Merge commit '8700c95adb03' into timers/nohz

The full dynticks tree needs the latest RCU and sched
upstream updates in order to fix some dependencies.

Merge a common upstream merge point that has these
updates.

Conflicts:
	include/linux/perf_event.h
	kernel/rcutree.h
	kernel/rcutree_plugin.h

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

84 files changed, 8743 insertions, 4072 deletions

diff --git a/kernel/.gitignore b/kernel/.gitignore
index ab4f1090f437..b3097bde4e9c 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -4,3 +4,4 @@
 config_data.h
 config_data.gz
 timeconst.h
+hz.bc
diff --git a/kernel/Makefile b/kernel/Makefile
index bbde5f1a4486..d1574d47cf27 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -24,6 +24,7 @@ endif
 
 obj-y += sched/
 obj-y += power/
+obj-y += cpu/
 
 obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
 obj-$(CONFIG_FREEZER) += freezer.o
diff --git a/kernel/async.c b/kernel/async.c
index 8ddee2c3e5b0..61f023ce0228 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -73,7 +73,7 @@ struct async_entry {
 	struct list_head	global_list;
 	struct work_struct	work;
 	async_cookie_t		cookie;
-	async_func_ptr		*func;
+	async_func_t		func;
 	void			*data;
 	struct async_domain	*domain;
 };
@@ -84,24 +84,20 @@ static atomic_t entry_count;
 
 static async_cookie_t lowest_in_progress(struct async_domain *domain)
 {
-	struct async_entry *first = NULL;
+	struct list_head *pending;
 	async_cookie_t ret = ASYNC_COOKIE_MAX;
 	unsigned long flags;
 
 	spin_lock_irqsave(&async_lock, flags);
 
-	if (domain) {
-		if (!list_empty(&domain->pending))
-			first = list_first_entry(&domain->pending,
-					struct async_entry, domain_list);
-	} else {
-		if (!list_empty(&async_global_pending))
-			first = list_first_entry(&async_global_pending,
-					struct async_entry, global_list);
-	}
+	if (domain)
+		pending = &domain->pending;
+	else
+		pending = &async_global_pending;
 
-	if (first)
-		ret = first->cookie;
+	if (!list_empty(pending))
+		ret = list_first_entry(pending, struct async_entry,
+				       domain_list)->cookie;
 
 	spin_unlock_irqrestore(&async_lock, flags);
 	return ret;
@@ -149,7 +145,7 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
-static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct async_domain *domain)
+static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain)
 {
 	struct async_entry *entry;
 	unsigned long flags;
@@ -169,13 +165,13 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a
 		spin_unlock_irqrestore(&async_lock, flags);
 
 		/* low on memory.. run synchronously */
-		ptr(data, newcookie);
+		func(data, newcookie);
 		return newcookie;
 	}
 	INIT_LIST_HEAD(&entry->domain_list);
 	INIT_LIST_HEAD(&entry->global_list);
 	INIT_WORK(&entry->work, async_run_entry_fn);
-	entry->func = ptr;
+	entry->func = func;
 	entry->data = data;
 	entry->domain = domain;
 
@@ -202,21 +198,21 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a
 
 /**
  * async_schedule - schedule a function for asynchronous execution
- * @ptr: function to execute asynchronously
+ * @func: function to execute asynchronously
  * @data: data pointer to pass to the function
  *
  * Returns an async_cookie_t that may be used for checkpointing later.
  * Note: This function may be called from atomic or non-atomic contexts.
  */
-async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
+async_cookie_t async_schedule(async_func_t func, void *data)
 {
-	return __async_schedule(ptr, data, &async_dfl_domain);
+	return __async_schedule(func, data, &async_dfl_domain);
 }
 EXPORT_SYMBOL_GPL(async_schedule);
 
 /**
  * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
- * @ptr: function to execute asynchronously
+ * @func: function to execute asynchronously
  * @data: data pointer to pass to the function
  * @domain: the domain
  *
@@ -226,10 +222,10 @@ EXPORT_SYMBOL_GPL(async_schedule);
  * synchronization domain is specified via @domain.  Note: This function
  * may be called from atomic or non-atomic contexts.
  */
-async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
+async_cookie_t async_schedule_domain(async_func_t func, void *data,
 				     struct async_domain *domain)
 {
-	return __async_schedule(ptr, data, domain);
+	return __async_schedule(func, data, domain);
 }
 EXPORT_SYMBOL_GPL(async_schedule_domain);
 
diff --git a/kernel/audit.c b/kernel/audit.c
index d596e5355f15..9816a1b96cfc 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -660,14 +660,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	/* As soon as there's any sign of userspace auditd,
 	 * start kauditd to talk to it */
-	if (!kauditd_task)
+	if (!kauditd_task) {
 		kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd");
-	if (IS_ERR(kauditd_task)) {
-		err = PTR_ERR(kauditd_task);
-		kauditd_task = NULL;
-		return err;
+		if (IS_ERR(kauditd_task)) {
+			err = PTR_ERR(kauditd_task);
+			kauditd_task = NULL;
+			return err;
+		}
 	}
-
 	loginuid = audit_get_loginuid(current);
 	sessionid = audit_get_sessionid(current);
 	security_task_getsecid(current, &sid);
diff --git a/kernel/audit.h b/kernel/audit.h
index d51cba868e1b..11468d99dad0 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -59,10 +59,7 @@ struct audit_entry {
 	struct audit_krule	rule;
 };
 
-#ifdef CONFIG_AUDIT
-extern int audit_enabled;
 extern int audit_ever_enabled;
-#endif
 
 extern int audit_pid;
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 642a89c4f3d6..a291aa23fb3f 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -617,9 +617,9 @@ void audit_trim_trees(void)
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
-		put_tree(tree);
 		drop_collected_mounts(root_mnt);
 skip_it:
+		put_tree(tree);
 		mutex_lock(&audit_filter_mutex);
 	}
 	list_del(&cursor);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index f9fc54bbe06f..267436826c3b 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -594,6 +594,10 @@ exit_nofree:
 	return entry;
 
 exit_free:
+	if (entry->rule.watch)
+		audit_put_watch(entry->rule.watch); /* matches initial get */
+	if (entry->rule.tree)
+		audit_put_tree(entry->rule.tree); /* that's the temporary one */
 	audit_free_rule(entry);
 	return ERR_PTR(err);
 }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index a371f857a0a9..c68229411a7c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1034,21 +1034,15 @@ static inline void audit_free_aux(struct audit_context *context)
 	}
 }
 
-static inline void audit_zero_context(struct audit_context *context,
-				      enum audit_state state)
-{
-	memset(context, 0, sizeof(*context));
-	context->state      = state;
-	context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
-}
-
 static inline struct audit_context *audit_alloc_context(enum audit_state state)
 {
 	struct audit_context *context;
 
-	if (!(context = kmalloc(sizeof(*context), GFP_KERNEL)))
+	context = kzalloc(sizeof(*context), GFP_KERNEL);
+	if (!context)
 		return NULL;
-	audit_zero_context(context, state);
+	context->state = state;
+	context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 	INIT_LIST_HEAD(&context->killed_trees);
 	INIT_LIST_HEAD(&context->names_list);
 	return context;
diff --git a/kernel/capability.c b/kernel/capability.c
index 493d97259484..f6c2ce5701e1 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -393,6 +393,30 @@ bool ns_capable(struct user_namespace *ns, int cap)
 EXPORT_SYMBOL(ns_capable);
 
 /**
+ * file_ns_capable - Determine if the file's opener had a capability in effect
+ * @file:  The file we want to check
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if task that opened the file had a capability in effect
+ * when the file was opened.
+ *
+ * This does not set PF_SUPERPRIV because the caller may not
+ * actually be privileged.
+ */
+bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap)
+{
+	if (WARN_ON_ONCE(!cap_valid(cap)))
+		return false;
+
+	if (security_capable(file->f_cred, ns, cap) == 0)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(file_ns_capable);
+
+/**
  * capable - Determine if the current task has a superior capability in effect
  * @cap: The capability to be tested for
  *
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a32f9432666c..d3abce2d6455 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -30,7 +30,6 @@
 #include <linux/cred.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
-#include <linux/fs.h>
 #include <linux/init_task.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
@@ -59,7 +58,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/eventfd.h>
 #include <linux/poll.h>
-#include <linux/flex_array.h> /* used in cgroup_attach_proc */
+#include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
 
 #include <linux/atomic.h>
@@ -83,7 +82,13 @@
  * B happens only through cgroup_show_options() and using cgroup_root_mutex
  * breaks it.
  */
+#ifdef CONFIG_PROVE_RCU
+DEFINE_MUTEX(cgroup_mutex);
+EXPORT_SYMBOL_GPL(cgroup_mutex);	/* only for task_subsys_state_check() */
+#else
 static DEFINE_MUTEX(cgroup_mutex);
+#endif
+
 static DEFINE_MUTEX(cgroup_root_mutex);
 
 /*
@@ -98,56 +103,6 @@ static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
 #include <linux/cgroup_subsys.h>
 };
 
-#define MAX_CGROUP_ROOT_NAMELEN 64
-
-/*
- * A cgroupfs_root represents the root of a cgroup hierarchy,
- * and may be associated with a superblock to form an active
- * hierarchy
- */
-struct cgroupfs_root {
-	struct super_block *sb;
-
-	/*
-	 * The bitmask of subsystems intended to be attached to this
-	 * hierarchy
-	 */
-	unsigned long subsys_mask;
-
-	/* Unique id for this hierarchy. */
-	int hierarchy_id;
-
-	/* The bitmask of subsystems currently attached to this hierarchy */
-	unsigned long actual_subsys_mask;
-
-	/* A list running through the attached subsystems */
-	struct list_head subsys_list;
-
-	/* The root cgroup for this hierarchy */
-	struct cgroup top_cgroup;
-
-	/* Tracks how many cgroups are currently defined in hierarchy.*/
-	int number_of_cgroups;
-
-	/* A list running through the active hierarchies */
-	struct list_head root_list;
-
-	/* All cgroups on this root, cgroup_mutex protected */
-	struct list_head allcg_list;
-
-	/* Hierarchy-specific flags */
-	unsigned long flags;
-
-	/* IDs for cgroups in this hierarchy */
-	struct ida cgroup_ida;
-
-	/* The path to use for release notifications. */
-	char release_agent_path[PATH_MAX];
-
-	/* The name for this hierarchy - may be empty */
-	char name[MAX_CGROUP_ROOT_NAMELEN];
-};
-
 /*
  * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
  * subsystems that are otherwise unattached - it never has more than a
@@ -162,6 +117,9 @@ struct cfent {
 	struct list_head		node;
 	struct dentry			*dentry;
 	struct cftype			*type;
+
+	/* file xattrs */
+	struct simple_xattrs		xattrs;
 };
 
 /*
@@ -238,6 +196,8 @@ static DEFINE_SPINLOCK(hierarchy_id_lock);
 /* dummytop is a shorthand for the dummy hierarchy's top cgroup */
 #define dummytop (&rootnode.top_cgroup)
 
+static struct cgroup_name root_cgroup_name = { .name = "/" };
+
 /* This flag indicates whether tasks in the fork and exit paths should
  * check for fork/exit handlers to call. This avoids us having to do
  * extra work in the fork/exit path if none of the subsystems need to
@@ -249,20 +209,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 			      struct cftype cfts[], bool is_add);
 
-#ifdef CONFIG_PROVE_LOCKING
-int cgroup_lock_is_held(void)
-{
-	return lockdep_is_held(&cgroup_mutex);
-}
-#else /* #ifdef CONFIG_PROVE_LOCKING */
-int cgroup_lock_is_held(void)
-{
-	return mutex_is_locked(&cgroup_mutex);
-}
-#endif /* #else #ifdef CONFIG_PROVE_LOCKING */
-
-EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
-
 static int css_unbias_refcnt(int refcnt)
 {
 	return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
@@ -282,11 +228,25 @@ inline int cgroup_is_removed(const struct cgroup *cgrp)
 	return test_bit(CGRP_REMOVED, &cgrp->flags);
 }
 
-/* bits in struct cgroupfs_root flags field */
-enum {
-	ROOT_NOPREFIX,	/* mounted subsystems have no named prefix */
-	ROOT_XATTR,	/* supports extended attributes */
-};
+/**
+ * cgroup_is_descendant - test ancestry
+ * @cgrp: the cgroup to be tested
+ * @ancestor: possible ancestor of @cgrp
+ *
+ * Test whether @cgrp is a descendant of @ancestor.  It also returns %true
+ * if @cgrp == @ancestor.  This function is safe to call as long as @cgrp
+ * and @ancestor are accessible.
+ */
+bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
+{
+	while (cgrp) {
+		if (cgrp == ancestor)
+			return true;
+		cgrp = cgrp->parent;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(cgroup_is_descendant);
 
 static int cgroup_is_releasable(const struct cgroup *cgrp)
 {
@@ -327,6 +287,23 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
 	return __d_cfe(dentry)->type;
 }
 
+/**
+ * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
+ * @cgrp: the cgroup to be checked for liveness
+ *
+ * On success, returns true; the mutex should be later unlocked.  On
+ * failure returns false with no lock held.
+ */
+static bool cgroup_lock_live_group(struct cgroup *cgrp)
+{
+	mutex_lock(&cgroup_mutex);
+	if (cgroup_is_removed(cgrp)) {
+		mutex_unlock(&cgroup_mutex);
+		return false;
+	}
+	return true;
+}
+
 /* the list of cgroups eligible for automatic release. Protected by
  * release_list_lock */
 static LIST_HEAD(release_list);
@@ -800,27 +777,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
-/**
- * cgroup_lock - lock out any changes to cgroup structures
- *
- */
-void cgroup_lock(void)
-{
-	mutex_lock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_lock);
-
-/**
- * cgroup_unlock - release lock on cgroup changes
- *
- * Undo the lock taken in a previous cgroup_lock() call.
- */
-void cgroup_unlock(void)
-{
-	mutex_unlock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_unlock);
-
 /*
  * A couple of forward declarations required, due to cyclic reference loop:
  * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
@@ -859,6 +815,17 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 	return inode;
 }
 
+static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry)
+{
+	struct cgroup_name *name;
+
+	name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL);
+	if (!name)
+		return NULL;
+	strcpy(name->name, dentry->d_name.name);
+	return name;
+}
+
 static void cgroup_free_fn(struct work_struct *work)
 {
 	struct cgroup *cgrp = container_of(work, struct cgroup, free_work);
@@ -875,8 +842,18 @@ static void cgroup_free_fn(struct work_struct *work)
 	mutex_unlock(&cgroup_mutex);
 
 	/*
+	 * We get a ref to the parent's dentry, and put the ref when
+	 * this cgroup is being freed, so it's guaranteed that the
+	 * parent won't be destroyed before its children.
+	 */
+	dput(cgrp->parent->dentry);
+
+	ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
+
+	/*
 	 * Drop the active superblock reference that we took when we
-	 * created the cgroup
+	 * created the cgroup. This will free cgrp->root, if we are
+	 * holding the last reference to @sb.
 	 */
 	deactivate_super(cgrp->root->sb);
 
@@ -888,7 +865,7 @@ static void cgroup_free_fn(struct work_struct *work)
 
 	simple_xattrs_free(&cgrp->xattrs);
 
-	ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
+	kfree(rcu_dereference_raw(cgrp->name));
 	kfree(cgrp);
 }
 
@@ -910,13 +887,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
 		struct cgroup *cgrp = dentry->d_parent->d_fsdata;
-		struct cftype *cft = cfe->type;
 
 		WARN_ONCE(!list_empty(&cfe->node) &&
 			  cgrp != &cgrp->root->top_cgroup,
 			  "cfe still linked for %s\n", cfe->type->name);
+		simple_xattrs_free(&cfe->xattrs);
 		kfree(cfe);
-		simple_xattrs_free(&cft->xattrs);
 	}
 	iput(inode);
 }
@@ -1108,9 +1084,11 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 	mutex_lock(&cgroup_root_mutex);
 	for_each_subsys(root, ss)
 		seq_printf(seq, ",%s", ss->name);
-	if (test_bit(ROOT_NOPREFIX, &root->flags))
+	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
+		seq_puts(seq, ",sane_behavior");
+	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
-	if (test_bit(ROOT_XATTR, &root->flags))
+	if (root->flags & CGRP_ROOT_XATTR)
 		seq_puts(seq, ",xattr");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
@@ -1172,8 +1150,12 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			all_ss = true;
 			continue;
 		}
+		if (!strcmp(token, "__DEVEL__sane_behavior")) {
+			opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
+			continue;
+		}
 		if (!strcmp(token, "noprefix")) {
-			set_bit(ROOT_NOPREFIX, &opts->flags);
+			opts->flags |= CGRP_ROOT_NOPREFIX;
 			continue;
 		}
 		if (!strcmp(token, "clone_children")) {
@@ -1181,7 +1163,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			continue;
 		}
 		if (!strcmp(token, "xattr")) {
-			set_bit(ROOT_XATTR, &opts->flags);
+			opts->flags |= CGRP_ROOT_XATTR;
 			continue;
 		}
 		if (!strncmp(token, "release_agent=", 14)) {
@@ -1259,13 +1241,26 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 
 	/* Consistency checks */
 
+	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
+		pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
+
+		if (opts->flags & CGRP_ROOT_NOPREFIX) {
+			pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
+			return -EINVAL;
+		}
+
+		if (opts->cpuset_clone_children) {
+			pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
+			return -EINVAL;
+		}
+	}
+
 	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
 	 * the cpuset subsystem.
 	 */
-	if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
-	    (opts->subsys_mask & mask))
+	if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
 		return -EINVAL;
 
 
@@ -1336,6 +1331,11 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	struct cgroup_sb_opts opts;
 	unsigned long added_mask, removed_mask;
 
+	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) {
+		pr_err("cgroup: sane_behavior: remount is not allowed\n");
+		return -EINVAL;
+	}
+
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 	mutex_lock(&cgroup_root_mutex);
@@ -1421,7 +1421,7 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	INIT_LIST_HEAD(&root->allcg_list);
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
-	cgrp->top_cgroup = cgrp;
+	cgrp->name = &root_cgroup_name;
 	init_cgroup_housekeeping(cgrp);
 	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 }
@@ -1685,6 +1685,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		 * any) is not needed
 		 */
 		cgroup_drop_root(opts.new_root);
+
+		if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) &&
+		    root->flags != opts.flags) {
+			pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
+			ret = -EINVAL;
+			goto drop_new_super;
+		}
+
 		/* no subsys rebinding, so refcounts don't change */
 		drop_parsed_module_refcounts(opts.subsys_mask);
 	}
@@ -1769,49 +1777,48 @@ static struct kobject *cgroup_kobj;
  * @buf: the buffer to write the path into
  * @buflen: the length of the buffer
  *
- * Called with cgroup_mutex held or else with an RCU-protected cgroup
- * reference.  Writes path of cgroup into buf.  Returns 0 on success,
- * -errno on error.
+ * Writes path of cgroup into buf.  Returns 0 on success, -errno on error.
+ *
+ * We can't generate cgroup path using dentry->d_name, as accessing
+ * dentry->name must be protected by irq-unsafe dentry->d_lock or parent
+ * inode's i_mutex, while on the other hand cgroup_path() can be called
+ * with some irq-safe spinlocks held.
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
-	struct dentry *dentry = cgrp->dentry;
+	int ret = -ENAMETOOLONG;
 	char *start;
 
-	rcu_lockdep_assert(rcu_read_lock_held() || cgroup_lock_is_held(),
-			   "cgroup_path() called without proper locking");
-
-	if (cgrp == dummytop) {
-		/*
-		 * Inactive subsystems have no dentry for their root
-		 * cgroup
-		 */
-		strcpy(buf, "/");
+	if (!cgrp->parent) {
+		if (strlcpy(buf, "/", buflen) >= buflen)
+			return -ENAMETOOLONG;
 		return 0;
 	}
 
 	start = buf + buflen - 1;
-
 	*start = '\0';
-	for (;;) {
-		int len = dentry->d_name.len;
 
+	rcu_read_lock();
+	do {
+		const char *name = cgroup_name(cgrp);
+		int len;
+
+		len = strlen(name);
 		if ((start -= len) < buf)
-			return -ENAMETOOLONG;
-		memcpy(start, dentry->d_name.name, len);
-		cgrp = cgrp->parent;
-		if (!cgrp)
-			break;
+			goto out;
+		memcpy(start, name, len);
 
-		dentry = cgrp->dentry;
-		if (!cgrp->parent)
-			continue;
 		if (--start < buf)
-			return -ENAMETOOLONG;
+			goto out;
 		*start = '/';
-	}
+
+		cgrp = cgrp->parent;
+	} while (cgrp->parent);
+	ret = 0;
 	memmove(buf, start, buf + buflen - start);
-	return 0;
+out:
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cgroup_path);
 
@@ -1900,7 +1907,7 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size);
  *
  * Must be called with cgroup_mutex and threadgroup locked.
  */
-static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+static void cgroup_task_migrate(struct cgroup *oldcgrp,
 				struct task_struct *tsk, struct css_set *newcg)
 {
 	struct css_set *oldcg;
@@ -1933,121 +1940,22 @@ static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
 }
 
 /**
- * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
- * @cgrp: the cgroup the task is attaching to
- * @tsk: the task to be attached
- *
- * Call with cgroup_mutex and threadgroup locked. May take task_lock of
- * @tsk during call.
- */
-int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
-{
-	int retval = 0;
-	struct cgroup_subsys *ss, *failed_ss = NULL;
-	struct cgroup *oldcgrp;
-	struct cgroupfs_root *root = cgrp->root;
-	struct cgroup_taskset tset = { };
-	struct css_set *newcg;
-
-	/* @tsk either already exited or can't exit until the end */
-	if (tsk->flags & PF_EXITING)
-		return -ESRCH;
-
-	/* Nothing to do if the task is already in that cgroup */
-	oldcgrp = task_cgroup_from_root(tsk, root);
-	if (cgrp == oldcgrp)
-		return 0;
-
-	tset.single.task = tsk;
-	tset.single.cgrp = oldcgrp;
-
-	for_each_subsys(root, ss) {
-		if (ss->can_attach) {
-			retval = ss->can_attach(cgrp, &tset);
-			if (retval) {
-				/*
-				 * Remember on which subsystem the can_attach()
-				 * failed, so that we only call cancel_attach()
-				 * against the subsystems whose can_attach()
-				 * succeeded. (See below)
-				 */
-				failed_ss = ss;
-				goto out;
-			}
-		}
-	}
-
-	newcg = find_css_set(tsk->cgroups, cgrp);
-	if (!newcg) {
-		retval = -ENOMEM;
-		goto out;
-	}
-
-	cgroup_task_migrate(cgrp, oldcgrp, tsk, newcg);
-
-	for_each_subsys(root, ss) {
-		if (ss->attach)
-			ss->attach(cgrp, &tset);
-	}
-
-out:
-	if (retval) {
-		for_each_subsys(root, ss) {
-			if (ss == failed_ss)
-				/*
-				 * This subsystem was the one that failed the
-				 * can_attach() check earlier, so we don't need
-				 * to call cancel_attach() against it or any
-				 * remaining subsystems.
-				 */
-				break;
-			if (ss->cancel_attach)
-				ss->cancel_attach(cgrp, &tset);
-		}
-	}
-	return retval;
-}
-
-/**
- * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
- * @from: attach to all cgroups of a given task
- * @tsk: the task to be attached
- */
-int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
-{
-	struct cgroupfs_root *root;
-	int retval = 0;
-
-	cgroup_lock();
-	for_each_active_root(root) {
-		struct cgroup *from_cg = task_cgroup_from_root(from, root);
-
-		retval = cgroup_attach_task(from_cg, tsk);
-		if (retval)
-			break;
-	}
-	cgroup_unlock();
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
-
-/**
- * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
  * @cgrp: the cgroup to attach to
- * @leader: the threadgroup leader task_struct of the group to be attached
+ * @tsk: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
  *
  * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of each thread in leader's threadgroup individually in turn.
+ * task_lock of @tsk or each thread in the threadgroup individually in turn.
  */
-static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
+static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
+			      bool threadgroup)
 {
 	int retval, i, group_size;
 	struct cgroup_subsys *ss, *failed_ss = NULL;
-	/* guaranteed to be initialized later, but the compiler needs this */
 	struct cgroupfs_root *root = cgrp->root;
 	/* threadgroup list cursor and array */
-	struct task_struct *tsk;
+	struct task_struct *leader = tsk;
 	struct task_and_cgroup *tc;
 	struct flex_array *group;
 	struct cgroup_taskset tset = { };
@@ -2059,17 +1967,19 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 * group - group_rwsem prevents new threads from appearing, and if
 	 * threads exit, this will just be an over-estimate.
 	 */
-	group_size = get_nr_threads(leader);
+	if (threadgroup)
+		group_size = get_nr_threads(tsk);
+	else
+		group_size = 1;
 	/* flex_array supports very large thread-groups better than kmalloc. */
 	group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
 	if (!group)
 		return -ENOMEM;
 	/* pre-allocate to guarantee space while iterating in rcu read-side. */
-	retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+	retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
 	if (retval)
 		goto out_free_group_list;
 
-	tsk = leader;
 	i = 0;
 	/*
 	 * Prevent freeing of tasks while we take a snapshot. Tasks that are
@@ -2098,6 +2008,9 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 		retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
 		BUG_ON(retval != 0);
 		i++;
+
+		if (!threadgroup)
+			break;
 	} while_each_thread(leader, tsk);
 	rcu_read_unlock();
 	/* remember the number of threads in the array for later. */
@@ -2143,7 +2056,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 */
 	for (i = 0; i < group_size; i++) {
 		tc = flex_array_get(group, i);
-		cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
+		cgroup_task_migrate(tc->cgrp, tc->task, tc->cg);
 	}
 	/* nothing is sensitive to fork() after this point. */
 
@@ -2224,11 +2137,11 @@ retry_find_task:
 		tsk = tsk->group_leader;
 
 	/*
-	 * Workqueue threads may acquire PF_THREAD_BOUND and become
+	 * Workqueue threads may acquire PF_NO_SETAFFINITY and become
 	 * trapped in a cpuset, or RT worker may be born in a cgroup
 	 * with no rt_runtime allocated.  Just say no.
 	 */
-	if (tsk == kthreadd_task || (tsk->flags & PF_THREAD_BOUND)) {
+	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		rcu_read_unlock();
 		goto out_unlock_cgroup;
@@ -2251,17 +2164,42 @@ retry_find_task:
 			put_task_struct(tsk);
 			goto retry_find_task;
 		}
-		ret = cgroup_attach_proc(cgrp, tsk);
-	} else
-		ret = cgroup_attach_task(cgrp, tsk);
+	}
+
+	ret = cgroup_attach_task(cgrp, tsk, threadgroup);
+
 	threadgroup_unlock(tsk);
 
 	put_task_struct(tsk);
 out_unlock_cgroup:
-	cgroup_unlock();
+	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
 
+/**
+ * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
+ * @from: attach to all cgroups of a given task
+ * @tsk: the task to be attached
+ */
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
+{
+	struct cgroupfs_root *root;
+	int retval = 0;
+
+	mutex_lock(&cgroup_mutex);
+	for_each_active_root(root) {
+		struct cgroup *from_cg = task_cgroup_from_root(from, root);
+
+		retval = cgroup_attach_task(from_cg, tsk, false);
+		if (retval)
+			break;
+	}
+	mutex_unlock(&cgroup_mutex);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
+
 static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
 {
 	return attach_task_by_pid(cgrp, pid, false);
@@ -2272,24 +2210,6 @@ static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
 	return attach_task_by_pid(cgrp, tgid, true);
 }
 
-/**
- * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
- * @cgrp: the cgroup to be checked for liveness
- *
- * On success, returns true; the lock should be later released with
- * cgroup_unlock(). On failure returns false with no lock held.
- */
-bool cgroup_lock_live_group(struct cgroup *cgrp)
-{
-	mutex_lock(&cgroup_mutex);
-	if (cgroup_is_removed(cgrp)) {
-		mutex_unlock(&cgroup_mutex);
-		return false;
-	}
-	return true;
-}
-EXPORT_SYMBOL_GPL(cgroup_lock_live_group);
-
 static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 				      const char *buffer)
 {
@@ -2301,7 +2221,7 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 	mutex_lock(&cgroup_root_mutex);
 	strcpy(cgrp->root->release_agent_path, buffer);
 	mutex_unlock(&cgroup_root_mutex);
-	cgroup_unlock();
+	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 
@@ -2312,7 +2232,14 @@ static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
 		return -ENODEV;
 	seq_puts(seq, cgrp->root->release_agent_path);
 	seq_putc(seq, '\n');
-	cgroup_unlock();
+	mutex_unlock(&cgroup_mutex);
+	return 0;
+}
+
+static int cgroup_sane_behavior_show(struct cgroup *cgrp, struct cftype *cft,
+				     struct seq_file *seq)
+{
+	seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
 	return 0;
 }
 
@@ -2537,13 +2464,40 @@ static int cgroup_file_release(struct inode *inode, struct file *file)
 static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
 			    struct inode *new_dir, struct dentry *new_dentry)
 {
+	int ret;
+	struct cgroup_name *name, *old_name;
+	struct cgroup *cgrp;
+
+	/*
+	 * It's convinient to use parent dir's i_mutex to protected
+	 * cgrp->name.
+	 */
+	lockdep_assert_held(&old_dir->i_mutex);
+
 	if (!S_ISDIR(old_dentry->d_inode->i_mode))
 		return -ENOTDIR;
 	if (new_dentry->d_inode)
 		return -EEXIST;
 	if (old_dir != new_dir)
 		return -EIO;
-	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
+
+	cgrp = __d_cgrp(old_dentry);
+
+	name = cgroup_alloc_name(new_dentry);
+	if (!name)
+		return -ENOMEM;
+
+	ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry);
+	if (ret) {
+		kfree(name);
+		return ret;
+	}
+
+	old_name = cgrp->name;
+	rcu_assign_pointer(cgrp->name, name);
+
+	kfree_rcu(old_name, rcu_head);
+	return 0;
 }
 
 static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
@@ -2551,13 +2505,13 @@ static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
 	if (S_ISDIR(dentry->d_inode->i_mode))
 		return &__d_cgrp(dentry)->xattrs;
 	else
-		return &__d_cft(dentry)->xattrs;
+		return &__d_cfe(dentry)->xattrs;
 }
 
 static inline int xattr_enabled(struct dentry *dentry)
 {
 	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
-	return test_bit(ROOT_XATTR, &root->flags);
+	return root->flags & CGRP_ROOT_XATTR;
 }
 
 static bool is_valid_xattr(const char *name)
@@ -2727,9 +2681,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 	umode_t mode;
 	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
 
-	simple_xattrs_init(&cft->xattrs);
-
-	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
+	if (subsys && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
 		strcpy(name, subsys->name);
 		strcat(name, ".");
 	}
@@ -2753,6 +2705,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 		cfe->type = (void *)cft;
 		cfe->dentry = dentry;
 		dentry->d_fsdata = cfe;
+		simple_xattrs_init(&cfe->xattrs);
 		list_add_tail(&cfe->node, &parent->files);
 		cfe = NULL;
 	}
@@ -2770,6 +2723,8 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		/* does cft->flags tell us to skip this file on @cgrp? */
+		if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
+			continue;
 		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
 			continue;
 		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
@@ -3300,6 +3255,34 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 	return 0;
 }
 
+static void cgroup_transfer_one_task(struct task_struct *task,
+				     struct cgroup_scanner *scan)
+{
+	struct cgroup *new_cgroup = scan->data;
+
+	mutex_lock(&cgroup_mutex);
+	cgroup_attach_task(new_cgroup, task, false);
+	mutex_unlock(&cgroup_mutex);
+}
+
+/**
+ * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
+ * @to: cgroup to which the tasks will be moved
+ * @from: cgroup in which the tasks currently reside
+ */
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
+{
+	struct cgroup_scanner scan;
+
+	scan.cg = from;
+	scan.test_task = NULL; /* select all tasks in cgroup */
+	scan.process_task = cgroup_transfer_one_task;
+	scan.heap = NULL;
+	scan.data = to;
+
+	return cgroup_scan_tasks(&scan);
+}
+
 /*
  * Stuff for reading the 'tasks'/'procs' files.
  *
@@ -3362,35 +3345,14 @@ static void pidlist_free(void *p)
 	else
 		kfree(p);
 }
-static void *pidlist_resize(void *p, int newcount)
-{
-	void *newlist;
-	/* note: if new alloc fails, old p will still be valid either way */
-	if (is_vmalloc_addr(p)) {
-		newlist = vmalloc(newcount * sizeof(pid_t));
-		if (!newlist)
-			return NULL;
-		memcpy(newlist, p, newcount * sizeof(pid_t));
-		vfree(p);
-	} else {
-		newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
-	}
-	return newlist;
-}
 
 /*
  * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
- * If the new stripped list is sufficiently smaller and there's enough memory
- * to allocate a new buffer, will let go of the unneeded memory. Returns the
- * number of unique elements.
+ * Returns the number of unique elements.
  */
-/* is the size difference enough that we should re-allocate the array? */
-#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
-static int pidlist_uniq(pid_t **p, int length)
+static int pidlist_uniq(pid_t *list, int length)
 {
 	int src, dest = 1;
-	pid_t *list = *p;
-	pid_t *newlist;
 
 	/*
 	 * we presume the 0th element is unique, so i starts at 1. trivial
@@ -3411,16 +3373,6 @@ static int pidlist_uniq(pid_t **p, int length)
 		dest++;
 	}
 after:
-	/*
-	 * if the length difference is large enough, we want to allocate a
-	 * smaller buffer to save memory. if this fails due to out of memory,
-	 * we'll just stay with what we've got.
-	 */
-	if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
-		newlist = pidlist_resize(list, dest);
-		if (newlist)
-			*p = newlist;
-	}
 	return dest;
 }
 
@@ -3516,7 +3468,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	/* now sort & (if procs) strip out duplicates */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);
 	if (type == CGROUP_FILE_PROCS)
-		length = pidlist_uniq(&array, length);
+		length = pidlist_uniq(array, length);
 	l = cgroup_pidlist_find(cgrp, type);
 	if (!l) {
 		pidlist_free(array);
@@ -3930,11 +3882,7 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
 	if (ret)
 		goto fail;
 
-	if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
-		event->cft->unregister_event(cgrp, event->cft, event->eventfd);
-		ret = 0;
-		goto fail;
-	}
+	efile->f_op->poll(efile, &event->pt);
 
 	/*
 	 * Events should be removed after rmdir of cgroup directory, but before
@@ -4016,10 +3964,16 @@ static struct cftype files[] = {
 	},
 	{
 		.name = "cgroup.clone_children",
+		.flags = CFTYPE_INSANE,
 		.read_u64 = cgroup_clone_children_read,
 		.write_u64 = cgroup_clone_children_write,
 	},
 	{
+		.name = "cgroup.sane_behavior",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.read_seq_string = cgroup_sane_behavior_show,
+	},
+	{
 		.name = "release_agent",
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.read_seq_string = cgroup_release_agent_show,
@@ -4131,17 +4085,8 @@ static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 	if (!(css->flags & CSS_ONLINE))
 		return;
 
-	/*
-	 * css_offline() should be called with cgroup_mutex unlocked.  See
-	 * 3fa59dfbc3 ("cgroup: fix potential deadlock in pre_destroy") for
-	 * details.  This temporary unlocking should go away once
-	 * cgroup_mutex is unexported from controllers.
-	 */
-	if (ss->css_offline) {
-		mutex_unlock(&cgroup_mutex);
+	if (ss->css_offline)
 		ss->css_offline(cgrp);
-		mutex_lock(&cgroup_mutex);
-	}
 
 	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
 }
@@ -4158,6 +4103,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			     umode_t mode)
 {
 	struct cgroup *cgrp;
+	struct cgroup_name *name;
 	struct cgroupfs_root *root = parent->root;
 	int err = 0;
 	struct cgroup_subsys *ss;
@@ -4168,9 +4114,14 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (!cgrp)
 		return -ENOMEM;
 
+	name = cgroup_alloc_name(dentry);
+	if (!name)
+		goto err_free_cgrp;
+	rcu_assign_pointer(cgrp->name, name);
+
 	cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL);
 	if (cgrp->id < 0)
-		goto err_free_cgrp;
+		goto err_free_name;
 
 	/*
 	 * Only live parents can have children.  Note that the liveliness
@@ -4198,7 +4149,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 	cgrp->parent = parent;
 	cgrp->root = parent->root;
-	cgrp->top_cgroup = parent->top_cgroup;
 
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -4241,6 +4191,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	for_each_subsys(root, ss)
 		dget(dentry);
 
+	/* hold a ref to the parent's dentry */
+	dget(parent->dentry);
+
 	/* creation succeeded, notify subsystems */
 	for_each_subsys(root, ss) {
 		err = online_css(ss, cgrp);
@@ -4276,6 +4229,8 @@ err_free_all:
 	deactivate_super(sb);
 err_free_id:
 	ida_simple_remove(&root->cgroup_ida, cgrp->id);
+err_free_name:
+	kfree(rcu_dereference_raw(cgrp->name));
 err_free_cgrp:
 	kfree(cgrp);
 	return err;
@@ -4295,56 +4250,13 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
 }
 
-/*
- * Check the reference count on each subsystem. Since we already
- * established that there are no tasks in the cgroup, if the css refcount
- * is also 1, then there should be no outstanding references, so the
- * subsystem is safe to destroy. We scan across all subsystems rather than
- * using the per-hierarchy linked list of mounted subsystems since we can
- * be called via check_for_release() with no synchronization other than
- * RCU, and the subsystem linked list isn't RCU-safe.
- */
-static int cgroup_has_css_refs(struct cgroup *cgrp)
-{
-	int i;
-
-	/*
-	 * We won't need to lock the subsys array, because the subsystems
-	 * we're concerned about aren't going anywhere since our cgroup root
-	 * has a reference on them.
-	 */
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup_subsys *ss = subsys[i];
-		struct cgroup_subsys_state *css;
-
-		/* Skip subsystems not present or not in this hierarchy */
-		if (ss == NULL || ss->root != cgrp->root)
-			continue;
-
-		css = cgrp->subsys[ss->subsys_id];
-		/*
-		 * When called from check_for_release() it's possible
-		 * that by this point the cgroup has been removed
-		 * and the css deleted. But a false-positive doesn't
-		 * matter, since it can only happen if the cgroup
-		 * has been deleted and hence no longer needs the
-		 * release agent to be called anyway.
-		 */
-		if (css && css_refcnt(css) > 1)
-			return 1;
-	}
-	return 0;
-}
-
 static int cgroup_destroy_locked(struct cgroup *cgrp)
 	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
 	struct dentry *d = cgrp->dentry;
 	struct cgroup *parent = cgrp->parent;
-	DEFINE_WAIT(wait);
 	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
-	LIST_HEAD(tmp_list);
 
 	lockdep_assert_held(&d->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_mutex);
@@ -4468,7 +4380,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * need to invoke fork callbacks here. */
 	BUG_ON(!list_empty(&init_task.tasks));
 
-	ss->active = 1;
 	BUG_ON(online_css(ss, dummytop));
 
 	mutex_unlock(&cgroup_mutex);
@@ -4573,7 +4484,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	}
 	write_unlock(&css_set_lock);
 
-	ss->active = 1;
 	ret = online_css(ss, dummytop);
 	if (ret)
 		goto err_unload;
@@ -4614,7 +4524,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	mutex_lock(&cgroup_mutex);
 
 	offline_css(ss, dummytop);
-	ss->active = 0;
 
 	if (ss->use_id)
 		idr_destroy(&ss->idr);
@@ -4935,17 +4844,17 @@ void cgroup_post_fork(struct task_struct *child)
 	 * and addition to css_set.
 	 */
 	if (need_forkexit_callback) {
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * fork/exit callbacks are supported only for builtin
+		 * subsystems, and the builtin section of the subsys
+		 * array is immutable, so we don't need to lock the
+		 * subsys array here. On the other hand, modular section
+		 * of the array can be freed at module unload, so we
+		 * can't touch that.
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 
-			/*
-			 * fork/exit callbacks are supported only for
-			 * builtin subsystems and we don't need further
-			 * synchronization as they never go away.
-			 */
-			if (!ss || ss->module)
-				continue;
-
 			if (ss->fork)
 				ss->fork(child);
 		}
@@ -5010,13 +4919,13 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	tsk->cgroups = &init_css_set;
 
 	if (run_callbacks && need_forkexit_callback) {
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * fork/exit callbacks are supported only for builtin
+		 * subsystems, see cgroup_post_fork() for details.
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 
-			/* modular subsystems can't use callbacks */
-			if (!ss || ss->module)
-				continue;
-
 			if (ss->exit) {
 				struct cgroup *old_cgrp =
 					rcu_dereference_raw(cg->subsys[i])->cgroup;
@@ -5030,44 +4939,19 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	put_css_set_taskexit(cg);
 }
 
-/**
- * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
- * @cgrp: the cgroup in question
- * @task: the task in question
- *
- * See if @cgrp is a descendant of @task's cgroup in the appropriate
- * hierarchy.
- *
- * If we are sending in dummytop, then presumably we are creating
- * the top cgroup in the subsystem.
- *
- * Called only by the ns (nsproxy) cgroup.
- */
-int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
-{
-	int ret;
-	struct cgroup *target;
-
-	if (cgrp == dummytop)
-		return 1;
-
-	target = task_cgroup_from_root(task, cgrp->root);
-	while (cgrp != target && cgrp!= cgrp->top_cgroup)
-		cgrp = cgrp->parent;
-	ret = (cgrp == target);
-	return ret;
-}
-
 static void check_for_release(struct cgroup *cgrp)
 {
 	/* All of these checks rely on RCU to keep the cgroup
 	 * structure alive */
-	if (cgroup_is_releasable(cgrp) && !atomic_read(&cgrp->count)
-	    && list_empty(&cgrp->children) && !cgroup_has_css_refs(cgrp)) {
-		/* Control Group is currently removeable. If it's not
+	if (cgroup_is_releasable(cgrp) &&
+	    !atomic_read(&cgrp->count) && list_empty(&cgrp->children)) {
+		/*
+		 * Control Group is currently removeable. If it's not
 		 * already queued for a userspace notification, queue
-		 * it now */
+		 * it now
+		 */
 		int need_schedule_work = 0;
+
 		raw_spin_lock(&release_list_lock);
 		if (!cgroup_is_removed(cgrp) &&
 		    list_empty(&cgrp->release_list)) {
@@ -5100,24 +4984,11 @@ EXPORT_SYMBOL_GPL(__css_tryget);
 /* Caller must verify that the css is not for root cgroup */
 void __css_put(struct cgroup_subsys_state *css)
 {
-	struct cgroup *cgrp = css->cgroup;
 	int v;
 
-	rcu_read_lock();
 	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
-
-	switch (v) {
-	case 1:
-		if (notify_on_release(cgrp)) {
-			set_bit(CGRP_RELEASABLE, &cgrp->flags);
-			check_for_release(cgrp);
-		}
-		break;
-	case 0:
+	if (v == 0)
 		schedule_work(&css->dput_work);
-		break;
-	}
-	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(__css_put);
 
@@ -5416,55 +5287,6 @@ struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
 }
 EXPORT_SYMBOL_GPL(css_lookup);
 
-/**
- * css_get_next - lookup next cgroup under specified hierarchy.
- * @ss: pointer to subsystem
- * @id: current position of iteration.
- * @root: pointer to css. search tree under this.
- * @foundid: position of found object.
- *
- * Search next css under the specified hierarchy of rootid. Calling under
- * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
- */
-struct cgroup_subsys_state *
-css_get_next(struct cgroup_subsys *ss, int id,
-	     struct cgroup_subsys_state *root, int *foundid)
-{
-	struct cgroup_subsys_state *ret = NULL;
-	struct css_id *tmp;
-	int tmpid;
-	int rootid = css_id(root);
-	int depth = css_depth(root);
-
-	if (!rootid)
-		return NULL;
-
-	BUG_ON(!ss->use_id);
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	/* fill start point for scan */
-	tmpid = id;
-	while (1) {
-		/*
-		 * scan next entry from bitmap(tree), tmpid is updated after
-		 * idr_get_next().
-		 */
-		tmp = idr_get_next(&ss->idr, &tmpid);
-		if (!tmp)
-			break;
-		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
-			ret = rcu_dereference(tmp->css);
-			if (ret) {
-				*foundid = tmpid;
-				break;
-			}
-		}
-		/* continue to scan from next id */
-		tmpid = tmpid + 1;
-	}
-	return ret;
-}
-
 /*
  * get corresponding css from file open on cgroupfs directory
  */
diff --git a/kernel/cpu/Makefile b/kernel/cpu/Makefile
new file mode 100644
index 000000000000..59ab052ef7a0
--- /dev/null
+++ b/kernel/cpu/Makefile
@@ -0,0 +1 @@
+obj-y	= idle.o
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
new file mode 100644
index 000000000000..168cf407a254
--- /dev/null
+++ b/kernel/cpu/idle.c
@@ -0,0 +1,107 @@
+/*
+ * Generic entry point for the idle threads
+ */
+#include <linux/sched.h>
+#include <linux/cpu.h>
+#include <linux/tick.h>
+#include <linux/mm.h>
+
+#include <asm/tlb.h>
+
+#include <trace/events/power.h>
+
+static int __read_mostly cpu_idle_force_poll;
+
+void cpu_idle_poll_ctrl(bool enable)
+{
+	if (enable) {
+		cpu_idle_force_poll++;
+	} else {
+		cpu_idle_force_poll--;
+		WARN_ON_ONCE(cpu_idle_force_poll < 0);
+	}
+}
+
+#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
+static int __init cpu_idle_poll_setup(char *__unused)
+{
+	cpu_idle_force_poll = 1;
+	return 1;
+}
+__setup("nohlt", cpu_idle_poll_setup);
+
+static int __init cpu_idle_nopoll_setup(char *__unused)
+{
+	cpu_idle_force_poll = 0;
+	return 1;
+}
+__setup("hlt", cpu_idle_nopoll_setup);
+#endif
+
+static inline int cpu_idle_poll(void)
+{
+	trace_cpu_idle_rcuidle(0, smp_processor_id());
+	local_irq_enable();
+	while (!need_resched())
+		cpu_relax();
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+	return 1;
+}
+
+/* Weak implementations for optional arch specific functions */
+void __weak arch_cpu_idle_prepare(void) { }
+void __weak arch_cpu_idle_enter(void) { }
+void __weak arch_cpu_idle_exit(void) { }
+void __weak arch_cpu_idle_dead(void) { }
+void __weak arch_cpu_idle(void)
+{
+	cpu_idle_force_poll = 1;
+}
+
+/*
+ * Generic idle loop implementation
+ */
+static void cpu_idle_loop(void)
+{
+	while (1) {
+		tick_nohz_idle_enter();
+
+		while (!need_resched()) {
+			check_pgt_cache();
+			rmb();
+
+			if (cpu_is_offline(smp_processor_id()))
+				arch_cpu_idle_dead();
+
+			local_irq_disable();
+			arch_cpu_idle_enter();
+
+			if (cpu_idle_force_poll) {
+				cpu_idle_poll();
+			} else {
+				current_clr_polling();
+				if (!need_resched()) {
+					stop_critical_timings();
+					rcu_idle_enter();
+					arch_cpu_idle();
+					WARN_ON_ONCE(irqs_disabled());
+					rcu_idle_exit();
+					start_critical_timings();
+				} else {
+					local_irq_enable();
+				}
+				current_set_polling();
+			}
+			arch_cpu_idle_exit();
+		}
+		tick_nohz_idle_exit();
+		schedule_preempt_disabled();
+	}
+}
+
+void cpu_startup_entry(enum cpuhp_state state)
+{
+	current_set_polling();
+	arch_cpu_idle_prepare();
+	cpu_idle_loop();
+}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4f9dfe43ecbd..12331120767c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -265,17 +265,6 @@ static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_MUTEX(callback_mutex);
 
 /*
- * cpuset_buffer_lock protects both the cpuset_name and cpuset_nodelist
- * buffers.  They are statically allocated to prevent using excess stack
- * when calling cpuset_print_task_mems_allowed().
- */
-#define CPUSET_NAME_LEN		(128)
-#define	CPUSET_NODELIST_LEN	(256)
-static char cpuset_name[CPUSET_NAME_LEN];
-static char cpuset_nodelist[CPUSET_NODELIST_LEN];
-static DEFINE_SPINLOCK(cpuset_buffer_lock);
-
-/*
  * CPU / memory hotplug is handled asynchronously.
  */
 static struct workqueue_struct *cpuset_propagate_hotplug_wq;
@@ -780,25 +769,26 @@ static void rebuild_sched_domains_locked(void)
 	lockdep_assert_held(&cpuset_mutex);
 	get_online_cpus();
 
+	/*
+	 * We have raced with CPU hotplug. Don't do anything to avoid
+	 * passing doms with offlined cpu to partition_sched_domains().
+	 * Anyways, hotplug work item will rebuild sched domains.
+	 */
+	if (!cpumask_equal(top_cpuset.cpus_allowed, cpu_active_mask))
+		goto out;
+
 	/* Generate domain masks and attrs */
 	ndoms = generate_sched_domains(&doms, &attr);
 
 	/* Have scheduler rebuild the domains */
 	partition_sched_domains(ndoms, doms, attr);
-
+out:
 	put_online_cpus();
 }
 #else /* !CONFIG_SMP */
 static void rebuild_sched_domains_locked(void)
 {
 }
-
-static int generate_sched_domains(cpumask_var_t **domains,
-			struct sched_domain_attr **attributes)
-{
-	*domains = NULL;
-	return 1;
-}
 #endif /* CONFIG_SMP */
 
 void rebuild_sched_domains(void)
@@ -1388,16 +1378,16 @@ static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 
 	cgroup_taskset_for_each(task, cgrp, tset) {
 		/*
-		 * Kthreads bound to specific cpus cannot be moved to a new
-		 * cpuset; we cannot change their cpu affinity and
-		 * isolating such threads by their set of allowed nodes is
-		 * unnecessary.  Thus, cpusets are not applicable for such
-		 * threads.  This prevents checking for success of
-		 * set_cpus_allowed_ptr() on all attached tasks before
-		 * cpus_allowed may be changed.
+		 * Kthreads which disallow setaffinity shouldn't be moved
+		 * to a new cpuset; we don't want to change their cpu
+		 * affinity and isolating such threads by their set of
+		 * allowed nodes is unnecessary.  Thus, cpusets are not
+		 * applicable for such threads.  This prevents checking for
+		 * success of set_cpus_allowed_ptr() on all attached tasks
+		 * before cpus_allowed may be changed.
 		 */
 		ret = -EINVAL;
-		if (task->flags & PF_THREAD_BOUND)
+		if (task->flags & PF_NO_SETAFFINITY)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
 		if (ret)
@@ -2005,50 +1995,6 @@ int __init cpuset_init(void)
 	return 0;
 }
 
-/**
- * cpuset_do_move_task - move a given task to another cpuset
- * @tsk: pointer to task_struct the task to move
- * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner
- *
- * Called by cgroup_scan_tasks() for each task in a cgroup.
- * Return nonzero to stop the walk through the tasks.
- */
-static void cpuset_do_move_task(struct task_struct *tsk,
-				struct cgroup_scanner *scan)
-{
-	struct cgroup *new_cgroup = scan->data;
-
-	cgroup_lock();
-	cgroup_attach_task(new_cgroup, tsk);
-	cgroup_unlock();
-}
-
-/**
- * move_member_tasks_to_cpuset - move tasks from one cpuset to another
- * @from: cpuset in which the tasks currently reside
- * @to: cpuset to which the tasks will be moved
- *
- * Called with cpuset_mutex held
- * callback_mutex must not be held, as cpuset_attach() will take it.
- *
- * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
- * calling callback functions for each.
- */
-static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to)
-{
-	struct cgroup_scanner scan;
-
-	scan.cg = from->css.cgroup;
-	scan.test_task = NULL; /* select all tasks in cgroup */
-	scan.process_task = cpuset_do_move_task;
-	scan.heap = NULL;
-	scan.data = to->css.cgroup;
-
-	if (cgroup_scan_tasks(&scan))
-		printk(KERN_ERR "move_member_tasks_to_cpuset: "
-				"cgroup_scan_tasks failed\n");
-}
-
 /*
  * If CPU and/or memory hotplug handlers, below, unplug any CPUs
  * or memory nodes, we need to walk over the cpuset hierarchy,
@@ -2069,7 +2015,12 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 			nodes_empty(parent->mems_allowed))
 		parent = parent_cs(parent);
 
-	move_member_tasks_to_cpuset(cs, parent);
+	if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
+		rcu_read_lock();
+		printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset %s\n",
+		       cgroup_name(cs->css.cgroup));
+		rcu_read_unlock();
+	}
 }
 
 /**
@@ -2222,17 +2173,8 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	flush_workqueue(cpuset_propagate_hotplug_wq);
 
 	/* rebuild sched domains if cpus_allowed has changed */
-	if (cpus_updated) {
-		struct sched_domain_attr *attr;
-		cpumask_var_t *doms;
-		int ndoms;
-
-		mutex_lock(&cpuset_mutex);
-		ndoms = generate_sched_domains(&doms, &attr);
-		mutex_unlock(&cpuset_mutex);
-
-		partition_sched_domains(ndoms, doms, attr);
-	}
+	if (cpus_updated)
+		rebuild_sched_domains();
 }
 
 void cpuset_update_active_cpus(bool cpu_online)
@@ -2251,7 +2193,6 @@ void cpuset_update_active_cpus(bool cpu_online)
 	schedule_work(&cpuset_hotplug_work);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY].
  * Call this routine anytime after node_states[N_MEMORY] changes.
@@ -2263,20 +2204,23 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 	schedule_work(&cpuset_hotplug_work);
 	return NOTIFY_OK;
 }
-#endif
+
+static struct notifier_block cpuset_track_online_nodes_nb = {
+	.notifier_call = cpuset_track_online_nodes,
+	.priority = 10,		/* ??! */
+};
 
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
  * Description: Finish top cpuset after cpu, node maps are initialized
- **/
-
+ */
 void __init cpuset_init_smp(void)
 {
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	top_cpuset.mems_allowed = node_states[N_MEMORY];
 
-	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
+	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
 
 	cpuset_propagate_hotplug_wq =
 		alloc_ordered_workqueue("cpuset_hotplug", 0);
@@ -2592,6 +2536,8 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 	return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed);
 }
 
+#define CPUSET_NODELIST_LEN	(256)
+
 /**
  * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed
  * @task: pointer to task_struct of some task.
@@ -2602,25 +2548,22 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
  */
 void cpuset_print_task_mems_allowed(struct task_struct *tsk)
 {
-	struct dentry *dentry;
+	 /* Statically allocated to prevent using excess stack. */
+	static char cpuset_nodelist[CPUSET_NODELIST_LEN];
+	static DEFINE_SPINLOCK(cpuset_buffer_lock);
 
-	dentry = task_cs(tsk)->css.cgroup->dentry;
-	spin_lock(&cpuset_buffer_lock);
+	struct cgroup *cgrp = task_cs(tsk)->css.cgroup;
 
-	if (!dentry) {
-		strcpy(cpuset_name, "/");
-	} else {
-		spin_lock(&dentry->d_lock);
-		strlcpy(cpuset_name, (const char *)dentry->d_name.name,
-			CPUSET_NAME_LEN);
-		spin_unlock(&dentry->d_lock);
-	}
+	rcu_read_lock();
+	spin_lock(&cpuset_buffer_lock);
 
 	nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
 			   tsk->mems_allowed);
 	printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n",
-	       tsk->comm, cpuset_name, cpuset_nodelist);
+	       tsk->comm, cgroup_name(cgrp), cpuset_nodelist);
+
 	spin_unlock(&cpuset_buffer_lock);
+	rcu_read_unlock();
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ddb993b52190..6b41c1899a8b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -38,6 +38,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/mm_types.h>
+#include <linux/cgroup.h>
 
 #include "internal.h"
 
@@ -235,6 +236,20 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
 #ifdef CONFIG_CGROUP_PERF
 
 /*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+	u64				time;
+	u64				timestamp;
+};
+
+struct perf_cgroup {
+	struct cgroup_subsys_state	css;
+	struct perf_cgroup_info	__percpu *info;
+};
+
+/*
  * Must ensure cgroup is pinned (css_get) before calling
  * this function. In other words, we cannot call this function
  * if there is no cgroup event for the current CPU context.
@@ -252,7 +267,22 @@ perf_cgroup_match(struct perf_event *event)
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
-	return !event->cgrp || event->cgrp == cpuctx->cgrp;
+	/* @event doesn't care about cgroup */
+	if (!event->cgrp)
+		return true;
+
+	/* wants specific cgroup scope but @cpuctx isn't associated with any */
+	if (!cpuctx->cgrp)
+		return false;
+
+	/*
+	 * Cgroup scoping is recursive.  An event enabled for a cgroup is
+	 * also enabled for all its descendant cgroups.  If @cpuctx's
+	 * cgroup is a descendant of @event's (the test covers identity
+	 * case), it's a match.
+	 */
+	return cgroup_is_descendant(cpuctx->cgrp->css.cgroup,
+				    event->cgrp->css.cgroup);
 }
 
 static inline bool perf_tryget_cgroup(struct perf_event *event)
@@ -966,9 +996,15 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		size += sizeof(data->period);
 
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		size += sizeof(data->weight);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
 
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		size += sizeof(data->data_src.val);
+
 	event->header_size = size;
 }
 
@@ -4193,6 +4229,12 @@ void perf_output_sample(struct perf_output_handle *handle,
 		perf_output_sample_ustack(handle,
 					  data->stack_user_size,
 					  data->regs_user.regs);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		perf_output_put(handle, data->weight);
+
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		perf_output_put(handle, data->data_src.val);
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -4449,12 +4491,15 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 			if (ctxn < 0)
 				goto next;
 			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+			if (ctx)
+				perf_event_task_ctx(ctx, task_event);
 		}
-		if (ctx)
-			perf_event_task_ctx(ctx, task_event);
 next:
 		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
+	if (task_event->task_ctx)
+		perf_event_task_ctx(task_event->task_ctx, task_event);
+
 	rcu_read_unlock();
 }
 
@@ -4608,6 +4653,7 @@ void perf_event_comm(struct task_struct *task)
 	struct perf_event_context *ctx;
 	int ctxn;
 
+	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
 		ctx = task->perf_event_ctxp[ctxn];
 		if (!ctx)
@@ -4615,6 +4661,7 @@ void perf_event_comm(struct task_struct *task)
 
 		perf_event_enable_on_exec(ctx);
 	}
+	rcu_read_unlock();
 
 	if (!atomic_read(&nr_comm_events))
 		return;
@@ -4749,7 +4796,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	} else {
 		if (arch_vma_name(mmap_event->vma)) {
 			name = strncpy(tmp, arch_vma_name(mmap_event->vma),
-				       sizeof(tmp));
+				       sizeof(tmp) - 1);
+			tmp[sizeof(tmp) - 1] = '\0';
 			goto got_name;
 		}
 
@@ -4776,6 +4824,9 @@ got_name:
 	mmap_event->file_name = name;
 	mmap_event->file_size = size;
 
+	if (!(vma->vm_flags & VM_EXEC))
+		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
 	rcu_read_lock();
@@ -5342,7 +5393,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 
 static int perf_swevent_init(struct perf_event *event)
 {
-	int event_id = event->attr.config;
+	u64 event_id = event->attr.config;
 
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
@@ -5662,6 +5713,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
 		event->attr.sample_period = NSEC_PER_SEC / freq;
 		hwc->sample_period = event->attr.sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
+		hwc->last_period = hwc->sample_period;
 		event->attr.freq = 0;
 	}
 }
@@ -5997,6 +6049,7 @@ skip_type:
 	if (pmu->pmu_cpu_context)
 		goto got_cpu_context;
 
+	ret = -ENOMEM;
 	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
 	if (!pmu->pmu_cpu_context)
 		goto free_dev;
@@ -7524,12 +7577,5 @@ struct cgroup_subsys perf_subsys = {
 	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,
 	.attach		= perf_cgroup_attach,
-
-	/*
-	 * perf_event cgroup doesn't handle nesting correctly.
-	 * ctx->nr_cgroups adjustments should be propagated through the
-	 * cgroup hierarchy.  Fix it and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index d56a64c99a8b..eb675c4d59df 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -16,7 +16,7 @@ struct ring_buffer {
 	int				page_order;	/* allocation order  */
 #endif
 	int				nr_pages;	/* nr of data pages  */
-	int				writable;	/* are we writable   */
+	int				overwrite;	/* can overwrite itself */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 23cb34ff3973..97fddb09762b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -18,12 +18,24 @@
 static bool perf_output_space(struct ring_buffer *rb, unsigned long tail,
 			      unsigned long offset, unsigned long head)
 {
-	unsigned long mask;
+	unsigned long sz = perf_data_size(rb);
+	unsigned long mask = sz - 1;
 
-	if (!rb->writable)
+	/*
+	 * check if user-writable
+	 * overwrite : over-write its own tail
+	 * !overwrite: buffer possibly drops events.
+	 */
+	if (rb->overwrite)
 		return true;
 
-	mask = perf_data_size(rb) - 1;
+	/*
+	 * verify that payload is not bigger than buffer
+	 * otherwise masking logic may fail to detect
+	 * the "not enough space" condition
+	 */
+	if ((head - offset) > sz)
+		return false;
 
 	offset = (offset - tail) & mask;
 	head   = (head   - tail) & mask;
@@ -212,7 +224,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->watermark = max_size / 2;
 
 	if (flags & RING_BUFFER_WRITABLE)
-		rb->writable = 1;
+		rb->overwrite = 0;
+	else
+		rb->overwrite = 1;
 
 	atomic_set(&rb->refcount, 1);
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index a567c8c7ef31..f3569747d629 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -75,6 +75,15 @@ struct uprobe {
 	struct arch_uprobe	arch;
 };
 
+struct return_instance {
+	struct uprobe		*uprobe;
+	unsigned long		func;
+	unsigned long		orig_ret_vaddr; /* original return address */
+	bool			chained;	/* true, if instance is nested */
+
+	struct return_instance	*next;		/* keep as stack */
+};
+
 /*
  * valid_vma: Verify if the specified vma is an executable vma
  * Relax restrictions while unregistering: vm_flags might have
@@ -173,10 +182,31 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn)
 	return *insn == UPROBE_SWBP_INSN;
 }
 
-static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode)
+/**
+ * is_trap_insn - check if instruction is breakpoint instruction.
+ * @insn: instruction to be checked.
+ * Default implementation of is_trap_insn
+ * Returns true if @insn is a breakpoint instruction.
+ *
+ * This function is needed for the case where an architecture has multiple
+ * trap instructions (like powerpc).
+ */
+bool __weak is_trap_insn(uprobe_opcode_t *insn)
+{
+	return is_swbp_insn(insn);
+}
+
+static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len)
 {
 	void *kaddr = kmap_atomic(page);
-	memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE);
+	memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len);
+	kunmap_atomic(kaddr);
+}
+
+static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len)
+{
+	void *kaddr = kmap_atomic(page);
+	memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len);
 	kunmap_atomic(kaddr);
 }
 
@@ -185,7 +215,16 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
 	uprobe_opcode_t old_opcode;
 	bool is_swbp;
 
-	copy_opcode(page, vaddr, &old_opcode);
+	/*
+	 * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here.
+	 * We do not check if it is any other 'trap variant' which could
+	 * be conditional trap instruction such as the one powerpc supports.
+	 *
+	 * The logic is that we do not care if the underlying instruction
+	 * is a trap variant; uprobes always wins over any other (gdb)
+	 * breakpoint.
+	 */
+	copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE);
 	is_swbp = is_swbp_insn(&old_opcode);
 
 	if (is_swbp_insn(new_opcode)) {
@@ -204,7 +243,7 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
  * Expect the breakpoint instruction to be the smallest size instruction for
  * the architecture. If an arch has variable length instruction and the
  * breakpoint instruction is not of the smallest length instruction
- * supported by that architecture then we need to modify is_swbp_at_addr and
+ * supported by that architecture then we need to modify is_trap_at_addr and
  * write_opcode accordingly. This would never be a problem for archs that
  * have fixed length instructions.
  */
@@ -225,7 +264,6 @@ static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
 			uprobe_opcode_t opcode)
 {
 	struct page *old_page, *new_page;
-	void *vaddr_old, *vaddr_new;
 	struct vm_area_struct *vma;
 	int ret;
 
@@ -246,15 +284,8 @@ retry:
 
 	__SetPageUptodate(new_page);
 
-	/* copy the page now that we've got it stable */
-	vaddr_old = kmap_atomic(old_page);
-	vaddr_new = kmap_atomic(new_page);
-
-	memcpy(vaddr_new, vaddr_old, PAGE_SIZE);
-	memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE);
-
-	kunmap_atomic(vaddr_new);
-	kunmap_atomic(vaddr_old);
+	copy_highpage(new_page, old_page);
+	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
 	ret = anon_vma_prepare(vma);
 	if (ret)
@@ -477,30 +508,18 @@ __copy_insn(struct address_space *mapping, struct file *filp, char *insn,
 			unsigned long nbytes, loff_t offset)
 {
 	struct page *page;
-	void *vaddr;
-	unsigned long off;
-	pgoff_t idx;
-
-	if (!filp)
-		return -EINVAL;
 
 	if (!mapping->a_ops->readpage)
 		return -EIO;
-
-	idx = offset >> PAGE_CACHE_SHIFT;
-	off = offset & ~PAGE_MASK;
-
 	/*
 	 * Ensure that the page that has the original instruction is
 	 * populated and in page-cache.
 	 */
-	page = read_mapping_page(mapping, idx, filp);
+	page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp);
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
-	vaddr = kmap_atomic(page);
-	memcpy(insn, vaddr + off, nbytes);
-	kunmap_atomic(vaddr);
+	copy_from_page(page, offset, insn, nbytes);
 	page_cache_release(page);
 
 	return 0;
@@ -550,7 +569,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 		goto out;
 
 	ret = -ENOTSUPP;
-	if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
+	if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
 		goto out;
 
 	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
@@ -758,7 +777,7 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		down_write(&mm->mmap_sem);
 		vma = find_vma(mm, info->vaddr);
 		if (!vma || !valid_vma(vma, is_register) ||
-		    vma->vm_file->f_mapping->host != uprobe->inode)
+		    file_inode(vma->vm_file) != uprobe->inode)
 			goto unlock;
 
 		if (vma->vm_start > info->vaddr ||
@@ -828,6 +847,10 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	struct uprobe *uprobe;
 	int ret;
 
+	/* Uprobe must have at least one set consumer */
+	if (!uc->handler && !uc->ret_handler)
+		return -EINVAL;
+
 	/* Racy, just to catch the obvious mistakes */
 	if (offset > i_size_read(inode))
 		return -EINVAL;
@@ -917,7 +940,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 		loff_t offset;
 
 		if (!valid_vma(vma, false) ||
-		    vma->vm_file->f_mapping->host != uprobe->inode)
+		    file_inode(vma->vm_file) != uprobe->inode)
 			continue;
 
 		offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
@@ -1010,7 +1033,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
 	if (no_uprobe_events() || !valid_vma(vma, true))
 		return 0;
 
-	inode = vma->vm_file->f_mapping->host;
+	inode = file_inode(vma->vm_file);
 	if (!inode)
 		return 0;
 
@@ -1041,7 +1064,7 @@ vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long e
 	struct inode *inode;
 	struct rb_node *n;
 
-	inode = vma->vm_file->f_mapping->host;
+	inode = file_inode(vma->vm_file);
 
 	min = vaddr_to_offset(vma, start);
 	max = min + (end - start) - 1;
@@ -1114,6 +1137,7 @@ static struct xol_area *get_xol_area(void)
 {
 	struct mm_struct *mm = current->mm;
 	struct xol_area *area;
+	uprobe_opcode_t insn = UPROBE_SWBP_INSN;
 
 	area = mm->uprobes_state.xol_area;
 	if (area)
@@ -1131,7 +1155,12 @@ static struct xol_area *get_xol_area(void)
 	if (!area->page)
 		goto free_bitmap;
 
+	/* allocate first slot of task's xol_area for the return probes */
+	set_bit(0, area->bitmap);
+	copy_to_page(area->page, 0, &insn, UPROBE_SWBP_INSN_SIZE);
+	atomic_set(&area->slot_count, 1);
 	init_waitqueue_head(&area->wq);
+
 	if (!xol_add_vma(area))
 		return area;
 
@@ -1216,9 +1245,7 @@ static unsigned long xol_take_insn_slot(struct xol_area *area)
 static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 {
 	struct xol_area *area;
-	unsigned long offset;
 	unsigned long xol_vaddr;
-	void *vaddr;
 
 	area = get_xol_area();
 	if (!area)
@@ -1229,10 +1256,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 		return 0;
 
 	/* Initialize the slot */
-	offset = xol_vaddr & ~PAGE_MASK;
-	vaddr = kmap_atomic(area->page);
-	memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES);
-	kunmap_atomic(vaddr);
+	copy_to_page(area->page, xol_vaddr, uprobe->arch.insn, MAX_UINSN_BYTES);
 	/*
 	 * We probably need flush_icache_user_range() but it needs vma.
 	 * This should work on supported architectures too.
@@ -1298,6 +1322,7 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
 void uprobe_free_utask(struct task_struct *t)
 {
 	struct uprobe_task *utask = t->utask;
+	struct return_instance *ri, *tmp;
 
 	if (!utask)
 		return;
@@ -1305,6 +1330,15 @@ void uprobe_free_utask(struct task_struct *t)
 	if (utask->active_uprobe)
 		put_uprobe(utask->active_uprobe);
 
+	ri = utask->return_instances;
+	while (ri) {
+		tmp = ri;
+		ri = ri->next;
+
+		put_uprobe(tmp->uprobe);
+		kfree(tmp);
+	}
+
 	xol_free_insn_slot(t);
 	kfree(utask);
 	t->utask = NULL;
@@ -1333,6 +1367,93 @@ static struct uprobe_task *get_utask(void)
 	return current->utask;
 }
 
+/*
+ * Current area->vaddr notion assume the trampoline address is always
+ * equal area->vaddr.
+ *
+ * Returns -1 in case the xol_area is not allocated.
+ */
+static unsigned long get_trampoline_vaddr(void)
+{
+	struct xol_area *area;
+	unsigned long trampoline_vaddr = -1;
+
+	area = current->mm->uprobes_state.xol_area;
+	smp_read_barrier_depends();
+	if (area)
+		trampoline_vaddr = area->vaddr;
+
+	return trampoline_vaddr;
+}
+
+static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
+{
+	struct return_instance *ri;
+	struct uprobe_task *utask;
+	unsigned long orig_ret_vaddr, trampoline_vaddr;
+	bool chained = false;
+
+	if (!get_xol_area())
+		return;
+
+	utask = get_utask();
+	if (!utask)
+		return;
+
+	if (utask->depth >= MAX_URETPROBE_DEPTH) {
+		printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to"
+				" nestedness limit pid/tgid=%d/%d\n",
+				current->pid, current->tgid);
+		return;
+	}
+
+	ri = kzalloc(sizeof(struct return_instance), GFP_KERNEL);
+	if (!ri)
+		goto fail;
+
+	trampoline_vaddr = get_trampoline_vaddr();
+	orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
+	if (orig_ret_vaddr == -1)
+		goto fail;
+
+	/*
+	 * We don't want to keep trampoline address in stack, rather keep the
+	 * original return address of first caller thru all the consequent
+	 * instances. This also makes breakpoint unwrapping easier.
+	 */
+	if (orig_ret_vaddr == trampoline_vaddr) {
+		if (!utask->return_instances) {
+			/*
+			 * This situation is not possible. Likely we have an
+			 * attack from user-space.
+			 */
+			pr_warn("uprobe: unable to set uretprobe pid/tgid=%d/%d\n",
+						current->pid, current->tgid);
+			goto fail;
+		}
+
+		chained = true;
+		orig_ret_vaddr = utask->return_instances->orig_ret_vaddr;
+	}
+
+	atomic_inc(&uprobe->ref);
+	ri->uprobe = uprobe;
+	ri->func = instruction_pointer(regs);
+	ri->orig_ret_vaddr = orig_ret_vaddr;
+	ri->chained = chained;
+
+	utask->depth++;
+
+	/* add instance to the stack */
+	ri->next = utask->return_instances;
+	utask->return_instances = ri;
+
+	return;
+
+ fail:
+	kfree(ri);
+}
+
 /* Prepare to single-step probed instruction out of line. */
 static int
 pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr)
@@ -1431,7 +1552,7 @@ static void mmf_recalc_uprobes(struct mm_struct *mm)
 	clear_bit(MMF_HAS_UPROBES, &mm->flags);
 }
 
-static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
+static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 {
 	struct page *page;
 	uprobe_opcode_t opcode;
@@ -1449,10 +1570,11 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	if (result < 0)
 		return result;
 
-	copy_opcode(page, vaddr, &opcode);
+	copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 	put_page(page);
  out:
-	return is_swbp_insn(&opcode);
+	/* This needs to return true for any variant of the trap insn */
+	return is_trap_insn(&opcode);
 }
 
 static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
@@ -1465,14 +1587,14 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	vma = find_vma(mm, bp_vaddr);
 	if (vma && vma->vm_start <= bp_vaddr) {
 		if (valid_vma(vma, false)) {
-			struct inode *inode = vma->vm_file->f_mapping->host;
+			struct inode *inode = file_inode(vma->vm_file);
 			loff_t offset = vaddr_to_offset(vma, bp_vaddr);
 
 			uprobe = find_uprobe(inode, offset);
 		}
 
 		if (!uprobe)
-			*is_swbp = is_swbp_at_addr(mm, bp_vaddr);
+			*is_swbp = is_trap_at_addr(mm, bp_vaddr);
 	} else {
 		*is_swbp = -EFAULT;
 	}
@@ -1488,16 +1610,27 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 {
 	struct uprobe_consumer *uc;
 	int remove = UPROBE_HANDLER_REMOVE;
+	bool need_prep = false; /* prepare return uprobe, when needed */
 
 	down_read(&uprobe->register_rwsem);
 	for (uc = uprobe->consumers; uc; uc = uc->next) {
-		int rc = uc->handler(uc, regs);
+		int rc = 0;
+
+		if (uc->handler) {
+			rc = uc->handler(uc, regs);
+			WARN(rc & ~UPROBE_HANDLER_MASK,
+				"bad rc=0x%x from %pf()\n", rc, uc->handler);
+		}
+
+		if (uc->ret_handler)
+			need_prep = true;
 
-		WARN(rc & ~UPROBE_HANDLER_MASK,
-			"bad rc=0x%x from %pf()\n", rc, uc->handler);
 		remove &= rc;
 	}
 
+	if (need_prep && !remove)
+		prepare_uretprobe(uprobe, regs); /* put bp at return */
+
 	if (remove && uprobe->consumers) {
 		WARN_ON(!uprobe_is_active(uprobe));
 		unapply_uprobe(uprobe, current->mm);
@@ -1505,6 +1638,64 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 	up_read(&uprobe->register_rwsem);
 }
 
