aboutsummaryrefslogblamecommitdiffstats
path: root/kernel/audit.c
blob: ef35166fdc29b459e0beb24505df6766972b261b (plain) (tree)
1
                              






































                                                                              
                                                                       






                         

                          





















                                                                      
                          







                                                                        
 



                                                              











                                                                       
                                                                       

                                                                      

                                            

                                 



                                             







                                                                       
                                                                   


















                                                                        
                                                                         
                                                                        

  





                                                                




                               





































































                                                                         
                                                                                           
                                                






                                            
                                                          


                                            
                                             
                                                                
                                                         


                   
                                                             


                                               
                                            
                                                                   
                                                            


                   
                                                       




                                         
                                            
                                                             
                                                      


                   
                                                       






                                         
                                            
                                                             
                                                      


                   































                                                                                                           











                                                                      
                       
 
                                                             


                                           



                                                                     




















                                                                  
                               


                                                            
                        
                                                        















                                                                       
                                    
                                                           
                                                                  
                                         




                                                                  








                                                                                          

                                       
                                            










                                                                    
                                                                           







                                                                           
                                                                               


                                                              
                                                                               




                                                          
                                                            
                                                                 
                                                            

                                                               
                                                                               
                                                                  

                                                                          
                      
                        
                                                        



                                                                 
                                                             
                                                  
                                                                   

                                       






                                                               
                                                                                
                                                                     
                      





                                                                              










                                                                        
                                                  







                                                                               
                               








                                                          





                                                      
                          
 
                                 
 



                                                                         



                               









                                                                         

                                                       

                                      
                                                     

                 















                                                                              



                                                      


                       

                                   
 







                                                            

                                                                          


                                       
                             










                                                            
                                                    
                        
                                 
         
 
                                                    
                     

                         
                      




                                                                  
                  


                              
 
 








































                                                                            





                                                                        
                                                                         

                                               
                                  
                                       



                               











                                                                       
                                                       




                                                                   
                                              
 




                                                              
   
                                                




                                                                  
                                                                  
 
                                      
                                                                 


                                                                
                         

                                 
 








                                                                        
                            
                      



                       



                                  
                                                       

                                 
         
                             
                                                     



                                                                      
                                                                                     

                                 
                                                              
         

                                  

               














                                                                    



                                                                         
 















                                                                            
 






                                                                        

 



                                                                             

                                                                           
                                        

                    
                                                          







                                                                  
                                                           


                                                                     
                       
 

                                                    
 




                                                                     
         






                                                                         

 



                                                                        
                                           
 




                                                      








                                                                                
         
                              

 


                                                                    
                                                                         



                                
                                        






                                                 
/* audit.c -- Auditing support
 * Gateway between the kernel (e.g., selinux) and the user-space audit daemon.
 * System-call specific features have moved to auditsc.c
 *
 * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * Written by Rickard E. (Rik) Faith <faith@redhat.com>
 *
 * Goals: 1) Integrate fully with SELinux.
 *	  2) Minimal run-time overhead:
 *	     a) Minimal when syscall auditing is disabled (audit_enable=0).
 *	     b) Small when syscall auditing is enabled and no audit record
 *		is generated (defer as much work as possible to record
 *		generation time):
 *		i) context is allocated,
 *		ii) names from getname are stored without a copy, and
 *		iii) inode information stored from path_lookup.
 *	  3) Ability to disable syscall auditing at boot time (audit=0).
 *	  4) Usable by other parts of the kernel (if audit_log* is called,
 *	     then a syscall record will be generated automatically for the
 *	     current syscall).
 *	  5) Netlink interface to user-space.
 *	  6) Support low-overhead kernel-based filtering to minimize the
 *	     information that must be passed to user-space.
 *
 * Example user-space utilities: http://people.redhat.com/sgrubb/audit/
 */

#include <linux/init.h>
#include <asm/atomic.h>
#include <asm/types.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/kthread.h>

#include <linux/audit.h>

#include <net/sock.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>

/* No auditing will take place until audit_initialized != 0.
 * (Initialization happens after skb_init is called.) */
static int	audit_initialized;

/* No syscall auditing will take place unless audit_enabled != 0. */
int		audit_enabled;

/* Default state when kernel boots without any parameters. */
static int	audit_default;

/* If auditing cannot proceed, audit_failure selects what happens. */
static int	audit_failure = AUDIT_FAIL_PRINTK;

/* If audit records are to be written to the netlink socket, audit_pid
 * contains the (non-zero) pid. */
int		audit_pid;

/* If audit_limit is non-zero, limit the rate of sending audit records
 * to that number per second.  This prevents DoS attacks, but results in
 * audit records being dropped. */
static int	audit_rate_limit;

/* Number of outstanding audit_buffers allowed. */
static int	audit_backlog_limit = 64;

/* The identity of the user shutting down the audit system. */
uid_t		audit_sig_uid = -1;
pid_t		audit_sig_pid = -1;

/* Records can be lost in several ways:
   0) [suppressed in audit_alloc]
   1) out of memory in audit_log_start [kmalloc of struct audit_buffer]
   2) out of memory in audit_log_move [alloc_skb]
   3) suppressed due to audit_rate_limit
   4) suppressed due to audit_backlog_limit
*/
static atomic_t    audit_lost = ATOMIC_INIT(0);

/* The netlink socket. */
static struct sock *audit_sock;

/* The audit_freelist is a list of pre-allocated audit buffers (if more
 * than AUDIT_MAXFREE are in use, the audit buffer is freed instead of
 * being placed on the freelist). */
static DEFINE_SPINLOCK(audit_freelist_lock);
static int	   audit_freelist_count = 0;
static LIST_HEAD(audit_freelist);

static struct sk_buff_head audit_skb_queue;
static struct task_struct *kauditd_task;
static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);

/* There are three lists of rules -- one to search at task creation
 * time, one to search at syscall entry time, and another to search at
 * syscall exit time. */
static LIST_HEAD(audit_tsklist);
static LIST_HEAD(audit_entlist);
static LIST_HEAD(audit_extlist);

/* The netlink socket is only to be read by 1 CPU, which lets us assume
 * that list additions and deletions never happen simultaneously in
 * auditsc.c */
static DECLARE_MUTEX(audit_netlink_sem);

/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
 * audit records.  Since printk uses a 1024 byte buffer, this buffer
 * should be at least that large. */
#define AUDIT_BUFSIZ 1024

/* AUDIT_MAXFREE is the number of empty audit_buffers we keep on the
 * audit_freelist.  Doing so eliminates many kmalloc/kfree calls. */
#define AUDIT_MAXFREE  (2*NR_CPUS)

/* The audit_buffer is used when formatting an audit record.  The caller
 * locks briefly to get the record off the freelist or to allocate the
 * buffer, and locks briefly to send the buffer to the netlink layer or
 * to place it on a transmit queue.  Multiple audit_buffers can be in
 * use simultaneously. */
struct audit_buffer {
	struct list_head     list;
	struct sk_buff       *skb;	/* formatted skb ready to send */
	struct audit_context *ctx;	/* NULL or associated context */
};

static void audit_set_pid(struct audit_buffer *ab, pid_t pid)
{
	struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data;
	nlh->nlmsg_pid = pid;
}

struct audit_entry {
	struct list_head  list;
	struct audit_rule rule;
};

static void audit_panic(const char *message)
{
	switch (audit_failure)
	{
	case AUDIT_FAIL_SILENT:
		break;
	case AUDIT_FAIL_PRINTK:
		printk(KERN_ERR "audit: %s\n", message);
		break;
	case AUDIT_FAIL_PANIC:
		panic("audit: %s\n", message);
		break;
	}
}

static inline int audit_rate_check(void)
{
	static unsigned long	last_check = 0;
	static int		messages   = 0;
	static DEFINE_SPINLOCK(lock);
	unsigned long		flags;
	unsigned long		now;
	unsigned long		elapsed;
	int			retval	   = 0;

	if (!audit_rate_limit) return 1;

	spin_lock_irqsave(&lock, flags);
	if (++messages < audit_rate_limit) {
		retval = 1;
	} else {
		now     = jiffies;
		elapsed = now - last_check;
		if (elapsed > HZ) {
			last_check = now;
			messages   = 0;
			retval     = 1;
		}
	}
	spin_unlock_irqrestore(&lock, flags);

	return retval;
}

/* Emit at least 1 message per second, even if audit_rate_check is
 * throttling. */
void audit_log_lost(const char *message)
{
	static unsigned long	last_msg = 0;
	static DEFINE_SPINLOCK(lock);
	unsigned long		flags;
	unsigned long		now;
	int			print;

	atomic_inc(&audit_lost);

	print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit);

	if (!print) {
		spin_lock_irqsave(&lock, flags);
		now = jiffies;
		if (now - last_msg > HZ) {
			print = 1;
			last_msg = now;
		}
		spin_unlock_irqrestore(&lock, flags);
	}

	if (print) {
		printk(KERN_WARNING
		       "audit: audit_lost=%d audit_rate_limit=%d audit_backlog_limit=%d\n",
		       atomic_read(&audit_lost),
		       audit_rate_limit,
		       audit_backlog_limit);
		audit_panic(message);
	}

}

static int audit_set_rate_limit(int limit, uid_t loginuid)
{
	int old		 = audit_rate_limit;
	audit_rate_limit = limit;
	audit_log(NULL, AUDIT_CONFIG_CHANGE, 
			"audit_rate_limit=%d old=%d by auid=%u",
			audit_rate_limit, old, loginuid);
	return old;
}

static int audit_set_backlog_limit(int limit, uid_t loginuid)
{
	int old		 = audit_backlog_limit;
	audit_backlog_limit = limit;
	audit_log(NULL, AUDIT_CONFIG_CHANGE,
			"audit_backlog_limit=%d old=%d by auid=%u",
			audit_backlog_limit, old, loginuid);
	return old;
}

static int audit_set_enabled(int state, uid_t loginuid)
{
	int old		 = audit_enabled;
	if (state != 0 && state != 1)
		return -EINVAL;
	audit_enabled = state;
	audit_log(NULL, AUDIT_CONFIG_CHANGE,
			"audit_enabled=%d old=%d by auid=%u",
			audit_enabled, old, loginuid);
	return old;
}

static int audit_set_failure(int state, uid_t loginuid)
{
	int old		 = audit_failure;
	if (state != AUDIT_FAIL_SILENT
	    && state != AUDIT_FAIL_PRINTK
	    && state != AUDIT_FAIL_PANIC)
		return -EINVAL;
	audit_failure = state;
	audit_log(NULL, AUDIT_CONFIG_CHANGE,
			"audit_failure=%d old=%d by auid=%u",
			audit_failure, old, loginuid);
	return old;
}

int kauditd_thread(void *dummy)
{
	struct sk_buff *skb;

	while (1) {
		skb = skb_dequeue(&audit_skb_queue);
		if (skb) {
			if (audit_pid) {
				int err = netlink_unicast(audit_sock, skb, audit_pid, 0);
				if (err < 0) {
					BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */
					printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
					audit_pid = 0;
				}
			} else {
				printk(KERN_ERR "%s\n", skb->data + NLMSG_SPACE(0));
				kfree_skb(skb);
			}
		} else {
			DECLARE_WAITQUEUE(wait, current);
			set_current_state(TASK_INTERRUPTIBLE);
			add_wait_queue(&kauditd_wait, &wait);

			if (!skb_queue_len(&audit_skb_queue))
				schedule();

			__set_current_state(TASK_RUNNING);
			remove_wait_queue(&kauditd_wait, &wait);
		}
	}
}

void audit_send_reply(int pid, int seq, int type, int done, int multi,
		      void *payload, int size)
{
	struct sk_buff	*skb;
	struct nlmsghdr	*nlh;
	int		len = NLMSG_SPACE(size);
	void		*data;
	int		flags = multi ? NLM_F_MULTI : 0;
	int		t     = done  ? NLMSG_DONE  : type;

	skb = alloc_skb(len, GFP_KERNEL);
	if (!skb)
		return;

	nlh		 = NLMSG_PUT(skb, pid, seq, t, size);
	nlh->nlmsg_flags = flags;
	data		 = NLMSG_DATA(nlh);
	memcpy(data, payload, size);

	/* Ignore failure. It'll only happen if the sender goes away,
	   because our timeout is set to infinite. */
	netlink_unicast(audit_sock, skb, pid, 0);
	return;

nlmsg_failure:			/* Used by NLMSG_PUT */
	if (skb)
		kfree_skb(skb);
}

/*
 * Check for appropriate CAP_AUDIT_ capabilities on incoming audit
 * control messages.
 */
static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type)
{
	int err = 0;

	switch (msg_type) {
	case AUDIT_GET:
	case AUDIT_LIST:
	case AUDIT_SET:
	case AUDIT_ADD:
	case AUDIT_DEL:
	case AUDIT_SIGNAL_INFO:
		if (!cap_raised(eff_cap, CAP_AUDIT_CONTROL))
			err = -EPERM;
		break;
	case AUDIT_USER:
	case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG:
		if (!cap_raised(eff_cap, CAP_AUDIT_WRITE))
			err = -EPERM;
		break;
	default:  /* bad msg */
		err = -EINVAL;
	}

	return err;
}

static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	u32			uid, pid, seq;
	void			*data;
	struct audit_status	*status_get, status_set;
	int			err;
	struct audit_buffer	*ab;
	u16			msg_type = nlh->nlmsg_type;
	uid_t			loginuid; /* loginuid of sender */
	struct audit_sig_info   sig_data;

	err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type);
	if (err)
		return err;

