Merge branch 'linus' into tracing/hw-breakpoints

Conflicts:
	arch/x86/kernel/process_64.c

Semantic conflict fixed in:
	arch/x86/kvm/x86.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>

49 files changed, 3938 insertions, 4181 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 52508612a08f..69943fdd7a41 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -80,11 +80,9 @@ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
-obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o
 obj-$(CONFIG_TREE_RCU) += rcutree.o
-obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o
+obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
-obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -120,7 +118,7 @@ $(obj)/config_data.gz: .config FORCE
 	$(call if_changed,gzip)
 
 quiet_cmd_ikconfiggz = IKCFG   $@
-      cmd_ikconfiggz = (echo "static const char kernel_config_data[] = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@
+      cmd_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@
 targets += config_data.h
 $(obj)/config_data.h: $(obj)/config_data.gz FORCE
 	$(call if_changed,ikconfiggz)
diff --git a/kernel/acct.c b/kernel/acct.c
index 9f3391090b3e..9a4715a2f6bf 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -491,13 +491,17 @@ static void do_acct_process(struct bsd_acct_struct *acct,
 	u64 run_time;
 	struct timespec uptime;
 	struct tty_struct *tty;
+	const struct cred *orig_cred;
+
+	/* Perform file operations on behalf of whoever enabled accounting */
+	orig_cred = override_creds(file->f_cred);
 
 	/*
 	 * First check to see if there is enough free_space to continue
 	 * the process accounting system.
 	 */
 	if (!check_free_space(acct, file))
-		return;
+		goto out;
 
 	/*
 	 * Fill the accounting struct with the needed info as recorded
@@ -578,6 +582,8 @@ static void do_acct_process(struct bsd_acct_struct *acct,
 			       sizeof(acct_t), &file->f_pos);
 	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim;
 	set_fs(fs);
+out:
+	revert_creds(orig_cred);
 }
 
 /**
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b6eadfe30e7b..c7ece8f027f2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -600,6 +600,7 @@ static struct inode_operations cgroup_dir_inode_operations;
 static struct file_operations proc_cgroupstats_operations;
 
 static struct backing_dev_info cgroup_backing_dev_info = {
+	.name		= "cgroup",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
diff --git a/kernel/cred.c b/kernel/cred.c
index 1bb4d7e5d616..d7f7a01082eb 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -18,6 +18,18 @@
 #include <linux/cn_proc.h>
 #include "cred-internals.h"
 
+#if 0
+#define kdebug(FMT, ...) \
+	printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__)
+#else
+static inline __attribute__((format(printf, 1, 2)))
+void no_printk(const char *fmt, ...)
+{
+}
+#define kdebug(FMT, ...) \
+	no_printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__)
+#endif
+
 static struct kmem_cache *cred_jar;
 
 /*
@@ -36,6 +48,10 @@ static struct thread_group_cred init_tgcred = {
  */
 struct cred init_cred = {
 	.usage			= ATOMIC_INIT(4),
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	.subscribers		= ATOMIC_INIT(2),
+	.magic			= CRED_MAGIC,
+#endif
 	.securebits		= SECUREBITS_DEFAULT,
 	.cap_inheritable	= CAP_INIT_INH_SET,
 	.cap_permitted		= CAP_FULL_SET,
@@ -48,6 +64,31 @@ struct cred init_cred = {
 #endif
 };
 
+static inline void set_cred_subscribers(struct cred *cred, int n)
+{
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	atomic_set(&cred->subscribers, n);
+#endif
+}
+
+static inline int read_cred_subscribers(const struct cred *cred)
+{
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	return atomic_read(&cred->subscribers);
+#else
+	return 0;
+#endif
+}
+
+static inline void alter_cred_subscribers(const struct cred *_cred, int n)
+{
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	struct cred *cred = (struct cred *) _cred;
+
+	atomic_add(n, &cred->subscribers);
+#endif
+}
+
 /*
  * Dispose of the shared task group credentials
  */
@@ -85,15 +126,29 @@ static void put_cred_rcu(struct rcu_head *rcu)
 {
 	struct cred *cred = container_of(rcu, struct cred, rcu);
 
+	kdebug("put_cred_rcu(%p)", cred);
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	if (cred->magic != CRED_MAGIC_DEAD ||
+	    atomic_read(&cred->usage) != 0 ||
+	    read_cred_subscribers(cred) != 0)
+		panic("CRED: put_cred_rcu() sees %p with"
+		      " mag %x, put %p, usage %d, subscr %d\n",
+		      cred, cred->magic, cred->put_addr,
+		      atomic_read(&cred->usage),
+		      read_cred_subscribers(cred));
+#else
 	if (atomic_read(&cred->usage) != 0)
 		panic("CRED: put_cred_rcu() sees %p with usage %d\n",
 		      cred, atomic_read(&cred->usage));
+#endif
 
 	security_cred_free(cred);
 	key_put(cred->thread_keyring);
 	key_put(cred->request_key_auth);
 	release_tgcred(cred);
-	put_group_info(cred->group_info);
+	if (cred->group_info)
+		put_group_info(cred->group_info);
 	free_uid(cred->user);
 	kmem_cache_free(cred_jar, cred);
 }
@@ -106,12 +161,90 @@ static void put_cred_rcu(struct rcu_head *rcu)
  */
 void __put_cred(struct cred *cred)
 {
+	kdebug("__put_cred(%p{%d,%d})", cred,
+	       atomic_read(&cred->usage),
+	       read_cred_subscribers(cred));
+
 	BUG_ON(atomic_read(&cred->usage) != 0);
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	BUG_ON(read_cred_subscribers(cred) != 0);
+	cred->magic = CRED_MAGIC_DEAD;
+	cred->put_addr = __builtin_return_address(0);
+#endif
+	BUG_ON(cred == current->cred);
+	BUG_ON(cred == current->real_cred);
 
 	call_rcu(&cred->rcu, put_cred_rcu);
 }
 EXPORT_SYMBOL(__put_cred);
 
+/*
+ * Clean up a task's credentials when it exits
+ */
+void exit_creds(struct task_struct *tsk)
+{
+	struct cred *cred;
+
+	kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
+	       atomic_read(&tsk->cred->usage),
+	       read_cred_subscribers(tsk->cred));
+
+	cred = (struct cred *) tsk->real_cred;
+	tsk->real_cred = NULL;
+	validate_creds(cred);
+	alter_cred_subscribers(cred, -1);
+	put_cred(cred);
+
+	cred = (struct cred *) tsk->cred;
+	tsk->cred = NULL;
+	validate_creds(cred);
+	alter_cred_subscribers(cred, -1);
+	put_cred(cred);
+
+	cred = (struct cred *) tsk->replacement_session_keyring;
+	if (cred) {
+		tsk->replacement_session_keyring = NULL;
+		validate_creds(cred);
+		put_cred(cred);
+	}
+}
+
+/*
+ * Allocate blank credentials, such that the credentials can be filled in at a
+ * later date without risk of ENOMEM.
+ */
+struct cred *cred_alloc_blank(void)
+{
+	struct cred *new;
+
+	new = kmem_cache_zalloc(cred_jar, GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+#ifdef CONFIG_KEYS
+	new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL);
+	if (!new->tgcred) {
+		kfree(new);
+		return NULL;
+	}
+	atomic_set(&new->tgcred->usage, 1);
+#endif
+
+	atomic_set(&new->usage, 1);
+
+	if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+		goto error;
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	new->magic = CRED_MAGIC;
+#endif
+	return new;
+
+error:
+	abort_creds(new);
+	return NULL;
+}
+
 /**
  * prepare_creds - Prepare a new set of credentials for modification
  *
@@ -132,16 +265,19 @@ struct cred *prepare_creds(void)
 	const struct cred *old;
 	struct cred *new;
 
-	BUG_ON(atomic_read(&task->real_cred->usage) < 1);
+	validate_process_creds();
 
 	new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
 	if (!new)
 		return NULL;
 
+	kdebug("prepare_creds() alloc %p", new);
+
 	old = task->cred;
 	memcpy(new, old, sizeof(struct cred));
 
 	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 
@@ -157,6 +293,7 @@ struct cred *prepare_creds(void)
 
 	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
 		goto error;
+	validate_creds(new);
 	return new;
 
 error:
@@ -229,9 +366,12 @@ struct cred *prepare_usermodehelper_creds(void)
 	if (!new)
 		return NULL;
 
+	kdebug("prepare_usermodehelper_creds() alloc %p", new);
+
 	memcpy(new, &init_cred, sizeof(struct cred));
 
 	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 
@@ -250,6 +390,7 @@ struct cred *prepare_usermodehelper_creds(void)
 #endif
 	if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0)
 		goto error;
+	validate_creds(new);
 
 	BUG_ON(atomic_read(&new->usage) != 1);
 	return new;
@@ -286,6 +427,10 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	    ) {
 		p->real_cred = get_cred(p->cred);
 		get_cred(p->cred);
+		alter_cred_subscribers(p->cred, 2);
+		kdebug("share_creds(%p{%d,%d})",
+		       p->cred, atomic_read(&p->cred->usage),
+		       read_cred_subscribers(p->cred));
 		atomic_inc(&p->cred->user->processes);
 		return 0;
 	}
@@ -331,6 +476,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 
 	atomic_inc(&new->user->processes);
 	p->cred = p->real_cred = get_cred(new);
+	alter_cred_subscribers(new, 2);
+	validate_creds(new);
 	return 0;
 
 error_put:
@@ -355,13 +502,20 @@ error_put:
 int commit_creds(struct cred *new)
 {
 	struct task_struct *task = current;
-	const struct cred *old;
+	const struct cred *old = task->real_cred;
 
-	BUG_ON(task->cred != task->real_cred);
-	BUG_ON(atomic_read(&task->real_cred->usage) < 2);
+	kdebug("commit_creds(%p{%d,%d})", new,
+	       atomic_read(&new->usage),
+	       read_cred_subscribers(new));
+
+	BUG_ON(task->cred != old);
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	BUG_ON(read_cred_subscribers(old) < 2);
+	validate_creds(old);
+	validate_creds(new);
+#endif
 	BUG_ON(atomic_read(&new->usage) < 1);
 
-	old = task->real_cred;
 	security_commit_creds(new, old);
 
 	get_cred(new); /* we will require a ref for the subj creds too */
@@ -390,12 +544,14 @@ int commit_creds(struct cred *new)
 	 *   cheaply with the new uid cache, so if it matters
 	 *   we should be checking for it.  -DaveM
 	 */
+	alter_cred_subscribers(new, 2);
 	if (new->user != old->user)
 		atomic_inc(&new->user->processes);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user)
 		atomic_dec(&old->user->processes);
+	alter_cred_subscribers(old, -2);
 
 	sched_switch_user(task);
 
@@ -428,6 +584,13 @@ EXPORT_SYMBOL(commit_creds);
  */
 void abort_creds(struct cred *new)
 {
+	kdebug("abort_creds(%p{%d,%d})", new,
+	       atomic_read(&new->usage),
+	       read_cred_subscribers(new));
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	BUG_ON(read_cred_subscribers(new) != 0);
+#endif
 	BUG_ON(atomic_read(&new->usage) < 1);
 	put_cred(new);
 }
@@ -444,7 +607,20 @@ const struct cred *override_creds(const struct cred *new)
 {
 	const struct cred *old = current->cred;
 
-	rcu_assign_pointer(current->cred, get_cred(new));
+	kdebug("override_creds(%p{%d,%d})", new,
+	       atomic_read(&new->usage),
+	       read_cred_subscribers(new));
+
+	validate_creds(old);
+	validate_creds(new);
+	get_cred(new);
+	alter_cred_subscribers(new, 1);
+	rcu_assign_pointer(current->cred, new);
+	alter_cred_subscribers(old, -1);
+
+	kdebug("override_creds() = %p{%d,%d}", old,
+	       atomic_read(&old->usage),
+	       read_cred_subscribers(old));
 	return old;
 }
 EXPORT_SYMBOL(override_creds);
@@ -460,7 +636,15 @@ void revert_creds(const struct cred *old)
 {
 	const struct cred *override = current->cred;
 
+	kdebug("revert_creds(%p{%d,%d})", old,
+	       atomic_read(&old->usage),
+	       read_cred_subscribers(old));
+
+	validate_creds(old);
+	validate_creds(override);
+	alter_cred_subscribers(old, 1);
 	rcu_assign_pointer(current->cred, old);
+	alter_cred_subscribers(override, -1);
 	put_cred(override);
 }
 EXPORT_SYMBOL(revert_creds);
@@ -502,11 +686,15 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (!new)
 		return NULL;
 
+	kdebug("prepare_kernel_cred() alloc %p", new);
+
 	if (daemon)
 		old = get_task_cred(daemon);
 	else
 		old = get_cred(&init_cred);
 
+	validate_creds(old);
+
 	*new = *old;
 	get_uid(new->user);
 	get_group_info(new->group_info);
@@ -526,7 +714,9 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 		goto error;
 
 	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	put_cred(old);
+	validate_creds(new);
 	return new;
 
 error:
@@ -589,3 +779,95 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 	return security_kernel_create_files_as(new, inode);
 }
 EXPORT_SYMBOL(set_create_files_as);
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+
+/*
+ * dump invalid credentials
+ */
+static void dump_invalid_creds(const struct cred *cred, const char *label,
+			       const struct task_struct *tsk)
+{
+	printk(KERN_ERR "CRED: %s credentials: %p %s%s%s\n",
+	       label, cred,
+	       cred == &init_cred ? "[init]" : "",
+	       cred == tsk->real_cred ? "[real]" : "",
+	       cred == tsk->cred ? "[eff]" : "");
+	printk(KERN_ERR "CRED: ->magic=%x, put_addr=%p\n",
+	       cred->magic, cred->put_addr);
+	printk(KERN_ERR "CRED: ->usage=%d, subscr=%d\n",
+	       atomic_read(&cred->usage),
+	       read_cred_subscribers(cred));
+	printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n",
+	       cred->uid, cred->euid, cred->suid, cred->fsuid);
+	printk(KERN_ERR "CRED: ->*gid = { %d,%d,%d,%d }\n",
+	       cred->gid, cred->egid, cred->sgid, cred->fsgid);
+#ifdef CONFIG_SECURITY
+	printk(KERN_ERR "CRED: ->security is %p\n", cred->security);
+	if ((unsigned long) cred->security >= PAGE_SIZE &&
+	    (((unsigned long) cred->security & 0xffffff00) !=
+	     (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
+		printk(KERN_ERR "CRED: ->security {%x, %x}\n",
+		       ((u32*)cred->security)[0],
+		       ((u32*)cred->security)[1]);
+#endif
+}
+
+/*
+ * report use of invalid credentials
+ */
+void __invalid_creds(const struct cred *cred, const char *file, unsigned line)
+{
+	printk(KERN_ERR "CRED: Invalid credentials\n");
+	printk(KERN_ERR "CRED: At %s:%u\n", file, line);
+	dump_invalid_creds(cred, "Specified", current);
+	BUG();
+}
+EXPORT_SYMBOL(__invalid_creds);
+
+/*
+ * check the credentials on a process
+ */
+void __validate_process_creds(struct task_struct *tsk,
+			      const char *file, unsigned line)
+{
+	if (tsk->cred == tsk->real_cred) {
+		if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
+			     creds_are_invalid(tsk->cred)))
+			goto invalid_creds;
+	} else {
+		if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
+			     read_cred_subscribers(tsk->cred) < 1 ||
+			     creds_are_invalid(tsk->real_cred) ||
+			     creds_are_invalid(tsk->cred)))
+			goto invalid_creds;
+	}
+	return;
+
+invalid_creds:
+	printk(KERN_ERR "CRED: Invalid process credentials\n");
+	printk(KERN_ERR "CRED: At %s:%u\n", file, line);
+
+	dump_invalid_creds(tsk->real_cred, "Real", tsk);
+	if (tsk->cred != tsk->real_cred)
+		dump_invalid_creds(tsk->cred, "Effective", tsk);
+	else
+		printk(KERN_ERR "CRED: Effective creds == Real creds\n");
+	BUG();
+}
+EXPORT_SYMBOL(__validate_process_creds);
+
+/*
+ * check creds for do_exit()
+ */
+void validate_creds_for_do_exit(struct task_struct *tsk)
+{
+	kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
+	       tsk->real_cred, tsk->cred,
+	       atomic_read(&tsk->cred->usage),
+	       read_cred_subscribers(tsk->cred));
+
+	__validate_process_creds(tsk, __FILE__, __LINE__);
+}
+
+#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/exit.c b/kernel/exit.c
index 869dc221733e..ae5d8660ddff 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -901,6 +901,8 @@ NORET_TYPE void do_exit(long code)
 
 	tracehook_report_exit(&code);
 
+	validate_creds_for_do_exit(tsk);
+
 	/*
 	 * We're taking recursive faults here in do_exit. Safest is to just
 	 * leave this task alone and wait for reboot.
@@ -1009,7 +1011,10 @@ NORET_TYPE void do_exit(long code)
 	if (tsk->splice_pipe)
 		__free_pipe_info(tsk->splice_pipe);
 
+	validate_creds_for_do_exit(tsk);
+
 	preempt_disable();
+	exit_rcu();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
 	schedule();
diff --git a/kernel/fork.c b/kernel/fork.c
index e6c04d462ab2..bfee931ee3fb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -152,8 +152,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
-	put_cred(tsk->real_cred);
-	put_cred(tsk->cred);
+	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
 
 	if (!profile_handoff_task(tsk))
@@ -1008,10 +1007,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	copy_flags(clone_flags, p);
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
-#ifdef CONFIG_PREEMPT_RCU
-	p->rcu_read_lock_nesting = 0;
-	p->rcu_flipctr_idx = 0;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
+	rcu_copy_process(p);
 	p->vfork_done = NULL;
 	spin_lock_init(&p->alloc_lock);
 
@@ -1297,8 +1293,7 @@ bad_fork_cleanup_put_domain:
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
-	put_cred(p->real_cred);
-	put_cred(p->cred);
+	exit_creds(p);
 bad_fork_free:
 	free_task(p);
 fork_out:
diff --git a/kernel/futex.c b/kernel/futex.c
index e18cfbdc7190..248dd119a86e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -115,6 +115,9 @@ struct futex_q {
 	/* rt_waiter storage for requeue_pi: */
 	struct rt_mutex_waiter *rt_waiter;
 
+	/* The expected requeue pi target futex key: */
+	union futex_key *requeue_pi_key;
+
 	/* Bitset for the optional bitmasked wakeup */
 	u32 bitset;
 };
@@ -1089,6 +1092,10 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	if (!top_waiter)
 		return 0;
 
+	/* Ensure we requeue to the expected futex. */
+	if (!match_futex(top_waiter->requeue_pi_key, key2))
+		return -EINVAL;
+
 	/*
 	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
 	 * the contended case or if set_waiters is 1.  The pi_state is returned
@@ -1276,6 +1283,12 @@ retry_private:
 			continue;
 		}
 
+		/* Ensure we requeue to the expected futex for requeue_pi. */
+		if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) {
+			ret = -EINVAL;
+			break;
+		}
+
 		/*
 		 * Requeue nr_requeue waiters and possibly one more in the case
 		 * of requeue_pi if we couldn't acquire the lock atomically.
@@ -1751,6 +1764,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 	q.pi_state = NULL;
 	q.bitset = bitset;
 	q.rt_waiter = NULL;
+	q.requeue_pi_key = NULL;
 
 	if (abs_time) {
 		to = &timeout;
@@ -1858,6 +1872,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 
 	q.pi_state = NULL;
 	q.rt_waiter = NULL;
+	q.requeue_pi_key = NULL;
 retry:
 	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
@@ -2118,11 +2133,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * We call schedule in futex_wait_queue_me() when we enqueue and return there
  * via the following:
  * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
- * 2) wakeup on uaddr2 after a requeue and subsequent unlock
- * 3) signal (before or after requeue)
- * 4) timeout (before or after requeue)
+ * 2) wakeup on uaddr2 after a requeue
+ * 3) signal
+ * 4) timeout
  *
- * If 3, we setup a restart_block with futex_wait_requeue_pi() as the function.
+ * If 3, cleanup and return -ERESTARTNOINTR.
  *
  * If 2, we may then block on trying to take the rt_mutex and return via:
  * 5) successful lock
@@ -2130,7 +2145,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * 7) timeout
  * 8) other lock acquisition failure
  *
- * If 6, we setup a restart_block with futex_lock_pi() as the function.
+ * If 6, return -EWOULDBLOCK (restarting the syscall would do the same).
  *
  * If 4 or 7, we cleanup and return with -ETIMEDOUT.
  *
@@ -2169,15 +2184,16 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 	debug_rt_mutex_init_waiter(&rt_waiter);
 	rt_waiter.task = NULL;
 
-	q.pi_state = NULL;
-	q.bitset = bitset;
-	q.rt_waiter = &rt_waiter;
-
 	key2 = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
+	q.pi_state = NULL;
+	q.bitset = bitset;
+	q.rt_waiter = &rt_waiter;
+	q.requeue_pi_key = &key2;
+
 	/* Prepare to wait on uaddr. */
 	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
 	if (ret)
@@ -2248,14 +2264,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 			rt_mutex_unlock(pi_mutex);
 	} else if (ret == -EINTR) {
 		/*
-		 * We've already been requeued, but we have no way to
-		 * restart by calling futex_lock_pi() directly. We
-		 * could restart the syscall, but that will look at
-		 * the user space value and return right away. So we
-		 * drop back with EWOULDBLOCK to tell user space that
-		 * "val" has been changed. That's the same what the
-		 * restart of the syscall would do in
-		 * futex_wait_setup().
+		 * We've already been requeued, but cannot restart by calling
+		 * futex_lock_pi() directly. We could restart this syscall, but
+		 * it would detect that the user space "val" changed and return
+		 * -EWOULDBLOCK.  Save the overhead of the restart and return
+		 * -EWOULDBLOCK directly.
 		 */
 		ret = -EWOULDBLOCK;
 	}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 49da79ab8486..05071bf6a37b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -485,6 +485,7 @@ void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
 	debug_object_init_on_stack(timer, &hrtimer_debug_descr);
 	__hrtimer_init(timer, clock_id, mode);
 }
+EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);
 
 void destroy_hrtimer_on_stack(struct hrtimer *timer)
 {
@@ -1477,6 +1478,7 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 	sl->timer.function = hrtimer_wakeup;
 	sl->task = task;
 }
+EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
 {
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 13c68e71b726..c1660194d115 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -222,6 +222,34 @@ int set_irq_chip_data(unsigned int irq, void *data)
 }
 EXPORT_SYMBOL(set_irq_chip_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)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	unsigned long flags;
+
+	if (!desc)
+		return;
+
+	spin_lock_irqsave(&desc->lock, flags);
+	if (nest)
+		desc->status |= IRQ_NESTED_THREAD;
+	else
+		desc->status &= ~IRQ_NESTED_THREAD;
+	spin_unlock_irqrestore(&desc->lock, flags);
+}
+EXPORT_SYMBOL_GPL(set_irq_nested_thread);
+
 /*
  * default enable function
  */
@@ -299,6 +327,45 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
 	}
 }
 
+/*
+ *	handle_nested_irq - Handle a nested irq from a irq thread
+ *	@irq:	the interrupt number
+ *
+ *	Handle interrupts which are nested into a threaded interrupt
+ *	handler. The handler function is called inside the calling
+ *	threads context.
+ */
+void handle_nested_irq(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irqaction *action;
+	irqreturn_t action_ret;
+
+	might_sleep();
+
+	spin_lock_irq(&desc->lock);
+
+	kstat_incr_irqs_this_cpu(irq, desc);
+
+	action = desc->action;
+	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+		goto out_unlock;
+
+	desc->status |= IRQ_INPROGRESS;
+	spin_unlock_irq(&desc->lock);
+
+	action_ret = action->thread_fn(action->irq, action->dev_id);
+	if (!noirqdebug)
+		note_interrupt(irq, desc, action_ret);
+
+	spin_lock_irq(&desc->lock);
+	desc->status &= ~IRQ_INPROGRESS;
+
+out_unlock:
+	spin_unlock_irq(&desc->lock);
+}
+EXPORT_SYMBOL_GPL(handle_nested_irq);
+
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
  *	@irq:	the interrupt number
@@ -382,7 +449,10 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
-	if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
+
+	if (unlikely(desc->status & IRQ_ONESHOT))
+		desc->status |= IRQ_MASKED;
+	else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
 		desc->chip->unmask(irq);
 out_unlock:
 	spin_unlock(&desc->lock);
@@ -572,6 +642,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		desc->chip = &dummy_irq_chip;
 	}
 
+	chip_bus_lock(irq, desc);
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/* Uninstall? */
@@ -591,6 +662,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		desc->chip->startup(irq);
 	}
 	spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL_GPL(__set_irq_handler);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 065205bdd920..a81cf80554db 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -161,7 +161,7 @@ int __init early_irq_init(void)
 
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
- 	node = first_online_node;
+	node = first_online_node;
 
 	/* allocate irq_desc_ptrs array based on nr_irqs */
 	irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
@@ -172,6 +172,9 @@ int __init early_irq_init(void)
 
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
+#ifdef CONFIG_SMP
+		desc[i].node = node;
+#endif
 		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		alloc_desc_masks(&desc[i], node, true);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index e70ed5592eb9..1b5d742c6a77 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -44,6 +44,19 @@ extern int irq_select_affinity_usr(unsigned int irq);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+/* Inline functions for support of irq chips on slow busses */
+static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc)
+{
+	if (unlikely(desc->chip->bus_lock))
+		desc->chip->bus_lock(irq);
+}
+
+static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc)
+{
+	if (unlikely(desc->chip->bus_sync_unlock))
+		desc->chip->bus_sync_unlock(irq);
+}
+
 /*
  * Debugging printout:
  */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0ec9ed831737..bde4c667d24d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -230,9 +230,11 @@ void disable_irq_nosync(unsigned int irq)
 	if (!desc)
 		return;
 
+	chip_bus_lock(irq, desc);
 	spin_lock_irqsave(&desc->lock, flags);
 	__disable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -294,7 +296,8 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  *	matches the last disable, processing of interrupts on this
  *	IRQ line is re-enabled.
  *
- *	This function may be called from IRQ context.
+ *	This function may be called from IRQ context only when
+ *	desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
@@ -304,9 +307,11 @@ void enable_irq(unsigned int irq)
 	if (!desc)
 		return;
 
+	chip_bus_lock(irq, desc);
 	spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -436,6 +441,26 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	return ret;
 }
 
+/*
+ * Default primary interrupt handler for threaded interrupts. Is
+ * assigned as primary handler when request_threaded_irq is called
+ * with handler == NULL. Useful for oneshot interrupts.
+ */
+static irqreturn_t irq_default_primary_handler(int irq, void *dev_id)
+{
+	return IRQ_WAKE_THREAD;
+}
+
+/*
+ * Primary handler for nested threaded interrupts. Should never be
+ * called.
+ */
+static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
+{
+	WARN(1, "Primary handler called for nested irq %d\n", irq);
+	return IRQ_NONE;
+}
+
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
 	while (!kthread_should_stop()) {
@@ -451,6 +476,23 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 	return -1;
 }
 
+/*
+ * Oneshot interrupts keep the irq line masked until the threaded
+ * 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)
+{
+	chip_bus_lock(irq, desc);
+	spin_lock_irq(&desc->lock);
+	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
+		desc->status &= ~IRQ_MASKED;
+		desc->chip->unmask(irq);
+	}
+	spin_unlock_irq(&desc->lock);
+	chip_bus_sync_unlock(irq, desc);
+}
+
 #ifdef CONFIG_SMP
 /*
  * Check whether we need to change the affinity of the interrupt thread.
@@ -492,7 +534,7 @@ static int irq_thread(void *data)
 	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake;
+	int wake, oneshot = desc->status & IRQ_ONESHOT;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -518,6 +560,9 @@ static int irq_thread(void *data)
 			spin_unlock_irq(&desc->lock);
 
 			action->thread_fn(action->irq, action->dev_id);
+
+			if (oneshot)
+				irq_finalize_oneshot(action->irq, desc);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -565,7 +610,7 @@ __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 shared = 0;
+	int nested, shared = 0;
 	int ret;
 
 	if (!desc)
@@ -590,10 +635,32 @@ __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;
+	if (nested) {
+		if (!new->thread_fn)
+			return -EINVAL;
+		/*
+		 * Replace the primary handler which was provided from
+		 * the driver for non nested interrupt handling by the
+		 * dummy function which warns when called.
+		 */
+		new->handler = irq_nested_primary_handler;
+	}
+
 	/*
-	 * Threaded handler ?
+	 * Create a handler thread when a thread function is supplied
+	 * and the interrupt does not nest into another interrupt
+	 * thread.
 	 */
-	if (new->thread_fn) {
+	if (new->thread_fn && !nested) {
 		struct task_struct *t;
 
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
@@ -662,9 +729,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING |
+		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT |
 				  IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
 
+		if (new->flags & IRQF_ONESHOT)
+			desc->status |= IRQ_ONESHOT;
+
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
@@ -875,7 +945,14 @@ EXPORT_SYMBOL_GPL(remove_irq);
  */
 void free_irq(unsigned int irq, void *dev_id)
 {
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc)
+		return;
+
+	chip_bus_lock(irq, desc);
 	kfree(__free_irq(irq, dev_id));
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -884,6 +961,8 @@ EXPORT_SYMBOL(free_irq);
  *	@irq: Interrupt line to allocate
  *	@handler: Function to be called when the IRQ occurs.
  *		  Primary handler for threaded interrupts
+ *		  If NULL and thread_fn != NULL the default
+ *		  primary handler is installed
  *	@thread_fn: Function called from the irq handler thread
  *		    If NULL, no irq thread is created
  *	@irqflags: Interrupt type flags
@@ -963,8 +1042,12 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 
 	if (desc->status & IRQ_NOREQUEST)
 		return -EINVAL;
-	if (!handler)
-		return -EINVAL;
+
+	if (!handler) {
+		if (!thread_fn)
+			return -EINVAL;
+		handler = irq_default_primary_handler;
+	}
 
 	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
 	if (!action)
@@ -976,7 +1059,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->name = devname;
 	action->dev_id = dev_id;
 
+	chip_bus_lock(irq, desc);
 	retval = __setup_irq(irq, desc, action);
+	chip_bus_sync_unlock(irq, desc);
+
 	if (retval)
 		kfree(action);
 
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 638d8bedec14..a0bb09e79867 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -15,10 +15,10 @@
 /**
  * suspend_device_irqs - disable all currently enabled interrupt lines
  *
- * During system-wide suspend or hibernation device interrupts need to be
- * disabled at the chip level and this function is provided for this purpose.
- * It disables all interrupt lines that are enabled at the moment and sets the
- * IRQ_SUSPENDED flag for them.
+ * 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.
  */
 void suspend_device_irqs(void)
 {
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 89c7117acf2b..090c3763f3a2 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -70,8 +70,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
 		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
-		if (!desc->chip || !desc->chip->retrigger ||
-					!desc->chip->retrigger(irq)) {
+		if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 4d568294de3e..114e704760fe 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -297,7 +297,6 @@ static int __init irqfixup_setup(char *str)
 
 __setup("irqfixup", irqfixup_setup);
 module_param(irqfixup, int, 0644);
-MODULE_PARM_DESC("irqfixup", "0: No fixup, 1: irqfixup mode, 2: irqpoll mode");
 
 static int __init irqpoll_setup(char *str)
 {
diff --git a/kernel/kmod.c b/kernel/kmod.c
index a92280870e30..9fcb53a11f87 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -80,6 +80,10 @@ int __request_module(bool wait, const char *fmt, ...)
 #define MAX_KMOD_CONCURRENT 50	/* Completely arbitrary value - KAO */
 	static int kmod_loop_msg;
 
+	ret = security_kernel_module_request();
+	if (ret)
+		return ret;
+
 	va_start(args, fmt);
 	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
 	va_end(args);
@@ -466,6 +470,7 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info,
 	int retval = 0;
 
 	BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+	validate_creds(sub_info->cred);
 
 	helper_lock();
 	if (sub_info->path[0] == '\0')
diff --git a/kernel/kthread.c b/kernel/kthread.c
index eb8751aa0418..5fe709982caa 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -16,8 +16,6 @@
 #include <linux/mutex.h>
 #include <trace/events/sched.h>
 
-#define KTHREAD_NICE_LEVEL (-5)
-
 static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
@@ -145,7 +143,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 		 * The kernel thread should not inherit these properties.
 		 */
 		sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
-		set_user_nice(create.result, KTHREAD_NICE_LEVEL);
 		set_cpus_allowed_ptr(create.result, cpu_all_mask);
 	}
 	return create.result;
@@ -221,7 +218,6 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_user_nice(tsk, KTHREAD_NICE_LEVEL);
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
 	set_mems_allowed(node_possible_map);
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 8bbeef996c76..f74d2d7aa605 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -42,6 +42,7 @@
 #include <linux/hash.h>
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
+#include <linux/bitops.h>
 
 #include <asm/sections.h>
 
@@ -366,11 +367,21 @@ static int save_trace(struct stack_trace *trace)
 
 	save_stack_trace(trace);
 
+	/*
+	 * Some daft arches put -1 at the end to indicate its a full trace.
+	 *
+	 * <rant> this is buggy anyway, since it takes a whole extra entry so a
+	 * complete trace that maxes out the entries provided will be reported
+	 * as incomplete, friggin useless </rant>
+	 */
+	if (trace->entries[trace->nr_entries-1] == ULONG_MAX)
+		trace->nr_entries--;
+
 	trace->max_entries = trace->nr_entries;
 
 	nr_stack_trace_entries += trace->nr_entries;
 
-	if (nr_stack_trace_entries == MAX_STACK_TRACE_ENTRIES) {
+	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
@@ -388,20 +399,6 @@ unsigned int nr_hardirq_chains;
 unsigned int nr_softirq_chains;
 unsigned int nr_process_chains;
 unsigned int max_lockdep_depth;
-unsigned int max_recursion_depth;
-
-static unsigned int lockdep_dependency_gen_id;
-
-static bool lockdep_dependency_visit(struct lock_class *source,
-				     unsigned int depth)
-{
-	if (!depth)
-		lockdep_dependency_gen_id++;
-	if (source->dep_gen_id == lockdep_dependency_gen_id)
-		return true;
-	source->dep_gen_id = lockdep_dependency_gen_id;
-	return false;
-}
 
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
@@ -431,11 +428,8 @@ atomic_t redundant_softirqs_on;
 atomic_t redundant_softirqs_off;
 atomic_t nr_unused_locks;
 atomic_t nr_cyclic_checks;
-atomic_t nr_cyclic_check_recursions;
 atomic_t nr_find_usage_forwards_checks;
-atomic_t nr_find_usage_forwards_recursions;
 atomic_t nr_find_usage_backwards_checks;
-atomic_t nr_find_usage_backwards_recursions;
 #endif
 
 /*
@@ -551,58 +545,6 @@ static void lockdep_print_held_locks(struct task_struct *curr)
 	}
 }
 
-static void print_lock_class_header(struct lock_class *class, int depth)
-{
-	int bit;
-
-	printk("%*s->", depth, "");
-	print_lock_name(class);
-	printk(" ops: %lu", class->ops);
-	printk(" {\n");
-
-	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
-		if (class->usage_mask & (1 << bit)) {
-			int len = depth;
-
-			len += printk("%*s   %s", depth, "", usage_str[bit]);
-			len += printk(" at:\n");
-			print_stack_trace(class->usage_traces + bit, len);
-		}
-	}
-	printk("%*s }\n", depth, "");
-
-	printk("%*s ... key      at: ",depth,"");
-	print_ip_sym((unsigned long)class->key);
-}
-
-/*
- * printk all lock dependencies starting at <entry>:
- */
-static void __used
-print_lock_dependencies(struct lock_class *class, int depth)
-{
-	struct lock_list *entry;
-
-	if (lockdep_dependency_visit(class, depth))
-		return;
-
-	if (DEBUG_LOCKS_WARN_ON(depth >= 20))
-		return;
-
-	print_lock_class_header(class, depth);
-
-	list_for_each_entry(entry, &class->locks_after, entry) {
-		if (DEBUG_LOCKS_WARN_ON(!entry->class))
-			return;
-
-		print_lock_dependencies(entry->class, depth + 1);
-
-		printk("%*s ... acquired at:\n",depth,"");
-		print_stack_trace(&entry->trace, 2);
-		printk("\n");
-	}
-}
-
 static void print_kernel_version(void)
 {
 	printk("%s %.*s\n", init_utsname()->release,
@@ -898,22 +840,203 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
 }
 
 /*
+ * For good efficiency of modular, we use power of 2
+ */
+#define MAX_CIRCULAR_QUEUE_SIZE		4096UL
+#define CQ_MASK				(MAX_CIRCULAR_QUEUE_SIZE-1)
+
+/*
+ * The circular_queue and helpers is used to implement the
+ * breadth-first search(BFS)algorithem, by which we can build
+ * the shortest path from the next lock to be acquired to the
+ * previous held lock if there is a circular between them.
+ */
+struct circular_queue {
+	unsigned long element[MAX_CIRCULAR_QUEUE_SIZE];
+	unsigned int  front, rear;
+};
+
+static struct circular_queue lock_cq;
+
+unsigned int max_bfs_queue_depth;
+
+static unsigned int lockdep_dependency_gen_id;
+
+static inline void __cq_init(struct circular_queue *cq)
+{
+	cq->front = cq->rear = 0;
+	lockdep_dependency_gen_id++;
+}
+
+static inline int __cq_empty(struct circular_queue *cq)
+{
+	return (cq->front == cq->rear);
+}
+
+static inline int __cq_full(struct circular_queue *cq)
+{
+	return ((cq->rear + 1) & CQ_MASK) == cq->front;
+}
+
+static inline int __cq_enqueue(struct circular_queue *cq, unsigned long elem)
+{
+	if (__cq_full(cq))
+		return -1;
+
+	cq->element[cq->rear] = elem;
+	cq->rear = (cq->rear + 1) & CQ_MASK;
+	return 0;
+}
+
+static inline int __cq_dequeue(struct circular_queue *cq, unsigned long *elem)
+{
+	if (__cq_empty(cq))
+		return -1;
+
+	*elem = cq->element[cq->front];
+	cq->front = (cq->front + 1) & CQ_MASK;
+	return 0;
+}
+
+static inline unsigned int  __cq_get_elem_count(struct circular_queue *cq)
+{
+	return (cq->rear - cq->front) & CQ_MASK;
+}
+
+static inline void mark_lock_accessed(struct lock_list *lock,
+					struct lock_list *parent)
+{
+	unsigned long nr;
+
+	nr = lock - list_entries;
+	WARN_ON(nr >= nr_list_entries);
+	lock->parent = parent;
+	lock->class->dep_gen_id = lockdep_dependency_gen_id;
+}
+
+static inline unsigned long lock_accessed(struct lock_list *lock)
+{
+	unsigned long nr;
+
+	nr = lock - list_entries;
+	WARN_ON(nr >= nr_list_entries);
+	return lock->class->dep_gen_id == lockdep_dependency_gen_id;
+}
+
+static inline struct lock_list *get_lock_parent(struct lock_list *child)
+{
+	return child->parent;
+}
+
+static inline int get_lock_depth(struct lock_list *child)
+{
+	int depth = 0;
+	struct lock_list *parent;
+
+	while ((parent = get_lock_parent(child))) {
+		child = parent;
+		depth++;
+	}
+	return depth;
+}
+
+static int __bfs(struct lock_list *source_entry,
+		 void *data,
+		 int (*match)(struct lock_list *entry, void *data),
+		 struct lock_list **target_entry,
+		 int forward)
+{
+	struct lock_list *entry;
+	struct list_head *head;
+	struct circular_queue *cq = &lock_cq;
+	int ret = 1;
+
+	if (match(source_entry, data)) {
+		*target_entry = source_entry;
+		ret = 0;
+		goto exit;
+	}
+
+	if (forward)
+		head = &source_entry->class->locks_after;
+	else
+		head = &source_entry->class->locks_before;
+
+	if (list_empty(head))
+		goto exit;
+
+	__cq_init(cq);
+	__cq_enqueue(cq, (unsigned long)source_entry);
+
+	while (!__cq_empty(cq)) {
+		struct lock_list *lock;
+
+		__cq_dequeue(cq, (unsigned long *)&lock);
+
+		if (!lock->class) {
+			ret = -2;
+			goto exit;
+		}
+
+		if (forward)
+			head = &lock->class->locks_after;
+		else
+			head = &lock->class->locks_before;
+
+		list_for_each_entry(entry, head, entry) {
+			if (!lock_accessed(entry)) {
+				unsigned int cq_depth;
+				mark_lock_accessed(entry, lock);
+				if (match(entry, data)) {
+					*target_entry = entry;
+					ret = 0;
+					goto exit;
+				}
+
+				if (__cq_enqueue(cq, (unsigned long)entry)) {
+					ret = -1;
+					goto exit;
+				}
+				cq_depth = __cq_get_elem_count(cq);
+				if (max_bfs_queue_depth < cq_depth)
+					max_bfs_queue_depth = cq_depth;
+			}
+		}
+	}
+exit:
+	return ret;
+}
+
+static inline int __bfs_forwards(struct lock_list *src_entry,
+			void *data,
+			int (*match)(struct lock_list *entry, void *data),
+			struct lock_list **target_entry)
+{
+	return __bfs(src_entry, data, match, target_entry, 1);
+
+}
+
+static inline int __bfs_backwards(struct lock_list *src_entry,
+			void *data,
+			int (*match)(struct lock_list *entry, void *data),
+			struct lock_list **target_entry)
+{
+	return __bfs(src_entry, data, match, target_entry, 0);
+
+}
+
+/*
  * Recursive, forwards-direction lock-dependency checking, used for
  * both noncyclic checking and for hardirq-unsafe/softirq-unsafe
  * checking.
- *
- * (to keep the stackframe of the recursive functions small we
- *  use these global variables, and we also mark various helper
- *  functions as noinline.)
  */
-static struct held_lock *check_source, *check_target;
 
