio_array *array;
+	int i;
+
+	array = &rt_rq->active;
+	for (i = 0; i < MAX_RT_PRIO; i++) {
+		INIT_LIST_HEAD(array->queue + i);
+		__clear_bit(i, array->bitmap);
+	}
+	/* delimiter for bitsearch: */
+	__set_bit(MAX_RT_PRIO, array->bitmap);
+
+#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+	rt_rq->highest_prio = MAX_RT_PRIO;
+#endif
+#ifdef CONFIG_SMP
+	rt_rq->rt_nr_migratory = 0;
+	rt_rq->overloaded = 0;
+#endif
+
+	rt_rq->rt_time = 0;
+	rt_rq->rt_throttled = 0;
+	rt_rq->rt_runtime = 0;
+	spin_lock_init(&rt_rq->rt_runtime_lock);
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	rt_rq->rt_nr_boosted = 0;
+	rt_rq->rq = rq;
+#endif
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
+				struct sched_entity *se, int cpu, int add,
+				struct sched_entity *parent)
+{
+	struct rq *rq = cpu_rq(cpu);
+	tg->cfs_rq[cpu] = cfs_rq;
+	init_cfs_rq(cfs_rq, rq);
+	cfs_rq->tg = tg;
+	if (add)
+		list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+
+	tg->se[cpu] = se;
+	/* se could be NULL for init_task_group */
+	if (!se)
+		return;
+
+	if (!parent)
+		se->cfs_rq = &rq->cfs;
+	else
+		se->cfs_rq = parent->my_q;
+
+	se->my_q = cfs_rq;
+	se->load.weight = tg->shares;
+	se->load.inv_weight = 0;
+	se->parent = parent;
+}
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
+		struct sched_rt_entity *rt_se, int cpu, int add,
+		struct sched_rt_entity *parent)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	tg->rt_rq[cpu] = rt_rq;
+	init_rt_rq(rt_rq, rq);
+	rt_rq->tg = tg;
+	rt_rq->rt_se = rt_se;
+	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
+	if (add)
+		list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
+
+	tg->rt_se[cpu] = rt_se;
+	if (!rt_se)
+		return;
+
+	if (!parent)
+		rt_se->rt_rq = &rq->rt;
+	else
+		rt_se->rt_rq = parent->my_q;
+
+	rt_se->my_q = rt_rq;
+	rt_se->parent = parent;
+	INIT_LIST_HEAD(&rt_se->run_list);
+}
+#endif
+
+void __init sched_init(void)
+{
+	int i, j;
+	unsigned long alloc_size = 0, ptr;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+#endif
+#ifdef CONFIG_USER_SCHED
+	alloc_size *= 2;
+#endif
+	/*
+	 * As sched_init() is called before page_alloc is setup,
+	 * we use alloc_bootmem().
+	 */
+	if (alloc_size) {
+		ptr = (unsigned long)alloc_bootmem(alloc_size);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+		init_task_group.se = (struct sched_entity **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+
+		init_task_group.cfs_rq = (struct cfs_rq **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+
+#ifdef CONFIG_USER_SCHED
+		root_task_group.se = (struct sched_entity **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+
+		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+#ifdef CONFIG_RT_GROUP_SCHED
+		init_task_group.rt_se = (struct sched_rt_entity **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+
+		init_task_group.rt_rq = (struct rt_rq **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+
+#ifdef CONFIG_USER_SCHED
+		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+
+		root_task_group.rt_rq = (struct rt_rq **)ptr;
+		ptr += nr_cpu_ids * sizeof(void **);
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_RT_GROUP_SCHED */
+	}
+
+#ifdef CONFIG_SMP
+	init_defrootdomain();
+#endif
+
+	init_rt_bandwidth(&def_rt_bandwidth,
+			global_rt_period(), global_rt_runtime());
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	init_rt_bandwidth(&init_task_group.rt_bandwidth,
+			global_rt_period(), global_rt_runtime());
+#ifdef CONFIG_USER_SCHED
+	init_rt_bandwidth(&root_task_group.rt_bandwidth,
+			global_rt_period(), RUNTIME_INF);
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+#ifdef CONFIG_GROUP_SCHED
+	list_add(&init_task_group.list, &task_groups);
+	INIT_LIST_HEAD(&init_task_group.children);
+
+#ifdef CONFIG_USER_SCHED
+	INIT_LIST_HEAD(&root_task_group.children);
+	init_task_group.parent = &root_task_group;
+	list_add(&init_task_group.siblings, &root_task_group.children);
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_GROUP_SCHED */
+
+	for_each_possible_cpu(i) {
+		struct rq *rq;
+
+		rq = cpu_rq(i);
+		spin_lock_init(&rq->lock);
+		rq->nr_running = 0;
+		init_cfs_rq(&rq->cfs, rq);
+		init_rt_rq(&rq->rt, rq);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+		init_task_group.shares = init_task_group_load;
+		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
+#ifdef CONFIG_CGROUP_SCHED
+		/*
+		 * How much cpu bandwidth does init_task_group get?
+		 *
+		 * In case of task-groups formed thr' the cgroup filesystem, it
+		 * gets 100% of the cpu resources in the system. This overall
+		 * system cpu resource is divided among the tasks of
+		 * init_task_group and its child task-groups in a fair manner,
+		 * based on each entity's (task or task-group's) weight
+		 * (se->load.weight).
+		 *
+		 * In other words, if init_task_group has 10 tasks of weight
+		 * 1024) and two child groups A0 and A1 (of weight 1024 each),
+		 * then A0's share of the cpu resource is:
+		 *
+		 * 	A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
+		 *
+		 * We achieve this by letting init_task_group's tasks sit
+		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
+		 */
+		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
+#elif defined CONFIG_USER_SCHED
+		root_task_group.shares = NICE_0_LOAD;
+		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL);
+		/*
+		 * In case of task-groups formed thr' the user id of tasks,
+		 * init_task_group represents tasks belonging to root user.
+		 * Hence it forms a sibling of all subsequent groups formed.
+		 * In this case, init_task_group gets only a fraction of overall
+		 * system cpu resource, based on the weight assigned to root
+		 * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
+		 * by letting tasks of init_task_group sit in a separate cfs_rq
+		 * (init_cfs_rq) and having one entity represent this group of
+		 * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
+		 */
+		init_tg_cfs_entry(&init_task_group,
+				&per_cpu(init_cfs_rq, i),
+				&per_cpu(init_sched_entity, i), i, 1,
+				root_task_group.se[i]);
+
+#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
+#ifdef CONFIG_RT_GROUP_SCHED
+		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
+#ifdef CONFIG_CGROUP_SCHED
+		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
+#elif defined CONFIG_USER_SCHED
+		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
+		init_tg_rt_entry(&init_task_group,
+				&per_cpu(init_rt_rq, i),
+				&per_cpu(init_sched_rt_entity, i), i, 1,
+				root_task_group.rt_se[i]);
+#endif
+#endif
+
+		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
+			rq->cpu_load[j] = 0;
+#ifdef CONFIG_SMP
+		rq->sd = NULL;
+		rq->rd = NULL;
+		rq->active_balance = 0;
+		rq->next_balance = jiffies;
+		rq->push_cpu = 0;
+		rq->cpu = i;
+		rq->online = 0;
+		rq->migration_thread = NULL;
+		INIT_LIST_HEAD(&rq->migration_queue);
+		rq_attach_root(rq, &def_root_domain);
+#endif
+		init_rq_hrtick(rq);
+		atomic_set(&rq->nr_iowait, 0);
+	}
+
+	set_load_weight(&init_task);
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
+#endif
+
+#ifdef CONFIG_SMP
+	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+	plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+#endif
+
+	/*
+	 * The boot idle thread does lazy MMU switching as well:
+	 */
+	atomic_inc(&init_mm.mm_count);
+	enter_lazy_tlb(&init_mm, current);
+
+	/*
+	 * Make us the idle thread. Technically, schedule() should not be
+	 * called from this thread, however somewhere below it might be,
+	 * but because we are the idle thread, we just pick up running again
+	 * when this runqueue becomes "idle".
+	 */
+	init_idle(current, smp_processor_id());
+	/*
+	 * During early bootup we pretend to be a normal task:
+	 */
+	current->sched_class = &fair_sched_class;
+
+	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
+	alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+	alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+#endif
+	alloc_bootmem_cpumask_var(&cpu_isolated_map);
+#endif /* SMP */
+
+	scheduler_running = 1;
+}
+
+#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
+void __might_sleep(char *file, int line)
+{
+#ifdef in_atomic
+	static unsigned long prev_jiffy;	/* ratelimiting */
+
+	if ((!in_atomic() && !irqs_disabled()) ||
+		    system_state != SYSTEM_RUNNING || oops_in_progress)
+		return;
+	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+		return;
+	prev_jiffy = jiffies;
+
+	printk(KERN_ERR
+		"BUG: sleeping function called from invalid context at %s:%d\n",
+			file, line);
+	printk(KERN_ERR
+		"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+			in_atomic(), irqs_disabled(),
+			current->pid, current->comm);
+
+	debug_show_held_locks(current);
+	if (irqs_disabled())
+		print_irqtrace_events(current);
+	dump_stack();
+#endif
+}
+EXPORT_SYMBOL(__might_sleep);
+#endif
+
+#ifdef CONFIG_MAGIC_SYSRQ
+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);
+	__setscheduler(rq, p, SCHED_NORMAL, 0);
+	if (on_rq) {
+		activate_task(rq, p, 0);
+		resched_task(rq->curr);
+	}
+}
+
+void normalize_rt_tasks(void)
+{
+	struct task_struct *g, *p;
+	unsigned long flags;
+	struct rq *rq;
+
+	read_lock_irqsave(&tasklist_lock, flags);
+	do_each_thread(g, p) {
+		/*
+		 * Only normalize user tasks:
+		 */
+		if (!p->mm)
+			continue;
+
+		p->se.exec_start		= 0;
+#ifdef CONFIG_SCHEDSTATS
+		p->se.wait_start		= 0;
+		p->se.sleep_start		= 0;
+		p->se.block_start		= 0;
+#endif
+
+		if (!rt_task(p)) {
+			/*
+			 * Renice negative nice level userspace
+			 * tasks back to 0:
+			 */
+			if (TASK_NICE(p) < 0 && p->mm)
+				set_user_nice(p, 0);
+			continue;
+		}
+
+		spin_lock(&p->pi_lock);
+		rq = __task_rq_lock(p);
+
+		normalize_task(rq, p);
+
+		__task_rq_unlock(rq);
+		spin_unlock(&p->pi_lock);
+	} while_each_thread(g, p);
+
+	read_unlock_irqrestore(&tasklist_lock, flags);
+}
+
+#endif /* CONFIG_MAGIC_SYSRQ */
+
+#ifdef CONFIG_IA64
+/*
+ * These functions are only useful for the IA64 MCA handling.
+ *
+ * They can only be called when the whole system has been
+ * stopped - every CPU needs to be quiescent, and no scheduling
+ * activity can take place. Using them for anything else would
+ * be a serious bug, and as a result, they aren't even visible
+ * under any other configuration.
+ */
+
+/**
+ * curr_task - return the current task for a given cpu.
+ * @cpu: the processor in question.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+struct task_struct *curr_task(int cpu)
+{
+	return cpu_curr(cpu);
+}
+
+/**
+ * set_curr_task - set the current task for a given cpu.
+ * @cpu: the processor in question.
+ * @p: the task pointer to set.
+ *
+ * Description: This function must only be used when non-maskable interrupts
+ * are serviced on a separate stack. It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner. This function
+ * must be called with all CPU's synchronized, and interrupts disabled, the
+ * and caller must save the original value of the current task (see
+ * curr_task() above) and restore that value before reenabling interrupts and
+ * re-starting the system.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+void set_curr_task(int cpu, struct task_struct *p)
+{
+	cpu_curr(cpu) = p;
+}
+
+#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void free_fair_sched_group(struct task_group *tg)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		if (tg->cfs_rq)
+			kfree(tg->cfs_rq[i]);
+		if (tg->se)
+			kfree(tg->se[i]);
+	}
+
+	kfree(tg->cfs_rq);
+	kfree(tg->se);
+}
+
+static
+int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
+{
+	struct cfs_rq *cfs_rq;
+	struct sched_entity *se;
+	struct rq *rq;
+	int i;
+
+	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
+	if (!tg->cfs_rq)
+		goto err;
+	tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
+	if (!tg->se)
+		goto err;
+
+	tg->shares = NICE_0_LOAD;
+
+	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+
+		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
+				      GFP_KERNEL, cpu_to_node(i));
+		if (!cfs_rq)
+			goto err;
+
+		se = kzalloc_node(sizeof(struct sched_entity),
+				  GFP_KERNEL, cpu_to_node(i));
+		if (!se)
+			goto err;
+
+		init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
+	}
+
+	return 1;
+
+ err:
+	return 0;
+}
+
+static inline void register_fair_sched_group(struct task_group *tg, int cpu)
+{
+	list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list,
+			&cpu_rq(cpu)->leaf_cfs_rq_list);
+}
+
+static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
+{
+	list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
+}
+#else /* !CONFG_FAIR_GROUP_SCHED */
+static inline void free_fair_sched_group(struct task_group *tg)
+{
+}
+
+static inline
+int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
+{
+	return 1;
+}
+
+static inline void register_fair_sched_group(struct task_group *tg, int cpu)
+{
+}
+
+static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
+{
+}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+#ifdef CONFIG_RT_GROUP_SCHED
+static void free_rt_sched_group(struct task_group *tg)
+{
+	int i;
+
+	destroy_rt_bandwidth(&tg->rt_bandwidth);
+
+	for_each_possible_cpu(i) {
+		if (tg->rt_rq)
+			kfree(tg->rt_rq[i]);
+		if (tg->rt_se)
+			kfree(tg->rt_se[i]);
+	}
+
+	kfree(tg->rt_rq);
+	kfree(tg->rt_se);
+}
+
+static
+int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
+{
+	struct rt_rq *rt_rq;
+	struct sched_rt_entity *rt_se;
+	struct rq *rq;
+	int i;
+
+	tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
+	if (!tg->rt_rq)
+		goto err;
+	tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL);
+	if (!tg->rt_se)
+		goto err;
+
+	init_rt_bandwidth(&tg->rt_bandwidth,
+			ktime_to_ns(def_rt_bandwidth.rt_period), 0);
+
+	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+
+		rt_rq = kzalloc_node(sizeof(struct rt_rq),
+				     GFP_KERNEL, cpu_to_node(i));
+		if (!rt_rq)
+			goto err;
+
+		rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
+				     GFP_KERNEL, cpu_to_node(i));
+		if (!rt_se)
+			goto err;
+
+		init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
+	}
+
+	return 1;
+
+ err:
+	return 0;
+}
+
+static inline void register_rt_sched_group(struct task_group *tg, int cpu)
+{
+	list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list,
+			&cpu_rq(cpu)->leaf_rt_rq_list);
+}
+
+static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
+{
+	list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
+}
+#else /* !CONFIG_RT_GROUP_SCHED */
+static inline void free_rt_sched_group(struct task_group *tg)
+{
+}
+
+static inline
+int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
+{
+	return 1;
+}
+
+static inline void register_rt_sched_group(struct task_group *tg, int cpu)
+{
+}
+
+static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
+{
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+#ifdef CONFIG_GROUP_SCHED
+static void free_sched_group(struct task_group *tg)
+{
+	free_fair_sched_group(tg);
+	free_rt_sched_group(tg);
+	kfree(tg);
+}
+
+/* allocate runqueue etc for a new task group */
+struct task_group *sched_create_group(struct task_group *parent)
+{
+	struct task_group *tg;
+	unsigned long flags;
+	int i;
+
+	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+	if (!tg)
+		return ERR_PTR(-ENOMEM);
+
+	if (!alloc_fair_sched_group(tg, parent))
+		goto err;
+
+	if (!alloc_rt_sched_group(tg, parent))
+		goto err;
+
+	spin_lock_irqsave(&task_group_lock, flags);
+	for_each_possible_cpu(i) {
+		register_fair_sched_group(tg, i);
+		register_rt_sched_group(tg, i);
+	}
+	list_add_rcu(&tg->list, &task_groups);
+
+	WARN_ON(!parent); /* root should already exist */
+
+	tg->parent = parent;
+	INIT_LIST_HEAD(&tg->children);
+	list_add_rcu(&tg->siblings, &parent->children);
+	spin_unlock_irqrestore(&task_group_lock, flags);
+
+	return tg;
+
+err:
+	free_sched_group(tg);
+	return ERR_PTR(-ENOMEM);
+}
+
+/* rcu callback to free various structures associated with a task group */
+static void free_sched_group_rcu(struct rcu_head *rhp)
+{
+	/* now it should be safe to free those cfs_rqs */
+	free_sched_group(container_of(rhp, struct task_group, rcu));
+}
+
+/* Destroy runqueue etc associated with a task group */
+void sched_destroy_group(struct task_group *tg)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&task_group_lock, flags);
+	for_each_possible_cpu(i) {
+		unregister_fair_sched_group(tg, i);
+		unregister_rt_sched_group(tg, i);
+	}
+	list_del_rcu(&tg->list);
+	list_del_rcu(&tg->siblings);
+	spin_unlock_irqrestore(&task_group_lock, flags);
+
+	/* wait for possible concurrent references to cfs_rqs complete */
+	call_rcu(&tg->rcu, free_sched_group_rcu);
+}
+
+/* change task's runqueue when it moves between groups.
+ *	The caller of this function should have put the task in its new group
+ *	by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
+ *	reflect its new group.
+ */
+void sched_move_task(struct task_struct *tsk)
+{
+	int on_rq, running;
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = task_rq_lock(tsk, &flags);
+
+	update_rq_clock(rq);
+
+	running = task_current(rq, tsk);
+	on_rq = tsk->se.on_rq;
+
+	if (on_rq)
+		dequeue_task(rq, tsk, 0);
+	if (unlikely(running))
+		tsk->sched_class->put_prev_task(rq, tsk);
+
+	set_task_rq(tsk, task_cpu(tsk));
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (tsk->sched_class->moved_group)
+		tsk->sched_class->moved_group(tsk);
+#endif
+
+	if (unlikely(running))
+		tsk->sched_class->set_curr_task(rq);
+	if (on_rq)
+		enqueue_task(rq, tsk, 0);
+
+	task_rq_unlock(rq, &flags);
+}
+#endif /* CONFIG_GROUP_SCHED */
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void __set_se_shares(struct sched_entity *se, unsigned long shares)
+{
+	struct cfs_rq *cfs_rq = se->cfs_rq;
+	int on_rq;
+
+	on_rq = se->on_rq;
+	if (on_rq)
+		dequeue_entity(cfs_rq, se, 0);
+
+	se->load.weight = shares;
+	se->load.inv_weight = 0;
+
+	if (on_rq)
+		enqueue_entity(cfs_rq, se, 0);
+}
+
+static void set_se_shares(struct sched_entity *se, unsigned long shares)
+{
+	struct cfs_rq *cfs_rq = se->cfs_rq;
+	struct rq *rq = cfs_rq->rq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+	__set_se_shares(se, shares);
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static DEFINE_MUTEX(shares_mutex);
+
+int sched_group_set_shares(struct task_group *tg, unsigned long shares)
+{
+	int i;
+	unsigned long flags;
+
+	/*
+	 * We can't change the weight of the root cgroup.
+	 */
+	if (!tg->se[0])
+		return -EINVAL;
+
+	if (shares < MIN_SHARES)
+		shares = MIN_SHARES;
+	else if (shares > MAX_SHARES)
+		shares = MAX_SHARES;
+
+	mutex_lock(&shares_mutex);
+	if (tg->shares == shares)
+		goto done;
+
+	spin_lock_irqsave(&task_group_lock, flags);
+	for_each_possible_cpu(i)
+		unregister_fair_sched_group(tg, i);
+	list_del_rcu(&tg->siblings);
+	spin_unlock_irqrestore(&task_group_lock, flags);
+
+	/* wait for any ongoing reference to this group to finish */
+	synchronize_sched();
+
+	/*
+	 * Now we are free to modify the group's share on each cpu
+	 * w/o tripping rebalance_share or load_balance_fair.
+	 */
+	tg->shares = shares;
+	for_each_possible_cpu(i) {
+		/*
+		 * force a rebalance
+		 */
+		cfs_rq_set_shares(tg->cfs_rq[i], 0);
+		set_se_shares(tg->se[i], shares);
+	}
+
+	/*
+	 * Enable load balance activity on this group, by inserting it back on
+	 * each cpu's rq->leaf_cfs_rq_list.
+	 */
+	spin_lock_irqsave(&task_group_lock, flags);
+	for_each_possible_cpu(i)
+		register_fair_sched_group(tg, i);
+	list_add_rcu(&tg->siblings, &tg->parent->children);
+	spin_unlock_irqrestore(&task_group_lock, flags);
+done:
+	mutex_unlock(&shares_mutex);
+	return 0;
+}
+
+unsigned long sched_group_shares(struct task_group *tg)
+{
+	return tg->shares;
+}
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+/*
+ * Ensure that the real time constraints are schedulable.
+ */
+static DEFINE_MUTEX(rt_constraints_mutex);
+
+static unsigned long to_ratio(u64 period, u64 runtime)
+{
+	if (runtime == RUNTIME_INF)
+		return 1ULL << 20;
+
+	return div64_u64(runtime << 20, period);
+}
+
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+	struct task_struct *g, *p;
+
+	do_each_thread(g, p) {
+		if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+			return 1;
+	} while_each_thread(g, p);
+
+	return 0;
+}
+
+struct rt_schedulable_data {
+	struct task_group *tg;
+	u64 rt_period;
+	u64 rt_runtime;
+};
+
+static int tg_schedulable(struct task_group *tg, void *data)
+{
+	struct rt_schedulable_data *d = data;
+	struct task_group *child;
+	unsigned long total, sum = 0;
+	u64 period, runtime;
+
+	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	runtime = tg->rt_bandwidth.rt_runtime;
+
+	if (tg == d->tg) {
+		period = d->rt_period;
+		runtime = d->rt_runtime;
+	}
+
+#ifdef CONFIG_USER_SCHED
+	if (tg == &root_task_group) {
+		period = global_rt_period();
+		runtime = global_rt_runtime();
+	}
+#endif
+
+	/*
+	 * Cannot have more runtime than the period.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
+
+	/*
+	 * Ensure we don't starve existing RT tasks.
+	 */
+	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+		return -EBUSY;
+
+	total = to_ratio(period, runtime);
+
+	/*
+	 * Nobody can have more than the global setting allows.
+	 */
+	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+		return -EINVAL;
+
+	/*
+	 * The sum of our children's runtime should not exceed our own.