	/* As soon as there's any sign of userspace auditd, start kauditd to talk to it */
	if (!kauditd_task)
		kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd");
	if (IS_ERR(kauditd_task)) {
		err = PTR_ERR(kauditd_task);
		kauditd_task = NULL;
		return err;
	}

	pid  = NETLINK_CREDS(skb)->pid;
	uid  = NETLINK_CREDS(skb)->uid;
	loginuid = NETLINK_CB(skb).loginuid;
	seq  = nlh->nlmsg_seq;
	data = NLMSG_DATA(nlh);

	switch (msg_type) {
	case AUDIT_GET:
		status_set.enabled	 = audit_enabled;
		status_set.failure	 = audit_failure;
		status_set.pid		 = audit_pid;
		status_set.rate_limit	 = audit_rate_limit;
		status_set.backlog_limit = audit_backlog_limit;
		status_set.lost		 = atomic_read(&audit_lost);
		status_set.backlog	 = skb_queue_len(&audit_skb_queue);
		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_GET, 0, 0,
				 &status_set, sizeof(status_set));
		break;
	case AUDIT_SET:
		if (nlh->nlmsg_len < sizeof(struct audit_status))
			return -EINVAL;
		status_get   = (struct audit_status *)data;
		if (status_get->mask & AUDIT_STATUS_ENABLED) {
			err = audit_set_enabled(status_get->enabled, loginuid);
			if (err < 0) return err;
		}
		if (status_get->mask & AUDIT_STATUS_FAILURE) {
			err = audit_set_failure(status_get->failure, loginuid);
			if (err < 0) return err;
		}
		if (status_get->mask & AUDIT_STATUS_PID) {
			int old   = audit_pid;
			audit_pid = status_get->pid;
			audit_log(NULL, AUDIT_CONFIG_CHANGE,
				"audit_pid=%d old=%d by auid=%u",
				  audit_pid, old, loginuid);
		}
		if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
			audit_set_rate_limit(status_get->rate_limit, loginuid);
		if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
			audit_set_backlog_limit(status_get->backlog_limit,
							loginuid);
		break;
	case AUDIT_USER:
	case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG:
		ab = audit_log_start(NULL, msg_type);
		if (!ab)
			break;	/* audit_panic has been called */
		audit_log_format(ab,
				 "user pid=%d uid=%u auid=%u"
				 " msg='%.1024s'",
				 pid, uid, loginuid, (char *)data);
		audit_set_pid(ab, pid);
		audit_log_end(ab);
		break;
	case AUDIT_ADD:
	case AUDIT_DEL:
		if (nlh->nlmsg_len < sizeof(struct audit_rule))
			return -EINVAL;
		/* fallthrough */
	case AUDIT_LIST:
		err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
					   uid, seq, data, loginuid);
		break;
	case AUDIT_SIGNAL_INFO:
		sig_data.uid = audit_sig_uid;
		sig_data.pid = audit_sig_pid;
		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO, 
				0, 0, &sig_data, sizeof(sig_data));
		break;
	default:
		err = -EINVAL;
		break;
	}

	return err < 0 ? err : 0;
}

/* Get message from skb (based on rtnetlink_rcv_skb).  Each message is
 * processed by audit_receive_msg.  Malformed skbs with wrong length are
 * discarded silently.  */
static void audit_receive_skb(struct sk_buff *skb)
{
	int		err;
	struct nlmsghdr	*nlh;
	u32		rlen;

	while (skb->len >= NLMSG_SPACE(0)) {
		nlh = (struct nlmsghdr *)skb->data;
		if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
			return;
		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
		if (rlen > skb->len)
			rlen = skb->len;
		if ((err = audit_receive_msg(skb, nlh))) {
			netlink_ack(skb, nlh, err);
		} else if (nlh->nlmsg_flags & NLM_F_ACK)
			netlink_ack(skb, nlh, 0);
		skb_pull(skb, rlen);
	}
}

/* Receive messages from netlink socket. */
static void audit_receive(struct sock *sk, int length)
{
	struct sk_buff  *skb;
	unsigned int qlen;

	down(&audit_netlink_sem);

	for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) {
		skb = skb_dequeue(&sk->sk_receive_queue);
		audit_receive_skb(skb);
		kfree_skb(skb);
	}
	up(&audit_netlink_sem);
}


/* Initialize audit support at boot time. */
static int __init audit_init(void)
{
	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
	       audit_default ? "enabled" : "disabled");
	audit_sock = netlink_kernel_create(NETLINK_AUDIT, audit_receive);
	if (!audit_sock)
		audit_panic("cannot initialize netlink socket");

	audit_sock->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
	skb_queue_head_init(&audit_skb_queue);
	audit_initialized = 1;
	audit_enabled = audit_default;
	audit_log(NULL, AUDIT_KERNEL, "initialized");
	return 0;
}
__initcall(audit_init);

/* Process kernel command-line parameter at boot time.  audit=0 or audit=1. */
static int __init audit_enable(char *str)
{
	audit_default = !!simple_strtol(str, NULL, 0);
	printk(KERN_INFO "audit: %s%s\n",
	       audit_default ? "enabled" : "disabled",
	       audit_initialized ? "" : " (after initialization)");
	if (audit_initialized)
		audit_enabled = audit_default;
	return 0;
}

__setup("audit=", audit_enable);

static void audit_buffer_free(struct audit_buffer *ab)
{
	unsigned long flags;

	if (!ab)
		return;

	if (ab->skb)
		kfree_skb(ab->skb);

	spin_lock_irqsave(&audit_freelist_lock, flags);
	if (++audit_freelist_count > AUDIT_MAXFREE)
		kfree(ab);
	else
		list_add(&ab->list, &audit_freelist);
	spin_unlock_irqrestore(&audit_freelist_lock, flags);
}

static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
						int gfp_mask, int type)
{
	unsigned long flags;
	struct audit_buffer *ab = NULL;
	struct nlmsghdr *nlh;

	spin_lock_irqsave(&audit_freelist_lock, flags);
	if (!list_empty(&audit_freelist)) {
		ab = list_entry(audit_freelist.next,
				struct audit_buffer, list);
		list_del(&ab->list);
		--audit_freelist_count;
	}
	spin_unlock_irqrestore(&audit_freelist_lock, flags);

	if (!ab) {
		ab = kmalloc(sizeof(*ab), gfp_mask);
		if (!ab)
			goto err;
	}

	ab->skb = alloc_skb(AUDIT_BUFSIZ, gfp_mask);
	if (!ab->skb)
		goto err;

	ab->ctx = ctx;
	nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0));
	nlh->nlmsg_type = type;
	nlh->nlmsg_flags = 0;
	nlh->nlmsg_pid = 0;
	nlh->nlmsg_seq = 0;
	return ab;
err:
	audit_buffer_free(ab);
	return NULL;
}

/* Compute a serial number for the audit record.  Audit records are
 * written to user-space as soon as they are generated, so a complete
 * audit record may be written in several pieces.  The timestamp of the
 * record and this serial number are used by the user-space tools to
 * determine which pieces belong to the same audit record.  The
 * (timestamp,serial) tuple is unique for each syscall and is live from
 * syscall entry to syscall exit.
 *
 * Atomic values are only guaranteed to be 24-bit, so we count down.
 *
 * NOTE: Another possibility is to store the formatted records off the
 * audit context (for those records that have a context), and emit them
 * all at syscall exit.  However, this could delay the reporting of
 * significant errors until syscall exit (or never, if the system
 * halts). */
unsigned int audit_serial(void)
{
	static atomic_t serial = ATOMIC_INIT(0xffffff);
	unsigned int a, b;

	do {
		a = atomic_read(&serial);
		if (atomic_dec_and_test(&serial))
			atomic_set(&serial, 0xffffff);
		b = atomic_read(&serial);
	} while (b != a - 1);

	return 0xffffff - b;
}

static inline void audit_get_stamp(struct audit_context *ctx, 
				   struct timespec *t, unsigned int *serial)
{
	if (ctx)
		auditsc_get_stamp(ctx, t, serial);
	else {
		*t = CURRENT_TIME;
		*serial = audit_serial();
	}
}

/* Obtain an audit buffer.  This routine does locking to obtain the
 * audit buffer, but then no locking is required for calls to
 * audit_log_*format.  If the tsk is a task that is currently in a
 * syscall, then the syscall is marked as auditable and an audit record
 * will be written at syscall exit.  If there is no associated task, tsk
 * should be NULL. */
struct audit_buffer *audit_log_start(struct audit_context *ctx, int type)
{
	struct audit_buffer	*ab	= NULL;
	struct timespec		t;
	unsigned int		serial;

	if (!audit_initialized)
		return NULL;

	if (audit_backlog_limit
	    && skb_queue_len(&audit_skb_queue) > audit_backlog_limit) {
		if (audit_rate_check())
			printk(KERN_WARNING
			       "audit: audit_backlog=%d > "
			       "audit_backlog_limit=%d\n",
			       skb_queue_len(&audit_skb_queue),
			       audit_backlog_limit);
		audit_log_lost("backlog limit exceeded");
		return NULL;
	}

	ab = audit_buffer_alloc(ctx, GFP_ATOMIC, type);
	if (!ab) {
		audit_log_lost("out of memory in audit_log_start");
		return NULL;
	}

	audit_get_stamp(ab->ctx, &t, &serial);

	audit_log_format(ab, "audit(%lu.%03lu:%u): ",
			 t.tv_sec, t.tv_nsec/1000000, serial);
	return ab;
}

/**
 * audit_expand - expand skb in the audit buffer
 * @ab: audit_buffer
 *
 * Returns 0 (no space) on failed expansion, or available space if
 * successful.
 */
static inline int audit_expand(struct audit_buffer *ab, int extra)
{
	struct sk_buff *skb = ab->skb;
	int ret = pskb_expand_head(skb, skb_headroom(skb), extra,
				   GFP_ATOMIC);
	if (ret < 0) {
		audit_log_lost("out of memory in audit_expand");
		return 0;
	}
	return skb_tailroom(skb);
}

/* Format an audit message into the audit buffer.  If there isn't enough
 * room in the audit buffer, more room will be allocated and vsnprint
 * will be called a second time.  Currently, we assume that a printk
 * can't format message larger than 1024 bytes, so we don't either. */
static void audit_log_vformat(struct audit_buffer *ab, const char *fmt,
			      va_list args)
{
	int len, avail;
	struct sk_buff *skb;
	va_list args2;

	if (!ab)
		return;

	BUG_ON(!ab->skb);
	skb = ab->skb;
	avail = skb_tailroom(skb);
	if (avail == 0) {
		avail = audit_expand(ab, AUDIT_BUFSIZ);
		if (!avail)
			goto out;
	}
	va_copy(args2, args);
	len = vsnprintf(skb->tail, avail, fmt, args);
	if (len >= avail) {
		/* The printk buffer is 1024 bytes long, so if we get
		 * here and AUDIT_BUFSIZ is at least 1024, then we can
		 * log everything that printk could have logged. */
		avail = audit_expand(ab, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail));
		if (!avail)
			goto out;
		len = vsnprintf(skb->tail, avail, fmt, args2);
	}
	if (len > 0)
		skb_put(skb, len);
out:
	return;
}

/* Format a message into the audit buffer.  All the work is done in
 * audit_log_vformat. */
void audit_log_format(struct audit_buffer *ab, const char *fmt, ...)
{
	va_list args;

	if (!ab)
		return;
	va_start(args, fmt);
	audit_log_vformat(ab, fmt, args);
	va_end(args);
}

/* This function will take the passed buf and convert it into a string of
 * ascii hex digits. The new string is placed onto the skb. */
void audit_log_hex(struct audit_buffer *ab, const unsigned char *buf, 
		size_t len)
{
	int i, avail, new_len;
	unsigned char *ptr;
	struct sk_buff *skb;
	static const unsigned char *hex = "0123456789ABCDEF";

	BUG_ON(!ab->skb);
	skb = ab->skb;
	avail = skb_tailroom(skb);
	new_len = len<<1;
	if (new_len >= avail) {
		/* Round the buffer request up to the next multiple */
		new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1);
		avail = audit_expand(ab, new_len);
		if (!avail)
			return;
	}

	ptr = skb->tail;
	for (i=0; i<len; i++) {
		*ptr++ = hex[(buf[i] & 0xF0)>>4]; /* Upper nibble */
		*ptr++ = hex[buf[i] & 0x0F];	  /* Lower nibble */
	}
	*ptr = 0;
	skb_put(skb, len << 1); /* new string is twice the old string */
}

/* This code will escape a string that is passed to it if the string
 * contains a control character, unprintable character, double quote mark, 
 * or a space. Unescaped strings will start and end with a double quote mark.
 * Strings that are escaped are printed in hex (2 digits per char). */
void audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
{
	const unsigned char *p = string;

	while (*p) {
		if (*p == '"' || *p < 0x21 || *p > 0x7f) {
			audit_log_hex(ab, string, strlen(string));
			return;
		}
		p++;
	}
	audit_log_format(ab, "\"%s\"", string);
}

/* This is a helper-function to print the escaped d_path */
void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
		      struct dentry *dentry, struct vfsmount *vfsmnt)
{
	char *p, *path;

	if (prefix)
		audit_log_format(ab, " %s", prefix);

	/* We will allow 11 spaces for ' (deleted)' to be appended */
	path = kmalloc(PATH_MAX+11, GFP_KERNEL);
	if (!path) {
		audit_log_format(ab, "<no memory>");
		return;
	}
	p = d_path(dentry, vfsmnt, path, PATH_MAX+11);
	if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */
		/* FIXME: can we save some information here? */
		audit_log_format(ab, "<too long>");
	} else 
		audit_log_untrustedstring(ab, p);
	kfree(path);
}

/* The netlink_* functions cannot be called inside an irq context, so
 * the audit buffer is places on a queue and a tasklet is scheduled to
 * remove them from the queue outside the irq context.  May be called in
 * any context. */
void audit_log_end(struct audit_buffer *ab)
{
	if (!ab)
		return;
	if (!audit_rate_check()) {
		audit_log_lost("rate limit exceeded");
	} else {
		if (audit_pid) {
			struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data;
			nlh->nlmsg_len = ab->skb->len - NLMSG_SPACE(0);
			skb_queue_tail(&audit_skb_queue, ab->skb);
			ab->skb = NULL;
			wake_up_interruptible(&kauditd_wait);
		} else {
			printk("%s\n", ab->skb->data + NLMSG_SPACE(0));
		}
	}
	audit_buffer_free(ab);
}

/* Log an audit record.  This is a convenience function that calls
 * audit_log_start, audit_log_vformat, and audit_log_end.  It may be
 * called in any context. */
void audit_log(struct audit_context *ctx, int type, const char *fmt, ...)
{
	struct audit_buffer *ab;
	va_list args;

	ab = audit_log_start(ctx, type);
	if (ab) {
		va_start(args, fmt);
		audit_log_vformat(ab, fmt, args);
		va_end(args);
		audit_log_end(ab);
	}
}
2' href='#n2192'>2192 2193 2194 2195 2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265







































































































































































                                                                          
                                             






































                                                                          
                                  




















































                                                                     

                                                                             
                                                             



                                                              
                                      
                                                                                





                                                            
                           




























































                                                                              
      

                                       
































                                                                             
                            



























                                                                            
                                  

















                                                                                   
                                                                                             
                                                                        

                                                                          

                                                                                               
                                 




















































                                                                              































































































































































































                                                                                
                                                              

























































                                                                               
                                 





















                                                                            
                                           












































































                                                                               

                              
 


                     




















                                                                      

































































                                                                        
                                                          


                                                                   

                                
 
                                                   




                                                            
                                                          


                                                                   

                                
 
                                                   

 







































































                                                                               














                                                                            
 




































                                                               




















                                                              
                                                                 




                                                   

                              































                                                                   
                                                 

















                                          

                      


                                              







                                                            

                 
 
                                                            

                                 
          
                                                                       
           


                                            
 

                                                                     

                                                       
 

                                                                    

                                                      
                          


                                                                              
                           
























                                                                                  



































































                                                                               



                                                                
                                                    
 






                                                       








                                                                        


                                                         


                                                              
                     
                                                            






















                                                                           
                                 


                           















                                                                        
                                         
                                      
                          
 






























































































                                                                                

















                                                                      


                                                    



                                                                           





                                                                       
                                                                   

                            
















                                                                             

                                     












                                                                 





                                                                           




















































































































































                                                                              































                                                                               

                                                                             


                     
                                          
                                                                
                  

                                                     





























                                                                           
                                                                           






                                                                    

                                                  



                                


                                   
                                    


                                                    
                                                         


                                                     
                         











                                                                             
                                                           


                                        
                                        

                    
                             

                         

                   





































                                                                              
                                                                           



























                                                                         


                                     













                                                                              
                     

                                                          





                                           













                                                                      
                                                                
                            
                                                                












                                                                            



                                                 







































































                                                                                   


                       














                                                                          
                                         










                                            





                                                                        










                                                                         
                                     
                               















                                                                   
                                   












                                                                          

                                                                    
                                            



                                                                            
         
 






                                                                               




                                                             
                                                   

                                                    
                                           





                                                                           
                                                                       
                 
              

                                          
                                      

                                                                         