 /*
  * Print a dependency chain entry (this is only done when a deadlock
  * has been detected):
  */
 static noinline int
-print_circular_bug_entry(struct lock_list *target, unsigned int depth)
+print_circular_bug_entry(struct lock_list *target, int depth)
 {
 	if (debug_locks_silent)
 		return 0;
@@ -930,11 +1053,13 @@ print_circular_bug_entry(struct lock_list *target, unsigned int depth)
  * header first:
  */
 static noinline int
-print_circular_bug_header(struct lock_list *entry, unsigned int depth)
+print_circular_bug_header(struct lock_list *entry, unsigned int depth,
+			struct held_lock *check_src,
+			struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
 
-	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
+	if (debug_locks_silent)
 		return 0;
 
 	printk("\n=======================================================\n");
@@ -943,9 +1068,9 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth)
 	printk(  "-------------------------------------------------------\n");
 	printk("%s/%d is trying to acquire lock:\n",
 		curr->comm, task_pid_nr(curr));
-	print_lock(check_source);
+	print_lock(check_src);
 	printk("\nbut task is already holding lock:\n");
-	print_lock(check_target);
+	print_lock(check_tgt);
 	printk("\nwhich lock already depends on the new lock.\n\n");
 	printk("\nthe existing dependency chain (in reverse order) is:\n");
 
@@ -954,19 +1079,36 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth)
 	return 0;
 }
 
-static noinline int print_circular_bug_tail(void)
+static inline int class_equal(struct lock_list *entry, void *data)
+{
+	return entry->class == data;
+}
+
+static noinline int print_circular_bug(struct lock_list *this,
+				struct lock_list *target,
+				struct held_lock *check_src,
+				struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
-	struct lock_list this;
+	struct lock_list *parent;
+	int depth;
 
-	if (debug_locks_silent)
+	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
 		return 0;
 
-	this.class = hlock_class(check_source);
-	if (!save_trace(&this.trace))
+	if (!save_trace(&this->trace))
 		return 0;
 
-	print_circular_bug_entry(&this, 0);
+	depth = get_lock_depth(target);
+
+	print_circular_bug_header(target, depth, check_src, check_tgt);
+
+	parent = get_lock_parent(target);
+
+	while (parent) {
+		print_circular_bug_entry(parent, --depth);
+		parent = get_lock_parent(parent);
+	}
 
 	printk("\nother info that might help us debug this:\n\n");
 	lockdep_print_held_locks(curr);
@@ -977,73 +1119,69 @@ static noinline int print_circular_bug_tail(void)
 	return 0;
 }
 
-#define RECURSION_LIMIT 40
-
-static int noinline print_infinite_recursion_bug(void)
+static noinline int print_bfs_bug(int ret)
 {
 	if (!debug_locks_off_graph_unlock())
 		return 0;
 
-	WARN_ON(1);
+	WARN(1, "lockdep bfs error:%d\n", ret);
 
 	return 0;
 }
 
-unsigned long __lockdep_count_forward_deps(struct lock_class *class,
-					   unsigned int depth)
+static int noop_count(struct lock_list *entry, void *data)
 {
-	struct lock_list *entry;
-	unsigned long ret = 1;
+	(*(unsigned long *)data)++;
+	return 0;
+}
 
-	if (lockdep_dependency_visit(class, depth))
-		return 0;
+unsigned long __lockdep_count_forward_deps(struct lock_list *this)
+{
+	unsigned long  count = 0;
+	struct lock_list *uninitialized_var(target_entry);
 
-	/*
-	 * Recurse this class's dependency list:
-	 */
-	list_for_each_entry(entry, &class->locks_after, entry)
-		ret += __lockdep_count_forward_deps(entry->class, depth + 1);
+	__bfs_forwards(this, (void *)&count, noop_count, &target_entry);
 
-	return ret;
+	return count;
 }
-
 unsigned long lockdep_count_forward_deps(struct lock_class *class)
 {
 	unsigned long ret, flags;
+	struct lock_list this;
+
+	this.parent = NULL;
+	this.class = class;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&lockdep_lock);
-	ret = __lockdep_count_forward_deps(class, 0);
+	ret = __lockdep_count_forward_deps(&this);
 	__raw_spin_unlock(&lockdep_lock);
 	local_irq_restore(flags);
 
 	return ret;
 }
 
-unsigned long __lockdep_count_backward_deps(struct lock_class *class,
-					    unsigned int depth)
+unsigned long __lockdep_count_backward_deps(struct lock_list *this)
 {
-	struct lock_list *entry;
-	unsigned long ret = 1;
+	unsigned long  count = 0;
+	struct lock_list *uninitialized_var(target_entry);
 
-	if (lockdep_dependency_visit(class, depth))
-		return 0;
-	/*
-	 * Recurse this class's dependency list:
-	 */
-	list_for_each_entry(entry, &class->locks_before, entry)
-		ret += __lockdep_count_backward_deps(entry->class, depth + 1);
+	__bfs_backwards(this, (void *)&count, noop_count, &target_entry);
 
-	return ret;
+	return count;
 }
 
 unsigned long lockdep_count_backward_deps(struct lock_class *class)
 {
 	unsigned long ret, flags;
+	struct lock_list this;
+
+	this.parent = NULL;
+	this.class = class;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&lockdep_lock);
-	ret = __lockdep_count_backward_deps(class, 0);
+	ret = __lockdep_count_backward_deps(&this);
 	__raw_spin_unlock(&lockdep_lock);
 	local_irq_restore(flags);
 
@@ -1055,29 +1193,16 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
  * lead to <target>. Print an error and return 0 if it does.
  */
 static noinline int
-check_noncircular(struct lock_class *source, unsigned int depth)
+check_noncircular(struct lock_list *root, struct lock_class *target,
+		struct lock_list **target_entry)
 {
-	struct lock_list *entry;
+	int result;
 
-	if (lockdep_dependency_visit(source, depth))
-		return 1;
+	debug_atomic_inc(&nr_cyclic_checks);
 
-	debug_atomic_inc(&nr_cyclic_check_recursions);
-	if (depth > max_recursion_depth)
-		max_recursion_depth = depth;
-	if (depth >= RECURSION_LIMIT)
-		return print_infinite_recursion_bug();
-	/*
-	 * Check this lock's dependency list:
-	 */
-	list_for_each_entry(entry, &source->locks_after, entry) {
-		if (entry->class == hlock_class(check_target))
-			return print_circular_bug_header(entry, depth+1);
-		debug_atomic_inc(&nr_cyclic_checks);
-		if (!check_noncircular(entry->class, depth+1))
-			return print_circular_bug_entry(entry, depth+1);
-	}
-	return 1;
+	result = __bfs_forwards(root, target, class_equal, target_entry);
+
+	return result;
 }
 
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
@@ -1086,103 +1211,121 @@ check_noncircular(struct lock_class *source, unsigned int depth)
  * proving that two subgraphs can be connected by a new dependency
  * without creating any illegal irq-safe -> irq-unsafe lock dependency.
  */
-static enum lock_usage_bit find_usage_bit;
-static struct lock_class *forwards_match, *backwards_match;
+
+static inline int usage_match(struct lock_list *entry, void *bit)
+{
+	return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit);
+}
+
+
 
 /*
  * Find a node in the forwards-direction dependency sub-graph starting
- * at <source> that matches <find_usage_bit>.
+ * at @root->class that matches @bit.
  *
- * Return 2 if such a node exists in the subgraph, and put that node
- * into <forwards_match>.
+ * Return 0 if such a node exists in the subgraph, and put that node
+ * into *@target_entry.
  *
- * Return 1 otherwise and keep <forwards_match> unchanged.
- * Return 0 on error.
+ * Return 1 otherwise and keep *@target_entry unchanged.
+ * Return <0 on error.
  */
-static noinline int
-find_usage_forwards(struct lock_class *source, unsigned int depth)
+static int
+find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
+			struct lock_list **target_entry)
 {
-	struct lock_list *entry;
-	int ret;
-
-	if (lockdep_dependency_visit(source, depth))
-		return 1;
-
-	if (depth > max_recursion_depth)
-		max_recursion_depth = depth;
-	if (depth >= RECURSION_LIMIT)
-		return print_infinite_recursion_bug();
+	int result;
 
 	debug_atomic_inc(&nr_find_usage_forwards_checks);
-	if (source->usage_mask & (1 << find_usage_bit)) {
-		forwards_match = source;
-		return 2;
-	}
 
-	/*
-	 * Check this lock's dependency list:
-	 */
-	list_for_each_entry(entry, &source->locks_after, entry) {
-		debug_atomic_inc(&nr_find_usage_forwards_recursions);
-		ret = find_usage_forwards(entry->class, depth+1);
-		if (ret == 2 || ret == 0)
-			return ret;
-	}
-	return 1;
+	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
+
+	return result;
 }
 
 /*
  * Find a node in the backwards-direction dependency sub-graph starting
- * at <source> that matches <find_usage_bit>.
+ * at @root->class that matches @bit.
  *
- * Return 2 if such a node exists in the subgraph, and put that node
- * into <backwards_match>.
+ * Return 0 if such a node exists in the subgraph, and put that node
+ * into *@target_entry.
  *
- * Return 1 otherwise and keep <backwards_match> unchanged.
- * Return 0 on error.
+ * Return 1 otherwise and keep *@target_entry unchanged.
+ * Return <0 on error.
  */
-static noinline int
-find_usage_backwards(struct lock_class *source, unsigned int depth)
+static int
+find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
+			struct lock_list **target_entry)
 {
-	struct lock_list *entry;
-	int ret;
+	int result;
 
-	if (lockdep_dependency_visit(source, depth))
-		return 1;
+	debug_atomic_inc(&nr_find_usage_backwards_checks);
 
-	if (!__raw_spin_is_locked(&lockdep_lock))
-		return DEBUG_LOCKS_WARN_ON(1);
+	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
 
-	if (depth > max_recursion_depth)
-		max_recursion_depth = depth;
-	if (depth >= RECURSION_LIMIT)
-		return print_infinite_recursion_bug();
+	return result;
+}
 
-	debug_atomic_inc(&nr_find_usage_backwards_checks);
-	if (source->usage_mask & (1 << find_usage_bit)) {
-		backwards_match = source;
-		return 2;
-	}
+static void print_lock_class_header(struct lock_class *class, int depth)
+{
+	int bit;
 
-	if (!source && debug_locks_off_graph_unlock()) {
-		WARN_ON(1);
-		return 0;
-	}
+	printk("%*s->", depth, "");
+	print_lock_name(class);
+	printk(" ops: %lu", class->ops);
+	printk(" {\n");
 
-	/*
-	 * Check this lock's dependency list:
-	 */
-	list_for_each_entry(entry, &source->locks_before, entry) {
-		debug_atomic_inc(&nr_find_usage_backwards_recursions);
-		ret = find_usage_backwards(entry->class, depth+1);
-		if (ret == 2 || ret == 0)
-			return ret;
+	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
+		if (class->usage_mask & (1 << bit)) {
+			int len = depth;
+
+			len += printk("%*s   %s", depth, "", usage_str[bit]);
+			len += printk(" at:\n");
+			print_stack_trace(class->usage_traces + bit, len);
+		}
 	}
-	return 1;
+	printk("%*s }\n", depth, "");
+
+	printk("%*s ... key      at: ",depth,"");
+	print_ip_sym((unsigned long)class->key);
+}
+
+/*
+ * printk the shortest lock dependencies from @start to @end in reverse order:
+ */
+static void __used
+print_shortest_lock_dependencies(struct lock_list *leaf,
+				struct lock_list *root)
+{
+	struct lock_list *entry = leaf;
+	int depth;
+
+	/*compute depth from generated tree by BFS*/
+	depth = get_lock_depth(leaf);
+
+	do {
+		print_lock_class_header(entry->class, depth);
+		printk("%*s ... acquired at:\n", depth, "");
+		print_stack_trace(&entry->trace, 2);
+		printk("\n");
+
+		if (depth == 0 && (entry != root)) {
+			printk("lockdep:%s bad BFS generated tree\n", __func__);
+			break;
+		}
+
+		entry = get_lock_parent(entry);
+		depth--;
+	} while (entry && (depth >= 0));
+
+	return;
 }
 
 static int
 print_bad_irq_dependency(struct task_struct *curr,
+			 struct lock_list *prev_root,
+			 struct lock_list *next_root,
+			 struct lock_list *backwards_entry,
+			 struct lock_list *forwards_entry,
 			 struct held_lock *prev,
 			 struct held_lock *next,
 			 enum lock_usage_bit bit1,
@@ -1215,26 +1358,32 @@ print_bad_irq_dependency(struct task_struct *curr,
 
 	printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
 		irqclass);
-	print_lock_name(backwards_match);
+	print_lock_name(backwards_entry->class);
 	printk("\n... which became %s-irq-safe at:\n", irqclass);
 
-	print_stack_trace(backwards_match->usage_traces + bit1, 1);
+	print_stack_trace(backwards_entry->class->usage_traces + bit1, 1);
 
 	printk("\nto a %s-irq-unsafe lock:\n", irqclass);
-	print_lock_name(forwards_match);
+	print_lock_name(forwards_entry->class);
 	printk("\n... which became %s-irq-unsafe at:\n", irqclass);
 	printk("...");
 
-	print_stack_trace(forwards_match->usage_traces + bit2, 1);
+	print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
 
 	printk("\nother info that might help us debug this:\n\n");
 	lockdep_print_held_locks(curr);
 
-	printk("\nthe %s-irq-safe lock's dependencies:\n", irqclass);
-	print_lock_dependencies(backwards_match, 0);
+	printk("\nthe dependencies between %s-irq-safe lock", irqclass);
+	printk(" and the holding lock:\n");
+	if (!save_trace(&prev_root->trace))
+		return 0;
+	print_shortest_lock_dependencies(backwards_entry, prev_root);
 
-	printk("\nthe %s-irq-unsafe lock's dependencies:\n", irqclass);
-	print_lock_dependencies(forwards_match, 0);
+	printk("\nthe dependencies between the lock to be acquired");
+	printk(" and %s-irq-unsafe lock:\n", irqclass);
+	if (!save_trace(&next_root->trace))
+		return 0;
+	print_shortest_lock_dependencies(forwards_entry, next_root);
 
 	printk("\nstack backtrace:\n");
 	dump_stack();
@@ -1248,19 +1397,30 @@ check_usage(struct task_struct *curr, struct held_lock *prev,
 	    enum lock_usage_bit bit_forwards, const char *irqclass)
 {
 	int ret;
+	struct lock_list this, that;
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *uninitialized_var(target_entry1);
 
-	find_usage_bit = bit_backwards;
-	/* fills in <backwards_match> */
-	ret = find_usage_backwards(hlock_class(prev), 0);
-	if (!ret || ret == 1)
+	this.parent = NULL;
+
+	this.class = hlock_class(prev);
+	ret = find_usage_backwards(&this, bit_backwards, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
 
-	find_usage_bit = bit_forwards;
-	ret = find_usage_forwards(hlock_class(next), 0);
-	if (!ret || ret == 1)
+	that.parent = NULL;
+	that.class = hlock_class(next);
+	ret = find_usage_forwards(&that, bit_forwards, &target_entry1);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
-	/* ret == 2 */
-	return print_bad_irq_dependency(curr, prev, next,
+
+	return print_bad_irq_dependency(curr, &this, &that,
+			target_entry, target_entry1,
+			prev, next,
 			bit_backwards, bit_forwards, irqclass);
 }
 
@@ -1472,6 +1632,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 {
 	struct lock_list *entry;
 	int ret;
+	struct lock_list this;
+	struct lock_list *uninitialized_var(target_entry);
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1482,10 +1644,13 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * We are using global variables to control the recursion, to
 	 * keep the stackframe size of the recursive functions low:
 	 */
-	check_source = next;
-	check_target = prev;
-	if (!(check_noncircular(hlock_class(next), 0)))
-		return print_circular_bug_tail();
+	this.class = hlock_class(next);
+	this.parent = NULL;
+	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
+	if (unlikely(!ret))
+		return print_circular_bug(&this, target_entry, next, prev);
+	else if (unlikely(ret < 0))
+		return print_bfs_bug(ret);
 
 	if (!check_prev_add_irq(curr, prev, next))
 		return 0;
@@ -1884,7 +2049,8 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
  * print irq inversion bug:
  */
 static int
-print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
+print_irq_inversion_bug(struct task_struct *curr,
+			struct lock_list *root, struct lock_list *other,
 			struct held_lock *this, int forwards,
 			const char *irqclass)
 {
@@ -1902,17 +2068,16 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
 		printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass);
 	else
 		printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass);
-	print_lock_name(other);
+	print_lock_name(other->class);
 	printk("\n\nand interrupts could create inverse lock ordering between them.\n\n");
 
 	printk("\nother info that might help us debug this:\n");
 	lockdep_print_held_locks(curr);
 
-	printk("\nthe first lock's dependencies:\n");
-	print_lock_dependencies(hlock_class(this), 0);
-
-	printk("\nthe second lock's dependencies:\n");
-	print_lock_dependencies(other, 0);
+	printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n");
+	if (!save_trace(&root->trace))
+		return 0;
+	print_shortest_lock_dependencies(other, root);
 
 	printk("\nstack backtrace:\n");
 	dump_stack();
@@ -1929,14 +2094,19 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 		     enum lock_usage_bit bit, const char *irqclass)
 {
 	int ret;
-
-	find_usage_bit = bit;
-	/* fills in <forwards_match> */
-	ret = find_usage_forwards(hlock_class(this), 0);
-	if (!ret || ret == 1)
+	struct lock_list root;
+	struct lock_list *uninitialized_var(target_entry);
+
+	root.parent = NULL;
+	root.class = hlock_class(this);
+	ret = find_usage_forwards(&root, bit, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, forwards_match, this, 1, irqclass);
+	return print_irq_inversion_bug(curr, &root, target_entry,
+					this, 1, irqclass);
 }
 
 /*
@@ -1948,14 +2118,19 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 		      enum lock_usage_bit bit, const char *irqclass)
 {
 	int ret;
-
-	find_usage_bit = bit;
-	/* fills in <backwards_match> */
-	ret = find_usage_backwards(hlock_class(this), 0);
-	if (!ret || ret == 1)
+	struct lock_list root;
+	struct lock_list *uninitialized_var(target_entry);
+
+	root.parent = NULL;
+	root.class = hlock_class(this);
+	ret = find_usage_backwards(&root, bit, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, backwards_match, this, 0, irqclass);
+	return print_irq_inversion_bug(curr, &root, target_entry,
+					this, 1, irqclass);
 }
 
 void print_irqtrace_events(struct task_struct *curr)
@@ -2530,13 +2705,15 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
  */
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			  int trylock, int read, int check, int hardirqs_off,
-			  struct lockdep_map *nest_lock, unsigned long ip)
+			  struct lockdep_map *nest_lock, unsigned long ip,
+			  int references)
 {
 	struct task_struct *curr = current;
 	struct lock_class *class = NULL;
 	struct held_lock *hlock;
 	unsigned int depth, id;
 	int chain_head = 0;
+	int class_idx;
 	u64 chain_key;
 
 	if (!prove_locking)
@@ -2584,10 +2761,24 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH))
 		return 0;
 
+	class_idx = class - lock_classes + 1;
+
+	if (depth) {
+		hlock = curr->held_locks + depth - 1;
+		if (hlock->class_idx == class_idx && nest_lock) {
+			if (hlock->references)
+				hlock->references++;
+			else
+				hlock->references = 2;
+
+			return 1;
+		}
+	}
+
 	hlock = curr->held_locks + depth;
 	if (DEBUG_LOCKS_WARN_ON(!class))
 		return 0;
-	hlock->class_idx = class - lock_classes + 1;
+	hlock->class_idx = class_idx;
 	hlock->acquire_ip = ip;
 	hlock->instance = lock;
 	hlock->nest_lock = nest_lock;
@@ -2595,6 +2786,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->read = read;
 	hlock->check = check;
 	hlock->hardirqs_off = !!hardirqs_off;
+	hlock->references = references;
 #ifdef CONFIG_LOCK_STAT
 	hlock->waittime_stamp = 0;
 	hlock->holdtime_stamp = sched_clock();
@@ -2703,6 +2895,30 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
 	return 1;
 }
 
+static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
+{
+	if (hlock->instance == lock)
+		return 1;
+
+	if (hlock->references) {
+		struct lock_class *class = lock->class_cache;
+
+		if (!class)
+			class = look_up_lock_class(lock, 0);
+
+		if (DEBUG_LOCKS_WARN_ON(!class))
+			return 0;
+
+		if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock))
+			return 0;
+
+		if (hlock->class_idx == class - lock_classes + 1)
+			return 1;
+	}
+
+	return 0;
+}
+
 static int
 __lock_set_class(struct lockdep_map *lock, const char *name,
 		 struct lock_class_key *key, unsigned int subclass,
@@ -2726,7 +2942,7 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
@@ -2745,7 +2961,8 @@ found_it:
 		if (!__lock_acquire(hlock->instance,
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
-				hlock->nest_lock, hlock->acquire_ip))
+				hlock->nest_lock, hlock->acquire_ip,
+				hlock->references))
 			return 0;
 	}
 
@@ -2784,20 +3001,34 @@ lock_release_non_nested(struct task_struct *curr,
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
 	return print_unlock_inbalance_bug(curr, lock, ip);
 
 found_it:
-	lock_release_holdtime(hlock);
+	if (hlock->instance == lock)
+		lock_release_holdtime(hlock);
+
+	if (hlock->references) {
+		hlock->references--;
+		if (hlock->references) {
+			/*
+			 * We had, and after removing one, still have
+			 * references, the current lock stack is still
+			 * valid. We're done!
+			 */
+			return 1;
+		}
+	}
 
 	/*
 	 * We have the right lock to unlock, 'hlock' points to it.
 	 * Now we remove it from the stack, and add back the other
 	 * entries (if any), recalculating the hash along the way:
 	 */
+
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
@@ -2806,7 +3037,8 @@ found_it:
 		if (!__lock_acquire(hlock->instance,
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
-				hlock->nest_lock, hlock->acquire_ip))
+				hlock->nest_lock, hlock->acquire_ip,
+				hlock->references))
 			return 0;
 	}
 
@@ -2836,7 +3068,7 @@ static int lock_release_nested(struct task_struct *curr,
 	/*
 	 * Is the unlock non-nested:
 	 */
-	if (hlock->instance != lock)
+	if (hlock->instance != lock || hlock->references)
 		return lock_release_non_nested(curr, lock, ip);
 	curr->lockdep_depth--;
 
@@ -2881,6 +3113,21 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 	check_chain_key(curr);
 }
 
+static int __lock_is_held(struct lockdep_map *lock)
+{
+	struct task_struct *curr = current;
+	int i;
+
+	for (i = 0; i < curr->lockdep_depth; i++) {
+		struct held_lock *hlock = curr->held_locks + i;
+
+		if (match_held_lock(hlock, lock))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * Check whether we follow the irq-flags state precisely:
  */
@@ -2957,7 +3204,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 	current->lockdep_recursion = 1;
 	__lock_acquire(lock, subclass, trylock, read, check,
-		       irqs_disabled_flags(flags), nest_lock, ip);
+		       irqs_disabled_flags(flags), nest_lock, ip, 0);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
@@ -2982,6 +3229,26 @@ void lock_release(struct lockdep_map *lock, int nested,
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
+int lock_is_held(struct lockdep_map *lock)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	if (unlikely(current->lockdep_recursion))
+		return ret;
+
+	raw_local_irq_save(flags);
+	check_flags(flags);
+
+	current->lockdep_recursion = 1;
+	ret = __lock_is_held(lock);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lock_is_held);
+
 void lockdep_set_current_reclaim_state(gfp_t gfp_mask)
 {
 	current->lockdep_reclaim_gfp = gfp_mask;
@@ -3041,7 +3308,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
@@ -3049,6 +3316,9 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	return;
 
 found_it:
+	if (hlock->instance != lock)
+		return;
+
 	hlock->waittime_stamp = sched_clock();
 
 	contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
@@ -3088,7 +3358,7 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
@@ -3096,6 +3366,9 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 	return;
 
 found_it:
+	if (hlock->instance != lock)
+		return;
+
 	cpu = smp_processor_id();
 	if (hlock->waittime_stamp) {
 		now = sched_clock();
@@ -3326,7 +3599,12 @@ void __init lockdep_info(void)
 		sizeof(struct list_head) * CLASSHASH_SIZE +
 		sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES +
 		sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS +
-		sizeof(struct list_head) * CHAINHASH_SIZE) / 1024);
+		sizeof(struct list_head) * CHAINHASH_SIZE
+#ifdef CONFIG_PROVE_LOCKING
+		+ sizeof(struct circular_queue)
+#endif
+		) / 1024
+		);
 
 	printk(" per task-struct memory footprint: %lu bytes\n",
 		sizeof(struct held_lock) * MAX_LOCK_DEPTH);
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index 699a2ac3a0d7..a2ee95ad1313 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -91,6 +91,8 @@ extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
 extern unsigned int max_recursion_depth;
 
+extern unsigned int max_bfs_queue_depth;
+
 #ifdef CONFIG_PROVE_LOCKING
 extern unsigned long lockdep_count_forward_deps(struct lock_class *);
 extern unsigned long lockdep_count_backward_deps(struct lock_class *);
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index e94caa666dba..d4b3dbc79fdb 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -25,38 +25,12 @@
 
 static void *l_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct lock_class *class;
-
-	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		class = m->private;
-	else {
-		class = v;
-
-		if (class->lock_entry.next != &all_lock_classes)
-			class = list_entry(class->lock_entry.next,
-					   struct lock_class, lock_entry);
-		else
-			class = NULL;
-	}
-
-	return class;
+	return seq_list_next(v, &all_lock_classes, pos);
 }
 
 static void *l_start(struct seq_file *m, loff_t *pos)
 {
-	struct lock_class *class;
-	loff_t i = 0;
-
-	if (*pos == 0)
-		return SEQ_START_TOKEN;
-
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
-		if (++i == *pos)
-		return class;
-	}
-	return NULL;
+	return seq_list_start_head(&all_lock_classes, *pos);
 }
 
 static void l_stop(struct seq_file *m, void *v)
@@ -82,11 +56,11 @@ static void print_name(struct seq_file *m, struct lock_class *class)
 
 static int l_show(struct seq_file *m, void *v)
 {
-	struct lock_class *class = v;
+	struct lock_class *class = list_entry(v, struct lock_class, lock_entry);
 	struct lock_list *entry;
 	char usage[LOCK_USAGE_CHARS];
 
-	if (v == SEQ_START_TOKEN) {
+	if (v == &all_lock_classes) {
 		seq_printf(m, "all lock classes:\n");
 		return 0;
 	}
@@ -128,17 +102,7 @@ static const struct seq_operations lockdep_ops = {
 
 static int lockdep_open(struct inode *inode, struct file *file)
 {
-	int res = seq_open(file, &lockdep_ops);
-	if (!res) {
-		struct seq_file *m = file->private_data;
-
-		if (!list_empty(&all_lock_classes))
-			m->private = list_entry(all_lock_classes.next,
-					struct lock_class, lock_entry);
-		else
-			m->private = NULL;
-	}
-	return res;
+	return seq_open(file, &lockdep_ops);
 }
 
 static const struct file_operations proc_lockdep_operations = {
@@ -149,37 +113,23 @@ static const struct file_operations proc_lockdep_operations = {
 };
 
 #ifdef CONFIG_PROVE_LOCKING
-static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	struct lock_chain *chain;
-
-	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		chain = m->private;
-	else {
-		chain = v;
-
-		if (*pos < nr_lock_chains)
-			chain = lock_chains + *pos;
-		else
-			chain = NULL;
-	}
-
-	return chain;
-}
-
 static void *lc_start(struct seq_file *m, loff_t *pos)
 {
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	if (*pos < nr_lock_chains)
-		return lock_chains + *pos;
+	if (*pos - 1 < nr_lock_chains)
+		return lock_chains + (*pos - 1);
 
 	return NULL;
 }
 
+static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return lc_start(m, pos);
+}
+
 static void lc_stop(struct seq_file *m, void *v)
 {
 }
@@ -220,16 +170,7 @@ static const struct seq_operations lockdep_chains_ops = {
 
 static int lockdep_chains_open(struct inode *inode, struct file *file)
 {
-	int res = seq_open(file, &lockdep_chains_ops);
-	if (!res) {
-		struct seq_file *m = file->private_data;
-
-		if (nr_lock_chains)
-			m->private = lock_chains;
-		else
-			m->private = NULL;
-	}
-	return res;
+	return seq_open(file, &lockdep_chains_ops);
 }
 
 static const struct file_operations proc_lockdep_chains_operations = {
@@ -258,16 +199,10 @@ static void lockdep_stats_debug_show(struct seq_file *m)
 		debug_atomic_read(&chain_lookup_hits));
 	seq_printf(m, " cyclic checks:                 %11u\n",
 		debug_atomic_read(&nr_cyclic_checks));
-	seq_printf(m, " cyclic-check recursions:       %11u\n",
-		debug_atomic_read(&nr_cyclic_check_recursions));
 	seq_printf(m, " find-mask forwards checks:     %11u\n",
 		debug_atomic_read(&nr_find_usage_forwards_checks));
-	seq_printf(m, " find-mask forwards recursions: %11u\n",
-		debug_atomic_read(&nr_find_usage_forwards_recursions));
 	seq_printf(m, " find-mask backwards checks:    %11u\n",
 		debug_atomic_read(&nr_find_usage_backwards_checks));
-	seq_printf(m, " find-mask backwards recursions:%11u\n",
-		debug_atomic_read(&nr_find_usage_backwards_recursions));
 
 	seq_printf(m, " hardirq on events:             %11u\n", hi1);
 	seq_printf(m, " hardirq off events:            %11u\n", hi2);
@@ -409,8 +344,10 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 			nr_unused);
 	seq_printf(m, " max locking depth:             %11u\n",
 			max_lockdep_depth);
-	seq_printf(m, " max recursion depth:           %11u\n",
-			max_recursion_depth);
+#ifdef CONFIG_PROVE_LOCKING
+	seq_printf(m, " max bfs queue depth:           %11u\n",
+			max_bfs_queue_depth);
+#endif
 	lockdep_stats_debug_show(m);
 	seq_printf(m, " debug_locks:                   %11u\n",
 			debug_locks);
@@ -438,7 +375,6 @@ struct lock_stat_data {
 };
 
 struct lock_stat_seq {
-	struct lock_stat_data *iter;
 	struct lock_stat_data *iter_end;
 	struct lock_stat_data stats[MAX_LOCKDEP_KEYS];
 };
@@ -626,34 +562,22 @@ static void seq_header(struct seq_file *m)
 static void *ls_start(struct seq_file *m, loff_t *pos)
 {
 	struct lock_stat_seq *data = m->private;
+	struct lock_stat_data *iter;
 
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	data->iter = data->stats + *pos;
-	if (data->iter >= data->iter_end)
-		data->iter = NULL;
+	iter = data->stats + (*pos - 1);
+	if (iter >= data->iter_end)
+		iter = NULL;
 
-	return data->iter;
+	return iter;
 }
 
 static void *ls_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct lock_stat_seq *data = m->private;
-
 	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		data->iter = data->stats;
-	else {
-		data->iter = v;
-		data->iter++;
-	}
-
-	if (data->iter == data->iter_end)
-		data->iter = NULL;
-
-	return data->iter;
+	return ls_start(m, pos);
 }
 
 static void ls_stop(struct seq_file *m, void *v)
@@ -691,7 +615,6 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 		struct lock_stat_data *iter = data->stats;
 		struct seq_file *m = file->private_data;
 
-		data->iter = iter;
 		list_for_each_entry(class, &all_lock_classes, lock_entry) {
 			iter->class = class;
 			iter->stats = lock_stats(class);
@@ -699,7 +622,7 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 		}
 		data->iter_end = iter;
 
-		sort(data->stats, data->iter_end - data->iter,
+		sort(data->stats, data->iter_end - data->stats,
 				sizeof(struct lock_stat_data),
 				lock_stat_cmp, NULL);
 
@@ -734,7 +657,6 @@ static int lock_stat_release(struct inode *inode, struct file *file)
 	struct seq_file *seq = file->private_data;
 
 	vfree(seq->private);
-	seq->private = NULL;
 	return seq_release(inode, file);
 }
 
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index d7cbc579fc80..e0d91fdf0c3c 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -46,12 +46,18 @@ static atomic_t nr_task_counters __read_mostly;
 
 /*
  * perf counter paranoia level:
- *  0 - not paranoid
- *  1 - disallow cpu counters to unpriv
- *  2 - disallow kernel profiling to unpriv
+ *  -1 - not paranoid at all
+ *   0 - disallow raw tracepoint access for unpriv
+ *   1 - disallow cpu counters for unpriv
+ *   2 - disallow kernel profiling for unpriv
  */
 int sysctl_perf_counter_paranoid __read_mostly = 1;
 
+static inline bool perf_paranoid_tracepoint_raw(void)
+{
+	return sysctl_perf_counter_paranoid > -1;
+}
+
 static inline bool perf_paranoid_cpu(void)
 {
 	return sysctl_perf_counter_paranoid > 0;
@@ -469,7 +475,8 @@ static void update_counter_times(struct perf_counter *counter)
 	struct perf_counter_context *ctx = counter->ctx;
 	u64 run_end;
 
-	if (counter->state < PERF_COUNTER_STATE_INACTIVE)
+	if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
+	    counter->group_leader->state < PERF_COUNTER_STATE_INACTIVE)
 		return;
 
 	counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
@@ -518,7 +525,7 @@ static void __perf_counter_disable(void *info)
 	 */
 	if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
 		update_context_time(ctx);
-		update_counter_times(counter);
+		update_group_times(counter);
 		if (counter == counter->group_leader)
 			group_sched_out(counter, cpuctx, ctx);
 		else
@@ -573,7 +580,7 @@ static void perf_counter_disable(struct perf_counter *counter)
 	 * in, so we can change the state safely.
 	 */
 	if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
-		update_counter_times(counter);
+		update_group_times(counter);
 		counter->state = PERF_COUNTER_STATE_OFF;
 	}
 
@@ -851,6 +858,27 @@ retry:
 }
 
 /*
+ * Put a counter into inactive state and update time fields.
+ * Enabling the leader of a group effectively enables all
+ * the group members that aren't explicitly disabled, so we
+ * have to update their ->tstamp_enabled also.
+ * Note: this works for group members as well as group leaders
+ * since the non-leader members' sibling_lists will be empty.
+ */
+static void __perf_counter_mark_enabled(struct perf_counter *counter,
+					struct perf_counter_context *ctx)
+{
+	struct perf_counter *sub;
+
+	counter->state = PERF_COUNTER_STATE_INACTIVE;
+	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+	list_for_each_entry(sub, &counter->sibling_list, list_entry)
+		if (sub->state >= PERF_COUNTER_STATE_INACTIVE)
+			sub->tstamp_enabled =
+				ctx->time - sub->total_time_enabled;
+}
+
+/*
  * Cross CPU call to enable a performance counter
  */
 static void __perf_counter_enable(void *info)
@@ -877,8 +905,7 @@ static void __perf_counter_enable(void *info)
 
 	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
 		goto unlock;
-	counter->state = PERF_COUNTER_STATE_INACTIVE;
-	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+	__perf_counter_mark_enabled(counter, ctx);
 
 	/*
 	 * If the counter is in a group and isn't the group leader,
@@ -971,11 +998,9 @@ static void perf_counter_enable(struct perf_counter *counter)
 	 * Since we have the lock this context can't be scheduled
 	 * in, so we can change the state safely.
 	 */
-	if (counter->state == PERF_COUNTER_STATE_OFF) {
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
-	}
+	if (counter->state == PERF_COUNTER_STATE_OFF)
+		__perf_counter_mark_enabled(counter, ctx);
+
  out:
 	spin_unlock_irq(&ctx->lock);
 }
@@ -1479,9 +1504,7 @@ static void perf_counter_enable_on_exec(struct task_struct *task)
 		counter->attr.enable_on_exec = 0;
 		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
 			continue;
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
+		__perf_counter_mark_enabled(counter, ctx);
 		enabled = 1;
 	}
 
@@ -1675,6 +1698,11 @@ static void free_counter(struct perf_counter *counter)
 			atomic_dec(&nr_task_counters);
 	}
 
+	if (counter->output) {
+		fput(counter->output->filp);
+		counter->output = NULL;
+	}
+
 	if (counter->destroy)
 		counter->destroy(counter);
 
@@ -1960,6 +1988,8 @@ unlock:
 	return ret;
 }
 
+int perf_counter_set_output(struct perf_counter *counter, int output_fd);
+
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct perf_counter *counter = file->private_data;
@@ -1983,6 +2013,9 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case PERF_COUNTER_IOC_PERIOD:
 		return perf_counter_period(counter, (u64 __user *)arg);
 
+	case PERF_COUNTER_IOC_SET_OUTPUT:
+		return perf_counter_set_output(counter, arg);
+
 	default:
 		return -ENOTTY;
 	}
@@ -2253,6 +2286,11 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	WARN_ON_ONCE(counter->ctx->parent_ctx);
 	mutex_lock(&counter->mmap_mutex);
+	if (counter->output) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	if (atomic_inc_not_zero(&counter->mmap_count)) {
 		if (nr_pages != counter->data->nr_pages)
 			ret = -EINVAL;
@@ -2638,6 +2676,7 @@ static int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_counter *counter, unsigned int size,
 			     int nmi, int sample)
 {
+	struct perf_counter *output_counter;
 	struct perf_mmap_data *data;
 	unsigned int offset, head;
 	int have_lost;
@@ -2647,13 +2686,17 @@ static int perf_output_begin(struct perf_output_handle *handle,
 		u64			 lost;
 	} lost_event;
 
+	rcu_read_lock();
 	/*
 	 * For inherited counters we send all the output towards the parent.
 	 */
 	if (counter->parent)
 		counter = counter->parent;
 
-	rcu_read_lock();
+	output_counter = rcu_dereference(counter->output);
+	if (output_counter)
+		counter = output_counter;
+
 	data = rcu_dereference(counter->data);
 	if (!data)
 		goto out;
@@ -3934,6 +3977,7 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 	 * have these.
 	 */
 	if ((counter->attr.sample_type & PERF_SAMPLE_RAW) &&
+			perf_paranoid_tracepoint_raw() &&
 			!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
@@ -4202,6 +4246,57 @@ err_size:
 	goto out;
 }
 
