Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into sh-latest

84 files changed, 5553 insertions, 2468 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index e4956244ae50..939500317066 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -74,6 +74,8 @@ static int	audit_initialized;
 int		audit_enabled;
 int		audit_ever_enabled;
 
+EXPORT_SYMBOL_GPL(audit_enabled);
+
 /* Default state when kernel boots without any parameters. */
 static int	audit_default;
 
@@ -671,9 +673,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	pid  = NETLINK_CREDS(skb)->pid;
 	uid  = NETLINK_CREDS(skb)->uid;
-	loginuid = NETLINK_CB(skb).loginuid;
-	sessionid = NETLINK_CB(skb).sessionid;
-	sid  = NETLINK_CB(skb).sid;
+	loginuid = audit_get_loginuid(current);
+	sessionid = audit_get_sessionid(current);
+	security_task_getsecid(current, &sid);
 	seq  = nlh->nlmsg_seq;
 	data = NLMSG_DATA(nlh);
 
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d2e3c7866460..e683869365d9 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -144,9 +144,9 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
 }
 
 /* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct nameidata *ndp)
+static struct audit_parent *audit_init_parent(struct path *path)
 {
-	struct inode *inode = ndp->path.dentry->d_inode;
+	struct inode *inode = path->dentry->d_inode;
 	struct audit_parent *parent;
 	int ret;
 
@@ -353,53 +353,40 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 }
 
 /* Get path information necessary for adding watches. */
-static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
+static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct nameidata *ndparent, *ndwatch;
+	struct nameidata nd;
+	struct dentry *d;
 	int err;
 
-	ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
-	if (unlikely(!ndparent))
-		return -ENOMEM;
+	err = kern_path_parent(watch->path, &nd);
+	if (err)
+		return err;
 
-	ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
-	if (unlikely(!ndwatch)) {
-		kfree(ndparent);
-		return -ENOMEM;
+	if (nd.last_type != LAST_NORM) {
+		path_put(&nd.path);
+		return -EINVAL;
 	}
 
-	err = path_lookup(path, LOOKUP_PARENT, ndparent);
-	if (err) {
-		kfree(ndparent);
-		kfree(ndwatch);
-		return err;
+	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+	if (IS_ERR(d)) {
+		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+		path_put(&nd.path);
+		return PTR_ERR(d);
 	}
-
-	err = path_lookup(path, 0, ndwatch);
-	if (err) {
-		kfree(ndwatch);
-		ndwatch = NULL;
+	if (d->d_inode) {
+		/* update watch filter fields */
+		watch->dev = d->d_inode->i_sb->s_dev;
+		watch->ino = d->d_inode->i_ino;
 	}
+	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 
-	*ndp = ndparent;
-	*ndw = ndwatch;
-
+	*parent = nd.path;
+	dput(d);
 	return 0;
 }
 
-/* Release resources used for watch path information. */
-static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
-{
-	if (ndp) {
-		path_put(&ndp->path);
-		kfree(ndp);
-	}
-	if (ndw) {
-		path_put(&ndw->path);
-		kfree(ndw);
-	}
-}
-
 /* Associate the given rule with an existing parent.
  * Caller must hold audit_filter_mutex. */
 static void audit_add_to_parent(struct audit_krule *krule,
@@ -440,31 +427,24 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 {
 	struct audit_watch *watch = krule->watch;
 	struct audit_parent *parent;
-	struct nameidata *ndp = NULL, *ndw = NULL;
+	struct path parent_path;
 	int h, ret = 0;
 
 	mutex_unlock(&audit_filter_mutex);
 
 	/* Avoid calling path_lookup under audit_filter_mutex. */
-	ret = audit_get_nd(watch->path, &ndp, &ndw);
-	if (ret) {
-		/* caller expects mutex locked */
-		mutex_lock(&audit_filter_mutex);
-		goto error;
-	}
+	ret = audit_get_nd(watch, &parent_path);
 
+	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	/* update watch filter fields */
-	if (ndw) {
-		watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
-		watch->ino = ndw->path.dentry->d_inode->i_ino;
-	}
+	if (ret)
+		return ret;
 
 	/* either find an old parent or attach a new one */
-	parent = audit_find_parent(ndp->path.dentry->d_inode);
+	parent = audit_find_parent(parent_path.dentry->d_inode);
 	if (!parent) {
-		parent = audit_init_parent(ndp);
+		parent = audit_init_parent(&parent_path);
 		if (IS_ERR(parent)) {
 			ret = PTR_ERR(parent);
 			goto error;
@@ -479,9 +459,8 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	h = audit_hash_ino((u32)watch->ino);
 	*list = &audit_inode_hash[h];
 error:
-	audit_put_nd(ndp, ndw);		/* NULL args OK */
+	path_put(&parent_path);
 	return ret;
-
 }
 
 void audit_remove_watch_rule(struct audit_krule *krule)
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index add2819af71b..f8277c80d678 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1238,6 +1238,7 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
 	for (i = 0; i < rule->field_count; i++) {
 		struct audit_field *f = &rule->fields[i];
 		int result = 0;
+		u32 sid;
 
 		switch (f->type) {
 		case AUDIT_PID:
@@ -1250,19 +1251,22 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
 			result = audit_comparator(cb->creds.gid, f->op, f->val);
 			break;
 		case AUDIT_LOGINUID:
-			result = audit_comparator(cb->loginuid, f->op, f->val);
+			result = audit_comparator(audit_get_loginuid(current),
+						  f->op, f->val);
 			break;
 		case AUDIT_SUBJ_USER:
 		case AUDIT_SUBJ_ROLE:
 		case AUDIT_SUBJ_TYPE:
 		case AUDIT_SUBJ_SEN:
 		case AUDIT_SUBJ_CLR:
-			if (f->lsm_rule)
-				result = security_audit_rule_match(cb->sid,
+			if (f->lsm_rule) {
+				security_task_getsecid(current, &sid);
+				result = security_audit_rule_match(sid,
 								   f->type,
 								   f->op,
 								   f->lsm_rule,
 								   NULL);
+			}
 			break;
 		}
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b24d7027b83c..95362d15128c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4230,20 +4230,8 @@ void cgroup_post_fork(struct task_struct *child)
  */
 void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 {
-	int i;
 	struct css_set *cg;
-
-	if (run_callbacks && need_forkexit_callback) {
-		/*
-		 * modular subsystems can't use callbacks, so no need to lock
-		 * the subsys array
-		 */
-		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-			if (ss->exit)
-				ss->exit(ss, tsk);
-		}
-	}
+	int i;
 
 	/*
 	 * Unlink from the css_set task list if necessary.
@@ -4261,7 +4249,24 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	task_lock(tsk);
 	cg = tsk->cgroups;
 	tsk->cgroups = &init_css_set;
+
+	if (run_callbacks && need_forkexit_callback) {
+		/*
+		 * modular subsystems can't use callbacks, so no need to lock
+		 * the subsys array
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss->exit) {
+				struct cgroup *old_cgrp =
+					rcu_dereference_raw(cg->subsys[i])->cgroup;
+				struct cgroup *cgrp = task_cgroup(tsk, i);
+				ss->exit(ss, cgrp, old_cgrp, tsk);
+			}
+		}
+	}
 	task_unlock(tsk);
+
 	if (cg)
 		put_css_set_taskexit(cg);
 }
@@ -4813,6 +4818,29 @@ css_get_next(struct cgroup_subsys *ss, int id,
 	return ret;
 }
 
+/*
+ * get corresponding css from file open on cgroupfs directory
+ */
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
+{
+	struct cgroup *cgrp;
+	struct inode *inode;
+	struct cgroup_subsys_state *css;
+
+	inode = f->f_dentry->d_inode;
+	/* check in cgroup filesystem dir */
+	if (inode->i_op != &cgroup_dir_inode_operations)
+		return ERR_PTR(-EBADF);
+
+	if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
+		return ERR_PTR(-EINVAL);
+
+	/* get cgroup */
+	cgrp = __d_cgrp(f->f_dentry);
+	css = cgrp->subsys[id];
+	return css ? css : ERR_PTR(-ENOENT);
+}
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
 						   struct cgroup *cont)
diff --git a/kernel/compat.c b/kernel/compat.c
index c9e2ec0b34a8..38b1d2c1cbe8 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -52,6 +52,64 @@ static int compat_put_timeval(struct compat_timeval __user *o,
 		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
 }
 
+static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
+{
+	memset(txc, 0, sizeof(struct timex));
+
+	if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
+			__get_user(txc->modes, &utp->modes) ||
+			__get_user(txc->offset, &utp->offset) ||
+			__get_user(txc->freq, &utp->freq) ||
+			__get_user(txc->maxerror, &utp->maxerror) ||
+			__get_user(txc->esterror, &utp->esterror) ||
+			__get_user(txc->status, &utp->status) ||
+			__get_user(txc->constant, &utp->constant) ||
+			__get_user(txc->precision, &utp->precision) ||
+			__get_user(txc->tolerance, &utp->tolerance) ||
+			__get_user(txc->time.tv_sec, &utp->time.tv_sec) ||
+			__get_user(txc->time.tv_usec, &utp->time.tv_usec) ||
+			__get_user(txc->tick, &utp->tick) ||
+			__get_user(txc->ppsfreq, &utp->ppsfreq) ||
+			__get_user(txc->jitter, &utp->jitter) ||
+			__get_user(txc->shift, &utp->shift) ||
+			__get_user(txc->stabil, &utp->stabil) ||
+			__get_user(txc->jitcnt, &utp->jitcnt) ||
+			__get_user(txc->calcnt, &utp->calcnt) ||
+			__get_user(txc->errcnt, &utp->errcnt) ||
+			__get_user(txc->stbcnt, &utp->stbcnt))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc)
+{
+	if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
+			__put_user(txc->modes, &utp->modes) ||
+			__put_user(txc->offset, &utp->offset) ||
+			__put_user(txc->freq, &utp->freq) ||
+			__put_user(txc->maxerror, &utp->maxerror) ||
+			__put_user(txc->esterror, &utp->esterror) ||
+			__put_user(txc->status, &utp->status) ||
+			__put_user(txc->constant, &utp->constant) ||
+			__put_user(txc->precision, &utp->precision) ||
+			__put_user(txc->tolerance, &utp->tolerance) ||
+			__put_user(txc->time.tv_sec, &utp->time.tv_sec) ||
+			__put_user(txc->time.tv_usec, &utp->time.tv_usec) ||
+			__put_user(txc->tick, &utp->tick) ||
+			__put_user(txc->ppsfreq, &utp->ppsfreq) ||
+			__put_user(txc->jitter, &utp->jitter) ||
+			__put_user(txc->shift, &utp->shift) ||
+			__put_user(txc->stabil, &utp->stabil) ||
+			__put_user(txc->jitcnt, &utp->jitcnt) ||
+			__put_user(txc->calcnt, &utp->calcnt) ||
+			__put_user(txc->errcnt, &utp->errcnt) ||
+			__put_user(txc->stbcnt, &utp->stbcnt) ||
+			__put_user(txc->tai, &utp->tai))
+		return -EFAULT;
+	return 0;
+}
+
 asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
 		struct timezone __user *tz)
 {
@@ -617,6 +675,29 @@ long compat_sys_clock_gettime(clockid_t which_clock,
 	return err;
 }
 
+long compat_sys_clock_adjtime(clockid_t which_clock,
+		struct compat_timex __user *utp)
+{
+	struct timex txc;
+	mm_segment_t oldfs;
+	int err, ret;
+
+	err = compat_get_timex(&txc, utp);
+	if (err)
+		return err;
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc);
+	set_fs(oldfs);
+
+	err = compat_put_timex(utp, &txc);
+	if (err)
+		return err;
+
+	return ret;
+}
+
 long compat_sys_clock_getres(clockid_t which_clock,
 		struct compat_timespec __user *tp)
 {
@@ -951,58 +1032,17 @@ asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat
 asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
 {
 	struct timex txc;
-	int ret;
-
-	memset(&txc, 0, sizeof(struct timex));
+	int err, ret;
 
-	if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
-			__get_user(txc.modes, &utp->modes) ||
-			__get_user(txc.offset, &utp->offset) ||
-			__get_user(txc.freq, &utp->freq) ||
-			__get_user(txc.maxerror, &utp->maxerror) ||
-			__get_user(txc.esterror, &utp->esterror) ||
-			__get_user(txc.status, &utp->status) ||
-			__get_user(txc.constant, &utp->constant) ||
-			__get_user(txc.precision, &utp->precision) ||
-			__get_user(txc.tolerance, &utp->tolerance) ||
-			__get_user(txc.time.tv_sec, &utp->time.tv_sec) ||
-			__get_user(txc.time.tv_usec, &utp->time.tv_usec) ||
-			__get_user(txc.tick, &utp->tick) ||
-			__get_user(txc.ppsfreq, &utp->ppsfreq) ||
-			__get_user(txc.jitter, &utp->jitter) ||
-			__get_user(txc.shift, &utp->shift) ||
-			__get_user(txc.stabil, &utp->stabil) ||
-			__get_user(txc.jitcnt, &utp->jitcnt) ||
-			__get_user(txc.calcnt, &utp->calcnt) ||
-			__get_user(txc.errcnt, &utp->errcnt) ||
-			__get_user(txc.stbcnt, &utp->stbcnt))
-		return -EFAULT;
+	err = compat_get_timex(&txc, utp);
+	if (err)
+		return err;
 
 	ret = do_adjtimex(&txc);
 
-	if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
-			__put_user(txc.modes, &utp->modes) ||
-			__put_user(txc.offset, &utp->offset) ||
-			__put_user(txc.freq, &utp->freq) ||
-			__put_user(txc.maxerror, &utp->maxerror) ||
-			__put_user(txc.esterror, &utp->esterror) ||
-			__put_user(txc.status, &utp->status) ||
-			__put_user(txc.constant, &utp->constant) ||
-			__put_user(txc.precision, &utp->precision) ||
-			__put_user(txc.tolerance, &utp->tolerance) ||
-			__put_user(txc.time.tv_sec, &utp->time.tv_sec) ||
-			__put_user(txc.time.tv_usec, &utp->time.tv_usec) ||
-			__put_user(txc.tick, &utp->tick) ||
-			__put_user(txc.ppsfreq, &utp->ppsfreq) ||
-			__put_user(txc.jitter, &utp->jitter) ||
-			__put_user(txc.shift, &utp->shift) ||
-			__put_user(txc.stabil, &utp->stabil) ||
-			__put_user(txc.jitcnt, &utp->jitcnt) ||
-			__put_user(txc.calcnt, &utp->calcnt) ||
-			__put_user(txc.errcnt, &utp->errcnt) ||
-			__put_user(txc.stbcnt, &utp->stbcnt) ||
-			__put_user(txc.tai, &utp->tai))
-		ret = -EFAULT;
+	err = compat_put_timex(utp, &txc);
+	if (err)
+		return err;
 
 	return ret;
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4349935c2ad8..e92e98189032 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
 		return -ENODEV;
 
 	trialcs = alloc_trial_cpuset(cs);
-	if (!trialcs)
-		return -ENOMEM;
+	if (!trialcs) {
+		retval = -ENOMEM;
+		goto out;
+	}
 
 	switch (cft->private) {
 	case FILE_CPULIST:
@@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
 	}
 
 	free_trial_cpuset(trialcs);
+out:
 	cgroup_unlock();
 	return retval;
 }
diff --git a/kernel/cred.c b/kernel/cred.c
index 3a9d6dd53a6c..2343c132c5a7 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar;
 static struct thread_group_cred init_tgcred = {
 	.usage	= ATOMIC_INIT(2),
 	.tgid	= 0,
-	.lock	= SPIN_LOCK_UNLOCKED,
+	.lock	= __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
 };
 #endif
 
diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28accd6..bda415715382 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -381,15 +381,16 @@ static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
 	return NULL;
 }
 
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+				      u32 uval, u32 newval)
 {
-	u32 curval;
+	int ret;
 
 	pagefault_disable();
-	curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
 	pagefault_enable();
 
-	return curval;
+	return ret;
 }
 
 static int get_futex_value_locked(u32 *dest, u32 __user *from)
@@ -674,7 +675,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct task_struct *task, int set_waiters)
 {
 	int lock_taken, ret, ownerdied = 0;
-	u32 uval, newval, curval;
+	u32 uval, newval, curval, vpid = task_pid_vnr(task);
 
 retry:
 	ret = lock_taken = 0;
@@ -684,19 +685,17 @@ retry:
 	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
 	 * the locks. It will most likely not succeed.
 	 */
-	newval = task_pid_vnr(task);
+	newval = vpid;
 	if (set_waiters)
 		newval |= FUTEX_WAITERS;
 
-	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
-	if (unlikely(curval == -EFAULT))
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
 		return -EFAULT;
 
 	/*
 	 * Detect deadlocks.
 	 */
-	if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
 		return -EDEADLK;
 
 	/*
@@ -723,14 +722,12 @@ retry:
 	 */
 	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
 		/* Keep the OWNER_DIED bit */
-		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+		newval = (curval & ~FUTEX_TID_MASK) | vpid;
 		ownerdied = 0;
 		lock_taken = 1;
 	}
 
-	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-	if (unlikely(curval == -EFAULT))
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 	if (unlikely(curval != uval))
 		goto retry;
@@ -775,6 +772,24 @@ retry:
 	return ret;
 }
 
+/**
+ * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
+ * @q:	The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be NULL and must be held by the caller.
+ */
+static void __unqueue_futex(struct futex_q *q)
+{
+	struct futex_hash_bucket *hb;
+
+	if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
+			|| plist_node_empty(&q->list)))
+		return;
+
+	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
+	plist_del(&q->list, &hb->chain);
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
@@ -792,7 +807,7 @@ static void wake_futex(struct futex_q *q)
 	 */
 	get_task_struct(p);
 
-	plist_del(&q->list, &q->list.plist);
+	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as
 	 * q->lock_ptr = NULL is written, without taking any locks. A
@@ -843,9 +858,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 
 		newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-		if (curval == -EFAULT)
+		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
 			ret = -EFAULT;
 		else if (curval != uval)
 			ret = -EINVAL;
@@ -880,10 +893,8 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
 	 * There is no waiter, so we unlock the futex. The owner died
 	 * bit has not to be preserved here. We are the owner:
 	 */
-	oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
-	if (oldval == -EFAULT)
-		return oldval;
+	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+		return -EFAULT;
 	if (oldval != uval)
 		return -EAGAIN;
 
@@ -1071,9 +1082,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 		plist_del(&q->list, &hb1->chain);
 		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-		q->list.plist.spinlock = &hb2->lock;
-#endif
 	}
 	get_futex_key_refs(key2);
 	q->key = *key2;
@@ -1100,16 +1108,12 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 	get_futex_key_refs(key);
 	q->key = *key;
 
-	WARN_ON(plist_node_empty(&q->list));
-	plist_del(&q->list, &q->list.plist);
+	__unqueue_futex(q);
 
 	WARN_ON(!q->rt_waiter);
 	q->rt_waiter = NULL;
 
 	q->lock_ptr = &hb->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-	q->list.plist.spinlock = &hb->lock;
-#endif
 
 	wake_up_state(q->task, TASK_NORMAL);
 }
@@ -1457,9 +1461,6 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 	prio = min(current->normal_prio, MAX_RT_PRIO);
 
 	plist_node_init(&q->list, prio);
-#ifdef CONFIG_DEBUG_PI_LIST
-	q->list.plist.spinlock = &hb->lock;
-#endif
 	plist_add(&q->list, &hb->chain);
 	q->task = current;
 	spin_unlock(&hb->lock);
@@ -1504,8 +1505,7 @@ retry:
 			spin_unlock(lock_ptr);
 			goto retry;
 		}
-		WARN_ON(plist_node_empty(&q->list));
-		plist_del(&q->list, &q->list.plist);
+		__unqueue_futex(q);
 
 		BUG_ON(q->pi_state);
 
@@ -1525,8 +1525,7 @@ retry:
 static void unqueue_me_pi(struct futex_q *q)
 	__releases(q->lock_ptr)
 {
-	WARN_ON(plist_node_empty(&q->list));
-	plist_del(&q->list, &q->list.plist);
+	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
 	free_pi_state(q->pi_state);
@@ -1556,10 +1555,10 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 
 	/*
 	 * We are here either because we stole the rtmutex from the
-	 * pending owner or we are the pending owner which failed to
-	 * get the rtmutex. We have to replace the pending owner TID
-	 * in the user space variable. This must be atomic as we have
-	 * to preserve the owner died bit here.
+	 * previous highest priority waiter or we are the highest priority
+	 * waiter but failed to get the rtmutex the first time.
+	 * We have to replace the newowner TID in the user space variable.
+	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
 	 * Note: We write the user space value _before_ changing the pi_state
 	 * because we can fault here. Imagine swapped out pages or a fork
@@ -1578,9 +1577,7 @@ retry:
 	while (1) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-		if (curval == -EFAULT)
+		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
 			goto handle_fault;
 		if (curval == uval)
 			break;
@@ -1608,8 +1605,8 @@ retry:
 
 	/*
 	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the pending
-	 * owner itself or the task which stole the rtmutex) the
+	 * lock here. That gives the other task (either the highest priority
+	 * waiter itself or the task which stole the rtmutex) the
 	 * chance to try the fixup of the pi_state. So once we are
 	 * back from handling the fault we need to check the pi_state
 	 * after reacquiring the hash bucket lock and before trying to
@@ -1685,18 +1682,20 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		/*
 		 * pi_state is incorrect, some other task did a lock steal and
 		 * we returned due to timeout or signal without taking the
-		 * rt_mutex. Too late. We can access the rt_mutex_owner without
-		 * locking, as the other task is now blocked on the hash bucket
-		 * lock. Fix the state up.
+		 * rt_mutex. Too late.
 		 */
+		raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
 		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+		if (!owner)
+			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
+		raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
 		ret = fixup_pi_state_owner(uaddr, q, owner);
 		goto out;
 	}
 
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
-	 * the owner, nor the pending owner, of the rt_mutex.
+	 * the owner of the rt_mutex.
 	 */
 	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
@@ -1781,13 +1780,14 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
 	 *
 	 * The basic logical guarantee of a futex is that it blocks ONLY
 	 * if cond(var) is known to be true at the time of blocking, for
-	 * any cond.  If we queued after testing *uaddr, that would open
-	 * a race condition where we could block indefinitely with
+	 * any cond.  If we locked the hash-bucket after testing *uaddr, that
+	 * would open a race condition where we could block indefinitely with
 	 * cond(var) false, which would violate the guarantee.
 	 *
-	 * A consequence is that futex_wait() can return zero and absorb
-	 * a wakeup when *uaddr != val on entry to the syscall.  This is
-	 * rare, but normal.
+	 * On the other hand, we insert q and release the hash-bucket only
+	 * after testing *uaddr.  This guarantees that futex_wait() will NOT
+	 * absorb a wakeup if *uaddr does not match the desired values
+	 * while the syscall executes.
 	 */
 retry:
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
@@ -2046,9 +2046,9 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	u32 uval;
 	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
+	u32 uval, vpid = task_pid_vnr(current);
 	int ret;
 
 retry:
@@ -2057,7 +2057,7 @@ retry:
 	/*
 	 * We release only a lock we actually own:
 	 */
-	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
+	if ((uval & FUTEX_TID_MASK) != vpid)
 		return -EPERM;
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
@@ -2072,17 +2072,14 @@ retry:
 	 * again. If it succeeds then we can return without waking
 	 * anyone else up:
 	 */
-	if (!(uval & FUTEX_OWNER_DIED))
-		uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0);
-
-
-	if (unlikely(uval == -EFAULT))
+	if (!(uval & FUTEX_OWNER_DIED) &&
+	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
 		goto pi_faulted;
 	/*
 	 * Rare case: we managed to release the lock atomically,
 	 * no need to wake anyone else up:
 	 */
-	if (unlikely(uval == task_pid_vnr(current)))
+	if (unlikely(uval == vpid))
 		goto out_unlock;
 
 	/*
@@ -2167,7 +2164,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 		 * We were woken prior to requeue by a timeout or a signal.
 		 * Unqueue the futex_q and determine which it was.
 		 */
-		plist_del(&q->list, &q->list.plist);
+		plist_del(&q->list, &hb->chain);
 
 		/* Handle spurious wakeups gracefully */
 		ret = -EWOULDBLOCK;
@@ -2463,11 +2460,20 @@ retry:
 		 * userspace.
 		 */
 		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
-		if (nval == -EFAULT)
-			return -1;
-
+		/*
+		 * We are not holding a lock here, but we want to have
+		 * the pagefault_disable/enable() protection because
+		 * we want to handle the fault gracefully. If the
+		 * access fails we try to fault in the futex with R/W
+		 * verification via get_user_pages. get_user() above
+		 * does not guarantee R/W access. If that fails we
+		 * give up and leave the futex locked.
+		 */
+		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+			if (fault_in_user_writeable(uaddr))
+				return -1;
+			goto retry;
+		}
 		if (nval != uval)
 			goto retry;
 
@@ -2678,8 +2684,7 @@ static int __init futex_init(void)
 	 * implementation, the non-functional ones will return
 	 * -ENOSYS.
 	 */
-	curval = cmpxchg_futex_value_locked(NULL, 0, 0);
-	if (curval == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
 	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c048615..9017478c5d4c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -53,11 +53,10 @@
 /*
  * The timer bases:
  *
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
@@ -74,30 +73,39 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get,
 			.resolution = KTIME_LOW_RES,
 		},
+		{
+			.index = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+			.resolution = KTIME_LOW_RES,
+		},
 	}
 };
 
+static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	return hrtimer_clock_to_base_table[clock_id];
+}
+
+
 /*
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
  */
 static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
-	ktime_t xtim, tomono;
-	struct timespec xts, tom;
-	unsigned long seq;
+	ktime_t xtim, mono, boot;
+	struct timespec xts, tom, slp;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		xts = __current_kernel_time();
-		tom = __get_wall_to_monotonic();
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
 
 	xtim = timespec_to_ktime(xts);
-	tomono = timespec_to_ktime(tom);
-	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
-	base->clock_base[CLOCK_MONOTONIC].softirq_time =
-		ktime_add(xtim, tomono);
+	mono = ktime_add(xtim, timespec_to_ktime(tom));
+	boot = ktime_add(mono, timespec_to_ktime(slp));
+	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
 }
 
 /*
@@ -184,10 +192,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 	struct hrtimer_cpu_base *new_cpu_base;
 	int this_cpu = smp_processor_id();
 	int cpu = hrtimer_get_target(this_cpu, pinned);
+	int basenum = hrtimer_clockid_to_base(base->index);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &new_cpu_base->clock_base[base->index];
+	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
 		/*
@@ -334,6 +343,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe);
 
 static struct debug_obj_descr hrtimer_debug_descr;
 
+static void *hrtimer_debug_hint(void *addr)
+{
+	return ((struct hrtimer *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -393,6 +407,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr hrtimer_debug_descr = {
 	.name		= "hrtimer",
+	.debug_hint	= hrtimer_debug_hint,
 	.fixup_init	= hrtimer_fixup_init,
 	.fixup_activate	= hrtimer_fixup_activate,
 	.fixup_free	= hrtimer_fixup_free,
@@ -611,24 +626,23 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base;
-	struct timespec realtime_offset, wtm;
-	unsigned long seq;
+	struct timespec realtime_offset, wtm, sleep;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		wtm = __get_wall_to_monotonic();
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_and_sleep_offset(&realtime_offset, &wtm,
+							&sleep);
 	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
 
 	base = &__get_cpu_var(hrtimer_bases);
 
 	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[CLOCK_REALTIME].offset =
+	base->clock_base[HRTIMER_BASE_REALTIME].offset =
 		timespec_to_ktime(realtime_offset);
+	base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
+		timespec_to_ktime(sleep);
 
 	hrtimer_force_reprogram(base, 0);
 	raw_spin_unlock(&base->lock);
@@ -673,14 +687,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 }
 
 /*
- * Initialize the high resolution related parts of a hrtimer
- */
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
-{
-}
-
-
-/*
  * When High resolution timers are active, try to reprogram. Note, that in case
  * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
  * check happens. The timer gets enqueued into the rbtree. The reprogramming
@@ -725,8 +731,9 @@ static int hrtimer_switch_to_hres(void)
 		return 0;
 	}
 	base->hres_active = 1;
-	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
-	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -750,7 +757,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 	return 0;
 }
 static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -1121,6 +1127,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
@@ -1129,8 +1136,8 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &cpu_base->clock_base[clock_id];
-	hrtimer_init_timer_hres(timer);
+	base = hrtimer_clockid_to_base(clock_id);
+	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
 
 #ifdef CONFIG_TIMER_STATS
@@ -1165,9 +1172,10 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base = hrtimer_clockid_to_base(which_clock);
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
 }
@@ -1714,6 +1722,10 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
 
 void __init hrtimers_init(void)
 {
+	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
+	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+	hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
+
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 8e42fec7686d..09bef82d74cb 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -1,5 +1,6 @@
+# Select this to activate the generic irq options below
 config HAVE_GENERIC_HARDIRQS
-	def_bool n
+	bool
 
 if HAVE_GENERIC_HARDIRQS
 menu "IRQ subsystem"
@@ -11,26 +12,44 @@ config GENERIC_HARDIRQS
 
 # Select this to disable the deprecated stuff
 config GENERIC_HARDIRQS_NO_DEPRECATED
-       def_bool n
+       bool
+
+config GENERIC_HARDIRQS_NO_COMPAT
+       bool
 
 # Options selectable by the architecture code
+
+# Make sparse irq Kconfig switch below available
 config HAVE_SPARSE_IRQ
-       def_bool n
+       bool
 
+# Enable the generic irq autoprobe mechanism
 config GENERIC_IRQ_PROBE
-	def_bool n
+	bool
+
+# Use the generic /proc/interrupts implementation
+config GENERIC_IRQ_SHOW
+       bool
 
+# Support for delayed migration from interrupt context
 config GENERIC_PENDING_IRQ
-	def_bool n
+	bool
 
+# Alpha specific irq affinity mechanism
 config AUTO_IRQ_AFFINITY
-       def_bool n
-
-config IRQ_PER_CPU
-       def_bool n
+       bool
 
+# Tasklet based software resend for pending interrupts on enable_irq()
 config HARDIRQS_SW_RESEND
-       def_bool n
+       bool
+
+# Preflow handler support for fasteoi (sparc64)
+config IRQ_PREFLOW_FASTEOI
+       bool
+
+# Support forced irq threading
+config IRQ_FORCED_THREADING
+       bool
 
 config SPARSE_IRQ
 	bool "Support sparse irq numbering"
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 505798f86c36..394784c57060 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -17,7 +17,7 @@
 /*
  * Autodetection depends on the fact that any interrupt that
  * comes in on to an unassigned handler will get stuck with
- * "IRQ_WAITING" cleared and the interrupt disabled.
+ * "IRQS_WAITING" cleared and the interrupt disabled.
  */
 static DEFINE_MUTEX(probing_active);
 
@@ -32,7 +32,6 @@ unsigned long probe_irq_on(void)
 {
 	struct irq_desc *desc;
 	unsigned long mask = 0;
-	unsigned int status;
 	int i;
 
 	/*
@@ -46,13 +45,7 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc_reverse(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
-			/*
-			 * An old-style architecture might still have
-			 * the handle_bad_irq handler there:
-			 */
-			compat_irq_chip_set_default_handler(desc);
-
+		if (!desc->action && irq_settings_can_probe(desc)) {
 			/*
 			 * Some chips need to know about probing in
 			 * progress:
@@ -60,7 +53,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			desc->irq_data.chip->irq_startup(&desc->irq_data);
+			irq_startup(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -75,10 +68,12 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc_reverse(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
-			desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
-			if (desc->irq_data.chip->irq_startup(&desc->irq_data))
-				desc->status |= IRQ_PENDING;
+		if (!desc->action && irq_settings_can_probe(desc)) {
+			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
+			if (irq_startup(desc)) {
+				irq_compat_set_pending(desc);
+				desc->istate |= IRQS_PENDING;
+			}
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -93,13 +88,12 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
 
-		if (status & IRQ_AUTODETECT) {
+		if (desc->istate & IRQS_AUTODETECT) {
 			/* It triggered already - consider it spurious. */
-			if (!(status & IRQ_WAITING)) {
-				desc->status = status & ~IRQ_AUTODETECT;
-				desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+			if (!(desc->istate & IRQS_WAITING)) {
+				desc->istate &= ~IRQS_AUTODETECT;
+				irq_shutdown(desc);
 			} else
 				if (i < 32)
 					mask |= 1 << i;
@@ -125,20 +119,18 @@ EXPORT_SYMBOL(probe_irq_on);
  */
 unsigned int probe_irq_mask(unsigned long val)
 {
-	unsigned int status, mask = 0;
+	unsigned int mask = 0;
 	struct irq_desc *desc;
 	int i;
 
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
-
-		if (status & IRQ_AUTODETECT) {
-			if (i < 16 && !(status & IRQ_WAITING))
+		if (desc->istate & IRQS_AUTODETECT) {
+			if (i < 16 && !(desc->istate & IRQS_WAITING))
 				mask |= 1 << i;
 
-			desc->status = status & ~IRQ_AUTODETECT;
-			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+			desc->istate &= ~IRQS_AUTODETECT;
+			irq_shutdown(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -169,20 +161,18 @@ int probe_irq_off(unsigned long val)
 {
 	int i, irq_found = 0, nr_of_irqs = 0;
 	struct irq_desc *desc;
-	unsigned int status;
 
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
 
-		if (status & IRQ_AUTODETECT) {
-			if (!(status & IRQ_WAITING)) {
+		if (desc->istate & IRQS_AUTODETECT) {
+			if (!(desc->istate & IRQS_WAITING)) {
 				if (!nr_of_irqs)
 					irq_found = i;
 				nr_of_irqs++;
 			}
-			desc->status = status & ~IRQ_AUTODETECT;
-			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+			desc->istate &= ~IRQS_AUTODETECT;
+			irq_shutdown(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index baa5c4acad83..c9c0601f0615 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -19,140 +19,110 @@
 #include "internals.h"
 
 /**
- *	set_irq_chip - set the irq chip for an irq
+ *	irq_set_chip - set the irq chip for an irq
  *	@irq:	irq number
  *	@chip:	pointer to irq chip description structure
  */
-int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
 
 	if (!chip)
 		chip = &no_irq_chip;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
 	desc->irq_data.chip = chip;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_chip);
+EXPORT_SYMBOL(irq_set_chip);
 
 /**
- *	set_irq_type - set the irq trigger type for an irq
+ *	irq_set_type - set the irq trigger type for an irq
  *	@irq:	irq number
  *	@type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
  */
-int set_irq_type(unsigned int irq, unsigned int type)
+int irq_set_irq_type(unsigned int irq, unsigned int type)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
-	int ret = -ENXIO;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	int ret = 0;
 
-	if (!desc) {
-		printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
-		return -ENODEV;
-	}
+	if (!desc)
+		return -EINVAL;
 
 	type &= IRQ_TYPE_SENSE_MASK;
-	if (type == IRQ_TYPE_NONE)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = __irq_set_trigger(desc, irq, type);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	if (type != IRQ_TYPE_NONE)
+		ret = __irq_set_trigger(desc, irq, type);
+	irq_put_desc_busunlock(desc, flags);
 	return ret;
 }
-EXPORT_SYMBOL(set_irq_type);
+EXPORT_SYMBOL(irq_set_irq_type);
 
 /**
- *	set_irq_data - set irq type data for an irq
+ *	irq_set_handler_data - set irq handler data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to interrupt specific data
  *
  *	Set the hardware irq controller data for an irq
  */
-int set_irq_data(unsigned int irq, void *data)
+int irq_set_handler_data(unsigned int irq, void *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install controller data for IRQ%d\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->irq_data.handler_data = data;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_data);
+EXPORT_SYMBOL(irq_set_handler_data);
 
 /**
- *	set_irq_msi - set MSI descriptor data for an irq
+ *	irq_set_msi_desc - set MSI descriptor data for an irq
  *	@irq:	Interrupt number
  *	@entry:	Pointer to MSI descriptor data
  *
  *	Set the MSI descriptor entry for an irq
  */
-int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install msi data for IRQ%d\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->irq_data.msi_desc = entry;
 	if (entry)
 		entry->irq = irq;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
 
 /**
- *	set_irq_chip_data - set irq chip data for an irq
+ *	irq_set_chip_data - set irq chip data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to chip specific data
  *
  *	Set the hardware irq chip data for an irq
  */
-int set_irq_chip_data(unsigned int irq, void *data)
+int irq_set_chip_data(unsigned int irq, void *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install chip data for IRQ%d\n", irq);
-		return -EINVAL;
-	}
-
-	if (!desc->irq_data.chip) {
-		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->irq_data.chip_data = data;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_chip_data);
+EXPORT_SYMBOL(irq_set_chip_data);
 
 struct irq_data *irq_get_irq_data(unsigned int irq)
 {
@@ -162,72 +132,75 @@ struct irq_data *irq_get_irq_data(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(irq_get_irq_data);
 
-/**
- *	set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
- *
- *	@irq:	Interrupt number
- *	@nest:	0 to clear / 1 to set the IRQ_NESTED_THREAD flag
- *
- *	The IRQ_NESTED_THREAD flag indicates that on
- *	request_threaded_irq() no separate interrupt thread should be
- *	created for the irq as the handler are called nested in the
- *	context of a demultiplexing interrupt handler thread.
- */
-void set_irq_nested_thread(unsigned int irq, int nest)
+static void irq_state_clr_disabled(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc)
-		return;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (nest)
-		desc->status |= IRQ_NESTED_THREAD;
-	else
-		desc->status &= ~IRQ_NESTED_THREAD;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	desc->istate &= ~IRQS_DISABLED;
+	irq_compat_clr_disabled(desc);
 }
-EXPORT_SYMBOL_GPL(set_irq_nested_thread);
 
-/*
- * default enable function
- */
-static void default_enable(struct irq_data *data)
+static void irq_state_set_disabled(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_data_to_desc(data);
+	desc->istate |= IRQS_DISABLED;
+	irq_compat_set_disabled(desc);
+}
 
-	desc->irq_data.chip->irq_unmask(&desc->irq_data);
-	desc->status &= ~IRQ_MASKED;
+static void irq_state_clr_masked(struct irq_desc *desc)
+{
+	desc->istate &= ~IRQS_MASKED;
+	irq_compat_clr_masked(desc);
 }
 
-/*
- * default disable function
- */
-static void default_disable(struct irq_data *data)
+static void irq_state_set_masked(struct irq_desc *desc)
 {
+	desc->istate |= IRQS_MASKED;
+	irq_compat_set_masked(desc);
 }
 
-/*
- * default startup function
- */
-static unsigned int default_startup(struct irq_data *data)
+int irq_startup(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_data_to_desc(data);
+	irq_state_clr_disabled(desc);
+	desc->depth = 0;
+
+	if (desc->irq_data.chip->irq_startup) {
+		int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+		irq_state_clr_masked(desc);
+		return ret;
+	}
 
-	desc->irq_data.chip->irq_enable(data);
+	irq_enable(desc);
 	return 0;
 }
 
-/*
- * default shutdown function
- */
-static void default_shutdown(struct irq_data *data)
+void irq_shutdown(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_data_to_desc(data);
+	irq_state_set_disabled(desc);
+	desc->depth = 1;
+	if (desc->irq_data.chip->irq_shutdown)
+		desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+	if (desc->irq_data.chip->irq_disable)
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
+	else
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
+	irq_state_set_masked(desc);
+}
 
-	desc->irq_data.chip->irq_mask(&desc->irq_data);
-	desc->status |= IRQ_MASKED;
+void irq_enable(struct irq_desc *desc)
+{
+	irq_state_clr_disabled(desc);
+	if (desc->irq_data.chip->irq_enable)
+		desc->irq_data.chip->irq_enable(&desc->irq_data);
+	else
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+	irq_state_clr_masked(desc);
+}
+
+void irq_disable(struct irq_desc *desc)
+{
+	irq_state_set_disabled(desc);
+	if (desc->irq_data.chip->irq_disable) {
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
+		irq_state_set_masked(desc);
+	}
 }
 
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
@@ -315,10 +288,6 @@ static void compat_bus_sync_unlock(struct irq_data *data)
 void irq_chip_set_defaults(struct irq_chip *chip)
 {
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
-	/*
-	 * Compat fixup functions need to be before we set the
-	 * defaults for enable/disable/startup/shutdown
-	 */
 	if (chip->enable)
 		chip->irq_enable = compat_irq_enable;
 	if (chip->disable)
@@ -327,33 +296,8 @@ void irq_chip_set_defaults(struct irq_chip *chip)
 		chip->irq_shutdown = compat_irq_shutdown;
 	if (chip->startup)
 		chip->irq_startup = compat_irq_startup;
-#endif
-	/*
-	 * The real defaults
-	 */
-	if (!chip->irq_enable)
-		chip->irq_enable = default_enable;
-	if (!chip->irq_disable)
-		chip->irq_disable = default_disable;
-	if (!chip->irq_startup)
-		chip->irq_startup = default_startup;
-	/*
-	 * We use chip->irq_disable, when the user provided its own. When
-	 * we have default_disable set for chip->irq_disable, then we need
-	 * to use default_shutdown, otherwise the irq line is not
-	 * disabled on free_irq():
-	 */
-	if (!chip->irq_shutdown)
-		chip->irq_shutdown = chip->irq_disable != default_disable ?
-			chip->irq_disable : default_shutdown;
-
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	if (!chip->end)
 		chip->end = dummy_irq_chip.end;
-
-	/*
-	 * Now fix up the remaining compat handlers
-	 */
 	if (chip->bus_lock)
 		chip->irq_bus_lock = compat_bus_lock;
 	if (chip->bus_sync_unlock)
@@ -388,22 +332,22 @@ static inline void mask_ack_irq(struct irq_desc *desc)
 		if (desc->irq_data.chip->irq_ack)
 			desc->irq_data.chip->irq_ack(&desc->irq_data);
 	}
-	desc->status |= IRQ_MASKED;
+	irq_state_set_masked(desc);
 }
 