+static void
+handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs)
+{
+	struct uprobe *uprobe = ri->uprobe;
+	struct uprobe_consumer *uc;
+
+	down_read(&uprobe->register_rwsem);
+	for (uc = uprobe->consumers; uc; uc = uc->next) {
+		if (uc->ret_handler)
+			uc->ret_handler(uc, ri->func, regs);
+	}
+	up_read(&uprobe->register_rwsem);
+}
+
+static bool handle_trampoline(struct pt_regs *regs)
+{
+	struct uprobe_task *utask;
+	struct return_instance *ri, *tmp;
+	bool chained;
+
+	utask = current->utask;
+	if (!utask)
+		return false;
+
+	ri = utask->return_instances;
+	if (!ri)
+		return false;
+
+	/*
+	 * TODO: we should throw out return_instance's invalidated by
+	 * longjmp(), currently we assume that the probed function always
+	 * returns.
+	 */
+	instruction_pointer_set(regs, ri->orig_ret_vaddr);
+
+	for (;;) {
+		handle_uretprobe_chain(ri, regs);
+
+		chained = ri->chained;
+		put_uprobe(ri->uprobe);
+
+		tmp = ri;
+		ri = ri->next;
+		kfree(tmp);
+
+		if (!chained)
+			break;
+
+		utask->depth--;
+
+		BUG_ON(!ri);
+	}
+
+	utask->return_instances = ri;
+
+	return true;
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1516,8 +1707,15 @@ static void handle_swbp(struct pt_regs *regs)
 	int uninitialized_var(is_swbp);
 
 	bp_vaddr = uprobe_get_swbp_addr(regs);
-	uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
+	if (bp_vaddr == get_trampoline_vaddr()) {
+		if (handle_trampoline(regs))
+			return;
+
+		pr_warn("uprobe: unable to handle uretprobe pid/tgid=%d/%d\n",
+						current->pid, current->tgid);
+	}
 
+	uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
 	if (!uprobe) {
 		if (is_swbp > 0) {
 			/* No matching uprobe; signal SIGTRAP. */
@@ -1616,7 +1814,11 @@ void uprobe_notify_resume(struct pt_regs *regs)
  */
 int uprobe_pre_sstep_notifier(struct pt_regs *regs)
 {
-	if (!current->mm || !test_bit(MMF_HAS_UPROBES, &current->mm->flags))
+	if (!current->mm)
+		return 0;
+
+	if (!test_bit(MMF_HAS_UPROBES, &current->mm->flags) &&
+	    (!current->utask || !current->utask->return_instances))
 		return 0;
 
 	set_thread_flag(TIF_UPROBE);
diff --git a/kernel/exit.c b/kernel/exit.c
index 51e485ca9935..60bc027c61c3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -835,7 +835,7 @@ void do_exit(long code)
 	/*
 	 * Make sure we are holding no locks:
 	 */
-	debug_check_no_locks_held();
+	debug_check_no_locks_held(tsk);
 	/*
 	 * We can do this unlocked here. The futex code uses this flag
 	 * just to verify whether the pi state cleanup has been done
diff --git a/kernel/fork.c b/kernel/fork.c
index f3146ed49074..339f60dfd62b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1141,6 +1141,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
 
+	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * Thread groups must share signals as well, and detached threads
 	 * can only be started up within the thread group.
@@ -1807,7 +1810,7 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	 * If unsharing a user namespace must also unshare the thread.
 	 */
 	if (unshare_flags & CLONE_NEWUSER)
-		unshare_flags |= CLONE_THREAD;
+		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
 	 * If unsharing a pid namespace must also unshare the thread.
 	 */
diff --git a/kernel/futex.c b/kernel/futex.c
index f0090a993dab..b26dcfc02c94 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -223,7 +223,8 @@ static void drop_futex_key_refs(union futex_key *key)
  * @rw:		mapping needs to be read/write (values: VERIFY_READ,
  *              VERIFY_WRITE)
  *
- * Returns a negative error code or 0
+ * Return: a negative error code or 0
+ *
  * The key words are stored in *key on success.
  *
  * For shared mappings, it's (page->index, file_inode(vma->vm_file),
@@ -705,9 +706,9 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
  *			be "current" except in the case of requeue pi.
  * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
  *
- * Returns:
- *  0 - ready to wait
- *  1 - acquired the lock
+ * Return:
+ *  0 - ready to wait;
+ *  1 - acquired the lock;
  * <0 - error
  *
  * The hb->lock and futex_key refs shall be held by the caller.
@@ -1191,9 +1192,9 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
  * hb1 and hb2 must be held by the caller.
  *
- * Returns:
- *  0 - failed to acquire the lock atomicly
- *  1 - acquired the lock
+ * Return:
+ *  0 - failed to acquire the lock atomically;
+ *  1 - acquired the lock;
  * <0 - error
  */
 static int futex_proxy_trylock_atomic(u32 __user *pifutex,
@@ -1254,8 +1255,8 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
  * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
  * uaddr2 atomically on behalf of the top waiter.
  *
- * Returns:
- * >=0 - on success, the number of tasks requeued or woken
+ * Return:
+ * >=0 - on success, the number of tasks requeued or woken;
  *  <0 - on error
  */
 static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
@@ -1536,8 +1537,8 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
  * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
  * be paired with exactly one earlier call to queue_me().
  *
- * Returns:
- *   1 - if the futex_q was still queued (and we removed unqueued it)
+ * Return:
+ *   1 - if the futex_q was still queued (and we removed unqueued it);
  *   0 - if the futex_q was already removed by the waking thread
  */
 static int unqueue_me(struct futex_q *q)
@@ -1707,9 +1708,9 @@ static long futex_wait_restart(struct restart_block *restart);
  * the pi_state owner as well as handle race conditions that may allow us to
  * acquire the lock. Must be called with the hb lock held.
  *
- * Returns:
- *  1 - success, lock taken
- *  0 - success, lock not taken
+ * Return:
+ *  1 - success, lock taken;
+ *  0 - success, lock not taken;
  * <0 - on error (-EFAULT)
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
@@ -1824,8 +1825,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
  * Return with the hb lock held and a q.key reference on success, and unlocked
  * with no q.key reference on failure.
  *
- * Returns:
- *  0 - uaddr contains val and hb has been locked
+ * Return:
+ *  0 - uaddr contains val and hb has been locked;
  * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked
  */
 static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
@@ -2203,9 +2204,9 @@ pi_faulted:
  * the wakeup and return the appropriate error code to the caller.  Must be
  * called with the hb lock held.
  *
- * Returns
- *  0 - no early wakeup detected
- * <0 - -ETIMEDOUT or -ERESTARTNOINTR
+ * Return:
+ *  0 = no early wakeup detected;
+ * <0 = -ETIMEDOUT or -ERESTARTNOINTR
  */
 static inline
 int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
@@ -2247,7 +2248,6 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * @val:	the expected value of uaddr
  * @abs_time:	absolute timeout
  * @bitset:	32 bit wakeup bitset set by userspace, defaults to all
- * @clockrt:	whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
  * @uaddr2:	the pi futex we will take prior to returning to user-space
  *
  * The caller will wait on uaddr and will be requeued by futex_requeue() to
@@ -2258,7 +2258,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * there was a need to.
  *
  * We call schedule in futex_wait_queue_me() when we enqueue and return there
- * via the following:
+ * via the following--
  * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
  * 2) wakeup on uaddr2 after a requeue
  * 3) signal
@@ -2276,8 +2276,8 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  *
  * If 4 or 7, we cleanup and return with -ETIMEDOUT.
  *
- * Returns:
- *  0 - On success
+ * Return:
+ *  0 - On success;
  * <0 - On error
  */
 static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ec60482d8b03..abfd89d687ac 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -63,6 +63,7 @@
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
 
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
 	.clock_base =
 	{
 		{
@@ -1642,8 +1643,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 	int i;
 
-	raw_spin_lock_init(&cpu_base->lock);
-
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		cpu_base->clock_base[i].cpu_base = cpu_base;
 		timerqueue_init_head(&cpu_base->clock_base[i].active);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index bddd3d7a74b6..b574920cbd4b 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -55,7 +55,7 @@ struct resource crashk_res = {
 	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
 };
 struct resource crashk_low_res = {
-	.name  = "Crash kernel low",
+	.name  = "Crash kernel",
 	.start = 0,
 	.end   = 0,
 	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
@@ -1118,12 +1118,8 @@ void __weak crash_free_reserved_phys_range(unsigned long begin,
 {
 	unsigned long addr;
 
-	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
-		init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
-		free_page((unsigned long)__va(addr));
-		totalram_pages++;
-	}
+	for (addr = begin; addr < end; addr += PAGE_SIZE)
+		free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
 }
 
 int crash_shrink_memory(unsigned long new_size)
@@ -1368,35 +1364,114 @@ static int __init parse_crashkernel_simple(char 		*cmdline,
 	return 0;
 }
 
+#define SUFFIX_HIGH 0
+#define SUFFIX_LOW  1
+#define SUFFIX_NULL 2
+static __initdata char *suffix_tbl[] = {
+	[SUFFIX_HIGH] = ",high",
+	[SUFFIX_LOW]  = ",low",
+	[SUFFIX_NULL] = NULL,
+};
+
 /*
- * That function is the entry point for command line parsing and should be
- * called from the arch-specific code.
+ * That function parses "suffix"  crashkernel command lines like
+ *
+ *	crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
  */
+static int __init parse_crashkernel_suffix(char *cmdline,
+					   unsigned long long	*crash_size,
+					   unsigned long long	*crash_base,
+					   const char *suffix)
+{
+	char *cur = cmdline;
+
+	*crash_size = memparse(cmdline, &cur);
+	if (cmdline == cur) {
+		pr_warn("crashkernel: memory value expected\n");
+		return -EINVAL;
+	}
+
+	/* check with suffix */
+	if (strncmp(cur, suffix, strlen(suffix))) {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+	cur += strlen(suffix);
+	if (*cur != ' ' && *cur != '\0') {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static __init char *get_last_crashkernel(char *cmdline,
+			     const char *name,
+			     const char *suffix)
+{
+	char *p = cmdline, *ck_cmdline = NULL;
+
+	/* find crashkernel and use the last one if there are more */
+	p = strstr(p, name);
+	while (p) {
+		char *end_p = strchr(p, ' ');
+		char *q;
+
+		if (!end_p)
+			end_p = p + strlen(p);
+
+		if (!suffix) {
+			int i;
+
+			/* skip the one with any known suffix */
+			for (i = 0; suffix_tbl[i]; i++) {
+				q = end_p - strlen(suffix_tbl[i]);
+				if (!strncmp(q, suffix_tbl[i],
+					     strlen(suffix_tbl[i])))
+					goto next;
+			}
+			ck_cmdline = p;
+		} else {
+			q = end_p - strlen(suffix);
+			if (!strncmp(q, suffix, strlen(suffix)))
+				ck_cmdline = p;
+		}
+next:
+		p = strstr(p+1, name);
+	}
+
+	if (!ck_cmdline)
+		return NULL;
+
+	return ck_cmdline;
+}
+
 static int __init __parse_crashkernel(char *cmdline,
 			     unsigned long long system_ram,
 			     unsigned long long *crash_size,
 			     unsigned long long *crash_base,
-				const char *name)
+			     const char *name,
+			     const char *suffix)
 {
-	char 	*p = cmdline, *ck_cmdline = NULL;
 	char	*first_colon, *first_space;
+	char	*ck_cmdline;
 
 	BUG_ON(!crash_size || !crash_base);
 	*crash_size = 0;
 	*crash_base = 0;
 
-	/* find crashkernel and use the last one if there are more */
-	p = strstr(p, name);
-	while (p) {
-		ck_cmdline = p;
-		p = strstr(p+1, name);
-	}
+	ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
 
 	if (!ck_cmdline)
 		return -EINVAL;
 
 	ck_cmdline += strlen(name);
 
+	if (suffix)
+		return parse_crashkernel_suffix(ck_cmdline, crash_size,
+				crash_base, suffix);
 	/*
 	 * if the commandline contains a ':', then that's the extended
 	 * syntax -- if not, it must be the classic syntax
@@ -1413,13 +1488,26 @@ static int __init __parse_crashkernel(char *cmdline,
 	return 0;
 }
 
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
 int __init parse_crashkernel(char *cmdline,
 			     unsigned long long system_ram,
 			     unsigned long long *crash_size,
 			     unsigned long long *crash_base)
 {
 	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-					"crashkernel=");
+					"crashkernel=", NULL);
+}
+
+int __init parse_crashkernel_high(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+				"crashkernel=", suffix_tbl[SUFFIX_HIGH]);
 }
 
 int __init parse_crashkernel_low(char *cmdline,
@@ -1428,7 +1516,7 @@ int __init parse_crashkernel_low(char *cmdline,
 			     unsigned long long *crash_base)
 {
 	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-					"crashkernel_low=");
+				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
 }
 
 static void update_vmcoreinfo_note(void)
@@ -1489,7 +1577,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_SYMBOL(swapper_pg_dir);
 #endif
 	VMCOREINFO_SYMBOL(_stext);
-	VMCOREINFO_SYMBOL(vmlist);
+	VMCOREINFO_SYMBOL(vmap_area_list);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 	VMCOREINFO_SYMBOL(mem_map);
@@ -1527,7 +1615,8 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(free_area, free_list);
 	VMCOREINFO_OFFSET(list_head, next);
 	VMCOREINFO_OFFSET(list_head, prev);
-	VMCOREINFO_OFFSET(vm_struct, addr);
+	VMCOREINFO_OFFSET(vmap_area, va_start);
+	VMCOREINFO_OFFSET(vmap_area, list);
 	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
 	log_buf_kexec_setup();
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e35be53f6613..3fed7f0cbcdf 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -794,16 +794,16 @@ out:
 }
 
 #ifdef CONFIG_SYSCTL
-/* This should be called with kprobe_mutex locked */
 static void __kprobes optimize_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
 	unsigned int i;
 
+	mutex_lock(&kprobe_mutex);
 	/* If optimization is already allowed, just return */
 	if (kprobes_allow_optimization)
-		return;
+		goto out;
 
 	kprobes_allow_optimization = true;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
@@ -813,18 +813,22 @@ static void __kprobes optimize_all_kprobes(void)
 				optimize_kprobe(p);
 	}
 	printk(KERN_INFO "Kprobes globally optimized\n");
+out:
+	mutex_unlock(&kprobe_mutex);
 }
 
-/* This should be called with kprobe_mutex locked */
 static void __kprobes unoptimize_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
 	unsigned int i;
 
+	mutex_lock(&kprobe_mutex);
 	/* If optimization is already prohibited, just return */
-	if (!kprobes_allow_optimization)
+	if (!kprobes_allow_optimization) {
+		mutex_unlock(&kprobe_mutex);
 		return;
+	}
 
 	kprobes_allow_optimization = false;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
@@ -834,11 +838,14 @@ static void __kprobes unoptimize_all_kprobes(void)
 				unoptimize_kprobe(p, false);
 		}
 	}
+	mutex_unlock(&kprobe_mutex);
+
 	/* Wait for unoptimizing completion */
 	wait_for_kprobe_optimizer();
 	printk(KERN_INFO "Kprobes globally unoptimized\n");
 }
 
+static DEFINE_MUTEX(kprobe_sysctl_mutex);
 int sysctl_kprobes_optimization;
 int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 				      void __user *buffer, size_t *length,
@@ -846,7 +853,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 {
 	int ret;
 
-	mutex_lock(&kprobe_mutex);
+	mutex_lock(&kprobe_sysctl_mutex);
 	sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
 
@@ -854,7 +861,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 		optimize_all_kprobes();
 	else
 		unoptimize_all_kprobes();
-	mutex_unlock(&kprobe_mutex);
+	mutex_unlock(&kprobe_sysctl_mutex);
 
 	return ret;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 691dc2ef9baf..16d8ddd268b1 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -52,8 +52,21 @@ enum KTHREAD_BITS {
 	KTHREAD_IS_PARKED,
 };
 
-#define to_kthread(tsk)	\
-	container_of((tsk)->vfork_done, struct kthread, exited)
+#define __to_kthread(vfork)	\
+	container_of(vfork, struct kthread, exited)
+
+static inline struct kthread *to_kthread(struct task_struct *k)
+{
+	return __to_kthread(k->vfork_done);
+}
+
+static struct kthread *to_live_kthread(struct task_struct *k)
+{
+	struct completion *vfork = ACCESS_ONCE(k->vfork_done);
+	if (likely(vfork))
+		return __to_kthread(vfork);
+	return NULL;
+}
 
 /**
  * kthread_should_stop - should this kthread return now?
@@ -124,12 +137,12 @@ void *kthread_data(struct task_struct *task)
 
 static void __kthread_parkme(struct kthread *self)
 {
-	__set_current_state(TASK_INTERRUPTIBLE);
+	__set_current_state(TASK_PARKED);
 	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
 		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
 			complete(&self->parked);
 		schedule();
-		__set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_PARKED);
 	}
 	clear_bit(KTHREAD_IS_PARKED, &self->flags);
 	__set_current_state(TASK_RUNNING);
@@ -256,11 +269,16 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
-static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
 {
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, state)) {
+		WARN_ON(1);
+		return;
+	}
 	/* It's safe because the task is inactive. */
 	do_set_cpus_allowed(p, cpumask_of(cpu));
-	p->flags |= PF_THREAD_BOUND;
+	p->flags |= PF_NO_SETAFFINITY;
 }
 
 /**
@@ -274,12 +292,7 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu)
  */
 void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
-	/* Must have done schedule() in kthread() before we set_task_cpu */
-	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
-		WARN_ON(1);
-		return;
-	}
-	__kthread_bind(p, cpu);
+	__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(kthread_bind);
 
@@ -311,17 +324,20 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 	return p;
 }
 
-static struct kthread *task_get_live_kthread(struct task_struct *k)
+static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
 {
-	struct kthread *kthread;
-
-	get_task_struct(k);
-	kthread = to_kthread(k);
-	/* It might have exited */
-	barrier();
-	if (k->vfork_done != NULL)
-		return kthread;
-	return NULL;
+	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	/*
+	 * We clear the IS_PARKED bit here as we don't wait
+	 * until the task has left the park code. So if we'd
+	 * park before that happens we'd see the IS_PARKED bit
+	 * which might be about to be cleared.
+	 */
+	if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+		if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+			__kthread_bind(k, kthread->cpu, TASK_PARKED);
+		wake_up_state(k, TASK_PARKED);
+	}
 }
 
 /**
@@ -334,23 +350,10 @@ static struct kthread *task_get_live_kthread(struct task_struct *k)
  */
 void kthread_unpark(struct task_struct *k)
 {
-	struct kthread *kthread = task_get_live_kthread(k);
+	struct kthread *kthread = to_live_kthread(k);
 
-	if (kthread) {
-		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
-		/*
-		 * We clear the IS_PARKED bit here as we don't wait
-		 * until the task has left the park code. So if we'd
-		 * park before that happens we'd see the IS_PARKED bit
-		 * which might be about to be cleared.
-		 */
-		if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
-			if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
-				__kthread_bind(k, kthread->cpu);
-			wake_up_process(k);
-		}
-	}
-	put_task_struct(k);
+	if (kthread)
+		__kthread_unpark(k, kthread);
 }
 
 /**
@@ -367,7 +370,7 @@ void kthread_unpark(struct task_struct *k)
  */
 int kthread_park(struct task_struct *k)
 {
-	struct kthread *kthread = task_get_live_kthread(k);
+	struct kthread *kthread = to_live_kthread(k);
 	int ret = -ENOSYS;
 
 	if (kthread) {
@@ -380,7 +383,6 @@ int kthread_park(struct task_struct *k)
 		}
 		ret = 0;
 	}
-	put_task_struct(k);
 	return ret;
 }
 
@@ -401,21 +403,23 @@ int kthread_park(struct task_struct *k)
  */
 int kthread_stop(struct task_struct *k)
 {
-	struct kthread *kthread = task_get_live_kthread(k);
+	struct kthread *kthread;
 	int ret;
 
 	trace_sched_kthread_stop(k);
+
+	get_task_struct(k);
+	kthread = to_live_kthread(k);
 	if (kthread) {
 		set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
-		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+		__kthread_unpark(k, kthread);
 		wake_up_process(k);
 		wait_for_completion(&kthread->exited);
 	}
 	ret = k->exit_code;
-
 	put_task_struct(k);
-	trace_sched_kthread_stop_ret(ret);
 
+	trace_sched_kthread_stop_ret(ret);
 	return ret;
 }
 EXPORT_SYMBOL(kthread_stop);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 259db207b5d9..6a3bccba7e7d 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -380,6 +380,13 @@ static int verbose(struct lock_class *class)
 unsigned long nr_stack_trace_entries;
 static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
 
+static void print_lockdep_off(const char *bug_msg)
+{
+	printk(KERN_DEBUG "%s\n", bug_msg);
+	printk(KERN_DEBUG "turning off the locking correctness validator.\n");
+	printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n");
+}
+
 static int save_trace(struct stack_trace *trace)
 {
 	trace->nr_entries = 0;
@@ -409,8 +416,7 @@ static int save_trace(struct stack_trace *trace)
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
-		printk("BUG: MAX_STACK_TRACE_ENTRIES too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!");
 		dump_stack();
 
 		return 0;
@@ -763,8 +769,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		}
 		raw_local_irq_restore(flags);
 
-		printk("BUG: MAX_LOCKDEP_KEYS too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
 		dump_stack();
 		return NULL;
 	}
@@ -834,8 +839,7 @@ static struct lock_list *alloc_list_entry(void)
 		if (!debug_locks_off_graph_unlock())
 			return NULL;
 
-		printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_LOCKDEP_ENTRIES too low!");
 		dump_stack();
 		return NULL;
 	}
@@ -2000,7 +2004,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	struct lock_class *class = hlock_class(hlock);
 	struct list_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
-	struct held_lock *hlock_curr, *hlock_next;
+	struct held_lock *hlock_curr;
 	int i, j;
 
 	/*
@@ -2048,8 +2052,7 @@ cache_hit:
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
-		printk("BUG: MAX_LOCKDEP_CHAINS too low!\n");
-		printk("turning off the locking correctness validator.\n");
+		print_lockdep_off("BUG: MAX_LOCKDEP_CHAINS too low!");
 		dump_stack();
 		return 0;
 	}
@@ -2057,12 +2060,10 @@ cache_hit:
 	chain->chain_key = chain_key;
 	chain->irq_context = hlock->irq_context;
 	/* Find the first held_lock of current chain */
-	hlock_next = hlock;
 	for (i = curr->lockdep_depth - 1; i >= 0; i--) {
 		hlock_curr = curr->held_locks + i;
-		if (hlock_curr->irq_context != hlock_next->irq_context)
+		if (hlock_curr->irq_context != hlock->irq_context)
 			break;
-		hlock_next = hlock;
 	}
 	i++;
 	chain->depth = curr->lockdep_depth + 1 - i;
@@ -3190,9 +3191,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 #endif
 	if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) {
 		debug_locks_off();
-		printk("BUG: MAX_LOCK_DEPTH too low, depth: %i  max: %lu!\n",
+		print_lockdep_off("BUG: MAX_LOCK_DEPTH too low!");
+		printk(KERN_DEBUG "depth: %i  max: %lu!\n",
 		       curr->lockdep_depth, MAX_LOCK_DEPTH);
-		printk("turning off the locking correctness validator.\n");
 
 		lockdep_print_held_locks(current);
 		debug_show_all_locks();
@@ -4088,7 +4089,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
 
-static void print_held_locks_bug(void)
+static void print_held_locks_bug(struct task_struct *curr)
 {
 	if (!debug_locks_off())
 		return;
@@ -4097,21 +4098,22 @@ static void print_held_locks_bug(void)
 
 	printk("\n");
 	printk("=====================================\n");
-	printk("[ BUG: %s/%d still has locks held! ]\n",
-	       current->comm, task_pid_nr(current));
+	printk("[ BUG: lock held at task exit time! ]\n");
 	print_kernel_ident();
 	printk("-------------------------------------\n");
-	lockdep_print_held_locks(current);
+	printk("%s/%d is exiting with locks still held!\n",
+		curr->comm, task_pid_nr(curr));
+	lockdep_print_held_locks(curr);
+
 	printk("\nstack backtrace:\n");
 	dump_stack();
 }
 
-void debug_check_no_locks_held(void)
+void debug_check_no_locks_held(struct task_struct *task)
 {
-	if (unlikely(current->lockdep_depth > 0))
-		print_held_locks_bug();
+	if (unlikely(task->lockdep_depth > 0))
+		print_held_locks_bug(task);
 }
-EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
 void debug_show_all_locks(void)
 {
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 52f23011b6e0..ad53a664f113 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -37,6 +37,12 @@
 # include <asm/mutex.h>
 #endif
 
+/*
+ * A negative mutex count indicates that waiters are sleeping waiting for the
+ * mutex.
+ */
+#define	MUTEX_SHOW_NO_WAITER(mutex)	(atomic_read(&(mutex)->count) >= 0)
+
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
@@ -44,6 +50,9 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	spin_lock_init(&lock->wait_lock);
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	lock->spin_mlock = NULL;
+#endif
 
 	debug_mutex_init(lock, name, key);
 }
@@ -95,6 +104,124 @@ void __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+/*
+ * In order to avoid a stampede of mutex spinners from acquiring the mutex
+ * more or less simultaneously, the spinners need to acquire a MCS lock
+ * first before spinning on the owner field.
+ *
+ * We don't inline mspin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+struct mspin_node {
+	struct mspin_node *next ;
+	int		  locked;	/* 1 if lock acquired */
+};
+#define	MLOCK(mutex)	((struct mspin_node **)&((mutex)->spin_mlock))
+
+static noinline
+void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
+{
+	struct mspin_node *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/* Lock acquired */
+		node->locked = 1;
+		return;
+	}
+	ACCESS_ONCE(prev->next) = node;
+	smp_wmb();
+	/* Wait until the lock holder passes the lock down */
+	while (!ACCESS_ONCE(node->locked))
+		arch_mutex_cpu_relax();
+}
+
+static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
+{
+	struct mspin_node *next = ACCESS_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * Release the lock by setting it to NULL
+		 */
+		if (cmpxchg(lock, node, NULL) == node)
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = ACCESS_ONCE(node->next)))
+			arch_mutex_cpu_relax();
+	}
+	ACCESS_ONCE(next->locked) = 1;
+	smp_wmb();
+}
+
+/*
+ * Mutex spinning code migrated from kernel/sched/core.c
+ */
+
+static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
+{
+	if (lock->owner != owner)
+		return false;
+
+	/*
+	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
+	 * lock->owner still matches owner, if that fails, owner might
+	 * point to free()d memory, if it still matches, the rcu_read_lock()
+	 * ensures the memory stays valid.
+	 */
+	barrier();
+
+	return owner->on_cpu;
+}
+
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+static noinline
+int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+{
+	rcu_read_lock();
+	while (owner_running(lock, owner)) {
+		if (need_resched())
+			break;
+
+		arch_mutex_cpu_relax();
+	}
+	rcu_read_unlock();
+
+	/*
+	 * We break out the loop above on need_resched() and when the
+	 * owner changed, which is a sign for heavy contention. Return
+	 * success only when lock->owner is NULL.
+	 */
+	return lock->owner == NULL;
+}
+
+/*
+ * Initial check for entering the mutex spinning loop
+ */
+static inline int mutex_can_spin_on_owner(struct mutex *lock)
+{
+	int retval = 1;
+
+	rcu_read_lock();
+	if (lock->owner)
+		retval = lock->owner->on_cpu;
+	rcu_read_unlock();
+	/*
+	 * if lock->owner is not set, the mutex owner may have just acquired
+	 * it and not set the owner yet or the mutex has been released.
+	 */
+	return retval;
+}
+#endif
+
 static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /**
@@ -158,25 +285,39 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 *
 	 * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
 	 * to serialize everything.
+	 *
+	 * The mutex spinners are queued up using MCS lock so that only one
+	 * spinner can compete for the mutex. However, if mutex spinning isn't
+	 * going to happen, there is no point in going through the lock/unlock
+	 * overhead.
 	 */
+	if (!mutex_can_spin_on_owner(lock))
+		goto slowpath;
 
 	for (;;) {
 		struct task_struct *owner;
+		struct mspin_node  node;
 
 		/*
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
+		mspin_lock(MLOCK(lock), &node);
 		owner = ACCESS_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner))
+		if (owner && !mutex_spin_on_owner(lock, owner)) {
+			mspin_unlock(MLOCK(lock), &node);
 			break;
+		}
 
-		if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
+		if ((atomic_read(&lock->count) == 1) &&
+		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
 			mutex_set_owner(lock);
+			mspin_unlock(MLOCK(lock), &node);
 			preempt_enable();
 			return 0;
 		}
+		mspin_unlock(MLOCK(lock), &node);
 
 		/*
 		 * When there's no owner, we might have preempted between the
@@ -195,6 +336,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 */
 		arch_mutex_cpu_relax();
 	}
+slowpath:
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
@@ -205,7 +347,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
-	if (atomic_xchg(&lock->count, -1) == 1)
+	if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, -1) == 1))
 		goto done;
 
 	lock_contended(&lock->dep_map, ip);
@@ -220,7 +362,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * that when we release the lock, we properly wake up the
 		 * other waiters:
 		 */
-		if (atomic_xchg(&lock->count, -1) == 1)
+		if (MUTEX_SHOW_NO_WAITER(lock) &&
+		   (atomic_xchg(&lock->count, -1) == 1))
 			break;
 
 		/*
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index c1c3dc1c6023..bea15bdf82b0 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -181,6 +181,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	int nr;
 	int rc;
 	struct task_struct *task, *me = current;
+	int init_pids = thread_group_leader(me) ? 1 : 2;
 
 	/* Don't allow any more processes into the pid namespace */
 	disable_pid_allocation(pid_ns);
@@ -230,7 +231,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 */
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (pid_ns->nr_hashed == 1)
+		if (pid_ns->nr_hashed == init_pids)
 			break;
 		schedule();
 	}
diff --git a/kernel/printk.c b/kernel/printk.c
index 0b31715f335a..376914e2869d 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -49,13 +49,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/printk.h>
 
-/*
- * Architectures can override it:
- */
-void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
-{
-}
-
 /* printk's without a loglevel use this.. */
 #define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL
 
@@ -63,8 +56,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
 #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
 #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
 
-DECLARE_WAIT_QUEUE_HEAD(log_wait);
-
 int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* console_loglevel */
 	DEFAULT_MESSAGE_LOGLEVEL,	/* default_message_loglevel */
@@ -224,6 +215,7 @@ struct log {
 static DEFINE_RAW_SPINLOCK(logbuf_lock);
 
 #ifdef CONFIG_PRINTK
+DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
 static u32 syslog_idx;
@@ -609,7 +601,8 @@ static unsigned int devkmsg_poll(struct file *file, poll_table *wait)
 		/* return error when data has vanished underneath us */
 		if (user->seq < log_first_seq)
 			ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI;
-		ret = POLLIN|POLLRDNORM;
+		else
+			ret = POLLIN|POLLRDNORM;
 	}
 	raw_spin_unlock_irq(&logbuf_lock);
 
@@ -1266,7 +1259,7 @@ static void call_console_drivers(int level, const char *text, size_t len)
 {
 	struct console *con;
 
-	trace_console(text, 0, len, len);
+	trace_console(text, len);
 
 	if (level >= console_loglevel && !ignore_loglevel)
 		return;
@@ -1724,6 +1717,29 @@ static size_t cont_print_text(char *text, size_t size) { return 0; }
 
 #endif /* CONFIG_PRINTK */
 
+#ifdef CONFIG_EARLY_PRINTK
+struct console *early_console;
+
+void early_vprintk(const char *fmt, va_list ap)
+{
+	if (early_console) {
+		char buf[512];
+		int n = vscnprintf(buf, sizeof(buf), fmt, ap);
+
+		early_console->write(early_console, buf, n);
+	}
+}
+
+asmlinkage void early_printk(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	early_vprintk(fmt, ap);
+	va_end(ap);
+}
+#endif
+
 static int __add_preferred_console(char *name, int idx, char *options,
 				   char *brl_options)
 {
@@ -1957,45 +1973,6 @@ int is_console_locked(void)
 	return console_locked;
 }
 
-/*
- * Delayed printk version, for scheduler-internal messages:
- */
-#define PRINTK_BUF_SIZE		512
-
-#define PRINTK_PENDING_WAKEUP	0x01
-#define PRINTK_PENDING_SCHED	0x02
-
-static DEFINE_PER_CPU(int, printk_pending);
-static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
-
-static void wake_up_klogd_work_func(struct irq_work *irq_work)
-{
-	int pending = __this_cpu_xchg(printk_pending, 0);
-
-	if (pending & PRINTK_PENDING_SCHED) {
-		char *buf = __get_cpu_var(printk_sched_buf);
-		printk(KERN_WARNING "[sched_delayed] %s", buf);
-	}
-
-	if (pending & PRINTK_PENDING_WAKEUP)
-		wake_up_interruptible(&log_wait);
-}
-
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-	.func = wake_up_klogd_work_func,
-	.flags = IRQ_WORK_LAZY,
-};
-
-void wake_up_klogd(void)
-{
-	preempt_disable();
-	if (waitqueue_active(&log_wait)) {
-		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
-	}
-	preempt_enable();
-}
-
 static void console_cont_flush(char *text, size_t size)
 {
 	unsigned long flags;
@@ -2458,6 +2435,44 @@ static int __init printk_late_init(void)
 late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
+/*
+ * Delayed printk version, for scheduler-internal messages:
+ */
+#define PRINTK_BUF_SIZE		512
+
+#define PRINTK_PENDING_WAKEUP	0x01
+#define PRINTK_PENDING_SCHED	0x02
+
+static DEFINE_PER_CPU(int, printk_pending);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
+
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
+{
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_SCHED) {
+		char *buf = __get_cpu_var(printk_sched_buf);
+		printk(KERN_WARNING "[sched_delayed] %s", buf);
+	}
+
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
+}
+
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
+
+void wake_up_klogd(void)
+{
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
+		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	}
+	preempt_enable();
+}
 
 int printk_sched(const char *fmt, ...)
 {
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1d4ceff793a4..16ea67925015 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -64,7 +64,7 @@
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 
-#define RCU_STATE_INITIALIZER(sname, cr) { \
+#define RCU_STATE_INITIALIZER(sname, sabbr, cr) { \
 	.level = { &sname##_state.node[0] }, \
 	.call = cr, \
 	.fqs_state = RCU_GP_IDLE, \
@@ -76,13 +76,14 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
 	.name = #sname, \
+	.abbr = sabbr, \
 }
 
 struct rcu_state rcu_sched_state =
-	RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched);
+	RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 
-struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh);
+struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 static struct rcu_state *rcu_state;
@@ -223,6 +224,8 @@ static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
 
+static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
+				  struct rcu_data *rdp);
 static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *));
 static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(int cpu);
@@ -310,6 +313,8 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	if (rcu_gp_in_progress(rsp))
 		return 0;  /* No, a grace period is already in progress. */
+	if (rcu_nocb_needs_gp(rsp))
+		return 1;  /* Yes, a no-CBs CPU needs one. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL])
 		return 0;  /* No, this is a no-CBs (or offline) CPU. */
 	if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
@@ -1045,10 +1050,11 @@ static void init_callback_list(struct rcu_data *rdp)
 {
 	int i;
 
+	if (init_nocb_callback_list(rdp))
+		return;
 	rdp->nxtlist = NULL;
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
-	init_nocb_callback_list(rdp);
 }
 
 /*
@@ -1081,6 +1087,120 @@ static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
 }
 
 /*
+ * Trace-event helper function for rcu_start_future_gp() and
+ * rcu_nocb_wait_gp().
+ */
+static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+				unsigned long c, char *s)
+{
+	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
+				      rnp->completed, c, rnp->level,
+				      rnp->grplo, rnp->grphi, s);
+}
+
+/*
+ * Start some future grace period, as needed to handle newly arrived
+ * callbacks.  The required future grace periods are recorded in each
+ * rcu_node structure's ->need_future_gp field.
+ *
+ * The caller must hold the specified rcu_node structure's ->lock.
+ */
+static unsigned long __maybe_unused
+rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	unsigned long c;
+	int i;
+	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+
+	/*
+	 * Pick up grace-period number for new callbacks.  If this
+	 * grace period is already marked as needed, return to the caller.
+	 */
+	c = rcu_cbs_completed(rdp->rsp, rnp);
+	trace_rcu_future_gp(rnp, rdp, c, "Startleaf");
+	if (rnp->need_future_gp[c & 0x1]) {
+		trace_rcu_future_gp(rnp, rdp, c, "Prestartleaf");
+		return c;
+	}
+
+	/*
+	 * If either this rcu_node structure or the root rcu_node structure
+	 * believe that a grace period is in progress, then we must wait
+	 * for the one following, which is in "c".  Because our request
+	 * will be noticed at the end of the current grace period, we don't
+	 * need to explicitly start one.
+	 */
+	if (rnp->gpnum != rnp->completed ||
+	    ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) {
+		rnp->need_future_gp[c & 0x1]++;
+		trace_rcu_future_gp(rnp, rdp, c, "Startedleaf");
+		return c;
+	}
+
+	/*
+	 * There might be no grace period in progress.  If we don't already
+	 * hold it, acquire the root rcu_node structure's lock in order to
+	 * start one (if needed).
+	 */
+	if (rnp != rnp_root)
+		raw_spin_lock(&rnp_root->lock);
+
+	/*
+	 * Get a new grace-period number.  If there really is no grace
+	 * period in progress, it will be smaller than the one we obtained
+	 * earlier.  Adjust callbacks as needed.  Note that even no-CBs
+	 * CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed.
+	 */
+	c = rcu_cbs_completed(rdp->rsp, rnp_root);
+	for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++)
+		if (ULONG_CMP_LT(c, rdp->nxtcompleted[i]))
+			rdp->nxtcompleted[i] = c;
+
+	/*
+	 * If the needed for the required grace period is already
+	 * recorded, trace and leave.
+	 */
+	if (rnp_root->need_future_gp[c & 0x1]) {
+		trace_rcu_future_gp(rnp, rdp, c, "Prestartedroot");
+		goto unlock_out;
+	}
+
+	/* Record the need for the future grace period. */
+	rnp_root->need_future_gp[c & 0x1]++;
+
+	/* If a grace period is not already in progress, start one. */
+	if (rnp_root->gpnum != rnp_root->completed) {
+		trace_rcu_future_gp(rnp, rdp, c, "Startedleafroot");
+	} else {
+		trace_rcu_future_gp(rnp, rdp, c, "Startedroot");
+		rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
+	}
+unlock_out:
+	if (rnp != rnp_root)
+		raw_spin_unlock(&rnp_root->lock);
+	return c;
+}
+
+/*
+ * Clean up any old requests for the just-ended grace period.  Also return
+ * whether any additional grace periods have been requested.  Also invoke
+ * rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads
+ * waiting for this grace period to complete.
+ */
+static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+	int c = rnp->completed;
+	int needmore;
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+
+	rcu_nocb_gp_cleanup(rsp, rnp);
+	rnp->need_future_gp[c & 0x1] = 0;
+	needmore = rnp->need_future_gp[(c + 1) & 0x1];
+	trace_rcu_future_gp(rnp, rdp, c, needmore ? "CleanupMore" : "Cleanup");
+	return needmore;
+}
+
+/*
  * If there is room, assign a ->completed number to any callbacks on
  * this CPU that have not already been assigned.  Also accelerate any
  * callbacks that were previously assigned a ->completed number that has
@@ -1139,6 +1259,8 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
 		rdp->nxtcompleted[i] = c;
 	}
+	/* Record any needed additional grace periods. */
+	rcu_start_future_gp(rnp, rdp);
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (!*rdp->nxttail[RCU_WAIT_TAIL])
@@ -1318,9 +1440,9 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		rnp->gpnum = rsp->gpnum;
+		ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
 		WARN_ON_ONCE(rnp->completed != rsp->completed);
-		rnp->completed = rsp->completed;
+		ACCESS_ONCE(rnp->completed) = rsp->completed;
 		if (rnp == rdp->mynode)
 			rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
@@ -1329,7 +1451,8 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 #ifdef CONFIG_PROVE_RCU_DELAY
-		if ((random32() % (rcu_num_nodes * 8)) == 0)
+		if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 &&
+		    system_state == SYSTEM_RUNNING)
 			schedule_timeout_uninterruptible(2);
 #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
@@ -1371,6 +1494,7 @@ int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
+	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1400,17 +1524,23 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
-		rnp->completed = rsp->gpnum;
+		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
+		rdp = this_cpu_ptr(rsp->rda);
+		if (rnp == rdp->mynode)
+			__rcu_process_gp_end(rsp, rnp, rdp);
+		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
 	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
+	rcu_advance_cbs(rsp, rnp, rdp);  /* Reduce false positives below. */
 	if (cpu_needs_another_gp(rsp, rdp))
 		rsp->gp_flags = 1;
 	raw_spin_unlock_irq(&rnp->lock);
@@ -1486,57 +1616,62 @@ static int __noreturn rcu_gp_kthread(void *arg)
 /*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
- * the root node's ->lock, which is released before return.  Hard irqs must
- * be disabled.
+ * the root node's ->lock and hard irqs must be disabled.
  *
  * Note that it is legal for a dying CPU (which is marked as offline) to
  * invoke this function.  This can happen when the dying CPU reports its
  * quiescent state.
  */
 static void
-rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
-	__releases(rcu_get_root(rsp)->lock)
+rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
+		      struct rcu_data *rdp)
 {
-	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-	struct rcu_node *rnp = rcu_get_root(rsp);
-
-	if (!rsp->gp_kthread ||
-	    !cpu_needs_another_gp(rsp, rdp)) {
+	if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
 		/*
 		 * Either we have not yet spawned the grace-period
 		 * task, this CPU does not need another grace period,
 		 * or a grace period is already in progress.
 		 * Either way, don't start a new grace period.
 		 */
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-
-	/*
-	 * Because there is no grace period in progress right now,
-	 * any callbacks we have up to this point will be satisfied
-	 * by the next grace period.  So this is a good place to
-	 * assign a grace period number to recently posted callbacks.
-	 */
-	rcu_accelerate_cbs(rsp, rnp, rdp);
-
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
-	raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
-
-	/* Ensure that CPU is aware of completion of last grace period. */
-	rcu_process_gp_end(rsp, rdp);
-	local_irq_restore(flags);
 
 	/* Wake up rcu_gp_kthread() to start the grace period. */
 	wake_up(&rsp->gp_wq);
 }
 
 /*
+ * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
+ * callbacks.  Note that rcu_start_gp_advanced() cannot do this because it
+ * is invoked indirectly from rcu_advance_cbs(), which would result in
+ * endless recursion -- or would do so if it wasn't for the self-deadlock
+ * that is encountered beforehand.
+ */
+static void
+rcu_start_gp(struct rcu_state *rsp)
+{
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	/*
+	 * If there is no grace period in progress right now, any
+	 * callbacks we have up to this point will be satisfied by the
+	 * next grace period.  Also, advancing the callbacks reduces the
+	 * probability of false positives from cpu_needs_another_gp()
+	 * resulting in pointless grace periods.  So, advance callbacks
+	 * then start the grace period!
+	 */
+	rcu_advance_cbs(rsp, rnp, rdp);
+	rcu_start_gp_advanced(rsp, rnp, rdp);
+}
+
+/*
  * Report a full set of quiescent states to the specified rcu_state
  * data structure.  This involves cleaning up after the prior grace
  * period and letting 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.
+ * if one is needed.  Note that the caller must hold rnp->lock, which
+ * is released before return.
  */
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
@@ -2134,7 +2269,8 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	local_irq_save(flags);
 	if (cpu_needs_another_gp(rsp, rdp)) {
 		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
-		rcu_start_gp(rsp, flags);  /* releases above lock */
+		rcu_start_gp(rsp);
+		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -2179,7 +2315,8 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 
 static void invoke_rcu_core(void)
 {
-	raise_softirq(RCU_SOFTIRQ);
+	if (cpu_online(smp_processor_id()))
+		raise_softirq(RCU_SOFTIRQ);
 }
 
 /*
@@ -2214,11 +2351,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
-			unsigned long nestflag;
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
-			raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
-			rcu_start_gp(rsp, nestflag);  /* rlses rnp_root->lock */
+			raw_spin_lock(&rnp_root->lock);
+			rcu_start_gp(rsp);
+			raw_spin_unlock(&rnp_root->lock);
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = LONG_MAX;
@@ -2638,19 +2775,27 @@ static int rcu_pending(int 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.
+ * Return true if the specified CPU has any callback.  If all_lazy is
+ * non-NULL, store an indication of whether all callbacks are lazy.
+ * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int rcu_cpu_has_callbacks(int cpu)
+static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 {
+	bool al = true;
+	bool hc = false;
+	struct rcu_data *rdp;
 	struct rcu_state *rsp;
 
-	/* RCU callbacks either ready or pending? */
-	for_each_rcu_flavor(rsp)
-		if (per_cpu_ptr(rsp->rda, cpu)->nxtlist)
-			return 1;
-	return 0;
+	for_each_rcu_flavor(rsp) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		if (rdp->qlen != rdp->qlen_lazy)
+			al = false;
+		if (rdp->nxtlist)
+			hc = true;
+	}
+	if (all_lazy)
+		*all_lazy = al;
+	return hc;
 }
 
 /*
@@ -2869,7 +3014,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
-	rcu_prepare_for_idle_init(cpu);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/* Add CPU to rcu_node bitmasks. */
@@ -2919,7 +3063,6 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 	struct rcu_state *rsp;
-	int ret = NOTIFY_OK;
 
 	trace_rcu_utilization("Start CPU hotplug");
 	switch (action) {
@@ -2933,21 +3076,12 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		rcu_boost_kthread_setaffinity(rnp, -1);
 		break;
 	case CPU_DOWN_PREPARE:
-		if (nocb_cpu_expendable(cpu))
-			rcu_boost_kthread_setaffinity(rnp, cpu);
-		else
-			ret = NOTIFY_BAD;
+		rcu_boost_kthread_setaffinity(rnp, cpu);
 		break;
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:
-		/*
-		 * The whole machine is "stopped" except this CPU, so we can
-		 * touch any data without introducing corruption. We send the
-		 * dying CPU's callbacks to an arbitrarily chosen online CPU.
-		 */
 		for_each_rcu_flavor(rsp)
 			rcu_cleanup_dying_cpu(rsp);
-		rcu_cleanup_after_idle(cpu);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
@@ -2960,7 +3094,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		break;
 	}
 	trace_rcu_utilization("End CPU hotplug");
-	return ret;
+	return NOTIFY_OK;
 }
 
 /*
@@ -3095,6 +3229,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 			}
 			rnp->level = i;
 			INIT_LIST_HEAD(&rnp->blkd_tasks);
+			rcu_init_one_nocb(rnp);
 		}
 	}
 
@@ -3180,8 +3315,7 @@ void __init rcu_init(void)
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
-	rcu_init_nocb();
-	 open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 38acc49da2c6..da77a8f57ff9 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -88,18 +88,13 @@ struct rcu_dynticks {
 	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
 	atomic_t dynticks;	    /* Even value for idle, else odd. */
 #ifdef CONFIG_RCU_FAST_NO_HZ
-	int dyntick_drain;	    /* Prepare-for-idle state variable. */
-	unsigned long dyntick_holdoff;
-				    /* No retries for the jiffy of failure. */
-	struct timer_list idle_gp_timer;
-				    /* Wake up CPU sleeping with callbacks. */
-	unsigned long idle_gp_timer_expires;
-				    /* When to wake up CPU (for repost). */
-	bool idle_first_pass;	    /* First pass of attempt to go idle? */
+	bool all_lazy;		    /* Are all CPU's CBs lazy? */
 	unsigned long nonlazy_posted;
 				    /* # times non-lazy CBs posted to CPU. */
 	unsigned long nonlazy_posted_snap;
 				    /* idle-period nonlazy_posted snapshot. */
+	unsigned long last_accelerate;
+				    /* Last jiffy CBs were accelerated. */
 	int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 };
@@ -134,9 +129,6 @@ struct rcu_node {
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
-	atomic_t wakemask;	/* CPUs whose kthread needs to be awakened. */
-				/*  Since this has meaning only for leaf */
-				/*  rcu_node structures, 32 bits suffices. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -196,6 +188,12 @@ struct rcu_node {
 				/* Refused to boost: not sure why, though. */
 				/*  This can happen due to race conditions. */
 #endif /* #ifdef CONFIG_RCU_BOOST */
+#ifdef CONFIG_RCU_NOCB_CPU
+	wait_queue_head_t nocb_gp_wq[2];
+				/* Place for rcu_nocb_kthread() to wait GP. */
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
+	int need_future_gp[2];
+				/* Counts of upcoming no-CB GP requests. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 } ____cacheline_internodealigned_in_smp;
 
@@ -328,6 +326,11 @@ struct rcu_data {
 	struct task_struct *nocb_kthread;
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
+	/* 8) RCU CPU stall data. */
+#ifdef CONFIG_RCU_CPU_STALL_INFO
+	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
+
 	int cpu;
 	struct rcu_state *rsp;
 };
@@ -375,12 +378,6 @@ struct rcu_state {
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
-#ifdef CONFIG_RCU_NOCB_CPU
-	void (*call_remote)(struct rcu_head *head,
-		     void (*func)(struct rcu_head *head));
-						/* call_rcu() flavor, but for */
-						/*  placing on remote CPU. */
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
@@ -443,6 +440,7 @@ struct rcu_state {
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	char *name;				/* Name of structure. */
+	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
 };
 
@@ -520,7 +518,6 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
 static void __cpuinit rcu_prepare_kthreads(int cpu);
-static void rcu_prepare_for_idle_init(int cpu);
 static void rcu_cleanup_after_idle(int cpu);
 static void rcu_prepare_for_idle(int cpu);
 static void rcu_idle_count_callbacks_posted(void);
@@ -529,16 +526,18 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
+static int rcu_nocb_needs_gp(struct rcu_state *rsp);
+static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
+static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
+static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy);
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 				      struct rcu_data *rdp);
-static bool nocb_cpu_expendable(int cpu);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
-static void init_nocb_callback_list(struct rcu_data *rdp);
-static void __init rcu_init_nocb(void);
 static void rcu_kick_nohz_cpu(int cpu);
+static bool init_nocb_callback_list(struct rcu_data *rdp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 0cd91cc18db4..71bd7337d0cc 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -86,11 +86,21 @@ static void __init rcu_bootup_announce_oddness(void)
 	if (nr_cpu_ids != NR_CPUS)
 		printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
 #ifdef CONFIG_RCU_NOCB_CPU
+#ifndef CONFIG_RCU_NOCB_CPU_NONE
+	if (!have_rcu_nocb_mask) {
+		alloc_bootmem_cpumask_var(&rcu_nocb_mask);
+		have_rcu_nocb_mask = true;
+	}
+#ifdef CONFIG_RCU_NOCB_CPU_ZERO
+	pr_info("\tExperimental no-CBs CPU 0\n");
+	cpumask_set_cpu(0, rcu_nocb_mask);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
+#ifdef CONFIG_RCU_NOCB_CPU_ALL
+	pr_info("\tExperimental no-CBs for all CPUs\n");
+	cpumask_setall(rcu_nocb_mask);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
 	if (have_rcu_nocb_mask) {
-		if (cpumask_test_cpu(0, rcu_nocb_mask)) {
-			cpumask_clear_cpu(0, rcu_nocb_mask);
-			pr_info("\tCPU 0: illegal no-CBs CPU (cleared).\n");
-		}
 		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
 		pr_info("\tExperimental no-CBs CPUs: %s.\n", nocb_buf);
 		if (rcu_nocb_poll)
@@ -102,7 +112,7 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 struct rcu_state rcu_preempt_state =
-	RCU_STATE_INITIALIZER(rcu_preempt, call_rcu);
+	RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
 DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static struct rcu_state *rcu_state = &rcu_preempt_state;
 
@@ -1534,14 +1544,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
 int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
-	return rcu_cpu_has_callbacks(cpu);
-}
-
-/*
- * Because we do not have RCU_FAST_NO_HZ, don't bother initializing for it.
- */
-static void rcu_prepare_for_idle_init(int cpu)
-{
+	return rcu_cpu_has_callbacks(cpu, NULL);
 }
 
 /*
@@ -1578,16 +1581,6 @@ static void rcu_idle_count_callbacks_posted(void)
  *
  * The following three proprocessor symbols control this state machine:
  *
- * RCU_IDLE_FLUSHES gives the maximum number of times that we will attempt
- *	to satisfy RCU.  Beyond this point, it is better to incur a periodic
- *	scheduling-clock interrupt than to loop through the state machine
- *	at full power.
- * RCU_IDLE_OPT_FLUSHES gives the number of RCU_IDLE_FLUSHES that are
- *	optional if RCU does not need anything immediately from this
- *	CPU, even if this CPU still has RCU callbacks queued.  The first
- *	times through the state machine are mandatory: we need to give
- *	the state machine a chance to communicate a quiescent state
- *	to the RCU core.
  * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
  *	to sleep in dyntick-idle mode with RCU callbacks pending.  This
  *	is sized to be roughly one RCU grace period.  Those energy-efficiency
@@ -1603,186 +1596,108 @@ static void rcu_idle_count_callbacks_posted(void)
  * adjustment, they can be converted into kernel config parameters, though
  * making the state machine smarter might be a better option.
  */
-#define RCU_IDLE_FLUSHES 5		/* Number of dyntick-idle tries. */
-#define RCU_IDLE_OPT_FLUSHES 3		/* Optional dyntick-idle tries. */
 #define RCU_IDLE_GP_DELAY 4		/* Roughly one grace period. */
 #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)	/* Roughly six seconds. */
 
-extern int tick_nohz_enabled;
-
-/*
- * Does the specified flavor of RCU have non-lazy callbacks pending on
- * the specified CPU?  Both RCU flavor and CPU are specified by the
- * rcu_data structure.
- */
-static bool __rcu_cpu_has_nonlazy_callbacks(struct rcu_data *rdp)
-{
-	return rdp->qlen != rdp->qlen_lazy;
-}
+static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY;
+module_param(rcu_idle_gp_delay, int, 0644);
+static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
+module_param(rcu_idle_lazy_gp_delay, int, 0644);
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+extern int tick_nohz_enabled;
 
 /*
- * Are there non-lazy RCU-preempt callbacks?  (There cannot be if there
- * is no RCU-preempt in the kernel.)
+ * Try to advance callbacks for all flavors of RCU on the current CPU.
+ * Afterwards, if there are any callbacks ready for immediate invocation,
+ * return true.
  */
-static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu)
+static bool rcu_try_advance_all_cbs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
-
-	return __rcu_cpu_has_nonlazy_callbacks(rdp);
-}
-
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	bool cbs_ready = false;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp;
 
-static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu)
-{
-	return 0;
-}
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		rnp = rdp->mynode;
 
-#endif /* else #ifdef CONFIG_TREE_PREEMPT_RCU */
+		/*
+		 * Don't bother checking unless a grace period has
+		 * completed since we last checked and there are
+		 * callbacks not yet ready to invoke.
+		 */
+		if (rdp->completed != rnp->completed &&
+		    rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
+			rcu_process_gp_end(rsp, rdp);
 
-/*
- * Does any flavor of RCU have non-lazy callbacks on the specified CPU?
- */
-static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
-{
-	return __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_sched_data, cpu)) ||
-	       __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_bh_data, cpu)) ||
-	       rcu_preempt_cpu_has_nonlazy_callbacks(cpu);
+		if (cpu_has_callbacks_ready_to_invoke(rdp))
+			cbs_ready = true;
+	}
+	return cbs_ready;
 }
 
 /*
- * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
- * callbacks on this CPU, (2) this CPU has not yet attempted to enter
- * dyntick-idle mode, or (3) this CPU is in the process of attempting to
- * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
- * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
- * it is better to incur scheduling-clock interrupts than to spin
- * continuously for the same time duration!
+ * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
+ * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
+ * caller to set the timeout based on whether or not there are non-lazy
+ * callbacks.
  *
- * The delta_jiffies argument is used to store the time when RCU is
- * going to need the CPU again if it still has callbacks.  The reason
- * for this is that rcu_prepare_for_idle() might need to post a timer,
- * but if so, it will do so after tick_nohz_stop_sched_tick() has set
- * the wakeup time for this CPU.  This means that RCU's timer can be
- * delayed until the wakeup time, which defeats the purpose of posting
- * a timer.
+ * The caller must have disabled interrupts.
  */
-int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+int rcu_needs_cpu(int cpu, unsigned long *dj)
 {
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
-	/* Flag a new idle sojourn to the idle-entry state machine. */
-	rdtp->idle_first_pass = 1;
+	/* Snapshot to detect later posting of non-lazy callback. */
+	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
+
 	/* If no callbacks, RCU doesn't need the CPU. */
-	if (!rcu_cpu_has_callbacks(cpu)) {
-		*delta_jiffies = ULONG_MAX;
+	if (!rcu_cpu_has_callbacks(cpu, &rdtp->all_lazy)) {
+		*dj = ULONG_MAX;
 		return 0;
 	}
-	if (rdtp->dyntick_holdoff == jiffies) {
-		/* RCU recently tried and failed, so don't try again. */
-		*delta_jiffies = 1;
+
+	/* Attempt to advance callbacks. */
+	if (rcu_try_advance_all_cbs()) {
+		/* Some ready to invoke, so initiate later invocation. */
+		invoke_rcu_core();
 		return 1;
 	}
-	/* Set up for the possibility that RCU will post a timer. */
-	if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
-		*delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies,
-					  RCU_IDLE_GP_DELAY) - jiffies;
+	rdtp->last_accelerate = jiffies;
+
+	/* Request timer delay depending on laziness, and round. */
+	if (rdtp->all_lazy) {
+		*dj = round_up(rcu_idle_gp_delay + jiffies,
+			       rcu_idle_gp_delay) - jiffies;
 	} else {
-		*delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY;
-		*delta_jiffies = round_jiffies(*delta_jiffies) - jiffies;
+		*dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
 	}
 	return 0;
 }
 
 /*
- * Handler for smp_call_function_single().  The only point of this
- * handler is to wake the CPU up, so the handler does only tracing.
- */
-void rcu_idle_demigrate(void *unused)
-{
-	trace_rcu_prep_idle("Demigrate");
-}
-
-/*
- * Timer handler used to force CPU to start pushing its remaining RCU
- * callbacks in the case where it entered dyntick-idle mode with callbacks
- * pending.  The hander doesn't really need to do anything because the
- * real work is done upon re-entry to idle, or by the next scheduling-clock
- * interrupt should idle not be re-entered.
- *
- * One special case: the timer gets migrated without awakening the CPU
- * on which the timer was scheduled on.  In this case, we must wake up
- * that CPU.  We do so with smp_call_function_single().
- */
-static void rcu_idle_gp_timer_func(unsigned long cpu_in)
-{
-	int cpu = (int)cpu_in;
-
-	trace_rcu_prep_idle("Timer");
-	if (cpu != smp_processor_id())
-		smp_call_function_single(cpu, rcu_idle_demigrate, NULL, 0);
-	else
-		WARN_ON_ONCE(1); /* Getting here can hang the system... */
-}
-
-/*
- * Initialize the timer used to pull CPUs out of dyntick-idle mode.
- */
-static void rcu_prepare_for_idle_init(int cpu)
-{
-	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
-
-	rdtp->dyntick_holdoff = jiffies - 1;
-	setup_timer(&rdtp->idle_gp_timer, rcu_idle_gp_timer_func, cpu);
-	rdtp->idle_gp_timer_expires = jiffies - 1;
-	rdtp->idle_first_pass = 1;
-}
-
-/*
- * Clean up for exit from idle.  Because we are exiting from idle, there
- * is no longer any point to ->idle_gp_timer, so cancel it.  This will
- * do nothing if this timer is not active, so just cancel it unconditionally.
- */
-static void rcu_cleanup_after_idle(int cpu)
-{
-	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
-
-	del_timer(&rdtp->idle_gp_timer);
-	trace_rcu_prep_idle("Cleanup after idle");
-	rdtp->tick_nohz_enabled_snap = ACCESS_ONCE(tick_nohz_enabled);
-}
-
-/*
- * Check to see if any RCU-related work can be done by the current CPU,
- * and if so, schedule a softirq to get it done.  This function is part
- * of the RCU implementation; it is -not- an exported member of the RCU API.
- *
- * The idea is for the current CPU to clear out all work required by the
- * RCU core for the current grace period, so that this CPU can be permitted
- * to enter dyntick-idle mode.  In some cases, it will need to be awakened
- * at the end of the grace period by whatever CPU ends the grace period.
- * This allows CPUs to go dyntick-idle more quickly, and to reduce the
- * number of wakeups by a modest integer factor.
- *
- * Because it is not legal to invoke rcu_process_callbacks() with irqs
- * disabled, we do one pass of force_quiescent_state(), then do a
- * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
- * later.  The ->dyntick_drain field controls the sequencing.
+ * Prepare a CPU for idle from an RCU perspective.  The first major task
+ * is to sense whether nohz mode has been enabled or disabled via sysfs.
+ * The second major task is to check to see if a non-lazy callback has
+ * arrived at a CPU that previously had only lazy callbacks.  The third
+ * major task is to accelerate (that is, assign grace-period numbers to)
+ * any recently arrived callbacks.
  *
  * The caller must have disabled interrupts.
  */
 static void rcu_prepare_for_idle(int cpu)
 {
-	struct timer_list *tp;
+	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+	struct rcu_node *rnp;
+	struct rcu_state *rsp;
 	int tne;
 
 	/* Handle nohz enablement switches conservatively. */
 	tne = ACCESS_ONCE(tick_nohz_enabled);
 	if (tne != rdtp->tick_nohz_enabled_snap) {
-		if (rcu_cpu_has_callbacks(cpu))
+		if (rcu_cpu_has_callbacks(cpu, NULL))
 			invoke_rcu_core(); /* force nohz to see update. */
 		rdtp->tick_nohz_enabled_snap = tne;
 		return;
@@ -1790,125 +1705,56 @@ static void rcu_prepare_for_idle(int cpu)
 	if (!tne)
 		return;
 
-	/* Adaptive-tick mode, where usermode execution is idle to RCU. */
-	if (!is_idle_task(current)) {
-		rdtp->dyntick_holdoff = jiffies - 1;
-		if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
-			trace_rcu_prep_idle("User dyntick with callbacks");
-			rdtp->idle_gp_timer_expires =
-				round_up(jiffies + RCU_IDLE_GP_DELAY,
-					 RCU_IDLE_GP_DELAY);
-		} else if (rcu_cpu_has_callbacks(cpu)) {
-			rdtp->idle_gp_timer_expires =
-				round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY);
-			trace_rcu_prep_idle("User dyntick with lazy callbacks");
-		} else {
-			return;
-		}
-		tp = &rdtp->idle_gp_timer;
-		mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
+	/* If this is a no-CBs CPU, no callbacks, just return. */
+	if (is_nocb_cpu(cpu))
 		return;
-	}
 
 	/*
-	 * If this is an idle re-entry, for example, due to use of
-	 * RCU_NONIDLE() or the new idle-loop tracing API within the idle
-	 * loop, then don't take any state-machine actions, unless the
-	 * momentary exit from idle queued additional non-lazy callbacks.
-	 * Instead, repost the ->idle_gp_timer if this CPU has callbacks
-	 * pending.
+	 * If a non-lazy callback arrived at a CPU having only lazy
+	 * callbacks, invoke RCU core for the side-effect of recalculating
+	 * idle duration on re-entry to idle.
 	 */
-	if (!rdtp->idle_first_pass &&
-	    (rdtp->nonlazy_posted == rdtp->nonlazy_posted_snap)) {
-		if (rcu_cpu_has_callbacks(cpu)) {
-			tp = &rdtp->idle_gp_timer;
-			mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
-		}
+	if (rdtp->all_lazy &&
+	    rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) {
+		invoke_rcu_core();
 		return;
 	}
-	rdtp->idle_first_pass = 0;
-	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted - 1;
 
 	/*
-	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
-	 * Also reset state to avoid prejudicing later attempts.
+	 * If we have not yet accelerated this jiffy, accelerate all
+	 * callbacks on this CPU.
 	 */
-	if (!rcu_cpu_has_callbacks(cpu)) {
-		rdtp->dyntick_holdoff = jiffies - 1;
-		rdtp->dyntick_drain = 0;
-		trace_rcu_prep_idle("No callbacks");
+	if (rdtp->last_accelerate == jiffies)
 		return;
+	rdtp->last_accelerate = jiffies;
+	for_each_rcu_flavor(rsp) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		if (!*rdp->nxttail[RCU_DONE_TAIL])
+			continue;
+		rnp = rdp->mynode;
+		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		rcu_accelerate_cbs(rsp, rnp, rdp);
+		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
+}
 
-	/*
-	 * If in holdoff mode, just return.  We will presumably have
-	 * refrained from disabling the scheduling-clock tick.
-	 */
-	if (rdtp->dyntick_holdoff == jiffies) {
-		trace_rcu_prep_idle("In holdoff");
-		return;
-	}
+/*
+ * Clean up for exit from idle.  Attempt to advance callbacks based on
+ * any grace periods that elapsed while the CPU was idle, and if any
+ * callbacks are now ready to invoke, initiate invocation.
+ */
+static void rcu_cleanup_after_idle(int cpu)
+{
+	struct rcu_data *rdp;
+	struct rcu_state *rsp;
 
-	/* Check and update the ->dyntick_drain sequencing. */
-	if (rdtp->dyntick_drain <= 0) {
-		/* First time through, initialize the counter. */
-		rdtp->dyntick_drain = RCU_IDLE_FLUSHES;
-	} else if (rdtp->dyntick_drain <= RCU_IDLE_OPT_FLUSHES &&
-		   !rcu_pending(cpu) &&
-		   !local_softirq_pending()) {
-		/* Can we go dyntick-idle despite still having callbacks? */
-		rdtp->dyntick_drain = 0;
-		rdtp->dyntick_holdoff = jiffies;
-		if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
-			trace_rcu_prep_idle("Dyntick with callbacks");
-			rdtp->idle_gp_timer_expires =
-				round_up(jiffies + RCU_IDLE_GP_DELAY,
-					 RCU_IDLE_GP_DELAY);
-		} else {
-			rdtp->idle_gp_timer_expires =
-				round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY);
-			trace_rcu_prep_idle("Dyntick with lazy callbacks");
-		}
-		tp = &rdtp->idle_gp_timer;
-		mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
-		rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
-		return; /* Nothing more to do immediately. */
-	} else if (--(rdtp->dyntick_drain) <= 0) {
-		/* We have hit the limit, so time to give up. */
-		rdtp->dyntick_holdoff = jiffies;
-		trace_rcu_prep_idle("Begin holdoff");
-		invoke_rcu_core();  /* Force the CPU out of dyntick-idle. */
+	if (is_nocb_cpu(cpu))
 		return;
-	}
-
-	/*
-	 * Do one step of pushing the remaining RCU callbacks through
-	 * the RCU core state machine.
-	 */
-#ifdef CONFIG_TREE_PREEMPT_RCU
-	if (per_cpu(rcu_preempt_data, cpu).nxtlist) {
-		rcu_preempt_qs(cpu);
-		force_quiescent_state(&rcu_preempt_state);
-	}
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-	if (per_cpu(rcu_sched_data, cpu).nxtlist) {
-		rcu_sched_qs(cpu);
-		force_quiescent_state(&rcu_sched_state);
-	}
-	if (per_cpu(rcu_bh_data, cpu).nxtlist) {
-		rcu_bh_qs(cpu);
-		force_quiescent_state(&rcu_bh_state);
-	}
-
-	/*
-	 * If RCU callbacks are still pending, RCU still needs this CPU.
-	 * So try forcing the callbacks through the grace period.
-	 */
-	if (rcu_cpu_has_callbacks(cpu)) {
-		trace_rcu_prep_idle("More callbacks");
-		invoke_rcu_core();
-	} else {
-		trace_rcu_prep_idle("Callbacks drained");
+	rcu_try_advance_all_cbs();
+	for_each_rcu_flavor(rsp) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		if (cpu_has_callbacks_ready_to_invoke(rdp))
+			invoke_rcu_core();
 	}
 }
 
@@ -2016,16 +1862,13 @@ early_initcall(rcu_register_oom_notifier);
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
-	struct timer_list *tltp = &rdtp->idle_gp_timer;
-	char c;
+	unsigned long nlpd = rdtp->nonlazy_posted - rdtp->nonlazy_posted_snap;
 
-	c = rdtp->dyntick_holdoff == jiffies ? 'H' : '.';
-	if (timer_pending(tltp))
-		sprintf(cp, "drain=%d %c timer=%lu",
-			rdtp->dyntick_drain, c, tltp->expires - jiffies);
-	else
-		sprintf(cp, "drain=%d %c timer not pending",
-			rdtp->dyntick_drain, c);
+	sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c",
+		rdtp->last_accelerate & 0xffff, jiffies & 0xffff,
+		ulong2long(nlpd),
+		rdtp->all_lazy ? 'L' : '.',
+		rdtp->tick_nohz_enabled_snap ? '.' : 'D');
 }
 
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -2071,10 +1914,11 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	printk(KERN_ERR "\t%d: (%lu %s) idle=%03x/%llx/%d %s\n",
+	printk(KERN_ERR "\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u %s\n",
 	       cpu, ticks_value, ticks_title,
 	       atomic_read(&rdtp->dynticks) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
+	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
 	       fast_no_hz);
 }
 
@@ -2088,6 +1932,7 @@ static void print_cpu_stall_info_end(void)
 static void zero_cpu_stall_ticks(struct rcu_data *rdp)
 {
 	rdp->ticks_this_gp = 0;
+	rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
 }
 
 /* Increment ->ticks_this_gp for all flavors of RCU. */
@@ -2166,6 +2011,47 @@ static int __init parse_rcu_nocb_poll(char *arg)
 }
 early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
 
+/*
+ * Do any no-CBs CPUs need another grace period?
+ *
+ * Interrupts must be disabled.  If the caller does not hold the root
+ * rnp_node structure's ->lock, the results are advisory only.
+ */
+static int rcu_nocb_needs_gp(struct rcu_state *rsp)
+{
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	return rnp->need_future_gp[(ACCESS_ONCE(rnp->completed) + 1) & 0x1];
+}
+
+/*
+ * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended
+ * grace period.
+ */
+static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+	wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]);
+}
+
+/*
+ * Set the root rcu_node structure's ->need_future_gp field
+ * based on the sum of those of all rcu_node structures.  This does
+ * double-count the root rcu_node structure's requests, but this
+ * is necessary to handle the possibility of a rcu_nocb_kthread()
+ * having awakened during the time that the rcu_node structures
+ * were being updated for the end of the previous grace period.
+ */
+static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
+{
+	rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
+}
+
+static void rcu_init_one_nocb(struct rcu_node *rnp)
+{
+	init_waitqueue_head(&rnp->nocb_gp_wq[0]);
+	init_waitqueue_head(&rnp->nocb_gp_wq[1]);
+}
+
 /* Is the specified CPU a no-CPUs CPU? */
 bool rcu_is_nocb_cpu(int cpu)
 {
@@ -2228,6 +2114,13 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return 0;
 	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
+		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
+					 (unsigned long)rhp->func,
+					 rdp->qlen_lazy, rdp->qlen);
+	else
+		trace_rcu_callback(rdp->rsp->name, rhp,
+				   rdp->qlen_lazy, rdp->qlen);
 	return 1;
 }
 
@@ -2266,95 +2159,36 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 }
 
 /*
- * There must be at least one non-no-CBs CPU in operation at any given
- * time, because no-CBs CPUs are not capable of initiating grace periods
- * independently.  This function therefore complains if the specified
- * CPU is the last non-no-CBs CPU, allowing the CPU-hotplug system to
- * avoid offlining the last such CPU.  (Recursion is a wonderful thing,
- * but you have to have a base case!)
+ * If necessary, kick off a new grace period, and either way wait
+ * for a subsequent grace period to complete.
  */
-static bool nocb_cpu_expendable(int cpu)
+static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 {
-	cpumask_var_t non_nocb_cpus;
-	int ret;
+	unsigned long c;
+	bool d;
+	unsigned long flags;
+	struct rcu_node *rnp = rdp->mynode;
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	c = rcu_start_future_gp(rnp, rdp);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
-	 * If there are no no-CB CPUs or if this CPU is not a no-CB CPU,
-	 * then offlining this CPU is harmless.  Let it happen.
+	 * Wait for the grace period.  Do so interruptibly to avoid messing
+	 * up the load average.
 	 */
-	if (!have_rcu_nocb_mask || rcu_is_nocb_cpu(cpu))
-		return 1;
-
-	/* If no memory, play it safe and keep the CPU around. */
-	if (!alloc_cpumask_var(&non_nocb_cpus, GFP_NOIO))
-		return 0;
-	cpumask_andnot(non_nocb_cpus, cpu_online_mask, rcu_nocb_mask);
-	cpumask_clear_cpu(cpu, non_nocb_cpus);
-	ret = !cpumask_empty(non_nocb_cpus);
-	free_cpumask_var(non_nocb_cpus);
-	return ret;
-}
-
-/*
- * Helper structure for remote registry of RCU callbacks.
- * This is needed for when a no-CBs CPU needs to start a grace period.
- * If it just invokes call_rcu(), the resulting callback will be queued,
- * which can result in deadlock.
- */
-struct rcu_head_remote {
-	struct rcu_head *rhp;
-	call_rcu_func_t *crf;
-	void (*func)(struct rcu_head *rhp);
-};
-
-/*
- * Register a callback as specified by the rcu_head_remote struct.
- * This function is intended to be invoked via smp_call_function_single().
- */
-static void call_rcu_local(void *arg)
-{
-	struct rcu_head_remote *rhrp =
-		container_of(arg, struct rcu_head_remote, rhp);
-
-	rhrp->crf(rhrp->rhp, rhrp->func);
-}
-
-/*
- * Set up an rcu_head_remote structure and the invoke call_rcu_local()
- * on CPU 0 (which is guaranteed to be a non-no-CBs CPU) via
- * smp_call_function_single().
- */
-static void invoke_crf_remote(struct rcu_head *rhp,
-			      void (*func)(struct rcu_head *rhp),
-			      call_rcu_func_t crf)
-{
-	struct rcu_head_remote rhr;
-
-	rhr.rhp = rhp;
-	rhr.crf = crf;
-	rhr.func = func;
-	smp_call_function_single(0, call_rcu_local, &rhr, 1);
-}
-
-/*
- * Helper functions to be passed to wait_rcu_gp(), each of which
- * invokes invoke_crf_remote() to register a callback appropriately.
- */
-static void __maybe_unused
-call_rcu_preempt_remote(struct rcu_head *rhp,
-			void (*func)(struct rcu_head *rhp))
-{
-	invoke_crf_remote(rhp, func, call_rcu);
-}
-static void call_rcu_bh_remote(struct rcu_head *rhp,
-			       void (*func)(struct rcu_head *rhp))
-{
-	invoke_crf_remote(rhp, func, call_rcu_bh);
-}
-static void call_rcu_sched_remote(struct rcu_head *rhp,
-				  void (*func)(struct rcu_head *rhp))
-{
-	invoke_crf_remote(rhp, func, call_rcu_sched);
+	trace_rcu_future_gp(rnp, rdp, c, "StartWait");
+	for (;;) {
+		wait_event_interruptible(
+			rnp->nocb_gp_wq[c & 0x1],
+			(d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
+		if (likely(d))
+			break;
+		flush_signals(current);
+		trace_rcu_future_gp(rnp, rdp, c, "ResumeWait");
+	}
+	trace_rcu_future_gp(rnp, rdp, c, "EndWait");
+	smp_mb(); /* Ensure that CB invocation happens after GP end. */
 }
 