+int perf_counter_set_output(struct perf_counter *counter, int output_fd)
+{
+	struct perf_counter *output_counter = NULL;
+	struct file *output_file = NULL;
+	struct perf_counter *old_output;
+	int fput_needed = 0;
+	int ret = -EINVAL;
+
+	if (!output_fd)
+		goto set;
+
+	output_file = fget_light(output_fd, &fput_needed);
+	if (!output_file)
+		return -EBADF;
+
+	if (output_file->f_op != &perf_fops)
+		goto out;
+
+	output_counter = output_file->private_data;
+
+	/* Don't chain output fds */
+	if (output_counter->output)
+		goto out;
+
+	/* Don't set an output fd when we already have an output channel */
+	if (counter->data)
+		goto out;
+
+	atomic_long_inc(&output_file->f_count);
+
+set:
+	mutex_lock(&counter->mmap_mutex);
+	old_output = counter->output;
+	rcu_assign_pointer(counter->output, output_counter);
+	mutex_unlock(&counter->mmap_mutex);
+
+	if (old_output) {
+		/*
+		 * we need to make sure no existing perf_output_*()
+		 * is still referencing this counter.
+		 */
+		synchronize_rcu();
+		fput(old_output->filp);
+	}
+
+	ret = 0;
+out:
+	fput_light(output_file, fput_needed);
+	return ret;
+}
+
 /**
  * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
  *
@@ -4221,15 +4316,15 @@ SYSCALL_DEFINE5(perf_counter_open,
 	struct file *group_file = NULL;
 	int fput_needed = 0;
 	int fput_needed2 = 0;
-	int ret;
+	int err;
 
 	/* for future expandability... */
-	if (flags)
+	if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
 		return -EINVAL;
 
-	ret = perf_copy_attr(attr_uptr, &attr);
-	if (ret)
-		return ret;
+	err = perf_copy_attr(attr_uptr, &attr);
+	if (err)
+		return err;
 
 	if (!attr.exclude_kernel) {
 		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
@@ -4252,8 +4347,8 @@ SYSCALL_DEFINE5(perf_counter_open,
 	 * Look up the group leader (we will attach this counter to it):
 	 */
 	group_leader = NULL;
-	if (group_fd != -1) {
-		ret = -EINVAL;
+	if (group_fd != -1 && !(flags & PERF_FLAG_FD_NO_GROUP)) {
+		err = -EINVAL;
 		group_file = fget_light(group_fd, &fput_needed);
 		if (!group_file)
 			goto err_put_context;
@@ -4282,18 +4377,24 @@ SYSCALL_DEFINE5(perf_counter_open,
 
 	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
 				     NULL, GFP_KERNEL);
-	ret = PTR_ERR(counter);
+	err = PTR_ERR(counter);
 	if (IS_ERR(counter))
 		goto err_put_context;
 
-	ret = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
-	if (ret < 0)
+	err = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
+	if (err < 0)
 		goto err_free_put_context;
 
-	counter_file = fget_light(ret, &fput_needed2);
+	counter_file = fget_light(err, &fput_needed2);
 	if (!counter_file)
 		goto err_free_put_context;
 
+	if (flags & PERF_FLAG_FD_OUTPUT) {
+		err = perf_counter_set_output(counter, group_fd);
+		if (err)
+			goto err_fput_free_put_context;
+	}
+
 	counter->filp = counter_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
@@ -4307,20 +4408,20 @@ SYSCALL_DEFINE5(perf_counter_open,
 	list_add_tail(&counter->owner_entry, &current->perf_counter_list);
 	mutex_unlock(&current->perf_counter_mutex);
 
+err_fput_free_put_context:
 	fput_light(counter_file, fput_needed2);
 
-out_fput:
-	fput_light(group_file, fput_needed);
-
-	return ret;
-
 err_free_put_context:
-	kfree(counter);
+	if (err < 0)
+		kfree(counter);
 
 err_put_context:
-	put_ctx(ctx);
+	if (err < 0)
+		put_ctx(ctx);
+
+	fput_light(group_file, fput_needed);
 
-	goto out_fput;
+	return err;
 }
 
 /*
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 72067cbdb37f..91e09d3b2eb2 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -208,3 +208,17 @@ config APM_EMULATION
 	  random kernel OOPSes or reboots that don't seem to be related to
 	  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.
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 81d2e7464893..04b3a83d686f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -298,8 +298,8 @@ int hibernation_snapshot(int platform_mode)
 	if (error)
 		return error;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	/* Preallocate image memory before shutting down devices. */
+	error = hibernate_preallocate_memory();
 	if (error)
 		goto Close;
 
@@ -315,6 +315,10 @@ int hibernation_snapshot(int platform_mode)
 	/* Control returns here after successful restore */
 
  Resume_devices:
+	/* We may need to release the preallocated image pages here. */
+	if (error || !in_suspend)
+		swsusp_free();
+
 	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 	resume_console();
@@ -460,11 +464,11 @@ int hibernation_platform_enter(void)
 
 	error = hibernation_ops->prepare();
 	if (error)
-		goto Platofrm_finish;
+		goto Platform_finish;
 
 	error = disable_nonboot_cpus();
 	if (error)
-		goto Platofrm_finish;
+		goto Platform_finish;
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_HIBERNATE);
@@ -476,7 +480,7 @@ int hibernation_platform_enter(void)
 	 * We don't need to reenable the nonboot CPUs or resume consoles, since
 	 * the system is going to be halted anyway.
 	 */
- Platofrm_finish:
+ Platform_finish:
 	hibernation_ops->finish();
 
 	dpm_suspend_noirq(PMSG_RESTORE);
@@ -578,7 +582,10 @@ int hibernate(void)
 		goto Thaw;
 
 	error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
-	if (in_suspend && !error) {
+	if (error)
+		goto Thaw;
+
+	if (in_suspend) {
 		unsigned int flags = 0;
 
 		if (hibernation_mode == HIBERNATION_PLATFORM)
@@ -590,8 +597,8 @@ int hibernate(void)
 			power_down();
 	} else {
 		pr_debug("PM: Image restored successfully.\n");
-		swsusp_free();
 	}
+
  Thaw:
 	thaw_processes();
  Finish:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f710e36930cc..347d2cc88cd0 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -11,6 +11,7 @@
 #include <linux/kobject.h>
 #include <linux/string.h>
 #include <linux/resume-trace.h>
+#include <linux/workqueue.h>
 
 #include "power.h"
 
@@ -217,8 +218,24 @@ static struct attribute_group attr_group = {
 	.attrs = g,
 };
 
+#ifdef CONFIG_PM_RUNTIME
+struct workqueue_struct *pm_wq;
+
+static int __init pm_start_workqueue(void)
+{
+	pm_wq = create_freezeable_workqueue("pm");
+
+	return pm_wq ? 0 : -ENOMEM;
+}
+#else
+static inline int pm_start_workqueue(void) { return 0; }
+#endif
+
 static int __init pm_init(void)
 {
+	int error = pm_start_workqueue();
+	if (error)
+		return error;
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 26d5a26f82e3..46c5a26630a3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -74,7 +74,7 @@ extern asmlinkage int swsusp_arch_resume(void);
 
 extern int create_basic_memory_bitmaps(void);
 extern void free_basic_memory_bitmaps(void);
-extern int swsusp_shrink_memory(void);
+extern int hibernate_preallocate_memory(void);
 
 /**
  *	Auxiliary structure used for reading the snapshot image data and
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 523a451b45d3..97955b0e44f4 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -233,7 +233,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 
 #define BM_END_OF_MAP	(~0UL)
 
-#define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
+#define BM_BITS_PER_BLOCK	(PAGE_SIZE * BITS_PER_BYTE)
 
 struct bm_block {
 	struct list_head hook;	/* hook into a list of bitmap blocks */
@@ -275,7 +275,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *	create_bm_block_list - create a list of block bitmap objects
- *	@nr_blocks - number of blocks to allocate
+ *	@pages - number of pages to track
  *	@list - list to put the allocated blocks into
  *	@ca - chain allocator to be used for allocating memory
  */
@@ -853,7 +853,7 @@ static unsigned int count_highmem_pages(void)
 	struct zone *zone;
 	unsigned int n = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long pfn, max_zone_pfn;
 
 		if (!is_highmem(zone))
@@ -916,7 +916,7 @@ static unsigned int count_data_pages(void)
 	unsigned long pfn, max_zone_pfn;
 	unsigned int n = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		if (is_highmem(zone))
 			continue;
 
@@ -1010,7 +1010,7 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 	struct zone *zone;
 	unsigned long pfn;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long max_zone_pfn;
 
 		mark_free_pages(zone);
@@ -1033,6 +1033,25 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 static unsigned int nr_copy_pages;
 /* Number of pages needed for saving the original pfns of the image pages */
 static unsigned int nr_meta_pages;
+/*
+ * Numbers of normal and highmem page frames allocated for hibernation image
+ * before suspending devices.
+ */
+unsigned int alloc_normal, alloc_highmem;
+/*
+ * Memory bitmap used for marking saveable pages (during hibernation) or
+ * hibernation image pages (during restore)
+ */
+static struct memory_bitmap orig_bm;
+/*
+ * Memory bitmap used during hibernation for marking allocated page frames that
+ * will contain copies of saveable pages.  During restore it is initially used
+ * for marking hibernation image pages, but then the set bits from it are
+ * duplicated in @orig_bm and it is released.  On highmem systems it is next
+ * used for marking "safe" highmem pages, but it has to be reinitialized for
+ * this purpose.
+ */
+static struct memory_bitmap copy_bm;
 
 /**
  *	swsusp_free - free pages allocated for the suspend.
@@ -1046,7 +1065,7 @@ void swsusp_free(void)
 	struct zone *zone;
 	unsigned long pfn, max_zone_pfn;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 			if (pfn_valid(pfn)) {
@@ -1064,74 +1083,286 @@ void swsusp_free(void)
 	nr_meta_pages = 0;
 	restore_pblist = NULL;
 	buffer = NULL;
+	alloc_normal = 0;
+	alloc_highmem = 0;
 }
 
+/* Helper functions used for the shrinking of memory. */
+
+#define GFP_IMAGE	(GFP_KERNEL | __GFP_NOWARN)
+
 /**
- *	swsusp_shrink_memory -  Try to free as much memory as needed
- *
- *	... but do not OOM-kill anyone
+ * preallocate_image_pages - Allocate a number of pages for hibernation image
+ * @nr_pages: Number of page frames to allocate.
+ * @mask: GFP flags to use for the allocation.
  *
- *	Notice: all userland should be stopped before it is called, or
- *	livelock is possible.
+ * Return value: Number of page frames actually allocated
+ */
+static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask)
+{
+	unsigned long nr_alloc = 0;
+
+	while (nr_pages > 0) {
+		struct page *page;
+
+		page = alloc_image_page(mask);
+		if (!page)
+			break;
+		memory_bm_set_bit(&copy_bm, page_to_pfn(page));
+		if (PageHighMem(page))
+			alloc_highmem++;
+		else
+			alloc_normal++;
+		nr_pages--;
+		nr_alloc++;
+	}
+
+	return nr_alloc;
+}
+
+static unsigned long preallocate_image_memory(unsigned long nr_pages)
+{
+	return preallocate_image_pages(nr_pages, GFP_IMAGE);
+}
+
+#ifdef CONFIG_HIGHMEM
+static unsigned long preallocate_image_highmem(unsigned long nr_pages)
+{
+	return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM);
+}
+
+/**
+ *  __fraction - Compute (an approximation of) x * (multiplier / base)
  */
+static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
+{
+	x *= multiplier;
+	do_div(x, base);
+	return (unsigned long)x;
+}
+
+static unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+						unsigned long highmem,
+						unsigned long total)
+{
+	unsigned long alloc = __fraction(nr_pages, highmem, total);
 
-#define SHRINK_BITE	10000
-static inline unsigned long __shrink_memory(long tmp)
+	return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM);
+}
+#else /* CONFIG_HIGHMEM */
+static inline unsigned long preallocate_image_highmem(unsigned long nr_pages)
 {
-	if (tmp > SHRINK_BITE)
-		tmp = SHRINK_BITE;
-	return shrink_all_memory(tmp);
+	return 0;
 }
 
-int swsusp_shrink_memory(void)
+static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+						unsigned long highmem,
+						unsigned long total)
+{
+	return 0;
+}
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ * free_unnecessary_pages - Release preallocated pages not needed for the image
+ */
+static void free_unnecessary_pages(void)
+{
+	unsigned long save_highmem, to_free_normal, to_free_highmem;
+
+	to_free_normal = alloc_normal - count_data_pages();
+	save_highmem = count_highmem_pages();
+	if (alloc_highmem > save_highmem) {
+		to_free_highmem = alloc_highmem - save_highmem;
+	} else {
+		to_free_highmem = 0;
+		to_free_normal -= save_highmem - alloc_highmem;
+	}
+
+	memory_bm_position_reset(&copy_bm);
+
+	while (to_free_normal > 0 && to_free_highmem > 0) {
+		unsigned long pfn = memory_bm_next_pfn(&copy_bm);
+		struct page *page = pfn_to_page(pfn);
+
+		if (PageHighMem(page)) {
+			if (!to_free_highmem)
+				continue;
+			to_free_highmem--;
+			alloc_highmem--;
+		} else {
+			if (!to_free_normal)
+				continue;
+			to_free_normal--;
+			alloc_normal--;
+		}
+		memory_bm_clear_bit(&copy_bm, pfn);
+		swsusp_unset_page_forbidden(page);
+		swsusp_unset_page_free(page);
+		__free_page(page);
+	}
+}
+
+/**
+ * minimum_image_size - Estimate the minimum acceptable size of an image
+ * @saveable: Number of saveable pages in the system.
+ *
+ * We want to avoid attempting to free too much memory too hard, so estimate the
+ * minimum acceptable size of a hibernation image to use as the lower limit for
+ * preallocating memory.
+ *
+ * We assume that the minimum image size should be proportional to
+ *
+ * [number of saveable pages] - [number of pages that can be freed in theory]
+ *
+ * where the second term is the sum of (1) reclaimable slab pages, (2) active
+ * and (3) inactive anonymouns pages, (4) active and (5) inactive file pages,
+ * minus mapped file pages.
+ */
+static unsigned long minimum_image_size(unsigned long saveable)
+{
+	unsigned long size;
+
+	size = global_page_state(NR_SLAB_RECLAIMABLE)
+		+ global_page_state(NR_ACTIVE_ANON)
+		+ global_page_state(NR_INACTIVE_ANON)
+		+ global_page_state(NR_ACTIVE_FILE)
+		+ global_page_state(NR_INACTIVE_FILE)
+		- global_page_state(NR_FILE_MAPPED);
+
+	return saveable <= size ? 0 : saveable - size;
+}
+
+/**
+ * hibernate_preallocate_memory - Preallocate memory for hibernation image
+ *
+ * To create a hibernation image it is necessary to make a copy of every page
+ * frame in use.  We also need a number of page frames to be free during
+ * hibernation for allocations made while saving the image and for device
+ * drivers, in case they need to allocate memory from their hibernation
+ * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
+ * respectively, both of which are rough estimates).  To make this happen, we
+ * compute the total number of available page frames and allocate at least
+ *
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ *
+ * of them, which corresponds to the maximum size of a hibernation image.
+ *
+ * If image_size is set below the number following from the above formula,
+ * the preallocation of memory is continued until the total number of saveable
+ * pages in the system is below the requested image size or the minimum
+ * acceptable image size returned by minimum_image_size(), whichever is greater.
+ */
+int hibernate_preallocate_memory(void)
 {
-	long tmp;
 	struct zone *zone;
-	unsigned long pages = 0;
-	unsigned int i = 0;
-	char *p = "-\\|/";
+	unsigned long saveable, size, max_size, count, highmem, pages = 0;
+	unsigned long alloc, save_highmem, pages_highmem;
 	struct timeval start, stop;
+	int error;
 
-	printk(KERN_INFO "PM: Shrinking memory...  ");
+	printk(KERN_INFO "PM: Preallocating image memory... ");
 	do_gettimeofday(&start);
-	do {
-		long size, highmem_size;
-
-		highmem_size = count_highmem_pages();
-		size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
-		tmp = size;
-		size += highmem_size;
-		for_each_populated_zone(zone) {
-			tmp += snapshot_additional_pages(zone);
-			if (is_highmem(zone)) {
-				highmem_size -=
-					zone_page_state(zone, NR_FREE_PAGES);
-			} else {
-				tmp -= zone_page_state(zone, NR_FREE_PAGES);
-				tmp += zone->lowmem_reserve[ZONE_NORMAL];
-			}
-		}
 
-		if (highmem_size < 0)
-			highmem_size = 0;
+	error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY);
+	if (error)
+		goto err_out;
 
-		tmp += highmem_size;
-		if (tmp > 0) {
-			tmp = __shrink_memory(tmp);
-			if (!tmp)
-				return -ENOMEM;
-			pages += tmp;
-		} else if (size > image_size / PAGE_SIZE) {
-			tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
-			pages += tmp;
-		}
-		printk("\b%c", p[i++%4]);
-	} while (tmp > 0);
+	error = memory_bm_create(&copy_bm, GFP_IMAGE, PG_ANY);
+	if (error)
+		goto err_out;
+
+	alloc_normal = 0;
+	alloc_highmem = 0;
+
+	/* Count the number of saveable data pages. */
+	save_highmem = count_highmem_pages();
+	saveable = count_data_pages();
+
+	/*
+	 * Compute the total number of page frames we can use (count) and the
+	 * number of pages needed for image metadata (size).
+	 */
+	count = saveable;
+	saveable += save_highmem;
+	highmem = save_highmem;
+	size = 0;
+	for_each_populated_zone(zone) {
+		size += snapshot_additional_pages(zone);
+		if (is_highmem(zone))
+			highmem += zone_page_state(zone, NR_FREE_PAGES);
+		else
+			count += zone_page_state(zone, NR_FREE_PAGES);
+	}
+	count += highmem;
+	count -= totalreserve_pages;
+
+	/* Compute the maximum number of saveable pages to leave in memory. */
+	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
+	if (size > max_size)
+		size = max_size;
+	/*
+	 * If the maximum is not less than the current number of saveable pages
+	 * in memory, allocate page frames for the image and we're done.
+	 */
+	if (size >= saveable) {
+		pages = preallocate_image_highmem(save_highmem);
+		pages += preallocate_image_memory(saveable - pages);
+		goto out;
+	}
+
+	/* Estimate the minimum size of the image. */
+	pages = minimum_image_size(saveable);
+	if (size < pages)
+		size = min_t(unsigned long, pages, max_size);
+
+	/*
+	 * Let the memory management subsystem know that we're going to need a
+	 * large number of page frames to allocate and make it free some memory.
+	 * NOTE: If this is not done, performance will be hurt badly in some
+	 * test cases.
+	 */
+	shrink_all_memory(saveable - size);
+
+	/*
+	 * The number of saveable pages in memory was too high, so apply some
+	 * pressure to decrease it.  First, make room for the largest possible
+	 * image and fail if that doesn't work.  Next, try to decrease the size
+	 * of the image as much as indicated by 'size' using allocations from
+	 * highmem and non-highmem zones separately.
+	 */
+	pages_highmem = preallocate_image_highmem(highmem / 2);
+	alloc = (count - max_size) - pages_highmem;
+	pages = preallocate_image_memory(alloc);
+	if (pages < alloc)
+		goto err_out;
+	size = max_size - size;
+	alloc = size;
+	size = preallocate_highmem_fraction(size, highmem, count);
+	pages_highmem += size;
+	alloc -= size;
+	pages += preallocate_image_memory(alloc);
+	pages += pages_highmem;
+
+	/*
+	 * We only need as many page frames for the image as there are saveable
+	 * pages in memory, but we have allocated more.  Release the excessive
+	 * ones now.
+	 */
+	free_unnecessary_pages();
+
+ out:
 	do_gettimeofday(&stop);
-	printk("\bdone (%lu pages freed)\n", pages);
-	swsusp_show_speed(&start, &stop, pages, "Freed");
+	printk(KERN_CONT "done (allocated %lu pages)\n", pages);
+	swsusp_show_speed(&start, &stop, pages, "Allocated");
 
 	return 0;
+
+ err_out:
+	printk(KERN_CONT "\n");
+	swsusp_free();
+	return -ENOMEM;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1142,7 +1373,7 @@ int swsusp_shrink_memory(void)
 
 static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
 {
-	unsigned int free_highmem = count_free_highmem_pages();
+	unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem;
 
 	if (free_highmem >= nr_highmem)
 		nr_highmem = 0;
@@ -1164,19 +1395,17 @@ count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
 static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
 {
 	struct zone *zone;
-	unsigned int free = 0, meta = 0;
+	unsigned int free = alloc_normal;
 
-	for_each_zone(zone) {
-		meta += snapshot_additional_pages(zone);
+	for_each_populated_zone(zone)
 		if (!is_highmem(zone))
 			free += zone_page_state(zone, NR_FREE_PAGES);
-	}
 
 	nr_pages += count_pages_for_highmem(nr_highmem);
-	pr_debug("PM: Normal pages needed: %u + %u + %u, available pages: %u\n",
-		nr_pages, PAGES_FOR_IO, meta, free);
+	pr_debug("PM: Normal pages needed: %u + %u, available pages: %u\n",
+		nr_pages, PAGES_FOR_IO, free);
 
-	return free > nr_pages + PAGES_FOR_IO + meta;
+	return free > nr_pages + PAGES_FOR_IO;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1198,7 +1427,7 @@ static inline int get_highmem_buffer(int safe_needed)
  */
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 {
 	unsigned int to_alloc = count_free_highmem_pages();
 
@@ -1218,7 +1447,7 @@ alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 static inline int get_highmem_buffer(int safe_needed) { return 0; }
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -1237,51 +1466,36 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 		unsigned int nr_pages, unsigned int nr_highmem)
 {
-	int error;
-
-	error = memory_bm_create(orig_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-	if (error)
-		goto Free;
-
-	error = memory_bm_create(copy_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-	if (error)
-		goto Free;
+	int error = 0;
 
 	if (nr_highmem > 0) {
 		error = get_highmem_buffer(PG_ANY);
 		if (error)
-			goto Free;
-
-		nr_pages += alloc_highmem_image_pages(copy_bm, nr_highmem);
+			goto err_out;
+		if (nr_highmem > alloc_highmem) {
+			nr_highmem -= alloc_highmem;
+			nr_pages += alloc_highmem_pages(copy_bm, nr_highmem);
+		}
 	}
-	while (nr_pages-- > 0) {
-		struct page *page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
-
-		if (!page)
-			goto Free;
+	if (nr_pages > alloc_normal) {
+		nr_pages -= alloc_normal;
+		while (nr_pages-- > 0) {
+			struct page *page;
 
-		memory_bm_set_bit(copy_bm, page_to_pfn(page));
+			page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
+			if (!page)
+				goto err_out;
+			memory_bm_set_bit(copy_bm, page_to_pfn(page));
+		}
 	}
+
 	return 0;
 
- Free:
+ err_out:
 	swsusp_free();
-	return -ENOMEM;
+	return error;
 }
 
-/* Memory bitmap used for marking saveable pages (during suspend) or the
- * suspend image pages (during resume)
- */
-static struct memory_bitmap orig_bm;
-/* Memory bitmap used on suspend for marking allocated pages that will contain
- * the copies of saveable pages.  During resume it is initially used for
- * marking the suspend image pages, but then its set bits are duplicated in
- * @orig_bm and it is released.  Next, on systems with high memory, it may be
- * used for marking "safe" highmem pages, but it has to be reinitialized for
- * this purpose.
- */
-static struct memory_bitmap copy_bm;
-
 asmlinkage int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
@@ -1474,7 +1688,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
 	unsigned long pfn, max_zone_pfn;
 
 	/* Clear page flags */
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 			if (pfn_valid(pfn))
diff --git a/kernel/printk.c b/kernel/printk.c
index b4d97b54c1ec..602033acd6c7 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -37,6 +37,12 @@
 #include <asm/uaccess.h>
 
 /*
+ * for_each_console() allows you to iterate on each console
+ */
+#define for_each_console(con) \
+	for (con = console_drivers; con != NULL; con = con->next)
+
+/*
  * Architectures can override it:
  */
 void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
@@ -61,6 +67,8 @@ int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* default_console_loglevel */
 };
 
+static int saved_console_loglevel = -1;
+
 /*
  * Low level drivers may need that to know if they can schedule in
  * their unblank() callback or not. So let's export it.
@@ -372,10 +380,15 @@ int do_syslog(int type, char __user *buf, int len)
 		logged_chars = 0;
 		break;
 	case 6:		/* Disable logging to console */
+		if (saved_console_loglevel == -1)
+			saved_console_loglevel = console_loglevel;
 		console_loglevel = minimum_console_loglevel;
 		break;
 	case 7:		/* Enable logging to console */
-		console_loglevel = default_console_loglevel;
+		if (saved_console_loglevel != -1) {
+			console_loglevel = saved_console_loglevel;
+			saved_console_loglevel = -1;
+		}
 		break;
 	case 8:		/* Set level of messages printed to console */
 		error = -EINVAL;
@@ -384,6 +397,8 @@ int do_syslog(int type, char __user *buf, int len)
 		if (len < minimum_console_loglevel)
 			len = minimum_console_loglevel;
 		console_loglevel = len;
+		/* Implicitly re-enable logging to console */
+		saved_console_loglevel = -1;
 		error = 0;
 		break;
 	case 9:		/* Number of chars in the log buffer */
@@ -412,7 +427,7 @@ static void __call_console_drivers(unsigned start, unsigned end)
 {
 	struct console *con;
 
-	for (con = console_drivers; con; con = con->next) {
+	for_each_console(con) {
 		if ((con->flags & CON_ENABLED) && con->write &&
 				(cpu_online(smp_processor_id()) ||
 				(con->flags & CON_ANYTIME)))
@@ -544,7 +559,7 @@ static int have_callable_console(void)
 {
 	struct console *con;
 
-	for (con = console_drivers; con; con = con->next)
+	for_each_console(con)
 		if (con->flags & CON_ANYTIME)
 			return 1;
 
@@ -1060,12 +1075,6 @@ void __sched console_conditional_schedule(void)
 }
 EXPORT_SYMBOL(console_conditional_schedule);
 
-void console_print(const char *s)
-{
-	printk(KERN_EMERG "%s", s);
-}
-EXPORT_SYMBOL(console_print);
-
 void console_unblank(void)
 {
 	struct console *c;
@@ -1082,7 +1091,7 @@ void console_unblank(void)
 
 	console_locked = 1;
 	console_may_schedule = 0;
-	for (c = console_drivers; c != NULL; c = c->next)
+	for_each_console(c)
 		if ((c->flags & CON_ENABLED) && c->unblank)
 			c->unblank();
 	release_console_sem();
@@ -1097,7 +1106,7 @@ struct tty_driver *console_device(int *index)
 	struct tty_driver *driver = NULL;
 
 	acquire_console_sem();
-	for (c = console_drivers; c != NULL; c = c->next) {
+	for_each_console(c) {
 		if (!c->device)
 			continue;
 		driver = c->device(c, index);
@@ -1134,25 +1143,49 @@ EXPORT_SYMBOL(console_start);
  * to register the console printing procedure with printk() and to
  * print any messages that were printed by the kernel before the
  * console driver was initialized.
+ *
+ * This can happen pretty early during the boot process (because of
+ * early_printk) - sometimes before setup_arch() completes - be careful
+ * of what kernel features are used - they may not be initialised yet.
+ *
+ * There are two types of consoles - bootconsoles (early_printk) and
+ * "real" consoles (everything which is not a bootconsole) which are
+ * handled differently.
+ *  - Any number of bootconsoles can be registered at any time.
+ *  - As soon as a "real" console is registered, all bootconsoles
+ *    will be unregistered automatically.
+ *  - Once a "real" console is registered, any attempt to register a
+ *    bootconsoles will be rejected
  */
-void register_console(struct console *console)
+void register_console(struct console *newcon)
 {
 	int i;
 	unsigned long flags;
-	struct console *bootconsole = NULL;
+	struct console *bcon = NULL;
 
-	if (console_drivers) {
-		if (console->flags & CON_BOOT)
-			return;
-		if (console_drivers->flags & CON_BOOT)
-			bootconsole = console_drivers;
+	/*
+	 * before we register a new CON_BOOT console, make sure we don't
+	 * already have a valid console
+	 */
+	if (console_drivers && newcon->flags & CON_BOOT) {
+		/* find the last or real console */
+		for_each_console(bcon) {
+			if (!(bcon->flags & CON_BOOT)) {
+				printk(KERN_INFO "Too late to register bootconsole %s%d\n",
+					newcon->name, newcon->index);
+				return;
+			}
+		}
 	}
 
-	if (preferred_console < 0 || bootconsole || !console_drivers)
+	if (console_drivers && console_drivers->flags & CON_BOOT)
+		bcon = console_drivers;
+
+	if (preferred_console < 0 || bcon || !console_drivers)
 		preferred_console = selected_console;
 
-	if (console->early_setup)
-		console->early_setup();
+	if (newcon->early_setup)
+		newcon->early_setup();
 
 	/*
 	 *	See if we want to use this console driver. If we
@@ -1160,13 +1193,13 @@ void register_console(struct console *console)
 	 *	that registers here.
 	 */
 	if (preferred_console < 0) {
-		if (console->index < 0)
-			console->index = 0;
-		if (console->setup == NULL ||
-		    console->setup(console, NULL) == 0) {
-			console->flags |= CON_ENABLED;
-			if (console->device) {
-				console->flags |= CON_CONSDEV;
+		if (newcon->index < 0)
+			newcon->index = 0;
+		if (newcon->setup == NULL ||
+		    newcon->setup(newcon, NULL) == 0) {
+			newcon->flags |= CON_ENABLED;
+			if (newcon->device) {
+				newcon->flags |= CON_CONSDEV;
 				preferred_console = 0;
 			}
 		}
@@ -1178,64 +1211,62 @@ void register_console(struct console *console)
 	 */
 	for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0];
 			i++) {
-		if (strcmp(console_cmdline[i].name, console->name) != 0)
+		if (strcmp(console_cmdline[i].name, newcon->name) != 0)
 			continue;
-		if (console->index >= 0 &&
-		    console->index != console_cmdline[i].index)
+		if (newcon->index >= 0 &&
+		    newcon->index != console_cmdline[i].index)
 			continue;
-		if (console->index < 0)
-			console->index = console_cmdline[i].index;
+		if (newcon->index < 0)
+			newcon->index = console_cmdline[i].index;
 #ifdef CONFIG_A11Y_BRAILLE_CONSOLE
 		if (console_cmdline[i].brl_options) {
-			console->flags |= CON_BRL;
-			braille_register_console(console,
+			newcon->flags |= CON_BRL;
+			braille_register_console(newcon,
 					console_cmdline[i].index,
 					console_cmdline[i].options,
 					console_cmdline[i].brl_options);
 			return;
 		}
 #endif
-		if (console->setup &&
-		    console->setup(console, console_cmdline[i].options) != 0)
+		if (newcon->setup &&
+		    newcon->setup(newcon, console_cmdline[i].options) != 0)
 			break;
-		console->flags |= CON_ENABLED;
-		console->index = console_cmdline[i].index;
+		newcon->flags |= CON_ENABLED;
+		newcon->index = console_cmdline[i].index;
 		if (i == selected_console) {
-			console->flags |= CON_CONSDEV;
+			newcon->flags |= CON_CONSDEV;
 			preferred_console = selected_console;
 		}
 		break;
 	}
 
-	if (!(console->flags & CON_ENABLED))
+	if (!(newcon->flags & CON_ENABLED))
 		return;
 
-	if (bootconsole && (console->flags & CON_CONSDEV)) {
-		printk(KERN_INFO "console handover: boot [%s%d] -> real [%s%d]\n",
-		       bootconsole->name, bootconsole->index,
-		       console->name, console->index);
-		unregister_console(bootconsole);
-		console->flags &= ~CON_PRINTBUFFER;
-	} else {
-		printk(KERN_INFO "console [%s%d] enabled\n",
-		       console->name, console->index);
-	}
+	/*
+	 * If we have a bootconsole, and are switching to a real console,
+	 * don't print everything out again, since when the boot console, and
+	 * the real console are the same physical device, it's annoying to
+	 * see the beginning boot messages twice
+	 */
+	if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV))
+		newcon->flags &= ~CON_PRINTBUFFER;
 
 	/*
 	 *	Put this console in the list - keep the
 	 *	preferred driver at the head of the list.
 	 */
 	acquire_console_sem();
-	if ((console->flags & CON_CONSDEV) || console_drivers == NULL) {
-		console->next = console_drivers;
-		console_drivers = console;
-		if (console->next)
-			console->next->flags &= ~CON_CONSDEV;
+	if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
+		newcon->next = console_drivers;
+		console_drivers = newcon;
+		if (newcon->next)
+			newcon->next->flags &= ~CON_CONSDEV;
 	} else {
-		console->next = console_drivers->next;
-		console_drivers->next = console;
+		newcon->next = console_drivers->next;
+		console_drivers->next = newcon;
 	}
-	if (console->flags & CON_PRINTBUFFER) {
+	if (newcon->flags & CON_PRINTBUFFER) {
 		/*
 		 * release_console_sem() will print out the buffered messages
 		 * for us.
@@ -1245,6 +1276,28 @@ void register_console(struct console *console)
 		spin_unlock_irqrestore(&logbuf_lock, flags);
 	}
 	release_console_sem();
+
+	/*
+	 * By unregistering the bootconsoles after we enable the real console
+	 * we get the "console xxx enabled" message on all the consoles -
+	 * boot consoles, real consoles, etc - this is to ensure that end
+	 * users know there might be something in the kernel's log buffer that
+	 * went to the bootconsole (that they do not see on the real console)
+	 */
+	if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) {
+		/* we need to iterate through twice, to make sure we print
+		 * everything out, before we unregister the console(s)
+		 */
+		printk(KERN_INFO "console [%s%d] enabled, bootconsole disabled\n",
+			newcon->name, newcon->index);
+		for_each_console(bcon)
+			if (bcon->flags & CON_BOOT)
+				unregister_console(bcon);
+	} else {
+		printk(KERN_INFO "%sconsole [%s%d] enabled\n",
+			(newcon->flags & CON_BOOT) ? "boot" : "" ,
+			newcon->name, newcon->index);
+	}
 }
 EXPORT_SYMBOL(register_console);
 
@@ -1287,11 +1340,13 @@ EXPORT_SYMBOL(unregister_console);
 
 static int __init disable_boot_consoles(void)
 {
-	if (console_drivers != NULL) {
-		if (console_drivers->flags & CON_BOOT) {
+	struct console *con;
+
+	for_each_console(con) {
+		if (con->flags & CON_BOOT) {
 			printk(KERN_INFO "turn off boot console %s%d\n",
-				console_drivers->name, console_drivers->index);
-			return unregister_console(console_drivers);
+				con->name, con->index);
+			unregister_console(con);
 		}
 	}
 	return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 082c320e4dbf..307c285af59e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -152,7 +152,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	if (!dumpable && !capable(CAP_SYS_PTRACE))
 		return -EPERM;
 
-	return security_ptrace_may_access(task, mode);
+	return security_ptrace_access_check(task, mode);
 }
 