-static inline void mask_irq(struct irq_desc *desc)
+void mask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_mask) {
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
-		desc->status |= IRQ_MASKED;
+		irq_state_set_masked(desc);
 	}
 }
 
-static inline void unmask_irq(struct irq_desc *desc)
+void unmask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_unmask) {
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
-		desc->status &= ~IRQ_MASKED;
+		irq_state_clr_masked(desc);
 	}
 }
 
@@ -428,10 +372,11 @@ void handle_nested_irq(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
+	irq_compat_set_progress(desc);
+	desc->istate |= IRQS_INPROGRESS;
 	raw_spin_unlock_irq(&desc->lock);
 
 	action_ret = action->thread_fn(action->irq, action->dev_id);
@@ -439,13 +384,21 @@ void handle_nested_irq(unsigned int irq)
 		note_interrupt(irq, desc, action_ret);
 
 	raw_spin_lock_irq(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
+	desc->istate &= ~IRQS_INPROGRESS;
+	irq_compat_clr_progress(desc);
 
 out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_nested_irq);
 
+static bool irq_check_poll(struct irq_desc *desc)
+{
+	if (!(desc->istate & IRQS_POLL_INPROGRESS))
+		return false;
+	return irq_wait_for_poll(desc);
+}
+
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
  *	@irq:	the interrupt number
@@ -461,29 +414,20 @@ EXPORT_SYMBOL_GPL(handle_nested_irq);
 void
 handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out_unlock;
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
+		if (!irq_check_poll(desc))
+			goto out_unlock;
+
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
-	raw_spin_unlock(&desc->lock);
+	handle_irq_event(desc);
 
-	action_ret = handle_IRQ_event(irq, action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
-
-	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -501,42 +445,42 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
 	raw_spin_lock(&desc->lock);
 	mask_ack_irq(desc);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out_unlock;
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
+		if (!irq_check_poll(desc))
+			goto out_unlock;
+
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
 	 * If its disabled or no action available
 	 * keep it masked and get out of here
 	 */
-	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
-	raw_spin_unlock(&desc->lock);
-
-	action_ret = handle_IRQ_event(irq, action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
+	handle_irq_event(desc);
 
-	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
-
-	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+	if (!(desc->istate & (IRQS_DISABLED | IRQS_ONESHOT)))
 		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_level_irq);
 
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void preflow_handler(struct irq_desc *desc)
+{
+	if (desc->preflow_handler)
+		desc->preflow_handler(&desc->irq_data);
+}
+#else
+static inline void preflow_handler(struct irq_desc *desc) { }
+#endif
+
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
  *	@irq:	the interrupt number
@@ -550,42 +494,41 @@ EXPORT_SYMBOL_GPL(handle_level_irq);
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out;
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
+		if (!irq_check_poll(desc))
+			goto out;
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
 	 * If its disabled or no action available
 	 * then mask it and get out of here:
 	 */
-	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
-		desc->status |= IRQ_PENDING;
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED))) {
+		irq_compat_set_pending(desc);
+		desc->istate |= IRQS_PENDING;
 		mask_irq(desc);
 		goto out;
 	}
 
-	desc->status |= IRQ_INPROGRESS;
-	desc->status &= ~IRQ_PENDING;
-	raw_spin_unlock(&desc->lock);
+	if (desc->istate & IRQS_ONESHOT)
+		mask_irq(desc);
 
-	action_ret = handle_IRQ_event(irq, action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
+	preflow_handler(desc);
+	handle_irq_event(desc);
 
-	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
-out:
+out_eoi:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
-
+out_unlock:
 	raw_spin_unlock(&desc->lock);
+	return;
+out:
+	if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
+		goto out_eoi;
+	goto out_unlock;
 }
 
 /**
@@ -609,32 +552,28 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	/*
 	 * If we're currently running this IRQ, or its disabled,
 	 * we shouldn't process the IRQ. Mark it pending, handle
 	 * the necessary masking and go out
 	 */
-	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
-		    !desc->action)) {
-		desc->status |= (IRQ_PENDING | IRQ_MASKED);
-		mask_ack_irq(desc);
-		goto out_unlock;
+	if (unlikely((desc->istate & (IRQS_DISABLED | IRQS_INPROGRESS) ||
+		      !desc->action))) {
+		if (!irq_check_poll(desc)) {
+			irq_compat_set_pending(desc);
+			desc->istate |= IRQS_PENDING;
+			mask_ack_irq(desc);
+			goto out_unlock;
+		}
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	/* Mark the IRQ currently in progress.*/
-	desc->status |= IRQ_INPROGRESS;
-
 	do {
-		struct irqaction *action = desc->action;
-		irqreturn_t action_ret;
-
-		if (unlikely(!action)) {
+		if (unlikely(!desc->action)) {
 			mask_irq(desc);
 			goto out_unlock;
 		}
@@ -644,22 +583,17 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		 * one, we could have masked the irq.
 		 * Renable it, if it was not disabled in meantime.
 		 */
-		if (unlikely((desc->status &
-			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
-			      (IRQ_PENDING | IRQ_MASKED))) {
-			unmask_irq(desc);
+		if (unlikely(desc->istate & IRQS_PENDING)) {
+			if (!(desc->istate & IRQS_DISABLED) &&
+			    (desc->istate & IRQS_MASKED))
+				unmask_irq(desc);
 		}
 
-		desc->status &= ~IRQ_PENDING;
-		raw_spin_unlock(&desc->lock);
-		action_ret = handle_IRQ_event(irq, action);
-		if (!noirqdebug)
-			note_interrupt(irq, desc, action_ret);
-		raw_spin_lock(&desc->lock);
+		handle_irq_event(desc);
 
-	} while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING);
+	} while ((desc->istate & IRQS_PENDING) &&
+		 !(desc->istate & IRQS_DISABLED));
 
-	desc->status &= ~IRQ_INPROGRESS;
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -674,103 +608,84 @@ out_unlock:
 void
 handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
-	irqreturn_t action_ret;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (desc->irq_data.chip->irq_ack)
-		desc->irq_data.chip->irq_ack(&desc->irq_data);
+	if (chip->irq_ack)
+		chip->irq_ack(&desc->irq_data);
 
-	action_ret = handle_IRQ_event(irq, desc->action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
+	handle_irq_event_percpu(desc, desc->action);
 
-	if (desc->irq_data.chip->irq_eoi)
-		desc->irq_data.chip->irq_eoi(&desc->irq_data);
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
 }
 
 void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install type control for IRQ%d\n", irq);
+	if (!desc)
 		return;
-	}
 
-	if (!handle)
+	if (!handle) {
 		handle = handle_bad_irq;
-	else if (desc->irq_data.chip == &no_irq_chip) {
-		printk(KERN_WARNING "Trying to install %sinterrupt handler "
-		       "for IRQ%d\n", is_chained ? "chained " : "", irq);
-		/*
-		 * Some ARM implementations install a handler for really dumb
-		 * interrupt hardware without setting an irq_chip. This worked
-		 * with the ARM no_irq_chip but the check in setup_irq would
-		 * prevent us to setup the interrupt at all. Switch it to
-		 * dummy_irq_chip for easy transition.
-		 */
-		desc->irq_data.chip = &dummy_irq_chip;
+	} else {
+		if (WARN_ON(desc->irq_data.chip == &no_irq_chip))
+			goto out;
 	}
 
-	chip_bus_lock(desc);
-	raw_spin_lock_irqsave(&desc->lock, flags);
-
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
 		if (desc->irq_data.chip != &no_irq_chip)
 			mask_ack_irq(desc);
-		desc->status |= IRQ_DISABLED;
+		irq_compat_set_disabled(desc);
+		desc->istate |= IRQS_DISABLED;
 		desc->depth = 1;
 	}
 	desc->handle_irq = handle;
 	desc->name = name;
 
 	if (handle != handle_bad_irq && is_chained) {
-		desc->status &= ~IRQ_DISABLED;
-		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
-		desc->depth = 0;
-		desc->irq_data.chip->irq_startup(&desc->irq_data);
+		irq_settings_set_noprobe(desc);
+		irq_settings_set_norequest(desc);
+		irq_startup(desc);
 	}
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(desc);
-}
-EXPORT_SYMBOL_GPL(__set_irq_handler);
-
-void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
-			 irq_flow_handler_t handle)
-{
-	set_irq_chip(irq, chip);
-	__set_irq_handler(irq, handle, 0, NULL);
+out:
+	irq_put_desc_busunlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(__irq_set_handler);
 
 void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 			      irq_flow_handler_t handle, const char *name)
 {
-	set_irq_chip(irq, chip);
-	__set_irq_handler(irq, handle, 0, name);
+	irq_set_chip(irq, chip);
+	__irq_set_handler(irq, handle, 0, name);
 }
 
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
 	if (!desc)
 		return;
+	irq_settings_clr_and_set(desc, clr, set);
+
+	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
+		   IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
+	if (irq_settings_has_no_balance_set(desc))
+		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+	if (irq_settings_is_per_cpu(desc))
+		irqd_set(&desc->irq_data, IRQD_PER_CPU);
+	if (irq_settings_can_move_pcntxt(desc))
+		irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
 
-	/* Sanitize flags */
-	set &= IRQF_MODIFY_MASK;
-	clr &= IRQF_MODIFY_MASK;
+	irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc));
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status &= ~clr;
-	desc->status |= set;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_unlock(desc, flags);
 }
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
new file mode 100644
index 000000000000..6bbaf66aca85
--- /dev/null
+++ b/kernel/irq/compat.h
@@ -0,0 +1,72 @@
+/*
+ * Compat layer for transition period
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline void irq_compat_set_progress(struct irq_desc *desc)
+{
+	desc->status |= IRQ_INPROGRESS;
+}
+
+static inline void irq_compat_clr_progress(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_INPROGRESS;
+}
+static inline void irq_compat_set_disabled(struct irq_desc *desc)
+{
+	desc->status |= IRQ_DISABLED;
+}
+static inline void irq_compat_clr_disabled(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_DISABLED;
+}
+static inline void irq_compat_set_pending(struct irq_desc *desc)
+{
+	desc->status |= IRQ_PENDING;
+}
+
+static inline void irq_compat_clr_pending(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_PENDING;
+}
+static inline void irq_compat_set_masked(struct irq_desc *desc)
+{
+	desc->status |= IRQ_MASKED;
+}
+
+static inline void irq_compat_clr_masked(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_MASKED;
+}
+static inline void irq_compat_set_move_pending(struct irq_desc *desc)
+{
+	desc->status |= IRQ_MOVE_PENDING;
+}
+
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_MOVE_PENDING;
+}
+static inline void irq_compat_set_affinity(struct irq_desc *desc)
+{
+	desc->status |= IRQ_AFFINITY_SET;
+}
+
+static inline void irq_compat_clr_affinity(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_AFFINITY_SET;
+}
+#else
+static inline void irq_compat_set_progress(struct irq_desc *desc) { }
+static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
+static inline void irq_compat_set_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_clr_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_set_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_masked(struct irq_desc *desc) { }
+static inline void irq_compat_clr_masked(struct irq_desc *desc) { }
+static inline void irq_compat_set_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_affinity(struct irq_desc *desc) { }
+static inline void irq_compat_clr_affinity(struct irq_desc *desc) { }
+#endif
+
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
new file mode 100644
index 000000000000..d1a33b7fa61d
--- /dev/null
+++ b/kernel/irq/debug.h
@@ -0,0 +1,40 @@
+/*
+ * Debugging printout:
+ */
+
+#include <linux/kallsyms.h>
+
+#define P(f) if (desc->status & f) printk("%14s set\n", #f)
+#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+
+static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+	printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
+		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
+	printk("->handle_irq():  %p, ", desc->handle_irq);
+	print_symbol("%s\n", (unsigned long)desc->handle_irq);
+	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
+	printk("->action(): %p\n", desc->action);
+	if (desc->action) {
+		printk("->action->handler(): %p, ", desc->action->handler);
+		print_symbol("%s\n", (unsigned long)desc->action->handler);
+	}
+
+	P(IRQ_LEVEL);
+	P(IRQ_PER_CPU);
+	P(IRQ_NOPROBE);
+	P(IRQ_NOREQUEST);
+	P(IRQ_NOAUTOEN);
+
+	PS(IRQS_AUTODETECT);
+	PS(IRQS_INPROGRESS);
+	PS(IRQS_REPLAY);
+	PS(IRQS_WAITING);
+	PS(IRQS_DISABLED);
+	PS(IRQS_PENDING);
+	PS(IRQS_MASKED);
+}
+
+#undef P
+#undef PS
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 3540a7190122..517561fc7317 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -51,30 +51,92 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 	       "but no thread function available.", irq, action->name);
 }
 
-/**
- * handle_IRQ_event - irq action chain handler
- * @irq:	the interrupt number
- * @action:	the interrupt action chain for this irq
- *
- * Handles the action chain of an irq event
- */
-irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
+static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+{
+	/*
+	 * Wake up the handler thread for this action. In case the
+	 * thread crashed and was killed we just pretend that we
+	 * handled the interrupt. The hardirq handler has disabled the
+	 * device interrupt, so no irq storm is lurking. If the
+	 * RUNTHREAD bit is already set, nothing to do.
+	 */
+	if (test_bit(IRQTF_DIED, &action->thread_flags) ||
+	    test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		return;
+
+	/*
+	 * It's safe to OR the mask lockless here. We have only two
+	 * places which write to threads_oneshot: This code and the
+	 * irq thread.
+	 *
+	 * This code is the hard irq context and can never run on two
+	 * cpus in parallel. If it ever does we have more serious
+	 * problems than this bitmask.
+	 *
+	 * The irq threads of this irq which clear their "running" bit
+	 * in threads_oneshot are serialized via desc->lock against
+	 * each other and they are serialized against this code by
+	 * IRQS_INPROGRESS.
+	 *
+	 * Hard irq handler:
+	 *
+	 *	spin_lock(desc->lock);
+	 *	desc->state |= IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *	set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+	 *	desc->threads_oneshot |= mask;
+	 *	spin_lock(desc->lock);
+	 *	desc->state &= ~IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * irq thread:
+	 *
+	 * again:
+	 *	spin_lock(desc->lock);
+	 *	if (desc->state & IRQS_INPROGRESS) {
+	 *		spin_unlock(desc->lock);
+	 *		while(desc->state & IRQS_INPROGRESS)
+	 *			cpu_relax();
+	 *		goto again;
+	 *	}
+	 *	if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	 *		desc->threads_oneshot &= ~mask;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * So either the thread waits for us to clear IRQS_INPROGRESS
+	 * or we are waiting in the flow handler for desc->lock to be
+	 * released before we reach this point. The thread also checks
+	 * IRQTF_RUNTHREAD under desc->lock. If set it leaves
+	 * threads_oneshot untouched and runs the thread another time.
+	 */
+	desc->threads_oneshot |= action->thread_mask;
+	wake_up_process(action->thread);
+}
+
+irqreturn_t
+handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
-	irqreturn_t ret, retval = IRQ_NONE;
-	unsigned int status = 0;
+	irqreturn_t retval = IRQ_NONE;
+	unsigned int random = 0, irq = desc->irq_data.irq;
 
 	do {
+		irqreturn_t res;
+
 		trace_irq_handler_entry(irq, action);
-		ret = action->handler(irq, action->dev_id);
-		trace_irq_handler_exit(irq, action, ret);
+		res = action->handler(irq, action->dev_id);
+		trace_irq_handler_exit(irq, action, res);
 
-		switch (ret) {
+		if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n",
+			      irq, action->handler))
+			local_irq_disable();
+
+		switch (res) {
 		case IRQ_WAKE_THREAD:
 			/*
 			 * Set result to handled so the spurious check
 			 * does not trigger.
 			 */
-			ret = IRQ_HANDLED;
+			res = IRQ_HANDLED;
 
 			/*
 			 * Catch drivers which return WAKE_THREAD but
@@ -85,36 +147,56 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 				break;
 			}
 
-			/*
-			 * Wake up the handler thread for this
-			 * action. In case the thread crashed and was
-			 * killed we just pretend that we handled the
-			 * interrupt. The hardirq handler above has
-			 * disabled the device interrupt, so no irq
-			 * storm is lurking.
-			 */
-			if (likely(!test_bit(IRQTF_DIED,
-					     &action->thread_flags))) {
-				set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
-				wake_up_process(action->thread);
-			}
+			irq_wake_thread(desc, action);
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
-			status |= action->flags;
+			random |= action->flags;
 			break;
 
 		default:
 			break;
 		}
 
-		retval |= ret;
+		retval |= res;
 		action = action->next;
 	} while (action);
 
-	if (status & IRQF_SAMPLE_RANDOM)
+	if (random & IRQF_SAMPLE_RANDOM)
 		add_interrupt_randomness(irq);
-	local_irq_disable();
 
+	if (!noirqdebug)
+		note_interrupt(irq, desc, retval);
 	return retval;
 }
+
+irqreturn_t handle_irq_event(struct irq_desc *desc)
+{
+	struct irqaction *action = desc->action;
+	irqreturn_t ret;
+
+	irq_compat_clr_pending(desc);
+	desc->istate &= ~IRQS_PENDING;
+	irq_compat_set_progress(desc);
+	desc->istate |= IRQS_INPROGRESS;
+	raw_spin_unlock(&desc->lock);
+
+	ret = handle_irq_event_percpu(desc, action);
+
+	raw_spin_lock(&desc->lock);
+	desc->istate &= ~IRQS_INPROGRESS;
+	irq_compat_clr_progress(desc);
+	return ret;
+}
+
+/**
+ * handle_IRQ_event - irq action chain handler
+ * @irq:	the interrupt number
+ * @action:	the interrupt action chain for this irq
+ *
+ * Handles the action chain of an irq event
+ */
+irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
+{
+	return handle_irq_event_percpu(irq_to_desc(irq), action);
+}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4571ae7e085a..6c6ec9a49027 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -1,27 +1,101 @@
 /*
  * IRQ subsystem internal functions and variables:
+ *
+ * Do not ever include this file from anything else than
+ * kernel/irq/. Do not even think about using any information outside
+ * of this file for your non core code.
  */
 #include <linux/irqdesc.h>
 
+#ifdef CONFIG_SPARSE_IRQ
+# define IRQ_BITMAP_BITS	(NR_IRQS + 8196)
+#else
+# define IRQ_BITMAP_BITS	NR_IRQS
+#endif
+
+#define istate core_internal_state__do_not_mess_with_it
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+# define status status_use_accessors
+#endif
+
 extern int noirqdebug;
 
+/*
+ * Bits used by threaded handlers:
+ * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
+ * IRQTF_DIED      - handler thread died
+ * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
+ * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
+ * IRQTF_FORCED_THREAD  - irq action is force threaded
+ */
+enum {
+	IRQTF_RUNTHREAD,
+	IRQTF_DIED,
+	IRQTF_WARNED,
+	IRQTF_AFFINITY,
+	IRQTF_FORCED_THREAD,
+};
+
+/*
+ * Bit masks for desc->state
+ *
+ * IRQS_AUTODETECT		- autodetection in progress
+ * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
+ *				  detection
+ * IRQS_POLL_INPROGRESS		- polling in progress
+ * IRQS_INPROGRESS		- Interrupt in progress
+ * IRQS_ONESHOT			- irq is not unmasked in primary handler
+ * IRQS_REPLAY			- irq is replayed
+ * IRQS_WAITING			- irq is waiting
+ * IRQS_DISABLED		- irq is disabled
+ * IRQS_PENDING			- irq is pending and replayed later
+ * IRQS_MASKED			- irq is masked
+ * IRQS_SUSPENDED		- irq is suspended
+ */
+enum {
+	IRQS_AUTODETECT		= 0x00000001,
+	IRQS_SPURIOUS_DISABLED	= 0x00000002,
+	IRQS_POLL_INPROGRESS	= 0x00000008,
+	IRQS_INPROGRESS		= 0x00000010,
+	IRQS_ONESHOT		= 0x00000020,
+	IRQS_REPLAY		= 0x00000040,
+	IRQS_WAITING		= 0x00000080,
+	IRQS_DISABLED		= 0x00000100,
+	IRQS_PENDING		= 0x00000200,
+	IRQS_MASKED		= 0x00000400,
+	IRQS_SUSPENDED		= 0x00000800,
+};
+
+#include "compat.h"
+#include "debug.h"
+#include "settings.h"
+
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
 
 /* Set default functions for irq_chip structures: */
 extern void irq_chip_set_defaults(struct irq_chip *chip);
 
-/* Set default handler: */
-extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
-
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
+extern int irq_startup(struct irq_desc *desc);
+extern void irq_shutdown(struct irq_desc *desc);
+extern void irq_enable(struct irq_desc *desc);
+extern void irq_disable(struct irq_desc *desc);
+extern void mask_irq(struct irq_desc *desc);
+extern void unmask_irq(struct irq_desc *desc);
+
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
+irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action);
+irqreturn_t handle_irq_event(struct irq_desc *desc);
+
 /* Resending of interrupts :*/
 void check_irq_resend(struct irq_desc *desc, unsigned int irq);
+bool irq_wait_for_poll(struct irq_desc *desc);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
@@ -37,20 +111,10 @@ static inline void unregister_handler_proc(unsigned int irq,
 					   struct irqaction *action) { }
 #endif
 
-extern int irq_select_affinity_usr(unsigned int irq);
+extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
-static inline void irq_end(unsigned int irq, struct irq_desc *desc)
-{
-	if (desc->irq_data.chip && desc->irq_data.chip->end)
-		desc->irq_data.chip->end(irq);
-}
-#else
-static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
-#endif
-
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
@@ -64,43 +128,60 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
+struct irq_desc *
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus);
+void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
+
+static inline struct irq_desc *
+irq_get_desc_buslock(unsigned int irq, unsigned long *flags)
+{
+	return __irq_get_desc_lock(irq, flags, true);
+}
+
+static inline void
+irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
+{
+	__irq_put_desc_unlock(desc, flags, true);
+}
+
+static inline struct irq_desc *
+irq_get_desc_lock(unsigned int irq, unsigned long *flags)
+{
+	return __irq_get_desc_lock(irq, flags, false);
+}
+
+static inline void
+irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
+{
+	__irq_put_desc_unlock(desc, flags, false);
+}
+
 /*
- * Debugging printout:
+ * Manipulation functions for irq_data.state
  */
+static inline void irqd_set_move_pending(struct irq_data *d)
+{
+	d->state_use_accessors |= IRQD_SETAFFINITY_PENDING;
+	irq_compat_set_move_pending(irq_data_to_desc(d));
+}
 
-#include <linux/kallsyms.h>
-
-#define P(f) if (desc->status & f) printk("%14s set\n", #f)
+static inline void irqd_clr_move_pending(struct irq_data *d)
+{
+	d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
+	irq_compat_clr_move_pending(irq_data_to_desc(d));
+}
 
-static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
+static inline void irqd_clear(struct irq_data *d, unsigned int mask)
 {
-	printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
-		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
-	printk("->handle_irq():  %p, ", desc->handle_irq);
-	print_symbol("%s\n", (unsigned long)desc->handle_irq);
-	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
-	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
-	printk("->action(): %p\n", desc->action);
-	if (desc->action) {
-		printk("->action->handler(): %p, ", desc->action->handler);
-		print_symbol("%s\n", (unsigned long)desc->action->handler);
-	}
-
-	P(IRQ_INPROGRESS);
-	P(IRQ_DISABLED);
-	P(IRQ_PENDING);
-	P(IRQ_REPLAY);
-	P(IRQ_AUTODETECT);
-	P(IRQ_WAITING);
-	P(IRQ_LEVEL);
-	P(IRQ_MASKED);
-#ifdef CONFIG_IRQ_PER_CPU
-	P(IRQ_PER_CPU);
-#endif
-	P(IRQ_NOPROBE);
-	P(IRQ_NOREQUEST);
-	P(IRQ_NOAUTOEN);
+	d->state_use_accessors &= ~mask;
 }
 
-#undef P
+static inline void irqd_set(struct irq_data *d, unsigned int mask)
+{
+	d->state_use_accessors |= mask;
+}
 
+static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
+{
+	return d->state_use_accessors & mask;
+}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 282f20230e67..dbccc799407f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -79,7 +79,8 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
 	desc->irq_data.chip_data = NULL;
 	desc->irq_data.handler_data = NULL;
 	desc->irq_data.msi_desc = NULL;
-	desc->status = IRQ_DEFAULT_INIT_FLAGS;
+	irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
+	desc->istate = IRQS_DISABLED;
 	desc->handle_irq = handle_bad_irq;
 	desc->depth = 1;
 	desc->irq_count = 0;
@@ -94,7 +95,7 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 
 #ifdef CONFIG_SPARSE_IRQ
 
@@ -206,6 +207,14 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 	return NULL;
 }
 
+static int irq_expand_nr_irqs(unsigned int nr)
+{
+	if (nr > IRQ_BITMAP_BITS)
+		return -ENOMEM;
+	nr_irqs = nr;
+	return 0;
+}
+
 int __init early_irq_init(void)
 {
 	int i, initcnt, node = first_online_node;
@@ -217,6 +226,15 @@ int __init early_irq_init(void)
 	initcnt = arch_probe_nr_irqs();
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
 
+	if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
+		nr_irqs = IRQ_BITMAP_BITS;
+
+	if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
+		initcnt = IRQ_BITMAP_BITS;
+
+	if (initcnt > nr_irqs)
+		nr_irqs = initcnt;
+
 	for (i = 0; i < initcnt; i++) {
 		desc = alloc_desc(i, node);
 		set_bit(i, allocated_irqs);
@@ -229,7 +247,7 @@ int __init early_irq_init(void)
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
-		.status		= IRQ_DEFAULT_INIT_FLAGS,
+		.istate		= IRQS_DISABLED,
 		.handle_irq	= handle_bad_irq,
 		.depth		= 1,
 		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
@@ -251,8 +269,8 @@ int __init early_irq_init(void)
 	for (i = 0; i < count; i++) {
 		desc[i].irq_data.irq = i;
 		desc[i].irq_data.chip = &no_irq_chip;
-		/* TODO : do this allocation on-demand ... */
 		desc[i].kstat_irqs = alloc_percpu(unsigned int);
+		irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
 		alloc_masks(desc + i, GFP_KERNEL, node);
 		desc_smp_init(desc + i, node);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
@@ -277,24 +295,14 @@ static void free_desc(unsigned int irq)
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
 {
-#if defined(CONFIG_KSTAT_IRQS_ONDEMAND)
-	struct irq_desc *desc;
-	unsigned int i;
-
-	for (i = 0; i < cnt; i++) {
-		desc = irq_to_desc(start + i);
-		if (desc && !desc->kstat_irqs) {
-			unsigned int __percpu *stats = alloc_percpu(unsigned int);
-
-			if (!stats)
-				return -1;
-			if (cmpxchg(&desc->kstat_irqs, NULL, stats) != NULL)
-				free_percpu(stats);
-		}
-	}
-#endif
 	return start;
 }
+
+static int irq_expand_nr_irqs(unsigned int nr)
+{
+	return -ENOMEM;
+}
+
 #endif /* !CONFIG_SPARSE_IRQ */
 
 /* Dynamic interrupt handling */
@@ -338,14 +346,17 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
 
 	mutex_lock(&sparse_irq_lock);
 
-	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
+					   from, cnt, 0);
 	ret = -EEXIST;
 	if (irq >=0 && start != irq)
 		goto err;
 
-	ret = -ENOMEM;
-	if (start >= nr_irqs)
-		goto err;
+	if (start + cnt > nr_irqs) {
+		ret = irq_expand_nr_irqs(start + cnt);
+		if (ret)
+			goto err;
+	}
 
 	bitmap_set(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
@@ -392,6 +403,26 @@ unsigned int irq_get_next_irq(unsigned int offset)
 	return find_next_bit(allocated_irqs, nr_irqs, offset);
 }
 
+struct irq_desc *
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		if (bus)
+			chip_bus_lock(desc);
+		raw_spin_lock_irqsave(&desc->lock, *flags);
+	}
+	return desc;
+}
+
+void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
+{
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	if (bus)
+		chip_bus_sync_unlock(desc);
+}
+
 /**
  * dynamic_irq_cleanup - cleanup a dynamically allocated irq
  * @irq:	irq number to initialize
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0caa59f747dd..acd599a43bfb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,17 @@
 
 #include "internals.h"
 
+#ifdef CONFIG_IRQ_FORCED_THREADING
+__read_mostly bool force_irqthreads;
+
+static int __init setup_forced_irqthreads(char *arg)
+{
+	force_irqthreads = true;
+	return 0;
+}
+early_param("threadirqs", setup_forced_irqthreads);
+#endif
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -30,7 +41,7 @@
 void synchronize_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned int status;
+	unsigned int state;
 
 	if (!desc)
 		return;
@@ -42,16 +53,16 @@ void synchronize_irq(unsigned int irq)
 		 * Wait until we're out of the critical section.  This might
 		 * give the wrong answer due to the lack of memory barriers.
 		 */
-		while (desc->status & IRQ_INPROGRESS)
+		while (desc->istate & IRQS_INPROGRESS)
 			cpu_relax();
 
 		/* Ok, that indicated we're done: double-check carefully. */
 		raw_spin_lock_irqsave(&desc->lock, flags);
-		status = desc->status;
+		state = desc->istate;
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 		/* Oops, that failed? */
-	} while (status & IRQ_INPROGRESS);
+	} while (state & IRQS_INPROGRESS);
 
 	/*
 	 * We made sure that no hardirq handler is running. Now verify
@@ -73,8 +84,8 @@ int irq_can_set_affinity(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
-	    !desc->irq_data.chip->irq_set_affinity)
+	if (!desc || !irqd_can_balance(&desc->irq_data) ||
+	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
 		return 0;
 
 	return 1;
@@ -100,67 +111,169 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 	}
 }
 
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool irq_can_move_pcntxt(struct irq_desc *desc)
+{
+	return irq_settings_can_move_pcntxt(desc);
+}
+static inline bool irq_move_pending(struct irq_desc *desc)
+{
+	return irqd_is_setaffinity_pending(&desc->irq_data);
+}
+static inline void
+irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
+{
+	cpumask_copy(desc->pending_mask, mask);
+}
+static inline void
+irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
+{
+	cpumask_copy(mask, desc->pending_mask);
+}
+#else
+static inline bool irq_can_move_pcntxt(struct irq_desc *desc) { return true; }
+static inline bool irq_move_pending(struct irq_desc *desc) { return false; }
+static inline void
+irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { }
+static inline void
+irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
+#endif
+
 /**
  *	irq_set_affinity - Set the irq affinity of a given irq
  *	@irq:		Interrupt to set affinity
  *	@cpumask:	cpumask
  *
  */
-int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_chip *chip = desc->irq_data.chip;
 	unsigned long flags;
+	int ret = 0;
 
 	if (!chip->irq_set_affinity)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PCNTXT) {
-		if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
-			cpumask_copy(desc->irq_data.affinity, cpumask);
+	if (irq_can_move_pcntxt(desc)) {
+		ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+		switch (ret) {
+		case IRQ_SET_MASK_OK:
+			cpumask_copy(desc->irq_data.affinity, mask);
+		case IRQ_SET_MASK_OK_NOCOPY:
 			irq_set_thread_affinity(desc);
+			ret = 0;
 		}
+	} else {
+		irqd_set_move_pending(&desc->irq_data);
+		irq_copy_pending(desc, mask);
 	}
-	else {
-		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(desc->pending_mask, cpumask);
-	}
-#else
-	if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
-		cpumask_copy(desc->irq_data.affinity, cpumask);
-		irq_set_thread_affinity(desc);
+
+	if (desc->affinity_notify) {
+		kref_get(&desc->affinity_notify->kref);
+		schedule_work(&desc->affinity_notify->work);
 	}
-#endif
-	desc->status |= IRQ_AFFINITY_SET;
+	irq_compat_set_affinity(desc);
+	irqd_set(&desc->irq_data, IRQD_AFFINITY_SET);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return 0;
+	return ret;
 }
 
 int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 {
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+
+	if (!desc)
+		return -EINVAL;
+	desc->affinity_hint = m;
+	irq_put_desc_unlock(desc, flags);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+
+static void irq_affinity_notify(struct work_struct *work)
+{
+	struct irq_affinity_notify *notify =
+		container_of(work, struct irq_affinity_notify, work);
+	struct irq_desc *desc = irq_to_desc(notify->irq);
+	cpumask_var_t cpumask;
+	unsigned long flags;
+
+	if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		goto out;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	if (irq_move_pending(desc))
+		irq_get_pending(cpumask, desc);
+	else
+		cpumask_copy(cpumask, desc->irq_data.affinity);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	notify->notify(notify, cpumask);
+
+	free_cpumask_var(cpumask);
+out:
+	kref_put(&notify->kref, notify->release);
+}
+
+/**
+ *	irq_set_affinity_notifier - control notification of IRQ affinity changes
+ *	@irq:		Interrupt for which to enable/disable notification
+ *	@notify:	Context for notification, or %NULL to disable
+ *			notification.  Function pointers must be initialised;
+ *			the other fields will be initialised by this function.
+ *
+ *	Must be called in process context.  Notification may only be enabled
+ *	after the IRQ is allocated and must be disabled before the IRQ is
+ *	freed using free_irq().
+ */
+int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
+{
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_affinity_notify *old_notify;
 	unsigned long flags;
 
+	/* The release function is promised process context */
+	might_sleep();
+
 	if (!desc)
 		return -EINVAL;
 
+	/* Complete initialisation of *notify */
+	if (notify) {
+		notify->irq = irq;
+		kref_init(&notify->kref);
+		INIT_WORK(&notify->work, irq_affinity_notify);
+	}
+
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->affinity_hint = m;
+	old_notify = desc->affinity_notify;
+	desc->affinity_notify = notify;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
+	if (old_notify)
+		kref_put(&old_notify->kref, old_notify->release);
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 
 #ifndef CONFIG_AUTO_IRQ_AFFINITY
 /*
  * Generic version of the affinity autoselector.
  */
-static int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct cpumask *set = irq_default_affinity;
+	int ret;
+
+	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
 		return 0;
 
@@ -168,22 +281,29 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 	 * Preserve an userspace affinity setup, but make sure that
 	 * one of the targets is online.
 	 */
-	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
-		    < nr_cpu_ids)
-			goto set_affinity;
-		else
-			desc->status &= ~IRQ_AFFINITY_SET;
+	if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
+		if (cpumask_intersects(desc->irq_data.affinity,
+				       cpu_online_mask))
+			set = desc->irq_data.affinity;
+		else {
+			irq_compat_clr_affinity(desc);
+			irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
+		}
 	}
 
-	cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
-set_affinity:
-	desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
-
+	cpumask_and(mask, cpu_online_mask, set);
+	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		cpumask_copy(desc->irq_data.affinity, mask);
+	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_set_thread_affinity(desc);
+	}
 	return 0;
 }
 #else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask)
 {
 	return irq_select_affinity(irq);
 }
@@ -192,23 +312,21 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
 /*
  * Called when affinity is set via /proc/irq
  */
-int irq_select_affinity_usr(unsigned int irq)
+int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 	int ret;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = setup_affinity(irq, desc);
-	if (!ret)
-		irq_set_thread_affinity(desc);
+	ret = setup_affinity(irq, desc, mask);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
 	return ret;
 }
 
 #else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
 	return 0;
 }
@@ -219,13 +337,23 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 	if (suspend) {
 		if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
 			return;
-		desc->status |= IRQ_SUSPENDED;
+		desc->istate |= IRQS_SUSPENDED;
 	}
 
-	if (!desc->depth++) {
-		desc->status |= IRQ_DISABLED;
-		desc->irq_data.chip->irq_disable(&desc->irq_data);
-	}
+	if (!desc->depth++)
+		irq_disable(desc);
+}
+
+static int __disable_irq_nosync(unsigned int irq)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+
+	if (!desc)
+		return -EINVAL;
+	__disable_irq(desc, irq, false);
+	irq_put_desc_busunlock(desc, flags);
+	return 0;
 }
 
 /**
@@ -241,17 +369,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
  */
 void disable_irq_nosync(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc)
-		return;
-
-	chip_bus_lock(desc);
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	__disable_irq(desc, irq, false);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(desc);
+	__disable_irq_nosync(irq);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -269,21 +387,24 @@ EXPORT_SYMBOL(disable_irq_nosync);
  */
 void disable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (!desc)
-		return;
-
-	disable_irq_nosync(irq);
-	if (desc->action)
+	if (!__disable_irq_nosync(irq))
 		synchronize_irq(irq);
 }
 EXPORT_SYMBOL(disable_irq);
 
 void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
-	if (resume)
-		desc->status &= ~IRQ_SUSPENDED;
+	if (resume) {
+		if (!(desc->istate & IRQS_SUSPENDED)) {
+			if (!desc->action)
+				return;
+			if (!(desc->action->flags & IRQF_FORCE_RESUME))
+				return;
+			/* Pretend that it got disabled ! */
+			desc->depth++;
+		}
+		desc->istate &= ~IRQS_SUSPENDED;
+	}
 
 	switch (desc->depth) {
 	case 0:
@@ -291,12 +412,11 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
-		unsigned int status = desc->status & ~IRQ_DISABLED;
-
-		if (desc->status & IRQ_SUSPENDED)
+		if (desc->istate & IRQS_SUSPENDED)
 			goto err_out;
 		/* Prevent probing on this irq: */
-		desc->status = status | IRQ_NOPROBE;
+		irq_settings_set_noprobe(desc);
+		irq_enable(desc);
 		check_irq_resend(desc, irq);
 		/* fall-through */
 	}
@@ -318,21 +438,18 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  */
 void enable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 
 	if (!desc)
 		return;
+	if (WARN(!desc->irq_data.chip,
+		 KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
+		goto out;
 
-	if (WARN(!desc->irq_data.chip || !desc->irq_data.chip->irq_enable,
-	    KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
-		return;
-
-	chip_bus_lock(desc);
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(desc);
+out:
+	irq_put_desc_busunlock(desc, flags);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -348,7 +465,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 }
 
 /**
- *	set_irq_wake - control irq power management wakeup
+ *	irq_set_irq_wake - control irq power management wakeup
  *	@irq:	interrupt to control
  *	@on:	enable/disable power management wakeup
  *
@@ -359,23 +476,22 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
  *	Wakeup mode lets this IRQ wake the system from sleep
  *	states like "suspend to RAM".
  */
-int set_irq_wake(unsigned int irq, unsigned int on)
+int irq_set_irq_wake(unsigned int irq, unsigned int on)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 	int ret = 0;
 
 	/* wakeup-capable irqs can be shared between drivers that
 	 * don't need to have the same sleep mode behaviors.
 	 */
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (on) {
 		if (desc->wake_depth++ == 0) {
 			ret = set_irq_wake_real(irq, on);
 			if (ret)
 				desc->wake_depth = 0;
 			else
-				desc->status |= IRQ_WAKEUP;
+				irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
 		}
 	} else {
 		if (desc->wake_depth == 0) {
@@ -385,14 +501,13 @@ int set_irq_wake(unsigned int irq, unsigned int on)
 			if (ret)
 				desc->wake_depth = 1;
 			else
-				desc->status &= ~IRQ_WAKEUP;
+				irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
 		}
 	}
-
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_busunlock(desc, flags);
 	return ret;
 }
-EXPORT_SYMBOL(set_irq_wake);
+EXPORT_SYMBOL(irq_set_irq_wake);
 
 /*
  * Internal function that tells the architecture code whether a
@@ -401,43 +516,27 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irqaction *action;
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	int canrequest = 0;
 
 	if (!desc)
 		return 0;
 
-	if (desc->status & IRQ_NOREQUEST)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	action = desc->action;
-	if (action)
-		if (irqflags & action->flags & IRQF_SHARED)
-			action = NULL;
-
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
-	return !action;
-}
-
-void compat_irq_chip_set_default_handler(struct irq_desc *desc)
-{
-	/*
-	 * If the architecture still has not overriden
-	 * the flow handler then zap the default. This
-	 * should catch incorrect flow-type setting.
-	 */
-	if (desc->handle_irq == &handle_bad_irq)
-		desc->handle_irq = NULL;
+	if (irq_settings_can_request(desc)) {
+		if (desc->action)
+			if (irqflags & desc->action->flags & IRQF_SHARED)
+				canrequest =1;
+	}
+	irq_put_desc_unlock(desc, flags);
+	return canrequest;
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		      unsigned long flags)
 {
-	int ret;
 	struct irq_chip *chip = desc->irq_data.chip;
+	int ret, unmask = 0;
 
 	if (!chip || !chip->irq_set_type) {
 		/*
@@ -449,23 +548,43 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		return 0;
 	}
 