                                                                             








                                             
                                  
                                            

                                                                         






















                                                                          
                                                          
                                  


                                            
                       
                                                          
                                  

         

                                   




                                                               
                                                                         

                                                         

                                          

                                    
                        




                                                   






























                                                                               
                              






                                              

          


                                                       
           
                                        
 



















                                                                                   



















                                                                       
              
 
                                                           













                                                                               






















































































































































































































































































                                                                               
                                             


                              




                                                   







































                                                                       
                                             




                              




                                                   












































































                                                                              
                                      



































                                                                          
                               

































                                                                              
                                                                            
                                                 
                                                                     












































































                                                                           
                                                                     





                                                                               







                                                                           






















                                                
                                              

                                                      





                                                                              






































































































                                                                                 
                                  



































                                                                               
                                                  





















                                                                            
                                                           





































































































































































































































































































                                                                                        












                                                                      


















                                                                     

                                








                                                              


                                                      






























                                                         
                             




































                                                                       
                                                         






























                                                                                    

                                                                     



                                                                     




                                                            

                                                                 











                                                                        















































































































































































































































































































































                                                                                         






                                                             



























                                                                               

                    


                                   
                        





                                            
                        
                                
         
                   










































                                                                            
                                                                          









                                              
                                                                          





























































































































































































                                                                                      







                                                                  













                                                 


                                                              














































































































































                                                                            
                                























                                                                    


                                                              


































                                                                           
                                               

































































































































































































                                                                               





























                                                                          
                         




                                                                




                                                                               

















































































                                                                                                          
                                                 





















                                                    
                                                        


























                                                                            



                                                                    
                                                        
 
                                     












                                                                             


                                    
                                       






























                                                                            
                                                         


































                                                                 


                                                                 



                                                        
                                    






                                                         
                                     











                                                          
                                     





























                                                                                

                                                                           
   
                                                         

              

          
                                                            
           
                                        



                                                                     
                                                       




                                               
                                    
















                                                       
                                                       








                                                                
                                                                       











                                                                           
                                                       








                                                                    
                                                            



                                                                 
                                        






















                                                                              
                                        








                                               





                                                                            
 













                                                                            


                                                             


                                  





































                                                                          



                                                                          
                                                                     




                                                                           


                              
                                                        














                                                                 
                                                 







                                
                                                 




























                                                                    
                                   




                                                 
                              

                                            




















































































                                                                              
/*
 *  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
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <asm/uaccess.h>
#include <linux/highmem.h>
#include <linux/smp_lock.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/suspend.h>
#include <linux/blkdev.h>
#include <linux/delay.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/seq_file.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/acct.h>
#include <asm/tlb.h>

#include <asm/unistd.h>

/*
 * 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))

/*
 * Some helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)	((TIME) / (1000000000 / HZ))
#define JIFFIES_TO_NS(TIME)	((TIME) * (1000000000 / HZ))

/*
 * These are the 'tuning knobs' of the scheduler:
 *
 * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
 * default timeslice is 100 msecs, maximum timeslice is 800 msecs.
 * Timeslices get refilled after they expire.
 */
#define MIN_TIMESLICE		max(5 * HZ / 1000, 1)
#define DEF_TIMESLICE		(100 * HZ / 1000)
#define ON_RUNQUEUE_WEIGHT	 30
#define CHILD_PENALTY		 95
#define PARENT_PENALTY		100
#define EXIT_WEIGHT		  3
#define PRIO_BONUS_RATIO	 25
#define MAX_BONUS		(MAX_USER_PRIO * PRIO_BONUS_RATIO / 100)
#define INTERACTIVE_DELTA	  2
#define MAX_SLEEP_AVG		(DEF_TIMESLICE * MAX_BONUS)
#define STARVATION_LIMIT	(MAX_SLEEP_AVG)
#define NS_MAX_SLEEP_AVG	(JIFFIES_TO_NS(MAX_SLEEP_AVG))

/*
 * If a task is 'interactive' then we reinsert it in the active
 * array after it has expired its current timeslice. (it will not
 * continue to run immediately, it will still roundrobin with
 * other interactive tasks.)
 *
 * This part scales the interactivity limit depending on niceness.
 *
 * We scale it linearly, offset by the INTERACTIVE_DELTA delta.
 * Here are a few examples of different nice levels:
 *
 *  TASK_INTERACTIVE(-20): [1,1,1,1,1,1,1,1,1,0,0]
 *  TASK_INTERACTIVE(-10): [1,1,1,1,1,1,1,0,0,0,0]
 *  TASK_INTERACTIVE(  0): [1,1,1,1,0,0,0,0,0,0,0]
 *  TASK_INTERACTIVE( 10): [1,1,0,0,0,0,0,0,0,0,0]
 *  TASK_INTERACTIVE( 19): [0,0,0,0,0,0,0,0,0,0,0]
 *
 * (the X axis represents the possible -5 ... 0 ... +5 dynamic
 *  priority range a task can explore, a value of '1' means the
 *  task is rated interactive.)
 *
 * Ie. nice +19 tasks can never get 'interactive' enough to be
 * reinserted into the active array. And only heavily CPU-hog nice -20
 * tasks will be expired. Default nice 0 tasks are somewhere between,
 * it takes some effort for them to get interactive, but it's not
 * too hard.
 */

#define CURRENT_BONUS(p) \
	(NS_TO_JIFFIES((p)->sleep_avg) * MAX_BONUS / \
		MAX_SLEEP_AVG)

#define GRANULARITY	(10 * HZ / 1000 ? : 1)

#ifdef CONFIG_SMP
#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \
			num_online_cpus())
#else
#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)))
#endif

#define SCALE(v1,v1_max,v2_max) \
	(v1) * (v2_max) / (v1_max)

#define DELTA(p) \
	(SCALE(TASK_NICE(p), 40, MAX_BONUS) + INTERACTIVE_DELTA)

#define TASK_INTERACTIVE(p) \
	((p)->prio <= (p)->static_prio - DELTA(p))

#define INTERACTIVE_SLEEP(p) \
	(JIFFIES_TO_NS(MAX_SLEEP_AVG * \
		(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))

#define TASK_PREEMPTS_CURR(p, rq) \
	((p)->prio < (rq)->curr->prio)

/*
 * task_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
 * to time slice values: [800ms ... 100ms ... 5ms]
 *
 * The higher a thread's priority, the bigger timeslices
 * it gets during one round of execution. But even the lowest
 * priority thread gets MIN_TIMESLICE worth of execution time.
 */

#define SCALE_PRIO(x, prio) \
	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE)

static unsigned int task_timeslice(task_t *p)
{
	if (p->static_prio < NICE_TO_PRIO(0))
		return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
	else
		return SCALE_PRIO(DEF_TIMESLICE, p->static_prio);
}
#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)	\
				< (long long) (sd)->cache_hot_time)

/*
 * These are the runqueue data structures:
 */

#define BITMAP_SIZE ((((MAX_PRIO+1+7)/8)+sizeof(long)-1)/sizeof(long))

typedef struct runqueue runqueue_t;

struct prio_array {
	unsigned int nr_active;
	unsigned long bitmap[BITMAP_SIZE];
	struct list_head queue[MAX_PRIO];
};

/*
 * 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 runqueue {
	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;
#ifdef CONFIG_SMP
	unsigned long cpu_load[3];
#endif
	unsigned long long nr_switches;

	/*
	 * 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;

	unsigned long expired_timestamp;
	unsigned long long timestamp_last_tick;
	task_t *curr, *idle;
	struct mm_struct *prev_mm;
	prio_array_t *active, *expired, arrays[2];
	int best_expired_prio;
	atomic_t nr_iowait;

#ifdef CONFIG_SMP
	struct sched_domain *sd;

	/* For active balancing */
	int active_balance;
	int push_cpu;

	task_t *migration_thread;
	struct list_head migration_queue;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* latency stats */
	struct sched_info rq_sched_info;

	/* sys_sched_yield() stats */
	unsigned long yld_exp_empty;
	unsigned long yld_act_empty;
	unsigned long yld_both_empty;
	unsigned long yld_cnt;

	/* schedule() stats */
	unsigned long sched_switch;
	unsigned long sched_cnt;
	unsigned long sched_goidle;

	/* try_to_wake_up() stats */
	unsigned long ttwu_cnt;
	unsigned long ttwu_local;
#endif
};

static DEFINE_PER_CPU(struct runqueue, runqueues);

/*
 * 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, domain) \
for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->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)

#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

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(runqueue_t *rq, task_t *p)
{
	return rq->curr == p;
}

static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
{
}

static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
{
	spin_unlock_irq(&rq->lock);
}

#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline int task_running(runqueue_t *rq, task_t *p)
{
#ifdef CONFIG_SMP
	return p->oncpu;
#else
	return rq->curr == p;
#endif
}

static inline void prepare_lock_switch(runqueue_t *rq, task_t *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(runqueue_t *rq, task_t *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 and disable
 * interrupts.  Note the ordering: we can safely lookup the task_rq without
 * explicitly disabling preemption.
 */
static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags)
	__acquires(rq->lock)
{
	struct runqueue *rq;

repeat_lock_task:
	local_irq_save(*flags);
	rq = task_rq(p);
	spin_lock(&rq->lock);
	if (unlikely(rq != task_rq(p))) {
		spin_unlock_irqrestore(&rq->lock, *flags);
		goto repeat_lock_task;
	}
	return rq;
}

static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags)
	__releases(rq->lock)
{
	spin_unlock_irqrestore(&rq->lock, *flags);
}

#ifdef CONFIG_SCHEDSTATS
/*
 * bump this up when changing the output format or the meaning of an existing
 * format, so that tools can adapt (or abort)
 */
#define SCHEDSTAT_VERSION 12

static int show_schedstat(struct seq_file *seq, void *v)
{
	int cpu;

	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
	seq_printf(seq, "timestamp %lu\n", jiffies);
	for_each_online_cpu(cpu) {
		runqueue_t *rq = cpu_rq(cpu);
#ifdef CONFIG_SMP
		struct sched_domain *sd;
		int dcnt = 0;
#endif

		/* runqueue-specific stats */
		seq_printf(seq,
		    "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu",
		    cpu, rq->yld_both_empty,
		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_cnt,
		    rq->sched_switch, rq->sched_cnt, rq->sched_goidle,
		    rq->ttwu_cnt, rq->ttwu_local,
		    rq->rq_sched_info.cpu_time,
		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt);

		seq_printf(seq, "\n");

#ifdef CONFIG_SMP
		/* domain-specific stats */
		preempt_disable();
		for_each_domain(cpu, sd) {
			enum idle_type itype;
			char mask_str[NR_CPUS];

			cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
			seq_printf(seq, "domain%d %s", dcnt++, mask_str);
			for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
					itype++) {
				seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu",
				    sd->lb_cnt[itype],
				    sd->lb_balanced[itype],
				    sd->lb_failed[itype],
				    sd->lb_imbalance[itype],
				    sd->lb_gained[itype],
				    sd->lb_hot_gained[itype],
				    sd->lb_nobusyq[itype],
				    sd->lb_nobusyg[itype]);
			}
			seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
			    sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
			    sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
			    sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
			    sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
		}
		preempt_enable();
#endif
	}
	return 0;
}

static int schedstat_open(struct inode *inode, struct file *file)
{
	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
	char *buf = kmalloc(size, GFP_KERNEL);
	struct seq_file *m;
	int res;

	if (!buf)
		return -ENOMEM;
	res = single_open(file, show_schedstat, NULL);
	if (!res) {
		m = file->private_data;
		m->buf = buf;
		m->size = size;
	} else
		kfree(buf);
	return res;
}

struct file_operations proc_schedstat_operations = {
	.open    = schedstat_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = single_release,
};

# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
#else /* !CONFIG_SCHEDSTATS */
# define schedstat_inc(rq, field)	do { } while (0)
# define schedstat_add(rq, field, amt)	do { } while (0)
#endif

/*
 * rq_lock - lock a given runqueue and disable interrupts.
 */
static inline runqueue_t *this_rq_lock(void)
	__acquires(rq->lock)
{
	runqueue_t *rq;

	local_irq_disable();
	rq = this_rq();
	spin_lock(&rq->lock);

	return rq;
}

#ifdef CONFIG_SCHEDSTATS
/*
 * Called when a process is dequeued from the active array and given
 * the cpu.  We should note that with the exception of interactive
 * tasks, the expired queue will become the active queue after the active
 * queue is empty, without explicitly dequeuing and requeuing tasks in the
 * expired queue.  (Interactive tasks may be requeued directly to the
 * active queue, thus delaying tasks in the expired queue from running;
 * see scheduler_tick()).
 *
 * This function is only called from sched_info_arrive(), rather than
 * dequeue_task(). Even though a task may be queued and dequeued multiple
 * times as it is shuffled about, we're really interested in knowing how
 * long it was from the *first* time it was queued to the time that it
 * finally hit a cpu.
 */
static inline void sched_info_dequeued(task_t *t)
{
	t->sched_info.last_queued = 0;
}

/*
 * Called when a task finally hits the cpu.  We can now calculate how
 * long it was waiting to run.  We also note when it began so that we
 * can keep stats on how long its timeslice is.
 */
static inline void sched_info_arrive(task_t *t)
{
	unsigned long now = jiffies, diff = 0;
	struct runqueue *rq = task_rq(t);

	if (t->sched_info.last_queued)
		diff = now - t->sched_info.last_queued;
	sched_info_dequeued(t);
	t->sched_info.run_delay += diff;
	t->sched_info.last_arrival = now;
	t->sched_info.pcnt++;

	if (!rq)
		return;

	rq->rq_sched_info.run_delay += diff;
	rq->rq_sched_info.pcnt++;
}

/*
 * Called when a process is queued into either the active or expired
 * array.  The time is noted and later used to determine how long we
 * had to wait for us to reach the cpu.  Since the expired queue will
 * become the active queue after active queue is empty, without dequeuing
 * and requeuing any tasks, we are interested in queuing to either. It
 * is unusual but not impossible for tasks to be dequeued and immediately
 * requeued in the same or another array: this can happen in sched_yield(),
 * set_user_nice(), and even load_balance() as it moves tasks from runqueue
 * to runqueue.
 *
 * This function is only called from enqueue_task(), but also only updates
 * the timestamp if it is already not set.  It's assumed that
 * sched_info_dequeued() will clear that stamp when appropriate.
 */
static inline void sched_info_queued(task_t *t)
{
	if (!t->sched_info.last_queued)
		t->sched_info.last_queued = jiffies;
}

/*
 * Called when a process ceases being the active-running process, either
 * voluntarily or involuntarily.  Now we can calculate how long we ran.
 */
static inline void sched_info_depart(task_t *t)
{
	struct runqueue *rq = task_rq(t);
	unsigned long diff = jiffies - t->sched_info.last_arrival;

	t->sched_info.cpu_time += diff;

	if (rq)
		rq->rq_sched_info.cpu_time += diff;
}

/*
 * Called when tasks are switched involuntarily due, typically, to expiring
 * their time slice.  (This may also be called when switching to or from
 * the idle task.)  We are only called when prev != next.
 */
static inline void sched_info_switch(task_t *prev, task_t *next)
{
	struct runqueue *rq = task_rq(prev);