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
deleted file mode 100644
index 0f2b0b311304..000000000000
--- a/kernel/rcuclassic.c
+++ /dev/null
@@ -1,807 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright IBM Corporation, 2001
- *
- * Authors: Dipankar Sarma <dipankar@in.ibm.com>
- *	    Manfred Spraul <manfred@colorfullife.com>
- *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
- * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
- * Papers:
- * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
- * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/mutex.h>
-#include <linux/time.h>
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
-EXPORT_SYMBOL_GPL(rcu_lock_map);
-#endif
-
-
-/* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_ctrlblk = {
-	.cur = -300,
-	.completed = -300,
-	.pending = -300,
-	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
-	.cpumask = CPU_BITS_NONE,
-};
-
-static struct rcu_ctrlblk rcu_bh_ctrlblk = {
-	.cur = -300,
-	.completed = -300,
-	.pending = -300,
-	.lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
-	.cpumask = CPU_BITS_NONE,
-};
-
-static DEFINE_PER_CPU(struct rcu_data, rcu_data);
-static DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
-
-/*
- * Increment the quiescent state counter.
- * The counter is a bit degenerated: We do not need to know
- * how many quiescent states passed, just if there was at least
- * one since the start of the grace period. Thus just a flag.
- */
-void rcu_qsctr_inc(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	rdp->passed_quiesc = 1;
-}
-
-void rcu_bh_qsctr_inc(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
-	rdp->passed_quiesc = 1;
-}
-
-static int blimit = 10;
-static int qhimark = 10000;
-static int qlowmark = 100;
-
-#ifdef CONFIG_SMP
-static void force_quiescent_state(struct rcu_data *rdp,
-			struct rcu_ctrlblk *rcp)
-{
-	int cpu;
-	unsigned long flags;
-
-	set_need_resched();
-	spin_lock_irqsave(&rcp->lock, flags);
-	if (unlikely(!rcp->signaled)) {
-		rcp->signaled = 1;
-		/*
-		 * Don't send IPI to itself. With irqs disabled,
-		 * rdp->cpu is the current cpu.
-		 *
-		 * cpu_online_mask is updated by the _cpu_down()
-		 * using __stop_machine(). Since we're in irqs disabled
-		 * section, __stop_machine() is not exectuting, hence
-		 * the cpu_online_mask is stable.
-		 *
-		 * However,  a cpu might have been offlined _just_ before
-		 * we disabled irqs while entering here.
-		 * And rcu subsystem might not yet have handled the CPU_DEAD
-		 * notification, leading to the offlined cpu's bit
-		 * being set in the rcp->cpumask.
-		 *
-		 * Hence cpumask = (rcp->cpumask & cpu_online_mask) to prevent
-		 * sending smp_reschedule() to an offlined CPU.
-		 */
-		for_each_cpu_and(cpu,
-				  to_cpumask(rcp->cpumask), cpu_online_mask) {
-			if (cpu != rdp->cpu)
-				smp_send_reschedule(cpu);
-		}
-	}
-	spin_unlock_irqrestore(&rcp->lock, flags);
-}
-#else
-static inline void force_quiescent_state(struct rcu_data *rdp,
-			struct rcu_ctrlblk *rcp)
-{
-	set_need_resched();
-}
-#endif
-
-static void __call_rcu(struct rcu_head *head, struct rcu_ctrlblk *rcp,
-		struct rcu_data *rdp)
-{
-	long batch;
-
-	head->next = NULL;
-	smp_mb(); /* Read of rcu->cur must happen after any change by caller. */
-
-	/*
-	 * Determine the batch number of this callback.
-	 *
-	 * Using ACCESS_ONCE to avoid the following error when gcc eliminates
-	 * local variable "batch" and emits codes like this:
-	 *	1) rdp->batch = rcp->cur + 1 # gets old value
-	 *	......
-	 *	2)rcu_batch_after(rcp->cur + 1, rdp->batch) # gets new value
-	 * then [*nxttail[0], *nxttail[1]) may contain callbacks
-	 * that batch# = rdp->batch, see the comment of struct rcu_data.
-	 */
-	batch = ACCESS_ONCE(rcp->cur) + 1;
-
-	if (rdp->nxtlist && rcu_batch_after(batch, rdp->batch)) {
-		/* process callbacks */
-		rdp->nxttail[0] = rdp->nxttail[1];
-		rdp->nxttail[1] = rdp->nxttail[2];
-		if (rcu_batch_after(batch - 1, rdp->batch))
-			rdp->nxttail[0] = rdp->nxttail[2];
-	}
-
-	rdp->batch = batch;
-	*rdp->nxttail[2] = head;
-	rdp->nxttail[2] = &head->next;
-
-	if (unlikely(++rdp->qlen > qhimark)) {
-		rdp->blimit = INT_MAX;
-		force_quiescent_state(rdp, &rcu_ctrlblk);
-	}
-}
-
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
-static void record_gp_stall_check_time(struct rcu_ctrlblk *rcp)
-{
-	rcp->gp_start = jiffies;
-	rcp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
-}
-
-static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-	int cpu;
-	long delta;
-	unsigned long flags;
-
-	/* Only let one CPU complain about others per time interval. */
-
-	spin_lock_irqsave(&rcp->lock, flags);
-	delta = jiffies - rcp->jiffies_stall;
-	if (delta < 2 || rcp->cur != rcp->completed) {
-		spin_unlock_irqrestore(&rcp->lock, flags);
-		return;
-	}
-	rcp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
-	spin_unlock_irqrestore(&rcp->lock, flags);
-
-	/* OK, time to rat on our buddy... */
-
-	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
-	for_each_possible_cpu(cpu) {
-		if (cpumask_test_cpu(cpu, to_cpumask(rcp->cpumask)))
-			printk(" %d", cpu);
-	}
-	printk(" (detected by %d, t=%ld jiffies)\n",
-	       smp_processor_id(), (long)(jiffies - rcp->gp_start));
-}
-
-static void print_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-	unsigned long flags;
-
-	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
-			smp_processor_id(), jiffies,
-			jiffies - rcp->gp_start);
-	dump_stack();
-	spin_lock_irqsave(&rcp->lock, flags);
-	if ((long)(jiffies - rcp->jiffies_stall) >= 0)
-		rcp->jiffies_stall =
-			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
-	spin_unlock_irqrestore(&rcp->lock, flags);
-	set_need_resched();  /* kick ourselves to get things going. */
-}
-
-static void check_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-	long delta;
-
-	delta = jiffies - rcp->jiffies_stall;
-	if (cpumask_test_cpu(smp_processor_id(), to_cpumask(rcp->cpumask)) &&
-		delta >= 0) {
-
-		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall(rcp);
-
-	} else if (rcp->cur != rcp->completed && delta >= 2) {
-
-		/* They had two seconds to dump stack, so complain. */
-		print_other_cpu_stall(rcp);
-	}
-}
-
-#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-static void record_gp_stall_check_time(struct rcu_ctrlblk *rcp)
-{
-}
-
-static inline void check_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-/**
- * call_rcu - Queue an RCU callback for invocation after a grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
- *
- * The update function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-void call_rcu(struct rcu_head *head,
-				void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-
-	head->func = func;
-	local_irq_save(flags);
-	__call_rcu(head, &rcu_ctrlblk, &__get_cpu_var(rcu_data));
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-/**
- * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
- *
- * The update function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_bh() assumes
- * that the read-side critical sections end on completion of a softirq
- * handler. This means that read-side critical sections in process
- * context must not be interrupted by softirqs. This interface is to be
- * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by rcu_read_lock() and
- * rcu_read_unlock(), * if in interrupt context or rcu_read_lock_bh()
- * and rcu_read_unlock_bh(), if in process context. These may be nested.
- */
-void call_rcu_bh(struct rcu_head *head,
-				void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-
-	head->func = func;
-	local_irq_save(flags);
-	__call_rcu(head, &rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu_bh);
-
-/*
- * Return the number of RCU batches processed thus far.  Useful
- * for debug and statistics.
- */
-long rcu_batches_completed(void)
-{
-	return rcu_ctrlblk.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU batches processed thus far.  Useful
- * for debug and statistics.
- */
-long rcu_batches_completed_bh(void)
-{
-	return rcu_bh_ctrlblk.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
-
-/* Raises the softirq for processing rcu_callbacks. */
-static inline void raise_rcu_softirq(void)
-{
-	raise_softirq(RCU_SOFTIRQ);
-}
-
-/*
- * Invoke the completed RCU callbacks. They are expected to be in
- * a per-cpu list.
- */
-static void rcu_do_batch(struct rcu_data *rdp)
-{
-	unsigned long flags;
-	struct rcu_head *next, *list;
-	int count = 0;
-
-	list = rdp->donelist;
-	while (list) {
-		next = list->next;
-		prefetch(next);
-		list->func(list);
-		list = next;
-		if (++count >= rdp->blimit)
-			break;
-	}
-	rdp->donelist = list;
-
-	local_irq_save(flags);
-	rdp->qlen -= count;
-	local_irq_restore(flags);
-	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
-		rdp->blimit = blimit;
-
-	if (!rdp->donelist)
-		rdp->donetail = &rdp->donelist;
-	else
-		raise_rcu_softirq();
-}
-
-/*
- * Grace period handling:
- * The grace period handling consists out of two steps:
- * - A new grace period is started.
- *   This is done by rcu_start_batch. The start is not broadcasted to
- *   all cpus, they must pick this up by comparing rcp->cur with
- *   rdp->quiescbatch. All cpus are recorded  in the
- *   rcu_ctrlblk.cpumask bitmap.
- * - All cpus must go through a quiescent state.
- *   Since the start of the grace period is not broadcasted, at least two
- *   calls to rcu_check_quiescent_state are required:
- *   The first call just notices that a new grace period is running. The
- *   following calls check if there was a quiescent state since the beginning
- *   of the grace period. If so, it updates rcu_ctrlblk.cpumask. If
- *   the bitmap is empty, then the grace period is completed.
- *   rcu_check_quiescent_state calls rcu_start_batch(0) to start the next grace
- *   period (if necessary).
- */
-
-/*
- * Register a new batch of callbacks, and start it up if there is currently no
- * active batch and the batch to be registered has not already occurred.
- * Caller must hold rcu_ctrlblk.lock.
- */
-static void rcu_start_batch(struct rcu_ctrlblk *rcp)
-{
-	if (rcp->cur != rcp->pending &&
-			rcp->completed == rcp->cur) {
-		rcp->cur++;
-		record_gp_stall_check_time(rcp);
-
-		/*
-		 * Accessing nohz_cpu_mask before incrementing rcp->cur needs a
-		 * Barrier  Otherwise it can cause tickless idle CPUs to be
-		 * included in rcp->cpumask, which will extend graceperiods
-		 * unnecessarily.
-		 */
-		smp_mb();
-		cpumask_andnot(to_cpumask(rcp->cpumask),
-			       cpu_online_mask, nohz_cpu_mask);
-
-		rcp->signaled = 0;
-	}
-}
-
-/*
- * cpu went through a quiescent state since the beginning of the grace period.
- * Clear it from the cpu mask and complete the grace period if it was the last
- * cpu. Start another grace period if someone has further entries pending
- */
-static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
-{
-	cpumask_clear_cpu(cpu, to_cpumask(rcp->cpumask));
-	if (cpumask_empty(to_cpumask(rcp->cpumask))) {
-		/* batch completed ! */
-		rcp->completed = rcp->cur;
-		rcu_start_batch(rcp);
-	}
-}
-
-/*
- * Check if the cpu has gone through a quiescent state (say context
- * switch). If so and if it already hasn't done so in this RCU
- * quiescent cycle, then indicate that it has done so.
- */
-static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
-					struct rcu_data *rdp)
-{
-	unsigned long flags;
-
-	if (rdp->quiescbatch != rcp->cur) {
-		/* start new grace period: */
-		rdp->qs_pending = 1;
-		rdp->passed_quiesc = 0;
-		rdp->quiescbatch = rcp->cur;
-		return;
-	}
-
-	/* Grace period already completed for this cpu?
-	 * qs_pending is checked instead of the actual bitmap to avoid
-	 * cacheline trashing.
-	 */
-	if (!rdp->qs_pending)
-		return;
-
-	/*
-	 * Was there a quiescent state since the beginning of the grace
-	 * period? If no, then exit and wait for the next call.
-	 */
-	if (!rdp->passed_quiesc)
-		return;
-	rdp->qs_pending = 0;
-
-	spin_lock_irqsave(&rcp->lock, flags);
-	/*
-	 * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync
-	 * during cpu startup. Ignore the quiescent state.
-	 */
-	if (likely(rdp->quiescbatch == rcp->cur))
-		cpu_quiet(rdp->cpu, rcp);
-
-	spin_unlock_irqrestore(&rcp->lock, flags);
-}
-
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/* warning! helper for rcu_offline_cpu. do not use elsewhere without reviewing
- * locking requirements, the list it's pulling from has to belong to a cpu
- * which is dead and hence not processing interrupts.
- */
-static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list,
-				struct rcu_head **tail, long batch)
-{
-	unsigned long flags;
-
-	if (list) {
-		local_irq_save(flags);
-		this_rdp->batch = batch;
-		*this_rdp->nxttail[2] = list;
-		this_rdp->nxttail[2] = tail;
-		local_irq_restore(flags);
-	}
-}
-
-static void __rcu_offline_cpu(struct rcu_data *this_rdp,
-				struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
-{
-	unsigned long flags;
-
-	/*
-	 * if the cpu going offline owns the grace period
-	 * we can block indefinitely waiting for it, so flush
-	 * it here
-	 */
-	spin_lock_irqsave(&rcp->lock, flags);
-	if (rcp->cur != rcp->completed)
-		cpu_quiet(rdp->cpu, rcp);
-	rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail, rcp->cur + 1);
-	rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail[2], rcp->cur + 1);
-	spin_unlock(&rcp->lock);
-
-	this_rdp->qlen += rdp->qlen;
-	local_irq_restore(flags);
-}
-
-static void rcu_offline_cpu(int cpu)
-{
-	struct rcu_data *this_rdp = &get_cpu_var(rcu_data);
-	struct rcu_data *this_bh_rdp = &get_cpu_var(rcu_bh_data);
-
-	__rcu_offline_cpu(this_rdp, &rcu_ctrlblk,
-					&per_cpu(rcu_data, cpu));
-	__rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk,
-					&per_cpu(rcu_bh_data, cpu));
-	put_cpu_var(rcu_data);
-	put_cpu_var(rcu_bh_data);
-}
-
-#else
-
-static void rcu_offline_cpu(int cpu)
-{
-}
-
-#endif
-
-/*
- * This does the RCU processing work from softirq context.
- */
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
-					struct rcu_data *rdp)
-{
-	unsigned long flags;
-	long completed_snap;
-
-	if (rdp->nxtlist) {
-		local_irq_save(flags);
-		completed_snap = ACCESS_ONCE(rcp->completed);
-
-		/*
-		 * move the other grace-period-completed entries to
-		 * [rdp->nxtlist, *rdp->nxttail[0]) temporarily
-		 */
-		if (!rcu_batch_before(completed_snap, rdp->batch))
-			rdp->nxttail[0] = rdp->nxttail[1] = rdp->nxttail[2];
-		else if (!rcu_batch_before(completed_snap, rdp->batch - 1))
-			rdp->nxttail[0] = rdp->nxttail[1];
-
-		/*
-		 * the grace period for entries in
-		 * [rdp->nxtlist, *rdp->nxttail[0]) has completed and
-		 * move these entries to donelist
-		 */
-		if (rdp->nxttail[0] != &rdp->nxtlist) {
-			*rdp->donetail = rdp->nxtlist;
-			rdp->donetail = rdp->nxttail[0];
-			rdp->nxtlist = *rdp->nxttail[0];
-			*rdp->donetail = NULL;
-
-			if (rdp->nxttail[1] == rdp->nxttail[0])
-				rdp->nxttail[1] = &rdp->nxtlist;
-			if (rdp->nxttail[2] == rdp->nxttail[0])
-				rdp->nxttail[2] = &rdp->nxtlist;
-			rdp->nxttail[0] = &rdp->nxtlist;
-		}
-
-		local_irq_restore(flags);
-
-		if (rcu_batch_after(rdp->batch, rcp->pending)) {
-			unsigned long flags2;
-
-			/* and start it/schedule start if it's a new batch */
-			spin_lock_irqsave(&rcp->lock, flags2);
-			if (rcu_batch_after(rdp->batch, rcp->pending)) {
-				rcp->pending = rdp->batch;
-				rcu_start_batch(rcp);
-			}
-			spin_unlock_irqrestore(&rcp->lock, flags2);
-		}
-	}
-
-	rcu_check_quiescent_state(rcp, rdp);
-	if (rdp->donelist)
-		rcu_do_batch(rdp);
-}
-
-static void rcu_process_callbacks(struct softirq_action *unused)
-{
-	/*
-	 * Memory references from any prior RCU read-side critical sections
-	 * executed by the interrupted code must be see before any RCU
-	 * grace-period manupulations below.
-	 */
-
-	smp_mb(); /* See above block comment. */
-
-	__rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data));
-	__rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
-
-	/*
-	 * Memory references from any later RCU read-side critical sections
-	 * executed by the interrupted code must be see after any RCU
-	 * grace-period manupulations above.
-	 */
-
-	smp_mb(); /* See above block comment. */
-}
-
-static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
-{
-	/* Check for CPU stalls, if enabled. */
-	check_cpu_stall(rcp);
-
-	if (rdp->nxtlist) {
-		long completed_snap = ACCESS_ONCE(rcp->completed);
-
-		/*
-		 * This cpu has pending rcu entries and the grace period
-		 * for them has completed.
-		 */
-		if (!rcu_batch_before(completed_snap, rdp->batch))
-			return 1;
-		if (!rcu_batch_before(completed_snap, rdp->batch - 1) &&
-				rdp->nxttail[0] != rdp->nxttail[1])
-			return 1;
-		if (rdp->nxttail[0] != &rdp->nxtlist)
-			return 1;
-
-		/*
-		 * This cpu has pending rcu entries and the new batch
-		 * for then hasn't been started nor scheduled start
-		 */
-		if (rcu_batch_after(rdp->batch, rcp->pending))
-			return 1;
-	}
-
-	/* This cpu has finished callbacks to invoke */
-	if (rdp->donelist)
-		return 1;
-
-	/* The rcu core waits for a quiescent state from the cpu */
-	if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
-		return 1;
-
-	/* nothing to do */
-	return 0;
-}
-
-/*
- * Check to see if there is any immediate RCU-related work to be done
- * by the current CPU, returning 1 if so.  This function is part of the
- * RCU implementation; it is -not- an exported member of the RCU API.
- */
-int rcu_pending(int cpu)
-{
-	return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
-		__rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
-}
-
-/*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so.  This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
- */
-int rcu_needs_cpu(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);
-
-	return !!rdp->nxtlist || !!rdp_bh->nxtlist || rcu_pending(cpu);
-}
-
-/*
- * Top-level function driving RCU grace-period detection, normally
- * invoked from the scheduler-clock interrupt.  This function simply
- * increments counters that are read only from softirq by this same
- * CPU, so there are no memory barriers required.
- */
-void rcu_check_callbacks(int cpu, int user)
-{
-	if (user ||
-	    (idle_cpu(cpu) && rcu_scheduler_active &&
-	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
-
-		/*
-		 * Get here if this CPU took its interrupt from user
-		 * mode or from the idle loop, and if this is not a
-		 * nested interrupt.  In this case, the CPU is in
-		 * a quiescent state, so count it.
-		 *
-		 * Also do a memory barrier.  This is needed to handle
-		 * the case where writes from a preempt-disable section
-		 * of code get reordered into schedule() by this CPU's
-		 * write buffer.  The memory barrier makes sure that
-		 * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
-		 * by other CPUs to happen after any such write.
-		 */
-
-		smp_mb();  /* See above block comment. */
-		rcu_qsctr_inc(cpu);
-		rcu_bh_qsctr_inc(cpu);
-
-	} else if (!in_softirq()) {
-
-		/*
-		 * Get here if this CPU did not take its interrupt from
-		 * softirq, in other words, if it is not interrupting
-		 * a rcu_bh read-side critical section.  This is an _bh
-		 * critical section, so count it.  The memory barrier
-		 * is needed for the same reason as is the above one.
-		 */
-
-		smp_mb();  /* See above block comment. */
-		rcu_bh_qsctr_inc(cpu);
-	}
-	raise_rcu_softirq();
-}
-
-static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
-						struct rcu_data *rdp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&rcp->lock, flags);
-	memset(rdp, 0, sizeof(*rdp));
-	rdp->nxttail[0] = rdp->nxttail[1] = rdp->nxttail[2] = &rdp->nxtlist;
-	rdp->donetail = &rdp->donelist;
-	rdp->quiescbatch = rcp->completed;
-	rdp->qs_pending = 0;
-	rdp->cpu = cpu;
-	rdp->blimit = blimit;
-	spin_unlock_irqrestore(&rcp->lock, flags);
-}
-
-static void __cpuinit rcu_online_cpu(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	struct rcu_data *bh_rdp = &per_cpu(rcu_bh_data, cpu);
-
-	rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp);
-	rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp);
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
-}
-
-static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		rcu_offline_cpu(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata rcu_nb = {
-	.notifier_call	= rcu_cpu_notify,
-};
-
-/*
- * Initializes rcu mechanism.  Assumed to be called early.
- * That is before local timer(SMP) or jiffie timer (uniproc) is setup.
- * Note that rcu_qsctr and friends are implicitly
- * initialized due to the choice of ``0'' for RCU_CTR_INVALID.
- */
-void __init __rcu_init(void)
-{
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-	rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,
-			(void *)(long)smp_processor_id());
-	/* Register notifier for non-boot CPUs */
-	register_cpu_notifier(&rcu_nb);
-}
-
-module_param(blimit, int, 0);
-module_param(qhimark, int, 0);
-module_param(qlowmark, int, 0);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a967c9feb90a..bd5d5c8e5140 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -98,6 +98,30 @@ void synchronize_rcu(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
+/**
+ * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu_bh grace
+ * period has elapsed, in other words after all currently executing rcu_bh
+ * read-side critical sections have completed.  RCU read-side critical
+ * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
+ * and may be nested.
+ */
+void synchronize_rcu_bh(void)
+{
+	struct rcu_synchronize rcu;
+
+	if (rcu_blocking_is_gp())
+		return;
+
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu_bh(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+
 static void rcu_barrier_callback(struct rcu_head *notused)
 {
 	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
@@ -129,6 +153,7 @@ static void rcu_barrier_func(void *type)
 static inline void wait_migrated_callbacks(void)
 {
 	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
+	smp_mb(); /* In case we didn't sleep. */
 }
 
 /*
@@ -192,9 +217,13 @@ static void rcu_migrate_callback(struct rcu_head *notused)
 		wake_up(&rcu_migrate_wq);
 }
 
+extern int rcu_cpu_notify(struct notifier_block *self,
+			  unsigned long action, void *hcpu);
+
 static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
 		unsigned long action, void *hcpu)
 {
+	rcu_cpu_notify(self, action, hcpu);
 	if (action == CPU_DYING) {
 		/*
 		 * preempt_disable() in on_each_cpu() prevents stop_machine(),
@@ -209,7 +238,8 @@ static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
 		call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
 		call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
 		call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
-	} else if (action == CPU_POST_DEAD) {
+	} else if (action == CPU_DOWN_PREPARE) {
+		/* Don't need to wait until next removal operation. */
 		/* rcu_migrate_head is protected by cpu_add_remove_lock */
 		wait_migrated_callbacks();
 	}
@@ -219,8 +249,18 @@ static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
 
 void __init rcu_init(void)
 {
+	int i;
+
 	__rcu_init();
-	hotcpu_notifier(rcu_barrier_cpu_hotplug, 0);
+	cpu_notifier(rcu_barrier_cpu_hotplug, 0);
+
+	/*
+	 * We don't need protection against CPU-hotplug here because
+	 * this is called early in boot, before either interrupts
+	 * or the scheduler are operational.
+	 */
+	for_each_online_cpu(i)
+		rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i);
 }
 