+	 */
+	list_for_each_entry_rcu(child, &tg->children, siblings) {
+		period = ktime_to_ns(child->rt_bandwidth.rt_period);
+		runtime = child->rt_bandwidth.rt_runtime;
+
+		if (child == d->tg) {
+			period = d->rt_period;
+			runtime = d->rt_runtime;
+		}
+
+		sum += to_ratio(period, runtime);
+	}
+
+	if (sum > total)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+{
+	struct rt_schedulable_data data = {
+		.tg = tg,
+		.rt_period = period,
+		.rt_runtime = runtime,
+	};
+
+	return walk_tg_tree(tg_schedulable, tg_nop, &data);
+}
+
+static int tg_set_bandwidth(struct task_group *tg,
+		u64 rt_period, u64 rt_runtime)
+{
+	int i, err = 0;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	err = __rt_schedulable(tg, rt_period, rt_runtime);
+	if (err)
+		goto unlock;
+
+	spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
+	tg->rt_bandwidth.rt_runtime = rt_runtime;
+
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = tg->rt_rq[i];
+
+		spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = rt_runtime;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+ unlock:
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return err;
+}
+
+int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
+	if (rt_runtime_us < 0)
+		rt_runtime = RUNTIME_INF;
+
+	return tg_set_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_runtime(struct task_group *tg)
+{
+	u64 rt_runtime_us;
+
+	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
+		return -1;
+
+	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
+	do_div(rt_runtime_us, NSEC_PER_USEC);
+	return rt_runtime_us;
+}
+
+int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+	rt_runtime = tg->rt_bandwidth.rt_runtime;
+
+	if (rt_period == 0)
+		return -EINVAL;
+
+	return tg_set_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_period(struct task_group *tg)
+{
+	u64 rt_period_us;
+
+	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	do_div(rt_period_us, NSEC_PER_USEC);
+	return rt_period_us;
+}
+
+static int sched_rt_global_constraints(void)
+{
+	u64 runtime, period;
+	int ret = 0;
+
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	runtime = global_rt_runtime();
+	period = global_rt_period();
+
+	/*
+	 * Sanity check on the sysctl variables.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	ret = __rt_schedulable(NULL, 0, 0);
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return ret;
+}
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
+#else /* !CONFIG_RT_GROUP_SCHED */
+static int sched_rt_global_constraints(void)
+{
+	unsigned long flags;
+	int i;
+
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
+
+		spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = global_rt_runtime();
+		spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+
+	return 0;
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+int sched_rt_handler(struct ctl_table *table, int write,
+		struct file *filp, void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	int old_period, old_runtime;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	old_period = sysctl_sched_rt_period;
+	old_runtime = sysctl_sched_rt_runtime;
+
+	ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+
+	if (!ret && write) {
+		ret = sched_rt_global_constraints();
+		if (ret) {
+			sysctl_sched_rt_period = old_period;
+			sysctl_sched_rt_runtime = old_runtime;
+		} else {
+			def_rt_bandwidth.rt_runtime = global_rt_runtime();
+			def_rt_bandwidth.rt_period =
+				ns_to_ktime(global_rt_period());
+		}
+	}
+	mutex_unlock(&mutex);
+
+	return ret;
+}
+
+#ifdef CONFIG_CGROUP_SCHED
+
+/* return corresponding task_group object of a cgroup */
+static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id),
+			    struct task_group, css);
+}
+
+static struct cgroup_subsys_state *
+cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct task_group *tg, *parent;
+
+	if (!cgrp->parent) {
+		/* This is early initialization for the top cgroup */
+		return &init_task_group.css;
+	}
+
+	parent = cgroup_tg(cgrp->parent);
+	tg = sched_create_group(parent);
+	if (IS_ERR(tg))
+		return ERR_PTR(-ENOMEM);
+
+	return &tg->css;
+}
+
+static void
+cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+
+	sched_destroy_group(tg);
+}
+
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		      struct task_struct *tsk)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
+		return -EINVAL;
+#else
+	/* We don't support RT-tasks being in separate groups */
+	if (tsk->sched_class != &fair_sched_class)
+		return -EINVAL;
+#endif
+
+	return 0;
+}
+
+static void
+cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+			struct cgroup *old_cont, struct task_struct *tsk)
+{
+	sched_move_task(tsk);
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
+				u64 shareval)
+{
+	return sched_group_set_shares(cgroup_tg(cgrp), shareval);
+}
+
+static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+
+	return (u64) tg->shares;
+}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+#ifdef CONFIG_RT_GROUP_SCHED
+static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
+				s64 val)
+{
+	return sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
+}
+
+static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	return sched_group_rt_runtime(cgroup_tg(cgrp));
+}
+
+static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype,
+		u64 rt_period_us)
+{
+	return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us);
+}
+
+static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft)
+{
+	return sched_group_rt_period(cgroup_tg(cgrp));
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static struct cftype cpu_files[] = {
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	{
+		.name = "shares",
+		.read_u64 = cpu_shares_read_u64,
+		.write_u64 = cpu_shares_write_u64,
+	},
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+	{
+		.name = "rt_runtime_us",
+		.read_s64 = cpu_rt_runtime_read,
+		.write_s64 = cpu_rt_runtime_write,
+	},
+	{
+		.name = "rt_period_us",
+		.read_u64 = cpu_rt_period_read_uint,
+		.write_u64 = cpu_rt_period_write_uint,
+	},
+#endif
+};
+
+static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+	return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
+}
+
+struct cgroup_subsys cpu_cgroup_subsys = {
+	.name		= "cpu",
+	.create		= cpu_cgroup_create,
+	.destroy	= cpu_cgroup_destroy,
+	.can_attach	= cpu_cgroup_can_attach,
+	.attach		= cpu_cgroup_attach,
+	.populate	= cpu_cgroup_populate,
+	.subsys_id	= cpu_cgroup_subsys_id,
+	.early_init	= 1,
+};
+
+#endif	/* CONFIG_CGROUP_SCHED */
+
+#ifdef CONFIG_CGROUP_CPUACCT
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+/* track cpu usage of a group of tasks and its child groups */
+struct cpuacct {
+	struct cgroup_subsys_state css;
+	/* cpuusage holds pointer to a u64-type object on every cpu */
+	u64 *cpuusage;
+	struct cpuacct *parent;
+};
+
+struct cgroup_subsys cpuacct_subsys;
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+/* return cpu accounting group to which this task belongs */
+static inline struct cpuacct *task_ca(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_create(
+	struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
+	if (!ca)
+		return ERR_PTR(-ENOMEM);
+
+	ca->cpuusage = alloc_percpu(u64);
+	if (!ca->cpuusage) {
+		kfree(ca);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (cgrp->parent)
+		ca->parent = cgroup_ca(cgrp->parent);
+
+	return &ca->css;
+}
+
+/* destroy an existing cpu accounting group */
+static void
+cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+
+	free_percpu(ca->cpuusage);
+	kfree(ca);
+}
+
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+	u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+	u64 data;
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+	 */
+	spin_lock_irq(&cpu_rq(cpu)->lock);
+	data = *cpuusage;
+	spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	data = *cpuusage;
+#endif
+
+	return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+	u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+	 */
+	spin_lock_irq(&cpu_rq(cpu)->lock);
+	*cpuusage = val;
+	spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	*cpuusage = val;
+#endif
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	u64 totalcpuusage = 0;
+	int i;
+
+	for_each_present_cpu(i)
+		totalcpuusage += cpuacct_cpuusage_read(ca, i);
+
+	return totalcpuusage;
+}
+
+static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
+								u64 reset)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int err = 0;
+	int i;
+
+	if (reset) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_present_cpu(i)
+		cpuacct_cpuusage_write(ca, i, 0);
+
+out:
+	return err;
+}
+
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+				   struct seq_file *m)
+{
+	struct cpuacct *ca = cgroup_ca(cgroup);
+	u64 percpu;
+	int i;
+
+	for_each_present_cpu(i) {
+		percpu = cpuacct_cpuusage_read(ca, i);
+		seq_printf(m, "%llu ", (unsigned long long) percpu);
+	}
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "usage",
+		.read_u64 = cpuusage_read,
+		.write_u64 = cpuusage_write,
+	},
+	{
+		.name = "usage_percpu",
+		.read_seq_string = cpuacct_percpu_seq_read,
+	},
+
+};
+
+static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files));
+}
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+	struct cpuacct *ca;
+	int cpu;
+
+	if (!cpuacct_subsys.active)
+		return;
+
+	cpu = task_cpu(tsk);
+	ca = task_ca(tsk);
+
+	for (; ca; ca = ca->parent) {
+		u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+		*cpuusage += cputime;
+	}
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+	.name = "cpuacct",
+	.create = cpuacct_create,
+	.destroy = cpuacct_destroy,
+	.populate = cpuacct_populate,
+	.subsys_id = cpuacct_subsys_id,
+};
+#endif	/* CONFIG_CGROUP_CPUACCT */
+#endif /* !DDE_LINUX */
diff --git a/libdde-linux26/lib/src/kernel/sched_cpupri.h b/libdde-linux26/lib/src/kernel/sched_cpupri.h
new file mode 100644
index 00000000..642a94ef
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/sched_cpupri.h
@@ -0,0 +1,37 @@
+#ifndef _LINUX_CPUPRI_H
+#define _LINUX_CPUPRI_H
+
+#include <linux/sched.h>
+
+#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO + 2)
+#define CPUPRI_NR_PRI_WORDS	BITS_TO_LONGS(CPUPRI_NR_PRIORITIES)
+
+#define CPUPRI_INVALID -1
+#define CPUPRI_IDLE     0
+#define CPUPRI_NORMAL   1
+/* values 2-101 are RT priorities 0-99 */
+
+struct cpupri_vec {
+	spinlock_t lock;
+	int        count;
+	cpumask_var_t mask;
+};
+
+struct cpupri {
+	struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
+	long              pri_active[CPUPRI_NR_PRI_WORDS];
+	int               cpu_to_pri[NR_CPUS];
+};
+
+#ifdef CONFIG_SMP
+int  cpupri_find(struct cpupri *cp,
+		 struct task_struct *p, cpumask_t *lowest_mask);
+void cpupri_set(struct cpupri *cp, int cpu, int pri);
+int cpupri_init(struct cpupri *cp, bool bootmem);
+void cpupri_cleanup(struct cpupri *cp);
+#else
+#define cpupri_set(cp, cpu, pri) do { } while (0)
+#define cpupri_init() do { } while (0)
+#endif
+
+#endif /* _LINUX_CPUPRI_H */
diff --git a/libdde-linux26/lib/src/kernel/sys.c b/libdde-linux26/lib/src/kernel/sys.c
new file mode 100644
index 00000000..6533cb97
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/sys.c
@@ -0,0 +1,1893 @@
+/*
+ *  linux/kernel/sys.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/utsname.h>
+#include <linux/mman.h>
+#include <linux/smp_lock.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/prctl.h>
+#include <linux/highuid.h>
+#include <linux/fs.h>
+#include <linux/resource.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/workqueue.h>
+#include <linux/capability.h>
+#include <linux/device.h>
+#include <linux/key.h>
+#include <linux/times.h>
+#include <linux/posix-timers.h>
+#include <linux/security.h>
+#include <linux/dcookies.h>
+#include <linux/suspend.h>
+#include <linux/tty.h>
+#include <linux/signal.h>
+#include <linux/cn_proc.h>
+#include <linux/getcpu.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/seccomp.h>
+#include <linux/cpu.h>
+#include <linux/ptrace.h>
+
+#include <linux/compat.h>
+#include <linux/syscalls.h>
+#include <linux/kprobes.h>
+#include <linux/user_namespace.h>
+
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/unistd.h>
+
+#ifndef SET_UNALIGN_CTL
+# define SET_UNALIGN_CTL(a,b)	(-EINVAL)
+#endif
+#ifndef GET_UNALIGN_CTL
+# define GET_UNALIGN_CTL(a,b)	(-EINVAL)
+#endif
+#ifndef SET_FPEMU_CTL
+# define SET_FPEMU_CTL(a,b)	(-EINVAL)
+#endif
+#ifndef GET_FPEMU_CTL
+# define GET_FPEMU_CTL(a,b)	(-EINVAL)
+#endif
+#ifndef SET_FPEXC_CTL
+# define SET_FPEXC_CTL(a,b)	(-EINVAL)
+#endif
+#ifndef GET_FPEXC_CTL
+# define GET_FPEXC_CTL(a,b)	(-EINVAL)
+#endif
+#ifndef GET_ENDIAN
+# define GET_ENDIAN(a,b)	(-EINVAL)
+#endif
+#ifndef SET_ENDIAN
+# define SET_ENDIAN(a,b)	(-EINVAL)
+#endif
+#ifndef GET_TSC_CTL
+# define GET_TSC_CTL(a)		(-EINVAL)
+#endif
+#ifndef SET_TSC_CTL
+# define SET_TSC_CTL(a)		(-EINVAL)
+#endif
+
+#ifndef DDE_LINUX
+/*
+ * this is where the system-wide overflow UID and GID are defined, for
+ * architectures that now have 32-bit UID/GID but didn't in the past
+ */
+
+int overflowuid = DEFAULT_OVERFLOWUID;
+int overflowgid = DEFAULT_OVERFLOWGID;
+
+#ifdef CONFIG_UID16
+EXPORT_SYMBOL(overflowuid);
+EXPORT_SYMBOL(overflowgid);
+#endif
+
+/*
+ * the same as above, but for filesystems which can only store a 16-bit
+ * UID and GID. as such, this is needed on all architectures
+ */
+
+int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
+int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;
+
+EXPORT_SYMBOL(fs_overflowuid);
+EXPORT_SYMBOL(fs_overflowgid);
+
+/*
+ * this indicates whether you can reboot with ctrl-alt-del: the default is yes
+ */
+
+int C_A_D = 1;
+#endif /* DDE_LINUX */
+struct pid *cad_pid;
+EXPORT_SYMBOL(cad_pid);
+
+/*
+ * If set, this is used for preparing the system to power off.
+ */
+
+void (*pm_power_off_prepare)(void);
+
+#ifndef DDE_LINUX
+/*
+ * set the priority of a task
+ * - the caller must hold the RCU read lock
+ */
+static int set_one_prio(struct task_struct *p, int niceval, int error)
+{
+	const struct cred *cred = current_cred(), *pcred = __task_cred(p);
+	int no_nice;
+
+	if (pcred->uid  != cred->euid &&
+	    pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
+		error = -EPERM;
+		goto out;
+	}
+	if (niceval < task_nice(p) && !can_nice(p, niceval)) {
+		error = -EACCES;
+		goto out;
+	}
+	no_nice = security_task_setnice(p, niceval);
+	if (no_nice) {
+		error = no_nice;
+		goto out;
+	}
+	if (error == -ESRCH)
+		error = 0;
+	set_user_nice(p, niceval);
+out:
+	return error;
+}
+
+SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
+{
+	struct task_struct *g, *p;
+	struct user_struct *user;
+	const struct cred *cred = current_cred();
+	int error = -EINVAL;
+	struct pid *pgrp;
+
+	if (which > PRIO_USER || which < PRIO_PROCESS)
+		goto out;
+
+	/* normalize: avoid signed division (rounding problems) */
+	error = -ESRCH;
+	if (niceval < -20)
+		niceval = -20;
+	if (niceval > 19)
+		niceval = 19;
+
+	read_lock(&tasklist_lock);
+	switch (which) {
+		case PRIO_PROCESS:
+			if (who)
+				p = find_task_by_vpid(who);
+			else
+				p = current;
+			if (p)
+				error = set_one_prio(p, niceval, error);
+			break;
+		case PRIO_PGRP:
+			if (who)
+				pgrp = find_vpid(who);
+			else
+				pgrp = task_pgrp(current);
+			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+				error = set_one_prio(p, niceval, error);
+			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			break;
+		case PRIO_USER:
+			user = (struct user_struct *) cred->user;
+			if (!who)
+				who = cred->uid;
+			else if ((who != cred->uid) &&
+				 !(user = find_user(who)))
+				goto out_unlock;	/* No processes for this user */
+
+			do_each_thread(g, p)
+				if (__task_cred(p)->uid == who)
+					error = set_one_prio(p, niceval, error);
+			while_each_thread(g, p);
+			if (who != cred->uid)
+				free_uid(user);		/* For find_user() */
+			break;
+	}
+out_unlock:
+	read_unlock(&tasklist_lock);
+out:
+	return error;
+}
+
+/*
+ * Ugh. To avoid negative return values, "getpriority()" will
+ * not return the normal nice-value, but a negated value that
+ * has been offset by 20 (ie it returns 40..1 instead of -20..19)
+ * to stay compatible.
+ */
+SYSCALL_DEFINE2(getpriority, int, which, int, who)
+{
+	struct task_struct *g, *p;
+	struct user_struct *user;
+	const struct cred *cred = current_cred();
+	long niceval, retval = -ESRCH;
+	struct pid *pgrp;
+
+	if (which > PRIO_USER || which < PRIO_PROCESS)
+		return -EINVAL;
+
+	read_lock(&tasklist_lock);
+	switch (which) {
+		case PRIO_PROCESS:
+			if (who)
+				p = find_task_by_vpid(who);
+			else
+				p = current;
+			if (p) {
+				niceval = 20 - task_nice(p);
+				if (niceval > retval)
+					retval = niceval;
+			}
+			break;
+		case PRIO_PGRP:
+			if (who)
+				pgrp = find_vpid(who);
+			else
+				pgrp = task_pgrp(current);
+			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+				niceval = 20 - task_nice(p);
+				if (niceval > retval)
+					retval = niceval;
+			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			break;
+		case PRIO_USER:
+			user = (struct user_struct *) cred->user;
+			if (!who)
+				who = cred->uid;
+			else if ((who != cred->uid) &&
+				 !(user = find_user(who)))
+				goto out_unlock;	/* No processes for this user */
+
+			do_each_thread(g, p)
+				if (__task_cred(p)->uid == who) {
+					niceval = 20 - task_nice(p);
+					if (niceval > retval)
+						retval = niceval;
+				}
+			while_each_thread(g, p);
+			if (who != cred->uid)
+				free_uid(user);		/* for find_user() */
+			break;
+	}
+out_unlock:
+	read_unlock(&tasklist_lock);
+
+	return retval;
+}
+
+/**
+ *	emergency_restart - reboot the system
+ *
+ *	Without shutting down any hardware or taking any locks
+ *	reboot the system.  This is called when we know we are in
+ *	trouble so this is our best effort to reboot.  This is
+ *	safe to call in interrupt context.
+ */
+void emergency_restart(void)
+{
+	machine_emergency_restart();
+}
+EXPORT_SYMBOL_GPL(emergency_restart);
+
+void kernel_restart_prepare(char *cmd)
+{
+	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
+	system_state = SYSTEM_RESTART;
+	device_shutdown();
+	sysdev_shutdown();
+}
+
+/**
+ *	kernel_restart - reboot the system
+ *	@cmd: pointer to buffer containing command to execute for restart
+ *		or %NULL
+ *
+ *	Shutdown everything and perform a clean reboot.
+ *	This is not safe to call in interrupt context.
+ */
+void kernel_restart(char *cmd)
+{
+	kernel_restart_prepare(cmd);
+	if (!cmd)
+		printk(KERN_EMERG "Restarting system.\n");
+	else
+		printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
+	machine_restart(cmd);
+}
+EXPORT_SYMBOL_GPL(kernel_restart);
+
+static void kernel_shutdown_prepare(enum system_states state)
+{
+	blocking_notifier_call_chain(&reboot_notifier_list,
+		(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
+	system_state = state;
+	device_shutdown();
+}
+/**
+ *	kernel_halt - halt the system
+ *
+ *	Shutdown everything and perform a clean system halt.
+ */
+void kernel_halt(void)
+{
+	kernel_shutdown_prepare(SYSTEM_HALT);
+	sysdev_shutdown();
+	printk(KERN_EMERG "System halted.\n");
+	machine_halt();
+}
+
+EXPORT_SYMBOL_GPL(kernel_halt);
+
+/**
+ *	kernel_power_off - power_off the system
+ *
+ *	Shutdown everything and perform a clean system power_off.
+ */
+void kernel_power_off(void)
+{
+	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
+	if (pm_power_off_prepare)
+		pm_power_off_prepare();
+	disable_nonboot_cpus();
+	sysdev_shutdown();
+	printk(KERN_EMERG "Power down.\n");
+	machine_power_off();
+}
+EXPORT_SYMBOL_GPL(kernel_power_off);
+/*
+ * Reboot system call: for obvious reasons only root may call it,
+ * and even root needs to set up some magic numbers in the registers
+ * so that some mistake won't make this reboot the whole machine.
+ * You can also set the meaning of the ctrl-alt-del-key here.
+ *
+ * reboot doesn't sync: do that yourself before calling this.
+ */
+SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
+		void __user *, arg)
+{
+	char buffer[256];
+
+	/* We only trust the superuser with rebooting the system. */
+	if (!capable(CAP_SYS_BOOT))
+		return -EPERM;
+
+	/* For safety, we require "magic" arguments. */
+	if (magic1 != LINUX_REBOOT_MAGIC1 ||
+	    (magic2 != LINUX_REBOOT_MAGIC2 &&
+	                magic2 != LINUX_REBOOT_MAGIC2A &&
+			magic2 != LINUX_REBOOT_MAGIC2B &&
+	                magic2 != LINUX_REBOOT_MAGIC2C))
+		return -EINVAL;
+
+	/* Instead of trying to make the power_off code look like
+	 * halt when pm_power_off is not set do it the easy way.
+	 */
+	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
+		cmd = LINUX_REBOOT_CMD_HALT;
+
+	lock_kernel();
+	switch (cmd) {
+	case LINUX_REBOOT_CMD_RESTART:
+		kernel_restart(NULL);
+		break;
+
+	case LINUX_REBOOT_CMD_CAD_ON:
+		C_A_D = 1;
+		break;
+
+	case LINUX_REBOOT_CMD_CAD_OFF:
+		C_A_D = 0;
+		break;
+
+	case LINUX_REBOOT_CMD_HALT:
+		kernel_halt();
+		unlock_kernel();
+		do_exit(0);
+		break;
+
+	case LINUX_REBOOT_CMD_POWER_OFF:
+		kernel_power_off();
+		unlock_kernel();
+		do_exit(0);
+		break;
+
+	case LINUX_REBOOT_CMD_RESTART2:
+		if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
+			unlock_kernel();
+			return -EFAULT;
+		}
+		buffer[sizeof(buffer) - 1] = '\0';
+
+		kernel_restart(buffer);
+		break;
+
+#ifdef CONFIG_KEXEC
+	case LINUX_REBOOT_CMD_KEXEC:
+		{
+			int ret;
+			ret = kernel_kexec();
+			unlock_kernel();
+			return ret;
+		}
+#endif
+
+#ifdef CONFIG_HIBERNATION
+	case LINUX_REBOOT_CMD_SW_SUSPEND:
+		{
+			int ret = hibernate();
+			unlock_kernel();
+			return ret;
+		}
+#endif
+
+	default:
+		unlock_kernel();
+		return -EINVAL;
+	}
+	unlock_kernel();
+	return 0;
+}
+
+static void deferred_cad(struct work_struct *dummy)
+{
+	kernel_restart(NULL);
+}
+
+/*
+ * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
+ * As it's called within an interrupt, it may NOT sync: the only choice
+ * is whether to reboot at once, or just ignore the ctrl-alt-del.
+ */
+void ctrl_alt_del(void)
+{
+	static DECLARE_WORK(cad_work, deferred_cad);
+
+	if (C_A_D)
+		schedule_work(&cad_work);
+	else
+		kill_cad_pid(SIGINT, 1);
+}
+	
+/*
+ * Unprivileged users may change the real gid to the effective gid
+ * or vice versa.  (BSD-style)
+ *
+ * If you set the real gid at all, or set the effective gid to a value not
+ * equal to the real gid, then the saved gid is set to the new effective gid.
+ *
+ * This makes it possible for a setgid program to completely drop its
+ * privileges, which is often a useful assertion to make when you are doing
+ * a security audit over a program.
+ *
+ * The general idea is that a program which uses just setregid() will be
+ * 100% compatible with BSD.  A program which uses just setgid() will be
+ * 100% compatible with POSIX with saved IDs. 
+ *
+ * SMP: There are not races, the GIDs are checked only by filesystem
+ *      operations (as far as semantic preservation is concerned).