 /*
@@ -2391,7 +2225,7 @@ static int rcu_nocb_kthread(void *arg)
 		cl = atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
 		ACCESS_ONCE(rdp->nocb_p_count) += c;
 		ACCESS_ONCE(rdp->nocb_p_count_lazy) += cl;
-		wait_rcu_gp(rdp->rsp->call_remote);
+		rcu_nocb_wait_gp(rdp);
 
 		/* Each pass through the following loop invokes a callback. */
 		trace_rcu_batch_start(rdp->rsp->name, cl, c, -1);
@@ -2437,32 +2271,41 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 		return;
 	for_each_cpu(cpu, rcu_nocb_mask) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
-		t = kthread_run(rcu_nocb_kthread, rdp, "rcuo%d", cpu);
+		t = kthread_run(rcu_nocb_kthread, rdp,
+				"rcuo%c/%d", rsp->abbr, cpu);
 		BUG_ON(IS_ERR(t));
 		ACCESS_ONCE(rdp->nocb_kthread) = t;
 	}
 }
 
 /* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */
-static void init_nocb_callback_list(struct rcu_data *rdp)
+static bool init_nocb_callback_list(struct rcu_data *rdp)
 {
 	if (rcu_nocb_mask == NULL ||
 	    !cpumask_test_cpu(rdp->cpu, rcu_nocb_mask))
-		return;
+		return false;
 	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+	return true;
+}
+
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+
+static int rcu_nocb_needs_gp(struct rcu_state *rsp)
+{
+	return 0;
 }
 
-/* Initialize the ->call_remote fields in the rcu_state structures. */
-static void __init rcu_init_nocb(void)
+static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-#ifdef CONFIG_PREEMPT_RCU
-	rcu_preempt_state.call_remote = call_rcu_preempt_remote;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-	rcu_bh_state.call_remote = call_rcu_bh_remote;
-	rcu_sched_state.call_remote = call_rcu_sched_remote;
 }
 
-#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
+{
+}
+
+static void rcu_init_one_nocb(struct rcu_node *rnp)
+{
+}
 
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy)
@@ -2476,11 +2319,6 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 	return 0;
 }
 
-static bool nocb_cpu_expendable(int cpu)
-{
-	return 1;
-}
-
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
@@ -2489,12 +2327,9 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 }
 
-static void init_nocb_callback_list(struct rcu_data *rdp)
-{
-}
-
-static void __init rcu_init_nocb(void)
+static bool init_nocb_callback_list(struct rcu_data *rdp)
 {
+	return false;
 }
 
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 0d095dcaa670..49099e81c87b 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -46,8 +46,6 @@
 #define RCU_TREE_NONCORE
 #include "rcutree.h"
 
-#define ulong2long(a) (*(long *)(&(a)))
-
 static int r_open(struct inode *inode, struct file *file,
 					const struct seq_operations *op)
 {
diff --git a/kernel/resource.c b/kernel/resource.c
index 73f35d4b30b9..d7386986e10e 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -21,6 +21,7 @@
 #include <linux/seq_file.h>
 #include <linux/device.h>
 #include <linux/pfn.h>
+#include <linux/mm.h>
 #include <asm/io.h>
 
 
@@ -50,6 +51,14 @@ struct resource_constraint {
 
 static DEFINE_RWLOCK(resource_lock);
 
+/*
+ * For memory hotplug, there is no way to free resource entries allocated
+ * by boot mem after the system is up. So for reusing the resource entry
+ * we need to remember the resource.
+ */
+static struct resource *bootmem_resource_free;
+static DEFINE_SPINLOCK(bootmem_resource_lock);
+
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
@@ -151,6 +160,40 @@ __initcall(ioresources_init);
 
 #endif /* CONFIG_PROC_FS */
 
+static void free_resource(struct resource *res)
+{
+	if (!res)
+		return;
+
+	if (!PageSlab(virt_to_head_page(res))) {
+		spin_lock(&bootmem_resource_lock);
+		res->sibling = bootmem_resource_free;
+		bootmem_resource_free = res;
+		spin_unlock(&bootmem_resource_lock);
+	} else {
+		kfree(res);
+	}
+}
+
+static struct resource *alloc_resource(gfp_t flags)
+{
+	struct resource *res = NULL;
+
+	spin_lock(&bootmem_resource_lock);
+	if (bootmem_resource_free) {
+		res = bootmem_resource_free;
+		bootmem_resource_free = res->sibling;
+	}
+	spin_unlock(&bootmem_resource_lock);
+
+	if (res)
+		memset(res, 0, sizeof(struct resource));
+	else
+		res = kzalloc(sizeof(struct resource), flags);
+
+	return res;
+}
+
 /* Return the conflict entry if you can't request it */
 static struct resource * __request_resource(struct resource *root, struct resource *new)
 {
@@ -706,24 +749,13 @@ void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
 	write_unlock(&resource_lock);
 }
 
-/**
- * adjust_resource - modify a resource's start and size
- * @res: resource to modify
- * @start: new start value
- * @size: new size
- *
- * Given an existing resource, change its start and size to match the
- * arguments.  Returns 0 on success, -EBUSY if it can't fit.
- * Existing children of the resource are assumed to be immutable.
- */
-int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size)
+static int __adjust_resource(struct resource *res, resource_size_t start,
+				resource_size_t size)
 {
 	struct resource *tmp, *parent = res->parent;
 	resource_size_t end = start + size - 1;
 	int result = -EBUSY;
 
-	write_lock(&resource_lock);
-
 	if (!parent)
 		goto skip;
 
@@ -751,6 +783,26 @@ skip:
 	result = 0;
 
  out:
+	return result;
+}
+
+/**
+ * adjust_resource - modify a resource's start and size
+ * @res: resource to modify
+ * @start: new start value
+ * @size: new size
+ *
+ * Given an existing resource, change its start and size to match the
+ * arguments.  Returns 0 on success, -EBUSY if it can't fit.
+ * Existing children of the resource are assumed to be immutable.
+ */
+int adjust_resource(struct resource *res, resource_size_t start,
+			resource_size_t size)
+{
+	int result;
+
+	write_lock(&resource_lock);
+	result = __adjust_resource(res, start, size);
 	write_unlock(&resource_lock);
 	return result;
 }
@@ -762,7 +814,7 @@ static void __init __reserve_region_with_split(struct resource *root,
 {
 	struct resource *parent = root;
 	struct resource *conflict;
-	struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC);
+	struct resource *res = alloc_resource(GFP_ATOMIC);
 	struct resource *next_res = NULL;
 
 	if (!res)
@@ -787,7 +839,7 @@ static void __init __reserve_region_with_split(struct resource *root,
 		/* conflict covered whole area */
 		if (conflict->start <= res->start &&
 				conflict->end >= res->end) {
-			kfree(res);
+			free_resource(res);
 			WARN_ON(next_res);
 			break;
 		}
@@ -797,10 +849,9 @@ static void __init __reserve_region_with_split(struct resource *root,
 			end = res->end;
 			res->end = conflict->start - 1;
 			if (conflict->end < end) {
-				next_res = kzalloc(sizeof(*next_res),
-						GFP_ATOMIC);
+				next_res = alloc_resource(GFP_ATOMIC);
 				if (!next_res) {
-					kfree(res);
+					free_resource(res);
 					break;
 				}
 				next_res->name = name;
@@ -890,7 +941,7 @@ struct resource * __request_region(struct resource *parent,
 				   const char *name, int flags)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
+	struct resource *res = alloc_resource(GFP_KERNEL);
 
 	if (!res)
 		return NULL;
@@ -924,7 +975,7 @@ struct resource * __request_region(struct resource *parent,
 			continue;
 		}
 		/* Uhhuh, that didn't work out.. */
-		kfree(res);
+		free_resource(res);
 		res = NULL;
 		break;
 	}
@@ -958,7 +1009,7 @@ int __check_region(struct resource *parent, resource_size_t start,
 		return -EBUSY;
 
 	release_resource(res);
-	kfree(res);
+	free_resource(res);
 	return 0;
 }
 EXPORT_SYMBOL(__check_region);
@@ -998,7 +1049,7 @@ void __release_region(struct resource *parent, resource_size_t start,
 			write_unlock(&resource_lock);
 			if (res->flags & IORESOURCE_MUXED)
 				wake_up(&muxed_resource_wait);
-			kfree(res);
+			free_resource(res);
 			return;
 		}
 		p = &res->sibling;
@@ -1012,6 +1063,109 @@ void __release_region(struct resource *parent, resource_size_t start,
 }
 EXPORT_SYMBOL(__release_region);
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/**
+ * release_mem_region_adjustable - release a previously reserved memory region
+ * @parent: parent resource descriptor
+ * @start: resource start address
+ * @size: resource region size
+ *
+ * This interface is intended for memory hot-delete.  The requested region
+ * is released from a currently busy memory resource.  The requested region
+ * must either match exactly or fit into a single busy resource entry.  In
+ * the latter case, the remaining resource is adjusted accordingly.
+ * Existing children of the busy memory resource must be immutable in the
+ * request.
+ *
+ * Note:
+ * - Additional release conditions, such as overlapping region, can be
+ *   supported after they are confirmed as valid cases.
+ * - When a busy memory resource gets split into two entries, the code
+ *   assumes that all children remain in the lower address entry for
+ *   simplicity.  Enhance this logic when necessary.
+ */
+int release_mem_region_adjustable(struct resource *parent,
+			resource_size_t start, resource_size_t size)
+{
+	struct resource **p;
+	struct resource *res;
+	struct resource *new_res;
+	resource_size_t end;
+	int ret = -EINVAL;
+
+	end = start + size - 1;
+	if ((start < parent->start) || (end > parent->end))
+		return ret;
+
+	/* The alloc_resource() result gets checked later */
+	new_res = alloc_resource(GFP_KERNEL);
+
+	p = &parent->child;
+	write_lock(&resource_lock);
+
+	while ((res = *p)) {
+		if (res->start >= end)
+			break;
+
+		/* look for the next resource if it does not fit into */
+		if (res->start > start || res->end < end) {
+			p = &res->sibling;
+			continue;
+		}
+
+		if (!(res->flags & IORESOURCE_MEM))
+			break;
+
+		if (!(res->flags & IORESOURCE_BUSY)) {
+			p = &res->child;
+			continue;
+		}
+
+		/* found the target resource; let's adjust accordingly */
+		if (res->start == start && res->end == end) {
+			/* free the whole entry */
+			*p = res->sibling;
+			free_resource(res);
+			ret = 0;
+		} else if (res->start == start && res->end != end) {
+			/* adjust the start */
+			ret = __adjust_resource(res, end + 1,
+						res->end - end);
+		} else if (res->start != start && res->end == end) {
+			/* adjust the end */
+			ret = __adjust_resource(res, res->start,
+						start - res->start);
+		} else {
+			/* split into two entries */
+			if (!new_res) {
+				ret = -ENOMEM;
+				break;
+			}
+			new_res->name = res->name;
+			new_res->start = end + 1;
+			new_res->end = res->end;
+			new_res->flags = res->flags;
+			new_res->parent = res->parent;
+			new_res->sibling = res->sibling;
+			new_res->child = NULL;
+
+			ret = __adjust_resource(res, res->start,
+						start - res->start);
+			if (ret)
+				break;
+			res->sibling = new_res;
+			new_res = NULL;
+		}
+
+		break;
+	}
+
+	write_unlock(&resource_lock);
+	free_resource(new_res);
+	return ret;
+}
+#endif	/* CONFIG_MEMORY_HOTREMOVE */
+
 /*
  * Managed region resource
  */
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 7890b10084a7..1d96dd0d93c1 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
+#include <linux/stat.h>
 
 #include "rtmutex.h"
 
@@ -366,8 +367,8 @@ static ssize_t sysfs_test_status(struct device *dev, struct device_attribute *at
 	return curr - buf;
 }
 
-static DEVICE_ATTR(status, 0600, sysfs_test_status, NULL);
-static DEVICE_ATTR(command, 0600, NULL, sysfs_test_command);
+static DEVICE_ATTR(status, S_IRUSR, sysfs_test_status, NULL);
+static DEVICE_ATTR(command, S_IWUSR, NULL, sysfs_test_command);
 
 static struct bus_type rttest_subsys = {
 	.name = "rttest",
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index f06d249e103b..deaf90e4a1de 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -16,3 +16,4 @@ obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c685e31492df..c3ae1446461c 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd)
 	u64 this_clock, remote_clock;
 	u64 *ptr, old_val, val;
 
+#if BITS_PER_LONG != 64
+again:
+	/*
+	 * Careful here: The local and the remote clock values need to
+	 * be read out atomic as we need to compare the values and
+	 * then update either the local or the remote side. So the
+	 * cmpxchg64 below only protects one readout.
+	 *
+	 * We must reread via sched_clock_local() in the retry case on
+	 * 32bit as an NMI could use sched_clock_local() via the
+	 * tracer and hit between the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	this_clock = sched_clock_local(my_scd);
+	/*
+	 * We must enforce atomic readout on 32bit, otherwise the
+	 * update on the remote cpu can hit inbetween the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	remote_clock = cmpxchg64(&scd->clock, 0, 0);
+#else
+	/*
+	 * On 64bit the read of [my]scd->clock is atomic versus the
+	 * update, so we can avoid the above 32bit dance.
+	 */
 	sched_clock_local(my_scd);
 again:
 	this_clock = my_scd->clock;
 	remote_clock = scd->clock;
+#endif
 
 	/*
 	 * Use the opportunity that we have both locks
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dd09def88567..e94842d4400c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -512,11 +512,6 @@ static inline void init_hrtick(void)
  * the target CPU.
  */
 #ifdef CONFIG_SMP
-
-#ifndef tsk_is_polling
-#define tsk_is_polling(t) 0
-#endif
-
 void resched_task(struct task_struct *p)
 {
 	int cpu;
@@ -1536,8 +1531,10 @@ static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
 
-	BUG_ON(rq != this_rq());
-	BUG_ON(p == current);
+	if (WARN_ON_ONCE(rq != this_rq()) ||
+	    WARN_ON_ONCE(p == current))
+		return;
+
 	lockdep_assert_held(&rq->lock);
 
 	if (!raw_spin_trylock(&p->pi_lock)) {
@@ -3037,51 +3034,6 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-
-static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
-{
-	if (lock->owner != owner)
-		return false;
-
-	/*
-	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
-	 * lock->owner still matches owner, if that fails, owner might
-	 * point to free()d memory, if it still matches, the rcu_read_lock()
-	 * ensures the memory stays valid.
-	 */
-	barrier();
-
-	return owner->on_cpu;
-}
-
-/*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
- */
-int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
-{
-	if (!sched_feat(OWNER_SPIN))
-		return 0;
-
-	rcu_read_lock();
-	while (owner_running(lock, owner)) {
-		if (need_resched())
-			break;
-
-		arch_mutex_cpu_relax();
-	}
-	rcu_read_unlock();
-
-	/*
-	 * We break out the loop above on need_resched() and when the
-	 * owner changed, which is a sign for heavy contention. Return
-	 * success only when lock->owner is NULL.
-	 */
-	return lock->owner == NULL;
-}
-#endif
-
 #ifdef CONFIG_PREEMPT
 /*
  * this is the entry point to schedule() from in-kernel preemption
@@ -4170,6 +4122,10 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	get_task_struct(p);
 	rcu_read_unlock();
 
+	if (p->flags & PF_NO_SETAFFINITY) {
+		retval = -EINVAL;
+		goto out_put_task;
+	}
 	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
 		retval = -ENOMEM;
 		goto out_put_task;
@@ -4817,11 +4773,6 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 	}
 
-	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	do_set_cpus_allowed(p, new_mask);
 
 	/* Can the task run on the task's current CPU? If so, we're done */
@@ -5043,7 +4994,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep)
 }
 
 static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
 
 static void
 set_table_entry(struct ctl_table *entry,
@@ -6292,7 +6243,7 @@ static void sched_init_numa(void)
 	 * 'level' contains the number of unique distances, excluding the
 	 * identity distance node_distance(i,i).
 	 *
-	 * The sched_domains_nume_distance[] array includes the actual distance
+	 * The sched_domains_numa_distance[] array includes the actual distance
 	 * numbers.
 	 */
 
@@ -6913,7 +6864,7 @@ struct task_group root_task_group;
 LIST_HEAD(task_groups);
 #endif
 
-DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 
 void __init sched_init(void)
 {
@@ -6950,7 +6901,7 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 		for_each_possible_cpu(i) {
-			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+			per_cpu(load_balance_mask, i) = (void *)ptr;
 			ptr += cpumask_size();
 		}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
@@ -6976,12 +6927,6 @@ void __init sched_init(void)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-#ifdef CONFIG_CGROUP_CPUACCT
-	root_cpuacct.cpustat = &kernel_cpustat;
-	root_cpuacct.cpuusage = alloc_percpu(u64);
-	/* Too early, not expected to fail */
-	BUG_ON(!root_cpuacct.cpuusage);
-#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
@@ -8083,226 +8028,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
-#ifdef CONFIG_CGROUP_CPUACCT
-
-/*
- * CPU accounting code for task groups.
- *
- * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
- * (balbir@in.ibm.com).
- */
-
-struct cpuacct root_cpuacct;
-
-/* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
-{
-	struct cpuacct *ca;
-
-	if (!cgrp->parent)
-		return &root_cpuacct.css;
-
-	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
-	if (!ca)
-		goto out;
-
-	ca->cpuusage = alloc_percpu(u64);
-	if (!ca->cpuusage)
-		goto out_free_ca;
-
-	ca->cpustat = alloc_percpu(struct kernel_cpustat);
-	if (!ca->cpustat)
-		goto out_free_cpuusage;
-
-	return &ca->css;
-
-out_free_cpuusage:
-	free_percpu(ca->cpuusage);
-out_free_ca:
-	kfree(ca);
-out:
-	return ERR_PTR(-ENOMEM);
-}
-
-/* destroy an existing cpu accounting group */
-static void cpuacct_css_free(struct cgroup *cgrp)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-
-	free_percpu(ca->cpustat);
-	free_percpu(ca->cpuusage);
-	kfree(ca);
-}
-
-static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
-{
-	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-	u64 data;
-
-#ifndef CONFIG_64BIT
-	/*
-	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
-	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
-	data = *cpuusage;
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
-#else
-	data = *cpuusage;
-#endif
-
-	return data;
-}
-
-static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
-{
-	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-
-#ifndef CONFIG_64BIT
-	/*
-	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
-	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
-	*cpuusage = val;
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
-#else
-	*cpuusage = val;
-#endif
-}
-
-/* return total cpu usage (in nanoseconds) of a group */
-static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	u64 totalcpuusage = 0;
-	int i;
-
-	for_each_present_cpu(i)
-		totalcpuusage += cpuacct_cpuusage_read(ca, i);
-
-	return totalcpuusage;
-}
-
-static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
-								u64 reset)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	int err = 0;
-	int i;
-
-	if (reset) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	for_each_present_cpu(i)
-		cpuacct_cpuusage_write(ca, i, 0);
-
-out:
-	return err;
-}
-
-static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
-				   struct seq_file *m)
-{
-	struct cpuacct *ca = cgroup_ca(cgroup);
-	u64 percpu;
-	int i;
-
-	for_each_present_cpu(i) {
-		percpu = cpuacct_cpuusage_read(ca, i);
-		seq_printf(m, "%llu ", (unsigned long long) percpu);
-	}
-	seq_printf(m, "\n");
-	return 0;
-}
-
-static const char *cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
-
-static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
-			      struct cgroup_map_cb *cb)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	int cpu;
-	s64 val = 0;
-
-	for_each_online_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_USER];
-		val += kcpustat->cpustat[CPUTIME_NICE];
-	}
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
-
-	val = 0;
-	for_each_online_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_SYSTEM];
-		val += kcpustat->cpustat[CPUTIME_IRQ];
-		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
-	}
-
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
-
-	return 0;
-}
-
-static struct cftype files[] = {
-	{
-		.name = "usage",
-		.read_u64 = cpuusage_read,
-		.write_u64 = cpuusage_write,
-	},
-	{
-		.name = "usage_percpu",
-		.read_seq_string = cpuacct_percpu_seq_read,
-	},
-	{
-		.name = "stat",
-		.read_map = cpuacct_stats_show,
-	},
-	{ }	/* terminate */
-};
-
-/*
- * charge this task's execution time to its accounting group.
- *
- * called with rq->lock held.
- */
-void cpuacct_charge(struct task_struct *tsk, u64 cputime)
-{
-	struct cpuacct *ca;
-	int cpu;
-
-	if (unlikely(!cpuacct_subsys.active))
-		return;
-
-	cpu = task_cpu(tsk);
-
-	rcu_read_lock();
-
-	ca = task_ca(tsk);
-
-	for (; ca; ca = parent_ca(ca)) {
-		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-		*cpuusage += cputime;
-	}
-
-	rcu_read_unlock();
-}
-
-struct cgroup_subsys cpuacct_subsys = {
-	.name = "cpuacct",
-	.css_alloc = cpuacct_css_alloc,
-	.css_free = cpuacct_css_free,
-	.subsys_id = cpuacct_subsys_id,
-	.base_cftypes = files,
-};
-#endif	/* CONFIG_CGROUP_CPUACCT */
-
 void dump_cpu_task(int cpu)
 {
 	pr_info("Task dump for CPU %d:\n", cpu);
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
new file mode 100644
index 000000000000..dbb7e2cd95eb
--- /dev/null
+++ b/kernel/sched/cpuacct.c
@@ -0,0 +1,296 @@
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/cpumask.h>
+#include <linux/seq_file.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel_stat.h>
+#include <linux/err.h>
+
+#include "sched.h"
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+/* Time spent by the tasks of the cpu accounting group executing in ... */
+enum cpuacct_stat_index {
+	CPUACCT_STAT_USER,	/* ... user mode */
+	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
+
+	CPUACCT_STAT_NSTATS,
+};
+
+/* track cpu usage of a group of tasks and its child groups */
+struct cpuacct {
+	struct cgroup_subsys_state css;
+	/* cpuusage holds pointer to a u64-type object on every cpu */
+	u64 __percpu *cpuusage;
+	struct kernel_cpustat __percpu *cpustat;
+};
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+/* return cpu accounting group to which this task belongs */
+static inline struct cpuacct *task_ca(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+static inline struct cpuacct *__parent_ca(struct cpuacct *ca)
+{
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
+static inline struct cpuacct *parent_ca(struct cpuacct *ca)
+{
+	if (!ca->css.cgroup->parent)
+		return NULL;
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
+static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
+static struct cpuacct root_cpuacct = {
+	.cpustat	= &kernel_cpustat,
+	.cpuusage	= &root_cpuacct_cpuusage,
+};
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
+{
+	struct cpuacct *ca;
+
+	if (!cgrp->parent)
+		return &root_cpuacct.css;
+
+	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	if (!ca)
+		goto out;
+
+	ca->cpuusage = alloc_percpu(u64);
+	if (!ca->cpuusage)
+		goto out_free_ca;
+
+	ca->cpustat = alloc_percpu(struct kernel_cpustat);
+	if (!ca->cpustat)
+		goto out_free_cpuusage;
+
+	return &ca->css;
+
+out_free_cpuusage:
+	free_percpu(ca->cpuusage);
+out_free_ca:
+	kfree(ca);
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+/* destroy an existing cpu accounting group */
+static void cpuacct_css_free(struct cgroup *cgrp)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+
+	free_percpu(ca->cpustat);
+	free_percpu(ca->cpuusage);
+	kfree(ca);
+}
+
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+	u64 data;
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+	 */
+	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	data = *cpuusage;
+	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	data = *cpuusage;
+#endif
+
+	return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+	 */
+	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	*cpuusage = val;
+	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	*cpuusage = val;
+#endif
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	u64 totalcpuusage = 0;
+	int i;
+
+	for_each_present_cpu(i)
+		totalcpuusage += cpuacct_cpuusage_read(ca, i);
+
+	return totalcpuusage;
+}
+
+static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
+								u64 reset)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int err = 0;
+	int i;
+
+	if (reset) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_present_cpu(i)
+		cpuacct_cpuusage_write(ca, i, 0);
+
+out:
+	return err;
+}
+
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+				   struct seq_file *m)
+{
+	struct cpuacct *ca = cgroup_ca(cgroup);
+	u64 percpu;
+	int i;
+
+	for_each_present_cpu(i) {
+		percpu = cpuacct_cpuusage_read(ca, i);
+		seq_printf(m, "%llu ", (unsigned long long) percpu);
+	}
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static const char * const cpuacct_stat_desc[] = {
+	[CPUACCT_STAT_USER] = "user",
+	[CPUACCT_STAT_SYSTEM] = "system",
+};
+
+static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
+			      struct cgroup_map_cb *cb)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int cpu;
+	s64 val = 0;
+
+	for_each_online_cpu(cpu) {
+		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
+		val += kcpustat->cpustat[CPUTIME_USER];
+		val += kcpustat->cpustat[CPUTIME_NICE];
+	}
+	val = cputime64_to_clock_t(val);
+	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+
+	val = 0;
+	for_each_online_cpu(cpu) {
+		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
+		val += kcpustat->cpustat[CPUTIME_SYSTEM];
+		val += kcpustat->cpustat[CPUTIME_IRQ];
+		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
+	}
+
+	val = cputime64_to_clock_t(val);
+	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+
+	return 0;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "usage",
+		.read_u64 = cpuusage_read,
+		.write_u64 = cpuusage_write,
+	},
+	{
+		.name = "usage_percpu",
+		.read_seq_string = cpuacct_percpu_seq_read,
+	},
+	{
+		.name = "stat",
+		.read_map = cpuacct_stats_show,
+	},
+	{ }	/* terminate */
+};
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+	struct cpuacct *ca;
+	int cpu;
+
+	cpu = task_cpu(tsk);
+
+	rcu_read_lock();
+
+	ca = task_ca(tsk);
+
+	while (true) {
+		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+		*cpuusage += cputime;
+
+		ca = parent_ca(ca);
+		if (!ca)
+			break;
+	}
+
+	rcu_read_unlock();
+}
+
+/*
+ * Add user/system time to cpuacct.
+ *
+ * Note: it's the caller that updates the account of the root cgroup.
+ */
+void cpuacct_account_field(struct task_struct *p, int index, u64 val)
+{
+	struct kernel_cpustat *kcpustat;
+	struct cpuacct *ca;
+
+	rcu_read_lock();
+	ca = task_ca(p);
+	while (ca != &root_cpuacct) {
+		kcpustat = this_cpu_ptr(ca->cpustat);
+		kcpustat->cpustat[index] += val;
+		ca = __parent_ca(ca);
+	}
+	rcu_read_unlock();
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+	.name		= "cpuacct",
+	.css_alloc	= cpuacct_css_alloc,
+	.css_free	= cpuacct_css_free,
+	.subsys_id	= cpuacct_subsys_id,
+	.base_cftypes	= files,
+	.early_init	= 1,
+};
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
new file mode 100644
index 000000000000..ed605624a5e7
--- /dev/null
+++ b/kernel/sched/cpuacct.h
@@ -0,0 +1,17 @@
+#ifdef CONFIG_CGROUP_CPUACCT
+
+extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
+
+#else
+
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+}
+
+static inline void
+cpuacct_account_field(struct task_struct *p, int index, u64 val)
+{
+}
+
+#endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 699d59756ece..ea32f02bf2c3 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -115,10 +115,6 @@ static int irqtime_account_si_update(void)
 static inline void task_group_account_field(struct task_struct *p, int index,
 					    u64 tmp)
 {
-#ifdef CONFIG_CGROUP_CPUACCT
-	struct kernel_cpustat *kcpustat;
-	struct cpuacct *ca;
-#endif
 	/*
 	 * Since all updates are sure to touch the root cgroup, we
 	 * get ourselves ahead and touch it first. If the root cgroup
@@ -127,19 +123,7 @@ static inline void task_group_account_field(struct task_struct *p, int index,
 	 */
 	__get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
 
-#ifdef CONFIG_CGROUP_CPUACCT
-	if (unlikely(!cpuacct_subsys.active))
-		return;
-
-	rcu_read_lock();
-	ca = task_ca(p);
-	while (ca && (ca != &root_cpuacct)) {
-		kcpustat = this_cpu_ptr(ca->cpustat);
-		kcpustat->cpustat[index] += tmp;
-		ca = parent_ca(ca);
-	}
-	rcu_read_unlock();
-#endif
+	cpuacct_account_field(p, index, tmp);
 }
 
 /*
@@ -310,7 +294,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 
 	t = tsk;
 	do {
-		task_cputime(tsk, &utime, &stime);
+		task_cputime(t, &utime, &stime);
 		times->utime += utime;
 		times->stime += stime;
 		times->sum_exec_runtime += task_sched_runtime(t);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5c97fca091a7..c61a614465c8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1563,6 +1563,27 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
 	} /* migrations, e.g. sleep=0 leave decay_count == 0 */
 }
+
+/*
+ * Update the rq's load with the elapsed running time before entering
+ * idle. if the last scheduled task is not a CFS task, idle_enter will
+ * be the only way to update the runnable statistic.
+ */
+void idle_enter_fair(struct rq *this_rq)
+{
+	update_rq_runnable_avg(this_rq, 1);
+}
+
+/*
+ * Update the rq's load with the elapsed idle time before a task is
+ * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
+ * be the only way to update the runnable statistic.
+ */
+void idle_exit_fair(struct rq *this_rq)
+{
+	update_rq_runnable_avg(this_rq, 0);
+}
+
 #else
 static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq) {}
@@ -3875,12 +3896,16 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	int tsk_cache_hot = 0;
 	/*
 	 * We do not migrate tasks that are:
-	 * 1) running (obviously), or
+	 * 1) throttled_lb_pair, or
 	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
-	 * 3) are cache-hot on their current CPU.
+	 * 3) running (obviously), or
+	 * 4) are cache-hot on their current CPU.
 	 */
+	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+		return 0;
+
 	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
-		int new_dst_cpu;
+		int cpu;
 
 		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 
@@ -3895,12 +3920,15 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
 			return 0;
 
-		new_dst_cpu = cpumask_first_and(env->dst_grpmask,
-						tsk_cpus_allowed(p));
-		if (new_dst_cpu < nr_cpu_ids) {
-			env->flags |= LBF_SOME_PINNED;
-			env->new_dst_cpu = new_dst_cpu;
+		/* Prevent to re-select dst_cpu via env's cpus */
+		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
+			if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
+				env->flags |= LBF_SOME_PINNED;
+				env->new_dst_cpu = cpu;
+				break;
+			}
 		}
+
 		return 0;
 	}
 
@@ -3921,20 +3949,17 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
-#ifdef CONFIG_SCHEDSTATS
+
 		if (tsk_cache_hot) {
 			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
-#endif
+
 		return 1;
 	}
 
-	if (tsk_cache_hot) {
-		schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
-		return 0;
-	}
-	return 1;
+	schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
+	return 0;
 }
 
 /*
@@ -3949,9 +3974,6 @@ static int move_one_task(struct lb_env *env)
 	struct task_struct *p, *n;
 
 	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
-		if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu))
-			continue;
-
 		if (!can_migrate_task(p, env))
 			continue;
 
@@ -4003,7 +4025,7 @@ static int move_tasks(struct lb_env *env)
 			break;
 		}
 
-		if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+		if (!can_migrate_task(p, env))
 			goto next;
 
 		load = task_h_load(p);
@@ -4014,9 +4036,6 @@ static int move_tasks(struct lb_env *env)
 		if ((load / 2) > env->imbalance)
 			goto next;
 
-		if (!can_migrate_task(p, env))
-			goto next;
-
 		move_task(p, env);
 		pulled++;
 		env->imbalance -= load;
@@ -4961,7 +4980,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 #define MAX_PINNED_INTERVAL	512
 
 /* Working cpumask for load_balance and load_balance_newidle. */
-DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 
 static int need_active_balance(struct lb_env *env)
 {
@@ -4992,11 +5011,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			int *balance)
 {
 	int ld_moved, cur_ld_moved, active_balance = 0;
-	int lb_iterations, max_lb_iterations;
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
+	struct cpumask *cpus = __get_cpu_var(load_balance_mask);
 
 	struct lb_env env = {
 		.sd		= sd,
@@ -5008,8 +5026,14 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.cpus		= cpus,
 	};
 
+	/*
+	 * For NEWLY_IDLE load_balancing, we don't need to consider
+	 * other cpus in our group
+	 */
+	if (idle == CPU_NEWLY_IDLE)
+		env.dst_grpmask = NULL;
+
 	cpumask_copy(cpus, cpu_active_mask);
-	max_lb_iterations = cpumask_weight(env.dst_grpmask);
 
 	schedstat_inc(sd, lb_count[idle]);
 
@@ -5035,7 +5059,6 @@ redo:
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
 	ld_moved = 0;
-	lb_iterations = 1;
 	if (busiest->nr_running > 1) {
 		/*
 		 * Attempt to move tasks. If find_busiest_group has found
@@ -5062,17 +5085,17 @@ more_balance:
 		double_rq_unlock(env.dst_rq, busiest);
 		local_irq_restore(flags);
 
-		if (env.flags & LBF_NEED_BREAK) {
-			env.flags &= ~LBF_NEED_BREAK;
-			goto more_balance;
-		}
-
 		/*
 		 * some other cpu did the load balance for us.
 		 */
 		if (cur_ld_moved && env.dst_cpu != smp_processor_id())
 			resched_cpu(env.dst_cpu);
 
+		if (env.flags & LBF_NEED_BREAK) {
+			env.flags &= ~LBF_NEED_BREAK;
+			goto more_balance;
+		}
+
 		/*
 		 * Revisit (affine) tasks on src_cpu that couldn't be moved to
 		 * us and move them to an alternate dst_cpu in our sched_group
@@ -5092,14 +5115,17 @@ more_balance:
 		 * moreover subsequent load balance cycles should correct the
 		 * excess load moved.
 		 */
-		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
-				lb_iterations++ < max_lb_iterations) {
+		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
 
 			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
 			env.dst_cpu	 = env.new_dst_cpu;
 			env.flags	&= ~LBF_SOME_PINNED;
 			env.loop	 = 0;
 			env.loop_break	 = sched_nr_migrate_break;
+
+			/* Prevent to re-select dst_cpu via env's cpus */
+			cpumask_clear_cpu(env.dst_cpu, env.cpus);
+
 			/*
 			 * Go back to "more_balance" rather than "redo" since we
 			 * need to continue with same src_cpu.
@@ -5220,8 +5246,6 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
 		return;
 
-	update_rq_runnable_avg(this_rq, 1);
-
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
 	 */
@@ -5396,13 +5420,16 @@ static inline void set_cpu_sd_state_busy(void)
 	struct sched_domain *sd;
 	int cpu = smp_processor_id();
 
-	if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-		return;
-	clear_bit(NOHZ_IDLE, nohz_flags(cpu));
-
 	rcu_read_lock();
-	for_each_domain(cpu, sd)
+	sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+
+	if (!sd || !sd->nohz_idle)
+		goto unlock;
+	sd->nohz_idle = 0;
+
+	for (; sd; sd = sd->parent)
 		atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+unlock:
 	rcu_read_unlock();
 }
 
@@ -5411,13 +5438,16 @@ void set_cpu_sd_state_idle(void)
 	struct sched_domain *sd;
 	int cpu = smp_processor_id();
 
-	if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-		return;
-	set_bit(NOHZ_IDLE, nohz_flags(cpu));
-
 	rcu_read_lock();
-	for_each_domain(cpu, sd)
+	sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+
+	if (!sd || sd->nohz_idle)
+		goto unlock;
+	sd->nohz_idle = 1;
+
+	for (; sd; sd = sd->parent)
 		atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+unlock:
 	rcu_read_unlock();
 }
 
@@ -5469,7 +5499,7 @@ void update_max_interval(void)
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
  *
- * Balancing parameters are set up in arch_init_sched_domains.
+ * Balancing parameters are set up in init_sched_domains.
  */
 static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 {
@@ -5507,10 +5537,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
 			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
-				 * We've pulled tasks over so either we're no
-				 * longer idle.
+				 * The LBF_SOME_PINNED logic could have changed
+				 * env->dst_cpu, so we can't know our idle
+				 * state even if we migrated tasks. Update it.
 				 */
-				idle = CPU_NOT_IDLE;
+				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
 			}
 			sd->last_balance = jiffies;
 		}
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1ad1d2b5395f..99399f8e4799 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -46,13 +46,6 @@ SCHED_FEAT(DOUBLE_TICK, false)
 SCHED_FEAT(LB_BIAS, true)
 
 /*
- * Spin-wait on mutex acquisition when the mutex owner is running on
- * another cpu -- assumes that when the owner is running, it will soon
- * release the lock. Decreases scheduling overhead.
- */
-SCHED_FEAT(OWNER_SPIN, true)
-
-/*
  * Decrement CPU power based on time not spent running tasks
  */
 SCHED_FEAT(NONTASK_POWER, true)
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index b6baf370cae9..b8ce77328341 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -13,6 +13,16 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
+
+static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
+{
+	idle_exit_fair(rq);
+}
+
+static void post_schedule_idle(struct rq *rq)
+{
+	idle_enter_fair(rq);
+}
 #endif /* CONFIG_SMP */
 /*
  * Idle tasks are unconditionally rescheduled:
@@ -25,6 +35,10 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
+#ifdef CONFIG_SMP
+	/* Trigger the post schedule to do an idle_enter for CFS */
+	rq->post_schedule = 1;
+#endif
 	return rq->idle;
 }
 
@@ -86,6 +100,8 @@ const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
+	.pre_schedule		= pre_schedule_idle,
+	.post_schedule		= post_schedule_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index eb363aa5d83c..24dc29897749 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -8,6 +8,7 @@
 #include <linux/tick.h>
 
 #include "cpupri.h"
+#include "cpuacct.h"
 
 extern __read_mostly int scheduler_running;
 
@@ -951,14 +952,6 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-/* Time spent by the tasks of the cpu accounting group executing in ... */
-enum cpuacct_stat_index {
-	CPUACCT_STAT_USER,	/* ... user mode */
-	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
-
-	CPUACCT_STAT_NSTATS,
-};
-
 #define ENQUEUE_WAKEUP		1
 #define ENQUEUE_HEAD		2
 #ifdef CONFIG_SMP
@@ -1032,6 +1025,18 @@ extern void update_group_power(struct sched_domain *sd, int cpu);
 extern void trigger_load_balance(struct rq *rq, int cpu);
 extern void idle_balance(int this_cpu, struct rq *this_rq);
 
+/*
+ * Only depends on SMP, FAIR_GROUP_SCHED may be removed when runnable_avg
+ * becomes useful in lb
+ */
+#if defined(CONFIG_FAIR_GROUP_SCHED)
+extern void idle_enter_fair(struct rq *this_rq);
+extern void idle_exit_fair(struct rq *this_rq);
+#else
+static inline void idle_enter_fair(struct rq *this_rq) {}
+static inline void idle_exit_fair(struct rq *this_rq) {}
+#endif
+
 #else	/* CONFIG_SMP */
 
 static inline void idle_balance(int cpu, struct rq *rq)
@@ -1055,45 +1060,6 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 
 extern void update_idle_cpu_load(struct rq *this_rq);
 
-#ifdef CONFIG_CGROUP_CPUACCT
-#include <linux/cgroup.h>
-/* track cpu usage of a group of tasks and its child groups */
-struct cpuacct {
-	struct cgroup_subsys_state css;
-	/* cpuusage holds pointer to a u64-type object on every cpu */
-	u64 __percpu *cpuusage;
-	struct kernel_cpustat __percpu *cpustat;
-};
-
-extern struct cgroup_subsys cpuacct_subsys;
-extern struct cpuacct root_cpuacct;
-
-/* return cpu accounting group corresponding to this container */
-static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
-{
-	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-/* return cpu accounting group to which this task belongs */
-static inline struct cpuacct *task_ca(struct task_struct *tsk)
-{
-	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-static inline struct cpuacct *parent_ca(struct cpuacct *ca)
-{
-	if (!ca || !ca->css.cgroup->parent)
-		return NULL;
-	return cgroup_ca(ca->css.cgroup->parent);
-}
-
-extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
-#else
-static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
-#endif
-
 #ifdef CONFIG_PARAVIRT
 static inline u64 steal_ticks(u64 steal)
 {
@@ -1348,7 +1314,6 @@ extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
 enum rq_nohz_flag_bits {
 	NOHZ_TICK_STOPPED,
 	NOHZ_BALANCE_KICK,
-	NOHZ_IDLE,
 };
 
 #define nohz_flags(cpu)	(&cpu_rq(cpu)->nohz_flags)
diff --git a/kernel/signal.c b/kernel/signal.c
index 2ec870a4c3c4..598dc06be421 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -485,6 +485,9 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 		if (force_default || ka->sa.sa_handler != SIG_IGN)
 			ka->sa.sa_handler = SIG_DFL;
 		ka->sa.sa_flags = 0;
+#ifdef __ARCH_HAS_SA_RESTORER
+		ka->sa.sa_restorer = NULL;
+#endif
 		sigemptyset(&ka->sa.sa_mask);
 		ka++;
 	}
@@ -2682,7 +2685,7 @@ static int do_sigpending(void *set, unsigned long sigsetsize)
 /**
  *  sys_rt_sigpending - examine a pending signal that has been raised
  *			while blocked
- *  @set: stores pending signals
+ *  @uset: stores pending signals
  *  @sigsetsize: size of sigset_t type or larger
  */
 SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize)
@@ -2945,7 +2948,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 
 static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
-	struct siginfo info;
+	struct siginfo info = {};
 
 	info.si_signo = sig;
 	info.si_errno = 0;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index b9bde5727829..02fc5c933673 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -131,7 +131,7 @@ static int smpboot_thread_fn(void *data)
 			continue;
 		}
 
-		//BUG_ON(td->cpu != smp_processor_id());
+		BUG_ON(td->cpu != smp_processor_id());
 
 		/* Check for state change setup */
 		switch (td->status) {
@@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
 	}
 	get_task_struct(tsk);
 	*per_cpu_ptr(ht->store, cpu) = tsk;
-	if (ht->create)
-		ht->create(cpu);
+	if (ht->create) {
+		/*
+		 * Make sure that the task has actually scheduled out
+		 * into park position, before calling the create
+		 * callback. At least the migration thread callback
+		 * requires that the task is off the runqueue.
+		 */
+		if (!wait_task_inactive(tsk, TASK_PARKED))
+			WARN_ON(1);
+		else
+			ht->create(cpu);
+	}
 	return 0;
 }
 
@@ -209,6 +219,8 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp
 {
 	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
 
+	if (ht->pre_unpark)
+		ht->pre_unpark(cpu);
 	kthread_unpark(tsk);
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 8b1446d4a4db..51a09d56e78b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -323,18 +323,10 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-	if (!force_irqthreads) {
-#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
+	if (!force_irqthreads)
 		__do_softirq();
-#else
-		do_softirq();
-#endif
-	} else {
-		__local_bh_disable((unsigned long)__builtin_return_address(0),
-				SOFTIRQ_OFFSET);
+	else
 		wakeup_softirqd();
-		__local_bh_enable(SOFTIRQ_OFFSET);
-	}
 }
 
 static inline void tick_irq_exit(void)
@@ -355,15 +347,20 @@ static inline void tick_irq_exit(void)
  */
 void irq_exit(void)
 {
+#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
+	local_irq_disable();
+#else
+	WARN_ON_ONCE(!irqs_disabled());
+#endif
+
 	account_irq_exit_time(current);
 	trace_hardirq_exit();
-	sub_preempt_count(IRQ_EXIT_OFFSET);
+	sub_preempt_count(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
 	tick_irq_exit();
 	rcu_irq_exit();
-	sched_preempt_enable_no_resched();
 }
 
 /*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 95d178c62d5a..c09f2955ae30 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -336,7 +336,7 @@ static struct smp_hotplug_thread cpu_stop_threads = {
 	.create			= cpu_stop_create,
 	.setup			= cpu_stop_unpark,
 	.park			= cpu_stop_park,
-	.unpark			= cpu_stop_unpark,
+	.pre_unpark		= cpu_stop_unpark,
 	.selfparking		= true,
 };
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 81f56445fba9..0da73cf73e60 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -324,7 +324,6 @@ void kernel_restart_prepare(char *cmd)
 	system_state = SYSTEM_RESTART;
 	usermodehelper_disable();
 	device_shutdown();
-	syscore_shutdown();
 }
 
 /**
@@ -370,6 +369,7 @@ void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
 	disable_nonboot_cpus();
+	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
 	else
@@ -395,6 +395,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
+	disable_nonboot_cpus();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -2185,9 +2186,8 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
 
 char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
 
-static int __orderly_poweroff(void)
+static int __orderly_poweroff(bool force)
 {
-	int argc;
 	char **argv;
 	static char *envp[] = {
 		"HOME=/",
@@ -2196,20 +2196,40 @@ static int __orderly_poweroff(void)
 	};
 	int ret;
 
-	argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
-	if (argv == NULL) {
+	argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
+	if (argv) {
+		ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+		argv_free(argv);
+	} else {
 		printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
-		       __func__, poweroff_cmd);
-		return -ENOMEM;
+					 __func__, poweroff_cmd);
+		ret = -ENOMEM;
 	}
 
-	ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_WAIT_EXEC,
-				      NULL, NULL, NULL);
-	argv_free(argv);
+	if (ret && force) {
+		printk(KERN_WARNING "Failed to start orderly shutdown: "
+					"forcing the issue\n");
+		/*
+		 * I guess this should try to kick off some daemon to sync and
+		 * poweroff asap.  Or not even bother syncing if we're doing an
+		 * emergency shutdown?
+		 */
+		emergency_sync();
+		kernel_power_off();
+	}
 
 	return ret;
 }
 
+static bool poweroff_force;
+
+static void poweroff_work_func(struct work_struct *work)
+{
+	__orderly_poweroff(poweroff_force);
+}
+
+static DECLARE_WORK(poweroff_work, poweroff_work_func);
+
 /**
  * orderly_poweroff - Trigger an orderly system poweroff
  * @force: force poweroff if command execution fails
@@ -2219,21 +2239,9 @@ static int __orderly_poweroff(void)
  */
 int orderly_poweroff(bool force)
 {
-	int ret = __orderly_poweroff();
-
-	if (ret && force) {
-		printk(KERN_WARNING "Failed to start orderly shutdown: "
-		       "forcing the issue\n");
-
-		/*
-		 * I guess this should try to kick off some daemon to sync and
-		 * poweroff asap.  Or not even bother syncing if we're doing an
-		 * emergency shutdown?
-		 */
-		emergency_sync();
-		kernel_power_off();
-	}
-
-	return ret;
+	if (force) /* do not override the pending "true" */
+		poweroff_force = true;
+	schedule_work(&poweroff_work);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(orderly_poweroff);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index afc1dc60f3f8..9edcf456e0fc 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -106,7 +106,6 @@ extern unsigned int core_pipe_limit;
 #endif
 extern int pid_max;
 extern int pid_max_min, pid_max_max;
-extern int sysctl_drop_caches;
 extern int percpu_pagelist_fraction;
 extern int compat_log;
 extern int latencytop_enabled;
@@ -1430,6 +1429,20 @@ static struct ctl_table vm_table[] = {
 		.extra2		= &one,
 	},
 #endif
+	{
+		.procname	= "user_reserve_kbytes",
+		.data		= &sysctl_user_reserve_kbytes,
+		.maxlen		= sizeof(sysctl_user_reserve_kbytes),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "admin_reserve_kbytes",
+		.data		= &sysctl_admin_reserve_kbytes,
+		.maxlen		= sizeof(sysctl_admin_reserve_kbytes),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{ }
 };
 
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index f8b11a283171..12d6ebbfdd83 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -365,7 +365,7 @@ int init_test_probes(void)
 	target2 = kprobe_target2;
 
 	do {
-		rand1 = random32();
+		rand1 = prandom_u32();
 	} while (rand1 <= div_factor);
 
 	printk(KERN_INFO "Kprobe smoke test started\n");
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index a3a3123f6272..40c10502c9e9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -67,7 +67,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
-	if ((tick_broadcast_device.evtdev &&
+	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (tick_broadcast_device.evtdev &&
 	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 192473b22799..5e9efd4b83a4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -176,6 +176,8 @@ config IRQSOFF_TRACER
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	select RING_BUFFER_ALLOW_SWAP
+	select TRACER_SNAPSHOT
+	select TRACER_SNAPSHOT_PER_CPU_SWAP
 	help
 	  This option measures the time spent in irqs-off critical
 	  sections, with microsecond accuracy.
@@ -198,6 +200,8 @@ config PREEMPT_TRACER
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	select RING_BUFFER_ALLOW_SWAP
+	select TRACER_SNAPSHOT
+	select TRACER_SNAPSHOT_PER_CPU_SWAP
 	help
 	  This option measures the time spent in preemption-off critical
 	  sections, with microsecond accuracy.
@@ -217,6 +221,7 @@ config SCHED_TRACER
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
+	select TRACER_SNAPSHOT
 	help
 	  This tracer tracks the latency of the highest priority task
 	  to be scheduled in, starting from the point it has woken up.
@@ -248,6 +253,27 @@ config TRACER_SNAPSHOT
 	      echo 1 > /sys/kernel/debug/tracing/snapshot
 	      cat snapshot
 
+config TRACER_SNAPSHOT_PER_CPU_SWAP
+        bool "Allow snapshot to swap per CPU"
+	depends on TRACER_SNAPSHOT
+	select RING_BUFFER_ALLOW_SWAP
+	help
+	  Allow doing a snapshot of a single CPU buffer instead of a
+	  full swap (all buffers). If this is set, then the following is
+	  allowed:
+
+	      echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
+
+	  After which, only the tracing buffer for CPU 2 was swapped with
+	  the main tracing buffer, and the other CPU buffers remain the same.
+
+	  When this is enabled, this adds a little more overhead to the
+	  trace recording, as it needs to add some checks to synchronize
+	  recording with swaps. But this does not affect the performance
+	  of the overall system. This is enabled by default when the preempt
+	  or irq latency tracers are enabled, as those need to swap as well
+	  and already adds the overhead (plus a lot more).
+
 config TRACE_BRANCH_PROFILING
 	bool
 	select GENERIC_TRACER
@@ -414,24 +440,28 @@ config PROBE_EVENTS
 	def_bool n
 
 config DYNAMIC_FTRACE
-	bool "enable/disable ftrace tracepoints dynamically"
+	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
 	default y
 	help
-          This option will modify all the calls to ftrace dynamically
-	  (will patch them out of the binary image and replace them
-	  with a No-Op instruction) as they are called. A table is
-	  created to dynamically enable them again.
+	  This option will modify all the calls to function tracing
+	  dynamically (will patch them out of the binary image and
+	  replace them with a No-Op instruction) on boot up. During
+	  compile time, a table is made of all the locations that ftrace
+	  can function trace, and this table is linked into the kernel
+	  image. When this is enabled, functions can be individually
+	  enabled, and the functions not enabled will not affect
+	  performance of the system.
+
+	  See the files in /sys/kernel/debug/tracing:
+	    available_filter_functions
+	    set_ftrace_filter
+	    set_ftrace_notrace
 
 	  This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
 	  otherwise has native performance as long as no tracing is active.
 
-	  The changes to the code are done by a kernel thread that
-	  wakes up once a second and checks to see if any ftrace calls
-	  were made. If so, it runs stop_machine (stops all CPUS)
-	  and modifies the code to jump over the call to ftrace.
-
 config DYNAMIC_FTRACE_WITH_REGS
 	def_bool y
 	depends on DYNAMIC_FTRACE
@@ -520,6 +550,29 @@ config RING_BUFFER_BENCHMARK
 
 	  If unsure, say N.
 
+config RING_BUFFER_STARTUP_TEST
+       bool "Ring buffer startup self test"
+       depends on RING_BUFFER
+       help
+         Run a simple self test on the ring buffer on boot up. Late in the
+	 kernel boot sequence, the test will start that kicks off
+	 a thread per cpu. Each thread will write various size events
+	 into the ring buffer. Another thread is created to send IPIs
+	 to each of the threads, where the IPI handler will also write
+	 to the ring buffer, to test/stress the nesting ability.
+	 If any anomalies are discovered, a warning will be displayed
+	 and all ring buffers will be disabled.
+
+	 The test runs for 10 seconds. This will slow your boot time
+	 by at least 10 more seconds.
+
+	 At the end of the test, statics and more checks are done.
+	 It will output the stats of each per cpu buffer. What
+	 was written, the sizes, what was read, what was lost, and
+	 other similar details.
+
+	 If unsure, say N
+
 endif # FTRACE
 
 endif # TRACING_SUPPORT
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9e5b8c272eec..ed58a3216a6d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -72,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
-		buffer = blk_tr->buffer;
+		buffer = blk_tr->trace_buffer.buffer;
 		pc = preempt_count();
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
@@ -218,7 +218,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
-		buffer = blk_tr->buffer;
+		buffer = blk_tr->trace_buffer.buffer;
 		pc = preempt_count();
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
@@ -739,12 +739,6 @@ static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
 				      struct request *rq)
 {
-	struct blk_trace *bt = q->blk_trace;
-
-	/* if control ever passes through here, it's a request based driver */
-	if (unlikely(bt && !bt->rq_based))
-		bt->rq_based = true;
-
 	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
 }
 
@@ -780,24 +774,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
 	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
 }
 
-static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error)
+static void blk_add_trace_bio_complete(void *ignore,
+				       struct request_queue *q, struct bio *bio,
+				       int error)
 {
-	struct request_queue *q;
-	struct blk_trace *bt;
-
-	if (!bio->bi_bdev)
-		return;
-
-	q = bdev_get_queue(bio->bi_bdev);
-	bt = q->blk_trace;
-
-	/*
-	 * Request based drivers will generate both rq and bio completions.
-	 * Ignore bio ones.
-	 */
-	if (likely(!bt) || bt->rq_based)
-		return;
-
 	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
 }
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ab25b88aae56..8a5c017bb50c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -66,7 +66,7 @@
 
 static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
-	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
 };
 
 /* ftrace_enabled is a method to turn ftrace on or off */
@@ -486,7 +486,6 @@ struct ftrace_profile_stat {
 #define PROFILES_PER_PAGE					\
 	(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
 
-static int ftrace_profile_bits __read_mostly;
 static int ftrace_profile_enabled __read_mostly;
 
 /* ftrace_profile_lock - synchronize the enable and disable of the profiler */
@@ -494,7 +493,8 @@ static DEFINE_MUTEX(ftrace_profile_lock);
 
 static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
 
-#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+#define FTRACE_PROFILE_HASH_BITS 10
+#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS)
 
 static void *
 function_stat_next(void *v, int idx)
@@ -676,7 +676,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 
 	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
 
-	for (i = 0; i < pages; i++) {
+	for (i = 1; i < pages; i++) {
 		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!pg->next)
 			goto out_free;
@@ -694,7 +694,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 		free_page(tmp);
 	}
 
-	free_page((unsigned long)stat->pages);
 	stat->pages = NULL;
 	stat->start = NULL;
 
@@ -725,13 +724,6 @@ static int ftrace_profile_init_cpu(int cpu)
 	if (!stat->hash)
 		return -ENOMEM;
 
-	if (!ftrace_profile_bits) {
-		size--;
-
-		for (; size; size >>= 1)
-			ftrace_profile_bits++;
-	}
-
 	/* Preallocate the function profiling pages */
 	if (ftrace_profile_pages_init(stat) < 0) {
 		kfree(stat->hash);
@@ -764,7 +756,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
 	struct hlist_head *hhd;
 	unsigned long key;
 
-	key = hash_long(ip, ftrace_profile_bits);
+	key = hash_long(ip, FTRACE_PROFILE_HASH_BITS);
 	hhd = &stat->hash[key];
 
 	if (hlist_empty(hhd))
@@ -783,7 +775,7 @@ static void ftrace_add_profile(struct ftrace_profile_stat *stat,
 {
 	unsigned long key;
 
-	key = hash_long(rec->ip, ftrace_profile_bits);
+	key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS);
 	hlist_add_head_rcu(&rec->node, &stat->hash[key]);
 }
 
@@ -1053,6 +1045,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+	loff_t ret;
+
+	if (file->f_mode & FMODE_READ)
+		ret = seq_lseek(file, offset, whence);
+	else
+		file->f_pos = ret = 1;
+
+	return ret;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -1067,7 +1072,7 @@ struct ftrace_func_probe {
 	unsigned long		flags;
 	unsigned long		ip;
 	void			*data;
-	struct rcu_head		rcu;
+	struct list_head	free_list;
 };
 
 struct ftrace_func_entry {
@@ -1317,7 +1322,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	struct hlist_head *hhd;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *new_hash;
-	unsigned long key;
 	int size = src->count;
 	int bits = 0;
 	int ret;
@@ -1360,10 +1364,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	for (i = 0; i < size; i++) {
 		hhd = &src->buckets[i];
 		hlist_for_each_entry_safe(entry, tn, hhd, hlist) {
-			if (bits > 0)
-				key = hash_long(entry->ip, bits);
-			else
-				key = 0;
 			remove_hash_entry(src, entry);
 			__add_hash_entry(new_hash, entry);
 		}
@@ -2613,7 +2613,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
  * routine, you can use ftrace_filter_write() for the write
  * routine if @flag has FTRACE_ITER_FILTER set, or
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_regex_lseek() should be used as the lseek routine, and
+ * ftrace_filter_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
  */
 int
@@ -2697,19 +2697,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 				 inode, file);
 }
 
-loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
-{
-	loff_t ret;
-
-	if (file->f_mode & FMODE_READ)
-		ret = seq_lseek(file, offset, whence);
-	else
-		file->f_pos = ret = 1;
-
-	return ret;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
 	int matched = 0;
@@ -2974,28 +2961,27 @@ static void __disable_ftrace_function_probe(void)
 }
 
 
-static void ftrace_free_entry_rcu(struct rcu_head *rhp)
+static void ftrace_free_entry(struct ftrace_func_probe *entry)
 {
-	struct ftrace_func_probe *entry =
-		container_of(rhp, struct ftrace_func_probe, rcu);
-
 	if (entry->ops->free)
-		entry->ops->free(&entry->data);
+		entry->ops->free(entry->ops, entry->ip, &entry->data);
 	kfree(entry);
 }
 
-
 int
 register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
 	struct ftrace_func_probe *entry;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
 	int type, len, not;
 	unsigned long key;
 	int count = 0;
 	char *search;
+	int ret;
 
 	type = filter_parse_regex(glob, strlen(glob), &search, &not);
 	len = strlen(search);
@@ -3006,8 +2992,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&ftrace_lock);
 
-	if (unlikely(ftrace_disabled))
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash) {
+		count = -ENOMEM;
+		goto out_unlock;
+	}
+
+	if (unlikely(ftrace_disabled)) {
+		count = -ENODEV;
 		goto out_unlock;
+	}
 
 	do_for_each_ftrace_rec(pg, rec) {
 
@@ -3031,14 +3025,21 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		 * for each function we find. We call the callback
 		 * to give the caller an opportunity to do so.
 		 */
-		if (ops->callback) {
-			if (ops->callback(rec->ip, &entry->data) < 0) {
+		if (ops->init) {
+			if (ops->init(ops, rec->ip, &entry->data) < 0) {
 				/* caller does not like this func */
 				kfree(entry);
 				continue;
 			}
 		}
 
+		ret = enter_record(hash, rec, 0);
+		if (ret < 0) {
+			kfree(entry);
+			count = ret;
+			goto out_unlock;
+		}
+
 		entry->ops = ops;
 		entry->ip = rec->ip;
 
@@ -3046,10 +3047,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]);
 
 	} while_for_each_ftrace_rec();
+
+	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	if (ret < 0)
+		count = ret;
+
 	__enable_ftrace_function_probe();
 
  out_unlock:
 	mutex_unlock(&ftrace_lock);
+	free_ftrace_hash(hash);
 
 	return count;
 }
@@ -3063,7 +3070,12 @@ static void
 __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				  void *data, int flags)
 {
+	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
+	struct ftrace_func_probe *p;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct list_head free_list;
+	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
 	int type = MATCH_FULL;
@@ -3084,6 +3096,14 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	}
 
 	mutex_lock(&ftrace_lock);
+
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash)
+		/* Hmm, should report this somehow */
+		goto out_unlock;
+
+	INIT_LIST_HEAD(&free_list);
+
 	for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
 		struct hlist_head *hhd = &ftrace_func_hash[i];
 
@@ -3104,12 +3124,30 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 					continue;
 			}
 
-			hlist_del(&entry->node);
-			call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+			rec_entry = ftrace_lookup_ip(hash, entry->ip);
+			/* It is possible more than one entry had this ip */
+			if (rec_entry)
+				free_hash_entry(hash, rec_entry);
+
+			hlist_del_rcu(&entry->node);
+			list_add(&entry->free_list, &free_list);
 		}
 	}
 	__disable_ftrace_function_probe();
+	/*
+	 * Remove after the disable is called. Otherwise, if the last
+	 * probe is removed, a null hash means *all enabled*.
+	 */
+	ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	synchronize_sched();
+	list_for_each_entry_safe(entry, p, &free_list, free_list) {
+		list_del(&entry->free_list);
+		ftrace_free_entry(entry);
+	}
+		
+ out_unlock:
 	mutex_unlock(&ftrace_lock);
+	free_ftrace_hash(hash);
 }
 
 void
@@ -3441,14 +3479,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
 
 static int __init set_ftrace_notrace(char *str)
 {
-	strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+	strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
 __setup("ftrace_notrace=", set_ftrace_notrace);
 
 static int __init set_ftrace_filter(char *str)
 {
-	strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+	strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
 __setup("ftrace_filter=", set_ftrace_filter);
@@ -3571,7 +3609,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3579,7 +3617,7 @@ static const struct file_operations ftrace_notrace_fops = {
 	.open = ftrace_notrace_open,
 	.read = seq_read,
 	.write = ftrace_notrace_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3737,7 +3775,8 @@ out:
 	if (fail)
 		return -EINVAL;
 
-	ftrace_graph_filter_enabled = 1;
+	ftrace_graph_filter_enabled = !!(*idx);
+
 	return 0;
 }
 
@@ -3784,8 +3823,8 @@ static const struct file_operations ftrace_graph_fops = {
 	.open		= ftrace_graph_open,
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_graph_release,
-	.llseek		= seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -4131,7 +4170,8 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	preempt_disable_notrace();
 	trace_recursion_set(TRACE_CONTROL_BIT);
 	do_for_each_ftrace_op(op, ftrace_control_list) {
-		if (!ftrace_function_local_disabled(op) &&
+		if (!(op->flags & FTRACE_OPS_FL_STUB) &&
+		    !ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
@@ -4439,7 +4479,7 @@ static const struct file_operations ftrace_pid_fops = {
 	.open		= ftrace_pid_open,
 	.write		= ftrace_pid_write,
 	.read		= seq_read,
-	.llseek		= seq_lseek,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_pid_release,
 };
 
@@ -4555,12 +4595,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 		ftrace_startup_sysctl();
 
 		/* we are starting ftrace again */
-		if (ftrace_ops_list != &ftrace_list_end) {
-			if (ftrace_ops_list->next == &ftrace_list_end)
-				ftrace_trace_function = ftrace_ops_list->func;
-			else
-				ftrace_trace_function = ftrace_ops_list_func;
-		}
+		if (ftrace_ops_list != &ftrace_list_end)
+			update_ftrace_function();
 
 	} else {
 		/* stopping ftrace calls (just send to ftrace_stub) */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6989df2ba194..b59aea2c48c2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -8,13 +8,16 @@
 #include <linux/trace_clock.h>
 #include <linux/trace_seq.h>
 #include <linux/spinlock.h>
+#include <linux/irq_work.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/kthread.h>	/* for self test */
 #include <linux/kmemcheck.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
@@ -444,6 +447,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 	return ret;
 }
 
+struct rb_irq_work {
+	struct irq_work			work;
+	wait_queue_head_t		waiters;
+	bool				waiters_pending;
+};
+
 /*
  * head_page == tail_page && head == tail then buffer is empty.
  */
@@ -478,6 +487,8 @@ struct ring_buffer_per_cpu {
 	struct list_head		new_pages; /* new pages to add */
 	struct work_struct		update_pages_work;
 	struct completion		update_done;
+
+	struct rb_irq_work		irq_work;
 };
 
 struct ring_buffer {
@@ -497,6 +508,8 @@ struct ring_buffer {
 	struct notifier_block		cpu_notify;
 #endif
 	u64				(*clock)(void);
+
+	struct rb_irq_work		irq_work;
 };
 
 struct ring_buffer_iter {
@@ -508,6 +521,118 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 };
 
+/*
+ * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
+ *
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * ring buffer waiters queue.
+ */
+static void rb_wake_up_waiters(struct irq_work *work)
+{
+	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
+
+	wake_up_all(&rbwork->waiters);
+}
+
+/**
+ * ring_buffer_wait - wait for input to the ring buffer
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ */
+void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	DEFINE_WAIT(wait);
+	struct rb_irq_work *work;
+
+	/*
+	 * Depending on what the caller is waiting for, either any
+	 * data in any cpu buffer, or a specific buffer, put the
+	 * caller on the appropriate wait queue.
+	 */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		work = &buffer->irq_work;
+	else {
+		cpu_buffer = buffer->buffers[cpu];
+		work = &cpu_buffer->irq_work;
+	}
+
+
+	prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	work->waiters_pending = true;
+
+	if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) ||
+	    (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu)))
+		schedule();
+
+	finish_wait(&work->waiters, &wait);
+}
+
+/**
+ * ring_buffer_poll_wait - poll on buffer input
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ * @filp: the file descriptor
+ * @poll_table: The poll descriptor
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ *
+ * Returns POLLIN | POLLRDNORM if data exists in the buffers,
+ * zero otherwise.
+ */
+int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
+			  struct file *filp, poll_table *poll_table)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct rb_irq_work *work;
+
+	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
+	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
+		return POLLIN | POLLRDNORM;
+
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		work = &buffer->irq_work;
+	else {
+		cpu_buffer = buffer->buffers[cpu];
+		work = &cpu_buffer->irq_work;
+	}
+
+	work->waiters_pending = true;
+	poll_wait(filp, &work->waiters, poll_table);
+
+	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
+	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
 /* buffer may be either ring_buffer or ring_buffer_per_cpu */
 #define RB_WARN_ON(b, cond)						\
 	({								\
@@ -1063,6 +1188,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 	cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 	INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler);
 	init_completion(&cpu_buffer->update_done);
+	init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters);
+	init_waitqueue_head(&cpu_buffer->irq_work.waiters);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
@@ -1158,6 +1285,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
 
+	init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters);
+	init_waitqueue_head(&buffer->irq_work.waiters);
+
 	/* need at least two pages */
 	if (nr_pages < 2)
 		nr_pages = 2;
@@ -1553,11 +1683,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			if (!cpu_buffer->nr_pages_to_update)
 				continue;
 
-			if (cpu_online(cpu))
+			/* The update must run on the CPU that is being updated. */
+			preempt_disable();
+			if (cpu == smp_processor_id() || !cpu_online(cpu)) {
+				rb_update_pages(cpu_buffer);
+				cpu_buffer->nr_pages_to_update = 0;
+			} else {
+				/*
+				 * Can not disable preemption for schedule_work_on()
+				 * on PREEMPT_RT.
+				 */
+				preempt_enable();
 				schedule_work_on(cpu,
 						&cpu_buffer->update_pages_work);
-			else
-				rb_update_pages(cpu_buffer);
+				preempt_disable();
+			}
+			preempt_enable();
 		}
 
 		/* wait for all the updates to complete */
@@ -1595,12 +1736,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 
 		get_online_cpus();
 
-		if (cpu_online(cpu_id)) {
+		preempt_disable();
+		/* The update must run on the CPU that is being updated. */
+		if (cpu_id == smp_processor_id() || !cpu_online(cpu_id))
+			rb_update_pages(cpu_buffer);
+		else {
+			/*
+			 * Can not disable preemption for schedule_work_on()
+			 * on PREEMPT_RT.
+			 */
+			preempt_enable();
 			schedule_work_on(cpu_id,
 					 &cpu_buffer->update_pages_work);
 			wait_for_completion(&cpu_buffer->update_done);
-		} else
-			rb_update_pages(cpu_buffer);
+			preempt_disable();
+		}
+		preempt_enable();
 
 		cpu_buffer->nr_pages_to_update = 0;
 		put_online_cpus();
@@ -2612,6 +2763,22 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 	rb_end_commit(cpu_buffer);
 }
 
+static __always_inline void
+rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
+{
+	if (buffer->irq_work.waiters_pending) {
+		buffer->irq_work.waiters_pending = false;
+		/* irq_work_queue() supplies it's own memory barriers */
+		irq_work_queue(&buffer->irq_work.work);
+	}
+
+	if (cpu_buffer->irq_work.waiters_pending) {
+		cpu_buffer->irq_work.waiters_pending = false;
+		/* irq_work_queue() supplies it's own memory barriers */
+		irq_work_queue(&cpu_buffer->irq_work.work);
+	}
+}
+
 /**
  * ring_buffer_unlock_commit - commit a reserved
  * @buffer: The buffer to commit to
@@ -2631,6 +2798,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	rb_commit(cpu_buffer, event);
 
+	rb_wakeups(buffer, cpu_buffer);
+
 	trace_recursive_unlock();
 
 	preempt_enable_notrace();
@@ -2803,6 +2972,8 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	rb_commit(cpu_buffer, event);
 
+	rb_wakeups(buffer, cpu_buffer);
+
 	ret = 0;
  out:
 	preempt_enable_notrace();
@@ -4467,3 +4638,320 @@ static int rb_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 #endif
+
+#ifdef CONFIG_RING_BUFFER_STARTUP_TEST
+/*
+ * This is a basic integrity check of the ring buffer.
+ * Late in the boot cycle this test will run when configured in.
+ * It will kick off a thread per CPU that will go into a loop
+ * writing to the per cpu ring buffer various sizes of data.
+ * Some of the data will be large items, some small.
+ *
+ * Another thread is created that goes into a spin, sending out
+ * IPIs to the other CPUs to also write into the ring buffer.
+ * this is to test the nesting ability of the buffer.
+ *
+ * Basic stats are recorded and reported. If something in the
+ * ring buffer should happen that's not expected, a big warning
+ * is displayed and all ring buffers are disabled.
+ */
+static struct task_struct *rb_threads[NR_CPUS] __initdata;
+
+struct rb_test_data {
+	struct ring_buffer	*buffer;
+	unsigned long		events;
+	unsigned long		bytes_written;
+	unsigned long		bytes_alloc;
+	unsigned long		bytes_dropped;
+	unsigned long		events_nested;
+	unsigned long		bytes_written_nested;
+	unsigned long		bytes_alloc_nested;
+	unsigned long		bytes_dropped_nested;
+	int			min_size_nested;
+	int			max_size_nested;
+	int			max_size;
+	int			min_size;
+	int			cpu;
+	int			cnt;
+};
+
+static struct rb_test_data rb_data[NR_CPUS] __initdata;
+
+/* 1 meg per cpu */
+#define RB_TEST_BUFFER_SIZE	1048576
+
+static char rb_string[] __initdata =
+	"abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\"
+	"?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890"
+	"!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv";
+
+static bool rb_test_started __initdata;
+
+struct rb_item {
+	int size;
+	char str[];
+};
+
+static __init int rb_write_something(struct rb_test_data *data, bool nested)
+{
+	struct ring_buffer_event *event;
+	struct rb_item *item;
+	bool started;
+	int event_len;
+	int size;
+	int len;
+	int cnt;
+
+	/* Have nested writes different that what is written */
+	cnt = data->cnt + (nested ? 27 : 0);
+
+	/* Multiply cnt by ~e, to make some unique increment */
+	size = (data->cnt * 68 / 25) % (sizeof(rb_string) - 1);
+
+	len = size + sizeof(struct rb_item);
+
+	started = rb_test_started;
+	/* read rb_test_started before checking buffer enabled */
+	smp_rmb();
+
+	event = ring_buffer_lock_reserve(data->buffer, len);
+	if (!event) {
+		/* Ignore dropped events before test starts. */
+		if (started) {
+			if (nested)
+				data->bytes_dropped += len;
+			else
+				data->bytes_dropped_nested += len;
+		}
+		return len;
+	}
+
+	event_len = ring_buffer_event_length(event);
+
+	if (RB_WARN_ON(data->buffer, event_len < len))
+		goto out;
+
+	item = ring_buffer_event_data(event);
+	item->size = size;
+	memcpy(item->str, rb_string, size);
+
+	if (nested) {
+		data->bytes_alloc_nested += event_len;
+		data->bytes_written_nested += len;
+		data->events_nested++;
+		if (!data->min_size_nested || len < data->min_size_nested)
+			data->min_size_nested = len;
+		if (len > data->max_size_nested)
+			data->max_size_nested = len;
+	} else {
+		data->bytes_alloc += event_len;
+		data->bytes_written += len;
+		data->events++;
+		if (!data->min_size || len < data->min_size)
+			data->max_size = len;
+		if (len > data->max_size)
+			data->max_size = len;
+	}
+
+ out:
+	ring_buffer_unlock_commit(data->buffer, event);
+
+	return 0;
+}
+
+static __init int rb_test(void *arg)
+{
+	struct rb_test_data *data = arg;
+
+	while (!kthread_should_stop()) {
+		rb_write_something(data, false);
+		data->cnt++;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		/* Now sleep between a min of 100-300us and a max of 1ms */
+		usleep_range(((data->cnt % 3) + 1) * 100, 1000);
+	}
+
+	return 0;
+}
+
+static __init void rb_ipi(void *ignore)
+{
+	struct rb_test_data *data;
+	int cpu = smp_processor_id();
+
+	data = &rb_data[cpu];
+	rb_write_something(data, true);
+}
+
+static __init int rb_hammer_test(void *arg)
+{
+	while (!kthread_should_stop()) {
+
+		/* Send an IPI to all cpus to write data! */
+		smp_call_function(rb_ipi, NULL, 1);
+		/* No sleep, but for non preempt, let others run */
+		schedule();
+	}
+
+	return 0;
+}
+
+static __init int test_ringbuffer(void)
+{
+	struct task_struct *rb_hammer;
+	struct ring_buffer *buffer;
+	int cpu;
+	int ret = 0;
+
+	pr_info("Running ring buffer tests...\n");
+
+	buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE);
+	if (WARN_ON(!buffer))
+		return 0;
+
+	/* Disable buffer so that threads can't write to it yet */
+	ring_buffer_record_off(buffer);
+
+	for_each_online_cpu(cpu) {
+		rb_data[cpu].buffer = buffer;
+		rb_data[cpu].cpu = cpu;
+		rb_data[cpu].cnt = cpu;
+		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
+						 "rbtester/%d", cpu);
+		if (WARN_ON(!rb_threads[cpu])) {
+			pr_cont("FAILED\n");
+			ret = -1;
+			goto out_free;
+		}
+
+		kthread_bind(rb_threads[cpu], cpu);
+ 		wake_up_process(rb_threads[cpu]);
+	}
+
+	/* Now create the rb hammer! */
+	rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
+	if (WARN_ON(!rb_hammer)) {
+		pr_cont("FAILED\n");
+		ret = -1;
+		goto out_free;
+	}
+
+	ring_buffer_record_on(buffer);
+	/*
+	 * Show buffer is enabled before setting rb_test_started.
+	 * Yes there's a small race window where events could be
+	 * dropped and the thread wont catch it. But when a ring
+	 * buffer gets enabled, there will always be some kind of
+	 * delay before other CPUs see it. Thus, we don't care about
+	 * those dropped events. We care about events dropped after
+	 * the threads see that the buffer is active.
+	 */
+	smp_wmb();
+	rb_test_started = true;
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	/* Just run for 10 seconds */;
+	schedule_timeout(10 * HZ);
+
+	kthread_stop(rb_hammer);
+
+ out_free:
+	for_each_online_cpu(cpu) {
+		if (!rb_threads[cpu])
+			break;
+		kthread_stop(rb_threads[cpu]);
+	}
+	if (ret) {
+		ring_buffer_free(buffer);
+		return ret;
+	}
+
+	/* Report! */
+	pr_info("finished\n");
+	for_each_online_cpu(cpu) {
+		struct ring_buffer_event *event;
+		struct rb_test_data *data = &rb_data[cpu];
+		struct rb_item *item;
+		unsigned long total_events;
+		unsigned long total_dropped;
+		unsigned long total_written;
+		unsigned long total_alloc;
+		unsigned long total_read = 0;
+		unsigned long total_size = 0;
+		unsigned long total_len = 0;
+		unsigned long total_lost = 0;
+		unsigned long lost;
+		int big_event_size;
+		int small_event_size;
+
+		ret = -1;
+
+		total_events = data->events + data->events_nested;
+		total_written = data->bytes_written + data->bytes_written_nested;
+		total_alloc = data->bytes_alloc + data->bytes_alloc_nested;
+		total_dropped = data->bytes_dropped + data->bytes_dropped_nested;
+
+		big_event_size = data->max_size + data->max_size_nested;
+		small_event_size = data->min_size + data->min_size_nested;
+
+		pr_info("CPU %d:\n", cpu);
+		pr_info("              events:    %ld\n", total_events);
+		pr_info("       dropped bytes:    %ld\n", total_dropped);
+		pr_info("       alloced bytes:    %ld\n", total_alloc);
+		pr_info("       written bytes:    %ld\n", total_written);
+		pr_info("       biggest event:    %d\n", big_event_size);
+		pr_info("      smallest event:    %d\n", small_event_size);
+
+		if (RB_WARN_ON(buffer, total_dropped))
+			break;
+
+		ret = 0;
+
+		while ((event = ring_buffer_consume(buffer, cpu, NULL, &lost))) {
+			total_lost += lost;
+			item = ring_buffer_event_data(event);
+			total_len += ring_buffer_event_length(event);
+			total_size += item->size + sizeof(struct rb_item);
+			if (memcmp(&item->str[0], rb_string, item->size) != 0) {
+				pr_info("FAILED!\n");
+				pr_info("buffer had: %.*s\n", item->size, item->str);
+				pr_info("expected:   %.*s\n", item->size, rb_string);
+				RB_WARN_ON(buffer, 1);
+				ret = -1;
+				break;
+			}
+			total_read++;
+		}
+		if (ret)
+			break;
+
+		ret = -1;
+
+		pr_info("         read events:   %ld\n", total_read);
+		pr_info("         lost events:   %ld\n", total_lost);
+		pr_info("        total events:   %ld\n", total_lost + total_read);
+		pr_info("  recorded len bytes:   %ld\n", total_len);
+		pr_info(" recorded size bytes:   %ld\n", total_size);
+		if (total_lost)
+			pr_info(" With dropped events, record len and size may not match\n"
+				" alloced and written from above\n");
+		if (!total_lost) {
+			if (RB_WARN_ON(buffer, total_len != total_alloc ||
+				       total_size != total_written))
+				break;
+		}
+		if (RB_WARN_ON(buffer, total_lost + total_read != total_events))
+			break;
+
+		ret = 0;
+	}
+	if (!ret)
+		pr_info("Ring buffer PASSED!\n");
+
+	ring_buffer_free(buffer);
+	return 0;
+}
+
+late_initcall(test_ringbuffer);
+#endif /* CONFIG_RING_BUFFER_STARTUP_TEST */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c2e2c2310374..ae6fa2d1cdf7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1,7 +1,7 @@
 /*
  * ring buffer based function tracer
  *
- * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2007-2012 Steven Rostedt <srostedt@redhat.com>
  * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
  *
  * Originally taken from the RT patch by:
@@ -19,7 +19,6 @@
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
-#include <linux/irq_work.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
@@ -48,7 +47,7 @@
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
  */
-int ring_buffer_expanded;
+bool ring_buffer_expanded;
 