 void rcu_scheduler_starting(void)
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
deleted file mode 100644
index beb0e659adcc..000000000000
--- a/kernel/rcupreempt.c
+++ /dev/null
@@ -1,1539 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion, realtime implementation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright IBM Corporation, 2006
- *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
- *		With thanks to Esben Nielsen, Bill Huey, and Ingo Molnar
- *		for pushing me away from locks and towards counters, and
- *		to Suparna Bhattacharya for pushing me completely away
- *		from atomic instructions on the read side.
- *
- *  - Added handling of Dynamic Ticks
- *      Copyright 2007 - Paul E. Mckenney <paulmck@us.ibm.com>
- *                     - Steven Rostedt <srostedt@redhat.com>
- *
- * Papers:  http://www.rdrop.com/users/paulmck/RCU
- *
- * Design Document: http://lwn.net/Articles/253651/
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU/ *.txt
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/kthread.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/cpumask.h>
-#include <linux/rcupreempt_trace.h>
-#include <asm/byteorder.h>
-
-/*
- * PREEMPT_RCU data structures.
- */
-
-/*
- * GP_STAGES specifies the number of times the state machine has
- * to go through the all the rcu_try_flip_states (see below)
- * in a single Grace Period.
- *
- * GP in GP_STAGES stands for Grace Period ;)
- */
-#define GP_STAGES    2
-struct rcu_data {
-	spinlock_t	lock;		/* Protect rcu_data fields. */
-	long		completed;	/* Number of last completed batch. */
-	int		waitlistcount;
-	struct rcu_head *nextlist;
-	struct rcu_head **nexttail;
-	struct rcu_head *waitlist[GP_STAGES];
-	struct rcu_head **waittail[GP_STAGES];
-	struct rcu_head *donelist;	/* from waitlist & waitschedlist */
-	struct rcu_head **donetail;
-	long rcu_flipctr[2];
-	struct rcu_head *nextschedlist;
-	struct rcu_head **nextschedtail;
-	struct rcu_head *waitschedlist;
-	struct rcu_head **waitschedtail;
-	int rcu_sched_sleeping;
-#ifdef CONFIG_RCU_TRACE
-	struct rcupreempt_trace trace;
-#endif /* #ifdef CONFIG_RCU_TRACE */
-};
-
-/*
- * States for rcu_try_flip() and friends.
- */
-
-enum rcu_try_flip_states {
-
-	/*
-	 * Stay here if nothing is happening. Flip the counter if somthing
-	 * starts happening. Denoted by "I"
-	 */
-	rcu_try_flip_idle_state,
-
-	/*
-	 * Wait here for all CPUs to notice that the counter has flipped. This
-	 * prevents the old set of counters from ever being incremented once
-	 * we leave this state, which in turn is necessary because we cannot
-	 * test any individual counter for zero -- we can only check the sum.
-	 * Denoted by "A".
-	 */
-	rcu_try_flip_waitack_state,
-
-	/*
-	 * Wait here for the sum of the old per-CPU counters to reach zero.
-	 * Denoted by "Z".
-	 */
-	rcu_try_flip_waitzero_state,
-
-	/*
-	 * Wait here for each of the other CPUs to execute a memory barrier.
-	 * This is necessary to ensure that these other CPUs really have
-	 * completed executing their RCU read-side critical sections, despite
-	 * their CPUs wildly reordering memory. Denoted by "M".
-	 */
-	rcu_try_flip_waitmb_state,
-};
-
-/*
- * States for rcu_ctrlblk.rcu_sched_sleep.
- */
-
-enum rcu_sched_sleep_states {
-	rcu_sched_not_sleeping,	/* Not sleeping, callbacks need GP.  */
-	rcu_sched_sleep_prep,	/* Thinking of sleeping, rechecking. */
-	rcu_sched_sleeping,	/* Sleeping, awaken if GP needed. */
-};
-
-struct rcu_ctrlblk {
-	spinlock_t	fliplock;	/* Protect state-machine transitions. */
-	long		completed;	/* Number of last completed batch. */
-	enum rcu_try_flip_states rcu_try_flip_state; /* The current state of
-							the rcu state machine */
-	spinlock_t	schedlock;	/* Protect rcu_sched sleep state. */
-	enum rcu_sched_sleep_states sched_sleep; /* rcu_sched state. */
-	wait_queue_head_t sched_wq;	/* Place for rcu_sched to sleep. */
-};
-
-struct rcu_dyntick_sched {
-	int dynticks;
-	int dynticks_snap;
-	int sched_qs;
-	int sched_qs_snap;
-	int sched_dynticks_snap;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
-	.dynticks = 1,
-};
-
-void rcu_qsctr_inc(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->sched_qs++;
-}
-
-#ifdef CONFIG_NO_HZ
-
-void rcu_enter_nohz(void)
-{
-	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
-
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	__get_cpu_var(rcu_dyntick_sched).dynticks++;
-	WARN_ON_RATELIMIT(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1, &rs);
-}
-
-void rcu_exit_nohz(void)
-{
-	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
-
-	__get_cpu_var(rcu_dyntick_sched).dynticks++;
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
-	WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1),
-				&rs);
-}
-
-#endif /* CONFIG_NO_HZ */
-
-
-static DEFINE_PER_CPU(struct rcu_data, rcu_data);
-
-static struct rcu_ctrlblk rcu_ctrlblk = {
-	.fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock),
-	.completed = 0,
-	.rcu_try_flip_state = rcu_try_flip_idle_state,
-	.schedlock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.schedlock),
-	.sched_sleep = rcu_sched_not_sleeping,
-	.sched_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rcu_ctrlblk.sched_wq),
-};
-
-static struct task_struct *rcu_sched_grace_period_task;
-
-#ifdef CONFIG_RCU_TRACE
-static char *rcu_try_flip_state_names[] =
-	{ "idle", "waitack", "waitzero", "waitmb" };
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-static DECLARE_BITMAP(rcu_cpu_online_map, NR_CPUS) __read_mostly
-	= CPU_BITS_NONE;
-
-/*
- * Enum and per-CPU flag to determine when each CPU has seen
- * the most recent counter flip.
- */
-
-enum rcu_flip_flag_values {
-	rcu_flip_seen,		/* Steady/initial state, last flip seen. */
-				/* Only GP detector can update. */
-	rcu_flipped		/* Flip just completed, need confirmation. */
-				/* Only corresponding CPU can update. */
-};
-static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_flip_flag_values, rcu_flip_flag)
-								= rcu_flip_seen;
-
-/*
- * Enum and per-CPU flag to determine when each CPU has executed the
- * needed memory barrier to fence in memory references from its last RCU
- * read-side critical section in the just-completed grace period.
- */
-
-enum rcu_mb_flag_values {
-	rcu_mb_done,		/* Steady/initial state, no mb()s required. */
-				/* Only GP detector can update. */
-	rcu_mb_needed		/* Flip just completed, need an mb(). */
-				/* Only corresponding CPU can update. */
-};
-static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_mb_flag_values, rcu_mb_flag)
-								= rcu_mb_done;
-
-/*
- * RCU_DATA_ME: find the current CPU's rcu_data structure.
- * RCU_DATA_CPU: find the specified CPU's rcu_data structure.
- */
-#define RCU_DATA_ME()		(&__get_cpu_var(rcu_data))
-#define RCU_DATA_CPU(cpu)	(&per_cpu(rcu_data, cpu))
-
-/*
- * Helper macro for tracing when the appropriate rcu_data is not
- * cached in a local variable, but where the CPU number is so cached.
- */
-#define RCU_TRACE_CPU(f, cpu) RCU_TRACE(f, &(RCU_DATA_CPU(cpu)->trace));
-
-/*
- * Helper macro for tracing when the appropriate rcu_data is not
- * cached in a local variable.
- */
-#define RCU_TRACE_ME(f) RCU_TRACE(f, &(RCU_DATA_ME()->trace));
-
-/*
- * Helper macro for tracing when the appropriate rcu_data is pointed
- * to by a local variable.
- */
-#define RCU_TRACE_RDP(f, rdp) RCU_TRACE(f, &((rdp)->trace));
-
-#define RCU_SCHED_BATCH_TIME (HZ / 50)
-
-/*
- * Return the number of RCU batches processed thus far.  Useful
- * for debug and statistics.
- */
-long rcu_batches_completed(void)
-{
-	return rcu_ctrlblk.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-void __rcu_read_lock(void)
-{
-	int idx;
-	struct task_struct *t = current;
-	int nesting;
-
-	nesting = ACCESS_ONCE(t->rcu_read_lock_nesting);
-	if (nesting != 0) {
-
-		/* An earlier rcu_read_lock() covers us, just count it. */
-
-		t->rcu_read_lock_nesting = nesting + 1;
-
-	} else {
-		unsigned long flags;
-
-		/*
-		 * We disable interrupts for the following reasons:
-		 * - If we get scheduling clock interrupt here, and we
-		 *   end up acking the counter flip, it's like a promise
-		 *   that we will never increment the old counter again.
-		 *   Thus we will break that promise if that
-		 *   scheduling clock interrupt happens between the time
-		 *   we pick the .completed field and the time that we
-		 *   increment our counter.
-		 *
-		 * - We don't want to be preempted out here.
-		 *
-		 * NMIs can still occur, of course, and might themselves
-		 * contain rcu_read_lock().
-		 */
-
-		local_irq_save(flags);
-
-		/*
-		 * Outermost nesting of rcu_read_lock(), so increment
-		 * the current counter for the current CPU.  Use volatile
-		 * casts to prevent the compiler from reordering.
-		 */
-
-		idx = ACCESS_ONCE(rcu_ctrlblk.completed) & 0x1;
-		ACCESS_ONCE(RCU_DATA_ME()->rcu_flipctr[idx])++;
-
-		/*
-		 * Now that the per-CPU counter has been incremented, we
-		 * are protected from races with rcu_read_lock() invoked
-		 * from NMI handlers on this CPU.  We can therefore safely
-		 * increment the nesting counter, relieving further NMIs
-		 * of the need to increment the per-CPU counter.
-		 */
-
-		ACCESS_ONCE(t->rcu_read_lock_nesting) = nesting + 1;
-
-		/*
-		 * Now that we have preventing any NMIs from storing
-		 * to the ->rcu_flipctr_idx, we can safely use it to
-		 * remember which counter to decrement in the matching
-		 * rcu_read_unlock().
-		 */
-
-		ACCESS_ONCE(t->rcu_flipctr_idx) = idx;
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL_GPL(__rcu_read_lock);
-
-void __rcu_read_unlock(void)
-{
-	int idx;
-	struct task_struct *t = current;
-	int nesting;
-
-	nesting = ACCESS_ONCE(t->rcu_read_lock_nesting);
-	if (nesting > 1) {
-
-		/*
-		 * We are still protected by the enclosing rcu_read_lock(),
-		 * so simply decrement the counter.
-		 */
-
-		t->rcu_read_lock_nesting = nesting - 1;
-
-	} else {
-		unsigned long flags;
-
-		/*
-		 * Disable local interrupts to prevent the grace-period
-		 * detection state machine from seeing us half-done.
-		 * NMIs can still occur, of course, and might themselves
-		 * contain rcu_read_lock() and rcu_read_unlock().
-		 */
-
-		local_irq_save(flags);
-
-		/*
-		 * Outermost nesting of rcu_read_unlock(), so we must
-		 * decrement the current counter for the current CPU.
-		 * This must be done carefully, because NMIs can
-		 * occur at any point in this code, and any rcu_read_lock()
-		 * and rcu_read_unlock() pairs in the NMI handlers
-		 * must interact non-destructively with this code.
-		 * Lots of volatile casts, and -very- careful ordering.
-		 *
-		 * Changes to this code, including this one, must be
-		 * inspected, validated, and tested extremely carefully!!!
-		 */
-
-		/*
-		 * First, pick up the index.
-		 */
-
-		idx = ACCESS_ONCE(t->rcu_flipctr_idx);
-
-		/*
-		 * Now that we have fetched the counter index, it is
-		 * safe to decrement the per-task RCU nesting counter.
-		 * After this, any interrupts or NMIs will increment and
-		 * decrement the per-CPU counters.
-		 */
-		ACCESS_ONCE(t->rcu_read_lock_nesting) = nesting - 1;
-
-		/*
-		 * It is now safe to decrement this task's nesting count.
-		 * NMIs that occur after this statement will route their
-		 * rcu_read_lock() calls through this "else" clause, and
-		 * will thus start incrementing the per-CPU counter on
-		 * their own.  They will also clobber ->rcu_flipctr_idx,
-		 * but that is OK, since we have already fetched it.
-		 */
-
-		ACCESS_ONCE(RCU_DATA_ME()->rcu_flipctr[idx])--;
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-
-/*
- * If a global counter flip has occurred since the last time that we
- * advanced callbacks, advance them.  Hardware interrupts must be
- * disabled when calling this function.
- */
-static void __rcu_advance_callbacks(struct rcu_data *rdp)
-{
-	int cpu;
-	int i;
-	int wlc = 0;
-
-	if (rdp->completed != rcu_ctrlblk.completed) {
-		if (rdp->waitlist[GP_STAGES - 1] != NULL) {
-			*rdp->donetail = rdp->waitlist[GP_STAGES - 1];
-			rdp->donetail = rdp->waittail[GP_STAGES - 1];
-			RCU_TRACE_RDP(rcupreempt_trace_move2done, rdp);
-		}
-		for (i = GP_STAGES - 2; i >= 0; i--) {
-			if (rdp->waitlist[i] != NULL) {
-				rdp->waitlist[i + 1] = rdp->waitlist[i];
-				rdp->waittail[i + 1] = rdp->waittail[i];
-				wlc++;
-			} else {
-				rdp->waitlist[i + 1] = NULL;
-				rdp->waittail[i + 1] =
-					&rdp->waitlist[i + 1];
-			}
-		}
-		if (rdp->nextlist != NULL) {
-			rdp->waitlist[0] = rdp->nextlist;
-			rdp->waittail[0] = rdp->nexttail;
-			wlc++;
-			rdp->nextlist = NULL;
-			rdp->nexttail = &rdp->nextlist;
-			RCU_TRACE_RDP(rcupreempt_trace_move2wait, rdp);
-		} else {
-			rdp->waitlist[0] = NULL;
-			rdp->waittail[0] = &rdp->waitlist[0];
-		}
-		rdp->waitlistcount = wlc;
-		rdp->completed = rcu_ctrlblk.completed;
-	}
-
-	/*
-	 * Check to see if this CPU needs to report that it has seen
-	 * the most recent counter flip, thereby declaring that all
-	 * subsequent rcu_read_lock() invocations will respect this flip.
-	 */
-
-	cpu = raw_smp_processor_id();
-	if (per_cpu(rcu_flip_flag, cpu) == rcu_flipped) {
-		smp_mb();  /* Subsequent counter accesses must see new value */
-		per_cpu(rcu_flip_flag, cpu) = rcu_flip_seen;
-		smp_mb();  /* Subsequent RCU read-side critical sections */
-			   /*  seen -after- acknowledgement. */
-	}
-}
-
-#ifdef CONFIG_NO_HZ
-static DEFINE_PER_CPU(int, rcu_update_flag);
-
-/**
- * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
- *
- * If the CPU was idle with dynamic ticks active, this updates the
- * rcu_dyntick_sched.dynticks to let the RCU handling know that the
- * CPU is active.
- */
-void rcu_irq_enter(void)
-{
-	int cpu = smp_processor_id();
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	if (per_cpu(rcu_update_flag, cpu))
-		per_cpu(rcu_update_flag, cpu)++;
-
-	/*
-	 * Only update if we are coming from a stopped ticks mode
-	 * (rcu_dyntick_sched.dynticks is even).
-	 */
-	if (!in_interrupt() &&
-	    (rdssp->dynticks & 0x1) == 0) {
-		/*
-		 * The following might seem like we could have a race
-		 * with NMI/SMIs. But this really isn't a problem.
-		 * Here we do a read/modify/write, and the race happens
-		 * when an NMI/SMI comes in after the read and before
-		 * the write. But NMI/SMIs will increment this counter
-		 * twice before returning, so the zero bit will not
-		 * be corrupted by the NMI/SMI which is the most important
-		 * part.
-		 *
-		 * The only thing is that we would bring back the counter
-		 * to a postion that it was in during the NMI/SMI.
-		 * But the zero bit would be set, so the rest of the
-		 * counter would again be ignored.
-		 *
-		 * On return from the IRQ, the counter may have the zero
-		 * bit be 0 and the counter the same as the return from
-		 * the NMI/SMI. If the state machine was so unlucky to
-		 * see that, it still doesn't matter, since all
-		 * RCU read-side critical sections on this CPU would
-		 * have already completed.
-		 */
-		rdssp->dynticks++;
-		/*
-		 * The following memory barrier ensures that any
-		 * rcu_read_lock() primitives in the irq handler
-		 * are seen by other CPUs to follow the above
-		 * increment to rcu_dyntick_sched.dynticks. This is
-		 * required in order for other CPUs to correctly
-		 * determine when it is safe to advance the RCU
-		 * grace-period state machine.
-		 */
-		smp_mb(); /* see above block comment. */
-		/*
-		 * Since we can't determine the dynamic tick mode from
-		 * the rcu_dyntick_sched.dynticks after this routine,
-		 * we use a second flag to acknowledge that we came
-		 * from an idle state with ticks stopped.
-		 */
-		per_cpu(rcu_update_flag, cpu)++;
-		/*
-		 * If we take an NMI/SMI now, they will also increment
-		 * the rcu_update_flag, and will not update the
-		 * rcu_dyntick_sched.dynticks on exit. That is for
-		 * this IRQ to do.
-		 */
-	}
-}
-
-/**
- * rcu_irq_exit - Called from exiting Hard irq context.
- *
- * If the CPU was idle with dynamic ticks active, update the
- * rcu_dyntick_sched.dynticks to put let the RCU handling be
- * aware that the CPU is going back to idle with no ticks.
- */
-void rcu_irq_exit(void)
-{
-	int cpu = smp_processor_id();
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	/*
-	 * rcu_update_flag is set if we interrupted the CPU
-	 * when it was idle with ticks stopped.
-	 * Once this occurs, we keep track of interrupt nesting
-	 * because a NMI/SMI could also come in, and we still
-	 * only want the IRQ that started the increment of the
-	 * rcu_dyntick_sched.dynticks to be the one that modifies
-	 * it on exit.
-	 */
-	if (per_cpu(rcu_update_flag, cpu)) {
-		if (--per_cpu(rcu_update_flag, cpu))
-			return;
-
-		/* This must match the interrupt nesting */
-		WARN_ON(in_interrupt());
-
-		/*
-		 * If an NMI/SMI happens now we are still
-		 * protected by the rcu_dyntick_sched.dynticks being odd.
-		 */
-
-		/*
-		 * The following memory barrier ensures that any
-		 * rcu_read_unlock() primitives in the irq handler
-		 * are seen by other CPUs to preceed the following
-		 * increment to rcu_dyntick_sched.dynticks. This
-		 * is required in order for other CPUs to determine
-		 * when it is safe to advance the RCU grace-period
-		 * state machine.
-		 */
-		smp_mb(); /* see above block comment. */
-		rdssp->dynticks++;
-		WARN_ON(rdssp->dynticks & 0x1);
-	}
-}
-
-void rcu_nmi_enter(void)
-{
-	rcu_irq_enter();
-}
-
-void rcu_nmi_exit(void)
-{
-	rcu_irq_exit();
-}
-
-static void dyntick_save_progress_counter(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->dynticks_snap = rdssp->dynticks;
-}
-
-static inline int
-rcu_try_flip_waitack_needed(int cpu)
-{
-	long curr;
-	long snap;
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	curr = rdssp->dynticks;
-	snap = rdssp->dynticks_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
-
-	/*
-	 * If the CPU remained in dynticks mode for the entire time
-	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
-	 * then it cannot be in the middle of an rcu_read_lock(), so
-	 * the next rcu_read_lock() it executes must use the new value
-	 * of the counter.  So we can safely pretend that this CPU
-	 * already acknowledged the counter.
-	 */
-
-	if ((curr == snap) && ((curr & 0x1) == 0))
-		return 0;
-
-	/*
-	 * If the CPU passed through or entered a dynticks idle phase with
-	 * no active irq handlers, then, as above, we can safely pretend
-	 * that this CPU already acknowledged the counter.
-	 */
-
-	if ((curr - snap) > 2 || (curr & 0x1) == 0)
-		return 0;
-
-	/* We need this CPU to explicitly acknowledge the counter flip. */
-
-	return 1;
-}
-
-static inline int
-rcu_try_flip_waitmb_needed(int cpu)
-{
-	long curr;
-	long snap;
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	curr = rdssp->dynticks;
-	snap = rdssp->dynticks_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
-
-	/*
-	 * If the CPU remained in dynticks mode for the entire time
-	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
-	 * then it cannot have executed an RCU read-side critical section
-	 * during that time, so there is no need for it to execute a
-	 * memory barrier.
-	 */
-
-	if ((curr == snap) && ((curr & 0x1) == 0))
-		return 0;
-
-	/*
-	 * If the CPU either entered or exited an outermost interrupt,
-	 * SMI, NMI, or whatever handler, then we know that it executed
-	 * a memory barrier when doing so.  So we don't need another one.
-	 */
-	if (curr != snap)
-		return 0;
-
-	/* We need the CPU to execute a memory barrier. */
-
-	return 1;
-}
-
-static void dyntick_save_progress_counter_sched(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->sched_dynticks_snap = rdssp->dynticks;
-}
-
-static int rcu_qsctr_inc_needed_dyntick(int cpu)
-{
-	long curr;
-	long snap;
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	curr = rdssp->dynticks;
-	snap = rdssp->sched_dynticks_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
-
-	/*
-	 * If the CPU remained in dynticks mode for the entire time
-	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
-	 * then it cannot be in the middle of an rcu_read_lock(), so
-	 * the next rcu_read_lock() it executes must use the new value
-	 * of the counter.  Therefore, this CPU has been in a quiescent
-	 * state the entire time, and we don't need to wait for it.
-	 */
-
-	if ((curr == snap) && ((curr & 0x1) == 0))
-		return 0;
-
-	/*
-	 * If the CPU passed through or entered a dynticks idle phase with
-	 * no active irq handlers, then, as above, this CPU has already
-	 * passed through a quiescent state.
-	 */
-
-	if ((curr - snap) > 2 || (snap & 0x1) == 0)
-		return 0;
-
-	/* We need this CPU to go through a quiescent state. */
-
-	return 1;
-}
-
-#else /* !CONFIG_NO_HZ */
-
-# define dyntick_save_progress_counter(cpu)		do { } while (0)
-# define rcu_try_flip_waitack_needed(cpu)		(1)
-# define rcu_try_flip_waitmb_needed(cpu)		(1)
-
-# define dyntick_save_progress_counter_sched(cpu)	do { } while (0)
-# define rcu_qsctr_inc_needed_dyntick(cpu)		(1)
-
-#endif /* CONFIG_NO_HZ */
-
-static void save_qsctr_sched(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->sched_qs_snap = rdssp->sched_qs;
-}
-
-static inline int rcu_qsctr_inc_needed(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	/*
-	 * If there has been a quiescent state, no more need to wait
-	 * on this CPU.
-	 */
-
-	if (rdssp->sched_qs != rdssp->sched_qs_snap) {
-		smp_mb(); /* force ordering with cpu entering schedule(). */
-		return 0;
-	}
-
-	/* We need this CPU to go through a quiescent state. */
-
-	return 1;
-}
-
-/*
- * Get here when RCU is idle.  Decide whether we need to
- * move out of idle state, and return non-zero if so.
- * "Straightforward" approach for the moment, might later
- * use callback-list lengths, grace-period duration, or
- * some such to determine when to exit idle state.
- * Might also need a pre-idle test that does not acquire
- * the lock, but let's get the simple case working first...
- */
-
-static int
-rcu_try_flip_idle(void)
-{
-	int cpu;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_i1);
-	if (!rcu_pending(smp_processor_id())) {
-		RCU_TRACE_ME(rcupreempt_trace_try_flip_ie1);
-		return 0;
-	}
-
-	/*
-	 * Do the flip.
-	 */
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_g1);
-	rcu_ctrlblk.completed++;  /* stands in for rcu_try_flip_g2 */
-
-	/*
-	 * Need a memory barrier so that other CPUs see the new
-	 * counter value before they see the subsequent change of all
-	 * the rcu_flip_flag instances to rcu_flipped.
-	 */
-
-	smp_mb();	/* see above block comment. */
-
-	/* Now ask each CPU for acknowledgement of the flip. */
-
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
-		per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
-		dyntick_save_progress_counter(cpu);
-	}
-
-	return 1;
-}
-
-/*
- * Wait for CPUs to acknowledge the flip.
- */
-
-static int
-rcu_try_flip_waitack(void)
-{
-	int cpu;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
-		if (rcu_try_flip_waitack_needed(cpu) &&
-		    per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
-			RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
-			return 0;
-		}
-
-	/*
-	 * Make sure our checks above don't bleed into subsequent
-	 * waiting for the sum of the counters to reach zero.
-	 */
-
-	smp_mb();	/* see above block comment. */
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_a2);
-	return 1;
-}
-
-/*
- * Wait for collective ``last'' counter to reach zero,
- * then tell all CPUs to do an end-of-grace-period memory barrier.
- */
-
-static int
-rcu_try_flip_waitzero(void)
-{
-	int cpu;
-	int lastidx = !(rcu_ctrlblk.completed & 0x1);
-	int sum = 0;
-
-	/* Check to see if the sum of the "last" counters is zero. */
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
-		sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
-	if (sum != 0) {
-		RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
-		return 0;
-	}
-
-	/*
-	 * This ensures that the other CPUs see the call for
-	 * memory barriers -after- the sum to zero has been
-	 * detected here
-	 */
-	smp_mb();  /*  ^^^^^^^^^^^^ */
-
-	/* Call for a memory barrier from each CPU. */
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
-		per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
-		dyntick_save_progress_counter(cpu);
-	}
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_z2);
-	return 1;
-}
-
-/*
- * Wait for all CPUs to do their end-of-grace-period memory barrier.
- * Return 0 once all CPUs have done so.
- */
-
-static int
-rcu_try_flip_waitmb(void)
-{
-	int cpu;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
-		if (rcu_try_flip_waitmb_needed(cpu) &&
-		    per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
-			RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
-			return 0;
-		}
-
-	smp_mb(); /* Ensure that the above checks precede any following flip. */
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_m2);
-	return 1;
-}
-
-/*
- * Attempt a single flip of the counters.  Remember, a single flip does
- * -not- constitute a grace period.  Instead, the interval between
- * at least GP_STAGES consecutive flips is a grace period.
- *
- * If anyone is nuts enough to run this CONFIG_PREEMPT_RCU implementation
- * on a large SMP, they might want to use a hierarchical organization of
- * the per-CPU-counter pairs.
- */
-static void rcu_try_flip(void)
-{
-	unsigned long flags;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_1);
-	if (unlikely(!spin_trylock_irqsave(&rcu_ctrlblk.fliplock, flags))) {
-		RCU_TRACE_ME(rcupreempt_trace_try_flip_e1);
-		return;
-	}
-
-	/*
-	 * Take the next transition(s) through the RCU grace-period
-	 * flip-counter state machine.
-	 */
-
-	switch (rcu_ctrlblk.rcu_try_flip_state) {
-	case rcu_try_flip_idle_state:
-		if (rcu_try_flip_idle())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_waitack_state;
-		break;
-	case rcu_try_flip_waitack_state:
-		if (rcu_try_flip_waitack())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_waitzero_state;
-		break;
-	case rcu_try_flip_waitzero_state:
-		if (rcu_try_flip_waitzero())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_waitmb_state;
-		break;
-	case rcu_try_flip_waitmb_state:
-		if (rcu_try_flip_waitmb())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_idle_state;
-	}
-	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
-}
-
-/*
- * Check to see if this CPU needs to do a memory barrier in order to
- * ensure that any prior RCU read-side critical sections have committed
- * their counter manipulations and critical-section memory references
- * before declaring the grace period to be completed.
- */
-static void rcu_check_mb(int cpu)
-{
-	if (per_cpu(rcu_mb_flag, cpu) == rcu_mb_needed) {
-		smp_mb();  /* Ensure RCU read-side accesses are visible. */
-		per_cpu(rcu_mb_flag, cpu) = rcu_mb_done;
-	}
-}
-
-void rcu_check_callbacks(int cpu, int user)
-{
-	unsigned long flags;
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	/*
-	 * If this CPU took its interrupt from user mode or from the
-	 * idle loop, and this is not a nested interrupt, then
-	 * this CPU has to have exited all prior preept-disable
-	 * sections of code.  So increment the counter to note this.
-	 *
-	 * The memory barrier is needed to handle the case where
-	 * writes from a preempt-disable section of code get reordered
-	 * into schedule() by this CPU's write buffer.  So the memory
-	 * barrier makes sure that the rcu_qsctr_inc() is seen by other
-	 * CPUs to happen after any such write.
-	 */
-
-	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-	     hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
-		smp_mb();	/* Guard against aggressive schedule(). */
-	     	rcu_qsctr_inc(cpu);
-	}
-
-	rcu_check_mb(cpu);
-	if (rcu_ctrlblk.completed == rdp->completed)
-		rcu_try_flip();
-	spin_lock_irqsave(&rdp->lock, flags);
-	RCU_TRACE_RDP(rcupreempt_trace_check_callbacks, rdp);
-	__rcu_advance_callbacks(rdp);
-	if (rdp->donelist == NULL) {
-		spin_unlock_irqrestore(&rdp->lock, flags);
-	} else {
-		spin_unlock_irqrestore(&rdp->lock, flags);
-		raise_softirq(RCU_SOFTIRQ);
-	}
-}
-
-/*
- * Needed by dynticks, to make sure all RCU processing has finished
- * when we go idle:
- */
-void rcu_advance_callbacks(int cpu, int user)
-{
-	unsigned long flags;
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	if (rcu_ctrlblk.completed == rdp->completed) {
-		rcu_try_flip();
-		if (rcu_ctrlblk.completed == rdp->completed)
-			return;
-	}
-	spin_lock_irqsave(&rdp->lock, flags);
-	RCU_TRACE_RDP(rcupreempt_trace_check_callbacks, rdp);
-	__rcu_advance_callbacks(rdp);
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-#define rcu_offline_cpu_enqueue(srclist, srctail, dstlist, dsttail) do { \
-		*dsttail = srclist; \
-		if (srclist != NULL) { \
-			dsttail = srctail; \
-			srclist = NULL; \
-			srctail = &srclist;\
-		} \
-	} while (0)
-
-void rcu_offline_cpu(int cpu)
-{
-	int i;
-	struct rcu_head *list = NULL;
-	unsigned long flags;
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-	struct rcu_head *schedlist = NULL;
-	struct rcu_head **schedtail = &schedlist;
-	struct rcu_head **tail = &list;
-
-	/*
-	 * Remove all callbacks from the newly dead CPU, retaining order.
-	 * Otherwise rcu_barrier() will fail
-	 */
-
-	spin_lock_irqsave(&rdp->lock, flags);
-	rcu_offline_cpu_enqueue(rdp->donelist, rdp->donetail, list, tail);
-	for (i = GP_STAGES - 1; i >= 0; i--)
-		rcu_offline_cpu_enqueue(rdp->waitlist[i], rdp->waittail[i],
-						list, tail);
-	rcu_offline_cpu_enqueue(rdp->nextlist, rdp->nexttail, list, tail);
-	rcu_offline_cpu_enqueue(rdp->waitschedlist, rdp->waitschedtail,
-				schedlist, schedtail);
-	rcu_offline_cpu_enqueue(rdp->nextschedlist, rdp->nextschedtail,
-				schedlist, schedtail);
-	rdp->rcu_sched_sleeping = 0;
-	spin_unlock_irqrestore(&rdp->lock, flags);
-	rdp->waitlistcount = 0;
-
-	/* Disengage the newly dead CPU from the grace-period computation. */
-
-	spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
-	rcu_check_mb(cpu);
-	if (per_cpu(rcu_flip_flag, cpu) == rcu_flipped) {
-		smp_mb();  /* Subsequent counter accesses must see new value */
-		per_cpu(rcu_flip_flag, cpu) = rcu_flip_seen;
-		smp_mb();  /* Subsequent RCU read-side critical sections */
-			   /*  seen -after- acknowledgement. */
-	}
-
-	RCU_DATA_ME()->rcu_flipctr[0] += RCU_DATA_CPU(cpu)->rcu_flipctr[0];
-	RCU_DATA_ME()->rcu_flipctr[1] += RCU_DATA_CPU(cpu)->rcu_flipctr[1];
-
-	RCU_DATA_CPU(cpu)->rcu_flipctr[0] = 0;
-	RCU_DATA_CPU(cpu)->rcu_flipctr[1] = 0;
-
-	cpumask_clear_cpu(cpu, to_cpumask(rcu_cpu_online_map));
-
-	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
-
-	/*
-	 * Place the removed callbacks on the current CPU's queue.
-	 * Make them all start a new grace period: simple approach,
-	 * in theory could starve a given set of callbacks, but
-	 * you would need to be doing some serious CPU hotplugging
-	 * to make this happen.  If this becomes a problem, adding
-	 * a synchronize_rcu() to the hotplug path would be a simple
-	 * fix.
-	 */
-
-	local_irq_save(flags);  /* disable preempt till we know what lock. */
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	*rdp->nexttail = list;
-	if (list)
-		rdp->nexttail = tail;
-	*rdp->nextschedtail = schedlist;
-	if (schedlist)
-		rdp->nextschedtail = schedtail;
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-void rcu_offline_cpu(int cpu)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
-void __cpuinit rcu_online_cpu(int cpu)
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-
-	spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
-	cpumask_set_cpu(cpu, to_cpumask(rcu_cpu_online_map));
-	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
-
-	/*
-	 * The rcu_sched grace-period processing might have bypassed
-	 * this CPU, given that it was not in the rcu_cpu_online_map
-	 * when the grace-period scan started.  This means that the
-	 * grace-period task might sleep.  So make sure that if this
-	 * should happen, the first callback posted to this CPU will
-	 * wake up the grace-period task if need be.
-	 */
-
-	rdp = RCU_DATA_CPU(cpu);
-	spin_lock_irqsave(&rdp->lock, flags);
-	rdp->rcu_sched_sleeping = 1;
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-
-static void rcu_process_callbacks(struct softirq_action *unused)
-{
-	unsigned long flags;
-	struct rcu_head *next, *list;
-	struct rcu_data *rdp;
-
-	local_irq_save(flags);
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	list = rdp->donelist;
-	if (list == NULL) {
-		spin_unlock_irqrestore(&rdp->lock, flags);
-		return;
-	}
-	rdp->donelist = NULL;
-	rdp->donetail = &rdp->donelist;
-	RCU_TRACE_RDP(rcupreempt_trace_done_remove, rdp);
-	spin_unlock_irqrestore(&rdp->lock, flags);
-	while (list) {
-		next = list->next;
-		list->func(list);
-		list = next;
-		RCU_TRACE_ME(rcupreempt_trace_invoke);
-	}
-}
-
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-
-	head->func = func;
-	head->next = NULL;
-	local_irq_save(flags);
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	__rcu_advance_callbacks(rdp);
-	*rdp->nexttail = head;
-	rdp->nexttail = &head->next;
-	RCU_TRACE_RDP(rcupreempt_trace_next_add, rdp);
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-	int wake_gp = 0;
-
-	head->func = func;
-	head->next = NULL;
-	local_irq_save(flags);
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	*rdp->nextschedtail = head;
-	rdp->nextschedtail = &head->next;
-	if (rdp->rcu_sched_sleeping) {
-
-		/* Grace-period processing might be sleeping... */
-
-		rdp->rcu_sched_sleeping = 0;
-		wake_gp = 1;
-	}
-	spin_unlock_irqrestore(&rdp->lock, flags);
-	if (wake_gp) {
-
-		/* Wake up grace-period processing, unless someone beat us. */
-
-		spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
-		if (rcu_ctrlblk.sched_sleep != rcu_sched_sleeping)
-			wake_gp = 0;
-		rcu_ctrlblk.sched_sleep = rcu_sched_not_sleeping;
-		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		if (wake_gp)
-			wake_up_interruptible(&rcu_ctrlblk.sched_wq);
-	}
-}
-EXPORT_SYMBOL_GPL(call_rcu_sched);
-
-/*
- * Wait until all currently running preempt_disable() code segments
- * (including hardware-irq-disable segments) complete.  Note that
- * in -rt this does -not- necessarily result in all currently executing
- * interrupt -handlers- having completed.
- */
-void __synchronize_sched(void)
-{
-	struct rcu_synchronize rcu;
-
-	if (num_online_cpus() == 1)
-		return;  /* blocking is gp if only one CPU! */
-
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	call_rcu_sched(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(__synchronize_sched);
-
-/*
- * kthread function that manages call_rcu_sched grace periods.
- */
-static int rcu_sched_grace_period(void *arg)
-{
-	int couldsleep;		/* might sleep after current pass. */
-	int couldsleepnext = 0; /* might sleep after next pass. */
-	int cpu;
-	unsigned long flags;
-	struct rcu_data *rdp;
-	int ret;
-
-	/*
-	 * Each pass through the following loop handles one
-	 * rcu_sched grace period cycle.
-	 */
-	do {
-		/* Save each CPU's current state. */
-
-		for_each_online_cpu(cpu) {
-			dyntick_save_progress_counter_sched(cpu);
-			save_qsctr_sched(cpu);
-		}
-
-		/*
-		 * Sleep for about an RCU grace-period's worth to
-		 * allow better batching and to consume less CPU.
-		 */
-		schedule_timeout_interruptible(RCU_SCHED_BATCH_TIME);
-
-		/*
-		 * If there was nothing to do last time, prepare to
-		 * sleep at the end of the current grace period cycle.
-		 */
-		couldsleep = couldsleepnext;
-		couldsleepnext = 1;
-		if (couldsleep) {
-			spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
-			rcu_ctrlblk.sched_sleep = rcu_sched_sleep_prep;
-			spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		}
-
-		/*
-		 * Wait on each CPU in turn to have either visited
-		 * a quiescent state or been in dynticks-idle mode.
-		 */
-		for_each_online_cpu(cpu) {
-			while (rcu_qsctr_inc_needed(cpu) &&
-			       rcu_qsctr_inc_needed_dyntick(cpu)) {
-				/* resched_cpu(cpu); @@@ */
-				schedule_timeout_interruptible(1);
-			}
-		}
-
-		/* Advance callbacks for each CPU.  */
-
-		for_each_online_cpu(cpu) {
-
-			rdp = RCU_DATA_CPU(cpu);
-			spin_lock_irqsave(&rdp->lock, flags);
-
-			/*
-			 * We are running on this CPU irq-disabled, so no
-			 * CPU can go offline until we re-enable irqs.
-			 * The current CPU might have already gone
-			 * offline (between the for_each_offline_cpu and
-			 * the spin_lock_irqsave), but in that case all its
-			 * callback lists will be empty, so no harm done.
-			 *
-			 * Advance the callbacks!  We share normal RCU's
-			 * donelist, since callbacks are invoked the
-			 * same way in either case.
-			 */
-			if (rdp->waitschedlist != NULL) {
-				*rdp->donetail = rdp->waitschedlist;
-				rdp->donetail = rdp->waitschedtail;
-
-				/*
-				 * Next rcu_check_callbacks() will
-				 * do the required raise_softirq().
-				 */
-			}
-			if (rdp->nextschedlist != NULL) {
-				rdp->waitschedlist = rdp->nextschedlist;
-				rdp->waitschedtail = rdp->nextschedtail;
-				couldsleep = 0;
-				couldsleepnext = 0;
-			} else {
-				rdp->waitschedlist = NULL;
-				rdp->waitschedtail = &rdp->waitschedlist;
-			}
-			rdp->nextschedlist = NULL;
-			rdp->nextschedtail = &rdp->nextschedlist;
-
-			/* Mark sleep intention. */
-
-			rdp->rcu_sched_sleeping = couldsleep;
-
-			spin_unlock_irqrestore(&rdp->lock, flags);
-		}
-
-		/* If we saw callbacks on the last scan, go deal with them. */
-
-		if (!couldsleep)
-			continue;
-
-		/* Attempt to block... */
-
-		spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
-		if (rcu_ctrlblk.sched_sleep != rcu_sched_sleep_prep) {
-
-			/*
-			 * Someone posted a callback after we scanned.
-			 * Go take care of it.
-			 */
-			spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-			couldsleepnext = 0;
-			continue;
-		}
-
-		/* Block until the next person posts a callback. */
-
-		rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
-		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		ret = 0; /* unused */
-		__wait_event_interruptible(rcu_ctrlblk.sched_wq,
-			rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
-			ret);
-
-		couldsleepnext = 0;
-
-	} while (!kthread_should_stop());
-
-	return (0);
-}
-
-/*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so.  Assumes that notifiers would take care of handling any
- * outstanding requests from the RCU core.
- *
- * This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
- */
-int rcu_needs_cpu(int cpu)
-{
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	return (rdp->donelist != NULL ||
-		!!rdp->waitlistcount ||
-		rdp->nextlist != NULL ||
-		rdp->nextschedlist != NULL ||
-		rdp->waitschedlist != NULL);
-}
-
-int rcu_pending(int cpu)
-{
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	/* The CPU has at least one callback queued somewhere. */
-
-	if (rdp->donelist != NULL ||
-	    !!rdp->waitlistcount ||
-	    rdp->nextlist != NULL ||
-	    rdp->nextschedlist != NULL ||
-	    rdp->waitschedlist != NULL)
-		return 1;
-
-	/* The RCU core needs an acknowledgement from this CPU. */
-
-	if ((per_cpu(rcu_flip_flag, cpu) == rcu_flipped) ||
-	    (per_cpu(rcu_mb_flag, cpu) == rcu_mb_needed))
-		return 1;
-
-	/* This CPU has fallen behind the global grace-period number. */
-
-	if (rdp->completed != rcu_ctrlblk.completed)
-		return 1;
-
-	/* Nothing needed from this CPU. */
-
-	return 0;
-}
-
-static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		rcu_offline_cpu(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata rcu_nb = {
-	.notifier_call = rcu_cpu_notify,
-};
-
-void __init __rcu_init(void)
-{
-	int cpu;
-	int i;
-	struct rcu_data *rdp;
-
-	printk(KERN_NOTICE "Preemptible RCU implementation.\n");
-	for_each_possible_cpu(cpu) {
-		rdp = RCU_DATA_CPU(cpu);
-		spin_lock_init(&rdp->lock);
-		rdp->completed = 0;
-		rdp->waitlistcount = 0;
-		rdp->nextlist = NULL;
-		rdp->nexttail = &rdp->nextlist;
-		for (i = 0; i < GP_STAGES; i++) {
-			rdp->waitlist[i] = NULL;
-			rdp->waittail[i] = &rdp->waitlist[i];
-		}
-		rdp->donelist = NULL;
-		rdp->donetail = &rdp->donelist;
-		rdp->rcu_flipctr[0] = 0;
-		rdp->rcu_flipctr[1] = 0;
-		rdp->nextschedlist = NULL;
-		rdp->nextschedtail = &rdp->nextschedlist;
-		rdp->waitschedlist = NULL;
-		rdp->waitschedtail = &rdp->waitschedlist;
-		rdp->rcu_sched_sleeping = 0;
-	}
-	register_cpu_notifier(&rcu_nb);
-
-	/*
-	 * We don't need protection against CPU-Hotplug here
-	 * since
-	 * a) If a CPU comes online while we are iterating over the
-	 *    cpu_online_mask below, we would only end up making a
-	 *    duplicate call to rcu_online_cpu() which sets the corresponding
-	 *    CPU's mask in the rcu_cpu_online_map.
-	 *
-	 * b) A CPU cannot go offline at this point in time since the user
-	 *    does not have access to the sysfs interface, nor do we
-	 *    suspend the system.
-	 */
-	for_each_online_cpu(cpu)
-		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,	(void *)(long) cpu);
-
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
-}
-
-/*
- * Late-boot-time RCU initialization that must wait until after scheduler
- * has been initialized.
- */
-void __init rcu_init_sched(void)
-{
-	rcu_sched_grace_period_task = kthread_run(rcu_sched_grace_period,
-						  NULL,
-						  "rcu_sched_grace_period");
-	WARN_ON(IS_ERR(rcu_sched_grace_period_task));
-}
-
-#ifdef CONFIG_RCU_TRACE
-long *rcupreempt_flipctr(int cpu)
-{
-	return &RCU_DATA_CPU(cpu)->rcu_flipctr[0];
-}
-EXPORT_SYMBOL_GPL(rcupreempt_flipctr);
-
-int rcupreempt_flip_flag(int cpu)
-{
-	return per_cpu(rcu_flip_flag, cpu);
-}
-EXPORT_SYMBOL_GPL(rcupreempt_flip_flag);
-
-int rcupreempt_mb_flag(int cpu)
-{
-	return per_cpu(rcu_mb_flag, cpu);
-}
-EXPORT_SYMBOL_GPL(rcupreempt_mb_flag);
-
-char *rcupreempt_try_flip_state_name(void)
-{
-	return rcu_try_flip_state_names[rcu_ctrlblk.rcu_try_flip_state];
-}
-EXPORT_SYMBOL_GPL(rcupreempt_try_flip_state_name);
-
-struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu)
-{
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	return &rdp->trace;
-}
-EXPORT_SYMBOL_GPL(rcupreempt_trace_cpu);
-
-#endif /* #ifdef RCU_TRACE */
diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c
deleted file mode 100644
index 7c2665cac172..000000000000
--- a/kernel/rcupreempt_trace.c
+++ /dev/null
@@ -1,334 +0,0 @@
-/*
- * Read-Copy Update tracing for realtime implementation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright IBM Corporation, 2006
- *
- * Papers:  http://www.rdrop.com/users/paulmck/RCU
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU/ *.txt
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/mutex.h>
-#include <linux/rcupreempt_trace.h>
-#include <linux/debugfs.h>
-
-static struct mutex rcupreempt_trace_mutex;
-static char *rcupreempt_trace_buf;
-#define RCUPREEMPT_TRACE_BUF_SIZE 4096
-
-void rcupreempt_trace_move2done(struct rcupreempt_trace *trace)
-{
-	trace->done_length += trace->wait_length;
-	trace->done_add += trace->wait_length;
-	trace->wait_length = 0;
-}
-void rcupreempt_trace_move2wait(struct rcupreempt_trace *trace)
-{
-	trace->wait_length += trace->next_length;
-	trace->wait_add += trace->next_length;
-	trace->next_length = 0;
-}
-void rcupreempt_trace_try_flip_1(struct rcupreempt_trace *trace)
-{
-	atomic_inc(&trace->rcu_try_flip_1);
-}
-void rcupreempt_trace_try_flip_e1(struct rcupreempt_trace *trace)
-{
-	atomic_inc(&trace->rcu_try_flip_e1);
-}
-void rcupreempt_trace_try_flip_i1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_i1++;
-}
-void rcupreempt_trace_try_flip_ie1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_ie1++;
-}
-void rcupreempt_trace_try_flip_g1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_g1++;
-}
-void rcupreempt_trace_try_flip_a1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_a1++;
-}
-void rcupreempt_trace_try_flip_ae1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_ae1++;
-}
-void rcupreempt_trace_try_flip_a2(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_a2++;
-}
-void rcupreempt_trace_try_flip_z1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_z1++;
-}
-void rcupreempt_trace_try_flip_ze1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_ze1++;
-}
-void rcupreempt_trace_try_flip_z2(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_z2++;
-}
-void rcupreempt_trace_try_flip_m1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_m1++;
-}
-void rcupreempt_trace_try_flip_me1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_me1++;
-}
-void rcupreempt_trace_try_flip_m2(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_m2++;
-}
-void rcupreempt_trace_check_callbacks(struct rcupreempt_trace *trace)
-{
-	trace->rcu_check_callbacks++;
-}
-void rcupreempt_trace_done_remove(struct rcupreempt_trace *trace)
-{
-	trace->done_remove += trace->done_length;
-	trace->done_length = 0;
-}
-void rcupreempt_trace_invoke(struct rcupreempt_trace *trace)
-{
-	atomic_inc(&trace->done_invoked);
-}
-void rcupreempt_trace_next_add(struct rcupreempt_trace *trace)
-{
-	trace->next_add++;
-	trace->next_length++;
-}
-
-static void rcupreempt_trace_sum(struct rcupreempt_trace *sp)
-{
-	struct rcupreempt_trace *cp;
-	int cpu;
-
-	memset(sp, 0, sizeof(*sp));
-	for_each_possible_cpu(cpu) {
-		cp = rcupreempt_trace_cpu(cpu);
-		sp->next_length += cp->next_length;
-		sp->next_add += cp->next_add;
-		sp->wait_length += cp->wait_length;
-		sp->wait_add += cp->wait_add;
-		sp->done_length += cp->done_length;
-		sp->done_add += cp->done_add;
-		sp->done_remove += cp->done_remove;
-		atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked);
-		sp->rcu_check_callbacks += cp->rcu_check_callbacks;
-		atomic_add(atomic_read(&cp->rcu_try_flip_1),
-			   &sp->rcu_try_flip_1);
-		atomic_add(atomic_read(&cp->rcu_try_flip_e1),
-			   &sp->rcu_try_flip_e1);
-		sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1;
-		sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1;
-		sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1;
-		sp->rcu_try_flip_a1 += cp->rcu_try_flip_a1;
-		sp->rcu_try_flip_ae1 += cp->rcu_try_flip_ae1;
-		sp->rcu_try_flip_a2 += cp->rcu_try_flip_a2;
-		sp->rcu_try_flip_z1 += cp->rcu_try_flip_z1;
-		sp->rcu_try_flip_ze1 += cp->rcu_try_flip_ze1;
-		sp->rcu_try_flip_z2 += cp->rcu_try_flip_z2;
-		sp->rcu_try_flip_m1 += cp->rcu_try_flip_m1;
-		sp->rcu_try_flip_me1 += cp->rcu_try_flip_me1;
-		sp->rcu_try_flip_m2 += cp->rcu_try_flip_m2;
-	}
-}
-
-static ssize_t rcustats_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	struct rcupreempt_trace trace;
-	ssize_t bcount;
-	int cnt = 0;
-
-	rcupreempt_trace_sum(&trace);
-	mutex_lock(&rcupreempt_trace_mutex);
-	snprintf(&rcupreempt_trace_buf[cnt], RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-		 "ggp=%ld rcc=%ld\n",
-		 rcu_batches_completed(),
-		 trace.rcu_check_callbacks);
-	snprintf(&rcupreempt_trace_buf[cnt], RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-		 "na=%ld nl=%ld wa=%ld wl=%ld da=%ld dl=%ld dr=%ld di=%d\n"
-		 "1=%d e1=%d i1=%ld ie1=%ld g1=%ld a1=%ld ae1=%ld a2=%ld\n"
-		 "z1=%ld ze1=%ld z2=%ld m1=%ld me1=%ld m2=%ld\n",
-
-		 trace.next_add, trace.next_length,
-		 trace.wait_add, trace.wait_length,
-		 trace.done_add, trace.done_length,
-		 trace.done_remove, atomic_read(&trace.done_invoked),
-		 atomic_read(&trace.rcu_try_flip_1),
-		 atomic_read(&trace.rcu_try_flip_e1),
-		 trace.rcu_try_flip_i1, trace.rcu_try_flip_ie1,
-		 trace.rcu_try_flip_g1,
-		 trace.rcu_try_flip_a1, trace.rcu_try_flip_ae1,
-			 trace.rcu_try_flip_a2,
-		 trace.rcu_try_flip_z1, trace.rcu_try_flip_ze1,
-			 trace.rcu_try_flip_z2,
-		 trace.rcu_try_flip_m1, trace.rcu_try_flip_me1,
-			trace.rcu_try_flip_m2);
-	bcount = simple_read_from_buffer(buffer, count, ppos,
-			rcupreempt_trace_buf, strlen(rcupreempt_trace_buf));
-	mutex_unlock(&rcupreempt_trace_mutex);
-	return bcount;
-}
-
-static ssize_t rcugp_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	long oldgp = rcu_batches_completed();
-	ssize_t bcount;
-
-	mutex_lock(&rcupreempt_trace_mutex);
-	synchronize_rcu();
-	snprintf(rcupreempt_trace_buf, RCUPREEMPT_TRACE_BUF_SIZE,
-		"oldggp=%ld  newggp=%ld\n", oldgp, rcu_batches_completed());
-	bcount = simple_read_from_buffer(buffer, count, ppos,
-			rcupreempt_trace_buf, strlen(rcupreempt_trace_buf));
-	mutex_unlock(&rcupreempt_trace_mutex);
-	return bcount;
-}
-
-static ssize_t rcuctrs_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	int cnt = 0;
-	int cpu;
-	int f = rcu_batches_completed() & 0x1;
-	ssize_t bcount;
-
-	mutex_lock(&rcupreempt_trace_mutex);
-
-	cnt += snprintf(&rcupreempt_trace_buf[cnt], RCUPREEMPT_TRACE_BUF_SIZE,
-				"CPU last cur F M\n");
-	for_each_online_cpu(cpu) {
-		long *flipctr = rcupreempt_flipctr(cpu);
-		cnt += snprintf(&rcupreempt_trace_buf[cnt],
-				RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-					"%3d %4ld %3ld %d %d\n",
-			       cpu,
-			       flipctr[!f],
-			       flipctr[f],
-			       rcupreempt_flip_flag(cpu),
-			       rcupreempt_mb_flag(cpu));
-	}
-	cnt += snprintf(&rcupreempt_trace_buf[cnt],
-			RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-			"ggp = %ld, state = %s\n",
-			rcu_batches_completed(),
-			rcupreempt_try_flip_state_name());
-	cnt += snprintf(&rcupreempt_trace_buf[cnt],
-			RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-			"\n");
-	bcount = simple_read_from_buffer(buffer, count, ppos,
-			rcupreempt_trace_buf, strlen(rcupreempt_trace_buf));
-	mutex_unlock(&rcupreempt_trace_mutex);
-	return bcount;
-}
-
-static struct file_operations rcustats_fops = {
-	.owner = THIS_MODULE,
-	.read = rcustats_read,
-};
-
-static struct file_operations rcugp_fops = {
-	.owner = THIS_MODULE,
-	.read = rcugp_read,
-};
-
-static struct file_operations rcuctrs_fops = {
-	.owner = THIS_MODULE,
-	.read = rcuctrs_read,
-};
-
-static struct dentry *rcudir, *statdir, *ctrsdir, *gpdir;
-static int rcupreempt_debugfs_init(void)
-{
-	rcudir = debugfs_create_dir("rcu", NULL);
-	if (!rcudir)
-		goto out;
-	statdir = debugfs_create_file("rcustats", 0444, rcudir,
-						NULL, &rcustats_fops);
-	if (!statdir)
-		goto free_out;
-
-	gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
-	if (!gpdir)
-		goto free_out;
-
-	ctrsdir = debugfs_create_file("rcuctrs", 0444, rcudir,
-						NULL, &rcuctrs_fops);
-	if (!ctrsdir)
-		goto free_out;
-	return 0;
-free_out:
-	if (statdir)
-		debugfs_remove(statdir);
-	if (gpdir)
-		debugfs_remove(gpdir);
-	debugfs_remove(rcudir);
-out:
-	return 1;
-}
-
-static int __init rcupreempt_trace_init(void)
-{
-	int ret;
-
-	mutex_init(&rcupreempt_trace_mutex);
-	rcupreempt_trace_buf = kmalloc(RCUPREEMPT_TRACE_BUF_SIZE, GFP_KERNEL);
-	if (!rcupreempt_trace_buf)
-		return 1;
-	ret = rcupreempt_debugfs_init();
-	if (ret)
-		kfree(rcupreempt_trace_buf);
-	return ret;
-}
-
-static void __exit rcupreempt_trace_cleanup(void)
-{
-	debugfs_remove(statdir);
-	debugfs_remove(gpdir);
-	debugfs_remove(ctrsdir);
-	debugfs_remove(rcudir);
-	kfree(rcupreempt_trace_buf);
-}
-
-
-module_init(rcupreempt_trace_init);
-module_exit(rcupreempt_trace_cleanup);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 9b4a975a4b4a..b33db539a8ad 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -257,14 +257,14 @@ struct rcu_torture_ops {
 	void (*init)(void);
 	void (*cleanup)(void);
 	int (*readlock)(void);
-	void (*readdelay)(struct rcu_random_state *rrsp);
+	void (*read_delay)(struct rcu_random_state *rrsp);
 	void (*readunlock)(int idx);
 	int (*completed)(void);
-	void (*deferredfree)(struct rcu_torture *p);
+	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*cb_barrier)(void);
 	int (*stats)(char *page);
-	int irqcapable;
+	int irq_capable;
 	char *name;
 };
 static struct rcu_torture_ops *cur_ops = NULL;
@@ -320,7 +320,7 @@ rcu_torture_cb(struct rcu_head *p)
 		rp->rtort_mbtest = 0;
 		rcu_torture_free(rp);
 	} else
-		cur_ops->deferredfree(rp);
+		cur_ops->deferred_free(rp);
 }
 
 static void rcu_torture_deferred_free(struct rcu_torture *p)
@@ -329,18 +329,18 @@ static void rcu_torture_deferred_free(struct rcu_torture *p)
 }
 
 static struct rcu_torture_ops rcu_ops = {
-	.init = NULL,
-	.cleanup = NULL,
-	.readlock = rcu_torture_read_lock,
-	.readdelay = rcu_read_delay,
-	.readunlock = rcu_torture_read_unlock,
-	.completed = rcu_torture_completed,
-	.deferredfree = rcu_torture_deferred_free,
-	.sync = synchronize_rcu,
-	.cb_barrier = rcu_barrier,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu"
+	.init		= NULL,
+	.cleanup	= NULL,
+	.readlock	= rcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= rcu_torture_read_unlock,
+	.completed	= rcu_torture_completed,
+	.deferred_free	= rcu_torture_deferred_free,
+	.sync		= synchronize_rcu,
+	.cb_barrier	= rcu_barrier,
+	.stats		= NULL,
+	.irq_capable 	= 1,
+	.name 		= "rcu"
 };
 
 static void rcu_sync_torture_deferred_free(struct rcu_torture *p)
@@ -370,18 +370,18 @@ static void rcu_sync_torture_init(void)
 }
 
 static struct rcu_torture_ops rcu_sync_ops = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = rcu_torture_read_lock,
-	.readdelay = rcu_read_delay,
-	.readunlock = rcu_torture_read_unlock,
-	.completed = rcu_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = synchronize_rcu,
-	.cb_barrier = NULL,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu_sync"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= rcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= rcu_torture_read_unlock,
+	.completed	= rcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= synchronize_rcu,
+	.cb_barrier	= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_sync"
 };
 
 /*
@@ -432,33 +432,33 @@ static void rcu_bh_torture_synchronize(void)
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
-	.init = NULL,
-	.cleanup = NULL,
-	.readlock = rcu_bh_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = rcu_bh_torture_read_unlock,
-	.completed = rcu_bh_torture_completed,
-	.deferredfree = rcu_bh_torture_deferred_free,
-	.sync = rcu_bh_torture_synchronize,
-	.cb_barrier = rcu_barrier_bh,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu_bh"
+	.init		= NULL,
+	.cleanup	= NULL,
+	.readlock	= rcu_bh_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_bh_torture_read_unlock,
+	.completed	= rcu_bh_torture_completed,
+	.deferred_free	= rcu_bh_torture_deferred_free,
+	.sync		= rcu_bh_torture_synchronize,
+	.cb_barrier	= rcu_barrier_bh,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_bh"
 };
 
 static struct rcu_torture_ops rcu_bh_sync_ops = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = rcu_bh_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = rcu_bh_torture_read_unlock,
-	.completed = rcu_bh_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = rcu_bh_torture_synchronize,
-	.cb_barrier = NULL,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu_bh_sync"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= rcu_bh_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_bh_torture_read_unlock,
+	.completed	= rcu_bh_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= rcu_bh_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_bh_sync"
 };
 
 /*
@@ -530,17 +530,17 @@ static int srcu_torture_stats(char *page)
 }
 
 static struct rcu_torture_ops srcu_ops = {
-	.init = srcu_torture_init,
-	.cleanup = srcu_torture_cleanup,
-	.readlock = srcu_torture_read_lock,
-	.readdelay = srcu_read_delay,
-	.readunlock = srcu_torture_read_unlock,
-	.completed = srcu_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = srcu_torture_synchronize,
-	.cb_barrier = NULL,
-	.stats = srcu_torture_stats,
-	.name = "srcu"
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu"
 };
 