+ */
+SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
+{
+	const struct cred *old;
+	struct cred *new;
+	int retval;
+
+	new = prepare_creds();
+	if (!new)
+		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 ||
+		    old->egid == rgid ||
+		    capable(CAP_SETGID))
+			new->gid = rgid;
+		else
+			goto error;
+	}
+	if (egid != (gid_t) -1) {
+		if (old->gid == egid ||
+		    old->egid == egid ||
+		    old->sgid == egid ||
+		    capable(CAP_SETGID))
+			new->egid = egid;
+		else
+			goto error;
+	}
+
+	if (rgid != (gid_t) -1 ||
+	    (egid != (gid_t) -1 && egid != old->gid))
+		new->sgid = new->egid;
+	new->fsgid = new->egid;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return retval;
+}
+
+/*
+ * setgid() is implemented like SysV w/ SAVED_IDS 
+ *
+ * SMP: Same implicit races as above.
+ */
+SYSCALL_DEFINE1(setgid, gid_t, gid)
+{
+	const struct cred *old;
+	struct cred *new;
+	int retval;
+
+	new = prepare_creds();
+	if (!new)
+		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;
+	else if (gid == old->gid || gid == old->sgid)
+		new->egid = new->fsgid = gid;
+	else
+		goto error;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return retval;
+}
+
+/*
+ * change the user struct in a credentials set to match the new UID
+ */
+static int set_user(struct cred *new)
+{
+	struct user_struct *new_user;
+
+	new_user = alloc_uid(current_user_ns(), new->uid);
+	if (!new_user)
+		return -EAGAIN;
+
+	if (!task_can_switch_user(new_user, current)) {
+		free_uid(new_user);
+		return -EINVAL;
+	}
+
+	if (atomic_read(&new_user->processes) >=
+				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
+			new_user != INIT_USER) {
+		free_uid(new_user);
+		return -EAGAIN;
+	}
+
+	free_uid(new->user);
+	new->user = new_user;
+	return 0;
+}
+
+/*
+ * Unprivileged users may change the real uid to the effective uid
+ * or vice versa.  (BSD-style)
+ *
+ * If you set the real uid at all, or set the effective uid to a value not
+ * equal to the real uid, then the saved uid is set to the new effective uid.
+ *
+ * This makes it possible for a setuid program to completely drop its
+ * privileges, which is often a useful assertion to make when you are doing
+ * a security audit over a program.
+ *
+ * The general idea is that a program which uses just setreuid() will be
+ * 100% compatible with BSD.  A program which uses just setuid() will be
+ * 100% compatible with POSIX with saved IDs. 
+ */
+SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
+{
+	const struct cred *old;
+	struct cred *new;
+	int retval;
+
+	new = prepare_creds();
+	if (!new)
+		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;
+		if (old->uid != ruid &&
+		    old->euid != ruid &&
+		    !capable(CAP_SETUID))
+			goto error;
+	}
+
+	if (euid != (uid_t) -1) {
+		new->euid = euid;
+		if (old->uid != euid &&
+		    old->euid != euid &&
+		    old->suid != euid &&
+		    !capable(CAP_SETUID))
+			goto error;
+	}
+
+	if (new->uid != old->uid) {
+		retval = set_user(new);
+		if (retval < 0)
+			goto error;
+	}
+	if (ruid != (uid_t) -1 ||
+	    (euid != (uid_t) -1 && euid != old->uid))
+		new->suid = new->euid;
+	new->fsuid = new->euid;
+
+	retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
+	if (retval < 0)
+		goto error;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return retval;
+}
+		
+/*
+ * setuid() is implemented like SysV with SAVED_IDS 
+ * 
+ * Note that SAVED_ID's is deficient in that a setuid root program
+ * like sendmail, for example, cannot set its uid to be a normal 
+ * user and then switch back, because if you're root, setuid() sets
+ * the saved uid too.  If you don't like this, blame the bright people
+ * in the POSIX committee and/or USG.  Note that the BSD-style setreuid()
+ * will allow a root program to temporarily drop privileges and be able to
+ * regain them by swapping the real and effective uid.  
+ */
+SYSCALL_DEFINE1(setuid, uid_t, uid)
+{
+	const struct cred *old;
+	struct cred *new;
+	int retval;
+
+	new = prepare_creds();
+	if (!new)
+		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;
+		if (uid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
+		}
+	} else if (uid != old->uid && uid != new->suid) {
+		goto error;
+	}
+
+	new->fsuid = new->euid = uid;
+
+	retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
+	if (retval < 0)
+		goto error;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return retval;
+}
+
+
+/*
+ * This function implements a generic ability to update ruid, euid,
+ * and suid.  This allows you to implement the 4.4 compatible seteuid().
+ */
+SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
+{
+	const struct cred *old;
+	struct cred *new;
+	int retval;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
+	if (retval)
+		goto error;
+	old = current_cred();
+
+	retval = -EPERM;
+	if (!capable(CAP_SETUID)) {
+		if (ruid != (uid_t) -1 && ruid != old->uid &&
+		    ruid != old->euid  && ruid != old->suid)
+			goto error;
+		if (euid != (uid_t) -1 && euid != old->uid &&
+		    euid != old->euid  && euid != old->suid)
+			goto error;
+		if (suid != (uid_t) -1 && suid != old->uid &&
+		    suid != old->euid  && suid != old->suid)
+			goto error;
+	}
+
+	if (ruid != (uid_t) -1) {
+		new->uid = ruid;
+		if (ruid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
+		}
+	}
+	if (euid != (uid_t) -1)
+		new->euid = euid;
+	if (suid != (uid_t) -1)
+		new->suid = suid;
+	new->fsuid = new->euid;
+
+	retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
+	if (retval < 0)
+		goto error;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return retval;
+}
+
+SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
+{
+	const struct cred *cred = current_cred();
+	int retval;
+
+	if (!(retval   = put_user(cred->uid,  ruid)) &&
+	    !(retval   = put_user(cred->euid, euid)))
+		retval = put_user(cred->suid, suid);
+
+	return retval;
+}
+
+/*
+ * Same as above, but for rgid, egid, sgid.
+ */
+SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
+{
+	const struct cred *old;
+	struct cred *new;
+	int retval;
+
+	new = prepare_creds();
+	if (!new)
+		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 &&
+		    rgid != old->egid  && rgid != old->sgid)
+			goto error;
+		if (egid != (gid_t) -1 && egid != old->gid &&
+		    egid != old->egid  && egid != old->sgid)
+			goto error;
+		if (sgid != (gid_t) -1 && sgid != old->gid &&
+		    sgid != old->egid  && sgid != old->sgid)
+			goto error;
+	}
+
+	if (rgid != (gid_t) -1)
+		new->gid = rgid;
+	if (egid != (gid_t) -1)
+		new->egid = egid;
+	if (sgid != (gid_t) -1)
+		new->sgid = sgid;
+	new->fsgid = new->egid;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return retval;
+}
+
+SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
+{
+	const struct cred *cred = current_cred();
+	int retval;
+
+	if (!(retval   = put_user(cred->gid,  rgid)) &&
+	    !(retval   = put_user(cred->egid, egid)))
+		retval = put_user(cred->sgid, sgid);
+
+	return retval;
+}
+
+
+/*
+ * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
+ * is used for "access()" and for the NFS daemon (letting nfsd stay at
+ * whatever uid it wants to). It normally shadows "euid", except when
+ * explicitly set by setfsuid() or for access..
+ */
+SYSCALL_DEFINE1(setfsuid, uid_t, uid)
+{
+	const struct cred *old;
+	struct cred *new;
+	uid_t old_fsuid;
+
+	new = prepare_creds();
+	if (!new)
+		return current_fsuid();
+	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)) {
+		if (uid != old_fsuid) {
+			new->fsuid = uid;
+			if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
+				goto change_okay;
+		}
+	}
+
+error:
+	abort_creds(new);
+	return old_fsuid;
+
+change_okay:
+	commit_creds(new);
+	return old_fsuid;
+}
+
+/*
+ * Samma på svenska..
+ */
+SYSCALL_DEFINE1(setfsgid, gid_t, gid)
+{
+	const struct cred *old;
+	struct cred *new;
+	gid_t old_fsgid;
+
+	new = prepare_creds();
+	if (!new)
+		return current_fsgid();
+	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)) {
+		if (gid != old_fsgid) {
+			new->fsgid = gid;
+			goto change_okay;
+		}
+	}
+
+error:
+	abort_creds(new);
+	return old_fsgid;
+
+change_okay:
+	commit_creds(new);
+	return old_fsgid;
+}
+
+void do_sys_times(struct tms *tms)
+{
+	struct task_cputime cputime;
+	cputime_t cutime, cstime;
+
+	thread_group_cputime(current, &cputime);
+	spin_lock_irq(&current->sighand->siglock);
+	cutime = current->signal->cutime;
+	cstime = current->signal->cstime;
+	spin_unlock_irq(&current->sighand->siglock);
+	tms->tms_utime = cputime_to_clock_t(cputime.utime);
+	tms->tms_stime = cputime_to_clock_t(cputime.stime);
+	tms->tms_cutime = cputime_to_clock_t(cutime);
+	tms->tms_cstime = cputime_to_clock_t(cstime);
+}
+
+SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
+{
+	if (tbuf) {
+		struct tms tmp;
+
+		do_sys_times(&tmp);
+		if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
+			return -EFAULT;
+	}
+	force_successful_syscall_return();
+	return (long) jiffies_64_to_clock_t(get_jiffies_64());
+}
+
+/*
+ * This needs some heavy checking ...
+ * I just haven't the stomach for it. I also don't fully
+ * understand sessions/pgrp etc. Let somebody who does explain it.
+ *
+ * OK, I think I have the protection semantics right.... this is really
+ * only important on a multi-user system anyway, to make sure one user
+ * can't send a signal to a process owned by another.  -TYT, 12/12/91
+ *
+ * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
+ * LBT 04.03.94
+ */
+SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
+{
+	struct task_struct *p;
+	struct task_struct *group_leader = current->group_leader;
+	struct pid *pgrp;
+	int err;
+
+	if (!pid)
+		pid = task_pid_vnr(group_leader);
+	if (!pgid)
+		pgid = pid;
+	if (pgid < 0)
+		return -EINVAL;
+
+	/* From this point forward we keep holding onto the tasklist lock
+	 * so that our parent does not change from under us. -DaveM
+	 */
+	write_lock_irq(&tasklist_lock);
+
+	err = -ESRCH;
+	p = find_task_by_vpid(pid);
+	if (!p)
+		goto out;
+
+	err = -EINVAL;
+	if (!thread_group_leader(p))
+		goto out;
+
+	if (same_thread_group(p->real_parent, group_leader)) {
+		err = -EPERM;
+		if (task_session(p) != task_session(group_leader))
+			goto out;
+		err = -EACCES;
+		if (p->did_exec)
+			goto out;
+	} else {
+		err = -ESRCH;
+		if (p != group_leader)
+			goto out;
+	}
+
+	err = -EPERM;
+	if (p->signal->leader)
+		goto out;
+
+	pgrp = task_pid(p);
+	if (pgid != pid) {
+		struct task_struct *g;
+
+		pgrp = find_vpid(pgid);
+		g = pid_task(pgrp, PIDTYPE_PGID);
+		if (!g || task_session(g) != task_session(group_leader))
+			goto out;
+	}
+
+	err = security_task_setpgid(p, pgid);
+	if (err)
+		goto out;
+
+	if (task_pgrp(p) != pgrp) {
+		change_pid(p, PIDTYPE_PGID, pgrp);
+		set_task_pgrp(p, pid_nr(pgrp));
+	}
+
+	err = 0;
+out:
+	/* All paths lead to here, thus we are safe. -DaveM */
+	write_unlock_irq(&tasklist_lock);
+	return err;
+}
+
+SYSCALL_DEFINE1(getpgid, pid_t, pid)
+{
+	struct task_struct *p;
+	struct pid *grp;
+	int retval;
+
+	rcu_read_lock();
+	if (!pid)
+		grp = task_pgrp(current);
+	else {
+		retval = -ESRCH;
+		p = find_task_by_vpid(pid);
+		if (!p)
+			goto out;
+		grp = task_pgrp(p);
+		if (!grp)
+			goto out;
+
+		retval = security_task_getpgid(p);
+		if (retval)
+			goto out;
+	}
+	retval = pid_vnr(grp);
+out:
+	rcu_read_unlock();
+	return retval;
+}
+
+#ifdef __ARCH_WANT_SYS_GETPGRP
+
+SYSCALL_DEFINE0(getpgrp)
+{
+	return sys_getpgid(0);
+}
+
+#endif
+
+SYSCALL_DEFINE1(getsid, pid_t, pid)
+{
+	struct task_struct *p;
+	struct pid *sid;
+	int retval;
+
+	rcu_read_lock();
+	if (!pid)
+		sid = task_session(current);
+	else {
+		retval = -ESRCH;
+		p = find_task_by_vpid(pid);
+		if (!p)
+			goto out;
+		sid = task_session(p);
+		if (!sid)
+			goto out;
+
+		retval = security_task_getsid(p);
+		if (retval)
+			goto out;
+	}
+	retval = pid_vnr(sid);
+out:
+	rcu_read_unlock();
+	return retval;
+}
+
+SYSCALL_DEFINE0(setsid)
+{
+	struct task_struct *group_leader = current->group_leader;
+	struct pid *sid = task_pid(group_leader);
+	pid_t session = pid_vnr(sid);
+	int err = -EPERM;
+
+	write_lock_irq(&tasklist_lock);
+	/* Fail if I am already a session leader */
+	if (group_leader->signal->leader)
+		goto out;
+
+	/* Fail if a process group id already exists that equals the
+	 * proposed session id.
+	 */
+	if (pid_task(sid, PIDTYPE_PGID))
+		goto out;
+
+	group_leader->signal->leader = 1;
+	__set_special_pids(sid);
+
+	proc_clear_tty(group_leader);
+
+	err = session;
+out:
+	write_unlock_irq(&tasklist_lock);
+	return err;
+}
+
+/*
+ * Supplementary group IDs
+ */
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+
+struct group_info *groups_alloc(int gidsetsize)
+{
+	struct group_info *group_info;
+	int nblocks;
+	int i;
+
+	nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
+	/* Make sure we always allocate at least one indirect block pointer */
+	nblocks = nblocks ? : 1;
+	group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
+	if (!group_info)
+		return NULL;
+	group_info->ngroups = gidsetsize;
+	group_info->nblocks = nblocks;
+	atomic_set(&group_info->usage, 1);
+
+	if (gidsetsize <= NGROUPS_SMALL)
+		group_info->blocks[0] = group_info->small_block;
+	else {
+		for (i = 0; i < nblocks; i++) {
+			gid_t *b;
+			b = (void *)__get_free_page(GFP_USER);
+			if (!b)
+				goto out_undo_partial_alloc;
+			group_info->blocks[i] = b;
+		}
+	}
+	return group_info;
+
+out_undo_partial_alloc:
+	while (--i >= 0) {
+		free_page((unsigned long)group_info->blocks[i]);
+	}
+	kfree(group_info);
+	return NULL;
+}
+
+EXPORT_SYMBOL(groups_alloc);
+
+void groups_free(struct group_info *group_info)
+{
+	if (group_info->blocks[0] != group_info->small_block) {
+		int i;
+		for (i = 0; i < group_info->nblocks; i++)
+			free_page((unsigned long)group_info->blocks[i]);
+	}
+	kfree(group_info);
+}
+
+EXPORT_SYMBOL(groups_free);
+
+/* export the group_info to a user-space array */
+static int groups_to_user(gid_t __user *grouplist,
+			  const struct group_info *group_info)
+{
+	int i;
+	unsigned int count = group_info->ngroups;
+
+	for (i = 0; i < group_info->nblocks; i++) {
+		unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
+		unsigned int len = cp_count * sizeof(*grouplist);
+
+		if (copy_to_user(grouplist, group_info->blocks[i], len))
+			return -EFAULT;
+
+		grouplist += NGROUPS_PER_BLOCK;
+		count -= cp_count;
+	}
+	return 0;
+}
+
+/* fill a group_info from a user-space array - it must be allocated already */
+static int groups_from_user(struct group_info *group_info,
+    gid_t __user *grouplist)
+{
+	int i;
+	unsigned int count = group_info->ngroups;
+
+	for (i = 0; i < group_info->nblocks; i++) {
+		unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
+		unsigned int len = cp_count * sizeof(*grouplist);
+
+		if (copy_from_user(group_info->blocks[i], grouplist, len))
+			return -EFAULT;
+
+		grouplist += NGROUPS_PER_BLOCK;
+		count -= cp_count;
+	}
+	return 0;
+}
+
+/* a simple Shell sort */
+static void groups_sort(struct group_info *group_info)
+{
+	int base, max, stride;
+	int gidsetsize = group_info->ngroups;
+
+	for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
+		; /* nothing */
+	stride /= 3;
+
+	while (stride) {
+		max = gidsetsize - stride;
+		for (base = 0; base < max; base++) {
+			int left = base;
+			int right = left + stride;
+			gid_t tmp = GROUP_AT(group_info, right);
+
+			while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
+				GROUP_AT(group_info, right) =
+				    GROUP_AT(group_info, left);
+				right = left;
+				left -= stride;
+			}
+			GROUP_AT(group_info, right) = tmp;
+		}
+		stride /= 3;
+	}
+}
+
+/* a simple bsearch */
+int groups_search(const struct group_info *group_info, gid_t grp)
+{
+	unsigned int left, right;
+
+	if (!group_info)
+		return 0;
+
+	left = 0;
+	right = group_info->ngroups;
+	while (left < right) {
+		unsigned int mid = (left+right)/2;
+		int cmp = grp - GROUP_AT(group_info, mid);
+		if (cmp > 0)
+			left = mid + 1;
+		else if (cmp < 0)
+			right = mid;
+		else
+			return 1;
+	}
+	return 0;
+}
+
+/**
+ * set_groups - Change a group subscription in a set of credentials
+ * @new: The newly prepared set of credentials to alter
+ * @group_info: The group list to install
+ *
+ * Validate a group subscription and, if valid, insert it into a set
+ * of credentials.
+ */
+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);
+	new->group_info = group_info;
+	return 0;
+}
+
+EXPORT_SYMBOL(set_groups);
+
+/**
+ * set_current_groups - Change current's group subscription
+ * @group_info: The group list to impose
+ *
+ * Validate a group subscription and, if valid, impose it upon current's task
+ * security record.
+ */
+int set_current_groups(struct group_info *group_info)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = set_groups(new, group_info);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret;
+	}
+
+	return commit_creds(new);
+}
+
+EXPORT_SYMBOL(set_current_groups);
+
+SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
+{
+	const struct cred *cred = current_cred();
+	int i;
+
+	if (gidsetsize < 0)
+		return -EINVAL;
+
+	/* no need to grab task_lock here; it cannot change */
+	i = cred->group_info->ngroups;
+	if (gidsetsize) {
+		if (i > gidsetsize) {
+			i = -EINVAL;
+			goto out;
+		}
+		if (groups_to_user(grouplist, cred->group_info)) {
+			i = -EFAULT;
+			goto out;
+		}
+	}
+out:
+	return i;
+}
+
+/*
+ *	SMP: Our groups are copy-on-write. We can set them safely
+ *	without another task interfering.
+ */
+ 
+SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
+{
+	struct group_info *group_info;
+	int retval;
+
+	if (!capable(CAP_SETGID))
+		return -EPERM;
+	if ((unsigned)gidsetsize > NGROUPS_MAX)
+		return -EINVAL;
+
+	group_info = groups_alloc(gidsetsize);
+	if (!group_info)
+		return -ENOMEM;
+	retval = groups_from_user(group_info, grouplist);
+	if (retval) {
+		put_group_info(group_info);
+		return retval;
+	}
+
+	retval = set_current_groups(group_info);
+	put_group_info(group_info);
+
+	return retval;
+}
+
+/*
+ * Check whether we're fsgid/egid or in the supplemental group..
+ */
+int in_group_p(gid_t grp)
+{
+	const struct cred *cred = current_cred();
+	int retval = 1;
+
+	if (grp != cred->fsgid)
+		retval = groups_search(cred->group_info, grp);
+	return retval;
+}
+
+EXPORT_SYMBOL(in_group_p);
+
+int in_egroup_p(gid_t grp)
+{
+	const struct cred *cred = current_cred();
+	int retval = 1;
+
+	if (grp != cred->egid)
+		retval = groups_search(cred->group_info, grp);
+	return retval;
+}
+
+EXPORT_SYMBOL(in_egroup_p);
+
+DECLARE_RWSEM(uts_sem);
+
+SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
+{
+	int errno = 0;
+
+	down_read(&uts_sem);
+	if (copy_to_user(name, utsname(), sizeof *name))
+		errno = -EFAULT;
+	up_read(&uts_sem);
+	return errno;
+}
+
+SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
+{
+	int errno;
+	char tmp[__NEW_UTS_LEN];
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (len < 0 || len > __NEW_UTS_LEN)
+		return -EINVAL;
+	down_write(&uts_sem);
+	errno = -EFAULT;
+	if (!copy_from_user(tmp, name, len)) {
+		struct new_utsname *u = utsname();
+
+		memcpy(u->nodename, tmp, len);
+		memset(u->nodename + len, 0, sizeof(u->nodename) - len);
+		errno = 0;
+	}
+	up_write(&uts_sem);
+	return errno;
+}
+
+#ifdef __ARCH_WANT_SYS_GETHOSTNAME
+
+SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
+{
+	int i, errno;
+	struct new_utsname *u;
+
+	if (len < 0)
+		return -EINVAL;
+	down_read(&uts_sem);
+	u = utsname();
+	i = 1 + strlen(u->nodename);
+	if (i > len)
+		i = len;
+	errno = 0;
+	if (copy_to_user(name, u->nodename, i))
+		errno = -EFAULT;
+	up_read(&uts_sem);
+	return errno;
+}
+
+#endif
+
+/*
+ * Only setdomainname; getdomainname can be implemented by calling
+ * uname()
+ */
+SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
+{
+	int errno;
+	char tmp[__NEW_UTS_LEN];
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (len < 0 || len > __NEW_UTS_LEN)
+		return -EINVAL;
+
+	down_write(&uts_sem);
+	errno = -EFAULT;
+	if (!copy_from_user(tmp, name, len)) {
+		struct new_utsname *u = utsname();
+
+		memcpy(u->domainname, tmp, len);
+		memset(u->domainname + len, 0, sizeof(u->domainname) - len);
+		errno = 0;
+	}
+	up_write(&uts_sem);
+	return errno;
+}
+
+SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+	if (resource >= RLIM_NLIMITS)
+		return -EINVAL;
+	else {
+		struct rlimit value;
+		task_lock(current->group_leader);
+		value = current->signal->rlim[resource];
+		task_unlock(current->group_leader);
+		return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
+	}
+}
+
+#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
+
+/*
+ *	Back compatibility for getrlimit. Needed for some apps.