	/*
	 * prev now departs the cpu.  It's not interesting to record
	 * stats about how efficient we were at scheduling the idle
	 * process, however.
	 */
	if (prev != rq->idle)
		sched_info_depart(prev);

	if (next != rq->idle)
		sched_info_arrive(next);
}
#else
#define sched_info_queued(t)		do { } while (0)
#define sched_info_switch(t, next)	do { } while (0)
#endif /* CONFIG_SCHEDSTATS */

/*
 * Adding/removing a task to/from a priority array:
 */
static void dequeue_task(struct task_struct *p, prio_array_t *array)
{
	array->nr_active--;
	list_del(&p->run_list);
	if (list_empty(array->queue + p->prio))
		__clear_bit(p->prio, array->bitmap);
}

static void enqueue_task(struct task_struct *p, prio_array_t *array)
{
	sched_info_queued(p);
	list_add_tail(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	array->nr_active++;
	p->array = array;
}

/*
 * Put task to the end of the run list without the overhead of dequeue
 * followed by enqueue.
 */
static void requeue_task(struct task_struct *p, prio_array_t *array)
{
	list_move_tail(&p->run_list, array->queue + p->prio);
}

static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array)
{
	list_add(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	array->nr_active++;
	p->array = array;
}

/*
 * effective_prio - return the priority that is based on the static
 * priority but is modified by bonuses/penalties.
 *
 * We scale the actual sleep average [0 .... MAX_SLEEP_AVG]
 * into the -5 ... 0 ... +5 bonus/penalty range.
 *
 * We use 25% of the full 0...39 priority range so that:
 *
 * 1) nice +19 interactive tasks do not preempt nice 0 CPU hogs.
 * 2) nice -20 CPU hogs do not get preempted by nice 0 tasks.
 *
 * Both properties are important to certain workloads.
 */
static int effective_prio(task_t *p)
{
	int bonus, prio;

	if (rt_task(p))
		return p->prio;

	bonus = CURRENT_BONUS(p) - MAX_BONUS / 2;

	prio = p->static_prio - bonus;
	if (prio < MAX_RT_PRIO)
		prio = MAX_RT_PRIO;
	if (prio > MAX_PRIO-1)
		prio = MAX_PRIO-1;
	return prio;
}

/*
 * __activate_task - move a task to the runqueue.
 */
static inline void __activate_task(task_t *p, runqueue_t *rq)
{
	enqueue_task(p, rq->active);
	rq->nr_running++;
}

/*
 * __activate_idle_task - move idle task to the _front_ of runqueue.
 */
static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
{
	enqueue_task_head(p, rq->active);
	rq->nr_running++;
}

static int recalc_task_prio(task_t *p, unsigned long long now)
{
	/* Caller must always ensure 'now >= p->timestamp' */
	unsigned long long __sleep_time = now - p->timestamp;
	unsigned long sleep_time;

	if (__sleep_time > NS_MAX_SLEEP_AVG)
		sleep_time = NS_MAX_SLEEP_AVG;
	else
		sleep_time = (unsigned long)__sleep_time;

	if (likely(sleep_time > 0)) {
		/*
		 * User tasks that sleep a long time are categorised as
		 * idle and will get just interactive status to stay active &
		 * prevent them suddenly becoming cpu hogs and starving
		 * other processes.
		 */
		if (p->mm && p->activated != -1 &&
			sleep_time > INTERACTIVE_SLEEP(p)) {
				p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG -
						DEF_TIMESLICE);
		} else {
			/*
			 * The lower the sleep avg a task has the more
			 * rapidly it will rise with sleep time.
			 */
			sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1;

			/*
			 * Tasks waking from uninterruptible sleep are
			 * limited in their sleep_avg rise as they
			 * are likely to be waiting on I/O
			 */
			if (p->activated == -1 && p->mm) {
				if (p->sleep_avg >= INTERACTIVE_SLEEP(p))
					sleep_time = 0;
				else if (p->sleep_avg + sleep_time >=
						INTERACTIVE_SLEEP(p)) {
					p->sleep_avg = INTERACTIVE_SLEEP(p);
					sleep_time = 0;
				}
			}

			/*
			 * This code gives a bonus to interactive tasks.
			 *
			 * The boost works by updating the 'average sleep time'
			 * value here, based on ->timestamp. The more time a
			 * task spends sleeping, the higher the average gets -
			 * and the higher the priority boost gets as well.
			 */
			p->sleep_avg += sleep_time;

			if (p->sleep_avg > NS_MAX_SLEEP_AVG)
				p->sleep_avg = NS_MAX_SLEEP_AVG;
		}
	}

	return effective_prio(p);
}

/*
 * activate_task - move a task to the runqueue and do priority recalculation
 *
 * Update all the scheduling statistics stuff. (sleep average
 * calculation, priority modifiers, etc.)
 */
static void activate_task(task_t *p, runqueue_t *rq, int local)
{
	unsigned long long now;

	now = sched_clock();
#ifdef CONFIG_SMP
	if (!local) {
		/* Compensate for drifting sched_clock */
		runqueue_t *this_rq = this_rq();
		now = (now - this_rq->timestamp_last_tick)
			+ rq->timestamp_last_tick;
	}
#endif

	p->prio = recalc_task_prio(p, now);

	/*
	 * This checks to make sure it's not an uninterruptible task
	 * that is now waking up.
	 */
	if (!p->activated) {
		/*
		 * Tasks which were woken up by interrupts (ie. hw events)
		 * are most likely of interactive nature. So we give them
		 * the credit of extending their sleep time to the period
		 * of time they spend on the runqueue, waiting for execution
		 * on a CPU, first time around:
		 */
		if (in_interrupt())
			p->activated = 2;
		else {
			/*
			 * Normal first-time wakeups get a credit too for
			 * on-runqueue time, but it will be weighted down:
			 */
			p->activated = 1;
		}
	}
	p->timestamp = now;

	__activate_task(p, rq);
}

/*
 * deactivate_task - remove a task from the runqueue.
 */
static void deactivate_task(struct task_struct *p, runqueue_t *rq)
{
	rq->nr_running--;
	dequeue_task(p, p->array);
	p->array = NULL;
}

/*
 * 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
static void resched_task(task_t *p)
{
	int need_resched, nrpolling;

	assert_spin_locked(&task_rq(p)->lock);

	/* minimise the chance of sending an interrupt to poll_idle() */
	nrpolling = test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
	need_resched = test_and_set_tsk_thread_flag(p,TIF_NEED_RESCHED);
	nrpolling |= test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);

	if (!need_resched && !nrpolling && (task_cpu(p) != smp_processor_id()))
		smp_send_reschedule(task_cpu(p));
}
#else
static inline void resched_task(task_t *p)
{
	set_tsk_need_resched(p);
}
#endif

/**
 * task_curr - is this task currently executing on a CPU?
 * @p: the task in question.
 */
inline int task_curr(const task_t *p)
{
	return cpu_curr(task_cpu(p)) == p;
}

#ifdef CONFIG_SMP
typedef struct {
	struct list_head list;

	task_t *task;
	int dest_cpu;

	struct completion done;
} migration_req_t;

/*
 * The task's runqueue lock must be held.
 * Returns true if you have to wait for migration thread.
 */
static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
{
	runqueue_t *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->array && !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.
 *
 * The caller must ensure that the task *will* unschedule sometime soon,
 * else this function might spin for a *long* time. This function can't
 * be called with interrupts off, or it may introduce deadlock with
 * smp_call_function() if an IPI is sent by the same process we are
 * waiting to become inactive.
 */
void wait_task_inactive(task_t * p)
{
	unsigned long flags;
	runqueue_t *rq;
	int preempted;

repeat:
	rq = task_rq_lock(p, &flags);
	/* Must be off runqueue entirely, not preempted. */
	if (unlikely(p->array || task_running(rq, p))) {
		/* If it's preempted, we yield.  It could be a while. */
		preempted = !task_running(rq, p);
		task_rq_unlock(rq, &flags);
		cpu_relax();
		if (preempted)
			yield();
		goto repeat;
	}
	task_rq_unlock(rq, &flags);
}

/***
 * 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(task_t *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.
 *
 * We want to under-estimate the load of migration sources, to
 * balance conservatively.
 */
static inline unsigned long source_load(int cpu, int type)
{
	runqueue_t *rq = cpu_rq(cpu);
	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
	if (type == 0)
		return load_now;

	return min(rq->cpu_load[type-1], load_now);
}

/*
 * Return a high guess at the load of a migration-target cpu
 */
static inline unsigned long target_load(int cpu, int type)
{
	runqueue_t *rq = cpu_rq(cpu);
	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
	if (type == 0)
		return load_now;

	return max(rq->cpu_load[type-1], load_now);
}

/*
 * 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;

		local_group = cpu_isset(this_cpu, group->cpumask);
		/* XXX: put a cpus allowed check */

		/* Tally up the load of all CPUs in the group */
		avg_load = 0;

		for_each_cpu_mask(i, group->cpumask) {
			/* 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 = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;

		if (local_group) {
			this_load = avg_load;
			this = group;
		} else if (avg_load < min_load) {
			min_load = avg_load;
			idlest = group;
		}
		group = group->next;
	} while (group != sd->groups);

	if (!idlest || 100*this_load < imbalance*min_load)
		return NULL;
	return idlest;
}

/*
 * find_idlest_queue - find the idlest runqueue among the cpus in group.
 */
static int find_idlest_cpu(struct sched_group *group, int this_cpu)
{
	unsigned long load, min_load = ULONG_MAX;
	int idlest = -1;
	int i;

	for_each_cpu_mask(i, group->cpumask) {
		load = source_load(i, 0);

		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 (tmp->flags & flag)
			sd = tmp;

	while (sd) {
		cpumask_t span;
		struct sched_group *group;
		int new_cpu;
		int weight;

		span = sd->span;
		group = find_idlest_group(sd, t, cpu);
		if (!group)
			goto nextlevel;

		new_cpu = find_idlest_cpu(group, cpu);
		if (new_cpu == -1 || new_cpu == cpu)
			goto nextlevel;

		/* Now try balancing at a lower domain level */
		cpu = new_cpu;
nextlevel:
		sd = NULL;
		weight = cpus_weight(span);
		for_each_domain(cpu, tmp) {
			if (weight <= cpus_weight(tmp->span))
				break;
			if (tmp->flags & flag)
				sd = tmp;
		}
		/* while loop will break here if sd == NULL */
	}

	return cpu;
}

#endif /* CONFIG_SMP */

/*
 * wake_idle() will wake a task on an idle cpu if task->cpu is
 * not idle and an idle cpu is available.  The span of cpus to
 * search starts with cpus closest then further out as needed,
 * so we always favor a closer, idle cpu.
 *
 * Returns the CPU we should wake onto.
 */
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, task_t *p)
{
	cpumask_t tmp;
	struct sched_domain *sd;
	int i;

	if (idle_cpu(cpu))
		return cpu;

	for_each_domain(cpu, sd) {
		if (sd->flags & SD_WAKE_IDLE) {
			cpus_and(tmp, sd->span, p->cpus_allowed);
			for_each_cpu_mask(i, tmp) {
				if (idle_cpu(i))
					return i;
			}
		}
		else
			break;
	}
	return cpu;
}
#else
static inline int wake_idle(int cpu, task_t *p)
{
	return cpu;
}
#endif

/***
 * 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(task_t * p, unsigned int state, int sync)
{
	int cpu, this_cpu, success = 0;
	unsigned long flags;
	long old_state;
	runqueue_t *rq;
#ifdef CONFIG_SMP
	unsigned long load, this_load;
	struct sched_domain *sd, *this_sd = NULL;
	int new_cpu;
#endif

	rq = task_rq_lock(p, &flags);
	old_state = p->state;
	if (!(old_state & state))
		goto out;

	if (p->array)
		goto out_running;

	cpu = task_cpu(p);
	this_cpu = smp_processor_id();

#ifdef CONFIG_SMP
	if (unlikely(task_running(rq, p)))
		goto out_activate;

	new_cpu = cpu;

	schedstat_inc(rq, ttwu_cnt);
	if (cpu == this_cpu) {
		schedstat_inc(rq, ttwu_local);
		goto out_set_cpu;
	}

	for_each_domain(this_cpu, sd) {
		if (cpu_isset(cpu, sd->span)) {
			schedstat_inc(sd, ttwu_wake_remote);
			this_sd = sd;
			break;
		}
	}

	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
		goto out_set_cpu;

	/*
	 * Check for affine wakeup and passive balancing possibilities.
	 */
	if (this_sd) {
		int idx = this_sd->wake_idx;
		unsigned int imbalance;

		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;

		load = source_load(cpu, idx);
		this_load = target_load(this_cpu, idx);

		new_cpu = this_cpu; /* Wake to this CPU if we can */

		if (this_sd->flags & SD_WAKE_AFFINE) {
			unsigned long tl = this_load;
			/*
			 * If sync wakeup then subtract the (maximum possible)
			 * effect of the currently running task from the load
			 * of the current CPU:
			 */
			if (sync)
				tl -= SCHED_LOAD_SCALE;

			if ((tl <= load &&
				tl + target_load(cpu, idx) <= SCHED_LOAD_SCALE) ||
				100*(tl + SCHED_LOAD_SCALE) <= imbalance*load) {
				/*
				 * This domain has SD_WAKE_AFFINE and
				 * p is cache cold in this domain, and
				 * there is no bad imbalance.
				 */
				schedstat_inc(this_sd, ttwu_move_affine);
				goto out_set_cpu;
			}
		}

		/*
		 * Start passive balancing when half the imbalance_pct
		 * limit is reached.
		 */
		if (this_sd->flags & SD_WAKE_BALANCE) {
			if (imbalance*this_load <= 100*load) {
				schedstat_inc(this_sd, ttwu_move_balance);
				goto out_set_cpu;
			}
		}
	}

	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
out_set_cpu:
	new_cpu = wake_idle(new_cpu, p);
	if (new_cpu != cpu) {
		set_task_cpu(p, new_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->array)
			goto out_running;

		this_cpu = smp_processor_id();
		cpu = task_cpu(p);
	}

out_activate:
#endif /* CONFIG_SMP */
	if (old_state == TASK_UNINTERRUPTIBLE) {
		rq->nr_uninterruptible--;
		/*
		 * Tasks on involuntary sleep don't earn
		 * sleep_avg beyond just interactive state.
		 */
		p->activated = -1;
	}

	/*
	 * Sync wakeups (i.e. those types of wakeups where the waker
	 * has indicated that it will leave the CPU in short order)
	 * don't trigger a preemption, if the woken up task will run on
	 * this cpu. (in this case the 'I will reschedule' promise of
	 * the waker guarantees that the freshly woken up task is going
	 * to be considered on this CPU.)
	 */
	activate_task(p, rq, cpu == this_cpu);
	if (!sync || cpu != this_cpu) {
		if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);
	}
	success = 1;

out_running:
	p->state = TASK_RUNNING;
out:
	task_rq_unlock(rq, &flags);

	return success;
}

int fastcall wake_up_process(task_t * p)
{
	return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
				 TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
}

EXPORT_SYMBOL(wake_up_process);

int fastcall wake_up_state(task_t *p, unsigned int state)
{
	return try_to_wake_up(p, state, 0);
}

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 */
void fastcall sched_fork(task_t *p, int clone_flags)
{
	int cpu = get_cpu();

#ifdef CONFIG_SMP
	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
#endif
	set_task_cpu(p, cpu);