 /*
@@ -574,32 +574,49 @@ static void sched_torture_synchronize(void)
 }
 
 static struct rcu_torture_ops sched_ops = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = sched_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = sched_torture_read_unlock,
-	.completed = sched_torture_completed,
-	.deferredfree = rcu_sched_torture_deferred_free,
-	.sync = sched_torture_synchronize,
-	.cb_barrier = rcu_barrier_sched,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "sched"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= sched_torture_completed,
+	.deferred_free	= rcu_sched_torture_deferred_free,
+	.sync		= sched_torture_synchronize,
+	.cb_barrier	= rcu_barrier_sched,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "sched"
 };
 
 static struct rcu_torture_ops sched_ops_sync = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = sched_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = sched_torture_read_unlock,
-	.completed = sched_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = sched_torture_synchronize,
-	.cb_barrier = NULL,
-	.stats = NULL,
-	.name = "sched_sync"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= sched_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= sched_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= NULL,
+	.name		= "sched_sync"
+};
+
+extern int rcu_expedited_torture_stats(char *page);
+
+static struct rcu_torture_ops sched_expedited_ops = {
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= sched_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= synchronize_sched_expedited,
+	.cb_barrier	= NULL,
+	.stats		= rcu_expedited_torture_stats,
+	.irq_capable	= 1,
+	.name		= "sched_expedited"
 };
 
 /*
@@ -635,7 +652,7 @@ rcu_torture_writer(void *arg)
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
 			old_rp->rtort_pipe_count++;
-			cur_ops->deferredfree(old_rp);
+			cur_ops->deferred_free(old_rp);
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
@@ -700,7 +717,7 @@ static void rcu_torture_timer(unsigned long unused)
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
 	spin_lock(&rand_lock);
-	cur_ops->readdelay(&rand);
+	cur_ops->read_delay(&rand);
 	n_rcu_torture_timers++;
 	spin_unlock(&rand_lock);
 	preempt_disable();
@@ -738,11 +755,11 @@ rcu_torture_reader(void *arg)
 
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
 	set_user_nice(current, 19);
-	if (irqreader && cur_ops->irqcapable)
+	if (irqreader && cur_ops->irq_capable)
 		setup_timer_on_stack(&t, rcu_torture_timer, 0);
 
 	do {
-		if (irqreader && cur_ops->irqcapable) {
+		if (irqreader && cur_ops->irq_capable) {
 			if (!timer_pending(&t))
 				mod_timer(&t, 1);
 		}
@@ -757,7 +774,7 @@ rcu_torture_reader(void *arg)
 		}
 		if (p->rtort_mbtest == 0)
 			atomic_inc(&n_rcu_torture_mberror);
-		cur_ops->readdelay(&rand);
+		cur_ops->read_delay(&rand);
 		preempt_disable();
 		pipe_count = p->rtort_pipe_count;
 		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
@@ -778,7 +795,7 @@ rcu_torture_reader(void *arg)
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
 	rcutorture_shutdown_absorb("rcu_torture_reader");
-	if (irqreader && cur_ops->irqcapable)
+	if (irqreader && cur_ops->irq_capable)
 		del_timer_sync(&t);
 	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
@@ -1078,6 +1095,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
+		  &sched_expedited_ops,
 		  &srcu_ops, &sched_ops, &sched_ops_sync, };
 
 	mutex_lock(&fullstop_mutex);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7717b95c2027..6b11b07cfe7f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -35,6 +35,7 @@
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/nmi.h>
 #include <asm/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
@@ -46,6 +47,8 @@
 #include <linux/mutex.h>
 #include <linux/time.h>
 
+#include "rcutree.h"
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
 struct lockdep_map rcu_lock_map =
@@ -72,30 +75,59 @@ EXPORT_SYMBOL_GPL(rcu_lock_map);
 	.n_force_qs_ngp = 0, \
 }
 
-struct rcu_state rcu_state = RCU_STATE_INITIALIZER(rcu_state);
-DEFINE_PER_CPU(struct rcu_data, rcu_data);
+struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+extern long rcu_batches_completed_sched(void);
+static struct rcu_node *rcu_get_root(struct rcu_state *rsp);
+static void cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp,
+			  struct rcu_node *rnp, unsigned long flags);
+static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags);
+#ifdef CONFIG_HOTPLUG_CPU
+static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+static void __rcu_process_callbacks(struct rcu_state *rsp,
+				    struct rcu_data *rdp);
+static void __call_rcu(struct rcu_head *head,
+		       void (*func)(struct rcu_head *rcu),
+		       struct rcu_state *rsp);
+static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp);
+static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp,
+					   int preemptable);
+
+#include "rcutree_plugin.h"
+
 /*
- * Increment the quiescent state counter.
- * The counter is a bit degenerated: We do not need to know
+ * Note a quiescent state.  Because we do not need to know
  * how many quiescent states passed, just if there was at least
- * one since the start of the grace period. Thus just a flag.
+ * one since the start of the grace period, this just sets a flag.
  */
-void rcu_qsctr_inc(int cpu)
+void rcu_sched_qs(int cpu)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	unsigned long flags;
+	struct rcu_data *rdp;
+
+	local_irq_save(flags);
+	rdp = &per_cpu(rcu_sched_data, cpu);
 	rdp->passed_quiesc = 1;
 	rdp->passed_quiesc_completed = rdp->completed;
+	rcu_preempt_qs(cpu);
+	local_irq_restore(flags);
 }
 
-void rcu_bh_qsctr_inc(int cpu)
+void rcu_bh_qs(int cpu)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+	unsigned long flags;
+	struct rcu_data *rdp;
+
+	local_irq_save(flags);
+	rdp = &per_cpu(rcu_bh_data, cpu);
 	rdp->passed_quiesc = 1;
 	rdp->passed_quiesc_completed = rdp->completed;
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_NO_HZ
@@ -110,15 +142,16 @@ static int qhimark = 10000;	/* If this many pending, ignore blimit. */
 static int qlowmark = 100;	/* Once only this many pending, use blimit. */
 
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
+static int rcu_pending(int cpu);
 
 /*
- * Return the number of RCU batches processed thus far for debug & stats.
+ * Return the number of RCU-sched batches processed thus far for debug & stats.
  */
-long rcu_batches_completed(void)
+long rcu_batches_completed_sched(void)
 {
-	return rcu_state.completed;
+	return rcu_sched_state.completed;
 }
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
+EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
 /*
  * Return the number of RCU BH batches processed thus far for debug & stats.
@@ -181,6 +214,10 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 		return 1;
 	}
 
+	/* If preemptable RCU, no point in sending reschedule IPI. */
+	if (rdp->preemptable)
+		return 0;
+
 	/* The CPU is online, so send it a reschedule IPI. */
 	if (rdp->cpu != smp_processor_id())
 		smp_send_reschedule(rdp->cpu);
@@ -193,7 +230,6 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 #endif /* #ifdef CONFIG_SMP */
 
 #ifdef CONFIG_NO_HZ
-static DEFINE_RATELIMIT_STATE(rcu_rs, 10 * HZ, 5);
 
 /**
  * rcu_enter_nohz - inform RCU that current CPU is entering nohz
@@ -213,7 +249,7 @@ void rcu_enter_nohz(void)
 	rdtp = &__get_cpu_var(rcu_dynticks);
 	rdtp->dynticks++;
 	rdtp->dynticks_nesting--;
-	WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+	WARN_ON_ONCE(rdtp->dynticks & 0x1);
 	local_irq_restore(flags);
 }
 
@@ -232,7 +268,7 @@ void rcu_exit_nohz(void)
 	rdtp = &__get_cpu_var(rcu_dynticks);
 	rdtp->dynticks++;
 	rdtp->dynticks_nesting++;
-	WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
 	local_irq_restore(flags);
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
@@ -251,7 +287,7 @@ void rcu_nmi_enter(void)
 	if (rdtp->dynticks & 0x1)
 		return;
 	rdtp->dynticks_nmi++;
-	WARN_ON_RATELIMIT(!(rdtp->dynticks_nmi & 0x1), &rcu_rs);
+	WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
@@ -270,7 +306,7 @@ void rcu_nmi_exit(void)
 		return;
 	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	rdtp->dynticks_nmi++;
-	WARN_ON_RATELIMIT(rdtp->dynticks_nmi & 0x1, &rcu_rs);
+	WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
 }
 
 /**
@@ -286,7 +322,7 @@ void rcu_irq_enter(void)
 	if (rdtp->dynticks_nesting++)
 		return;
 	rdtp->dynticks++;
-	WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
@@ -305,10 +341,10 @@ void rcu_irq_exit(void)
 		return;
 	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	rdtp->dynticks++;
-	WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+	WARN_ON_ONCE(rdtp->dynticks & 0x1);
 
 	/* If the interrupt queued a callback, get out of dyntick mode. */
-	if (__get_cpu_var(rcu_data).nxtlist ||
+	if (__get_cpu_var(rcu_sched_data).nxtlist ||
 	    __get_cpu_var(rcu_bh_data).nxtlist)
 		set_need_resched();
 }
@@ -461,6 +497,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 
 	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
 	for (; rnp_cur < rnp_end; rnp_cur++) {
+		rcu_print_task_stall(rnp);
 		if (rnp_cur->qsmask == 0)
 			continue;
 		for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++)
@@ -469,6 +506,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	}
 	printk(" (detected by %d, t=%ld jiffies)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
+	trigger_all_cpu_backtrace();
+
 	force_quiescent_state(rsp, 0);  /* Kick them all. */
 }
 
@@ -479,12 +518,14 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
 			smp_processor_id(), jiffies - rsp->gp_start);
-	dump_stack();
+	trigger_all_cpu_backtrace();
+
 	spin_lock_irqsave(&rnp->lock, flags);
 	if ((long)(jiffies - rsp->jiffies_stall) >= 0)
 		rsp->jiffies_stall =
 			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
 	spin_unlock_irqrestore(&rnp->lock, flags);
+
 	set_need_resched();  /* kick ourselves to get things going. */
 }
 
@@ -674,6 +715,19 @@ rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
+ * Clean up after the prior grace period and let rcu_start_gp() start up
+ * the next grace period if one is needed.  Note that the caller must
+ * hold rnp->lock, as required by rcu_start_gp(), which will release it.
+ */
+static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
+	__releases(rnp->lock)
+{
+	rsp->completed = rsp->gpnum;
+	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
+	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
+}
+
+/*
  * Similar to cpu_quiet(), for which it is a helper function.  Allows
  * a group of CPUs to be quieted at one go, though all the CPUs in the
  * group must be represented by the same leaf rcu_node structure.
@@ -694,7 +748,7 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
 			return;
 		}
 		rnp->qsmask &= ~mask;
-		if (rnp->qsmask != 0) {
+		if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
 
 			/* Other bits still set at this level, so done. */
 			spin_unlock_irqrestore(&rnp->lock, flags);
@@ -714,14 +768,10 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
 
 	/*
 	 * Get here if we are the last CPU to pass through a quiescent
-	 * state for this grace period.  Clean up and let rcu_start_gp()
-	 * start up the next grace period if one is needed.  Note that
-	 * we still hold rnp->lock, as required by rcu_start_gp(), which
-	 * will release it.
+	 * state for this grace period.  Invoke cpu_quiet_msk_finish()
+	 * to clean up and start the next grace period if one is needed.
 	 */
-	rsp->completed = rsp->gpnum;
-	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
-	rcu_start_gp(rsp, flags);  /* releases rnp->lock. */
+	cpu_quiet_msk_finish(rsp, flags); /* releases rnp->lock. */
 }
 
 /*
@@ -828,11 +878,12 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 		spin_lock(&rnp->lock);		/* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
-			spin_unlock(&rnp->lock); /* irqs already disabled. */
+			spin_unlock(&rnp->lock); /* irqs remain disabled. */
 			break;
 		}
+		rcu_preempt_offline_tasks(rsp, rnp);
 		mask = rnp->grpmask;
-		spin_unlock(&rnp->lock);	/* irqs already disabled. */
+		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 		rnp = rnp->parent;
 	} while (rnp != NULL);
 	lastcomp = rsp->completed;
@@ -845,7 +896,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	/*
 	 * Move callbacks from the outgoing CPU to the running CPU.
 	 * Note that the outgoing CPU is now quiscent, so it is now
-	 * (uncharacteristically) safe to access it rcu_data structure.
+	 * (uncharacteristically) safe to access its rcu_data structure.
 	 * Note also that we must carefully retain the order of the
 	 * outgoing CPU's callbacks in order for rcu_barrier() to work
 	 * correctly.  Finally, note that we start all the callbacks
@@ -876,8 +927,9 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
  */
 static void rcu_offline_cpu(int cpu)
 {
-	__rcu_offline_cpu(cpu, &rcu_state);
+	__rcu_offline_cpu(cpu, &rcu_sched_state);
 	__rcu_offline_cpu(cpu, &rcu_bh_state);
+	rcu_preempt_offline_cpu(cpu);
 }
 
 #else /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -963,6 +1015,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
  */
 void rcu_check_callbacks(int cpu, int user)
 {
+	if (!rcu_pending(cpu))
+		return; /* if nothing for RCU to do. */
 	if (user ||
 	    (idle_cpu(cpu) && rcu_scheduler_active &&
 	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
@@ -971,17 +1025,16 @@ void rcu_check_callbacks(int cpu, int user)
 		 * Get here if this CPU took its interrupt from user
 		 * mode or from the idle loop, and if this is not a
 		 * nested interrupt.  In this case, the CPU is in
-		 * a quiescent state, so count it.
+		 * a quiescent state, so note it.
 		 *
 		 * No memory barrier is required here because both
-		 * rcu_qsctr_inc() and rcu_bh_qsctr_inc() reference
-		 * only CPU-local variables that other CPUs neither
-		 * access nor modify, at least not while the corresponding
-		 * CPU is online.
+		 * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local
+		 * variables that other CPUs neither access nor modify,
+		 * at least not while the corresponding CPU is online.
 		 */
 
-		rcu_qsctr_inc(cpu);
-		rcu_bh_qsctr_inc(cpu);
+		rcu_sched_qs(cpu);
+		rcu_bh_qs(cpu);
 
 	} else if (!in_softirq()) {
 
@@ -989,11 +1042,12 @@ void rcu_check_callbacks(int cpu, int user)
 		 * Get here if this CPU did not take its interrupt from
 		 * softirq, in other words, if it is not interrupting
 		 * a rcu_bh read-side critical section.  This is an _bh
-		 * critical section, so count it.
+		 * critical section, so note it.
 		 */
 
-		rcu_bh_qsctr_inc(cpu);
+		rcu_bh_qs(cpu);
 	}
+	rcu_preempt_check_callbacks(cpu);
 	raise_softirq(RCU_SOFTIRQ);
 }
 
@@ -1132,6 +1186,8 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 
+	WARN_ON_ONCE(rdp->beenonline == 0);
+
 	/*
 	 * If an RCU GP has gone long enough, go check for dyntick
 	 * idle CPUs and, if needed, send resched IPIs.
@@ -1170,8 +1226,10 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 	 */
 	smp_mb(); /* See above block comment. */
 
-	__rcu_process_callbacks(&rcu_state, &__get_cpu_var(rcu_data));
+	__rcu_process_callbacks(&rcu_sched_state,
+				&__get_cpu_var(rcu_sched_data));
 	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+	rcu_preempt_process_callbacks();
 
 	/*
 	 * Memory references from any later RCU read-side critical sections
@@ -1227,13 +1285,13 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 }
 
 /*
- * Queue an RCU callback for invocation after a grace period.
+ * Queue an RCU-sched callback for invocation after a grace period.
  */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_state);
+	__call_rcu(head, func, &rcu_sched_state);
 }
-EXPORT_SYMBOL_GPL(call_rcu);
+EXPORT_SYMBOL_GPL(call_rcu_sched);
 
 /*
  * Queue an RCU for invocation after a quicker grace period.
@@ -1305,10 +1363,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
  * by the current CPU, returning 1 if so.  This function is part of the
  * RCU implementation; it is -not- an exported member of the RCU API.
  */
-int rcu_pending(int cpu)
+static int rcu_pending(int cpu)
 {
-	return __rcu_pending(&rcu_state, &per_cpu(rcu_data, cpu)) ||
-	       __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu));
+	return __rcu_pending(&rcu_sched_state, &per_cpu(rcu_sched_data, cpu)) ||
+	       __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)) ||
+	       rcu_preempt_pending(cpu);
 }
 
 /*
@@ -1320,27 +1379,46 @@ int rcu_pending(int cpu)
 int rcu_needs_cpu(int cpu)
 {
 	/* RCU callbacks either ready or pending? */
-	return per_cpu(rcu_data, cpu).nxtlist ||
-	       per_cpu(rcu_bh_data, cpu).nxtlist;
+	return per_cpu(rcu_sched_data, cpu).nxtlist ||
+	       per_cpu(rcu_bh_data, cpu).nxtlist ||
+	       rcu_preempt_needs_cpu(cpu);
 }
 
 /*
- * Initialize a CPU's per-CPU RCU data.  We take this "scorched earth"
- * approach so that we don't have to worry about how long the CPU has
- * been gone, or whether it ever was online previously.  We do trust the
- * ->mynode field, as it is constant for a given struct rcu_data and
- * initialized during early boot.
- *
- * Note that only one online or offline event can be happening at a given
- * time.  Note also that we can accept some slop in the rsp->completed
- * access due to the fact that this CPU cannot possibly have any RCU
- * callbacks in flight yet.
+ * Do boot-time initialization of a CPU's per-CPU RCU data.
  */
-static void __cpuinit
-rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
+static void __init
+rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
 	int i;
+	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	/* Set up local state, ensuring consistent view of global state. */
+	spin_lock_irqsave(&rnp->lock, flags);
+	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
+	rdp->nxtlist = NULL;
+	for (i = 0; i < RCU_NEXT_SIZE; i++)
+		rdp->nxttail[i] = &rdp->nxtlist;
+	rdp->qlen = 0;
+#ifdef CONFIG_NO_HZ
+	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
+#endif /* #ifdef CONFIG_NO_HZ */
+	rdp->cpu = cpu;
+	spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Initialize a CPU's per-CPU RCU data.  Note that only one online or
+ * offline event can be happening at a given time.  Note also that we
+ * can accept some slop in the rsp->completed access due to the fact
+ * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ */
+static void __cpuinit
+rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
+{
+	unsigned long flags;
 	long lastcomp;
 	unsigned long mask;
 	struct rcu_data *rdp = rsp->rda[cpu];
@@ -1354,17 +1432,9 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
 	rdp->qs_pending = 1;	 /*  so set up to respond to current GP. */
 	rdp->beenonline = 1;	 /* We have now been online. */
+	rdp->preemptable = preemptable;
 	rdp->passed_quiesc_completed = lastcomp - 1;
-	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
-	rdp->nxtlist = NULL;
-	for (i = 0; i < RCU_NEXT_SIZE; i++)
-		rdp->nxttail[i] = &rdp->nxtlist;
-	rdp->qlen = 0;
 	rdp->blimit = blimit;
-#ifdef CONFIG_NO_HZ
-	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
-#endif /* #ifdef CONFIG_NO_HZ */
-	rdp->cpu = cpu;
 	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/*
@@ -1405,16 +1475,16 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 
 static void __cpuinit rcu_online_cpu(int cpu)
 {
-	rcu_init_percpu_data(cpu, &rcu_state);
-	rcu_init_percpu_data(cpu, &rcu_bh_state);
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
+	rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
+	rcu_preempt_init_percpu_data(cpu);
 }
 
 /*
- * Handle CPU online/offline notifcation events.
+ * Handle CPU online/offline notification events.
  */
-static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
+int __cpuinit rcu_cpu_notify(struct notifier_block *self,
+			     unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
 
@@ -1486,6 +1556,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		rnp = rsp->level[i];
 		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
 			spin_lock_init(&rnp->lock);
+			rnp->gpnum = 0;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
@@ -1503,16 +1574,20 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 					      j / rsp->levelspread[i - 1];
 			}
 			rnp->level = i;
+			INIT_LIST_HEAD(&rnp->blocked_tasks[0]);
+			INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
 		}
 	}
 }
 
 /*
- * Helper macro for __rcu_init().  To be used nowhere else!
- * Assigns leaf node pointers into each CPU's rcu_data structure.
+ * Helper macro for __rcu_init() and __rcu_init_preempt().  To be used
+ * nowhere else!  Assigns leaf node pointers into each CPU's rcu_data
+ * structure.
  */
-#define RCU_DATA_PTR_INIT(rsp, rcu_data) \
+#define RCU_INIT_FLAVOR(rsp, rcu_data) \
 do { \
+	rcu_init_one(rsp); \
 	rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
 	j = 0; \
 	for_each_possible_cpu(i) { \
@@ -1520,32 +1595,43 @@ do { \
 			j++; \
 		per_cpu(rcu_data, i).mynode = &rnp[j]; \
 		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
+		rcu_boot_init_percpu_data(i, rsp); \
 	} \
 } while (0)
 
-static struct notifier_block __cpuinitdata rcu_nb = {
-	.notifier_call	= rcu_cpu_notify,
-};
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+void __init __rcu_init_preempt(void)
+{
+	int i;			/* All used by RCU_INIT_FLAVOR(). */
+	int j;
+	struct rcu_node *rnp;
+
+	RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+}
+
+#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+void __init __rcu_init_preempt(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 void __init __rcu_init(void)
 {
-	int i;			/* All used by RCU_DATA_PTR_INIT(). */
+	int i;			/* All used by RCU_INIT_FLAVOR(). */
 	int j;
 	struct rcu_node *rnp;
 
-	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+	rcu_bootup_announce();
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-	rcu_init_one(&rcu_state);
-	RCU_DATA_PTR_INIT(&rcu_state, rcu_data);
-	rcu_init_one(&rcu_bh_state);
-	RCU_DATA_PTR_INIT(&rcu_bh_state, rcu_bh_data);
-
-	for_each_online_cpu(i)
-		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
-	/* Register notifier for non-boot CPUs */
-	register_cpu_notifier(&rcu_nb);
+	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
+	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
+	__rcu_init_preempt();
+	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
 
 module_param(blimit, int, 0);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 5e872bbf07f5..bf8a6f9f134d 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -1,10 +1,259 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2008
+ *
+ * Author: Ingo Molnar <mingo@elte.hu>
+ *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/seqlock.h>
+
+/*
+ * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
+ * In theory, it should be possible to add more levels straightforwardly.
+ * In practice, this has not been tested, so there is probably some
+ * bug somewhere.
+ */
+#define MAX_RCU_LVLS 3
+#define RCU_FANOUT	      (CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_SQ	      (RCU_FANOUT * RCU_FANOUT)
+#define RCU_FANOUT_CUBE	      (RCU_FANOUT_SQ * RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT
+#  define NUM_RCU_LVLS	      1
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      (NR_CPUS)
+#  define NUM_RCU_LVL_2	      0
+#  define NUM_RCU_LVL_3	      0
+#elif NR_CPUS <= RCU_FANOUT_SQ
+#  define NUM_RCU_LVLS	      2
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT)
+#  define NUM_RCU_LVL_2	      (NR_CPUS)
+#  define NUM_RCU_LVL_3	      0
+#elif NR_CPUS <= RCU_FANOUT_CUBE
+#  define NUM_RCU_LVLS	      3
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ)
+#  define NUM_RCU_LVL_2	      (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT))
+#  define NUM_RCU_LVL_3	      NR_CPUS
+#else
+# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
+#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
+
+/*
+ * Dynticks per-CPU state.
+ */
+struct rcu_dynticks {
+	int dynticks_nesting;	/* Track nesting level, sort of. */
+	int dynticks;		/* Even value for dynticks-idle, else odd. */
+	int dynticks_nmi;	/* Even value for either dynticks-idle or */
+				/*  not in nmi handler, else odd.  So this */
+				/*  remains even for nmi from irq handler. */
+};
+
+/*
+ * Definition for node within the RCU grace-period-detection hierarchy.
+ */
+struct rcu_node {
+	spinlock_t lock;
+	long	gpnum;		/* Current grace period for this node. */
+				/*  This will either be equal to or one */
+				/*  behind the root rcu_node's gpnum. */
+	unsigned long qsmask;	/* CPUs or groups that need to switch in */
+				/*  order for current grace period to proceed.*/
+	unsigned long qsmaskinit;
+				/* Per-GP initialization for qsmask. */
+	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
+	int	grplo;		/* lowest-numbered CPU or group here. */
+	int	grphi;		/* highest-numbered CPU or group here. */
+	u8	grpnum;		/* CPU/group number for next level up. */
+	u8	level;		/* root is at level 0. */
+	struct rcu_node *parent;
+	struct list_head blocked_tasks[2];
+				/* Tasks blocked in RCU read-side critsect. */
+} ____cacheline_internodealigned_in_smp;
+
+/* Index values for nxttail array in struct rcu_data. */
+#define RCU_DONE_TAIL		0	/* Also RCU_WAIT head. */
+#define RCU_WAIT_TAIL		1	/* Also RCU_NEXT_READY head. */
+#define RCU_NEXT_READY_TAIL	2	/* Also RCU_NEXT head. */
+#define RCU_NEXT_TAIL		3
+#define RCU_NEXT_SIZE		4
+
+/* Per-CPU data for read-copy update. */
+struct rcu_data {
+	/* 1) quiescent-state and grace-period handling : */
+	long		completed;	/* Track rsp->completed gp number */
+					/*  in order to detect GP end. */
+	long		gpnum;		/* Highest gp number that this CPU */
+					/*  is aware of having started. */
+	long		passed_quiesc_completed;
+					/* Value of completed at time of qs. */
+	bool		passed_quiesc;	/* User-mode/idle loop etc. */
+	bool		qs_pending;	/* Core waits for quiesc state. */
+	bool		beenonline;	/* CPU online at least once. */
+	bool		preemptable;	/* Preemptable RCU? */
+	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
+	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
+
+	/* 2) batch handling */
+	/*
+	 * If nxtlist is not NULL, it is partitioned as follows.
+	 * Any of the partitions might be empty, in which case the
+	 * pointer to that partition will be equal to the pointer for
+	 * the following partition.  When the list is empty, all of
+	 * the nxttail elements point to nxtlist, which is NULL.
+	 *
+	 * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]):
+	 *	Entries that might have arrived after current GP ended
+	 * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
+	 *	Entries known to have arrived before current GP ended
+	 * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
+	 *	Entries that batch # <= ->completed - 1: waiting for current GP
+	 * [nxtlist, *nxttail[RCU_DONE_TAIL]):
+	 *	Entries that batch # <= ->completed
+	 *	The grace period for these entries has completed, and
+	 *	the other grace-period-completed entries may be moved
+	 *	here temporarily in rcu_process_callbacks().
+	 */
+	struct rcu_head *nxtlist;
+	struct rcu_head **nxttail[RCU_NEXT_SIZE];
+	long		qlen; 	 	/* # of queued callbacks */
+	long		blimit;		/* Upper limit on a processed batch */
+
+#ifdef CONFIG_NO_HZ
+	/* 3) dynticks interface. */
+	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
+	int dynticks_snap;		/* Per-GP tracking for dynticks. */
+	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
+#endif /* #ifdef CONFIG_NO_HZ */
+
+	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
+#ifdef CONFIG_NO_HZ
+	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
+#endif /* #ifdef CONFIG_NO_HZ */
+	unsigned long offline_fqs;	/* Kicked due to being offline. */
+	unsigned long resched_ipi;	/* Sent a resched IPI. */
+
+	/* 5) __rcu_pending() statistics. */
+	long n_rcu_pending;		/* rcu_pending() calls since boot. */
+	long n_rp_qs_pending;
+	long n_rp_cb_ready;
+	long n_rp_cpu_needs_gp;
+	long n_rp_gp_completed;
+	long n_rp_gp_started;
+	long n_rp_need_fqs;
+	long n_rp_need_nothing;
+
+	int cpu;
+};
+
+/* Values for signaled field in struct rcu_state. */
+#define RCU_GP_INIT		0	/* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK	1	/* Need to scan dyntick state. */
+#define RCU_FORCE_QS		2	/* Need to force quiescent state. */
+#ifdef CONFIG_NO_HZ
+#define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
+#else /* #ifdef CONFIG_NO_HZ */
+#define RCU_SIGNAL_INIT		RCU_FORCE_QS
+#endif /* #else #ifdef CONFIG_NO_HZ */
+
+#define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
+#define RCU_STALL_RAT_DELAY		2	  /* Allow other CPUs time */
+						  /*  to take at least one */
+						  /*  scheduling clock irq */
+						  /*  before ratting on them. */
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * RCU global state, including node hierarchy.  This hierarchy is
+ * represented in "heap" form in a dense array.  The root (first level)
+ * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
+ * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
+ * and the third level in ->node[m+1] and following (->node[m+1] referenced
+ * by ->level[2]).  The number of levels is determined by the number of
+ * CPUs and by CONFIG_RCU_FANOUT.  Small systems will have a "hierarchy"
+ * consisting of a single rcu_node.
+ */
+struct rcu_state {
+	struct rcu_node node[NUM_RCU_NODES];	/* Hierarchy. */
+	struct rcu_node *level[NUM_RCU_LVLS];	/* Hierarchy levels. */
+	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
+	u8 levelspread[NUM_RCU_LVLS];		/* kids/node in each level. */
+	struct rcu_data *rda[NR_CPUS];		/* array of rdp pointers. */
+
+	/* The following fields are guarded by the root rcu_node's lock. */
+
+	u8	signaled ____cacheline_internodealigned_in_smp;
+						/* Force QS state. */
+	long	gpnum;				/* Current gp number. */
+	long	completed;			/* # of last completed gp. */
+	spinlock_t onofflock;			/* exclude on/offline and */
+						/*  starting new GP. */
+	spinlock_t fqslock;			/* Only one task forcing */
+						/*  quiescent states. */
+	unsigned long jiffies_force_qs;		/* Time at which to invoke */
+						/*  force_quiescent_state(). */
+	unsigned long n_force_qs;		/* Number of calls to */
+						/*  force_quiescent_state(). */
+	unsigned long n_force_qs_lh;		/* ~Number of calls leaving */
+						/*  due to lock unavailable. */
+	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
+						/*  due to no GP active. */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+	unsigned long gp_start;			/* Time at which GP started, */
+						/*  but in jiffies. */
+	unsigned long jiffies_stall;		/* Time at which to check */
+						/*  for CPU stalls. */
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#ifdef CONFIG_NO_HZ
+	long dynticks_completed;		/* Value of completed @ snap. */
+#endif /* #ifdef CONFIG_NO_HZ */
+};
+
+#ifdef RCU_TREE_NONCORE
 
 /*
  * RCU implementation internal declarations:
  */
-extern struct rcu_state rcu_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_data);
+extern struct rcu_state rcu_sched_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
 
 extern struct rcu_state rcu_bh_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+#ifdef CONFIG_TREE_PREEMPT_RCU
+extern struct rcu_state rcu_preempt_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+#endif /* #ifdef RCU_TREE_NONCORE */
+
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
new file mode 100644
index 000000000000..47789369ea59
--- /dev/null
+++ b/kernel/rcutree_plugin.h
@@ -0,0 +1,532 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions that provide either classic
+ * or preemptable semantics.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright Red Hat, 2009
+ * Copyright IBM Corporation, 2009
+ *
+ * Author: Ingo Molnar <mingo@elte.hu>
+ *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+
+/*
+ * Tell them what RCU they are running.
+ */
+static inline void rcu_bootup_announce(void)
+{
+	printk(KERN_INFO
+	       "Experimental preemptable hierarchical RCU implementation.\n");
+}
+
+/*
+ * Return the number of RCU-preempt batches processed thus far
+ * for debug and statistics.
+ */
+long rcu_batches_completed_preempt(void)
+{
+	return rcu_preempt_state.completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);
+
+/*
+ * Return the number of RCU batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed(void)
+{
+	return rcu_batches_completed_preempt();
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Record a preemptable-RCU quiescent state for the specified CPU.  Note
+ * that this just means that the task currently running on the CPU is
+ * not in a quiescent state.  There might be any number of tasks blocked
+ * while in an RCU read-side critical section.
+ */
+static void rcu_preempt_qs_record(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+	rdp->passed_quiesc = 1;
+	rdp->passed_quiesc_completed = rdp->completed;
+}
+
+/*
+ * We have entered the scheduler or are between softirqs in ksoftirqd.
+ * If we are in an RCU read-side critical section, we need to reflect
+ * that in the state of the rcu_node structure corresponding to this CPU.
+ * Caller must disable hardirqs.
+ */
+static void rcu_preempt_qs(int cpu)
+{
+	struct task_struct *t = current;
+	int phase;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	if (t->rcu_read_lock_nesting &&
+	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
+
+		/* Possibly blocking in an RCU read-side critical section. */
+		rdp = rcu_preempt_state.rda[cpu];
+		rnp = rdp->mynode;
+		spin_lock(&rnp->lock);
+		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
+		t->rcu_blocked_node = rnp;
+
+		/*
+		 * If this CPU has already checked in, then this task
+		 * will hold up the next grace period rather than the
+		 * current grace period.  Queue the task accordingly.
+		 * If the task is queued for the current grace period
+		 * (i.e., this CPU has not yet passed through a quiescent
+		 * state for the current grace period), then as long
+		 * as that task remains queued, the current grace period
+		 * cannot end.
+		 */
+		phase = !(rnp->qsmask & rdp->grpmask) ^ (rnp->gpnum & 0x1);
+		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
+		smp_mb();  /* Ensure later ctxt swtch seen after above. */
+		spin_unlock(&rnp->lock);
+	}
+
+	/*
+	 * Either we were not in an RCU read-side critical section to
+	 * begin with, or we have now recorded that critical section
+	 * globally.  Either way, we can now note a quiescent state
+	 * for this CPU.  Again, if we were in an RCU read-side critical
+	 * section, and if that critical section was blocking the current
+	 * grace period, then the fact that the task has been enqueued
+	 * means that we continue to block the current grace period.
+	 */
+	rcu_preempt_qs_record(cpu);
+	t->rcu_read_unlock_special &= ~(RCU_READ_UNLOCK_NEED_QS |
+					RCU_READ_UNLOCK_GOT_QS);
+}
+
+/*
+ * Tree-preemptable RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+	ACCESS_ONCE(current->rcu_read_lock_nesting)++;
+	barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+static void rcu_read_unlock_special(struct task_struct *t)
+{
+	int empty;
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp;
+	int special;
+
+	/* NMI handlers cannot block and cannot safely manipulate state. */
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+
+	/*
+	 * If RCU core is waiting for this CPU to exit critical section,
+	 * let it know that we have done so.
+	 */
+	special = t->rcu_read_unlock_special;
+	if (special & RCU_READ_UNLOCK_NEED_QS) {
+		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_GOT_QS;
+	}
+
+	/* Hardware IRQ handlers cannot block. */
+	if (in_irq()) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	/* Clean up if blocked during RCU read-side critical section. */
+	if (special & RCU_READ_UNLOCK_BLOCKED) {
+		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
+
+		/*
+		 * Remove this task from the list it blocked on.  The
+		 * task can migrate while we acquire the lock, but at
+		 * most one time.  So at most two passes through loop.
+		 */
+		for (;;) {
+			rnp = t->rcu_blocked_node;
+			spin_lock(&rnp->lock);
+			if (rnp == t->rcu_blocked_node)
+				break;
+			spin_unlock(&rnp->lock);
+		}
+		empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+		list_del_init(&t->rcu_node_entry);
+		t->rcu_blocked_node = NULL;
+
+		/*
+		 * If this was the last task on the current list, and if
+		 * we aren't waiting on any CPUs, report the quiescent state.
+		 * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk()
+		 * drop rnp->lock and restore irq.
+		 */
+		if (!empty && rnp->qsmask == 0 &&
+		    list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) {
+			t->rcu_read_unlock_special &=
+				~(RCU_READ_UNLOCK_NEED_QS |
+				  RCU_READ_UNLOCK_GOT_QS);
+			if (rnp->parent == NULL) {
+				/* Only one rcu_node in the tree. */
+				cpu_quiet_msk_finish(&rcu_preempt_state, flags);
+				return;
+			}
+			/* Report up the rest of the hierarchy. */
+			mask = rnp->grpmask;
+			spin_unlock_irqrestore(&rnp->lock, flags);
+			rnp = rnp->parent;
+			spin_lock_irqsave(&rnp->lock, flags);
+			cpu_quiet_msk(mask, &rcu_preempt_state, rnp, flags);
+			return;
+		}
+		spin_unlock(&rnp->lock);
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Tree-preemptable RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+	struct task_struct *t = current;
+
+	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
+	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
+	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+		rcu_read_unlock_special(t);
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each.
+ */
+static void rcu_print_task_stall(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	struct list_head *lp;
+	int phase = rnp->gpnum & 0x1;
+	struct task_struct *t;
+
+	if (!list_empty(&rnp->blocked_tasks[phase])) {
+		spin_lock_irqsave(&rnp->lock, flags);
+		phase = rnp->gpnum & 0x1; /* re-read under lock. */
+		lp = &rnp->blocked_tasks[phase];
+		list_for_each_entry(t, lp, rcu_node_entry)
+			printk(" P%d", t->pid);
+		spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+}
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * Check for preempted RCU readers for the specified rcu_node structure.
+ * If the caller needs a reliable answer, it must hold the rcu_node's
+ * >lock.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+	return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Handle tasklist migration for case in which all CPUs covered by the
+ * specified rcu_node have gone offline.  Move them up to the root
+ * rcu_node.  The reason for not just moving them to the immediate
+ * parent is to remove the need for rcu_read_unlock_special() to
+ * make more than two attempts to acquire the target rcu_node's lock.
+ *
+ * The caller must hold rnp->lock with irqs disabled.
+ */
+static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
+				      struct rcu_node *rnp)
+{
+	int i;
+	struct list_head *lp;
+	struct list_head *lp_root;
+	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	struct task_struct *tp;
+
+	if (rnp == rnp_root) {
+		WARN_ONCE(1, "Last CPU thought to be offlined?");
+		return;  /* Shouldn't happen: at least one CPU online. */
+	}
+
+	/*
+	 * Move tasks up to root rcu_node.  Rely on the fact that the
+	 * root rcu_node can be at most one ahead of the rest of the
+	 * rcu_nodes in terms of gp_num value.  This fact allows us to
+	 * move the blocked_tasks[] array directly, element by element.
+	 */
+	for (i = 0; i < 2; i++) {
+		lp = &rnp->blocked_tasks[i];
+		lp_root = &rnp_root->blocked_tasks[i];
+		while (!list_empty(lp)) {
+			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
+			spin_lock(&rnp_root->lock); /* irqs already disabled */
+			list_del(&tp->rcu_node_entry);
+			tp->rcu_blocked_node = rnp_root;
+			list_add(&tp->rcu_node_entry, lp_root);
+			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
+		}
+	}
+}
+
+/*
+ * Do CPU-offline processing for preemptable RCU.
+ */
+static void rcu_preempt_offline_cpu(int cpu)
+{
+	__rcu_offline_cpu(cpu, &rcu_preempt_state);
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Check for a quiescent state from the current CPU.  When a task blocks,
+ * the task is recorded in the corresponding CPU's rcu_node structure,
+ * which is checked elsewhere.
+ *
+ * Caller must disable hard irqs.
+ */
+static void rcu_preempt_check_callbacks(int cpu)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting == 0) {
+		t->rcu_read_unlock_special &=
+			~(RCU_READ_UNLOCK_NEED_QS | RCU_READ_UNLOCK_GOT_QS);
+		rcu_preempt_qs_record(cpu);
+		return;
+	}
+	if (per_cpu(rcu_preempt_data, cpu).qs_pending) {
+		if (t->rcu_read_unlock_special & RCU_READ_UNLOCK_GOT_QS) {
+			rcu_preempt_qs_record(cpu);
+			t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_GOT_QS;
+		} else if (!(t->rcu_read_unlock_special &
+			     RCU_READ_UNLOCK_NEED_QS)) {
+			t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
+		}
+	}
+}
+
+/*
+ * Process callbacks for preemptable RCU.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+	__rcu_process_callbacks(&rcu_preempt_state,
+				&__get_cpu_var(rcu_preempt_data));
+}
+
+/*
+ * Queue a preemptable-RCU callback for invocation after a grace period.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, &rcu_preempt_state);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Check to see if there is any immediate preemptable-RCU-related work
+ * to be done.
+ */
+static int rcu_preempt_pending(int cpu)
+{
+	return __rcu_pending(&rcu_preempt_state,
+			     &per_cpu(rcu_preempt_data, cpu));
+}
+
+/*
+ * Does preemptable RCU need the CPU to stay out of dynticks mode?
+ */
+static int rcu_preempt_needs_cpu(int cpu)
+{
+	return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
+}
+
+/*
+ * Initialize preemptable RCU's per-CPU data.
+ */
+static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
+{
+	rcu_init_percpu_data(cpu, &rcu_preempt_state, 1);
+}
+
+/*
+ * Check for a task exiting while in a preemptable-RCU read-side
+ * critical section, clean up if so.  No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting == 0)
+		return;
+	t->rcu_read_lock_nesting = 1;
+	rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+/*
+ * Tell them what RCU they are running.
+ */
+static inline void rcu_bootup_announce(void)
+{
+	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+}
+
+/*
+ * Return the number of RCU batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed(void)
+{
+	return rcu_batches_completed_sched();
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Because preemptable RCU does not exist, we never have to check for
+ * CPUs being in quiescent states.
+ */
+static void rcu_preempt_qs(int cpu)
+{
+}
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+/*
+ * Because preemptable RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static void rcu_print_task_stall(struct rcu_node *rnp)
+{
+}
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * Because preemptable RCU does not exist, there are never any preempted
+ * RCU readers.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Because preemptable RCU does not exist, it never needs to migrate
+ * tasks that were blocked within RCU read-side critical sections.
+ */
+static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
+				      struct rcu_node *rnp)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, it never needs CPU-offline
+ * processing.
+ */
+static void rcu_preempt_offline_cpu(int cpu)
+{
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Because preemptable RCU does not exist, it never has any callbacks
+ * to check.
+ */
+void rcu_preempt_check_callbacks(int cpu)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, it never has any callbacks
+ * to process.
+ */
+void rcu_preempt_process_callbacks(void)
+{
+}
+
+/*
+ * In classic RCU, call_rcu() is just call_rcu_sched().
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	call_rcu_sched(head, func);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Because preemptable RCU does not exist, it never has any work to do.
+ */
+static int rcu_preempt_pending(int cpu)
+{
+	return 0;
+}
+
+/*
+ * Because preemptable RCU does not exist, it never needs any CPU.
+ */
+static int rcu_preempt_needs_cpu(int cpu)
+{
+	return 0;
+}
+
+/*
+ * Because preemptable RCU does not exist, there is no per-CPU
+ * data to initialize.
+ */
+static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index fe1dcdbf1ca3..0ea1bff69727 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -43,6 +43,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#define RCU_TREE_NONCORE
 #include "rcutree.h"
 