+ */
+ 
+SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+		struct rlimit __user *, rlim)
+{
+	struct rlimit x;
+	if (resource >= RLIM_NLIMITS)
+		return -EINVAL;
+
+	task_lock(current->group_leader);
+	x = current->signal->rlim[resource];
+	task_unlock(current->group_leader);
+	if (x.rlim_cur > 0x7FFFFFFF)
+		x.rlim_cur = 0x7FFFFFFF;
+	if (x.rlim_max > 0x7FFFFFFF)
+		x.rlim_max = 0x7FFFFFFF;
+	return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
+}
+
+#endif
+
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+	struct rlimit new_rlim, *old_rlim;
+	int retval;
+
+	if (resource >= RLIM_NLIMITS)
+		return -EINVAL;
+	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+		return -EFAULT;
+	if (new_rlim.rlim_cur > new_rlim.rlim_max)
+		return -EINVAL;
+	old_rlim = current->signal->rlim + resource;
+	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
+	    !capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+		return -EPERM;
+
+	retval = security_task_setrlimit(resource, &new_rlim);
+	if (retval)
+		return retval;
+
+	if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
+		/*
+		 * The caller is asking for an immediate RLIMIT_CPU
+		 * expiry.  But we use the zero value to mean "it was
+		 * never set".  So let's cheat and make it one second
+		 * instead
+		 */
+		new_rlim.rlim_cur = 1;
+	}
+
+	task_lock(current->group_leader);
+	*old_rlim = new_rlim;
+	task_unlock(current->group_leader);
+
+	if (resource != RLIMIT_CPU)
+		goto out;
+
+	/*
+	 * RLIMIT_CPU handling.   Note that the kernel fails to return an error
+	 * code if it rejected the user's attempt to set RLIMIT_CPU.  This is a
+	 * very long-standing error, and fixing it now risks breakage of
+	 * applications, so we live with it
+	 */
+	if (new_rlim.rlim_cur == RLIM_INFINITY)
+		goto out;
+
+	update_rlimit_cpu(new_rlim.rlim_cur);
+out:
+	return 0;
+}
+
+/*
+ * It would make sense to put struct rusage in the task_struct,
+ * except that would make the task_struct be *really big*.  After
+ * task_struct gets moved into malloc'ed memory, it would
+ * make sense to do this.  It will make moving the rest of the information
+ * a lot simpler!  (Which we're not doing right now because we're not
+ * measuring them yet).
+ *
+ * When sampling multiple threads for RUSAGE_SELF, under SMP we might have
+ * races with threads incrementing their own counters.  But since word
+ * reads are atomic, we either get new values or old values and we don't
+ * care which for the sums.  We always take the siglock to protect reading
+ * the c* fields from p->signal from races with exit.c updating those
+ * fields when reaping, so a sample either gets all the additions of a
+ * given child after it's reaped, or none so this sample is before reaping.
+ *
+ * Locking:
+ * We need to take the siglock for CHILDEREN, SELF and BOTH
+ * for  the cases current multithreaded, non-current single threaded
+ * non-current multithreaded.  Thread traversal is now safe with
+ * the siglock held.
+ * Strictly speaking, we donot need to take the siglock if we are current and
+ * single threaded,  as no one else can take our signal_struct away, no one
+ * else can  reap the  children to update signal->c* counters, and no one else
+ * can race with the signal-> fields. If we do not take any lock, the
+ * signal-> fields could be read out of order while another thread was just
+ * exiting. So we should  place a read memory barrier when we avoid the lock.
+ * On the writer side,  write memory barrier is implied in  __exit_signal
+ * as __exit_signal releases  the siglock spinlock after updating the signal->
+ * fields. But we don't do this yet to keep things simple.
+ *
+ */
+
+static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
+{
+	r->ru_nvcsw += t->nvcsw;
+	r->ru_nivcsw += t->nivcsw;
+	r->ru_minflt += t->min_flt;
+	r->ru_majflt += t->maj_flt;
+	r->ru_inblock += task_io_get_inblock(t);
+	r->ru_oublock += task_io_get_oublock(t);
+}
+
+static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
+{
+	struct task_struct *t;
+	unsigned long flags;
+	cputime_t utime, stime;
+	struct task_cputime cputime;
+
+	memset((char *) r, 0, sizeof *r);
+	utime = stime = cputime_zero;
+
+	if (who == RUSAGE_THREAD) {
+		utime = task_utime(current);
+		stime = task_stime(current);
+		accumulate_thread_rusage(p, r);
+		goto out;
+	}
+
+	if (!lock_task_sighand(p, &flags))
+		return;
+
+	switch (who) {
+		case RUSAGE_BOTH:
+		case RUSAGE_CHILDREN:
+			utime = p->signal->cutime;
+			stime = p->signal->cstime;
+			r->ru_nvcsw = p->signal->cnvcsw;
+			r->ru_nivcsw = p->signal->cnivcsw;
+			r->ru_minflt = p->signal->cmin_flt;
+			r->ru_majflt = p->signal->cmaj_flt;
+			r->ru_inblock = p->signal->cinblock;
+			r->ru_oublock = p->signal->coublock;
+
+			if (who == RUSAGE_CHILDREN)
+				break;
+
+		case RUSAGE_SELF:
+			thread_group_cputime(p, &cputime);
+			utime = cputime_add(utime, cputime.utime);
+			stime = cputime_add(stime, cputime.stime);
+			r->ru_nvcsw += p->signal->nvcsw;
+			r->ru_nivcsw += p->signal->nivcsw;
+			r->ru_minflt += p->signal->min_flt;
+			r->ru_majflt += p->signal->maj_flt;
+			r->ru_inblock += p->signal->inblock;
+			r->ru_oublock += p->signal->oublock;
+			t = p;
+			do {
+				accumulate_thread_rusage(t, r);
+				t = next_thread(t);
+			} while (t != p);
+			break;
+
+		default:
+			BUG();
+	}
+	unlock_task_sighand(p, &flags);
+
+out:
+	cputime_to_timeval(utime, &r->ru_utime);
+	cputime_to_timeval(stime, &r->ru_stime);
+}
+
+int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
+{
+	struct rusage r;
+	k_getrusage(p, who, &r);
+	return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
+}
+
+SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
+{
+	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
+	    who != RUSAGE_THREAD)
+		return -EINVAL;
+	return getrusage(current, who, ru);
+}
+
+SYSCALL_DEFINE1(umask, int, mask)
+{
+	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
+	return mask;
+}
+
+SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
+		unsigned long, arg4, unsigned long, arg5)
+{
+	struct task_struct *me = current;
+	unsigned char comm[sizeof(me->comm)];
+	long error;
+
+	error = security_task_prctl(option, arg2, arg3, arg4, arg5);
+	if (error != -ENOSYS)
+		return error;
+
+	error = 0;
+	switch (option) {
+		case PR_SET_PDEATHSIG:
+			if (!valid_signal(arg2)) {
+				error = -EINVAL;
+				break;
+			}
+			me->pdeath_signal = arg2;
+			error = 0;
+			break;
+		case PR_GET_PDEATHSIG:
+			error = put_user(me->pdeath_signal, (int __user *)arg2);
+			break;
+		case PR_GET_DUMPABLE:
+			error = get_dumpable(me->mm);
+			break;
+		case PR_SET_DUMPABLE:
+			if (arg2 < 0 || arg2 > 1) {
+				error = -EINVAL;
+				break;
+			}
+			set_dumpable(me->mm, arg2);
+			error = 0;
+			break;
+
+		case PR_SET_UNALIGN:
+			error = SET_UNALIGN_CTL(me, arg2);
+			break;
+		case PR_GET_UNALIGN:
+			error = GET_UNALIGN_CTL(me, arg2);
+			break;
+		case PR_SET_FPEMU:
+			error = SET_FPEMU_CTL(me, arg2);
+			break;
+		case PR_GET_FPEMU:
+			error = GET_FPEMU_CTL(me, arg2);
+			break;
+		case PR_SET_FPEXC:
+			error = SET_FPEXC_CTL(me, arg2);
+			break;
+		case PR_GET_FPEXC:
+			error = GET_FPEXC_CTL(me, arg2);
+			break;
+		case PR_GET_TIMING:
+			error = PR_TIMING_STATISTICAL;
+			break;
+		case PR_SET_TIMING:
+			if (arg2 != PR_TIMING_STATISTICAL)
+				error = -EINVAL;
+			else
+				error = 0;
+			break;
+
+		case PR_SET_NAME:
+			comm[sizeof(me->comm)-1] = 0;
+			if (strncpy_from_user(comm, (char __user *)arg2,
+					      sizeof(me->comm) - 1) < 0)
+				return -EFAULT;
+			set_task_comm(me, comm);
+			return 0;
+		case PR_GET_NAME:
+			get_task_comm(comm, me);
+			if (copy_to_user((char __user *)arg2, comm,
+					 sizeof(comm)))
+				return -EFAULT;
+			return 0;
+		case PR_GET_ENDIAN:
+			error = GET_ENDIAN(me, arg2);
+			break;
+		case PR_SET_ENDIAN:
+			error = SET_ENDIAN(me, arg2);
+			break;
+
+		case PR_GET_SECCOMP:
+			error = prctl_get_seccomp();
+			break;
+		case PR_SET_SECCOMP:
+			error = prctl_set_seccomp(arg2);
+			break;
+		case PR_GET_TSC:
+			error = GET_TSC_CTL(arg2);
+			break;
+		case PR_SET_TSC:
+			error = SET_TSC_CTL(arg2);
+			break;
+		case PR_GET_TIMERSLACK:
+			error = current->timer_slack_ns;
+			break;
+		case PR_SET_TIMERSLACK:
+			if (arg2 <= 0)
+				current->timer_slack_ns =
+					current->default_timer_slack_ns;
+			else
+				current->timer_slack_ns = arg2;
+			error = 0;
+			break;
+		default:
+			error = -EINVAL;
+			break;
+	}
+	return error;
+}
+
+SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
+		struct getcpu_cache __user *, unused)
+{
+	int err = 0;
+	int cpu = raw_smp_processor_id();
+	if (cpup)
+		err |= put_user(cpu, cpup);
+	if (nodep)
+		err |= put_user(cpu_to_node(cpu), nodep);
+	return err ? -EFAULT : 0;
+}
+
+char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
+
+static void argv_cleanup(char **argv, char **envp)
+{
+	argv_free(argv);
+}
+
+/**
+ * orderly_poweroff - Trigger an orderly system poweroff
+ * @force: force poweroff if command execution fails
+ *
+ * This may be called from any context to trigger a system shutdown.
+ * If the orderly shutdown fails, it will force an immediate shutdown.
+ */
+int orderly_poweroff(bool force)
+{
+	int argc;
+	char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
+	static char *envp[] = {
+		"HOME=/",
+		"PATH=/sbin:/bin:/usr/sbin:/usr/bin",
+		NULL
+	};
+	int ret = -ENOMEM;
+	struct subprocess_info *info;
+
+	if (argv == NULL) {
+		printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
+		       __func__, poweroff_cmd);
+		goto out;
+	}
+
+	info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
+	if (info == NULL) {
+		argv_free(argv);
+		goto out;
+	}
+
+	call_usermodehelper_setcleanup(info, argv_cleanup);
+
+	ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
+
+  out:
+	if (ret && force) {
+		printk(KERN_WARNING "Failed to start orderly shutdown: "
+		       "forcing the issue\n");
+
+		/* I guess this should try to kick off some daemon to
+		   sync and poweroff asap.  Or not even bother syncing
+		   if we're doing an emergency shutdown? */
+		emergency_sync();
+		kernel_power_off();
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(orderly_poweroff);
+#endif /* DDE_LINUX */
diff --git a/libdde-linux26/lib/src/kernel/time.c b/libdde-linux26/lib/src/kernel/time.c
new file mode 100644
index 00000000..ce5b5fd4
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/time.c
@@ -0,0 +1,765 @@
+/*
+ *  linux/kernel/time.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  This file contains the interface functions for the various
+ *  time related system calls: time, stime, gettimeofday, settimeofday,
+ *			       adjtime
+ */
+/*
+ * Modification history kernel/time.c
+ *
+ * 1993-09-02    Philip Gladstone
+ *      Created file with time related functions from sched.c and adjtimex()
+ * 1993-10-08    Torsten Duwe
+ *      adjtime interface update and CMOS clock write code
+ * 1995-08-13    Torsten Duwe
+ *      kernel PLL updated to 1994-12-13 specs (rfc-1589)
+ * 1999-01-16    Ulrich Windl
+ *	Introduced error checking for many cases in adjtimex().
+ *	Updated NTP code according to technical memorandum Jan '96
+ *	"A Kernel Model for Precision Timekeeping" by Dave Mills
+ *	Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10)
+ *	(Even though the technical memorandum forbids it)
+ * 2004-07-14	 Christoph Lameter
+ *	Added getnstimeofday to allow the posix timer functions to return
+ *	with nanosecond accuracy
+ */
+
+#include <linux/module.h>
+#include <linux/timex.h>
+#include <linux/capability.h>
+#include <linux/clocksource.h>
+#include <linux/errno.h>
+#include <linux/syscalls.h>
+#include <linux/security.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/math64.h>
+#include <linux/ptrace.h>
+
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+
+#include "timeconst.h"
+#include <ddekit/timer.h>
+
+/*
+ * The timezone where the local system is located.  Used as a default by some
+ * programs who obtain this value by using gettimeofday.
+ */
+struct timezone sys_tz;
+
+EXPORT_SYMBOL(sys_tz);
+
+#ifdef __ARCH_WANT_SYS_TIME
+
+/*
+ * sys_time() can be implemented in user-level using
+ * sys_gettimeofday().  Is this for backwards compatibility?  If so,
+ * why not move it into the appropriate arch directory (for those
+ * architectures that need it).
+ */
+SYSCALL_DEFINE1(time, time_t __user *, tloc)
+{
+	time_t i = get_seconds();
+
+	if (tloc) {
+		if (put_user(i,tloc))
+			return -EFAULT;
+	}
+	force_successful_syscall_return();
+	return i;
+}
+
+/*
+ * sys_stime() can be implemented in user-level using
+ * sys_settimeofday().  Is this for backwards compatibility?  If so,
+ * why not move it into the appropriate arch directory (for those
+ * architectures that need it).
+ */
+
+SYSCALL_DEFINE1(stime, time_t __user *, tptr)
+{
+	struct timespec tv;
+	int err;
+
+	if (get_user(tv.tv_sec, tptr))
+		return -EFAULT;
+
+	tv.tv_nsec = 0;
+
+	err = security_settime(&tv, NULL);
+	if (err)
+		return err;
+
+	do_settimeofday(&tv);
+	return 0;
+}
+
+#endif /* __ARCH_WANT_SYS_TIME */
+
+SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
+		struct timezone __user *, tz)
+{
+	if (likely(tv != NULL)) {
+		struct timeval ktv;
+		do_gettimeofday(&ktv);
+		if (copy_to_user(tv, &ktv, sizeof(ktv)))
+			return -EFAULT;
+	}
+	if (unlikely(tz != NULL)) {
+		if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+/*
+ * Adjust the time obtained from the CMOS to be UTC time instead of
+ * local time.
+ *
+ * This is ugly, but preferable to the alternatives.  Otherwise we
+ * would either need to write a program to do it in /etc/rc (and risk
+ * confusion if the program gets run more than once; it would also be
+ * hard to make the program warp the clock precisely n hours)  or
+ * compile in the timezone information into the kernel.  Bad, bad....
+ *
+ *						- TYT, 1992-01-01
+ *
+ * The best thing to do is to keep the CMOS clock in universal time (UTC)
+ * as real UNIX machines always do it. This avoids all headaches about
+ * daylight saving times and warping kernel clocks.
+ */
+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();
+}
+
+/*
+ * In case for some reason the CMOS clock has not already been running
+ * in UTC, but in some local time: The first time we set the timezone,
+ * we will warp the clock so that it is ticking UTC time instead of
+ * local time. Presumably, if someone is setting the timezone then we
+ * are running in an environment where the programs understand about
+ * timezones. This should be done at boot time in the /etc/rc script,
+ * as soon as possible, so that the clock can be set right. Otherwise,
+ * various programs will get confused when the clock gets warped.
+ */
+
+int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
+{
+	static int firsttime = 1;
+	int error = 0;
+
+	if (tv && !timespec_valid(tv))
+		return -EINVAL;
+
+	error = security_settime(tv, tz);
+	if (error)
+		return error;
+
+	if (tz) {
+		/* SMP safe, global irq locking makes it work. */
+		sys_tz = *tz;
+		update_vsyscall_tz();
+		if (firsttime) {
+			firsttime = 0;
+			if (!tv)
+				warp_clock();
+		}
+	}
+	if (tv)
+	{
+		/* SMP safe, again the code in arch/foo/time.c should
+		 * globally block out interrupts when it runs.
+		 */
+		return do_settimeofday(tv);
+	}
+	return 0;
+}
+
+SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
+		struct timezone __user *, tz)
+{
+	struct timeval user_tv;
+	struct timespec	new_ts;
+	struct timezone new_tz;
+
+	if (tv) {
+		if (copy_from_user(&user_tv, tv, sizeof(*tv)))
+			return -EFAULT;
+		new_ts.tv_sec = user_tv.tv_sec;
+		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
+	}
+	if (tz) {
+		if (copy_from_user(&new_tz, tz, sizeof(*tz)))
+			return -EFAULT;
+	}
+
+	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
+}
+
+SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
+{
+	struct timex txc;		/* Local copy of parameter */
+	int ret;
+
+	/* Copy the user data space into the kernel copy
+	 * structure. But bear in mind that the structures
+	 * may change
+	 */
+	if(copy_from_user(&txc, txc_p, sizeof(struct timex)))
+		return -EFAULT;
+	ret = do_adjtimex(&txc);
+	return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
+}
+
+#ifndef DDE_LINUX
+/**
+ * current_fs_time - Return FS time
+ * @sb: Superblock.
+ *
+ * Return the current time truncated to the time granularity supported by
+ * the fs.
+ */
+struct timespec current_fs_time(struct super_block *sb)
+{
+	struct timespec now = current_kernel_time();
+	return timespec_trunc(now, sb->s_time_gran);
+}
+EXPORT_SYMBOL(current_fs_time);
+
+/*
+ * Convert jiffies to milliseconds and back.
+ *
+ * Avoid unnecessary multiplications/divisions in the
+ * two most common HZ cases:
+ */
+unsigned int inline jiffies_to_msecs(const unsigned long j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+	return (MSEC_PER_SEC / HZ) * j;
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+	return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
+#else
+# if BITS_PER_LONG == 32
+	return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+# else
+	return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+# endif
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_msecs);
+
+unsigned int inline jiffies_to_usecs(const unsigned long j)
+{
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+	return (USEC_PER_SEC / HZ) * j;
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+	return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
+#else
+# if BITS_PER_LONG == 32
+	return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32;
+# else
+	return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN;
+# endif
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_usecs);
+#endif
+
+/**
+ * timespec_trunc - Truncate timespec to a granularity
+ * @t: Timespec
+ * @gran: Granularity in ns.
+ *
+ * Truncate a timespec to a granularity. gran must be smaller than a second.
+ * Always rounds down.
+ *
+ * This function should be only used for timestamps returned by
+ * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because
+ * it doesn't handle the better resolution of the latter.
+ */
+struct timespec timespec_trunc(struct timespec t, unsigned gran)
+{
+	/*
+	 * Division is pretty slow so avoid it for common cases.
+	 * Currently current_kernel_time() never returns better than
+	 * jiffies resolution. Exploit that.
+	 */
+	if (gran <= jiffies_to_usecs(1) * 1000) {
+		/* nothing */
+	} else if (gran == 1000000000) {
+		t.tv_nsec = 0;
+	} else {
+		t.tv_nsec -= t.tv_nsec % gran;
+	}
+	return t;
+}
+EXPORT_SYMBOL(timespec_trunc);
+
+#ifndef CONFIG_GENERIC_TIME
+/*
+ * Simulate gettimeofday using do_gettimeofday which only allows a timeval
+ * and therefore only yields usec accuracy
+ */
+void getnstimeofday(struct timespec *tv)
+{
+	struct timeval x;
+
+	do_gettimeofday(&x);
+	tv->tv_sec = x.tv_sec;
+	tv->tv_nsec = x.tv_usec * NSEC_PER_USEC;
+}
+EXPORT_SYMBOL_GPL(getnstimeofday);
+#endif
+
+/* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
+ * Assumes input in normal date format, i.e. 1980-12-31 23:59:59
+ * => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
+ *
+ * [For the Julian calendar (which was used in Russia before 1917,
+ * Britain & colonies before 1752, anywhere else before 1582,
+ * and is still in use by some communities) leave out the
+ * -year/100+year/400 terms, and add 10.]
+ *
+ * This algorithm was first published by Gauss (I think).
+ *
+ * WARNING: this function will overflow on 2106-02-07 06:28:16 on
+ * machines where long is 32-bit! (However, as time_t is signed, we
+ * will already get problems at other places on 2038-01-19 03:14:08)
+ */
+unsigned long
+mktime(const unsigned int year0, const unsigned int mon0,
+       const unsigned int day, const unsigned int hour,
+       const unsigned int min, const unsigned int sec)
+{
+	unsigned int mon = mon0, year = year0;
+
+	/* 1..12 -> 11,12,1..10 */
+	if (0 >= (int) (mon -= 2)) {
+		mon += 12;	/* Puts Feb last since it has leap day */
+		year -= 1;
+	}
+
+	return ((((unsigned long)
+		  (year/4 - year/100 + year/400 + 367*mon/12 + day) +
+		  year*365 - 719499
+	    )*24 + hour /* now have hours */
+	  )*60 + min /* now have minutes */
+	)*60 + sec; /* finally seconds */
+}
+
+EXPORT_SYMBOL(mktime);
+
+/**
+ * set_normalized_timespec - set timespec sec and nsec parts and normalize
+ *
+ * @ts:		pointer to timespec variable to be set
+ * @sec:	seconds to set
+ * @nsec:	nanoseconds to set
+ *
+ * Set seconds and nanoseconds field of a timespec variable and
+ * normalize to the timespec storage format
+ *
+ * Note: The tv_nsec part is always in the range of
+ *	0 <= tv_nsec < NSEC_PER_SEC
+ * For negative values only the tv_sec field is negative !
+ */
+void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec)
+{
+	while (nsec >= NSEC_PER_SEC) {
+		nsec -= NSEC_PER_SEC;
+		++sec;
+	}
+	while (nsec < 0) {
+		nsec += NSEC_PER_SEC;
+		--sec;
+	}
+	ts->tv_sec = sec;
+	ts->tv_nsec = nsec;
+}
+EXPORT_SYMBOL(set_normalized_timespec);
+
+/**
+ * ns_to_timespec - Convert nanoseconds to timespec
+ * @nsec:       the nanoseconds value to be converted
+ *
+ * Returns the timespec representation of the nsec parameter.
+ */
+struct timespec ns_to_timespec(const s64 nsec)
+{
+	struct timespec ts;
+	s32 rem;
+
+	if (!nsec)
+		return (struct timespec) {0, 0};
+
+	ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
+	if (unlikely(rem < 0)) {
+		ts.tv_sec--;
+		rem += NSEC_PER_SEC;
+	}
+	ts.tv_nsec = rem;
+
+	return ts;
+}
+EXPORT_SYMBOL(ns_to_timespec);
+
+/**
+ * ns_to_timeval - Convert nanoseconds to timeval
+ * @nsec:       the nanoseconds value to be converted
+ *
+ * Returns the timeval representation of the nsec parameter.
+ */
+struct timeval ns_to_timeval(const s64 nsec)
+{
+	struct timespec ts = ns_to_timespec(nsec);
+	struct timeval tv;
+
+	tv.tv_sec = ts.tv_sec;
+	tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;
+
+	return tv;
+}
+EXPORT_SYMBOL(ns_to_timeval);
+
+#ifndef DDE_LINUX
+/*
+ * Convert jiffies to milliseconds and back.
+ *
+ * Avoid unnecessary multiplications/divisions in the
+ * two most common HZ cases:
+ */
+unsigned int jiffies_to_msecs(const unsigned long j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+	return (MSEC_PER_SEC / HZ) * j;
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+	return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
+#else
+	return (j * MSEC_PER_SEC) / HZ;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_msecs);
+
+unsigned int jiffies_to_usecs(const unsigned long j)
+{
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+	return (USEC_PER_SEC / HZ) * j;
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+	return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
+#else
+	return (j * USEC_PER_SEC) / HZ;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_usecs);
+
+/*
+ * When we convert to jiffies then we interpret incoming values
+ * the following way:
+ *
+ * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
+ *
+ * - 'too large' values [that would result in larger than
+ *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ *   the input value by a factor or dividing it with a factor
+ *
+ * We must also be careful about 32-bit overflows.