	/*
	 * 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;
	INIT_LIST_HEAD(&p->run_list);
	p->array = NULL;
#ifdef CONFIG_SCHEDSTATS
	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. */
	p->thread_info->preempt_count = 1;
#endif
	/*
	 * Share the timeslice between parent and child, thus the
	 * total amount of pending timeslices in the system doesn't change,
	 * resulting in more scheduling fairness.
	 */
	local_irq_disable();
	p->time_slice = (current->time_slice + 1) >> 1;
	/*
	 * The remainder of the first timeslice might be recovered by
	 * the parent if the child exits early enough.
	 */
	p->first_time_slice = 1;
	current->time_slice >>= 1;
	p->timestamp = sched_clock();
	if (unlikely(!current->time_slice)) {
		/*
		 * This case is rare, it happens when the parent has only
		 * a single jiffy left from its timeslice. Taking the
		 * runqueue lock is not a problem.
		 */
		current->time_slice = 1;
		scheduler_tick();
	}
	local_irq_enable();
	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 fastcall wake_up_new_task(task_t * p, unsigned long clone_flags)
{
	unsigned long flags;
	int this_cpu, cpu;
	runqueue_t *rq, *this_rq;

	rq = task_rq_lock(p, &flags);
	BUG_ON(p->state != TASK_RUNNING);
	this_cpu = smp_processor_id();
	cpu = task_cpu(p);

	/*
	 * We decrease the sleep average of forking parents
	 * and children as well, to keep max-interactive tasks
	 * from forking tasks that are max-interactive. The parent
	 * (current) is done further down, under its lock.
	 */
	p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) *
		CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);

	p->prio = effective_prio(p);

	if (likely(cpu == this_cpu)) {
		if (!(clone_flags & CLONE_VM)) {
			/*
			 * The VM isn't cloned, so we're in a good position to
			 * do child-runs-first in anticipation of an exec. This
			 * usually avoids a lot of COW overhead.
			 */
			if (unlikely(!current->array))
				__activate_task(p, rq);
			else {
				p->prio = current->prio;
				list_add_tail(&p->run_list, &current->run_list);
				p->array = current->array;
				p->array->nr_active++;
				rq->nr_running++;
			}
			set_need_resched();
		} else
			/* Run child last */
			__activate_task(p, rq);
		/*
		 * We skip the following code due to cpu == this_cpu
	 	 *
		 *   task_rq_unlock(rq, &flags);
		 *   this_rq = task_rq_lock(current, &flags);
		 */
		this_rq = rq;
	} else {
		this_rq = cpu_rq(this_cpu);

		/*
		 * Not the local CPU - must adjust timestamp. This should
		 * get optimised away in the !CONFIG_SMP case.
		 */
		p->timestamp = (p->timestamp - this_rq->timestamp_last_tick)
					+ rq->timestamp_last_tick;
		__activate_task(p, rq);
		if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);

		/*
		 * Parent and child are on different CPUs, now get the
		 * parent runqueue to update the parent's ->sleep_avg:
		 */
		task_rq_unlock(rq, &flags);
		this_rq = task_rq_lock(current, &flags);
	}
	current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
		PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
	task_rq_unlock(this_rq, &flags);
}

/*
 * Potentially available exiting-child timeslices are
 * retrieved here - this way the parent does not get
 * penalized for creating too many threads.
 *
 * (this cannot be used to 'generate' timeslices
 * artificially, because any timeslice recovered here
 * was given away by the parent in the first place.)
 */
void fastcall sched_exit(task_t * p)
{
	unsigned long flags;
	runqueue_t *rq;

	/*
	 * If the child was a (relative-) CPU hog then decrease
	 * the sleep_avg of the parent as well.
	 */
	rq = task_rq_lock(p->parent, &flags);
	if (p->first_time_slice) {
		p->parent->time_slice += p->time_slice;
		if (unlikely(p->parent->time_slice > task_timeslice(p)))
			p->parent->time_slice = task_timeslice(p);
	}
	if (p->sleep_avg < p->parent->sleep_avg)
		p->parent->sleep_avg = p->parent->sleep_avg /
		(EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg /
		(EXIT_WEIGHT + 1);
	task_rq_unlock(rq, &flags);
}

/**
 * prepare_task_switch - prepare to switch tasks
 * @rq: the runqueue preparing to switch
 * @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(runqueue_t *rq, task_t *next)
{
	prepare_lock_switch(rq, next);
	prepare_arch_switch(next);
}

/**
 * finish_task_switch - clean up after a 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 inline void finish_task_switch(runqueue_t *rq, task_t *prev)
	__releases(rq->lock)
{
	struct mm_struct *mm = rq->prev_mm;
	unsigned long prev_task_flags;

	rq->prev_mm = NULL;

	/*
	 * A task struct has one reference for the use as "current".
	 * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
	 * calls schedule one last time. The schedule call will never return,
	 * and the scheduled task must drop that reference.
	 * The test for EXIT_ZOMBIE must occur while the runqueue locks are
	 * still held, otherwise prev could be scheduled on another cpu, die
	 * there before we look at prev->state, and then the reference would
	 * be dropped twice.
	 *		Manfred Spraul <manfred@colorfullife.com>
	 */
	prev_task_flags = prev->flags;
	finish_arch_switch(prev);
	finish_lock_switch(rq, prev);
	if (mm)
		mmdrop(mm);
	if (unlikely(prev_task_flags & PF_DEAD))
		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(task_t *prev)
	__releases(rq->lock)
{
	runqueue_t *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(current->pid, current->set_child_tid);
}

/*
 * context_switch - switch to the new MM and the new
 * thread's register state.
 */
static inline
task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next)
{
	struct mm_struct *mm = next->mm;
	struct mm_struct *oldmm = prev->active_mm;

	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;
		WARN_ON(rq->prev_mm);
		rq->prev_mm = oldmm;
	}

	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);

	return 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_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)
{
	unsigned long long i, sum = 0;

	for_each_cpu(i)
		sum += cpu_rq(i)->nr_switches;

	return sum;
}

unsigned long nr_iowait(void)
{
	unsigned long i, sum = 0;

	for_each_cpu(i)
		sum += atomic_read(&cpu_rq(i)->nr_iowait);

	return sum;
}

#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(runqueue_t *rq1, runqueue_t *rq2)
	__acquires(rq1->lock)
	__acquires(rq2->lock)
{
	if (rq1 == rq2) {
		spin_lock(&rq1->lock);
		__acquire(rq2->lock);	/* Fake it out ;) */
	} else {
		if (rq1 < rq2) {
			spin_lock(&rq1->lock);
			spin_lock(&rq2->lock);
		} else {
			spin_lock(&rq2->lock);
			spin_lock(&rq1->lock);
		}
	}
}

/*
 * 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(runqueue_t *rq1, runqueue_t *rq2)
	__releases(rq1->lock)
	__releases(rq2->lock)
{
	spin_unlock(&rq1->lock);
	if (rq1 != rq2)
		spin_unlock(&rq2->lock);
	else
		__release(rq2->lock);
}

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	if (unlikely(!spin_trylock(&busiest->lock))) {
		if (busiest < this_rq) {
			spin_unlock(&this_rq->lock);
			spin_lock(&busiest->lock);
			spin_lock(&this_rq->lock);
		} else
			spin_lock(&busiest->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(task_t *p, int dest_cpu)
{
	migration_req_t req;
	runqueue_t *rq;
	unsigned long flags;

	rq = task_rq_lock(p, &flags);
	if (!cpu_isset(dest_cpu, p->cpus_allowed)
	    || unlikely(cpu_is_offline(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 inline
void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
	       runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
{
	dequeue_task(p, src_array);
	src_rq->nr_running--;
	set_task_cpu(p, this_cpu);
	this_rq->nr_running++;
	enqueue_task(p, this_array);
	p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
				+ this_rq->timestamp_last_tick;
	/*
	 * Note that idle threads have a prio of MAX_PRIO, for this test
	 * to be always true for them.
	 */
	if (TASK_PREEMPTS_CURR(p, this_rq))
		resched_task(this_rq->curr);
}

/*
 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
 */
static inline
int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
	     struct sched_domain *sd, enum 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 (!cpu_isset(this_cpu, p->cpus_allowed))
		return 0;
	*all_pinned = 0;

	if (task_running(rq, p))
		return 0;

	/*
	 * Aggressive migration if:
	 * 1) task is cache cold, or
	 * 2) too many balance attempts have failed.
	 */

	if (sd->nr_balance_failed > sd->cache_nice_tries)
		return 1;

	if (task_hot(p, rq->timestamp_last_tick, sd))
		return 0;
	return 1;
}

/*
 * move_tasks tries to move up to max_nr_move tasks from busiest to this_rq,
 * as part of a balancing operation within "domain". Returns the number of
 * tasks moved.
 *
 * Called with both runqueues locked.
 */
static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
		      unsigned long max_nr_move, struct sched_domain *sd,
		      enum idle_type idle, int *all_pinned)
{
	prio_array_t *array, *dst_array;
	struct list_head *head, *curr;
	int idx, pulled = 0, pinned = 0;
	task_t *tmp;

	if (max_nr_move == 0)
		goto out;

	pinned = 1;

	/*
	 * We first consider expired tasks. Those will likely not be
	 * executed in the near future, and they are most likely to
	 * be cache-cold, thus switching CPUs has the least effect
	 * on them.
	 */
	if (busiest->expired->nr_active) {
		array = busiest->expired;
		dst_array = this_rq->expired;
	} else {
		array = busiest->active;
		dst_array = this_rq->active;
	}

new_array:
	/* Start searching at priority 0: */
	idx = 0;
skip_bitmap:
	if (!idx)
		idx = sched_find_first_bit(array->bitmap);
	else
		idx = find_next_bit(array->bitmap, MAX_PRIO, idx);
	if (idx >= MAX_PRIO) {
		if (array == busiest->expired && busiest->active->nr_active) {
			array = busiest->active;
			dst_array = this_rq->active;
			goto new_array;
		}
		goto out;
	}

	head = array->queue + idx;
	curr = head->prev;
skip_queue:
	tmp = list_entry(curr, task_t, run_list);

	curr = curr->prev;

	if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
		if (curr != head)
			goto skip_queue;
		idx++;
		goto skip_bitmap;
	}

#ifdef CONFIG_SCHEDSTATS
	if (task_hot(tmp, busiest->timestamp_last_tick, sd))
		schedstat_inc(sd, lb_hot_gained[idle]);
#endif

	pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
	pulled++;

	/* We only want to steal up to the prescribed number of tasks. */
	if (pulled < max_nr_move) {
		if (curr != head)
			goto skip_queue;
		idx++;
		goto skip_bitmap;
	}
out:
	/*
	 * Right now, this is the only place 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 pulled;
}

/*
 * find_busiest_group finds and returns the busiest CPU group within the
 * domain. It calculates and returns the number of tasks 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 idle_type idle)
{
	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
	int load_idx;

	max_load = this_load = total_load = total_pwr = 0;
	if (idle == NOT_IDLE)
		load_idx = sd->busy_idx;
	else if (idle == NEWLY_IDLE)
		load_idx = sd->newidle_idx;
	else
		load_idx = sd->idle_idx;

	do {
		unsigned long load;
		int local_group;
		int i;

		local_group = cpu_isset(this_cpu, group->cpumask);

		/* Tally up the load of all CPUs in the group */
		avg_load = 0;

		for_each_cpu_mask(i, group->cpumask) {
			/* Bias balancing toward cpus of our domain */
			if (local_group)
				load = target_load(i, load_idx);
			else
				load = source_load(i, load_idx);

			avg_load += load;
		}

		total_load += avg_load;
		total_pwr += group->cpu_power;

		/* Adjust by relative CPU power of the group */
		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;

		if (local_group) {
			this_load = avg_load;
			this = group;
		} else if (avg_load > max_load) {
			max_load = avg_load;
			busiest = group;
		}
		group = group->next;
	} while (group != sd->groups);

	if (!busiest || this_load >= max_load)
		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;

	/*
	 * 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.
	 */
	/* How much load to actually move to equalise the imbalance */
	*imbalance = min((max_load - avg_load) * busiest->cpu_power,
				(avg_load - this_load) * this->cpu_power)
			/ SCHED_LOAD_SCALE;

	if (*imbalance < SCHED_LOAD_SCALE) {
		unsigned long pwr_now = 0, pwr_move = 0;
		unsigned long tmp;

		if (max_load - this_load >= SCHED_LOAD_SCALE*2) {
			*imbalance = 1;
			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(SCHED_LOAD_SCALE, max_load);
		pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load);
		pwr_now /= SCHED_LOAD_SCALE;

		/* Amount of load we'd subtract */
		tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/busiest->cpu_power;
		if (max_load > tmp)
			pwr_move += busiest->cpu_power*min(SCHED_LOAD_SCALE,
							max_load - tmp);

		/* Amount of load we'd add */
		if (max_load*busiest->cpu_power <
				SCHED_LOAD_SCALE*SCHED_LOAD_SCALE)
			tmp = max_load*busiest->cpu_power/this->cpu_power;
		else
			tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power;
		pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp);
		pwr_move /= SCHED_LOAD_SCALE;

		/* Move if we gain throughput */
		if (pwr_move <= pwr_now)
			goto out_balanced;

		*imbalance = 1;
		return busiest;
	}

	/* Get rid of the scaling factor, rounding down as we divide */
	*imbalance = *imbalance / SCHED_LOAD_SCALE;
	return busiest;

out_balanced:

	*imbalance = 0;
	return NULL;
}

/*
 * find_busiest_queue - find the busiest runqueue among the cpus in group.
 */
static runqueue_t *find_busiest_queue(struct sched_group *group)
{
	unsigned long load, max_load = 0;
	runqueue_t *busiest = NULL;
	int i;

	for_each_cpu_mask(i, group->cpumask) {
		load = source_load(i, 0);

		if (load > max_load) {
			max_load = load;
			busiest = cpu_rq(i);
		}
	}

	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.
 *
 * Called with this_rq unlocked.
 */
static int load_balance(int this_cpu, runqueue_t *this_rq,
			struct sched_domain *sd, enum idle_type idle)
{
	struct sched_group *group;
	runqueue_t *busiest;
	unsigned long imbalance;
	int nr_moved, all_pinned = 0;
	int active_balance = 0;

	spin_lock(&this_rq->lock);
	schedstat_inc(sd, lb_cnt[idle]);

	group = find_busiest_group(sd, this_cpu, &imbalance, idle);
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

	BUG_ON(busiest == this_rq);

	schedstat_add(sd, lb_imbalance[idle], imbalance);

	nr_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. nr_moved simply stays zero, so it is
		 * correctly treated as an imbalance.
		 */
		double_lock_balance(this_rq, busiest);
		nr_moved = move_tasks(this_rq, this_cpu, busiest,
						imbalance, sd, idle,
						&all_pinned);
		spin_unlock(&busiest->lock);

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(all_pinned))
			goto out_balanced;
	}

	spin_unlock(&this_rq->lock);

	if (!nr_moved) {
		schedstat_inc(sd, lb_failed[idle]);
		sd->nr_balance_failed++;

		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {

			spin_lock(&busiest->lock);
			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
				active_balance = 1;
			}
			spin_unlock(&busiest->lock);
			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;
	}

	return nr_moved;

out_balanced:
	spin_unlock(&this_rq->lock);

	schedstat_inc(sd, lb_balanced[idle]);

	sd->nr_balance_failed = 0;
	/* tune up the balancing interval */
	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
		sd->balance_interval *= 2;

	return 0;
}

/*
 * 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 (NEWLY_IDLE).
 * this_rq is locked.
 */
static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
				struct sched_domain *sd)
{
	struct sched_group *group;
	runqueue_t *busiest = NULL;
	unsigned long imbalance;
	int nr_moved = 0;

	schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE);
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
		goto out_balanced;
	}