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
@@ -76,8 +77,12 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 
 static int show_rcudata(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "rcu:\n");
-	PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "rcu_preempt:\n");
+	PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data, m);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "rcu_sched:\n");
+	PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data, m);
 	seq_puts(m, "rcu_bh:\n");
 	PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m);
 	return 0;
@@ -102,7 +107,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		return;
 	seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d",
 		   rdp->cpu,
-		   cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"",
+		   cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"",
 		   rdp->completed, rdp->gpnum,
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
 		   rdp->qs_pending);
@@ -124,8 +129,12 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
-	seq_puts(m, "\"rcu:\"\n");
-	PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "\"rcu_preempt:\"\n");
+	PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "\"rcu_sched:\"\n");
+	PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data_csv, m);
 	seq_puts(m, "\"rcu_bh:\"\n");
 	PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m);
 	return 0;
@@ -171,8 +180,12 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 
 static int show_rcuhier(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "rcu:\n");
-	print_one_rcu_state(m, &rcu_state);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "rcu_preempt:\n");
+	print_one_rcu_state(m, &rcu_preempt_state);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "rcu_sched:\n");
+	print_one_rcu_state(m, &rcu_sched_state);
 	seq_puts(m, "rcu_bh:\n");
 	print_one_rcu_state(m, &rcu_bh_state);
 	return 0;
@@ -193,8 +206,12 @@ static struct file_operations rcuhier_fops = {
 
 static int show_rcugp(struct seq_file *m, void *unused)
 {
-	seq_printf(m, "rcu: completed=%ld  gpnum=%ld\n",
-		   rcu_state.completed, rcu_state.gpnum);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%ld\n",
+		   rcu_preempt_state.completed, rcu_preempt_state.gpnum);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_printf(m, "rcu_sched: completed=%ld  gpnum=%ld\n",
+		   rcu_sched_state.completed, rcu_sched_state.gpnum);
 	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%ld\n",
 		   rcu_bh_state.completed, rcu_bh_state.gpnum);
 	return 0;
@@ -243,8 +260,12 @@ static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
 
 static int show_rcu_pending(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "rcu:\n");
-	print_rcu_pendings(m, &rcu_state);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "rcu_preempt:\n");
+	print_rcu_pendings(m, &rcu_preempt_state);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "rcu_sched:\n");
+	print_rcu_pendings(m, &rcu_sched_state);
 	seq_puts(m, "rcu_bh:\n");
 	print_rcu_pendings(m, &rcu_bh_state);
 	return 0;
@@ -264,62 +285,47 @@ static struct file_operations rcu_pending_fops = {
 };
 
 static struct dentry *rcudir;
-static struct dentry *datadir;
-static struct dentry *datadir_csv;
-static struct dentry *gpdir;
-static struct dentry *hierdir;
-static struct dentry *rcu_pendingdir;
 
 static int __init rcuclassic_trace_init(void)
 {
+	struct dentry *retval;
+
 	rcudir = debugfs_create_dir("rcu", NULL);
 	if (!rcudir)
-		goto out;
+		goto free_out;
 
-	datadir = debugfs_create_file("rcudata", 0444, rcudir,
+	retval = debugfs_create_file("rcudata", 0444, rcudir,
 						NULL, &rcudata_fops);
-	if (!datadir)
+	if (!retval)
 		goto free_out;
 
-	datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir,
+	retval = debugfs_create_file("rcudata.csv", 0444, rcudir,
 						NULL, &rcudata_csv_fops);
-	if (!datadir_csv)
+	if (!retval)
 		goto free_out;
 
-	gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
-	if (!gpdir)
+	retval = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
+	if (!retval)
 		goto free_out;
 
-	hierdir = debugfs_create_file("rcuhier", 0444, rcudir,
+	retval = debugfs_create_file("rcuhier", 0444, rcudir,
 						NULL, &rcuhier_fops);
-	if (!hierdir)
+	if (!retval)
 		goto free_out;
 
-	rcu_pendingdir = debugfs_create_file("rcu_pending", 0444, rcudir,
+	retval = debugfs_create_file("rcu_pending", 0444, rcudir,
 						NULL, &rcu_pending_fops);
-	if (!rcu_pendingdir)
+	if (!retval)
 		goto free_out;
 	return 0;
 free_out:
-	if (datadir)
-		debugfs_remove(datadir);
-	if (datadir_csv)
-		debugfs_remove(datadir_csv);
-	if (gpdir)
-		debugfs_remove(gpdir);
-	debugfs_remove(rcudir);
-out:
+	debugfs_remove_recursive(rcudir);
 	return 1;
 }
 
 static void __exit rcuclassic_trace_cleanup(void)
 {
-	debugfs_remove(datadir);
-	debugfs_remove(datadir_csv);
-	debugfs_remove(gpdir);
-	debugfs_remove(hierdir);
-	debugfs_remove(rcu_pendingdir);
-	debugfs_remove(rcudir);
+	debugfs_remove_recursive(rcudir);
 }
 
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 1b59e265273b..e27a53685ed9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -64,7 +64,6 @@
 #include <linux/tsacct_kern.h>
 #include <linux/kprobes.h>
 #include <linux/delayacct.h>
-#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
@@ -120,30 +119,8 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-#ifdef CONFIG_SMP
-
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
 
-/*
- * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
- * Since cpu_power is a 'constant', we can use a reciprocal divide.
- */
-static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
-{
-	return reciprocal_divide(load, sg->reciprocal_cpu_power);
-}
-
-/*
- * Each time a sched group cpu_power is changed,
- * we must compute its reciprocal value
- */
-static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
-{
-	sg->__cpu_power += val;
-	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
-}
-#endif
-
 static inline int rt_policy(int policy)
 {
 	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
@@ -309,8 +286,8 @@ void set_tg_uid(struct user_struct *user)
 
 /*
  * Root task group.
- * 	Every UID task group (including init_task_group aka UID-0) will
- * 	be a child to this group.
+ *	Every UID task group (including init_task_group aka UID-0) will
+ *	be a child to this group.
  */
 struct task_group root_task_group;
 
@@ -318,7 +295,7 @@ struct task_group root_task_group;
 /* Default task group's sched entity on each cpu */
 static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
 /* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(struct cfs_rq, init_tg_cfs_rq) ____cacheline_aligned_in_smp;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -616,6 +593,7 @@ struct rq {
 
 	unsigned char idle_at_tick;
 	/* For active balancing */
+	int post_schedule;
 	int active_balance;
 	int push_cpu;
 	/* cpu of this runqueue: */
@@ -626,6 +604,9 @@ struct rq {
 
 	struct task_struct *migration_thread;
 	struct list_head migration_queue;
+
+	u64 rt_avg;
+	u64 age_stamp;
 #endif
 
 	/* calc_load related fields */
@@ -693,6 +674,7 @@ static inline int cpu_of(struct rq *rq)
 #define this_rq()		(&__get_cpu_var(runqueues))
 #define task_rq(p)		cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+#define raw_rq()		(&__raw_get_cpu_var(runqueues))
 
 inline void update_rq_clock(struct rq *rq)
 {
@@ -861,6 +843,14 @@ unsigned int sysctl_sched_shares_ratelimit = 250000;
 unsigned int sysctl_sched_shares_thresh = 4;
 
 /*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -1278,12 +1268,37 @@ void wake_up_idle_cpu(int cpu)
 }
 #endif /* CONFIG_NO_HZ */
 
+static u64 sched_avg_period(void)
+{
+	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+	s64 period = sched_avg_period();
+
+	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		rq->age_stamp += period;
+		rq->rt_avg /= 2;
+	}
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+	rq->rt_avg += rt_delta;
+	sched_avg_update(rq);
+}
+
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
 	assert_spin_locked(&task_rq(p)->lock);
 	set_tsk_need_resched(p);
 }
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -1513,28 +1528,35 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
+struct update_shares_data {
+	unsigned long rq_weight[NR_CPUS];
+};
+
+static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
 /*
  * Calculate and set the cpu's group shares.
  */
-static void
-update_group_shares_cpu(struct task_group *tg, int cpu,
-			unsigned long sd_shares, unsigned long sd_rq_weight)
+static void update_group_shares_cpu(struct task_group *tg, int cpu,
+				    unsigned long sd_shares,
+				    unsigned long sd_rq_weight,
+				    struct update_shares_data *usd)
 {
-	unsigned long shares;
-	unsigned long rq_weight;
-
-	if (!tg->se[cpu])
-		return;
+	unsigned long shares, rq_weight;
+	int boost = 0;
 
-	rq_weight = tg->cfs_rq[cpu]->rq_weight;
+	rq_weight = usd->rq_weight[cpu];
+	if (!rq_weight) {
+		boost = 1;
+		rq_weight = NICE_0_LOAD;
+	}
 
 	/*
-	 *           \Sum shares * rq_weight
-	 * shares =  -----------------------
-	 *               \Sum rq_weight
-	 *
+	 *             \Sum_j shares_j * rq_weight_i
+	 * shares_i =  -----------------------------
+	 *                  \Sum_j rq_weight_j
 	 */
 	shares = (sd_shares * rq_weight) / sd_rq_weight;
 	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
@@ -1545,8 +1567,8 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
 		unsigned long flags;
 
 		spin_lock_irqsave(&rq->lock, flags);
-		tg->cfs_rq[cpu]->shares = shares;
-
+		tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
+		tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
 		__set_se_shares(tg->se[cpu], shares);
 		spin_unlock_irqrestore(&rq->lock, flags);
 	}
@@ -1559,22 +1581,30 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
  */
 static int tg_shares_up(struct task_group *tg, void *data)
 {
-	unsigned long weight, rq_weight = 0;
-	unsigned long shares = 0;
+	unsigned long weight, rq_weight = 0, shares = 0;
+	struct update_shares_data *usd;
 	struct sched_domain *sd = data;
+	unsigned long flags;
 	int i;
 
+	if (!tg->se[0])
+		return 0;
+
+	local_irq_save(flags);
+	usd = &__get_cpu_var(update_shares_data);
+
 	for_each_cpu(i, sched_domain_span(sd)) {
+		weight = tg->cfs_rq[i]->load.weight;
+		usd->rq_weight[i] = weight;
+
 		/*
 		 * If there are currently no tasks on the cpu pretend there
 		 * is one of average load so that when a new task gets to
 		 * run here it will not get delayed by group starvation.
 		 */
-		weight = tg->cfs_rq[i]->load.weight;
 		if (!weight)
 			weight = NICE_0_LOAD;
 
-		tg->cfs_rq[i]->rq_weight = weight;
 		rq_weight += weight;
 		shares += tg->cfs_rq[i]->shares;
 	}
@@ -1586,7 +1616,9 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		shares = tg->shares;
 
 	for_each_cpu(i, sched_domain_span(sd))
-		update_group_shares_cpu(tg, i, shares, rq_weight);
+		update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+
+	local_irq_restore(flags);
 
 	return 0;
 }
@@ -1616,8 +1648,14 @@ static int tg_load_down(struct task_group *tg, void *data)
 
 static void update_shares(struct sched_domain *sd)
 {
-	u64 now = cpu_clock(raw_smp_processor_id());
-	s64 elapsed = now - sd->last_update;
+	s64 elapsed;
+	u64 now;
+
+	if (root_task_group_empty())
+		return;
+
+	now = cpu_clock(raw_smp_processor_id());
+	elapsed = now - sd->last_update;
 
 	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
 		sd->last_update = now;
@@ -1627,6 +1665,9 @@ static void update_shares(struct sched_domain *sd)
 
 static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 {
+	if (root_task_group_empty())
+		return;
+
 	spin_unlock(&rq->lock);
 	update_shares(sd);
 	spin_lock(&rq->lock);
@@ -1634,6 +1675,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 static void update_h_load(long cpu)
 {
+	if (root_task_group_empty())
+		return;
+
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
@@ -2268,8 +2312,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 		}
 
 		/* Adjust by relative CPU power of the group */
-		avg_load = sg_div_cpu_power(group,
-				avg_load * SCHED_LOAD_SCALE);
+		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 		if (local_group) {
 			this_load = avg_load;
@@ -2637,9 +2680,32 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	set_task_cpu(p, cpu);
 
 	/*
-	 * Make sure we do not leak PI boosting priority to the child:
+	 * Make sure we do not leak PI boosting priority to the child.
 	 */
 	p->prio = current->normal_prio;
+
+	/*
+	 * Revert to default priority/policy on fork if requested.
+	 */
+	if (unlikely(p->sched_reset_on_fork)) {
+		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+			p->policy = SCHED_NORMAL;
+
+		if (p->normal_prio < DEFAULT_PRIO)
+			p->prio = DEFAULT_PRIO;
+
+		if (PRIO_TO_NICE(p->static_prio) < 0) {
+			p->static_prio = NICE_TO_PRIO(0);
+			set_load_weight(p);
+		}
+
+		/*
+		 * We don't need the reset flag anymore after the fork. It has
+		 * fulfilled its duty:
+		 */
+		p->sched_reset_on_fork = 0;
+	}
+
 	if (!rt_prio(p->prio))
 		p->sched_class = &fair_sched_class;
 
@@ -2796,12 +2862,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 {
 	struct mm_struct *mm = rq->prev_mm;
 	long prev_state;
-#ifdef CONFIG_SMP
-	int post_schedule = 0;
-
-	if (current->sched_class->needs_post_schedule)
-		post_schedule = current->sched_class->needs_post_schedule(rq);
-#endif
 
 	rq->prev_mm = NULL;
 
@@ -2820,10 +2880,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	finish_arch_switch(prev);
 	perf_counter_task_sched_in(current, cpu_of(rq));
 	finish_lock_switch(rq, prev);
-#ifdef CONFIG_SMP
-	if (post_schedule)
-		current->sched_class->post_schedule(rq);
-#endif
 
 	fire_sched_in_preempt_notifiers(current);
 	if (mm)
@@ -2838,6 +2894,42 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+#ifdef CONFIG_SMP
+
+/* assumes rq->lock is held */
+static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
+{
+	if (prev->sched_class->pre_schedule)
+		prev->sched_class->pre_schedule(rq, prev);
+}
+
+/* rq->lock is NOT held, but preemption is disabled */
+static inline void post_schedule(struct rq *rq)
+{
+	if (rq->post_schedule) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&rq->lock, flags);
+		if (rq->curr->sched_class->post_schedule)
+			rq->curr->sched_class->post_schedule(rq);
+		spin_unlock_irqrestore(&rq->lock, flags);
+
+		rq->post_schedule = 0;
+	}
+}
+
+#else
+
+static inline void pre_schedule(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline void post_schedule(struct rq *rq)
+{
+}
+
+#endif
+
 /**
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
@@ -2848,6 +2940,13 @@ asmlinkage void schedule_tail(struct task_struct *prev)
 	struct rq *rq = this_rq();
 
 	finish_task_switch(rq, prev);
+
+	/*
+	 * FIXME: do we need to worry about rq being invalidated by the
+	 * task_switch?
+	 */
+	post_schedule(rq);
+
 #ifdef __ARCH_WANT_UNLOCKED_CTXSW
 	/* In this case, finish_task_switch does not reenable preemption */
 	preempt_enable();
@@ -3379,9 +3478,10 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 {
 	const struct sched_class *class;
 
-	for (class = sched_class_highest; class; class = class->next)
+	for_each_class(class) {
 		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
 			return 1;
+	}
 
 	return 0;
 }
@@ -3544,7 +3644,7 @@ static inline void update_sd_power_savings_stats(struct sched_group *group,
 	 * capacity but still has some space to pick up some load
 	 * from other group and save more power
 	 */
-	if (sgs->sum_nr_running > sgs->group_capacity - 1)
+	if (sgs->sum_nr_running + 1 > sgs->group_capacity)
 		return;
 
 	if (sgs->sum_nr_running > sds->leader_nr_running ||
@@ -3611,6 +3711,77 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long power = SCHED_LOAD_SCALE;
+	struct sched_group *sdg = sd->groups;
+
+	/* here we could scale based on cpufreq */
+
+	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+		power *= arch_scale_smt_power(sd, cpu);
+		power >>= SCHED_LOAD_SHIFT;
+	}
+
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
+
+	sdg->cpu_power = power;
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power;
+
+	if (!child) {
+		update_cpu_power(sd, cpu);
+		return;
+	}
+
+	power = 0;
+
+	group = child->groups;
+	do {
+		power += group->cpu_power;
+		group = group->next;
+	} while (group != child->groups);
+
+	sdg->cpu_power = power;
+}
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
@@ -3624,7 +3795,8 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
  * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
-static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+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,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
@@ -3635,8 +3807,11 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	unsigned long sum_avg_load_per_task;
 	unsigned long avg_load_per_task;
 
-	if (local_group)
+	if (local_group) {
 		balance_cpu = group_first_cpu(group);
+		if (balance_cpu == this_cpu)
+			update_group_power(sd, this_cpu);
+	}
 
 	/* Tally up the load of all CPUs in the group */
 	sum_avg_load_per_task = avg_load_per_task = 0;
@@ -3685,8 +3860,7 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	}
 
 	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = sg_div_cpu_power(group,
-			sgs->group_load * SCHED_LOAD_SCALE);
+	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 
 	/*
@@ -3698,14 +3872,14 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	 *      normalized nr_running number somewhere that negates
 	 *      the hierarchy?
 	 */
-	avg_load_per_task = sg_div_cpu_power(group,
-			sum_avg_load_per_task * SCHED_LOAD_SCALE);
+	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+		group->cpu_power;
 
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
 
-	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
-
+	sgs->group_capacity =
+		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 }
 
 /**
@@ -3723,9 +3897,13 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			const struct cpumask *cpus, int *balance,
 			struct sd_lb_stats *sds)
 {
+	struct sched_domain *child = sd->child;
 	struct sched_group *group = sd->groups;
 	struct sg_lb_stats sgs;
-	int load_idx;
+	int load_idx, prefer_sibling = 0;
+
+	if (child && child->flags & SD_PREFER_SIBLING)
+		prefer_sibling = 1;
 
 	init_sd_power_savings_stats(sd, sds, idle);
 	load_idx = get_sd_load_idx(sd, idle);
@@ -3736,14 +3914,22 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_cpus(group));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
 				local_group, cpus, balance, &sgs);
 
 		if (local_group && balance && !(*balance))
 			return;
 
 		sds->total_load += sgs.group_load;
-		sds->total_pwr += group->__cpu_power;
+		sds->total_pwr += group->cpu_power;
+
+		/*
+		 * In case the child domain prefers tasks go to siblings
+		 * first, lower the group capacity to one so that we'll try
+		 * and move all the excess tasks away.
+		 */
+		if (prefer_sibling)
+			sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
 		if (local_group) {
 			sds->this_load = sgs.avg_load;
@@ -3763,7 +3949,6 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		update_sd_power_savings_stats(group, sds, local_group, &sgs);
 		group = group->next;
 	} while (group != sd->groups);
-
 }
 
 /**
@@ -3801,28 +3986,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 	 * moving them.
 	 */
 
-	pwr_now += sds->busiest->__cpu_power *
+	pwr_now += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->__cpu_power *
+	pwr_now += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load);
 	pwr_now /= SCHED_LOAD_SCALE;
 
 	/* Amount of load we'd subtract */
-	tmp = sg_div_cpu_power(sds->busiest,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+		sds->busiest->cpu_power;
 	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->__cpu_power *
+		pwr_move += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load - tmp);
 
 	/* Amount of load we'd add */
-	if (sds->max_load * sds->busiest->__cpu_power <
+	if (sds->max_load * sds->busiest->cpu_power <
 		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
-		tmp = sg_div_cpu_power(sds->this,
-			sds->max_load * sds->busiest->__cpu_power);
+		tmp = (sds->max_load * sds->busiest->cpu_power) /
+			sds->this->cpu_power;
 	else
-		tmp = sg_div_cpu_power(sds->this,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
-	pwr_move += sds->this->__cpu_power *
+		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+			sds->this->cpu_power;
+	pwr_move += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load + tmp);
 	pwr_move /= SCHED_LOAD_SCALE;
 
@@ -3857,8 +4042,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 			sds->max_load - sds->busiest_load_per_task);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->__cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
+	*imbalance = min(max_pull * sds->busiest->cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
 			/ SCHED_LOAD_SCALE;
 
 	/*
@@ -3976,6 +4161,26 @@ ret:
 	return NULL;
 }
 
+static struct sched_group *group_of(int cpu)
+{
+	struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return NULL;
+
+	return sd->groups;
+}
+
+static unsigned long power_of(int cpu)
+{
+	struct sched_group *group = group_of(cpu);
+
+	if (!group)
+		return SCHED_LOAD_SCALE;
+
+	return group->cpu_power;
+}
+
 /*
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
@@ -3988,15 +4193,18 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
 	int i;
 
 	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long power = power_of(i);
+		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
 		unsigned long wl;
 
 		if (!cpumask_test_cpu(i, cpus))
 			continue;
 
 		rq = cpu_rq(i);
-		wl = weighted_cpuload(i);
+		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+		wl /= power;
 
-		if (rq->nr_running == 1 && wl > imbalance)
+		if (capacity && rq->nr_running == 1 && wl > imbalance)
 			continue;
 
 		if (wl > max_load) {
@@ -5325,7 +5533,7 @@ need_resched:
 	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_qsctr_inc(cpu);
+	rcu_sched_qs(cpu);
 	prev = rq->curr;
 	switch_count = &prev->nivcsw;
 
@@ -5349,10 +5557,7 @@ need_resched_nonpreemptible:
 		switch_count = &prev->nvcsw;
 	}
 
-#ifdef CONFIG_SMP
-	if (prev->sched_class->pre_schedule)
-		prev->sched_class->pre_schedule(rq, prev);
-#endif
+	pre_schedule(rq, prev);
 
 	if (unlikely(!rq->nr_running))
 		idle_balance(cpu, rq);
@@ -5378,6 +5583,8 @@ need_resched_nonpreemptible:
 	} else
 		spin_unlock_irq(&rq->lock);
 
+	post_schedule(rq);
+
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
 
@@ -6123,17 +6330,25 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
 	unsigned long flags;
 	const struct sched_class *prev_class = p->sched_class;
 	struct rq *rq;
+	int reset_on_fork;
 
 	/* may grab non-irq protected spin_locks */
 	BUG_ON(in_interrupt());
 recheck:
 	/* double check policy once rq lock held */
-	if (policy < 0)
+	if (policy < 0) {
+		reset_on_fork = p->sched_reset_on_fork;
 		policy = oldpolicy = p->policy;
-	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
-			policy != SCHED_NORMAL && policy != SCHED_BATCH &&
-			policy != SCHED_IDLE)
-		return -EINVAL;
+	} else {
+		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+		policy &= ~SCHED_RESET_ON_FORK;
+
+		if (policy != SCHED_FIFO && policy != SCHED_RR &&
+				policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+				policy != SCHED_IDLE)
+			return -EINVAL;
+	}
+
 	/*
 	 * Valid priorities for SCHED_FIFO and SCHED_RR are
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
@@ -6177,6 +6392,10 @@ recheck:
 		/* can't change other user's priorities */
 		if (!check_same_owner(p))
 			return -EPERM;
+
+		/* Normal users shall not reset the sched_reset_on_fork flag */
+		if (p->sched_reset_on_fork && !reset_on_fork)
+			return -EPERM;
 	}
 
 	if (user) {
@@ -6220,6 +6439,8 @@ recheck:
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
+	p->sched_reset_on_fork = reset_on_fork;
+
 	oldprio = p->prio;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
@@ -6336,14 +6557,15 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 	if (p) {
 		retval = security_task_getscheduler(p);
 		if (!retval)
-			retval = p->policy;
+			retval = p->policy
+				| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
 	}
 	read_unlock(&tasklist_lock);
 	return retval;
 }
 
 /**
- * sys_sched_getscheduler - get the RT priority of a thread
+ * sys_sched_getparam - get the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
@@ -6571,19 +6793,9 @@ static inline int should_resched(void)
 
 static void __cond_resched(void)
 {
-#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-	__might_sleep(__FILE__, __LINE__);
-#endif
-	/*
-	 * The BKS might be reacquired before we have dropped
-	 * PREEMPT_ACTIVE, which could trigger a second
-	 * cond_resched() call.
-	 */
-	do {
-		add_preempt_count(PREEMPT_ACTIVE);
-		schedule();
-		sub_preempt_count(PREEMPT_ACTIVE);
-	} while (need_resched());
+	add_preempt_count(PREEMPT_ACTIVE);
+	schedule();
+	sub_preempt_count(PREEMPT_ACTIVE);
 }
 
 int __sched _cond_resched(void)
@@ -6597,18 +6809,20 @@ int __sched _cond_resched(void)
 EXPORT_SYMBOL(_cond_resched);
 
 /*
- * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
  * call schedule, and on return reacquire the lock.
  *
  * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
  * operations here to prevent schedule() from being called twice (once via
  * spin_unlock(), once by hand).
  */
-int cond_resched_lock(spinlock_t *lock)
+int __cond_resched_lock(spinlock_t *lock)
 {
 	int resched = should_resched();
 	int ret = 0;
 
+	lockdep_assert_held(lock);
+
 	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
 		if (resched)
@@ -6620,9 +6834,9 @@ int cond_resched_lock(spinlock_t *lock)
 	}
 	return ret;
 }
-EXPORT_SYMBOL(cond_resched_lock);
+EXPORT_SYMBOL(__cond_resched_lock);
 
-int __sched cond_resched_softirq(void)
+int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
@@ -6634,7 +6848,7 @@ int __sched cond_resched_softirq(void)
 	}
 	return 0;
 }
-EXPORT_SYMBOL(cond_resched_softirq);
+EXPORT_SYMBOL(__cond_resched_softirq);
 
 /**
  * yield - yield the current processor to other threads.
@@ -6658,11 +6872,13 @@ EXPORT_SYMBOL(yield);
  */
 void __sched io_schedule(void)
 {
-	struct rq *rq = &__raw_get_cpu_var(runqueues);
+	struct rq *rq = raw_rq();
 
 	delayacct_blkio_start();
 	atomic_inc(&rq->nr_iowait);
+	current->in_iowait = 1;
 	schedule();
+	current->in_iowait = 0;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
 }
@@ -6670,12 +6886,14 @@ EXPORT_SYMBOL(io_schedule);
 
 long __sched io_schedule_timeout(long timeout)
 {
-	struct rq *rq = &__raw_get_cpu_var(runqueues);
+	struct rq *rq = raw_rq();
 	long ret;
 
 	delayacct_blkio_start();
 	atomic_inc(&rq->nr_iowait);
+	current->in_iowait = 1;
 	ret = schedule_timeout(timeout);
+	current->in_iowait = 0;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
 	return ret;
@@ -6992,8 +7210,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
 	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
 		/* Need help from migration thread: drop lock and wait. */
+		struct task_struct *mt = rq->migration_thread;
+
+		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
 		wake_up_process(rq->migration_thread);
+		put_task_struct(mt);
 		wait_for_completion(&req.done);
 		tlb_migrate_finish(p->mm);
 		return 0;
@@ -7051,6 +7273,11 @@ fail:
 	return ret;
 }
 
+#define RCU_MIGRATION_IDLE	0
+#define RCU_MIGRATION_NEED_QS	1
+#define RCU_MIGRATION_GOT_QS	2
+#define RCU_MIGRATION_MUST_SYNC	3
+
 /*
  * migration_thread - this is a highprio system thread that performs
  * thread migration by bumping thread off CPU then 'pushing' onto
@@ -7058,6 +7285,7 @@ fail:
  */
 static int migration_thread(void *data)
 {
+	int badcpu;
 	int cpu = (long)data;
 	struct rq *rq;
 
@@ -7092,8 +7320,17 @@ static int migration_thread(void *data)
 		req = list_entry(head->next, struct migration_req, list);
 		list_del_init(head->next);
 
-		spin_unlock(&rq->lock);
-		__migrate_task(req->task, cpu, req->dest_cpu);
+		if (req->task != NULL) {
+			spin_unlock(&rq->lock);
+			__migrate_task(req->task, cpu, req->dest_cpu);
+		} else if (likely(cpu == (badcpu = smp_processor_id()))) {
+			req->dest_cpu = RCU_MIGRATION_GOT_QS;
+			spin_unlock(&rq->lock);
+		} else {
+			req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
+			spin_unlock(&rq->lock);
+			WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
+		}
 		local_irq_enable();
 
 		complete(&req->done);
@@ -7625,7 +7862,7 @@ static int __init migration_init(void)
 	migration_call(&migration_notifier, CPU_ONLINE, cpu);
 	register_cpu_notifier(&migration_notifier);
 
-	return err;
+	return 0;
 }
 early_initcall(migration_init);
 #endif
@@ -7672,7 +7909,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!group->__cpu_power) {
+		if (!group->cpu_power) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -7696,9 +7933,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->__cpu_power != SCHED_LOAD_SCALE) {
-			printk(KERN_CONT " (__cpu_power = %d)",
-				group->__cpu_power);
+		if (group->cpu_power != SCHED_LOAD_SCALE) {
+			printk(KERN_CONT " (cpu_power = %d)",
+				group->cpu_power);
 		}
 
 		group = group->next;
@@ -7841,7 +8078,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	rq->rd = rd;
 
 	cpumask_set_cpu(rq->cpu, rd->span);
-	if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
@@ -7983,7 +8220,7 @@ init_sched_build_groups(const struct cpumask *span,
 			continue;
 
 		cpumask_clear(sched_group_cpus(sg));
-		sg->__cpu_power = 0;
+		sg->cpu_power = 0;
 
 		for_each_cpu(j, span) {
 			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
@@ -8091,6 +8328,39 @@ struct static_sched_domain {
 	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
 };
 
+struct s_data {
+#ifdef CONFIG_NUMA
+	int			sd_allnodes;
+	cpumask_var_t		domainspan;
+	cpumask_var_t		covered;
+	cpumask_var_t		notcovered;
+#endif
+	cpumask_var_t		nodemask;
+	cpumask_var_t		this_sibling_map;
+	cpumask_var_t		this_core_map;
+	cpumask_var_t		send_covered;
+	cpumask_var_t		tmpmask;
+	struct sched_group	**sched_group_nodes;
+	struct root_domain	*rd;
+};
+
+enum s_alloc {
+	sa_sched_groups = 0,
+	sa_rootdomain,
+	sa_tmpmask,
+	sa_send_covered,
+	sa_this_core_map,
+	sa_this_sibling_map,
+	sa_nodemask,
+	sa_sched_group_nodes,
+#ifdef CONFIG_NUMA
+	sa_notcovered,
+	sa_covered,
+	sa_domainspan,
+#endif
+	sa_none,
+};
+
 /*
  * SMT sched-domains:
  */
@@ -8208,11 +8478,76 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 				continue;
 			}
 
-			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+			sg->cpu_power += sd->groups->cpu_power;
 		}
 		sg = sg->next;
 	} while (sg != group_head);
 }
+
+static int build_numa_sched_groups(struct s_data *d,
+				   const struct cpumask *cpu_map, int num)
+{
+	struct sched_domain *sd;
+	struct sched_group *sg, *prev;
+	int n, j;
+
+	cpumask_clear(d->covered);
+	cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
+	if (cpumask_empty(d->nodemask)) {
+		d->sched_group_nodes[num] = NULL;
+		goto out;
+	}
+
+	sched_domain_node_span(num, d->domainspan);
+	cpumask_and(d->domainspan, d->domainspan, cpu_map);
+
+	sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+			  GFP_KERNEL, num);
+	if (!sg) {
+		printk(KERN_WARNING "Can not alloc domain group for node %d\n",
+		       num);
+		return -ENOMEM;
+	}
+	d->sched_group_nodes[num] = sg;
+
+	for_each_cpu(j, d->nodemask) {
+		sd = &per_cpu(node_domains, j).sd;
+		sd->groups = sg;
+	}
+
+	sg->cpu_power = 0;
+	cpumask_copy(sched_group_cpus(sg), d->nodemask);
+	sg->next = sg;
+	cpumask_or(d->covered, d->covered, d->nodemask);
+
+	prev = sg;
+	for (j = 0; j < nr_node_ids; j++) {
+		n = (num + j) % nr_node_ids;
+		cpumask_complement(d->notcovered, d->covered);
+		cpumask_and(d->tmpmask, d->notcovered, cpu_map);
+		cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
+		if (cpumask_empty(d->tmpmask))
+			break;
+		cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
+		if (cpumask_empty(d->tmpmask))
+			continue;
+		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				  GFP_KERNEL, num);
+		if (!sg) {
+			printk(KERN_WARNING
+			       "Can not alloc domain group for node %d\n", j);
+			return -ENOMEM;
+		}
+		sg->cpu_power = 0;
+		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
+		sg->next = prev->next;
+		cpumask_or(d->covered, d->covered, d->tmpmask);
+		prev->next = sg;
+		prev = sg;
+	}
+out:
+	return 0;
+}
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_NUMA
@@ -8266,15 +8601,13 @@ static void free_sched_groups(const struct cpumask *cpu_map,
  * there are asymmetries in the topology. If there are asymmetries, group
  * having more cpu_power will pickup more load compared to the group having
  * less cpu_power.
- *
- * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
- * the maximum number of tasks a group can handle in the presence of other idle
- * or lightly loaded groups in the same sched domain.
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
 	struct sched_domain *child;
 	struct sched_group *group;
+	long power;
+	int weight;
 
 	WARN_ON(!sd || !sd->groups);
 
@@ -8283,28 +8616,32 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	child = sd->child;
 
-	sd->groups->__cpu_power = 0;
+	sd->groups->cpu_power = 0;
 
-	/*
-	 * For perf policy, if the groups in child domain share resources
-	 * (for example cores sharing some portions of the cache hierarchy
-	 * or SMT), then set this domain groups cpu_power such that each group
-	 * can handle only one task, when there are other idle groups in the
-	 * same sched domain.
-	 */
-	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
-		       (child->flags &
-			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
-		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+	if (!child) {
+		power = SCHED_LOAD_SCALE;
+		weight = cpumask_weight(sched_domain_span(sd));
+		/*
+		 * SMT siblings share the power of a single core.
+		 * Usually multiple threads get a better yield out of
+		 * that one core than a single thread would have,
+		 * reflect that in sd->smt_gain.
+		 */
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+			power *= sd->smt_gain;
+			power /= weight;
+			power >>= SCHED_LOAD_SHIFT;
+		}
+		sd->groups->cpu_power += power;
 		return;
 	}
 
 	/*
-	 * add cpu_power of each child group to this groups cpu_power
+	 * Add cpu_power of each child group to this groups cpu_power.
 	 */
 	group = child->groups;
 	do {
-		sg_inc_cpu_power(sd->groups, group->__cpu_power);
+		sd->groups->cpu_power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
 }
@@ -8378,280 +8715,285 @@ static void set_domain_attribute(struct sched_domain *sd,
 	}
 }
 
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-static int __build_sched_domains(const struct cpumask *cpu_map,
-				 struct sched_domain_attr *attr)
-{
-	int i, err = -ENOMEM;
-	struct root_domain *rd;
-	cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
-		tmpmask;
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+				 const struct cpumask *cpu_map)
+{
+	switch (what) {
+	case sa_sched_groups:
+		free_sched_groups(cpu_map, d->tmpmask); /* fall through */
+		d->sched_group_nodes = NULL;
+	case sa_rootdomain:
+		free_rootdomain(d->rd); /* fall through */
+	case sa_tmpmask:
+		free_cpumask_var(d->tmpmask); /* fall through */
+	case sa_send_covered:
+		free_cpumask_var(d->send_covered); /* fall through */
+	case sa_this_core_map:
+		free_cpumask_var(d->this_core_map); /* fall through */
+	case sa_this_sibling_map:
+		free_cpumask_var(d->this_sibling_map); /* fall through */
+	case sa_nodemask:
+		free_cpumask_var(d->nodemask); /* fall through */
+	case sa_sched_group_nodes:
 #ifdef CONFIG_NUMA
-	cpumask_var_t domainspan, covered, notcovered;
-	struct sched_group **sched_group_nodes = NULL;
-	int sd_allnodes = 0;
-
-	if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
-		goto out;
-	if (!alloc_cpumask_var(&covered, GFP_KERNEL))
-		goto free_domainspan;
-	if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
-		goto free_covered;
-#endif
-
-	if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
-		goto free_notcovered;
-	if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
-		goto free_nodemask;
-	if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
-		goto free_this_sibling_map;
-	if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
-		goto free_this_core_map;
-	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		goto free_send_covered;
+		kfree(d->sched_group_nodes); /* fall through */
+	case sa_notcovered:
+		free_cpumask_var(d->notcovered); /* fall through */
+	case sa_covered:
+		free_cpumask_var(d->covered); /* fall through */
+	case sa_domainspan:
+		free_cpumask_var(d->domainspan); /* fall through */
+#endif
+	case sa_none:
+		break;
+	}
+}
 
+static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
+						   const struct cpumask *cpu_map)
+{
 #ifdef CONFIG_NUMA
-	/*
-	 * Allocate the per-node list of sched groups
-	 */
-	sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
-				    GFP_KERNEL);
-	if (!sched_group_nodes) {
+	if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
+		return sa_none;
+	if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
+		return sa_domainspan;
+	if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
+		return sa_covered;
+	/* Allocate the per-node list of sched groups */
+	d->sched_group_nodes = kcalloc(nr_node_ids,
+				      sizeof(struct sched_group *), GFP_KERNEL);
+	if (!d->sched_group_nodes) {
 		printk(KERN_WARNING "Can not alloc sched group node list\n");
-		goto free_tmpmask;
-	}
-#endif
-
-	rd = alloc_rootdomain();
-	if (!rd) {
+		return sa_notcovered;
+	}
+	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
+#endif
+	if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
+		return sa_sched_group_nodes;
+	if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
+		return sa_nodemask;
+	if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
+		return sa_this_sibling_map;
+	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+		return sa_this_core_map;
+	if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
+		return sa_send_covered;
+	d->rd = alloc_rootdomain();
+	if (!d->rd) {
 		printk(KERN_WARNING "Cannot alloc root domain\n");
-		goto free_sched_groups;
+		return sa_tmpmask;
 	}
+	return sa_rootdomain;
+}
 