+	flags &= IRQ_TYPE_SENSE_MASK;
+
+	if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
+		if (!(desc->istate & IRQS_MASKED))
+			mask_irq(desc);
+		if (!(desc->istate & IRQS_DISABLED))
+			unmask = 1;
+	}
+
 	/* caller masked out all except trigger mode flags */
 	ret = chip->irq_set_type(&desc->irq_data, flags);
 
-	if (ret)
-		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
-		       flags, irq, chip->irq_set_type);
-	else {
-		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
-			flags |= IRQ_LEVEL;
-		/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
-		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
-		desc->status |= flags;
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
+		irqd_set(&desc->irq_data, flags);
+
+	case IRQ_SET_MASK_OK_NOCOPY:
+		flags = irqd_get_trigger_type(&desc->irq_data);
+		irq_settings_set_trigger_mask(desc, flags);
+		irqd_clear(&desc->irq_data, IRQD_LEVEL);
+		irq_settings_clr_level(desc);
+		if (flags & IRQ_TYPE_LEVEL_MASK) {
+			irq_settings_set_level(desc);
+			irqd_set(&desc->irq_data, IRQD_LEVEL);
+		}
 
 		if (chip != desc->irq_data.chip)
 			irq_chip_set_defaults(desc->irq_data.chip);
+		ret = 0;
+		break;
+	default:
+		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		       flags, irq, chip->irq_set_type);
 	}
-
+	if (unmask)
+		unmask_irq(desc);
 	return ret;
 }
 
@@ -509,8 +628,11 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  * handler finished. unmask if the interrupt has not been disabled and
  * is marked MASKED.
  */
-static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
+static void irq_finalize_oneshot(struct irq_desc *desc,
+				 struct irqaction *action, bool force)
 {
+	if (!(desc->istate & IRQS_ONESHOT))
+		return;
 again:
 	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
@@ -522,26 +644,44 @@ again:
 	 * The thread is faster done than the hard interrupt handler
 	 * on the other CPU. If we unmask the irq line then the
 	 * interrupt can come in again and masks the line, leaves due
-	 * to IRQ_INPROGRESS and the irq line is masked forever.
+	 * to IRQS_INPROGRESS and the irq line is masked forever.
+	 *
+	 * This also serializes the state of shared oneshot handlers
+	 * versus "desc->threads_onehsot |= action->thread_mask;" in
+	 * irq_wake_thread(). See the comment there which explains the
+	 * serialization.
 	 */
-	if (unlikely(desc->status & IRQ_INPROGRESS)) {
+	if (unlikely(desc->istate & IRQS_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
 		chip_bus_sync_unlock(desc);
 		cpu_relax();
 		goto again;
 	}
 
-	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
-		desc->status &= ~IRQ_MASKED;
+	/*
+	 * Now check again, whether the thread should run. Otherwise
+	 * we would clear the threads_oneshot bit of this thread which
+	 * was just set.
+	 */
+	if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		goto out_unlock;
+
+	desc->threads_oneshot &= ~action->thread_mask;
+
+	if (!desc->threads_oneshot && !(desc->istate & IRQS_DISABLED) &&
+	    (desc->istate & IRQS_MASKED)) {
+		irq_compat_clr_masked(desc);
+		desc->istate &= ~IRQS_MASKED;
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
+out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
 	chip_bus_sync_unlock(desc);
 }
 
 #ifdef CONFIG_SMP
 /*
- * Check whether we need to change the affinity of the interrupt thread.
+ * Check whether we need to chasnge the affinity of the interrupt thread.
  */
 static void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
@@ -573,6 +713,32 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
 #endif
 
 /*
+ * Interrupts which are not explicitely requested as threaded
+ * interrupts rely on the implicit bh/preempt disable of the hard irq
+ * context. So we need to disable bh here to avoid deadlocks and other
+ * side effects.
+ */
+static void
+irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	local_bh_disable();
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+	local_bh_enable();
+}
+
+/*
+ * Interrupts explicitely requested as threaded interupts want to be
+ * preemtible - many of them need to sleep and wait for slow busses to
+ * complete.
+ */
+static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+}
+
+/*
  * Interrupt handler thread
  */
 static int irq_thread(void *data)
@@ -582,7 +748,14 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake, oneshot = desc->status & IRQ_ONESHOT;
+	void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+	int wake;
+
+	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
+					&action->thread_flags))
+		handler_fn = irq_forced_thread_fn;
+	else
+		handler_fn = irq_thread_fn;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -594,23 +767,20 @@ static int irq_thread(void *data)
 		atomic_inc(&desc->threads_active);
 
 		raw_spin_lock_irq(&desc->lock);
-		if (unlikely(desc->status & IRQ_DISABLED)) {
+		if (unlikely(desc->istate & IRQS_DISABLED)) {
 			/*
 			 * CHECKME: We might need a dedicated
 			 * IRQ_THREAD_PENDING flag here, which
 			 * retriggers the thread in check_irq_resend()
-			 * but AFAICT IRQ_PENDING should be fine as it
+			 * but AFAICT IRQS_PENDING should be fine as it
 			 * retriggers the interrupt itself --- tglx
 			 */
-			desc->status |= IRQ_PENDING;
+			irq_compat_set_pending(desc);
+			desc->istate |= IRQS_PENDING;
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
 			raw_spin_unlock_irq(&desc->lock);
-
-			action->thread_fn(action->irq, action->dev_id);
-
-			if (oneshot)
-				irq_finalize_oneshot(action->irq, desc);
+			handler_fn(desc, action);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -619,6 +789,9 @@ static int irq_thread(void *data)
 			wake_up(&desc->wait_for_threads);
 	}
 
+	/* Prevent a stale desc->threads_oneshot */
+	irq_finalize_oneshot(desc, action, true);
+
 	/*
 	 * Clear irqaction. Otherwise exit_irq_thread() would make
 	 * fuzz about an active irq thread going into nirvana.
@@ -633,6 +806,7 @@ static int irq_thread(void *data)
 void exit_irq_thread(void)
 {
 	struct task_struct *tsk = current;
+	struct irq_desc *desc;
 
 	if (!tsk->irqaction)
 		return;
@@ -641,6 +815,14 @@ void exit_irq_thread(void)
 	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
 	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
 
+	desc = irq_to_desc(tsk->irqaction->irq);
+
+	/*
+	 * Prevent a stale desc->threads_oneshot. Must be called
+	 * before setting the IRQTF_DIED flag.
+	 */
+	irq_finalize_oneshot(desc, tsk->irqaction, true);
+
 	/*
 	 * Set the THREAD DIED flag to prevent further wakeups of the
 	 * soon to be gone threaded handler.
@@ -648,6 +830,22 @@ void exit_irq_thread(void)
 	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
 }
 
+static void irq_setup_forced_threading(struct irqaction *new)
+{
+	if (!force_irqthreads)
+		return;
+	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
+		return;
+
+	new->flags |= IRQF_ONESHOT;
+
+	if (!new->thread_fn) {
+		set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
+		new->thread_fn = new->handler;
+		new->handler = irq_default_primary_handler;
+	}
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -657,9 +855,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
 	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
-	unsigned long flags;
-	int nested, shared = 0;
-	int ret;
+	unsigned long flags, thread_mask = 0;
+	int ret, nested, shared = 0;
+	cpumask_var_t mask;
 
 	if (!desc)
 		return -EINVAL;
@@ -683,15 +881,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		rand_initialize_irq(irq);
 	}
 
-	/* Oneshot interrupts are not allowed with shared */
-	if ((new->flags & IRQF_ONESHOT) && (new->flags & IRQF_SHARED))
-		return -EINVAL;
-
 	/*
 	 * Check whether the interrupt nests into another interrupt
 	 * thread.
 	 */
-	nested = desc->status & IRQ_NESTED_THREAD;
+	nested = irq_settings_is_nested_thread(desc);
 	if (nested) {
 		if (!new->thread_fn)
 			return -EINVAL;
@@ -701,6 +895,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * dummy function which warns when called.
 		 */
 		new->handler = irq_nested_primary_handler;
+	} else {
+		irq_setup_forced_threading(new);
 	}
 
 	/*
@@ -724,6 +920,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		new->thread = t;
 	}
 
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out_thread;
+	}
+
 	/*
 	 * The following block of code has to be executed atomically
 	 */
@@ -735,29 +936,40 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * Can't share interrupts unless both agree to and are
 		 * the same type (level, edge, polarity). So both flag
 		 * fields must have IRQF_SHARED set and the bits which
-		 * set the trigger type must match.
+		 * set the trigger type must match. Also all must
+		 * agree on ONESHOT.
 		 */
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
-		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) {
+		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
+		    ((old->flags ^ new->flags) & IRQF_ONESHOT)) {
 			old_name = old->name;
 			goto mismatch;
 		}
 
-#if defined(CONFIG_IRQ_PER_CPU)
 		/* All handlers must agree on per-cpuness */
 		if ((old->flags & IRQF_PERCPU) !=
 		    (new->flags & IRQF_PERCPU))
 			goto mismatch;
-#endif
 
 		/* add new interrupt at end of irq queue */
 		do {
+			thread_mask |= old->thread_mask;
 			old_ptr = &old->next;
 			old = *old_ptr;
 		} while (old);
 		shared = 1;
 	}
 
+	/*
+	 * Setup the thread mask for this irqaction. Unlikely to have
+	 * 32 resp 64 irqs sharing one line, but who knows.
+	 */
+	if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
+		ret = -EBUSY;
+		goto out_mask;
+	}
+	new->thread_mask = 1 << ffz(thread_mask);
+
 	if (!shared) {
 		irq_chip_set_defaults(desc->irq_data.chip);
 
@@ -769,42 +981,44 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 					new->flags & IRQF_TRIGGER_MASK);
 
 			if (ret)
-				goto out_thread;
-		} else
-			compat_irq_chip_set_default_handler(desc);
-#if defined(CONFIG_IRQ_PER_CPU)
-		if (new->flags & IRQF_PERCPU)
-			desc->status |= IRQ_PER_CPU;
-#endif
+				goto out_mask;
+		}
 
-		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT |
-				  IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
+		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
+				  IRQS_INPROGRESS | IRQS_ONESHOT | \
+				  IRQS_WAITING);
+
+		if (new->flags & IRQF_PERCPU) {
+			irqd_set(&desc->irq_data, IRQD_PER_CPU);
+			irq_settings_set_per_cpu(desc);
+		}
 
 		if (new->flags & IRQF_ONESHOT)
-			desc->status |= IRQ_ONESHOT;
+			desc->istate |= IRQS_ONESHOT;
 
-		if (!(desc->status & IRQ_NOAUTOEN)) {
-			desc->depth = 0;
-			desc->status &= ~IRQ_DISABLED;
-			desc->irq_data.chip->irq_startup(&desc->irq_data);
-		} else
+		if (irq_settings_can_autoenable(desc))
+			irq_startup(desc);
+		else
 			/* Undo nested disables: */
 			desc->depth = 1;
 
 		/* Exclude IRQ from balancing if requested */
-		if (new->flags & IRQF_NOBALANCING)
-			desc->status |= IRQ_NO_BALANCING;
+		if (new->flags & IRQF_NOBALANCING) {
+			irq_settings_set_no_balancing(desc);
+			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+		}
 
 		/* Set default affinity mask once everything is setup */
-		setup_affinity(irq, desc);
-
-	} else if ((new->flags & IRQF_TRIGGER_MASK)
-			&& (new->flags & IRQF_TRIGGER_MASK)
-				!= (desc->status & IRQ_TYPE_SENSE_MASK)) {
-		/* hope the handler works with the actual trigger mode... */
-		pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
-				irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
-				(int)(new->flags & IRQF_TRIGGER_MASK));
+		setup_affinity(irq, desc, mask);
+
+	} else if (new->flags & IRQF_TRIGGER_MASK) {
+		unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
+		unsigned int omsk = irq_settings_get_trigger_mask(desc);
+
+		if (nmsk != omsk)
+			/* hope the handler works with current  trigger mode */
+			pr_warning("IRQ %d uses trigger mode %u; requested %u\n",
+				   irq, nmsk, omsk);
 	}
 
 	new->irq = irq;
@@ -818,8 +1032,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 * Check whether we disabled the irq via the spurious handler
 	 * before. Reenable it and give it another chance.
 	 */
-	if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
-		desc->status &= ~IRQ_SPURIOUS_DISABLED;
+	if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
+		desc->istate &= ~IRQS_SPURIOUS_DISABLED;
 		__enable_irq(desc, irq, false);
 	}
 
@@ -849,6 +1063,9 @@ mismatch:
 #endif
 	ret = -EBUSY;
 
+out_mask:
+	free_cpumask_var(mask);
+
 out_thread:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	if (new->thread) {
@@ -871,9 +1088,14 @@ out_thread:
  */
 int setup_irq(unsigned int irq, struct irqaction *act)
 {
+	int retval;
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	return __setup_irq(irq, desc, act);
+	chip_bus_lock(desc);
+	retval = __setup_irq(irq, desc, act);
+	chip_bus_sync_unlock(desc);
+
+	return retval;
 }
 EXPORT_SYMBOL_GPL(setup_irq);
 
@@ -924,13 +1146,8 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 #endif
 
 	/* If this was the last handler, shut down the IRQ line: */
-	if (!desc->action) {
-		desc->status |= IRQ_DISABLED;
-		if (desc->irq_data.chip->irq_shutdown)
-			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
-		else
-			desc->irq_data.chip->irq_disable(&desc->irq_data);
-	}
+	if (!desc->action)
+		irq_shutdown(desc);
 
 #ifdef CONFIG_SMP
 	/* make sure affinity_hint is cleaned up */
@@ -1004,6 +1221,11 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (!desc)
 		return;
 
+#ifdef CONFIG_SMP
+	if (WARN_ON(desc->affinity_notify))
+		desc->affinity_notify = NULL;
+#endif
+
 	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
 	chip_bus_sync_unlock(desc);
@@ -1074,7 +1296,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->status & IRQ_NOREQUEST)
+	if (!irq_settings_can_request(desc))
 		return -EINVAL;
 
 	if (!handler) {
@@ -1100,7 +1322,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	if (retval)
 		kfree(action);
 
-#ifdef CONFIG_DEBUG_SHIRQ
+#ifdef CONFIG_DEBUG_SHIRQ_FIXME
 	if (!retval && (irqflags & IRQF_SHARED)) {
 		/*
 		 * It's a shared IRQ -- the driver ought to be prepared for it
@@ -1149,7 +1371,7 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->status & IRQ_NESTED_THREAD) {
+	if (irq_settings_is_nested_thread(desc)) {
 		ret = request_threaded_irq(irq, NULL, handler,
 					   flags, name, dev_id);
 		return !ret ? IRQC_IS_NESTED : ret;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 441fd629ff04..ec4806d4778b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -4,23 +4,23 @@
 
 #include "internals.h"
 
-void move_masked_irq(int irq)
+void irq_move_masked_irq(struct irq_data *idata)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_chip *chip = desc->irq_data.chip;
+	struct irq_desc *desc = irq_data_to_desc(idata);
+	struct irq_chip *chip = idata->chip;
 
-	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
 		return;
 
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (CHECK_IRQ_PER_CPU(desc->status)) {
+	if (!irqd_can_balance(&desc->irq_data)) {
 		WARN_ON(1);
 		return;
 	}
 
-	desc->status &= ~IRQ_MOVE_PENDING;
+	irqd_clr_move_pending(&desc->irq_data);
 
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
@@ -53,15 +53,20 @@ void move_masked_irq(int irq)
 	cpumask_clear(desc->pending_mask);
 }
 
-void move_native_irq(int irq)
+void move_masked_irq(int irq)
+{
+	irq_move_masked_irq(irq_get_irq_data(irq));
+}
+
+void irq_move_irq(struct irq_data *idata)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(idata);
 	bool masked;
 
-	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+	if (likely(!irqd_is_setaffinity_pending(idata)))
 		return;
 
-	if (unlikely(desc->status & IRQ_DISABLED))
+	if (unlikely(desc->istate & IRQS_DISABLED))
 		return;
 
 	/*
@@ -69,10 +74,15 @@ void move_native_irq(int irq)
 	 * threaded interrupt with ONESHOT set, we can end up with an
 	 * interrupt storm.
 	 */
-	masked = desc->status & IRQ_MASKED;
+	masked = desc->istate & IRQS_MASKED;
 	if (!masked)
-		desc->irq_data.chip->irq_mask(&desc->irq_data);
-	move_masked_irq(irq);
+		idata->chip->irq_mask(idata);
+	irq_move_masked_irq(idata);
 	if (!masked)
-		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+		idata->chip->irq_unmask(idata);
+}
+
+void move_native_irq(int irq)
+{
+	irq_move_irq(irq_get_irq_data(irq));
 }
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 0d4005d85b03..f76fc00c9877 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -18,7 +18,7 @@
  * During system-wide suspend or hibernation device drivers need to be prevented
  * from receiving interrupts and this function is provided for this purpose.
  * It marks all interrupt lines in use, except for the timer ones, as disabled
- * and sets the IRQ_SUSPENDED flag for each of them.
+ * and sets the IRQS_SUSPENDED flag for each of them.
  */
 void suspend_device_irqs(void)
 {
@@ -34,7 +34,7 @@ void suspend_device_irqs(void)
 	}
 
 	for_each_irq_desc(irq, desc)
-		if (desc->status & IRQ_SUSPENDED)
+		if (desc->istate & IRQS_SUSPENDED)
 			synchronize_irq(irq);
 }
 EXPORT_SYMBOL_GPL(suspend_device_irqs);
@@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(suspend_device_irqs);
  * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
  *
  * Enable all interrupt lines previously disabled by suspend_device_irqs() that
- * have the IRQ_SUSPENDED flag set.
+ * have the IRQS_SUSPENDED flag set.
  */
 void resume_device_irqs(void)
 {
@@ -53,9 +53,6 @@ void resume_device_irqs(void)
 	for_each_irq_desc(irq, desc) {
 		unsigned long flags;
 
-		if (!(desc->status & IRQ_SUSPENDED))
-			continue;
-
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		__enable_irq(desc, irq, true);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -71,9 +68,24 @@ int check_wakeup_irqs(void)
 	struct irq_desc *desc;
 	int irq;
 
-	for_each_irq_desc(irq, desc)
-		if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING))
-			return -EBUSY;
+	for_each_irq_desc(irq, desc) {
+		if (irqd_is_wakeup_set(&desc->irq_data)) {
+			if (desc->istate & IRQS_PENDING)
+				return -EBUSY;
+			continue;
+		}
+		/*
+		 * Check the non wakeup interrupts whether they need
+		 * to be masked before finally going into suspend
+		 * state. That's for hardware which has no wakeup
+		 * source configuration facility. The chip
+		 * implementation indicates that with
+		 * IRQCHIP_MASK_ON_SUSPEND.
+		 */
+		if (desc->istate & IRQS_SUSPENDED &&
+		    irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+			mask_irq(desc);
+	}
 
 	return 0;
 }
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6c8a2a9f8a7b..4cc2e5ed0bec 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -11,6 +11,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
 
 #include "internals.h"
 
@@ -24,7 +25,7 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v)
 	const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PENDING)
+	if (irqd_is_setaffinity_pending(&desc->irq_data))
 		mask = desc->pending_mask;
 #endif
 	seq_cpumask(m, mask);
@@ -65,8 +66,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
-	    irq_balancing_disabled(irq))
+	if (!irq_can_set_affinity(irq) || no_irq_affinity)
 		return -EIO;
 
 	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
@@ -89,7 +89,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	if (!cpumask_intersects(new_value, cpu_online_mask)) {
 		/* Special case for empty set - allow the architecture
 		   code to set default SMP affinity. */
-		err = irq_select_affinity_usr(irq) ? -EINVAL : count;
+		err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count;
 	} else {
 		irq_set_affinity(irq, new_value);
 		err = count;
@@ -357,3 +357,65 @@ void init_irq_proc(void)
 	}
 }
 
+#ifdef CONFIG_GENERIC_IRQ_SHOW
+
+int __weak arch_show_interrupts(struct seq_file *p, int prec)
+{
+	return 0;
+}
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+	static int prec;
+
+	unsigned long flags, any_count = 0;
+	int i = *(loff_t *) v, j;
+	struct irqaction *action;
+	struct irq_desc *desc;
+
+	if (i > nr_irqs)
+		return 0;
+
+	if (i == nr_irqs)
+		return arch_show_interrupts(p, prec);
+
+	/* print header and calculate the width of the first column */
+	if (i == 0) {
+		for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+			j *= 10;
+
+		seq_printf(p, "%*s", prec + 8, "");
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%-8d", j);
+		seq_putc(p, '\n');
+	}
+
+	desc = irq_to_desc(i);
+	if (!desc)
+		return 0;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	for_each_online_cpu(j)
+		any_count |= kstat_irqs_cpu(i, j);
+	action = desc->action;
+	if (!action && !any_count)
+		goto out;
+
+	seq_printf(p, "%*d: ", prec, i);
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+	seq_printf(p, " %8s", desc->irq_data.chip->name);
+	seq_printf(p, "-%-8s", desc->name);
+
+	if (action) {
+		seq_printf(p, "  %s", action->name);
+		while ((action = action->next) != NULL)
+			seq_printf(p, ", %s", action->name);
+	}
+
+	seq_putc(p, '\n');
+out:
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	return 0;
+}
+#endif
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 891115a929aa..ad683a99b1ec 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -23,7 +23,7 @@
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 
 /* Bitmap to handle software resend of interrupts: */
-static DECLARE_BITMAP(irqs_resend, NR_IRQS);
+static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
 
 /*
  * Run software resends of IRQ's
@@ -55,20 +55,19 @@ static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0);
  */
 void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 {
-	unsigned int status = desc->status;
-
-	/*
-	 * Make sure the interrupt is enabled, before resending it:
-	 */
-	desc->irq_data.chip->irq_enable(&desc->irq_data);
-
 	/*
 	 * We do not resend level type interrupts. Level type
 	 * interrupts are resent by hardware when they are still
 	 * active.
 	 */
-	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
-		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
+	if (irq_settings_is_level(desc))
+		return;
+	if (desc->istate & IRQS_REPLAY)
+		return;
+	if (desc->istate & IRQS_PENDING) {
+		irq_compat_clr_pending(desc);
+		desc->istate &= ~IRQS_PENDING;
+		desc->istate |= IRQS_REPLAY;
 
 		if (!desc->irq_data.chip->irq_retrigger ||
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
new file mode 100644
index 000000000000..0227ad358272
--- /dev/null
+++ b/kernel/irq/settings.h
@@ -0,0 +1,138 @@
+/*
+ * Internal header to deal with irq_desc->status which will be renamed
+ * to irq_desc->settings.
+ */
+enum {
+	_IRQ_DEFAULT_INIT_FLAGS	= IRQ_DEFAULT_INIT_FLAGS,
+	_IRQ_PER_CPU		= IRQ_PER_CPU,
+	_IRQ_LEVEL		= IRQ_LEVEL,
+	_IRQ_NOPROBE		= IRQ_NOPROBE,
+	_IRQ_NOREQUEST		= IRQ_NOREQUEST,
+	_IRQ_NOAUTOEN		= IRQ_NOAUTOEN,
+	_IRQ_MOVE_PCNTXT	= IRQ_MOVE_PCNTXT,
+	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
+	_IRQ_NESTED_THREAD	= IRQ_NESTED_THREAD,
+	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
+};
+
+#define IRQ_INPROGRESS		GOT_YOU_MORON
+#define IRQ_REPLAY		GOT_YOU_MORON
+#define IRQ_WAITING		GOT_YOU_MORON
+#define IRQ_DISABLED		GOT_YOU_MORON
+#define IRQ_PENDING		GOT_YOU_MORON
+#define IRQ_MASKED		GOT_YOU_MORON
+#define IRQ_WAKEUP		GOT_YOU_MORON
+#define IRQ_MOVE_PENDING	GOT_YOU_MORON
+#define IRQ_PER_CPU		GOT_YOU_MORON
+#define IRQ_NO_BALANCING	GOT_YOU_MORON
+#define IRQ_AFFINITY_SET	GOT_YOU_MORON
+#define IRQ_LEVEL		GOT_YOU_MORON
+#define IRQ_NOPROBE		GOT_YOU_MORON
+#define IRQ_NOREQUEST		GOT_YOU_MORON
+#define IRQ_NOAUTOEN		GOT_YOU_MORON
+#define IRQ_NESTED_THREAD	GOT_YOU_MORON
+#undef IRQF_MODIFY_MASK
+#define IRQF_MODIFY_MASK	GOT_YOU_MORON
+
+static inline void
+irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
+{
+	desc->status &= ~(clr & _IRQF_MODIFY_MASK);
+	desc->status |= (set & _IRQF_MODIFY_MASK);
+}
+
+static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_no_balancing(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NO_BALANCING;
+}
+
+static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_NO_BALANCING;
+}
+
+static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc)
+{
+	return desc->status & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline void
+irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask)
+{
+	desc->status &= ~IRQ_TYPE_SENSE_MASK;
+	desc->status |= mask & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline bool irq_settings_is_level(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_LEVEL;
+}
+
+static inline void irq_settings_clr_level(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_LEVEL;
+}
+
+static inline void irq_settings_set_level(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_LEVEL;
+}
+
+static inline bool irq_settings_can_request(struct irq_desc *desc)
+{
+	return !(desc->status & _IRQ_NOREQUEST);
+}
+
+static inline void irq_settings_clr_norequest(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_NOREQUEST;
+}
+
+static inline void irq_settings_set_norequest(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NOREQUEST;
+}
+
+static inline bool irq_settings_can_probe(struct irq_desc *desc)
+{
+	return !(desc->status & _IRQ_NOPROBE);
+}
+
+static inline void irq_settings_clr_noprobe(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_NOPROBE;
+}
+
+static inline void irq_settings_set_noprobe(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NOPROBE;
+}
+
+static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_MOVE_PCNTXT;
+}
+
+static inline bool irq_settings_can_autoenable(struct irq_desc *desc)
+{
+	return !(desc->status & _IRQ_NOAUTOEN);
+}
+
+static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_NESTED_THREAD;
+}
+
+/* Nothing should touch desc->status from now on */
+#undef status
+#define status		USE_THE_PROPER_WRAPPERS_YOU_MORON
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 3089d3b9d5f3..dd586ebf9c8c 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -21,70 +21,94 @@ static int irqfixup __read_mostly;
 #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
 static void poll_spurious_irqs(unsigned long dummy);
 static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
+static int irq_poll_cpu;
+static atomic_t irq_poll_active;
+
+/*
+ * We wait here for a poller to finish.
+ *
+ * If the poll runs on this CPU, then we yell loudly and return
+ * false. That will leave the interrupt line disabled in the worst
+ * case, but it should never happen.
+ *
+ * We wait until the poller is done and then recheck disabled and
+ * action (about to be disabled). Only if it's still active, we return
+ * true and let the handler run.
+ */
+bool irq_wait_for_poll(struct irq_desc *desc)
+{
+	if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
+		      "irq poll in progress on cpu %d for irq %d\n",
+		      smp_processor_id(), desc->irq_data.irq))
+		return false;
+
+#ifdef CONFIG_SMP
+	do {
+		raw_spin_unlock(&desc->lock);
+		while (desc->istate & IRQS_INPROGRESS)
+			cpu_relax();
+		raw_spin_lock(&desc->lock);
+	} while (desc->istate & IRQS_INPROGRESS);
+	/* Might have been disabled in meantime */
+	return !(desc->istate & IRQS_DISABLED) && desc->action;
+#else
+	return false;
+#endif
+}
+
 
 /*
  * Recovery handler for misrouted interrupts.
  */
-static int try_one_irq(int irq, struct irq_desc *desc)
+static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 {
+	irqreturn_t ret = IRQ_NONE;
 	struct irqaction *action;
-	int ok = 0, work = 0;
 
 	raw_spin_lock(&desc->lock);
-	/* Already running on another processor */
-	if (desc->status & IRQ_INPROGRESS) {
-		/*
-		 * Already running: If it is shared get the other
-		 * CPU to go looking for our mystery interrupt too
-		 */
-		if (desc->action && (desc->action->flags & IRQF_SHARED))
-			desc->status |= IRQ_PENDING;
-		raw_spin_unlock(&desc->lock);
-		return ok;
-	}
-	/* Honour the normal IRQ locking */
-	desc->status |= IRQ_INPROGRESS;
-	action = desc->action;
-	raw_spin_unlock(&desc->lock);
 
-	while (action) {
-		/* Only shared IRQ handlers are safe to call */
-		if (action->flags & IRQF_SHARED) {
-			if (action->handler(irq, action->dev_id) ==
-				IRQ_HANDLED)
-				ok = 1;
-		}
-		action = action->next;
-	}
-	local_irq_disable();
-	/* Now clean up the flags */
-	raw_spin_lock(&desc->lock);
-	action = desc->action;
+	/* PER_CPU and nested thread interrupts are never polled */
+	if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc))
+		goto out;
 
 	/*
-	 * While we were looking for a fixup someone queued a real
-	 * IRQ clashing with our walk:
+	 * Do not poll disabled interrupts unless the spurious
+	 * disabled poller asks explicitely.
 	 */
-	while ((desc->status & IRQ_PENDING) && action) {
+	if ((desc->istate & IRQS_DISABLED) && !force)
+		goto out;
+
+	/*
+	 * All handlers must agree on IRQF_SHARED, so we test just the
+	 * first. Check for action->next as well.
+	 */
+	action = desc->action;
+	if (!action || !(action->flags & IRQF_SHARED) ||
+	    (action->flags & __IRQF_TIMER) || !action->next)
+		goto out;
+
+	/* Already running on another processor */
+	if (desc->istate & IRQS_INPROGRESS) {
 		/*
-		 * Perform real IRQ processing for the IRQ we deferred
+		 * Already running: If it is shared get the other
+		 * CPU to go looking for our mystery interrupt too
 		 */
-		work = 1;
-		raw_spin_unlock(&desc->lock);
-		handle_IRQ_event(irq, action);
-		raw_spin_lock(&desc->lock);
-		desc->status &= ~IRQ_PENDING;
+		irq_compat_set_pending(desc);
+		desc->istate |= IRQS_PENDING;
+		goto out;
 	}
-	desc->status &= ~IRQ_INPROGRESS;
-	/*
-	 * If we did actual work for the real IRQ line we must let the
-	 * IRQ controller clean up too
-	 */
-	if (work)
-		irq_end(irq, desc);
-	raw_spin_unlock(&desc->lock);
 
-	return ok;
+	/* Mark it poll in progress */
+	desc->istate |= IRQS_POLL_INPROGRESS;
+	do {
+		if (handle_irq_event(desc) == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+		action = desc->action;
+	} while ((desc->istate & IRQS_PENDING) && action);
+	desc->istate &= ~IRQS_POLL_INPROGRESS;
+out:
+	raw_spin_unlock(&desc->lock);
+	return ret == IRQ_HANDLED;
 }
 
 static int misrouted_irq(int irq)
@@ -92,6 +116,11 @@ static int misrouted_irq(int irq)
 	struct irq_desc *desc;
 	int i, ok = 0;
 
+	if (atomic_inc_return(&irq_poll_active) == 1)
+		goto out;
+
+	irq_poll_cpu = smp_processor_id();
+
 	for_each_irq_desc(i, desc) {
 		if (!i)
 			 continue;
@@ -99,9 +128,11 @@ static int misrouted_irq(int irq)
 		if (i == irq)	/* Already tried */
 			continue;
 
-		if (try_one_irq(i, desc))
+		if (try_one_irq(i, desc, false))
 			ok = 1;
 	}
+out:
+	atomic_dec(&irq_poll_active);
 	/* So the caller can adjust the irq error counts */
 	return ok;
 }
@@ -111,23 +142,28 @@ static void poll_spurious_irqs(unsigned long dummy)
 	struct irq_desc *desc;
 	int i;
 
+	if (atomic_inc_return(&irq_poll_active) != 1)
+		goto out;
+	irq_poll_cpu = smp_processor_id();
+
 	for_each_irq_desc(i, desc) {
-		unsigned int status;
+		unsigned int state;
 
 		if (!i)
 			 continue;
 
 		/* Racy but it doesn't matter */
-		status = desc->status;
+		state = desc->istate;
 		barrier();
-		if (!(status & IRQ_SPURIOUS_DISABLED))
+		if (!(state & IRQS_SPURIOUS_DISABLED))
 			continue;
 
 		local_irq_disable();
-		try_one_irq(i, desc);
+		try_one_irq(i, desc, true);
 		local_irq_enable();
 	}
-
+out:
+	atomic_dec(&irq_poll_active);
 	mod_timer(&poll_spurious_irq_timer,
 		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
@@ -139,15 +175,13 @@ static void poll_spurious_irqs(unsigned long dummy)
  *
  * (The other 100-of-100,000 interrupts may have been a correctly
  *  functioning device sharing an IRQ with the failing one)
- *
- * Called under desc->lock
  */
-
 static void
 __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 		 irqreturn_t action_ret)
 {
 	struct irqaction *action;
+	unsigned long flags;
 
 	if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
 		printk(KERN_ERR "irq event %d: bogus return value %x\n",
@@ -159,6 +193,13 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 	dump_stack();
 	printk(KERN_ERR "handlers:\n");
 
+	/*
+	 * We need to take desc->lock here. note_interrupt() is called
+	 * w/o desc->lock held, but IRQ_PROGRESS set. We might race
+	 * with something else removing an action. It's ok to take
+	 * desc->lock here. See synchronize_irq().
+	 */
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	action = desc->action;
 	while (action) {
 		printk(KERN_ERR "[<%p>]", action->handler);
@@ -167,6 +208,7 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 		printk("\n");
 		action = action->next;
 	}
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 static void
@@ -218,6 +260,9 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
+	if (desc->istate & IRQS_POLL_INPROGRESS)
+		return;
+
 	if (unlikely(action_ret != IRQ_HANDLED)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
@@ -254,9 +299,9 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		 * Now kill the IRQ
 		 */
 		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
-		desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
+		desc->istate |= IRQS_SPURIOUS_DISABLED;
 		desc->depth++;
-		desc->irq_data.chip->irq_disable(&desc->irq_data);
+		irq_disable(desc);
 
 		mod_timer(&poll_spurious_irq_timer,
 			  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 999835b6112b..ed253aa24ba4 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,13 +38,96 @@
 
 #include <asm/irq_regs.h>
 
+struct remote_function_call {
+	struct task_struct *p;
+	int (*func)(void *info);
+	void *info;
+	int ret;
+};
+
+static void remote_function(void *data)
+{
+	struct remote_function_call *tfc = data;
+	struct task_struct *p = tfc->p;
+
+	if (p) {
+		tfc->ret = -EAGAIN;
+		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+			return;
+	}
+
+	tfc->ret = tfc->func(tfc->info);
+}
+
+/**
+ * task_function_call - call a function on the cpu on which a task runs
+ * @p:		the task to evaluate
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ *
+ * returns: @func return value, or
+ *	    -ESRCH  - when the process isn't running
+ *	    -EAGAIN - when the process moved away
+ */
+static int
+task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+{
+	struct remote_function_call data = {
+		.p = p,
+		.func = func,
+		.info = info,
+		.ret = -ESRCH, /* No such (running) process */
+	};
+
+	if (task_curr(p))
+		smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+
+	return data.ret;
+}
+
+/**
+ * cpu_function_call - call a function on the cpu
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func on the remote cpu.
+ *
+ * returns: @func return value or -ENXIO when the cpu is offline
+ */
+static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+{
+	struct remote_function_call data = {
+		.p = NULL,
+		.func = func,
+		.info = info,
+		.ret = -ENXIO, /* No such CPU */
+	};
+
+	smp_call_function_single(cpu, remote_function, &data, 1);
+
+	return data.ret;
+}
+
+#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
+		       PERF_FLAG_FD_OUTPUT  |\
+		       PERF_FLAG_PID_CGROUP)
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
-atomic_t perf_task_events __read_mostly;
+/*
+ * perf_sched_events : >0 events exist
+ * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
+ */
+atomic_t perf_sched_events __read_mostly;
+static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
@@ -67,7 +150,24 @@ int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 /*
  * max perf event sample rate
  */
-int sysctl_perf_event_sample_rate __read_mostly = 100000;
+#define DEFAULT_MAX_SAMPLE_RATE 100000
+int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
+static int max_samples_per_tick __read_mostly =
+	DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+
+int perf_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (ret || !write)
+		return ret;
+
+	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+
+	return 0;
+}
 
 static atomic64_t perf_event_id;
 
@@ -75,7 +175,11 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			      enum event_type_t event_type);
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type);
+			     enum event_type_t event_type,
+			     struct task_struct *task);
+
+static void update_context_time(struct perf_event_context *ctx);
+static u64 perf_event_time(struct perf_event *event);
 
 void __weak perf_event_print_debug(void)	{ }
 
@@ -89,6 +193,360 @@ static inline u64 perf_clock(void)
 	return local_clock();
 }
 
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+#ifdef CONFIG_CGROUP_PERF
+
+/*
+ * Must ensure cgroup is pinned (css_get) before calling
+ * this function. In other words, we cannot call this function
+ * if there is no cgroup event for the current CPU context.
+ */
+static inline struct perf_cgroup *
+perf_cgroup_from_task(struct task_struct *task)
+{
+	return container_of(task_subsys_state(task, perf_subsys_id),
+			struct perf_cgroup, css);
+}
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+
+	return !event->cgrp || event->cgrp == cpuctx->cgrp;
+}
+
+static inline void perf_get_cgroup(struct perf_event *event)
+{
+	css_get(&event->cgrp->css);
+}
+
+static inline void perf_put_cgroup(struct perf_event *event)
+{
+	css_put(&event->cgrp->css);
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{
+	perf_put_cgroup(event);
+	event->cgrp = NULL;
+}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+	return event->cgrp != NULL;
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+	struct perf_cgroup_info *t;
+
+	t = per_cpu_ptr(event->cgrp->info, event->cpu);
+	return t->time;
+}
+
+static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
+{
+	struct perf_cgroup_info *info;
+	u64 now;
+
+	now = perf_clock();
+
+	info = this_cpu_ptr(cgrp->info);
+
+	info->time += now - info->timestamp;
+	info->timestamp = now;
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
+	if (cgrp_out)
+		__update_cgrp_time(cgrp_out);
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+	struct perf_cgroup *cgrp;
+
+	/*
+	 * ensure we access cgroup data only when needed and
+	 * when we know the cgroup is pinned (css_get)
+	 */
+	if (!is_cgroup_event(event))
+		return;
+
+	cgrp = perf_cgroup_from_task(current);
+	/*
+	 * Do not update time when cgroup is not active
+	 */
+	if (cgrp == event->cgrp)
+		__update_cgrp_time(event->cgrp);
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+			  struct perf_event_context *ctx)
+{
+	struct perf_cgroup *cgrp;
+	struct perf_cgroup_info *info;
+
+	/*
+	 * ctx->lock held by caller
+	 * ensure we do not access cgroup data
+	 * unless we have the cgroup pinned (css_get)
+	 */
+	if (!task || !ctx->nr_cgroups)
+		return;
+
+	cgrp = perf_cgroup_from_task(task);
+	info = this_cpu_ptr(cgrp->info);
+	info->timestamp = ctx->timestamp;
+}
+
+#define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
+#define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */
+
+/*
+ * reschedule events based on the cgroup constraint of task.
+ *
+ * mode SWOUT : schedule out everything
+ * mode SWIN : schedule in based on cgroup for next
+ */
+void perf_cgroup_switch(struct task_struct *task, int mode)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/*
+	 * disable interrupts to avoid geting nr_cgroup
+	 * changes via __perf_event_disable(). Also
+	 * avoids preemption.
+	 */
+	local_irq_save(flags);
+
+	/*
+	 * we reschedule only in the presence of cgroup
+	 * constrained events.
+	 */
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		perf_pmu_disable(cpuctx->ctx.pmu);
+
+		/*
+		 * perf_cgroup_events says at least one
+		 * context on this CPU has cgroup events.
+		 *
+		 * ctx->nr_cgroups reports the number of cgroup
+		 * events for a context.
+		 */
+		if (cpuctx->ctx.nr_cgroups > 0) {
+
+			if (mode & PERF_CGROUP_SWOUT) {
+				cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+				/*
+				 * must not be done before ctxswout due
+				 * to event_filter_match() in event_sched_out()
+				 */
+				cpuctx->cgrp = NULL;
+			}
+
+			if (mode & PERF_CGROUP_SWIN) {
+				/* set cgrp before ctxsw in to
+				 * allow event_filter_match() to not
+				 * have to pass task around
+				 */
+				cpuctx->cgrp = perf_cgroup_from_task(task);
+				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+			}
+		}
+
+		perf_pmu_enable(cpuctx->ctx.pmu);
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+	perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+	perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+}
+
+static inline int perf_cgroup_connect(int fd, struct perf_event *event,
+				      struct perf_event_attr *attr,
+				      struct perf_event *group_leader)
+{
+	struct perf_cgroup *cgrp;
+	struct cgroup_subsys_state *css;
+	struct file *file;
+	int ret = 0, fput_needed;
+
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+
+	css = cgroup_css_from_dir(file, perf_subsys_id);
+	if (IS_ERR(css)) {
+		ret = PTR_ERR(css);
+		goto out;
+	}
+
+	cgrp = container_of(css, struct perf_cgroup, css);
+	event->cgrp = cgrp;
+
+	/* must be done before we fput() the file */
+	perf_get_cgroup(event);
+
+	/*
+	 * all events in a group must monitor
+	 * the same cgroup because a task belongs
+	 * to only one perf cgroup at a time
+	 */
+	if (group_leader && group_leader->cgrp != cgrp) {
+		perf_detach_cgroup(event);
+		ret = -EINVAL;
+	}
+out:
+	fput_light(file, fput_needed);
+	return ret;
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+	struct perf_cgroup_info *t;
+	t = per_cpu_ptr(event->cgrp->info, event->cpu);
+	event->shadow_ctx_time = now - t->timestamp;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+	/*
+	 * when the current task's perf cgroup does not match
+	 * the event's, we need to remember to call the
+	 * perf_mark_enable() function the first time a task with
+	 * a matching perf cgroup is scheduled in.
+	 */
+	if (is_cgroup_event(event) && !perf_cgroup_match(event))
+		event->cgrp_defer_enabled = 1;
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+			 struct perf_event_context *ctx)
+{
+	struct perf_event *sub;
+	u64 tstamp = perf_event_time(event);
+
+	if (!event->cgrp_defer_enabled)
+		return;
+
+	event->cgrp_defer_enabled = 0;
+
+	event->tstamp_enabled = tstamp - event->total_time_enabled;
+	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
+			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+			sub->cgrp_defer_enabled = 0;
+		}
+	}
+}
+#else /* !CONFIG_CGROUP_PERF */
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+	return true;
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+}
+
+static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
+				      struct perf_event_attr *attr,
+				      struct perf_event *group_leader)
+{
+	return -EINVAL;
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+			  struct perf_event_context *ctx)
+{
+}
+
+void
+perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+{
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+			 struct perf_event_context *ctx)
+{
+}
+#endif
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -254,7 +712,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 	raw_spin_lock_irqsave(&ctx->lock, flags);
 	--ctx->pin_count;
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	put_ctx(ctx);
 }
 