+ */
+unsigned long msecs_to_jiffies(const unsigned int m)
+{
+	/*
+	 * Negative value, means infinite timeout:
+	 */
+	if ((int)m < 0)
+		return MAX_JIFFY_OFFSET;
+
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+	/*
+	 * HZ is equal to or smaller than 1000, and 1000 is a nice
+	 * round multiple of HZ, divide with the factor between them,
+	 * but round upwards:
+	 */
+	return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+	/*
+	 * HZ is larger than 1000, and HZ is a nice round multiple of
+	 * 1000 - simply multiply with the factor between them.
+	 *
+	 * But first make sure the multiplication result cannot
+	 * overflow:
+	 */
+	if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+
+	return m * (HZ / MSEC_PER_SEC);
+#else
+	/*
+	 * Generic case - multiply, round and divide. But first
+	 * check that if we are doing a net multiplication, that
+	 * we wouldn't overflow:
+	 */
+	if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+
+	return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32)
+		>> MSEC_TO_HZ_SHR32;
+#endif
+}
+EXPORT_SYMBOL(msecs_to_jiffies);
+
+unsigned long usecs_to_jiffies(const unsigned int u)
+{
+	if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+	return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+	return u * (HZ / USEC_PER_SEC);
+#else
+	return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
+		>> USEC_TO_HZ_SHR32;
+#endif
+}
+EXPORT_SYMBOL(usecs_to_jiffies);
+#else /* DDE_LINUX */
+unsigned int jiffies_to_msecs(const unsigned long j)
+{
+	return (j*1000) / HZ;
+}
+EXPORT_SYMBOL(jiffies_to_msecs);
+
+unsigned int jiffies_to_usecs(const unsigned long j)
+{
+	return (j*1000000) / HZ;
+}
+EXPORT_SYMBOL(jiffies_to_usecs);
+
+unsigned long msecs_to_jiffies(const unsigned int m)
+{
+	if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+	return (m * HZ + MSEC_PER_SEC) / MSEC_PER_SEC;
+}
+EXPORT_SYMBOL(msecs_to_jiffies);
+
+unsigned long usecs_to_jiffies(const unsigned int u)
+{
+	if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+	return (u * HZ + USEC_PER_SEC - 1) / USEC_PER_SEC;
+}
+EXPORT_SYMBOL(usecs_to_jiffies);
+#endif
+
+/*
+ * The TICK_NSEC - 1 rounds up the value to the next resolution.  Note
+ * that a remainder subtract here would not do the right thing as the
+ * resolution values don't fall on second boundries.  I.e. the line:
+ * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ *
+ * Rather, we just shift the bits off the right.
+ *
+ * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
+ * value to a scaled second value.
+ */
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	unsigned long sec = value->tv_sec;
+	long nsec = value->tv_nsec + TICK_NSEC - 1;
+
+	if (sec >= MAX_SEC_IN_JIFFIES){
+		sec = MAX_SEC_IN_JIFFIES;
+		nsec = 0;
+	}
+	return (((u64)sec * SEC_CONVERSION) +
+		(((u64)nsec * NSEC_CONVERSION) >>
+		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+
+}
+EXPORT_SYMBOL(timespec_to_jiffies);
+
+void
+jiffies_to_timespec(const unsigned long jiffiesv, struct timespec *value)
+{
+	/*
+	 * Convert jiffies to nanoseconds and separate with
+	 * one divide.
+	 */
+	u32 rem;
+	value->tv_sec = div_u64_rem((u64)jiffiesv * TICK_NSEC,
+				    NSEC_PER_SEC, &rem);
+	value->tv_nsec = rem;
+}
+EXPORT_SYMBOL(jiffies_to_timespec);
+
+/* Same for "timeval"
+ *
+ * Well, almost.  The problem here is that the real system resolution is
+ * in nanoseconds and the value being converted is in micro seconds.
+ * Also for some machines (those that use HZ = 1024, in-particular),
+ * there is a LARGE error in the tick size in microseconds.
+
+ * The solution we use is to do the rounding AFTER we convert the
+ * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
+ * Instruction wise, this should cost only an additional add with carry
+ * instruction above the way it was done above.
+ */
+unsigned long
+timeval_to_jiffies(const struct timeval *value)
+{
+	unsigned long sec = value->tv_sec;
+	long usec = value->tv_usec;
+
+	if (sec >= MAX_SEC_IN_JIFFIES){
+		sec = MAX_SEC_IN_JIFFIES;
+		usec = 0;
+	}
+	return (((u64)sec * SEC_CONVERSION) +
+		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
+		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+}
+EXPORT_SYMBOL(timeval_to_jiffies);
+
+void jiffies_to_timeval(const unsigned long jiffiesv, struct timeval *value)
+{
+	/*
+	 * Convert jiffies to nanoseconds and separate with
+	 * one divide.
+	 */
+	u32 rem;
+
+	value->tv_sec = div_u64_rem((u64)jiffiesv * TICK_NSEC,
+				    NSEC_PER_SEC, &rem);
+	value->tv_usec = rem / NSEC_PER_USEC;
+}
+EXPORT_SYMBOL(jiffies_to_timeval);
+
+/*
+ * Convert jiffies/jiffies_64 to clock_t and back.
+ */
+clock_t jiffies_to_clock_t(long x)
+{
+#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
+# if HZ < USER_HZ
+	return x * (USER_HZ / HZ);
+# else
+	return x / (HZ / USER_HZ);
+# endif
+#else
+	return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ);
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_clock_t);
+
+#ifndef DDE_LINUX
+unsigned long clock_t_to_jiffies(unsigned long x)
+{
+#if (HZ % USER_HZ)==0
+	if (x >= ~0UL / (HZ / USER_HZ))
+		return ~0UL;
+	return x * (HZ / USER_HZ);
+#else
+	/* Don't worry about loss of precision here .. */
+	if (x >= ~0UL / HZ * USER_HZ)
+		return ~0UL;
+
+	/* .. but do try to contain it here */
+	return div_u64((u64)x * HZ, USER_HZ);
+#endif
+}
+#else
+unsigned long clock_t_to_jiffies(unsigned long x)
+{
+	assert (HZ);
+	assert (USER_HZ);
+	if (x >= ~0UL / (HZ / USER_HZ))
+		return ~0UL;
+	return x * (HZ / USER_HZ);
+}
+#endif /* DDE_LINUX */
+EXPORT_SYMBOL(clock_t_to_jiffies);
+
+u64 jiffies_64_to_clock_t(u64 x)
+{
+#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
+# if HZ < USER_HZ
+	x = div_u64(x * USER_HZ, HZ);
+# elif HZ > USER_HZ
+	x = div_u64(x, HZ / USER_HZ);
+# else
+	/* Nothing to do */
+# endif
+#else
+	/*
+	 * There are better ways that don't overflow early,
+	 * but even this doesn't overflow in hundreds of years
+	 * in 64 bits, so..
+	 */
+	x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ));
+#endif
+	return x;
+}
+EXPORT_SYMBOL(jiffies_64_to_clock_t);
+
+u64 nsec_to_clock_t(u64 x)
+{
+#if (NSEC_PER_SEC % USER_HZ) == 0
+	return div_u64(x, NSEC_PER_SEC / USER_HZ);
+#elif (USER_HZ % 512) == 0
+	return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512);
+#else
+	/*
+         * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
+         * overflow after 64.99 years.
+         * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
+         */
+	return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ);
+#endif
+}
+
+#if (BITS_PER_LONG < 64)
+u64 get_jiffies_64(void)
+{
+	unsigned long seq;
+	u64 ret;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		ret = jiffies_64;
+	} while (read_seqretry(&xtime_lock, seq));
+	return ret;
+}
+EXPORT_SYMBOL(get_jiffies_64);
+#endif
+
+EXPORT_SYMBOL(jiffies);
+
+/*
+ * Add two timespec values and do a safety check for overflow.
+ * It's assumed that both values are valid (>= 0)
+ */
+struct timespec timespec_add_safe(const struct timespec lhs,
+				  const struct timespec rhs)
+{
+	struct timespec res;
+
+	set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec,
+				lhs.tv_nsec + rhs.tv_nsec);
+
+	if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)
+		res.tv_sec = TIME_T_MAX;
+
+	return res;
+}
diff --git a/libdde-linux26/lib/src/kernel/timeconst.pl b/libdde-linux26/lib/src/kernel/timeconst.pl
new file mode 100755
index 00000000..d459895f
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/timeconst.pl
@@ -0,0 +1,378 @@
+#!/usr/bin/perl
+# -----------------------------------------------------------------------
+#
+#   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+#
+#   This file is part of the Linux kernel, and is made available under
+#   the terms of the GNU General Public License version 2 or (at your
+#   option) any later version; incorporated herein by reference.
+#
+# -----------------------------------------------------------------------
+#
+
+#
+# Usage: timeconst.pl HZ > timeconst.h
+#
+
+# Precomputed values for systems without Math::BigInt
+# Generated by:
+# timeconst.pl --can 24 32 48 64 100 122 128 200 250 256 300 512 1000 1024 1200
+%canned_values = (
+	24 => [
+		'0xa6aaaaab','0x2aaaaaa',26,
+		125,3,
+		'0xc49ba5e4','0x1fbe76c8b4',37,
+		3,125,
+		'0xa2c2aaab','0xaaaa',16,
+		125000,3,
+		'0xc9539b89','0x7fffbce4217d',47,
+		3,125000,
+	], 32 => [
+		'0xfa000000','0x6000000',27,
+		125,4,
+		'0x83126e98','0xfdf3b645a',36,
+		4,125,
+		'0xf4240000','0x0',17,
+		31250,1,
+		'0x8637bd06','0x3fff79c842fa',46,
+		1,31250,
+	], 48 => [
+		'0xa6aaaaab','0x6aaaaaa',27,
+		125,6,
+		'0xc49ba5e4','0xfdf3b645a',36,
+		6,125,
+		'0xa2c2aaab','0x15555',17,
+		62500,3,
+		'0xc9539b89','0x3fffbce4217d',46,
+		3,62500,
+	], 64 => [
+		'0xfa000000','0xe000000',28,
+		125,8,
+		'0x83126e98','0x7ef9db22d',35,
+		8,125,
+		'0xf4240000','0x0',18,
+		15625,1,
+		'0x8637bd06','0x1fff79c842fa',45,
+		1,15625,
+	], 100 => [
+		'0xa0000000','0x0',28,
+		10,1,
+		'0xcccccccd','0x733333333',35,
+		1,10,
+		'0x9c400000','0x0',18,
+		10000,1,
+		'0xd1b71759','0x1fff2e48e8a7',45,
+		1,10000,
+	], 122 => [
+		'0x8325c53f','0xfbcda3a',28,
+		500,61,
+		'0xf9db22d1','0x7fbe76c8b',35,
+		61,500,
+		'0x8012e2a0','0x3ef36',18,
+		500000,61,
+		'0xffda4053','0x1ffffbce4217',45,
+		61,500000,
+	], 128 => [
+		'0xfa000000','0x1e000000',29,
+		125,16,
+		'0x83126e98','0x3f7ced916',34,
+		16,125,
+		'0xf4240000','0x40000',19,
+		15625,2,
+		'0x8637bd06','0xfffbce4217d',44,
+		2,15625,
+	], 200 => [
+		'0xa0000000','0x0',29,
+		5,1,
+		'0xcccccccd','0x333333333',34,
+		1,5,
+		'0x9c400000','0x0',19,
+		5000,1,
+		'0xd1b71759','0xfff2e48e8a7',44,
+		1,5000,
+	], 250 => [
+		'0x80000000','0x0',29,
+		4,1,
+		'0x80000000','0x180000000',33,
+		1,4,
+		'0xfa000000','0x0',20,
+		4000,1,
+		'0x83126e98','0x7ff7ced9168',43,
+		1,4000,
+	], 256 => [
+		'0xfa000000','0x3e000000',30,
+		125,32,
+		'0x83126e98','0x1fbe76c8b',33,
+		32,125,
+		'0xf4240000','0xc0000',20,
+		15625,4,
+		'0x8637bd06','0x7ffde7210be',43,
+		4,15625,
+	], 300 => [
+		'0xd5555556','0x2aaaaaaa',30,
+		10,3,
+		'0x9999999a','0x1cccccccc',33,
+		3,10,
+		'0xd0555556','0xaaaaa',20,
+		10000,3,
+		'0x9d495183','0x7ffcb923a29',43,
+		3,10000,
+	], 512 => [
+		'0xfa000000','0x7e000000',31,
+		125,64,
+		'0x83126e98','0xfdf3b645',32,
+		64,125,
+		'0xf4240000','0x1c0000',21,
+		15625,8,
+		'0x8637bd06','0x3ffef39085f',42,
+		8,15625,
+	], 1000 => [
+		'0x80000000','0x0',31,
+		1,1,
+		'0x80000000','0x0',31,
+		1,1,
+		'0xfa000000','0x0',22,
+		1000,1,
+		'0x83126e98','0x1ff7ced9168',41,
+		1,1000,
+	], 1024 => [
+		'0xfa000000','0xfe000000',32,
+		125,128,
+		'0x83126e98','0x7ef9db22',31,
+		128,125,
+		'0xf4240000','0x3c0000',22,
+		15625,16,
+		'0x8637bd06','0x1fff79c842f',41,
+		16,15625,
+	], 1200 => [
+		'0xd5555556','0xd5555555',32,
+		5,6,
+		'0x9999999a','0x66666666',31,
+		6,5,
+		'0xd0555556','0x2aaaaa',22,
+		2500,3,
+		'0x9d495183','0x1ffcb923a29',41,
+		3,2500,
+	]
+);
+
+$has_bigint = eval 'use Math::BigInt qw(bgcd); 1;';
+
+sub bint($)
+{
+	my($x) = @_;
+	return Math::BigInt->new($x);
+}
+
+#
+# Constants for division by reciprocal multiplication.
+# (bits, numerator, denominator)
+#
+sub fmul($$$)
+{
+	my ($b,$n,$d) = @_;
+
+	$n = bint($n);
+	$d = bint($d);
+
+	return scalar (($n << $b)+$d-bint(1))/$d;
+}
+
+sub fadj($$$)
+{
+	my($b,$n,$d) = @_;
+
+	$n = bint($n);
+	$d = bint($d);
+
+	$d = $d/bgcd($n, $d);
+	return scalar (($d-bint(1)) << $b)/$d;
+}
+
+sub fmuls($$$) {
+	my($b,$n,$d) = @_;
+	my($s,$m);
+	my($thres) = bint(1) << ($b-1);
+
+	$n = bint($n);
+	$d = bint($d);
+
+	for ($s = 0; 1; $s++) {
+		$m = fmul($s,$n,$d);
+		return $s if ($m >= $thres);
+	}
+	return 0;
+}
+
+# Generate a hex value if the result fits in 64 bits;
+# otherwise skip.
+sub bignum_hex($) {
+	my($x) = @_;
+	my $s = $x->as_hex();
+
+	return (length($s) > 18) ? undef : $s;
+}
+
+# Provides mul, adj, and shr factors for a specific
+# (bit, time, hz) combination
+sub muladj($$$) {
+	my($b, $t, $hz) = @_;
+	my $s = fmuls($b, $t, $hz);
+	my $m = fmul($s, $t, $hz);
+	my $a = fadj($s, $t, $hz);
+	return (bignum_hex($m), bignum_hex($a), $s);
+}
+
+# Provides numerator, denominator values
+sub numden($$) {
+	my($n, $d) = @_;
+	my $g = bgcd($n, $d);
+	return ($n/$g, $d/$g);
+}
+
+# All values for a specific (time, hz) combo
+sub conversions($$) {
+	my ($t, $hz) = @_;
+	my @val = ();
+
+	# HZ_TO_xx
+	push(@val, muladj(32, $t, $hz));
+	push(@val, numden($t, $hz));
+
+	# xx_TO_HZ
+	push(@val, muladj(32, $hz, $t));
+	push(@val, numden($hz, $t));
+
+	return @val;
+}
+
+sub compute_values($) {
+	my($hz) = @_;
+	my @val = ();
+	my $s, $m, $a, $g;
+
+	if (!$has_bigint) {
+		die "$0: HZ == $hz not canned and ".
+		    "Math::BigInt not available\n";
+	}
+
+	# MSEC conversions
+	push(@val, conversions(1000, $hz));
+
+	# USEC conversions
+	push(@val, conversions(1000000, $hz));
+
+	return @val;
+}
+
+sub outputval($$)
+{
+	my($name, $val) = @_;
+	my $csuf;
+
+	if (defined($val)) {
+	    if ($name !~ /SHR/) {
+		$val = "U64_C($val)";
+	    }
+	    printf "#define %-23s %s\n", $name.$csuf, $val.$csuf;
+	}
+}
+
+sub output($@)
+{
+	my($hz, @val) = @_;
+	my $pfx, $bit, $suf, $s, $m, $a;
+
+	print "/* Automatically generated by kernel/timeconst.pl */\n";
+	print "/* Conversion constants for HZ == $hz */\n";
+	print "\n";
+	print "#ifndef KERNEL_TIMECONST_H\n";
+	print "#define KERNEL_TIMECONST_H\n";
+	print "\n";
+
+	print "#include <linux/param.h>\n";
+	print "#include <linux/types.h>\n";
+
+	print "\n";
+	print "#if HZ != $hz && !defined(DDE_LINUX)\n";
+	print "#error \"kernel/timeconst.h has the wrong HZ value!\"\n";
+	print "#endif\n";
+	print "\n";
+
+	foreach $pfx ('HZ_TO_MSEC','MSEC_TO_HZ',
+		      'HZ_TO_USEC','USEC_TO_HZ') {
+		foreach $bit (32) {
+			foreach $suf ('MUL', 'ADJ', 'SHR') {
+				outputval("${pfx}_$suf$bit", shift(@val));
+			}
+		}
+		foreach $suf ('NUM', 'DEN') {
+			outputval("${pfx}_$suf", shift(@val));
+		}
+	}
+
+	print "\n";
+	print "#endif /* KERNEL_TIMECONST_H */\n";
+}
+
+# Pretty-print Perl values
+sub perlvals(@) {
+	my $v;
+	my @l = ();
+
+	foreach $v (@_) {
+		if (!defined($v)) {
+			push(@l, 'undef');
+		} elsif ($v =~ /^0x/) {
+			push(@l, "\'".$v."\'");
+		} else {
+			push(@l, $v.'');
+		}
+	}
+	return join(',', @l);
+}
+
+($hz) = @ARGV;
+
+# Use this to generate the %canned_values structure
+if ($hz eq '--can') {
+	shift(@ARGV);
+	@hzlist = sort {$a <=> $b} (@ARGV);
+
+	print "# Precomputed values for systems without Math::BigInt\n";
+	print "# Generated by:\n";
+	print "# timeconst.pl --can ", join(' ', @hzlist), "\n";
+	print "\%canned_values = (\n";
+	my $pf = "\t";
+	foreach $hz (@hzlist) {
+		my @values = compute_values($hz);
+		print "$pf$hz => [\n";
+		while (scalar(@values)) {
+			my $bit;
+			foreach $bit (32) {
+				my $m = shift(@values);
+				my $a = shift(@values);
+				my $s = shift(@values);
+				print "\t\t", perlvals($m,$a,$s), ",\n";
+			}
+			my $n = shift(@values);
+			my $d = shift(@values);
+			print "\t\t", perlvals($n,$d), ",\n";
+		}
+		print "\t]";
+		$pf = ', ';
+	}
+	print "\n);\n";
+} else {
+	$hz += 0;			# Force to number
+	if ($hz < 1) {
+		die "Usage: $0 HZ\n";
+	}
+
+	@val = @{$canned_values{$hz}};
+	if (!defined(@val)) {
+		@val = compute_values($hz);
+	}
+	output($hz, @val);
+}
+exit 0;
diff --git a/libdde-linux26/lib/src/kernel/timer.c b/libdde-linux26/lib/src/kernel/timer.c
new file mode 100644
index 00000000..951d6ffc
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/timer.c
@@ -0,0 +1,1590 @@
+/*
+ *  linux/kernel/timer.c
+ *
+ *  Kernel internal timers, basic process system calls
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  1997-01-28  Modified by Finn Arne Gangstad to make timers scale better.
+ *
+ *  1997-09-10  Updated NTP code according to technical memorandum Jan '96
+ *              "A Kernel Model for Precision Timekeeping" by Dave Mills
+ *  1998-12-24  Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ *              serialize accesses to xtime/lost_ticks).
+ *                              Copyright (C) 1998  Andrea Arcangeli
+ *  1999-03-10  Improved NTP compatibility by Ulrich Windl
+ *  2002-05-31	Move sys_sysinfo here and make its locking sane, Robert Love
+ *  2000-10-05  Implemented scalable SMP per-CPU timer handling.
+ *                              Copyright (C) 2000, 2001, 2002  Ingo Molnar
+ *              Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pid_namespace.h>
+#include <linux/notifier.h>
+#include <linux/thread_info.h>
+#include <linux/time.h>
+#include <linux/jiffies.h>
+#include <linux/posix-timers.h>
+#include <linux/cpu.h>
+#include <linux/syscalls.h>
+#include <linux/delay.h>
+#include <linux/tick.h>
+#include <linux/kallsyms.h>
+
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/div64.h>
+#include <asm/timex.h>
+#include <asm/io.h>
+
+#include <ddekit/timer.h>
+
+#ifndef DDE_LINUX
+
+u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
+
+EXPORT_SYMBOL(jiffies_64);
+
+/*
+ * per-CPU timer vector definitions:
+ */
+#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6)
+#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8)
+#define TVN_SIZE (1 << TVN_BITS)
+#define TVR_SIZE (1 << TVR_BITS)
+#define TVN_MASK (TVN_SIZE - 1)
+#define TVR_MASK (TVR_SIZE - 1)
+
+struct tvec {
+	struct list_head vec[TVN_SIZE];
+};
+
+struct tvec_root {
+	struct list_head vec[TVR_SIZE];
+};
+
+struct tvec_base {
+	spinlock_t lock;
+	struct timer_list *running_timer;
+	unsigned long timer_jiffies;
+	struct tvec_root tv1;
+	struct tvec tv2;
+	struct tvec tv3;
+	struct tvec tv4;
+	struct tvec tv5;
+} ____cacheline_aligned;
+
+struct tvec_base boot_tvec_bases;
+EXPORT_SYMBOL(boot_tvec_bases);
+static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
+
+/*
+ * Note that all tvec_bases are 2 byte aligned and lower bit of
+ * base in timer_list is guaranteed to be zero. Use the LSB for
+ * the new flag to indicate whether the timer is deferrable
+ */
+#define TBASE_DEFERRABLE_FLAG		(0x1)
+
+/* Functions below help us manage 'deferrable' flag */
+static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
+{
+	return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG);
+}
+
+static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
+{
+	return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG));
+}
+
+static inline void timer_set_deferrable(struct timer_list *timer)
+{
+	timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
+				       TBASE_DEFERRABLE_FLAG));
+}
+
+static inline void
+timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
+{
+	timer->base = (struct tvec_base *)((unsigned long)(new_base) |
+				      tbase_get_deferrable(timer->base));
+}
+#endif /* DDE_LINUX */
+
+static unsigned long round_jiffies_common(unsigned long j, int cpu,
+		bool force_up)
+{
+	int rem;
+	unsigned long original = j;
+
+	/*
+	 * We don't want all cpus firing their timers at once hitting the
+	 * same lock or cachelines, so we skew each extra cpu with an extra
+	 * 3 jiffies. This 3 jiffies came originally from the mm/ code which
+	 * already did this.
+	 * The skew is done by adding 3*cpunr, then round, then subtract this
+	 * extra offset again.