+static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
+{
+	struct sched_domain *sd = NULL;
 #ifdef CONFIG_NUMA
-	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
-#endif
-
-	/*
-	 * Set up domains for cpus specified by the cpu_map.
-	 */
-	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = NULL, *p;
-
-		cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
-
-#ifdef CONFIG_NUMA
-		if (cpumask_weight(cpu_map) >
-				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
-			sd = &per_cpu(allnodes_domains, i).sd;
-			SD_INIT(sd, ALLNODES);
-			set_domain_attribute(sd, attr);
-			cpumask_copy(sched_domain_span(sd), cpu_map);
-			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
-			p = sd;
-			sd_allnodes = 1;
-		} else
-			p = NULL;
+	struct sched_domain *parent;
 
-		sd = &per_cpu(node_domains, i).sd;
-		SD_INIT(sd, NODE);
+	d->sd_allnodes = 0;
+	if (cpumask_weight(cpu_map) >
+	    SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
+		sd = &per_cpu(allnodes_domains, i).sd;
+		SD_INIT(sd, ALLNODES);
 		set_domain_attribute(sd, attr);
-		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
-		sd->parent = p;
-		if (p)
-			p->child = sd;
-		cpumask_and(sched_domain_span(sd),
-			    sched_domain_span(sd), cpu_map);
+		cpumask_copy(sched_domain_span(sd), cpu_map);
+		cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
+		d->sd_allnodes = 1;
+	}
+	parent = sd;
+
+	sd = &per_cpu(node_domains, i).sd;
+	SD_INIT(sd, NODE);
+	set_domain_attribute(sd, attr);
+	sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
+	sd->parent = parent;
+	if (parent)
+		parent->child = sd;
+	cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
 #endif
+	return sd;
+}
 
-		p = sd;
-		sd = &per_cpu(phys_domains, i).sd;
-		SD_INIT(sd, CPU);
-		set_domain_attribute(sd, attr);
-		cpumask_copy(sched_domain_span(sd), nodemask);
-		sd->parent = p;
-		if (p)
-			p->child = sd;
-		cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
+static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd;
+	sd = &per_cpu(phys_domains, i).sd;
+	SD_INIT(sd, CPU);
+	set_domain_attribute(sd, attr);
+	cpumask_copy(sched_domain_span(sd), d->nodemask);
+	sd->parent = parent;
+	if (parent)
+		parent->child = sd;
+	cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
+	return sd;
+}
 
+static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd = parent;
 #ifdef CONFIG_SCHED_MC
-		p = sd;
-		sd = &per_cpu(core_domains, i).sd;
-		SD_INIT(sd, MC);
-		set_domain_attribute(sd, attr);
-		cpumask_and(sched_domain_span(sd), cpu_map,
-						   cpu_coregroup_mask(i));
-		sd->parent = p;
-		p->child = sd;
-		cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
+	sd = &per_cpu(core_domains, i).sd;
+	SD_INIT(sd, MC);
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
+	sd->parent = parent;
+	parent->child = sd;
+	cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
 #endif
+	return sd;
+}
 
+static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd = parent;
 #ifdef CONFIG_SCHED_SMT
-		p = sd;
-		sd = &per_cpu(cpu_domains, i).sd;
-		SD_INIT(sd, SIBLING);
-		set_domain_attribute(sd, attr);
-		cpumask_and(sched_domain_span(sd),
-			    topology_thread_cpumask(i), cpu_map);
-		sd->parent = p;
-		p->child = sd;
-		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
+	sd = &per_cpu(cpu_domains, i).sd;
+	SD_INIT(sd, SIBLING);
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
+	sd->parent = parent;
+	parent->child = sd;
+	cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
 #endif
-	}
+	return sd;
+}
 
+static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
+			       const struct cpumask *cpu_map, int cpu)
+{
+	switch (l) {
 #ifdef CONFIG_SCHED_SMT
-	/* Set up CPU (sibling) groups */
-	for_each_cpu(i, cpu_map) {
-		cpumask_and(this_sibling_map,
-			    topology_thread_cpumask(i), cpu_map);
-		if (i != cpumask_first(this_sibling_map))
-			continue;
-
-		init_sched_build_groups(this_sibling_map, cpu_map,
-					&cpu_to_cpu_group,
-					send_covered, tmpmask);
-	}
+	case SD_LV_SIBLING: /* set up CPU (sibling) groups */
+		cpumask_and(d->this_sibling_map, cpu_map,
+			    topology_thread_cpumask(cpu));
+		if (cpu == cpumask_first(d->this_sibling_map))
+			init_sched_build_groups(d->this_sibling_map, cpu_map,
+						&cpu_to_cpu_group,
+						d->send_covered, d->tmpmask);
+		break;
 #endif
-
 #ifdef CONFIG_SCHED_MC
-	/* Set up multi-core groups */
-	for_each_cpu(i, cpu_map) {
-		cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
-		if (i != cpumask_first(this_core_map))
-			continue;
-
-		init_sched_build_groups(this_core_map, cpu_map,
-					&cpu_to_core_group,
-					send_covered, tmpmask);
-	}
+	case SD_LV_MC: /* set up multi-core groups */
+		cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
+		if (cpu == cpumask_first(d->this_core_map))
+			init_sched_build_groups(d->this_core_map, cpu_map,
+						&cpu_to_core_group,
+						d->send_covered, d->tmpmask);
+		break;
 #endif
-
-	/* Set up physical groups */
-	for (i = 0; i < nr_node_ids; i++) {
-		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
-		if (cpumask_empty(nodemask))
-			continue;
-
-		init_sched_build_groups(nodemask, cpu_map,
-					&cpu_to_phys_group,
-					send_covered, tmpmask);
-	}
-
+	case SD_LV_CPU: /* set up physical groups */
+		cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
+		if (!cpumask_empty(d->nodemask))
+			init_sched_build_groups(d->nodemask, cpu_map,
+						&cpu_to_phys_group,
+						d->send_covered, d->tmpmask);
+		break;
 #ifdef CONFIG_NUMA
-	/* Set up node groups */
-	if (sd_allnodes) {
-		init_sched_build_groups(cpu_map, cpu_map,
-					&cpu_to_allnodes_group,
-					send_covered, tmpmask);
+	case SD_LV_ALLNODES:
+		init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
+					d->send_covered, d->tmpmask);
+		break;
+#endif
+	default:
+		break;
 	}
+}
 
-	for (i = 0; i < nr_node_ids; i++) {
-		/* Set up node groups */
-		struct sched_group *sg, *prev;
-		int j;
-
-		cpumask_clear(covered);
-		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
-		if (cpumask_empty(nodemask)) {
-			sched_group_nodes[i] = NULL;
-			continue;
-		}
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int __build_sched_domains(const struct cpumask *cpu_map,
+				 struct sched_domain_attr *attr)
+{
+	enum s_alloc alloc_state = sa_none;
+	struct s_data d;
+	struct sched_domain *sd;
+	int i;
+#ifdef CONFIG_NUMA
+	d.sd_allnodes = 0;
+#endif
 
-		sched_domain_node_span(i, domainspan);
-		cpumask_and(domainspan, domainspan, cpu_map);
+	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+	if (alloc_state != sa_rootdomain)
+		goto error;
+	alloc_state = sa_sched_groups;
 
-		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				  GFP_KERNEL, i);
-		if (!sg) {
-			printk(KERN_WARNING "Can not alloc domain group for "
-				"node %d\n", i);
-			goto error;
-		}
-		sched_group_nodes[i] = sg;
-		for_each_cpu(j, nodemask) {
-			struct sched_domain *sd;
+	/*
+	 * Set up domains for cpus specified by the cpu_map.
+	 */
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
+			    cpu_map);
 
-			sd = &per_cpu(node_domains, j).sd;
-			sd->groups = sg;
-		}
-		sg->__cpu_power = 0;
-		cpumask_copy(sched_group_cpus(sg), nodemask);
-		sg->next = sg;
-		cpumask_or(covered, covered, nodemask);
-		prev = sg;
+		sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
+		sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+		sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
+		sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
+	}
 
-		for (j = 0; j < nr_node_ids; j++) {
-			int n = (i + j) % nr_node_ids;
+	for_each_cpu(i, cpu_map) {
+		build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+		build_sched_groups(&d, SD_LV_MC, cpu_map, i);
+	}
 
-			cpumask_complement(notcovered, covered);
-			cpumask_and(tmpmask, notcovered, cpu_map);
-			cpumask_and(tmpmask, tmpmask, domainspan);
-			if (cpumask_empty(tmpmask))
-				break;
+	/* Set up physical groups */
+	for (i = 0; i < nr_node_ids; i++)
+		build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
 
-			cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
-			if (cpumask_empty(tmpmask))
-				continue;
+#ifdef CONFIG_NUMA
+	/* Set up node groups */
+	if (d.sd_allnodes)
+		build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
 
-			sg = kmalloc_node(sizeof(struct sched_group) +
-					  cpumask_size(),
-					  GFP_KERNEL, i);
-			if (!sg) {
-				printk(KERN_WARNING
-				"Can not alloc domain group for node %d\n", j);
-				goto error;
-			}
-			sg->__cpu_power = 0;
-			cpumask_copy(sched_group_cpus(sg), tmpmask);
-			sg->next = prev->next;
-			cpumask_or(covered, covered, tmpmask);
-			prev->next = sg;
-			prev = sg;
-		}
-	}
+	for (i = 0; i < nr_node_ids; i++)
+		if (build_numa_sched_groups(&d, cpu_map, i))
+			goto error;
 #endif
 
 	/* Calculate CPU power for physical packages and nodes */
 #ifdef CONFIG_SCHED_SMT
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
-
+		sd = &per_cpu(cpu_domains, i).sd;
 		init_sched_groups_power(i, sd);
 	}
 #endif
 #ifdef CONFIG_SCHED_MC
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = &per_cpu(core_domains, i).sd;
-
+		sd = &per_cpu(core_domains, i).sd;
 		init_sched_groups_power(i, sd);
 	}
 #endif
 
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
-
+		sd = &per_cpu(phys_domains, i).sd;
 		init_sched_groups_power(i, sd);
 	}
 
 #ifdef CONFIG_NUMA
 	for (i = 0; i < nr_node_ids; i++)
-		init_numa_sched_groups_power(sched_group_nodes[i]);
+		init_numa_sched_groups_power(d.sched_group_nodes[i]);
 
-	if (sd_allnodes) {
+	if (d.sd_allnodes) {
 		struct sched_group *sg;
 
 		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
-								tmpmask);
+								d.tmpmask);
 		init_numa_sched_groups_power(sg);
 	}
 #endif
 
 	/* Attach the domains */
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd;
 #ifdef CONFIG_SCHED_SMT
 		sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
@@ -8659,44 +9001,16 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 #else
 		sd = &per_cpu(phys_domains, i).sd;
 #endif
-		cpu_attach_domain(sd, rd, i);
+		cpu_attach_domain(sd, d.rd, i);
 	}
 
-	err = 0;
-
-free_tmpmask:
-	free_cpumask_var(tmpmask);
-free_send_covered:
-	free_cpumask_var(send_covered);
-free_this_core_map:
-	free_cpumask_var(this_core_map);
-free_this_sibling_map:
-	free_cpumask_var(this_sibling_map);
-free_nodemask:
-	free_cpumask_var(nodemask);
-free_notcovered:
-#ifdef CONFIG_NUMA
-	free_cpumask_var(notcovered);
-free_covered:
-	free_cpumask_var(covered);
-free_domainspan:
-	free_cpumask_var(domainspan);
-out:
-#endif
-	return err;
-
-free_sched_groups:
-#ifdef CONFIG_NUMA
-	kfree(sched_group_nodes);
-#endif
-	goto free_tmpmask;
+	d.sched_group_nodes = NULL; /* don't free this we still need it */
+	__free_domain_allocs(&d, sa_tmpmask, cpu_map);
+	return 0;
 
-#ifdef CONFIG_NUMA
 error:
-	free_sched_groups(cpu_map, tmpmask);
-	free_rootdomain(rd);
-	goto free_tmpmask;
-#endif
+	__free_domain_allocs(&d, alloc_state, cpu_map);
+	return -ENOMEM;
 }
 
 static int build_sched_domains(const struct cpumask *cpu_map)
@@ -9304,11 +9618,11 @@ void __init sched_init(void)
 		 * system cpu resource, based on the weight assigned to root
 		 * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
 		 * by letting tasks of init_task_group sit in a separate cfs_rq
-		 * (init_cfs_rq) and having one entity represent this group of
+		 * (init_tg_cfs_rq) and having one entity represent this group of
 		 * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
 		 */
 		init_tg_cfs_entry(&init_task_group,
-				&per_cpu(init_cfs_rq, i),
+				&per_cpu(init_tg_cfs_rq, i),
 				&per_cpu(init_sched_entity, i), i, 1,
 				root_task_group.se[i]);
 
@@ -9334,6 +9648,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
+		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
 		rq->push_cpu = 0;
@@ -9398,13 +9713,20 @@ void __init sched_init(void)
 }
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-void __might_sleep(char *file, int line)
+static inline int preempt_count_equals(int preempt_offset)
+{
+	int nested = preempt_count() & ~PREEMPT_ACTIVE;
+
+	return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+}
+
+void __might_sleep(char *file, int line, int preempt_offset)
 {
 #ifdef in_atomic
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
-	if ((!in_atomic() && !irqs_disabled()) ||
-		    system_state != SYSTEM_RUNNING || oops_in_progress)
+	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+	    system_state != SYSTEM_RUNNING || oops_in_progress)
 		return;
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
 		return;
@@ -10581,3 +10903,113 @@ struct cgroup_subsys cpuacct_subsys = {
 	.subsys_id = cpuacct_subsys_id,
 };
 #endif	/* CONFIG_CGROUP_CPUACCT */
+
+#ifndef CONFIG_SMP
+
+int rcu_expedited_torture_stats(char *page)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+void synchronize_sched_expedited(void)
+{
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
+static DEFINE_MUTEX(rcu_sched_expedited_mutex);
+
+#define RCU_EXPEDITED_STATE_POST -2
+#define RCU_EXPEDITED_STATE_IDLE -1
+
+static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+
+int rcu_expedited_torture_stats(char *page)
+{
+	int cnt = 0;
+	int cpu;
+
+	cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
+	for_each_online_cpu(cpu) {
+		 cnt += sprintf(&page[cnt], " %d:%d",
+				cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
+	}
+	cnt += sprintf(&page[cnt], "\n");
+	return cnt;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+static long synchronize_sched_expedited_count;
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly.  This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier.  Failing to
+ * observe this restriction will result in deadlock.
+ */
+void synchronize_sched_expedited(void)
+{
+	int cpu;
+	unsigned long flags;
+	bool need_full_sync = 0;
+	struct rq *rq;
+	struct migration_req *req;
+	long snap;
+	int trycount = 0;
+
+	smp_mb();  /* ensure prior mod happens before capturing snap. */
+	snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+	get_online_cpus();
+	while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+		put_online_cpus();
+		if (trycount++ < 10)
+			udelay(trycount * num_online_cpus());
+		else {
+			synchronize_sched();
+			return;
+		}
+		if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+			smp_mb(); /* ensure test happens before caller kfree */
+			return;
+		}
+		get_online_cpus();
+	}
+	rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
+	for_each_online_cpu(cpu) {
+		rq = cpu_rq(cpu);
+		req = &per_cpu(rcu_migration_req, cpu);
+		init_completion(&req->done);
+		req->task = NULL;
+		req->dest_cpu = RCU_MIGRATION_NEED_QS;
+		spin_lock_irqsave(&rq->lock, flags);
+		list_add(&req->list, &rq->migration_queue);
+		spin_unlock_irqrestore(&rq->lock, flags);
+		wake_up_process(rq->migration_thread);
+	}
+	for_each_online_cpu(cpu) {
+		rcu_expedited_state = cpu;
+		req = &per_cpu(rcu_migration_req, cpu);
+		rq = cpu_rq(cpu);
+		wait_for_completion(&req->done);
+		spin_lock_irqsave(&rq->lock, flags);
+		if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
+			need_full_sync = 1;
+		req->dest_cpu = RCU_MIGRATION_IDLE;
+		spin_unlock_irqrestore(&rq->lock, flags);
+	}
+	rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+	mutex_unlock(&rcu_sched_expedited_mutex);
+	put_online_cpus();
+	if (need_full_sync)
+		synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index d014efbf947a..0f052fc674d5 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -127,21 +127,11 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 
 	/*
 	 * If the cpu was currently mapped to a different value, we
-	 * first need to unmap the old value
+	 * need to map it to the new value then remove the old value.
+	 * Note, we must add the new value first, otherwise we risk the
+	 * cpu being cleared from pri_active, and this cpu could be
+	 * missed for a push or pull.
 	 */
-	if (likely(oldpri != CPUPRI_INVALID)) {
-		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
-
-		spin_lock_irqsave(&vec->lock, flags);
-
-		vec->count--;
-		if (!vec->count)
-			clear_bit(oldpri, cp->pri_active);
-		cpumask_clear_cpu(cpu, vec->mask);
-
-		spin_unlock_irqrestore(&vec->lock, flags);
-	}
-
 	if (likely(newpri != CPUPRI_INVALID)) {
 		struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
 
@@ -154,6 +144,18 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 
 		spin_unlock_irqrestore(&vec->lock, flags);
 	}
+	if (likely(oldpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
+
+		spin_lock_irqsave(&vec->lock, flags);
+
+		vec->count--;
+		if (!vec->count)
+			clear_bit(oldpri, cp->pri_active);
+		cpumask_clear_cpu(cpu, vec->mask);
+
+		spin_unlock_irqrestore(&vec->lock, flags);
+	}
 
 	*currpri = newpri;
 }
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 70c7e0b79946..5ddbd0891267 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -409,6 +409,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.wait_max);
 	PN(se.wait_sum);
 	P(se.wait_count);
+	PN(se.iowait_sum);
+	P(se.iowait_count);
 	P(sched_info.bkl_count);
 	P(se.nr_migrations);
 	P(se.nr_migrations_cold);
@@ -479,6 +481,8 @@ void proc_sched_set_task(struct task_struct *p)
 	p->se.wait_max				= 0;
 	p->se.wait_sum				= 0;
 	p->se.wait_count			= 0;
+	p->se.iowait_sum			= 0;
+	p->se.iowait_count			= 0;
 	p->se.sleep_max				= 0;
 	p->se.sum_sleep_runtime			= 0;
 	p->se.block_max				= 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 652e8bdef9aa..aa7f84121016 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -24,7 +24,7 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -34,13 +34,13 @@
  * (to see the precise effective timeslice length of your workload,
  *  run vmstat and monitor the context-switches (cs) field)
  */
-unsigned int sysctl_sched_latency = 20000000ULL;
+unsigned int sysctl_sched_latency = 5000000ULL;
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 4000000ULL;
+unsigned int sysctl_sched_min_granularity = 1000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
@@ -48,10 +48,10 @@ unsigned int sysctl_sched_min_granularity = 4000000ULL;
 static unsigned int sched_nr_latency = 5;
 
 /*
- * After fork, child runs first. (default) If set to 0 then
+ * After fork, child runs first. If set to 0 (default) then
  * parent will (try to) run first.
  */
-const_debug unsigned int sysctl_sched_child_runs_first = 1;
+unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
  * sys_sched_yield() compat mode
@@ -63,13 +63,13 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -79,11 +79,6 @@ static const struct sched_class fair_sched_class;
  * CFS operations on generic schedulable entities:
  */
 
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
-	return container_of(se, struct task_struct, se);
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 /* cpu runqueue to which this cfs_rq is attached */
@@ -95,6 +90,14 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 /* An entity is a task if it doesn't "own" a runqueue */
 #define entity_is_task(se)	(!se->my_q)
 
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(!entity_is_task(se));
+#endif
+	return container_of(se, struct task_struct, se);
+}
+
 /* Walk up scheduling entities hierarchy */
 #define for_each_sched_entity(se) \
 		for (; se; se = se->parent)
@@ -186,7 +189,12 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 	}
 }
 
-#else	/* CONFIG_FAIR_GROUP_SCHED */
+#else	/* !CONFIG_FAIR_GROUP_SCHED */
+
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+	return container_of(se, struct task_struct, se);
+}
 
 static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 {
@@ -537,6 +545,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	schedstat_set(se->wait_count, se->wait_count + 1);
 	schedstat_set(se->wait_sum, se->wait_sum +
 			rq_of(cfs_rq)->clock - se->wait_start);
+#ifdef CONFIG_SCHEDSTATS
+	if (entity_is_task(se)) {
+		trace_sched_stat_wait(task_of(se),
+			rq_of(cfs_rq)->clock - se->wait_start);
+	}
+#endif
 	schedstat_set(se->wait_start, 0);
 }
 
@@ -628,8 +642,10 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		se->sleep_start = 0;
 		se->sum_sleep_runtime += delta;
 
-		if (tsk)
+		if (tsk) {
 			account_scheduler_latency(tsk, delta >> 10, 1);
+			trace_sched_stat_sleep(tsk, delta);
+		}
 	}
 	if (se->block_start) {
 		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
@@ -644,6 +660,12 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		se->sum_sleep_runtime += delta;
 
 		if (tsk) {
+			if (tsk->in_iowait) {
+				se->iowait_sum += delta;
+				se->iowait_count++;
+				trace_sched_stat_iowait(tsk, delta);
+			}
+
 			/*
 			 * Blocking time is in units of nanosecs, so shift by
 			 * 20 to get a milliseconds-range estimation of the
@@ -705,11 +727,11 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 			vruntime -= thresh;
 		}
-
-		/* ensure we never gain time by being placed backwards. */
-		vruntime = max_vruntime(se->vruntime, vruntime);
 	}
 
+	/* ensure we never gain time by being placed backwards. */
+	vruntime = max_vruntime(se->vruntime, vruntime);
+
 	se->vruntime = vruntime;
 }
 
@@ -1046,17 +1068,21 @@ static void yield_task_fair(struct rq *rq)
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
  * Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_mask)
+ * hence we need to mask them out (rq->rd->online)
  *
  * Returns the CPU we should wake onto.
  */
 #if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+
+#define cpu_rd_active(cpu, rq) cpumask_test_cpu(cpu, rq->rd->online)
+
 static int wake_idle(int cpu, struct task_struct *p)
 {
 	struct sched_domain *sd;
 	int i;
 	unsigned int chosen_wakeup_cpu;
 	int this_cpu;
+	struct rq *task_rq = task_rq(p);
 
 	/*
 	 * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
@@ -1089,10 +1115,10 @@ static int wake_idle(int cpu, struct task_struct *p)
 	for_each_domain(cpu, sd) {
 		if ((sd->flags & SD_WAKE_IDLE)
 		    || ((sd->flags & SD_WAKE_IDLE_FAR)
-			&& !task_hot(p, task_rq(p)->clock, sd))) {
+			&& !task_hot(p, task_rq->clock, sd))) {
 			for_each_cpu_and(i, sched_domain_span(sd),
 					 &p->cpus_allowed) {
-				if (cpu_active(i) && idle_cpu(i)) {
+				if (cpu_rd_active(i, task_rq) && idle_cpu(i)) {
 					if (i != task_cpu(p)) {
 						schedstat_inc(p,
 						       se.nr_wakeups_idle);
@@ -1235,7 +1261,17 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	tg = task_group(p);
 	weight = p->se.load.weight;
 
-	balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+	/*
+	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
+	 * due to the sync cause above having dropped tl to 0, we'll always have
+	 * an imbalance, but there's really nothing you can do about that, so
+	 * that's good too.
+	 *
+	 * Otherwise check if either cpus are near enough in load to allow this
+	 * task to be woken on this_cpu.
+	 */
+	balanced = !tl ||
+		100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
 		imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
 
 	/*
@@ -1278,8 +1314,6 @@ static int select_task_rq_fair(struct task_struct *p, int sync)
 	this_rq		= cpu_rq(this_cpu);
 	new_cpu		= prev_cpu;
 
-	if (prev_cpu == this_cpu)
-		goto out;
 	/*
 	 * 'this_sd' is the first domain that both
 	 * this_cpu and prev_cpu are present in:
@@ -1721,6 +1755,8 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 	sched_info_queued(p);
 
 	update_curr(cfs_rq);
+	if (curr)
+		se->vruntime = curr->vruntime;
 	place_entity(cfs_rq, se, 1);
 
 	/* 'curr' will be NULL if the child belongs to a different group */
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 4569bfa7df9b..e2dc63a5815d 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,4 +1,4 @@
-SCHED_FEAT(NEW_FAIR_SLEEPERS, 1)
+SCHED_FEAT(NEW_FAIR_SLEEPERS, 0)
 SCHED_FEAT(NORMALIZED_SLEEPER, 0)
 SCHED_FEAT(ADAPTIVE_GRAN, 1)
 SCHED_FEAT(WAKEUP_PREEMPT, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 3918e01994e0..2eb4bd6a526c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -3,15 +3,18 @@
  * policies)
  */
 
+#ifdef CONFIG_RT_GROUP_SCHED
+
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
 static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 {
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(!rt_entity_is_task(rt_se));
+#endif
 	return container_of(rt_se, struct task_struct, rt);
 }
 
-#ifdef CONFIG_RT_GROUP_SCHED
-
-#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
-
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return rt_rq->rq;
@@ -26,6 +29,11 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 
 #define rt_entity_is_task(rt_se) (1)
 
+static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+{
+	return container_of(rt_se, struct task_struct, rt);
+}
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return container_of(rt_rq, struct rq, rt);
@@ -128,6 +136,11 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
 }
 
+static inline int has_pushable_tasks(struct rq *rq)
+{
+	return !plist_head_empty(&rq->rt.pushable_tasks);
+}
+
 #else
 
 static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
@@ -602,6 +615,8 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -874,8 +889,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -886,8 +899,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
@@ -1064,6 +1075,14 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 	if (p)
 		dequeue_pushable_task(rq, p);
 
+#ifdef CONFIG_SMP
+	/*
+	 * We detect this state here so that we can avoid taking the RQ
+	 * lock again later if there is no need to push
+	 */
+	rq->post_schedule = has_pushable_tasks(rq);
+#endif
+
 	return p;
 }
 
@@ -1162,13 +1181,6 @@ static int find_lowest_rq(struct task_struct *task)
 		return -1; /* No targets found */
 
 	/*
-	 * Only consider CPUs that are usable for migration.
-	 * I guess we might want to change cpupri_find() to ignore those
-	 * in the first place.
-	 */
-	cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
-
-	/*
 	 * At this point we have built a mask of cpus representing the
 	 * lowest priority tasks in the system.  Now we want to elect
 	 * the best one based on our affinity and topology.
@@ -1262,11 +1274,6 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 	return lowest_rq;
 }
 
-static inline int has_pushable_tasks(struct rq *rq)
-{
-	return !plist_head_empty(&rq->rt.pushable_tasks);
-}
-
 static struct task_struct *pick_next_pushable_task(struct rq *rq)
 {
 	struct task_struct *p;
@@ -1466,23 +1473,9 @@ static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
 		pull_rt_task(rq);
 }
 
-/*
- * assumes rq->lock is held
- */
-static int needs_post_schedule_rt(struct rq *rq)
-{
-	return has_pushable_tasks(rq);
-}
-
 static void post_schedule_rt(struct rq *rq)
 {
-	/*
-	 * This is only called if needs_post_schedule_rt() indicates that
-	 * we need to push tasks away
-	 */
-	spin_lock_irq(&rq->lock);
 	push_rt_tasks(rq);
-	spin_unlock_irq(&rq->lock);
 }
 
 /*
@@ -1758,7 +1751,6 @@ static const struct sched_class rt_sched_class = {
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
 	.pre_schedule		= pre_schedule_rt,
-	.needs_post_schedule	= needs_post_schedule_rt,
 	.post_schedule		= post_schedule_rt,
 	.task_wake_up		= task_wake_up_rt,
 	.switched_from		= switched_from_rt,
diff --git a/kernel/softirq.c b/kernel/softirq.c
index eb5e131a0485..7db25067cd2d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -227,7 +227,7 @@ restart:
 				preempt_count() = prev_count;
 			}
 
-			rcu_bh_qsctr_inc(cpu);
+			rcu_bh_qs(cpu);
 		}
 		h++;
 		pending >>= 1;
@@ -721,7 +721,7 @@ static int ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
-			rcu_qsctr_inc((long)__bind_cpu);
+			rcu_sched_qs((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 7932653c4ebd..5ddab730cb2f 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -21,44 +21,29 @@
 #include <linux/debug_locks.h>
 #include <linux/module.h>
 
+#ifndef _spin_trylock
 int __lockfunc _spin_trylock(spinlock_t *lock)
 {
-	preempt_disable();
-	if (_raw_spin_trylock(lock)) {
-		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-	
-	preempt_enable();
-	return 0;
+	return __spin_trylock(lock);
 }
 EXPORT_SYMBOL(_spin_trylock);
+#endif
 
+#ifndef _read_trylock
 int __lockfunc _read_trylock(rwlock_t *lock)
 {
-	preempt_disable();
-	if (_raw_read_trylock(lock)) {
-		rwlock_acquire_read(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-
-	preempt_enable();
-	return 0;
+	return __read_trylock(lock);
 }
 EXPORT_SYMBOL(_read_trylock);
+#endif
 
+#ifndef _write_trylock
 int __lockfunc _write_trylock(rwlock_t *lock)
 {
-	preempt_disable();
-	if (_raw_write_trylock(lock)) {
-		rwlock_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-
-	preempt_enable();
-	return 0;
+	return __write_trylock(lock);
 }
 EXPORT_SYMBOL(_write_trylock);
+#endif
 
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
@@ -67,132 +52,101 @@ EXPORT_SYMBOL(_write_trylock);
  */
 #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
 
+#ifndef _read_lock
 void __lockfunc _read_lock(rwlock_t *lock)
 {
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	__read_lock(lock);
 }
 EXPORT_SYMBOL(_read_lock);
+#endif
 
+#ifndef _spin_lock_irqsave
 unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	/*
-	 * On lockdep we dont want the hand-coded irq-enable of
-	 * _raw_spin_lock_flags() code, because lockdep assumes
-	 * that interrupts are not re-enabled during lock-acquire:
-	 */
-#ifdef CONFIG_LOCKDEP
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
-#else
-	_raw_spin_lock_flags(lock, &flags);
-#endif
-	return flags;
+	return __spin_lock_irqsave(lock);
 }
 EXPORT_SYMBOL(_spin_lock_irqsave);
+#endif
 
+#ifndef _spin_lock_irq
 void __lockfunc _spin_lock_irq(spinlock_t *lock)
 {
-	local_irq_disable();
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+	__spin_lock_irq(lock);
 }
 EXPORT_SYMBOL(_spin_lock_irq);
+#endif
 
+#ifndef _spin_lock_bh
 void __lockfunc _spin_lock_bh(spinlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+	__spin_lock_bh(lock);
 }
 EXPORT_SYMBOL(_spin_lock_bh);
+#endif
 
+#ifndef _read_lock_irqsave
 unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock,
-			     _raw_read_lock_flags, &flags);
-	return flags;
+	return __read_lock_irqsave(lock);
 }
 EXPORT_SYMBOL(_read_lock_irqsave);
+#endif
 
+#ifndef _read_lock_irq
 void __lockfunc _read_lock_irq(rwlock_t *lock)
 {
-	local_irq_disable();
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	__read_lock_irq(lock);
 }
 EXPORT_SYMBOL(_read_lock_irq);
+#endif
 
+#ifndef _read_lock_bh
 void __lockfunc _read_lock_bh(rwlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	__read_lock_bh(lock);
 }
 EXPORT_SYMBOL(_read_lock_bh);
+#endif
 
+#ifndef _write_lock_irqsave
 unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock,
-			     _raw_write_lock_flags, &flags);
-	return flags;
+	return __write_lock_irqsave(lock);
 }
 EXPORT_SYMBOL(_write_lock_irqsave);
+#endif
 
+#ifndef _write_lock_irq
 void __lockfunc _write_lock_irq(rwlock_t *lock)
 {
-	local_irq_disable();
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	__write_lock_irq(lock);
 }
 EXPORT_SYMBOL(_write_lock_irq);
+#endif
 
+#ifndef _write_lock_bh
 void __lockfunc _write_lock_bh(rwlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	__write_lock_bh(lock);
 }
 EXPORT_SYMBOL(_write_lock_bh);
+#endif
 
+#ifndef _spin_lock
 void __lockfunc _spin_lock(spinlock_t *lock)
 {
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+	__spin_lock(lock);
 }
-
 EXPORT_SYMBOL(_spin_lock);
+#endif
 
+#ifndef _write_lock
 void __lockfunc _write_lock(rwlock_t *lock)
 {
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	__write_lock(lock);
 }
-
 EXPORT_SYMBOL(_write_lock);
+#endif
 
 #else /* CONFIG_PREEMPT: */
 
@@ -318,125 +272,109 @@ EXPORT_SYMBOL(_spin_lock_nest_lock);
 
 #endif
 
+#ifndef _spin_unlock
 void __lockfunc _spin_unlock(spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	preempt_enable();
+	__spin_unlock(lock);
 }
 EXPORT_SYMBOL(_spin_unlock);
+#endif
 
+#ifndef _write_unlock
 void __lockfunc _write_unlock(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	preempt_enable();
+	__write_unlock(lock);
 }
 EXPORT_SYMBOL(_write_unlock);
+#endif
 
+#ifndef _read_unlock
 void __lockfunc _read_unlock(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	preempt_enable();
+	__read_unlock(lock);
 }
 EXPORT_SYMBOL(_read_unlock);
+#endif
 
+#ifndef _spin_unlock_irqrestore
 void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	local_irq_restore(flags);
-	preempt_enable();
+	__spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(_spin_unlock_irqrestore);
+#endif
 
+#ifndef _spin_unlock_irq
 void __lockfunc _spin_unlock_irq(spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	local_irq_enable();
-	preempt_enable();
+	__spin_unlock_irq(lock);
 }
 EXPORT_SYMBOL(_spin_unlock_irq);
+#endif
 
+#ifndef _spin_unlock_bh
 void __lockfunc _spin_unlock_bh(spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__spin_unlock_bh(lock);
 }
 EXPORT_SYMBOL(_spin_unlock_bh);
+#endif
 
+#ifndef _read_unlock_irqrestore
 void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	local_irq_restore(flags);
-	preempt_enable();
+	__read_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(_read_unlock_irqrestore);
+#endif
 
+#ifndef _read_unlock_irq
 void __lockfunc _read_unlock_irq(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	local_irq_enable();
-	preempt_enable();
+	__read_unlock_irq(lock);
 }
 EXPORT_SYMBOL(_read_unlock_irq);
+#endif
 
+#ifndef _read_unlock_bh
 void __lockfunc _read_unlock_bh(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__read_unlock_bh(lock);
 }
 EXPORT_SYMBOL(_read_unlock_bh);
+#endif
 
+#ifndef _write_unlock_irqrestore
 void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	local_irq_restore(flags);
-	preempt_enable();
+	__write_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(_write_unlock_irqrestore);
+#endif
 
+#ifndef _write_unlock_irq
 void __lockfunc _write_unlock_irq(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	local_irq_enable();
-	preempt_enable();
+	__write_unlock_irq(lock);
 }
 EXPORT_SYMBOL(_write_unlock_irq);
+#endif
 
+#ifndef _write_unlock_bh
 void __lockfunc _write_unlock_bh(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__write_unlock_bh(lock);
 }
 EXPORT_SYMBOL(_write_unlock_bh);
+#endif
 
+#ifndef _spin_trylock_bh
 int __lockfunc _spin_trylock_bh(spinlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	if (_raw_spin_trylock(lock)) {
-		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
-	return 0;
+	return __spin_trylock_bh(lock);
 }
 EXPORT_SYMBOL(_spin_trylock_bh);
+#endif
 
 notrace int in_lock_functions(unsigned long addr)
 {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be76017fd0..6bb59f707402 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -49,7 +49,6 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
-#include <linux/security.h>
 #include <linux/slow-work.h>
 #include <linux/perf_counter.h>
 
@@ -92,6 +91,7 @@ extern int sysctl_nr_trim_pages;
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
+extern int blk_iopoll_enabled;
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_DETECT_SOFTLOCKUP
@@ -246,6 +246,14 @@ static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 #endif
 
 static struct ctl_table kern_table[] = {
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_child_runs_first",
+		.data		= &sysctl_sched_child_runs_first,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #ifdef CONFIG_SCHED_DEBUG
 	{
 		.ctl_name	= CTL_UNNUMBERED,
@@ -300,14 +308,6 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "sched_child_runs_first",
-		.data		= &sysctl_sched_child_runs_first,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_features",
 		.data		= &sysctl_sched_features,
 		.maxlen		= sizeof(unsigned int),
@@ -332,6 +332,14 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_time_avg",
+		.data		= &sysctl_sched_time_avg,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),
@@ -990,7 +998,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
-
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "blk_iopoll",
+		.data		= &blk_iopoll_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 888adbcca30c..ea8384d3caa7 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -108,7 +108,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
 /*
  * Send taskstats data in @skb to listener with nl_pid @pid
  */
-static int send_reply(struct sk_buff *skb, pid_t pid)
+static int send_reply(struct sk_buff *skb, struct genl_info *info)
 {
 	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
 	void *reply = genlmsg_data(genlhdr);
@@ -120,7 +120,7 @@ static int send_reply(struct sk_buff *skb, pid_t pid)
 		return rc;
 	}
 
-	return genlmsg_unicast(skb, pid);
+	return genlmsg_reply(skb, info);
 }
 
 /*
@@ -150,7 +150,7 @@ static void send_cpu_listeners(struct sk_buff *skb,
 			if (!skb_next)
 				break;
 		}
-		rc = genlmsg_unicast(skb_cur, s->pid);
+		rc = genlmsg_unicast(&init_net, skb_cur, s->pid);
 		if (rc == -ECONNREFUSED) {
 			s->valid = 0;
 			delcount++;
@@ -418,7 +418,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 		goto err;
 	}
 
-	rc = send_reply(rep_skb, info->snd_pid);
+	rc = send_reply(rep_skb, info);
 
 err:
 	fput_light(file, fput_needed);
@@ -487,7 +487,7 @@ free_return_rc:
 	} else
 		goto err;
 
-	return send_reply(rep_skb, info->snd_pid);
+	return send_reply(rep_skb, info);
 err:
 	nlmsg_free(rep_skb);
 	return rc;
diff --git a/kernel/timer.c b/kernel/timer.c
index a7f07d5a6241..a3d25f415019 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1156,8 +1156,7 @@ void update_process_times(int user_tick)
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
-	if (rcu_pending(cpu))
-		rcu_check_callbacks(cpu, user_tick);
+	rcu_check_callbacks(cpu, user_tick);
 	printk_tick();
 	scheduler_tick();
 	run_posix_cpu_timers(p);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0668795d8818..addfe2df93b1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -317,8 +317,6 @@ static int worker_thread(void *__cwq)
 	if (cwq->wq->freezeable)
 		set_freezable();
 
-	set_user_nice(current, -5);
-
 	for (;;) {
 		prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
 		if (!freezing(current) &&
@@ -600,7 +598,12 @@ static struct workqueue_struct *keventd_wq __read_mostly;
  * schedule_work - put work task in global workqueue
  * @work: job to be done
  *
- * This puts a job in the kernel-global workqueue.
+ * Returns zero if @work was already on the kernel-global workqueue and
+ * non-zero otherwise.
+ *
+ * This puts a job in the kernel-global workqueue if it was not already
+ * queued and leaves it in the same position on the kernel-global
+ * workqueue otherwise.
  */
 int schedule_work(struct work_struct *work)
 {