 /*
  * We need to change this state when a selftest is running.
@@ -87,14 +86,6 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
 static DEFINE_PER_CPU(bool, trace_cmdline_save);
 
 /*
- * When a reader is waiting for data, then this variable is
- * set to true.
- */
-static bool trace_wakeup_needed;
-
-static struct irq_work trace_work_wakeup;
-
-/*
  * Kill all tracing for good (never come back).
  * It is initialized to 1 but will turn to zero if the initialization
  * of the tracer is successful. But that is the only place that sets
@@ -130,12 +121,14 @@ static int tracing_set_tracer(const char *buf);
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
+static bool allocate_snapshot;
+
 static int __init set_cmdline_ftrace(char *str)
 {
-	strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+	strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
 	/* We are using ftrace early, expand it */
-	ring_buffer_expanded = 1;
+	ring_buffer_expanded = true;
 	return 1;
 }
 __setup("ftrace=", set_cmdline_ftrace);
@@ -156,13 +149,22 @@ static int __init set_ftrace_dump_on_oops(char *str)
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
+static int __init boot_alloc_snapshot(char *str)
+{
+	allocate_snapshot = true;
+	/* We also need the main ring buffer expanded */
+	ring_buffer_expanded = true;
+	return 1;
+}
+__setup("alloc_snapshot", boot_alloc_snapshot);
+
 
 static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
 static char *trace_boot_options __initdata;
 
 static int __init set_trace_boot_options(char *str)
 {
-	strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+	strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
 	trace_boot_options = trace_boot_options_buf;
 	return 0;
 }
@@ -189,7 +191,7 @@ unsigned long long ns2usecs(cycle_t nsec)
  */
 static struct trace_array	global_trace;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+LIST_HEAD(ftrace_trace_arrays);
 
 int filter_current_check_discard(struct ring_buffer *buffer,
 				 struct ftrace_event_call *call, void *rec,
@@ -204,29 +206,15 @@ cycle_t ftrace_now(int cpu)
 	u64 ts;
 
 	/* Early boot up does not have a buffer yet */
-	if (!global_trace.buffer)
+	if (!global_trace.trace_buffer.buffer)
 		return trace_clock_local();
 
-	ts = ring_buffer_time_stamp(global_trace.buffer, cpu);
-	ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts);
+	ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu);
+	ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts);
 
 	return ts;
 }
 
-/*
- * The max_tr is used to snapshot the global_trace when a maximum
- * latency is reached. Some tracers will use this to store a maximum
- * trace while it continues examining live traces.
- *
- * The buffers for the max_tr are set up the same as the global_trace.
- * When a snapshot is taken, the link list of the max_tr is swapped
- * with the link list of the global_trace and the buffers are reset for
- * the global_trace so the tracing can continue.
- */
-static struct trace_array	max_tr;
-
-static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
-
 int tracing_is_enabled(void)
 {
 	return tracing_is_on();
@@ -249,9 +237,6 @@ static unsigned long		trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
 /* trace_types holds a link list of available tracers. */
 static struct tracer		*trace_types __read_mostly;
 
-/* current_trace points to the tracer that is currently active */
-static struct tracer		*current_trace __read_mostly = &nop_trace;
-
 /*
  * trace_types_lock is used to protect the trace_types list.
  */
@@ -285,13 +270,13 @@ static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
 
 static inline void trace_access_lock(int cpu)
 {
-	if (cpu == TRACE_PIPE_ALL_CPU) {
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		/* gain it for accessing the whole ring buffer. */
 		down_write(&all_cpu_access_lock);
 	} else {
 		/* gain it for accessing a cpu ring buffer. */
 
-		/* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+		/* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */
 		down_read(&all_cpu_access_lock);
 
 		/* Secondly block other access to this @cpu ring buffer. */
@@ -301,7 +286,7 @@ static inline void trace_access_lock(int cpu)
 
 static inline void trace_access_unlock(int cpu)
 {
-	if (cpu == TRACE_PIPE_ALL_CPU) {
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		up_write(&all_cpu_access_lock);
 	} else {
 		mutex_unlock(&per_cpu(cpu_access_lock, cpu));
@@ -339,30 +324,11 @@ static inline void trace_access_lock_init(void)
 
 #endif
 
-/* trace_wait is a waitqueue for tasks blocked on trace_poll */
-static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
-
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
 	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
-	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS;
-
-static int trace_stop_count;
-static DEFINE_RAW_SPINLOCK(tracing_start_lock);
-
-/**
- * trace_wake_up - wake up tasks waiting for trace input
- *
- * Schedules a delayed work to wake up any task that is blocked on the
- * trace_wait queue. These is used with trace_poll for tasks polling the
- * trace.
- */
-static void trace_wake_up(struct irq_work *work)
-{
-	wake_up_all(&trace_wait);
-
-}
+	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION;
 
 /**
  * tracing_on - enable tracing buffers
@@ -372,8 +338,8 @@ static void trace_wake_up(struct irq_work *work)
  */
 void tracing_on(void)
 {
-	if (global_trace.buffer)
-		ring_buffer_record_on(global_trace.buffer);
+	if (global_trace.trace_buffer.buffer)
+		ring_buffer_record_on(global_trace.trace_buffer.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
@@ -385,6 +351,196 @@ void tracing_on(void)
 EXPORT_SYMBOL_GPL(tracing_on);
 
 /**
+ * __trace_puts - write a constant string into the trace buffer.
+ * @ip:	   The address of the caller
+ * @str:   The constant string to write
+ * @size:  The size of the string.
+ */
+int __trace_puts(unsigned long ip, const char *str, int size)
+{
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct print_entry *entry;
+	unsigned long irq_flags;
+	int alloc;
+
+	alloc = sizeof(*entry) + size + 2; /* possible \n added */
+
+	local_save_flags(irq_flags);
+	buffer = global_trace.trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
+					  irq_flags, preempt_count());
+	if (!event)
+		return 0;
+
+	entry = ring_buffer_event_data(event);
+	entry->ip = ip;
+
+	memcpy(&entry->buf, str, size);
+
+	/* Add a newline if necessary */
+	if (entry->buf[size - 1] != '\n') {
+		entry->buf[size] = '\n';
+		entry->buf[size + 1] = '\0';
+	} else
+		entry->buf[size] = '\0';
+
+	__buffer_unlock_commit(buffer, event);
+
+	return size;
+}
+EXPORT_SYMBOL_GPL(__trace_puts);
+
+/**
+ * __trace_bputs - write the pointer to a constant string into trace buffer
+ * @ip:	   The address of the caller
+ * @str:   The constant string to write to the buffer to
+ */
+int __trace_bputs(unsigned long ip, const char *str)
+{
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct bputs_entry *entry;
+	unsigned long irq_flags;
+	int size = sizeof(struct bputs_entry);
+
+	local_save_flags(irq_flags);
+	buffer = global_trace.trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
+					  irq_flags, preempt_count());
+	if (!event)
+		return 0;
+
+	entry = ring_buffer_event_data(event);
+	entry->ip			= ip;
+	entry->str			= str;
+
+	__buffer_unlock_commit(buffer, event);
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(__trace_bputs);
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+/**
+ * trace_snapshot - take a snapshot of the current buffer.
+ *
+ * This causes a swap between the snapshot buffer and the current live
+ * tracing buffer. You can use this to take snapshots of the live
+ * trace when some condition is triggered, but continue to trace.
+ *
+ * Note, make sure to allocate the snapshot with either
+ * a tracing_snapshot_alloc(), or by doing it manually
+ * with: echo 1 > /sys/kernel/debug/tracing/snapshot
+ *
+ * If the snapshot buffer is not allocated, it will stop tracing.
+ * Basically making a permanent snapshot.
+ */
+void tracing_snapshot(void)
+{
+	struct trace_array *tr = &global_trace;
+	struct tracer *tracer = tr->current_trace;
+	unsigned long flags;
+
+	if (in_nmi()) {
+		internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n");
+		internal_trace_puts("*** snapshot is being ignored        ***\n");
+		return;
+	}
+
+	if (!tr->allocated_snapshot) {
+		internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n");
+		internal_trace_puts("*** stopping trace here!   ***\n");
+		tracing_off();
+		return;
+	}
+
+	/* Note, snapshot can not be used when the tracer uses it */
+	if (tracer->use_max_tr) {
+		internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n");
+		internal_trace_puts("*** Can not use snapshot (sorry) ***\n");
+		return;
+	}
+
+	local_irq_save(flags);
+	update_max_tr(tr, current, smp_processor_id());
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot);
+
+static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
+					struct trace_buffer *size_buf, int cpu_id);
+static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);
+
+static int alloc_snapshot(struct trace_array *tr)
+{
+	int ret;
+
+	if (!tr->allocated_snapshot) {
+
+		/* allocate spare buffer */
+		ret = resize_buffer_duplicate_size(&tr->max_buffer,
+				   &tr->trace_buffer, RING_BUFFER_ALL_CPUS);
+		if (ret < 0)
+			return ret;
+
+		tr->allocated_snapshot = true;
+	}
+
+	return 0;
+}
+
+void free_snapshot(struct trace_array *tr)
+{
+	/*
+	 * We don't free the ring buffer. instead, resize it because
+	 * The max_tr ring buffer has some state (e.g. ring->clock) and
+	 * we want preserve it.
+	 */
+	ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
+	set_buffer_entries(&tr->max_buffer, 1);
+	tracing_reset_online_cpus(&tr->max_buffer);
+	tr->allocated_snapshot = false;
+}
+
+/**
+ * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
+ *
+ * This is similar to trace_snapshot(), but it will allocate the
+ * snapshot buffer if it isn't already allocated. Use this only
+ * where it is safe to sleep, as the allocation may sleep.
+ *
+ * This causes a swap between the snapshot buffer and the current live
+ * tracing buffer. You can use this to take snapshots of the live
+ * trace when some condition is triggered, but continue to trace.
+ */
+void tracing_snapshot_alloc(void)
+{
+	struct trace_array *tr = &global_trace;
+	int ret;
+
+	ret = alloc_snapshot(tr);
+	if (WARN_ON(ret < 0))
+		return;
+
+	tracing_snapshot();
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
+#else
+void tracing_snapshot(void)
+{
+	WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot);
+void tracing_snapshot_alloc(void)
+{
+	/* Give warning */
+	tracing_snapshot();
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+/**
  * tracing_off - turn off tracing buffers
  *
  * This function stops the tracing buffers from recording data.
@@ -394,8 +550,8 @@ EXPORT_SYMBOL_GPL(tracing_on);
  */
 void tracing_off(void)
 {
-	if (global_trace.buffer)
-		ring_buffer_record_off(global_trace.buffer);
+	if (global_trace.trace_buffer.buffer)
+		ring_buffer_record_off(global_trace.trace_buffer.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
@@ -411,8 +567,8 @@ EXPORT_SYMBOL_GPL(tracing_off);
  */
 int tracing_is_on(void)
 {
-	if (global_trace.buffer)
-		return ring_buffer_record_is_on(global_trace.buffer);
+	if (global_trace.trace_buffer.buffer)
+		return ring_buffer_record_is_on(global_trace.trace_buffer.buffer);
 	return !global_trace.buffer_disabled;
 }
 EXPORT_SYMBOL_GPL(tracing_is_on);
@@ -479,6 +635,7 @@ static const char *trace_options[] = {
 	"disable_on_free",
 	"irq-info",
 	"markers",
+	"function-trace",
 	NULL
 };
 
@@ -490,6 +647,8 @@ static struct {
 	{ trace_clock_local,	"local",	1 },
 	{ trace_clock_global,	"global",	1 },
 	{ trace_clock_counter,	"counter",	0 },
+	{ trace_clock_jiffies,	"uptime",	1 },
+	{ trace_clock,		"perf",		1 },
 	ARCH_TRACE_CLOCKS
 };
 
@@ -670,13 +829,14 @@ unsigned long __read_mostly	tracing_max_latency;
 static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-	struct trace_array_cpu *data = tr->data[cpu];
-	struct trace_array_cpu *max_data;
+	struct trace_buffer *trace_buf = &tr->trace_buffer;
+	struct trace_buffer *max_buf = &tr->max_buffer;
+	struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu);
+	struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu);
 
-	max_tr.cpu = cpu;
-	max_tr.time_start = data->preempt_timestamp;
+	max_buf->cpu = cpu;
+	max_buf->time_start = data->preempt_timestamp;
 
-	max_data = max_tr.data[cpu];
 	max_data->saved_latency = tracing_max_latency;
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
@@ -704,23 +864,24 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-	struct ring_buffer *buf = tr->buffer;
+	struct ring_buffer *buf;
 
-	if (trace_stop_count)
+	if (tr->stop_count)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (!current_trace->allocated_snapshot) {
+	if (!tr->allocated_snapshot) {
 		/* Only the nop tracer should hit this when disabling */
-		WARN_ON_ONCE(current_trace != &nop_trace);
+		WARN_ON_ONCE(tr->current_trace != &nop_trace);
 		return;
 	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
-	tr->buffer = max_tr.buffer;
-	max_tr.buffer = buf;
+	buf = tr->trace_buffer.buffer;
+	tr->trace_buffer.buffer = tr->max_buffer.buffer;
+	tr->max_buffer.buffer = buf;
 
 	__update_max_tr(tr, tsk, cpu);
 	arch_spin_unlock(&ftrace_max_lock);
@@ -739,16 +900,19 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	int ret;
 
-	if (trace_stop_count)
+	if (tr->stop_count)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (WARN_ON_ONCE(!current_trace->allocated_snapshot))
+	if (!tr->allocated_snapshot) {
+		/* Only the nop tracer should hit this when disabling */
+		WARN_ON_ONCE(tr->current_trace != &nop_trace);
 		return;
+	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
-	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
+	ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
 
 	if (ret == -EBUSY) {
 		/*
@@ -757,7 +921,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		 * the max trace buffer (no one writes directly to it)
 		 * and flag that it failed.
 		 */
-		trace_array_printk(&max_tr, _THIS_IP_,
+		trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_,
 			"Failed to swap buffers due to commit in progress\n");
 	}
 
@@ -770,37 +934,78 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 static void default_wait_pipe(struct trace_iterator *iter)
 {
-	DEFINE_WAIT(wait);
+	/* Iterators are static, they should be filled or empty */
+	if (trace_buffer_iter(iter, iter->cpu_file))
+		return;
 
-	prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
+	ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+}
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+static int run_tracer_selftest(struct tracer *type)
+{
+	struct trace_array *tr = &global_trace;
+	struct tracer *saved_tracer = tr->current_trace;
+	int ret;
+
+	if (!type->selftest || tracing_selftest_disabled)
+		return 0;
 
 	/*
-	 * The events can happen in critical sections where
-	 * checking a work queue can cause deadlocks.
-	 * After adding a task to the queue, this flag is set
-	 * only to notify events to try to wake up the queue
-	 * using irq_work.
-	 *
-	 * We don't clear it even if the buffer is no longer
-	 * empty. The flag only causes the next event to run
-	 * irq_work to do the work queue wake up. The worse
-	 * that can happen if we race with !trace_empty() is that
-	 * an event will cause an irq_work to try to wake up
-	 * an empty queue.
-	 *
-	 * There's no reason to protect this flag either, as
-	 * the work queue and irq_work logic will do the necessary
-	 * synchronization for the wake ups. The only thing
-	 * that is necessary is that the wake up happens after
-	 * a task has been queued. It's OK for spurious wake ups.
+	 * Run a selftest on this tracer.
+	 * Here we reset the trace buffer, and set the current
+	 * tracer to be this tracer. The tracer can then run some
+	 * internal tracing to verify that everything is in order.
+	 * If we fail, we do not register this tracer.
 	 */
-	trace_wakeup_needed = true;
+	tracing_reset_online_cpus(&tr->trace_buffer);
 
-	if (trace_empty(iter))
-		schedule();
+	tr->current_trace = type;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (type->use_max_tr) {
+		/* If we expanded the buffers, make sure the max is expanded too */
+		if (ring_buffer_expanded)
+			ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size,
+					   RING_BUFFER_ALL_CPUS);
+		tr->allocated_snapshot = true;
+	}
+#endif
 
-	finish_wait(&trace_wait, &wait);
+	/* the test is responsible for initializing and enabling */
+	pr_info("Testing tracer %s: ", type->name);
+	ret = type->selftest(type, tr);
+	/* the test is responsible for resetting too */
+	tr->current_trace = saved_tracer;
+	if (ret) {
+		printk(KERN_CONT "FAILED!\n");
+		/* Add the warning after printing 'FAILED' */
+		WARN_ON(1);
+		return -1;
+	}
+	/* Only reset on passing, to avoid touching corrupted buffers */
+	tracing_reset_online_cpus(&tr->trace_buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (type->use_max_tr) {
+		tr->allocated_snapshot = false;
+
+		/* Shrink the max buffer again */
+		if (ring_buffer_expanded)
+			ring_buffer_resize(tr->max_buffer.buffer, 1,
+					   RING_BUFFER_ALL_CPUS);
+	}
+#endif
+
+	printk(KERN_CONT "PASSED\n");
+	return 0;
 }
+#else
+static inline int run_tracer_selftest(struct tracer *type)
+{
+	return 0;
+}
+#endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 /**
  * register_tracer - register a tracer with the ftrace system.
@@ -847,57 +1052,9 @@ int register_tracer(struct tracer *type)
 	if (!type->wait_pipe)
 		type->wait_pipe = default_wait_pipe;
 
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
-	if (type->selftest && !tracing_selftest_disabled) {
-		struct tracer *saved_tracer = current_trace;
-		struct trace_array *tr = &global_trace;
-
-		/*
-		 * Run a selftest on this tracer.
-		 * Here we reset the trace buffer, and set the current
-		 * tracer to be this tracer. The tracer can then run some
-		 * internal tracing to verify that everything is in order.
-		 * If we fail, we do not register this tracer.
-		 */
-		tracing_reset_online_cpus(tr);
-
-		current_trace = type;
-
-		if (type->use_max_tr) {
-			/* If we expanded the buffers, make sure the max is expanded too */
-			if (ring_buffer_expanded)
-				ring_buffer_resize(max_tr.buffer, trace_buf_size,
-						   RING_BUFFER_ALL_CPUS);
-			type->allocated_snapshot = true;
-		}
-
-		/* the test is responsible for initializing and enabling */
-		pr_info("Testing tracer %s: ", type->name);
-		ret = type->selftest(type, tr);
-		/* the test is responsible for resetting too */
-		current_trace = saved_tracer;
-		if (ret) {
-			printk(KERN_CONT "FAILED!\n");
-			/* Add the warning after printing 'FAILED' */
-			WARN_ON(1);
-			goto out;
-		}
-		/* Only reset on passing, to avoid touching corrupted buffers */
-		tracing_reset_online_cpus(tr);
-
-		if (type->use_max_tr) {
-			type->allocated_snapshot = false;
-
-			/* Shrink the max buffer again */
-			if (ring_buffer_expanded)
-				ring_buffer_resize(max_tr.buffer, 1,
-						   RING_BUFFER_ALL_CPUS);
-		}
-
-		printk(KERN_CONT "PASSED\n");
-	}
-#endif
+	ret = run_tracer_selftest(type);
+	if (ret < 0)
+		goto out;
 
 	type->next = trace_types;
 	trace_types = type;
@@ -917,7 +1074,7 @@ int register_tracer(struct tracer *type)
 	tracing_set_tracer(type->name);
 	default_bootup_tracer = NULL;
 	/* disable other selftests, since this will break it. */
-	tracing_selftest_disabled = 1;
+	tracing_selftest_disabled = true;
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n",
 	       type->name);
@@ -927,9 +1084,9 @@ int register_tracer(struct tracer *type)
 	return ret;
 }
 
-void tracing_reset(struct trace_array *tr, int cpu)
+void tracing_reset(struct trace_buffer *buf, int cpu)
 {
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = buf->buffer;
 
 	if (!buffer)
 		return;
@@ -943,9 +1100,9 @@ void tracing_reset(struct trace_array *tr, int cpu)
 	ring_buffer_record_enable(buffer);
 }
 
-void tracing_reset_online_cpus(struct trace_array *tr)
+void tracing_reset_online_cpus(struct trace_buffer *buf)
 {
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = buf->buffer;
 	int cpu;
 
 	if (!buffer)
@@ -956,7 +1113,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	/* Make sure all commits have finished */
 	synchronize_sched();
 
-	tr->time_start = ftrace_now(tr->cpu);
+	buf->time_start = ftrace_now(buf->cpu);
 
 	for_each_online_cpu(cpu)
 		ring_buffer_reset_cpu(buffer, cpu);
@@ -966,12 +1123,21 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 
 void tracing_reset_current(int cpu)
 {
-	tracing_reset(&global_trace, cpu);
+	tracing_reset(&global_trace.trace_buffer, cpu);
 }
 
-void tracing_reset_current_online_cpus(void)
+void tracing_reset_all_online_cpus(void)
 {
-	tracing_reset_online_cpus(&global_trace);
+	struct trace_array *tr;
+
+	mutex_lock(&trace_types_lock);
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		tracing_reset_online_cpus(&tr->trace_buffer);
+#ifdef CONFIG_TRACER_MAX_TRACE
+		tracing_reset_online_cpus(&tr->max_buffer);
+#endif
+	}
+	mutex_unlock(&trace_types_lock);
 }
 
 #define SAVED_CMDLINES 128
@@ -994,7 +1160,7 @@ static void trace_init_cmdlines(void)
 
 int is_tracing_stopped(void)
 {
-	return trace_stop_count;
+	return global_trace.stop_count;
 }
 
 /**
@@ -1026,12 +1192,12 @@ void tracing_start(void)
 	if (tracing_disabled)
 		return;
 
-	raw_spin_lock_irqsave(&tracing_start_lock, flags);
-	if (--trace_stop_count) {
-		if (trace_stop_count < 0) {
+	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
+	if (--global_trace.stop_count) {
+		if (global_trace.stop_count < 0) {
 			/* Someone screwed up their debugging */
 			WARN_ON_ONCE(1);
-			trace_stop_count = 0;
+			global_trace.stop_count = 0;
 		}
 		goto out;
 	}
@@ -1039,19 +1205,52 @@ void tracing_start(void)
 	/* Prevent the buffers from switching */
 	arch_spin_lock(&ftrace_max_lock);
 
-	buffer = global_trace.buffer;
+	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
-	buffer = max_tr.buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+	buffer = global_trace.max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
+#endif
 
 	arch_spin_unlock(&ftrace_max_lock);
 
 	ftrace_start();
  out:
-	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
+	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+}
+
+static void tracing_start_tr(struct trace_array *tr)
+{
+	struct ring_buffer *buffer;
+	unsigned long flags;
+
+	if (tracing_disabled)
+		return;
+
+	/* If global, we need to also start the max tracer */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		return tracing_start();
+
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+
+	if (--tr->stop_count) {
+		if (tr->stop_count < 0) {
+			/* Someone screwed up their debugging */
+			WARN_ON_ONCE(1);
+			tr->stop_count = 0;
+		}
+		goto out;
+	}
+
+	buffer = tr->trace_buffer.buffer;
+	if (buffer)
+		ring_buffer_record_enable(buffer);
+
+ out:
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 /**
@@ -1066,25 +1265,48 @@ void tracing_stop(void)
 	unsigned long flags;
 
 	ftrace_stop();
-	raw_spin_lock_irqsave(&tracing_start_lock, flags);
-	if (trace_stop_count++)
+	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
+	if (global_trace.stop_count++)
 		goto out;
 
 	/* Prevent the buffers from switching */
 	arch_spin_lock(&ftrace_max_lock);
 
-	buffer = global_trace.buffer;
+	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
-	buffer = max_tr.buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+	buffer = global_trace.max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
+#endif
 
 	arch_spin_unlock(&ftrace_max_lock);
 
  out:
-	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
+	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
+{
+	struct ring_buffer *buffer;
+	unsigned long flags;
+
+	/* If global, we need to also stop the max tracer */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		return tracing_stop();
+
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (tr->stop_count++)
+		goto out;
+
+	buffer = tr->trace_buffer.buffer;
+	if (buffer)
+		ring_buffer_record_disable(buffer);
+
+ out:
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 void trace_stop_cmdline_recording(void);
@@ -1217,11 +1439,6 @@ void
 __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
 {
 	__this_cpu_write(trace_cmdline_save, true);
-	if (trace_wakeup_needed) {
-		trace_wakeup_needed = false;
-		/* irq_work_queue() supplies it's own memory barriers */
-		irq_work_queue(&trace_work_wakeup);
-	}
 	ring_buffer_unlock_commit(buffer, event);
 }
 
@@ -1245,11 +1462,23 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
 struct ring_buffer_event *
+trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
+			  struct ftrace_event_file *ftrace_file,
+			  int type, unsigned long len,
+			  unsigned long flags, int pc)
+{
+	*current_rb = ftrace_file->tr->trace_buffer.buffer;
+	return trace_buffer_lock_reserve(*current_rb,
+					 type, len, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
+
+struct ring_buffer_event *
 trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
 				  int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
-	*current_rb = global_trace.buffer;
+	*current_rb = global_trace.trace_buffer.buffer;
 	return trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
 }
@@ -1288,7 +1517,7 @@ trace_function(struct trace_array *tr,
 	       int pc)
 {
 	struct ftrace_event_call *call = &event_function;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -1429,13 +1658,14 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc)
 {
-	__ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
+	__ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL);
 }
 
 /**
  * trace_dump_stack - record a stack back trace in the trace buffer
+ * @skip: Number of functions to skip (helper handlers)
  */
-void trace_dump_stack(void)
+void trace_dump_stack(int skip)
 {
 	unsigned long flags;
 
@@ -1444,8 +1674,13 @@ void trace_dump_stack(void)
 
 	local_save_flags(flags);
 
-	/* skipping 3 traces, seems to get us at the caller of this function */
-	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL);
+	/*
+	 * Skip 3 more, seems to get us at the caller of
+	 * this function.
+	 */
+	skip += 3;
+	__ftrace_trace_stack(global_trace.trace_buffer.buffer,
+			     flags, skip, preempt_count(), NULL);
 }
 
 static DEFINE_PER_CPU(int, user_stack_count);
@@ -1615,7 +1850,7 @@ void trace_printk_init_buffers(void)
 	 * directly here. If the global_trace.buffer is already
 	 * allocated here, then this was called by module code.
 	 */
-	if (global_trace.buffer)
+	if (global_trace.trace_buffer.buffer)
 		tracing_start_cmdline_record();
 }
 
@@ -1675,7 +1910,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	local_save_flags(flags);
 	size = sizeof(*entry) + sizeof(u32) * len;
-	buffer = tr->buffer;
+	buffer = tr->trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
 					  flags, pc);
 	if (!event)
@@ -1698,27 +1933,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_array_printk(struct trace_array *tr,
-		       unsigned long ip, const char *fmt, ...)
-{
-	int ret;
-	va_list ap;
-
-	if (!(trace_flags & TRACE_ITER_PRINTK))
-		return 0;
-
-	va_start(ap, fmt);
-	ret = trace_array_vprintk(tr, ip, fmt, ap);
-	va_end(ap);
-	return ret;
-}
-
-int trace_array_vprintk(struct trace_array *tr,
-			unsigned long ip, const char *fmt, va_list args)
+static int
+__trace_array_vprintk(struct ring_buffer *buffer,
+		      unsigned long ip, const char *fmt, va_list args)
 {
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
-	struct ring_buffer *buffer;
 	int len = 0, size, pc;
 	struct print_entry *entry;
 	unsigned long flags;
@@ -1746,7 +1966,6 @@ int trace_array_vprintk(struct trace_array *tr,
 
 	local_save_flags(flags);
 	size = sizeof(*entry) + len + 1;
-	buffer = tr->buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					  flags, pc);
 	if (!event)
@@ -1767,6 +1986,42 @@ int trace_array_vprintk(struct trace_array *tr,
 	return len;
 }
 
+int trace_array_vprintk(struct trace_array *tr,
+			unsigned long ip, const char *fmt, va_list args)
+{
+	return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
+}
+
+int trace_array_printk(struct trace_array *tr,
+		       unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	va_start(ap, fmt);
+	ret = trace_array_vprintk(tr, ip, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+
+int trace_array_printk_buf(struct ring_buffer *buffer,
+			   unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	va_start(ap, fmt);
+	ret = __trace_array_vprintk(buffer, ip, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -1792,7 +2047,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+		event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts,
 					 lost_events);
 
 	if (event) {
@@ -1807,7 +2062,7 @@ static struct trace_entry *
 __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 		  unsigned long *missing_events, u64 *ent_ts)
 {
-	struct ring_buffer *buffer = iter->tr->buffer;
+	struct ring_buffer *buffer = iter->trace_buffer->buffer;
 	struct trace_entry *ent, *next = NULL;
 	unsigned long lost_events = 0, next_lost = 0;
 	int cpu_file = iter->cpu_file;
@@ -1820,7 +2075,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 	 * If we are in a per_cpu trace file, don't bother by iterating over
 	 * all cpu and peek directly.
 	 */
-	if (cpu_file > TRACE_PIPE_ALL_CPU) {
+	if (cpu_file > RING_BUFFER_ALL_CPUS) {
 		if (ring_buffer_empty_cpu(buffer, cpu_file))
 			return NULL;
 		ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
@@ -1884,7 +2139,7 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter)
 
 static void trace_consume(struct trace_iterator *iter)
 {
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+	ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts,
 			    &iter->lost_events);
 }
 
@@ -1917,13 +2172,12 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 {
-	struct trace_array *tr = iter->tr;
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter;
 	unsigned long entries = 0;
 	u64 ts;
 
-	tr->data[cpu]->skipped_entries = 0;
+	per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0;
 
 	buf_iter = trace_buffer_iter(iter, cpu);
 	if (!buf_iter)
@@ -1937,13 +2191,13 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 	 * by the timestamp being before the start of the buffer.
 	 */
 	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
-		if (ts >= iter->tr->time_start)
+		if (ts >= iter->trace_buffer->time_start)
 			break;
 		entries++;
 		ring_buffer_read(buf_iter, NULL);
 	}
 
-	tr->data[cpu]->skipped_entries = entries;
+	per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries;
 }
 
 /*
@@ -1953,6 +2207,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
 	struct trace_iterator *iter = m->private;
+	struct trace_array *tr = iter->tr;
 	int cpu_file = iter->cpu_file;
 	void *p = NULL;
 	loff_t l = 0;
@@ -1965,12 +2220,14 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	 * will point to the same string as current_trace->name.
 	 */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(current_trace && iter->trace->name != current_trace->name))
-		*iter->trace = *current_trace;
+	if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name))
+		*iter->trace = *tr->current_trace;
 	mutex_unlock(&trace_types_lock);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 	if (iter->snapshot && iter->trace->use_max_tr)
 		return ERR_PTR(-EBUSY);
+#endif
 
 	if (!iter->snapshot)
 		atomic_inc(&trace_record_cmdline_disabled);
@@ -1980,7 +2237,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		iter->cpu = 0;
 		iter->idx = -1;
 
-		if (cpu_file == TRACE_PIPE_ALL_CPU) {
+		if (cpu_file == RING_BUFFER_ALL_CPUS) {
 			for_each_tracing_cpu(cpu)
 				tracing_iter_reset(iter, cpu);
 		} else
@@ -2012,17 +2269,21 @@ static void s_stop(struct seq_file *m, void *p)
 {
 	struct trace_iterator *iter = m->private;
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 	if (iter->snapshot && iter->trace->use_max_tr)
 		return;
+#endif
 
 	if (!iter->snapshot)
 		atomic_dec(&trace_record_cmdline_disabled);
+
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
 
 static void
-get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries)
+get_total_entries(struct trace_buffer *buf,
+		  unsigned long *total, unsigned long *entries)
 {
 	unsigned long count;
 	int cpu;
@@ -2031,19 +2292,19 @@ get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *e
 	*entries = 0;
 
 	for_each_tracing_cpu(cpu) {
-		count = ring_buffer_entries_cpu(tr->buffer, cpu);
+		count = ring_buffer_entries_cpu(buf->buffer, cpu);
 		/*
 		 * If this buffer has skipped entries, then we hold all
 		 * entries for the trace and we need to ignore the
 		 * ones before the time stamp.
 		 */
-		if (tr->data[cpu]->skipped_entries) {
-			count -= tr->data[cpu]->skipped_entries;
+		if (per_cpu_ptr(buf->data, cpu)->skipped_entries) {
+			count -= per_cpu_ptr(buf->data, cpu)->skipped_entries;
 			/* total is the same as the entries */
 			*total += count;
 		} else
 			*total += count +
-				ring_buffer_overrun_cpu(tr->buffer, cpu);
+				ring_buffer_overrun_cpu(buf->buffer, cpu);
 		*entries += count;
 	}
 }
@@ -2060,27 +2321,27 @@ static void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
-static void print_event_info(struct trace_array *tr, struct seq_file *m)
+static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
 {
 	unsigned long total;
 	unsigned long entries;
 
-	get_total_entries(tr, &total, &entries);
+	get_total_entries(buf, &total, &entries);
 	seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu   #P:%d\n",
 		   entries, total, num_online_cpus());
 	seq_puts(m, "#\n");
 }
 
-static void print_func_help_header(struct trace_array *tr, struct seq_file *m)
+static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
 {
-	print_event_info(tr, m);
+	print_event_info(buf, m);
 	seq_puts(m, "#           TASK-PID   CPU#      TIMESTAMP  FUNCTION\n");
 	seq_puts(m, "#              | |       |          |         |\n");
 }
 
-static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m)
+static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
 {
-	print_event_info(tr, m);
+	print_event_info(buf, m);
 	seq_puts(m, "#                              _-----=> irqs-off\n");
 	seq_puts(m, "#                             / _----=> need-resched\n");
 	seq_puts(m, "#                            | / _---=> hardirq/softirq\n");
@@ -2094,16 +2355,16 @@ void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
 	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
-	struct trace_array *tr = iter->tr;
-	struct trace_array_cpu *data = tr->data[tr->cpu];
-	struct tracer *type = current_trace;
+	struct trace_buffer *buf = iter->trace_buffer;
+	struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu);
+	struct tracer *type = iter->trace;
 	unsigned long entries;
 	unsigned long total;
 	const char *name = "preemption";
 
 	name = type->name;
 
-	get_total_entries(tr, &total, &entries);
+	get_total_entries(buf, &total, &entries);
 
 	seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
 		   name, UTS_RELEASE);
@@ -2114,7 +2375,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		   nsecs_to_usecs(data->saved_latency),
 		   entries,
 		   total,
-		   tr->cpu,
+		   buf->cpu,
 #if defined(CONFIG_PREEMPT_NONE)
 		   "server",
 #elif defined(CONFIG_PREEMPT_VOLUNTARY)
@@ -2165,7 +2426,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
 	if (cpumask_test_cpu(iter->cpu, iter->started))
 		return;
 
-	if (iter->tr->data[iter->cpu]->skipped_entries)
+	if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
 		return;
 
 	cpumask_set_cpu(iter->cpu, iter->started);
@@ -2288,14 +2549,14 @@ int trace_empty(struct trace_iterator *iter)
 	int cpu;
 
 	/* If we are looking at one CPU buffer, only check that one */
-	if (iter->cpu_file != TRACE_PIPE_ALL_CPU) {
+	if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
 		cpu = iter->cpu_file;
 		buf_iter = trace_buffer_iter(iter, cpu);
 		if (buf_iter) {
 			if (!ring_buffer_iter_empty(buf_iter))
 				return 0;
 		} else {
-			if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+			if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu))
 				return 0;
 		}
 		return 1;
@@ -2307,7 +2568,7 @@ int trace_empty(struct trace_iterator *iter)
 			if (!ring_buffer_iter_empty(buf_iter))
 				return 0;
 		} else {
-			if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+			if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu))
 				return 0;
 		}
 	}
@@ -2331,6 +2592,11 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
 			return ret;
 	}
 
+	if (iter->ent->type == TRACE_BPUTS &&
+			trace_flags & TRACE_ITER_PRINTK &&
+			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+		return trace_print_bputs_msg_only(iter);
+
 	if (iter->ent->type == TRACE_BPRINT &&
 			trace_flags & TRACE_ITER_PRINTK &&
 			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
@@ -2385,9 +2651,9 @@ void trace_default_header(struct seq_file *m)
 	} else {
 		if (!(trace_flags & TRACE_ITER_VERBOSE)) {
 			if (trace_flags & TRACE_ITER_IRQ_INFO)
-				print_func_help_header_irq(iter->tr, m);
+				print_func_help_header_irq(iter->trace_buffer, m);
 			else
-				print_func_help_header(iter->tr, m);
+				print_func_help_header(iter->trace_buffer, m);
 		}
 	}
 }
@@ -2400,6 +2666,50 @@ static void test_ftrace_alive(struct seq_file *m)
 	seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
 }
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+static void show_snapshot_main_help(struct seq_file *m)
+{
+	seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
+	seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
+	seq_printf(m, "#                      Takes a snapshot of the main buffer.\n");
+	seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
+	seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
+	seq_printf(m, "#                       is not a '0' or '1')\n");
+}
+
+static void show_snapshot_percpu_help(struct seq_file *m)
+{
+	seq_printf(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n");
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+	seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
+	seq_printf(m, "#                      Takes a snapshot of the main buffer for this cpu.\n");
+#else
+	seq_printf(m, "# echo 1 > snapshot : Not supported with this kernel.\n");
+	seq_printf(m, "#                     Must use main snapshot file to allocate.\n");
+#endif
+	seq_printf(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n");
+	seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
+	seq_printf(m, "#                       is not a '0' or '1')\n");
+}
+
+static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
+{
+	if (iter->tr->allocated_snapshot)
+		seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
+	else
+		seq_printf(m, "#\n# * Snapshot is freed *\n#\n");
+
+	seq_printf(m, "# Snapshot commands:\n");
+	if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+		show_snapshot_main_help(m);
+	else
+		show_snapshot_percpu_help(m);
+}
+#else
+/* Should never be called */
+static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { }
+#endif
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2411,7 +2721,9 @@ static int s_show(struct seq_file *m, void *v)
 			seq_puts(m, "#\n");
 			test_ftrace_alive(m);
 		}
-		if (iter->trace && iter->trace->print_header)
+		if (iter->snapshot && trace_empty(iter))
+			print_snapshot_help(m, iter);
+		else if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
 		else
 			trace_default_header(m);
@@ -2452,7 +2764,8 @@ static const struct seq_operations tracer_seq_ops = {
 static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
-	long cpu_file = (long) inode->i_private;
+	struct trace_cpu *tc = inode->i_private;
+	struct trace_array *tr = tc->tr;
 	struct trace_iterator *iter;
 	int cpu;
 
@@ -2477,26 +2790,31 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (!iter->trace)
 		goto fail;
 
-	*iter->trace = *current_trace;
+	*iter->trace = *tr->current_trace;
 
 	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
 
-	if (current_trace->print_max || snapshot)
-		iter->tr = &max_tr;
+	iter->tr = tr;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	/* Currently only the top directory has a snapshot */
+	if (tr->current_trace->print_max || snapshot)
+		iter->trace_buffer = &tr->max_buffer;
 	else
-		iter->tr = &global_trace;
+#endif
+		iter->trace_buffer = &tr->trace_buffer;
 	iter->snapshot = snapshot;
 	iter->pos = -1;
 	mutex_init(&iter->mutex);
-	iter->cpu_file = cpu_file;
+	iter->cpu_file = tc->cpu;
 
 	/* Notify the tracer early; before we stop tracing. */
 	if (iter->trace && iter->trace->open)
 		iter->trace->open(iter);
 
 	/* Annotate start of buffers if we had overruns */
-	if (ring_buffer_overruns(iter->tr->buffer))
+	if (ring_buffer_overruns(iter->trace_buffer->buffer))
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
 	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
@@ -2505,12 +2823,12 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 
 	/* stop the trace while dumping if we are not opening "snapshot" */
 	if (!iter->snapshot)
-		tracing_stop();
+		tracing_stop_tr(tr);
 
-	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
+	if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
 			iter->buffer_iter[cpu] =
-				ring_buffer_read_prepare(iter->tr->buffer, cpu);
+				ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
 		}
 		ring_buffer_read_prepare_sync();
 		for_each_tracing_cpu(cpu) {
@@ -2520,12 +2838,14 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
-			ring_buffer_read_prepare(iter->tr->buffer, cpu);
+			ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
 		ring_buffer_read_prepare_sync();
 		ring_buffer_read_start(iter->buffer_iter[cpu]);
 		tracing_iter_reset(iter, cpu);
 	}
 
+	tr->ref++;
+
 	mutex_unlock(&trace_types_lock);
 
 	return iter;
@@ -2552,14 +2872,20 @@ static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = file->private_data;
 	struct trace_iterator *iter;
+	struct trace_array *tr;
 	int cpu;
 
 	if (!(file->f_mode & FMODE_READ))
 		return 0;
 
 	iter = m->private;
+	tr = iter->tr;
 
 	mutex_lock(&trace_types_lock);
+
+	WARN_ON(!tr->ref);
+	tr->ref--;
+
 	for_each_tracing_cpu(cpu) {
 		if (iter->buffer_iter[cpu])
 			ring_buffer_read_finish(iter->buffer_iter[cpu]);
@@ -2570,7 +2896,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	if (!iter->snapshot)
 		/* reenable tracing if it was previously enabled */
-		tracing_start();
+		tracing_start_tr(tr);
 	mutex_unlock(&trace_types_lock);
 
 	mutex_destroy(&iter->mutex);
@@ -2589,12 +2915,13 @@ static int tracing_open(struct inode *inode, struct file *file)
 	/* If this file was open for write, then erase contents */
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC)) {
-		long cpu = (long) inode->i_private;
+		struct trace_cpu *tc = inode->i_private;
+		struct trace_array *tr = tc->tr;
 
-		if (cpu == TRACE_PIPE_ALL_CPU)
-			tracing_reset_online_cpus(&global_trace);
+		if (tc->cpu == RING_BUFFER_ALL_CPUS)
+			tracing_reset_online_cpus(&tr->trace_buffer);
 		else
-			tracing_reset(&global_trace, cpu);
+			tracing_reset(&tr->trace_buffer, tc->cpu);
 	}
 
 	if (file->f_mode & FMODE_READ) {
@@ -2741,8 +3068,9 @@ static ssize_t
 tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		      size_t count, loff_t *ppos)
 {
-	int err, cpu;
+	struct trace_array *tr = filp->private_data;
 	cpumask_var_t tracing_cpumask_new;
+	int err, cpu;
 
 	if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
@@ -2762,13 +3090,13 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		 */
 		if (cpumask_test_cpu(cpu, tracing_cpumask) &&
 				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
-			atomic_inc(&global_trace.data[cpu]->disabled);
-			ring_buffer_record_disable_cpu(global_trace.buffer, cpu);
+			atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
+			ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu);
 		}
 		if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
 				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
-			atomic_dec(&global_trace.data[cpu]->disabled);
-			ring_buffer_record_enable_cpu(global_trace.buffer, cpu);
+			atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
+			ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
 		}
 	}
 	arch_spin_unlock(&ftrace_max_lock);
@@ -2797,12 +3125,13 @@ static const struct file_operations tracing_cpumask_fops = {
 static int tracing_trace_options_show(struct seq_file *m, void *v)
 {
 	struct tracer_opt *trace_opts;
+	struct trace_array *tr = m->private;
 	u32 tracer_flags;
 	int i;
 
 	mutex_lock(&trace_types_lock);
-	tracer_flags = current_trace->flags->val;
-	trace_opts = current_trace->flags->opts;
+	tracer_flags = tr->current_trace->flags->val;
+	trace_opts = tr->current_trace->flags->opts;
 
 	for (i = 0; trace_options[i]; i++) {
 		if (trace_flags & (1 << i))
@@ -2857,11 +3186,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 	return -EINVAL;
 }
 
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+	if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+		return -1;
+
+	return 0;
+}
+
+int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
 	/* do nothing if flag is already set */
 	if (!!(trace_flags & mask) == !!enabled)
-		return;
+		return 0;
+
+	/* Give the tracer a chance to approve the change */
+	if (tr->current_trace->flag_changed)
+		if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled))
+			return -EINVAL;
 
 	if (enabled)
 		trace_flags |= mask;
@@ -2871,18 +3214,24 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
 
-	if (mask == TRACE_ITER_OVERWRITE)
-		ring_buffer_change_overwrite(global_trace.buffer, enabled);
+	if (mask == TRACE_ITER_OVERWRITE) {
+		ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
+#ifdef CONFIG_TRACER_MAX_TRACE
+		ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled);
+#endif
+	}
 
 	if (mask == TRACE_ITER_PRINTK)
 		trace_printk_start_stop_comm(enabled);
+
+	return 0;
 }
 
-static int trace_set_options(char *option)
+static int trace_set_options(struct trace_array *tr, char *option)
 {
 	char *cmp;
 	int neg = 0;
-	int ret = 0;
+	int ret = -ENODEV;
 	int i;
 
 	cmp = strstrip(option);
@@ -2892,19 +3241,20 @@ static int trace_set_options(char *option)
 		cmp += 2;
 	}
 
+	mutex_lock(&trace_types_lock);
+
 	for (i = 0; trace_options[i]; i++) {
 		if (strcmp(cmp, trace_options[i]) == 0) {
-			set_tracer_flags(1 << i, !neg);
+			ret = set_tracer_flag(tr, 1 << i, !neg);
 			break;
 		}
 	}
 
 	/* If no option could be set, test the specific tracer options */
-	if (!trace_options[i]) {
-		mutex_lock(&trace_types_lock);
-		ret = set_tracer_option(current_trace, cmp, neg);
-		mutex_unlock(&trace_types_lock);
-	}
+	if (!trace_options[i])
+		ret = set_tracer_option(tr->current_trace, cmp, neg);
+
+	mutex_unlock(&trace_types_lock);
 
 	return ret;
 }
@@ -2913,7 +3263,10 @@ static ssize_t
 tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
 {
+	struct seq_file *m = filp->private_data;
+	struct trace_array *tr = m->private;
 	char buf[64];
+	int ret;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
@@ -2923,7 +3276,9 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 
 	buf[cnt] = 0;
 
-	trace_set_options(buf);
+	ret = trace_set_options(tr, buf);
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -2934,7 +3289,8 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file)
 {
 	if (tracing_disabled)
 		return -ENODEV;
-	return single_open(file, tracing_trace_options_show, NULL);
+
+	return single_open(file, tracing_trace_options_show, inode->i_private);
 }
 
 static const struct file_operations tracing_iter_fops = {
@@ -2947,20 +3303,84 @@ static const struct file_operations tracing_iter_fops = {
 
 static const char readme_msg[] =
 	"tracing mini-HOWTO:\n\n"
-	"# mount -t debugfs nodev /sys/kernel/debug\n\n"
-	"# cat /sys/kernel/debug/tracing/available_tracers\n"
-	"wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n"
-	"# cat /sys/kernel/debug/tracing/current_tracer\n"
-	"nop\n"
-	"# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n"
-	"# cat /sys/kernel/debug/tracing/current_tracer\n"
-	"wakeup\n"
-	"# cat /sys/kernel/debug/tracing/trace_options\n"
-	"noprint-parent nosym-offset nosym-addr noverbose\n"
-	"# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
-	"# echo 1 > /sys/kernel/debug/tracing/tracing_on\n"
-	"# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n"
-	"# echo 0 > /sys/kernel/debug/tracing/tracing_on\n"
+	"# echo 0 > tracing_on : quick way to disable tracing\n"
+	"# echo 1 > tracing_on : quick way to re-enable tracing\n\n"
+	" Important files:\n"
+	"  trace\t\t\t- The static contents of the buffer\n"
+	"\t\t\t  To clear the buffer write into this file: echo > trace\n"
+	"  trace_pipe\t\t- A consuming read to see the contents of the buffer\n"
+	"  current_tracer\t- function and latency tracers\n"
+	"  available_tracers\t- list of configured tracers for current_tracer\n"
+	"  buffer_size_kb\t- view and modify size of per cpu buffer\n"
+	"  buffer_total_size_kb  - view total size of all cpu buffers\n\n"
+	"  trace_clock\t\t-change the clock used to order events\n"
+	"       local:   Per cpu clock but may not be synced across CPUs\n"
+	"      global:   Synced across CPUs but slows tracing down.\n"
+	"     counter:   Not a clock, but just an increment\n"
+	"      uptime:   Jiffy counter from time of boot\n"
+	"        perf:   Same clock that perf events use\n"
+#ifdef CONFIG_X86_64
+	"     x86-tsc:   TSC cycle counter\n"
+#endif
+	"\n  trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
+	"  tracing_cpumask\t- Limit which CPUs to trace\n"
+	"  instances\t\t- Make sub-buffers with: mkdir instances/foo\n"
+	"\t\t\t  Remove sub-buffer with rmdir\n"
+	"  trace_options\t\t- Set format or modify how tracing happens\n"
+	"\t\t\t  Disable an option by adding a suffix 'no' to the option name\n"
+#ifdef CONFIG_DYNAMIC_FTRACE
+	"\n  available_filter_functions - list of functions that can be filtered on\n"
+	"  set_ftrace_filter\t- echo function name in here to only trace these functions\n"
+	"            accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"            modules: Can select a group via module\n"
+	"             Format: :mod:<module-name>\n"
+	"             example: echo :mod:ext3 > set_ftrace_filter\n"
+	"            triggers: a command to perform when function is hit\n"
+	"              Format: <function>:<trigger>[:count]\n"
+	"             trigger: traceon, traceoff\n"
+	"                      enable_event:<system>:<event>\n"
+	"                      disable_event:<system>:<event>\n"
+#ifdef CONFIG_STACKTRACE
+	"                      stacktrace\n"
+#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+	"                      snapshot\n"
+#endif
+	"             example: echo do_fault:traceoff > set_ftrace_filter\n"
+	"                      echo do_trap:traceoff:3 > set_ftrace_filter\n"
+	"             The first one will disable tracing every time do_fault is hit\n"
+	"             The second will disable tracing at most 3 times when do_trap is hit\n"
+	"               The first time do trap is hit and it disables tracing, the counter\n"
+	"               will decrement to 2. If tracing is already disabled, the counter\n"
+	"               will not decrement. It only decrements when the trigger did work\n"
+	"             To remove trigger without count:\n"
+	"               echo '!<function>:<trigger> > set_ftrace_filter\n"
+	"             To remove trigger with a count:\n"
+	"               echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
+	"  set_ftrace_notrace\t- echo function name in here to never trace.\n"
+	"            accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"            modules: Can select a group via module command :mod:\n"
+	"            Does not accept triggers\n"
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#ifdef CONFIG_FUNCTION_TRACER
+	"  set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n"
+#endif
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	"  set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
+	"  max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n"
+#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+	"\n  snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
+	"\t\t\t  Read the contents for more information\n"
+#endif
+#ifdef CONFIG_STACKTRACE
+	"  stack_trace\t\t- Shows the max stack trace when active\n"
+	"  stack_max_size\t- Shows current max stack size that was traced\n"
+	"\t\t\t  Write into this file to reset the max size (trigger a new trace)\n"
+#ifdef CONFIG_DYNAMIC_FTRACE
+	"  stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
+#endif
+#endif /* CONFIG_STACKTRACE */
 ;
 
 static ssize_t
@@ -3032,11 +3452,12 @@ static ssize_t
 tracing_set_trace_read(struct file *filp, char __user *ubuf,
 		       size_t cnt, loff_t *ppos)
 {
+	struct trace_array *tr = filp->private_data;
 	char buf[MAX_TRACER_SIZE+2];
 	int r;
 
 	mutex_lock(&trace_types_lock);
-	r = sprintf(buf, "%s\n", current_trace->name);
+	r = sprintf(buf, "%s\n", tr->current_trace->name);
 	mutex_unlock(&trace_types_lock);
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -3044,43 +3465,48 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
 
 int tracer_init(struct tracer *t, struct trace_array *tr)
 {
-	tracing_reset_online_cpus(tr);
+	tracing_reset_online_cpus(&tr->trace_buffer);
 	return t->init(tr);
 }
 
-static void set_buffer_entries(struct trace_array *tr, unsigned long val)
+static void set_buffer_entries(struct trace_buffer *buf, unsigned long val)
 {
 	int cpu;
+
 	for_each_tracing_cpu(cpu)
-		tr->data[cpu]->entries = val;
+		per_cpu_ptr(buf->data, cpu)->entries = val;
 }
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 /* resize @tr's buffer to the size of @size_tr's entries */
-static int resize_buffer_duplicate_size(struct trace_array *tr,
-					struct trace_array *size_tr, int cpu_id)
+static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
+					struct trace_buffer *size_buf, int cpu_id)
 {
 	int cpu, ret = 0;
 
 	if (cpu_id == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
-			ret = ring_buffer_resize(tr->buffer,
-					size_tr->data[cpu]->entries, cpu);
+			ret = ring_buffer_resize(trace_buf->buffer,
+				 per_cpu_ptr(size_buf->data, cpu)->entries, cpu);
 			if (ret < 0)
 				break;
-			tr->data[cpu]->entries = size_tr->data[cpu]->entries;
+			per_cpu_ptr(trace_buf->data, cpu)->entries =
+				per_cpu_ptr(size_buf->data, cpu)->entries;
 		}
 	} else {
-		ret = ring_buffer_resize(tr->buffer,
-					size_tr->data[cpu_id]->entries, cpu_id);
+		ret = ring_buffer_resize(trace_buf->buffer,
+				 per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id);
 		if (ret == 0)
-			tr->data[cpu_id]->entries =
-				size_tr->data[cpu_id]->entries;
+			per_cpu_ptr(trace_buf->data, cpu_id)->entries =
+				per_cpu_ptr(size_buf->data, cpu_id)->entries;
 	}
 
 	return ret;
 }
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
-static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
+static int __tracing_resize_ring_buffer(struct trace_array *tr,
+					unsigned long size, int cpu)
 {
 	int ret;
 
@@ -3089,23 +3515,25 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
 	 * we use the size that was given, and we can forget about
 	 * expanding it later.
 	 */
-	ring_buffer_expanded = 1;
+	ring_buffer_expanded = true;
 
 	/* May be called before buffers are initialized */
-	if (!global_trace.buffer)
+	if (!tr->trace_buffer.buffer)
 		return 0;
 
-	ret = ring_buffer_resize(global_trace.buffer, size, cpu);
+	ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu);
 	if (ret < 0)
 		return ret;
 
-	if (!current_trace->use_max_tr)
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
+	    !tr->current_trace->use_max_tr)
 		goto out;
 
-	ret = ring_buffer_resize(max_tr.buffer, size, cpu);
+	ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
 	if (ret < 0) {
-		int r = resize_buffer_duplicate_size(&global_trace,
-						     &global_trace, cpu);
+		int r = resize_buffer_duplicate_size(&tr->trace_buffer,
+						     &tr->trace_buffer, cpu);
 		if (r < 0) {
 			/*
 			 * AARGH! We are left with different
@@ -3128,20 +3556,23 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
 	}
 
 	if (cpu == RING_BUFFER_ALL_CPUS)
-		set_buffer_entries(&max_tr, size);
+		set_buffer_entries(&tr->max_buffer, size);
 	else
-		max_tr.data[cpu]->entries = size;
+		per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size;
 
  out:
+#endif /* CONFIG_TRACER_MAX_TRACE */
+
 	if (cpu == RING_BUFFER_ALL_CPUS)
-		set_buffer_entries(&global_trace, size);
+		set_buffer_entries(&tr->trace_buffer, size);
 	else
-		global_trace.data[cpu]->entries = size;
+		per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size;
 
 	return ret;
 }
 
-static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
+static ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
+					  unsigned long size, int cpu_id)
 {
 	int ret = size;
 
@@ -3155,7 +3586,7 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
 		}
 	}
 
-	ret = __tracing_resize_ring_buffer(size, cpu_id);
+	ret = __tracing_resize_ring_buffer(tr, size, cpu_id);
 	if (ret < 0)
 		ret = -ENOMEM;
 
@@ -3182,7 +3613,7 @@ int tracing_update_buffers(void)
 
 	mutex_lock(&trace_types_lock);
 	if (!ring_buffer_expanded)
-		ret = __tracing_resize_ring_buffer(trace_buf_size,
+		ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size,
 						RING_BUFFER_ALL_CPUS);
 	mutex_unlock(&trace_types_lock);
 
@@ -3192,7 +3623,7 @@ int tracing_update_buffers(void)
 struct trace_option_dentry;
 
 static struct trace_option_dentry *
-create_trace_option_files(struct tracer *tracer);
+create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
 
 static void
 destroy_trace_option_files(struct trace_option_dentry *topts);
@@ -3202,13 +3633,15 @@ static int tracing_set_tracer(const char *buf)
 	static struct trace_option_dentry *topts;
 	struct trace_array *tr = &global_trace;
 	struct tracer *t;
+#ifdef CONFIG_TRACER_MAX_TRACE
 	bool had_max_tr;
+#endif
 	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
 
 	if (!ring_buffer_expanded) {
-		ret = __tracing_resize_ring_buffer(trace_buf_size,
+		ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
 						RING_BUFFER_ALL_CPUS);
 		if (ret < 0)
 			goto out;
@@ -3223,15 +3656,21 @@ static int tracing_set_tracer(const char *buf)
 		ret = -EINVAL;
 		goto out;
 	}
-	if (t == current_trace)
+	if (t == tr->current_trace)
 		goto out;
 
 	trace_branch_disable();
-	if (current_trace->reset)
-		current_trace->reset(tr);
 
-	had_max_tr = current_trace->allocated_snapshot;
-	current_trace = &nop_trace;
+	tr->current_trace->enabled = false;
+
+	if (tr->current_trace->reset)
+		tr->current_trace->reset(tr);
+
+	/* Current trace needs to be nop_trace before synchronize_sched */
+	tr->current_trace = &nop_trace;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	had_max_tr = tr->allocated_snapshot;
 
 	if (had_max_tr && !t->use_max_tr) {
 		/*
@@ -3242,27 +3681,20 @@ static int tracing_set_tracer(const char *buf)
 		 * so a synchronized_sched() is sufficient.
 		 */
 		synchronize_sched();
-		/*
-		 * We don't free the ring buffer. instead, resize it because
-		 * The max_tr ring buffer has some state (e.g. ring->clock) and
-		 * we want preserve it.
-		 */
-		ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS);
-		set_buffer_entries(&max_tr, 1);
-		tracing_reset_online_cpus(&max_tr);
-		current_trace->allocated_snapshot = false;
+		free_snapshot(tr);
 	}
+#endif
 	destroy_trace_option_files(topts);
 
-	topts = create_trace_option_files(t);
+	topts = create_trace_option_files(tr, t);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
 	if (t->use_max_tr && !had_max_tr) {
-		/* we need to make per cpu buffer sizes equivalent */
-		ret = resize_buffer_duplicate_size(&max_tr, &global_trace,
-						   RING_BUFFER_ALL_CPUS);
+		ret = alloc_snapshot(tr);
 		if (ret < 0)
 			goto out;
-		t->allocated_snapshot = true;
 	}
+#endif
 
 	if (t->init) {
 		ret = tracer_init(t, tr);
@@ -3270,7 +3702,8 @@ static int tracing_set_tracer(const char *buf)
 			goto out;
 	}
 
-	current_trace = t;
+	tr->current_trace = t;
+	tr->current_trace->enabled = true;
 	trace_branch_enable(tr);
  out:
 	mutex_unlock(&trace_types_lock);
@@ -3344,7 +3777,8 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
-	long cpu_file = (long) inode->i_private;
+	struct trace_cpu *tc = inode->i_private;
+	struct trace_array *tr = tc->tr;
 	struct trace_iterator *iter;
 	int ret = 0;
 
@@ -3369,7 +3803,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		ret = -ENOMEM;
 		goto fail;
 	}
-	*iter->trace = *current_trace;
+	*iter->trace = *tr->current_trace;
 
 	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
 		ret = -ENOMEM;
@@ -3386,8 +3820,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (trace_clocks[trace_clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	iter->cpu_file = cpu_file;
-	iter->tr = &global_trace;
+	iter->cpu_file = tc->cpu;
+	iter->tr = tc->tr;
+	iter->trace_buffer = &tc->tr->trace_buffer;
 	mutex_init(&iter->mutex);
 	filp->private_data = iter;
 
@@ -3426,24 +3861,28 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 }
 
 static unsigned int
-tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table)
 {
-	struct trace_iterator *iter = filp->private_data;
+	/* Iterators are static, they should be filled or empty */
+	if (trace_buffer_iter(iter, iter->cpu_file))
+		return POLLIN | POLLRDNORM;
 
-	if (trace_flags & TRACE_ITER_BLOCK) {
+	if (trace_flags & TRACE_ITER_BLOCK)
 		/*
 		 * Always select as readable when in blocking mode
 		 */
 		return POLLIN | POLLRDNORM;
-	} else {
-		if (!trace_empty(iter))
-			return POLLIN | POLLRDNORM;
-		poll_wait(filp, &trace_wait, poll_table);
-		if (!trace_empty(iter))
-			return POLLIN | POLLRDNORM;
+	else
+		return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file,
+					     filp, poll_table);
+}
 
-		return 0;
-	}
+static unsigned int
+tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+{
+	struct trace_iterator *iter = filp->private_data;
+
+	return trace_poll(iter, filp, poll_table);
 }
 
 /*
@@ -3509,6 +3948,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
 	struct trace_iterator *iter = filp->private_data;
+	struct trace_array *tr = iter->tr;
 	ssize_t sret;
 
 	/* return any leftover data */
@@ -3520,8 +3960,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(iter->trace->name != current_trace->name))
-		*iter->trace = *current_trace;
+	if (unlikely(iter->trace->name != tr->current_trace->name))
+		*iter->trace = *tr->current_trace;
 	mutex_unlock(&trace_types_lock);
 
 	/*
@@ -3677,6 +4117,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
+	struct trace_array *tr = iter->tr;
 	ssize_t ret;
 	size_t rem;
 	unsigned int i;
@@ -3686,8 +4127,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(iter->trace->name != current_trace->name))
-		*iter->trace = *current_trace;
+	if (unlikely(iter->trace->name != tr->current_trace->name))
+		*iter->trace = *tr->current_trace;
 	mutex_unlock(&trace_types_lock);
 
 	mutex_lock(&iter->mutex);
@@ -3749,43 +4190,19 @@ out_err:
 	goto out;
 }
 
-struct ftrace_entries_info {
-	struct trace_array	*tr;
-	int			cpu;
-};
-
-static int tracing_entries_open(struct inode *inode, struct file *filp)
-{
-	struct ftrace_entries_info *info;
-
-	if (tracing_disabled)
-		return -ENODEV;
-
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->tr = &global_trace;
-	info->cpu = (unsigned long)inode->i_private;
-
-	filp->private_data = info;
-
-	return 0;
-}
-
 static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
 		     size_t cnt, loff_t *ppos)
 {
-	struct ftrace_entries_info *info = filp->private_data;
-	struct trace_array *tr = info->tr;
+	struct trace_cpu *tc = filp->private_data;
+	struct trace_array *tr = tc->tr;
 	char buf[64];
 	int r = 0;
 	ssize_t ret;
 
 	mutex_lock(&trace_types_lock);
 
-	if (info->cpu == RING_BUFFER_ALL_CPUS) {
+	if (tc->cpu == RING_BUFFER_ALL_CPUS) {
 		int cpu, buf_size_same;
 		unsigned long size;
 
@@ -3795,8 +4212,8 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
 		for_each_tracing_cpu(cpu) {
 			/* fill in the size from first enabled cpu */
 			if (size == 0)
-				size = tr->data[cpu]->entries;
-			if (size != tr->data[cpu]->entries) {
+				size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries;
+			if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) {
 				buf_size_same = 0;
 				break;
 			}
@@ -3812,7 +4229,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
 		} else
 			r = sprintf(buf, "X\n");
 	} else
-		r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10);
+		r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -3824,7 +4241,7 @@ static ssize_t
 tracing_entries_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
-	struct ftrace_entries_info *info = filp->private_data;
+	struct trace_cpu *tc = filp->private_data;
 	unsigned long val;
 	int ret;
 
@@ -3839,7 +4256,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	/* value is in KB */
 	val <<= 10;
 
-	ret = tracing_resize_ring_buffer(val, info->cpu);
+	ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu);
 	if (ret < 0)
 		return ret;
 
@@ -3848,16 +4265,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
-static int
-tracing_entries_release(struct inode *inode, struct file *filp)
-{
-	struct ftrace_entries_info *info = filp->private_data;
-
-	kfree(info);
-
-	return 0;
-}
-
 static ssize_t
 tracing_total_entries_read(struct file *filp, char __user *ubuf,
 				size_t cnt, loff_t *ppos)
@@ -3869,7 +4276,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
 
 	mutex_lock(&trace_types_lock);
 	for_each_tracing_cpu(cpu) {
-		size += tr->data[cpu]->entries >> 10;
+		size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10;
 		if (!ring_buffer_expanded)
 			expanded_size += trace_buf_size >> 10;
 	}
@@ -3899,11 +4306,13 @@ tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
 static int
 tracing_free_buffer_release(struct inode *inode, struct file *filp)
 {
+	struct trace_array *tr = inode->i_private;
+
 	/* disable tracing ? */
 	if (trace_flags & TRACE_ITER_STOP_ON_FREE)
 		tracing_off();
 	/* resize the ring buffer to 0 */
-	tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS);
+	tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS);
 
 	return 0;
 }
@@ -3972,7 +4381,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 
 	local_save_flags(irq_flags);
 	size = sizeof(*entry) + cnt + 2; /* possible \n added */
-	buffer = global_trace.buffer;
+	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					  irq_flags, preempt_count());
 	if (!event) {
@@ -4014,13 +4423,14 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_clock_show(struct seq_file *m, void *v)
 {
+	struct trace_array *tr = m->private;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
 		seq_printf(m,
 			"%s%s%s%s", i ? " " : "",
-			i == trace_clock_id ? "[" : "", trace_clocks[i].name,
-			i == trace_clock_id ? "]" : "");
+			i == tr->clock_id ? "[" : "", trace_clocks[i].name,
+			i == tr->clock_id ? "]" : "");
 	seq_putc(m, '\n');
 
 	return 0;
@@ -4029,6 +4439,8 @@ static int tracing_clock_show(struct seq_file *m, void *v)
 static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 				   size_t cnt, loff_t *fpos)
 {
+	struct seq_file *m = filp->private_data;
+	struct trace_array *tr = m->private;
 	char buf[64];
 	const char *clockstr;
 	int i;
@@ -4050,20 +4462,23 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 	if (i == ARRAY_SIZE(trace_clocks))
 		return -EINVAL;
 
-	trace_clock_id = i;
-
 	mutex_lock(&trace_types_lock);
 
-	ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func);
-	if (max_tr.buffer)
-		ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func);
+	tr->clock_id = i;
+
+	ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func);
 
 	/*
 	 * New clock may not be consistent with the previous clock.
 	 * Reset the buffer so that it doesn't have incomparable timestamps.
 	 */
-	tracing_reset_online_cpus(&global_trace);
-	tracing_reset_online_cpus(&max_tr);
+	tracing_reset_online_cpus(&global_trace.trace_buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
+		ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
+	tracing_reset_online_cpus(&global_trace.max_buffer);
+#endif
 
 	mutex_unlock(&trace_types_lock);
 
@@ -4076,20 +4491,45 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
 {
 	if (tracing_disabled)
 		return -ENODEV;
-	return single_open(file, tracing_clock_show, NULL);
+
+	return single_open(file, tracing_clock_show, inode->i_private);
 }
 
+struct ftrace_buffer_info {
+	struct trace_iterator	iter;
+	void			*spare;
+	unsigned int		read;
+};
+
 #ifdef CONFIG_TRACER_SNAPSHOT
 static int tracing_snapshot_open(struct inode *inode, struct file *file)
 {
+	struct trace_cpu *tc = inode->i_private;
 	struct trace_iterator *iter;
+	struct seq_file *m;
 	int ret = 0;
 
 	if (file->f_mode & FMODE_READ) {
 		iter = __tracing_open(inode, file, true);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
+	} else {
+		/* Writes still need the seq_file to hold the private data */
+		m = kzalloc(sizeof(*m), GFP_KERNEL);
+		if (!m)
+			return -ENOMEM;
+		iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+		if (!iter) {
+			kfree(m);
+			return -ENOMEM;
+		}
+		iter->tr = tc->tr;
+		iter->trace_buffer = &tc->tr->max_buffer;
+		iter->cpu_file = tc->cpu;
+		m->private = iter;
+		file->private_data = m;
 	}
+
 	return ret;
 }
 
@@ -4097,6 +4537,9 @@ static ssize_t
 tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		       loff_t *ppos)
 {
+	struct seq_file *m = filp->private_data;
+	struct trace_iterator *iter = m->private;
+	struct trace_array *tr = iter->tr;
 	unsigned long val;
 	int ret;
 
@@ -4110,42 +4553,48 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	mutex_lock(&trace_types_lock);
 
-	if (current_trace->use_max_tr) {
+	if (tr->current_trace->use_max_tr) {
 		ret = -EBUSY;
 		goto out;
 	}
 
 	switch (val) {
 	case 0:
-		if (current_trace->allocated_snapshot) {
-			/* free spare buffer */
-			ring_buffer_resize(max_tr.buffer, 1,
-					   RING_BUFFER_ALL_CPUS);
-			set_buffer_entries(&max_tr, 1);
-			tracing_reset_online_cpus(&max_tr);
-			current_trace->allocated_snapshot = false;
+		if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
+			ret = -EINVAL;
+			break;
 		}
+		if (tr->allocated_snapshot)
+			free_snapshot(tr);
 		break;
 	case 1:
-		if (!current_trace->allocated_snapshot) {
-			/* allocate spare buffer */
-			ret = resize_buffer_duplicate_size(&max_tr,
-					&global_trace, RING_BUFFER_ALL_CPUS);
+/* Only allow per-cpu swap if the ring buffer supports it */
+#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP
+		if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
+			ret = -EINVAL;
+			break;
+		}
+#endif
+		if (!tr->allocated_snapshot) {
+			ret = alloc_snapshot(tr);
 			if (ret < 0)
 				break;
-			current_trace->allocated_snapshot = true;
 		}
-
 		local_irq_disable();
 		/* Now, we're going to swap */
-		update_max_tr(&global_trace, current, smp_processor_id());
+		if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+			update_max_tr(tr, current, smp_processor_id());
+		else
+			update_max_tr_single(tr, current, iter->cpu_file);
 		local_irq_enable();
 		break;
 	default:
-		if (current_trace->allocated_snapshot)
-			tracing_reset_online_cpus(&max_tr);
-		else
-			ret = -EINVAL;
+		if (tr->allocated_snapshot) {
+			if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+				tracing_reset_online_cpus(&tr->max_buffer);
+			else
+				tracing_reset(&tr->max_buffer, iter->cpu_file);
+		}
 		break;
 	}
 