+	 */
+	j += cpu * 3;
+
+	rem = j % HZ;
+
+	/*
+	 * If the target jiffie is just after a whole second (which can happen
+	 * due to delays of the timer irq, long irq off times etc etc) then
+	 * we should round down to the whole second, not up. Use 1/4th second
+	 * as cutoff for this rounding as an extreme upper bound for this.
+	 * But never round down if @force_up is set.
+	 */
+	if (rem < HZ/4 && !force_up) /* round down */
+		j = j - rem;
+	else /* round up */
+		j = j - rem + HZ;
+
+	/* now that we have rounded, subtract the extra skew again */
+	j -= cpu * 3;
+
+	if (j <= jiffies) /* rounding ate our timeout entirely; */
+		return original;
+	return j;
+}
+
+/**
+ * __round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies(unsigned long j, int cpu)
+{
+	return round_jiffies_common(j, cpu, false);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies);
+
+/**
+ * __round_jiffies_relative - function to round jiffies to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies_relative() rounds a time delta  in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies_relative(unsigned long j, int cpu)
+{
+	unsigned long j0 = jiffies;
+
+	/* Use j0 because jiffies might change while we run */
+	return round_jiffies_common(j + j0, cpu, false) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_relative);
+
+/**
+ * round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long round_jiffies(unsigned long j)
+{
+	return round_jiffies_common(j, raw_smp_processor_id(), false);
+}
+EXPORT_SYMBOL_GPL(round_jiffies);
+
+/**
+ * round_jiffies_relative - function to round jiffies to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * round_jiffies_relative() rounds a time delta  in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long round_jiffies_relative(unsigned long j)
+{
+	return __round_jiffies_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_relative);
+
+/**
+ * __round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up(unsigned long j, int cpu)
+{
+	return round_jiffies_common(j, cpu, true);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up);
+
+/**
+ * __round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
+{
+	unsigned long j0 = jiffies;
+
+	/* Use j0 because jiffies might change while we run */
+	return round_jiffies_common(j + j0, cpu, true) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);
+
+/**
+ * round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up(unsigned long j)
+{
+	return round_jiffies_common(j, raw_smp_processor_id(), true);
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up);
+
+/**
+ * round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up_relative(unsigned long j)
+{
+	return __round_jiffies_up_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
+
+
+#ifndef DDE_LINUX
+static inline void set_running_timer(struct tvec_base *base,
+					struct timer_list *timer)
+{
+#ifdef CONFIG_SMP
+	base->running_timer = timer;
+#endif
+}
+
+static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+{
+	unsigned long expires = timer->expires;
+	unsigned long idx = expires - base->timer_jiffies;
+	struct list_head *vec;
+
+	if (idx < TVR_SIZE) {
+		int i = expires & TVR_MASK;
+		vec = base->tv1.vec + i;
+	} else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
+		int i = (expires >> TVR_BITS) & TVN_MASK;
+		vec = base->tv2.vec + i;
+	} else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
+		int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
+		vec = base->tv3.vec + i;
+	} else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
+		int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
+		vec = base->tv4.vec + i;
+	} else if ((signed long) idx < 0) {
+		/*
+		 * Can happen if you add a timer with expires == jiffies,
+		 * or you set a timer to go off in the past
+		 */
+		vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
+	} else {
+		int i;
+		/* If the timeout is larger than 0xffffffff on 64-bit
+		 * architectures then we use the maximum timeout:
+		 */
+		if (idx > 0xffffffffUL) {
+			idx = 0xffffffffUL;
+			expires = idx + base->timer_jiffies;
+		}
+		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
+		vec = base->tv5.vec + i;
+	}
+	/*
+	 * Timers are FIFO:
+	 */
+	list_add_tail(&timer->entry, vec);
+}
+
+#ifdef CONFIG_TIMER_STATS
+void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
+{
+	if (timer->start_site)
+		return;
+
+	timer->start_site = addr;
+	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
+	timer->start_pid = current->pid;
+}
+
+static void timer_stats_account_timer(struct timer_list *timer)
+{
+	unsigned int flag = 0;
+
+	if (unlikely(tbase_get_deferrable(timer->base)))
+		flag |= TIMER_STATS_FLAG_DEFERRABLE;
+
+	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
+				 timer->function, timer->start_comm, flag);
+}
+
+#else
+static void timer_stats_account_timer(struct timer_list *timer) {}
+#endif
+
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+
+static struct debug_obj_descr timer_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int timer_fixup_init(void *addr, enum debug_obj_state state)
+{
+	struct timer_list *timer = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		del_timer_sync(timer);
+		debug_object_init(timer, &timer_debug_descr);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int timer_fixup_activate(void *addr, enum debug_obj_state state)
+{
+	struct timer_list *timer = addr;
+
+	switch (state) {
+
+	case ODEBUG_STATE_NOTAVAILABLE:
+		/*
+		 * This is not really a fixup. The timer was
+		 * statically initialized. We just make sure that it
+		 * is tracked in the object tracker.
+		 */
+		if (timer->entry.next == NULL &&
+		    timer->entry.prev == TIMER_ENTRY_STATIC) {
+			debug_object_init(timer, &timer_debug_descr);
+			debug_object_activate(timer, &timer_debug_descr);
+			return 0;
+		} else {
+			WARN_ON_ONCE(1);
+		}
+		return 0;
+
+	case ODEBUG_STATE_ACTIVE:
+		WARN_ON(1);
+
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int timer_fixup_free(void *addr, enum debug_obj_state state)
+{
+	struct timer_list *timer = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		del_timer_sync(timer);
+		debug_object_free(timer, &timer_debug_descr);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static struct debug_obj_descr timer_debug_descr = {
+	.name		= "timer_list",
+	.fixup_init	= timer_fixup_init,
+	.fixup_activate	= timer_fixup_activate,
+	.fixup_free	= timer_fixup_free,
+};
+
+static inline void debug_timer_init(struct timer_list *timer)
+{
+	debug_object_init(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_activate(struct timer_list *timer)
+{
+	debug_object_activate(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_deactivate(struct timer_list *timer)
+{
+	debug_object_deactivate(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_free(struct timer_list *timer)
+{
+	debug_object_free(timer, &timer_debug_descr);
+}
+
+static void __init_timer(struct timer_list *timer);
+
+void init_timer_on_stack(struct timer_list *timer)
+{
+	debug_object_init_on_stack(timer, &timer_debug_descr);
+	__init_timer(timer);
+}
+EXPORT_SYMBOL_GPL(init_timer_on_stack);
+
+void destroy_timer_on_stack(struct timer_list *timer)
+{
+	debug_object_free(timer, &timer_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_timer_on_stack);
+
+#else
+static inline void debug_timer_init(struct timer_list *timer) { }
+static inline void debug_timer_activate(struct timer_list *timer) { }
+static inline void debug_timer_deactivate(struct timer_list *timer) { }
+#endif
+
+static void __init_timer(struct timer_list *timer)
+{
+	timer->entry.next = NULL;
+	timer->base = __raw_get_cpu_var(tvec_bases);
+#ifdef CONFIG_TIMER_STATS
+	timer->start_site = NULL;
+	timer->start_pid = -1;
+	memset(timer->start_comm, 0, TASK_COMM_LEN);
+#endif
+}
+
+/**
+ * init_timer - initialize a timer.
+ * @timer: the timer to be initialized
+ *
+ * init_timer() must be done to a timer prior calling *any* of the
+ * other timer functions.
+ */
+void init_timer(struct timer_list *timer)
+{
+	debug_timer_init(timer);
+	__init_timer(timer);
+}
+EXPORT_SYMBOL(init_timer);
+
+void init_timer_deferrable(struct timer_list *timer)
+{
+	init_timer(timer);
+	timer_set_deferrable(timer);
+}
+EXPORT_SYMBOL(init_timer_deferrable);
+
+static inline void detach_timer(struct timer_list *timer,
+				int clear_pending)
+{
+	struct list_head *entry = &timer->entry;
+
+	debug_timer_deactivate(timer);
+
+	__list_del(entry->prev, entry->next);
+	if (clear_pending)
+		entry->next = NULL;
+	entry->prev = LIST_POISON2;
+}
+
+/*
+ * We are using hashed locking: holding per_cpu(tvec_bases).lock
+ * means that all timers which are tied to this base via timer->base are
+ * locked, and the base itself is locked too.
+ *
+ * So __run_timers/migrate_timers can safely modify all timers which could
+ * be found on ->tvX lists.
+ *
+ * When the timer's base is locked, and the timer removed from list, it is
+ * possible to set timer->base = NULL and drop the lock: the timer remains
+ * locked.
+ */
+static struct tvec_base *lock_timer_base(struct timer_list *timer,
+					unsigned long *flags)
+	__acquires(timer->base->lock)
+{
+	struct tvec_base *base;
+
+	for (;;) {
+		struct tvec_base *prelock_base = timer->base;
+		base = tbase_get_base(prelock_base);
+		if (likely(base != NULL)) {
+			spin_lock_irqsave(&base->lock, *flags);
+			if (likely(prelock_base == timer->base))
+				return base;
+			/* The timer has migrated to another CPU */
+			spin_unlock_irqrestore(&base->lock, *flags);
+		}
+		cpu_relax();
+	}
+}
+
+int __mod_timer(struct timer_list *timer, unsigned long expires)
+{
+	struct tvec_base *base, *new_base;
+	unsigned long flags;
+	int ret = 0;
+
+	timer_stats_timer_set_start_info(timer);
+	BUG_ON(!timer->function);
+
+	base = lock_timer_base(timer, &flags);
+
+	if (timer_pending(timer)) {
+		detach_timer(timer, 0);
+		ret = 1;
+	}
+
+	debug_timer_activate(timer);
+
+	new_base = __get_cpu_var(tvec_bases);
+
+	if (base != new_base) {
+		/*
+		 * We are trying to schedule the timer on the local CPU.
+		 * However we can't change timer's base while it is running,
+		 * otherwise del_timer_sync() can't detect that the timer's
+		 * handler yet has not finished. This also guarantees that
+		 * the timer is serialized wrt itself.
+		 */
+		if (likely(base->running_timer != timer)) {
+			/* See the comment in lock_timer_base() */
+			timer_set_base(timer, NULL);
+			spin_unlock(&base->lock);
+			base = new_base;
+			spin_lock(&base->lock);
+			timer_set_base(timer, base);
+		}
+	}
+
+	timer->expires = expires;
+	internal_add_timer(base, timer);
+	spin_unlock_irqrestore(&base->lock, flags);
+
+	return ret;
+}
+
+EXPORT_SYMBOL(__mod_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+	struct tvec_base *base = per_cpu(tvec_bases, cpu);
+	unsigned long flags;
+
+	timer_stats_timer_set_start_info(timer);
+	BUG_ON(timer_pending(timer) || !timer->function);
+	spin_lock_irqsave(&base->lock, flags);
+	timer_set_base(timer, base);
+	debug_timer_activate(timer);
+	internal_add_timer(base, timer);
+	/*
+	 * Check whether the other CPU is idle and needs to be
+	 * triggered to reevaluate the timer wheel when nohz is
+	 * active. We are protected against the other CPU fiddling
+	 * with the timer by holding the timer base lock. This also
+	 * makes sure that a CPU on the way to idle can not evaluate
+	 * the timer wheel.
+	 */
+	wake_up_idle_cpu(cpu);
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
+ * mod_timer - modify a timer's timeout
+ * @timer: the timer to be modified
+ * @expires: new timeout in jiffies
+ *
+ * mod_timer() is a more efficient way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ *
+ * mod_timer(timer, expires) is equivalent to:
+ *
+ *     del_timer(timer); timer->expires = expires; add_timer(timer);
+ *
+ * Note that if there are multiple unserialized concurrent users of the
+ * same timer, then mod_timer() is the only safe way to modify the timeout,
+ * since add_timer() cannot modify an already running timer.
+ *
+ * The function returns whether it has modified a pending timer or not.
+ * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
+ * active timer returns 1.)
+ */
+int mod_timer(struct timer_list *timer, unsigned long expires)
+{
+	BUG_ON(!timer->function);
+
+	timer_stats_timer_set_start_info(timer);
+	/*
+	 * This is a common optimization triggered by the
+	 * networking code - if the timer is re-modified
+	 * to be the same thing then just return:
+	 */
+	if (timer->expires == expires && timer_pending(timer))
+		return 1;
+
+	return __mod_timer(timer, expires);
+}
+
+EXPORT_SYMBOL(mod_timer);
+
+/**
+ * del_timer - deactive a timer.
+ * @timer: the timer to be deactivated
+ *
+ * del_timer() deactivates a timer - this works on both active and inactive
+ * timers.
+ *
+ * The function returns whether it has deactivated a pending timer or not.
+ * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
+ * active timer returns 1.)
+ */
+int del_timer(struct timer_list *timer)
+{
+	struct tvec_base *base;
+	unsigned long flags;
+	int ret = 0;
+
+	timer_stats_timer_clear_start_info(timer);
+	if (timer_pending(timer)) {
+		base = lock_timer_base(timer, &flags);
+		if (timer_pending(timer)) {
+			detach_timer(timer, 1);
+			ret = 1;
+		}
+		spin_unlock_irqrestore(&base->lock, flags);
+	}
+
+	return ret;
+}
+
+EXPORT_SYMBOL(del_timer);
+
+#ifdef CONFIG_SMP
+/**
+ * try_to_del_timer_sync - Try to deactivate a timer
+ * @timer: timer do del
+ *
+ * This function tries to deactivate a timer. Upon successful (ret >= 0)
+ * exit the timer is not queued and the handler is not running on any CPU.
+ *
+ * It must not be called from interrupt contexts.
+ */
+int try_to_del_timer_sync(struct timer_list *timer)
+{
+	struct tvec_base *base;
+	unsigned long flags;
+	int ret = -1;
+
+	base = lock_timer_base(timer, &flags);
+
+	if (base->running_timer == timer)
+		goto out;
+
+	ret = 0;
+	if (timer_pending(timer)) {
+		detach_timer(timer, 1);
+		ret = 1;
+	}
+out:
+	spin_unlock_irqrestore(&base->lock, flags);
+
+	return ret;
+}
+
+EXPORT_SYMBOL(try_to_del_timer_sync);
+
+/**
+ * del_timer_sync - deactivate a timer and wait for the handler to finish.
+ * @timer: the timer to be deactivated
+ *
+ * This function only differs from del_timer() on SMP: besides deactivating
+ * the timer it also makes sure the handler has finished executing on other
+ * CPUs.
+ *
+ * Synchronization rules: Callers must prevent restarting of the timer,
+ * otherwise this function is meaningless. It must not be called from
+ * interrupt contexts. The caller must not hold locks which would prevent
+ * completion of the timer's handler. The timer's handler must not call
+ * add_timer_on(). Upon exit the timer is not queued and the handler is
+ * not running on any CPU.
+ *
+ * The function returns whether it has deactivated a pending timer or not.
+ */
+int del_timer_sync(struct timer_list *timer)
+{
+	for (;;) {
+		int ret = try_to_del_timer_sync(timer);
+		if (ret >= 0)
+			return ret;
+		cpu_relax();
+	}
+}
+
+EXPORT_SYMBOL(del_timer_sync);
+#endif
+
+static int cascade(struct tvec_base *base, struct tvec *tv, int index)
+{
+	/* cascade all the timers from tv up one level */
+	struct timer_list *timer, *tmp;
+	struct list_head tv_list;
+
+	list_replace_init(tv->vec + index, &tv_list);
+
+	/*
+	 * We are removing _all_ timers from the list, so we
+	 * don't have to detach them individually.
+	 */
+	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
+		BUG_ON(tbase_get_base(timer->base) != base);
+		internal_add_timer(base, timer);
+	}
+
+	return index;
+}
+
+#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
+
+/**
+ * __run_timers - run all expired timers (if any) on this CPU.
+ * @base: the timer vector to be processed.
+ *
+ * This function cascades all vectors and executes all expired timer
+ * vectors.
+ */
+static inline void __run_timers(struct tvec_base *base)
+{
+	struct timer_list *timer;
+
+	spin_lock_irq(&base->lock);
+	while (time_after_eq(jiffies, base->timer_jiffies)) {
+		struct list_head work_list;
+		struct list_head *head = &work_list;
+		int index = base->timer_jiffies & TVR_MASK;
+
+		/*
+		 * Cascade timers:
+		 */
+		if (!index &&
+			(!cascade(base, &base->tv2, INDEX(0))) &&
+				(!cascade(base, &base->tv3, INDEX(1))) &&
+					!cascade(base, &base->tv4, INDEX(2)))
+			cascade(base, &base->tv5, INDEX(3));
+		++base->timer_jiffies;
+		list_replace_init(base->tv1.vec + index, &work_list);
+		while (!list_empty(head)) {
+			void (*fn)(unsigned long);
+			unsigned long data;
+
+			timer = list_first_entry(head, struct timer_list,entry);
+			fn = timer->function;
+			data = timer->data;
+
+			timer_stats_account_timer(timer);
+
+			set_running_timer(base, timer);
+			detach_timer(timer, 1);
+			spin_unlock_irq(&base->lock);
+			{
+				int preempt_count = preempt_count();
+				fn(data);
+				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();
+				}
+			}
+			spin_lock_irq(&base->lock);
+		}
+	}
+	set_running_timer(base, NULL);
+	spin_unlock_irq(&base->lock);
+}
+
+#ifdef CONFIG_NO_HZ
+/*
+ * Find out when the next timer event is due to happen. This
+ * is used on S/390 to stop all activity when a cpus is idle.
+ * This functions needs to be called disabled.
+ */
+static unsigned long __next_timer_interrupt(struct tvec_base *base)
+{
+	unsigned long timer_jiffies = base->timer_jiffies;
+	unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
+	int index, slot, array, found = 0;
+	struct timer_list *nte;
+	struct tvec *varray[4];
+
+	/* Look for timer events in tv1. */
+	index = slot = timer_jiffies & TVR_MASK;
+	do {
+		list_for_each_entry(nte, base->tv1.vec + slot, entry) {
+			if (tbase_get_deferrable(nte->base))
+				continue;
+
+			found = 1;
+			expires = nte->expires;
+			/* Look at the cascade bucket(s)? */
+			if (!index || slot < index)
+				goto cascade;
+			return expires;
+		}
+		slot = (slot + 1) & TVR_MASK;
+	} while (slot != index);
+
+cascade:
+	/* Calculate the next cascade event */
+	if (index)
+		timer_jiffies += TVR_SIZE - index;
+	timer_jiffies >>= TVR_BITS;
+
+	/* Check tv2-tv5. */
+	varray[0] = &base->tv2;
+	varray[1] = &base->tv3;
+	varray[2] = &base->tv4;
+	varray[3] = &base->tv5;
+
+	for (array = 0; array < 4; array++) {
+		struct tvec *varp = varray[array];
+
+		index = slot = timer_jiffies & TVN_MASK;
+		do {
+			list_for_each_entry(nte, varp->vec + slot, entry) {
+				found = 1;
+				if (time_before(nte->expires, expires))
+					expires = nte->expires;
+			}
+			/*
+			 * Do we still search for the first timer or are
+			 * we looking up the cascade buckets ?
+			 */
+			if (found) {
+				/* Look at the cascade bucket(s)? */
+				if (!index || slot < index)
+					break;
+				return expires;
+			}
+			slot = (slot + 1) & TVN_MASK;
+		} while (slot != index);
+
+		if (index)
+			timer_jiffies += TVN_SIZE - index;
+		timer_jiffies >>= TVN_BITS;
+	}
+	return expires;
+}
+
+/*
+ * Check, if the next hrtimer event is before the next timer wheel
+ * event:
+ */
+static unsigned long cmp_next_hrtimer_event(unsigned long now,
+					    unsigned long expires)
+{
+	ktime_t hr_delta = hrtimer_get_next_event();
+	struct timespec tsdelta;
+	unsigned long delta;
+
+	if (hr_delta.tv64 == KTIME_MAX)
+		return expires;
+
+	/*
+	 * Expired timer available, let it expire in the next tick
+	 */
+	if (hr_delta.tv64 <= 0)
+		return now + 1;
+
+	tsdelta = ktime_to_timespec(hr_delta);
+	delta = timespec_to_jiffies(&tsdelta);
+
+	/*
+	 * Limit the delta to the max value, which is checked in
+	 * tick_nohz_stop_sched_tick():
+	 */
+	if (delta > NEXT_TIMER_MAX_DELTA)
+		delta = NEXT_TIMER_MAX_DELTA;
+
+	/*
+	 * Take rounding errors in to account and make sure, that it
+	 * expires in the next tick. Otherwise we go into an endless
+	 * ping pong due to tick_nohz_stop_sched_tick() retriggering
+	 * the timer softirq
+	 */
+	if (delta < 1)
+		delta = 1;
+	now += delta;
+	if (time_before(now, expires))
+		return now;
+	return expires;
+}
+
+/**
+ * get_next_timer_interrupt - return the jiffy of the next pending timer
+ * @now: current time (in jiffies)
+ */
+unsigned long get_next_timer_interrupt(unsigned long now)
+{
+	struct tvec_base *base = __get_cpu_var(tvec_bases);
+	unsigned long expires;
+
+	spin_lock(&base->lock);
+	expires = __next_timer_interrupt(base);
+	spin_unlock(&base->lock);
+
+	if (time_before_eq(expires, now))
+		return now;
+
+	return cmp_next_hrtimer_event(now, expires);
+}
+#endif
+
+/*
+ * Called from the timer interrupt handler to charge one tick to the current
+ * process.  user_tick is 1 if the tick is user time, 0 for system.
+ */
+void update_process_times(int user_tick)
+{
+	struct task_struct *p = current;
+	int cpu = smp_processor_id();
+
+	/* Note: this timer irq context must be accounted for as well. */
+	account_process_tick(p, user_tick);
+	run_local_timers();
+	if (rcu_pending(cpu))
+		rcu_check_callbacks(cpu, user_tick);
+	printk_tick();
+	scheduler_tick();
+	run_posix_cpu_timers(p);
+}
+
+/*
+ * Nr of active tasks - counted in fixed-point numbers
+ */
+static unsigned long count_active_tasks(void)
+{
+	return nr_active() * FIXED_1;
+}
+
+/*
+ * Hmm.. Changed this, as the GNU make sources (load.c) seems to
+ * imply that avenrun[] is the standard name for this kind of thing.
+ * Nothing else seems to be standardized: the fractional size etc
+ * all seem to differ on different machines.
+ *
+ * Requires xtime_lock to access.
+ */
+unsigned long avenrun[3];
+
+EXPORT_SYMBOL(avenrun);
+
+/*
+ * calc_load - given tick count, update the avenrun load estimates.
+ * This is called while holding a write_lock on xtime_lock.
+ */
+static inline void calc_load(unsigned long ticks)
+{
+	unsigned long active_tasks; /* fixed-point */
+	static int count = LOAD_FREQ;
+
+	count -= ticks;
+	if (unlikely(count < 0)) {
+		active_tasks = count_active_tasks();
+		do {
+			CALC_LOAD(avenrun[0], EXP_1, active_tasks);
+			CALC_LOAD(avenrun[1], EXP_5, active_tasks);
+			CALC_LOAD(avenrun[2], EXP_15, active_tasks);
+			count += LOAD_FREQ;
+		} while (count < 0);
+	}
+}
+
+/*
+ * This function runs timers and the timer-tq in bottom half context.
+ */
+static void run_timer_softirq(struct softirq_action *h)
+{
+	struct tvec_base *base = __get_cpu_var(tvec_bases);
+
+	hrtimer_run_pending();
+
+	if (time_after_eq(jiffies, base->timer_jiffies))
+		__run_timers(base);
+}
+
+/*
+ * Called by the local, per-CPU timer interrupt on SMP.