 /*
@@ -271,6 +728,10 @@ static void update_context_time(struct perf_event_context *ctx)
 static u64 perf_event_time(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
+
+	if (is_cgroup_event(event))
+		return perf_cgroup_event_time(event);
+
 	return ctx ? ctx->time : 0;
 }
 
@@ -285,9 +746,20 @@ static void update_event_times(struct perf_event *event)
 	if (event->state < PERF_EVENT_STATE_INACTIVE ||
 	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
 		return;
-
-	if (ctx->is_active)
+	/*
+	 * in cgroup mode, time_enabled represents
+	 * the time the event was enabled AND active
+	 * tasks were in the monitored cgroup. This is
+	 * independent of the activity of the context as
+	 * there may be a mix of cgroup and non-cgroup events.
+	 *
+	 * That is why we treat cgroup events differently
+	 * here.
+	 */
+	if (is_cgroup_event(event))
 		run_end = perf_event_time(event);
+	else if (ctx->is_active)
+		run_end = ctx->time;
 	else
 		run_end = event->tstamp_stopped;
 
@@ -299,6 +771,7 @@ static void update_event_times(struct perf_event *event)
 		run_end = perf_event_time(event);
 
 	event->total_time_running = run_end - event->tstamp_running;
+
 }
 
 /*
@@ -347,6 +820,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		list_add_tail(&event->group_entry, list);
 	}
 
+	if (is_cgroup_event(event))
+		ctx->nr_cgroups++;
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -473,6 +949,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
+	if (is_cgroup_event(event))
+		ctx->nr_cgroups--;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -544,7 +1023,8 @@ out:
 static inline int
 event_filter_match(struct perf_event *event)
 {
-	return event->cpu == -1 || event->cpu == smp_processor_id();
+	return (event->cpu == -1 || event->cpu == smp_processor_id())
+	    && perf_cgroup_match(event);
 }
 
 static void
@@ -562,7 +1042,7 @@ event_sched_out(struct perf_event *event,
 	 */
 	if (event->state == PERF_EVENT_STATE_INACTIVE
 	    && !event_filter_match(event)) {
-		delta = ctx->time - event->tstamp_stopped;
+		delta = tstamp - event->tstamp_stopped;
 		event->tstamp_running += delta;
 		event->tstamp_stopped = tstamp;
 	}
@@ -606,47 +1086,30 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
-	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
 /*
  * Cross CPU call to remove a performance event
  *
  * We disable the event on the hardware level first. After that we
  * remove it from the context list.
  */
-static void __perf_event_remove_from_context(void *info)
+static int __perf_remove_from_context(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
-	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
-
 	raw_spin_lock(&ctx->lock);
-
 	event_sched_out(event, cpuctx, ctx);
-
 	list_del_event(event, ctx);
-
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
- * Must be called with ctx->mutex held.
- *
  * CPU events are removed with a smp call. For task events we only
  * call when the task is on a CPU.
  *
@@ -657,49 +1120,48 @@ static void __perf_event_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_event_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
 
+	lockdep_assert_held(&ctx->mutex);
+
 	if (!task) {
 		/*
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		smp_call_function_single(event->cpu,
-					 __perf_event_remove_from_context,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_remove_from_context, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_event_remove_from_context,
-				 event);
+	if (!task_function_call(task, __perf_remove_from_context, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * If the context is active we need to retry the smp call.
+	 * If we failed to find a running task, but find the context active now
+	 * that we've acquired the ctx->lock, retry.
 	 */
-	if (ctx->nr_active && !list_empty(&event->group_entry)) {
+	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
 		goto retry;
 	}
 
 	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can remove the event safely, if the call above did not
-	 * succeed.
+	 * Since the task isn't running, its safe to remove the event, us
+	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
-	if (!list_empty(&event->group_entry))
-		list_del_event(event, ctx);
+	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
  * Cross CPU call to disable a performance event
  */
-static void __perf_event_disable(void *info)
+static int __perf_event_disable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -708,9 +1170,12 @@ static void __perf_event_disable(void *info)
 	/*
 	 * If this is a per-task event, need to check whether this
 	 * event's task is the current task on this cpu.
+	 *
+	 * Can trigger due to concurrent perf_event_context_sched_out()
+	 * flipping contexts around.
 	 */
 	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
+		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
 
@@ -720,6 +1185,7 @@ static void __perf_event_disable(void *info)
 	 */
 	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
 		update_context_time(ctx);
+		update_cgrp_time_from_event(event);
 		update_group_times(event);
 		if (event == event->group_leader)
 			group_sched_out(event, cpuctx, ctx);
@@ -729,6 +1195,8 @@ static void __perf_event_disable(void *info)
 	}
 
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -753,13 +1221,13 @@ void perf_event_disable(struct perf_event *event)
 		/*
 		 * Disable the event on the cpu that it's on
 		 */
-		smp_call_function_single(event->cpu, __perf_event_disable,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_event_disable, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_event_disable, event);
+	if (!task_function_call(task, __perf_event_disable, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
@@ -767,6 +1235,11 @@ retry:
 	 */
 	if (event->state == PERF_EVENT_STATE_ACTIVE) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -778,10 +1251,48 @@ retry:
 		update_group_times(event);
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+static void perf_set_shadow_time(struct perf_event *event,
+				 struct perf_event_context *ctx,
+				 u64 tstamp)
+{
+	/*
+	 * use the correct time source for the time snapshot
+	 *
+	 * We could get by without this by leveraging the
+	 * fact that to get to this function, the caller
+	 * has most likely already called update_context_time()
+	 * and update_cgrp_time_xx() and thus both timestamp
+	 * are identical (or very close). Given that tstamp is,
+	 * already adjusted for cgroup, we could say that:
+	 *    tstamp - ctx->timestamp
+	 * is equivalent to
+	 *    tstamp - cgrp->timestamp.
+	 *
+	 * Then, in perf_output_read(), the calculation would
+	 * work with no changes because:
+	 * - event is guaranteed scheduled in
+	 * - no scheduled out in between
+	 * - thus the timestamp would be the same
+	 *
+	 * But this is a bit hairy.
+	 *
+	 * So instead, we have an explicit cgroup call to remain
+	 * within the time time source all along. We believe it
+	 * is cleaner and simpler to understand.
+	 */
+	if (is_cgroup_event(event))
+		perf_cgroup_set_shadow_time(event, tstamp);
+	else
+		event->shadow_ctx_time = tstamp - ctx->timestamp;
+}
+
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
 static int
 event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
@@ -794,6 +1305,17 @@ event_sched_in(struct perf_event *event,
 
 	event->state = PERF_EVENT_STATE_ACTIVE;
 	event->oncpu = smp_processor_id();
+
+	/*
+	 * Unthrottle events, since we scheduled we might have missed several
+	 * ticks already, also for a heavily scheduling task there is little
+	 * guarantee it'll get a tick in a timely manner.
+	 */
+	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+		perf_log_throttle(event, 1);
+		event->hw.interrupts = 0;
+	}
+
 	/*
 	 * The new state must be visible before we turn it on in the hardware:
 	 */
@@ -807,7 +1329,7 @@ event_sched_in(struct perf_event *event,
 
 	event->tstamp_running += tstamp - event->tstamp_stopped;
 
-	event->shadow_ctx_time = tstamp - ctx->timestamp;
+	perf_set_shadow_time(event, ctx, tstamp);
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
@@ -928,12 +1450,15 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+					struct task_struct *tsk);
+
 /*
  * Cross CPU call to install and enable a performance event
  *
  * Must be called with ctx->mutex held
  */
-static void __perf_install_in_context(void *info)
+static int  __perf_install_in_context(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -942,21 +1467,22 @@ static void __perf_install_in_context(void *info)
 	int err;
 
 	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 * Or possibly this is the right context but it isn't
-	 * on this cpu because it had no events.
+	 * In case we're installing a new context to an already running task,
+	 * could also happen before perf_event_task_sched_in() on architectures
+	 * which do context switches with IRQs enabled.
 	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
+	if (ctx->task && !cpuctx->task_ctx)
+		perf_event_context_sched_in(ctx, ctx->task);
 
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	update_context_time(ctx);
+	/*
+	 * update cgrp time only if current cgrp
+	 * matches event->cgrp. Must be done before
+	 * calling add_event_to_ctx()
+	 */
+	update_cgrp_time_from_event(event);
 
 	add_event_to_ctx(event, ctx);
 
@@ -997,6 +1523,8 @@ static void __perf_install_in_context(void *info)
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -1008,8 +1536,6 @@ unlock:
  * If the event is attached to a task which is on a CPU we use a smp
  * call to enable it in the task context. The task might have been
  * scheduled away, but we check this in the smp call again.
- *
- * Must be called with ctx->mutex held.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
@@ -1018,6 +1544,8 @@ perf_install_in_context(struct perf_event_context *ctx,
 {
 	struct task_struct *task = ctx->task;
 
+	lockdep_assert_held(&ctx->mutex);
+
 	event->ctx = ctx;
 
 	if (!task) {
@@ -1025,31 +1553,29 @@ perf_install_in_context(struct perf_event_context *ctx,
 		 * Per cpu events are installed via an smp call and
 		 * the install is always successful.
 		 */
-		smp_call_function_single(cpu, __perf_install_in_context,
-					 event, 1);
+		cpu_function_call(cpu, __perf_install_in_context, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_install_in_context,
-				 event);
+	if (!task_function_call(task, __perf_install_in_context, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * we need to retry the smp call.
+	 * If we failed to find a running task, but find the context active now
+	 * that we've acquired the ctx->lock, retry.
 	 */
-	if (ctx->is_active && list_empty(&event->group_entry)) {
+	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
 		goto retry;
 	}
 
 	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can add the event safely, if it the call above did not
-	 * succeed.
+	 * Since the task isn't running, its safe to add the event, us holding
+	 * the ctx->lock ensures the task won't get scheduled in.
 	 */
-	if (list_empty(&event->group_entry))
-		add_event_to_ctx(event, ctx);
+	add_event_to_ctx(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -1078,7 +1604,7 @@ static void __perf_event_mark_enabled(struct perf_event *event,
 /*
  * Cross CPU call to enable a performance event
  */
-static void __perf_event_enable(void *info)
+static int __perf_event_enable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -1086,26 +1612,27 @@ static void __perf_event_enable(void *info)
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
-	/*
-	 * If this is a per-task event, need to check whether this
-	 * event's task is the current task on this cpu.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
+	if (WARN_ON_ONCE(!ctx->is_active))
+		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
-	ctx->is_active = 1;
 	update_context_time(ctx);
 
 	if (event->state >= PERF_EVENT_STATE_INACTIVE)
 		goto unlock;
+
+	/*
+	 * set current task's cgroup time reference point
+	 */
+	perf_cgroup_set_timestamp(current, ctx);
+
 	__perf_event_mark_enabled(event, ctx);
 
-	if (!event_filter_match(event))
+	if (!event_filter_match(event)) {
+		if (is_cgroup_event(event))
+			perf_cgroup_defer_enabled(event);
 		goto unlock;
+	}
 
 	/*
 	 * If the event is in a group and isn't the group leader,
@@ -1138,6 +1665,8 @@ static void __perf_event_enable(void *info)
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -1158,8 +1687,7 @@ void perf_event_enable(struct perf_event *event)
 		/*
 		 * Enable the event on the cpu that it's on
 		 */
-		smp_call_function_single(event->cpu, __perf_event_enable,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_event_enable, event);
 		return;
 	}
 
@@ -1178,8 +1706,15 @@ void perf_event_enable(struct perf_event *event)
 		event->state = PERF_EVENT_STATE_OFF;
 
 retry:
+	if (!ctx->is_active) {
+		__perf_event_mark_enabled(event, ctx);
+		goto out;
+	}
+
 	raw_spin_unlock_irq(&ctx->lock);
-	task_oncpu_function_call(task, __perf_event_enable, event);
+
+	if (!task_function_call(task, __perf_event_enable, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 
@@ -1187,15 +1722,14 @@ retry:
 	 * If the context is active and the event is still off,
 	 * we need to retry the cross-call.
 	 */
-	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
+	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
+		/*
+		 * task could have been flipped by a concurrent
+		 * perf_event_context_sched_out()
+		 */
+		task = ctx->task;
 		goto retry;
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (event->state == PERF_EVENT_STATE_OFF)
-		__perf_event_mark_enabled(event, ctx);
+	}
 
 out:
 	raw_spin_unlock_irq(&ctx->lock);
@@ -1227,6 +1761,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		goto out;
 	update_context_time(ctx);
+	update_cgrp_time_from_cpuctx(cpuctx);
 
 	if (!ctx->nr_active)
 		goto out;
@@ -1339,8 +1874,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
 	}
 }
 
-void perf_event_context_sched_out(struct task_struct *task, int ctxn,
-				  struct task_struct *next)
+static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+					 struct task_struct *next)
 {
 	struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
 	struct perf_event_context *next_ctx;
@@ -1416,6 +1951,14 @@ void __perf_event_task_sched_out(struct task_struct *task,
 
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
+
+	/*
+	 * if cgroup events exist on this CPU, then we need
+	 * to check if we have to switch out PMU state.
+	 * cgroup event are system-wide mode only
+	 */
+	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+		perf_cgroup_sched_out(task);
 }
 
 static void task_ctx_sched_out(struct perf_event_context *ctx,
@@ -1454,6 +1997,10 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		/* may need to reset tstamp_enabled */
+		if (is_cgroup_event(event))
+			perf_cgroup_mark_enabled(event, ctx);
+
 		if (group_can_go_on(event, cpuctx, 1))
 			group_sched_in(event, cpuctx, ctx);
 
@@ -1486,6 +2033,10 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		/* may need to reset tstamp_enabled */
+		if (is_cgroup_event(event))
+			perf_cgroup_mark_enabled(event, ctx);
+
 		if (group_can_go_on(event, cpuctx, can_add_hw)) {
 			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
@@ -1496,15 +2047,19 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type)
+	     enum event_type_t event_type,
+	     struct task_struct *task)
 {
+	u64 now;
+
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	if (likely(!ctx->nr_events))
 		goto out;
 
-	ctx->timestamp = perf_clock();
-
+	now = perf_clock();
+	ctx->timestamp = now;
+	perf_cgroup_set_timestamp(task, ctx);
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
@@ -1521,11 +2076,12 @@ out:
 }
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type)
+			     enum event_type_t event_type,
+			     struct task_struct *task)
 {
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
-	ctx_sched_in(ctx, cpuctx, event_type);
+	ctx_sched_in(ctx, cpuctx, event_type, task);
 }
 
 static void task_ctx_sched_in(struct perf_event_context *ctx,
@@ -1533,15 +2089,16 @@ static void task_ctx_sched_in(struct perf_event_context *ctx,
 {
 	struct perf_cpu_context *cpuctx;
 
-       	cpuctx = __get_cpu_context(ctx);
+	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
 
-	ctx_sched_in(ctx, cpuctx, event_type);
+	ctx_sched_in(ctx, cpuctx, event_type, NULL);
 	cpuctx->task_ctx = ctx;
 }
 
-void perf_event_context_sched_in(struct perf_event_context *ctx)
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+					struct task_struct *task)
 {
 	struct perf_cpu_context *cpuctx;
 
@@ -1557,9 +2114,9 @@ void perf_event_context_sched_in(struct perf_event_context *ctx)
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
-	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
+	ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 
 	cpuctx->task_ctx = ctx;
 
@@ -1592,14 +2149,17 @@ void __perf_event_task_sched_in(struct task_struct *task)
 		if (likely(!ctx))
 			continue;
 
-		perf_event_context_sched_in(ctx);
+		perf_event_context_sched_in(ctx, task);
 	}
+	/*
+	 * if cgroup events exist on this CPU, then we need
+	 * to check if we have to switch in PMU state.
+	 * cgroup event are system-wide mode only
+	 */
+	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+		perf_cgroup_sched_in(task);
 }
 
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	u64 frequency = event->attr.sample_freq;
@@ -1627,7 +2187,7 @@ static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 	 * Reduce accuracy by one bit such that @a and @b converge
 	 * to a similar magnitude.
 	 */
-#define REDUCE_FLS(a, b) 		\
+#define REDUCE_FLS(a, b)		\
 do {					\
 	if (a##_fls > b##_fls) {	\
 		a >>= 1;		\
@@ -1797,7 +2357,7 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 	if (ctx)
 		rotate_ctx(ctx);
 
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current);
 	if (ctx)
 		task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
 
@@ -1876,7 +2436,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
 	raw_spin_unlock(&ctx->lock);
 
-	perf_event_context_sched_in(ctx);
+	perf_event_context_sched_in(ctx, ctx->task);
 out:
 	local_irq_restore(flags);
 }
@@ -1901,8 +2461,10 @@ static void __perf_event_read(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	if (ctx->is_active)
+	if (ctx->is_active) {
 		update_context_time(ctx);
+		update_cgrp_time_from_event(event);
+	}
 	update_event_times(event);
 	if (event->state == PERF_EVENT_STATE_ACTIVE)
 		event->pmu->read(event);
@@ -1933,8 +2495,10 @@ static u64 perf_event_read(struct perf_event *event)
 		 * (e.g., thread is blocked), in that case
 		 * we cannot update context time
 		 */
-		if (ctx->is_active)
+		if (ctx->is_active) {
 			update_context_time(ctx);
+			update_cgrp_time_from_event(event);
+		}
 		update_event_times(event);
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
@@ -2213,6 +2777,9 @@ errout:
 
 }
 
+/*
+ * Returns a matching context with refcount and pincount.
+ */
 static struct perf_event_context *
 find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 {
@@ -2237,6 +2804,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
+		++ctx->pin_count;
 
 		return ctx;
 	}
@@ -2250,6 +2818,7 @@ retry:
 	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		unclone_ctx(ctx);
+		++ctx->pin_count;
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
@@ -2271,8 +2840,10 @@ retry:
 			err = -ESRCH;
 		else if (task->perf_event_ctxp[ctxn])
 			err = -EAGAIN;
-		else
+		else {
+			++ctx->pin_count;
 			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+		}
 		mutex_unlock(&task->perf_event_mutex);
 
 		if (unlikely(err)) {
@@ -2312,7 +2883,7 @@ static void free_event(struct perf_event *event)
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_dec(&perf_task_events);
+			jump_label_dec(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_dec(&nr_mmap_events);
 		if (event->attr.comm)
@@ -2321,6 +2892,10 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&nr_task_events);
 		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
 			put_callchain_buffers();
+		if (is_cgroup_event(event)) {
+			atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
+			jump_label_dec(&perf_sched_events);
+		}
 	}
 
 	if (event->buffer) {
@@ -2328,6 +2903,9 @@ static void free_event(struct perf_event *event)
 		event->buffer = NULL;
 	}
 
+	if (is_cgroup_event(event))
+		perf_detach_cgroup(event);
+
 	if (event->destroy)
 		event->destroy(event);
 
@@ -4395,26 +4973,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	if (unlikely(!is_sampling_event(event)))
 		return 0;
 
-	if (!throttle) {
-		hwc->interrupts++;
-	} else {
-		if (hwc->interrupts != MAX_INTERRUPTS) {
-			hwc->interrupts++;
-			if (HZ * hwc->interrupts >
-					(u64)sysctl_perf_event_sample_rate) {
-				hwc->interrupts = MAX_INTERRUPTS;
-				perf_log_throttle(event, 0);
-				ret = 1;
-			}
-		} else {
-			/*
-			 * Keep re-disabling events even though on the previous
-			 * pass we disabled it - just in case we raced with a
-			 * sched-in and the event got enabled again:
-			 */
+	if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
+		if (throttle) {
+			hwc->interrupts = MAX_INTERRUPTS;
+			perf_log_throttle(event, 0);
 			ret = 1;
 		}
-	}
+	} else
+		hwc->interrupts++;
 
 	if (event->attr.freq) {
 		u64 now = perf_clock();
@@ -5051,6 +5617,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	u64 period;
 
 	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return HRTIMER_NORESTART;
+
 	event->pmu->read(event);
 
 	perf_sample_data_init(&data, 0);
@@ -5077,9 +5647,6 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
 	if (!is_sampling_event(event))
 		return;
 
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swevent_hrtimer;
-
 	period = local64_read(&hwc->period_left);
 	if (period) {
 		if (period < 0)
@@ -5106,6 +5673,30 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 	}
 }
 
+static void perf_swevent_init_hrtimer(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!is_sampling_event(event))
+		return;
+
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swevent_hrtimer;
+
+	/*
+	 * Since hrtimers have a fixed rate, we can do a static freq->period
+	 * mapping and avoid the whole period adjust feedback stuff.
+	 */
+	if (event->attr.freq) {
+		long freq = event->attr.sample_freq;
+
+		event->attr.sample_period = NSEC_PER_SEC / freq;
+		hwc->sample_period = event->attr.sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+		event->attr.freq = 0;
+	}
+}
+
 /*
  * Software event: cpu wall time clock
  */
@@ -5158,6 +5749,8 @@ static int cpu_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
 		return -ENOENT;
 
+	perf_swevent_init_hrtimer(event);
+
 	return 0;
 }
 
@@ -5213,16 +5806,9 @@ static void task_clock_event_del(struct perf_event *event, int flags)
 
 static void task_clock_event_read(struct perf_event *event)
 {
-	u64 time;
-
-	if (!in_nmi()) {
-		update_context_time(event->ctx);
-		time = event->ctx->time;
-	} else {
-		u64 now = perf_clock();
-		u64 delta = now - event->ctx->timestamp;
-		time = event->ctx->time + delta;
-	}
+	u64 now = perf_clock();
+	u64 delta = now - event->ctx->timestamp;
+	u64 time = event->ctx->time + delta;
 
 	task_clock_event_update(event, time);
 }
@@ -5235,6 +5821,8 @@ static int task_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
 		return -ENOENT;
 
+	perf_swevent_init_hrtimer(event);
+
 	return 0;
 }
 
@@ -5506,17 +6094,22 @@ struct pmu *perf_init_event(struct perf_event *event)
 {
 	struct pmu *pmu = NULL;
 	int idx;
+	int ret;
 
 	idx = srcu_read_lock(&pmus_srcu);
 
 	rcu_read_lock();
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
-	if (pmu)
+	if (pmu) {
+		ret = pmu->event_init(event);
+		if (ret)
+			pmu = ERR_PTR(ret);
 		goto unlock;
+	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		int ret = pmu->event_init(event);
+		ret = pmu->event_init(event);
 		if (!ret)
 			goto unlock;
 
@@ -5642,7 +6235,7 @@ done:
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_inc(&perf_task_events);
+			jump_label_inc(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_inc(&nr_mmap_events);
 		if (event->attr.comm)
@@ -5817,7 +6410,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int err;
 
 	/* for future expandability... */
-	if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
+	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
 	err = perf_copy_attr(attr_uptr, &attr);
@@ -5834,6 +6427,15 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}
 
+	/*
+	 * In cgroup mode, the pid argument is used to pass the fd
+	 * opened to the cgroup directory in cgroupfs. The cpu argument
+	 * designates the cpu on which to monitor threads from that
+	 * cgroup.
+	 */
+	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
+		return -EINVAL;
+
 	event_fd = get_unused_fd_flags(O_RDWR);
 	if (event_fd < 0)
 		return event_fd;
@@ -5851,7 +6453,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			group_leader = NULL;
 	}
 
-	if (pid != -1) {
+	if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
 		task = find_lively_task_by_vpid(pid);
 		if (IS_ERR(task)) {
 			err = PTR_ERR(task);
@@ -5865,6 +6467,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_task;
 	}
 
+	if (flags & PERF_FLAG_PID_CGROUP) {
+		err = perf_cgroup_connect(pid, event, &attr, group_leader);
+		if (err)
+			goto err_alloc;
+		/*
+		 * one more event:
+		 * - that has cgroup constraint on event->cpu
+		 * - that may need work on context switch
+		 */
+		atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
+		jump_label_inc(&perf_sched_events);
+	}
+
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -5950,10 +6565,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_event_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_event_remove_from_context(sibling);
+			perf_remove_from_context(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);
@@ -5976,6 +6591,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
+	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
@@ -6001,6 +6617,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	return event_fd;
 
 err_context:
+	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
 	free_event(event);
@@ -6051,6 +6668,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	mutex_lock(&ctx->mutex);
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
+	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
 	return event;
@@ -6104,7 +6722,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 {
 	struct perf_event *parent_event;
 
-	perf_event_remove_from_context(child_event);
+	perf_remove_from_context(child_event);
 
 	parent_event = child_event->parent;
 	/*
@@ -6411,7 +7029,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		return 0;
 	}
 
-       	child_ctx = child->perf_event_ctxp[ctxn];
+	child_ctx = child->perf_event_ctxp[ctxn];
 	if (!child_ctx) {
 		/*
 		 * This is executed from the parent task context, so
@@ -6526,6 +7144,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
+	put_ctx(parent_ctx);
 
 	return ret;
 }
@@ -6595,9 +7214,9 @@ static void __perf_event_exit_context(void *__info)
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_event_remove_from_context(event);
+		__perf_remove_from_context(event);
 	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
-		__perf_event_remove_from_context(event);
+		__perf_remove_from_context(event);
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -6721,3 +7340,83 @@ unlock:
 	return ret;
 }
 device_initcall(perf_event_sysfs_init);
+
+#ifdef CONFIG_CGROUP_PERF
+static struct cgroup_subsys_state *perf_cgroup_create(
+	struct cgroup_subsys *ss, struct cgroup *cont)
+{
+	struct perf_cgroup *jc;
+
+	jc = kzalloc(sizeof(*jc), GFP_KERNEL);
+	if (!jc)
+		return ERR_PTR(-ENOMEM);
+
+	jc->info = alloc_percpu(struct perf_cgroup_info);
+	if (!jc->info) {
+		kfree(jc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return &jc->css;
+}
+
+static void perf_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+	struct perf_cgroup *jc;
+	jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
+			  struct perf_cgroup, css);
+	free_percpu(jc->info);
+	kfree(jc);
+}
+
+static int __perf_cgroup_move(void *info)
+{
+	struct task_struct *task = info;
+	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+	return 0;
+}
+
+static void perf_cgroup_move(struct task_struct *task)
+{
+	task_function_call(task, __perf_cgroup_move, task);
+}
+
+static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task,
+		bool threadgroup)
+{
+	perf_cgroup_move(task);
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+			perf_cgroup_move(c);
+		}
+		rcu_read_unlock();
+	}
+}
+
+static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
+{
+	/*
+	 * cgroup_exit() is called in the copy_process() failure path.
+	 * Ignore this case since the task hasn't ran yet, this avoids
+	 * trying to poke a half freed task state from generic code.
+	 */
+	if (!(task->flags & PF_EXITING))
+		return;
+
+	perf_cgroup_move(task);
+}
+
+struct cgroup_subsys perf_subsys = {
+	.name = "perf_event",
+	.subsys_id = perf_subsys_id,
+	.create = perf_cgroup_create,
+	.destroy = perf_cgroup_destroy,
+	.exit = perf_cgroup_exit,
+	.attach = perf_cgroup_attach,
+};
+#endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index aeaa7f846821..0da058bff8eb 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -103,11 +103,14 @@ static struct pm_qos_object *pm_qos_array[] = {
 
 static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos);
+static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
+		size_t count, loff_t *f_pos);
 static int pm_qos_power_open(struct inode *inode, struct file *filp);
 static int pm_qos_power_release(struct inode *inode, struct file *filp);
 
 static const struct file_operations pm_qos_power_fops = {
 	.write = pm_qos_power_write,
+	.read = pm_qos_power_read,
 	.open = pm_qos_power_open,
 	.release = pm_qos_power_release,
 	.llseek = noop_llseek,
@@ -376,6 +379,27 @@ static int pm_qos_power_release(struct inode *inode, struct file *filp)
 }
 
 
+static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
+		size_t count, loff_t *f_pos)
+{
+	s32 value;
+	unsigned long flags;
+	struct pm_qos_object *o;
+	struct pm_qos_request_list *pm_qos_req = filp->private_data;;
+
+	if (!pm_qos_req)
+		return -EINVAL;
+	if (!pm_qos_request_active(pm_qos_req))
+		return -EINVAL;
+
+	o = pm_qos_array[pm_qos_req->pm_qos_class];
+	spin_lock_irqsave(&pm_qos_lock, flags);
+	value = pm_qos_get_value(o);
+	spin_unlock_irqrestore(&pm_qos_lock, flags);
+
+	return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
+}
+
 static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos)
 {
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 05bb7173850e..67fea9d25d55 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -176,7 +176,8 @@ static inline cputime_t virt_ticks(struct task_struct *p)
 	return p->utime;
 }
 
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
 	int error = check_clock(which_clock);
 	if (!error) {
@@ -194,7 +195,8 @@ int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 	return error;
 }
 
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
 {
 	/*
 	 * You can never reset a CPU clock, but we check for other errors
@@ -317,7 +319,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 }
 
 
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
 	int error = -EINVAL;
@@ -379,7 +381,7 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
  * This is called from sys_timer_create() and do_cpu_nanosleep() with the
  * new timer already all-zeros initialized.
  */
-int posix_cpu_timer_create(struct k_itimer *new_timer)
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
 {
 	int ret = 0;
 	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
@@ -425,7 +427,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_del(struct k_itimer *timer)
+static int posix_cpu_timer_del(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
@@ -665,8 +667,8 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-			struct itimerspec *new, struct itimerspec *old)
+static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+			       struct itimerspec *new, struct itimerspec *old)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	union cpu_time_count old_expires, new_expires, old_incr, val;
@@ -820,7 +822,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	return ret;
 }
 
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
 	union cpu_time_count now;
 	struct task_struct *p = timer->it.cpu.task;
@@ -1481,11 +1483,13 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 	return error;
 }
 
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
 	struct restart_block *restart_block =
-	    &current_thread_info()->restart_block;
+		&current_thread_info()->restart_block;
 	struct itimerspec it;
 	int error;
 
@@ -1501,56 +1505,47 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 
 	if (error == -ERESTART_RESTARTBLOCK) {
 
-	       	if (flags & TIMER_ABSTIME)
+		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 		/*
-	 	 * Report back to the user the time still remaining.
-	 	 */
-		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 * Report back to the user the time still remaining.
+		 */
+		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
 		restart_block->fn = posix_cpu_nsleep_restart;
-		restart_block->arg0 = which_clock;
-		restart_block->arg1 = (unsigned long) rmtp;
-		restart_block->arg2 = rqtp->tv_sec;
-		restart_block->arg3 = rqtp->tv_nsec;
+		restart_block->nanosleep.index = which_clock;
+		restart_block->nanosleep.rmtp = rmtp;
+		restart_block->nanosleep.expires = timespec_to_ns(rqtp);
 	}
 	return error;
 }
 
-long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 {
-	clockid_t which_clock = restart_block->arg0;
-	struct timespec __user *rmtp;
+	clockid_t which_clock = restart_block->nanosleep.index;
 	struct timespec t;
 	struct itimerspec it;
 	int error;
 
-	rmtp = (struct timespec __user *) restart_block->arg1;
-	t.tv_sec = restart_block->arg2;
-	t.tv_nsec = restart_block->arg3;
+	t = ns_to_timespec(restart_block->nanosleep.expires);
 
-	restart_block->fn = do_no_restart_syscall;
 	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
 
 	if (error == -ERESTART_RESTARTBLOCK) {
+		struct timespec __user *rmtp = restart_block->nanosleep.rmtp;
 		/*
-	 	 * Report back to the user the time still remaining.
-	 	 */
-		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 * Report back to the user the time still remaining.
+		 */
+		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
-		restart_block->arg0 = which_clock;
-		restart_block->arg1 = (unsigned long) rmtp;
-		restart_block->arg2 = t.tv_sec;
-		restart_block->arg3 = t.tv_nsec;
+		restart_block->nanosleep.expires = timespec_to_ns(&t);
 	}
 	return error;
 
 }
 
-
 #define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
 #define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
 
@@ -1594,38 +1589,37 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
 	timer->it_clock = THREAD_CLOCK;
 	return posix_cpu_timer_create(timer);
 }
-static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
-			      struct timespec *rqtp, struct timespec __user *rmtp)
-{
-	return -EINVAL;
-}
-static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
-{
-	return -EINVAL;
-}
+
+struct k_clock clock_posix_cpu = {
+	.clock_getres	= posix_cpu_clock_getres,
+	.clock_set	= posix_cpu_clock_set,
+	.clock_get	= posix_cpu_clock_get,
+	.timer_create	= posix_cpu_timer_create,
+	.nsleep		= posix_cpu_nsleep,
+	.nsleep_restart	= posix_cpu_nsleep_restart,
+	.timer_set	= posix_cpu_timer_set,
+	.timer_del	= posix_cpu_timer_del,
+	.timer_get	= posix_cpu_timer_get,
+};
 
 static __init int init_posix_cpu_timers(void)
 {
 	struct k_clock process = {
-		.clock_getres = process_cpu_clock_getres,
-		.clock_get = process_cpu_clock_get,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = process_cpu_timer_create,
-		.nsleep = process_cpu_nsleep,
-		.nsleep_restart = process_cpu_nsleep_restart,
+		.clock_getres	= process_cpu_clock_getres,
+		.clock_get	= process_cpu_clock_get,
+		.timer_create	= process_cpu_timer_create,
+		.nsleep		= process_cpu_nsleep,
+		.nsleep_restart	= process_cpu_nsleep_restart,
 	};
 	struct k_clock thread = {
-		.clock_getres = thread_cpu_clock_getres,
-		.clock_get = thread_cpu_clock_get,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = thread_cpu_timer_create,
-		.nsleep = thread_cpu_nsleep,
-		.nsleep_restart = thread_cpu_nsleep_restart,
+		.clock_getres	= thread_cpu_clock_getres,
+		.clock_get	= thread_cpu_clock_get,
+		.timer_create	= thread_cpu_timer_create,
 	};
 	struct timespec ts;
 
-	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
-	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+	posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+	posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
 	cputime_to_timespec(cputime_one_jiffy, &ts);
 	onecputick = ts.tv_nsec;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 93bd2eb2bc53..4c0124919f9a 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -41,6 +41,7 @@
 #include <linux/init.h>
 #include <linux/compiler.h>
 #include <linux/idr.h>
+#include <linux/posix-clock.h>
 #include <linux/posix-timers.h>
 #include <linux/syscalls.h>
 #include <linux/wait.h>
@@ -81,6 +82,14 @@ static DEFINE_SPINLOCK(idr_lock);
 #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
 #endif
 
+/*
+ * parisc wants ENOTSUP instead of EOPNOTSUPP
+ */
+#ifndef ENOTSUP
+# define ENANOSLEEP_NOTSUP EOPNOTSUPP
+#else
+# define ENANOSLEEP_NOTSUP ENOTSUP
+#endif
 
 /*
  * The timer ID is turned into a timer address by idr_find().
@@ -94,11 +103,7 @@ static DEFINE_SPINLOCK(idr_lock);
 /*
  * CLOCKs: The POSIX standard calls for a couple of clocks and allows us
  *	    to implement others.  This structure defines the various
- *	    clocks and allows the possibility of adding others.	 We
- *	    provide an interface to add clocks to the table and expect
- *	    the "arch" code to add at least one clock that is high
- *	    resolution.	 Here we define the standard CLOCK_REALTIME as a
- *	    1/HZ resolution clock.
+ *	    clocks.
  *
  * RESOLUTION: Clock resolution is used to round up timer and interval
  *	    times, NOT to report clock times, which are reported with as
@@ -108,20 +113,13 @@ static DEFINE_SPINLOCK(idr_lock);
  *	    necessary code is written.	The standard says we should say
  *	    something about this issue in the documentation...
  *
- * FUNCTIONS: The CLOCKs structure defines possible functions to handle
- *	    various clock functions.  For clocks that use the standard
- *	    system timer code these entries should be NULL.  This will
- *	    allow dispatch without the overhead of indirect function
- *	    calls.  CLOCKS that depend on other sources (e.g. WWV or GPS)
- *	    must supply functions here, even if the function just returns
- *	    ENOSYS.  The standard POSIX timer management code assumes the
- *	    following: 1.) The k_itimer struct (sched.h) is used for the
- *	    timer.  2.) The list, it_lock, it_clock, it_id and it_pid
- *	    fields are not modified by timer code.
+ * FUNCTIONS: The CLOCKs structure defines possible functions to
+ *	    handle various clock functions.
  *
- *          At this time all functions EXCEPT clock_nanosleep can be
- *          redirected by the CLOCKS structure.  Clock_nanosleep is in
- *          there, but the code ignores it.
+ *	    The standard POSIX timer management code assumes the
+ *	    following: 1.) The k_itimer struct (sched.h) is used for
+ *	    the timer.  2.) The list, it_lock, it_clock, it_id and
+ *	    it_pid fields are not modified by timer code.
  *
  * Permissions: It is assumed that the clock_settime() function defined
  *	    for each clock will take care of permission checks.	 Some
@@ -138,6 +136,7 @@ static struct k_clock posix_clocks[MAX_CLOCKS];
  */
 static int common_nsleep(const clockid_t, int flags, struct timespec *t,
 			 struct timespec __user *rmtp);
+static int common_timer_create(struct k_itimer *new_timer);
 static void common_timer_get(struct k_itimer *, struct itimerspec *);
 static int common_timer_set(struct k_itimer *, int,
 			    struct itimerspec *, struct itimerspec *);
@@ -158,76 +157,24 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 	spin_unlock_irqrestore(&timr->it_lock, flags);
 }
 
-/*
- * Call the k_clock hook function if non-null, or the default function.
- */
-#define CLOCK_DISPATCH(clock, call, arglist) \
- 	((clock) < 0 ? posix_cpu_##call arglist : \
- 	 (posix_clocks[clock].call != NULL \
- 	  ? (*posix_clocks[clock].call) arglist : common_##call arglist))
-
-/*
- * Default clock hook functions when the struct k_clock passed
- * to register_posix_clock leaves a function pointer null.
- *
- * The function common_CALL is the default implementation for
- * the function pointer CALL in struct k_clock.
- */
-
-static inline int common_clock_getres(const clockid_t which_clock,
-				      struct timespec *tp)
-{
-	tp->tv_sec = 0;
-	tp->tv_nsec = posix_clocks[which_clock].res;
-	return 0;
-}
-
-/*
- * Get real time for posix timers
- */
-static int common_clock_get(clockid_t which_clock, struct timespec *tp)
+/* Get clock_realtime */
+static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
 {
 	ktime_get_real_ts(tp);
 	return 0;
 }
 
-static inline int common_clock_set(const clockid_t which_clock,
-				   struct timespec *tp)
+/* Set clock_realtime */
+static int posix_clock_realtime_set(const clockid_t which_clock,
+				    const struct timespec *tp)
 {
 	return do_sys_settimeofday(tp, NULL);
 }
 