@@ -4157,6 +4606,51 @@ out:
 	mutex_unlock(&trace_types_lock);
 	return ret;
 }
+
+static int tracing_snapshot_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+
+	if (file->f_mode & FMODE_READ)
+		return tracing_release(inode, file);
+
+	/* If write only, the seq_file is just a stub */
+	if (m)
+		kfree(m->private);
+	kfree(m);
+
+	return 0;
+}
+
+static int tracing_buffers_open(struct inode *inode, struct file *filp);
+static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf,
+				    size_t count, loff_t *ppos);
+static int tracing_buffers_release(struct inode *inode, struct file *file);
+static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos,
+		   struct pipe_inode_info *pipe, size_t len, unsigned int flags);
+
+static int snapshot_raw_open(struct inode *inode, struct file *filp)
+{
+	struct ftrace_buffer_info *info;
+	int ret;
+
+	ret = tracing_buffers_open(inode, filp);
+	if (ret < 0)
+		return ret;
+
+	info = filp->private_data;
+
+	if (info->iter.trace->use_max_tr) {
+		tracing_buffers_release(inode, filp);
+		return -EBUSY;
+	}
+
+	info->iter.snapshot = true;
+	info->iter.trace_buffer = &info->iter.tr->max_buffer;
+
+	return ret;
+}
+
 #endif /* CONFIG_TRACER_SNAPSHOT */
 
 
@@ -4184,10 +4678,9 @@ static const struct file_operations tracing_pipe_fops = {
 };
 
 static const struct file_operations tracing_entries_fops = {
-	.open		= tracing_entries_open,
+	.open		= tracing_open_generic,
 	.read		= tracing_entries_read,
 	.write		= tracing_entries_write,
-	.release	= tracing_entries_release,
 	.llseek		= generic_file_llseek,
 };
 
@@ -4222,20 +4715,23 @@ static const struct file_operations snapshot_fops = {
 	.read		= seq_read,
 	.write		= tracing_snapshot_write,
 	.llseek		= tracing_seek,
-	.release	= tracing_release,
+	.release	= tracing_snapshot_release,
 };
-#endif /* CONFIG_TRACER_SNAPSHOT */
 
-struct ftrace_buffer_info {
-	struct trace_array	*tr;
-	void			*spare;
-	int			cpu;
-	unsigned int		read;
+static const struct file_operations snapshot_raw_fops = {
+	.open		= snapshot_raw_open,
+	.read		= tracing_buffers_read,
+	.release	= tracing_buffers_release,
+	.splice_read	= tracing_buffers_splice_read,
+	.llseek		= no_llseek,
 };
 
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
 static int tracing_buffers_open(struct inode *inode, struct file *filp)
 {
-	int cpu = (int)(long)inode->i_private;
+	struct trace_cpu *tc = inode->i_private;
+	struct trace_array *tr = tc->tr;
 	struct ftrace_buffer_info *info;
 
 	if (tracing_disabled)
@@ -4245,72 +4741,131 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 	if (!info)
 		return -ENOMEM;
 
-	info->tr	= &global_trace;
-	info->cpu	= cpu;
-	info->spare	= NULL;
+	mutex_lock(&trace_types_lock);
+
+	tr->ref++;
+
+	info->iter.tr		= tr;
+	info->iter.cpu_file	= tc->cpu;
+	info->iter.trace	= tr->current_trace;
+	info->iter.trace_buffer = &tr->trace_buffer;
+	info->spare		= NULL;
 	/* Force reading ring buffer for first read */
-	info->read	= (unsigned int)-1;
+	info->read		= (unsigned int)-1;
 
 	filp->private_data = info;
 
+	mutex_unlock(&trace_types_lock);
+
 	return nonseekable_open(inode, filp);
 }
 
+static unsigned int
+tracing_buffers_poll(struct file *filp, poll_table *poll_table)
+{
+	struct ftrace_buffer_info *info = filp->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	return trace_poll(iter, filp, poll_table);
+}
+
 static ssize_t
 tracing_buffers_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
 	struct ftrace_buffer_info *info = filp->private_data;
+	struct trace_iterator *iter = &info->iter;
 	ssize_t ret;
-	size_t size;
+	ssize_t size;
 
 	if (!count)
 		return 0;
 
+	mutex_lock(&trace_types_lock);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (iter->snapshot && iter->tr->current_trace->use_max_tr) {
+		size = -EBUSY;
+		goto out_unlock;
+	}
+#endif
+
 	if (!info->spare)
-		info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu);
+		info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
+							  iter->cpu_file);
+	size = -ENOMEM;
 	if (!info->spare)
-		return -ENOMEM;
+		goto out_unlock;
 
 	/* Do we have previous read data to read? */
 	if (info->read < PAGE_SIZE)
 		goto read;
 
-	trace_access_lock(info->cpu);
-	ret = ring_buffer_read_page(info->tr->buffer,
+ again:
+	trace_access_lock(iter->cpu_file);
+	ret = ring_buffer_read_page(iter->trace_buffer->buffer,
 				    &info->spare,
 				    count,
-				    info->cpu, 0);
-	trace_access_unlock(info->cpu);
-	if (ret < 0)
-		return 0;
+				    iter->cpu_file, 0);
+	trace_access_unlock(iter->cpu_file);
 
-	info->read = 0;
+	if (ret < 0) {
+		if (trace_empty(iter)) {
+			if ((filp->f_flags & O_NONBLOCK)) {
+				size = -EAGAIN;
+				goto out_unlock;
+			}
+			mutex_unlock(&trace_types_lock);
+			iter->trace->wait_pipe(iter);
+			mutex_lock(&trace_types_lock);
+			if (signal_pending(current)) {
+				size = -EINTR;
+				goto out_unlock;
+			}
+			goto again;
+		}
+		size = 0;
+		goto out_unlock;
+	}
 
-read:
+	info->read = 0;
+ read:
 	size = PAGE_SIZE - info->read;
 	if (size > count)
 		size = count;
 
 	ret = copy_to_user(ubuf, info->spare + info->read, size);
-	if (ret == size)
-		return -EFAULT;
+	if (ret == size) {
+		size = -EFAULT;
+		goto out_unlock;
+	}
 	size -= ret;
 
 	*ppos += size;
 	info->read += size;
 
+ out_unlock:
+	mutex_unlock(&trace_types_lock);
+
 	return size;
 }
 
 static int tracing_buffers_release(struct inode *inode, struct file *file)
 {
 	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	mutex_lock(&trace_types_lock);
+
+	WARN_ON(!iter->tr->ref);
+	iter->tr->ref--;
 
 	if (info->spare)
-		ring_buffer_free_read_page(info->tr->buffer, info->spare);
+		ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare);
 	kfree(info);
 
+	mutex_unlock(&trace_types_lock);
+
 	return 0;
 }
 
@@ -4375,6 +4930,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			    unsigned int flags)
 {
 	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
 	struct partial_page partial_def[PIPE_DEF_BUFFERS];
 	struct page *pages_def[PIPE_DEF_BUFFERS];
 	struct splice_pipe_desc spd = {
@@ -4387,10 +4943,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	};
 	struct buffer_ref *ref;
 	int entries, size, i;
-	size_t ret;
+	ssize_t ret;
 
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
+	mutex_lock(&trace_types_lock);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (iter->snapshot && iter->tr->current_trace->use_max_tr) {
+		ret = -EBUSY;
+		goto out;
+	}
+#endif
+
+	if (splice_grow_spd(pipe, &spd)) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	if (*ppos & (PAGE_SIZE - 1)) {
 		ret = -EINVAL;
@@ -4405,8 +4972,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
-	trace_access_lock(info->cpu);
-	entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+ again:
+	trace_access_lock(iter->cpu_file);
+	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
 
 	for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
 		struct page *page;
@@ -4417,15 +4985,15 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 
 		ref->ref = 1;
-		ref->buffer = info->tr->buffer;
-		ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu);
+		ref->buffer = iter->trace_buffer->buffer;
+		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
 		if (!ref->page) {
 			kfree(ref);
 			break;
 		}
 
 		r = ring_buffer_read_page(ref->buffer, &ref->page,
-					  len, info->cpu, 1);
+					  len, iter->cpu_file, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer, ref->page);
 			kfree(ref);
@@ -4449,31 +5017,40 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		spd.nr_pages++;
 		*ppos += PAGE_SIZE;
 
-		entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+		entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
 	}
 
-	trace_access_unlock(info->cpu);
+	trace_access_unlock(iter->cpu_file);
 	spd.nr_pages = i;
 
 	/* did we read anything? */
 	if (!spd.nr_pages) {
-		if (flags & SPLICE_F_NONBLOCK)
+		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) {
 			ret = -EAGAIN;
-		else
-			ret = 0;
-		/* TODO: block */
-		goto out;
+			goto out;
+		}
+		mutex_unlock(&trace_types_lock);
+		iter->trace->wait_pipe(iter);
+		mutex_lock(&trace_types_lock);
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
+		goto again;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
 	splice_shrink_spd(&spd);
 out:
+	mutex_unlock(&trace_types_lock);
+
 	return ret;
 }
 
 static const struct file_operations tracing_buffers_fops = {
 	.open		= tracing_buffers_open,
 	.read		= tracing_buffers_read,
+	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
 	.splice_read	= tracing_buffers_splice_read,
 	.llseek		= no_llseek,
@@ -4483,12 +5060,14 @@ static ssize_t
 tracing_stats_read(struct file *filp, char __user *ubuf,
 		   size_t count, loff_t *ppos)
 {
-	unsigned long cpu = (unsigned long)filp->private_data;
-	struct trace_array *tr = &global_trace;
+	struct trace_cpu *tc = filp->private_data;
+	struct trace_array *tr = tc->tr;
+	struct trace_buffer *trace_buf = &tr->trace_buffer;
 	struct trace_seq *s;
 	unsigned long cnt;
 	unsigned long long t;
 	unsigned long usec_rem;
+	int cpu = tc->cpu;
 
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
@@ -4496,41 +5075,41 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 
 	trace_seq_init(s);
 
-	cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+	cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "entries: %ld\n", cnt);
 
-	cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+	cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "overrun: %ld\n", cnt);
 
-	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+	cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
 
-	cnt = ring_buffer_bytes_cpu(tr->buffer, cpu);
+	cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "bytes: %ld\n", cnt);
 
 	if (trace_clocks[trace_clock_id].in_ns) {
 		/* local or global for trace_clock */
-		t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu));
+		t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu));
 		usec_rem = do_div(t, USEC_PER_SEC);
 		trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n",
 								t, usec_rem);
 
-		t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu));
+		t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu));
 		usec_rem = do_div(t, USEC_PER_SEC);
 		trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
 	} else {
 		/* counter or tsc mode for trace_clock */
 		trace_seq_printf(s, "oldest event ts: %llu\n",
-				ring_buffer_oldest_event_ts(tr->buffer, cpu));
+				ring_buffer_oldest_event_ts(trace_buf->buffer, cpu));
 
 		trace_seq_printf(s, "now ts: %llu\n",
-				ring_buffer_time_stamp(tr->buffer, cpu));
+				ring_buffer_time_stamp(trace_buf->buffer, cpu));
 	}
 
-	cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu);
+	cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "dropped events: %ld\n", cnt);
 
-	cnt = ring_buffer_read_events_cpu(tr->buffer, cpu);
+	cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "read events: %ld\n", cnt);
 
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
@@ -4582,60 +5161,161 @@ static const struct file_operations tracing_dyn_info_fops = {
 	.read		= tracing_read_dyn_info,
 	.llseek		= generic_file_llseek,
 };
-#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
 
-static struct dentry *d_tracer;
+#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE)
+static void
+ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	tracing_snapshot();
+}
 
-struct dentry *tracing_init_dentry(void)
+static void
+ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	unsigned long *count = (long *)data;
+
+	if (!*count)
+		return;
+
+	if (*count != -1)
+		(*count)--;
+
+	tracing_snapshot();
+}
+
+static int
+ftrace_snapshot_print(struct seq_file *m, unsigned long ip,
+		      struct ftrace_probe_ops *ops, void *data)
+{
+	long count = (long)data;
+
+	seq_printf(m, "%ps:", (void *)ip);
+
+	seq_printf(m, "snapshot");
+
+	if (count == -1)
+		seq_printf(m, ":unlimited\n");
+	else
+		seq_printf(m, ":count=%ld\n", count);
+
+	return 0;
+}
+
+static struct ftrace_probe_ops snapshot_probe_ops = {
+	.func			= ftrace_snapshot,
+	.print			= ftrace_snapshot_print,
+};
+
+static struct ftrace_probe_ops snapshot_count_probe_ops = {
+	.func			= ftrace_count_snapshot,
+	.print			= ftrace_snapshot_print,
+};
+
+static int
+ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
+			       char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+	void *count = (void *)-1;
+	char *number;
+	int ret;
+
+	/* hash funcs only work with set_ftrace_filter */
+	if (!enable)
+		return -EINVAL;
+
+	ops = param ? &snapshot_count_probe_ops :  &snapshot_probe_ops;
+
+	if (glob[0] == '!') {
+		unregister_ftrace_function_probe_func(glob+1, ops);
+		return 0;
+	}
+
+	if (!param)
+		goto out_reg;
+
+	number = strsep(&param, ":");
+
+	if (!strlen(number))
+		goto out_reg;
+
+	/*
+	 * We use the callback data field (which is a pointer)
+	 * as our counter.
+	 */
+	ret = kstrtoul(number, 0, (unsigned long *)&count);
+	if (ret)
+		return ret;
+
+ out_reg:
+	ret = register_ftrace_function_probe(glob, ops, count);
+
+	if (ret >= 0)
+		alloc_snapshot(&global_trace);
+
+	return ret < 0 ? ret : 0;
+}
+
+static struct ftrace_func_command ftrace_snapshot_cmd = {
+	.name			= "snapshot",
+	.func			= ftrace_trace_snapshot_callback,
+};
+
+static int register_snapshot_cmd(void)
 {
-	static int once;
+	return register_ftrace_command(&ftrace_snapshot_cmd);
+}
+#else
+static inline int register_snapshot_cmd(void) { return 0; }
+#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */
 
-	if (d_tracer)
-		return d_tracer;
+struct dentry *tracing_init_dentry_tr(struct trace_array *tr)
+{
+	if (tr->dir)
+		return tr->dir;
 
 	if (!debugfs_initialized())
 		return NULL;
 
-	d_tracer = debugfs_create_dir("tracing", NULL);
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		tr->dir = debugfs_create_dir("tracing", NULL);
 
-	if (!d_tracer && !once) {
-		once = 1;
-		pr_warning("Could not create debugfs directory 'tracing'\n");
-		return NULL;
-	}
+	if (!tr->dir)
+		pr_warn_once("Could not create debugfs directory 'tracing'\n");
 
-	return d_tracer;
+	return tr->dir;
 }
 
-static struct dentry *d_percpu;
+struct dentry *tracing_init_dentry(void)
+{
+	return tracing_init_dentry_tr(&global_trace);
+}
 
-static struct dentry *tracing_dentry_percpu(void)
+static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
 {
-	static int once;
 	struct dentry *d_tracer;
 
-	if (d_percpu)
-		return d_percpu;
-
-	d_tracer = tracing_init_dentry();
+	if (tr->percpu_dir)
+		return tr->percpu_dir;
 
+	d_tracer = tracing_init_dentry_tr(tr);
 	if (!d_tracer)
 		return NULL;
 
-	d_percpu = debugfs_create_dir("per_cpu", d_tracer);
+	tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer);
 
-	if (!d_percpu && !once) {
-		once = 1;
-		pr_warning("Could not create debugfs directory 'per_cpu'\n");
-		return NULL;
-	}
+	WARN_ONCE(!tr->percpu_dir,
+		  "Could not create debugfs directory 'per_cpu/%d'\n", cpu);
 
-	return d_percpu;
+	return tr->percpu_dir;
 }
 
-static void tracing_init_debugfs_percpu(long cpu)
+static void
+tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 {
-	struct dentry *d_percpu = tracing_dentry_percpu();
+	struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+	struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
 	struct dentry *d_cpu;
 	char cpu_dir[30]; /* 30 characters should be more than enough */
 
@@ -4651,20 +5331,28 @@ static void tracing_init_debugfs_percpu(long cpu)
 
 	/* per cpu trace_pipe */
 	trace_create_file("trace_pipe", 0444, d_cpu,
-			(void *) cpu, &tracing_pipe_fops);
+			(void *)&data->trace_cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
 	trace_create_file("trace", 0644, d_cpu,
-			(void *) cpu, &tracing_fops);
+			(void *)&data->trace_cpu, &tracing_fops);
 
 	trace_create_file("trace_pipe_raw", 0444, d_cpu,
-			(void *) cpu, &tracing_buffers_fops);
+			(void *)&data->trace_cpu, &tracing_buffers_fops);
 
 	trace_create_file("stats", 0444, d_cpu,
-			(void *) cpu, &tracing_stats_fops);
+			(void *)&data->trace_cpu, &tracing_stats_fops);
 
 	trace_create_file("buffer_size_kb", 0444, d_cpu,
-			(void *) cpu, &tracing_entries_fops);
+			(void *)&data->trace_cpu, &tracing_entries_fops);
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+	trace_create_file("snapshot", 0644, d_cpu,
+			  (void *)&data->trace_cpu, &snapshot_fops);
+
+	trace_create_file("snapshot_raw", 0444, d_cpu,
+			(void *)&data->trace_cpu, &snapshot_raw_fops);
+#endif
 }
 
 #ifdef CONFIG_FTRACE_SELFTEST
@@ -4675,6 +5363,7 @@ static void tracing_init_debugfs_percpu(long cpu)
 struct trace_option_dentry {
 	struct tracer_opt		*opt;
 	struct tracer_flags		*flags;
+	struct trace_array		*tr;
 	struct dentry			*entry;
 };
 
@@ -4710,7 +5399,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (!!(topt->flags->val & topt->opt->bit) != val) {
 		mutex_lock(&trace_types_lock);
-		ret = __set_tracer_option(current_trace, topt->flags,
+		ret = __set_tracer_option(topt->tr->current_trace, topt->flags,
 					  topt->opt, !val);
 		mutex_unlock(&trace_types_lock);
 		if (ret)
@@ -4749,6 +5438,7 @@ static ssize_t
 trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 			 loff_t *ppos)
 {
+	struct trace_array *tr = &global_trace;
 	long index = (long)filp->private_data;
 	unsigned long val;
 	int ret;
@@ -4759,7 +5449,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (val != 0 && val != 1)
 		return -EINVAL;
-	set_tracer_flags(1 << index, val);
+
+	mutex_lock(&trace_types_lock);
+	ret = set_tracer_flag(tr, 1 << index, val);
+	mutex_unlock(&trace_types_lock);
+
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -4789,40 +5485,41 @@ struct dentry *trace_create_file(const char *name,
 }
 
 
-static struct dentry *trace_options_init_dentry(void)
+static struct dentry *trace_options_init_dentry(struct trace_array *tr)
 {
 	struct dentry *d_tracer;
-	static struct dentry *t_options;
 
-	if (t_options)
-		return t_options;
+	if (tr->options)
+		return tr->options;
 
-	d_tracer = tracing_init_dentry();
+	d_tracer = tracing_init_dentry_tr(tr);
 	if (!d_tracer)
 		return NULL;
 
-	t_options = debugfs_create_dir("options", d_tracer);
-	if (!t_options) {
+	tr->options = debugfs_create_dir("options", d_tracer);
+	if (!tr->options) {
 		pr_warning("Could not create debugfs directory 'options'\n");
 		return NULL;
 	}
 
-	return t_options;
+	return tr->options;
 }
 
 static void
-create_trace_option_file(struct trace_option_dentry *topt,
+create_trace_option_file(struct trace_array *tr,
+			 struct trace_option_dentry *topt,
 			 struct tracer_flags *flags,
 			 struct tracer_opt *opt)
 {
 	struct dentry *t_options;
 
-	t_options = trace_options_init_dentry();
+	t_options = trace_options_init_dentry(tr);
 	if (!t_options)
 		return;
 
 	topt->flags = flags;
 	topt->opt = opt;
+	topt->tr = tr;
 
 	topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
 				    &trace_options_fops);
@@ -4830,7 +5527,7 @@ create_trace_option_file(struct trace_option_dentry *topt,
 }
 
 static struct trace_option_dentry *
-create_trace_option_files(struct tracer *tracer)
+create_trace_option_files(struct trace_array *tr, struct tracer *tracer)
 {
 	struct trace_option_dentry *topts;
 	struct tracer_flags *flags;
@@ -4855,7 +5552,7 @@ create_trace_option_files(struct tracer *tracer)
 		return NULL;
 
 	for (cnt = 0; opts[cnt].name; cnt++)
-		create_trace_option_file(&topts[cnt], flags,
+		create_trace_option_file(tr, &topts[cnt], flags,
 					 &opts[cnt]);
 
 	return topts;
@@ -4878,11 +5575,12 @@ destroy_trace_option_files(struct trace_option_dentry *topts)
 }
 
 static struct dentry *
-create_trace_option_core_file(const char *option, long index)
+create_trace_option_core_file(struct trace_array *tr,
+			      const char *option, long index)
 {
 	struct dentry *t_options;
 
-	t_options = trace_options_init_dentry();
+	t_options = trace_options_init_dentry(tr);
 	if (!t_options)
 		return NULL;
 
@@ -4890,17 +5588,17 @@ create_trace_option_core_file(const char *option, long index)
 				    &trace_options_core_fops);
 }
 
-static __init void create_trace_options_dir(void)
+static __init void create_trace_options_dir(struct trace_array *tr)
 {
 	struct dentry *t_options;
 	int i;
 
-	t_options = trace_options_init_dentry();
+	t_options = trace_options_init_dentry(tr);
 	if (!t_options)
 		return;
 
 	for (i = 0; trace_options[i]; i++)
-		create_trace_option_core_file(trace_options[i], i);
+		create_trace_option_core_file(tr, trace_options[i], i);
 }
 
 static ssize_t
@@ -4908,7 +5606,7 @@ rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	char buf[64];
 	int r;
 
@@ -4927,7 +5625,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	unsigned long val;
 	int ret;
 
@@ -4939,12 +5637,12 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 		mutex_lock(&trace_types_lock);
 		if (val) {
 			ring_buffer_record_on(buffer);
-			if (current_trace->start)
-				current_trace->start(tr);
+			if (tr->current_trace->start)
+				tr->current_trace->start(tr);
 		} else {
 			ring_buffer_record_off(buffer);
-			if (current_trace->stop)
-				current_trace->stop(tr);
+			if (tr->current_trace->stop)
+				tr->current_trace->stop(tr);
 		}
 		mutex_unlock(&trace_types_lock);
 	}
@@ -4961,23 +5659,310 @@ static const struct file_operations rb_simple_fops = {
 	.llseek		= default_llseek,
 };
 
+struct dentry *trace_instance_dir;
+
+static void
+init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
+
+static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf)
+{
+	int cpu;
+
+	for_each_tracing_cpu(cpu) {
+		memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu));
+		per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu;
+		per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr;
+	}
+}
+
+static int
+allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
+{
+	enum ring_buffer_flags rb_flags;
+
+	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
+	buf->buffer = ring_buffer_alloc(size, rb_flags);
+	if (!buf->buffer)
+		return -ENOMEM;
+
+	buf->data = alloc_percpu(struct trace_array_cpu);
+	if (!buf->data) {
+		ring_buffer_free(buf->buffer);
+		return -ENOMEM;
+	}
+
+	init_trace_buffers(tr, buf);
+
+	/* Allocate the first page for all buffers */
+	set_buffer_entries(&tr->trace_buffer,
+			   ring_buffer_size(tr->trace_buffer.buffer, 0));
+
+	return 0;
+}
+
+static int allocate_trace_buffers(struct trace_array *tr, int size)
+{
+	int ret;
+
+	ret = allocate_trace_buffer(tr, &tr->trace_buffer, size);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	ret = allocate_trace_buffer(tr, &tr->max_buffer,
+				    allocate_snapshot ? size : 1);
+	if (WARN_ON(ret)) {
+		ring_buffer_free(tr->trace_buffer.buffer);
+		free_percpu(tr->trace_buffer.data);
+		return -ENOMEM;
+	}
+	tr->allocated_snapshot = allocate_snapshot;
+
+	/*
+	 * Only the top level trace array gets its snapshot allocated
+	 * from the kernel command line.
+	 */
+	allocate_snapshot = false;
+#endif
+	return 0;
+}
+
+static int new_instance_create(const char *name)
+{
+	struct trace_array *tr;
+	int ret;
+
+	mutex_lock(&trace_types_lock);
+
+	ret = -EEXIST;
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr->name && strcmp(tr->name, name) == 0)
+			goto out_unlock;
+	}
+
+	ret = -ENOMEM;
+	tr = kzalloc(sizeof(*tr), GFP_KERNEL);
+	if (!tr)
+		goto out_unlock;
+
+	tr->name = kstrdup(name, GFP_KERNEL);
+	if (!tr->name)
+		goto out_free_tr;
+
+	raw_spin_lock_init(&tr->start_lock);
+
+	tr->current_trace = &nop_trace;
+
+	INIT_LIST_HEAD(&tr->systems);
+	INIT_LIST_HEAD(&tr->events);
+
+	if (allocate_trace_buffers(tr, trace_buf_size) < 0)
+		goto out_free_tr;
+
+	/* Holder for file callbacks */
+	tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
+	tr->trace_cpu.tr = tr;
+
+	tr->dir = debugfs_create_dir(name, trace_instance_dir);
+	if (!tr->dir)
+		goto out_free_tr;
+
+	ret = event_trace_add_tracer(tr->dir, tr);
+	if (ret)
+		goto out_free_tr;
+
+	init_tracer_debugfs(tr, tr->dir);
+
+	list_add(&tr->list, &ftrace_trace_arrays);
+
+	mutex_unlock(&trace_types_lock);
+
+	return 0;
+
+ out_free_tr:
+	if (tr->trace_buffer.buffer)
+		ring_buffer_free(tr->trace_buffer.buffer);
+	kfree(tr->name);
+	kfree(tr);
+
+ out_unlock:
+	mutex_unlock(&trace_types_lock);
+
+	return ret;
+
+}
+
+static int instance_delete(const char *name)
+{
+	struct trace_array *tr;
+	int found = 0;
+	int ret;
+
+	mutex_lock(&trace_types_lock);
+
+	ret = -ENODEV;
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr->name && strcmp(tr->name, name) == 0) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found)
+		goto out_unlock;
+
+	ret = -EBUSY;
+	if (tr->ref)
+		goto out_unlock;
+
+	list_del(&tr->list);
+
+	event_trace_del_tracer(tr);
+	debugfs_remove_recursive(tr->dir);
+	free_percpu(tr->trace_buffer.data);
+	ring_buffer_free(tr->trace_buffer.buffer);
+
+	kfree(tr->name);
+	kfree(tr);
+
+	ret = 0;
+
+ out_unlock:
+	mutex_unlock(&trace_types_lock);
+
+	return ret;
+}
+
+static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode)
+{
+	struct dentry *parent;
+	int ret;
+
+	/* Paranoid: Make sure the parent is the "instances" directory */
+	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	if (WARN_ON_ONCE(parent != trace_instance_dir))
+		return -ENOENT;
+
+	/*
+	 * The inode mutex is locked, but debugfs_create_dir() will also
+	 * take the mutex. As the instances directory can not be destroyed
+	 * or changed in any other way, it is safe to unlock it, and
+	 * let the dentry try. If two users try to make the same dir at
+	 * the same time, then the new_instance_create() will determine the
+	 * winner.
+	 */
+	mutex_unlock(&inode->i_mutex);
+
+	ret = new_instance_create(dentry->d_iname);
+
+	mutex_lock(&inode->i_mutex);
+
+	return ret;
+}
+
+static int instance_rmdir(struct inode *inode, struct dentry *dentry)
+{
+	struct dentry *parent;
+	int ret;
+
+	/* Paranoid: Make sure the parent is the "instances" directory */
+	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	if (WARN_ON_ONCE(parent != trace_instance_dir))
+		return -ENOENT;
+
+	/* The caller did a dget() on dentry */
+	mutex_unlock(&dentry->d_inode->i_mutex);
+
+	/*
+	 * The inode mutex is locked, but debugfs_create_dir() will also
+	 * take the mutex. As the instances directory can not be destroyed
+	 * or changed in any other way, it is safe to unlock it, and
+	 * let the dentry try. If two users try to make the same dir at
+	 * the same time, then the instance_delete() will determine the
+	 * winner.
+	 */
+	mutex_unlock(&inode->i_mutex);
+
+	ret = instance_delete(dentry->d_iname);
+
+	mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+	mutex_lock(&dentry->d_inode->i_mutex);
+
+	return ret;
+}
+
+static const struct inode_operations instance_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.mkdir		= instance_mkdir,
+	.rmdir		= instance_rmdir,
+};
+
+static __init void create_trace_instances(struct dentry *d_tracer)
+{
+	trace_instance_dir = debugfs_create_dir("instances", d_tracer);
+	if (WARN_ON(!trace_instance_dir))
+		return;
+
+	/* Hijack the dir inode operations, to allow mkdir */
+	trace_instance_dir->d_inode->i_op = &instance_dir_inode_operations;
+}
+
+static void
+init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
+{
+	int cpu;
+
+	trace_create_file("trace_options", 0644, d_tracer,
+			  tr, &tracing_iter_fops);
+
+	trace_create_file("trace", 0644, d_tracer,
+			(void *)&tr->trace_cpu, &tracing_fops);
+
+	trace_create_file("trace_pipe", 0444, d_tracer,
+			(void *)&tr->trace_cpu, &tracing_pipe_fops);
+
+	trace_create_file("buffer_size_kb", 0644, d_tracer,
+			(void *)&tr->trace_cpu, &tracing_entries_fops);
+
+	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
+			  tr, &tracing_total_entries_fops);
+
+	trace_create_file("free_buffer", 0644, d_tracer,
+			  tr, &tracing_free_buffer_fops);
+
+	trace_create_file("trace_marker", 0220, d_tracer,
+			  tr, &tracing_mark_fops);
+
+	trace_create_file("trace_clock", 0644, d_tracer, tr,
+			  &trace_clock_fops);
+
+	trace_create_file("tracing_on", 0644, d_tracer,
+			    tr, &rb_simple_fops);
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+	trace_create_file("snapshot", 0644, d_tracer,
+			  (void *)&tr->trace_cpu, &snapshot_fops);
+#endif
+
+	for_each_tracing_cpu(cpu)
+		tracing_init_debugfs_percpu(tr, cpu);
+
+}
+
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	int cpu;
 
 	trace_access_lock_init();
 
 	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
 
-	trace_create_file("trace_options", 0644, d_tracer,
-			NULL, &tracing_iter_fops);
+	init_tracer_debugfs(&global_trace, d_tracer);
 
 	trace_create_file("tracing_cpumask", 0644, d_tracer,
-			NULL, &tracing_cpumask_fops);
-
-	trace_create_file("trace", 0644, d_tracer,
-			(void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
+			&global_trace, &tracing_cpumask_fops);
 
 	trace_create_file("available_tracers", 0444, d_tracer,
 			&global_trace, &show_traces_fops);
@@ -4996,44 +5981,17 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
 
-	trace_create_file("trace_pipe", 0444, d_tracer,
-			(void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
-
-	trace_create_file("buffer_size_kb", 0644, d_tracer,
-			(void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops);
-
-	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
-			&global_trace, &tracing_total_entries_fops);
-
-	trace_create_file("free_buffer", 0644, d_tracer,
-			&global_trace, &tracing_free_buffer_fops);
-
-	trace_create_file("trace_marker", 0220, d_tracer,
-			NULL, &tracing_mark_fops);
-
 	trace_create_file("saved_cmdlines", 0444, d_tracer,
 			NULL, &tracing_saved_cmdlines_fops);
 
-	trace_create_file("trace_clock", 0644, d_tracer, NULL,
-			  &trace_clock_fops);
-
-	trace_create_file("tracing_on", 0644, d_tracer,
-			    &global_trace, &rb_simple_fops);
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
 
-#ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_file("snapshot", 0644, d_tracer,
-			  (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops);
-#endif
-
-	create_trace_options_dir();
+	create_trace_instances(d_tracer);
 
-	for_each_tracing_cpu(cpu)
-		tracing_init_debugfs_percpu(cpu);
+	create_trace_options_dir(&global_trace);
 
 	return 0;
 }
@@ -5089,8 +6047,8 @@ void
 trace_printk_seq(struct trace_seq *s)
 {
 	/* Probably should print a warning here. */
-	if (s->len >= 1000)
-		s->len = 1000;
+	if (s->len >= TRACE_MAX_PRINT)
+		s->len = TRACE_MAX_PRINT;
 
 	/* should be zero ended, but we are paranoid. */
 	s->buffer[s->len] = 0;
@@ -5103,46 +6061,43 @@ trace_printk_seq(struct trace_seq *s)
 void trace_init_global_iter(struct trace_iterator *iter)
 {
 	iter->tr = &global_trace;
-	iter->trace = current_trace;
-	iter->cpu_file = TRACE_PIPE_ALL_CPU;
+	iter->trace = iter->tr->current_trace;
+	iter->cpu_file = RING_BUFFER_ALL_CPUS;
+	iter->trace_buffer = &global_trace.trace_buffer;
 }
 
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-	static arch_spinlock_t ftrace_dump_lock =
-		(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
+	static atomic_t dump_running;
 	unsigned int old_userobj;
-	static int dump_ran;
 	unsigned long flags;
 	int cnt = 0, cpu;
 
-	/* only one dump */
-	local_irq_save(flags);
-	arch_spin_lock(&ftrace_dump_lock);
-	if (dump_ran)
-		goto out;
-
-	dump_ran = 1;
+	/* Only allow one dump user at a time. */
+	if (atomic_inc_return(&dump_running) != 1) {
+		atomic_dec(&dump_running);
+		return;
+	}
 
+	/*
+	 * Always turn off tracing when we dump.
+	 * We don't need to show trace output of what happens
+	 * between multiple crashes.
+	 *
+	 * If the user does a sysrq-z, then they can re-enable
+	 * tracing with echo 1 > tracing_on.
+	 */
 	tracing_off();
 
-	/* Did function tracer already get disabled? */
-	if (ftrace_is_dead()) {
-		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
-		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
-	}
-
-	if (disable_tracing)
-		ftrace_kill();
+	local_irq_save(flags);
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
 
 	for_each_tracing_cpu(cpu) {
-		atomic_inc(&iter.tr->data[cpu]->disabled);
+		atomic_inc(&per_cpu_ptr(iter.tr->trace_buffer.data, cpu)->disabled);
 	}
 
 	old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
@@ -5152,7 +6107,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 
 	switch (oops_dump_mode) {
 	case DUMP_ALL:
-		iter.cpu_file = TRACE_PIPE_ALL_CPU;
+		iter.cpu_file = RING_BUFFER_ALL_CPUS;
 		break;
 	case DUMP_ORIG:
 		iter.cpu_file = raw_smp_processor_id();
@@ -5161,11 +6116,17 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 		goto out_enable;
 	default:
 		printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
-		iter.cpu_file = TRACE_PIPE_ALL_CPU;
+		iter.cpu_file = RING_BUFFER_ALL_CPUS;
 	}
 
 	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
+	/* Did function tracer already get disabled? */
+	if (ftrace_is_dead()) {
+		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
+	}
+
 	/*
 	 * We need to stop all tracing on all CPUS to read the
 	 * the next buffer. This is a bit expensive, but is
@@ -5205,33 +6166,19 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 		printk(KERN_TRACE "---------------------------------\n");
 
  out_enable:
-	/* Re-enable tracing if requested */
-	if (!disable_tracing) {
-		trace_flags |= old_userobj;
+	trace_flags |= old_userobj;
 
-		for_each_tracing_cpu(cpu) {
-			atomic_dec(&iter.tr->data[cpu]->disabled);
-		}
-		tracing_on();
+	for_each_tracing_cpu(cpu) {
+		atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
-
- out:
-	arch_spin_unlock(&ftrace_dump_lock);
+ 	atomic_dec(&dump_running);
 	local_irq_restore(flags);
 }
-
-/* By default: disable tracing after the dump */
-void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
-{
-	__ftrace_dump(true, oops_dump_mode);
-}
 EXPORT_SYMBOL_GPL(ftrace_dump);
 
 __init static int tracer_alloc_buffers(void)
 {
 	int ring_buf_size;
-	enum ring_buffer_flags rb_flags;
-	int i;
 	int ret = -ENOMEM;
 
 
@@ -5252,49 +6199,27 @@ __init static int tracer_alloc_buffers(void)
 	else
 		ring_buf_size = 1;
 
-	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
-
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
 
+	raw_spin_lock_init(&global_trace.start_lock);
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
-	global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
-	if (!global_trace.buffer) {
+	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
 		goto out_free_cpumask;
 	}
+
 	if (global_trace.buffer_disabled)
 		tracing_off();
 
-
-#ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(1, rb_flags);
-	if (!max_tr.buffer) {
-		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
-		WARN_ON(1);
-		ring_buffer_free(global_trace.buffer);
-		goto out_free_cpumask;
-	}
-#endif
-
-	/* Allocate the first page for all buffers */
-	for_each_tracing_cpu(i) {
-		global_trace.data[i] = &per_cpu(global_trace_cpu, i);
-		max_tr.data[i] = &per_cpu(max_tr_data, i);
-	}
-
-	set_buffer_entries(&global_trace,
-			   ring_buffer_size(global_trace.buffer, 0));
-#ifdef CONFIG_TRACER_MAX_TRACE
-	set_buffer_entries(&max_tr, 1);
-#endif
-
 	trace_init_cmdlines();
-	init_irq_work(&trace_work_wakeup, trace_wake_up);
 
 	register_tracer(&nop_trace);
 
+	global_trace.current_trace = &nop_trace;
+
 	/* All seems OK, enable tracing */
 	tracing_disabled = 0;
 
@@ -5303,16 +6228,32 @@ __init static int tracer_alloc_buffers(void)
 
 	register_die_notifier(&trace_die_notifier);
 
+	global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
+
+	/* Holder for file callbacks */
+	global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
+	global_trace.trace_cpu.tr = &global_trace;
+
+	INIT_LIST_HEAD(&global_trace.systems);
+	INIT_LIST_HEAD(&global_trace.events);
+	list_add(&global_trace.list, &ftrace_trace_arrays);
+
 	while (trace_boot_options) {
 		char *option;
 
 		option = strsep(&trace_boot_options, ",");
-		trace_set_options(option);
+		trace_set_options(&global_trace, option);
 	}
 
+	register_snapshot_cmd();
+
 	return 0;
 
 out_free_cpumask:
+	free_percpu(global_trace.trace_buffer.data);
+#ifdef CONFIG_TRACER_MAX_TRACE
+	free_percpu(global_trace.max_buffer.data);
+#endif
 	free_cpumask_var(tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 57d7e5397d56..711ca7d3e7f1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -13,6 +13,11 @@
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+#include <asm/unistd.h>		/* For NR_SYSCALLS	     */
+#include <asm/syscall.h>	/* some archs define it here */
+#endif
+
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
 
@@ -29,6 +34,7 @@ enum trace_type {
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
 	TRACE_BLK,
+	TRACE_BPUTS,
 
 	__TRACE_LAST_TYPE,
 };
@@ -103,11 +109,6 @@ struct kretprobe_trace_entry_head {
 	unsigned long		ret_ip;
 };
 
-struct uprobe_trace_entry_head {
-	struct trace_entry	ent;
-	unsigned long		ip;
-};
-
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -127,12 +128,21 @@ enum trace_flag_type {
 
 #define TRACE_BUF_SIZE		1024
 
+struct trace_array;
+
+struct trace_cpu {
+	struct trace_array	*tr;
+	struct dentry		*dir;
+	int			cpu;
+};
+
 /*
  * The CPU trace array - it consists of thousands of trace entries
  * plus some other descriptor data: (for example which task started
  * the trace, etc.)
  */
 struct trace_array_cpu {
+	struct trace_cpu	trace_cpu;
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
@@ -151,20 +161,83 @@ struct trace_array_cpu {
 	char			comm[TASK_COMM_LEN];
 };
 
+struct tracer;
+
+struct trace_buffer {
+	struct trace_array		*tr;
+	struct ring_buffer		*buffer;
+	struct trace_array_cpu __percpu	*data;
+	cycle_t				time_start;
+	int				cpu;
+};
+
 /*
  * The trace array - an array of per-CPU trace arrays. This is the
  * highest level data structure that individual tracers deal with.
  * They have on/off state as well:
  */
 struct trace_array {
-	struct ring_buffer	*buffer;
-	int			cpu;
+	struct list_head	list;
+	char			*name;
+	struct trace_buffer	trace_buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+	/*
+	 * The max_buffer is used to snapshot the trace when a maximum
+	 * latency is reached, or when the user initiates a snapshot.
+	 * Some tracers will use this to store a maximum trace while
+	 * it continues examining live traces.
+	 *
+	 * The buffers for the max_buffer are set up the same as the trace_buffer
+	 * When a snapshot is taken, the buffer of the max_buffer is swapped
+	 * with the buffer of the trace_buffer and the buffers are reset for
+	 * the trace_buffer so the tracing can continue.
+	 */
+	struct trace_buffer	max_buffer;
+	bool			allocated_snapshot;
+#endif
 	int			buffer_disabled;
-	cycle_t			time_start;
+	struct trace_cpu	trace_cpu;	/* place holder */
+#ifdef CONFIG_FTRACE_SYSCALLS
+	int			sys_refcount_enter;
+	int			sys_refcount_exit;
+	DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
+	DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+#endif
+	int			stop_count;
+	int			clock_id;
+	struct tracer		*current_trace;
+	unsigned int		flags;
+	raw_spinlock_t		start_lock;
+	struct dentry		*dir;
+	struct dentry		*options;
+	struct dentry		*percpu_dir;
+	struct dentry		*event_dir;
+	struct list_head	systems;
+	struct list_head	events;
 	struct task_struct	*waiter;
-	struct trace_array_cpu	*data[NR_CPUS];
+	int			ref;
+};
+
+enum {
+	TRACE_ARRAY_FL_GLOBAL	= (1 << 0)
 };
 
+extern struct list_head ftrace_trace_arrays;
+
+/*
+ * The global tracer (top) should be the first trace array added,
+ * but we check the flag anyway.
+ */
+static inline struct trace_array *top_trace_array(void)
+{
+	struct trace_array *tr;
+
+	tr = list_entry(ftrace_trace_arrays.prev,
+			typeof(*tr), list);
+	WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
+	return tr;
+}
+
 #define FTRACE_CMP_TYPE(var, type) \
 	__builtin_types_compatible_p(typeof(var), type *)
 
@@ -200,6 +273,7 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
+		IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS);	\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
@@ -283,11 +357,16 @@ struct tracer {
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
+	/* Return 0 if OK with change, else return non-zero */
+	int			(*flag_changed)(struct tracer *tracer,
+						u32 mask, int set);
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	bool			print_max;
+	bool			enabled;
+#ifdef CONFIG_TRACER_MAX_TRACE
 	bool			use_max_tr;
-	bool			allocated_snapshot;
+#endif
 };
 
 
@@ -423,8 +502,6 @@ static __always_inline void trace_clear_recursion(int bit)
 	current->trace_recursion = val;
 }
 
-#define TRACE_PIPE_ALL_CPU	-1
-
 static inline struct ring_buffer_iter *
 trace_buffer_iter(struct trace_iterator *iter, int cpu)
 {
@@ -435,10 +512,10 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
-void tracing_reset(struct trace_array *tr, int cpu);
-void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset(struct trace_buffer *buf, int cpu);
+void tracing_reset_online_cpus(struct trace_buffer *buf);
 void tracing_reset_current(int cpu);
-void tracing_reset_current_online_cpus(void);
+void tracing_reset_all_online_cpus(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 struct dentry *trace_create_file(const char *name,
 				 umode_t mode,
@@ -446,6 +523,7 @@ struct dentry *trace_create_file(const char *name,
 				 void *data,
 				 const struct file_operations *fops);
 
+struct dentry *tracing_init_dentry_tr(struct trace_array *tr);
 struct dentry *tracing_init_dentry(void);
 
 struct ring_buffer_event;
@@ -579,7 +657,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
 #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
 extern int DYN_FTRACE_TEST_NAME2(void);
 
-extern int ring_buffer_expanded;
+extern bool ring_buffer_expanded;
 extern bool tracing_selftest_disabled;
 DECLARE_PER_CPU(int, ftrace_cpu_disabled);
 
@@ -615,6 +693,8 @@ trace_array_vprintk(struct trace_array *tr,
 		    unsigned long ip, const char *fmt, va_list args);
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...);
+int trace_array_printk_buf(struct ring_buffer *buffer,
+			   unsigned long ip, const char *fmt, ...);
 void trace_printk_seq(struct trace_seq *s);
 enum print_line_t print_trace_line(struct trace_iterator *iter);
 
@@ -782,6 +862,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_STOP_ON_FREE		= 0x400000,
 	TRACE_ITER_IRQ_INFO		= 0x800000,
 	TRACE_ITER_MARKERS		= 0x1000000,
+	TRACE_ITER_FUNCTION		= 0x2000000,
 };
 
 /*
@@ -828,8 +909,8 @@ enum {
 
 struct ftrace_event_field {
 	struct list_head	link;
-	char			*name;
-	char			*type;
+	const char		*name;
+	const char		*type;
 	int			filter_type;
 	int			offset;
 	int			size;
@@ -847,12 +928,19 @@ struct event_filter {
 struct event_subsystem {
 	struct list_head	list;
 	const char		*name;
-	struct dentry		*entry;
 	struct event_filter	*filter;
-	int			nr_events;
 	int			ref_count;
 };
 
+struct ftrace_subsystem_dir {
+	struct list_head		list;
+	struct event_subsystem		*subsystem;
+	struct trace_array		*tr;
+	struct dentry			*entry;
+	int				ref_count;
+	int				nr_events;
+};
+
 #define FILTER_PRED_INVALID	((unsigned short)-1)
 #define FILTER_PRED_IS_RIGHT	(1 << 15)
 #define FILTER_PRED_FOLD	(1 << 15)
@@ -902,22 +990,20 @@ struct filter_pred {
 	unsigned short		right;
 };
 
-extern struct list_head ftrace_common_fields;
-
 extern enum regex_type
 filter_parse_regex(char *buff, int len, char **search, int *not);
 extern void print_event_filter(struct ftrace_event_call *call,
 			       struct trace_seq *s);
 extern int apply_event_filter(struct ftrace_event_call *call,
 			      char *filter_string);
-extern int apply_subsystem_event_filter(struct event_subsystem *system,
+extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 					char *filter_string);
 extern void print_subsystem_event_filter(struct event_subsystem *system,
 					 struct trace_seq *s);
 extern int filter_assign_type(const char *type);
 
-struct list_head *
-trace_get_fields(struct ftrace_event_call *event_call);
+struct ftrace_event_field *
+trace_find_event_field(struct ftrace_event_call *call, char *name);
 
 static inline int
 filter_check_discard(struct ftrace_event_call *call, void *rec,
@@ -934,6 +1020,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
 }
 
 extern void trace_event_enable_cmd_record(bool enable);
+extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
+extern int event_trace_del_tracer(struct trace_array *tr);
 
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
@@ -943,6 +1031,19 @@ extern const char *__stop___trace_bprintk_fmt[];
 
 void trace_printk_init_buffers(void);
 void trace_printk_start_comm(void);
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
+
+/*
+ * Normal trace_printk() and friends allocates special buffers
+ * to do the manipulation, as well as saves the print formats
+ * into sections to display. But the trace infrastructure wants
+ * to use these without the added overhead at the price of being
+ * a bit slower (used mainly for warnings, where we don't care
+ * about performance). The internal_trace_puts() is for such
+ * a purpose.
+ */
+#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str))
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 95e96842ed29..d594da0dc03c 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -32,6 +32,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 {
 	struct ftrace_event_call *call = &event_branch;
 	struct trace_array *tr = branch_tracer;
+	struct trace_array_cpu *data;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
 	struct ring_buffer *buffer;
@@ -51,11 +52,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
-	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+	if (atomic_inc_return(&data->disabled) != 1)
 		goto out;
 
 	pc = preempt_count();
-	buffer = tr->buffer;
+	buffer = tr->trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -80,7 +82,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 		__buffer_unlock_commit(buffer, event);
 
  out:
-	atomic_dec(&tr->data[cpu]->disabled);
+	atomic_dec(&data->disabled);
 	local_irq_restore(flags);
 }
 
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index aa8f5f48dae6..26dc348332b7 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -57,6 +57,16 @@ u64 notrace trace_clock(void)
 	return local_clock();
 }
 
+/*
+ * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ */
+u64 notrace trace_clock_jiffies(void)
+{
+	u64 jiffy = jiffies - INITIAL_JIFFIES;
+
+	/* Return nsecs */
+	return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+}
 
 /*
  * trace_clock_global(): special globally coherent trace clock
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 4108e1250ca2..e2d027ac66a2 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -223,8 +223,8 @@ FTRACE_ENTRY(bprint, bprint_entry,
 		__dynamic_array(	u32,	buf	)
 	),
 
-	F_printk("%08lx fmt:%p",
-		 __entry->ip, __entry->fmt),
+	F_printk("%pf: %s",
+		 (void *)__entry->ip, __entry->fmt),
 
 	FILTER_OTHER
 );
@@ -238,8 +238,23 @@ FTRACE_ENTRY(print, print_entry,
 		__dynamic_array(	char,	buf	)
 	),
 
-	F_printk("%08lx %s",
-		 __entry->ip, __entry->buf),
+	F_printk("%pf: %s",
+		 (void *)__entry->ip, __entry->buf),
+
+	FILTER_OTHER
+);
+
+FTRACE_ENTRY(bputs, bputs_entry,
+
+	TRACE_BPUTS,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip	)
+		__field(	const char *,	str	)
+	),
+
+	F_printk("%pf: %s",
+		 (void *)__entry->ip, __entry->str),
 
 	FILTER_OTHER
 );
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 57e9b284250c..53582e982e51 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -34,9 +34,27 @@ char event_storage[EVENT_STORAGE_SIZE];
 EXPORT_SYMBOL_GPL(event_storage);
 
 LIST_HEAD(ftrace_events);
-LIST_HEAD(ftrace_common_fields);
+static LIST_HEAD(ftrace_common_fields);
 
-struct list_head *
+#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
+
+static struct kmem_cache *field_cachep;
+static struct kmem_cache *file_cachep;
+
+/* Double loops, do not use break, only goto's work */
+#define do_for_each_event_file(tr, file)			\
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {	\
+		list_for_each_entry(file, &tr->events, list)
+
+#define do_for_each_event_file_safe(tr, file)			\
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {	\
+		struct ftrace_event_file *___n;				\
+		list_for_each_entry_safe(file, ___n, &tr->events, list)
+
+#define while_for_each_event_file()		\
+	}
+
+static struct list_head *
 trace_get_fields(struct ftrace_event_call *event_call)
 {
 	if (!event_call->class->get_fields)
@@ -44,23 +62,45 @@ trace_get_fields(struct ftrace_event_call *event_call)
 	return event_call->class->get_fields(event_call);
 }
 
+static struct ftrace_event_field *
+__find_event_field(struct list_head *head, char *name)
+{
+	struct ftrace_event_field *field;
+
+	list_for_each_entry(field, head, link) {
+		if (!strcmp(field->name, name))
+			return field;
+	}
+
+	return NULL;
+}
+
+struct ftrace_event_field *
+trace_find_event_field(struct ftrace_event_call *call, char *name)
+{
+	struct ftrace_event_field *field;
+	struct list_head *head;
+
+	field = __find_event_field(&ftrace_common_fields, name);
+	if (field)
+		return field;
+
+	head = trace_get_fields(call);
+	return __find_event_field(head, name);
+}
+
 static int __trace_define_field(struct list_head *head, const char *type,
 				const char *name, int offset, int size,
 				int is_signed, int filter_type)
 {
 	struct ftrace_event_field *field;
 
-	field = kzalloc(sizeof(*field), GFP_KERNEL);
+	field = kmem_cache_alloc(field_cachep, GFP_TRACE);
 	if (!field)
 		goto err;
 
-	field->name = kstrdup(name, GFP_KERNEL);
-	if (!field->name)
-		goto err;
-
-	field->type = kstrdup(type, GFP_KERNEL);
-	if (!field->type)
-		goto err;
+	field->name = name;
+	field->type = type;
 
 	if (filter_type == FILTER_OTHER)
 		field->filter_type = filter_assign_type(type);
@@ -76,9 +116,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
 	return 0;
 
 err:
-	if (field)
-		kfree(field->name);
-	kfree(field);
+	kmem_cache_free(field_cachep, field);
 
 	return -ENOMEM;
 }
@@ -120,7 +158,7 @@ static int trace_define_common_fields(void)
 	return ret;
 }
 
-void trace_destroy_fields(struct ftrace_event_call *call)
+static void trace_destroy_fields(struct ftrace_event_call *call)
 {
 	struct ftrace_event_field *field, *next;
 	struct list_head *head;
@@ -128,9 +166,7 @@ void trace_destroy_fields(struct ftrace_event_call *call)
 	head = trace_get_fields(call);
 	list_for_each_entry_safe(field, next, head, link) {
 		list_del(&field->link);
-		kfree(field->type);
-		kfree(field->name);
-		kfree(field);
+		kmem_cache_free(field_cachep, field);
 	}
 }
 
@@ -149,15 +185,17 @@ EXPORT_SYMBOL_GPL(trace_event_raw_init);
 int ftrace_event_reg(struct ftrace_event_call *call,
 		     enum trace_reg type, void *data)
 {
+	struct ftrace_event_file *file = data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
 		return tracepoint_probe_register(call->name,
 						 call->class->probe,
-						 call);
+						 file);
 	case TRACE_REG_UNREGISTER:
 		tracepoint_probe_unregister(call->name,
 					    call->class->probe,
-					    call);
+					    file);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
@@ -183,54 +221,100 @@ EXPORT_SYMBOL_GPL(ftrace_event_reg);
 
 void trace_event_enable_cmd_record(bool enable)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_file *file;
+	struct trace_array *tr;
 
 	mutex_lock(&event_mutex);
-	list_for_each_entry(call, &ftrace_events, list) {
-		if (!(call->flags & TRACE_EVENT_FL_ENABLED))
+	do_for_each_event_file(tr, file) {
+
+		if (!(file->flags & FTRACE_EVENT_FL_ENABLED))
 			continue;
 
 		if (enable) {
 			tracing_start_cmdline_record();
-			call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+			set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
 		} else {
 			tracing_stop_cmdline_record();
-			call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+			clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
 		}
-	}
+	} while_for_each_event_file();
 	mutex_unlock(&event_mutex);
 }
 
-static int ftrace_event_enable_disable(struct ftrace_event_call *call,
-					int enable)
+static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
+					 int enable, int soft_disable)
 {
+	struct ftrace_event_call *call = file->event_call;
 	int ret = 0;
+	int disable;
 
 	switch (enable) {
 	case 0:
-		if (call->flags & TRACE_EVENT_FL_ENABLED) {
-			call->flags &= ~TRACE_EVENT_FL_ENABLED;
-			if (call->flags & TRACE_EVENT_FL_RECORDED_CMD) {
+		/*
+		 * When soft_disable is set and enable is cleared, we want
+		 * to clear the SOFT_DISABLED flag but leave the event in the
+		 * state that it was. That is, if the event was enabled and
+		 * SOFT_DISABLED isn't set, then do nothing. But if SOFT_DISABLED
+		 * is set we do not want the event to be enabled before we
+		 * clear the bit.
+		 *
+		 * When soft_disable is not set but the SOFT_MODE flag is,
+		 * we do nothing. Do not disable the tracepoint, otherwise
+		 * "soft enable"s (clearing the SOFT_DISABLED bit) wont work.
+		 */
+		if (soft_disable) {
+			disable = file->flags & FTRACE_EVENT_FL_SOFT_DISABLED;
+			clear_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags);
+		} else
+			disable = !(file->flags & FTRACE_EVENT_FL_SOFT_MODE);
+
+		if (disable && (file->flags & FTRACE_EVENT_FL_ENABLED)) {
+			clear_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags);
+			if (file->flags & FTRACE_EVENT_FL_RECORDED_CMD) {
 				tracing_stop_cmdline_record();
-				call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+				clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
 			}
-			call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
+			call->class->reg(call, TRACE_REG_UNREGISTER, file);
 		}
+		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT */
+		if (file->flags & FTRACE_EVENT_FL_SOFT_MODE)
+			set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
 		break;
 	case 1:
-		if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
+		/*
+		 * When soft_disable is set and enable is set, we want to
+		 * register the tracepoint for the event, but leave the event
+		 * as is. That means, if the event was already enabled, we do
+		 * nothing (but set SOFT_MODE). If the event is disabled, we
+		 * set SOFT_DISABLED before enabling the event tracepoint, so
+		 * it still seems to be disabled.
+		 */
+		if (!soft_disable)
+			clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
+		else
+			set_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags);
+
+		if (!(file->flags & FTRACE_EVENT_FL_ENABLED)) {
+
+			/* Keep the event disabled, when going to SOFT_MODE. */
+			if (soft_disable)
+				set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
+
 			if (trace_flags & TRACE_ITER_RECORD_CMD) {
 				tracing_start_cmdline_record();
-				call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+				set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
 			}
-			ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
+			ret = call->class->reg(call, TRACE_REG_REGISTER, file);
 			if (ret) {
 				tracing_stop_cmdline_record();
 				pr_info("event trace: Could not enable event "
 					"%s\n", call->name);
 				break;
 			}
-			call->flags |= TRACE_EVENT_FL_ENABLED;
+			set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags);
+
+			/* WAS_ENABLED gets set but never cleared. */
+			call->flags |= TRACE_EVENT_FL_WAS_ENABLED;
 		}
 		break;
 	}
@@ -238,13 +322,19 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 	return ret;
 }
 
-static void ftrace_clear_events(void)
+static int ftrace_event_enable_disable(struct ftrace_event_file *file,
+				       int enable)
 {
-	struct ftrace_event_call *call;
+	return __ftrace_event_enable_disable(file, enable, 0);
+}
+
+static void ftrace_clear_events(struct trace_array *tr)
+{
+	struct ftrace_event_file *file;
 
 	mutex_lock(&event_mutex);
-	list_for_each_entry(call, &ftrace_events, list) {
-		ftrace_event_enable_disable(call, 0);
+	list_for_each_entry(file, &tr->events, list) {
+		ftrace_event_enable_disable(file, 0);
 	}
 	mutex_unlock(&event_mutex);
 }
@@ -257,11 +347,12 @@ static void __put_system(struct event_subsystem *system)
 	if (--system->ref_count)
 		return;
 
+	list_del(&system->list);
+
 	if (filter) {
 		kfree(filter->filter_string);
 		kfree(filter);
 	}
-	kfree(system->name);
 	kfree(system);
 }
 
@@ -271,24 +362,45 @@ static void __get_system(struct event_subsystem *system)
 	system->ref_count++;
 }
 
-static void put_system(struct event_subsystem *system)
+static void __get_system_dir(struct ftrace_subsystem_dir *dir)
+{
+	WARN_ON_ONCE(dir->ref_count == 0);
+	dir->ref_count++;
+	__get_system(dir->subsystem);
+}
+
+static void __put_system_dir(struct ftrace_subsystem_dir *dir)
+{
+	WARN_ON_ONCE(dir->ref_count == 0);
+	/* If the subsystem is about to be freed, the dir must be too */
+	WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1);
+
+	__put_system(dir->subsystem);
+	if (!--dir->ref_count)
+		kfree(dir);
+}
+
+static void put_system(struct ftrace_subsystem_dir *dir)
 {
 	mutex_lock(&event_mutex);
-	__put_system(system);
+	__put_system_dir(dir);
 	mutex_unlock(&event_mutex);
 }
 
 /*
  * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
  */
-static int __ftrace_set_clr_event(const char *match, const char *sub,
-				  const char *event, int set)
+static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
+				  const char *sub, const char *event, int set)
 {
+	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
-	list_for_each_entry(call, &ftrace_events, list) {
+	list_for_each_entry(file, &tr->events, list) {
+
+		call = file->event_call;
 
 		if (!call->name || !call->class || !call->class->reg)
 			continue;
@@ -307,7 +419,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
 		if (event && strcmp(event, call->name) != 0)
 			continue;
 
-		ftrace_event_enable_disable(call, set);
+		ftrace_event_enable_disable(file, set);
 
 		ret = 0;
 	}
@@ -316,7 +428,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
 	return ret;
 }
 
-static int ftrace_set_clr_event(char *buf, int set)
+static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
 {
 	char *event = NULL, *sub = NULL, *match;
 
@@ -344,7 +456,7 @@ static int ftrace_set_clr_event(char *buf, int set)
 			event = NULL;
 	}
 
-	return __ftrace_set_clr_event(match, sub, event, set);
+	return __ftrace_set_clr_event(tr, match, sub, event, set);
 }
 
 /**
@@ -361,7 +473,9 @@ static int ftrace_set_clr_event(char *buf, int set)
  */
 int trace_set_clr_event(const char *system, const char *event, int set)
 {
-	return __ftrace_set_clr_event(NULL, system, event, set);
+	struct trace_array *tr = top_trace_array();
+
+	return __ftrace_set_clr_event(tr, NULL, system, event, set);
 }
 EXPORT_SYMBOL_GPL(trace_set_clr_event);
 
@@ -373,6 +487,8 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_parser parser;
+	struct seq_file *m = file->private_data;
+	struct trace_array *tr = m->private;
 	ssize_t read, ret;
 
 	if (!cnt)
@@ -395,7 +511,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 
 		parser.buffer[parser.idx] = 0;
 
-		ret = ftrace_set_clr_event(parser.buffer + !set, set);
+		ret = ftrace_set_clr_event(tr, parser.buffer + !set, set);
 		if (ret)
 			goto out_put;
 	}
@@ -411,17 +527,20 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct ftrace_event_call *call = v;
+	struct ftrace_event_file *file = v;
+	struct ftrace_event_call *call;
+	struct trace_array *tr = m->private;
 
 	(*pos)++;
 
-	list_for_each_entry_continue(call, &ftrace_events, list) {
+	list_for_each_entry_continue(file, &tr->events, list) {
+		call = file->event_call;
 		/*
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
 		if (call->class && call->class->reg)
-			return call;
+			return file;
 	}
 
 	return NULL;
@@ -429,30 +548,32 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_file *file;
+	struct trace_array *tr = m->private;
 	loff_t l;
 
 	mutex_lock(&event_mutex);
 
-	call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+	file = list_entry(&tr->events, struct ftrace_event_file, list);
 	for (l = 0; l <= *pos; ) {
-		call = t_next(m, call, &l);
-		if (!call)
+		file = t_next(m, file, &l);
+		if (!file)
 			break;
 	}
-	return call;
+	return file;
 }
 
 static void *
 s_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct ftrace_event_call *call = v;
+	struct ftrace_event_file *file = v;
+	struct trace_array *tr = m->private;
 
 	(*pos)++;
 
-	list_for_each_entry_continue(call, &ftrace_events, list) {
-		if (call->flags & TRACE_EVENT_FL_ENABLED)
-			return call;
+	list_for_each_entry_continue(file, &tr->events, list) {
+		if (file->flags & FTRACE_EVENT_FL_ENABLED)
+			return file;
 	}
 
 	return NULL;
@@ -460,23 +581,25 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_file *file;
+	struct trace_array *tr = m->private;
 	loff_t l;
 
 	mutex_lock(&event_mutex);
 
-	call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+	file = list_entry(&tr->events, struct ftrace_event_file, list);
 	for (l = 0; l <= *pos; ) {
-		call = s_next(m, call, &l);
-		if (!call)
+		file = s_next(m, file, &l);
+		if (!file)
 			break;
 	}
-	return call;
+	return file;
 }
 
 static int t_show(struct seq_file *m, void *v)
 {
-	struct ftrace_event_call *call = v;
+	struct ftrace_event_file *file = v;
+	struct ftrace_event_call *call = file->event_call;
 
 	if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
 		seq_printf(m, "%s:", call->class->system);
@@ -494,25 +617,31 @@ static ssize_t
 event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
 {
-	struct ftrace_event_call *call = filp->private_data;
+	struct ftrace_event_file *file = filp->private_data;
 	char *buf;
 
-	if (call->flags & TRACE_EVENT_FL_ENABLED)
-		buf = "1\n";
-	else
+	if (file->flags & FTRACE_EVENT_FL_ENABLED) {
+		if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)
+			buf = "0*\n";
+		else
+			buf = "1\n";
+	} else
 		buf = "0\n";
 
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf));
 }
 
 static ssize_t
 event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
-	struct ftrace_event_call *call = filp->private_data;
+	struct ftrace_event_file *file = filp->private_data;
 	unsigned long val;
 	int ret;
 
+	if (!file)
+		return -EINVAL;
+
 	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
 	if (ret)
 		return ret;
@@ -525,7 +654,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	case 0:
 	case 1:
 		mutex_lock(&event_mutex);
-		ret = ftrace_event_enable_disable(call, val);
+		ret = ftrace_event_enable_disable(file, val);
 		mutex_unlock(&event_mutex);
 		break;
 
@@ -543,14 +672,18 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
 	const char set_to_char[4] = { '?', '0', '1', 'X' };
-	struct event_subsystem *system = filp->private_data;
+	struct ftrace_subsystem_dir *dir = filp->private_data;
+	struct event_subsystem *system = dir->subsystem;
 	struct ftrace_event_call *call;
+	struct ftrace_event_file *file;
+	struct trace_array *tr = dir->tr;
 	char buf[2];
 	int set = 0;
 	int ret;
 
 	mutex_lock(&event_mutex);
-	list_for_each_entry(call, &ftrace_events, list) {
+	list_for_each_entry(file, &tr->events, list) {
+		call = file->event_call;
 		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
@@ -562,7 +695,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		 * or if all events or cleared, or if we have
 		 * a mixture.
 		 */
-		set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
+		set |= (1 << !!(file->flags & FTRACE_EVENT_FL_ENABLED));
 
 		/*
 		 * If we have a mixture, no need to look further.
@@ -584,7 +717,8 @@ static ssize_t
 system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		    loff_t *ppos)
 {
-	struct event_subsystem *system = filp->private_data;
+	struct ftrace_subsystem_dir *dir = filp->private_data;
+	struct event_subsystem *system = dir->subsystem;
 	const char *name = NULL;
 	unsigned long val;
 	ssize_t ret;
@@ -607,7 +741,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	if (system)
 		name = system->name;
 
-	ret = __ftrace_set_clr_event(NULL, name, NULL, val);
+	ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val);
 	if (ret)
 		goto out;
 
@@ -845,43 +979,75 @@ static LIST_HEAD(event_subsystems);
 static int subsystem_open(struct inode *inode, struct file *filp)
 {
 	struct event_subsystem *system = NULL;
+	struct ftrace_subsystem_dir *dir = NULL; /* Initialize for gcc */
+	struct trace_array *tr;
 	int ret;
 
-	if (!inode->i_private)
-		goto skip_search;
-
 	/* Make sure the system still exists */
 	mutex_lock(&event_mutex);
-	list_for_each_entry(system, &event_subsystems, list) {
-		if (system == inode->i_private) {
-			/* Don't open systems with no events */
-			if (!system->nr_events) {
-				system = NULL;
-				break;
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		list_for_each_entry(dir, &tr->systems, list) {
+			if (dir == inode->i_private) {
+				/* Don't open systems with no events */
+				if (dir->nr_events) {
+					__get_system_dir(dir);
+					system = dir->subsystem;
+				}
+				goto exit_loop;
 			}
-			__get_system(system);
-			break;
 		}
 	}
+ exit_loop:
 	mutex_unlock(&event_mutex);
 
-	if (system != inode->i_private)
+	if (!system)
 		return -ENODEV;
 
- skip_search:
+	/* Some versions of gcc think dir can be uninitialized here */
+	WARN_ON(!dir);
+
 	ret = tracing_open_generic(inode, filp);
-	if (ret < 0 && system)
-		put_system(system);
+	if (ret < 0)
+		put_system(dir);
+
+	return ret;
+}
+
+static int system_tr_open(struct inode *inode, struct file *filp)
+{
+	struct ftrace_subsystem_dir *dir;
+	struct trace_array *tr = inode->i_private;
+	int ret;
+
+	/* Make a temporary dir that has no system but points to tr */
+	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+	if (!dir)
+		return -ENOMEM;
+
+	dir->tr = tr;
+
+	ret = tracing_open_generic(inode, filp);
+	if (ret < 0)
+		kfree(dir);
+
+	filp->private_data = dir;
 
 	return ret;
 }
 
 static int subsystem_release(struct inode *inode, struct file *file)
 {
-	struct event_subsystem *system = inode->i_private;
+	struct ftrace_subsystem_dir *dir = file->private_data;
 
-	if (system)
-		put_system(system);
+	/*
+	 * If dir->subsystem is NULL, then this is a temporary
+	 * descriptor that was made for a trace_array to enable
+	 * all subsystems.
+	 */
+	if (dir->subsystem)
+		put_system(dir);
+	else
+		kfree(dir);
 
 	return 0;
 }
@@ -890,7 +1056,8 @@ static ssize_t
 subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 		      loff_t *ppos)
 {
-	struct event_subsystem *system = filp->private_data;
+	struct ftrace_subsystem_dir *dir = filp->private_data;
+	struct event_subsystem *system = dir->subsystem;
 	struct trace_seq *s;
 	int r;
 
@@ -915,7 +1082,7 @@ static ssize_t
 subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		       loff_t *ppos)
 {
-	struct event_subsystem *system = filp->private_data;
+	struct ftrace_subsystem_dir *dir = filp->private_data;
 	char *buf;
 	int err;
 
@@ -932,7 +1099,7 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	}
 	buf[cnt] = '\0';
 
-	err = apply_subsystem_event_filter(system, buf);
+	err = apply_subsystem_event_filter(dir, buf);
 	free_page((unsigned long) buf);
 	if (err < 0)
 		return err;
@@ -1041,30 +1208,35 @@ static const struct file_operations ftrace_system_enable_fops = {
 	.release = subsystem_release,
 };
 
+static const struct file_operations ftrace_tr_enable_fops = {
+	.open = system_tr_open,
+	.read = system_enable_read,
+	.write = system_enable_write,
+	.llseek = default_llseek,
+	.release = subsystem_release,
+};
+
 static const struct file_operations ftrace_show_header_fops = {
 	.open = tracing_open_generic,
 	.read = show_header,
 	.llseek = default_llseek,
 };
 
-static struct dentry *event_trace_events_dir(void)
+static int
+ftrace_event_open(struct inode *inode, struct file *file,
+		  const struct seq_operations *seq_ops)
 {
-	static struct dentry *d_tracer;
-	static struct dentry *d_events;
-
-	if (d_events)
-		return d_events;
-
-	d_tracer = tracing_init_dentry();
-	if (!d_tracer)
-		return NULL;
+	struct seq_file *m;
+	int ret;
 
-	d_events = debugfs_create_dir("events", d_tracer);
-	if (!d_events)
-		pr_warning("Could not create debugfs "
-			   "'events' directory\n");
+	ret = seq_open(file, seq_ops);
+	if (ret < 0)
+		return ret;
+	m = file->private_data;
+	/* copy tr over to seq ops */
+	m->private = inode->i_private;
 
-	return d_events;
+	return ret;
 }
 
 static int
@@ -1072,117 +1244,165 @@ ftrace_event_avail_open(struct inode *inode, struct file *file)
 {
 	const struct seq_operations *seq_ops = &show_event_seq_ops;
 
-	return seq_open(file, seq_ops);
+	return ftrace_event_open(inode, file, seq_ops);
 }
 
 static int
 ftrace_event_set_open(struct inode *inode, struct file *file)
 {
 	const struct seq_operations *seq_ops = &show_set_event_seq_ops;
+	struct trace_array *tr = inode->i_private;
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
-		ftrace_clear_events();
+		ftrace_clear_events(tr);
 
-	return seq_open(file, seq_ops);
+	return ftrace_event_open(inode, file, seq_ops);
+}
+
+static struct event_subsystem *
+create_new_subsystem(const char *name)
+{
+	struct event_subsystem *system;
+
+	/* need to create new entry */
+	system = kmalloc(sizeof(*system), GFP_KERNEL);
+	if (!system)
+		return NULL;
+
+	system->ref_count = 1;
+	system->name = name;
+
+	system->filter = NULL;
+
+	system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+	if (!system->filter)
+		goto out_free;
+
+	list_add(&system->list, &event_subsystems);
+
+	return system;
+
+ out_free:
+	kfree(system);
+	return NULL;
 }
 
 static struct dentry *
-event_subsystem_dir(const char *name, struct dentry *d_events)
+event_subsystem_dir(struct trace_array *tr, const char *name,
+		    struct ftrace_event_file *file, struct dentry *parent)
 {
+	struct ftrace_subsystem_dir *dir;
 	struct event_subsystem *system;
 	struct dentry *entry;
 
 	/* First see if we did not already create this dir */
-	list_for_each_entry(system, &event_subsystems, list) {
+	list_for_each_entry(dir, &tr->systems, list) {
+		system = dir->subsystem;
 		if (strcmp(system->name, name) == 0) {
-			system->nr_events++;
-			return system->entry;
+			dir->nr_events++;
+			file->system = dir;
+			return dir->entry;
 		}
 	}
 
-	/* need to create new entry */
-	system = kmalloc(sizeof(*system), GFP_KERNEL);
-	if (!system) {
-		pr_warning("No memory to create event subsystem %s\n",
-			   name);
-		return d_events;
+	/* Now see if the system itself exists. */
+	list_for_each_entry(system, &event_subsystems, list) {
+		if (strcmp(system->name, name) == 0)
+			break;
 	}
+	/* Reset system variable when not found */
+	if (&system->list == &event_subsystems)
+		system = NULL;
 
-	system->entry = debugfs_create_dir(name, d_events);
-	if (!system->entry) {
-		pr_warning("Could not create event subsystem %s\n",
-			   name);
-		kfree(system);
-		return d_events;
-	}
+	dir = kmalloc(sizeof(*dir), GFP_KERNEL);
+	if (!dir)
+		goto out_fail;
 
-	system->nr_events = 1;
-	system->ref_count = 1;
-	system->name = kstrdup(name, GFP_KERNEL);
-	if (!system->name) {
-		debugfs_remove(system->entry);
-		kfree(system);
-		return d_events;
+	if (!system) {
+		system = create_new_subsystem(name);
+		if (!system)
+			goto out_free;
+	} else
+		__get_system(system);
+
+	dir->entry = debugfs_create_dir(name, parent);
+	if (!dir->entry) {
+		pr_warning("Failed to create system directory %s\n", name);
+		__put_system(system);
+		goto out_free;
 	}
 
-	list_add(&system->list, &event_subsystems);
-
-	system->filter = NULL;
-
-	system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
-	if (!system->filter) {
-		pr_warning("Could not allocate filter for subsystem "
-			   "'%s'\n", name);
-		return system->entry;
-	}
+	dir->tr = tr;
+	dir->ref_count = 1;
+	dir->nr_events = 1;
+	dir->subsystem = system;
+	file->system = dir;
 
-	entry = debugfs_create_file("filter", 0644, system->entry, system,
+	entry = debugfs_create_file("filter", 0644, dir->entry, dir,
 				    &ftrace_subsystem_filter_fops);
 	if (!entry) {
 		kfree(system->filter);
 		system->filter = NULL;
-		pr_warning("Could not create debugfs "
-			   "'%s/filter' entry\n", name);
+		pr_warning("Could not create debugfs '%s/filter' entry\n", name);
 	}
 