+ */
+void run_local_timers(void)
+{
+	hrtimer_run_queues();
+	raise_softirq(TIMER_SOFTIRQ);
+	softlockup_tick();
+}
+
+/*
+ * Called by the timer interrupt. xtime_lock must already be taken
+ * by the timer IRQ!
+ */
+static inline void update_times(unsigned long ticks)
+{
+	update_wall_time();
+	calc_load(ticks);
+}
+
+/*
+ * The 64-bit jiffies value is not atomic - you MUST NOT read it
+ * without sampling the sequence number in xtime_lock.
+ * jiffies is defined in the linker script...
+ */
+
+void do_timer(unsigned long ticks)
+{
+	jiffies_64 += ticks;
+	update_times(ticks);
+}
+
+#ifdef __ARCH_WANT_SYS_ALARM
+
+/*
+ * For backwards compatibility?  This can be done in libc so Alpha
+ * and all newer ports shouldn't need it.
+ */
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
+{
+	return alarm_setitimer(seconds);
+}
+
+#endif
+
+#ifndef __alpha__
+
+/*
+ * The Alpha uses getxpid, getxuid, and getxgid instead.  Maybe this
+ * should be moved into arch/i386 instead?
+ */
+
+/**
+ * sys_getpid - return the thread group id of the current process
+ *
+ * Note, despite the name, this returns the tgid not the pid.  The tgid and
+ * the pid are identical unless CLONE_THREAD was specified on clone() in
+ * which case the tgid is the same in all threads of the same group.
+ *
+ * This is SMP safe as current->tgid does not change.
+ */
+SYSCALL_DEFINE0(getpid)
+{
+	return task_tgid_vnr(current);
+}
+
+/*
+ * Accessing ->real_parent is not SMP-safe, it could
+ * change from under us. However, we can use a stale
+ * value of ->real_parent under rcu_read_lock(), see
+ * release_task()->call_rcu(delayed_put_task_struct).
+ */
+SYSCALL_DEFINE0(getppid)
+{
+	int pid;
+
+	rcu_read_lock();
+	pid = task_tgid_vnr(current->real_parent);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+SYSCALL_DEFINE0(getuid)
+{
+	/* Only we change this so SMP safe */
+	return current_uid();
+}
+
+SYSCALL_DEFINE0(geteuid)
+{
+	/* Only we change this so SMP safe */
+	return current_euid();
+}
+
+SYSCALL_DEFINE0(getgid)
+{
+	/* Only we change this so SMP safe */
+	return current_gid();
+}
+
+SYSCALL_DEFINE0(getegid)
+{
+	/* Only we change this so SMP safe */
+	return  current_egid();
+}
+
+#endif
+
+static void process_timeout(unsigned long __data)
+{
+	wake_up_process((struct task_struct *)__data);
+}
+
+/**
+ * schedule_timeout - sleep until timeout
+ * @timeout: timeout value in jiffies
+ *
+ * Make the current task sleep until @timeout jiffies have
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
+ * pass before the routine returns. The routine will return 0
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task. In this case the remaining time
+ * in jiffies will be returned, or 0 if the timer expired in time
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
+ * the CPU away without a bound on the timeout. In this case the return
+ * value will be %MAX_SCHEDULE_TIMEOUT.
+ *
+ * In all cases the return value is guaranteed to be non-negative.
+ */
+signed long __sched schedule_timeout(signed long timeout)
+{
+	struct timer_list timer;
+	unsigned long expire;
+
+	switch (timeout)
+	{
+	case MAX_SCHEDULE_TIMEOUT:
+		/*
+		 * These two special cases are useful to be comfortable
+		 * in the caller. Nothing more. We could take
+		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
+		 * but I' d like to return a valid offset (>=0) to allow
+		 * the caller to do everything it want with the retval.
+		 */
+		schedule();
+		goto out;
+	default:
+		/*
+		 * Another bit of PARANOID. Note that the retval will be
+		 * 0 since no piece of kernel is supposed to do a check
+		 * for a negative retval of schedule_timeout() (since it
+		 * should never happens anyway). You just have the printk()
+		 * that will tell you if something is gone wrong and where.
+		 */
+		if (timeout < 0) {
+			printk(KERN_ERR "schedule_timeout: wrong timeout "
+				"value %lx\n", timeout);
+			dump_stack();
+			current->state = TASK_RUNNING;
+			goto out;
+		}
+	}
+
+	expire = timeout + jiffies;
+
+	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
+	__mod_timer(&timer, expire);
+	schedule();
+	del_singleshot_timer_sync(&timer);
+
+	/* Remove the timer from the object tracker */
+	destroy_timer_on_stack(&timer);
+
+	timeout = expire - jiffies;
+
+ out:
+	return timeout < 0 ? 0 : timeout;
+}
+EXPORT_SYMBOL(schedule_timeout);
+
+/*
+ * We can use __set_current_state() here because schedule_timeout() calls
+ * schedule() unconditionally.
+ */
+signed long __sched schedule_timeout_interruptible(signed long timeout)
+{
+	__set_current_state(TASK_INTERRUPTIBLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_interruptible);
+
+signed long __sched schedule_timeout_killable(signed long timeout)
+{
+	__set_current_state(TASK_KILLABLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_killable);
+
+signed long __sched schedule_timeout_uninterruptible(signed long timeout)
+{
+	__set_current_state(TASK_UNINTERRUPTIBLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_uninterruptible);
+
+/* Thread ID - the internal kernel "pid" */
+SYSCALL_DEFINE0(gettid)
+{
+	return task_pid_vnr(current);
+}
+
+/**
+ * do_sysinfo - fill in sysinfo struct
+ * @info: pointer to buffer to fill
+ */
+int do_sysinfo(struct sysinfo *info)
+{
+	unsigned long mem_total, sav_total;
+	unsigned int mem_unit, bitcount;
+	unsigned long seq;
+
+	memset(info, 0, sizeof(struct sysinfo));
+
+	do {
+		struct timespec tp;
+		seq = read_seqbegin(&xtime_lock);
+
+		/*
+		 * This is annoying.  The below is the same thing
+		 * posix_get_clock_monotonic() does, but it wants to
+		 * take the lock which we want to cover the loads stuff
+		 * too.
+		 */
+
+		getnstimeofday(&tp);
+		tp.tv_sec += wall_to_monotonic.tv_sec;
+		tp.tv_nsec += wall_to_monotonic.tv_nsec;
+		monotonic_to_bootbased(&tp);
+		if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
+			tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
+			tp.tv_sec++;
+		}
+		info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
+
+		info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
+		info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
+		info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
+
+		info->procs = nr_threads;
+	} while (read_seqretry(&xtime_lock, seq));
+
+	si_meminfo(info);
+	si_swapinfo(info);
+
+	/*
+	 * If the sum of all the available memory (i.e. ram + swap)
+	 * is less than can be stored in a 32 bit unsigned long then
+	 * we can be binary compatible with 2.2.x kernels.  If not,
+	 * well, in that case 2.2.x was broken anyways...
+	 *
+	 *  -Erik Andersen <andersee@debian.org>
+	 */
+
+	mem_total = info->totalram + info->totalswap;
+	if (mem_total < info->totalram || mem_total < info->totalswap)
+		goto out;
+	bitcount = 0;
+	mem_unit = info->mem_unit;
+	while (mem_unit > 1) {
+		bitcount++;
+		mem_unit >>= 1;
+		sav_total = mem_total;
+		mem_total <<= 1;
+		if (mem_total < sav_total)
+			goto out;
+	}
+
+	/*
+	 * If mem_total did not overflow, multiply all memory values by
+	 * info->mem_unit and set it to 1.  This leaves things compatible
+	 * with 2.2.x, and also retains compatibility with earlier 2.4.x
+	 * kernels...
+	 */
+
+	info->mem_unit = 1;
+	info->totalram <<= bitcount;
+	info->freeram <<= bitcount;
+	info->sharedram <<= bitcount;
+	info->bufferram <<= bitcount;
+	info->totalswap <<= bitcount;
+	info->freeswap <<= bitcount;
+	info->totalhigh <<= bitcount;
+	info->freehigh <<= bitcount;
+
+out:
+	return 0;
+}
+
+SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
+{
+	struct sysinfo val;
+
+	do_sysinfo(&val);
+
+	if (copy_to_user(info, &val, sizeof(struct sysinfo)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int __cpuinit init_timers_cpu(int cpu)
+{
+	int j;
+	struct tvec_base *base;
+	static char __cpuinitdata tvec_base_done[NR_CPUS];
+
+	if (!tvec_base_done[cpu]) {
+		static char boot_done;
+
+		if (boot_done) {
+			/*
+			 * The APs use this path later in boot
+			 */
+			base = kmalloc_node(sizeof(*base),
+						GFP_KERNEL | __GFP_ZERO,
+						cpu_to_node(cpu));
+			if (!base)
+				return -ENOMEM;
+
+			/* Make sure that tvec_base is 2 byte aligned */
+			if (tbase_get_deferrable(base)) {
+				WARN_ON(1);
+				kfree(base);
+				return -ENOMEM;
+			}
+			per_cpu(tvec_bases, cpu) = base;
+		} else {
+			/*
+			 * This is for the boot CPU - we use compile-time
+			 * static initialisation because per-cpu memory isn't
+			 * ready yet and because the memory allocators are not
+			 * initialised either.
+			 */
+			boot_done = 1;
+			base = &boot_tvec_bases;
+		}
+		tvec_base_done[cpu] = 1;
+	} else {
+		base = per_cpu(tvec_bases, cpu);
+	}
+
+	spin_lock_init(&base->lock);
+
+	for (j = 0; j < TVN_SIZE; j++) {
+		INIT_LIST_HEAD(base->tv5.vec + j);
+		INIT_LIST_HEAD(base->tv4.vec + j);
+		INIT_LIST_HEAD(base->tv3.vec + j);
+		INIT_LIST_HEAD(base->tv2.vec + j);
+	}
+	for (j = 0; j < TVR_SIZE; j++)
+		INIT_LIST_HEAD(base->tv1.vec + j);
+
+	base->timer_jiffies = jiffies;
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
+{
+	struct timer_list *timer;
+
+	while (!list_empty(head)) {
+		timer = list_first_entry(head, struct timer_list, entry);
+		detach_timer(timer, 0);
+		timer_set_base(timer, new_base);
+		internal_add_timer(new_base, timer);
+	}
+}
+
+static void __cpuinit migrate_timers(int cpu)
+{
+	struct tvec_base *old_base;
+	struct tvec_base *new_base;
+	int i;
+
+	BUG_ON(cpu_online(cpu));
+	old_base = per_cpu(tvec_bases, cpu);
+	new_base = get_cpu_var(tvec_bases);
+	/*
+	 * The caller is globally serialized and nobody else
+	 * takes two locks at once, deadlock is not possible.
+	 */
+	spin_lock_irq(&new_base->lock);
+	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+
+	BUG_ON(old_base->running_timer);
+
+	for (i = 0; i < TVR_SIZE; i++)
+		migrate_timer_list(new_base, old_base->tv1.vec + i);
+	for (i = 0; i < TVN_SIZE; i++) {
+		migrate_timer_list(new_base, old_base->tv2.vec + i);
+		migrate_timer_list(new_base, old_base->tv3.vec + i);
+		migrate_timer_list(new_base, old_base->tv4.vec + i);
+		migrate_timer_list(new_base, old_base->tv5.vec + i);
+	}
+
+	spin_unlock(&old_base->lock);
+	spin_unlock_irq(&new_base->lock);
+	put_cpu_var(tvec_bases);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static int __cpuinit timer_cpu_notify(struct notifier_block *self,
+				unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+	switch(action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		if (init_timers_cpu(cpu) < 0)
+			return NOTIFY_BAD;
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		migrate_timers(cpu);
+		break;
+#endif
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata timers_nb = {
+	.notifier_call	= timer_cpu_notify,
+};
+
+
+void __init init_timers(void)
+{
+	int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
+				(void *)(long)smp_processor_id());
+
+	init_timer_stats();
+
+	BUG_ON(err == NOTIFY_BAD);
+	register_cpu_notifier(&timers_nb);
+	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
+}
+
+/**
+ * msleep - sleep safely even with waitqueue interruptions
+ * @msecs: Time in milliseconds to sleep for
+ */
+void msleep(unsigned int msecs)
+{
+	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+
+	while (timeout)
+		timeout = schedule_timeout_uninterruptible(timeout);
+}
+
+EXPORT_SYMBOL(msleep);
+#endif /* DDE */
+
+/**
+ * msleep_interruptible - sleep waiting for signals
+ * @msecs: Time in milliseconds to sleep for
+ */
+unsigned long msleep_interruptible(unsigned int msecs)
+{
+	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+
+	while (timeout && !signal_pending(current))
+		timeout = schedule_timeout_interruptible(timeout);
+	return jiffies_to_msecs(timeout);
+}
+
+EXPORT_SYMBOL(msleep_interruptible);
diff --git a/libdde-linux26/lib/src/kernel/wait.c b/libdde-linux26/lib/src/kernel/wait.c
new file mode 100644
index 00000000..b10d867f
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/wait.c
@@ -0,0 +1,301 @@
+/*
+ * Generic waiting primitives.
+ *
+ * (C) 2004 William Irwin, Oracle
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/wait.h>
+#include <linux/hash.h>
+
+#ifdef DDE_LINUX
+#include "local.h"
+#endif
+
+void init_waitqueue_head(wait_queue_head_t *q)
+{
+	spin_lock_init(&q->lock);
+	INIT_LIST_HEAD(&q->task_list);
+}
+
+EXPORT_SYMBOL(init_waitqueue_head);
+
+void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(add_wait_queue);
+
+void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	wait->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue_tail(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(add_wait_queue_exclusive);
+
+void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__remove_wait_queue(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(remove_wait_queue);
+
+
+/*
+ * Note: we use "set_current_state()" _after_ the wait-queue add,
+ * because we need a memory barrier there on SMP, so that any
+ * wake-function that tests for the wait-queue being active
+ * will be guaranteed to see waitqueue addition _or_ subsequent
+ * tests in this thread will see the wakeup having taken place.
+ *
+ * The spin_unlock() itself is semi-permeable and only protects
+ * one way (it only protects stuff inside the critical region and
+ * stops them from bleeding out - it would still allow subsequent
+ * loads to move into the critical region).
+ */
+void
+prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list))
+		__add_wait_queue(q, wait);
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(prepare_to_wait);
+
+void
+prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	wait->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list))
+		__add_wait_queue_tail(q, wait);
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(prepare_to_wait_exclusive);
+
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
+void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	/*
+	 * We can check for list emptiness outside the lock
+	 * IFF:
+	 *  - we use the "careful" check that verifies both
+	 *    the next and prev pointers, so that there cannot
+	 *    be any half-pending updates in progress on other
+	 *    CPU's that we haven't seen yet (and that might
+	 *    still change the stack area.
+	 * and
+	 *  - all other users take the lock (ie we can only
+	 *    have _one_ other CPU that looks at or modifies
+	 *    the list).
+	 */
+	if (!list_empty_careful(&wait->task_list)) {
+		spin_lock_irqsave(&q->lock, flags);
+		list_del_init(&wait->task_list);
+		spin_unlock_irqrestore(&q->lock, flags);
+	}
+}
+EXPORT_SYMBOL(finish_wait);
+
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	spin_lock_irqsave(&q->lock, flags);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+	else if (waitqueue_active(q))
+		__wake_up_common(q, mode, 1, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
+int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	int ret = default_wake_function(wait, mode, sync, key);
+
+	if (ret)
+		list_del_init(&wait->task_list);
+	return ret;
+}
+EXPORT_SYMBOL(autoremove_wake_function);
+
+int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue *wait_bit
+		= container_of(wait, struct wait_bit_queue, wait);
+
+	if (wait_bit->key.flags != key->flags ||
+			wait_bit->key.bit_nr != key->bit_nr ||
+			test_bit(key->bit_nr, key->flags))
+		return 0;
+	else
+		return autoremove_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(wake_bit_function);
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking)
+ * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
+ * permitted return codes. Nonzero return codes halt waiting and return.
+ */
+int __sched
+__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
+			int (*action)(void *), unsigned mode)
+{
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq, &q->wait, mode);
+		if (test_bit(q->key.bit_nr, q->key.flags))
+			ret = (*action)(q->key.flags);
+	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
+	finish_wait(wq, &q->wait);
+	return ret;
+}
+EXPORT_SYMBOL(__wait_on_bit);
+
+int __sched out_of_line_wait_on_bit(void *word, int bit,
+					int (*action)(void *), unsigned mode)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	return __wait_on_bit(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit);
+
+int __sched
+__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
+			int (*action)(void *), unsigned mode)
+{
+	do {
+		int ret;
+
+		prepare_to_wait_exclusive(wq, &q->wait, mode);
+		if (!test_bit(q->key.bit_nr, q->key.flags))
+			continue;
+		ret = action(q->key.flags);
+		if (!ret)
+			continue;
+		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+		return ret;
+	} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
+	finish_wait(wq, &q->wait);
+	return 0;
+}
+EXPORT_SYMBOL(__wait_on_bit_lock);
+
+int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
+					int (*action)(void *), unsigned mode)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	return __wait_on_bit_lock(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
+
+void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit)
+{
+#ifndef DDE_LINUX
+	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
+	if (waitqueue_active(wq))
+		__wake_up(wq, TASK_NORMAL, 1, &key);
+#else
+	WARN_UNIMPL;
+#endif
+}
+EXPORT_SYMBOL(__wake_up_bit);
+
+/**
+ * wake_up_bit - wake up a waiter on a bit
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that wakes up waiters
+ * on a bit. For instance, if one were to have waiters on a bitflag,
+ * one would call wake_up_bit() after clearing the bit.
+ *
+ * In order for this to function properly, as it uses waitqueue_active()
+ * internally, some kind of memory barrier must be done prior to calling
+ * this. Typically, this will be smp_mb__after_clear_bit(), but in some
+ * cases where bitflags are manipulated non-atomically under a lock, one
+ * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
+ * because spin_unlock() does not guarantee a memory barrier.
+ */
+void wake_up_bit(void *word, int bit)
+{
+	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
+}
+EXPORT_SYMBOL(wake_up_bit);
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+#ifndef DDE_LINUX
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	const struct zone *zone = page_zone(virt_to_page(word));
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
+#else
+	WARN_UNIMPL;
+	return NULL;
+#endif
+}
+EXPORT_SYMBOL(bit_waitqueue);
diff --git a/libdde-linux26/lib/src/kernel/workqueue.c b/libdde-linux26/lib/src/kernel/workqueue.c
new file mode 100644
index 00000000..5ad26d9f
--- /dev/null
+++ b/libdde-linux26/lib/src/kernel/workqueue.c
@@ -0,0 +1,1038 @@
+/*
+ * linux/kernel/workqueue.c
+ *
+ * Generic mechanism for defining kernel helper threads for running
+ * arbitrary tasks in process context.
+ *
+ * Started by Ingo Molnar, Copyright (C) 2002
+ *
+ * Derived from the taskqueue/keventd code by:
+ *
+ *   David Woodhouse <dwmw2@infradead.org>
+ *   Andrew Morton
+ *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
+ *   Theodore Ts'o <tytso@mit.edu>
+ *
+ * Made to use alloc_percpu by Christoph Lameter.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/signal.h>
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/notifier.h>
+#include <linux/kthread.h>
+#include <linux/hardirq.h>
+#include <linux/mempolicy.h>
+#include <linux/freezer.h>
+#include <linux/kallsyms.h>
+#include <linux/debug_locks.h>
+#include <linux/lockdep.h>
+
+#ifdef DDE_LINUX
+#include "local.h"
+#endif
+
+/*
+ * The per-CPU workqueue (if single thread, we always use the first
+ * possible cpu).
+ */
+struct cpu_workqueue_struct {
+
+	spinlock_t lock;
+
+	struct list_head worklist;
+	wait_queue_head_t more_work;
+	struct work_struct *current_work;
+
+	struct workqueue_struct *wq;
+	struct task_struct *thread;
+
+	int run_depth;		/* Detect run_workqueue() recursion depth */
+} ____cacheline_aligned;
+
+/*
+ * The externally visible workqueue abstraction is an array of
+ * per-CPU workqueues:
+ */
+struct workqueue_struct {
+	struct cpu_workqueue_struct *cpu_wq;
+	struct list_head list;
+	const char *name;
+	int singlethread;
+	int freezeable;		/* Freeze threads during suspend */
+	int rt;
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map lockdep_map;
+#endif
+};
+
+/* Serializes the accesses to the list of workqueues. */
+static DEFINE_SPINLOCK(workqueue_lock);
+static LIST_HEAD(workqueues);
+
+static int singlethread_cpu __read_mostly;
+static const struct cpumask *cpu_singlethread_map __read_mostly;
+/*
+ * _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
+ * flushes cwq->worklist. This means that flush_workqueue/wait_on_work
+ * which comes in between can't use for_each_online_cpu(). We could
+ * use cpu_possible_map, the cpumask below is more a documentation
+ * than optimization.
+ */
+static cpumask_var_t cpu_populated_map __read_mostly;
+
+/* If it's single threaded, it isn't in the list of workqueues. */
+static inline int is_wq_single_threaded(struct workqueue_struct *wq)
+{
+	return wq->singlethread;
+}
+
+static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
+{
+	return is_wq_single_threaded(wq)
+		? cpu_singlethread_map : cpu_populated_map;
+}
+
+static
+struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
+{
+	if (unlikely(is_wq_single_threaded(wq)))
+		cpu = singlethread_cpu;
+	return per_cpu_ptr(wq->cpu_wq, cpu);
+}
+
+/*
+ * Set the workqueue on which a work item is to be run
+ * - Must *only* be called if the pending flag is set
+ */
+static inline void set_wq_data(struct work_struct *work,
+				struct cpu_workqueue_struct *cwq)
+{
+	unsigned long new;
+
+	BUG_ON(!work_pending(work));
+
+	new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING);
+	new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work);
+	atomic_long_set(&work->data, new);
+}
+
+static inline
+struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
+{
+	return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
+}
+
+static void insert_work(struct cpu_workqueue_struct *cwq,
+			struct work_struct *work, struct list_head *head)
+{
+	set_wq_data(work, cwq);
+	/*
+	 * Ensure that we get the right work->data if we see the
+	 * result of list_add() below, see try_to_grab_pending().
+	 */
+	smp_wmb();
+	list_add_tail(&work->entry, head);
+	wake_up(&cwq->more_work);
+}
+
+static void __queue_work(struct cpu_workqueue_struct *cwq,
+			 struct work_struct *work)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cwq->lock, flags);
+	insert_work(cwq, work, &cwq->worklist);
+	spin_unlock_irqrestore(&cwq->lock, flags);
+}
+
+/**
+ * queue_work - queue work on a workqueue
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * Returns 0 if @work was already on a queue, non-zero otherwise.
+ *
+ * We queue the work to the CPU on which it was submitted, but if the CPU dies
+ * it can be processed by another CPU.
+ */
+int queue_work(struct workqueue_struct *wq, struct work_struct *work)
+{
+	int ret;
+
+	ret = queue_work_on(get_cpu(), wq, work);
+	put_cpu();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(queue_work);
+
+/**
+ * queue_work_on - queue work on specific cpu
+ * @cpu: CPU number to execute work on
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * Returns 0 if @work was already on a queue, non-zero otherwise.
+ *
+ * We queue the work to a specific CPU, the caller must ensure it
+ * can't go away.