-static int common_timer_create(struct k_itimer *new_timer)
-{
-	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
-	return 0;
-}
-
-static int no_timer_create(struct k_itimer *new_timer)
-{
-	return -EOPNOTSUPP;
-}
-
-static int no_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *tsave, struct timespec __user *rmtp)
-{
-	return -EOPNOTSUPP;
-}
-
-/*
- * Return nonzero if we know a priori this clockid_t value is bogus.
- */
-static inline int invalid_clockid(const clockid_t which_clock)
+static int posix_clock_realtime_adj(const clockid_t which_clock,
+				    struct timex *t)
 {
-	if (which_clock < 0)	/* CPU clock, posix_cpu_* will check it */
-		return 0;
-	if ((unsigned) which_clock >= MAX_CLOCKS)
-		return 1;
-	if (posix_clocks[which_clock].clock_getres != NULL)
-		return 0;
-	if (posix_clocks[which_clock].res != 0)
-		return 0;
-	return 1;
+	return do_adjtimex(t);
 }
 
 /*
@@ -240,7 +187,7 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 }
 
 /*
- * Get monotonic time for posix timers
+ * Get monotonic-raw time for posix timers
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
 {
@@ -267,46 +214,70 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp
 	*tp = ktime_to_timespec(KTIME_LOW_RES);
 	return 0;
 }
+
+static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+{
+	get_monotonic_boottime(tp);
+	return 0;
+}
+
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
 {
 	struct k_clock clock_realtime = {
-		.clock_getres = hrtimer_get_res,
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_clock_realtime_get,
+		.clock_set	= posix_clock_realtime_set,
+		.clock_adj	= posix_clock_realtime_adj,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic = {
-		.clock_getres = hrtimer_get_res,
-		.clock_get = posix_ktime_get_ts,
-		.clock_set = do_posix_clock_nosettime,
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_ktime_get_ts,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic_raw = {
-		.clock_getres = hrtimer_get_res,
-		.clock_get = posix_get_monotonic_raw,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = no_timer_create,
-		.nsleep = no_nsleep,
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_get_monotonic_raw,
 	};
 	struct k_clock clock_realtime_coarse = {
-		.clock_getres = posix_get_coarse_res,
-		.clock_get = posix_get_realtime_coarse,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = no_timer_create,
-		.nsleep = no_nsleep,
+		.clock_getres	= posix_get_coarse_res,
+		.clock_get	= posix_get_realtime_coarse,
 	};
 	struct k_clock clock_monotonic_coarse = {
-		.clock_getres = posix_get_coarse_res,
-		.clock_get = posix_get_monotonic_coarse,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = no_timer_create,
-		.nsleep = no_nsleep,
+		.clock_getres	= posix_get_coarse_res,
+		.clock_get	= posix_get_monotonic_coarse,
+	};
+	struct k_clock clock_boottime = {
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_get_boottime,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
 	};
 
-	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
-	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
-	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
-	register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
-	register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
+	posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
+	posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
@@ -482,17 +453,29 @@ static struct pid *good_sigevent(sigevent_t * event)
 	return task_pid(rtn);
 }
 
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
+void posix_timers_register_clock(const clockid_t clock_id,
+				 struct k_clock *new_clock)
 {
 	if ((unsigned) clock_id >= MAX_CLOCKS) {
-		printk("POSIX clock register failed for clock_id %d\n",
+		printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
+		       clock_id);
+		return;
+	}
+
+	if (!new_clock->clock_get) {
+		printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
+		       clock_id);
+		return;
+	}
+	if (!new_clock->clock_getres) {
+		printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
 		       clock_id);
 		return;
 	}
 
 	posix_clocks[clock_id] = *new_clock;
 }
-EXPORT_SYMBOL_GPL(register_posix_clock);
+EXPORT_SYMBOL_GPL(posix_timers_register_clock);
 
 static struct k_itimer * alloc_posix_timer(void)
 {
@@ -523,19 +506,39 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 	kmem_cache_free(posix_timers_cache, tmr);
 }
 
+static struct k_clock *clockid_to_kclock(const clockid_t id)
+{
+	if (id < 0)
+		return (id & CLOCKFD_MASK) == CLOCKFD ?
+			&clock_posix_dynamic : &clock_posix_cpu;
+
+	if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
+		return NULL;
+	return &posix_clocks[id];
+}
+
+static int common_timer_create(struct k_itimer *new_timer)
+{
+	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
+	return 0;
+}
+
 /* Create a POSIX.1b interval timer. */
 
 SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 		struct sigevent __user *, timer_event_spec,
 		timer_t __user *, created_timer_id)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct k_itimer *new_timer;
 	int error, new_timer_id;
 	sigevent_t event;
 	int it_id_set = IT_ID_NOT_SET;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
+	if (!kc->timer_create)
+		return -EOPNOTSUPP;
 
 	new_timer = alloc_posix_timer();
 	if (unlikely(!new_timer))
@@ -597,7 +600,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 		goto out;
 	}
 
-	error = CLOCK_DISPATCH(which_clock, timer_create, (new_timer));
+	error = kc->timer_create(new_timer);
 	if (error)
 		goto out;
 
@@ -607,7 +610,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 	spin_unlock_irq(&current->sighand->siglock);
 
 	return 0;
- 	/*
+	/*
 	 * In the case of the timer belonging to another task, after
 	 * the task is unlocked, the timer is owned by the other task
 	 * and may cease to exist at any time.  Don't use or modify
@@ -709,22 +712,28 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 		struct itimerspec __user *, setting)
 {
-	struct k_itimer *timr;
 	struct itimerspec cur_setting;
+	struct k_itimer *timr;
+	struct k_clock *kc;
 	unsigned long flags;
+	int ret = 0;
 
 	timr = lock_timer(timer_id, &flags);
 	if (!timr)
 		return -EINVAL;
 
-	CLOCK_DISPATCH(timr->it_clock, timer_get, (timr, &cur_setting));
+	kc = clockid_to_kclock(timr->it_clock);
+	if (WARN_ON_ONCE(!kc || !kc->timer_get))
+		ret = -EINVAL;
+	else
+		kc->timer_get(timr, &cur_setting);
 
 	unlock_timer(timr, flags);
 
-	if (copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
+	if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
 		return -EFAULT;
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -813,6 +822,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	int error = 0;
 	unsigned long flag;
 	struct itimerspec *rtn = old_setting ? &old_spec : NULL;
+	struct k_clock *kc;
 
 	if (!new_setting)
 		return -EINVAL;
@@ -828,8 +838,11 @@ retry:
 	if (!timr)
 		return -EINVAL;
 
-	error = CLOCK_DISPATCH(timr->it_clock, timer_set,
-			       (timr, flags, &new_spec, rtn));
+	kc = clockid_to_kclock(timr->it_clock);
+	if (WARN_ON_ONCE(!kc || !kc->timer_set))
+		error = -EINVAL;
+	else
+		error = kc->timer_set(timr, flags, &new_spec, rtn);
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
@@ -844,7 +857,7 @@ retry:
 	return error;
 }
 
-static inline int common_timer_del(struct k_itimer *timer)
+static int common_timer_del(struct k_itimer *timer)
 {
 	timer->it.real.interval.tv64 = 0;
 
@@ -855,7 +868,11 @@ static inline int common_timer_del(struct k_itimer *timer)
 
 static inline int timer_delete_hook(struct k_itimer *timer)
 {
-	return CLOCK_DISPATCH(timer->it_clock, timer_del, (timer));
+	struct k_clock *kc = clockid_to_kclock(timer->it_clock);
+
+	if (WARN_ON_ONCE(!kc || !kc->timer_del))
+		return -EINVAL;
+	return kc->timer_del(timer);
 }
 
 /* Delete a POSIX.1b interval timer. */
@@ -927,69 +944,76 @@ void exit_itimers(struct signal_struct *sig)
 	}
 }
 
-/* Not available / possible... functions */
-int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp)
-{
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nosettime);
-
-int do_posix_clock_nonanosleep(const clockid_t clock, int flags,
-			       struct timespec *t, struct timespec __user *r)
-{
-#ifndef ENOTSUP
-	return -EOPNOTSUPP;	/* aka ENOTSUP in userland for POSIX */
-#else  /*  parisc does define it separately.  */
-	return -ENOTSUP;
-#endif
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep);
-
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec new_tp;
 
-	if (invalid_clockid(which_clock))
+	if (!kc || !kc->clock_set)
 		return -EINVAL;
+
 	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
 		return -EFAULT;
 
-	return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp));
+	return kc->clock_set(which_clock, &new_tp);
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 		struct timespec __user *,tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec kernel_tp;
 	int error;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
-	error = CLOCK_DISPATCH(which_clock, clock_get,
-			       (which_clock, &kernel_tp));
+
+	error = kc->clock_get(which_clock, &kernel_tp);
+
 	if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
 		error = -EFAULT;
 
 	return error;
+}
+
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+		struct timex __user *, utx)
+{
+	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timex ktx;
+	int err;
+
+	if (!kc)
+		return -EINVAL;
+	if (!kc->clock_adj)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&ktx, utx, sizeof(ktx)))
+		return -EFAULT;
+
+	err = kc->clock_adj(which_clock, &ktx);
+
+	if (!err && copy_to_user(utx, &ktx, sizeof(ktx)))
+		return -EFAULT;
 
+	return err;
 }
 
 SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 		struct timespec __user *, tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec rtn_tp;
 	int error;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
 
-	error = CLOCK_DISPATCH(which_clock, clock_getres,
-			       (which_clock, &rtn_tp));
+	error = kc->clock_getres(which_clock, &rtn_tp);
 
-	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp))) {
+	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
 		error = -EFAULT;
-	}
 
 	return error;
 }
@@ -1009,10 +1033,13 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		const struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec t;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
+	if (!kc->nsleep)
+		return -ENANOSLEEP_NOTSUP;
 
 	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
 		return -EFAULT;
@@ -1020,27 +1047,20 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!timespec_valid(&t))
 		return -EINVAL;
 
-	return CLOCK_DISPATCH(which_clock, nsleep,
-			      (which_clock, flags, &t, rmtp));
-}
-
-/*
- * nanosleep_restart for monotonic and realtime clocks
- */
-static int common_nsleep_restart(struct restart_block *restart_block)
-{
-	return hrtimer_nanosleep_restart(restart_block);
+	return kc->nsleep(which_clock, flags, &t, rmtp);
 }
 
 /*
  * This will restart clock_nanosleep. This is required only by
  * compat_clock_nanosleep_restart for now.
  */
-long
-clock_nanosleep_restart(struct restart_block *restart_block)
+long clock_nanosleep_restart(struct restart_block *restart_block)
 {
-	clockid_t which_clock = restart_block->arg0;
+	clockid_t which_clock = restart_block->nanosleep.index;
+	struct k_clock *kc = clockid_to_kclock(which_clock);
+
+	if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
+		return -EINVAL;
 
-	return CLOCK_DISPATCH(which_clock, nsleep_restart,
-			      (restart_block));
+	return kc->nsleep_restart(restart_block);
 }
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 265729966ece..4603f08dc47b 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -1,125 +1,12 @@
-config PM
-	bool "Power Management support"
-	depends on !IA64_HP_SIM
-	---help---
-	  "Power Management" means that parts of your computer are shut
-	  off or put into a power conserving "sleep" mode if they are not
-	  being used.  There are two competing standards for doing this: APM
-	  and ACPI.  If you want to use either one, say Y here and then also
-	  to the requisite support below.
-
-	  Power Management is most important for battery powered laptop
-	  computers; if you have a laptop, check out the Linux Laptop home
-	  page on the WWW at <http://www.linux-on-laptops.com/> or
-	  Tuxmobil - Linux on Mobile Computers at <http://www.tuxmobil.org/>
-	  and the Battery Powered Linux mini-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
-
-	  Note that, even if you say N here, Linux on the x86 architecture
-	  will issue the hlt instruction if nothing is to be done, thereby
-	  sending the processor to sleep and saving power.
-
-config PM_DEBUG
-	bool "Power Management Debug Support"
-	depends on PM
-	---help---
-	This option enables various debugging support in the Power Management
-	code. This is helpful when debugging and reporting PM bugs, like
-	suspend support.
-
-config PM_ADVANCED_DEBUG
-	bool "Extra PM attributes in sysfs for low-level debugging/testing"
-	depends on PM_DEBUG
-	default n
-	---help---
-	Add extra sysfs attributes allowing one to access some Power Management
-	fields of device objects from user space.  If you are not a kernel
-	developer interested in debugging/testing Power Management, say "no".
-
-config PM_VERBOSE
-	bool "Verbose Power Management debugging"
-	depends on PM_DEBUG
-	default n
-	---help---
-	This option enables verbose messages from the Power Management code.
-
-config CAN_PM_TRACE
-	def_bool y
-	depends on PM_DEBUG && PM_SLEEP && EXPERIMENTAL
-
-config PM_TRACE
-	bool
-	help
-	  This enables code to save the last PM event point across
-	  reboot. The architecture needs to support this, x86 for
-	  example does by saving things in the RTC, see below.
-
-	  The architecture specific code must provide the extern
-	  functions from <linux/resume-trace.h> as well as the
-	  <asm/resume-trace.h> header with a TRACE_RESUME() macro.
-
-	  The way the information is presented is architecture-
-	  dependent, x86 will print the information during a
-	  late_initcall.
-
-config PM_TRACE_RTC
-	bool "Suspend/resume event tracing"
-	depends on CAN_PM_TRACE
-	depends on X86
-	select PM_TRACE
-	default n
-	---help---
-	This enables some cheesy code to save the last PM event point in the
-	RTC across reboots, so that you can debug a machine that just hangs
-	during suspend (or more commonly, during resume).
-
-	To use this debugging feature you should attempt to suspend the
-	machine, reboot it and then run
-
-		dmesg -s 1000000 | grep 'hash matches'
-
-	CAUTION: this option will cause your machine's real-time clock to be
-	set to an invalid time after a resume.
-
-config PM_SLEEP_SMP
-	bool
-	depends on SMP
-	depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE
-	depends on PM_SLEEP
-	select HOTPLUG
-	select HOTPLUG_CPU
-	default y
-
-config PM_SLEEP
-	bool
-	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
-	default y
-
-config PM_SLEEP_ADVANCED_DEBUG
-	bool
-	depends on PM_ADVANCED_DEBUG
-	default n
-
 config SUSPEND
 	bool "Suspend to RAM and standby"
-	depends on PM && ARCH_SUSPEND_POSSIBLE
+	depends on ARCH_SUSPEND_POSSIBLE
 	default y
 	---help---
 	  Allow the system to enter sleep states in which main memory is
 	  powered and thus its contents are preserved, such as the
 	  suspend-to-RAM state (e.g. the ACPI S3 state).
 
-config PM_TEST_SUSPEND
-	bool "Test suspend/resume and wakealarm during bootup"
-	depends on SUSPEND && PM_DEBUG && RTC_CLASS=y
-	---help---
-	This option will let you suspend your machine during bootup, and
-	make it wake up a few seconds later using an RTC wakeup alarm.
-	Enable this with a kernel parameter like "test_suspend=mem".
-
-	You probably want to have your system's RTC driver statically
-	linked, ensuring that it's available when this test runs.
-
 config SUSPEND_FREEZER
 	bool "Enable freezer for suspend to RAM/standby" \
 		if ARCH_WANTS_FREEZER_CONTROL || BROKEN
@@ -133,7 +20,7 @@ config SUSPEND_FREEZER
 
 config HIBERNATION
 	bool "Hibernation (aka 'suspend to disk')"
-	depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
+	depends on SWAP && ARCH_HIBERNATION_POSSIBLE
 	select LZO_COMPRESS
 	select LZO_DECOMPRESS
 	---help---
@@ -196,6 +83,106 @@ config PM_STD_PARTITION
 	  suspended image to. It will simply pick the first available swap 
 	  device.
 
+config PM_SLEEP
+	def_bool y
+	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
+
+config PM_SLEEP_SMP
+	def_bool y
+	depends on SMP
+	depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE
+	depends on PM_SLEEP
+	select HOTPLUG
+	select HOTPLUG_CPU
+
+config PM_RUNTIME
+	bool "Run-time PM core functionality"
+	depends on !IA64_HP_SIM
+	---help---
+	  Enable functionality allowing I/O devices to be put into energy-saving
+	  (low power) states at run time (or autosuspended) after a specified
+	  period of inactivity and woken up in response to a hardware-generated
+	  wake-up event or a driver's request.
+
+	  Hardware support is generally required for this functionality to work
+	  and the bus type drivers of the buses the devices are on are
+	  responsible for the actual handling of the autosuspend requests and
+	  wake-up events.
+
+config PM
+	def_bool y
+	depends on PM_SLEEP || PM_RUNTIME
+
+config PM_DEBUG
+	bool "Power Management Debug Support"
+	depends on PM
+	---help---
+	This option enables various debugging support in the Power Management
+	code. This is helpful when debugging and reporting PM bugs, like
+	suspend support.
+
+config PM_VERBOSE
+	bool "Verbose Power Management debugging"
+	depends on PM_DEBUG
+	---help---
+	This option enables verbose messages from the Power Management code.
+
+config PM_ADVANCED_DEBUG
+	bool "Extra PM attributes in sysfs for low-level debugging/testing"
+	depends on PM_DEBUG
+	---help---
+	Add extra sysfs attributes allowing one to access some Power Management
+	fields of device objects from user space.  If you are not a kernel
+	developer interested in debugging/testing Power Management, say "no".
+
+config PM_TEST_SUSPEND
+	bool "Test suspend/resume and wakealarm during bootup"
+	depends on SUSPEND && PM_DEBUG && RTC_CLASS=y
+	---help---
+	This option will let you suspend your machine during bootup, and
+	make it wake up a few seconds later using an RTC wakeup alarm.
+	Enable this with a kernel parameter like "test_suspend=mem".
+
+	You probably want to have your system's RTC driver statically
+	linked, ensuring that it's available when this test runs.
+
+config CAN_PM_TRACE
+	def_bool y
+	depends on PM_DEBUG && PM_SLEEP
+
+config PM_TRACE
+	bool
+	help
+	  This enables code to save the last PM event point across
+	  reboot. The architecture needs to support this, x86 for
+	  example does by saving things in the RTC, see below.
+
+	  The architecture specific code must provide the extern
+	  functions from <linux/resume-trace.h> as well as the
+	  <asm/resume-trace.h> header with a TRACE_RESUME() macro.
+
+	  The way the information is presented is architecture-
+	  dependent, x86 will print the information during a
+	  late_initcall.
+
+config PM_TRACE_RTC
+	bool "Suspend/resume event tracing"
+	depends on CAN_PM_TRACE
+	depends on X86
+	select PM_TRACE
+	---help---
+	This enables some cheesy code to save the last PM event point in the
+	RTC across reboots, so that you can debug a machine that just hangs
+	during suspend (or more commonly, during resume).
+
+	To use this debugging feature you should attempt to suspend the
+	machine, reboot it and then run
+
+		dmesg -s 1000000 | grep 'hash matches'
+
+	CAUTION: this option will cause your machine's real-time clock to be
+	set to an invalid time after a resume.
+
 config APM_EMULATION
 	tristate "Advanced Power Management Emulation"
 	depends on PM && SYS_SUPPORTS_APM_EMULATION
@@ -222,31 +209,11 @@ config APM_EMULATION
 	  anything, try disabling/enabling this option (or disabling/enabling
 	  APM in your BIOS).
 
-config PM_RUNTIME
-	bool "Run-time PM core functionality"
-	depends on PM
-	---help---
-	  Enable functionality allowing I/O devices to be put into energy-saving
-	  (low power) states at run time (or autosuspended) after a specified
-	  period of inactivity and woken up in response to a hardware-generated
-	  wake-up event or a driver's request.
-
-	  Hardware support is generally required for this functionality to work
-	  and the bus type drivers of the buses the devices are on are
-	  responsible for the actual handling of the autosuspend requests and
-	  wake-up events.
-
-config PM_OPS
-	bool
-	depends on PM_SLEEP || PM_RUNTIME
-	default y
-
 config ARCH_HAS_OPP
 	bool
 
 config PM_OPP
 	bool "Operating Performance Point (OPP) Layer library"
-	depends on PM
 	depends on ARCH_HAS_OPP
 	---help---
 	  SOCs have a standard set of tuples consisting of frequency and
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 1832bd264219..aeabd26e3342 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/freezer.h>
 #include <linux/gfp.h>
+#include <linux/syscore_ops.h>
 #include <scsi/scsi_scan.h>
 #include <asm/suspend.h>
 
@@ -272,6 +273,8 @@ static int create_image(int platform_mode)
 	local_irq_disable();
 
 	error = sysdev_suspend(PMSG_FREEZE);
+	if (!error)
+		error = syscore_suspend();
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
@@ -295,6 +298,7 @@ static int create_image(int platform_mode)
 	}
 
  Power_up:
+	syscore_resume();
 	sysdev_resume();
 	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
@@ -403,6 +407,8 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_disable();
 
 	error = sysdev_suspend(PMSG_QUIESCE);
+	if (!error)
+		error = syscore_suspend();
 	if (error)
 		goto Enable_irqs;
 
@@ -429,6 +435,7 @@ static int resume_target_kernel(bool platform_mode)
 	restore_processor_state();
 	touch_softlockup_watchdog();
 
+	syscore_resume();
 	sysdev_resume();
 
  Enable_irqs:
@@ -516,6 +523,7 @@ int hibernation_platform_enter(void)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_HIBERNATE);
+	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
 		goto Power_up;
@@ -526,6 +534,7 @@ int hibernation_platform_enter(void)
 	while (1);
 
  Power_up:
+	syscore_resume();
 	sysdev_resume();
 	local_irq_enable();
 	enable_nonboot_cpus();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7b5db6a8561e..8eaba5f27b10 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -17,9 +17,6 @@
 
 DEFINE_MUTEX(pm_mutex);
 
-unsigned int pm_flags;
-EXPORT_SYMBOL(pm_flags);
-
 #ifdef CONFIG_PM_SLEEP
 
 /* Routines for PM-transition notifications */
@@ -326,7 +323,7 @@ EXPORT_SYMBOL_GPL(pm_wq);
 
 static int __init pm_start_workqueue(void)
 {
-	pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+	pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
 
 	return pm_wq ? 0 : -ENOMEM;
 }
diff --git a/kernel/power/process.c b/kernel/power/process.c
index d6d2a10320e0..0cf3a27a6c9d 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -22,7 +22,7 @@
  */
 #define TIMEOUT	(20 * HZ)
 
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
 {
 	if ((p == current) ||
 	    (p->flags & PF_NOFREEZE) ||
@@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only)
 		todo = 0;
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			if (frozen(p) || !freezeable(p))
+			if (frozen(p) || !freezable(p))
 				continue;
 
 			if (!freeze_task(p, sig_only))
@@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only)
 
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
-		if (!freezeable(p))
+		if (!freezable(p))
 			continue;
 
 		if (nosig_only && should_send_signal(p))
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0dac75ea4456..ca0aacc24874 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -42,15 +42,15 @@ static void swsusp_unset_page_forbidden(struct page *);
 
 /*
  * Preferred image size in bytes (tunable via /sys/power/image_size).
- * When it is set to N, swsusp will do its best to ensure the image
- * size will not exceed N bytes, but if that is impossible, it will
- * try to create the smallest image possible.
+ * When it is set to N, the image creating code will do its best to
+ * ensure the image size will not exceed N bytes, but if that is
+ * impossible, it will try to create the smallest image possible.
  */
 unsigned long image_size;
 
 void __init hibernate_image_size_init(void)
 {
-	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
+	image_size = (totalram_pages / 3) * PAGE_SIZE;
 }
 
 /* List of PBEs needed for restoring the pages that were allocated before
@@ -1519,11 +1519,8 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 		unsigned int nr_pages, unsigned int nr_highmem)
 {
-	int error = 0;
-
 	if (nr_highmem > 0) {
-		error = get_highmem_buffer(PG_ANY);
-		if (error)
+		if (get_highmem_buffer(PG_ANY))
 			goto err_out;
 		if (nr_highmem > alloc_highmem) {
 			nr_highmem -= alloc_highmem;
@@ -1546,7 +1543,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 
  err_out:
 	swsusp_free();
-	return error;
+	return -ENOMEM;
 }
 
 asmlinkage int swsusp_save(void)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index de6f86bfa303..2814c32aed51 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -22,6 +22,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/syscore_ops.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -163,11 +164,14 @@ static int suspend_enter(suspend_state_t state)
 	BUG_ON(!irqs_disabled());
 
 	error = sysdev_suspend(PMSG_SUSPEND);
+	if (!error)
+		error = syscore_suspend();
 	if (!error) {
 		if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
 			error = suspend_ops->enter(state);
 			events_check_enabled = false;
 		}
+		syscore_resume();
 		sysdev_resume();
 	}
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 36231525e22f..33284adb2189 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -515,6 +515,71 @@ static void _call_console_drivers(unsigned start,
 }
 
 /*
+ * Parse the syslog header <[0-9]*>. The decimal value represents 32bit, the
+ * lower 3 bit are the log level, the rest are the log facility. In case
+ * userspace passes usual userspace syslog messages to /dev/kmsg or
+ * /dev/ttyprintk, the log prefix might contain the facility. Printk needs
+ * to extract the correct log level for in-kernel processing, and not mangle
+ * the original value.
+ *
+ * If a prefix is found, the length of the prefix is returned. If 'level' is
+ * passed, it will be filled in with the log level without a possible facility
+ * value. If 'special' is passed, the special printk prefix chars are accepted
+ * and returned. If no valid header is found, 0 is returned and the passed
+ * variables are not touched.
+ */
+static size_t log_prefix(const char *p, unsigned int *level, char *special)
+{
+	unsigned int lev = 0;
+	char sp = '\0';
+	size_t len;
+
+	if (p[0] != '<' || !p[1])
+		return 0;
+	if (p[2] == '>') {
+		/* usual single digit level number or special char */
+		switch (p[1]) {
+		case '0' ... '7':
+			lev = p[1] - '0';
+			break;
+		case 'c': /* KERN_CONT */
+		case 'd': /* KERN_DEFAULT */
+			sp = p[1];
+			break;
+		default:
+			return 0;
+		}
+		len = 3;
+	} else {
+		/* multi digit including the level and facility number */
+		char *endp = NULL;
+
+		if (p[1] < '0' && p[1] > '9')
+			return 0;
+
+		lev = (simple_strtoul(&p[1], &endp, 10) & 7);
+		if (endp == NULL || endp[0] != '>')
+			return 0;
+		len = (endp + 1) - p;
+	}
+
+	/* do not accept special char if not asked for */
+	if (sp && !special)
+		return 0;
+
+	if (special) {
+		*special = sp;
+		/* return special char, do not touch level */
+		if (sp)
+			return len;
+	}
+
+	if (level)
+		*level = lev;
+	return len;
+}
+
+/*
  * Call the console drivers, asking them to write out
  * log_buf[start] to log_buf[end - 1].
  * The console_lock must be held.
@@ -529,13 +594,9 @@ static void call_console_drivers(unsigned start, unsigned end)
 	cur_index = start;
 	start_print = start;
 	while (cur_index != end) {
-		if (msg_level < 0 && ((end - cur_index) > 2) &&
-				LOG_BUF(cur_index + 0) == '<' &&
-				LOG_BUF(cur_index + 1) >= '0' &&
-				LOG_BUF(cur_index + 1) <= '7' &&
-				LOG_BUF(cur_index + 2) == '>') {
-			msg_level = LOG_BUF(cur_index + 1) - '0';
-			cur_index += 3;
+		if (msg_level < 0 && ((end - cur_index) > 2)) {
+			/* strip log prefix */
+			cur_index += log_prefix(&LOG_BUF(cur_index), &msg_level, NULL);
 			start_print = cur_index;
 		}
 		while (cur_index != end) {
@@ -733,6 +794,8 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	unsigned long flags;
 	int this_cpu;
 	char *p;
+	size_t plen;
+	char special;
 
 	boot_delay_msec();
 	printk_delay();
@@ -773,45 +836,52 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	printed_len += vscnprintf(printk_buf + printed_len,
 				  sizeof(printk_buf) - printed_len, fmt, args);
 
-
 	p = printk_buf;
 
-	/* Do we have a loglevel in the string? */
-	if (p[0] == '<') {
-		unsigned char c = p[1];
-		if (c && p[2] == '>') {
-			switch (c) {
-			case '0' ... '7': /* loglevel */
-				current_log_level = c - '0';
-			/* Fallthrough - make sure we're on a new line */
-			case 'd': /* KERN_DEFAULT */
-				if (!new_text_line) {
-					emit_log_char('\n');
-					new_text_line = 1;
-				}
-			/* Fallthrough - skip the loglevel */
-			case 'c': /* KERN_CONT */
-				p += 3;
-				break;
+	/* Read log level and handle special printk prefix */
+	plen = log_prefix(p, &current_log_level, &special);
+	if (plen) {
+		p += plen;
+
+		switch (special) {
+		case 'c': /* Strip <c> KERN_CONT, continue line */
+			plen = 0;
+			break;
+		case 'd': /* Strip <d> KERN_DEFAULT, start new line */
+			plen = 0;
+		default:
+			if (!new_text_line) {
+				emit_log_char('\n');
+				new_text_line = 1;
 			}
 		}
 	}
 
 	/*
-	 * Copy the output into log_buf.  If the caller didn't provide
-	 * appropriate log level tags, we insert them here
+	 * Copy the output into log_buf. If the caller didn't provide
+	 * the appropriate log prefix, we insert them here
 	 */
-	for ( ; *p; p++) {
+	for (; *p; p++) {
 		if (new_text_line) {
-			/* Always output the token */
-			emit_log_char('<');
-			emit_log_char(current_log_level + '0');
-			emit_log_char('>');
-			printed_len += 3;
 			new_text_line = 0;
 
+			if (plen) {
+				/* Copy original log prefix */
+				int i;
+
+				for (i = 0; i < plen; i++)
+					emit_log_char(printk_buf[i]);
+				printed_len += plen;
+			} else {
+				/* Add log prefix */
+				emit_log_char('<');
+				emit_log_char(current_log_level + '0');
+				emit_log_char('>');
+				printed_len += 3;
+			}
+
 			if (printk_time) {
-				/* Follow the token with the time */
+				/* Add the current time stamp */
 				char tbuf[50], *tp;
 				unsigned tlen;
 				unsigned long long t;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1708b1e2972d..e2302e40b360 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 	return !err;
 }
 
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
 {
 	int retval;
 
@@ -219,7 +219,7 @@ out:
  * Performs checks and sets PT_PTRACED.
  * Should be used by all ptrace implementations for PTRACE_TRACEME.
  */
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
 {
 	int ret = -EPERM;
 
@@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 	return false;
 }
 
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
 {
 	bool dead = false;
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a23a57a976d1..f3240e987928 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -214,11 +214,12 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
+		 * Note that the machinery to reliably determine whether
+		 * or not we are in an RCU read-side critical section
+		 * exists only in the preemptible RCU implementations
+		 * (TINY_PREEMPT_RCU and TREE_PREEMPT_RCU), which is why
+		 * DEBUG_OBJECTS_RCU_HEAD is disallowed if !PREEMPT.
 		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON(1);
-		return 0;
-#else
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
 			WARN_ON(1);
@@ -229,7 +230,6 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
 		rcu_barrier_bh();
 		debug_object_free(head, &rcuhead_debug_descr);
 		return 1;
-#endif
 	default:
 		return 0;
 	}
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 015abaea962a..3cb8e362e883 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -852,7 +852,7 @@ void exit_rcu(void)
 	if (t->rcu_read_lock_nesting == 0)
 		return;
 	t->rcu_read_lock_nesting = 1;
-	rcu_read_unlock();
+	__rcu_read_unlock();
 }
 
 #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 89613f97ff26..c224da41890c 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -47,7 +47,6 @@
 #include <linux/srcu.h>
 #include <linux/slab.h>
 #include <asm/byteorder.h>
-#include <linux/sched.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index ddabb54bb5c8..3c7cbc2c33be 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -215,7 +215,6 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 	put_pid(waiter->deadlock_task_pid);
 	TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry));
 	TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-	TRACE_WARN_ON(waiter->task);
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 66cb89bc5ef1..5c9ccd380966 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -9,7 +9,6 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/sysdev.h>
 #include <linux/timer.h>
@@ -27,7 +26,6 @@ struct test_thread_data {
 	int			opcode;
 	int			opdata;
 	int			mutexes[MAX_RT_TEST_MUTEXES];
-	int			bkl;
 	int			event;
 	struct sys_device	sysdev;
 };
@@ -46,9 +44,8 @@ enum test_opcodes {
 	RTTEST_LOCKINTNOWAIT,	/* 6 Lock interruptible no wait in wakeup, data = lockindex */
 	RTTEST_LOCKCONT,	/* 7 Continue locking after the wakeup delay */
 	RTTEST_UNLOCK,		/* 8 Unlock, data = lockindex */
-	RTTEST_LOCKBKL,		/* 9 Lock BKL */
-	RTTEST_UNLOCKBKL,	/* 10 Unlock BKL */
-	RTTEST_SIGNAL,		/* 11 Signal other test thread, data = thread id */
+	/* 9, 10 - reserved for BKL commemoration */
+	RTTEST_SIGNAL = 11,	/* 11 Signal other test thread, data = thread id */
 	RTTEST_RESETEVENT = 98,	/* 98 Reset event counter */
 	RTTEST_RESET = 99,	/* 99 Reset all pending operations */
 };
@@ -74,13 +71,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
 				td->mutexes[i] = 0;
 			}
 		}
-
-		if (!lockwakeup && td->bkl == 4) {
-#ifdef CONFIG_LOCK_KERNEL
-			unlock_kernel();
-#endif
-			td->bkl = 0;
-		}
 		return 0;
 
 	case RTTEST_RESETEVENT:
@@ -131,25 +121,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
 		td->mutexes[id] = 0;
 		return 0;
 
-	case RTTEST_LOCKBKL:
-		if (td->bkl)
-			return 0;
-		td->bkl = 1;
-#ifdef CONFIG_LOCK_KERNEL
-		lock_kernel();
-#endif
-		td->bkl = 4;
-		return 0;
-
-	case RTTEST_UNLOCKBKL:
-		if (td->bkl != 4)
-			break;
-#ifdef CONFIG_LOCK_KERNEL
-		unlock_kernel();
-#endif
-		td->bkl = 0;
-		return 0;
-
 	default:
 		break;
 	}
@@ -196,7 +167,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex)
 		td->event = atomic_add_return(1, &rttest_event);
 		break;
 
-	case RTTEST_LOCKBKL:
 	default:
 		break;
 	}
@@ -229,8 +199,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex)
 		td->event = atomic_add_return(1, &rttest_event);
 		return;
 
-	case RTTEST_LOCKBKL:
-		return;
 	default:
 		return;
 	}
@@ -380,11 +348,11 @@ static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute
 	spin_lock(&rttest_lock);
 
 	curr += sprintf(curr,
-		"O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, K: %d, M:",
+		"O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, M:",
 		td->opcode, td->event, tsk->state,
 			(MAX_RT_PRIO - 1) - tsk->prio,
 			(MAX_RT_PRIO - 1) - tsk->normal_prio,
-		tsk->pi_blocked_on, td->bkl);
+		tsk->pi_blocked_on);
 
 	for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--)
 		curr += sprintf(curr, "%d", td->mutexes[i]);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a9604815786a..ab449117aaf2 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -20,41 +20,34 @@
 /*
  * lock->owner state tracking:
  *
- * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1
- * are used to keep track of the "owner is pending" and "lock has
- * waiters" state.
+ * lock->owner holds the task_struct pointer of the owner. Bit 0
+ * is used to keep track of the "lock has waiters" state.
  *
- * owner	bit1	bit0
- * NULL		0	0	lock is free (fast acquire possible)
- * NULL		0	1	invalid state
- * NULL		1	0	Transitional State*
- * NULL		1	1	invalid state
- * taskpointer	0	0	lock is held (fast release possible)
- * taskpointer	0	1	task is pending owner
- * taskpointer	1	0	lock is held and has waiters
- * taskpointer	1	1	task is pending owner and lock has more waiters
- *
- * Pending ownership is assigned to the top (highest priority)
- * waiter of the lock, when the lock is released. The thread is woken
- * up and can now take the lock. Until the lock is taken (bit 0
- * cleared) a competing higher priority thread can steal the lock
- * which puts the woken up thread back on the waiters list.
+ * owner	bit0
+ * NULL		0	lock is free (fast acquire possible)
+ * NULL		1	lock is free and has waiters and the top waiter
+ *				is going to take the lock*
+ * taskpointer	0	lock is held (fast release possible)
+ * taskpointer	1	lock is held and has waiters**
  *
  * The fast atomic compare exchange based acquire and release is only
- * possible when bit 0 and 1 of lock->owner are 0.
+ * possible when bit 0 of lock->owner is 0.
+ *
+ * (*) It also can be a transitional state when grabbing the lock
+ * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+ * we need to set the bit0 before looking at the lock, and the owner may be
+ * NULL in this small time, hence this can be a transitional state.
  *
- * (*) There's a small time where the owner can be NULL and the
- * "lock has waiters" bit is set.  This can happen when grabbing the lock.
- * To prevent a cmpxchg of the owner releasing the lock, we need to set this
- * bit before looking at the lock, hence the reason this is a transitional
- * state.
+ * (**) There is a small time when bit 0 is set but there are no
+ * waiters. This can happen when grabbing the lock in the slow path.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to
+ * set this bit before looking at the lock.
  */
 
 static void
-rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
-		   unsigned long mask)
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
 {
-	unsigned long val = (unsigned long)owner | mask;
+	unsigned long val = (unsigned long)owner;
 
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
@@ -203,15 +196,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * reached or the state of the chain has changed while we
 	 * dropped the locks.
 	 */
-	if (!waiter || !waiter->task)
+	if (!waiter)
 		goto out_unlock_pi;
 
 	/*
 	 * Check the orig_waiter state. After we dropped the locks,
-	 * the previous owner of the lock might have released the lock
-	 * and made us the pending owner:
+	 * the previous owner of the lock might have released the lock.
 	 */
-	if (orig_waiter && !orig_waiter->task)
+	if (orig_waiter && !rt_mutex_owner(orig_lock))
 		goto out_unlock_pi;
 
 	/*
@@ -254,6 +246,17 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	if (!rt_mutex_owner(lock)) {
+		/*
+		 * If the requeue above changed the top waiter, then we need
+		 * to wake the new top waiter up to try to get the lock.
+		 */
+
+		if (top_waiter != rt_mutex_top_waiter(lock))
+			wake_up_process(rt_mutex_top_waiter(lock)->task);
+		raw_spin_unlock(&lock->wait_lock);
+		goto out_put_task;
+	}
 	put_task_struct(task);
 
 	/* Grab the next task */
@@ -296,78 +299,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 }
 
 /*
- * Optimization: check if we can steal the lock from the
- * assigned pending owner [which might not have taken the
- * lock yet]:
- */
-static inline int try_to_steal_lock(struct rt_mutex *lock,
-				    struct task_struct *task)
-{
-	struct task_struct *pendowner = rt_mutex_owner(lock);
-	struct rt_mutex_waiter *next;
-	unsigned long flags;
-
-	if (!rt_mutex_owner_pending(lock))
-		return 0;
-
-	if (pendowner == task)
-		return 1;
-
-	raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-	if (task->prio >= pendowner->prio) {
-		raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-		return 0;
-	}
-
-	/*
-	 * Check if a waiter is enqueued on the pending owners
-	 * pi_waiters list. Remove it and readjust pending owners
-	 * priority.
-	 */
-	if (likely(!rt_mutex_has_waiters(lock))) {
-		raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-		return 1;
-	}
-
-	/* No chain handling, pending owner is not blocked on anything: */
-	next = rt_mutex_top_waiter(lock);
-	plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
-	__rt_mutex_adjust_prio(pendowner);
-	raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
-	/*
-	 * We are going to steal the lock and a waiter was
-	 * enqueued on the pending owners pi_waiters queue. So
-	 * we have to enqueue this waiter into
-	 * task->pi_waiters list. This covers the case,
-	 * where task is boosted because it holds another
-	 * lock and gets unboosted because the booster is
-	 * interrupted, so we would delay a waiter with higher
-	 * priority as task->normal_prio.
-	 *
-	 * Note: in the rare case of a SCHED_OTHER task changing
-	 * its priority and thus stealing the lock, next->task
-	 * might be task:
-	 */
-	if (likely(next->task != task)) {
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
-		plist_add(&next->pi_list_entry, &task->pi_waiters);
-		__rt_mutex_adjust_prio(task);
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	}
-	return 1;
-}
-
-/*
  * Try to take an rt-mutex
  *
- * This fails
- * - when the lock has a real owner
- * - when a different pending owner exists and has higher priority than current
- *
  * Must be called with lock->wait_lock held.
+ *
+ * @lock:   the lock to be acquired.
+ * @task:   the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+		struct rt_mutex_waiter *waiter)
 {
 	/*
 	 * We have to be careful here if the atomic speedups are
@@ -390,15 +331,52 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
 	 */
 	mark_rt_mutex_waiters(lock);
 