-	trace_create_file("enable", 0644, system->entry, system,
+	trace_create_file("enable", 0644, dir->entry, dir,
 			  &ftrace_system_enable_fops);
 
-	return system->entry;
+	list_add(&dir->list, &tr->systems);
+
+	return dir->entry;
+
+ out_free:
+	kfree(dir);
+ out_fail:
+	/* Only print this message if failed on memory allocation */
+	if (!dir || !system)
+		pr_warning("No memory to create event subsystem %s\n",
+			   name);
+	return NULL;
 }
 
 static int
-event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+event_create_dir(struct dentry *parent,
+		 struct ftrace_event_file *file,
 		 const struct file_operations *id,
 		 const struct file_operations *enable,
 		 const struct file_operations *filter,
 		 const struct file_operations *format)
 {
+	struct ftrace_event_call *call = file->event_call;
+	struct trace_array *tr = file->tr;
 	struct list_head *head;
+	struct dentry *d_events;
 	int ret;
 
 	/*
 	 * If the trace point header did not define TRACE_SYSTEM
 	 * then the system would be called "TRACE_SYSTEM".
 	 */
-	if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
-		d_events = event_subsystem_dir(call->class->system, d_events);
-
-	call->dir = debugfs_create_dir(call->name, d_events);
-	if (!call->dir) {
-		pr_warning("Could not create debugfs "
-			   "'%s' directory\n", call->name);
+	if (strcmp(call->class->system, TRACE_SYSTEM) != 0) {
+		d_events = event_subsystem_dir(tr, call->class->system, file, parent);
+		if (!d_events)
+			return -ENOMEM;
+	} else
+		d_events = parent;
+
+	file->dir = debugfs_create_dir(call->name, d_events);
+	if (!file->dir) {
+		pr_warning("Could not create debugfs '%s' directory\n",
+			   call->name);
 		return -1;
 	}
 
 	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
-		trace_create_file("enable", 0644, call->dir, call,
+		trace_create_file("enable", 0644, file->dir, file,
 				  enable);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (call->event.type && call->class->reg)
-		trace_create_file("id", 0444, call->dir, call,
+		trace_create_file("id", 0444, file->dir, call,
 		 		  id);
 #endif
 
@@ -1196,23 +1416,76 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		if (ret < 0) {
 			pr_warning("Could not initialize trace point"
 				   " events/%s\n", call->name);
-			return ret;
+			return -1;
 		}
 	}
-	trace_create_file("filter", 0644, call->dir, call,
+	trace_create_file("filter", 0644, file->dir, call,
 			  filter);
 
-	trace_create_file("format", 0444, call->dir, call,
+	trace_create_file("format", 0444, file->dir, call,
 			  format);
 
 	return 0;
 }
 
+static void remove_subsystem(struct ftrace_subsystem_dir *dir)
+{
+	if (!dir)
+		return;
+
+	if (!--dir->nr_events) {
+		debugfs_remove_recursive(dir->entry);
+		list_del(&dir->list);
+		__put_system_dir(dir);
+	}
+}
+
+static void remove_event_from_tracers(struct ftrace_event_call *call)
+{
+	struct ftrace_event_file *file;
+	struct trace_array *tr;
+
+	do_for_each_event_file_safe(tr, file) {
+
+		if (file->event_call != call)
+			continue;
+
+		list_del(&file->list);
+		debugfs_remove_recursive(file->dir);
+		remove_subsystem(file->system);
+		kmem_cache_free(file_cachep, file);
+
+		/*
+		 * The do_for_each_event_file_safe() is
+		 * a double loop. After finding the call for this
+		 * trace_array, we use break to jump to the next
+		 * trace_array.
+		 */
+		break;
+	} while_for_each_event_file();
+}
+
 static void event_remove(struct ftrace_event_call *call)
 {
-	ftrace_event_enable_disable(call, 0);
+	struct trace_array *tr;
+	struct ftrace_event_file *file;
+
+	do_for_each_event_file(tr, file) {
+		if (file->event_call != call)
+			continue;
+		ftrace_event_enable_disable(file, 0);
+		/*
+		 * The do_for_each_event_file() is
+		 * a double loop. After finding the call for this
+		 * trace_array, we use break to jump to the next
+		 * trace_array.
+		 */
+		break;
+	} while_for_each_event_file();
+
 	if (call->event.funcs)
 		__unregister_ftrace_event(&call->event);
+	remove_event_from_tracers(call);
 	list_del(&call->list);
 }
 
@@ -1234,82 +1507,99 @@ static int event_init(struct ftrace_event_call *call)
 }
 
 static int
-__trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
-		       const struct file_operations *id,
-		       const struct file_operations *enable,
-		       const struct file_operations *filter,
-		       const struct file_operations *format)
+__register_event(struct ftrace_event_call *call, struct module *mod)
 {
-	struct dentry *d_events;
 	int ret;
 
 	ret = event_init(call);
 	if (ret < 0)
 		return ret;
 
-	d_events = event_trace_events_dir();
-	if (!d_events)
-		return -ENOENT;
-
-	ret = event_create_dir(call, d_events, id, enable, filter, format);
-	if (!ret)
-		list_add(&call->list, &ftrace_events);
+	list_add(&call->list, &ftrace_events);
 	call->mod = mod;
 
-	return ret;
+	return 0;
+}
+
+/* Add an event to a trace directory */
+static int
+__trace_add_new_event(struct ftrace_event_call *call,
+		      struct trace_array *tr,
+		      const struct file_operations *id,
+		      const struct file_operations *enable,
+		      const struct file_operations *filter,
+		      const struct file_operations *format)
+{
+	struct ftrace_event_file *file;
+
+	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
+	if (!file)
+		return -ENOMEM;
+
+	file->event_call = call;
+	file->tr = tr;
+	list_add(&file->list, &tr->events);
+
+	return event_create_dir(tr->event_dir, file, id, enable, filter, format);
 }
 
+/*
+ * Just create a decriptor for early init. A descriptor is required
+ * for enabling events at boot. We want to enable events before
+ * the filesystem is initialized.
+ */
+static __init int
+__trace_early_add_new_event(struct ftrace_event_call *call,
+			    struct trace_array *tr)
+{
+	struct ftrace_event_file *file;
+
+	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
+	if (!file)
+		return -ENOMEM;
+
+	file->event_call = call;
+	file->tr = tr;
+	list_add(&file->list, &tr->events);
+
+	return 0;
+}
+
+struct ftrace_module_file_ops;
+static void __add_event_to_tracers(struct ftrace_event_call *call,
+				   struct ftrace_module_file_ops *file_ops);
+
 /* Add an additional event_call dynamically */
 int trace_add_event_call(struct ftrace_event_call *call)
 {
 	int ret;
 	mutex_lock(&event_mutex);
-	ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
-				     &ftrace_enable_fops,
-				     &ftrace_event_filter_fops,
-				     &ftrace_event_format_fops);
-	mutex_unlock(&event_mutex);
-	return ret;
-}
 
-static void remove_subsystem_dir(const char *name)
-{
-	struct event_subsystem *system;
-
-	if (strcmp(name, TRACE_SYSTEM) == 0)
-		return;
+	ret = __register_event(call, NULL);
+	if (ret >= 0)
+		__add_event_to_tracers(call, NULL);
 
-	list_for_each_entry(system, &event_subsystems, list) {
-		if (strcmp(system->name, name) == 0) {
-			if (!--system->nr_events) {
-				debugfs_remove_recursive(system->entry);
-				list_del(&system->list);
-				__put_system(system);
-			}
-			break;
-		}
-	}
+	mutex_unlock(&event_mutex);
+	return ret;
 }
 
 /*
- * Must be called under locking both of event_mutex and trace_event_mutex.
+ * Must be called under locking both of event_mutex and trace_event_sem.
  */
 static void __trace_remove_event_call(struct ftrace_event_call *call)
 {
 	event_remove(call);
 	trace_destroy_fields(call);
 	destroy_preds(call);
-	debugfs_remove_recursive(call->dir);
-	remove_subsystem_dir(call->class->system);
 }
 
 /* Remove an event_call */
 void trace_remove_event_call(struct ftrace_event_call *call)
 {
 	mutex_lock(&event_mutex);
-	down_write(&trace_event_mutex);
+	down_write(&trace_event_sem);
 	__trace_remove_event_call(call);
-	up_write(&trace_event_mutex);
+	up_write(&trace_event_sem);
 	mutex_unlock(&event_mutex);
 }
 
@@ -1336,6 +1626,26 @@ struct ftrace_module_file_ops {
 };
 
 static struct ftrace_module_file_ops *
+find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod)
+{
+	/*
+	 * As event_calls are added in groups by module,
+	 * when we find one file_ops, we don't need to search for
+	 * each call in that module, as the rest should be the
+	 * same. Only search for a new one if the last one did
+	 * not match.
+	 */
+	if (file_ops && mod == file_ops->mod)
+		return file_ops;
+
+	list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+		if (file_ops->mod == mod)
+			return file_ops;
+	}
+	return NULL;
+}
+
+static struct ftrace_module_file_ops *
 trace_create_file_ops(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops;
@@ -1386,9 +1696,8 @@ static void trace_module_add_events(struct module *mod)
 		return;
 
 	for_each_event(call, start, end) {
-		__trace_add_event_call(*call, mod,
-				       &file_ops->id, &file_ops->enable,
-				       &file_ops->filter, &file_ops->format);
+		__register_event(*call, mod);
+		__add_event_to_tracers(*call, file_ops);
 	}
 }
 
@@ -1396,12 +1705,13 @@ static void trace_module_remove_events(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops;
 	struct ftrace_event_call *call, *p;
-	bool found = false;
+	bool clear_trace = false;
 
-	down_write(&trace_event_mutex);
+	down_write(&trace_event_sem);
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		if (call->mod == mod) {
-			found = true;
+			if (call->flags & TRACE_EVENT_FL_WAS_ENABLED)
+				clear_trace = true;
 			__trace_remove_event_call(call);
 		}
 	}
@@ -1415,14 +1725,18 @@ static void trace_module_remove_events(struct module *mod)
 		list_del(&file_ops->list);
 		kfree(file_ops);
 	}
+	up_write(&trace_event_sem);
 
 	/*
 	 * It is safest to reset the ring buffer if the module being unloaded
-	 * registered any events.
+	 * registered any events that were used. The only worry is if
+	 * a new module gets loaded, and takes on the same id as the events
+	 * of this module. When printing out the buffer, traced events left
+	 * over from this module may be passed to the new module events and
+	 * unexpected results may occur.
 	 */
-	if (found)
-		tracing_reset_current_online_cpus();
-	up_write(&trace_event_mutex);
+	if (clear_trace)
+		tracing_reset_all_online_cpus();
 }
 
 static int trace_module_notify(struct notifier_block *self,
@@ -1443,14 +1757,433 @@ static int trace_module_notify(struct notifier_block *self,
 
 	return 0;
 }
+
+static int
+__trace_add_new_mod_event(struct ftrace_event_call *call,
+			  struct trace_array *tr,
+			  struct ftrace_module_file_ops *file_ops)
+{
+	return __trace_add_new_event(call, tr,
+				     &file_ops->id, &file_ops->enable,
+				     &file_ops->filter, &file_ops->format);
+}
+
 #else
-static int trace_module_notify(struct notifier_block *self,
-			       unsigned long val, void *data)
+static inline struct ftrace_module_file_ops *
+find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod)
+{
+	return NULL;
+}
+static inline int trace_module_notify(struct notifier_block *self,
+				      unsigned long val, void *data)
 {
 	return 0;
 }
+static inline int
+__trace_add_new_mod_event(struct ftrace_event_call *call,
+			  struct trace_array *tr,
+			  struct ftrace_module_file_ops *file_ops)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_MODULES */
 
+/* Create a new event directory structure for a trace directory. */
+static void
+__trace_add_event_dirs(struct trace_array *tr)
+{
+	struct ftrace_module_file_ops *file_ops = NULL;
+	struct ftrace_event_call *call;
+	int ret;
+
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (call->mod) {
+			/*
+			 * Directories for events by modules need to
+			 * keep module ref counts when opened (as we don't
+			 * want the module to disappear when reading one
+			 * of these files). The file_ops keep account of
+			 * the module ref count.
+			 */
+			file_ops = find_ftrace_file_ops(file_ops, call->mod);
+			if (!file_ops)
+				continue; /* Warn? */
+			ret = __trace_add_new_mod_event(call, tr, file_ops);
+			if (ret < 0)
+				pr_warning("Could not create directory for event %s\n",
+					   call->name);
+			continue;
+		}
+		ret = __trace_add_new_event(call, tr,
+					    &ftrace_event_id_fops,
+					    &ftrace_enable_fops,
+					    &ftrace_event_filter_fops,
+					    &ftrace_event_format_fops);
+		if (ret < 0)
+			pr_warning("Could not create directory for event %s\n",
+				   call->name);
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR	"enable_event"
+#define DISABLE_EVENT_STR	"disable_event"
+
+struct event_probe_data {
+	struct ftrace_event_file	*file;
+	unsigned long			count;
+	int				ref;
+	bool				enable;
+};
+
+static struct ftrace_event_file *
+find_event_file(struct trace_array *tr, const char *system,  const char *event)
+{
+	struct ftrace_event_file *file;
+	struct ftrace_event_call *call;
+
+	list_for_each_entry(file, &tr->events, list) {
+
+		call = file->event_call;
+
+		if (!call->name || !call->class || !call->class->reg)
+			continue;
+
+		if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
+			continue;
+
+		if (strcmp(event, call->name) == 0 &&
+		    strcmp(system, call->class->system) == 0)
+			return file;
+	}
+	return NULL;
+}
+
+static void
+event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+{
+	struct event_probe_data **pdata = (struct event_probe_data **)_data;
+	struct event_probe_data *data = *pdata;
+
+	if (!data)
+		return;
+
+	if (data->enable)
+		clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags);
+	else
+		set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags);
+}
+
+static void
+event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+{
+	struct event_probe_data **pdata = (struct event_probe_data **)_data;
+	struct event_probe_data *data = *pdata;
+
+	if (!data)
+		return;
+
+	if (!data->count)
+		return;
+
+	/* Skip if the event is in a state we want to switch to */
+	if (data->enable == !(data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+		return;
+
+	if (data->count != -1)
+		(data->count)--;
+
+	event_enable_probe(ip, parent_ip, _data);
+}
+
+static int
+event_enable_print(struct seq_file *m, unsigned long ip,
+		      struct ftrace_probe_ops *ops, void *_data)
+{
+	struct event_probe_data *data = _data;
+
+	seq_printf(m, "%ps:", (void *)ip);
+
+	seq_printf(m, "%s:%s:%s",
+		   data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+		   data->file->event_call->class->system,
+		   data->file->event_call->name);
+
+	if (data->count == -1)
+		seq_printf(m, ":unlimited\n");
+	else
+		seq_printf(m, ":count=%ld\n", data->count);
+
+	return 0;
+}
+
+static int
+event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip,
+		  void **_data)
+{
+	struct event_probe_data **pdata = (struct event_probe_data **)_data;
+	struct event_probe_data *data = *pdata;
+
+	data->ref++;
+	return 0;
+}
+
+static void
+event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip,
+		  void **_data)
+{
+	struct event_probe_data **pdata = (struct event_probe_data **)_data;
+	struct event_probe_data *data = *pdata;
+
+	if (WARN_ON_ONCE(data->ref <= 0))
+		return;
+
+	data->ref--;
+	if (!data->ref) {
+		/* Remove the SOFT_MODE flag */
+		__ftrace_event_enable_disable(data->file, 0, 1);
+		module_put(data->file->event_call->mod);
+		kfree(data);
+	}
+	*pdata = NULL;
+}
+
+static struct ftrace_probe_ops event_enable_probe_ops = {
+	.func			= event_enable_probe,
+	.print			= event_enable_print,
+	.init			= event_enable_init,
+	.free			= event_enable_free,
+};
+
+static struct ftrace_probe_ops event_enable_count_probe_ops = {
+	.func			= event_enable_count_probe,
+	.print			= event_enable_print,
+	.init			= event_enable_init,
+	.free			= event_enable_free,
+};
+
+static struct ftrace_probe_ops event_disable_probe_ops = {
+	.func			= event_enable_probe,
+	.print			= event_enable_print,
+	.init			= event_enable_init,
+	.free			= event_enable_free,
+};
+
+static struct ftrace_probe_ops event_disable_count_probe_ops = {
+	.func			= event_enable_count_probe,
+	.print			= event_enable_print,
+	.init			= event_enable_init,
+	.free			= event_enable_free,
+};
+
+static int
+event_enable_func(struct ftrace_hash *hash,
+		  char *glob, char *cmd, char *param, int enabled)
+{
+	struct trace_array *tr = top_trace_array();
+	struct ftrace_event_file *file;
+	struct ftrace_probe_ops *ops;
+	struct event_probe_data *data;
+	const char *system;
+	const char *event;
+	char *number;
+	bool enable;
+	int ret;
+
+	/* hash funcs only work with set_ftrace_filter */
+	if (!enabled)
+		return -EINVAL;
+
+	if (!param)
+		return -EINVAL;
+
+	system = strsep(&param, ":");
+	if (!param)
+		return -EINVAL;
+
+	event = strsep(&param, ":");
+
+	mutex_lock(&event_mutex);
+
+	ret = -EINVAL;
+	file = find_event_file(tr, system, event);
+	if (!file)
+		goto out;
+
+	enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+	if (enable)
+		ops = param ? &event_enable_count_probe_ops : &event_enable_probe_ops;
+	else
+		ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops;
+
+	if (glob[0] == '!') {
+		unregister_ftrace_function_probe_func(glob+1, ops);
+		ret = 0;
+		goto out;
+	}
+
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out;
+
+	data->enable = enable;
+	data->count = -1;
+	data->file = file;
+
+	if (!param)
+		goto out_reg;
+
+	number = strsep(&param, ":");
+
+	ret = -EINVAL;
+	if (!strlen(number))
+		goto out_free;
+
+	/*
+	 * We use the callback data field (which is a pointer)
+	 * as our counter.
+	 */
+	ret = kstrtoul(number, 0, &data->count);
+	if (ret)
+		goto out_free;
+
+ out_reg:
+	/* Don't let event modules unload while probe registered */
+	ret = try_module_get(file->event_call->mod);
+	if (!ret)
+		goto out_free;
+
+	ret = __ftrace_event_enable_disable(file, 1, 1);
+	if (ret < 0)
+		goto out_put;
+	ret = register_ftrace_function_probe(glob, ops, data);
+	if (!ret)
+		goto out_disable;
+ out:
+	mutex_unlock(&event_mutex);
+	return ret;
+
+ out_disable:
+	__ftrace_event_enable_disable(file, 0, 1);
+ out_put:
+	module_put(file->event_call->mod);
+ out_free:
+	kfree(data);
+	goto out;
+}
+
+static struct ftrace_func_command event_enable_cmd = {
+	.name			= ENABLE_EVENT_STR,
+	.func			= event_enable_func,
+};
+
+static struct ftrace_func_command event_disable_cmd = {
+	.name			= DISABLE_EVENT_STR,
+	.func			= event_enable_func,
+};
+
+static __init int register_event_cmds(void)
+{
+	int ret;
+
+	ret = register_ftrace_command(&event_enable_cmd);
+	if (WARN_ON(ret < 0))
+		return ret;
+	ret = register_ftrace_command(&event_disable_cmd);
+	if (WARN_ON(ret < 0))
+		unregister_ftrace_command(&event_enable_cmd);
+	return ret;
+}
+#else
+static inline int register_event_cmds(void) { return 0; }
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * The top level array has already had its ftrace_event_file
+ * descriptors created in order to allow for early events to
+ * be recorded. This function is called after the debugfs has been
+ * initialized, and we now have to create the files associated
+ * to the events.
+ */
+static __init void
+__trace_early_add_event_dirs(struct trace_array *tr)
+{
+	struct ftrace_event_file *file;
+	int ret;
+
+
+	list_for_each_entry(file, &tr->events, list) {
+		ret = event_create_dir(tr->event_dir, file,
+				       &ftrace_event_id_fops,
+				       &ftrace_enable_fops,
+				       &ftrace_event_filter_fops,
+				       &ftrace_event_format_fops);
+		if (ret < 0)
+			pr_warning("Could not create directory for event %s\n",
+				   file->event_call->name);
+	}
+}
+
+/*
+ * For early boot up, the top trace array requires to have
+ * a list of events that can be enabled. This must be done before
+ * the filesystem is set up in order to allow events to be traced
+ * early.
+ */
+static __init void
+__trace_early_add_events(struct trace_array *tr)
+{
+	struct ftrace_event_call *call;
+	int ret;
+
+	list_for_each_entry(call, &ftrace_events, list) {
+		/* Early boot up should not have any modules loaded */
+		if (WARN_ON_ONCE(call->mod))
+			continue;
+
+		ret = __trace_early_add_new_event(call, tr);
+		if (ret < 0)
+			pr_warning("Could not create early event %s\n",
+				   call->name);
+	}
+}
+
+/* Remove the event directory structure for a trace directory. */
+static void
+__trace_remove_event_dirs(struct trace_array *tr)
+{
+	struct ftrace_event_file *file, *next;
+
+	list_for_each_entry_safe(file, next, &tr->events, list) {
+		list_del(&file->list);
+		debugfs_remove_recursive(file->dir);
+		remove_subsystem(file->system);
+		kmem_cache_free(file_cachep, file);
+	}
+}
+
+static void
+__add_event_to_tracers(struct ftrace_event_call *call,
+		       struct ftrace_module_file_ops *file_ops)
+{
+	struct trace_array *tr;
+
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (file_ops)
+			__trace_add_new_mod_event(call, tr, file_ops);
+		else
+			__trace_add_new_event(call, tr,
+					      &ftrace_event_id_fops,
+					      &ftrace_enable_fops,
+					      &ftrace_event_filter_fops,
+					      &ftrace_event_format_fops);
+	}
+}
+
 static struct notifier_block trace_module_nb = {
 	.notifier_call = trace_module_notify,
 	.priority = 0,
@@ -1464,15 +2197,135 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
 static __init int setup_trace_event(char *str)
 {
 	strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
-	ring_buffer_expanded = 1;
-	tracing_selftest_disabled = 1;
+	ring_buffer_expanded = true;
+	tracing_selftest_disabled = true;
 
 	return 1;
 }
 __setup("trace_event=", setup_trace_event);
 
+/* Expects to have event_mutex held when called */
+static int
+create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
+{
+	struct dentry *d_events;
+	struct dentry *entry;
+
+	entry = debugfs_create_file("set_event", 0644, parent,
+				    tr, &ftrace_set_event_fops);
+	if (!entry) {
+		pr_warning("Could not create debugfs 'set_event' entry\n");
+		return -ENOMEM;
+	}
+
+	d_events = debugfs_create_dir("events", parent);
+	if (!d_events) {
+		pr_warning("Could not create debugfs 'events' directory\n");
+		return -ENOMEM;
+	}
+
+	/* ring buffer internal formats */
+	trace_create_file("header_page", 0444, d_events,
+			  ring_buffer_print_page_header,
+			  &ftrace_show_header_fops);
+
+	trace_create_file("header_event", 0444, d_events,
+			  ring_buffer_print_entry_header,
+			  &ftrace_show_header_fops);
+
+	trace_create_file("enable", 0644, d_events,
+			  tr, &ftrace_tr_enable_fops);
+
+	tr->event_dir = d_events;
+
+	return 0;
+}
+
+/**
+ * event_trace_add_tracer - add a instance of a trace_array to events
+ * @parent: The parent dentry to place the files/directories for events in
+ * @tr: The trace array associated with these events
+ *
+ * When a new instance is created, it needs to set up its events
+ * directory, as well as other files associated with events. It also
+ * creates the event hierachry in the @parent/events directory.
+ *
+ * Returns 0 on success.
+ */
+int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
+{
+	int ret;
+
+	mutex_lock(&event_mutex);
+
+	ret = create_event_toplevel_files(parent, tr);
+	if (ret)
+		goto out_unlock;
+
+	down_write(&trace_event_sem);
+	__trace_add_event_dirs(tr);
+	up_write(&trace_event_sem);
+
+ out_unlock:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+/*
+ * The top trace array already had its file descriptors created.
+ * Now the files themselves need to be created.
+ */
+static __init int
+early_event_add_tracer(struct dentry *parent, struct trace_array *tr)
+{
+	int ret;
+
+	mutex_lock(&event_mutex);
+
+	ret = create_event_toplevel_files(parent, tr);
+	if (ret)
+		goto out_unlock;
+
+	down_write(&trace_event_sem);
+	__trace_early_add_event_dirs(tr);
+	up_write(&trace_event_sem);
+
+ out_unlock:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+int event_trace_del_tracer(struct trace_array *tr)
+{
+	/* Disable any running events */
+	__ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
+
+	mutex_lock(&event_mutex);
+
+	down_write(&trace_event_sem);
+	__trace_remove_event_dirs(tr);
+	debugfs_remove_recursive(tr->event_dir);
+	up_write(&trace_event_sem);
+
+	tr->event_dir = NULL;
+
+	mutex_unlock(&event_mutex);
+
+	return 0;
+}
+
+static __init int event_trace_memsetup(void)
+{
+	field_cachep = KMEM_CACHE(ftrace_event_field, SLAB_PANIC);
+	file_cachep = KMEM_CACHE(ftrace_event_file, SLAB_PANIC);
+	return 0;
+}
+
 static __init int event_trace_enable(void)
 {
+	struct trace_array *tr = top_trace_array();
 	struct ftrace_event_call **iter, *call;
 	char *buf = bootup_event_buf;
 	char *token;
@@ -1486,6 +2339,14 @@ static __init int event_trace_enable(void)
 			list_add(&call->list, &ftrace_events);
 	}
 
+	/*
+	 * We need the top trace array to have a working set of trace
+	 * points at early init, before the debug files and directories
+	 * are created. Create the file entries now, and attach them
+	 * to the actual file dentries later.
+	 */
+	__trace_early_add_events(tr);
+
 	while (true) {
 		token = strsep(&buf, ",");
 
@@ -1494,73 +2355,43 @@ static __init int event_trace_enable(void)
 		if (!*token)
 			continue;
 
-		ret = ftrace_set_clr_event(token, 1);
+		ret = ftrace_set_clr_event(tr, token, 1);
 		if (ret)
 			pr_warn("Failed to enable trace event: %s\n", token);
 	}
 
 	trace_printk_start_comm();
 
+	register_event_cmds();
+
 	return 0;
 }
 
 static __init int event_trace_init(void)
 {
-	struct ftrace_event_call *call;
+	struct trace_array *tr;
 	struct dentry *d_tracer;
 	struct dentry *entry;
-	struct dentry *d_events;
 	int ret;
 
+	tr = top_trace_array();
+
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
 		return 0;
 
 	entry = debugfs_create_file("available_events", 0444, d_tracer,
-				    NULL, &ftrace_avail_fops);
+				    tr, &ftrace_avail_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs "
 			   "'available_events' entry\n");
 
-	entry = debugfs_create_file("set_event", 0644, d_tracer,
-				    NULL, &ftrace_set_event_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_event' entry\n");
-
-	d_events = event_trace_events_dir();
-	if (!d_events)
-		return 0;
-
-	/* ring buffer internal formats */
-	trace_create_file("header_page", 0444, d_events,
-			  ring_buffer_print_page_header,
-			  &ftrace_show_header_fops);
-
-	trace_create_file("header_event", 0444, d_events,
-			  ring_buffer_print_entry_header,
-			  &ftrace_show_header_fops);
-
-	trace_create_file("enable", 0644, d_events,
-			  NULL, &ftrace_system_enable_fops);
-
 	if (trace_define_common_fields())
 		pr_warning("tracing: Failed to allocate common fields");
 
-	/*
-	 * Early initialization already enabled ftrace event.
-	 * Now it's only necessary to create the event directory.
-	 */
-	list_for_each_entry(call, &ftrace_events, list) {
-
-		ret = event_create_dir(call, d_events,
-				       &ftrace_event_id_fops,
-				       &ftrace_enable_fops,
-				       &ftrace_event_filter_fops,
-				       &ftrace_event_format_fops);
-		if (ret < 0)
-			event_remove(call);
-	}
+	ret = early_event_add_tracer(d_tracer, tr);
+	if (ret)
+		return ret;
 
 	ret = register_module_notifier(&trace_module_nb);
 	if (ret)
@@ -1568,6 +2399,7 @@ static __init int event_trace_init(void)
 
 	return 0;
 }
+early_initcall(event_trace_memsetup);
 core_initcall(event_trace_enable);
 fs_initcall(event_trace_init);
 
@@ -1627,13 +2459,20 @@ static __init void event_test_stuff(void)
  */
 static __init void event_trace_self_tests(void)
 {
+	struct ftrace_subsystem_dir *dir;
+	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
 	struct event_subsystem *system;
+	struct trace_array *tr;
 	int ret;
 
+	tr = top_trace_array();
+
 	pr_info("Running tests on trace events:\n");
 
-	list_for_each_entry(call, &ftrace_events, list) {
+	list_for_each_entry(file, &tr->events, list) {
+
+		call = file->event_call;
 
 		/* Only test those that have a probe */
 		if (!call->class || !call->class->probe)
@@ -1657,15 +2496,15 @@ static __init void event_trace_self_tests(void)
 		 * If an event is already enabled, someone is using
 		 * it and the self test should not be on.
 		 */
-		if (call->flags & TRACE_EVENT_FL_ENABLED) {
+		if (file->flags & FTRACE_EVENT_FL_ENABLED) {
 			pr_warning("Enabled event during self test!\n");
 			WARN_ON_ONCE(1);
 			continue;
 		}
 
-		ftrace_event_enable_disable(call, 1);
+		ftrace_event_enable_disable(file, 1);
 		event_test_stuff();
-		ftrace_event_enable_disable(call, 0);
+		ftrace_event_enable_disable(file, 0);
 
 		pr_cont("OK\n");
 	}
@@ -1674,7 +2513,9 @@ static __init void event_trace_self_tests(void)
 
 	pr_info("Running tests on trace event systems:\n");
 
-	list_for_each_entry(system, &event_subsystems, list) {
+	list_for_each_entry(dir, &tr->systems, list) {
+
+		system = dir->subsystem;
 
 		/* the ftrace system is special, skip it */
 		if (strcmp(system->name, "ftrace") == 0)
@@ -1682,7 +2523,7 @@ static __init void event_trace_self_tests(void)
 
 		pr_info("Testing event system %s: ", system->name);
 
-		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
+		ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1);
 		if (WARN_ON_ONCE(ret)) {
 			pr_warning("error enabling system %s\n",
 				   system->name);
@@ -1691,7 +2532,7 @@ static __init void event_trace_self_tests(void)
 
 		event_test_stuff();
 
-		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
+		ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0);
 		if (WARN_ON_ONCE(ret)) {
 			pr_warning("error disabling system %s\n",
 				   system->name);
@@ -1706,7 +2547,7 @@ static __init void event_trace_self_tests(void)
 	pr_info("Running tests on all trace events:\n");
 	pr_info("Testing all events: ");
 
-	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
+	ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warning("error enabling all events\n");
 		return;
@@ -1715,7 +2556,7 @@ static __init void event_trace_self_tests(void)
 	event_test_stuff();
 
 	/* reset sysname */
-	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
+	ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warning("error disabling all events\n");
 		return;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e5b0ca8b8d4d..a6361178de5a 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -658,33 +658,6 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 	mutex_unlock(&event_mutex);
 }
 
-static struct ftrace_event_field *
-__find_event_field(struct list_head *head, char *name)
-{
-	struct ftrace_event_field *field;
-
-	list_for_each_entry(field, head, link) {
-		if (!strcmp(field->name, name))
-			return field;
-	}
-
-	return NULL;
-}
-
-static struct ftrace_event_field *
-find_event_field(struct ftrace_event_call *call, char *name)
-{
-	struct ftrace_event_field *field;
-	struct list_head *head;
-
-	field = __find_event_field(&ftrace_common_fields, name);
-	if (field)
-		return field;
-
-	head = trace_get_fields(call);
-	return __find_event_field(head, name);
-}
-
 static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
 {
 	stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL);
@@ -1337,7 +1310,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps,
 		return NULL;
 	}
 
-	field = find_event_field(call, operand1);
+	field = trace_find_event_field(call, operand1);
 	if (!field) {
 		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
 		return NULL;
@@ -1907,16 +1880,17 @@ out_unlock:
 	return err;
 }
 
-int apply_subsystem_event_filter(struct event_subsystem *system,
+int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 				 char *filter_string)
 {
+	struct event_subsystem *system = dir->subsystem;
 	struct event_filter *filter;
 	int err = 0;
 
 	mutex_lock(&event_mutex);
 
 	/* Make sure the system still has events */
-	if (!system->nr_events) {
+	if (!dir->nr_events) {
 		err = -ENODEV;
 		goto out_unlock;
 	}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index e039906b037d..d21a74670088 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -129,7 +129,7 @@ static void __always_unused ____ftrace_check_##name(void)		\
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
-int									\
+static int __init							\
 ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 {									\
 	struct struct_name field;					\
@@ -168,7 +168,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 #define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
 			 regfn)						\
 									\
-struct ftrace_event_class event_class_ftrace_##call = {			\
+struct ftrace_event_class __refdata event_class_ftrace_##call = {	\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.define_fields		= ftrace_define_fields_##call,		\
 	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 601152523326..c4d6d7191988 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -28,7 +28,7 @@ static void tracing_stop_function_trace(void);
 static int function_trace_init(struct trace_array *tr)
 {
 	func_trace = tr;
-	tr->cpu = get_cpu();
+	tr->trace_buffer.cpu = get_cpu();
 	put_cpu();
 
 	tracing_start_cmdline_record();
@@ -44,7 +44,7 @@ static void function_trace_reset(struct trace_array *tr)
 
 static void function_trace_start(struct trace_array *tr)
 {
-	tracing_reset_online_cpus(tr);
+	tracing_reset_online_cpus(&tr->trace_buffer);
 }
 
 /* Our option */
@@ -76,7 +76,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 		goto out;
 
 	cpu = smp_processor_id();
-	data = tr->data[cpu];
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	if (!atomic_read(&data->disabled)) {
 		local_save_flags(flags);
 		trace_function(tr, ip, parent_ip, flags, pc);
@@ -107,7 +107,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	 */
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);
 
 	if (likely(disabled == 1)) {
@@ -214,66 +214,89 @@ static struct tracer function_trace __read_mostly =
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-static void
-ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
+static int update_count(void **data)
 {
-	long *count = (long *)data;
-
-	if (tracing_is_on())
-		return;
+	unsigned long *count = (long *)data;
 
 	if (!*count)
-		return;
+		return 0;
 
 	if (*count != -1)
 		(*count)--;
 
-	tracing_on();
+	return 1;
 }
 
 static void
-ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, void **data)
 {
-	long *count = (long *)data;
+	if (tracing_is_on())
+		return;
+
+	if (update_count(data))
+		tracing_on();
+}
 
+static void
+ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, void **data)
+{
 	if (!tracing_is_on())
 		return;
 
-	if (!*count)
+	if (update_count(data))
+		tracing_off();
+}
+
+static void
+ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	if (tracing_is_on())
 		return;
 
-	if (*count != -1)
-		(*count)--;
+	tracing_on();
+}
+
+static void
+ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	if (!tracing_is_on())
+		return;
 
 	tracing_off();
 }
 
-static int
-ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
-			 struct ftrace_probe_ops *ops, void *data);
+/*
+ * Skip 4:
+ *   ftrace_stacktrace()
+ *   function_trace_probe_call()
+ *   ftrace_ops_list_func()
+ *   ftrace_call()
+ */
+#define STACK_SKIP 4
 
-static struct ftrace_probe_ops traceon_probe_ops = {
-	.func			= ftrace_traceon,
-	.print			= ftrace_trace_onoff_print,
-};
+static void
+ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	trace_dump_stack(STACK_SKIP);
+}
 
-static struct ftrace_probe_ops traceoff_probe_ops = {
-	.func			= ftrace_traceoff,
-	.print			= ftrace_trace_onoff_print,
-};
+static void
+ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	if (!tracing_is_on())
+		return;
+
+	if (update_count(data))
+		trace_dump_stack(STACK_SKIP);
+}
 
 static int
-ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
-			 struct ftrace_probe_ops *ops, void *data)
+ftrace_probe_print(const char *name, struct seq_file *m,
+		   unsigned long ip, void *data)
 {
 	long count = (long)data;
 
-	seq_printf(m, "%ps:", (void *)ip);
-
-	if (ops == &traceon_probe_ops)
-		seq_printf(m, "traceon");
-	else
-		seq_printf(m, "traceoff");
+	seq_printf(m, "%ps:%s", (void *)ip, name);
 
 	if (count == -1)
 		seq_printf(m, ":unlimited\n");
@@ -284,26 +307,61 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
 }
 
 static int
-ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param)
+ftrace_traceon_print(struct seq_file *m, unsigned long ip,
+			 struct ftrace_probe_ops *ops, void *data)
 {
-	struct ftrace_probe_ops *ops;
-
-	/* we register both traceon and traceoff to this callback */
-	if (strcmp(cmd, "traceon") == 0)
-		ops = &traceon_probe_ops;
-	else
-		ops = &traceoff_probe_ops;
+	return ftrace_probe_print("traceon", m, ip, data);
+}
 
-	unregister_ftrace_function_probe_func(glob, ops);
+static int
+ftrace_traceoff_print(struct seq_file *m, unsigned long ip,
+			 struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("traceoff", m, ip, data);
+}
 
-	return 0;
+static int
+ftrace_stacktrace_print(struct seq_file *m, unsigned long ip,
+			struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("stacktrace", m, ip, data);
 }
 
+static struct ftrace_probe_ops traceon_count_probe_ops = {
+	.func			= ftrace_traceon_count,
+	.print			= ftrace_traceon_print,
+};
+
+static struct ftrace_probe_ops traceoff_count_probe_ops = {
+	.func			= ftrace_traceoff_count,
+	.print			= ftrace_traceoff_print,
+};
+
+static struct ftrace_probe_ops stacktrace_count_probe_ops = {
+	.func			= ftrace_stacktrace_count,
+	.print			= ftrace_stacktrace_print,
+};
+
+static struct ftrace_probe_ops traceon_probe_ops = {
+	.func			= ftrace_traceon,
+	.print			= ftrace_traceon_print,
+};
+
+static struct ftrace_probe_ops traceoff_probe_ops = {
+	.func			= ftrace_traceoff,
+	.print			= ftrace_traceoff_print,
+};
+
+static struct ftrace_probe_ops stacktrace_probe_ops = {
+	.func			= ftrace_stacktrace,
+	.print			= ftrace_stacktrace_print,
+};
+
 static int
-ftrace_trace_onoff_callback(struct ftrace_hash *hash,
-			    char *glob, char *cmd, char *param, int enable)
+ftrace_trace_probe_callback(struct ftrace_probe_ops *ops,
+			    struct ftrace_hash *hash, char *glob,
+			    char *cmd, char *param, int enable)
 {
-	struct ftrace_probe_ops *ops;
 	void *count = (void *)-1;
 	char *number;
 	int ret;
@@ -312,14 +370,10 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash,
 	if (!enable)
 		return -EINVAL;
 
-	if (glob[0] == '!')
-		return ftrace_trace_onoff_unreg(glob+1, cmd, param);
-
-	/* we register both traceon and traceoff to this callback */
-	if (strcmp(cmd, "traceon") == 0)
-		ops = &traceon_probe_ops;
-	else
-		ops = &traceoff_probe_ops;
+	if (glob[0] == '!') {
+		unregister_ftrace_function_probe_func(glob+1, ops);
+		return 0;
+	}
 
 	if (!param)
 		goto out_reg;
@@ -343,6 +397,34 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash,
 	return ret < 0 ? ret : 0;
 }
 
+static int
+ftrace_trace_onoff_callback(struct ftrace_hash *hash,
+			    char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	/* we register both traceon and traceoff to this callback */
+	if (strcmp(cmd, "traceon") == 0)
+		ops = param ? &traceon_count_probe_ops : &traceon_probe_ops;
+	else
+		ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops;
+
+	return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+					   param, enable);
+}
+
+static int
+ftrace_stacktrace_callback(struct ftrace_hash *hash,
+			   char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops;
+
+	return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+					   param, enable);
+}
+
 static struct ftrace_func_command ftrace_traceon_cmd = {
 	.name			= "traceon",
 	.func			= ftrace_trace_onoff_callback,
@@ -353,6 +435,11 @@ static struct ftrace_func_command ftrace_traceoff_cmd = {
 	.func			= ftrace_trace_onoff_callback,
 };
 
+static struct ftrace_func_command ftrace_stacktrace_cmd = {
+	.name			= "stacktrace",
+	.func			= ftrace_stacktrace_callback,
+};
+
 static int __init init_func_cmd_traceon(void)
 {
 	int ret;
@@ -364,6 +451,12 @@ static int __init init_func_cmd_traceon(void)
 	ret = register_ftrace_command(&ftrace_traceon_cmd);
 	if (ret)
 		unregister_ftrace_command(&ftrace_traceoff_cmd);
+
+	ret = register_ftrace_command(&ftrace_stacktrace_cmd);
+	if (ret) {
+		unregister_ftrace_command(&ftrace_traceoff_cmd);
+		unregister_ftrace_command(&ftrace_traceon_cmd);
+	}
 	return ret;
 }
 #else
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 39ada66389cc..8388bc99f2ee 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -218,7 +218,7 @@ int __trace_graph_entry(struct trace_array *tr,
 {
 	struct ftrace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ftrace_graph_ent_entry *entry;
 
 	if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
@@ -265,7 +265,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
@@ -323,7 +323,7 @@ void __trace_graph_return(struct trace_array *tr,
 {
 	struct ftrace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ftrace_graph_ret_entry *entry;
 
 	if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
@@ -350,7 +350,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
 
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
@@ -560,9 +560,9 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * We need to consume the current entry to see
 			 * the next one.
 			 */
-			ring_buffer_consume(iter->tr->buffer, iter->cpu,
+			ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu,
 					    NULL, NULL);
-			event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+			event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu,
 						 NULL, NULL);
 		}
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 713a2cac4881..b19d065a28cb 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,8 @@ enum {
 
 static int trace_type __read_mostly;
 
-static int save_lat_flag;
+static int save_flags;
+static bool function_enabled;
 
 static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
 static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -121,7 +122,7 @@ static int func_prolog_dec(struct trace_array *tr,
 	if (!irqs_disabled_flags(*flags))
 		return 0;
 
-	*data = tr->data[cpu];
+	*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	disabled = atomic_inc_return(&(*data)->disabled);
 
 	if (likely(disabled == 1))
@@ -175,7 +176,7 @@ static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
 		per_cpu(tracing_cpu, cpu) = 0;
 
 	tracing_max_latency = 0;
-	tracing_reset_online_cpus(irqsoff_trace);
+	tracing_reset_online_cpus(&irqsoff_trace->trace_buffer);
 
 	return start_irqsoff_tracer(irqsoff_trace, set);
 }
@@ -380,7 +381,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	if (per_cpu(tracing_cpu, cpu))
 		return;
 
-	data = tr->data[cpu];
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 
 	if (unlikely(!data) || atomic_read(&data->disabled))
 		return;
@@ -418,7 +419,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 	if (!tracer_enabled)
 		return;
 
-	data = tr->data[cpu];
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 
 	if (unlikely(!data) ||
 	    !data->critical_start || atomic_read(&data->disabled))
@@ -528,15 +529,60 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
-static int start_irqsoff_tracer(struct trace_array *tr, int graph)
+static int register_irqsoff_function(int graph, int set)
 {
-	int ret = 0;
+	int ret;
 
-	if (!graph)
-		ret = register_ftrace_function(&trace_ops);
-	else
+	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+	if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION)))
+		return 0;
+
+	if (graph)
 		ret = register_ftrace_graph(&irqsoff_graph_return,
 					    &irqsoff_graph_entry);
+	else
+		ret = register_ftrace_function(&trace_ops);
+
+	if (!ret)
+		function_enabled = true;
+
+	return ret;
+}
+
+static void unregister_irqsoff_function(int graph)
+{
+	if (!function_enabled)
+		return;
+
+	if (graph)
+		unregister_ftrace_graph();
+	else
+		unregister_ftrace_function(&trace_ops);
+
+	function_enabled = false;
+}
+
+static void irqsoff_function_set(int set)
+{
+	if (set)
+		register_irqsoff_function(is_graph(), 1);
+	else
+		unregister_irqsoff_function(is_graph());
+}
+
+static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set)
+{
+	if (mask & TRACE_ITER_FUNCTION)
+		irqsoff_function_set(set);
+
+	return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
+{
+	int ret;
+
+	ret = register_irqsoff_function(graph, 0);
 
 	if (!ret && tracing_is_enabled())
 		tracer_enabled = 1;
@@ -550,22 +596,22 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 {
 	tracer_enabled = 0;
 
-	if (!graph)
-		unregister_ftrace_function(&trace_ops);
-	else
-		unregister_ftrace_graph();
+	unregister_irqsoff_function(graph);
 }
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
-	tracing_reset_online_cpus(tr);
+	tracing_reset_online_cpus(&tr->trace_buffer);
 
 	if (start_irqsoff_tracer(tr, is_graph()))
 		printk(KERN_ERR "failed to start irqsoff tracer\n");
@@ -573,10 +619,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_irqsoff_tracer(tr, is_graph());
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
@@ -609,6 +658,7 @@ static struct tracer irqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= irqsoff_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
 #endif
@@ -642,6 +692,7 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= irqsoff_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
 #endif
@@ -677,6 +728,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= irqsoff_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 3c5c5dfea0b3..bd90e1b06088 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -26,7 +26,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
 	trace_init_global_iter(&iter);
 
 	for_each_tracing_cpu(cpu) {
-		atomic_inc(&iter.tr->data[cpu]->disabled);
+		atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
 
 	old_userobj = trace_flags;
@@ -43,17 +43,17 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
 	iter.iter_flags |= TRACE_FILE_LAT_FMT;
 	iter.pos = -1;
 
-	if (cpu_file == TRACE_PIPE_ALL_CPU) {
+	if (cpu_file == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
 			iter.buffer_iter[cpu] =
-			ring_buffer_read_prepare(iter.tr->buffer, cpu);
+			ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu);
 			ring_buffer_read_start(iter.buffer_iter[cpu]);
 			tracing_iter_reset(&iter, cpu);
 		}
 	} else {
 		iter.cpu_file = cpu_file;
 		iter.buffer_iter[cpu_file] =
-			ring_buffer_read_prepare(iter.tr->buffer, cpu_file);
+			ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file);
 		ring_buffer_read_start(iter.buffer_iter[cpu_file]);
 		tracing_iter_reset(&iter, cpu_file);
 	}
@@ -83,7 +83,7 @@ out:
 	trace_flags = old_userobj;
 
 	for_each_tracing_cpu(cpu) {
-		atomic_dec(&iter.tr->data[cpu]->disabled);
+		atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
 
 	for_each_tracing_cpu(cpu)
@@ -115,7 +115,7 @@ static int kdb_ftdump(int argc, const char **argv)
 		    !cpu_online(cpu_file))
 			return KDB_BADINT;
 	} else {
-		cpu_file = TRACE_PIPE_ALL_CPU;
+		cpu_file = RING_BUFFER_ALL_CPUS;
 	}
 
 	kdb_trap_printk++;
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index fd3c8aae55e5..a5e8f4878bfa 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -31,7 +31,7 @@ static void mmio_reset_data(struct trace_array *tr)
 	overrun_detected = false;
 	prev_overruns = 0;
 
-	tracing_reset_online_cpus(tr);
+	tracing_reset_online_cpus(&tr->trace_buffer);
 }
 
 static int mmio_trace_init(struct trace_array *tr)
@@ -128,7 +128,7 @@ static void mmio_close(struct trace_iterator *iter)
 static unsigned long count_overruns(struct trace_iterator *iter)
 {
 	unsigned long cnt = atomic_xchg(&dropped_count, 0);
-	unsigned long over = ring_buffer_overruns(iter->tr->buffer);
+	unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer);
 
 	if (over > prev_overruns)
 		cnt += over - prev_overruns;
@@ -309,7 +309,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 				struct mmiotrace_rw *rw)
 {
 	struct ftrace_event_call *call = &event_mmiotrace_rw;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_rw *entry;
 	int pc = preempt_count();
@@ -330,7 +330,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 void mmio_trace_rw(struct mmiotrace_rw *rw)
 {
 	struct trace_array *tr = mmio_trace_array;
-	struct trace_array_cpu *data = tr->data[smp_processor_id()];
+	struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id());
 	__trace_mmiotrace_rw(tr, data, rw);
 }
 
@@ -339,7 +339,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 				struct mmiotrace_map *map)
 {
 	struct ftrace_event_call *call = &event_mmiotrace_map;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_map *entry;
 	int pc = preempt_count();
@@ -363,7 +363,7 @@ void mmio_trace_mapping(struct mmiotrace_map *map)
 	struct trace_array_cpu *data;
 
 	preempt_disable();
-	data = tr->data[smp_processor_id()];
+	data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id());
 	__trace_mmiotrace_map(tr, data, map);
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 697e88d13907..bb922d9ee51b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -14,7 +14,7 @@
 /* must be a power of 2 */
 #define EVENT_HASHSIZE	128
 
-DECLARE_RWSEM(trace_event_mutex);
+DECLARE_RWSEM(trace_event_sem);
 
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
@@ -37,6 +37,22 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s)
 	return ret;
 }
 
+enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct bputs_entry *field;
+	int ret;
+
+	trace_assign_type(field, entry);
+
+	ret = trace_seq_puts(s, field->str);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
 enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -397,6 +413,32 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 }
 EXPORT_SYMBOL(ftrace_print_hex_seq);
 
+int ftrace_raw_output_prep(struct trace_iterator *iter,
+			   struct trace_event *trace_event)
+{
+	struct ftrace_event_call *event;
+	struct trace_seq *s = &iter->seq;
+	struct trace_seq *p = &iter->tmp_seq;
+	struct trace_entry *entry;
+	int ret;
+
+	event = container_of(trace_event, struct ftrace_event_call, event);
+	entry = iter->ent;
+
+	if (entry->type != event->event.type) {
+		WARN_ON_ONCE(1);
+		return TRACE_TYPE_UNHANDLED;
+	}
+
+	trace_seq_init(p);
+	ret = trace_seq_printf(s, "%s: ", event->name);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return 0;
+}
+EXPORT_SYMBOL(ftrace_raw_output_prep);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
@@ -617,7 +659,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
 {
 	unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE;
 	unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS;
-	unsigned long long abs_ts = iter->ts - iter->tr->time_start;
+	unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start;
 	unsigned long long rel_ts = next_ts - iter->ts;
 	struct trace_seq *s = &iter->seq;
 
@@ -783,12 +825,12 @@ static int trace_search_list(struct list_head **list)
 
 void trace_event_read_lock(void)
 {
-	down_read(&trace_event_mutex);
+	down_read(&trace_event_sem);
 }
 
 void trace_event_read_unlock(void)
 {
-	up_read(&trace_event_mutex);
+	up_read(&trace_event_sem);
 }
 
 /**
@@ -811,7 +853,7 @@ int register_ftrace_event(struct trace_event *event)
 	unsigned key;
 	int ret = 0;
 
-	down_write(&trace_event_mutex);
+	down_write(&trace_event_sem);
 
 	if (WARN_ON(!event))
 		goto out;
@@ -866,14 +908,14 @@ int register_ftrace_event(struct trace_event *event)
 
 	ret = event->type;
  out:
-	up_write(&trace_event_mutex);
+	up_write(&trace_event_sem);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_ftrace_event);
 
 /*
- * Used by module code with the trace_event_mutex held for write.
+ * Used by module code with the trace_event_sem held for write.
  */
 int __unregister_ftrace_event(struct trace_event *event)
 {
@@ -888,9 +930,9 @@ int __unregister_ftrace_event(struct trace_event *event)
  */
 int unregister_ftrace_event(struct trace_event *event)
 {
-	down_write(&trace_event_mutex);
+	down_write(&trace_event_sem);
 	__unregister_ftrace_event(event);
-	up_write(&trace_event_mutex);
+	up_write(&trace_event_sem);
 
 	return 0;
 }
@@ -1217,6 +1259,64 @@ static struct trace_event trace_user_stack_event = {
 	.funcs		= &trace_user_stack_funcs,
 };
 
+/* TRACE_BPUTS */
+static enum print_line_t
+trace_bputs_print(struct trace_iterator *iter, int flags,
+		   struct trace_event *event)
+{
+	struct trace_entry *entry = iter->ent;
+	struct trace_seq *s = &iter->seq;
+	struct bputs_entry *field;
+
+	trace_assign_type(field, entry);
+
+	if (!seq_print_ip_sym(s, field->ip, flags))
+		goto partial;
+
+	if (!trace_seq_puts(s, ": "))
+		goto partial;
+
+	if (!trace_seq_puts(s, field->str))
+		goto partial;
+
+	return TRACE_TYPE_HANDLED;
+
+ partial:
+	return TRACE_TYPE_PARTIAL_LINE;
+}
+
+
+static enum print_line_t
+trace_bputs_raw(struct trace_iterator *iter, int flags,
+		struct trace_event *event)
+{
+	struct bputs_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	if (!trace_seq_printf(s, ": %lx : ", field->ip))
+		goto partial;
+
+	if (!trace_seq_puts(s, field->str))
+		goto partial;
+
+	return TRACE_TYPE_HANDLED;
+
+ partial:
+	return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static struct trace_event_functions trace_bputs_funcs = {
+	.trace		= trace_bputs_print,
+	.raw		= trace_bputs_raw,
+};
+
+static struct trace_event trace_bputs_event = {
+	.type		= TRACE_BPUTS,
+	.funcs		= &trace_bputs_funcs,
+};
+
 /* TRACE_BPRINT */
 static enum print_line_t
 trace_bprint_print(struct trace_iterator *iter, int flags,
@@ -1329,6 +1429,7 @@ static struct trace_event *events[] __initdata = {
 	&trace_wake_event,
 	&trace_stack_event,
 	&trace_user_stack_event,
+	&trace_bputs_event,
 	&trace_bprint_event,
 	&trace_print_event,
 	NULL
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index c038eba0492b..127a9d8c8357 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -5,6 +5,8 @@
 #include "trace.h"
 
 extern enum print_line_t
+trace_print_bputs_msg_only(struct trace_iterator *iter);
+extern enum print_line_t
 trace_print_bprintk_msg_only(struct trace_iterator *iter);
 extern enum print_line_t
 trace_print_printk_msg_only(struct trace_iterator *iter);
@@ -31,7 +33,7 @@ trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 
 /* used by module unregistering */
 extern int __unregister_ftrace_event(struct trace_event *event);
-extern struct rw_semaphore trace_event_mutex;
+extern struct rw_semaphore trace_event_sem;
 
 #define MAX_MEMHEX_BYTES	8
 #define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 3374c792ccd8..4e98e3b257a3 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -28,7 +28,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   unsigned long flags, int pc)
 {
 	struct ftrace_event_call *call = &event_context_switch;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -69,7 +69,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n
 	pc = preempt_count();
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
-	data = ctx_trace->data[cpu];
+	data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu);
 
 	if (likely(!atomic_read(&data->disabled)))
 		tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc);
@@ -86,7 +86,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	struct ftrace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
 					  sizeof(*entry), flags, pc);
@@ -123,7 +123,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
 	pc = preempt_count();
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
-	data = ctx_trace->data[cpu];
+	data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu);
 
 	if (likely(!atomic_read(&data->disabled)))
 		tracing_sched_wakeup_trace(ctx_trace, wakee, current,
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 75aa97fbe1a1..fee77e15d815 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,8 @@ static void __wakeup_reset(struct trace_array *tr);
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
 static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
-static int save_lat_flag;
+static int save_flags;
+static bool function_enabled;
 
 #define TRACE_DISPLAY_GRAPH     1
 
@@ -89,7 +90,7 @@ func_prolog_preempt_disable(struct trace_array *tr,
 	if (cpu != wakeup_current_cpu)
 		goto out_enable;
 
-	*data = tr->data[cpu];
+	*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	disabled = atomic_inc_return(&(*data)->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
@@ -134,15 +135,60 @@ static struct ftrace_ops trace_ops __read_mostly =
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
-static int start_func_tracer(int graph)
+static int register_wakeup_function(int graph, int set)
 {
 	int ret;
 
-	if (!graph)
-		ret = register_ftrace_function(&trace_ops);
-	else
+	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+	if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION)))
+		return 0;
+
+	if (graph)
 		ret = register_ftrace_graph(&wakeup_graph_return,
 					    &wakeup_graph_entry);
+	else
+		ret = register_ftrace_function(&trace_ops);
+
+	if (!ret)
+		function_enabled = true;
+
+	return ret;
+}
+
+static void unregister_wakeup_function(int graph)
+{
+	if (!function_enabled)
+		return;
+
+	if (graph)
+		unregister_ftrace_graph();
+	else
+		unregister_ftrace_function(&trace_ops);
+
+	function_enabled = false;
+}
+
+static void wakeup_function_set(int set)
+{
+	if (set)
+		register_wakeup_function(is_graph(), 1);
+	else
+		unregister_wakeup_function(is_graph());
+}
+
+static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set)
+{
+	if (mask & TRACE_ITER_FUNCTION)
+		wakeup_function_set(set);
+
+	return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_func_tracer(int graph)
+{
+	int ret;
+
+	ret = register_wakeup_function(graph, 0);
 
 	if (!ret && tracing_is_enabled())
 		tracer_enabled = 1;
@@ -156,10 +202,7 @@ static void stop_func_tracer(int graph)
 {
 	tracer_enabled = 0;
 
-	if (!graph)
-		unregister_ftrace_function(&trace_ops);
-	else
-		unregister_ftrace_graph();
+	unregister_wakeup_function(graph);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -353,7 +396,7 @@ probe_wakeup_sched_switch(void *ignore,
 
 	/* disable local data, not wakeup_cpu data */
 	cpu = raw_smp_processor_id();
-	disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
+	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
 	if (likely(disabled != 1))
 		goto out;
 
@@ -365,7 +408,7 @@ probe_wakeup_sched_switch(void *ignore,
 		goto out_unlock;
 
 	/* The task we are waiting for is waking up */
-	data = wakeup_trace->data[wakeup_cpu];
+	data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu);
 
 	__trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
 	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
@@ -387,7 +430,7 @@ out_unlock:
 	arch_spin_unlock(&wakeup_lock);
 	local_irq_restore(flags);
 out:
-	atomic_dec(&wakeup_trace->data[cpu]->disabled);
+	atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
 }
 
 static void __wakeup_reset(struct trace_array *tr)
@@ -405,7 +448,7 @@ static void wakeup_reset(struct trace_array *tr)
 {
 	unsigned long flags;
 
-	tracing_reset_online_cpus(tr);
+	tracing_reset_online_cpus(&tr->trace_buffer);
 
 	local_irq_save(flags);
 	arch_spin_lock(&wakeup_lock);
@@ -435,7 +478,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 		return;
 
 	pc = preempt_count();
-	disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
+	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
 
@@ -458,7 +501,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 
 	local_save_flags(flags);
 
-	data = wakeup_trace->data[wakeup_cpu];
+	data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu);
 	data->preempt_timestamp = ftrace_now(cpu);
 	tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
 
@@ -472,7 +515,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 out_locked:
 	arch_spin_unlock(&wakeup_lock);
 out:
-	atomic_dec(&wakeup_trace->data[cpu]->disabled);
+	atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
 }
 
 static void start_wakeup_tracer(struct trace_array *tr)
@@ -540,8 +583,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	wakeup_trace = tr;
@@ -563,12 +609,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_wakeup_tracer(tr);
 	/* make sure we put back any tasks we are tracing */
 	wakeup_reset(tr);
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
@@ -594,6 +643,7 @@ static struct tracer wakeup_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= wakeup_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
@@ -615,6 +665,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= wakeup_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 51c819c12c29..55e2cf66967b 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -21,13 +21,13 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	return 0;
 }
 
-static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
+static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu)
 {
 	struct ring_buffer_event *event;
 	struct trace_entry *entry;
 	unsigned int loops = 0;
 
-	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
+	while ((event = ring_buffer_consume(buf->buffer, cpu, NULL, NULL))) {
 		entry = ring_buffer_event_data(event);
 
 		/*
@@ -58,7 +58,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
  * Test the trace buffer to see if all the elements
  * are still sane.
  */
-static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
+static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count)
 {
 	unsigned long flags, cnt = 0;
 	int cpu, ret = 0;
@@ -67,7 +67,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	local_irq_save(flags);
 	arch_spin_lock(&ftrace_max_lock);
 
-	cnt = ring_buffer_entries(tr->buffer);
+	cnt = ring_buffer_entries(buf->buffer);
 
 	/*
 	 * The trace_test_buffer_cpu runs a while loop to consume all data.
@@ -78,7 +78,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	 */
 	tracing_off();
 	for_each_possible_cpu(cpu) {
-		ret = trace_test_buffer_cpu(tr, cpu);
+		ret = trace_test_buffer_cpu(buf, cpu);
 		if (ret)
 			break;
 	}
@@ -355,7 +355,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	msleep(100);
 
 	/* we should have nothing in the buffer */
-	ret = trace_test_buffer(tr, &count);
+	ret = trace_test_buffer(&tr->trace_buffer, &count);
 	if (ret)
 		goto out;
 
@@ -376,7 +376,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	ftrace_enabled = 0;
 
 	/* check the trace buffer */
-	ret = trace_test_buffer(tr, &count);
+	ret = trace_test_buffer(&tr->trace_buffer, &count);
 	tracing_start();
 
 	/* we should only have one item */
@@ -666,7 +666,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 	ftrace_enabled = 0;
 
 	/* check the trace buffer */
-	ret = trace_test_buffer(tr, &count);
+	ret = trace_test_buffer(&tr->trace_buffer, &count);
 	trace->reset(tr);
 	tracing_start();
 
@@ -703,8 +703,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 /* Maximum number of functions to trace before diagnosing a hang */
 #define GRAPH_MAX_FUNC_TEST	100000000
 
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
 static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
@@ -714,8 +712,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
 		ftrace_graph_stop();
 		printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
-		if (ftrace_dump_on_oops)
-			__ftrace_dump(false, DUMP_ALL);
+		if (ftrace_dump_on_oops) {
+			ftrace_dump(DUMP_ALL);
+			/* ftrace_dump() disables tracing */
+			tracing_on();
+		}
 		return 0;
 	}
 
@@ -737,7 +738,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 * Simulate the init() callback but we attach a watchdog callback
 	 * to detect and recover from possible hangs
 	 */
-	tracing_reset_online_cpus(tr);
+	tracing_reset_online_cpus(&tr->trace_buffer);
 	set_graph_array(tr);
 	ret = register_ftrace_graph(&trace_graph_return,
 				    &trace_graph_entry_watchdog);
@@ -760,7 +761,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	tracing_stop();
 
 	/* check the trace buffer */
-	ret = trace_test_buffer(tr, &count);
+	ret = trace_test_buffer(&tr->trace_buffer, &count);
 
 	trace->reset(tr);
 	tracing_start();
@@ -815,9 +816,9 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
-	ret = trace_test_buffer(tr, NULL);
+	ret = trace_test_buffer(&tr->trace_buffer, NULL);
 	if (!ret)
-		ret = trace_test_buffer(&max_tr, &count);
+		ret = trace_test_buffer(&tr->max_buffer, &count);
 	trace->reset(tr);
 	tracing_start();
 
@@ -877,9 +878,9 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
-	ret = trace_test_buffer(tr, NULL);
+	ret = trace_test_buffer(&tr->trace_buffer, NULL);
 	if (!ret)
-		ret = trace_test_buffer(&max_tr, &count);
+		ret = trace_test_buffer(&tr->max_buffer, &count);
 	trace->reset(tr);
 	tracing_start();
 
@@ -943,11 +944,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
-	ret = trace_test_buffer(tr, NULL);
+	ret = trace_test_buffer(&tr->trace_buffer, NULL);
 	if (ret)
 		goto out;
 
-	ret = trace_test_buffer(&max_tr, &count);
+	ret = trace_test_buffer(&tr->max_buffer, &count);
 	if (ret)
 		goto out;
 
@@ -973,11 +974,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
-	ret = trace_test_buffer(tr, NULL);
+	ret = trace_test_buffer(&tr->trace_buffer, NULL);
 	if (ret)
 		goto out;
 
-	ret = trace_test_buffer(&max_tr, &count);
+	ret = trace_test_buffer(&tr->max_buffer, &count);
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -1084,10 +1085,10 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
-	ret = trace_test_buffer(tr, NULL);
+	ret = trace_test_buffer(&tr->trace_buffer, NULL);
 	printk("ret = %d\n", ret);
 	if (!ret)
-		ret = trace_test_buffer(&max_tr, &count);
+		ret = trace_test_buffer(&tr->max_buffer, &count);
 
 
 	trace->reset(tr);
@@ -1126,7 +1127,7 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
 	/* stop the tracing. */
 	tracing_stop();
 	/* check the trace buffer */
-	ret = trace_test_buffer(tr, &count);
+	ret = trace_test_buffer(&tr->trace_buffer, &count);
 	trace->reset(tr);
 	tracing_start();
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 42ca822fc701..b20428c5efe2 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -20,13 +20,24 @@
 
 #define STACK_TRACE_ENTRIES 500
 
+#ifdef CC_USING_FENTRY
+# define fentry		1
+#else
+# define fentry		0
+#endif
+
 static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
 	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
 static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
 
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
 static struct stack_trace max_stack_trace = {
-	.max_entries		= STACK_TRACE_ENTRIES,
-	.entries		= stack_dump_trace,
+	.max_entries		= STACK_TRACE_ENTRIES - 1,
+	.entries		= &stack_dump_trace[1],
 };
 
 static unsigned long max_stack_size;
@@ -39,25 +50,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
 int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
-static inline void check_stack(void)
+static inline void
+check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags;
 	unsigned long *p, *top, *start;
+	static int tracer_frame;
+	int frame_size = ACCESS_ONCE(tracer_frame);
 	int i;
 
-	this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
 	this_size = THREAD_SIZE - this_size;
+	/* Remove the frame of the tracer */
+	this_size -= frame_size;
 
 	if (this_size <= max_stack_size)
 		return;
 
 	/* we do not handle interrupt stacks yet */
-	if (!object_is_on_stack(&this_size))
+	if (!object_is_on_stack(stack))
 		return;
 
 	local_irq_save(flags);
 	arch_spin_lock(&max_stack_lock);
 
+	/* In case another CPU set the tracer_frame on us */
+	if (unlikely(!frame_size))
+		this_size -= tracer_frame;
+
 	/* a race could have already updated it */
 	if (this_size <= max_stack_size)
 		goto out;
@@ -70,10 +90,18 @@ static inline void check_stack(void)
 	save_stack_trace(&max_stack_trace);
 
 	/*
+	 * Add the passed in ip from the function tracer.
+	 * Searching for this on the stack will skip over
+	 * most of the overhead from the stack tracer itself.
+	 */
+	stack_dump_trace[0] = ip;
+	max_stack_trace.nr_entries++;
+
+	/*
 	 * Now find where in the stack these are.
 	 */
 	i = 0;
-	start = &this_size;
+	start = stack;
 	top = (unsigned long *)
 		(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
 
@@ -97,6 +125,18 @@ static inline void check_stack(void)
 				found = 1;
 				/* Start the search from here */
 				start = p + 1;
+				/*
+				 * We do not want to show the overhead
+				 * of the stack tracer stack in the
+				 * max stack. If we haven't figured
+				 * out what that is, then figure it out
+				 * now.
+				 */
+				if (unlikely(!tracer_frame) && i == 1) {
+					tracer_frame = (p - stack) *
+						sizeof(unsigned long);
+					max_stack_size -= tracer_frame;
+				}
 			}
 		}
 
@@ -113,6 +153,7 @@ static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		 struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
+	unsigned long stack;
 	int cpu;
 
 	preempt_disable_notrace();
@@ -122,7 +163,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (per_cpu(trace_active, cpu)++ != 0)
 		goto out;
 
-	check_stack();
+	/*
+	 * When fentry is used, the traced function does not get
+	 * its stack frame set up, and we lose the parent.
+	 * The ip is pretty useless because the function tracer
+	 * was called before that function set up its stack frame.
+	 * In this case, we use the parent ip.
+	 *
+	 * By adding the return address of either the parent ip
+	 * or the current ip we can disregard most of the stack usage
+	 * caused by the stack tracer itself.
+	 *
+	 * The function tracer always reports the address of where the
+	 * mcount call was, but the stack will hold the return address.
+	 */
+	if (fentry)
+		ip = parent_ip;
+	else
+		ip += MCOUNT_INSN_SIZE;
+
+	check_stack(ip, &stack);
 
  out:
 	per_cpu(trace_active, cpu)--;
@@ -322,7 +382,7 @@ static const struct file_operations stack_trace_filter_fops = {
 	.open = stack_trace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -371,6 +431,8 @@ static __init int stack_trace_init(void)
 	struct dentry *d_tracer;
 
 	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
 
 	trace_create_file("stack_max_size", 0644, d_tracer,
 			&max_stack_size, &stack_max_size_fops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 96cffb269e73..847f88a6194b 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -307,6 +307,8 @@ static int tracing_stat_init(void)
 	struct dentry *d_tracing;
 
 	d_tracing = tracing_init_dentry();
+	if (!d_tracing)
+		return 0;
 
 	stat_dir = debugfs_create_dir("trace_stat", d_tracing);
 	if (!stat_dir)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7a809e321058..8f2ac73c7a5f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -12,10 +12,6 @@
 #include "trace.h"
 
 static DEFINE_MUTEX(syscall_trace_lock);
-static int sys_refcount_enter;
-static int sys_refcount_exit;
-static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
 static int syscall_enter_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data);
@@ -41,7 +37,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 	/*
 	 * Only compare after the "sys" prefix. Archs that use
 	 * syscall wrappers may have syscalls symbols aliases prefixed
-	 * with "SyS" instead of "sys", leading to an unwanted
+	 * with ".SyS" or ".sys" instead of "sys", leading to an unwanted
 	 * mismatch.
 	 */
 	return !strcmp(sym + 3, name + 3);
@@ -265,7 +261,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call)
 		kfree(call->print_fmt);
 }
 
-static int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int __init syscall_enter_define_fields(struct ftrace_event_call *call)
 {
 	struct syscall_trace_enter trace;
 	struct syscall_metadata *meta = call->data;
@@ -288,7 +284,7 @@ static int syscall_enter_define_fields(struct ftrace_event_call *call)
 	return ret;
 }
 
-static int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
 {
 	struct syscall_trace_exit trace;
 	int ret;
@@ -303,8 +299,9 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call)
 	return ret;
 }
 
-static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 {
+	struct trace_array *tr = data;
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
@@ -315,7 +312,7 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
-	if (!test_bit(syscall_nr, enabled_enter_syscalls))
+	if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -324,7 +321,8 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	event = trace_current_buffer_lock_reserve(&buffer,
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer,
 			sys_data->enter_event->event.type, size, 0, 0);
 	if (!event)
 		return;
@@ -338,8 +336,9 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 {
+	struct trace_array *tr = data;
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
@@ -349,14 +348,15 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
-	if (!test_bit(syscall_nr, enabled_exit_syscalls))
+	if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
 		return;
 
-	event = trace_current_buffer_lock_reserve(&buffer,
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer,
 			sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
 	if (!event)
 		return;
@@ -370,8 +370,10 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-static int reg_event_syscall_enter(struct ftrace_event_call *call)
+static int reg_event_syscall_enter(struct ftrace_event_file *file,
+				   struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int ret = 0;
 	int num;
 
@@ -379,33 +381,37 @@ static int reg_event_syscall_enter(struct ftrace_event_call *call)
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_refcount_enter)
-		ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
+	if (!tr->sys_refcount_enter)
+		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
 	if (!ret) {
-		set_bit(num, enabled_enter_syscalls);
-		sys_refcount_enter++;
+		set_bit(num, tr->enabled_enter_syscalls);
+		tr->sys_refcount_enter++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-static void unreg_event_syscall_enter(struct ftrace_event_call *call)
+static void unreg_event_syscall_enter(struct ftrace_event_file *file,
+				      struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
-	sys_refcount_enter--;
-	clear_bit(num, enabled_enter_syscalls);
-	if (!sys_refcount_enter)
-		unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
+	tr->sys_refcount_enter--;
+	clear_bit(num, tr->enabled_enter_syscalls);
+	if (!tr->sys_refcount_enter)
+		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static int reg_event_syscall_exit(struct ftrace_event_call *call)
+static int reg_event_syscall_exit(struct ftrace_event_file *file,
+				  struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int ret = 0;
 	int num;
 
@@ -413,28 +419,30 @@ static int reg_event_syscall_exit(struct ftrace_event_call *call)
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_refcount_exit)
-		ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
+	if (!tr->sys_refcount_exit)
+		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
 	if (!ret) {
-		set_bit(num, enabled_exit_syscalls);
-		sys_refcount_exit++;
+		set_bit(num, tr->enabled_exit_syscalls);
+		tr->sys_refcount_exit++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-static void unreg_event_syscall_exit(struct ftrace_event_call *call)
+static void unreg_event_syscall_exit(struct ftrace_event_file *file,
+				     struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
-	sys_refcount_exit--;
-	clear_bit(num, enabled_exit_syscalls);
-	if (!sys_refcount_exit)
-		unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
+	tr->sys_refcount_exit--;
+	clear_bit(num, tr->enabled_exit_syscalls);
+	if (!tr->sys_refcount_exit)
+		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
 	mutex_unlock(&syscall_trace_lock);
 }
 
@@ -471,7 +479,7 @@ struct trace_event_functions exit_syscall_print_funcs = {
 	.trace		= print_syscall_exit,
 };
 
-struct ftrace_event_class event_class_syscall_enter = {
+struct ftrace_event_class __refdata event_class_syscall_enter = {
 	.system		= "syscalls",
 	.reg		= syscall_enter_register,
 	.define_fields	= syscall_enter_define_fields,
@@ -479,7 +487,7 @@ struct ftrace_event_class event_class_syscall_enter = {
 	.raw_init	= init_syscall_trace,
 };
 
-struct ftrace_event_class event_class_syscall_exit = {
+struct ftrace_event_class __refdata event_class_syscall_exit = {
 	.system		= "syscalls",
 	.reg		= syscall_exit_register,
 	.define_fields	= syscall_exit_define_fields,
@@ -685,11 +693,13 @@ static void perf_sysexit_disable(struct ftrace_event_call *call)
 static int syscall_enter_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data)
 {
+	struct ftrace_event_file *file = data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return reg_event_syscall_enter(event);
+		return reg_event_syscall_enter(file, event);
 	case TRACE_REG_UNREGISTER:
-		unreg_event_syscall_enter(event);
+		unreg_event_syscall_enter(file, event);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
@@ -711,11 +721,13 @@ static int syscall_enter_register(struct ftrace_event_call *event,
 static int syscall_exit_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data)
 {
+	struct ftrace_event_file *file = data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return reg_event_syscall_exit(event);
+		return reg_event_syscall_exit(file, event);
 	case TRACE_REG_UNREGISTER:
-		unreg_event_syscall_exit(event);
+		unreg_event_syscall_exit(file, event);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8dad2a92dee9..32494fb0ee64 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -28,6 +28,18 @@
 
 #define UPROBE_EVENT_SYSTEM	"uprobes"
 