+ */
+int
+queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
+{
+	int ret = 0;
+
+	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
+		BUG_ON(!list_empty(&work->entry));
+		__queue_work(wq_per_cpu(wq, cpu), work);
+		ret = 1;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(queue_work_on);
+
+static void delayed_work_timer_fn(unsigned long __data)
+{
+	struct delayed_work *dwork = (struct delayed_work *)__data;
+	struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work);
+	struct workqueue_struct *wq = cwq->wq;
+
+	__queue_work(wq_per_cpu(wq, smp_processor_id()), &dwork->work);
+}
+
+/**
+ * queue_delayed_work - queue work on a workqueue after delay
+ * @wq: workqueue to use
+ * @dwork: delayable work to queue
+ * @delay: number of jiffies to wait before queueing
+ *
+ * Returns 0 if @work was already on a queue, non-zero otherwise.
+ */
+int queue_delayed_work(struct workqueue_struct *wq,
+			struct delayed_work *dwork, unsigned long delay)
+{
+	if (delay == 0)
+		return queue_work(wq, &dwork->work);
+
+	return queue_delayed_work_on(-1, wq, dwork, delay);
+}
+EXPORT_SYMBOL_GPL(queue_delayed_work);
+
+/**
+ * queue_delayed_work_on - queue work on specific CPU after delay
+ * @cpu: CPU number to execute work on
+ * @wq: workqueue to use
+ * @dwork: work to queue
+ * @delay: number of jiffies to wait before queueing
+ *
+ * Returns 0 if @work was already on a queue, non-zero otherwise.
+ */
+int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
+			struct delayed_work *dwork, unsigned long delay)
+{
+	int ret = 0;
+	struct timer_list *timer = &dwork->timer;
+	struct work_struct *work = &dwork->work;
+
+	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
+		BUG_ON(timer_pending(timer));
+		BUG_ON(!list_empty(&work->entry));
+
+		timer_stats_timer_set_start_info(&dwork->timer);
+
+		/* This stores cwq for the moment, for the timer_fn */
+		set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id()));
+		timer->expires = jiffies + delay;
+		timer->data = (unsigned long)dwork;
+		timer->function = delayed_work_timer_fn;
+
+		if (unlikely(cpu >= 0))
+			add_timer_on(timer, cpu);
+		else
+			add_timer(timer);
+		ret = 1;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(queue_delayed_work_on);
+
+static void run_workqueue(struct cpu_workqueue_struct *cwq)
+{
+	spin_lock_irq(&cwq->lock);
+	cwq->run_depth++;
+	if (cwq->run_depth > 3) {
+		/* morton gets to eat his hat */
+		printk("%s: recursion depth exceeded: %d\n",
+			__func__, cwq->run_depth);
+		dump_stack();
+	}
+	while (!list_empty(&cwq->worklist)) {
+		struct work_struct *work = list_entry(cwq->worklist.next,
+						struct work_struct, entry);
+		work_func_t f = work->func;
+#ifdef CONFIG_LOCKDEP
+		/*
+		 * It is permissible to free the struct work_struct
+		 * 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 work->lockdep_map,
+		 * make a copy and use that here.
+		 */
+		struct lockdep_map lockdep_map = work->lockdep_map;
+#endif
+
+		cwq->current_work = work;
+		list_del_init(cwq->worklist.next);
+		spin_unlock_irq(&cwq->lock);
+
+		BUG_ON(get_wq_data(work) != cwq);
+		work_clear_pending(work);
+		lock_map_acquire(&cwq->wq->lockdep_map);
+		lock_map_acquire(&lockdep_map);
+		f(work);
+		lock_map_release(&lockdep_map);
+		lock_map_release(&cwq->wq->lockdep_map);
+
+		if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
+			printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
+					"%s/0x%08x/%d\n",
+					current->comm, preempt_count(),
+				       	task_pid_nr(current));
+#ifndef DDE_LINUX
+			printk(KERN_ERR "    last function: ");
+			print_symbol("%s\n", (unsigned long)f);
+			debug_show_held_locks(current);
+			dump_stack();
+#endif /* DDE_LINUX */
+		}
+
+		spin_lock_irq(&cwq->lock);
+		cwq->current_work = NULL;
+	}
+	cwq->run_depth--;
+	spin_unlock_irq(&cwq->lock);
+}
+
+static int worker_thread(void *__cwq)
+{
+	struct cpu_workqueue_struct *cwq = __cwq;
+	DEFINE_WAIT(wait);
+
+	if (cwq->wq->freezeable)
+		set_freezable();
+
+	set_user_nice(current, -5);
+
+	for (;;) {
+		prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
+		if (!freezing(current) &&
+		    !kthread_should_stop() &&
+		    list_empty(&cwq->worklist))
+			schedule();
+		finish_wait(&cwq->more_work, &wait);
+
+		try_to_freeze();
+
+		if (kthread_should_stop())
+			break;
+
+		run_workqueue(cwq);
+	}
+
+	return 0;
+}
+
+struct wq_barrier {
+	struct work_struct	work;
+	struct completion	done;
+};
+
+static void wq_barrier_func(struct work_struct *work)
+{
+	struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
+	complete(&barr->done);
+}
+
+static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
+			struct wq_barrier *barr, struct list_head *head)
+{
+	INIT_WORK(&barr->work, wq_barrier_func);
+	__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
+
+	init_completion(&barr->done);
+
+	insert_work(cwq, &barr->work, head);
+}
+
+static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
+{
+	int active;
+
+	if (cwq->thread == current) {
+		/*
+		 * Probably keventd trying to flush its own queue. So simply run
+		 * it by hand rather than deadlocking.
+		 */
+		run_workqueue(cwq);
+		active = 1;
+	} else {
+		struct wq_barrier barr;
+
+		active = 0;
+		spin_lock_irq(&cwq->lock);
+		if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
+			insert_wq_barrier(cwq, &barr, &cwq->worklist);
+			active = 1;
+		}
+		spin_unlock_irq(&cwq->lock);
+
+		if (active)
+			wait_for_completion(&barr.done);
+	}
+
+	return active;
+}
+
+/**
+ * flush_workqueue - ensure that any scheduled work has run to completion.
+ * @wq: workqueue to flush
+ *
+ * Forces execution of the workqueue and blocks until its completion.
+ * This is typically used in driver shutdown handlers.
+ *
+ * We sleep until all works which were queued on entry have been handled,
+ * but we are not livelocked by new incoming ones.
+ *
+ * This function used to run the workqueues itself.  Now we just wait for the
+ * helper threads to do it.
+ */
+void flush_workqueue(struct workqueue_struct *wq)
+{
+	const struct cpumask *cpu_map = wq_cpu_map(wq);
+	int cpu;
+
+	might_sleep();
+	lock_map_acquire(&wq->lockdep_map);
+	lock_map_release(&wq->lockdep_map);
+	for_each_cpu_mask_nr(cpu, *cpu_map)
+		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
+}
+EXPORT_SYMBOL_GPL(flush_workqueue);
+
+/**
+ * flush_work - block until a work_struct's callback has terminated
+ * @work: the work which is to be flushed
+ *
+ * Returns false if @work has already terminated.
+ *
+ * It is expected that, prior to calling flush_work(), the caller has
+ * arranged for the work to not be requeued, otherwise it doesn't make
+ * sense to use this function.
+ */
+int flush_work(struct work_struct *work)
+{
+	struct cpu_workqueue_struct *cwq;
+	struct list_head *prev;
+	struct wq_barrier barr;
+
+	might_sleep();
+	cwq = get_wq_data(work);
+	if (!cwq)
+		return 0;
+
+	lock_map_acquire(&cwq->wq->lockdep_map);
+	lock_map_release(&cwq->wq->lockdep_map);
+
+	prev = NULL;
+	spin_lock_irq(&cwq->lock);
+	if (!list_empty(&work->entry)) {
+		/*
+		 * See the comment near try_to_grab_pending()->smp_rmb().
+		 * If it was re-queued under us we are not going to wait.
+		 */
+		smp_rmb();
+		if (unlikely(cwq != get_wq_data(work)))
+			goto out;
+		prev = &work->entry;
+	} else {
+		if (cwq->current_work != work)
+			goto out;
+		prev = &cwq->worklist;
+	}
+	insert_wq_barrier(cwq, &barr, prev->next);
+out:
+	spin_unlock_irq(&cwq->lock);
+	if (!prev)
+		return 0;
+
+	wait_for_completion(&barr.done);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(flush_work);
+
+/*
+ * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
+ * so this work can't be re-armed in any way.
+ */
+static int try_to_grab_pending(struct work_struct *work)
+{
+	struct cpu_workqueue_struct *cwq;
+	int ret = -1;
+
+	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work)))
+		return 0;
+
+	/*
+	 * The queueing is in progress, or it is already queued. Try to
+	 * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
+	 */
+
+	cwq = get_wq_data(work);
+	if (!cwq)
+		return ret;
+
+	spin_lock_irq(&cwq->lock);
+	if (!list_empty(&work->entry)) {
+		/*
+		 * This work is queued, but perhaps we locked the wrong cwq.
+		 * In that case we must see the new value after rmb(), see
+		 * insert_work()->wmb().
+		 */
+		smp_rmb();
+		if (cwq == get_wq_data(work)) {
+			list_del_init(&work->entry);
+			ret = 1;
+		}
+	}
+	spin_unlock_irq(&cwq->lock);
+
+	return ret;
+}
+
+static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
+				struct work_struct *work)
+{
+	struct wq_barrier barr;
+	int running = 0;
+
+	spin_lock_irq(&cwq->lock);
+	if (unlikely(cwq->current_work == work)) {
+		insert_wq_barrier(cwq, &barr, cwq->worklist.next);
+		running = 1;
+	}
+	spin_unlock_irq(&cwq->lock);
+
+	if (unlikely(running))
+		wait_for_completion(&barr.done);
+}
+
+static void wait_on_work(struct work_struct *work)
+{
+	struct cpu_workqueue_struct *cwq;
+	struct workqueue_struct *wq;
+	const struct cpumask *cpu_map;
+	int cpu;
+
+	might_sleep();
+
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
+
+	cwq = get_wq_data(work);
+	if (!cwq)
+		return;
+
+	wq = cwq->wq;
+	cpu_map = wq_cpu_map(wq);
+
+	for_each_cpu_mask_nr(cpu, *cpu_map)
+		wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
+}
+
+static int __cancel_work_timer(struct work_struct *work,
+				struct timer_list* timer)
+{
+	int ret;
+
+	do {
+		ret = (timer && likely(del_timer(timer)));
+		if (!ret)
+			ret = try_to_grab_pending(work);
+		wait_on_work(work);
+	} while (unlikely(ret < 0));
+
+	work_clear_pending(work);
+	return ret;
+}
+
+/**
+ * cancel_work_sync - block until a work_struct's callback has terminated
+ * @work: the work which is to be flushed
+ *
+ * Returns true if @work was pending.
+ *
+ * cancel_work_sync() will cancel the work if it is queued. If the work's
+ * callback appears to be running, cancel_work_sync() will block until it
+ * has completed.
+ *
+ * It is possible to use this function if the work re-queues itself. It can
+ * cancel the work even if it migrates to another workqueue, however in that
+ * case it only guarantees that work->func() has completed on the last queued
+ * workqueue.
+ *
+ * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
+ * pending, otherwise it goes into a busy-wait loop until the timer expires.
+ *
+ * The caller must ensure that workqueue_struct on which this work was last
+ * queued can't be destroyed before this function returns.
+ */
+int cancel_work_sync(struct work_struct *work)
+{
+	return __cancel_work_timer(work, NULL);
+}
+EXPORT_SYMBOL_GPL(cancel_work_sync);
+
+/**
+ * cancel_delayed_work_sync - reliably kill off a delayed work.
+ * @dwork: the delayed work struct
+ *
+ * Returns true if @dwork was pending.
+ *
+ * It is possible to use this function if @dwork rearms itself via queue_work()
+ * or queue_delayed_work(). See also the comment for cancel_work_sync().
+ */
+int cancel_delayed_work_sync(struct delayed_work *dwork)
+{
+	return __cancel_work_timer(&dwork->work, &dwork->timer);
+}
+EXPORT_SYMBOL(cancel_delayed_work_sync);
+
+static struct workqueue_struct *keventd_wq __read_mostly;
+
+/**
+ * schedule_work - put work task in global workqueue
+ * @work: job to be done
+ *
+ * This puts a job in the kernel-global workqueue.
+ */
+int schedule_work(struct work_struct *work)
+{
+	return queue_work(keventd_wq, work);
+}
+EXPORT_SYMBOL(schedule_work);
+
+/*
+ * schedule_work_on - put work task on a specific cpu
+ * @cpu: cpu to put the work task on
+ * @work: job to be done
+ *
+ * This puts a job on a specific cpu
+ */
+int schedule_work_on(int cpu, struct work_struct *work)
+{
+	return queue_work_on(cpu, keventd_wq, work);
+}
+EXPORT_SYMBOL(schedule_work_on);
+
+/**
+ * schedule_delayed_work - put work task in global workqueue after delay
+ * @dwork: job to be done
+ * @delay: number of jiffies to wait or 0 for immediate execution
+ *
+ * After waiting for a given time this puts a job in the kernel-global
+ * workqueue.
+ */
+int schedule_delayed_work(struct delayed_work *dwork,
+					unsigned long delay)
+{
+	return queue_delayed_work(keventd_wq, dwork, delay);
+}
+EXPORT_SYMBOL(schedule_delayed_work);
+
+/**
+ * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
+ * @cpu: cpu to use
+ * @dwork: job to be done
+ * @delay: number of jiffies to wait
+ *
+ * After waiting for a given time this puts a job in the kernel-global
+ * workqueue on the specified CPU.
+ */
+int schedule_delayed_work_on(int cpu,
+			struct delayed_work *dwork, unsigned long delay)
+{
+	return queue_delayed_work_on(cpu, keventd_wq, dwork, delay);
+}
+EXPORT_SYMBOL(schedule_delayed_work_on);
+
+/**
+ * schedule_on_each_cpu - call a function on each online CPU from keventd
+ * @func: the function to call
+ *
+ * Returns zero on success.
+ * Returns -ve errno on failure.
+ *
+ * schedule_on_each_cpu() is very slow.
+ */
+int schedule_on_each_cpu(work_func_t func)
+{
+	int cpu;
+	struct work_struct *works;
+
+	works = alloc_percpu(struct work_struct);
+	if (!works)
+		return -ENOMEM;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		struct work_struct *work = per_cpu_ptr(works, cpu);
+
+		INIT_WORK(work, func);
+		schedule_work_on(cpu, work);
+	}
+	for_each_online_cpu(cpu)
+		flush_work(per_cpu_ptr(works, cpu));
+	put_online_cpus();
+	free_percpu(works);
+	return 0;
+}
+
+void flush_scheduled_work(void)
+{
+	flush_workqueue(keventd_wq);
+}
+EXPORT_SYMBOL(flush_scheduled_work);
+
+/**
+ * execute_in_process_context - reliably execute the routine with user context
+ * @fn:		the function to execute
+ * @ew:		guaranteed storage for the execute work structure (must
+ *		be available when the work executes)
+ *
+ * Executes the function immediately if process context is available,
+ * otherwise schedules the function for delayed execution.
+ *
+ * Returns:	0 - function was executed
+ *		1 - function was scheduled for execution
+ */
+int execute_in_process_context(work_func_t fn, struct execute_work *ew)
+{
+	if (!in_interrupt()) {
+		fn(&ew->work);
+		return 0;
+	}
+
+	INIT_WORK(&ew->work, fn);
+	schedule_work(&ew->work);
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(execute_in_process_context);
+
+int keventd_up(void)
+{
+	return keventd_wq != NULL;
+}
+
+int current_is_keventd(void)
+{
+	struct cpu_workqueue_struct *cwq;
+	int cpu = raw_smp_processor_id(); /* preempt-safe: keventd is per-cpu */
+	int ret = 0;
+
+	BUG_ON(!keventd_wq);
+
+	cwq = per_cpu_ptr(keventd_wq->cpu_wq, cpu);
+	if (current == cwq->thread)
+		ret = 1;
+
+	return ret;
+
+}
+
+static struct cpu_workqueue_struct *
+init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
+{
+	struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
+
+	cwq->wq = wq;
+	spin_lock_init(&cwq->lock);
+	INIT_LIST_HEAD(&cwq->worklist);
+	init_waitqueue_head(&cwq->more_work);
+
+	return cwq;
+}
+
+static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+	struct workqueue_struct *wq = cwq->wq;
+	const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
+	struct task_struct *p;
+
+	p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);
+	/*
+	 * Nobody can add the work_struct to this cwq,
+	 *	if (caller is __create_workqueue)
+	 *		nobody should see this wq
+	 *	else // caller is CPU_UP_PREPARE
+	 *		cpu is not on cpu_online_map
+	 * so we can abort safely.
+	 */
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+	if (cwq->wq->rt)
+		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
+	cwq->thread = p;
+
+	return 0;
+}
+
+static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
+{
+	struct task_struct *p = cwq->thread;
+
+	if (p != NULL) {
+		if (cpu >= 0)
+			kthread_bind(p, cpu);
+		wake_up_process(p);
+	}
+}
+
+struct workqueue_struct *__create_workqueue_key(const char *name,
+						int singlethread,
+						int freezeable,
+						int rt,
+						struct lock_class_key *key,
+						const char *lock_name)
+{
+	struct workqueue_struct *wq;
+	struct cpu_workqueue_struct *cwq;
+	int err = 0, cpu;
+
+	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
+	if (!wq)
+		return NULL;
+
+	wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct);
+	if (!wq->cpu_wq) {
+		kfree(wq);
+		return NULL;
+	}
+
+	wq->name = name;
+	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
+	wq->singlethread = singlethread;
+	wq->freezeable = freezeable;
+	wq->rt = rt;
+	INIT_LIST_HEAD(&wq->list);
+
+	if (singlethread) {
+		cwq = init_cpu_workqueue(wq, singlethread_cpu);
+		err = create_workqueue_thread(cwq, singlethread_cpu);
+		start_workqueue_thread(cwq, -1);
+	} else {
+		cpu_maps_update_begin();
+		/*
+		 * We must place this wq on list even if the code below fails.
+		 * cpu_down(cpu) can remove cpu from cpu_populated_map before
+		 * destroy_workqueue() takes the lock, in that case we leak
+		 * cwq[cpu]->thread.
+		 */
+		spin_lock(&workqueue_lock);
+		list_add(&wq->list, &workqueues);
+		spin_unlock(&workqueue_lock);
+		/*
+		 * We must initialize cwqs for each possible cpu even if we
+		 * are going to call destroy_workqueue() finally. Otherwise
+		 * cpu_up() can hit the uninitialized cwq once we drop the
+		 * lock.
+		 */
+		for_each_possible_cpu(cpu) {
+			cwq = init_cpu_workqueue(wq, cpu);
+			if (err || !cpu_online(cpu))
+				continue;
+			err = create_workqueue_thread(cwq, cpu);
+			start_workqueue_thread(cwq, cpu);
+		}
+		cpu_maps_update_done();
+	}
+
+	if (err) {
+		destroy_workqueue(wq);
+		wq = NULL;
+	}
+	return wq;
+}
+EXPORT_SYMBOL_GPL(__create_workqueue_key);
+
+static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
+{
+	/*
+	 * Our caller is either destroy_workqueue() or CPU_POST_DEAD,
+	 * cpu_add_remove_lock protects cwq->thread.
+	 */
+	if (cwq->thread == NULL)
+		return;
+
+	lock_map_acquire(&cwq->wq->lockdep_map);
+	lock_map_release(&cwq->wq->lockdep_map);
+
+	flush_cpu_workqueue(cwq);
+	/*
+	 * If the caller is CPU_POST_DEAD and cwq->worklist was not empty,
+	 * a concurrent flush_workqueue() can insert a barrier after us.
+	 * However, in that case run_workqueue() won't return and check
+	 * kthread_should_stop() until it flushes all work_struct's.
+	 * When ->worklist becomes empty it is safe to exit because no
+	 * more work_structs can be queued on this cwq: flush_workqueue
+	 * checks list_empty(), and a "normal" queue_work() can't use
+	 * a dead CPU.
+	 */
+	kthread_stop(cwq->thread);
+	cwq->thread = NULL;
+}
+
+/**
+ * destroy_workqueue - safely terminate a workqueue
+ * @wq: target workqueue
+ *
+ * Safely destroy a workqueue. All work currently pending will be done first.
+ */
+void destroy_workqueue(struct workqueue_struct *wq)
+{
+	const struct cpumask *cpu_map = wq_cpu_map(wq);
+	int cpu;
+
+	cpu_maps_update_begin();
+	spin_lock(&workqueue_lock);
+	list_del(&wq->list);
+	spin_unlock(&workqueue_lock);
+
+	for_each_cpu_mask_nr(cpu, *cpu_map)
+		cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
+ 	cpu_maps_update_done();
+
+	free_percpu(wq->cpu_wq);
+	kfree(wq);
+}
+EXPORT_SYMBOL_GPL(destroy_workqueue);
+
+static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
+						unsigned long action,
+						void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	struct cpu_workqueue_struct *cwq;
+	struct workqueue_struct *wq;
+	int ret = NOTIFY_OK;
+
+	action &= ~CPU_TASKS_FROZEN;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+		cpumask_set_cpu(cpu, cpu_populated_map);
+	}
+undo:
+	list_for_each_entry(wq, &workqueues, list) {
+		cwq = per_cpu_ptr(wq->cpu_wq, cpu);
+
+		switch (action) {
+		case CPU_UP_PREPARE:
+			if (!create_workqueue_thread(cwq, cpu))
+				break;
+			printk(KERN_ERR "workqueue [%s] for %i failed\n",
+				wq->name, cpu);
+			action = CPU_UP_CANCELED;
+			ret = NOTIFY_BAD;
+			goto undo;
+
+		case CPU_ONLINE:
+			start_workqueue_thread(cwq, cpu);
+			break;
+
+		case CPU_UP_CANCELED:
+			start_workqueue_thread(cwq, -1);
+		case CPU_POST_DEAD:
+			cleanup_workqueue_thread(cwq);
+			break;
+		}
+	}
+
+	switch (action) {
+	case CPU_UP_CANCELED:
+	case CPU_POST_DEAD:
+		cpumask_clear_cpu(cpu, cpu_populated_map);
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_SMP
+static struct workqueue_struct *work_on_cpu_wq __read_mostly;
+
+struct work_for_cpu {
+	struct work_struct work;
+	long (*fn)(void *);
+	void *arg;
+	long ret;
+};
+
+static void do_work_for_cpu(struct work_struct *w)
+{
+	struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
+
+	wfc->ret = wfc->fn(wfc->arg);
+}
+
+/**
+ * work_on_cpu - run a function in user context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn: the function to run
+ * @arg: the function arg
+ *
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
+ */
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+	struct work_for_cpu wfc;
+
+	INIT_WORK(&wfc.work, do_work_for_cpu);
+	wfc.fn = fn;
+	wfc.arg = arg;
+	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
+	flush_work(&wfc.work);
+
+	return wfc.ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu);
+#endif /* CONFIG_SMP */
+
+void __init init_workqueues(void)
+{
+	alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);
+
+	cpumask_copy(cpu_populated_map, cpu_online_mask);
+	singlethread_cpu = cpumask_first(cpu_possible_mask);
+	cpu_singlethread_map = cpumask_of(singlethread_cpu);
+	hotcpu_notifier(workqueue_cpu_callback, 0);
+	keventd_wq = create_workqueue("events");
+	BUG_ON(!keventd_wq);
+#ifdef CONFIG_SMP
+	work_on_cpu_wq = create_workqueue("work_on_cpu");
+	BUG_ON(!work_on_cpu_wq);
+#endif
+}
+
+#ifdef DDE_LINUX
+core_initcall(init_workqueues);
+#endif