-	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
+	if (rt_mutex_owner(lock))
 		return 0;
 
+	/*
+	 * It will get the lock because of one of these conditions:
+	 * 1) there is no waiter
+	 * 2) higher priority than waiters
+	 * 3) it is top waiter
+	 */
+	if (rt_mutex_has_waiters(lock)) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+			if (!waiter || waiter != rt_mutex_top_waiter(lock))
+				return 0;
+		}
+	}
+
+	if (waiter || rt_mutex_has_waiters(lock)) {
+		unsigned long flags;
+		struct rt_mutex_waiter *top;
+
+		raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+		/* remove the queued waiter. */
+		if (waiter) {
+			plist_del(&waiter->list_entry, &lock->wait_list);
+			task->pi_blocked_on = NULL;
+		}
+
+		/*
+		 * We have to enqueue the top waiter(if it exists) into
+		 * task->pi_waiters list.
+		 */
+		if (rt_mutex_has_waiters(lock)) {
+			top = rt_mutex_top_waiter(lock);
+			top->pi_list_entry.prio = top->list_entry.prio;
+			plist_add(&top->pi_list_entry, &task->pi_waiters);
+		}
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	}
+
 	/* We got the lock. */
 	debug_rt_mutex_lock(lock);
 
-	rt_mutex_set_owner(lock, current, 0);
+	rt_mutex_set_owner(lock, task);
 
-	rt_mutex_deadlock_account_lock(lock, current);
+	rt_mutex_deadlock_account_lock(lock, task);
 
 	return 1;
 }
@@ -436,6 +414,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
+	if (!owner)
+		return 0;
+
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
@@ -472,21 +453,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and from
- * the lock waiter list. Set it as pending owner. Then wake it up.
+ * Remove the top waiter from the current tasks waiter list and wake it up.
  *
  * Called with lock->wait_lock held.
  */
 static void wakeup_next_waiter(struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *waiter;
-	struct task_struct *pendowner;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 
 	waiter = rt_mutex_top_waiter(lock);
-	plist_del(&waiter->list_entry, &lock->wait_list);
 
 	/*
 	 * Remove it from current->pi_waiters. We do not adjust a
@@ -495,43 +473,19 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * lock->wait_lock.
 	 */
 	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
-	pendowner = waiter->task;
-	waiter->task = NULL;
 
-	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
+	rt_mutex_set_owner(lock, NULL);
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	/*
-	 * Clear the pi_blocked_on variable and enqueue a possible
-	 * waiter into the pi_waiters list of the pending owner. This
-	 * prevents that in case the pending owner gets unboosted a
-	 * waiter with higher priority than pending-owner->normal_prio
-	 * is blocked on the unboosted (pending) owner.
-	 */
-	raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-
-	WARN_ON(!pendowner->pi_blocked_on);
-	WARN_ON(pendowner->pi_blocked_on != waiter);
-	WARN_ON(pendowner->pi_blocked_on->lock != lock);
-
-	pendowner->pi_blocked_on = NULL;
-
-	if (rt_mutex_has_waiters(lock)) {
-		struct rt_mutex_waiter *next;
-
-		next = rt_mutex_top_waiter(lock);
-		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
-	}
-	raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
-	wake_up_process(pendowner);
+	wake_up_process(waiter->task);
 }
 
 /*
- * Remove a waiter from a lock
+ * Remove a waiter from a lock and give up
  *
- * Must be called with lock->wait_lock held
+ * Must be called with lock->wait_lock held and
+ * have just failed to try_to_take_rt_mutex().
  */
 static void remove_waiter(struct rt_mutex *lock,
 			  struct rt_mutex_waiter *waiter)
@@ -543,11 +497,13 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->task = NULL;
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	if (first && owner != current) {
+	if (!owner)
+		return;
+
+	if (first) {
 
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
@@ -614,21 +570,19 @@ void rt_mutex_adjust_pi(struct task_struct *task)
  * 			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
- * @detect_deadlock:	 passed to task_blocks_on_rt_mutex
  *
  * lock->wait_lock must be held by the caller.
  */
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct hrtimer_sleeper *timeout,
-		    struct rt_mutex_waiter *waiter,
-		    int detect_deadlock)
+		    struct rt_mutex_waiter *waiter)
 {
 	int ret = 0;
 
 	for (;;) {
 		/* Try to acquire the lock: */
-		if (try_to_take_rt_mutex(lock))
+		if (try_to_take_rt_mutex(lock, current, waiter))
 			break;
 
 		/*
@@ -645,39 +599,11 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 				break;
 		}
 
-		/*
-		 * waiter->task is NULL the first time we come here and
-		 * when we have been woken up by the previous owner
-		 * but the lock got stolen by a higher prio task.
-		 */
-		if (!waiter->task) {
-			ret = task_blocks_on_rt_mutex(lock, waiter, current,
-						      detect_deadlock);
-			/*
-			 * If we got woken up by the owner then start loop
-			 * all over without going into schedule to try
-			 * to get the lock now:
-			 */
-			if (unlikely(!waiter->task)) {
-				/*
-				 * Reset the return value. We might
-				 * have returned with -EDEADLK and the
-				 * owner released the lock while we
-				 * were walking the pi chain.
-				 */
-				ret = 0;
-				continue;
-			}
-			if (unlikely(ret))
-				break;
-		}
-
 		raw_spin_unlock(&lock->wait_lock);
 
 		debug_rt_mutex_print_deadlock(waiter);
 
-		if (waiter->task)
-			schedule_rt_mutex(lock);
+		schedule_rt_mutex(lock);
 
 		raw_spin_lock(&lock->wait_lock);
 		set_current_state(state);
@@ -698,12 +624,11 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
-	waiter.task = NULL;
 
 	raw_spin_lock(&lock->wait_lock);
 
 	/* Try to acquire the lock again: */
-	if (try_to_take_rt_mutex(lock)) {
+	if (try_to_take_rt_mutex(lock, current, NULL)) {
 		raw_spin_unlock(&lock->wait_lock);
 		return 0;
 	}
@@ -717,12 +642,14 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 			timeout->task = NULL;
 	}
 
-	ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
-				  detect_deadlock);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+
+	if (likely(!ret))
+		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(waiter.task))
+	if (unlikely(ret))
 		remove_waiter(lock, &waiter);
 
 	/*
@@ -737,14 +664,6 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	if (unlikely(timeout))
 		hrtimer_cancel(&timeout->timer);
 
-	/*
-	 * Readjust priority, when we did not get the lock. We might
-	 * have been the pending owner and boosted. Since we did not
-	 * take the lock, the PI boost has to go.
-	 */
-	if (unlikely(ret))
-		rt_mutex_adjust_prio(current);
-
 	debug_rt_mutex_free_waiter(&waiter);
 
 	return ret;
@@ -762,7 +681,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 
 	if (likely(rt_mutex_owner(lock) != current)) {
 
-		ret = try_to_take_rt_mutex(lock);
+		ret = try_to_take_rt_mutex(lock, current, NULL);
 		/*
 		 * try_to_take_rt_mutex() sets the lock waiters
 		 * bit unconditionally. Clean this up.
@@ -992,7 +911,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 {
 	__rt_mutex_init(lock, NULL);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
-	rt_mutex_set_owner(lock, proxy_owner, 0);
+	rt_mutex_set_owner(lock, proxy_owner);
 	rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
@@ -1008,7 +927,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 			   struct task_struct *proxy_owner)
 {
 	debug_rt_mutex_proxy_unlock(lock);
-	rt_mutex_set_owner(lock, NULL, 0);
+	rt_mutex_set_owner(lock, NULL);
 	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
@@ -1034,20 +953,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_lock(&lock->wait_lock);
 
-	mark_rt_mutex_waiters(lock);
-
-	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
-		/* We got the lock for task. */
-		debug_rt_mutex_lock(lock);
-		rt_mutex_set_owner(lock, task, 0);
+	if (try_to_take_rt_mutex(lock, task, NULL)) {
 		raw_spin_unlock(&lock->wait_lock);
-		rt_mutex_deadlock_account_lock(lock, task);
 		return 1;
 	}
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
-	if (ret && !waiter->task) {
+	if (ret && !rt_mutex_owner(lock)) {
 		/*
 		 * Reset the return value. We might have
 		 * returned with -EDEADLK and the owner
@@ -1056,6 +969,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		 */
 		ret = 0;
 	}
+
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
+
 	raw_spin_unlock(&lock->wait_lock);
 
 	debug_rt_mutex_print_deadlock(waiter);
@@ -1110,12 +1027,11 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
-				  detect_deadlock);
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(waiter->task))
+	if (unlikely(ret))
 		remove_waiter(lock, waiter);
 
 	/*
@@ -1126,13 +1042,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	/*
-	 * Readjust priority, when we did not get the lock. We might have been
-	 * the pending owner and boosted. Since we did not take the lock, the
-	 * PI boost has to go.
-	 */
-	if (unlikely(ret))
-		rt_mutex_adjust_prio(current);
-
 	return ret;
 }
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 97a2f81866af..53a66c85261b 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -91,9 +91,8 @@ task_top_pi_waiter(struct task_struct *p)
 /*
  * lock->owner state tracking:
  */
-#define RT_MUTEX_OWNER_PENDING	1UL
-#define RT_MUTEX_HAS_WAITERS	2UL
-#define RT_MUTEX_OWNER_MASKALL	3UL
+#define RT_MUTEX_HAS_WAITERS	1UL
+#define RT_MUTEX_OWNER_MASKALL	1UL
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
@@ -101,17 +100,6 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
 }
 
-static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
-{
-	return (struct task_struct *)
-		((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
-}
-
-static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
-{
-	return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
-}
-
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..a172494a9a63 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -32,7 +32,6 @@
 #include <linux/init.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
-#include <linux/smp_lock.h>
 #include <asm/mmu_context.h>
 #include <linux/interrupt.h>
 #include <linux/capability.h>
@@ -324,7 +323,7 @@ struct cfs_rq {
 	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr, *next, *last;
+	struct sched_entity *curr, *next, *last, *skip;
 
 	unsigned int nr_spread_over;
 
@@ -606,9 +605,6 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
-	if (p->flags & PF_EXITING)
-		return &root_task_group;
-
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
@@ -664,10 +660,9 @@ static void update_rq_clock(struct rq *rq)
 #endif
 
 /**
- * runqueue_is_locked
+ * runqueue_is_locked - Returns true if the current cpu runqueue is locked
  * @cpu: the processor in question.
  *
- * Returns true if the current cpu runqueue is locked.
  * This interface allows printk to be called with the runqueue lock
  * held and know whether or not it is OK to wake up the klogd.
  */
@@ -1686,6 +1681,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 		__release(rq2->lock);
 }
 
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	BUG_ON(rq1 != rq2);
+	raw_spin_lock(&rq1->lock);
+	__acquire(rq2->lock);	/* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	BUG_ON(rq1 != rq2);
+	raw_spin_unlock(&rq1->lock);
+	__release(rq2->lock);
+}
+
 #endif
 
 static void calc_load_account_idle(struct rq *this_rq);
@@ -1880,7 +1908,7 @@ void account_system_vtime(struct task_struct *curr)
 	 */
 	if (hardirq_count())
 		__this_cpu_add(cpu_hardirq_time, delta);
-	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
 		__this_cpu_add(cpu_softirq_time, delta);
 
 	irq_time_write_end();
@@ -1920,8 +1948,40 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 		sched_rt_avg_update(rq, irq_delta);
 }
 
+static int irqtime_account_hi_update(void)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_hardirq_time);
+	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_softirq_time);
+	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
+#define sched_clock_irqtime	(0)
+
 static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
 	rq->clock_task += delta;
@@ -2025,14 +2085,14 @@ inline int task_curr(const struct task_struct *p)
 
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 				       const struct sched_class *prev_class,
-				       int oldprio, int running)
+				       int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
-			prev_class->switched_from(rq, p, running);
-		p->sched_class->switched_to(rq, p, running);
-	} else
-		p->sched_class->prio_changed(rq, p, oldprio, running);
+			prev_class->switched_from(rq, p);
+		p->sched_class->switched_to(rq, p);
+	} else if (oldprio != p->prio)
+		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
 static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
@@ -2224,7 +2284,10 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * yield - it could be a while.
 		 */
 		if (unlikely(on_rq)) {
-			schedule_timeout_uninterruptible(1);
+			ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
+
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
 			continue;
 		}
 
@@ -2265,27 +2328,6 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 #endif /* CONFIG_SMP */
 
-/**
- * task_oncpu_function_call - call a function on the cpu on which a task runs
- * @p:		the task to evaluate
- * @func:	the function to be called
- * @info:	the function call argument
- *
- * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
- */
-void task_oncpu_function_call(struct task_struct *p,
-			      void (*func) (void *info), void *info)
-{
-	int cpu;
-
-	preempt_disable();
-	cpu = task_cpu(p);
-	if (task_curr(p))
-		smp_call_function_single(cpu, func, info, 1);
-	preempt_enable();
-}
-
 #ifdef CONFIG_SMP
 /*
  * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
@@ -2566,6 +2608,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
+	p->se.vruntime			= 0;
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -2776,9 +2819,12 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
+	sched_info_switch(prev, next);
+	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_lock_switch(rq, next);
 	prepare_arch_switch(next);
+	trace_sched_switch(prev, next);
 }
 
 /**
@@ -2911,7 +2957,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_sched_switch(prev, next);
+
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -3568,6 +3614,32 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 }
 
 /*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+			cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+	cputime64_t tmp = cputime_to_cputime64(cputime);
+
+	/* Add system time to process. */
+	p->stime = cputime_add(p->stime, cputime);
+	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+	account_group_system_time(p, cputime);
+
+	/* Add system time to cpustat. */
+	*target_cputime64 = cputime64_add(*target_cputime64, tmp);
+	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
+	/* Account for system time used */
+	acct_update_integrals(p);
+}
+
+/*
  * 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()
@@ -3578,36 +3650,26 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 			 cputime_t cputime, cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	cputime64_t tmp;
+	cputime64_t *target_cputime64;
 
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
 		account_guest_time(p, cputime, cputime_scaled);
 		return;
 	}
 
-	/* Add system time to process. */
-	p->stime = cputime_add(p->stime, cputime);
-	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
-	account_group_system_time(p, cputime);
-
-	/* Add system time to cpustat. */
-	tmp = cputime_to_cputime64(cputime);
 	if (hardirq_count() - hardirq_offset)
-		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+		target_cputime64 = &cpustat->irq;
 	else if (in_serving_softirq())
-		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+		target_cputime64 = &cpustat->softirq;
 	else
-		cpustat->system = cputime64_add(cpustat->system, tmp);
-
-	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+		target_cputime64 = &cpustat->system;
 
-	/* Account for system time used */
-	acct_update_integrals(p);
+	__account_system_time(p, cputime, cputime_scaled, target_cputime64);
 }
 
 /*
  * Account for involuntary wait time.
- * @steal: the cpu time spent in involuntary wait
+ * @cputime: the cpu time spent in involuntary wait
  */
 void account_steal_time(cputime_t cputime)
 {
@@ -3635,6 +3697,73 @@ void account_idle_time(cputime_t cputime)
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ *   - check for guest_time
+ *   - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq)
+{
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+	if (irqtime_account_hi_update()) {
+		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+	} else if (irqtime_account_si_update()) {
+		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+	} else if (this_cpu_ksoftirqd() == p) {
+		/*
+		 * ksoftirqd time do not get accounted in cpu_softirq_time.
+		 * So, we have to handle it separately here.
+		 * Also, p->stime needs to be updated for ksoftirqd.
+		 */
+		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+					&cpustat->softirq);
+	} else if (user_tick) {
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	} else if (p == rq->idle) {
+		account_idle_time(cputime_one_jiffy);
+	} else if (p->flags & PF_VCPU) { /* System time or guest time */
+		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	} else {
+		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+					&cpustat->system);
+	}
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+	int i;
+	struct rq *rq = this_rq();
+
+	for (i = 0; i < ticks; i++)
+		irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
 /*
  * Account a single tick of cpu time.
  * @p: the process that the cpu time gets accounted to
@@ -3645,6 +3774,11 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
+	if (sched_clock_irqtime) {
+		irqtime_account_process_tick(p, user_tick, rq);
+		return;
+	}
+
 	if (user_tick)
 		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
@@ -3670,6 +3804,12 @@ void account_steal_ticks(unsigned long ticks)
  */
 void account_idle_ticks(unsigned long ticks)
 {
+
+	if (sched_clock_irqtime) {
+		irqtime_account_idle_ticks(ticks);
+		return;
+	}
+
 	account_idle_time(jiffies_to_cputime(ticks));
 }
 
@@ -3945,9 +4085,6 @@ need_resched:
 	rcu_note_context_switch(cpu);
 	prev = rq->curr;
 
-	release_kernel_lock(prev);
-need_resched_nonpreemptible:
-
 	schedule_debug(prev);
 
 	if (sched_feat(HRTICK))
@@ -3989,9 +4126,6 @@ need_resched_nonpreemptible:
 	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
-		sched_info_switch(prev, next);
-		perf_event_task_sched_out(prev, next);
-
 		rq->nr_switches++;
 		rq->curr = next;
 		++*switch_count;
@@ -4010,9 +4144,6 @@ need_resched_nonpreemptible:
 
 	post_schedule(rq);
 
-	if (unlikely(reacquire_kernel_lock(prev)))
-		goto need_resched_nonpreemptible;
-
 	preempt_enable_no_resched();
 	if (need_resched())
 		goto need_resched;
@@ -4213,6 +4344,7 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
 	__wake_up_common(q, mode, 1, 0, key);
 }
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
@@ -4570,11 +4702,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, &flags);
 }
 
@@ -4822,12 +4953,15 @@ recheck:
 			    param->sched_priority > rlim_rtprio)
 				return -EPERM;
 		}
+
 		/*
-		 * Like positive nice levels, dont allow tasks to
-		 * move out of SCHED_IDLE either:
+		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
+		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
-		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
-			return -EPERM;
+		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+			if (!can_nice(p, TASK_NICE(p)))
+				return -EPERM;
+		}
 
 		/* can't change other user's priorities */
 		if (!check_same_owner(p))
@@ -4902,11 +5036,10 @@ recheck:
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		activate_task(rq, p, 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	__task_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -5323,6 +5456,65 @@ void __sched yield(void)
 }
 EXPORT_SYMBOL(yield);
 
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+	struct task_struct *curr = current;
+	struct rq *rq, *p_rq;
+	unsigned long flags;
+	bool yielded = 0;
+
+	local_irq_save(flags);
+	rq = this_rq();
+
+again:
+	p_rq = task_rq(p);
+	double_rq_lock(rq, p_rq);
+	while (task_rq(p) != p_rq) {
+		double_rq_unlock(rq, p_rq);
+		goto again;
+	}
+
+	if (!curr->sched_class->yield_to_task)
+		goto out;
+
+	if (curr->sched_class != p->sched_class)
+		goto out;
+
+	if (task_running(p_rq, p) || p->state)
+		goto out;
+
+	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	if (yielded) {
+		schedstat_inc(rq, yld_count);
+		/*
+		 * Make p's CPU reschedule; pick_next_entity takes care of
+		 * fairness.
+		 */
+		if (preempt && rq != p_rq)
+			resched_task(p_rq->curr);
+	}
+
+out:
+	double_rq_unlock(rq, p_rq);
+	local_irq_restore(flags);
+
+	if (yielded)
+		schedule();
+
+	return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
 /*
  * 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.
@@ -5571,7 +5763,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
-	ftrace_graph_init_task(idle);
+	ftrace_graph_init_idle_task(idle, cpu);
 }
 
 /*
@@ -7796,6 +7988,10 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 	INIT_LIST_HEAD(&cfs_rq->tasks);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	cfs_rq->rq = rq;
+	/* allow initial update_cfs_load() to truncate */
+#ifdef CONFIG_SMP
+	cfs_rq->load_stamp = 1;
+#endif
 #endif
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 }
@@ -8074,7 +8270,7 @@ static inline int preempt_count_equals(int preempt_offset)
 {
 	int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
 
-	return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+	return (nested == preempt_offset);
 }
 
 void __might_sleep(const char *file, int line, int preempt_offset)
@@ -8109,6 +8305,8 @@ EXPORT_SYMBOL(__might_sleep);
 #ifdef CONFIG_MAGIC_SYSRQ
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
+	const struct sched_class *prev_class = p->sched_class;
+	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->se.on_rq;
@@ -8119,6 +8317,8 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 		activate_task(rq, p, 0);
 		resched_task(rq->curr);
 	}
+
+	check_class_changed(rq, p, prev_class, old_prio);
 }
 
 void normalize_rt_tasks(void)
@@ -8510,7 +8710,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		/* Propagate contribution to hierarchy */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		for_each_sched_entity(se)
-			update_cfs_shares(group_cfs_rq(se), 0);
+			update_cfs_shares(group_cfs_rq(se));
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
@@ -8884,7 +9084,8 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 }
 
 static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
 {
 	/*
 	 * cgroup_exit() is called in the copy_process() failure path.
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
index 9fb656283157..5946ac515602 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched_autogroup.c
@@ -12,7 +12,6 @@ static atomic_t autogroup_seq_nr;
 static void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
-	root_task_group.autogroup = &autogroup_default;
 	kref_init(&autogroup_default.kref);
 	init_rwsem(&autogroup_default.lock);
 	init_task->signal->autogroup = &autogroup_default;
@@ -130,7 +129,7 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 
 static inline bool task_group_is_autogroup(struct task_group *tg)
 {
-	return tg != &root_task_group && tg->autogroup;
+	return !!tg->autogroup;
 }
 
 static inline struct task_group *
@@ -161,11 +160,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
+	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+		goto out;
+
 	t = p;
 	do {
 		sched_move_task(t);
 	} while_each_thread(p, t);
 
+out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }
@@ -247,10 +250,14 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 {
 	struct autogroup *ag = autogroup_task_get(p);
 
+	if (!task_group_is_autogroup(ag->tg))
+		goto out;
+
 	down_read(&ag->lock);
 	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
 	up_read(&ag->lock);
 
+out:
 	autogroup_kref_put(ag);
 }
 #endif /* CONFIG_PROC_FS */
@@ -258,9 +265,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 #ifdef CONFIG_SCHED_DEBUG
 static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (!enabled || !tg->autogroup)
+	if (!task_group_is_autogroup(tg))
 		return 0;
 
 	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
index 7b859ffe5dad..05577055cfca 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched_autogroup.h
@@ -1,6 +1,11 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 struct autogroup {
+	/*
+	 * reference doesn't mean how many thread attach to this
+	 * autogroup now. It just stands for the number of task
+	 * could use this autogroup.
+	 */
 	struct kref		kref;
 	struct task_group	*tg;
 	struct rw_semaphore	lock;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index eb6cb8edd075..7bacd83a4158 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -179,7 +179,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 	if (cfs_rq->rb_leftmost)
-		MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
+		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
 		max_vruntime = last->vruntime;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c26e2df450e..3f7ec9e27ee1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -69,14 +69,6 @@ static unsigned int sched_nr_latency = 8;
 unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
-/*
  * SCHED_OTHER wake-up granularity.
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
@@ -419,7 +411,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *left = cfs_rq->rb_leftmost;
 
@@ -429,6 +421,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 	return rb_entry(left, struct sched_entity, run_node);
 }
 
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+	struct rb_node *next = rb_next(&se->run_node);
+
+	if (!next)
+		return NULL;
+
+	return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
 static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
@@ -443,7 +446,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  * Scheduling class statistics methods:
  */
 
-#ifdef CONFIG_SCHED_DEBUG
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -540,7 +542,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
 
 /*
  * Update the current task's runtime statistics. Skip current tasks that
@@ -733,6 +735,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 	    now - cfs_rq->load_last > 4 * period) {
 		cfs_rq->load_period = 0;
 		cfs_rq->load_avg = 0;
+		delta = period - 1;
 	}
 
 	cfs_rq->load_stamp = now;
@@ -763,16 +766,15 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 		list_del_leaf_cfs_rq(cfs_rq);
 }
 
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
-				long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	long load_weight, load, shares;
 
-	load = cfs_rq->load.weight + weight_delta;
+	load = cfs_rq->load.weight;
 
 	load_weight = atomic_read(&tg->load_weight);
-	load_weight -= cfs_rq->load_contribution;
 	load_weight += load;
+	load_weight -= cfs_rq->load_contribution;
 
 	shares = (tg->shares * load);
 	if (load_weight)
@@ -790,7 +792,7 @@ static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
 {
 	if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 }
 # else /* CONFIG_SMP */
@@ -798,8 +800,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
 }
 
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
-				long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	return tg->shares;
 }
@@ -824,7 +825,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		account_entity_enqueue(cfs_rq, se);
 }
 
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 	struct task_group *tg;
 	struct sched_entity *se;
@@ -838,7 +839,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 	if (likely(se->load.weight == tg->shares))
 		return;
 #endif
-	shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+	shares = calc_cfs_shares(cfs_rq, tg);
 
 	reweight_entity(cfs_rq_of(se), se, shares);
 }
@@ -847,7 +848,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
 }
 
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 }
 
@@ -978,8 +979,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
-	update_cfs_shares(cfs_rq, se->load.weight);
 	account_entity_enqueue(cfs_rq, se);
+	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
@@ -996,19 +997,49 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		list_add_leaf_cfs_rq(cfs_rq);
 }
 
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->last == se)
+			cfs_rq->last = NULL;
+		else
+			break;
+	}
+}
+
+static void __clear_buddies_next(struct sched_entity *se)
 {
-	if (!se || cfs_rq->last == se)
-		cfs_rq->last = NULL;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->next == se)
+			cfs_rq->next = NULL;
+		else
+			break;
+	}
+}
 
-	if (!se || cfs_rq->next == se)
-		cfs_rq->next = NULL;
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->skip == se)
+			cfs_rq->skip = NULL;
+		else
+			break;
+	}
 }
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		__clear_buddies(cfs_rq_of(se), se);
+	if (cfs_rq->last == se)
+		__clear_buddies_last(se);
+
+	if (cfs_rq->next == se)
+		__clear_buddies_next(se);
+
+	if (cfs_rq->skip == se)
+		__clear_buddies_skip(se);
 }
 
 static void
@@ -1041,7 +1072,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_cfs_load(cfs_rq, 0);
 	account_entity_dequeue(cfs_rq, se);
 	update_min_vruntime(cfs_rq);
-	update_cfs_shares(cfs_rq, 0);
+	update_cfs_shares(cfs_rq);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -1084,7 +1115,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		return;
 
 	if (cfs_rq->nr_running > 1) {
-		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		struct sched_entity *se = __pick_first_entity(cfs_rq);
 		s64 delta = curr->vruntime - se->vruntime;
 
 		if (delta < 0)
@@ -1128,13 +1159,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static int
 wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_next_entity(cfs_rq);
+	struct sched_entity *se = __pick_first_entity(cfs_rq);
 	struct sched_entity *left = se;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
-		se = cfs_rq->next;
+	/*
+	 * Avoid running the skip buddy, if running something else can
+	 * be done without getting too unfair.
+	 */
+	if (cfs_rq->skip == se) {
+		struct sched_entity *second = __pick_next_entity(se);
+		if (second && wakeup_preempt_entity(second, left) < 1)
+			se = second;
+	}
 
 	/*
 	 * Prefer last buddy, try to return the CPU to a preempted task.
@@ -1142,6 +1187,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
 		se = cfs_rq->last;
 
+	/*
+	 * Someone really wants this to run. If it's not unfair, run it.
+	 */
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
+
 	clear_buddies(cfs_rq, se);
 
 	return se;
@@ -1282,7 +1333,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 
 	hrtick_update(rq);
@@ -1312,58 +1363,12 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 
 	hrtick_update(rq);
 }
 
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
-	struct task_struct *curr = rq->curr;
-	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	struct sched_entity *rightmost, *se = &curr->se;
-
-	/*
-	 * Are we the only task in the tree?
-	 */
-	if (unlikely(cfs_rq->nr_running == 1))
-		return;
-
-	clear_buddies(cfs_rq, se);
-
-	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-		update_rq_clock(rq);
-		/*
-		 * Update run-time statistics of the 'current'.
-		 */
-		update_curr(cfs_rq);
-
-		return;
-	}
-	/*
-	 * Find the rightmost entry in the rbtree:
-	 */
-	rightmost = __pick_last_entity(cfs_rq);
-	/*
-	 * Already in the rightmost position?
-	 */
-	if (unlikely(!rightmost || entity_before(rightmost, se)))
-		return;
-
-	/*
-	 * Minimally necessary key value to be last in the tree:
-	 * Upon rescheduling, sched_class::put_prev_task() will place
-	 * 'current' within the tree based on its new key value.
-	 */
-	se->vruntime = rightmost->vruntime + 1;
-}
-
 #ifdef CONFIG_SMP
 
 static void task_waking_fair(struct rq *rq, struct task_struct *p)
@@ -1834,6 +1839,14 @@ static void set_next_buddy(struct sched_entity *se)
 	}
 }
 
+static void set_skip_buddy(struct sched_entity *se)
+{
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->skip = se;
+	}
+}
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -1857,16 +1870,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (test_tsk_need_resched(curr))
 		return;
 
+	/* Idle tasks are by definition preempted by non-idle tasks. */
+	if (unlikely(curr->policy == SCHED_IDLE) &&
+	    likely(p->policy != SCHED_IDLE))
+		goto preempt;
+
 	/*
-	 * Batch and idle tasks do not preempt (their preemption is driven by
-	 * the tick):
+	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
+	 * is driven by the tick):
 	 */
 	if (unlikely(p->policy != SCHED_NORMAL))
 		return;
 
-	/* Idle tasks are by definition preempted by everybody. */
-	if (unlikely(curr->policy == SCHED_IDLE))
-		goto preempt;
 
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
@@ -1932,6 +1947,51 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	struct sched_entity *se = &curr->se;
+
+	/*
+	 * Are we the only task in the tree?
+	 */
+	if (unlikely(rq->nr_running == 1))
+		return;
+
+	clear_buddies(cfs_rq, se);
+
+	if (curr->policy != SCHED_BATCH) {
+		update_rq_clock(rq);
+		/*
+		 * Update run-time statistics of the 'current'.
+		 */
+		update_curr(cfs_rq);
+	}
+
+	set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+	struct sched_entity *se = &p->se;
+
+	if (!se->on_rq)
+		return false;
+
+	/* Tell the scheduler that we'd really like pse to run next. */
+	set_next_buddy(se);
+
+	yield_task_fair(rq);
+
+	return true;
+}
+
 #ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
@@ -2123,7 +2183,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu)
 	 * We need to update shares after updating tg->load_weight in
 	 * order to adjust the weight of groups with long running tasks.
 	 */
-	update_cfs_shares(cfs_rq, 0);
+	update_cfs_shares(cfs_rq);
 
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
@@ -2610,7 +2670,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
  * @local_group: Does group contain this_cpu.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
@@ -2618,7 +2677,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  */
 static inline void update_sg_lb_stats(struct sched_domain *sd,
 			struct sched_group *group, int this_cpu,
-			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			enum cpu_idle_type idle, int load_idx,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
 {
@@ -2638,9 +2697,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
 		struct rq *rq = cpu_rq(i);
 
-		if (*sd_idle && rq->nr_running)
-			*sd_idle = 0;
-
 		/* Bias balancing toward cpus of our domain */
 		if (local_group) {
 			if (idle_cpu(i) && !first_idle_cpu) {
@@ -2685,7 +2741,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
-	 * than the average weight of two tasks.
+	 * than the average weight of a task.
 	 *
 	 * APZ: with cgroup the avg task weight can vary wildly and
 	 *      might not be a suitable number - should we keep a
@@ -2695,7 +2751,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if (sgs->sum_nr_running)
 		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
 		sgs->group_imb = 1;
 
 	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
@@ -2755,15 +2811,13 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
  * @sd: sched_domain whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing sg.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
  */
 static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
-			enum cpu_idle_type idle, int *sd_idle,
-			const struct cpumask *cpus, int *balance,
-			struct sd_lb_stats *sds)
+			enum cpu_idle_type idle, const struct cpumask *cpus,
+			int *balance, struct sd_lb_stats *sds)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *sg = sd->groups;
@@ -2781,7 +2835,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 
 		local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle,
+		update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
 				local_group, cpus, balance, &sgs);
 
 		if (local_group && !(*balance))
@@ -3033,7 +3087,6 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
  * @imbalance: Variable which stores amount of weighted load which should
  *		be moved to restore balance/put a group to idle.
  * @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
  * @cpus: The set of CPUs under consideration for load-balancing.
  * @balance: Pointer to a variable indicating if this_cpu
  *	is the appropriate cpu to perform load balancing at this_level.
@@ -3046,7 +3099,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 static struct sched_group *
 find_busiest_group(struct sched_domain *sd, int this_cpu,
 		   unsigned long *imbalance, enum cpu_idle_type idle,
-		   int *sd_idle, const struct cpumask *cpus, int *balance)
+		   const struct cpumask *cpus, int *balance)
 {
 	struct sd_lb_stats sds;
 
@@ -3056,22 +3109,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	 * Compute the various statistics relavent for load balancing at
 	 * this level.
 	 */
-	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
-					balance, &sds);
-
-	/* Cases where imbalance does not exist from POV of this_cpu */
-	/* 1) this_cpu is not the appropriate cpu to perform load balancing
-	 *    at this level.
-	 * 2) There is no busy sibling group to pull from.
-	 * 3) This group is the busiest group.
-	 * 4) This group is more busy than the avg busieness at this
-	 *    sched_domain.
-	 * 5) The imbalance is within the specified limit.
-	 *
-	 * Note: when doing newidle balance, if the local group has excess
-	 * capacity (i.e. nr_running < group_capacity) and the busiest group
-	 * does not have any capacity, we force a load balance to pull tasks
-	 * to the local group. In this case, we skip past checks 3, 4 and 5.
+	update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+
+	/*
+	 * this_cpu is not the appropriate cpu to perform load balancing at
+	 * this level.
 	 */
 	if (!(*balance))
 		goto ret;
@@ -3080,41 +3122,55 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	    check_asym_packing(sd, &sds, this_cpu, imbalance))
 		return sds.busiest;
 
+	/* There is no busy sibling group to pull tasks from */
 	if (!sds.busiest || sds.busiest_nr_running == 0)
 		goto out_balanced;
 
-	/*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+	/*
+	 * If the busiest group is imbalanced the below checks don't
+	 * work because they assumes all things are equal, which typically
+	 * isn't true due to cpus_allowed constraints and the like.
+	 */
+	if (sds.group_imb)
+		goto force_balance;
+
+	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
 	if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
 			!sds.busiest_has_capacity)
 		goto force_balance;
 
+	/*
+	 * If the local group is more busy than the selected busiest group
+	 * don't try and pull any tasks.
+	 */
 	if (sds.this_load >= sds.max_load)
 		goto out_balanced;
 
+	/*
+	 * Don't pull any tasks if this group is already above the domain
+	 * average load.
+	 */
 	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
 	if (sds.this_load >= sds.avg_load)
 		goto out_balanced;
 
-	/*
-	 * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
-	 * And to check for busy balance use !idle_cpu instead of
-	 * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
-	 * even when they are idle.
-	 */
-	if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
-		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-			goto out_balanced;
-	} else {
+	if (idle == CPU_IDLE) {
 		/*
 		 * This cpu is idle. If the busiest group load doesn't
 		 * have more tasks than the number of available cpu's and
 		 * there is no imbalance between this and busiest group
 		 * wrt to idle cpu's, it is balanced.
 		 */
-		if ((sds.this_idle_cpus  <= sds.busiest_idle_cpus + 1) &&
+		if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
 		    sds.busiest_nr_running <= sds.busiest_group_weight)
 			goto out_balanced;
+	} else {
+		/*
+		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+		 * imbalance_pct to be conservative.
+		 */
+		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+			goto out_balanced;
 	}
 
 force_balance:
@@ -3193,7 +3249,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
 /* Working cpumask for load_balance and load_balance_newidle. */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
 
-static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
+static int need_active_balance(struct sched_domain *sd, int idle,
 			       int busiest_cpu, int this_cpu)
 {
 	if (idle == CPU_NEWLY_IDLE) {
@@ -3225,10 +3281,6 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
 		 * move_tasks() will succeed.  ld_moved will be true and this
 		 * active balance code will not be triggered.
 		 */
-		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-			return 0;
-
 		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
 			return 0;
 	}
@@ -3246,7 +3298,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *balance)
 {
-	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+	int ld_moved, all_pinned = 0, active_balance = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
@@ -3255,20 +3307,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 
 	cpumask_copy(cpus, cpu_active_mask);
 
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
 	schedstat_inc(sd, lb_count[idle]);
 
 redo:
-	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle,
 				   cpus, balance);
 
 	if (*balance == 0)
@@ -3330,8 +3372,7 @@ redo:
 		if (idle != CPU_NEWLY_IDLE)
 			sd->nr_balance_failed++;
 
-		if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
-					this_cpu)) {
+		if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
 			/* don't kick the active_load_balance_cpu_stop,
@@ -3386,10 +3427,6 @@ redo:
 			sd->balance_interval *= 2;
 	}
 
-	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-
 	goto out;
 
 out_balanced:
@@ -3403,11 +3440,7 @@ out_one_pinned:
 			(sd->balance_interval < sd->max_interval))
 		sd->balance_interval *= 2;
 
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-	else
-		ld_moved = 0;
+	ld_moved = 0;
 out:
 	return ld_moved;
 }
@@ -3831,8 +3864,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
-				 * longer idle, or one of our SMT siblings is
-				 * not idle.
+				 * longer idle.
 				 */
 				idle = CPU_NOT_IDLE;
 			}
@@ -4079,33 +4111,62 @@ static void task_fork_fair(struct task_struct *p)
  * Priority of the task has changed. Check to see if we preempt
  * the current task.
  */
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 {
+	if (!p->se.on_rq)
+		return;
+
 	/*
 	 * 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 (running) {
+	if (rq->curr == p) {
 		if (p->prio > oldprio)
 			resched_task(rq->curr);
 	} else
 		check_preempt_curr(rq, p, 0);
 }
 
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	/*
+	 * Ensure the task's vruntime is normalized, so that when its
+	 * switched back to the fair class the enqueue_entity(.flags=0) will
+	 * do the right thing.
+	 *
+	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * the task is sleeping will it still have non-normalized vruntime.
+	 */
+	if (!se->on_rq && p->state != TASK_RUNNING) {
+		/*
+		 * Fix up our vruntime so that the current sleep doesn't
+		 * cause 'unlimited' sleep bonus.
+		 */
+		place_entity(cfs_rq, se, 0);
+		se->vruntime -= cfs_rq->min_vruntime;
+	}
+}
+
 /*
  * We switched to the sched_fair class.
  */
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
+	if (!p->se.on_rq)
+		return;
+
 	/*
 	 * We were most likely switched from sched_rt, so
 	 * kick off the schedule if running, otherwise just see
 	 * if we can still preempt the current task.
 	 */
-	if (running)
+	if (rq->curr == p)
 		resched_task(rq->curr);
 	else
 		check_preempt_curr(rq, p, 0);
@@ -4171,6 +4232,7 @@ static const struct sched_class fair_sched_class = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
+	.yield_to_task		= yield_to_task_fair,
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
@@ -4191,6 +4253,7 @@ static const struct sched_class fair_sched_class = {
 	.task_fork		= task_fork_fair,
 
 	.prio_changed		= prio_changed_fair,
+	.switched_from		= switched_from_fair,
 	.switched_to		= switched_to_fair,
 
 	.get_rr_interval	= get_rr_interval_fair,
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 9fa0f402c87c..c82f26c1b7c3 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -52,31 +52,15 @@ static void set_curr_task_idle(struct rq *rq)
 {
 }
 
-static void switched_to_idle(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_idle(struct rq *rq, struct task_struct *p)
 {
-	/* Can this actually happen?? */
-	if (running)
-		resched_task(rq->curr);
-	else
-		check_preempt_curr(rq, p, 0);
+	BUG();
 }
 
-static void prio_changed_idle(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	/* This can happen for hot plug CPUS */
-
-	/*
-	 * 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 (running) {
-		if (p->prio > oldprio)
-			resched_task(rq->curr);
-	} else
-		check_preempt_curr(rq, p, 0);
+	BUG();
 }
 
 static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index ad6267714c84..db308cb08b75 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -210,11 +210,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
-	int this_cpu = smp_processor_id();
 	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
 	struct sched_rt_entity *rt_se;
 
-	rt_se = rt_rq->tg->rt_se[this_cpu];
+	int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+	rt_se = rt_rq->tg->rt_se[cpu];
 
 	if (rt_rq->rt_nr_running) {
 		if (rt_se && !on_rt_rq(rt_se))
@@ -226,10 +227,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-	int this_cpu = smp_processor_id();
 	struct sched_rt_entity *rt_se;
+	int cpu = cpu_of(rq_of_rt_rq(rt_rq));
 