+struct uprobe_trace_entry_head {
+	struct trace_entry	ent;
+	unsigned long		vaddr[];
+};
+
+#define SIZEOF_TRACE_ENTRY(is_return)			\
+	(sizeof(struct uprobe_trace_entry_head) +	\
+	 sizeof(unsigned long) * (is_return ? 2 : 1))
+
+#define DATAOF_TRACE_ENTRY(entry, is_return)		\
+	((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return))
+
 struct trace_uprobe_filter {
 	rwlock_t		rwlock;
 	int			nr_systemwide;
@@ -64,6 +76,8 @@ static DEFINE_MUTEX(uprobe_lock);
 static LIST_HEAD(uprobe_list);
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
+static int uretprobe_dispatcher(struct uprobe_consumer *con,
+				unsigned long func, struct pt_regs *regs);
 
 static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
 {
@@ -77,11 +91,16 @@ static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter)
 	return !filter->nr_systemwide && list_empty(&filter->perf_events);
 }
 
+static inline bool is_ret_probe(struct trace_uprobe *tu)
+{
+	return tu->consumer.ret_handler != NULL;
+}
+
 /*
  * Allocate new trace_uprobe and initialize it (including uprobes).
  */
 static struct trace_uprobe *
-alloc_trace_uprobe(const char *group, const char *event, int nargs)
+alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 {
 	struct trace_uprobe *tu;
 
@@ -106,6 +125,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs)
 
 	INIT_LIST_HEAD(&tu->list);
 	tu->consumer.handler = uprobe_dispatcher;
+	if (is_ret)
+		tu->consumer.ret_handler = uretprobe_dispatcher;
 	init_trace_uprobe_filter(&tu->filter);
 	return tu;
 
@@ -180,7 +201,7 @@ end:
 
 /*
  * Argument syntax:
- *  - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS]
+ *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS]
  *
  *  - Remove uprobe: -:[GRP/]EVENT
  */
@@ -192,20 +213,23 @@ static int create_trace_uprobe(int argc, char **argv)
 	char buf[MAX_EVENT_NAME_LEN];
 	struct path path;
 	unsigned long offset;
-	bool is_delete;
+	bool is_delete, is_return;
 	int i, ret;
 
 	inode = NULL;
 	ret = 0;
 	is_delete = false;
+	is_return = false;
 	event = NULL;
 	group = NULL;
 
 	/* argc must be >= 1 */
 	if (argv[0][0] == '-')
 		is_delete = true;
+	else if (argv[0][0] == 'r')
+		is_return = true;
 	else if (argv[0][0] != 'p') {
-		pr_info("Probe definition must be started with 'p' or '-'.\n");
+		pr_info("Probe definition must be started with 'p', 'r' or '-'.\n");
 		return -EINVAL;
 	}
 
@@ -303,7 +327,7 @@ static int create_trace_uprobe(int argc, char **argv)
 		kfree(tail);
 	}
 
-	tu = alloc_trace_uprobe(group, event, argc);
+	tu = alloc_trace_uprobe(group, event, argc, is_return);
 	if (IS_ERR(tu)) {
 		pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu));
 		ret = PTR_ERR(tu);
@@ -414,9 +438,10 @@ static void probes_seq_stop(struct seq_file *m, void *v)
 static int probes_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_uprobe *tu = v;
+	char c = is_ret_probe(tu) ? 'r' : 'p';
 	int i;
 
-	seq_printf(m, "p:%s/%s", tu->call.class->system, tu->call.name);
+	seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name);
 	seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
 
 	for (i = 0; i < tu->nr_args; i++)
@@ -485,65 +510,81 @@ static const struct file_operations uprobe_profile_ops = {
 	.release	= seq_release,
 };
 
-/* uprobe handler */
-static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static void uprobe_trace_print(struct trace_uprobe *tu,
+				unsigned long func, struct pt_regs *regs)
 {
 	struct uprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	u8 *data;
-	int size, i, pc;
-	unsigned long irq_flags;
+	void *data;
+	int size, i;
 	struct ftrace_event_call *call = &tu->call;
 
-	local_save_flags(irq_flags);
-	pc = preempt_count();
-
-	size = sizeof(*entry) + tu->size;
-
+	size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
-						  size, irq_flags, pc);
+						  size + tu->size, 0, 0);
 	if (!event)
-		return 0;
+		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->ip = instruction_pointer(task_pt_regs(current));
-	data = (u8 *)&entry[1];
+	if (is_ret_probe(tu)) {
+		entry->vaddr[0] = func;
+		entry->vaddr[1] = instruction_pointer(regs);
+		data = DATAOF_TRACE_ENTRY(entry, true);
+	} else {
+		entry->vaddr[0] = instruction_pointer(regs);
+		data = DATAOF_TRACE_ENTRY(entry, false);
+	}
+
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
-		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
+}
 
+/* uprobe handler */
+static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+{
+	if (!is_ret_probe(tu))
+		uprobe_trace_print(tu, 0, regs);
 	return 0;
 }
 
+static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
+				struct pt_regs *regs)
+{
+	uprobe_trace_print(tu, func, regs);
+}
+
 /* Event entry printers */
 static enum print_line_t
 print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event)
 {
-	struct uprobe_trace_entry_head *field;
+	struct uprobe_trace_entry_head *entry;
 	struct trace_seq *s = &iter->seq;
 	struct trace_uprobe *tu;
 	u8 *data;
 	int i;
 
-	field = (struct uprobe_trace_entry_head *)iter->ent;
+	entry = (struct uprobe_trace_entry_head *)iter->ent;
 	tu = container_of(event, struct trace_uprobe, call.event);
 
-	if (!trace_seq_printf(s, "%s: (", tu->call.name))
-		goto partial;
-
-	if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
-		goto partial;
-
-	if (!trace_seq_puts(s, ")"))
-		goto partial;
+	if (is_ret_probe(tu)) {
+		if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name,
+					entry->vaddr[1], entry->vaddr[0]))
+			goto partial;
+		data = DATAOF_TRACE_ENTRY(entry, true);
+	} else {
+		if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name,
+					entry->vaddr[0]))
+			goto partial;
+		data = DATAOF_TRACE_ENTRY(entry, false);
+	}
 
-	data = (u8 *)&field[1];
 	for (i = 0; i < tu->nr_args; i++) {
 		if (!tu->args[i].type->print(s, tu->args[i].name,
-					     data + tu->args[i].offset, field))
+					     data + tu->args[i].offset, entry))
 			goto partial;
 	}
 
@@ -595,16 +636,23 @@ static void probe_event_disable(struct trace_uprobe *tu, int flag)
 
 static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
-	int ret, i;
+	int ret, i, size;
 	struct uprobe_trace_entry_head field;
-	struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data;
+	struct trace_uprobe *tu = event_call->data;
 
-	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+	if (is_ret_probe(tu)) {
+		DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0);
+		DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0);
+		size = SIZEOF_TRACE_ENTRY(true);
+	} else {
+		DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0);
+		size = SIZEOF_TRACE_ENTRY(false);
+	}
 	/* Set argument names as fields */
 	for (i = 0; i < tu->nr_args; i++) {
 		ret = trace_define_field(event_call, tu->args[i].type->fmttype,
 					 tu->args[i].name,
-					 sizeof(field) + tu->args[i].offset,
+					 size + tu->args[i].offset,
 					 tu->args[i].type->size,
 					 tu->args[i].type->is_signed,
 					 FILTER_OTHER);
@@ -622,8 +670,13 @@ static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len)
 	int i;
 	int pos = 0;
 
-	fmt = "(%lx)";
-	arg = "REC->" FIELD_STRING_IP;
+	if (is_ret_probe(tu)) {
+		fmt = "(%lx <- %lx)";
+		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+	} else {
+		fmt = "(%lx)";
+		arg = "REC->" FIELD_STRING_IP;
+	}
 
 	/* When len=0, we just calculate the needed length */
 
@@ -752,49 +805,68 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
 	return ret;
 }
 
-/* uprobe profile handler */
-static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static void uprobe_perf_print(struct trace_uprobe *tu,
+				unsigned long func, struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &tu->call;
 	struct uprobe_trace_entry_head *entry;
 	struct hlist_head *head;
-	u8 *data;
-	int size, __size, i;
-	int rctx;
+	void *data;
+	int size, rctx, i;
 
-	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
-		return UPROBE_HANDLER_REMOVE;
-
-	__size = sizeof(*entry) + tu->size;
-	size = ALIGN(__size + sizeof(u32), sizeof(u64));
-	size -= sizeof(u32);
+	size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+	size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
-		return 0;
+		return;
 
 	preempt_disable();
+	head = this_cpu_ptr(call->perf_events);
+	if (hlist_empty(head))
+		goto out;
 
 	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
 	if (!entry)
 		goto out;
 
-	entry->ip = instruction_pointer(task_pt_regs(current));
-	data = (u8 *)&entry[1];
+	if (is_ret_probe(tu)) {
+		entry->vaddr[0] = func;
+		entry->vaddr[1] = instruction_pointer(regs);
+		data = DATAOF_TRACE_ENTRY(entry, true);
+	} else {
+		entry->vaddr[0] = instruction_pointer(regs);
+		data = DATAOF_TRACE_ENTRY(entry, false);
+	}
+
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
 
-	head = this_cpu_ptr(call->perf_events);
-	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL);
-
+	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
  out:
 	preempt_enable();
+}
+
+/* uprobe profile handler */
+static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+{
+	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
+		return UPROBE_HANDLER_REMOVE;
+
+	if (!is_ret_probe(tu))
+		uprobe_perf_print(tu, 0, regs);
 	return 0;
 }
+
+static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
+				struct pt_regs *regs)
+{
+	uprobe_perf_print(tu, func, regs);
+}
 #endif	/* CONFIG_PERF_EVENTS */
 
 static
 int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data)
 {
-	struct trace_uprobe *tu = (struct trace_uprobe *)event->data;
+	struct trace_uprobe *tu = event->data;
 
 	switch (type) {
 	case TRACE_REG_REGISTER:
@@ -843,6 +915,23 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 	return ret;
 }
 
+static int uretprobe_dispatcher(struct uprobe_consumer *con,
+				unsigned long func, struct pt_regs *regs)
+{
+	struct trace_uprobe *tu;
+
+	tu = container_of(con, struct trace_uprobe, consumer);
+
+	if (tu->flags & TP_FLAG_TRACE)
+		uretprobe_trace_func(tu, func, regs);
+
+#ifdef CONFIG_PERF_EVENTS
+	if (tu->flags & TP_FLAG_PROFILE)
+		uretprobe_perf_func(tu, func, regs);
+#endif
+	return 0;
+}
+
 static struct trace_event_functions uprobe_funcs = {
 	.trace		= print_uprobe_event
 };
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 0c05a4592047..29f26540e9c9 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -112,7 +112,8 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry,
 	int nr_probes = 0;
 	struct tracepoint_func *old, *new;
 
-	WARN_ON(!probe);
+	if (WARN_ON(!probe))
+		return ERR_PTR(-EINVAL);
 
 	debug_print_probes(entry);
 	old = entry->funcs;
@@ -152,13 +153,18 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
 
 	debug_print_probes(entry);
 	/* (N -> M), (N > 1, M >= 0) probes */
-	for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
-		if (!probe ||
-		    (old[nr_probes].func == probe &&
-		     old[nr_probes].data == data))
-			nr_del++;
+	if (probe) {
+		for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
+			if (old[nr_probes].func == probe &&
+			     old[nr_probes].data == data)
+				nr_del++;
+		}
 	}
 
+	/*
+	 * If probe is NULL, then nr_probes = nr_del = 0, and then the
+	 * entire entry will be removed.
+	 */
 	if (nr_probes - nr_del == 0) {
 		/* N -> 0, (N > 1) */
 		entry->funcs = NULL;
@@ -173,8 +179,7 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
 		if (new == NULL)
 			return ERR_PTR(-ENOMEM);
 		for (i = 0; old[i].func; i++)
-			if (probe &&
-			    (old[i].func != probe || old[i].data != data))
+			if (old[i].func != probe || old[i].data != data)
 				new[j++] = old[i];
 		new[nr_probes - nr_del].func = NULL;
 		entry->refcount = nr_probes - nr_del;
diff --git a/kernel/user.c b/kernel/user.c
index e81978e8c03b..8e635a18ab52 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,8 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.may_mount_sysfs = true,
+	.may_mount_proc = true,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 8b650837083e..e134d8f365dd 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,10 +21,12 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/projid.h>
+#include <linux/fs_struct.h>
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
 
-static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+static bool new_idmap_permitted(const struct file *file,
+				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *map);
 
 static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
@@ -60,6 +62,15 @@ int create_user_ns(struct cred *new)
 	kgid_t group = new->egid;
 	int ret;
 
+	/*
+	 * Verify that we can not violate the policy of which files
+	 * may be accessed that is specified by the root directory,
+	 * by verifing that the root directory is at the root of the
+	 * mount namespace which allows all files to be accessed.
+	 */
+	if (current_chrooted())
+		return -EPERM;
+
 	/* The creator needs a mapping in the parent user namespace
 	 * or else we won't be able to reasonably tell userspace who
 	 * created a user_namespace.
@@ -86,6 +97,8 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+	update_mnt_policy(ns);
+
 	return 0;
 }
 
@@ -600,10 +613,10 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	if (map->nr_extents != 0)
 		goto out;
 
-	/* Require the appropriate privilege CAP_SETUID or CAP_SETGID
-	 * over the user namespace in order to set the id mapping.
+	/*
+	 * Adjusting namespace settings requires capabilities on the target.
 	 */
-	if (cap_valid(cap_setid) && !ns_capable(ns, cap_setid))
+	if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
 		goto out;
 
 	/* Get a buffer */
@@ -688,7 +701,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 
 	ret = -EPERM;
 	/* Validate the user is allowed to use user id's mapped to. */
-	if (!new_idmap_permitted(ns, cap_setid, &new_map))
+	if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
 		goto out;
 
 	/* Map the lower ids from the parent user namespace to the
@@ -775,7 +788,8 @@ ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t
 			 &ns->projid_map, &ns->parent->projid_map);
 }
 
-static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+static bool new_idmap_permitted(const struct file *file, 
+				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *new_map)
 {
 	/* Allow mapping to your own filesystem ids */
@@ -783,12 +797,12 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 		u32 id = new_map->extent[0].lower_first;
 		if (cap_setid == CAP_SETUID) {
 			kuid_t uid = make_kuid(ns->parent, id);
-			if (uid_eq(uid, current_fsuid()))
+			if (uid_eq(uid, file->f_cred->fsuid))
 				return true;
 		}
 		else if (cap_setid == CAP_SETGID) {
 			kgid_t gid = make_kgid(ns->parent, id);
-			if (gid_eq(gid, current_fsgid()))
+			if (gid_eq(gid, file->f_cred->fsgid))
 				return true;
 		}
 	}
@@ -799,8 +813,10 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 
 	/* Allow the specified ids if we have the appropriate capability
 	 * (CAP_SETUID or CAP_SETGID) over the parent user namespace.
+	 * And the opener of the id file also had the approprpiate capability.
 	 */
-	if (ns_capable(ns->parent, cap_setid))
+	if (ns_capable(ns->parent, cap_setid) &&
+	    file_ns_capable(file, ns->parent, cap_setid))
 		return true;
 
 	return false;
@@ -837,6 +853,9 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
 	if (atomic_read(&current->mm->mm_users) > 1)
 		return -EINVAL;
 
+	if (current->fs->users != 1)
+		return -EINVAL;
+
 	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4a944676358e..05039e348f07 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -517,6 +517,11 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		return ret;
 
 	set_sample_period();
+	/*
+	 * Watchdog threads shouldn't be enabled if they are
+	 * disabled. The 'watchdog_disabled' variable check in
+	 * watchdog_*_all_cpus() function takes care of this.
+	 */
 	if (watchdog_enabled && watchdog_thresh)
 		watchdog_enable_all_cpus();
 	else
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 81f2457811eb..154aa12af48e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -41,7 +41,11 @@
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
 #include <linux/idr.h>
+#include <linux/jhash.h>
 #include <linux/hashtable.h>
+#include <linux/rculist.h>
+#include <linux/nodemask.h>
+#include <linux/moduleparam.h>
 
 #include "workqueue_internal.h"
 
@@ -58,12 +62,11 @@ enum {
 	 * %WORKER_UNBOUND set and concurrency management disabled, and may
 	 * be executing on any CPU.  The pool behaves as an unbound one.
 	 *
-	 * Note that DISASSOCIATED can be flipped only while holding
-	 * assoc_mutex to avoid changing binding state while
+	 * Note that DISASSOCIATED should be flipped only while holding
+	 * manager_mutex to avoid changing binding state while
 	 * create_worker() is in progress.
 	 */
 	POOL_MANAGE_WORKERS	= 1 << 0,	/* need to manage workers */
-	POOL_MANAGING_WORKERS   = 1 << 1,       /* managing workers */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
 	POOL_FREEZING		= 1 << 3,	/* freeze in progress */
 
@@ -74,12 +77,14 @@ enum {
 	WORKER_PREP		= 1 << 3,	/* preparing to run works */
 	WORKER_CPU_INTENSIVE	= 1 << 6,	/* cpu intensive */
 	WORKER_UNBOUND		= 1 << 7,	/* worker is unbound */
+	WORKER_REBOUND		= 1 << 8,	/* worker was rebound */
 
-	WORKER_NOT_RUNNING	= WORKER_PREP | WORKER_UNBOUND |
-				  WORKER_CPU_INTENSIVE,
+	WORKER_NOT_RUNNING	= WORKER_PREP | WORKER_CPU_INTENSIVE |
+				  WORKER_UNBOUND | WORKER_REBOUND,
 
 	NR_STD_WORKER_POOLS	= 2,		/* # standard pools per cpu */
 
+	UNBOUND_POOL_HASH_ORDER	= 6,		/* hashed by pool->attrs */
 	BUSY_WORKER_HASH_ORDER	= 6,		/* 64 pointers */
 
 	MAX_IDLE_WORKERS_RATIO	= 4,		/* 1/4 of busy can be idle */
@@ -97,6 +102,8 @@ enum {
 	 */
 	RESCUER_NICE_LEVEL	= -20,
 	HIGHPRI_NICE_LEVEL	= -20,
+
+	WQ_NAME_LEN		= 24,
 };
 
 /*
@@ -115,16 +122,26 @@ enum {
  *    cpu or grabbing pool->lock is enough for read access.  If
  *    POOL_DISASSOCIATED is set, it's identical to L.
  *
- * F: wq->flush_mutex protected.
+ * MG: pool->manager_mutex and pool->lock protected.  Writes require both
+ *     locks.  Reads can happen under either lock.
+ *
+ * PL: wq_pool_mutex protected.
+ *
+ * PR: wq_pool_mutex protected for writes.  Sched-RCU protected for reads.
+ *
+ * WQ: wq->mutex protected.
  *
- * W: workqueue_lock protected.
+ * WR: wq->mutex protected for writes.  Sched-RCU protected for reads.
+ *
+ * MD: wq_mayday_lock protected.
  */
 
 /* struct worker is defined in workqueue_internal.h */
 
 struct worker_pool {
 	spinlock_t		lock;		/* the pool lock */
-	unsigned int		cpu;		/* I: the associated cpu */
+	int			cpu;		/* I: the associated cpu */
+	int			node;		/* I: the associated node ID */
 	int			id;		/* I: pool ID */
 	unsigned int		flags;		/* X: flags */
 
@@ -138,12 +155,18 @@ struct worker_pool {
 	struct timer_list	idle_timer;	/* L: worker idle timeout */
 	struct timer_list	mayday_timer;	/* L: SOS timer for workers */
 
-	/* workers are chained either in busy_hash or idle_list */
+	/* a workers is either on busy_hash or idle_list, or the manager */
 	DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
 						/* L: hash of busy workers */
 
-	struct mutex		assoc_mutex;	/* protect POOL_DISASSOCIATED */
-	struct ida		worker_ida;	/* L: for worker IDs */
+	/* see manage_workers() for details on the two manager mutexes */
+	struct mutex		manager_arb;	/* manager arbitration */
+	struct mutex		manager_mutex;	/* manager exclusion */
+	struct idr		worker_idr;	/* MG: worker IDs and iteration */
+
+	struct workqueue_attrs	*attrs;		/* I: worker attributes */
+	struct hlist_node	hash_node;	/* PL: unbound_pool_hash node */
+	int			refcnt;		/* PL: refcnt for unbound pools */
 
 	/*
 	 * The current concurrency level.  As it's likely to be accessed
@@ -151,6 +174,12 @@ struct worker_pool {
 	 * cacheline.
 	 */
 	atomic_t		nr_running ____cacheline_aligned_in_smp;
+
+	/*
+	 * Destruction of pool is sched-RCU protected to allow dereferences
+	 * from get_work_pool().
+	 */
+	struct rcu_head		rcu;
 } ____cacheline_aligned_in_smp;
 
 /*
@@ -164,75 +193,107 @@ struct pool_workqueue {
 	struct workqueue_struct *wq;		/* I: the owning workqueue */
 	int			work_color;	/* L: current color */
 	int			flush_color;	/* L: flushing color */
+	int			refcnt;		/* L: reference count */
 	int			nr_in_flight[WORK_NR_COLORS];
 						/* L: nr of in_flight works */
 	int			nr_active;	/* L: nr of active works */
 	int			max_active;	/* L: max active works */
 	struct list_head	delayed_works;	/* L: delayed works */
-};
+	struct list_head	pwqs_node;	/* WR: node on wq->pwqs */
+	struct list_head	mayday_node;	/* MD: node on wq->maydays */
+
+	/*
+	 * Release of unbound pwq is punted to system_wq.  See put_pwq()
+	 * and pwq_unbound_release_workfn() for details.  pool_workqueue
+	 * itself is also sched-RCU protected so that the first pwq can be
+	 * determined without grabbing wq->mutex.
+	 */
+	struct work_struct	unbound_release_work;
+	struct rcu_head		rcu;
+} __aligned(1 << WORK_STRUCT_FLAG_BITS);
 
 /*
  * Structure used to wait for workqueue flush.
  */
 struct wq_flusher {
-	struct list_head	list;		/* F: list of flushers */
-	int			flush_color;	/* F: flush color waiting for */
+	struct list_head	list;		/* WQ: list of flushers */
+	int			flush_color;	/* WQ: flush color waiting for */
 	struct completion	done;		/* flush completion */
 };
 
-/*
- * All cpumasks are assumed to be always set on UP and thus can't be
- * used to determine whether there's something to be done.
- */
-#ifdef CONFIG_SMP
-typedef cpumask_var_t mayday_mask_t;
-#define mayday_test_and_set_cpu(cpu, mask)	\
-	cpumask_test_and_set_cpu((cpu), (mask))
-#define mayday_clear_cpu(cpu, mask)		cpumask_clear_cpu((cpu), (mask))
-#define for_each_mayday_cpu(cpu, mask)		for_each_cpu((cpu), (mask))
-#define alloc_mayday_mask(maskp, gfp)		zalloc_cpumask_var((maskp), (gfp))
-#define free_mayday_mask(mask)			free_cpumask_var((mask))
-#else
-typedef unsigned long mayday_mask_t;
-#define mayday_test_and_set_cpu(cpu, mask)	test_and_set_bit(0, &(mask))
-#define mayday_clear_cpu(cpu, mask)		clear_bit(0, &(mask))
-#define for_each_mayday_cpu(cpu, mask)		if ((cpu) = 0, (mask))
-#define alloc_mayday_mask(maskp, gfp)		true
-#define free_mayday_mask(mask)			do { } while (0)
-#endif
+struct wq_device;
 
 /*
- * The externally visible workqueue abstraction is an array of
- * per-CPU workqueues:
+ * The externally visible workqueue.  It relays the issued work items to
+ * the appropriate worker_pool through its pool_workqueues.
  */
 struct workqueue_struct {
-	unsigned int		flags;		/* W: WQ_* flags */
-	union {
-		struct pool_workqueue __percpu		*pcpu;
-		struct pool_workqueue			*single;
-		unsigned long				v;
-	} pool_wq;				/* I: pwq's */
-	struct list_head	list;		/* W: list of all workqueues */
-
-	struct mutex		flush_mutex;	/* protects wq flushing */
-	int			work_color;	/* F: current work color */
-	int			flush_color;	/* F: current flush color */
+	struct list_head	pwqs;		/* WR: all pwqs of this wq */
+	struct list_head	list;		/* PL: list of all workqueues */
+
+	struct mutex		mutex;		/* protects this wq */
+	int			work_color;	/* WQ: current work color */
+	int			flush_color;	/* WQ: current flush color */
 	atomic_t		nr_pwqs_to_flush; /* flush in progress */
-	struct wq_flusher	*first_flusher;	/* F: first flusher */
-	struct list_head	flusher_queue;	/* F: flush waiters */
-	struct list_head	flusher_overflow; /* F: flush overflow list */
+	struct wq_flusher	*first_flusher;	/* WQ: first flusher */
+	struct list_head	flusher_queue;	/* WQ: flush waiters */
+	struct list_head	flusher_overflow; /* WQ: flush overflow list */
 
-	mayday_mask_t		mayday_mask;	/* cpus requesting rescue */
+	struct list_head	maydays;	/* MD: pwqs requesting rescue */
 	struct worker		*rescuer;	/* I: rescue worker */
 
-	int			nr_drainers;	/* W: drain in progress */
-	int			saved_max_active; /* W: saved pwq max_active */
+	int			nr_drainers;	/* WQ: drain in progress */
+	int			saved_max_active; /* WQ: saved pwq max_active */
+
+	struct workqueue_attrs	*unbound_attrs;	/* WQ: only for unbound wqs */
+	struct pool_workqueue	*dfl_pwq;	/* WQ: only for unbound wqs */
+
+#ifdef CONFIG_SYSFS
+	struct wq_device	*wq_dev;	/* I: for sysfs interface */
+#endif
 #ifdef CONFIG_LOCKDEP
 	struct lockdep_map	lockdep_map;
 #endif
-	char			name[];		/* I: workqueue name */
+	char			name[WQ_NAME_LEN]; /* I: workqueue name */
+
+	/* hot fields used during command issue, aligned to cacheline */
+	unsigned int		flags ____cacheline_aligned; /* WQ: WQ_* flags */
+	struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */
+	struct pool_workqueue __rcu *numa_pwq_tbl[]; /* FR: unbound pwqs indexed by node */
 };
 
+static struct kmem_cache *pwq_cache;
+
+static int wq_numa_tbl_len;		/* highest possible NUMA node id + 1 */
+static cpumask_var_t *wq_numa_possible_cpumask;
+					/* possible CPUs of each node */
+
+static bool wq_disable_numa;
+module_param_named(disable_numa, wq_disable_numa, bool, 0444);
+
+static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
+
+/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
+static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
+
+static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
+static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
+
+static LIST_HEAD(workqueues);		/* PL: list of all workqueues */
+static bool workqueue_freezing;		/* PL: have wqs started freezing? */
+
+/* the per-cpu worker pools */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
+				     cpu_worker_pools);
+
+static DEFINE_IDR(worker_pool_idr);	/* PR: idr of all pools */
+
+/* PL: hash of all unbound pools keyed by pool->attrs */
+static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
+
+/* I: attributes used when instantiating standard unbound pools on demand */
+static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
+
 struct workqueue_struct *system_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_wq);
 struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -244,64 +305,87 @@ EXPORT_SYMBOL_GPL(system_unbound_wq);
 struct workqueue_struct *system_freezable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_freezable_wq);
 
+static int worker_thread(void *__worker);
+static void copy_workqueue_attrs(struct workqueue_attrs *to,
+				 const struct workqueue_attrs *from);
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
 
-#define for_each_std_worker_pool(pool, cpu)				\
-	for ((pool) = &std_worker_pools(cpu)[0];			\
-	     (pool) < &std_worker_pools(cpu)[NR_STD_WORKER_POOLS]; (pool)++)
+#define assert_rcu_or_pool_mutex()					\
+	rcu_lockdep_assert(rcu_read_lock_sched_held() ||		\
+			   lockdep_is_held(&wq_pool_mutex),		\
+			   "sched RCU or wq_pool_mutex should be held")
 
-#define for_each_busy_worker(worker, i, pool)				\
-	hash_for_each(pool->busy_hash, i, worker, hentry)
+#define assert_rcu_or_wq_mutex(wq)					\
+	rcu_lockdep_assert(rcu_read_lock_sched_held() ||		\
+			   lockdep_is_held(&wq->mutex),			\
+			   "sched RCU or wq->mutex should be held")
 
-static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
-				unsigned int sw)
-{
-	if (cpu < nr_cpu_ids) {
-		if (sw & 1) {
-			cpu = cpumask_next(cpu, mask);
-			if (cpu < nr_cpu_ids)
-				return cpu;
-		}
-		if (sw & 2)
-			return WORK_CPU_UNBOUND;
-	}
-	return WORK_CPU_END;
-}
+#ifdef CONFIG_LOCKDEP
+#define assert_manager_or_pool_lock(pool)				\
+	WARN_ONCE(debug_locks &&					\
+		  !lockdep_is_held(&(pool)->manager_mutex) &&		\
+		  !lockdep_is_held(&(pool)->lock),			\
+		  "pool->manager_mutex or ->lock should be held")
+#else
+#define assert_manager_or_pool_lock(pool)	do { } while (0)
+#endif
 
-static inline int __next_pwq_cpu(int cpu, const struct cpumask *mask,
-				 struct workqueue_struct *wq)
-{
-	return __next_wq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2);
-}
+#define for_each_cpu_worker_pool(pool, cpu)				\
+	for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];		\
+	     (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \
+	     (pool)++)
 
-/*
- * CPU iterators
+/**
+ * for_each_pool - iterate through all worker_pools in the system
+ * @pool: iteration cursor
+ * @pi: integer used for iteration
  *
- * An extra cpu number is defined using an invalid cpu number
- * (WORK_CPU_UNBOUND) to host workqueues which are not bound to any
- * specific CPU.  The following iterators are similar to for_each_*_cpu()
- * iterators but also considers the unbound CPU.
+ * This must be called either with wq_pool_mutex held or sched RCU read
+ * locked.  If the pool needs to be used beyond the locking in effect, the
+ * caller is responsible for guaranteeing that the pool stays online.
  *
- * for_each_wq_cpu()		: possible CPUs + WORK_CPU_UNBOUND
- * for_each_online_wq_cpu()	: online CPUs + WORK_CPU_UNBOUND
- * for_each_pwq_cpu()		: possible CPUs for bound workqueues,
- *				  WORK_CPU_UNBOUND for unbound workqueues
+ * The if/else clause exists only for the lockdep assertion and can be
+ * ignored.
  */
-#define for_each_wq_cpu(cpu)						\
-	for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, 3);		\
-	     (cpu) < WORK_CPU_END;					\
-	     (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, 3))
+#define for_each_pool(pool, pi)						\
+	idr_for_each_entry(&worker_pool_idr, pool, pi)			\
+		if (({ assert_rcu_or_pool_mutex(); false; })) { }	\
+		else
 
-#define for_each_online_wq_cpu(cpu)					\
-	for ((cpu) = __next_wq_cpu(-1, cpu_online_mask, 3);		\
-	     (cpu) < WORK_CPU_END;					\
-	     (cpu) = __next_wq_cpu((cpu), cpu_online_mask, 3))
+/**
+ * for_each_pool_worker - iterate through all workers of a worker_pool
+ * @worker: iteration cursor
+ * @wi: integer used for iteration
+ * @pool: worker_pool to iterate workers of
+ *
+ * This must be called with either @pool->manager_mutex or ->lock held.
+ *
+ * The if/else clause exists only for the lockdep assertion and can be
+ * ignored.
+ */
+#define for_each_pool_worker(worker, wi, pool)				\
+	idr_for_each_entry(&(pool)->worker_idr, (worker), (wi))		\
+		if (({ assert_manager_or_pool_lock((pool)); false; })) { } \
+		else
 
-#define for_each_pwq_cpu(cpu, wq)					\
-	for ((cpu) = __next_pwq_cpu(-1, cpu_possible_mask, (wq));	\
-	     (cpu) < WORK_CPU_END;					\
-	     (cpu) = __next_pwq_cpu((cpu), cpu_possible_mask, (wq)))
+/**
+ * for_each_pwq - iterate through all pool_workqueues of the specified workqueue
+ * @pwq: iteration cursor
+ * @wq: the target workqueue
+ *
+ * This must be called either with wq->mutex held or sched RCU read locked.
+ * If the pwq needs to be used beyond the locking in effect, the caller is
+ * responsible for guaranteeing that the pwq stays online.
+ *
+ * The if/else clause exists only for the lockdep assertion and can be
+ * ignored.
+ */
+#define for_each_pwq(pwq, wq)						\
+	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node)		\
+		if (({ assert_rcu_or_wq_mutex(wq); false; })) { }	\
+		else
 
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 
@@ -419,76 +503,35 @@ static inline void debug_work_activate(struct work_struct *work) { }
 static inline void debug_work_deactivate(struct work_struct *work) { }
 #endif
 
-/* Serializes the accesses to the list of workqueues. */
-static DEFINE_SPINLOCK(workqueue_lock);
-static LIST_HEAD(workqueues);
-static bool workqueue_freezing;		/* W: have wqs started freezing? */
-
-/*
- * The CPU and unbound standard worker pools.  The unbound ones have
- * POOL_DISASSOCIATED set, and their workers have WORKER_UNBOUND set.
- */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
-				     cpu_std_worker_pools);
-static struct worker_pool unbound_std_worker_pools[NR_STD_WORKER_POOLS];
-
-/* idr of all pools */
-static DEFINE_MUTEX(worker_pool_idr_mutex);
-static DEFINE_IDR(worker_pool_idr);
-
-static int worker_thread(void *__worker);
-
-static struct worker_pool *std_worker_pools(int cpu)
-{
-	if (cpu != WORK_CPU_UNBOUND)
-		return per_cpu(cpu_std_worker_pools, cpu);
-	else
-		return unbound_std_worker_pools;
-}
-
-static int std_worker_pool_pri(struct worker_pool *pool)
-{
-	return pool - std_worker_pools(pool->cpu);
-}
-
 /* allocate ID and assign it to @pool */
 static int worker_pool_assign_id(struct worker_pool *pool)
 {
 	int ret;
 
-	mutex_lock(&worker_pool_idr_mutex);
-	idr_pre_get(&worker_pool_idr, GFP_KERNEL);
-	ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
-	mutex_unlock(&worker_pool_idr_mutex);
+	lockdep_assert_held(&wq_pool_mutex);
 
+	ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
+	if (ret >= 0) {
+		pool->id = ret;
+		return 0;
+	}
 	return ret;
 }
 
-/*
- * Lookup worker_pool by id.  The idr currently is built during boot and
- * never modified.  Don't worry about locking for now.
+/**
+ * unbound_pwq_by_node - return the unbound pool_workqueue for the given node
+ * @wq: the target workqueue
+ * @node: the node ID
+ *
+ * This must be called either with pwq_lock held or sched RCU read locked.
+ * If the pwq needs to be used beyond the locking in effect, the caller is
+ * responsible for guaranteeing that the pwq stays online.
  */
-static struct worker_pool *worker_pool_by_id(int pool_id)
-{
-	return idr_find(&worker_pool_idr, pool_id);
-}
-
-static struct worker_pool *get_std_worker_pool(int cpu, bool highpri)
+static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
+						  int node)
 {
-	struct worker_pool *pools = std_worker_pools(cpu);
-
-	return &pools[highpri];
-}
-
-static struct pool_workqueue *get_pwq(unsigned int cpu,
-				      struct workqueue_struct *wq)
-{
-	if (!(wq->flags & WQ_UNBOUND)) {
-		if (likely(cpu < nr_cpu_ids))
-			return per_cpu_ptr(wq->pool_wq.pcpu, cpu);
-	} else if (likely(cpu == WORK_CPU_UNBOUND))
-		return wq->pool_wq.single;
-	return NULL;
+	assert_rcu_or_wq_mutex(wq);
+	return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
 static unsigned int work_color_to_flags(int color)
@@ -530,7 +573,7 @@ static int work_next_color(int color)
 static inline void set_work_data(struct work_struct *work, unsigned long data,
 				 unsigned long flags)
 {
-	BUG_ON(!work_pending(work));
+	WARN_ON_ONCE(!work_pending(work));
 	atomic_long_set(&work->data, data | flags | work_static(work));
 }
 
@@ -582,13 +625,23 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work)
  * @work: the work item of interest
  *
  * Return the worker_pool @work was last associated with.  %NULL if none.
+ *
+ * Pools are created and destroyed under wq_pool_mutex, and allows read
+ * access under sched-RCU read lock.  As such, this function should be
+ * called under wq_pool_mutex or with preemption disabled.
+ *
+ * All fields of the returned pool are accessible as long as the above
+ * mentioned locking is in effect.  If the returned pool needs to be used
+ * beyond the critical section, the caller is responsible for ensuring the
+ * returned pool is and stays online.
  */
 static struct worker_pool *get_work_pool(struct work_struct *work)
 {
 	unsigned long data = atomic_long_read(&work->data);
-	struct worker_pool *pool;
 	int pool_id;
 
+	assert_rcu_or_pool_mutex();
+
 	if (data & WORK_STRUCT_PWQ)
 		return ((struct pool_workqueue *)
 			(data & WORK_STRUCT_WQ_DATA_MASK))->pool;
@@ -597,9 +650,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work)
 	if (pool_id == WORK_OFFQ_POOL_NONE)
 		return NULL;
 
-	pool = worker_pool_by_id(pool_id);
-	WARN_ON_ONCE(!pool);
-	return pool;
+	return idr_find(&worker_pool_idr, pool_id);
 }
 
 /**
@@ -688,7 +739,7 @@ static bool need_to_manage_workers(struct worker_pool *pool)
 /* Do we have too many workers and should some go away? */
 static bool too_many_workers(struct worker_pool *pool)
 {
-	bool managing = pool->flags & POOL_MANAGING_WORKERS;
+	bool managing = mutex_is_locked(&pool->manager_arb);
 	int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
 	int nr_busy = pool->nr_workers - nr_idle;
 
@@ -743,7 +794,7 @@ static void wake_up_worker(struct worker_pool *pool)
  * CONTEXT:
  * spin_lock_irq(rq->lock)
  */
-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
+void wq_worker_waking_up(struct task_struct *task, int cpu)
 {
 	struct worker *worker = kthread_data(task);
 
@@ -768,8 +819,7 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
  * RETURNS:
  * Worker task on @cpu to wake up, %NULL if none.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task,
-				       unsigned int cpu)
+struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
 {
 	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
 	struct worker_pool *pool;
@@ -785,7 +835,8 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task,
 	pool = worker->pool;
 
 	/* this can only happen on the local cpu */
-	BUG_ON(cpu != raw_smp_processor_id());
+	if (WARN_ON_ONCE(cpu != raw_smp_processor_id()))
+		return NULL;
 
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
@@ -890,13 +941,12 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
  * recycled work item as currently executing and make it wait until the
  * current execution finishes, introducing an unwanted dependency.
  *
- * This function checks the work item address, work function and workqueue
- * to avoid false positives.  Note that this isn't complete as one may
- * construct a work function which can introduce dependency onto itself
- * through a recycled work item.  Well, if somebody wants to shoot oneself
- * in the foot that badly, there's only so much we can do, and if such
- * deadlock actually occurs, it should be easy to locate the culprit work
- * function.
+ * This function checks the work item address and work function to avoid
+ * false positives.  Note that this isn't complete as one may construct a
+ * work function which can introduce dependency onto itself through a
+ * recycled work item.  Well, if somebody wants to shoot oneself in the
+ * foot that badly, there's only so much we can do, and if such deadlock
+ * actually occurs, it should be easy to locate the culprit work function.
  *
  * CONTEXT:
  * spin_lock_irq(pool->lock).
@@ -960,6 +1010,64 @@ static void move_linked_works(struct work_struct *work, struct list_head *head,
 		*nextp = n;
 }
 
+/**
+ * get_pwq - get an extra reference on the specified pool_workqueue
+ * @pwq: pool_workqueue to get
+ *
+ * Obtain an extra reference on @pwq.  The caller should guarantee that
+ * @pwq has positive refcnt and be holding the matching pool->lock.
+ */
+static void get_pwq(struct pool_workqueue *pwq)
+{
+	lockdep_assert_held(&pwq->pool->lock);
+	WARN_ON_ONCE(pwq->refcnt <= 0);
+	pwq->refcnt++;
+}
+
+/**
+ * put_pwq - put a pool_workqueue reference
+ * @pwq: pool_workqueue to put
+ *
+ * Drop a reference of @pwq.  If its refcnt reaches zero, schedule its
+ * destruction.  The caller should be holding the matching pool->lock.
+ */
+static void put_pwq(struct pool_workqueue *pwq)
+{
+	lockdep_assert_held(&pwq->pool->lock);
+	if (likely(--pwq->refcnt))
+		return;
+	if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND)))
+		return;
+	/*
+	 * @pwq can't be released under pool->lock, bounce to
+	 * pwq_unbound_release_workfn().  This never recurses on the same
+	 * pool->lock as this path is taken only for unbound workqueues and
+	 * the release work item is scheduled on a per-cpu workqueue.  To
+	 * avoid lockdep warning, unbound pool->locks are given lockdep
+	 * subclass of 1 in get_unbound_pool().
+	 */
+	schedule_work(&pwq->unbound_release_work);
+}
+
+/**
+ * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock
+ * @pwq: pool_workqueue to put (can be %NULL)
+ *
+ * put_pwq() with locking.  This function also allows %NULL @pwq.
+ */
+static void put_pwq_unlocked(struct pool_workqueue *pwq)
+{
+	if (pwq) {
+		/*
+		 * As both pwqs and pools are sched-RCU protected, the
+		 * following lock operations are safe.
+		 */
+		spin_lock_irq(&pwq->pool->lock);
+		put_pwq(pwq);
+		spin_unlock_irq(&pwq->pool->lock);
+	}
+}
+
 static void pwq_activate_delayed_work(struct work_struct *work)
 {
 	struct pool_workqueue *pwq = get_work_pwq(work);
@@ -991,9 +1099,9 @@ static void pwq_activate_first_delayed(struct pool_workqueue *pwq)
  */
 static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
 {
-	/* ignore uncolored works */
+	/* uncolored work items don't participate in flushing or nr_active */
 	if (color == WORK_NO_COLOR)
-		return;
+		goto out_put;
 
 	pwq->nr_in_flight[color]--;
 
@@ -1006,11 +1114,11 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
 
 	/* is flush in progress and are we at the flushing tip? */
 	if (likely(pwq->flush_color != color))
-		return;
+		goto out_put;
 
 	/* are there still in-flight works? */
 	if (pwq->nr_in_flight[color])
-		return;
+		goto out_put;
 
 	/* this pwq is done, clear flush_color */
 	pwq->flush_color = -1;
@@ -1021,6 +1129,8 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
 	 */
 	if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush))
 		complete(&pwq->wq->first_flusher->done);
+out_put:
+	put_pwq(pwq);
 }
 
 /**
@@ -1143,11 +1253,12 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 	/* we own @work, set data and link */
 	set_work_pwq(work, pwq, extra_flags);
 	list_add_tail(&work->entry, head);
+	get_pwq(pwq);
 
 	/*
-	 * Ensure either worker_sched_deactivated() sees the above
-	 * list_add_tail() or we see zero nr_running to avoid workers
-	 * lying around lazily while there are works to be processed.
+	 * Ensure either wq_worker_sleeping() sees the above
+	 * list_add_tail() or we see zero nr_running to avoid workers lying
+	 * around lazily while there are works to be processed.
 	 */
 	smp_mb();
 
@@ -1171,10 +1282,11 @@ static bool is_chained_work(struct workqueue_struct *wq)
 	return worker && worker->current_pwq->wq == wq;
 }
 
-static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
+static void __queue_work(int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
 	struct pool_workqueue *pwq;
+	struct worker_pool *last_pool;
 	struct list_head *worklist;
 	unsigned int work_flags;
 	unsigned int req_cpu = cpu;
@@ -1190,48 +1302,62 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 	debug_work_activate(work);
 
 	/* if dying, only works from the same workqueue are allowed */
-	if (unlikely(wq->flags & WQ_DRAINING) &&
+	if (unlikely(wq->flags & __WQ_DRAINING) &&
 	    WARN_ON_ONCE(!is_chained_work(wq)))
 		return;
+retry:
+	if (req_cpu == WORK_CPU_UNBOUND)
+		cpu = raw_smp_processor_id();
 
-	/* determine the pwq to use */
-	if (!(wq->flags & WQ_UNBOUND)) {
-		struct worker_pool *last_pool;
-
-		if (cpu == WORK_CPU_UNBOUND)
-			cpu = raw_smp_processor_id();
-
-		/*
-		 * It's multi cpu.  If @work was previously on a different
-		 * cpu, it might still be running there, in which case the
-		 * work needs to be queued on that cpu to guarantee
-		 * non-reentrancy.
-		 */
-		pwq = get_pwq(cpu, wq);
-		last_pool = get_work_pool(work);
+	/* pwq which will be used unless @work is executing elsewhere */
+	if (!(wq->flags & WQ_UNBOUND))
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	else
+		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
 
-		if (last_pool && last_pool != pwq->pool) {
-			struct worker *worker;
+	/*
+	 * If @work was previously on a different pool, it might still be
+	 * running there, in which case the work needs to be queued on that
+	 * pool to guarantee non-reentrancy.
+	 */
+	last_pool = get_work_pool(work);
+	if (last_pool && last_pool != pwq->pool) {
+		struct worker *worker;
 
-			spin_lock(&last_pool->lock);
+		spin_lock(&last_pool->lock);
 
-			worker = find_worker_executing_work(last_pool, work);
+		worker = find_worker_executing_work(last_pool, work);
 
-			if (worker && worker->current_pwq->wq == wq) {
-				pwq = get_pwq(last_pool->cpu, wq);
-			} else {
-				/* meh... not running there, queue here */
-				spin_unlock(&last_pool->lock);
-				spin_lock(&pwq->pool->lock);
-			}
+		if (worker && worker->current_pwq->wq == wq) {
+			pwq = worker->current_pwq;
 		} else {
+			/* meh... not running there, queue here */
+			spin_unlock(&last_pool->lock);
 			spin_lock(&pwq->pool->lock);
 		}
 	} else {
-		pwq = get_pwq(WORK_CPU_UNBOUND, wq);
 		spin_lock(&pwq->pool->lock);
 	}
 
+	/*
+	 * pwq is determined and locked.  For unbound pools, we could have
+	 * raced with pwq release and it could already be dead.  If its
+	 * refcnt is zero, repeat pwq selection.  Note that pwqs never die
+	 * without another pwq replacing it in the numa_pwq_tbl or while
+	 * work items are executing on it, so the retrying is guaranteed to
+	 * make forward-progress.
+	 */
+	if (unlikely(!pwq->refcnt)) {
+		if (wq->flags & WQ_UNBOUND) {
+			spin_unlock(&pwq->pool->lock);
+			cpu_relax();
+			goto retry;
+		}
+		/* oops */
+		WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt",
+			  wq->name, cpu);
+	}
+
 	/* pwq determined, queue */
 	trace_workqueue_queue_work(req_cpu, pwq, work);
 
@@ -1286,22 +1412,6 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_work_on);
 
-/**
- * queue_work - queue work on a workqueue
- * @wq: workqueue to use
- * @work: work to queue
- *
- * Returns %false if @work was already on a queue, %true otherwise.
- *
- * We queue the work to the CPU on which it was submitted, but if the CPU dies
- * it can be processed by another CPU.
- */
-bool queue_work(struct workqueue_struct *wq, struct work_struct *work)
-{
-	return queue_work_on(WORK_CPU_UNBOUND, wq, work);
-}
-EXPORT_SYMBOL_GPL(queue_work);
-
 void delayed_work_timer_fn(unsigned long __data)
 {
 	struct delayed_work *dwork = (struct delayed_work *)__data;
@@ -1377,21 +1487,6 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 EXPORT_SYMBOL_GPL(queue_delayed_work_on);
 
 /**
- * queue_delayed_work - queue work on a workqueue after delay
- * @wq: workqueue to use
- * @dwork: delayable work to queue
- * @delay: number of jiffies to wait before queueing
- *
- * Equivalent to queue_delayed_work_on() but tries to use the local CPU.
- */
-bool queue_delayed_work(struct workqueue_struct *wq,
-			struct delayed_work *dwork, unsigned long delay)
-{
-	return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
-}
-EXPORT_SYMBOL_GPL(queue_delayed_work);
-
-/**
  * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU
  * @cpu: CPU number to execute work on
  * @wq: workqueue to use
@@ -1430,21 +1525,6 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
 EXPORT_SYMBOL_GPL(mod_delayed_work_on);
 
 /**
- * mod_delayed_work - modify delay of or queue a delayed work
- * @wq: workqueue to use
- * @dwork: work to queue
- * @delay: number of jiffies to wait before queueing
- *
- * mod_delayed_work_on() on local CPU.
- */
-bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork,
-		      unsigned long delay)
-{
-	return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
-}
-EXPORT_SYMBOL_GPL(mod_delayed_work);
-
-/**
  * worker_enter_idle - enter idle state
  * @worker: worker which is entering idle state
  *
@@ -1458,9 +1538,10 @@ static void worker_enter_idle(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	BUG_ON(worker->flags & WORKER_IDLE);
-	BUG_ON(!list_empty(&worker->entry) &&
-	       (worker->hentry.next || worker->hentry.pprev));
+	if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) ||
+	    WARN_ON_ONCE(!list_empty(&worker->entry) &&
+			 (worker->hentry.next || worker->hentry.pprev)))
+		return;
 
 	/* can't use worker_set_flags(), also called from start_worker() */
 	worker->flags |= WORKER_IDLE;
@@ -1497,22 +1578,25 @@ static void worker_leave_idle(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	BUG_ON(!(worker->flags & WORKER_IDLE));
+	if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE)))
+		return;
 	worker_clr_flags(worker, WORKER_IDLE);
 	pool->nr_idle--;
 	list_del_init(&worker->entry);
 }
 
 /**
- * worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock pool
- * @worker: self
+ * worker_maybe_bind_and_lock - try to bind %current to worker_pool and lock it
+ * @pool: target worker_pool
+ *
+ * Bind %current to the cpu of @pool if it is associated and lock @pool.
  *
  * Works which are scheduled while the cpu is online must at least be
  * scheduled to a worker which is bound to the cpu so that if they are
  * flushed from cpu callbacks while cpu is going down, they are
  * guaranteed to execute on the cpu.
  *
- * This function is to be used by rogue workers and rescuers to bind
+ * This function is to be used by unbound workers and rescuers to bind
  * themselves to the target cpu and may race with cpu going down or
  * coming online.  kthread_bind() can't be used because it may put the
  * worker to already dead cpu and set_cpus_allowed_ptr() can't be used
@@ -1533,12 +1617,9 @@ static void worker_leave_idle(struct worker *worker)
  * %true if the associated pool is online (@worker is successfully
  * bound), %false if offline.
  */
-static bool worker_maybe_bind_and_lock(struct worker *worker)
+static bool worker_maybe_bind_and_lock(struct worker_pool *pool)
 __acquires(&pool->lock)
 {
-	struct worker_pool *pool = worker->pool;
-	struct task_struct *task = worker->task;
-
 	while (true) {
 		/*
 		 * The following call may fail, succeed or succeed
@@ -1547,14 +1628,13 @@ __acquires(&pool->lock)
 		 * against POOL_DISASSOCIATED.
 		 */
 		if (!(pool->flags & POOL_DISASSOCIATED))
-			set_cpus_allowed_ptr(task, get_cpu_mask(pool->cpu));
+			set_cpus_allowed_ptr(current, pool->attrs->cpumask);
 
 		spin_lock_irq(&pool->lock);
 		if (pool->flags & POOL_DISASSOCIATED)
 			return false;
-		if (task_cpu(task) == pool->cpu &&
-		    cpumask_equal(&current->cpus_allowed,
-				  get_cpu_mask(pool->cpu)))
+		if (task_cpu(current) == pool->cpu &&
+		    cpumask_equal(&current->cpus_allowed, pool->attrs->cpumask))
 			return true;
 		spin_unlock_irq(&pool->lock);
 
@@ -1569,108 +1649,6 @@ __acquires(&pool->lock)
 	}
 }
 
-/*
- * Rebind an idle @worker to its CPU.  worker_thread() will test
- * list_empty(@worker->entry) before leaving idle and call this function.
- */
-static void idle_worker_rebind(struct worker *worker)
-{
-	/* CPU may go down again inbetween, clear UNBOUND only on success */
-	if (worker_maybe_bind_and_lock(worker))
-		worker_clr_flags(worker, WORKER_UNBOUND);
-
-	/* rebind complete, become available again */
-	list_add(&worker->entry, &worker->pool->idle_list);
-	spin_unlock_irq(&worker->pool->lock);
-}
-
-/*
- * Function for @worker->rebind.work used to rebind unbound busy workers to
- * the associated cpu which is coming back online.  This is scheduled by
- * cpu up but can race with other cpu hotplug operations and may be
- * executed twice without intervening cpu down.
- */
-static void busy_worker_rebind_fn(struct work_struct *work)
-{
-	struct worker *worker = container_of(work, struct worker, rebind_work);
-
-	if (worker_maybe_bind_and_lock(worker))
-		worker_clr_flags(worker, WORKER_UNBOUND);
-
-	spin_unlock_irq(&worker->pool->lock);
-}
-
-/**
- * rebind_workers - rebind all workers of a pool to the associated CPU
- * @pool: pool of interest
- *
- * @pool->cpu is coming online.  Rebind all workers to the CPU.  Rebinding
- * is different for idle and busy ones.
- *
- * Idle ones will be removed from the idle_list and woken up.  They will
- * add themselves back after completing rebind.  This ensures that the
- * idle_list doesn't contain any unbound workers when re-bound busy workers
- * try to perform local wake-ups for concurrency management.
- *
- * Busy workers can rebind after they finish their current work items.
- * Queueing the rebind work item at the head of the scheduled list is
- * enough.  Note that nr_running will be properly bumped as busy workers
- * rebind.
- *
- * On return, all non-manager workers are scheduled for rebind - see
- * manage_workers() for the manager special case.  Any idle worker
- * including the manager will not appear on @idle_list until rebind is
- * complete, making local wake-ups safe.
- */
-static void rebind_workers(struct worker_pool *pool)
-{
-	struct worker *worker, *n;
-	int i;
-
-	lockdep_assert_held(&pool->assoc_mutex);
-	lockdep_assert_held(&pool->lock);
-
-	/* dequeue and kick idle ones */
-	list_for_each_entry_safe(worker, n, &pool->idle_list, entry) {
-		/*
-		 * idle workers should be off @pool->idle_list until rebind
-		 * is complete to avoid receiving premature local wake-ups.
-		 */
-		list_del_init(&worker->entry);
-
-		/*
-		 * worker_thread() will see the above dequeuing and call
-		 * idle_worker_rebind().
-		 */
-		wake_up_process(worker->task);
-	}
-
-	/* rebind busy workers */
-	for_each_busy_worker(worker, i, pool) {
-		struct work_struct *rebind_work = &worker->rebind_work;
-		struct workqueue_struct *wq;
-
-		if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
-				     work_data_bits(rebind_work)))
-			continue;
-
-		debug_work_activate(rebind_work);
-
-		/*
-		 * wq doesn't really matter but let's keep @worker->pool
-		 * and @pwq->pool consistent for sanity.
-		 */
-		if (std_worker_pool_pri(worker->pool))
-			wq = system_highpri_wq;
-		else
-			wq = system_wq;
-
-		insert_work(get_pwq(pool->cpu, wq), rebind_work,
-			    worker->scheduled.next,
-			    work_color_to_flags(WORK_NO_COLOR));
-	}
-}
-
 static struct worker *alloc_worker(void)
 {
 	struct worker *worker;
@@ -1679,7 +1657,6 @@ static struct worker *alloc_worker(void)
 	if (worker) {
 		INIT_LIST_HEAD(&worker->entry);
 		INIT_LIST_HEAD(&worker->scheduled);
-		INIT_WORK(&worker->rebind_work, busy_worker_rebind_fn);
 		/* on creation a worker is in !idle && prep state */
 		worker->flags = WORKER_PREP;
 	}
@@ -1702,18 +1679,25 @@ static struct worker *alloc_worker(void)
  */
 static struct worker *create_worker(struct worker_pool *pool)
 {
-	const char *pri = std_worker_pool_pri(pool) ? "H" : "";
 	struct worker *worker = NULL;
 	int id = -1;
+	char id_buf[16];
 
+	lockdep_assert_held(&pool->manager_mutex);
+
+	/*
+	 * ID is needed to determine kthread name.  Allocate ID first
+	 * without installing the pointer.
+	 */
+	idr_preload(GFP_KERNEL);
 	spin_lock_irq(&pool->lock);
-	while (ida_get_new(&pool->worker_ida, &id)) {
-		spin_unlock_irq(&pool->lock);
-		if (!ida_pre_get(&pool->worker_ida, GFP_KERNEL))
-			goto fail;
-		spin_lock_irq(&pool->lock);
-	}
+
+	id = idr_alloc(&pool->worker_idr, NULL, 0, 0, GFP_NOWAIT);
+
 	spin_unlock_irq(&pool->lock);
+	idr_preload_end();
+	if (id < 0)
+		goto fail;
 
 	worker = alloc_worker();
 	if (!worker)
@@ -1722,40 +1706,46 @@ static struct worker *create_worker(struct worker_pool *pool)
 	worker->pool = pool;
 	worker->id = id;
 
-	if (pool->cpu != WORK_CPU_UNBOUND)
-		worker->task = kthread_create_on_node(worker_thread,
-					worker, cpu_to_node(pool->cpu),
-					"kworker/%u:%d%s", pool->cpu, id, pri);
+	if (pool->cpu >= 0)
+		snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id,
+			 pool->attrs->nice < 0  ? "H" : "");
 	else
-		worker->task = kthread_create(worker_thread, worker,
-					      "kworker/u:%d%s", id, pri);
+		snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id);
+
+	worker->task = kthread_create_on_node(worker_thread, worker, pool->node,
+					      "kworker/%s", id_buf);
 	if (IS_ERR(worker->task))
 		goto fail;
 
-	if (std_worker_pool_pri(pool))
-		set_user_nice(worker->task, HIGHPRI_NICE_LEVEL);
+	/*
+	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
+	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
+	 */
+	set_user_nice(worker->task, pool->attrs->nice);
+	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+
+	/* prevent userland from meddling with cpumask of workqueue workers */
+	worker->task->flags |= PF_NO_SETAFFINITY;
 
 	/*
-	 * Determine CPU binding of the new worker depending on
-	 * %POOL_DISASSOCIATED.  The caller is responsible for ensuring the
-	 * flag remains stable across this function.  See the comments
-	 * above the flag definition for details.
-	 *
-	 * As an unbound worker may later become a regular one if CPU comes
-	 * online, make sure every worker has %PF_THREAD_BOUND set.
+	 * The caller is responsible for ensuring %POOL_DISASSOCIATED
+	 * remains stable across this function.  See the comments above the
+	 * flag definition for details.
 	 */
-	if (!(pool->flags & POOL_DISASSOCIATED)) {
-		kthread_bind(worker->task, pool->cpu);
-	} else {
-		worker->task->flags |= PF_THREAD_BOUND;
+	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
-	}
+
+	/* successful, commit the pointer to idr */
+	spin_lock_irq(&pool->lock);
+	idr_replace(&pool->worker_idr, worker, worker->id);
+	spin_unlock_irq(&pool->lock);
 
 	return worker;
+
 fail:
 	if (id >= 0) {
 		spin_lock_irq(&pool->lock);
-		ida_remove(&pool->worker_ida, id);
+		idr_remove(&pool->worker_idr, id);
 		spin_unlock_irq(&pool->lock);
 	}
 	kfree(worker);
@@ -1780,6 +1770,30 @@ static void start_worker(struct worker *worker)
 }
 
 /**
+ * create_and_start_worker - create and start a worker for a pool
+ * @pool: the target pool
+ *
+ * Grab the managership of @pool and create and start a new worker for it.
+ */
+static int create_and_start_worker(struct worker_pool *pool)
+{
+	struct worker *worker;
+
+	mutex_lock(&pool->manager_mutex);
+
+	worker = create_worker(pool);
+	if (worker) {
+		spin_lock_irq(&pool->lock);
+		start_worker(worker);
+		spin_unlock_irq(&pool->lock);
+	}
+
+	mutex_unlock(&pool->manager_mutex);
+
+	return worker ? 0 : -ENOMEM;
+}
+
+/**
  * destroy_worker - destroy a workqueue worker
  * @worker: worker to be destroyed
  *
@@ -1791,11 +1805,14 @@ static void start_worker(struct worker *worker)
 static void destroy_worker(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
-	int id = worker->id;
+
+	lockdep_assert_held(&pool->manager_mutex);
+	lockdep_assert_held(&pool->lock);
 
 	/* sanity check frenzy */
-	BUG_ON(worker->current_work);
-	BUG_ON(!list_empty(&worker->scheduled));
+	if (WARN_ON(worker->current_work) ||
+	    WARN_ON(!list_empty(&worker->scheduled)))
+		return;
 
 	if (worker->flags & WORKER_STARTED)
 		pool->nr_workers--;
@@ -1805,13 +1822,14 @@ static void destroy_worker(struct worker *worker)
 	list_del_init(&worker->entry);
 	worker->flags |= WORKER_DIE;
 
+	idr_remove(&pool->worker_idr, worker->id);
+
 	spin_unlock_irq(&pool->lock);
 
 	kthread_stop(worker->task);
 	kfree(worker);
 
 	spin_lock_irq(&pool->lock);
-	ida_remove(&pool->worker_ida, id);
 }
 
 static void idle_worker_timeout(unsigned long __pool)
@@ -1840,23 +1858,21 @@ static void idle_worker_timeout(unsigned long __pool)
 	spin_unlock_irq(&pool->lock);
 }
 
-static bool send_mayday(struct work_struct *work)
+static void send_mayday(struct work_struct *work)
 {
 	struct pool_workqueue *pwq = get_work_pwq(work);
 	struct workqueue_struct *wq = pwq->wq;
-	unsigned int cpu;
 
-	if (!(wq->flags & WQ_RESCUER))
-		return false;
+	lockdep_assert_held(&wq_mayday_lock);
+
+	if (!wq->rescuer)
+		return;
 
 	/* mayday mayday mayday */
-	cpu = pwq->pool->cpu;
-	/* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */
-	if (cpu == WORK_CPU_UNBOUND)
-		cpu = 0;
-	if (!mayday_test_and_set_cpu(cpu, wq->mayday_mask))
+	if (list_empty(&pwq->mayday_node)) {
+		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
-	return true;
+	}
 }
 
 static void pool_mayday_timeout(unsigned long __pool)
@@ -1864,7 +1880,8 @@ static void pool_mayday_timeout(unsigned long __pool)
 	struct worker_pool *pool = (void *)__pool;
 	struct work_struct *work;
 
-	spin_lock_irq(&pool->lock);
+	spin_lock_irq(&wq_mayday_lock);		/* for wq->maydays */
+	spin_lock(&pool->lock);
 
 	if (need_to_create_worker(pool)) {
 		/*
@@ -1877,7 +1894,8 @@ static void pool_mayday_timeout(unsigned long __pool)
 			send_mayday(work);
 	}
 
-	spin_unlock_irq(&pool->lock);
+	spin_unlock(&pool->lock);
+	spin_unlock_irq(&wq_mayday_lock);
 
 	mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL);
 }
@@ -1892,8 +1910,8 @@ static void pool_mayday_timeout(unsigned long __pool)
  * sent to all rescuers with works scheduled on @pool to resolve
  * possible allocation deadlock.
  *
- * On return, need_to_create_worker() is guaranteed to be false and
- * may_start_working() true.
+ * On return, need_to_create_worker() is guaranteed to be %false and
+ * may_start_working() %true.
  *
  * LOCKING:
  * spin_lock_irq(pool->lock) which may be released and regrabbed
@@ -1901,7 +1919,7 @@ static void pool_mayday_timeout(unsigned long __pool)
  * manager.
  *
  * RETURNS:
- * false if no action was taken and pool->lock stayed locked, true
+ * %false if no action was taken and pool->lock stayed locked, %true
  * otherwise.
  */
 static bool maybe_create_worker(struct worker_pool *pool)
@@ -1924,7 +1942,8 @@ restart:
 			del_timer_sync(&pool->mayday_timer);
 			spin_lock_irq(&pool->lock);
 			start_worker(worker);
-			BUG_ON(need_to_create_worker(pool));
+			if (WARN_ON_ONCE(need_to_create_worker(pool)))
+				goto restart;
 			return true;
 		}
 
@@ -1957,7 +1976,7 @@ restart:
  * multiple times.  Called only from manager.
  *
  * RETURNS:
- * false if no action was taken and pool->lock stayed locked, true
+ * %false if no action was taken and pool->lock stayed locked, %true
  * otherwise.
  */
 static bool maybe_destroy_workers(struct worker_pool *pool)
@@ -2008,42 +2027,37 @@ static bool manage_workers(struct worker *worker)
 	struct worker_pool *pool = worker->pool;
 	bool ret = false;
 
-	if (pool->flags & POOL_MANAGING_WORKERS)
+	/*
+	 * Managership is governed by two mutexes - manager_arb and
+	 * manager_mutex.  manager_arb handles arbitration of manager role.
+	 * Anyone who successfully grabs manager_arb wins the arbitration
+	 * and becomes the manager.  mutex_trylock() on pool->manager_arb
+	 * failure while holding pool->lock reliably indicates that someone
+	 * else is managing the pool and the worker which failed trylock
+	 * can proceed to executing work items.  This means that anyone
+	 * grabbing manager_arb is responsible for actually performing
+	 * manager duties.  If manager_arb is grabbed and released without
+	 * actual management, the pool may stall indefinitely.
+	 *
+	 * manager_mutex is used for exclusion of actual management
+	 * operations.  The holder of manager_mutex can be sure that none
+	 * of management operations, including creation and destruction of
+	 * workers, won't take place until the mutex is released.  Because
+	 * manager_mutex doesn't interfere with manager role arbitration,
+	 * it is guaranteed that the pool's management, while may be
+	 * delayed, won't be disturbed by someone else grabbing
+	 * manager_mutex.
+	 */
+	if (!mutex_trylock(&pool->manager_arb))
 		return ret;
 
-	pool->flags |= POOL_MANAGING_WORKERS;
-
 	/*
-	 * To simplify both worker management and CPU hotplug, hold off
-	 * management while hotplug is in progress.  CPU hotplug path can't
-	 * grab %POOL_MANAGING_WORKERS to achieve this because that can
-	 * lead to idle worker depletion (all become busy thinking someone
-	 * else is managing) which in turn can result in deadlock under
-	 * extreme circumstances.  Use @pool->assoc_mutex to synchronize
-	 * manager against CPU hotplug.
-	 *
-	 * assoc_mutex would always be free unless CPU hotplug is in
-	 * progress.  trylock first without dropping @pool->lock.
+	 * With manager arbitration won, manager_mutex would be free in
+	 * most cases.  trylock first without dropping @pool->lock.
 	 */
-	if (unlikely(!mutex_trylock(&pool->assoc_mutex))) {
+	if (unlikely(!mutex_trylock(&pool->manager_mutex))) {
 		spin_unlock_irq(&pool->lock);
-		mutex_lock(&pool->assoc_mutex);
-		/*
-		 * CPU hotplug could have happened while we were waiting
-		 * for assoc_mutex.  Hotplug itself can't handle us
-		 * because manager isn't either on idle or busy list, and
-		 * @pool's state and ours could have deviated.
-		 *
-		 * As hotplug is now excluded via assoc_mutex, we can
-		 * simply try to bind.  It will succeed or fail depending
-		 * on @pool's current state.  Try it and adjust
-		 * %WORKER_UNBOUND accordingly.
-		 */
-		if (worker_maybe_bind_and_lock(worker))
-			worker->flags &= ~WORKER_UNBOUND;
-		else
-			worker->flags |= WORKER_UNBOUND;
-
+		mutex_lock(&pool->manager_mutex);
 		ret = true;
 	}
 
@@ -2056,8 +2070,8 @@ static bool manage_workers(struct worker *worker)
 	ret |= maybe_destroy_workers(pool);
 	ret |= maybe_create_worker(pool);
 
-	pool->flags &= ~POOL_MANAGING_WORKERS;
-	mutex_unlock(&pool->assoc_mutex);
+	mutex_unlock(&pool->manager_mutex);
+	mutex_unlock(&pool->manager_arb);
 	return ret;
 }
 
@@ -2211,11 +2225,11 @@ static void process_scheduled_works(struct worker *worker)
  * worker_thread - the worker thread function
  * @__worker: self
  *
- * The worker thread function.  There are NR_CPU_WORKER_POOLS dynamic pools
- * of these per each cpu.  These workers process all works regardless of
- * their specific target workqueue.  The only exception is works which
- * belong to workqueues with a rescuer which will be explained in
- * rescuer_thread().
+ * The worker thread function.  All workers belong to a worker_pool -
+ * either a per-cpu one or dynamic unbound one.  These workers process all
+ * work items regardless of their specific target workqueue.  The only
+ * exception is work items which belong to workqueues with a rescuer which
+ * will be explained in rescuer_thread().
  */
 static int worker_thread(void *__worker)
 {
@@ -2227,19 +2241,12 @@ static int worker_thread(void *__worker)
 woke_up:
 	spin_lock_irq(&pool->lock);
 
-	/* we are off idle list if destruction or rebind is requested */
-	if (unlikely(list_empty(&worker->entry))) {
+	/* am I supposed to die? */
+	if (unlikely(worker->flags & WORKER_DIE)) {
 		spin_unlock_irq(&pool->lock);
-
-		/* if DIE is set, destruction is requested */
-		if (worker->flags & WORKER_DIE) {
-			worker->task->flags &= ~PF_WQ_WORKER;
-			return 0;
-		}
-
-		/* otherwise, rebind */
-		idle_worker_rebind(worker);
-		goto woke_up;
+		WARN_ON_ONCE(!list_empty(&worker->entry));
+		worker->task->flags &= ~PF_WQ_WORKER;
+		return 0;
 	}
 
 	worker_leave_idle(worker);
@@ -2257,14 +2264,16 @@ recheck:
 	 * preparing to process a work or actually processing it.
 	 * Make sure nobody diddled with it while I was sleeping.
 	 */
-	BUG_ON(!list_empty(&worker->scheduled));
+	WARN_ON_ONCE(!list_empty(&worker->scheduled));
 
 	/*
-	 * When control reaches this point, we're guaranteed to have
-	 * at least one idle worker or that someone else has already
-	 * assumed the manager role.
+	 * Finish PREP stage.  We're guaranteed to have at least one idle
+	 * worker or that someone else has already assumed the manager
+	 * role.  This is where @worker starts participating in concurrency
+	 * management if applicable and concurrency management is restored
+	 * after being rebound.  See rebind_workers() for details.
 	 */
-	worker_clr_flags(worker, WORKER_PREP);
+	worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND);
 
 	do {
 		struct work_struct *work =
@@ -2306,7 +2315,7 @@ sleep:
  * @__rescuer: self
  *
  * Workqueue rescuer thread function.  There's one rescuer for each
- * workqueue which has WQ_RESCUER set.
+ * workqueue which has WQ_MEM_RECLAIM set.
  *
  * Regular work processing on a pool may block trying to create a new
  * worker which uses GFP_KERNEL allocation which has slight chance of
@@ -2325,8 +2334,6 @@ static int rescuer_thread(void *__rescuer)
 	struct worker *rescuer = __rescuer;
 	struct workqueue_struct *wq = rescuer->rescue_wq;
 	struct list_head *scheduled = &rescuer->scheduled;
-	bool is_unbound = wq->flags & WQ_UNBOUND;
-	unsigned int cpu;
 
 	set_user_nice(current, RESCUER_NICE_LEVEL);
 
@@ -2344,28 +2351,29 @@ repeat:
 		return 0;
 	}
 
-	/*
-	 * See whether any cpu is asking for help.  Unbounded
-	 * workqueues use cpu 0 in mayday_mask for CPU_UNBOUND.
-	 */
-	for_each_mayday_cpu(cpu, wq->mayday_mask) {
-		unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu;
-		struct pool_workqueue *pwq = get_pwq(tcpu, wq);
+	/* see whether any pwq is asking for help */
+	spin_lock_irq(&wq_mayday_lock);
+
+	while (!list_empty(&wq->maydays)) {
+		struct pool_workqueue *pwq = list_first_entry(&wq->maydays,
+					struct pool_workqueue, mayday_node);
 		struct worker_pool *pool = pwq->pool;
 		struct work_struct *work, *n;
 
 		__set_current_state(TASK_RUNNING);
-		mayday_clear_cpu(cpu, wq->mayday_mask);
+		list_del_init(&pwq->mayday_node);
+
+		spin_unlock_irq(&wq_mayday_lock);
 
 		/* migrate to the target cpu if possible */
+		worker_maybe_bind_and_lock(pool);
 		rescuer->pool = pool;
-		worker_maybe_bind_and_lock(rescuer);
 
 		/*
 		 * Slurp in all works issued via this workqueue and
 		 * process'em.
 		 */
-		BUG_ON(!list_empty(&rescuer->scheduled));
+		WARN_ON_ONCE(!list_empty(&rescuer->scheduled));
 		list_for_each_entry_safe(work, n, &pool->worklist, entry)
 			if (get_work_pwq(work) == pwq)
 				move_linked_works(work, scheduled, &n);
@@ -2380,9 +2388,13 @@ repeat:
 		if (keep_working(pool))
 			wake_up_worker(pool);
 
-		spin_unlock_irq(&pool->lock);
+		rescuer->pool = NULL;
+		spin_unlock(&pool->lock);
+		spin_lock(&wq_mayday_lock);
 	}
 
+	spin_unlock_irq(&wq_mayday_lock);
+
 	/* rescuers should never participate in concurrency management */
 	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
 	schedule();
@@ -2486,7 +2498,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
  * advanced to @work_color.
  *
  * CONTEXT:
- * mutex_lock(wq->flush_mutex).
+ * mutex_lock(wq->mutex).
  *
  * RETURNS:
  * %true if @flush_color >= 0 and there's something to flush.  %false
@@ -2496,21 +2508,20 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
 				      int flush_color, int work_color)
 {
 	bool wait = false;
-	unsigned int cpu;
+	struct pool_workqueue *pwq;
 
 	if (flush_color >= 0) {
-		BUG_ON(atomic_read(&wq->nr_pwqs_to_flush));
+		WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush));
 		atomic_set(&wq->nr_pwqs_to_flush, 1);
 	}
 
-	for_each_pwq_cpu(cpu, wq) {
-		struct pool_workqueue *pwq = get_pwq(cpu, wq);
+	for_each_pwq(pwq, wq) {
 		struct worker_pool *pool = pwq->pool;
 
 		spin_lock_irq(&pool->lock);
 
 		if (flush_color >= 0) {
-			BUG_ON(pwq->flush_color != -1);
+			WARN_ON_ONCE(pwq->flush_color != -1);
 
 			if (pwq->nr_in_flight[flush_color]) {
 				pwq->flush_color = flush_color;
@@ -2520,7 +2531,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
 		}
 
 		if (work_color >= 0) {
-			BUG_ON(work_color != work_next_color(pwq->work_color));
+			WARN_ON_ONCE(work_color != work_next_color(pwq->work_color));
 			pwq->work_color = work_color;
 		}
 