	BUG_ON(busiest == this_rq);

	/* Attempt to move tasks */
	double_lock_balance(this_rq, busiest);

	schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
	nr_moved = move_tasks(this_rq, this_cpu, busiest,
					imbalance, sd, NEWLY_IDLE, NULL);
	if (!nr_moved)
		schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
	else
		sd->nr_balance_failed = 0;

	spin_unlock(&busiest->lock);
	return nr_moved;

out_balanced:
	schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
	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 inline void idle_balance(int this_cpu, runqueue_t *this_rq)
{
	struct sched_domain *sd;

	for_each_domain(this_cpu, sd) {
		if (sd->flags & SD_BALANCE_NEWIDLE) {
			if (load_balance_newidle(this_cpu, this_rq, sd)) {
				/* We've pulled tasks over so stop searching */
				break;
			}
		}
	}
}

/*
 * 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(runqueue_t *busiest_rq, int busiest_cpu)
{
	struct sched_domain *sd;
	runqueue_t *target_rq;
	int target_cpu = busiest_rq->push_cpu;

	if (busiest_rq->nr_running <= 1)
		/* no task to move */
		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);

	/* Search for an sd spanning us and the target CPU. */
	for_each_domain(target_cpu, sd)
		if ((sd->flags & SD_LOAD_BALANCE) &&
			cpu_isset(busiest_cpu, sd->span))
				break;

	if (unlikely(sd == NULL))
		goto out;

	schedstat_inc(sd, alb_cnt);

	if (move_tasks(target_rq, target_cpu, busiest_rq, 1, sd, SCHED_IDLE, NULL))
		schedstat_inc(sd, alb_pushed);
	else
		schedstat_inc(sd, alb_failed);
out:
	spin_unlock(&target_rq->lock);
}

/*
 * rebalance_tick will get called every timer tick, on every CPU.
 *
 * 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.
 */

/* Don't have all balancing operations going off at once */
#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS)

static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
			   enum idle_type idle)
{
	unsigned long old_load, this_load;
	unsigned long j = jiffies + CPU_OFFSET(this_cpu);
	struct sched_domain *sd;
	int i;

	this_load = this_rq->nr_running * SCHED_LOAD_SCALE;
	/* Update our load */
	for (i = 0; i < 3; i++) {
		unsigned long new_load = this_load;
		int scale = 1 << i;
		old_load = this_rq->cpu_load[i];
		/*
		 * 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) / scale;
	}

	for_each_domain(this_cpu, sd) {
		unsigned long interval;

		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		interval = sd->balance_interval;
		if (idle != SCHED_IDLE)
			interval *= sd->busy_factor;

		/* scale ms to jiffies */
		interval = msecs_to_jiffies(interval);
		if (unlikely(!interval))
			interval = 1;

		if (j - sd->last_balance >= interval) {
			if (load_balance(this_cpu, this_rq, sd, idle)) {
				/* We've pulled tasks over so no longer idle */
				idle = NOT_IDLE;
			}
			sd->last_balance += interval;
		}
	}
}
#else
/*
 * on UP we do not need to balance between CPUs:
 */
static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle)
{
}
static inline void idle_balance(int cpu, runqueue_t *rq)
{
}
#endif

static inline int wake_priority_sleeper(runqueue_t *rq)
{
	int ret = 0;
#ifdef CONFIG_SCHED_SMT
	spin_lock(&rq->lock);
	/*
	 * If an SMT sibling task has been put to sleep for priority
	 * reasons reschedule the idle task to see if it can now run.
	 */
	if (rq->nr_running) {
		resched_task(rq->idle);
		ret = 1;
	}
	spin_unlock(&rq->lock);
#endif
	return ret;
}

DEFINE_PER_CPU(struct kernel_stat, kstat);

EXPORT_PER_CPU_SYMBOL(kstat);

/*
 * This is called on clock ticks and on context switches.
 * Bank in p->sched_time the ns elapsed since the last tick or switch.
 */
static inline void update_cpu_clock(task_t *p, runqueue_t *rq,
				    unsigned long long now)
{
	unsigned long long last = max(p->timestamp, rq->timestamp_last_tick);
	p->sched_time += now - last;
}

/*
 * Return current->sched_time plus any more ns on the sched_clock
 * that have not yet been banked.
 */
unsigned long long current_sched_time(const task_t *tsk)
{
	unsigned long long ns;
	unsigned long flags;
	local_irq_save(flags);
	ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick);
	ns = tsk->sched_time + (sched_clock() - ns);
	local_irq_restore(flags);
	return ns;
}

/*
 * We place interactive tasks back into the active array, if possible.
 *
 * To guarantee that this does not starve expired tasks we ignore the
 * interactivity of a task if the first expired task had to wait more
 * than a 'reasonable' amount of time. This deadline timeout is
 * load-dependent, as the frequency of array switched decreases with
 * increasing number of running tasks. We also ignore the interactivity
 * if a better static_prio task has expired:
 */
#define EXPIRED_STARVING(rq) \
	((STARVATION_LIMIT && ((rq)->expired_timestamp && \
		(jiffies - (rq)->expired_timestamp >= \
			STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
			((rq)->curr->static_prio > (rq)->best_expired_prio))

/*
 * Account user 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 user space since the last update
 */
void account_user_time(struct task_struct *p, cputime_t cputime)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t tmp;

	p->utime = cputime_add(p->utime, 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 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
 */
void account_system_time(struct task_struct *p, int hardirq_offset,
			 cputime_t cputime)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	runqueue_t *rq = this_rq();
	cputime64_t tmp;

	p->stime = cputime_add(p->stime, 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 if (p != rq->idle)
		cpustat->system = cputime64_add(cpustat->system, tmp);
	else if (atomic_read(&rq->nr_iowait) > 0)
		cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
	else
		cpustat->idle = cputime64_add(cpustat->idle, tmp);
	/* Account for system time used */
	acct_update_integrals(p);
	/* Update rss highwater mark */
	update_mem_hiwater(p);
}

/*
 * Account for involuntary wait time.
 * @p: the process from which the cpu time has been stolen
 * @steal: the cpu time spent in involuntary wait
 */
void account_steal_time(struct task_struct *p, cputime_t steal)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t tmp = cputime_to_cputime64(steal);
	runqueue_t *rq = this_rq();

	if (p == rq->idle) {
		p->stime = cputime_add(p->stime, steal);
		if (atomic_read(&rq->nr_iowait) > 0)
			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
		else
			cpustat->idle = cputime64_add(cpustat->idle, tmp);
	} else
		cpustat->steal = cputime64_add(cpustat->steal, tmp);
}

/*
 * 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();
	runqueue_t *rq = this_rq();
	task_t *p = current;
	unsigned long long now = sched_clock();

	update_cpu_clock(p, rq, now);

	rq->timestamp_last_tick = now;

	if (p == rq->idle) {
		if (wake_priority_sleeper(rq))
			goto out;
		rebalance_tick(cpu, rq, SCHED_IDLE);
		return;
	}

	/* Task might have expired already, but not scheduled off yet */
	if (p->array != rq->active) {
		set_tsk_need_resched(p);
		goto out;
	}
	spin_lock(&rq->lock);
	/*
	 * The task was running during this tick - update the
	 * time slice counter. Note: we do not update a thread's
	 * priority until it either goes to sleep or uses up its
	 * timeslice. This makes it possible for interactive tasks
	 * to use up their timeslices at their highest priority levels.
	 */
	if (rt_task(p)) {
		/*
		 * RR tasks need a special form of timeslice management.
		 * FIFO tasks have no timeslices.
		 */
		if ((p->policy == SCHED_RR) && !--p->time_slice) {
			p->time_slice = task_timeslice(p);
			p->first_time_slice = 0;
			set_tsk_need_resched(p);

			/* put it at the end of the queue: */
			requeue_task(p, rq->active);
		}
		goto out_unlock;
	}
	if (!--p->time_slice) {
		dequeue_task(p, rq->active);
		set_tsk_need_resched(p);
		p->prio = effective_prio(p);
		p->time_slice = task_timeslice(p);
		p->first_time_slice = 0;

		if (!rq->expired_timestamp)
			rq->expired_timestamp = jiffies;
		if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
			enqueue_task(p, rq->expired);
			if (p->static_prio < rq->best_expired_prio)
				rq->best_expired_prio = p->static_prio;
		} else
			enqueue_task(p, rq->active);
	} else {
		/*
		 * Prevent a too long timeslice allowing a task to monopolize
		 * the CPU. We do this by splitting up the timeslice into
		 * smaller pieces.
		 *
		 * Note: this does not mean the task's timeslices expire or
		 * get lost in any way, they just might be preempted by
		 * another task of equal priority. (one with higher
		 * priority would have preempted this task already.) We
		 * requeue this task to the end of the list on this priority
		 * level, which is in essence a round-robin of tasks with
		 * equal priority.
		 *
		 * This only applies to tasks in the interactive
		 * delta range with at least TIMESLICE_GRANULARITY to requeue.
		 */
		if (TASK_INTERACTIVE(p) && !((task_timeslice(p) -
			p->time_slice) % TIMESLICE_GRANULARITY(p)) &&
			(p->time_slice >= TIMESLICE_GRANULARITY(p)) &&
			(p->array == rq->active)) {

			requeue_task(p, rq->active);
			set_tsk_need_resched(p);
		}
	}
out_unlock:
	spin_unlock(&rq->lock);
out:
	rebalance_tick(cpu, rq, NOT_IDLE);
}

#ifdef CONFIG_SCHED_SMT
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
	struct sched_domain *tmp, *sd = NULL;
	cpumask_t sibling_map;
	int i;

	for_each_domain(this_cpu, tmp)
		if (tmp->flags & SD_SHARE_CPUPOWER)
			sd = tmp;

	if (!sd)
		return;

	/*
	 * Unlock the current runqueue because we have to lock in
	 * CPU order to avoid deadlocks. Caller knows that we might
	 * unlock. We keep IRQs disabled.
	 */
	spin_unlock(&this_rq->lock);

	sibling_map = sd->span;

	for_each_cpu_mask(i, sibling_map)
		spin_lock(&cpu_rq(i)->lock);
	/*
	 * We clear this CPU from the mask. This both simplifies the
	 * inner loop and keps this_rq locked when we exit:
	 */
	cpu_clear(this_cpu, sibling_map);

	for_each_cpu_mask(i, sibling_map) {
		runqueue_t *smt_rq = cpu_rq(i);

		/*
		 * If an SMT sibling task is sleeping due to priority
		 * reasons wake it up now.
		 */
		if (smt_rq->curr == smt_rq->idle && smt_rq->nr_running)
			resched_task(smt_rq->idle);
	}

	for_each_cpu_mask(i, sibling_map)
		spin_unlock(&cpu_rq(i)->lock);
	/*
	 * We exit with this_cpu's rq still held and IRQs
	 * still disabled:
	 */
}

static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
	struct sched_domain *tmp, *sd = NULL;
	cpumask_t sibling_map;
	prio_array_t *array;
	int ret = 0, i;
	task_t *p;

	for_each_domain(this_cpu, tmp)
		if (tmp->flags & SD_SHARE_CPUPOWER)
			sd = tmp;

	if (!sd)
		return 0;

	/*
	 * The same locking rules and details apply as for
	 * wake_sleeping_dependent():
	 */
	spin_unlock(&this_rq->lock);
	sibling_map = sd->span;
	for_each_cpu_mask(i, sibling_map)
		spin_lock(&cpu_rq(i)->lock);
	cpu_clear(this_cpu, sibling_map);

	/*
	 * Establish next task to be run - it might have gone away because
	 * we released the runqueue lock above:
	 */
	if (!this_rq->nr_running)
		goto out_unlock;
	array = this_rq->active;
	if (!array->nr_active)
		array = this_rq->expired;
	BUG_ON(!array->nr_active);

	p = list_entry(array->queue[sched_find_first_bit(array->bitmap)].next,
		task_t, run_list);

	for_each_cpu_mask(i, sibling_map) {
		runqueue_t *smt_rq = cpu_rq(i);
		task_t *smt_curr = smt_rq->curr;

		/*
		 * If a user task with lower static priority than the
		 * running task on the SMT sibling is trying to schedule,
		 * delay it till there is proportionately less timeslice
		 * left of the sibling task to prevent a lower priority
		 * task from using an unfair proportion of the
		 * physical cpu's resources. -ck
		 */
		if (((smt_curr->time_slice * (100 - sd->per_cpu_gain) / 100) >
			task_timeslice(p) || rt_task(smt_curr)) &&
			p->mm && smt_curr->mm && !rt_task(p))
				ret = 1;

		/*
		 * Reschedule a lower priority task on the SMT sibling,
		 * or wake it up if it has been put to sleep for priority
		 * reasons.
		 */
		if ((((p->time_slice * (100 - sd->per_cpu_gain) / 100) >
			task_timeslice(smt_curr) || rt_task(p)) &&
			smt_curr->mm && p->mm && !rt_task(smt_curr)) ||
			(smt_curr == smt_rq->idle && smt_rq->nr_running))
				resched_task(smt_curr);
	}
out_unlock:
	for_each_cpu_mask(i, sibling_map)
		spin_unlock(&cpu_rq(i)->lock);
	return ret;
}
#else
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
}

static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
	return 0;
}
#endif

#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)

void fastcall add_preempt_count(int val)
{
	/*
	 * Underflow?
	 */
	BUG_ON((preempt_count() < 0));
	preempt_count() += val;
	/*
	 * Spinlock count overflowing soon?
	 */
	BUG_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
}
EXPORT_SYMBOL(add_preempt_count);

void fastcall sub_preempt_count(int val)
{
	/*
	 * Underflow?
	 */
	BUG_ON(val > preempt_count());
	/*
	 * Is the spinlock portion underflowing?
	 */
	BUG_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK));
	preempt_count() -= val;
}
EXPORT_SYMBOL(sub_preempt_count);

#endif

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
	long *switch_count;
	task_t *prev, *next;
	runqueue_t *rq;
	prio_array_t *array;
	struct list_head *queue;
	unsigned long long now;
	unsigned long run_time;
	int cpu, idx, new_prio;

	/*
	 * 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 (likely(!current->exit_state)) {
		if (unlikely(in_atomic())) {
			printk(KERN_ERR "scheduling while atomic: "
				"%s/0x%08x/%d\n",
				current->comm, preempt_count(), current->pid);
			dump_stack();
		}
	}
	profile_hit(SCHED_PROFILING, __builtin_return_address(0));

need_resched:
	preempt_disable();
	prev = current;
	release_kernel_lock(prev);
need_resched_nonpreemptible:
	rq = this_rq();

	/*
	 * The idle thread is not allowed to schedule!
	 * Remove this check after it has been exercised a bit.
	 */
	if (unlikely(prev == rq->idle) && prev->state != TASK_RUNNING) {
		printk(KERN_ERR "bad: scheduling from the idle thread!\n");
		dump_stack();
	}

	schedstat_inc(rq, sched_cnt);
	now = sched_clock();
	if (likely((long long)(now - prev->timestamp) < NS_MAX_SLEEP_AVG)) {
		run_time = now - prev->timestamp;
		if (unlikely((long long)(now - prev->timestamp) < 0))
			run_time = 0;
	} else
		run_time = NS_MAX_SLEEP_AVG;

	/*
	 * Tasks charged proportionately less run_time at high sleep_avg to
	 * delay them losing their interactive status
	 */
	run_time /= (CURRENT_BONUS(prev) ? : 1);

	spin_lock_irq(&rq->lock);

	if (unlikely(prev->flags & PF_DEAD))
		prev->state = EXIT_DEAD;

	switch_count = &prev->nivcsw;
	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
		switch_count = &prev->nvcsw;
		if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
				unlikely(signal_pending(prev))))
			prev->state = TASK_RUNNING;
		else {
			if (prev->state == TASK_UNINTERRUPTIBLE)
				rq->nr_uninterruptible++;
			deactivate_task(prev, rq);
		}
	}

	cpu = smp_processor_id();
	if (unlikely(!rq->nr_running)) {
go_idle:
		idle_balance(cpu, rq);
		if (!rq->nr_running) {
			next = rq->idle;
			rq->expired_timestamp = 0;
			wake_sleeping_dependent(cpu, rq);
			/*
			 * wake_sleeping_dependent() might have released
			 * the runqueue, so break out if we got new
			 * tasks meanwhile:
			 */
			if (!rq->nr_running)
				goto switch_tasks;
		}
	} else {
		if (dependent_sleeper(cpu, rq)) {
			next = rq->idle;
			goto switch_tasks;
		}
		/*
		 * dependent_sleeper() releases and reacquires the runqueue
		 * lock, hence go into the idle loop if the rq went
		 * empty meanwhile:
		 */
		if (unlikely(!rq->nr_running))
			goto go_idle;
	}

	array = rq->active;
	if (unlikely(!array->nr_active)) {
		/*
		 * Switch the active and expired arrays.
		 */
		schedstat_inc(rq, sched_switch);
		rq->active = rq->expired;
		rq->expired = array;
		array = rq->active;
		rq->expired_timestamp = 0;
		rq->best_expired_prio = MAX_PRIO;
	}

	idx = sched_find_first_bit(array->bitmap);
	queue = array->queue + idx;
	next = list_entry(queue->next, task_t, run_list);

	if (!rt_task(next) && next->activated > 0) {
		unsigned long long delta = now - next->timestamp;
		if (unlikely((long long)(now - next->timestamp) < 0))
			delta = 0;

		if (next->activated == 1)
			delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;

		array = next->array;
		new_prio = recalc_task_prio(next, next->timestamp + delta);

		if (unlikely(next->prio != new_prio)) {
			dequeue_task(next, array);
			next->prio = new_prio;
			enqueue_task(next, array);
		} else
			requeue_task(next, array);
	}
	next->activated = 0;
switch_tasks:
	if (next == rq->idle)
		schedstat_inc(rq, sched_goidle);
	prefetch(next);
	clear_tsk_need_resched(prev);
	rcu_qsctr_inc(task_cpu(prev));

	update_cpu_clock(prev, rq, now);

	prev->sleep_avg -= run_time;
	if ((long)prev->sleep_avg <= 0)
		prev->sleep_avg = 0;
	prev->timestamp = prev->last_ran = now;

	sched_info_switch(prev, next);
	if (likely(prev != next)) {
		next->timestamp = now;
		rq->nr_switches++;
		rq->curr = next;
		++*switch_count;

		prepare_task_switch(rq, next);
		prev = context_switch(rq, prev, next);
		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);
	} else
		spin_unlock_irq(&rq->lock);

	prev = current;
	if (unlikely(reacquire_kernel_lock(prev) < 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 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();
#ifdef CONFIG_PREEMPT_BKL
	struct task_struct *task = current;
	int saved_lock_depth;
#endif
	/*
	 * If there is a non-zero preempt_count or interrupts are disabled,
	 * we do not want to preempt the current task.  Just return..
	 */
	if (unlikely(ti->preempt_count || irqs_disabled()))
		return;

need_resched:
	add_preempt_count(PREEMPT_ACTIVE);
	/*
	 * We keep the big kernel semaphore locked, but we
	 * clear ->lock_depth so that schedule() doesnt
	 * auto-release the semaphore:
	 */
#ifdef CONFIG_PREEMPT_BKL
	saved_lock_depth = task->lock_depth;
	task->lock_depth = -1;
#endif
	schedule();
#ifdef CONFIG_PREEMPT_BKL
	task->lock_depth = saved_lock_depth;
#endif
	sub_preempt_count(PREEMPT_ACTIVE);

	/* we could miss a preemption opportunity between schedule and now */
	barrier();
	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
		goto need_resched;
}

EXPORT_SYMBOL(preempt_schedule);

/*
 * this is 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();
#ifdef CONFIG_PREEMPT_BKL
	struct task_struct *task = current;
	int saved_lock_depth;
#endif
	/* Catch callers which need to be fixed*/
	BUG_ON(ti->preempt_count || !irqs_disabled());

need_resched:
	add_preempt_count(PREEMPT_ACTIVE);
	/*
	 * We keep the big kernel semaphore locked, but we
	 * clear ->lock_depth so that schedule() doesnt
	 * auto-release the semaphore:
	 */
#ifdef CONFIG_PREEMPT_BKL
	saved_lock_depth = task->lock_depth;
	task->lock_depth = -1;
#endif
	local_irq_enable();
	schedule();
	local_irq_disable();
#ifdef CONFIG_PREEMPT_BKL
	task->lock_depth = saved_lock_depth;
#endif
	sub_preempt_count(PREEMPT_ACTIVE);

	/* we could miss a preemption opportunity between schedule and now */
	barrier();
	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
		goto need_resched;
}

#endif /* CONFIG_PREEMPT */

int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, void *key)
{
	task_t *p = curr->private;
	return try_to_wake_up(p, 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.
 */
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
			     int nr_exclusive, int sync, void *key)
{
	struct list_head *tmp, *next;

	list_for_each_safe(tmp, next, &q->task_list) {
		wait_queue_t *curr;
		unsigned flags;
		curr = list_entry(tmp, wait_queue_t, task_list);
		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 fastcall __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 fastcall __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 fastcall __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 */

void fastcall complete(struct completion *x)
{
	unsigned long flags;

	spin_lock_irqsave(&x->wait.lock, flags);
	x->done++;
	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
			 1, 0, NULL);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);

void fastcall 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_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
			 0, 0, NULL);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);

void fastcall __sched wait_for_completion(struct completion *x)
{
	might_sleep();
	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			__set_current_state(TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			schedule();
			spin_lock_irq(&x->wait.lock);
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
	spin_unlock_irq(&x->wait.lock);
}
EXPORT_SYMBOL(wait_for_completion);

unsigned long fastcall __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
	might_sleep();

	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			__set_current_state(TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			timeout = schedule_timeout(timeout);
			spin_lock_irq(&x->wait.lock);
			if (!timeout) {
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
out:
	spin_unlock_irq(&x->wait.lock);
	return timeout;
}
EXPORT_SYMBOL(wait_for_completion_timeout);

int fastcall __sched wait_for_completion_interruptible(struct completion *x)
{
	int ret = 0;

	might_sleep();

	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			if (signal_pending(current)) {
				ret = -ERESTARTSYS;
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
			__set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			schedule();
			spin_lock_irq(&x->wait.lock);
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
out:
	spin_unlock_irq(&x->wait.lock);

	return ret;
}
EXPORT_SYMBOL(wait_for_completion_interruptible);

unsigned long fastcall __sched
wait_for_completion_interruptible_timeout(struct completion *x,
					  unsigned long timeout)
{
	might_sleep();

	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			if (signal_pending(current)) {
				timeout = -ERESTARTSYS;
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
			__set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			timeout = schedule_timeout(timeout);
			spin_lock_irq(&x->wait.lock);
			if (!timeout) {
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
out:
	spin_unlock_irq(&x->wait.lock);
	return timeout;
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);


#define	SLEEP_ON_VAR					\
	unsigned long flags;				\
	wait_queue_t wait;				\
	init_waitqueue_entry(&wait, current);

#define SLEEP_ON_HEAD					\
	spin_lock_irqsave(&q->lock,flags);		\
	__add_wait_queue(q, &wait);			\
	spin_unlock(&q->lock);

#define	SLEEP_ON_TAIL					\
	spin_lock_irq(&q->lock);			\
	__remove_wait_queue(q, &wait);			\
	spin_unlock_irqrestore(&q->lock, flags);

void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q)
{
	SLEEP_ON_VAR

	current->state = TASK_INTERRUPTIBLE;

	SLEEP_ON_HEAD
	schedule();
	SLEEP_ON_TAIL
}

EXPORT_SYMBOL(interruptible_sleep_on);

long fastcall __sched interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	SLEEP_ON_VAR

	current->state = TASK_INTERRUPTIBLE;

	SLEEP_ON_HEAD
	timeout = schedule_timeout(timeout);
	SLEEP_ON_TAIL

	return timeout;
}

EXPORT_SYMBOL(interruptible_sleep_on_timeout);

void fastcall __sched sleep_on(wait_queue_head_t *q)
{
	SLEEP_ON_VAR

	current->state = TASK_UNINTERRUPTIBLE;

	SLEEP_ON_HEAD
	schedule();
	SLEEP_ON_TAIL
}

EXPORT_SYMBOL(sleep_on);

long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	SLEEP_ON_VAR

	current->state = TASK_UNINTERRUPTIBLE;

	SLEEP_ON_HEAD
	timeout = schedule_timeout(timeout);
	SLEEP_ON_TAIL

	return timeout;
}

EXPORT_SYMBOL(sleep_on_timeout);

void set_user_nice(task_t *p, long nice)
{
	unsigned long flags;
	prio_array_t *array;
	runqueue_t *rq;
	int old_prio, new_prio, delta;

	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);
	/*
	 * 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
	 * not SCHED_NORMAL:
	 */
	if (rt_task(p)) {
		p->static_prio = NICE_TO_PRIO(nice);
		goto out_unlock;
	}
	array = p->array;
	if (array)
		dequeue_task(p, array);

	old_prio = p->prio;
	new_prio = NICE_TO_PRIO(nice);
	delta = new_prio - old_prio;
	p->static_prio = NICE_TO_PRIO(nice);
	p->prio += delta;

	if (array) {
		enqueue_task(p, array);
		/*
		 * 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 task_t *p, const int nice)
{
	/* convert nice value [19,-20] to rlimit style value [0,39] */
	int nice_rlim = 19 - 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.
 */
asmlinkage long sys_nice(int increment)
{
	int retval;
	long nice;

	/*
	 * 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 task_t *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 task_t *p)
{
	return TASK_NICE(p);
}
EXPORT_SYMBOL_GPL(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;
}

EXPORT_SYMBOL_GPL(idle_cpu);

/**
 * idle_task - return the idle task for a given cpu.
 * @cpu: the processor in question.
 */
task_t *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 inline task_t *find_process_by_pid(pid_t pid)
{
	return pid ? find_task_by_pid(pid) : current;
}

/* Actually do priority change: must hold rq lock. */
static void __setscheduler(struct task_struct *p, int policy, int prio)
{
	BUG_ON(p->array);
	p->policy = policy;
	p->rt_priority = prio;
	if (policy != SCHED_NORMAL)
		p->prio = MAX_RT_PRIO-1 - p->rt_priority;
	else
		p->prio = p->static_prio;
}

/**
 * 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.
 */
int sched_setscheduler(struct task_struct *p, int policy, struct sched_param *param)
{
	int retval;
	int oldprio, oldpolicy = -1;
	prio_array_t *array;
	unsigned long flags;
	runqueue_t *rq;

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)
			return -EINVAL;
	/*
	 * Valid priorities for SCHED_FIFO and SCHED_RR are
	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL 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 ((policy == SCHED_NORMAL) != (param->sched_priority == 0))
		return -EINVAL;

	/*
	 * Allow unprivileged RT tasks to decrease priority:
	 */
	if (!capable(CAP_SYS_NICE)) {
		/* can't change policy */
		if (policy != p->policy &&
			!p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
			return -EPERM;
		/* can't increase priority */
		if (policy != SCHED_NORMAL &&
		    param->sched_priority > p->rt_priority &&
		    param->sched_priority >
				p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
			return -EPERM;
		/* can't change other user's priorities */
		if ((current->euid != p->euid) &&
		    (current->euid != p->uid))
			return -EPERM;
	}

	retval = security_task_setscheduler(p, policy, param);
	if (retval)
		return retval;
	/*
	 * To be able to change p->policy safely, the apropriate
	 * runqueue lock must be held.
	 */
	rq = task_rq_lock(p, &flags);
	/* recheck policy now with rq lock held */
	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
		policy = oldpolicy = -1;
		task_rq_unlock(rq, &flags);
		goto recheck;
	}
	array = p->array;
	if (array)
		deactivate_task(p, rq);
	oldprio = p->prio;
	__setscheduler(p, policy, param->sched_priority);
	if (array) {
		__activate_task(p, rq);
		/*
		 * Reschedule if we are currently running on this runqueue and
		 * our priority decreased, or if we are not currently running on
		 * this runqueue and our priority is higher than the current's
		 */
		if (task_running(rq, p)) {
			if (p->prio > oldprio)
				resched_task(rq->curr);
		} else if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);
	}
	task_rq_unlock(rq, &flags);
	return 0;
}
EXPORT_SYMBOL_GPL(sched_setscheduler);

static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
	int retval;
	struct sched_param lparam;
	struct task_struct *p;

	if (!param || pid < 0)
		return -EINVAL;
	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
		return -EFAULT;
	read_lock_irq(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (!p) {
		read_unlock_irq(&tasklist_lock);
		return -ESRCH;
	}
	retval = sched_setscheduler(p, policy, &lparam);
	read_unlock_irq(&tasklist_lock);
	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.
 */
asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
				       struct sched_param __user *param)
{
	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.
 */
asmlinkage long sys_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.
 */
asmlinkage long sys_sched_getscheduler(pid_t pid)
{
	int retval = -EINVAL;
	task_t *p;

	if (pid < 0)
		goto out_nounlock;

	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);

out_nounlock:
	return retval;
}

/**
 * sys_sched_getscheduler - get the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the RT priority.
 */
asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
{
	struct sched_param lp;
	int retval = -EINVAL;
	task_t *p;

	if (!param || pid < 0)
		goto out_nounlock;

	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;

out_nounlock:
	return retval;

out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

long sched_setaffinity(pid_t pid, cpumask_t new_mask)
{
	task_t *p;
	int retval;
	cpumask_t cpus_allowed;

	lock_cpu_hotplug();
	read_lock(&tasklist_lock);

	p = find_process_by_pid(pid);
	if (!p) {
		read_unlock(&tasklist_lock);
		unlock_cpu_hotplug();
		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);

	retval = -EPERM;
	if ((current->euid != p->euid) && (current->euid != p->uid) &&
			!capable(CAP_SYS_NICE))
		goto out_unlock;

	cpus_allowed = cpuset_cpus_allowed(p);
	cpus_and(new_mask, new_mask, cpus_allowed);
	retval = set_cpus_allowed(p, new_mask);

out_unlock:
	put_task_struct(p);
	unlock_cpu_hotplug();
	return retval;
}

static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
			     cpumask_t *new_mask)
{
	if (len < sizeof(cpumask_t)) {
		memset(new_mask, 0, sizeof(cpumask_t));
	} else if (len > sizeof(cpumask_t)) {
		len = sizeof(cpumask_t);
	}
	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
 */
asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
				      unsigned long __user *user_mask_ptr)
{
	cpumask_t new_mask;
	int retval;

	retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask);
	if (retval)
		return retval;

	return sched_setaffinity(pid, new_mask);
}

/*
 * Represents all cpu's present in the system
 * In systems capable of hotplug, this map could dynamically grow
 * as new cpu's are detected in the system via any platform specific
 * method, such as ACPI for e.g.
 */

cpumask_t cpu_present_map;
EXPORT_SYMBOL(cpu_present_map);

#ifndef CONFIG_SMP
cpumask_t cpu_online_map = CPU_MASK_ALL;
cpumask_t cpu_possible_map = CPU_MASK_ALL;
#endif

long sched_getaffinity(pid_t pid, cpumask_t *mask)
{
	int retval;
	task_t *p;

	lock_cpu_hotplug();
	read_lock(&tasklist_lock);

	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = 0;
	cpus_and(*mask, p->cpus_allowed, cpu_possible_map);

out_unlock:
	read_unlock(&tasklist_lock);
	unlock_cpu_hotplug();
	if (retval)
		return retval;

	return 0;
}

/**
 * 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
 */
asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
				      unsigned long __user *user_mask_ptr)
{
	int ret;
	cpumask_t mask;

	if (len < sizeof(cpumask_t))
		return -EINVAL;

	ret = sched_getaffinity(pid, &mask);
	if (ret < 0)
		return ret;

	if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t)))
		return -EFAULT;

	return sizeof(cpumask_t);
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * this function yields the current CPU by moving the calling thread
 * to the expired array. If there are no other threads running on this
 * CPU then this function will return.
 */
asmlinkage long sys_sched_yield(void)
{
	runqueue_t *rq = this_rq_lock();
	prio_array_t *array = current->array;
	prio_array_t *target = rq->expired;

	schedstat_inc(rq, yld_cnt);
	/*
	 * We implement yielding by moving the task into the expired
	 * queue.
	 *
	 * (special rule: RT tasks will just roundrobin in the active
	 *  array.)
	 */
	if (rt_task(current))
		target = rq->active;

	if (current->array->nr_active == 1) {
		schedstat_inc(rq, yld_act_empty);
		if (!rq->expired->nr_active)
			schedstat_inc(rq, yld_both_empty);
	} else if (!rq->expired->nr_active)
		schedstat_inc(rq, yld_exp_empty);

	if (array != target) {
		dequeue_task(current, array);
		enqueue_task(current, target);
	} else
		/*
		 * requeue_task is cheaper so perform that if possible.
		 */
		requeue_task(current, array);

	/*
	 * Since we are going to call schedule() anyway, there's
	 * no need to preempt or enable interrupts:
	 */
	__release(rq->lock);
	_raw_spin_unlock(&rq->lock);
	preempt_enable_no_resched();

	schedule();

	return 0;
}

static inline void __cond_resched(void)
{
	/*
	 * The BKS might be reacquired before we have dropped
	 * PREEMPT_ACTIVE, which could trigger a second
	 * cond_resched() call.
	 */
	if (unlikely(preempt_count()))
		return;
	do {
		add_preempt_count(PREEMPT_ACTIVE);
		schedule();
		sub_preempt_count(PREEMPT_ACTIVE);
	} while (need_resched());
}

int __sched cond_resched(void)
{
	if (need_resched()) {
		__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 ret = 0;

	if (need_lockbreak(lock)) {
		spin_unlock(lock);
		cpu_relax();
		ret = 1;
		spin_lock(lock);
	}
	if (need_resched()) {
		_raw_spin_unlock(lock);
		preempt_enable_no_resched();
		__cond_resched();
		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()) {
		__local_bh_enable();
		__cond_resched();
		local_bh_disable();
		return 1;
	}
	return 0;
}

EXPORT_SYMBOL(cond_resched_softirq);


/**
 * 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 runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());

	atomic_inc(&rq->nr_iowait);
	schedule();
	atomic_dec(&rq->nr_iowait);
}

EXPORT_SYMBOL(io_schedule);

long __sched io_schedule_timeout(long timeout)
{
	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
	long ret;

	atomic_inc(&rq->nr_iowait);
	ret = schedule_timeout(timeout);
	atomic_dec(&rq->nr_iowait);
	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.
 */
asmlinkage long sys_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:
		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.
 */
asmlinkage long sys_sched_get_priority_min(int policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = 1;
		break;
	case SCHED_NORMAL:
		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.
 */
asmlinkage
long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
{
	int retval = -EINVAL;
	struct timespec t;
	task_t *p;

	if (pid < 0)
		goto out_nounlock;

	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;

	jiffies_to_timespec(p->policy & SCHED_FIFO ?
				0 : task_timeslice(p), &t);
	read_unlock(&tasklist_lock);
	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
out_nounlock:
	return retval;
out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

static inline struct task_struct *eldest_child(struct task_struct *p)
{
	if (list_empty(&p->children)) return NULL;
	return list_entry(p->children.next,struct task_struct,sibling);
}

static inline struct task_struct *older_sibling(struct task_struct *p)
{
	if (p->sibling.prev==&p->parent->children) return NULL;
	return list_entry(p->sibling.prev,struct task_struct,sibling);
}

static inline struct task_struct *younger_sibling(struct task_struct *p)
{
	if (p->sibling.next==&p->parent->children) return NULL;
	return list_entry(p->sibling.next,struct task_struct,sibling);
}

static void show_task(task_t * p)
{
	task_t *relative;
	unsigned state;
	unsigned long free = 0;
	static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };

	printk("%-13.13s ", p->comm);
	state = p->state ? __ffs(p->state) + 1 : 0;
	if (state < ARRAY_SIZE(stat_nam))
		printk(stat_nam[state]);
	else
		printk("?");
#if (BITS_PER_LONG == 32)
	if (state == TASK_RUNNING)
		printk(" running ");
	else
		printk(" %08lX ", thread_saved_pc(p));
#else
	if (state == TASK_RUNNING)
		printk("  running task   ");
	else
		printk(" %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
	{
		unsigned long * n = (unsigned long *) (p->thread_info+1);
		while (!*n)
			n++;
		free = (unsigned long) n - (unsigned long)(p->thread_info+1);
	}
#endif
	printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
	if ((relative = eldest_child(p)))
		printk("%5d ", relative->pid);
	else
		printk("      ");
	if ((relative = younger_sibling(p)))
		printk("%7d", relative->pid);
	else
		printk("       ");
	if ((relative = older_sibling(p)))
		printk(" %5d", relative->pid);
	else
		printk("      ");
	if (!p->mm)
		printk(" (L-TLB)\n");
	else
		printk(" (NOTLB)\n");

	if (state != TASK_RUNNING)
		show_stack(p, NULL);
}

void show_state(void)
{
	task_t *g, *p;

#if (BITS_PER_LONG == 32)
	printk("\n"
	       "                                               sibling\n");
	printk("  task             PC      pid father child younger older\n");
#else
	printk("\n"
	       "                                                       sibling\n");
	printk("  task                 PC          pid father child younger older\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();
		show_task(p);
	} while_each_thread(g, p);

	read_unlock(&tasklist_lock);
}

/**
 * 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 __devinit init_idle(task_t *idle, int cpu)
{
	runqueue_t *rq = cpu_rq(cpu);
	unsigned long flags;

	idle->sleep_avg = 0;
	idle->array = NULL;
	idle->prio = MAX_PRIO;
	idle->state = TASK_RUNNING;
	idle->cpus_allowed = cpumask_of_cpu(cpu);
	set_task_cpu(idle, cpu);

	spin_lock_irqsave(&rq->lock, flags);
	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) && !defined(CONFIG_PREEMPT_BKL)
	idle->thread_info->preempt_count = (idle->lock_depth >= 0);
#else
	idle->thread_info->preempt_count = 0;
#endif
}

/*
 * 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_MASK_NONE.
 */
cpumask_t nohz_cpu_mask = CPU_MASK_NONE;

#ifdef CONFIG_SMP
/*
 * This is how migration works:
 *
 * 1) we queue a migration_req_t 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(task_t *p, cpumask_t new_mask)
{
	unsigned long flags;
	int ret = 0;
	migration_req_t req;
	runqueue_t *rq;

	rq = task_rq_lock(p, &flags);
	if (!cpus_intersects(new_mask, cpu_online_map)) {
		ret = -EINVAL;
		goto out;
	}

	p->cpus_allowed = new_mask;
	/* Can the task run on the task's current CPU? If so, we're done */
	if (cpu_isset(task_cpu(p), new_mask))
		goto out;

	if (migrate_task(p, any_online_cpu(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);

/*
 * 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.
 */
static void __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
{
	runqueue_t *rq_dest, *rq_src;

	if (unlikely(cpu_is_offline(dest_cpu)))
		return;

	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 out;
	/* Affinity changed (again). */
	if (!cpu_isset(dest_cpu, p->cpus_allowed))
		goto out;

	set_task_cpu(p, dest_cpu);
	if (p->array) {
		/*
		 * Sync timestamp with rq_dest's before activating.
		 * The same thing could be achieved by doing this step
		 * afterwards, and pretending it was a local activate.
		 * This way is cleaner and logically correct.
		 */
		p->timestamp = p->timestamp - rq_src->timestamp_last_tick
				+ rq_dest->timestamp_last_tick;
		deactivate_task(p, rq_src);
		activate_task(p, rq_dest, 0);
		if (TASK_PREEMPTS_CURR(p, rq_dest))
			resched_task(rq_dest->curr);
	}

out:
	double_rq_unlock(rq_src, rq_dest);
}

/*
 * 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)
{
	runqueue_t *rq;
	int cpu = (long)data;

	rq = cpu_rq(cpu);
	BUG_ON(rq->migration_thread != current);

	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		struct list_head *head;
		migration_req_t *req;

		try_to_freeze();

		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, migration_req_t, 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
/* Figure out where task on dead CPU should go, use force if neccessary. */
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk)
{
	int dest_cpu;
	cpumask_t mask;

	/* On same node? */
	mask = node_to_cpumask(cpu_to_node(dead_cpu));
	cpus_and(mask, mask, tsk->cpus_allowed);
	dest_cpu = any_online_cpu(mask);

	/* On any allowed CPU? */
	if (dest_cpu == NR_CPUS)
		dest_cpu = any_online_cpu(tsk->cpus_allowed);

	/* No more Mr. Nice Guy. */
	if (dest_cpu == NR_CPUS) {
		cpus_setall(tsk->cpus_allowed);
		dest_cpu = any_online_cpu(tsk->cpus_allowed);

		/*
		 * Don't tell them about moving exiting tasks or
		 * kernel threads (both mm NULL), since they never
		 * leave kernel.
		 */
		if (tsk->mm && printk_ratelimit())
			printk(KERN_INFO "process %d (%s) no "
			       "longer affine to cpu%d\n",
			       tsk->pid, tsk->comm, dead_cpu);
	}
	__migrate_task(tsk, dead_cpu, dest_cpu);
}

/*
 * 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(runqueue_t *rq_src)
{
	runqueue_t *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
	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 *tsk, *t;

	write_lock_irq(&tasklist_lock);

	do_each_thread(t, tsk) {
		if (tsk == current)
			continue;

		if (task_cpu(tsk) == src_cpu)
			move_task_off_dead_cpu(src_cpu, tsk);
	} while_each_thread(t, tsk);

	write_unlock_irq(&tasklist_lock);
}

/* Schedules idle task to be the next runnable task on current CPU.
 * It does so by boosting its priority to highest possible and adding it to
 * the _front_ of runqueue. Used by CPU offline code.
 */
void sched_idle_next(void)
{
	int cpu = smp_processor_id();
	runqueue_t *rq = this_rq();
	struct task_struct *p = rq->idle;
	unsigned long flags;

	/* cpu has to be offline */
	BUG_ON(cpu_online(cpu));

	/* Strictly not necessary since rest of the CPUs are stopped by now
	 * and interrupts disabled on current cpu.
	 */
	spin_lock_irqsave(&rq->lock, flags);

	__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
	/* Add idle task to _front_ of it's priority queue */
	__activate_idle_task(p, rq);

	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);
}

static void migrate_dead(unsigned int dead_cpu, task_t *tsk)
{
	struct runqueue *rq = cpu_rq(dead_cpu);

	/* Must be exiting, otherwise would be on tasklist. */
	BUG_ON(tsk->exit_state != EXIT_ZOMBIE && tsk->exit_state != EXIT_DEAD);

	/* Cannot have done final schedule yet: would have vanished. */
	BUG_ON(tsk->flags & PF_DEAD);

	get_task_struct(tsk);

	/*
	 * 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, tsk);
	spin_lock_irq(&rq->lock);

	put_task_struct(tsk);
}

/* release_task() removes task from tasklist, so we won't find dead tasks. */
static void migrate_dead_tasks(unsigned int dead_cpu)
{
	unsigned arr, i;
	struct runqueue *rq = cpu_rq(dead_cpu);

	for (arr = 0; arr < 2; arr++) {
		for (i = 0; i < MAX_PRIO; i++) {
			struct list_head *list = &rq->arrays[arr].queue[i];
			while (!list_empty(list))
				migrate_dead(dead_cpu,
					     list_entry(list->next, task_t,
							run_list));
		}
	}
}
#endif /* CONFIG_HOTPLUG_CPU */

/*
 * 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 migration_call(struct notifier_block *nfb, unsigned long action,
			  void *hcpu)
{
	int cpu = (long)hcpu;
	struct task_struct *p;
	struct runqueue *rq;
	unsigned long flags;

	switch (action) {
	case CPU_UP_PREPARE:
		p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
		if (IS_ERR(p))
			return NOTIFY_BAD;
		p->flags |= PF_NOFREEZE;
		kthread_bind(p, cpu);
		/* Must be high prio: stop_machine expects to yield to it. */
		rq = task_rq_lock(p, &flags);
		__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
		task_rq_unlock(rq, &flags);
		cpu_rq(cpu)->migration_thread = p;
		break;
	case CPU_ONLINE:
		/* Strictly unneccessary, as first user will wake it. */
		wake_up_process(cpu_rq(cpu)->migration_thread);
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
		/* Unbind it from offline cpu so it can run.  Fall thru. */
		kthread_bind(cpu_rq(cpu)->migration_thread,smp_processor_id());
		kthread_stop(cpu_rq(cpu)->migration_thread);
		cpu_rq(cpu)->migration_thread = NULL;
		break;
	case CPU_DEAD:
		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) */
		rq = task_rq_lock(rq->idle, &flags);
		deactivate_task(rq->idle, rq);
		rq->idle->static_prio = MAX_PRIO;
		__setscheduler(rq->idle, SCHED_NORMAL, 0);
		migrate_dead_tasks(cpu);
		task_rq_unlock(rq, &flags);
		migrate_nr_uninterruptible(rq);
		BUG_ON(rq->nr_running != 0);

		/* No need to migrate the tasks: it was best-effort if
		 * they didn't do lock_cpu_hotplug().  Just wake up
		 * the requestors. */
		spin_lock_irq(&rq->lock);
		while (!list_empty(&rq->migration_queue)) {
			migration_req_t *req;