-	rt_se = rt_rq->tg->rt_se[this_cpu];
+	rt_se = rt_rq->tg->rt_se[cpu];
 
 	if (rt_se && on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se);
@@ -565,8 +566,11 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 			if (rt_rq->rt_time || rt_rq->rt_nr_running)
 				idle = 0;
 			raw_spin_unlock(&rt_rq->rt_runtime_lock);
-		} else if (rt_rq->rt_nr_running)
+		} else if (rt_rq->rt_nr_running) {
 			idle = 0;
+			if (!rt_rq_throttled(rt_rq))
+				enqueue = 1;
+		}
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
@@ -1595,8 +1599,7 @@ static void rq_offline_rt(struct rq *rq)
  * When switch from the rt queue, we bring ourselves to a position
  * that we might want to pull RT tasks from other runqueues.
  */
-static void switched_from_rt(struct rq *rq, struct task_struct *p,
-			   int running)
+static void switched_from_rt(struct rq *rq, struct task_struct *p)
 {
 	/*
 	 * If there are other RT tasks then we will reschedule
@@ -1605,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p,
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (!rq->rt.rt_nr_running)
+	if (p->se.on_rq && !rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
 
@@ -1624,8 +1627,7 @@ static inline void init_sched_rt_class(void)
  * with RT tasks. In this case we try to push them off to
  * other runqueues.
  */
-static void switched_to_rt(struct rq *rq, struct task_struct *p,
-			   int running)
+static void switched_to_rt(struct rq *rq, struct task_struct *p)
 {
 	int check_resched = 1;
 
@@ -1636,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (!running) {
+	if (p->se.on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->rt.overloaded && push_rt_task(rq) &&
 		    /* Don't resched if we changed runqueues */
@@ -1652,10 +1654,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
  * Priority of the task has changed. This may cause
  * us to initiate a push or pull.
  */
-static void prio_changed_rt(struct rq *rq, struct task_struct *p,
-			    int oldprio, int running)
+static void
+prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (running) {
+	if (!p->se.on_rq)
+		return;
+
+	if (rq->curr == p) {
 #ifdef CONFIG_SMP
 		/*
 		 * If our priority decreases while running, we
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 2bf6b47058c1..84ec9bcf82d9 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -59,14 +59,13 @@ static void set_curr_task_stop(struct rq *rq)
 {
 }
 
-static void switched_to_stop(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_stop(struct rq *rq, struct task_struct *p)
 {
 	BUG(); /* its impossible to change to this class */
 }
 
-static void prio_changed_stop(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
 {
 	BUG(); /* how!?, what priority? */
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 68eb5efec388..56e5dec837f0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_stat);
 
 static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
-static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
@@ -311,9 +311,21 @@ void irq_enter(void)
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
-# define invoke_softirq()	__do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		__do_softirq();
+	else
+		wakeup_softirqd();
+}
 #else
-# define invoke_softirq()	do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		do_softirq();
+	else
+		wakeup_softirqd();
+}
 #endif
 
 /*
@@ -721,7 +733,6 @@ static int run_ksoftirqd(void * __bind_cpu)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	current->flags |= PF_KSOFTIRQD;
 	while (!kthread_should_stop()) {
 		preempt_disable();
 		if (!local_softirq_pending()) {
@@ -738,7 +749,10 @@ static int run_ksoftirqd(void * __bind_cpu)
 			   don't process */
 			if (cpu_is_offline((long)__bind_cpu))
 				goto wait_to_die;
-			do_softirq();
+			local_irq_disable();
+			if (local_softirq_pending())
+				__do_softirq();
+			local_irq_enable();
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
diff --git a/kernel/sys.c b/kernel/sys.c
index 18da702ec813..1ad48b3b9068 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -37,6 +37,7 @@
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
 #include <linux/gfp.h>
+#include <linux/syscore_ops.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -298,6 +299,7 @@ void kernel_restart_prepare(char *cmd)
 	system_state = SYSTEM_RESTART;
 	device_shutdown();
 	sysdev_shutdown();
+	syscore_shutdown();
 }
 
 /**
@@ -336,6 +338,7 @@ void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
 	sysdev_shutdown();
+	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
 	machine_halt();
@@ -355,6 +358,7 @@ void kernel_power_off(void)
 		pm_power_off_prepare();
 	disable_nonboot_cpus();
 	sysdev_shutdown();
+	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
 	machine_power_off();
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9924c7..25cc41cd8f33 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,8 @@ cond_syscall(sys_perf_event_open);
 /* fanotify! */
 cond_syscall(sys_fanotify_init);
 cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0f1bd83db985..40245d697602 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write,
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
-	.count = 1,
+	{{.count = 1,
 	.ctl_table = root_table,
-	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
+	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
 	.root = &sysctl_table_root,
 	.set = &sysctl_table_root.default_set,
 };
@@ -361,20 +361,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rt_handler,
 	},
-	{
-		.procname	= "sched_compat_yield",
-		.data		= &sysctl_sched_compat_yield,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",
 		.data		= &sysctl_sched_autogroup_enabled,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
@@ -948,7 +941,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_perf_event_sample_rate,
 		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= perf_proc_update_handler,
 	},
 #endif
 #ifdef CONFIG_KMEMCHECK
@@ -1567,11 +1560,16 @@ void sysctl_head_get(struct ctl_table_header *head)
 	spin_unlock(&sysctl_lock);
 }
 
+static void free_head(struct rcu_head *rcu)
+{
+	kfree(container_of(rcu, struct ctl_table_header, rcu));
+}
+
 void sysctl_head_put(struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
 	if (!--head->count)
-		kfree(head);
+		call_rcu(&head->rcu, free_head);
 	spin_unlock(&sysctl_lock);
 }
 
@@ -1685,13 +1683,8 @@ static int test_perm(int mode, int op)
 
 int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
 {
-	int error;
 	int mode;
 
-	error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
-	if (error)
-		return error;
-
 	if (root->permissions)
 		mode = root->permissions(root, current->nsproxy, table);
 	else
@@ -1948,10 +1941,10 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 	start_unregistering(header);
 	if (!--header->parent->count) {
 		WARN_ON(1);
-		kfree(header->parent);
+		call_rcu(&header->parent->rcu, free_head);
 	}
 	if (!--header->count)
-		kfree(header);
+		call_rcu(&header->rcu, free_head);
 	spin_unlock(&sysctl_lock);
 }
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b875bedf7c9a..3b8e028b9601 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1321,13 +1321,11 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
 {
 	const struct bin_table *table = NULL;
-	struct nameidata nd;
 	struct vfsmount *mnt;
 	struct file *file;
 	ssize_t result;
 	char *pathname;
 	int flags;
-	int acc_mode;
 
 	pathname = sysctl_getname(name, nlen, &table);
 	result = PTR_ERR(pathname);
@@ -1337,28 +1335,17 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	/* How should the sysctl be accessed? */
 	if (oldval && oldlen && newval && newlen) {
 		flags = O_RDWR;
-		acc_mode = MAY_READ | MAY_WRITE;
 	} else if (newval && newlen) {
 		flags = O_WRONLY;
-		acc_mode = MAY_WRITE;
 	} else if (oldval && oldlen) {
 		flags = O_RDONLY;
-		acc_mode = MAY_READ;
 	} else {
 		result = 0;
 		goto out_putname;
 	}
 
 	mnt = current->nsproxy->pid_ns->proc_mnt;
-	result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
-	if (result)
-		goto out_putname;
-
-	result = may_open(&nd.path, acc_mode, flags);
-	if (result)
-		goto out_putpath;
-
-	file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+	file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
 	result = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_putname;
@@ -1370,10 +1357,6 @@ out_putname:
 	putname(pathname);
 out:
 	return result;
-
-out_putpath:
-	path_put(&nd.path);
-	goto out_putname;
 }
 
 
diff --git a/kernel/time.c b/kernel/time.c
index 32174359576f..8e8dc6d705c9 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -150,7 +150,7 @@ static inline void warp_clock(void)
  * various programs will get confused when the clock gets warped.
  */
 
-int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
+int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 {
 	static int firsttime = 1;
 	int error = 0;
@@ -645,7 +645,7 @@ u64 nsec_to_clock_t(u64 x)
 }
 
 /**
- * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
  *
  * @n:	nsecs in u64
  *
@@ -657,7 +657,7 @@ u64 nsec_to_clock_t(u64 x)
  *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
  *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
  */
-unsigned long nsecs_to_jiffies(u64 n)
+u64 nsecs_to_jiffies64(u64 n)
 {
 #if (NSEC_PER_SEC % HZ) == 0
 	/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
@@ -674,22 +674,23 @@ unsigned long nsecs_to_jiffies(u64 n)
 #endif
 }
 
-#if (BITS_PER_LONG < 64)
-u64 get_jiffies_64(void)
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n:	nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
 {
-	unsigned long seq;
-	u64 ret;
-
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		ret = jiffies_64;
-	} while (read_seqretry(&xtime_lock, seq));
-	return ret;
+	return (unsigned long)nsecs_to_jiffies64(n);
 }
-EXPORT_SYMBOL(get_jiffies_64);
-#endif
-
-EXPORT_SYMBOL(jiffies);
 
 /*
  * Add two timespec values and do a safety check for overflow.
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ee266620b06c..b0425991e9ac 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,5 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timeconv.o posix-clock.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index d7395fdfb9f3..0d74b9ba90c8 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -18,7 +18,6 @@
 #include <linux/notifier.h>
 #include <linux/smp.h>
 #include <linux/sysdev.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 5404a8456909..b2fa506667c0 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -22,8 +22,11 @@
 ************************************************************************/
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
+#include <linux/module.h>
 #include <linux/init.h>
 
+#include "tick-internal.h"
+
 /* The Jiffies based clocksource is the lowest common
  * denominator clock source which should function on
  * all systems. It has the same coarse resolution as
@@ -64,6 +67,23 @@ struct clocksource clocksource_jiffies = {
 	.shift		= JIFFIES_SHIFT,
 };
 
+#if (BITS_PER_LONG < 64)
+u64 get_jiffies_64(void)
+{
+	unsigned long seq;
+	u64 ret;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		ret = jiffies_64;
+	} while (read_seqretry(&xtime_lock, seq));
+	return ret;
+}
+EXPORT_SYMBOL(get_jiffies_64);
+#endif
+
+EXPORT_SYMBOL(jiffies);
+
 static int __init init_jiffies_clocksource(void)
 {
 	return clocksource_register(&clocksource_jiffies);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5c00242fa921..5f1bb8e2008f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -16,6 +16,8 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 
+#include "tick-internal.h"
+
 /*
  * NTP timekeeping variables:
  */
@@ -646,6 +648,17 @@ int do_adjtimex(struct timex *txc)
 			hrtimer_cancel(&leap_timer);
 	}
 
+	if (txc->modes & ADJ_SETOFFSET) {
+		struct timespec delta;
+		delta.tv_sec  = txc->time.tv_sec;
+		delta.tv_nsec = txc->time.tv_usec;
+		if (!(txc->modes & ADJ_NANO))
+			delta.tv_nsec *= 1000;
+		result = timekeeping_inject_offset(&delta);
+		if (result)
+			return result;
+	}
+
 	getnstimeofday(&ts);
 
 	write_seqlock_irq(&xtime_lock);
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
new file mode 100644
index 000000000000..25028dd4fa18
--- /dev/null
+++ b/kernel/time/posix-clock.c
@@ -0,0 +1,451 @@
+/*
+ * posix-clock.c - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/mutex.h>
+#include <linux/posix-clock.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+static void delete_clock(struct kref *kref);
+
+/*
+ * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
+ */
+static struct posix_clock *get_posix_clock(struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+
+	mutex_lock(&clk->mutex);
+
+	if (!clk->zombie)
+		return clk;
+
+	mutex_unlock(&clk->mutex);
+
+	return NULL;
+}
+
+static void put_posix_clock(struct posix_clock *clk)
+{
+	mutex_unlock(&clk->mutex);
+}
+
+static ssize_t posix_clock_read(struct file *fp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -EINVAL;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.read)
+		err = clk->ops.read(clk, fp->f_flags, buf, count);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int result = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.poll)
+		result = clk->ops.poll(clk, fp, wait);
+
+	put_posix_clock(clk);
+
+	return result;
+}
+
+static int posix_clock_fasync(int fd, struct file *fp, int on)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.fasync)
+		err = clk->ops.fasync(clk, fd, fp, on);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENODEV;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.mmap)
+		err = clk->ops.mmap(clk, vma);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static long posix_clock_ioctl(struct file *fp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long posix_clock_compat_ioctl(struct file *fp,
+				     unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+#endif
+
+static int posix_clock_open(struct inode *inode, struct file *fp)
+{
+	int err;
+	struct posix_clock *clk =
+		container_of(inode->i_cdev, struct posix_clock, cdev);
+
+	mutex_lock(&clk->mutex);
+
+	if (clk->zombie) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (clk->ops.open)
+		err = clk->ops.open(clk, fp->f_mode);
+	else
+		err = 0;
+
+	if (!err) {
+		kref_get(&clk->kref);
+		fp->private_data = clk;
+	}
+out:
+	mutex_unlock(&clk->mutex);
+	return err;
+}
+
+static int posix_clock_release(struct inode *inode, struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+	int err = 0;
+
+	if (clk->ops.release)
+		err = clk->ops.release(clk);
+
+	kref_put(&clk->kref, delete_clock);
+
+	fp->private_data = NULL;
+
+	return err;
+}
+
+static const struct file_operations posix_clock_file_operations = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= posix_clock_read,
+	.poll		= posix_clock_poll,
+	.unlocked_ioctl	= posix_clock_ioctl,
+	.open		= posix_clock_open,
+	.release	= posix_clock_release,
+	.fasync		= posix_clock_fasync,
+	.mmap		= posix_clock_mmap,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= posix_clock_compat_ioctl,
+#endif
+};
+
+int posix_clock_register(struct posix_clock *clk, dev_t devid)
+{
+	int err;
+
+	kref_init(&clk->kref);
+	mutex_init(&clk->mutex);
+
+	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	clk->cdev.owner = clk->ops.owner;
+	err = cdev_add(&clk->cdev, devid, 1);
+	if (err)
+		goto no_cdev;
+
+	return err;
+no_cdev:
+	mutex_destroy(&clk->mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(posix_clock_register);
+
+static void delete_clock(struct kref *kref)
+{
+	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
+	mutex_destroy(&clk->mutex);
+	if (clk->release)
+		clk->release(clk);
+}
+
+void posix_clock_unregister(struct posix_clock *clk)
+{
+	cdev_del(&clk->cdev);
+
+	mutex_lock(&clk->mutex);
+	clk->zombie = true;
+	mutex_unlock(&clk->mutex);
+
+	kref_put(&clk->kref, delete_clock);
+}
+EXPORT_SYMBOL_GPL(posix_clock_unregister);
+
+struct posix_clock_desc {
+	struct file *fp;
+	struct posix_clock *clk;
+};
+
+static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
+{
+	struct file *fp = fget(CLOCKID_TO_FD(id));
+	int err = -EINVAL;
+
+	if (!fp)
+		return err;
+
+	if (fp->f_op->open != posix_clock_open || !fp->private_data)
+		goto out;
+
+	cd->fp = fp;
+	cd->clk = get_posix_clock(fp);
+
+	err = cd->clk ? 0 : -ENODEV;
+out:
+	if (err)
+		fput(fp);
+	return err;
+}
+
+static void put_clock_desc(struct posix_clock_desc *cd)
+{
+	put_posix_clock(cd->clk);
+	fput(cd->fp);
+}
+
+static int pc_clock_adjtime(clockid_t id, struct timex *tx)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_adjtime)
+		err = cd.clk->ops.clock_adjtime(cd.clk, tx);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_gettime)
+		err = cd.clk->ops.clock_gettime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_getres(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_getres)
+		err = cd.clk->ops.clock_getres(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_settime)
+		err = cd.clk->ops.clock_settime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_create(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_create)
+		err = cd.clk->ops.timer_create(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_delete(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_delete)
+		err = cd.clk->ops.timer_delete(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+
+	if (get_clock_desc(id, &cd))
+		return;
+
+	if (cd.clk->ops.timer_gettime)
+		cd.clk->ops.timer_gettime(cd.clk, kit, ts);
+
+	put_clock_desc(&cd);
+}
+
+static int pc_timer_settime(struct k_itimer *kit, int flags,
+			    struct itimerspec *ts, struct itimerspec *old)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_settime)
+		err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+struct k_clock clock_posix_dynamic = {
+	.clock_getres	= pc_clock_getres,
+	.clock_set	= pc_clock_settime,
+	.clock_get	= pc_clock_gettime,
+	.clock_adj	= pc_clock_adjtime,
+	.timer_create	= pc_timer_create,
+	.timer_set	= pc_timer_settime,
+	.timer_del	= pc_timer_delete,
+	.timer_get	= pc_timer_gettime,
+};
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 48b2761b5668..da800ffa810c 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
@@ -600,4 +599,14 @@ int tick_broadcast_oneshot_active(void)
 	return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
 }
 
+/*
+ * Check whether the broadcast device supports oneshot.
+ */
+bool tick_broadcast_oneshot_available(void)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+}
+
 #endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 051bc80a0c43..119528de8235 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include <asm/irq_regs.h>
 
@@ -51,7 +50,11 @@ int tick_is_oneshot_available(void)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-	return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return 0;
+	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 1;
+	return tick_broadcast_oneshot_available();
 }
 
 /*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 290eefbc1f60..1009b06d6f89 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,10 @@
 /*
  * tick internal variable and functions used by low/high res code
  */
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
 
 #define TICK_DO_TIMER_NONE	-1
 #define TICK_DO_TIMER_BOOT	-2
@@ -36,6 +40,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast(int cpu);
+bool tick_broadcast_oneshot_available(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -46,6 +51,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline bool tick_broadcast_oneshot_available(void) { return true; }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */
@@ -76,6 +82,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 	return 0;
 }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline bool tick_broadcast_oneshot_available(void) { return false; }
 #endif /* !TICK_ONESHOT */
 
 /*
@@ -132,3 +139,8 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 {
 	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
+
+#endif
+
+extern void do_timer(unsigned long ticks);
+extern seqlock_t xtime_lock;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 5cbc101f908b..2d04411a5f05 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c55ea2433471..d5097c44b407 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -19,7 +19,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 #include <linux/module.h>
 
 #include <asm/irq_regs.h>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d27c7562902c..3bd7e3d5c632 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -353,7 +353,7 @@ EXPORT_SYMBOL(do_gettimeofday);
  *
  * Sets the time of day to the new time and update NTP and notify hrtimers
  */
-int do_settimeofday(struct timespec *tv)
+int do_settimeofday(const struct timespec *tv)
 {
 	struct timespec ts_delta;
 	unsigned long flags;
@@ -387,6 +387,42 @@ int do_settimeofday(struct timespec *tv)
 
 EXPORT_SYMBOL(do_settimeofday);
 
+
+/**
+ * timekeeping_inject_offset - Adds or subtracts from the current time.
+ * @tv:		pointer to the timespec variable containing the offset
+ *
+ * Adds or subtracts an offset value from the current time.
+ */
+int timekeeping_inject_offset(struct timespec *ts)
+{
+	unsigned long flags;
+
+	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+		return -EINVAL;
+
+	write_seqlock_irqsave(&xtime_lock, flags);
+
+	timekeeping_forward_now();
+
+	xtime = timespec_add(xtime, *ts);
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
+
+	timekeeper.ntp_error = 0;
+	ntp_clear();
+
+	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+				timekeeper.mult);
+
+	write_sequnlock_irqrestore(&xtime_lock, flags);
+
+	/* signal hrtimers about time change */
+	clock_was_set();
+
+	return 0;
+}
+EXPORT_SYMBOL(timekeeping_inject_offset);
+
 /**
  * change_clocksource - Swaps clocksources if a new one is available
  *
@@ -779,7 +815,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
  *
  * Called from the timer interrupt, must hold a write on xtime_lock.
  */
-void update_wall_time(void)
+static void update_wall_time(void)
 {
 	struct clocksource *clock;
 	cycle_t offset;
@@ -871,7 +907,7 @@ void update_wall_time(void)
  * getboottime - Return the real time of system boot.
  * @ts:		pointer to the timespec to be set
  *
- * Returns the time of day in a timespec.
+ * Returns the wall-time of boot in a timespec.
  *
  * This is based on the wall_to_monotonic offset and the total suspend
  * time. Calls to settimeofday will affect the value returned (which
@@ -889,6 +925,55 @@ void getboottime(struct timespec *ts)
 }
 EXPORT_SYMBOL_GPL(getboottime);
 
+
+/**
+ * get_monotonic_boottime - Returns monotonic time since boot
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the monotonic time since boot in a timespec.
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
+ * includes the time spent in suspend.
+ */
+void get_monotonic_boottime(struct timespec *ts)
+{
+	struct timespec tomono, sleep;
+	unsigned int seq;
+	s64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*ts = xtime;
+		tomono = wall_to_monotonic;
+		sleep = total_sleep_time;
+		nsecs = timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
+			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+}
+EXPORT_SYMBOL_GPL(get_monotonic_boottime);
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in a ktime
+ *
+ * Returns the monotonic time since boot in a ktime
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also
+ * includes the time spent in suspend.
+ */
+ktime_t ktime_get_boottime(void)
+{
+	struct timespec ts;
+
+	get_monotonic_boottime(&ts);
+	return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL_GPL(ktime_get_boottime);
+
 /**
  * monotonic_to_bootbased - Convert the monotonic time to boot based.
  * @ts:		pointer to the timespec to be converted
@@ -910,11 +995,6 @@ struct timespec __current_kernel_time(void)
 	return xtime;
 }
 
-struct timespec __get_wall_to_monotonic(void)
-{
-	return wall_to_monotonic;
-}
-
 struct timespec current_kernel_time(void)
 {
 	struct timespec now;
@@ -946,3 +1026,48 @@ struct timespec get_monotonic_coarse(void)
 				now.tv_nsec + mono.tv_nsec);
 	return now;
 }
+
+/*
+ * The 64-bit jiffies value is not atomic - you MUST NOT read it
+ * without sampling the sequence number in xtime_lock.
+ * jiffies is defined in the linker script...
+ */
+void do_timer(unsigned long ticks)
+{
+	jiffies_64 += ticks;
+	update_wall_time();
+	calc_global_load(ticks);
+}
+
+/**
+ * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic,
+ *    and sleep offsets.
+ * @xtim:	pointer to timespec to be set with xtime
+ * @wtom:	pointer to timespec to be set with wall_to_monotonic
+ * @sleep:	pointer to timespec to be set with time in suspend
+ */
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+				struct timespec *wtom, struct timespec *sleep)
+{
+	unsigned long seq;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*xtim = xtime;
+		*wtom = wall_to_monotonic;
+		*sleep = total_sleep_time;
+	} while (read_seqretry(&xtime_lock, seq));
+}
+
+/**
+ * xtime_update() - advances the timekeeping infrastructure
+ * @ticks:	number of ticks, that have elapsed since the last call.
+ *
+ * Must be called with interrupts disabled.
+ */
+void xtime_update(unsigned long ticks)
+{
+	write_seqlock(&xtime_lock);
+	do_timer(ticks);
+	write_sequnlock(&xtime_lock);
+}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 32a19f9397fc..3258455549f4 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -41,7 +41,7 @@ static void print_name_offset(struct seq_file *m, void *sym)
 	char symname[KSYM_NAME_LEN];
 
 	if (lookup_symbol_name((unsigned long)sym, symname) < 0)
-		SEQ_printf(m, "<%p>", sym);
+		SEQ_printf(m, "<%pK>", sym);
 	else
 		SEQ_printf(m, "%s", symname);
 }
@@ -112,7 +112,7 @@ next_one:
 static void
 print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 {
-	SEQ_printf(m, "  .base:       %p\n", base);
+	SEQ_printf(m, "  .base:       %pK\n", base);
 	SEQ_printf(m, "  .index:      %d\n",
 			base->index);
 	SEQ_printf(m, "  .resolution: %Lu nsecs\n",
diff --git a/kernel/timer.c b/kernel/timer.c
index d53ce66daea0..fd6198692b57 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -404,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {}
 
 static struct debug_obj_descr timer_debug_descr;
 
+static void *timer_debug_hint(void *addr)
+{
+	return ((struct timer_list *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -477,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr timer_debug_descr = {
 	.name		= "timer_list",
+	.debug_hint	= timer_debug_hint,
 	.fixup_init	= timer_fixup_init,
 	.fixup_activate	= timer_fixup_activate,
 	.fixup_free	= timer_fixup_free,
@@ -959,11 +965,30 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  *
  * Synchronization rules: Callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
- * hardirq contexts. The caller must not hold locks which would prevent
+ * interrupt contexts. The caller must not hold locks which would prevent
  * completion of the timer's handler. The timer's handler must not call
  * add_timer_on(). Upon exit the timer is not queued and the handler is
  * not running on any CPU.
  *
+ * Note: You must not hold locks that are held in interrupt context
+ *   while calling this function. Even if the lock has nothing to do
+ *   with the timer in question.  Here's why:
+ *
+ *    CPU0                             CPU1
+ *    ----                             ----
+ *                                   <SOFTIRQ>
+ *                                   call_timer_fn();
+ *                                     base->running_timer = mytimer;
+ *  spin_lock_irq(somelock);
+ *                                     <IRQ>
+ *                                        spin_lock(somelock);
+ *  del_timer_sync(mytimer);
+ *   while (base->running_timer == mytimer);
+ *
+ * Now del_timer_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but
+ * it has interrupted the softirq that CPU0 is waiting to finish.
+ *
  * The function returns whether it has deactivated a pending timer or not.
  */
 int del_timer_sync(struct timer_list *timer)
@@ -971,12 +996,14 @@ int del_timer_sync(struct timer_list *timer)
 #ifdef CONFIG_LOCKDEP
 	unsigned long flags;
 
-	raw_local_irq_save(flags);
-	local_bh_disable();
+	/*
+	 * If lockdep gives a backtrace here, please reference
+	 * the synchronization rules above.
+	 */
+	local_irq_save(flags);
 	lock_map_acquire(&timer->lockdep_map);
 	lock_map_release(&timer->lockdep_map);
-	_local_bh_enable();
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 #endif
 	/*
 	 * don't use it in hardirq context, because it
@@ -1297,19 +1324,6 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
-/*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
- */
-
-void do_timer(unsigned long ticks)
-{
-	jiffies_64 += ticks;
-	update_wall_time();
-	calc_global_load(ticks);
-}
-
 #ifdef __ARCH_WANT_SYS_ALARM
 
 /*
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d95721f33702..cbafed7d4f38 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1827,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 	rwbs[i] = '\0';
 }
 
-void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
-{
-	int rw = rq->cmd_flags & 0x03;
-	int bytes;
-
-	if (rq->cmd_flags & REQ_DISCARD)
-		rw |= REQ_DISCARD;
-
-	if (rq->cmd_flags & REQ_SECURE)
-		rw |= REQ_SECURE;
-
-	bytes = blk_rq_bytes(rq);
-
-	blk_fill_rwbs(rwbs, rw, bytes);
-}
-
 #endif /* CONFIG_EVENT_TRACING */
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f3dadae83883..888b611897d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3328,7 +3328,7 @@ static int start_graph_tracing(void)
 	/* The cpu_boot init_task->ret_stack will never be freed */
 	for_each_online_cpu(cpu) {
 		if (!idle_task(cpu)->ret_stack)
-			ftrace_graph_init_task(idle_task(cpu));
+			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
 	}
 
 	do {
@@ -3418,6 +3418,49 @@ void unregister_ftrace_graph(void)
 	mutex_unlock(&ftrace_lock);
 }
 
+static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
+
+static void
+graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
+{
+	atomic_set(&t->tracing_graph_pause, 0);
+	atomic_set(&t->trace_overrun, 0);
+	t->ftrace_timestamp = 0;
+	/* make curr_ret_stack visable before we add the ret_stack */
+	smp_wmb();
+	t->ret_stack = ret_stack;
+}
+
+/*
+ * Allocate a return stack for the idle task. May be the first
+ * time through, or it may be done by CPU hotplug online.
+ */
+void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
+{
+	t->curr_ret_stack = -1;
+	/*
+	 * The idle task has no parent, it either has its own
+	 * stack or no stack at all.
+	 */
+	if (t->ret_stack)
+		WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
+
+	if (ftrace_graph_active) {
+		struct ftrace_ret_stack *ret_stack;
+
+		ret_stack = per_cpu(idle_ret_stack, cpu);
+		if (!ret_stack) {
+			ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+					    * sizeof(struct ftrace_ret_stack),
+					    GFP_KERNEL);
+			if (!ret_stack)
+				return;
+			per_cpu(idle_ret_stack, cpu) = ret_stack;
+		}
+		graph_init_task(t, ret_stack);
+	}
+}
+
 /* Allocate a return stack for newly created task */
 void ftrace_graph_init_task(struct task_struct *t)
 {
@@ -3433,12 +3476,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 				GFP_KERNEL);
 		if (!ret_stack)
 			return;
-		atomic_set(&t->tracing_graph_pause, 0);
-		atomic_set(&t->trace_overrun, 0);
-		t->ftrace_timestamp = 0;
-		/* make curr_ret_stack visable before we add the ret_stack */
-		smp_wmb();
-		t->ret_stack = ret_stack;
+		graph_init_task(t, ret_stack);
 	}
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd1c35a4fbcc..db7b439d23ee 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5,7 +5,6 @@
  */
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
-#include <linux/ftrace_irq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -1429,6 +1428,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+	mutex_lock(&buffer->mutex);
+	if (val)
+		buffer->flags |= RB_FL_OVERWRITE;
+	else
+		buffer->flags &= ~RB_FL_OVERWRITE;
+	mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
@@ -2162,11 +2172,19 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 	if (likely(ts >= cpu_buffer->write_stamp)) {
 		delta = diff;
 		if (unlikely(test_time_stamp(delta))) {
+			int local_clock_stable = 1;
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+			local_clock_stable = sched_clock_stable;
+#endif
 			WARN_ONCE(delta > (1ULL << 59),
-				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
 				  (unsigned long long)delta,
 				  (unsigned long long)ts,
-				  (unsigned long long)cpu_buffer->write_stamp);
+				  (unsigned long long)cpu_buffer->write_stamp,
+				  local_clock_stable ? "" :
+				  "If you just came from a suspend/resume,\n"
+				  "please switch to the trace global clock:\n"
+				  "  echo global > /sys/kernel/debug/tracing/trace_clock\n");
 			add_timestamp = 1;
 		}
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dc53ecb80589..9541c27c1cf2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,8 +41,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-#define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
@@ -340,7 +338,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
 
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +423,7 @@ static const char *trace_options[] = {
 	"sleep-time",
 	"graph-time",
 	"record-cmd",
+	"overwrite",
 	NULL
 };
 
@@ -780,6 +779,11 @@ __acquires(kernel_lock)
 		tracing_reset_online_cpus(tr);
 
 		current_trace = type;
+
+		/* If we expanded the buffers, make sure the max is expanded too */
+		if (ring_buffer_expanded && type->use_max_tr)
+			ring_buffer_resize(max_tr.buffer, trace_buf_size);
+
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
 		ret = type->selftest(type, tr);
@@ -792,6 +796,10 @@ __acquires(kernel_lock)
 		/* Only reset on passing, to avoid touching corrupted buffers */
 		tracing_reset_online_cpus(tr);
 
+		/* Shrink the max buffer again */
+		if (ring_buffer_expanded && type->use_max_tr)
+			ring_buffer_resize(max_tr.buffer, 1);
+
 		printk(KERN_CONT "PASSED\n");
 	}
 #endif
@@ -1102,7 +1110,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->lock_depth		= (tsk) ? tsk->lock_depth : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1749,10 +1756,9 @@ static void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#                | / _----=> need-resched    \n");
 	seq_puts(m, "#                || / _---=> hardirq/softirq \n");
 	seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-	seq_puts(m, "#                |||| /_--=> lock-depth       \n");
-	seq_puts(m, "#                |||||/     delay             \n");
-	seq_puts(m, "#  cmd     pid   |||||| time  |   caller      \n");
-	seq_puts(m, "#     \\   /      ||||||   \\   |   /           \n");
+	seq_puts(m, "#                |||| /     delay             \n");
+	seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
+	seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
@@ -2529,6 +2535,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
+
+	if (mask == TRACE_ITER_OVERWRITE)
+		ring_buffer_change_overwrite(global_trace.buffer, enabled);
 }
 
 static ssize_t
@@ -2710,6 +2719,10 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 
 	mutex_lock(&trace_types_lock);
 	if (tracer_enabled ^ val) {
+
+		/* Only need to warn if this is used to change the state */
+		WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on");
+
 		if (val) {
 			tracer_enabled = 1;
 			if (current_trace->start)
@@ -4551,9 +4564,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 __init static int tracer_alloc_buffers(void)
 {
 	int ring_buf_size;
+	enum ring_buffer_flags rb_flags;
 	int i;
 	int ret = -ENOMEM;
 
+
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;
 
@@ -4566,12 +4581,13 @@ __init static int tracer_alloc_buffers(void)
 	else
 		ring_buf_size = 1;
 
+	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
-	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
-						   TRACE_BUFFER_FLAGS);
+	global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
 	if (!global_trace.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
@@ -4581,7 +4597,7 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+	max_tr.buffer = ring_buffer_alloc(1, rb_flags);
 	if (!max_tr.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
 		WARN_ON(1);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9021f8c0c0c3..5e9dfc6286dd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -272,8 +272,8 @@ struct tracer {
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
 	struct tracer		*next;
-	int			print_max;
 	struct tracer_flags	*flags;
+	int			print_max;
 	int			use_max_tr;
 };
 
@@ -606,6 +606,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_SLEEP_TIME		= 0x40000,
 	TRACE_ITER_GRAPH_TIME		= 0x80000,
 	TRACE_ITER_RECORD_CMD		= 0x100000,
+	TRACE_ITER_OVERWRITE		= 0x200000,
 };
 
 /*
@@ -661,8 +662,10 @@ struct ftrace_event_field {
 };
 
 struct event_filter {
-	int			n_preds;
-	struct filter_pred	**preds;
+	int			n_preds;	/* Number assigned */
+	int			a_preds;	/* allocated */
+	struct filter_pred	*preds;
+	struct filter_pred	*root;
 	char			*filter_string;
 };
 
@@ -674,11 +677,23 @@ struct event_subsystem {
 	int			nr_events;
 };
 
+#define FILTER_PRED_INVALID	((unsigned short)-1)
+#define FILTER_PRED_IS_RIGHT	(1 << 15)
+#define FILTER_PRED_FOLD	(1 << 15)
+
+/*
+ * The max preds is the size of unsigned short with
+ * two flags at the MSBs. One bit is used for both the IS_RIGHT
+ * and FOLD flags. The other is reserved.
+ *
+ * 2^14 preds is way more than enough.
+ */
+#define MAX_FILTER_PRED		16384
+
 struct filter_pred;
 struct regex;
 
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
-				 int val1, int val2);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
 
 typedef int (*regex_match_func)(char *str, struct regex *r, int len);
 
@@ -700,11 +715,23 @@ struct filter_pred {
 	filter_pred_fn_t 	fn;
 	u64 			val;
 	struct regex		regex;
-	char 			*field_name;
+	/*
+	 * Leaf nodes use field_name, ops is used by AND and OR
+	 * nodes. The field_name is always freed when freeing a pred.
+	 * We can overload field_name for ops and have it freed
+	 * as well.
+	 */
+	union {
+		char		*field_name;
+		unsigned short	*ops;
+	};
 	int 			offset;
 	int 			not;
 	int 			op;
-	int 			pop_n;
+	unsigned short		index;
+	unsigned short		parent;
+	unsigned short		left;
+	unsigned short		right;
 };
 
 extern struct list_head ftrace_common_fields;
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 6cf223764be8..1516cb3ec549 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -109,12 +109,12 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
  */
 #define FTRACE_CTX_FIELDS					\
 	__field(	unsigned int,	prev_pid	)	\
+	__field(	unsigned int,	next_pid	)	\
+	__field(	unsigned int,	next_cpu	)       \
 	__field(	unsigned char,	prev_prio	)	\
 	__field(	unsigned char,	prev_state	)	\
-	__field(	unsigned int,	next_pid	)	\
 	__field(	unsigned char,	next_prio	)	\
-	__field(	unsigned char,	next_state	)	\
-	__field(	unsigned int,	next_cpu	)
+	__field(	unsigned char,	next_state	)
 
 FTRACE_ENTRY(context_switch, ctx_switch_entry,
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5f499e0438a4..e88f74fe1d4c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, lock_depth);
 
 	return ret;
 }
@@ -326,6 +325,7 @@ int trace_set_clr_event(const char *system, const char *event, int set)
 {
 	return __ftrace_set_clr_event(NULL, system, event, set);
 }
+EXPORT_SYMBOL_GPL(trace_set_clr_event);
 
 /* 128 should be much more than enough */
 #define EVENT_BUF_SIZE		127
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 36d40104b17f..3249b4f77ef0 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -123,9 +123,13 @@ struct filter_parse_state {
 	} operand;
 };
 
+struct pred_stack {
+	struct filter_pred	**preds;
+	int			index;
+};
+
 #define DEFINE_COMPARISON_PRED(type)					\
-static int filter_pred_##type(struct filter_pred *pred, void *event,	\
-			      int val1, int val2)			\
+static int filter_pred_##type(struct filter_pred *pred, void *event)	\
 {									\
 	type *addr = (type *)(event + pred->offset);			\
 	type val = (type)pred->val;					\
@@ -152,8 +156,7 @@ static int filter_pred_##type(struct filter_pred *pred, void *event,	\
 }
 
 #define DEFINE_EQUALITY_PRED(size)					\
-static int filter_pred_##size(struct filter_pred *pred, void *event,	\
-			      int val1, int val2)			\
+static int filter_pred_##size(struct filter_pred *pred, void *event)	\
 {									\
 	u##size *addr = (u##size *)(event + pred->offset);		\
 	u##size val = (u##size)pred->val;				\
@@ -178,23 +181,8 @@ DEFINE_EQUALITY_PRED(32);
 DEFINE_EQUALITY_PRED(16);
 DEFINE_EQUALITY_PRED(8);
 
-static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
-			   void *event __attribute((unused)),
-			   int val1, int val2)
-{
-	return val1 && val2;
-}
-
-static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
-			  void *event __attribute((unused)),
-			  int val1, int val2)
-{
-	return val1 || val2;
-}
-
 /* Filter predicate for fixed sized arrays of characters */
-static int filter_pred_string(struct filter_pred *pred, void *event,
-			      int val1, int val2)
+static int filter_pred_string(struct filter_pred *pred, void *event)
 {
 	char *addr = (char *)(event + pred->offset);
 	int cmp, match;
@@ -207,8 +195,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 }
 
 /* Filter predicate for char * pointers */
-static int filter_pred_pchar(struct filter_pred *pred, void *event,
-			     int val1, int val2)
+static int filter_pred_pchar(struct filter_pred *pred, void *event)
 {
 	char **addr = (char **)(event + pred->offset);
 	int cmp, match;
@@ -231,8 +218,7 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
  * and add it to the address of the entry, and at last we have
  * the address of the string.
  */
-static int filter_pred_strloc(struct filter_pred *pred, void *event,
-			      int val1, int val2)
+static int filter_pred_strloc(struct filter_pred *pred, void *event)
 {
 	u32 str_item = *(u32 *)(event + pred->offset);
 	int str_loc = str_item & 0xffff;
@@ -247,8 +233,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
 	return match;
 }
 
-static int filter_pred_none(struct filter_pred *pred, void *event,
-			    int val1, int val2)
+static int filter_pred_none(struct filter_pred *pred, void *event)
 {
 	return 0;
 }
@@ -377,32 +362,147 @@ static void filter_build_regex(struct filter_pred *pred)
 	pred->not ^= not;
 }
 
+enum move_type {
+	MOVE_DOWN,
+	MOVE_UP_FROM_LEFT,
+	MOVE_UP_FROM_RIGHT
+};
+
+static struct filter_pred *
+get_pred_parent(struct filter_pred *pred, struct filter_pred *preds,
+		int index, enum move_type *move)
+{
+	if (pred->parent & FILTER_PRED_IS_RIGHT)
+		*move = MOVE_UP_FROM_RIGHT;
+	else
+		*move = MOVE_UP_FROM_LEFT;
+	pred = &preds[pred->parent & ~FILTER_PRED_IS_RIGHT];
+
+	return pred;
+}
+
+/*
+ * A series of AND or ORs where found together. Instead of
+ * climbing up and down the tree branches, an array of the
+ * ops were made in order of checks. We can just move across
+ * the array and short circuit if needed.
+ */
+static int process_ops(struct filter_pred *preds,
+		       struct filter_pred *op, void *rec)
+{
+	struct filter_pred *pred;
+	int type;
+	int match;
+	int i;
+
+	/*
+	 * Micro-optimization: We set type to true if op
+	 * is an OR and false otherwise (AND). Then we
+	 * just need to test if the match is equal to
+	 * the type, and if it is, we can short circuit the
+	 * rest of the checks:
+	 *
+	 * if ((match && op->op == OP_OR) ||
+	 *     (!match && op->op == OP_AND))
+	 *	  return match;
+	 */
+	type = op->op == OP_OR;
+
+	for (i = 0; i < op->val; i++) {
+		pred = &preds[op->ops[i]];
+		match = pred->fn(pred, rec);
+		if (!!match == type)
+			return match;
+	}
+	return match;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct event_filter *filter, void *rec)
 {
-	int match, top = 0, val1 = 0, val2 = 0;
-	int stack[MAX_FILTER_PRED];
+	int match = -1;
+	enum move_type move = MOVE_DOWN;
+	struct filter_pred *preds;
 	struct filter_pred *pred;
-	int i;
+	struct filter_pred *root;
+	int n_preds;
+	int done = 0;
+
+	/* no filter is considered a match */
+	if (!filter)
+		return 1;
+
+	n_preds = filter->n_preds;
+
+	if (!n_preds)
+		return 1;
+
+	/*
+	 * n_preds, root and filter->preds are protect with preemption disabled.
+	 */
+	preds = rcu_dereference_sched(filter->preds);
+	root = rcu_dereference_sched(filter->root);
+	if (!root)
+		return 1;
+
+	pred = root;
 
-	for (i = 0; i < filter->n_preds; i++) {
-		pred = filter->preds[i];
-		if (!pred->pop_n) {
-			match = pred->fn(pred, rec, val1, val2);
-			stack[top++] = match;
+	/* match is currently meaningless */
+	match = -1;
+
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			/* only AND and OR have children */
+			if (pred->left != FILTER_PRED_INVALID) {
+				/* If ops is set, then it was folded. */
+				if (!pred->ops) {
+					/* keep going to down the left side */
+					pred = &preds[pred->left];
+					continue;
+				}
+				/* We can treat folded ops as a leaf node */
+				match = process_ops(preds, pred, rec);
+			} else
+				match = pred->fn(pred, rec);
+			/* If this pred is the only pred */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			/*
+			 * Check for short circuits.
+			 *
+			 * Optimization: !!match == (pred->op == OP_OR)
+			 *   is the same as:
+			 * if ((match && pred->op == OP_OR) ||
+			 *     (!match && pred->op == OP_AND))
+			 */
+			if (!!match == (pred->op == OP_OR)) {
+				if (pred == root)
+					break;
+				pred = get_pred_parent(pred, preds,
+						       pred->parent, &move);
+				continue;
+			}
+			/* now go down the right side of the tree. */
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			/* We finished this equation. */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
 			continue;
 		}
-		if (pred->pop_n > top) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		val1 = stack[--top];
-		val2 = stack[--top];
-		match = pred->fn(pred, rec, val1, val2);
-		stack[top++] = match;
-	}
+		done = 1;
+	} while (!done);
 
-	return stack[--top];
+	return match;
 }
 EXPORT_SYMBOL_GPL(filter_match_preds);
 
@@ -414,6 +514,9 @@ static void parse_error(struct filter_parse_state *ps, int err, int pos)
 
 static void remove_filter_string(struct event_filter *filter)
 {
+	if (!filter)
+		return;
+
 	kfree(filter->filter_string);
 	filter->filter_string = NULL;
 }
@@ -473,9 +576,10 @@ static void append_filter_err(struct filter_parse_state *ps,
 
 void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	struct event_filter *filter = call->filter;
+	struct event_filter *filter;
 
 	mutex_lock(&event_mutex);
+	filter = call->filter;
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
@@ -486,9 +590,10 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 void print_subsystem_event_filter(struct event_subsystem *system,
 				  struct trace_seq *s)
 {
-	struct event_filter *filter = system->filter;
+	struct event_filter *filter;
 
 	mutex_lock(&event_mutex);
+	filter = system->filter;
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
@@ -539,10 +644,58 @@ static void filter_clear_pred(struct filter_pred *pred)
 	pred->regex.len = 0;
 }
 
-static int filter_set_pred(struct filter_pred *dest,
+static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
+{
+	stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+	if (!stack->preds)
+		return -ENOMEM;
+	stack->index = n_preds;
+	return 0;
+}
+
+static void __free_pred_stack(struct pred_stack *stack)
+{
+	kfree(stack->preds);
+	stack->index = 0;
+}
+
+static int __push_pred_stack(struct pred_stack *stack,
+			     struct filter_pred *pred)
+{
+	int index = stack->index;
+
+	if (WARN_ON(index == 0))
+		return -ENOSPC;
+
+	stack->preds[--index] = pred;
+	stack->index = index;
+	return 0;
+}
+
+static struct filter_pred *
+__pop_pred_stack(struct pred_stack *stack)
+{
+	struct filter_pred *pred;
+	int index = stack->index;
+
+	pred = stack->preds[index++];
+	if (!pred)
+		return NULL;
+
+	stack->index = index;
+	return pred;
+}
+
+static int filter_set_pred(struct event_filter *filter,
+			   int idx,
+			   struct pred_stack *stack,
 			   struct filter_pred *src,
 			   filter_pred_fn_t fn)
 {
+	struct filter_pred *dest = &filter->preds[idx];
+	struct filter_pred *left;
+	struct filter_pred *right;
+
 	*dest = *src;
 	if (src->field_name) {
 		dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
@@ -550,116 +703,140 @@ static int filter_set_pred(struct filter_pred *dest,
 			return -ENOMEM;
 	}
 	dest->fn = fn;
+	dest->index = idx;
 
-	return 0;
+	if (dest->op == OP_OR || dest->op == OP_AND) {
+		right = __pop_pred_stack(stack);
+		left = __pop_pred_stack(stack);
+		if (!left || !right)
+			return -EINVAL;
+		/*
+		 * If both children can be folded
+		 * and they are the same op as this op or a leaf,
+		 * then this op can be folded.
+		 */
+		if (left->index & FILTER_PRED_FOLD &&
+		    (left->op == dest->op ||
+		     left->left == FILTER_PRED_INVALID) &&
+		    right->index & FILTER_PRED_FOLD &&
+		    (right->op == dest->op ||
+		     right->left == FILTER_PRED_INVALID))
+			dest->index |= FILTER_PRED_FOLD;
+
+		dest->left = left->index & ~FILTER_PRED_FOLD;
+		dest->right = right->index & ~FILTER_PRED_FOLD;
+		left->parent = dest->index & ~FILTER_PRED_FOLD;
+		right->parent = dest->index | FILTER_PRED_IS_RIGHT;
+	} else {
+		/*
+		 * Make dest->left invalid to be used as a quick
+		 * way to know this is a leaf node.
+		 */
+		dest->left = FILTER_PRED_INVALID;
+
+		/* All leafs allow folding the parent ops. */
+		dest->index |= FILTER_PRED_FOLD;
+	}
+
+	return __push_pred_stack(stack, dest);
 }
 
-static void filter_disable_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
 {
-	struct event_filter *filter = call->filter;
 	int i;
 
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
+	if (filter->preds) {
+		for (i = 0; i < filter->a_preds; i++)
+			kfree(filter->preds[i].field_name);
+		kfree(filter->preds);
+		filter->preds = NULL;
+	}
+	filter->a_preds = 0;
 	filter->n_preds = 0;
-
-	for (i = 0; i < MAX_FILTER_PRED; i++)
-		filter->preds[i]->fn = filter_pred_none;
 }
 
-static void __free_preds(struct event_filter *filter)
+static void filter_disable(struct ftrace_event_call *call)
 {
-	int i;
+	call->flags &= ~TRACE_EVENT_FL_FILTERED;
+}
 
+static void __free_filter(struct event_filter *filter)
+{
 	if (!filter)
 		return;
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (filter->preds[i])
-			filter_free_pred(filter->preds[i]);
-	}
-	kfree(filter->preds);
+	__free_preds(filter);
 	kfree(filter->filter_string);
 	kfree(filter);
 }
 
+/*
+ * Called when destroying the ftrace_event_call.
+ * The call is being freed, so we do not need to worry about
+ * the call being currently used. This is for module code removing
+ * the tracepoints from within it.
+ */
 void destroy_preds(struct ftrace_event_call *call)
 {
-	__free_preds(call->filter);
+	__free_filter(call->filter);
 	call->filter = NULL;
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
 }
 
-static struct event_filter *__alloc_preds(void)
+static struct event_filter *__alloc_filter(void)
 {
 	struct event_filter *filter;
+
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	return filter;
+}
+
+static int __alloc_preds(struct event_filter *filter, int n_preds)
+{
 	struct filter_pred *pred;
 	int i;
 
-	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
-	if (!filter)
-		return ERR_PTR(-ENOMEM);
+	if (filter->preds)
+		__free_preds(filter);
 
-	filter->n_preds = 0;
+	filter->preds =
+		kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
 
-	filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
 	if (!filter->preds)
-		goto oom;
+		return -ENOMEM;
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-		if (!pred)
-			goto oom;
+	filter->a_preds = n_preds;
+	filter->n_preds = 0;
+
+	for (i = 0; i < n_preds; i++) {
+		pred = &filter->preds[i];
 		pred->fn = filter_pred_none;
-		filter->preds[i] = pred;
 	}
 
-	return filter;
-
-oom:
-	__free_preds(filter);
-	return ERR_PTR(-ENOMEM);
-}
-
-static int init_preds(struct ftrace_event_call *call)
-{
-	if (call->filter)
-		return 0;
-
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
-	call->filter = __alloc_preds();
-	if (IS_ERR(call->filter))
-		return PTR_ERR(call->filter);
-
 	return 0;
 }
 
-static int init_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
 {
 	struct ftrace_event_call *call;
-	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		err = init_preds(call);
-		if (err)
-			return err;
+		filter_disable(call);
+		remove_filter_string(call->filter);
 	}
-
-	return 0;
 }
 
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_filters(struct event_subsystem *system)
 {
 	struct ftrace_event_call *call;
 
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
-
-		filter_disable_preds(call);
-		remove_filter_string(call->filter);
+		__free_filter(call->filter);
+		call->filter = NULL;
 	}
 }
 
@@ -667,18 +844,19 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
 			      struct ftrace_event_call *call,
 			      struct event_filter *filter,
 			      struct filter_pred *pred,
+			      struct pred_stack *stack,
 			      filter_pred_fn_t fn)
 {
 	int idx, err;
 
-	if (filter->n_preds == MAX_FILTER_PRED) {
+	if (WARN_ON(filter->n_preds == filter->a_preds)) {
 		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
 		return -ENOSPC;
 	}
 
 	idx = filter->n_preds;
-	filter_clear_pred(filter->preds[idx]);
-	err = filter_set_pred(filter->preds[idx], pred, fn);
+	filter_clear_pred(&filter->preds[idx]);
+	err = filter_set_pred(filter, idx, stack, pred, fn);
 	if (err)
 		return err;
 
@@ -763,6 +941,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 			   struct ftrace_event_call *call,
 			   struct event_filter *filter,
 			   struct filter_pred *pred,
+			   struct pred_stack *stack,
 			   bool dry_run)
 {
 	struct ftrace_event_field *field;
@@ -770,17 +949,12 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	unsigned long long val;
 	int ret;
 
-	pred->fn = filter_pred_none;
+	fn = pred->fn = filter_pred_none;
 
-	if (pred->op == OP_AND) {
-		pred->pop_n = 2;
-		fn = filter_pred_and;
+	if (pred->op == OP_AND)
 		goto add_pred_fn;
-	} else if (pred->op == OP_OR) {
-		pred->pop_n = 2;
-		fn = filter_pred_or;
+	else if (pred->op == OP_OR)
 		goto add_pred_fn;
-	}
 
 	field = find_event_field(call, pred->field_name);
 	if (!field) {
@@ -829,7 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 
 add_pred_fn:
 	if (!dry_run)
-		return filter_add_pred_fn(ps, call, filter, pred, fn);
+		return filter_add_pred_fn(ps, call, filter, pred, stack, fn);
 	return 0;
 }
 
@@ -1187,6 +1361,234 @@ static int check_preds(struct filter_parse_state *ps)
 	return 0;
 }
 
+static int count_preds(struct filter_parse_state *ps)
+{
+	struct postfix_elt *elt;
+	int n_preds = 0;
+
+	list_for_each_entry(elt, &ps->postfix, list) {
+		if (elt->op == OP_NONE)
+			continue;
+		n_preds++;
+	}
+
+	return n_preds;
+}
+
+/*
+ * The tree is walked at filtering of an event. If the tree is not correctly
+ * built, it may cause an infinite loop. Check here that the tree does
+ * indeed terminate.
+ */
+static int check_pred_tree(struct event_filter *filter,
+			   struct filter_pred *root)
+{
+	struct filter_pred *preds;
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int count = 0;
+	int done = 0;
+	int max;
+
+	/*
+	 * The max that we can hit a node is three times.
+	 * Once going down, once coming up from left, and
+	 * once coming up from right. This is more than enough
+	 * since leafs are only hit a single time.
+	 */
+	max = 3 * filter->n_preds;
+
+	preds = filter->preds;
+	if  (!preds)
+		return -EINVAL;
+	pred = root;
+
+	do {
+		if (WARN_ON(count++ > max))
+			return -EINVAL;
+
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			/* A leaf at the root is just a leaf in the tree */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	/* We are fine. */
+	return 0;
+}
+
+static int count_leafs(struct filter_pred *preds, struct filter_pred *root)
+{
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int count = 0;
+	int done = 0;
+
+	pred = root;
+
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			/* A leaf at the root is just a leaf in the tree */
+			if (pred == root)
+				return 1;
+			count++;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	return count;
+}
+
+static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
+{
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int count = 0;
+	int children;
+	int done = 0;
+
+	/* No need to keep the fold flag */
+	root->index &= ~FILTER_PRED_FOLD;
+
+	/* If the root is a leaf then do nothing */
+	if (root->left == FILTER_PRED_INVALID)
+		return 0;
+
+	/* count the children */
+	children = count_leafs(preds, &preds[root->left]);
+	children += count_leafs(preds, &preds[root->right]);
+
+	root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+	if (!root->ops)
+		return -ENOMEM;
+
+	root->val = children;
+
+	pred = root;
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			if (WARN_ON(count == children))
+				return -EINVAL;
+			pred->index &= ~FILTER_PRED_FOLD;
+			root->ops[count++] = pred->index;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	return 0;
+}
+
+/*
+ * To optimize the processing of the ops, if we have several "ors" or
+ * "ands" together, we can put them in an array and process them all
+ * together speeding up the filter logic.
+ */
+static int fold_pred_tree(struct event_filter *filter,
+			   struct filter_pred *root)
+{
+	struct filter_pred *preds;
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int done = 0;
+	int err;
+
+	preds = filter->preds;
+	if  (!preds)
+		return -EINVAL;
+	pred = root;
+
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->index & FILTER_PRED_FOLD) {
+				err = fold_pred(preds, pred);
+				if (err)
+					return err;
+				/* Folded nodes are like leafs */
+			} else if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+
+			/* A leaf at the root is just a leaf in the tree */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	return 0;
+}
+
 static int replace_preds(struct ftrace_event_call *call,
 			 struct event_filter *filter,
 			 struct filter_parse_state *ps,
@@ -1195,14 +1597,32 @@ static int replace_preds(struct ftrace_event_call *call,
 {
 	char *operand1 = NULL, *operand2 = NULL;
 	struct filter_pred *pred;
+	struct filter_pred *root;
 	struct postfix_elt *elt;
+	struct pred_stack stack = { }; /* init to NULL */
 	int err;
 	int n_preds = 0;
 
+	n_preds = count_preds(ps);
+	if (n_preds >= MAX_FILTER_PRED) {
+		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+		return -ENOSPC;
+	}
+
 	err = check_preds(ps);
 	if (err)
 		return err;
 
+	if (!dry_run) {
+		err = __alloc_pred_stack(&stack, n_preds);
+		if (err)
+			return err;
+		err = __alloc_preds(filter, n_preds);
+		if (err)
+			goto fail;
+	}
+
+	n_preds = 0;
 	list_for_each_entry(elt, &ps->postfix, list) {
 		if (elt->op == OP_NONE) {
 			if (!operand1)
@@ -1211,14 +1631,16 @@ static int replace_preds(struct ftrace_event_call *call,
 				operand2 = elt->operand;
 			else {
 				parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
-				return -EINVAL;
+				err = -EINVAL;
+				goto fail;
 			}
 			continue;
 		}
 
-		if (n_preds++ == MAX_FILTER_PRED) {
+		if (WARN_ON(n_preds++ == MAX_FILTER_PRED)) {
 			parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
-			return -ENOSPC;
+			err = -ENOSPC;
+			goto fail;
 		}
 
 		if (elt->op == OP_AND || elt->op == OP_OR) {
@@ -1228,76 +1650,181 @@ static int replace_preds(struct ftrace_event_call *call,
 
 		if (!operand1 || !operand2) {
 			parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
-			return -EINVAL;
+			err = -EINVAL;
+			goto fail;
 		}
 
 		pred = create_pred(elt->op, operand1, operand2);
 add_pred:
-		if (!pred)
-			return -ENOMEM;
-		err = filter_add_pred(ps, call, filter, pred, dry_run);
+		if (!pred) {
+			err = -ENOMEM;
+			goto fail;
+		}
+		err = filter_add_pred(ps, call, filter, pred, &stack, dry_run);
 		filter_free_pred(pred);
 		if (err)
-			return err;
+			goto fail;
 
 		operand1 = operand2 = NULL;
 	}
 
-	return 0;
+	if (!dry_run) {
+		/* We should have one item left on the stack */
+		pred = __pop_pred_stack(&stack);
+		if (!pred)
+			return -EINVAL;
+		/* This item is where we start from in matching */
+		root = pred;
+		/* Make sure the stack is empty */
+		pred = __pop_pred_stack(&stack);
+		if (WARN_ON(pred)) {
+			err = -EINVAL;
+			filter->root = NULL;
+			goto fail;
+		}
+		err = check_pred_tree(filter, root);
+		if (err)
+			goto fail;
+
+		/* Optimize the tree */
+		err = fold_pred_tree(filter, root);
+		if (err)
+			goto fail;
+
+		/* We don't set root until we know it works */
+		barrier();
+		filter->root = root;
+	}
+
+	err = 0;
+fail:
+	__free_pred_stack(&stack);
+	return err;
 }
 
+struct filter_list {
+	struct list_head	list;
+	struct event_filter	*filter;
+};
+
 static int replace_system_preds(struct event_subsystem *system,
 				struct filter_parse_state *ps,
 				char *filter_string)
 {
 	struct ftrace_event_call *call;
+	struct filter_list *filter_item;
+	struct filter_list *tmp;
+	LIST_HEAD(filter_list);
 	bool fail = true;
 	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		struct event_filter *filter = call->filter;
 
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		/* try to see if the filter can be applied */
-		err = replace_preds(call, filter, ps, filter_string, true);
+		/*
+		 * Try to see if the filter can be applied
+		 *  (filter arg is ignored on dry_run)
+		 */
+		err = replace_preds(call, NULL, ps, filter_string, true);
 		if (err)
+			goto fail;
+	}
+
+	list_for_each_entry(call, &ftrace_events, list) {
+		struct event_filter *filter;
+
+		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		/* really apply the filter */
-		filter_disable_preds(call);
-		err = replace_preds(call, filter, ps, filter_string, false);
+		filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
+		if (!filter_item)
+			goto fail_mem;
+
+		list_add_tail(&filter_item->list, &filter_list);
+
+		filter_item->filter = __alloc_filter();
+		if (!filter_item->filter)
+			goto fail_mem;
+		filter = filter_item->filter;
+
+		/* Can only fail on no memory */
+		err = replace_filter_string(filter, filter_string);
 		if (err)
-			filter_disable_preds(call);
-		else {
+			goto fail_mem;
+
+		err = replace_preds(call, filter, ps, filter_string, false);
+		if (err) {
+			filter_disable(call);
+			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+			append_filter_err(ps, filter);
+		} else
 			call->flags |= TRACE_EVENT_FL_FILTERED;
-			replace_filter_string(filter, filter_string);
-		}
+		/*
+		 * Regardless of if this returned an error, we still
+		 * replace the filter for the call.
+		 */
+		filter = call->filter;
+		call->filter = filter_item->filter;
+		filter_item->filter = filter;
+
 		fail = false;
 	}
 
-	if (fail) {
-		parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-		return -EINVAL;
+	if (fail)
+		goto fail;
+
+	/*
+	 * The calls can still be using the old filters.
+	 * Do a synchronize_sched() to ensure all calls are
+	 * done with them before we free them.
+	 */
+	synchronize_sched();
+	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+		__free_filter(filter_item->filter);
+		list_del(&filter_item->list);
+		kfree(filter_item);
 	}
 	return 0;
+ fail:
+	/* No call succeeded */
+	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+		list_del(&filter_item->list);
+		kfree(filter_item);
+	}
+	parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+	return -EINVAL;
+ fail_mem:
+	/* If any call succeeded, we still need to sync */
+	if (!fail)
+		synchronize_sched();
+	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+		__free_filter(filter_item->filter);
+		list_del(&filter_item->list);
+		kfree(filter_item);
+	}
+	return -ENOMEM;
 }
 
 int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 {
-	int err;
 	struct filter_parse_state *ps;
+	struct event_filter *filter;
+	struct event_filter *tmp;
+	int err = 0;
 
 	mutex_lock(&event_mutex);
 
-	err = init_preds(call);
-	if (err)
-		goto out_unlock;
-
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_disable_preds(call);
-		remove_filter_string(call->filter);
+		filter_disable(call);
+		filter = call->filter;
+		if (!filter)
+			goto out_unlock;
+		call->filter = NULL;
+		/* Make sure the filter is not being used */
+		synchronize_sched();
+		__free_filter(filter);
 		goto out_unlock;
 	}
 
@@ -1306,22 +1833,41 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 	if (!ps)
 		goto out_unlock;
 
-	filter_disable_preds(call);
-	replace_filter_string(call->filter, filter_string);
+	filter = __alloc_filter();
+	if (!filter) {
+		kfree(ps);
+		goto out_unlock;
+	}
+
+	replace_filter_string(filter, filter_string);
 
 	parse_init(ps, filter_ops, filter_string);
 	err = filter_parse(ps);
 	if (err) {
-		append_filter_err(ps, call->filter);
+		append_filter_err(ps, filter);
 		goto out;
 	}
 
-	err = replace_preds(call, call->filter, ps, filter_string, false);
-	if (err)
-		append_filter_err(ps, call->filter);
-	else
+	err = replace_preds(call, filter, ps, filter_string, false);
+	if (err) {
+		filter_disable(call);
+		append_filter_err(ps, filter);
+	} else
 		call->flags |= TRACE_EVENT_FL_FILTERED;
 out:
+	/*
+	 * Always swap the call filter with the new filter
+	 * even if there was an error. If there was an error
+	 * in the filter, we disable the filter and show the error
+	 * string
+	 */
+	tmp = call->filter;
+	call->filter = filter;
+	if (tmp) {
+		/* Make sure the call is done with the filter */
+		synchronize_sched();
+		__free_filter(tmp);
+	}
 	filter_opstack_clear(ps);
 	postfix_clear(ps);
 	kfree(ps);
@@ -1334,18 +1880,21 @@ out_unlock:
 int apply_subsystem_event_filter(struct event_subsystem *system,
 				 char *filter_string)
 {
-	int err;
 	struct filter_parse_state *ps;
+	struct event_filter *filter;
+	int err = 0;
 
 	mutex_lock(&event_mutex);
 
-	err = init_subsystem_preds(system);
-	if (err)
-		goto out_unlock;
-
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_free_subsystem_preds(system);
 		remove_filter_string(system->filter);
+		filter = system->filter;
+		system->filter = NULL;
+		/* Ensure all filters are no longer used */
+		synchronize_sched();
+		filter_free_subsystem_filters(system);
+		__free_filter(filter);
 		goto out_unlock;
 	}
 
@@ -1354,7 +1903,17 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 	if (!ps)
 		goto out_unlock;
 
-	replace_filter_string(system->filter, filter_string);
+	filter = __alloc_filter();
+	if (!filter)
+		goto out;
+
+	replace_filter_string(filter, filter_string);
+	/*
+	 * No event actually uses the system filter
+	 * we can free it without synchronize_sched().
+	 */
+	__free_filter(system->filter);
+	system->filter = filter;
 
 	parse_init(ps, filter_ops, filter_string);
 	err = filter_parse(ps);
@@ -1384,7 +1943,7 @@ void ftrace_profile_free_filter(struct perf_event *event)
 	struct event_filter *filter = event->filter;
 
 	event->filter = NULL;
-	__free_preds(filter);
+	__free_filter(filter);
 }
 
 int ftrace_profile_set_filter(struct perf_event *event, int event_id,
@@ -1410,8 +1969,8 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	if (event->filter)
 		goto out_unlock;
 
-	filter = __alloc_preds();
-	if (IS_ERR(filter)) {
+	filter = __alloc_filter();
+	if (!filter) {
 		err = PTR_ERR(filter);
 		goto out_unlock;
 	}
@@ -1419,7 +1978,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	err = -ENOMEM;
 	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
 	if (!ps)
-		goto free_preds;
+		goto free_filter;
 
 	parse_init(ps, filter_ops, filter_str);
 	err = filter_parse(ps);
@@ -1435,9 +1994,9 @@ free_ps:
 	postfix_clear(ps);
 	kfree(ps);
 
-free_preds:
+free_filter:
 	if (err)
-		__free_preds(filter);
+		__free_filter(filter);
 
 out_unlock:
 	mutex_unlock(&event_mutex);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2dec9bcde8b4..8435b43b1782 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -353,6 +353,43 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 	kfree(data);
 }
 
+/* Bitfield fetch function */
+struct bitfield_fetch_param {
+	struct fetch_param orig;
+	unsigned char hi_shift;
+	unsigned char low_shift;
+};
+
+#define DEFINE_FETCH_bitfield(type)					\
+static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+					    void *data, void *dest)	\
+{									\
+	struct bitfield_fetch_param *bprm = data;			\
+	type buf = 0;							\
+	call_fetch(&bprm->orig, regs, &buf);				\
+	if (buf) {							\
+		buf <<= bprm->hi_shift;					\
+		buf >>= bprm->low_shift;				\
+	}								\
+	*(type *)dest = buf;						\
+}
+DEFINE_BASIC_FETCH_FUNCS(bitfield)
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+static __kprobes void
+free_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		free_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		free_symbol_cache(data->orig.data);
+	kfree(data);
+}
 /* Default (unsigned long) fetch type */
 #define __DEFAULT_FETCH_TYPE(t) u##t
 #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
@@ -367,6 +404,7 @@ enum {
 	FETCH_MTD_memory,
 	FETCH_MTD_symbol,
 	FETCH_MTD_deref,
+	FETCH_MTD_bitfield,
 	FETCH_MTD_END,
 };
 
@@ -387,6 +425,7 @@ ASSIGN_FETCH_FUNC(retval, ftype),			\
 ASSIGN_FETCH_FUNC(memory, ftype),			\
 ASSIGN_FETCH_FUNC(symbol, ftype),			\
 ASSIGN_FETCH_FUNC(deref, ftype),			\
+ASSIGN_FETCH_FUNC(bitfield, ftype),			\
 	  }						\
 	}
 
@@ -430,9 +469,33 @@ static const struct fetch_type *find_fetch_type(const char *type)
 	if (!type)
 		type = DEFAULT_FETCH_TYPE_STR;
 
+	/* Special case: bitfield */
+	if (*type == 'b') {
+		unsigned long bs;
+		type = strchr(type, '/');
+		if (!type)
+			goto fail;
+		type++;
+		if (strict_strtoul(type, 0, &bs))
+			goto fail;
+		switch (bs) {
+		case 8:
+			return find_fetch_type("u8");
+		case 16:
+			return find_fetch_type("u16");
+		case 32:
+			return find_fetch_type("u32");
+		case 64:
+			return find_fetch_type("u64");
+		default:
+			goto fail;
+		}
+	}
+
 	for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
 		if (strcmp(type, fetch_type_table[i].name) == 0)
 			return &fetch_type_table[i];
+fail:
 	return NULL;
 }
 
@@ -586,7 +649,9 @@ error:
 
 static void free_probe_arg(struct probe_arg *arg)
 {
-	if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+		free_bitfield_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
 		free_deref_fetch_param(arg->fetch.data);
 	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
 		free_symbol_cache(arg->fetch.data);
@@ -767,16 +832,15 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 		}
 		break;
 	case '+':	/* deref memory */
+		arg++;	/* Skip '+', because strict_strtol() rejects it. */
 	case '-':
 		tmp = strchr(arg, '(');
 		if (!tmp)
 			break;
 		*tmp = '\0';
-		ret = strict_strtol(arg + 1, 0, &offset);
+		ret = strict_strtol(arg, 0, &offset);
 		if (ret)
 			break;
-		if (arg[0] == '-')
-			offset = -offset;
 		arg = tmp + 1;
 		tmp = strrchr(arg, ')');
 		if (tmp) {
@@ -807,6 +871,41 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 	return ret;
 }
 
+#define BYTES_TO_BITS(nb)	((BITS_PER_LONG * (nb)) / sizeof(long))
+
+/* Bitfield type needs to be parsed into a fetch function */
+static int __parse_bitfield_probe_arg(const char *bf,
+				      const struct fetch_type *t,
+				      struct fetch_param *f)
+{
+	struct bitfield_fetch_param *bprm;
+	unsigned long bw, bo;
+	char *tail;
+
+	if (*bf != 'b')
+		return 0;
+
+	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	if (!bprm)
+		return -ENOMEM;
+	bprm->orig = *f;
+	f->fn = t->fetch[FETCH_MTD_bitfield];
+	f->data = (void *)bprm;
+
+	bw = simple_strtoul(bf + 1, &tail, 0);	/* Use simple one */
+	if (bw == 0 || *tail != '@')
+		return -EINVAL;
+
+	bf = tail + 1;
+	bo = simple_strtoul(bf, &tail, 0);
+	if (tail == bf || *tail != '/')
+		return -EINVAL;
+
+	bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
+	bprm->low_shift = bprm->hi_shift + bo;
+	return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
+}
+
 /* String length checking wrapper */
 static int parse_probe_arg(char *arg, struct trace_probe *tp,
 			   struct probe_arg *parg, int is_return)
@@ -836,6 +935,8 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp,
 	parg->offset = tp->size;
 	tp->size += parg->type->size;
 	ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+	if (ret >= 0 && t != NULL)
+		ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
 	if (ret >= 0) {
 		parg->fetch_size.fn = get_fetch_size_function(parg->type,
 							      parg->fetch.fn);
@@ -1130,7 +1231,7 @@ static int command_trace_probe(const char *buf)
 	return ret;
 }
 
-#define WRITE_BUFSIZE 128
+#define WRITE_BUFSIZE 4096
 
 static ssize_t probes_write(struct file *file, const char __user *buffer,
 			    size_t count, loff_t *ppos)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02272baa2206..456be9063c2d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -529,24 +529,34 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
  * @entry: The trace entry field from the ring buffer
  *
  * Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
  */
 int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
-	int hardirq, softirq;
+	char hardsoft_irq;
+	char need_resched;
+	char irqs_off;
+	int hardirq;
+	int softirq;
 	int ret;
 
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
+	irqs_off =
+		(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+		(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+		'.';
+	need_resched =
+		(entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+	hardsoft_irq =
+		(hardirq && softirq) ? 'H' :
+		hardirq ? 'h' :
+		softirq ? 's' :
+		'.';
+
 	if (!trace_seq_printf(s, "%c%c%c",
-			      (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
-				(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
-				  'X' : '.',
-			      (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
-				'N' : '.',
-			      (hardirq && softirq) ? 'H' :
-				hardirq ? 'h' : softirq ? 's' : '.'))
+			      irqs_off, need_resched, hardsoft_irq))
 		return 0;
 
 	if (entry->preempt_count)
@@ -554,13 +564,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 	else
 		ret = trace_seq_putc(s, '.');
 
-	if (!ret)
-		return 0;
-
-	if (entry->lock_depth < 0)
-		return trace_seq_putc(s, '.');
-
-	return trace_seq_printf(s, "%d", entry->lock_depth);
+	return ret;
 }
 
 static int
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 8f758d070c43..7e62c0a18456 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -247,51 +247,3 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr)
 	ctx_trace = tr;
 }
 
-static void stop_sched_trace(struct trace_array *tr)
-{
-	tracing_stop_sched_switch_record();
-}
-
-static int sched_switch_trace_init(struct trace_array *tr)
-{
-	ctx_trace = tr;
-	tracing_reset_online_cpus(tr);
-	tracing_start_sched_switch_record();
-	return 0;
-}
-
-static void sched_switch_trace_reset(struct trace_array *tr)
-{
-	if (sched_ref)
-		stop_sched_trace(tr);
-}
-
-static void sched_switch_trace_start(struct trace_array *tr)
-{
-	sched_stopped = 0;
-}
-
-static void sched_switch_trace_stop(struct trace_array *tr)
-{
-	sched_stopped = 1;
-}
-
-static struct tracer sched_switch_trace __read_mostly =
-{
-	.name		= "sched_switch",
-	.init		= sched_switch_trace_init,
-	.reset		= sched_switch_trace_reset,
-	.start		= sched_switch_trace_start,
-	.stop		= sched_switch_trace_stop,
-	.wait_pipe	= poll_wait_pipe,
-#ifdef CONFIG_FTRACE_SELFTEST
-	.selftest    = trace_selftest_startup_sched_switch,
-#endif
-};
-
-__init static int init_sched_switch_trace(void)
-{
-	return register_tracer(&sched_switch_trace);
-}
-device_initcall(init_sched_switch_trace);
-
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5c9fe08d2093..ee7b5a0bb9f8 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -60,6 +60,19 @@ extern struct syscall_metadata *__stop_syscalls_metadata[];
 
 static struct syscall_metadata **syscalls_metadata;
 
+#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/*
+	 * Only compare after the "sys" prefix. Archs that use
+	 * syscall wrappers may have syscalls symbols aliases prefixed
+	 * with "SyS" instead of "sys", leading to an unwanted
+	 * mismatch.
+	 */
+	return !strcmp(sym + 3, name + 3);
+}
+#endif
+
 static __init struct syscall_metadata *
 find_syscall_meta(unsigned long syscall)
 {
@@ -72,14 +85,11 @@ find_syscall_meta(unsigned long syscall)
 	stop = __stop_syscalls_metadata;
 	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
 
+	if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
+		return NULL;
+
 	for ( ; start < stop; start++) {
-		/*
-		 * Only compare after the "sys" prefix. Archs that use
-		 * syscall wrappers may have syscalls symbols aliases prefixed
-		 * with "SyS" instead of "sys", leading to an unwanted
-		 * mismatch.
-		 */
-		if ((*start)->name && !strcmp((*start)->name + 3, str + 3))
+		if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
 			return *start;
 	}
 	return NULL;
@@ -359,7 +369,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_refcount_enter)
@@ -377,7 +387,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
 	sys_refcount_enter--;
@@ -393,7 +403,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_refcount_exit)
@@ -411,7 +421,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
 	sys_refcount_exit--;
@@ -424,6 +434,14 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
 int init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (num < 0 || num >= NR_syscalls) {
+		pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
+				((struct syscall_metadata *)call->data)->name);
+		return -ENOSYS;
+	}
 
 	if (set_syscall_print_fmt(call) < 0)
 		return -ENOMEM;
@@ -438,7 +456,7 @@ int init_syscall_trace(struct ftrace_event_call *call)
 	return id;
 }
 
-unsigned long __init arch_syscall_addr(int nr)
+unsigned long __init __weak arch_syscall_addr(int nr)
 {
 	return (unsigned long)sys_call_table[nr];
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f37f974aa81b..18bb15776c57 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -363,8 +363,14 @@ static int watchdog_nmi_enable(int cpu)
 		goto out_save;
 	}
 
-	printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
-	       cpu, PTR_ERR(event));
+
+	/* vary the KERN level based on the returned errno */
+	if (PTR_ERR(event) == -EOPNOTSUPP)
+		printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+	else if (PTR_ERR(event) == -ENOENT)
+		printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu);
+	else
+		printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event));
 	return PTR_ERR(event);
 
 	/* success path */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 11869faa6819..5ca7ce9ce754 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -79,7 +79,9 @@ enum {
 	MAX_IDLE_WORKERS_RATIO	= 4,		/* 1/4 of busy can be idle */
 	IDLE_WORKER_TIMEOUT	= 300 * HZ,	/* keep idle ones for 5 mins */
 
-	MAYDAY_INITIAL_TIMEOUT	= HZ / 100,	/* call for help after 10ms */
+	MAYDAY_INITIAL_TIMEOUT  = HZ / 100 >= 2 ? HZ / 100 : 2,
+						/* call for help after 10ms
+						   (min two ticks) */
 	MAYDAY_INTERVAL		= HZ / 10,	/* and then every 100ms */
 	CREATE_COOLDOWN		= HZ,		/* time to breath after fail */
 	TRUSTEE_COOLDOWN	= HZ / 10,	/* for trustee draining */
@@ -249,10 +251,12 @@ struct workqueue_struct *system_wq __read_mostly;
 struct workqueue_struct *system_long_wq __read_mostly;
 struct workqueue_struct *system_nrt_wq __read_mostly;
 struct workqueue_struct *system_unbound_wq __read_mostly;
+struct workqueue_struct *system_freezable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_wq);
 EXPORT_SYMBOL_GPL(system_long_wq);
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
+EXPORT_SYMBOL_GPL(system_freezable_wq);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
@@ -314,6 +318,11 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
 
 static struct debug_obj_descr work_debug_descr;
 
+static void *work_debug_hint(void *addr)
+{
+	return ((struct work_struct *) addr)->func;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -385,6 +394,7 @@ static int work_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr work_debug_descr = {
 	.name		= "work_struct",
+	.debug_hint	= work_debug_hint,
 	.fixup_init	= work_fixup_init,
 	.fixup_activate	= work_fixup_activate,
 	.fixup_free	= work_fixup_free,
@@ -2047,6 +2057,15 @@ repeat:
 				move_linked_works(work, scheduled, &n);
 
 		process_scheduled_works(rescuer);
+
+		/*
+		 * Leave this gcwq.  If keep_working() is %true, notify a
+		 * regular worker; otherwise, we end up with 0 concurrency
+		 * and stalling the execution.
+		 */
+		if (keep_working(gcwq))
+			wake_up_worker(gcwq);
+
 		spin_unlock_irq(&gcwq->lock);
 	}
 
@@ -2956,7 +2975,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
 	 */
 	spin_lock(&workqueue_lock);
 
-	if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+	if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
 		for_each_cwq_cpu(cpu, wq)
 			get_cwq(cpu, wq)->max_active = 0;
 
@@ -3068,7 +3087,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 
 		spin_lock_irq(&gcwq->lock);
 
-		if (!(wq->flags & WQ_FREEZEABLE) ||
+		if (!(wq->flags & WQ_FREEZABLE) ||
 		    !(gcwq->flags & GCWQ_FREEZING))
 			get_cwq(gcwq->cpu, wq)->max_active = max_active;
 
@@ -3318,7 +3337,7 @@ static int __cpuinit trustee_thread(void *__gcwq)
 	 * want to get it over with ASAP - spam rescuers, wake up as
 	 * many idlers as necessary and create new ones till the
 	 * worklist is empty.  Note that if the gcwq is frozen, there
-	 * may be frozen works in freezeable cwqs.  Don't declare
+	 * may be frozen works in freezable cwqs.  Don't declare
 	 * completion while frozen.
 	 */
 	while (gcwq->nr_workers != gcwq->nr_idle ||
@@ -3576,9 +3595,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 /**
  * freeze_workqueues_begin - begin freezing workqueues
  *
- * Start freezing workqueues.  After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues.  After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
  *
  * CONTEXT:
  * Grabs and releases workqueue_lock and gcwq->lock's.
@@ -3604,7 +3623,7 @@ void freeze_workqueues_begin(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (cwq && wq->flags & WQ_FREEZEABLE)
+			if (cwq && wq->flags & WQ_FREEZABLE)
 				cwq->max_active = 0;
 		}
 
@@ -3615,7 +3634,7 @@ void freeze_workqueues_begin(void)
 }
 
 /**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
  *
  * Check whether freezing is complete.  This function must be called
  * between freeze_workqueues_begin() and thaw_workqueues().
@@ -3624,8 +3643,8 @@ void freeze_workqueues_begin(void)
  * Grabs and releases workqueue_lock.
  *
  * RETURNS:
- * %true if some freezeable workqueues are still busy.  %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy.  %false if freezing
+ * is complete.
  */
 bool freeze_workqueues_busy(void)
 {
@@ -3645,7 +3664,7 @@ bool freeze_workqueues_busy(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+			if (!cwq || !(wq->flags & WQ_FREEZABLE))
 				continue;
 
 			BUG_ON(cwq->nr_active < 0);
@@ -3690,7 +3709,7 @@ void thaw_workqueues(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+			if (!cwq || !(wq->flags & WQ_FREEZABLE))
 				continue;
 
 			/* restore max_active and repopulate worklist */
@@ -3764,8 +3783,10 @@ static int __init init_workqueues(void)
 	system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0);
 	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
 					    WQ_UNBOUND_MAX_ACTIVE);
+	system_freezable_wq = alloc_workqueue("events_freezable",
+					      WQ_FREEZABLE, 0);
 	BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq ||
-	       !system_unbound_wq);
+	       !system_unbound_wq || !system_freezable_wq);
 	return 0;
 }
 early_initcall(init_workqueues);