@@ -2537,11 +2548,8 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
  * flush_workqueue - ensure that any scheduled work has run to completion.
  * @wq: workqueue to flush
  *
- * Forces execution of the workqueue and blocks until its completion.
- * This is typically used in driver shutdown handlers.
- *
- * We sleep until all works which were queued on entry have been handled,
- * but we are not livelocked by new incoming ones.
+ * This function sleeps until all work items which were queued on entry
+ * have finished execution, but it is not livelocked by new incoming ones.
  */
 void flush_workqueue(struct workqueue_struct *wq)
 {
@@ -2555,7 +2563,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 	lock_map_acquire(&wq->lockdep_map);
 	lock_map_release(&wq->lockdep_map);
 
-	mutex_lock(&wq->flush_mutex);
+	mutex_lock(&wq->mutex);
 
 	/*
 	 * Start-to-wait phase
@@ -2568,13 +2576,13 @@ void flush_workqueue(struct workqueue_struct *wq)
 		 * becomes our flush_color and work_color is advanced
 		 * by one.
 		 */
-		BUG_ON(!list_empty(&wq->flusher_overflow));
+		WARN_ON_ONCE(!list_empty(&wq->flusher_overflow));
 		this_flusher.flush_color = wq->work_color;
 		wq->work_color = next_color;
 
 		if (!wq->first_flusher) {
 			/* no flush in progress, become the first flusher */
-			BUG_ON(wq->flush_color != this_flusher.flush_color);
+			WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color);
 
 			wq->first_flusher = &this_flusher;
 
@@ -2587,7 +2595,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 			}
 		} else {
 			/* wait in queue */
-			BUG_ON(wq->flush_color == this_flusher.flush_color);
+			WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color);
 			list_add_tail(&this_flusher.list, &wq->flusher_queue);
 			flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
 		}
@@ -2600,7 +2608,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 		list_add_tail(&this_flusher.list, &wq->flusher_overflow);
 	}
 
-	mutex_unlock(&wq->flush_mutex);
+	mutex_unlock(&wq->mutex);
 
 	wait_for_completion(&this_flusher.done);
 
@@ -2613,7 +2621,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 	if (wq->first_flusher != &this_flusher)
 		return;
 
-	mutex_lock(&wq->flush_mutex);
+	mutex_lock(&wq->mutex);
 
 	/* we might have raced, check again with mutex held */
 	if (wq->first_flusher != &this_flusher)
@@ -2621,8 +2629,8 @@ void flush_workqueue(struct workqueue_struct *wq)
 
 	wq->first_flusher = NULL;
 
-	BUG_ON(!list_empty(&this_flusher.list));
-	BUG_ON(wq->flush_color != this_flusher.flush_color);
+	WARN_ON_ONCE(!list_empty(&this_flusher.list));
+	WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color);
 
 	while (true) {
 		struct wq_flusher *next, *tmp;
@@ -2635,8 +2643,8 @@ void flush_workqueue(struct workqueue_struct *wq)
 			complete(&next->done);
 		}
 
-		BUG_ON(!list_empty(&wq->flusher_overflow) &&
-		       wq->flush_color != work_next_color(wq->work_color));
+		WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) &&
+			     wq->flush_color != work_next_color(wq->work_color));
 
 		/* this flush_color is finished, advance by one */
 		wq->flush_color = work_next_color(wq->flush_color);
@@ -2660,7 +2668,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 		}
 
 		if (list_empty(&wq->flusher_queue)) {
-			BUG_ON(wq->flush_color != wq->work_color);
+			WARN_ON_ONCE(wq->flush_color != wq->work_color);
 			break;
 		}
 
@@ -2668,8 +2676,8 @@ void flush_workqueue(struct workqueue_struct *wq)
 		 * Need to flush more colors.  Make the next flusher
 		 * the new first flusher and arm pwqs.
 		 */
-		BUG_ON(wq->flush_color == wq->work_color);
-		BUG_ON(wq->flush_color != next->flush_color);
+		WARN_ON_ONCE(wq->flush_color == wq->work_color);
+		WARN_ON_ONCE(wq->flush_color != next->flush_color);
 
 		list_del_init(&next->list);
 		wq->first_flusher = next;
@@ -2685,7 +2693,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 	}
 
 out_unlock:
-	mutex_unlock(&wq->flush_mutex);
+	mutex_unlock(&wq->mutex);
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
@@ -2703,22 +2711,23 @@ EXPORT_SYMBOL_GPL(flush_workqueue);
 void drain_workqueue(struct workqueue_struct *wq)
 {
 	unsigned int flush_cnt = 0;
-	unsigned int cpu;
+	struct pool_workqueue *pwq;
 
 	/*
 	 * __queue_work() needs to test whether there are drainers, is much
 	 * hotter than drain_workqueue() and already looks at @wq->flags.
-	 * Use WQ_DRAINING so that queue doesn't have to check nr_drainers.
+	 * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers.
 	 */
-	spin_lock(&workqueue_lock);
+	mutex_lock(&wq->mutex);
 	if (!wq->nr_drainers++)
-		wq->flags |= WQ_DRAINING;
-	spin_unlock(&workqueue_lock);
+		wq->flags |= __WQ_DRAINING;
+	mutex_unlock(&wq->mutex);
 reflush:
 	flush_workqueue(wq);
 
-	for_each_pwq_cpu(cpu, wq) {
-		struct pool_workqueue *pwq = get_pwq(cpu, wq);
+	mutex_lock(&wq->mutex);
+
+	for_each_pwq(pwq, wq) {
 		bool drained;
 
 		spin_lock_irq(&pwq->pool->lock);
@@ -2730,15 +2739,16 @@ reflush:
 
 		if (++flush_cnt == 10 ||
 		    (flush_cnt % 100 == 0 && flush_cnt <= 1000))
-			pr_warn("workqueue %s: flush on destruction isn't complete after %u tries\n",
+			pr_warn("workqueue %s: drain_workqueue() isn't complete after %u tries\n",
 				wq->name, flush_cnt);
+
+		mutex_unlock(&wq->mutex);
 		goto reflush;
 	}
 
-	spin_lock(&workqueue_lock);
 	if (!--wq->nr_drainers)
-		wq->flags &= ~WQ_DRAINING;
-	spin_unlock(&workqueue_lock);
+		wq->flags &= ~__WQ_DRAINING;
+	mutex_unlock(&wq->mutex);
 }
 EXPORT_SYMBOL_GPL(drain_workqueue);
 
@@ -2749,11 +2759,15 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
 	struct pool_workqueue *pwq;
 
 	might_sleep();
+
+	local_irq_disable();
 	pool = get_work_pool(work);
-	if (!pool)
+	if (!pool) {
+		local_irq_enable();
 		return false;
+	}
 
-	spin_lock_irq(&pool->lock);
+	spin_lock(&pool->lock);
 	/* see the comment in try_to_grab_pending() with the same code */
 	pwq = get_work_pwq(work);
 	if (pwq) {
@@ -2775,7 +2789,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
 	 * flusher is not running on the same workqueue by verifying write
 	 * access.
 	 */
-	if (pwq->wq->saved_max_active == 1 || pwq->wq->flags & WQ_RESCUER)
+	if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)
 		lock_map_acquire(&pwq->wq->lockdep_map);
 	else
 		lock_map_acquire_read(&pwq->wq->lockdep_map);
@@ -2932,66 +2946,6 @@ bool cancel_delayed_work_sync(struct delayed_work *dwork)
 EXPORT_SYMBOL(cancel_delayed_work_sync);
 
 /**
- * schedule_work_on - put work task on a specific cpu
- * @cpu: cpu to put the work task on
- * @work: job to be done
- *
- * This puts a job on a specific cpu
- */
-bool schedule_work_on(int cpu, struct work_struct *work)
-{
-	return queue_work_on(cpu, system_wq, work);
-}
-EXPORT_SYMBOL(schedule_work_on);
-
-/**
- * schedule_work - put work task in global workqueue
- * @work: job to be done
- *
- * Returns %false if @work was already on the kernel-global workqueue and
- * %true 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.
- */
-bool schedule_work(struct work_struct *work)
-{
-	return queue_work(system_wq, work);
-}
-EXPORT_SYMBOL(schedule_work);
-
-/**
- * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
- * @cpu: cpu to use
- * @dwork: job to be done
- * @delay: number of jiffies to wait
- *
- * After waiting for a given time this puts a job in the kernel-global
- * workqueue on the specified CPU.
- */
-bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
-			      unsigned long delay)
-{
-	return queue_delayed_work_on(cpu, system_wq, dwork, delay);
-}
-EXPORT_SYMBOL(schedule_delayed_work_on);
-
-/**
- * schedule_delayed_work - put work task in global workqueue after delay
- * @dwork: job to be done
- * @delay: number of jiffies to wait or 0 for immediate execution
- *
- * After waiting for a given time this puts a job in the kernel-global
- * workqueue.
- */
-bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay)
-{
-	return queue_delayed_work(system_wq, dwork, delay);
-}
-EXPORT_SYMBOL(schedule_delayed_work);
-
-/**
  * schedule_on_each_cpu - execute a function synchronously on each online CPU
  * @func: the function to call
  *
@@ -3084,51 +3038,1025 @@ int execute_in_process_context(work_func_t fn, struct execute_work *ew)
 }
 EXPORT_SYMBOL_GPL(execute_in_process_context);
 
-int keventd_up(void)
+#ifdef CONFIG_SYSFS
+/*
+ * Workqueues with WQ_SYSFS flag set is visible to userland via
+ * /sys/bus/workqueue/devices/WQ_NAME.  All visible workqueues have the
+ * following attributes.
+ *
+ *  per_cpu	RO bool	: whether the workqueue is per-cpu or unbound
+ *  max_active	RW int	: maximum number of in-flight work items
+ *
+ * Unbound workqueues have the following extra attributes.
+ *
+ *  id		RO int	: the associated pool ID
+ *  nice	RW int	: nice value of the workers
+ *  cpumask	RW mask	: bitmask of allowed CPUs for the workers
+ */
+struct wq_device {
+	struct workqueue_struct		*wq;
+	struct device			dev;
+};
+
+static struct workqueue_struct *dev_to_wq(struct device *dev)
+{
+	struct wq_device *wq_dev = container_of(dev, struct wq_device, dev);
+
+	return wq_dev->wq;
+}
+
+static ssize_t wq_per_cpu_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND));
+}
+
+static ssize_t wq_max_active_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active);
+}
+
+static ssize_t wq_max_active_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	int val;
+
+	if (sscanf(buf, "%d", &val) != 1 || val <= 0)
+		return -EINVAL;
+
+	workqueue_set_max_active(wq, val);
+	return count;
+}
+
+static struct device_attribute wq_sysfs_attrs[] = {
+	__ATTR(per_cpu, 0444, wq_per_cpu_show, NULL),
+	__ATTR(max_active, 0644, wq_max_active_show, wq_max_active_store),
+	__ATTR_NULL,
+};
+
+static ssize_t wq_pool_ids_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	const char *delim = "";
+	int node, written = 0;
+
+	rcu_read_lock_sched();
+	for_each_node(node) {
+		written += scnprintf(buf + written, PAGE_SIZE - written,
+				     "%s%d:%d", delim, node,
+				     unbound_pwq_by_node(wq, node)->pool->id);
+		delim = " ";
+	}
+	written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
+	rcu_read_unlock_sched();
+
+	return written;
+}
+
+static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	int written;
+
+	mutex_lock(&wq->mutex);
+	written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice);
+	mutex_unlock(&wq->mutex);
+
+	return written;
+}
+
+/* prepare workqueue_attrs for sysfs store operations */
+static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
+{
+	struct workqueue_attrs *attrs;
+
+	attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	if (!attrs)
+		return NULL;
+
+	mutex_lock(&wq->mutex);
+	copy_workqueue_attrs(attrs, wq->unbound_attrs);
+	mutex_unlock(&wq->mutex);
+	return attrs;
+}
+
+static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	struct workqueue_attrs *attrs;
+	int ret;
+
+	attrs = wq_sysfs_prep_attrs(wq);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (sscanf(buf, "%d", &attrs->nice) == 1 &&
+	    attrs->nice >= -20 && attrs->nice <= 19)
+		ret = apply_workqueue_attrs(wq, attrs);
+	else
+		ret = -EINVAL;
+
+	free_workqueue_attrs(attrs);
+	return ret ?: count;
+}
+
+static ssize_t wq_cpumask_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	int written;
+
+	mutex_lock(&wq->mutex);
+	written = cpumask_scnprintf(buf, PAGE_SIZE, wq->unbound_attrs->cpumask);
+	mutex_unlock(&wq->mutex);
+
+	written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
+	return written;
+}
+
+static ssize_t wq_cpumask_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	struct workqueue_attrs *attrs;
+	int ret;
+
+	attrs = wq_sysfs_prep_attrs(wq);
+	if (!attrs)
+		return -ENOMEM;
+
+	ret = cpumask_parse(buf, attrs->cpumask);
+	if (!ret)
+		ret = apply_workqueue_attrs(wq, attrs);
+
+	free_workqueue_attrs(attrs);
+	return ret ?: count;
+}
+
+static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	int written;
+
+	mutex_lock(&wq->mutex);
+	written = scnprintf(buf, PAGE_SIZE, "%d\n",
+			    !wq->unbound_attrs->no_numa);
+	mutex_unlock(&wq->mutex);
+
+	return written;
+}
+
+static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	struct workqueue_attrs *attrs;
+	int v, ret;
+
+	attrs = wq_sysfs_prep_attrs(wq);
+	if (!attrs)
+		return -ENOMEM;
+
+	ret = -EINVAL;
+	if (sscanf(buf, "%d", &v) == 1) {
+		attrs->no_numa = !v;
+		ret = apply_workqueue_attrs(wq, attrs);
+	}
+
+	free_workqueue_attrs(attrs);
+	return ret ?: count;
+}
+
+static struct device_attribute wq_sysfs_unbound_attrs[] = {
+	__ATTR(pool_ids, 0444, wq_pool_ids_show, NULL),
+	__ATTR(nice, 0644, wq_nice_show, wq_nice_store),
+	__ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store),
+	__ATTR(numa, 0644, wq_numa_show, wq_numa_store),
+	__ATTR_NULL,
+};
+
+static struct bus_type wq_subsys = {
+	.name				= "workqueue",
+	.dev_attrs			= wq_sysfs_attrs,
+};
+
+static int __init wq_sysfs_init(void)
 {
-	return system_wq != NULL;
+	return subsys_virtual_register(&wq_subsys, NULL);
 }
+core_initcall(wq_sysfs_init);
 
-static int alloc_pwqs(struct workqueue_struct *wq)
+static void wq_device_release(struct device *dev)
 {
+	struct wq_device *wq_dev = container_of(dev, struct wq_device, dev);
+
+	kfree(wq_dev);
+}
+
+/**
+ * workqueue_sysfs_register - make a workqueue visible in sysfs
+ * @wq: the workqueue to register
+ *
+ * Expose @wq in sysfs under /sys/bus/workqueue/devices.
+ * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set
+ * which is the preferred method.
+ *
+ * Workqueue user should use this function directly iff it wants to apply
+ * workqueue_attrs before making the workqueue visible in sysfs; otherwise,
+ * apply_workqueue_attrs() may race against userland updating the
+ * attributes.
+ *
+ * Returns 0 on success, -errno on failure.
+ */
+int workqueue_sysfs_register(struct workqueue_struct *wq)
+{
+	struct wq_device *wq_dev;
+	int ret;
+
 	/*
-	 * pwqs are forced aligned according to WORK_STRUCT_FLAG_BITS.
-	 * Make sure that the alignment isn't lower than that of
-	 * unsigned long long.
+	 * Adjusting max_active or creating new pwqs by applyting
+	 * attributes breaks ordering guarantee.  Disallow exposing ordered
+	 * workqueues.
 	 */
-	const size_t size = sizeof(struct pool_workqueue);
-	const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS,
-				   __alignof__(unsigned long long));
+	if (WARN_ON(wq->flags & __WQ_ORDERED))
+		return -EINVAL;
 
-	if (!(wq->flags & WQ_UNBOUND))
-		wq->pool_wq.pcpu = __alloc_percpu(size, align);
-	else {
-		void *ptr;
+	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
+	if (!wq_dev)
+		return -ENOMEM;
+
+	wq_dev->wq = wq;
+	wq_dev->dev.bus = &wq_subsys;
+	wq_dev->dev.init_name = wq->name;
+	wq_dev->dev.release = wq_device_release;
+
+	/*
+	 * unbound_attrs are created separately.  Suppress uevent until
+	 * everything is ready.
+	 */
+	dev_set_uevent_suppress(&wq_dev->dev, true);
+
+	ret = device_register(&wq_dev->dev);
+	if (ret) {
+		kfree(wq_dev);
+		wq->wq_dev = NULL;
+		return ret;
+	}
+
+	if (wq->flags & WQ_UNBOUND) {
+		struct device_attribute *attr;
+
+		for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) {
+			ret = device_create_file(&wq_dev->dev, attr);
+			if (ret) {
+				device_unregister(&wq_dev->dev);
+				wq->wq_dev = NULL;
+				return ret;
+			}
+		}
+	}
+
+	kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
+	return 0;
+}
+
+/**
+ * workqueue_sysfs_unregister - undo workqueue_sysfs_register()
+ * @wq: the workqueue to unregister
+ *
+ * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister.
+ */
+static void workqueue_sysfs_unregister(struct workqueue_struct *wq)
+{
+	struct wq_device *wq_dev = wq->wq_dev;
+
+	if (!wq->wq_dev)
+		return;
+
+	wq->wq_dev = NULL;
+	device_unregister(&wq_dev->dev);
+}
+#else	/* CONFIG_SYSFS */
+static void workqueue_sysfs_unregister(struct workqueue_struct *wq)	{ }
+#endif	/* CONFIG_SYSFS */
+
+/**
+ * free_workqueue_attrs - free a workqueue_attrs
+ * @attrs: workqueue_attrs to free
+ *
+ * Undo alloc_workqueue_attrs().
+ */
+void free_workqueue_attrs(struct workqueue_attrs *attrs)
+{
+	if (attrs) {
+		free_cpumask_var(attrs->cpumask);
+		kfree(attrs);
+	}
+}
+
+/**
+ * alloc_workqueue_attrs - allocate a workqueue_attrs
+ * @gfp_mask: allocation mask to use
+ *
+ * Allocate a new workqueue_attrs, initialize with default settings and
+ * return it.  Returns NULL on failure.
+ */
+struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask)
+{
+	struct workqueue_attrs *attrs;
+
+	attrs = kzalloc(sizeof(*attrs), gfp_mask);
+	if (!attrs)
+		goto fail;
+	if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask))
+		goto fail;
+
+	cpumask_copy(attrs->cpumask, cpu_possible_mask);
+	return attrs;
+fail:
+	free_workqueue_attrs(attrs);
+	return NULL;
+}
+
+static void copy_workqueue_attrs(struct workqueue_attrs *to,
+				 const struct workqueue_attrs *from)
+{
+	to->nice = from->nice;
+	cpumask_copy(to->cpumask, from->cpumask);
+}
+
+/* hash value of the content of @attr */
+static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
+{
+	u32 hash = 0;
+
+	hash = jhash_1word(attrs->nice, hash);
+	hash = jhash(cpumask_bits(attrs->cpumask),
+		     BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash);
+	return hash;
+}
+
+/* content equality test */
+static bool wqattrs_equal(const struct workqueue_attrs *a,
+			  const struct workqueue_attrs *b)
+{
+	if (a->nice != b->nice)
+		return false;
+	if (!cpumask_equal(a->cpumask, b->cpumask))
+		return false;
+	return true;
+}
+
+/**
+ * init_worker_pool - initialize a newly zalloc'd worker_pool
+ * @pool: worker_pool to initialize
+ *
+ * Initiailize a newly zalloc'd @pool.  It also allocates @pool->attrs.
+ * Returns 0 on success, -errno on failure.  Even on failure, all fields
+ * inside @pool proper are initialized and put_unbound_pool() can be called
+ * on @pool safely to release it.
+ */
+static int init_worker_pool(struct worker_pool *pool)
+{
+	spin_lock_init(&pool->lock);
+	pool->id = -1;
+	pool->cpu = -1;
+	pool->node = NUMA_NO_NODE;
+	pool->flags |= POOL_DISASSOCIATED;
+	INIT_LIST_HEAD(&pool->worklist);
+	INIT_LIST_HEAD(&pool->idle_list);
+	hash_init(pool->busy_hash);
+
+	init_timer_deferrable(&pool->idle_timer);
+	pool->idle_timer.function = idle_worker_timeout;
+	pool->idle_timer.data = (unsigned long)pool;
+
+	setup_timer(&pool->mayday_timer, pool_mayday_timeout,
+		    (unsigned long)pool);
+
+	mutex_init(&pool->manager_arb);
+	mutex_init(&pool->manager_mutex);
+	idr_init(&pool->worker_idr);
+
+	INIT_HLIST_NODE(&pool->hash_node);
+	pool->refcnt = 1;
+
+	/* shouldn't fail above this point */
+	pool->attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	if (!pool->attrs)
+		return -ENOMEM;
+	return 0;
+}
+
+static void rcu_free_pool(struct rcu_head *rcu)
+{
+	struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu);
+
+	idr_destroy(&pool->worker_idr);
+	free_workqueue_attrs(pool->attrs);
+	kfree(pool);
+}
+
+/**
+ * put_unbound_pool - put a worker_pool
+ * @pool: worker_pool to put
+ *
+ * Put @pool.  If its refcnt reaches zero, it gets destroyed in sched-RCU
+ * safe manner.  get_unbound_pool() calls this function on its failure path
+ * and this function should be able to release pools which went through,
+ * successfully or not, init_worker_pool().
+ *
+ * Should be called with wq_pool_mutex held.
+ */
+static void put_unbound_pool(struct worker_pool *pool)
+{
+	struct worker *worker;
+
+	lockdep_assert_held(&wq_pool_mutex);
+
+	if (--pool->refcnt)
+		return;
+
+	/* sanity checks */
+	if (WARN_ON(!(pool->flags & POOL_DISASSOCIATED)) ||
+	    WARN_ON(!list_empty(&pool->worklist)))
+		return;
+
+	/* release id and unhash */
+	if (pool->id >= 0)
+		idr_remove(&worker_pool_idr, pool->id);
+	hash_del(&pool->hash_node);
+
+	/*
+	 * Become the manager and destroy all workers.  Grabbing
+	 * manager_arb prevents @pool's workers from blocking on
+	 * manager_mutex.
+	 */
+	mutex_lock(&pool->manager_arb);
+	mutex_lock(&pool->manager_mutex);
+	spin_lock_irq(&pool->lock);
+
+	while ((worker = first_worker(pool)))
+		destroy_worker(worker);
+	WARN_ON(pool->nr_workers || pool->nr_idle);
+
+	spin_unlock_irq(&pool->lock);
+	mutex_unlock(&pool->manager_mutex);
+	mutex_unlock(&pool->manager_arb);
+
+	/* shut down the timers */
+	del_timer_sync(&pool->idle_timer);
+	del_timer_sync(&pool->mayday_timer);
+
+	/* sched-RCU protected to allow dereferences from get_work_pool() */
+	call_rcu_sched(&pool->rcu, rcu_free_pool);
+}
+
+/**
+ * get_unbound_pool - get a worker_pool with the specified attributes
+ * @attrs: the attributes of the worker_pool to get
+ *
+ * Obtain a worker_pool which has the same attributes as @attrs, bump the
+ * reference count and return it.  If there already is a matching
+ * worker_pool, it will be used; otherwise, this function attempts to
+ * create a new one.  On failure, returns NULL.
+ *
+ * Should be called with wq_pool_mutex held.
+ */
+static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
+{
+	u32 hash = wqattrs_hash(attrs);
+	struct worker_pool *pool;
+	int node;
+
+	lockdep_assert_held(&wq_pool_mutex);
+
+	/* do we already have a matching pool? */
+	hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) {
+		if (wqattrs_equal(pool->attrs, attrs)) {
+			pool->refcnt++;
+			goto out_unlock;
+		}
+	}
+
+	/* nope, create a new one */
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool || init_worker_pool(pool) < 0)
+		goto fail;
+
+	if (workqueue_freezing)
+		pool->flags |= POOL_FREEZING;
+
+	lockdep_set_subclass(&pool->lock, 1);	/* see put_pwq() */
+	copy_workqueue_attrs(pool->attrs, attrs);
+
+	/* if cpumask is contained inside a NUMA node, we belong to that node */
+	if (wq_numa_enabled) {
+		for_each_node(node) {
+			if (cpumask_subset(pool->attrs->cpumask,
+					   wq_numa_possible_cpumask[node])) {
+				pool->node = node;
+				break;
+			}
+		}
+	}
+
+	if (worker_pool_assign_id(pool) < 0)
+		goto fail;
+
+	/* create and start the initial worker */
+	if (create_and_start_worker(pool) < 0)
+		goto fail;
+
+	/* install */
+	hash_add(unbound_pool_hash, &pool->hash_node, hash);
+out_unlock:
+	return pool;
+fail:
+	if (pool)
+		put_unbound_pool(pool);
+	return NULL;
+}
+
+static void rcu_free_pwq(struct rcu_head *rcu)
+{
+	kmem_cache_free(pwq_cache,
+			container_of(rcu, struct pool_workqueue, rcu));
+}
+
+/*
+ * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt
+ * and needs to be destroyed.
+ */
+static void pwq_unbound_release_workfn(struct work_struct *work)
+{
+	struct pool_workqueue *pwq = container_of(work, struct pool_workqueue,
+						  unbound_release_work);
+	struct workqueue_struct *wq = pwq->wq;
+	struct worker_pool *pool = pwq->pool;
+	bool is_last;
+
+	if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
+		return;
+
+	/*
+	 * Unlink @pwq.  Synchronization against wq->mutex isn't strictly
+	 * necessary on release but do it anyway.  It's easier to verify
+	 * and consistent with the linking path.
+	 */
+	mutex_lock(&wq->mutex);
+	list_del_rcu(&pwq->pwqs_node);
+	is_last = list_empty(&wq->pwqs);
+	mutex_unlock(&wq->mutex);
+
+	mutex_lock(&wq_pool_mutex);
+	put_unbound_pool(pool);
+	mutex_unlock(&wq_pool_mutex);
+
+	call_rcu_sched(&pwq->rcu, rcu_free_pwq);
+
+	/*
+	 * If we're the last pwq going away, @wq is already dead and no one
+	 * is gonna access it anymore.  Free it.
+	 */
+	if (is_last) {
+		free_workqueue_attrs(wq->unbound_attrs);
+		kfree(wq);
+	}
+}
+
+/**
+ * pwq_adjust_max_active - update a pwq's max_active to the current setting
+ * @pwq: target pool_workqueue
+ *
+ * If @pwq isn't freezing, set @pwq->max_active to the associated
+ * workqueue's saved_max_active and activate delayed work items
+ * accordingly.  If @pwq is freezing, clear @pwq->max_active to zero.
+ */
+static void pwq_adjust_max_active(struct pool_workqueue *pwq)
+{
+	struct workqueue_struct *wq = pwq->wq;
+	bool freezable = wq->flags & WQ_FREEZABLE;
+
+	/* for @wq->saved_max_active */
+	lockdep_assert_held(&wq->mutex);
+
+	/* fast exit for non-freezable wqs */
+	if (!freezable && pwq->max_active == wq->saved_max_active)
+		return;
+
+	spin_lock_irq(&pwq->pool->lock);
+
+	if (!freezable || !(pwq->pool->flags & POOL_FREEZING)) {
+		pwq->max_active = wq->saved_max_active;
+
+		while (!list_empty(&pwq->delayed_works) &&
+		       pwq->nr_active < pwq->max_active)
+			pwq_activate_first_delayed(pwq);
 
 		/*
-		 * Allocate enough room to align pwq and put an extra
-		 * pointer at the end pointing back to the originally
-		 * allocated pointer which will be used for free.
+		 * Need to kick a worker after thawed or an unbound wq's
+		 * max_active is bumped.  It's a slow path.  Do it always.
 		 */
-		ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL);
-		if (ptr) {
-			wq->pool_wq.single = PTR_ALIGN(ptr, align);
-			*(void **)(wq->pool_wq.single + 1) = ptr;
+		wake_up_worker(pwq->pool);
+	} else {
+		pwq->max_active = 0;
+	}
+
+	spin_unlock_irq(&pwq->pool->lock);
+}
+
+/* initialize newly alloced @pwq which is associated with @wq and @pool */
+static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
+		     struct worker_pool *pool)
+{
+	BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
+
+	memset(pwq, 0, sizeof(*pwq));
+
+	pwq->pool = pool;
+	pwq->wq = wq;
+	pwq->flush_color = -1;
+	pwq->refcnt = 1;
+	INIT_LIST_HEAD(&pwq->delayed_works);
+	INIT_LIST_HEAD(&pwq->pwqs_node);
+	INIT_LIST_HEAD(&pwq->mayday_node);
+	INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn);
+}
+
+/* sync @pwq with the current state of its associated wq and link it */
+static void link_pwq(struct pool_workqueue *pwq)
+{
+	struct workqueue_struct *wq = pwq->wq;
+
+	lockdep_assert_held(&wq->mutex);
+
+	/* may be called multiple times, ignore if already linked */
+	if (!list_empty(&pwq->pwqs_node))
+		return;
+
+	/*
+	 * Set the matching work_color.  This is synchronized with
+	 * wq->mutex to avoid confusing flush_workqueue().
+	 */
+	pwq->work_color = wq->work_color;
+
+	/* sync max_active to the current setting */
+	pwq_adjust_max_active(pwq);
+
+	/* link in @pwq */
+	list_add_rcu(&pwq->pwqs_node, &wq->pwqs);
+}
+
+/* obtain a pool matching @attr and create a pwq associating the pool and @wq */
+static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq,
+					const struct workqueue_attrs *attrs)
+{
+	struct worker_pool *pool;
+	struct pool_workqueue *pwq;
+
+	lockdep_assert_held(&wq_pool_mutex);
+
+	pool = get_unbound_pool(attrs);
+	if (!pool)
+		return NULL;
+
+	pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node);
+	if (!pwq) {
+		put_unbound_pool(pool);
+		return NULL;
+	}
+
+	init_pwq(pwq, wq, pool);
+	return pwq;
+}
+
+/* undo alloc_unbound_pwq(), used only in the error path */
+static void free_unbound_pwq(struct pool_workqueue *pwq)
+{
+	lockdep_assert_held(&wq_pool_mutex);
+
+	if (pwq) {
+		put_unbound_pool(pwq->pool);
+		kmem_cache_free(pwq_cache, pwq);
+	}
+}
+
+/**
+ * wq_calc_node_mask - calculate a wq_attrs' cpumask for the specified node
+ * @attrs: the wq_attrs of interest
+ * @node: the target NUMA node
+ * @cpu_going_down: if >= 0, the CPU to consider as offline
+ * @cpumask: outarg, the resulting cpumask
+ *
+ * Calculate the cpumask a workqueue with @attrs should use on @node.  If
+ * @cpu_going_down is >= 0, that cpu is considered offline during
+ * calculation.  The result is stored in @cpumask.  This function returns
+ * %true if the resulting @cpumask is different from @attrs->cpumask,
+ * %false if equal.
+ *
+ * If NUMA affinity is not enabled, @attrs->cpumask is always used.  If
+ * enabled and @node has online CPUs requested by @attrs, the returned
+ * cpumask is the intersection of the possible CPUs of @node and
+ * @attrs->cpumask.
+ *
+ * The caller is responsible for ensuring that the cpumask of @node stays
+ * stable.
+ */
+static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
+				 int cpu_going_down, cpumask_t *cpumask)
+{
+	if (!wq_numa_enabled || attrs->no_numa)
+		goto use_dfl;
+
+	/* does @node have any online CPUs @attrs wants? */
+	cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask);
+	if (cpu_going_down >= 0)
+		cpumask_clear_cpu(cpu_going_down, cpumask);
+
+	if (cpumask_empty(cpumask))
+		goto use_dfl;
+
+	/* yeap, return possible CPUs in @node that @attrs wants */
+	cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]);
+	return !cpumask_equal(cpumask, attrs->cpumask);
+
+use_dfl:
+	cpumask_copy(cpumask, attrs->cpumask);
+	return false;
+}
+
+/* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */
+static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq,
+						   int node,
+						   struct pool_workqueue *pwq)
+{
+	struct pool_workqueue *old_pwq;
+
+	lockdep_assert_held(&wq->mutex);
+
+	/* link_pwq() can handle duplicate calls */
+	link_pwq(pwq);
+
+	old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]);
+	rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq);
+	return old_pwq;
+}
+
+/**
+ * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue
+ * @wq: the target workqueue
+ * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs()
+ *
+ * Apply @attrs to an unbound workqueue @wq.  Unless disabled, on NUMA
+ * machines, this function maps a separate pwq to each NUMA node with
+ * possibles CPUs in @attrs->cpumask so that work items are affine to the
+ * NUMA node it was issued on.  Older pwqs are released as in-flight work
+ * items finish.  Note that a work item which repeatedly requeues itself
+ * back-to-back will stay on its current pwq.
+ *
+ * Performs GFP_KERNEL allocations.  Returns 0 on success and -errno on
+ * failure.
+ */
+int apply_workqueue_attrs(struct workqueue_struct *wq,
+			  const struct workqueue_attrs *attrs)
+{
+	struct workqueue_attrs *new_attrs, *tmp_attrs;
+	struct pool_workqueue **pwq_tbl, *dfl_pwq;
+	int node, ret;
+
+	/* only unbound workqueues can change attributes */
+	if (WARN_ON(!(wq->flags & WQ_UNBOUND)))
+		return -EINVAL;
+
+	/* creating multiple pwqs breaks ordering guarantee */
+	if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
+		return -EINVAL;
+
+	pwq_tbl = kzalloc(wq_numa_tbl_len * sizeof(pwq_tbl[0]), GFP_KERNEL);
+	new_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	if (!pwq_tbl || !new_attrs || !tmp_attrs)
+		goto enomem;
+
+	/* make a copy of @attrs and sanitize it */
+	copy_workqueue_attrs(new_attrs, attrs);
+	cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask);
+
+	/*
+	 * We may create multiple pwqs with differing cpumasks.  Make a
+	 * copy of @new_attrs which will be modified and used to obtain
+	 * pools.
+	 */
+	copy_workqueue_attrs(tmp_attrs, new_attrs);
+
+	/*
+	 * CPUs should stay stable across pwq creations and installations.
+	 * Pin CPUs, determine the target cpumask for each node and create
+	 * pwqs accordingly.
+	 */
+	get_online_cpus();
+
+	mutex_lock(&wq_pool_mutex);
+
+	/*
+	 * If something goes wrong during CPU up/down, we'll fall back to
+	 * the default pwq covering whole @attrs->cpumask.  Always create
+	 * it even if we don't use it immediately.
+	 */
+	dfl_pwq = alloc_unbound_pwq(wq, new_attrs);
+	if (!dfl_pwq)
+		goto enomem_pwq;
+
+	for_each_node(node) {
+		if (wq_calc_node_cpumask(attrs, node, -1, tmp_attrs->cpumask)) {
+			pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs);
+			if (!pwq_tbl[node])
+				goto enomem_pwq;
+		} else {
+			dfl_pwq->refcnt++;
+			pwq_tbl[node] = dfl_pwq;
 		}
 	}
 
-	/* just in case, make sure it's actually aligned */
-	BUG_ON(!IS_ALIGNED(wq->pool_wq.v, align));
-	return wq->pool_wq.v ? 0 : -ENOMEM;
+	mutex_unlock(&wq_pool_mutex);
+
+	/* all pwqs have been created successfully, let's install'em */
+	mutex_lock(&wq->mutex);
+
+	copy_workqueue_attrs(wq->unbound_attrs, new_attrs);
+
+	/* save the previous pwq and install the new one */
+	for_each_node(node)
+		pwq_tbl[node] = numa_pwq_tbl_install(wq, node, pwq_tbl[node]);
+
+	/* @dfl_pwq might not have been used, ensure it's linked */
+	link_pwq(dfl_pwq);
+	swap(wq->dfl_pwq, dfl_pwq);
+
+	mutex_unlock(&wq->mutex);
+
+	/* put the old pwqs */
+	for_each_node(node)
+		put_pwq_unlocked(pwq_tbl[node]);
+	put_pwq_unlocked(dfl_pwq);
+
+	put_online_cpus();
+	ret = 0;
+	/* fall through */
+out_free:
+	free_workqueue_attrs(tmp_attrs);
+	free_workqueue_attrs(new_attrs);
+	kfree(pwq_tbl);
+	return ret;
+
+enomem_pwq:
+	free_unbound_pwq(dfl_pwq);
+	for_each_node(node)
+		if (pwq_tbl && pwq_tbl[node] != dfl_pwq)
+			free_unbound_pwq(pwq_tbl[node]);
+	mutex_unlock(&wq_pool_mutex);
+	put_online_cpus();
+enomem:
+	ret = -ENOMEM;
+	goto out_free;
 }
 
-static void free_pwqs(struct workqueue_struct *wq)
+/**
+ * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug
+ * @wq: the target workqueue
+ * @cpu: the CPU coming up or going down
+ * @online: whether @cpu is coming up or going down
+ *
+ * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and
+ * %CPU_DOWN_FAILED.  @cpu is being hot[un]plugged, update NUMA affinity of
+ * @wq accordingly.
+ *
+ * If NUMA affinity can't be adjusted due to memory allocation failure, it
+ * falls back to @wq->dfl_pwq which may not be optimal but is always
+ * correct.
+ *
+ * Note that when the last allowed CPU of a NUMA node goes offline for a
+ * workqueue with a cpumask spanning multiple nodes, the workers which were
+ * already executing the work items for the workqueue will lose their CPU
+ * affinity and may execute on any CPU.  This is similar to how per-cpu
+ * workqueues behave on CPU_DOWN.  If a workqueue user wants strict
+ * affinity, it's the user's responsibility to flush the work item from
+ * CPU_DOWN_PREPARE.
+ */
+static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
+				   bool online)
 {
-	if (!(wq->flags & WQ_UNBOUND))
-		free_percpu(wq->pool_wq.pcpu);
-	else if (wq->pool_wq.single) {
-		/* the pointer to free is stored right after the pwq */
-		kfree(*(void **)(wq->pool_wq.single + 1));
+	int node = cpu_to_node(cpu);
+	int cpu_off = online ? -1 : cpu;
+	struct pool_workqueue *old_pwq = NULL, *pwq;
+	struct workqueue_attrs *target_attrs;
+	cpumask_t *cpumask;
+
+	lockdep_assert_held(&wq_pool_mutex);
+
+	if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND))
+		return;
+
+	/*
+	 * We don't wanna alloc/free wq_attrs for each wq for each CPU.
+	 * Let's use a preallocated one.  The following buf is protected by
+	 * CPU hotplug exclusion.
+	 */
+	target_attrs = wq_update_unbound_numa_attrs_buf;
+	cpumask = target_attrs->cpumask;
+
+	mutex_lock(&wq->mutex);
+	if (wq->unbound_attrs->no_numa)
+		goto out_unlock;
+
+	copy_workqueue_attrs(target_attrs, wq->unbound_attrs);
+	pwq = unbound_pwq_by_node(wq, node);
+
+	/*
+	 * Let's determine what needs to be done.  If the target cpumask is
+	 * different from wq's, we need to compare it to @pwq's and create
+	 * a new one if they don't match.  If the target cpumask equals
+	 * wq's, the default pwq should be used.  If @pwq is already the
+	 * default one, nothing to do; otherwise, install the default one.
+	 */
+	if (wq_calc_node_cpumask(wq->unbound_attrs, node, cpu_off, cpumask)) {
+		if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask))
+			goto out_unlock;
+	} else {
+		if (pwq == wq->dfl_pwq)
+			goto out_unlock;
+		else
+			goto use_dfl_pwq;
+	}
+
+	mutex_unlock(&wq->mutex);
+
+	/* create a new pwq */
+	pwq = alloc_unbound_pwq(wq, target_attrs);
+	if (!pwq) {
+		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
+			   wq->name);
+		goto out_unlock;
+	}
+
+	/*
+	 * Install the new pwq.  As this function is called only from CPU
+	 * hotplug callbacks and applying a new attrs is wrapped with
+	 * get/put_online_cpus(), @wq->unbound_attrs couldn't have changed
+	 * inbetween.
+	 */
+	mutex_lock(&wq->mutex);
+	old_pwq = numa_pwq_tbl_install(wq, node, pwq);
+	goto out_unlock;
+
+use_dfl_pwq:
+	spin_lock_irq(&wq->dfl_pwq->pool->lock);
+	get_pwq(wq->dfl_pwq);
+	spin_unlock_irq(&wq->dfl_pwq->pool->lock);
+	old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq);
+out_unlock:
+	mutex_unlock(&wq->mutex);
+	put_pwq_unlocked(old_pwq);
+}
+
+static int alloc_and_link_pwqs(struct workqueue_struct *wq)
+{
+	bool highpri = wq->flags & WQ_HIGHPRI;
+	int cpu;
+
+	if (!(wq->flags & WQ_UNBOUND)) {
+		wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
+		if (!wq->cpu_pwqs)
+			return -ENOMEM;
+
+		for_each_possible_cpu(cpu) {
+			struct pool_workqueue *pwq =
+				per_cpu_ptr(wq->cpu_pwqs, cpu);
+			struct worker_pool *cpu_pools =
+				per_cpu(cpu_worker_pools, cpu);
+
+			init_pwq(pwq, wq, &cpu_pools[highpri]);
+
+			mutex_lock(&wq->mutex);
+			link_pwq(pwq);
+			mutex_unlock(&wq->mutex);
+		}
+		return 0;
+	} else {
+		return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
 	}
 }
 
@@ -3150,30 +4078,28 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 					       struct lock_class_key *key,
 					       const char *lock_name, ...)
 {
-	va_list args, args1;
+	size_t tbl_size = 0;
+	va_list args;
 	struct workqueue_struct *wq;
-	unsigned int cpu;
-	size_t namelen;
+	struct pool_workqueue *pwq;
 
-	/* determine namelen, allocate wq and format name */
-	va_start(args, lock_name);
-	va_copy(args1, args);
-	namelen = vsnprintf(NULL, 0, fmt, args) + 1;
+	/* allocate wq and format name */
+	if (flags & WQ_UNBOUND)
+		tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]);
 
-	wq = kzalloc(sizeof(*wq) + namelen, GFP_KERNEL);
+	wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL);
 	if (!wq)
-		goto err;
+		return NULL;
 
-	vsnprintf(wq->name, namelen, fmt, args1);
-	va_end(args);
-	va_end(args1);
+	if (flags & WQ_UNBOUND) {
+		wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+		if (!wq->unbound_attrs)
+			goto err_free_wq;
+	}
 
-	/*
-	 * Workqueues which may be used during memory reclaim should
-	 * have a rescuer to guarantee forward progress.
-	 */
-	if (flags & WQ_MEM_RECLAIM)
-		flags |= WQ_RESCUER;
+	va_start(args, lock_name);
+	vsnprintf(wq->name, sizeof(wq->name), fmt, args);
+	va_end(args);
 
 	max_active = max_active ?: WQ_DFL_ACTIVE;
 	max_active = wq_clamp_max_active(max_active, flags, wq->name);
@@ -3181,71 +4107,70 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	/* init wq */
 	wq->flags = flags;
 	wq->saved_max_active = max_active;
-	mutex_init(&wq->flush_mutex);
+	mutex_init(&wq->mutex);
 	atomic_set(&wq->nr_pwqs_to_flush, 0);
+	INIT_LIST_HEAD(&wq->pwqs);
 	INIT_LIST_HEAD(&wq->flusher_queue);
 	INIT_LIST_HEAD(&wq->flusher_overflow);
+	INIT_LIST_HEAD(&wq->maydays);
 
 	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
 	INIT_LIST_HEAD(&wq->list);
 
-	if (alloc_pwqs(wq) < 0)
-		goto err;
-
-	for_each_pwq_cpu(cpu, wq) {
-		struct pool_workqueue *pwq = get_pwq(cpu, wq);
+	if (alloc_and_link_pwqs(wq) < 0)
+		goto err_free_wq;
 
-		BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
-		pwq->pool = get_std_worker_pool(cpu, flags & WQ_HIGHPRI);
-		pwq->wq = wq;
-		pwq->flush_color = -1;
-		pwq->max_active = max_active;
-		INIT_LIST_HEAD(&pwq->delayed_works);
-	}
-
-	if (flags & WQ_RESCUER) {
+	/*
+	 * Workqueues which may be used during memory reclaim should
+	 * have a rescuer to guarantee forward progress.
+	 */
+	if (flags & WQ_MEM_RECLAIM) {
 		struct worker *rescuer;
 
-		if (!alloc_mayday_mask(&wq->mayday_mask, GFP_KERNEL))
-			goto err;
-
-		wq->rescuer = rescuer = alloc_worker();
+		rescuer = alloc_worker();
 		if (!rescuer)
-			goto err;
+			goto err_destroy;
 
 		rescuer->rescue_wq = wq;
 		rescuer->task = kthread_create(rescuer_thread, rescuer, "%s",
 					       wq->name);
-		if (IS_ERR(rescuer->task))
-			goto err;
+		if (IS_ERR(rescuer->task)) {
+			kfree(rescuer);
+			goto err_destroy;
+		}
 
-		rescuer->task->flags |= PF_THREAD_BOUND;
+		wq->rescuer = rescuer;
+		rescuer->task->flags |= PF_NO_SETAFFINITY;
 		wake_up_process(rescuer->task);
 	}
 
+	if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq))
+		goto err_destroy;
+
 	/*
-	 * workqueue_lock protects global freeze state and workqueues
-	 * list.  Grab it, set max_active accordingly and add the new
-	 * workqueue to workqueues list.
+	 * wq_pool_mutex protects global freeze state and workqueues list.
+	 * Grab it, adjust max_active and add the new @wq to workqueues
+	 * list.
 	 */
-	spin_lock(&workqueue_lock);
+	mutex_lock(&wq_pool_mutex);
 
-	if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
-		for_each_pwq_cpu(cpu, wq)
-			get_pwq(cpu, wq)->max_active = 0;
+	mutex_lock(&wq->mutex);
+	for_each_pwq(pwq, wq)
+		pwq_adjust_max_active(pwq);
+	mutex_unlock(&wq->mutex);
 
 	list_add(&wq->list, &workqueues);
 
-	spin_unlock(&workqueue_lock);
+	mutex_unlock(&wq_pool_mutex);
 
 	return wq;
-err:
-	if (wq) {
-		free_pwqs(wq);
-		free_mayday_mask(wq->mayday_mask);
-		kfree(wq->rescuer);
-		kfree(wq);
-	}
+
+err_free_wq:
+	free_workqueue_attrs(wq->unbound_attrs);
+	kfree(wq);
+	return NULL;
+err_destroy:
+	destroy_workqueue(wq);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(__alloc_workqueue_key);
@@ -3258,60 +4183,78 @@ EXPORT_SYMBOL_GPL(__alloc_workqueue_key);
  */
 void destroy_workqueue(struct workqueue_struct *wq)
 {
-	unsigned int cpu;
+	struct pool_workqueue *pwq;
+	int node;
 
 	/* drain it before proceeding with destruction */
 	drain_workqueue(wq);
 
+	/* sanity checks */
+	mutex_lock(&wq->mutex);
+	for_each_pwq(pwq, wq) {
+		int i;
+
+		for (i = 0; i < WORK_NR_COLORS; i++) {
+			if (WARN_ON(pwq->nr_in_flight[i])) {
+				mutex_unlock(&wq->mutex);
+				return;
+			}
+		}
+
+		if (WARN_ON((pwq != wq->dfl_pwq) && (pwq->refcnt > 1)) ||
+		    WARN_ON(pwq->nr_active) ||
+		    WARN_ON(!list_empty(&pwq->delayed_works))) {
+			mutex_unlock(&wq->mutex);
+			return;
+		}
+	}
+	mutex_unlock(&wq->mutex);
+
 	/*
 	 * wq list is used to freeze wq, remove from list after
 	 * flushing is complete in case freeze races us.
 	 */
-	spin_lock(&workqueue_lock);
-	list_del(&wq->list);
-	spin_unlock(&workqueue_lock);
+	mutex_lock(&wq_pool_mutex);
+	list_del_init(&wq->list);
+	mutex_unlock(&wq_pool_mutex);
 
-	/* sanity check */
-	for_each_pwq_cpu(cpu, wq) {
-		struct pool_workqueue *pwq = get_pwq(cpu, wq);
-		int i;
+	workqueue_sysfs_unregister(wq);
 
-		for (i = 0; i < WORK_NR_COLORS; i++)
-			BUG_ON(pwq->nr_in_flight[i]);
-		BUG_ON(pwq->nr_active);
-		BUG_ON(!list_empty(&pwq->delayed_works));
-	}
-
-	if (wq->flags & WQ_RESCUER) {
+	if (wq->rescuer) {
 		kthread_stop(wq->rescuer->task);
-		free_mayday_mask(wq->mayday_mask);
 		kfree(wq->rescuer);
+		wq->rescuer = NULL;
 	}
 
-	free_pwqs(wq);
-	kfree(wq);
-}
-EXPORT_SYMBOL_GPL(destroy_workqueue);
-
-/**
- * pwq_set_max_active - adjust max_active of a pwq
- * @pwq: target pool_workqueue
- * @max_active: new max_active value.
- *
- * Set @pwq->max_active to @max_active and activate delayed works if
- * increased.
- *
- * CONTEXT:
- * spin_lock_irq(pool->lock).
- */
-static void pwq_set_max_active(struct pool_workqueue *pwq, int max_active)
-{
-	pwq->max_active = max_active;
+	if (!(wq->flags & WQ_UNBOUND)) {
+		/*
+		 * The base ref is never dropped on per-cpu pwqs.  Directly
+		 * free the pwqs and wq.
+		 */
+		free_percpu(wq->cpu_pwqs);
+		kfree(wq);
+	} else {
+		/*
+		 * We're the sole accessor of @wq at this point.  Directly
+		 * access numa_pwq_tbl[] and dfl_pwq to put the base refs.
+		 * @wq will be freed when the last pwq is released.
+		 */
+		for_each_node(node) {
+			pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]);
+			RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL);
+			put_pwq_unlocked(pwq);
+		}
 
-	while (!list_empty(&pwq->delayed_works) &&
-	       pwq->nr_active < pwq->max_active)
-		pwq_activate_first_delayed(pwq);
+		/*
+		 * Put dfl_pwq.  @wq may be freed any time after dfl_pwq is
+		 * put.  Don't access it afterwards.
+		 */
+		pwq = wq->dfl_pwq;
+		wq->dfl_pwq = NULL;
+		put_pwq_unlocked(pwq);
+	}
 }
+EXPORT_SYMBOL_GPL(destroy_workqueue);
 
 /**
  * workqueue_set_max_active - adjust max_active of a workqueue
@@ -3325,30 +4268,37 @@ static void pwq_set_max_active(struct pool_workqueue *pwq, int max_active)
  */
 void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 {
-	unsigned int cpu;
+	struct pool_workqueue *pwq;
+
+	/* disallow meddling with max_active for ordered workqueues */
+	if (WARN_ON(wq->flags & __WQ_ORDERED))
+		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
-	spin_lock(&workqueue_lock);
+	mutex_lock(&wq->mutex);
 
 	wq->saved_max_active = max_active;
 
-	for_each_pwq_cpu(cpu, wq) {
-		struct pool_workqueue *pwq = get_pwq(cpu, wq);
-		struct worker_pool *pool = pwq->pool;
-
-		spin_lock_irq(&pool->lock);
+	for_each_pwq(pwq, wq)
+		pwq_adjust_max_active(pwq);
 
-		if (!(wq->flags & WQ_FREEZABLE) ||
-		    !(pool->flags & POOL_FREEZING))
-			pwq_set_max_active(pwq, max_active);
+	mutex_unlock(&wq->mutex);
+}
+EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
-		spin_unlock_irq(&pool->lock);
-	}
+/**
+ * current_is_workqueue_rescuer - is %current workqueue rescuer?
+ *
+ * Determine whether %current is a workqueue rescuer.  Can be used from
+ * work functions to determine whether it's being run off the rescuer task.
+ */
+bool current_is_workqueue_rescuer(void)
+{
+	struct worker *worker = current_wq_worker();
 
-	spin_unlock(&workqueue_lock);
+	return worker && worker->rescue_wq;
 }
-EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
 /**
  * workqueue_congested - test whether a workqueue is congested
@@ -3362,11 +4312,22 @@ EXPORT_SYMBOL_GPL(workqueue_set_max_active);
  * RETURNS:
  * %true if congested, %false otherwise.
  */
-bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq)
+bool workqueue_congested(int cpu, struct workqueue_struct *wq)
 {
-	struct pool_workqueue *pwq = get_pwq(cpu, wq);
+	struct pool_workqueue *pwq;
+	bool ret;
+
+	rcu_read_lock_sched();
+
+	if (!(wq->flags & WQ_UNBOUND))
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	else
+		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
+
+	ret = !list_empty(&pwq->delayed_works);
+	rcu_read_unlock_sched();
 
-	return !list_empty(&pwq->delayed_works);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(workqueue_congested);
 
@@ -3383,19 +4344,22 @@ EXPORT_SYMBOL_GPL(workqueue_congested);
  */
 unsigned int work_busy(struct work_struct *work)
 {
-	struct worker_pool *pool = get_work_pool(work);
+	struct worker_pool *pool;
 	unsigned long flags;
 	unsigned int ret = 0;
 
 	if (work_pending(work))
 		ret |= WORK_BUSY_PENDING;
 
+	local_irq_save(flags);
+	pool = get_work_pool(work);
 	if (pool) {
-		spin_lock_irqsave(&pool->lock, flags);
+		spin_lock(&pool->lock);
 		if (find_worker_executing_work(pool, work))
 			ret |= WORK_BUSY_RUNNING;
-		spin_unlock_irqrestore(&pool->lock, flags);
+		spin_unlock(&pool->lock);
 	}
+	local_irq_restore(flags);
 
 	return ret;
 }
@@ -3421,53 +4385,153 @@ static void wq_unbind_fn(struct work_struct *work)
 	int cpu = smp_processor_id();
 	struct worker_pool *pool;
 	struct worker *worker;
-	int i;
+	int wi;
 
-	for_each_std_worker_pool(pool, cpu) {
-		BUG_ON(cpu != smp_processor_id());
+	for_each_cpu_worker_pool(pool, cpu) {
+		WARN_ON_ONCE(cpu != smp_processor_id());
 
-		mutex_lock(&pool->assoc_mutex);
+		mutex_lock(&pool->manager_mutex);
 		spin_lock_irq(&pool->lock);
 
 		/*
-		 * We've claimed all manager positions.  Make all workers
+		 * We've blocked all manager operations.  Make all workers
 		 * unbound and set DISASSOCIATED.  Before this, all workers
 		 * except for the ones which are still executing works from
 		 * before the last CPU down must be on the cpu.  After
 		 * this, they may become diasporas.
 		 */
-		list_for_each_entry(worker, &pool->idle_list, entry)
-			worker->flags |= WORKER_UNBOUND;
-
-		for_each_busy_worker(worker, i, pool)
+		for_each_pool_worker(worker, wi, pool)
 			worker->flags |= WORKER_UNBOUND;
 
 		pool->flags |= POOL_DISASSOCIATED;
 
 		spin_unlock_irq(&pool->lock);
-		mutex_unlock(&pool->assoc_mutex);
+		mutex_unlock(&pool->manager_mutex);
+
+		/*
+		 * Call schedule() so that we cross rq->lock and thus can
+		 * guarantee sched callbacks see the %WORKER_UNBOUND flag.
+		 * This is necessary as scheduler callbacks may be invoked
+		 * from other cpus.
+		 */
+		schedule();
+
+		/*
+		 * Sched callbacks are disabled now.  Zap nr_running.
+		 * After this, nr_running stays zero and need_more_worker()
+		 * and keep_working() are always true as long as the
+		 * worklist is not empty.  This pool now behaves as an
+		 * unbound (in terms of concurrency management) pool which
+		 * are served by workers tied to the pool.
+		 */
+		atomic_set(&pool->nr_running, 0);
+
+		/*
+		 * With concurrency management just turned off, a busy
+		 * worker blocking could lead to lengthy stalls.  Kick off
+		 * unbound chain execution of currently pending work items.
+		 */
+		spin_lock_irq(&pool->lock);
+		wake_up_worker(pool);
+		spin_unlock_irq(&pool->lock);
 	}
+}
 
-	/*
-	 * Call schedule() so that we cross rq->lock and thus can guarantee
-	 * sched callbacks see the %WORKER_UNBOUND flag.  This is necessary
-	 * as scheduler callbacks may be invoked from other cpus.
-	 */
-	schedule();
+/**
+ * rebind_workers - rebind all workers of a pool to the associated CPU
+ * @pool: pool of interest
+ *
+ * @pool->cpu is coming online.  Rebind all workers to the CPU.
+ */
+static void rebind_workers(struct worker_pool *pool)
+{
+	struct worker *worker;
+	int wi;
+
+	lockdep_assert_held(&pool->manager_mutex);
 
 	/*
-	 * Sched callbacks are disabled now.  Zap nr_running.  After this,
-	 * nr_running stays zero and need_more_worker() and keep_working()
-	 * are always true as long as the worklist is not empty.  Pools on
-	 * @cpu now behave as unbound (in terms of concurrency management)
-	 * pools which are served by workers tied to the CPU.
-	 *
-	 * On return from this function, the current worker would trigger
-	 * unbound chain execution of pending work items if other workers
-	 * didn't already.
+	 * Restore CPU affinity of all workers.  As all idle workers should
+	 * be on the run-queue of the associated CPU before any local
+	 * wake-ups for concurrency management happen, restore CPU affinty
+	 * of all workers first and then clear UNBOUND.  As we're called
+	 * from CPU_ONLINE, the following shouldn't fail.
 	 */
-	for_each_std_worker_pool(pool, cpu)
-		atomic_set(&pool->nr_running, 0);
+	for_each_pool_worker(worker, wi, pool)
+		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
+						  pool->attrs->cpumask) < 0);
+
+	spin_lock_irq(&pool->lock);
+
+	for_each_pool_worker(worker, wi, pool) {
+		unsigned int worker_flags = worker->flags;
+
+		/*
+		 * A bound idle worker should actually be on the runqueue
+		 * of the associated CPU for local wake-ups targeting it to
+		 * work.  Kick all idle workers so that they migrate to the
+		 * associated CPU.  Doing this in the same loop as
+		 * replacing UNBOUND with REBOUND is safe as no worker will
+		 * be bound before @pool->lock is released.
+		 */
+		if (worker_flags & WORKER_IDLE)
+			wake_up_process(worker->task);
+
+		/*
+		 * We want to clear UNBOUND but can't directly call
+		 * worker_clr_flags() or adjust nr_running.  Atomically
+		 * replace UNBOUND with another NOT_RUNNING flag REBOUND.
+		 * @worker will clear REBOUND using worker_clr_flags() when
+		 * it initiates the next execution cycle thus restoring
+		 * concurrency management.  Note that when or whether
+		 * @worker clears REBOUND doesn't affect correctness.
+		 *
+		 * ACCESS_ONCE() is necessary because @worker->flags may be
+		 * tested without holding any lock in
+		 * wq_worker_waking_up().  Without it, NOT_RUNNING test may
+		 * fail incorrectly leading to premature concurrency
+		 * management operations.
+		 */
+		WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND));
+		worker_flags |= WORKER_REBOUND;
+		worker_flags &= ~WORKER_UNBOUND;
+		ACCESS_ONCE(worker->flags) = worker_flags;
+	}
+
+	spin_unlock_irq(&pool->lock);
+}
+
+/**
+ * restore_unbound_workers_cpumask - restore cpumask of unbound workers
+ * @pool: unbound pool of interest
+ * @cpu: the CPU which is coming up
+ *
+ * An unbound pool may end up with a cpumask which doesn't have any online
+ * CPUs.  When a worker of such pool get scheduled, the scheduler resets
+ * its cpus_allowed.  If @cpu is in @pool's cpumask which didn't have any
+ * online CPU before, cpus_allowed of all its workers should be restored.
+ */
+static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
+{
+	static cpumask_t cpumask;
+	struct worker *worker;
+	int wi;
+
+	lockdep_assert_held(&pool->manager_mutex);
+
+	/* is @cpu allowed for @pool? */
+	if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
+		return;
+
+	/* is @cpu the only online CPU? */
+	cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask);
+	if (cpumask_weight(&cpumask) != 1)
+		return;
+
+	/* as we're called from CPU_ONLINE, the following shouldn't fail */
+	for_each_pool_worker(worker, wi, pool)
+		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
+						  pool->attrs->cpumask) < 0);
 }
 
 /*
@@ -3478,39 +4542,46 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb,
 					       unsigned long action,
 					       void *hcpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
+	int cpu = (unsigned long)hcpu;
 	struct worker_pool *pool;
+	struct workqueue_struct *wq;
+	int pi;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-		for_each_std_worker_pool(pool, cpu) {
-			struct worker *worker;
-
+		for_each_cpu_worker_pool(pool, cpu) {
 			if (pool->nr_workers)
 				continue;
-
-			worker = create_worker(pool);
-			if (!worker)
+			if (create_and_start_worker(pool) < 0)
 				return NOTIFY_BAD;
-
-			spin_lock_irq(&pool->lock);
-			start_worker(worker);
-			spin_unlock_irq(&pool->lock);
 		}
 		break;
 
 	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
-		for_each_std_worker_pool(pool, cpu) {
-			mutex_lock(&pool->assoc_mutex);
-			spin_lock_irq(&pool->lock);
+		mutex_lock(&wq_pool_mutex);
 
-			pool->flags &= ~POOL_DISASSOCIATED;
-			rebind_workers(pool);
+		for_each_pool(pool, pi) {
+			mutex_lock(&pool->manager_mutex);
+
+			if (pool->cpu == cpu) {
+				spin_lock_irq(&pool->lock);
+				pool->flags &= ~POOL_DISASSOCIATED;
+				spin_unlock_irq(&pool->lock);
+
+				rebind_workers(pool);
+			} else if (pool->cpu < 0) {
+				restore_unbound_workers_cpumask(pool, cpu);
+			}
 
-			spin_unlock_irq(&pool->lock);
-			mutex_unlock(&pool->assoc_mutex);
+			mutex_unlock(&pool->manager_mutex);
 		}
+
+		/* update NUMA affinity of unbound workqueues */
+		list_for_each_entry(wq, &workqueues, list)
+			wq_update_unbound_numa(wq, cpu, true);
+
+		mutex_unlock(&wq_pool_mutex);
 		break;
 	}
 	return NOTIFY_OK;
@@ -3524,14 +4595,23 @@ static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb,
 						 unsigned long action,
 						 void *hcpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
+	int cpu = (unsigned long)hcpu;
 	struct work_struct unbind_work;
+	struct workqueue_struct *wq;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
-		/* unbinding should happen on the local CPU */
+		/* unbinding per-cpu workers should happen on the local CPU */
 		INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn);
 		queue_work_on(cpu, system_highpri_wq, &unbind_work);
+
+		/* update NUMA affinity of unbound workqueues */
+		mutex_lock(&wq_pool_mutex);
+		list_for_each_entry(wq, &workqueues, list)
+			wq_update_unbound_numa(wq, cpu, false);
+		mutex_unlock(&wq_pool_mutex);
+
+		/* wait for per-cpu unbinding to finish */
 		flush_work(&unbind_work);
 		break;
 	}
@@ -3564,7 +4644,7 @@ static void work_for_cpu_fn(struct work_struct *work)
  * It is up to the caller to ensure that the cpu doesn't go offline.
  * The caller must not hold any locks which would prevent @fn from completing.
  */
-long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 {
 	struct work_for_cpu wfc = { .fn = fn, .arg = arg };
 
@@ -3582,44 +4662,40 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
  * freeze_workqueues_begin - begin freezing workqueues
  *
  * Start freezing workqueues.  After this function returns, all freezable
- * workqueues will queue new works to their frozen_works list instead of
+ * workqueues will queue new works to their delayed_works list instead of
  * pool->worklist.
  *
  * CONTEXT:
- * Grabs and releases workqueue_lock and pool->lock's.
+ * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's.
  */
 void freeze_workqueues_begin(void)
 {
-	unsigned int cpu;
+	struct worker_pool *pool;
+	struct workqueue_struct *wq;
+	struct pool_workqueue *pwq;
+	int pi;
 
-	spin_lock(&workqueue_lock);
+	mutex_lock(&wq_pool_mutex);
 
-	BUG_ON(workqueue_freezing);
+	WARN_ON_ONCE(workqueue_freezing);
 	workqueue_freezing = true;
 
-	for_each_wq_cpu(cpu) {
-		struct worker_pool *pool;
-		struct workqueue_struct *wq;
-
-		for_each_std_worker_pool(pool, cpu) {
-			spin_lock_irq(&pool->lock);
-
-			WARN_ON_ONCE(pool->flags & POOL_FREEZING);
-			pool->flags |= POOL_FREEZING;
-
-			list_for_each_entry(wq, &workqueues, list) {
-				struct pool_workqueue *pwq = get_pwq(cpu, wq);
-
-				if (pwq && pwq->pool == pool &&
-				    (wq->flags & WQ_FREEZABLE))
-					pwq->max_active = 0;
-			}
+	/* set FREEZING */
+	for_each_pool(pool, pi) {
+		spin_lock_irq(&pool->lock);
+		WARN_ON_ONCE(pool->flags & POOL_FREEZING);
+		pool->flags |= POOL_FREEZING;
+		spin_unlock_irq(&pool->lock);
+	}
 
-			spin_unlock_irq(&pool->lock);
-		}
+	list_for_each_entry(wq, &workqueues, list) {
+		mutex_lock(&wq->mutex);
+		for_each_pwq(pwq, wq)
+			pwq_adjust_max_active(pwq);
+		mutex_unlock(&wq->mutex);
 	}
 
-	spin_unlock(&workqueue_lock);
+	mutex_unlock(&wq_pool_mutex);
 }
 
 /**
@@ -3629,7 +4705,7 @@ void freeze_workqueues_begin(void)
  * between freeze_workqueues_begin() and thaw_workqueues().
  *
  * CONTEXT:
- * Grabs and releases workqueue_lock.
+ * Grabs and releases wq_pool_mutex.
  *
  * RETURNS:
  * %true if some freezable workqueues are still busy.  %false if freezing
@@ -3637,34 +4713,34 @@ void freeze_workqueues_begin(void)
  */
 bool freeze_workqueues_busy(void)
 {
-	unsigned int cpu;
 	bool busy = false;
+	struct workqueue_struct *wq;
+	struct pool_workqueue *pwq;
 
-	spin_lock(&workqueue_lock);
+	mutex_lock(&wq_pool_mutex);
 
-	BUG_ON(!workqueue_freezing);
+	WARN_ON_ONCE(!workqueue_freezing);
 
-	for_each_wq_cpu(cpu) {
-		struct workqueue_struct *wq;
+	list_for_each_entry(wq, &workqueues, list) {
+		if (!(wq->flags & WQ_FREEZABLE))
+			continue;
 		/*
 		 * nr_active is monotonically decreasing.  It's safe
 		 * to peek without lock.
 		 */
-		list_for_each_entry(wq, &workqueues, list) {
-			struct pool_workqueue *pwq = get_pwq(cpu, wq);
-
-			if (!pwq || !(wq->flags & WQ_FREEZABLE))
-				continue;
-
-			BUG_ON(pwq->nr_active < 0);
+		rcu_read_lock_sched();
+		for_each_pwq(pwq, wq) {
+			WARN_ON_ONCE(pwq->nr_active < 0);
 			if (pwq->nr_active) {
 				busy = true;
+				rcu_read_unlock_sched();
 				goto out_unlock;
 			}
 		}
+		rcu_read_unlock_sched();
 	}
 out_unlock:
-	spin_unlock(&workqueue_lock);
+	mutex_unlock(&wq_pool_mutex);
 	return busy;
 }
 
@@ -3675,104 +4751,141 @@ out_unlock:
  * frozen works are transferred to their respective pool worklists.
  *
  * CONTEXT:
- * Grabs and releases workqueue_lock and pool->lock's.
+ * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's.
  */
 void thaw_workqueues(void)
 {
-	unsigned int cpu;
+	struct workqueue_struct *wq;
+	struct pool_workqueue *pwq;
+	struct worker_pool *pool;
+	int pi;
 
-	spin_lock(&workqueue_lock);
+	mutex_lock(&wq_pool_mutex);
 
 	if (!workqueue_freezing)
 		goto out_unlock;
 
-	for_each_wq_cpu(cpu) {
-		struct worker_pool *pool;
-		struct workqueue_struct *wq;
+	/* clear FREEZING */
+	for_each_pool(pool, pi) {
+		spin_lock_irq(&pool->lock);
+		WARN_ON_ONCE(!(pool->flags & POOL_FREEZING));
+		pool->flags &= ~POOL_FREEZING;
+		spin_unlock_irq(&pool->lock);
+	}
 
-		for_each_std_worker_pool(pool, cpu) {
-			spin_lock_irq(&pool->lock);
+	/* restore max_active and repopulate worklist */
+	list_for_each_entry(wq, &workqueues, list) {
+		mutex_lock(&wq->mutex);
+		for_each_pwq(pwq, wq)
+			pwq_adjust_max_active(pwq);
+		mutex_unlock(&wq->mutex);
+	}
+
+	workqueue_freezing = false;
+out_unlock:
+	mutex_unlock(&wq_pool_mutex);
+}
+#endif /* CONFIG_FREEZER */
 
-			WARN_ON_ONCE(!(pool->flags & POOL_FREEZING));
-			pool->flags &= ~POOL_FREEZING;
+static void __init wq_numa_init(void)
+{
+	cpumask_var_t *tbl;
+	int node, cpu;
 
-			list_for_each_entry(wq, &workqueues, list) {
-				struct pool_workqueue *pwq = get_pwq(cpu, wq);
+	/* determine NUMA pwq table len - highest node id + 1 */
+	for_each_node(node)
+		wq_numa_tbl_len = max(wq_numa_tbl_len, node + 1);
 
-				if (!pwq || pwq->pool != pool ||
-				    !(wq->flags & WQ_FREEZABLE))
-					continue;
+	if (num_possible_nodes() <= 1)
+		return;
 
-				/* restore max_active and repopulate worklist */
-				pwq_set_max_active(pwq, wq->saved_max_active);
-			}
+	if (wq_disable_numa) {
+		pr_info("workqueue: NUMA affinity support disabled\n");
+		return;
+	}
 
-			wake_up_worker(pool);
+	wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL);
+	BUG_ON(!wq_update_unbound_numa_attrs_buf);
 
-			spin_unlock_irq(&pool->lock);
+	/*
+	 * We want masks of possible CPUs of each node which isn't readily
+	 * available.  Build one from cpu_to_node() which should have been
+	 * fully initialized by now.
+	 */
+	tbl = kzalloc(wq_numa_tbl_len * sizeof(tbl[0]), GFP_KERNEL);
+	BUG_ON(!tbl);
+
+	for_each_node(node)
+		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node));
+
+	for_each_possible_cpu(cpu) {
+		node = cpu_to_node(cpu);
+		if (WARN_ON(node == NUMA_NO_NODE)) {
+			pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu);
+			/* happens iff arch is bonkers, let's just proceed */
+			return;
 		}
+		cpumask_set_cpu(cpu, tbl[node]);
 	}
 
-	workqueue_freezing = false;
-out_unlock:
-	spin_unlock(&workqueue_lock);
+	wq_numa_possible_cpumask = tbl;
+	wq_numa_enabled = true;
 }
-#endif /* CONFIG_FREEZER */
 
 static int __init init_workqueues(void)
 {
-	unsigned int cpu;
+	int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
+	int i, cpu;
 
 	/* make sure we have enough bits for OFFQ pool ID */
 	BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) <
 		     WORK_CPU_END * NR_STD_WORKER_POOLS);
 
+	WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
+
+	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
+
 	cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP);
 	hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN);
 
+	wq_numa_init();
+
 	/* initialize CPU pools */
-	for_each_wq_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		struct worker_pool *pool;
 
-		for_each_std_worker_pool(pool, cpu) {
-			spin_lock_init(&pool->lock);
+		i = 0;
+		for_each_cpu_worker_pool(pool, cpu) {
+			BUG_ON(init_worker_pool(pool));
 			pool->cpu = cpu;
-			pool->flags |= POOL_DISASSOCIATED;
-			INIT_LIST_HEAD(&pool->worklist);
-			INIT_LIST_HEAD(&pool->idle_list);
-			hash_init(pool->busy_hash);
-
-			init_timer_deferrable(&pool->idle_timer);
-			pool->idle_timer.function = idle_worker_timeout;
-			pool->idle_timer.data = (unsigned long)pool;
-
-			setup_timer(&pool->mayday_timer, pool_mayday_timeout,
-				    (unsigned long)pool);
-
-			mutex_init(&pool->assoc_mutex);
-			ida_init(&pool->worker_ida);
+			cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
+			pool->attrs->nice = std_nice[i++];
+			pool->node = cpu_to_node(cpu);
 
 			/* alloc pool ID */
+			mutex_lock(&wq_pool_mutex);
 			BUG_ON(worker_pool_assign_id(pool));
+			mutex_unlock(&wq_pool_mutex);
 		}
 	}
 
 	/* create the initial worker */
-	for_each_online_wq_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct worker_pool *pool;
 
-		for_each_std_worker_pool(pool, cpu) {
-			struct worker *worker;
+		for_each_cpu_worker_pool(pool, cpu) {
+			pool->flags &= ~POOL_DISASSOCIATED;
+			BUG_ON(create_and_start_worker(pool) < 0);
+		}
+	}
 
-			if (cpu != WORK_CPU_UNBOUND)
-				pool->flags &= ~POOL_DISASSOCIATED;
+	/* create default unbound wq attrs */
+	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
+		struct workqueue_attrs *attrs;
 
-			worker = create_worker(pool);
-			BUG_ON(!worker);
-			spin_lock_irq(&pool->lock);
-			start_worker(worker);
-			spin_unlock_irq(&pool->lock);
-		}
+		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+		attrs->nice = std_nice[i];
+		unbound_std_wq_attrs[i] = attrs;
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 07650264ec15..84ab6e1dc6fb 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -32,14 +32,12 @@ struct worker {
 	struct list_head	scheduled;	/* L: scheduled works */
 	struct task_struct	*task;		/* I: worker task */
 	struct worker_pool	*pool;		/* I: the associated pool */
+						/* L: for rescuers */
 	/* 64 bytes boundary on 64bit, 32 on 32bit */
 	unsigned long		last_active;	/* L: last active timestamp */
 	unsigned int		flags;		/* X: flags */
 	int			id;		/* I: worker id */
 
-	/* for rebinding worker to CPU */
-	struct work_struct	rebind_work;	/* L: for busy worker */
-
 	/* used only by rescuers to point to the target workqueue */
 	struct workqueue_struct	*rescue_wq;	/* I: the workqueue to rescue */
 };
@@ -58,8 +56,7 @@ static inline struct worker *current_wq_worker(void)
  * Scheduler hooks for concurrency managed workqueue.  Only to be used from
  * sched.c and workqueue.c.
  */
-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task,
-				       unsigned int cpu);
+void wq_worker_waking_up(struct task_struct *task, int cpu);
+struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */